xiaomi-sm8450/android_kernel_xiaomi_sm8450
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge branch 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Browse Source 
Pull RCU updates from Ingo Molnar:
 "The main changes in this cycle were:

   - changes related to No-CBs CPUs and NO_HZ_FULL

   - RCU-tasks implementation

   - torture-test updates

   - miscellaneous fixes

   - locktorture updates

   - RCU documentation updates"

* 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (81 commits)
  workqueue: Use cond_resched_rcu_qs macro
  workqueue: Add quiescent state between work items
  locktorture: Cleanup header usage
  locktorture: Cannot hold read and write lock
  locktorture: Fix __acquire annotation for spinlock irq
  locktorture: Support rwlocks
  rcu: Eliminate deadlock between CPU hotplug and expedited grace periods
  locktorture: Document boot/module parameters
  rcutorture: Rename rcutorture_runnable parameter
  locktorture: Add test scenario for rwsem_lock
  locktorture: Add test scenario for mutex_lock
  locktorture: Make torture scripting account for new _runnable name
  locktorture: Introduce torture context
  locktorture: Support rwsems
  locktorture: Add infrastructure for torturing read locks
  torture: Address race in module cleanup
  locktorture: Make statistics generic
  locktorture: Teach about lock debugging
  locktorture: Support mutexes
  locktorture: Add documentation
  ...
This commit is contained in:
Linus Torvalds
2014-10-13 15:44:12 +02:00
parent 5ff0b9e1a1 fd19bda491
commit d6dd50e07c
63 changed files with 1935 additions and 546 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
kernel/cpu.c
View File

@@ -79,6 +79,8 @@ static struct {
/* Lockdep annotations for get/put_online_cpus() and cpu_hotplug_begin/end() */
#define cpuhp_lock_acquire_read() lock_map_acquire_read(&cpu_hotplug.dep_map)
#define cpuhp_lock_acquire_tryread() \
lock_map_acquire_tryread(&cpu_hotplug.dep_map)
#define cpuhp_lock_acquire() lock_map_acquire(&cpu_hotplug.dep_map)
#define cpuhp_lock_release() lock_map_release(&cpu_hotplug.dep_map)
@@ -91,10 +93,22 @@ void get_online_cpus(void)
mutex_lock(&cpu_hotplug.lock);
cpu_hotplug.refcount++;
mutex_unlock(&cpu_hotplug.lock);
}
EXPORT_SYMBOL_GPL(get_online_cpus);
bool try_get_online_cpus(void)
{
if (cpu_hotplug.active_writer == current)
return true;
if (!mutex_trylock(&cpu_hotplug.lock))
return false;
cpuhp_lock_acquire_tryread();
cpu_hotplug.refcount++;
mutex_unlock(&cpu_hotplug.lock);
return true;
}
EXPORT_SYMBOL_GPL(try_get_online_cpus);
void put_online_cpus(void)
{
if (cpu_hotplug.active_writer == current)

3
kernel/exit.c
View File

@@ -667,6 +667,7 @@ void do_exit(long code)
{
struct task_struct *tsk = current;
int group_dead;
TASKS_RCU(int tasks_rcu_i);
profile_task_exit(tsk);
@@ -775,6 +776,7 @@ void do_exit(long code)
*/
flush_ptrace_hw_breakpoint(tsk);
TASKS_RCU(tasks_rcu_i = __srcu_read_lock(&tasks_rcu_exit_srcu));
exit_notify(tsk, group_dead);
proc_exit_connector(tsk);
#ifdef CONFIG_NUMA
@@ -814,6 +816,7 @@ void do_exit(long code)
if (tsk->nr_dirtied)
__this_cpu_add(dirty_throttle_leaks, tsk->nr_dirtied);
exit_rcu();
TASKS_RCU(__srcu_read_unlock(&tasks_rcu_exit_srcu, tasks_rcu_i));
/*
* The setting of TASK_RUNNING by try_to_wake_up() may be delayed

529
kernel/locking/locktorture.c
View File

@@ -20,30 +20,20 @@
* Author: Paul E. McKenney <paulmck@us.ibm.com>
* Based on kernel/rcu/torture.c.
*/
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/kthread.h>
#include <linux/err.h>
#include <linux/spinlock.h>
#include <linux/rwlock.h>
#include <linux/mutex.h>
#include <linux/rwsem.h>
#include <linux/smp.h>
#include <linux/interrupt.h>
#include <linux/sched.h>
#include <linux/atomic.h>
#include <linux/bitops.h>
#include <linux/completion.h>
#include <linux/moduleparam.h>
#include <linux/percpu.h>
#include <linux/notifier.h>
#include <linux/reboot.h>
#include <linux/freezer.h>
#include <linux/cpu.h>
#include <linux/delay.h>
#include <linux/stat.h>
#include <linux/slab.h>
#include <linux/trace_clock.h>
#include <asm/byteorder.h>
#include <linux/torture.h>
MODULE_LICENSE("GPL");
@@ -51,6 +41,8 @@ MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com>");
torture_param(int, nwriters_stress, -1,
"Number of write-locking stress-test threads");
torture_param(int, nreaders_stress, -1,
"Number of read-locking stress-test threads");
torture_param(int, onoff_holdoff, 0, "Time after boot before CPU hotplugs (s)");
torture_param(int, onoff_interval, 0,
"Time between CPU hotplugs (s), 0=disable");
@@ -66,30 +58,28 @@ torture_param(bool, verbose, true,
static char *torture_type = "spin_lock";
module_param(torture_type, charp, 0444);
MODULE_PARM_DESC(torture_type,
"Type of lock to torture (spin_lock, spin_lock_irq, ...)");
static atomic_t n_lock_torture_errors;
"Type of lock to torture (spin_lock, spin_lock_irq, mutex_lock, ...)");
static struct task_struct *stats_task;
static struct task_struct **writer_tasks;
static struct task_struct **reader_tasks;
static int nrealwriters_stress;
static bool lock_is_write_held;
static bool lock_is_read_held;
struct lock_writer_stress_stats {
long n_write_lock_fail;
long n_write_lock_acquired;
struct lock_stress_stats {
long n_lock_fail;
long n_lock_acquired;
};
static struct lock_writer_stress_stats *lwsa;
#if defined(MODULE)
#define LOCKTORTURE_RUNNABLE_INIT 1
#else
#define LOCKTORTURE_RUNNABLE_INIT 0
#endif
int locktorture_runnable = LOCKTORTURE_RUNNABLE_INIT;
module_param(locktorture_runnable, int, 0444);
MODULE_PARM_DESC(locktorture_runnable, "Start locktorture at module init");
int torture_runnable = LOCKTORTURE_RUNNABLE_INIT;
module_param(torture_runnable, int, 0444);
MODULE_PARM_DESC(torture_runnable, "Start locktorture at module init");
/* Forward reference. */
static void lock_torture_cleanup(void);
@@ -102,12 +92,25 @@ struct lock_torture_ops {
int (*writelock)(void);
void (*write_delay)(struct torture_random_state *trsp);
void (*writeunlock)(void);
int (*readlock)(void);
void (*read_delay)(struct torture_random_state *trsp);
void (*readunlock)(void);
unsigned long flags;
const char *name;
};
static struct lock_torture_ops *cur_ops;
struct lock_torture_cxt {
int nrealwriters_stress;
int nrealreaders_stress;
bool debug_lock;
atomic_t n_lock_torture_errors;
struct lock_torture_ops *cur_ops;
struct lock_stress_stats *lwsa; /* writer statistics */
struct lock_stress_stats *lrsa; /* reader statistics */
};
static struct lock_torture_cxt cxt = { 0, 0, false,
ATOMIC_INIT(0),
NULL, NULL};
/*
* Definitions for lock torture testing.
*/
@@ -123,10 +126,10 @@ static void torture_lock_busted_write_delay(struct torture_random_state *trsp)
/* We want a long delay occasionally to force massive contention. */
if (!(torture_random(trsp) %
(nrealwriters_stress * 2000 * longdelay_us)))
(cxt.nrealwriters_stress * 2000 * longdelay_us)))
mdelay(longdelay_us);
#ifdef CONFIG_PREEMPT
if (!(torture_random(trsp) % (nrealwriters_stress * 20000)))
if (!(torture_random(trsp) % (cxt.nrealwriters_stress * 20000)))
preempt_schedule(); /* Allow test to be preempted. */
#endif
}
@@ -140,6 +143,9 @@ static struct lock_torture_ops lock_busted_ops = {
.writelock = torture_lock_busted_write_lock,
.write_delay = torture_lock_busted_write_delay,
.writeunlock = torture_lock_busted_write_unlock,
.readlock = NULL,
.read_delay = NULL,
.readunlock = NULL,
.name = "lock_busted"
};
@@ -160,13 +166,13 @@ static void torture_spin_lock_write_delay(struct torture_random_state *trsp)
* we want a long delay occasionally to force massive contention.
*/
if (!(torture_random(trsp) %
(nrealwriters_stress * 2000 * longdelay_us)))
(cxt.nrealwriters_stress * 2000 * longdelay_us)))
mdelay(longdelay_us);
if (!(torture_random(trsp) %
(nrealwriters_stress * 2 * shortdelay_us)))
(cxt.nrealwriters_stress * 2 * shortdelay_us)))
udelay(shortdelay_us);
#ifdef CONFIG_PREEMPT
if (!(torture_random(trsp) % (nrealwriters_stress * 20000)))
if (!(torture_random(trsp) % (cxt.nrealwriters_stress * 20000)))
preempt_schedule(); /* Allow test to be preempted. */
#endif
}
@@ -180,39 +186,253 @@ static struct lock_torture_ops spin_lock_ops = {
.writelock = torture_spin_lock_write_lock,
.write_delay = torture_spin_lock_write_delay,
.writeunlock = torture_spin_lock_write_unlock,
.readlock = NULL,
.read_delay = NULL,
.readunlock = NULL,
.name = "spin_lock"
};
static int torture_spin_lock_write_lock_irq(void)
__acquires(torture_spinlock_irq)
__acquires(torture_spinlock)
{
unsigned long flags;
spin_lock_irqsave(&torture_spinlock, flags);
cur_ops->flags = flags;
cxt.cur_ops->flags = flags;
return 0;
}
static void torture_lock_spin_write_unlock_irq(void)
__releases(torture_spinlock)
{
spin_unlock_irqrestore(&torture_spinlock, cur_ops->flags);
spin_unlock_irqrestore(&torture_spinlock, cxt.cur_ops->flags);
}
static struct lock_torture_ops spin_lock_irq_ops = {
.writelock = torture_spin_lock_write_lock_irq,
.write_delay = torture_spin_lock_write_delay,
.writeunlock = torture_lock_spin_write_unlock_irq,
.readlock = NULL,
.read_delay = NULL,
.readunlock = NULL,
.name = "spin_lock_irq"
};
static DEFINE_RWLOCK(torture_rwlock);
static int torture_rwlock_write_lock(void) __acquires(torture_rwlock)
{
write_lock(&torture_rwlock);
return 0;
}
static void torture_rwlock_write_delay(struct torture_random_state *trsp)
{
const unsigned long shortdelay_us = 2;
const unsigned long longdelay_ms = 100;
/* We want a short delay mostly to emulate likely code, and
* we want a long delay occasionally to force massive contention.
*/
if (!(torture_random(trsp) %
(cxt.nrealwriters_stress * 2000 * longdelay_ms)))
mdelay(longdelay_ms);
else
udelay(shortdelay_us);
}
static void torture_rwlock_write_unlock(void) __releases(torture_rwlock)
{
write_unlock(&torture_rwlock);
}
static int torture_rwlock_read_lock(void) __acquires(torture_rwlock)
{
read_lock(&torture_rwlock);
return 0;
}
static void torture_rwlock_read_delay(struct torture_random_state *trsp)
{
const unsigned long shortdelay_us = 10;
const unsigned long longdelay_ms = 100;
/* We want a short delay mostly to emulate likely code, and
* we want a long delay occasionally to force massive contention.
*/
if (!(torture_random(trsp) %
(cxt.nrealreaders_stress * 2000 * longdelay_ms)))
mdelay(longdelay_ms);
else
udelay(shortdelay_us);
}
static void torture_rwlock_read_unlock(void) __releases(torture_rwlock)
{
read_unlock(&torture_rwlock);
}
static struct lock_torture_ops rw_lock_ops = {
.writelock = torture_rwlock_write_lock,
.write_delay = torture_rwlock_write_delay,
.writeunlock = torture_rwlock_write_unlock,
.readlock = torture_rwlock_read_lock,
.read_delay = torture_rwlock_read_delay,
.readunlock = torture_rwlock_read_unlock,
.name = "rw_lock"
};
static int torture_rwlock_write_lock_irq(void) __acquires(torture_rwlock)
{
unsigned long flags;
write_lock_irqsave(&torture_rwlock, flags);
cxt.cur_ops->flags = flags;
return 0;
}
static void torture_rwlock_write_unlock_irq(void)
__releases(torture_rwlock)
{
write_unlock_irqrestore(&torture_rwlock, cxt.cur_ops->flags);
}
static int torture_rwlock_read_lock_irq(void) __acquires(torture_rwlock)
{
unsigned long flags;
read_lock_irqsave(&torture_rwlock, flags);
cxt.cur_ops->flags = flags;
return 0;
}
static void torture_rwlock_read_unlock_irq(void)
__releases(torture_rwlock)
{
write_unlock_irqrestore(&torture_rwlock, cxt.cur_ops->flags);
}
static struct lock_torture_ops rw_lock_irq_ops = {
.writelock = torture_rwlock_write_lock_irq,
.write_delay = torture_rwlock_write_delay,
.writeunlock = torture_rwlock_write_unlock_irq,
.readlock = torture_rwlock_read_lock_irq,
.read_delay = torture_rwlock_read_delay,
.readunlock = torture_rwlock_read_unlock_irq,
.name = "rw_lock_irq"
};
static DEFINE_MUTEX(torture_mutex);
static int torture_mutex_lock(void) __acquires(torture_mutex)
{
mutex_lock(&torture_mutex);
return 0;
}
static void torture_mutex_delay(struct torture_random_state *trsp)
{
const unsigned long longdelay_ms = 100;
/* We want a long delay occasionally to force massive contention. */
if (!(torture_random(trsp) %
(cxt.nrealwriters_stress * 2000 * longdelay_ms)))
mdelay(longdelay_ms * 5);
else
mdelay(longdelay_ms / 5);
#ifdef CONFIG_PREEMPT
if (!(torture_random(trsp) % (cxt.nrealwriters_stress * 20000)))
preempt_schedule(); /* Allow test to be preempted. */
#endif
}
static void torture_mutex_unlock(void) __releases(torture_mutex)
{
mutex_unlock(&torture_mutex);
}
static struct lock_torture_ops mutex_lock_ops = {
.writelock = torture_mutex_lock,
.write_delay = torture_mutex_delay,
.writeunlock = torture_mutex_unlock,
.readlock = NULL,
.read_delay = NULL,
.readunlock = NULL,
.name = "mutex_lock"
};
static DECLARE_RWSEM(torture_rwsem);
static int torture_rwsem_down_write(void) __acquires(torture_rwsem)
{
down_write(&torture_rwsem);
return 0;
}
static void torture_rwsem_write_delay(struct torture_random_state *trsp)
{
const unsigned long longdelay_ms = 100;
/* We want a long delay occasionally to force massive contention. */
if (!(torture_random(trsp) %
(cxt.nrealwriters_stress * 2000 * longdelay_ms)))
mdelay(longdelay_ms * 10);
else
mdelay(longdelay_ms / 10);
#ifdef CONFIG_PREEMPT
if (!(torture_random(trsp) % (cxt.nrealwriters_stress * 20000)))
preempt_schedule(); /* Allow test to be preempted. */
#endif
}
static void torture_rwsem_up_write(void) __releases(torture_rwsem)
{
up_write(&torture_rwsem);
}
static int torture_rwsem_down_read(void) __acquires(torture_rwsem)
{
down_read(&torture_rwsem);
return 0;
}
static void torture_rwsem_read_delay(struct torture_random_state *trsp)
{
const unsigned long longdelay_ms = 100;
/* We want a long delay occasionally to force massive contention. */
if (!(torture_random(trsp) %
(cxt.nrealwriters_stress * 2000 * longdelay_ms)))
mdelay(longdelay_ms * 2);
else
mdelay(longdelay_ms / 2);
#ifdef CONFIG_PREEMPT
if (!(torture_random(trsp) % (cxt.nrealreaders_stress * 20000)))
preempt_schedule(); /* Allow test to be preempted. */
#endif
}
static void torture_rwsem_up_read(void) __releases(torture_rwsem)
{
up_read(&torture_rwsem);
}
static struct lock_torture_ops rwsem_lock_ops = {
.writelock = torture_rwsem_down_write,
.write_delay = torture_rwsem_write_delay,
.writeunlock = torture_rwsem_up_write,
.readlock = torture_rwsem_down_read,
.read_delay = torture_rwsem_read_delay,
.readunlock = torture_rwsem_up_read,
.name = "rwsem_lock"
};
/*
* Lock torture writer kthread. Repeatedly acquires and releases
* the lock, checking for duplicate acquisitions.
*/
static int lock_torture_writer(void *arg)
{
struct lock_writer_stress_stats *lwsp = arg;
struct lock_stress_stats *lwsp = arg;
static DEFINE_TORTURE_RANDOM(rand);
VERBOSE_TOROUT_STRING("lock_torture_writer task started");
@@ -221,47 +441,86 @@ static int lock_torture_writer(void *arg)
do {
if ((torture_random(&rand) & 0xfffff) == 0)
schedule_timeout_uninterruptible(1);
cur_ops->writelock();
cxt.cur_ops->writelock();
if (WARN_ON_ONCE(lock_is_write_held))
lwsp->n_write_lock_fail++;
lwsp->n_lock_fail++;
lock_is_write_held = 1;
lwsp->n_write_lock_acquired++;
cur_ops->write_delay(&rand);
if (WARN_ON_ONCE(lock_is_read_held))
lwsp->n_lock_fail++; /* rare, but... */
lwsp->n_lock_acquired++;
cxt.cur_ops->write_delay(&rand);
lock_is_write_held = 0;
cur_ops->writeunlock();
cxt.cur_ops->writeunlock();
stutter_wait("lock_torture_writer");
} while (!torture_must_stop());
torture_kthread_stopping("lock_torture_writer");
return 0;
}
/*
* Lock torture reader kthread. Repeatedly acquires and releases
* the reader lock.
*/
static int lock_torture_reader(void *arg)
{
struct lock_stress_stats *lrsp = arg;
static DEFINE_TORTURE_RANDOM(rand);
VERBOSE_TOROUT_STRING("lock_torture_reader task started");
set_user_nice(current, MAX_NICE);
do {
if ((torture_random(&rand) & 0xfffff) == 0)
schedule_timeout_uninterruptible(1);
cxt.cur_ops->readlock();
lock_is_read_held = 1;
if (WARN_ON_ONCE(lock_is_write_held))
lrsp->n_lock_fail++; /* rare, but... */
lrsp->n_lock_acquired++;
cxt.cur_ops->read_delay(&rand);
lock_is_read_held = 0;
cxt.cur_ops->readunlock();
stutter_wait("lock_torture_reader");
} while (!torture_must_stop());
torture_kthread_stopping("lock_torture_reader");
return 0;
}
/*
* Create an lock-torture-statistics message in the specified buffer.
*/
static void lock_torture_printk(char *page)
static void __torture_print_stats(char *page,
struct lock_stress_stats *statp, bool write)
{
bool fail = 0;
int i;
int i, n_stress;
long max = 0;
long min = lwsa[0].n_write_lock_acquired;
long min = statp[0].n_lock_acquired;
long long sum = 0;
for (i = 0; i < nrealwriters_stress; i++) {
if (lwsa[i].n_write_lock_fail)
n_stress = write ? cxt.nrealwriters_stress : cxt.nrealreaders_stress;
for (i = 0; i < n_stress; i++) {
if (statp[i].n_lock_fail)
fail = true;
sum += lwsa[i].n_write_lock_acquired;
if (max < lwsa[i].n_write_lock_fail)
max = lwsa[i].n_write_lock_fail;
if (min > lwsa[i].n_write_lock_fail)
min = lwsa[i].n_write_lock_fail;
sum += statp[i].n_lock_acquired;
if (max < statp[i].n_lock_fail)
max = statp[i].n_lock_fail;
if (min > statp[i].n_lock_fail)
min = statp[i].n_lock_fail;
}
page += sprintf(page, "%s%s ", torture_type, TORTURE_FLAG);
page += sprintf(page,
"Writes: Total: %lld Max/Min: %ld/%ld %s Fail: %d %s\n",
"%s: Total: %lld Max/Min: %ld/%ld %s Fail: %d %s\n",
write ? "Writes" : "Reads ",
sum, max, min, max / 2 > min ? "???" : "",
fail, fail ? "!!!" : "");
if (fail)
atomic_inc(&n_lock_torture_errors);
atomic_inc(&cxt.n_lock_torture_errors);
}
/*
@@ -274,18 +533,35 @@ static void lock_torture_printk(char *page)
*/
static void lock_torture_stats_print(void)
{
int size = nrealwriters_stress * 200 + 8192;
int size = cxt.nrealwriters_stress * 200 + 8192;
char *buf;
if (cxt.cur_ops->readlock)
size += cxt.nrealreaders_stress * 200 + 8192;
buf = kmalloc(size, GFP_KERNEL);
if (!buf) {
pr_err("lock_torture_stats_print: Out of memory, need: %d",
size);
return;
}
lock_torture_printk(buf);
__torture_print_stats(buf, cxt.lwsa, true);
pr_alert("%s", buf);
kfree(buf);
if (cxt.cur_ops->readlock) {
buf = kmalloc(size, GFP_KERNEL);
if (!buf) {
pr_err("lock_torture_stats_print: Out of memory, need: %d",
size);
return;
}
__torture_print_stats(buf, cxt.lrsa, false);
pr_alert("%s", buf);
kfree(buf);
}
}
/*
@@ -312,9 +588,10 @@ lock_torture_print_module_parms(struct lock_torture_ops *cur_ops,
const char *tag)
{
pr_alert("%s" TORTURE_FLAG
"--- %s: nwriters_stress=%d stat_interval=%d verbose=%d shuffle_interval=%d stutter=%d shutdown_secs=%d onoff_interval=%d onoff_holdoff=%d\n",
torture_type, tag, nrealwriters_stress, stat_interval, verbose,
shuffle_interval, stutter, shutdown_secs,
"--- %s%s: nwriters_stress=%d nreaders_stress=%d stat_interval=%d verbose=%d shuffle_interval=%d stutter=%d shutdown_secs=%d onoff_interval=%d onoff_holdoff=%d\n",
torture_type, tag, cxt.debug_lock ? " [debug]": "",
cxt.nrealwriters_stress, cxt.nrealreaders_stress, stat_interval,
verbose, shuffle_interval, stutter, shutdown_secs,
onoff_interval, onoff_holdoff);
}
@@ -322,46 +599,59 @@ static void lock_torture_cleanup(void)
{
int i;
if (torture_cleanup())
if (torture_cleanup_begin())
return;
if (writer_tasks) {
for (i = 0; i < nrealwriters_stress; i++)
for (i = 0; i < cxt.nrealwriters_stress; i++)
torture_stop_kthread(lock_torture_writer,
writer_tasks[i]);
kfree(writer_tasks);
writer_tasks = NULL;
}
if (reader_tasks) {
for (i = 0; i < cxt.nrealreaders_stress; i++)
torture_stop_kthread(lock_torture_reader,
reader_tasks[i]);
kfree(reader_tasks);
reader_tasks = NULL;
}
torture_stop_kthread(lock_torture_stats, stats_task);
lock_torture_stats_print(); /* -After- the stats thread is stopped! */
if (atomic_read(&n_lock_torture_errors))
lock_torture_print_module_parms(cur_ops,
if (atomic_read(&cxt.n_lock_torture_errors))
lock_torture_print_module_parms(cxt.cur_ops,
"End of test: FAILURE");
else if (torture_onoff_failures())
lock_torture_print_module_parms(cur_ops,
lock_torture_print_module_parms(cxt.cur_ops,
"End of test: LOCK_HOTPLUG");
else
lock_torture_print_module_parms(cur_ops,
lock_torture_print_module_parms(cxt.cur_ops,
"End of test: SUCCESS");
torture_cleanup_end();
}
static int __init lock_torture_init(void)
{
int i;
int i, j;
int firsterr = 0;
static struct lock_torture_ops *torture_ops[] = {
&lock_busted_ops, &spin_lock_ops, &spin_lock_irq_ops,
&lock_busted_ops,
&spin_lock_ops, &spin_lock_irq_ops,
&rw_lock_ops, &rw_lock_irq_ops,
&mutex_lock_ops,
&rwsem_lock_ops,
};
if (!torture_init_begin(torture_type, verbose, &locktorture_runnable))
if (!torture_init_begin(torture_type, verbose, &torture_runnable))
return -EBUSY;
/* Process args and tell the world that the torturer is on the job. */
for (i = 0; i < ARRAY_SIZE(torture_ops); i++) {
cur_ops = torture_ops[i];
if (strcmp(torture_type, cur_ops->name) == 0)
cxt.cur_ops = torture_ops[i];
if (strcmp(torture_type, cxt.cur_ops->name) == 0)
break;
}
if (i == ARRAY_SIZE(torture_ops)) {
@@ -374,31 +664,69 @@ static int __init lock_torture_init(void)
torture_init_end();
return -EINVAL;
}
if (cur_ops->init)
cur_ops->init(); /* no "goto unwind" prior to this point!!! */
if (cxt.cur_ops->init)
cxt.cur_ops->init(); /* no "goto unwind" prior to this point!!! */
if (nwriters_stress >= 0)
nrealwriters_stress = nwriters_stress;
cxt.nrealwriters_stress = nwriters_stress;
else
nrealwriters_stress = 2 * num_online_cpus();
lock_torture_print_module_parms(cur_ops, "Start of test");
cxt.nrealwriters_stress = 2 * num_online_cpus();
#ifdef CONFIG_DEBUG_MUTEXES
if (strncmp(torture_type, "mutex", 5) == 0)
cxt.debug_lock = true;
#endif
#ifdef CONFIG_DEBUG_SPINLOCK
if ((strncmp(torture_type, "spin", 4) == 0) ||
(strncmp(torture_type, "rw_lock", 7) == 0))
cxt.debug_lock = true;
#endif
/* Initialize the statistics so that each run gets its own numbers. */
lock_is_write_held = 0;
lwsa = kmalloc(sizeof(*lwsa) * nrealwriters_stress, GFP_KERNEL);
if (lwsa == NULL) {
VERBOSE_TOROUT_STRING("lwsa: Out of memory");
cxt.lwsa = kmalloc(sizeof(*cxt.lwsa) * cxt.nrealwriters_stress, GFP_KERNEL);
if (cxt.lwsa == NULL) {
VERBOSE_TOROUT_STRING("cxt.lwsa: Out of memory");
firsterr = -ENOMEM;
goto unwind;
}
for (i = 0; i < nrealwriters_stress; i++) {
lwsa[i].n_write_lock_fail = 0;
lwsa[i].n_write_lock_acquired = 0;
for (i = 0; i < cxt.nrealwriters_stress; i++) {
cxt.lwsa[i].n_lock_fail = 0;
cxt.lwsa[i].n_lock_acquired = 0;
}
/* Start up the kthreads. */
if (cxt.cur_ops->readlock) {
if (nreaders_stress >= 0)
cxt.nrealreaders_stress = nreaders_stress;
else {
/*
* By default distribute evenly the number of
* readers and writers. We still run the same number
* of threads as the writer-only locks default.
*/
if (nwriters_stress < 0) /* user doesn't care */
cxt.nrealwriters_stress = num_online_cpus();
cxt.nrealreaders_stress = cxt.nrealwriters_stress;
}
lock_is_read_held = 0;
cxt.lrsa = kmalloc(sizeof(*cxt.lrsa) * cxt.nrealreaders_stress, GFP_KERNEL);
if (cxt.lrsa == NULL) {
VERBOSE_TOROUT_STRING("cxt.lrsa: Out of memory");
firsterr = -ENOMEM;
kfree(cxt.lwsa);
goto unwind;
}
for (i = 0; i < cxt.nrealreaders_stress; i++) {
cxt.lrsa[i].n_lock_fail = 0;
cxt.lrsa[i].n_lock_acquired = 0;
}
}
lock_torture_print_module_parms(cxt.cur_ops, "Start of test");
/* Prepare torture context. */
if (onoff_interval > 0) {
firsterr = torture_onoff_init(onoff_holdoff * HZ,
onoff_interval * HZ);
@@ -422,18 +750,51 @@ static int __init lock_torture_init(void)
goto unwind;
}
writer_tasks = kzalloc(nrealwriters_stress * sizeof(writer_tasks[0]),
writer_tasks = kzalloc(cxt.nrealwriters_stress * sizeof(writer_tasks[0]),
GFP_KERNEL);
if (writer_tasks == NULL) {
VERBOSE_TOROUT_ERRSTRING("writer_tasks: Out of memory");
firsterr = -ENOMEM;
goto unwind;
}
for (i = 0; i < nrealwriters_stress; i++) {
firsterr = torture_create_kthread(lock_torture_writer, &lwsa[i],
if (cxt.cur_ops->readlock) {
reader_tasks = kzalloc(cxt.nrealreaders_stress * sizeof(reader_tasks[0]),
GFP_KERNEL);
if (reader_tasks == NULL) {
VERBOSE_TOROUT_ERRSTRING("reader_tasks: Out of memory");
firsterr = -ENOMEM;
goto unwind;
}
}
/*
* Create the kthreads and start torturing (oh, those poor little locks).
*
* TODO: Note that we interleave writers with readers, giving writers a
* slight advantage, by creating its kthread first. This can be modified
* for very specific needs, or even let the user choose the policy, if
* ever wanted.
*/
for (i = 0, j = 0; i < cxt.nrealwriters_stress ||
j < cxt.nrealreaders_stress; i++, j++) {
if (i >= cxt.nrealwriters_stress)
goto create_reader;
/* Create writer. */
firsterr = torture_create_kthread(lock_torture_writer, &cxt.lwsa[i],
writer_tasks[i]);
if (firsterr)
goto unwind;
create_reader:
if (cxt.cur_ops->readlock == NULL || (j >= cxt.nrealreaders_stress))
continue;
/* Create reader. */
firsterr = torture_create_kthread(lock_torture_reader, &cxt.lrsa[j],
reader_tasks[j]);
if (firsterr)
goto unwind;
}
if (stat_interval > 0) {
firsterr = torture_create_kthread(lock_torture_stats, NULL,

278
kernel/rcu/rcutorture.c
View File

@@ -49,11 +49,19 @@
#include <linux/trace_clock.h>
#include <asm/byteorder.h>
#include <linux/torture.h>
#include <linux/vmalloc.h>
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com> and Josh Triplett <josh@joshtriplett.org>");
torture_param(int, cbflood_inter_holdoff, HZ,
"Holdoff between floods (jiffies)");
torture_param(int, cbflood_intra_holdoff, 1,
"Holdoff between bursts (jiffies)");
torture_param(int, cbflood_n_burst, 3, "# bursts in flood, zero to disable");
torture_param(int, cbflood_n_per_burst, 20000,
"# callbacks per burst in flood");
torture_param(int, fqs_duration, 0,
"Duration of fqs bursts (us), 0 to disable");
torture_param(int, fqs_holdoff, 0, "Holdoff time within fqs bursts (us)");
@@ -96,10 +104,12 @@ module_param(torture_type, charp, 0444);
MODULE_PARM_DESC(torture_type, "Type of RCU to torture (rcu, rcu_bh, ...)");
static int nrealreaders;
static int ncbflooders;
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 **cbflood_task;
static struct task_struct *fqs_task;
static struct task_struct *boost_tasks[NR_CPUS];
static struct task_struct *stall_task;
@@ -138,6 +148,7 @@ static long n_rcu_torture_boosts;
static long n_rcu_torture_timers;
static long n_barrier_attempts;
static long n_barrier_successes;
static atomic_long_t n_cbfloods;
static struct list_head rcu_torture_removed;
static int rcu_torture_writer_state;
@@ -157,9 +168,9 @@ static int rcu_torture_writer_state;
#else
#define RCUTORTURE_RUNNABLE_INIT 0
#endif
int rcutorture_runnable = RCUTORTURE_RUNNABLE_INIT;
module_param(rcutorture_runnable, int, 0444);
MODULE_PARM_DESC(rcutorture_runnable, "Start rcutorture at boot");
static int torture_runnable = RCUTORTURE_RUNNABLE_INIT;
module_param(torture_runnable, int, 0444);
MODULE_PARM_DESC(torture_runnable, "Start rcutorture at boot");
#if defined(CONFIG_RCU_BOOST) && !defined(CONFIG_HOTPLUG_CPU)
#define rcu_can_boost() 1
@@ -182,7 +193,7 @@ static u64 notrace rcu_trace_clock_local(void)
#endif /* #else #ifdef CONFIG_RCU_TRACE */
static unsigned long boost_starttime; /* jiffies of next boost test start. */
DEFINE_MUTEX(boost_mutex); /* protect setting boost_starttime */
static DEFINE_MUTEX(boost_mutex); /* protect setting boost_starttime */
/* and boost task create/destroy. */
static atomic_t barrier_cbs_count; /* Barrier callbacks registered. */
static bool barrier_phase; /* Test phase. */
@@ -242,7 +253,7 @@ struct rcu_torture_ops {
void (*call)(struct rcu_head *head, void (*func)(struct rcu_head *rcu));
void (*cb_barrier)(void);
void (*fqs)(void);
void (*stats)(char *page);
void (*stats)(void);
int irq_capable;
int can_boost;
const char *name;
@@ -525,21 +536,21 @@ static void srcu_torture_barrier(void)
srcu_barrier(&srcu_ctl);
}
static void srcu_torture_stats(char *page)
static void srcu_torture_stats(void)
{
int cpu;
int idx = srcu_ctl.completed & 0x1;
page += sprintf(page, "%s%s per-CPU(idx=%d):",
torture_type, TORTURE_FLAG, idx);
pr_alert("%s%s per-CPU(idx=%d):",
torture_type, TORTURE_FLAG, idx);
for_each_possible_cpu(cpu) {
long c0, c1;
c0 = (long)per_cpu_ptr(srcu_ctl.per_cpu_ref, cpu)->c[!idx];
c1 = (long)per_cpu_ptr(srcu_ctl.per_cpu_ref, cpu)->c[idx];
page += sprintf(page, " %d(%ld,%ld)", cpu, c0, c1);
pr_cont(" %d(%ld,%ld)", cpu, c0, c1);
}
sprintf(page, "\n");
pr_cont("\n");
}
static void srcu_torture_synchronize_expedited(void)
@@ -601,6 +612,52 @@ static struct rcu_torture_ops sched_ops = {
.name = "sched"
};
#ifdef CONFIG_TASKS_RCU
/*
* Definitions for RCU-tasks torture testing.
*/
static int tasks_torture_read_lock(void)
{
return 0;
}
static void tasks_torture_read_unlock(int idx)
{
}
static void rcu_tasks_torture_deferred_free(struct rcu_torture *p)
{
call_rcu_tasks(&p->rtort_rcu, rcu_torture_cb);
}
static struct rcu_torture_ops tasks_ops = {
.ttype = RCU_TASKS_FLAVOR,
.init = rcu_sync_torture_init,
.readlock = tasks_torture_read_lock,
.read_delay = rcu_read_delay, /* just reuse rcu's version. */
.readunlock = tasks_torture_read_unlock,
.completed = rcu_no_completed,
.deferred_free = rcu_tasks_torture_deferred_free,
.sync = synchronize_rcu_tasks,
.exp_sync = synchronize_rcu_tasks,
.call = call_rcu_tasks,
.cb_barrier = rcu_barrier_tasks,
.fqs = NULL,
.stats = NULL,
.irq_capable = 1,
.name = "tasks"
};
#define RCUTORTURE_TASKS_OPS &tasks_ops,
#else /* #ifdef CONFIG_TASKS_RCU */
#define RCUTORTURE_TASKS_OPS
#endif /* #else #ifdef CONFIG_TASKS_RCU */
/*
* RCU torture priority-boost testing. Runs one real-time thread per
* CPU for moderate bursts, repeatedly registering RCU callbacks and
@@ -667,7 +724,7 @@ static int rcu_torture_boost(void *arg)
}
call_rcu_time = jiffies;
}
cond_resched();
cond_resched_rcu_qs();
stutter_wait("rcu_torture_boost");
if (torture_must_stop())
goto checkwait;
@@ -707,6 +764,58 @@ checkwait: stutter_wait("rcu_torture_boost");
return 0;
}
static void rcu_torture_cbflood_cb(struct rcu_head *rhp)
{
}
/*
* RCU torture callback-flood kthread. Repeatedly induces bursts of calls
* to call_rcu() or analogous, increasing the probability of occurrence
* of callback-overflow corner cases.
*/
static int
rcu_torture_cbflood(void *arg)
{
int err = 1;
int i;
int j;
struct rcu_head *rhp;
if (cbflood_n_per_burst > 0 &&
cbflood_inter_holdoff > 0 &&
cbflood_intra_holdoff > 0 &&
cur_ops->call &&
cur_ops->cb_barrier) {
rhp = vmalloc(sizeof(*rhp) *
cbflood_n_burst * cbflood_n_per_burst);
err = !rhp;
}
if (err) {
VERBOSE_TOROUT_STRING("rcu_torture_cbflood disabled: Bad args or OOM");
while (!torture_must_stop())
schedule_timeout_interruptible(HZ);
return 0;
}
VERBOSE_TOROUT_STRING("rcu_torture_cbflood task started");
do {
schedule_timeout_interruptible(cbflood_inter_holdoff);
atomic_long_inc(&n_cbfloods);
WARN_ON(signal_pending(current));
for (i = 0; i < cbflood_n_burst; i++) {
for (j = 0; j < cbflood_n_per_burst; j++) {
cur_ops->call(&rhp[i * cbflood_n_per_burst + j],
rcu_torture_cbflood_cb);
}
schedule_timeout_interruptible(cbflood_intra_holdoff);
WARN_ON(signal_pending(current));
}
cur_ops->cb_barrier();
stutter_wait("rcu_torture_cbflood");
} while (!torture_must_stop());
torture_kthread_stopping("rcu_torture_cbflood");
return 0;
}
/*
* RCU torture force-quiescent-state kthread. Repeatedly induces
* bursts of calls to force_quiescent_state(), increasing the probability
@@ -1019,7 +1128,7 @@ rcu_torture_reader(void *arg)
__this_cpu_inc(rcu_torture_batch[completed]);
preempt_enable();
cur_ops->readunlock(idx);
cond_resched();
cond_resched_rcu_qs();
stutter_wait("rcu_torture_reader");
} while (!torture_must_stop());
if (irqreader && cur_ops->irq_capable) {
@@ -1031,10 +1140,15 @@ rcu_torture_reader(void *arg)
}
/*
* Create an RCU-torture statistics message in the specified buffer.
* Print torture statistics. Caller must ensure that there is only
* one call to this function at a given time!!! This is normally
* accomplished by relying on the module system to only have one copy
* of the module loaded, and then by giving the rcu_torture_stats
* kthread full control (or the init/cleanup functions when rcu_torture_stats
* thread is not running).
*/
static void
rcu_torture_printk(char *page)
rcu_torture_stats_print(void)
{
int cpu;
int i;
@@ -1052,55 +1166,61 @@ rcu_torture_printk(char *page)
if (pipesummary[i] != 0)
break;
}
page += sprintf(page, "%s%s ", torture_type, TORTURE_FLAG);
page += sprintf(page,
"rtc: %p ver: %lu tfle: %d rta: %d rtaf: %d rtf: %d ",
rcu_torture_current,
rcu_torture_current_version,
list_empty(&rcu_torture_freelist),
atomic_read(&n_rcu_torture_alloc),
atomic_read(&n_rcu_torture_alloc_fail),
atomic_read(&n_rcu_torture_free));
page += sprintf(page, "rtmbe: %d rtbke: %ld rtbre: %ld ",
atomic_read(&n_rcu_torture_mberror),
n_rcu_torture_boost_ktrerror,
n_rcu_torture_boost_rterror);
page += sprintf(page, "rtbf: %ld rtb: %ld nt: %ld ",
n_rcu_torture_boost_failure,
n_rcu_torture_boosts,
n_rcu_torture_timers);
page = torture_onoff_stats(page);
page += sprintf(page, "barrier: %ld/%ld:%ld",
n_barrier_successes,
n_barrier_attempts,
n_rcu_torture_barrier_error);
page += sprintf(page, "\n%s%s ", torture_type, TORTURE_FLAG);
pr_alert("%s%s ", torture_type, TORTURE_FLAG);
pr_cont("rtc: %p ver: %lu tfle: %d rta: %d rtaf: %d rtf: %d ",
rcu_torture_current,
rcu_torture_current_version,
list_empty(&rcu_torture_freelist),
atomic_read(&n_rcu_torture_alloc),
atomic_read(&n_rcu_torture_alloc_fail),
atomic_read(&n_rcu_torture_free));
pr_cont("rtmbe: %d rtbke: %ld rtbre: %ld ",
atomic_read(&n_rcu_torture_mberror),
n_rcu_torture_boost_ktrerror,
n_rcu_torture_boost_rterror);
pr_cont("rtbf: %ld rtb: %ld nt: %ld ",
n_rcu_torture_boost_failure,
n_rcu_torture_boosts,
n_rcu_torture_timers);
torture_onoff_stats();
pr_cont("barrier: %ld/%ld:%ld ",
n_barrier_successes,
n_barrier_attempts,
n_rcu_torture_barrier_error);
pr_cont("cbflood: %ld\n", atomic_long_read(&n_cbfloods));
pr_alert("%s%s ", torture_type, TORTURE_FLAG);
if (atomic_read(&n_rcu_torture_mberror) != 0 ||
n_rcu_torture_barrier_error != 0 ||
n_rcu_torture_boost_ktrerror != 0 ||
n_rcu_torture_boost_rterror != 0 ||
n_rcu_torture_boost_failure != 0 ||
i > 1) {
page += sprintf(page, "!!! ");
pr_cont("%s", "!!! ");
atomic_inc(&n_rcu_torture_error);
WARN_ON_ONCE(1);
}
page += sprintf(page, "Reader Pipe: ");
pr_cont("Reader Pipe: ");
for (i = 0; i < RCU_TORTURE_PIPE_LEN + 1; i++)
page += sprintf(page, " %ld", pipesummary[i]);
page += sprintf(page, "\n%s%s ", torture_type, TORTURE_FLAG);
page += sprintf(page, "Reader Batch: ");
pr_cont(" %ld", pipesummary[i]);
pr_cont("\n");
pr_alert("%s%s ", torture_type, TORTURE_FLAG);
pr_cont("Reader Batch: ");
for (i = 0; i < RCU_TORTURE_PIPE_LEN + 1; i++)
page += sprintf(page, " %ld", batchsummary[i]);
page += sprintf(page, "\n%s%s ", torture_type, TORTURE_FLAG);
page += sprintf(page, "Free-Block Circulation: ");
pr_cont(" %ld", batchsummary[i]);
pr_cont("\n");
pr_alert("%s%s ", torture_type, TORTURE_FLAG);
pr_cont("Free-Block Circulation: ");
for (i = 0; i < RCU_TORTURE_PIPE_LEN + 1; i++) {
page += sprintf(page, " %d",
atomic_read(&rcu_torture_wcount[i]));
pr_cont(" %d", atomic_read(&rcu_torture_wcount[i]));
}
page += sprintf(page, "\n");
pr_cont("\n");
if (cur_ops->stats)
cur_ops->stats(page);
cur_ops->stats();
if (rtcv_snap == rcu_torture_current_version &&
rcu_torture_current != NULL) {
int __maybe_unused flags;
@@ -1109,40 +1229,15 @@ rcu_torture_printk(char *page)
rcutorture_get_gp_data(cur_ops->ttype,
&flags, &gpnum, &completed);
page += sprintf(page,
"??? Writer stall state %d g%lu c%lu f%#x\n",
rcu_torture_writer_state,
gpnum, completed, flags);
pr_alert("??? Writer stall state %d g%lu c%lu f%#x\n",
rcu_torture_writer_state,
gpnum, completed, flags);
show_rcu_gp_kthreads();
rcutorture_trace_dump();
}
rtcv_snap = rcu_torture_current_version;
}
/*
* Print torture statistics. Caller must ensure that there is only
* one call to this function at a given time!!! This is normally
* accomplished by relying on the module system to only have one copy
* of the module loaded, and then by giving the rcu_torture_stats
* kthread full control (or the init/cleanup functions when rcu_torture_stats
* thread is not running).
*/
static void
rcu_torture_stats_print(void)
{
int size = nr_cpu_ids * 200 + 8192;
char *buf;
buf = kmalloc(size, GFP_KERNEL);
if (!buf) {
pr_err("rcu-torture: Out of memory, need: %d", size);
return;
}
rcu_torture_printk(buf);
pr_alert("%s", buf);
kfree(buf);
}
/*
* Periodically prints torture statistics, if periodic statistics printing
* was specified via the stat_interval module parameter.
@@ -1295,7 +1390,8 @@ static int rcu_torture_barrier_cbs(void *arg)
if (atomic_dec_and_test(&barrier_cbs_count))
wake_up(&barrier_wq);
} while (!torture_must_stop());
cur_ops->cb_barrier();
if (cur_ops->cb_barrier != NULL)
cur_ops->cb_barrier();
destroy_rcu_head_on_stack(&rcu);
torture_kthread_stopping("rcu_torture_barrier_cbs");
return 0;
@@ -1418,7 +1514,7 @@ rcu_torture_cleanup(void)
int i;
rcutorture_record_test_transition();
if (torture_cleanup()) {
if (torture_cleanup_begin()) {
if (cur_ops->cb_barrier != NULL)
cur_ops->cb_barrier();
return;
@@ -1447,6 +1543,8 @@ rcu_torture_cleanup(void)
torture_stop_kthread(rcu_torture_stats, stats_task);
torture_stop_kthread(rcu_torture_fqs, fqs_task);
for (i = 0; i < ncbflooders; i++)
torture_stop_kthread(rcu_torture_cbflood, cbflood_task[i]);
if ((test_boost == 1 && cur_ops->can_boost) ||
test_boost == 2) {
unregister_cpu_notifier(&rcutorture_cpu_nb);
@@ -1468,6 +1566,7 @@ rcu_torture_cleanup(void)
"End of test: RCU_HOTPLUG");
else
rcu_torture_print_module_parms(cur_ops, "End of test: SUCCESS");
torture_cleanup_end();
}
#ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD
@@ -1534,9 +1633,10 @@ rcu_torture_init(void)
int firsterr = 0;
static struct rcu_torture_ops *torture_ops[] = {
&rcu_ops, &rcu_bh_ops, &rcu_busted_ops, &srcu_ops, &sched_ops,
RCUTORTURE_TASKS_OPS
};
if (!torture_init_begin(torture_type, verbose, &rcutorture_runnable))
if (!torture_init_begin(torture_type, verbose, &torture_runnable))
return -EBUSY;
/* Process args and tell the world that the torturer is on the job. */
@@ -1693,6 +1793,24 @@ rcu_torture_init(void)
goto unwind;
if (object_debug)
rcu_test_debug_objects();
if (cbflood_n_burst > 0) {
/* Create the cbflood threads */
ncbflooders = (num_online_cpus() + 3) / 4;
cbflood_task = kcalloc(ncbflooders, sizeof(*cbflood_task),
GFP_KERNEL);
if (!cbflood_task) {
VERBOSE_TOROUT_ERRSTRING("out of memory");
firsterr = -ENOMEM;
goto unwind;
}
for (i = 0; i < ncbflooders; i++) {
firsterr = torture_create_kthread(rcu_torture_cbflood,
NULL,
cbflood_task[i]);
if (firsterr)
goto unwind;
}
}
rcutorture_record_test_transition();
torture_init_end();
return 0;

20
kernel/rcu/tiny.c
View File

@@ -51,7 +51,7 @@ static long long rcu_dynticks_nesting = DYNTICK_TASK_EXIT_IDLE;
#include "tiny_plugin.h"
/* Common code for rcu_idle_enter() and rcu_irq_exit(), see kernel/rcutree.c. */
/* Common code for rcu_idle_enter() and rcu_irq_exit(), see kernel/rcu/tree.c. */
static void rcu_idle_enter_common(long long newval)
{
if (newval) {
@@ -62,7 +62,7 @@ static void rcu_idle_enter_common(long long newval)
}
RCU_TRACE(trace_rcu_dyntick(TPS("Start"),
rcu_dynticks_nesting, newval));
if (!is_idle_task(current)) {
if (IS_ENABLED(CONFIG_RCU_TRACE) && !is_idle_task(current)) {
struct task_struct *idle __maybe_unused = idle_task(smp_processor_id());
RCU_TRACE(trace_rcu_dyntick(TPS("Entry error: not idle task"),
@@ -72,7 +72,7 @@ static void rcu_idle_enter_common(long long newval)
current->pid, current->comm,
idle->pid, idle->comm); /* must be idle task! */
}
rcu_sched_qs(0); /* implies rcu_bh_qsctr_inc(0) */
rcu_sched_qs(); /* implies rcu_bh_inc() */
barrier();
rcu_dynticks_nesting = newval;
}
@@ -114,7 +114,7 @@ void rcu_irq_exit(void)
}
EXPORT_SYMBOL_GPL(rcu_irq_exit);
/* Common code for rcu_idle_exit() and rcu_irq_enter(), see kernel/rcutree.c. */
/* Common code for rcu_idle_exit() and rcu_irq_enter(), see kernel/rcu/tree.c. */
static void rcu_idle_exit_common(long long oldval)
{
if (oldval) {
@@ -123,7 +123,7 @@ static void rcu_idle_exit_common(long long oldval)
return;
}
RCU_TRACE(trace_rcu_dyntick(TPS("End"), oldval, rcu_dynticks_nesting));
if (!is_idle_task(current)) {
if (IS_ENABLED(CONFIG_RCU_TRACE) && !is_idle_task(current)) {
struct task_struct *idle __maybe_unused = idle_task(smp_processor_id());
RCU_TRACE(trace_rcu_dyntick(TPS("Exit error: not idle task"),
@@ -217,7 +217,7 @@ static int rcu_qsctr_help(struct rcu_ctrlblk *rcp)
* are at it, given that any rcu quiescent state is also an rcu_bh
* quiescent state. Use "+" instead of "||" to defeat short circuiting.
*/
void rcu_sched_qs(int cpu)
void rcu_sched_qs(void)
{
unsigned long flags;
@@ -231,7 +231,7 @@ void rcu_sched_qs(int cpu)
/*
* Record an rcu_bh quiescent state.
*/
void rcu_bh_qs(int cpu)
void rcu_bh_qs(void)
{
unsigned long flags;
@@ -251,9 +251,11 @@ void rcu_check_callbacks(int cpu, int user)
{
RCU_TRACE(check_cpu_stalls());
if (user || rcu_is_cpu_rrupt_from_idle())
rcu_sched_qs(cpu);
rcu_sched_qs();
else if (!in_softirq())
rcu_bh_qs(cpu);
rcu_bh_qs();
if (user)
rcu_note_voluntary_context_switch(current);
}
/*

115
kernel/rcu/tree.c
View File

@@ -79,9 +79,18 @@ static struct lock_class_key rcu_fqs_class[RCU_NUM_LVLS];
* the tracing userspace tools to be able to decipher the string
* address to the matching string.
*/
#define RCU_STATE_INITIALIZER(sname, sabbr, cr) \
#ifdef CONFIG_TRACING
# define DEFINE_RCU_TPS(sname) \
static char sname##_varname[] = #sname; \
static const char *tp_##sname##_varname __used __tracepoint_string = sname##_varname; \
static const char *tp_##sname##_varname __used __tracepoint_string = sname##_varname;
# define RCU_STATE_NAME(sname) sname##_varname
#else
# define DEFINE_RCU_TPS(sname)
# define RCU_STATE_NAME(sname) __stringify(sname)
#endif
#define RCU_STATE_INITIALIZER(sname, sabbr, cr) \
DEFINE_RCU_TPS(sname) \
struct rcu_state sname##_state = { \
.level = { &sname##_state.node[0] }, \
.call = cr, \
@@ -93,7 +102,7 @@ struct rcu_state sname##_state = { \
.orphan_donetail = &sname##_state.orphan_donelist, \
.barrier_mutex = __MUTEX_INITIALIZER(sname##_state.barrier_mutex), \
.onoff_mutex = __MUTEX_INITIALIZER(sname##_state.onoff_mutex), \
.name = sname##_varname, \
.name = RCU_STATE_NAME(sname), \
.abbr = sabbr, \
}; \
DEFINE_PER_CPU(struct rcu_data, sname##_data)
@@ -188,22 +197,24 @@ static int rcu_gp_in_progress(struct rcu_state *rsp)
* one since the start of the grace period, this just sets a flag.
* The caller must have disabled preemption.
*/
void rcu_sched_qs(int cpu)
void rcu_sched_qs(void)
{
struct rcu_data *rdp = &per_cpu(rcu_sched_data, cpu);
if (rdp->passed_quiesce == 0)
trace_rcu_grace_period(TPS("rcu_sched"), rdp->gpnum, TPS("cpuqs"));
rdp->passed_quiesce = 1;
if (!__this_cpu_read(rcu_sched_data.passed_quiesce)) {
trace_rcu_grace_period(TPS("rcu_sched"),
__this_cpu_read(rcu_sched_data.gpnum),
TPS("cpuqs"));
__this_cpu_write(rcu_sched_data.passed_quiesce, 1);
}
}
void rcu_bh_qs(int cpu)
void rcu_bh_qs(void)
{
struct rcu_data *rdp = &per_cpu(rcu_bh_data, cpu);
if (rdp->passed_quiesce == 0)
trace_rcu_grace_period(TPS("rcu_bh"), rdp->gpnum, TPS("cpuqs"));
rdp->passed_quiesce = 1;
if (!__this_cpu_read(rcu_bh_data.passed_quiesce)) {
trace_rcu_grace_period(TPS("rcu_bh"),
__this_cpu_read(rcu_bh_data.gpnum),
TPS("cpuqs"));
__this_cpu_write(rcu_bh_data.passed_quiesce, 1);
}
}
static DEFINE_PER_CPU(int, rcu_sched_qs_mask);
@@ -278,7 +289,7 @@ static void rcu_momentary_dyntick_idle(void)
void rcu_note_context_switch(int cpu)
{
trace_rcu_utilization(TPS("Start context switch"));
rcu_sched_qs(cpu);
rcu_sched_qs();
rcu_preempt_note_context_switch(cpu);
if (unlikely(raw_cpu_read(rcu_sched_qs_mask)))
rcu_momentary_dyntick_idle();
@@ -526,6 +537,7 @@ static void rcu_eqs_enter_common(struct rcu_dynticks *rdtp, long long oldval,
atomic_inc(&rdtp->dynticks);
smp_mb__after_atomic(); /* Force ordering with next sojourn. */
WARN_ON_ONCE(atomic_read(&rdtp->dynticks) & 0x1);
rcu_dynticks_task_enter();
/*
* It is illegal to enter an extended quiescent state while
@@ -642,6 +654,7 @@ void rcu_irq_exit(void)
static void rcu_eqs_exit_common(struct rcu_dynticks *rdtp, long long oldval,
int user)
{
rcu_dynticks_task_exit();
smp_mb__before_atomic(); /* Force ordering w/previous sojourn. */
atomic_inc(&rdtp->dynticks);
/* CPUs seeing atomic_inc() must see later RCU read-side crit sects */
@@ -819,7 +832,7 @@ bool notrace __rcu_is_watching(void)
*/
bool notrace rcu_is_watching(void)
{
int ret;
bool ret;
preempt_disable();
ret = __rcu_is_watching();
@@ -1647,7 +1660,7 @@ static int rcu_gp_init(struct rcu_state *rsp)
rnp->level, rnp->grplo,
rnp->grphi, rnp->qsmask);
raw_spin_unlock_irq(&rnp->lock);
cond_resched();
cond_resched_rcu_qs();
}
mutex_unlock(&rsp->onoff_mutex);
@@ -1668,7 +1681,7 @@ static int rcu_gp_fqs(struct rcu_state *rsp, int fqs_state_in)
if (fqs_state == RCU_SAVE_DYNTICK) {
/* Collect dyntick-idle snapshots. */
if (is_sysidle_rcu_state(rsp)) {
isidle = 1;
isidle = true;
maxj = jiffies - ULONG_MAX / 4;
}
force_qs_rnp(rsp, dyntick_save_progress_counter,
@@ -1677,14 +1690,15 @@ static int rcu_gp_fqs(struct rcu_state *rsp, int fqs_state_in)
fqs_state = RCU_FORCE_QS;
} else {
/* Handle dyntick-idle and offline CPUs. */
isidle = 0;
isidle = false;
force_qs_rnp(rsp, rcu_implicit_dynticks_qs, &isidle, &maxj);
}
/* Clear flag to prevent immediate re-entry. */
if (ACCESS_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) {
raw_spin_lock_irq(&rnp->lock);
smp_mb__after_unlock_lock();
ACCESS_ONCE(rsp->gp_flags) &= ~RCU_GP_FLAG_FQS;
ACCESS_ONCE(rsp->gp_flags) =
ACCESS_ONCE(rsp->gp_flags) & ~RCU_GP_FLAG_FQS;
raw_spin_unlock_irq(&rnp->lock);
}
return fqs_state;
@@ -1736,7 +1750,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
/* smp_mb() provided by prior unlock-lock pair. */
nocb += rcu_future_gp_cleanup(rsp, rnp);
raw_spin_unlock_irq(&rnp->lock);
cond_resched();
cond_resched_rcu_qs();
}
rnp = rcu_get_root(rsp);
raw_spin_lock_irq(&rnp->lock);
@@ -1785,8 +1799,8 @@ static int __noreturn rcu_gp_kthread(void *arg)
/* Locking provides needed memory barrier. */
if (rcu_gp_init(rsp))
break;
cond_resched();
flush_signals(current);
cond_resched_rcu_qs();
WARN_ON(signal_pending(current));
trace_rcu_grace_period(rsp->name,
ACCESS_ONCE(rsp->gpnum),
TPS("reqwaitsig"));
@@ -1828,11 +1842,11 @@ static int __noreturn rcu_gp_kthread(void *arg)
trace_rcu_grace_period(rsp->name,
ACCESS_ONCE(rsp->gpnum),
TPS("fqsend"));
cond_resched();
cond_resched_rcu_qs();
} else {
/* Deal with stray signal. */
cond_resched();
flush_signals(current);
cond_resched_rcu_qs();
WARN_ON(signal_pending(current));
trace_rcu_grace_period(rsp->name,
ACCESS_ONCE(rsp->gpnum),
TPS("fqswaitsig"));
@@ -1928,7 +1942,7 @@ static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags)
{
WARN_ON_ONCE(!rcu_gp_in_progress(rsp));
raw_spin_unlock_irqrestore(&rcu_get_root(rsp)->lock, flags);
wake_up(&rsp->gp_wq); /* Memory barrier implied by wake_up() path. */
rcu_gp_kthread_wake(rsp);
}
/*
@@ -2210,8 +2224,6 @@ static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp)
/* Adjust any no-longer-needed kthreads. */
rcu_boost_kthread_setaffinity(rnp, -1);
/* Remove the dead CPU from the bitmasks in the rcu_node hierarchy. */
/* Exclude any attempts to start a new grace period. */
mutex_lock(&rsp->onoff_mutex);
raw_spin_lock_irqsave(&rsp->orphan_lock, flags);
@@ -2393,8 +2405,8 @@ void rcu_check_callbacks(int cpu, int user)
* at least not while the corresponding CPU is online.
*/
rcu_sched_qs(cpu);
rcu_bh_qs(cpu);
rcu_sched_qs();
rcu_bh_qs();
} else if (!in_softirq()) {
@@ -2405,11 +2417,13 @@ void rcu_check_callbacks(int cpu, int user)
* critical section, so note it.
*/
rcu_bh_qs(cpu);
rcu_bh_qs();
}
rcu_preempt_check_callbacks(cpu);
if (rcu_pending(cpu))
invoke_rcu_core();
if (user)
rcu_note_voluntary_context_switch(current);
trace_rcu_utilization(TPS("End scheduler-tick"));
}
@@ -2432,7 +2446,7 @@ static void force_qs_rnp(struct rcu_state *rsp,
struct rcu_node *rnp;
rcu_for_each_leaf_node(rsp, rnp) {
cond_resched();
cond_resched_rcu_qs();
mask = 0;
raw_spin_lock_irqsave(&rnp->lock, flags);
smp_mb__after_unlock_lock();
@@ -2449,7 +2463,7 @@ static void force_qs_rnp(struct rcu_state *rsp,
for (; cpu <= rnp->grphi; cpu++, bit <<= 1) {
if ((rnp->qsmask & bit) != 0) {
if ((rnp->qsmaskinit & bit) != 0)
*isidle = 0;
*isidle = false;
if (f(per_cpu_ptr(rsp->rda, cpu), isidle, maxj))
mask |= bit;
}
@@ -2505,9 +2519,10 @@ static void force_quiescent_state(struct rcu_state *rsp)
raw_spin_unlock_irqrestore(&rnp_old->lock, flags);
return; /* Someone beat us to it. */
}
ACCESS_ONCE(rsp->gp_flags) |= RCU_GP_FLAG_FQS;
ACCESS_ONCE(rsp->gp_flags) =
ACCESS_ONCE(rsp->gp_flags) | RCU_GP_FLAG_FQS;
raw_spin_unlock_irqrestore(&rnp_old->lock, flags);
wake_up(&rsp->gp_wq); /* Memory barrier implied by wake_up() path. */
rcu_gp_kthread_wake(rsp);
}
/*
@@ -2925,11 +2940,6 @@ static int synchronize_sched_expedited_cpu_stop(void *data)
* restructure your code to batch your updates, and then use a single
* synchronize_sched() instead.
*
* Note that it is illegal to call this function while holding any lock
* that is acquired by a CPU-hotplug notifier. And yes, it is also illegal
* to call this function from a CPU-hotplug notifier. Failing to observe
* these restriction will result in deadlock.
*
* This implementation can be thought of as an application of ticket
* locking to RCU, with sync_sched_expedited_started and
* sync_sched_expedited_done taking on the roles of the halves
@@ -2979,7 +2989,12 @@ void synchronize_sched_expedited(void)
*/
snap = atomic_long_inc_return(&rsp->expedited_start);
firstsnap = snap;
get_online_cpus();
if (!try_get_online_cpus()) {
/* CPU hotplug operation in flight, fall back to normal GP. */
wait_rcu_gp(call_rcu_sched);
atomic_long_inc(&rsp->expedited_normal);
return;
}
WARN_ON_ONCE(cpu_is_offline(raw_smp_processor_id()));
/*
@@ -3026,7 +3041,12 @@ void synchronize_sched_expedited(void)
* and they started after our first try, so their grace
* period works for us.
*/
get_online_cpus();
if (!try_get_online_cpus()) {
/* CPU hotplug operation in flight, use normal GP. */
wait_rcu_gp(call_rcu_sched);
atomic_long_inc(&rsp->expedited_normal);
return;
}
snap = atomic_long_read(&rsp->expedited_start);
smp_mb(); /* ensure read is before try_stop_cpus(). */
}
@@ -3442,6 +3462,7 @@ static int rcu_cpu_notify(struct notifier_block *self,
case CPU_UP_PREPARE_FROZEN:
rcu_prepare_cpu(cpu);
rcu_prepare_kthreads(cpu);
rcu_spawn_all_nocb_kthreads(cpu);
break;
case CPU_ONLINE:
case CPU_DOWN_FAILED:
@@ -3489,7 +3510,7 @@ static int rcu_pm_notify(struct notifier_block *self,
}
/*
* Spawn the kthread that handles this RCU flavor's grace periods.
* Spawn the kthreads that handle each RCU flavor's grace periods.
*/
static int __init rcu_spawn_gp_kthread(void)
{
@@ -3498,6 +3519,7 @@ static int __init rcu_spawn_gp_kthread(void)
struct rcu_state *rsp;
struct task_struct *t;
rcu_scheduler_fully_active = 1;
for_each_rcu_flavor(rsp) {
t = kthread_run(rcu_gp_kthread, rsp, "%s", rsp->name);
BUG_ON(IS_ERR(t));
@@ -3505,8 +3527,9 @@ static int __init rcu_spawn_gp_kthread(void)
raw_spin_lock_irqsave(&rnp->lock, flags);
rsp->gp_kthread = t;
raw_spin_unlock_irqrestore(&rnp->lock, flags);
rcu_spawn_nocb_kthreads(rsp);
}
rcu_spawn_nocb_kthreads();
rcu_spawn_boost_kthreads();
return 0;
}
early_initcall(rcu_spawn_gp_kthread);

18
kernel/rcu/tree.h
View File

@@ -350,7 +350,7 @@ struct rcu_data {
int nocb_p_count_lazy; /* (approximate). */
wait_queue_head_t nocb_wq; /* For nocb kthreads to sleep on. */
struct task_struct *nocb_kthread;
bool nocb_defer_wakeup; /* Defer wakeup of nocb_kthread. */
int nocb_defer_wakeup; /* Defer wakeup of nocb_kthread. */
/* The following fields are used by the leader, hence own cacheline. */
struct rcu_head *nocb_gp_head ____cacheline_internodealigned_in_smp;
@@ -383,6 +383,11 @@ struct rcu_data {
#define RCU_FORCE_QS 3 /* Need to force quiescent state. */
#define RCU_SIGNAL_INIT RCU_SAVE_DYNTICK
/* Values for nocb_defer_wakeup field in struct rcu_data. */
#define RCU_NOGP_WAKE_NOT 0
#define RCU_NOGP_WAKE 1
#define RCU_NOGP_WAKE_FORCE 2
#define RCU_JIFFIES_TILL_FORCE_QS (1 + (HZ > 250) + (HZ > 500))
/* For jiffies_till_first_fqs and */
/* and jiffies_till_next_fqs. */
@@ -572,6 +577,7 @@ static void rcu_preempt_do_callbacks(void);
static int rcu_spawn_one_boost_kthread(struct rcu_state *rsp,
struct rcu_node *rnp);
#endif /* #ifdef CONFIG_RCU_BOOST */
static void __init rcu_spawn_boost_kthreads(void);
static void rcu_prepare_kthreads(int cpu);
static void rcu_cleanup_after_idle(int cpu);
static void rcu_prepare_for_idle(int cpu);
@@ -589,10 +595,14 @@ static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp,
static bool rcu_nocb_adopt_orphan_cbs(struct rcu_state *rsp,
struct rcu_data *rdp,
unsigned long flags);
static bool rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp);
static int rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp);
static void do_nocb_deferred_wakeup(struct rcu_data *rdp);
static void rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp);
static void rcu_spawn_nocb_kthreads(struct rcu_state *rsp);
static void rcu_spawn_all_nocb_kthreads(int cpu);
static void __init rcu_spawn_nocb_kthreads(void);
#ifdef CONFIG_RCU_NOCB_CPU
static void __init rcu_organize_nocb_kthreads(struct rcu_state *rsp);
#endif /* #ifdef CONFIG_RCU_NOCB_CPU */
static void __maybe_unused rcu_kick_nohz_cpu(int cpu);
static bool init_nocb_callback_list(struct rcu_data *rdp);
static void rcu_sysidle_enter(struct rcu_dynticks *rdtp, int irq);
@@ -605,6 +615,8 @@ static void rcu_sysidle_report_gp(struct rcu_state *rsp, int isidle,
static void rcu_bind_gp_kthread(void);
static void rcu_sysidle_init_percpu_data(struct rcu_dynticks *rdtp);
static bool rcu_nohz_full_cpu(struct rcu_state *rsp);
static void rcu_dynticks_task_enter(void);
static void rcu_dynticks_task_exit(void);
#endif /* #ifndef RCU_TREE_NONCORE */

400
kernel/rcu/tree_plugin.h
View File

@@ -85,33 +85,6 @@ static void __init rcu_bootup_announce_oddness(void)
pr_info("\tBoot-time adjustment of leaf fanout to %d.\n", rcu_fanout_leaf);
if (nr_cpu_ids != NR_CPUS)
pr_info("\tRCU restricting CPUs from NR_CPUS=%d to nr_cpu_ids=%d.\n", NR_CPUS, nr_cpu_ids);
#ifdef CONFIG_RCU_NOCB_CPU
#ifndef CONFIG_RCU_NOCB_CPU_NONE
if (!have_rcu_nocb_mask) {
zalloc_cpumask_var(&rcu_nocb_mask, GFP_KERNEL);
have_rcu_nocb_mask = true;
}
#ifdef CONFIG_RCU_NOCB_CPU_ZERO
pr_info("\tOffload RCU callbacks from CPU 0\n");
cpumask_set_cpu(0, rcu_nocb_mask);
#endif /* #ifdef CONFIG_RCU_NOCB_CPU_ZERO */
#ifdef CONFIG_RCU_NOCB_CPU_ALL
pr_info("\tOffload RCU callbacks from all CPUs\n");
cpumask_copy(rcu_nocb_mask, cpu_possible_mask);
#endif /* #ifdef CONFIG_RCU_NOCB_CPU_ALL */
#endif /* #ifndef CONFIG_RCU_NOCB_CPU_NONE */
if (have_rcu_nocb_mask) {
if (!cpumask_subset(rcu_nocb_mask, cpu_possible_mask)) {
pr_info("\tNote: kernel parameter 'rcu_nocbs=' contains nonexistent CPUs.\n");
cpumask_and(rcu_nocb_mask, cpu_possible_mask,
rcu_nocb_mask);
}
cpulist_scnprintf(nocb_buf, sizeof(nocb_buf), rcu_nocb_mask);
pr_info("\tOffload RCU callbacks from CPUs: %s.\n", nocb_buf);
if (rcu_nocb_poll)
pr_info("\tPoll for callbacks from no-CBs CPUs.\n");
}
#endif /* #ifdef CONFIG_RCU_NOCB_CPU */
}
#ifdef CONFIG_TREE_PREEMPT_RCU
@@ -134,7 +107,7 @@ static void __init rcu_bootup_announce(void)
* Return the number of RCU-preempt batches processed thus far
* for debug and statistics.
*/
long rcu_batches_completed_preempt(void)
static long rcu_batches_completed_preempt(void)
{
return rcu_preempt_state.completed;
}
@@ -155,18 +128,19 @@ EXPORT_SYMBOL_GPL(rcu_batches_completed);
* not in a quiescent state. There might be any number of tasks blocked
* while in an RCU read-side critical section.
*
* Unlike the other rcu_*_qs() functions, callers to this function
* must disable irqs in order to protect the assignment to
* ->rcu_read_unlock_special.
* As with the other rcu_*_qs() functions, callers to this function
* must disable preemption.
*/
static void rcu_preempt_qs(int cpu)
static void rcu_preempt_qs(void)
{
struct rcu_data *rdp = &per_cpu(rcu_preempt_data, cpu);
if (rdp->passed_quiesce == 0)
trace_rcu_grace_period(TPS("rcu_preempt"), rdp->gpnum, TPS("cpuqs"));
rdp->passed_quiesce = 1;
current->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_NEED_QS;
if (!__this_cpu_read(rcu_preempt_data.passed_quiesce)) {
trace_rcu_grace_period(TPS("rcu_preempt"),
__this_cpu_read(rcu_preempt_data.gpnum),
TPS("cpuqs"));
__this_cpu_write(rcu_preempt_data.passed_quiesce, 1);
barrier(); /* Coordinate with rcu_preempt_check_callbacks(). */
current->rcu_read_unlock_special.b.need_qs = false;
}
}
/*
@@ -190,14 +164,14 @@ static void rcu_preempt_note_context_switch(int cpu)
struct rcu_node *rnp;
if (t->rcu_read_lock_nesting > 0 &&
(t->rcu_read_unlock_special & RCU_READ_UNLOCK_BLOCKED) == 0) {
!t->rcu_read_unlock_special.b.blocked) {
/* Possibly blocking in an RCU read-side critical section. */
rdp = per_cpu_ptr(rcu_preempt_state.rda, cpu);
rnp = rdp->mynode;
raw_spin_lock_irqsave(&rnp->lock, flags);
smp_mb__after_unlock_lock();
t->rcu_read_unlock_special |= RCU_READ_UNLOCK_BLOCKED;
t->rcu_read_unlock_special.b.blocked = true;
t->rcu_blocked_node = rnp;
/*
@@ -239,7 +213,7 @@ static void rcu_preempt_note_context_switch(int cpu)
: rnp->gpnum + 1);
raw_spin_unlock_irqrestore(&rnp->lock, flags);
} else if (t->rcu_read_lock_nesting < 0 &&
t->rcu_read_unlock_special) {
t->rcu_read_unlock_special.s) {
/*
* Complete exit from RCU read-side critical section on
@@ -257,9 +231,7 @@ static void rcu_preempt_note_context_switch(int cpu)
* grace period, then the fact that the task has been enqueued
* means that we continue to block the current grace period.
*/
local_irq_save(flags);
rcu_preempt_qs(cpu);
local_irq_restore(flags);
rcu_preempt_qs();
}
/*
@@ -340,7 +312,7 @@ void rcu_read_unlock_special(struct task_struct *t)
bool drop_boost_mutex = false;
#endif /* #ifdef CONFIG_RCU_BOOST */
struct rcu_node *rnp;
int special;
union rcu_special special;
/* NMI handlers cannot block and cannot safely manipulate state. */
if (in_nmi())
@@ -350,12 +322,13 @@ void rcu_read_unlock_special(struct task_struct *t)
/*
* If RCU core is waiting for this CPU to exit critical section,
* let it know that we have done so.
* let it know that we have done so. Because irqs are disabled,
* t->rcu_read_unlock_special cannot change.
*/
special = t->rcu_read_unlock_special;
if (special & RCU_READ_UNLOCK_NEED_QS) {
rcu_preempt_qs(smp_processor_id());
if (!t->rcu_read_unlock_special) {
if (special.b.need_qs) {
rcu_preempt_qs();
if (!t->rcu_read_unlock_special.s) {
local_irq_restore(flags);
return;
}
@@ -368,8 +341,8 @@ void rcu_read_unlock_special(struct task_struct *t)
}
/* Clean up if blocked during RCU read-side critical section. */
if (special & RCU_READ_UNLOCK_BLOCKED) {
t->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_BLOCKED;
if (special.b.blocked) {
t->rcu_read_unlock_special.b.blocked = false;
/*
* Remove this task from the list it blocked on. The
@@ -653,12 +626,13 @@ static void rcu_preempt_check_callbacks(int cpu)
struct task_struct *t = current;
if (t->rcu_read_lock_nesting == 0) {
rcu_preempt_qs(cpu);
rcu_preempt_qs();
return;
}
if (t->rcu_read_lock_nesting > 0 &&
per_cpu(rcu_preempt_data, cpu).qs_pending)
t->rcu_read_unlock_special |= RCU_READ_UNLOCK_NEED_QS;
per_cpu(rcu_preempt_data, cpu).qs_pending &&
!per_cpu(rcu_preempt_data, cpu).passed_quiesce)
t->rcu_read_unlock_special.b.need_qs = true;
}
#ifdef CONFIG_RCU_BOOST
@@ -819,11 +793,6 @@ sync_rcu_preempt_exp_init(struct rcu_state *rsp, struct rcu_node *rnp)
* In fact, if you are using synchronize_rcu_expedited() in a loop,
* please restructure your code to batch your updates, and then Use a
* single synchronize_rcu() instead.
*
* Note that it is illegal to call this function while holding any lock
* that is acquired by a CPU-hotplug notifier. And yes, it is also illegal
* to call this function from a CPU-hotplug notifier. Failing to observe
* these restriction will result in deadlock.
*/
void synchronize_rcu_expedited(void)
{
@@ -845,7 +814,11 @@ void synchronize_rcu_expedited(void)
* being boosted. This simplifies the process of moving tasks
* from leaf to root rcu_node structures.
*/
get_online_cpus();
if (!try_get_online_cpus()) {
/* CPU-hotplug operation in flight, fall back to normal GP. */
wait_rcu_gp(call_rcu);
return;
}
/*
* Acquire lock, falling back to synchronize_rcu() if too many
@@ -897,7 +870,8 @@ void synchronize_rcu_expedited(void)
/* Clean up and exit. */
smp_mb(); /* ensure expedited GP seen before counter increment. */
ACCESS_ONCE(sync_rcu_preempt_exp_count)++;
ACCESS_ONCE(sync_rcu_preempt_exp_count) =
sync_rcu_preempt_exp_count + 1;
unlock_mb_ret:
mutex_unlock(&sync_rcu_preempt_exp_mutex);
mb_ret:
@@ -941,7 +915,7 @@ void exit_rcu(void)
return;
t->rcu_read_lock_nesting = 1;
barrier();
t->rcu_read_unlock_special = RCU_READ_UNLOCK_BLOCKED;
t->rcu_read_unlock_special.b.blocked = true;
__rcu_read_unlock();
}
@@ -1462,14 +1436,13 @@ static struct smp_hotplug_thread rcu_cpu_thread_spec = {
};
/*
* Spawn all kthreads -- called as soon as the scheduler is running.
* Spawn boost kthreads -- called as soon as the scheduler is running.
*/
static int __init rcu_spawn_kthreads(void)
static void __init rcu_spawn_boost_kthreads(void)
{
struct rcu_node *rnp;
int cpu;
rcu_scheduler_fully_active = 1;
for_each_possible_cpu(cpu)
per_cpu(rcu_cpu_has_work, cpu) = 0;
BUG_ON(smpboot_register_percpu_thread(&rcu_cpu_thread_spec));
@@ -1479,9 +1452,7 @@ static int __init rcu_spawn_kthreads(void)
rcu_for_each_leaf_node(rcu_state_p, rnp)
(void)rcu_spawn_one_boost_kthread(rcu_state_p, rnp);
}
return 0;
}
early_initcall(rcu_spawn_kthreads);
static void rcu_prepare_kthreads(int cpu)
{
@@ -1519,12 +1490,9 @@ static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu)
{
}
static int __init rcu_scheduler_really_started(void)
static void __init rcu_spawn_boost_kthreads(void)
{
rcu_scheduler_fully_active = 1;
return 0;
}
early_initcall(rcu_scheduler_really_started);
static void rcu_prepare_kthreads(int cpu)
{
@@ -1625,7 +1593,7 @@ static bool __maybe_unused rcu_try_advance_all_cbs(void)
/* Exit early if we advanced recently. */
if (jiffies == rdtp->last_advance_all)
return 0;
return false;
rdtp->last_advance_all = jiffies;
for_each_rcu_flavor(rsp) {
@@ -1848,7 +1816,7 @@ static int rcu_oom_notify(struct notifier_block *self,
get_online_cpus();
for_each_online_cpu(cpu) {
smp_call_function_single(cpu, rcu_oom_notify_cpu, NULL, 1);
cond_resched();
cond_resched_rcu_qs();
}
put_online_cpus();
@@ -2075,7 +2043,7 @@ static void wake_nocb_leader(struct rcu_data *rdp, bool force)
if (!ACCESS_ONCE(rdp_leader->nocb_kthread))
return;
if (ACCESS_ONCE(rdp_leader->nocb_leader_sleep) || force) {
/* Prior xchg orders against prior callback enqueue. */
/* Prior smp_mb__after_atomic() orders against prior enqueue. */
ACCESS_ONCE(rdp_leader->nocb_leader_sleep) = false;
wake_up(&rdp_leader->nocb_wq);
}
@@ -2104,6 +2072,7 @@ static void __call_rcu_nocb_enqueue(struct rcu_data *rdp,
ACCESS_ONCE(*old_rhpp) = rhp;
atomic_long_add(rhcount, &rdp->nocb_q_count);
atomic_long_add(rhcount_lazy, &rdp->nocb_q_count_lazy);
smp_mb__after_atomic(); /* Store *old_rhpp before _wake test. */
/* If we are not being polled and there is a kthread, awaken it ... */
t = ACCESS_ONCE(rdp->nocb_kthread);
@@ -2120,16 +2089,23 @@ static void __call_rcu_nocb_enqueue(struct rcu_data *rdp,
trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
TPS("WakeEmpty"));
} else {
rdp->nocb_defer_wakeup = true;
rdp->nocb_defer_wakeup = RCU_NOGP_WAKE;
trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
TPS("WakeEmptyIsDeferred"));
}
rdp->qlen_last_fqs_check = 0;
} else if (len > rdp->qlen_last_fqs_check + qhimark) {
/* ... or if many callbacks queued. */
wake_nocb_leader(rdp, true);
if (!irqs_disabled_flags(flags)) {
wake_nocb_leader(rdp, true);
trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
TPS("WakeOvf"));
} else {
rdp->nocb_defer_wakeup = RCU_NOGP_WAKE_FORCE;
trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
TPS("WakeOvfIsDeferred"));
}
rdp->qlen_last_fqs_check = LONG_MAX / 2;
trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("WakeOvf"));
} else {
trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("WakeNot"));
}
@@ -2150,7 +2126,7 @@ static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp,
{
if (!rcu_is_nocb_cpu(rdp->cpu))
return 0;
return false;
__call_rcu_nocb_enqueue(rdp, rhp, &rhp->next, 1, lazy, flags);
if (__is_kfree_rcu_offset((unsigned long)rhp->func))
trace_rcu_kfree_callback(rdp->rsp->name, rhp,
@@ -2161,7 +2137,18 @@ static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp,
trace_rcu_callback(rdp->rsp->name, rhp,
-atomic_long_read(&rdp->nocb_q_count_lazy),
-atomic_long_read(&rdp->nocb_q_count));
return 1;
/*
* If called from an extended quiescent state with interrupts
* disabled, invoke the RCU core in order to allow the idle-entry
* deferred-wakeup check to function.
*/
if (irqs_disabled_flags(flags) &&
!rcu_is_watching() &&
cpu_online(smp_processor_id()))
invoke_rcu_core();
return true;
}
/*
@@ -2177,7 +2164,7 @@ static bool __maybe_unused rcu_nocb_adopt_orphan_cbs(struct rcu_state *rsp,
/* If this is not a no-CBs CPU, tell the caller to do it the old way. */
if (!rcu_is_nocb_cpu(smp_processor_id()))
return 0;
return false;
rsp->qlen = 0;
rsp->qlen_lazy = 0;
@@ -2196,7 +2183,7 @@ static bool __maybe_unused rcu_nocb_adopt_orphan_cbs(struct rcu_state *rsp,
rsp->orphan_nxtlist = NULL;
rsp->orphan_nxttail = &rsp->orphan_nxtlist;
}
return 1;
return true;
}
/*
@@ -2229,7 +2216,7 @@ static void rcu_nocb_wait_gp(struct rcu_data *rdp)
(d = ULONG_CMP_GE(ACCESS_ONCE(rnp->completed), c)));
if (likely(d))
break;
flush_signals(current);
WARN_ON(signal_pending(current));
trace_rcu_future_gp(rnp, rdp, c, TPS("ResumeWait"));
}
trace_rcu_future_gp(rnp, rdp, c, TPS("EndWait"));
@@ -2288,7 +2275,7 @@ wait_again:
if (!rcu_nocb_poll)
trace_rcu_nocb_wake(my_rdp->rsp->name, my_rdp->cpu,
"WokeEmpty");
flush_signals(current);
WARN_ON(signal_pending(current));
schedule_timeout_interruptible(1);
/* Rescan in case we were a victim of memory ordering. */
@@ -2327,6 +2314,7 @@ wait_again:
atomic_long_add(rdp->nocb_gp_count, &rdp->nocb_follower_count);
atomic_long_add(rdp->nocb_gp_count_lazy,
&rdp->nocb_follower_count_lazy);
smp_mb__after_atomic(); /* Store *tail before wakeup. */
if (rdp != my_rdp && tail == &rdp->nocb_follower_head) {
/*
* List was empty, wake up the follower.
@@ -2367,7 +2355,7 @@ static void nocb_follower_wait(struct rcu_data *rdp)
if (!rcu_nocb_poll)
trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
"WokeEmpty");
flush_signals(current);
WARN_ON(signal_pending(current));
schedule_timeout_interruptible(1);
}
}
@@ -2428,15 +2416,16 @@ static int rcu_nocb_kthread(void *arg)
list = next;
}
trace_rcu_batch_end(rdp->rsp->name, c, !!list, 0, 0, 1);
ACCESS_ONCE(rdp->nocb_p_count) -= c;
ACCESS_ONCE(rdp->nocb_p_count_lazy) -= cl;
ACCESS_ONCE(rdp->nocb_p_count) = rdp->nocb_p_count - c;
ACCESS_ONCE(rdp->nocb_p_count_lazy) =
rdp->nocb_p_count_lazy - cl;
rdp->n_nocbs_invoked += c;
}
return 0;
}
/* Is a deferred wakeup of rcu_nocb_kthread() required? */
static bool rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp)
static int rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp)
{
return ACCESS_ONCE(rdp->nocb_defer_wakeup);
}
@@ -2444,11 +2433,79 @@ static bool rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp)
/* Do a deferred wakeup of rcu_nocb_kthread(). */
static void do_nocb_deferred_wakeup(struct rcu_data *rdp)
{
int ndw;
if (!rcu_nocb_need_deferred_wakeup(rdp))
return;
ACCESS_ONCE(rdp->nocb_defer_wakeup) = false;
wake_nocb_leader(rdp, false);
trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("DeferredWakeEmpty"));
ndw = ACCESS_ONCE(rdp->nocb_defer_wakeup);
ACCESS_ONCE(rdp->nocb_defer_wakeup) = RCU_NOGP_WAKE_NOT;
wake_nocb_leader(rdp, ndw == RCU_NOGP_WAKE_FORCE);
trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("DeferredWake"));
}
void __init rcu_init_nohz(void)
{
int cpu;
bool need_rcu_nocb_mask = true;
struct rcu_state *rsp;
#ifdef CONFIG_RCU_NOCB_CPU_NONE
need_rcu_nocb_mask = false;
#endif /* #ifndef CONFIG_RCU_NOCB_CPU_NONE */
#if defined(CONFIG_NO_HZ_FULL)
if (tick_nohz_full_running && cpumask_weight(tick_nohz_full_mask))
need_rcu_nocb_mask = true;
#endif /* #if defined(CONFIG_NO_HZ_FULL) */
if (!have_rcu_nocb_mask && need_rcu_nocb_mask) {
if (!zalloc_cpumask_var(&rcu_nocb_mask, GFP_KERNEL)) {
pr_info("rcu_nocb_mask allocation failed, callback offloading disabled.\n");
return;
}
have_rcu_nocb_mask = true;
}
if (!have_rcu_nocb_mask)
return;
#ifdef CONFIG_RCU_NOCB_CPU_ZERO
pr_info("\tOffload RCU callbacks from CPU 0\n");
cpumask_set_cpu(0, rcu_nocb_mask);
#endif /* #ifdef CONFIG_RCU_NOCB_CPU_ZERO */
#ifdef CONFIG_RCU_NOCB_CPU_ALL
pr_info("\tOffload RCU callbacks from all CPUs\n");
cpumask_copy(rcu_nocb_mask, cpu_possible_mask);
#endif /* #ifdef CONFIG_RCU_NOCB_CPU_ALL */
#if defined(CONFIG_NO_HZ_FULL)
if (tick_nohz_full_running)
cpumask_or(rcu_nocb_mask, rcu_nocb_mask, tick_nohz_full_mask);
#endif /* #if defined(CONFIG_NO_HZ_FULL) */
if (!cpumask_subset(rcu_nocb_mask, cpu_possible_mask)) {
pr_info("\tNote: kernel parameter 'rcu_nocbs=' contains nonexistent CPUs.\n");
cpumask_and(rcu_nocb_mask, cpu_possible_mask,
rcu_nocb_mask);
}
cpulist_scnprintf(nocb_buf, sizeof(nocb_buf), rcu_nocb_mask);
pr_info("\tOffload RCU callbacks from CPUs: %s.\n", nocb_buf);
if (rcu_nocb_poll)
pr_info("\tPoll for callbacks from no-CBs CPUs.\n");
for_each_rcu_flavor(rsp) {
for_each_cpu(cpu, rcu_nocb_mask) {
struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
/*
* If there are early callbacks, they will need
* to be moved to the nocb lists.
*/
WARN_ON_ONCE(rdp->nxttail[RCU_NEXT_TAIL] !=
&rdp->nxtlist &&
rdp->nxttail[RCU_NEXT_TAIL] != NULL);
init_nocb_callback_list(rdp);
}
rcu_organize_nocb_kthreads(rsp);
}
}
/* Initialize per-rcu_data variables for no-CBs CPUs. */
@@ -2459,15 +2516,85 @@ static void __init rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp)
rdp->nocb_follower_tail = &rdp->nocb_follower_head;
}
/*
* If the specified CPU is a no-CBs CPU that does not already have its
* rcuo kthread for the specified RCU flavor, spawn it. If the CPUs are
* brought online out of order, this can require re-organizing the
* leader-follower relationships.
*/
static void rcu_spawn_one_nocb_kthread(struct rcu_state *rsp, int cpu)
{
struct rcu_data *rdp;
struct rcu_data *rdp_last;
struct rcu_data *rdp_old_leader;
struct rcu_data *rdp_spawn = per_cpu_ptr(rsp->rda, cpu);
struct task_struct *t;
/*
* If this isn't a no-CBs CPU or if it already has an rcuo kthread,
* then nothing to do.
*/
if (!rcu_is_nocb_cpu(cpu) || rdp_spawn->nocb_kthread)
return;
/* If we didn't spawn the leader first, reorganize! */
rdp_old_leader = rdp_spawn->nocb_leader;
if (rdp_old_leader != rdp_spawn && !rdp_old_leader->nocb_kthread) {
rdp_last = NULL;
rdp = rdp_old_leader;
do {
rdp->nocb_leader = rdp_spawn;
if (rdp_last && rdp != rdp_spawn)
rdp_last->nocb_next_follower = rdp;
rdp_last = rdp;
rdp = rdp->nocb_next_follower;
rdp_last->nocb_next_follower = NULL;
} while (rdp);
rdp_spawn->nocb_next_follower = rdp_old_leader;
}
/* Spawn the kthread for this CPU and RCU flavor. */
t = kthread_run(rcu_nocb_kthread, rdp_spawn,
"rcuo%c/%d", rsp->abbr, cpu);
BUG_ON(IS_ERR(t));
ACCESS_ONCE(rdp_spawn->nocb_kthread) = t;
}
/*
* If the specified CPU is a no-CBs CPU that does not already have its
* rcuo kthreads, spawn them.
*/
static void rcu_spawn_all_nocb_kthreads(int cpu)
{
struct rcu_state *rsp;
if (rcu_scheduler_fully_active)
for_each_rcu_flavor(rsp)
rcu_spawn_one_nocb_kthread(rsp, cpu);
}
/*
* Once the scheduler is running, spawn rcuo kthreads for all online
* no-CBs CPUs. This assumes that the early_initcall()s happen before
* non-boot CPUs come online -- if this changes, we will need to add
* some mutual exclusion.
*/
static void __init rcu_spawn_nocb_kthreads(void)
{
int cpu;
for_each_online_cpu(cpu)
rcu_spawn_all_nocb_kthreads(cpu);
}
/* How many follower CPU IDs per leader? Default of -1 for sqrt(nr_cpu_ids). */
static int rcu_nocb_leader_stride = -1;
module_param(rcu_nocb_leader_stride, int, 0444);
/*
* Create a kthread for each RCU flavor for each no-CBs CPU.
* Also initialize leader-follower relationships.
* Initialize leader-follower relationships for all no-CBs CPU.
*/
static void __init rcu_spawn_nocb_kthreads(struct rcu_state *rsp)
static void __init rcu_organize_nocb_kthreads(struct rcu_state *rsp)
{
int cpu;
int ls = rcu_nocb_leader_stride;
@@ -2475,14 +2602,9 @@ static void __init rcu_spawn_nocb_kthreads(struct rcu_state *rsp)
struct rcu_data *rdp;
struct rcu_data *rdp_leader = NULL; /* Suppress misguided gcc warn. */
struct rcu_data *rdp_prev = NULL;
struct task_struct *t;
if (rcu_nocb_mask == NULL)
if (!have_rcu_nocb_mask)
return;
#if defined(CONFIG_NO_HZ_FULL) && !defined(CONFIG_NO_HZ_FULL_ALL)
if (tick_nohz_full_running)
cpumask_or(rcu_nocb_mask, rcu_nocb_mask, tick_nohz_full_mask);
#endif /* #if defined(CONFIG_NO_HZ_FULL) && !defined(CONFIG_NO_HZ_FULL_ALL) */
if (ls == -1) {
ls = int_sqrt(nr_cpu_ids);
rcu_nocb_leader_stride = ls;
@@ -2505,21 +2627,15 @@ static void __init rcu_spawn_nocb_kthreads(struct rcu_state *rsp)
rdp_prev->nocb_next_follower = rdp;
}
rdp_prev = rdp;
/* Spawn the kthread for this CPU. */
t = kthread_run(rcu_nocb_kthread, rdp,
"rcuo%c/%d", rsp->abbr, cpu);
BUG_ON(IS_ERR(t));
ACCESS_ONCE(rdp->nocb_kthread) = t;
}
}
/* Prevent __call_rcu() from enqueuing callbacks on no-CBs CPUs */
static bool init_nocb_callback_list(struct rcu_data *rdp)
{
if (rcu_nocb_mask == NULL ||
!cpumask_test_cpu(rdp->cpu, rcu_nocb_mask))
if (!rcu_is_nocb_cpu(rdp->cpu))
return false;
rdp->nxttail[RCU_NEXT_TAIL] = NULL;
return true;
}
@@ -2541,21 +2657,21 @@ static void rcu_init_one_nocb(struct rcu_node *rnp)
static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp,
bool lazy, unsigned long flags)
{
return 0;
return false;
}
static bool __maybe_unused rcu_nocb_adopt_orphan_cbs(struct rcu_state *rsp,
struct rcu_data *rdp,
unsigned long flags)
{
return 0;
return false;
}
static void __init rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp)
{
}
static bool rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp)
static int rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp)
{
return false;
}
@@ -2564,7 +2680,11 @@ static void do_nocb_deferred_wakeup(struct rcu_data *rdp)
{
}
static void __init rcu_spawn_nocb_kthreads(struct rcu_state *rsp)
static void rcu_spawn_all_nocb_kthreads(int cpu)
{
}
static void __init rcu_spawn_nocb_kthreads(void)
{
}
@@ -2595,16 +2715,6 @@ static void __maybe_unused rcu_kick_nohz_cpu(int cpu)
#ifdef CONFIG_NO_HZ_FULL_SYSIDLE
/*
* Define RCU flavor that holds sysidle state. This needs to be the
* most active flavor of RCU.
*/
#ifdef CONFIG_PREEMPT_RCU
static struct rcu_state *rcu_sysidle_state = &rcu_preempt_state;
#else /* #ifdef CONFIG_PREEMPT_RCU */
static struct rcu_state *rcu_sysidle_state = &rcu_sched_state;
#endif /* #else #ifdef CONFIG_PREEMPT_RCU */
static int full_sysidle_state; /* Current system-idle state. */
#define RCU_SYSIDLE_NOT 0 /* Some CPU is not idle. */
#define RCU_SYSIDLE_SHORT 1 /* All CPUs idle for brief period. */
@@ -2622,6 +2732,10 @@ static void rcu_sysidle_enter(struct rcu_dynticks *rdtp, int irq)
{
unsigned long j;
/* If there are no nohz_full= CPUs, no need to track this. */
if (!tick_nohz_full_enabled())
return;
/* Adjust nesting, check for fully idle. */
if (irq) {
rdtp->dynticks_idle_nesting--;
@@ -2687,6 +2801,10 @@ void rcu_sysidle_force_exit(void)
*/
static void rcu_sysidle_exit(struct rcu_dynticks *rdtp, int irq)
{
/* If there are no nohz_full= CPUs, no need to track this. */
if (!tick_nohz_full_enabled())
return;
/* Adjust nesting, check for already non-idle. */
if (irq) {
rdtp->dynticks_idle_nesting++;
@@ -2741,12 +2859,16 @@ static void rcu_sysidle_check_cpu(struct rcu_data *rdp, bool *isidle,
unsigned long j;
struct rcu_dynticks *rdtp = rdp->dynticks;
/* If there are no nohz_full= CPUs, don't check system-wide idleness. */
if (!tick_nohz_full_enabled())
return;
/*
* If some other CPU has already reported non-idle, if this is
* not the flavor of RCU that tracks sysidle state, or if this
* is an offline or the timekeeping CPU, nothing to do.
*/
if (!*isidle || rdp->rsp != rcu_sysidle_state ||
if (!*isidle || rdp->rsp != rcu_state_p ||
cpu_is_offline(rdp->cpu) || rdp->cpu == tick_do_timer_cpu)
return;
if (rcu_gp_in_progress(rdp->rsp))
@@ -2772,7 +2894,7 @@ static void rcu_sysidle_check_cpu(struct rcu_data *rdp, bool *isidle,
*/
static bool is_sysidle_rcu_state(struct rcu_state *rsp)
{
return rsp == rcu_sysidle_state;
return rsp == rcu_state_p;
}
/*
@@ -2850,7 +2972,7 @@ static void rcu_sysidle_cancel(void)
static void rcu_sysidle_report(struct rcu_state *rsp, int isidle,
unsigned long maxj, bool gpkt)
{
if (rsp != rcu_sysidle_state)
if (rsp != rcu_state_p)
return; /* Wrong flavor, ignore. */
if (gpkt && nr_cpu_ids <= CONFIG_NO_HZ_FULL_SYSIDLE_SMALL)
return; /* Running state machine from timekeeping CPU. */
@@ -2867,6 +2989,10 @@ static void rcu_sysidle_report(struct rcu_state *rsp, int isidle,
static void rcu_sysidle_report_gp(struct rcu_state *rsp, int isidle,
unsigned long maxj)
{
/* If there are no nohz_full= CPUs, no need to track this. */
if (!tick_nohz_full_enabled())
return;
rcu_sysidle_report(rsp, isidle, maxj, true);
}
@@ -2893,7 +3019,8 @@ static void rcu_sysidle_cb(struct rcu_head *rhp)
/*
* Check to see if the system is fully idle, other than the timekeeping CPU.
* The caller must have disabled interrupts.
* The caller must have disabled interrupts. This is not intended to be
* called unless tick_nohz_full_enabled().
*/
bool rcu_sys_is_idle(void)
{
@@ -2919,13 +3046,12 @@ bool rcu_sys_is_idle(void)
/* Scan all the CPUs looking for nonidle CPUs. */
for_each_possible_cpu(cpu) {
rdp = per_cpu_ptr(rcu_sysidle_state->rda, cpu);
rdp = per_cpu_ptr(rcu_state_p->rda, cpu);
rcu_sysidle_check_cpu(rdp, &isidle, &maxj);
if (!isidle)
break;
}
rcu_sysidle_report(rcu_sysidle_state,
isidle, maxj, false);
rcu_sysidle_report(rcu_state_p, isidle, maxj, false);
oldrss = rss;
rss = ACCESS_ONCE(full_sysidle_state);
}
@@ -2952,7 +3078,7 @@ bool rcu_sys_is_idle(void)
* provided by the memory allocator.
*/
if (nr_cpu_ids > CONFIG_NO_HZ_FULL_SYSIDLE_SMALL &&
!rcu_gp_in_progress(rcu_sysidle_state) &&
!rcu_gp_in_progress(rcu_state_p) &&
!rsh.inuse && xchg(&rsh.inuse, 1) == 0)
call_rcu(&rsh.rh, rcu_sysidle_cb);
return false;
@@ -3036,3 +3162,19 @@ static void rcu_bind_gp_kthread(void)
housekeeping_affine(current);
#endif /* #else #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */
}
/* Record the current task on dyntick-idle entry. */
static void rcu_dynticks_task_enter(void)
{
#if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL)
ACCESS_ONCE(current->rcu_tasks_idle_cpu) = smp_processor_id();
#endif /* #if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL) */
}
/* Record no current task on dyntick-idle exit. */
static void rcu_dynticks_task_exit(void)
{
#if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL)
ACCESS_ONCE(current->rcu_tasks_idle_cpu) = -1;
#endif /* #if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL) */
}

345
kernel/rcu/update.c
View File

@@ -47,6 +47,8 @@
#include <linux/hardirq.h>
#include <linux/delay.h>
#include <linux/module.h>
#include <linux/kthread.h>
#include <linux/tick.h>
#define CREATE_TRACE_POINTS
@@ -91,7 +93,7 @@ void __rcu_read_unlock(void)
barrier(); /* critical section before exit code. */
t->rcu_read_lock_nesting = INT_MIN;
barrier(); /* assign before ->rcu_read_unlock_special load */
if (unlikely(ACCESS_ONCE(t->rcu_read_unlock_special)))
if (unlikely(ACCESS_ONCE(t->rcu_read_unlock_special.s)))
rcu_read_unlock_special(t);
barrier(); /* ->rcu_read_unlock_special load before assign */
t->rcu_read_lock_nesting = 0;
@@ -136,6 +138,38 @@ int notrace debug_lockdep_rcu_enabled(void)
}
EXPORT_SYMBOL_GPL(debug_lockdep_rcu_enabled);
/**
* rcu_read_lock_held() - might we be in RCU read-side critical section?
*
* If CONFIG_DEBUG_LOCK_ALLOC is selected, returns nonzero iff in an RCU
* read-side critical section. In absence of CONFIG_DEBUG_LOCK_ALLOC,
* this assumes we are in an RCU read-side critical section unless it can
* prove otherwise. This is useful for debug checks in functions that
* require that they be called within an RCU read-side critical section.
*
* Checks debug_lockdep_rcu_enabled() to prevent false positives during boot
* and while lockdep is disabled.
*
* 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.
*
* 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.
*/
int rcu_read_lock_held(void)
{
if (!debug_lockdep_rcu_enabled())
return 1;
if (!rcu_is_watching())
return 0;
if (!rcu_lockdep_current_cpu_online())
return 0;
return lock_is_held(&rcu_lock_map);
}
EXPORT_SYMBOL_GPL(rcu_read_lock_held);
/**
* rcu_read_lock_bh_held() - might we be in RCU-bh read-side critical section?
*
@@ -347,3 +381,312 @@ static int __init check_cpu_stall_init(void)
early_initcall(check_cpu_stall_init);
#endif /* #ifdef CONFIG_RCU_STALL_COMMON */
#ifdef CONFIG_TASKS_RCU
/*
* Simple variant of RCU whose quiescent states are voluntary context switch,
* user-space execution, and idle. As such, grace periods can take one good
* long time. There are no read-side primitives similar to rcu_read_lock()
* and rcu_read_unlock() because this implementation is intended to get
* the system into a safe state for some of the manipulations involved in
* tracing and the like. Finally, this implementation does not support
* high call_rcu_tasks() rates from multiple CPUs. If this is required,
* per-CPU callback lists will be needed.
*/
/* Global list of callbacks and associated lock. */
static struct rcu_head *rcu_tasks_cbs_head;
static struct rcu_head **rcu_tasks_cbs_tail = &rcu_tasks_cbs_head;
static DECLARE_WAIT_QUEUE_HEAD(rcu_tasks_cbs_wq);
static DEFINE_RAW_SPINLOCK(rcu_tasks_cbs_lock);
/* Track exiting tasks in order to allow them to be waited for. */
DEFINE_SRCU(tasks_rcu_exit_srcu);
/* Control stall timeouts. Disable with <= 0, otherwise jiffies till stall. */
static int rcu_task_stall_timeout __read_mostly = HZ * 60 * 10;
module_param(rcu_task_stall_timeout, int, 0644);
static void rcu_spawn_tasks_kthread(void);
/*
* Post an RCU-tasks callback. First call must be from process context
* after the scheduler if fully operational.
*/
void call_rcu_tasks(struct rcu_head *rhp, void (*func)(struct rcu_head *rhp))
{
unsigned long flags;
bool needwake;
rhp->next = NULL;
rhp->func = func;
raw_spin_lock_irqsave(&rcu_tasks_cbs_lock, flags);
needwake = !rcu_tasks_cbs_head;
*rcu_tasks_cbs_tail = rhp;
rcu_tasks_cbs_tail = &rhp->next;
raw_spin_unlock_irqrestore(&rcu_tasks_cbs_lock, flags);
if (needwake) {
rcu_spawn_tasks_kthread();
wake_up(&rcu_tasks_cbs_wq);
}
}
EXPORT_SYMBOL_GPL(call_rcu_tasks);
/**
* synchronize_rcu_tasks - wait until an rcu-tasks grace period has elapsed.
*
* Control will return to the caller some time after a full rcu-tasks
* grace period has elapsed, in other words after all currently
* executing rcu-tasks read-side critical sections have elapsed. These
* read-side critical sections are delimited by calls to schedule(),
* cond_resched_rcu_qs(), idle execution, userspace execution, calls
* to synchronize_rcu_tasks(), and (in theory, anyway) cond_resched().
*
* This is a very specialized primitive, intended only for a few uses in
* tracing and other situations requiring manipulation of function
* preambles and profiling hooks. The synchronize_rcu_tasks() function
* is not (yet) intended for heavy use from multiple CPUs.
*
* Note that this guarantee implies further memory-ordering guarantees.
* On systems with more than one CPU, when synchronize_rcu_tasks() returns,
* each CPU is guaranteed to have executed a full memory barrier since the
* end of its last RCU-tasks read-side critical section whose beginning
* preceded the call to synchronize_rcu_tasks(). In addition, each CPU
* having an RCU-tasks read-side critical section that extends beyond
* the return from synchronize_rcu_tasks() is guaranteed to have executed
* a full memory barrier after the beginning of synchronize_rcu_tasks()
* and before the beginning of that RCU-tasks 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 synchronize_rcu_tasks(), which returned
* to its caller on CPU B, then both CPU A and CPU B are guaranteed
* to have executed a full memory barrier during the execution of
* synchronize_rcu_tasks() -- even if CPU A and CPU B are the same CPU
* (but again only if the system has more than one CPU).
*/
void synchronize_rcu_tasks(void)
{
/* Complain if the scheduler has not started. */
rcu_lockdep_assert(!rcu_scheduler_active,
"synchronize_rcu_tasks called too soon");
/* Wait for the grace period. */
wait_rcu_gp(call_rcu_tasks);
}
EXPORT_SYMBOL_GPL(synchronize_rcu_tasks);
/**
* rcu_barrier_tasks - Wait for in-flight call_rcu_tasks() callbacks.
*
* Although the current implementation is guaranteed to wait, it is not
* obligated to, for example, if there are no pending callbacks.
*/
void rcu_barrier_tasks(void)
{
/* There is only one callback queue, so this is easy. ;-) */
synchronize_rcu_tasks();
}
EXPORT_SYMBOL_GPL(rcu_barrier_tasks);
/* See if tasks are still holding out, complain if so. */
static void check_holdout_task(struct task_struct *t,
bool needreport, bool *firstreport)
{
int cpu;
if (!ACCESS_ONCE(t->rcu_tasks_holdout) ||
t->rcu_tasks_nvcsw != ACCESS_ONCE(t->nvcsw) ||
!ACCESS_ONCE(t->on_rq) ||
(IS_ENABLED(CONFIG_NO_HZ_FULL) &&
!is_idle_task(t) && t->rcu_tasks_idle_cpu >= 0)) {
ACCESS_ONCE(t->rcu_tasks_holdout) = false;
list_del_init(&t->rcu_tasks_holdout_list);
put_task_struct(t);
return;
}
if (!needreport)
return;
if (*firstreport) {
pr_err("INFO: rcu_tasks detected stalls on tasks:\n");
*firstreport = false;
}
cpu = task_cpu(t);
pr_alert("%p: %c%c nvcsw: %lu/%lu holdout: %d idle_cpu: %d/%d\n",
t, ".I"[is_idle_task(t)],
"N."[cpu < 0 || !tick_nohz_full_cpu(cpu)],
t->rcu_tasks_nvcsw, t->nvcsw, t->rcu_tasks_holdout,
t->rcu_tasks_idle_cpu, cpu);
sched_show_task(t);
}
/* RCU-tasks kthread that detects grace periods and invokes callbacks. */
static int __noreturn rcu_tasks_kthread(void *arg)
{
unsigned long flags;
struct task_struct *g, *t;
unsigned long lastreport;
struct rcu_head *list;
struct rcu_head *next;
LIST_HEAD(rcu_tasks_holdouts);
/* FIXME: Add housekeeping affinity. */
/*
* Each pass through the following loop makes one check for
* newly arrived callbacks, and, if there are some, waits for
* one RCU-tasks grace period and then invokes the callbacks.
* This loop is terminated by the system going down. ;-)
*/
for (;;) {
/* Pick up any new callbacks. */
raw_spin_lock_irqsave(&rcu_tasks_cbs_lock, flags);
list = rcu_tasks_cbs_head;
rcu_tasks_cbs_head = NULL;
rcu_tasks_cbs_tail = &rcu_tasks_cbs_head;
raw_spin_unlock_irqrestore(&rcu_tasks_cbs_lock, flags);
/* If there were none, wait a bit and start over. */
if (!list) {
wait_event_interruptible(rcu_tasks_cbs_wq,
rcu_tasks_cbs_head);
if (!rcu_tasks_cbs_head) {
WARN_ON(signal_pending(current));
schedule_timeout_interruptible(HZ/10);
}
continue;
}
/*
* Wait for all pre-existing t->on_rq and t->nvcsw
* transitions to complete. Invoking synchronize_sched()
* suffices because all these transitions occur with
* interrupts disabled. Without this synchronize_sched(),
* a read-side critical section that started before the
* grace period might be incorrectly seen as having started
* after the grace period.
*
* This synchronize_sched() also dispenses with the
* need for a memory barrier on the first store to
* ->rcu_tasks_holdout, as it forces the store to happen
* after the beginning of the grace period.
*/
synchronize_sched();
/*
* There were callbacks, so we need to wait for an
* RCU-tasks grace period. Start off by scanning
* the task list for tasks that are not already
* voluntarily blocked. Mark these tasks and make
* a list of them in rcu_tasks_holdouts.
*/
rcu_read_lock();
for_each_process_thread(g, t) {
if (t != current && ACCESS_ONCE(t->on_rq) &&
!is_idle_task(t)) {
get_task_struct(t);
t->rcu_tasks_nvcsw = ACCESS_ONCE(t->nvcsw);
ACCESS_ONCE(t->rcu_tasks_holdout) = true;
list_add(&t->rcu_tasks_holdout_list,
&rcu_tasks_holdouts);
}
}
rcu_read_unlock();
/*
* Wait for tasks that are in the process of exiting.
* This does only part of the job, ensuring that all
* tasks that were previously exiting reach the point
* where they have disabled preemption, allowing the
* later synchronize_sched() to finish the job.
*/
synchronize_srcu(&tasks_rcu_exit_srcu);
/*
* Each pass through the following loop scans the list
* of holdout tasks, removing any that are no longer
* holdouts. When the list is empty, we are done.
*/
lastreport = jiffies;
while (!list_empty(&rcu_tasks_holdouts)) {
bool firstreport;
bool needreport;
int rtst;
struct task_struct *t1;
schedule_timeout_interruptible(HZ);
rtst = ACCESS_ONCE(rcu_task_stall_timeout);
needreport = rtst > 0 &&
time_after(jiffies, lastreport + rtst);
if (needreport)
lastreport = jiffies;
firstreport = true;
WARN_ON(signal_pending(current));
list_for_each_entry_safe(t, t1, &rcu_tasks_holdouts,
rcu_tasks_holdout_list) {
check_holdout_task(t, needreport, &firstreport);
cond_resched();
}
}
/*
* Because ->on_rq and ->nvcsw are not guaranteed
* to have a full memory barriers prior to them in the
* schedule() path, memory reordering on other CPUs could
* cause their RCU-tasks read-side critical sections to
* extend past the end of the grace period. However,
* because these ->nvcsw updates are carried out with
* interrupts disabled, we can use synchronize_sched()
* to force the needed ordering on all such CPUs.
*
* This synchronize_sched() also confines all
* ->rcu_tasks_holdout accesses to be within the grace
* period, avoiding the need for memory barriers for
* ->rcu_tasks_holdout accesses.
*
* In addition, this synchronize_sched() waits for exiting
* tasks to complete their final preempt_disable() region
* of execution, cleaning up after the synchronize_srcu()
* above.
*/
synchronize_sched();
/* Invoke the callbacks. */
while (list) {
next = list->next;
local_bh_disable();
list->func(list);
local_bh_enable();
list = next;
cond_resched();
}
schedule_timeout_uninterruptible(HZ/10);
}
}
/* Spawn rcu_tasks_kthread() at first call to call_rcu_tasks(). */
static void rcu_spawn_tasks_kthread(void)
{
static DEFINE_MUTEX(rcu_tasks_kthread_mutex);
static struct task_struct *rcu_tasks_kthread_ptr;
struct task_struct *t;
if (ACCESS_ONCE(rcu_tasks_kthread_ptr)) {
smp_mb(); /* Ensure caller sees full kthread. */
return;
}
mutex_lock(&rcu_tasks_kthread_mutex);
if (rcu_tasks_kthread_ptr) {
mutex_unlock(&rcu_tasks_kthread_mutex);
return;
}
t = kthread_run(rcu_tasks_kthread, NULL, "rcu_tasks_kthread");
BUG_ON(IS_ERR(t));
smp_mb(); /* Ensure others see full kthread. */
ACCESS_ONCE(rcu_tasks_kthread_ptr) = t;
mutex_unlock(&rcu_tasks_kthread_mutex);
}
#endif /* #ifdef CONFIG_TASKS_RCU */

2
kernel/softirq.c
View File

@@ -278,7 +278,7 @@ restart:
pending >>= softirq_bit;
}
rcu_bh_qs(smp_processor_id());
rcu_bh_qs();
local_irq_disable();
pending = local_softirq_pending();

9
kernel/sysctl.c
View File

@@ -1055,15 +1055,6 @@ static struct ctl_table kern_table[] = {
.child = key_sysctls,
},
#endif
#ifdef CONFIG_RCU_TORTURE_TEST
{
.procname = "rcutorture_runnable",
.data = &rcutorture_runnable,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
#endif
#ifdef CONFIG_PERF_EVENTS
/*
* User-space scripts rely on the existence of this file

32
kernel/torture.c
View File

@@ -211,18 +211,16 @@ EXPORT_SYMBOL_GPL(torture_onoff_cleanup);
/*
* Print online/offline testing statistics.
*/
char *torture_onoff_stats(char *page)
void torture_onoff_stats(void)
{
#ifdef CONFIG_HOTPLUG_CPU
page += sprintf(page,
"onoff: %ld/%ld:%ld/%ld %d,%d:%d,%d %lu:%lu (HZ=%d) ",
n_online_successes, n_online_attempts,
n_offline_successes, n_offline_attempts,
min_online, max_online,
min_offline, max_offline,
sum_online, sum_offline, HZ);
pr_cont("onoff: %ld/%ld:%ld/%ld %d,%d:%d,%d %lu:%lu (HZ=%d) ",
n_online_successes, n_online_attempts,
n_offline_successes, n_offline_attempts,
min_online, max_online,
min_offline, max_offline,
sum_online, sum_offline, HZ);
#endif /* #ifdef CONFIG_HOTPLUG_CPU */
return page;
}
EXPORT_SYMBOL_GPL(torture_onoff_stats);
@@ -635,8 +633,13 @@ EXPORT_SYMBOL_GPL(torture_init_end);
*
* This must be called before the caller starts shutting down its own
* kthreads.
*
* Both torture_cleanup_begin() and torture_cleanup_end() must be paired,
* in order to correctly perform the cleanup. They are separated because
* threads can still need to reference the torture_type type, thus nullify
* only after completing all other relevant calls.
*/
bool torture_cleanup(void)
bool torture_cleanup_begin(void)
{
mutex_lock(&fullstop_mutex);
if (ACCESS_ONCE(fullstop) == FULLSTOP_SHUTDOWN) {
@@ -651,12 +654,17 @@ bool torture_cleanup(void)
torture_shuffle_cleanup();
torture_stutter_cleanup();
torture_onoff_cleanup();
return false;
}
EXPORT_SYMBOL_GPL(torture_cleanup_begin);
void torture_cleanup_end(void)
{
mutex_lock(&fullstop_mutex);
torture_type = NULL;
mutex_unlock(&fullstop_mutex);
return false;
}
EXPORT_SYMBOL_GPL(torture_cleanup);
EXPORT_SYMBOL_GPL(torture_cleanup_end);
/*
* Is it time for the current torture test to stop?

5
kernel/workqueue.c
View File

@@ -2043,9 +2043,10 @@ __acquires(&pool->lock)
* kernels, where a requeueing work item waiting for something to
* happen could deadlock with stop_machine as such work item could
* indefinitely requeue itself while all other CPUs are trapped in
* stop_machine.
* stop_machine. At the same time, report a quiescent RCU state so
* the same condition doesn't freeze RCU.
*/
cond_resched();
cond_resched_rcu_qs();
spin_lock_irq(&pool->lock);