forge/linux-pinenote
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Merge branches 'array.2015.05.27a', 'doc.2015.05.27a', 'fixes.2015.05.27a', 'hotplug.2015.05.27a', 'init.2015.05.27a', 'tiny.2015.05.27a' and 'torture.2015.05.27a' into HEAD

Browse source 
array.2015.05.27a:  Remove all uses of RCU-protected array indexes.
doc.2015.05.27a:  Docuemntation updates.
fixes.2015.05.27a:  Miscellaneous fixes.
hotplug.2015.05.27a:  CPU-hotplug updates.
init.2015.05.27a:  Initialization/Kconfig updates.
tiny.2015.05.27a:  Updates to Tiny RCU.
torture.2015.05.27a:  Torture-testing updates.
This commit is contained in:
Paul E. McKenney 2015-05-27 13:00:49 -07:00
commit 0868aa2216
49 changed files with 581 additions and 341 deletions
Download patch file Download diff file Expand all files Collapse all files

4
kernel/cpu.c
View file

@ -398,7 +398,6 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
err = __stop_machine(take_cpu_down, &tcd_param, cpumask_of(cpu));
if (err) {
/* CPU didn't die: tell everyone. Can't complain. */
smpboot_unpark_threads(cpu);
cpu_notify_nofail(CPU_DOWN_FAILED | mod, hcpu);
goto out_release;
}
@ -463,6 +462,7 @@ static int smpboot_thread_call(struct notifier_block *nfb,
switch (action & ~CPU_TASKS_FROZEN) {
case CPU_DOWN_FAILED:
case CPU_ONLINE:
smpboot_unpark_threads(cpu);
break;
@ -479,7 +479,7 @@ static struct notifier_block smpboot_thread_notifier = {
.priority = CPU_PRI_SMPBOOT,
};
void __cpuinit smpboot_thread_init(void)
void smpboot_thread_init(void)
{
register_cpu_notifier(&smpboot_thread_notifier);
}

2
kernel/events/ring_buffer.c
View file

@ -141,7 +141,7 @@ int perf_output_begin(struct perf_output_handle *handle,
perf_output_get_handle(handle);
do {
tail = ACCESS_ONCE(rb->user_page->data_tail);
tail = READ_ONCE_CTRL(rb->user_page->data_tail);
offset = head = local_read(&rb->head);
if (!rb->overwrite &&
unlikely(CIRC_SPACE(head, tail, perf_data_size(rb)) < size))

14
kernel/locking/locktorture.c
View file

@ -122,12 +122,12 @@ static int torture_lock_busted_write_lock(void)
static void torture_lock_busted_write_delay(struct torture_random_state *trsp)
{
const unsigned long longdelay_us = 100;
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_us)))
mdelay(longdelay_us);
(cxt.nrealwriters_stress * 2000 * longdelay_ms)))
mdelay(longdelay_ms);
#ifdef CONFIG_PREEMPT
if (!(torture_random(trsp) % (cxt.nrealwriters_stress * 20000)))
preempt_schedule(); /* Allow test to be preempted. */
@ -160,14 +160,14 @@ static int torture_spin_lock_write_lock(void) __acquires(torture_spinlock)
static void torture_spin_lock_write_delay(struct torture_random_state *trsp)
{
const unsigned long shortdelay_us = 2;
const unsigned long longdelay_us = 100;
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_us)))
mdelay(longdelay_us);
(cxt.nrealwriters_stress * 2000 * longdelay_ms)))
mdelay(longdelay_ms);
if (!(torture_random(trsp) %
(cxt.nrealwriters_stress * 2 * shortdelay_us)))
udelay(shortdelay_us);
@ -309,7 +309,7 @@ static int torture_rwlock_read_lock_irq(void) __acquires(torture_rwlock)
static void torture_rwlock_read_unlock_irq(void)
__releases(torture_rwlock)
{
write_unlock_irqrestore(&torture_rwlock, cxt.cur_ops->flags);
read_unlock_irqrestore(&torture_rwlock, cxt.cur_ops->flags);
}
static struct lock_torture_ops rw_lock_irq_ops = {

103
kernel/rcu/rcutorture.c
View file

@ -241,6 +241,7 @@ rcu_torture_free(struct rcu_torture *p)
struct rcu_torture_ops {
int ttype;
void (*init)(void);
void (*cleanup)(void);
int (*readlock)(void);
void (*read_delay)(struct torture_random_state *rrsp);
void (*readunlock)(int idx);
@ -477,10 +478,12 @@ static struct rcu_torture_ops rcu_busted_ops = {
*/
DEFINE_STATIC_SRCU(srcu_ctl);
static struct srcu_struct srcu_ctld;
static struct srcu_struct *srcu_ctlp = &srcu_ctl;
static int srcu_torture_read_lock(void) __acquires(&srcu_ctl)
static int srcu_torture_read_lock(void) __acquires(srcu_ctlp)
{
return srcu_read_lock(&srcu_ctl);
return srcu_read_lock(srcu_ctlp);
}
static void srcu_read_delay(struct torture_random_state *rrsp)
@ -499,49 +502,49 @@ static void srcu_read_delay(struct torture_random_state *rrsp)
rcu_read_delay(rrsp);
}
static void srcu_torture_read_unlock(int idx) __releases(&srcu_ctl)
static void srcu_torture_read_unlock(int idx) __releases(srcu_ctlp)
{
srcu_read_unlock(&srcu_ctl, idx);
srcu_read_unlock(srcu_ctlp, idx);
}
static unsigned long srcu_torture_completed(void)
{
return srcu_batches_completed(&srcu_ctl);
return srcu_batches_completed(srcu_ctlp);
}
static void srcu_torture_deferred_free(struct rcu_torture *rp)
{
call_srcu(&srcu_ctl, &rp->rtort_rcu, rcu_torture_cb);
call_srcu(srcu_ctlp, &rp->rtort_rcu, rcu_torture_cb);
}
static void srcu_torture_synchronize(void)
{
synchronize_srcu(&srcu_ctl);
synchronize_srcu(srcu_ctlp);
}
static void srcu_torture_call(struct rcu_head *head,
void (*func)(struct rcu_head *head))
{
call_srcu(&srcu_ctl, head, func);
call_srcu(srcu_ctlp, head, func);
}
static void srcu_torture_barrier(void)
{
srcu_barrier(&srcu_ctl);
srcu_barrier(srcu_ctlp);
}
static void srcu_torture_stats(void)
{
int cpu;
int idx = srcu_ctl.completed & 0x1;
int idx = srcu_ctlp->completed & 0x1;
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];
c0 = (long)per_cpu_ptr(srcu_ctlp->per_cpu_ref, cpu)->c[!idx];
c1 = (long)per_cpu_ptr(srcu_ctlp->per_cpu_ref, cpu)->c[idx];
pr_cont(" %d(%ld,%ld)", cpu, c0, c1);
}
pr_cont("\n");
@ -549,7 +552,7 @@ static void srcu_torture_stats(void)
static void srcu_torture_synchronize_expedited(void)
{
synchronize_srcu_expedited(&srcu_ctl);
synchronize_srcu_expedited(srcu_ctlp);
}
static struct rcu_torture_ops srcu_ops = {
@ -569,6 +572,38 @@ static struct rcu_torture_ops srcu_ops = {
.name = "srcu"
};
static void srcu_torture_init(void)
{
rcu_sync_torture_init();
WARN_ON(init_srcu_struct(&srcu_ctld));
srcu_ctlp = &srcu_ctld;
}
static void srcu_torture_cleanup(void)
{
cleanup_srcu_struct(&srcu_ctld);
srcu_ctlp = &srcu_ctl; /* In case of a later rcutorture run. */
}
/* As above, but dynamically allocated. */
static struct rcu_torture_ops srcud_ops = {
.ttype = SRCU_FLAVOR,
.init = srcu_torture_init,
.cleanup = srcu_torture_cleanup,
.readlock = srcu_torture_read_lock,
.read_delay = srcu_read_delay,
.readunlock = srcu_torture_read_unlock,
.started = NULL,
.completed = srcu_torture_completed,
.deferred_free = srcu_torture_deferred_free,
.sync = srcu_torture_synchronize,
.exp_sync = srcu_torture_synchronize_expedited,
.call = srcu_torture_call,
.cb_barrier = srcu_torture_barrier,
.stats = srcu_torture_stats,
.name = "srcud"
};
/*
* Definitions for sched torture testing.
*/
@ -672,8 +707,8 @@ static void rcu_torture_boost_cb(struct rcu_head *head)
struct rcu_boost_inflight *rbip =
container_of(head, struct rcu_boost_inflight, rcu);
smp_mb(); /* Ensure RCU-core accesses precede clearing ->inflight */
rbip->inflight = 0;
/* Ensure RCU-core accesses precede clearing ->inflight */
smp_store_release(&rbip->inflight, 0);
}
static int rcu_torture_boost(void *arg)
@ -710,9 +745,9 @@ static int rcu_torture_boost(void *arg)
call_rcu_time = jiffies;
while (ULONG_CMP_LT(jiffies, endtime)) {
/* If we don't have a callback in flight, post one. */
if (!rbi.inflight) {
smp_mb(); /* RCU core before ->inflight = 1. */
rbi.inflight = 1;
if (!smp_load_acquire(&rbi.inflight)) {
/* RCU core before ->inflight = 1. */
smp_store_release(&rbi.inflight, 1);
call_rcu(&rbi.rcu, rcu_torture_boost_cb);
if (jiffies - call_rcu_time >
test_boost_duration * HZ - HZ / 2) {
@ -751,11 +786,10 @@ checkwait: stutter_wait("rcu_torture_boost");
} while (!torture_must_stop());
/* Clean up and exit. */
while (!kthread_should_stop() || rbi.inflight) {
while (!kthread_should_stop() || smp_load_acquire(&rbi.inflight)) {
torture_shutdown_absorb("rcu_torture_boost");
schedule_timeout_uninterruptible(1);
}
smp_mb(); /* order accesses to ->inflight before stack-frame death. */
destroy_rcu_head_on_stack(&rbi.rcu);
torture_kthread_stopping("rcu_torture_boost");
return 0;
@ -1054,7 +1088,7 @@ static void rcu_torture_timer(unsigned long unused)
p = rcu_dereference_check(rcu_torture_current,
rcu_read_lock_bh_held() ||
rcu_read_lock_sched_held() ||
srcu_read_lock_held(&srcu_ctl));
srcu_read_lock_held(srcu_ctlp));
if (p == NULL) {
/* Leave because rcu_torture_writer is not yet underway */
cur_ops->readunlock(idx);
@ -1128,7 +1162,7 @@ rcu_torture_reader(void *arg)
p = rcu_dereference_check(rcu_torture_current,
rcu_read_lock_bh_held() ||
rcu_read_lock_sched_held() ||
srcu_read_lock_held(&srcu_ctl));
srcu_read_lock_held(srcu_ctlp));
if (p == NULL) {
/* Wait for rcu_torture_writer to get underway */
cur_ops->readunlock(idx);
@ -1413,12 +1447,15 @@ static int rcu_torture_barrier_cbs(void *arg)
do {
wait_event(barrier_cbs_wq[myid],
(newphase =
READ_ONCE(barrier_phase)) != lastphase ||
smp_load_acquire(&barrier_phase)) != lastphase ||
torture_must_stop());
lastphase = newphase;
smp_mb(); /* ensure barrier_phase load before ->call(). */
if (torture_must_stop())
break;
/*
* The above smp_load_acquire() ensures barrier_phase load
* is ordered before the folloiwng ->call().
*/
cur_ops->call(&rcu, rcu_torture_barrier_cbf);
if (atomic_dec_and_test(&barrier_cbs_count))
wake_up(&barrier_wq);
@ -1439,8 +1476,8 @@ static int rcu_torture_barrier(void *arg)
do {
atomic_set(&barrier_cbs_invoked, 0);
atomic_set(&barrier_cbs_count, n_barrier_cbs);
smp_mb(); /* Ensure barrier_phase after prior assignments. */
barrier_phase = !barrier_phase;
/* Ensure barrier_phase ordered after prior assignments. */
smp_store_release(&barrier_phase, !barrier_phase);
for (i = 0; i < n_barrier_cbs; i++)
wake_up(&barrier_cbs_wq[i]);
wait_event(barrier_wq,
@ -1588,10 +1625,14 @@ rcu_torture_cleanup(void)
rcutorture_booster_cleanup(i);
}
/* Wait for all RCU callbacks to fire. */
/*
* Wait for all RCU callbacks to fire, then do flavor-specific
* cleanup operations.
*/
if (cur_ops->cb_barrier != NULL)
cur_ops->cb_barrier();
if (cur_ops->cleanup != NULL)
cur_ops->cleanup();
rcu_torture_stats_print(); /* -After- the stats thread is stopped! */
@ -1668,8 +1709,8 @@ rcu_torture_init(void)
int cpu;
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
&rcu_ops, &rcu_bh_ops, &rcu_busted_ops, &srcu_ops, &srcud_ops,
&sched_ops, RCUTORTURE_TASKS_OPS
};
if (!torture_init_begin(torture_type, verbose, &torture_runnable))
@ -1701,7 +1742,7 @@ rcu_torture_init(void)
if (nreaders >= 0) {
nrealreaders = nreaders;
} else {
nrealreaders = num_online_cpus() - 1;
nrealreaders = num_online_cpus() - 2 - nreaders;
if (nrealreaders <= 0)
nrealreaders = 1;
}

38
kernel/rcu/tiny.c
View file

@ -49,39 +49,6 @@ static void __call_rcu(struct rcu_head *head,
#include "tiny_plugin.h"
/*
* Enter idle, which is an extended quiescent state if we have fully
* entered that mode.
*/
void rcu_idle_enter(void)
{
}
EXPORT_SYMBOL_GPL(rcu_idle_enter);
/*
* Exit an interrupt handler towards idle.
*/
void rcu_irq_exit(void)
{
}
EXPORT_SYMBOL_GPL(rcu_irq_exit);
/*
* Exit idle, so that we are no longer in an extended quiescent state.
*/
void rcu_idle_exit(void)
{
}
EXPORT_SYMBOL_GPL(rcu_idle_exit);
/*
* Enter an interrupt handler, moving away from idle.
*/
void rcu_irq_enter(void)
{
}
EXPORT_SYMBOL_GPL(rcu_irq_enter);
#if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE)
/*
@ -170,6 +137,11 @@ static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp)
/* Move the ready-to-invoke callbacks to a local list. */
local_irq_save(flags);
if (rcp->donetail == &rcp->rcucblist) {
/* No callbacks ready, so just leave. */
local_irq_restore(flags);
return;
}
RCU_TRACE(trace_rcu_batch_start(rcp->name, 0, rcp->qlen, -1));
list = rcp->rcucblist;
rcp->rcucblist = *rcp->donetail;

181
kernel/rcu/tree.c
View file

@ -91,7 +91,7 @@ static const char *tp_##sname##_varname __used __tracepoint_string = sname##_var
#define RCU_STATE_INITIALIZER(sname, sabbr, cr) \
DEFINE_RCU_TPS(sname) \
DEFINE_PER_CPU_SHARED_ALIGNED(struct rcu_data, sname##_data); \
static DEFINE_PER_CPU_SHARED_ALIGNED(struct rcu_data, sname##_data); \
struct rcu_state sname##_state = { \
.level = { &sname##_state.node[0] }, \
.rda = &sname##_data, \
@ -110,11 +110,18 @@ struct rcu_state sname##_state = { \
RCU_STATE_INITIALIZER(rcu_sched, 's', call_rcu_sched);
RCU_STATE_INITIALIZER(rcu_bh, 'b', call_rcu_bh);
static struct rcu_state *rcu_state_p;
static struct rcu_state *const rcu_state_p;
static struct rcu_data __percpu *const rcu_data_p;
LIST_HEAD(rcu_struct_flavors);
/* Increase (but not decrease) the CONFIG_RCU_FANOUT_LEAF at boot time. */
static int rcu_fanout_leaf = CONFIG_RCU_FANOUT_LEAF;
/* Dump rcu_node combining tree at boot to verify correct setup. */
static bool dump_tree;
module_param(dump_tree, bool, 0444);
/* Control rcu_node-tree auto-balancing at boot time. */
static bool rcu_fanout_exact;
module_param(rcu_fanout_exact, bool, 0444);
/* Increase (but not decrease) the RCU_FANOUT_LEAF at boot time. */
static int rcu_fanout_leaf = RCU_FANOUT_LEAF;
module_param(rcu_fanout_leaf, int, 0444);
int rcu_num_lvls __read_mostly = RCU_NUM_LVLS;
static int num_rcu_lvl[] = { /* Number of rcu_nodes at specified level. */
@ -159,17 +166,46 @@ static void invoke_rcu_core(void);
static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp);
/* rcuc/rcub kthread realtime priority */
#ifdef CONFIG_RCU_KTHREAD_PRIO
static int kthread_prio = CONFIG_RCU_KTHREAD_PRIO;
#else /* #ifdef CONFIG_RCU_KTHREAD_PRIO */
static int kthread_prio = IS_ENABLED(CONFIG_RCU_BOOST) ? 1 : 0;
#endif /* #else #ifdef CONFIG_RCU_KTHREAD_PRIO */
module_param(kthread_prio, int, 0644);
/* Delay in jiffies for grace-period initialization delays, debug only. */
#ifdef CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT
static int gp_preinit_delay = CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT_DELAY;
module_param(gp_preinit_delay, int, 0644);
#else /* #ifdef CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT */
static const int gp_preinit_delay;
#endif /* #else #ifdef CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT */
#ifdef CONFIG_RCU_TORTURE_TEST_SLOW_INIT
static int gp_init_delay = CONFIG_RCU_TORTURE_TEST_SLOW_INIT_DELAY;
module_param(gp_init_delay, int, 0644);
#else /* #ifdef CONFIG_RCU_TORTURE_TEST_SLOW_INIT */
static const int gp_init_delay;
#endif /* #else #ifdef CONFIG_RCU_TORTURE_TEST_SLOW_INIT */
#define PER_RCU_NODE_PERIOD 10 /* Number of grace periods between delays. */
#ifdef CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP
static int gp_cleanup_delay = CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP_DELAY;
module_param(gp_cleanup_delay, int, 0644);
#else /* #ifdef CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP */
static const int gp_cleanup_delay;
#endif /* #else #ifdef CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP */
/*
* Number of grace periods between delays, normalized by the duration of
* the delay. The longer the the delay, the more the grace periods between
* each delay. The reason for this normalization is that it means that,
* for non-zero delays, the overall slowdown of grace periods is constant
* regardless of the duration of the delay. This arrangement balances
* the need for long delays to increase some race probabilities with the
* need for fast grace periods to increase other race probabilities.
*/
#define PER_RCU_NODE_PERIOD 3 /* Number of grace periods between delays. */
/*
* Track the rcutorture test sequence number and the update version
@ -585,7 +621,8 @@ static void rcu_eqs_enter_common(long long oldval, bool user)
struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
trace_rcu_dyntick(TPS("Start"), oldval, rdtp->dynticks_nesting);
if (!user && !is_idle_task(current)) {
if (IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
!user && !is_idle_task(current)) {
struct task_struct *idle __maybe_unused =
idle_task(smp_processor_id());
@ -604,7 +641,8 @@ static void rcu_eqs_enter_common(long long oldval, bool user)
smp_mb__before_atomic(); /* See above. */
atomic_inc(&rdtp->dynticks);
smp_mb__after_atomic(); /* Force ordering with next sojourn. */
WARN_ON_ONCE(atomic_read(&rdtp->dynticks) & 0x1);
WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
atomic_read(&rdtp->dynticks) & 0x1);
rcu_dynticks_task_enter();
/*
@ -630,7 +668,8 @@ static void rcu_eqs_enter(bool user)
rdtp = this_cpu_ptr(&rcu_dynticks);
oldval = rdtp->dynticks_nesting;
WARN_ON_ONCE((oldval & DYNTICK_TASK_NEST_MASK) == 0);
WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
(oldval & DYNTICK_TASK_NEST_MASK) == 0);
if ((oldval & DYNTICK_TASK_NEST_MASK) == DYNTICK_TASK_NEST_VALUE) {
rdtp->dynticks_nesting = 0;
rcu_eqs_enter_common(oldval, user);
@ -703,7 +742,8 @@ void rcu_irq_exit(void)
rdtp = this_cpu_ptr(&rcu_dynticks);
oldval = rdtp->dynticks_nesting;
rdtp->dynticks_nesting--;
WARN_ON_ONCE(rdtp->dynticks_nesting < 0);
WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
rdtp->dynticks_nesting < 0);
if (rdtp->dynticks_nesting)
trace_rcu_dyntick(TPS("--="), oldval, rdtp->dynticks_nesting);
else
@ -728,10 +768,12 @@ static void rcu_eqs_exit_common(long long oldval, int user)
atomic_inc(&rdtp->dynticks);
/* CPUs seeing atomic_inc() must see later RCU read-side crit sects */
smp_mb__after_atomic(); /* See above. */
WARN_ON_ONCE(!(atomic_read(&rdtp->dynticks) & 0x1));
WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
!(atomic_read(&rdtp->dynticks) & 0x1));
rcu_cleanup_after_idle();
trace_rcu_dyntick(TPS("End"), oldval, rdtp->dynticks_nesting);
if (!user && !is_idle_task(current)) {
if (IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
!user && !is_idle_task(current)) {
struct task_struct *idle __maybe_unused =
idle_task(smp_processor_id());
@ -755,7 +797,7 @@ static void rcu_eqs_exit(bool user)
rdtp = this_cpu_ptr(&rcu_dynticks);
oldval = rdtp->dynticks_nesting;
WARN_ON_ONCE(oldval < 0);
WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && oldval < 0);
if (oldval & DYNTICK_TASK_NEST_MASK) {
rdtp->dynticks_nesting += DYNTICK_TASK_NEST_VALUE;
} else {
@ -828,7 +870,8 @@ void rcu_irq_enter(void)
rdtp = this_cpu_ptr(&rcu_dynticks);
oldval = rdtp->dynticks_nesting;
rdtp->dynticks_nesting++;
WARN_ON_ONCE(rdtp->dynticks_nesting == 0);
WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
rdtp->dynticks_nesting == 0);
if (oldval)
trace_rcu_dyntick(TPS("++="), oldval, rdtp->dynticks_nesting);
else
@ -1135,8 +1178,9 @@ static void rcu_check_gp_kthread_starvation(struct rcu_state *rsp)
j = jiffies;
gpa = READ_ONCE(rsp->gp_activity);
if (j - gpa > 2 * HZ)
pr_err("%s kthread starved for %ld jiffies!\n",
rsp->name, j - gpa);
pr_err("%s kthread starved for %ld jiffies! g%lu c%lu f%#x\n",
rsp->name, j - gpa,
rsp->gpnum, rsp->completed, rsp->gp_flags);
}
/*
@ -1732,6 +1776,13 @@ static void note_gp_changes(struct rcu_state *rsp, struct rcu_data *rdp)
rcu_gp_kthread_wake(rsp);
}
static void rcu_gp_slow(struct rcu_state *rsp, int delay)
{
if (delay > 0 &&
!(rsp->gpnum % (rcu_num_nodes * PER_RCU_NODE_PERIOD * delay)))
schedule_timeout_uninterruptible(delay);
}
/*
* Initialize a new grace period. Return 0 if no grace period required.
*/
@ -1774,6 +1825,7 @@ static int rcu_gp_init(struct rcu_state *rsp)
* will handle subsequent offline CPUs.
*/
rcu_for_each_leaf_node(rsp, rnp) {
rcu_gp_slow(rsp, gp_preinit_delay);
raw_spin_lock_irq(&rnp->lock);
smp_mb__after_unlock_lock();
if (rnp->qsmaskinit == rnp->qsmaskinitnext &&
@ -1830,6 +1882,7 @@ static int rcu_gp_init(struct rcu_state *rsp)
* process finishes, because this kthread handles both.
*/
rcu_for_each_node_breadth_first(rsp, rnp) {
rcu_gp_slow(rsp, gp_init_delay);
raw_spin_lock_irq(&rnp->lock);
smp_mb__after_unlock_lock();
rdp = this_cpu_ptr(rsp->rda);
@ -1847,9 +1900,6 @@ static int rcu_gp_init(struct rcu_state *rsp)
raw_spin_unlock_irq(&rnp->lock);
cond_resched_rcu_qs();
WRITE_ONCE(rsp->gp_activity, jiffies);
if (gp_init_delay > 0 &&
!(rsp->gpnum % (rcu_num_nodes * PER_RCU_NODE_PERIOD)))
schedule_timeout_uninterruptible(gp_init_delay);
}
return 1;
@ -1944,6 +1994,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
raw_spin_unlock_irq(&rnp->lock);
cond_resched_rcu_qs();
WRITE_ONCE(rsp->gp_activity, jiffies);
rcu_gp_slow(rsp, gp_cleanup_delay);
}
rnp = rcu_get_root(rsp);
raw_spin_lock_irq(&rnp->lock);
@ -2138,6 +2189,7 @@ static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags)
__releases(rcu_get_root(rsp)->lock)
{
WARN_ON_ONCE(!rcu_gp_in_progress(rsp));
WRITE_ONCE(rsp->gp_flags, READ_ONCE(rsp->gp_flags) | RCU_GP_FLAG_FQS);
raw_spin_unlock_irqrestore(&rcu_get_root(rsp)->lock, flags);
rcu_gp_kthread_wake(rsp);
}
@ -2335,8 +2387,6 @@ rcu_check_quiescent_state(struct rcu_state *rsp, struct rcu_data *rdp)
rcu_report_qs_rdp(rdp->cpu, rsp, rdp);
}
#ifdef CONFIG_HOTPLUG_CPU
/*
* Send the specified CPU's RCU callbacks to the orphanage. The
* specified CPU must be offline, and the caller must hold the
@ -2347,7 +2397,7 @@ rcu_send_cbs_to_orphanage(int cpu, struct rcu_state *rsp,
struct rcu_node *rnp, struct rcu_data *rdp)
{
/* No-CBs CPUs do not have orphanable callbacks. */
if (rcu_is_nocb_cpu(rdp->cpu))
if (!IS_ENABLED(CONFIG_HOTPLUG_CPU) || rcu_is_nocb_cpu(rdp->cpu))
return;
/*
@ -2406,7 +2456,8 @@ static void rcu_adopt_orphan_cbs(struct rcu_state *rsp, unsigned long flags)
struct rcu_data *rdp = raw_cpu_ptr(rsp->rda);
/* No-CBs CPUs are handled specially. */
if (rcu_nocb_adopt_orphan_cbs(rsp, rdp, flags))
if (!IS_ENABLED(CONFIG_HOTPLUG_CPU) ||
rcu_nocb_adopt_orphan_cbs(rsp, rdp, flags))
return;
/* Do the accounting first. */
@ -2453,6 +2504,9 @@ static void rcu_cleanup_dying_cpu(struct rcu_state *rsp)
RCU_TRACE(struct rcu_data *rdp = this_cpu_ptr(rsp->rda));
RCU_TRACE(struct rcu_node *rnp = rdp->mynode);
if (!IS_ENABLED(CONFIG_HOTPLUG_CPU))
return;
RCU_TRACE(mask = rdp->grpmask);
trace_rcu_grace_period(rsp->name,
rnp->gpnum + 1 - !!(rnp->qsmask & mask),
@ -2481,7 +2535,8 @@ static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf)
long mask;
struct rcu_node *rnp = rnp_leaf;
if (rnp->qsmaskinit || rcu_preempt_has_tasks(rnp))
if (!IS_ENABLED(CONFIG_HOTPLUG_CPU) ||
rnp->qsmaskinit || rcu_preempt_has_tasks(rnp))
return;
for (;;) {
mask = rnp->grpmask;
@ -2512,6 +2567,9 @@ static void rcu_cleanup_dying_idle_cpu(int cpu, struct rcu_state *rsp)
struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
struct rcu_node *rnp = rdp->mynode; /* Outgoing CPU's rdp & rnp. */
if (!IS_ENABLED(CONFIG_HOTPLUG_CPU))
return;
/* Remove outgoing CPU from mask in the leaf rcu_node structure. */
mask = rdp->grpmask;
raw_spin_lock_irqsave(&rnp->lock, flags);
@ -2533,6 +2591,9 @@ static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp)
struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
struct rcu_node *rnp = rdp->mynode; /* Outgoing CPU's rdp & rnp. */
if (!IS_ENABLED(CONFIG_HOTPLUG_CPU))
return;
/* Adjust any no-longer-needed kthreads. */
rcu_boost_kthread_setaffinity(rnp, -1);
@ -2547,26 +2608,6 @@ static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp)
cpu, rdp->qlen, rdp->nxtlist);
}
#else /* #ifdef CONFIG_HOTPLUG_CPU */
static void rcu_cleanup_dying_cpu(struct rcu_state *rsp)
{
}
static void __maybe_unused rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf)
{
}
static void rcu_cleanup_dying_idle_cpu(int cpu, struct rcu_state *rsp)
{
}
static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp)
{
}
#endif /* #else #ifdef CONFIG_HOTPLUG_CPU */
/*
* Invoke any RCU callbacks that have made it to the end of their grace
* period. Thottle as specified by rdp->blimit.
@ -2731,10 +2772,6 @@ static void force_qs_rnp(struct rcu_state *rsp,
mask = 0;
raw_spin_lock_irqsave(&rnp->lock, flags);
smp_mb__after_unlock_lock();
if (!rcu_gp_in_progress(rsp)) {
raw_spin_unlock_irqrestore(&rnp->lock, flags);
return;
}
if (rnp->qsmask == 0) {
if (rcu_state_p == &rcu_sched_state ||
rsp != rcu_state_p ||
@ -2764,8 +2801,6 @@ static void force_qs_rnp(struct rcu_state *rsp,
bit = 1;
for (; cpu <= rnp->grphi; cpu++, bit <<= 1) {
if ((rnp->qsmask & bit) != 0) {
if ((rnp->qsmaskinit & bit) == 0)
*isidle = false; /* Pending hotplug. */
if (f(per_cpu_ptr(rsp->rda, cpu), isidle, maxj))
mask |= bit;
}
@ -3287,7 +3322,7 @@ void synchronize_sched_expedited(void)
if (ULONG_CMP_GE((ulong)atomic_long_read(&rsp->expedited_start),
(ulong)atomic_long_read(&rsp->expedited_done) +
ULONG_MAX / 8)) {
synchronize_sched();
wait_rcu_gp(call_rcu_sched);
atomic_long_inc(&rsp->expedited_wrap);
return;
}
@ -3493,7 +3528,7 @@ static int rcu_pending(void)
* non-NULL, store an indication of whether all callbacks are lazy.
* (If there are no callbacks, all of them are deemed to be lazy.)
*/
static int __maybe_unused rcu_cpu_has_callbacks(bool *all_lazy)
static bool __maybe_unused rcu_cpu_has_callbacks(bool *all_lazy)
{
bool al = true;
bool hc = false;
@ -3780,7 +3815,7 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp)
rdp->gpnum = rnp->completed; /* Make CPU later note any new GP. */
rdp->completed = rnp->completed;
rdp->passed_quiesce = false;
rdp->rcu_qs_ctr_snap = __this_cpu_read(rcu_qs_ctr);
rdp->rcu_qs_ctr_snap = per_cpu(rcu_qs_ctr, cpu);
rdp->qs_pending = false;
trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpuonl"));
raw_spin_unlock_irqrestore(&rnp->lock, flags);
@ -3924,16 +3959,16 @@ void rcu_scheduler_starting(void)
/*
* Compute the per-level fanout, either using the exact fanout specified
* or balancing the tree, depending on CONFIG_RCU_FANOUT_EXACT.
* or balancing the tree, depending on the rcu_fanout_exact boot parameter.
*/
static void __init rcu_init_levelspread(struct rcu_state *rsp)
{
int i;
if (IS_ENABLED(CONFIG_RCU_FANOUT_EXACT)) {
if (rcu_fanout_exact) {
rsp->levelspread[rcu_num_lvls - 1] = rcu_fanout_leaf;
for (i = rcu_num_lvls - 2; i >= 0; i--)
rsp->levelspread[i] = CONFIG_RCU_FANOUT;
rsp->levelspread[i] = RCU_FANOUT;
} else {
int ccur;
int cprv;
@ -3971,9 +4006,9 @@ static void __init rcu_init_one(struct rcu_state *rsp,
BUILD_BUG_ON(MAX_RCU_LVLS > ARRAY_SIZE(buf)); /* Fix buf[] init! */
/* Silence gcc 4.8 warning about array index out of range. */
if (rcu_num_lvls > RCU_NUM_LVLS)
panic("rcu_init_one: rcu_num_lvls overflow");
/* Silence gcc 4.8 false positive about array index out of range. */
if (rcu_num_lvls <= 0 || rcu_num_lvls > RCU_NUM_LVLS)
panic("rcu_init_one: rcu_num_lvls out of range");
/* Initialize the level-tracking arrays. */
@ -4059,7 +4094,7 @@ static void __init rcu_init_geometry(void)
jiffies_till_next_fqs = d;
/* If the compile-time values are accurate, just leave. */
if (rcu_fanout_leaf == CONFIG_RCU_FANOUT_LEAF &&
if (rcu_fanout_leaf == RCU_FANOUT_LEAF &&
nr_cpu_ids == NR_CPUS)
return;
pr_info("RCU: Adjusting geometry for rcu_fanout_leaf=%d, nr_cpu_ids=%d\n",
@ -4073,7 +4108,7 @@ static void __init rcu_init_geometry(void)
rcu_capacity[0] = 1;
rcu_capacity[1] = rcu_fanout_leaf;
for (i = 2; i <= MAX_RCU_LVLS; i++)
rcu_capacity[i] = rcu_capacity[i - 1] * CONFIG_RCU_FANOUT;
rcu_capacity[i] = rcu_capacity[i - 1] * RCU_FANOUT;
/*
* The boot-time rcu_fanout_leaf parameter is only permitted
@ -4083,7 +4118,7 @@ static void __init rcu_init_geometry(void)
* the configured number of CPUs. Complain and fall back to the
* compile-time values if these limits are exceeded.
*/
if (rcu_fanout_leaf < CONFIG_RCU_FANOUT_LEAF ||
if (rcu_fanout_leaf < RCU_FANOUT_LEAF ||
rcu_fanout_leaf > sizeof(unsigned long) * 8 ||
n > rcu_capacity[MAX_RCU_LVLS]) {
WARN_ON(1);
@ -4109,6 +4144,28 @@ static void __init rcu_init_geometry(void)
rcu_num_nodes -= n;
}
/*
* Dump out the structure of the rcu_node combining tree associated
* with the rcu_state structure referenced by rsp.
*/
static void __init rcu_dump_rcu_node_tree(struct rcu_state *rsp)
{
int level = 0;
struct rcu_node *rnp;
pr_info("rcu_node tree layout dump\n");
pr_info(" ");
rcu_for_each_node_breadth_first(rsp, rnp) {
if (rnp->level != level) {
pr_cont("\n");
pr_info(" ");
level = rnp->level;
}
pr_cont("%d:%d ^%d ", rnp->grplo, rnp->grphi, rnp->grpnum);
}
pr_cont("\n");
}
void __init rcu_init(void)
{
int cpu;
@ -4119,6 +4176,8 @@ void __init rcu_init(void)
rcu_init_geometry();
rcu_init_one(&rcu_bh_state, &rcu_bh_data);
rcu_init_one(&rcu_sched_state, &rcu_sched_data);
if (dump_tree)
rcu_dump_rcu_node_tree(&rcu_sched_state);
__rcu_init_preempt();
open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);

35
kernel/rcu/tree.h
View file

@ -35,11 +35,33 @@
* In practice, this did work well going from three levels to four.
* Of course, your mileage may vary.
*/
#define MAX_RCU_LVLS 4
#define RCU_FANOUT_1 (CONFIG_RCU_FANOUT_LEAF)
#define RCU_FANOUT_2 (RCU_FANOUT_1 * CONFIG_RCU_FANOUT)
#define RCU_FANOUT_3 (RCU_FANOUT_2 * CONFIG_RCU_FANOUT)
#define RCU_FANOUT_4 (RCU_FANOUT_3 * CONFIG_RCU_FANOUT)
#ifdef CONFIG_RCU_FANOUT
#define RCU_FANOUT CONFIG_RCU_FANOUT
#else /* #ifdef CONFIG_RCU_FANOUT */
# ifdef CONFIG_64BIT
# define RCU_FANOUT 64
# else
# define RCU_FANOUT 32
# endif
#endif /* #else #ifdef CONFIG_RCU_FANOUT */
#ifdef CONFIG_RCU_FANOUT_LEAF
#define RCU_FANOUT_LEAF CONFIG_RCU_FANOUT_LEAF
#else /* #ifdef CONFIG_RCU_FANOUT_LEAF */
# ifdef CONFIG_64BIT
# define RCU_FANOUT_LEAF 64
# else
# define RCU_FANOUT_LEAF 32
# endif
#endif /* #else #ifdef CONFIG_RCU_FANOUT_LEAF */
#define RCU_FANOUT_1 (RCU_FANOUT_LEAF)
#define RCU_FANOUT_2 (RCU_FANOUT_1 * RCU_FANOUT)
#define RCU_FANOUT_3 (RCU_FANOUT_2 * RCU_FANOUT)
#define RCU_FANOUT_4 (RCU_FANOUT_3 * RCU_FANOUT)
#if NR_CPUS <= RCU_FANOUT_1
# define RCU_NUM_LVLS 1
@ -170,7 +192,6 @@ struct rcu_node {
/* if there is no such task. If there */
/* is no current expedited grace period, */
/* then there can cannot be any such task. */
#ifdef CONFIG_RCU_BOOST
struct list_head *boost_tasks;
/* Pointer to first task that needs to be */
/* priority boosted, or NULL if no priority */
@ -208,7 +229,6 @@ struct rcu_node {
unsigned long n_balk_nos;
/* Refused to boost: not sure why, though. */
/* This can happen due to race conditions. */
#endif /* #ifdef CONFIG_RCU_BOOST */
#ifdef CONFIG_RCU_NOCB_CPU
wait_queue_head_t nocb_gp_wq[2];
/* Place for rcu_nocb_kthread() to wait GP. */
@ -519,14 +539,11 @@ extern struct list_head rcu_struct_flavors;
* RCU implementation internal declarations:
*/
extern struct rcu_state rcu_sched_state;
DECLARE_PER_CPU(struct rcu_data, rcu_sched_data);
extern struct rcu_state rcu_bh_state;
DECLARE_PER_CPU(struct rcu_data, rcu_bh_data);
#ifdef CONFIG_PREEMPT_RCU
extern struct rcu_state rcu_preempt_state;
DECLARE_PER_CPU(struct rcu_data, rcu_preempt_data);
#endif /* #ifdef CONFIG_PREEMPT_RCU */
#ifdef CONFIG_RCU_BOOST

123
kernel/rcu/tree_plugin.h
View file

@ -43,7 +43,17 @@ DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_status);
DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_loops);
DEFINE_PER_CPU(char, rcu_cpu_has_work);
#endif /* #ifdef CONFIG_RCU_BOOST */
#else /* #ifdef CONFIG_RCU_BOOST */
/*
* Some architectures do not define rt_mutexes, but if !CONFIG_RCU_BOOST,
* all uses are in dead code. Provide a definition to keep the compiler
* happy, but add WARN_ON_ONCE() to complain if used in the wrong place.
* This probably needs to be excluded from -rt builds.
*/
#define rt_mutex_owner(a) ({ WARN_ON_ONCE(1); NULL; })
#endif /* #else #ifdef CONFIG_RCU_BOOST */
#ifdef CONFIG_RCU_NOCB_CPU
static cpumask_var_t rcu_nocb_mask; /* CPUs to have callbacks offloaded. */
@ -60,11 +70,11 @@ static void __init rcu_bootup_announce_oddness(void)
{
if (IS_ENABLED(CONFIG_RCU_TRACE))
pr_info("\tRCU debugfs-based tracing is enabled.\n");
if ((IS_ENABLED(CONFIG_64BIT) && CONFIG_RCU_FANOUT != 64) ||
(!IS_ENABLED(CONFIG_64BIT) && CONFIG_RCU_FANOUT != 32))
if ((IS_ENABLED(CONFIG_64BIT) && RCU_FANOUT != 64) ||
(!IS_ENABLED(CONFIG_64BIT) && RCU_FANOUT != 32))
pr_info("\tCONFIG_RCU_FANOUT set to non-default value of %d\n",
CONFIG_RCU_FANOUT);
if (IS_ENABLED(CONFIG_RCU_FANOUT_EXACT))
RCU_FANOUT);
if (rcu_fanout_exact)
pr_info("\tHierarchical RCU autobalancing is disabled.\n");
if (IS_ENABLED(CONFIG_RCU_FAST_NO_HZ))
pr_info("\tRCU dyntick-idle grace-period acceleration is enabled.\n");
@ -76,10 +86,10 @@ static void __init rcu_bootup_announce_oddness(void)
pr_info("\tAdditional per-CPU info printed with stalls.\n");
if (NUM_RCU_LVL_4 != 0)
pr_info("\tFour-level hierarchy is enabled.\n");
if (CONFIG_RCU_FANOUT_LEAF != 16)
if (RCU_FANOUT_LEAF != 16)
pr_info("\tBuild-time adjustment of leaf fanout to %d.\n",
CONFIG_RCU_FANOUT_LEAF);
if (rcu_fanout_leaf != CONFIG_RCU_FANOUT_LEAF)
RCU_FANOUT_LEAF);
if (rcu_fanout_leaf != RCU_FANOUT_LEAF)
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);
@ -90,7 +100,8 @@ static void __init rcu_bootup_announce_oddness(void)
#ifdef CONFIG_PREEMPT_RCU
RCU_STATE_INITIALIZER(rcu_preempt, 'p', call_rcu);
static struct rcu_state *rcu_state_p = &rcu_preempt_state;
static struct rcu_state *const rcu_state_p = &rcu_preempt_state;
static struct rcu_data __percpu *const rcu_data_p = &rcu_preempt_data;
static int rcu_preempted_readers_exp(struct rcu_node *rnp);
static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
@ -116,11 +127,11 @@ static void __init rcu_bootup_announce(void)
*/
static void rcu_preempt_qs(void)
{
if (!__this_cpu_read(rcu_preempt_data.passed_quiesce)) {
if (!__this_cpu_read(rcu_data_p->passed_quiesce)) {
trace_rcu_grace_period(TPS("rcu_preempt"),
__this_cpu_read(rcu_preempt_data.gpnum),
__this_cpu_read(rcu_data_p->gpnum),
TPS("cpuqs"));
__this_cpu_write(rcu_preempt_data.passed_quiesce, 1);
__this_cpu_write(rcu_data_p->passed_quiesce, 1);
barrier(); /* Coordinate with rcu_preempt_check_callbacks(). */
current->rcu_read_unlock_special.b.need_qs = false;
}
@ -150,7 +161,7 @@ static void rcu_preempt_note_context_switch(void)
!t->rcu_read_unlock_special.b.blocked) {
/* Possibly blocking in an RCU read-side critical section. */
rdp = this_cpu_ptr(rcu_preempt_state.rda);
rdp = this_cpu_ptr(rcu_state_p->rda);
rnp = rdp->mynode;
raw_spin_lock_irqsave(&rnp->lock, flags);
smp_mb__after_unlock_lock();
@ -180,10 +191,9 @@ static void rcu_preempt_note_context_switch(void)
if ((rnp->qsmask & rdp->grpmask) && rnp->gp_tasks != NULL) {
list_add(&t->rcu_node_entry, rnp->gp_tasks->prev);
rnp->gp_tasks = &t->rcu_node_entry;
#ifdef CONFIG_RCU_BOOST
if (rnp->boost_tasks != NULL)
if (IS_ENABLED(CONFIG_RCU_BOOST) &&
rnp->boost_tasks != NULL)
rnp->boost_tasks = rnp->gp_tasks;
#endif /* #ifdef CONFIG_RCU_BOOST */
} else {
list_add(&t->rcu_node_entry, &rnp->blkd_tasks);
if (rnp->qsmask & rdp->grpmask)
@ -263,9 +273,7 @@ void rcu_read_unlock_special(struct task_struct *t)
bool empty_exp_now;
unsigned long flags;
struct list_head *np;
#ifdef CONFIG_RCU_BOOST
bool drop_boost_mutex = false;
#endif /* #ifdef CONFIG_RCU_BOOST */
struct rcu_node *rnp;
union rcu_special special;
@ -307,9 +315,11 @@ void rcu_read_unlock_special(struct task_struct *t)
t->rcu_read_unlock_special.b.blocked = false;
/*
* Remove this task from the list it blocked on. The
* task can migrate while we acquire the lock, but at
* most one time. So at most two passes through loop.
* Remove this task from the list it blocked on. The task
* now remains queued on the rcu_node corresponding to
* the CPU it first blocked on, so the first attempt to
* acquire the task's rcu_node's ->lock will succeed.
* Keep the loop and add a WARN_ON() out of sheer paranoia.
*/
for (;;) {
rnp = t->rcu_blocked_node;
@ -317,6 +327,7 @@ void rcu_read_unlock_special(struct task_struct *t)
smp_mb__after_unlock_lock();
if (rnp == t->rcu_blocked_node)
break;
WARN_ON_ONCE(1);
raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
}
empty_norm = !rcu_preempt_blocked_readers_cgp(rnp);
@ -331,12 +342,12 @@ void rcu_read_unlock_special(struct task_struct *t)
rnp->gp_tasks = np;
if (&t->rcu_node_entry == rnp->exp_tasks)
rnp->exp_tasks = np;
#ifdef CONFIG_RCU_BOOST
if (&t->rcu_node_entry == rnp->boost_tasks)
rnp->boost_tasks = np;
/* Snapshot ->boost_mtx ownership with rcu_node lock held. */
drop_boost_mutex = rt_mutex_owner(&rnp->boost_mtx) == t;
#endif /* #ifdef CONFIG_RCU_BOOST */
if (IS_ENABLED(CONFIG_RCU_BOOST)) {
if (&t->rcu_node_entry == rnp->boost_tasks)
rnp->boost_tasks = np;
/* Snapshot ->boost_mtx ownership w/rnp->lock held. */
drop_boost_mutex = rt_mutex_owner(&rnp->boost_mtx) == t;
}
/*
* If this was the last task on the current list, and if
@ -353,24 +364,21 @@ void rcu_read_unlock_special(struct task_struct *t)
rnp->grplo,
rnp->grphi,
!!rnp->gp_tasks);
rcu_report_unblock_qs_rnp(&rcu_preempt_state,
rnp, flags);
rcu_report_unblock_qs_rnp(rcu_state_p, rnp, flags);
} else {
raw_spin_unlock_irqrestore(&rnp->lock, flags);
}
#ifdef CONFIG_RCU_BOOST
/* Unboost if we were boosted. */
if (drop_boost_mutex)
if (IS_ENABLED(CONFIG_RCU_BOOST) && drop_boost_mutex)
rt_mutex_unlock(&rnp->boost_mtx);
#endif /* #ifdef CONFIG_RCU_BOOST */
/*
* If this was the last task on the expedited lists,
* then we need to report up the rcu_node hierarchy.
*/
if (!empty_exp && empty_exp_now)
rcu_report_exp_rnp(&rcu_preempt_state, rnp, true);
rcu_report_exp_rnp(rcu_state_p, rnp, true);
} else {
local_irq_restore(flags);
}
@ -390,7 +398,7 @@ static void rcu_print_detail_task_stall_rnp(struct rcu_node *rnp)
raw_spin_unlock_irqrestore(&rnp->lock, flags);
return;
}
t = list_entry(rnp->gp_tasks,
t = list_entry(rnp->gp_tasks->prev,
struct task_struct, rcu_node_entry);
list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry)
sched_show_task(t);
@ -447,7 +455,7 @@ static int rcu_print_task_stall(struct rcu_node *rnp)
if (!rcu_preempt_blocked_readers_cgp(rnp))
return 0;
rcu_print_task_stall_begin(rnp);
t = list_entry(rnp->gp_tasks,
t = list_entry(rnp->gp_tasks->prev,
struct task_struct, rcu_node_entry);
list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry) {
pr_cont(" P%d", t->pid);
@ -491,8 +499,8 @@ static void rcu_preempt_check_callbacks(void)
return;
}
if (t->rcu_read_lock_nesting > 0 &&
__this_cpu_read(rcu_preempt_data.qs_pending) &&
!__this_cpu_read(rcu_preempt_data.passed_quiesce))
__this_cpu_read(rcu_data_p->qs_pending) &&
!__this_cpu_read(rcu_data_p->passed_quiesce))
t->rcu_read_unlock_special.b.need_qs = true;
}
@ -500,7 +508,7 @@ static void rcu_preempt_check_callbacks(void)
static void rcu_preempt_do_callbacks(void)
{
rcu_do_batch(&rcu_preempt_state, this_cpu_ptr(&rcu_preempt_data));
rcu_do_batch(rcu_state_p, this_cpu_ptr(rcu_data_p));
}
#endif /* #ifdef CONFIG_RCU_BOOST */
@ -510,7 +518,7 @@ static void rcu_preempt_do_callbacks(void)
*/
void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
{
__call_rcu(head, func, &rcu_preempt_state, -1, 0);
__call_rcu(head, func, rcu_state_p, -1, 0);
}
EXPORT_SYMBOL_GPL(call_rcu);
@ -711,7 +719,7 @@ sync_rcu_preempt_exp_init2(struct rcu_state *rsp, struct rcu_node *rnp)
void synchronize_rcu_expedited(void)
{
struct rcu_node *rnp;
struct rcu_state *rsp = &rcu_preempt_state;
struct rcu_state *rsp = rcu_state_p;
unsigned long snap;
int trycount = 0;
@ -798,7 +806,7 @@ EXPORT_SYMBOL_GPL(synchronize_rcu_expedited);
*/
void rcu_barrier(void)
{
_rcu_barrier(&rcu_preempt_state);
_rcu_barrier(rcu_state_p);
}
EXPORT_SYMBOL_GPL(rcu_barrier);
@ -807,7 +815,7 @@ EXPORT_SYMBOL_GPL(rcu_barrier);
*/
static void __init __rcu_init_preempt(void)
{
rcu_init_one(&rcu_preempt_state, &rcu_preempt_data);
rcu_init_one(rcu_state_p, rcu_data_p);
}
/*
@ -830,7 +838,8 @@ void exit_rcu(void)
#else /* #ifdef CONFIG_PREEMPT_RCU */
static struct rcu_state *rcu_state_p = &rcu_sched_state;
static struct rcu_state *const rcu_state_p = &rcu_sched_state;
static struct rcu_data __percpu *const rcu_data_p = &rcu_sched_data;
/*
* Tell them what RCU they are running.
@ -1172,7 +1181,7 @@ static int rcu_spawn_one_boost_kthread(struct rcu_state *rsp,
struct sched_param sp;
struct task_struct *t;
if (&rcu_preempt_state != rsp)
if (rcu_state_p != rsp)
return 0;
if (!rcu_scheduler_fully_active || rcu_rnp_online_cpus(rnp) == 0)
@ -1366,13 +1375,12 @@ static void rcu_prepare_kthreads(int cpu)
* Because we not have RCU_FAST_NO_HZ, just check whether this CPU needs
* any flavor of RCU.
*/
#ifndef CONFIG_RCU_NOCB_CPU_ALL
int rcu_needs_cpu(unsigned long *delta_jiffies)
{
*delta_jiffies = ULONG_MAX;
return rcu_cpu_has_callbacks(NULL);
return IS_ENABLED(CONFIG_RCU_NOCB_CPU_ALL)
? 0 : rcu_cpu_has_callbacks(NULL);
}
#endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */
/*
* Because we do not have RCU_FAST_NO_HZ, don't bother cleaning up
@ -1479,11 +1487,15 @@ static bool __maybe_unused rcu_try_advance_all_cbs(void)
*
* The caller must have disabled interrupts.
*/
#ifndef CONFIG_RCU_NOCB_CPU_ALL
int rcu_needs_cpu(unsigned long *dj)
{
struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
if (IS_ENABLED(CONFIG_RCU_NOCB_CPU_ALL)) {
*dj = ULONG_MAX;
return 0;
}
/* Snapshot to detect later posting of non-lazy callback. */
rdtp->nonlazy_posted_snap = rdtp->nonlazy_posted;
@ -1510,7 +1522,6 @@ int rcu_needs_cpu(unsigned long *dj)
}
return 0;
}
#endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */
/*
* Prepare a CPU for idle from an RCU perspective. The first major task
@ -1524,7 +1535,6 @@ int rcu_needs_cpu(unsigned long *dj)
*/
static void rcu_prepare_for_idle(void)
{
#ifndef CONFIG_RCU_NOCB_CPU_ALL
bool needwake;
struct rcu_data *rdp;
struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
@ -1532,6 +1542,9 @@ static void rcu_prepare_for_idle(void)
struct rcu_state *rsp;
int tne;
if (IS_ENABLED(CONFIG_RCU_NOCB_CPU_ALL))
return;
/* Handle nohz enablement switches conservatively. */
tne = READ_ONCE(tick_nohz_active);
if (tne != rdtp->tick_nohz_enabled_snap) {
@ -1579,7 +1592,6 @@ static void rcu_prepare_for_idle(void)
if (needwake)
rcu_gp_kthread_wake(rsp);
}
#endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */
}
/*
@ -1589,12 +1601,11 @@ static void rcu_prepare_for_idle(void)
*/
static void rcu_cleanup_after_idle(void)
{
#ifndef CONFIG_RCU_NOCB_CPU_ALL
if (rcu_is_nocb_cpu(smp_processor_id()))
if (IS_ENABLED(CONFIG_RCU_NOCB_CPU_ALL) ||
rcu_is_nocb_cpu(smp_processor_id()))
return;
if (rcu_try_advance_all_cbs())
invoke_rcu_core();
#endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */
}
/*
@ -3048,9 +3059,9 @@ static bool rcu_nohz_full_cpu(struct rcu_state *rsp)
if (tick_nohz_full_cpu(smp_processor_id()) &&
(!rcu_gp_in_progress(rsp) ||
ULONG_CMP_LT(jiffies, READ_ONCE(rsp->gp_start) + HZ)))
return 1;
return true;
#endif /* #ifdef CONFIG_NO_HZ_FULL */
return 0;
return false;
}
/*