#include <linux/delay.h>
#include <linux/stop_machine.h>
#include <linux/random.h>
-#include <linux/ftrace_event.h>
+#include <linux/trace_events.h>
#include <linux/suspend.h>
#include <linux/delay.h>
#include <linux/gfp.h>
static struct lock_class_key rcu_node_class[RCU_NUM_LVLS];
static struct lock_class_key rcu_fqs_class[RCU_NUM_LVLS];
+static struct lock_class_key rcu_exp_class[RCU_NUM_LVLS];
/*
* In order to export the rcu_state name to the tracing tools, it
#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, \
.call = cr, \
- .fqs_state = RCU_GP_IDLE, \
+ .gp_state = RCU_GP_IDLE, \
.gpnum = 0UL - 300UL, \
.completed = 0UL - 300UL, \
.orphan_lock = __RAW_SPIN_LOCK_UNLOCKED(&sname##_state.orphan_lock), \
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. */
- NUM_RCU_LVL_0,
- NUM_RCU_LVL_1,
- NUM_RCU_LVL_2,
- NUM_RCU_LVL_3,
- NUM_RCU_LVL_4,
-};
+/* Number of rcu_nodes at specified level. */
+static int num_rcu_lvl[] = NUM_RCU_LVL_INIT;
int rcu_num_nodes __read_mostly = NUM_RCU_NODES; /* Total # rcu_nodes in use. */
/*
static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu);
static void invoke_rcu_core(void);
static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp);
+static void rcu_report_exp_rdp(struct rcu_state *rsp,
+ struct rcu_data *rdp, bool wake);
/* 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
*/
unsigned long rcu_rnp_online_cpus(struct rcu_node *rnp)
{
- return ACCESS_ONCE(rnp->qsmaskinitnext);
+ return READ_ONCE(rnp->qsmaskinitnext);
}
/*
- * Return true if an RCU grace period is in progress. The ACCESS_ONCE()s
+ * Return true if an RCU grace period is in progress. The READ_ONCE()s
* permit this function to be invoked without holding the root rcu_node
* structure's ->lock, but of course results can be subject to change.
*/
static int rcu_gp_in_progress(struct rcu_state *rsp)
{
- return ACCESS_ONCE(rsp->completed) != ACCESS_ONCE(rsp->gpnum);
+ return READ_ONCE(rsp->completed) != READ_ONCE(rsp->gpnum);
}
/*
*/
void rcu_sched_qs(void)
{
- if (!__this_cpu_read(rcu_sched_data.passed_quiesce)) {
+ unsigned long flags;
+
+ if (__this_cpu_read(rcu_sched_data.cpu_no_qs.s)) {
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);
+ __this_cpu_write(rcu_sched_data.cpu_no_qs.b.norm, false);
+ if (!__this_cpu_read(rcu_sched_data.cpu_no_qs.b.exp))
+ return;
+ local_irq_save(flags);
+ if (__this_cpu_read(rcu_sched_data.cpu_no_qs.b.exp)) {
+ __this_cpu_write(rcu_sched_data.cpu_no_qs.b.exp, false);
+ rcu_report_exp_rdp(&rcu_sched_state,
+ this_cpu_ptr(&rcu_sched_data),
+ true);
+ }
+ local_irq_restore(flags);
}
}
#else
void rcu_bh_qs(void)
{
- if (!__this_cpu_read(rcu_bh_data.passed_quiesce)) {
+ if (__this_cpu_read(rcu_bh_data.cpu_no_qs.s)) {
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);
+ __this_cpu_write(rcu_bh_data.cpu_no_qs.b.norm, false);
}
}
#endif
if (!(resched_mask & rsp->flavor_mask))
continue;
smp_mb(); /* rcu_sched_qs_mask before cond_resched_completed. */
- if (ACCESS_ONCE(rdp->mynode->completed) !=
- ACCESS_ONCE(rdp->cond_resched_completed))
+ if (READ_ONCE(rdp->mynode->completed) !=
+ READ_ONCE(rdp->cond_resched_completed))
continue;
/*
*/
void rcu_note_context_switch(void)
{
+ barrier(); /* Avoid RCU read-side critical sections leaking down. */
trace_rcu_utilization(TPS("Start context switch"));
rcu_sched_qs();
rcu_preempt_note_context_switch();
if (unlikely(raw_cpu_read(rcu_sched_qs_mask)))
rcu_momentary_dyntick_idle();
trace_rcu_utilization(TPS("End context switch"));
+ barrier(); /* Avoid RCU read-side critical sections leaking up. */
}
EXPORT_SYMBOL_GPL(rcu_note_context_switch);
* RCU flavors in desperate need of a quiescent state, which will normally
* be none of them). Either way, do a lightweight quiescent state for
* all RCU flavors.
+ *
+ * The barrier() calls are redundant in the common case when this is
+ * called externally, but just in case this is called from within this
+ * file.
+ *
*/
void rcu_all_qs(void)
{
+ barrier(); /* Avoid RCU read-side critical sections leaking down. */
if (unlikely(raw_cpu_read(rcu_sched_qs_mask)))
rcu_momentary_dyntick_idle();
this_cpu_inc(rcu_qs_ctr);
+ barrier(); /* Avoid RCU read-side critical sections leaking up. */
}
EXPORT_SYMBOL_GPL(rcu_all_qs);
/*
* Return the number of RCU BH batches started thus far for debug & stats.
*/
+#ifndef CONFIG_PREEMPT_RT_FULL
unsigned long rcu_batches_started_bh(void)
{
return rcu_bh_state.gpnum;
}
EXPORT_SYMBOL_GPL(rcu_batches_started_bh);
+#endif
/*
* Return the number of RCU batches completed thus far for debug & stats.
case RCU_FLAVOR:
rsp = rcu_state_p;
break;
+#ifndef CONFIG_PREEMPT_RT_FULL
case RCU_BH_FLAVOR:
rsp = &rcu_bh_state;
break;
+#endif
case RCU_SCHED_FLAVOR:
rsp = &rcu_sched_state;
break;
break;
}
if (rsp != NULL) {
- *flags = ACCESS_ONCE(rsp->gp_flags);
- *gpnum = ACCESS_ONCE(rsp->gpnum);
- *completed = ACCESS_ONCE(rsp->completed);
+ *flags = READ_ONCE(rsp->gp_flags);
+ *gpnum = READ_ONCE(rsp->gpnum);
+ *completed = READ_ONCE(rsp->completed);
return;
}
*flags = 0;
static int rcu_future_needs_gp(struct rcu_state *rsp)
{
struct rcu_node *rnp = rcu_get_root(rsp);
- int idx = (ACCESS_ONCE(rnp->completed) + 1) & 0x1;
+ int idx = (READ_ONCE(rnp->completed) + 1) & 0x1;
int *fp = &rnp->need_future_gp[idx];
- return ACCESS_ONCE(*fp);
+ return READ_ONCE(*fp);
}
/*
return 1; /* Yes, this CPU has newly registered callbacks. */
for (i = RCU_WAIT_TAIL; i < RCU_NEXT_TAIL; i++)
if (rdp->nxttail[i - 1] != rdp->nxttail[i] &&
- ULONG_CMP_LT(ACCESS_ONCE(rsp->completed),
+ ULONG_CMP_LT(READ_ONCE(rsp->completed),
rdp->nxtcompleted[i]))
return 1; /* Yes, CBs for future grace period. */
return 0; /* No grace period needed. */
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());
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();
/*
* It is illegal to enter an extended quiescent state while
* in an RCU read-side critical section.
*/
- rcu_lockdep_assert(!lock_is_held(&rcu_lock_map),
- "Illegal idle entry in RCU read-side critical section.");
- rcu_lockdep_assert(!lock_is_held(&rcu_bh_lock_map),
- "Illegal idle entry in RCU-bh read-side critical section.");
- rcu_lockdep_assert(!lock_is_held(&rcu_sched_lock_map),
- "Illegal idle entry in RCU-sched read-side critical section.");
+ RCU_LOCKDEP_WARN(lock_is_held(&rcu_lock_map),
+ "Illegal idle entry in RCU read-side critical section.");
+ RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map),
+ "Illegal idle entry in RCU-bh read-side critical section.");
+ RCU_LOCKDEP_WARN(lock_is_held(&rcu_sched_lock_map),
+ "Illegal idle entry in RCU-sched read-side critical section.");
}
/*
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);
}
EXPORT_SYMBOL_GPL(rcu_idle_enter);
-#ifdef CONFIG_RCU_USER_QS
+#ifdef CONFIG_NO_HZ_FULL
/**
* rcu_user_enter - inform RCU that we are resuming userspace.
*
{
rcu_eqs_enter(1);
}
-#endif /* CONFIG_RCU_USER_QS */
+#endif /* CONFIG_NO_HZ_FULL */
/**
* rcu_irq_exit - inform RCU that current CPU is exiting irq towards idle
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
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());
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 {
}
EXPORT_SYMBOL_GPL(rcu_idle_exit);
-#ifdef CONFIG_RCU_USER_QS
+#ifdef CONFIG_NO_HZ_FULL
/**
* rcu_user_exit - inform RCU that we are exiting userspace.
*
{
rcu_eqs_exit(1);
}
-#endif /* CONFIG_RCU_USER_QS */
+#endif /* CONFIG_NO_HZ_FULL */
/**
* rcu_irq_enter - inform RCU that current CPU is entering irq away from idle
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
{
bool ret;
- preempt_disable();
+ preempt_disable_notrace();
ret = __rcu_is_watching();
- preempt_enable();
+ preempt_enable_notrace();
return ret;
}
EXPORT_SYMBOL_GPL(rcu_is_watching);
trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("dti"));
return 1;
} else {
- if (ULONG_CMP_LT(ACCESS_ONCE(rdp->gpnum) + ULONG_MAX / 4,
+ if (ULONG_CMP_LT(READ_ONCE(rdp->gpnum) + ULONG_MAX / 4,
rdp->mynode->gpnum))
- ACCESS_ONCE(rdp->gpwrap) = true;
+ WRITE_ONCE(rdp->gpwrap, true);
return 0;
}
}
if (ULONG_CMP_GE(jiffies,
rdp->rsp->gp_start + jiffies_till_sched_qs) ||
ULONG_CMP_GE(jiffies, rdp->rsp->jiffies_resched)) {
- if (!(ACCESS_ONCE(*rcrmp) & rdp->rsp->flavor_mask)) {
- ACCESS_ONCE(rdp->cond_resched_completed) =
- ACCESS_ONCE(rdp->mynode->completed);
+ if (!(READ_ONCE(*rcrmp) & rdp->rsp->flavor_mask)) {
+ WRITE_ONCE(rdp->cond_resched_completed,
+ READ_ONCE(rdp->mynode->completed));
smp_mb(); /* ->cond_resched_completed before *rcrmp. */
- ACCESS_ONCE(*rcrmp) =
- ACCESS_ONCE(*rcrmp) + rdp->rsp->flavor_mask;
+ WRITE_ONCE(*rcrmp,
+ READ_ONCE(*rcrmp) + rdp->rsp->flavor_mask);
resched_cpu(rdp->cpu); /* Force CPU into scheduler. */
rdp->rsp->jiffies_resched += 5; /* Enable beating. */
} else if (ULONG_CMP_GE(jiffies, rdp->rsp->jiffies_resched)) {
rsp->gp_start = j;
smp_wmb(); /* Record start time before stall time. */
j1 = rcu_jiffies_till_stall_check();
- ACCESS_ONCE(rsp->jiffies_stall) = j + j1;
+ WRITE_ONCE(rsp->jiffies_stall, j + j1);
rsp->jiffies_resched = j + j1 / 2;
- rsp->n_force_qs_gpstart = ACCESS_ONCE(rsp->n_force_qs);
+ rsp->n_force_qs_gpstart = READ_ONCE(rsp->n_force_qs);
}
/*
unsigned long j;
j = jiffies;
- gpa = ACCESS_ONCE(rsp->gp_activity);
+ 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 s%d ->state=%#lx\n",
+ rsp->name, j - gpa,
+ rsp->gpnum, rsp->completed,
+ rsp->gp_flags, rsp->gp_state,
+ rsp->gp_kthread ? rsp->gp_kthread->state : 0);
}
/*
/* Only let one CPU complain about others per time interval. */
raw_spin_lock_irqsave(&rnp->lock, flags);
- delta = jiffies - ACCESS_ONCE(rsp->jiffies_stall);
+ delta = jiffies - READ_ONCE(rsp->jiffies_stall);
if (delta < RCU_STALL_RAT_DELAY || !rcu_gp_in_progress(rsp)) {
raw_spin_unlock_irqrestore(&rnp->lock, flags);
return;
}
- ACCESS_ONCE(rsp->jiffies_stall) = jiffies + 3 * rcu_jiffies_till_stall_check() + 3;
+ WRITE_ONCE(rsp->jiffies_stall,
+ jiffies + 3 * rcu_jiffies_till_stall_check() + 3);
raw_spin_unlock_irqrestore(&rnp->lock, flags);
/*
if (ndetected) {
rcu_dump_cpu_stacks(rsp);
} else {
- if (ACCESS_ONCE(rsp->gpnum) != gpnum ||
- ACCESS_ONCE(rsp->completed) == gpnum) {
+ if (READ_ONCE(rsp->gpnum) != gpnum ||
+ READ_ONCE(rsp->completed) == gpnum) {
pr_err("INFO: Stall ended before state dump start\n");
} else {
j = jiffies;
- gpa = ACCESS_ONCE(rsp->gp_activity);
+ gpa = READ_ONCE(rsp->gp_activity);
pr_err("All QSes seen, last %s kthread activity %ld (%ld-%ld), jiffies_till_next_fqs=%ld, root ->qsmask %#lx\n",
rsp->name, j - gpa, j, gpa,
jiffies_till_next_fqs,
rcu_dump_cpu_stacks(rsp);
raw_spin_lock_irqsave(&rnp->lock, flags);
- if (ULONG_CMP_GE(jiffies, ACCESS_ONCE(rsp->jiffies_stall)))
- ACCESS_ONCE(rsp->jiffies_stall) = jiffies +
- 3 * rcu_jiffies_till_stall_check() + 3;
+ if (ULONG_CMP_GE(jiffies, READ_ONCE(rsp->jiffies_stall)))
+ WRITE_ONCE(rsp->jiffies_stall,
+ jiffies + 3 * rcu_jiffies_till_stall_check() + 3);
raw_spin_unlock_irqrestore(&rnp->lock, flags);
/*
* Given this check, comparisons of jiffies, rsp->jiffies_stall,
* and rsp->gp_start suffice to forestall false positives.
*/
- gpnum = ACCESS_ONCE(rsp->gpnum);
+ gpnum = READ_ONCE(rsp->gpnum);
smp_rmb(); /* Pick up ->gpnum first... */
- js = ACCESS_ONCE(rsp->jiffies_stall);
+ js = READ_ONCE(rsp->jiffies_stall);
smp_rmb(); /* ...then ->jiffies_stall before the rest... */
- gps = ACCESS_ONCE(rsp->gp_start);
+ gps = READ_ONCE(rsp->gp_start);
smp_rmb(); /* ...and finally ->gp_start before ->completed. */
- completed = ACCESS_ONCE(rsp->completed);
+ completed = READ_ONCE(rsp->completed);
if (ULONG_CMP_GE(completed, gpnum) ||
ULONG_CMP_LT(j, js) ||
ULONG_CMP_GE(gps, js))
return; /* No stall or GP completed since entering function. */
rnp = rdp->mynode;
if (rcu_gp_in_progress(rsp) &&
- (ACCESS_ONCE(rnp->qsmask) & rdp->grpmask)) {
+ (READ_ONCE(rnp->qsmask) & rdp->grpmask)) {
/* We haven't checked in, so go dump stack. */
print_cpu_stall(rsp);
struct rcu_state *rsp;
for_each_rcu_flavor(rsp)
- ACCESS_ONCE(rsp->jiffies_stall) = jiffies + ULONG_MAX / 2;
+ WRITE_ONCE(rsp->jiffies_stall, jiffies + ULONG_MAX / 2);
}
/*
* doing some extra useless work.
*/
if (rnp->gpnum != rnp->completed ||
- ACCESS_ONCE(rnp_root->gpnum) != ACCESS_ONCE(rnp_root->completed)) {
+ READ_ONCE(rnp_root->gpnum) != READ_ONCE(rnp_root->completed)) {
rnp->need_future_gp[c & 0x1]++;
trace_rcu_future_gp(rnp, rdp, c, TPS("Startedleaf"));
goto out;
int needmore;
struct rcu_data *rdp = this_cpu_ptr(rsp->rda);
- rcu_nocb_gp_cleanup(rsp, rnp);
rnp->need_future_gp[c & 0x1] = 0;
needmore = rnp->need_future_gp[(c + 1) & 0x1];
trace_rcu_future_gp(rnp, rdp, c,
static void rcu_gp_kthread_wake(struct rcu_state *rsp)
{
if (current == rsp->gp_kthread ||
- !ACCESS_ONCE(rsp->gp_flags) ||
+ !READ_ONCE(rsp->gp_flags) ||
!rsp->gp_kthread)
return;
- swait_wake(&rsp->gp_wq);
+ swake_up(&rsp->gp_wq);
}
/*
/* Handle the ends of any preceding grace periods first. */
if (rdp->completed == rnp->completed &&
- !unlikely(ACCESS_ONCE(rdp->gpwrap))) {
+ !unlikely(READ_ONCE(rdp->gpwrap))) {
/* No grace period end, so just accelerate recent callbacks. */
ret = rcu_accelerate_cbs(rsp, rnp, rdp);
trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpuend"));
}
- if (rdp->gpnum != rnp->gpnum || unlikely(ACCESS_ONCE(rdp->gpwrap))) {
+ if (rdp->gpnum != rnp->gpnum || unlikely(READ_ONCE(rdp->gpwrap))) {
/*
* If the current grace period is waiting for this CPU,
* set up to detect a quiescent state, otherwise don't
*/
rdp->gpnum = rnp->gpnum;
trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpustart"));
- rdp->passed_quiesce = 0;
+ rdp->cpu_no_qs.b.norm = true;
rdp->rcu_qs_ctr_snap = __this_cpu_read(rcu_qs_ctr);
- rdp->qs_pending = !!(rnp->qsmask & rdp->grpmask);
+ rdp->core_needs_qs = !!(rnp->qsmask & rdp->grpmask);
zero_cpu_stall_ticks(rdp);
- ACCESS_ONCE(rdp->gpwrap) = false;
+ WRITE_ONCE(rdp->gpwrap, false);
}
return ret;
}
local_irq_save(flags);
rnp = rdp->mynode;
- if ((rdp->gpnum == ACCESS_ONCE(rnp->gpnum) &&
- rdp->completed == ACCESS_ONCE(rnp->completed) &&
- !unlikely(ACCESS_ONCE(rdp->gpwrap))) || /* w/out lock. */
+ if ((rdp->gpnum == READ_ONCE(rnp->gpnum) &&
+ rdp->completed == READ_ONCE(rnp->completed) &&
+ !unlikely(READ_ONCE(rdp->gpwrap))) || /* w/out lock. */
!raw_spin_trylock(&rnp->lock)) { /* irqs already off, so later. */
local_irq_restore(flags);
return;
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.
*/
struct rcu_data *rdp;
struct rcu_node *rnp = rcu_get_root(rsp);
- ACCESS_ONCE(rsp->gp_activity) = jiffies;
+ WRITE_ONCE(rsp->gp_activity, jiffies);
raw_spin_lock_irq(&rnp->lock);
smp_mb__after_unlock_lock();
- if (!ACCESS_ONCE(rsp->gp_flags)) {
+ if (!READ_ONCE(rsp->gp_flags)) {
/* Spurious wakeup, tell caller to go back to sleep. */
raw_spin_unlock_irq(&rnp->lock);
return 0;
}
- ACCESS_ONCE(rsp->gp_flags) = 0; /* Clear all flags: New grace period. */
+ WRITE_ONCE(rsp->gp_flags, 0); /* Clear all flags: New grace period. */
if (WARN_ON_ONCE(rcu_gp_in_progress(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 &&
* 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);
rcu_preempt_check_blocked_tasks(rnp);
rnp->qsmask = rnp->qsmaskinit;
- ACCESS_ONCE(rnp->gpnum) = rsp->gpnum;
+ WRITE_ONCE(rnp->gpnum, rsp->gpnum);
if (WARN_ON_ONCE(rnp->completed != rsp->completed))
- ACCESS_ONCE(rnp->completed) = rsp->completed;
+ WRITE_ONCE(rnp->completed, rsp->completed);
if (rnp == rdp->mynode)
(void)__note_gp_changes(rsp, rnp, rdp);
rcu_preempt_boost_start_gp(rnp);
rnp->grphi, rnp->qsmask);
raw_spin_unlock_irq(&rnp->lock);
cond_resched_rcu_qs();
- ACCESS_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);
+ WRITE_ONCE(rsp->gp_activity, jiffies);
}
return 1;
}
+/*
+ * Helper function for wait_event_interruptible_timeout() wakeup
+ * at force-quiescent-state time.
+ */
+static bool rcu_gp_fqs_check_wake(struct rcu_state *rsp, int *gfp)
+{
+ struct rcu_node *rnp = rcu_get_root(rsp);
+
+ /* Someone like call_rcu() requested a force-quiescent-state scan. */
+ *gfp = READ_ONCE(rsp->gp_flags);
+ if (*gfp & RCU_GP_FLAG_FQS)
+ return true;
+
+ /* The current grace period has completed. */
+ if (!READ_ONCE(rnp->qsmask) && !rcu_preempt_blocked_readers_cgp(rnp))
+ return true;
+
+ return false;
+}
+
/*
* Do one round of quiescent-state forcing.
*/
-static int rcu_gp_fqs(struct rcu_state *rsp, int fqs_state_in)
+static void rcu_gp_fqs(struct rcu_state *rsp, bool first_time)
{
- int fqs_state = fqs_state_in;
bool isidle = false;
unsigned long maxj;
struct rcu_node *rnp = rcu_get_root(rsp);
- ACCESS_ONCE(rsp->gp_activity) = jiffies;
+ WRITE_ONCE(rsp->gp_activity, jiffies);
rsp->n_force_qs++;
- if (fqs_state == RCU_SAVE_DYNTICK) {
+ if (first_time) {
/* Collect dyntick-idle snapshots. */
if (is_sysidle_rcu_state(rsp)) {
isidle = true;
force_qs_rnp(rsp, dyntick_save_progress_counter,
&isidle, &maxj);
rcu_sysidle_report_gp(rsp, isidle, maxj);
- fqs_state = RCU_FORCE_QS;
} else {
/* Handle dyntick-idle and offline CPUs. */
isidle = true;
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) {
+ if (READ_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) {
raw_spin_lock_irq(&rnp->lock);
smp_mb__after_unlock_lock();
- ACCESS_ONCE(rsp->gp_flags) =
- ACCESS_ONCE(rsp->gp_flags) & ~RCU_GP_FLAG_FQS;
+ WRITE_ONCE(rsp->gp_flags,
+ READ_ONCE(rsp->gp_flags) & ~RCU_GP_FLAG_FQS);
raw_spin_unlock_irq(&rnp->lock);
}
- return fqs_state;
}
/*
int nocb = 0;
struct rcu_data *rdp;
struct rcu_node *rnp = rcu_get_root(rsp);
+ struct swait_queue_head *sq;
- ACCESS_ONCE(rsp->gp_activity) = jiffies;
+ WRITE_ONCE(rsp->gp_activity, jiffies);
raw_spin_lock_irq(&rnp->lock);
smp_mb__after_unlock_lock();
gp_duration = jiffies - rsp->gp_start;
smp_mb__after_unlock_lock();
WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp));
WARN_ON_ONCE(rnp->qsmask);
- ACCESS_ONCE(rnp->completed) = rsp->gpnum;
+ WRITE_ONCE(rnp->completed, rsp->gpnum);
rdp = this_cpu_ptr(rsp->rda);
if (rnp == rdp->mynode)
needgp = __note_gp_changes(rsp, rnp, rdp) || needgp;
/* smp_mb() provided by prior unlock-lock pair. */
nocb += rcu_future_gp_cleanup(rsp, rnp);
+ sq = rcu_nocb_gp_get(rnp);
raw_spin_unlock_irq(&rnp->lock);
+ rcu_nocb_gp_cleanup(sq);
cond_resched_rcu_qs();
- ACCESS_ONCE(rsp->gp_activity) = jiffies;
+ WRITE_ONCE(rsp->gp_activity, jiffies);
+ rcu_gp_slow(rsp, gp_cleanup_delay);
}
rnp = rcu_get_root(rsp);
raw_spin_lock_irq(&rnp->lock);
rcu_nocb_gp_set(rnp, nocb);
/* Declare grace period done. */
- ACCESS_ONCE(rsp->completed) = rsp->gpnum;
+ WRITE_ONCE(rsp->completed, rsp->gpnum);
trace_rcu_grace_period(rsp->name, rsp->completed, TPS("end"));
- rsp->fqs_state = RCU_GP_IDLE;
+ rsp->gp_state = RCU_GP_IDLE;
rdp = this_cpu_ptr(rsp->rda);
/* Advance CBs to reduce false positives below. */
needgp = rcu_advance_cbs(rsp, rnp, rdp) || needgp;
if (needgp || cpu_needs_another_gp(rsp, rdp)) {
- ACCESS_ONCE(rsp->gp_flags) = RCU_GP_FLAG_INIT;
+ WRITE_ONCE(rsp->gp_flags, RCU_GP_FLAG_INIT);
trace_rcu_grace_period(rsp->name,
- ACCESS_ONCE(rsp->gpnum),
+ READ_ONCE(rsp->gpnum),
TPS("newreq"));
}
raw_spin_unlock_irq(&rnp->lock);
*/
static int __noreturn rcu_gp_kthread(void *arg)
{
- int fqs_state;
+ bool first_gp_fqs;
int gf;
unsigned long j;
int ret;
/* Handle grace-period start. */
for (;;) {
trace_rcu_grace_period(rsp->name,
- ACCESS_ONCE(rsp->gpnum),
+ READ_ONCE(rsp->gpnum),
TPS("reqwait"));
rsp->gp_state = RCU_GP_WAIT_GPS;
swait_event_interruptible(rsp->gp_wq,
- ACCESS_ONCE(rsp->gp_flags) &
+ READ_ONCE(rsp->gp_flags) &
RCU_GP_FLAG_INIT);
+ rsp->gp_state = RCU_GP_DONE_GPS;
/* Locking provides needed memory barrier. */
if (rcu_gp_init(rsp))
break;
cond_resched_rcu_qs();
- ACCESS_ONCE(rsp->gp_activity) = jiffies;
+ WRITE_ONCE(rsp->gp_activity, jiffies);
WARN_ON(signal_pending(current));
trace_rcu_grace_period(rsp->name,
- ACCESS_ONCE(rsp->gpnum),
+ READ_ONCE(rsp->gpnum),
TPS("reqwaitsig"));
}
/* Handle quiescent-state forcing. */
- fqs_state = RCU_SAVE_DYNTICK;
+ first_gp_fqs = true;
j = jiffies_till_first_fqs;
if (j > HZ) {
j = HZ;
if (!ret)
rsp->jiffies_force_qs = jiffies + j;
trace_rcu_grace_period(rsp->name,
- ACCESS_ONCE(rsp->gpnum),
+ READ_ONCE(rsp->gpnum),
TPS("fqswait"));
rsp->gp_state = RCU_GP_WAIT_FQS;
ret = swait_event_interruptible_timeout(rsp->gp_wq,
- ((gf = ACCESS_ONCE(rsp->gp_flags)) &
- RCU_GP_FLAG_FQS) ||
- (!ACCESS_ONCE(rnp->qsmask) &&
- !rcu_preempt_blocked_readers_cgp(rnp)),
- j);
+ rcu_gp_fqs_check_wake(rsp, &gf), j);
+ rsp->gp_state = RCU_GP_DOING_FQS;
/* Locking provides needed memory barriers. */
/* If grace period done, leave loop. */
- if (!ACCESS_ONCE(rnp->qsmask) &&
+ if (!READ_ONCE(rnp->qsmask) &&
!rcu_preempt_blocked_readers_cgp(rnp))
break;
/* If time for quiescent-state forcing, do it. */
if (ULONG_CMP_GE(jiffies, rsp->jiffies_force_qs) ||
(gf & RCU_GP_FLAG_FQS)) {
trace_rcu_grace_period(rsp->name,
- ACCESS_ONCE(rsp->gpnum),
+ READ_ONCE(rsp->gpnum),
TPS("fqsstart"));
- fqs_state = rcu_gp_fqs(rsp, fqs_state);
+ rcu_gp_fqs(rsp, first_gp_fqs);
+ first_gp_fqs = false;
trace_rcu_grace_period(rsp->name,
- ACCESS_ONCE(rsp->gpnum),
+ READ_ONCE(rsp->gpnum),
TPS("fqsend"));
cond_resched_rcu_qs();
- ACCESS_ONCE(rsp->gp_activity) = jiffies;
+ WRITE_ONCE(rsp->gp_activity, jiffies);
} else {
/* Deal with stray signal. */
cond_resched_rcu_qs();
- ACCESS_ONCE(rsp->gp_activity) = jiffies;
+ WRITE_ONCE(rsp->gp_activity, jiffies);
WARN_ON(signal_pending(current));
trace_rcu_grace_period(rsp->name,
- ACCESS_ONCE(rsp->gpnum),
+ READ_ONCE(rsp->gpnum),
TPS("fqswaitsig"));
}
j = jiffies_till_next_fqs;
}
/* Handle grace-period end. */
+ rsp->gp_state = RCU_GP_CLEANUP;
rcu_gp_cleanup(rsp);
+ rsp->gp_state = RCU_GP_CLEANED;
}
}
*/
return false;
}
- ACCESS_ONCE(rsp->gp_flags) = RCU_GP_FLAG_INIT;
- trace_rcu_grace_period(rsp->name, ACCESS_ONCE(rsp->gpnum),
+ WRITE_ONCE(rsp->gp_flags, RCU_GP_FLAG_INIT);
+ trace_rcu_grace_period(rsp->name, READ_ONCE(rsp->gpnum),
TPS("newreq"));
/*
__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);
+ swake_up(&rsp->gp_wq); /* Memory barrier implied by swake_up() path. */
}
/*
rnp = rdp->mynode;
raw_spin_lock_irqsave(&rnp->lock, flags);
smp_mb__after_unlock_lock();
- if ((rdp->passed_quiesce == 0 &&
+ if ((rdp->cpu_no_qs.b.norm &&
rdp->rcu_qs_ctr_snap == __this_cpu_read(rcu_qs_ctr)) ||
rdp->gpnum != rnp->gpnum || rnp->completed == rnp->gpnum ||
rdp->gpwrap) {
* We will instead need a new quiescent state that lies
* within the current grace period.
*/
- rdp->passed_quiesce = 0; /* need qs for new gp. */
+ rdp->cpu_no_qs.b.norm = true; /* need qs for new gp. */
rdp->rcu_qs_ctr_snap = __this_cpu_read(rcu_qs_ctr);
raw_spin_unlock_irqrestore(&rnp->lock, flags);
return;
if ((rnp->qsmask & mask) == 0) {
raw_spin_unlock_irqrestore(&rnp->lock, flags);
} else {
- rdp->qs_pending = 0;
+ rdp->core_needs_qs = 0;
/*
* This GP can't end until cpu checks in, so all of our
* Does this CPU still need to do its part for current grace period?
* If no, return and let the other CPUs do their part as well.
*/
- if (!rdp->qs_pending)
+ if (!rdp->core_needs_qs)
return;
/*
* Was there a quiescent state since the beginning of the grace
* period? If no, then exit and wait for the next call.
*/
- if (!rdp->passed_quiesce &&
+ if (rdp->cpu_no_qs.b.norm &&
rdp->rcu_qs_ctr_snap == __this_cpu_read(rcu_qs_ctr))
return;
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
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;
/*
rsp->qlen += rdp->qlen;
rdp->n_cbs_orphaned += rdp->qlen;
rdp->qlen_lazy = 0;
- ACCESS_ONCE(rdp->qlen) = 0;
+ WRITE_ONCE(rdp->qlen, 0);
}
/*
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. */
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),
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;
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);
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);
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.
/* If no callbacks are ready, just return. */
if (!cpu_has_callbacks_ready_to_invoke(rdp)) {
trace_rcu_batch_start(rsp->name, rdp->qlen_lazy, rdp->qlen, 0);
- trace_rcu_batch_end(rsp->name, 0, !!ACCESS_ONCE(rdp->nxtlist),
+ trace_rcu_batch_end(rsp->name, 0, !!READ_ONCE(rdp->nxtlist),
need_resched(), is_idle_task(current),
rcu_is_callbacks_kthread());
return;
}
smp_mb(); /* List handling before counting for rcu_barrier(). */
rdp->qlen_lazy -= count_lazy;
- ACCESS_ONCE(rdp->qlen) = rdp->qlen - count;
+ WRITE_ONCE(rdp->qlen, rdp->qlen - count);
rdp->n_cbs_invoked += count;
/* Reinstate batch limit if we have worked down the excess. */
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 ||
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;
}
/* Funnel through hierarchy to reduce memory contention. */
rnp = __this_cpu_read(rsp->rda->mynode);
for (; rnp != NULL; rnp = rnp->parent) {
- ret = (ACCESS_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) ||
+ ret = (READ_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) ||
!raw_spin_trylock(&rnp->fqslock);
if (rnp_old != NULL)
raw_spin_unlock(&rnp_old->fqslock);
raw_spin_lock_irqsave(&rnp_old->lock, flags);
smp_mb__after_unlock_lock();
raw_spin_unlock(&rnp_old->fqslock);
- if (ACCESS_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) {
+ if (READ_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) {
rsp->n_force_qs_lh++;
raw_spin_unlock_irqrestore(&rnp_old->lock, flags);
return; /* Someone beat us to it. */
}
- ACCESS_ONCE(rsp->gp_flags) =
- ACCESS_ONCE(rsp->gp_flags) | RCU_GP_FLAG_FQS;
+ WRITE_ONCE(rsp->gp_flags, READ_ONCE(rsp->gp_flags) | RCU_GP_FLAG_FQS);
raw_spin_unlock_irqrestore(&rnp_old->lock, flags);
- rcu_gp_kthread_wake(rsp);
+ swake_up(&rsp->gp_wq); /* Memory barrier implied by swake_up() path. */
}
/*
*/
static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp)
{
- if (unlikely(!ACCESS_ONCE(rcu_scheduler_fully_active)))
+ if (unlikely(!READ_ONCE(rcu_scheduler_fully_active)))
return;
rcu_do_batch(rsp, rdp);
}
* is expected to specify a CPU.
*/
static void
-__call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu),
+__call_rcu(struct rcu_head *head, rcu_callback_t func,
struct rcu_state *rsp, int cpu, bool lazy)
{
unsigned long flags;
WARN_ON_ONCE((unsigned long)head & 0x1); /* Misaligned rcu_head! */
if (debug_rcu_head_queue(head)) {
/* Probable double call_rcu(), so leak the callback. */
- ACCESS_ONCE(head->func) = rcu_leak_callback;
+ WRITE_ONCE(head->func, rcu_leak_callback);
WARN_ONCE(1, "__call_rcu(): Leaked duplicate callback\n");
return;
}
if (!likely(rdp->nxtlist))
init_default_callback_list(rdp);
}
- ACCESS_ONCE(rdp->qlen) = rdp->qlen + 1;
+ WRITE_ONCE(rdp->qlen, rdp->qlen + 1);
if (lazy)
rdp->qlen_lazy++;
else
/*
* Queue an RCU-sched callback for invocation after a grace period.
*/
-void call_rcu_sched(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
+void call_rcu_sched(struct rcu_head *head, rcu_callback_t func)
{
__call_rcu(head, func, &rcu_sched_state, -1, 0);
}
/*
* Queue an RCU callback for invocation after a quicker grace period.
*/
-void call_rcu_bh(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
+void call_rcu_bh(struct rcu_head *head, rcu_callback_t func)
{
__call_rcu(head, func, &rcu_bh_state, -1, 0);
}
* function may only be called from __kfree_rcu().
*/
void kfree_call_rcu(struct rcu_head *head,
- void (*func)(struct rcu_head *rcu))
+ rcu_callback_t func)
{
__call_rcu(head, func, rcu_state_p, -1, 1);
}
*/
void synchronize_sched(void)
{
- rcu_lockdep_assert(!lock_is_held(&rcu_bh_lock_map) &&
- !lock_is_held(&rcu_lock_map) &&
- !lock_is_held(&rcu_sched_lock_map),
- "Illegal synchronize_sched() in RCU-sched read-side critical section");
+ RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map) ||
+ lock_is_held(&rcu_lock_map) ||
+ lock_is_held(&rcu_sched_lock_map),
+ "Illegal synchronize_sched() in RCU-sched read-side critical section");
if (rcu_blocking_is_gp())
return;
if (rcu_gp_is_expedited())
*/
void synchronize_rcu_bh(void)
{
- rcu_lockdep_assert(!lock_is_held(&rcu_bh_lock_map) &&
- !lock_is_held(&rcu_lock_map) &&
- !lock_is_held(&rcu_sched_lock_map),
- "Illegal synchronize_rcu_bh() in RCU-bh read-side critical section");
+ RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map) ||
+ lock_is_held(&rcu_lock_map) ||
+ lock_is_held(&rcu_sched_lock_map),
+ "Illegal synchronize_rcu_bh() in RCU-bh read-side critical section");
if (rcu_blocking_is_gp())
return;
if (rcu_gp_is_expedited())
}
EXPORT_SYMBOL_GPL(cond_synchronize_rcu);
-static int synchronize_sched_expedited_cpu_stop(void *data)
+/**
+ * get_state_synchronize_sched - Snapshot current RCU-sched state
+ *
+ * Returns a cookie that is used by a later call to cond_synchronize_sched()
+ * to determine whether or not a full grace period has elapsed in the
+ * meantime.
+ */
+unsigned long get_state_synchronize_sched(void)
{
/*
- * There must be a full memory barrier on each affected CPU
- * between the time that try_stop_cpus() is called and the
- * time that it returns.
- *
- * In the current initial implementation of cpu_stop, the
- * above condition is already met when the control reaches
- * this point and the following smp_mb() is not strictly
- * necessary. Do smp_mb() anyway for documentation and
- * robustness against future implementation changes.
+ * Any prior manipulation of RCU-protected data must happen
+ * before the load from ->gpnum.
*/
- smp_mb(); /* See above comment block. */
- return 0;
+ smp_mb(); /* ^^^ */
+
+ /*
+ * Make sure this load happens before the purportedly
+ * time-consuming work between get_state_synchronize_sched()
+ * and cond_synchronize_sched().
+ */
+ return smp_load_acquire(&rcu_sched_state.gpnum);
}
+EXPORT_SYMBOL_GPL(get_state_synchronize_sched);
/**
- * synchronize_sched_expedited - Brute-force RCU-sched grace period
+ * cond_synchronize_sched - Conditionally wait for an RCU-sched grace period
*
- * Wait for an RCU-sched grace period to elapse, but use a "big hammer"
- * approach to force the grace period to end quickly. This consumes
- * significant time on all CPUs and is unfriendly to real-time workloads,
- * so is thus not recommended for any sort of common-case code. In fact,
- * if you are using synchronize_sched_expedited() in a loop, please
- * restructure your code to batch your updates, and then use a single
- * synchronize_sched() instead.
- *
- * 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
- * of the ticket-lock word. Each task atomically increments
- * sync_sched_expedited_started upon entry, snapshotting the old value,
- * then attempts to stop all the CPUs. If this succeeds, then each
- * CPU will have executed a context switch, resulting in an RCU-sched
- * grace period. We are then done, so we use atomic_cmpxchg() to
- * update sync_sched_expedited_done to match our snapshot -- but
- * only if someone else has not already advanced past our snapshot.
+ * @oldstate: return value from earlier call to get_state_synchronize_sched()
*
- * On the other hand, if try_stop_cpus() fails, we check the value
- * of sync_sched_expedited_done. If it has advanced past our
- * initial snapshot, then someone else must have forced a grace period
- * some time after we took our snapshot. In this case, our work is
- * done for us, and we can simply return. Otherwise, we try again,
- * but keep our initial snapshot for purposes of checking for someone
- * doing our work for us.
+ * If a full RCU-sched grace period has elapsed since the earlier call to
+ * get_state_synchronize_sched(), just return. Otherwise, invoke
+ * synchronize_sched() to wait for a full grace period.
*
- * If we fail too many times in a row, we fall back to synchronize_sched().
+ * Yes, this function does not take counter wrap into account. But
+ * counter wrap is harmless. If the counter wraps, we have waited for
+ * more than 2 billion grace periods (and way more on a 64-bit system!),
+ * so waiting for one additional grace period should be just fine.
*/
-void synchronize_sched_expedited(void)
+void cond_synchronize_sched(unsigned long oldstate)
{
- cpumask_var_t cm;
- bool cma = false;
- int cpu;
- long firstsnap, s, snap;
- int trycount = 0;
- struct rcu_state *rsp = &rcu_sched_state;
+ unsigned long newstate;
/*
- * If we are in danger of counter wrap, just do synchronize_sched().
- * By allowing sync_sched_expedited_started to advance no more than
- * ULONG_MAX/8 ahead of sync_sched_expedited_done, we are ensuring
- * that more than 3.5 billion CPUs would be required to force a
- * counter wrap on a 32-bit system. Quite a few more CPUs would of
- * course be required on a 64-bit system.
+ * Ensure that this load happens before any RCU-destructive
+ * actions the caller might carry out after we return.
*/
- if (ULONG_CMP_GE((ulong)atomic_long_read(&rsp->expedited_start),
- (ulong)atomic_long_read(&rsp->expedited_done) +
- ULONG_MAX / 8)) {
+ newstate = smp_load_acquire(&rcu_sched_state.completed);
+ if (ULONG_CMP_GE(oldstate, newstate))
synchronize_sched();
- atomic_long_inc(&rsp->expedited_wrap);
+}
+EXPORT_SYMBOL_GPL(cond_synchronize_sched);
+
+/* Adjust sequence number for start of update-side operation. */
+static void rcu_seq_start(unsigned long *sp)
+{
+ WRITE_ONCE(*sp, *sp + 1);
+ smp_mb(); /* Ensure update-side operation after counter increment. */
+ WARN_ON_ONCE(!(*sp & 0x1));
+}
+
+/* Adjust sequence number for end of update-side operation. */
+static void rcu_seq_end(unsigned long *sp)
+{
+ smp_mb(); /* Ensure update-side operation before counter increment. */
+ WRITE_ONCE(*sp, *sp + 1);
+ WARN_ON_ONCE(*sp & 0x1);
+}
+
+/* Take a snapshot of the update side's sequence number. */
+static unsigned long rcu_seq_snap(unsigned long *sp)
+{
+ unsigned long s;
+
+ smp_mb(); /* Caller's modifications seen first by other CPUs. */
+ s = (READ_ONCE(*sp) + 3) & ~0x1;
+ smp_mb(); /* Above access must not bleed into critical section. */
+ return s;
+}
+
+/*
+ * Given a snapshot from rcu_seq_snap(), determine whether or not a
+ * full update-side operation has occurred.
+ */
+static bool rcu_seq_done(unsigned long *sp, unsigned long s)
+{
+ return ULONG_CMP_GE(READ_ONCE(*sp), s);
+}
+
+/* Wrapper functions for expedited grace periods. */
+static void rcu_exp_gp_seq_start(struct rcu_state *rsp)
+{
+ rcu_seq_start(&rsp->expedited_sequence);
+}
+static void rcu_exp_gp_seq_end(struct rcu_state *rsp)
+{
+ rcu_seq_end(&rsp->expedited_sequence);
+ smp_mb(); /* Ensure that consecutive grace periods serialize. */
+}
+static unsigned long rcu_exp_gp_seq_snap(struct rcu_state *rsp)
+{
+ return rcu_seq_snap(&rsp->expedited_sequence);
+}
+static bool rcu_exp_gp_seq_done(struct rcu_state *rsp, unsigned long s)
+{
+ return rcu_seq_done(&rsp->expedited_sequence, s);
+}
+
+/*
+ * Reset the ->expmaskinit values in the rcu_node tree to reflect any
+ * recent CPU-online activity. Note that these masks are not cleared
+ * when CPUs go offline, so they reflect the union of all CPUs that have
+ * ever been online. This means that this function normally takes its
+ * no-work-to-do fastpath.
+ */
+static void sync_exp_reset_tree_hotplug(struct rcu_state *rsp)
+{
+ bool done;
+ unsigned long flags;
+ unsigned long mask;
+ unsigned long oldmask;
+ int ncpus = READ_ONCE(rsp->ncpus);
+ struct rcu_node *rnp;
+ struct rcu_node *rnp_up;
+
+ /* If no new CPUs onlined since last time, nothing to do. */
+ if (likely(ncpus == rsp->ncpus_snap))
return;
- }
+ rsp->ncpus_snap = ncpus;
/*
- * Take a ticket. Note that atomic_inc_return() implies a
- * full memory barrier.
+ * Each pass through the following loop propagates newly onlined
+ * CPUs for the current rcu_node structure up the rcu_node tree.
*/
- snap = atomic_long_inc_return(&rsp->expedited_start);
- firstsnap = snap;
- 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;
+ rcu_for_each_leaf_node(rsp, rnp) {
+ raw_spin_lock_irqsave(&rnp->lock, flags);
+ smp_mb__after_unlock_lock();
+ if (rnp->expmaskinit == rnp->expmaskinitnext) {
+ raw_spin_unlock_irqrestore(&rnp->lock, flags);
+ continue; /* No new CPUs, nothing to do. */
+ }
+
+ /* Update this node's mask, track old value for propagation. */
+ oldmask = rnp->expmaskinit;
+ rnp->expmaskinit = rnp->expmaskinitnext;
+ raw_spin_unlock_irqrestore(&rnp->lock, flags);
+
+ /* If was already nonzero, nothing to propagate. */
+ if (oldmask)
+ continue;
+
+ /* Propagate the new CPU up the tree. */
+ mask = rnp->grpmask;
+ rnp_up = rnp->parent;
+ done = false;
+ while (rnp_up) {
+ raw_spin_lock_irqsave(&rnp_up->lock, flags);
+ smp_mb__after_unlock_lock();
+ if (rnp_up->expmaskinit)
+ done = true;
+ rnp_up->expmaskinit |= mask;
+ raw_spin_unlock_irqrestore(&rnp_up->lock, flags);
+ if (done)
+ break;
+ mask = rnp_up->grpmask;
+ rnp_up = rnp_up->parent;
+ }
}
- WARN_ON_ONCE(cpu_is_offline(raw_smp_processor_id()));
-
- /* Offline CPUs, idle CPUs, and any CPU we run on are quiescent. */
- cma = zalloc_cpumask_var(&cm, GFP_KERNEL);
- if (cma) {
- cpumask_copy(cm, cpu_online_mask);
- cpumask_clear_cpu(raw_smp_processor_id(), cm);
- for_each_cpu(cpu, cm) {
- struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu);
+}
+
+/*
+ * Reset the ->expmask values in the rcu_node tree in preparation for
+ * a new expedited grace period.
+ */
+static void __maybe_unused sync_exp_reset_tree(struct rcu_state *rsp)
+{
+ unsigned long flags;
+ struct rcu_node *rnp;
- if (!(atomic_add_return(0, &rdtp->dynticks) & 0x1))
- cpumask_clear_cpu(cpu, cm);
+ sync_exp_reset_tree_hotplug(rsp);
+ rcu_for_each_node_breadth_first(rsp, rnp) {
+ raw_spin_lock_irqsave(&rnp->lock, flags);
+ smp_mb__after_unlock_lock();
+ WARN_ON_ONCE(rnp->expmask);
+ rnp->expmask = rnp->expmaskinit;
+ raw_spin_unlock_irqrestore(&rnp->lock, flags);
+ }
+}
+
+/*
+ * Return non-zero if there is no RCU expedited grace period in progress
+ * for the specified rcu_node structure, in other words, if all CPUs and
+ * tasks covered by the specified rcu_node structure have done their bit
+ * for the current expedited grace period. Works only for preemptible
+ * RCU -- other RCU implementation use other means.
+ *
+ * Caller must hold the root rcu_node's exp_funnel_mutex.
+ */
+static int sync_rcu_preempt_exp_done(struct rcu_node *rnp)
+{
+ return rnp->exp_tasks == NULL &&
+ READ_ONCE(rnp->expmask) == 0;
+}
+
+/*
+ * Report the exit from RCU read-side critical section for the last task
+ * that queued itself during or before the current expedited preemptible-RCU
+ * grace period. This event is reported either to the rcu_node structure on
+ * which the task was queued or to one of that rcu_node structure's ancestors,
+ * recursively up the tree. (Calm down, calm down, we do the recursion
+ * iteratively!)
+ *
+ * Caller must hold the root rcu_node's exp_funnel_mutex and the
+ * specified rcu_node structure's ->lock.
+ */
+static void __rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
+ bool wake, unsigned long flags)
+ __releases(rnp->lock)
+{
+ unsigned long mask;
+
+ for (;;) {
+ if (!sync_rcu_preempt_exp_done(rnp)) {
+ if (!rnp->expmask)
+ rcu_initiate_boost(rnp, flags);
+ else
+ raw_spin_unlock_irqrestore(&rnp->lock, flags);
+ break;
+ }
+ if (rnp->parent == NULL) {
+ raw_spin_unlock_irqrestore(&rnp->lock, flags);
+ if (wake) {
+ smp_mb(); /* EGP done before wake_up(). */
+ swake_up(&rsp->expedited_wq);
+ }
+ break;
}
- if (cpumask_weight(cm) == 0)
- goto all_cpus_idle;
+ mask = rnp->grpmask;
+ raw_spin_unlock(&rnp->lock); /* irqs remain disabled */
+ rnp = rnp->parent;
+ raw_spin_lock(&rnp->lock); /* irqs already disabled */
+ smp_mb__after_unlock_lock();
+ WARN_ON_ONCE(!(rnp->expmask & mask));
+ rnp->expmask &= ~mask;
}
+}
+
+/*
+ * Report expedited quiescent state for specified node. This is a
+ * lock-acquisition wrapper function for __rcu_report_exp_rnp().
+ *
+ * Caller must hold the root rcu_node's exp_funnel_mutex.
+ */
+static void __maybe_unused rcu_report_exp_rnp(struct rcu_state *rsp,
+ struct rcu_node *rnp, bool wake)
+{
+ unsigned long flags;
+
+ raw_spin_lock_irqsave(&rnp->lock, flags);
+ smp_mb__after_unlock_lock();
+ __rcu_report_exp_rnp(rsp, rnp, wake, flags);
+}
+
+/*
+ * Report expedited quiescent state for multiple CPUs, all covered by the
+ * specified leaf rcu_node structure. Caller must hold the root
+ * rcu_node's exp_funnel_mutex.
+ */
+static void rcu_report_exp_cpu_mult(struct rcu_state *rsp, struct rcu_node *rnp,
+ unsigned long mask, bool wake)
+{
+ unsigned long flags;
+
+ raw_spin_lock_irqsave(&rnp->lock, flags);
+ smp_mb__after_unlock_lock();
+ if (!(rnp->expmask & mask)) {
+ raw_spin_unlock_irqrestore(&rnp->lock, flags);
+ return;
+ }
+ rnp->expmask &= ~mask;
+ __rcu_report_exp_rnp(rsp, rnp, wake, flags); /* Releases rnp->lock. */
+}
+
+/*
+ * Report expedited quiescent state for specified rcu_data (CPU).
+ * Caller must hold the root rcu_node's exp_funnel_mutex.
+ */
+static void rcu_report_exp_rdp(struct rcu_state *rsp, struct rcu_data *rdp,
+ bool wake)
+{
+ rcu_report_exp_cpu_mult(rsp, rdp->mynode, rdp->grpmask, wake);
+}
+
+/* Common code for synchronize_{rcu,sched}_expedited() work-done checking. */
+static bool sync_exp_work_done(struct rcu_state *rsp, struct rcu_node *rnp,
+ struct rcu_data *rdp,
+ atomic_long_t *stat, unsigned long s)
+{
+ if (rcu_exp_gp_seq_done(rsp, s)) {
+ if (rnp)
+ mutex_unlock(&rnp->exp_funnel_mutex);
+ else if (rdp)
+ mutex_unlock(&rdp->exp_funnel_mutex);
+ /* Ensure test happens before caller kfree(). */
+ smp_mb__before_atomic(); /* ^^^ */
+ atomic_long_inc(stat);
+ return true;
+ }
+ return false;
+}
+
+/*
+ * Funnel-lock acquisition for expedited grace periods. Returns a
+ * pointer to the root rcu_node structure, or NULL if some other
+ * task did the expedited grace period for us.
+ */
+static struct rcu_node *exp_funnel_lock(struct rcu_state *rsp, unsigned long s)
+{
+ struct rcu_data *rdp;
+ struct rcu_node *rnp0;
+ struct rcu_node *rnp1 = NULL;
/*
- * Each pass through the following loop attempts to force a
- * context switch on each CPU.
+ * First try directly acquiring the root lock in order to reduce
+ * latency in the common case where expedited grace periods are
+ * rare. We check mutex_is_locked() to avoid pathological levels of
+ * memory contention on ->exp_funnel_mutex in the heavy-load case.
*/
- while (try_stop_cpus(cma ? cm : cpu_online_mask,
- synchronize_sched_expedited_cpu_stop,
- NULL) == -EAGAIN) {
- put_online_cpus();
- atomic_long_inc(&rsp->expedited_tryfail);
-
- /* Check to see if someone else did our work for us. */
- s = atomic_long_read(&rsp->expedited_done);
- if (ULONG_CMP_GE((ulong)s, (ulong)firstsnap)) {
- /* ensure test happens before caller kfree */
- smp_mb__before_atomic(); /* ^^^ */
- atomic_long_inc(&rsp->expedited_workdone1);
- free_cpumask_var(cm);
- return;
+ rnp0 = rcu_get_root(rsp);
+ if (!mutex_is_locked(&rnp0->exp_funnel_mutex)) {
+ if (mutex_trylock(&rnp0->exp_funnel_mutex)) {
+ if (sync_exp_work_done(rsp, rnp0, NULL,
+ &rsp->expedited_workdone0, s))
+ return NULL;
+ return rnp0;
}
+ }
- /* No joy, try again later. Or just synchronize_sched(). */
- if (trycount++ < 10) {
- udelay(trycount * num_online_cpus());
- } else {
- wait_rcu_gp(call_rcu_sched);
- atomic_long_inc(&rsp->expedited_normal);
- free_cpumask_var(cm);
- return;
- }
+ /*
+ * Each pass through the following loop works its way
+ * up the rcu_node tree, returning if others have done the
+ * work or otherwise falls through holding the root rnp's
+ * ->exp_funnel_mutex. The mapping from CPU to rcu_node structure
+ * can be inexact, as it is just promoting locality and is not
+ * strictly needed for correctness.
+ */
+ rdp = per_cpu_ptr(rsp->rda, raw_smp_processor_id());
+ if (sync_exp_work_done(rsp, NULL, NULL, &rsp->expedited_workdone1, s))
+ return NULL;
+ mutex_lock(&rdp->exp_funnel_mutex);
+ rnp0 = rdp->mynode;
+ for (; rnp0 != NULL; rnp0 = rnp0->parent) {
+ if (sync_exp_work_done(rsp, rnp1, rdp,
+ &rsp->expedited_workdone2, s))
+ return NULL;
+ mutex_lock(&rnp0->exp_funnel_mutex);
+ if (rnp1)
+ mutex_unlock(&rnp1->exp_funnel_mutex);
+ else
+ mutex_unlock(&rdp->exp_funnel_mutex);
+ rnp1 = rnp0;
+ }
+ if (sync_exp_work_done(rsp, rnp1, rdp,
+ &rsp->expedited_workdone3, s))
+ return NULL;
+ return rnp1;
+}
- /* Recheck to see if someone else did our work for us. */
- s = atomic_long_read(&rsp->expedited_done);
- if (ULONG_CMP_GE((ulong)s, (ulong)firstsnap)) {
- /* ensure test happens before caller kfree */
- smp_mb__before_atomic(); /* ^^^ */
- atomic_long_inc(&rsp->expedited_workdone2);
- free_cpumask_var(cm);
- return;
+/* Invoked on each online non-idle CPU for expedited quiescent state. */
+static void sync_sched_exp_handler(void *data)
+{
+ struct rcu_data *rdp;
+ struct rcu_node *rnp;
+ struct rcu_state *rsp = data;
+
+ rdp = this_cpu_ptr(rsp->rda);
+ rnp = rdp->mynode;
+ if (!(READ_ONCE(rnp->expmask) & rdp->grpmask) ||
+ __this_cpu_read(rcu_sched_data.cpu_no_qs.b.exp))
+ return;
+ __this_cpu_write(rcu_sched_data.cpu_no_qs.b.exp, true);
+ resched_cpu(smp_processor_id());
+}
+
+/* Send IPI for expedited cleanup if needed at end of CPU-hotplug operation. */
+static void sync_sched_exp_online_cleanup(int cpu)
+{
+ struct rcu_data *rdp;
+ int ret;
+ struct rcu_node *rnp;
+ struct rcu_state *rsp = &rcu_sched_state;
+
+ rdp = per_cpu_ptr(rsp->rda, cpu);
+ rnp = rdp->mynode;
+ if (!(READ_ONCE(rnp->expmask) & rdp->grpmask))
+ return;
+ ret = smp_call_function_single(cpu, sync_sched_exp_handler, rsp, 0);
+ WARN_ON_ONCE(ret);
+}
+
+/*
+ * Select the nodes that the upcoming expedited grace period needs
+ * to wait for.
+ */
+static void sync_rcu_exp_select_cpus(struct rcu_state *rsp,
+ smp_call_func_t func)
+{
+ int cpu;
+ unsigned long flags;
+ unsigned long mask;
+ unsigned long mask_ofl_test;
+ unsigned long mask_ofl_ipi;
+ int ret;
+ struct rcu_node *rnp;
+
+ sync_exp_reset_tree(rsp);
+ rcu_for_each_leaf_node(rsp, rnp) {
+ raw_spin_lock_irqsave(&rnp->lock, flags);
+ smp_mb__after_unlock_lock();
+
+ /* Each pass checks a CPU for identity, offline, and idle. */
+ mask_ofl_test = 0;
+ for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++) {
+ struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
+ struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu);
+
+ if (raw_smp_processor_id() == cpu ||
+ !(atomic_add_return(0, &rdtp->dynticks) & 0x1))
+ mask_ofl_test |= rdp->grpmask;
}
+ mask_ofl_ipi = rnp->expmask & ~mask_ofl_test;
/*
- * Refetching sync_sched_expedited_started allows later
- * callers to piggyback on our grace period. We retry
- * after they started, so our grace period works for them,
- * and they started after our first try, so their grace
- * period works for us.
+ * Need to wait for any blocked tasks as well. Note that
+ * additional blocking tasks will also block the expedited
+ * GP until such time as the ->expmask bits are cleared.
*/
- 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);
- free_cpumask_var(cm);
- return;
+ if (rcu_preempt_has_tasks(rnp))
+ rnp->exp_tasks = rnp->blkd_tasks.next;
+ raw_spin_unlock_irqrestore(&rnp->lock, flags);
+
+ /* IPI the remaining CPUs for expedited quiescent state. */
+ mask = 1;
+ for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++, mask <<= 1) {
+ if (!(mask_ofl_ipi & mask))
+ continue;
+retry_ipi:
+ ret = smp_call_function_single(cpu, func, rsp, 0);
+ if (!ret) {
+ mask_ofl_ipi &= ~mask;
+ } else {
+ /* Failed, raced with offline. */
+ raw_spin_lock_irqsave(&rnp->lock, flags);
+ if (cpu_online(cpu) &&
+ (rnp->expmask & mask)) {
+ raw_spin_unlock_irqrestore(&rnp->lock,
+ flags);
+ schedule_timeout_uninterruptible(1);
+ if (cpu_online(cpu) &&
+ (rnp->expmask & mask))
+ goto retry_ipi;
+ raw_spin_lock_irqsave(&rnp->lock,
+ flags);
+ }
+ if (!(rnp->expmask & mask))
+ mask_ofl_ipi &= ~mask;
+ raw_spin_unlock_irqrestore(&rnp->lock, flags);
+ }
}
- snap = atomic_long_read(&rsp->expedited_start);
- smp_mb(); /* ensure read is before try_stop_cpus(). */
+ /* Report quiescent states for those that went offline. */
+ mask_ofl_test |= mask_ofl_ipi;
+ if (mask_ofl_test)
+ rcu_report_exp_cpu_mult(rsp, rnp, mask_ofl_test, false);
}
- atomic_long_inc(&rsp->expedited_stoppedcpus);
+}
-all_cpus_idle:
- free_cpumask_var(cm);
+static void synchronize_sched_expedited_wait(struct rcu_state *rsp)
+{
+ int cpu;
+ unsigned long jiffies_stall;
+ unsigned long jiffies_start;
+ unsigned long mask;
+ struct rcu_node *rnp;
+ struct rcu_node *rnp_root = rcu_get_root(rsp);
+ int ret;
- /*
- * Everyone up to our most recent fetch is covered by our grace
- * period. Update the counter, but only if our work is still
- * relevant -- which it won't be if someone who started later
- * than we did already did their update.
- */
- do {
- atomic_long_inc(&rsp->expedited_done_tries);
- s = atomic_long_read(&rsp->expedited_done);
- if (ULONG_CMP_GE((ulong)s, (ulong)snap)) {
- /* ensure test happens before caller kfree */
- smp_mb__before_atomic(); /* ^^^ */
- atomic_long_inc(&rsp->expedited_done_lost);
- break;
+ jiffies_stall = rcu_jiffies_till_stall_check();
+ jiffies_start = jiffies;
+
+ for (;;) {
+ ret = swait_event_timeout(
+ rsp->expedited_wq,
+ sync_rcu_preempt_exp_done(rnp_root),
+ jiffies_stall);
+ if (ret > 0)
+ return;
+ if (ret < 0) {
+ /* Hit a signal, disable CPU stall warnings. */
+ swait_event(rsp->expedited_wq,
+ sync_rcu_preempt_exp_done(rnp_root));
+ return;
}
- } while (atomic_long_cmpxchg(&rsp->expedited_done, s, snap) != s);
- atomic_long_inc(&rsp->expedited_done_exit);
+ pr_err("INFO: %s detected expedited stalls on CPUs/tasks: {",
+ rsp->name);
+ rcu_for_each_leaf_node(rsp, rnp) {
+ (void)rcu_print_task_exp_stall(rnp);
+ mask = 1;
+ for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++, mask <<= 1) {
+ struct rcu_data *rdp;
+
+ if (!(rnp->expmask & mask))
+ continue;
+ rdp = per_cpu_ptr(rsp->rda, cpu);
+ pr_cont(" %d-%c%c%c", cpu,
+ "O."[cpu_online(cpu)],
+ "o."[!!(rdp->grpmask & rnp->expmaskinit)],
+ "N."[!!(rdp->grpmask & rnp->expmaskinitnext)]);
+ }
+ mask <<= 1;
+ }
+ pr_cont(" } %lu jiffies s: %lu\n",
+ jiffies - jiffies_start, rsp->expedited_sequence);
+ rcu_for_each_leaf_node(rsp, rnp) {
+ mask = 1;
+ for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++, mask <<= 1) {
+ if (!(rnp->expmask & mask))
+ continue;
+ dump_cpu_task(cpu);
+ }
+ }
+ jiffies_stall = 3 * rcu_jiffies_till_stall_check() + 3;
+ }
+}
- put_online_cpus();
+/**
+ * synchronize_sched_expedited - Brute-force RCU-sched grace period
+ *
+ * Wait for an RCU-sched grace period to elapse, but use a "big hammer"
+ * approach to force the grace period to end quickly. This consumes
+ * significant time on all CPUs and is unfriendly to real-time workloads,
+ * so is thus not recommended for any sort of common-case code. In fact,
+ * if you are using synchronize_sched_expedited() in a loop, please
+ * restructure your code to batch your updates, and then use a single
+ * synchronize_sched() instead.
+ *
+ * This implementation can be thought of as an application of sequence
+ * locking to expedited grace periods, but using the sequence counter to
+ * determine when someone else has already done the work instead of for
+ * retrying readers.
+ */
+void synchronize_sched_expedited(void)
+{
+ unsigned long s;
+ struct rcu_node *rnp;
+ struct rcu_state *rsp = &rcu_sched_state;
+
+ /* Take a snapshot of the sequence number. */
+ s = rcu_exp_gp_seq_snap(rsp);
+
+ rnp = exp_funnel_lock(rsp, s);
+ if (rnp == NULL)
+ return; /* Someone else did our work for us. */
+
+ rcu_exp_gp_seq_start(rsp);
+ sync_rcu_exp_select_cpus(rsp, sync_sched_exp_handler);
+ synchronize_sched_expedited_wait(rsp);
+
+ rcu_exp_gp_seq_end(rsp);
+ mutex_unlock(&rnp->exp_funnel_mutex);
}
EXPORT_SYMBOL_GPL(synchronize_sched_expedited);
/* Is the RCU core waiting for a quiescent state from this CPU? */
if (rcu_scheduler_fully_active &&
- rdp->qs_pending && !rdp->passed_quiesce &&
+ rdp->core_needs_qs && rdp->cpu_no_qs.b.norm &&
rdp->rcu_qs_ctr_snap == __this_cpu_read(rcu_qs_ctr)) {
- rdp->n_rp_qs_pending++;
- } else if (rdp->qs_pending &&
- (rdp->passed_quiesce ||
+ rdp->n_rp_core_needs_qs++;
+ } else if (rdp->core_needs_qs &&
+ (!rdp->cpu_no_qs.b.norm ||
rdp->rcu_qs_ctr_snap != __this_cpu_read(rcu_qs_ctr))) {
rdp->n_rp_report_qs++;
return 1;
}
/* Has another RCU grace period completed? */
- if (ACCESS_ONCE(rnp->completed) != rdp->completed) { /* outside lock */
+ if (READ_ONCE(rnp->completed) != rdp->completed) { /* outside lock */
rdp->n_rp_gp_completed++;
return 1;
}
/* Has a new RCU grace period started? */
- if (ACCESS_ONCE(rnp->gpnum) != rdp->gpnum ||
- unlikely(ACCESS_ONCE(rdp->gpwrap))) { /* outside lock */
+ if (READ_ONCE(rnp->gpnum) != rdp->gpnum ||
+ unlikely(READ_ONCE(rdp->gpwrap))) { /* outside lock */
rdp->n_rp_gp_started++;
return 1;
}
* 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;
struct rcu_state *rsp = rdp->rsp;
if (atomic_dec_and_test(&rsp->barrier_cpu_count)) {
- _rcu_barrier_trace(rsp, "LastCB", -1, rsp->n_barrier_done);
+ _rcu_barrier_trace(rsp, "LastCB", -1, rsp->barrier_sequence);
complete(&rsp->barrier_completion);
} else {
- _rcu_barrier_trace(rsp, "CB", -1, rsp->n_barrier_done);
+ _rcu_barrier_trace(rsp, "CB", -1, rsp->barrier_sequence);
}
}
struct rcu_state *rsp = type;
struct rcu_data *rdp = raw_cpu_ptr(rsp->rda);
- _rcu_barrier_trace(rsp, "IRQ", -1, rsp->n_barrier_done);
+ _rcu_barrier_trace(rsp, "IRQ", -1, rsp->barrier_sequence);
atomic_inc(&rsp->barrier_cpu_count);
rsp->call(&rdp->barrier_head, rcu_barrier_callback);
}
{
int cpu;
struct rcu_data *rdp;
- unsigned long snap = ACCESS_ONCE(rsp->n_barrier_done);
- unsigned long snap_done;
+ unsigned long s = rcu_seq_snap(&rsp->barrier_sequence);
- _rcu_barrier_trace(rsp, "Begin", -1, snap);
+ _rcu_barrier_trace(rsp, "Begin", -1, s);
/* Take mutex to serialize concurrent rcu_barrier() requests. */
mutex_lock(&rsp->barrier_mutex);
- /*
- * Ensure that all prior references, including to ->n_barrier_done,
- * are ordered before the _rcu_barrier() machinery.
- */
- smp_mb(); /* See above block comment. */
-
- /*
- * Recheck ->n_barrier_done to see if others did our work for us.
- * This means checking ->n_barrier_done for an even-to-odd-to-even
- * transition. The "if" expression below therefore rounds the old
- * value up to the next even number and adds two before comparing.
- */
- snap_done = rsp->n_barrier_done;
- _rcu_barrier_trace(rsp, "Check", -1, snap_done);
-
- /*
- * If the value in snap is odd, we needed to wait for the current
- * rcu_barrier() to complete, then wait for the next one, in other
- * words, we need the value of snap_done to be three larger than
- * the value of snap. On the other hand, if the value in snap is
- * even, we only had to wait for the next rcu_barrier() to complete,
- * in other words, we need the value of snap_done to be only two
- * greater than the value of snap. The "(snap + 3) & ~0x1" computes
- * this for us (thank you, Linus!).
- */
- if (ULONG_CMP_GE(snap_done, (snap + 3) & ~0x1)) {
- _rcu_barrier_trace(rsp, "EarlyExit", -1, snap_done);
+ /* Did someone else do our work for us? */
+ if (rcu_seq_done(&rsp->barrier_sequence, s)) {
+ _rcu_barrier_trace(rsp, "EarlyExit", -1, rsp->barrier_sequence);
smp_mb(); /* caller's subsequent code after above check. */
mutex_unlock(&rsp->barrier_mutex);
return;
}
- /*
- * Increment ->n_barrier_done to avoid duplicate work. Use
- * ACCESS_ONCE() to prevent the compiler from speculating
- * the increment to precede the early-exit check.
- */
- ACCESS_ONCE(rsp->n_barrier_done) = rsp->n_barrier_done + 1;
- WARN_ON_ONCE((rsp->n_barrier_done & 0x1) != 1);
- _rcu_barrier_trace(rsp, "Inc1", -1, rsp->n_barrier_done);
- smp_mb(); /* Order ->n_barrier_done increment with below mechanism. */
+ /* Mark the start of the barrier operation. */
+ rcu_seq_start(&rsp->barrier_sequence);
+ _rcu_barrier_trace(rsp, "Inc1", -1, rsp->barrier_sequence);
/*
* Initialize the count to one rather than to zero in order to
if (rcu_is_nocb_cpu(cpu)) {
if (!rcu_nocb_cpu_needs_barrier(rsp, cpu)) {
_rcu_barrier_trace(rsp, "OfflineNoCB", cpu,
- rsp->n_barrier_done);
+ rsp->barrier_sequence);
} else {
_rcu_barrier_trace(rsp, "OnlineNoCB", cpu,
- rsp->n_barrier_done);
+ rsp->barrier_sequence);
smp_mb__before_atomic();
atomic_inc(&rsp->barrier_cpu_count);
__call_rcu(&rdp->barrier_head,
rcu_barrier_callback, rsp, cpu, 0);
}
- } else if (ACCESS_ONCE(rdp->qlen)) {
+ } else if (READ_ONCE(rdp->qlen)) {
_rcu_barrier_trace(rsp, "OnlineQ", cpu,
- rsp->n_barrier_done);
+ rsp->barrier_sequence);
smp_call_function_single(cpu, rcu_barrier_func, rsp, 1);
} else {
_rcu_barrier_trace(rsp, "OnlineNQ", cpu,
- rsp->n_barrier_done);
+ rsp->barrier_sequence);
}
}
put_online_cpus();
if (atomic_dec_and_test(&rsp->barrier_cpu_count))
complete(&rsp->barrier_completion);
- /* Increment ->n_barrier_done to prevent duplicate work. */
- smp_mb(); /* Keep increment after above mechanism. */
- ACCESS_ONCE(rsp->n_barrier_done) = rsp->n_barrier_done + 1;
- WARN_ON_ONCE((rsp->n_barrier_done & 0x1) != 0);
- _rcu_barrier_trace(rsp, "Inc2", -1, rsp->n_barrier_done);
- smp_mb(); /* Keep increment before caller's subsequent code. */
-
/* Wait for all rcu_barrier_callback() callbacks to be invoked. */
wait_for_completion(&rsp->barrier_completion);
+ /* Mark the end of the barrier operation. */
+ _rcu_barrier_trace(rsp, "Inc2", -1, rsp->barrier_sequence);
+ rcu_seq_end(&rsp->barrier_sequence);
+
/* Other rcu_barrier() invocations can now safely proceed. */
mutex_unlock(&rsp->barrier_mutex);
}
WARN_ON_ONCE(atomic_read(&rdp->dynticks->dynticks) != 1);
rdp->cpu = cpu;
rdp->rsp = rsp;
+ mutex_init(&rdp->exp_funnel_mutex);
rcu_boot_init_nocb_percpu_data(rdp);
raw_spin_unlock_irqrestore(&rnp->lock, flags);
}
/* Set up local state, ensuring consistent view of global state. */
raw_spin_lock_irqsave(&rnp->lock, flags);
- rdp->beenonline = 1; /* We have now been online. */
rdp->qlen_last_fqs_check = 0;
rdp->n_force_qs_snap = rsp->n_force_qs;
rdp->blimit = blimit;
raw_spin_lock(&rnp->lock); /* irqs already disabled. */
smp_mb__after_unlock_lock();
rnp->qsmaskinitnext |= mask;
+ rnp->expmaskinitnext |= mask;
+ if (!rdp->beenonline)
+ WRITE_ONCE(rsp->ncpus, READ_ONCE(rsp->ncpus) + 1);
+ rdp->beenonline = true; /* We have now been online. */
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->qs_pending = false;
+ rdp->cpu_no_qs.b.norm = true;
+ rdp->rcu_qs_ctr_snap = per_cpu(rcu_qs_ctr, cpu);
+ rdp->core_needs_qs = false;
trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpuonl"));
raw_spin_unlock_irqrestore(&rnp->lock, flags);
}
break;
case CPU_ONLINE:
case CPU_DOWN_FAILED:
+ sync_sched_exp_online_cleanup(cpu);
rcu_boost_kthread_setaffinity(rnp, -1);
break;
case CPU_DOWN_PREPARE:
rcu_cleanup_dying_cpu(rsp);
break;
case CPU_DYING_IDLE:
+ /* QS for any half-done expedited RCU-sched GP. */
+ preempt_disable();
+ rcu_report_exp_rdp(&rcu_sched_state,
+ this_cpu_ptr(rcu_sched_state.rda), true);
+ preempt_enable();
+
for_each_rcu_flavor(rsp) {
rcu_cleanup_dying_idle_cpu(cpu, rsp);
}
/*
* 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)
+static void __init rcu_init_levelspread(int *levelspread, const int *levelcnt)
{
int i;
- if (IS_ENABLED(CONFIG_RCU_FANOUT_EXACT)) {
- rsp->levelspread[rcu_num_lvls - 1] = rcu_fanout_leaf;
+ if (rcu_fanout_exact) {
+ levelspread[rcu_num_lvls - 1] = rcu_fanout_leaf;
for (i = rcu_num_lvls - 2; i >= 0; i--)
- rsp->levelspread[i] = CONFIG_RCU_FANOUT;
+ levelspread[i] = RCU_FANOUT;
} else {
int ccur;
int cprv;
cprv = nr_cpu_ids;
for (i = rcu_num_lvls - 1; i >= 0; i--) {
- ccur = rsp->levelcnt[i];
- rsp->levelspread[i] = (cprv + ccur - 1) / ccur;
+ ccur = levelcnt[i];
+ levelspread[i] = (cprv + ccur - 1) / ccur;
cprv = ccur;
}
}
static void __init rcu_init_one(struct rcu_state *rsp,
struct rcu_data __percpu *rda)
{
- static const char * const buf[] = {
- "rcu_node_0",
- "rcu_node_1",
- "rcu_node_2",
- "rcu_node_3" }; /* Match MAX_RCU_LVLS */
- static const char * const fqs[] = {
- "rcu_node_fqs_0",
- "rcu_node_fqs_1",
- "rcu_node_fqs_2",
- "rcu_node_fqs_3" }; /* Match MAX_RCU_LVLS */
+ static const char * const buf[] = RCU_NODE_NAME_INIT;
+ static const char * const fqs[] = RCU_FQS_NAME_INIT;
+ static const char * const exp[] = RCU_EXP_NAME_INIT;
static u8 fl_mask = 0x1;
+
+ int levelcnt[RCU_NUM_LVLS]; /* # nodes in each level. */
+ int levelspread[RCU_NUM_LVLS]; /* kids/node in each level. */
int cpustride = 1;
int i;
int j;
struct rcu_node *rnp;
- BUILD_BUG_ON(MAX_RCU_LVLS > ARRAY_SIZE(buf)); /* Fix buf[] init! */
+ BUILD_BUG_ON(RCU_NUM_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. */
for (i = 0; i < rcu_num_lvls; i++)
- rsp->levelcnt[i] = num_rcu_lvl[i];
+ levelcnt[i] = num_rcu_lvl[i];
for (i = 1; i < rcu_num_lvls; i++)
- rsp->level[i] = rsp->level[i - 1] + rsp->levelcnt[i - 1];
- rcu_init_levelspread(rsp);
+ rsp->level[i] = rsp->level[i - 1] + levelcnt[i - 1];
+ rcu_init_levelspread(levelspread, levelcnt);
rsp->flavor_mask = fl_mask;
fl_mask <<= 1;
/* Initialize the elements themselves, starting from the leaves. */
for (i = rcu_num_lvls - 1; i >= 0; i--) {
- cpustride *= rsp->levelspread[i];
+ cpustride *= levelspread[i];
rnp = rsp->level[i];
- for (j = 0; j < rsp->levelcnt[i]; j++, rnp++) {
+ for (j = 0; j < levelcnt[i]; j++, rnp++) {
raw_spin_lock_init(&rnp->lock);
lockdep_set_class_and_name(&rnp->lock,
&rcu_node_class[i], buf[i]);
rnp->grpmask = 0;
rnp->parent = NULL;
} else {
- rnp->grpnum = j % rsp->levelspread[i - 1];
+ rnp->grpnum = j % levelspread[i - 1];
rnp->grpmask = 1UL << rnp->grpnum;
rnp->parent = rsp->level[i - 1] +
- j / rsp->levelspread[i - 1];
+ j / levelspread[i - 1];
}
rnp->level = i;
INIT_LIST_HEAD(&rnp->blkd_tasks);
rcu_init_one_nocb(rnp);
+ mutex_init(&rnp->exp_funnel_mutex);
+ lockdep_set_class_and_name(&rnp->exp_funnel_mutex,
+ &rcu_exp_class[i], exp[i]);
}
}
- init_swait_head(&rsp->gp_wq);
+ init_swait_queue_head(&rsp->gp_wq);
+ init_swait_queue_head(&rsp->expedited_wq);
rnp = rsp->level[rcu_num_lvls - 1];
for_each_possible_cpu(i) {
while (i > rnp->grphi)
{
ulong d;
int i;
- int j;
- int n = nr_cpu_ids;
- int rcu_capacity[MAX_RCU_LVLS + 1];
+ int rcu_capacity[RCU_NUM_LVLS];
/*
* Initialize any unspecified boot parameters.
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",
rcu_fanout_leaf, nr_cpu_ids);
+ /*
+ * The boot-time rcu_fanout_leaf parameter must be at least two
+ * and cannot exceed the number of bits in the rcu_node masks.
+ * Complain and fall back to the compile-time values if this
+ * limit is exceeded.
+ */
+ if (rcu_fanout_leaf < 2 ||
+ rcu_fanout_leaf > sizeof(unsigned long) * 8) {
+ rcu_fanout_leaf = RCU_FANOUT_LEAF;
+ WARN_ON(1);
+ return;
+ }
+
/*
* Compute number of nodes that can be handled an rcu_node tree
- * with the given number of levels. Setting rcu_capacity[0] makes
- * some of the arithmetic easier.
+ * with the given number of levels.
*/
- 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[0] = rcu_fanout_leaf;
+ for (i = 1; i < RCU_NUM_LVLS; i++)
+ rcu_capacity[i] = rcu_capacity[i - 1] * RCU_FANOUT;
/*
- * The boot-time rcu_fanout_leaf parameter is only permitted
- * to increase the leaf-level fanout, not decrease it. Of course,
- * the leaf-level fanout cannot exceed the number of bits in
- * the rcu_node masks. Finally, the tree must be able to accommodate
- * the configured number of CPUs. Complain and fall back to the
- * compile-time values if these limits are exceeded.
+ * The tree must be able to accommodate the configured number of CPUs.
+ * If this limit is exceeded, fall back to the compile-time values.
*/
- if (rcu_fanout_leaf < CONFIG_RCU_FANOUT_LEAF ||
- rcu_fanout_leaf > sizeof(unsigned long) * 8 ||
- n > rcu_capacity[MAX_RCU_LVLS]) {
+ if (nr_cpu_ids > rcu_capacity[RCU_NUM_LVLS - 1]) {
+ rcu_fanout_leaf = RCU_FANOUT_LEAF;
WARN_ON(1);
return;
}
+ /* Calculate the number of levels in the tree. */
+ for (i = 0; nr_cpu_ids > rcu_capacity[i]; i++) {
+ }
+ rcu_num_lvls = i + 1;
+
/* Calculate the number of rcu_nodes at each level of the tree. */
- for (i = 1; i <= MAX_RCU_LVLS; i++)
- if (n <= rcu_capacity[i]) {
- for (j = 0; j <= i; j++)
- num_rcu_lvl[j] =
- DIV_ROUND_UP(n, rcu_capacity[i - j]);
- rcu_num_lvls = i;
- for (j = i + 1; j <= MAX_RCU_LVLS; j++)
- num_rcu_lvl[j] = 0;
- break;
- }
+ for (i = 0; i < rcu_num_lvls; i++) {
+ int cap = rcu_capacity[(rcu_num_lvls - 1) - i];
+ num_rcu_lvl[i] = DIV_ROUND_UP(nr_cpu_ids, cap);
+ }
/* Calculate the total number of rcu_node structures. */
rcu_num_nodes = 0;
- for (i = 0; i <= MAX_RCU_LVLS; i++)
+ for (i = 0; i < rcu_num_lvls; i++)
rcu_num_nodes += num_rcu_lvl[i];
- 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)
rcu_bootup_announce();
rcu_init_geometry();
+#ifndef CONFIG_PREEMPT_RT_FULL
rcu_init_one(&rcu_bh_state, &rcu_bh_data);
+#endif
rcu_init_one(&rcu_sched_state, &rcu_sched_data);
+ if (dump_tree)
+ rcu_dump_rcu_node_tree(&rcu_sched_state);
__rcu_init_preempt();
/*