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];
+static struct lock_class_key rcu_exp_sched_class[RCU_NUM_LVLS];
/*
* In order to export the rcu_state name to the tracing tools, it
* 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.");
}
/*
}
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
}
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
{
bool ret;
- preempt_disable();
+ preempt_disable_notrace();
ret = __rcu_is_watching();
- preempt_enable();
+ preempt_enable_notrace();
return ret;
}
EXPORT_SYMBOL_GPL(rcu_is_watching);
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.
*/
TPS("fqswait"));
rsp->gp_state = RCU_GP_WAIT_FQS;
ret = wait_event_interruptible_timeout(rsp->gp_wq,
- ((gf = READ_ONCE(rsp->gp_flags)) &
- RCU_GP_FLAG_FQS) ||
- (!READ_ONCE(rnp->qsmask) &&
- !rcu_preempt_blocked_readers_cgp(rnp)),
- j);
- rsp->gp_state = RCU_GP_DONE_FQS;
+ 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 (!READ_ONCE(rnp->qsmask) &&
*/
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);
+/**
+ * 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)
+{
+ /*
+ * Any prior manipulation of RCU-protected data must happen
+ * before the load from ->gpnum.
+ */
+ 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);
+
+/**
+ * cond_synchronize_sched - Conditionally wait for an RCU-sched grace period
+ *
+ * @oldstate: return value from earlier call to get_state_synchronize_sched()
+ *
+ * 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.
+ *
+ * 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 cond_synchronize_sched(unsigned long oldstate)
+{
+ unsigned long newstate;
+
+ /*
+ * Ensure that this load happens before any RCU-destructive
+ * actions the caller might carry out after we return.
+ */
+ newstate = smp_load_acquire(&rcu_sched_state.completed);
+ if (ULONG_CMP_GE(oldstate, newstate))
+ synchronize_sched();
+}
+EXPORT_SYMBOL_GPL(cond_synchronize_sched);
+
/* Adjust sequence number for start of update-side operation. */
static void rcu_seq_start(unsigned long *sp)
{
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)
{
/* 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);
*/
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;
+ /*
+ * 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.
+ */
+ 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;
+ }
+ }
+
/*
* Each pass through the following loop works its way
* up the rcu_node tree, returning if others have done the
* can be inexact, as it is just promoting locality and is not
* strictly needed for correctness.
*/
- rnp0 = per_cpu_ptr(rsp->rda, raw_smp_processor_id())->mynode;
+ 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, &rsp->expedited_workdone1, s))
+ 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, &rsp->expedited_workdone2, s))
+ if (sync_exp_work_done(rsp, rnp1, rdp,
+ &rsp->expedited_workdone3, s))
return NULL;
return rnp1;
}
+/* Invoked on each online non-idle CPU for expedited quiescent state. */
static int synchronize_sched_expedited_cpu_stop(void *data)
{
- struct rcu_state *rsp = data;
+ struct rcu_data *rdp = data;
+ struct rcu_state *rsp = rdp->rsp;
/* We are here: If we are last, do the wakeup. */
+ rdp->exp_done = true;
if (atomic_dec_and_test(&rsp->expedited_need_qs))
wake_up(&rsp->expedited_wq);
return 0;
}
+static void synchronize_sched_expedited_wait(struct rcu_state *rsp)
+{
+ int cpu;
+ unsigned long jiffies_stall;
+ unsigned long jiffies_start;
+ struct rcu_data *rdp;
+ int ret;
+
+ jiffies_stall = rcu_jiffies_till_stall_check();
+ jiffies_start = jiffies;
+
+ for (;;) {
+ ret = wait_event_interruptible_timeout(
+ rsp->expedited_wq,
+ !atomic_read(&rsp->expedited_need_qs),
+ jiffies_stall);
+ if (ret > 0)
+ return;
+ if (ret < 0) {
+ /* Hit a signal, disable CPU stall warnings. */
+ wait_event(rsp->expedited_wq,
+ !atomic_read(&rsp->expedited_need_qs));
+ return;
+ }
+ pr_err("INFO: %s detected expedited stalls on CPUs: {",
+ rsp->name);
+ for_each_online_cpu(cpu) {
+ rdp = per_cpu_ptr(rsp->rda, cpu);
+
+ if (rdp->exp_done)
+ continue;
+ pr_cont(" %d", cpu);
+ }
+ pr_cont(" } %lu jiffies s: %lu\n",
+ jiffies - jiffies_start, rsp->expedited_sequence);
+ for_each_online_cpu(cpu) {
+ rdp = per_cpu_ptr(rsp->rda, cpu);
+
+ if (rdp->exp_done)
+ continue;
+ dump_cpu_task(cpu);
+ }
+ jiffies_stall = 3 * rcu_jiffies_till_stall_check() + 3;
+ }
+}
+
/**
* synchronize_sched_expedited - Brute-force RCU-sched grace period
*
struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu);
+ rdp->exp_done = false;
+
/* Skip our CPU and any idle CPUs. */
if (raw_smp_processor_id() == cpu ||
!(atomic_add_return(0, &rdtp->dynticks) & 0x1))
continue;
atomic_inc(&rsp->expedited_need_qs);
stop_one_cpu_nowait(cpu, synchronize_sched_expedited_cpu_stop,
- rsp, &rdp->exp_stop_work);
+ rdp, &rdp->exp_stop_work);
}
/* Remove extra count and, if necessary, wait for CPUs to stop. */
if (!atomic_dec_and_test(&rsp->expedited_need_qs))
- wait_event(rsp->expedited_wq,
- !atomic_read(&rsp->expedited_need_qs));
+ synchronize_sched_expedited_wait(rsp);
rcu_exp_gp_seq_end(rsp);
mutex_unlock(&rnp->exp_funnel_mutex);
- smp_mb(); /* ensure subsequent action seen after grace period. */
put_online_cpus();
}
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);
}
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 const char * const exp_sched[] = RCU_EXP_SCHED_NAME_INIT;
static u8 fl_mask = 0x1;
int levelcnt[RCU_NUM_LVLS]; /* # nodes in each level. */
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]);
+ if (rsp == &rcu_sched_state)
+ lockdep_set_class_and_name(
+ &rnp->exp_funnel_mutex,
+ &rcu_exp_sched_class[i], exp_sched[i]);
+ else
+ lockdep_set_class_and_name(
+ &rnp->exp_funnel_mutex,
+ &rcu_exp_class[i], exp[i]);
}
}