early_param("rcu_nocb_poll", parse_rcu_nocb_poll);
/*
- * Acquire the specified rcu_data structure's ->nocb_lock, but only
- * if it corresponds to a no-CBs CPU. If the lock isn't immediately
- * available, increment ->nocb_lock_contended to flag the contention.
+ * Don't bother bypassing ->cblist if the call_rcu() rate is low.
+ * After all, the main point of bypassing is to avoid lock contention
+ * on ->nocb_lock, which only can happen at high call_rcu() rates.
*/
-static void rcu_nocb_lock(struct rcu_data *rdp)
+int nocb_nobypass_lim_per_jiffy = 16 * 1000 / HZ;
+module_param(nocb_nobypass_lim_per_jiffy, int, 0);
+
+/*
+ * Acquire the specified rcu_data structure's ->nocb_bypass_lock. If the
+ * lock isn't immediately available, increment ->nocb_lock_contended to
+ * flag the contention.
+ */
+static void rcu_nocb_bypass_lock(struct rcu_data *rdp)
{
lockdep_assert_irqs_disabled();
- if (!rcu_segcblist_is_offloaded(&rdp->cblist) ||
- raw_spin_trylock(&rdp->nocb_lock))
+ if (raw_spin_trylock(&rdp->nocb_bypass_lock))
return;
atomic_inc(&rdp->nocb_lock_contended);
smp_mb__after_atomic(); /* atomic_inc() before lock. */
- raw_spin_lock(&rdp->nocb_lock);
+ raw_spin_lock(&rdp->nocb_bypass_lock);
smp_mb__before_atomic(); /* atomic_dec() after lock. */
atomic_dec(&rdp->nocb_lock_contended);
}
}
/*
+ * Conditionally acquire the specified rcu_data structure's
+ * ->nocb_bypass_lock.
+ */
+static bool rcu_nocb_bypass_trylock(struct rcu_data *rdp)
+{
+ lockdep_assert_irqs_disabled();
+ return raw_spin_trylock(&rdp->nocb_bypass_lock);
+}
+
+/*
+ * Release the specified rcu_data structure's ->nocb_bypass_lock.
+ */
+static void rcu_nocb_bypass_unlock(struct rcu_data *rdp)
+{
+ lockdep_assert_irqs_disabled();
+ raw_spin_unlock(&rdp->nocb_bypass_lock);
+}
+
+/*
+ * Acquire the specified rcu_data structure's ->nocb_lock, but only
+ * if it corresponds to a no-CBs CPU.
+ */
+static void rcu_nocb_lock(struct rcu_data *rdp)
+{
+ lockdep_assert_irqs_disabled();
+ if (!rcu_segcblist_is_offloaded(&rdp->cblist))
+ return;
+ raw_spin_lock(&rdp->nocb_lock);
+}
+
+/*
* Release the specified rcu_data structure's ->nocb_lock, but only
* if it corresponds to a no-CBs CPU.
*/
}
}
+/* Lockdep check that ->cblist may be safely accessed. */
+static void rcu_lockdep_assert_cblist_protected(struct rcu_data *rdp)
+{
+ lockdep_assert_irqs_disabled();
+ if (rcu_segcblist_is_offloaded(&rdp->cblist) &&
+ cpu_online(rdp->cpu))
+ lockdep_assert_held(&rdp->nocb_lock);
+}
+
/*
* Wake up any no-CBs CPUs' kthreads that were waiting on the just-ended
* grace period.
unsigned long flags)
__releases(rdp->nocb_lock)
{
+ bool needwake = false;
struct rcu_data *rdp_gp = rdp->nocb_gp_rdp;
lockdep_assert_held(&rdp->nocb_lock);
if (!READ_ONCE(rdp_gp->nocb_gp_kthread)) {
+ trace_rcu_nocb_wake(rcu_state.name, rdp->cpu,
+ TPS("AlreadyAwake"));
rcu_nocb_unlock_irqrestore(rdp, flags);
return;
}
- if (READ_ONCE(rdp_gp->nocb_gp_sleep) || force) {
- del_timer(&rdp->nocb_timer);
- rcu_nocb_unlock_irqrestore(rdp, flags);
- smp_mb(); /* enqueue before ->nocb_gp_sleep. */
- raw_spin_lock_irqsave(&rdp_gp->nocb_gp_lock, flags);
+ del_timer(&rdp->nocb_timer);
+ rcu_nocb_unlock_irqrestore(rdp, flags);
+ raw_spin_lock_irqsave(&rdp_gp->nocb_gp_lock, flags);
+ if (force || READ_ONCE(rdp_gp->nocb_gp_sleep)) {
WRITE_ONCE(rdp_gp->nocb_gp_sleep, false);
- raw_spin_unlock_irqrestore(&rdp_gp->nocb_gp_lock, flags);
- wake_up_process(rdp_gp->nocb_gp_kthread);
- } else {
- rcu_nocb_unlock_irqrestore(rdp, flags);
+ needwake = true;
+ trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("DoWake"));
}
+ raw_spin_unlock_irqrestore(&rdp_gp->nocb_gp_lock, flags);
+ if (needwake)
+ wake_up_process(rdp_gp->nocb_gp_kthread);
}
/*
}
/*
+ * Flush the ->nocb_bypass queue into ->cblist, enqueuing rhp if non-NULL.
+ * However, if there is a callback to be enqueued and if ->nocb_bypass
+ * proves to be initially empty, just return false because the no-CB GP
+ * kthread may need to be awakened in this case.
+ *
+ * Note that this function always returns true if rhp is NULL.
+ */
+static bool rcu_nocb_do_flush_bypass(struct rcu_data *rdp, struct rcu_head *rhp,
+ unsigned long j)
+{
+ struct rcu_cblist rcl;
+
+ WARN_ON_ONCE(!rcu_segcblist_is_offloaded(&rdp->cblist));
+ rcu_lockdep_assert_cblist_protected(rdp);
+ lockdep_assert_held(&rdp->nocb_bypass_lock);
+ if (rhp && !rcu_cblist_n_cbs(&rdp->nocb_bypass)) {
+ raw_spin_unlock(&rdp->nocb_bypass_lock);
+ return false;
+ }
+ /* Note: ->cblist.len already accounts for ->nocb_bypass contents. */
+ if (rhp)
+ rcu_segcblist_inc_len(&rdp->cblist); /* Must precede enqueue. */
+ rcu_cblist_flush_enqueue(&rcl, &rdp->nocb_bypass, rhp);
+ rcu_segcblist_insert_pend_cbs(&rdp->cblist, &rcl);
+ WRITE_ONCE(rdp->nocb_bypass_first, j);
+ rcu_nocb_bypass_unlock(rdp);
+ return true;
+}
+
+/*
+ * Flush the ->nocb_bypass queue into ->cblist, enqueuing rhp if non-NULL.
+ * However, if there is a callback to be enqueued and if ->nocb_bypass
+ * proves to be initially empty, just return false because the no-CB GP
+ * kthread may need to be awakened in this case.
+ *
+ * Note that this function always returns true if rhp is NULL.
+ */
+static bool rcu_nocb_flush_bypass(struct rcu_data *rdp, struct rcu_head *rhp,
+ unsigned long j)
+{
+ if (!rcu_segcblist_is_offloaded(&rdp->cblist))
+ return true;
+ rcu_lockdep_assert_cblist_protected(rdp);
+ rcu_nocb_bypass_lock(rdp);
+ return rcu_nocb_do_flush_bypass(rdp, rhp, j);
+}
+
+/*
+ * If the ->nocb_bypass_lock is immediately available, flush the
+ * ->nocb_bypass queue into ->cblist.
+ */
+static void rcu_nocb_try_flush_bypass(struct rcu_data *rdp, unsigned long j)
+{
+ rcu_lockdep_assert_cblist_protected(rdp);
+ if (!rcu_segcblist_is_offloaded(&rdp->cblist) ||
+ !rcu_nocb_bypass_trylock(rdp))
+ return;
+ WARN_ON_ONCE(!rcu_nocb_do_flush_bypass(rdp, NULL, j));
+}
+
+/*
+ * See whether it is appropriate to use the ->nocb_bypass list in order
+ * to control contention on ->nocb_lock. A limited number of direct
+ * enqueues are permitted into ->cblist per jiffy. If ->nocb_bypass
+ * is non-empty, further callbacks must be placed into ->nocb_bypass,
+ * otherwise rcu_barrier() breaks. Use rcu_nocb_flush_bypass() to switch
+ * back to direct use of ->cblist. However, ->nocb_bypass should not be
+ * used if ->cblist is empty, because otherwise callbacks can be stranded
+ * on ->nocb_bypass because we cannot count on the current CPU ever again
+ * invoking call_rcu(). The general rule is that if ->nocb_bypass is
+ * non-empty, the corresponding no-CBs grace-period kthread must not be
+ * in an indefinite sleep state.
+ *
+ * Finally, it is not permitted to use the bypass during early boot,
+ * as doing so would confuse the auto-initialization code. Besides
+ * which, there is no point in worrying about lock contention while
+ * there is only one CPU in operation.
+ */
+static bool rcu_nocb_try_bypass(struct rcu_data *rdp, struct rcu_head *rhp,
+ bool *was_alldone, unsigned long flags)
+{
+ unsigned long c;
+ unsigned long cur_gp_seq;
+ unsigned long j = jiffies;
+ long ncbs = rcu_cblist_n_cbs(&rdp->nocb_bypass);
+
+ if (!rcu_segcblist_is_offloaded(&rdp->cblist)) {
+ *was_alldone = !rcu_segcblist_pend_cbs(&rdp->cblist);
+ return false; /* Not offloaded, no bypassing. */
+ }
+ lockdep_assert_irqs_disabled();
+
+ // Don't use ->nocb_bypass during early boot.
+ if (rcu_scheduler_active != RCU_SCHEDULER_RUNNING) {
+ rcu_nocb_lock(rdp);
+ WARN_ON_ONCE(rcu_cblist_n_cbs(&rdp->nocb_bypass));
+ *was_alldone = !rcu_segcblist_pend_cbs(&rdp->cblist);
+ return false;
+ }
+
+ // If we have advanced to a new jiffy, reset counts to allow
+ // moving back from ->nocb_bypass to ->cblist.
+ if (j == rdp->nocb_nobypass_last) {
+ c = rdp->nocb_nobypass_count + 1;
+ } else {
+ WRITE_ONCE(rdp->nocb_nobypass_last, j);
+ c = rdp->nocb_nobypass_count - nocb_nobypass_lim_per_jiffy;
+ if (ULONG_CMP_LT(rdp->nocb_nobypass_count,
+ nocb_nobypass_lim_per_jiffy))
+ c = 0;
+ else if (c > nocb_nobypass_lim_per_jiffy)
+ c = nocb_nobypass_lim_per_jiffy;
+ }
+ WRITE_ONCE(rdp->nocb_nobypass_count, c);
+
+ // If there hasn't yet been all that many ->cblist enqueues
+ // this jiffy, tell the caller to enqueue onto ->cblist. But flush
+ // ->nocb_bypass first.
+ if (rdp->nocb_nobypass_count < nocb_nobypass_lim_per_jiffy) {
+ rcu_nocb_lock(rdp);
+ *was_alldone = !rcu_segcblist_pend_cbs(&rdp->cblist);
+ if (*was_alldone)
+ trace_rcu_nocb_wake(rcu_state.name, rdp->cpu,
+ TPS("FirstQ"));
+ WARN_ON_ONCE(!rcu_nocb_flush_bypass(rdp, NULL, j));
+ WARN_ON_ONCE(rcu_cblist_n_cbs(&rdp->nocb_bypass));
+ return false; // Caller must enqueue the callback.
+ }
+
+ // If ->nocb_bypass has been used too long or is too full,
+ // flush ->nocb_bypass to ->cblist.
+ if ((ncbs && j != READ_ONCE(rdp->nocb_bypass_first)) ||
+ ncbs >= qhimark) {
+ rcu_nocb_lock(rdp);
+ if (!rcu_nocb_flush_bypass(rdp, rhp, j)) {
+ *was_alldone = !rcu_segcblist_pend_cbs(&rdp->cblist);
+ if (*was_alldone)
+ trace_rcu_nocb_wake(rcu_state.name, rdp->cpu,
+ TPS("FirstQ"));
+ WARN_ON_ONCE(rcu_cblist_n_cbs(&rdp->nocb_bypass));
+ return false; // Caller must enqueue the callback.
+ }
+ if (j != rdp->nocb_gp_adv_time &&
+ rcu_segcblist_nextgp(&rdp->cblist, &cur_gp_seq) &&
+ rcu_seq_done(&rdp->mynode->gp_seq, cur_gp_seq)) {
+ rcu_advance_cbs_nowake(rdp->mynode, rdp);
+ rdp->nocb_gp_adv_time = j;
+ }
+ rcu_nocb_unlock_irqrestore(rdp, flags);
+ return true; // Callback already enqueued.
+ }
+
+ // We need to use the bypass.
+ rcu_nocb_wait_contended(rdp);
+ rcu_nocb_bypass_lock(rdp);
+ ncbs = rcu_cblist_n_cbs(&rdp->nocb_bypass);
+ rcu_segcblist_inc_len(&rdp->cblist); /* Must precede enqueue. */
+ rcu_cblist_enqueue(&rdp->nocb_bypass, rhp);
+ if (!ncbs) {
+ WRITE_ONCE(rdp->nocb_bypass_first, j);
+ trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("FirstBQ"));
+ }
+ rcu_nocb_bypass_unlock(rdp);
+ smp_mb(); /* Order enqueue before wake. */
+ if (ncbs) {
+ local_irq_restore(flags);
+ } else {
+ // No-CBs GP kthread might be indefinitely asleep, if so, wake.
+ rcu_nocb_lock(rdp); // Rare during call_rcu() flood.
+ if (!rcu_segcblist_pend_cbs(&rdp->cblist)) {
+ trace_rcu_nocb_wake(rcu_state.name, rdp->cpu,
+ TPS("FirstBQwake"));
+ __call_rcu_nocb_wake(rdp, true, flags);
+ } else {
+ trace_rcu_nocb_wake(rcu_state.name, rdp->cpu,
+ TPS("FirstBQnoWake"));
+ rcu_nocb_unlock_irqrestore(rdp, flags);
+ }
+ }
+ return true; // Callback already enqueued.
+}
+
+/*
* Awaken the no-CBs grace-period kthead if needed, either due to it
* legitimately being asleep or due to overload conditions.
*
trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("WakeNot"));
rcu_nocb_unlock_irqrestore(rdp, flags);
}
- if (!irqs_disabled_flags(flags)) {
- lockdep_assert_irqs_enabled();
- rcu_nocb_wait_contended(rdp);
- }
return;
}
+/* Wake up the no-CBs GP kthread to flush ->nocb_bypass. */
+static void do_nocb_bypass_wakeup_timer(struct timer_list *t)
+{
+ unsigned long flags;
+ struct rcu_data *rdp = from_timer(rdp, t, nocb_bypass_timer);
+
+ trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("Timer"));
+ rcu_nocb_lock_irqsave(rdp, flags);
+ __call_rcu_nocb_wake(rdp, true, flags);
+}
+
/*
* No-CBs GP kthreads come here to wait for additional callbacks to show up
* or for grace periods to end.
*/
static void nocb_gp_wait(struct rcu_data *my_rdp)
{
+ bool bypass = false;
+ long bypass_ncbs;
int __maybe_unused cpu = my_rdp->cpu;
unsigned long cur_gp_seq;
unsigned long flags;
bool gotcbs;
+ unsigned long j = jiffies;
bool needwait_gp = false; // This prevents actual uninitialized use.
bool needwake;
bool needwake_gp;
* and the global grace-period kthread are awakened if needed.
*/
for (rdp = my_rdp; rdp; rdp = rdp->nocb_next_cb_rdp) {
- if (rcu_segcblist_empty(&rdp->cblist))
+ trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("Check"));
+ rcu_nocb_lock_irqsave(rdp, flags);
+ bypass_ncbs = rcu_cblist_n_cbs(&rdp->nocb_bypass);
+ if (bypass_ncbs &&
+ (time_after(j, READ_ONCE(rdp->nocb_bypass_first) + 1) ||
+ bypass_ncbs > 2 * qhimark)) {
+ // Bypass full or old, so flush it.
+ (void)rcu_nocb_try_flush_bypass(rdp, j);
+ bypass_ncbs = rcu_cblist_n_cbs(&rdp->nocb_bypass);
+ } else if (!bypass_ncbs && rcu_segcblist_empty(&rdp->cblist)) {
+ rcu_nocb_unlock_irqrestore(rdp, flags);
continue; /* No callbacks here, try next. */
+ }
+ if (bypass_ncbs) {
+ trace_rcu_nocb_wake(rcu_state.name, rdp->cpu,
+ TPS("Bypass"));
+ bypass = true;
+ }
rnp = rdp->mynode;
- rcu_nocb_lock_irqsave(rdp, flags);
- WRITE_ONCE(my_rdp->nocb_defer_wakeup, RCU_NOCB_WAKE_NOT);
- del_timer(&my_rdp->nocb_timer);
- raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */
- needwake_gp = rcu_advance_cbs(rnp, rdp);
- raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled. */
+ if (bypass) { // Avoid race with first bypass CB.
+ WRITE_ONCE(my_rdp->nocb_defer_wakeup,
+ RCU_NOCB_WAKE_NOT);
+ del_timer(&my_rdp->nocb_timer);
+ }
+ // Advance callbacks if helpful and low contention.
+ needwake_gp = false;
+ if (!rcu_segcblist_restempty(&rdp->cblist,
+ RCU_NEXT_READY_TAIL) ||
+ (rcu_segcblist_nextgp(&rdp->cblist, &cur_gp_seq) &&
+ rcu_seq_done(&rnp->gp_seq, cur_gp_seq))) {
+ raw_spin_lock_rcu_node(rnp); /* irqs disabled. */
+ needwake_gp = rcu_advance_cbs(rnp, rdp);
+ raw_spin_unlock_rcu_node(rnp); /* irqs disabled. */
+ }
// Need to wait on some grace period?
+ WARN_ON_ONCE(!rcu_segcblist_restempty(&rdp->cblist,
+ RCU_NEXT_READY_TAIL));
if (rcu_segcblist_nextgp(&rdp->cblist, &cur_gp_seq)) {
if (!needwait_gp ||
ULONG_CMP_LT(cur_gp_seq, wait_gp_seq))
wait_gp_seq = cur_gp_seq;
needwait_gp = true;
+ trace_rcu_nocb_wake(rcu_state.name, rdp->cpu,
+ TPS("NeedWaitGP"));
}
if (rcu_segcblist_ready_cbs(&rdp->cblist)) {
needwake = rdp->nocb_cb_sleep;
rcu_gp_kthread_wake();
}
+ if (bypass && !rcu_nocb_poll) {
+ // At least one child with non-empty ->nocb_bypass, so set
+ // timer in order to avoid stranding its callbacks.
+ raw_spin_lock_irqsave(&my_rdp->nocb_gp_lock, flags);
+ mod_timer(&my_rdp->nocb_bypass_timer, j + 2);
+ raw_spin_unlock_irqrestore(&my_rdp->nocb_gp_lock, flags);
+ }
if (rcu_nocb_poll) {
/* Polling, so trace if first poll in the series. */
if (gotcbs)
trace_rcu_nocb_wake(rcu_state.name, cpu, TPS("Sleep"));
swait_event_interruptible_exclusive(my_rdp->nocb_gp_wq,
!READ_ONCE(my_rdp->nocb_gp_sleep));
+ trace_rcu_nocb_wake(rcu_state.name, cpu, TPS("EndSleep"));
} else {
rnp = my_rdp->mynode;
trace_rcu_this_gp(rnp, my_rdp, wait_gp_seq, TPS("StartWait"));
}
if (!rcu_nocb_poll) {
raw_spin_lock_irqsave(&my_rdp->nocb_gp_lock, flags);
+ if (bypass)
+ del_timer(&my_rdp->nocb_bypass_timer);
WRITE_ONCE(my_rdp->nocb_gp_sleep, true);
raw_spin_unlock_irqrestore(&my_rdp->nocb_gp_lock, flags);
}
init_swait_queue_head(&rdp->nocb_cb_wq);
init_swait_queue_head(&rdp->nocb_gp_wq);
raw_spin_lock_init(&rdp->nocb_lock);
+ raw_spin_lock_init(&rdp->nocb_bypass_lock);
raw_spin_lock_init(&rdp->nocb_gp_lock);
timer_setup(&rdp->nocb_timer, do_nocb_deferred_wakeup_timer, 0);
+ timer_setup(&rdp->nocb_bypass_timer, do_nocb_bypass_wakeup_timer, 0);
+ rcu_cblist_init(&rdp->nocb_bypass);
}
/*
local_irq_restore(flags);
}
+/* Lockdep check that ->cblist may be safely accessed. */
+static void rcu_lockdep_assert_cblist_protected(struct rcu_data *rdp)
+{
+ lockdep_assert_irqs_disabled();
+}
+
static void rcu_nocb_gp_cleanup(struct swait_queue_head *sq)
{
}
{
}
+static bool rcu_nocb_flush_bypass(struct rcu_data *rdp, struct rcu_head *rhp,
+ unsigned long j)
+{
+ return true;
+}
+
+static bool rcu_nocb_try_bypass(struct rcu_data *rdp, struct rcu_head *rhp,
+ bool *was_alldone, unsigned long flags)
+{
+ return false;
+}
+
static void __call_rcu_nocb_wake(struct rcu_data *rdp, bool was_empty,
unsigned long flags)
{
OSDN Git Service
