lkml.org 
[lkml]   [2019]   [Oct]   [2]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
From
Subject[PATCH tip/core/rcu 10/12] rcu: Reset CPU hints when reporting a quiescent state
Date
From: "Joel Fernandes (Google)" <joel@joelfernandes.org>

In some cases, tracing shows that need_heavy_qs is still set even though
urgent_qs was cleared upon reporting of a quiescent state. One such
case is when the softirq reports that a CPU has passed quiescent state.

Commit 671a63517cf9 ("rcu: Avoid unnecessary softirq when system is
idle") fixed a bug where core_needs_qs was not being cleared. In order
to avoid running into similar situations with the urgent-grace-period
flags, this commit causes rcu_disable_urgency_upon_qs(), previously
rcu_disable_tick_upon_qs(), to clear the urgency hints, ->rcu_urgent_qs
and ->rcu_need_heavy_qs. Note that it is possible for CPUs to go
offline with these urgency hints still set. This is handled because
rcu_disable_urgency_upon_qs() is also invoked during the online process.

Because these hints can be cleared both by the corresponding CPU and by
the grace-period kthread, this commit also adds a number of READ_ONCE()
and WRITE_ONCE() calls.

Tested overnight with rcutorture running for 60 minutes on all
configurations of RCU.

Signed-off-by: "Joel Fernandes (Google)" <joel@joelfernandes.org>
[ paulmck: Clear urgency flags in rcu_disable_urgency_upon_qs(). ]
[ paulmck: Remove ->core_needs_qs from the set cleared at quiescent state. ]
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
---
kernel/rcu/tree.c | 17 ++++++++++-------
1 file changed, 10 insertions(+), 7 deletions(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 1601fa6..59527b0 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -826,7 +826,7 @@ static __always_inline void rcu_nmi_enter_common(bool irq)
incby = 1;
} else if (tick_nohz_full_cpu(rdp->cpu) &&
rdp->dynticks_nmi_nesting == DYNTICK_IRQ_NONIDLE &&
- rdp->rcu_urgent_qs && !rdp->rcu_forced_tick) {
+ READ_ONCE(rdp->rcu_urgent_qs) && !rdp->rcu_forced_tick) {
rdp->rcu_forced_tick = true;
tick_dep_set_cpu(rdp->cpu, TICK_DEP_BIT_RCU);
}
@@ -891,11 +891,14 @@ void rcu_irq_enter_irqson(void)
}

/*
- * If the scheduler-clock interrupt was enabled on a nohz_full CPU
- * in order to get to a quiescent state, disable it.
+ * If any sort of urgency was applied to the current CPU (for example,
+ * the scheduler-clock interrupt was enabled on a nohz_full CPU) in order
+ * to get to a quiescent state, disable it.
*/
-void rcu_disable_tick_upon_qs(struct rcu_data *rdp)
+void rcu_disable_urgency_upon_qs(struct rcu_data *rdp)
{
+ WRITE_ONCE(rdp->rcu_urgent_qs, false);
+ WRITE_ONCE(rdp->rcu_need_heavy_qs, false);
if (tick_nohz_full_cpu(rdp->cpu) && rdp->rcu_forced_tick) {
tick_dep_clear_cpu(rdp->cpu, TICK_DEP_BIT_RCU);
rdp->rcu_forced_tick = false;
@@ -1996,7 +1999,7 @@ rcu_report_qs_rdp(int cpu, struct rcu_data *rdp)
if (!offloaded)
needwake = rcu_accelerate_cbs(rnp, rdp);

- rcu_disable_tick_upon_qs(rdp);
+ rcu_disable_urgency_upon_qs(rdp);
rcu_report_qs_rnp(mask, rnp, rnp->gp_seq, flags);
/* ^^^ Released rnp->lock */
if (needwake)
@@ -2314,7 +2317,7 @@ static void force_qs_rnp(int (*f)(struct rcu_data *rdp))
rdp = per_cpu_ptr(&rcu_data, cpu);
if (f(rdp)) {
mask |= bit;
- rcu_disable_tick_upon_qs(rdp);
+ rcu_disable_urgency_upon_qs(rdp);
}
}
}
@@ -3189,7 +3192,7 @@ void rcu_cpu_starting(unsigned int cpu)
rdp->rcu_onl_gp_seq = READ_ONCE(rcu_state.gp_seq);
rdp->rcu_onl_gp_flags = READ_ONCE(rcu_state.gp_flags);
if (rnp->qsmask & mask) { /* RCU waiting on incoming CPU? */
- rcu_disable_tick_upon_qs(rdp);
+ rcu_disable_urgency_upon_qs(rdp);
/* Report QS -after- changing ->qsmaskinitnext! */
rcu_report_qs_rnp(mask, rnp, rnp->gp_seq, flags);
} else {
--
2.9.5
\
 
 \ /
  Last update: 2019-10-03 03:40    [W:0.084 / U:0.088 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site