nohz: Allow rcu extended quiescent state handling seperately from tick stop
It is assumed that rcu won't be used once we switch to tickless
mode and until we restart the tick. However this is not always
true, as in x86-64 where we dereference the idle notifiers after
the tick is stopped.
To prepare for fixing this, add two new APIs:
tick_nohz_idle_enter_norcu() and tick_nohz_idle_exit_norcu().
If no use of RCU is made in the idle loop between
tick_nohz_enter_idle() and tick_nohz_exit_idle() calls, the arch
must instead call the new *_norcu() version such that the arch doesn't
need to call rcu_idle_enter() and rcu_idle_exit().
Otherwise the arch must call tick_nohz_enter_idle() and
tick_nohz_exit_idle() and also call explicitly:
- rcu_idle_enter() after its last use of RCU before the CPU is put
to sleep.
- rcu_idle_exit() before the first use of RCU after the CPU is woken
up.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Mike Frysinger <vapier@gentoo.org>
Cc: Guan Xuetao <gxt@mprc.pku.edu.cn>
Cc: David Miller <davem@davemloft.net>
Cc: Chris Metcalf <cmetcalf@tilera.com>
Cc: Hans-Christian Egtvedt <hans-christian.egtvedt@atmel.com>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Paul Mundt <lethal@linux-sh.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index 3f1f8da..47e34c0 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -183,7 +183,7 @@
/* endless idle loop with no priority at all */
while (1) {
- tick_nohz_idle_enter();
+ tick_nohz_idle_enter_norcu();
leds_event(led_idle_start);
while (!need_resched()) {
#ifdef CONFIG_HOTPLUG_CPU
@@ -213,7 +213,7 @@
}
}
leds_event(led_idle_end);
- tick_nohz_idle_exit();
+ tick_nohz_idle_exit_norcu();
preempt_enable_no_resched();
schedule();
preempt_disable();
diff --git a/arch/avr32/kernel/process.c b/arch/avr32/kernel/process.c
index 6ee7952..34c8c70 100644
--- a/arch/avr32/kernel/process.c
+++ b/arch/avr32/kernel/process.c
@@ -34,10 +34,10 @@
{
/* endless idle loop with no priority at all */
while (1) {
- tick_nohz_idle_enter();
+ tick_nohz_idle_enter_norcu();
while (!need_resched())
cpu_idle_sleep();
- tick_nohz_idle_exit();
+ tick_nohz_idle_exit_norcu();
preempt_enable_no_resched();
schedule();
preempt_disable();
diff --git a/arch/blackfin/kernel/process.c b/arch/blackfin/kernel/process.c
index 7b141b5..57e0749 100644
--- a/arch/blackfin/kernel/process.c
+++ b/arch/blackfin/kernel/process.c
@@ -88,10 +88,10 @@
#endif
if (!idle)
idle = default_idle;
- tick_nohz_idle_enter();
+ tick_nohz_idle_enter_norcu();
while (!need_resched())
idle();
- tick_nohz_idle_exit();
+ tick_nohz_idle_exit_norcu();
preempt_enable_no_resched();
schedule();
preempt_disable();
diff --git a/arch/microblaze/kernel/process.c b/arch/microblaze/kernel/process.c
index 5407f09..13d59f3 100644
--- a/arch/microblaze/kernel/process.c
+++ b/arch/microblaze/kernel/process.c
@@ -103,10 +103,10 @@
if (!idle)
idle = default_idle;
- tick_nohz_idle_enter();
+ tick_nohz_idle_enter_norcu();
while (!need_resched())
idle();
- tick_nohz_idle_exit();
+ tick_nohz_idle_exit_norcu();
preempt_enable_no_resched();
schedule();
diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c
index c11e5ca2..17fb3a2 100644
--- a/arch/mips/kernel/process.c
+++ b/arch/mips/kernel/process.c
@@ -56,7 +56,7 @@
/* endless idle loop with no priority at all */
while (1) {
- tick_nohz_idle_enter();
+ tick_nohz_idle_enter_norcu();
while (!need_resched() && cpu_online(cpu)) {
#ifdef CONFIG_MIPS_MT_SMTC
extern void smtc_idle_loop_hook(void);
@@ -77,7 +77,7 @@
system_state == SYSTEM_BOOTING))
play_dead();
#endif
- tick_nohz_idle_exit();
+ tick_nohz_idle_exit_norcu();
preempt_enable_no_resched();
schedule();
preempt_disable();
diff --git a/arch/openrisc/kernel/idle.c b/arch/openrisc/kernel/idle.c
index fb6a9bf..2e82cd0 100644
--- a/arch/openrisc/kernel/idle.c
+++ b/arch/openrisc/kernel/idle.c
@@ -51,7 +51,7 @@
/* endless idle loop with no priority at all */
while (1) {
- tick_nohz_idle_enter();
+ tick_nohz_idle_enter_norcu();
while (!need_resched()) {
check_pgt_cache();
@@ -69,7 +69,7 @@
set_thread_flag(TIF_POLLING_NRFLAG);
}
- tick_nohz_idle_exit();
+ tick_nohz_idle_exit_norcu();
preempt_enable_no_resched();
schedule();
preempt_disable();
diff --git a/arch/powerpc/kernel/idle.c b/arch/powerpc/kernel/idle.c
index 878572f..2e782a3 100644
--- a/arch/powerpc/kernel/idle.c
+++ b/arch/powerpc/kernel/idle.c
@@ -56,7 +56,7 @@
set_thread_flag(TIF_POLLING_NRFLAG);
while (1) {
- tick_nohz_idle_enter();
+ tick_nohz_idle_enter_norcu();
while (!need_resched() && !cpu_should_die()) {
ppc64_runlatch_off();
@@ -93,7 +93,7 @@
HMT_medium();
ppc64_runlatch_on();
- tick_nohz_idle_exit();
+ tick_nohz_idle_exit_norcu();
preempt_enable_no_resched();
if (cpu_should_die())
cpu_die();
diff --git a/arch/powerpc/platforms/iseries/setup.c b/arch/powerpc/platforms/iseries/setup.c
index e83dfaf..d69d3d1 100644
--- a/arch/powerpc/platforms/iseries/setup.c
+++ b/arch/powerpc/platforms/iseries/setup.c
@@ -563,7 +563,7 @@
static void iseries_shared_idle(void)
{
while (1) {
- tick_nohz_idle_enter();
+ tick_nohz_idle_enter_norcu();
while (!need_resched() && !hvlpevent_is_pending()) {
local_irq_disable();
ppc64_runlatch_off();
@@ -577,7 +577,7 @@
}
ppc64_runlatch_on();
- tick_nohz_idle_exit();
+ tick_nohz_idle_exit_norcu();
if (hvlpevent_is_pending())
process_iSeries_events();
@@ -593,7 +593,7 @@
set_thread_flag(TIF_POLLING_NRFLAG);
while (1) {
- tick_nohz_idle_enter();
+ tick_nohz_idle_enter_norcu();
if (!need_resched()) {
while (!need_resched()) {
ppc64_runlatch_off();
@@ -610,7 +610,7 @@
}
ppc64_runlatch_on();
- tick_nohz_idle_exit();
+ tick_nohz_idle_exit_norcu();
preempt_enable_no_resched();
schedule();
preempt_disable();
diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c
index 6224f9d..6fa9873 100644
--- a/arch/s390/kernel/process.c
+++ b/arch/s390/kernel/process.c
@@ -91,10 +91,10 @@
void cpu_idle(void)
{
for (;;) {
- tick_nohz_idle_enter();
+ tick_nohz_idle_enter_norcu();
while (!need_resched())
default_idle();
- tick_nohz_idle_exit();
+ tick_nohz_idle_exit_norcu();
preempt_enable_no_resched();
schedule();
preempt_disable();
diff --git a/arch/sh/kernel/idle.c b/arch/sh/kernel/idle.c
index 6015743..ad58e75 100644
--- a/arch/sh/kernel/idle.c
+++ b/arch/sh/kernel/idle.c
@@ -89,7 +89,7 @@
/* endless idle loop with no priority at all */
while (1) {
- tick_nohz_idle_enter();
+ tick_nohz_idle_enter_norcu();
while (!need_resched()) {
check_pgt_cache();
@@ -111,7 +111,7 @@
start_critical_timings();
}
- tick_nohz_idle_exit();
+ tick_nohz_idle_exit_norcu();
preempt_enable_no_resched();
schedule();
preempt_disable();
diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c
index 9c2795b..4a0e7d7 100644
--- a/arch/sparc/kernel/process_64.c
+++ b/arch/sparc/kernel/process_64.c
@@ -95,12 +95,12 @@
set_thread_flag(TIF_POLLING_NRFLAG);
while(1) {
- tick_nohz_idle_enter();
+ tick_nohz_idle_enter_norcu();
while (!need_resched() && !cpu_is_offline(cpu))
sparc64_yield(cpu);
- tick_nohz_idle_exit();
+ tick_nohz_idle_exit_norcu();
preempt_enable_no_resched();
diff --git a/arch/tile/kernel/process.c b/arch/tile/kernel/process.c
index 920e674..53ac895 100644
--- a/arch/tile/kernel/process.c
+++ b/arch/tile/kernel/process.c
@@ -85,7 +85,7 @@
/* endless idle loop with no priority at all */
while (1) {
- tick_nohz_idle_enter();
+ tick_nohz_idle_enter_norcu();
while (!need_resched()) {
if (cpu_is_offline(cpu))
BUG(); /* no HOTPLUG_CPU */
@@ -105,7 +105,7 @@
local_irq_enable();
current_thread_info()->status |= TS_POLLING;
}
- tick_nohz_idle_exit();
+ tick_nohz_idle_exit_norcu();
preempt_enable_no_resched();
schedule();
preempt_disable();
diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c
index cfb657e..55d2cf4 100644
--- a/arch/um/kernel/process.c
+++ b/arch/um/kernel/process.c
@@ -246,10 +246,10 @@
if (need_resched())
schedule();
- tick_nohz_idle_enter();
+ tick_nohz_idle_enter_norcu();
nsecs = disable_timer();
idle_sleep(nsecs);
- tick_nohz_idle_exit();
+ tick_nohz_idle_exit_norcu();
}
}
diff --git a/arch/unicore32/kernel/process.c b/arch/unicore32/kernel/process.c
index 9999b9a..095ff5a 100644
--- a/arch/unicore32/kernel/process.c
+++ b/arch/unicore32/kernel/process.c
@@ -55,7 +55,7 @@
{
/* endless idle loop with no priority at all */
while (1) {
- tick_nohz_idle_enter();
+ tick_nohz_idle_enter_norcu();
while (!need_resched()) {
local_irq_disable();
stop_critical_timings();
@@ -63,7 +63,7 @@
local_irq_enable();
start_critical_timings();
}
- tick_nohz_idle_exit();
+ tick_nohz_idle_exit_norcu();
preempt_enable_no_resched();
schedule();
preempt_disable();
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 6d9d4d5..f94da39 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -99,7 +99,7 @@
/* endless idle loop with no priority at all */
while (1) {
- tick_nohz_idle_enter();
+ tick_nohz_idle_enter_norcu();
while (!need_resched()) {
check_pgt_cache();
@@ -116,7 +116,7 @@
pm_idle();
start_critical_timings();
}
- tick_nohz_idle_exit();
+ tick_nohz_idle_exit_norcu();
preempt_enable_no_resched();
schedule();
preempt_disable();
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index b069e9d..18e8cf3 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -122,7 +122,7 @@
/* endless idle loop with no priority at all */
while (1) {
- tick_nohz_idle_enter();
+ tick_nohz_idle_enter_norcu();
while (!need_resched()) {
rmb();
@@ -149,7 +149,7 @@
__exit_idle();
}
- tick_nohz_idle_exit();
+ tick_nohz_idle_exit_norcu();
preempt_enable_no_resched();
schedule();
preempt_disable();
diff --git a/include/linux/tick.h b/include/linux/tick.h
index 0df1d50..327434a 100644
--- a/include/linux/tick.h
+++ b/include/linux/tick.h
@@ -7,6 +7,7 @@
#define _LINUX_TICK_H
#include <linux/clockchips.h>
+#include <linux/irqflags.h>
#ifdef CONFIG_GENERIC_CLOCKEVENTS
@@ -121,18 +122,57 @@
#endif /* !CONFIG_GENERIC_CLOCKEVENTS */
# ifdef CONFIG_NO_HZ
-extern void tick_nohz_idle_enter(void);
+extern void __tick_nohz_idle_enter(void);
+static inline void tick_nohz_idle_enter(void)
+{
+ local_irq_disable();
+ __tick_nohz_idle_enter();
+ local_irq_enable();
+}
extern void tick_nohz_idle_exit(void);
+
+/*
+ * Call this pair of function if the arch doesn't make any use
+ * of RCU in-between. You won't need to call rcu_idle_enter() and
+ * rcu_idle_exit().
+ * Otherwise you need to call tick_nohz_idle_enter() and tick_nohz_idle_exit()
+ * and explicitly tell RCU about the window around the place the CPU enters low
+ * power mode where no RCU use is made. This is done by calling rcu_idle_enter()
+ * after the last use of RCU before the CPU is put to sleep and by calling
+ * rcu_idle_exit() before the first use of RCU after the CPU woke up.
+ */
+static inline void tick_nohz_idle_enter_norcu(void)
+{
+ /*
+ * Also call rcu_idle_enter() in the irq disabled section even
+ * if it disables irq itself.
+ * Just an optimization that prevents from an interrupt happening
+ * between it and __tick_nohz_idle_enter() to lose time to help
+ * completing a grace period while we could be in extended grace
+ * period already.
+ */
+ local_irq_disable();
+ __tick_nohz_idle_enter();
+ rcu_idle_enter();
+ local_irq_enable();
+}
+static inline void tick_nohz_idle_exit_norcu(void)
+{
+ rcu_idle_exit();
+ tick_nohz_idle_exit();
+}
extern void tick_nohz_irq_exit(void);
extern ktime_t tick_nohz_get_sleep_length(void);
extern u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time);
extern u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time);
# else
-static inline void tick_nohz_idle_enter(void)
+static inline void tick_nohz_idle_enter(void) { }
+static inline void tick_nohz_idle_exit(void) { }
+static inline void tick_nohz_idle_enter_norcu(void)
{
rcu_idle_enter();
}
-static inline void tick_nohz_idle_exit(void)
+static inline void tick_nohz_idle_exit_norcu(void)
{
rcu_idle_exit();
}
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 266c242..c76aefe 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -453,18 +453,22 @@
*
* When the next event is more than a tick into the future, stop the idle tick
* Called when we start the idle loop.
- * This also enters into RCU extended quiescent state so that this CPU doesn't
- * need anymore to be part of any global grace period completion. This way
- * the tick can be stopped safely as we don't need to report quiescent states.
+ *
+ * If no use of RCU is made in the idle loop between
+ * tick_nohz_idle_enter() and tick_nohz_idle_exit() calls, then
+ * tick_nohz_idle_enter_norcu() should be called instead and the arch
+ * doesn't need to call rcu_idle_enter() and rcu_idle_exit() explicitly.
+ *
+ * Otherwise the arch is responsible of calling:
+ *
+ * - rcu_idle_enter() after its last use of RCU before the CPU is put
+ * to sleep.
+ * - rcu_idle_exit() before the first use of RCU after the CPU is woken up.
*/
-void tick_nohz_idle_enter(void)
+void __tick_nohz_idle_enter(void)
{
struct tick_sched *ts;
- WARN_ON_ONCE(irqs_disabled());
-
- local_irq_disable();
-
ts = &__get_cpu_var(tick_cpu_sched);
/*
* set ts->inidle unconditionally. even if the system did not
@@ -473,9 +477,6 @@
*/
ts->inidle = 1;
tick_nohz_stop_sched_tick(ts);
- rcu_idle_enter();
-
- local_irq_enable();
}
/**
@@ -551,7 +552,7 @@
ktime_t now;
local_irq_disable();
- rcu_idle_exit();
+
if (ts->idle_active || (ts->inidle && ts->tick_stopped))
now = ktime_get();
