[PATCH] nohz: Remove tick_nohz_idle_enter_norcu() / tick_nohz_idle_exit_norcu()
From: Frederic Weisbecker
Date: Thu Nov 17 2011 - 12:48:25 EST
Those two APIs were provided to optimize the calls of
tick_nohz_idle_enter() and rcu_idle_enter() into a single
irq disabled section. This way no interrupt happening in-between would
needlessly process any RCU job.
Now we are talking about an optimization for which benefits
have yet to be measured. Let's start simple and completely decouple
idle rcu and dyntick idle logics to simplify.
Signed-off-by: Frederic Weisbecker <fweisbec@xxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Josh Triplett <josh@xxxxxxxxxxxxxxxx>
---
arch/arm/kernel/process.c | 6 +++-
arch/avr32/kernel/process.c | 6 +++-
arch/blackfin/kernel/process.c | 6 +++-
arch/microblaze/kernel/process.c | 6 +++-
arch/mips/kernel/process.c | 6 +++-
arch/openrisc/kernel/idle.c | 6 +++-
arch/powerpc/kernel/idle.c | 15 +++++-----
arch/powerpc/platforms/iseries/setup.c | 12 +++++---
arch/s390/kernel/process.c | 6 +++-
arch/sh/kernel/idle.c | 6 +++-
arch/sparc/kernel/process_64.c | 6 +++-
arch/tile/kernel/process.c | 6 +++-
arch/um/kernel/process.c | 6 +++-
arch/unicore32/kernel/process.c | 6 +++-
arch/x86/kernel/process_32.c | 6 +++-
include/linux/tick.h | 47 +-------------------------------
kernel/time/tick-sched.c | 15 +++++-----
17 files changed, 76 insertions(+), 91 deletions(-)
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index 4f83362..0e42a9c 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -183,7 +183,8 @@ void cpu_idle(void)
/* endless idle loop with no priority at all */
while (1) {
- tick_nohz_idle_enter_norcu();
+ tick_nohz_idle_enter();
+ rcu_idle_enter();
leds_event(led_idle_start);
while (!need_resched()) {
#ifdef CONFIG_HOTPLUG_CPU
@@ -210,7 +211,8 @@ void cpu_idle(void)
}
}
leds_event(led_idle_end);
- tick_nohz_idle_exit_norcu();
+ rcu_idle_exit();
+ tick_nohz_idle_exit();
preempt_enable_no_resched();
schedule();
preempt_disable();
diff --git a/arch/avr32/kernel/process.c b/arch/avr32/kernel/process.c
index 34c8c70..ea33957 100644
--- a/arch/avr32/kernel/process.c
+++ b/arch/avr32/kernel/process.c
@@ -34,10 +34,12 @@ void cpu_idle(void)
{
/* endless idle loop with no priority at all */
while (1) {
- tick_nohz_idle_enter_norcu();
+ tick_nohz_idle_enter();
+ rcu_idle_enter();
while (!need_resched())
cpu_idle_sleep();
- tick_nohz_idle_exit_norcu();
+ rcu_idle_exit();
+ tick_nohz_idle_exit();
preempt_enable_no_resched();
schedule();
preempt_disable();
diff --git a/arch/blackfin/kernel/process.c b/arch/blackfin/kernel/process.c
index 57e0749..8dd0416 100644
--- a/arch/blackfin/kernel/process.c
+++ b/arch/blackfin/kernel/process.c
@@ -88,10 +88,12 @@ void cpu_idle(void)
#endif
if (!idle)
idle = default_idle;
- tick_nohz_idle_enter_norcu();
+ tick_nohz_idle_enter();
+ rcu_idle_enter();
while (!need_resched())
idle();
- tick_nohz_idle_exit_norcu();
+ rcu_idle_exit();
+ tick_nohz_idle_exit();
preempt_enable_no_resched();
schedule();
preempt_disable();
diff --git a/arch/microblaze/kernel/process.c b/arch/microblaze/kernel/process.c
index c6ece38..37ed945 100644
--- a/arch/microblaze/kernel/process.c
+++ b/arch/microblaze/kernel/process.c
@@ -103,10 +103,12 @@ void cpu_idle(void)
if (!idle)
idle = default_idle;
- tick_nohz_idle_enter_norcu();
+ tick_nohz_idle_enter();
+ rcu_idle_enter();
while (!need_resched())
idle();
- tick_nohz_idle_exit_norcu();
+ rcu_idle_exit();
+ tick_nohz_idle_exit();
preempt_enable_no_resched();
schedule();
diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c
index 7df2ffc..7937367 100644
--- a/arch/mips/kernel/process.c
+++ b/arch/mips/kernel/process.c
@@ -56,7 +56,8 @@ void __noreturn cpu_idle(void)
/* endless idle loop with no priority at all */
while (1) {
- tick_nohz_idle_enter_norcu();
+ tick_nohz_idle_enter();
+ rcu_idle_enter();
while (!need_resched() && cpu_online(cpu)) {
#ifdef CONFIG_MIPS_MT_SMTC
extern void smtc_idle_loop_hook(void);
@@ -77,7 +78,8 @@ void __noreturn cpu_idle(void)
system_state == SYSTEM_BOOTING))
play_dead();
#endif
- tick_nohz_idle_exit_norcu();
+ rcu_idle_exit();
+ tick_nohz_idle_exit();
preempt_enable_no_resched();
schedule();
preempt_disable();
diff --git a/arch/openrisc/kernel/idle.c b/arch/openrisc/kernel/idle.c
index 2e82cd0..e5fc7887 100644
--- a/arch/openrisc/kernel/idle.c
+++ b/arch/openrisc/kernel/idle.c
@@ -51,7 +51,8 @@ void cpu_idle(void)
/* endless idle loop with no priority at all */
while (1) {
- tick_nohz_idle_enter_norcu();
+ tick_nohz_idle_enter();
+ rcu_idle_enter();
while (!need_resched()) {
check_pgt_cache();
@@ -69,7 +70,8 @@ void cpu_idle(void)
set_thread_flag(TIF_POLLING_NRFLAG);
}
- tick_nohz_idle_exit_norcu();
+ rcu_idle_exit();
+ tick_nohz_idle_exit();
preempt_enable_no_resched();
schedule();
preempt_disable();
diff --git a/arch/powerpc/kernel/idle.c b/arch/powerpc/kernel/idle.c
index 3cd73d1..9c3cd49 100644
--- a/arch/powerpc/kernel/idle.c
+++ b/arch/powerpc/kernel/idle.c
@@ -62,10 +62,10 @@ void cpu_idle(void)
set_thread_flag(TIF_POLLING_NRFLAG);
while (1) {
- if (idle_uses_rcu)
- tick_nohz_idle_enter();
- else
- tick_nohz_idle_enter_norcu();
+ tick_nohz_idle_enter();
+ if (!idle_uses_rcu)
+ rcu_idle_enter();
+
while (!need_resched() && !cpu_should_die()) {
ppc64_runlatch_off();
@@ -102,10 +102,9 @@ void cpu_idle(void)
HMT_medium();
ppc64_runlatch_on();
- if (idle_uses_rcu)
- tick_nohz_idle_exit();
- else
- tick_nohz_idle_exit_norcu();
+ if (!idle_uses_rcu)
+ rcu_idle_exit();
+ tick_nohz_idle_exit();
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 77ff6eb..097f7d5 100644
--- a/arch/powerpc/platforms/iseries/setup.c
+++ b/arch/powerpc/platforms/iseries/setup.c
@@ -562,7 +562,8 @@ static void yield_shared_processor(void)
static void iseries_shared_idle(void)
{
while (1) {
- tick_nohz_idle_enter_norcu();
+ tick_nohz_idle_enter();
+ rcu_idle_enter();
while (!need_resched() && !hvlpevent_is_pending()) {
local_irq_disable();
ppc64_runlatch_off();
@@ -576,7 +577,8 @@ static void iseries_shared_idle(void)
}
ppc64_runlatch_on();
- tick_nohz_idle_exit_norcu();
+ rcu_idle_exit();
+ tick_nohz_idle_exit();
if (hvlpevent_is_pending())
process_iSeries_events();
@@ -592,7 +594,8 @@ static void iseries_dedicated_idle(void)
set_thread_flag(TIF_POLLING_NRFLAG);
while (1) {
- tick_nohz_idle_enter_norcu();
+ tick_nohz_idle_enter();
+ rcu_idle_enter();
if (!need_resched()) {
while (!need_resched()) {
ppc64_runlatch_off();
@@ -609,7 +612,8 @@ static void iseries_dedicated_idle(void)
}
ppc64_runlatch_on();
- tick_nohz_idle_exit_norcu();
+ rcu_idle_exit();
+ tick_nohz_idle_exit();
preempt_enable_no_resched();
schedule();
preempt_disable();
diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c
index 44028ae..bf2bc31 100644
--- a/arch/s390/kernel/process.c
+++ b/arch/s390/kernel/process.c
@@ -90,10 +90,12 @@ static void default_idle(void)
void cpu_idle(void)
{
for (;;) {
- tick_nohz_idle_enter_norcu();
+ tick_nohz_idle_enter();
+ rcu_idle_enter();
while (!need_resched())
default_idle();
- tick_nohz_idle_exit_norcu();
+ rcu_idle_exit();
+ tick_nohz_idle_exit();
preempt_enable_no_resched();
schedule();
preempt_disable();
diff --git a/arch/sh/kernel/idle.c b/arch/sh/kernel/idle.c
index ad58e75..406508d 100644
--- a/arch/sh/kernel/idle.c
+++ b/arch/sh/kernel/idle.c
@@ -89,7 +89,8 @@ void cpu_idle(void)
/* endless idle loop with no priority at all */
while (1) {
- tick_nohz_idle_enter_norcu();
+ tick_nohz_idle_enter();
+ rcu_idle_enter();
while (!need_resched()) {
check_pgt_cache();
@@ -111,7 +112,8 @@ void cpu_idle(void)
start_critical_timings();
}
- tick_nohz_idle_exit_norcu();
+ rcu_idle_exit();
+ tick_nohz_idle_exit();
preempt_enable_no_resched();
schedule();
preempt_disable();
diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c
index 78b1bc0..fde8d72 100644
--- a/arch/sparc/kernel/process_64.c
+++ b/arch/sparc/kernel/process_64.c
@@ -95,12 +95,14 @@ void cpu_idle(void)
set_thread_flag(TIF_POLLING_NRFLAG);
while(1) {
- tick_nohz_idle_enter_norcu();
+ tick_nohz_idle_enter();
+ rcu_idle_enter();
while (!need_resched() && !cpu_is_offline(cpu))
sparc64_yield(cpu);
- tick_nohz_idle_exit_norcu();
+ rcu_idle_exit();
+ tick_nohz_idle_exit();
preempt_enable_no_resched();
diff --git a/arch/tile/kernel/process.c b/arch/tile/kernel/process.c
index 53ac895..4c1ac6e 100644
--- a/arch/tile/kernel/process.c
+++ b/arch/tile/kernel/process.c
@@ -85,7 +85,8 @@ void cpu_idle(void)
/* endless idle loop with no priority at all */
while (1) {
- tick_nohz_idle_enter_norcu();
+ tick_nohz_idle_enter();
+ rcu_idle_enter();
while (!need_resched()) {
if (cpu_is_offline(cpu))
BUG(); /* no HOTPLUG_CPU */
@@ -105,7 +106,8 @@ void cpu_idle(void)
local_irq_enable();
current_thread_info()->status |= TS_POLLING;
}
- tick_nohz_idle_exit_norcu();
+ rcu_idle_exit();
+ tick_nohz_idle_exit();
preempt_enable_no_resched();
schedule();
preempt_disable();
diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c
index 9e7176b..b652ff1 100644
--- a/arch/um/kernel/process.c
+++ b/arch/um/kernel/process.c
@@ -245,10 +245,12 @@ void default_idle(void)
if (need_resched())
schedule();
- tick_nohz_idle_enter_norcu();
+ tick_nohz_idle_enter();
+ rcu_idle_enter();
nsecs = disable_timer();
idle_sleep(nsecs);
- tick_nohz_idle_exit_norcu();
+ rcu_idle_exit();
+ tick_nohz_idle_exit();
}
}
diff --git a/arch/unicore32/kernel/process.c b/arch/unicore32/kernel/process.c
index 095ff5a..52edc2b 100644
--- a/arch/unicore32/kernel/process.c
+++ b/arch/unicore32/kernel/process.c
@@ -55,7 +55,8 @@ void cpu_idle(void)
{
/* endless idle loop with no priority at all */
while (1) {
- tick_nohz_idle_enter_norcu();
+ tick_nohz_idle_enter();
+ rcu_idle_enter();
while (!need_resched()) {
local_irq_disable();
stop_critical_timings();
@@ -63,7 +64,8 @@ void cpu_idle(void)
local_irq_enable();
start_critical_timings();
}
- tick_nohz_idle_exit_norcu();
+ rcu_idle_exit();
+ tick_nohz_idle_exit();
preempt_enable_no_resched();
schedule();
preempt_disable();
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index f311d096..44e3384 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -98,7 +98,8 @@ void cpu_idle(void)
/* endless idle loop with no priority at all */
while (1) {
- tick_nohz_idle_enter_norcu();
+ tick_nohz_idle_enter();
+ rcu_idle_enter();
while (!need_resched()) {
check_pgt_cache();
@@ -114,7 +115,8 @@ void cpu_idle(void)
pm_idle();
start_critical_timings();
}
- tick_nohz_idle_exit_norcu();
+ rcu_idle_exit();
+ tick_nohz_idle_exit();
preempt_enable_no_resched();
schedule();
preempt_disable();
diff --git a/include/linux/tick.h b/include/linux/tick.h
index 327434a..ab8be90 100644
--- a/include/linux/tick.h
+++ b/include/linux/tick.h
@@ -122,45 +122,8 @@ static inline int tick_oneshot_mode_active(void) { return 0; }
#endif /* !CONFIG_GENERIC_CLOCKEVENTS */
# ifdef CONFIG_NO_HZ
-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_enter(void);
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);
@@ -168,14 +131,6 @@ 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_exit(void) { }
-static inline void tick_nohz_idle_enter_norcu(void)
-{
- rcu_idle_enter();
-}
-static inline void tick_nohz_idle_exit_norcu(void)
-{
- rcu_idle_exit();
-}
static inline ktime_t tick_nohz_get_sleep_length(void)
{
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 360d028..0d887e8 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -425,21 +425,20 @@ out:
* When the next event is more than a tick into the future, stop the idle tick
* Called when we start the idle loop.
*
- * 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:
+ * 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
@@ -448,6 +447,8 @@ void __tick_nohz_idle_enter(void)
*/
ts->inidle = 1;
tick_nohz_stop_sched_tick(ts);
+
+ local_irq_enable();
}
/**
--
1.7.5.4
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/