Commit 64c7c8f8 authored by Nick Piggin's avatar Nick Piggin Committed by Linus Torvalds

[PATCH] sched: resched and cpu_idle rework

Make some changes to the NEED_RESCHED and POLLING_NRFLAG to reduce
confusion, and make their semantics rigid.  Improves efficiency of
resched_task and some cpu_idle routines.

* In resched_task:
- TIF_NEED_RESCHED is only cleared with the task's runqueue lock held,
  and as we hold it during resched_task, then there is no need for an
  atomic test and set there. The only other time this should be set is
  when the task's quantum expires, in the timer interrupt - this is
  protected against because the rq lock is irq-safe.

- If TIF_NEED_RESCHED is set, then we don't need to do anything. It
  won't get unset until the task get's schedule()d off.

- If we are running on the same CPU as the task we resched, then set
  TIF_NEED_RESCHED and no further action is required.

- If we are running on another CPU, and TIF_POLLING_NRFLAG is *not* set
  after TIF_NEED_RESCHED has been set, then we need to send an IPI.

Using these rules, we are able to remove the test and set operation in
resched_task, and make clear the previously vague semantics of
POLLING_NRFLAG.

* In idle routines:
- Enter cpu_idle with preempt disabled. When the need_resched() condition
  becomes true, explicitly call schedule(). This makes things a bit clearer
  (IMO), but haven't updated all architectures yet.

- Many do a test and clear of TIF_NEED_RESCHED for some reason. According
  to the resched_task rules, this isn't needed (and actually breaks the
  assumption that TIF_NEED_RESCHED is only cleared with the runqueue lock
  held). So remove that. Generally one less locked memory op when switching
  to the idle thread.

- Many idle routines clear TIF_POLLING_NRFLAG, and only set it in the inner
  most polling idle loops. The above resched_task semantics allow it to be
  set until before the last time need_resched() is checked before going into
  a halt requiring interrupt wakeup.

  Many idle routines simply never enter such a halt, and so POLLING_NRFLAG
  can be always left set, completely eliminating resched IPIs when rescheduling
  the idle task.

  POLLING_NRFLAG width can be increased, to reduce the chance of resched IPIs.
Signed-off-by: default avatarNick Piggin <npiggin@suse.de>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Con Kolivas <kernel@kolivas.org>
Signed-off-by: default avatarAndrew Morton <akpm@osdl.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@osdl.org>
parent 5bfb5d69
CPU Scheduler implementation hints for architecture specific code
Nick Piggin, 2005
Context switch
==============
1. Runqueue locking
By default, the switch_to arch function is called with the runqueue
locked. This is usually not a problem unless switch_to may need to
take the runqueue lock. This is usually due to a wake up operation in
the context switch. See include/asm-ia64/system.h for an example.
To request the scheduler call switch_to with the runqueue unlocked,
you must `#define __ARCH_WANT_UNLOCKED_CTXSW` in a header file
(typically the one where switch_to is defined).
Unlocked context switches introduce only a very minor performance
penalty to the core scheduler implementation in the CONFIG_SMP case.
2. Interrupt status
By default, the switch_to arch function is called with interrupts
disabled. Interrupts may be enabled over the call if it is likely to
introduce a significant interrupt latency by adding the line
`#define __ARCH_WANT_INTERRUPTS_ON_CTXSW` in the same place as for
unlocked context switches. This define also implies
`__ARCH_WANT_UNLOCKED_CTXSW`. See include/asm-arm/system.h for an
example.
CPU idle
========
Your cpu_idle routines need to obey the following rules:
1. Preempt should now disabled over idle routines. Should only
be enabled to call schedule() then disabled again.
2. need_resched/TIF_NEED_RESCHED is only ever set, and will never
be cleared until the running task has called schedule(). Idle
threads need only ever query need_resched, and may never set or
clear it.
3. When cpu_idle finds (need_resched() == 'true'), it should call
schedule(). It should not call schedule() otherwise.
4. The only time interrupts need to be disabled when checking
need_resched is if we are about to sleep the processor until
the next interrupt (this doesn't provide any protection of
need_resched, it prevents losing an interrupt).
4a. Common problem with this type of sleep appears to be:
local_irq_disable();
if (!need_resched()) {
local_irq_enable();
*** resched interrupt arrives here ***
__asm__("sleep until next interrupt");
}
5. TIF_POLLING_NRFLAG can be set by idle routines that do not
need an interrupt to wake them up when need_resched goes high.
In other words, they must be periodically polling need_resched,
although it may be reasonable to do some background work or enter
a low CPU priority.
5a. If TIF_POLLING_NRFLAG is set, and we do decide to enter
an interrupt sleep, it needs to be cleared then a memory
barrier issued (followed by a test of need_resched with
interrupts disabled, as explained in 3).
arch/i386/kernel/process.c has examples of both polling and
sleeping idle functions.
Possible arch/ problems
=======================
Possible arch problems I found (and either tried to fix or didn't):
h8300 - Is such sleeping racy vs interrupts? (See #4a).
The H8/300 manual I found indicates yes, however disabling IRQs
over the sleep mean only NMIs can wake it up, so can't fix easily
without doing spin waiting.
ia64 - is safe_halt call racy vs interrupts? (does it sleep?) (See #4a)
sh64 - Is sleeping racy vs interrupts? (See #4a)
sparc - IRQs on at this point(?), change local_irq_save to _disable.
- TODO: needs secondary CPUs to disable preempt (See #1)
...@@ -43,21 +43,17 @@ ...@@ -43,21 +43,17 @@
#include "proto.h" #include "proto.h"
#include "pci_impl.h" #include "pci_impl.h"
void default_idle(void)
{
barrier();
}
void void
cpu_idle(void) cpu_idle(void)
{ {
set_thread_flag(TIF_POLLING_NRFLAG);
while (1) { while (1) {
void (*idle)(void) = default_idle;
/* FIXME -- EV6 and LCA45 know how to power down /* FIXME -- EV6 and LCA45 know how to power down
the CPU. */ the CPU. */
while (!need_resched()) while (!need_resched())
idle(); cpu_relax();
schedule(); schedule();
} }
} }
......
...@@ -86,12 +86,16 @@ EXPORT_SYMBOL(pm_power_off); ...@@ -86,12 +86,16 @@ EXPORT_SYMBOL(pm_power_off);
*/ */
void default_idle(void) void default_idle(void)
{ {
local_irq_disable(); if (hlt_counter)
if (!need_resched() && !hlt_counter) { cpu_relax();
timer_dyn_reprogram(); else {
arch_idle(); local_irq_disable();
if (!need_resched()) {
timer_dyn_reprogram();
arch_idle();
}
local_irq_enable();
} }
local_irq_enable();
} }
/* /*
......
...@@ -769,8 +769,26 @@ static int set_system_power_state(u_short state) ...@@ -769,8 +769,26 @@ static int set_system_power_state(u_short state)
static int apm_do_idle(void) static int apm_do_idle(void)
{ {
u32 eax; u32 eax;
u8 ret = 0;
int idled = 0;
int polling;
polling = test_thread_flag(TIF_POLLING_NRFLAG);
if (polling) {
clear_thread_flag(TIF_POLLING_NRFLAG);
smp_mb__after_clear_bit();
}
if (!need_resched()) {
idled = 1;
ret = apm_bios_call_simple(APM_FUNC_IDLE, 0, 0, &eax);
}
if (polling)
set_thread_flag(TIF_POLLING_NRFLAG);
if (!idled)
return 0;
if (apm_bios_call_simple(APM_FUNC_IDLE, 0, 0, &eax)) { if (ret) {
static unsigned long t; static unsigned long t;
/* This always fails on some SMP boards running UP kernels. /* This always fails on some SMP boards running UP kernels.
......
...@@ -99,14 +99,22 @@ EXPORT_SYMBOL(enable_hlt); ...@@ -99,14 +99,22 @@ EXPORT_SYMBOL(enable_hlt);
*/ */
void default_idle(void) void default_idle(void)
{ {
local_irq_enable();
if (!hlt_counter && boot_cpu_data.hlt_works_ok) { if (!hlt_counter && boot_cpu_data.hlt_works_ok) {
local_irq_disable(); clear_thread_flag(TIF_POLLING_NRFLAG);
if (!need_resched()) smp_mb__after_clear_bit();
safe_halt(); while (!need_resched()) {
else local_irq_disable();
local_irq_enable(); if (!need_resched())
safe_halt();
else
local_irq_enable();
}
set_thread_flag(TIF_POLLING_NRFLAG);
} else { } else {
cpu_relax(); while (!need_resched())
cpu_relax();
} }
} }
#ifdef CONFIG_APM_MODULE #ifdef CONFIG_APM_MODULE
...@@ -120,29 +128,14 @@ EXPORT_SYMBOL(default_idle); ...@@ -120,29 +128,14 @@ EXPORT_SYMBOL(default_idle);
*/ */
static void poll_idle (void) static void poll_idle (void)
{ {
int oldval;
local_irq_enable(); local_irq_enable();
/* asm volatile(
* Deal with another CPU just having chosen a thread to "2:"
* run here: "testl %0, %1;"
*/ "rep; nop;"
oldval = test_and_clear_thread_flag(TIF_NEED_RESCHED); "je 2b;"
: : "i"(_TIF_NEED_RESCHED), "m" (current_thread_info()->flags));
if (!oldval) {
set_thread_flag(TIF_POLLING_NRFLAG);
asm volatile(
"2:"
"testl %0, %1;"
"rep; nop;"
"je 2b;"
: : "i"(_TIF_NEED_RESCHED), "m" (current_thread_info()->flags));
clear_thread_flag(TIF_POLLING_NRFLAG);
} else {
set_need_resched();
}
} }
#ifdef CONFIG_HOTPLUG_CPU #ifdef CONFIG_HOTPLUG_CPU
...@@ -181,6 +174,8 @@ void cpu_idle(void) ...@@ -181,6 +174,8 @@ void cpu_idle(void)
{ {
int cpu = smp_processor_id(); int cpu = smp_processor_id();
set_thread_flag(TIF_POLLING_NRFLAG);
/* endless idle loop with no priority at all */ /* endless idle loop with no priority at all */
while (1) { while (1) {
while (!need_resched()) { while (!need_resched()) {
...@@ -246,15 +241,12 @@ static void mwait_idle(void) ...@@ -246,15 +241,12 @@ static void mwait_idle(void)
{ {
local_irq_enable(); local_irq_enable();
if (!need_resched()) { while (!need_resched()) {
set_thread_flag(TIF_POLLING_NRFLAG); __monitor((void *)&current_thread_info()->flags, 0, 0);
do { smp_mb();
__monitor((void *)&current_thread_info()->flags, 0, 0); if (need_resched())
if (need_resched()) break;
break; __mwait(0, 0);
__mwait(0, 0);
} while (!need_resched());
clear_thread_flag(TIF_POLLING_NRFLAG);
} }
} }
......
...@@ -197,11 +197,15 @@ void ...@@ -197,11 +197,15 @@ void
default_idle (void) default_idle (void)
{ {
local_irq_enable(); local_irq_enable();
while (!need_resched()) while (!need_resched()) {
if (can_do_pal_halt) if (can_do_pal_halt) {
safe_halt(); local_irq_disable();
else if (!need_resched())
safe_halt();
local_irq_enable();
} else
cpu_relax(); cpu_relax();
}
} }
#ifdef CONFIG_HOTPLUG_CPU #ifdef CONFIG_HOTPLUG_CPU
...@@ -263,16 +267,16 @@ void __attribute__((noreturn)) ...@@ -263,16 +267,16 @@ void __attribute__((noreturn))
cpu_idle (void) cpu_idle (void)
{ {
void (*mark_idle)(int) = ia64_mark_idle; void (*mark_idle)(int) = ia64_mark_idle;
int cpu = smp_processor_id();
set_thread_flag(TIF_POLLING_NRFLAG);
/* endless idle loop with no priority at all */ /* endless idle loop with no priority at all */
while (1) { while (1) {
if (!need_resched()) {
void (*idle)(void);
#ifdef CONFIG_SMP #ifdef CONFIG_SMP
if (!need_resched())
min_xtp(); min_xtp();
#endif #endif
while (!need_resched()) {
void (*idle)(void);
if (__get_cpu_var(cpu_idle_state)) if (__get_cpu_var(cpu_idle_state))
__get_cpu_var(cpu_idle_state) = 0; __get_cpu_var(cpu_idle_state) = 0;
...@@ -284,19 +288,17 @@ cpu_idle (void) ...@@ -284,19 +288,17 @@ cpu_idle (void)
if (!idle) if (!idle)
idle = default_idle; idle = default_idle;
(*idle)(); (*idle)();
} if (mark_idle)
(*mark_idle)(0);
if (mark_idle)
(*mark_idle)(0);
#ifdef CONFIG_SMP #ifdef CONFIG_SMP
normal_xtp(); normal_xtp();
#endif #endif
}
preempt_enable_no_resched(); preempt_enable_no_resched();
schedule(); schedule();
preempt_disable(); preempt_disable();
check_pgt_cache(); check_pgt_cache();
if (cpu_is_offline(smp_processor_id())) if (cpu_is_offline(cpu))
play_dead(); play_dead();
} }
} }
......
...@@ -88,6 +88,8 @@ void default_idle(void) ...@@ -88,6 +88,8 @@ void default_idle(void)
*/ */
void cpu_idle(void) void cpu_idle(void)
{ {
set_thread_flag(TIF_POLLING_NRFLAG);
/* endless idle loop with no priority at all */ /* endless idle loop with no priority at all */
while (1) { while (1) {
while (!need_resched()) while (!need_resched())
......
...@@ -703,13 +703,10 @@ static void iseries_shared_idle(void) ...@@ -703,13 +703,10 @@ static void iseries_shared_idle(void)
static void iseries_dedicated_idle(void) static void iseries_dedicated_idle(void)
{ {
long oldval; long oldval;
set_thread_flag(TIF_POLLING_NRFLAG);
while (1) { while (1) {
oldval = test_and_clear_thread_flag(TIF_NEED_RESCHED); if (!need_resched()) {
if (!oldval) {
set_thread_flag(TIF_POLLING_NRFLAG);
while (!need_resched()) { while (!need_resched()) {
ppc64_runlatch_off(); ppc64_runlatch_off();
HMT_low(); HMT_low();
...@@ -722,9 +719,6 @@ static void iseries_dedicated_idle(void) ...@@ -722,9 +719,6 @@ static void iseries_dedicated_idle(void)
} }
HMT_medium(); HMT_medium();
clear_thread_flag(TIF_POLLING_NRFLAG);
} else {
set_need_resched();
} }
ppc64_runlatch_on(); ppc64_runlatch_on();
......
...@@ -469,6 +469,7 @@ static inline void dedicated_idle_sleep(unsigned int cpu) ...@@ -469,6 +469,7 @@ static inline void dedicated_idle_sleep(unsigned int cpu)
* more. * more.
*/ */
clear_thread_flag(TIF_POLLING_NRFLAG); clear_thread_flag(TIF_POLLING_NRFLAG);
smp_mb__after_clear_bit();
/* /*
* SMT dynamic mode. Cede will result in this thread going * SMT dynamic mode. Cede will result in this thread going
...@@ -481,6 +482,7 @@ static inline void dedicated_idle_sleep(unsigned int cpu) ...@@ -481,6 +482,7 @@ static inline void dedicated_idle_sleep(unsigned int cpu)
cede_processor(); cede_processor();
else else
local_irq_enable(); local_irq_enable();
set_thread_flag(TIF_POLLING_NRFLAG);
} else { } else {
/* /*
* Give the HV an opportunity at the processor, since we are * Give the HV an opportunity at the processor, since we are
...@@ -492,11 +494,11 @@ static inline void dedicated_idle_sleep(unsigned int cpu) ...@@ -492,11 +494,11 @@ static inline void dedicated_idle_sleep(unsigned int cpu)
static void pseries_dedicated_idle(void) static void pseries_dedicated_idle(void)
{ {
long oldval;
struct paca_struct *lpaca = get_paca(); struct paca_struct *lpaca = get_paca();
unsigned int cpu = smp_processor_id(); unsigned int cpu = smp_processor_id();
unsigned long start_snooze; unsigned long start_snooze;
unsigned long *smt_snooze_delay = &__get_cpu_var(smt_snooze_delay); unsigned long *smt_snooze_delay = &__get_cpu_var(smt_snooze_delay);
set_thread_flag(TIF_POLLING_NRFLAG);
while (1) { while (1) {
/* /*
...@@ -505,10 +507,7 @@ static void pseries_dedicated_idle(void) ...@@ -505,10 +507,7 @@ static void pseries_dedicated_idle(void)
*/ */
lpaca->lppaca.idle = 1; lpaca->lppaca.idle = 1;
oldval = test_and_clear_thread_flag(TIF_NEED_RESCHED); if (!need_resched()) {
if (!oldval) {
set_thread_flag(TIF_POLLING_NRFLAG);
start_snooze = __get_tb() + start_snooze = __get_tb() +
*smt_snooze_delay * tb_ticks_per_usec; *smt_snooze_delay * tb_ticks_per_usec;
...@@ -531,9 +530,6 @@ static void pseries_dedicated_idle(void) ...@@ -531,9 +530,6 @@ static void pseries_dedicated_idle(void)
} }
HMT_medium(); HMT_medium();
clear_thread_flag(TIF_POLLING_NRFLAG);
} else {
set_need_resched();
} }
lpaca->lppaca.idle = 0; lpaca->lppaca.idle = 0;
......
...@@ -63,18 +63,18 @@ void cpu_idle(void) ...@@ -63,18 +63,18 @@ void cpu_idle(void)
int cpu = smp_processor_id(); int cpu = smp_processor_id();
for (;;) { for (;;) {
if (ppc_md.idle != NULL) while (need_resched()) {
ppc_md.idle(); if (ppc_md.idle != NULL)
else ppc_md.idle();
default_idle(); else
if (cpu_is_offline(cpu) && system_state == SYSTEM_RUNNING) default_idle();
cpu_die();
if (need_resched()) {
preempt_enable_no_resched();
schedule();
preempt_disable();
} }
if (cpu_is_offline(cpu) && system_state == SYSTEM_RUNNING)
cpu_die();
preempt_enable_no_resched();
schedule();
preempt_disable();
} }
} }
......
...@@ -34,15 +34,11 @@ extern void power4_idle(void); ...@@ -34,15 +34,11 @@ extern void power4_idle(void);
void default_idle(void) void default_idle(void)
{ {
long oldval;
unsigned int cpu = smp_processor_id(); unsigned int cpu = smp_processor_id();
set_thread_flag(TIF_POLLING_NRFLAG);
while (1) { while (1) {
oldval = test_and_clear_thread_flag(TIF_NEED_RESCHED); if (!need_resched()) {
if (!oldval) {
set_thread_flag(TIF_POLLING_NRFLAG);
while (!need_resched() && !cpu_is_offline(cpu)) { while (!need_resched() && !cpu_is_offline(cpu)) {
ppc64_runlatch_off(); ppc64_runlatch_off();
...@@ -55,9 +51,6 @@ void default_idle(void) ...@@ -55,9 +51,6 @@ void default_idle(void)
} }
HMT_medium(); HMT_medium();
clear_thread_flag(TIF_POLLING_NRFLAG);
} else {
set_need_resched();
} }
ppc64_runlatch_on(); ppc64_runlatch_on();
......
...@@ -99,14 +99,15 @@ void default_idle(void) ...@@ -99,14 +99,15 @@ void default_idle(void)
{ {
int cpu, rc; int cpu, rc;
/* CPU is going idle. */
cpu = smp_processor_id();
local_irq_disable(); local_irq_disable();
if (need_resched()) { if (need_resched()) {
local_irq_enable(); local_irq_enable();
return; return;
} }
/* CPU is going idle. */
cpu = smp_processor_id();
rc = notifier_call_chain(&idle_chain, CPU_IDLE, (void *)(long) cpu); rc = notifier_call_chain(&idle_chain, CPU_IDLE, (void *)(long) cpu);
if (rc != NOTIFY_OK && rc != NOTIFY_DONE) if (rc != NOTIFY_OK && rc != NOTIFY_DONE)
BUG(); BUG();
...@@ -119,7 +120,7 @@ void default_idle(void) ...@@ -119,7 +120,7 @@ void default_idle(void)
__ctl_set_bit(8, 15); __ctl_set_bit(8, 15);
#ifdef CONFIG_HOTPLUG_CPU #ifdef CONFIG_HOTPLUG_CPU
if (cpu_is_offline(smp_processor_id())) if (cpu_is_offline(cpu))
cpu_die(); cpu_die();
#endif #endif
......
...@@ -51,14 +51,13 @@ void enable_hlt(void) ...@@ -51,14 +51,13 @@ void enable_hlt(void)
EXPORT_SYMBOL(enable_hlt); EXPORT_SYMBOL(enable_hlt);
void default_idle(void) void cpu_idle(void)
{ {
/* endless idle loop with no priority at all */ /* endless idle loop with no priority at all */
while (1) { while (1) {
if (hlt_counter) { if (hlt_counter) {
while (1) while (!need_resched())
if (need_resched()) cpu_relax();
break;
} else { } else {
while (!need_resched()) while (!need_resched())
cpu_sleep(); cpu_sleep();
...@@ -70,11 +69,6 @@ void default_idle(void) ...@@ -70,11 +69,6 @@ void default_idle(void)
} }
} }
void cpu_idle(void)
{
default_idle();
}
void machine_restart(char * __unused) void machine_restart(char * __unused)
{ {
/* SR.BL=1 and invoke address error to let CPU reset (manual reset) */ /* SR.BL=1 and invoke address error to let CPU reset (manual reset) */
......
...@@ -307,23 +307,19 @@ __setup("hlt", hlt_setup); ...@@ -307,23 +307,19 @@ __setup("hlt", hlt_setup);
static inline void hlt(void) static inline void hlt(void)
{ {
if (hlt_counter)
return;
__asm__ __volatile__ ("sleep" : : : "memory"); __asm__ __volatile__ ("sleep" : : : "memory");
} }
/* /*
* The idle loop on a uniprocessor SH.. * The idle loop on a uniprocessor SH..
*/ */
void default_idle(void) void cpu_idle(void)
{ {
/* endless idle loop with no priority at all */ /* endless idle loop with no priority at all */
while (1) { while (1) {
if (hlt_counter) { if (hlt_counter) {
while (1) while (!need_resched())
if (need_resched()) cpu_relax();
break;
} else { } else {
local_irq_disable(); local_irq_disable();
while (!need_resched()) { while (!need_resched()) {
...@@ -338,11 +334,7 @@ void default_idle(void) ...@@ -338,11 +334,7 @@ void default_idle(void)
schedule(); schedule();
preempt_disable(); preempt_disable();
} }
}
void cpu_idle(void)
{
default_idle();
} }
void machine_restart(char * __unused) void machine_restart(char * __unused)
......
...@@ -67,13 +67,6 @@ extern void fpsave(unsigned long *, unsigned long *, void *, unsigned long *); ...@@ -67,13 +67,6 @@ extern void fpsave(unsigned long *, unsigned long *, void *, unsigned long *);
struct task_struct *last_task_used_math = NULL; struct task_struct *last_task_used_math = NULL;
struct thread_info *current_set[NR_CPUS]; struct thread_info *current_set[NR_CPUS];
/*
* default_idle is new in 2.5. XXX Review, currently stolen from sparc64.
*/
void default_idle(void)
{
}
#ifndef CONFIG_SMP #ifndef CONFIG_SMP
#define SUN4C_FAULT_HIGH 100 #define SUN4C_FAULT_HIGH 100
...@@ -92,12 +85,11 @@ void cpu_idle(void) ...@@ -92,12 +85,11 @@ void cpu_idle(void)
static unsigned long fps; static unsigned long fps;
unsigned long now; unsigned long now;
unsigned long faults; unsigned long faults;
unsigned long flags;
extern unsigned long sun4c_kernel_faults; extern unsigned long sun4c_kernel_faults;
extern void sun4c_grow_kernel_ring(void); extern void sun4c_grow_kernel_ring(void);
local_irq_save(flags); local_irq_disable();
now = jiffies; now = jiffies;
count -= (now - last_jiffies); count -= (now - last_jiffies);
last_jiffies = now; last_jiffies = now;
...@@ -113,13 +105,16 @@ void cpu_idle(void) ...@@ -113,13 +105,16 @@ void cpu_idle(void)
sun4c_grow_kernel_ring(); sun4c_grow_kernel_ring();
} }
} }
local_irq_restore(flags); local_irq_enable();
} }
while((!need_resched()) && pm_idle) { if (pm_idle) {
(*pm_idle)(); while (!need_resched())
(*pm_idle)();
} else {
while (!need_resched())
cpu_relax();
} }
preempt_enable_no_resched(); preempt_enable_no_resched();
schedule(); schedule();
preempt_disable(); preempt_disable();
...@@ -132,15 +127,15 @@ void cpu_idle(void) ...@@ -132,15 +127,15 @@ void cpu_idle(void)
/* This is being executed in task 0 'user space'. */ /* This is being executed in task 0 'user space'. */
void cpu_idle(void) void cpu_idle(void)
{ {
set_thread_flag(TIF_POLLING_NRFLAG);
/* endless idle loop with no priority at all */ /* endless idle loop with no priority at all */
while(1) { while(1) {
if(need_resched()) { while (!need_resched())
preempt_enable_no_resched(); cpu_relax();
schedule(); preempt_enable_no_resched();
preempt_disable(); schedule();
check_pgt_cache(); preempt_disable();
} check_pgt_cache();
barrier(); /* or else gcc optimizes... */
} }
} }
......
...@@ -85,23 +85,31 @@ void cpu_idle(void) ...@@ -85,23 +85,31 @@ void cpu_idle(void)
/* /*
* the idle loop on a UltraMultiPenguin... * the idle loop on a UltraMultiPenguin...
*
* TIF_POLLING_NRFLAG is set because we do not sleep the cpu
* inside of the idler task, so an interrupt is not needed
* to get a clean fast response.
*
* XXX Reverify this assumption... -DaveM
*
* Addendum: We do want it to do something for the signal
* delivery case, we detect that by just seeing
* if we are trying to send this to an idler or not.
*/ */
#define idle_me_harder() (cpu_data(smp_processor_id()).idle_volume += 1)
#define unidle_me() (cpu_data(smp_processor_id()).idle_volume = 0)
void cpu_idle(void) void cpu_idle(void)
{ {
cpuinfo_sparc *cpuinfo = &local_cpu_data();
set_thread_flag(TIF_POLLING_NRFLAG); set_thread_flag(TIF_POLLING_NRFLAG);
while(1) { while(1) {
if (need_resched()) { if (need_resched()) {
unidle_me(); cpuinfo->idle_volume = 0;
clear_thread_flag(TIF_POLLING_NRFLAG);
preempt_enable_no_resched(); preempt_enable_no_resched();
schedule(); schedule();
preempt_disable(); preempt_disable();
set_thread_flag(TIF_POLLING_NRFLAG);
check_pgt_cache(); check_pgt_cache();
} }
idle_me_harder(); cpuinfo->idle_volume++;
/* The store ordering is so that IRQ handlers on /* The store ordering is so that IRQ handlers on
* other cpus see our increasing idleness for the buddy * other cpus see our increasing idleness for the buddy
......
...@@ -1152,20 +1152,9 @@ void __init smp_cpus_done(unsigned int max_cpus) ...@@ -1152,20 +1152,9 @@ void __init smp_cpus_done(unsigned int max_cpus)
(bogosum/(5000/HZ))%100); (bogosum/(5000/HZ))%100);
} }
/* This needn't do anything as we do not sleep the cpu
* inside of the idler task, so an interrupt is not needed
* to get a clean fast response.
*
* XXX Reverify this assumption... -DaveM
*
* Addendum: We do want it to do something for the signal
* delivery case, we detect that by just seeing
* if we are trying to send this to an idler or not.
*/
void smp_send_reschedule(int cpu) void smp_send_reschedule(int cpu)
{ {
if (cpu_data(cpu).idle_volume == 0) smp_receive_signal(cpu);
smp_receive_signal(cpu);
} }
/* This is a nop because we capture all other cpus /* This is a nop because we capture all other cpus
......
...@@ -86,12 +86,22 @@ EXPORT_SYMBOL(enable_hlt); ...@@ -86,12 +86,22 @@ EXPORT_SYMBOL(enable_hlt);
*/ */
void default_idle(void) void default_idle(void)
{ {
local_irq_enable();
if (!atomic_read(&hlt_counter)) { if (!atomic_read(&hlt_counter)) {
local_irq_disable(); clear_thread_flag(TIF_POLLING_NRFLAG);
if (!need_resched()) smp_mb__after_clear_bit();
safe_halt(); while (!need_resched()) {
else local_irq_disable();
local_irq_enable(); if (!need_resched())
safe_halt();
else
local_irq_enable();
}
set_thread_flag(TIF_POLLING_NRFLAG);
} else {
while (!need_resched())
cpu_relax();
} }
} }
...@@ -102,30 +112,16 @@ void default_idle(void) ...@@ -102,30 +112,16 @@ void default_idle(void)
*/ */
static void poll_idle (void) static void poll_idle (void)
{ {
int oldval;
local_irq_enable(); local_irq_enable();
/* asm volatile(
* Deal with another CPU just having chosen a thread to "2:"
* run here: "testl %0,%1;"
*/ "rep; nop;"
oldval = test_and_clear_thread_flag(TIF_NEED_RESCHED); "je 2b;"
: :
if (!oldval) { "i" (_TIF_NEED_RESCHED),
set_thread_flag(TIF_POLLING_NRFLAG); "m" (current_thread_info()->flags));
asm volatile(
"2:"
"testl %0,%1;"
"rep; nop;"
"je 2b;"
: :
"i" (_TIF_NEED_RESCHED),
"m" (current_thread_info()->flags));
clear_thread_flag(TIF_POLLING_NRFLAG);
} else {
set_need_resched();
}
} }
void cpu_idle_wait(void) void cpu_idle_wait(void)
...@@ -187,6 +183,8 @@ static inline void play_dead(void) ...@@ -187,6 +183,8 @@ static inline void play_dead(void)
*/ */
void cpu_idle (void) void cpu_idle (void)
{ {
set_thread_flag(TIF_POLLING_NRFLAG);
/* endless idle loop with no priority at all */ /* endless idle loop with no priority at all */
while (1) { while (1) {
while (!need_resched()) { while (!need_resched()) {
...@@ -221,15 +219,12 @@ static void mwait_idle(void) ...@@ -221,15 +219,12 @@ static void mwait_idle(void)
{ {
local_irq_enable(); local_irq_enable();
if (!need_resched()) { while (!need_resched()) {
set_thread_flag(TIF_POLLING_NRFLAG); __monitor((void *)&current_thread_info()->flags, 0, 0);
do { smp_mb();
__monitor((void *)&current_thread_info()->flags, 0, 0); if (need_resched())
if (need_resched()) break;
break; __mwait(0, 0);
__mwait(0, 0);
} while (!need_resched());
clear_thread_flag(TIF_POLLING_NRFLAG);
} }
} }
......
...@@ -167,6 +167,19 @@ acpi_processor_power_activate(struct acpi_processor *pr, ...@@ -167,6 +167,19 @@ acpi_processor_power_activate(struct acpi_processor *pr,
return; return;
} }
static void acpi_safe_halt(void)
{
int polling = test_thread_flag(TIF_POLLING_NRFLAG);
if (polling) {
clear_thread_flag(TIF_POLLING_NRFLAG);
smp_mb__after_clear_bit();
}
if (!need_resched())
safe_halt();
if (polling)
set_thread_flag(TIF_POLLING_NRFLAG);
}
static atomic_t c3_cpu_count; static atomic_t c3_cpu_count;
static void acpi_processor_idle(void) static void acpi_processor_idle(void)
...@@ -177,7 +190,7 @@ static void acpi_processor_idle(void) ...@@ -177,7 +190,7 @@ static void acpi_processor_idle(void)
int sleep_ticks = 0; int sleep_ticks = 0;
u32 t1, t2 = 0; u32 t1, t2 = 0;
pr = processors[raw_smp_processor_id()]; pr = processors[smp_processor_id()];
if (!pr) if (!pr)
return; return;
...@@ -197,8 +210,13 @@ static void acpi_processor_idle(void) ...@@ -197,8 +210,13 @@ static void acpi_processor_idle(void)
} }
cx = pr->power.state; cx = pr->power.state;
if (!cx) if (!cx) {
goto easy_out; if (pm_idle_save)
pm_idle_save();
else
acpi_safe_halt();
return;
}
/* /*
* Check BM Activity * Check BM Activity
...@@ -278,7 +296,8 @@ static void acpi_processor_idle(void) ...@@ -278,7 +296,8 @@ static void acpi_processor_idle(void)
if (pm_idle_save) if (pm_idle_save)
pm_idle_save(); pm_idle_save();
else else
safe_halt(); acpi_safe_halt();
/* /*
* TBD: Can't get time duration while in C1, as resumes * TBD: Can't get time duration while in C1, as resumes
* go to an ISR rather than here. Need to instrument * go to an ISR rather than here. Need to instrument
...@@ -414,16 +433,6 @@ static void acpi_processor_idle(void) ...@@ -414,16 +433,6 @@ static void acpi_processor_idle(void)
*/ */
if (next_state != pr->power.state) if (next_state != pr->power.state)
acpi_processor_power_activate(pr, next_state); acpi_processor_power_activate(pr, next_state);
return;
easy_out:
/* do C1 instead of busy loop */
if (pm_idle_save)
pm_idle_save();
else
safe_halt();
return;
} }
static int acpi_processor_set_power_policy(struct acpi_processor *pr) static int acpi_processor_set_power_policy(struct acpi_processor *pr)
......
...@@ -864,21 +864,28 @@ static void deactivate_task(struct task_struct *p, runqueue_t *rq) ...@@ -864,21 +864,28 @@ static void deactivate_task(struct task_struct *p, runqueue_t *rq)
#ifdef CONFIG_SMP #ifdef CONFIG_SMP
static void resched_task(task_t *p) static void resched_task(task_t *p)
{ {
int need_resched, nrpolling; int cpu;
assert_spin_locked(&task_rq(p)->lock); assert_spin_locked(&task_rq(p)->lock);
/* minimise the chance of sending an interrupt to poll_idle() */ if (unlikely(test_tsk_thread_flag(p, TIF_NEED_RESCHED)))
nrpolling = test_tsk_thread_flag(p,TIF_POLLING_NRFLAG); return;
need_resched = test_and_set_tsk_thread_flag(p,TIF_NEED_RESCHED);
nrpolling |= test_tsk_thread_flag(p,TIF_POLLING_NRFLAG); set_tsk_thread_flag(p, TIF_NEED_RESCHED);
cpu = task_cpu(p);
if (cpu == smp_processor_id())
return;
if (!need_resched && !nrpolling && (task_cpu(p) != smp_processor_id())) /* NEED_RESCHED must be visible before we test POLLING_NRFLAG */
smp_send_reschedule(task_cpu(p)); smp_mb();
if (!test_tsk_thread_flag(p, TIF_POLLING_NRFLAG))
smp_send_reschedule(cpu);
} }
#else #else
static inline void resched_task(task_t *p) static inline void resched_task(task_t *p)
{ {
assert_spin_locked(&task_rq(p)->lock);
set_tsk_need_resched(p); set_tsk_need_resched(p);
} }
#endif #endif
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment