The patch titled
sched: rationalise resched and cpu_idle
has been added to the -mm tree. Its filename is
sched-rationalise-resched-and-cpu_idle.patch
Patches currently in -mm which might be from [EMAIL PROTECTED] are
ia64-cpuset-build_sched_domains-mangles-structures.patch
mm-comment-rmap.patch
mm-micro-optimise-rmap.patch
mm-cleanup-rmap.patch
mm-remap-zero_page-mappings.patch
mm-remove-atomic.patch
sched-idlest-cpus_allowed-aware.patch
sched-implement-nice-support-across-physical-cpus-on-smp.patch
sched-change_prio_bias_only_if_queued.patch
sched-account_rt_tasks_in_prio_bias.patch
sched-less-newidle-locking.patch
sched-less-locking.patch
sched-ht-optimisation.patch
sched-consider-migration-thread-with-smp-nice.patch
sched-rationalise-resched-and-cpu_idle.patch
sched2-sched-domain-sysctl.patch
From: Nick Piggin <[EMAIL PROTECTED]>
Make some changes to the NEED_RESCHED and POLLING_NRFLAG to reduce
confusion, and make their semantics rigid. Also have preempt explicitly
disabled in idle routines. 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: Nick Piggin <[EMAIL PROTECTED]>
Acked-by: Ingo Molnar <[EMAIL PROTECTED]>
Cc: Con Kolivas <[EMAIL PROTECTED]>
Signed-off-by: Andrew Morton <[EMAIL PROTECTED]>
---
Documentation/sched-arch.txt | 89 ++++++++++++++++++++++++++++++++++++++
arch/alpha/kernel/process.c | 10 +---
arch/arm/kernel/process.c | 18 ++++---
arch/arm/kernel/smp.c | 5 +-
arch/arm26/kernel/process.c | 12 ++---
arch/cris/arch-v32/kernel/smp.c | 2
arch/cris/kernel/process.c | 2
arch/frv/kernel/process.c | 6 ++
arch/h8300/kernel/process.c | 28 ++++++-----
arch/i386/kernel/apm.c | 20 ++++++++
arch/i386/kernel/process.c | 68 +++++++++++++----------------
arch/i386/kernel/smpboot.c | 2
arch/ia64/kernel/process.c | 34 ++++++++------
arch/ia64/kernel/smpboot.c | 2
arch/m32r/kernel/process.c | 2
arch/m32r/kernel/smpboot.c | 1
arch/m68k/kernel/process.c | 2
arch/mips/kernel/process.c | 2
arch/mips/kernel/smp.c | 6 ++
arch/parisc/kernel/process.c | 4 +
arch/parisc/kernel/smp.c | 2
arch/ppc/kernel/idle.c | 19 +++++---
arch/ppc/kernel/smp.c | 2
arch/ppc64/kernel/iSeries_setup.c | 14 ++---
arch/ppc64/kernel/idle.c | 14 ++---
arch/ppc64/kernel/pSeries_setup.c | 15 +++---
arch/ppc64/kernel/smp.c | 5 +-
arch/s390/kernel/process.c | 23 +++++----
arch/s390/kernel/smp.c | 2
arch/sh/kernel/process.c | 14 ++---
arch/sh/kernel/smp.c | 6 ++
arch/sh64/kernel/process.c | 16 ++----
arch/sparc/kernel/process.c | 35 +++++++-------
arch/sparc64/kernel/process.c | 24 +++++++---
arch/sparc64/kernel/smp.c | 16 +-----
arch/v850/kernel/process.c | 16 ++++--
arch/x86_64/kernel/process.c | 68 ++++++++++++++---------------
arch/x86_64/kernel/smpboot.c | 1
arch/xtensa/kernel/process.c | 3 -
drivers/acpi/processor_idle.c | 38 ++++++++++------
init/main.c | 4 +
kernel/sched.c | 21 +++++---
42 files changed, 422 insertions(+), 251 deletions(-)
diff -puN arch/alpha/kernel/process.c~sched-rationalise-resched-and-cpu_idle
arch/alpha/kernel/process.c
--- devel/arch/alpha/kernel/process.c~sched-rationalise-resched-and-cpu_idle
2005-08-29 23:46:39.000000000 -0700
+++ devel-akpm/arch/alpha/kernel/process.c 2005-08-29 23:46:39.000000000
-0700
@@ -43,21 +43,17 @@
#include "proto.h"
#include "pci_impl.h"
-void default_idle(void)
-{
- barrier();
-}
-
void
cpu_idle(void)
{
+ set_thread_flag(TIF_POLLING_NRFLAG);
+
while (1) {
- void (*idle)(void) = default_idle;
/* FIXME -- EV6 and LCA45 know how to power down
the CPU. */
while (!need_resched())
- idle();
+ cpu_relax();
schedule();
}
}
diff -puN arch/arm26/kernel/process.c~sched-rationalise-resched-and-cpu_idle
arch/arm26/kernel/process.c
--- devel/arch/arm26/kernel/process.c~sched-rationalise-resched-and-cpu_idle
2005-08-29 23:46:39.000000000 -0700
+++ devel-akpm/arch/arm26/kernel/process.c 2005-08-29 23:46:39.000000000
-0700
@@ -74,15 +74,13 @@ __setup("hlt", hlt_setup);
void cpu_idle(void)
{
/* endless idle loop with no priority at all */
- preempt_disable();
while (1) {
- while (!need_resched()) {
- local_irq_disable();
- if (!need_resched() && !hlt_counter)
- local_irq_enable();
- }
+ while (!need_resched())
+ cpu_relax();
+ preempt_enable_no_resched();
+ schedule();
+ preempt_disable();
}
- schedule();
}
static char reboot_mode = 'h';
diff -puN arch/arm/kernel/process.c~sched-rationalise-resched-and-cpu_idle
arch/arm/kernel/process.c
--- devel/arch/arm/kernel/process.c~sched-rationalise-resched-and-cpu_idle
2005-08-29 23:46:39.000000000 -0700
+++ devel-akpm/arch/arm/kernel/process.c 2005-08-29 23:46:39.000000000
-0700
@@ -85,12 +85,16 @@ EXPORT_SYMBOL(pm_power_off);
*/
void default_idle(void)
{
- local_irq_disable();
- if (!need_resched() && !hlt_counter) {
- timer_dyn_reprogram();
- arch_idle();
+ if (hlt_counter)
+ cpu_relax();
+ else {
+ local_irq_disable();
+ if (!need_resched()) {
+ timer_dyn_reprogram();
+ arch_idle();
+ }
+ local_irq_enable();
}
- local_irq_enable();
}
/*
@@ -107,13 +111,13 @@ void cpu_idle(void)
void (*idle)(void) = pm_idle;
if (!idle)
idle = default_idle;
- preempt_disable();
leds_event(led_idle_start);
while (!need_resched())
idle();
leds_event(led_idle_end);
- preempt_enable();
+ preempt_enable_no_resched();
schedule();
+ preempt_disable();
}
}
diff -puN arch/arm/kernel/smp.c~sched-rationalise-resched-and-cpu_idle
arch/arm/kernel/smp.c
--- devel/arch/arm/kernel/smp.c~sched-rationalise-resched-and-cpu_idle
2005-08-29 23:46:39.000000000 -0700
+++ devel-akpm/arch/arm/kernel/smp.c 2005-08-29 23:46:39.000000000 -0700
@@ -162,7 +162,10 @@ int __cpuinit __cpu_up(unsigned int cpu)
asmlinkage void __cpuinit secondary_start_kernel(void)
{
struct mm_struct *mm = &init_mm;
- unsigned int cpu = smp_processor_id();
+ unsigned int cpu;
+
+ preempt_disable();
+ cpu = smp_processor_id();
printk("CPU%u: Booted secondary processor\n", cpu);
diff -puN
arch/cris/arch-v32/kernel/smp.c~sched-rationalise-resched-and-cpu_idle
arch/cris/arch-v32/kernel/smp.c
---
devel/arch/cris/arch-v32/kernel/smp.c~sched-rationalise-resched-and-cpu_idle
2005-08-29 23:46:39.000000000 -0700
+++ devel-akpm/arch/cris/arch-v32/kernel/smp.c 2005-08-29 23:46:39.000000000
-0700
@@ -144,6 +144,8 @@ void __init smp_callin(void)
int cpu = cpu_now_booting;
reg_intr_vect_rw_mask vect_mask = {0};
+ preempt_disable();
+
/* Initialise the idle task for this CPU */
atomic_inc(&init_mm.mm_count);
current->active_mm = &init_mm;
diff -puN arch/cris/kernel/process.c~sched-rationalise-resched-and-cpu_idle
arch/cris/kernel/process.c
--- devel/arch/cris/kernel/process.c~sched-rationalise-resched-and-cpu_idle
2005-08-29 23:46:39.000000000 -0700
+++ devel-akpm/arch/cris/kernel/process.c 2005-08-29 23:46:39.000000000
-0700
@@ -218,7 +218,9 @@ void cpu_idle (void)
idle = default_idle;
idle();
}
+ preempt_enable_no_resched();
schedule();
+ preempt_disable();
}
}
diff -puN arch/frv/kernel/process.c~sched-rationalise-resched-and-cpu_idle
arch/frv/kernel/process.c
--- devel/arch/frv/kernel/process.c~sched-rationalise-resched-and-cpu_idle
2005-08-29 23:46:39.000000000 -0700
+++ devel-akpm/arch/frv/kernel/process.c 2005-08-29 23:46:39.000000000
-0700
@@ -77,16 +77,20 @@ void (*idle)(void) = core_sleep_idle;
*/
void cpu_idle(void)
{
+ int cpu = smp_processor_id();
+
/* endless idle loop with no priority at all */
while (1) {
while (!need_resched()) {
- irq_stat[smp_processor_id()].idle_timestamp = jiffies;
+ irq_stat[cpu].idle_timestamp = jiffies;
if (!frv_dma_inprogress && idle)
idle();
}
+ preempt_enable_no_resched();
schedule();
+ preempt_disable();
}
}
diff -puN arch/h8300/kernel/process.c~sched-rationalise-resched-and-cpu_idle
arch/h8300/kernel/process.c
--- devel/arch/h8300/kernel/process.c~sched-rationalise-resched-and-cpu_idle
2005-08-29 23:46:39.000000000 -0700
+++ devel-akpm/arch/h8300/kernel/process.c 2005-08-29 23:46:39.000000000
-0700
@@ -53,22 +53,18 @@ asmlinkage void ret_from_fork(void);
#if !defined(CONFIG_H8300H_SIM) && !defined(CONFIG_H8S_SIM)
void default_idle(void)
{
- while(1) {
- if (!need_resched()) {
- local_irq_enable();
- __asm__("sleep");
- local_irq_disable();
- }
- schedule();
- }
+ local_irq_disable();
+ if (!need_resched()) {
+ local_irq_enable();
+ /* XXX: race here! What if need_resched() gets set now? */
+ __asm__("sleep");
+ } else
+ local_irq_enable();
}
#else
void default_idle(void)
{
- while(1) {
- if (need_resched())
- schedule();
- }
+ cpu_relax();
}
#endif
void (*idle)(void) = default_idle;
@@ -81,7 +77,13 @@ void (*idle)(void) = default_idle;
*/
void cpu_idle(void)
{
- idle();
+ while (1) {
+ while (!need_resched())
+ idle();
+ preempt_enable_no_resched();
+ schedule();
+ preempt_disable();
+ }
}
void machine_restart(char * __unused)
diff -puN arch/i386/kernel/apm.c~sched-rationalise-resched-and-cpu_idle
arch/i386/kernel/apm.c
--- devel/arch/i386/kernel/apm.c~sched-rationalise-resched-and-cpu_idle
2005-08-29 23:46:39.000000000 -0700
+++ devel-akpm/arch/i386/kernel/apm.c 2005-08-29 23:46:39.000000000 -0700
@@ -770,8 +770,26 @@ static int set_system_power_state(u_shor
static int apm_do_idle(void)
{
u32 eax;
+ u8 ret;
+ 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;
/* This always fails on some SMP boards running UP kernels.
diff -puN arch/i386/kernel/process.c~sched-rationalise-resched-and-cpu_idle
arch/i386/kernel/process.c
--- devel/arch/i386/kernel/process.c~sched-rationalise-resched-and-cpu_idle
2005-08-29 23:46:39.000000000 -0700
+++ devel-akpm/arch/i386/kernel/process.c 2005-08-29 23:46:39.000000000
-0700
@@ -102,14 +102,22 @@ EXPORT_SYMBOL(enable_hlt);
*/
void default_idle(void)
{
+ local_irq_enable();
+
if (!hlt_counter && boot_cpu_data.hlt_works_ok) {
- local_irq_disable();
- if (!need_resched())
- safe_halt();
- else
- local_irq_enable();
+ clear_thread_flag(TIF_POLLING_NRFLAG);
+ smp_mb__after_clear_bit();
+ while (!need_resched()) {
+ local_irq_disable();
+ if (!need_resched())
+ safe_halt();
+ else
+ local_irq_enable();
+ }
+ set_thread_flag(TIF_POLLING_NRFLAG);
} else {
- cpu_relax();
+ while (!need_resched())
+ cpu_relax();
}
}
#ifdef CONFIG_APM_MODULE
@@ -123,29 +131,14 @@ EXPORT_SYMBOL(default_idle);
*/
static void poll_idle (void)
{
- int oldval;
-
local_irq_enable();
- /*
- * Deal with another CPU just having chosen a thread to
- * run here:
- */
- oldval = test_and_clear_thread_flag(TIF_NEED_RESCHED);
-
- 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();
- }
+ asm volatile(
+ "2:"
+ "testl %0, %1;"
+ "rep; nop;"
+ "je 2b;"
+ : : "i"(_TIF_NEED_RESCHED), "m" (current_thread_info()->flags));
}
#ifdef CONFIG_HOTPLUG_CPU
@@ -182,7 +175,9 @@ static inline void play_dead(void)
*/
void cpu_idle(void)
{
- int cpu = raw_smp_processor_id();
+ int cpu = smp_processor_id();
+
+ set_thread_flag(TIF_POLLING_NRFLAG);
/* endless idle loop with no priority at all */
while (1) {
@@ -204,7 +199,9 @@ void cpu_idle(void)
__get_cpu_var(irq_stat).idle_timestamp = jiffies;
idle();
}
+ preempt_enable_no_resched();
schedule();
+ preempt_disable();
}
}
@@ -247,15 +244,12 @@ static void mwait_idle(void)
{
local_irq_enable();
- if (!need_resched()) {
- set_thread_flag(TIF_POLLING_NRFLAG);
- do {
- __monitor((void *)¤t_thread_info()->flags, 0, 0);
- if (need_resched())
- break;
- __mwait(0, 0);
- } while (!need_resched());
- clear_thread_flag(TIF_POLLING_NRFLAG);
+ while (!need_resched()) {
+ __monitor((void *)¤t_thread_info()->flags, 0, 0);
+ smp_mb();
+ if (need_resched())
+ break;
+ __mwait(0, 0);
}
}
diff -puN arch/i386/kernel/smpboot.c~sched-rationalise-resched-and-cpu_idle
arch/i386/kernel/smpboot.c
--- devel/arch/i386/kernel/smpboot.c~sched-rationalise-resched-and-cpu_idle
2005-08-29 23:46:39.000000000 -0700
+++ devel-akpm/arch/i386/kernel/smpboot.c 2005-08-29 23:46:39.000000000
-0700
@@ -478,6 +478,8 @@ set_cpu_sibling_map(int cpu)
*/
static void __devinit start_secondary(void *unused)
{
+ preempt_disable();
+
/*
* Dont put anything before smp_callin(), SMP
* booting is too fragile that we want to limit the
diff -puN arch/ia64/kernel/process.c~sched-rationalise-resched-and-cpu_idle
arch/ia64/kernel/process.c
--- devel/arch/ia64/kernel/process.c~sched-rationalise-resched-and-cpu_idle
2005-08-29 23:46:39.000000000 -0700
+++ devel-akpm/arch/ia64/kernel/process.c 2005-08-29 23:46:39.000000000
-0700
@@ -197,11 +197,15 @@ void
default_idle (void)
{
local_irq_enable();
- while (!need_resched())
- if (can_do_pal_halt)
- safe_halt();
- else
+ while (!need_resched()) {
+ if (can_do_pal_halt) {
+ local_irq_disable();
+ if (!need_resched())
+ safe_halt();
+ local_irq_enable();
+ } else
cpu_relax();
+ }
}
#ifdef CONFIG_HOTPLUG_CPU
@@ -263,16 +267,16 @@ void __attribute__((noreturn))
cpu_idle (void)
{
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 */
while (1) {
+ if (!need_resched()) {
+ void (*idle)(void);
#ifdef CONFIG_SMP
- if (!need_resched())
min_xtp();
#endif
- while (!need_resched()) {
- void (*idle)(void);
-
if (__get_cpu_var(cpu_idle_state))
__get_cpu_var(cpu_idle_state) = 0;
@@ -284,17 +288,17 @@ cpu_idle (void)
if (!idle)
idle = default_idle;
(*idle)();
- }
-
- if (mark_idle)
- (*mark_idle)(0);
-
+ if (mark_idle)
+ (*mark_idle)(0);
#ifdef CONFIG_SMP
- normal_xtp();
+ normal_xtp();
#endif
+ }
+ preempt_enable_no_resched();
schedule();
+ preempt_disable();
check_pgt_cache();
- if (cpu_is_offline(smp_processor_id()))
+ if (cpu_is_offline(cpu))
play_dead();
}
}
diff -puN arch/ia64/kernel/smpboot.c~sched-rationalise-resched-and-cpu_idle
arch/ia64/kernel/smpboot.c
--- devel/arch/ia64/kernel/smpboot.c~sched-rationalise-resched-and-cpu_idle
2005-08-29 23:46:39.000000000 -0700
+++ devel-akpm/arch/ia64/kernel/smpboot.c 2005-08-29 23:46:39.000000000
-0700
@@ -394,6 +394,8 @@ smp_callin (void)
int __devinit
start_secondary (void *unused)
{
+ preempt_disable();
+
/* Early console may use I/O ports */
ia64_set_kr(IA64_KR_IO_BASE, __pa(ia64_iobase));
Dprintk("start_secondary: starting CPU 0x%x\n",
hard_smp_processor_id());
diff -puN arch/m32r/kernel/process.c~sched-rationalise-resched-and-cpu_idle
arch/m32r/kernel/process.c
--- devel/arch/m32r/kernel/process.c~sched-rationalise-resched-and-cpu_idle
2005-08-29 23:46:39.000000000 -0700
+++ devel-akpm/arch/m32r/kernel/process.c 2005-08-29 23:46:39.000000000
-0700
@@ -104,7 +104,9 @@ void cpu_idle (void)
idle();
}
+ preempt_enable_no_resched();
schedule();
+ preempt_disable();
}
}
diff -puN arch/m32r/kernel/smpboot.c~sched-rationalise-resched-and-cpu_idle
arch/m32r/kernel/smpboot.c
--- devel/arch/m32r/kernel/smpboot.c~sched-rationalise-resched-and-cpu_idle
2005-08-29 23:46:39.000000000 -0700
+++ devel-akpm/arch/m32r/kernel/smpboot.c 2005-08-29 23:46:39.000000000
-0700
@@ -425,6 +425,7 @@ void __init smp_cpus_done(unsigned int m
*==========================================================================*/
int __init start_secondary(void *unused)
{
+ preempt_disable();
cpu_init();
smp_callin();
while (!cpu_isset(smp_processor_id(), smp_commenced_mask))
diff -puN arch/m68k/kernel/process.c~sched-rationalise-resched-and-cpu_idle
arch/m68k/kernel/process.c
--- devel/arch/m68k/kernel/process.c~sched-rationalise-resched-and-cpu_idle
2005-08-29 23:46:39.000000000 -0700
+++ devel-akpm/arch/m68k/kernel/process.c 2005-08-29 23:46:39.000000000
-0700
@@ -102,7 +102,9 @@ void cpu_idle(void)
while (1) {
while (!need_resched())
idle();
+ preempt_enable_no_resched();
schedule();
+ preempt_disable();
}
}
diff -puN arch/mips/kernel/process.c~sched-rationalise-resched-and-cpu_idle
arch/mips/kernel/process.c
--- devel/arch/mips/kernel/process.c~sched-rationalise-resched-and-cpu_idle
2005-08-29 23:46:39.000000000 -0700
+++ devel-akpm/arch/mips/kernel/process.c 2005-08-29 23:46:39.000000000
-0700
@@ -58,7 +58,9 @@ ATTRIB_NORET void cpu_idle(void)
while (!need_resched())
if (cpu_wait)
(*cpu_wait)();
+ preempt_enable_no_resched();
schedule();
+ preempt_disable()
}
}
diff -puN arch/mips/kernel/smp.c~sched-rationalise-resched-and-cpu_idle
arch/mips/kernel/smp.c
--- devel/arch/mips/kernel/smp.c~sched-rationalise-resched-and-cpu_idle
2005-08-29 23:46:39.000000000 -0700
+++ devel-akpm/arch/mips/kernel/smp.c 2005-08-29 23:46:39.000000000 -0700
@@ -83,7 +83,11 @@ extern ATTRIB_NORET void cpu_idle(void);
*/
asmlinkage void start_secondary(void)
{
- unsigned int cpu = smp_processor_id();
+ unsigned int cpu;
+
+ preempt_disable();
+
+ cpu = smp_processor_id();
cpu_probe();
cpu_report();
diff -puN arch/parisc/kernel/process.c~sched-rationalise-resched-and-cpu_idle
arch/parisc/kernel/process.c
--- devel/arch/parisc/kernel/process.c~sched-rationalise-resched-and-cpu_idle
2005-08-29 23:46:39.000000000 -0700
+++ devel-akpm/arch/parisc/kernel/process.c 2005-08-29 23:46:39.000000000
-0700
@@ -88,11 +88,15 @@ void default_idle(void)
*/
void cpu_idle(void)
{
+ set_thread_flag(TIF_POLLING_NRFLAG);
+
/* endless idle loop with no priority at all */
while (1) {
while (!need_resched())
barrier();
+ preempt_enable_no_resched();
schedule();
+ preempt_disable();
check_pgt_cache();
}
}
diff -puN arch/parisc/kernel/smp.c~sched-rationalise-resched-and-cpu_idle
arch/parisc/kernel/smp.c
--- devel/arch/parisc/kernel/smp.c~sched-rationalise-resched-and-cpu_idle
2005-08-29 23:46:39.000000000 -0700
+++ devel-akpm/arch/parisc/kernel/smp.c 2005-08-29 23:46:39.000000000 -0700
@@ -462,6 +462,8 @@ void __init smp_callin(void)
void *istack;
#endif
+ preempt_disable();
+
smp_cpu_init(slave_id);
#if 0 /* NOT WORKING YET - see entry.S */
diff -puN arch/ppc64/kernel/idle.c~sched-rationalise-resched-and-cpu_idle
arch/ppc64/kernel/idle.c
--- devel/arch/ppc64/kernel/idle.c~sched-rationalise-resched-and-cpu_idle
2005-08-29 23:46:39.000000000 -0700
+++ devel-akpm/arch/ppc64/kernel/idle.c 2005-08-29 23:46:39.000000000 -0700
@@ -35,13 +35,10 @@ int default_idle(void)
{
long oldval;
unsigned int cpu = smp_processor_id();
+ set_thread_flag(TIF_POLLING_NRFLAG);
while (1) {
- oldval = test_and_clear_thread_flag(TIF_NEED_RESCHED);
-
- if (!oldval) {
- set_thread_flag(TIF_POLLING_NRFLAG);
-
+ if (!need_resched()) {
while (!need_resched() && !cpu_is_offline(cpu)) {
ppc64_runlatch_off();
@@ -54,13 +51,12 @@ int default_idle(void)
}
HMT_medium();
- clear_thread_flag(TIF_POLLING_NRFLAG);
- } else {
- set_need_resched();
}
ppc64_runlatch_on();
+ preempt_enable_no_resched();
schedule();
+ preempt_disable();
if (cpu_is_offline(cpu) && system_state == SYSTEM_RUNNING)
cpu_die();
}
@@ -78,7 +74,9 @@ int native_idle(void)
if (need_resched()) {
ppc64_runlatch_on();
+ preempt_enable_no_resched();
schedule();
+ preempt_disable();
}
if (cpu_is_offline(smp_processor_id()) &&
diff -puN
arch/ppc64/kernel/iSeries_setup.c~sched-rationalise-resched-and-cpu_idle
arch/ppc64/kernel/iSeries_setup.c
---
devel/arch/ppc64/kernel/iSeries_setup.c~sched-rationalise-resched-and-cpu_idle
2005-08-29 23:46:39.000000000 -0700
+++ devel-akpm/arch/ppc64/kernel/iSeries_setup.c 2005-08-29
23:46:39.000000000 -0700
@@ -878,7 +878,9 @@ static int iseries_shared_idle(void)
if (hvlpevent_is_pending())
process_iSeries_events();
+ preempt_enable_no_resched();
schedule();
+ preempt_disable();
}
return 0;
@@ -887,13 +889,10 @@ static int iseries_shared_idle(void)
static int iseries_dedicated_idle(void)
{
long oldval;
+ set_thread_flag(TIF_POLLING_NRFLAG);
while (1) {
- oldval = test_and_clear_thread_flag(TIF_NEED_RESCHED);
-
- if (!oldval) {
- set_thread_flag(TIF_POLLING_NRFLAG);
-
+ if (!need_resched()) {
while (!need_resched()) {
ppc64_runlatch_off();
HMT_low();
@@ -906,13 +905,12 @@ static int iseries_dedicated_idle(void)
}
HMT_medium();
- clear_thread_flag(TIF_POLLING_NRFLAG);
- } else {
- set_need_resched();
}
ppc64_runlatch_on();
+ preempt_enable_no_resched();
schedule();
+ preempt_disable();
}
return 0;
diff -puN
arch/ppc64/kernel/pSeries_setup.c~sched-rationalise-resched-and-cpu_idle
arch/ppc64/kernel/pSeries_setup.c
---
devel/arch/ppc64/kernel/pSeries_setup.c~sched-rationalise-resched-and-cpu_idle
2005-08-29 23:46:39.000000000 -0700
+++ devel-akpm/arch/ppc64/kernel/pSeries_setup.c 2005-08-29
23:46:39.000000000 -0700
@@ -451,6 +451,7 @@ static inline void dedicated_idle_sleep(
* more.
*/
clear_thread_flag(TIF_POLLING_NRFLAG);
+ smp_mb__after_clear_bit();
/*
* SMT dynamic mode. Cede will result in this thread going
@@ -463,6 +464,7 @@ static inline void dedicated_idle_sleep(
cede_processor();
else
local_irq_enable();
+ set_thread_flag(TIF_POLLING_NRFLAG);
} else {
/*
* Give the HV an opportunity at the processor, since we are
@@ -479,6 +481,7 @@ static int pseries_dedicated_idle(void)
unsigned int cpu = smp_processor_id();
unsigned long start_snooze;
unsigned long *smt_snooze_delay = &__get_cpu_var(smt_snooze_delay);
+ set_thread_flag(TIF_POLLING_NRFLAG);
while (1) {
/*
@@ -487,10 +490,7 @@ static int pseries_dedicated_idle(void)
*/
lpaca->lppaca.idle = 1;
- oldval = test_and_clear_thread_flag(TIF_NEED_RESCHED);
- if (!oldval) {
- set_thread_flag(TIF_POLLING_NRFLAG);
-
+ if (!need_resched()) {
start_snooze = __get_tb() +
*smt_snooze_delay * tb_ticks_per_usec;
@@ -513,15 +513,14 @@ static int pseries_dedicated_idle(void)
}
HMT_medium();
- clear_thread_flag(TIF_POLLING_NRFLAG);
- } else {
- set_need_resched();
}
lpaca->lppaca.idle = 0;
ppc64_runlatch_on();
+ preempt_enable_no_resched();
schedule();
+ preempt_disable();
if (cpu_is_offline(cpu) && system_state == SYSTEM_RUNNING)
cpu_die();
@@ -565,7 +564,9 @@ static int pseries_shared_idle(void)
lpaca->lppaca.idle = 0;
ppc64_runlatch_on();
+ preempt_enable_no_resched();
schedule();
+ preempt_disable();
if (cpu_is_offline(cpu) && system_state == SYSTEM_RUNNING)
cpu_die();
diff -puN arch/ppc64/kernel/smp.c~sched-rationalise-resched-and-cpu_idle
arch/ppc64/kernel/smp.c
--- devel/arch/ppc64/kernel/smp.c~sched-rationalise-resched-and-cpu_idle
2005-08-29 23:46:39.000000000 -0700
+++ devel-akpm/arch/ppc64/kernel/smp.c 2005-08-29 23:46:39.000000000 -0700
@@ -545,7 +545,10 @@ int __devinit __cpu_up(unsigned int cpu)
/* Activate a secondary processor. */
int __devinit start_secondary(void *unused)
{
- unsigned int cpu = smp_processor_id();
+ unsigned int cpu;
+
+ preempt_disable();
+ cpu = smp_processor_id();
atomic_inc(&init_mm.mm_count);
current->active_mm = &init_mm;
diff -puN arch/ppc/kernel/idle.c~sched-rationalise-resched-and-cpu_idle
arch/ppc/kernel/idle.c
--- devel/arch/ppc/kernel/idle.c~sched-rationalise-resched-and-cpu_idle
2005-08-29 23:46:39.000000000 -0700
+++ devel-akpm/arch/ppc/kernel/idle.c 2005-08-29 23:46:39.000000000 -0700
@@ -50,8 +50,6 @@ void default_idle(void)
}
#endif
}
- if (need_resched())
- schedule();
}
/*
@@ -59,11 +57,18 @@ void default_idle(void)
*/
void cpu_idle(void)
{
- for (;;)
- if (ppc_md.idle != NULL)
- ppc_md.idle();
- else
- default_idle();
+ for (;;) {
+ while (need_resched()) {
+ if (ppc_md.idle != NULL)
+ ppc_md.idle();
+ else
+ default_idle();
+ }
+
+ preempt_enable_no_resched();
+ schedule();
+ preempt_disable();
+ }
}
#if defined(CONFIG_SYSCTL) && defined(CONFIG_6xx)
diff -puN arch/ppc/kernel/smp.c~sched-rationalise-resched-and-cpu_idle
arch/ppc/kernel/smp.c
--- devel/arch/ppc/kernel/smp.c~sched-rationalise-resched-and-cpu_idle
2005-08-29 23:46:39.000000000 -0700
+++ devel-akpm/arch/ppc/kernel/smp.c 2005-08-29 23:46:39.000000000 -0700
@@ -326,6 +326,8 @@ int __devinit start_secondary(void *unus
{
int cpu;
+ preempt_disable();
+
atomic_inc(&init_mm.mm_count);
current->active_mm = &init_mm;
diff -puN arch/s390/kernel/process.c~sched-rationalise-resched-and-cpu_idle
arch/s390/kernel/process.c
--- devel/arch/s390/kernel/process.c~sched-rationalise-resched-and-cpu_idle
2005-08-29 23:46:39.000000000 -0700
+++ devel-akpm/arch/s390/kernel/process.c 2005-08-29 23:46:39.000000000
-0700
@@ -99,15 +99,15 @@ void default_idle(void)
{
int cpu, rc;
+ /* CPU is going idle. */
+ cpu = smp_processor_id();
+
local_irq_disable();
- if (need_resched()) {
+ if (need_resched()) {
local_irq_enable();
- schedule();
- return;
- }
+ return;
+ }
- /* CPU is going idle. */
- cpu = smp_processor_id();
rc = notifier_call_chain(&idle_chain, CPU_IDLE, (void *)(long) cpu);
if (rc != NOTIFY_OK && rc != NOTIFY_DONE)
BUG();
@@ -120,7 +120,7 @@ void default_idle(void)
__ctl_set_bit(8, 15);
#ifdef CONFIG_HOTPLUG_CPU
- if (cpu_is_offline(smp_processor_id()))
+ if (cpu_is_offline(cpu))
cpu_die();
#endif
@@ -139,8 +139,13 @@ void default_idle(void)
void cpu_idle(void)
{
- for (;;)
- default_idle();
+ for (;;) {
+ while (!need_resched())
+ default_idle();
+ preempt_enable_no_resched();
+ schedule();
+ preempt_disable();
+ }
}
void show_regs(struct pt_regs *regs)
diff -puN arch/s390/kernel/smp.c~sched-rationalise-resched-and-cpu_idle
arch/s390/kernel/smp.c
--- devel/arch/s390/kernel/smp.c~sched-rationalise-resched-and-cpu_idle
2005-08-29 23:46:39.000000000 -0700
+++ devel-akpm/arch/s390/kernel/smp.c 2005-08-29 23:46:39.000000000 -0700
@@ -528,6 +528,8 @@ extern void pfault_fini(void);
int __devinit start_secondary(void *cpuvoid)
{
+ preempt_disable();
+
/* Setup the cpu */
cpu_init();
/* init per CPU timer */
diff -puN arch/sh64/kernel/process.c~sched-rationalise-resched-and-cpu_idle
arch/sh64/kernel/process.c
--- devel/arch/sh64/kernel/process.c~sched-rationalise-resched-and-cpu_idle
2005-08-29 23:46:39.000000000 -0700
+++ devel-akpm/arch/sh64/kernel/process.c 2005-08-29 23:46:39.000000000
-0700
@@ -307,23 +307,19 @@ __setup("hlt", hlt_setup);
static inline void hlt(void)
{
- if (hlt_counter)
- return;
-
__asm__ __volatile__ ("sleep" : : : "memory");
}
/*
* The idle loop on a uniprocessor SH..
*/
-void default_idle(void)
+void cpu_idle(void)
{
/* endless idle loop with no priority at all */
while (1) {
if (hlt_counter) {
- while (1)
- if (need_resched())
- break;
+ while (!need_resched())
+ cpu_relax();
} else {
local_irq_disable();
while (!need_resched()) {
@@ -334,13 +330,11 @@ void default_idle(void)
}
local_irq_enable();
}
+ preempt_enable_no_resched();
schedule();
+ preempt_disable();
}
-}
-void cpu_idle(void)
-{
- default_idle();
}
void machine_restart(char * __unused)
diff -puN arch/sh/kernel/process.c~sched-rationalise-resched-and-cpu_idle
arch/sh/kernel/process.c
--- devel/arch/sh/kernel/process.c~sched-rationalise-resched-and-cpu_idle
2005-08-29 23:46:39.000000000 -0700
+++ devel-akpm/arch/sh/kernel/process.c 2005-08-29 23:46:39.000000000 -0700
@@ -51,28 +51,24 @@ void enable_hlt(void)
EXPORT_SYMBOL(enable_hlt);
-void default_idle(void)
+void cpu_idle(void)
{
/* endless idle loop with no priority at all */
while (1) {
if (hlt_counter) {
- while (1)
- if (need_resched())
- break;
+ while (!need_resched())
+ cpu_relax();
} else {
while (!need_resched())
cpu_sleep();
}
+ preempt_disable_no_resched();
schedule();
+ preempt_enable();
}
}
-void cpu_idle(void)
-{
- default_idle();
-}
-
void machine_restart(char * __unused)
{
/* SR.BL=1 and invoke address error to let CPU reset (manual reset) */
diff -puN arch/sh/kernel/smp.c~sched-rationalise-resched-and-cpu_idle
arch/sh/kernel/smp.c
--- devel/arch/sh/kernel/smp.c~sched-rationalise-resched-and-cpu_idle
2005-08-29 23:46:39.000000000 -0700
+++ devel-akpm/arch/sh/kernel/smp.c 2005-08-29 23:46:39.000000000 -0700
@@ -109,7 +109,11 @@ int __cpu_up(unsigned int cpu)
int start_secondary(void *unused)
{
- unsigned int cpu = smp_processor_id();
+ unsigned int cpu;
+
+ preempt_disable();
+
+ cpu = smp_processor_id();
atomic_inc(&init_mm.mm_count);
current->active_mm = &init_mm;
diff -puN arch/sparc64/kernel/process.c~sched-rationalise-resched-and-cpu_idle
arch/sparc64/kernel/process.c
--- devel/arch/sparc64/kernel/process.c~sched-rationalise-resched-and-cpu_idle
2005-08-29 23:46:39.000000000 -0700
+++ devel-akpm/arch/sparc64/kernel/process.c 2005-08-29 23:46:39.000000000
-0700
@@ -74,7 +74,9 @@ void cpu_idle(void)
while (!need_resched())
barrier();
+ preempt_enable_no_resched();
schedule();
+ preempt_disable();
check_pgt_cache();
}
}
@@ -83,21 +85,31 @@ void cpu_idle(void)
/*
* 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)
{
+ cpuinfo_sparc *cpuinfo = &local_cpu_data();
set_thread_flag(TIF_POLLING_NRFLAG);
+
while(1) {
if (need_resched()) {
- unidle_me();
- clear_thread_flag(TIF_POLLING_NRFLAG);
+ cpuinfo->idle_volume = 0;
+ preempt_enable_no_resched();
schedule();
- set_thread_flag(TIF_POLLING_NRFLAG);
+ preempt_disable();
check_pgt_cache();
}
- idle_me_harder();
+ cpuinfo->idle_volume++;
/* The store ordering is so that IRQ handlers on
* other cpus see our increasing idleness for the buddy
diff -puN arch/sparc64/kernel/smp.c~sched-rationalise-resched-and-cpu_idle
arch/sparc64/kernel/smp.c
--- devel/arch/sparc64/kernel/smp.c~sched-rationalise-resched-and-cpu_idle
2005-08-29 23:46:39.000000000 -0700
+++ devel-akpm/arch/sparc64/kernel/smp.c 2005-08-29 23:46:39.000000000
-0700
@@ -147,6 +147,9 @@ void __init smp_callin(void)
membar("#LoadLoad");
cpu_set(cpuid, cpu_online_map);
+
+ /* idle thread is expected to have preempt disabled */
+ preempt_disable();
}
void cpu_panic(void)
@@ -1170,20 +1173,9 @@ void __init smp_cpus_done(unsigned int m
(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)
{
- 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
diff -puN arch/sparc/kernel/process.c~sched-rationalise-resched-and-cpu_idle
arch/sparc/kernel/process.c
--- devel/arch/sparc/kernel/process.c~sched-rationalise-resched-and-cpu_idle
2005-08-29 23:46:39.000000000 -0700
+++ devel-akpm/arch/sparc/kernel/process.c 2005-08-29 23:46:39.000000000
-0700
@@ -67,13 +67,6 @@ extern void fpsave(unsigned long *, unsi
struct task_struct *last_task_used_math = NULL;
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
#define SUN4C_FAULT_HIGH 100
@@ -92,12 +85,11 @@ void cpu_idle(void)
static unsigned long fps;
unsigned long now;
unsigned long faults;
- unsigned long flags;
extern unsigned long sun4c_kernel_faults;
extern void sun4c_grow_kernel_ring(void);
- local_irq_save(flags);
+ local_irq_disable();
now = jiffies;
count -= (now - last_jiffies);
last_jiffies = now;
@@ -113,14 +105,19 @@ void cpu_idle(void)
sun4c_grow_kernel_ring();
}
}
- local_irq_restore(flags);
+ local_irq_enable();
}
- while((!need_resched()) && pm_idle) {
- (*pm_idle)();
+ if (pm_idle) {
+ while (!need_resched())
+ (*pm_idle)();
+ } else {
+ while (!need_resched())
+ cpu_relax();
}
-
+ preempt_enable_no_resched();
schedule();
+ preempt_disable();
check_pgt_cache();
}
}
@@ -130,13 +127,15 @@ void cpu_idle(void)
/* This is being executed in task 0 'user space'. */
void cpu_idle(void)
{
+ set_thread_flag(TIF_POLLING_NRFLAG);
/* endless idle loop with no priority at all */
while(1) {
- if(need_resched()) {
- schedule();
- check_pgt_cache();
- }
- barrier(); /* or else gcc optimizes... */
+ while (!need_resched())
+ cpu_relax();
+ preempt_enable_no_resched();
+ schedule();
+ preempt_disable();
+ check_pgt_cache();
}
}
diff -puN arch/v850/kernel/process.c~sched-rationalise-resched-and-cpu_idle
arch/v850/kernel/process.c
--- devel/arch/v850/kernel/process.c~sched-rationalise-resched-and-cpu_idle
2005-08-29 23:46:39.000000000 -0700
+++ devel-akpm/arch/v850/kernel/process.c 2005-08-29 23:46:39.000000000
-0700
@@ -36,11 +36,8 @@ extern void ret_from_fork (void);
/* The idle loop. */
void default_idle (void)
{
- while (1) {
- while (! need_resched ())
- asm ("halt; nop; nop; nop; nop; nop" ::: "cc");
- schedule ();
- }
+ while (! need_resched ())
+ asm ("halt; nop; nop; nop; nop; nop" ::: "cc");
}
void (*idle)(void) = default_idle;
@@ -54,7 +51,14 @@ void (*idle)(void) = default_idle;
void cpu_idle (void)
{
/* endless idle loop with no priority at all */
- (*idle) ();
+ while (1) {
+ while (!need_resched())
+ (*idle) ();
+
+ preempt_enable_no_resched();
+ schedule();
+ preempt_disable();
+ }
}
/*
diff -puN arch/x86_64/kernel/process.c~sched-rationalise-resched-and-cpu_idle
arch/x86_64/kernel/process.c
--- devel/arch/x86_64/kernel/process.c~sched-rationalise-resched-and-cpu_idle
2005-08-29 23:46:39.000000000 -0700
+++ devel-akpm/arch/x86_64/kernel/process.c 2005-08-29 23:46:39.000000000
-0700
@@ -88,12 +88,22 @@ EXPORT_SYMBOL(enable_hlt);
*/
void default_idle(void)
{
+ local_irq_enable();
+
if (!atomic_read(&hlt_counter)) {
- local_irq_disable();
- if (!need_resched())
- safe_halt();
- else
- local_irq_enable();
+ clear_thread_flag(TIF_POLLING_NRFLAG);
+ smp_mb__after_clear_bit();
+ while (!need_resched()) {
+ local_irq_disable();
+ if (!need_resched())
+ safe_halt();
+ else
+ local_irq_enable();
+ }
+ set_thread_flag(TIF_POLLING_NRFLAG);
+ } else {
+ while (!need_resched())
+ cpu_relax();
}
}
@@ -104,29 +114,16 @@ void default_idle(void)
*/
static void poll_idle (void)
{
- int oldval;
-
local_irq_enable();
- /*
- * Deal with another CPU just having chosen a thread to
- * run here:
- */
- oldval = test_and_clear_thread_flag(TIF_NEED_RESCHED);
-
- 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));
- } else {
- set_need_resched();
- }
+ asm volatile(
+ "2:"
+ "testl %0,%1;"
+ "rep; nop;"
+ "je 2b;"
+ : :
+ "i" (_TIF_NEED_RESCHED),
+ "m" (current_thread_info()->flags));
}
void cpu_idle_wait(void)
@@ -188,6 +185,8 @@ static inline void play_dead(void)
*/
void cpu_idle (void)
{
+ set_thread_flag(TIF_POLLING_NRFLAG);
+
/* endless idle loop with no priority at all */
while (1) {
while (!need_resched()) {
@@ -205,7 +204,9 @@ void cpu_idle (void)
idle();
}
+ preempt_enable_no_resched();
schedule();
+ preempt_disable();
}
}
@@ -220,15 +221,12 @@ static void mwait_idle(void)
{
local_irq_enable();
- if (!need_resched()) {
- set_thread_flag(TIF_POLLING_NRFLAG);
- do {
- __monitor((void *)¤t_thread_info()->flags, 0, 0);
- if (need_resched())
- break;
- __mwait(0, 0);
- } while (!need_resched());
- clear_thread_flag(TIF_POLLING_NRFLAG);
+ while (!need_resched()) {
+ __monitor((void *)¤t_thread_info()->flags, 0, 0);
+ smp_mb();
+ if (need_resched())
+ break;
+ __mwait(0, 0);
}
}
diff -puN arch/x86_64/kernel/smpboot.c~sched-rationalise-resched-and-cpu_idle
arch/x86_64/kernel/smpboot.c
--- devel/arch/x86_64/kernel/smpboot.c~sched-rationalise-resched-and-cpu_idle
2005-08-29 23:46:39.000000000 -0700
+++ devel-akpm/arch/x86_64/kernel/smpboot.c 2005-08-29 23:46:39.000000000
-0700
@@ -467,6 +467,7 @@ void __cpuinit start_secondary(void)
* booting is too fragile that we want to limit the
* things done here to the most necessary things.
*/
+ preempt_disable();
cpu_init();
smp_callin();
diff -puN arch/xtensa/kernel/process.c~sched-rationalise-resched-and-cpu_idle
arch/xtensa/kernel/process.c
--- devel/arch/xtensa/kernel/process.c~sched-rationalise-resched-and-cpu_idle
2005-08-29 23:46:39.000000000 -0700
+++ devel-akpm/arch/xtensa/kernel/process.c 2005-08-29 23:46:39.000000000
-0700
@@ -96,8 +96,9 @@ void cpu_idle(void)
while (1) {
while (!need_resched())
platform_idle();
- preempt_enable();
+ preempt_enable_no_resched();
schedule();
+ preempt_disable();
}
}
diff -puN /dev/null Documentation/sched-arch.txt
--- /dev/null 2003-09-15 06:40:47.000000000 -0700
+++ devel-akpm/Documentation/sched-arch.txt 2005-08-29 23:46:39.000000000
-0700
@@ -0,0 +1,89 @@
+ 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)
+
diff -puN drivers/acpi/processor_idle.c~sched-rationalise-resched-and-cpu_idle
drivers/acpi/processor_idle.c
--- devel/drivers/acpi/processor_idle.c~sched-rationalise-resched-and-cpu_idle
2005-08-29 23:46:39.000000000 -0700
+++ devel-akpm/drivers/acpi/processor_idle.c 2005-08-29 23:46:39.000000000
-0700
@@ -166,6 +166,20 @@ acpi_processor_power_activate(struct acp
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 void acpi_processor_idle(void)
@@ -176,7 +190,7 @@ static void acpi_processor_idle(void)
int sleep_ticks = 0;
u32 t1, t2 = 0;
- pr = processors[raw_smp_processor_id()];
+ pr = processors[smp_processor_id()];
if (!pr)
return;
@@ -196,8 +210,13 @@ static void acpi_processor_idle(void)
}
cx = pr->power.state;
- if (!cx)
- goto easy_out;
+ if (!cx) {
+ if (pm_idle_save)
+ pm_idle_save();
+ else
+ acpi_safe_halt();
+ return;
+ }
/*
* Check BM Activity
@@ -277,7 +296,8 @@ static void acpi_processor_idle(void)
if (pm_idle_save)
pm_idle_save();
else
- safe_halt();
+ acpi_safe_halt();
+
/*
* TBD: Can't get time duration while in C1, as resumes
* go to an ISR rather than here. Need to instrument
@@ -413,16 +433,6 @@ static void acpi_processor_idle(void)
*/
if (next_state != pr->power.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)
diff -puN init/main.c~sched-rationalise-resched-and-cpu_idle init/main.c
--- devel/init/main.c~sched-rationalise-resched-and-cpu_idle 2005-08-29
23:46:39.000000000 -0700
+++ devel-akpm/init/main.c 2005-08-29 23:46:39.000000000 -0700
@@ -394,14 +394,16 @@ static void noinline rest_init(void)
kernel_thread(init, NULL, CLONE_FS | CLONE_SIGHAND);
numa_default_policy();
unlock_kernel();
- preempt_enable_no_resched();
/*
* The boot idle thread must execute schedule()
* at least one to get things moving:
*/
+ preempt_enable_no_resched();
schedule();
+ preempt_disable();
+ /* Call into cpu_idle with preempt disabled */
cpu_idle();
}
diff -puN kernel/sched.c~sched-rationalise-resched-and-cpu_idle kernel/sched.c
--- devel/kernel/sched.c~sched-rationalise-resched-and-cpu_idle 2005-08-29
23:46:39.000000000 -0700
+++ devel-akpm/kernel/sched.c 2005-08-29 23:46:39.000000000 -0700
@@ -862,21 +862,28 @@ static void deactivate_task(struct task_
#ifdef CONFIG_SMP
static void resched_task(task_t *p)
{
- int need_resched, nrpolling;
+ int cpu;
assert_spin_locked(&task_rq(p)->lock);
- /* minimise the chance of sending an interrupt to poll_idle() */
- nrpolling = test_tsk_thread_flag(p,TIF_POLLING_NRFLAG);
- need_resched = test_and_set_tsk_thread_flag(p,TIF_NEED_RESCHED);
- nrpolling |= test_tsk_thread_flag(p,TIF_POLLING_NRFLAG);
+ if (unlikely(test_tsk_thread_flag(p, TIF_NEED_RESCHED)))
+ return;
+
+ 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()))
- smp_send_reschedule(task_cpu(p));
+ /* NEED_RESCHED must be visible before we test POLLING_NRFLAG */
+ smp_mb();
+ if (!test_tsk_thread_flag(p, TIF_POLLING_NRFLAG))
+ smp_send_reschedule(cpu);
}
#else
static inline void resched_task(task_t *p)
{
+ assert_spin_locked(&task_rq(p)->lock);
set_tsk_need_resched(p);
}
#endif
_
-
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to [EMAIL PROTECTED]
More majordomo info at http://vger.kernel.org/majordomo-info.html
