static void iseries_dedicated_idle(void)
{
set_thread_flag(TIF_POLLING_NRFLAG);
while (1) {
tick_nohz_stop_sched_tick(1);
if (!need_resched()) {
while (!need_resched()) {
ppc64_runlatch_off();
HMT_low();
if (hvlpevent_is_pending()) {
HMT_medium();
ppc64_runlatch_on();
process_iSeries_events();
}
}
HMT_medium();
}
ppc64_runlatch_on();
tick_nohz_restart_sched_tick();
preempt_enable_no_resched();
schedule();
preempt_disable();
}
}
static int pseries_dedicated_idle(void)
{
long oldval;
struct paca_struct *lpaca = get_paca();
unsigned int cpu = smp_processor_id();
unsigned long start_snooze;
unsigned long *smt_snooze_delay = &__get_cpu_var(smt_snooze_delay);
while (1) {
/*
* Indicate to the HV that we are idle. Now would be
* a good time to find other work to dispatch.
*/
lpaca->lppaca.idle = 1;
oldval = test_and_clear_thread_flag(TIF_NEED_RESCHED);
if (!oldval) {
set_thread_flag(TIF_POLLING_NRFLAG);
start_snooze = __get_tb() +
*smt_snooze_delay * tb_ticks_per_usec;
while (!need_resched() && !cpu_is_offline(cpu)) {
ppc64_runlatch_off();
/*
* Go into low thread priority and possibly
* low power mode.
*/
HMT_low();
HMT_very_low();
if (*smt_snooze_delay != 0 &&
__get_tb() > start_snooze) {
HMT_medium();
dedicated_idle_sleep(cpu);
}
}
HMT_medium();
clear_thread_flag(TIF_POLLING_NRFLAG);
} else {
set_need_resched();
}
lpaca->lppaca.idle = 0;
ppc64_runlatch_on();
schedule();
if (cpu_is_offline(cpu) && system_state == SYSTEM_RUNNING)
cpu_die();
}
}
static void pseries_dedicated_idle_sleep(void)
{
unsigned int cpu = smp_processor_id();
unsigned long start_snooze;
unsigned long *smt_snooze_delay = &__get_cpu_var(smt_snooze_delay);
unsigned long in_purr, out_purr;
/*
* Indicate to the HV that we are idle. Now would be
* a good time to find other work to dispatch.
*/
get_lppaca()->idle = 1;
get_lppaca()->cpuctls_task_attrs = 1;
in_purr = mfspr(SPRN_PURR);
/*
* We come in with interrupts disabled, and need_resched()
* has been checked recently. If we should poll for a little
* while, do so.
*/
if (*smt_snooze_delay) {
start_snooze = get_tb() +
*smt_snooze_delay * tb_ticks_per_usec;
local_irq_enable();
set_thread_flag(TIF_POLLING_NRFLAG);
while (get_tb() < start_snooze) {
if (need_resched() || cpu_is_offline(cpu))
goto out;
ppc64_runlatch_off();
HMT_low();
HMT_very_low();
}
HMT_medium();
clear_thread_flag(TIF_POLLING_NRFLAG);
smp_mb();
local_irq_disable();
if (need_resched() || cpu_is_offline(cpu))
goto out;
}
cede_processor();
out:
HMT_medium();
get_lppaca()->cpuctls_task_attrs = 0;
out_purr = mfspr(SPRN_PURR);
get_lppaca()->wait_state_cycles += out_purr - in_purr;
get_lppaca()->idle = 0;
}
static int default_idle(void)
{
long oldval;
unsigned int cpu = smp_processor_id();
while (1) {
oldval = test_and_clear_thread_flag(TIF_NEED_RESCHED);
if (!oldval) {
set_thread_flag(TIF_POLLING_NRFLAG);
while (!need_resched() && !cpu_is_offline(cpu)) {
barrier();
/*
* Go into low thread priority and possibly
* low power mode.
*/
HMT_low();
HMT_very_low();
}
HMT_medium();
clear_thread_flag(TIF_POLLING_NRFLAG);
} else {
set_need_resched();
}
schedule();
if (cpu_is_offline(cpu) && system_state == SYSTEM_RUNNING)
cpu_die();
}
return 0;
}
static void iseries_shared_idle(void)
{
while (1) {
tick_nohz_stop_sched_tick(1);
while (!need_resched() && !hvlpevent_is_pending()) {
local_irq_disable();
ppc64_runlatch_off();
/* Recheck with irqs off */
if (!need_resched() && !hvlpevent_is_pending())
yield_shared_processor();
HMT_medium();
local_irq_enable();
}
ppc64_runlatch_on();
tick_nohz_restart_sched_tick();
if (hvlpevent_is_pending())
process_iSeries_events();
preempt_enable_no_resched();
schedule();
preempt_disable();
}
}
static int snooze_loop(struct cpuidle_device *dev,
struct cpuidle_driver *drv,
int index)
{
unsigned long in_purr;
int cpu = dev->cpu;
idle_loop_prolog(&in_purr);
local_irq_enable();
set_thread_flag(TIF_POLLING_NRFLAG);
while ((!need_resched()) && cpu_online(cpu)) {
ppc64_runlatch_off();
HMT_low();
HMT_very_low();
}
HMT_medium();
clear_thread_flag(TIF_POLLING_NRFLAG);
smp_mb();
idle_loop_epilog(in_purr);
return index;
}
/*
* The body of the idle task.
*/
void cpu_idle(void)
{
if (ppc_md.idle_loop)
ppc_md.idle_loop(); /* doesn't return */
set_thread_flag(TIF_POLLING_NRFLAG);
while (1) {
tick_nohz_idle_enter();
rcu_idle_enter();
while (!need_resched() && !cpu_should_die()) {
ppc64_runlatch_off();
if (ppc_md.power_save) {
clear_thread_flag(TIF_POLLING_NRFLAG);
/*
* smp_mb is so clearing of TIF_POLLING_NRFLAG
* is ordered w.r.t. need_resched() test.
*/
smp_mb();
local_irq_disable();
/* Don't trace irqs off for idle */
stop_critical_timings();
/* check again after disabling irqs */
if (!need_resched() && !cpu_should_die())
ppc_md.power_save();
start_critical_timings();
/* Some power_save functions return with
* interrupts enabled, some don't.
*/
if (irqs_disabled())
local_irq_enable();
set_thread_flag(TIF_POLLING_NRFLAG);
} else {
/*
* Go into low thread priority and possibly
* low power mode.
*/
HMT_low();
HMT_very_low();
}
}
HMT_medium();
ppc64_runlatch_on();
rcu_idle_exit();
tick_nohz_idle_exit();
if (cpu_should_die()) {
sched_preempt_enable_no_resched();
cpu_die();
}
schedule_preempt_disabled();
}
}
/*
* The body of the idle task.
*/
void cpu_idle(void)
{
if (ppc_md.idle_loop)
ppc_md.idle_loop(); /* doesn't return */
set_thread_flag(TIF_POLLING_NRFLAG);
while (1) {
hrtimer_stop_sched_tick();
while (!need_resched() && !need_resched_delayed() &&
!cpu_should_die()) {
ppc64_runlatch_off();
/*
*
* We have irqs disabled here, so stop latency tracing
* at this point and restart it after we return:
*/
stop_critical_timing();
if (ppc_md.power_save) {
clear_thread_flag(TIF_POLLING_NRFLAG);
/*
* smp_mb is so clearing of TIF_POLLING_NRFLAG
* is ordered w.r.t. need_resched() test.
*/
smp_mb();
local_irq_disable();
/* check again after disabling irqs */
if (!need_resched() && !cpu_should_die())
ppc_md.power_save();
local_irq_enable();
set_thread_flag(TIF_POLLING_NRFLAG);
} else {
/*
* Go into low thread priority and possibly
* low power mode.
*/
HMT_low();
HMT_very_low();
}
touch_critical_timing();
}
HMT_medium();
ppc64_runlatch_on();
if (cpu_should_die())
cpu_die();
hrtimer_restart_sched_tick();
__preempt_enable_no_resched();
schedule();
preempt_disable();
}
}
static int iSeries_idle(void)
{
struct paca_struct *lpaca;
long oldval;
unsigned long CTRL;
/* ensure iSeries run light will be out when idle */
clear_thread_flag(TIF_RUN_LIGHT);
CTRL = mfspr(CTRLF);
CTRL &= ~RUNLATCH;
mtspr(CTRLT, CTRL);
lpaca = get_paca();
while (1) {
if (lpaca->lppaca.xSharedProc) {
if (ItLpQueue_isLpIntPending(lpaca->lpqueue_ptr))
process_iSeries_events();
if (!need_resched())
yield_shared_processor();
} else {
oldval = test_and_clear_thread_flag(TIF_NEED_RESCHED);
if (!oldval) {
set_thread_flag(TIF_POLLING_NRFLAG);
while (!need_resched()) {
HMT_medium();
if (ItLpQueue_isLpIntPending(lpaca->lpqueue_ptr))
process_iSeries_events();
HMT_low();
}
HMT_medium();
clear_thread_flag(TIF_POLLING_NRFLAG);
} else {
set_need_resched();
}
}
schedule();
}
return 0;
}
void __raw_spin_unlock_wait(raw_spinlock_t *lock)
{
while (lock->slock) {
HMT_low();
if (SHARED_PROCESSOR)
__spin_yield(lock);
}
HMT_medium();
}
static int snooze_loop(struct cpuidle_device *dev,
struct cpuidle_driver *drv,
int index)
{
unsigned long in_purr;
ktime_t kt_before;
unsigned long start_snooze;
long snooze = drv->states[0].target_residency;
idle_loop_prolog(&in_purr, &kt_before);
if (snooze) {
start_snooze = get_tb() + snooze * tb_ticks_per_usec;
local_irq_enable();
set_thread_flag(TIF_POLLING_NRFLAG);
while ((snooze < 0) || (get_tb() < start_snooze)) {
if (need_resched() || cpu_is_offline(dev->cpu))
goto out;
ppc64_runlatch_off();
HMT_low();
HMT_very_low();
}
HMT_medium();
clear_thread_flag(TIF_POLLING_NRFLAG);
smp_mb();
local_irq_disable();
}
out:
HMT_medium();
dev->last_residency =
(int)idle_loop_epilog(in_purr, kt_before);
return index;
}
void cpu_idle(void)
{
if (ppc_md.idle_loop)
ppc_md.idle_loop();
set_thread_flag(TIF_POLLING_NRFLAG);
while (1) {
tick_nohz_idle_enter();
rcu_idle_enter();
while (!need_resched() && !cpu_should_die()) {
ppc64_runlatch_off();
if (ppc_md.power_save) {
clear_thread_flag(TIF_POLLING_NRFLAG);
smp_mb();
local_irq_disable();
stop_critical_timings();
if (!need_resched() && !cpu_should_die())
ppc_md.power_save();
start_critical_timings();
if (irqs_disabled())
local_irq_enable();
set_thread_flag(TIF_POLLING_NRFLAG);
} else {
HMT_low();
HMT_very_low();
}
}
HMT_medium();
ppc64_runlatch_on();
rcu_idle_exit();
tick_nohz_idle_exit();
if (cpu_should_die()) {
sched_preempt_enable_no_resched();
cpu_die();
}
schedule_preempt_disabled();
}
}
/*
* The body of the idle task.
*/
void cpu_idle(void)
{
if (ppc_md.idle_loop)
ppc_md.idle_loop(); /* doesn't return */
set_thread_flag(TIF_POLLING_NRFLAG);
while (1) {
tick_nohz_stop_sched_tick();
while (!need_resched() && !cpu_should_die()) {
ppc64_runlatch_off();
if (ppc_md.power_save) {
clear_thread_flag(TIF_POLLING_NRFLAG);
/*
* smp_mb is so clearing of TIF_POLLING_NRFLAG
* is ordered w.r.t. need_resched() test.
*/
smp_mb();
local_irq_disable();
/* check again after disabling irqs */
if (!need_resched() && !cpu_should_die())
ppc_md.power_save();
local_irq_enable();
set_thread_flag(TIF_POLLING_NRFLAG);
} else {
/*
* Go into low thread priority and possibly
* low power mode.
*/
HMT_low();
HMT_very_low();
}
}
HMT_medium();
ppc64_runlatch_on();
tick_nohz_restart_sched_tick();
if (cpu_should_die())
cpu_die();
preempt_enable_no_resched();
schedule();
preempt_disable();
}
}
static void cbe_idle(void)
{
unsigned long ctrl;
/* Why do we do that on every idle ? Couldn't that be done once for
* all or do we lose the state some way ? Also, the pm_control
* register setting, that can't be set once at boot ? We really want
* to move that away in order to implement a simple powersave
*/
cbe_enable_pause_zero();
while (1) {
if (!need_resched()) {
local_irq_disable();
while (!need_resched()) {
/* go into low thread priority */
HMT_low();
/*
* atomically disable thread execution
* and runlatch.
* External and Decrementer exceptions
* are still handled when the thread
* is disabled but now enter in
* cbe_system_reset_exception()
*/
ctrl = mfspr(SPRN_CTRLF);
ctrl &= ~(CTRL_RUNLATCH | CTRL_TE);
mtspr(SPRN_CTRLT, ctrl);
}
/* restore thread prio */
HMT_medium();
local_irq_enable();
}
/*
* turn runlatch on again before scheduling the
* process we just woke up
*/
ppc64_runlatch_on();
preempt_enable_no_resched();
schedule();
preempt_disable();
}
}
static int pseries_shared_idle(void)
{
struct paca_struct *lpaca = get_paca();
unsigned int cpu = smp_processor_id();
while (1) {
/*
* Indicate to the HV that we are idle. Now would be
* a good time to find other work to dispatch.
*/
lpaca->lppaca.idle = 1;
while (!need_resched() && !cpu_is_offline(cpu)) {
local_irq_disable();
ppc64_runlatch_off();
/*
* Yield the processor to the hypervisor. We return if
* an external interrupt occurs (which are driven prior
* to returning here) or if a prod occurs from another
* processor. When returning here, external interrupts
* are enabled.
*
* Check need_resched() again with interrupts disabled
* to avoid a race.
*/
if (!need_resched())
cede_processor();
else
local_irq_enable();
HMT_medium();
}
lpaca->lppaca.idle = 0;
ppc64_runlatch_on();
schedule();
if (cpu_is_offline(cpu) && system_state == SYSTEM_RUNNING)
cpu_die();
}
return 0;
}
static int dedicated_cede_loop(struct cpuidle_device *dev,
struct cpuidle_driver *drv,
int index)
{
unsigned long in_purr;
idle_loop_prolog(&in_purr);
get_lppaca()->donate_dedicated_cpu = 1;
HMT_medium();
check_and_cede_processor();
get_lppaca()->donate_dedicated_cpu = 0;
idle_loop_epilog(in_purr);
return index;
}
static int dedicated_cede_loop(struct cpuidle_device *dev,
struct cpuidle_driver *drv,
int index)
{
unsigned long in_purr;
ktime_t kt_before;
idle_loop_prolog(&in_purr, &kt_before);
get_lppaca()->donate_dedicated_cpu = 1;
ppc64_runlatch_off();
HMT_medium();
check_and_cede_processor();
get_lppaca()->donate_dedicated_cpu = 0;
dev->last_residency =
(int)idle_loop_epilog(in_purr, kt_before);
return index;
}
static int snooze_loop(struct cpuidle_device *dev,
struct cpuidle_driver *drv,
int index)
{
local_irq_enable();
set_thread_flag(TIF_POLLING_NRFLAG);
ppc64_runlatch_off();
while (!need_resched()) {
HMT_low();
HMT_very_low();
}
HMT_medium();
ppc64_runlatch_on();
clear_thread_flag(TIF_POLLING_NRFLAG);
smp_mb();
return index;
}
static void cbe_idle(void)
{
unsigned long ctrl;
cbe_enable_pause_zero();
while (1) {
if (!need_resched()) {
local_irq_disable();
while (!need_resched()) {
/* go into low thread priority */
HMT_low();
/*
* atomically disable thread execution
* and runlatch.
* External and Decrementer exceptions
* are still handled when the thread
* is disabled but now enter in
* cbe_system_reset_exception()
*/
ctrl = mfspr(SPRN_CTRLF);
ctrl &= ~(CTRL_RUNLATCH | CTRL_TE);
mtspr(SPRN_CTRLT, ctrl);
}
/* restore thread prio */
HMT_medium();
local_irq_enable();
}
/*
* turn runlatch on again before scheduling the
* process we just woke up
*/
ppc64_runlatch_on();
preempt_enable_no_resched();
schedule();
preempt_disable();
}
}
/*
* pnv_cpu_offline: A function that puts the CPU into the deepest
* available platform idle state on a CPU-Offline.
* interrupts hard disabled and no lazy irq pending.
*/
unsigned long pnv_cpu_offline(unsigned int cpu)
{
unsigned long srr1;
u32 idle_states = pnv_get_supported_cpuidle_states();
__ppc64_runlatch_off();
if (cpu_has_feature(CPU_FTR_ARCH_300) && deepest_stop_found) {
unsigned long psscr;
psscr = mfspr(SPRN_PSSCR);
psscr = (psscr & ~pnv_deepest_stop_psscr_mask) |
pnv_deepest_stop_psscr_val;
srr1 = power9_idle_stop(psscr);
} else if (idle_states & OPAL_PM_WINKLE_ENABLED) {
srr1 = power7_idle_insn(PNV_THREAD_WINKLE);
} else if ((idle_states & OPAL_PM_SLEEP_ENABLED) ||
(idle_states & OPAL_PM_SLEEP_ENABLED_ER1)) {
srr1 = power7_idle_insn(PNV_THREAD_SLEEP);
} else if (idle_states & OPAL_PM_NAP_ENABLED) {
srr1 = power7_idle_insn(PNV_THREAD_NAP);
} else {
/* This is the fallback method. We emulate snooze */
while (!generic_check_cpu_restart(cpu)) {
HMT_low();
HMT_very_low();
}
srr1 = 0;
HMT_medium();
}
__ppc64_runlatch_on();
return srr1;
}
static int snooze_loop(struct cpuidle_device *dev,
struct cpuidle_driver *drv,
int index)
{
u64 snooze_exit_time;
local_irq_enable();
set_thread_flag(TIF_POLLING_NRFLAG);
snooze_exit_time = get_tb() + snooze_timeout;
ppc64_runlatch_off();
while (!need_resched()) {
HMT_low();
HMT_very_low();
if (snooze_timeout_en && get_tb() > snooze_exit_time)
break;
}
HMT_medium();
ppc64_runlatch_on();
clear_thread_flag(TIF_POLLING_NRFLAG);
smp_mb();
return index;
}
/*
* pnv_cpu_offline: A function that puts the CPU into the deepest
* available platform idle state on a CPU-Offline.
* interrupts hard disabled and no lazy irq pending.
*/
unsigned long pnv_cpu_offline(unsigned int cpu)
{
unsigned long srr1;
u32 idle_states = pnv_get_supported_cpuidle_states();
u64 lpcr_val;
/*
* We don't want to take decrementer interrupts while we are
* offline, so clear LPCR:PECE1. We keep PECE2 (and
* LPCR_PECE_HVEE on P9) enabled as to let IPIs in.
*
* If the CPU gets woken up by a special wakeup, ensure that
* the SLW engine sets LPCR with decrementer bit cleared, else
* the CPU will come back to the kernel due to a spurious
* wakeup.
*/
lpcr_val = mfspr(SPRN_LPCR) & ~(u64)LPCR_PECE1;
pnv_program_cpu_hotplug_lpcr(cpu, lpcr_val);
__ppc64_runlatch_off();
if (cpu_has_feature(CPU_FTR_ARCH_300) && deepest_stop_found) {
unsigned long psscr;
psscr = mfspr(SPRN_PSSCR);
psscr = (psscr & ~pnv_deepest_stop_psscr_mask) |
pnv_deepest_stop_psscr_val;
srr1 = power9_offline_stop(psscr);
} else if ((idle_states & OPAL_PM_WINKLE_ENABLED) &&
(idle_states & OPAL_PM_LOSE_FULL_CONTEXT)) {
srr1 = power7_idle_insn(PNV_THREAD_WINKLE);
} else if ((idle_states & OPAL_PM_SLEEP_ENABLED) ||
(idle_states & OPAL_PM_SLEEP_ENABLED_ER1)) {
srr1 = power7_idle_insn(PNV_THREAD_SLEEP);
} else if (idle_states & OPAL_PM_NAP_ENABLED) {
srr1 = power7_idle_insn(PNV_THREAD_NAP);
} else {
/* This is the fallback method. We emulate snooze */
while (!generic_check_cpu_restart(cpu)) {
HMT_low();
HMT_very_low();
}
srr1 = 0;
HMT_medium();
}
__ppc64_runlatch_on();
/*
* Re-enable decrementer interrupts in LPCR.
*
* Further, we want stop states to be woken up by decrementer
* for non-hotplug cases. So program the LPCR via stop api as
* well.
*/
lpcr_val = mfspr(SPRN_LPCR) | (u64)LPCR_PECE1;
pnv_program_cpu_hotplug_lpcr(cpu, lpcr_val);
return srr1;
}
/*
* This function sends a 'generic call function' IPI to all other CPUs
* in the system.
*
* [SUMMARY] Run a function on all other CPUs.
* <func> The function to run. This must be fast and non-blocking.
* <info> An arbitrary pointer to pass to the function.
* <nonatomic> currently unused.
* <wait> If true, wait (atomically) until function has completed on other CPUs.
* [RETURNS] 0 on success, else a negative status code. Does not return until
* remote CPUs are nearly ready to execute <<func>> or are or have executed.
*
* You must not call this function with disabled interrupts or from a
* hardware interrupt handler or from a bottom half handler.
*/
int smp_call_function (void (*func) (void *info), void *info, int nonatomic,
int wait)
{
struct call_data_struct data;
int ret = -1, cpus = smp_num_cpus-1;
int timeout;
if (!cpus)
return 0;
data.func = func;
data.info = info;
atomic_set(&data.started, 0);
data.wait = wait;
if (wait)
atomic_set(&data.finished, 0);
spin_lock_bh(&call_lock);
call_data = &data;
/* Send a message to all other CPUs and wait for them to respond */
smp_message_pass(MSG_ALL_BUT_SELF, PPC_MSG_CALL_FUNCTION, 0, 0);
/* Wait for response */
timeout = 8000000;
while (atomic_read(&data.started) != cpus) {
HMT_low();
if (--timeout == 0) {
printk("smp_call_function on cpu %d: other cpus not responding (%d)\n",
smp_processor_id(), atomic_read(&data.started));
#ifdef CONFIG_XMON
xmon(0);
#endif
#ifdef CONFIG_KDB
kdb(KDB_REASON_CALL,0, (kdb_eframe_t) 0);
#endif
#ifdef CONFIG_PPC_ISERIES
HvCall_terminateMachineSrc();
#endif
goto out;
}
barrier();
udelay(1);
}
if (wait) {
timeout = 1000000;
while (atomic_read(&data.finished) != cpus) {
HMT_low();
if (--timeout == 0) {
printk("smp_call_function on cpu %d: other cpus not finishing (%d/%d)\n",
smp_processor_id(), atomic_read(&data.finished), atomic_read(&data.started));
#ifdef CONFIG_PPC_ISERIES
HvCall_terminateMachineSrc();
#endif
goto out;
}
barrier();
udelay(1);
}
}
ret = 0;
out:
call_data = NULL;
HMT_medium();
spin_unlock_bh(&call_lock);
return ret;
}
int dedicated_idle(void)
{
long oldval;
struct paca_struct *lpaca = get_paca(), *ppaca;
unsigned long start_snooze;
unsigned long *smt_snooze_delay = &__get_cpu_var(smt_snooze_delay);
unsigned int cpu = smp_processor_id();
ppaca = &paca[cpu ^ 1];
while (1) {
/*
* Indicate to the HV that we are idle. Now would be
* a good time to find other work to dispatch.
*/
lpaca->lppaca.xIdle = 1;
oldval = test_and_clear_thread_flag(TIF_NEED_RESCHED);
if (!oldval) {
set_thread_flag(TIF_POLLING_NRFLAG);
start_snooze = __get_tb() +
*smt_snooze_delay * tb_ticks_per_usec;
while (!need_resched() && !cpu_is_offline(cpu)) {
/*
* Go into low thread priority and possibly
* low power mode.
*/
HMT_low();
HMT_very_low();
if (*smt_snooze_delay == 0 ||
__get_tb() < start_snooze)
continue;
HMT_medium();
if (!(ppaca->lppaca.xIdle)) {
local_irq_disable();
/*
* We are about to sleep the thread
* and so wont be polling any
* more.
*/
clear_thread_flag(TIF_POLLING_NRFLAG);
/*
* SMT dynamic mode. Cede will result
* in this thread going dormant, if the
* partner thread is still doing work.
* Thread wakes up if partner goes idle,
* an interrupt is presented, or a prod
* occurs. Returning from the cede
* enables external interrupts.
*/
if (!need_resched())
cede_processor();
else
local_irq_enable();
} else {
/*
* Give the HV an opportunity at the
* processor, since we are not doing
* any work.
*/
poll_pending();
}
}
clear_thread_flag(TIF_POLLING_NRFLAG);
} else {
set_need_resched();
}
HMT_medium();
lpaca->lppaca.xIdle = 0;
schedule();
if (cpu_is_offline(cpu) && system_state == SYSTEM_RUNNING)
cpu_die();
}
return 0;
}
/*
* This function sends a 'generic call function' IPI to all other CPUs
* in the system.
*
* [SUMMARY] Run a function on all other CPUs.
* <func> The function to run. This must be fast and non-blocking.
* <info> An arbitrary pointer to pass to the function.
* <nonatomic> currently unused.
* <wait> If true, wait (atomically) until function has completed on other CPUs.
* [RETURNS] 0 on success, else a negative status code. Does not return until
* remote CPUs are nearly ready to execute <<func>> or are or have executed.
*
* You must not call this function with disabled interrupts or from a
* hardware interrupt handler or from a bottom half handler.
*/
int smp_call_function (void (*func) (void *info), void *info, int nonatomic,
int wait)
{
struct call_data_struct data;
int ret = -1, cpus;
u64 timeout;
/* Can deadlock when called with interrupts disabled */
WARN_ON(irqs_disabled());
data.func = func;
data.info = info;
atomic_set(&data.started, 0);
data.wait = wait;
if (wait)
atomic_set(&data.finished, 0);
spin_lock(&call_lock);
/* Must grab online cpu count with preempt disabled, otherwise
* it can change. */
cpus = num_online_cpus() - 1;
if (!cpus) {
ret = 0;
goto out;
}
call_data = &data;
smp_wmb();
/* Send a message to all other CPUs and wait for them to respond */
smp_ops->message_pass(MSG_ALL_BUT_SELF, PPC_MSG_CALL_FUNCTION);
timeout = get_tb() + (u64) SMP_CALL_TIMEOUT * tb_ticks_per_sec;
/* Wait for response */
while (atomic_read(&data.started) != cpus) {
HMT_low();
if (get_tb() >= timeout) {
printk("smp_call_function on cpu %d: other cpus not "
"responding (%d)\n", smp_processor_id(),
atomic_read(&data.started));
debugger(NULL);
goto out;
}
}
if (wait) {
while (atomic_read(&data.finished) != cpus) {
HMT_low();
if (get_tb() >= timeout) {
printk("smp_call_function on cpu %d: other "
"cpus not finishing (%d/%d)\n",
smp_processor_id(),
atomic_read(&data.finished),
atomic_read(&data.started));
debugger(NULL);
goto out;
}
}
}
ret = 0;
out:
call_data = NULL;
HMT_medium();
spin_unlock(&call_lock);
return ret;
}
/*
* These functions send a 'generic call function' IPI to other online
* CPUS in the system.
*
* [SUMMARY] Run a function on other CPUs.
* <func> The function to run. This must be fast and non-blocking.
* <info> An arbitrary pointer to pass to the function.
* <nonatomic> currently unused.
* <wait> If true, wait (atomically) until function has completed on other CPUs.
* [RETURNS] 0 on success, else a negative status code. Does not return until
* remote CPUs are nearly ready to execute <<func>> or are or have executed.
* <map> is a cpu map of the cpus to send IPI to.
*
* You must not call this function with disabled interrupts or from a
* hardware interrupt handler or from a bottom half handler.
*/
static int __smp_call_function_map(void (*func) (void *info), void *info,
int nonatomic, int wait, cpumask_t map)
{
struct call_data_struct data;
int ret = -1, num_cpus;
int cpu;
u64 timeout;
if (unlikely(smp_ops == NULL))
return ret;
data.func = func;
data.info = info;
atomic_set(&data.started, 0);
data.wait = wait;
if (wait)
atomic_set(&data.finished, 0);
/* remove 'self' from the map */
if (cpu_isset(smp_processor_id(), map))
cpu_clear(smp_processor_id(), map);
/* sanity check the map, remove any non-online processors. */
cpus_and(map, map, cpu_online_map);
num_cpus = cpus_weight(map);
if (!num_cpus)
goto done;
call_data = &data;
smp_wmb();
/* Send a message to all CPUs in the map */
for_each_cpu_mask(cpu, map)
smp_ops->message_pass(cpu, PPC_MSG_CALL_FUNCTION);
timeout = get_tb() + (u64) SMP_CALL_TIMEOUT * tb_ticks_per_sec;
/* Wait for indication that they have received the message */
while (atomic_read(&data.started) != num_cpus) {
HMT_low();
if (get_tb() >= timeout) {
printk("smp_call_function on cpu %d: other cpus not "
"responding (%d)\n", smp_processor_id(),
atomic_read(&data.started));
if (!ipi_fail_ok)
debugger(NULL);
goto out;
}
}
/* optionally wait for the CPUs to complete */
if (wait) {
while (atomic_read(&data.finished) != num_cpus) {
HMT_low();
if (get_tb() >= timeout) {
printk("smp_call_function on cpu %d: other "
"cpus not finishing (%d/%d)\n",
smp_processor_id(),
atomic_read(&data.finished),
atomic_read(&data.started));
debugger(NULL);
goto out;
}
}
}
done:
ret = 0;
out:
call_data = NULL;
HMT_medium();
return ret;
}
