/*
* the idle thread
* - there's no useful work to be done, so just try to conserve power and have
* a low exit latency (ie sit in a loop waiting for somebody to say that
* they'd like to reschedule)
*/
void cpu_idle(void)
{
int cpu = smp_processor_id();
/* endless idle loop with no priority at all */
for (;;) {
while (!need_resched()) {
void (*idle)(void);
smp_rmb();
idle = pm_idle;
if (!idle)
idle = default_idle;
irq_stat[cpu].idle_timestamp = jiffies;
idle();
}
preempt_enable_no_resched();
schedule();
preempt_disable();
}
}
/*
* The idle thread. We try to conserve power, while trying to keep
* overall latency low. The architecture specific idle is passed
* a value to indicate the level of "idleness" of the system.
*/
void cpu_idle(void)
{
/* endless idle loop with no priority at all */
while (1) {
void (*idle)(void) = pm_idle;
#ifdef CONFIG_HOTPLUG_CPU
if (cpu_is_offline(smp_processor_id()))
cpu_die();
#endif
if (!idle)
idle = default_idle;
tick_nohz_idle_enter();
rcu_idle_enter();
while (!need_resched())
idle();
rcu_idle_exit();
tick_nohz_idle_exit();
preempt_enable_no_resched();
schedule();
preempt_disable();
}
}
int parport_poll_peripheral(struct parport *port,
unsigned char mask,
unsigned char result,
int usec)
{
/* Zero return code is success, >0 is timeout. */
int count = usec / 5 + 2;
int i;
unsigned char status;
for (i = 0; i < count; i++) {
status = parport_read_status (port);
if ((status & mask) == result)
return 0;
if (signal_pending (current))
return -EINTR;
if (need_resched())
break;
if (i >= 2)
udelay (5);
}
return 1;
}
static int snooze_loop(struct cpuidle_device *dev,
struct cpuidle_driver *drv,
int index)
{
unsigned long in_purr;
idle_loop_prolog(&in_purr);
local_irq_enable();
set_thread_flag(TIF_POLLING_NRFLAG);
while (!need_resched()) {
HMT_low();
HMT_very_low();
}
HMT_medium();
clear_thread_flag(TIF_POLLING_NRFLAG);
smp_mb();
idle_loop_epilog(in_purr);
return index;
}
static int journal_clean_one_cp_list(struct journal_head *jh, int *released)
{
struct journal_head *last_jh;
struct journal_head *next_jh = jh;
int ret, freed = 0;
*released = 0;
if (!jh)
return 0;
last_jh = jh->b_cpprev;
do {
jh = next_jh;
next_jh = jh->b_cpnext;
/* Use trylock because of the ranking */
if (jbd_trylock_bh_state(jh2bh(jh))) {
ret = __try_to_free_cp_buf(jh);
if (ret) {
freed++;
if (ret == 2) {
*released = 1;
return freed;
}
}
}
/*
* This function only frees up some memory
* if possible so we dont have an obligation
* to finish processing. Bail out if preemption
* requested:
*/
if (need_resched())
return freed;
} while (jh != last_jh);
return freed;
}
static unsigned long msync_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
unsigned long addr, unsigned long end)
{
pte_t *pte;
spinlock_t *ptl;
int progress = 0;
unsigned long ret = 0;
again:
pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
do {
struct page *page;
if (progress >= 64) {
progress = 0;
if (need_resched() || need_lockbreak(ptl))
break;
}
progress++;
if (!pte_present(*pte))
continue;
if (!pte_maybe_dirty(*pte))
continue;
page = vm_normal_page(vma, addr, *pte);
if (!page)
continue;
if (ptep_clear_flush_dirty(vma, addr, pte) ||
page_test_and_clear_dirty(page))
ret += set_page_dirty(page);
progress += 3;
} while (pte++, addr += PAGE_SIZE, addr != end);
pte_unmap_unlock(pte - 1, ptl);
cond_resched();
if (addr != end)
goto again;
return ret;
}
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;
}
void sc8825_idle(void)
{
int this_cpu = smp_processor_id();
int val;
if (!need_resched()) {
hw_local_irq_disable();
if (!arch_local_irq_pending()) {
val = os_ctx->idle(os_ctx);
if (0 == val) {
#ifdef CONFIG_CACHE_L2X0
/*l2cache power control, standby mode enable*/
/*L2X0_POWER_CTRL
__raw_writel(1, SPRD_L2_BASE+0xF80);
l2x0_suspend();
*/
#endif
#if defined(CONFIG_LOCAL_TIMERS)
clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &this_cpu);
#endif
cpu_do_idle();
#if defined(CONFIG_LOCAL_TIMERS)
clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &this_cpu);
#endif
#ifdef CONFIG_CACHE_L2X0
/*
l2x0_resume(1);
*/
#endif
}
}
hw_local_irq_enable();
}
local_irq_enable();
return;
}
/*
* The idle thread. There's no useful work to be done, so just try to conserve
* power and have a low exit latency (ie sit in a loop waiting for somebody to
* say that they'd like to reschedule)
*/
void cpu_idle(void)
{
unsigned int cpu = smp_processor_id();
set_thread_flag(TIF_POLLING_NRFLAG);
/* endless idle loop with no priority at all */
while (1) {
tick_nohz_idle_enter();
rcu_idle_enter();
while (!need_resched()) {
check_pgt_cache();
rmb();
if (cpu_is_offline(cpu))
play_dead();
local_irq_disable();
/* Don't trace irqs off for idle */
stop_critical_timings();
if (cpuidle_idle_call())
sh_idle();
/*
* Sanity check to ensure that sh_idle() returns
* with IRQs enabled
*/
WARN_ON(irqs_disabled());
start_critical_timings();
}
rcu_idle_exit();
tick_nohz_idle_exit();
schedule_preempt_disabled();
}
}
void cpu_idle(void)
{
set_thread_flag(TIF_POLLING_NRFLAG);
/* endless idle loop with no priority at all */
while (1) {
void (*idle)(void) = pm_idle;
if (!idle)
idle = default_idle;
tick_nohz_idle_enter();
rcu_idle_enter();
while (!need_resched())
idle();
rcu_idle_exit();
tick_nohz_idle_exit();
preempt_enable_no_resched();
schedule();
preempt_disable();
check_pgt_cache();
}
}
/*
* the idle thread
* - there's no useful work to be done, so just try to conserve power and have
* a low exit latency (ie sit in a loop waiting for somebody to say that
* they'd like to reschedule)
*/
void cpu_idle(void)
{
/* endless idle loop with no priority at all */
for (;;) {
while (!need_resched()) {
void (*idle)(void);
smp_rmb();
idle = pm_idle;
if (!idle) {
#if defined(CONFIG_SMP) && !defined(CONFIG_HOTPLUG_CPU)
idle = poll_idle;
#else /* CONFIG_SMP && !CONFIG_HOTPLUG_CPU */
idle = default_idle;
#endif /* CONFIG_SMP && !CONFIG_HOTPLUG_CPU */
}
idle();
}
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;
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;
}
/*
* Let's power down on idle, but only if we are really
* idle, because once we start down the path of
* going idle we continue to do idle even if we get
* a clock tick interrupt . .
*/
void omap_pm_idle(void)
{
unsigned int mask32 = 0;
/*
* If the DSP is being used let's just idle the CPU, the overhead
* to wake up from Big Sleep is big, milliseconds versus micro
* seconds for wait for interrupt.
*/
local_irq_disable();
local_fiq_disable();
if (need_resched()) {
local_fiq_enable();
local_irq_enable();
return;
}
mask32 = omap_readl(ARM_SYSST);
/*
* Prevent the ULPD from entering low power state by setting
* POWER_CTRL_REG:4 = 0
*/
omap_writew(omap_readw(ULPD_POWER_CTRL) &
~ULPD_DEEP_SLEEP_TRANSITION_EN, ULPD_POWER_CTRL);
/*
* Since an interrupt may set up a timer, we don't want to
* reprogram the hardware timer with interrupts enabled.
* Re-enable interrupts only after returning from idle.
*/
timer_dyn_reprogram();
if ((mask32 & DSP_IDLE) == 0) {
__asm__ volatile ("mcr p15, 0, r0, c7, c0, 4");
} else
void rk28_panic_reset(void)
{
int at_debug = rk28_system_crash;
printk("%s::crash=%d\n" , __func__ , rk28_system_crash);
if( __system_crashed() )
return ;
rk28_system_crash |= (1<<16); /* 20091206,HSL@RK,must set flag ! */
if( at_debug >= RKDBG_LOADER ) {
kld_reboot(1,1);
} else if( at_debug >= RKDBG_CUSTOMER0) {
//rk28_system_crash |= RKDBG_CUSTOMER1;
__rkusb_bk_save( 0 );
local_irq_enable(); /* for get log by usb */
rk28_usb();
while( 1 ) {
if( need_resched() && at_debug >= RKDBG_CUSTOMER1 ) {
//debug_print("schedule after panic\n");
schedule();
}
}
}
//rk28_write_file("misc");
kld_reboot(1,0);
}
void cpu_idle(void)
{
for (;;) {
rcu_idle_enter();
while (!need_resched()) {
void (*idle)(void);
smp_rmb();
idle = pm_idle;
if (!idle) {
#if defined(CONFIG_SMP) && !defined(CONFIG_HOTPLUG_CPU)
idle = poll_idle;
#else
idle = default_idle;
#endif
}
idle();
}
rcu_idle_exit();
schedule_preempt_disabled();
}
}
/*
* The idle thread. There's no useful work to be done, so just try to conserve
* power and have a low exit latency (ie sit in a loop waiting for somebody to
* say that they'd like to reschedule)
*/
void __noreturn cpu_idle(void)
{
int cpu;
/* CPU is going idle. */
cpu = smp_processor_id();
/* endless idle loop with no priority at all */
while (1) {
tick_nohz_idle_enter();
rcu_idle_enter();
while (!need_resched() && cpu_online(cpu)) {
#ifdef CONFIG_MIPS_MT_SMTC
extern void smtc_idle_loop_hook(void);
smtc_idle_loop_hook();
#endif
if (cpu_wait) {
/* Don't trace irqs off for idle */
stop_critical_timings();
(*cpu_wait)();
start_critical_timings();
}
}
#ifdef CONFIG_HOTPLUG_CPU
if (!cpu_online(cpu) && !cpu_isset(cpu, cpu_callin_map) &&
(system_state == SYSTEM_RUNNING ||
system_state == SYSTEM_BOOTING))
play_dead();
#endif
rcu_idle_exit();
tick_nohz_idle_exit();
schedule_preempt_disabled();
}
}
/*
* Invoke the RCU callbacks on the specified rcu_ctrlkblk structure
* whose grace period has elapsed.
*/
static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp)
{
const char *rn = NULL;
struct rcu_head *next, *list;
unsigned long flags;
RCU_TRACE(int cb_count = 0);
/* Move the ready-to-invoke callbacks to a local list. */
local_irq_save(flags);
RCU_TRACE(trace_rcu_batch_start(rcp->name, 0, rcp->qlen, -1));
list = rcp->rcucblist;
rcp->rcucblist = *rcp->donetail;
*rcp->donetail = NULL;
if (rcp->curtail == rcp->donetail)
rcp->curtail = &rcp->rcucblist;
rcp->donetail = &rcp->rcucblist;
local_irq_restore(flags);
/* Invoke the callbacks on the local list. */
RCU_TRACE(rn = rcp->name);
while (list) {
next = list->next;
prefetch(next);
debug_rcu_head_unqueue(list);
local_bh_disable();
__rcu_reclaim(rn, list);
local_bh_enable();
list = next;
RCU_TRACE(cb_count++);
}
RCU_TRACE(rcu_trace_sub_qlen(rcp, cb_count));
RCU_TRACE(trace_rcu_batch_end(rcp->name,
cb_count, 0, need_resched(),
is_idle_task(current),
false));
}
/*
* Let's power down on idle, but only if we are really
* idle, because once we start down the path of
* going idle we continue to do idle even if we get
* a clock tick interrupt . .
*/
void omap_pm_idle(void)
{
extern __u32 arm_idlect1_mask;
__u32 use_idlect1 = arm_idlect1_mask;
int do_sleep = 0;
local_irq_disable();
local_fiq_disable();
if (need_resched()) {
local_fiq_enable();
local_irq_enable();
return;
}
/*
* Since an interrupt may set up a timer, we don't want to
* reprogram the hardware timer with interrupts enabled.
* Re-enable interrupts only after returning from idle.
*/
timer_dyn_reprogram();
#ifdef CONFIG_OMAP_MPU_TIMER
#warning Enable 32kHz OS timer in order to allow sleep states in idle
use_idlect1 = use_idlect1 & ~(1 << 9);
#else
while (enable_dyn_sleep) {
#ifdef CONFIG_CBUS_TAHVO_USB
extern int vbus_active;
/* Clock requirements? */
if (vbus_active)
break;
#endif
do_sleep = 1;
break;
}
#endif
#ifdef CONFIG_OMAP_DM_TIMER
use_idlect1 = omap_dm_timer_modify_idlect_mask(use_idlect1);
#endif
if (omap_dma_running())
use_idlect1 &= ~(1 << 6);
/* We should be able to remove the do_sleep variable and multiple
* tests above as soon as drivers, timer and DMA code have been fixed.
* Even the sleep block count should become obsolete. */
if ((use_idlect1 != ~0) || !do_sleep) {
__u32 saved_idlect1 = omap_readl(ARM_IDLECT1);
if (cpu_is_omap15xx())
use_idlect1 &= OMAP1510_BIG_SLEEP_REQUEST;
else
use_idlect1 &= OMAP1610_IDLECT1_SLEEP_VAL;
omap_writel(use_idlect1, ARM_IDLECT1);
__asm__ volatile ("mcr p15, 0, r0, c7, c0, 4");
omap_writel(saved_idlect1, ARM_IDLECT1);
local_fiq_enable();
local_irq_enable();
return;
}
/* avoid HT sibilings if possible */
if (cpumask_empty(tmp))
cpumask_andnot(tmp, cpu_online_mask, pad_busy_cpus);
if (cpumask_empty(tmp)) {
mutex_unlock(&round_robin_lock);
return;
}
for_each_cpu(cpu, tmp) {
if (cpu_weight[cpu] < min_weight) {
min_weight = cpu_weight[cpu];
preferred_cpu = cpu;
}
}
if (tsk_in_cpu[tsk_index] != -1)
cpumask_clear_cpu(tsk_in_cpu[tsk_index], pad_busy_cpus);
tsk_in_cpu[tsk_index] = preferred_cpu;
cpumask_set_cpu(preferred_cpu, pad_busy_cpus);
cpu_weight[preferred_cpu]++;
mutex_unlock(&round_robin_lock);
set_cpus_allowed_ptr(current, cpumask_of(preferred_cpu));
}
static void exit_round_robin(unsigned int tsk_index)
{
struct cpumask *pad_busy_cpus = to_cpumask(pad_busy_cpus_bits);
cpumask_clear_cpu(tsk_in_cpu[tsk_index], pad_busy_cpus);
tsk_in_cpu[tsk_index] = -1;
}
static unsigned int idle_pct = 5; /* percentage */
static unsigned int round_robin_time = 1; /* second */
static int power_saving_thread(void *data)
{
struct sched_param param = {.sched_priority = 1};
int do_sleep;
unsigned int tsk_index = (unsigned long)data;
u64 last_jiffies = 0;
sched_setscheduler(current, SCHED_RR, ¶m);
set_freezable();
while (!kthread_should_stop()) {
int cpu;
u64 expire_time;
try_to_freeze();
/* round robin to cpus */
if (last_jiffies + round_robin_time * HZ < jiffies) {
last_jiffies = jiffies;
round_robin_cpu(tsk_index);
}
do_sleep = 0;
expire_time = jiffies + HZ * (100 - idle_pct) / 100;
while (!need_resched()) {
if (tsc_detected_unstable && !tsc_marked_unstable) {
/* TSC could halt in idle, so notify users */
mark_tsc_unstable("TSC halts in idle");
tsc_marked_unstable = 1;
}
if (lapic_detected_unstable && !lapic_marked_unstable) {
int i;
/* LAPIC could halt in idle, so notify users */
for_each_online_cpu(i)
clockevents_notify(
CLOCK_EVT_NOTIFY_BROADCAST_ON,
&i);
lapic_marked_unstable = 1;
}
local_irq_disable();
cpu = smp_processor_id();
if (lapic_marked_unstable)
clockevents_notify(
CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &cpu);
stop_critical_timings();
__monitor((void *)¤t_thread_info()->flags, 0, 0);
smp_mb();
if (!need_resched())
__mwait(power_saving_mwait_eax, 1);
start_critical_timings();
if (lapic_marked_unstable)
clockevents_notify(
CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &cpu);
local_irq_enable();
if (jiffies > expire_time) {
do_sleep = 1;
break;
}
}
/*
* current sched_rt has threshold for rt task running time.
* When a rt task uses 95% CPU time, the rt thread will be
* scheduled out for 5% CPU time to not starve other tasks. But
* the mechanism only works when all CPUs have RT task running,
* as if one CPU hasn't RT task, RT task from other CPUs will
* borrow CPU time from this CPU and cause RT task use > 95%
* CPU time. To make 'avoid starvation' work, takes a nap here.
*/
if (do_sleep)
schedule_timeout_killable(HZ * idle_pct / 100);
}
exit_round_robin(tsk_index);
return 0;
}
static struct task_struct *ps_tsks[NR_CPUS];
static unsigned int ps_tsk_num;
static int create_power_saving_task(void)
{
int rc = -ENOMEM;
ps_tsks[ps_tsk_num] = kthread_run(power_saving_thread,
(void *)(unsigned long)ps_tsk_num,
"acpi_pad/%d", ps_tsk_num);
rc = PTR_RET(ps_tsks[ps_tsk_num]);
if (!rc)
ps_tsk_num++;
else
ps_tsks[ps_tsk_num] = NULL;
return rc;
}
/**
* cpuidle_idle_call - the main idle function
*
* NOTE: no locks or semaphores should be used here
*/
static void cpuidle_idle_call(void)
{
struct cpuidle_device *dev = __this_cpu_read(cpuidle_devices);
struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
int next_state, entered_state;
bool broadcast;
/*
* Check if the idle task must be rescheduled. If it is the
* case, exit the function after re-enabling the local irq.
*/
if (need_resched()) {
local_irq_enable();
return;
}
/*
* During the idle period, stop measuring the disabled irqs
* critical sections latencies
*/
stop_critical_timings();
/*
* Tell the RCU framework we are entering an idle section,
* so no more rcu read side critical sections and one more
* step to the grace period
*/
rcu_idle_enter();
/*
* Ask the cpuidle framework to choose a convenient idle state.
* Fall back to the default arch idle method on errors.
*/
next_state = cpuidle_select(drv, dev);
if (next_state < 0) {
use_default:
/*
* We can't use the cpuidle framework, let's use the default
* idle routine.
*/
if (current_clr_polling_and_test())
local_irq_enable();
else
arch_cpu_idle();
goto exit_idle;
}
/*
* The idle task must be scheduled, it is pointless to
* go to idle, just update no idle residency and get
* out of this function
*/
if (current_clr_polling_and_test()) {
dev->last_residency = 0;
entered_state = next_state;
local_irq_enable();
goto exit_idle;
}
broadcast = !!(drv->states[next_state].flags & CPUIDLE_FLAG_TIMER_STOP);
/*
* Tell the time framework to switch to a broadcast timer
* because our local timer will be shutdown. If a local timer
* is used from another cpu as a broadcast timer, this call may
* fail if it is not available
*/
if (broadcast &&
clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &dev->cpu))
goto use_default;
trace_cpu_idle_rcuidle(next_state, dev->cpu);
/*
* Enter the idle state previously returned by the governor decision.
* This function will block until an interrupt occurs and will take
* care of re-enabling the local interrupts
*/
entered_state = cpuidle_enter(drv, dev, next_state);
trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, dev->cpu);
if (broadcast)
clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &dev->cpu);
/*
* Give the governor an opportunity to reflect on the outcome
*/
cpuidle_reflect(dev, entered_state);
exit_idle:
__current_set_polling();
/*
* It is up to the idle functions to reenable local interrupts
*/
if (WARN_ON_ONCE(irqs_disabled()))
local_irq_enable();
rcu_idle_exit();
start_critical_timings();
}
/**
* tick_nohz_stop_sched_tick - stop the idle tick from the idle task
*
* When the next event is more than a tick into the future, stop the idle tick
* Called either from the idle loop or from irq_exit() when an idle period was
* just interrupted by an interrupt which did not cause a reschedule.
*/
void tick_nohz_stop_sched_tick(int inidle)
{
unsigned long seq, last_jiffies, next_jiffies, delta_jiffies, flags;
struct tick_sched *ts;
ktime_t last_update, expires, now;
struct clock_event_device *dev = __get_cpu_var(tick_cpu_device).evtdev;
u64 time_delta;
int cpu;
local_irq_save(flags);
cpu = smp_processor_id();
ts = &per_cpu(tick_cpu_sched, cpu);
/*
* Call to tick_nohz_start_idle stops the last_update_time from being
* updated. Thus, it must not be called in the event we are called from
* irq_exit() with the prior state different than idle.
*/
if (!inidle && !ts->inidle)
goto end;
/*
* Set ts->inidle unconditionally. Even if the system did not
* switch to NOHZ mode the cpu frequency governers rely on the
* update of the idle time accounting in tick_nohz_start_idle().
*/
ts->inidle = 1;
now = tick_nohz_start_idle(ts);
/*
* If this cpu is offline and it is the one which updates
* jiffies, then give up the assignment and let it be taken by
* the cpu which runs the tick timer next. If we don't drop
* this here the jiffies might be stale and do_timer() never
* invoked.
*/
if (unlikely(!cpu_online(cpu))) {
if (cpu == tick_do_timer_cpu)
tick_do_timer_cpu = TICK_DO_TIMER_NONE;
}
if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE))
goto end;
if (need_resched())
goto end;
if (unlikely(local_softirq_pending() && cpu_online(cpu))) {
static int ratelimit;
if (ratelimit < 10) {
printk(KERN_ERR "NOHZ: local_softirq_pending %02x\n",
local_softirq_pending());
ratelimit++;
}
goto end;
}
ts->idle_calls++;
/* Read jiffies and the time when jiffies were updated last */
do {
seq = read_seqbegin(&xtime_lock);
last_update = last_jiffies_update;
last_jiffies = jiffies;
/*
* On SMP we really should only care for the CPU which
* has the do_timer duty assigned. All other CPUs can
* sleep as long as they want.
*/
if (cpu == tick_do_timer_cpu ||
tick_do_timer_cpu == TICK_DO_TIMER_NONE)
time_delta = timekeeping_max_deferment();
else
time_delta = KTIME_MAX;
} while (read_seqretry(&xtime_lock, seq));
if (rcu_needs_cpu(cpu) || printk_needs_cpu(cpu) ||
arch_needs_cpu(cpu)) {
next_jiffies = last_jiffies + 1;
delta_jiffies = 1;
} else {
/* Get the next timer wheel timer */
next_jiffies = get_next_timer_interrupt(last_jiffies);
delta_jiffies = next_jiffies - last_jiffies;
}
/*
* Do not stop the tick, if we are only one off
* or if the cpu is required for rcu
*/
if (!ts->tick_stopped && delta_jiffies == 1)
goto out;
/* Schedule the tick, if we are at least one jiffie off */
if ((long)delta_jiffies >= 1) {
/*
* calculate the expiry time for the next timer wheel
* timer. delta_jiffies >= NEXT_TIMER_MAX_DELTA signals
* that there is no timer pending or at least extremely
* far into the future (12 days for HZ=1000). In this
* case we set the expiry to the end of time.
*/
if (likely(delta_jiffies < NEXT_TIMER_MAX_DELTA)) {
/*
* Calculate the time delta for the next timer event.
* If the time delta exceeds the maximum time delta
* permitted by the current clocksource then adjust
* the time delta accordingly to ensure the
* clocksource does not wrap.
*/
time_delta = min_t(u64, time_delta,
tick_period.tv64 * delta_jiffies);
expires = ktime_add_ns(last_update, time_delta);
} else {
expires.tv64 = KTIME_MAX;
}
/*
* If this cpu is the one which updates jiffies, then
* give up the assignment and let it be taken by the
* cpu which runs the tick timer next, which might be
* this cpu as well. If we don't drop this here the
* jiffies might be stale and do_timer() never
* invoked.
*/
if (cpu == tick_do_timer_cpu)
tick_do_timer_cpu = TICK_DO_TIMER_NONE;
if (delta_jiffies > 1)
cpumask_set_cpu(cpu, nohz_cpu_mask);
/* Skip reprogram of event if its not changed */
if (ts->tick_stopped && ktime_equal(expires, dev->next_event))
goto out;
/*
* nohz_stop_sched_tick can be called several times before
* the nohz_restart_sched_tick is called. This happens when
* interrupts arrive which do not cause a reschedule. In the
* first call we save the current tick time, so we can restart
* the scheduler tick in nohz_restart_sched_tick.
*/
if (!ts->tick_stopped) {
if (select_nohz_load_balancer(1)) {
/*
* sched tick not stopped!
*/
cpumask_clear_cpu(cpu, nohz_cpu_mask);
goto out;
}
ts->idle_tick = hrtimer_get_expires(&ts->sched_timer);
ts->tick_stopped = 1;
ts->idle_jiffies = last_jiffies;
rcu_enter_nohz();
}
ts->idle_sleeps++;
/* Mark expires */
ts->idle_expires = expires;
/*
* If the expiration time == KTIME_MAX, then
* in this case we simply stop the tick timer.
*/
if (unlikely(expires.tv64 == KTIME_MAX)) {
if (ts->nohz_mode == NOHZ_MODE_HIGHRES)
hrtimer_cancel(&ts->sched_timer);
goto out;
}
if (ts->nohz_mode == NOHZ_MODE_HIGHRES) {
hrtimer_start(&ts->sched_timer, expires,
HRTIMER_MODE_ABS_PINNED);
/* Check, if the timer was already in the past */
if (hrtimer_active(&ts->sched_timer))
goto out;
} else if (!tick_program_event(expires, 0))
goto out;
/*
* We are past the event already. So we crossed a
* jiffie boundary. Update jiffies and raise the
* softirq.
*/
tick_do_update_jiffies64(ktime_get());
cpumask_clear_cpu(cpu, nohz_cpu_mask);
}
raise_softirq_irqoff(TIMER_SOFTIRQ);
out:
ts->next_jiffies = next_jiffies;
ts->last_jiffies = last_jiffies;
ts->sleep_length = ktime_sub(dev->next_event, now);
end:
local_irq_restore(flags);
}
int jbd2_log_do_checkpoint(journal_t *journal)
{
transaction_t *transaction;
tid_t this_tid;
int result;
jbd_debug(1, "Start checkpoint\n");
result = jbd2_cleanup_journal_tail(journal);
trace_jbd2_checkpoint(journal, result);
jbd_debug(1, "cleanup_journal_tail returned %d\n", result);
if (result <= 0)
return result;
result = 0;
spin_lock(&journal->j_list_lock);
if (!journal->j_checkpoint_transactions)
goto out;
transaction = journal->j_checkpoint_transactions;
if (transaction->t_chp_stats.cs_chp_time == 0)
transaction->t_chp_stats.cs_chp_time = jiffies;
this_tid = transaction->t_tid;
restart:
if (journal->j_checkpoint_transactions == transaction &&
transaction->t_tid == this_tid) {
int batch_count = 0;
struct journal_head *jh;
int retry = 0, err;
while (!retry && transaction->t_checkpoint_list) {
jh = transaction->t_checkpoint_list;
retry = __process_buffer(journal, jh, &batch_count,
transaction);
if (retry < 0 && !result)
result = retry;
if (!retry && (need_resched() ||
spin_needbreak(&journal->j_list_lock))) {
spin_unlock(&journal->j_list_lock);
retry = 1;
break;
}
}
if (batch_count) {
if (!retry) {
spin_unlock(&journal->j_list_lock);
retry = 1;
}
__flush_batch(journal, &batch_count);
}
if (retry) {
spin_lock(&journal->j_list_lock);
goto restart;
}
err = __wait_cp_io(journal, transaction);
if (!result)
result = err;
}
out:
spin_unlock(&journal->j_list_lock);
if (result < 0)
jbd2_journal_abort(journal, result);
else
result = jbd2_cleanup_journal_tail(journal);
return (result < 0) ? result : 0;
}
/**
* cpuidle_idle_call - the main idle function
*
* NOTE: no locks or semaphores should be used here
*
* On archs that support TIF_POLLING_NRFLAG, is called with polling
* set, and it returns with polling set. If it ever stops polling, it
* must clear the polling bit.
*/
static void cpuidle_idle_call(void)
{
struct cpuidle_device *dev = __this_cpu_read(cpuidle_devices);
struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
int next_state, entered_state;
/*
* Check if the idle task must be rescheduled. If it is the
* case, exit the function after re-enabling the local irq.
*/
if (need_resched()) {
local_irq_enable();
return;
}
/*
* During the idle period, stop measuring the disabled irqs
* critical sections latencies
*/
stop_critical_timings();
/*
* Tell the RCU framework we are entering an idle section,
* so no more rcu read side critical sections and one more
* step to the grace period
*/
rcu_idle_enter();
/*
* Check if the cpuidle framework is ready, otherwise fallback
* to the default arch specific idle method
*/
next_state = cpuidle_select(drv, dev);
if (next_state < 0) {
default_idle_call();
goto exit_idle;
}
/*
* The idle task must be scheduled, it is pointless to
* go to idle, just update no idle residency and get
* out of this function
*/
if (current_clr_polling_and_test()) {
dev->last_residency = 0;
entered_state = next_state;
local_irq_enable();
goto exit_idle;
}
/* Take note of the planned idle state. */
idle_set_state(this_rq(), &drv->states[next_state]);
/*
* Enter the idle state previously returned by the governor decision.
* This function will block until an interrupt occurs and will take
* care of re-enabling the local interrupts
*/
entered_state = cpuidle_enter(drv, dev, next_state);
/* The cpu is no longer idle or about to enter idle. */
idle_set_state(this_rq(), NULL);
if (entered_state == -EBUSY) {
default_idle_call();
goto exit_idle;
}
/*
* Give the governor an opportunity to reflect on the outcome
*/
cpuidle_reflect(dev, entered_state);
exit_idle:
__current_set_polling();
/*
* It is up to the idle functions to reenable local interrupts
*/
if (WARN_ON_ONCE(irqs_disabled()))
local_irq_enable();
rcu_idle_exit();
start_critical_timings();
}
/*
* Garbage collector for unused keys.
*
* This is done in process context so that we don't have to disable interrupts
* all over the place. key_put() schedules this rather than trying to do the
* cleanup itself, which means key_put() doesn't have to sleep.
*/
static void key_garbage_collector(struct work_struct *work)
{
static LIST_HEAD(graveyard);
static u8 gc_state; /* Internal persistent state */
#define KEY_GC_REAP_AGAIN 0x01 /* - Need another cycle */
#define KEY_GC_REAPING_LINKS 0x02 /* - We need to reap links */
#define KEY_GC_SET_TIMER 0x04 /* - We need to restart the timer */
#define KEY_GC_REAPING_DEAD_1 0x10 /* - We need to mark dead keys */
#define KEY_GC_REAPING_DEAD_2 0x20 /* - We need to reap dead key links */
#define KEY_GC_REAPING_DEAD_3 0x40 /* - We need to reap dead keys */
#define KEY_GC_FOUND_DEAD_KEY 0x80 /* - We found at least one dead key */
struct rb_node *cursor;
struct key *key;
time_t new_timer, limit;
kenter("[%lx,%x]", key_gc_flags, gc_state);
limit = current_kernel_time().tv_sec;
if (limit > key_gc_delay)
limit -= key_gc_delay;
else
limit = key_gc_delay;
/* Work out what we're going to be doing in this pass */
gc_state &= KEY_GC_REAPING_DEAD_1 | KEY_GC_REAPING_DEAD_2;
gc_state <<= 1;
if (test_and_clear_bit(KEY_GC_KEY_EXPIRED, &key_gc_flags))
gc_state |= KEY_GC_REAPING_LINKS | KEY_GC_SET_TIMER;
if (test_and_clear_bit(KEY_GC_REAP_KEYTYPE, &key_gc_flags))
gc_state |= KEY_GC_REAPING_DEAD_1;
kdebug("new pass %x", gc_state);
new_timer = LONG_MAX;
/* As only this function is permitted to remove things from the key
* serial tree, if cursor is non-NULL then it will always point to a
* valid node in the tree - even if lock got dropped.
*/
spin_lock(&key_serial_lock);
cursor = rb_first(&key_serial_tree);
continue_scanning:
while (cursor) {
key = rb_entry(cursor, struct key, serial_node);
cursor = rb_next(cursor);
if (atomic_read(&key->usage) == 0)
goto found_unreferenced_key;
if (unlikely(gc_state & KEY_GC_REAPING_DEAD_1)) {
if (key->type == key_gc_dead_keytype) {
gc_state |= KEY_GC_FOUND_DEAD_KEY;
set_bit(KEY_FLAG_DEAD, &key->flags);
key->perm = 0;
goto skip_dead_key;
}
}
if (gc_state & KEY_GC_SET_TIMER) {
if (key->expiry > limit && key->expiry < new_timer) {
kdebug("will expire %x in %ld",
key_serial(key), key->expiry - limit);
new_timer = key->expiry;
}
}
if (unlikely(gc_state & KEY_GC_REAPING_DEAD_2))
if (key->type == key_gc_dead_keytype)
gc_state |= KEY_GC_FOUND_DEAD_KEY;
if ((gc_state & KEY_GC_REAPING_LINKS) ||
unlikely(gc_state & KEY_GC_REAPING_DEAD_2)) {
if (key->type == &key_type_keyring)
goto found_keyring;
}
if (unlikely(gc_state & KEY_GC_REAPING_DEAD_3))
if (key->type == key_gc_dead_keytype)
goto destroy_dead_key;
skip_dead_key:
if (spin_is_contended(&key_serial_lock) || need_resched())
goto contended;
}
contended:
spin_unlock(&key_serial_lock);
maybe_resched:
if (cursor) {
cond_resched();
spin_lock(&key_serial_lock);
goto continue_scanning;
}
/* We've completed the pass. Set the timer if we need to and queue a
* new cycle if necessary. We keep executing cycles until we find one
* where we didn't reap any keys.
*/
kdebug("pass complete");
if (gc_state & KEY_GC_SET_TIMER && new_timer != (time_t)LONG_MAX) {
new_timer += key_gc_delay;
key_schedule_gc(new_timer);
}
if (unlikely(gc_state & KEY_GC_REAPING_DEAD_2) ||
!list_empty(&graveyard)) {
/* Make sure that all pending keyring payload destructions are
* fulfilled and that people aren't now looking at dead or
* dying keys that they don't have a reference upon or a link
* to.
*/
kdebug("gc sync");
synchronize_rcu();
}
if (!list_empty(&graveyard)) {
kdebug("gc keys");
key_gc_unused_keys(&graveyard);
}
if (unlikely(gc_state & (KEY_GC_REAPING_DEAD_1 |
KEY_GC_REAPING_DEAD_2))) {
if (!(gc_state & KEY_GC_FOUND_DEAD_KEY)) {
/* No remaining dead keys: short circuit the remaining
* keytype reap cycles.
*/
kdebug("dead short");
gc_state &= ~(KEY_GC_REAPING_DEAD_1 | KEY_GC_REAPING_DEAD_2);
gc_state |= KEY_GC_REAPING_DEAD_3;
} else {
gc_state |= KEY_GC_REAP_AGAIN;
}
}
if (unlikely(gc_state & KEY_GC_REAPING_DEAD_3)) {
kdebug("dead wake");
smp_mb();
clear_bit(KEY_GC_REAPING_KEYTYPE, &key_gc_flags);
wake_up_bit(&key_gc_flags, KEY_GC_REAPING_KEYTYPE);
}
if (gc_state & KEY_GC_REAP_AGAIN)
schedule_work(&key_gc_work);
kleave(" [end %x]", gc_state);
return;
/* We found an unreferenced key - once we've removed it from the tree,
* we can safely drop the lock.
*/
found_unreferenced_key:
kdebug("unrefd key %d", key->serial);
rb_erase(&key->serial_node, &key_serial_tree);
spin_unlock(&key_serial_lock);
list_add_tail(&key->graveyard_link, &graveyard);
gc_state |= KEY_GC_REAP_AGAIN;
goto maybe_resched;
/* We found a keyring and we need to check the payload for links to
* dead or expired keys. We don't flag another reap immediately as we
* have to wait for the old payload to be destroyed by RCU before we
* can reap the keys to which it refers.
*/
found_keyring:
spin_unlock(&key_serial_lock);
kdebug("scan keyring %d", key->serial);
key_gc_keyring(key, limit);
goto maybe_resched;
/* We found a dead key that is still referenced. Reset its type and
* destroy its payload with its semaphore held.
*/
destroy_dead_key:
spin_unlock(&key_serial_lock);
kdebug("destroy key %d", key->serial);
down_write(&key->sem);
key->type = &key_type_dead;
if (key_gc_dead_keytype->destroy)
key_gc_dead_keytype->destroy(key);
memset(&key->payload, KEY_DESTROY, sizeof(key->payload));
up_write(&key->sem);
goto maybe_resched;
}
/*
* Submit all the data buffers to disk
*/
static int journal_submit_data_buffers(journal_t *journal,
transaction_t *commit_transaction,
int write_op)
{
struct journal_head *jh;
struct buffer_head *bh;
int locked;
int bufs = 0;
struct buffer_head **wbuf = journal->j_wbuf;
int err = 0;
/*
* Whenever we unlock the journal and sleep, things can get added
* onto ->t_sync_datalist, so we have to keep looping back to
* write_out_data until we *know* that the list is empty.
*
* Cleanup any flushed data buffers from the data list. Even in
* abort mode, we want to flush this out as soon as possible.
*/
write_out_data:
cond_resched();
spin_lock(&journal->j_list_lock);
while (commit_transaction->t_sync_datalist) {
jh = commit_transaction->t_sync_datalist;
bh = jh2bh(jh);
locked = 0;
/* Get reference just to make sure buffer does not disappear
* when we are forced to drop various locks */
get_bh(bh);
/* If the buffer is dirty, we need to submit IO and hence
* we need the buffer lock. We try to lock the buffer without
* blocking. If we fail, we need to drop j_list_lock and do
* blocking lock_buffer().
*/
if (buffer_dirty(bh)) {
if (!trylock_buffer(bh)) {
BUFFER_TRACE(bh, "needs blocking lock");
spin_unlock(&journal->j_list_lock);
trace_jbd_do_submit_data(journal,
commit_transaction);
/* Write out all data to prevent deadlocks */
journal_do_submit_data(wbuf, bufs, write_op);
bufs = 0;
lock_buffer(bh);
spin_lock(&journal->j_list_lock);
}
locked = 1;
}
/* We have to get bh_state lock. Again out of order, sigh. */
if (!inverted_lock(journal, bh)) {
jbd_lock_bh_state(bh);
spin_lock(&journal->j_list_lock);
}
/* Someone already cleaned up the buffer? */
if (!buffer_jbd(bh) || bh2jh(bh) != jh
|| jh->b_transaction != commit_transaction
|| jh->b_jlist != BJ_SyncData) {
jbd_unlock_bh_state(bh);
if (locked)
unlock_buffer(bh);
BUFFER_TRACE(bh, "already cleaned up");
release_data_buffer(bh);
continue;
}
if (locked && test_clear_buffer_dirty(bh)) {
BUFFER_TRACE(bh, "needs writeout, adding to array");
wbuf[bufs++] = bh;
__journal_file_buffer(jh, commit_transaction,
BJ_Locked);
jbd_unlock_bh_state(bh);
if (bufs == journal->j_wbufsize) {
spin_unlock(&journal->j_list_lock);
trace_jbd_do_submit_data(journal,
commit_transaction);
journal_do_submit_data(wbuf, bufs, write_op);
bufs = 0;
goto write_out_data;
}
} else if (!locked && buffer_locked(bh)) {
__journal_file_buffer(jh, commit_transaction,
BJ_Locked);
jbd_unlock_bh_state(bh);
put_bh(bh);
} else {
BUFFER_TRACE(bh, "writeout complete: unfile");
if (unlikely(!buffer_uptodate(bh)))
err = -EIO;
__journal_unfile_buffer(jh);
jbd_unlock_bh_state(bh);
if (locked)
unlock_buffer(bh);
release_data_buffer(bh);
}
if (need_resched() || spin_needbreak(&journal->j_list_lock)) {
spin_unlock(&journal->j_list_lock);
goto write_out_data;
}
}
spin_unlock(&journal->j_list_lock);
trace_jbd_do_submit_data(journal, commit_transaction);
journal_do_submit_data(wbuf, bufs, write_op);
return err;
}
asmlinkage void __do_softirq(void)
{
struct softirq_action *h;
__u32 pending;
unsigned long end = jiffies + MAX_SOFTIRQ_TIME;
int cpu;
unsigned long old_flags = current->flags;
int max_restart = MAX_SOFTIRQ_RESTART;
/*
* Mask out PF_MEMALLOC s current task context is borrowed for the
* softirq. A softirq handled such as network RX might set PF_MEMALLOC
* again if the socket is related to swap
*/
current->flags &= ~PF_MEMALLOC;
pending = local_softirq_pending();
account_system_vtime(current);
__local_bh_disable((unsigned long)__builtin_return_address(0),
SOFTIRQ_OFFSET);
lockdep_softirq_enter();
cpu = smp_processor_id();
restart:
/* Reset the pending bitmask before enabling irqs */
set_softirq_pending(0);
local_irq_enable();
h = softirq_vec;
do {
if (pending & 1) {
unsigned int vec_nr = h - softirq_vec;
int prev_count = preempt_count();
kstat_incr_softirqs_this_cpu(vec_nr);
trace_softirq_entry(vec_nr);
h->action(h);
trace_softirq_exit(vec_nr);
if (unlikely(prev_count != preempt_count())) {
printk(KERN_ERR "huh, entered softirq %u %s %p"
"with preempt_count %08x,"
" exited with %08x?\n", vec_nr,
softirq_to_name[vec_nr], h->action,
prev_count, preempt_count());
preempt_count_set(prev_count);
}
rcu_bh_qs(cpu);
}
h++;
pending >>= 1;
} while (pending);
local_irq_disable();
pending = local_softirq_pending();
if (pending) {
if (time_before(jiffies, end) && !need_resched() &&
--max_restart)
goto restart;
wakeup_softirqd();
}
lockdep_softirq_exit();
account_system_vtime(current);
__local_bh_enable(SOFTIRQ_OFFSET);
tsk_restore_flags(current, old_flags, PF_MEMALLOC);
}
/*
* Lock a mutex (possibly interruptible), slowpath:
*/
static inline int __sched
__mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
struct lockdep_map *nest_lock, unsigned long ip)
{
struct task_struct *task = current;
struct mutex_waiter waiter;
unsigned long flags;
preempt_disable();
mutex_acquire_nest(&lock->dep_map, subclass, 0, nest_lock, ip);
#ifdef CONFIG_MUTEX_SPIN_ON_OWNER
/*
* Optimistic spinning.
*
* We try to spin for acquisition when we find that there are no
* pending waiters and the lock owner is currently running on a
* (different) CPU.
*
* The rationale is that if the lock owner is running, it is likely to
* release the lock soon.
*
* Since this needs the lock owner, and this mutex implementation
* doesn't track the owner atomically in the lock field, we need to
* track it non-atomically.
*
* We can't do this for DEBUG_MUTEXES because that relies on wait_lock
* to serialize everything.
*
* The mutex spinners are queued up using MCS lock so that only one
* spinner can compete for the mutex. However, if mutex spinning isn't
* going to happen, there is no point in going through the lock/unlock
* overhead.
*/
if (!mutex_can_spin_on_owner(lock))
goto slowpath;
for (;;) {
struct task_struct *owner;
struct mspin_node node;
/*
* If there's an owner, wait for it to either
* release the lock or go to sleep.
*/
mspin_lock(MLOCK(lock), &node);
owner = ACCESS_ONCE(lock->owner);
if (owner && !mutex_spin_on_owner(lock, owner)) {
mspin_unlock(MLOCK(lock), &node);
break;
}
if ((atomic_read(&lock->count) == 1) &&
(atomic_cmpxchg(&lock->count, 1, 0) == 1)) {
lock_acquired(&lock->dep_map, ip);
mutex_set_owner(lock);
mspin_unlock(MLOCK(lock), &node);
preempt_enable();
return 0;
}
mspin_unlock(MLOCK(lock), &node);
/*
* When there's no owner, we might have preempted between the
* owner acquiring the lock and setting the owner field. If
* we're an RT task that will live-lock because we won't let
* the owner complete.
*/
if (!owner && (need_resched() || rt_task(task)))
break;
/*
* The cpu_relax() call is a compiler barrier which forces
* everything in this loop to be re-loaded. We don't need
* memory barriers as we'll eventually observe the right
* values at the cost of a few extra spins.
*/
arch_mutex_cpu_relax();
}
slowpath:
#endif
spin_lock_mutex(&lock->wait_lock, flags);
debug_mutex_lock_common(lock, &waiter);
debug_mutex_add_waiter(lock, &waiter, task_thread_info(task));
/* add waiting tasks to the end of the waitqueue (FIFO): */
list_add_tail(&waiter.list, &lock->wait_list);
waiter.task = task;
if (MUTEX_SHOW_NO_WAITER(lock) && (atomic_xchg(&lock->count, -1) == 1))
goto done;
lock_contended(&lock->dep_map, ip);
for (;;) {
/*
* Lets try to take the lock again - this is needed even if
* we get here for the first time (shortly after failing to
* acquire the lock), to make sure that we get a wakeup once
* it's unlocked. Later on, if we sleep, this is the
* operation that gives us the lock. We xchg it to -1, so
* that when we release the lock, we properly wake up the
* other waiters:
*/
if (MUTEX_SHOW_NO_WAITER(lock) &&
(atomic_xchg(&lock->count, -1) == 1))
break;
/*
* got a signal? (This code gets eliminated in the
* TASK_UNINTERRUPTIBLE case.)
*/
if (unlikely(signal_pending_state(state, task))) {
mutex_remove_waiter(lock, &waiter,
task_thread_info(task));
mutex_release(&lock->dep_map, 1, ip);
spin_unlock_mutex(&lock->wait_lock, flags);
debug_mutex_free_waiter(&waiter);
preempt_enable();
return -EINTR;
}
__set_task_state(task, state);
/* didn't get the lock, go to sleep: */
spin_unlock_mutex(&lock->wait_lock, flags);
schedule_preempt_disabled();
spin_lock_mutex(&lock->wait_lock, flags);
}
done:
lock_acquired(&lock->dep_map, ip);
/* got the lock - rejoice! */
mutex_remove_waiter(lock, &waiter, current_thread_info());
mutex_set_owner(lock);
/* set it to 0 if there are no waiters left: */
if (likely(list_empty(&lock->wait_list)))
atomic_set(&lock->count, 0);
spin_unlock_mutex(&lock->wait_lock, flags);
debug_mutex_free_waiter(&waiter);
preempt_enable();
return 0;
}
/*
* Perform an actual checkpoint. We take the first transaction on the
* list of transactions to be checkpointed and send all its buffers
* to disk. We submit larger chunks of data at once.
*
* The journal should be locked before calling this function.
* Called with j_checkpoint_mutex held.
*/
int jbd2_log_do_checkpoint(journal_t *journal)
{
struct journal_head *jh;
struct buffer_head *bh;
transaction_t *transaction;
tid_t this_tid;
int result, batch_count = 0;
jbd_debug(1, "Start checkpoint\n");
/*
* First thing: if there are any transactions in the log which
* don't need checkpointing, just eliminate them from the
* journal straight away.
*/
result = jbd2_cleanup_journal_tail(journal);
trace_jbd2_checkpoint(journal, result);
jbd_debug(1, "cleanup_journal_tail returned %d\n", result);
if (result <= 0)
return result;
/*
* OK, we need to start writing disk blocks. Take one transaction
* and write it.
*/
result = 0;
spin_lock(&journal->j_list_lock);
if (!journal->j_checkpoint_transactions)
goto out;
transaction = journal->j_checkpoint_transactions;
if (transaction->t_chp_stats.cs_chp_time == 0)
transaction->t_chp_stats.cs_chp_time = jiffies;
this_tid = transaction->t_tid;
restart:
/*
* If someone cleaned up this transaction while we slept, we're
* done (maybe it's a new transaction, but it fell at the same
* address).
*/
if (journal->j_checkpoint_transactions != transaction ||
transaction->t_tid != this_tid)
goto out;
/* checkpoint all of the transaction's buffers */
while (transaction->t_checkpoint_list) {
jh = transaction->t_checkpoint_list;
bh = jh2bh(jh);
if (buffer_locked(bh)) {
spin_unlock(&journal->j_list_lock);
get_bh(bh);
wait_on_buffer(bh);
/* the journal_head may have gone by now */
BUFFER_TRACE(bh, "brelse");
__brelse(bh);
goto retry;
}
if (jh->b_transaction != NULL) {
transaction_t *t = jh->b_transaction;
tid_t tid = t->t_tid;
transaction->t_chp_stats.cs_forced_to_close++;
spin_unlock(&journal->j_list_lock);
if (unlikely(journal->j_flags & JBD2_UNMOUNT))
/*
* The journal thread is dead; so
* starting and waiting for a commit
* to finish will cause us to wait for
* a _very_ long time.
*/
printk(KERN_ERR
"JBD2: %s: Waiting for Godot: block %llu\n",
journal->j_devname, (unsigned long long) bh->b_blocknr);
jbd2_log_start_commit(journal, tid);
jbd2_log_wait_commit(journal, tid);
goto retry;
}
if (!buffer_dirty(bh)) {
if (unlikely(buffer_write_io_error(bh)) && !result)
result = -EIO;
BUFFER_TRACE(bh, "remove from checkpoint");
if (__jbd2_journal_remove_checkpoint(jh))
/* The transaction was released; we're done */
goto out;
continue;
}
/*
* Important: we are about to write the buffer, and
* possibly block, while still holding the journal
* lock. We cannot afford to let the transaction
* logic start messing around with this buffer before
* we write it to disk, as that would break
* recoverability.
*/
BUFFER_TRACE(bh, "queue");
get_bh(bh);
J_ASSERT_BH(bh, !buffer_jwrite(bh));
journal->j_chkpt_bhs[batch_count++] = bh;
__buffer_relink_io(jh);
transaction->t_chp_stats.cs_written++;
if ((batch_count == JBD2_NR_BATCH) ||
need_resched() ||
spin_needbreak(&journal->j_list_lock))
goto unlock_and_flush;
}
if (batch_count) {
unlock_and_flush:
spin_unlock(&journal->j_list_lock);
retry:
if (batch_count)
__flush_batch(journal, &batch_count);
spin_lock(&journal->j_list_lock);
goto restart;
}
/*
* Now we issued all of the transaction's buffers, let's deal
* with the buffers that are out for I/O.
*/
restart2:
/* Did somebody clean up the transaction in the meanwhile? */
if (journal->j_checkpoint_transactions != transaction ||
transaction->t_tid != this_tid)
goto out;
while (transaction->t_checkpoint_io_list) {
jh = transaction->t_checkpoint_io_list;
bh = jh2bh(jh);
if (buffer_locked(bh)) {
spin_unlock(&journal->j_list_lock);
get_bh(bh);
wait_on_buffer(bh);
/* the journal_head may have gone by now */
BUFFER_TRACE(bh, "brelse");
__brelse(bh);
spin_lock(&journal->j_list_lock);
goto restart2;
}
if (unlikely(buffer_write_io_error(bh)) && !result)
result = -EIO;
/*
* Now in whatever state the buffer currently is, we
* know that it has been written out and so we can
* drop it from the list
*/
if (__jbd2_journal_remove_checkpoint(jh))
break;
}
out:
spin_unlock(&journal->j_list_lock);
if (result < 0)
jbd2_journal_abort(journal, result);
else
result = jbd2_cleanup_journal_tail(journal);
return (result < 0) ? result : 0;
}
bool osq_lock(struct optimistic_spin_queue *lock)
{
struct optimistic_spin_node *node = this_cpu_ptr(&osq_node);
struct optimistic_spin_node *prev, *next;
int curr = encode_cpu(smp_processor_id());
int old;
node->locked = 0;
node->next = NULL;
node->cpu = curr;
/*
* We need both ACQUIRE (pairs with corresponding RELEASE in
* unlock() uncontended, or fastpath) and RELEASE (to publish
* the node fields we just initialised) semantics when updating
* the lock tail.
*/
old = atomic_xchg(&lock->tail, curr);
if (old == OSQ_UNLOCKED_VAL)
return true;
prev = decode_cpu(old);
node->prev = prev;
WRITE_ONCE(prev->next, node);
/*
* Normally @prev is untouchable after the above store; because at that
* moment unlock can proceed and wipe the node element from stack.
*
* However, since our nodes are static per-cpu storage, we're
* guaranteed their existence -- this allows us to apply
* cmpxchg in an attempt to undo our queueing.
*/
while (!READ_ONCE(node->locked)) {
/*
* If we need to reschedule bail... so we can block.
*/
if (need_resched())
goto unqueue;
cpu_relax_lowlatency();
}
return true;
unqueue:
/*
* Step - A -- stabilize @prev
*
* Undo our @prev->next assignment; this will make @prev's
* unlock()/unqueue() wait for a next pointer since @lock points to us
* (or later).
*/
for (;;) {
if (prev->next == node &&
cmpxchg(&prev->next, node, NULL) == node)
break;
/*
* We can only fail the cmpxchg() racing against an unlock(),
* in which case we should observe @node->locked becomming
* true.
*/
if (smp_load_acquire(&node->locked))
return true;
cpu_relax_lowlatency();
/*
* Or we race against a concurrent unqueue()'s step-B, in which
* case its step-C will write us a new @node->prev pointer.
*/
prev = READ_ONCE(node->prev);
}
/*
* Step - B -- stabilize @next
*
* Similar to unlock(), wait for @node->next or move @lock from @node
* back to @prev.
*/
next = osq_wait_next(lock, node, prev);
if (!next)
return false;
/*
* Step - C -- unlink
*
* @prev is stable because its still waiting for a new @prev->next
* pointer, @next is stable because our @node->next pointer is NULL and
* it will wait in Step-A.
*/
WRITE_ONCE(next->prev, prev);
WRITE_ONCE(prev->next, next);
return false;
}
static void tick_nohz_stop_sched_tick(struct tick_sched *ts)
{
unsigned long seq, last_jiffies, next_jiffies, delta_jiffies;
unsigned long rcu_delta_jiffies;
ktime_t last_update, expires, now;
struct clock_event_device *dev = __get_cpu_var(tick_cpu_device).evtdev;
u64 time_delta;
int cpu;
cpu = smp_processor_id();
ts = &per_cpu(tick_cpu_sched, cpu);
now = tick_nohz_start_idle(cpu, ts);
if (unlikely(!cpu_online(cpu))) {
if (cpu == tick_do_timer_cpu)
tick_do_timer_cpu = TICK_DO_TIMER_NONE;
}
if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE))
return;
if (need_resched())
return;
if (unlikely(local_softirq_pending() && cpu_online(cpu))) {
static int ratelimit;
if (ratelimit < 10) {
printk(KERN_ERR "NOHZ: local_softirq_pending %02x\n",
(unsigned int) local_softirq_pending());
ratelimit++;
}
return;
}
ts->idle_calls++;
do {
seq = read_seqbegin(&xtime_lock);
last_update = last_jiffies_update;
last_jiffies = jiffies;
time_delta = timekeeping_max_deferment();
} while (read_seqretry(&xtime_lock, seq));
if (rcu_needs_cpu(cpu, &rcu_delta_jiffies) || printk_needs_cpu(cpu) ||
arch_needs_cpu(cpu)) {
next_jiffies = last_jiffies + 1;
delta_jiffies = 1;
} else {
next_jiffies = get_next_timer_interrupt(last_jiffies);
delta_jiffies = next_jiffies - last_jiffies;
if (rcu_delta_jiffies < delta_jiffies) {
next_jiffies = last_jiffies + rcu_delta_jiffies;
delta_jiffies = rcu_delta_jiffies;
}
}
if (!ts->tick_stopped && delta_jiffies == 1)
goto out;
if ((long)delta_jiffies >= 1) {
if (cpu == tick_do_timer_cpu) {
tick_do_timer_cpu = TICK_DO_TIMER_NONE;
ts->do_timer_last = 1;
} else if (tick_do_timer_cpu != TICK_DO_TIMER_NONE) {
time_delta = KTIME_MAX;
ts->do_timer_last = 0;
} else if (!ts->do_timer_last) {
time_delta = KTIME_MAX;
}
if (likely(delta_jiffies < NEXT_TIMER_MAX_DELTA)) {
time_delta = min_t(u64, time_delta,
tick_period.tv64 * delta_jiffies);
}
if (time_delta < KTIME_MAX)
expires = ktime_add_ns(last_update, time_delta);
else
expires.tv64 = KTIME_MAX;
if (ts->tick_stopped && ktime_equal(expires, dev->next_event))
goto out;
if (!ts->tick_stopped) {
select_nohz_load_balancer(1);
ts->idle_tick = hrtimer_get_expires(&ts->sched_timer);
ts->tick_stopped = 1;
ts->idle_jiffies = last_jiffies;
}
ts->idle_sleeps++;
ts->idle_expires = expires;
if (unlikely(expires.tv64 == KTIME_MAX)) {
if (ts->nohz_mode == NOHZ_MODE_HIGHRES)
hrtimer_cancel(&ts->sched_timer);
goto out;
}
if (ts->nohz_mode == NOHZ_MODE_HIGHRES) {
hrtimer_start(&ts->sched_timer, expires,
HRTIMER_MODE_ABS_PINNED);
if (hrtimer_active(&ts->sched_timer))
goto out;
} else if (!tick_program_event(expires, 0))
goto out;
tick_do_update_jiffies64(ktime_get());
}
raise_softirq_irqoff(TIMER_SOFTIRQ);
out:
ts->next_jiffies = next_jiffies;
ts->last_jiffies = last_jiffies;
}