/*
* Must be called with interrupts disabled !
*/
static void tick_do_update_jiffies64(ktime_t now)
{
unsigned long ticks = 0;
ktime_t delta;
/*
* Do a quick check without holding xtime_lock:
*/
delta = ktime_sub(now, last_jiffies_update);
if (delta.tv64 < tick_period.tv64)
return;
/* Reevalute with xtime_lock held */
write_seqlock(&xtime_lock);
delta = ktime_sub(now, last_jiffies_update);
if (delta.tv64 >= tick_period.tv64) {
delta = ktime_sub(delta, tick_period);
last_jiffies_update = ktime_add(last_jiffies_update,
tick_period);
/* Slow path for long timeouts */
if (unlikely(delta.tv64 >= tick_period.tv64)) {
s64 incr = ktime_to_ns(tick_period);
ticks = ktime_divns(delta, incr);
last_jiffies_update = ktime_add_ns(last_jiffies_update,
incr * ticks);
}
do_timer(++ticks);
/* Keep the tick_next_period variable up to date */
tick_next_period = ktime_add(last_jiffies_update, tick_period);
}
write_sequnlock(&xtime_lock);
}
/**
* pch_i2c_wait_for_bus_idle() - check the status of bus.
* @adap: Pointer to struct i2c_algo_pch_data.
* @timeout: waiting time counter (us).
*/
static s32 pch_i2c_wait_for_bus_idle(struct i2c_algo_pch_data *adap,
s32 timeout)
{
void __iomem *p = adap->pch_base_address;
ktime_t ns_val;
if ((ioread32(p + PCH_I2CSR) & I2CMBB_BIT) == 0)
return 0;
/* MAX timeout value is timeout*1000*1000nsec */
ns_val = ktime_add_ns(ktime_get(), timeout*1000*1000);
do {
msleep(20);
if ((ioread32(p + PCH_I2CSR) & I2CMBB_BIT) == 0)
return 0;
} while (ktime_lt(ktime_get(), ns_val));
pch_dbg(adap, "I2CSR = %x\n", ioread32(p + PCH_I2CSR));
pch_err(adap, "%s: Timeout Error.return%d\n", __func__, -ETIME);
pch_i2c_init(adap);
return -ETIME;
}
/**
* hrtimer_forward - forward the timer expiry
* @timer: hrtimer to forward
* @now: forward past this time
* @interval: the interval to forward
*
* Forward the timer expiry so it will expire in the future.
* Returns the number of overruns.
*/
unsigned long
hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval)
{
unsigned long orun = 1;
ktime_t delta;
delta = ktime_sub(now, timer->expires);
if (delta.tv64 < 0)
return 0;
if (interval.tv64 < timer->base->resolution.tv64)
interval.tv64 = timer->base->resolution.tv64;
if (unlikely(delta.tv64 >= interval.tv64)) {
s64 incr = ktime_to_ns(interval);
orun = ktime_divns(delta, incr);
timer->expires = ktime_add_ns(timer->expires, incr * orun);
if (timer->expires.tv64 > now.tv64)
return orun;
/*
* This (and the ktime_add() below) is the
* correction for exact:
*/
orun++;
}
timer->expires = ktime_add(timer->expires, interval);
/*
* Make sure, that the result did not wrap with a very large
* interval.
*/
if (timer->expires.tv64 < 0)
timer->expires = ktime_set(KTIME_SEC_MAX, 0);
return orun;
}
enum hrtimer_restart hrtimer_auto_trigger_func(struct hrtimer *p_timer)
{
//printk("The function SMI hrtimer_auto_trigger_func, times is %lu\n", hrtimer_trigger_times);
//before Linux 2.6.3 //hrtimer_auto_trigger.expires=ktime_add_ns(hrtimer_auto_trigger.expires,(u64)(hrtimer_smi_time_interval*1000000));
hrtimer_set_expires(&hrtimer_auto_trigger, ktime_add_ns(hrtimer_get_expires(&hrtimer_auto_trigger),(u64)(hrtimer_smi_time_interval*1000000)));
//Get SMI data
SMI_Manual_Trigger_Result(hrtimer_cfg, hrtimer_cfg_ex, & hrtimer_result);
auto_trigger_result[hrtimer_trigger_times] = hrtimer_result;
//Update Conuter
hrtimer_trigger_times ++;
if(hrtimer_trigger_times>=hrtimer_smi_time_count)
{
return HRTIMER_NORESTART;
}
else
{
return HRTIMER_RESTART;
}
}
int journal_stop(handle_t *handle)
{
transaction_t *transaction = handle->h_transaction;
journal_t *journal = transaction->t_journal;
int err;
pid_t pid;
J_ASSERT(journal_current_handle() == handle);
if (is_handle_aborted(handle))
err = -EIO;
else {
J_ASSERT(transaction->t_updates > 0);
err = 0;
}
if (--handle->h_ref > 0) {
jbd_debug(4, "h_ref %d -> %d\n", handle->h_ref + 1,
handle->h_ref);
return err;
}
jbd_debug(4, "Handle %p going down\n", handle);
/*
* Implement synchronous transaction batching. If the handle
* was synchronous, don't force a commit immediately. Let's
* yield and let another thread piggyback onto this transaction.
* Keep doing that while new threads continue to arrive.
* It doesn't cost much - we're about to run a commit and sleep
* on IO anyway. Speeds up many-threaded, many-dir operations
* by 30x or more...
*
* We try and optimize the sleep time against what the underlying disk
* can do, instead of having a static sleep time. This is usefull for
* the case where our storage is so fast that it is more optimal to go
* ahead and force a flush and wait for the transaction to be committed
* than it is to wait for an arbitrary amount of time for new writers to
* join the transaction. We achieve this by measuring how long it takes
* to commit a transaction, and compare it with how long this
* transaction has been running, and if run time < commit time then we
* sleep for the delta and commit. This greatly helps super fast disks
* that would see slowdowns as more threads started doing fsyncs.
*
* But don't do this if this process was the most recent one to
* perform a synchronous write. We do this to detect the case where a
* single process is doing a stream of sync writes. No point in waiting
* for joiners in that case.
*/
pid = current->pid;
if (handle->h_sync && journal->j_last_sync_writer != pid) {
u64 commit_time, trans_time;
journal->j_last_sync_writer = pid;
spin_lock(&journal->j_state_lock);
commit_time = journal->j_average_commit_time;
spin_unlock(&journal->j_state_lock);
trans_time = ktime_to_ns(ktime_sub(ktime_get(),
transaction->t_start_time));
commit_time = min_t(u64, commit_time,
1000*jiffies_to_usecs(1));
if (trans_time < commit_time) {
ktime_t expires = ktime_add_ns(ktime_get(),
commit_time);
set_current_state(TASK_UNINTERRUPTIBLE);
schedule_hrtimeout(&expires, HRTIMER_MODE_ABS);
}
}
if (handle->h_sync)
transaction->t_synchronous_commit = 1;
current->journal_info = NULL;
spin_lock(&journal->j_state_lock);
spin_lock(&transaction->t_handle_lock);
transaction->t_outstanding_credits -= handle->h_buffer_credits;
transaction->t_updates--;
if (!transaction->t_updates) {
wake_up(&journal->j_wait_updates);
if (journal->j_barrier_count)
wake_up(&journal->j_wait_transaction_locked);
}
/*
* If the handle is marked SYNC, we need to set another commit
* going! We also want to force a commit if the current
* transaction is occupying too much of the log, or if the
* transaction is too old now.
*/
if (handle->h_sync ||
transaction->t_outstanding_credits >
journal->j_max_transaction_buffers ||
time_after_eq(jiffies, transaction->t_expires)) {
/* Do this even for aborted journals: an abort still
* completes the commit thread, it just doesn't write
* anything to disk. */
tid_t tid = transaction->t_tid;
spin_unlock(&transaction->t_handle_lock);
jbd_debug(2, "transaction too old, requesting commit for "
"handle %p\n", handle);
/* This is non-blocking */
__log_start_commit(journal, transaction->t_tid);
spin_unlock(&journal->j_state_lock);
/*
* Special case: JFS_SYNC synchronous updates require us
* to wait for the commit to complete.
*/
if (handle->h_sync && !(current->flags & PF_MEMALLOC))
err = log_wait_commit(journal, tid);
} else {
spin_unlock(&transaction->t_handle_lock);
spin_unlock(&journal->j_state_lock);
}
lock_map_release(&handle->h_lockdep_map);
jbd_free_handle(handle);
return err;
}
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;
}
/**
* 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(void)
{
unsigned long seq, last_jiffies, next_jiffies, delta_jiffies, flags;
struct tick_sched *ts;
ktime_t last_update, expires, now, delta;
int cpu;
local_irq_save(flags);
cpu = smp_processor_id();
ts = &per_cpu(tick_cpu_sched, cpu);
if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE))
goto end;
if (need_resched())
goto end;
cpu = smp_processor_id();
if (unlikely(local_softirq_pending()))
printk(KERN_ERR "NOHZ: local_softirq_pending %02x\n",
local_softirq_pending());
now = ktime_get();
/*
* When called from irq_exit we need to account the idle sleep time
* correctly.
*/
if (ts->tick_stopped) {
delta = ktime_sub(now, ts->idle_entrytime);
ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta);
}
ts->idle_entrytime = now;
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;
} while (read_seqretry(&xtime_lock, seq));
/* Get the next timer wheel timer */
next_jiffies = get_next_timer_interrupt(last_jiffies);
delta_jiffies = next_jiffies - last_jiffies;
if (rcu_needs_cpu(cpu))
delta_jiffies = 1;
/*
* 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) {
if (delta_jiffies > 1)
cpu_set(cpu, nohz_cpu_mask);
/*
* 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) {
ts->idle_tick = ts->sched_timer.expires;
ts->tick_stopped = 1;
ts->idle_jiffies = last_jiffies;
}
/*
* 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 = -1;
/*
* calculate the expiry time for the next timer wheel
* timer
*/
expires = ktime_add_ns(last_update, tick_period.tv64 *
delta_jiffies);
ts->idle_expires = expires;
ts->idle_sleeps++;
if (ts->nohz_mode == NOHZ_MODE_HIGHRES) {
hrtimer_start(&ts->sched_timer, expires,
HRTIMER_MODE_ABS);
/* 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());
cpu_clear(cpu, nohz_cpu_mask);
}
raise_softirq_irqoff(TIMER_SOFTIRQ);
out:
ts->next_jiffies = next_jiffies;
ts->last_jiffies = last_jiffies;
end:
local_irq_restore(flags);
}
static void tick_nohz_stop_sched_tick(struct tick_sched *ts)
{
unsigned long seq, last_jiffies, next_jiffies, 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 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))
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++;
/* Read jiffies and the time when jiffies were updated last */
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) || 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) {
/*
* 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. Keep track of the fact that it was the one
* which had the do_timer() duty last. If this cpu is
* the one which had the do_timer() duty last, we
* limit the sleep time to the timekeeping
* max_deferement value which we retrieved
* above. Otherwise we can sleep as long as we want.
*/
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;
}
/*
* 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);
}
if (time_delta < KTIME_MAX)
expires = ktime_add_ns(last_update, time_delta);
else
expires.tv64 = KTIME_MAX;
/* 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) {
select_nohz_load_balancer(1);
calc_load_enter_idle();
ts->idle_tick = hrtimer_get_expires(&ts->sched_timer);
ts->tick_stopped = 1;
ts->idle_jiffies = last_jiffies;
}
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());
}
raise_softirq_irqoff(TIMER_SOFTIRQ);
out:
ts->next_jiffies = next_jiffies;
ts->last_jiffies = last_jiffies;
}
void hrtimer_interrupt(struct clock_event_device *dev)
{
struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
ktime_t expires_next, now, entry_time, delta;
int i, retries = 0;
BUG_ON(!cpu_base->hres_active);
cpu_base->nr_events++;
dev->next_event.tv64 = KTIME_MAX;
raw_spin_lock(&cpu_base->lock);
entry_time = now = hrtimer_update_base(cpu_base);
retry:
expires_next.tv64 = KTIME_MAX;
cpu_base->expires_next.tv64 = KTIME_MAX;
for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
struct hrtimer_clock_base *base;
struct timerqueue_node *node;
ktime_t basenow;
if (!(cpu_base->active_bases & (1 << i)))
continue;
base = cpu_base->clock_base + i;
basenow = ktime_add(now, base->offset);
while ((node = timerqueue_getnext(&base->active))) {
struct hrtimer *timer;
timer = container_of(node, struct hrtimer, node);
if (basenow.tv64 < hrtimer_get_softexpires_tv64(timer)) {
ktime_t expires;
expires = ktime_sub(hrtimer_get_expires(timer),
base->offset);
if (expires.tv64 < expires_next.tv64)
expires_next = expires;
break;
}
__run_hrtimer(timer, &basenow);
}
}
cpu_base->expires_next = expires_next;
raw_spin_unlock(&cpu_base->lock);
if (expires_next.tv64 == KTIME_MAX ||
!tick_program_event(expires_next, 0)) {
cpu_base->hang_detected = 0;
return;
}
raw_spin_lock(&cpu_base->lock);
now = hrtimer_update_base(cpu_base);
cpu_base->nr_retries++;
if (++retries < 3)
goto retry;
cpu_base->nr_hangs++;
cpu_base->hang_detected = 1;
raw_spin_unlock(&cpu_base->lock);
delta = ktime_sub(now, entry_time);
if (delta.tv64 > cpu_base->max_hang_time.tv64)
cpu_base->max_hang_time = delta;
if (delta.tv64 > 100 * NSEC_PER_MSEC)
expires_next = ktime_add_ns(now, 100 * NSEC_PER_MSEC);
else
expires_next = ktime_add(now, delta);
tick_program_event(expires_next, 1);
printk_once(KERN_WARNING "hrtimer: interrupt took %llu ns\n",
ktime_to_ns(delta));
}
/* timer_arm: as in "arm the timer", not as in ARM the company */
static void timer_arm(struct arch_timer_cpu *timer, u64 ns)
{
timer->armed = true;
hrtimer_start(&timer->timer, ktime_add_ns(ktime_get(), ns),
HRTIMER_MODE_ABS);
}
tEplKernel PUBLIC EplTimerHighReskModifyTimerNs(tEplTimerHdl * pTimerHdl_p,
unsigned long long ullTimeNs_p,
tEplTimerkCallback
pfnCallback_p,
unsigned long ulArgument_p,
BOOL fContinuously_p)
{
tEplKernel Ret;
unsigned int uiIndex;
tEplTimerHighReskTimerInfo *pTimerInfo;
ktime_t RelTime;
Ret = kEplSuccessful;
// check pointer to handle
if (pTimerHdl_p == NULL) {
Ret = kEplTimerInvalidHandle;
goto Exit;
}
if (*pTimerHdl_p == 0) { // no timer created yet
// search free timer info structure
pTimerInfo = &EplTimerHighReskInstance_l.m_aTimerInfo[0];
for (uiIndex = 0; uiIndex < TIMER_COUNT;
uiIndex++, pTimerInfo++) {
if (pTimerInfo->m_EventArg.m_TimerHdl == 0) { // free structure found
break;
}
}
if (uiIndex >= TIMER_COUNT) { // no free structure found
Ret = kEplTimerNoTimerCreated;
goto Exit;
}
pTimerInfo->m_EventArg.m_TimerHdl = HDL_INIT(uiIndex);
} else {
uiIndex = HDL_TO_IDX(*pTimerHdl_p);
if (uiIndex >= TIMER_COUNT) { // invalid handle
Ret = kEplTimerInvalidHandle;
goto Exit;
}
pTimerInfo = &EplTimerHighReskInstance_l.m_aTimerInfo[uiIndex];
}
/*
* increment timer handle
* (if timer expires right after this statement, the user
* would detect an unknown timer handle and discard it)
*/
pTimerInfo->m_EventArg.m_TimerHdl =
HDL_INC(pTimerInfo->m_EventArg.m_TimerHdl);
*pTimerHdl_p = pTimerInfo->m_EventArg.m_TimerHdl;
// reject too small time values
if ((fContinuously_p && (ullTimeNs_p < TIMER_MIN_VAL_CYCLE))
|| (!fContinuously_p && (ullTimeNs_p < TIMER_MIN_VAL_SINGLE))) {
Ret = kEplTimerNoTimerCreated;
goto Exit;
}
pTimerInfo->m_EventArg.m_ulArg = ulArgument_p;
pTimerInfo->m_pfnCallback = pfnCallback_p;
pTimerInfo->m_fContinuously = fContinuously_p;
pTimerInfo->m_ullPeriod = ullTimeNs_p;
/*
* HRTIMER_MODE_REL does not influence general handling of this timer.
* It only sets relative mode for this start operation.
* -> Expire time is calculated by: Now + RelTime
* hrtimer_start also skips pending timer events.
* The state HRTIMER_STATE_CALLBACK is ignored.
* We have to cope with that in our callback function.
*/
RelTime = ktime_add_ns(ktime_set(0, 0), ullTimeNs_p);
hrtimer_start(&pTimerInfo->m_Timer, RelTime, HRTIMER_MODE_REL);
Exit:
return Ret;
}
/*
* High resolution timer interrupt
* Called with interrupts disabled
*/
void hrtimer_interrupt(struct clock_event_device *dev)
{
struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
ktime_t expires_next, now, entry_time, delta;
int retries = 0;
BUG_ON(!cpu_base->hres_active);
cpu_base->nr_events++;
dev->next_event.tv64 = KTIME_MAX;
raw_spin_lock(&cpu_base->lock);
entry_time = now = hrtimer_update_base(cpu_base);
retry:
cpu_base->in_hrtirq = 1;
/*
* We set expires_next to KTIME_MAX here with cpu_base->lock
* held to prevent that a timer is enqueued in our queue via
* the migration code. This does not affect enqueueing of
* timers which run their callback and need to be requeued on
* this CPU.
*/
cpu_base->expires_next.tv64 = KTIME_MAX;
__hrtimer_run_queues(cpu_base, now);
/* Reevaluate the clock bases for the next expiry */
expires_next = __hrtimer_get_next_event(cpu_base);
/*
* Store the new expiry value so the migration code can verify
* against it.
*/
cpu_base->expires_next = expires_next;
cpu_base->in_hrtirq = 0;
raw_spin_unlock(&cpu_base->lock);
/* Reprogramming necessary ? */
if (!tick_program_event(expires_next, 0)) {
cpu_base->hang_detected = 0;
return;
}
/*
* The next timer was already expired due to:
* - tracing
* - long lasting callbacks
* - being scheduled away when running in a VM
*
* We need to prevent that we loop forever in the hrtimer
* interrupt routine. We give it 3 attempts to avoid
* overreacting on some spurious event.
*
* Acquire base lock for updating the offsets and retrieving
* the current time.
*/
raw_spin_lock(&cpu_base->lock);
now = hrtimer_update_base(cpu_base);
cpu_base->nr_retries++;
if (++retries < 3)
goto retry;
/*
* Give the system a chance to do something else than looping
* here. We stored the entry time, so we know exactly how long
* we spent here. We schedule the next event this amount of
* time away.
*/
cpu_base->nr_hangs++;
cpu_base->hang_detected = 1;
raw_spin_unlock(&cpu_base->lock);
delta = ktime_sub(now, entry_time);
if ((unsigned int)delta.tv64 > cpu_base->max_hang_time)
cpu_base->max_hang_time = (unsigned int) delta.tv64;
/*
* Limit it to a sensible value as we enforce a longer
* delay. Give the CPU at least 100ms to catch up.
*/
if (delta.tv64 > 100 * NSEC_PER_MSEC)
expires_next = ktime_add_ns(now, 100 * NSEC_PER_MSEC);
else
expires_next = ktime_add(now, delta);
tick_program_event(expires_next, 1);
printk_once(KERN_WARNING "hrtimer: interrupt took %llu ns\n",
ktime_to_ns(delta));
}
static void midi_port_work(struct work_struct *work)
{
struct snd_fw_async_midi_port *port =
container_of(work, struct snd_fw_async_midi_port, work);
struct snd_rawmidi_substream *substream = ACCESS_ONCE(port->substream);
int generation;
int type;
/* Under transacting or error state. */
if (!port->idling || port->error)
return;
/* Nothing to do. */
if (substream == NULL || snd_rawmidi_transmit_empty(substream))
return;
/* Do it in next chance. */
if (ktime_after(port->next_ktime, ktime_get())) {
schedule_work(&port->work);
return;
}
/*
* Fill the buffer. The callee must use snd_rawmidi_transmit_peek().
* Later, snd_rawmidi_transmit_ack() is called.
*/
memset(port->buf, 0, port->len);
port->consume_bytes = port->fill(substream, port->buf);
if (port->consume_bytes <= 0) {
/* Do it in next chance, immediately. */
if (port->consume_bytes == 0) {
port->next_ktime = ktime_set(0, 0);
schedule_work(&port->work);
} else {
/* Fatal error. */
port->error = true;
}
return;
}
/* Calculate type of transaction. */
if (port->len == 4)
type = TCODE_WRITE_QUADLET_REQUEST;
else
type = TCODE_WRITE_BLOCK_REQUEST;
/* Set interval to next transaction. */
port->next_ktime = ktime_add_ns(ktime_get(),
port->consume_bytes * 8 * NSEC_PER_SEC / 31250);
/* Start this transaction. */
port->idling = false;
/*
* In Linux FireWire core, when generation is updated with memory
* barrier, node id has already been updated. In this module, After
* this smp_rmb(), load/store instructions to memory are completed.
* Thus, both of generation and node id are available with recent
* values. This is a light-serialization solution to handle bus reset
* events on IEEE 1394 bus.
*/
generation = port->parent->generation;
smp_rmb();
fw_send_request(port->parent->card, &port->transaction, type,
port->parent->node_id, generation,
port->parent->max_speed, port->addr,
port->buf, port->len, async_midi_port_callback,
port);
}
static int lowmem_shrink(struct shrinker *s, struct shrink_control *sc)
{
static DEFINE_SPINLOCK(lowmem_lock);
struct task_struct *tsk;
struct task_struct *selected = NULL;
int rem = 0;
static int same_count;
static int busy_count;
static int busy_count_dropped;
static int oldpid;
static int lastpid;
static ktime_t next_busy_print;
int tasksize;
int i;
int min_score_adj = OOM_SCORE_ADJ_MAX + 1;
int selected_tasksize = 0;
int selected_oom_score_adj;
int array_size = ARRAY_SIZE(lowmem_adj);
int other_free;
int other_file;
unsigned long nr_to_scan = sc->nr_to_scan;
if (nr_to_scan > 0) {
if (mutex_lock_interruptible(&scan_mutex) < 0)
return 0;
}
other_free = global_page_state(NR_FREE_PAGES);
other_file = global_page_state(NR_FILE_PAGES) -
global_page_state(NR_FILE_MAPPED);
tune_lmk_param(&other_free, &other_file, sc);
if (lowmem_adj_size < array_size)
array_size = lowmem_adj_size;
if (lowmem_minfree_size < array_size)
array_size = lowmem_minfree_size;
for (i = 0; i < array_size; i++) {
if (other_free < lowmem_minfree[i] &&
other_file < lowmem_minfree[i]) {
min_score_adj = lowmem_adj[i];
break;
}
}
if (nr_to_scan > 0)
lowmem_print(3, "lowmem_shrink %lu, %x, ofree %d %d, ma %d\n",
nr_to_scan, sc->gfp_mask, other_free,
other_file, min_score_adj);
rem = global_page_state(NR_ACTIVE_ANON) +
global_page_state(NR_ACTIVE_FILE) +
global_page_state(NR_INACTIVE_ANON) +
global_page_state(NR_INACTIVE_FILE);
if (nr_to_scan <= 0 || min_score_adj == OOM_SCORE_ADJ_MAX + 1) {
lowmem_print(5, "lowmem_shrink %lu, %x, return %d\n",
nr_to_scan, sc->gfp_mask, rem);
if (nr_to_scan > 0)
mutex_unlock(&scan_mutex);
return rem;
}
selected_oom_score_adj = min_score_adj;
if (spin_trylock(&lowmem_lock) == 0) {
if (ktime_us_delta(ktime_get(), next_busy_print) > 0) {
lowmem_print(2, "Lowmemkiller busy %d %d %d\n",
busy_count, busy_count_dropped,
oom_killer_disabled);
next_busy_print = ktime_add(ktime_get(),
ktime_set(5, 0));
busy_count_dropped = 0;
}
busy_count++;
busy_count_dropped++;
mutex_unlock(&scan_mutex);
return LMK_BUSY;
}
rcu_read_lock();
for_each_process(tsk) {
struct task_struct *p;
int oom_score_adj;
if (tsk->flags & PF_KTHREAD)
continue;
/* if task no longer has any memory ignore it */
if (test_task_flag(tsk, TIF_MM_RELEASED))
continue;
if (ktime_us_delta(ktime_get(), lowmem_deathpending_timeout) < 0
&& (test_task_flag(tsk, TIF_MEMDIE))) {
same_count++;
if (tsk->pid != oldpid || same_count > 1000) {
lowmem_print(1, "terminate loop for %d (%s)" \
"old:%d last:%d %ld %d\n",
tsk->pid,
tsk->comm,
oldpid,
lastpid,
(long)ktime_us_delta(
ktime_get(),
lowmem_deathpending_timeout),
same_count);
lowmem_print(2,
"state:%ld flag:0x%x la:%lld " \
"busy: %d %d\n",
tsk->state,
tsk->flags,
tsk->sched_info.last_arrival,
busy_count,
oom_killer_disabled);
oldpid = tsk->pid;
same_count = 0;
}
rcu_read_unlock();
spin_unlock(&lowmem_lock);
mutex_unlock(&scan_mutex);
/* wait one jiffie */
schedule_timeout(1);
return LMK_BUSY;
}
p = find_lock_task_mm(tsk);
if (!p)
continue;
oom_score_adj = p->signal->oom_score_adj;
if (oom_score_adj < min_score_adj) {
task_unlock(p);
continue;
}
tasksize = get_mm_rss(p->mm);
task_unlock(p);
if (tasksize <= 0)
continue;
if (selected) {
if (oom_score_adj < selected_oom_score_adj)
continue;
if (oom_score_adj == selected_oom_score_adj &&
tasksize <= selected_tasksize)
continue;
}
selected = p;
selected_tasksize = tasksize;
selected_oom_score_adj = oom_score_adj;
lowmem_print(4, "select %d (%s), adj %d, size %d, to kill\n",
p->pid, p->comm, oom_score_adj, tasksize);
}
if (selected) {
lowmem_print(1, "send sigkill to %d (%s), adj %d, size %d\n",
selected->pid, selected->comm,
selected_oom_score_adj, selected_tasksize);
send_sig(SIGKILL, selected, 0);
lowmem_deathpending_timeout = ktime_add_ns(ktime_get(),
NSEC_PER_SEC/2);
lowmem_print(2, "state:%ld flag:0x%x la:%lld busy:%d %d\n",
selected->state, selected->flags,
selected->sched_info.last_arrival,
busy_count, oom_killer_disabled);
lastpid = selected->pid;
set_tsk_thread_flag(selected, TIF_MEMDIE);
rem -= selected_tasksize;
}
rcu_read_unlock();
lowmem_print(4, "lowmem_shrink %lu, %x, return %d\n",
nr_to_scan, sc->gfp_mask, rem);
spin_unlock(&lowmem_lock);
mutex_unlock(&scan_mutex);
return rem;
}
/**
* 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_journal_stop(handle_t *handle)
{
transaction_t *transaction = handle->h_transaction;
journal_t *journal = transaction->t_journal;
int err, wait_for_commit = 0;
tid_t tid;
pid_t pid;
J_ASSERT(journal_current_handle() == handle);
if (is_handle_aborted(handle))
err = -EIO;
else {
J_ASSERT(atomic_read(&transaction->t_updates) > 0);
err = 0;
}
if (--handle->h_ref > 0) {
jbd_debug(4, "h_ref %d -> %d\n", handle->h_ref + 1,
handle->h_ref);
return err;
}
jbd_debug(4, "Handle %p going down\n", handle);
pid = current->pid;
if (handle->h_sync && journal->j_last_sync_writer != pid) {
u64 commit_time, trans_time;
journal->j_last_sync_writer = pid;
read_lock(&journal->j_state_lock);
commit_time = journal->j_average_commit_time;
read_unlock(&journal->j_state_lock);
trans_time = ktime_to_ns(ktime_sub(ktime_get(),
transaction->t_start_time));
commit_time = max_t(u64, commit_time,
1000*journal->j_min_batch_time);
commit_time = min_t(u64, commit_time,
1000*journal->j_max_batch_time);
if (trans_time < commit_time) {
ktime_t expires = ktime_add_ns(ktime_get(),
commit_time);
set_current_state(TASK_UNINTERRUPTIBLE);
schedule_hrtimeout(&expires, HRTIMER_MODE_ABS);
}
}
if (handle->h_sync)
transaction->t_synchronous_commit = 1;
current->journal_info = NULL;
atomic_sub(handle->h_buffer_credits,
&transaction->t_outstanding_credits);
if (handle->h_sync ||
(atomic_read(&transaction->t_outstanding_credits) >
journal->j_max_transaction_buffers) ||
time_after_eq(jiffies, transaction->t_expires)) {
jbd_debug(2, "transaction too old, requesting commit for "
"handle %p\n", handle);
jbd2_log_start_commit(journal, transaction->t_tid);
if (handle->h_sync && !(current->flags & PF_MEMALLOC))
wait_for_commit = 1;
}
tid = transaction->t_tid;
if (atomic_dec_and_test(&transaction->t_updates)) {
wake_up(&journal->j_wait_updates);
if (journal->j_barrier_count)
wake_up(&journal->j_wait_transaction_locked);
}
if (wait_for_commit)
err = jbd2_log_wait_commit(journal, tid);
lock_map_release(&handle->h_lockdep_map);
jbd2_free_handle(handle);
return err;
}
/*
* High resolution timer interrupt
* Called with interrupts disabled
*/
void hrtimer_interrupt(struct clock_event_device *dev)
{
struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
ktime_t expires_next, now, entry_time, delta;
int i, retries = 0;
BUG_ON(!cpu_base->hres_active);
cpu_base->nr_events++;
dev->next_event.tv64 = KTIME_MAX;
raw_spin_lock(&cpu_base->lock);
entry_time = now = hrtimer_update_base(cpu_base);
retry:
expires_next.tv64 = KTIME_MAX;
/*
* We set expires_next to KTIME_MAX here with cpu_base->lock
* held to prevent that a timer is enqueued in our queue via
* the migration code. This does not affect enqueueing of
* timers which run their callback and need to be requeued on
* this CPU.
*/
cpu_base->expires_next.tv64 = KTIME_MAX;
for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
struct hrtimer_clock_base *base;
struct timerqueue_node *node;
ktime_t basenow;
if (!(cpu_base->active_bases & (1 << i)))
continue;
base = cpu_base->clock_base + i;
basenow = ktime_add(now, base->offset);
while ((node = timerqueue_getnext(&base->active))) {
struct hrtimer *timer;
timer = container_of(node, struct hrtimer, node);
/*
* The immediate goal for using the softexpires is
* minimizing wakeups, not running timers at the
* earliest interrupt after their soft expiration.
* This allows us to avoid using a Priority Search
* Tree, which can answer a stabbing querry for
* overlapping intervals and instead use the simple
* BST we already have.
* We don't add extra wakeups by delaying timers that
* are right-of a not yet expired timer, because that
* timer will have to trigger a wakeup anyway.
*/
if (basenow.tv64 < hrtimer_get_softexpires_tv64(timer)) {
ktime_t expires;
expires = ktime_sub(hrtimer_get_expires(timer),
base->offset);
if (expires.tv64 < 0)
expires.tv64 = KTIME_MAX;
if (expires.tv64 < expires_next.tv64)
expires_next = expires;
break;
}
__run_hrtimer(timer, &basenow);
}
}
/*
* Store the new expiry value so the migration code can verify
* against it.
*/
cpu_base->expires_next = expires_next;
raw_spin_unlock(&cpu_base->lock);
/* Reprogramming necessary ? */
if (expires_next.tv64 == KTIME_MAX ||
!tick_program_event(expires_next, 0)) {
cpu_base->hang_detected = 0;
return;
}
/*
* The next timer was already expired due to:
* - tracing
* - long lasting callbacks
* - being scheduled away when running in a VM
*
* We need to prevent that we loop forever in the hrtimer
* interrupt routine. We give it 3 attempts to avoid
* overreacting on some spurious event.
*
* Acquire base lock for updating the offsets and retrieving
* the current time.
*/
raw_spin_lock(&cpu_base->lock);
now = hrtimer_update_base(cpu_base);
cpu_base->nr_retries++;
if (++retries < 3)
goto retry;
/*
* Give the system a chance to do something else than looping
* here. We stored the entry time, so we know exactly how long
* we spent here. We schedule the next event this amount of
* time away.
*/
cpu_base->nr_hangs++;
cpu_base->hang_detected = 1;
raw_spin_unlock(&cpu_base->lock);
delta = ktime_sub(now, entry_time);
if (delta.tv64 > cpu_base->max_hang_time.tv64)
cpu_base->max_hang_time = delta;
/*
* Limit it to a sensible value as we enforce a longer
* delay. Give the CPU at least 100ms to catch up.
*/
if (delta.tv64 > 100 * NSEC_PER_MSEC)
expires_next = ktime_add_ns(now, 100 * NSEC_PER_MSEC);
else
expires_next = ktime_add(now, delta);
tick_program_event(expires_next, 1);
printk_once(KERN_WARNING "hrtimer: interrupt took %llu ns\n",
ktime_to_ns(delta));
}
static int lowmem_shrink(struct shrinker *s, struct shrink_control *sc)
{
static DEFINE_SPINLOCK(lowmem_lock);
struct task_struct *tsk;
struct task_struct *selected = NULL;
int rem = 0;
static int same_count;
static int busy_count;
static int busy_count_dropped;
static int oldpid;
static int lastpid;
static ktime_t next_busy_print;
int tasksize;
int i;
int min_score_adj = OOM_SCORE_ADJ_MAX + 1;
int selected_tasksize = 0;
int selected_oom_score_adj;
int array_size = ARRAY_SIZE(lowmem_adj);
int other_free = global_page_state(NR_FREE_PAGES);
int other_file = global_page_state(NR_FILE_PAGES) -
global_page_state(NR_FILE_MAPPED);
if (lowmem_adj_size < array_size)
array_size = lowmem_adj_size;
if (lowmem_minfree_size < array_size)
array_size = lowmem_minfree_size;
for (i = 0; i < array_size; i++) {
/*
* Convert lowmem_minfree[i] to signed to avoid that other_free
* and/or other_file are converted to unsigned.
*
*/
if (other_free < (int) lowmem_minfree[i] &&
other_file < (int) lowmem_minfree[i]) {
min_score_adj = lowmem_adj[i];
break;
}
}
if (sc->nr_to_scan > 0)
lowmem_print(3, "lowmem_shrink %lu, %x, ofree %d %d (%lu %lu), ma %d\n",
sc->nr_to_scan, sc->gfp_mask, other_free,
other_file,
global_page_state(NR_FILE_PAGES),
global_page_state(NR_FILE_MAPPED),
min_score_adj);
rem = global_page_state(NR_ACTIVE_ANON) +
global_page_state(NR_ACTIVE_FILE) +
global_page_state(NR_INACTIVE_ANON) +
global_page_state(NR_INACTIVE_FILE);
if (sc->nr_to_scan <= 0 || min_score_adj == OOM_SCORE_ADJ_MAX + 1) {
lowmem_print(5, "lowmem_shrink %lu, %x, return %d\n",
sc->nr_to_scan, sc->gfp_mask, rem);
return rem;
}
selected_oom_score_adj = min_score_adj;
if (spin_trylock(&lowmem_lock) == 0) {
if (ktime_us_delta(ktime_get(), next_busy_print) > 0) {
lowmem_print(2, "Lowmemkiller busy %d %d %d\n",
busy_count, busy_count_dropped,
oom_killer_disabled);
next_busy_print = ktime_add(ktime_get(),
ktime_set(5, 0));
busy_count_dropped = 0;
}
busy_count++;
busy_count_dropped++;
return LMK_BUSY;
}
/* turn of scheduling to protect task list */
rcu_read_lock();
for_each_process(tsk) {
struct task_struct *p;
int oom_score_adj;
if (tsk->flags & PF_KTHREAD)
continue;
p = find_lock_task_mm(tsk);
if (!p)
continue;
if (test_tsk_thread_flag(p, TIF_MEMDIE) &&
ktime_us_delta(ktime_get(),
lowmem_deathpending_timeout) < 0) {
task_unlock(p);
same_count++;
if (p->pid != oldpid || same_count > 1000) {
lowmem_print(1,
"terminate %d (%s) old:%d last:%d %ld %d\n",
p->pid, p->comm, oldpid, lastpid,
(long)ktime_us_delta(ktime_get(),
lowmem_deathpending_timeout),
same_count);
lowmem_print(2,
"state:%ld flag:0x%x la:%lld busy:%d %d\n",
p->state, p->flags,
p->sched_info.last_arrival,
busy_count, oom_killer_disabled);
oldpid = p->pid;
same_count = 0;
}
rcu_read_unlock();
spin_unlock(&lowmem_lock);
/* wait one jiffie */
schedule_timeout(1);
return LMK_BUSY;
}
oom_score_adj = p->signal->oom_score_adj;
if (oom_score_adj < min_score_adj) {
task_unlock(p);
continue;
}
tasksize = get_mm_rss(p->mm);
task_unlock(p);
if (tasksize <= 0)
continue;
if (selected) {
if (oom_score_adj < selected_oom_score_adj)
continue;
if (oom_score_adj == selected_oom_score_adj &&
tasksize <= selected_tasksize)
continue;
}
selected = p;
selected_tasksize = tasksize;
selected_oom_score_adj = oom_score_adj;
lowmem_print(4, "select %d (%s), adj %d, size %d, to kill\n",
p->pid, p->comm, oom_score_adj, tasksize);
}
if (selected) {
lowmem_print(1, "send sigkill to %d (%s), adj %d,\n"
" to free %ldkB on behalf of '%s' (%d) because\n"
" cache %ldkB is below limit %ldkB for oom_score_adj %d\n"
" Free memory is %ldkB above reserved\n",
selected->pid, selected->comm,
selected_oom_score_adj,
selected_tasksize * (long)(PAGE_SIZE / 1024),
current->comm, current->pid,
other_file * (long)(PAGE_SIZE / 1024),
lowmem_minfree[i] * (long)(PAGE_SIZE / 1024),
min_score_adj,
other_free * (long)(PAGE_SIZE / 1024));
send_sig(SIGKILL, selected, 0);
lowmem_deathpending_timeout = ktime_add_ns(ktime_get(),
NSEC_PER_SEC/2);
lowmem_print(2, "state:%ld flag:0x%x la:%lld busy:%d %d\n",
selected->state, selected->flags,
selected->sched_info.last_arrival,
busy_count, oom_killer_disabled);
lastpid = selected->pid;
set_tsk_thread_flag(selected, TIF_MEMDIE);
rem -= selected_tasksize;
}
lowmem_print(4, "lowmem_shrink %lu, %x, return %d\n",
sc->nr_to_scan, sc->gfp_mask, rem);
rcu_read_unlock();
spin_unlock(&lowmem_lock);
return rem;
}
