static void __run_hrtimer(struct hrtimer_cpu_base *cpu_base,
struct hrtimer_clock_base *base,
struct hrtimer *timer, ktime_t *now)
{
enum hrtimer_restart (*fn)(struct hrtimer *);
int restart;
lockdep_assert_held(&cpu_base->lock);
debug_deactivate(timer);
cpu_base->running = timer;
/*
* Separate the ->running assignment from the ->state assignment.
*
* As with a regular write barrier, this ensures the read side in
* hrtimer_active() cannot observe cpu_base->running == NULL &&
* timer->state == INACTIVE.
*/
raw_write_seqcount_barrier(&cpu_base->seq);
__remove_hrtimer(timer, base, HRTIMER_STATE_INACTIVE, 0);
fn = timer->function;
/*
* Clear the 'is relative' flag for the TIME_LOW_RES case. If the
* timer is restarted with a period then it becomes an absolute
* timer. If its not restarted it does not matter.
*/
if (IS_ENABLED(CONFIG_TIME_LOW_RES))
timer->is_rel = false;
/*
* Because we run timers from hardirq context, there is no chance
* they get migrated to another cpu, therefore its safe to unlock
* the timer base.
*/
raw_spin_unlock(&cpu_base->lock);
trace_hrtimer_expire_entry(timer, now);
restart = fn(timer);
trace_hrtimer_expire_exit(timer);
raw_spin_lock(&cpu_base->lock);
/*
* Note: We clear the running state after enqueue_hrtimer and
* we do not reprogram the event hardware. Happens either in
* hrtimer_start_range_ns() or in hrtimer_interrupt()
*
* Note: Because we dropped the cpu_base->lock above,
* hrtimer_start_range_ns() can have popped in and enqueued the timer
* for us already.
*/
if (restart != HRTIMER_NORESTART &&
!(timer->state & HRTIMER_STATE_ENQUEUED))
enqueue_hrtimer(timer, base);
/*
* Separate the ->running assignment from the ->state assignment.
*
* As with a regular write barrier, this ensures the read side in
* hrtimer_active() cannot observe cpu_base->running == NULL &&
* timer->state == INACTIVE.
*/
raw_write_seqcount_barrier(&cpu_base->seq);
WARN_ON_ONCE(cpu_base->running != timer);
cpu_base->running = NULL;
}
/* A cpu has been removed from cpu_online_mask. Reset irq affinities. */
void fixup_irqs(void)
{
unsigned int irq, vector;
static int warned;
struct irq_desc *desc;
struct irq_data *data;
struct irq_chip *chip;
for_each_irq_desc(irq, desc) {
int break_affinity = 0;
int set_affinity = 1;
const struct cpumask *affinity;
if (!desc)
continue;
if (irq == 2)
continue;
/* interrupt's are disabled at this point */
raw_spin_lock(&desc->lock);
data = irq_desc_get_irq_data(desc);
affinity = data->affinity;
if (!irq_has_action(irq) || irqd_is_per_cpu(data) ||
cpumask_subset(affinity, cpu_online_mask)) {
raw_spin_unlock(&desc->lock);
continue;
}
/*
* Complete the irq move. This cpu is going down and for
* non intr-remapping case, we can't wait till this interrupt
* arrives at this cpu before completing the irq move.
*/
irq_force_complete_move(irq);
if (cpumask_any_and(affinity, cpu_online_mask) >= nr_cpu_ids) {
break_affinity = 1;
affinity = cpu_all_mask;
}
chip = irq_data_get_irq_chip(data);
if (!irqd_can_move_in_process_context(data) && chip->irq_mask)
chip->irq_mask(data);
if (chip->irq_set_affinity)
chip->irq_set_affinity(data, affinity, true);
else if (!(warned++))
set_affinity = 0;
if (!irqd_can_move_in_process_context(data) &&
!irqd_irq_disabled(data) && chip->irq_unmask)
chip->irq_unmask(data);
raw_spin_unlock(&desc->lock);
if (break_affinity && set_affinity)
printk("Broke affinity for irq %i\n", irq);
else if (!set_affinity)
printk("Cannot set affinity for irq %i\n", irq);
}
void switch_mmu_context(struct mm_struct *prev, struct mm_struct *next)
{
unsigned int i, id, cpu = smp_processor_id();
unsigned long *map;
/* No lockless fast path .. yet */
raw_spin_lock(&context_lock);
pr_hard("[%d] activating context for mm @%p, active=%d, id=%d",
cpu, next, next->context.active, next->context.id);
#ifdef CONFIG_SMP
/* Mark us active and the previous one not anymore */
next->context.active++;
if (prev) {
pr_hardcont(" (old=0x%p a=%d)", prev, prev->context.active);
WARN_ON(prev->context.active < 1);
prev->context.active--;
}
again:
#endif /* CONFIG_SMP */
/* If we already have a valid assigned context, skip all that */
id = next->context.id;
if (likely(id != MMU_NO_CONTEXT)) {
#ifdef DEBUG_MAP_CONSISTENCY
if (context_mm[id] != next)
pr_err("MMU: mm 0x%p has id %d but context_mm[%d] says 0x%p\n",
next, id, id, context_mm[id]);
#endif
goto ctxt_ok;
}
/* We really don't have a context, let's try to acquire one */
id = next_context;
if (id > last_context)
id = first_context;
map = context_map;
/* No more free contexts, let's try to steal one */
if (nr_free_contexts == 0) {
#ifdef CONFIG_SMP
if (num_online_cpus() > 1) {
id = steal_context_smp(id);
if (id == MMU_NO_CONTEXT)
goto again;
goto stolen;
}
#endif /* CONFIG_SMP */
id = steal_context_up(id);
goto stolen;
}
nr_free_contexts--;
/* We know there's at least one free context, try to find it */
while (__test_and_set_bit(id, map)) {
id = find_next_zero_bit(map, last_context+1, id);
if (id > last_context)
id = first_context;
}
stolen:
next_context = id + 1;
context_mm[id] = next;
next->context.id = id;
pr_hardcont(" | new id=%d,nrf=%d", id, nr_free_contexts);
context_check_map();
ctxt_ok:
/* If that context got marked stale on this CPU, then flush the
* local TLB for it and unmark it before we use it
*/
if (test_bit(id, stale_map[cpu])) {
pr_hardcont(" | stale flush %d [%d..%d]",
id, cpu_first_thread_in_core(cpu),
cpu_last_thread_in_core(cpu));
local_flush_tlb_mm(next);
/* XXX This clear should ultimately be part of local_flush_tlb_mm */
for (i = cpu_first_thread_in_core(cpu);
i <= cpu_last_thread_in_core(cpu); i++) {
__clear_bit(id, stale_map[i]);
}
}
/* Flick the MMU and release lock */
pr_hardcont(" -> %d\n", id);
set_context(id, next->pgd);
raw_spin_unlock(&context_lock);
}
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));
}
/**
* acpi_idle_enter_bm - enters C3 with proper BM handling
* @dev: the target CPU
* @index: the index of suggested state
*
* If BM is detected, the deepest non-C3 idle state is entered instead.
*/
static int acpi_idle_enter_bm(struct cpuidle_device *dev, int index)
{
struct acpi_processor *pr;
struct cpuidle_state_usage *state_usage = &dev->states_usage[index];
struct acpi_processor_cx *cx = cpuidle_get_statedata(state_usage);
ktime_t kt1, kt2;
s64 idle_time_ns;
s64 idle_time;
pr = __this_cpu_read(processors);
dev->last_residency = 0;
if (unlikely(!pr))
return -EINVAL;
if (!cx->bm_sts_skip && acpi_idle_bm_check()) {
if (dev->safe_state_index >= 0) {
return dev->states[dev->safe_state_index].enter(dev,
dev->safe_state_index);
} else {
local_irq_disable();
acpi_safe_halt();
local_irq_enable();
return -EINVAL;
}
}
local_irq_disable();
if (cx->entry_method != ACPI_CSTATE_FFH) {
current_thread_info()->status &= ~TS_POLLING;
/*
* TS_POLLING-cleared state must be visible before we test
* NEED_RESCHED:
*/
smp_mb();
if (unlikely(need_resched())) {
current_thread_info()->status |= TS_POLLING;
local_irq_enable();
return -EINVAL;
}
}
acpi_unlazy_tlb(smp_processor_id());
/* Tell the scheduler that we are going deep-idle: */
sched_clock_idle_sleep_event();
/*
* Must be done before busmaster disable as we might need to
* access HPET !
*/
lapic_timer_state_broadcast(pr, cx, 1);
kt1 = ktime_get_real();
/*
* disable bus master
* bm_check implies we need ARB_DIS
* !bm_check implies we need cache flush
* bm_control implies whether we can do ARB_DIS
*
* That leaves a case where bm_check is set and bm_control is
* not set. In that case we cannot do much, we enter C3
* without doing anything.
*/
if (pr->flags.bm_check && pr->flags.bm_control) {
raw_spin_lock(&c3_lock);
c3_cpu_count++;
/* Disable bus master arbitration when all CPUs are in C3 */
if (c3_cpu_count == num_online_cpus())
acpi_write_bit_register(ACPI_BITREG_ARB_DISABLE, 1);
raw_spin_unlock(&c3_lock);
} else if (!pr->flags.bm_check) {
ACPI_FLUSH_CPU_CACHE();
}
acpi_idle_do_entry(cx);
/* Re-enable bus master arbitration */
if (pr->flags.bm_check && pr->flags.bm_control) {
raw_spin_lock(&c3_lock);
acpi_write_bit_register(ACPI_BITREG_ARB_DISABLE, 0);
c3_cpu_count--;
raw_spin_unlock(&c3_lock);
}
kt2 = ktime_get_real();
idle_time_ns = ktime_to_ns(ktime_sub(kt2, kt1));
idle_time = idle_time_ns;
do_div(idle_time, NSEC_PER_USEC);
/* Update device last_residency*/
dev->last_residency = (int)idle_time;
/* Tell the scheduler how much we idled: */
sched_clock_idle_wakeup_event(idle_time_ns);
local_irq_enable();
if (cx->entry_method != ACPI_CSTATE_FFH)
current_thread_info()->status |= TS_POLLING;
cx->usage++;
lapic_timer_state_broadcast(pr, cx, 0);
cx->time += idle_time;
return index;
}
asmlinkage int vprintk(const char *fmt, va_list args)
{
int printed_len = 0;
int current_log_level = default_message_loglevel;
unsigned long flags;
int this_cpu;
char *p;
boot_delay_msec();
printk_delay();
preempt_disable();
/* This stops the holder of console_mutex just where we want him */
raw_local_irq_save(flags);
this_cpu = raw_smp_processor_id();
/*
* Ouch, printk recursed into itself!
*/
if (unlikely(printk_cpu == this_cpu)) {
/*
* If a crash is occurring during printk() on this CPU,
* then try to get the crash message out but make sure
* we can't deadlock. Otherwise just return to avoid the
* recursion and return - but flag the recursion so that
* it can be printed at the next appropriate moment:
*/
if (!oops_in_progress) {
recursion_bug = 1;
goto out;
}
zap_locks();
}
lockdep_off();
raw_spin_lock(&logbuf_lock);
printk_cpu = this_cpu;
preempt_enable();
if (recursion_bug) {
recursion_bug = 0;
strcpy(printk_buf, recursion_bug_msg);
printed_len = strlen(recursion_bug_msg);
}
/* Emit the output into the temporary buffer */
printed_len += vscnprintf(printk_buf + printed_len,
sizeof(printk_buf) - printed_len, fmt, args);
p = printk_buf;
/* Do we have a loglevel in the string? */
if (p[0] == '<') {
unsigned char c = p[1];
if (c && p[2] == '>') {
switch (c) {
case '0' ... '7': /* loglevel */
current_log_level = c - '0';
/* Fallthrough - make sure we're on a new line */
case 'd': /* KERN_DEFAULT */
if (!new_text_line) {
emit_log_char('\n');
new_text_line = 1;
}
/* Fallthrough - skip the loglevel */
case 'c': /* KERN_CONT */
p += 3;
break;
}
}
}
/**
* acpi_idle_enter_bm - enters C3 with proper BM handling
* @dev: the target CPU
* @drv: cpuidle driver containing state data
* @index: the index of suggested state
*
* If BM is detected, the deepest non-C3 idle state is entered instead.
*/
static int acpi_idle_enter_bm(struct cpuidle_device *dev,
struct cpuidle_driver *drv, int index)
{
struct acpi_processor *pr;
struct acpi_processor_cx *cx = per_cpu(acpi_cstate[index], dev->cpu);
pr = __this_cpu_read(processors);
if (unlikely(!pr))
return -EINVAL;
if (!cx->bm_sts_skip && acpi_idle_bm_check()) {
if (drv->safe_state_index >= 0) {
return drv->states[drv->safe_state_index].enter(dev,
drv, drv->safe_state_index);
} else {
acpi_safe_halt();
return -EBUSY;
}
}
if (cx->entry_method == ACPI_CSTATE_FFH) {
if (current_set_polling_and_test())
return -EINVAL;
}
acpi_unlazy_tlb(smp_processor_id());
/* Tell the scheduler that we are going deep-idle: */
sched_clock_idle_sleep_event();
/*
* Must be done before busmaster disable as we might need to
* access HPET !
*/
lapic_timer_state_broadcast(pr, cx, 1);
/*
* disable bus master
* bm_check implies we need ARB_DIS
* !bm_check implies we need cache flush
* bm_control implies whether we can do ARB_DIS
*
* That leaves a case where bm_check is set and bm_control is
* not set. In that case we cannot do much, we enter C3
* without doing anything.
*/
if (pr->flags.bm_check && pr->flags.bm_control) {
raw_spin_lock(&c3_lock);
c3_cpu_count++;
/* Disable bus master arbitration when all CPUs are in C3 */
if (c3_cpu_count == num_online_cpus())
acpi_write_bit_register(ACPI_BITREG_ARB_DISABLE, 1);
raw_spin_unlock(&c3_lock);
} else if (!pr->flags.bm_check) {
ACPI_FLUSH_CPU_CACHE();
}
acpi_idle_do_entry(cx);
/* Re-enable bus master arbitration */
if (pr->flags.bm_check && pr->flags.bm_control) {
raw_spin_lock(&c3_lock);
acpi_write_bit_register(ACPI_BITREG_ARB_DISABLE, 0);
c3_cpu_count--;
raw_spin_unlock(&c3_lock);
}
sched_clock_idle_wakeup_event(0);
lapic_timer_state_broadcast(pr, cx, 0);
return index;
}
static void __sched notrace __schedule(bool preempt)
{
struct task_struct *prev, *next;
unsigned long *switch_count;
struct rq *rq;
int cpu;
/* ==1==
找到当前cpu上的就绪队列rq
并将正在运行的进程curr保存到prev中 */
cpu = smp_processor_id();
rq = cpu_rq(cpu);
prev = rq->curr;
/*
* do_exit() calls schedule() with preemption disabled as an exception;
* however we must fix that up, otherwise the next task will see an
* inconsistent (higher) preempt count.
*
* It also avoids the below schedule_debug() test from complaining
* about this.
*/
if (unlikely(prev->state == TASK_DEAD))
preempt_enable_no_resched_notrace();
/* 如果禁止内核抢占，而又调用了cond_resched就会出错
* 这里就是用来捕获该错误的 */
schedule_debug(prev);
if (sched_feat(HRTICK))
hrtick_clear(rq);
/* 关闭本地中断 */
local_irq_disable();
/* 更新全局状态，
* 标识当前CPU发生上下文的切换 */
rcu_note_context_switch();
/*
* Make sure that signal_pending_state()->signal_pending() below
* can't be reordered with __set_current_state(TASK_INTERRUPTIBLE)
* done by the caller to avoid the race with signal_wake_up().
*/
smp_mb__before_spinlock();
/* 锁住该队列 */
raw_spin_lock(&rq->lock);
lockdep_pin_lock(&rq->lock);
rq->clock_skip_update <<= 1; /* promote REQ to ACT */
/* 切换次数记录, 默认认为非主动调度计数(抢占) */
switch_count = &prev->nivcsw;
/*
* scheduler检查prev的状态state和内核抢占表示
* 如果prev是不可运行的, 并且在内核态没有被抢占
*
* 此时当前进程不是处于运行态, 并且不是被抢占
* 此时不能只检查抢占计数
* 因为可能某个进程(如网卡轮询)直接调用了schedule
* 如果不判断prev->stat就可能误认为task进程为RUNNING状态
* 到达这里，有两种可能，一种是主动schedule, 另外一种是被抢占
* 被抢占有两种情况, 一种是时间片到点, 一种是时间片没到点
* 时间片到点后, 主要是置当前进程的need_resched标志
* 接下来在时钟中断结束后, 会preempt_schedule_irq抢占调度
*
* 那么我们正常应该做的是应该将进程prev从就绪队列rq中删除,
* 但是如果当前进程prev有非阻塞等待信号,
* 并且它的状态是TASK_INTERRUPTIBLE
* 我们就不应该从就绪队列总删除它
* 而是配置其状态为TASK_RUNNING, 并且把他留在rq中
/* 如果内核态没有被抢占, 并且内核抢占有效
即是否同时满足以下条件：
1 该进程处于停止状态
2 该进程没有在内核态被抢占 */
if (!preempt && prev->state)
{
/* 如果当前进程有非阻塞等待信号，并且它的状态是TASK_INTERRUPTIBLE */
if (unlikely(signal_pending_state(prev->state, prev)))
{
/* 将当前进程的状态设为：TASK_RUNNING */
prev->state = TASK_RUNNING;
}
else /* 否则需要将prev进程从就绪队列中删除*/
{
/* 将当前进程从runqueue(运行队列)中删除 */
deactivate_task(rq, prev, DEQUEUE_SLEEP);
/* 标识当前进程不在runqueue中 */
prev->on_rq = 0;
/*
* If a worker went to sleep, notify and ask workqueue
* whether it wants to wake up a task to maintain
* concurrency.
*/
if (prev->flags & PF_WQ_WORKER) {
struct task_struct *to_wakeup;
to_wakeup = wq_worker_sleeping(prev);
if (to_wakeup)
try_to_wake_up_local(to_wakeup);
}
}
/* 如果不是被抢占的，就累加主动切换次数 */
switch_count = &prev->nvcsw;
}
/* 如果prev进程仍然在就绪队列上没有被删除 */
if (task_on_rq_queued(prev))
update_rq_clock(rq); /* 跟新就绪队列的时钟 */
/* 挑选一个优先级最高的任务将其排进队列 */
next = pick_next_task(rq, prev);
/* 清除pre的TIF_NEED_RESCHED标志 */
clear_tsk_need_resched(prev);
/* 清楚内核抢占标识 */
clear_preempt_need_resched();
rq->clock_skip_update = 0;
/* 如果prev和next非同一个进程 */
if (likely(prev != next))
{
rq->nr_switches++; /* 队列切换次数更新 */
rq->curr = next; /* 将next标记为队列的curr进程 */
++*switch_count; /* 进程切换次数更新 */
trace_sched_switch(preempt, prev, next);
/* 进程之间上下文切换 */
rq = context_switch(rq, prev, next); /* unlocks the rq */
}
else /* 如果prev和next为同一进程，则不进行进程切换 */
{
lockdep_unpin_lock(&rq->lock);
raw_spin_unlock_irq(&rq->lock);
}
balance_callback(rq);
}
static int kgdb_cpu_enter(struct kgdb_state *ks, struct pt_regs *regs,
int exception_state)
{
unsigned long flags;
int sstep_tries = 100;
int error;
int cpu;
int trace_on = 0;
int online_cpus = num_online_cpus();
#ifdef CONFIG_KGDB_KDB
if (force_panic) /* Force panic in previous KDB, so skip this time */
return NOTIFY_DONE;
#endif
kgdb_info[ks->cpu].enter_kgdb++;
kgdb_info[ks->cpu].exception_state |= exception_state;
if (exception_state == DCPU_WANT_MASTER)
atomic_inc(&masters_in_kgdb);
else
atomic_inc(&slaves_in_kgdb);
if (arch_kgdb_ops.disable_hw_break)
arch_kgdb_ops.disable_hw_break(regs);
acquirelock:
/*
* Interrupts will be restored by the 'trap return' code, except when
* single stepping.
*/
local_irq_save(flags);
cpu = ks->cpu;
kgdb_info[cpu].debuggerinfo = regs;
kgdb_info[cpu].task = current;
kgdb_info[cpu].ret_state = 0;
kgdb_info[cpu].irq_depth = hardirq_count() >> HARDIRQ_SHIFT;
/* Make sure the above info reaches the primary CPU */
smp_mb();
if (exception_level == 1) {
if (raw_spin_trylock(&dbg_master_lock))
atomic_xchg(&kgdb_active, cpu);
goto cpu_master_loop;
}
/*
* CPU will loop if it is a slave or request to become a kgdb
* master cpu and acquire the kgdb_active lock:
*/
while (1) {
cpu_loop:
if (kgdb_info[cpu].exception_state & DCPU_NEXT_MASTER) {
kgdb_info[cpu].exception_state &= ~DCPU_NEXT_MASTER;
goto cpu_master_loop;
} else if (kgdb_info[cpu].exception_state & DCPU_WANT_MASTER) {
if (raw_spin_trylock(&dbg_master_lock)) {
atomic_xchg(&kgdb_active, cpu);
break;
}
} else if (kgdb_info[cpu].exception_state & DCPU_IS_SLAVE) {
if (!raw_spin_is_locked(&dbg_slave_lock))
goto return_normal;
} else {
return_normal:
/* Return to normal operation by executing any
* hw breakpoint fixup.
*/
if (arch_kgdb_ops.correct_hw_break)
arch_kgdb_ops.correct_hw_break();
if (trace_on)
tracing_on();
kgdb_info[cpu].exception_state &=
~(DCPU_WANT_MASTER | DCPU_IS_SLAVE);
kgdb_info[cpu].enter_kgdb--;
smp_mb__before_atomic_dec();
atomic_dec(&slaves_in_kgdb);
dbg_touch_watchdogs();
local_irq_restore(flags);
return 0;
}
cpu_relax();
}
/*
* For single stepping, try to only enter on the processor
* that was single stepping. To guard against a deadlock, the
* kernel will only try for the value of sstep_tries before
* giving up and continuing on.
*/
if (atomic_read(&kgdb_cpu_doing_single_step) != -1 &&
(kgdb_info[cpu].task &&
kgdb_info[cpu].task->pid != kgdb_sstep_pid) && --sstep_tries) {
atomic_set(&kgdb_active, -1);
raw_spin_unlock(&dbg_master_lock);
dbg_touch_watchdogs();
local_irq_restore(flags);
goto acquirelock;
}
if (!kgdb_io_ready(1)) {
kgdb_info[cpu].ret_state = 1;
goto kgdb_restore; /* No I/O connection, resume the system */
}
/*
* Don't enter if we have hit a removed breakpoint.
*/
if (kgdb_skipexception(ks->ex_vector, ks->linux_regs))
goto kgdb_restore;
/* Call the I/O driver's pre_exception routine */
if (dbg_io_ops->pre_exception)
dbg_io_ops->pre_exception();
/*
* Get the passive CPU lock which will hold all the non-primary
* CPU in a spin state while the debugger is active
*/
if (!kgdb_single_step)
raw_spin_lock(&dbg_slave_lock);
#ifdef CONFIG_SMP
/* Signal the other CPUs to enter kgdb_wait() */
if ((!kgdb_single_step) && kgdb_do_roundup)
kgdb_roundup_cpus(flags);
#endif
/*
* Wait for the other CPUs to be notified and be waiting for us:
*/
while (kgdb_do_roundup && (atomic_read(&masters_in_kgdb) +
atomic_read(&slaves_in_kgdb)) != online_cpus)
cpu_relax();
/*
* At this point the primary processor is completely
* in the debugger and all secondary CPUs are quiescent
*/
dbg_deactivate_sw_breakpoints();
kgdb_single_step = 0;
kgdb_contthread = current;
exception_level = 0;
trace_on = tracing_is_on();
if (trace_on)
tracing_off();
while (1) {
cpu_master_loop:
if (dbg_kdb_mode) {
kgdb_connected = 1;
error = kdb_stub(ks);
if (error == -1)
continue;
kgdb_connected = 0;
} else {
error = gdb_serial_stub(ks);
}
if (error == DBG_PASS_EVENT) {
dbg_kdb_mode = !dbg_kdb_mode;
} else if (error == DBG_SWITCH_CPU_EVENT) {
kgdb_info[dbg_switch_cpu].exception_state |=
DCPU_NEXT_MASTER;
goto cpu_loop;
} else {
kgdb_info[cpu].ret_state = error;
break;
}
}
/* Call the I/O driver's post_exception routine */
if (dbg_io_ops->post_exception)
dbg_io_ops->post_exception();
if (!kgdb_single_step) {
raw_spin_unlock(&dbg_slave_lock);
/* Wait till all the CPUs have quit from the debugger. */
while (kgdb_do_roundup && atomic_read(&slaves_in_kgdb))
cpu_relax();
}
kgdb_restore:
if (atomic_read(&kgdb_cpu_doing_single_step) != -1) {
int sstep_cpu = atomic_read(&kgdb_cpu_doing_single_step);
if (kgdb_info[sstep_cpu].task)
kgdb_sstep_pid = kgdb_info[sstep_cpu].task->pid;
else
kgdb_sstep_pid = 0;
}
if (arch_kgdb_ops.correct_hw_break)
arch_kgdb_ops.correct_hw_break();
if (trace_on)
tracing_on();
kgdb_info[cpu].exception_state &=
~(DCPU_WANT_MASTER | DCPU_IS_SLAVE);
kgdb_info[cpu].enter_kgdb--;
smp_mb__before_atomic_dec();
atomic_dec(&masters_in_kgdb);
/* Free kgdb_active */
atomic_set(&kgdb_active, -1);
raw_spin_unlock(&dbg_master_lock);
dbg_touch_watchdogs();
local_irq_restore(flags);
#ifdef CONFIG_KGDB_KDB
/* If no user input, force trigger kernel panic here */
if (force_panic) {
printk("KDB : Force Kernal Panic ! \n");
do { *(volatile int *)0 = 0; } while (1);
}
#endif
return kgdb_info[cpu].ret_state;
}
/*
* Task blocks on lock.
*
* Prepare waiter and propagate pi chain
*
* This must be called with lock->wait_lock held.
*/
static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
struct rt_mutex_waiter *waiter,
struct task_struct *task,
int detect_deadlock)
{
struct task_struct *owner = rt_mutex_owner(lock);
struct rt_mutex_waiter *top_waiter = waiter;
unsigned long flags;
int chain_walk = 0, res;
raw_spin_lock_irqsave(&task->pi_lock, flags);
__rt_mutex_adjust_prio(task);
waiter->task = task;
waiter->lock = lock;
plist_node_init(&waiter->list_entry, task->prio);
plist_node_init(&waiter->pi_list_entry, task->prio);
/* Get the top priority waiter on the lock */
if (rt_mutex_has_waiters(lock))
top_waiter = rt_mutex_top_waiter(lock);
plist_add(&waiter->list_entry, &lock->wait_list);
task->pi_blocked_on = waiter;
raw_spin_unlock_irqrestore(&task->pi_lock, flags);
if (!owner)
return 0;
if (waiter == rt_mutex_top_waiter(lock)) {
raw_spin_lock_irqsave(&owner->pi_lock, flags);
plist_del(&top_waiter->pi_list_entry, &owner->pi_waiters);
plist_add(&waiter->pi_list_entry, &owner->pi_waiters);
__rt_mutex_adjust_prio(owner);
if (owner->pi_blocked_on)
chain_walk = 1;
raw_spin_unlock_irqrestore(&owner->pi_lock, flags);
}
else if (debug_rt_mutex_detect_deadlock(waiter, detect_deadlock))
chain_walk = 1;
if (!chain_walk)
return 0;
/*
* The owner can't disappear while holding a lock,
* so the owner struct is protected by wait_lock.
* Gets dropped in rt_mutex_adjust_prio_chain()!
*/
get_task_struct(owner);
raw_spin_unlock(&lock->wait_lock);
res = rt_mutex_adjust_prio_chain(owner, detect_deadlock, lock, waiter,
task);
raw_spin_lock(&lock->wait_lock);
return res;
}
static void __vic_handler(unsigned int irq, struct irq_desc *desc)
{
void __iomem *base;
u32 stat[2], pend = 0;
int i = 0, gic = irq;
int cpu, n;
static u32 vic_nr[4] = { 0, 1, 0, 1};
#if defined (CONFIG_CPU_S5P4418_SMP_ISR)
static u32 vic_mask[3] = { 0, } ;
#endif
#if (DEBUG_TIMESTAMP)
long long ts = ktime_to_us(ktime_get());
static long long max = 0;
#endif
stat[0] = readl_relaxed(VIC0_INT_BASE+VIC_IRQ_STATUS);
stat[1] = readl_relaxed(VIC1_INT_BASE+VIC_IRQ_STATUS);
cpu = raw_smp_processor_id();
/* 1st usb-otg */
if (stat[1] & (1<<(IRQ_PHY_USB20OTG - 32))) {
pend = (1<<(IRQ_PHY_USB20OTG - 32));
irq = IRQ_PHY_USB20OTG;
writel_relaxed(0, (VIC1_INT_BASE + VIC_PL192_VECT_ADDR) );
goto irq_hnd;
}
/* 2nd event timer */
if (stat[0] & (1<<IRQ_PHY_TIMER_INT1)) {
pend = (1<<IRQ_PHY_TIMER_INT1);
irq = IRQ_PHY_TIMER_INT1;
writel_relaxed(0, (VIC0_INT_BASE + VIC_PL192_VECT_ADDR) );
goto irq_hnd;
}
/*
* Other round-robin vic groupt
*/
n = vic_nr[cpu];
for (i = 0; 2 > i; i++, n ^= 1) {
pend = stat[n];
if (pend) {
vic_nr[cpu] = !n;
base = n ? VIC1_INT_BASE : VIC0_INT_BASE;
irq = readl_relaxed(base + VIC_PL192_VECT_ADDR);
writel_relaxed(0, base + VIC_PL192_VECT_ADDR);
break;
}
}
#if defined (CONFIG_CPU_S5P4418_SMP_ISR)
pr_debug("%s: cpu.%d vic[%s] gic irq=%d, vic=%d, stat=0x%02x [0x%08x:0x%08x:0x%08x]\n",
__func__, cpu, i?"1":"0", gic, irq, pend, vic_mask[0], vic_mask[1], vic_mask[2]);
#endif
if (0 == pend)
goto irq_eoi;
irq_hnd:
#if defined (CONFIG_CPU_S5P4418_SMP_ISR)
raw_spin_lock(&smp_irq_lock);
if (vic_mask[irq>>5] & (1<<(irq&0x1f))) {
writel_relaxed(31, GIC_CPUI_BASE + GIC_CPU_EOI);
raw_spin_unlock(&smp_irq_lock);
return;
}
vic_mask[irq>>5] |= (1<<(irq&0x1f));
raw_spin_unlock(&smp_irq_lock);
#endif
/* vic descriptor */
desc = irq_desc + irq;
if (desc)
generic_handle_irq_desc(irq, desc);
else
printk(KERN_ERR "Error, not registered vic irq=%d !!!\n", irq);
#if defined (CONFIG_CPU_S5P4418_SMP_ISR)
raw_spin_lock(&smp_irq_lock);
vic_mask[irq>>5] &= ~(1<<(irq&0x1f));
raw_spin_unlock(&smp_irq_lock);
#endif
#if (DEBUG_TIMESTAMP)
ts = ktime_to_us(ktime_get()) - ts;
if (ts > 2000) {
max = ts;
printk("[cpu.%d irq.%d, %03lldms]\n", cpu, irq, div64_s64(ts, 1000));
}
#endif
irq_eoi:
writel_relaxed(31, GIC_CPUI_BASE + GIC_CPU_EOI);
return;
}
/*
* schedule() is the main scheduler function.
*/
asmlinkage void __sched schedule(void)
{
struct task_struct *prev, *next;
unsigned long *switch_count;
struct rq *rq;
int cpu;
need_resched:
preempt_disable();
cpu = smp_processor_id();
rq = cpu_rq(cpu);
rcu_note_context_switch(cpu);
prev = rq->curr;
schedule_debug(prev);
if (sched_feat(HRTICK))
hrtick_clear(rq);
raw_spin_lock_irq(&rq->lock);
switch_count = &prev->nivcsw;
if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) {
if (unlikely(signal_pending_state(prev->state, prev))) {
prev->state = TASK_RUNNING;
} else {
/*
* If a worker is going to sleep, notify and
* ask workqueue whether it wants to wake up a
* task to maintain concurrency. If so, wake
* up the task.
*/
if (prev->flags & PF_WQ_WORKER) {
struct task_struct *to_wakeup;
to_wakeup = wq_worker_sleeping(prev, cpu);
if (to_wakeup)
try_to_wake_up_local(to_wakeup);
}
deactivate_task(rq, prev, DEQUEUE_SLEEP);
/*
* If we are going to sleep and we have plugged IO queued, make
* sure to submit it to avoid deadlocks.
*/
if (blk_needs_flush_plug(prev)) {
raw_spin_unlock(&rq->lock);
blk_schedule_flush_plug(prev);
raw_spin_lock(&rq->lock);
}
}
switch_count = &prev->nvcsw;
}
pre_schedule(rq, prev);
if (unlikely(!rq->nr_running))
idle_balance(cpu, rq);
put_prev_task(rq, prev);
next = pick_next_task(rq);
clear_tsk_need_resched(prev);
rq->skip_clock_update = 0;
if (likely(prev != next)) {
rq->nr_switches++;
rq->curr = next;
++*switch_count;
context_switch(rq, prev, next); /* unlocks the rq */
/*
* The context switch have flipped the stack from under us
* and restored the local variables which were saved when
* this task called schedule() in the past. prev == current
* is still correct, but it can be moved to another cpu/rq.
*/
cpu = smp_processor_id();
rq = cpu_rq(cpu);
} else
raw_spin_unlock_irq(&rq->lock);
post_schedule(rq);
preempt_enable_no_resched();
if (need_resched())
goto need_resched;
}
/* A cpu has been removed from cpu_online_mask. Reset irq affinities. */
void fixup_irqs(void)
{
unsigned int irq, vector;
static int warned;
struct irq_desc *desc;
struct irq_data *data;
struct irq_chip *chip;
int ret;
for_each_irq_desc(irq, desc) {
int break_affinity = 0;
int set_affinity = 1;
const struct cpumask *affinity;
if (!desc)
continue;
if (irq == 2)
continue;
/* interrupt's are disabled at this point */
raw_spin_lock(&desc->lock);
data = irq_desc_get_irq_data(desc);
affinity = irq_data_get_affinity_mask(data);
if (!irq_has_action(irq) || irqd_is_per_cpu(data) ||
cpumask_subset(affinity, cpu_online_mask)) {
raw_spin_unlock(&desc->lock);
continue;
}
/*
* Complete the irq move. This cpu is going down and for
* non intr-remapping case, we can't wait till this interrupt
* arrives at this cpu before completing the irq move.
*/
irq_force_complete_move(desc);
if (cpumask_any_and(affinity, cpu_online_mask) >= nr_cpu_ids) {
break_affinity = 1;
affinity = cpu_online_mask;
}
chip = irq_data_get_irq_chip(data);
/*
* The interrupt descriptor might have been cleaned up
* already, but it is not yet removed from the radix tree
*/
if (!chip) {
raw_spin_unlock(&desc->lock);
continue;
}
if (!irqd_can_move_in_process_context(data) && chip->irq_mask)
chip->irq_mask(data);
if (chip->irq_set_affinity) {
ret = chip->irq_set_affinity(data, affinity, true);
if (ret == -ENOSPC)
pr_crit("IRQ %d set affinity failed because there are no available vectors. The device assigned to this IRQ is unstable.\n", irq);
} else {
if (!(warned++))
set_affinity = 0;
}
/*
* We unmask if the irq was not marked masked by the
* core code. That respects the lazy irq disable
* behaviour.
*/
if (!irqd_can_move_in_process_context(data) &&
!irqd_irq_masked(data) && chip->irq_unmask)
chip->irq_unmask(data);
raw_spin_unlock(&desc->lock);
if (break_affinity && set_affinity)
pr_notice("Broke affinity for irq %i\n", irq);
else if (!set_affinity)
pr_notice("Cannot set affinity for irq %i\n", irq);
}
/*
* This cpu is going to be removed and its vectors migrated to the remaining
* online cpus. Check to see if there are enough vectors in the remaining cpus.
* This function is protected by stop_machine().
*/
int check_irq_vectors_for_cpu_disable(void)
{
unsigned int this_cpu, vector, this_count, count;
struct irq_desc *desc;
struct irq_data *data;
int cpu;
this_cpu = smp_processor_id();
cpumask_copy(&online_new, cpu_online_mask);
cpumask_clear_cpu(this_cpu, &online_new);
this_count = 0;
for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) {
desc = __this_cpu_read(vector_irq[vector]);
if (IS_ERR_OR_NULL(desc))
continue;
/*
* Protect against concurrent action removal, affinity
* changes etc.
*/
raw_spin_lock(&desc->lock);
data = irq_desc_get_irq_data(desc);
cpumask_copy(&affinity_new,
irq_data_get_affinity_mask(data));
cpumask_clear_cpu(this_cpu, &affinity_new);
/* Do not count inactive or per-cpu irqs. */
if (!irq_desc_has_action(desc) || irqd_is_per_cpu(data)) {
raw_spin_unlock(&desc->lock);
continue;
}
raw_spin_unlock(&desc->lock);
/*
* A single irq may be mapped to multiple cpu's
* vector_irq[] (for example IOAPIC cluster mode). In
* this case we have two possibilities:
*
* 1) the resulting affinity mask is empty; that is
* this the down'd cpu is the last cpu in the irq's
* affinity mask, or
*
* 2) the resulting affinity mask is no longer a
* subset of the online cpus but the affinity mask is
* not zero; that is the down'd cpu is the last online
* cpu in a user set affinity mask.
*/
if (cpumask_empty(&affinity_new) ||
!cpumask_subset(&affinity_new, &online_new))
this_count++;
}
count = 0;
for_each_online_cpu(cpu) {
if (cpu == this_cpu)
continue;
/*
* We scan from FIRST_EXTERNAL_VECTOR to first system
* vector. If the vector is marked in the used vectors
* bitmap or an irq is assigned to it, we don't count
* it as available.
*
* As this is an inaccurate snapshot anyway, we can do
* this w/o holding vector_lock.
*/
for (vector = FIRST_EXTERNAL_VECTOR;
vector < first_system_vector; vector++) {
if (!test_bit(vector, used_vectors) &&
IS_ERR_OR_NULL(per_cpu(vector_irq, cpu)[vector]))
count++;
}
}
if (count < this_count) {
pr_warn("CPU %d disable failed: CPU has %u vectors assigned and there are only %u available.\n",
this_cpu, this_count, count);
return -ERANGE;
}
return 0;
}
/*
* 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 = 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 = 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 > cpu_base->max_hang_time)
cpu_base->max_hang_time = (unsigned int) delta;
/*
* Limit it to a sensible value as we enforce a longer
* delay. Give the CPU at least 100ms to catch up.
*/
if (delta > 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));
}
/**
* __do_IRQ - original all in one highlevel IRQ handler
* @irq: the interrupt number
*
* __do_IRQ handles all normal device IRQ's (the special
* SMP cross-CPU interrupts have their own specific
* handlers).
*
* This is the original x86 implementation which is used for every
* interrupt type.
*/
unsigned int __do_IRQ(unsigned int irq)
{
struct irq_desc *desc = irq_to_desc(irq);
struct irqaction *action;
unsigned int status;
kstat_incr_irqs_this_cpu(irq, desc);
if (CHECK_IRQ_PER_CPU(desc->status)) {
irqreturn_t action_ret;
/*
* No locking required for CPU-local interrupts:
*/
if (desc->chip->ack)
desc->chip->ack(irq);
if (likely(!(desc->status & IRQ_DISABLED))) {
action_ret = handle_IRQ_event(irq, desc->action);
if (!noirqdebug)
note_interrupt(irq, desc, action_ret);
}
desc->chip->end(irq);
return 1;
}
raw_spin_lock(&desc->lock);
if (desc->chip->ack)
desc->chip->ack(irq);
/*
* REPLAY is when Linux resends an IRQ that was dropped earlier
* WAITING is used by probe to mark irqs that are being tested
*/
status = desc->status & ~(IRQ_REPLAY | IRQ_WAITING);
status |= IRQ_PENDING; /* we _want_ to handle it */
/*
* If the IRQ is disabled for whatever reason, we cannot
* use the action we have.
*/
action = NULL;
if (likely(!(status & (IRQ_DISABLED | IRQ_INPROGRESS)))) {
action = desc->action;
status &= ~IRQ_PENDING; /* we commit to handling */
status |= IRQ_INPROGRESS; /* we are handling it */
}
desc->status = status;
/*
* If there is no IRQ handler or it was disabled, exit early.
* Since we set PENDING, if another processor is handling
* a different instance of this same irq, the other processor
* will take care of it.
*/
if (unlikely(!action))
goto out;
/*
* Edge triggered interrupts need to remember
* pending events.
* This applies to any hw interrupts that allow a second
* instance of the same irq to arrive while we are in do_IRQ
* or in the handler. But the code here only handles the _second_
* instance of the irq, not the third or fourth. So it is mostly
* useful for irq hardware that does not mask cleanly in an
* SMP environment.
*/
for (;;) {
irqreturn_t action_ret;
raw_spin_unlock(&desc->lock);
action_ret = handle_IRQ_event(irq, action);
if (!noirqdebug)
note_interrupt(irq, desc, action_ret);
raw_spin_lock(&desc->lock);
if (likely(!(desc->status & IRQ_PENDING)))
break;
desc->status &= ~IRQ_PENDING;
}
desc->status &= ~IRQ_INPROGRESS;
out:
/*
* The ->end() handler has to deal with interrupts which got
* disabled while the handler was running.
*/
desc->chip->end(irq);
raw_spin_unlock(&desc->lock);
return 1;
}
/*
* 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));
}
void switch_mmu_context(struct mm_struct *prev, struct mm_struct *next)
{
unsigned int i, id, cpu = smp_processor_id();
unsigned long *map;
raw_spin_lock(&context_lock);
pr_hard("[%d] activating context for mm @%p, active=%d, id=%d",
cpu, next, next->context.active, next->context.id);
#ifdef CONFIG_SMP
next->context.active++;
if (prev) {
pr_hardcont(" (old=0x%p a=%d)", prev, prev->context.active);
WARN_ON(prev->context.active < 1);
prev->context.active--;
}
again:
#endif
id = next->context.id;
if (likely(id != MMU_NO_CONTEXT)) {
#ifdef DEBUG_MAP_CONSISTENCY
if (context_mm[id] != next)
pr_err("MMU: mm 0x%p has id %d but context_mm[%d] says 0x%p\n",
next, id, id, context_mm[id]);
#endif
goto ctxt_ok;
}
id = next_context;
if (id > last_context)
id = first_context;
map = context_map;
if (nr_free_contexts == 0) {
#ifdef CONFIG_SMP
if (num_online_cpus() > 1) {
id = steal_context_smp(id);
if (id == MMU_NO_CONTEXT)
goto again;
goto stolen;
}
#endif
id = steal_context_up(id);
goto stolen;
}
nr_free_contexts--;
while (__test_and_set_bit(id, map)) {
id = find_next_zero_bit(map, last_context+1, id);
if (id > last_context)
id = first_context;
}
stolen:
next_context = id + 1;
context_mm[id] = next;
next->context.id = id;
pr_hardcont(" | new id=%d,nrf=%d", id, nr_free_contexts);
context_check_map();
ctxt_ok:
if (test_bit(id, stale_map[cpu])) {
pr_hardcont(" | stale flush %d [%d..%d]",
id, cpu_first_thread_sibling(cpu),
cpu_last_thread_sibling(cpu));
local_flush_tlb_mm(next);
for (i = cpu_first_thread_sibling(cpu);
i <= cpu_last_thread_sibling(cpu); i++) {
__clear_bit(id, stale_map[i]);
}
}
pr_hardcont(" -> %d\n", id);
set_context(id, next->pgd);
raw_spin_unlock(&context_lock);
}
