softirq.c 14.6 KB
Newer Older
L
Linus Torvalds 已提交
1 2 3 4 5
/*
 *	linux/kernel/softirq.c
 *
 *	Copyright (C) 1992 Linus Torvalds
 *
P
Pavel Machek 已提交
6 7 8
 *	Distribute under GPLv2.
 *
 *	Rewritten. Old one was good in 2.2, but in 2.3 it was immoral. --ANK (990903)
L
Linus Torvalds 已提交
9 10 11 12 13 14 15 16 17 18
 */

#include <linux/module.h>
#include <linux/kernel_stat.h>
#include <linux/interrupt.h>
#include <linux/init.h>
#include <linux/mm.h>
#include <linux/notifier.h>
#include <linux/percpu.h>
#include <linux/cpu.h>
19
#include <linux/freezer.h>
L
Linus Torvalds 已提交
20 21
#include <linux/kthread.h>
#include <linux/rcupdate.h>
22
#include <linux/smp.h>
23
#include <linux/tick.h>
L
Linus Torvalds 已提交
24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67

#include <asm/irq.h>
/*
   - No shared variables, all the data are CPU local.
   - If a softirq needs serialization, let it serialize itself
     by its own spinlocks.
   - Even if softirq is serialized, only local cpu is marked for
     execution. Hence, we get something sort of weak cpu binding.
     Though it is still not clear, will it result in better locality
     or will not.

   Examples:
   - NET RX softirq. It is multithreaded and does not require
     any global serialization.
   - NET TX softirq. It kicks software netdevice queues, hence
     it is logically serialized per device, but this serialization
     is invisible to common code.
   - Tasklets: serialized wrt itself.
 */

#ifndef __ARCH_IRQ_STAT
irq_cpustat_t irq_stat[NR_CPUS] ____cacheline_aligned;
EXPORT_SYMBOL(irq_stat);
#endif

static struct softirq_action softirq_vec[32] __cacheline_aligned_in_smp;

static DEFINE_PER_CPU(struct task_struct *, ksoftirqd);

/*
 * we cannot loop indefinitely here to avoid userspace starvation,
 * but we also don't want to introduce a worst case 1/HZ latency
 * to the pending events, so lets the scheduler to balance
 * the softirq load for us.
 */
static inline void wakeup_softirqd(void)
{
	/* Interrupts are disabled: no need to stop preemption */
	struct task_struct *tsk = __get_cpu_var(ksoftirqd);

	if (tsk && tsk->state != TASK_RUNNING)
		wake_up_process(tsk);
}

68 69 70 71
/*
 * This one is for softirq.c-internal use,
 * where hardirqs are disabled legitimately:
 */
72
#ifdef CONFIG_TRACE_IRQFLAGS
73 74 75 76 77 78 79 80 81 82 83 84 85 86 87
static void __local_bh_disable(unsigned long ip)
{
	unsigned long flags;

	WARN_ON_ONCE(in_irq());

	raw_local_irq_save(flags);
	add_preempt_count(SOFTIRQ_OFFSET);
	/*
	 * Were softirqs turned off above:
	 */
	if (softirq_count() == SOFTIRQ_OFFSET)
		trace_softirqs_off(ip);
	raw_local_irq_restore(flags);
}
88 89 90 91 92 93 94
#else /* !CONFIG_TRACE_IRQFLAGS */
static inline void __local_bh_disable(unsigned long ip)
{
	add_preempt_count(SOFTIRQ_OFFSET);
	barrier();
}
#endif /* CONFIG_TRACE_IRQFLAGS */
95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135

void local_bh_disable(void)
{
	__local_bh_disable((unsigned long)__builtin_return_address(0));
}

EXPORT_SYMBOL(local_bh_disable);

void __local_bh_enable(void)
{
	WARN_ON_ONCE(in_irq());

	/*
	 * softirqs should never be enabled by __local_bh_enable(),
	 * it always nests inside local_bh_enable() sections:
	 */
	WARN_ON_ONCE(softirq_count() == SOFTIRQ_OFFSET);

	sub_preempt_count(SOFTIRQ_OFFSET);
}
EXPORT_SYMBOL_GPL(__local_bh_enable);

/*
 * Special-case - softirqs can safely be enabled in
 * cond_resched_softirq(), or by __do_softirq(),
 * without processing still-pending softirqs:
 */
void _local_bh_enable(void)
{
	WARN_ON_ONCE(in_irq());
	WARN_ON_ONCE(!irqs_disabled());

	if (softirq_count() == SOFTIRQ_OFFSET)
		trace_softirqs_on((unsigned long)__builtin_return_address(0));
	sub_preempt_count(SOFTIRQ_OFFSET);
}

EXPORT_SYMBOL(_local_bh_enable);

void local_bh_enable(void)
{
136
#ifdef CONFIG_TRACE_IRQFLAGS
137 138 139
	unsigned long flags;

	WARN_ON_ONCE(in_irq());
140
#endif
141 142
	WARN_ON_ONCE(irqs_disabled());

143
#ifdef CONFIG_TRACE_IRQFLAGS
144
	local_irq_save(flags);
145
#endif
146 147 148 149 150 151 152 153 154 155 156 157 158 159 160
	/*
	 * Are softirqs going to be turned on now:
	 */
	if (softirq_count() == SOFTIRQ_OFFSET)
		trace_softirqs_on((unsigned long)__builtin_return_address(0));
	/*
	 * Keep preemption disabled until we are done with
	 * softirq processing:
 	 */
 	sub_preempt_count(SOFTIRQ_OFFSET - 1);

	if (unlikely(!in_interrupt() && local_softirq_pending()))
		do_softirq();

	dec_preempt_count();
161
#ifdef CONFIG_TRACE_IRQFLAGS
162
	local_irq_restore(flags);
163
#endif
164 165 166 167 168 169
	preempt_check_resched();
}
EXPORT_SYMBOL(local_bh_enable);

void local_bh_enable_ip(unsigned long ip)
{
170
#ifdef CONFIG_TRACE_IRQFLAGS
171 172 173 174 175
	unsigned long flags;

	WARN_ON_ONCE(in_irq());

	local_irq_save(flags);
176
#endif
177 178 179 180 181 182 183 184 185 186 187 188 189 190 191
	/*
	 * Are softirqs going to be turned on now:
	 */
	if (softirq_count() == SOFTIRQ_OFFSET)
		trace_softirqs_on(ip);
	/*
	 * Keep preemption disabled until we are done with
	 * softirq processing:
 	 */
 	sub_preempt_count(SOFTIRQ_OFFSET - 1);

	if (unlikely(!in_interrupt() && local_softirq_pending()))
		do_softirq();

	dec_preempt_count();
192
#ifdef CONFIG_TRACE_IRQFLAGS
193
	local_irq_restore(flags);
194
#endif
195 196 197 198
	preempt_check_resched();
}
EXPORT_SYMBOL(local_bh_enable_ip);

L
Linus Torvalds 已提交
199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217
/*
 * We restart softirq processing MAX_SOFTIRQ_RESTART times,
 * and we fall back to softirqd after that.
 *
 * This number has been established via experimentation.
 * The two things to balance is latency against fairness -
 * we want to handle softirqs as soon as possible, but they
 * should not be able to lock up the box.
 */
#define MAX_SOFTIRQ_RESTART 10

asmlinkage void __do_softirq(void)
{
	struct softirq_action *h;
	__u32 pending;
	int max_restart = MAX_SOFTIRQ_RESTART;
	int cpu;

	pending = local_softirq_pending();
218 219
	account_system_vtime(current);

220 221
	__local_bh_disable((unsigned long)__builtin_return_address(0));
	trace_softirq_enter();
L
Linus Torvalds 已提交
222 223 224 225

	cpu = smp_processor_id();
restart:
	/* Reset the pending bitmask before enabling irqs */
226
	set_softirq_pending(0);
L
Linus Torvalds 已提交
227

228
	local_irq_enable();
L
Linus Torvalds 已提交
229 230 231 232 233 234 235 236 237 238 239 240

	h = softirq_vec;

	do {
		if (pending & 1) {
			h->action(h);
			rcu_bh_qsctr_inc(cpu);
		}
		h++;
		pending >>= 1;
	} while (pending);

241
	local_irq_disable();
L
Linus Torvalds 已提交
242 243 244 245 246 247 248 249

	pending = local_softirq_pending();
	if (pending && --max_restart)
		goto restart;

	if (pending)
		wakeup_softirqd();

250
	trace_softirq_exit();
251 252

	account_system_vtime(current);
253
	_local_bh_enable();
L
Linus Torvalds 已提交
254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277
}

#ifndef __ARCH_HAS_DO_SOFTIRQ

asmlinkage void do_softirq(void)
{
	__u32 pending;
	unsigned long flags;

	if (in_interrupt())
		return;

	local_irq_save(flags);

	pending = local_softirq_pending();

	if (pending)
		__do_softirq();

	local_irq_restore(flags);
}

#endif

I
Ingo Molnar 已提交
278 279 280 281 282
/*
 * Enter an interrupt context.
 */
void irq_enter(void)
{
283 284 285 286 287
#ifdef CONFIG_NO_HZ
	int cpu = smp_processor_id();
	if (idle_cpu(cpu) && !in_interrupt())
		tick_nohz_stop_idle(cpu);
#endif
288 289
	__irq_enter();
#ifdef CONFIG_NO_HZ
290
	if (idle_cpu(cpu))
291 292
		tick_nohz_update_jiffies();
#endif
I
Ingo Molnar 已提交
293 294
}

L
Linus Torvalds 已提交
295 296 297 298 299 300 301 302 303 304 305 306
#ifdef __ARCH_IRQ_EXIT_IRQS_DISABLED
# define invoke_softirq()	__do_softirq()
#else
# define invoke_softirq()	do_softirq()
#endif

/*
 * Exit an interrupt context. Process softirqs if needed and possible:
 */
void irq_exit(void)
{
	account_system_vtime(current);
307
	trace_hardirq_exit();
L
Linus Torvalds 已提交
308 309 310
	sub_preempt_count(IRQ_EXIT_OFFSET);
	if (!in_interrupt() && local_softirq_pending())
		invoke_softirq();
311 312 313 314 315

#ifdef CONFIG_NO_HZ
	/* Make sure that timer wheel updates are propagated */
	if (!in_interrupt() && idle_cpu(smp_processor_id()) && !need_resched())
		tick_nohz_stop_sched_tick();
316
	rcu_irq_exit();
317
#endif
L
Linus Torvalds 已提交
318 319 320 321 322 323
	preempt_enable_no_resched();
}

/*
 * This function must run with irqs disabled!
 */
324
inline void raise_softirq_irqoff(unsigned int nr)
L
Linus Torvalds 已提交
325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340
{
	__raise_softirq_irqoff(nr);

	/*
	 * If we're in an interrupt or softirq, we're done
	 * (this also catches softirq-disabled code). We will
	 * actually run the softirq once we return from
	 * the irq or softirq.
	 *
	 * Otherwise we wake up ksoftirqd to make sure we
	 * schedule the softirq soon.
	 */
	if (!in_interrupt())
		wakeup_softirqd();
}

341
void raise_softirq(unsigned int nr)
L
Linus Torvalds 已提交
342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366
{
	unsigned long flags;

	local_irq_save(flags);
	raise_softirq_irqoff(nr);
	local_irq_restore(flags);
}

void open_softirq(int nr, void (*action)(struct softirq_action*), void *data)
{
	softirq_vec[nr].data = data;
	softirq_vec[nr].action = action;
}

/* Tasklets */
struct tasklet_head
{
	struct tasklet_struct *list;
};

/* Some compilers disobey section attribute on statics when not
   initialized -- RR */
static DEFINE_PER_CPU(struct tasklet_head, tasklet_vec) = { NULL };
static DEFINE_PER_CPU(struct tasklet_head, tasklet_hi_vec) = { NULL };

367
void __tasklet_schedule(struct tasklet_struct *t)
L
Linus Torvalds 已提交
368 369 370 371 372 373 374 375 376 377 378 379
{
	unsigned long flags;

	local_irq_save(flags);
	t->next = __get_cpu_var(tasklet_vec).list;
	__get_cpu_var(tasklet_vec).list = t;
	raise_softirq_irqoff(TASKLET_SOFTIRQ);
	local_irq_restore(flags);
}

EXPORT_SYMBOL(__tasklet_schedule);

380
void __tasklet_hi_schedule(struct tasklet_struct *t)
L
Linus Torvalds 已提交
381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588
{
	unsigned long flags;

	local_irq_save(flags);
	t->next = __get_cpu_var(tasklet_hi_vec).list;
	__get_cpu_var(tasklet_hi_vec).list = t;
	raise_softirq_irqoff(HI_SOFTIRQ);
	local_irq_restore(flags);
}

EXPORT_SYMBOL(__tasklet_hi_schedule);

static void tasklet_action(struct softirq_action *a)
{
	struct tasklet_struct *list;

	local_irq_disable();
	list = __get_cpu_var(tasklet_vec).list;
	__get_cpu_var(tasklet_vec).list = NULL;
	local_irq_enable();

	while (list) {
		struct tasklet_struct *t = list;

		list = list->next;

		if (tasklet_trylock(t)) {
			if (!atomic_read(&t->count)) {
				if (!test_and_clear_bit(TASKLET_STATE_SCHED, &t->state))
					BUG();
				t->func(t->data);
				tasklet_unlock(t);
				continue;
			}
			tasklet_unlock(t);
		}

		local_irq_disable();
		t->next = __get_cpu_var(tasklet_vec).list;
		__get_cpu_var(tasklet_vec).list = t;
		__raise_softirq_irqoff(TASKLET_SOFTIRQ);
		local_irq_enable();
	}
}

static void tasklet_hi_action(struct softirq_action *a)
{
	struct tasklet_struct *list;

	local_irq_disable();
	list = __get_cpu_var(tasklet_hi_vec).list;
	__get_cpu_var(tasklet_hi_vec).list = NULL;
	local_irq_enable();

	while (list) {
		struct tasklet_struct *t = list;

		list = list->next;

		if (tasklet_trylock(t)) {
			if (!atomic_read(&t->count)) {
				if (!test_and_clear_bit(TASKLET_STATE_SCHED, &t->state))
					BUG();
				t->func(t->data);
				tasklet_unlock(t);
				continue;
			}
			tasklet_unlock(t);
		}

		local_irq_disable();
		t->next = __get_cpu_var(tasklet_hi_vec).list;
		__get_cpu_var(tasklet_hi_vec).list = t;
		__raise_softirq_irqoff(HI_SOFTIRQ);
		local_irq_enable();
	}
}


void tasklet_init(struct tasklet_struct *t,
		  void (*func)(unsigned long), unsigned long data)
{
	t->next = NULL;
	t->state = 0;
	atomic_set(&t->count, 0);
	t->func = func;
	t->data = data;
}

EXPORT_SYMBOL(tasklet_init);

void tasklet_kill(struct tasklet_struct *t)
{
	if (in_interrupt())
		printk("Attempt to kill tasklet from interrupt\n");

	while (test_and_set_bit(TASKLET_STATE_SCHED, &t->state)) {
		do
			yield();
		while (test_bit(TASKLET_STATE_SCHED, &t->state));
	}
	tasklet_unlock_wait(t);
	clear_bit(TASKLET_STATE_SCHED, &t->state);
}

EXPORT_SYMBOL(tasklet_kill);

void __init softirq_init(void)
{
	open_softirq(TASKLET_SOFTIRQ, tasklet_action, NULL);
	open_softirq(HI_SOFTIRQ, tasklet_hi_action, NULL);
}

static int ksoftirqd(void * __bind_cpu)
{
	set_current_state(TASK_INTERRUPTIBLE);

	while (!kthread_should_stop()) {
		preempt_disable();
		if (!local_softirq_pending()) {
			preempt_enable_no_resched();
			schedule();
			preempt_disable();
		}

		__set_current_state(TASK_RUNNING);

		while (local_softirq_pending()) {
			/* Preempt disable stops cpu going offline.
			   If already offline, we'll be on wrong CPU:
			   don't process */
			if (cpu_is_offline((long)__bind_cpu))
				goto wait_to_die;
			do_softirq();
			preempt_enable_no_resched();
			cond_resched();
			preempt_disable();
		}
		preempt_enable();
		set_current_state(TASK_INTERRUPTIBLE);
	}
	__set_current_state(TASK_RUNNING);
	return 0;

wait_to_die:
	preempt_enable();
	/* Wait for kthread_stop */
	set_current_state(TASK_INTERRUPTIBLE);
	while (!kthread_should_stop()) {
		schedule();
		set_current_state(TASK_INTERRUPTIBLE);
	}
	__set_current_state(TASK_RUNNING);
	return 0;
}

#ifdef CONFIG_HOTPLUG_CPU
/*
 * tasklet_kill_immediate is called to remove a tasklet which can already be
 * scheduled for execution on @cpu.
 *
 * Unlike tasklet_kill, this function removes the tasklet
 * _immediately_, even if the tasklet is in TASKLET_STATE_SCHED state.
 *
 * When this function is called, @cpu must be in the CPU_DEAD state.
 */
void tasklet_kill_immediate(struct tasklet_struct *t, unsigned int cpu)
{
	struct tasklet_struct **i;

	BUG_ON(cpu_online(cpu));
	BUG_ON(test_bit(TASKLET_STATE_RUN, &t->state));

	if (!test_bit(TASKLET_STATE_SCHED, &t->state))
		return;

	/* CPU is dead, so no lock needed. */
	for (i = &per_cpu(tasklet_vec, cpu).list; *i; i = &(*i)->next) {
		if (*i == t) {
			*i = t->next;
			return;
		}
	}
	BUG();
}

static void takeover_tasklets(unsigned int cpu)
{
	struct tasklet_struct **i;

	/* CPU is dead, so no lock needed. */
	local_irq_disable();

	/* Find end, append list for that CPU. */
	for (i = &__get_cpu_var(tasklet_vec).list; *i; i = &(*i)->next);
	*i = per_cpu(tasklet_vec, cpu).list;
	per_cpu(tasklet_vec, cpu).list = NULL;
	raise_softirq_irqoff(TASKLET_SOFTIRQ);

	for (i = &__get_cpu_var(tasklet_hi_vec).list; *i; i = &(*i)->next);
	*i = per_cpu(tasklet_hi_vec, cpu).list;
	per_cpu(tasklet_hi_vec, cpu).list = NULL;
	raise_softirq_irqoff(HI_SOFTIRQ);

	local_irq_enable();
}
#endif /* CONFIG_HOTPLUG_CPU */

589
static int __cpuinit cpu_callback(struct notifier_block *nfb,
L
Linus Torvalds 已提交
590 591 592 593 594 595 596 597
				  unsigned long action,
				  void *hcpu)
{
	int hotcpu = (unsigned long)hcpu;
	struct task_struct *p;

	switch (action) {
	case CPU_UP_PREPARE:
598
	case CPU_UP_PREPARE_FROZEN:
L
Linus Torvalds 已提交
599 600 601 602 603 604 605 606 607
		p = kthread_create(ksoftirqd, hcpu, "ksoftirqd/%d", hotcpu);
		if (IS_ERR(p)) {
			printk("ksoftirqd for %i failed\n", hotcpu);
			return NOTIFY_BAD;
		}
		kthread_bind(p, hotcpu);
  		per_cpu(ksoftirqd, hotcpu) = p;
 		break;
	case CPU_ONLINE:
608
	case CPU_ONLINE_FROZEN:
L
Linus Torvalds 已提交
609 610 611 612
		wake_up_process(per_cpu(ksoftirqd, hotcpu));
		break;
#ifdef CONFIG_HOTPLUG_CPU
	case CPU_UP_CANCELED:
613
	case CPU_UP_CANCELED_FROZEN:
614 615
		if (!per_cpu(ksoftirqd, hotcpu))
			break;
L
Linus Torvalds 已提交
616
		/* Unbind so it can run.  Fall thru. */
617 618
		kthread_bind(per_cpu(ksoftirqd, hotcpu),
			     any_online_cpu(cpu_online_map));
L
Linus Torvalds 已提交
619
	case CPU_DEAD:
620 621 622
	case CPU_DEAD_FROZEN: {
		struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 };

L
Linus Torvalds 已提交
623 624
		p = per_cpu(ksoftirqd, hotcpu);
		per_cpu(ksoftirqd, hotcpu) = NULL;
625
		sched_setscheduler(p, SCHED_FIFO, &param);
L
Linus Torvalds 已提交
626 627 628
		kthread_stop(p);
		takeover_tasklets(hotcpu);
		break;
629
	}
L
Linus Torvalds 已提交
630 631 632 633 634
#endif /* CONFIG_HOTPLUG_CPU */
 	}
	return NOTIFY_OK;
}

635
static struct notifier_block __cpuinitdata cpu_nfb = {
L
Linus Torvalds 已提交
636 637 638 639 640 641
	.notifier_call = cpu_callback
};

__init int spawn_ksoftirqd(void)
{
	void *cpu = (void *)(long)smp_processor_id();
642 643 644
	int err = cpu_callback(&cpu_nfb, CPU_UP_PREPARE, cpu);

	BUG_ON(err == NOTIFY_BAD);
L
Linus Torvalds 已提交
645 646 647 648
	cpu_callback(&cpu_nfb, CPU_ONLINE, cpu);
	register_cpu_notifier(&cpu_nfb);
	return 0;
}
649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667

#ifdef CONFIG_SMP
/*
 * Call a function on all processors
 */
int on_each_cpu(void (*func) (void *info), void *info, int retry, int wait)
{
	int ret = 0;

	preempt_disable();
	ret = smp_call_function(func, info, retry, wait);
	local_irq_disable();
	func(info);
	local_irq_enable();
	preempt_enable();
	return ret;
}
EXPORT_SYMBOL(on_each_cpu);
#endif