Boot Linux faster!

Check our new training course

Boot Linux faster!

Check our new training course
and Creative Commons CC-BY-SA
lecture and lab materials

Bootlin logo

Elixir Cross Referencer

  1
  2
  3
  4
  5
  6
  7
  8
  9
 10
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 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
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 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
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
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
367
368
369
370
371
372
373
374
375
376
377
378
379
380
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
/*
 *	linux/kernel/softirq.c
 *
 *	Copyright (C) 1992 Linus Torvalds
 *
 * Fixed a disable_bh()/enable_bh() race (was causing a console lockup)
 * due bh_mask_count not atomic handling. Copyright (C) 1998  Andrea Arcangeli
 *
 * Rewritten. Old one was good in 2.2, but in 2.3 it was immoral. --ANK (990903)
 */

#include <linux/config.h>
#include <linux/mm.h>
#include <linux/kernel_stat.h>
#include <linux/interrupt.h>
#include <linux/smp_lock.h>
#include <linux/init.h>
#include <linux/tqueue.h>
#include <linux/percpu.h>
#include <linux/notifier.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.
   - Bottom halves: globally serialized, grr...
 */

irq_cpustat_t irq_stat[NR_CPUS];

static struct softirq_action softirq_vec[32] __cacheline_aligned_in_smp;

/*
 * 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(unsigned cpu)
{
	struct task_struct * tsk = ksoftirqd_task(cpu);

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

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

	if (in_interrupt())
		return;

	local_irq_save(flags);
	cpu = smp_processor_id();

	pending = softirq_pending(cpu);

	if (pending) {
		struct softirq_action *h;

		mask = ~pending;
		local_bh_disable();
restart:
		/* Reset the pending bitmask before enabling irqs */
		softirq_pending(cpu) = 0;

		local_irq_enable();

		h = softirq_vec;

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

		local_irq_disable();

		pending = softirq_pending(cpu);
		if (pending & mask) {
			mask &= ~pending;
			goto restart;
		}
		__local_bh_enable();

		if (pending)
			wakeup_softirqd(cpu);
	}

	local_irq_restore(flags);
}

/*
 * This function must run with irqs disabled!
 */
inline void cpu_raise_softirq(unsigned int cpu, unsigned int nr)
{
	__cpu_raise_softirq(cpu, nr);

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

void raise_softirq(unsigned int nr)
{
	unsigned long flags;

	local_irq_save(flags);
	cpu_raise_softirq(smp_processor_id(), 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 };

void __tasklet_schedule(struct tasklet_struct *t)
{
	unsigned long flags;

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

void __tasklet_hi_schedule(struct tasklet_struct *t)
{
	unsigned long flags;

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

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;
		__cpu_raise_softirq(smp_processor_id(), 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;
		__cpu_raise_softirq(smp_processor_id(), 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;
}

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);
}



/* Old style BHs */

static void (*bh_base[32])(void);
struct tasklet_struct bh_task_vec[32];

/* BHs are serialized by spinlock global_bh_lock.

   It is still possible to make synchronize_bh() as
   spin_unlock_wait(&global_bh_lock). This operation is not used
   by kernel now, so that this lock is not made private only
   due to wait_on_irq().

   It can be removed only after auditing all the BHs.
 */
spinlock_t global_bh_lock = SPIN_LOCK_UNLOCKED;

static void bh_action(unsigned long nr)
{
	if (!spin_trylock(&global_bh_lock))
		goto resched;

	if (bh_base[nr])
		bh_base[nr]();

	hardirq_endlock();
	spin_unlock(&global_bh_lock);
	return;

	spin_unlock(&global_bh_lock);
resched:
	mark_bh(nr);
}

void init_bh(int nr, void (*routine)(void))
{
	bh_base[nr] = routine;
	mb();
}

void remove_bh(int nr)
{
	tasklet_kill(bh_task_vec+nr);
	bh_base[nr] = NULL;
}

void __init softirq_init()
{
	int i;

	for (i=0; i<32; i++)
		tasklet_init(bh_task_vec+i, bh_action, i);

	open_softirq(TASKLET_SOFTIRQ, tasklet_action, NULL);
	open_softirq(HI_SOFTIRQ, tasklet_hi_action, NULL);
}

void __run_task_queue(task_queue *list)
{
	struct list_head head, *next;
	unsigned long flags;

	spin_lock_irqsave(&tqueue_lock, flags);
	list_add(&head, list);
	list_del_init(list);
	spin_unlock_irqrestore(&tqueue_lock, flags);

	next = head.next;
	while (next != &head) {
		void (*f) (void *);
		struct tq_struct *p;
		void *data;

		p = list_entry(next, struct tq_struct, list);
		next = next->next;
		f = p->routine;
		data = p->data;
		wmb();
		p->sync = 0;
		if (f)
			f(data);
	}
}

static int ksoftirqd(void * __bind_cpu)
{
	int cpu = (int) (long) __bind_cpu;

	daemonize();
	set_user_nice(current, 19);
	current->flags |= PF_IOTHREAD;
	sigfillset(&current->blocked);

	/* Migrate to the right CPU */
	set_cpus_allowed(current, 1UL << cpu);
	if (smp_processor_id() != cpu)
		BUG();

	sprintf(current->comm, "ksoftirqd_CPU%d", cpu);

	__set_current_state(TASK_INTERRUPTIBLE);
	mb();

	ksoftirqd_task(cpu) = current;

	for (;;) {
		if (!softirq_pending(cpu))
			schedule();

		__set_current_state(TASK_RUNNING);

		while (softirq_pending(cpu)) {
			do_softirq();
			cond_resched();
		}

		__set_current_state(TASK_INTERRUPTIBLE);
	}
}

static int __devinit cpu_callback(struct notifier_block *nfb,
				  unsigned long action,
				  void *hcpu)
{
	int hotcpu = (unsigned long)hcpu;

	if (action == CPU_ONLINE) {
		if (kernel_thread(ksoftirqd, hcpu, CLONE_KERNEL) < 0) {
			printk("ksoftirqd for %i failed\n", hotcpu);
			return NOTIFY_BAD;
		}

		while (!ksoftirqd_task(hotcpu))
			yield();
		return NOTIFY_OK;
 	}
	return NOTIFY_BAD;
}

static struct notifier_block cpu_nfb = { &cpu_callback, NULL, 0 };

__init int spawn_ksoftirqd(void)
{
	cpu_callback(&cpu_nfb, CPU_ONLINE, (void *)(long)smp_processor_id());
	register_cpu_notifier(&cpu_nfb);
	return 0;
}