Home Home > GIT Browse
summaryrefslogtreecommitdiff
blob: 76b318e88382e1e83448f8a42caac995651bd4a9 (plain)
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
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
/*
 * Xen event channels (FIFO-based ABI)
 *
 * Copyright (C) 2013 Citrix Systems R&D ltd.
 *
 * This source code is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License as
 * published by the Free Software Foundation; either version 2 of the
 * License, or (at your option) any later version.
 *
 * Or, when distributed separately from the Linux kernel or
 * incorporated into other software packages, subject to the following
 * license:
 *
 * Permission is hereby granted, free of charge, to any person obtaining a copy
 * of this source file (the "Software"), to deal in the Software without
 * restriction, including without limitation the rights to use, copy, modify,
 * merge, publish, distribute, sublicense, and/or sell copies of the Software,
 * and to permit persons to whom the Software is furnished to do so, subject to
 * the following conditions:
 *
 * The above copyright notice and this permission notice shall be included in
 * all copies or substantial portions of the Software.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
 * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
 * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
 * IN THE SOFTWARE.
 */

#define pr_fmt(fmt) "xen:" KBUILD_MODNAME ": " fmt

#include <linux/linkage.h>
#include <linux/interrupt.h>
#include <linux/irq.h>
#include <linux/smp.h>
#include <linux/percpu.h>
#include <linux/cpu.h>

#include <asm/barrier.h>
#include <asm/sync_bitops.h>
#include <asm/xen/hypercall.h>
#include <asm/xen/hypervisor.h>

#include <xen/xen.h>
#include <xen/xen-ops.h>
#include <xen/events.h>
#include <xen/interface/xen.h>
#include <xen/interface/event_channel.h>
#include <xen/page.h>

#include "events_internal.h"

#define EVENT_WORDS_PER_PAGE (XEN_PAGE_SIZE / sizeof(event_word_t))
#define MAX_EVENT_ARRAY_PAGES (EVTCHN_FIFO_NR_CHANNELS / EVENT_WORDS_PER_PAGE)

struct evtchn_fifo_queue {
	uint32_t head[EVTCHN_FIFO_MAX_QUEUES];
};

static DEFINE_PER_CPU(struct evtchn_fifo_control_block *, cpu_control_block);
static DEFINE_PER_CPU(struct evtchn_fifo_queue, cpu_queue);
static event_word_t *event_array[MAX_EVENT_ARRAY_PAGES] __read_mostly;
static unsigned event_array_pages __read_mostly;

/*
 * sync_set_bit() and friends must be unsigned long aligned.
 */
#if BITS_PER_LONG > 32

#define BM(w) (unsigned long *)((unsigned long)w & ~0x7UL)
#define EVTCHN_FIFO_BIT(b, w) \
    (((unsigned long)w & 0x4UL) ? (EVTCHN_FIFO_ ##b + 32) : EVTCHN_FIFO_ ##b)

#else

#define BM(w) ((unsigned long *)(w))
#define EVTCHN_FIFO_BIT(b, w) EVTCHN_FIFO_ ##b

#endif

static inline event_word_t *event_word_from_port(unsigned port)
{
	unsigned i = port / EVENT_WORDS_PER_PAGE;

	return event_array[i] + port % EVENT_WORDS_PER_PAGE;
}

static unsigned evtchn_fifo_max_channels(void)
{
	return EVTCHN_FIFO_NR_CHANNELS;
}

static unsigned evtchn_fifo_nr_channels(void)
{
	return event_array_pages * EVENT_WORDS_PER_PAGE;
}

static int init_control_block(int cpu,
                              struct evtchn_fifo_control_block *control_block)
{
	struct evtchn_fifo_queue *q = &per_cpu(cpu_queue, cpu);
	struct evtchn_init_control init_control;
	unsigned int i;

	/* Reset the control block and the local HEADs. */
	clear_page(control_block);
	for (i = 0; i < EVTCHN_FIFO_MAX_QUEUES; i++)
		q->head[i] = 0;

	init_control.control_gfn = virt_to_gfn(control_block);
	init_control.offset      = 0;
	init_control.vcpu        = xen_vcpu_nr(cpu);

	return HYPERVISOR_event_channel_op(EVTCHNOP_init_control, &init_control);
}

static void free_unused_array_pages(void)
{
	unsigned i;

	for (i = event_array_pages; i < MAX_EVENT_ARRAY_PAGES; i++) {
		if (!event_array[i])
			break;
		free_page((unsigned long)event_array[i]);
		event_array[i] = NULL;
	}
}

static void init_array_page(event_word_t *array_page)
{
	unsigned i;

	for (i = 0; i < EVENT_WORDS_PER_PAGE; i++)
		array_page[i] = 1 << EVTCHN_FIFO_MASKED;
}

static int evtchn_fifo_setup(struct irq_info *info)
{
	unsigned port = info->evtchn;
	unsigned new_array_pages;
	int ret;

	new_array_pages = port / EVENT_WORDS_PER_PAGE + 1;

	if (new_array_pages > MAX_EVENT_ARRAY_PAGES)
		return -EINVAL;

	while (event_array_pages < new_array_pages) {
		void *array_page;
		struct evtchn_expand_array expand_array;

		/* Might already have a page if we've resumed. */
		array_page = event_array[event_array_pages];
		if (!array_page) {
			array_page = (void *)__get_free_page(GFP_KERNEL);
			if (array_page == NULL) {
				ret = -ENOMEM;
				goto error;
			}
			event_array[event_array_pages] = array_page;
		}

		/* Mask all events in this page before adding it. */
		init_array_page(array_page);

		expand_array.array_gfn = virt_to_gfn(array_page);

		ret = HYPERVISOR_event_channel_op(EVTCHNOP_expand_array, &expand_array);
		if (ret < 0)
			goto error;

		event_array_pages++;
	}
	return 0;

  error:
	if (event_array_pages == 0)
		panic("xen: unable to expand event array with initial page (%d)\n", ret);
	else
		pr_err("unable to expand event array (%d)\n", ret);
	free_unused_array_pages();
	return ret;
}

static void evtchn_fifo_bind_to_cpu(struct irq_info *info, unsigned cpu)
{
	/* no-op */
}

static void evtchn_fifo_clear_pending(unsigned port)
{
	event_word_t *word = event_word_from_port(port);
	sync_clear_bit(EVTCHN_FIFO_BIT(PENDING, word), BM(word));
}

static void evtchn_fifo_set_pending(unsigned port)
{
	event_word_t *word = event_word_from_port(port);
	sync_set_bit(EVTCHN_FIFO_BIT(PENDING, word), BM(word));
}

static bool evtchn_fifo_is_pending(unsigned port)
{
	event_word_t *word = event_word_from_port(port);
	return sync_test_bit(EVTCHN_FIFO_BIT(PENDING, word), BM(word));
}

static bool evtchn_fifo_test_and_set_mask(unsigned port)
{
	event_word_t *word = event_word_from_port(port);
	return sync_test_and_set_bit(EVTCHN_FIFO_BIT(MASKED, word), BM(word));
}

static void evtchn_fifo_mask(unsigned port)
{
	event_word_t *word = event_word_from_port(port);
	sync_set_bit(EVTCHN_FIFO_BIT(MASKED, word), BM(word));
}

static bool evtchn_fifo_is_masked(unsigned port)
{
	event_word_t *word = event_word_from_port(port);
	return sync_test_bit(EVTCHN_FIFO_BIT(MASKED, word), BM(word));
}
/*
 * Clear MASKED, spinning if BUSY is set.
 */
static void clear_masked(volatile event_word_t *word)
{
	event_word_t new, old, w;

	w = *word;

	do {
		old = w & ~(1 << EVTCHN_FIFO_BUSY);
		new = old & ~(1 << EVTCHN_FIFO_MASKED);
		w = sync_cmpxchg(word, old, new);
	} while (w != old);
}

static void evtchn_fifo_unmask(unsigned port)
{
	event_word_t *word = event_word_from_port(port);

	BUG_ON(!irqs_disabled());

	clear_masked(word);
	if (evtchn_fifo_is_pending(port)) {
		struct evtchn_unmask unmask = { .port = port };
		(void)HYPERVISOR_event_channel_op(EVTCHNOP_unmask, &unmask);
	}
}

static uint32_t clear_linked(volatile event_word_t *word)
{
	event_word_t new, old, w;

	w = *word;

	do {
		old = w;
		new = (w & ~((1 << EVTCHN_FIFO_LINKED)
			     | EVTCHN_FIFO_LINK_MASK));
	} while ((w = sync_cmpxchg(word, old, new)) != old);

	return w & EVTCHN_FIFO_LINK_MASK;
}

static void handle_irq_for_port(unsigned port)
{
	int irq;

	irq = get_evtchn_to_irq(port);
	if (irq != -1)
		generic_handle_irq(irq);
}

static void consume_one_event(unsigned cpu,
			      struct evtchn_fifo_control_block *control_block,
			      unsigned priority, unsigned long *ready,
			      bool drop)
{
	struct evtchn_fifo_queue *q = &per_cpu(cpu_queue, cpu);
	uint32_t head;
	unsigned port;
	event_word_t *word;

	head = q->head[priority];

	/*
	 * Reached the tail last time?  Read the new HEAD from the
	 * control block.
	 */
	if (head == 0) {
		virt_rmb(); /* Ensure word is up-to-date before reading head. */
		head = control_block->head[priority];
	}

	port = head;
	word = event_word_from_port(port);
	head = clear_linked(word);

	/*
	 * If the link is non-zero, there are more events in the
	 * queue, otherwise the queue is empty.
	 *
	 * If the queue is empty, clear this priority from our local
	 * copy of the ready word.
	 */
	if (head == 0)
		clear_bit(priority, ready);

	if (evtchn_fifo_is_pending(port) && !evtchn_fifo_is_masked(port)) {
		if (unlikely(drop))
			pr_warn("Dropping pending event for port %u\n", port);
		else
			handle_irq_for_port(port);
	}

	q->head[priority] = head;
}

static void __evtchn_fifo_handle_events(unsigned cpu, bool drop)
{
	struct evtchn_fifo_control_block *control_block;
	unsigned long ready;
	unsigned q;

	control_block = per_cpu(cpu_control_block, cpu);

	ready = xchg(&control_block->ready, 0);

	while (ready) {
		q = find_first_bit(&ready, EVTCHN_FIFO_MAX_QUEUES);
		consume_one_event(cpu, control_block, q, &ready, drop);
		ready |= xchg(&control_block->ready, 0);
	}
}

static void evtchn_fifo_handle_events(unsigned cpu)
{
	__evtchn_fifo_handle_events(cpu, false);
}

static void evtchn_fifo_resume(void)
{
	unsigned cpu;

	for_each_possible_cpu(cpu) {
		void *control_block = per_cpu(cpu_control_block, cpu);
		int ret;

		if (!control_block)
			continue;

		/*
		 * If this CPU is offline, take the opportunity to
		 * free the control block while it is not being
		 * used.
		 */
		if (!cpu_online(cpu)) {
			free_page((unsigned long)control_block);
			per_cpu(cpu_control_block, cpu) = NULL;
			continue;
		}

		ret = init_control_block(cpu, control_block);
		BUG_ON(ret < 0);
	}

	/*
	 * The event array starts out as empty again and is extended
	 * as normal when events are bound.  The existing pages will
	 * be reused.
	 */
	event_array_pages = 0;
}

static const struct evtchn_ops evtchn_ops_fifo = {
	.max_channels      = evtchn_fifo_max_channels,
	.nr_channels       = evtchn_fifo_nr_channels,
	.setup             = evtchn_fifo_setup,
	.bind_to_cpu       = evtchn_fifo_bind_to_cpu,
	.clear_pending     = evtchn_fifo_clear_pending,
	.set_pending       = evtchn_fifo_set_pending,
	.is_pending        = evtchn_fifo_is_pending,
	.test_and_set_mask = evtchn_fifo_test_and_set_mask,
	.mask              = evtchn_fifo_mask,
	.unmask            = evtchn_fifo_unmask,
	.handle_events     = evtchn_fifo_handle_events,
	.resume            = evtchn_fifo_resume,
};

static int evtchn_fifo_alloc_control_block(unsigned cpu)
{
	void *control_block = NULL;
	int ret = -ENOMEM;

	control_block = (void *)__get_free_page(GFP_KERNEL);
	if (control_block == NULL)
		goto error;

	ret = init_control_block(cpu, control_block);
	if (ret < 0)
		goto error;

	per_cpu(cpu_control_block, cpu) = control_block;

	return 0;

  error:
	free_page((unsigned long)control_block);
	return ret;
}

static int xen_evtchn_cpu_prepare(unsigned int cpu)
{
	if (!per_cpu(cpu_control_block, cpu))
		return evtchn_fifo_alloc_control_block(cpu);
	return 0;
}

static int xen_evtchn_cpu_dead(unsigned int cpu)
{
	__evtchn_fifo_handle_events(cpu, true);
	return 0;
}

int __init xen_evtchn_fifo_init(void)
{
	int cpu = smp_processor_id();
	int ret;

	ret = evtchn_fifo_alloc_control_block(cpu);
	if (ret < 0)
		return ret;

	pr_info("Using FIFO-based ABI\n");

	evtchn_ops = &evtchn_ops_fifo;

	cpuhp_setup_state_nocalls(CPUHP_XEN_EVTCHN_PREPARE,
				  "xen/evtchn:prepare",
				  xen_evtchn_cpu_prepare, xen_evtchn_cpu_dead);

	return ret;
}