summaryrefslogtreecommitdiffstats
path: root/drivers/input/mousedev.c
blob: 412fa71245afe26a7a8ad75705566f83633ba347 (plain) (blame)
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
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
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
/*
 * Input driver to ExplorerPS/2 device driver module.
 *
 * Copyright (c) 1999-2002 Vojtech Pavlik
 * Copyright (c) 2004      Dmitry Torokhov
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 as published by
 * the Free Software Foundation.
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#define MOUSEDEV_MINOR_BASE	32
#define MOUSEDEV_MINORS		31
#define MOUSEDEV_MIX		63

#include <linux/bitops.h>
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/poll.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/input.h>
#include <linux/random.h>
#include <linux/major.h>
#include <linux/device.h>
#include <linux/cdev.h>
#include <linux/kernel.h>

MODULE_AUTHOR("Vojtech Pavlik <vojtech@ucw.cz>");
MODULE_DESCRIPTION("Mouse (ExplorerPS/2) device interfaces");
MODULE_LICENSE("GPL");

#ifndef CONFIG_INPUT_MOUSEDEV_SCREEN_X
#define CONFIG_INPUT_MOUSEDEV_SCREEN_X	1024
#endif
#ifndef CONFIG_INPUT_MOUSEDEV_SCREEN_Y
#define CONFIG_INPUT_MOUSEDEV_SCREEN_Y	768
#endif

static int xres = CONFIG_INPUT_MOUSEDEV_SCREEN_X;
module_param(xres, uint, 0644);
MODULE_PARM_DESC(xres, "Horizontal screen resolution");

static int yres = CONFIG_INPUT_MOUSEDEV_SCREEN_Y;
module_param(yres, uint, 0644);
MODULE_PARM_DESC(yres, "Vertical screen resolution");

static unsigned tap_time = 200;
module_param(tap_time, uint, 0644);
MODULE_PARM_DESC(tap_time, "Tap time for touchpads in absolute mode (msecs)");

struct mousedev_hw_data {
	int dx, dy, dz;
	int x, y;
	int abs_event;
	unsigned long buttons;
};

struct mousedev {
	int open;
	struct input_handle handle;
	wait_queue_head_t wait;
	struct list_head client_list;
	spinlock_t client_lock; /* protects client_list */
	struct mutex mutex;
	struct device dev;
	struct cdev cdev;
	bool exist;

	struct list_head mixdev_node;
	bool opened_by_mixdev;

	struct mousedev_hw_data packet;
	unsigned int pkt_count;
	int old_x[4], old_y[4];
	int frac_dx, frac_dy;
	unsigned long touch;

	int (*open_device)(struct mousedev *mousedev);
	void (*close_device)(struct mousedev *mousedev);
};

enum mousedev_emul {
	MOUSEDEV_EMUL_PS2,
	MOUSEDEV_EMUL_IMPS,
	MOUSEDEV_EMUL_EXPS
};

struct mousedev_motion {
	int dx, dy, dz;
	unsigned long buttons;
};

#define PACKET_QUEUE_LEN	16
struct mousedev_client {
	struct fasync_struct *fasync;
	struct mousedev *mousedev;
	struct list_head node;

	struct mousedev_motion packets[PACKET_QUEUE_LEN];
	unsigned int head, tail;
	spinlock_t packet_lock;
	int pos_x, pos_y;

	u8 ps2[6];
	unsigned char ready, buffer, bufsiz;
	unsigned char imexseq, impsseq;
	enum mousedev_emul mode;
	unsigned long last_buttons;
};

#define MOUSEDEV_SEQ_LEN	6

static unsigned char mousedev_imps_seq[] = { 0xf3, 200, 0xf3, 100, 0xf3, 80 };
static unsigned char mousedev_imex_seq[] = { 0xf3, 200, 0xf3, 200, 0xf3, 80 };

static struct mousedev *mousedev_mix;
static LIST_HEAD(mousedev_mix_list);

#define fx(i)  (mousedev->old_x[(mousedev->pkt_count - (i)) & 03])
#define fy(i)  (mousedev->old_y[(mousedev->pkt_count - (i)) & 03])

static void mousedev_touchpad_event(struct input_dev *dev,
				    struct mousedev *mousedev,
				    unsigned int code, int value)
{
	int size, tmp;
	enum { FRACTION_DENOM = 128 };

	switch (code) {

	case ABS_X:

		fx(0) = value;
		if (mousedev->touch && mousedev->pkt_count >= 2) {
			size = input_abs_get_max(dev, ABS_X) -
					input_abs_get_min(dev, ABS_X);
			if (size == 0)
				size = 256 * 2;

			tmp = ((value - fx(2)) * 256 * FRACTION_DENOM) / size;
			tmp += mousedev->frac_dx;
			mousedev->packet.dx = tmp / FRACTION_DENOM;
			mousedev->frac_dx =
				tmp - mousedev->packet.dx * FRACTION_DENOM;
		}
		break;

	case ABS_Y:
		fy(0) = value;
		if (mousedev->touch && mousedev->pkt_count >= 2) {
			/* use X size for ABS_Y to keep the same scale */
			size = input_abs_get_max(dev, ABS_X) -
					input_abs_get_min(dev, ABS_X);
			if (size == 0)
				size = 256 * 2;

			tmp = -((value - fy(2)) * 256 * FRACTION_DENOM) / size;
			tmp += mousedev->frac_dy;
			mousedev->packet.dy = tmp / FRACTION_DENOM;
			mousedev->frac_dy = tmp -
				mousedev->packet.dy * FRACTION_DENOM;
		}
		break;
	}
}

static void mousedev_abs_event(struct input_dev *dev, struct mousedev *mousedev,
				unsigned int code, int value)
{
	int min, max, size;

	switch (code) {

	case ABS_X:
		min = input_abs_get_min(dev, ABS_X);
		max = input_abs_get_max(dev, ABS_X);

		size = max - min;
		if (size == 0)
			size = xres ? : 1;

		value = clamp(value, min, max);

		mousedev->packet.x = ((value - min) * xres) / size;
		mousedev->packet.abs_event = 1;
		break;

	case ABS_Y:
		min = input_abs_get_min(dev, ABS_Y);
		max = input_abs_get_max(dev, ABS_Y);

		size = max - min;
		if (size == 0)
			size = yres ? : 1;

		value = clamp(value, min, max);

		mousedev->packet.y = yres - ((value - min) * yres) / size;
		mousedev->packet.abs_event = 1;
		break;
	}
}

static void mousedev_rel_event(struct mousedev *mousedev,
				unsigned int code, int value)
{
	switch (code) {
	case REL_X:
		mousedev->packet.dx += value;
		break;

	case REL_Y:
		mousedev->packet.dy -= value;
		break;

	case REL_WHEEL:
		mousedev->packet.dz -= value;
		break;
	}
}

static void mousedev_key_event(struct mousedev *mousedev,
				unsigned int code, int value)
{
	int index;

	switch (code) {

	case BTN_TOUCH:
	case BTN_0:
	case BTN_LEFT:		index = 0; break;

	case BTN_STYLUS:
	case BTN_1:
	case BTN_RIGHT:		index = 1; break;

	case BTN_2:
	case BTN_FORWARD:
	case BTN_STYLUS2:
	case BTN_MIDDLE:	index = 2; break;

	case BTN_3:
	case BTN_BACK:
	case BTN_SIDE:		index = 3; break;

	case BTN_4:
	case BTN_EXTRA:		index = 4; break;

	default:		return;
	}

	if (value) {
		set_bit(index, &mousedev->packet.buttons);
		set_bit(index, &mousedev_mix->packet.buttons);
	} else {
		clear_bit(index, &mousedev->packet.buttons);
		clear_bit(index, &mousedev_mix->packet.buttons);
	}
}

static void mousedev_notify_readers(struct mousedev *mousedev,
				    struct mousedev_hw_data *packet)
{
	struct mousedev_client *client;
	struct mousedev_motion *p;
	unsigned int new_head;
	int wake_readers = 0;

	rcu_read_lock();
	list_for_each_entry_rcu(client, &mousedev->client_list, node) {

		/* Just acquire the lock, interrupts already disabled */
		spin_lock(&client->packet_lock);

		p = &client->packets[client->head];
		if (client->ready && p->buttons != mousedev->packet.buttons) {
			new_head = (client->head + 1) % PACKET_QUEUE_LEN;
			if (new_head != client->tail) {
				p = &client->packets[client->head = new_head];
				memset(p, 0, sizeof(struct mousedev_motion));
			}
		}

		if (packet->abs_event) {
			p->dx += packet->x - client->pos_x;
			p->dy += packet->y - client->pos_y;
			client->pos_x = packet->x;
			client->pos_y = packet->y;
		}

		client->pos_x += packet->dx;
		client->pos_x = clamp_val(client->pos_x, 0, xres);

		client->pos_y += packet->dy;
		client->pos_y = clamp_val(client->pos_y, 0, yres);

		p->dx += packet->dx;
		p->dy += packet->dy;
		p->dz += packet->dz;
		p->buttons = mousedev->packet.buttons;

		if (p->dx || p->dy || p->dz ||
		    p->buttons != client->last_buttons)
			client->ready = 1;

		spin_unlock(&client->packet_lock);

		if (client->ready) {
			kill_fasync(&client->fasync, SIGIO, POLL_IN);
			wake_readers = 1;
		}
	}
	rcu_read_unlock();

	if (wake_readers)
		wake_up_interruptible(&mousedev->wait);
}

static void mousedev_touchpad_touch(struct mousedev *mousedev, int value)
{
	if (!value) {
		if (mousedev->touch &&
		    time_before(jiffies,
				mousedev->touch + msecs_to_jiffies(tap_time))) {
			/*
			 * Toggle left button to emulate tap.
			 * We rely on the fact that mousedev_mix always has 0
			 * motion packet so we won't mess current position.
			 */
			set_bit(0, &mousedev->packet.buttons);
			set_bit(0, &mousedev_mix->packet.buttons);
			mousedev_notify_readers(mousedev, &mousedev_mix->packet);
			mousedev_notify_readers(mousedev_mix,
						&mousedev_mix->packet);
			clear_bit(0, &mousedev->packet.buttons);
			clear_bit(0, &mousedev_mix->packet.buttons);
		}
		mousedev->touch = mousedev->pkt_count = 0;
		mousedev->frac_dx = 0;
		mousedev->frac_dy = 0;

	} else if (!mousedev->touch)
		mousedev->touch = jiffies;
}

static void mousedev_event(struct input_handle *handle,
			   unsigned int type, unsigned int code, int value)
{
	struct mousedev *mousedev = handle->private;

	switch (type) {

	case EV_ABS:
		/* Ignore joysticks */
		if (test_bit(BTN_TRIGGER, handle->dev->keybit))
			return;

		if (test_bit(BTN_TOOL_FINGER, handle->dev->keybit))
			mousedev_touchpad_event(handle->dev,
						mousedev, code, value);
		else
			mousedev_abs_event(handle->dev, mousedev, code, value);

		break;

	case EV_REL:
		mousedev_rel_event(mousedev, code, value);
		break;

	case EV_KEY:
		if (value != 2) {
			if (code == BTN_TOUCH &&
			    test_bit(BTN_TOOL_FINGER, handle->dev->keybit))
				mousedev_touchpad_touch(mousedev, value);
			else
				mousedev_key_event(mousedev, code, value);
		}
		break;

	case EV_SYN:
		if (code == SYN_REPORT) {
			if (mousedev->touch) {
				mousedev->pkt_count++;
				/*
				 * Input system eats duplicate events,
				 * but we need all of them to do correct
				 * averaging so apply present one forward
				 */
				fx(0) = fx(1);
				fy(0) = fy(1);
			}

			mousedev_notify_readers(mousedev, &mousedev->packet);
			mousedev_notify_readers(mousedev_mix, &mousedev->packet);

			mousedev->packet.dx = mousedev->packet.dy =
				mousedev->packet.dz = 0;
			mousedev->packet.abs_event = 0;
		}
		break;
	}
}

static int mousedev_fasync(int fd, struct file *file, int on)
{
	struct mousedev_client *client = file->private_data;

	return fasync_helper(fd, file, on, &client->fasync);
}

static void mousedev_free(struct device *dev)
{
	struct mousedev *mousedev = container_of(dev, struct mousedev, dev);

	input_put_device(mousedev->handle.dev);
	kfree(mousedev);
}

static int mousedev_open_device(struct mousedev *mousedev)
{
	int retval;

	retval = mutex_lock_interruptible(&mousedev->mutex);
	if (retval)
		return retval;

	if (!mousedev->exist)
		retval = -ENODEV;
	else if (!mousedev->open++) {
		retval = input_open_device(&mousedev->handle);
		if (retval)
			mousedev->open--;
	}

	mutex_unlock(&mousedev->mutex);
	return retval;
}

static void mousedev_close_device(struct mousedev *mousedev)
{
	mutex_lock(&mousedev->mutex);

	if (mousedev->exist && !--mousedev->open)
		input_close_device(&mousedev->handle);

	mutex_unlock(&mousedev->mutex);
}

/*
 * Open all available devices so they can all be multiplexed in one.
 * stream. Note that this function is called with mousedev_mix->mutex
 * held.
 */
static int mixdev_open_devices(struct mousedev *mixdev)
{
	int error;

	error = mutex_lock_interruptible(&mixdev->mutex);
	if (error)
		return error;

	if (!mixdev->open++) {
		struct mousedev *mousedev;

		list_for_each_entry(mousedev, &mousedev_mix_list, mixdev_node) {
			if (!mousedev->opened_by_mixdev) {
				if (mousedev_open_device(mousedev))
					continue;

				mousedev->opened_by_mixdev = true;
			}
		}
	}

	mutex_unlock(&mixdev->mutex);
	return 0;
}

/*
 * Close all devices that were opened as part of multiplexed
 * device. Note that this function is called with mousedev_mix->mutex
 * held.
 */
static void mixdev_close_devices(struct mousedev *mixdev)
{
	mutex_lock(&mixdev->mutex);

	if (!--mixdev->open) {
		struct mousedev *mousedev;

		list_for_each_entry(mousedev, &mousedev_mix_list, mixdev_node) {
			if (mousedev->opened_by_mixdev) {
				mousedev->opened_by_mixdev = false;
				mousedev_close_device(mousedev);
			}
		}
	}

	mutex_unlock(&mixdev->mutex);
}


static void mousedev_attach_client(struct mousedev *mousedev,
				   struct mousedev_client *client)
{
	spin_lock(&mousedev->client_lock);
	list_add_tail_rcu(&client->node, &mousedev->client_list);
	spin_unlock(&mousedev->client_lock);
}

static void mousedev_detach_client(struct mousedev *mousedev,
				   struct mousedev_client *client)
{
	spin_lock(&mousedev->client_lock);
	list_del_rcu(&client->node);
	spin_unlock(&mousedev->client_lock);
	synchronize_rcu();
}

static int mousedev_release(struct inode *inode, struct file *file)
{
	struct mousedev_client *client = file->private_data;
	struct mousedev *mousedev = client->mousedev;

	mousedev_detach_client(mousedev, client);
	kfree(client);

	mousedev->close_device(mousedev);

	return 0;
}

static int mousedev_open(struct inode *inode, struct file *file)
{
	struct mousedev_client *client;
	struct mousedev *mousedev;
	int error;

#ifdef CONFIG_INPUT_MOUSEDEV_PSAUX
	if (imajor(inode) == MISC_MAJOR)
		mousedev = mousedev_mix;
	else
#endif
		mousedev = container_of(inode->i_cdev, struct mousedev, cdev);

	client = kzalloc(sizeof(struct mousedev_client), GFP_KERNEL);
	if (!client)
		return -ENOMEM;

	spin_lock_init(&client->packet_lock);
	client->pos_x = xres / 2;
	client->pos_y = yres / 2;
	client->mousedev = mousedev;
	mousedev_attach_client(mousedev, client);

	error = mousedev->open_device(mousedev);
	if (error)
		goto err_free_client;

	file->private_data = client;
	nonseekable_open(inode, file);

	return 0;

 err_free_client:
	mousedev_detach_client(mousedev, client);
	kfree(client);
	return error;
}

static void mousedev_packet(struct mousedev_client *client, u8 *ps2_data)
{
	struct mousedev_motion *p = &client->packets[client->tail];
	s8 dx, dy, dz;

	dx = clamp_val(p->dx, -127, 127);
	p->dx -= dx;

	dy = clamp_val(p->dy, -127, 127);
	p->dy -= dy;

	ps2_data[0] = BIT(3);
	ps2_data[0] |= ((dx & BIT(7)) >> 3) | ((dy & BIT(7)) >> 2);
	ps2_data[0] |= p->buttons & 0x07;
	ps2_data[1] = dx;
	ps2_data[2] = dy;

	switch (client->mode) {
	case MOUSEDEV_EMUL_EXPS:
		dz = clamp_val(p->dz, -7, 7);
		p->dz -= dz;

		ps2_data[3] = (dz & 0x0f) | ((p->buttons & 0x18) << 1);
		client->bufsiz = 4;
		break;

	case MOUSEDEV_EMUL_IMPS:
		dz = clamp_val(p->dz, -127, 127);
		p->dz -= dz;

		ps2_data[0] |= ((p->buttons & 0x10) >> 3) |
			       ((p->buttons & 0x08) >> 1);
		ps2_data[3] = dz;

		client->bufsiz = 4;
		break;

	case MOUSEDEV_EMUL_PS2:
	default:
		p->dz = 0;

		ps2_data[0] |= ((p->buttons & 0x10) >> 3) |
			       ((p->buttons & 0x08) >> 1);

		client->bufsiz = 3;
		break;
	}

	if (!p->dx && !p->dy && !p->dz) {
		if (client->tail == client->head) {
			client->ready = 0;
			client->last_buttons = p->buttons;
		} else
			client->tail = (client->tail + 1) % PACKET_QUEUE_LEN;
	}
}

static void mousedev_generate_response(struct mousedev_client *client,
					int command)
{
	client->ps2[0] = 0xfa; /* ACK */

	switch (command) {

	case 0xeb: /* Poll */
		mousedev_packet(client, &client->ps2[1]);
		client->bufsiz++; /* account for leading ACK */
		break;

	case 0xf2: /* Get ID */
		switch (client->mode) {
		case MOUSEDEV_EMUL_PS2:
			client->ps2[1] = 0;
			break;
		case MOUSEDEV_EMUL_IMPS:
			client->ps2[1] = 3;
			break;
		case MOUSEDEV_EMUL_EXPS:
			client->ps2[1] = 4;
			break;
		}
		client->bufsiz = 2;
		break;

	case 0xe9: /* Get info */
		client->ps2[1] = 0x60; client->ps2[2] = 3; client->ps2[3] = 200;
		client->bufsiz = 4;
		break;

	case 0xff: /* Reset */
		client->impsseq = client->imexseq = 0;
		client->mode = MOUSEDEV_EMUL_PS2;
		client->ps2[1] = 0xaa; client->ps2[2] = 0x00;
		client->bufsiz = 3;
		break;

	default:
		client->bufsiz = 1;
		break;
	}
	client->buffer = client->bufsiz;
}

static ssize_t mousedev_write(struct file *file, const char __user *buffer,
				size_t count, loff_t *ppos)
{
	struct mousedev_client *client = file->private_data;
	unsigned char c;
	unsigned int i;

	for (i = 0; i < count; i++) {

		if (get_user(c, buffer + i))
			return -EFAULT;

		spin_lock_irq(&client->packet_lock);

		if (c == mousedev_imex_seq[client->imexseq]) {
			if (++client->imexseq == MOUSEDEV_SEQ_LEN) {
				client->imexseq = 0;
				client->mode = MOUSEDEV_EMUL_EXPS;
			}
		} else
			client->imexseq = 0;

		if (c == mousedev_imps_seq[client->impsseq]) {
			if (++client->impsseq == MOUSEDEV_SEQ_LEN) {
				client->impsseq = 0;
				client->mode = MOUSEDEV_EMUL_IMPS;
			}
		} else
			client->impsseq = 0;

		mousedev_generate_response(client, c);

		spin_unlock_irq(&client->packet_lock);
		cond_resched();
	}

	kill_fasync(&client->fasync, SIGIO, POLL_IN);
	wake_up_interruptible(&client->mousedev->wait);

	return count;
}

static ssize_t mousedev_read(struct file *file, char __user *buffer,
			     size_t count, loff_t *ppos)
{
	struct mousedev_client *client = file->private_data;
	struct mousedev *mousedev = client->mousedev;
	u8 data[sizeof(client->ps2)];
	int retval = 0;

	if (!client->ready && !client->buffer && mousedev->exist &&
	    (file->f_flags & O_NONBLOCK))
		return -EAGAIN;

	retval = wait_event_interruptible(mousedev->wait,
			!mousedev->exist || client->ready || client->buffer);
	if (retval)
		return retval;

	if (!mousedev->exist)
		return -ENODEV;

	spin_lock_irq(&client->packet_lock);

	if (!client->buffer && client->ready) {
		mousedev_packet(client, client->ps2);
		client->buffer = client->bufsiz;
	}

	if (count > client->buffer)
		count = client->buffer;

	memcpy(data, client->ps2 + client->bufsiz - client->buffer, count);
	client->buffer -= count;

	spin_unlock_irq(&client->packet_lock);

	if (copy_to_user(buffer, data, count))
		return -EFAULT;

	return count;
}

/* No kernel lock - fine */
static __poll_t mousedev_poll(struct file *file, poll_table *wait)
{
	struct mousedev_client *client = file->private_data;
	struct mousedev *mousedev = client->mousedev;
	__poll_t mask;

	poll_wait(file, &mousedev->wait, wait);

	mask = mousedev->exist ? EPOLLOUT | EPOLLWRNORM : EPOLLHUP | EPOLLERR;
	if (client->ready || client->buffer)
		mask |= EPOLLIN | EPOLLRDNORM;

	return mask;
}

static const struct file_operations mousedev_fops = {
	.owner		= THIS_MODULE,
	.read		= mousedev_read,
	.write		= mousedev_write,
	.poll		= mousedev_poll,
	.open		= mousedev_open,
	.release	= mousedev_release,
	.fasync		= mousedev_fasync,
	.llseek		= noop_llseek,
};

/*
 * Mark device non-existent. This disables writes, ioctls and
 * prevents new users from opening the device. Already posted
 * blocking reads will stay, however new ones will fail.
 */
static void mousedev_mark_dead(struct mousedev *mousedev)
{
	mutex_lock(&mousedev->mutex);
	mousedev->exist = false;
	mutex_unlock(&mousedev->mutex);
}

/*
 * Wake up users waiting for IO so they can disconnect from
 * dead device.
 */
static void mousedev_hangup(struct mousedev *mousedev)
{
	struct mousedev_client *client;

	spin_lock(&mousedev->client_lock);
	list_for_each_entry(client, &mousedev->client_list, node)
		kill_fasync(&client->fasync, SIGIO, POLL_HUP);
	spin_unlock(&mousedev->client_lock);

	wake_up_interruptible(&mousedev->wait);
}

static void mousedev_cleanup(struct mousedev *mousedev)
{
	struct input_handle *handle = &mousedev->handle;

	mousedev_mark_dead(mousedev);
	mousedev_hangup(mousedev);

	/* mousedev is marked dead so no one else accesses mousedev->open */
	if (mousedev->open)
		input_close_device(handle);
}

static int mousedev_reserve_minor(bool mixdev)
{
	int minor;

	if (mixdev) {
		minor = input_get_new_minor(MOUSEDEV_MIX, 1, false);
		if (minor < 0)
			pr_err("failed to reserve mixdev minor: %d\n", minor);
	} else {
		minor = input_get_new_minor(MOUSEDEV_MINOR_BASE,
					    MOUSEDEV_MINORS, true);
		if (minor < 0)
			pr_err("failed to reserve new minor: %d\n", minor);
	}

	return minor;
}

static struct mousedev *mousedev_create(struct input_dev *dev,
					struct input_handler *handler,
					bool mixdev)
{
	struct mousedev *mousedev;
	int minor;
	int error;

	minor = mousedev_reserve_minor(mixdev);
	if (minor < 0) {
		error = minor;
		goto err_out;
	}

	mousedev = kzalloc(sizeof(struct mousedev), GFP_KERNEL);
	if (!mousedev) {
		error = -ENOMEM;
		goto err_free_minor;
	}

	INIT_LIST_HEAD(&mousedev->client_list);
	INIT_LIST_HEAD(&mousedev->mixdev_node);
	spin_lock_init(&mousedev->client_lock);
	mutex_init(&mousedev->mutex);
	lockdep_set_subclass(&mousedev->mutex,
			     mixdev ? SINGLE_DEPTH_NESTING : 0);
	init_waitqueue_head(&mousedev->wait);

	if (mixdev) {
		dev_set_name(&mousedev->dev, "mice");

		mousedev->open_device = mixdev_open_devices;
		mousedev->close_device = mixdev_close_devices;
	} else {
		int dev_no = minor;
		/* Normalize device number if it falls into legacy range */
		if (dev_no < MOUSEDEV_MINOR_BASE + MOUSEDEV_MINORS)
			dev_no -= MOUSEDEV_MINOR_BASE;
		dev_set_name(&mousedev->dev, "mouse%d", dev_no);

		mousedev->open_device = mousedev_open_device;
		mousedev->close_device = mousedev_close_device;
	}

	mousedev->exist = true;
	mousedev->handle.dev = input_get_device(dev);
	mousedev->handle.name = dev_name(&mousedev->dev);
	mousedev->handle.handler = handler;
	mousedev->handle.private = mousedev;

	mousedev->dev.class = &input_class;
	if (dev)
		mousedev->dev.parent = &dev->dev;
	mousedev->dev.devt = MKDEV(INPUT_MAJOR, minor);
	mousedev->dev.release = mousedev_free;
	device_initialize(&mousedev->dev);

	if (!mixdev) {
		error = input_register_handle(&mousedev->handle);
		if (error)
			goto err_free_mousedev;
	}

	cdev_init(&mousedev->cdev, &mousedev_fops);

	error = cdev_device_add(&mousedev->cdev, &mousedev->dev);
	if (error)
		goto err_cleanup_mousedev;

	return mousedev;

 err_cleanup_mousedev:
	mousedev_cleanup(mousedev);
	if (!mixdev)
		input_unregister_handle(&mousedev->handle);
 err_free_mousedev:
	put_device(&mousedev->dev);
 err_free_minor:
	input_free_minor(minor);
 err_out:
	return ERR_PTR(error);
}

static void mousedev_destroy(struct mousedev *mousedev)
{
	cdev_device_del(&mousedev->cdev, &mousedev->dev);
	mousedev_cleanup(mousedev);
	input_free_minor(MINOR(mousedev->dev.devt));
	if (mousedev != mousedev_mix)
		input_unregister_handle(&mousedev->handle);
	put_device(&mousedev->dev);
}

static int mixdev_add_device(struct mousedev *mousedev)
{
	int retval;

	retval = mutex_lock_interruptible(&mousedev_mix->mutex);
	if (retval)
		return retval;

	if (mousedev_mix->open) {
		retval = mousedev_open_device(mousedev);
		if (retval)
			goto out;

		mousedev->opened_by_mixdev = true;
	}

	get_device(&mousedev->dev);
	list_add_tail(&mousedev->mixdev_node, &mousedev_mix_list);

 out:
	mutex_unlock(&mousedev_mix->mutex);
	return retval;
}

static void mixdev_remove_device(struct mousedev *mousedev)
{
	mutex_lock(&mousedev_mix->mutex);

	if (mousedev->opened_by_mixdev) {
		mousedev->opened_by_mixdev = false;
		mousedev_close_device(mousedev);
	}

	list_del_init(&mousedev->mixdev_node);
	mutex_unlock(&mousedev_mix->mutex);

	put_device(&mousedev->dev);
}

static int mousedev_connect(struct input_handler *handler,
			    struct input_dev *dev,
			    const struct input_device_id *id)
{
	struct mousedev *mousedev;
	int error;

	mousedev = mousedev_create(dev, handler, false);
	if (IS_ERR(mousedev))
		return PTR_ERR(mousedev);

	error = mixdev_add_device(mousedev);
	if (error) {
		mousedev_destroy(mousedev);
		return error;
	}

	return 0;
}

static void mousedev_disconnect(struct input_handle *handle)
{
	struct mousedev *mousedev = handle->private;

	mixdev_remove_device(mousedev);
	mousedev_destroy(mousedev);
}

static const struct input_device_id mousedev_ids[] = {
	{
		.flags = INPUT_DEVICE_ID_MATCH_EVBIT |
				INPUT_DEVICE_ID_MATCH_KEYBIT |
				INPUT_DEVICE_ID_MATCH_RELBIT,
		.evbit = { BIT_MASK(EV_KEY) | BIT_MASK(EV_REL) },
		.keybit = { [BIT_WORD(BTN_LEFT)] = BIT_MASK(BTN_LEFT) },
		.relbit = { BIT_MASK(REL_X) | BIT_MASK(REL_Y) },
	},	/* A mouse like device, at least one button,
		   two relative axes */
	{
		.flags = INPUT_DEVICE_ID_MATCH_EVBIT |
				INPUT_DEVICE_ID_MATCH_RELBIT,
		.evbit = { BIT_MASK(EV_KEY) | BIT_MASK(EV_REL) },
		.relbit = { BIT_MASK(REL_WHEEL) },
	},	/* A separate scrollwheel */
	{
		.flags = INPUT_DEVICE_ID_MATCH_EVBIT |
				INPUT_DEVICE_ID_MATCH_KEYBIT |
				INPUT_DEVICE_ID_MATCH_ABSBIT,
		.evbit = { BIT_MASK(EV_KEY) | BIT_MASK(EV_ABS) },
		.keybit = { [BIT_WORD(BTN_TOUCH)] = BIT_MASK(BTN_TOUCH) },
		.absbit = { BIT_MASK(ABS_X) | BIT_MASK(ABS_Y) },
	},	/* A tablet like device, at least touch detection,
		   two absolute axes */
	{
		.flags = INPUT_DEVICE_ID_MATCH_EVBIT |
				INPUT_DEVICE_ID_MATCH_KEYBIT |
				INPUT_DEVICE_ID_MATCH_ABSBIT,
		.evbit = { BIT_MASK(EV_KEY) | BIT_MASK(EV_ABS) },
		.keybit = { [BIT_WORD(BTN_TOOL_FINGER)] =
				BIT_MASK(BTN_TOOL_FINGER) },
		.absbit = { BIT_MASK(ABS_X) | BIT_MASK(ABS_Y) |
				BIT_MASK(ABS_PRESSURE) |
				BIT_MASK(ABS_TOOL_WIDTH) },
	},	/* A touchpad */
	{
		.flags = INPUT_DEVICE_ID_MATCH_EVBIT |
			INPUT_DEVICE_ID_MATCH_KEYBIT |
			INPUT_DEVICE_ID_MATCH_ABSBIT,
		.evbit = { BIT_MASK(EV_KEY) | BIT_MASK(EV_ABS) },
		.keybit = { [BIT_WORD(BTN_LEFT)] = BIT_MASK(BTN_LEFT) },
		.absbit = { BIT_MASK(ABS_X) | BIT_MASK(ABS_Y) },
	},	/* Mouse-like device with absolute X and Y but ordinary
		   clicks, like hp ILO2 High Performance mouse */

	{ },	/* Terminating entry */
};

MODULE_DEVICE_TABLE(input, mousedev_ids);

static struct input_handler mousedev_handler = {
	.event		= mousedev_event,
	.connect	= mousedev_connect,
	.disconnect	= mousedev_disconnect,
	.legacy_minors	= true,
	.minor		= MOUSEDEV_MINOR_BASE,
	.name		= "mousedev",
	.id_table	= mousedev_ids,
};

#ifdef CONFIG_INPUT_MOUSEDEV_PSAUX
#include <linux/miscdevice.h>

static struct miscdevice psaux_mouse = {
	.minor	= PSMOUSE_MINOR,
	.name	= "psaux",
	.fops	= &mousedev_fops,
};

static bool psaux_registered;

static void __init mousedev_psaux_register(void)
{
	int error;

	error = misc_register(&psaux_mouse);
	if (error)
		pr_warn("could not register psaux device, error: %d\n",
			   error);
	else
		psaux_registered = true;
}

static void __exit mousedev_psaux_unregister(void)
{
	if (psaux_registered)
		misc_deregister(&psaux_mouse);
}
#else
static inline void mousedev_psaux_register(void) { }
static inline void mousedev_psaux_unregister(void) { }
#endif

static int __init mousedev_init(void)
{
	int error;

	mousedev_mix = mousedev_create(NULL, &mousedev_handler, true);
	if (IS_ERR(mousedev_mix))
		return PTR_ERR(mousedev_mix);

	error = input_register_handler(&mousedev_handler);
	if (error) {
		mousedev_destroy(mousedev_mix);
		return error;
	}

	mousedev_psaux_register();

	pr_info("PS/2 mouse device common for all mice\n");

	return 0;
}

static void __exit mousedev_exit(void)
{
	mousedev_psaux_unregister();
	input_unregister_handler(&mousedev_handler);
	mousedev_destroy(mousedev_mix);
}

module_init(mousedev_init);
module_exit(mousedev_exit);
"hl kwb">static void __page_check_anon_rmap(struct page *page, struct vm_area_struct *vma, unsigned long address) { #ifdef CONFIG_DEBUG_VM /* * The page's anon-rmap details (mapping and index) are guaranteed to * be set up correctly at this point. * * We have exclusion against page_add_anon_rmap because the caller * always holds the page locked, except if called from page_dup_rmap, * in which case the page is already known to be setup. * * We have exclusion against page_add_new_anon_rmap because those pages * are initially only visible via the pagetables, and the pte is locked * over the call to page_add_new_anon_rmap. */ BUG_ON(page_anon_vma(page)->root != vma->anon_vma->root); BUG_ON(page->index != linear_page_index(vma, address)); #endif } /** * page_add_anon_rmap - add pte mapping to an anonymous page * @page: the page to add the mapping to * @vma: the vm area in which the mapping is added * @address: the user virtual address mapped * * The caller needs to hold the pte lock, and the page must be locked in * the anon_vma case: to serialize mapping,index checking after setting, * and to ensure that PageAnon is not being upgraded racily to PageKsm * (but PageKsm is never downgraded to PageAnon). */ void page_add_anon_rmap(struct page *page, struct vm_area_struct *vma, unsigned long address) { do_page_add_anon_rmap(page, vma, address, 0); } /* * Special version of the above for do_swap_page, which often runs * into pages that are exclusively owned by the current process. * Everybody else should continue to use page_add_anon_rmap above. */ void do_page_add_anon_rmap(struct page *page, struct vm_area_struct *vma, unsigned long address, int exclusive) { int first = atomic_inc_and_test(&page->_mapcount); if (first) { if (PageTransHuge(page)) __inc_zone_page_state(page, NR_ANON_TRANSPARENT_HUGEPAGES); __mod_zone_page_state(page_zone(page), NR_ANON_PAGES, hpage_nr_pages(page)); } if (unlikely(PageKsm(page))) return; VM_BUG_ON(!PageLocked(page)); /* address might be in next vma when migration races vma_adjust */ if (first) __page_set_anon_rmap(page, vma, address, exclusive); else __page_check_anon_rmap(page, vma, address); } /** * page_add_new_anon_rmap - add pte mapping to a new anonymous page * @page: the page to add the mapping to * @vma: the vm area in which the mapping is added * @address: the user virtual address mapped * * Same as page_add_anon_rmap but must only be called on *new* pages. * This means the inc-and-test can be bypassed. * Page does not have to be locked. */ void page_add_new_anon_rmap(struct page *page, struct vm_area_struct *vma, unsigned long address) { VM_BUG_ON(address < vma->vm_start || address >= vma->vm_end); SetPageSwapBacked(page); atomic_set(&page->_mapcount, 0); /* increment count (starts at -1) */ if (PageTransHuge(page)) __inc_zone_page_state(page, NR_ANON_TRANSPARENT_HUGEPAGES); __mod_zone_page_state(page_zone(page), NR_ANON_PAGES, hpage_nr_pages(page)); __page_set_anon_rmap(page, vma, address, 1); if (!mlocked_vma_newpage(vma, page)) { SetPageActive(page); lru_cache_add(page); } else add_page_to_unevictable_list(page); } /** * page_add_file_rmap - add pte mapping to a file page * @page: the page to add the mapping to * * The caller needs to hold the pte lock. */ void page_add_file_rmap(struct page *page) { bool locked; unsigned long flags; mem_cgroup_begin_update_page_stat(page, &locked, &flags); if (atomic_inc_and_test(&page->_mapcount)) { __inc_zone_page_state(page, NR_FILE_MAPPED); mem_cgroup_inc_page_stat(page, MEM_CGROUP_STAT_FILE_MAPPED); } mem_cgroup_end_update_page_stat(page, &locked, &flags); } /** * page_remove_rmap - take down pte mapping from a page * @page: page to remove mapping from * * The caller needs to hold the pte lock. */ void page_remove_rmap(struct page *page) { bool anon = PageAnon(page); bool locked; unsigned long flags; /* * The anon case has no mem_cgroup page_stat to update; but may * uncharge_page() below, where the lock ordering can deadlock if * we hold the lock against page_stat move: so avoid it on anon. */ if (!anon) mem_cgroup_begin_update_page_stat(page, &locked, &flags); /* page still mapped by someone else? */ if (!atomic_add_negative(-1, &page->_mapcount)) goto out; /* * Hugepages are not counted in NR_ANON_PAGES nor NR_FILE_MAPPED * and not charged by memcg for now. */ if (unlikely(PageHuge(page))) goto out; if (anon) { mem_cgroup_uncharge_page(page); if (PageTransHuge(page)) __dec_zone_page_state(page, NR_ANON_TRANSPARENT_HUGEPAGES); __mod_zone_page_state(page_zone(page), NR_ANON_PAGES, -hpage_nr_pages(page)); } else { __dec_zone_page_state(page, NR_FILE_MAPPED); mem_cgroup_dec_page_stat(page, MEM_CGROUP_STAT_FILE_MAPPED); mem_cgroup_end_update_page_stat(page, &locked, &flags); } if (unlikely(PageMlocked(page))) clear_page_mlock(page); /* * It would be tidy to reset the PageAnon mapping here, * but that might overwrite a racing page_add_anon_rmap * which increments mapcount after us but sets mapping * before us: so leave the reset to free_hot_cold_page, * and remember that it's only reliable while mapped. * Leaving it set also helps swapoff to reinstate ptes * faster for those pages still in swapcache. */ return; out: if (!anon) mem_cgroup_end_update_page_stat(page, &locked, &flags); } /* * Subfunctions of try_to_unmap: try_to_unmap_one called * repeatedly from try_to_unmap_ksm, try_to_unmap_anon or try_to_unmap_file. */ int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, unsigned long address, enum ttu_flags flags) { struct mm_struct *mm = vma->vm_mm; pte_t *pte; pte_t pteval; spinlock_t *ptl; int ret = SWAP_AGAIN; pte = page_check_address(page, mm, address, &ptl, 0); if (!pte) goto out; /* * If the page is mlock()d, we cannot swap it out. * If it's recently referenced (perhaps page_referenced * skipped over this mm) then we should reactivate it. */ if (!(flags & TTU_IGNORE_MLOCK)) { if (vma->vm_flags & VM_LOCKED) goto out_mlock; if (TTU_ACTION(flags) == TTU_MUNLOCK) goto out_unmap; } if (!(flags & TTU_IGNORE_ACCESS)) { if (ptep_clear_flush_young_notify(vma, address, pte)) { ret = SWAP_FAIL; goto out_unmap; } } /* Nuke the page table entry. */ flush_cache_page(vma, address, page_to_pfn(page)); pteval = ptep_clear_flush(vma, address, pte); /* Move the dirty bit to the physical page now the pte is gone. */ if (pte_dirty(pteval)) set_page_dirty(page); /* Update high watermark before we lower rss */ update_hiwater_rss(mm); if (PageHWPoison(page) && !(flags & TTU_IGNORE_HWPOISON)) { if (!PageHuge(page)) { if (PageAnon(page)) dec_mm_counter(mm, MM_ANONPAGES); else dec_mm_counter(mm, MM_FILEPAGES); } set_pte_at(mm, address, pte, swp_entry_to_pte(make_hwpoison_entry(page))); } else if (PageAnon(page)) { swp_entry_t entry = { .val = page_private(page) }; pte_t swp_pte; if (PageSwapCache(page)) { /* * Store the swap location in the pte. * See handle_pte_fault() ... */ if (swap_duplicate(entry) < 0) { set_pte_at(mm, address, pte, pteval); ret = SWAP_FAIL; goto out_unmap; } if (list_empty(&mm->mmlist)) { spin_lock(&mmlist_lock); if (list_empty(&mm->mmlist)) list_add(&mm->mmlist, &init_mm.mmlist); spin_unlock(&mmlist_lock); } dec_mm_counter(mm, MM_ANONPAGES); inc_mm_counter(mm, MM_SWAPENTS); } else if (IS_ENABLED(CONFIG_MIGRATION)) { /* * Store the pfn of the page in a special migration * pte. do_swap_page() will wait until the migration * pte is removed and then restart fault handling. */ BUG_ON(TTU_ACTION(flags) != TTU_MIGRATION); entry = make_migration_entry(page, pte_write(pteval)); } swp_pte = swp_entry_to_pte(entry); if (pte_soft_dirty(pteval)) swp_pte = pte_swp_mksoft_dirty(swp_pte); set_pte_at(mm, address, pte, swp_pte); BUG_ON(pte_file(*pte)); } else if (IS_ENABLED(CONFIG_MIGRATION) && (TTU_ACTION(flags) == TTU_MIGRATION)) { /* Establish migration entry for a file page */ swp_entry_t entry; entry = make_migration_entry(page, pte_write(pteval)); set_pte_at(mm, address, pte, swp_entry_to_pte(entry)); } else dec_mm_counter(mm, MM_FILEPAGES); page_remove_rmap(page); page_cache_release(page); out_unmap: pte_unmap_unlock(pte, ptl); if (ret != SWAP_FAIL) mmu_notifier_invalidate_page(mm, address); out: return ret; out_mlock: pte_unmap_unlock(pte, ptl); /* * We need mmap_sem locking, Otherwise VM_LOCKED check makes * unstable result and race. Plus, We can't wait here because * we now hold anon_vma->rwsem or mapping->i_mmap_mutex. * if trylock failed, the page remain in evictable lru and later * vmscan could retry to move the page to unevictable lru if the * page is actually mlocked. */ if (down_read_trylock(&vma->vm_mm->mmap_sem)) { if (vma->vm_flags & VM_LOCKED) { mlock_vma_page(page); ret = SWAP_MLOCK; } up_read(&vma->vm_mm->mmap_sem); } return ret; } /* * objrmap doesn't work for nonlinear VMAs because the assumption that * offset-into-file correlates with offset-into-virtual-addresses does not hold. * Consequently, given a particular page and its ->index, we cannot locate the * ptes which are mapping that page without an exhaustive linear search. * * So what this code does is a mini "virtual scan" of each nonlinear VMA which * maps the file to which the target page belongs. The ->vm_private_data field * holds the current cursor into that scan. Successive searches will circulate * around the vma's virtual address space. * * So as more replacement pressure is applied to the pages in a nonlinear VMA, * more scanning pressure is placed against them as well. Eventually pages * will become fully unmapped and are eligible for eviction. * * For very sparsely populated VMAs this is a little inefficient - chances are * there there won't be many ptes located within the scan cluster. In this case * maybe we could scan further - to the end of the pte page, perhaps. * * Mlocked pages: check VM_LOCKED under mmap_sem held for read, if we can * acquire it without blocking. If vma locked, mlock the pages in the cluster, * rather than unmapping them. If we encounter the "check_page" that vmscan is * trying to unmap, return SWAP_MLOCK, else default SWAP_AGAIN. */ #define CLUSTER_SIZE min(32*PAGE_SIZE, PMD_SIZE) #define CLUSTER_MASK (~(CLUSTER_SIZE - 1)) static int try_to_unmap_cluster(unsigned long cursor, unsigned int *mapcount, struct vm_area_struct *vma, struct page *check_page) { struct mm_struct *mm = vma->vm_mm; pmd_t *pmd; pte_t *pte; pte_t pteval; spinlock_t *ptl; struct page *page; unsigned long address; unsigned long mmun_start; /* For mmu_notifiers */ unsigned long mmun_end; /* For mmu_notifiers */ unsigned long end; int ret = SWAP_AGAIN; int locked_vma = 0; address = (vma->vm_start + cursor) & CLUSTER_MASK; end = address + CLUSTER_SIZE; if (address < vma->vm_start) address = vma->vm_start; if (end > vma->vm_end) end = vma->vm_end; pmd = mm_find_pmd(mm, address); if (!pmd) return ret; mmun_start = address; mmun_end = end; mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end); /* * If we can acquire the mmap_sem for read, and vma is VM_LOCKED, * keep the sem while scanning the cluster for mlocking pages. */ if (down_read_trylock(&vma->vm_mm->mmap_sem)) { locked_vma = (vma->vm_flags & VM_LOCKED); if (!locked_vma) up_read(&vma->vm_mm->mmap_sem); /* don't need it */ } pte = pte_offset_map_lock(mm, pmd, address, &ptl); /* Update high watermark before we lower rss */ update_hiwater_rss(mm); for (; address < end; pte++, address += PAGE_SIZE) { if (!pte_present(*pte)) continue; page = vm_normal_page(vma, address, *pte); BUG_ON(!page || PageAnon(page)); if (locked_vma) { mlock_vma_page(page); /* no-op if already mlocked */ if (page == check_page) ret = SWAP_MLOCK; continue; /* don't unmap */ } if (ptep_clear_flush_young_notify(vma, address, pte)) continue; /* Nuke the page table entry. */ flush_cache_page(vma, address, pte_pfn(*pte)); pteval = ptep_clear_flush(vma, address, pte); /* If nonlinear, store the file page offset in the pte. */ if (page->index != linear_page_index(vma, address)) { pte_t ptfile = pgoff_to_pte(page->index); if (pte_soft_dirty(pteval)) pte_file_mksoft_dirty(ptfile); set_pte_at(mm, address, pte, ptfile); } /* Move the dirty bit to the physical page now the pte is gone. */ if (pte_dirty(pteval)) set_page_dirty(page); page_remove_rmap(page); page_cache_release(page); dec_mm_counter(mm, MM_FILEPAGES); (*mapcount)--; } pte_unmap_unlock(pte - 1, ptl); mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); if (locked_vma) up_read(&vma->vm_mm->mmap_sem); return ret; } bool is_vma_temporary_stack(struct vm_area_struct *vma) { int maybe_stack = vma->vm_flags & (VM_GROWSDOWN | VM_GROWSUP); if (!maybe_stack) return false; if ((vma->vm_flags & VM_STACK_INCOMPLETE_SETUP) == VM_STACK_INCOMPLETE_SETUP) return true; return false; } /** * try_to_unmap_anon - unmap or unlock anonymous page using the object-based * rmap method * @page: the page to unmap/unlock * @flags: action and flags * * Find all the mappings of a page using the mapping pointer and the vma chains * contained in the anon_vma struct it points to. * * This function is only called from try_to_unmap/try_to_munlock for * anonymous pages. * When called from try_to_munlock(), the mmap_sem of the mm containing the vma * where the page was found will be held for write. So, we won't recheck * vm_flags for that VMA. That should be OK, because that vma shouldn't be * 'LOCKED. */ static int try_to_unmap_anon(struct page *page, enum ttu_flags flags) { struct anon_vma *anon_vma; pgoff_t pgoff; struct anon_vma_chain *avc; int ret = SWAP_AGAIN; anon_vma = page_lock_anon_vma_read(page); if (!anon_vma) return ret; pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); anon_vma_interval_tree_foreach(avc, &anon_vma->rb_root, pgoff, pgoff) { struct vm_area_struct *vma = avc->vma; unsigned long address; /* * During exec, a temporary VMA is setup and later moved. * The VMA is moved under the anon_vma lock but not the * page tables leading to a race where migration cannot * find the migration ptes. Rather than increasing the * locking requirements of exec(), migration skips * temporary VMAs until after exec() completes. */ if (IS_ENABLED(CONFIG_MIGRATION) && (flags & TTU_MIGRATION) && is_vma_temporary_stack(vma)) continue; address = vma_address(page, vma); ret = try_to_unmap_one(page, vma, address, flags); if (ret != SWAP_AGAIN || !page_mapped(page)) break; } page_unlock_anon_vma_read(anon_vma); return ret; } /** * try_to_unmap_file - unmap/unlock file page using the object-based rmap method * @page: the page to unmap/unlock * @flags: action and flags * * Find all the mappings of a page using the mapping pointer and the vma chains * contained in the address_space struct it points to. * * This function is only called from try_to_unmap/try_to_munlock for * object-based pages. * When called from try_to_munlock(), the mmap_sem of the mm containing the vma * where the page was found will be held for write. So, we won't recheck * vm_flags for that VMA. That should be OK, because that vma shouldn't be * 'LOCKED. */ static int try_to_unmap_file(struct page *page, enum ttu_flags flags) { struct address_space *mapping = page->mapping; pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); struct vm_area_struct *vma; int ret = SWAP_AGAIN; unsigned long cursor; unsigned long max_nl_cursor = 0; unsigned long max_nl_size = 0; unsigned int mapcount; if (PageHuge(page)) pgoff = page->index << compound_order(page); mutex_lock(&mapping->i_mmap_mutex); vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) { unsigned long address = vma_address(page, vma); ret = try_to_unmap_one(page, vma, address, flags); if (ret != SWAP_AGAIN || !page_mapped(page)) goto out; } if (list_empty(&mapping->i_mmap_nonlinear)) goto out; /* * We don't bother to try to find the munlocked page in nonlinears. * It's costly. Instead, later, page reclaim logic may call * try_to_unmap(TTU_MUNLOCK) and recover PG_mlocked lazily. */ if (TTU_ACTION(flags) == TTU_MUNLOCK) goto out; list_for_each_entry(vma, &mapping->i_mmap_nonlinear, shared.nonlinear) { cursor = (unsigned long) vma->vm_private_data; if (cursor > max_nl_cursor) max_nl_cursor = cursor; cursor = vma->vm_end - vma->vm_start; if (cursor > max_nl_size) max_nl_size = cursor; } if (max_nl_size == 0) { /* all nonlinears locked or reserved ? */ ret = SWAP_FAIL; goto out; } /* * We don't try to search for this page in the nonlinear vmas, * and page_referenced wouldn't have found it anyway. Instead * just walk the nonlinear vmas trying to age and unmap some. * The mapcount of the page we came in with is irrelevant, * but even so use it as a guide to how hard we should try? */ mapcount = page_mapcount(page); if (!mapcount) goto out; cond_resched(); max_nl_size = (max_nl_size + CLUSTER_SIZE - 1) & CLUSTER_MASK; if (max_nl_cursor == 0) max_nl_cursor = CLUSTER_SIZE; do { list_for_each_entry(vma, &mapping->i_mmap_nonlinear, shared.nonlinear) { cursor = (unsigned long) vma->vm_private_data; while ( cursor < max_nl_cursor && cursor < vma->vm_end - vma->vm_start) { if (try_to_unmap_cluster(cursor, &mapcount, vma, page) == SWAP_MLOCK) ret = SWAP_MLOCK; cursor += CLUSTER_SIZE; vma->vm_private_data = (void *) cursor; if ((int)mapcount <= 0) goto out; } vma->vm_private_data = (void *) max_nl_cursor; } cond_resched(); max_nl_cursor += CLUSTER_SIZE; } while (max_nl_cursor <= max_nl_size); /* * Don't loop forever (perhaps all the remaining pages are * in locked vmas). Reset cursor on all unreserved nonlinear * vmas, now forgetting on which ones it had fallen behind. */ list_for_each_entry(vma, &mapping->i_mmap_nonlinear, shared.nonlinear) vma->vm_private_data = NULL; out: mutex_unlock(&mapping->i_mmap_mutex); return ret; } /** * try_to_unmap - try to remove all page table mappings to a page * @page: the page to get unmapped * @flags: action and flags * * Tries to remove all the page table entries which are mapping this * page, used in the pageout path. Caller must hold the page lock. * Return values are: * * SWAP_SUCCESS - we succeeded in removing all mappings * SWAP_AGAIN - we missed a mapping, try again later * SWAP_FAIL - the page is unswappable * SWAP_MLOCK - page is mlocked. */ int try_to_unmap(struct page *page, enum ttu_flags flags) { int ret; BUG_ON(!PageLocked(page)); VM_BUG_ON(!PageHuge(page) && PageTransHuge(page)); if (unlikely(PageKsm(page))) ret = try_to_unmap_ksm(page, flags); else if (PageAnon(page)) ret = try_to_unmap_anon(page, flags); else ret = try_to_unmap_file(page, flags); if (ret != SWAP_MLOCK && !page_mapped(page)) ret = SWAP_SUCCESS; return ret; } /** * try_to_munlock - try to munlock a page * @page: the page to be munlocked * * Called from munlock code. Checks all of the VMAs mapping the page * to make sure nobody else has this page mlocked. The page will be * returned with PG_mlocked cleared if no other vmas have it mlocked. * * Return values are: * * SWAP_AGAIN - no vma is holding page mlocked, or, * SWAP_AGAIN - page mapped in mlocked vma -- couldn't acquire mmap sem * SWAP_FAIL - page cannot be located at present * SWAP_MLOCK - page is now mlocked. */ int try_to_munlock(struct page *page) { VM_BUG_ON(!PageLocked(page) || PageLRU(page)); if (unlikely(PageKsm(page))) return try_to_unmap_ksm(page, TTU_MUNLOCK); else if (PageAnon(page)) return try_to_unmap_anon(page, TTU_MUNLOCK); else return try_to_unmap_file(page, TTU_MUNLOCK); } void __put_anon_vma(struct anon_vma *anon_vma) { struct anon_vma *root = anon_vma->root; if (root != anon_vma && atomic_dec_and_test(&root->refcount)) anon_vma_free(root); anon_vma_free(anon_vma); } #ifdef CONFIG_MIGRATION /* * rmap_walk() and its helpers rmap_walk_anon() and rmap_walk_file(): * Called by migrate.c to remove migration ptes, but might be used more later. */ static int rmap_walk_anon(struct page *page, int (*rmap_one)(struct page *, struct vm_area_struct *, unsigned long, void *), void *arg) { struct anon_vma *anon_vma; pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); struct anon_vma_chain *avc; int ret = SWAP_AGAIN; /* * Note: remove_migration_ptes() cannot use page_lock_anon_vma_read() * because that depends on page_mapped(); but not all its usages * are holding mmap_sem. Users without mmap_sem are required to * take a reference count to prevent the anon_vma disappearing */ anon_vma = page_anon_vma(page); if (!anon_vma) return ret; anon_vma_lock_read(anon_vma); anon_vma_interval_tree_foreach(avc, &anon_vma->rb_root, pgoff, pgoff) { struct vm_area_struct *vma = avc->vma; unsigned long address = vma_address(page, vma); ret = rmap_one(page, vma, address, arg); if (ret != SWAP_AGAIN) break; } anon_vma_unlock_read(anon_vma); return ret; } static int rmap_walk_file(struct page *page, int (*rmap_one)(struct page *, struct vm_area_struct *, unsigned long, void *), void *arg) { struct address_space *mapping = page->mapping; pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); struct vm_area_struct *vma; int ret = SWAP_AGAIN; if (!mapping) return ret; mutex_lock(&mapping->i_mmap_mutex); vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) { unsigned long address = vma_address(page, vma); ret = rmap_one(page, vma, address, arg); if (ret != SWAP_AGAIN) break; } /* * No nonlinear handling: being always shared, nonlinear vmas * never contain migration ptes. Decide what to do about this * limitation to linear when we need rmap_walk() on nonlinear. */ mutex_unlock(&mapping->i_mmap_mutex); return ret; } int rmap_walk(struct page *page, int (*rmap_one)(struct page *, struct vm_area_struct *, unsigned long, void *), void *arg) { VM_BUG_ON(!PageLocked(page)); if (unlikely(PageKsm(page))) return rmap_walk_ksm(page, rmap_one, arg); else if (PageAnon(page)) return rmap_walk_anon(page, rmap_one, arg); else return rmap_walk_file(page, rmap_one, arg); } #endif /* CONFIG_MIGRATION */ #ifdef CONFIG_HUGETLB_PAGE /* * The following three functions are for anonymous (private mapped) hugepages. * Unlike common anonymous pages, anonymous hugepages have no accounting code * and no lru code, because we handle hugepages differently from common pages. */ static void __hugepage_set_anon_rmap(struct page *page, struct vm_area_struct *vma, unsigned long address, int exclusive) { struct anon_vma *anon_vma = vma->anon_vma; BUG_ON(!anon_vma); if (PageAnon(page)) return; if (!exclusive) anon_vma = anon_vma->root; anon_vma = (void *) anon_vma + PAGE_MAPPING_ANON; page->mapping = (struct address_space *) anon_vma; page->index = linear_page_index(vma, address); } void hugepage_add_anon_rmap(struct page *page, struct vm_area_struct *vma, unsigned long address) { struct anon_vma *anon_vma = vma->anon_vma; int first; BUG_ON(!PageLocked(page)); BUG_ON(!anon_vma); /* address might be in next vma when migration races vma_adjust */ first = atomic_inc_and_test(&page->_mapcount); if (first) __hugepage_set_anon_rmap(page, vma, address, 0); } void hugepage_add_new_anon_rmap(struct page *page, struct vm_area_struct *vma, unsigned long address) { BUG_ON(address < vma->vm_start || address >= vma->vm_end); atomic_set(&page->_mapcount, 0); __hugepage_set_anon_rmap(page, vma, address, 1); } #endif /* CONFIG_HUGETLB_PAGE */