summaryrefslogtreecommitdiffstats
path: root/drivers/android/binder_alloc.c
blob: 69609696a843f9e909f48f11e4d3fb708479f5c0 (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
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
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
// SPDX-License-Identifier: GPL-2.0-only
/* binder_alloc.c
 *
 * Android IPC Subsystem
 *
 * Copyright (C) 2007-2017 Google, Inc.
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/list.h>
#include <linux/sched/mm.h>
#include <linux/module.h>
#include <linux/rtmutex.h>
#include <linux/rbtree.h>
#include <linux/seq_file.h>
#include <linux/vmalloc.h>
#include <linux/slab.h>
#include <linux/sched.h>
#include <linux/list_lru.h>
#include <linux/ratelimit.h>
#include <asm/cacheflush.h>
#include <linux/uaccess.h>
#include <linux/highmem.h>
#include <linux/sizes.h>
#include "binder_alloc.h"
#include "binder_trace.h"

struct list_lru binder_alloc_lru;

static DEFINE_MUTEX(binder_alloc_mmap_lock);

enum {
	BINDER_DEBUG_USER_ERROR             = 1U << 0,
	BINDER_DEBUG_OPEN_CLOSE             = 1U << 1,
	BINDER_DEBUG_BUFFER_ALLOC           = 1U << 2,
	BINDER_DEBUG_BUFFER_ALLOC_ASYNC     = 1U << 3,
};
static uint32_t binder_alloc_debug_mask = BINDER_DEBUG_USER_ERROR;

module_param_named(debug_mask, binder_alloc_debug_mask,
		   uint, 0644);

#define binder_alloc_debug(mask, x...) \
	do { \
		if (binder_alloc_debug_mask & mask) \
			pr_info_ratelimited(x); \
	} while (0)

static struct binder_buffer *binder_buffer_next(struct binder_buffer *buffer)
{
	return list_entry(buffer->entry.next, struct binder_buffer, entry);
}

static struct binder_buffer *binder_buffer_prev(struct binder_buffer *buffer)
{
	return list_entry(buffer->entry.prev, struct binder_buffer, entry);
}

static size_t binder_alloc_buffer_size(struct binder_alloc *alloc,
				       struct binder_buffer *buffer)
{
	if (list_is_last(&buffer->entry, &alloc->buffers))
		return alloc->buffer + alloc->buffer_size - buffer->user_data;
	return binder_buffer_next(buffer)->user_data - buffer->user_data;
}

static void binder_insert_free_buffer(struct binder_alloc *alloc,
				      struct binder_buffer *new_buffer)
{
	struct rb_node **p = &alloc->free_buffers.rb_node;
	struct rb_node *parent = NULL;
	struct binder_buffer *buffer;
	size_t buffer_size;
	size_t new_buffer_size;

	BUG_ON(!new_buffer->free);

	new_buffer_size = binder_alloc_buffer_size(alloc, new_buffer);

	binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
		     "%d: add free buffer, size %zd, at %pK\n",
		      alloc->pid, new_buffer_size, new_buffer);

	while (*p) {
		parent = *p;
		buffer = rb_entry(parent, struct binder_buffer, rb_node);
		BUG_ON(!buffer->free);

		buffer_size = binder_alloc_buffer_size(alloc, buffer);

		if (new_buffer_size < buffer_size)
			p = &parent->rb_left;
		else
			p = &parent->rb_right;
	}
	rb_link_node(&new_buffer->rb_node, parent, p);
	rb_insert_color(&new_buffer->rb_node, &alloc->free_buffers);
}

static void binder_insert_allocated_buffer_locked(
		struct binder_alloc *alloc, struct binder_buffer *new_buffer)
{
	struct rb_node **p = &alloc->allocated_buffers.rb_node;
	struct rb_node *parent = NULL;
	struct binder_buffer *buffer;

	BUG_ON(new_buffer->free);

	while (*p) {
		parent = *p;
		buffer = rb_entry(parent, struct binder_buffer, rb_node);
		BUG_ON(buffer->free);

		if (new_buffer->user_data < buffer->user_data)
			p = &parent->rb_left;
		else if (new_buffer->user_data > buffer->user_data)
			p = &parent->rb_right;
		else
			BUG();
	}
	rb_link_node(&new_buffer->rb_node, parent, p);
	rb_insert_color(&new_buffer->rb_node, &alloc->allocated_buffers);
}

static struct binder_buffer *binder_alloc_prepare_to_free_locked(
		struct binder_alloc *alloc,
		uintptr_t user_ptr)
{
	struct rb_node *n = alloc->allocated_buffers.rb_node;
	struct binder_buffer *buffer;
	void __user *uptr;

	uptr = (void __user *)user_ptr;

	while (n) {
		buffer = rb_entry(n, struct binder_buffer, rb_node);
		BUG_ON(buffer->free);

		if (uptr < buffer->user_data)
			n = n->rb_left;
		else if (uptr > buffer->user_data)
			n = n->rb_right;
		else {
			/*
			 * Guard against user threads attempting to
			 * free the buffer when in use by kernel or
			 * after it's already been freed.
			 */
			if (!buffer->allow_user_free)
				return ERR_PTR(-EPERM);
			buffer->allow_user_free = 0;
			return buffer;
		}
	}
	return NULL;
}

/**
 * binder_alloc_prepare_to_free() - get buffer given user ptr
 * @alloc:	binder_alloc for this proc
 * @user_ptr:	User pointer to buffer data
 *
 * Validate userspace pointer to buffer data and return buffer corresponding to
 * that user pointer. Search the rb tree for buffer that matches user data
 * pointer.
 *
 * Return:	Pointer to buffer or NULL
 */
struct binder_buffer *binder_alloc_prepare_to_free(struct binder_alloc *alloc,
						   uintptr_t user_ptr)
{
	struct binder_buffer *buffer;

	mutex_lock(&alloc->mutex);
	buffer = binder_alloc_prepare_to_free_locked(alloc, user_ptr);
	mutex_unlock(&alloc->mutex);
	return buffer;
}

static int binder_update_page_range(struct binder_alloc *alloc, int allocate,
				    void __user *start, void __user *end)
{
	void __user *page_addr;
	unsigned long user_page_addr;
	struct binder_lru_page *page;
	struct vm_area_struct *vma = NULL;
	struct mm_struct *mm = NULL;
	bool need_mm = false;

	binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
		     "%d: %s pages %pK-%pK\n", alloc->pid,
		     allocate ? "allocate" : "free", start, end);

	if (end <= start)
		return 0;

	trace_binder_update_page_range(alloc, allocate, start, end);

	if (allocate == 0)
		goto free_range;

	for (page_addr = start; page_addr < end; page_addr += PAGE_SIZE) {
		page = &alloc->pages[(page_addr - alloc->buffer) / PAGE_SIZE];
		if (!page->page_ptr) {
			need_mm = true;
			break;
		}
	}

	if (need_mm && mmget_not_zero(alloc->vma_vm_mm))
		mm = alloc->vma_vm_mm;

	if (mm) {
		mmap_read_lock(mm);
		vma = alloc->vma;
	}

	if (!vma && need_mm) {
		binder_alloc_debug(BINDER_DEBUG_USER_ERROR,
				   "%d: binder_alloc_buf failed to map pages in userspace, no vma\n",
				   alloc->pid);
		goto err_no_vma;
	}

	for (page_addr = start; page_addr < end; page_addr += PAGE_SIZE) {
		int ret;
		bool on_lru;
		size_t index;

		index = (page_addr - alloc->buffer) / PAGE_SIZE;
		page = &alloc->pages[index];

		if (page->page_ptr) {
			trace_binder_alloc_lru_start(alloc, index);

			on_lru = list_lru_del(&binder_alloc_lru, &page->lru);
			WARN_ON(!on_lru);

			trace_binder_alloc_lru_end(alloc, index);
			continue;
		}

		if (WARN_ON(!vma))
			goto err_page_ptr_cleared;

		trace_binder_alloc_page_start(alloc, index);
		page->page_ptr = alloc_page(GFP_KERNEL |
					    __GFP_HIGHMEM |
					    __GFP_ZERO);
		if (!page->page_ptr) {
			pr_err("%d: binder_alloc_buf failed for page at %pK\n",
				alloc->pid, page_addr);
			goto err_alloc_page_failed;
		}
		page->alloc = alloc;
		INIT_LIST_HEAD(&page->lru);

		user_page_addr = (uintptr_t)page_addr;
		ret = vm_insert_page(vma, user_page_addr, page[0].page_ptr);
		if (ret) {
			pr_err("%d: binder_alloc_buf failed to map page at %lx in userspace\n",
			       alloc->pid, user_page_addr);
			goto err_vm_insert_page_failed;
		}

		if (index + 1 > alloc->pages_high)
			alloc->pages_high = index + 1;

		trace_binder_alloc_page_end(alloc, index);
	}
	if (mm) {
		mmap_read_unlock(mm);
		mmput(mm);
	}
	return 0;

free_range:
	for (page_addr = end - PAGE_SIZE; 1; page_addr -= PAGE_SIZE) {
		bool ret;
		size_t index;

		index = (page_addr - alloc->buffer) / PAGE_SIZE;
		page = &alloc->pages[index];

		trace_binder_free_lru_start(alloc, index);

		ret = list_lru_add(&binder_alloc_lru, &page->lru);
		WARN_ON(!ret);

		trace_binder_free_lru_end(alloc, index);
		if (page_addr == start)
			break;
		continue;

err_vm_insert_page_failed:
		__free_page(page->page_ptr);
		page->page_ptr = NULL;
err_alloc_page_failed:
err_page_ptr_cleared:
		if (page_addr == start)
			break;
	}
err_no_vma:
	if (mm) {
		mmap_read_unlock(mm);
		mmput(mm);
	}
	return vma ? -ENOMEM : -ESRCH;
}


static inline void binder_alloc_set_vma(struct binder_alloc *alloc,
		struct vm_area_struct *vma)
{
	if (vma)
		alloc->vma_vm_mm = vma->vm_mm;
	/*
	 * If we see alloc->vma is not NULL, buffer data structures set up
	 * completely. Look at smp_rmb side binder_alloc_get_vma.
	 * We also want to guarantee new alloc->vma_vm_mm is always visible
	 * if alloc->vma is set.
	 */
	smp_wmb();
	alloc->vma = vma;
}

static inline struct vm_area_struct *binder_alloc_get_vma(
		struct binder_alloc *alloc)
{
	struct vm_area_struct *vma = NULL;

	if (alloc->vma) {
		/* Look at description in binder_alloc_set_vma */
		smp_rmb();
		vma = alloc->vma;
	}
	return vma;
}

static struct binder_buffer *binder_alloc_new_buf_locked(
				struct binder_alloc *alloc,
				size_t data_size,
				size_t offsets_size,
				size_t extra_buffers_size,
				int is_async)
{
	struct rb_node *n = alloc->free_buffers.rb_node;
	struct binder_buffer *buffer;
	size_t buffer_size;
	struct rb_node *best_fit = NULL;
	void __user *has_page_addr;
	void __user *end_page_addr;
	size_t size, data_offsets_size;
	int ret;

	if (!binder_alloc_get_vma(alloc)) {
		binder_alloc_debug(BINDER_DEBUG_USER_ERROR,
				   "%d: binder_alloc_buf, no vma\n",
				   alloc->pid);
		return ERR_PTR(-ESRCH);
	}

	data_offsets_size = ALIGN(data_size, sizeof(void *)) +
		ALIGN(offsets_size, sizeof(void *));

	if (data_offsets_size < data_size || data_offsets_size < offsets_size) {
		binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
				"%d: got transaction with invalid size %zd-%zd\n",
				alloc->pid, data_size, offsets_size);
		return ERR_PTR(-EINVAL);
	}
	size = data_offsets_size + ALIGN(extra_buffers_size, sizeof(void *));
	if (size < data_offsets_size || size < extra_buffers_size) {
		binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
				"%d: got transaction with invalid extra_buffers_size %zd\n",
				alloc->pid, extra_buffers_size);
		return ERR_PTR(-EINVAL);
	}
	if (is_async &&
	    alloc->free_async_space < size + sizeof(struct binder_buffer)) {
		binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
			     "%d: binder_alloc_buf size %zd failed, no async space left\n",
			      alloc->pid, size);
		return ERR_PTR(-ENOSPC);
	}

	/* Pad 0-size buffers so they get assigned unique addresses */
	size = max(size, sizeof(void *));

	while (n) {
		buffer = rb_entry(n, struct binder_buffer, rb_node);
		BUG_ON(!buffer->free);
		buffer_size = binder_alloc_buffer_size(alloc, buffer);

		if (size < buffer_size) {
			best_fit = n;
			n = n->rb_left;
		} else if (size > buffer_size)
			n = n->rb_right;
		else {
			best_fit = n;
			break;
		}
	}
	if (best_fit == NULL) {
		size_t allocated_buffers = 0;
		size_t largest_alloc_size = 0;
		size_t total_alloc_size = 0;
		size_t free_buffers = 0;
		size_t largest_free_size = 0;
		size_t total_free_size = 0;

		for (n = rb_first(&alloc->allocated_buffers); n != NULL;
		     n = rb_next(n)) {
			buffer = rb_entry(n, struct binder_buffer, rb_node);
			buffer_size = binder_alloc_buffer_size(alloc, buffer);
			allocated_buffers++;
			total_alloc_size += buffer_size;
			if (buffer_size > largest_alloc_size)
				largest_alloc_size = buffer_size;
		}
		for (n = rb_first(&alloc->free_buffers); n != NULL;
		     n = rb_next(n)) {
			buffer = rb_entry(n, struct binder_buffer, rb_node);
			buffer_size = binder_alloc_buffer_size(alloc, buffer);
			free_buffers++;
			total_free_size += buffer_size;
			if (buffer_size > largest_free_size)
				largest_free_size = buffer_size;
		}
		binder_alloc_debug(BINDER_DEBUG_USER_ERROR,
				   "%d: binder_alloc_buf size %zd failed, no address space\n",
				   alloc->pid, size);
		binder_alloc_debug(BINDER_DEBUG_USER_ERROR,
				   "allocated: %zd (num: %zd largest: %zd), free: %zd (num: %zd largest: %zd)\n",
				   total_alloc_size, allocated_buffers,
				   largest_alloc_size, total_free_size,
				   free_buffers, largest_free_size);
		return ERR_PTR(-ENOSPC);
	}
	if (n == NULL) {
		buffer = rb_entry(best_fit, struct binder_buffer, rb_node);
		buffer_size = binder_alloc_buffer_size(alloc, buffer);
	}

	binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
		     "%d: binder_alloc_buf size %zd got buffer %pK size %zd\n",
		      alloc->pid, size, buffer, buffer_size);

	has_page_addr = (void __user *)
		(((uintptr_t)buffer->user_data + buffer_size) & PAGE_MASK);
	WARN_ON(n && buffer_size != size);
	end_page_addr =
		(void __user *)PAGE_ALIGN((uintptr_t)buffer->user_data + size);
	if (end_page_addr > has_page_addr)
		end_page_addr = has_page_addr;
	ret = binder_update_page_range(alloc, 1, (void __user *)
		PAGE_ALIGN((uintptr_t)buffer->user_data), end_page_addr);
	if (ret)
		return ERR_PTR(ret);

	if (buffer_size != size) {
		struct binder_buffer *new_buffer;

		new_buffer = kzalloc(sizeof(*buffer), GFP_KERNEL);
		if (!new_buffer) {
			pr_err("%s: %d failed to alloc new buffer struct\n",
			       __func__, alloc->pid);
			goto err_alloc_buf_struct_failed;
		}
		new_buffer->user_data = (u8 __user *)buffer->user_data + size;
		list_add(&new_buffer->entry, &buffer->entry);
		new_buffer->free = 1;
		binder_insert_free_buffer(alloc, new_buffer);
	}

	rb_erase(best_fit, &alloc->free_buffers);
	buffer->free = 0;
	buffer->allow_user_free = 0;
	binder_insert_allocated_buffer_locked(alloc, buffer);
	binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
		     "%d: binder_alloc_buf size %zd got %pK\n",
		      alloc->pid, size, buffer);
	buffer->data_size = data_size;
	buffer->offsets_size = offsets_size;
	buffer->async_transaction = is_async;
	buffer->extra_buffers_size = extra_buffers_size;
	if (is_async) {
		alloc->free_async_space -= size + sizeof(struct binder_buffer);
		binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC_ASYNC,
			     "%d: binder_alloc_buf size %zd async free %zd\n",
			      alloc->pid, size, alloc->free_async_space);
	}
	return buffer;

err_alloc_buf_struct_failed:
	binder_update_page_range(alloc, 0, (void __user *)
				 PAGE_ALIGN((uintptr_t)buffer->user_data),
				 end_page_addr);
	return ERR_PTR(-ENOMEM);
}

/**
 * binder_alloc_new_buf() - Allocate a new binder buffer
 * @alloc:              binder_alloc for this proc
 * @data_size:          size of user data buffer
 * @offsets_size:       user specified buffer offset
 * @extra_buffers_size: size of extra space for meta-data (eg, security context)
 * @is_async:           buffer for async transaction
 *
 * Allocate a new buffer given the requested sizes. Returns
 * the kernel version of the buffer pointer. The size allocated
 * is the sum of the three given sizes (each rounded up to
 * pointer-sized boundary)
 *
 * Return:	The allocated buffer or %NULL if error
 */
struct binder_buffer *binder_alloc_new_buf(struct binder_alloc *alloc,
					   size_t data_size,
					   size_t offsets_size,
					   size_t extra_buffers_size,
					   int is_async)
{
	struct binder_buffer *buffer;

	mutex_lock(&alloc->mutex);
	buffer = binder_alloc_new_buf_locked(alloc, data_size, offsets_size,
					     extra_buffers_size, is_async);
	mutex_unlock(&alloc->mutex);
	return buffer;
}

static void __user *buffer_start_page(struct binder_buffer *buffer)
{
	return (void __user *)((uintptr_t)buffer->user_data & PAGE_MASK);
}

static void __user *prev_buffer_end_page(struct binder_buffer *buffer)
{
	return (void __user *)
		(((uintptr_t)(buffer->user_data) - 1) & PAGE_MASK);
}

static void binder_delete_free_buffer(struct binder_alloc *alloc,
				      struct binder_buffer *buffer)
{
	struct binder_buffer *prev, *next = NULL;
	bool to_free = true;

	BUG_ON(alloc->buffers.next == &buffer->entry);
	prev = binder_buffer_prev(buffer);
	BUG_ON(!prev->free);
	if (prev_buffer_end_page(prev) == buffer_start_page(buffer)) {
		to_free = false;
		binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
				   "%d: merge free, buffer %pK share page with %pK\n",
				   alloc->pid, buffer->user_data,
				   prev->user_data);
	}

	if (!list_is_last(&buffer->entry, &alloc->buffers)) {
		next = binder_buffer_next(buffer);
		if (buffer_start_page(next) == buffer_start_page(buffer)) {
			to_free = false;
			binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
					   "%d: merge free, buffer %pK share page with %pK\n",
					   alloc->pid,
					   buffer->user_data,
					   next->user_data);
		}
	}

	if (PAGE_ALIGNED(buffer->user_data)) {
		binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
				   "%d: merge free, buffer start %pK is page aligned\n",
				   alloc->pid, buffer->user_data);
		to_free = false;
	}

	if (to_free) {
		binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
				   "%d: merge free, buffer %pK do not share page with %pK or %pK\n",
				   alloc->pid, buffer->user_data,
				   prev->user_data,
				   next ? next->user_data : NULL);
		binder_update_page_range(alloc, 0, buffer_start_page(buffer),
					 buffer_start_page(buffer) + PAGE_SIZE);
	}
	list_del(&buffer->entry);
	kfree(buffer);
}

static void binder_free_buf_locked(struct binder_alloc *alloc,
				   struct binder_buffer *buffer)
{
	size_t size, buffer_size;

	buffer_size = binder_alloc_buffer_size(alloc, buffer);

	size = ALIGN(buffer->data_size, sizeof(void *)) +
		ALIGN(buffer->offsets_size, sizeof(void *)) +
		ALIGN(buffer->extra_buffers_size, sizeof(void *));

	binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
		     "%d: binder_free_buf %pK size %zd buffer_size %zd\n",
		      alloc->pid, buffer, size, buffer_size);

	BUG_ON(buffer->free);
	BUG_ON(size > buffer_size);
	BUG_ON(buffer->transaction != NULL);
	BUG_ON(buffer->user_data < alloc->buffer);
	BUG_ON(buffer->user_data > alloc->buffer + alloc->buffer_size);

	if (buffer->async_transaction) {
		alloc->free_async_space += size + sizeof(struct binder_buffer);

		binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC_ASYNC,
			     "%d: binder_free_buf size %zd async free %zd\n",
			      alloc->pid, size, alloc->free_async_space);
	}

	binder_update_page_range(alloc, 0,
		(void __user *)PAGE_ALIGN((uintptr_t)buffer->user_data),
		(void __user *)(((uintptr_t)
			  buffer->user_data + buffer_size) & PAGE_MASK));

	rb_erase(&buffer->rb_node, &alloc->allocated_buffers);
	buffer->free = 1;
	if (!list_is_last(&buffer->entry, &alloc->buffers)) {
		struct binder_buffer *next = binder_buffer_next(buffer);

		if (next->free) {
			rb_erase(&next->rb_node, &alloc->free_buffers);
			binder_delete_free_buffer(alloc, next);
		}
	}
	if (alloc->buffers.next != &buffer->entry) {
		struct binder_buffer *prev = binder_buffer_prev(buffer);

		if (prev->free) {
			binder_delete_free_buffer(alloc, buffer);
			rb_erase(&prev->rb_node, &alloc->free_buffers);
			buffer = prev;
		}
	}
	binder_insert_free_buffer(alloc, buffer);
}

/**
 * binder_alloc_free_buf() - free a binder buffer
 * @alloc:	binder_alloc for this proc
 * @buffer:	kernel pointer to buffer
 *
 * Free the buffer allocated via binder_alloc_new_buffer()
 */
void binder_alloc_free_buf(struct binder_alloc *alloc,
			    struct binder_buffer *buffer)
{
	mutex_lock(&alloc->mutex);
	binder_free_buf_locked(alloc, buffer);
	mutex_unlock(&alloc->mutex);
}

/**
 * binder_alloc_mmap_handler() - map virtual address space for proc
 * @alloc:	alloc structure for this proc
 * @vma:	vma passed to mmap()
 *
 * Called by binder_mmap() to initialize the space specified in
 * vma for allocating binder buffers
 *
 * Return:
 *      0 = success
 *      -EBUSY = address space already mapped
 *      -ENOMEM = failed to map memory to given address space
 */
int binder_alloc_mmap_handler(struct binder_alloc *alloc,
			      struct vm_area_struct *vma)
{
	int ret;
	const char *failure_string;
	struct binder_buffer *buffer;

	mutex_lock(&binder_alloc_mmap_lock);
	if (alloc->buffer_size) {
		ret = -EBUSY;
		failure_string = "already mapped";
		goto err_already_mapped;
	}
	alloc->buffer_size = min_t(unsigned long, vma->vm_end - vma->vm_start,
				   SZ_4M);
	mutex_unlock(&binder_alloc_mmap_lock);

	alloc->buffer = (void __user *)vma->vm_start;

	alloc->pages = kcalloc(alloc->buffer_size / PAGE_SIZE,
			       sizeof(alloc->pages[0]),
			       GFP_KERNEL);
	if (alloc->pages == NULL) {
		ret = -ENOMEM;
		failure_string = "alloc page array";
		goto err_alloc_pages_failed;
	}

	buffer = kzalloc(sizeof(*buffer), GFP_KERNEL);
	if (!buffer) {
		ret = -ENOMEM;
		failure_string = "alloc buffer struct";
		goto err_alloc_buf_struct_failed;
	}

	buffer->user_data = alloc->buffer;
	list_add(&buffer->entry, &alloc->buffers);
	buffer->free = 1;
	binder_insert_free_buffer(alloc, buffer);
	alloc->free_async_space = alloc->buffer_size / 2;
	binder_alloc_set_vma(alloc, vma);
	mmgrab(alloc->vma_vm_mm);

	return 0;

err_alloc_buf_struct_failed:
	kfree(alloc->pages);
	alloc->pages = NULL;
err_alloc_pages_failed:
	alloc->buffer = NULL;
	mutex_lock(&binder_alloc_mmap_lock);
	alloc->buffer_size = 0;
err_already_mapped:
	mutex_unlock(&binder_alloc_mmap_lock);
	binder_alloc_debug(BINDER_DEBUG_USER_ERROR,
			   "%s: %d %lx-%lx %s failed %d\n", __func__,
			   alloc->pid, vma->vm_start, vma->vm_end,
			   failure_string, ret);
	return ret;
}


void binder_alloc_deferred_release(struct binder_alloc *alloc)
{
	struct rb_node *n;
	int buffers, page_count;
	struct binder_buffer *buffer;

	buffers = 0;
	mutex_lock(&alloc->mutex);
	BUG_ON(alloc->vma);

	while ((n = rb_first(&alloc->allocated_buffers))) {
		buffer = rb_entry(n, struct binder_buffer, rb_node);

		/* Transaction should already have been freed */
		BUG_ON(buffer->transaction);

		binder_free_buf_locked(alloc, buffer);
		buffers++;
	}

	while (!list_empty(&alloc->buffers)) {
		buffer = list_first_entry(&alloc->buffers,
					  struct binder_buffer, entry);
		WARN_ON(!buffer->free);

		list_del(&buffer->entry);
		WARN_ON_ONCE(!list_empty(&alloc->buffers));
		kfree(buffer);
	}

	page_count = 0;
	if (alloc->pages) {
		int i;

		for (i = 0; i < alloc->buffer_size / PAGE_SIZE; i++) {
			void __user *page_addr;
			bool on_lru;

			if (!alloc->pages[i].page_ptr)
				continue;

			on_lru = list_lru_del(&binder_alloc_lru,
					      &alloc->pages[i].lru);
			page_addr = alloc->buffer + i * PAGE_SIZE;
			binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
				     "%s: %d: page %d at %pK %s\n",
				     __func__, alloc->pid, i, page_addr,
				     on_lru ? "on lru" : "active");
			__free_page(alloc->pages[i].page_ptr);
			page_count++;
		}
		kfree(alloc->pages);
	}
	mutex_unlock(&alloc->mutex);
	if (alloc->vma_vm_mm)
		mmdrop(alloc->vma_vm_mm);

	binder_alloc_debug(BINDER_DEBUG_OPEN_CLOSE,
		     "%s: %d buffers %d, pages %d\n",
		     __func__, alloc->pid, buffers, page_count);
}

static void print_binder_buffer(struct seq_file *m, const char *prefix,
				struct binder_buffer *buffer)
{
	seq_printf(m, "%s %d: %pK size %zd:%zd:%zd %s\n",
		   prefix, buffer->debug_id, buffer->user_data,
		   buffer->data_size, buffer->offsets_size,
		   buffer->extra_buffers_size,
		   buffer->transaction ? "active" : "delivered");
}

/**
 * binder_alloc_print_allocated() - print buffer info
 * @m:     seq_file for output via seq_printf()
 * @alloc: binder_alloc for this proc
 *
 * Prints information about every buffer associated with
 * the binder_alloc state to the given seq_file
 */
void binder_alloc_print_allocated(struct seq_file *m,
				  struct binder_alloc *alloc)
{
	struct rb_node *n;

	mutex_lock(&alloc->mutex);
	for (n = rb_first(&alloc->allocated_buffers); n != NULL; n = rb_next(n))
		print_binder_buffer(m, "  buffer",
				    rb_entry(n, struct binder_buffer, rb_node));
	mutex_unlock(&alloc->mutex);
}

/**
 * binder_alloc_print_pages() - print page usage
 * @m:     seq_file for output via seq_printf()
 * @alloc: binder_alloc for this proc
 */
void binder_alloc_print_pages(struct seq_file *m,
			      struct binder_alloc *alloc)
{
	struct binder_lru_page *page;
	int i;
	int active = 0;
	int lru = 0;
	int free = 0;

	mutex_lock(&alloc->mutex);
	/*
	 * Make sure the binder_alloc is fully initialized, otherwise we might
	 * read inconsistent state.
	 */
	if (binder_alloc_get_vma(alloc) != NULL) {
		for (i = 0; i < alloc->buffer_size / PAGE_SIZE; i++) {
			page = &alloc->pages[i];
			if (!page->page_ptr)
				free++;
			else if (list_empty(&page->lru))
				active++;
			else
				lru++;
		}
	}
	mutex_unlock(&alloc->mutex);
	seq_printf(m, "  pages: %d:%d:%d\n", active, lru, free);
	seq_printf(m, "  pages high watermark: %zu\n", alloc->pages_high);
}

/**
 * binder_alloc_get_allocated_count() - return count of buffers
 * @alloc: binder_alloc for this proc
 *
 * Return: count of allocated buffers
 */
int binder_alloc_get_allocated_count(struct binder_alloc *alloc)
{
	struct rb_node *n;
	int count = 0;

	mutex_lock(&alloc->mutex);
	for (n = rb_first(&alloc->allocated_buffers); n != NULL; n = rb_next(n))
		count++;
	mutex_unlock(&alloc->mutex);
	return count;
}


/**
 * binder_alloc_vma_close() - invalidate address space
 * @alloc: binder_alloc for this proc
 *
 * Called from binder_vma_close() when releasing address space.
 * Clears alloc->vma to prevent new incoming transactions from
 * allocating more buffers.
 */
void binder_alloc_vma_close(struct binder_alloc *alloc)
{
	binder_alloc_set_vma(alloc, NULL);
}

/**
 * binder_alloc_free_page() - shrinker callback to free pages
 * @item:   item to free
 * @lock:   lock protecting the item
 * @cb_arg: callback argument
 *
 * Called from list_lru_walk() in binder_shrink_scan() to free
 * up pages when the system is under memory pressure.
 */
enum lru_status binder_alloc_free_page(struct list_head *item,
				       struct list_lru_one *lru,
				       spinlock_t *lock,
				       void *cb_arg)
	__must_hold(lock)
{
	struct mm_struct *mm = NULL;
	struct binder_lru_page *page = container_of(item,
						    struct binder_lru_page,
						    lru);
	struct binder_alloc *alloc;
	uintptr_t page_addr;
	size_t index;
	struct vm_area_struct *vma;

	alloc = page->alloc;
	if (!mutex_trylock(&alloc->mutex))
		goto err_get_alloc_mutex_failed;

	if (!page->page_ptr)
		goto err_page_already_freed;

	index = page - alloc->pages;
	page_addr = (uintptr_t)alloc->buffer + index * PAGE_SIZE;

	mm = alloc->vma_vm_mm;
	if (!mmget_not_zero(mm))
		goto err_mmget;
	if (!mmap_read_trylock(mm))
		goto err_mmap_read_lock_failed;
	vma = binder_alloc_get_vma(alloc);

	list_lru_isolate(lru, item);
	spin_unlock(lock);

	if (vma) {
		trace_binder_unmap_user_start(alloc, index);

		zap_page_range(vma, page_addr, PAGE_SIZE);

		trace_binder_unmap_user_end(alloc, index);
	}
	mmap_read_unlock(mm);
	mmput_async(mm);

	trace_binder_unmap_kernel_start(alloc, index);

	__free_page(page->page_ptr);
	page->page_ptr = NULL;

	trace_binder_unmap_kernel_end(alloc, index);

	spin_lock(lock);
	mutex_unlock(&alloc->mutex);
	return LRU_REMOVED_RETRY;

err_mmap_read_lock_failed:
	mmput_async(mm);
err_mmget:
err_page_already_freed:
	mutex_unlock(&alloc->mutex);
err_get_alloc_mutex_failed:
	return LRU_SKIP;
}

static unsigned long
binder_shrink_count(struct shrinker *shrink, struct shrink_control *sc)
{
	unsigned long ret = list_lru_count(&binder_alloc_lru);
	return ret;
}

static unsigned long
binder_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
{
	unsigned long ret;

	ret = list_lru_walk(&binder_alloc_lru, binder_alloc_free_page,
			    NULL, sc->nr_to_scan);
	return ret;
}

static struct shrinker binder_shrinker = {
	.count_objects = binder_shrink_count,
	.scan_objects = binder_shrink_scan,
	.seeks = DEFAULT_SEEKS,
};

/**
 * binder_alloc_init() - called by binder_open() for per-proc initialization
 * @alloc: binder_alloc for this proc
 *
 * Called from binder_open() to initialize binder_alloc fields for
 * new binder proc
 */
void binder_alloc_init(struct binder_alloc *alloc)
{
	alloc->pid = current->group_leader->pid;
	mutex_init(&alloc->mutex);
	INIT_LIST_HEAD(&alloc->buffers);
}

int binder_alloc_shrinker_init(void)
{
	int ret = list_lru_init(&binder_alloc_lru);

	if (ret == 0) {
		ret = register_shrinker(&binder_shrinker);
		if (ret)
			list_lru_destroy(&binder_alloc_lru);
	}
	return ret;
}

/**
 * check_buffer() - verify that buffer/offset is safe to access
 * @alloc: binder_alloc for this proc
 * @buffer: binder buffer to be accessed
 * @offset: offset into @buffer data
 * @bytes: bytes to access from offset
 *
 * Check that the @offset/@bytes are within the size of the given
 * @buffer and that the buffer is currently active and not freeable.
 * Offsets must also be multiples of sizeof(u32). The kernel is
 * allowed to touch the buffer in two cases:
 *
 * 1) when the buffer is being created:
 *     (buffer->free == 0 && buffer->allow_user_free == 0)
 * 2) when the buffer is being torn down:
 *     (buffer->free == 0 && buffer->transaction == NULL).
 *
 * Return: true if the buffer is safe to access
 */
static inline bool check_buffer(struct binder_alloc *alloc,
				struct binder_buffer *buffer,
				binder_size_t offset, size_t bytes)
{
	size_t buffer_size = binder_alloc_buffer_size(alloc, buffer);

	return buffer_size >= bytes &&
		offset <= buffer_size - bytes &&
		IS_ALIGNED(offset, sizeof(u32)) &&
		!buffer->free &&
		(!buffer->allow_user_free || !buffer->transaction);
}

/**
 * binder_alloc_get_page() - get kernel pointer for given buffer offset
 * @alloc: binder_alloc for this proc
 * @buffer: binder buffer to be accessed
 * @buffer_offset: offset into @buffer data
 * @pgoffp: address to copy final page offset to
 *
 * Lookup the struct page corresponding to the address
 * at @buffer_offset into @buffer->user_data. If @pgoffp is not
 * NULL, the byte-offset into the page is written there.
 *
 * The caller is responsible to ensure that the offset points
 * to a valid address within the @buffer and that @buffer is
 * not freeable by the user. Since it can't be freed, we are
 * guaranteed that the corresponding elements of @alloc->pages[]
 * cannot change.
 *
 * Return: struct page
 */
static struct page *binder_alloc_get_page(struct binder_alloc *alloc,
					  struct binder_buffer *buffer,
					  binder_size_t buffer_offset,
					  pgoff_t *pgoffp)
{
	binder_size_t buffer_space_offset = buffer_offset +
		(buffer->user_data - alloc->buffer);
	pgoff_t pgoff = buffer_space_offset & ~PAGE_MASK;
	size_t index = buffer_space_offset >> PAGE_SHIFT;
	struct binder_lru_page *lru_page;

	lru_page = &alloc->pages[index];
	*pgoffp = pgoff;
	return lru_page->page_ptr;
}

/**
 * binder_alloc_copy_user_to_buffer() - copy src user to tgt user
 * @alloc: binder_alloc for this proc
 * @buffer: binder buffer to be accessed
 * @buffer_offset: offset into @buffer data
 * @from: userspace pointer to source buffer
 * @bytes: bytes to copy
 *
 * Copy bytes from source userspace to target buffer.
 *
 * Return: bytes remaining to be copied
 */
unsigned long
binder_alloc_copy_user_to_buffer(struct binder_alloc *alloc,
				 struct binder_buffer *buffer,
				 binder_size_t buffer_offset,
				 const void __user *from,
				 size_t bytes)
{
	if (!check_buffer(alloc, buffer, buffer_offset, bytes))
		return bytes;

	while (bytes) {
		unsigned long size;
		unsigned long ret;
		struct page *page;
		pgoff_t pgoff;
		void *kptr;

		page = binder_alloc_get_page(alloc, buffer,
					     buffer_offset, &pgoff);
		size = min_t(size_t, bytes, PAGE_SIZE - pgoff);
		kptr = kmap(page) + pgoff;
		ret = copy_from_user(kptr, from, size);
		kunmap(page);
		if (ret)
			return bytes - size + ret;
		bytes -= size;
		from += size;
		buffer_offset += size;
	}
	return 0;
}

static int binder_alloc_do_buffer_copy(struct binder_alloc *alloc,
				       bool to_buffer,
				       struct binder_buffer *buffer,
				       binder_size_t buffer_offset,
				       void *ptr,
				       size_t bytes)
{
	/* All copies must be 32-bit aligned and 32-bit size */
	if (!check_buffer(alloc, buffer, buffer_offset, bytes))
		return -EINVAL;

	while (bytes) {
		unsigned long size;
		struct page *page;
		pgoff_t pgoff;
		void *tmpptr;
		void *base_ptr;

		page = binder_alloc_get_page(alloc, buffer,
					     buffer_offset, &pgoff);
		size = min_t(size_t, bytes, PAGE_SIZE - pgoff);
		base_ptr = kmap_atomic(page);
		tmpptr = base_ptr + pgoff;
		if (to_buffer)
			memcpy(tmpptr, ptr, size);
		else
			memcpy(ptr, tmpptr, size);
		/*
		 * kunmap_atomic() takes care of flushing the cache
		 * if this device has VIVT cache arch
		 */
		kunmap_atomic(base_ptr);
		bytes -= size;
		pgoff = 0;
		ptr = ptr + size;
		buffer_offset += size;
	}
	return 0;
}

int binder_alloc_copy_to_buffer(struct binder_alloc *alloc,
				struct binder_buffer *buffer,
				binder_size_t buffer_offset,
				void *src,
				size_t bytes)
{
	return binder_alloc_do_buffer_copy(alloc, true, buffer, buffer_offset,
					   src, bytes);
}

int binder_alloc_copy_from_buffer(struct binder_alloc *alloc,
				  void *dest,
				  struct binder_buffer *buffer,
				  binder_size_t buffer_offset,
				  size_t bytes)
{
	return binder_alloc_do_buffer_copy(alloc, false, buffer, buffer_offset,
					   dest, bytes);
}