aboutsummaryrefslogtreecommitdiff
path: root/arch/x86/mm/mpx.c
blob: e323ef65c9ff467d7474d364a02081686221825a (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
/*
 * mpx.c - Memory Protection eXtensions
 *
 * Copyright (c) 2014, Intel Corporation.
 * Qiaowei Ren <qiaowei.ren@intel.com>
 * Dave Hansen <dave.hansen@intel.com>
 */
#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/syscalls.h>
#include <linux/sched/sysctl.h>

#include <asm/insn.h>
#include <asm/mman.h>
#include <asm/mmu_context.h>
#include <asm/mpx.h>
#include <asm/processor.h>
#include <asm/fpu/internal.h>

#define CREATE_TRACE_POINTS
#include <asm/trace/mpx.h>

static const char *mpx_mapping_name(struct vm_area_struct *vma)
{
	return "[mpx]";
}

static struct vm_operations_struct mpx_vma_ops = {
	.name = mpx_mapping_name,
};

static int is_mpx_vma(struct vm_area_struct *vma)
{
	return (vma->vm_ops == &mpx_vma_ops);
}

static inline unsigned long mpx_bd_size_bytes(struct mm_struct *mm)
{
	if (is_64bit_mm(mm))
		return MPX_BD_SIZE_BYTES_64;
	else
		return MPX_BD_SIZE_BYTES_32;
}

static inline unsigned long mpx_bt_size_bytes(struct mm_struct *mm)
{
	if (is_64bit_mm(mm))
		return MPX_BT_SIZE_BYTES_64;
	else
		return MPX_BT_SIZE_BYTES_32;
}

/*
 * This is really a simplified "vm_mmap". it only handles MPX
 * bounds tables (the bounds directory is user-allocated).
 *
 * Later on, we use the vma->vm_ops to uniquely identify these
 * VMAs.
 */
static unsigned long mpx_mmap(unsigned long len)
{
	unsigned long ret;
	unsigned long addr, pgoff;
	struct mm_struct *mm = current->mm;
	vm_flags_t vm_flags;
	struct vm_area_struct *vma;

	/* Only bounds table can be allocated here */
	if (len != mpx_bt_size_bytes(mm))
		return -EINVAL;

	down_write(&mm->mmap_sem);

	/* Too many mappings? */
	if (mm->map_count > sysctl_max_map_count) {
		ret = -ENOMEM;
		goto out;
	}

	/* Obtain the address to map to. we verify (or select) it and ensure
	 * that it represents a valid section of the address space.
	 */
	addr = get_unmapped_area(NULL, 0, len, 0, MAP_ANONYMOUS | MAP_PRIVATE);
	if (addr & ~PAGE_MASK) {
		ret = addr;
		goto out;
	}

	vm_flags = VM_READ | VM_WRITE | VM_MPX |
			mm->def_flags | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC;

	/* Set pgoff according to addr for anon_vma */
	pgoff = addr >> PAGE_SHIFT;

	ret = mmap_region(NULL, addr, len, vm_flags, pgoff);
	if (IS_ERR_VALUE(ret))
		goto out;

	vma = find_vma(mm, ret);
	if (!vma) {
		ret = -ENOMEM;
		goto out;
	}
	vma->vm_ops = &mpx_vma_ops;

	if (vm_flags & VM_LOCKED) {
		up_write(&mm->mmap_sem);
		mm_populate(ret, len);
		return ret;
	}

out:
	up_write(&mm->mmap_sem);
	return ret;
}

enum reg_type {
	REG_TYPE_RM = 0,
	REG_TYPE_INDEX,
	REG_TYPE_BASE,
};

static int get_reg_offset(struct insn *insn, struct pt_regs *regs,
			  enum reg_type type)
{
	int regno = 0;

	static const int regoff[] = {
		offsetof(struct pt_regs, ax),
		offsetof(struct pt_regs, cx),
		offsetof(struct pt_regs, dx),
		offsetof(struct pt_regs, bx),
		offsetof(struct pt_regs, sp),
		offsetof(struct pt_regs, bp),
		offsetof(struct pt_regs, si),
		offsetof(struct pt_regs, di),
#ifdef CONFIG_X86_64
		offsetof(struct pt_regs, r8),
		offsetof(struct pt_regs, r9),
		offsetof(struct pt_regs, r10),
		offsetof(struct pt_regs, r11),
		offsetof(struct pt_regs, r12),
		offsetof(struct pt_regs, r13),
		offsetof(struct pt_regs, r14),
		offsetof(struct pt_regs, r15),
#endif
	};
	int nr_registers = ARRAY_SIZE(regoff);
	/*
	 * Don't possibly decode a 32-bit instructions as
	 * reading a 64-bit-only register.
	 */
	if (IS_ENABLED(CONFIG_X86_64) && !insn->x86_64)
		nr_registers -= 8;

	switch (type) {
	case REG_TYPE_RM:
		regno = X86_MODRM_RM(insn->modrm.value);
		if (X86_REX_B(insn->rex_prefix.value) == 1)
			regno += 8;
		break;

	case REG_TYPE_INDEX:
		regno = X86_SIB_INDEX(insn->sib.value);
		if (X86_REX_X(insn->rex_prefix.value) == 1)
			regno += 8;
		break;

	case REG_TYPE_BASE:
		regno = X86_SIB_BASE(insn->sib.value);
		if (X86_REX_B(insn->rex_prefix.value) == 1)
			regno += 8;
		break;

	default:
		pr_err("invalid register type");
		BUG();
		break;
	}

	if (regno > nr_registers) {
		WARN_ONCE(1, "decoded an instruction with an invalid register");
		return -EINVAL;
	}
	return regoff[regno];
}

/*
 * return the address being referenced be instruction
 * for rm=3 returning the content of the rm reg
 * for rm!=3 calculates the address using SIB and Disp
 */
static void __user *mpx_get_addr_ref(struct insn *insn, struct pt_regs *regs)
{
	unsigned long addr, base, indx;
	int addr_offset, base_offset, indx_offset;
	insn_byte_t sib;

	insn_get_modrm(insn);
	insn_get_sib(insn);
	sib = insn->sib.value;

	if (X86_MODRM_MOD(insn->modrm.value) == 3) {
		addr_offset = get_reg_offset(insn, regs, REG_TYPE_RM);
		if (addr_offset < 0)
			goto out_err;
		addr = regs_get_register(regs, addr_offset);
	} else {
		if (insn->sib.nbytes) {
			base_offset = get_reg_offset(insn, regs, REG_TYPE_BASE);
			if (base_offset < 0)
				goto out_err;

			indx_offset = get_reg_offset(insn, regs, REG_TYPE_INDEX);
			if (indx_offset < 0)
				goto out_err;

			base = regs_get_register(regs, base_offset);
			indx = regs_get_register(regs, indx_offset);
			addr = base + indx * (1 << X86_SIB_SCALE(sib));
		} else {
			addr_offset = get_reg_offset(insn, regs, REG_TYPE_RM);
			if (addr_offset < 0)
				goto out_err;
			addr = regs_get_register(regs, addr_offset);
		}
		addr += insn->displacement.value;
	}
	return (void __user *)addr;
out_err:
	return (void __user *)-1;
}

static int mpx_insn_decode(struct insn *insn,
			   struct pt_regs *regs)
{
	unsigned char buf[MAX_INSN_SIZE];
	int x86_64 = !test_thread_flag(TIF_IA32);
	int not_copied;
	int nr_copied;

	not_copied = copy_from_user(buf, (void __user *)regs->ip, sizeof(buf));
	nr_copied = sizeof(buf) - not_copied;
	/*
	 * The decoder _should_ fail nicely if we pass it a short buffer.
	 * But, let's not depend on that implementation detail.  If we
	 * did not get anything, just error out now.
	 */
	if (!nr_copied)
		return -EFAULT;
	insn_init(insn, buf, nr_copied, x86_64);
	insn_get_length(insn);
	/*
	 * copy_from_user() tries to get as many bytes as we could see in
	 * the largest possible instruction.  If the instruction we are
	 * after is shorter than that _and_ we attempt to copy from
	 * something unreadable, we might get a short read.  This is OK
	 * as long as the read did not stop in the middle of the
	 * instruction.  Check to see if we got a partial instruction.
	 */
	if (nr_copied < insn->length)
		return -EFAULT;

	insn_get_opcode(insn);
	/*
	 * We only _really_ need to decode bndcl/bndcn/bndcu
	 * Error out on anything else.
	 */
	if (insn->opcode.bytes[0] != 0x0f)
		goto bad_opcode;
	if ((insn->opcode.bytes[1] != 0x1a) &&
	    (insn->opcode.bytes[1] != 0x1b))
		goto bad_opcode;

	return 0;
bad_opcode:
	return -EINVAL;
}

/*
 * If a bounds overflow occurs then a #BR is generated. This
 * function decodes MPX instructions to get violation address
 * and set this address into extended struct siginfo.
 *
 * Note that this is not a super precise way of doing this.
 * Userspace could have, by the time we get here, written
 * anything it wants in to the instructions.  We can not
 * trust anything about it.  They might not be valid
 * instructions or might encode invalid registers, etc...
 *
 * The caller is expected to kfree() the returned siginfo_t.
 */
siginfo_t *mpx_generate_siginfo(struct pt_regs *regs)
{
	const struct bndreg *bndregs, *bndreg;
	siginfo_t *info = NULL;
	struct insn insn;
	uint8_t bndregno;
	int err;

	err = mpx_insn_decode(&insn, regs);
	if (err)
		goto err_out;

	/*
	 * We know at this point that we are only dealing with
	 * MPX instructions.
	 */
	insn_get_modrm(&insn);
	bndregno = X86_MODRM_REG(insn.modrm.value);
	if (bndregno > 3) {
		err = -EINVAL;
		goto err_out;
	}
	/* get bndregs field from current task's xsave area */
	bndregs = get_xsave_field_ptr(XSTATE_BNDREGS);
	if (!bndregs) {
		err = -EINVAL;
		goto err_out;
	}
	/* now go select the individual register in the set of 4 */
	bndreg = &bndregs[bndregno];

	info = kzalloc(sizeof(*info), GFP_KERNEL);
	if (!info) {
		err = -ENOMEM;
		goto err_out;
	}
	/*
	 * The registers are always 64-bit, but the upper 32
	 * bits are ignored in 32-bit mode.  Also, note that the
	 * upper bounds are architecturally represented in 1's
	 * complement form.
	 *
	 * The 'unsigned long' cast is because the compiler
	 * complains when casting from integers to different-size
	 * pointers.
	 */
	info->si_lower = (void __user *)(unsigned long)bndreg->lower_bound;
	info->si_upper = (void __user *)(unsigned long)~bndreg->upper_bound;
	info->si_addr_lsb = 0;
	info->si_signo = SIGSEGV;
	info->si_errno = 0;
	info->si_code = SEGV_BNDERR;
	info->si_addr = mpx_get_addr_ref(&insn, regs);
	/*
	 * We were not able to extract an address from the instruction,
	 * probably because there was something invalid in it.
	 */
	if (info->si_addr == (void *)-1) {
		err = -EINVAL;
		goto err_out;
	}
	trace_mpx_bounds_register_exception(info->si_addr, bndreg);
	return info;
err_out:
	/* info might be NULL, but kfree() handles that */
	kfree(info);
	return ERR_PTR(err);
}

static __user void *mpx_get_bounds_dir(void)
{
	const struct bndcsr *bndcsr;

	if (!cpu_feature_enabled(X86_FEATURE_MPX))
		return MPX_INVALID_BOUNDS_DIR;

	/*
	 * 32-bit binaries on 64-bit kernels are currently
	 * unsupported.
	 */
	if (IS_ENABLED(CONFIG_X86_64) && test_thread_flag(TIF_IA32))
		return MPX_INVALID_BOUNDS_DIR;
	/*
	 * The bounds directory pointer is stored in a register
	 * only accessible if we first do an xsave.
	 */
	bndcsr = get_xsave_field_ptr(XSTATE_BNDCSR);
	if (!bndcsr)
		return MPX_INVALID_BOUNDS_DIR;

	/*
	 * Make sure the register looks valid by checking the
	 * enable bit.
	 */
	if (!(bndcsr->bndcfgu & MPX_BNDCFG_ENABLE_FLAG))
		return MPX_INVALID_BOUNDS_DIR;

	/*
	 * Lastly, mask off the low bits used for configuration
	 * flags, and return the address of the bounds table.
	 */
	return (void __user *)(unsigned long)
		(bndcsr->bndcfgu & MPX_BNDCFG_ADDR_MASK);
}

int mpx_enable_management(void)
{
	void __user *bd_base = MPX_INVALID_BOUNDS_DIR;
	struct mm_struct *mm = current->mm;
	int ret = 0;

	/*
	 * runtime in the userspace will be responsible for allocation of
	 * the bounds directory. Then, it will save the base of the bounds
	 * directory into XSAVE/XRSTOR Save Area and enable MPX through
	 * XRSTOR instruction.
	 *
	 * The copy_xregs_to_kernel() beneath get_xsave_field_ptr() is
	 * expected to be relatively expensive. Storing the bounds
	 * directory here means that we do not have to do xsave in the
	 * unmap path; we can just use mm->bd_addr instead.
	 */
	bd_base = mpx_get_bounds_dir();
	down_write(&mm->mmap_sem);
	mm->bd_addr = bd_base;
	if (mm->bd_addr == MPX_INVALID_BOUNDS_DIR)
		ret = -ENXIO;

	up_write(&mm->mmap_sem);
	return ret;
}

int mpx_disable_management(void)
{
	struct mm_struct *mm = current->mm;

	if (!cpu_feature_enabled(X86_FEATURE_MPX))
		return -ENXIO;

	down_write(&mm->mmap_sem);
	mm->bd_addr = MPX_INVALID_BOUNDS_DIR;
	up_write(&mm->mmap_sem);
	return 0;
}

static int mpx_cmpxchg_bd_entry(struct mm_struct *mm,
		unsigned long *curval,
		unsigned long __user *addr,
		unsigned long old_val, unsigned long new_val)
{
	int ret;
	/*
	 * user_atomic_cmpxchg_inatomic() actually uses sizeof()
	 * the pointer that we pass to it to figure out how much
	 * data to cmpxchg.  We have to be careful here not to
	 * pass a pointer to a 64-bit data type when we only want
	 * a 32-bit copy.
	 */
	if (is_64bit_mm(mm)) {
		ret = user_atomic_cmpxchg_inatomic(curval,
				addr, old_val, new_val);
	} else {
		u32 uninitialized_var(curval_32);
		u32 old_val_32 = old_val;
		u32 new_val_32 = new_val;
		u32 __user *addr_32 = (u32 __user *)addr;

		ret = user_atomic_cmpxchg_inatomic(&curval_32,
				addr_32, old_val_32, new_val_32);
		*curval = curval_32;
	}
	return ret;
}

/*
 * With 32-bit mode, a bounds directory is 4MB, and the size of each
 * bounds table is 16KB. With 64-bit mode, a bounds directory is 2GB,
 * and the size of each bounds table is 4MB.
 */
static int allocate_bt(struct mm_struct *mm, long __user *bd_entry)
{
	unsigned long expected_old_val = 0;
	unsigned long actual_old_val = 0;
	unsigned long bt_addr;
	unsigned long bd_new_entry;
	int ret = 0;

	/*
	 * Carve the virtual space out of userspace for the new
	 * bounds table:
	 */
	bt_addr = mpx_mmap(mpx_bt_size_bytes(mm));
	if (IS_ERR((void *)bt_addr))
		return PTR_ERR((void *)bt_addr);
	/*
	 * Set the valid flag (kinda like _PAGE_PRESENT in a pte)
	 */
	bd_new_entry = bt_addr | MPX_BD_ENTRY_VALID_FLAG;

	/*
	 * Go poke the address of the new bounds table in to the
	 * bounds directory entry out in userspace memory.  Note:
	 * we may race with another CPU instantiating the same table.
	 * In that case the cmpxchg will see an unexpected
	 * 'actual_old_val'.
	 *
	 * This can fault, but that's OK because we do not hold
	 * mmap_sem at this point, unlike some of the other part
	 * of the MPX code that have to pagefault_disable().
	 */
	ret = mpx_cmpxchg_bd_entry(mm, &actual_old_val,	bd_entry,
				   expected_old_val, bd_new_entry);
	if (ret)
		goto out_unmap;

	/*
	 * The user_atomic_cmpxchg_inatomic() will only return nonzero
	 * for faults, *not* if the cmpxchg itself fails.  Now we must
	 * verify that the cmpxchg itself completed successfully.
	 */
	/*
	 * We expected an empty 'expected_old_val', but instead found
	 * an apparently valid entry.  Assume we raced with another
	 * thread to instantiate this table and desclare succecss.
	 */
	if (actual_old_val & MPX_BD_ENTRY_VALID_FLAG) {
		ret = 0;
		goto out_unmap;
	}
	/*
	 * We found a non-empty bd_entry but it did not have the
	 * VALID_FLAG set.  Return an error which will result in
	 * a SEGV since this probably means that somebody scribbled
	 * some invalid data in to a bounds table.
	 */
	if (expected_old_val != actual_old_val) {
		ret = -EINVAL;
		goto out_unmap;
	}
	trace_mpx_new_bounds_table(bt_addr);
	return 0;
out_unmap:
	vm_munmap(bt_addr, mpx_bt_size_bytes(mm));
	return ret;
}

/*
 * When a BNDSTX instruction attempts to save bounds to a bounds
 * table, it will first attempt to look up the table in the
 * first-level bounds directory.  If it does not find a table in
 * the directory, a #BR is generated and we get here in order to
 * allocate a new table.
 *
 * With 32-bit mode, the size of BD is 4MB, and the size of each
 * bound table is 16KB. With 64-bit mode, the size of BD is 2GB,
 * and the size of each bound table is 4MB.
 */
static int do_mpx_bt_fault(void)
{
	unsigned long bd_entry, bd_base;
	const struct bndcsr *bndcsr;
	struct mm_struct *mm = current->mm;

	bndcsr = get_xsave_field_ptr(XSTATE_BNDCSR);
	if (!bndcsr)
		return -EINVAL;
	/*
	 * Mask off the preserve and enable bits
	 */
	bd_base = bndcsr->bndcfgu & MPX_BNDCFG_ADDR_MASK;
	/*
	 * The hardware provides the address of the missing or invalid
	 * entry via BNDSTATUS, so we don't have to go look it up.
	 */
	bd_entry = bndcsr->bndstatus & MPX_BNDSTA_ADDR_MASK;
	/*
	 * Make sure the directory entry is within where we think
	 * the directory is.
	 */
	if ((bd_entry < bd_base) ||
	    (bd_entry >= bd_base + mpx_bd_size_bytes(mm)))
		return -EINVAL;

	return allocate_bt(mm, (long __user *)bd_entry);
}

int mpx_handle_bd_fault(void)
{
	/*
	 * Userspace never asked us to manage the bounds tables,
	 * so refuse to help.
	 */
	if (!kernel_managing_mpx_tables(current->mm))
		return -EINVAL;

	if (do_mpx_bt_fault()) {
		force_sig(SIGSEGV, current);
		/*
		 * The force_sig() is essentially "handling" this
		 * exception, so we do not pass up the error
		 * from do_mpx_bt_fault().
		 */
	}
	return 0;
}

/*
 * A thin wrapper around get_user_pages().  Returns 0 if the
 * fault was resolved or -errno if not.
 */
static int mpx_resolve_fault(long __user *addr, int write)
{
	long gup_ret;
	int nr_pages = 1;
	int force = 0;

	gup_ret = get_user_pages(current, current->mm, (unsigned long)addr,
				 nr_pages, write, force, NULL, NULL);
	/*
	 * get_user_pages() returns number of pages gotten.
	 * 0 means we failed to fault in and get anything,
	 * probably because 'addr' is bad.
	 */
	if (!gup_ret)
		return -EFAULT;
	/* Other error, return it */
	if (gup_ret < 0)
		return gup_ret;
	/* must have gup'd a page and gup_ret>0, success */
	return 0;
}

static unsigned long mpx_bd_entry_to_bt_addr(struct mm_struct *mm,
					     unsigned long bd_entry)
{
	unsigned long bt_addr = bd_entry;
	int align_to_bytes;
	/*
	 * Bit 0 in a bt_entry is always the valid bit.
	 */
	bt_addr &= ~MPX_BD_ENTRY_VALID_FLAG;
	/*
	 * Tables are naturally aligned at 8-byte boundaries
	 * on 64-bit and 4-byte boundaries on 32-bit.  The
	 * documentation makes it appear that the low bits
	 * are ignored by the hardware, so we do the same.
	 */
	if (is_64bit_mm(mm))
		align_to_bytes = 8;
	else
		align_to_bytes = 4;
	bt_addr &= ~(align_to_bytes-1);
	return bt_addr;
}

/*
 * Get the base of bounds tables pointed by specific bounds
 * directory entry.
 */
static int get_bt_addr(struct mm_struct *mm,
			long __user *bd_entry_ptr,
			unsigned long *bt_addr_result)
{
	int ret;
	int valid_bit;
	unsigned long bd_entry;
	unsigned long bt_addr;

	if (!access_ok(VERIFY_READ, (bd_entry_ptr), sizeof(*bd_entry_ptr)))
		return -EFAULT;

	while (1) {
		int need_write = 0;

		pagefault_disable();
		ret = get_user(bd_entry, bd_entry_ptr);
		pagefault_enable();
		if (!ret)
			break;
		if (ret == -EFAULT)
			ret = mpx_resolve_fault(bd_entry_ptr, need_write);
		/*
		 * If we could not resolve the fault, consider it
		 * userspace's fault and error out.
		 */
		if (ret)
			return ret;
	}

	valid_bit = bd_entry & MPX_BD_ENTRY_VALID_FLAG;
	bt_addr = mpx_bd_entry_to_bt_addr(mm, bd_entry);

	/*
	 * When the kernel is managing bounds tables, a bounds directory
	 * entry will either have a valid address (plus the valid bit)
	 * *OR* be completely empty. If we see a !valid entry *and* some
	 * data in the address field, we know something is wrong. This
	 * -EINVAL return will cause a SIGSEGV.
	 */
	if (!valid_bit && bt_addr)
		return -EINVAL;
	/*
	 * Do we have an completely zeroed bt entry?  That is OK.  It
	 * just means there was no bounds table for this memory.  Make
	 * sure to distinguish this from -EINVAL, which will cause
	 * a SEGV.
	 */
	if (!valid_bit)
		return -ENOENT;

	*bt_addr_result = bt_addr;
	return 0;
}

/*
 * Free the backing physical pages of bounds table 'bt_addr'.
 * Assume start...end is within that bounds table.
 */
static int zap_bt_entries(struct mm_struct *mm,
		unsigned long bt_addr,
		unsigned long start, unsigned long end)
{
	struct vm_area_struct *vma;
	unsigned long addr, len;

	/*
	 * Find the first overlapping vma. If vma->vm_start > start, there
	 * will be a hole in the bounds table. This -EINVAL return will
	 * cause a SIGSEGV.
	 */
	vma = find_vma(mm, start);
	if (!vma || vma->vm_start > start)
		return -EINVAL;

	/*
	 * A NUMA policy on a VM_MPX VMA could cause this bouds table to
	 * be split. So we need to look across the entire 'start -> end'
	 * range of this bounds table, find all of the VM_MPX VMAs, and
	 * zap only those.
	 */
	addr = start;
	while (vma && vma->vm_start < end) {
		/*
		 * We followed a bounds directory entry down
		 * here.  If we find a non-MPX VMA, that's bad,
		 * so stop immediately and return an error.  This
		 * probably results in a SIGSEGV.
		 */
		if (!is_mpx_vma(vma))
			return -EINVAL;

		len = min(vma->vm_end, end) - addr;
		zap_page_range(vma, addr, len, NULL);
		trace_mpx_unmap_zap(addr, addr+len);

		vma = vma->vm_next;
		addr = vma->vm_start;
	}

	return 0;
}

static int unmap_single_bt(struct mm_struct *mm,
		long __user *bd_entry, unsigned long bt_addr)
{
	unsigned long expected_old_val = bt_addr | MPX_BD_ENTRY_VALID_FLAG;
	unsigned long uninitialized_var(actual_old_val);
	int ret;

	while (1) {
		int need_write = 1;
		unsigned long cleared_bd_entry = 0;

		pagefault_disable();
		ret = mpx_cmpxchg_bd_entry(mm, &actual_old_val,
				bd_entry, expected_old_val, cleared_bd_entry);
		pagefault_enable();
		if (!ret)
			break;
		if (ret == -EFAULT)
			ret = mpx_resolve_fault(bd_entry, need_write);
		/*
		 * If we could not resolve the fault, consider it
		 * userspace's fault and error out.
		 */
		if (ret)
			return ret;
	}
	/*
	 * The cmpxchg was performed, check the results.
	 */
	if (actual_old_val != expected_old_val) {
		/*
		 * Someone else raced with us to unmap the table.
		 * There was no bounds table pointed to by the
		 * directory, so declare success.  Somebody freed
		 * it.
		 */
		if (!actual_old_val)
			return 0;
		/*
		 * Something messed with the bounds directory
		 * entry.  We hold mmap_sem for read or write
		 * here, so it could not be a _new_ bounds table
		 * that someone just allocated.  Something is
		 * wrong, so pass up the error and SIGSEGV.
		 */
		return -EINVAL;
	}

	/*
	 * Note, we are likely being called under do_munmap() already. To
	 * avoid recursion, do_munmap() will check whether it comes
	 * from one bounds table through VM_MPX flag.
	 */
	return do_munmap(mm, bt_addr, mpx_bt_size_bytes(mm));
}

static inline int bt_entry_size_bytes(struct mm_struct *mm)
{
	if (is_64bit_mm(mm))
		return MPX_BT_ENTRY_BYTES_64;
	else
		return MPX_BT_ENTRY_BYTES_32;
}

/*
 * Take a virtual address and turns it in to the offset in bytes
 * inside of the bounds table where the bounds table entry
 * controlling 'addr' can be found.
 */
static unsigned long mpx_get_bt_entry_offset_bytes(struct mm_struct *mm,
		unsigned long addr)
{
	unsigned long bt_table_nr_entries;
	unsigned long offset = addr;

	if (is_64bit_mm(mm)) {
		/* Bottom 3 bits are ignored on 64-bit */
		offset >>= 3;
		bt_table_nr_entries = MPX_BT_NR_ENTRIES_64;
	} else {
		/* Bottom 2 bits are ignored on 32-bit */
		offset >>= 2;
		bt_table_nr_entries = MPX_BT_NR_ENTRIES_32;
	}
	/*
	 * We know the size of the table in to which we are
	 * indexing, and we have eliminated all the low bits
	 * which are ignored for indexing.
	 *
	 * Mask out all the high bits which we do not need
	 * to index in to the table.  Note that the tables
	 * are always powers of two so this gives us a proper
	 * mask.
	 */
	offset &= (bt_table_nr_entries-1);
	/*
	 * We now have an entry offset in terms of *entries* in
	 * the table.  We need to scale it back up to bytes.
	 */
	offset *= bt_entry_size_bytes(mm);
	return offset;
}

/*
 * How much virtual address space does a single bounds
 * directory entry cover?
 *
 * Note, we need a long long because 4GB doesn't fit in
 * to a long on 32-bit.
 */
static inline unsigned long bd_entry_virt_space(struct mm_struct *mm)
{
	unsigned long long virt_space = (1ULL << boot_cpu_data.x86_virt_bits);
	if (is_64bit_mm(mm))
		return virt_space / MPX_BD_NR_ENTRIES_64;
	else
		return virt_space / MPX_BD_NR_ENTRIES_32;
}

/*
 * Return an offset in terms of bytes in to the bounds
 * directory where the bounds directory entry for a given
 * virtual address resides.
 *
 * This has to be in bytes because the directory entries
 * are different sizes on 64/32 bit.
 */
static unsigned long mpx_get_bd_entry_offset(struct mm_struct *mm,
		unsigned long addr)
{
	/*
	 * There are several ways to derive the bd offsets.  We
	 * use the following approach here:
	 * 1. We know the size of the virtual address space
	 * 2. We know the number of entries in a bounds table
	 * 3. We know that each entry covers a fixed amount of
	 *    virtual address space.
	 * So, we can just divide the virtual address by the
	 * virtual space used by one entry to determine which
	 * entry "controls" the given virtual address.
	 */
	if (is_64bit_mm(mm)) {
		int bd_entry_size = 8; /* 64-bit pointer */
		/*
		 * Take the 64-bit addressing hole in to account.
		 */
		addr &= ((1UL << boot_cpu_data.x86_virt_bits) - 1);
		return (addr / bd_entry_virt_space(mm)) * bd_entry_size;
	} else {
		int bd_entry_size = 4; /* 32-bit pointer */
		/*
		 * 32-bit has no hole so this case needs no mask
		 */
		return (addr / bd_entry_virt_space(mm)) * bd_entry_size;
	}
	/*
	 * The two return calls above are exact copies.  If we
	 * pull out a single copy and put it in here, gcc won't
	 * realize that we're doing a power-of-2 divide and use
	 * shifts.  It uses a real divide.  If we put them up
	 * there, it manages to figure it out (gcc 4.8.3).
	 */
}

/*
 * If the bounds table pointed by bounds directory 'bd_entry' is
 * not shared, unmap this whole bounds table. Otherwise, only free
 * those backing physical pages of bounds table entries covered
 * in this virtual address region start...end.
 */
static int unmap_shared_bt(struct mm_struct *mm,
		long __user *bd_entry, unsigned long start,
		unsigned long end, bool prev_shared, bool next_shared)
{
	unsigned long bt_addr;
	unsigned long start_off, end_off;
	int ret;

	ret = get_bt_addr(mm, bd_entry, &bt_addr);
	/*
	 * We could see an "error" ret for not-present bounds
	 * tables (not really an error), or actual errors, but
	 * stop unmapping either way.
	 */
	if (ret)
		return ret;

	start_off = mpx_get_bt_entry_offset_bytes(mm, start);
	end_off   = mpx_get_bt_entry_offset_bytes(mm, end);

	if (prev_shared && next_shared)
		ret = zap_bt_entries(mm, bt_addr,
				bt_addr + start_off,
				bt_addr + end_off);
	else if (prev_shared)
		ret = zap_bt_entries(mm, bt_addr,
				bt_addr + start_off,
				bt_addr + mpx_bt_size_bytes(mm));
	else if (next_shared)
		ret = zap_bt_entries(mm, bt_addr, bt_addr,
				bt_addr + end_off);
	else
		ret = unmap_single_bt(mm, bd_entry, bt_addr);

	return ret;
}

/*
 * A virtual address region being munmap()ed might share bounds table
 * with adjacent VMAs. We only need to free the backing physical
 * memory of these shared bounds tables entries covered in this virtual
 * address region.
 */
static int unmap_edge_bts(struct mm_struct *mm,
		unsigned long start, unsigned long end)
{
	int ret;
	long __user *bde_start, *bde_end;
	struct vm_area_struct *prev, *next;
	bool prev_shared = false, next_shared = false;

	bde_start = mm->bd_addr + mpx_get_bd_entry_offset(mm, start);
	bde_end   = mm->bd_addr + mpx_get_bd_entry_offset(mm, end-1);

	/*
	 * Check whether bde_start and bde_end are shared with adjacent
	 * VMAs.
	 *
	 * We already unliked the VMAs from the mm's rbtree so 'start'
	 * is guaranteed to be in a hole. This gets us the first VMA
	 * before the hole in to 'prev' and the next VMA after the hole
	 * in to 'next'.
	 */
	next = find_vma_prev(mm, start, &prev);
	if (prev && (mm->bd_addr + mpx_get_bd_entry_offset(mm, prev->vm_end-1))
			== bde_start)
		prev_shared = true;
	if (next && (mm->bd_addr + mpx_get_bd_entry_offset(mm, next->vm_start))
			== bde_end)
		next_shared = true;

	/*
	 * This virtual address region being munmap()ed is only
	 * covered by one bounds table.
	 *
	 * In this case, if this table is also shared with adjacent
	 * VMAs, only part of the backing physical memory of the bounds
	 * table need be freeed. Otherwise the whole bounds table need
	 * be unmapped.
	 */
	if (bde_start == bde_end) {
		return unmap_shared_bt(mm, bde_start, start, end,
				prev_shared, next_shared);
	}

	/*
	 * If more than one bounds tables are covered in this virtual
	 * address region being munmap()ed, we need to separately check
	 * whether bde_start and bde_end are shared with adjacent VMAs.
	 */
	ret = unmap_shared_bt(mm, bde_start, start, end, prev_shared, false);
	if (ret)
		return ret;
	ret = unmap_shared_bt(mm, bde_end, start, end, false, next_shared);
	if (ret)
		return ret;

	return 0;
}

static int mpx_unmap_tables(struct mm_struct *mm,
		unsigned long start, unsigned long end)
{
	int ret;
	long __user *bd_entry, *bde_start, *bde_end;
	unsigned long bt_addr;

	trace_mpx_unmap_search(start, end);
	/*
	 * "Edge" bounds tables are those which are being used by the region
	 * (start -> end), but that may be shared with adjacent areas.  If they
	 * turn out to be completely unshared, they will be freed.  If they are
	 * shared, we will free the backing store (like an MADV_DONTNEED) for
	 * areas used by this region.
	 */
	ret = unmap_edge_bts(mm, start, end);
	switch (ret) {
		/* non-present tables are OK */
		case 0:
		case -ENOENT:
			/* Success, or no tables to unmap */
			break;
		case -EINVAL:
		case -EFAULT:
		default:
			return ret;
	}

	/*
	 * Only unmap the bounds table that are
	 *   1. fully covered
	 *   2. not at the edges of the mapping, even if full aligned
	 */
	bde_start = mm->bd_addr + mpx_get_bd_entry_offset(mm, start);
	bde_end   = mm->bd_addr + mpx_get_bd_entry_offset(mm, end-1);
	for (bd_entry = bde_start + 1; bd_entry < bde_end; bd_entry++) {
		ret = get_bt_addr(mm, bd_entry, &bt_addr);
		switch (ret) {
			case 0:
				break;
			case -ENOENT:
				/* No table here, try the next one */
				continue;
			case -EINVAL:
			case -EFAULT:
			default:
				/*
				 * Note: we are being strict here.
				 * Any time we run in to an issue
				 * unmapping tables, we stop and
				 * SIGSEGV.
				 */
				return ret;
		}

		ret = unmap_single_bt(mm, bd_entry, bt_addr);
		if (ret)
			return ret;
	}

	return 0;
}

/*
 * Free unused bounds tables covered in a virtual address region being
 * munmap()ed. Assume end > start.
 *
 * This function will be called by do_munmap(), and the VMAs covering
 * the virtual address region start...end have already been split if
 * necessary, and the 'vma' is the first vma in this range (start -> end).
 */
void mpx_notify_unmap(struct mm_struct *mm, struct vm_area_struct *vma,
		unsigned long start, unsigned long end)
{
	int ret;

	/*
	 * Refuse to do anything unless userspace has asked
	 * the kernel to help manage the bounds tables,
	 */
	if (!kernel_managing_mpx_tables(current->mm))
		return;
	/*
	 * This will look across the entire 'start -> end' range,
	 * and find all of the non-VM_MPX VMAs.
	 *
	 * To avoid recursion, if a VM_MPX vma is found in the range
	 * (start->end), we will not continue follow-up work. This
	 * recursion represents having bounds tables for bounds tables,
	 * which should not occur normally. Being strict about it here
	 * helps ensure that we do not have an exploitable stack overflow.
	 */
	do {
		if (vma->vm_flags & VM_MPX)
			return;
		vma = vma->vm_next;
	} while (vma && vma->vm_start < end);

	ret = mpx_unmap_tables(mm, start, end);
	if (ret)
		force_sig(SIGSEGV, current);
}