aboutsummaryrefslogtreecommitdiff
path: root/arch/x86/mm/tlb.c
blob: d400b6d9d246b93c5a274a579997a3054a5b2e22 (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
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
// SPDX-License-Identifier: GPL-2.0-only
#include <linux/init.h>

#include <linux/mm.h>
#include <linux/spinlock.h>
#include <linux/smp.h>
#include <linux/interrupt.h>
#include <linux/export.h>
#include <linux/cpu.h>
#include <linux/debugfs.h>
#include <linux/sched/smt.h>
#include <linux/task_work.h>

#include <asm/tlbflush.h>
#include <asm/mmu_context.h>
#include <asm/nospec-branch.h>
#include <asm/cache.h>
#include <asm/cacheflush.h>
#include <asm/apic.h>
#include <asm/perf_event.h>

#include "mm_internal.h"

#ifdef CONFIG_PARAVIRT
# define STATIC_NOPV
#else
# define STATIC_NOPV			static
# define __flush_tlb_local		native_flush_tlb_local
# define __flush_tlb_global		native_flush_tlb_global
# define __flush_tlb_one_user(addr)	native_flush_tlb_one_user(addr)
# define __flush_tlb_multi(msk, info)	native_flush_tlb_multi(msk, info)
#endif

/*
 *	TLB flushing, formerly SMP-only
 *		c/o Linus Torvalds.
 *
 *	These mean you can really definitely utterly forget about
 *	writing to user space from interrupts. (Its not allowed anyway).
 *
 *	Optimizations Manfred Spraul <manfred@colorfullife.com>
 *
 *	More scalable flush, from Andi Kleen
 *
 *	Implement flush IPI by CALL_FUNCTION_VECTOR, Alex Shi
 */

/*
 * Bits to mangle the TIF_SPEC_* state into the mm pointer which is
 * stored in cpu_tlb_state.last_user_mm_spec.
 */
#define LAST_USER_MM_IBPB	0x1UL
#define LAST_USER_MM_L1D_FLUSH	0x2UL
#define LAST_USER_MM_SPEC_MASK	(LAST_USER_MM_IBPB | LAST_USER_MM_L1D_FLUSH)

/* Bits to set when tlbstate and flush is (re)initialized */
#define LAST_USER_MM_INIT	LAST_USER_MM_IBPB

/*
 * The x86 feature is called PCID (Process Context IDentifier). It is similar
 * to what is traditionally called ASID on the RISC processors.
 *
 * We don't use the traditional ASID implementation, where each process/mm gets
 * its own ASID and flush/restart when we run out of ASID space.
 *
 * Instead we have a small per-cpu array of ASIDs and cache the last few mm's
 * that came by on this CPU, allowing cheaper switch_mm between processes on
 * this CPU.
 *
 * We end up with different spaces for different things. To avoid confusion we
 * use different names for each of them:
 *
 * ASID  - [0, TLB_NR_DYN_ASIDS-1]
 *         the canonical identifier for an mm
 *
 * kPCID - [1, TLB_NR_DYN_ASIDS]
 *         the value we write into the PCID part of CR3; corresponds to the
 *         ASID+1, because PCID 0 is special.
 *
 * uPCID - [2048 + 1, 2048 + TLB_NR_DYN_ASIDS]
 *         for KPTI each mm has two address spaces and thus needs two
 *         PCID values, but we can still do with a single ASID denomination
 *         for each mm. Corresponds to kPCID + 2048.
 *
 */

/* There are 12 bits of space for ASIDS in CR3 */
#define CR3_HW_ASID_BITS		12

/*
 * When enabled, PAGE_TABLE_ISOLATION consumes a single bit for
 * user/kernel switches
 */
#ifdef CONFIG_PAGE_TABLE_ISOLATION
# define PTI_CONSUMED_PCID_BITS	1
#else
# define PTI_CONSUMED_PCID_BITS	0
#endif

#define CR3_AVAIL_PCID_BITS (X86_CR3_PCID_BITS - PTI_CONSUMED_PCID_BITS)

/*
 * ASIDs are zero-based: 0->MAX_AVAIL_ASID are valid.  -1 below to account
 * for them being zero-based.  Another -1 is because PCID 0 is reserved for
 * use by non-PCID-aware users.
 */
#define MAX_ASID_AVAILABLE ((1 << CR3_AVAIL_PCID_BITS) - 2)

/*
 * Given @asid, compute kPCID
 */
static inline u16 kern_pcid(u16 asid)
{
	VM_WARN_ON_ONCE(asid > MAX_ASID_AVAILABLE);

#ifdef CONFIG_PAGE_TABLE_ISOLATION
	/*
	 * Make sure that the dynamic ASID space does not conflict with the
	 * bit we are using to switch between user and kernel ASIDs.
	 */
	BUILD_BUG_ON(TLB_NR_DYN_ASIDS >= (1 << X86_CR3_PTI_PCID_USER_BIT));

	/*
	 * The ASID being passed in here should have respected the
	 * MAX_ASID_AVAILABLE and thus never have the switch bit set.
	 */
	VM_WARN_ON_ONCE(asid & (1 << X86_CR3_PTI_PCID_USER_BIT));
#endif
	/*
	 * The dynamically-assigned ASIDs that get passed in are small
	 * (<TLB_NR_DYN_ASIDS).  They never have the high switch bit set,
	 * so do not bother to clear it.
	 *
	 * If PCID is on, ASID-aware code paths put the ASID+1 into the
	 * PCID bits.  This serves two purposes.  It prevents a nasty
	 * situation in which PCID-unaware code saves CR3, loads some other
	 * value (with PCID == 0), and then restores CR3, thus corrupting
	 * the TLB for ASID 0 if the saved ASID was nonzero.  It also means
	 * that any bugs involving loading a PCID-enabled CR3 with
	 * CR4.PCIDE off will trigger deterministically.
	 */
	return asid + 1;
}

/*
 * Given @asid, compute uPCID
 */
static inline u16 user_pcid(u16 asid)
{
	u16 ret = kern_pcid(asid);
#ifdef CONFIG_PAGE_TABLE_ISOLATION
	ret |= 1 << X86_CR3_PTI_PCID_USER_BIT;
#endif
	return ret;
}

static inline unsigned long build_cr3(pgd_t *pgd, u16 asid)
{
	if (static_cpu_has(X86_FEATURE_PCID)) {
		return __sme_pa(pgd) | kern_pcid(asid);
	} else {
		VM_WARN_ON_ONCE(asid != 0);
		return __sme_pa(pgd);
	}
}

static inline unsigned long build_cr3_noflush(pgd_t *pgd, u16 asid)
{
	VM_WARN_ON_ONCE(asid > MAX_ASID_AVAILABLE);
	/*
	 * Use boot_cpu_has() instead of this_cpu_has() as this function
	 * might be called during early boot. This should work even after
	 * boot because all CPU's the have same capabilities:
	 */
	VM_WARN_ON_ONCE(!boot_cpu_has(X86_FEATURE_PCID));
	return __sme_pa(pgd) | kern_pcid(asid) | CR3_NOFLUSH;
}

/*
 * We get here when we do something requiring a TLB invalidation
 * but could not go invalidate all of the contexts.  We do the
 * necessary invalidation by clearing out the 'ctx_id' which
 * forces a TLB flush when the context is loaded.
 */
static void clear_asid_other(void)
{
	u16 asid;

	/*
	 * This is only expected to be set if we have disabled
	 * kernel _PAGE_GLOBAL pages.
	 */
	if (!static_cpu_has(X86_FEATURE_PTI)) {
		WARN_ON_ONCE(1);
		return;
	}

	for (asid = 0; asid < TLB_NR_DYN_ASIDS; asid++) {
		/* Do not need to flush the current asid */
		if (asid == this_cpu_read(cpu_tlbstate.loaded_mm_asid))
			continue;
		/*
		 * Make sure the next time we go to switch to
		 * this asid, we do a flush:
		 */
		this_cpu_write(cpu_tlbstate.ctxs[asid].ctx_id, 0);
	}
	this_cpu_write(cpu_tlbstate.invalidate_other, false);
}

atomic64_t last_mm_ctx_id = ATOMIC64_INIT(1);


static void choose_new_asid(struct mm_struct *next, u64 next_tlb_gen,
			    u16 *new_asid, bool *need_flush)
{
	u16 asid;

	if (!static_cpu_has(X86_FEATURE_PCID)) {
		*new_asid = 0;
		*need_flush = true;
		return;
	}

	if (this_cpu_read(cpu_tlbstate.invalidate_other))
		clear_asid_other();

	for (asid = 0; asid < TLB_NR_DYN_ASIDS; asid++) {
		if (this_cpu_read(cpu_tlbstate.ctxs[asid].ctx_id) !=
		    next->context.ctx_id)
			continue;

		*new_asid = asid;
		*need_flush = (this_cpu_read(cpu_tlbstate.ctxs[asid].tlb_gen) <
			       next_tlb_gen);
		return;
	}

	/*
	 * We don't currently own an ASID slot on this CPU.
	 * Allocate a slot.
	 */
	*new_asid = this_cpu_add_return(cpu_tlbstate.next_asid, 1) - 1;
	if (*new_asid >= TLB_NR_DYN_ASIDS) {
		*new_asid = 0;
		this_cpu_write(cpu_tlbstate.next_asid, 1);
	}
	*need_flush = true;
}

/*
 * Given an ASID, flush the corresponding user ASID.  We can delay this
 * until the next time we switch to it.
 *
 * See SWITCH_TO_USER_CR3.
 */
static inline void invalidate_user_asid(u16 asid)
{
	/* There is no user ASID if address space separation is off */
	if (!IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION))
		return;

	/*
	 * We only have a single ASID if PCID is off and the CR3
	 * write will have flushed it.
	 */
	if (!cpu_feature_enabled(X86_FEATURE_PCID))
		return;

	if (!static_cpu_has(X86_FEATURE_PTI))
		return;

	__set_bit(kern_pcid(asid),
		  (unsigned long *)this_cpu_ptr(&cpu_tlbstate.user_pcid_flush_mask));
}

static void load_new_mm_cr3(pgd_t *pgdir, u16 new_asid, bool need_flush)
{
	unsigned long new_mm_cr3;

	if (need_flush) {
		invalidate_user_asid(new_asid);
		new_mm_cr3 = build_cr3(pgdir, new_asid);
	} else {
		new_mm_cr3 = build_cr3_noflush(pgdir, new_asid);
	}

	/*
	 * Caution: many callers of this function expect
	 * that load_cr3() is serializing and orders TLB
	 * fills with respect to the mm_cpumask writes.
	 */
	write_cr3(new_mm_cr3);
}

void leave_mm(int cpu)
{
	struct mm_struct *loaded_mm = this_cpu_read(cpu_tlbstate.loaded_mm);

	/*
	 * It's plausible that we're in lazy TLB mode while our mm is init_mm.
	 * If so, our callers still expect us to flush the TLB, but there
	 * aren't any user TLB entries in init_mm to worry about.
	 *
	 * This needs to happen before any other sanity checks due to
	 * intel_idle's shenanigans.
	 */
	if (loaded_mm == &init_mm)
		return;

	/* Warn if we're not lazy. */
	WARN_ON(!this_cpu_read(cpu_tlbstate_shared.is_lazy));

	switch_mm(NULL, &init_mm, NULL);
}
EXPORT_SYMBOL_GPL(leave_mm);

void switch_mm(struct mm_struct *prev, struct mm_struct *next,
	       struct task_struct *tsk)
{
	unsigned long flags;

	local_irq_save(flags);
	switch_mm_irqs_off(prev, next, tsk);
	local_irq_restore(flags);
}

/*
 * Invoked from return to user/guest by a task that opted-in to L1D
 * flushing but ended up running on an SMT enabled core due to wrong
 * affinity settings or CPU hotplug. This is part of the paranoid L1D flush
 * contract which this task requested.
 */
static void l1d_flush_force_sigbus(struct callback_head *ch)
{
	force_sig(SIGBUS);
}

static void l1d_flush_evaluate(unsigned long prev_mm, unsigned long next_mm,
				struct task_struct *next)
{
	/* Flush L1D if the outgoing task requests it */
	if (prev_mm & LAST_USER_MM_L1D_FLUSH)
		wrmsrl(MSR_IA32_FLUSH_CMD, L1D_FLUSH);

	/* Check whether the incoming task opted in for L1D flush */
	if (likely(!(next_mm & LAST_USER_MM_L1D_FLUSH)))
		return;

	/*
	 * Validate that it is not running on an SMT sibling as this would
	 * make the excercise pointless because the siblings share L1D. If
	 * it runs on a SMT sibling, notify it with SIGBUS on return to
	 * user/guest
	 */
	if (this_cpu_read(cpu_info.smt_active)) {
		clear_ti_thread_flag(&next->thread_info, TIF_SPEC_L1D_FLUSH);
		next->l1d_flush_kill.func = l1d_flush_force_sigbus;
		task_work_add(next, &next->l1d_flush_kill, TWA_RESUME);
	}
}

static unsigned long mm_mangle_tif_spec_bits(struct task_struct *next)
{
	unsigned long next_tif = read_task_thread_flags(next);
	unsigned long spec_bits = (next_tif >> TIF_SPEC_IB) & LAST_USER_MM_SPEC_MASK;

	/*
	 * Ensure that the bit shift above works as expected and the two flags
	 * end up in bit 0 and 1.
	 */
	BUILD_BUG_ON(TIF_SPEC_L1D_FLUSH != TIF_SPEC_IB + 1);

	return (unsigned long)next->mm | spec_bits;
}

static void cond_mitigation(struct task_struct *next)
{
	unsigned long prev_mm, next_mm;

	if (!next || !next->mm)
		return;

	next_mm = mm_mangle_tif_spec_bits(next);
	prev_mm = this_cpu_read(cpu_tlbstate.last_user_mm_spec);

	/*
	 * Avoid user/user BTB poisoning by flushing the branch predictor
	 * when switching between processes. This stops one process from
	 * doing Spectre-v2 attacks on another.
	 *
	 * Both, the conditional and the always IBPB mode use the mm
	 * pointer to avoid the IBPB when switching between tasks of the
	 * same process. Using the mm pointer instead of mm->context.ctx_id
	 * opens a hypothetical hole vs. mm_struct reuse, which is more or
	 * less impossible to control by an attacker. Aside of that it
	 * would only affect the first schedule so the theoretically
	 * exposed data is not really interesting.
	 */
	if (static_branch_likely(&switch_mm_cond_ibpb)) {
		/*
		 * This is a bit more complex than the always mode because
		 * it has to handle two cases:
		 *
		 * 1) Switch from a user space task (potential attacker)
		 *    which has TIF_SPEC_IB set to a user space task
		 *    (potential victim) which has TIF_SPEC_IB not set.
		 *
		 * 2) Switch from a user space task (potential attacker)
		 *    which has TIF_SPEC_IB not set to a user space task
		 *    (potential victim) which has TIF_SPEC_IB set.
		 *
		 * This could be done by unconditionally issuing IBPB when
		 * a task which has TIF_SPEC_IB set is either scheduled in
		 * or out. Though that results in two flushes when:
		 *
		 * - the same user space task is scheduled out and later
		 *   scheduled in again and only a kernel thread ran in
		 *   between.
		 *
		 * - a user space task belonging to the same process is
		 *   scheduled in after a kernel thread ran in between
		 *
		 * - a user space task belonging to the same process is
		 *   scheduled in immediately.
		 *
		 * Optimize this with reasonably small overhead for the
		 * above cases. Mangle the TIF_SPEC_IB bit into the mm
		 * pointer of the incoming task which is stored in
		 * cpu_tlbstate.last_user_mm_spec for comparison.
		 *
		 * Issue IBPB only if the mm's are different and one or
		 * both have the IBPB bit set.
		 */
		if (next_mm != prev_mm &&
		    (next_mm | prev_mm) & LAST_USER_MM_IBPB)
			indirect_branch_prediction_barrier();
	}

	if (static_branch_unlikely(&switch_mm_always_ibpb)) {
		/*
		 * Only flush when switching to a user space task with a
		 * different context than the user space task which ran
		 * last on this CPU.
		 */
		if ((prev_mm & ~LAST_USER_MM_SPEC_MASK) !=
					(unsigned long)next->mm)
			indirect_branch_prediction_barrier();
	}

	if (static_branch_unlikely(&switch_mm_cond_l1d_flush)) {
		/*
		 * Flush L1D when the outgoing task requested it and/or
		 * check whether the incoming task requested L1D flushing
		 * and ended up on an SMT sibling.
		 */
		if (unlikely((prev_mm | next_mm) & LAST_USER_MM_L1D_FLUSH))
			l1d_flush_evaluate(prev_mm, next_mm, next);
	}

	this_cpu_write(cpu_tlbstate.last_user_mm_spec, next_mm);
}

#ifdef CONFIG_PERF_EVENTS
static inline void cr4_update_pce_mm(struct mm_struct *mm)
{
	if (static_branch_unlikely(&rdpmc_always_available_key) ||
	    (!static_branch_unlikely(&rdpmc_never_available_key) &&
	     atomic_read(&mm->context.perf_rdpmc_allowed))) {
		/*
		 * Clear the existing dirty counters to
		 * prevent the leak for an RDPMC task.
		 */
		perf_clear_dirty_counters();
		cr4_set_bits_irqsoff(X86_CR4_PCE);
	} else
		cr4_clear_bits_irqsoff(X86_CR4_PCE);
}

void cr4_update_pce(void *ignored)
{
	cr4_update_pce_mm(this_cpu_read(cpu_tlbstate.loaded_mm));
}

#else
static inline void cr4_update_pce_mm(struct mm_struct *mm) { }
#endif

void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
			struct task_struct *tsk)
{
	struct mm_struct *real_prev = this_cpu_read(cpu_tlbstate.loaded_mm);
	u16 prev_asid = this_cpu_read(cpu_tlbstate.loaded_mm_asid);
	bool was_lazy = this_cpu_read(cpu_tlbstate_shared.is_lazy);
	unsigned cpu = smp_processor_id();
	u64 next_tlb_gen;
	bool need_flush;
	u16 new_asid;

	/*
	 * NB: The scheduler will call us with prev == next when switching
	 * from lazy TLB mode to normal mode if active_mm isn't changing.
	 * When this happens, we don't assume that CR3 (and hence
	 * cpu_tlbstate.loaded_mm) matches next.
	 *
	 * NB: leave_mm() calls us with prev == NULL and tsk == NULL.
	 */

	/* We don't want flush_tlb_func() to run concurrently with us. */
	if (IS_ENABLED(CONFIG_PROVE_LOCKING))
		WARN_ON_ONCE(!irqs_disabled());

	/*
	 * Verify that CR3 is what we think it is.  This will catch
	 * hypothetical buggy code that directly switches to swapper_pg_dir
	 * without going through leave_mm() / switch_mm_irqs_off() or that
	 * does something like write_cr3(read_cr3_pa()).
	 *
	 * Only do this check if CONFIG_DEBUG_VM=y because __read_cr3()
	 * isn't free.
	 */
#ifdef CONFIG_DEBUG_VM
	if (WARN_ON_ONCE(__read_cr3() != build_cr3(real_prev->pgd, prev_asid))) {
		/*
		 * If we were to BUG here, we'd be very likely to kill
		 * the system so hard that we don't see the call trace.
		 * Try to recover instead by ignoring the error and doing
		 * a global flush to minimize the chance of corruption.
		 *
		 * (This is far from being a fully correct recovery.
		 *  Architecturally, the CPU could prefetch something
		 *  back into an incorrect ASID slot and leave it there
		 *  to cause trouble down the road.  It's better than
		 *  nothing, though.)
		 */
		__flush_tlb_all();
	}
#endif
	if (was_lazy)
		this_cpu_write(cpu_tlbstate_shared.is_lazy, false);

	/*
	 * The membarrier system call requires a full memory barrier and
	 * core serialization before returning to user-space, after
	 * storing to rq->curr, when changing mm.  This is because
	 * membarrier() sends IPIs to all CPUs that are in the target mm
	 * to make them issue memory barriers.  However, if another CPU
	 * switches to/from the target mm concurrently with
	 * membarrier(), it can cause that CPU not to receive an IPI
	 * when it really should issue a memory barrier.  Writing to CR3
	 * provides that full memory barrier and core serializing
	 * instruction.
	 */
	if (real_prev == next) {
		VM_WARN_ON(this_cpu_read(cpu_tlbstate.ctxs[prev_asid].ctx_id) !=
			   next->context.ctx_id);

		/*
		 * Even in lazy TLB mode, the CPU should stay set in the
		 * mm_cpumask. The TLB shootdown code can figure out from
		 * cpu_tlbstate_shared.is_lazy whether or not to send an IPI.
		 */
		if (WARN_ON_ONCE(real_prev != &init_mm &&
				 !cpumask_test_cpu(cpu, mm_cpumask(next))))
			cpumask_set_cpu(cpu, mm_cpumask(next));

		/*
		 * If the CPU is not in lazy TLB mode, we are just switching
		 * from one thread in a process to another thread in the same
		 * process. No TLB flush required.
		 */
		if (!was_lazy)
			return;

		/*
		 * Read the tlb_gen to check whether a flush is needed.
		 * If the TLB is up to date, just use it.
		 * The barrier synchronizes with the tlb_gen increment in
		 * the TLB shootdown code.
		 */
		smp_mb();
		next_tlb_gen = atomic64_read(&next->context.tlb_gen);
		if (this_cpu_read(cpu_tlbstate.ctxs[prev_asid].tlb_gen) ==
				next_tlb_gen)
			return;

		/*
		 * TLB contents went out of date while we were in lazy
		 * mode. Fall through to the TLB switching code below.
		 */
		new_asid = prev_asid;
		need_flush = true;
	} else {
		/*
		 * Apply process to process speculation vulnerability
		 * mitigations if applicable.
		 */
		cond_mitigation(tsk);

		/*
		 * Stop remote flushes for the previous mm.
		 * Skip kernel threads; we never send init_mm TLB flushing IPIs,
		 * but the bitmap manipulation can cause cache line contention.
		 */
		if (real_prev != &init_mm) {
			VM_WARN_ON_ONCE(!cpumask_test_cpu(cpu,
						mm_cpumask(real_prev)));
			cpumask_clear_cpu(cpu, mm_cpumask(real_prev));
		}

		/*
		 * Start remote flushes and then read tlb_gen.
		 */
		if (next != &init_mm)
			cpumask_set_cpu(cpu, mm_cpumask(next));
		next_tlb_gen = atomic64_read(&next->context.tlb_gen);

		choose_new_asid(next, next_tlb_gen, &new_asid, &need_flush);

		/* Let nmi_uaccess_okay() know that we're changing CR3. */
		this_cpu_write(cpu_tlbstate.loaded_mm, LOADED_MM_SWITCHING);
		barrier();
	}

	if (need_flush) {
		this_cpu_write(cpu_tlbstate.ctxs[new_asid].ctx_id, next->context.ctx_id);
		this_cpu_write(cpu_tlbstate.ctxs[new_asid].tlb_gen, next_tlb_gen);
		load_new_mm_cr3(next->pgd, new_asid, true);

		trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
	} else {
		/* The new ASID is already up to date. */
		load_new_mm_cr3(next->pgd, new_asid, false);

		trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, 0);
	}

	/* Make sure we write CR3 before loaded_mm. */
	barrier();

	this_cpu_write(cpu_tlbstate.loaded_mm, next);
	this_cpu_write(cpu_tlbstate.loaded_mm_asid, new_asid);

	if (next != real_prev) {
		cr4_update_pce_mm(next);
		switch_ldt(real_prev, next);
	}
}

/*
 * Please ignore the name of this function.  It should be called
 * switch_to_kernel_thread().
 *
 * enter_lazy_tlb() is a hint from the scheduler that we are entering a
 * kernel thread or other context without an mm.  Acceptable implementations
 * include doing nothing whatsoever, switching to init_mm, or various clever
 * lazy tricks to try to minimize TLB flushes.
 *
 * The scheduler reserves the right to call enter_lazy_tlb() several times
 * in a row.  It will notify us that we're going back to a real mm by
 * calling switch_mm_irqs_off().
 */
void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
{
	if (this_cpu_read(cpu_tlbstate.loaded_mm) == &init_mm)
		return;

	this_cpu_write(cpu_tlbstate_shared.is_lazy, true);
}

/*
 * Call this when reinitializing a CPU.  It fixes the following potential
 * problems:
 *
 * - The ASID changed from what cpu_tlbstate thinks it is (most likely
 *   because the CPU was taken down and came back up with CR3's PCID
 *   bits clear.  CPU hotplug can do this.
 *
 * - The TLB contains junk in slots corresponding to inactive ASIDs.
 *
 * - The CPU went so far out to lunch that it may have missed a TLB
 *   flush.
 */
void initialize_tlbstate_and_flush(void)
{
	int i;
	struct mm_struct *mm = this_cpu_read(cpu_tlbstate.loaded_mm);
	u64 tlb_gen = atomic64_read(&init_mm.context.tlb_gen);
	unsigned long cr3 = __read_cr3();

	/* Assert that CR3 already references the right mm. */
	WARN_ON((cr3 & CR3_ADDR_MASK) != __pa(mm->pgd));

	/*
	 * Assert that CR4.PCIDE is set if needed.  (CR4.PCIDE initialization
	 * doesn't work like other CR4 bits because it can only be set from
	 * long mode.)
	 */
	WARN_ON(boot_cpu_has(X86_FEATURE_PCID) &&
		!(cr4_read_shadow() & X86_CR4_PCIDE));

	/* Force ASID 0 and force a TLB flush. */
	write_cr3(build_cr3(mm->pgd, 0));

	/* Reinitialize tlbstate. */
	this_cpu_write(cpu_tlbstate.last_user_mm_spec, LAST_USER_MM_INIT);
	this_cpu_write(cpu_tlbstate.loaded_mm_asid, 0);
	this_cpu_write(cpu_tlbstate.next_asid, 1);
	this_cpu_write(cpu_tlbstate.ctxs[0].ctx_id, mm->context.ctx_id);
	this_cpu_write(cpu_tlbstate.ctxs[0].tlb_gen, tlb_gen);

	for (i = 1; i < TLB_NR_DYN_ASIDS; i++)
		this_cpu_write(cpu_tlbstate.ctxs[i].ctx_id, 0);
}

/*
 * flush_tlb_func()'s memory ordering requirement is that any
 * TLB fills that happen after we flush the TLB are ordered after we
 * read active_mm's tlb_gen.  We don't need any explicit barriers
 * because all x86 flush operations are serializing and the
 * atomic64_read operation won't be reordered by the compiler.
 */
static void flush_tlb_func(void *info)
{
	/*
	 * We have three different tlb_gen values in here.  They are:
	 *
	 * - mm_tlb_gen:     the latest generation.
	 * - local_tlb_gen:  the generation that this CPU has already caught
	 *                   up to.
	 * - f->new_tlb_gen: the generation that the requester of the flush
	 *                   wants us to catch up to.
	 */
	const struct flush_tlb_info *f = info;
	struct mm_struct *loaded_mm = this_cpu_read(cpu_tlbstate.loaded_mm);
	u32 loaded_mm_asid = this_cpu_read(cpu_tlbstate.loaded_mm_asid);
	u64 mm_tlb_gen = atomic64_read(&loaded_mm->context.tlb_gen);
	u64 local_tlb_gen = this_cpu_read(cpu_tlbstate.ctxs[loaded_mm_asid].tlb_gen);
	bool local = smp_processor_id() == f->initiating_cpu;
	unsigned long nr_invalidate = 0;

	/* This code cannot presently handle being reentered. */
	VM_WARN_ON(!irqs_disabled());

	if (!local) {
		inc_irq_stat(irq_tlb_count);
		count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED);

		/* Can only happen on remote CPUs */
		if (f->mm && f->mm != loaded_mm)
			return;
	}

	if (unlikely(loaded_mm == &init_mm))
		return;

	VM_WARN_ON(this_cpu_read(cpu_tlbstate.ctxs[loaded_mm_asid].ctx_id) !=
		   loaded_mm->context.ctx_id);

	if (this_cpu_read(cpu_tlbstate_shared.is_lazy)) {
		/*
		 * We're in lazy mode.  We need to at least flush our
		 * paging-structure cache to avoid speculatively reading
		 * garbage into our TLB.  Since switching to init_mm is barely
		 * slower than a minimal flush, just switch to init_mm.
		 *
		 * This should be rare, with native_flush_tlb_multi() skipping
		 * IPIs to lazy TLB mode CPUs.
		 */
		switch_mm_irqs_off(NULL, &init_mm, NULL);
		return;
	}

	if (unlikely(local_tlb_gen == mm_tlb_gen)) {
		/*
		 * There's nothing to do: we're already up to date.  This can
		 * happen if two concurrent flushes happen -- the first flush to
		 * be handled can catch us all the way up, leaving no work for
		 * the second flush.
		 */
		goto done;
	}

	WARN_ON_ONCE(local_tlb_gen > mm_tlb_gen);
	WARN_ON_ONCE(f->new_tlb_gen > mm_tlb_gen);

	/*
	 * If we get to this point, we know that our TLB is out of date.
	 * This does not strictly imply that we need to flush (it's
	 * possible that f->new_tlb_gen <= local_tlb_gen), but we're
	 * going to need to flush in the very near future, so we might
	 * as well get it over with.
	 *
	 * The only question is whether to do a full or partial flush.
	 *
	 * We do a partial flush if requested and two extra conditions
	 * are met:
	 *
	 * 1. f->new_tlb_gen == local_tlb_gen + 1.  We have an invariant that
	 *    we've always done all needed flushes to catch up to
	 *    local_tlb_gen.  If, for example, local_tlb_gen == 2 and
	 *    f->new_tlb_gen == 3, then we know that the flush needed to bring
	 *    us up to date for tlb_gen 3 is the partial flush we're
	 *    processing.
	 *
	 *    As an example of why this check is needed, suppose that there
	 *    are two concurrent flushes.  The first is a full flush that
	 *    changes context.tlb_gen from 1 to 2.  The second is a partial
	 *    flush that changes context.tlb_gen from 2 to 3.  If they get
	 *    processed on this CPU in reverse order, we'll see
	 *     local_tlb_gen == 1, mm_tlb_gen == 3, and end != TLB_FLUSH_ALL.
	 *    If we were to use __flush_tlb_one_user() and set local_tlb_gen to
	 *    3, we'd be break the invariant: we'd update local_tlb_gen above
	 *    1 without the full flush that's needed for tlb_gen 2.
	 *
	 * 2. f->new_tlb_gen == mm_tlb_gen.  This is purely an optimization.
	 *    Partial TLB flushes are not all that much cheaper than full TLB
	 *    flushes, so it seems unlikely that it would be a performance win
	 *    to do a partial flush if that won't bring our TLB fully up to
	 *    date.  By doing a full flush instead, we can increase
	 *    local_tlb_gen all the way to mm_tlb_gen and we can probably
	 *    avoid another flush in the very near future.
	 */
	if (f->end != TLB_FLUSH_ALL &&
	    f->new_tlb_gen == local_tlb_gen + 1 &&
	    f->new_tlb_gen == mm_tlb_gen) {
		/* Partial flush */
		unsigned long addr = f->start;

		nr_invalidate = (f->end - f->start) >> f->stride_shift;

		while (addr < f->end) {
			flush_tlb_one_user(addr);
			addr += 1UL << f->stride_shift;
		}
		if (local)
			count_vm_tlb_events(NR_TLB_LOCAL_FLUSH_ONE, nr_invalidate);
	} else {
		/* Full flush. */
		nr_invalidate = TLB_FLUSH_ALL;

		flush_tlb_local();
		if (local)
			count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
	}

	/* Both paths above update our state to mm_tlb_gen. */
	this_cpu_write(cpu_tlbstate.ctxs[loaded_mm_asid].tlb_gen, mm_tlb_gen);

	/* Tracing is done in a unified manner to reduce the code size */
done:
	trace_tlb_flush(!local ? TLB_REMOTE_SHOOTDOWN :
				(f->mm == NULL) ? TLB_LOCAL_SHOOTDOWN :
						  TLB_LOCAL_MM_SHOOTDOWN,
			nr_invalidate);
}

static bool tlb_is_not_lazy(int cpu, void *data)
{
	return !per_cpu(cpu_tlbstate_shared.is_lazy, cpu);
}

DEFINE_PER_CPU_SHARED_ALIGNED(struct tlb_state_shared, cpu_tlbstate_shared);
EXPORT_PER_CPU_SYMBOL(cpu_tlbstate_shared);

STATIC_NOPV void native_flush_tlb_multi(const struct cpumask *cpumask,
					 const struct flush_tlb_info *info)
{
	/*
	 * Do accounting and tracing. Note that there are (and have always been)
	 * cases in which a remote TLB flush will be traced, but eventually
	 * would not happen.
	 */
	count_vm_tlb_event(NR_TLB_REMOTE_FLUSH);
	if (info->end == TLB_FLUSH_ALL)
		trace_tlb_flush(TLB_REMOTE_SEND_IPI, TLB_FLUSH_ALL);
	else
		trace_tlb_flush(TLB_REMOTE_SEND_IPI,
				(info->end - info->start) >> PAGE_SHIFT);

	/*
	 * If no page tables were freed, we can skip sending IPIs to
	 * CPUs in lazy TLB mode. They will flush the CPU themselves
	 * at the next context switch.
	 *
	 * However, if page tables are getting freed, we need to send the
	 * IPI everywhere, to prevent CPUs in lazy TLB mode from tripping
	 * up on the new contents of what used to be page tables, while
	 * doing a speculative memory access.
	 */
	if (info->freed_tables)
		on_each_cpu_mask(cpumask, flush_tlb_func, (void *)info, true);
	else
		on_each_cpu_cond_mask(tlb_is_not_lazy, flush_tlb_func,
				(void *)info, 1, cpumask);
}

void flush_tlb_multi(const struct cpumask *cpumask,
		      const struct flush_tlb_info *info)
{
	__flush_tlb_multi(cpumask, info);
}

/*
 * See Documentation/x86/tlb.rst for details.  We choose 33
 * because it is large enough to cover the vast majority (at
 * least 95%) of allocations, and is small enough that we are
 * confident it will not cause too much overhead.  Each single
 * flush is about 100 ns, so this caps the maximum overhead at
 * _about_ 3,000 ns.
 *
 * This is in units of pages.
 */
unsigned long tlb_single_page_flush_ceiling __read_mostly = 33;

static DEFINE_PER_CPU_SHARED_ALIGNED(struct flush_tlb_info, flush_tlb_info);

#ifdef CONFIG_DEBUG_VM
static DEFINE_PER_CPU(unsigned int, flush_tlb_info_idx);
#endif

static struct flush_tlb_info *get_flush_tlb_info(struct mm_struct *mm,
			unsigned long start, unsigned long end,
			unsigned int stride_shift, bool freed_tables,
			u64 new_tlb_gen)
{
	struct flush_tlb_info *info = this_cpu_ptr(&flush_tlb_info);

#ifdef CONFIG_DEBUG_VM
	/*
	 * Ensure that the following code is non-reentrant and flush_tlb_info
	 * is not overwritten. This means no TLB flushing is initiated by
	 * interrupt handlers and machine-check exception handlers.
	 */
	BUG_ON(this_cpu_inc_return(flush_tlb_info_idx) != 1);
#endif

	info->start		= start;
	info->end		= end;
	info->mm		= mm;
	info->stride_shift	= stride_shift;
	info->freed_tables	= freed_tables;
	info->new_tlb_gen	= new_tlb_gen;
	info->initiating_cpu	= smp_processor_id();

	return info;
}

static void put_flush_tlb_info(void)
{
#ifdef CONFIG_DEBUG_VM
	/* Complete reentrancy prevention checks */
	barrier();
	this_cpu_dec(flush_tlb_info_idx);
#endif
}

void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
				unsigned long end, unsigned int stride_shift,
				bool freed_tables)
{
	struct flush_tlb_info *info;
	u64 new_tlb_gen;
	int cpu;

	cpu = get_cpu();

	/* Should we flush just the requested range? */
	if ((end == TLB_FLUSH_ALL) ||
	    ((end - start) >> stride_shift) > tlb_single_page_flush_ceiling) {
		start = 0;
		end = TLB_FLUSH_ALL;
	}

	/* This is also a barrier that synchronizes with switch_mm(). */
	new_tlb_gen = inc_mm_tlb_gen(mm);

	info = get_flush_tlb_info(mm, start, end, stride_shift, freed_tables,
				  new_tlb_gen);

	/*
	 * flush_tlb_multi() is not optimized for the common case in which only
	 * a local TLB flush is needed. Optimize this use-case by calling
	 * flush_tlb_func_local() directly in this case.
	 */
	if (cpumask_any_but(mm_cpumask(mm), cpu) < nr_cpu_ids) {
		flush_tlb_multi(mm_cpumask(mm), info);
	} else if (mm == this_cpu_read(cpu_tlbstate.loaded_mm)) {
		lockdep_assert_irqs_enabled();
		local_irq_disable();
		flush_tlb_func(info);
		local_irq_enable();
	}

	put_flush_tlb_info();
	put_cpu();
}


static void do_flush_tlb_all(void *info)
{
	count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED);
	__flush_tlb_all();
}

void flush_tlb_all(void)
{
	count_vm_tlb_event(NR_TLB_REMOTE_FLUSH);
	on_each_cpu(do_flush_tlb_all, NULL, 1);
}

static void do_kernel_range_flush(void *info)
{
	struct flush_tlb_info *f = info;
	unsigned long addr;

	/* flush range by one by one 'invlpg' */
	for (addr = f->start; addr < f->end; addr += PAGE_SIZE)
		flush_tlb_one_kernel(addr);
}

void flush_tlb_kernel_range(unsigned long start, unsigned long end)
{
	/* Balance as user space task's flush, a bit conservative */
	if (end == TLB_FLUSH_ALL ||
	    (end - start) > tlb_single_page_flush_ceiling << PAGE_SHIFT) {
		on_each_cpu(do_flush_tlb_all, NULL, 1);
	} else {
		struct flush_tlb_info *info;

		preempt_disable();
		info = get_flush_tlb_info(NULL, start, end, 0, false, 0);

		on_each_cpu(do_kernel_range_flush, info, 1);

		put_flush_tlb_info();
		preempt_enable();
	}
}

/*
 * This can be used from process context to figure out what the value of
 * CR3 is without needing to do a (slow) __read_cr3().
 *
 * It's intended to be used for code like KVM that sneakily changes CR3
 * and needs to restore it.  It needs to be used very carefully.
 */
unsigned long __get_current_cr3_fast(void)
{
	unsigned long cr3 = build_cr3(this_cpu_read(cpu_tlbstate.loaded_mm)->pgd,
		this_cpu_read(cpu_tlbstate.loaded_mm_asid));

	/* For now, be very restrictive about when this can be called. */
	VM_WARN_ON(in_nmi() || preemptible());

	VM_BUG_ON(cr3 != __read_cr3());
	return cr3;
}
EXPORT_SYMBOL_GPL(__get_current_cr3_fast);

/*
 * Flush one page in the kernel mapping
 */
void flush_tlb_one_kernel(unsigned long addr)
{
	count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ONE);

	/*
	 * If PTI is off, then __flush_tlb_one_user() is just INVLPG or its
	 * paravirt equivalent.  Even with PCID, this is sufficient: we only
	 * use PCID if we also use global PTEs for the kernel mapping, and
	 * INVLPG flushes global translations across all address spaces.
	 *
	 * If PTI is on, then the kernel is mapped with non-global PTEs, and
	 * __flush_tlb_one_user() will flush the given address for the current
	 * kernel address space and for its usermode counterpart, but it does
	 * not flush it for other address spaces.
	 */
	flush_tlb_one_user(addr);

	if (!static_cpu_has(X86_FEATURE_PTI))
		return;

	/*
	 * See above.  We need to propagate the flush to all other address
	 * spaces.  In principle, we only need to propagate it to kernelmode
	 * address spaces, but the extra bookkeeping we would need is not
	 * worth it.
	 */
	this_cpu_write(cpu_tlbstate.invalidate_other, true);
}

/*
 * Flush one page in the user mapping
 */
STATIC_NOPV void native_flush_tlb_one_user(unsigned long addr)
{
	u32 loaded_mm_asid = this_cpu_read(cpu_tlbstate.loaded_mm_asid);

	asm volatile("invlpg (%0)" ::"r" (addr) : "memory");

	if (!static_cpu_has(X86_FEATURE_PTI))
		return;

	/*
	 * Some platforms #GP if we call invpcid(type=1/2) before CR4.PCIDE=1.
	 * Just use invalidate_user_asid() in case we are called early.
	 */
	if (!this_cpu_has(X86_FEATURE_INVPCID_SINGLE))
		invalidate_user_asid(loaded_mm_asid);
	else
		invpcid_flush_one(user_pcid(loaded_mm_asid), addr);
}

void flush_tlb_one_user(unsigned long addr)
{
	__flush_tlb_one_user(addr);
}

/*
 * Flush everything
 */
STATIC_NOPV void native_flush_tlb_global(void)
{
	unsigned long flags;

	if (static_cpu_has(X86_FEATURE_INVPCID)) {
		/*
		 * Using INVPCID is considerably faster than a pair of writes
		 * to CR4 sandwiched inside an IRQ flag save/restore.
		 *
		 * Note, this works with CR4.PCIDE=0 or 1.
		 */
		invpcid_flush_all();
		return;
	}

	/*
	 * Read-modify-write to CR4 - protect it from preemption and
	 * from interrupts. (Use the raw variant because this code can
	 * be called from deep inside debugging code.)
	 */
	raw_local_irq_save(flags);

	__native_tlb_flush_global(this_cpu_read(cpu_tlbstate.cr4));

	raw_local_irq_restore(flags);
}

/*
 * Flush the entire current user mapping
 */
STATIC_NOPV void native_flush_tlb_local(void)
{
	/*
	 * Preemption or interrupts must be disabled to protect the access
	 * to the per CPU variable and to prevent being preempted between
	 * read_cr3() and write_cr3().
	 */
	WARN_ON_ONCE(preemptible());

	invalidate_user_asid(this_cpu_read(cpu_tlbstate.loaded_mm_asid));

	/* If current->mm == NULL then the read_cr3() "borrows" an mm */
	native_write_cr3(__native_read_cr3());
}

void flush_tlb_local(void)
{
	__flush_tlb_local();
}

/*
 * Flush everything
 */
void __flush_tlb_all(void)
{
	/*
	 * This is to catch users with enabled preemption and the PGE feature
	 * and don't trigger the warning in __native_flush_tlb().
	 */
	VM_WARN_ON_ONCE(preemptible());

	if (boot_cpu_has(X86_FEATURE_PGE)) {
		__flush_tlb_global();
	} else {
		/*
		 * !PGE -> !PCID (setup_pcid()), thus every flush is total.
		 */
		flush_tlb_local();
	}
}
EXPORT_SYMBOL_GPL(__flush_tlb_all);

void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch)
{
	struct flush_tlb_info *info;

	int cpu = get_cpu();

	info = get_flush_tlb_info(NULL, 0, TLB_FLUSH_ALL, 0, false, 0);
	/*
	 * flush_tlb_multi() is not optimized for the common case in which only
	 * a local TLB flush is needed. Optimize this use-case by calling
	 * flush_tlb_func_local() directly in this case.
	 */
	if (cpumask_any_but(&batch->cpumask, cpu) < nr_cpu_ids) {
		flush_tlb_multi(&batch->cpumask, info);
	} else if (cpumask_test_cpu(cpu, &batch->cpumask)) {
		lockdep_assert_irqs_enabled();
		local_irq_disable();
		flush_tlb_func(info);
		local_irq_enable();
	}

	cpumask_clear(&batch->cpumask);

	put_flush_tlb_info();
	put_cpu();
}

/*
 * Blindly accessing user memory from NMI context can be dangerous
 * if we're in the middle of switching the current user task or
 * switching the loaded mm.  It can also be dangerous if we
 * interrupted some kernel code that was temporarily using a
 * different mm.
 */
bool nmi_uaccess_okay(void)
{
	struct mm_struct *loaded_mm = this_cpu_read(cpu_tlbstate.loaded_mm);
	struct mm_struct *current_mm = current->mm;

	VM_WARN_ON_ONCE(!loaded_mm);

	/*
	 * The condition we want to check is
	 * current_mm->pgd == __va(read_cr3_pa()).  This may be slow, though,
	 * if we're running in a VM with shadow paging, and nmi_uaccess_okay()
	 * is supposed to be reasonably fast.
	 *
	 * Instead, we check the almost equivalent but somewhat conservative
	 * condition below, and we rely on the fact that switch_mm_irqs_off()
	 * sets loaded_mm to LOADED_MM_SWITCHING before writing to CR3.
	 */
	if (loaded_mm != current_mm)
		return false;

	VM_WARN_ON_ONCE(current_mm->pgd != __va(read_cr3_pa()));

	return true;
}

static ssize_t tlbflush_read_file(struct file *file, char __user *user_buf,
			     size_t count, loff_t *ppos)
{
	char buf[32];
	unsigned int len;

	len = sprintf(buf, "%ld\n", tlb_single_page_flush_ceiling);
	return simple_read_from_buffer(user_buf, count, ppos, buf, len);
}

static ssize_t tlbflush_write_file(struct file *file,
		 const char __user *user_buf, size_t count, loff_t *ppos)
{
	char buf[32];
	ssize_t len;
	int ceiling;

	len = min(count, sizeof(buf) - 1);
	if (copy_from_user(buf, user_buf, len))
		return -EFAULT;

	buf[len] = '\0';
	if (kstrtoint(buf, 0, &ceiling))
		return -EINVAL;

	if (ceiling < 0)
		return -EINVAL;

	tlb_single_page_flush_ceiling = ceiling;
	return count;
}

static const struct file_operations fops_tlbflush = {
	.read = tlbflush_read_file,
	.write = tlbflush_write_file,
	.llseek = default_llseek,
};

static int __init create_tlb_single_page_flush_ceiling(void)
{
	debugfs_create_file("tlb_single_page_flush_ceiling", S_IRUSR | S_IWUSR,
			    arch_debugfs_dir, NULL, &fops_tlbflush);
	return 0;
}
late_initcall(create_tlb_single_page_flush_ceiling);