summaryrefslogtreecommitdiff
path: root/arch/arm64/kernel/fpsimd.c
blob: 5280e098cfb5d556e409de021cc38c5adca9ddc5 (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
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
// SPDX-License-Identifier: GPL-2.0-only
/*
 * FP/SIMD context switching and fault handling
 *
 * Copyright (C) 2012 ARM Ltd.
 * Author: Catalin Marinas <catalin.marinas@arm.com>
 */

#include <linux/bitmap.h>
#include <linux/bitops.h>
#include <linux/bottom_half.h>
#include <linux/bug.h>
#include <linux/cache.h>
#include <linux/compat.h>
#include <linux/compiler.h>
#include <linux/cpu.h>
#include <linux/cpu_pm.h>
#include <linux/ctype.h>
#include <linux/kernel.h>
#include <linux/linkage.h>
#include <linux/irqflags.h>
#include <linux/init.h>
#include <linux/percpu.h>
#include <linux/prctl.h>
#include <linux/preempt.h>
#include <linux/ptrace.h>
#include <linux/sched/signal.h>
#include <linux/sched/task_stack.h>
#include <linux/signal.h>
#include <linux/slab.h>
#include <linux/stddef.h>
#include <linux/sysctl.h>
#include <linux/swab.h>

#include <asm/esr.h>
#include <asm/exception.h>
#include <asm/fpsimd.h>
#include <asm/cpufeature.h>
#include <asm/cputype.h>
#include <asm/neon.h>
#include <asm/processor.h>
#include <asm/simd.h>
#include <asm/sigcontext.h>
#include <asm/sysreg.h>
#include <asm/traps.h>
#include <asm/virt.h>

#define FPEXC_IOF	(1 << 0)
#define FPEXC_DZF	(1 << 1)
#define FPEXC_OFF	(1 << 2)
#define FPEXC_UFF	(1 << 3)
#define FPEXC_IXF	(1 << 4)
#define FPEXC_IDF	(1 << 7)

/*
 * (Note: in this discussion, statements about FPSIMD apply equally to SVE.)
 *
 * In order to reduce the number of times the FPSIMD state is needlessly saved
 * and restored, we need to keep track of two things:
 * (a) for each task, we need to remember which CPU was the last one to have
 *     the task's FPSIMD state loaded into its FPSIMD registers;
 * (b) for each CPU, we need to remember which task's userland FPSIMD state has
 *     been loaded into its FPSIMD registers most recently, or whether it has
 *     been used to perform kernel mode NEON in the meantime.
 *
 * For (a), we add a fpsimd_cpu field to thread_struct, which gets updated to
 * the id of the current CPU every time the state is loaded onto a CPU. For (b),
 * we add the per-cpu variable 'fpsimd_last_state' (below), which contains the
 * address of the userland FPSIMD state of the task that was loaded onto the CPU
 * the most recently, or NULL if kernel mode NEON has been performed after that.
 *
 * With this in place, we no longer have to restore the next FPSIMD state right
 * when switching between tasks. Instead, we can defer this check to userland
 * resume, at which time we verify whether the CPU's fpsimd_last_state and the
 * task's fpsimd_cpu are still mutually in sync. If this is the case, we
 * can omit the FPSIMD restore.
 *
 * As an optimization, we use the thread_info flag TIF_FOREIGN_FPSTATE to
 * indicate whether or not the userland FPSIMD state of the current task is
 * present in the registers. The flag is set unless the FPSIMD registers of this
 * CPU currently contain the most recent userland FPSIMD state of the current
 * task. If the task is behaving as a VMM, then this is will be managed by
 * KVM which will clear it to indicate that the vcpu FPSIMD state is currently
 * loaded on the CPU, allowing the state to be saved if a FPSIMD-aware
 * softirq kicks in. Upon vcpu_put(), KVM will save the vcpu FP state and
 * flag the register state as invalid.
 *
 * In order to allow softirq handlers to use FPSIMD, kernel_neon_begin() may
 * save the task's FPSIMD context back to task_struct from softirq context.
 * To prevent this from racing with the manipulation of the task's FPSIMD state
 * from task context and thereby corrupting the state, it is necessary to
 * protect any manipulation of a task's fpsimd_state or TIF_FOREIGN_FPSTATE
 * flag with {, __}get_cpu_fpsimd_context(). This will still allow softirqs to
 * run but prevent them to use FPSIMD.
 *
 * For a certain task, the sequence may look something like this:
 * - the task gets scheduled in; if both the task's fpsimd_cpu field
 *   contains the id of the current CPU, and the CPU's fpsimd_last_state per-cpu
 *   variable points to the task's fpsimd_state, the TIF_FOREIGN_FPSTATE flag is
 *   cleared, otherwise it is set;
 *
 * - the task returns to userland; if TIF_FOREIGN_FPSTATE is set, the task's
 *   userland FPSIMD state is copied from memory to the registers, the task's
 *   fpsimd_cpu field is set to the id of the current CPU, the current
 *   CPU's fpsimd_last_state pointer is set to this task's fpsimd_state and the
 *   TIF_FOREIGN_FPSTATE flag is cleared;
 *
 * - the task executes an ordinary syscall; upon return to userland, the
 *   TIF_FOREIGN_FPSTATE flag will still be cleared, so no FPSIMD state is
 *   restored;
 *
 * - the task executes a syscall which executes some NEON instructions; this is
 *   preceded by a call to kernel_neon_begin(), which copies the task's FPSIMD
 *   register contents to memory, clears the fpsimd_last_state per-cpu variable
 *   and sets the TIF_FOREIGN_FPSTATE flag;
 *
 * - the task gets preempted after kernel_neon_end() is called; as we have not
 *   returned from the 2nd syscall yet, TIF_FOREIGN_FPSTATE is still set so
 *   whatever is in the FPSIMD registers is not saved to memory, but discarded.
 */
struct fpsimd_last_state_struct {
	struct user_fpsimd_state *st;
	void *sve_state;
	unsigned int sve_vl;
};

static DEFINE_PER_CPU(struct fpsimd_last_state_struct, fpsimd_last_state);

__ro_after_init struct vl_info vl_info[ARM64_VEC_MAX] = {
#ifdef CONFIG_ARM64_SVE
	[ARM64_VEC_SVE] = {
		.type			= ARM64_VEC_SVE,
		.name			= "SVE",
		.min_vl			= SVE_VL_MIN,
		.max_vl			= SVE_VL_MIN,
		.max_virtualisable_vl	= SVE_VL_MIN,
	},
#endif
};

static unsigned int vec_vl_inherit_flag(enum vec_type type)
{
	switch (type) {
	case ARM64_VEC_SVE:
		return TIF_SVE_VL_INHERIT;
	default:
		WARN_ON_ONCE(1);
		return 0;
	}
}

struct vl_config {
	int __default_vl;		/* Default VL for tasks */
};

static struct vl_config vl_config[ARM64_VEC_MAX];

static inline int get_default_vl(enum vec_type type)
{
	return READ_ONCE(vl_config[type].__default_vl);
}

#ifdef CONFIG_ARM64_SVE

static inline int get_sve_default_vl(void)
{
	return get_default_vl(ARM64_VEC_SVE);
}

static inline void set_default_vl(enum vec_type type, int val)
{
	WRITE_ONCE(vl_config[type].__default_vl, val);
}

static inline void set_sve_default_vl(int val)
{
	set_default_vl(ARM64_VEC_SVE, val);
}

static void __percpu *efi_sve_state;

#else /* ! CONFIG_ARM64_SVE */

/* Dummy declaration for code that will be optimised out: */
extern void __percpu *efi_sve_state;

#endif /* ! CONFIG_ARM64_SVE */

DEFINE_PER_CPU(bool, fpsimd_context_busy);
EXPORT_PER_CPU_SYMBOL(fpsimd_context_busy);

static void fpsimd_bind_task_to_cpu(void);

static void __get_cpu_fpsimd_context(void)
{
	bool busy = __this_cpu_xchg(fpsimd_context_busy, true);

	WARN_ON(busy);
}

/*
 * Claim ownership of the CPU FPSIMD context for use by the calling context.
 *
 * The caller may freely manipulate the FPSIMD context metadata until
 * put_cpu_fpsimd_context() is called.
 *
 * The double-underscore version must only be called if you know the task
 * can't be preempted.
 */
static void get_cpu_fpsimd_context(void)
{
	local_bh_disable();
	__get_cpu_fpsimd_context();
}

static void __put_cpu_fpsimd_context(void)
{
	bool busy = __this_cpu_xchg(fpsimd_context_busy, false);

	WARN_ON(!busy); /* No matching get_cpu_fpsimd_context()? */
}

/*
 * Release the CPU FPSIMD context.
 *
 * Must be called from a context in which get_cpu_fpsimd_context() was
 * previously called, with no call to put_cpu_fpsimd_context() in the
 * meantime.
 */
static void put_cpu_fpsimd_context(void)
{
	__put_cpu_fpsimd_context();
	local_bh_enable();
}

static bool have_cpu_fpsimd_context(void)
{
	return !preemptible() && __this_cpu_read(fpsimd_context_busy);
}

/*
 * Call __sve_free() directly only if you know task can't be scheduled
 * or preempted.
 */
static void __sve_free(struct task_struct *task)
{
	kfree(task->thread.sve_state);
	task->thread.sve_state = NULL;
}

static void sve_free(struct task_struct *task)
{
	WARN_ON(test_tsk_thread_flag(task, TIF_SVE));

	__sve_free(task);
}

unsigned int task_get_vl(const struct task_struct *task, enum vec_type type)
{
	return task->thread.vl[type];
}

void task_set_vl(struct task_struct *task, enum vec_type type,
		 unsigned long vl)
{
	task->thread.vl[type] = vl;
}

unsigned int task_get_vl_onexec(const struct task_struct *task,
				enum vec_type type)
{
	return task->thread.vl_onexec[type];
}

void task_set_vl_onexec(struct task_struct *task, enum vec_type type,
			unsigned long vl)
{
	task->thread.vl_onexec[type] = vl;
}

/*
 * TIF_SVE controls whether a task can use SVE without trapping while
 * in userspace, and also the way a task's FPSIMD/SVE state is stored
 * in thread_struct.
 *
 * The kernel uses this flag to track whether a user task is actively
 * using SVE, and therefore whether full SVE register state needs to
 * be tracked.  If not, the cheaper FPSIMD context handling code can
 * be used instead of the more costly SVE equivalents.
 *
 *  * TIF_SVE set:
 *
 *    The task can execute SVE instructions while in userspace without
 *    trapping to the kernel.
 *
 *    When stored, Z0-Z31 (incorporating Vn in bits[127:0] or the
 *    corresponding Zn), P0-P15 and FFR are encoded in in
 *    task->thread.sve_state, formatted appropriately for vector
 *    length task->thread.sve_vl.
 *
 *    task->thread.sve_state must point to a valid buffer at least
 *    sve_state_size(task) bytes in size.
 *
 *    During any syscall, the kernel may optionally clear TIF_SVE and
 *    discard the vector state except for the FPSIMD subset.
 *
 *  * TIF_SVE clear:
 *
 *    An attempt by the user task to execute an SVE instruction causes
 *    do_sve_acc() to be called, which does some preparation and then
 *    sets TIF_SVE.
 *
 *    When stored, FPSIMD registers V0-V31 are encoded in
 *    task->thread.uw.fpsimd_state; bits [max : 128] for each of Z0-Z31 are
 *    logically zero but not stored anywhere; P0-P15 and FFR are not
 *    stored and have unspecified values from userspace's point of
 *    view.  For hygiene purposes, the kernel zeroes them on next use,
 *    but userspace is discouraged from relying on this.
 *
 *    task->thread.sve_state does not need to be non-NULL, valid or any
 *    particular size: it must not be dereferenced.
 *
 *  * FPSR and FPCR are always stored in task->thread.uw.fpsimd_state
 *    irrespective of whether TIF_SVE is clear or set, since these are
 *    not vector length dependent.
 */

/*
 * Update current's FPSIMD/SVE registers from thread_struct.
 *
 * This function should be called only when the FPSIMD/SVE state in
 * thread_struct is known to be up to date, when preparing to enter
 * userspace.
 */
static void task_fpsimd_load(void)
{
	WARN_ON(!system_supports_fpsimd());
	WARN_ON(!have_cpu_fpsimd_context());

	if (IS_ENABLED(CONFIG_ARM64_SVE) && test_thread_flag(TIF_SVE)) {
		sve_set_vq(sve_vq_from_vl(task_get_sve_vl(current)) - 1);
		sve_load_state(sve_pffr(&current->thread),
			       &current->thread.uw.fpsimd_state.fpsr, true);
	} else {
		fpsimd_load_state(&current->thread.uw.fpsimd_state);
	}
}

/*
 * Ensure FPSIMD/SVE storage in memory for the loaded context is up to
 * date with respect to the CPU registers.
 */
static void fpsimd_save(void)
{
	struct fpsimd_last_state_struct const *last =
		this_cpu_ptr(&fpsimd_last_state);
	/* set by fpsimd_bind_task_to_cpu() or fpsimd_bind_state_to_cpu() */

	WARN_ON(!system_supports_fpsimd());
	WARN_ON(!have_cpu_fpsimd_context());

	if (test_thread_flag(TIF_FOREIGN_FPSTATE))
		return;

	if (IS_ENABLED(CONFIG_ARM64_SVE) &&
	    test_thread_flag(TIF_SVE)) {
		if (WARN_ON(sve_get_vl() != last->sve_vl)) {
			/*
			 * Can't save the user regs, so current would
			 * re-enter user with corrupt state.
			 * There's no way to recover, so kill it:
			 */
			force_signal_inject(SIGKILL, SI_KERNEL, 0, 0);
			return;
		}

		sve_save_state((char *)last->sve_state +
					sve_ffr_offset(last->sve_vl),
			       &last->st->fpsr, true);
	} else {
		fpsimd_save_state(last->st);
	}
}

/*
 * All vector length selection from userspace comes through here.
 * We're on a slow path, so some sanity-checks are included.
 * If things go wrong there's a bug somewhere, but try to fall back to a
 * safe choice.
 */
static unsigned int find_supported_vector_length(enum vec_type type,
						 unsigned int vl)
{
	struct vl_info *info = &vl_info[type];
	int bit;
	int max_vl = info->max_vl;

	if (WARN_ON(!sve_vl_valid(vl)))
		vl = info->min_vl;

	if (WARN_ON(!sve_vl_valid(max_vl)))
		max_vl = info->min_vl;

	if (vl > max_vl)
		vl = max_vl;

	bit = find_next_bit(info->vq_map, SVE_VQ_MAX,
			    __vq_to_bit(sve_vq_from_vl(vl)));
	return sve_vl_from_vq(__bit_to_vq(bit));
}

#if defined(CONFIG_ARM64_SVE) && defined(CONFIG_SYSCTL)

static int vec_proc_do_default_vl(struct ctl_table *table, int write,
				  void *buffer, size_t *lenp, loff_t *ppos)
{
	struct vl_info *info = table->extra1;
	enum vec_type type = info->type;
	int ret;
	int vl = get_default_vl(type);
	struct ctl_table tmp_table = {
		.data = &vl,
		.maxlen = sizeof(vl),
	};

	ret = proc_dointvec(&tmp_table, write, buffer, lenp, ppos);
	if (ret || !write)
		return ret;

	/* Writing -1 has the special meaning "set to max": */
	if (vl == -1)
		vl = info->max_vl;

	if (!sve_vl_valid(vl))
		return -EINVAL;

	set_default_vl(type, find_supported_vector_length(type, vl));
	return 0;
}

static struct ctl_table sve_default_vl_table[] = {
	{
		.procname	= "sve_default_vector_length",
		.mode		= 0644,
		.proc_handler	= vec_proc_do_default_vl,
		.extra1		= &vl_info[ARM64_VEC_SVE],
	},
	{ }
};

static int __init sve_sysctl_init(void)
{
	if (system_supports_sve())
		if (!register_sysctl("abi", sve_default_vl_table))
			return -EINVAL;

	return 0;
}

#else /* ! (CONFIG_ARM64_SVE && CONFIG_SYSCTL) */
static int __init sve_sysctl_init(void) { return 0; }
#endif /* ! (CONFIG_ARM64_SVE && CONFIG_SYSCTL) */

#define ZREG(sve_state, vq, n) ((char *)(sve_state) +		\
	(SVE_SIG_ZREG_OFFSET(vq, n) - SVE_SIG_REGS_OFFSET))

#ifdef CONFIG_CPU_BIG_ENDIAN
static __uint128_t arm64_cpu_to_le128(__uint128_t x)
{
	u64 a = swab64(x);
	u64 b = swab64(x >> 64);

	return ((__uint128_t)a << 64) | b;
}
#else
static __uint128_t arm64_cpu_to_le128(__uint128_t x)
{
	return x;
}
#endif

#define arm64_le128_to_cpu(x) arm64_cpu_to_le128(x)

static void __fpsimd_to_sve(void *sst, struct user_fpsimd_state const *fst,
			    unsigned int vq)
{
	unsigned int i;
	__uint128_t *p;

	for (i = 0; i < SVE_NUM_ZREGS; ++i) {
		p = (__uint128_t *)ZREG(sst, vq, i);
		*p = arm64_cpu_to_le128(fst->vregs[i]);
	}
}

/*
 * Transfer the FPSIMD state in task->thread.uw.fpsimd_state to
 * task->thread.sve_state.
 *
 * Task can be a non-runnable task, or current.  In the latter case,
 * the caller must have ownership of the cpu FPSIMD context before calling
 * this function.
 * task->thread.sve_state must point to at least sve_state_size(task)
 * bytes of allocated kernel memory.
 * task->thread.uw.fpsimd_state must be up to date before calling this
 * function.
 */
static void fpsimd_to_sve(struct task_struct *task)
{
	unsigned int vq;
	void *sst = task->thread.sve_state;
	struct user_fpsimd_state const *fst = &task->thread.uw.fpsimd_state;

	if (!system_supports_sve())
		return;

	vq = sve_vq_from_vl(task_get_sve_vl(task));
	__fpsimd_to_sve(sst, fst, vq);
}

/*
 * Transfer the SVE state in task->thread.sve_state to
 * task->thread.uw.fpsimd_state.
 *
 * Task can be a non-runnable task, or current.  In the latter case,
 * the caller must have ownership of the cpu FPSIMD context before calling
 * this function.
 * task->thread.sve_state must point to at least sve_state_size(task)
 * bytes of allocated kernel memory.
 * task->thread.sve_state must be up to date before calling this function.
 */
static void sve_to_fpsimd(struct task_struct *task)
{
	unsigned int vq;
	void const *sst = task->thread.sve_state;
	struct user_fpsimd_state *fst = &task->thread.uw.fpsimd_state;
	unsigned int i;
	__uint128_t const *p;

	if (!system_supports_sve())
		return;

	vq = sve_vq_from_vl(task_get_sve_vl(task));
	for (i = 0; i < SVE_NUM_ZREGS; ++i) {
		p = (__uint128_t const *)ZREG(sst, vq, i);
		fst->vregs[i] = arm64_le128_to_cpu(*p);
	}
}

#ifdef CONFIG_ARM64_SVE

/*
 * Return how many bytes of memory are required to store the full SVE
 * state for task, given task's currently configured vector length.
 */
static size_t sve_state_size(struct task_struct const *task)
{
	return SVE_SIG_REGS_SIZE(sve_vq_from_vl(task_get_sve_vl(task)));
}

/*
 * Ensure that task->thread.sve_state is allocated and sufficiently large.
 *
 * This function should be used only in preparation for replacing
 * task->thread.sve_state with new data.  The memory is always zeroed
 * here to prevent stale data from showing through: this is done in
 * the interest of testability and predictability: except in the
 * do_sve_acc() case, there is no ABI requirement to hide stale data
 * written previously be task.
 */
void sve_alloc(struct task_struct *task)
{
	if (task->thread.sve_state) {
		memset(task->thread.sve_state, 0, sve_state_size(task));
		return;
	}

	/* This is a small allocation (maximum ~8KB) and Should Not Fail. */
	task->thread.sve_state =
		kzalloc(sve_state_size(task), GFP_KERNEL);
}


/*
 * Ensure that task->thread.sve_state is up to date with respect to
 * the user task, irrespective of when SVE is in use or not.
 *
 * This should only be called by ptrace.  task must be non-runnable.
 * task->thread.sve_state must point to at least sve_state_size(task)
 * bytes of allocated kernel memory.
 */
void fpsimd_sync_to_sve(struct task_struct *task)
{
	if (!test_tsk_thread_flag(task, TIF_SVE))
		fpsimd_to_sve(task);
}

/*
 * Ensure that task->thread.uw.fpsimd_state is up to date with respect to
 * the user task, irrespective of whether SVE is in use or not.
 *
 * This should only be called by ptrace.  task must be non-runnable.
 * task->thread.sve_state must point to at least sve_state_size(task)
 * bytes of allocated kernel memory.
 */
void sve_sync_to_fpsimd(struct task_struct *task)
{
	if (test_tsk_thread_flag(task, TIF_SVE))
		sve_to_fpsimd(task);
}

/*
 * Ensure that task->thread.sve_state is up to date with respect to
 * the task->thread.uw.fpsimd_state.
 *
 * This should only be called by ptrace to merge new FPSIMD register
 * values into a task for which SVE is currently active.
 * task must be non-runnable.
 * task->thread.sve_state must point to at least sve_state_size(task)
 * bytes of allocated kernel memory.
 * task->thread.uw.fpsimd_state must already have been initialised with
 * the new FPSIMD register values to be merged in.
 */
void sve_sync_from_fpsimd_zeropad(struct task_struct *task)
{
	unsigned int vq;
	void *sst = task->thread.sve_state;
	struct user_fpsimd_state const *fst = &task->thread.uw.fpsimd_state;

	if (!test_tsk_thread_flag(task, TIF_SVE))
		return;

	vq = sve_vq_from_vl(task_get_sve_vl(task));

	memset(sst, 0, SVE_SIG_REGS_SIZE(vq));
	__fpsimd_to_sve(sst, fst, vq);
}

int vec_set_vector_length(struct task_struct *task, enum vec_type type,
			  unsigned long vl, unsigned long flags)
{
	if (flags & ~(unsigned long)(PR_SVE_VL_INHERIT |
				     PR_SVE_SET_VL_ONEXEC))
		return -EINVAL;

	if (!sve_vl_valid(vl))
		return -EINVAL;

	/*
	 * Clamp to the maximum vector length that VL-agnostic code
	 * can work with.  A flag may be assigned in the future to
	 * allow setting of larger vector lengths without confusing
	 * older software.
	 */
	if (vl > VL_ARCH_MAX)
		vl = VL_ARCH_MAX;

	vl = find_supported_vector_length(type, vl);

	if (flags & (PR_SVE_VL_INHERIT |
		     PR_SVE_SET_VL_ONEXEC))
		task_set_vl_onexec(task, type, vl);
	else
		/* Reset VL to system default on next exec: */
		task_set_vl_onexec(task, type, 0);

	/* Only actually set the VL if not deferred: */
	if (flags & PR_SVE_SET_VL_ONEXEC)
		goto out;

	if (vl == task_get_vl(task, type))
		goto out;

	/*
	 * To ensure the FPSIMD bits of the SVE vector registers are preserved,
	 * write any live register state back to task_struct, and convert to a
	 * regular FPSIMD thread.  Since the vector length can only be changed
	 * with a syscall we can't be in streaming mode while reconfiguring.
	 */
	if (task == current) {
		get_cpu_fpsimd_context();

		fpsimd_save();
	}

	fpsimd_flush_task_state(task);
	if (test_and_clear_tsk_thread_flag(task, TIF_SVE))
		sve_to_fpsimd(task);

	if (task == current)
		put_cpu_fpsimd_context();

	/*
	 * Force reallocation of task SVE state to the correct size
	 * on next use:
	 */
	sve_free(task);

	task_set_vl(task, type, vl);

out:
	update_tsk_thread_flag(task, vec_vl_inherit_flag(type),
			       flags & PR_SVE_VL_INHERIT);

	return 0;
}

/*
 * Encode the current vector length and flags for return.
 * This is only required for prctl(): ptrace has separate fields.
 * SVE and SME use the same bits for _ONEXEC and _INHERIT.
 *
 * flags are as for vec_set_vector_length().
 */
static int vec_prctl_status(enum vec_type type, unsigned long flags)
{
	int ret;

	if (flags & PR_SVE_SET_VL_ONEXEC)
		ret = task_get_vl_onexec(current, type);
	else
		ret = task_get_vl(current, type);

	if (test_thread_flag(vec_vl_inherit_flag(type)))
		ret |= PR_SVE_VL_INHERIT;

	return ret;
}

/* PR_SVE_SET_VL */
int sve_set_current_vl(unsigned long arg)
{
	unsigned long vl, flags;
	int ret;

	vl = arg & PR_SVE_VL_LEN_MASK;
	flags = arg & ~vl;

	if (!system_supports_sve() || is_compat_task())
		return -EINVAL;

	ret = vec_set_vector_length(current, ARM64_VEC_SVE, vl, flags);
	if (ret)
		return ret;

	return vec_prctl_status(ARM64_VEC_SVE, flags);
}

/* PR_SVE_GET_VL */
int sve_get_current_vl(void)
{
	if (!system_supports_sve() || is_compat_task())
		return -EINVAL;

	return vec_prctl_status(ARM64_VEC_SVE, 0);
}

static void vec_probe_vqs(struct vl_info *info,
			  DECLARE_BITMAP(map, SVE_VQ_MAX))
{
	unsigned int vq, vl;

	bitmap_zero(map, SVE_VQ_MAX);

	for (vq = SVE_VQ_MAX; vq >= SVE_VQ_MIN; --vq) {
		write_vl(info->type, vq - 1); /* self-syncing */
		vl = sve_get_vl();
		vq = sve_vq_from_vl(vl); /* skip intervening lengths */
		set_bit(__vq_to_bit(vq), map);
	}
}

/*
 * Initialise the set of known supported VQs for the boot CPU.
 * This is called during kernel boot, before secondary CPUs are brought up.
 */
void __init vec_init_vq_map(enum vec_type type)
{
	struct vl_info *info = &vl_info[type];
	vec_probe_vqs(info, info->vq_map);
	bitmap_copy(info->vq_partial_map, info->vq_map, SVE_VQ_MAX);
}

/*
 * If we haven't committed to the set of supported VQs yet, filter out
 * those not supported by the current CPU.
 * This function is called during the bring-up of early secondary CPUs only.
 */
void vec_update_vq_map(enum vec_type type)
{
	struct vl_info *info = &vl_info[type];
	DECLARE_BITMAP(tmp_map, SVE_VQ_MAX);

	vec_probe_vqs(info, tmp_map);
	bitmap_and(info->vq_map, info->vq_map, tmp_map, SVE_VQ_MAX);
	bitmap_or(info->vq_partial_map, info->vq_partial_map, tmp_map,
		  SVE_VQ_MAX);
}

/*
 * Check whether the current CPU supports all VQs in the committed set.
 * This function is called during the bring-up of late secondary CPUs only.
 */
int vec_verify_vq_map(enum vec_type type)
{
	struct vl_info *info = &vl_info[type];
	DECLARE_BITMAP(tmp_map, SVE_VQ_MAX);
	unsigned long b;

	vec_probe_vqs(info, tmp_map);

	bitmap_complement(tmp_map, tmp_map, SVE_VQ_MAX);
	if (bitmap_intersects(tmp_map, info->vq_map, SVE_VQ_MAX)) {
		pr_warn("%s: cpu%d: Required vector length(s) missing\n",
			info->name, smp_processor_id());
		return -EINVAL;
	}

	if (!IS_ENABLED(CONFIG_KVM) || !is_hyp_mode_available())
		return 0;

	/*
	 * For KVM, it is necessary to ensure that this CPU doesn't
	 * support any vector length that guests may have probed as
	 * unsupported.
	 */

	/* Recover the set of supported VQs: */
	bitmap_complement(tmp_map, tmp_map, SVE_VQ_MAX);
	/* Find VQs supported that are not globally supported: */
	bitmap_andnot(tmp_map, tmp_map, info->vq_map, SVE_VQ_MAX);

	/* Find the lowest such VQ, if any: */
	b = find_last_bit(tmp_map, SVE_VQ_MAX);
	if (b >= SVE_VQ_MAX)
		return 0; /* no mismatches */

	/*
	 * Mismatches above sve_max_virtualisable_vl are fine, since
	 * no guest is allowed to configure ZCR_EL2.LEN to exceed this:
	 */
	if (sve_vl_from_vq(__bit_to_vq(b)) <= info->max_virtualisable_vl) {
		pr_warn("%s: cpu%d: Unsupported vector length(s) present\n",
			info->name, smp_processor_id());
		return -EINVAL;
	}

	return 0;
}

static void __init sve_efi_setup(void)
{
	struct vl_info *info = &vl_info[ARM64_VEC_SVE];

	if (!IS_ENABLED(CONFIG_EFI))
		return;

	/*
	 * alloc_percpu() warns and prints a backtrace if this goes wrong.
	 * This is evidence of a crippled system and we are returning void,
	 * so no attempt is made to handle this situation here.
	 */
	if (!sve_vl_valid(info->max_vl))
		goto fail;

	efi_sve_state = __alloc_percpu(
		SVE_SIG_REGS_SIZE(sve_vq_from_vl(info->max_vl)), SVE_VQ_BYTES);
	if (!efi_sve_state)
		goto fail;

	return;

fail:
	panic("Cannot allocate percpu memory for EFI SVE save/restore");
}

/*
 * Enable SVE for EL1.
 * Intended for use by the cpufeatures code during CPU boot.
 */
void sve_kernel_enable(const struct arm64_cpu_capabilities *__always_unused p)
{
	write_sysreg(read_sysreg(CPACR_EL1) | CPACR_EL1_ZEN_EL1EN, CPACR_EL1);
	isb();
}

/*
 * Read the pseudo-ZCR used by cpufeatures to identify the supported SVE
 * vector length.
 *
 * Use only if SVE is present.
 * This function clobbers the SVE vector length.
 */
u64 read_zcr_features(void)
{
	u64 zcr;
	unsigned int vq_max;

	/*
	 * Set the maximum possible VL, and write zeroes to all other
	 * bits to see if they stick.
	 */
	sve_kernel_enable(NULL);
	write_sysreg_s(ZCR_ELx_LEN_MASK, SYS_ZCR_EL1);

	zcr = read_sysreg_s(SYS_ZCR_EL1);
	zcr &= ~(u64)ZCR_ELx_LEN_MASK; /* find sticky 1s outside LEN field */
	vq_max = sve_vq_from_vl(sve_get_vl());
	zcr |= vq_max - 1; /* set LEN field to maximum effective value */

	return zcr;
}

void __init sve_setup(void)
{
	struct vl_info *info = &vl_info[ARM64_VEC_SVE];
	u64 zcr;
	DECLARE_BITMAP(tmp_map, SVE_VQ_MAX);
	unsigned long b;

	if (!system_supports_sve())
		return;

	/*
	 * The SVE architecture mandates support for 128-bit vectors,
	 * so sve_vq_map must have at least SVE_VQ_MIN set.
	 * If something went wrong, at least try to patch it up:
	 */
	if (WARN_ON(!test_bit(__vq_to_bit(SVE_VQ_MIN), info->vq_map)))
		set_bit(__vq_to_bit(SVE_VQ_MIN), info->vq_map);

	zcr = read_sanitised_ftr_reg(SYS_ZCR_EL1);
	info->max_vl = sve_vl_from_vq((zcr & ZCR_ELx_LEN_MASK) + 1);

	/*
	 * Sanity-check that the max VL we determined through CPU features
	 * corresponds properly to sve_vq_map.  If not, do our best:
	 */
	if (WARN_ON(info->max_vl != find_supported_vector_length(ARM64_VEC_SVE,
								 info->max_vl)))
		info->max_vl = find_supported_vector_length(ARM64_VEC_SVE,
							    info->max_vl);

	/*
	 * For the default VL, pick the maximum supported value <= 64.
	 * VL == 64 is guaranteed not to grow the signal frame.
	 */
	set_sve_default_vl(find_supported_vector_length(ARM64_VEC_SVE, 64));

	bitmap_andnot(tmp_map, info->vq_partial_map, info->vq_map,
		      SVE_VQ_MAX);

	b = find_last_bit(tmp_map, SVE_VQ_MAX);
	if (b >= SVE_VQ_MAX)
		/* No non-virtualisable VLs found */
		info->max_virtualisable_vl = SVE_VQ_MAX;
	else if (WARN_ON(b == SVE_VQ_MAX - 1))
		/* No virtualisable VLs?  This is architecturally forbidden. */
		info->max_virtualisable_vl = SVE_VQ_MIN;
	else /* b + 1 < SVE_VQ_MAX */
		info->max_virtualisable_vl = sve_vl_from_vq(__bit_to_vq(b + 1));

	if (info->max_virtualisable_vl > info->max_vl)
		info->max_virtualisable_vl = info->max_vl;

	pr_info("%s: maximum available vector length %u bytes per vector\n",
		info->name, info->max_vl);
	pr_info("%s: default vector length %u bytes per vector\n",
		info->name, get_sve_default_vl());

	/* KVM decides whether to support mismatched systems. Just warn here: */
	if (sve_max_virtualisable_vl() < sve_max_vl())
		pr_warn("%s: unvirtualisable vector lengths present\n",
			info->name);

	sve_efi_setup();
}

/*
 * Called from the put_task_struct() path, which cannot get here
 * unless dead_task is really dead and not schedulable.
 */
void fpsimd_release_task(struct task_struct *dead_task)
{
	__sve_free(dead_task);
}

#endif /* CONFIG_ARM64_SVE */

/*
 * Trapped SVE access
 *
 * Storage is allocated for the full SVE state, the current FPSIMD
 * register contents are migrated across, and the access trap is
 * disabled.
 *
 * TIF_SVE should be clear on entry: otherwise, fpsimd_restore_current_state()
 * would have disabled the SVE access trap for userspace during
 * ret_to_user, making an SVE access trap impossible in that case.
 */
void do_sve_acc(unsigned int esr, struct pt_regs *regs)
{
	/* Even if we chose not to use SVE, the hardware could still trap: */
	if (unlikely(!system_supports_sve()) || WARN_ON(is_compat_task())) {
		force_signal_inject(SIGILL, ILL_ILLOPC, regs->pc, 0);
		return;
	}

	sve_alloc(current);
	if (!current->thread.sve_state) {
		force_sig(SIGKILL);
		return;
	}

	get_cpu_fpsimd_context();

	if (test_and_set_thread_flag(TIF_SVE))
		WARN_ON(1); /* SVE access shouldn't have trapped */

	/*
	 * Convert the FPSIMD state to SVE, zeroing all the state that
	 * is not shared with FPSIMD. If (as is likely) the current
	 * state is live in the registers then do this there and
	 * update our metadata for the current task including
	 * disabling the trap, otherwise update our in-memory copy.
	 */
	if (!test_thread_flag(TIF_FOREIGN_FPSTATE)) {
		unsigned long vq_minus_one =
			sve_vq_from_vl(task_get_sve_vl(current)) - 1;
		sve_set_vq(vq_minus_one);
		sve_flush_live(true, vq_minus_one);
		fpsimd_bind_task_to_cpu();
	} else {
		fpsimd_to_sve(current);
	}

	put_cpu_fpsimd_context();
}

/*
 * Trapped FP/ASIMD access.
 */
void do_fpsimd_acc(unsigned int esr, struct pt_regs *regs)
{
	/* TODO: implement lazy context saving/restoring */
	WARN_ON(1);
}

/*
 * Raise a SIGFPE for the current process.
 */
void do_fpsimd_exc(unsigned int esr, struct pt_regs *regs)
{
	unsigned int si_code = FPE_FLTUNK;

	if (esr & ESR_ELx_FP_EXC_TFV) {
		if (esr & FPEXC_IOF)
			si_code = FPE_FLTINV;
		else if (esr & FPEXC_DZF)
			si_code = FPE_FLTDIV;
		else if (esr & FPEXC_OFF)
			si_code = FPE_FLTOVF;
		else if (esr & FPEXC_UFF)
			si_code = FPE_FLTUND;
		else if (esr & FPEXC_IXF)
			si_code = FPE_FLTRES;
	}

	send_sig_fault(SIGFPE, si_code,
		       (void __user *)instruction_pointer(regs),
		       current);
}

void fpsimd_thread_switch(struct task_struct *next)
{
	bool wrong_task, wrong_cpu;

	if (!system_supports_fpsimd())
		return;

	__get_cpu_fpsimd_context();

	/* Save unsaved fpsimd state, if any: */
	fpsimd_save();

	/*
	 * Fix up TIF_FOREIGN_FPSTATE to correctly describe next's
	 * state.  For kernel threads, FPSIMD registers are never loaded
	 * and wrong_task and wrong_cpu will always be true.
	 */
	wrong_task = __this_cpu_read(fpsimd_last_state.st) !=
					&next->thread.uw.fpsimd_state;
	wrong_cpu = next->thread.fpsimd_cpu != smp_processor_id();

	update_tsk_thread_flag(next, TIF_FOREIGN_FPSTATE,
			       wrong_task || wrong_cpu);

	__put_cpu_fpsimd_context();
}

static void fpsimd_flush_thread_vl(enum vec_type type)
{
	int vl, supported_vl;

	/*
	 * Reset the task vector length as required.  This is where we
	 * ensure that all user tasks have a valid vector length
	 * configured: no kernel task can become a user task without
	 * an exec and hence a call to this function.  By the time the
	 * first call to this function is made, all early hardware
	 * probing is complete, so __sve_default_vl should be valid.
	 * If a bug causes this to go wrong, we make some noise and
	 * try to fudge thread.sve_vl to a safe value here.
	 */
	vl = task_get_vl_onexec(current, type);
	if (!vl)
		vl = get_default_vl(type);

	if (WARN_ON(!sve_vl_valid(vl)))
		vl = vl_info[type].min_vl;

	supported_vl = find_supported_vector_length(type, vl);
	if (WARN_ON(supported_vl != vl))
		vl = supported_vl;

	task_set_vl(current, type, vl);

	/*
	 * If the task is not set to inherit, ensure that the vector
	 * length will be reset by a subsequent exec:
	 */
	if (!test_thread_flag(vec_vl_inherit_flag(type)))
		task_set_vl_onexec(current, type, 0);
}

void fpsimd_flush_thread(void)
{
	if (!system_supports_fpsimd())
		return;

	get_cpu_fpsimd_context();

	fpsimd_flush_task_state(current);
	memset(&current->thread.uw.fpsimd_state, 0,
	       sizeof(current->thread.uw.fpsimd_state));

	if (system_supports_sve()) {
		clear_thread_flag(TIF_SVE);
		sve_free(current);
		fpsimd_flush_thread_vl(ARM64_VEC_SVE);
	}

	put_cpu_fpsimd_context();
}

/*
 * Save the userland FPSIMD state of 'current' to memory, but only if the state
 * currently held in the registers does in fact belong to 'current'
 */
void fpsimd_preserve_current_state(void)
{
	if (!system_supports_fpsimd())
		return;

	get_cpu_fpsimd_context();
	fpsimd_save();
	put_cpu_fpsimd_context();
}

/*
 * Like fpsimd_preserve_current_state(), but ensure that
 * current->thread.uw.fpsimd_state is updated so that it can be copied to
 * the signal frame.
 */
void fpsimd_signal_preserve_current_state(void)
{
	fpsimd_preserve_current_state();
	if (test_thread_flag(TIF_SVE))
		sve_to_fpsimd(current);
}

/*
 * Associate current's FPSIMD context with this cpu
 * The caller must have ownership of the cpu FPSIMD context before calling
 * this function.
 */
static void fpsimd_bind_task_to_cpu(void)
{
	struct fpsimd_last_state_struct *last =
		this_cpu_ptr(&fpsimd_last_state);

	WARN_ON(!system_supports_fpsimd());
	last->st = &current->thread.uw.fpsimd_state;
	last->sve_state = current->thread.sve_state;
	last->sve_vl = task_get_sve_vl(current);
	current->thread.fpsimd_cpu = smp_processor_id();

	if (system_supports_sve()) {
		/* Toggle SVE trapping for userspace if needed */
		if (test_thread_flag(TIF_SVE))
			sve_user_enable();
		else
			sve_user_disable();

		/* Serialised by exception return to user */
	}
}

void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *st, void *sve_state,
			      unsigned int sve_vl)
{
	struct fpsimd_last_state_struct *last =
		this_cpu_ptr(&fpsimd_last_state);

	WARN_ON(!system_supports_fpsimd());
	WARN_ON(!in_softirq() && !irqs_disabled());

	last->st = st;
	last->sve_state = sve_state;
	last->sve_vl = sve_vl;
}

/*
 * Load the userland FPSIMD state of 'current' from memory, but only if the
 * FPSIMD state already held in the registers is /not/ the most recent FPSIMD
 * state of 'current'.  This is called when we are preparing to return to
 * userspace to ensure that userspace sees a good register state.
 */
void fpsimd_restore_current_state(void)
{
	/*
	 * For the tasks that were created before we detected the absence of
	 * FP/SIMD, the TIF_FOREIGN_FPSTATE could be set via fpsimd_thread_switch(),
	 * e.g, init. This could be then inherited by the children processes.
	 * If we later detect that the system doesn't support FP/SIMD,
	 * we must clear the flag for  all the tasks to indicate that the
	 * FPSTATE is clean (as we can't have one) to avoid looping for ever in
	 * do_notify_resume().
	 */
	if (!system_supports_fpsimd()) {
		clear_thread_flag(TIF_FOREIGN_FPSTATE);
		return;
	}

	get_cpu_fpsimd_context();

	if (test_and_clear_thread_flag(TIF_FOREIGN_FPSTATE)) {
		task_fpsimd_load();
		fpsimd_bind_task_to_cpu();
	}

	put_cpu_fpsimd_context();
}

/*
 * Load an updated userland FPSIMD state for 'current' from memory and set the
 * flag that indicates that the FPSIMD register contents are the most recent
 * FPSIMD state of 'current'. This is used by the signal code to restore the
 * register state when returning from a signal handler in FPSIMD only cases,
 * any SVE context will be discarded.
 */
void fpsimd_update_current_state(struct user_fpsimd_state const *state)
{
	if (WARN_ON(!system_supports_fpsimd()))
		return;

	get_cpu_fpsimd_context();

	current->thread.uw.fpsimd_state = *state;
	if (test_thread_flag(TIF_SVE))
		fpsimd_to_sve(current);

	task_fpsimd_load();
	fpsimd_bind_task_to_cpu();

	clear_thread_flag(TIF_FOREIGN_FPSTATE);

	put_cpu_fpsimd_context();
}

/*
 * Invalidate live CPU copies of task t's FPSIMD state
 *
 * This function may be called with preemption enabled.  The barrier()
 * ensures that the assignment to fpsimd_cpu is visible to any
 * preemption/softirq that could race with set_tsk_thread_flag(), so
 * that TIF_FOREIGN_FPSTATE cannot be spuriously re-cleared.
 *
 * The final barrier ensures that TIF_FOREIGN_FPSTATE is seen set by any
 * subsequent code.
 */
void fpsimd_flush_task_state(struct task_struct *t)
{
	t->thread.fpsimd_cpu = NR_CPUS;
	/*
	 * If we don't support fpsimd, bail out after we have
	 * reset the fpsimd_cpu for this task and clear the
	 * FPSTATE.
	 */
	if (!system_supports_fpsimd())
		return;
	barrier();
	set_tsk_thread_flag(t, TIF_FOREIGN_FPSTATE);

	barrier();
}

/*
 * Invalidate any task's FPSIMD state that is present on this cpu.
 * The FPSIMD context should be acquired with get_cpu_fpsimd_context()
 * before calling this function.
 */
static void fpsimd_flush_cpu_state(void)
{
	WARN_ON(!system_supports_fpsimd());
	__this_cpu_write(fpsimd_last_state.st, NULL);
	set_thread_flag(TIF_FOREIGN_FPSTATE);
}

/*
 * Save the FPSIMD state to memory and invalidate cpu view.
 * This function must be called with preemption disabled.
 */
void fpsimd_save_and_flush_cpu_state(void)
{
	if (!system_supports_fpsimd())
		return;
	WARN_ON(preemptible());
	__get_cpu_fpsimd_context();
	fpsimd_save();
	fpsimd_flush_cpu_state();
	__put_cpu_fpsimd_context();
}

#ifdef CONFIG_KERNEL_MODE_NEON

/*
 * Kernel-side NEON support functions
 */

/*
 * kernel_neon_begin(): obtain the CPU FPSIMD registers for use by the calling
 * context
 *
 * Must not be called unless may_use_simd() returns true.
 * Task context in the FPSIMD registers is saved back to memory as necessary.
 *
 * A matching call to kernel_neon_end() must be made before returning from the
 * calling context.
 *
 * The caller may freely use the FPSIMD registers until kernel_neon_end() is
 * called.
 */
void kernel_neon_begin(void)
{
	if (WARN_ON(!system_supports_fpsimd()))
		return;

	BUG_ON(!may_use_simd());

	get_cpu_fpsimd_context();

	/* Save unsaved fpsimd state, if any: */
	fpsimd_save();

	/* Invalidate any task state remaining in the fpsimd regs: */
	fpsimd_flush_cpu_state();
}
EXPORT_SYMBOL(kernel_neon_begin);

/*
 * kernel_neon_end(): give the CPU FPSIMD registers back to the current task
 *
 * Must be called from a context in which kernel_neon_begin() was previously
 * called, with no call to kernel_neon_end() in the meantime.
 *
 * The caller must not use the FPSIMD registers after this function is called,
 * unless kernel_neon_begin() is called again in the meantime.
 */
void kernel_neon_end(void)
{
	if (!system_supports_fpsimd())
		return;

	put_cpu_fpsimd_context();
}
EXPORT_SYMBOL(kernel_neon_end);

#ifdef CONFIG_EFI

static DEFINE_PER_CPU(struct user_fpsimd_state, efi_fpsimd_state);
static DEFINE_PER_CPU(bool, efi_fpsimd_state_used);
static DEFINE_PER_CPU(bool, efi_sve_state_used);

/*
 * EFI runtime services support functions
 *
 * The ABI for EFI runtime services allows EFI to use FPSIMD during the call.
 * This means that for EFI (and only for EFI), we have to assume that FPSIMD
 * is always used rather than being an optional accelerator.
 *
 * These functions provide the necessary support for ensuring FPSIMD
 * save/restore in the contexts from which EFI is used.
 *
 * Do not use them for any other purpose -- if tempted to do so, you are
 * either doing something wrong or you need to propose some refactoring.
 */

/*
 * __efi_fpsimd_begin(): prepare FPSIMD for making an EFI runtime services call
 */
void __efi_fpsimd_begin(void)
{
	if (!system_supports_fpsimd())
		return;

	WARN_ON(preemptible());

	if (may_use_simd()) {
		kernel_neon_begin();
	} else {
		/*
		 * If !efi_sve_state, SVE can't be in use yet and doesn't need
		 * preserving:
		 */
		if (system_supports_sve() && likely(efi_sve_state)) {
			char *sve_state = this_cpu_ptr(efi_sve_state);

			__this_cpu_write(efi_sve_state_used, true);

			sve_save_state(sve_state + sve_ffr_offset(sve_max_vl()),
				       &this_cpu_ptr(&efi_fpsimd_state)->fpsr,
				       true);
		} else {
			fpsimd_save_state(this_cpu_ptr(&efi_fpsimd_state));
		}

		__this_cpu_write(efi_fpsimd_state_used, true);
	}
}

/*
 * __efi_fpsimd_end(): clean up FPSIMD after an EFI runtime services call
 */
void __efi_fpsimd_end(void)
{
	if (!system_supports_fpsimd())
		return;

	if (!__this_cpu_xchg(efi_fpsimd_state_used, false)) {
		kernel_neon_end();
	} else {
		if (system_supports_sve() &&
		    likely(__this_cpu_read(efi_sve_state_used))) {
			char const *sve_state = this_cpu_ptr(efi_sve_state);

			sve_set_vq(sve_vq_from_vl(sve_get_vl()) - 1);
			sve_load_state(sve_state + sve_ffr_offset(sve_max_vl()),
				       &this_cpu_ptr(&efi_fpsimd_state)->fpsr,
				       true);

			__this_cpu_write(efi_sve_state_used, false);
		} else {
			fpsimd_load_state(this_cpu_ptr(&efi_fpsimd_state));
		}
	}
}

#endif /* CONFIG_EFI */

#endif /* CONFIG_KERNEL_MODE_NEON */

#ifdef CONFIG_CPU_PM
static int fpsimd_cpu_pm_notifier(struct notifier_block *self,
				  unsigned long cmd, void *v)
{
	switch (cmd) {
	case CPU_PM_ENTER:
		fpsimd_save_and_flush_cpu_state();
		break;
	case CPU_PM_EXIT:
		break;
	case CPU_PM_ENTER_FAILED:
	default:
		return NOTIFY_DONE;
	}
	return NOTIFY_OK;
}

static struct notifier_block fpsimd_cpu_pm_notifier_block = {
	.notifier_call = fpsimd_cpu_pm_notifier,
};

static void __init fpsimd_pm_init(void)
{
	cpu_pm_register_notifier(&fpsimd_cpu_pm_notifier_block);
}

#else
static inline void fpsimd_pm_init(void) { }
#endif /* CONFIG_CPU_PM */

#ifdef CONFIG_HOTPLUG_CPU
static int fpsimd_cpu_dead(unsigned int cpu)
{
	per_cpu(fpsimd_last_state.st, cpu) = NULL;
	return 0;
}

static inline void fpsimd_hotplug_init(void)
{
	cpuhp_setup_state_nocalls(CPUHP_ARM64_FPSIMD_DEAD, "arm64/fpsimd:dead",
				  NULL, fpsimd_cpu_dead);
}

#else
static inline void fpsimd_hotplug_init(void) { }
#endif

/*
 * FP/SIMD support code initialisation.
 */
static int __init fpsimd_init(void)
{
	if (cpu_have_named_feature(FP)) {
		fpsimd_pm_init();
		fpsimd_hotplug_init();
	} else {
		pr_notice("Floating-point is not implemented\n");
	}

	if (!cpu_have_named_feature(ASIMD))
		pr_notice("Advanced SIMD is not implemented\n");

	return sve_sysctl_init();
}
core_initcall(fpsimd_init);