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
|
// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (C) 1994 Linus Torvalds
*
* Pentium III FXSR, SSE support
* General FPU state handling cleanups
* Gareth Hughes <gareth@valinux.com>, May 2000
*/
#include <asm/fpu/api.h>
#include <asm/fpu/regset.h>
#include <asm/fpu/sched.h>
#include <asm/fpu/signal.h>
#include <asm/fpu/types.h>
#include <asm/traps.h>
#include <asm/irq_regs.h>
#include <linux/hardirq.h>
#include <linux/pkeys.h>
#include <linux/vmalloc.h>
#include "context.h"
#include "internal.h"
#include "legacy.h"
#include "xstate.h"
#define CREATE_TRACE_POINTS
#include <asm/trace/fpu.h>
#ifdef CONFIG_X86_64
DEFINE_STATIC_KEY_FALSE(__fpu_state_size_dynamic);
DEFINE_PER_CPU(u64, xfd_state);
#endif
/* The FPU state configuration data for kernel and user space */
struct fpu_state_config fpu_kernel_cfg __ro_after_init;
struct fpu_state_config fpu_user_cfg __ro_after_init;
/*
* Represents the initial FPU state. It's mostly (but not completely) zeroes,
* depending on the FPU hardware format:
*/
struct fpstate init_fpstate __ro_after_init;
/*
* Track whether the kernel is using the FPU state
* currently.
*
* This flag is used:
*
* - by IRQ context code to potentially use the FPU
* if it's unused.
*
* - to debug kernel_fpu_begin()/end() correctness
*/
static DEFINE_PER_CPU(bool, in_kernel_fpu);
/*
* Track which context is using the FPU on the CPU:
*/
DEFINE_PER_CPU(struct fpu *, fpu_fpregs_owner_ctx);
static bool kernel_fpu_disabled(void)
{
return this_cpu_read(in_kernel_fpu);
}
static bool interrupted_kernel_fpu_idle(void)
{
return !kernel_fpu_disabled();
}
/*
* Were we in user mode (or vm86 mode) when we were
* interrupted?
*
* Doing kernel_fpu_begin/end() is ok if we are running
* in an interrupt context from user mode - we'll just
* save the FPU state as required.
*/
static bool interrupted_user_mode(void)
{
struct pt_regs *regs = get_irq_regs();
return regs && user_mode(regs);
}
/*
* Can we use the FPU in kernel mode with the
* whole "kernel_fpu_begin/end()" sequence?
*
* It's always ok in process context (ie "not interrupt")
* but it is sometimes ok even from an irq.
*/
bool irq_fpu_usable(void)
{
return !in_interrupt() ||
interrupted_user_mode() ||
interrupted_kernel_fpu_idle();
}
EXPORT_SYMBOL(irq_fpu_usable);
/*
* Save the FPU register state in fpu->fpstate->regs. The register state is
* preserved.
*
* Must be called with fpregs_lock() held.
*
* The legacy FNSAVE instruction clears all FPU state unconditionally, so
* register state has to be reloaded. That might be a pointless exercise
* when the FPU is going to be used by another task right after that. But
* this only affects 20+ years old 32bit systems and avoids conditionals all
* over the place.
*
* FXSAVE and all XSAVE variants preserve the FPU register state.
*/
void save_fpregs_to_fpstate(struct fpu *fpu)
{
if (likely(use_xsave())) {
os_xsave(fpu->fpstate);
/*
* AVX512 state is tracked here because its use is
* known to slow the max clock speed of the core.
*/
if (fpu->fpstate->regs.xsave.header.xfeatures & XFEATURE_MASK_AVX512)
fpu->avx512_timestamp = jiffies;
return;
}
if (likely(use_fxsr())) {
fxsave(&fpu->fpstate->regs.fxsave);
return;
}
/*
* Legacy FPU register saving, FNSAVE always clears FPU registers,
* so we have to reload them from the memory state.
*/
asm volatile("fnsave %[fp]; fwait" : [fp] "=m" (fpu->fpstate->regs.fsave));
frstor(&fpu->fpstate->regs.fsave);
}
void restore_fpregs_from_fpstate(struct fpstate *fpstate, u64 mask)
{
/*
* AMD K7/K8 and later CPUs up to Zen don't save/restore
* FDP/FIP/FOP unless an exception is pending. Clear the x87 state
* here by setting it to fixed values. "m" is a random variable
* that should be in L1.
*/
if (unlikely(static_cpu_has_bug(X86_BUG_FXSAVE_LEAK))) {
asm volatile(
"fnclex\n\t"
"emms\n\t"
"fildl %P[addr]" /* set F?P to defined value */
: : [addr] "m" (fpstate));
}
if (use_xsave()) {
/*
* Dynamically enabled features are enabled in XCR0, but
* usage requires also that the corresponding bits in XFD
* are cleared. If the bits are set then using a related
* instruction will raise #NM. This allows to do the
* allocation of the larger FPU buffer lazy from #NM or if
* the task has no permission to kill it which would happen
* via #UD if the feature is disabled in XCR0.
*
* XFD state is following the same life time rules as
* XSTATE and to restore state correctly XFD has to be
* updated before XRSTORS otherwise the component would
* stay in or go into init state even if the bits are set
* in fpstate::regs::xsave::xfeatures.
*/
xfd_update_state(fpstate);
/*
* Restoring state always needs to modify all features
* which are in @mask even if the current task cannot use
* extended features.
*
* So fpstate->xfeatures cannot be used here, because then
* a feature for which the task has no permission but was
* used by the previous task would not go into init state.
*/
mask = fpu_kernel_cfg.max_features & mask;
os_xrstor(fpstate, mask);
} else {
if (use_fxsr())
fxrstor(&fpstate->regs.fxsave);
else
frstor(&fpstate->regs.fsave);
}
}
void fpu_reset_from_exception_fixup(void)
{
restore_fpregs_from_fpstate(&init_fpstate, XFEATURE_MASK_FPSTATE);
}
#if IS_ENABLED(CONFIG_KVM)
static void __fpstate_reset(struct fpstate *fpstate, u64 xfd);
static void fpu_init_guest_permissions(struct fpu_guest *gfpu)
{
struct fpu_state_perm *fpuperm;
u64 perm;
if (!IS_ENABLED(CONFIG_X86_64))
return;
spin_lock_irq(¤t->sighand->siglock);
fpuperm = ¤t->group_leader->thread.fpu.guest_perm;
perm = fpuperm->__state_perm;
/* First fpstate allocation locks down permissions. */
WRITE_ONCE(fpuperm->__state_perm, perm | FPU_GUEST_PERM_LOCKED);
spin_unlock_irq(¤t->sighand->siglock);
gfpu->perm = perm & ~FPU_GUEST_PERM_LOCKED;
}
bool fpu_alloc_guest_fpstate(struct fpu_guest *gfpu)
{
struct fpstate *fpstate;
unsigned int size;
size = fpu_user_cfg.default_size + ALIGN(offsetof(struct fpstate, regs), 64);
fpstate = vzalloc(size);
if (!fpstate)
return false;
/* Leave xfd to 0 (the reset value defined by spec) */
__fpstate_reset(fpstate, 0);
fpstate_init_user(fpstate);
fpstate->is_valloc = true;
fpstate->is_guest = true;
gfpu->fpstate = fpstate;
gfpu->xfeatures = fpu_user_cfg.default_features;
gfpu->perm = fpu_user_cfg.default_features;
gfpu->uabi_size = fpu_user_cfg.default_size;
fpu_init_guest_permissions(gfpu);
return true;
}
EXPORT_SYMBOL_GPL(fpu_alloc_guest_fpstate);
void fpu_free_guest_fpstate(struct fpu_guest *gfpu)
{
struct fpstate *fps = gfpu->fpstate;
if (!fps)
return;
if (WARN_ON_ONCE(!fps->is_valloc || !fps->is_guest || fps->in_use))
return;
gfpu->fpstate = NULL;
vfree(fps);
}
EXPORT_SYMBOL_GPL(fpu_free_guest_fpstate);
/*
* fpu_enable_guest_xfd_features - Check xfeatures against guest perm and enable
* @guest_fpu: Pointer to the guest FPU container
* @xfeatures: Features requested by guest CPUID
*
* Enable all dynamic xfeatures according to guest perm and requested CPUID.
*
* Return: 0 on success, error code otherwise
*/
int fpu_enable_guest_xfd_features(struct fpu_guest *guest_fpu, u64 xfeatures)
{
lockdep_assert_preemption_enabled();
/* Nothing to do if all requested features are already enabled. */
xfeatures &= ~guest_fpu->xfeatures;
if (!xfeatures)
return 0;
return __xfd_enable_feature(xfeatures, guest_fpu);
}
EXPORT_SYMBOL_GPL(fpu_enable_guest_xfd_features);
#ifdef CONFIG_X86_64
void fpu_update_guest_xfd(struct fpu_guest *guest_fpu, u64 xfd)
{
fpregs_lock();
guest_fpu->fpstate->xfd = xfd;
if (guest_fpu->fpstate->in_use)
xfd_update_state(guest_fpu->fpstate);
fpregs_unlock();
}
EXPORT_SYMBOL_GPL(fpu_update_guest_xfd);
#endif /* CONFIG_X86_64 */
int fpu_swap_kvm_fpstate(struct fpu_guest *guest_fpu, bool enter_guest)
{
struct fpstate *guest_fps = guest_fpu->fpstate;
struct fpu *fpu = ¤t->thread.fpu;
struct fpstate *cur_fps = fpu->fpstate;
fpregs_lock();
if (!cur_fps->is_confidential && !test_thread_flag(TIF_NEED_FPU_LOAD))
save_fpregs_to_fpstate(fpu);
/* Swap fpstate */
if (enter_guest) {
fpu->__task_fpstate = cur_fps;
fpu->fpstate = guest_fps;
guest_fps->in_use = true;
} else {
guest_fps->in_use = false;
fpu->fpstate = fpu->__task_fpstate;
fpu->__task_fpstate = NULL;
}
cur_fps = fpu->fpstate;
if (!cur_fps->is_confidential) {
/* Includes XFD update */
restore_fpregs_from_fpstate(cur_fps, XFEATURE_MASK_FPSTATE);
} else {
/*
* XSTATE is restored by firmware from encrypted
* memory. Make sure XFD state is correct while
* running with guest fpstate
*/
xfd_update_state(cur_fps);
}
fpregs_mark_activate();
fpregs_unlock();
return 0;
}
EXPORT_SYMBOL_GPL(fpu_swap_kvm_fpstate);
void fpu_copy_guest_fpstate_to_uabi(struct fpu_guest *gfpu, void *buf,
unsigned int size, u32 pkru)
{
struct fpstate *kstate = gfpu->fpstate;
union fpregs_state *ustate = buf;
struct membuf mb = { .p = buf, .left = size };
if (cpu_feature_enabled(X86_FEATURE_XSAVE)) {
__copy_xstate_to_uabi_buf(mb, kstate, pkru, XSTATE_COPY_XSAVE);
} else {
memcpy(&ustate->fxsave, &kstate->regs.fxsave,
sizeof(ustate->fxsave));
/* Make it restorable on a XSAVE enabled host */
ustate->xsave.header.xfeatures = XFEATURE_MASK_FPSSE;
}
}
EXPORT_SYMBOL_GPL(fpu_copy_guest_fpstate_to_uabi);
int fpu_copy_uabi_to_guest_fpstate(struct fpu_guest *gfpu, const void *buf,
u64 xcr0, u32 *vpkru)
{
struct fpstate *kstate = gfpu->fpstate;
const union fpregs_state *ustate = buf;
struct pkru_state *xpkru;
int ret;
if (!cpu_feature_enabled(X86_FEATURE_XSAVE)) {
if (ustate->xsave.header.xfeatures & ~XFEATURE_MASK_FPSSE)
return -EINVAL;
if (ustate->fxsave.mxcsr & ~mxcsr_feature_mask)
return -EINVAL;
memcpy(&kstate->regs.fxsave, &ustate->fxsave, sizeof(ustate->fxsave));
return 0;
}
if (ustate->xsave.header.xfeatures & ~xcr0)
return -EINVAL;
ret = copy_uabi_from_kernel_to_xstate(kstate, ustate);
if (ret)
return ret;
/* Retrieve PKRU if not in init state */
if (kstate->regs.xsave.header.xfeatures & XFEATURE_MASK_PKRU) {
xpkru = get_xsave_addr(&kstate->regs.xsave, XFEATURE_PKRU);
*vpkru = xpkru->pkru;
}
/* Ensure that XCOMP_BV is set up for XSAVES */
xstate_init_xcomp_bv(&kstate->regs.xsave, kstate->xfeatures);
return 0;
}
EXPORT_SYMBOL_GPL(fpu_copy_uabi_to_guest_fpstate);
#endif /* CONFIG_KVM */
void kernel_fpu_begin_mask(unsigned int kfpu_mask)
{
preempt_disable();
WARN_ON_FPU(!irq_fpu_usable());
WARN_ON_FPU(this_cpu_read(in_kernel_fpu));
this_cpu_write(in_kernel_fpu, true);
if (!(current->flags & PF_KTHREAD) &&
!test_thread_flag(TIF_NEED_FPU_LOAD)) {
set_thread_flag(TIF_NEED_FPU_LOAD);
save_fpregs_to_fpstate(¤t->thread.fpu);
}
__cpu_invalidate_fpregs_state();
/* Put sane initial values into the control registers. */
if (likely(kfpu_mask & KFPU_MXCSR) && boot_cpu_has(X86_FEATURE_XMM))
ldmxcsr(MXCSR_DEFAULT);
if (unlikely(kfpu_mask & KFPU_387) && boot_cpu_has(X86_FEATURE_FPU))
asm volatile ("fninit");
}
EXPORT_SYMBOL_GPL(kernel_fpu_begin_mask);
void kernel_fpu_end(void)
{
WARN_ON_FPU(!this_cpu_read(in_kernel_fpu));
this_cpu_write(in_kernel_fpu, false);
preempt_enable();
}
EXPORT_SYMBOL_GPL(kernel_fpu_end);
/*
* Sync the FPU register state to current's memory register state when the
* current task owns the FPU. The hardware register state is preserved.
*/
void fpu_sync_fpstate(struct fpu *fpu)
{
WARN_ON_FPU(fpu != ¤t->thread.fpu);
fpregs_lock();
trace_x86_fpu_before_save(fpu);
if (!test_thread_flag(TIF_NEED_FPU_LOAD))
save_fpregs_to_fpstate(fpu);
trace_x86_fpu_after_save(fpu);
fpregs_unlock();
}
static inline unsigned int init_fpstate_copy_size(void)
{
if (!use_xsave())
return fpu_kernel_cfg.default_size;
/* XSAVE(S) just needs the legacy and the xstate header part */
return sizeof(init_fpstate.regs.xsave);
}
static inline void fpstate_init_fxstate(struct fpstate *fpstate)
{
fpstate->regs.fxsave.cwd = 0x37f;
fpstate->regs.fxsave.mxcsr = MXCSR_DEFAULT;
}
/*
* Legacy x87 fpstate state init:
*/
static inline void fpstate_init_fstate(struct fpstate *fpstate)
{
fpstate->regs.fsave.cwd = 0xffff037fu;
fpstate->regs.fsave.swd = 0xffff0000u;
fpstate->regs.fsave.twd = 0xffffffffu;
fpstate->regs.fsave.fos = 0xffff0000u;
}
/*
* Used in two places:
* 1) Early boot to setup init_fpstate for non XSAVE systems
* 2) fpu_init_fpstate_user() which is invoked from KVM
*/
void fpstate_init_user(struct fpstate *fpstate)
{
if (!cpu_feature_enabled(X86_FEATURE_FPU)) {
fpstate_init_soft(&fpstate->regs.soft);
return;
}
xstate_init_xcomp_bv(&fpstate->regs.xsave, fpstate->xfeatures);
if (cpu_feature_enabled(X86_FEATURE_FXSR))
fpstate_init_fxstate(fpstate);
else
fpstate_init_fstate(fpstate);
}
static void __fpstate_reset(struct fpstate *fpstate, u64 xfd)
{
/* Initialize sizes and feature masks */
fpstate->size = fpu_kernel_cfg.default_size;
fpstate->user_size = fpu_user_cfg.default_size;
fpstate->xfeatures = fpu_kernel_cfg.default_features;
fpstate->user_xfeatures = fpu_user_cfg.default_features;
fpstate->xfd = xfd;
}
void fpstate_reset(struct fpu *fpu)
{
/* Set the fpstate pointer to the default fpstate */
fpu->fpstate = &fpu->__fpstate;
__fpstate_reset(fpu->fpstate, init_fpstate.xfd);
/* Initialize the permission related info in fpu */
fpu->perm.__state_perm = fpu_kernel_cfg.default_features;
fpu->perm.__state_size = fpu_kernel_cfg.default_size;
fpu->perm.__user_state_size = fpu_user_cfg.default_size;
/* Same defaults for guests */
fpu->guest_perm = fpu->perm;
}
static inline void fpu_inherit_perms(struct fpu *dst_fpu)
{
if (fpu_state_size_dynamic()) {
struct fpu *src_fpu = ¤t->group_leader->thread.fpu;
spin_lock_irq(¤t->sighand->siglock);
/* Fork also inherits the permissions of the parent */
dst_fpu->perm = src_fpu->perm;
dst_fpu->guest_perm = src_fpu->guest_perm;
spin_unlock_irq(¤t->sighand->siglock);
}
}
/* Clone current's FPU state on fork */
int fpu_clone(struct task_struct *dst, unsigned long clone_flags)
{
struct fpu *src_fpu = ¤t->thread.fpu;
struct fpu *dst_fpu = &dst->thread.fpu;
/* The new task's FPU state cannot be valid in the hardware. */
dst_fpu->last_cpu = -1;
fpstate_reset(dst_fpu);
if (!cpu_feature_enabled(X86_FEATURE_FPU))
return 0;
/*
* Enforce reload for user space tasks and prevent kernel threads
* from trying to save the FPU registers on context switch.
*/
set_tsk_thread_flag(dst, TIF_NEED_FPU_LOAD);
/*
* No FPU state inheritance for kernel threads and IO
* worker threads.
*/
if (dst->flags & (PF_KTHREAD | PF_IO_WORKER)) {
/* Clear out the minimal state */
memcpy(&dst_fpu->fpstate->regs, &init_fpstate.regs,
init_fpstate_copy_size());
return 0;
}
/*
* If a new feature is added, ensure all dynamic features are
* caller-saved from here!
*/
BUILD_BUG_ON(XFEATURE_MASK_USER_DYNAMIC != XFEATURE_MASK_XTILE_DATA);
/*
* Save the default portion of the current FPU state into the
* clone. Assume all dynamic features to be defined as caller-
* saved, which enables skipping both the expansion of fpstate
* and the copying of any dynamic state.
*
* Do not use memcpy() when TIF_NEED_FPU_LOAD is set because
* copying is not valid when current uses non-default states.
*/
fpregs_lock();
if (test_thread_flag(TIF_NEED_FPU_LOAD))
fpregs_restore_userregs();
save_fpregs_to_fpstate(dst_fpu);
if (!(clone_flags & CLONE_THREAD))
fpu_inherit_perms(dst_fpu);
fpregs_unlock();
trace_x86_fpu_copy_src(src_fpu);
trace_x86_fpu_copy_dst(dst_fpu);
return 0;
}
/*
* Whitelist the FPU register state embedded into task_struct for hardened
* usercopy.
*/
void fpu_thread_struct_whitelist(unsigned long *offset, unsigned long *size)
{
*offset = offsetof(struct thread_struct, fpu.__fpstate.regs);
*size = fpu_kernel_cfg.default_size;
}
/*
* Drops current FPU state: deactivates the fpregs and
* the fpstate. NOTE: it still leaves previous contents
* in the fpregs in the eager-FPU case.
*
* This function can be used in cases where we know that
* a state-restore is coming: either an explicit one,
* or a reschedule.
*/
void fpu__drop(struct fpu *fpu)
{
preempt_disable();
if (fpu == ¤t->thread.fpu) {
/* Ignore delayed exceptions from user space */
asm volatile("1: fwait\n"
"2:\n"
_ASM_EXTABLE(1b, 2b));
fpregs_deactivate(fpu);
}
trace_x86_fpu_dropped(fpu);
preempt_enable();
}
/*
* Clear FPU registers by setting them up from the init fpstate.
* Caller must do fpregs_[un]lock() around it.
*/
static inline void restore_fpregs_from_init_fpstate(u64 features_mask)
{
if (use_xsave())
os_xrstor(&init_fpstate, features_mask);
else if (use_fxsr())
fxrstor(&init_fpstate.regs.fxsave);
else
frstor(&init_fpstate.regs.fsave);
pkru_write_default();
}
/*
* Reset current->fpu memory state to the init values.
*/
static void fpu_reset_fpregs(void)
{
struct fpu *fpu = ¤t->thread.fpu;
fpregs_lock();
fpu__drop(fpu);
/*
* This does not change the actual hardware registers. It just
* resets the memory image and sets TIF_NEED_FPU_LOAD so a
* subsequent return to usermode will reload the registers from the
* task's memory image.
*
* Do not use fpstate_init() here. Just copy init_fpstate which has
* the correct content already except for PKRU.
*
* PKRU handling does not rely on the xstate when restoring for
* user space as PKRU is eagerly written in switch_to() and
* flush_thread().
*/
memcpy(&fpu->fpstate->regs, &init_fpstate.regs, init_fpstate_copy_size());
set_thread_flag(TIF_NEED_FPU_LOAD);
fpregs_unlock();
}
/*
* Reset current's user FPU states to the init states. current's
* supervisor states, if any, are not modified by this function. The
* caller guarantees that the XSTATE header in memory is intact.
*/
void fpu__clear_user_states(struct fpu *fpu)
{
WARN_ON_FPU(fpu != ¤t->thread.fpu);
fpregs_lock();
if (!cpu_feature_enabled(X86_FEATURE_FPU)) {
fpu_reset_fpregs();
fpregs_unlock();
return;
}
/*
* Ensure that current's supervisor states are loaded into their
* corresponding registers.
*/
if (xfeatures_mask_supervisor() &&
!fpregs_state_valid(fpu, smp_processor_id()))
os_xrstor_supervisor(fpu->fpstate);
/* Reset user states in registers. */
restore_fpregs_from_init_fpstate(XFEATURE_MASK_USER_RESTORE);
/*
* Now all FPU registers have their desired values. Inform the FPU
* state machine that current's FPU registers are in the hardware
* registers. The memory image does not need to be updated because
* any operation relying on it has to save the registers first when
* current's FPU is marked active.
*/
fpregs_mark_activate();
fpregs_unlock();
}
void fpu_flush_thread(void)
{
fpstate_reset(¤t->thread.fpu);
fpu_reset_fpregs();
}
/*
* Load FPU context before returning to userspace.
*/
void switch_fpu_return(void)
{
if (!static_cpu_has(X86_FEATURE_FPU))
return;
fpregs_restore_userregs();
}
EXPORT_SYMBOL_GPL(switch_fpu_return);
#ifdef CONFIG_X86_DEBUG_FPU
/*
* If current FPU state according to its tracking (loaded FPU context on this
* CPU) is not valid then we must have TIF_NEED_FPU_LOAD set so the context is
* loaded on return to userland.
*/
void fpregs_assert_state_consistent(void)
{
struct fpu *fpu = ¤t->thread.fpu;
if (test_thread_flag(TIF_NEED_FPU_LOAD))
return;
WARN_ON_FPU(!fpregs_state_valid(fpu, smp_processor_id()));
}
EXPORT_SYMBOL_GPL(fpregs_assert_state_consistent);
#endif
void fpregs_mark_activate(void)
{
struct fpu *fpu = ¤t->thread.fpu;
fpregs_activate(fpu);
fpu->last_cpu = smp_processor_id();
clear_thread_flag(TIF_NEED_FPU_LOAD);
}
/*
* x87 math exception handling:
*/
int fpu__exception_code(struct fpu *fpu, int trap_nr)
{
int err;
if (trap_nr == X86_TRAP_MF) {
unsigned short cwd, swd;
/*
* (~cwd & swd) will mask out exceptions that are not set to unmasked
* status. 0x3f is the exception bits in these regs, 0x200 is the
* C1 reg you need in case of a stack fault, 0x040 is the stack
* fault bit. We should only be taking one exception at a time,
* so if this combination doesn't produce any single exception,
* then we have a bad program that isn't synchronizing its FPU usage
* and it will suffer the consequences since we won't be able to
* fully reproduce the context of the exception.
*/
if (boot_cpu_has(X86_FEATURE_FXSR)) {
cwd = fpu->fpstate->regs.fxsave.cwd;
swd = fpu->fpstate->regs.fxsave.swd;
} else {
cwd = (unsigned short)fpu->fpstate->regs.fsave.cwd;
swd = (unsigned short)fpu->fpstate->regs.fsave.swd;
}
err = swd & ~cwd;
} else {
/*
* The SIMD FPU exceptions are handled a little differently, as there
* is only a single status/control register. Thus, to determine which
* unmasked exception was caught we must mask the exception mask bits
* at 0x1f80, and then use these to mask the exception bits at 0x3f.
*/
unsigned short mxcsr = MXCSR_DEFAULT;
if (boot_cpu_has(X86_FEATURE_XMM))
mxcsr = fpu->fpstate->regs.fxsave.mxcsr;
err = ~(mxcsr >> 7) & mxcsr;
}
if (err & 0x001) { /* Invalid op */
/*
* swd & 0x240 == 0x040: Stack Underflow
* swd & 0x240 == 0x240: Stack Overflow
* User must clear the SF bit (0x40) if set
*/
return FPE_FLTINV;
} else if (err & 0x004) { /* Divide by Zero */
return FPE_FLTDIV;
} else if (err & 0x008) { /* Overflow */
return FPE_FLTOVF;
} else if (err & 0x012) { /* Denormal, Underflow */
return FPE_FLTUND;
} else if (err & 0x020) { /* Precision */
return FPE_FLTRES;
}
/*
* If we're using IRQ 13, or supposedly even some trap
* X86_TRAP_MF implementations, it's possible
* we get a spurious trap, which is not an error.
*/
return 0;
}
|