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
|
/*
* Copyright (C) 1994 Linus Torvalds
*
* Pentium III FXSR, SSE support
* General FPU state handling cleanups
* Gareth Hughes <gareth@valinux.com>, May 2000
* x86-64 work by Andi Kleen 2002
*/
#ifndef _ASM_X86_FPU_INTERNAL_H
#define _ASM_X86_FPU_INTERNAL_H
#include <linux/compat.h>
#include <linux/sched.h>
#include <linux/slab.h>
#include <asm/user.h>
#include <asm/fpu/api.h>
#include <asm/fpu/xstate.h>
/*
* High level FPU state handling functions:
*/
extern void fpu__activate_curr(struct fpu *fpu);
extern void fpu__activate_fpstate(struct fpu *fpu);
extern void fpu__save(struct fpu *fpu);
extern void fpu__restore(struct fpu *fpu);
extern int fpu__restore_sig(void __user *buf, int ia32_frame);
extern void fpu__drop(struct fpu *fpu);
extern int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu);
extern void fpu__clear(struct fpu *fpu);
extern int fpu__exception_code(struct fpu *fpu, int trap_nr);
extern int dump_fpu(struct pt_regs *ptregs, struct user_i387_struct *fpstate);
/*
* Boot time FPU initialization functions:
*/
extern void fpu__init_cpu(void);
extern void fpu__init_system_xstate(void);
extern void fpu__init_cpu_xstate(void);
extern void fpu__init_system(struct cpuinfo_x86 *c);
extern void fpu__init_check_bugs(void);
extern void fpu__resume_cpu(void);
/*
* Debugging facility:
*/
#ifdef CONFIG_X86_DEBUG_FPU
# define WARN_ON_FPU(x) WARN_ON_ONCE(x)
#else
# define WARN_ON_FPU(x) ({ 0; })
#endif
/*
* FPU related CPU feature flag helper routines:
*/
static __always_inline __pure bool use_eager_fpu(void)
{
return static_cpu_has_safe(X86_FEATURE_EAGER_FPU);
}
static __always_inline __pure bool use_xsaveopt(void)
{
return static_cpu_has_safe(X86_FEATURE_XSAVEOPT);
}
static __always_inline __pure bool use_xsave(void)
{
return static_cpu_has_safe(X86_FEATURE_XSAVE);
}
static __always_inline __pure bool use_fxsr(void)
{
return static_cpu_has_safe(X86_FEATURE_FXSR);
}
/*
* fpstate handling functions:
*/
extern union fpregs_state init_fpstate;
extern void fpstate_init(union fpregs_state *state);
#ifdef CONFIG_MATH_EMULATION
extern void fpstate_init_soft(struct swregs_state *soft);
#else
static inline void fpstate_init_soft(struct swregs_state *soft) {}
#endif
static inline void fpstate_init_fxstate(struct fxregs_state *fx)
{
fx->cwd = 0x37f;
fx->mxcsr = MXCSR_DEFAULT;
}
extern void fpstate_sanitize_xstate(struct fpu *fpu);
#define user_insn(insn, output, input...) \
({ \
int err; \
asm volatile(ASM_STAC "\n" \
"1:" #insn "\n\t" \
"2: " ASM_CLAC "\n" \
".section .fixup,\"ax\"\n" \
"3: movl $-1,%[err]\n" \
" jmp 2b\n" \
".previous\n" \
_ASM_EXTABLE(1b, 3b) \
: [err] "=r" (err), output \
: "0"(0), input); \
err; \
})
#define check_insn(insn, output, input...) \
({ \
int err; \
asm volatile("1:" #insn "\n\t" \
"2:\n" \
".section .fixup,\"ax\"\n" \
"3: movl $-1,%[err]\n" \
" jmp 2b\n" \
".previous\n" \
_ASM_EXTABLE(1b, 3b) \
: [err] "=r" (err), output \
: "0"(0), input); \
err; \
})
static inline int copy_fregs_to_user(struct fregs_state __user *fx)
{
return user_insn(fnsave %[fx]; fwait, [fx] "=m" (*fx), "m" (*fx));
}
static inline int copy_fxregs_to_user(struct fxregs_state __user *fx)
{
if (config_enabled(CONFIG_X86_32))
return user_insn(fxsave %[fx], [fx] "=m" (*fx), "m" (*fx));
else if (config_enabled(CONFIG_AS_FXSAVEQ))
return user_insn(fxsaveq %[fx], [fx] "=m" (*fx), "m" (*fx));
/* See comment in copy_fxregs_to_kernel() below. */
return user_insn(rex64/fxsave (%[fx]), "=m" (*fx), [fx] "R" (fx));
}
static inline int copy_kernel_to_fxregs(struct fxregs_state *fx)
{
if (config_enabled(CONFIG_X86_32))
return check_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx));
else if (config_enabled(CONFIG_AS_FXSAVEQ))
return check_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx));
/* See comment in copy_fxregs_to_kernel() below. */
return check_insn(rex64/fxrstor (%[fx]), "=m" (*fx), [fx] "R" (fx),
"m" (*fx));
}
static inline int copy_user_to_fxregs(struct fxregs_state __user *fx)
{
if (config_enabled(CONFIG_X86_32))
return user_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx));
else if (config_enabled(CONFIG_AS_FXSAVEQ))
return user_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx));
/* See comment in copy_fxregs_to_kernel() below. */
return user_insn(rex64/fxrstor (%[fx]), "=m" (*fx), [fx] "R" (fx),
"m" (*fx));
}
static inline int copy_kernel_to_fregs(struct fregs_state *fx)
{
return check_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx));
}
static inline int copy_user_to_fregs(struct fregs_state __user *fx)
{
return user_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx));
}
static inline void copy_fxregs_to_kernel(struct fpu *fpu)
{
if (config_enabled(CONFIG_X86_32))
asm volatile( "fxsave %[fx]" : [fx] "=m" (fpu->state.fxsave));
else if (config_enabled(CONFIG_AS_FXSAVEQ))
asm volatile("fxsaveq %[fx]" : [fx] "=m" (fpu->state.fxsave));
else {
/* Using "rex64; fxsave %0" is broken because, if the memory
* operand uses any extended registers for addressing, a second
* REX prefix will be generated (to the assembler, rex64
* followed by semicolon is a separate instruction), and hence
* the 64-bitness is lost.
*
* Using "fxsaveq %0" would be the ideal choice, but is only
* supported starting with gas 2.16.
*
* Using, as a workaround, the properly prefixed form below
* isn't accepted by any binutils version so far released,
* complaining that the same type of prefix is used twice if
* an extended register is needed for addressing (fix submitted
* to mainline 2005-11-21).
*
* asm volatile("rex64/fxsave %0" : "=m" (fpu->state.fxsave));
*
* This, however, we can work around by forcing the compiler to
* select an addressing mode that doesn't require extended
* registers.
*/
asm volatile( "rex64/fxsave (%[fx])"
: "=m" (fpu->state.fxsave)
: [fx] "R" (&fpu->state.fxsave));
}
}
/* These macros all use (%edi)/(%rdi) as the single memory argument. */
#define XSAVE ".byte " REX_PREFIX "0x0f,0xae,0x27"
#define XSAVEOPT ".byte " REX_PREFIX "0x0f,0xae,0x37"
#define XSAVES ".byte " REX_PREFIX "0x0f,0xc7,0x2f"
#define XRSTOR ".byte " REX_PREFIX "0x0f,0xae,0x2f"
#define XRSTORS ".byte " REX_PREFIX "0x0f,0xc7,0x1f"
/* xstate instruction fault handler: */
#define xstate_fault(__err) \
\
".section .fixup,\"ax\"\n" \
\
"3: movl $-2,%[_err]\n" \
" jmp 2b\n" \
\
".previous\n" \
\
_ASM_EXTABLE(1b, 3b) \
: [_err] "=r" (__err)
/*
* This function is called only during boot time when x86 caps are not set
* up and alternative can not be used yet.
*/
static inline void copy_xregs_to_kernel_booting(struct xregs_state *xstate)
{
u64 mask = -1;
u32 lmask = mask;
u32 hmask = mask >> 32;
int err = 0;
WARN_ON(system_state != SYSTEM_BOOTING);
if (boot_cpu_has(X86_FEATURE_XSAVES))
asm volatile("1:"XSAVES"\n\t"
"2:\n\t"
xstate_fault(err)
: "D" (xstate), "m" (*xstate), "a" (lmask), "d" (hmask), "0" (err)
: "memory");
else
asm volatile("1:"XSAVE"\n\t"
"2:\n\t"
xstate_fault(err)
: "D" (xstate), "m" (*xstate), "a" (lmask), "d" (hmask), "0" (err)
: "memory");
/* We should never fault when copying to a kernel buffer: */
WARN_ON_FPU(err);
}
/*
* This function is called only during boot time when x86 caps are not set
* up and alternative can not be used yet.
*/
static inline void copy_kernel_to_xregs_booting(struct xregs_state *xstate, u64 mask)
{
u32 lmask = mask;
u32 hmask = mask >> 32;
int err = 0;
WARN_ON(system_state != SYSTEM_BOOTING);
if (boot_cpu_has(X86_FEATURE_XSAVES))
asm volatile("1:"XRSTORS"\n\t"
"2:\n\t"
xstate_fault(err)
: "D" (xstate), "m" (*xstate), "a" (lmask), "d" (hmask), "0" (err)
: "memory");
else
asm volatile("1:"XRSTOR"\n\t"
"2:\n\t"
xstate_fault(err)
: "D" (xstate), "m" (*xstate), "a" (lmask), "d" (hmask), "0" (err)
: "memory");
/* We should never fault when copying from a kernel buffer: */
WARN_ON_FPU(err);
}
/*
* Save processor xstate to xsave area.
*/
static inline void copy_xregs_to_kernel(struct xregs_state *xstate)
{
u64 mask = -1;
u32 lmask = mask;
u32 hmask = mask >> 32;
int err = 0;
WARN_ON(!alternatives_patched);
/*
* If xsaves is enabled, xsaves replaces xsaveopt because
* it supports compact format and supervisor states in addition to
* modified optimization in xsaveopt.
*
* Otherwise, if xsaveopt is enabled, xsaveopt replaces xsave
* because xsaveopt supports modified optimization which is not
* supported by xsave.
*
* If none of xsaves and xsaveopt is enabled, use xsave.
*/
alternative_input_2(
"1:"XSAVE,
XSAVEOPT,
X86_FEATURE_XSAVEOPT,
XSAVES,
X86_FEATURE_XSAVES,
[xstate] "D" (xstate), "a" (lmask), "d" (hmask) :
"memory");
asm volatile("2:\n\t"
xstate_fault(err)
: "0" (err)
: "memory");
/* We should never fault when copying to a kernel buffer: */
WARN_ON_FPU(err);
}
/*
* Restore processor xstate from xsave area.
*/
static inline void copy_kernel_to_xregs(struct xregs_state *xstate, u64 mask)
{
u32 lmask = mask;
u32 hmask = mask >> 32;
int err = 0;
/*
* Use xrstors to restore context if it is enabled. xrstors supports
* compacted format of xsave area which is not supported by xrstor.
*/
alternative_input(
"1: " XRSTOR,
XRSTORS,
X86_FEATURE_XSAVES,
"D" (xstate), "m" (*xstate), "a" (lmask), "d" (hmask)
: "memory");
asm volatile("2:\n"
xstate_fault(err)
: "0" (err)
: "memory");
/* We should never fault when copying from a kernel buffer: */
WARN_ON_FPU(err);
}
/*
* Save xstate to user space xsave area.
*
* We don't use modified optimization because xrstor/xrstors might track
* a different application.
*
* We don't use compacted format xsave area for
* backward compatibility for old applications which don't understand
* compacted format of xsave area.
*/
static inline int copy_xregs_to_user(struct xregs_state __user *buf)
{
int err;
/*
* Clear the xsave header first, so that reserved fields are
* initialized to zero.
*/
err = __clear_user(&buf->header, sizeof(buf->header));
if (unlikely(err))
return -EFAULT;
__asm__ __volatile__(ASM_STAC "\n"
"1:"XSAVE"\n"
"2: " ASM_CLAC "\n"
xstate_fault(err)
: "D" (buf), "a" (-1), "d" (-1), "0" (err)
: "memory");
return err;
}
/*
* Restore xstate from user space xsave area.
*/
static inline int copy_user_to_xregs(struct xregs_state __user *buf, u64 mask)
{
struct xregs_state *xstate = ((__force struct xregs_state *)buf);
u32 lmask = mask;
u32 hmask = mask >> 32;
int err = 0;
__asm__ __volatile__(ASM_STAC "\n"
"1:"XRSTOR"\n"
"2: " ASM_CLAC "\n"
xstate_fault(err)
: "D" (xstate), "a" (lmask), "d" (hmask), "0" (err)
: "memory"); /* memory required? */
return err;
}
/*
* These must be called with preempt disabled. Returns
* 'true' if the FPU state is still intact and we can
* keep registers active.
*
* The legacy FNSAVE instruction cleared all FPU state
* unconditionally, so registers are essentially destroyed.
* Modern FPU state can be kept in registers, if there are
* no pending FP exceptions.
*/
static inline int copy_fpregs_to_fpstate(struct fpu *fpu)
{
if (likely(use_xsave())) {
copy_xregs_to_kernel(&fpu->state.xsave);
return 1;
}
if (likely(use_fxsr())) {
copy_fxregs_to_kernel(fpu);
return 1;
}
/*
* Legacy FPU register saving, FNSAVE always clears FPU registers,
* so we have to mark them inactive:
*/
asm volatile("fnsave %[fp]; fwait" : [fp] "=m" (fpu->state.fsave));
return 0;
}
static inline int __copy_fpstate_to_fpregs(struct fpu *fpu)
{
if (use_xsave()) {
copy_kernel_to_xregs(&fpu->state.xsave, -1);
return 0;
} else {
if (use_fxsr())
return copy_kernel_to_fxregs(&fpu->state.fxsave);
else
return copy_kernel_to_fregs(&fpu->state.fsave);
}
}
static inline int copy_fpstate_to_fpregs(struct fpu *fpu)
{
/*
* AMD K7/K8 CPUs 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_safe(X86_BUG_FXSAVE_LEAK))) {
asm volatile(
"fnclex\n\t"
"emms\n\t"
"fildl %P[addr]" /* set F?P to defined value */
: : [addr] "m" (fpu->fpregs_active));
}
return __copy_fpstate_to_fpregs(fpu);
}
extern int copy_fpstate_to_sigframe(void __user *buf, void __user *fp, int size);
/*
* FPU context switch related helper methods:
*/
DECLARE_PER_CPU(struct fpu *, fpu_fpregs_owner_ctx);
/*
* Must be run with preemption disabled: this clears the fpu_fpregs_owner_ctx,
* on this CPU.
*
* This will disable any lazy FPU state restore of the current FPU state,
* but if the current thread owns the FPU, it will still be saved by.
*/
static inline void __cpu_disable_lazy_restore(unsigned int cpu)
{
per_cpu(fpu_fpregs_owner_ctx, cpu) = NULL;
}
static inline int fpu_want_lazy_restore(struct fpu *fpu, unsigned int cpu)
{
return fpu == this_cpu_read_stable(fpu_fpregs_owner_ctx) && cpu == fpu->last_cpu;
}
/*
* Wrap lazy FPU TS handling in a 'hw fpregs activation/deactivation'
* idiom, which is then paired with the sw-flag (fpregs_active) later on:
*/
static inline void __fpregs_activate_hw(void)
{
if (!use_eager_fpu())
clts();
}
static inline void __fpregs_deactivate_hw(void)
{
if (!use_eager_fpu())
stts();
}
/* Must be paired with an 'stts' (fpregs_deactivate_hw()) after! */
static inline void __fpregs_deactivate(struct fpu *fpu)
{
WARN_ON_FPU(!fpu->fpregs_active);
fpu->fpregs_active = 0;
this_cpu_write(fpu_fpregs_owner_ctx, NULL);
}
/* Must be paired with a 'clts' (fpregs_activate_hw()) before! */
static inline void __fpregs_activate(struct fpu *fpu)
{
WARN_ON_FPU(fpu->fpregs_active);
fpu->fpregs_active = 1;
this_cpu_write(fpu_fpregs_owner_ctx, fpu);
}
/*
* The question "does this thread have fpu access?"
* is slightly racy, since preemption could come in
* and revoke it immediately after the test.
*
* However, even in that very unlikely scenario,
* we can just assume we have FPU access - typically
* to save the FP state - we'll just take a #NM
* fault and get the FPU access back.
*/
static inline int fpregs_active(void)
{
return current->thread.fpu.fpregs_active;
}
/*
* Encapsulate the CR0.TS handling together with the
* software flag.
*
* These generally need preemption protection to work,
* do try to avoid using these on their own.
*/
static inline void fpregs_activate(struct fpu *fpu)
{
__fpregs_activate_hw();
__fpregs_activate(fpu);
}
static inline void fpregs_deactivate(struct fpu *fpu)
{
__fpregs_deactivate(fpu);
__fpregs_deactivate_hw();
}
/*
* FPU state switching for scheduling.
*
* This is a two-stage process:
*
* - switch_fpu_prepare() saves the old state and
* sets the new state of the CR0.TS bit. This is
* done within the context of the old process.
*
* - switch_fpu_finish() restores the new state as
* necessary.
*/
typedef struct { int preload; } fpu_switch_t;
static inline fpu_switch_t
switch_fpu_prepare(struct fpu *old_fpu, struct fpu *new_fpu, int cpu)
{
fpu_switch_t fpu;
/*
* If the task has used the math, pre-load the FPU on xsave processors
* or if the past 5 consecutive context-switches used math.
*/
fpu.preload = new_fpu->fpstate_active &&
(use_eager_fpu() || new_fpu->counter > 5);
if (old_fpu->fpregs_active) {
if (!copy_fpregs_to_fpstate(old_fpu))
old_fpu->last_cpu = -1;
else
old_fpu->last_cpu = cpu;
/* But leave fpu_fpregs_owner_ctx! */
old_fpu->fpregs_active = 0;
/* Don't change CR0.TS if we just switch! */
if (fpu.preload) {
new_fpu->counter++;
__fpregs_activate(new_fpu);
prefetch(&new_fpu->state);
} else {
__fpregs_deactivate_hw();
}
} else {
old_fpu->counter = 0;
old_fpu->last_cpu = -1;
if (fpu.preload) {
new_fpu->counter++;
if (fpu_want_lazy_restore(new_fpu, cpu))
fpu.preload = 0;
else
prefetch(&new_fpu->state);
fpregs_activate(new_fpu);
}
}
return fpu;
}
/*
* Misc helper functions:
*/
/*
* By the time this gets called, we've already cleared CR0.TS and
* given the process the FPU if we are going to preload the FPU
* state - all we need to do is to conditionally restore the register
* state itself.
*/
static inline void switch_fpu_finish(struct fpu *new_fpu, fpu_switch_t fpu_switch)
{
if (fpu_switch.preload) {
if (unlikely(copy_fpstate_to_fpregs(new_fpu))) {
WARN_ON_FPU(1);
fpu__clear(new_fpu);
}
}
}
/*
* Needs to be preemption-safe.
*
* NOTE! user_fpu_begin() must be used only immediately before restoring
* the save state. It does not do any saving/restoring on its own. In
* lazy FPU mode, it is just an optimization to avoid a #NM exception,
* the task can lose the FPU right after preempt_enable().
*/
static inline void user_fpu_begin(void)
{
struct fpu *fpu = ¤t->thread.fpu;
preempt_disable();
if (!fpregs_active())
fpregs_activate(fpu);
preempt_enable();
}
/*
* MXCSR and XCR definitions:
*/
extern unsigned int mxcsr_feature_mask;
#define XCR_XFEATURE_ENABLED_MASK 0x00000000
static inline u64 xgetbv(u32 index)
{
u32 eax, edx;
asm volatile(".byte 0x0f,0x01,0xd0" /* xgetbv */
: "=a" (eax), "=d" (edx)
: "c" (index));
return eax + ((u64)edx << 32);
}
static inline void xsetbv(u32 index, u64 value)
{
u32 eax = value;
u32 edx = value >> 32;
asm volatile(".byte 0x0f,0x01,0xd1" /* xsetbv */
: : "a" (eax), "d" (edx), "c" (index));
}
#endif /* _ASM_X86_FPU_INTERNAL_H */
|