summaryrefslogtreecommitdiffstats
path: root/arch/s390/include/asm/fpu-insn.h
blob: 028d285701705caf817b8d10c683b16b71b54d5a (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
/* SPDX-License-Identifier: GPL-2.0 */
/*
 * Support for Floating Point and Vector Instructions
 *
 */

#ifndef __ASM_S390_FPU_INSN_H
#define __ASM_S390_FPU_INSN_H

#include <asm/fpu-insn-asm.h>

#ifndef __ASSEMBLY__

#include <linux/instrumented.h>
#include <asm/asm-extable.h>

asm(".include \"asm/fpu-insn-asm.h\"\n");

/*
 * Various small helper functions, which can and should be used within
 * kernel fpu code sections. Each function represents only one floating
 * point or vector instruction (except for helper functions which require
 * exception handling).
 *
 * This allows to use floating point and vector instructions like C
 * functions, which has the advantage that all supporting code, like
 * e.g. loops, can be written in easy to read C code.
 *
 * Each of the helper functions provides support for code instrumentation,
 * like e.g. KASAN. Therefore instrumentation is also covered automatically
 * when using these functions.
 *
 * In order to ensure that code generated with the helper functions stays
 * within kernel fpu sections, which are guarded with kernel_fpu_begin()
 * and kernel_fpu_end() calls, each function has a mandatory "memory"
 * barrier.
 */

static __always_inline void fpu_ld(unsigned short fpr, freg_t *reg)
{
	instrument_read(reg, sizeof(*reg));
	asm volatile("ld	 %[fpr],%[reg]\n"
		     :
		     : [fpr] "I" (fpr), [reg] "Q" (reg->ui)
		     : "memory");
}

static __always_inline void fpu_lfpc(unsigned int *fpc)
{
	instrument_read(fpc, sizeof(*fpc));
	asm volatile("lfpc	%[fpc]"
		     :
		     : [fpc] "Q" (*fpc)
		     : "memory");
}

/**
 * fpu_lfpc_safe - Load floating point control register safely.
 * @fpc: new value for floating point control register
 *
 * Load floating point control register. This may lead to an exception,
 * since a saved value may have been modified by user space (ptrace,
 * signal return, kvm registers) to an invalid value. In such a case
 * set the floating point control register to zero.
 */
static inline void fpu_lfpc_safe(unsigned int *fpc)
{
	u32 tmp;

	instrument_read(fpc, sizeof(*fpc));
	asm volatile("\n"
		"0:	lfpc	%[fpc]\n"
		"1:	nopr	%%r7\n"
		".pushsection .fixup, \"ax\"\n"
		"2:	lghi	%[tmp],0\n"
		"	sfpc	%[tmp]\n"
		"	jg	1b\n"
		".popsection\n"
		EX_TABLE(1b, 2b)
		: [tmp] "=d" (tmp)
		: [fpc] "Q" (*fpc)
		: "memory");
}

static __always_inline void fpu_std(unsigned short fpr, freg_t *reg)
{
	instrument_write(reg, sizeof(*reg));
	asm volatile("std	 %[fpr],%[reg]\n"
		     : [reg] "=Q" (reg->ui)
		     : [fpr] "I" (fpr)
		     : "memory");
}

static __always_inline void fpu_sfpc(unsigned int fpc)
{
	asm volatile("sfpc	%[fpc]"
		     :
		     : [fpc] "d" (fpc)
		     : "memory");
}

static __always_inline void fpu_stfpc(unsigned int *fpc)
{
	instrument_write(fpc, sizeof(*fpc));
	asm volatile("stfpc	%[fpc]"
		     : [fpc] "=Q" (*fpc)
		     :
		     : "memory");
}

static __always_inline void fpu_vab(u8 v1, u8 v2, u8 v3)
{
	asm volatile("VAB	%[v1],%[v2],%[v3]"
		     :
		     : [v1] "I" (v1), [v2] "I" (v2), [v3] "I" (v3)
		     : "memory");
}

static __always_inline void fpu_vcksm(u8 v1, u8 v2, u8 v3)
{
	asm volatile("VCKSM	%[v1],%[v2],%[v3]"
		     :
		     : [v1] "I" (v1), [v2] "I" (v2), [v3] "I" (v3)
		     : "memory");
}

static __always_inline void fpu_vesravb(u8 v1, u8 v2, u8 v3)
{
	asm volatile("VESRAVB	%[v1],%[v2],%[v3]"
		     :
		     : [v1] "I" (v1), [v2] "I" (v2), [v3] "I" (v3)
		     : "memory");
}

#ifdef CONFIG_CC_IS_CLANG

static __always_inline void fpu_vl(u8 v1, const void *vxr)
{
	instrument_read(vxr, sizeof(__vector128));
	asm volatile("\n"
		"	la	1,%[vxr]\n"
		"	VL	%[v1],0,,1\n"
		:
		: [vxr] "R" (*(__vector128 *)vxr),
		  [v1] "I" (v1)
		: "memory", "1");
}

#else /* CONFIG_CC_IS_CLANG */

static __always_inline void fpu_vl(u8 v1, const void *vxr)
{
	instrument_read(vxr, sizeof(__vector128));
	asm volatile("VL	%[v1],%O[vxr],,%R[vxr]\n"
		     :
		     : [vxr] "Q" (*(__vector128 *)vxr),
		       [v1] "I" (v1)
		     : "memory");
}

#endif /* CONFIG_CC_IS_CLANG */

static __always_inline u64 fpu_vlgvf(u8 v, u16 index)
{
	u64 val;

	asm volatile("VLGVF	%[val],%[v],%[index]"
		     : [val] "=d" (val)
		     : [v] "I" (v), [index] "L" (index)
		     : "memory");
	return val;
}

#ifdef CONFIG_CC_IS_CLANG

static __always_inline void fpu_vll(u8 v1, u32 index, const void *vxr)
{
	unsigned int size;

	size = min(index + 1, sizeof(__vector128));
	instrument_read(vxr, size);
	asm volatile("\n"
		"	la	1,%[vxr]\n"
		"	VLL	%[v1],%[index],0,1\n"
		:
		: [vxr] "R" (*(u8 *)vxr),
		  [index] "d" (index),
		  [v1] "I" (v1)
		: "memory", "1");
}

#else /* CONFIG_CC_IS_CLANG */

static __always_inline void fpu_vll(u8 v1, u32 index, const void *vxr)
{
	unsigned int size;

	size = min(index + 1, sizeof(__vector128));
	instrument_read(vxr, size);
	asm volatile("VLL	%[v1],%[index],%O[vxr],%R[vxr]\n"
		     :
		     : [vxr] "Q" (*(u8 *)vxr),
		       [index] "d" (index),
		       [v1] "I" (v1)
		     : "memory");
}

#endif /* CONFIG_CC_IS_CLANG */

#ifdef CONFIG_CC_IS_CLANG

#define fpu_vlm(_v1, _v3, _vxrs)					\
({									\
	unsigned int size = ((_v3) - (_v1) + 1) * sizeof(__vector128);	\
	struct {							\
		__vector128 _v[(_v3) - (_v1) + 1];			\
	} *_v = (void *)(_vxrs);					\
									\
	instrument_read(_v, size);					\
	asm volatile("\n"						\
		"	la	1,%[vxrs]\n"				\
		"	VLM	%[v1],%[v3],0,1\n"			\
		:							\
		: [vxrs] "R" (*_v),					\
		  [v1] "I" (_v1), [v3] "I" (_v3)			\
		: "memory", "1");					\
	(_v3) - (_v1) + 1;						\
})

#else /* CONFIG_CC_IS_CLANG */

#define fpu_vlm(_v1, _v3, _vxrs)					\
({									\
	unsigned int size = ((_v3) - (_v1) + 1) * sizeof(__vector128);	\
	struct {							\
		__vector128 _v[(_v3) - (_v1) + 1];			\
	} *_v = (void *)(_vxrs);					\
									\
	instrument_read(_v, size);					\
	asm volatile("VLM	%[v1],%[v3],%O[vxrs],%R[vxrs]\n"	\
		     :							\
		     : [vxrs] "Q" (*_v),				\
		       [v1] "I" (_v1), [v3] "I" (_v3)			\
		     : "memory");					\
	(_v3) - (_v1) + 1;						\
})

#endif /* CONFIG_CC_IS_CLANG */

static __always_inline void fpu_vlr(u8 v1, u8 v2)
{
	asm volatile("VLR	%[v1],%[v2]"
		     :
		     : [v1] "I" (v1), [v2] "I" (v2)
		     : "memory");
}

static __always_inline void fpu_vlvgf(u8 v, u32 val, u16 index)
{
	asm volatile("VLVGF	%[v],%[val],%[index]"
		     :
		     : [v] "I" (v), [val] "d" (val), [index] "L" (index)
		     : "memory");
}

static __always_inline void fpu_vn(u8 v1, u8 v2, u8 v3)
{
	asm volatile("VN	%[v1],%[v2],%[v3]"
		     :
		     : [v1] "I" (v1), [v2] "I" (v2), [v3] "I" (v3)
		     : "memory");
}

static __always_inline void fpu_vrepib(u8 v1, s16 i2)
{
	asm volatile("VREPIB	%[v1],%[i2]"
		     :
		     : [v1] "I" (v1), [i2] "K" (i2)
		     : "memory");
}

#ifdef CONFIG_CC_IS_CLANG

static __always_inline void fpu_vst(u8 v1, const void *vxr)
{
	instrument_write(vxr, sizeof(__vector128));
	asm volatile("\n"
		"	la	1,%[vxr]\n"
		"	VST	%[v1],0,,1\n"
		: [vxr] "=R" (*(__vector128 *)vxr)
		: [v1] "I" (v1)
		: "memory", "1");
}

#else /* CONFIG_CC_IS_CLANG */

static __always_inline void fpu_vst(u8 v1, const void *vxr)
{
	instrument_write(vxr, sizeof(__vector128));
	asm volatile("VST	%[v1],%O[vxr],,%R[vxr]\n"
		     : [vxr] "=Q" (*(__vector128 *)vxr)
		     : [v1] "I" (v1)
		     : "memory");
}

#endif /* CONFIG_CC_IS_CLANG */

#ifdef CONFIG_CC_IS_CLANG

static __always_inline void fpu_vstl(u8 v1, u32 index, const void *vxr)
{
	unsigned int size;

	size = min(index + 1, sizeof(__vector128));
	instrument_write(vxr, size);
	asm volatile("\n"
		"	la	1,%[vxr]\n"
		"	VSTL	%[v1],%[index],0,1\n"
		: [vxr] "=R" (*(u8 *)vxr)
		: [index] "d" (index), [v1] "I" (v1)
		: "memory", "1");
}

#else /* CONFIG_CC_IS_CLANG */

static __always_inline void fpu_vstl(u8 v1, u32 index, const void *vxr)
{
	unsigned int size;

	size = min(index + 1, sizeof(__vector128));
	instrument_write(vxr, size);
	asm volatile("VSTL	%[v1],%[index],%O[vxr],%R[vxr]\n"
		     : [vxr] "=Q" (*(u8 *)vxr)
		     : [index] "d" (index), [v1] "I" (v1)
		     : "memory");
}

#endif /* CONFIG_CC_IS_CLANG */

#ifdef CONFIG_CC_IS_CLANG

#define fpu_vstm(_v1, _v3, _vxrs)					\
({									\
	unsigned int size = ((_v3) - (_v1) + 1) * sizeof(__vector128);	\
	struct {							\
		__vector128 _v[(_v3) - (_v1) + 1];			\
	} *_v = (void *)(_vxrs);					\
									\
	instrument_write(_v, size);					\
	asm volatile("\n"						\
		"	la	1,%[vxrs]\n"				\
		"	VSTM	%[v1],%[v3],0,1\n"			\
		: [vxrs] "=R" (*_v)					\
		: [v1] "I" (_v1), [v3] "I" (_v3)			\
		: "memory", "1");					\
	(_v3) - (_v1) + 1;						\
})

#else /* CONFIG_CC_IS_CLANG */

#define fpu_vstm(_v1, _v3, _vxrs)					\
({									\
	unsigned int size = ((_v3) - (_v1) + 1) * sizeof(__vector128);	\
	struct {							\
		__vector128 _v[(_v3) - (_v1) + 1];			\
	} *_v = (void *)(_vxrs);					\
									\
	instrument_write(_v, size);					\
	asm volatile("VSTM	%[v1],%[v3],%O[vxrs],%R[vxrs]\n"	\
		     : [vxrs] "=Q" (*_v)				\
		     : [v1] "I" (_v1), [v3] "I" (_v3)			\
		     : "memory");					\
	(_v3) - (_v1) + 1;						\
})

#endif /* CONFIG_CC_IS_CLANG */

static __always_inline void fpu_vx(u8 v1, u8 v2, u8 v3)
{
	asm volatile("VX	%[v1],%[v2],%[v3]"
		     :
		     : [v1] "I" (v1), [v2] "I" (v2), [v3] "I" (v3)
		     : "memory");
}

static __always_inline void fpu_vzero(u8 v)
{
	asm volatile("VZERO	%[v]"
		     :
		     : [v] "I" (v)
		     : "memory");
}

#endif /* __ASSEMBLY__ */
#endif	/* __ASM_S390_FPU_INSN_H */