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
|
/*
* MMX 3DNow! library helper functions
*
* To do:
* We can use MMX just for prefetch in IRQ's. This may be a win.
* (reported so on K6-III)
* We should use a better code neutral filler for the short jump
* leal ebx. [ebx] is apparently best for K6-2, but Cyrix ??
* We also want to clobber the filler register so we don't get any
* register forwarding stalls on the filler.
*
* Add *user handling. Checksums are not a win with MMX on any CPU
* tested so far for any MMX solution figured.
*
* 22/09/2000 - Arjan van de Ven
* Improved for non-egineering-sample Athlons
*
*/
#include <linux/hardirq.h>
#include <linux/string.h>
#include <linux/export.h>
#include <linux/sched.h>
#include <linux/types.h>
#include <asm/fpu/api.h>
#include <asm/asm.h>
void *_mmx_memcpy(void *to, const void *from, size_t len)
{
void *p;
int i;
if (unlikely(in_interrupt()))
return __memcpy(to, from, len);
p = to;
i = len >> 6; /* len/64 */
kernel_fpu_begin();
__asm__ __volatile__ (
"1: prefetch (%0)\n" /* This set is 28 bytes */
" prefetch 64(%0)\n"
" prefetch 128(%0)\n"
" prefetch 192(%0)\n"
" prefetch 256(%0)\n"
"2: \n"
".section .fixup, \"ax\"\n"
"3: movw $0x1AEB, 1b\n" /* jmp on 26 bytes */
" jmp 2b\n"
".previous\n"
_ASM_EXTABLE(1b, 3b)
: : "r" (from));
for ( ; i > 5; i--) {
__asm__ __volatile__ (
"1: prefetch 320(%0)\n"
"2: movq (%0), %%mm0\n"
" movq 8(%0), %%mm1\n"
" movq 16(%0), %%mm2\n"
" movq 24(%0), %%mm3\n"
" movq %%mm0, (%1)\n"
" movq %%mm1, 8(%1)\n"
" movq %%mm2, 16(%1)\n"
" movq %%mm3, 24(%1)\n"
" movq 32(%0), %%mm0\n"
" movq 40(%0), %%mm1\n"
" movq 48(%0), %%mm2\n"
" movq 56(%0), %%mm3\n"
" movq %%mm0, 32(%1)\n"
" movq %%mm1, 40(%1)\n"
" movq %%mm2, 48(%1)\n"
" movq %%mm3, 56(%1)\n"
".section .fixup, \"ax\"\n"
"3: movw $0x05EB, 1b\n" /* jmp on 5 bytes */
" jmp 2b\n"
".previous\n"
_ASM_EXTABLE(1b, 3b)
: : "r" (from), "r" (to) : "memory");
from += 64;
to += 64;
}
for ( ; i > 0; i--) {
__asm__ __volatile__ (
" movq (%0), %%mm0\n"
" movq 8(%0), %%mm1\n"
" movq 16(%0), %%mm2\n"
" movq 24(%0), %%mm3\n"
" movq %%mm0, (%1)\n"
" movq %%mm1, 8(%1)\n"
" movq %%mm2, 16(%1)\n"
" movq %%mm3, 24(%1)\n"
" movq 32(%0), %%mm0\n"
" movq 40(%0), %%mm1\n"
" movq 48(%0), %%mm2\n"
" movq 56(%0), %%mm3\n"
" movq %%mm0, 32(%1)\n"
" movq %%mm1, 40(%1)\n"
" movq %%mm2, 48(%1)\n"
" movq %%mm3, 56(%1)\n"
: : "r" (from), "r" (to) : "memory");
from += 64;
to += 64;
}
/*
* Now do the tail of the block:
*/
__memcpy(to, from, len & 63);
kernel_fpu_end();
return p;
}
EXPORT_SYMBOL(_mmx_memcpy);
#ifdef CONFIG_MK7
/*
* The K7 has streaming cache bypass load/store. The Cyrix III, K6 and
* other MMX using processors do not.
*/
static void fast_clear_page(void *page)
{
int i;
kernel_fpu_begin();
__asm__ __volatile__ (
" pxor %%mm0, %%mm0\n" : :
);
for (i = 0; i < 4096/64; i++) {
__asm__ __volatile__ (
" movntq %%mm0, (%0)\n"
" movntq %%mm0, 8(%0)\n"
" movntq %%mm0, 16(%0)\n"
" movntq %%mm0, 24(%0)\n"
" movntq %%mm0, 32(%0)\n"
" movntq %%mm0, 40(%0)\n"
" movntq %%mm0, 48(%0)\n"
" movntq %%mm0, 56(%0)\n"
: : "r" (page) : "memory");
page += 64;
}
/*
* Since movntq is weakly-ordered, a "sfence" is needed to become
* ordered again:
*/
__asm__ __volatile__("sfence\n"::);
kernel_fpu_end();
}
static void fast_copy_page(void *to, void *from)
{
int i;
kernel_fpu_begin();
/*
* maybe the prefetch stuff can go before the expensive fnsave...
* but that is for later. -AV
*/
__asm__ __volatile__(
"1: prefetch (%0)\n"
" prefetch 64(%0)\n"
" prefetch 128(%0)\n"
" prefetch 192(%0)\n"
" prefetch 256(%0)\n"
"2: \n"
".section .fixup, \"ax\"\n"
"3: movw $0x1AEB, 1b\n" /* jmp on 26 bytes */
" jmp 2b\n"
".previous\n"
_ASM_EXTABLE(1b, 3b) : : "r" (from));
for (i = 0; i < (4096-320)/64; i++) {
__asm__ __volatile__ (
"1: prefetch 320(%0)\n"
"2: movq (%0), %%mm0\n"
" movntq %%mm0, (%1)\n"
" movq 8(%0), %%mm1\n"
" movntq %%mm1, 8(%1)\n"
" movq 16(%0), %%mm2\n"
" movntq %%mm2, 16(%1)\n"
" movq 24(%0), %%mm3\n"
" movntq %%mm3, 24(%1)\n"
" movq 32(%0), %%mm4\n"
" movntq %%mm4, 32(%1)\n"
" movq 40(%0), %%mm5\n"
" movntq %%mm5, 40(%1)\n"
" movq 48(%0), %%mm6\n"
" movntq %%mm6, 48(%1)\n"
" movq 56(%0), %%mm7\n"
" movntq %%mm7, 56(%1)\n"
".section .fixup, \"ax\"\n"
"3: movw $0x05EB, 1b\n" /* jmp on 5 bytes */
" jmp 2b\n"
".previous\n"
_ASM_EXTABLE(1b, 3b) : : "r" (from), "r" (to) : "memory");
from += 64;
to += 64;
}
for (i = (4096-320)/64; i < 4096/64; i++) {
__asm__ __volatile__ (
"2: movq (%0), %%mm0\n"
" movntq %%mm0, (%1)\n"
" movq 8(%0), %%mm1\n"
" movntq %%mm1, 8(%1)\n"
" movq 16(%0), %%mm2\n"
" movntq %%mm2, 16(%1)\n"
" movq 24(%0), %%mm3\n"
" movntq %%mm3, 24(%1)\n"
" movq 32(%0), %%mm4\n"
" movntq %%mm4, 32(%1)\n"
" movq 40(%0), %%mm5\n"
" movntq %%mm5, 40(%1)\n"
" movq 48(%0), %%mm6\n"
" movntq %%mm6, 48(%1)\n"
" movq 56(%0), %%mm7\n"
" movntq %%mm7, 56(%1)\n"
: : "r" (from), "r" (to) : "memory");
from += 64;
to += 64;
}
/*
* Since movntq is weakly-ordered, a "sfence" is needed to become
* ordered again:
*/
__asm__ __volatile__("sfence \n"::);
kernel_fpu_end();
}
#else /* CONFIG_MK7 */
/*
* Generic MMX implementation without K7 specific streaming
*/
static void fast_clear_page(void *page)
{
int i;
kernel_fpu_begin();
__asm__ __volatile__ (
" pxor %%mm0, %%mm0\n" : :
);
for (i = 0; i < 4096/128; i++) {
__asm__ __volatile__ (
" movq %%mm0, (%0)\n"
" movq %%mm0, 8(%0)\n"
" movq %%mm0, 16(%0)\n"
" movq %%mm0, 24(%0)\n"
" movq %%mm0, 32(%0)\n"
" movq %%mm0, 40(%0)\n"
" movq %%mm0, 48(%0)\n"
" movq %%mm0, 56(%0)\n"
" movq %%mm0, 64(%0)\n"
" movq %%mm0, 72(%0)\n"
" movq %%mm0, 80(%0)\n"
" movq %%mm0, 88(%0)\n"
" movq %%mm0, 96(%0)\n"
" movq %%mm0, 104(%0)\n"
" movq %%mm0, 112(%0)\n"
" movq %%mm0, 120(%0)\n"
: : "r" (page) : "memory");
page += 128;
}
kernel_fpu_end();
}
static void fast_copy_page(void *to, void *from)
{
int i;
kernel_fpu_begin();
__asm__ __volatile__ (
"1: prefetch (%0)\n"
" prefetch 64(%0)\n"
" prefetch 128(%0)\n"
" prefetch 192(%0)\n"
" prefetch 256(%0)\n"
"2: \n"
".section .fixup, \"ax\"\n"
"3: movw $0x1AEB, 1b\n" /* jmp on 26 bytes */
" jmp 2b\n"
".previous\n"
_ASM_EXTABLE(1b, 3b) : : "r" (from));
for (i = 0; i < 4096/64; i++) {
__asm__ __volatile__ (
"1: prefetch 320(%0)\n"
"2: movq (%0), %%mm0\n"
" movq 8(%0), %%mm1\n"
" movq 16(%0), %%mm2\n"
" movq 24(%0), %%mm3\n"
" movq %%mm0, (%1)\n"
" movq %%mm1, 8(%1)\n"
" movq %%mm2, 16(%1)\n"
" movq %%mm3, 24(%1)\n"
" movq 32(%0), %%mm0\n"
" movq 40(%0), %%mm1\n"
" movq 48(%0), %%mm2\n"
" movq 56(%0), %%mm3\n"
" movq %%mm0, 32(%1)\n"
" movq %%mm1, 40(%1)\n"
" movq %%mm2, 48(%1)\n"
" movq %%mm3, 56(%1)\n"
".section .fixup, \"ax\"\n"
"3: movw $0x05EB, 1b\n" /* jmp on 5 bytes */
" jmp 2b\n"
".previous\n"
_ASM_EXTABLE(1b, 3b)
: : "r" (from), "r" (to) : "memory");
from += 64;
to += 64;
}
|