Gitiles
Code Review Sign In
192.168.1.100 / T800 / feb6f202200107c1997957b0cdcd1f83784dba9d / . / src / kernel / linux / v4.19 / arch / sparc / lib / memcpy.S
blob: ee823d8c92157d0842e586839f1a61a9802a008b [file] [log] [blame]
xjb04a4022021-11-25 15:01:52 +0800[diff] [blame]1/* SPDX-License-Identifier: GPL-2.0 */
2/* memcpy.S: Sparc optimized memcpy and memmove code
3 * Hand optimized from GNU libc's memcpy and memmove
4 * Copyright (C) 1991,1996 Free Software Foundation
5 * Copyright (C) 1995 Linus Torvalds (Linus.Torvalds@helsinki.fi)
6 * Copyright (C) 1996 David S. Miller (davem@caip.rutgers.edu)
7 * Copyright (C) 1996 Eddie C. Dost (ecd@skynet.be)
8 * Copyright (C) 1996 Jakub Jelinek (jj@sunsite.mff.cuni.cz)
9 */
10
11#include <asm/export.h>
12#define FUNC(x) \
13 .globl x; \
14 .type x,@function; \
15 .align 4; \
16x:
17
18/* Both these macros have to start with exactly the same insn */
19#define MOVE_BIGCHUNK(src, dst, offset, t0, t1, t2, t3, t4, t5, t6, t7) \
20 ldd [%src + (offset) + 0x00], %t0; \
21 ldd [%src + (offset) + 0x08], %t2; \
22 ldd [%src + (offset) + 0x10], %t4; \
23 ldd [%src + (offset) + 0x18], %t6; \
24 st %t0, [%dst + (offset) + 0x00]; \
25 st %t1, [%dst + (offset) + 0x04]; \
26 st %t2, [%dst + (offset) + 0x08]; \
27 st %t3, [%dst + (offset) + 0x0c]; \
28 st %t4, [%dst + (offset) + 0x10]; \
29 st %t5, [%dst + (offset) + 0x14]; \
30 st %t6, [%dst + (offset) + 0x18]; \
31 st %t7, [%dst + (offset) + 0x1c];
32
33#define MOVE_BIGALIGNCHUNK(src, dst, offset, t0, t1, t2, t3, t4, t5, t6, t7) \
34 ldd [%src + (offset) + 0x00], %t0; \
35 ldd [%src + (offset) + 0x08], %t2; \
36 ldd [%src + (offset) + 0x10], %t4; \
37 ldd [%src + (offset) + 0x18], %t6; \
38 std %t0, [%dst + (offset) + 0x00]; \
39 std %t2, [%dst + (offset) + 0x08]; \
40 std %t4, [%dst + (offset) + 0x10]; \
41 std %t6, [%dst + (offset) + 0x18];
42
43#define MOVE_LASTCHUNK(src, dst, offset, t0, t1, t2, t3) \
44 ldd [%src - (offset) - 0x10], %t0; \
45 ldd [%src - (offset) - 0x08], %t2; \
46 st %t0, [%dst - (offset) - 0x10]; \
47 st %t1, [%dst - (offset) - 0x0c]; \
48 st %t2, [%dst - (offset) - 0x08]; \
49 st %t3, [%dst - (offset) - 0x04];
50
51#define MOVE_LASTALIGNCHUNK(src, dst, offset, t0, t1, t2, t3) \
52 ldd [%src - (offset) - 0x10], %t0; \
53 ldd [%src - (offset) - 0x08], %t2; \
54 std %t0, [%dst - (offset) - 0x10]; \
55 std %t2, [%dst - (offset) - 0x08];
56
57#define MOVE_SHORTCHUNK(src, dst, offset, t0, t1) \
58 ldub [%src - (offset) - 0x02], %t0; \
59 ldub [%src - (offset) - 0x01], %t1; \
60 stb %t0, [%dst - (offset) - 0x02]; \
61 stb %t1, [%dst - (offset) - 0x01];
62
63 .text
64 .align 4
65
66FUNC(memmove)
67EXPORT_SYMBOL(memmove)
68 cmp %o0, %o1
69 mov %o0, %g7
70 bleu 9f
71 sub %o0, %o1, %o4
72
73 add %o1, %o2, %o3
74 cmp %o3, %o0
75 bleu 0f
76 andcc %o4, 3, %o5
77
78 add %o1, %o2, %o1
79 add %o0, %o2, %o0
80 sub %o1, 1, %o1
81 sub %o0, 1, %o0
82
831: /* reverse_bytes */
84
85 ldub [%o1], %o4
86 subcc %o2, 1, %o2
87 stb %o4, [%o0]
88 sub %o1, 1, %o1
89 bne 1b
90 sub %o0, 1, %o0
91
92 retl
93 mov %g7, %o0
94
95/* NOTE: This code is executed just for the cases,
96 where %src (=%o1) & 3 is != 0.
97 We need to align it to 4. So, for (%src & 3)
98 1 we need to do ldub,lduh
99 2 lduh
100 3 just ldub
101 so even if it looks weird, the branches
102 are correct here. -jj
103 */
10478: /* dword_align */
105
106 andcc %o1, 1, %g0
107 be 4f
108 andcc %o1, 2, %g0
109
110 ldub [%o1], %g2
111 add %o1, 1, %o1
112 stb %g2, [%o0]
113 sub %o2, 1, %o2
114 bne 3f
115 add %o0, 1, %o0
1164:
117 lduh [%o1], %g2
118 add %o1, 2, %o1
119 sth %g2, [%o0]
120 sub %o2, 2, %o2
121 b 3f
122 add %o0, 2, %o0
123
124FUNC(memcpy) /* %o0=dst %o1=src %o2=len */
125EXPORT_SYMBOL(memcpy)
126
127 sub %o0, %o1, %o4
128 mov %o0, %g7
1299:
130 andcc %o4, 3, %o5
1310:
132 bne 86f
133 cmp %o2, 15
134
135 bleu 90f
136 andcc %o1, 3, %g0
137
138 bne 78b
1393:
140 andcc %o1, 4, %g0
141
142 be 2f
143 mov %o2, %g1
144
145 ld [%o1], %o4
146 sub %g1, 4, %g1
147 st %o4, [%o0]
148 add %o1, 4, %o1
149 add %o0, 4, %o0
1502:
151 andcc %g1, 0xffffff80, %g0
152 be 3f
153 andcc %o0, 4, %g0
154
155 be 82f + 4
1565:
157 MOVE_BIGCHUNK(o1, o0, 0x00, o2, o3, o4, o5, g2, g3, g4, g5)
158 MOVE_BIGCHUNK(o1, o0, 0x20, o2, o3, o4, o5, g2, g3, g4, g5)
159 MOVE_BIGCHUNK(o1, o0, 0x40, o2, o3, o4, o5, g2, g3, g4, g5)
160 MOVE_BIGCHUNK(o1, o0, 0x60, o2, o3, o4, o5, g2, g3, g4, g5)
161 sub %g1, 128, %g1
162 add %o1, 128, %o1
163 cmp %g1, 128
164 bge 5b
165 add %o0, 128, %o0
1663:
167 andcc %g1, 0x70, %g4
168 be 80f
169 andcc %g1, 8, %g0
170
171 sethi %hi(80f), %o5
172 srl %g4, 1, %o4
173 add %g4, %o4, %o4
174 add %o1, %g4, %o1
175 sub %o5, %o4, %o5
176 jmpl %o5 + %lo(80f), %g0
177 add %o0, %g4, %o0
178
17979: /* memcpy_table */
180
181 MOVE_LASTCHUNK(o1, o0, 0x60, g2, g3, g4, g5)
182 MOVE_LASTCHUNK(o1, o0, 0x50, g2, g3, g4, g5)
183 MOVE_LASTCHUNK(o1, o0, 0x40, g2, g3, g4, g5)
184 MOVE_LASTCHUNK(o1, o0, 0x30, g2, g3, g4, g5)
185 MOVE_LASTCHUNK(o1, o0, 0x20, g2, g3, g4, g5)
186 MOVE_LASTCHUNK(o1, o0, 0x10, g2, g3, g4, g5)
187 MOVE_LASTCHUNK(o1, o0, 0x00, g2, g3, g4, g5)
188
18980: /* memcpy_table_end */
190 be 81f
191 andcc %g1, 4, %g0
192
193 ldd [%o1], %g2
194 add %o0, 8, %o0
195 st %g2, [%o0 - 0x08]
196 add %o1, 8, %o1
197 st %g3, [%o0 - 0x04]
198
19981: /* memcpy_last7 */
200
201 be 1f
202 andcc %g1, 2, %g0
203
204 ld [%o1], %g2
205 add %o1, 4, %o1
206 st %g2, [%o0]
207 add %o0, 4, %o0
2081:
209 be 1f
210 andcc %g1, 1, %g0
211
212 lduh [%o1], %g2
213 add %o1, 2, %o1
214 sth %g2, [%o0]
215 add %o0, 2, %o0
2161:
217 be 1f
218 nop
219
220 ldub [%o1], %g2
221 stb %g2, [%o0]
2221:
223 retl
224 mov %g7, %o0
225
22682: /* ldd_std */
227 MOVE_BIGALIGNCHUNK(o1, o0, 0x00, o2, o3, o4, o5, g2, g3, g4, g5)
228 MOVE_BIGALIGNCHUNK(o1, o0, 0x20, o2, o3, o4, o5, g2, g3, g4, g5)
229 MOVE_BIGALIGNCHUNK(o1, o0, 0x40, o2, o3, o4, o5, g2, g3, g4, g5)
230 MOVE_BIGALIGNCHUNK(o1, o0, 0x60, o2, o3, o4, o5, g2, g3, g4, g5)
231 subcc %g1, 128, %g1
232 add %o1, 128, %o1
233 cmp %g1, 128
234 bge 82b
235 add %o0, 128, %o0
236
237 andcc %g1, 0x70, %g4
238 be 84f
239 andcc %g1, 8, %g0
240
241 sethi %hi(84f), %o5
242 add %o1, %g4, %o1
243 sub %o5, %g4, %o5
244 jmpl %o5 + %lo(84f), %g0
245 add %o0, %g4, %o0
246
24783: /* amemcpy_table */
248
249 MOVE_LASTALIGNCHUNK(o1, o0, 0x60, g2, g3, g4, g5)
250 MOVE_LASTALIGNCHUNK(o1, o0, 0x50, g2, g3, g4, g5)
251 MOVE_LASTALIGNCHUNK(o1, o0, 0x40, g2, g3, g4, g5)
252 MOVE_LASTALIGNCHUNK(o1, o0, 0x30, g2, g3, g4, g5)
253 MOVE_LASTALIGNCHUNK(o1, o0, 0x20, g2, g3, g4, g5)
254 MOVE_LASTALIGNCHUNK(o1, o0, 0x10, g2, g3, g4, g5)
255 MOVE_LASTALIGNCHUNK(o1, o0, 0x00, g2, g3, g4, g5)
256
25784: /* amemcpy_table_end */
258 be 85f
259 andcc %g1, 4, %g0
260
261 ldd [%o1], %g2
262 add %o0, 8, %o0
263 std %g2, [%o0 - 0x08]
264 add %o1, 8, %o1
26585: /* amemcpy_last7 */
266 be 1f
267 andcc %g1, 2, %g0
268
269 ld [%o1], %g2
270 add %o1, 4, %o1
271 st %g2, [%o0]
272 add %o0, 4, %o0
2731:
274 be 1f
275 andcc %g1, 1, %g0
276
277 lduh [%o1], %g2
278 add %o1, 2, %o1
279 sth %g2, [%o0]
280 add %o0, 2, %o0
2811:
282 be 1f
283 nop
284
285 ldub [%o1], %g2
286 stb %g2, [%o0]
2871:
288 retl
289 mov %g7, %o0
290
29186: /* non_aligned */
292 cmp %o2, 6
293 bleu 88f
294 nop
295
296 save %sp, -96, %sp
297 andcc %i0, 3, %g0
298 be 61f
299 andcc %i0, 1, %g0
300 be 60f
301 andcc %i0, 2, %g0
302
303 ldub [%i1], %g5
304 add %i1, 1, %i1
305 stb %g5, [%i0]
306 sub %i2, 1, %i2
307 bne 61f
308 add %i0, 1, %i0
30960:
310 ldub [%i1], %g3
311 add %i1, 2, %i1
312 stb %g3, [%i0]
313 sub %i2, 2, %i2
314 ldub [%i1 - 1], %g3
315 add %i0, 2, %i0
316 stb %g3, [%i0 - 1]
31761:
318 and %i1, 3, %g2
319 and %i2, 0xc, %g3
320 and %i1, -4, %i1
321 cmp %g3, 4
322 sll %g2, 3, %g4
323 mov 32, %g2
324 be 4f
325 sub %g2, %g4, %l0
326
327 blu 3f
328 cmp %g3, 0x8
329
330 be 2f
331 srl %i2, 2, %g3
332
333 ld [%i1], %i3
334 add %i0, -8, %i0
335 ld [%i1 + 4], %i4
336 b 8f
337 add %g3, 1, %g3
3382:
339 ld [%i1], %i4
340 add %i0, -12, %i0
341 ld [%i1 + 4], %i5
342 add %g3, 2, %g3
343 b 9f
344 add %i1, -4, %i1
3453:
346 ld [%i1], %g1
347 add %i0, -4, %i0
348 ld [%i1 + 4], %i3
349 srl %i2, 2, %g3
350 b 7f
351 add %i1, 4, %i1
3524:
353 ld [%i1], %i5
354 cmp %i2, 7
355 ld [%i1 + 4], %g1
356 srl %i2, 2, %g3
357 bleu 10f
358 add %i1, 8, %i1
359
360 ld [%i1], %i3
361 add %g3, -1, %g3
3625:
363 sll %i5, %g4, %g2
364 srl %g1, %l0, %g5
365 or %g2, %g5, %g2
366 st %g2, [%i0]
3677:
368 ld [%i1 + 4], %i4
369 sll %g1, %g4, %g2
370 srl %i3, %l0, %g5
371 or %g2, %g5, %g2
372 st %g2, [%i0 + 4]
3738:
374 ld [%i1 + 8], %i5
375 sll %i3, %g4, %g2
376 srl %i4, %l0, %g5
377 or %g2, %g5, %g2
378 st %g2, [%i0 + 8]
3799:
380 ld [%i1 + 12], %g1
381 sll %i4, %g4, %g2
382 srl %i5, %l0, %g5
383 addcc %g3, -4, %g3
384 or %g2, %g5, %g2
385 add %i1, 16, %i1
386 st %g2, [%i0 + 12]
387 add %i0, 16, %i0
388 bne,a 5b
389 ld [%i1], %i3
39010:
391 sll %i5, %g4, %g2
392 srl %g1, %l0, %g5
393 srl %l0, 3, %g3
394 or %g2, %g5, %g2
395 sub %i1, %g3, %i1
396 andcc %i2, 2, %g0
397 st %g2, [%i0]
398 be 1f
399 andcc %i2, 1, %g0
400
401 ldub [%i1], %g2
402 add %i1, 2, %i1
403 stb %g2, [%i0 + 4]
404 add %i0, 2, %i0
405 ldub [%i1 - 1], %g2
406 stb %g2, [%i0 + 3]
4071:
408 be 1f
409 nop
410 ldub [%i1], %g2
411 stb %g2, [%i0 + 4]
4121:
413 ret
414 restore %g7, %g0, %o0
415
41688: /* short_end */
417
418 and %o2, 0xe, %o3
41920:
420 sethi %hi(89f), %o5
421 sll %o3, 3, %o4
422 add %o0, %o3, %o0
423 sub %o5, %o4, %o5
424 add %o1, %o3, %o1
425 jmpl %o5 + %lo(89f), %g0
426 andcc %o2, 1, %g0
427
428 MOVE_SHORTCHUNK(o1, o0, 0x0c, g2, g3)
429 MOVE_SHORTCHUNK(o1, o0, 0x0a, g2, g3)
430 MOVE_SHORTCHUNK(o1, o0, 0x08, g2, g3)
431 MOVE_SHORTCHUNK(o1, o0, 0x06, g2, g3)
432 MOVE_SHORTCHUNK(o1, o0, 0x04, g2, g3)
433 MOVE_SHORTCHUNK(o1, o0, 0x02, g2, g3)
434 MOVE_SHORTCHUNK(o1, o0, 0x00, g2, g3)
435
43689: /* short_table_end */
437
438 be 1f
439 nop
440
441 ldub [%o1], %g2
442 stb %g2, [%o0]
4431:
444 retl
445 mov %g7, %o0
446
44790: /* short_aligned_end */
448 bne 88b
449 andcc %o2, 8, %g0
450
451 be 1f
452 andcc %o2, 4, %g0
453
454 ld [%o1 + 0x00], %g2
455 ld [%o1 + 0x04], %g3
456 add %o1, 8, %o1
457 st %g2, [%o0 + 0x00]
458 st %g3, [%o0 + 0x04]
459 add %o0, 8, %o0
4601:
461 b 81b
462 mov %o2, %g1