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
|
/* SPDX-License-Identifier: GPL-2.0 */
/*
* arch/alpha/lib/ev6-stxncpy.S
* 21264 version contributed by Rick Gorton <rick.gorton@api-networks.com>
*
* Copy no more than COUNT bytes of the null-terminated string from
* SRC to DST.
*
* This is an internal routine used by strncpy, stpncpy, and strncat.
* As such, it uses special linkage conventions to make implementation
* of these public functions more efficient.
*
* On input:
* t9 = return address
* a0 = DST
* a1 = SRC
* a2 = COUNT
*
* Furthermore, COUNT may not be zero.
*
* On output:
* t0 = last word written
* t10 = bitmask (with one bit set) indicating the byte position of
* the end of the range specified by COUNT
* t12 = bitmask (with one bit set) indicating the last byte written
* a0 = unaligned address of the last *word* written
* a2 = the number of full words left in COUNT
*
* Furthermore, v0, a3-a5, t11, and $at are untouched.
*
* Much of the information about 21264 scheduling/coding comes from:
* Compiler Writer's Guide for the Alpha 21264
* abbreviated as 'CWG' in other comments here
* ftp.digital.com/pub/Digital/info/semiconductor/literature/dsc-library.html
* Scheduling notation:
* E - either cluster
* U - upper subcluster; U0 - subcluster U0; U1 - subcluster U1
* L - lower subcluster; L0 - subcluster L0; L1 - subcluster L1
* Try not to change the actual algorithm if possible for consistency.
*/
#include <asm/regdef.h>
.set noat
.set noreorder
.text
/* There is a problem with either gdb (as of 4.16) or gas (as of 2.7) that
doesn't like putting the entry point for a procedure somewhere in the
middle of the procedure descriptor. Work around this by putting the
aligned copy in its own procedure descriptor */
.ent stxncpy_aligned
.align 4
stxncpy_aligned:
.frame sp, 0, t9, 0
.prologue 0
/* On entry to this basic block:
t0 == the first destination word for masking back in
t1 == the first source word. */
/* Create the 1st output word and detect 0's in the 1st input word. */
lda t2, -1 # E : build a mask against false zero
mskqh t2, a1, t2 # U : detection in the src word (stall)
mskqh t1, a1, t3 # U :
ornot t1, t2, t2 # E : (stall)
mskql t0, a1, t0 # U : assemble the first output word
cmpbge zero, t2, t8 # E : bits set iff null found
or t0, t3, t0 # E : (stall)
beq a2, $a_eoc # U :
bne t8, $a_eos # U :
nop
nop
nop
/* On entry to this basic block:
t0 == a source word not containing a null. */
/*
* nops here to:
* separate store quads from load quads
* limit of 1 bcond/quad to permit training
*/
$a_loop:
stq_u t0, 0(a0) # L :
addq a0, 8, a0 # E :
subq a2, 1, a2 # E :
nop
ldq_u t0, 0(a1) # L :
addq a1, 8, a1 # E :
cmpbge zero, t0, t8 # E :
beq a2, $a_eoc # U :
beq t8, $a_loop # U :
nop
nop
nop
/* Take care of the final (partial) word store. At this point
the end-of-count bit is set in t8 iff it applies.
On entry to this basic block we have:
t0 == the source word containing the null
t8 == the cmpbge mask that found it. */
$a_eos:
negq t8, t12 # E : find low bit set
and t8, t12, t12 # E : (stall)
/* For the sake of the cache, don't read a destination word
if we're not going to need it. */
and t12, 0x80, t6 # E : (stall)
bne t6, 1f # U : (stall)
/* We're doing a partial word store and so need to combine
our source and original destination words. */
ldq_u t1, 0(a0) # L :
subq t12, 1, t6 # E :
or t12, t6, t8 # E : (stall)
zapnot t0, t8, t0 # U : clear src bytes > null (stall)
zap t1, t8, t1 # .. e1 : clear dst bytes <= null
or t0, t1, t0 # e1 : (stall)
nop
nop
1: stq_u t0, 0(a0) # L :
ret (t9) # L0 : Latency=3
nop
nop
/* Add the end-of-count bit to the eos detection bitmask. */
$a_eoc:
or t10, t8, t8 # E :
br $a_eos # L0 : Latency=3
nop
nop
.end stxncpy_aligned
.align 4
.ent __stxncpy
.globl __stxncpy
__stxncpy:
.frame sp, 0, t9, 0
.prologue 0
/* Are source and destination co-aligned? */
xor a0, a1, t1 # E :
and a0, 7, t0 # E : find dest misalignment
and t1, 7, t1 # E : (stall)
addq a2, t0, a2 # E : bias count by dest misalignment (stall)
subq a2, 1, a2 # E :
and a2, 7, t2 # E : (stall)
srl a2, 3, a2 # U : a2 = loop counter = (count - 1)/8 (stall)
addq zero, 1, t10 # E :
sll t10, t2, t10 # U : t10 = bitmask of last count byte
bne t1, $unaligned # U :
/* We are co-aligned; take care of a partial first word. */
ldq_u t1, 0(a1) # L : load first src word
addq a1, 8, a1 # E :
beq t0, stxncpy_aligned # U : avoid loading dest word if not needed
ldq_u t0, 0(a0) # L :
nop
nop
br stxncpy_aligned # .. e1 :
nop
nop
nop
/* The source and destination are not co-aligned. Align the destination
and cope. We have to be very careful about not reading too much and
causing a SEGV. */
.align 4
$u_head:
/* We know just enough now to be able to assemble the first
full source word. We can still find a zero at the end of it
that prevents us from outputting the whole thing.
On entry to this basic block:
t0 == the first dest word, unmasked
t1 == the shifted low bits of the first source word
t6 == bytemask that is -1 in dest word bytes */
ldq_u t2, 8(a1) # L : Latency=3 load second src word
addq a1, 8, a1 # E :
mskql t0, a0, t0 # U : mask trailing garbage in dst
extqh t2, a1, t4 # U : (3 cycle stall on t2)
or t1, t4, t1 # E : first aligned src word complete (stall)
mskqh t1, a0, t1 # U : mask leading garbage in src (stall)
or t0, t1, t0 # E : first output word complete (stall)
or t0, t6, t6 # E : mask original data for zero test (stall)
cmpbge zero, t6, t8 # E :
beq a2, $u_eocfin # U :
lda t6, -1 # E :
nop
bne t8, $u_final # U :
mskql t6, a1, t6 # U : mask out bits already seen
stq_u t0, 0(a0) # L : store first output word
or t6, t2, t2 # E : (stall)
cmpbge zero, t2, t8 # E : find nulls in second partial
addq a0, 8, a0 # E :
subq a2, 1, a2 # E :
bne t8, $u_late_head_exit # U :
/* Finally, we've got all the stupid leading edge cases taken care
of and we can set up to enter the main loop. */
extql t2, a1, t1 # U : position hi-bits of lo word
beq a2, $u_eoc # U :
ldq_u t2, 8(a1) # L : read next high-order source word
addq a1, 8, a1 # E :
extqh t2, a1, t0 # U : position lo-bits of hi word (stall)
cmpbge zero, t2, t8 # E :
nop
bne t8, $u_eos # U :
/* Unaligned copy main loop. In order to avoid reading too much,
the loop is structured to detect zeros in aligned source words.
This has, unfortunately, effectively pulled half of a loop
iteration out into the head and half into the tail, but it does
prevent nastiness from accumulating in the very thing we want
to run as fast as possible.
On entry to this basic block:
t0 == the shifted low-order bits from the current source word
t1 == the shifted high-order bits from the previous source word
t2 == the unshifted current source word
We further know that t2 does not contain a null terminator. */
.align 4
$u_loop:
or t0, t1, t0 # E : current dst word now complete
subq a2, 1, a2 # E : decrement word count
extql t2, a1, t1 # U : extract low bits for next time
addq a0, 8, a0 # E :
stq_u t0, -8(a0) # U : save the current word
beq a2, $u_eoc # U :
ldq_u t2, 8(a1) # U : Latency=3 load high word for next time
addq a1, 8, a1 # E :
extqh t2, a1, t0 # U : extract low bits (2 cycle stall)
cmpbge zero, t2, t8 # E : test new word for eos
nop
beq t8, $u_loop # U :
/* We'
|