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
|
// SPDX-License-Identifier: GPL-2.0-only
// Copyright (C) 2021 ARM Limited.
// Original author: Mark Brown <broonie@kernel.org>
//
// Scalable Matrix Extension ZA context switch test
// Repeatedly writes unique test patterns into each ZA tile
// and reads them back to verify integrity.
//
// for x in `seq 1 NR_CPUS`; do sve-test & pids=$pids\ $! ; done
// (leave it running for as long as you want...)
// kill $pids
#include <asm/unistd.h>
#include "assembler.h"
#include "asm-offsets.h"
#include "sme-inst.h"
.arch_extension sve
#define MAXVL 2048
#define MAXVL_B (MAXVL / 8)
// Declare some storage space to shadow ZA register contents and a
// scratch buffer for a vector.
.pushsection .text
.data
.align 4
zaref:
.space MAXVL_B * MAXVL_B
scratch:
.space MAXVL_B
.popsection
// Trivial memory copy: copy x2 bytes, starting at address x1, to address x0.
// Clobbers x0-x3
function memcpy
cmp x2, #0
b.eq 1f
0: ldrb w3, [x1], #1
strb w3, [x0], #1
subs x2, x2, #1
b.ne 0b
1: ret
endfunction
// Generate a test pattern for storage in ZA
// x0: pid
// x1: row in ZA
// x2: generation
// These values are used to constuct a 32-bit pattern that is repeated in the
// scratch buffer as many times as will fit:
// bits 31:28 generation number (increments once per test_loop)
// bits 27:16 pid
// bits 15: 8 row number
// bits 7: 0 32-bit lane index
function pattern
mov w3, wzr
bfi w3, w0, #16, #12 // PID
bfi w3, w1, #8, #8 // Row
bfi w3, w2, #28, #4 // Generation
ldr x0, =scratch
mov w1, #MAXVL_B / 4
0: str w3, [x0], #4
add w3, w3, #1 // Lane
subs w1, w1, #1
b.ne 0b
ret
endfunction
// Get the address of shadow data for ZA horizontal vector xn
.macro _adrza xd, xn, nrtmp
ldr \xd, =zaref
rdsvl \nrtmp, 1
madd \xd, x\nrtmp, \xn, \xd
.endm
// Set up test pattern in a ZA horizontal vector
// x0: pid
// x1: row number
// x2: generation
function setup_za
mov x4, x30
mov x12, x1 // Use x12 for vector select
bl pattern // Get pattern in scratch buffer
_adrza x0, x12, 2 // Shadow buffer pointer to x0 and x5
mov x5, x0
ldr x1, =scratch
bl memcpy // length set up in x2 by _adrza
_ldr_za 12, 5 // load vector w12 from pointer x5
ret x4
endfunction
// Trivial memory compare: compare x2 bytes starting at address x0 with
// bytes starting at address x1.
// Returns only if all bytes match; otherwise, the program is aborted.
// Clobbers x0-x5.
function memcmp
cbz x2, 2f
stp x0, x1, [sp, #-0x20]!
str x2, [sp, #0x10]
mov x5, #0
0: ldrb w3, [x0, x5]
ldrb w4, [x1, x5]
add x5, x5, #1
cmp w3, w4
b.ne 1f
subs x2, x2, #1
b.ne 0b
1: ldr x2, [sp, #0x10]
ldp x0, x1, [sp], #0x20
b.ne barf
2: ret
endfunction
// Verify that a ZA vector matches its shadow in memory, else abort
// x0: row number
// Clobbers x0-x7 and x12.
function check_za
mov x3, x30
mov x12, x0
_adrza x5, x0, 6 // pointer to expected value in x5
mov x4, x0
ldr x7, =scratch // x7 is scratch
mov x0, x7 // Poison scratch
mov x1, x6
bl memfill_ae
_str_za 12, 7 // save vector w12 to pointer x7
mov x0, x5
mov x1, x7
mov x2, x6
mov x30, x3
b memcmp
endfunction
// Any SME register modified here can cause corruption in the main
// thread -- but *only* the locations modified here.
function irritator_handler
// Increment the irritation signal count (x23):
ldr x0, [x2, #ucontext_regs + 8 * 23]
add x0, x0, #1
str x0, [x2, #ucontext_regs + 8 * 23]
// Corrupt some random ZA data
#if 0
adr x0, .text + (irritator_handler - .text) / 16 * 16
movi v0.8b, #1
movi v9.16b, #2
movi v31.8b, #3
#endif
ret
endfunction
function terminate_handler
mov w21, w0
mov x20, x2
puts "Terminated by signal "
mov w0, w21
bl putdec
puts ", no error, iterations="
ldr x0, [x20, #ucontext_regs + 8 * 22]
bl putdec
puts ", signals="
ldr x0, [x20, #ucontext_regs + 8 * 23]
bl putdecn
mov x0, #0
mov x8, #__NR_exit
svc #0
endfunction
// w0: signal number
// x1: sa_action
// w2: sa_flags
// Clobbers x0-x6,x8
function setsignal
str x30, [sp, #-((sa_sz + 15) / 16 * 16 + 16)]!
mov w4, w0
mov x5, x1
mov w6, w2
add x0, sp, #16
mov x1, #sa_sz
bl memclr
mov w0, w4
add x1, sp, #16
str w6, [x1, #sa_flags]
str x5, [x1, #sa_handler]
mov x2, #0
mov x3, #sa_mask_sz
mov x8, #__NR_rt_sigaction
svc #0
cbz w0, 1f
puts "sigaction failure\n"
b .Labort
1: ldr x30, [sp], #((sa_sz + 15) / 16 * 16 + 16)
ret
endfunction
// Main program entry point
.globl _start
function _start
_start:
puts "Streaming mode "
smstart_za
// Sanity-check and report the vector length
rdsvl 19, 8
cmp x19, #128
b.lo 1f
cmp x19, #2048
b.hi 1f
tst x19, #(8 - 1)
b.eq 2f
1: puts "bad vector length: "
mov x0, x19
bl putdecn
b .Labort
2: puts "vector length:\t"
mov x0, x19
bl putdec
puts " bits\n"
// Obtain our PID, to ensure test pattern uniqueness between processes
mov x8, #__NR_getpid
svc #0
mov x20, x0
puts "PID:\t"
mov x0, x20
bl putdecn
mov x23, #0 // Irritation signal count
mov w0, #SIGINT
adr x1, terminate_handler
mov w2, #SA_SIGINFO
bl setsignal
mov w0, #SIGTERM
adr x1, terminate_handler
mov w2, #SA_SIGINFO
bl setsignal
mov w0, #SIGUSR1
adr x1, irritator_handler
mov w2, #SA_SIGINFO
orr w2, w2, #SA_NODEFER
bl setsignal
mov x22, #0 // generation number, increments per iteration
.Ltest_loop:
rdsvl 0, 8
cmp x0, x19
b.ne vl_barf
rdsvl 21, 1 // Set up ZA & shadow with test pattern
0: mov x0, x20
sub x1, x21, #1
mov x2, x22
bl setup_za
subs x21, x21, #1
b.ne 0b
and x8, x22, #127 // Every 128 interations...
cbz x8, 0f
mov x8, #__NR_getpid // (otherwise minimal syscall)
b 1f
0:
mov x8, #__NR_sched_yield // ...encourage preemption
1:
svc #0
mrs x0, S3_3_C4_C2_2 // SVCR should have ZA=1,SM=0
and x1, x0, #3
cmp x1, #2
b.ne svcr_barf
rdsvl 21, 1 // Verify that the data made it through
rdsvl 24, 1 // Verify that the data made it through
0: sub x0, x24, x21
bl check_za
subs x21, x21, #1
bne 0b
add x22, x22, #1 // Everything still working
b .Ltest_loop
.Labort:
mov x0, #0
mov x1, #SIGABRT
mov x8, #__NR_kill
svc #0
endfunction
function barf
// fpsimd.c acitivty log dump hack
// ldr w0, =0xdeadc0de
// mov w8, #__NR_exit
// svc #0
// end hack
smstop
mov x10, x0 // expected data
mov x11, x1 // actual data
mov x12, x2 // data size
puts "Mismatch: PID="
mov x0, x20
bl putdec
puts ", iteration="
mov x0, x22
bl putdec
puts ", row="
mov x0, x21
bl putdecn
puts "\tExpected ["
mov x0, x10
mov x1, x12
bl dumphex
puts "]\n\tGot ["
mov x0, x11
mov x1, x12
bl dumphex
puts "]\n"
mov x8, #__NR_getpid
svc #0
// fpsimd.c acitivty log dump hack
// ldr w0, =0xdeadc0de
// mov w8, #__NR_exit
// svc #0
// ^ end of hack
mov x1, #SIGABRT
mov x8, #__NR_kill
svc #0
// mov x8, #__NR_exit
// mov x1, #1
// svc #0
endfunction
function vl_barf
mov x10, x0
puts "Bad active VL: "
mov x0, x10
bl putdecn
mov x8, #__NR_exit
mov x1, #1
svc #0
endfunction
function svcr_barf
mov x10, x0
puts "Bad SVCR: "
mov x0, x10
bl putdecn
mov x8, #__NR_exit
mov x1, #1
svc #0
endfunction
|