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
|
/* SPDX-License-Identifier: GPL-2.0 */
/*
* Copyright (C) IBM Corporation, 2011
* Derived from copyuser_power7.s by Anton Blanchard <anton@au.ibm.com>
* Author - Balbir Singh <bsingharora@gmail.com>
*/
#include <linux/export.h>
#include <asm/ppc_asm.h>
#include <asm/errno.h>
.macro err1
100:
EX_TABLE(100b,.Ldo_err1)
.endm
.macro err2
200:
EX_TABLE(200b,.Ldo_err2)
.endm
.macro err3
300: EX_TABLE(300b,.Ldone)
.endm
.Ldo_err2:
ld r22,STK_REG(R22)(r1)
ld r21,STK_REG(R21)(r1)
ld r20,STK_REG(R20)(r1)
ld r19,STK_REG(R19)(r1)
ld r18,STK_REG(R18)(r1)
ld r17,STK_REG(R17)(r1)
ld r16,STK_REG(R16)(r1)
ld r15,STK_REG(R15)(r1)
ld r14,STK_REG(R14)(r1)
addi r1,r1,STACKFRAMESIZE
.Ldo_err1:
/* Do a byte by byte copy to get the exact remaining size */
mtctr r7
46:
err3; lbz r0,0(r4)
addi r4,r4,1
err3; stb r0,0(r3)
addi r3,r3,1
bdnz 46b
li r3,0
blr
.Ldone:
mfctr r3
blr
_GLOBAL(copy_mc_generic)
mr r7,r5
cmpldi r5,16
blt .Lshort_copy
.Lcopy:
/* Get the source 8B aligned */
neg r6,r4
mtocrf 0x01,r6
clrldi r6,r6,(64-3)
bf cr7*4+3,1f
err1; lbz r0,0(r4)
addi r4,r4,1
err1; stb r0,0(r3)
addi r3,r3,1
subi r7,r7,1
1: bf cr7*4+2,2f
err1; lhz r0,0(r4)
addi r4,r4,2
err1; sth r0,0(r3)
addi r3,r3,2
subi r7,r7,2
2: bf cr7*4+1,3f
err1; lwz r0,0(r4)
addi r4,r4,4
err1; stw r0,0(r3)
addi r3,r3,4
subi r7,r7,4
3: sub r5,r5,r6
cmpldi r5,128
mflr r0
stdu r1,-STACKFRAMESIZE(r1)
std r14,STK_REG(R14)(r1)
std r15,STK_REG(R15)(r1)
std r16,STK_REG(R16)(r1)
std r17,STK_REG(R17)(r1)
std r18,STK_REG(R18)(r1)
std r19,STK_REG(R19)(r1)
std r20,STK_REG(R20)(r1)
std r21,STK_REG(R21)(r1)
std r22,STK_REG(R22)(r1)
std r0,STACKFRAMESIZE+16(r1)
blt 5f
srdi r6,r5,7
mtctr r6
/* Now do cacheline (128B) sized loads and stores. */
.align 5
4:
err2; ld r0,0(r4)
err2; ld r6,8(r4)
err2; ld r8,16(r4)
err2; ld r9,24(r4)
err2; ld r10,32(r4)
err2; ld r11,40(r4)
err2; ld r12,48(r4)
err2; ld r14,56(r4)
err2; ld r15,64(r4)
err2; ld r16,72(r4)
err2; ld r17,80(r4)
err2; ld r18,88(r4)
err2; ld r19,96(r4)
err2; ld r20,104(r4)
err2; ld r21,112(r4)
err2; ld r22,120(r4)
addi r4,r4,128
err2; std r0,0(r3)
err2; std r6,8(r3)
err2; std r8,16(r3)
err2; std r9,24(r3)
err2; std r10,32(r3)
err2; std r11,40(r3)
err2; std r12,48(r3)
err2; std r14,56(r3)
err2; std r15,64(r3)
err2; std r16,72(r3)
err2; std r17,80(r3)
err2; std r18,88(r3)
err2; std r19,96(r3)
err2; std r20,104(r3)
err2; std r21,112(r3)
err2; std r22,120(r3)
addi r3,r3,128
subi r7,r7,128
bdnz 4b
clrldi r5,r5,(64-7)
/* Up to 127B to go */
5: srdi r6,r5,4
mtocrf 0x01,r6
6: bf cr7*4+1,7f
err2; ld r0,0(r4)
err2; ld r6,8(r4)
err2; ld r8,16(r4)
err2; ld r9,24(r4)
err2; ld r10,32(r4)
err2; ld r11,40(r4)
err2; ld r12,48(r4)
err2; ld r14,56(r4)
addi r4,r4,64
err2; std r0,0(r3)
err2; std r6,8(r3)
err2; std r8,16(r3)
err2; std r9,24(r3)
err2; std r10,32(r3)
err2; std r11,40(r3)
err2; std r12,48(r3)
err2; std r14,56(r3)
addi r3,r3,64
subi r7,r7,64
7: ld r14,STK_REG(R14)(r1)
ld r15,STK_REG(R15)(r1)
ld r16,STK_REG(R16)(r1)
ld r17,STK_REG(R17)(r1)
ld r18,STK_REG(R18)(r1)
ld r19,STK_REG(R19)(r1)
ld r20,STK_REG(R20)(r1)
ld r21,STK_REG(R21)(r1)
ld r22,STK_REG(R22)(r1)
addi r1,r1,STACKFRAMESIZE
/* Up to 63B to go */
bf cr7*4+2,8f
err1; ld r0,0(r4)
err1; ld r6,8(r4)
err1; ld r8,16(r4)
err1; ld r9,24(r4)
addi r4,r4,32
err1; std r0,0(r3)
err1; std r6,8(r3)
err1; std r8,16(r3)
err1; std r9,24(r3)
addi r3,r3,32
subi r7,r7,32
/* Up to 31B to go */
8: bf cr7*4+3,9f
err1; ld r0,0(r4)
err1; ld r6,8(r4)
addi r4,r4,16
err1; std r0,0(r3)
err1; std r6,8(r3)
addi r3,r3,16
subi r7,r7,16
9: clrldi r5,r5,(64-4)
/* Up to 15B to go */
.Lshort_copy:
mtocrf 0x01,r5
bf cr7*4+0,12f
err1; lwz r0,0(r4) /* Less chance of a reject with word ops */
err1; lwz r6,4(r4)
addi r4,r4,8
err1; stw r0,0(r3)
err1; stw r6,4(r3)
addi r3,r3,8
subi r7,r7,8
12: bf cr7*4+1,13f
err1; lwz r0,0(r4)
addi r4,r4,4
err1; stw r0,0(r3)
addi r3,r3,4
subi r7,r7,4
13: bf cr7*4+2,14f
err1; lhz r0,0(r4)
addi r4,r4,2
err1; sth r0,0(r3)
addi r3,r3,2
subi r7,r7,2
14: bf cr7*4+3,15f
err1; lbz r0,0(r4)
err1; stb r0,0(r3)
15: li r3,0
blr
EXPORT_SYMBOL_GPL(copy_mc_generic);
|
