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
| /*
| * Copyright 2002, 2003 Andi Kleen, SuSE Labs.
| *
| * This file is subject to the terms and conditions of the GNU General Public
| * License. See the file COPYING in the main directory of this archive
| * for more details. No warranty for anything given at all.
| */
| #include <linux/linkage.h>
| #include <asm/errno.h>
| #include <asm/asm.h>
|
| /*
| * Checksum copy with exception handling.
| * On exceptions src_err_ptr or dst_err_ptr is set to -EFAULT and the
| * destination is zeroed.
| *
| * Input
| * rdi source
| * rsi destination
| * edx len (32bit)
| *
| * Output
| * eax 64bit sum. undefined in case of exception.
| *
| * Wrappers need to take care of valid exception sum and zeroing.
| * They also should align source or destination to 8 bytes.
| */
|
| .macro source
| 10:
| _ASM_EXTABLE_UA(10b, .Lfault)
| .endm
|
| .macro dest
| 20:
| _ASM_EXTABLE_UA(20b, .Lfault)
| .endm
|
| SYM_FUNC_START(csum_partial_copy_generic)
| subq $5*8, %rsp
| movq %rbx, 0*8(%rsp)
| movq %r12, 1*8(%rsp)
| movq %r14, 2*8(%rsp)
| movq %r13, 3*8(%rsp)
| movq %r15, 4*8(%rsp)
|
| movl $-1, %eax
| xorl %r9d, %r9d
| movl %edx, %ecx
| cmpl $8, %ecx
| jb .Lshort
|
| testb $7, %sil
| jne .Lunaligned
| .Laligned:
| movl %ecx, %r12d
|
| shrq $6, %r12
| jz .Lhandle_tail /* < 64 */
|
| clc
|
| /* main loop. clear in 64 byte blocks */
| /* r9: zero, r8: temp2, rbx: temp1, rax: sum, rcx: saved length */
| /* r11: temp3, rdx: temp4, r12 loopcnt */
| /* r10: temp5, r15: temp6, r14 temp7, r13 temp8 */
| .p2align 4
| .Lloop:
| source
| movq (%rdi), %rbx
| source
| movq 8(%rdi), %r8
| source
| movq 16(%rdi), %r11
| source
| movq 24(%rdi), %rdx
|
| source
| movq 32(%rdi), %r10
| source
| movq 40(%rdi), %r15
| source
| movq 48(%rdi), %r14
| source
| movq 56(%rdi), %r13
|
| 30:
| /*
| * No _ASM_EXTABLE_UA; this is used for intentional prefetch on a
| * potentially unmapped kernel address.
| */
| _ASM_EXTABLE(30b, 2f)
| prefetcht0 5*64(%rdi)
| 2:
| adcq %rbx, %rax
| adcq %r8, %rax
| adcq %r11, %rax
| adcq %rdx, %rax
| adcq %r10, %rax
| adcq %r15, %rax
| adcq %r14, %rax
| adcq %r13, %rax
|
| decl %r12d
|
| dest
| movq %rbx, (%rsi)
| dest
| movq %r8, 8(%rsi)
| dest
| movq %r11, 16(%rsi)
| dest
| movq %rdx, 24(%rsi)
|
| dest
| movq %r10, 32(%rsi)
| dest
| movq %r15, 40(%rsi)
| dest
| movq %r14, 48(%rsi)
| dest
| movq %r13, 56(%rsi)
|
| leaq 64(%rdi), %rdi
| leaq 64(%rsi), %rsi
|
| jnz .Lloop
|
| adcq %r9, %rax
|
| /* do last up to 56 bytes */
| .Lhandle_tail:
| /* ecx: count, rcx.63: the end result needs to be rol8 */
| movq %rcx, %r10
| andl $63, %ecx
| shrl $3, %ecx
| jz .Lfold
| clc
| .p2align 4
| .Lloop_8:
| source
| movq (%rdi), %rbx
| adcq %rbx, %rax
| decl %ecx
| dest
| movq %rbx, (%rsi)
| leaq 8(%rsi), %rsi /* preserve carry */
| leaq 8(%rdi), %rdi
| jnz .Lloop_8
| adcq %r9, %rax /* add in carry */
|
| .Lfold:
| /* reduce checksum to 32bits */
| movl %eax, %ebx
| shrq $32, %rax
| addl %ebx, %eax
| adcl %r9d, %eax
|
| /* do last up to 6 bytes */
| .Lhandle_7:
| movl %r10d, %ecx
| andl $7, %ecx
| .L1: /* .Lshort rejoins the common path here */
| shrl $1, %ecx
| jz .Lhandle_1
| movl $2, %edx
| xorl %ebx, %ebx
| clc
| .p2align 4
| .Lloop_1:
| source
| movw (%rdi), %bx
| adcl %ebx, %eax
| decl %ecx
| dest
| movw %bx, (%rsi)
| leaq 2(%rdi), %rdi
| leaq 2(%rsi), %rsi
| jnz .Lloop_1
| adcl %r9d, %eax /* add in carry */
|
| /* handle last odd byte */
| .Lhandle_1:
| testb $1, %r10b
| jz .Lende
| xorl %ebx, %ebx
| source
| movb (%rdi), %bl
| dest
| movb %bl, (%rsi)
| addl %ebx, %eax
| adcl %r9d, %eax /* carry */
|
| .Lende:
| testq %r10, %r10
| js .Lwas_odd
| .Lout:
| movq 0*8(%rsp), %rbx
| movq 1*8(%rsp), %r12
| movq 2*8(%rsp), %r14
| movq 3*8(%rsp), %r13
| movq 4*8(%rsp), %r15
| addq $5*8, %rsp
| RET
| .Lshort:
| movl %ecx, %r10d
| jmp .L1
| .Lunaligned:
| xorl %ebx, %ebx
| testb $1, %sil
| jne .Lodd
| 1: testb $2, %sil
| je 2f
| source
| movw (%rdi), %bx
| dest
| movw %bx, (%rsi)
| leaq 2(%rdi), %rdi
| subq $2, %rcx
| leaq 2(%rsi), %rsi
| addq %rbx, %rax
| 2: testb $4, %sil
| je .Laligned
| source
| movl (%rdi), %ebx
| dest
| movl %ebx, (%rsi)
| leaq 4(%rdi), %rdi
| subq $4, %rcx
| leaq 4(%rsi), %rsi
| addq %rbx, %rax
| jmp .Laligned
|
| .Lodd:
| source
| movb (%rdi), %bl
| dest
| movb %bl, (%rsi)
| leaq 1(%rdi), %rdi
| leaq 1(%rsi), %rsi
| /* decrement, set MSB */
| leaq -1(%rcx, %rcx), %rcx
| rorq $1, %rcx
| shll $8, %ebx
| addq %rbx, %rax
| jmp 1b
|
| .Lwas_odd:
| roll $8, %eax
| jmp .Lout
|
| /* Exception: just return 0 */
| .Lfault:
| xorl %eax, %eax
| jmp .Lout
| SYM_FUNC_END(csum_partial_copy_generic)
|
|
