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
| /* Copyright 2002 Andi Kleen */
|
| #include <linux/linkage.h>
| #include <asm/errno.h>
| #include <asm/cpufeatures.h>
| #include <asm/mcsafe_test.h>
| #include <asm/alternative-asm.h>
| #include <asm/export.h>
|
| /*
| * We build a jump to memcpy_orig by default which gets NOPped out on
| * the majority of x86 CPUs which set REP_GOOD. In addition, CPUs which
| * have the enhanced REP MOVSB/STOSB feature (ERMS), change those NOPs
| * to a jmp to memcpy_erms which does the REP; MOVSB mem copy.
| */
|
| .weak memcpy
|
| /*
| * memcpy - Copy a memory block.
| *
| * Input:
| * rdi destination
| * rsi source
| * rdx count
| *
| * Output:
| * rax original destination
| */
| ENTRY(__memcpy)
| ENTRY(memcpy)
| ALTERNATIVE_2 "jmp memcpy_orig", "", X86_FEATURE_REP_GOOD, \
| "jmp memcpy_erms", X86_FEATURE_ERMS
|
| movq %rdi, %rax
| movq %rdx, %rcx
| shrq $3, %rcx
| andl $7, %edx
| rep movsq
| movl %edx, %ecx
| rep movsb
| ret
| ENDPROC(memcpy)
| ENDPROC(__memcpy)
| EXPORT_SYMBOL(memcpy)
| EXPORT_SYMBOL(__memcpy)
|
| /*
| * memcpy_erms() - enhanced fast string memcpy. This is faster and
| * simpler than memcpy. Use memcpy_erms when possible.
| */
| ENTRY(memcpy_erms)
| movq %rdi, %rax
| movq %rdx, %rcx
| rep movsb
| ret
| ENDPROC(memcpy_erms)
|
| ENTRY(memcpy_orig)
| movq %rdi, %rax
|
| cmpq $0x20, %rdx
| jb .Lhandle_tail
|
| /*
| * We check whether memory false dependence could occur,
| * then jump to corresponding copy mode.
| */
| cmp %dil, %sil
| jl .Lcopy_backward
| subq $0x20, %rdx
| .Lcopy_forward_loop:
| subq $0x20, %rdx
|
| /*
| * Move in blocks of 4x8 bytes:
| */
| movq 0*8(%rsi), %r8
| movq 1*8(%rsi), %r9
| movq 2*8(%rsi), %r10
| movq 3*8(%rsi), %r11
| leaq 4*8(%rsi), %rsi
|
| movq %r8, 0*8(%rdi)
| movq %r9, 1*8(%rdi)
| movq %r10, 2*8(%rdi)
| movq %r11, 3*8(%rdi)
| leaq 4*8(%rdi), %rdi
| jae .Lcopy_forward_loop
| addl $0x20, %edx
| jmp .Lhandle_tail
|
| .Lcopy_backward:
| /*
| * Calculate copy position to tail.
| */
| addq %rdx, %rsi
| addq %rdx, %rdi
| subq $0x20, %rdx
| /*
| * At most 3 ALU operations in one cycle,
| * so append NOPS in the same 16 bytes trunk.
| */
| .p2align 4
| .Lcopy_backward_loop:
| subq $0x20, %rdx
| movq -1*8(%rsi), %r8
| movq -2*8(%rsi), %r9
| movq -3*8(%rsi), %r10
| movq -4*8(%rsi), %r11
| leaq -4*8(%rsi), %rsi
| movq %r8, -1*8(%rdi)
| movq %r9, -2*8(%rdi)
| movq %r10, -3*8(%rdi)
| movq %r11, -4*8(%rdi)
| leaq -4*8(%rdi), %rdi
| jae .Lcopy_backward_loop
|
| /*
| * Calculate copy position to head.
| */
| addl $0x20, %edx
| subq %rdx, %rsi
| subq %rdx, %rdi
| .Lhandle_tail:
| cmpl $16, %edx
| jb .Lless_16bytes
|
| /*
| * Move data from 16 bytes to 31 bytes.
| */
| movq 0*8(%rsi), %r8
| movq 1*8(%rsi), %r9
| movq -2*8(%rsi, %rdx), %r10
| movq -1*8(%rsi, %rdx), %r11
| movq %r8, 0*8(%rdi)
| movq %r9, 1*8(%rdi)
| movq %r10, -2*8(%rdi, %rdx)
| movq %r11, -1*8(%rdi, %rdx)
| retq
| .p2align 4
| .Lless_16bytes:
| cmpl $8, %edx
| jb .Lless_8bytes
| /*
| * Move data from 8 bytes to 15 bytes.
| */
| movq 0*8(%rsi), %r8
| movq -1*8(%rsi, %rdx), %r9
| movq %r8, 0*8(%rdi)
| movq %r9, -1*8(%rdi, %rdx)
| retq
| .p2align 4
| .Lless_8bytes:
| cmpl $4, %edx
| jb .Lless_3bytes
|
| /*
| * Move data from 4 bytes to 7 bytes.
| */
| movl (%rsi), %ecx
| movl -4(%rsi, %rdx), %r8d
| movl %ecx, (%rdi)
| movl %r8d, -4(%rdi, %rdx)
| retq
| .p2align 4
| .Lless_3bytes:
| subl $1, %edx
| jb .Lend
| /*
| * Move data from 1 bytes to 3 bytes.
| */
| movzbl (%rsi), %ecx
| jz .Lstore_1byte
| movzbq 1(%rsi), %r8
| movzbq (%rsi, %rdx), %r9
| movb %r8b, 1(%rdi)
| movb %r9b, (%rdi, %rdx)
| .Lstore_1byte:
| movb %cl, (%rdi)
|
| .Lend:
| retq
| ENDPROC(memcpy_orig)
|
| #ifndef CONFIG_UML
|
| MCSAFE_TEST_CTL
|
| /*
| * __memcpy_mcsafe - memory copy with machine check exception handling
| * Note that we only catch machine checks when reading the source addresses.
| * Writes to target are posted and don't generate machine checks.
| */
| ENTRY(__memcpy_mcsafe)
| cmpl $8, %edx
| /* Less than 8 bytes? Go to byte copy loop */
| jb .L_no_whole_words
|
| /* Check for bad alignment of source */
| testl $7, %esi
| /* Already aligned */
| jz .L_8byte_aligned
|
| /* Copy one byte at a time until source is 8-byte aligned */
| movl %esi, %ecx
| andl $7, %ecx
| subl $8, %ecx
| negl %ecx
| subl %ecx, %edx
| .L_read_leading_bytes:
| movb (%rsi), %al
| MCSAFE_TEST_SRC %rsi 1 .E_leading_bytes
| MCSAFE_TEST_DST %rdi 1 .E_leading_bytes
| .L_write_leading_bytes:
| movb %al, (%rdi)
| incq %rsi
| incq %rdi
| decl %ecx
| jnz .L_read_leading_bytes
|
| .L_8byte_aligned:
| movl %edx, %ecx
| andl $7, %edx
| shrl $3, %ecx
| jz .L_no_whole_words
|
| .L_read_words:
| movq (%rsi), %r8
| MCSAFE_TEST_SRC %rsi 8 .E_read_words
| MCSAFE_TEST_DST %rdi 8 .E_write_words
| .L_write_words:
| movq %r8, (%rdi)
| addq $8, %rsi
| addq $8, %rdi
| decl %ecx
| jnz .L_read_words
|
| /* Any trailing bytes? */
| .L_no_whole_words:
| andl %edx, %edx
| jz .L_done_memcpy_trap
|
| /* Copy trailing bytes */
| movl %edx, %ecx
| .L_read_trailing_bytes:
| movb (%rsi), %al
| MCSAFE_TEST_SRC %rsi 1 .E_trailing_bytes
| MCSAFE_TEST_DST %rdi 1 .E_trailing_bytes
| .L_write_trailing_bytes:
| movb %al, (%rdi)
| incq %rsi
| incq %rdi
| decl %ecx
| jnz .L_read_trailing_bytes
|
| /* Copy successful. Return zero */
| .L_done_memcpy_trap:
| xorl %eax, %eax
| ret
| ENDPROC(__memcpy_mcsafe)
| EXPORT_SYMBOL_GPL(__memcpy_mcsafe)
|
| .section .fixup, "ax"
| /*
| * Return number of bytes not copied for any failure. Note that
| * there is no "tail" handling since the source buffer is 8-byte
| * aligned and poison is cacheline aligned.
| */
| .E_read_words:
| shll $3, %ecx
| .E_leading_bytes:
| addl %edx, %ecx
| .E_trailing_bytes:
| mov %ecx, %eax
| ret
|
| /*
| * For write fault handling, given the destination is unaligned,
| * we handle faults on multi-byte writes with a byte-by-byte
| * copy up to the write-protected page.
| */
| .E_write_words:
| shll $3, %ecx
| addl %edx, %ecx
| movl %ecx, %edx
| jmp mcsafe_handle_tail
|
| .previous
|
| _ASM_EXTABLE_FAULT(.L_read_leading_bytes, .E_leading_bytes)
| _ASM_EXTABLE_FAULT(.L_read_words, .E_read_words)
| _ASM_EXTABLE_FAULT(.L_read_trailing_bytes, .E_trailing_bytes)
| _ASM_EXTABLE(.L_write_leading_bytes, .E_leading_bytes)
| _ASM_EXTABLE(.L_write_words, .E_write_words)
| _ASM_EXTABLE(.L_write_trailing_bytes, .E_trailing_bytes)
| #endif
|
|
