1 # SOME DESCRIPTIVE TITLE
2 # Copyright (C) YEAR Free Software Foundation, Inc.
3 # This file is distributed under the same license as the PACKAGE package.
4 # FIRST AUTHOR <EMAIL@ADDRESS>, YEAR.
8 "Project-Id-Version: PACKAGE VERSION\n"
9 "POT-Creation-Date: 2015-02-04 23:30+0900\n"
10 "PO-Revision-Date: 2015-01-27 02:55+0900\n"
11 "Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
12 "Language-Team: LANGUAGE <LL@li.org>\n"
15 "Content-Type: text/plain; charset=UTF-8\n"
16 "Content-Transfer-Encoding: 8bit\n"
19 #: build/C/man2/arch_prctl.2:25
25 #: build/C/man2/arch_prctl.2:25
31 #: build/C/man2/arch_prctl.2:25 build/C/man2/futex.2:53
32 #: build/C/man2/get_robust_list.2:29 build/C/man2/getunwind.2:27
33 #: build/C/man2/kexec_load.2:27 build/C/man2/lookup_dcookie.2:27
34 #: build/C/man2/modify_ldt.2:24 build/C/man2/nfsservctl.2:8
35 #: build/C/man2/outb.2:26 build/C/man2/pciconfig_read.2:8
36 #: build/C/man2/perf_event_open.2:27 build/C/man2/perfmonctl.2:27
37 #: build/C/man2/personality.2:32 build/C/man2/pivot_root.2:10
38 #: build/C/man2/process_vm_readv.2:29 build/C/man2/ptrace.2:46
39 #: build/C/man2/quotactl.2:27 build/C/man2/sendfile.2:19
40 #: build/C/man2/set_tid_address.2:25 build/C/man2/splice.2:26
41 #: build/C/man2/tee.2:26 build/C/man2/vm86.2:26 build/C/man2/vmsplice.2:26
47 #: build/C/man2/arch_prctl.2:25 build/C/man2/futex.2:53
48 #: build/C/man2/getunwind.2:27 build/C/man2/kexec_load.2:27
49 #: build/C/man2/lookup_dcookie.2:27 build/C/man2/modify_ldt.2:24
50 #: build/C/man2/nfsservctl.2:8 build/C/man2/outb.2:26
51 #: build/C/man2/pciconfig_read.2:8 build/C/man2/perf_event_open.2:27
52 #: build/C/man2/perfmonctl.2:27 build/C/man2/personality.2:32
53 #: build/C/man2/pivot_root.2:10 build/C/man2/process_vm_readv.2:29
54 #: build/C/man2/ptrace.2:46 build/C/man2/quotactl.2:27
55 #: build/C/man2/sendfile.2:19 build/C/man2/set_tid_address.2:25
56 #: build/C/man2/splice.2:26 build/C/man2/tee.2:26 build/C/man2/vm86.2:26
57 #: build/C/man2/vmsplice.2:26
59 msgid "Linux Programmer's Manual"
60 msgstr "Linux Programmer's Manual"
63 #: build/C/man2/arch_prctl.2:26 build/C/man2/futex.2:54
64 #: build/C/man2/get_robust_list.2:30 build/C/man2/getunwind.2:28
65 #: build/C/man2/kexec_load.2:28 build/C/man2/lookup_dcookie.2:28
66 #: build/C/man2/modify_ldt.2:25 build/C/man2/nfsservctl.2:9
67 #: build/C/man2/outb.2:27 build/C/man2/pciconfig_read.2:9
68 #: build/C/man2/perf_event_open.2:28 build/C/man2/perfmonctl.2:28
69 #: build/C/man2/personality.2:33 build/C/man2/pivot_root.2:11
70 #: build/C/man2/process_vm_readv.2:30 build/C/man2/ptrace.2:47
71 #: build/C/man2/quotactl.2:28 build/C/man2/sendfile.2:20
72 #: build/C/man2/set_tid_address.2:26 build/C/man2/splice.2:27
73 #: build/C/man2/tee.2:27 build/C/man2/vm86.2:27 build/C/man2/vmsplice.2:27
79 #: build/C/man2/arch_prctl.2:28
80 msgid "arch_prctl - set architecture-specific thread state"
81 msgstr "arch_prctl - アーキテクチャー固有のスレッド状態を設定する"
84 #: build/C/man2/arch_prctl.2:28 build/C/man2/futex.2:56
85 #: build/C/man2/get_robust_list.2:32 build/C/man2/getunwind.2:30
86 #: build/C/man2/kexec_load.2:30 build/C/man2/lookup_dcookie.2:30
87 #: build/C/man2/modify_ldt.2:27 build/C/man2/nfsservctl.2:11
88 #: build/C/man2/outb.2:31 build/C/man2/pciconfig_read.2:11
89 #: build/C/man2/perf_event_open.2:30 build/C/man2/perfmonctl.2:30
90 #: build/C/man2/personality.2:35 build/C/man2/pivot_root.2:13
91 #: build/C/man2/process_vm_readv.2:32 build/C/man2/ptrace.2:49
92 #: build/C/man2/quotactl.2:30 build/C/man2/sendfile.2:22
93 #: build/C/man2/set_tid_address.2:28 build/C/man2/splice.2:29
94 #: build/C/man2/tee.2:29 build/C/man2/vm86.2:29 build/C/man2/vmsplice.2:29
100 #: build/C/man2/arch_prctl.2:31
102 msgid "B<#include E<lt>asm/prctl.hE<gt>>\n"
103 msgstr "B<#include E<lt>asm/prctl.hE<gt>>\n"
106 #: build/C/man2/arch_prctl.2:33
108 msgid "B<#include E<lt>sys/prctl.hE<gt>>\n"
109 msgstr "B<#include E<lt>sys/prctl.hE<gt>>\n"
112 #: build/C/man2/arch_prctl.2:36
115 "B<int arch_prctl(int >I<code>B<, unsigned long >I<addr>B<);>\n"
116 "B<int arch_prctl(int >I<code>B<, unsigned long *>I<addr>B<);>\n"
117 msgstr "B<int arch_prctl(int >I<code>B<, unsigned long *>I<addr>B<);>\n"
119 #. Return type was long before glibc 2.7
121 #: build/C/man2/arch_prctl.2:37 build/C/man2/futex.2:70
122 #: build/C/man2/get_robust_list.2:45 build/C/man2/getunwind.2:40
123 #: build/C/man2/kexec_load.2:47 build/C/man2/lookup_dcookie.2:32
124 #: build/C/man2/modify_ldt.2:36 build/C/man2/nfsservctl.2:18
125 #: build/C/man2/outb.2:62 build/C/man2/pciconfig_read.2:22
126 #: build/C/man2/perf_event_open.2:42 build/C/man2/perfmonctl.2:39
127 #: build/C/man2/personality.2:39 build/C/man2/pivot_root.2:18
128 #: build/C/man2/process_vm_readv.2:66 build/C/man2/ptrace.2:56
129 #: build/C/man2/quotactl.2:38 build/C/man2/sendfile.2:47
130 #: build/C/man2/set_tid_address.2:34 build/C/man2/splice.2:39
131 #: build/C/man2/tee.2:38 build/C/man2/vm86.2:35 build/C/man2/vmsplice.2:39
137 #: build/C/man2/arch_prctl.2:52
139 "The B<arch_prctl>() function sets architecture-specific process or thread "
140 "state. I<code> selects a subfunction and passes argument I<addr> to it; "
141 "I<addr> is interpreted as either an I<unsigned long> for the \"set\" "
142 "operations, or as an I<unsigned long\\ *>, for the \"get\" operations."
144 "B<arch_prctl>() 関数はアーキテクチャー固有のプロセス状態またはスレッド状態を"
145 "設定する。 I<code> は副機能を選択し、引き数 I<addr> を副機能に渡す。 I<addr> "
146 "は、\"set\" 操作では I<unsigned long> として、\"get\" 操作では I<unsigned "
147 "long\\ *> として解釈される。"
150 #: build/C/man2/arch_prctl.2:54
151 msgid "Subfunctions for x86-64 are:"
152 msgstr "x86-64 の副機能は以下の通り:"
155 #: build/C/man2/arch_prctl.2:54
157 msgid "B<ARCH_SET_FS>"
158 msgstr "B<ARCH_SET_FS>"
161 #: build/C/man2/arch_prctl.2:60
162 msgid "Set the 64-bit base for the I<FS> register to I<addr>."
163 msgstr "I<FS> レジスターの 64 ビットベースを I<addr> に設定する。"
166 #: build/C/man2/arch_prctl.2:60
168 msgid "B<ARCH_GET_FS>"
169 msgstr "B<ARCH_GET_FS>"
172 #: build/C/man2/arch_prctl.2:68
174 "Return the 64-bit base value for the I<FS> register of the current thread in "
175 "the I<unsigned long> pointed to by I<addr>."
177 "現在のスレッドの I<FS> レジスターの 64 ビットベース値を、 I<addr> が指す "
178 "I<unsigned long> の領域に格納する。"
181 #: build/C/man2/arch_prctl.2:68
183 msgid "B<ARCH_SET_GS>"
184 msgstr "B<ARCH_SET_GS>"
187 #: build/C/man2/arch_prctl.2:74
188 msgid "Set the 64-bit base for the I<GS> register to I<addr>."
189 msgstr "I<GS> レジスターの 64 ビットベースを I<addr> に設定する。"
192 #: build/C/man2/arch_prctl.2:74
194 msgid "B<ARCH_GET_GS>"
195 msgstr "B<ARCH_GET_GS>"
198 #: build/C/man2/arch_prctl.2:82
200 "Return the 64-bit base value for the I<GS> register of the current thread in "
201 "the I<unsigned long> pointed to by I<addr>."
203 "現在のスレッドの I<GS> レジスターの 64 ビットベース値を、 I<addr> が指す "
204 "I<unsigned long> の領域に格納する。"
207 #: build/C/man2/arch_prctl.2:82 build/C/man2/futex.2:216
208 #: build/C/man2/get_robust_list.2:78 build/C/man2/getunwind.2:81
209 #: build/C/man2/kexec_load.2:242 build/C/man2/lookup_dcookie.2:43
210 #: build/C/man2/modify_ldt.2:98 build/C/man2/nfsservctl.2:53
211 #: build/C/man2/pciconfig_read.2:50 build/C/man2/perf_event_open.2:2607
212 #: build/C/man2/perfmonctl.2:190 build/C/man2/personality.2:62
213 #: build/C/man2/pivot_root.2:101 build/C/man2/process_vm_readv.2:225
214 #: build/C/man2/ptrace.2:1896 build/C/man2/quotactl.2:419
215 #: build/C/man2/sendfile.2:108 build/C/man2/set_tid_address.2:88
216 #: build/C/man2/splice.2:135 build/C/man2/tee.2:85 build/C/man2/vm86.2:54
217 #: build/C/man2/vmsplice.2:117
223 #: build/C/man2/arch_prctl.2:88
225 "On success, B<arch_prctl>() returns 0; on error, -1 is returned, and "
226 "I<errno> is set to indicate the error."
228 "成功すると、 B<arch_prctl>() は 0 を返す。エラーの場合、-1 を返し、 "
229 "I<errno> をエラーを示す値に設定する。"
232 #: build/C/man2/arch_prctl.2:88 build/C/man2/futex.2:241
233 #: build/C/man2/get_robust_list.2:85 build/C/man2/getunwind.2:88
234 #: build/C/man2/kexec_load.2:247 build/C/man2/lookup_dcookie.2:50
235 #: build/C/man2/modify_ldt.2:108 build/C/man2/pciconfig_read.2:77
236 #: build/C/man2/perf_event_open.2:2613 build/C/man2/personality.2:69
237 #: build/C/man2/pivot_root.2:105 build/C/man2/process_vm_readv.2:245
238 #: build/C/man2/ptrace.2:1911 build/C/man2/quotactl.2:427
239 #: build/C/man2/sendfile.2:115 build/C/man2/set_tid_address.2:91
240 #: build/C/man2/splice.2:150 build/C/man2/tee.2:100 build/C/man2/vm86.2:59
241 #: build/C/man2/vmsplice.2:126
247 #: build/C/man2/arch_prctl.2:89 build/C/man2/futex.2:256
248 #: build/C/man2/get_robust_list.2:112 build/C/man2/lookup_dcookie.2:51
249 #: build/C/man2/modify_ldt.2:109 build/C/man2/perf_event_open.2:2659
250 #: build/C/man2/process_vm_readv.2:267 build/C/man2/process_vm_readv.2:272
251 #: build/C/man2/ptrace.2:1915 build/C/man2/quotactl.2:428
252 #: build/C/man2/sendfile.2:125 build/C/man2/vm86.2:60
258 #: build/C/man2/arch_prctl.2:93
260 "I<addr> points to an unmapped address or is outside the process address "
263 "I<addr> がアンマップされたアドレスを指しているか、プロセスのアドレス空間の外"
267 #: build/C/man2/arch_prctl.2:93 build/C/man2/futex.2:268
268 #: build/C/man2/get_robust_list.2:89 build/C/man2/kexec_load.2:279
269 #: build/C/man2/kexec_load.2:283 build/C/man2/kexec_load.2:292
270 #: build/C/man2/kexec_load.2:298 build/C/man2/kexec_load.2:301
271 #: build/C/man2/kexec_load.2:306 build/C/man2/lookup_dcookie.2:54
272 #: build/C/man2/modify_ldt.2:113 build/C/man2/pciconfig_read.2:78
273 #: build/C/man2/perf_event_open.2:2664 build/C/man2/personality.2:70
274 #: build/C/man2/pivot_root.2:114 build/C/man2/process_vm_readv.2:246
275 #: build/C/man2/process_vm_readv.2:257 build/C/man2/process_vm_readv.2:261
276 #: build/C/man2/ptrace.2:1926 build/C/man2/quotactl.2:434
277 #: build/C/man2/quotactl.2:501 build/C/man2/sendfile.2:128
278 #: build/C/man2/splice.2:161 build/C/man2/tee.2:107
279 #: build/C/man2/vmsplice.2:137
285 #: build/C/man2/arch_prctl.2:97
286 msgid "I<code> is not a valid subcommand."
287 msgstr "I<code> が有効なサブコマンドでない。"
290 #: build/C/man2/arch_prctl.2:97 build/C/man2/get_robust_list.2:99
291 #: build/C/man2/kexec_load.2:323 build/C/man2/lookup_dcookie.2:65
292 #: build/C/man2/pciconfig_read.2:105 build/C/man2/perf_event_open.2:2732
293 #: build/C/man2/pivot_root.2:120 build/C/man2/process_vm_readv.2:283
294 #: build/C/man2/ptrace.2:1936 build/C/man2/quotactl.2:456
295 #: build/C/man2/vm86.2:68
301 #. Man page written by Andi Kleen.
303 #: build/C/man2/arch_prctl.2:103
304 msgid "I<addr> is outside the process address space."
305 msgstr "I<addr> がプロセスのアドレス空間の外にある。"
308 #: build/C/man2/arch_prctl.2:103 build/C/man2/futex.2:303
309 #: build/C/man2/getunwind.2:96 build/C/man2/kexec_load.2:335
310 #: build/C/man2/lookup_dcookie.2:78 build/C/man2/modify_ldt.2:130
311 #: build/C/man2/nfsservctl.2:58 build/C/man2/outb.2:87
312 #: build/C/man2/pciconfig_read.2:112 build/C/man2/perf_event_open.2:2756
313 #: build/C/man2/perfmonctl.2:199 build/C/man2/personality.2:73
314 #: build/C/man2/pivot_root.2:128 build/C/man2/process_vm_readv.2:295
315 #: build/C/man2/ptrace.2:1954 build/C/man2/sendfile.2:148
316 #: build/C/man2/set_tid_address.2:97 build/C/man2/splice.2:184
317 #: build/C/man2/tee.2:125 build/C/man2/vm86.2:73 build/C/man2/vmsplice.2:153
319 msgid "CONFORMING TO"
323 #: build/C/man2/arch_prctl.2:107
325 "B<arch_prctl>() is a Linux/x86-64 extension and should not be used in "
326 "programs intended to be portable."
328 "B<arch_prctl>() は Linux/x86-64 拡張であり、移植性を意図したプログラムでは使"
332 #: build/C/man2/arch_prctl.2:107 build/C/man2/futex.2:305
333 #: build/C/man2/get_robust_list.2:118 build/C/man2/getunwind.2:99
334 #: build/C/man2/kexec_load.2:337 build/C/man2/lookup_dcookie.2:81
335 #: build/C/man2/modify_ldt.2:133 build/C/man2/perf_event_open.2:2761
336 #: build/C/man2/perfmonctl.2:202 build/C/man2/pivot_root.2:131
337 #: build/C/man2/process_vm_readv.2:297 build/C/man2/ptrace.2:1956
338 #: build/C/man2/sendfile.2:155 build/C/man2/splice.2:186
339 #: build/C/man2/tee.2:127 build/C/man2/vmsplice.2:155
345 #: build/C/man2/arch_prctl.2:110
347 "B<arch_prctl>() is supported only on Linux/x86-64 for 64-bit programs "
350 "B<arch_prctl>() は現在のところ Linux/x86-64 上の 64 ビットプログラムでのみサ"
354 #: build/C/man2/arch_prctl.2:112
355 msgid "The 64-bit base changes when a new 32-bit segment selector is loaded."
357 "新しい 32 ビットセグメントセレクタがロードされた場合、 64 ビットベースは変更"
361 #: build/C/man2/arch_prctl.2:115
362 msgid "B<ARCH_SET_GS> is disabled in some kernels."
363 msgstr "B<ARCH_SET_GS> が無効にされているカーネルもある。"
366 #: build/C/man2/arch_prctl.2:130
368 "Context switches for 64-bit segment bases are rather expensive. It may be a "
369 "faster alternative to set a 32-bit base using a segment selector by setting "
370 "up an LDT with B<modify_ldt>(2) or using the B<set_thread_area>(2) system "
371 "call in kernel 2.5 or later. B<arch_prctl>() is needed only when you want "
372 "to set bases that are larger than 4GB. Memory in the first 2GB of address "
373 "space can be allocated by using B<mmap>(2) with the B<MAP_32BIT> flag."
375 "64 ビットセグメントベースのコンテキストスイッチは、やや高価である。 LDT を "
376 "B<modify_ldt>(2) で設定してセグメントセレクタを使うか、 (カーネル 2.5 以降"
377 "の) B<set_thread_area>(2) システムコールを使うことにより、 32 ビットベース"
378 "を設定するという高速な代替手段もある。 4GB より大きなベースを設定したい場合に"
379 "のみ、 B<arch_prctl>() が必要である。 アドレス空間の最初の 2GB にあるメモ"
380 "リーは、 B<mmap>(2) に B<MAP_32BIT> フラグを指定して割り当てることができる。"
383 #: build/C/man2/arch_prctl.2:135
385 "As of version 2.7, glibc provides no prototype for B<arch_prctl>(). You "
386 "have to declare it yourself for now. This may be fixed in future glibc "
389 "バージョン 2.7 時点では、glibc には B<arch_prctl>() のプロトタイプがない。 "
390 "今のところユーザーは自分自身で宣言する必要がある。 これは将来の glibc のバー"
394 #: build/C/man2/arch_prctl.2:138
395 msgid "I<FS> may be already used by the threading library."
396 msgstr "I<FS> はスレッドライブラリで既に使われているかもしれない。"
399 #: build/C/man2/arch_prctl.2:138 build/C/man2/futex.2:319
400 #: build/C/man2/get_robust_list.2:127 build/C/man2/getunwind.2:111
401 #: build/C/man2/kexec_load.2:341 build/C/man2/modify_ldt.2:136
402 #: build/C/man2/outb.2:96 build/C/man2/pciconfig_read.2:114
403 #: build/C/man2/perf_event_open.2:2903 build/C/man2/perfmonctl.2:205
404 #: build/C/man2/personality.2:77 build/C/man2/pivot_root.2:143
405 #: build/C/man2/process_vm_readv.2:347 build/C/man2/ptrace.2:2122
406 #: build/C/man2/quotactl.2:507 build/C/man2/sendfile.2:197
407 #: build/C/man2/set_tid_address.2:99 build/C/man2/splice.2:240
408 #: build/C/man2/tee.2:214 build/C/man2/vmsplice.2:164
414 #: build/C/man2/arch_prctl.2:143
415 msgid "B<mmap>(2), B<modify_ldt>(2), B<prctl>(2), B<set_thread_area>(2)"
416 msgstr "B<mmap>(2), B<modify_ldt>(2), B<prctl>(2), B<set_thread_area>(2)"
419 #: build/C/man2/arch_prctl.2:145
420 msgid "AMD X86-64 Programmer's manual"
421 msgstr "AMD X86-64 Programmer's manual"
424 #: build/C/man2/arch_prctl.2:145 build/C/man2/futex.2:333
425 #: build/C/man2/get_robust_list.2:136 build/C/man2/getunwind.2:113
426 #: build/C/man2/kexec_load.2:350 build/C/man2/lookup_dcookie.2:88
427 #: build/C/man2/modify_ldt.2:138 build/C/man2/nfsservctl.2:60
428 #: build/C/man2/outb.2:99 build/C/man2/pciconfig_read.2:116
429 #: build/C/man2/perf_event_open.2:2909 build/C/man2/perfmonctl.2:209
430 #: build/C/man2/personality.2:79 build/C/man2/pivot_root.2:149
431 #: build/C/man2/process_vm_readv.2:350 build/C/man2/ptrace.2:2137
432 #: build/C/man2/quotactl.2:512 build/C/man2/sendfile.2:203
433 #: build/C/man2/set_tid_address.2:103 build/C/man2/splice.2:244
434 #: build/C/man2/tee.2:217 build/C/man2/vm86.2:76 build/C/man2/vmsplice.2:167
440 #: build/C/man2/arch_prctl.2:153 build/C/man2/futex.2:341
441 #: build/C/man2/get_robust_list.2:144 build/C/man2/getunwind.2:121
442 #: build/C/man2/kexec_load.2:358 build/C/man2/lookup_dcookie.2:96
443 #: build/C/man2/modify_ldt.2:146 build/C/man2/nfsservctl.2:68
444 #: build/C/man2/outb.2:107 build/C/man2/pciconfig_read.2:124
445 #: build/C/man2/perf_event_open.2:2917 build/C/man2/perfmonctl.2:217
446 #: build/C/man2/personality.2:87 build/C/man2/pivot_root.2:157
447 #: build/C/man2/process_vm_readv.2:358 build/C/man2/ptrace.2:2145
448 #: build/C/man2/quotactl.2:520 build/C/man2/sendfile.2:211
449 #: build/C/man2/set_tid_address.2:111 build/C/man2/splice.2:252
450 #: build/C/man2/tee.2:225 build/C/man2/vm86.2:84 build/C/man2/vmsplice.2:175
453 #| "This page is part of release 3.78 of the Linux I<man-pages> project. A "
454 #| "description of the project, information about reporting bugs, and the "
455 #| "latest version of this page, can be found at \\%http://www.kernel.org/doc/"
458 "This page is part of release 3.79 of the Linux I<man-pages> project. A "
459 "description of the project, information about reporting bugs, and the latest "
460 "version of this page, can be found at \\%http://www.kernel.org/doc/man-"
463 "この man ページは Linux I<man-pages> プロジェクトのリリース 3.78 の一部\n"
464 "である。プロジェクトの説明とバグ報告に関する情報は\n"
465 "http://www.kernel.org/doc/man-pages/ に書かれている。"
468 #: build/C/man2/futex.2:53
474 #: build/C/man2/futex.2:53
480 #: build/C/man2/futex.2:56
481 msgid "futex - fast user-space locking"
482 msgstr "futex - 高速ユーザー空間ロック"
485 #: build/C/man2/futex.2:61
488 "B<#include E<lt>linux/futex.hE<gt>>\n"
489 "B<#include E<lt>sys/time.hE<gt>>\n"
491 "B<#include E<lt>linux/futex.hE<gt>>\n"
492 "B<#include E<lt>sys/time.hE<gt>>\n"
495 #: build/C/man2/futex.2:64
497 msgid "B<int futex(int *>I<uaddr>B<, int >I<op>B<, int >I<val>B<, const struct timespec *>I<timeout>B<,>\n"
498 msgstr "B<int futex(int *>I<uaddr>B<, int >I<op>B<, int >I<val>B<, const struct timespec *>I<timeout>B<,>\n"
500 #. int *? void *? u32 *?
502 #: build/C/man2/futex.2:67
504 msgid "B< int *>I<uaddr2>B<, int >I<val3>B<);>\n"
505 msgstr "B< int *>I<uaddr2>B<, int >I<val3>B<);>\n"
508 #: build/C/man2/futex.2:70 build/C/man2/getunwind.2:40
509 #: build/C/man2/modify_ldt.2:36 build/C/man2/perf_event_open.2:42
510 #: build/C/man2/perfmonctl.2:39 build/C/man2/pivot_root.2:18
511 msgid "I<Note>: There is no glibc wrapper for this system call; see NOTES."
513 "I<注>: このシステムコールには glibc のラッパー関数は存在しない。「注意」の節"
517 #: build/C/man2/futex.2:86
519 "The B<futex>() system call provides a method for a program to wait for a "
520 "value at a given address to change, and a method to wake up anyone waiting "
521 "on a particular address (while the addresses for the same memory in separate "
522 "processes may not be equal, the kernel maps them internally so the same "
523 "memory mapped in different locations will correspond for B<futex>() "
524 "calls). This system call is typically used to implement the contended case "
525 "of a lock in shared memory, as described in B<futex>(7)."
527 "B<futex>() システムコールは、 指定したアドレスの値が変更されるのをプログラム"
528 "が待つ手段や 特定のアドレスに対して待機中のプロセスを wake (起床) させる手段"
529 "を提供する (プロセスが異なれば同じメモリーに対するアドレスも同じではないかも"
530 "しれないが、 カーネルは異なる位置にマップされた同じメモリーを B<futex>() で"
531 "使えるよう内部でマップする)。 通常は、このシステムコールは B<futex>(7) に書"
532 "かれているように、 共有メモリー中のロックが競合する場合の処理を実装するのに用"
536 #: build/C/man2/futex.2:93
538 "When a B<futex>(7) operation did not finish uncontended in user space, a "
539 "call needs to be made to the kernel to arbitrate. Arbitration can either "
540 "mean putting the calling process to sleep or, conversely, waking a waiting "
543 "B<futex>(7) の操作がユーザー空間で競合なく完了しなかった場合、 カーネルに仲"
544 "裁させるためにシステムコールを呼ぶ必要がある。 仲裁というのは、呼び出しプロセ"
545 "スを sleep (起床待ち) させたり、反対に 待ちプロセスを wake させたりすることを"
549 #: build/C/man2/futex.2:100
551 "Callers of this function are expected to adhere to the semantics as set out "
552 "in B<futex>(7). As these semantics involve writing nonportable assembly "
553 "instructions, this in turn probably means that most users will in fact be "
554 "library authors and not general application developers."
556 "この関数を呼び出すプロセスは B<futex>(7) に記述されているセマンティクスに忠"
557 "実であることが要求される。 このセマンティクスには移植不可能なアセンブリ命令を"
558 "書くことが含まれる。 このことは言い換えると futex のユーザーのほとんどは実際"
559 "はライブラリの作者であり、 一般アプリケーションの開発者ではないということであ"
563 #: build/C/man2/futex.2:108
565 "The I<uaddr> argument needs to point to an aligned integer which stores the "
566 "counter. The operation to execute is passed via the I<op> argument, along "
567 "with a value I<val>."
569 "I<uaddr> 引き数は、カウンターを格納する、 アラインメントの揃った int 型変数を"
570 "指している必要がある。 実行する操作は I<op> 引き数を介して、値 I<val> ととも"
574 #: build/C/man2/futex.2:110
575 msgid "Five operations are currently defined:"
576 msgstr "現在のところ 5 つの操作が定義されている:"
579 #: build/C/man2/futex.2:110 build/C/man2/futex.2:223
581 msgid "B<FUTEX_WAIT>"
582 msgstr "B<FUTEX_WAIT>"
585 #: build/C/man2/futex.2:133
587 "This operation atomically verifies that the futex address I<uaddr> still "
588 "contains the value I<val>, and sleeps awaiting B<FUTEX_WAKE> on this futex "
589 "address. If the I<timeout> argument is non-NULL, its contents specify the "
590 "duration of the wait. (This interval will be rounded up to the system clock "
591 "granularity, and kernel scheduling delays mean that the blocking interval "
592 "may overrun by a small amount.) If I<timeout> is NULL, the call blocks "
593 "indefinitely. The arguments I<uaddr2> and I<val3> are ignored."
595 "この操作は futex アドレス I<uaddr> に指定された値 I<val> がまだ格納されている"
596 "かどうかを不可分操作で検証し、 sleep 状態で この futex アドレスに対して "
597 "B<FUTEX_WAKE> が実行されるのを待つ。 I<timeout> 引き数が NULL でない場合、そ"
598 "の内容は待ち時間の最大値を表す (この停止時間はシステムクロックの粒度に切り上"
599 "げられ、 カーネルのスケジューリング遅延により少しだけ長くなる可能性がある)。 "
600 "NULL の場合、 呼び出しは無限に停止する。 引き数 I<uaddr2> と I<val3> は無視さ"
604 #: build/C/man2/futex.2:141
606 "For B<futex>(7), this call is executed if decrementing the count gave a "
607 "negative value (indicating contention), and will sleep until another process "
608 "releases the futex and executes the B<FUTEX_WAKE> operation."
610 "B<futex>(7) に照らし合わせると、この呼び出しは カウントのデクリメントで負の"
611 "値 (競合を表す) になった場合に実行され、 別のプロセスがその futex を解放し "
612 "B<FUTEX_WAKE> の操作を実行するまで sleep する。"
615 #: build/C/man2/futex.2:141 build/C/man2/futex.2:229
617 msgid "B<FUTEX_WAKE>"
618 msgstr "B<FUTEX_WAKE>"
621 #: build/C/man2/futex.2:152
623 "This operation wakes at most I<val> processes waiting on this futex address "
624 "(i.e., inside B<FUTEX_WAIT>). The arguments I<timeout>, I<uaddr2> and "
625 "I<val3> are ignored."
627 "この操作では指定した futex アドレスに対して待ち状態の (すなわち "
628 "B<FUTEX_WAIT> 中の) 最大 I<val> 個のプロセスを wake させる。 引き数 "
629 "I<timeout>, I<uaddr2>, I<val3> は無視される。"
632 #: build/C/man2/futex.2:158
634 "For B<futex>(7), this is executed if incrementing the count showed that "
635 "there were waiters, once the futex value has been set to 1 (indicating that "
638 "B<futex>(4) に照らし合わせると、 この操作は カウントのインクリメントで待ちプ"
639 "ロセスがあると判明し、 futex 値が 1 に設定された (利用可能であることを表す) "
643 #: build/C/man2/futex.2:158
645 msgid "B<FUTEX_FD> (present up to and including Linux 2.6.25)"
646 msgstr "B<FUTEX_FD> (Linux 2.6.25 以前)"
648 #. , suitable for .BR poll (2).
650 #: build/C/man2/futex.2:174
652 "To support asynchronous wakeups, this operation associates a file descriptor "
653 "with a futex. If another process executes a B<FUTEX_WAKE>, the process will "
654 "receive the signal number that was passed in I<val>. The calling process "
655 "must close the returned file descriptor after use. The arguments "
656 "I<timeout>, I<uaddr2> and I<val3> are ignored."
658 "非同期の wake に対応するため、この操作はファイルディスクリプターを futex に "
659 "関連づける。 別のプロセスが B<FUTEX_WAKE> を実行すると、プロセスは I<val> で"
660 "渡されたシグナル番号のシグナルを受信する。 呼び出しプロセスは使用後、返された"
661 "ファイルディスクリプターを クローズしなければならない。 引き数 I<timeout>, "
662 "I<uaddr2>, I<val3> は無視される。"
665 #: build/C/man2/futex.2:179
667 "To prevent race conditions, the caller should test if the futex has been "
668 "upped after B<FUTEX_FD> returns."
670 "競合状態を防止するため、呼び出しプロセスは B<FUTEX_FD> が返ったあと futex が "
671 "up されたかどうかを確認しなければならない。"
674 #: build/C/man2/futex.2:183
676 "Because it was inherently racy, B<FUTEX_FD> has been removed from Linux "
679 "B<FUTEX_FD> はもともと競合が起きやすかったため、 Linux 2.6.26 以降で削除され"
683 #: build/C/man2/futex.2:183
685 msgid "B<FUTEX_REQUEUE> (since Linux 2.5.70)"
686 msgstr "B<FUTEX_REQUEUE> (Linux 2.5.70 以降)"
689 #: build/C/man2/futex.2:198
691 "This operation was introduced in order to avoid a \"thundering herd\" effect "
692 "when B<FUTEX_WAKE> is used and all processes woken up need to acquire "
693 "another futex. This call wakes up I<val> processes, and requeues all other "
694 "waiters on the futex at address I<uaddr2>. The arguments I<timeout> and "
695 "I<val3> are ignored."
697 "この操作は、 B<FUTEX_WAKE> が使われていて、かつ wake されている全てのプロセス"
698 "が 他の futex を取得する必要がある場合に、 「獣の群れの暴走 (thundering "
699 "herd)」効果を避けるために導入された。 この呼び出しは I<val> 個のプロセスを "
700 "wake し、アドレス I<uaddr2> で futex を待っている他の全てのプロセスを再度"
701 "キューにいれる。 引き数 I<timeout> と I<val3> は無視される。"
704 #: build/C/man2/futex.2:198
706 msgid "B<FUTEX_CMP_REQUEUE> (since Linux 2.6.7)"
707 msgstr "B<FUTEX_CMP_REQUEUE> (Linux 2.6.7 以降)"
710 #: build/C/man2/futex.2:216
712 "There was a race in the intended use of B<FUTEX_REQUEUE>, so "
713 "B<FUTEX_CMP_REQUEUE> was introduced. This is similar to B<FUTEX_REQUEUE>, "
714 "but first checks whether the location I<uaddr> still contains the value "
715 "I<val3>. If not, the operation fails with the error B<EAGAIN>. The "
716 "argument I<timeout> is ignored."
718 "故意に B<FUTEX_REQUEUE> を使う場合に競合が起こるため、 B<FUTEX_CMP_REQUEUE> "
719 "が導入された。これは B<FUTEX_REQUEUE> と似ているが、場所 I<uaddr> に値 "
720 "I<val3> がまだ保持されているかを最初にチェックする。 保持されていない場合、操"
721 "作はエラー B<EAGAIN> で失敗する。引き数 I<timeout> は無視される。"
724 #: build/C/man2/futex.2:223
726 "In the event of an error, all operations return -1, and set I<errno> to "
727 "indicate the error. The return value on success depends on the operation, "
728 "as described in the following list:"
730 "エラーの場合、全ての操作で -1 が返り、 I<errno> がエラーの内容を示す値に設定"
731 "される。成功時の返り値は操作によって異なり、以下のリストに書かれている通りで"
735 #: build/C/man2/futex.2:229
737 "Returns 0 if the process was woken by a B<FUTEX_WAKE> call. See ERRORS for "
738 "the various possible error returns."
740 "そのプロセスが B<FUTEX_WAKE> により wake された場合 0 を返す。発生する可能性"
741 "があるエラーについては「エラー」の節を参照。"
744 #: build/C/man2/futex.2:232 build/C/man2/futex.2:238 build/C/man2/futex.2:241
745 msgid "Returns the number of processes woken up."
746 msgstr "wake したプロセスの数を返す。"
749 #: build/C/man2/futex.2:232
755 #: build/C/man2/futex.2:235
756 msgid "Returns the new file descriptor associated with the futex."
757 msgstr "futex に関連づけられた新たなファイルディスクリプターを返す。"
760 #: build/C/man2/futex.2:235
762 msgid "B<FUTEX_REQUEUE>"
763 msgstr "B<FUTEX_REQUEUE>"
766 #: build/C/man2/futex.2:238
768 msgid "B<FUTEX_CMP_REQUEUE>"
769 msgstr "B<FUTEX_CMP_REQUEUE>"
772 #: build/C/man2/futex.2:242 build/C/man2/perf_event_open.2:2635
773 #: build/C/man2/quotactl.2:486
779 #: build/C/man2/futex.2:245
780 msgid "No read access to futex memory."
781 msgstr "futex メモリーに読み込みアクセス権がなかった。"
784 #: build/C/man2/futex.2:245 build/C/man2/sendfile.2:116
785 #: build/C/man2/splice.2:151 build/C/man2/tee.2:101
786 #: build/C/man2/vmsplice.2:127
792 #: build/C/man2/futex.2:256
794 "B<FUTEX_CMP_REQUEUE> detected that the value pointed to by I<uaddr> is not "
795 "equal to the expected value I<val3>. (This probably indicates a race; use "
796 "the safe B<FUTEX_WAKE> now.)"
798 "B<FUTEX_CMP_REQUEUE> で、I<uaddr> が指す値が期待値 I<val3> と異なる状況が検出"
799 "された。 (これは競合を示しているかもしれない。この場合は安全な B<FUTEX_WAKE> "
803 #: build/C/man2/futex.2:261
804 msgid "Error retrieving I<timeout> information from user space."
805 msgstr "ユーザー空間から I<timeout> の情報を取得する際にエラーが発生した。"
808 #: build/C/man2/futex.2:261
814 #: build/C/man2/futex.2:268
816 "A B<FUTEX_WAIT> operation was interrupted by a signal (see B<signal>(7)) or "
819 "B<FUTEX_WAIT> 操作がシグナル (B<signal>(7) 参照) もしくは偽の wakeup により中"
823 #: build/C/man2/futex.2:271
824 msgid "Invalid argument."
828 #: build/C/man2/futex.2:271
834 #: build/C/man2/futex.2:274
835 msgid "The system limit on the total number of open files has been reached."
836 msgstr "オープンされているファイルの総数がシステムの制限に達した。"
839 #: build/C/man2/futex.2:274 build/C/man2/modify_ldt.2:126
840 #: build/C/man2/pciconfig_read.2:93 build/C/man2/perf_event_open.2:2718
841 #: build/C/man2/quotactl.2:447 build/C/man2/vm86.2:64
847 #: build/C/man2/futex.2:278
848 msgid "Invalid operation specified in I<op>."
849 msgstr "I<op> に無効な操作が指定された。"
852 #: build/C/man2/futex.2:278
855 msgstr "B<ETIMEDOUT>"
858 #: build/C/man2/futex.2:283
859 msgid "Timeout during the B<FUTEX_WAIT> operation."
860 msgstr "B<FUTEX_WAIT> 操作でタイムアウトが発生した。"
863 #: build/C/man2/futex.2:283
865 msgid "B<EWOULDBLOCK>"
866 msgstr "B<EWOULDBLOCK>"
869 #: build/C/man2/futex.2:293
871 "I<op> was B<FUTEX_WAIT> and the value pointed to by I<uaddr> was not equal "
872 "to the expected value I<val> at the time of the call."
874 "I<op> が B<FUTEX_WAIT> で、その呼び出しにおいて I<uaddr> が指す値が期待値 "
878 #: build/C/man2/futex.2:293 build/C/man2/get_robust_list.2:116
879 #: build/C/man2/getunwind.2:94 build/C/man2/kexec_load.2:328
880 #: build/C/man2/lookup_dcookie.2:73 build/C/man2/perfmonctl.2:196
881 #: build/C/man2/pivot_root.2:125 build/C/man2/process_vm_readv.2:292
882 #: build/C/man2/sendfile.2:142 build/C/man2/set_tid_address.2:94
883 #: build/C/man2/splice.2:179 build/C/man2/tee.2:120
884 #: build/C/man2/vmsplice.2:148
890 #: build/C/man2/futex.2:303
892 "Initial futex support was merged in Linux 2.5.7 but with different semantics "
893 "from what was described above. A 4-argument system call with the semantics "
894 "described in this page was introduced in Linux 2.5.40. In Linux 2.5.70, one "
895 "argument was added. In Linux 2.6.7, a sixth argument was added\\(emmessy, "
896 "especially on the s390 architecture."
898 "最初の futex 対応は Linux 2.5.7 で組み込まれたが、 上記のセマンティクスとは異"
899 "なる。 4 つの引き数のここに書かれているセマンティクスを持つ システムコール"
900 "は、Linux 2.5.40 で導入された。 Linux 2.5.70 では 1 つの引き数が追加された。 "
901 "Linux 2.6.7 では 6 番目の引き数が追加された。 これは汚く、s390 アーキテク"
905 #: build/C/man2/futex.2:305 build/C/man2/set_tid_address.2:99
906 #: build/C/man2/splice.2:186 build/C/man2/tee.2:127
907 #: build/C/man2/vmsplice.2:155
908 msgid "This system call is Linux-specific."
909 msgstr "このシステムコールは Linux 固有である。"
913 #. Futexes were designed and worked on by
914 #. Hubertus Franke (IBM Thomas J. Watson Research Center),
915 #. Matthew Kirkwood, Ingo Molnar (Red Hat)
916 #. and Rusty Russell (IBM Linux Technology Center).
917 #. This page written by bert hubert.
919 #: build/C/man2/futex.2:319
921 "To reiterate, bare futexes are not intended as an easy-to-use abstraction "
922 "for end-users. (There is no wrapper function for this system call in "
923 "glibc.) Implementors are expected to be assembly literate and to have read "
924 "the sources of the futex user-space library referenced below."
926 "繰り返すが、裸の futex はエンドユーザーが容易に使うことのできる概念として 意"
927 "図されたものではない (glibc にはこのシステムコールに対するラッパー関数はな"
928 "い)。 実装者は、アセンブリ言語に慣れており、以下に挙げる futex ユーザー空間ラ"
929 "イブラリの ソースを読み終えていることが要求される。"
932 #: build/C/man2/futex.2:322
933 msgid "B<restart_syscall>(2), B<futex>(7)"
934 msgstr "B<restart_syscall>(2), B<futex>(7)"
937 #: build/C/man2/futex.2:325
939 "I<Fuss, Futexes and Furwocks: Fast Userlevel Locking in Linux> (proceedings "
940 "of the Ottawa Linux Symposium 2002), online at"
942 "I<Fuss, Futexes and Furwocks: Fast Userlevel Locking in Linux> (proceedings "
943 "of the Ottawa Linux Symposium 2002), online at"
946 #: build/C/man2/futex.2:328
948 "E<.UR http://kernel.org\\:/doc\\:/ols\\:/2002\\:/ols2002-pages-479-495.pdf> "
951 "E<.UR http://kernel.org\\:/doc\\:/ols\\:/2002\\:/ols2002-pages-479-495.pdf> "
955 #: build/C/man2/futex.2:330
956 msgid "Futex example library, futex-*.tar.bz2 at"
957 msgstr "futex の使用例ライブラリ, futex-*.tar.bz2"
960 #: build/C/man2/futex.2:333
962 "E<.UR ftp://ftp.kernel.org\\:/pub\\:/linux\\:/kernel\\:/people\\:/rusty/> E<."
965 "E<.UR ftp://ftp.kernel.org\\:/pub\\:/linux\\:/kernel\\:/people\\:/rusty/> E<."
969 #: build/C/man2/get_robust_list.2:29
971 msgid "GET_ROBUST_LIST"
972 msgstr "GET_ROBUST_LIST"
975 #: build/C/man2/get_robust_list.2:29 build/C/man2/ptrace.2:46
981 #: build/C/man2/get_robust_list.2:29
983 msgid "Linux System Calls"
984 msgstr "Linux System Calls"
987 #: build/C/man2/get_robust_list.2:32
988 msgid "get_robust_list, set_robust_list - get/set list of robust futexes"
992 #: build/C/man2/get_robust_list.2:37
995 "B<#include E<lt>linux/futex.hE<gt>>\n"
996 "B<#include E<lt>sys/types.hE<gt>>\n"
997 "B<#include E<lt>syscall.hE<gt>>\n"
999 "B<#include E<lt>linux/futex.hE<gt>>\n"
1000 "B<#include E<lt>sys/types.hE<gt>>\n"
1001 "B<#include E<lt>syscall.hE<gt>>\n"
1004 #: build/C/man2/get_robust_list.2:41
1007 "B<long get_robust_list(int >I<pid>B<, struct robust_list_head **>I<head_ptr>B<,>\n"
1008 "B< size_t *>I<len_ptr>B<);>\n"
1009 "B<long set_robust_list(struct robust_list_head *>I<head>B<, size_t >I<len>B<);>\n"
1013 #: build/C/man2/get_robust_list.2:45 build/C/man2/kexec_load.2:47
1014 msgid "I<Note>: There are no glibc wrappers for these system calls; see NOTES."
1016 "I<注意>: これらのシステムコールには glibc ラッパー関数は存在しない。 「注意」"
1020 #: build/C/man2/get_robust_list.2:50
1022 "The robust futex implementation needs to maintain per-thread lists of robust "
1023 "futexes which are unlocked when the thread exits. These lists are managed "
1024 "in user space; the kernel is notified about only the location of the head of "
1029 #: build/C/man2/get_robust_list.2:66
1031 "The B<get_robust_list>() system call returns the head of the robust futex "
1032 "list of the thread whose thread ID is specified in I<pid>. If I<pid> is 0, "
1033 "the head of the list for the calling thread is returned. The list head is "
1034 "stored in the location pointed to by I<head_ptr>. The size of the object "
1035 "pointed to by I<**head_ptr> is stored in I<len_ptr>."
1039 #: build/C/man2/get_robust_list.2:78
1041 "The B<set_robust_list>() system call requests the kernel to record the head "
1042 "of the list of robust futexes owned by the calling thread. The I<head> "
1043 "argument is the list head to record. The I<len> argument should be "
1048 #: build/C/man2/get_robust_list.2:85
1050 "The B<set_robust_list>() and B<get_robust_list>() system calls return zero "
1051 "when the operation is successful, an error code otherwise."
1055 #: build/C/man2/get_robust_list.2:89
1057 "The B<set_robust_list>() system call can fail with the following error:"
1061 #: build/C/man2/get_robust_list.2:95
1063 "I<len> does not match the size of structure B<struct robust_list_head> "
1064 "expected by kernel."
1068 #: build/C/man2/get_robust_list.2:99
1070 "The B<get_robust_list>() system call can fail with the following errors:"
1074 #: build/C/man2/get_robust_list.2:107
1076 "The calling process does not have permission to see the robust futex list of "
1077 "the thread with the thread ID I<pid>, and does not have the "
1078 "B<CAP_SYS_PTRACE> capability."
1082 #: build/C/man2/get_robust_list.2:107 build/C/man2/perf_event_open.2:2746
1083 #: build/C/man2/process_vm_readv.2:287 build/C/man2/ptrace.2:1949
1084 #: build/C/man2/quotactl.2:461 build/C/man2/quotactl.2:504
1090 #: build/C/man2/get_robust_list.2:112
1091 msgid "No thread with the thread ID I<pid> could be found."
1095 #: build/C/man2/get_robust_list.2:116
1097 "The head of the robust futex list can't be stored at the location I<head>."
1101 #: build/C/man2/get_robust_list.2:118
1102 msgid "These system calls were added in Linux 2.6.17."
1103 msgstr "これらのシステムコールは Linux 2.6.17 で追加された。"
1106 #: build/C/man2/get_robust_list.2:123
1108 "These system calls are not needed by normal applications. No support for "
1109 "them is provided in glibc. In the unlikely event that you want to call them "
1110 "directly, use B<syscall>(2)."
1112 "通常のアプリケーションでは、これらのシステムコールは必要ではない。 glibc によ"
1113 "るサポートは提供されていない。おそらくないと思うが、このシステムコールを直接"
1114 "呼び出したい場合は B<syscall>(2) を使うこと。"
1117 #: build/C/man2/get_robust_list.2:127
1119 "A thread can have only one robust futex list; therefore applications that "
1120 "wish to use this functionality should use the robust mutexes provided by "
1124 #. .BR pthread_mutexattr_setrobust_np (3)
1126 #: build/C/man2/get_robust_list.2:130
1128 msgstr "B<futex>(2)"
1130 #. http://lwn.net/Articles/172149/
1132 #: build/C/man2/get_robust_list.2:136
1134 "I<Documentation/robust-futexes.txt> and I<Documentation/robust-futex-ABI."
1135 "txt> in the Linux kernel source tree"
1139 #: build/C/man2/getunwind.2:27
1145 #: build/C/man2/getunwind.2:27
1151 #: build/C/man2/getunwind.2:30
1152 msgid "getunwind - copy the unwind data to caller's buffer"
1156 #: build/C/man2/getunwind.2:34
1159 "B<#include E<lt>syscall.hE<gt>>\n"
1160 "B<#include E<lt>linux/unwind.hE<gt>>\n"
1162 "B<#include E<lt>syscall.hE<gt>>\n"
1163 "B<#include E<lt>linux/unwind.hE<gt>>\n"
1166 #: build/C/man2/getunwind.2:36
1168 msgid "B<long getunwind(void >I<*buf>B<, size_t >I<buf_size>B<);>\n"
1172 #: build/C/man2/getunwind.2:42
1173 msgid "I<Note: this function is obsolete.>"
1177 #: build/C/man2/getunwind.2:52
1179 "The IA-64-specific B<getunwind>() system call copies the kernel's call "
1180 "frame unwind data into the buffer pointed to by I<buf> and returns the size "
1181 "of the unwind data; this data describes the gate page (kernel code that is "
1182 "mapped into user space)."
1186 #: build/C/man2/getunwind.2:64
1188 "The size of the buffer I<buf> is specified in I<buf_size>. The data is "
1189 "copied only if I<buf_size> is greater than or equal to the size of the "
1190 "unwind data and I<buf> is not NULL; otherwise, no data is copied, and the "
1191 "call succeeds, returning the size that would be needed to store the unwind "
1196 #: build/C/man2/getunwind.2:68
1198 "The first part of the unwind data contains an unwind table. The rest "
1199 "contains the associated unwind information, in no particular order. The "
1200 "unwind table contains entries of the following form:"
1204 #: build/C/man2/getunwind.2:73
1207 " u64 start; (64-bit address of start of function)\n"
1208 " u64 end; (64-bit address of end of function)\n"
1209 " u64 info; (BUF-relative offset to unwind info)\n"
1213 #: build/C/man2/getunwind.2:81
1215 "An entry whose I<start> value is zero indicates the end of the table. For "
1216 "more information about the format, see the I<IA-64 Software Conventions and "
1217 "Runtime Architecture> manual."
1221 #: build/C/man2/getunwind.2:88
1223 "On success, B<getunwind>() returns the size of the unwind data. On error, "
1224 "-1 is returned and I<errno> is set to indicate the error."
1226 "成功すると、 B<getunwind> は unwind されたデータのサイズを返す。 エラーの場"
1227 "合、 -1 が返り、 I<errno> にエラーを示す値が設定される。"
1230 #: build/C/man2/getunwind.2:94
1232 "B<getunwind>() fails with the error B<EFAULT> if the unwind info can't be "
1233 "stored in the space specified by I<buf>."
1237 #: build/C/man2/getunwind.2:96
1238 msgid "This system call is available since Linux 2.4."
1242 #: build/C/man2/getunwind.2:99
1244 "This system call is Linux-specific, and is available only on the IA-64 "
1249 #: build/C/man2/getunwind.2:107
1251 "This system call has been deprecated. The modern way to obtain the kernel's "
1252 "unwind data is via the gate DSO. The address of the ELF header for this DSO "
1253 "is passed to user level via B<AT_SYSINFO_EHDR> (see B<getauxval>(3))."
1257 #: build/C/man2/getunwind.2:111
1259 "Glibc does not provide a wrapper for this system call; in the unlikely event "
1260 "that you want to call it, use B<syscall>(2)."
1262 "glibc はこのシステムコールに対するラッパー関数を提供していない。おそらくない"
1263 "と思うが、このシステムコールを呼び出したい場合は B<syscall>(2) を使うこと。"
1266 #: build/C/man2/getunwind.2:113
1267 msgid "B<getauxval>(3)"
1268 msgstr "B<getauxval>(3)"
1271 #: build/C/man2/kexec_load.2:27
1277 #: build/C/man2/kexec_load.2:27 build/C/man2/personality.2:32
1279 #| msgid "2015-01-10"
1284 #: build/C/man2/kexec_load.2:30
1286 #| msgid "kexec_load - load a new kernel for later execution"
1287 msgid "kexec_load, kexec_file_load - load a new kernel for later execution"
1288 msgstr "kexec_load - 新しいカーネルを後で実行するためにロードする"
1291 #: build/C/man2/kexec_load.2:33
1293 #| msgid "B<#include E<lt>linux/kexec.hE<gt>>"
1294 msgid "B<#include E<lt>linux/kexec.hE<gt>>\n"
1295 msgstr "B<#include E<lt>linux/kexec.hE<gt>>"
1298 #: build/C/man2/kexec_load.2:37
1300 #| msgid "B<long kexec_load(unsigned long >I<entry>B<, unsigned long >I<nr_segments>B<,>"
1302 "B<long kexec_load(unsigned long >I<entry>B<, unsigned long >I<nr_segments>B<,>\n"
1303 "B< struct kexec_segment *>I<segments>B<, unsigned long >I<flags>B<);>\n"
1304 msgstr "B<long kexec_load(unsigned long >I<entry>B<, unsigned long >I<nr_segments>B<,>"
1307 #: build/C/man2/kexec_load.2:39
1309 #| msgid "B<long kexec_load(unsigned long >I<entry>B<, unsigned long >I<nr_segments>B<,>"
1310 msgid "B<long kexec_file_load(int >I<kernel_fd>B<, int >I<initrd_fd>B<,>\n"
1311 msgstr "B<long kexec_load(unsigned long >I<entry>B<, unsigned long >I<nr_segments>B<,>"
1314 #: build/C/man2/kexec_load.2:43
1317 #| "B<int perf_event_open(struct perf_event_attr *>I<attr>B<,>\n"
1318 #| "B< pid_t >I<pid>B<, int >I<cpu>B<, int >I<group_fd>B<,>\n"
1319 #| "B< unsigned long >I<flags>B<);>\n"
1321 "B< unsigned long >I<cmdline_len>B<, const char *>I<cmdline>B<,>\n"
1322 "B< unsigned long >I<flags>B<);>\n"
1324 "B<int perf_event_open(struct perf_event_attr *>I<attr>B<,>\n"
1325 "B< pid_t >I<pid>B<, int >I<cpu>B<, int >I<group_fd>B<,>\n"
1326 "B< unsigned long >I<flags>B<);>\n"
1329 #: build/C/man2/kexec_load.2:52
1331 "The B<kexec_load>() system call loads a new kernel that can be executed "
1332 "later by B<reboot>(2)."
1334 "B<kexec_load>() システムコールは、新しいカーネルをロードし、\n"
1335 "その後の B<reboot>(2) で実行できるようにする。"
1338 #: build/C/man2/kexec_load.2:58
1340 "The I<flags> argument is a bit mask that controls the operation of the "
1341 "call. The following values can be specified in I<flags>:"
1343 "I<flags> 引き数は、システムコールの呼び出しの動作を制御するマスクビットであ"
1344 "る。 I<flags> には以下の値を指定できる。"
1347 #: build/C/man2/kexec_load.2:58
1349 msgid "B<KEXEC_ON_CRASH> (since Linux 2.6.13)"
1350 msgstr "B<KEXEC_ON_CRASH> (Linux 2.6.13 以降)"
1353 #: build/C/man2/kexec_load.2:74
1355 "Execute the new kernel automatically on a system crash. This \"crash kernel"
1356 "\" is loaded into an area of reserved memory that is determined at boot time "
1357 "using the I<craskkernel> kernel command-line parameter. The location of "
1358 "this reserved memory is exported to user space via the I</proc/iomem> file, "
1359 "in an entry labeled \"Crash kernel\". A user-space application can parse "
1360 "this file and prepare a list of segments (see below) that specify this "
1361 "reserved memory as destination. If this flag is specified, the kernel "
1362 "checks that the target segments specified in I<segments> fall within the "
1367 #: build/C/man2/kexec_load.2:74
1369 msgid "B<KEXEC_PRESERVE_CONTEXT> (since Linux 2.6.27)"
1370 msgstr "B<KEXEC_PRESERVE_CONTEXT> (Linux 2.6.27 以降)"
1373 #: build/C/man2/kexec_load.2:84
1375 "Preserve the system hardware and software states before executing the new "
1376 "kernel. This could be used for system suspend. This flag is available only "
1377 "if the kernel was configured with B<CONFIG_KEXEC_JUMP>, and is effective "
1378 "only if I<nr_segments> is greater than 0."
1381 "システムのハードウェアとソフトウェアの状態を保存する。\n"
1382 "システムの中断時 (suspend) などで使用できる。\n"
1383 "このフラグは、カーネルの設定で B<CONFIG_KEXEC_JUMP> が有効の場合のみ\n"
1384 "利用可能であり、 I<nr_segments> が 0 より大きい場合のみ効果がある。"
1387 #: build/C/man2/kexec_load.2:105
1389 "The high-order bits (corresponding to the mask 0xffff0000) of I<flags> "
1390 "contain the architecture of the to-be-executed kernel. Specify (OR) the "
1391 "constant B<KEXEC_ARCH_DEFAULT> to use the current architecture, or one of "
1392 "the following architecture constants B<KEXEC_ARCH_386>, B<KEXEC_ARCH_68K>, "
1393 "B<KEXEC_ARCH_X86_64>, B<KEXEC_ARCH_PPC>, B<KEXEC_ARCH_PPC64>, "
1394 "B<KEXEC_ARCH_IA_64>, B<KEXEC_ARCH_ARM>, B<KEXEC_ARCH_S390>, "
1395 "B<KEXEC_ARCH_SH>, B<KEXEC_ARCH_MIPS>, and B<KEXEC_ARCH_MIPS_LE>. The "
1396 "architecture must be executable on the CPU of the system."
1398 "I<flags> の上位ビット (マスク 0xffff0000 に対応) には、\n"
1399 "実行されるカーネルのアーキテクチャーが入る。\n"
1400 "現在のアーキテクチャーを使うことを意味する定数 B<KEXEC_ARCH_DEFAULT> か、\n"
1401 "アーキテクチャー定数 B<KEXEC_ARCH_386>, B<KEXEC_ARCH_68K>, "
1402 "B<KEXEC_ARCH_X86_64>,\n"
1403 "B<KEXEC_ARCH_PPC>, B<KEXEC_ARCH_PPC64>, B<KEXEC_ARCH_IA_64>,\n"
1404 "B<KEXEC_ARCH_ARM>, B<KEXEC_ARCH_S390>, B<KEXEC_ARCH_SH>,\n"
1405 "B<KEXEC_ARCH_MIPS>, B<KEXEC_ARCH_MIPS_LE> の\n"
1406 "いずれか一つを (OR で) 指定する。指定するアーキテクチャーは、\n"
1407 "システムの CPU で実行可能なものでなければならない。"
1410 #: build/C/man2/kexec_load.2:120
1412 "The I<entry> argument is the physical entry address in the kernel image. "
1413 "The I<nr_segments> argument is the number of segments pointed to by the "
1414 "I<segments> pointer; the kernel imposes an (arbitrary) limit of 16 on the "
1415 "number of segments. The I<segments> argument is an array of "
1416 "I<kexec_segment> structures which define the kernel layout:"
1418 "I<entry> 引き数は、カーネルイメージの物理エントリーアドレスである。 "
1419 "I<nr_segments> 引き数は、 I<segments> ポインターが指すセグメントの数である。 "
1420 "なお、セグメント数には、カーネルにより 16 という (強制的な) 上限が課される。 "
1421 "I<segments> 引き数は I<kexec_segment> 構造体の配列で、 この構造体によりカーネ"
1425 #: build/C/man2/kexec_load.2:129
1428 "struct kexec_segment {\n"
1429 " void *buf; /* Buffer in user space */\n"
1430 " size_t bufsz; /* Buffer length in user space */\n"
1431 " void *mem; /* Physical address of kernel */\n"
1432 " size_t memsz; /* Physical address length */\n"
1435 "struct kexec_segment {\n"
1436 " void *buf; /* Buffer in user space */\n"
1437 " size_t bufsz; /* Buffer length in user space */\n"
1438 " void *mem; /* Physical address of kernel */\n"
1439 " size_t memsz; /* Physical address length */\n"
1443 #: build/C/man2/kexec_load.2:146
1445 "The kernel image defined by I<segments> is copied from the calling process "
1446 "into the kernel either in regular memory or in reserved memory (if "
1447 "B<KEXEC_ON_CRASH> is set). The kernel first performs various sanity checks "
1448 "on the information passed in I<segments>. If these checks pass, the kernel "
1449 "copies the segment data to kernel memory. Each segment specified in "
1450 "I<segments> is copied as follows:"
1454 #: build/C/man2/kexec_load.2:146 build/C/man2/kexec_load.2:157
1455 #: build/C/man2/kexec_load.2:164 build/C/man2/perf_event_open.2:1238
1456 #: build/C/man2/perf_event_open.2:1256 build/C/man2/ptrace.2:1735
1457 #: build/C/man2/ptrace.2:1745 build/C/man2/ptrace.2:1753
1458 #: build/C/man2/ptrace.2:1759 build/C/man2/ptrace.2:1888
1459 #: build/C/man2/splice.2:55 build/C/man2/splice.2:61 build/C/man2/splice.2:70
1465 #: build/C/man2/kexec_load.2:157
1467 "I<buf> and I<bufsz> identify a memory region in the caller's virtual address "
1468 "space that is the source of the copy. The value in I<bufsz> may not exceed "
1469 "the value in the I<memsz> field."
1473 #: build/C/man2/kexec_load.2:164
1475 "I<mem> and I<memsz> specify a physical address range that is the target of "
1476 "the copy. The values specified in both fields must be multiples of the "
1481 #: build/C/man2/kexec_load.2:172
1483 "I<bufsz> bytes are copied from the source buffer to the target kernel "
1484 "buffer. If I<bufsz> is less than I<memsz>, then the excess bytes in the "
1485 "kernel buffer are zeroed out."
1489 #: build/C/man2/kexec_load.2:181
1491 "In case of a normal kexec (i.e., the B<KEXEC_ON_CRASH> flag is not set), the "
1492 "segment data is loaded in any available memory and is moved to the final "
1493 "destination at kexec reboot time (e.g., when the B<kexec>(8) command is "
1494 "executed with the I<-e> option)."
1498 #: build/C/man2/kexec_load.2:187
1500 "In case of kexec on panic (i.e., the B<KEXEC_ON_CRASH> flag is set), the "
1501 "segment data is loaded to reserved memory at the time of the call, and, "
1502 "after a crash, the kexec mechanism simply passes control to that kernel."
1506 #: build/C/man2/kexec_load.2:192
1509 #| "This system call is available only if the kernel was configured with "
1510 #| "B<CONFIG_KEXEC>."
1512 "The B<kexec_load>() system call is available only if the kernel was "
1513 "configured with B<CONFIG_KEXEC>."
1515 "このシステムコールは、カーネルの設定で B<CONFIG_KEXEC> が有効になって\n"
1519 #: build/C/man2/kexec_load.2:192
1521 msgid "kexec_file_load()"
1525 #: build/C/man2/kexec_load.2:211
1527 "The B<kexec_file_load>() system call is similar to B<kexec_load>(), but it "
1528 "takes a different set of arguments. It reads the kernel to be loaded from "
1529 "the file referred to by the descriptor I<kernel_fd>, and the initrd (initial "
1530 "RAM disk) to be loaded from file referred to by the descriptor "
1531 "I<initrd_fd>. The I<cmdline> argument is a pointer to a buffer containing "
1532 "the command line for the new kernel. The I<cmdline_len> argument specifies "
1533 "size of the buffer. The last byte in the buffer must be a null byte (\\(aq"
1538 #: build/C/man2/kexec_load.2:217
1541 #| "The I<flags> argument is a bit mask that controls the operation of the "
1542 #| "call. The following values can be specified in I<flags>:"
1544 "The I<flags> argument is a bit mask which modifies the behavior of the "
1545 "call. The following values can be specified in I<flags>:"
1547 "I<flags> 引き数は、システムコールの呼び出しの動作を制御するマスクビットであ"
1548 "る。 I<flags> には以下の値を指定できる。"
1551 #: build/C/man2/kexec_load.2:217
1553 #| msgid "KEXEC_LOAD"
1554 msgid "B<KEXEC_FILE_UNLOAD>"
1558 #: build/C/man2/kexec_load.2:220
1559 msgid "Unload the currently loaded kernel."
1563 #: build/C/man2/kexec_load.2:220
1565 msgid "B<KEXEC_FILE_ON_CRASH>"
1569 #: build/C/man2/kexec_load.2:226
1571 "Load the new kernel in the memory region reserved for the crash kernel (as "
1572 "for B<KEXEC_ON_CRASH).> This kernel is booted if the currently running "
1577 #: build/C/man2/kexec_load.2:226
1579 msgid "B<KEXEC_FILE_NO_INITRAMFS>"
1583 #: build/C/man2/kexec_load.2:233
1585 "Loading initrd/initramfs is optional. Specify this flag if no initramfs is "
1586 "being loaded. If this flag is set, the value passed in I<initrd_fd> is "
1590 #. See also http://lwn.net/Articles/603116/
1592 #: build/C/man2/kexec_load.2:242
1594 "The B<kexec_file_load>() system call was added to provide support for "
1595 "systems where \"kexec\" loading should be restricted to only kernels that "
1596 "are signed. This system call is available only if the kernel was configured "
1597 "with B<CONFIG_KEXEC_FILE>."
1601 #: build/C/man2/kexec_load.2:247
1604 #| "On success, B<kexec_load>() returns 0. On error, -1 is returned and "
1605 #| "I<errno> is set to indicate the error."
1607 "On success, these system calls returns 0. On error, -1 is returned and "
1608 "I<errno> is set to indicate the error."
1610 "成功すると、 B<kexec_load> は 0 を返す。\n"
1611 "エラーの場合、 -1 が返り、 I<errno> にエラーを示す値が設定される。"
1614 #: build/C/man2/kexec_load.2:248 build/C/man2/kexec_load.2:260
1616 msgid "B<EADDRNOTAVAIL>"
1619 #. See kernel/kexec.::sanity_check_segment_list in the 3.19 kernel source
1621 #: build/C/man2/kexec_load.2:260
1623 "The B<KEXEC_ON_CRASH> flags was specified, but the region specified by the "
1624 "I<mem> and I<memsz> fields of one of the I<segments> entries lies outside "
1625 "the range of memory reserved for the crash kernel."
1629 #: build/C/man2/kexec_load.2:269
1631 "The value in a I<mem> or I<memsz> field in one of the I<segments> entries is "
1632 "not a multiple of the system page size."
1636 #: build/C/man2/kexec_load.2:269 build/C/man2/perf_event_open.2:2649
1637 #: build/C/man2/sendfile.2:121 build/C/man2/splice.2:157
1638 #: build/C/man2/vmsplice.2:133
1644 #: build/C/man2/kexec_load.2:275
1646 #| msgid "I<new_root> or I<put_old> is not a directory."
1647 msgid "I<kernel_fd> or I<initrd_fd> is not a valid file descriptor."
1648 msgstr "I<new_root> または I<put_old> がディレクトリでない。"
1651 #: build/C/man2/kexec_load.2:275 build/C/man2/pivot_root.2:110
1652 #: build/C/man2/ptrace.2:1912 build/C/man2/quotactl.2:495
1658 #: build/C/man2/kexec_load.2:279
1660 "Another crash kernel is already being loaded or a crash kernel is already in "
1663 "別のクラッシュカーネルがすでにロードされているか、\n"
1664 "クラッシュカーネルがすでに使用されている。"
1667 #: build/C/man2/kexec_load.2:283
1669 #| msgid "I<flags> is not 0."
1670 msgid "I<flags> is invalid."
1671 msgstr "I<flags> が 0 でない。"
1674 #: build/C/man2/kexec_load.2:292
1676 "The value of a I<bufsz> field in one of the I<segments> entries exceeds the "
1677 "value in the corresponding I<memsz> field."
1681 #: build/C/man2/kexec_load.2:298
1682 msgid "I<nr_segments> exceeds B<KEXEC_SEGMENT_MAX> (16)."
1686 #: build/C/man2/kexec_load.2:301
1687 msgid "Two or more of the kernel target buffers overlap."
1691 #: build/C/man2/kexec_load.2:306
1692 msgid "The value in I<cmdline[cmdline_len-1]> is not \\(aq\\e0\\(aq."
1696 #: build/C/man2/kexec_load.2:313
1698 "The file referred to by I<kernel_fd> or I<initrd_fd> is empty (length zero)."
1702 #: build/C/man2/kexec_load.2:313 build/C/man2/lookup_dcookie.2:61
1703 #: build/C/man2/process_vm_readv.2:278 build/C/man2/sendfile.2:138
1704 #: build/C/man2/splice.2:169 build/C/man2/tee.2:117
1705 #: build/C/man2/vmsplice.2:145
1711 #: build/C/man2/kexec_load.2:316
1713 #| msgid "Out of memory."
1714 msgid "Could not allocate memory."
1718 #: build/C/man2/kexec_load.2:316
1720 #| msgid "B<ENOENT>"
1725 #: build/C/man2/kexec_load.2:323
1727 "I<kernel_fd> does not refer to an open file, or the kernel can't load this "
1728 "file. Currently, the file must be a bzImage and contain an x86 kernel that "
1729 "is loadable above 4GiB in memory (see the kernel source file I<Documentation/"
1734 #: build/C/man2/kexec_load.2:328
1735 msgid "The caller does not have the B<CAP_SYS_BOOT> capability."
1736 msgstr "呼び出し側が B<CAP_SYS_BOOT> ケーパビリティを持っていない。"
1739 #: build/C/man2/kexec_load.2:335
1741 #| msgid "The B<kexec_load>() system call first appeared in Linux 2.6.13."
1743 "The B<kexec_load>() system call first appeared in Linux 2.6.13. The "
1744 "B<kexec_file_load>() system call first appeared in Linux 3.17."
1745 msgstr "B<kexec_load>() システムコールは Linux 2.6.13 で初めて登場した。"
1748 #: build/C/man2/kexec_load.2:337
1750 #| msgid "This system call is Linux-specific."
1751 msgid "These system calls are Linux-specific."
1752 msgstr "このシステムコールは Linux 固有である。"
1755 #: build/C/man2/kexec_load.2:341
1758 #| "Currently, there is no glibc support for B<kexec_load>(). Call it using "
1761 "Currently, there is no glibc support for these system calls. Call them "
1762 "using B<syscall>(2)."
1764 "現在のところ、 B<kexec_load>() は glibc ではサポートされていない。\n"
1765 "B<syscall>(2) を使って呼び出すこと。"
1768 #: build/C/man2/kexec_load.2:345
1770 #| msgid "B<reboot>(2), B<syscall>(2)"
1771 msgid "B<reboot>(2), B<syscall>(2), B<kexec>(8)"
1772 msgstr "B<reboot>(2), B<syscall>(2)"
1775 #: build/C/man2/kexec_load.2:350
1777 "The kernel source files I<Documentation/kdump/kdump.txt> and I<Documentation/"
1778 "kernel-parameters.txt>."
1782 #: build/C/man2/lookup_dcookie.2:27
1784 msgid "LOOKUP_DCOOKIE"
1785 msgstr "LOOKUP_DCOOKIE"
1788 #: build/C/man2/lookup_dcookie.2:27
1794 #: build/C/man2/lookup_dcookie.2:30
1795 msgid "lookup_dcookie - return a directory entry's path"
1796 msgstr "lookup_dcookie - ディレクトリエントリーのパス名を返す"
1799 #: build/C/man2/lookup_dcookie.2:32
1801 "B<int lookup_dcookie(u64 >I<cookie>B<, char *>I<buffer>B<, size_t >I<len>B<);"
1804 "B<int lookup_dcookie(u64 >I<cookie>B<, char *>I<buffer>B<, size_t >I<len>B<);"
1808 #: build/C/man2/lookup_dcookie.2:38
1810 "Look up the full path of the directory entry specified by the value "
1811 "I<cookie>. The cookie is an opaque identifier uniquely identifying a "
1812 "particular directory entry. The buffer given is filled in with the full "
1813 "path of the directory entry."
1815 "I<cookie> 値で指定されたディレクトリエントリーのフルパス名を検索する。 "
1816 "cookie は、個々のディレクトリエントリーを区別する内部識別子 (opaque "
1817 "identifier) である。引き数で指定されたバッファーに、ディレクトリエントリーの "
1821 #: build/C/man2/lookup_dcookie.2:43
1823 "For B<lookup_dcookie>() to return successfully, the kernel must still hold "
1824 "a cookie reference to the directory entry."
1826 "B<lookup_dcookie>() が正常に値を返すためには、カーネルがディレクトリエント"
1827 "リーへの cookie 参照を 保持していなければならない。"
1830 #: build/C/man2/lookup_dcookie.2:50
1832 "On success, B<lookup_dcookie>() returns the length of the path string "
1833 "copied into the buffer. On error, -1 is returned, and I<errno> is set "
1836 "成功した場合、 B<lookup_dcookie>() はバッファーにコピーしたパス文字列の長さ"
1837 "を返す。 エラーの場合は -1 を返し、 I<errno> に適切な値を設定する。"
1840 #: build/C/man2/lookup_dcookie.2:54
1841 msgid "The buffer was not valid."
1842 msgstr "バッファーが有効でなかった。"
1845 #: build/C/man2/lookup_dcookie.2:58
1847 "The kernel has no registered cookie/directory entry mappings at the time of "
1848 "lookup, or the cookie does not refer to a valid directory entry."
1850 "検索が行われた時、cookie とディレクトリエントリーのマッピングがカーネルに 登"
1851 "録されていなかったか、または cookie が有効なディレクトリエントリーを 参照して"
1855 #: build/C/man2/lookup_dcookie.2:58
1857 msgid "B<ENAMETOOLONG>"
1858 msgstr "B<ENAMETOOLONG>"
1861 #: build/C/man2/lookup_dcookie.2:61
1862 msgid "The name could not fit in the buffer."
1863 msgstr "名前がバッファーに入り切らなかった。"
1866 #: build/C/man2/lookup_dcookie.2:65
1868 "The kernel could not allocate memory for the temporary buffer holding the "
1871 "カーネルが、パス名を保持する一時バッファー用のメモリーを割り当てることが でき"
1875 #: build/C/man2/lookup_dcookie.2:70
1877 "The process does not have the capability B<CAP_SYS_ADMIN> required to look "
1880 "プロセスが cookie 値を検索するのに必要なケーパビリティ B<CAP_SYS_ADMIN> を"
1884 #: build/C/man2/lookup_dcookie.2:70 build/C/man2/quotactl.2:474
1890 #: build/C/man2/lookup_dcookie.2:73
1892 "The buffer was not large enough to hold the path of the directory entry."
1894 "バッファーが、ディレクトリエントリーのパス名を収容するのに 十分な大きさではな"
1898 #: build/C/man2/lookup_dcookie.2:78
1900 "Available since Linux 2.5.43. The B<ENAMETOOLONG> error return was added in "
1903 "Linux 2.5.43 以降で利用できる。 エラー B<ENAMETOOLONG> を返す仕様は 2.5.70 で"
1907 #: build/C/man2/lookup_dcookie.2:81
1908 msgid "B<lookup_dcookie>() is Linux-specific."
1909 msgstr "B<lookup_dcookie>() は Linux 独自の関数である。"
1912 #: build/C/man2/lookup_dcookie.2:85
1914 "B<lookup_dcookie>() is a special-purpose system call, currently used only "
1915 "by the oprofile profiler. It relies on a kernel driver to register cookies "
1916 "for directory entries."
1918 "B<lookup_dcookie>() は特殊な用途に使われるシステムコールで、現在のところ "
1919 "oprofile profiler で 使われているだけである。"
1922 #: build/C/man2/lookup_dcookie.2:88
1924 "The path returned may be suffixed by the string \" (deleted)\" if the "
1925 "directory entry has been removed."
1927 "指定されたディレクトリエントリーが削除されていた場合、返されるパス名の最後に "
1928 "\" (deleted)\" という文字列が付加されることがある。"
1931 #: build/C/man2/modify_ldt.2:24
1937 #: build/C/man2/modify_ldt.2:24 build/C/man2/pivot_root.2:10
1943 #: build/C/man2/modify_ldt.2:27
1944 msgid "modify_ldt - get or set ldt"
1945 msgstr "modify_ldt - ldt を設定または取得する"
1948 #: build/C/man2/modify_ldt.2:30
1950 msgid "B<#include E<lt>sys/types.hE<gt>>\n"
1951 msgstr "B<#include E<lt>sys/types.hE<gt>>\n"
1954 #: build/C/man2/modify_ldt.2:32
1956 msgid "B<int modify_ldt(int >I<func>B<, void *>I<ptr>B<, unsigned long >I<bytecount>B<);>\n"
1957 msgstr "B<int modify_ldt(int >I<func>B<, void *>I<ptr>B<, unsigned long >I<bytecount>B<);>\n"
1960 #: build/C/man2/modify_ldt.2:41
1962 "B<modify_ldt>() reads or writes the local descriptor table (ldt) for a "
1963 "process. The ldt is a per-process memory management table used by the i386 "
1964 "processor. For more information on this table, see an Intel 386 processor "
1967 "B<modify_ldt>() はプロセスのローカルディスクリプターテーブル (local "
1968 "descriptor table; ldt) を読み書きする。 ldt は i386 プロセッサで使用されるプ"
1969 "ロセスごとのメモリー管理テーブルである。 このテーブルに関してのより詳しい情報"
1970 "は Intel 386 processor handbook を 参照すること。"
1973 #: build/C/man2/modify_ldt.2:51
1975 "When I<func> is 0, B<modify_ldt>() reads the ldt into the memory pointed to "
1976 "by I<ptr>. The number of bytes read is the smaller of I<bytecount> and the "
1977 "actual size of the ldt."
1979 "I<func> が 0 ならば、 B<modify_ldt>() は ldt を I<ptr> が指しているメモリー"
1980 "に読み込む。 読み込むバイト数は実際の ldt のサイズか I<bytecount> より小さい"
1983 #. FIXME Should this page say something about func == 2 and func == 0x11?
1984 #. In Linux 2.4, func == 2 returned "the default ldt"
1985 #. In Linux 2.6, func == 2 is a nop, returning a zeroed out structure.
1986 #. Linux 2.4 and 2.6 implement an operation for func == 0x11
1988 #: build/C/man2/modify_ldt.2:69
1990 "When I<func> is 1, B<modify_ldt>() modifies one ldt entry. I<ptr> points "
1991 "to a I<user_desc> structure and I<bytecount> must equal the size of this "
1994 "I<func> が 1 ならば、 B<modify_ldt>() は ldt エントリーの一つを変更する。 "
1995 "I<ptr> は I<user_desc> 構造体を指し、 I<bytecount> はこの構造体の大きさに等し"
1999 #: build/C/man2/modify_ldt.2:73
2000 msgid "The I<user_desc> structure is defined in I<E<lt>asm/ldt.hE<gt>> as:"
2002 "I<user_desc> 構造体は I<E<lt>asm/ldt.hE<gt>> で以下のように定義されている:"
2005 #: build/C/man2/modify_ldt.2:87
2008 "struct user_desc {\n"
2009 " unsigned int entry_number;\n"
2010 " unsigned long base_addr;\n"
2011 " unsigned int limit;\n"
2012 " unsigned int seg_32bit:1;\n"
2013 " unsigned int contents:2;\n"
2014 " unsigned int read_exec_only:1;\n"
2015 " unsigned int limit_in_pages:1;\n"
2016 " unsigned int seg_not_present:1;\n"
2017 " unsigned int useable:1;\n"
2020 "struct user_desc {\n"
2021 " unsigned int entry_number;\n"
2022 " unsigned long base_addr;\n"
2023 " unsigned int limit;\n"
2024 " unsigned int seg_32bit:1;\n"
2025 " unsigned int contents:2;\n"
2026 " unsigned int read_exec_only:1;\n"
2027 " unsigned int limit_in_pages:1;\n"
2028 " unsigned int seg_not_present:1;\n"
2029 " unsigned int useable:1;\n"
2033 #. The ldt is specific for the calling process. Any attempts to change
2034 #. the ldt to include the address space of another process or the kernel
2035 #. will result in a segmentation violation when trying to access the memory
2036 #. outside of the process address space. The memory protection is enforced
2037 #. at the paging layer.
2039 #: build/C/man2/modify_ldt.2:98
2040 msgid "In Linux 2.4 and earlier, this structure was named I<modify_ldt_ldt_s>."
2042 "Linux 2.4 以前では、この構造体は I<modify_ldt_ldt_s> という名前であった。"
2045 #: build/C/man2/modify_ldt.2:108
2047 "On success, B<modify_ldt>() returns either the actual number of bytes read "
2048 "(for reading) or 0 (for writing). On failure, B<modify_ldt>() returns -1 "
2049 "and sets I<errno> to indicate the error."
2051 "成功した場合は、 B<modify_ldt>() は (読み込みの場合は) 実際に読み込んだバイ"
2052 "ト数、 または (書き込みの場合は) 0 を返す。 失敗した場合は B<modify_ldt>() "
2053 "は -1 を返し、 I<errno> をエラーを示す値に設定する。"
2056 #: build/C/man2/modify_ldt.2:113
2057 msgid "I<ptr> points outside the address space."
2058 msgstr "I<ptr> がアドレス空間の外を指している。"
2061 #: build/C/man2/modify_ldt.2:126
2063 "I<ptr> is 0, or I<func> is 1 and I<bytecount> is not equal to the size of "
2064 "the structure I<modify_ldt_ldt_s>, or I<func> is 1 and the new ldt entry has "
2067 "I<ptr> が 0 である、 または I<func> が 1 で I<bytecount> が "
2068 "I<modify_ldt_ldt_s> 構造体のサイズと等しくないか、 I<func> が 1 で新しい ldt "
2072 #: build/C/man2/modify_ldt.2:130
2073 msgid "I<func> is neither 0 nor 1."
2074 msgstr "I<func> が 0 でも 1 でもない。"
2077 #: build/C/man2/modify_ldt.2:133
2079 "This call is Linux-specific and should not be used in programs intended to "
2082 "このコールは Linux 特有であり、移植を意図したプログラムでは 使用してはいけな"
2086 #: build/C/man2/modify_ldt.2:136 build/C/man2/perfmonctl.2:205
2087 #: build/C/man2/pivot_root.2:134
2089 "Glibc does not provide a wrapper for this system call; call it using "
2092 "glibc はこのシステムコールに対するラッパー関数を提供していない。 "
2093 "B<syscall>(2) を使って呼び出すこと。"
2096 #: build/C/man2/modify_ldt.2:138
2101 #: build/C/man2/nfsservctl.2:8
2107 #: build/C/man2/nfsservctl.2:8
2113 #: build/C/man2/nfsservctl.2:11
2114 msgid "nfsservctl - syscall interface to kernel nfs daemon"
2115 msgstr "nfsservctl - カーネル nfs デーモンのためのインターフェース"
2118 #: build/C/man2/nfsservctl.2:14
2120 msgid "B<#include E<lt>linux/nfsd/syscall.hE<gt>>\n"
2121 msgstr "B<#include E<lt>linux/nfsd/syscall.hE<gt>>\n"
2124 #: build/C/man2/nfsservctl.2:17
2127 "B<long nfsservctl(int >I<cmd>B<, struct nfsctl_arg *>I<argp>B<,>\n"
2128 "B< union nfsctl_res *>I<resp>B<);>\n"
2130 "B<long nfsservctl(int >I<cmd>B<, struct nfsctl_arg *>I<argp>B<,>\n"
2131 "B< union nfsctl_res *>I<resp>B<);>\n"
2134 #: build/C/man2/nfsservctl.2:21
2135 msgid "I<Note>: Since Linux 3.1, this system call no longer exists."
2136 msgstr "I<注意>: Linux 3.1 以降では、このシステムコールはもはや存在しない。"
2139 #: build/C/man2/nfsservctl.2:35
2143 " * These are the commands understood by nfsctl().\n"
2145 "#define NFSCTL_SVC 0 /* This is a server process. */\n"
2146 "#define NFSCTL_ADDCLIENT 1 /* Add an NFS client. */\n"
2147 "#define NFSCTL_DELCLIENT 2 /* Remove an NFS client. */\n"
2148 "#define NFSCTL_EXPORT 3 /* Export a filesystem. */\n"
2149 "#define NFSCTL_UNEXPORT 4 /* Unexport a filesystem. */\n"
2150 "#define NFSCTL_UGIDUPDATE 5 /* Update a client's UID/GID map\n"
2151 " (only in Linux 2.4.x and earlier). */\n"
2152 "#define NFSCTL_GETFH 6 /* Get a file handle (used by mountd)\n"
2153 " (only in Linux 2.4.x and earlier). */\n"
2156 " * nfsctl() によって理解されるコマンド\n"
2158 "#define NFSCTL_SVC 0 /* サーバープロセス */\n"
2159 "#define NFSCTL_ADDCLIENT 1 /* NFS クライアントを追加 */\n"
2160 "#define NFSCTL_DELCLIENT 2 /* NFS クライアンドを削除 */\n"
2161 "#define NFSCTL_EXPORT 3 /* ファイルシステムのエクスポート */\n"
2162 "#define NFSCTL_UNEXPORT 4 /* ファイルシステムのアンエクスポート */\n"
2163 "#define NFSCTL_UGIDUPDATE 5 /* UID/GID マップの更新\n"
2164 " (Linux 2.4.x とそれ以前のみ) */\n"
2165 "#define NFSCTL_GETFH 6 /* (mountd で使用される) fh の取得\n"
2166 " (Linux 2.4.x とそれ以前のみ) */\n"
2169 #: build/C/man2/nfsservctl.2:47
2172 "struct nfsctl_arg {\n"
2173 " int ca_version; /* safeguard */\n"
2175 " struct nfsctl_svc u_svc;\n"
2176 " struct nfsctl_client u_client;\n"
2177 " struct nfsctl_export u_export;\n"
2178 " struct nfsctl_uidmap u_umap;\n"
2179 " struct nfsctl_fhparm u_getfh;\n"
2180 " unsigned int u_debug;\n"
2184 "struct nfsctl_arg {\n"
2185 " int ca_version; /* safeguard */\n"
2187 " struct nfsctl_svc u_svc;\n"
2188 " struct nfsctl_client u_client;\n"
2189 " struct nfsctl_export u_export;\n"
2190 " struct nfsctl_uidmap u_umap;\n"
2191 " struct nfsctl_fhparm u_getfh;\n"
2192 " unsigned int u_debug;\n"
2197 #: build/C/man2/nfsservctl.2:52
2200 "union nfsctl_res {\n"
2201 " struct knfs_fh cr_getfh;\n"
2202 " unsigned int cr_debug;\n"
2205 "union nfsctl_res {\n"
2206 " struct knfs_fh cr_getfh;\n"
2207 " unsigned int cr_debug;\n"
2211 #: build/C/man2/nfsservctl.2:58 build/C/man2/pivot_root.2:105
2212 #: build/C/man2/vm86.2:59
2214 "On success, zero is returned. On error, -1 is returned, and I<errno> is set "
2217 "成功した場合は 0 が返される。エラーの場合は -1 が返され、 I<errno> が適切に設"
2221 #: build/C/man2/nfsservctl.2:60
2222 msgid "This call is Linux-specific."
2223 msgstr "このコールは Linux 特有である。"
2226 #: build/C/man2/outb.2:26
2232 #: build/C/man2/outb.2:26
2238 #: build/C/man2/outb.2:31
2240 "outb, outw, outl, outsb, outsw, outsl, inb, inw, inl, insb, insw, insl, "
2241 "outb_p, outw_p, outl_p, inb_p, inw_p, inl_p - port I/O"
2243 "outb, outw, outl, outsb, outsw, outsl, inb, inw, inl, insb, insw, insl, "
2244 "outb_p, outw_p, outl_p, inb_p, inw_p, inl_p - ポート入出力"
2247 #: build/C/man2/outb.2:34
2249 msgid "B<#include E<lt>sys/io.hE<gt>>\n"
2250 msgstr "B<#include E<lt>sys/io.hE<gt>>\n"
2253 #: build/C/man2/outb.2:41
2256 "B<unsigned char inb(unsigned short int >I<port>B<);>\n"
2257 "B<unsigned char inb_p(unsigned short int >I<port>B<);>\n"
2258 "B<unsigned short int inw(unsigned short int >I<port>B<);>\n"
2259 "B<unsigned short int inw_p(unsigned short int >I<port>B<);>\n"
2260 "B<unsigned int inl(unsigned short int >I<port>B<);>\n"
2261 "B<unsigned int inl_p(unsigned short int >I<port>B<);>\n"
2263 "B<unsigned char inb(unsigned short int >I<port>B<);>\n"
2264 "B<unsigned char inb_p(unsigned short int >I<port>B<);>\n"
2265 "B<unsigned short int inw(unsigned short int >I<port>B<);>\n"
2266 "B<unsigned short int inw_p(unsigned short int >I<port>B<);>\n"
2267 "B<unsigned int inl(unsigned short int >I<port>B<);>\n"
2268 "B<unsigned int inl_p(unsigned short int >I<port>B<);>\n"
2271 #: build/C/man2/outb.2:48
2274 "B<void outb(unsigned char >I<value>B<, unsigned short int >I<port>B<);>\n"
2275 "B<void outb_p(unsigned char >I<value>B<, unsigned short int >I<port>B<);>\n"
2276 "B<void outw(unsigned short int >I<value>B<, unsigned short int >I<port>B<);>\n"
2277 "B<void outw_p(unsigned short int >I<value>B<, unsigned short int >I<port>B<);>\n"
2278 "B<void outl(unsigned int >I<value>B<, unsigned short int >I<port>B<);>\n"
2279 "B<void outl_p(unsigned int >I<value>B<, unsigned short int >I<port>B<);>\n"
2281 "B<void outb(unsigned char >I<value>B<, unsigned short int >I<port>B<);>\n"
2282 "B<void outb_p(unsigned char >I<value>B<, unsigned short int >I<port>B<);>\n"
2283 "B<void outw(unsigned short int >I<value>B<, unsigned short int >I<port>B<);>\n"
2284 "B<void outw_p(unsigned short int >I<value>B<, unsigned short int >I<port>B<);>\n"
2285 "B<void outl(unsigned int >I<value>B<, unsigned short int >I<port>B<);>\n"
2286 "B<void outl_p(unsigned int >I<value>B<, unsigned short int >I<port>B<);>\n"
2289 #: build/C/man2/outb.2:61
2292 "B<void insb(unsigned short int >I<port>B<, void *>I<addr>B<,>\n"
2293 "B< unsigned long int >I<count>B<);>\n"
2294 "B<void insw(unsigned short int >I<port>B<, void *>I<addr>B<,>\n"
2295 "B< unsigned long int >I<count>B<);>\n"
2296 "B<void insl(unsigned short int >I<port>B<, void *>I<addr>B<,>\n"
2297 "B< unsigned long int >I<count>B<);>\n"
2298 "B<void outsb(unsigned short int >I<port>B<, const void *>I<addr>B<,>\n"
2299 "B< unsigned long int >I<count>B<);>\n"
2300 "B<void outsw(unsigned short int >I<port>B<, const void *>I<addr>B<,>\n"
2301 "B< unsigned long int >I<count>B<);>\n"
2302 "B<void outsl(unsigned short int >I<port>B<, const void *>I<addr>B<,>\n"
2303 "B< unsigned long int >I<count>B<);>\n"
2305 "B<void insb(unsigned short int >I<port>B<, void *>I<addr>B<,>\n"
2306 "B< unsigned long int >I<count>B<);>\n"
2307 "B<void insw(unsigned short int >I<port>B<, void *>I<addr>B<,>\n"
2308 "B< unsigned long int >I<count>B<);>\n"
2309 "B<void insl(unsigned short int >I<port>B<, void *>I<addr>B<,>\n"
2310 "B< unsigned long int >I<count>B<);>\n"
2311 "B<void outsb(unsigned short int >I<port>B<, const void *>I<addr>B<,>\n"
2312 "B< unsigned long int >I<count>B<);>\n"
2313 "B<void outsw(unsigned short int >I<port>B<, const void *>I<addr>B<,>\n"
2314 "B< unsigned long int >I<count>B<);>\n"
2315 "B<void outsl(unsigned short int >I<port>B<, const void *>I<addr>B<,>\n"
2316 "B< unsigned long int >I<count>B<);>\n"
2319 #: build/C/man2/outb.2:67
2321 "This family of functions is used to do low-level port input and output. The "
2322 "out* functions do port output, the in* functions do port input; the b-suffix "
2323 "functions are byte-width and the w-suffix functions word-width; the _p-"
2324 "suffix functions pause until the I/O completes."
2326 "この一連の関数はポートに対する低レベルの入出力に使用する。 out* 関数はポート"
2327 "出力、in* 関数はポート入力を行う。 語尾に b がついている関数はバイト単位、w "
2328 "がついている関数はワード単位である。 _p がついている関数は I/O が終了するまで"
2331 #. , given the following information
2332 #. in addition to that given in
2335 #: build/C/man2/outb.2:73
2337 "They are primarily designed for internal kernel use, but can be used from "
2340 "これらの関数はもともとカーネル内部での使用を想定して設計されているが、 ユー"
2344 #: build/C/man2/outb.2:78
2346 "You must compile with B<-O> or B<-O2> or similar. The functions are defined "
2347 "as inline macros, and will not be substituted in without optimization "
2348 "enabled, causing unresolved references at link time."
2350 "B<-O> や B<-O2> などを指定してコンパイルしなければならない。 これらの関数はイ"
2351 "ンラインマクロとして定義されており、 最適化を行わないと関数の展開が行われ"
2352 "ず、 リンクの時に「解決できない参照(unresolved reference)」が発生する。"
2355 #: build/C/man2/outb.2:87
2357 "You use B<ioperm>(2) or alternatively B<iopl>(2) to tell the kernel to "
2358 "allow the user space application to access the I/O ports in question. "
2359 "Failure to do this will cause the application to receive a segmentation "
2362 "ユーザー空間のアプリケーションが I/O ポートにアクセスすることを カーネルに教"
2363 "えるために B<ioperm>(2) もしくは B<iopl>(2) を使用すること。これを忘れると"
2364 "アプリケーションはセグメンテーション違反 (segmentation fault) を受けとること"
2368 #: build/C/man2/outb.2:96
2370 "B<outb>() and friends are hardware-specific. The I<value> argument is "
2371 "passed first and the I<port> argument is passed second, which is the "
2372 "opposite order from most DOS implementations."
2374 "B<outb>() とその仲間はハードウェア特有である。 I<value> 引数が最初に渡さ"
2375 "れ、 I<port> 引数が二番目に渡される。 この順序はほとんどの DOS での実装とは逆"
2379 #: build/C/man2/outb.2:99
2380 msgid "B<ioperm>(2), B<iopl>(2)"
2381 msgstr "B<ioperm>(2), B<iopl>(2)"
2384 #: build/C/man2/pciconfig_read.2:8
2386 msgid "PCICONFIG_READ"
2387 msgstr "PCICONFIG_READ"
2390 #: build/C/man2/pciconfig_read.2:8
2396 #: build/C/man2/pciconfig_read.2:11
2398 "pciconfig_read, pciconfig_write, pciconfig_iobase - pci device information "
2401 "pciconfig_read, pciconfig_write, pciconfig_iobase - pci デバイス情報を扱う"
2404 #: build/C/man2/pciconfig_read.2:14
2406 msgid "B<#include E<lt>pci.hE<gt>>\n"
2407 msgstr "B<#include E<lt>pci.hE<gt>>\n"
2410 #: build/C/man2/pciconfig_read.2:21
2413 "B<int pciconfig_read(unsigned long >I<bus>B<, unsigned long >I<dfn>B<,>\n"
2414 "B< unsigned long >I<off>B<, unsigned long >I<len>B<, void *>I<buf>B<);>\n"
2415 "B<int pciconfig_write(unsigned long >I<bus>B<, unsigned long >I<dfn>B<,>\n"
2416 "B< unsigned long >I<off>B<, unsigned long >I<len>B<, void *>I<buf>B<);>\n"
2417 "B<int pciconfig_iobase(long >I<which>B<, unsigned long >I<bus>B<,>\n"
2418 "B< unsigned long >I<devfn>B<);>\n"
2420 "B<int pciconfig_read(unsigned long >I<bus>B<, unsigned long >I<dfn>B<,>\n"
2421 "B< unsigned long >I<off>B<, unsigned long >I<len>B<, void *>I<buf>B<);>\n"
2422 "B<int pciconfig_write(unsigned long >I<bus>B<, unsigned long >I<dfn>B<,>\n"
2423 "B< unsigned long >I<off>B<, unsigned long >I<len>B<, void *>I<buf>B<);>\n"
2424 "B<int pciconfig_iobase(long >I<which>B<, unsigned long >I<bus>B<,>\n"
2425 "B< unsigned long >I<devfn>B<);>\n"
2428 #: build/C/man2/pciconfig_read.2:27
2430 "Most of the interaction with PCI devices is already handled by the kernel "
2431 "PCI layer, and thus these calls should not normally need to be accessed from "
2434 "PCI デバイスとのやり取り (interaction) は カーネル PCI レイヤですでに処理され"
2435 "ているので、 通常はこららの関数をユーザー空間からアクセスする必要はない。"
2438 #: build/C/man2/pciconfig_read.2:27 build/C/man2/pciconfig_read.2:51
2440 msgid "B<pciconfig_read>()"
2441 msgstr "B<pciconfig_read>()"
2444 #: build/C/man2/pciconfig_read.2:36
2445 msgid "Reads to I<buf> from device I<dev> at offset I<off> value."
2446 msgstr "デバイス I<dev> のオフセット I<off> の値を I<buf> に読み込む。"
2449 #: build/C/man2/pciconfig_read.2:36 build/C/man2/pciconfig_read.2:57
2451 msgid "B<pciconfig_write>()"
2452 msgstr "B<pciconfig_write>()"
2455 #: build/C/man2/pciconfig_read.2:45
2456 msgid "Writes from I<buf> to device I<dev> at offset I<off> value."
2457 msgstr "デバイス I<dev> のオフセット I<off> に I<buf> の値を書き込む。"
2460 #: build/C/man2/pciconfig_read.2:45 build/C/man2/pciconfig_read.2:63
2462 msgid "B<pciconfig_iobase>()"
2463 msgstr "B<pciconfig_iobase>()"
2466 #: build/C/man2/pciconfig_read.2:50
2468 "You pass it a bus/devfn pair and get a physical address for either the "
2469 "memory offset (for things like prep, this is 0xc0000000), the IO base for "
2470 "PIO cycles, or the ISA holes if any."
2472 "bus/devfn ペアをこの関数に渡し、 メモリーオフセット (prep のようなものでは、"
2473 "この値は 0xc0000000 である) と PIO サイクルの IO ベースの物理アドレスを取得す"
2474 "る。 また、もしあるならば ISA hole の物理アドレスを取得する。"
2477 #: build/C/man2/pciconfig_read.2:57 build/C/man2/pciconfig_read.2:63
2479 "On success zero is returned. On error, -1 is returned and I<errno> is set "
2482 "成功した場合、0 が返される。 エラーの場合、-1 が返され、 I<errno> が適切に設"
2486 #: build/C/man2/pciconfig_read.2:77
2488 "Returns information on locations of various I/O regions in physical memory "
2489 "according to the I<which> value. Values for I<which> are: "
2490 "B<IOBASE_BRIDGE_NUMBER>, B<IOBASE_MEMORY>, B<IOBASE_IO>, B<IOBASE_ISA_IO>, "
2491 "B<IOBASE_ISA_MEM>."
2493 "I<which> の値に基づいて、物理メモリー内の様々な I/O 領域の位置情報が返され"
2494 "る。 I<which> の値は、 B<IOBASE_BRIDGE_NUMBER>, B<IOBASE_MEMORY>, "
2495 "B<IOBASE_IO>, B<IOBASE_ISA_IO>, B<IOBASE_ISA_MEM> である。"
2498 #: build/C/man2/pciconfig_read.2:84
2499 msgid "I<len> value is invalid. This does not apply to B<pciconfig_iobase>()."
2501 "I<len> の値が無効である。 このエラーは B<pciconfig_iobase>() には適用されな"
2505 #: build/C/man2/pciconfig_read.2:84 build/C/man2/ptrace.2:1929
2506 #: build/C/man2/sendfile.2:134
2512 #: build/C/man2/pciconfig_read.2:87
2517 #: build/C/man2/pciconfig_read.2:87 build/C/man2/perf_event_open.2:2696
2523 #: build/C/man2/pciconfig_read.2:93
2525 "For B<pciconfig_iobase>(), \"hose\" value is NULL. For the other calls, "
2526 "could not find a slot."
2528 "B<pciconfig_iobase>() の場合、でホース (hose) の値が NULL である。 他の呼び"
2529 "出しの場合、スロット (slot) が見つからない。"
2532 #: build/C/man2/pciconfig_read.2:98
2533 msgid "The system has not implemented these calls (B<CONFIG_PCI> not defined)."
2535 "このシステムはこれらの呼び出しを実装していない。 (B<CONFIG_PCI> が定義されて"
2539 #: build/C/man2/pciconfig_read.2:98 build/C/man2/perf_event_open.2:2725
2541 msgid "B<EOPNOTSUPP>"
2542 msgstr "B<EOPNOTSUPP>"
2545 #: build/C/man2/pciconfig_read.2:105
2547 "This return value is valid only for B<pciconfig_iobase>(). It is returned "
2548 "if the value for I<which> is invalid."
2550 "この返り値は B<pciconfig_iobase>() でのみ有効である。 このエラーは I<which> "
2554 #: build/C/man2/pciconfig_read.2:112
2556 "User does not have the B<CAP_SYS_ADMIN> capability. This does not apply to "
2557 "B<pciconfig_iobase>()."
2559 "ユーザーが B<CAP_SYS_ADMIN> 権限を持っていない。 このエラーは "
2560 "B<pciconfig_iobase>() には適用されない。"
2563 #: build/C/man2/pciconfig_read.2:114
2564 msgid "These calls are Linux-specific, available since Linux 2.0.26/2.1.11."
2566 "これらの呼び出しは Linux 特有のものであり、 Linux 2.0.26/2.1.11 から使用可能"
2570 #: build/C/man2/pciconfig_read.2:116
2571 msgid "B<capabilities>(7)"
2572 msgstr "B<capabilities>(7)"
2575 #: build/C/man2/perf_event_open.2:27
2577 msgid "PERF_EVENT_OPEN"
2578 msgstr "PERF_EVENT_OPEN"
2581 #: build/C/man2/perf_event_open.2:27
2587 #: build/C/man2/perf_event_open.2:30
2588 msgid "perf_event_open - set up performance monitoring"
2592 #: build/C/man2/perf_event_open.2:34
2595 "B<#include E<lt>linux/perf_event.hE<gt>>\n"
2596 "B<#include E<lt>linux/hw_breakpoint.hE<gt>>\n"
2598 "B<#include E<lt>linux/perf_event.hE<gt>>\n"
2599 "B<#include E<lt>linux/hw_breakpoint.hE<gt>>\n"
2602 #: build/C/man2/perf_event_open.2:38
2605 "B<int perf_event_open(struct perf_event_attr *>I<attr>B<,>\n"
2606 "B< pid_t >I<pid>B<, int >I<cpu>B<, int >I<group_fd>B<,>\n"
2607 "B< unsigned long >I<flags>B<);>\n"
2609 "B<int perf_event_open(struct perf_event_attr *>I<attr>B<,>\n"
2610 "B< pid_t >I<pid>B<, int >I<cpu>B<, int >I<group_fd>B<,>\n"
2611 "B< unsigned long >I<flags>B<);>\n"
2614 #: build/C/man2/perf_event_open.2:47
2616 "Given a list of parameters, B<perf_event_open>() returns a file descriptor, "
2617 "for use in subsequent system calls (B<read>(2), B<mmap>(2), B<prctl>(2), "
2618 "B<fcntl>(2), etc.)."
2622 #: build/C/man2/perf_event_open.2:55
2624 "A call to B<perf_event_open>() creates a file descriptor that allows "
2625 "measuring performance information. Each file descriptor corresponds to one "
2626 "event that is measured; these can be grouped together to measure multiple "
2627 "events simultaneously."
2631 #: build/C/man2/perf_event_open.2:62
2633 "Events can be enabled and disabled in two ways: via B<ioctl>(2) and via "
2634 "B<prctl>(2). When an event is disabled it does not count or generate "
2635 "overflows but does continue to exist and maintain its count value."
2639 #: build/C/man2/perf_event_open.2:76
2641 "Events come in two flavors: counting and sampled. A I<counting> event is "
2642 "one that is used for counting the aggregate number of events that occur. In "
2643 "general, counting event results are gathered with a B<read>(2) call. A "
2644 "I<sampling> event periodically writes measurements to a buffer that can then "
2645 "be accessed via B<mmap>(2)."
2649 #: build/C/man2/perf_event_open.2:76
2655 #: build/C/man2/perf_event_open.2:83
2657 "The I<pid> and I<cpu> arguments allow specifying which process and CPU to "
2662 #: build/C/man2/perf_event_open.2:83
2664 msgid "B<pid == 0> and B<cpu == -1>"
2665 msgstr "B<pid == 0> and B<cpu == -1>"
2668 #: build/C/man2/perf_event_open.2:86
2669 msgid "This measures the calling process/thread on any CPU."
2673 #: build/C/man2/perf_event_open.2:86
2675 msgid "B<pid == 0> and B<cpu E<gt>= 0>"
2676 msgstr "B<pid == 0> and B<cpu E<gt>= 0>"
2679 #: build/C/man2/perf_event_open.2:90
2681 "This measures the calling process/thread only when running on the specified "
2686 #: build/C/man2/perf_event_open.2:90
2688 msgid "B<pid E<gt> 0> and B<cpu == -1>"
2689 msgstr "B<pid E<gt> 0> and B<cpu == -1>"
2692 #: build/C/man2/perf_event_open.2:93
2693 msgid "This measures the specified process/thread on any CPU."
2697 #: build/C/man2/perf_event_open.2:93
2699 msgid "B<pid E<gt> 0> and B<cpu E<gt>= 0>"
2700 msgstr "B<pid E<gt> 0> and B<cpu E<gt>= 0>"
2703 #: build/C/man2/perf_event_open.2:97
2705 "This measures the specified process/thread only when running on the "
2710 #: build/C/man2/perf_event_open.2:97
2712 msgid "B<pid == -1> and B<cpu E<gt>= 0>"
2713 msgstr "B<pid == -1> and B<cpu E<gt>= 0>"
2716 #: build/C/man2/perf_event_open.2:105
2718 "This measures all processes/threads on the specified CPU. This requires "
2719 "B<CAP_SYS_ADMIN> capability or a I</proc/sys/kernel/perf_event_paranoid> "
2720 "value of less than 1."
2724 #: build/C/man2/perf_event_open.2:105
2726 msgid "B<pid == -1> and B<cpu == -1>"
2727 msgstr "B<pid == -1> and B<cpu == -1>"
2730 #: build/C/man2/perf_event_open.2:108
2731 msgid "This setting is invalid and will return an error."
2735 #: build/C/man2/perf_event_open.2:130
2737 "The I<group_fd> argument allows event groups to be created. An event group "
2738 "has one event which is the group leader. The leader is created first, with "
2739 "I<group_fd> = -1. The rest of the group members are created with subsequent "
2740 "B<perf_event_open>() calls with I<group_fd> being set to the file "
2741 "descriptor of the group leader. (A single event on its own is created with "
2742 "I<group_fd> = -1 and is considered to be a group with only 1 member.) An "
2743 "event group is scheduled onto the CPU as a unit: it will be put onto the CPU "
2744 "only if all of the events in the group can be put onto the CPU. This means "
2745 "that the values of the member events can be meaningfully compared\\(emadded, "
2746 "divided (to get ratios), and so on\\(emwith each other, since they have "
2747 "counted events for the same set of executed instructions."
2751 #: build/C/man2/perf_event_open.2:134
2753 "The I<flags> argument is formed by ORing together zero or more of the "
2756 "I<flags> 引き数には、以下の値の 0 個以上をビット毎の論理和の形で指定する。"
2759 #: build/C/man2/perf_event_open.2:134
2761 msgid "B<PERF_FLAG_FD_CLOEXEC> (since Linux 3.14)"
2762 msgstr "B<PERF_FLAG_FD_CLOEXEC> (Linux 3.14 以降)"
2764 #. commit a21b0b354d4ac39be691f51c53562e2c24443d9e
2766 #: build/C/man2/perf_event_open.2:151
2768 "This flag enables the close-on-exec flag for the created event file "
2769 "descriptor, so that the file descriptor is automatically closed on "
2770 "B<execve>(2). Setting the close-on-exec flags at creation time, rather than "
2771 "later with B<fcntl>(2), avoids potential race conditions where the calling "
2772 "thread invokes B<perf_event_open>() and B<fcntl>(2) at the same time as "
2773 "another thread calls B<fork>(2) then B<execve>(2)."
2777 #: build/C/man2/perf_event_open.2:151
2779 msgid "B<PERF_FLAG_FD_NO_GROUP>"
2780 msgstr "B<PERF_FLAG_FD_NO_GROUP>"
2783 #: build/C/man2/perf_event_open.2:159
2785 "This flag tells the event to ignore the I<group_fd> parameter except for the "
2786 "purpose of setting up output redirection using the B<PERF_FLAG_FD_OUTPUT> "
2791 #: build/C/man2/perf_event_open.2:159
2793 msgid "B<PERF_FLAG_FD_OUTPUT> (broken since Linux 2.6.35)"
2794 msgstr "B<PERF_FLAG_FD_OUTPUT> (Linux 2.6.35 以降では正しく動作しない)"
2796 #. commit ac9721f3f54b27a16c7e1afb2481e7ee95a70318
2798 #: build/C/man2/perf_event_open.2:165
2800 "This flag re-routes the event's sampled output to instead be included in the "
2801 "mmap buffer of the event specified by I<group_fd>."
2805 #: build/C/man2/perf_event_open.2:165
2807 msgid "B<PERF_FLAG_PID_CGROUP> (since Linux 2.6.39)"
2808 msgstr "B<PERF_FLAG_PID_CGROUP> (Linux 2.6.39 以降)"
2810 #. commit e5d1367f17ba6a6fed5fd8b74e4d5720923e0c25
2812 #: build/C/man2/perf_event_open.2:189
2814 "This flag activates per-container system-wide monitoring. A container is an "
2815 "abstraction that isolates a set of resources for finer-grained control "
2816 "(CPUs, memory, etc.). In this mode, the event is measured only if the "
2817 "thread running on the monitored CPU belongs to the designated container "
2818 "(cgroup). The cgroup is identified by passing a file descriptor opened on "
2819 "its directory in the cgroupfs filesystem. For instance, if the cgroup to "
2820 "monitor is called I<test>, then a file descriptor opened on I</dev/cgroup/"
2821 "test> (assuming cgroupfs is mounted on I</dev/cgroup>) must be passed as "
2822 "the I<pid> parameter. cgroup monitoring is available only for system-wide "
2823 "events and may therefore require extra permissions."
2827 #: build/C/man2/perf_event_open.2:194
2829 "The I<perf_event_attr> structure provides detailed configuration information "
2830 "for the event being created."
2834 #: build/C/man2/perf_event_open.2:201
2837 "struct perf_event_attr {\n"
2838 " __u32 type; /* Type of event */\n"
2839 " __u32 size; /* Size of attribute structure */\n"
2840 " __u64 config; /* Type-specific configuration */\n"
2842 "struct perf_event_attr {\n"
2843 " __u32 type; /* Type of event */\n"
2844 " __u32 size; /* Size of attribute structure */\n"
2845 " __u64 config; /* Type-specific configuration */\n"
2848 #: build/C/man2/perf_event_open.2:206
2852 " __u64 sample_period; /* Period of sampling */\n"
2853 " __u64 sample_freq; /* Frequency of sampling */\n"
2857 " __u64 sample_period; /* Period of sampling */\n"
2858 " __u64 sample_freq; /* Frequency of sampling */\n"
2862 #: build/C/man2/perf_event_open.2:209
2865 " __u64 sample_type; /* Specifies values included in sample */\n"
2866 " __u64 read_format; /* Specifies values returned in read */\n"
2868 " __u64 sample_type; /* Specifies values included in sample */\n"
2869 " __u64 read_format; /* Specifies values returned in read */\n"
2872 #: build/C/man2/perf_event_open.2:237
2875 " __u64 disabled : 1, /* off by default */\n"
2876 " inherit : 1, /* children inherit it */\n"
2877 " pinned : 1, /* must always be on PMU */\n"
2878 " exclusive : 1, /* only group on PMU */\n"
2879 " exclude_user : 1, /* don't count user */\n"
2880 " exclude_kernel : 1, /* don't count kernel */\n"
2881 " exclude_hv : 1, /* don't count hypervisor */\n"
2882 " exclude_idle : 1, /* don't count when idle */\n"
2883 " mmap : 1, /* include mmap data */\n"
2884 " comm : 1, /* include comm data */\n"
2885 " freq : 1, /* use freq, not period */\n"
2886 " inherit_stat : 1, /* per task counts */\n"
2887 " enable_on_exec : 1, /* next exec enables */\n"
2888 " task : 1, /* trace fork/exit */\n"
2889 " watermark : 1, /* wakeup_watermark */\n"
2890 " precise_ip : 2, /* skid constraint */\n"
2891 " mmap_data : 1, /* non-exec mmap data */\n"
2892 " sample_id_all : 1, /* sample_type all events */\n"
2893 " exclude_host : 1, /* don't count in host */\n"
2894 " exclude_guest : 1, /* don't count in guest */\n"
2895 " exclude_callchain_kernel : 1,\n"
2896 " /* exclude kernel callchains */\n"
2897 " exclude_callchain_user : 1,\n"
2898 " /* exclude user callchains */\n"
2899 " mmap2 : 1, /* include mmap with inode data */\n"
2900 " comm_exec : 1, /* flag comm events that are due to exec */\n"
2901 " __reserved_1 : 39;\n"
2903 " __u64 disabled : 1, /* off by default */\n"
2904 " inherit : 1, /* children inherit it */\n"
2905 " pinned : 1, /* must always be on PMU */\n"
2906 " exclusive : 1, /* only group on PMU */\n"
2907 " exclude_user : 1, /* don't count user */\n"
2908 " exclude_kernel : 1, /* don't count kernel */\n"
2909 " exclude_hv : 1, /* don't count hypervisor */\n"
2910 " exclude_idle : 1, /* don't count when idle */\n"
2911 " mmap : 1, /* include mmap data */\n"
2912 " comm : 1, /* include comm data */\n"
2913 " freq : 1, /* use freq, not period */\n"
2914 " inherit_stat : 1, /* per task counts */\n"
2915 " enable_on_exec : 1, /* next exec enables */\n"
2916 " task : 1, /* trace fork/exit */\n"
2917 " watermark : 1, /* wakeup_watermark */\n"
2918 " precise_ip : 2, /* skid constraint */\n"
2919 " mmap_data : 1, /* non-exec mmap data */\n"
2920 " sample_id_all : 1, /* sample_type all events */\n"
2921 " exclude_host : 1, /* don't count in host */\n"
2922 " exclude_guest : 1, /* don't count in guest */\n"
2923 " exclude_callchain_kernel : 1,\n"
2924 " /* exclude kernel callchains */\n"
2925 " exclude_callchain_user : 1,\n"
2926 " /* exclude user callchains */\n"
2927 " mmap2 : 1, /* include mmap with inode data */\n"
2928 " comm_exec : 1, /* flag comm events that are due to exec */\n"
2929 " __reserved_1 : 39;\n"
2932 #: build/C/man2/perf_event_open.2:242
2936 " __u32 wakeup_events; /* wakeup every n events */\n"
2937 " __u32 wakeup_watermark; /* bytes before wakeup */\n"
2941 " __u32 wakeup_events; /* wakeup every n events */\n"
2942 " __u32 wakeup_watermark; /* bytes before wakeup */\n"
2946 #: build/C/man2/perf_event_open.2:244
2948 msgid " __u32 bp_type; /* breakpoint type */\n"
2949 msgstr " __u32 bp_type; /* breakpoint type */\n"
2952 #: build/C/man2/perf_event_open.2:249
2956 " __u64 bp_addr; /* breakpoint address */\n"
2957 " __u64 config1; /* extension of config */\n"
2961 " __u64 bp_addr; /* breakpoint address */\n"
2962 " __u64 config1; /* extension of config */\n"
2966 #: build/C/man2/perf_event_open.2:259
2970 " __u64 bp_len; /* breakpoint length */\n"
2971 " __u64 config2; /* extension of config1 */\n"
2973 " __u64 branch_sample_type; /* enum perf_branch_sample_type */\n"
2974 " __u64 sample_regs_user; /* user regs to dump on samples */\n"
2975 " __u32 sample_stack_user; /* size of stack to dump on\n"
2977 " __u32 __reserved_2; /* Align to u64 */\n"
2980 " __u64 bp_len; /* breakpoint length */\n"
2981 " __u64 config2; /* extension of config1 */\n"
2983 " __u64 branch_sample_type; /* enum perf_branch_sample_type */\n"
2984 " __u64 sample_regs_user; /* user regs to dump on samples */\n"
2985 " __u32 sample_stack_user; /* size of stack to dump on\n"
2987 " __u32 __reserved_2; /* Align to u64 */\n"
2990 #: build/C/man2/perf_event_open.2:261
2996 #: build/C/man2/perf_event_open.2:267
2998 "The fields of the I<perf_event_attr> structure are described in more detail "
3003 #: build/C/man2/perf_event_open.2:267 build/C/man2/perf_event_open.2:1669
3009 #: build/C/man2/perf_event_open.2:271
3011 "This field specifies the overall event type. It has one of the following "
3016 #: build/C/man2/perf_event_open.2:272
3018 msgid "B<PERF_TYPE_HARDWARE>"
3019 msgstr "B<PERF_TYPE_HARDWARE>"
3022 #: build/C/man2/perf_event_open.2:279
3024 "This indicates one of the \"generalized\" hardware events provided by the "
3025 "kernel. See the I<config> field definition for more details."
3029 #: build/C/man2/perf_event_open.2:279
3031 msgid "B<PERF_TYPE_SOFTWARE>"
3032 msgstr "B<PERF_TYPE_SOFTWARE>"
3035 #: build/C/man2/perf_event_open.2:283
3037 "This indicates one of the software-defined events provided by the kernel "
3038 "(even if no hardware support is available)."
3042 #: build/C/man2/perf_event_open.2:283
3044 msgid "B<PERF_TYPE_TRACEPOINT>"
3045 msgstr "B<PERF_TYPE_TRACEPOINT>"
3048 #: build/C/man2/perf_event_open.2:287
3050 "This indicates a tracepoint provided by the kernel tracepoint infrastructure."
3054 #: build/C/man2/perf_event_open.2:287
3056 msgid "B<PERF_TYPE_HW_CACHE>"
3057 msgstr "B<PERF_TYPE_HW_CACHE>"
3060 #: build/C/man2/perf_event_open.2:293
3062 "This indicates a hardware cache event. This has a special encoding, "
3063 "described in the I<config> field definition."
3067 #: build/C/man2/perf_event_open.2:293
3069 msgid "B<PERF_TYPE_RAW>"
3070 msgstr "B<PERF_TYPE_RAW>"
3073 #: build/C/man2/perf_event_open.2:297
3075 "This indicates a \"raw\" implementation-specific event in the I<config> "
3080 #: build/C/man2/perf_event_open.2:297
3082 msgid "B<PERF_TYPE_BREAKPOINT> (since Linux 2.6.33)"
3083 msgstr "B<PERF_TYPE_BREAKPOINT> (Linux 2.6.33 以降)"
3085 #. commit 24f1e32c60c45c89a997c73395b69c8af6f0a84e
3087 #: build/C/man2/perf_event_open.2:303
3089 "This indicates a hardware breakpoint as provided by the CPU. Breakpoints "
3090 "can be read/write accesses to an address as well as execution of an "
3091 "instruction address."
3095 #: build/C/man2/perf_event_open.2:303
3100 #. commit 2e80a82a49c4c7eca4e35734380f28298ba5db19
3102 #: build/C/man2/perf_event_open.2:323
3104 "Since Linux 2.6.38, B<perf_event_open>() can support multiple PMUs. To "
3105 "enable this, a value exported by the kernel can be used in the I<type> field "
3106 "to indicate which PMU to use. The value to use can be found in the sysfs "
3107 "filesystem: there is a subdirectory per PMU instance under I</sys/bus/"
3108 "event_source/devices>. In each subdirectory there is a I<type> file whose "
3109 "content is an integer that can be used in the I<type> field. For instance, "
3110 "I</sys/bus/event_source/devices/cpu/type> contains the value for the core "
3111 "CPU PMU, which is usually 4."
3115 #: build/C/man2/perf_event_open.2:324 build/C/man2/perf_event_open.2:1601
3121 #: build/C/man2/perf_event_open.2:333
3123 "The size of the I<perf_event_attr> structure for forward/backward "
3124 "compatibility. Set this using I<sizeof(struct perf_event_attr)> to allow "
3125 "the kernel to see the struct size at the time of compilation."
3128 #. commit cb5d76999029ae7a517cb07dfa732c1b5a934fc2
3129 #. this was added much later when PERF_ATTR_SIZE_VER2 happened
3130 #. but the actual attr_size had increased in 2.6.33
3131 #. commit cb5d76999029ae7a517cb07dfa732c1b5a934fc2
3132 #. commit 1659d129ed014b715b0b2120e6fd929bdd33ed03
3134 #: build/C/man2/perf_event_open.2:353
3136 "The related define B<PERF_ATTR_SIZE_VER0> is set to 64; this was the size of "
3137 "the first published struct. B<PERF_ATTR_SIZE_VER1> is 72, corresponding to "
3138 "the addition of breakpoints in Linux 2.6.33. B<PERF_ATTR_SIZE_VER2> is 80 "
3139 "corresponding to the addition of branch sampling in Linux 3.4. "
3140 "B<PERF_ATTR_SIZE_VER3> is 96 corresponding to the addition of "
3141 "I<sample_regs_user> and I<sample_stack_user> in Linux 3.7."
3145 #: build/C/man2/perf_event_open.2:353
3151 #: build/C/man2/perf_event_open.2:364
3153 "This specifies which event you want, in conjunction with the I<type> field. "
3154 "The I<config1> and I<config2> fields are also taken into account in cases "
3155 "where 64 bits is not enough to fully specify the event. The encoding of "
3156 "these fields are event dependent."
3160 #: build/C/man2/perf_event_open.2:375
3162 "There are various ways to set the I<config> field that are dependent on the "
3163 "value of the previously described I<type> field. What follows are various "
3164 "possible settings for I<config> separated out by I<type>."
3168 #: build/C/man2/perf_event_open.2:385
3170 "If I<type> is B<PERF_TYPE_HARDWARE>, we are measuring one of the generalized "
3171 "hardware CPU events. Not all of these are available on all platforms. Set "
3172 "I<config> to one of the following:"
3176 #: build/C/man2/perf_event_open.2:386
3178 msgid "B<PERF_COUNT_HW_CPU_CYCLES>"
3179 msgstr "B<PERF_COUNT_HW_CPU_CYCLES>"
3182 #: build/C/man2/perf_event_open.2:390
3183 msgid "Total cycles. Be wary of what happens during CPU frequency scaling."
3187 #: build/C/man2/perf_event_open.2:390
3189 msgid "B<PERF_COUNT_HW_INSTRUCTIONS>"
3190 msgstr "B<PERF_COUNT_HW_INSTRUCTIONS>"
3193 #: build/C/man2/perf_event_open.2:395
3195 "Retired instructions. Be careful, these can be affected by various issues, "
3196 "most notably hardware interrupt counts."
3200 #: build/C/man2/perf_event_open.2:395
3202 msgid "B<PERF_COUNT_HW_CACHE_REFERENCES>"
3203 msgstr "B<PERF_COUNT_HW_CACHE_REFERENCES>"
3206 #: build/C/man2/perf_event_open.2:402
3208 "Cache accesses. Usually this indicates Last Level Cache accesses but this "
3209 "may vary depending on your CPU. This may include prefetches and coherency "
3210 "messages; again this depends on the design of your CPU."
3214 #: build/C/man2/perf_event_open.2:402
3216 msgid "B<PERF_COUNT_HW_CACHE_MISSES>"
3217 msgstr "B<PERF_COUNT_HW_CACHE_MISSES>"
3220 #: build/C/man2/perf_event_open.2:409
3222 "Cache misses. Usually this indicates Last Level Cache misses; this is "
3223 "intended to be used in conjunction with the "
3224 "B<PERF_COUNT_HW_CACHE_REFERENCES> event to calculate cache miss rates."
3228 #: build/C/man2/perf_event_open.2:409
3230 msgid "B<PERF_COUNT_HW_BRANCH_INSTRUCTIONS>"
3231 msgstr "B<PERF_COUNT_HW_BRANCH_INSTRUCTIONS>"
3233 #. commit f287d332ce835f77a4f5077d2c0ef1e3f9ea42d2
3235 #: build/C/man2/perf_event_open.2:415
3237 "Retired branch instructions. Prior to Linux 2.6.35, this used the wrong "
3238 "event on AMD processors."
3242 #: build/C/man2/perf_event_open.2:415
3244 msgid "B<PERF_COUNT_HW_BRANCH_MISSES>"
3245 msgstr "B<PERF_COUNT_HW_BRANCH_MISSES>"
3248 #: build/C/man2/perf_event_open.2:418
3249 msgid "Mispredicted branch instructions."
3253 #: build/C/man2/perf_event_open.2:418
3255 msgid "B<PERF_COUNT_HW_BUS_CYCLES>"
3256 msgstr "B<PERF_COUNT_HW_BUS_CYCLES>"
3259 #: build/C/man2/perf_event_open.2:421
3260 msgid "Bus cycles, which can be different from total cycles."
3264 #: build/C/man2/perf_event_open.2:421
3266 msgid "B<PERF_COUNT_HW_STALLED_CYCLES_FRONTEND> (since Linux 3.0)"
3267 msgstr "B<PERF_COUNT_HW_STALLED_CYCLES_FRONTEND> (Linux 3.0 以降)"
3269 #. commit 8f62242246351b5a4bc0c1f00c0c7003edea128a
3271 #: build/C/man2/perf_event_open.2:425
3272 msgid "Stalled cycles during issue."
3276 #: build/C/man2/perf_event_open.2:425
3278 msgid "B<PERF_COUNT_HW_STALLED_CYCLES_BACKEND> (since Linux 3.0)"
3279 msgstr "B<PERF_COUNT_HW_STALLED_CYCLES_BACKEND> (Linux 3.0 以降)"
3281 #. commit 8f62242246351b5a4bc0c1f00c0c7003edea128a
3283 #: build/C/man2/perf_event_open.2:429
3284 msgid "Stalled cycles during retirement."
3288 #: build/C/man2/perf_event_open.2:429
3290 msgid "B<PERF_COUNT_HW_REF_CPU_CYCLES> (since Linux 3.3)"
3291 msgstr "B<PERF_COUNT_HW_REF_CPU_CYCLES> (Linux 3.3 以降)"
3293 #. commit c37e17497e01fc0f5d2d6feb5723b210b3ab8890
3295 #: build/C/man2/perf_event_open.2:433
3296 msgid "Total cycles; not affected by CPU frequency scaling."
3300 #: build/C/man2/perf_event_open.2:443
3302 "If I<type> is B<PERF_TYPE_SOFTWARE>, we are measuring software events "
3303 "provided by the kernel. Set I<config> to one of the following:"
3307 #: build/C/man2/perf_event_open.2:444
3309 msgid "B<PERF_COUNT_SW_CPU_CLOCK>"
3310 msgstr "B<PERF_COUNT_SW_CPU_CLOCK>"
3313 #: build/C/man2/perf_event_open.2:447
3314 msgid "This reports the CPU clock, a high-resolution per-CPU timer."
3318 #: build/C/man2/perf_event_open.2:447
3320 msgid "B<PERF_COUNT_SW_TASK_CLOCK>"
3321 msgstr "B<PERF_COUNT_SW_TASK_CLOCK>"
3324 #: build/C/man2/perf_event_open.2:450
3325 msgid "This reports a clock count specific to the task that is running."
3329 #: build/C/man2/perf_event_open.2:450
3331 msgid "B<PERF_COUNT_SW_PAGE_FAULTS>"
3332 msgstr "B<PERF_COUNT_SW_PAGE_FAULTS>"
3335 #: build/C/man2/perf_event_open.2:453
3336 msgid "This reports the number of page faults."
3340 #: build/C/man2/perf_event_open.2:453
3342 msgid "B<PERF_COUNT_SW_CONTEXT_SWITCHES>"
3343 msgstr "B<PERF_COUNT_SW_CONTEXT_SWITCHES>"
3345 #. commit e49a5bd38159dfb1928fd25b173bc9de4bbadb21
3347 #: build/C/man2/perf_event_open.2:459
3349 "This counts context switches. Until Linux 2.6.34, these were all reported "
3350 "as user-space events, after that they are reported as happening in the "
3355 #: build/C/man2/perf_event_open.2:459
3357 msgid "B<PERF_COUNT_SW_CPU_MIGRATIONS>"
3358 msgstr "B<PERF_COUNT_SW_CPU_MIGRATIONS>"
3361 #: build/C/man2/perf_event_open.2:463
3362 msgid "This reports the number of times the process has migrated to a new CPU."
3366 #: build/C/man2/perf_event_open.2:463
3368 msgid "B<PERF_COUNT_SW_PAGE_FAULTS_MIN>"
3369 msgstr "B<PERF_COUNT_SW_PAGE_FAULTS_MIN>"
3372 #: build/C/man2/perf_event_open.2:467
3374 "This counts the number of minor page faults. These did not require disk I/O "
3379 #: build/C/man2/perf_event_open.2:467
3381 msgid "B<PERF_COUNT_SW_PAGE_FAULTS_MAJ>"
3382 msgstr "B<PERF_COUNT_SW_PAGE_FAULTS_MAJ>"
3385 #: build/C/man2/perf_event_open.2:471
3387 "This counts the number of major page faults. These required disk I/O to "
3392 #: build/C/man2/perf_event_open.2:471
3394 msgid "B<PERF_COUNT_SW_ALIGNMENT_FAULTS> (since Linux 2.6.33)"
3395 msgstr "B<PERF_COUNT_SW_ALIGNMENT_FAULTS> (Linux 2.6.33 以降)"
3397 #. commit f7d7986060b2890fc26db6ab5203efbd33aa2497
3399 #: build/C/man2/perf_event_open.2:478
3401 "This counts the number of alignment faults. These happen when unaligned "
3402 "memory accesses happen; the kernel can handle these but it reduces "
3403 "performance. This happens only on some architectures (never on x86)."
3407 #: build/C/man2/perf_event_open.2:478
3409 msgid "B<PERF_COUNT_SW_EMULATION_FAULTS> (since Linux 2.6.33)"
3410 msgstr "B<PERF_COUNT_SW_EMULATION_FAULTS> (Linux 2.6.33 以降)"
3412 #. commit f7d7986060b2890fc26db6ab5203efbd33aa2497
3414 #: build/C/man2/perf_event_open.2:485
3416 "This counts the number of emulation faults. The kernel sometimes traps on "
3417 "unimplemented instructions and emulates them for user space. This can "
3418 "negatively impact performance."
3422 #: build/C/man2/perf_event_open.2:485
3424 msgid "B<PERF_COUNT_SW_DUMMY> (since Linux 3.12)"
3425 msgstr "B<PERF_COUNT_SW_DUMMY> (Linux 3.12 以降)"
3427 #. commit fa0097ee690693006ab1aea6c01ad3c851b65c77
3429 #: build/C/man2/perf_event_open.2:493
3431 "This is a placeholder event that counts nothing. Informational sample "
3432 "record types such as mmap or comm must be associated with an active event. "
3433 "This dummy event allows gathering such records without requiring a counting "
3438 #: build/C/man2/perf_event_open.2:506
3440 "If I<type> is B<PERF_TYPE_TRACEPOINT>, then we are measuring kernel "
3441 "tracepoints. The value to use in I<config> can be obtained from under "
3442 "debugfs I<tracing/events/*/*/id> if ftrace is enabled in the kernel."
3446 #: build/C/man2/perf_event_open.2:517
3448 "If I<type> is B<PERF_TYPE_HW_CACHE>, then we are measuring a hardware CPU "
3449 "cache event. To calculate the appropriate I<config> value use the following "
3454 #: build/C/man2/perf_event_open.2:522
3457 " (perf_hw_cache_id) | (perf_hw_cache_op_id E<lt>E<lt> 8) |\n"
3458 " (perf_hw_cache_op_result_id E<lt>E<lt> 16)\n"
3460 " (perf_hw_cache_id) | (perf_hw_cache_op_id E<lt>E<lt> 8) |\n"
3461 " (perf_hw_cache_op_result_id E<lt>E<lt> 16)\n"
3464 #: build/C/man2/perf_event_open.2:527
3465 msgid "where I<perf_hw_cache_id> is one of:"
3469 #: build/C/man2/perf_event_open.2:528
3471 msgid "B<PERF_COUNT_HW_CACHE_L1D>"
3472 msgstr "B<PERF_COUNT_HW_CACHE_L1D>"
3475 #: build/C/man2/perf_event_open.2:531
3476 msgid "for measuring Level 1 Data Cache"
3480 #: build/C/man2/perf_event_open.2:531
3482 msgid "B<PERF_COUNT_HW_CACHE_L1I>"
3483 msgstr "B<PERF_COUNT_HW_CACHE_L1I>"
3486 #: build/C/man2/perf_event_open.2:534
3487 msgid "for measuring Level 1 Instruction Cache"
3491 #: build/C/man2/perf_event_open.2:534
3493 msgid "B<PERF_COUNT_HW_CACHE_LL>"
3494 msgstr "B<PERF_COUNT_HW_CACHE_LL>"
3497 #: build/C/man2/perf_event_open.2:537
3498 msgid "for measuring Last-Level Cache"
3502 #: build/C/man2/perf_event_open.2:537
3504 msgid "B<PERF_COUNT_HW_CACHE_DTLB>"
3505 msgstr "B<PERF_COUNT_HW_CACHE_DTLB>"
3508 #: build/C/man2/perf_event_open.2:540
3509 msgid "for measuring the Data TLB"
3513 #: build/C/man2/perf_event_open.2:540
3515 msgid "B<PERF_COUNT_HW_CACHE_ITLB>"
3516 msgstr "B<PERF_COUNT_HW_CACHE_ITLB>"
3519 #: build/C/man2/perf_event_open.2:543
3520 msgid "for measuring the Instruction TLB"
3524 #: build/C/man2/perf_event_open.2:543
3526 msgid "B<PERF_COUNT_HW_CACHE_BPU>"
3527 msgstr "B<PERF_COUNT_HW_CACHE_BPU>"
3530 #: build/C/man2/perf_event_open.2:546
3531 msgid "for measuring the branch prediction unit"
3535 #: build/C/man2/perf_event_open.2:546
3537 msgid "B<PERF_COUNT_HW_CACHE_NODE> (since Linux 3.1)"
3538 msgstr "B<PERF_COUNT_HW_CACHE_NODE> (Linux 3.1 以降)"
3540 #. commit 89d6c0b5bdbb1927775584dcf532d98b3efe1477
3542 #: build/C/man2/perf_event_open.2:550
3543 msgid "for measuring local memory accesses"
3547 #: build/C/man2/perf_event_open.2:555
3548 msgid "and I<perf_hw_cache_op_id> is one of"
3552 #: build/C/man2/perf_event_open.2:556
3554 msgid "B<PERF_COUNT_HW_CACHE_OP_READ>"
3555 msgstr "B<PERF_COUNT_HW_CACHE_OP_READ>"
3558 #: build/C/man2/perf_event_open.2:559
3559 msgid "for read accesses"
3563 #: build/C/man2/perf_event_open.2:559
3565 msgid "B<PERF_COUNT_HW_CACHE_OP_WRITE>"
3566 msgstr "B<PERF_COUNT_HW_CACHE_OP_WRITE>"
3569 #: build/C/man2/perf_event_open.2:562
3570 msgid "for write accesses"
3574 #: build/C/man2/perf_event_open.2:562
3576 msgid "B<PERF_COUNT_HW_CACHE_OP_PREFETCH>"
3577 msgstr "B<PERF_COUNT_HW_CACHE_OP_PREFETCH>"
3580 #: build/C/man2/perf_event_open.2:565
3581 msgid "for prefetch accesses"
3585 #: build/C/man2/perf_event_open.2:570
3586 msgid "and I<perf_hw_cache_op_result_id> is one of"
3590 #: build/C/man2/perf_event_open.2:571
3592 msgid "B<PERF_COUNT_HW_CACHE_RESULT_ACCESS>"
3593 msgstr "B<PERF_COUNT_HW_CACHE_RESULT_ACCESS>"
3596 #: build/C/man2/perf_event_open.2:574
3597 msgid "to measure accesses"
3601 #: build/C/man2/perf_event_open.2:574
3603 msgid "B<PERF_COUNT_HW_CACHE_RESULT_MISS>"
3604 msgstr "B<PERF_COUNT_HW_CACHE_RESULT_MISS>"
3607 #: build/C/man2/perf_event_open.2:577
3608 msgid "to measure misses"
3612 #: build/C/man2/perf_event_open.2:595
3614 "If I<type> is B<PERF_TYPE_RAW>, then a custom \"raw\" I<config> value is "
3615 "needed. Most CPUs support events that are not covered by the \"generalized"
3616 "\" events. These are implementation defined; see your CPU manual (for "
3617 "example the Intel Volume 3B documentation or the AMD BIOS and Kernel "
3618 "Developer Guide). The libpfm4 library can be used to translate from the "
3619 "name in the architectural manuals to the raw hex value B<perf_event_open>() "
3620 "expects in this field."
3624 #: build/C/man2/perf_event_open.2:604
3626 "If I<type> is B<PERF_TYPE_BREAKPOINT>, then leave I<config> set to zero. "
3627 "Its parameters are set in other places."
3631 #: build/C/man2/perf_event_open.2:605
3633 msgid "I<sample_period>, I<sample_freq>"
3634 msgstr "I<sample_period>, I<sample_freq>"
3637 #: build/C/man2/perf_event_open.2:617
3639 "A \"sampling\" event is one that generates an overflow notification every N "
3640 "events, where N is given by I<sample_period>. A sampling event has "
3641 "I<sample_period> E<gt> 0. When an overflow occurs, requested data is "
3642 "recorded in the mmap buffer. The I<sample_type> field controls what data is "
3643 "recorded on each overflow."
3647 #: build/C/man2/perf_event_open.2:627
3649 "I<sample_freq> can be used if you wish to use frequency rather than period. "
3650 "In this case, you set the I<freq> flag. The kernel will adjust the sampling "
3651 "period to try and achieve the desired rate. The rate of adjustment is a "
3656 #: build/C/man2/perf_event_open.2:627
3658 msgid "I<sample_type>"
3659 msgstr "I<sample_type>"
3662 #: build/C/man2/perf_event_open.2:639
3664 "The various bits in this field specify which values to include in the "
3665 "sample. They will be recorded in a ring-buffer, which is available to user "
3666 "space using B<mmap>(2). The order in which the values are saved in the "
3667 "sample are documented in the MMAP Layout subsection below; it is not the "
3668 "I<enum perf_event_sample_format> order."
3672 #: build/C/man2/perf_event_open.2:640
3674 msgid "B<PERF_SAMPLE_IP>"
3675 msgstr "B<PERF_SAMPLE_IP>"
3678 #: build/C/man2/perf_event_open.2:643
3679 msgid "Records instruction pointer."
3683 #: build/C/man2/perf_event_open.2:643
3685 msgid "B<PERF_SAMPLE_TID>"
3686 msgstr "B<PERF_SAMPLE_TID>"
3689 #: build/C/man2/perf_event_open.2:646
3690 msgid "Records the process and thread IDs."
3694 #: build/C/man2/perf_event_open.2:646
3696 msgid "B<PERF_SAMPLE_TIME>"
3697 msgstr "B<PERF_SAMPLE_TIME>"
3700 #: build/C/man2/perf_event_open.2:649
3701 msgid "Records a timestamp."
3705 #: build/C/man2/perf_event_open.2:649
3707 msgid "B<PERF_SAMPLE_ADDR>"
3708 msgstr "B<PERF_SAMPLE_ADDR>"
3711 #: build/C/man2/perf_event_open.2:652
3712 msgid "Records an address, if applicable."
3716 #: build/C/man2/perf_event_open.2:652
3718 msgid "B<PERF_SAMPLE_READ>"
3719 msgstr "B<PERF_SAMPLE_READ>"
3722 #: build/C/man2/perf_event_open.2:655
3724 "Record counter values for all events in a group, not just the group leader."
3728 #: build/C/man2/perf_event_open.2:655
3730 msgid "B<PERF_SAMPLE_CALLCHAIN>"
3731 msgstr "B<PERF_SAMPLE_CALLCHAIN>"
3734 #: build/C/man2/perf_event_open.2:658
3735 msgid "Records the callchain (stack backtrace)."
3739 #: build/C/man2/perf_event_open.2:658
3741 msgid "B<PERF_SAMPLE_ID>"
3742 msgstr "B<PERF_SAMPLE_ID>"
3745 #: build/C/man2/perf_event_open.2:661
3746 msgid "Records a unique ID for the opened event's group leader."
3750 #: build/C/man2/perf_event_open.2:661
3752 msgid "B<PERF_SAMPLE_CPU>"
3753 msgstr "B<PERF_SAMPLE_CPU>"
3756 #: build/C/man2/perf_event_open.2:664
3757 msgid "Records CPU number."
3761 #: build/C/man2/perf_event_open.2:664
3763 msgid "B<PERF_SAMPLE_PERIOD>"
3764 msgstr "B<PERF_SAMPLE_PERIOD>"
3767 #: build/C/man2/perf_event_open.2:667
3768 msgid "Records the current sampling period."
3772 #: build/C/man2/perf_event_open.2:667
3774 msgid "B<PERF_SAMPLE_STREAM_ID>"
3775 msgstr "B<PERF_SAMPLE_STREAM_ID>"
3778 #: build/C/man2/perf_event_open.2:675
3780 "Records a unique ID for the opened event. Unlike B<PERF_SAMPLE_ID> the "
3781 "actual ID is returned, not the group leader. This ID is the same as the one "
3782 "returned by B<PERF_FORMAT_ID>."
3786 #: build/C/man2/perf_event_open.2:675
3788 msgid "B<PERF_SAMPLE_RAW>"
3789 msgstr "B<PERF_SAMPLE_RAW>"
3792 #: build/C/man2/perf_event_open.2:679
3794 "Records additional data, if applicable. Usually returned by tracepoint "
3799 #: build/C/man2/perf_event_open.2:679
3801 msgid "B<PERF_SAMPLE_BRANCH_STACK> (since Linux 3.4)"
3802 msgstr "B<PERF_SAMPLE_BRANCH_STACK> (Linux 3.4 以降)"
3804 #. commit bce38cd53e5ddba9cb6d708c4ef3d04a4016ec7e
3806 #: build/C/man2/perf_event_open.2:685
3808 "This provides a record of recent branches, as provided by CPU branch "
3809 "sampling hardware (such as Intel Last Branch Record). Not all hardware "
3810 "supports this feature."
3814 #: build/C/man2/perf_event_open.2:689
3816 "See the I<branch_sample_type> field for how to filter which branches are "
3821 #: build/C/man2/perf_event_open.2:689
3823 msgid "B<PERF_SAMPLE_REGS_USER> (since Linux 3.7)"
3824 msgstr "B<PERF_SAMPLE_REGS_USER> (Linux 3.7 以降)"
3826 #. commit 4018994f3d8785275ef0e7391b75c3462c029e56
3828 #: build/C/man2/perf_event_open.2:694
3830 "Records the current user-level CPU register state (the values in the process "
3831 "before the kernel was called)."
3835 #: build/C/man2/perf_event_open.2:694
3837 msgid "B<PERF_SAMPLE_STACK_USER> (since Linux 3.7)"
3838 msgstr "B<PERF_SAMPLE_STACK_USER> (Linux 3.7 以降)"
3840 #. commit c5ebcedb566ef17bda7b02686e0d658a7bb42ee7
3842 #: build/C/man2/perf_event_open.2:698
3843 msgid "Records the user level stack, allowing stack unwinding."
3847 #: build/C/man2/perf_event_open.2:698
3849 msgid "B<PERF_SAMPLE_WEIGHT> (since Linux 3.10)"
3850 msgstr "B<PERF_SAMPLE_WEIGHT> (Linux 3.10 以降)"
3852 #. commit c3feedf2aaf9ac8bad6f19f5d21e4ee0b4b87e9c
3854 #: build/C/man2/perf_event_open.2:705
3856 "Records a hardware provided weight value that expresses how costly the "
3857 "sampled event was. This allows the hardware to highlight expensive events "
3862 #: build/C/man2/perf_event_open.2:705
3864 msgid "B<PERF_SAMPLE_DATA_SRC> (since Linux 3.10)"
3865 msgstr "B<PERF_SAMPLE_DATA_SRC> (Linux 3.10 以降)"
3867 #. commit d6be9ad6c960f43800a6f118932bc8a5a4eadcd1
3869 #: build/C/man2/perf_event_open.2:712
3871 "Records the data source: where in the memory hierarchy the data associated "
3872 "with the sampled instruction came from. This is available only if the "
3873 "underlying hardware supports this feature."
3877 #: build/C/man2/perf_event_open.2:712
3879 msgid "B<PERF_SAMPLE_IDENTIFIER> (since Linux 3.12)"
3880 msgstr "B<PERF_SAMPLE_IDENTIFIER> (Linux 3.12 以降)"
3882 #. commit ff3d527cebc1fa3707c617bfe9e74f53fcfb0955
3884 #: build/C/man2/perf_event_open.2:720
3886 "Places the B<SAMPLE_ID> value in a fixed position in the record, either at "
3887 "the beginning (for sample events) or at the end (if a non-sample event)."
3891 #: build/C/man2/perf_event_open.2:732
3893 "This was necessary because a sample stream may have records from various "
3894 "different event sources with different I<sample_type> settings. Parsing the "
3895 "event stream properly was not possible because the format of the record was "
3896 "needed to find B<SAMPLE_ID>, but the format could not be found without "
3897 "knowing what event the sample belonged to (causing a circular dependency)."
3901 #: build/C/man2/perf_event_open.2:742
3903 "The B<PERF_SAMPLE_IDENTIFIER> setting makes the event stream always parsable "
3904 "by putting B<SAMPLE_ID> in a fixed location, even though it means having "
3905 "duplicate B<SAMPLE_ID> values in records."
3909 #: build/C/man2/perf_event_open.2:742
3911 msgid "B<PERF_SAMPLE_TRANSACTION> (since Linux 3.13)"
3912 msgstr "B<PERF_SAMPLE_TRANSACTION> (Linux 3.13 以降)"
3914 #. commit fdfbbd07e91f8fe387140776f3fd94605f0c89e5
3916 #: build/C/man2/perf_event_open.2:747
3918 "Records reasons for transactional memory abort events (for example, from "
3919 "Intel TSX transactional memory support)."
3923 #: build/C/man2/perf_event_open.2:755
3925 "The I<precise_ip> setting must be greater than 0 and a transactional memory "
3926 "abort event must be measured or no values will be recorded. Also note that "
3927 "some perf_event measurements, such as sampled cycle counting, may cause "
3928 "extraneous aborts (by causing an interrupt during a transaction)."
3932 #: build/C/man2/perf_event_open.2:756
3934 msgid "I<read_format>"
3935 msgstr "I<read_format>"
3938 #: build/C/man2/perf_event_open.2:763
3940 "This field specifies the format of the data returned by B<read>(2) on a "
3941 "B<perf_event_open>() file descriptor."
3945 #: build/C/man2/perf_event_open.2:764
3947 msgid "B<PERF_FORMAT_TOTAL_TIME_ENABLED>"
3948 msgstr "B<PERF_FORMAT_TOTAL_TIME_ENABLED>"
3951 #: build/C/man2/perf_event_open.2:771
3953 "Adds the 64-bit I<time_enabled> field. This can be used to calculate "
3954 "estimated totals if the PMU is overcommitted and multiplexing is happening."
3958 #: build/C/man2/perf_event_open.2:771
3960 msgid "B<PERF_FORMAT_TOTAL_TIME_RUNNING>"
3961 msgstr "B<PERF_FORMAT_TOTAL_TIME_RUNNING>"
3964 #: build/C/man2/perf_event_open.2:778
3966 "Adds the 64-bit I<time_running> field. This can be used to calculate "
3967 "estimated totals if the PMU is overcommitted and multiplexing is happening."
3971 #: build/C/man2/perf_event_open.2:778
3973 msgid "B<PERF_FORMAT_ID>"
3974 msgstr "B<PERF_FORMAT_ID>"
3977 #: build/C/man2/perf_event_open.2:781
3978 msgid "Adds a 64-bit unique value that corresponds to the event group."
3982 #: build/C/man2/perf_event_open.2:781
3984 msgid "B<PERF_FORMAT_GROUP>"
3985 msgstr "B<PERF_FORMAT_GROUP>"
3988 #: build/C/man2/perf_event_open.2:784
3989 msgid "Allows all counter values in an event group to be read with one read."
3993 #: build/C/man2/perf_event_open.2:785
3996 msgstr "I<disabled>"
3999 #: build/C/man2/perf_event_open.2:795
4001 "The I<disabled> bit specifies whether the counter starts out disabled or "
4002 "enabled. If disabled, the event can later be enabled by B<ioctl>(2), "
4003 "B<prctl>(2), or I<enable_on_exec>."
4007 #: build/C/man2/perf_event_open.2:806
4009 "When creating an event group, typically the group leader is initialized with "
4010 "I<disabled> set to 1 and any child events are initialized with I<disabled> "
4011 "set to 0. Despite I<disabled> being 0, the child events will not start "
4012 "until the group leader is enabled."
4016 #: build/C/man2/perf_event_open.2:806
4022 #: build/C/man2/perf_event_open.2:815
4024 "The I<inherit> bit specifies that this counter should count events of child "
4025 "tasks as well as the task specified. This applies only to new children, not "
4026 "to any existing children at the time the counter is created (nor to any new "
4027 "children of existing children)."
4031 #: build/C/man2/perf_event_open.2:820
4033 "Inherit does not work for some combinations of I<read_format>s, such as "
4034 "B<PERF_FORMAT_GROUP>."
4038 #: build/C/man2/perf_event_open.2:820
4044 #: build/C/man2/perf_event_open.2:833
4046 "The I<pinned> bit specifies that the counter should always be on the CPU if "
4047 "at all possible. It applies only to hardware counters and only to group "
4048 "leaders. If a pinned counter cannot be put onto the CPU (e.g., because "
4049 "there are not enough hardware counters or because of a conflict with some "
4050 "other event), then the counter goes into an 'error' state, where reads "
4051 "return end-of-file (i.e., B<read>(2) returns 0) until the counter is "
4052 "subsequently enabled or disabled."
4056 #: build/C/man2/perf_event_open.2:833
4058 msgid "I<exclusive>"
4059 msgstr "I<exclusive>"
4062 #: build/C/man2/perf_event_open.2:842
4064 "The I<exclusive> bit specifies that when this counter's group is on the CPU, "
4065 "it should be the only group using the CPU's counters. In the future this "
4066 "may allow monitoring programs to support PMU features that need to run alone "
4067 "so that they do not disrupt other hardware counters."
4071 #: build/C/man2/perf_event_open.2:849
4073 "Note that many unexpected situations may prevent events with the "
4074 "I<exclusive> bit set from ever running. This includes any users running a "
4075 "system-wide measurement as well as any kernel use of the performance "
4076 "counters (including the commonly enabled NMI Watchdog Timer interface)."
4080 #: build/C/man2/perf_event_open.2:849
4082 msgid "I<exclude_user>"
4083 msgstr "I<exclude_user>"
4086 #: build/C/man2/perf_event_open.2:852
4088 "If this bit is set, the count excludes events that happen in user space."
4092 #: build/C/man2/perf_event_open.2:852
4094 msgid "I<exclude_kernel>"
4095 msgstr "I<exclude_kernel>"
4098 #: build/C/man2/perf_event_open.2:855
4100 "If this bit is set, the count excludes events that happen in kernel-space."
4104 #: build/C/man2/perf_event_open.2:855
4106 msgid "I<exclude_hv>"
4107 msgstr "I<exclude_hv>"
4110 #: build/C/man2/perf_event_open.2:863
4112 "If this bit is set, the count excludes events that happen in the "
4113 "hypervisor. This is mainly for PMUs that have built-in support for handling "
4114 "this (such as POWER). Extra support is needed for handling hypervisor "
4115 "measurements on most machines."
4119 #: build/C/man2/perf_event_open.2:863
4121 msgid "I<exclude_idle>"
4122 msgstr "I<exclude_idle>"
4125 #: build/C/man2/perf_event_open.2:866
4126 msgid "If set, don't count when the CPU is idle."
4130 #: build/C/man2/perf_event_open.2:866
4136 #: build/C/man2/perf_event_open.2:880
4138 "The I<mmap> bit enables generation of B<PERF_RECORD_MMAP> samples for every "
4139 "B<mmap>(2) call that has B<PROT_EXEC> set. This allows tools to notice new "
4140 "executable code being mapped into a program (dynamic shared libraries for "
4141 "example) so that addresses can be mapped back to the original code."
4145 #: build/C/man2/perf_event_open.2:880 build/C/man2/perf_event_open.2:1761
4150 #. commit 82b897782d10fcc4930c9d4a15b175348fdd2871
4152 #: build/C/man2/perf_event_open.2:899
4154 "The I<comm> bit enables tracking of process command name as modified by the "
4155 "B<exec>(2) and B<prctl>(PR_SET_NAME) system calls as well as writing to I</"
4156 "proc/self/comm>. If the I<comm_exec> flag is also successfully set "
4157 "(possible since Linux 3.16), then the misc flag "
4158 "B<PERF_RECORD_MISC_COMM_EXEC> can be used to differentiate the B<exec>(2) "
4159 "case from the others."
4163 #: build/C/man2/perf_event_open.2:899
4169 #: build/C/man2/perf_event_open.2:906
4171 "If this bit is set, then I<sample_frequency> not I<sample_period> is used "
4172 "when setting up the sampling interval."
4176 #: build/C/man2/perf_event_open.2:906
4178 msgid "I<inherit_stat>"
4179 msgstr "I<inherit_stat>"
4182 #: build/C/man2/perf_event_open.2:913
4184 "This bit enables saving of event counts on context switch for inherited "
4185 "tasks. This is meaningful only if the I<inherit> field is set."
4189 #: build/C/man2/perf_event_open.2:913
4191 msgid "I<enable_on_exec>"
4192 msgstr "I<enable_on_exec>"
4195 #: build/C/man2/perf_event_open.2:918
4197 "If this bit is set, a counter is automatically enabled after a call to "
4202 #: build/C/man2/perf_event_open.2:918
4208 #: build/C/man2/perf_event_open.2:922
4210 "If this bit is set, then fork/exit notifications are included in the ring "
4215 #: build/C/man2/perf_event_open.2:922
4217 msgid "I<watermark>"
4218 msgstr "I<watermark>"
4221 #: build/C/man2/perf_event_open.2:930
4223 "If set, have an overflow notification happen when we cross the "
4224 "I<wakeup_watermark> boundary. Otherwise, overflow notifications happen "
4225 "after I<wakeup_events> samples."
4229 #: build/C/man2/perf_event_open.2:930
4231 msgid "I<precise_ip> (since Linux 2.6.35)"
4232 msgstr "I<precise_ip> (Linux 2.6.35 以降)"
4234 #. commit ab608344bcbde4f55ec4cd911b686b0ce3eae076
4236 #: build/C/man2/perf_event_open.2:941
4238 "This controls the amount of skid. Skid is how many instructions execute "
4239 "between an event of interest happening and the kernel being able to stop and "
4240 "record the event. Smaller skid is better and allows more accurate reporting "
4241 "of which events correspond to which instructions, but hardware is often "
4242 "limited with how small this can be."
4246 #: build/C/man2/perf_event_open.2:943
4247 msgid "The values of this are the following:"
4251 #: build/C/man2/perf_event_open.2:944
4257 #: build/C/man2/perf_event_open.2:948
4258 msgid "B<SAMPLE_IP> can have arbitrary skid."
4262 #: build/C/man2/perf_event_open.2:948
4268 #: build/C/man2/perf_event_open.2:952
4269 msgid "B<SAMPLE_IP> must have constant skid."
4273 #: build/C/man2/perf_event_open.2:952
4279 #: build/C/man2/perf_event_open.2:956
4280 msgid "B<SAMPLE_IP> requested to have 0 skid."
4284 #: build/C/man2/perf_event_open.2:956
4290 #: build/C/man2/perf_event_open.2:962
4291 msgid "B<SAMPLE_IP> must have 0 skid. See also B<PERF_RECORD_MISC_EXACT_IP>."
4295 #: build/C/man2/perf_event_open.2:963
4297 msgid "I<mmap_data> (since Linux 2.6.36)"
4298 msgstr "I<mmap_data> (Linux 2.6.36 以降)"
4300 #. commit 3af9e859281bda7eb7c20b51879cf43aa788ac2e
4302 #: build/C/man2/perf_event_open.2:976
4304 "The counterpart of the I<mmap> field. This enables generation of "
4305 "B<PERF_RECORD_MMAP> samples for B<mmap>(2) calls that do not have "
4306 "B<PROT_EXEC> set (for example data and SysV shared memory)."
4310 #: build/C/man2/perf_event_open.2:976
4312 msgid "I<sample_id_all> (since Linux 2.6.38)"
4313 msgstr "I<sample_id_all> (Linux 2.6.38 以降)"
4315 #. commit c980d1091810df13f21aabbce545fd98f545bbf7
4317 #: build/C/man2/perf_event_open.2:985
4319 "If set, then TID, TIME, ID, STREAM_ID, and CPU can additionally be included "
4320 "in non-B<PERF_RECORD_SAMPLE>s if the corresponding I<sample_type> is "
4325 #: build/C/man2/perf_event_open.2:993
4327 "If B<PERF_SAMPLE_IDENTIFIER> is specified, then an additional ID value is "
4328 "included as the last value to ease parsing the record stream. This may lead "
4329 "to the I<id> value appearing twice."
4333 #: build/C/man2/perf_event_open.2:995
4334 msgid "The layout is described by this pseudo-structure:"
4338 #: build/C/man2/perf_event_open.2:1005
4341 "struct sample_id {\n"
4342 " { u32 pid, tid; } /* if PERF_SAMPLE_TID set */\n"
4343 " { u64 time; } /* if PERF_SAMPLE_TIME set */\n"
4344 " { u64 id; } /* if PERF_SAMPLE_ID set */\n"
4345 " { u64 stream_id;} /* if PERF_SAMPLE_STREAM_ID set */\n"
4346 " { u32 cpu, res; } /* if PERF_SAMPLE_CPU set */\n"
4347 " { u64 id; } /* if PERF_SAMPLE_IDENTIFIER set */\n"
4350 "struct sample_id {\n"
4351 " { u32 pid, tid; } /* if PERF_SAMPLE_TID set */\n"
4352 " { u64 time; } /* if PERF_SAMPLE_TIME set */\n"
4353 " { u64 id; } /* if PERF_SAMPLE_ID set */\n"
4354 " { u64 stream_id;} /* if PERF_SAMPLE_STREAM_ID set */\n"
4355 " { u32 cpu, res; } /* if PERF_SAMPLE_CPU set */\n"
4356 " { u64 id; } /* if PERF_SAMPLE_IDENTIFIER set */\n"
4360 #: build/C/man2/perf_event_open.2:1006
4362 msgid "I<exclude_host> (since Linux 3.2)"
4363 msgstr "I<exclude_host> (Linux 3.2 以降)"
4365 #. commit a240f76165e6255384d4bdb8139895fac7988799
4367 #: build/C/man2/perf_event_open.2:1010
4368 msgid "Do not measure time spent in VM host."
4372 #: build/C/man2/perf_event_open.2:1010
4374 msgid "I<exclude_guest> (since Linux 3.2)"
4375 msgstr "I<exclude_guest> (Linux 3.2 以降)"
4377 #. commit a240f76165e6255384d4bdb8139895fac7988799
4379 #: build/C/man2/perf_event_open.2:1014
4380 msgid "Do not measure time spent in VM guest."
4384 #: build/C/man2/perf_event_open.2:1014
4386 msgid "I<exclude_callchain_kernel> (since Linux 3.7)"
4387 msgstr "I<exclude_callchain_kernel> (Linux 3.7 以降)"
4389 #. commit d077526485d5c9b12fe85d0b2b3b7041e6bc5f91
4391 #: build/C/man2/perf_event_open.2:1018
4392 msgid "Do not include kernel callchains."
4396 #: build/C/man2/perf_event_open.2:1018
4398 msgid "I<exclude_callchain_user> (since Linux 3.7)"
4399 msgstr "I<exclude_callchain_user> (Linux 3.7 以降)"
4401 #. commit d077526485d5c9b12fe85d0b2b3b7041e6bc5f91
4403 #: build/C/man2/perf_event_open.2:1022
4404 msgid "Do not include user callchains."
4408 #: build/C/man2/perf_event_open.2:1022
4410 msgid "I<mmap2> (since Linux 3.16)"
4411 msgstr "I<mmap2> (Linux 3.16 以降)"
4413 #. commit 13d7a2410fa637f450a29ecb515ac318ee40c741
4414 #. This is tricky; was committed during 3.12 development
4415 #. but right before release was disabled.
4416 #. So while you could select mmap2 starting with 3.12
4417 #. it did not work until 3.16
4418 #. commit a5a5ba72843dd05f991184d6cb9a4471acce1005
4420 #: build/C/man2/perf_event_open.2:1035
4422 "Generate an extended executable mmap record that contains enough additional "
4423 "information to uniquely identify shared mappings. The I<mmap> flag must "
4424 "also be set for this to work."
4428 #: build/C/man2/perf_event_open.2:1035
4430 msgid "I<comm_exec> (since Linux 3.16)"
4431 msgstr "I<comm_exec> (Linux 3.16 以降)"
4433 #. commit 82b897782d10fcc4930c9d4a15b175348fdd2871
4435 #: build/C/man2/perf_event_open.2:1051
4437 "This is purely a feature-detection flag, it does not change kernel "
4438 "behavior. If this flag can successfully be set, then, when I<comm> is "
4439 "enabled, the B<PERF_RECORD_MISC_COMM_EXEC> flag will be set in the I<misc> "
4440 "field of a comm record header if the rename event being reported was caused "
4441 "by a call to B<exec>(2). This allows tools to distinguish between the "
4442 "various types of process renaming."
4446 #: build/C/man2/perf_event_open.2:1051
4448 msgid "I<wakeup_events>, I<wakeup_watermark>"
4449 msgstr "I<wakeup_events>, I<wakeup_watermark>"
4452 #: build/C/man2/perf_event_open.2:1061
4454 "This union sets how many samples (I<wakeup_events>) or bytes "
4455 "(I<wakeup_watermark>) happen before an overflow notification happens. "
4456 "Which one is used is selected by the I<watermark> bit flag."
4460 #: build/C/man2/perf_event_open.2:1071
4462 "I<wakeup_events> counts only B<PERF_RECORD_SAMPLE> record types. To receive "
4463 "overflow notification for all B<PERF_RECORD> types choose watermark and set "
4464 "I<wakeup_watermark> to 1."
4467 #. commit f506b3dc0ec454a16d40cab9ee5d75435b39dc50
4469 #: build/C/man2/perf_event_open.2:1077
4471 "Prior to Linux 3.0 setting I<wakeup_events> to 0 resulted in no overflow "
4472 "notifications; more recent kernels treat 0 the same as 1."
4476 #: build/C/man2/perf_event_open.2:1077
4478 msgid "I<bp_type> (since Linux 2.6.33)"
4479 msgstr "I<bp_type> (Linux 2.6.33 以降)"
4481 #. commit 24f1e32c60c45c89a997c73395b69c8af6f0a84e
4483 #: build/C/man2/perf_event_open.2:1082
4484 msgid "This chooses the breakpoint type. It is one of:"
4488 #: build/C/man2/perf_event_open.2:1083
4490 msgid "B<HW_BREAKPOINT_EMPTY>"
4491 msgstr "B<HW_BREAKPOINT_EMPTY>"
4494 #: build/C/man2/perf_event_open.2:1086
4495 msgid "No breakpoint."
4499 #: build/C/man2/perf_event_open.2:1086
4501 msgid "B<HW_BREAKPOINT_R>"
4502 msgstr "B<HW_BREAKPOINT_R>"
4505 #: build/C/man2/perf_event_open.2:1089
4506 msgid "Count when we read the memory location."
4510 #: build/C/man2/perf_event_open.2:1089
4512 msgid "B<HW_BREAKPOINT_W>"
4513 msgstr "B<HW_BREAKPOINT_W>"
4516 #: build/C/man2/perf_event_open.2:1092
4517 msgid "Count when we write the memory location."
4521 #: build/C/man2/perf_event_open.2:1092
4523 msgid "B<HW_BREAKPOINT_RW>"
4524 msgstr "B<HW_BREAKPOINT_RW>"
4527 #: build/C/man2/perf_event_open.2:1095
4528 msgid "Count when we read or write the memory location."
4532 #: build/C/man2/perf_event_open.2:1095
4534 msgid "B<HW_BREAKPOINT_X>"
4535 msgstr "B<HW_BREAKPOINT_X>"
4538 #: build/C/man2/perf_event_open.2:1098
4539 msgid "Count when we execute code at the memory location."
4543 #: build/C/man2/perf_event_open.2:1107
4545 "The values can be combined via a bitwise or, but the combination of "
4546 "B<HW_BREAKPOINT_R> or B<HW_BREAKPOINT_W> with B<HW_BREAKPOINT_X> is not "
4551 #: build/C/man2/perf_event_open.2:1108
4553 msgid "I<bp_addr> (since Linux 2.6.33)"
4554 msgstr "I<bp_addr> (Linux 2.6.33 以降)"
4556 #. commit 24f1e32c60c45c89a997c73395b69c8af6f0a84e
4558 #: build/C/man2/perf_event_open.2:1116
4560 "I<bp_addr> address of the breakpoint. For execution breakpoints this is the "
4561 "memory address of the instruction of interest; for read and write "
4562 "breakpoints it is the memory address of the memory location of interest."
4566 #: build/C/man2/perf_event_open.2:1116
4568 msgid "I<config1> (since Linux 2.6.39)"
4569 msgstr "I<config1> (Linux 2.6.39 以降)"
4571 #. commit a7e3ed1e470116c9d12c2f778431a481a6be8ab6
4573 #: build/C/man2/perf_event_open.2:1124
4575 "I<config1> is used for setting events that need an extra register or "
4576 "otherwise do not fit in the regular config field. Raw OFFCORE_EVENTS on "
4577 "Nehalem/Westmere/SandyBridge use this field on 3.3 and later kernels."
4581 #: build/C/man2/perf_event_open.2:1124
4583 msgid "I<bp_len> (since Linux 2.6.33)"
4584 msgstr "I<bp_len> (Linux 2.6.33 以降)"
4586 #. commit 24f1e32c60c45c89a997c73395b69c8af6f0a84e
4588 #: build/C/man2/perf_event_open.2:1139
4590 "I<bp_len> is the length of the breakpoint being measured if I<type> is "
4591 "B<PERF_TYPE_BREAKPOINT>. Options are B<HW_BREAKPOINT_LEN_1>, "
4592 "B<HW_BREAKPOINT_LEN_2>, B<HW_BREAKPOINT_LEN_4>, B<HW_BREAKPOINT_LEN_8>. For "
4593 "an execution breakpoint, set this to I<sizeof(long)>."
4597 #: build/C/man2/perf_event_open.2:1139
4599 msgid "I<config2> (since Linux 2.6.39)"
4600 msgstr "I<config2> (Linux 2.6.39 以降)"
4602 #. commit a7e3ed1e470116c9d12c2f778431a481a6be8ab6
4604 #: build/C/man2/perf_event_open.2:1147
4605 msgid "I<config2> is a further extension of the I<config1> field."
4609 #: build/C/man2/perf_event_open.2:1147
4611 msgid "I<branch_sample_type> (since Linux 3.4)"
4612 msgstr "I<branch_sample_type> (Linux 3.4 以降)"
4614 #. commit bce38cd53e5ddba9cb6d708c4ef3d04a4016ec7e
4616 #: build/C/man2/perf_event_open.2:1154
4618 "If B<PERF_SAMPLE_BRANCH_STACK> is enabled, then this specifies what branches "
4619 "to include in the branch record."
4623 #: build/C/man2/perf_event_open.2:1160
4625 "The first part of the value is the privilege level, which is a combination "
4626 "of one of the following values. If the user does not set privilege level "
4627 "explicitly, the kernel will use the event's privilege level. Event and "
4628 "branch privilege levels do not have to match."
4632 #: build/C/man2/perf_event_open.2:1161
4634 msgid "B<PERF_SAMPLE_BRANCH_USER>"
4638 #: build/C/man2/perf_event_open.2:1164
4639 msgid "Branch target is in user space."
4643 #: build/C/man2/perf_event_open.2:1164
4645 msgid "B<PERF_SAMPLE_BRANCH_KERNEL>"
4649 #: build/C/man2/perf_event_open.2:1167
4650 msgid "Branch target is in kernel space."
4654 #: build/C/man2/perf_event_open.2:1167
4656 msgid "B<PERF_SAMPLE_BRANCH_HV>"
4660 #: build/C/man2/perf_event_open.2:1170
4661 msgid "Branch target is in hypervisor."
4665 #: build/C/man2/perf_event_open.2:1170
4667 msgid "B<PERF_SAMPLE_BRANCH_PLM_ALL>"
4671 #: build/C/man2/perf_event_open.2:1173
4672 msgid "A convenience value that is the three preceding values ORed together."
4676 #: build/C/man2/perf_event_open.2:1177
4678 "In addition to the privilege value, at least one or more of the following "
4683 #: build/C/man2/perf_event_open.2:1178
4685 msgid "B<PERF_SAMPLE_BRANCH_ANY>"
4689 #: build/C/man2/perf_event_open.2:1181
4690 msgid "Any branch type."
4694 #: build/C/man2/perf_event_open.2:1181
4696 msgid "B<PERF_SAMPLE_BRANCH_ANY_CALL>"
4700 #: build/C/man2/perf_event_open.2:1184
4701 msgid "Any call branch."
4705 #: build/C/man2/perf_event_open.2:1184
4707 msgid "B<PERF_SAMPLE_BRANCH_ANY_RETURN>"
4711 #: build/C/man2/perf_event_open.2:1187
4712 msgid "Any return branch."
4716 #: build/C/man2/perf_event_open.2:1187
4718 msgid "B<PERF_SAMPLE_BRANCH_IND_CALL>"
4722 #: build/C/man2/perf_event_open.2:1190
4723 msgid "Indirect calls."
4727 #: build/C/man2/perf_event_open.2:1190
4729 msgid "B<PERF_SAMPLE_BRANCH_COND> (since Linux 3.16)"
4730 msgstr "B<PERF_SAMPLE_BRANCH_COND> (Linux 3.16 以降)"
4732 #. commit bac52139f0b7ab31330e98fd87fc5a2664951050
4734 #: build/C/man2/perf_event_open.2:1194
4735 msgid "Conditional branches."
4739 #: build/C/man2/perf_event_open.2:1194
4741 msgid "B<PERF_SAMPLE_BRANCH_ABORT_TX> (since Linux 3.11)"
4742 msgstr "B<PERF_SAMPLE_BRANCH_ABORT_TX> (Linux 3.11 以降)"
4744 #. commit 135c5612c460f89657c4698fe2ea753f6f667963
4746 #: build/C/man2/perf_event_open.2:1198
4747 msgid "Transactional memory aborts."
4751 #: build/C/man2/perf_event_open.2:1198
4753 msgid "B<PERF_SAMPLE_BRANCH_IN_TX> (since Linux 3.11)"
4754 msgstr "B<PERF_SAMPLE_BRANCH_IN_TX> (Linux 3.11 以降)"
4756 #. commit 135c5612c460f89657c4698fe2ea753f6f667963
4758 #: build/C/man2/perf_event_open.2:1202
4759 msgid "Branch in transactional memory transaction."
4763 #: build/C/man2/perf_event_open.2:1202
4765 msgid "B<PERF_SAMPLE_BRANCH_NO_TX> (since Linux 3.11)"
4766 msgstr "B<PERF_SAMPLE_BRANCH_NO_TX> (Linux 3.11 以降)"
4768 #. commit 135c5612c460f89657c4698fe2ea753f6f667963
4770 #: build/C/man2/perf_event_open.2:1206
4771 msgid "Branch not in transactional memory transaction."
4775 #: build/C/man2/perf_event_open.2:1208
4777 msgid "I<sample_regs_user> (since Linux 3.7)"
4778 msgstr "I<sample_regs_user> (Linux 3.7 以降)"
4780 #. commit 4018994f3d8785275ef0e7391b75c3462c029e56
4782 #: build/C/man2/perf_event_open.2:1215
4784 "This bit mask defines the set of user CPU registers to dump on samples. The "
4785 "layout of the register mask is architecture-specific and described in the "
4786 "kernel header I<arch/ARCH/include/uapi/asm/perf_regs.h>."
4790 #: build/C/man2/perf_event_open.2:1215
4792 msgid "I<sample_stack_user> (since Linux 3.7)"
4793 msgstr "I<sample_stack_user> (Linux 3.7 以降)"
4795 #. commit c5ebcedb566ef17bda7b02686e0d658a7bb42ee7
4797 #: build/C/man2/perf_event_open.2:1221
4799 "This defines the size of the user stack to dump if B<PERF_SAMPLE_STACK_USER> "
4804 #: build/C/man2/perf_event_open.2:1221
4806 msgid "Reading results"
4810 #: build/C/man2/perf_event_open.2:1231
4812 "Once a B<perf_event_open>() file descriptor has been opened, the values of "
4813 "the events can be read from the file descriptor. The values that are there "
4814 "are specified by the I<read_format> field in the I<attr> structure at open "
4819 #: build/C/man2/perf_event_open.2:1236
4821 "If you attempt to read into a buffer that is not big enough to hold the data "
4822 "B<ENOSPC> is returned"
4826 #: build/C/man2/perf_event_open.2:1238
4827 msgid "Here is the layout of the data returned by a read:"
4831 #: build/C/man2/perf_event_open.2:1242
4833 "If B<PERF_FORMAT_GROUP> was specified to allow reading all events in a group "
4838 #: build/C/man2/perf_event_open.2:1254
4841 "struct read_format {\n"
4842 " u64 nr; /* The number of events */\n"
4843 " u64 time_enabled; /* if PERF_FORMAT_TOTAL_TIME_ENABLED */\n"
4844 " u64 time_running; /* if PERF_FORMAT_TOTAL_TIME_RUNNING */\n"
4846 " u64 value; /* The value of the event */\n"
4847 " u64 id; /* if PERF_FORMAT_ID */\n"
4853 #: build/C/man2/perf_event_open.2:1262
4854 msgid "If B<PERF_FORMAT_GROUP> was I<not> specified:"
4858 #: build/C/man2/perf_event_open.2:1271
4861 "struct read_format {\n"
4862 " u64 value; /* The value of the event */\n"
4863 " u64 time_enabled; /* if PERF_FORMAT_TOTAL_TIME_ENABLED */\n"
4864 " u64 time_running; /* if PERF_FORMAT_TOTAL_TIME_RUNNING */\n"
4865 " u64 id; /* if PERF_FORMAT_ID */\n"
4870 #: build/C/man2/perf_event_open.2:1275
4871 msgid "The values read are as follows:"
4875 #: build/C/man2/perf_event_open.2:1275
4881 #: build/C/man2/perf_event_open.2:1281
4883 "The number of events in this file descriptor. Only available if "
4884 "B<PERF_FORMAT_GROUP> was specified."
4888 #: build/C/man2/perf_event_open.2:1281
4890 msgid "I<time_enabled>, I<time_running>"
4894 #: build/C/man2/perf_event_open.2:1293
4896 "Total time the event was enabled and running. Normally these are the same. "
4897 "If more events are started, then available counter slots on the PMU, then "
4898 "multiplexing happens and events run only part of the time. In that case, "
4899 "the I<time_enabled> and I<time running> values can be used to scale an "
4900 "estimated value for the count."
4904 #: build/C/man2/perf_event_open.2:1293
4910 #: build/C/man2/perf_event_open.2:1296
4911 msgid "An unsigned 64-bit value containing the counter result."
4915 #: build/C/man2/perf_event_open.2:1296 build/C/man2/perf_event_open.2:1732
4916 #: build/C/man2/perf_event_open.2:1898
4922 #: build/C/man2/perf_event_open.2:1302
4924 "A globally unique value for this particular event, only present if "
4925 "B<PERF_FORMAT_ID> was specified in I<read_format>."
4929 #: build/C/man2/perf_event_open.2:1302
4935 #: build/C/man2/perf_event_open.2:1312
4937 "When using B<perf_event_open>() in sampled mode, asynchronous events (like "
4938 "counter overflow or B<PROT_EXEC> mmap tracking) are logged into a ring-"
4939 "buffer. This ring-buffer is created and accessed through B<mmap>(2)."
4943 #: build/C/man2/perf_event_open.2:1318
4945 "The mmap size should be 1+2^n pages, where the first page is a metadata page "
4946 "(I<struct perf_event_mmap_page>) that contains various bits of information "
4947 "such as where the ring-buffer head is."
4951 #: build/C/man2/perf_event_open.2:1321
4953 "Before kernel 2.6.39, there is a bug that means you must allocate a mmap "
4954 "ring buffer when sampling even if you do not plan to access it."
4958 #: build/C/man2/perf_event_open.2:1323
4959 msgid "The structure of the first metadata mmap page is as follows:"
4963 #: build/C/man2/perf_event_open.2:1352
4966 "struct perf_event_mmap_page {\n"
4967 " __u32 version; /* version number of this structure */\n"
4968 " __u32 compat_version; /* lowest version this is compat with */\n"
4969 " __u32 lock; /* seqlock for synchronization */\n"
4970 " __u32 index; /* hardware counter identifier */\n"
4971 " __s64 offset; /* add to hardware counter value */\n"
4972 " __u64 time_enabled; /* time event active */\n"
4973 " __u64 time_running; /* time event on CPU */\n"
4975 " __u64 capabilities;\n"
4977 " __u64 cap_usr_time / cap_usr_rdpmc / cap_bit0 : 1,\n"
4978 " cap_bit0_is_deprecated : 1,\n"
4979 " cap_user_rdpmc : 1,\n"
4980 " cap_user_time : 1,\n"
4981 " cap_user_time_zero : 1,\n"
4984 " __u16 pmc_width;\n"
4985 " __u16 time_shift;\n"
4986 " __u32 time_mult;\n"
4987 " __u64 time_offset;\n"
4988 " __u64 __reserved[120]; /* Pad to 1k */\n"
4989 " __u64 data_head; /* head in the data section */\n"
4990 " __u64 data_tail; /* user-space written tail */\n"
4995 #: build/C/man2/perf_event_open.2:1358
4997 "The following list describes the fields in the I<perf_event_mmap_page> "
4998 "structure in more detail:"
5002 #: build/C/man2/perf_event_open.2:1358
5008 #: build/C/man2/perf_event_open.2:1361
5009 msgid "Version number of this structure."
5013 #: build/C/man2/perf_event_open.2:1361
5015 msgid "I<compat_version>"
5019 #: build/C/man2/perf_event_open.2:1364
5020 msgid "The lowest version this is compatible with."
5024 #: build/C/man2/perf_event_open.2:1364
5030 #: build/C/man2/perf_event_open.2:1367
5031 msgid "A seqlock for synchronization."
5035 #: build/C/man2/perf_event_open.2:1367
5041 #: build/C/man2/perf_event_open.2:1370
5042 msgid "A unique hardware counter identifier."
5046 #: build/C/man2/perf_event_open.2:1370
5052 #: build/C/man2/perf_event_open.2:1375
5054 "When using rdpmc for reads this offset value must be added to the one "
5055 "returned by rdpmc to get the current total event count."
5059 #: build/C/man2/perf_event_open.2:1375
5061 msgid "I<time_enabled>"
5065 #: build/C/man2/perf_event_open.2:1378
5066 msgid "Time the event was active."
5070 #: build/C/man2/perf_event_open.2:1378
5072 msgid "I<time_running>"
5076 #: build/C/man2/perf_event_open.2:1381
5077 msgid "Time the event was running."
5081 #: build/C/man2/perf_event_open.2:1381
5083 msgid "I<cap_usr_time> / I<cap_usr_rdpmc> / I<cap_bit0> (since Linux 3.4)"
5086 #. commit c7206205d00ab375839bd6c7ddb247d600693c09
5088 #: build/C/man2/perf_event_open.2:1395
5090 "There was a bug in the definition of I<cap_usr_time> and I<cap_usr_rdpmc> "
5091 "from Linux 3.4 until Linux 3.11. Both bits were defined to point to the "
5092 "same location, so it was impossible to know if I<cap_usr_time> or "
5093 "I<cap_usr_rdpmc> were actually set."
5096 #. commit fa7315871046b9a4c48627905691dbde57e51033
5098 #: build/C/man2/perf_event_open.2:1404
5100 "Starting with Linux 3.12, these are renamed to I<cap_bit0> and you should "
5101 "use the I<cap_user_time> and I<cap_user_rdpmc> fields instead."
5105 #: build/C/man2/perf_event_open.2:1405
5107 msgid "I<cap_bit0_is_deprecated> (since Linux 3.12)"
5108 msgstr "I<cap_bit0_is_deprecated> (Linux 3.12 以降)"
5110 #. commit fa7315871046b9a4c48627905691dbde57e51033
5112 #: build/C/man2/perf_event_open.2:1414
5114 "If set, this bit indicates that the kernel supports the properly separated "
5115 "I<cap_user_time> and I<cap_user_rdpmc> bits."
5119 #: build/C/man2/perf_event_open.2:1421
5121 "If not-set, it indicates an older kernel where I<cap_usr_time> and "
5122 "I<cap_usr_rdpmc> map to the same bit and thus both features should be used "
5127 #: build/C/man2/perf_event_open.2:1422
5129 msgid "I<cap_user_rdpmc> (since Linux 3.12)"
5130 msgstr "I<cap_user_rdpmc> (Linux 3.12 以降)"
5132 #. commit fa7315871046b9a4c48627905691dbde57e51033
5134 #: build/C/man2/perf_event_open.2:1428
5136 "If the hardware supports user-space read of performance counters without "
5137 "syscall (this is the \"rdpmc\" instruction on x86), then the following code "
5138 "can be used to do a read:"
5142 #: build/C/man2/perf_event_open.2:1434
5145 "u32 seq, time_mult, time_shift, idx, width;\n"
5146 "u64 count, enabled, running;\n"
5147 "u64 cyc, time_offset;\n"
5149 "u32 seq, time_mult, time_shift, idx, width;\n"
5150 "u64 count, enabled, running;\n"
5151 "u64 cyc, time_offset;\n"
5154 #: build/C/man2/perf_event_open.2:1440
5158 " seq = pc-E<gt>lock;\n"
5160 " enabled = pc-E<gt>time_enabled;\n"
5161 " running = pc-E<gt>time_running;\n"
5164 " seq = pc-E<gt>lock;\n"
5166 " enabled = pc-E<gt>time_enabled;\n"
5167 " running = pc-E<gt>time_running;\n"
5170 #: build/C/man2/perf_event_open.2:1447
5173 " if (pc-E<gt>cap_usr_time && enabled != running) {\n"
5175 " time_offset = pc-E<gt>time_offset;\n"
5176 " time_mult = pc-E<gt>time_mult;\n"
5177 " time_shift = pc-E<gt>time_shift;\n"
5180 " if (pc-E<gt>cap_usr_time && enabled != running) {\n"
5182 " time_offset = pc-E<gt>time_offset;\n"
5183 " time_mult = pc-E<gt>time_mult;\n"
5184 " time_shift = pc-E<gt>time_shift;\n"
5188 #: build/C/man2/perf_event_open.2:1450
5191 " idx = pc-E<gt>index;\n"
5192 " count = pc-E<gt>offset;\n"
5194 " idx = pc-E<gt>index;\n"
5195 " count = pc-E<gt>offset;\n"
5198 #: build/C/man2/perf_event_open.2:1455
5201 " if (pc-E<gt>cap_usr_rdpmc && idx) {\n"
5202 " width = pc-E<gt>pmc_width;\n"
5203 " count += rdpmc(idx - 1);\n"
5206 " if (pc-E<gt>cap_usr_rdpmc && idx) {\n"
5207 " width = pc-E<gt>pmc_width;\n"
5208 " count += rdpmc(idx - 1);\n"
5212 #: build/C/man2/perf_event_open.2:1458
5216 "} while (pc-E<gt>lock != seq);\n"
5219 "} while (pc-E<gt>lock != seq);\n"
5222 #: build/C/man2/perf_event_open.2:1460
5224 msgid "I<cap_user_time> (since Linux 3.12)"
5225 msgstr "I<cap_user_time> (Linux 3.12 以降)"
5227 #. commit fa7315871046b9a4c48627905691dbde57e51033
5229 #: build/C/man2/perf_event_open.2:1465
5231 "This bit indicates the hardware has a constant, nonstop timestamp counter "
5236 #: build/C/man2/perf_event_open.2:1465
5238 msgid "I<cap_user_time_zero> (since Linux 3.12)"
5239 msgstr "I<cap_user_time_zero> (Linux 3.12 以降)"
5241 #. commit fa7315871046b9a4c48627905691dbde57e51033
5243 #: build/C/man2/perf_event_open.2:1472
5245 "Indicates the presence of I<time_zero> which allows mapping timestamp values "
5246 "to the hardware clock."
5250 #: build/C/man2/perf_event_open.2:1472
5252 msgid "I<pmc_width>"
5253 msgstr "I<pmc_width>"
5256 #: build/C/man2/perf_event_open.2:1479
5258 "If I<cap_usr_rdpmc>, this field provides the bit-width of the value read "
5259 "using the rdpmc or equivalent instruction. This can be used to sign extend "
5264 #: build/C/man2/perf_event_open.2:1485
5267 "pmc E<lt>E<lt>= 64 - pmc_width;\n"
5268 "pmc E<gt>E<gt>= 64 - pmc_width; // signed shift right\n"
5271 "pmc E<lt>E<lt>= 64 - pmc_width;\n"
5272 "pmc E<gt>E<gt>= 64 - pmc_width; // signed shift right\n"
5276 #: build/C/man2/perf_event_open.2:1487
5278 msgid "I<time_shift>, I<time_mult>, I<time_offset>"
5279 msgstr "I<time_shift>, I<time_mult>, I<time_offset>"
5282 #: build/C/man2/perf_event_open.2:1494
5284 "If I<cap_usr_time>, these fields can be used to compute the time delta since "
5285 "time_enabled (in nanoseconds) using rdtsc or similar."
5289 #: build/C/man2/perf_event_open.2:1502
5294 " quot = (cyc E<gt>E<gt> time_shift);\n"
5295 " rem = cyc & ((1 E<lt>E<lt> time_shift) - 1);\n"
5296 " delta = time_offset + quot * time_mult +\n"
5297 " ((rem * time_mult) E<gt>E<gt> time_shift);\n"
5301 " quot = (cyc E<gt>E<gt> time_shift);\n"
5302 " rem = cyc & ((1 E<lt>E<lt> time_shift) - 1);\n"
5303 " delta = time_offset + quot * time_mult +\n"
5304 " ((rem * time_mult) E<gt>E<gt> time_shift);\n"
5307 #: build/C/man2/perf_event_open.2:1514
5309 "Where I<time_offset>, I<time_mult>, I<time_shift>, and I<cyc> are read in "
5310 "the seqcount loop described above. This delta can then be added to enabled "
5311 "and possible running (if idx), improving the scaling:"
5315 #: build/C/man2/perf_event_open.2:1522
5318 " enabled += delta;\n"
5320 " running += delta;\n"
5321 " quot = count / running;\n"
5322 " rem = count % running;\n"
5323 " count = quot * enabled + (rem * enabled) / running;\n"
5325 " enabled += delta;\n"
5327 " running += delta;\n"
5328 " quot = count / running;\n"
5329 " rem = count % running;\n"
5330 " count = quot * enabled + (rem * enabled) / running;\n"
5333 #: build/C/man2/perf_event_open.2:1523
5335 msgid "I<time_zero> (since Linux 3.12)"
5336 msgstr "I<time_zero> (Linux 3.12 以降)"
5338 #. commit fa7315871046b9a4c48627905691dbde57e51033
5340 #: build/C/man2/perf_event_open.2:1532
5342 "If I<cap_usr_time_zero> is set, then the hardware clock (the TSC timestamp "
5343 "counter on x86) can be calculated from the I<time_zero>, I<time_mult>, and "
5344 "I<time_shift> values:"
5348 #: build/C/man2/perf_event_open.2:1538
5351 " time = timestamp - time_zero;\n"
5352 " quot = time / time_mult;\n"
5353 " rem = time % time_mult;\n"
5354 " cyc = (quot E<lt>E<lt> time_shift) + (rem E<lt>E<lt> time_shift) / time_mult;\n"
5356 " time = timestamp - time_zero;\n"
5357 " quot = time / time_mult;\n"
5358 " rem = time % time_mult;\n"
5359 " cyc = (quot E<lt>E<lt> time_shift) + (rem E<lt>E<lt> time_shift) / time_mult;\n"
5362 #: build/C/man2/perf_event_open.2:1541
5363 msgid "And vice versa:"
5367 #: build/C/man2/perf_event_open.2:1547
5370 " quot = cyc E<gt>E<gt> time_shift;\n"
5371 " rem = cyc & ((1 E<lt>E<lt> time_shift) - 1);\n"
5372 " timestamp = time_zero + quot * time_mult +\n"
5373 " ((rem * time_mult) E<gt>E<gt> time_shift);\n"
5375 " quot = cyc E<gt>E<gt> time_shift;\n"
5376 " rem = cyc & ((1 E<lt>E<lt> time_shift) - 1);\n"
5377 " timestamp = time_zero + quot * time_mult +\n"
5378 " ((rem * time_mult) E<gt>E<gt> time_shift);\n"
5381 #: build/C/man2/perf_event_open.2:1548
5383 msgid "I<data_head>"
5384 msgstr "I<data_head>"
5387 #: build/C/man2/perf_event_open.2:1554
5389 "This points to the head of the data section. The value continuously "
5390 "increases, it does not wrap. The value needs to be manually wrapped by the "
5391 "size of the mmap buffer before accessing the samples."
5395 #: build/C/man2/perf_event_open.2:1559
5397 "On SMP-capable platforms, after reading the I<data_head> value, user space "
5398 "should issue an rmb()."
5402 #: build/C/man2/perf_event_open.2:1559
5404 msgid "I<data_tail>"
5405 msgstr "I<data_tail>"
5408 #: build/C/man2/perf_event_open.2:1567
5410 "When the mapping is B<PROT_WRITE>, the I<data_tail> value should be written "
5411 "by user space to reflect the last read data. In this case, the kernel will "
5412 "not overwrite unread data."
5416 #: build/C/man2/perf_event_open.2:1569
5417 msgid "The following 2^n ring-buffer pages have the layout described below."
5421 #: build/C/man2/perf_event_open.2:1583
5423 "If I<perf_event_attr.sample_id_all> is set, then all event types will have "
5424 "the sample_type selected fields related to where/when (identity) an event "
5425 "took place (TID, TIME, ID, CPU, STREAM_ID) described in "
5426 "B<PERF_RECORD_SAMPLE> below, it will be stashed just after the "
5427 "I<perf_event_header> and the fields already present for the existing fields, "
5428 "that is, at the end of the payload. That way a newer perf.data file will be "
5429 "supported by older perf tools, with these new optional fields being ignored."
5433 #: build/C/man2/perf_event_open.2:1585
5434 msgid "The mmap values start with a header:"
5438 #: build/C/man2/perf_event_open.2:1593
5441 "struct perf_event_header {\n"
5447 "struct perf_event_header {\n"
5454 #: build/C/man2/perf_event_open.2:1601
5456 "Below, we describe the I<perf_event_header> fields in more detail. For ease "
5457 "of reading, the fields with shorter descriptions are presented first."
5461 #: build/C/man2/perf_event_open.2:1604
5462 msgid "This indicates the size of the record."
5466 #: build/C/man2/perf_event_open.2:1604
5472 #: build/C/man2/perf_event_open.2:1609
5473 msgid "The I<misc> field contains additional information about the sample."
5477 #: build/C/man2/perf_event_open.2:1614
5479 "The CPU mode can be determined from this value by masking with "
5480 "B<PERF_RECORD_MISC_CPUMODE_MASK> and looking for one of the following (note "
5481 "these are not bit masks, only one can be set at a time):"
5485 #: build/C/man2/perf_event_open.2:1615
5487 msgid "B<PERF_RECORD_MISC_CPUMODE_UNKNOWN>"
5488 msgstr "B<PERF_RECORD_MISC_CPUMODE_UNKNOWN>"
5491 #: build/C/man2/perf_event_open.2:1618
5492 msgid "Unknown CPU mode."
5496 #: build/C/man2/perf_event_open.2:1618
5498 msgid "B<PERF_RECORD_MISC_KERNEL>"
5499 msgstr "B<PERF_RECORD_MISC_KERNEL>"
5502 #: build/C/man2/perf_event_open.2:1621
5503 msgid "Sample happened in the kernel."
5507 #: build/C/man2/perf_event_open.2:1621
5509 msgid "B<PERF_RECORD_MISC_USER>"
5510 msgstr "B<PERF_RECORD_MISC_USER>"
5513 #: build/C/man2/perf_event_open.2:1624
5514 msgid "Sample happened in user code."
5518 #: build/C/man2/perf_event_open.2:1624
5520 msgid "B<PERF_RECORD_MISC_HYPERVISOR>"
5521 msgstr "B<PERF_RECORD_MISC_HYPERVISOR>"
5524 #: build/C/man2/perf_event_open.2:1627
5525 msgid "Sample happened in the hypervisor."
5529 #: build/C/man2/perf_event_open.2:1627
5531 #| msgid "B<PERF_RECORD_MISC_GUEST_KERNEL> (since Linux2.6.35)"
5532 msgid "B<PERF_RECORD_MISC_GUEST_KERNEL> (since Linux 2.6.35)"
5533 msgstr "B<PERF_RECORD_MISC_GUEST_KERNEL> (Linux 2.6.35 以降)"
5535 #. commit 39447b386c846bbf1c56f6403c5282837486200f
5537 #: build/C/man2/perf_event_open.2:1631
5538 msgid "Sample happened in the guest kernel."
5542 #: build/C/man2/perf_event_open.2:1631
5544 #| msgid "B<PERF_RECORD_MISC_GUEST_USER (since Linux2.6.35)>"
5545 msgid "B<PERF_RECORD_MISC_GUEST_USER (since Linux 2.6.35)>"
5546 msgstr "B<PERF_RECORD_MISC_GUEST_USER (Linux 2.6.35 以降)>"
5548 #. commit 39447b386c846bbf1c56f6403c5282837486200f
5550 #: build/C/man2/perf_event_open.2:1635
5551 msgid "Sample happened in guest user code."
5555 #: build/C/man2/perf_event_open.2:1639
5556 msgid "In addition, one of the following bits can be set:"
5560 #: build/C/man2/perf_event_open.2:1639
5562 msgid "B<PERF_RECORD_MISC_MMAP_DATA> (since Linux 3.10)"
5563 msgstr "B<PERF_RECORD_MISC_MMAP_DATA> (Linux 3.10 以降)"
5565 #. commit 2fe85427e3bf65d791700d065132772fc26e4d75
5567 #: build/C/man2/perf_event_open.2:1644
5569 "This is set when the mapping is not executable; otherwise the mapping is "
5574 #: build/C/man2/perf_event_open.2:1644
5576 msgid "B<PERF_RECORD_MISC_COMM_EXEC> (since Linux 3.16)"
5577 msgstr "B<PERF_RECORD_MISC_COMM_EXEC> (Linux 3.16 以降)"
5579 #. commit 82b897782d10fcc4930c9d4a15b175348fdd2871
5581 #: build/C/man2/perf_event_open.2:1656
5583 "This is set for a B<PERF_RECORD_COMM> record on kernels more recent than "
5584 "Linux 3.16 if a process name change was caused by an B<exec>(2) system "
5585 "call. It is an alias for B<PERF_RECORD_MISC_MMAP_DATA> since the two values "
5586 "would not be set in the same record."
5590 #: build/C/man2/perf_event_open.2:1656
5592 msgid "B<PERF_RECORD_MISC_EXACT_IP>"
5593 msgstr "B<PERF_RECORD_MISC_EXACT_IP>"
5596 #: build/C/man2/perf_event_open.2:1664
5598 "This indicates that the content of B<PERF_SAMPLE_IP> points to the actual "
5599 "instruction that triggered the event. See also I<perf_event_attr."
5604 #: build/C/man2/perf_event_open.2:1664
5606 msgid "B<PERF_RECORD_MISC_EXT_RESERVED> (since Linux 2.6.35)"
5607 msgstr "B<PERF_RECORD_MISC_EXT_RESERVED> (Linux 2.6.35 以降)"
5609 #. commit 1676b8a077c352085d52578fb4f29350b58b6e74
5611 #: build/C/man2/perf_event_open.2:1668
5612 msgid "This indicates there is extended data available (currently not used)."
5616 #: build/C/man2/perf_event_open.2:1678
5618 "The I<type> value is one of the below. The values in the corresponding "
5619 "record (that follows the header) depend on the I<type> selected as shown."
5623 #: build/C/man2/perf_event_open.2:1680
5625 msgid "B<PERF_RECORD_MMAP>"
5626 msgstr "B<PERF_RECORD_MMAP>"
5629 #: build/C/man2/perf_event_open.2:1687
5631 "The MMAP events record the B<PROT_EXEC> mappings so that we can correlate "
5632 "user-space IPs to code. They have the following structure:"
5636 #: build/C/man2/perf_event_open.2:1698
5640 " struct perf_event_header header;\n"
5645 " char filename[];\n"
5649 " struct perf_event_header header;\n"
5654 " char filename[];\n"
5658 #: build/C/man2/perf_event_open.2:1701 build/C/man2/perf_event_open.2:1755
5659 #: build/C/man2/perf_event_open.2:2276
5665 #: build/C/man2/perf_event_open.2:1704 build/C/man2/perf_event_open.2:1758
5666 #: build/C/man2/perf_event_open.2:2279
5667 msgid "is the process ID."
5671 #: build/C/man2/perf_event_open.2:1704 build/C/man2/perf_event_open.2:1758
5672 #: build/C/man2/perf_event_open.2:2279
5678 #: build/C/man2/perf_event_open.2:1707 build/C/man2/perf_event_open.2:1761
5679 #: build/C/man2/perf_event_open.2:2282
5680 msgid "is the thread ID."
5684 #: build/C/man2/perf_event_open.2:1707 build/C/man2/perf_event_open.2:1891
5685 #: build/C/man2/perf_event_open.2:2282
5691 #: build/C/man2/perf_event_open.2:1716
5693 "is the address of the allocated memory. I<len> is the length of the "
5694 "allocated memory. I<pgoff> is the page offset of the allocated memory. "
5695 "I<filename> is a string describing the backing of the allocated memory."
5699 #: build/C/man2/perf_event_open.2:1717
5701 msgid "B<PERF_RECORD_LOST>"
5702 msgstr "B<PERF_RECORD_LOST>"
5705 #: build/C/man2/perf_event_open.2:1720
5706 msgid "This record indicates when events are lost."
5710 #: build/C/man2/perf_event_open.2:1729
5714 " struct perf_event_header header;\n"
5717 " struct sample_id sample_id;\n"
5721 " struct perf_event_header header;\n"
5724 " struct sample_id sample_id;\n"
5728 #: build/C/man2/perf_event_open.2:1735
5729 msgid "is the unique event ID for the samples that were lost."
5733 #: build/C/man2/perf_event_open.2:1735
5739 #: build/C/man2/perf_event_open.2:1738
5740 msgid "is the number of events that were lost."
5744 #: build/C/man2/perf_event_open.2:1739
5746 msgid "B<PERF_RECORD_COMM>"
5747 msgstr "B<PERF_RECORD_COMM>"
5750 #: build/C/man2/perf_event_open.2:1742
5751 msgid "This record indicates a change in the process name."
5755 #: build/C/man2/perf_event_open.2:1752
5759 " struct perf_event_header header;\n"
5763 " struct sample_id sample_id;\n"
5767 " struct perf_event_header header;\n"
5771 " struct sample_id sample_id;\n"
5775 #: build/C/man2/perf_event_open.2:1764
5776 msgid "is a string containing the new name of the process."
5780 #: build/C/man2/perf_event_open.2:1765
5782 msgid "B<PERF_RECORD_EXIT>"
5783 msgstr "B<PERF_RECORD_EXIT>"
5786 #: build/C/man2/perf_event_open.2:1768
5787 msgid "This record indicates a process exit event."
5791 #: build/C/man2/perf_event_open.2:1778 build/C/man2/perf_event_open.2:1808
5795 " struct perf_event_header header;\n"
5799 " struct sample_id sample_id;\n"
5803 " struct perf_event_header header;\n"
5807 " struct sample_id sample_id;\n"
5811 #: build/C/man2/perf_event_open.2:1780
5813 msgid "B<PERF_RECORD_THROTTLE>, B<PERF_RECORD_UNTHROTTLE>"
5814 msgstr "B<PERF_RECORD_THROTTLE>, B<PERF_RECORD_UNTHROTTLE>"
5817 #: build/C/man2/perf_event_open.2:1783
5818 msgid "This record indicates a throttle/unthrottle event."
5822 #: build/C/man2/perf_event_open.2:1793
5826 " struct perf_event_header header;\n"
5830 " struct sample_id sample_id;\n"
5834 " struct perf_event_header header;\n"
5838 " struct sample_id sample_id;\n"
5842 #: build/C/man2/perf_event_open.2:1795
5844 msgid "B<PERF_RECORD_FORK>"
5845 msgstr "B<PERF_RECORD_FORK>"
5848 #: build/C/man2/perf_event_open.2:1798
5849 msgid "This record indicates a fork event."
5853 #: build/C/man2/perf_event_open.2:1810
5855 msgid "B<PERF_RECORD_READ>"
5856 msgstr "B<PERF_RECORD_READ>"
5859 #: build/C/man2/perf_event_open.2:1813
5860 msgid "This record indicates a read event."
5864 #: build/C/man2/perf_event_open.2:1822
5868 " struct perf_event_header header;\n"
5870 " struct read_format values;\n"
5871 " struct sample_id sample_id;\n"
5875 " struct perf_event_header header;\n"
5877 " struct read_format values;\n"
5878 " struct sample_id sample_id;\n"
5882 #: build/C/man2/perf_event_open.2:1824
5884 msgid "B<PERF_RECORD_SAMPLE>"
5885 msgstr "B<PERF_RECORD_SAMPLE>"
5888 #: build/C/man2/perf_event_open.2:1827
5889 msgid "This record indicates a sample."
5893 #: build/C/man2/perf_event_open.2:1859
5897 " struct perf_event_header header;\n"
5898 " u64 sample_id; /* if PERF_SAMPLE_IDENTIFIER */\n"
5899 " u64 ip; /* if PERF_SAMPLE_IP */\n"
5900 " u32 pid, tid; /* if PERF_SAMPLE_TID */\n"
5901 " u64 time; /* if PERF_SAMPLE_TIME */\n"
5902 " u64 addr; /* if PERF_SAMPLE_ADDR */\n"
5903 " u64 id; /* if PERF_SAMPLE_ID */\n"
5904 " u64 stream_id; /* if PERF_SAMPLE_STREAM_ID */\n"
5905 " u32 cpu, res; /* if PERF_SAMPLE_CPU */\n"
5906 " u64 period; /* if PERF_SAMPLE_PERIOD */\n"
5907 " struct read_format v; /* if PERF_SAMPLE_READ */\n"
5908 " u64 nr; /* if PERF_SAMPLE_CALLCHAIN */\n"
5909 " u64 ips[nr]; /* if PERF_SAMPLE_CALLCHAIN */\n"
5910 " u32 size; /* if PERF_SAMPLE_RAW */\n"
5911 " char data[size]; /* if PERF_SAMPLE_RAW */\n"
5912 " u64 bnr; /* if PERF_SAMPLE_BRANCH_STACK */\n"
5913 " struct perf_branch_entry lbr[bnr];\n"
5914 " /* if PERF_SAMPLE_BRANCH_STACK */\n"
5915 " u64 abi; /* if PERF_SAMPLE_REGS_USER */\n"
5916 " u64 regs[weight(mask)];\n"
5917 " /* if PERF_SAMPLE_REGS_USER */\n"
5918 " u64 size; /* if PERF_SAMPLE_STACK_USER */\n"
5919 " char data[size]; /* if PERF_SAMPLE_STACK_USER */\n"
5920 " u64 dyn_size; /* if PERF_SAMPLE_STACK_USER */\n"
5921 " u64 weight; /* if PERF_SAMPLE_WEIGHT */\n"
5922 " u64 data_src; /* if PERF_SAMPLE_DATA_SRC */\n"
5923 " u64 transaction;/* if PERF_SAMPLE_TRANSACTION */\n"
5927 " struct perf_event_header header;\n"
5928 " u64 sample_id; /* if PERF_SAMPLE_IDENTIFIER */\n"
5929 " u64 ip; /* if PERF_SAMPLE_IP */\n"
5930 " u32 pid, tid; /* if PERF_SAMPLE_TID */\n"
5931 " u64 time; /* if PERF_SAMPLE_TIME */\n"
5932 " u64 addr; /* if PERF_SAMPLE_ADDR */\n"
5933 " u64 id; /* if PERF_SAMPLE_ID */\n"
5934 " u64 stream_id; /* if PERF_SAMPLE_STREAM_ID */\n"
5935 " u32 cpu, res; /* if PERF_SAMPLE_CPU */\n"
5936 " u64 period; /* if PERF_SAMPLE_PERIOD */\n"
5937 " struct read_format v; /* if PERF_SAMPLE_READ */\n"
5938 " u64 nr; /* if PERF_SAMPLE_CALLCHAIN */\n"
5939 " u64 ips[nr]; /* if PERF_SAMPLE_CALLCHAIN */\n"
5940 " u32 size; /* if PERF_SAMPLE_RAW */\n"
5941 " char data[size]; /* if PERF_SAMPLE_RAW */\n"
5942 " u64 bnr; /* if PERF_SAMPLE_BRANCH_STACK */\n"
5943 " struct perf_branch_entry lbr[bnr];\n"
5944 " /* if PERF_SAMPLE_BRANCH_STACK */\n"
5945 " u64 abi; /* if PERF_SAMPLE_REGS_USER */\n"
5946 " u64 regs[weight(mask)];\n"
5947 " /* if PERF_SAMPLE_REGS_USER */\n"
5948 " u64 size; /* if PERF_SAMPLE_STACK_USER */\n"
5949 " char data[size]; /* if PERF_SAMPLE_STACK_USER */\n"
5950 " u64 dyn_size; /* if PERF_SAMPLE_STACK_USER */\n"
5951 " u64 weight; /* if PERF_SAMPLE_WEIGHT */\n"
5952 " u64 data_src; /* if PERF_SAMPLE_DATA_SRC */\n"
5953 " u64 transaction;/* if PERF_SAMPLE_TRANSACTION */\n"
5957 #: build/C/man2/perf_event_open.2:1861
5959 msgid "I<sample_id>"
5960 msgstr "I<sample_id>"
5963 #: build/C/man2/perf_event_open.2:1871
5965 "If B<PERF_SAMPLE_IDENTIFIER> is enabled, a 64-bit unique ID is included. "
5966 "This is a duplication of the B<PERF_SAMPLE_ID> I<id> value, but included at "
5967 "the beginning of the sample so parsers can easily obtain the value."
5971 #: build/C/man2/perf_event_open.2:1871
5977 #: build/C/man2/perf_event_open.2:1877
5979 "If B<PERF_SAMPLE_IP> is enabled, then a 64-bit instruction pointer value is "
5984 #: build/C/man2/perf_event_open.2:1877
5986 msgid "I<pid>, I<tid>"
5987 msgstr "I<pid>, I<tid>"
5990 #: build/C/man2/perf_event_open.2:1883
5992 "If B<PERF_SAMPLE_TID> is enabled, then a 32-bit process ID and 32-bit thread "
5997 #: build/C/man2/perf_event_open.2:1883
6003 #: build/C/man2/perf_event_open.2:1891
6005 "If B<PERF_SAMPLE_TIME> is enabled, then a 64-bit timestamp is included. "
6006 "This is obtained via local_clock() which is a hardware timestamp if "
6007 "available and the jiffies value if not."
6011 #: build/C/man2/perf_event_open.2:1898
6013 "If B<PERF_SAMPLE_ADDR> is enabled, then a 64-bit address is included. This "
6014 "is usually the address of a tracepoint, breakpoint, or software event; "
6015 "otherwise the value is 0."
6019 #: build/C/man2/perf_event_open.2:1906
6021 "If B<PERF_SAMPLE_ID> is enabled, a 64-bit unique ID is included. If the "
6022 "event is a member of an event group, the group leader ID is returned. This "
6023 "ID is the same as the one returned by B<PERF_FORMAT_ID>."
6027 #: build/C/man2/perf_event_open.2:1906
6029 msgid "I<stream_id>"
6030 msgstr "I<stream_id>"
6033 #: build/C/man2/perf_event_open.2:1916
6035 "If B<PERF_SAMPLE_STREAM_ID> is enabled, a 64-bit unique ID is included. "
6036 "Unlike B<PERF_SAMPLE_ID> the actual ID is returned, not the group leader. "
6037 "This ID is the same as the one returned by B<PERF_FORMAT_ID>."
6041 #: build/C/man2/perf_event_open.2:1916
6043 msgid "I<cpu>, I<res>"
6044 msgstr "I<cpu>, I<res>"
6047 #: build/C/man2/perf_event_open.2:1923
6049 "If B<PERF_SAMPLE_CPU> is enabled, this is a 32-bit value indicating which "
6050 "CPU was being used, in addition to a reserved (unused) 32-bit value."
6054 #: build/C/man2/perf_event_open.2:1923
6060 #: build/C/man2/perf_event_open.2:1929
6062 "If B<PERF_SAMPLE_PERIOD> is enabled, a 64-bit value indicating the current "
6063 "sampling period is written."
6067 #: build/C/man2/perf_event_open.2:1929
6073 #: build/C/man2/perf_event_open.2:1940
6075 "If B<PERF_SAMPLE_READ> is enabled, a structure of type read_format is "
6076 "included which has values for all events in the event group. The values "
6077 "included depend on the I<read_format> value used at B<perf_event_open>() "
6082 #: build/C/man2/perf_event_open.2:1940
6084 msgid "I<nr>, I<ips[nr]>"
6085 msgstr "I<nr>, I<ips[nr]>"
6088 #: build/C/man2/perf_event_open.2:1948
6090 "If B<PERF_SAMPLE_CALLCHAIN> is enabled, then a 64-bit number is included "
6091 "which indicates how many following 64-bit instruction pointers will follow. "
6092 "This is the current callchain."
6096 #: build/C/man2/perf_event_open.2:1948
6098 msgid "I<size>, I<data[size]>"
6099 msgstr "I<size>, I<data[size]>"
6102 #: build/C/man2/perf_event_open.2:1955
6104 "If B<PERF_SAMPLE_RAW> is enabled, then a 32-bit value indicating size is "
6105 "included followed by an array of 8-bit values of length size. The values "
6106 "are padded with 0 to have 64-bit alignment."
6110 #: build/C/man2/perf_event_open.2:1960
6112 "This RAW record data is opaque with respect to the ABI. The ABI doesn't "
6113 "make any promises with respect to the stability of its content, it may vary "
6114 "depending on event, hardware, and kernel version."
6118 #: build/C/man2/perf_event_open.2:1960
6120 msgid "I<bnr>, I<lbr[bnr]>"
6121 msgstr "I<bnr>, I<lbr[bnr]>"
6124 #: build/C/man2/perf_event_open.2:1969
6126 "If B<PERF_SAMPLE_BRANCH_STACK> is enabled, then a 64-bit value indicating "
6127 "the number of records is included, followed by I<bnr> I<perf_branch_entry> "
6128 "structures which each include the fields:"
6132 #: build/C/man2/perf_event_open.2:1970
6138 #: build/C/man2/perf_event_open.2:1973
6139 msgid "This indicates the source instruction (may not be a branch)."
6143 #: build/C/man2/perf_event_open.2:1973
6149 #: build/C/man2/perf_event_open.2:1976
6150 msgid "The branch target."
6154 #: build/C/man2/perf_event_open.2:1976
6160 #: build/C/man2/perf_event_open.2:1979
6161 msgid "The branch target was mispredicted."
6165 #: build/C/man2/perf_event_open.2:1979
6167 msgid "I<predicted>"
6168 msgstr "I<predicted>"
6171 #: build/C/man2/perf_event_open.2:1982
6172 msgid "The branch target was predicted."
6176 #: build/C/man2/perf_event_open.2:1982
6178 msgid "I<in_tx> (since Linux 3.11)"
6179 msgstr "I<in_tx> (Linux 3.11 以降)"
6181 #. commit 135c5612c460f89657c4698fe2ea753f6f667963
6183 #: build/C/man2/perf_event_open.2:1986
6184 msgid "The branch was in a transactional memory transaction."
6188 #: build/C/man2/perf_event_open.2:1986
6190 msgid "I<abort> (since Linux 3.11)"
6191 msgstr "I<abort> (Linux 3.11 以降)"
6193 #. commit 135c5612c460f89657c4698fe2ea753f6f667963
6195 #: build/C/man2/perf_event_open.2:1990
6196 msgid "The branch was in an aborted transactional memory transaction."
6200 #: build/C/man2/perf_event_open.2:1994
6202 "The entries are from most to least recent, so the first entry has the most "
6207 #: build/C/man2/perf_event_open.2:2001
6209 "Support for I<mispred> and I<predicted> is optional; if not supported, both "
6214 #: build/C/man2/perf_event_open.2:2005
6216 "The type of branches recorded is specified by the I<branch_sample_type> "
6221 #: build/C/man2/perf_event_open.2:2007
6223 msgid "I<abi>, I<regs[weight(mask)]>"
6224 msgstr "I<abi>, I<regs[weight(mask)]>"
6227 #: build/C/man2/perf_event_open.2:2012
6229 "If B<PERF_SAMPLE_REGS_USER> is enabled, then the user CPU registers are "
6234 #: build/C/man2/perf_event_open.2:2018
6236 "The I<abi> field is one of B<PERF_SAMPLE_REGS_ABI_NONE>, "
6237 "B<PERF_SAMPLE_REGS_ABI_32> or B<PERF_SAMPLE_REGS_ABI_64>."
6241 #: build/C/man2/perf_event_open.2:2028
6243 "The I<regs> field is an array of the CPU registers that were specified by "
6244 "the I<sample_regs_user> attr field. The number of values is the number of "
6245 "bits set in the I<sample_regs_user> bit mask."
6249 #: build/C/man2/perf_event_open.2:2028
6251 msgid "I<size>, I<data[size]>, I<dyn_size>"
6252 msgstr "I<size>, I<data[size]>, I<dyn_size>"
6255 #: build/C/man2/perf_event_open.2:2044
6257 "If B<PERF_SAMPLE_STACK_USER> is enabled, then the user stack is recorded. "
6258 "This can be used to generate stack backtraces. I<size> is the size "
6259 "requested by the user in I<sample_stack_user> or else the maximum record "
6260 "size. I<data> is the stack data (a raw dump of the memory pointed to by the "
6261 "stack pointer at the time of sampling). I<dyn_size> is the amount of data "
6262 "actually dumped (can be less than I<size>)."
6266 #: build/C/man2/perf_event_open.2:2044
6272 #: build/C/man2/perf_event_open.2:2052
6274 "If B<PERF_SAMPLE_WEIGHT> is enabled, then a 64-bit value provided by the "
6275 "hardware is recorded that indicates how costly the event was. This allows "
6276 "expensive events to stand out more clearly in profiles."
6280 #: build/C/man2/perf_event_open.2:2052
6283 msgstr "I<data_src>"
6286 #: build/C/man2/perf_event_open.2:2058
6288 "If B<PERF_SAMPLE_DATA_SRC> is enabled, then a 64-bit value is recorded that "
6289 "is made up of the following fields:"
6293 #: build/C/man2/perf_event_open.2:2059
6299 #: build/C/man2/perf_event_open.2:2062
6300 msgid "Type of opcode, a bitwise combination of:"
6304 #: build/C/man2/perf_event_open.2:2065
6306 msgid "B<PERF_MEM_OP_NA>"
6307 msgstr "B<PERF_MEM_OP_NA>"
6310 #: build/C/man2/perf_event_open.2:2068 build/C/man2/perf_event_open.2:2093
6311 #: build/C/man2/perf_event_open.2:2144 build/C/man2/perf_event_open.2:2168
6312 #: build/C/man2/perf_event_open.2:2184
6313 msgid "Not available"
6317 #: build/C/man2/perf_event_open.2:2068
6319 msgid "B<PERF_MEM_OP_LOAD>"
6320 msgstr "B<PERF_MEM_OP_LOAD>"
6323 #: build/C/man2/perf_event_open.2:2071
6324 msgid "Load instruction"
6328 #: build/C/man2/perf_event_open.2:2071
6330 msgid "B<PERF_MEM_OP_STORE>"
6331 msgstr "B<PERF_MEM_OP_STORE>"
6334 #: build/C/man2/perf_event_open.2:2074
6335 msgid "Store instruction"
6339 #: build/C/man2/perf_event_open.2:2074
6341 msgid "B<PERF_MEM_OP_PFETCH>"
6342 msgstr "B<PERF_MEM_OP_PFETCH>"
6345 #: build/C/man2/perf_event_open.2:2077
6350 #: build/C/man2/perf_event_open.2:2077
6352 msgid "B<PERF_MEM_OP_EXEC>"
6353 msgstr "B<PERF_MEM_OP_EXEC>"
6356 #: build/C/man2/perf_event_open.2:2080
6357 msgid "Executable code"
6361 #: build/C/man2/perf_event_open.2:2082
6367 #: build/C/man2/perf_event_open.2:2087
6369 "Memory hierarchy level hit or miss, a bitwise combination of the following, "
6370 "shifted left by B<PERF_MEM_LVL_SHIFT>:"
6374 #: build/C/man2/perf_event_open.2:2090
6376 msgid "B<PERF_MEM_LVL_NA>"
6377 msgstr "B<PERF_MEM_LVL_NA>"
6380 #: build/C/man2/perf_event_open.2:2093
6382 msgid "B<PERF_MEM_LVL_HIT>"
6383 msgstr "B<PERF_MEM_LVL_HIT>"
6386 #: build/C/man2/perf_event_open.2:2096 build/C/man2/perf_event_open.2:2187
6391 #: build/C/man2/perf_event_open.2:2096
6393 msgid "B<PERF_MEM_LVL_MISS>"
6394 msgstr "B<PERF_MEM_LVL_MISS>"
6397 #: build/C/man2/perf_event_open.2:2099 build/C/man2/perf_event_open.2:2190
6402 #: build/C/man2/perf_event_open.2:2099
6404 msgid "B<PERF_MEM_LVL_L1>"
6405 msgstr "B<PERF_MEM_LVL_L1>"
6408 #: build/C/man2/perf_event_open.2:2102
6409 msgid "Level 1 cache"
6413 #: build/C/man2/perf_event_open.2:2102
6415 msgid "B<PERF_MEM_LVL_LFB>"
6416 msgstr "B<PERF_MEM_LVL_LFB>"
6419 #: build/C/man2/perf_event_open.2:2105
6420 msgid "Line fill buffer"
6424 #: build/C/man2/perf_event_open.2:2105
6426 msgid "B<PERF_MEM_LVL_L2>"
6427 msgstr "B<PERF_MEM_LVL_L2>"
6430 #: build/C/man2/perf_event_open.2:2108
6431 msgid "Level 2 cache"
6435 #: build/C/man2/perf_event_open.2:2108
6437 msgid "B<PERF_MEM_LVL_L3>"
6438 msgstr "B<PERF_MEM_LVL_L3>"
6441 #: build/C/man2/perf_event_open.2:2111
6442 msgid "Level 3 cache"
6446 #: build/C/man2/perf_event_open.2:2111
6448 msgid "B<PERF_MEM_LVL_LOC_RAM>"
6449 msgstr "B<PERF_MEM_LVL_LOC_RAM>"
6452 #: build/C/man2/perf_event_open.2:2114
6457 #: build/C/man2/perf_event_open.2:2114
6459 msgid "B<PERF_MEM_LVL_REM_RAM1>"
6460 msgstr "B<PERF_MEM_LVL_REM_RAM1>"
6463 #: build/C/man2/perf_event_open.2:2117
6464 msgid "Remote DRAM 1 hop"
6468 #: build/C/man2/perf_event_open.2:2117
6470 msgid "B<PERF_MEM_LVL_REM_RAM2>"
6471 msgstr "B<PERF_MEM_LVL_REM_RAM2>"
6474 #: build/C/man2/perf_event_open.2:2120
6475 msgid "Remote DRAM 2 hops"
6479 #: build/C/man2/perf_event_open.2:2120
6481 msgid "B<PERF_MEM_LVL_REM_CCE1>"
6482 msgstr "B<PERF_MEM_LVL_REM_CCE1>"
6485 #: build/C/man2/perf_event_open.2:2123
6486 msgid "Remote cache 1 hop"
6490 #: build/C/man2/perf_event_open.2:2123
6492 msgid "B<PERF_MEM_LVL_REM_CCE2>"
6493 msgstr "B<PERF_MEM_LVL_REM_CCE2>"
6496 #: build/C/man2/perf_event_open.2:2126
6497 msgid "Remote cache 2 hops"
6501 #: build/C/man2/perf_event_open.2:2126
6503 msgid "B<PERF_MEM_LVL_IO>"
6504 msgstr "B<PERF_MEM_LVL_IO>"
6507 #: build/C/man2/perf_event_open.2:2129
6512 #: build/C/man2/perf_event_open.2:2129
6514 msgid "B<PERF_MEM_LVL_UNC>"
6515 msgstr "B<PERF_MEM_LVL_UNC>"
6518 #: build/C/man2/perf_event_open.2:2132
6519 msgid "Uncached memory"
6523 #: build/C/man2/perf_event_open.2:2134
6525 msgid "I<mem_snoop>"
6526 msgstr "I<mem_snoop>"
6529 #: build/C/man2/perf_event_open.2:2138
6531 "Snoop mode, a bitwise combination of the following, shifted left by "
6532 "B<PERF_MEM_SNOOP_SHIFT>:"
6536 #: build/C/man2/perf_event_open.2:2141
6538 msgid "B<PERF_MEM_SNOOP_NA>"
6539 msgstr "B<PERF_MEM_SNOOP_NA>"
6542 #: build/C/man2/perf_event_open.2:2144
6544 msgid "B<PERF_MEM_SNOOP_NONE>"
6545 msgstr "B<PERF_MEM_SNOOP_NONE>"
6548 #: build/C/man2/perf_event_open.2:2147
6553 #: build/C/man2/perf_event_open.2:2147
6555 msgid "B<PERF_MEM_SNOOP_HIT>"
6556 msgstr "B<PERF_MEM_SNOOP_HIT>"
6559 #: build/C/man2/perf_event_open.2:2150
6564 #: build/C/man2/perf_event_open.2:2150
6566 msgid "B<PERF_MEM_SNOOP_MISS>"
6567 msgstr "B<PERF_MEM_SNOOP_MISS>"
6570 #: build/C/man2/perf_event_open.2:2153
6575 #: build/C/man2/perf_event_open.2:2153
6577 msgid "B<PERF_MEM_SNOOP_HITM>"
6578 msgstr "B<PERF_MEM_SNOOP_HITM>"
6581 #: build/C/man2/perf_event_open.2:2156
6582 msgid "Snoop hit modified"
6586 #: build/C/man2/perf_event_open.2:2158
6589 msgstr "I<mem_lock>"
6592 #: build/C/man2/perf_event_open.2:2162
6594 "Lock instruction, a bitwise combination of the following, shifted left by "
6595 "B<PERF_MEM_LOCK_SHIFT>:"
6599 #: build/C/man2/perf_event_open.2:2165
6601 msgid "B<PERF_MEM_LOCK_NA>"
6602 msgstr "B<PERF_MEM_LOCK_NA>"
6605 #: build/C/man2/perf_event_open.2:2168
6607 msgid "B<PERF_MEM_LOCK_LOCKED>"
6608 msgstr "B<PERF_MEM_LOCK_LOCKED>"
6611 #: build/C/man2/perf_event_open.2:2171
6612 msgid "Locked transaction"
6616 #: build/C/man2/perf_event_open.2:2173
6619 msgstr "I<mem_dtlb>"
6622 #: build/C/man2/perf_event_open.2:2178
6624 "TLB access hit or miss, a bitwise combination of the following, shifted left "
6625 "by B<PERF_MEM_TLB_SHIFT>:"
6629 #: build/C/man2/perf_event_open.2:2181
6631 msgid "B<PERF_MEM_TLB_NA>"
6632 msgstr "B<PERF_MEM_TLB_NA>"
6635 #: build/C/man2/perf_event_open.2:2184
6637 msgid "B<PERF_MEM_TLB_HIT>"
6638 msgstr "B<PERF_MEM_TLB_HIT>"
6641 #: build/C/man2/perf_event_open.2:2187
6643 msgid "B<PERF_MEM_TLB_MISS>"
6644 msgstr "B<PERF_MEM_TLB_MISS>"
6647 #: build/C/man2/perf_event_open.2:2190
6649 msgid "B<PERF_MEM_TLB_L1>"
6650 msgstr "B<PERF_MEM_TLB_L1>"
6653 #: build/C/man2/perf_event_open.2:2193
6658 #: build/C/man2/perf_event_open.2:2193
6660 msgid "B<PERF_MEM_TLB_L2>"
6661 msgstr "B<PERF_MEM_TLB_L2>"
6664 #: build/C/man2/perf_event_open.2:2196
6669 #: build/C/man2/perf_event_open.2:2196
6671 msgid "B<PERF_MEM_TLB_WK>"
6672 msgstr "B<PERF_MEM_TLB_WK>"
6675 #: build/C/man2/perf_event_open.2:2199
6676 msgid "Hardware walker"
6680 #: build/C/man2/perf_event_open.2:2199
6682 msgid "B<PERF_MEM_TLB_OS>"
6683 msgstr "B<PERF_MEM_TLB_OS>"
6686 #: build/C/man2/perf_event_open.2:2202
6687 msgid "OS fault handler"
6691 #: build/C/man2/perf_event_open.2:2205
6693 msgid "I<transaction>"
6694 msgstr "I<transaction>"
6697 #: build/C/man2/perf_event_open.2:2211
6699 "If the B<PERF_SAMPLE_TRANSACTION> flag is set, then a 64-bit field is "
6700 "recorded describing the sources of any transactional memory aborts."
6704 #: build/C/man2/perf_event_open.2:2213
6705 msgid "The field is a bitwise combination of the following values:"
6709 #: build/C/man2/perf_event_open.2:2214
6711 msgid "B<PERF_TXN_ELISION>"
6712 msgstr "B<PERF_TXN_ELISION>"
6715 #: build/C/man2/perf_event_open.2:2217
6716 msgid "Abort from an elision type transaction (Intel-CPU-specific)."
6720 #: build/C/man2/perf_event_open.2:2217
6722 msgid "B<PERF_TXN_TRANSACTION>"
6723 msgstr "B<PERF_TXN_TRANSACTION>"
6726 #: build/C/man2/perf_event_open.2:2220
6727 msgid "Abort from a generic transaction."
6731 #: build/C/man2/perf_event_open.2:2220
6733 msgid "B<PERF_TXN_SYNC>"
6734 msgstr "B<PERF_TXN_SYNC>"
6737 #: build/C/man2/perf_event_open.2:2223
6738 msgid "Synchronous abort (related to the reported instruction)."
6742 #: build/C/man2/perf_event_open.2:2223
6744 msgid "B<PERF_TXN_ASYNC>"
6745 msgstr "B<PERF_TXN_ASYNC>"
6748 #: build/C/man2/perf_event_open.2:2226
6749 msgid "Asynchronous abort (not related to the reported instruction)."
6753 #: build/C/man2/perf_event_open.2:2226
6755 msgid "B<PERF_TXN_RETRY>"
6756 msgstr "B<PERF_TXN_RETRY>"
6759 #: build/C/man2/perf_event_open.2:2229
6760 msgid "Retryable abort (retrying the transaction may have succeeded)."
6764 #: build/C/man2/perf_event_open.2:2229
6766 msgid "B<PERF_TXN_CONFLICT>"
6767 msgstr "B<PERF_TXN_CONFLICT>"
6770 #: build/C/man2/perf_event_open.2:2232
6771 msgid "Abort due to memory conflicts with other threads."
6775 #: build/C/man2/perf_event_open.2:2232
6777 msgid "B<PERF_TXN_CAPACITY_WRITE>"
6781 #: build/C/man2/perf_event_open.2:2235
6782 msgid "Abort due to write capacity overflow."
6786 #: build/C/man2/perf_event_open.2:2235
6788 msgid "B<PERF_TXN_CAPACITY_READ>"
6792 #: build/C/man2/perf_event_open.2:2238
6793 msgid "Abort due to read capacity overflow."
6797 #: build/C/man2/perf_event_open.2:2245
6799 "In addition, a user-specified abort code can be obtained from the high 32 "
6800 "bits of the field by shifting right by B<PERF_TXN_ABORT_SHIFT> and masking "
6801 "with B<PERF_TXN_ABORT_MASK>."
6805 #: build/C/man2/perf_event_open.2:2246
6807 msgid "B<PERF_RECORD_MMAP2>"
6808 msgstr "B<PERF_RECORD_MMAP2>"
6811 #: build/C/man2/perf_event_open.2:2255
6813 "This record includes extended information on B<mmap>(2) calls returning "
6814 "executable mappings. The format is similar to that of the "
6815 "B<PERF_RECORD_MMAP> record, but includes extra values that allow uniquely "
6816 "identifying shared mappings."
6820 #: build/C/man2/perf_event_open.2:2274
6824 " struct perf_event_header header;\n"
6833 " u64 ino_generation;\n"
6836 " char filename[];\n"
6837 " struct sample_id sample_id;\n"
6841 " struct perf_event_header header;\n"
6850 " u64 ino_generation;\n"
6853 " char filename[];\n"
6854 " struct sample_id sample_id;\n"
6858 #: build/C/man2/perf_event_open.2:2285
6859 msgid "is the address of the allocated memory."
6863 #: build/C/man2/perf_event_open.2:2285
6869 #: build/C/man2/perf_event_open.2:2288
6870 msgid "is the length of the allocated memory."
6874 #: build/C/man2/perf_event_open.2:2288
6880 #: build/C/man2/perf_event_open.2:2291
6881 msgid "is the page offset of the allocated memory."
6885 #: build/C/man2/perf_event_open.2:2291
6891 #: build/C/man2/perf_event_open.2:2294
6892 msgid "is the major ID of the underlying device."
6896 #: build/C/man2/perf_event_open.2:2294
6902 #: build/C/man2/perf_event_open.2:2297
6903 msgid "is the minor ID of the underlying device."
6907 #: build/C/man2/perf_event_open.2:2297
6913 #: build/C/man2/perf_event_open.2:2300
6914 msgid "is the inode number."
6918 #: build/C/man2/perf_event_open.2:2300
6920 msgid "I<ino_generation>"
6921 msgstr "I<ino_generation>"
6924 #: build/C/man2/perf_event_open.2:2303
6925 msgid "is the inode generation."
6929 #: build/C/man2/perf_event_open.2:2303
6935 #: build/C/man2/perf_event_open.2:2306
6936 msgid "is the protection information."
6940 #: build/C/man2/perf_event_open.2:2306
6946 #: build/C/man2/perf_event_open.2:2309
6947 msgid "is the flags information."
6951 #: build/C/man2/perf_event_open.2:2309
6954 msgstr "I<filename>"
6957 #: build/C/man2/perf_event_open.2:2312
6958 msgid "is a string describing the backing of the allocated memory."
6962 #: build/C/man2/perf_event_open.2:2314
6964 msgid "Overflow handling"
6968 #: build/C/man2/perf_event_open.2:2327
6970 "Events can be set to notify when a threshold is crossed, indicating an "
6971 "overflow. Overflow conditions can be captured by monitoring the event file "
6972 "descriptor with B<poll>(2), B<select>(2), or B<epoll>(2). Alternately, a "
6973 "SIGIO signal handler can be created and the event configured with "
6974 "B<fcntl>(2) to generate SIGIO signals."
6978 #: build/C/man2/perf_event_open.2:2331
6980 "Overflows are generated only by sampling events (I<sample_period> must have "
6985 #: build/C/man2/perf_event_open.2:2333
6986 msgid "There are two ways to generate overflow notifications."
6990 #: build/C/man2/perf_event_open.2:2343
6992 "The first is to set a I<wakeup_events> or I<wakeup_watermark> value that "
6993 "will trigger if a certain number of samples or bytes have been written to "
6994 "the mmap ring buffer. In this case B<POLL_IN> is indicated."
6998 #: build/C/man2/perf_event_open.2:2355
7000 "The other way is by use of the B<PERF_EVENT_IOC_REFRESH> ioctl. This ioctl "
7001 "adds to a counter that decrements each time the event overflows. When "
7002 "nonzero, B<POLL_IN> is indicated, but once the counter reaches 0 B<POLL_HUP> "
7003 "is indicated and the underlying event is disabled."
7006 #. commit 179033b3e064d2cd3f5f9945e76b0a0f0fbf4883
7008 #: build/C/man2/perf_event_open.2:2361
7010 "Starting with Linux 3.18, B<POLL_HUP> is indicated if the event being "
7011 "monitored is attached to a different process and that process exits."
7015 #: build/C/man2/perf_event_open.2:2361
7017 msgid "rdpmc instruction"
7020 #. commit c7206205d00ab375839bd6c7ddb247d600693c09
7022 #: build/C/man2/perf_event_open.2:2369
7024 "Starting with Linux 3.4 on x86, you can use the I<rdpmc> instruction to get "
7025 "low-latency reads without having to enter the kernel. Note that using "
7026 "I<rdpmc> is not necessarily faster than other methods for reading event "
7031 #: build/C/man2/perf_event_open.2:2374
7033 "Support for this can be detected with the I<cap_usr_rdpmc> field in the mmap "
7034 "page; documentation on how to calculate event values can be found in that "
7039 #: build/C/man2/perf_event_open.2:2374
7041 msgid "perf_event ioctl calls"
7045 #: build/C/man2/perf_event_open.2:2379
7046 msgid "Various ioctls act on B<perf_event_open>() file descriptors:"
7050 #: build/C/man2/perf_event_open.2:2379
7052 msgid "B<PERF_EVENT_IOC_ENABLE>"
7053 msgstr "B<PERF_EVENT_IOC_ENABLE>"
7056 #: build/C/man2/perf_event_open.2:2383
7058 "This enables the individual event or event group specified by the file "
7059 "descriptor argument."
7063 #: build/C/man2/perf_event_open.2:2389
7065 "If the B<PERF_IOC_FLAG_GROUP> bit is set in the ioctl argument, then all "
7066 "events in a group are enabled, even if the event specified is not the group "
7067 "leader (but see BUGS)."
7071 #: build/C/man2/perf_event_open.2:2389
7073 msgid "B<PERF_EVENT_IOC_DISABLE>"
7074 msgstr "B<PERF_EVENT_IOC_DISABLE>"
7077 #: build/C/man2/perf_event_open.2:2393
7079 "This disables the individual counter or event group specified by the file "
7080 "descriptor argument."
7084 #: build/C/man2/perf_event_open.2:2400
7086 "Enabling or disabling the leader of a group enables or disables the entire "
7087 "group; that is, while the group leader is disabled, none of the counters in "
7088 "the group will count. Enabling or disabling a member of a group other than "
7089 "the leader affects only that counter; disabling a non-leader stops that "
7090 "counter from counting but doesn't affect any other counter."
7094 #: build/C/man2/perf_event_open.2:2406
7096 "If the B<PERF_IOC_FLAG_GROUP> bit is set in the ioctl argument, then all "
7097 "events in a group are disabled, even if the event specified is not the group "
7098 "leader (but see BUGS)."
7102 #: build/C/man2/perf_event_open.2:2406
7104 msgid "B<PERF_EVENT_IOC_REFRESH>"
7105 msgstr "B<PERF_EVENT_IOC_REFRESH>"
7108 #: build/C/man2/perf_event_open.2:2420
7110 "Non-inherited overflow counters can use this to enable a counter for a "
7111 "number of overflows specified by the argument, after which it is disabled. "
7112 "Subsequent calls of this ioctl add the argument value to the current count. "
7113 "An overflow notification with B<POLL_IN> set will happen on each overflow "
7114 "until the count reaches 0; when that happens a notification with B<POLL_HUP> "
7115 "set is sent and the event is disabled. Using an argument of 0 is considered "
7116 "undefined behavior."
7120 #: build/C/man2/perf_event_open.2:2420
7122 msgid "B<PERF_EVENT_IOC_RESET>"
7123 msgstr "B<PERF_EVENT_IOC_RESET>"
7126 #: build/C/man2/perf_event_open.2:2430
7128 "Reset the event count specified by the file descriptor argument to zero. "
7129 "This resets only the counts; there is no way to reset the multiplexing "
7130 "I<time_enabled> or I<time_running> values."
7134 #: build/C/man2/perf_event_open.2:2436
7136 "If the B<PERF_IOC_FLAG_GROUP> bit is set in the ioctl argument, then all "
7137 "events in a group are reset, even if the event specified is not the group "
7138 "leader (but see BUGS)."
7142 #: build/C/man2/perf_event_open.2:2436
7144 msgid "B<PERF_EVENT_IOC_PERIOD>"
7145 msgstr "B<PERF_EVENT_IOC_PERIOD>"
7148 #: build/C/man2/perf_event_open.2:2439
7149 msgid "This updates the overflow period for the event."
7152 #. commit 3581fe0ef37ce12ac7a4f74831168352ae848edc
7153 #. commit bad7192b842c83e580747ca57104dd51fe08c223
7155 #: build/C/man2/perf_event_open.2:2447
7157 "Since Linux 3.7 (on ARM) and Linux 3.14 (all other architectures), the new "
7158 "period takes effect immediately. On older kernels, the new period did not "
7159 "take effect until after the next overflow."
7163 #: build/C/man2/perf_event_open.2:2450
7165 "The argument is a pointer to a 64-bit value containing the desired new "
7169 #. commit ad0cf3478de8677f720ee06393b3147819568d6a
7171 #: build/C/man2/perf_event_open.2:2455
7173 "Prior to Linux 2.6.36 this ioctl always failed due to a bug in the kernel."
7177 #: build/C/man2/perf_event_open.2:2456
7179 msgid "B<PERF_EVENT_IOC_SET_OUTPUT>"
7183 #: build/C/man2/perf_event_open.2:2461
7185 "This tells the kernel to report event notifications to the specified file "
7186 "descriptor rather than the default one. The file descriptors must all be on "
7191 #: build/C/man2/perf_event_open.2:2464
7193 "The argument specifies the desired file descriptor, or -1 if output should "
7198 #: build/C/man2/perf_event_open.2:2464
7200 msgid "B<PERF_EVENT_IOC_SET_FILTER> (since Linux 2.6.33)"
7201 msgstr "B<PERF_EVENT_IOC_SET_FILTER> (Linux 2.6.33 以降)"
7203 #. commit 6fb2915df7f0747d9044da9dbff5b46dc2e20830
7205 #: build/C/man2/perf_event_open.2:2468
7206 msgid "This adds an ftrace filter to this event."
7210 #: build/C/man2/perf_event_open.2:2470
7211 msgid "The argument is a pointer to the desired ftrace filter."
7215 #: build/C/man2/perf_event_open.2:2470
7217 msgid "B<PERF_EVENT_IOC_ID> (since Linux 3.12)"
7218 msgstr "B<PERF_EVENT_IOC_ID> (Linux 3.12 以降)"
7220 #. commit cf4957f17f2a89984915ea808876d9c82225b862
7222 #: build/C/man2/perf_event_open.2:2474
7223 msgid "This returns the event ID value for the given event file descriptor."
7227 #: build/C/man2/perf_event_open.2:2477
7229 "The argument is a pointer to a 64-bit unsigned integer to hold the result."
7233 #: build/C/man2/perf_event_open.2:2477
7239 #: build/C/man2/perf_event_open.2:2490
7241 "A process can enable or disable all the event groups that are attached to it "
7242 "using the B<prctl>(2) B<PR_TASK_PERF_EVENTS_ENABLE> and "
7243 "B<PR_TASK_PERF_EVENTS_DISABLE> operations. This applies to all counters on "
7244 "the calling process, whether created by this process or by another, and does "
7245 "not affect any counters that this process has created on other processes. "
7246 "It enables or disables only the group leaders, not any other members in the "
7251 #: build/C/man2/perf_event_open.2:2490
7253 msgid "perf_event related configuration files"
7257 #: build/C/man2/perf_event_open.2:2493
7258 msgid "Files in I</proc/sys/kernel/>"
7262 #: build/C/man2/perf_event_open.2:2494
7264 msgid "I</proc/sys/kernel/perf_event_paranoid>"
7268 #: build/C/man2/perf_event_open.2:2500
7270 "The I<perf_event_paranoid> file can be set to restrict access to the "
7271 "performance counters."
7275 #: build/C/man2/perf_event_open.2:2501
7281 #: build/C/man2/perf_event_open.2:2503
7282 msgid "allow only user-space measurements."
7286 #: build/C/man2/perf_event_open.2:2503
7292 #: build/C/man2/perf_event_open.2:2505
7293 msgid "allow both kernel and user measurements (default)."
7297 #: build/C/man2/perf_event_open.2:2505
7303 #: build/C/man2/perf_event_open.2:2507
7304 msgid "allow access to CPU-specific data but not raw tracepoint samples."
7308 #: build/C/man2/perf_event_open.2:2507
7314 #: build/C/man2/perf_event_open.2:2509
7315 msgid "no restrictions."
7319 #: build/C/man2/perf_event_open.2:2515
7321 "The existence of the I<perf_event_paranoid> file is the official method for "
7322 "determining if a kernel supports B<perf_event_open>()."
7326 #: build/C/man2/perf_event_open.2:2515
7328 msgid "I</proc/sys/kernel/perf_event_max_sample_rate>"
7332 #: build/C/man2/perf_event_open.2:2524
7334 "This sets the maximum sample rate. Setting this too high can allow users to "
7335 "sample at a rate that impacts overall machine performance and potentially "
7336 "lock up the machine. The default value is 100000 (samples per second)."
7340 #: build/C/man2/perf_event_open.2:2524
7342 msgid "I</proc/sys/kernel/perf_event_mlock_kb>"
7346 #: build/C/man2/perf_event_open.2:2530
7348 "Maximum number of pages an unprivileged user can B<mlock>(2). The default "
7353 #: build/C/man2/perf_event_open.2:2534
7354 msgid "Files in I</sys/bus/event_source/devices/>"
7358 #: build/C/man2/perf_event_open.2:2540
7360 "Since Linux 2.6.34, the kernel supports having multiple PMUs available for "
7361 "monitoring. Information on how to program these PMUs can be found under I</"
7362 "sys/bus/event_source/devices/>. Each subdirectory corresponds to a "
7367 #: build/C/man2/perf_event_open.2:2540
7369 msgid "I</sys/bus/event_source/devices/*/type> (since Linux 2.6.38)"
7370 msgstr "I</sys/bus/event_source/devices/*/type> (Linux 2.6.38 以降)"
7372 #. commit abe43400579d5de0078c2d3a760e6598e183f871
7374 #: build/C/man2/perf_event_open.2:2548
7376 "This contains an integer that can be used in the I<type> field of "
7377 "I<perf_event_attr> to indicate that you wish to use this PMU."
7381 #: build/C/man2/perf_event_open.2:2548
7383 msgid "I</sys/bus/event_source/devices/*/rdpmc> (since Linux 3.4)"
7384 msgstr "I</sys/bus/event_source/devices/*/rdpmc> (Linux 3.4 以降)"
7386 #. commit 0c9d42ed4cee2aa1dfc3a260b741baae8615744f
7388 #: build/C/man2/perf_event_open.2:2554
7390 "If this file is 1, then direct user-space access to the performance counter "
7391 "registers is allowed via the rdpmc instruction. This can be disabled by "
7392 "echoing 0 to the file."
7396 #: build/C/man2/perf_event_open.2:2554
7398 msgid "I</sys/bus/event_source/devices/*/format/> (since Linux 3.4)"
7399 msgstr "I</sys/bus/event_source/devices/*/format/> (Linux 3.4 以降)"
7401 #. commit 641cc938815dfd09f8fa1ec72deb814f0938ac33
7403 #: build/C/man2/perf_event_open.2:2563
7405 "This subdirectory contains information on the architecture-specific "
7406 "subfields available for programming the various I<config> fields in the "
7407 "I<perf_event_attr> struct."
7411 #: build/C/man2/perf_event_open.2:2574
7413 "The content of each file is the name of the config field, followed by a "
7414 "colon, followed by a series of integer bit ranges separated by commas. For "
7415 "example, the file I<event> may contain the value I<config1:1,6-10,44> which "
7416 "indicates that event is an attribute that occupies bits 1,6-10, and 44 of "
7417 "I<perf_event_attr::config1>."
7421 #: build/C/man2/perf_event_open.2:2574
7423 msgid "I</sys/bus/event_source/devices/*/events/> (since Linux 3.4)"
7424 msgstr "I</sys/bus/event_source/devices/*/events/> (Linux 3.4 以降)"
7426 #. commit 641cc938815dfd09f8fa1ec72deb814f0938ac33
7428 #: build/C/man2/perf_event_open.2:2584
7430 "This subdirectory contains files with predefined events. The contents are "
7431 "strings describing the event settings expressed in terms of the fields found "
7432 "in the previously mentioned I<./format/> directory. These are not "
7433 "necessarily complete lists of all events supported by a PMU, but usually a "
7434 "subset of events deemed useful or interesting."
7438 #: build/C/man2/perf_event_open.2:2592
7440 "The content of each file is a list of attribute names separated by commas. "
7441 "Each entry has an optional value (either hex or decimal). If no value is "
7442 "specified, then it is assumed to be a single-bit field with a value of 1. "
7443 "An example entry may look like this: I<event=0x2,inv,ldlat=3>."
7447 #: build/C/man2/perf_event_open.2:2592
7449 msgid "I</sys/bus/event_source/devices/*/uevent>"
7450 msgstr "I</sys/bus/event_source/devices/*/uevent>"
7453 #: build/C/man2/perf_event_open.2:2596
7455 "This file is the standard kernel device interface for injecting hotplug "
7460 #: build/C/man2/perf_event_open.2:2596
7462 msgid "I</sys/bus/event_source/devices/*/cpumask> (since Linux 3.7)"
7463 msgstr "I</sys/bus/event_source/devices/*/cpumask> (Linux 3.7 以降)"
7465 #. commit 314d9f63f385096580e9e2a06eaa0745d92fe4ac
7467 #: build/C/man2/perf_event_open.2:2606
7469 "The I<cpumask> file contains a comma-separated list of integers that "
7470 "indicate a representative CPU number for each socket (package) on the "
7471 "motherboard. This is needed when setting up uncore or northbridge events, "
7472 "as those PMUs present socket-wide events."
7476 #: build/C/man2/perf_event_open.2:2613
7478 "B<perf_event_open>() returns the new file descriptor, or -1 if an error "
7479 "occurred (in which case, I<errno> is set appropriately)."
7483 #: build/C/man2/perf_event_open.2:2618
7485 "The errors returned by B<perf_event_open>() can be inconsistent, and may "
7486 "vary across processor architectures and performance monitoring units."
7490 #: build/C/man2/perf_event_open.2:2618
7496 #: build/C/man2/perf_event_open.2:2635
7498 "Returned if the I<perf_event_attr> I<size> value is too small (smaller than "
7499 "B<PERF_ATTR_SIZE_VER0>), too big (larger than the page size), or larger than "
7500 "the kernel supports and the extra bytes are not zero. When B<E2BIG> is "
7501 "returned, the I<perf_event_attr> I<size> field is overwritten by the kernel "
7502 "to be the size of the structure it was expecting."
7506 #: build/C/man2/perf_event_open.2:2649
7508 "Returned when the requested event requires B<CAP_SYS_ADMIN> permissions (or "
7509 "a more permissive perf_event paranoid setting). Some common cases where an "
7510 "unprivileged process may encounter this error: attaching to a process owned "
7511 "by a different user; monitoring all processes on a given CPU (i.e., "
7512 "specifying the I<pid> argument as -1); and not setting I<exclude_kernel> "
7513 "when the paranoid setting requires it."
7517 #: build/C/man2/perf_event_open.2:2659
7519 "Returned if the I<group_fd> file descriptor is not valid, or, if "
7520 "B<PERF_FLAG_PID_CGROUP> is set, the cgroup file descriptor in I<pid> is not "
7525 #: build/C/man2/perf_event_open.2:2664
7526 msgid "Returned if the I<attr> pointer points at an invalid memory address."
7530 #: build/C/man2/perf_event_open.2:2690
7532 "Returned if the specified event is invalid. There are many possible reasons "
7533 "for this. A not-exhaustive list: I<sample_freq> is higher than the maximum "
7534 "setting; the I<cpu> to monitor does not exist; I<read_format> is out of "
7535 "range; I<sample_type> is out of range; the I<flags> value is out of range; "
7536 "I<exclusive> or I<pinned> set and the event is not a group leader; the event "
7537 "I<config> values are out of range or set reserved bits; the generic event "
7538 "selected is not supported; or there is not enough room to add the selected "
7543 #: build/C/man2/perf_event_open.2:2690
7549 #: build/C/man2/perf_event_open.2:2696
7551 "Each opened event uses one file descriptor. If a large number of events are "
7552 "opened the per-user file descriptor limit (often 1024) will be hit and no "
7553 "more events can be created."
7557 #: build/C/man2/perf_event_open.2:2700
7559 "Returned when the event involves a feature not supported by the current CPU."
7563 #: build/C/man2/perf_event_open.2:2700 build/C/man2/quotactl.2:440
7569 #: build/C/man2/perf_event_open.2:2707
7571 "Returned if the I<type> setting is not valid. This error is also returned "
7572 "for some unsupported generic events."
7576 #: build/C/man2/perf_event_open.2:2707
7581 #. commit aa2bc1ade59003a379ffc485d6da2d92ea3370a6
7583 #: build/C/man2/perf_event_open.2:2718
7585 "Prior to Linux 3.3, if there was not enough room for the event, B<ENOSPC> "
7586 "was returned. In Linux 3.3, this was changed to B<EINVAL>. B<ENOSPC> is "
7587 "still returned if you try to add more breakpoint events than supported by "
7592 #: build/C/man2/perf_event_open.2:2725
7594 "Returned if B<PERF_SAMPLE_STACK_USER> is set in I<sample_type> and it is not "
7595 "supported by hardware."
7599 #: build/C/man2/perf_event_open.2:2732
7601 "Returned if an event requiring a specific hardware feature is requested but "
7602 "there is no hardware support. This includes requesting low-skid events if "
7603 "not supported, branch tracing if it is not available, sampling if no PMU "
7604 "interrupt is available, and branch stacks for software events."
7608 #: build/C/man2/perf_event_open.2:2737
7610 "Returned on many (but not all) architectures when an unsupported "
7611 "I<exclude_hv>, I<exclude_idle>, I<exclude_user>, or I<exclude_kernel> "
7612 "setting is specified."
7615 #. commit a4e95fc2cbb31d70a65beffeaf8773f881328c34
7617 #: build/C/man2/perf_event_open.2:2746
7619 "It can also happen, as with B<EACCES>, when the requested event requires "
7620 "B<CAP_SYS_ADMIN> permissions (or a more permissive perf_event paranoid "
7621 "setting). This includes setting a breakpoint on a kernel address, and "
7622 "(since Linux 3.13) setting a kernel function-trace tracepoint."
7626 #: build/C/man2/perf_event_open.2:2749
7627 msgid "Returned if attempting to attach to a process that does not exist."
7631 #: build/C/man2/perf_event_open.2:2749
7636 #. commit 0793a61d4df8daeac6492dbf8d2f3e5713caae5e
7637 #. commit cdd6c482c9ff9c55475ee7392ec8f672eddb7be6
7639 #: build/C/man2/perf_event_open.2:2756
7641 "B<perf_event_open>() was introduced in Linux 2.6.31 but was called "
7642 "B<perf_counter_open>(). It was renamed in Linux 2.6.32."
7646 #: build/C/man2/perf_event_open.2:2761
7648 "This B<perf_event_open>() system call Linux- specific and should not be "
7649 "used in programs intended to be portable."
7651 "B<perf_event_open>() システムコールは Linux 固有であり、 移植を意図したプログ"
7655 #: build/C/man2/perf_event_open.2:2765
7657 "Glibc does not provide a wrapper for this system call; call it using "
7658 "B<syscall>(2). See the example below."
7660 "glibc はこのシステムコールに対するラッパー関数を提供していない。 "
7661 "B<syscall>(2) を使って呼び出すこと。 以下の例を参照。"
7664 #: build/C/man2/perf_event_open.2:2771
7666 "The official way of knowing if B<perf_event_open>() support is enabled is "
7667 "checking for the existence of the file I</proc/sys/kernel/"
7668 "perf_event_paranoid>."
7672 #: build/C/man2/perf_event_open.2:2771 build/C/man2/pivot_root.2:134
7673 #: build/C/man2/ptrace.2:2006
7678 #. commit ba0a6c9f6fceed11c6a99e8326f0477fe383e6b5
7680 #: build/C/man2/perf_event_open.2:2779
7682 "The B<F_SETOWN_EX> option to B<fcntl>(2) is needed to properly get overflow "
7683 "signals in threads. This was introduced in Linux 2.6.32."
7686 #. commit b690081d4d3f6a23541493f1682835c3cd5c54a1
7688 #: build/C/man2/perf_event_open.2:2789
7690 "Prior to Linux 2.6.33 (at least for x86), the kernel did not check if events "
7691 "could be scheduled together until read time. The same happens on all known "
7692 "kernels if the NMI watchdog is enabled. This means to see if a given set of "
7693 "events works you have to B<perf_event_open>(), start, then read before you "
7694 "know for sure you can get valid measurements."
7697 #. FIXME: cannot find a kernel commit for this one
7699 #: build/C/man2/perf_event_open.2:2794
7701 "Prior to Linux 2.6.34, event constraints were not enforced by the kernel. "
7702 "In that case, some events would silently return \"0\" if the kernel "
7703 "scheduled them in an improper counter slot."
7706 #. commit 45e16a6834b6af098702e5ea6c9a40de42ff77d8
7708 #: build/C/man2/perf_event_open.2:2798
7710 "Prior to Linux 2.6.34, there was a bug when multiplexing where the wrong "
7711 "results could be returned."
7714 #. commit 38b435b16c36b0d863efcf3f07b34a6fac9873fd
7716 #: build/C/man2/perf_event_open.2:2802
7718 "Kernels from Linux 2.6.35 to Linux 2.6.39 can quickly crash the kernel if "
7719 "\"inherit\" is enabled and many threads are started."
7722 #. commit 050735b08ca8a016bbace4445fa025b88fee770b
7724 #: build/C/man2/perf_event_open.2:2807
7726 "Prior to Linux 2.6.35, B<PERF_FORMAT_GROUP> did not work with attached "
7731 #: build/C/man2/perf_event_open.2:2812
7733 "In older Linux 2.6 versions, refreshing an event group leader refreshed all "
7734 "siblings, and refreshing with a parameter of 0 enabled infinite refresh. "
7735 "This behavior is unsupported and should not be relied on."
7738 #. commit 4ec8363dfc1451f8c8f86825731fe712798ada02
7740 #: build/C/man2/perf_event_open.2:2819
7742 "There is a bug in the kernel code between Linux 2.6.36 and Linux 3.0 that "
7743 "ignores the \"watermark\" field and acts as if a wakeup_event was chosen if "
7744 "the union has a nonzero value in it."
7747 #. commit 724b6daa13e100067c30cfc4d1ad06629609dc4e
7749 #: build/C/man2/perf_event_open.2:2826
7751 "From Linux 2.6.31 to Linux 3.4, the B<PERF_IOC_FLAG_GROUP> ioctl argument "
7752 "was broken and would repeatedly operate on the event specified rather than "
7753 "iterating across all sibling events in a group."
7756 #. commit fa7315871046b9a4c48627905691dbde57e51033
7758 #: build/C/man2/perf_event_open.2:2838
7760 "From Linux 3.4 to Linux 3.11, the mmap I<cap_usr_rdpmc> and I<cap_usr_time> "
7761 "bits mapped to the same location. Code should migrate to the new "
7762 "I<cap_user_rdpmc> and I<cap_user_time> fields instead."
7765 #. commit f287d332ce835f77a4f5077d2c0ef1e3f9ea42d2
7767 #: build/C/man2/perf_event_open.2:2844
7769 "Always double-check your results! Various generalized events have had wrong "
7770 "values. For example, retired branches measured the wrong thing on AMD "
7771 "machines until Linux 2.6.35."
7775 #: build/C/man2/perf_event_open.2:2844 build/C/man2/process_vm_readv.2:311
7776 #: build/C/man2/splice.2:237 build/C/man2/tee.2:136
7782 #: build/C/man2/perf_event_open.2:2848
7784 "The following is a short example that measures the total instruction count "
7785 "of a call to B<printf>(3)."
7789 #: build/C/man2/perf_event_open.2:2857
7792 "#include E<lt>stdlib.hE<gt>\n"
7793 "#include E<lt>stdio.hE<gt>\n"
7794 "#include E<lt>unistd.hE<gt>\n"
7795 "#include E<lt>string.hE<gt>\n"
7796 "#include E<lt>sys/ioctl.hE<gt>\n"
7797 "#include E<lt>linux/perf_event.hE<gt>\n"
7798 "#include E<lt>asm/unistd.hE<gt>\n"
7800 "#include E<lt>stdlib.hE<gt>\n"
7801 "#include E<lt>stdio.hE<gt>\n"
7802 "#include E<lt>unistd.hE<gt>\n"
7803 "#include E<lt>string.hE<gt>\n"
7804 "#include E<lt>sys/ioctl.hE<gt>\n"
7805 "#include E<lt>linux/perf_event.hE<gt>\n"
7806 "#include E<lt>asm/unistd.hE<gt>\n"
7809 #: build/C/man2/perf_event_open.2:2863
7813 "perf_event_open(struct perf_event_attr *hw_event, pid_t pid,\n"
7814 " int cpu, int group_fd, unsigned long flags)\n"
7819 "perf_event_open(struct perf_event_attr *hw_event, pid_t pid,\n"
7820 " int cpu, int group_fd, unsigned long flags)\n"
7825 #: build/C/man2/perf_event_open.2:2868
7828 " ret = syscall(__NR_perf_event_open, hw_event, pid, cpu,\n"
7829 " group_fd, flags);\n"
7833 " ret = syscall(__NR_perf_event_open, hw_event, pid, cpu,\n"
7834 " group_fd, flags);\n"
7839 #: build/C/man2/perf_event_open.2:2875
7843 "main(int argc, char **argv)\n"
7845 " struct perf_event_attr pe;\n"
7846 " long long count;\n"
7850 "main(int argc, char **argv)\n"
7852 " struct perf_event_attr pe;\n"
7853 " long long count;\n"
7857 #: build/C/man2/perf_event_open.2:2883
7860 " memset(&pe, 0, sizeof(struct perf_event_attr));\n"
7861 " pe.type = PERF_TYPE_HARDWARE;\n"
7862 " pe.size = sizeof(struct perf_event_attr);\n"
7863 " pe.config = PERF_COUNT_HW_INSTRUCTIONS;\n"
7864 " pe.disabled = 1;\n"
7865 " pe.exclude_kernel = 1;\n"
7866 " pe.exclude_hv = 1;\n"
7868 " memset(&pe, 0, sizeof(struct perf_event_attr));\n"
7869 " pe.type = PERF_TYPE_HARDWARE;\n"
7870 " pe.size = sizeof(struct perf_event_attr);\n"
7871 " pe.config = PERF_COUNT_HW_INSTRUCTIONS;\n"
7872 " pe.disabled = 1;\n"
7873 " pe.exclude_kernel = 1;\n"
7874 " pe.exclude_hv = 1;\n"
7877 #: build/C/man2/perf_event_open.2:2889
7880 " fd = perf_event_open(&pe, 0, -1, -1, 0);\n"
7881 " if (fd == -1) {\n"
7882 " fprintf(stderr, \"Error opening leader %llx\\en\", pe.config);\n"
7883 " exit(EXIT_FAILURE);\n"
7886 " fd = perf_event_open(&pe, 0, -1, -1, 0);\n"
7887 " if (fd == -1) {\n"
7888 " fprintf(stderr, \"Error opening leader %llx\\en\", pe.config);\n"
7889 " exit(EXIT_FAILURE);\n"
7893 #: build/C/man2/perf_event_open.2:2892
7896 " ioctl(fd, PERF_EVENT_IOC_RESET, 0);\n"
7897 " ioctl(fd, PERF_EVENT_IOC_ENABLE, 0);\n"
7899 " ioctl(fd, PERF_EVENT_IOC_RESET, 0);\n"
7900 " ioctl(fd, PERF_EVENT_IOC_ENABLE, 0);\n"
7903 #: build/C/man2/perf_event_open.2:2894
7905 msgid " printf(\"Measuring instruction count for this printf\\en\");\n"
7906 msgstr " printf(\"Measuring instruction count for this printf\\en\");\n"
7909 #: build/C/man2/perf_event_open.2:2897
7912 " ioctl(fd, PERF_EVENT_IOC_DISABLE, 0);\n"
7913 " read(fd, &count, sizeof(long long));\n"
7915 " ioctl(fd, PERF_EVENT_IOC_DISABLE, 0);\n"
7916 " read(fd, &count, sizeof(long long));\n"
7919 #: build/C/man2/perf_event_open.2:2899
7921 msgid " printf(\"Used %lld instructions\\en\", count);\n"
7922 msgstr " printf(\"Used %lld instructions\\en\", count);\n"
7925 #: build/C/man2/perf_event_open.2:2902
7935 #: build/C/man2/perf_event_open.2:2909
7936 msgid "B<fcntl>(2), B<mmap>(2), B<open>(2), B<prctl>(2), B<read>(2)"
7937 msgstr "B<fcntl>(2), B<mmap>(2), B<open>(2), B<prctl>(2), B<read>(2)"
7940 #: build/C/man2/perfmonctl.2:27
7946 #: build/C/man2/perfmonctl.2:27
7952 #: build/C/man2/perfmonctl.2:30
7953 msgid "perfmonctl - interface to IA-64 performance monitoring unit"
7954 msgstr "perfmonctl - IA-64 の PMU (性能監視ユニット) のインターフェース"
7957 #: build/C/man2/perfmonctl.2:34
7960 "B<#include E<lt>syscall.hE<gt>>\n"
7961 "B<#include E<lt>perfmon.hE<gt>>\n"
7963 "B<#include E<lt>syscall.hE<gt>>\n"
7964 "B<#include E<lt>perfmon.hE<gt>>\n"
7967 #: build/C/man2/perfmonctl.2:36
7969 msgid "B<long perfmonctl(int >I<fd>B<, int >I<cmd>B<, void *>I<arg>B<, int >I<narg>B<);>\n"
7970 msgstr "B<long perfmonctl(int >I<fd>B<, int >I<cmd>B<, void *>I<arg>B<, int >I<narg>B<);>\n"
7973 #: build/C/man2/perfmonctl.2:47
7975 "The IA-64-specific B<perfmonctl>() system call provides an interface to the "
7976 "PMU (performance monitoring unit). The PMU consists of PMD (performance "
7977 "monitoring data) registers and PMC (performance monitoring control) "
7978 "registers, which gather hardware statistics."
7980 "IA-64 固有の B<perfmonctl>() システムコールは PMU (性能監視ユニット; "
7981 "performance monitoring unit) へのインターフェースを提供する。 PMU は PMD "
7982 "(performance monitoring data) レジスターと PMC (performance monitoring "
7983 "control) レジスターで構成され、 ハードウェアの統計を収集する。"
7986 #: build/C/man2/perfmonctl.2:57
7988 "B<perfmonctl>() applies the operation I<cmd> to the input arguments "
7989 "specified by I<arg>. The number of arguments is defined by I<narg>. The "
7990 "I<fd> argument specifies the perfmon context to operate on."
7992 "B<perfmonctl>() は、 操作 I<cmd> を I<arg> で指定された入力引き数で行う。 引"
7993 "き数の数は I<narg> で規定される。 I<fd> 引き数は操作対象の perfmon コンテキス"
7997 #: build/C/man2/perfmonctl.2:61
7998 msgid "Supported values for I<cmd> are:"
7999 msgstr "I<cmd> に指定できる値は以下のとおりである。"
8002 #: build/C/man2/perfmonctl.2:61
8004 msgid "B<PFM_CREATE_CONTEXT>"
8005 msgstr "B<PFM_CREATE_CONTEXT>"
8008 #: build/C/man2/perfmonctl.2:65
8010 msgid "B<perfmonctl(int >I<fd>B<, PFM_CREATE_CONTEXT, pfarg_context_t *>I<ctxt>B<, 1);>\n"
8011 msgstr "B<perfmonctl(int >I<fd>B<, PFM_CREATE_CONTEXT, pfarg_context_t *>I<ctxt>B<, 1);>\n"
8014 #: build/C/man2/perfmonctl.2:67
8015 msgid "Set up a context."
8016 msgstr "コンテキストを用意する。"
8019 #: build/C/man2/perfmonctl.2:74
8021 "The I<fd> parameter is ignored. A new perfmon context is created as "
8022 "specified in I<ctxt> and its file descriptor is returned in I<ctxt-"
8025 "I<fd> 引き数は無視される。 新しい perfmon コンテキストを I<ctxt> で指定した内"
8026 "容で作成し、 そのファイルディスクリプターを I<ctxt-E<gt>ctx_fd> で返す。"
8029 #: build/C/man2/perfmonctl.2:86
8031 "The file descriptor can be used in subsequent calls to B<perfmonctl>() and "
8032 "can be used to read event notifications (type I<pfm_msg_t>) using "
8033 "B<read>(2). The file descriptor is pollable using B<select>(2), B<poll>(2), "
8036 "ファイルディスクリプターはそれ以降の B<perfmonctl>() の呼び出しで使用した"
8037 "り、 B<read>(2) を使ってイベント通知 (I<pfm_msg_t> 型) を読み出したりするのに"
8038 "使用できる。 このファイルディスクリプターは B<select>(2), B<poll>(2), "
8039 "B<epoll>(7) で状態監視 (ポーリング) することができる。"
8042 #: build/C/man2/perfmonctl.2:90
8044 "The context can be destroyed by calling B<close>(2) on the file descriptor."
8046 "コンテキストを破棄するには、 そのファイルディスクリプターに対して "
8047 "B<close>(2) を呼び出す。"
8050 #: build/C/man2/perfmonctl.2:90
8052 msgid "B<PFM_WRITE_PMCS>"
8053 msgstr "B<PFM_WRITE_PMCS>"
8056 #: build/C/man2/perfmonctl.2:95
8058 msgid "B<perfmonctl(int >I<fd>B<, PFM_WRITE_PMCS, pfarg_reg_t *>I<pmcs>B<, n);>\n"
8059 msgstr "B<perfmonctl(int >I<fd>B<, PFM_WRITE_PMCS, pfarg_reg_t *>I<pmcs>B<, n);>\n"
8062 #: build/C/man2/perfmonctl.2:97
8063 msgid "Set PMC registers."
8064 msgstr "PMC レジスターを設定する。"
8067 #: build/C/man2/perfmonctl.2:97
8069 msgid "B<PFM_WRITE_PMDS>"
8070 msgstr "B<PFM_WRITE_PMDS>"
8073 #: build/C/man2/perfmonctl.2:101
8075 msgid "B<perfmonctl(int >I<fd>B<, PFM_WRITE_PMDS, pfarg_reg_t *>I<pmds>B<, n);>\n"
8076 msgstr "B<perfmonctl(int >I<fd>B<, PFM_WRITE_PMDS, pfarg_reg_t *>I<pmds>B<, n);>\n"
8080 #: build/C/man2/perfmonctl.2:104
8081 msgid "Set PMD registers."
8082 msgstr "PMD レジスターを設定する。"
8085 #: build/C/man2/perfmonctl.2:104
8087 msgid "B<PFM_READ_PMDS>"
8088 msgstr "B<PFM_READ_PMDS>"
8091 #: build/C/man2/perfmonctl.2:109
8093 msgid "B<perfmonctl(int >I<fd>B<, PFM_READ_PMDS, pfarg_reg_t *>I<pmds>B<, n);>\n"
8094 msgstr "B<perfmonctl(int >I<fd>B<, PFM_READ_PMDS, pfarg_reg_t *>I<pmds>B<, n);>\n"
8097 #: build/C/man2/perfmonctl.2:111
8098 msgid "Read PMD registers."
8099 msgstr "PMD レジスターを読み出す。"
8102 #: build/C/man2/perfmonctl.2:111
8104 msgid "B<PFM_START>"
8105 msgstr "B<PFM_START>"
8107 #. .BI "perfmonctl(int " fd ", PFM_START, arg, 1);
8109 #: build/C/man2/perfmonctl.2:117
8111 msgid "B<perfmonctl(int >I<fd>B<, PFM_START, NULL, 0);>\n"
8112 msgstr "B<perfmonctl(int >I<fd>B<, PFM_START, NULL, 0);>\n"
8115 #: build/C/man2/perfmonctl.2:119
8116 msgid "Start monitoring."
8120 #: build/C/man2/perfmonctl.2:119
8123 msgstr "B<PFM_STOP>"
8126 #: build/C/man2/perfmonctl.2:124
8128 msgid "B<perfmonctl(int >I<fd>B<, PFM_STOP, NULL, 0);>\n"
8129 msgstr "B<perfmonctl(int >I<fd>B<, PFM_STOP, NULL, 0);>\n"
8132 #: build/C/man2/perfmonctl.2:126
8133 msgid "Stop monitoring."
8137 #: build/C/man2/perfmonctl.2:126
8139 msgid "B<PFM_LOAD_CONTEXT>"
8140 msgstr "B<PFM_LOAD_CONTEXT>"
8143 #: build/C/man2/perfmonctl.2:131
8145 msgid "B<perfmonctl(int >I<fd>B<, PFM_LOAD_CONTEXT, pfarg_load_t *>I<largs>B<, 1);>\n"
8146 msgstr "B<perfmonctl(int >I<fd>B<, PFM_LOAD_CONTEXT, pfarg_load_t *>I<largs>B<, 1);>\n"
8149 #: build/C/man2/perfmonctl.2:133
8150 msgid "Attach the context to a thread."
8151 msgstr "指定したコンテキストをスレッドに接続する。"
8154 #: build/C/man2/perfmonctl.2:133
8156 msgid "B<PFM_UNLOAD_CONTEXT>"
8157 msgstr "B<PFM_UNLOAD_CONTEXT>"
8160 #: build/C/man2/perfmonctl.2:138
8162 msgid "B<perfmonctl(int >I<fd>B<, PFM_UNLOAD_CONTEXT, NULL, 0);>\n"
8163 msgstr "B<perfmonctl(int >I<fd>B<, PFM_UNLOAD_CONTEXT, NULL, 0);>\n"
8166 #: build/C/man2/perfmonctl.2:140
8167 msgid "Detach the context from a thread."
8168 msgstr "指定したコンテキストをスレッドが切り離す。"
8171 #: build/C/man2/perfmonctl.2:140
8173 msgid "B<PFM_RESTART>"
8174 msgstr "B<PFM_RESTART>"
8177 #: build/C/man2/perfmonctl.2:145
8179 msgid "B<perfmonctl(int >I<fd>B<, PFM_RESTART, NULL, 0);>\n"
8180 msgstr "B<perfmonctl(int >I<fd>B<, PFM_RESTART, NULL, 0);>\n"
8183 #: build/C/man2/perfmonctl.2:147
8184 msgid "Restart monitoring after receiving an overflow notification."
8185 msgstr "オーバーフロー通知を受信した後、 監視を再開する。"
8188 #: build/C/man2/perfmonctl.2:147
8190 msgid "B<PFM_GET_FEATURES>"
8191 msgstr "B<PFM_GET_FEATURES>"
8194 #: build/C/man2/perfmonctl.2:152
8196 msgid "B<perfmonctl(int >I<fd>B<, PFM_GET_FEARURES, pfarg_features_t *>I<arg>B<, 1);>\n"
8197 msgstr "B<perfmonctl(int >I<fd>B<, PFM_GET_FEARURES, pfarg_features_t *>I<arg>B<, 1);>\n"
8200 #: build/C/man2/perfmonctl.2:153
8202 msgid "B<PFM_DEBUG>"
8203 msgstr "B<PFM_DEBUG>"
8206 #: build/C/man2/perfmonctl.2:158
8208 msgid "B<perfmonctl(int >I<fd>B<, PFM_DEBUG, >I<val>B<, 0);>\n"
8209 msgstr "B<perfmonctl(int >I<fd>B<, PFM_DEBUG, >I<val>B<, 0);>\n"
8212 #: build/C/man2/perfmonctl.2:162
8213 msgid "If I<val> is nonzero, enable debugging mode, otherwise disable."
8215 "I<val> が 0 以外の場合、デバッグモードを有効にする。 そうでない場合、 無効に"
8219 #: build/C/man2/perfmonctl.2:162
8221 msgid "B<PFM_GET_PMC_RESET_VAL>"
8222 msgstr "B<PFM_GET_PMC_RESET_VAL>"
8225 #: build/C/man2/perfmonctl.2:167
8227 msgid "B<perfmonctl(int >I<fd>B<, PFM_GET_PMC_RESET_VAL, pfarg_reg_t * >I<req>B<, n);>\n"
8228 msgstr "B<perfmonctl(int >I<fd>B<, PFM_GET_PMC_RESET_VAL, pfarg_reg_t * >I<req>B<, n);>\n"
8234 #. .B PFM_CREATE_EVTSETS
8235 #. create or modify event sets
8237 #. .BI "perfmonctl(int " fd ", PFM_CREATE_EVTSETS, pfarg_setdesc_t *desc , n);
8240 #. .B PFM_DELETE_EVTSETS
8241 #. delete event sets
8243 #. .BI "perfmonctl(int " fd ", PFM_DELETE_EVTSET, pfarg_setdesc_t *desc , n);
8246 #. .B PFM_GETINFO_EVTSETS
8247 #. get information about event sets
8249 #. .BI "perfmonctl(int " fd ", PFM_GETINFO_EVTSETS, pfarg_setinfo_t *info, n);
8252 #: build/C/man2/perfmonctl.2:190
8253 msgid "Reset PMC registers to default values."
8254 msgstr "PMC レジスターをデフォルト値にリセットする。"
8257 #: build/C/man2/perfmonctl.2:196
8259 "B<perfmonctl>() returns zero when the operation is successful. On error, "
8260 "-1 is returned and I<errno> is set to indicate the cause of the error."
8262 "B<perfmonctl>() は操作が成功すると 0 を返す。 エラーの場合、 -1 が返り、 "
8263 "I<errno> にエラーの原因を示す値が設定される。"
8266 #: build/C/man2/perfmonctl.2:199
8267 msgid "B<perfmonctl>() is available since Linux 2.4."
8268 msgstr "B<perfmonctl>() は Linux 2.4 以降で利用可能である。"
8271 #: build/C/man2/perfmonctl.2:202
8273 "B<perfmonctl>() is Linux-specific and is available only on the IA-64 "
8276 "B<perfmonctl>() は Linux 固有で、 IA-64 アーキテクチャーでのみ利用できる。"
8279 #: build/C/man2/perfmonctl.2:207
8281 msgstr "B<gprof>(1)"
8284 #: build/C/man2/perfmonctl.2:209
8285 msgid "The perfmon2 interface specification"
8286 msgstr "perfmon2 インターフェース仕様"
8289 #: build/C/man2/personality.2:32
8292 msgstr "PERSONALITY"
8295 #: build/C/man2/personality.2:35
8296 msgid "personality - set the process execution domain"
8297 msgstr "personality - プロセスを実行するドメインを設定する"
8300 #: build/C/man2/personality.2:37
8301 msgid "B<#include E<lt>sys/personality.hE<gt>>"
8302 msgstr "B<#include E<lt>sys/personality.hE<gt>>"
8305 #: build/C/man2/personality.2:39
8306 msgid "B<int personality(unsigned long >I<persona>B<);>"
8307 msgstr "B<int personality(unsigned long >I<persona>B<);>"
8310 #: build/C/man2/personality.2:47
8312 "Linux supports different execution domains, or personalities, for each "
8313 "process. Among other things, execution domains tell Linux how to map signal "
8314 "numbers into signal actions. The execution domain system allows Linux to "
8315 "provide limited support for binaries compiled under other UNIX-like "
8316 "operating systems."
8318 "Linux は、プロセス毎の異なる実行ドメイン、すなわち パーソナリティ "
8319 "(personality) をサポートしている。 実行ドメインは Linux にシグナル番号にどの"
8320 "シグナルを割り付けるかを 教えたりする。また、実行ドメインシステムにより、 "
8321 "Linux は、 他の UNIX 風のオペレーティングシステムでコンパイルされたバイナリに"
8322 "対する限定的なサポートを提供している。"
8325 #: build/C/man2/personality.2:59
8327 "If I<persona> is not 0xffffffff, then B<personality>() sets the caller's "
8328 "execution domain to the value specified by I<persona>. Specifying "
8329 "I<persona> as 0xffffffff provides a way of retrieving the current persona "
8330 "without changing it."
8332 "I<persona> が 0xffffffff 以外の場合、 B<personality>() は呼び出し元の実行ドメ"
8333 "インを I<persona> で指定された値に設定する。 I<persona> に 0xffffffff を指定"
8334 "すると、変更を行わず、現在の persona 値を取得できる。"
8337 #: build/C/man2/personality.2:62
8339 "A list of the available execution domains can be found in I<E<lt>sys/"
8340 "personality.hE<gt>>."
8342 "利用可能な実行ドメインのリストは I<E<lt>sys/personality.hE<gt>> にある。"
8345 #: build/C/man2/personality.2:69
8347 "On success, the previous I<persona> is returned. On error, -1 is returned, "
8348 "and I<errno> is set appropriately."
8350 "成功した場合、以前の I<persona> が返される。エラーの場合は、-1 が返され、 "
8351 "I<errno> が適切に設定される。"
8354 #: build/C/man2/personality.2:73
8355 msgid "The kernel was unable to change the personality."
8356 msgstr "カーネルがパーソナリティを変更できなかった。"
8359 #: build/C/man2/personality.2:77
8361 "B<personality>() is Linux-specific and should not be used in programs "
8362 "intended to be portable."
8364 "B<personality>() は Linux 固有であり、移植を意図したプログラムで使用すべきで"
8368 #: build/C/man2/personality.2:79
8369 msgid "B<setarch>(8)"
8373 #: build/C/man2/pivot_root.2:10
8379 #: build/C/man2/pivot_root.2:13
8380 msgid "pivot_root - change the root filesystem"
8381 msgstr "pivot_root - root ファイルシステムを変更する"
8384 #: build/C/man2/pivot_root.2:15
8386 "B<int pivot_root(const char *>I<new_root>B<, const char *>I<put_old>B<);>"
8388 "B<int pivot_root(const char *>I<new_root>B<, const char *>I<put_old>B<);>"
8392 #. capability is required.
8394 #: build/C/man2/pivot_root.2:27
8396 "B<pivot_root>() moves the root filesystem of the calling process to the "
8397 "directory I<put_old> and makes I<new_root> the new root filesystem of the "
8400 "B<pivot_root>() は呼び出し元のプロセスの root ファイルシステムを I<put_old> "
8401 "ディレクトリに移動し、 I<new_root> を呼び出し元のプロセスの新しい root ファイ"
8405 #: build/C/man2/pivot_root.2:34
8407 "The typical use of B<pivot_root>() is during system startup, when the "
8408 "system mounts a temporary root filesystem (e.g., an B<initrd>), then mounts "
8409 "the real root filesystem, and eventually turns the latter into the current "
8410 "root of all relevant processes or threads."
8412 "B<pivot_root>() の典型的な利用法は、システムの起動中にシステムが一時的な "
8413 "root ファイルシステム (例えば B<initrd>) をマウントし、これに続いて本当の "
8414 "root ファイルシステムをマウントし、 後者を必要な全てのプロセス・スレッドの カ"
8415 "レント root に変更するような場合である。"
8418 #: build/C/man2/pivot_root.2:46
8420 "B<pivot_root>() may or may not change the current root and the current "
8421 "working directory of any processes or threads which use the old root "
8422 "directory. The caller of B<pivot_root>() must ensure that processes with "
8423 "root or current working directory at the old root operate correctly in "
8424 "either case. An easy way to ensure this is to change their root and current "
8425 "working directory to I<new_root> before invoking B<pivot_root>()."
8427 "古い root ディレクトリを使っていた全てのプロセスやスレッドの カレント root と"
8428 "カレントワーキングディレクトリを、 B<pivot_root>() が変更するかどうかはわか"
8429 "らない。 B<pivot_root>() の呼びだしプロセスは、古い root やカレントワーキン"
8430 "グディレクトリを使っていた プロセスが、いずれの場合でも正しく動作することを保"
8431 "証しなければならない。 これを簡単に行うには、それらのプロセスの root と カレ"
8432 "ントワーキングディレクトリを B<pivot_root>() を呼び出す前に I<new_root> に変"
8436 #: build/C/man2/pivot_root.2:64
8438 "The paragraph above is intentionally vague because the implementation of "
8439 "B<pivot_root>() may change in the future. At the time of writing, "
8440 "B<pivot_root>() changes root and current working directory of each process "
8441 "or thread to I<new_root> if they point to the old root directory. This is "
8442 "necessary in order to prevent kernel threads from keeping the old root "
8443 "directory busy with their root and current working directory, even if they "
8444 "never access the filesystem in any way. In the future, there may be a "
8445 "mechanism for kernel threads to explicitly relinquish any access to the "
8446 "filesystem, such that this fairly intrusive mechanism can be removed from "
8449 "上記の段落は、将来 B<pivot_root>() が変更されるかも知れないことを鑑みて、わ"
8450 "ざと曖昧に書いてある。 本ページを記述している時点では、 B<pivot_root>() は古"
8451 "い root ディレクトリを用いている全てのプロセス・スレッドの root と カレント"
8452 "ワーキングディレクトリを I<new_root> に変更する。これはカーネルのスレッドが古"
8453 "い root ディレクトリを busy 状態にしないために必要である。これらのスレッドが "
8454 "古いディレクトリを root やカレントワーキングディレクトリとしていると、 ファイ"
8455 "ルシステムに一切アクセスしない場合でも 古い root が busy になってしまうからで"
8456 "ある。 将来は、カーネルスレッドがあらゆるファイルシステムへのアクセスを 明示"
8457 "的に放棄するメカニズムができ、このでしゃばりな機能は B<pivot_root>() から削"
8461 #: build/C/man2/pivot_root.2:72
8463 "Note that this also applies to the calling process: B<pivot_root>() may or "
8464 "may not affect its current working directory. It is therefore recommended "
8465 "to call B<chdir(\"/\")> immediately after B<pivot_root>()."
8467 "これは呼び出し元のプロセスについても当てはまることに注意。 B<pivot_root>() "
8468 "がカレントプロセスのカレントワーキングディレクトリに影響するかどうかは 分から"
8469 "ない。したがって B<pivot_root>() の直後に B<chdir(\"/\")> を呼び出すとよい。"
8472 #: build/C/man2/pivot_root.2:74
8473 msgid "The following restrictions apply to I<new_root> and I<put_old>:"
8474 msgstr "I<new_root> および I<put_old> には以下の制限がある:"
8477 #: build/C/man2/pivot_root.2:74 build/C/man2/pivot_root.2:76
8478 #: build/C/man2/pivot_root.2:79 build/C/man2/pivot_root.2:83
8484 #: build/C/man2/pivot_root.2:76
8485 msgid "They must be directories."
8486 msgstr "ディレクトリでなければならない。"
8489 #: build/C/man2/pivot_root.2:79
8491 "I<new_root> and I<put_old> must not be on the same filesystem as the current "
8494 "I<new_root> と I<put_old> は現在の root と同じファイルシステムにあってはなら"
8498 #: build/C/man2/pivot_root.2:83
8500 "I<put_old> must be underneath I<new_root>, that is, adding a nonzero number "
8501 "of I</..> to the string pointed to by I<put_old> must yield the same "
8502 "directory as I<new_root>."
8504 "I<put_old> は I<new_root> 以下になければならない。すなわち I<put_old> を差す"
8505 "文字列に 1 個以上の I<../> を付けることによって I<new_root> と同じディレクト"
8509 #: build/C/man2/pivot_root.2:85
8510 msgid "No other filesystem may be mounted on I<put_old>."
8511 msgstr "他のファイルシステムが I<put_old> にマウントされていてはならない。"
8514 #: build/C/man2/pivot_root.2:89
8515 msgid "See also B<pivot_root>(8) for additional usage examples."
8516 msgstr "利用例については B<pivot_root>(8) を参照のこと。"
8519 #: build/C/man2/pivot_root.2:96
8521 "If the current root is not a mount point (e.g., after B<chroot>(2) or "
8522 "B<pivot_root>(), see also below), not the old root directory, but the mount "
8523 "point of that filesystem is mounted on I<put_old>."
8525 "現在の root がマウントポイントではない (B<chroot>(2) や B<pivot_root>() の"
8526 "後など。以下も参照) 場合、 古い root ディレクトリではなく、 そのファイルシス"
8527 "テムのマウントポイントが I<put_old> にマウントされる。"
8530 #: build/C/man2/pivot_root.2:101
8532 "I<new_root> does not have to be a mount point. In this case, I</proc/"
8533 "mounts> will show the mount point of the filesystem containing I<new_root> "
8536 "I<new_root> はマウントポイントでなくてもよい。 この場合 I</proc/mounts> は、 "
8537 "I<new_root> を root (I</>) とするファイルシステムのマウントポイントを表示す"
8541 #: build/C/man2/pivot_root.2:110
8543 "B<pivot_root>() may return (in I<errno>) any of the errors returned by "
8544 "B<stat>(2). Additionally, it may return:"
8546 "B<pivot_root>() は B<stat>(2) の返すあらゆるエラーを (I<errno> に) 返す可能"
8547 "性がある。さらに以下を返すことがある:"
8550 #: build/C/man2/pivot_root.2:114
8552 "I<new_root> or I<put_old> are on the current root filesystem, or a "
8553 "filesystem is already mounted on I<put_old>."
8555 "I<new_root> または I<put_old> が、現在の root ファイルシステム上にあるか、既"
8556 "に I<put_old> になんらかのファイルシステムがマウントされている。"
8559 #: build/C/man2/pivot_root.2:117
8560 msgid "I<put_old> is not underneath I<new_root>."
8561 msgstr "I<put_old> が I<new_root> の下層にない。"
8564 #: build/C/man2/pivot_root.2:117
8570 #: build/C/man2/pivot_root.2:120
8571 msgid "I<new_root> or I<put_old> is not a directory."
8572 msgstr "I<new_root> または I<put_old> がディレクトリでない。"
8575 #: build/C/man2/pivot_root.2:125
8576 msgid "The calling process does not have the B<CAP_SYS_ADMIN> capability."
8577 msgstr "呼び出し元のプロセスが B<CAP_SYS_ADMIN> ケーパビリティを持っていない。"
8580 #: build/C/man2/pivot_root.2:128
8581 msgid "B<pivot_root>() was introduced in Linux 2.3.41."
8582 msgstr "B<pivot_root>() は Linux 2.3.41 で導入された。"
8585 #: build/C/man2/pivot_root.2:131
8586 msgid "B<pivot_root>() is Linux-specific and hence is not portable."
8587 msgstr "B<pivot_root>() は Linux に固有のものなので、移植性はない。"
8590 #: build/C/man2/pivot_root.2:138
8592 "B<pivot_root>() should not have to change root and current working "
8593 "directory of all other processes in the system."
8595 "B<pivot_root>() はシステムの他のプロセス全ての root と カレントワーキング"
8596 "ディレクトリとを変更しなくてもよいはずである。"
8599 #: build/C/man2/pivot_root.2:143
8601 "Some of the more obscure uses of B<pivot_root>() may quickly lead to "
8604 "B<pivot_root>() の使い方がもうちょっと曖昧になると、 あっという間にわけのわ"
8608 #: build/C/man2/pivot_root.2:149
8609 msgid "B<chdir>(2), B<chroot>(2), B<stat>(2), B<initrd>(4), B<pivot_root>(8)"
8610 msgstr "B<chdir>(2), B<chroot>(2), B<stat>(2), B<initrd>(4), B<pivot_root>(8)"
8613 #: build/C/man2/process_vm_readv.2:29
8615 msgid "PROCESS_VM_READV"
8616 msgstr "PROCESS_VM_READV"
8619 #: build/C/man2/process_vm_readv.2:29
8625 #: build/C/man2/process_vm_readv.2:32
8627 "process_vm_readv, process_vm_writev - transfer data between process address "
8630 "process_vm_readv, process_vm_writev - プロセスのアドレス空間間でデータを転送"
8634 #: build/C/man2/process_vm_readv.2:35
8636 msgid "B<#include E<lt>sys/uio.hE<gt>>\n"
8637 msgstr "B<#include E<lt>sys/uio.hE<gt>>\n"
8640 #: build/C/man2/process_vm_readv.2:42
8643 "B<ssize_t process_vm_readv(pid_t >I<pid>B<,>\n"
8644 "B< const struct iovec *>I<local_iov>B<,>\n"
8645 "B< unsigned long >I<liovcnt>B<,>\n"
8646 "B< const struct iovec *>I<remote_iov>B<,>\n"
8647 "B< unsigned long >I<riovcnt>B<,>\n"
8648 "B< unsigned long >I<flags>B<);>\n"
8650 "B<ssize_t process_vm_readv(pid_t >I<pid>B<,>\n"
8651 "B< const struct iovec *>I<local_iov>B<,>\n"
8652 "B< unsigned long >I<liovcnt>B<,>\n"
8653 "B< const struct iovec *>I<remote_iov>B<,>\n"
8654 "B< unsigned long >I<riovcnt>B<,>\n"
8655 "B< unsigned long >I<flags>B<);>\n"
8658 #: build/C/man2/process_vm_readv.2:49
8661 "B<ssize_t process_vm_writev(pid_t >I<pid>B<,>\n"
8662 "B< const struct iovec *>I<local_iov>B<,>\n"
8663 "B< unsigned long >I<liovcnt>B<,>\n"
8664 "B< const struct iovec *>I<remote_iov>B<,>\n"
8665 "B< unsigned long >I<riovcnt>B<,>\n"
8666 "B< unsigned long >I<flags>B<);>\n"
8668 "B<ssize_t process_vm_writev(pid_t >I<pid>B<,>\n"
8669 "B< const struct iovec *>I<local_iov>B<,>\n"
8670 "B< unsigned long >I<liovcnt>B<,>\n"
8671 "B< const struct iovec *>I<remote_iov>B<,>\n"
8672 "B< unsigned long >I<riovcnt>B<,>\n"
8673 "B< unsigned long >I<flags>B<);>\n"
8676 #: build/C/man2/process_vm_readv.2:54
8678 "Feature Test Macro Requirements for glibc (see B<feature_test_macros>(7)):"
8679 msgstr "glibc 向けの機能検査マクロの要件 (B<feature_test_macros>(7) 参照):"
8682 #: build/C/man2/process_vm_readv.2:58
8683 msgid "B<process_vm_readv>(), B<process_vm_writev>():"
8684 msgstr "B<process_vm_readv>(), B<process_vm_writev>():"
8687 #: build/C/man2/process_vm_readv.2:62
8688 msgid "B<_GNU_SOURCE>"
8689 msgstr "B<_GNU_SOURCE>"
8692 #: build/C/man2/process_vm_readv.2:73
8694 "These system calls transfer data between the address space of the calling "
8695 "process (\"the local process\") and the process identified by I<pid> (\"the "
8696 "remote process\"). The data moves directly between the address spaces of "
8697 "the two processes, without passing through kernel space."
8699 "これらのシステムコールは、 呼び出し元プロセス (「ローカルプロセス」) と "
8700 "I<pid> で指定されるプロセス (「リモートプロセス」) のアドレス空間間でデータを"
8701 "転送する。 データの移動は、 カーネル空間を経由することなく、 2 つのプロセスの"
8705 #: build/C/man2/process_vm_readv.2:98
8707 "The B<process_vm_readv>() system call transfers data from the remote "
8708 "process to the local process. The data to be transferred is identified by "
8709 "I<remote_iov> and I<riovcnt>: I<remote_iov> is a pointer to an array "
8710 "describing address ranges in the process I<pid>, and I<riovcnt> specifies "
8711 "the number of elements in I<remote_iov>. The data is transferred to the "
8712 "locations specified by I<local_iov> and I<liovcnt>: I<local_iov> is a "
8713 "pointer to an array describing address ranges in the calling process, and "
8714 "I<liovcnt> specifies the number of elements in I<local_iov>."
8716 "B<process_vm_readv>() システムコールは、 リモートプロセスからローカルプロセス"
8717 "へデータを転送する。 転送対象のデータは I<remote_iov> と I<riovcnt> で指定さ"
8718 "れる。 I<remote_iov> はプロセス I<pid> におけるアドレス範囲を指定する配列への"
8719 "ポインターで、 I<riovcnt> は I<remote_iov> の要素数を指定する。 データは "
8720 "I<local_iov> と I<liovcnt> で指定された場所に転送される。 I<local_iov> は呼び"
8721 "出し元プロセスにおけるアドレス範囲を指定する配列で、 I<liovcnt> は "
8722 "I<local_iov> の要素数を指定する。"
8725 #: build/C/man2/process_vm_readv.2:112
8727 "The B<process_vm_writev>() system call is the converse of "
8728 "B<process_vm_readv>()\\(emit transfers data from the local process to the "
8729 "remote process. Other than the direction of the transfer, the arguments "
8730 "I<liovcnt>, I<local_iov>, I<riovcnt>, and I<remote_iov> have the same "
8731 "meaning as for B<process_vm_readv>()."
8733 "B<process_vm_writev>() システムコールは B<process_vm_readv>() の逆で、 ローカ"
8734 "ルプロセスからリモートプロセスにデータを転送する。 転送の方向が違う以外は、 "
8735 "引き数 I<liovcnt>, I<local_iov>, I<riovcnt>, I<remote_iov> は "
8736 "B<process_vm_readv>() と同じ意味を持つ。"
8739 #: build/C/man2/process_vm_readv.2:122
8741 "The I<local_iov> and I<remote_iov> arguments point to an array of I<iovec> "
8742 "structures, defined in I<E<lt>sys/uio.hE<gt>> as:"
8744 "引き数 I<local_iov> と I<remote_iov> は I<iovec> 構造体の配列へのポイン\n"
8745 "タである。 I<iovec> 構造体は I<E<lt>sys/uio.hE<gt>> で以下のように定義\n"
8749 #: build/C/man2/process_vm_readv.2:129
8753 " void *iov_base; /* Starting address */\n"
8754 " size_t iov_len; /* Number of bytes to transfer */\n"
8758 " void *iov_base; /* Starting address */\n"
8759 " size_t iov_len; /* Number of bytes to transfer */\n"
8763 #: build/C/man2/process_vm_readv.2:145
8765 "Buffers are processed in array order. This means that "
8766 "B<process_vm_readv>() completely fills I<local_iov[0]> before proceeding to "
8767 "I<local_iov[1]>, and so on. Likewise, I<remote_iov[0]> is completely read "
8768 "before proceeding to I<remote_iov[1]>, and so on."
8770 "バッファーは配列の順序で処理される。 つまり、 B<process_vm_readv>() は "
8771 "I<local_iov>[0] が一杯になるまでデータを詰めてから、 I<local_iov>[1] に進むこ"
8772 "とを意味する。 同様に、 I<remote_iov>[0] を全部読み出してから "
8773 "I<remote_iov>[1] に進み、 以降も同様である。"
8776 #: build/C/man2/process_vm_readv.2:156
8778 "Similarly, B<process_vm_writev>() writes out the entire contents of "
8779 "I<local_iov[0]> before proceeding to I<local_iov[1]>, and it completely "
8780 "fills I<remote_iov[0]> before proceeding to I<remote_iov[1]>."
8782 "同様に、 B<process_vm_writev>() は I<local_iov[0]> の内容を全部読み出してか"
8783 "ら I<local_iov[1]> に進み、 書き込み先でも I<remote_iov[0]> が一杯になってか"
8784 "ら I<remote_iov[1]> に進む。"
8787 #: build/C/man2/process_vm_readv.2:164
8789 "The lengths of I<remote_iov[i].iov_len> and I<local_iov[i].iov_len> do not "
8790 "have to be the same. Thus, it is possible to split a single local buffer "
8791 "into multiple remote buffers, or vice versa."
8793 "長さ I<remote_iov[i].iov_len> と I<local_iov[i].iov_len> は同じである必要はな"
8794 "い。 したがって、 ローカル側で 1 つのバッファーのデータがリモート側で複数の"
8795 "バッファーに分割されることがあるし、 その逆も起こりえる。"
8798 #: build/C/man2/process_vm_readv.2:168
8799 msgid "The I<flags> argument is currently unused and must be set to 0."
8800 msgstr "I<flags> 引き数は現在使用されておらず、 0 を設定しなければならない。"
8802 #. In time, glibc might provide a wrapper that works around this limit,
8803 #. as is done for readv()/writev()
8805 #: build/C/man2/process_vm_readv.2:181
8807 "The values specified in the I<liovcnt> and I<riovcnt> arguments must be less "
8808 "than or equal to B<IOV_MAX> (defined in I<E<lt>limits.hE<gt>> or accessible "
8809 "via the call I<sysconf(_SC_IOV_MAX)>)."
8811 "I<liovcnt> と I<riovcnt> で指定される値は B<IOV_MAX> 以下でなければならない "
8812 "(B<IOV_MAX> は I<E<lt>limits.hE<gt>> で定義されており、 "
8813 "I<sysconf(_SC_IOV_MAX)> の呼び出しでも入手できる)。"
8816 #: build/C/man2/process_vm_readv.2:191
8818 "The count arguments and I<local_iov> are checked before doing any "
8819 "transfers. If the counts are too big, or I<local_iov> is invalid, or the "
8820 "addresses refer to regions that are inaccessible to the local process, none "
8821 "of the vectors will be processed and an error will be returned immediately."
8823 "要素数引き数と I<local_iov> のチェックは、 すべてのデータ転送に先立って行われ"
8824 "る。 要素数が大きすぎる場合や I<local_iov> が無効な場合、 アドレスがローカル"
8825 "プロセスがアクセスできない領域を参照している場合は、 配列のどの要素も処理され"
8829 #: build/C/man2/process_vm_readv.2:211
8831 "Note, however, that these system calls do not check the memory regions in "
8832 "the remote process until just before doing the read/write. Consequently, a "
8833 "partial read/write (see RETURN VALUE) may result if one of the "
8834 "I<remote_iov> elements points to an invalid memory region in the remote "
8835 "process. No further reads/writes will be attempted beyond that point. Keep "
8836 "this in mind when attempting to read data of unknown length (such as C "
8837 "strings that are null-terminated) from a remote process, by avoiding "
8838 "spanning memory pages (typically 4KiB) in a single remote I<iovec> element. "
8839 "(Instead, split the remote read into two I<remote_iov> elements and have "
8840 "them merge back into a single write I<local_iov> entry. The first read "
8841 "entry goes up to the page boundary, while the second starts on the next page "
8844 "ただし、 これらのシステムコールは、 実際に読み出し/書き込みを行う直前までリ"
8845 "モートプロセスのメモリー領域のチェックを行わない点に注意すること。 結果とし"
8846 "て、 I<remote_iov> の要素の一つがリモートプロセスで無効なメモリー領域を参照し"
8847 "ている場合、 部分的な読み出し/書き込み (「返り値」の節を参照) が行われること"
8848 "になる。 これ以降は読み出し/書き込みは行われない。 リモートプロセスから長さ不"
8849 "明のデータ (例えば NULL 終端された C 文字列) を読み出す際で、 リモート側の一"
8850 "つの I<iovec> 要素が複数のメモリーページ (通常は 4KiB) にまたがらないようにし"
8851 "ている場合は、 この点に注意が必要である。\n"
8852 "(リモートからの読み出しを 2 つの I<remote_iov> 要素に分割し、 1 つの "
8853 "I<local_iov> 要素への書き込みにマージすればよい。 最初の読み出しでページ境界"
8854 "まで読み出し、 次の読み出しを次のページ境界から行う。)"
8857 #: build/C/man2/process_vm_readv.2:225
8859 "In order to read from or write to another process, either the caller must "
8860 "have the capability B<CAP_SYS_PTRACE>, or the real user ID, effective user "
8861 "ID, and saved set-user-ID of the remote process must match the real user ID "
8862 "of the caller I<and> the real group ID, effective group ID, and saved set-"
8863 "group-ID of the remote process must match the real group ID of the caller. "
8864 "(The permission required is exactly the same as that required to perform a "
8865 "B<ptrace>(2) B<PTRACE_ATTACH> on the remote process.)"
8867 "他のプロセスからの読み出しや他のプロセスへの書き込みを行うには、 呼び出し元が"
8868 "ケーパビリティ B<CAP_SYS_PTRACE> を持っていなければならない、もしくは、 リ"
8869 "モートプロセスの実ユーザー ID、 実効ユーザー ID、 保存 set-user-ID が呼び出し"
8870 "元の実ユーザー ID と一致し、 かつリモートプロセスの実グループ ID、 実効グルー"
8871 "プ ID、 保存 set-group-ID が呼び出し元の実グループ ID と一致していなければな"
8872 "らない。 (ここで必要なアクセス許可は、 リモートプロセスに対して B<ptrace>(2) "
8873 "の B<PTRACE_ATTACH> を実行するのに必要な許可と全く同じである。)"
8876 #: build/C/man2/process_vm_readv.2:241
8878 "On success, B<process_vm_readv>() returns the number of bytes read and "
8879 "B<process_vm_writev>() returns the number of bytes written. This return "
8880 "value may be less than the total number of requested bytes, if a partial "
8881 "read/write occurred. (Partial transfers apply at the granularity of "
8882 "I<iovec> elements. These system calls won't perform a partial transfer that "
8883 "splits a single I<iovec> element.) The caller should check the return value "
8884 "to determine whether a partial read/write occurred."
8886 "成功すると、 B<process_vm_readv>() は読み出したバイト数を返し、 "
8887 "B<process_vm_writev>() は書き込んだバイト数を返す。 この返り値は、 読み出し/"
8888 "書き込みが部分的に行われた場合には、 要求された総バイト数よりも小さくなること"
8889 "がある (部分的な転送は I<iovec> 要素単位に行われ、 これらのシステムコールが一"
8890 "つの I<iovec> 要素の一部だけが転送されることはない)。 呼び出し元は返り値を検"
8891 "査して、 部分的な読み出し/書き込みが起こったかどうかを判定できる。"
8894 #: build/C/man2/process_vm_readv.2:245
8895 msgid "On error, -1 is returned and I<errno> is set appropriately."
8896 msgstr "エラーの場合は -1 が返され、 I<errno> が適切に設定される。"
8899 #: build/C/man2/process_vm_readv.2:257
8901 "The sum of the I<iov_len> values of either I<local_iov> or I<remote_iov> "
8902 "overflows a I<ssize_t> value."
8904 "I<local_iov> か I<remote_iov> のいずれかの I<iov_len> の合計値が I<ssize_t> "
8908 #: build/C/man2/process_vm_readv.2:261
8909 msgid "I<flags> is not 0."
8910 msgstr "I<flags> が 0 でない。"
8913 #: build/C/man2/process_vm_readv.2:267
8914 msgid "I<liovcnt> or I<riovcnt> is too large."
8915 msgstr "I<liovcnt> か I<riovcnt> が大きすぎる。"
8918 #: build/C/man2/process_vm_readv.2:272
8920 "The memory described by I<local_iov> is outside the caller's accessible "
8923 "I<local_iov> で指定されたメモリーが呼び出し元がアクセス可能なアドレス空間の外"
8927 #: build/C/man2/process_vm_readv.2:278
8929 "The memory described by I<remote_iov> is outside the accessible address "
8930 "space of the process I<pid>."
8932 "I<remote_iov> で指定されたメモリーがプロセス I<pid> がアクセス可能なアドレス"
8936 #: build/C/man2/process_vm_readv.2:283
8938 "Could not allocate memory for internal copies of the I<iovec> structures."
8939 msgstr "I<iovec> 構造体の内部コピーのためのメモリーを割り当てできなかった。"
8942 #: build/C/man2/process_vm_readv.2:287
8944 "The caller does not have permission to access the address space of the "
8947 "呼び出し側がプロセス I<pid> のアドレス空間に対するアクセス許可を\n"
8951 #: build/C/man2/process_vm_readv.2:292
8952 msgid "No process with ID I<pid> exists."
8953 msgstr "ID が I<pid> のプロセスが存在しない。"
8956 #: build/C/man2/process_vm_readv.2:295
8958 "These system calls were added in Linux 3.2. Support is provided in glibc "
8959 "since version 2.15."
8961 "これらのシステムコールは Linux 3.2 で追加された。ライブラリによる\n"
8962 "サポートは glibc バージョン 2.15 以降で提供されている。"
8965 #: build/C/man2/process_vm_readv.2:297
8966 msgid "These system calls are nonstandard Linux extensions."
8967 msgstr "これらのシステムコールは非標準で Linux による拡張である。"
8970 #: build/C/man2/process_vm_readv.2:303
8972 "The data transfers performed by B<process_vm_readv>() and "
8973 "B<process_vm_writev>() are not guaranteed to be atomic in any way."
8975 "B<process_vm_readv>() と B<process_vm_writev>() により実行されるデータ転送を"
8976 "どのように行ったとしても、 これらがアトミックに行われる保証はない。"
8978 #. Original user is MPI, http://www.mcs.anl.gov/research/projects/mpi/
8979 #. See also some benchmarks at http://lwn.net/Articles/405284/
8980 #. and http://marc.info/?l=linux-mm&m=130105930902915&w=2
8982 #: build/C/man2/process_vm_readv.2:311
8984 "These system calls were designed to permit fast message passing by allowing "
8985 "messages to be exchanged with a single copy operation (rather than the "
8986 "double copy that would be required when using, for example, shared memory or "
8989 "これらのシステムコールは、 (共有メモリーやパイプなどを使った場合に必要となる "
8991 "1 回のコピー処理でメッセージの交換を許すことで、 高速なメッセージ送信をできる"
8995 #: build/C/man2/process_vm_readv.2:319
8997 "The following code sample demonstrates the use of B<process_vm_readv>(). It "
8998 "reads 20 bytes at the address 0x10000 from the process with PID 10 and "
8999 "writes the first 10 bytes into I<buf1> and the second 10 bytes into I<buf2>."
9001 "以下のサンプルコードは B<process_vm_readv>() の使用例を示すものである。 この"
9002 "コードは PID 10 のプロセスのアドレス 0x10000 から 20 バイトを読み取り、 最初"
9003 "の 10 バイトを I<buf1> に、 残りの 10 バイトを I<buf2> に書き込む。"
9006 #: build/C/man2/process_vm_readv.2:322
9008 msgid "#include E<lt>sys/uio.hE<gt>\n"
9009 msgstr "#include E<lt>sys/uio.hE<gt>\n"
9012 #: build/C/man2/process_vm_readv.2:332
9018 " struct iovec local[2];\n"
9019 " struct iovec remote[1];\n"
9023 " pid_t pid = 10; /* PID of remote process */\n"
9028 " struct iovec local[2];\n"
9029 " struct iovec remote[1];\n"
9033 " pid_t pid = 10; /* PID of remote process */\n"
9036 #: build/C/man2/process_vm_readv.2:339
9039 " local[0].iov_base = buf1;\n"
9040 " local[0].iov_len = 10;\n"
9041 " local[1].iov_base = buf2;\n"
9042 " local[1].iov_len = 10;\n"
9043 " remote[0].iov_base = (void *) 0x10000;\n"
9044 " remote[0].iov_len = 20;\n"
9046 " local[0].iov_base = buf1;\n"
9047 " local[0].iov_len = 10;\n"
9048 " local[1].iov_base = buf2;\n"
9049 " local[1].iov_len = 10;\n"
9050 " remote[0].iov_base = (void *) 0x10000;\n"
9051 " remote[0].iov_len = 20;\n"
9054 #: build/C/man2/process_vm_readv.2:346
9057 " nread = process_vm_readv(pid, local, 2, remote, 1, 0);\n"
9058 " if (nread != 20)\n"
9064 " nread = process_vm_readv(pid, local, 2, remote, 1, 0);\n"
9065 " if (nread != 20)\n"
9072 #: build/C/man2/process_vm_readv.2:350
9073 msgid "B<readv>(2), B<writev>(2)"
9074 msgstr "B<readv>(2), B<writev>(2)"
9077 #: build/C/man2/ptrace.2:46
9083 #: build/C/man2/ptrace.2:49
9084 msgid "ptrace - process trace"
9085 msgstr "ptrace - プロセスのトレース"
9088 #: build/C/man2/ptrace.2:52
9090 msgid "B<#include E<lt>sys/ptrace.hE<gt>>\n"
9091 msgstr "B<#include E<lt>sys/ptrace.hE<gt>>\n"
9094 #: build/C/man2/ptrace.2:55
9097 "B<long ptrace(enum __ptrace_request >I<request>B<, pid_t >I<pid>B<, >\n"
9098 "B< void *>I<addr>B<, void *>I<data>B<);>\n"
9100 "B<long ptrace(enum __ptrace_request >I<request>B<, pid_t >I<pid>B<, >\n"
9101 "B< void *>I<addr>B<, void *>I<data>B<);>\n"
9104 #: build/C/man2/ptrace.2:64
9106 "The B<ptrace>() system call provides a means by which one process (the "
9107 "\"tracer\") may observe and control the execution of another process (the "
9108 "\"tracee\"), and examine and change the tracee's memory and registers. It "
9109 "is primarily used to implement breakpoint debugging and system call tracing."
9111 "B<ptrace>() システムコールは、 あるプロセス (\"tracer\") が、 別のプロセス "
9112 "(\"tracee\") の実行の監視/制御を行ったり、 tracee のメモリーやレジスターの調"
9113 "査/変更を行ったりする手段を提供する。 B<ptrace>() は、 主にブレークポイント"
9114 "によるデバッグやシステムコールのトレースを実装するのに用いられる。"
9117 #: build/C/man2/ptrace.2:75
9119 "A tracee first needs to be attached to the tracer. Attachment and "
9120 "subsequent commands are per thread: in a multithreaded process, every thread "
9121 "can be individually attached to a (potentially different) tracer, or left "
9122 "not attached and thus not debugged. Therefore, \"tracee\" always means "
9123 "\"(one) thread\", never \"a (possibly multithreaded) process\". Ptrace "
9124 "commands are always sent to a specific tracee using a call of the form"
9128 #: build/C/man2/ptrace.2:77
9130 msgid " ptrace(PTRACE_foo, pid, ...)\n"
9131 msgstr " ptrace(PTRACE_foo, pid, ...)\n"
9134 #: build/C/man2/ptrace.2:81
9135 msgid "where I<pid> is the thread ID of the corresponding Linux thread."
9136 msgstr "ここで I<pid> は対応する Linux スレッドのスレッド ID である。"
9139 #: build/C/man2/ptrace.2:87
9141 "(Note that in this page, a \"multithreaded process\" means a thread group "
9142 "consisting of threads created using the B<clone>(2) B<CLONE_THREAD> flag.)"
9146 #: build/C/man2/ptrace.2:98
9148 "A process can initiate a trace by calling B<fork>(2) and having the "
9149 "resulting child do a B<PTRACE_TRACEME>, followed (typically) by an "
9150 "B<execve>(2). Alternatively, one process may commence tracing another "
9151 "process using B<PTRACE_ATTACH> or B<PTRACE_SEIZE>."
9153 "プロセスがトレースを開始するには、 まず親プロセスで B<fork>(2) を呼び出す。 "
9154 "生成された子プロセスで B<PTRACE_TRACEME> を行い、 続いて (典型的には) "
9155 "B<execve>(2) を行なう。 別の方法としては、 プロセスが別のプロセスに対して "
9156 "B<PTRACE_ATTACH> か B<PTRACE_SEIZE> を使用し、 トレースを開始する。"
9159 #: build/C/man2/ptrace.2:115
9161 "While being traced, the tracee will stop each time a signal is delivered, "
9162 "even if the signal is being ignored. (An exception is B<SIGKILL>, which has "
9163 "its usual effect.) The tracer will be notified at its next call to "
9164 "B<waitpid>(2) (or one of the related \"wait\" system calls); that call will "
9165 "return a I<status> value containing information that indicates the cause of "
9166 "the stop in the tracee. While the tracee is stopped, the tracer can use "
9167 "various ptrace requests to inspect and modify the tracee. The tracer then "
9168 "causes the tracee to continue, optionally ignoring the delivered signal (or "
9169 "even delivering a different signal instead)."
9171 "トレースの実行中、tracee はシグナルが配送されるたびに、 たとえそのシグナルが"
9172 "無視されている場合であっても停止する (B<SIGKILL> は例外で、通常どおりの効果を"
9173 "持つ)。 tracer には次の B<waitpid>(2) (や関連の \"wait\" システムコール) の呼"
9174 "び出しで通知され、 その呼び出しでは tracee で停止の原因を示す情報が入った "
9175 "I<status> 値が返される。 tracee が停止している間に、 tracer は様々な ptrace "
9176 "の要求を使って tracee を調査したり修正したりすることができる。 それから "
9177 "tracer は tracee の実行を再開させるが、 配送されたシグナルを無視することもで"
9178 "きる (あるいは別のシグナルを配送することもできる) 。"
9181 #: build/C/man2/ptrace.2:125
9183 "If the B<PTRACE_O_TRACEEXEC> option is not in effect, all successful calls "
9184 "to B<execve>(2) by the traced process will cause it to be sent a B<SIGTRAP> "
9185 "signal, giving the parent a chance to gain control before the new program "
9190 #: build/C/man2/ptrace.2:129
9192 "When the tracer is finished tracing, it can cause the tracee to continue "
9193 "executing in a normal, untraced mode via B<PTRACE_DETACH>."
9195 "tracer がトレースを終了する際には、 B<PTRACE_DETACH> を用いて tracee を通常の"
9196 "トレースなしのモードにして、 実行を継続させることができる。"
9199 #: build/C/man2/ptrace.2:133
9200 msgid "The value of I<request> determines the action to be performed:"
9201 msgstr "I<request> の値がこのシステムコールの動作を決定する:"
9204 #: build/C/man2/ptrace.2:133
9206 msgid "B<PTRACE_TRACEME>"
9207 msgstr "B<PTRACE_TRACEME>"
9210 #: build/C/man2/ptrace.2:143
9212 "Indicate that this process is to be traced by its parent. A process "
9213 "probably shouldn't make this request if its parent isn't expecting to trace "
9214 "it. (I<pid>, I<addr>, and I<data> are ignored.)"
9216 "このプロセスが親プロセスによってトレースされることを表す。親プロセスが自プロ"
9217 "セスをトレースするつもりがない場合には、 おそらくこのプロセスは本要求を行うべ"
9218 "きではないだろう。 (I<pid>, I<addr>, I<data> は無視される。)"
9221 #: build/C/man2/ptrace.2:158
9223 "The B<PTRACE_TRACEME> request is used only by the tracee; the remaining "
9224 "requests are used only by the tracer. In the following requests, I<pid> "
9225 "specifies the thread ID of the tracee to be acted on. For requests other "
9226 "than B<PTRACE_ATTACH>, B<PTRACE_SEIZE>, B<PTRACE_INTERRUPT>, and "
9227 "B<PTRACE_KILL>, the tracee must be stopped."
9229 "B<PTRACE_TRACEME> 要求は tracee だけが使用するものである。 残りの要求は "
9230 "tracer だけが使用する。 以下の要求では、I<pid> は操作の対象となる tracee のス"
9231 "レッド ID を指定する。 B<PTRACE_ATTACH>, B<PTRACE_SEIZE>, "
9232 "B<PTRACE_INTERRUPT>, B<PTRACE_KILL> 以外の要求では、 tracee は停止していなけ"
9236 #: build/C/man2/ptrace.2:158
9238 msgid "B<PTRACE_PEEKTEXT>, B<PTRACE_PEEKDATA>"
9239 msgstr "B<PTRACE_PEEKTEXT>, B<PTRACE_PEEKDATA>"
9242 #: build/C/man2/ptrace.2:169
9244 "Read a word at the address I<addr> in the tracee's memory, returning the "
9245 "word as the result of the B<ptrace>() call. Linux does not have separate "
9246 "text and data address spaces, so these two requests are currently "
9247 "equivalent. (I<data> is ignored; but see NOTES.)"
9249 "tracee のメモリーの I<addr> のアドレスから 1 ワードを読み出す。 読み出した"
9250 "ワードは B<ptrace>() の返り値として返される。 Linux ではテキスト (text) と"
9251 "データ (data) で 同じアドレス空間を使用するため、これらの 2 つの要求は現在の"
9252 "ところ 同じものである。 (I<data> は無視される。 ただし「注意」を参照。)"
9255 #: build/C/man2/ptrace.2:169
9257 msgid "B<PTRACE_PEEKUSER>"
9258 msgstr "B<PTRACE_PEEKUSER>"
9260 #. PTRACE_PEEKUSR in kernel source, but glibc uses PTRACE_PEEKUSER,
9261 #. and that is the name that seems common on other systems.
9263 #: build/C/man2/ptrace.2:187
9265 "Read a word at offset I<addr> in the tracee's USER area, which holds the "
9266 "registers and other information about the process (see I<E<lt>sys/user."
9267 "hE<gt>>). The word is returned as the result of the B<ptrace>() call. "
9268 "Typically, the offset must be word-aligned, though this might vary by "
9269 "architecture. See NOTES. (I<data> is ignored; but see NOTES.)"
9271 "tracee の USER 領域のオフセット I<addr> の位置から 1 ワードを読み込む。USER "
9272 "領域にはそのプロセスの レジスター (registers) などの情報が保持されている "
9273 "(I<E<lt>sys/user.hE<gt>> を参照)。読み込んだワードは B<ptrace>() コールの結"
9274 "果として返される。 たいていはオフセットはワード境界になければならないが、 "
9275 "アーキテクチャーによってはその必要はない。 「注意」の節を参照。 (I<data> は無"
9276 "視される。 ただし「注意」を参照。)"
9279 #: build/C/man2/ptrace.2:187
9281 msgid "B<PTRACE_POKETEXT>, B<PTRACE_POKEDATA>"
9282 msgstr "B<PTRACE_POKETEXT>, B<PTRACE_POKEDATA>"
9285 #: build/C/man2/ptrace.2:199
9287 "Copy the word I<data> to the address I<addr> in the tracee's memory. As for "
9288 "B<PTRACE_PEEKTEXT> and B<PTRACE_PEEKDATA>, these two requests are currently "
9291 "ワード I<data> を tracee のメモリーの I<addr> のアドレスへコピーする。 "
9292 "B<PTRACE_PEEKTEXT> や B<PTRACE_PEEKDATA> と同様に、 現在のところ二つの要求は"
9296 #: build/C/man2/ptrace.2:199
9298 msgid "B<PTRACE_POKEUSER>"
9299 msgstr "B<PTRACE_POKEUSER>"
9301 #. PTRACE_POKEUSR in kernel source, but glibc uses PTRACE_POKEUSER,
9302 #. and that is the name that seems common on other systems.
9303 #. FIXME In the preceding sentence, which modifications are disallowed,
9304 #. and when they are disallowed, how does user space discover that fact?
9306 #: build/C/man2/ptrace.2:215
9308 "Copy the word I<data> to offset I<addr> in the tracee's USER area. As for "
9309 "B<PTRACE_PEEKUSER>, the offset must typically be word-aligned. In order to "
9310 "maintain the integrity of the kernel, some modifications to the USER area "
9313 "ワード I<data> を tracee の USER 領域のオフセット I<addr> のアドレスにコピー"
9314 "する。 B<PTRACE_PEEKUSER> と同様に、通常、オフセットはワード境界になければな"
9315 "らない。 カーネルの完全性 (integrity) を維持するため、 変更内容によっては "
9316 "USER 領域の変更は禁止されている。"
9319 #: build/C/man2/ptrace.2:215
9321 msgid "B<PTRACE_GETREGS>, B<PTRACE_GETFPREGS>"
9322 msgstr "B<PTRACE_GETREGS>, B<PTRACE_GETFPREGS>"
9325 #: build/C/man2/ptrace.2:238
9327 "Copy the tracee's general-purpose or floating-point registers, respectively, "
9328 "to the address I<data> in the tracer. See I<E<lt>sys/user.hE<gt>> for "
9329 "information on the format of this data. (I<addr> is ignored.) Note that "
9330 "SPARC systems have the meaning of I<data> and I<addr> reversed; that is, "
9331 "I<data> is ignored and the registers are copied to the address I<addr>. "
9332 "B<PTRACE_GETREGS> and B<PTRACE_GETFPREGS> are not present on all "
9335 "それぞれ、 tracee の汎用レジスター、 浮動小数点レジスターを tracer の "
9336 "I<data> のアドレスにコピーする。この data の書式に関しては I<E<lt>sys/user."
9337 "hE<gt>> を参照すること。(I<addr> は無視される。) SPARC システムでは I<data> "
9338 "と I<addr> の意味が逆になっている点に注意。 つまり、 I<data> は無視され、 レ"
9339 "ジスターはアドレス I<addr> にコピーされる。 B<PTRACE_GETREGS> と "
9340 "B<PTRACE_GETFPREGS> はすべてのアーキテクチャーで存在するわけではない。"
9343 #: build/C/man2/ptrace.2:238
9345 msgid "B<PTRACE_GETREGSET> (since Linux 2.6.34)"
9346 msgstr " B<PTRACE_GETREGSET> (since Linux 2.6.34)"
9349 #: build/C/man2/ptrace.2:259
9351 "Read the tracee's registers. I<addr> specifies, in an architecture-"
9352 "dependent way, the type of registers to be read. B<NT_PRSTATUS> (with "
9353 "numerical value 1) usually results in reading of general-purpose "
9354 "registers. If the CPU has, for example, floating-point and/or vector "
9355 "registers, they can be retrieved by setting I<addr> to the corresponding "
9356 "B<NT_foo> constant. I<data> points to a B<struct iovec>, which describes "
9357 "the destination buffer's location and length. On return, the kernel "
9358 "modifies B<iov.len> to indicate the actual number of bytes returned."
9362 #: build/C/man2/ptrace.2:259
9364 msgid "B<PTRACE_SETREGS>, B<PTRACE_SETFPREGS>"
9365 msgstr "B<PTRACE_SETREGS>, B<PTRACE_SETFPREGS>"
9367 #. FIXME . In the preceding sentence, which modifications are disallowed,
9368 #. and when they are disallowed, how does user space discover that fact?
9370 #: build/C/man2/ptrace.2:284
9372 "Modify the tracee's general-purpose or floating-point registers, "
9373 "respectively, from the address I<data> in the tracer. As for "
9374 "B<PTRACE_POKEUSER>, some general-purpose register modifications may be "
9375 "disallowed. (I<addr> is ignored.) Note that SPARC systems have the meaning "
9376 "of I<data> and I<addr> reversed; that is, I<data> is ignored and the "
9377 "registers are copied from the address I<addr>. B<PTRACE_SETREGS> and "
9378 "B<PTRACE_SETFPREGS> are not present on all architectures."
9380 "それぞれ、 tracee の汎用レジスター、浮動小数点レジスターに tracer の I<date> "
9381 "のアドレスからコピーする。 B<PTRACE_POKEUSER> と同様に、汎用レジスターによっ"
9382 "ては 変更が禁止されている場合がある。 (I<addr> は無視される。)\n"
9384 "Note that SPARC systems have the meaning of I<data> and I<addr>\n"
9385 "reversed; that is, I<data> is ignored and the registers are copied\n"
9386 "from the address I<addr>. B<PTRACE_SETREGS> and B<PTRACE_SETFPREGS>\n"
9387 "are not present on all architectures."
9390 #: build/C/man2/ptrace.2:284
9392 msgid "B<PTRACE_SETREGSET> (since Linux 2.6.34)"
9393 msgstr " B<PTRACE_SETREGSET> (since Linux 2.6.34)"
9396 #: build/C/man2/ptrace.2:293
9398 "Modify the tracee's registers. The meaning of I<addr> and I<data> is "
9399 "analogous to B<PTRACE_GETREGSET>."
9403 #: build/C/man2/ptrace.2:293
9405 msgid "B<PTRACE_GETSIGINFO> (since Linux 2.3.99-pre6)"
9406 msgstr "B<PTRACE_GETSIGINFO> (Linux 2.3.99-pre6 以降)"
9409 #: build/C/man2/ptrace.2:305
9411 "Retrieve information about the signal that caused the stop. Copy a "
9412 "I<siginfo_t> structure (see B<sigaction>(2)) from the tracee to the address "
9413 "I<data> in the tracer. (I<addr> is ignored.)"
9415 "停止の原因となったシグナルに関する情報を取得する。 I<siginfo_t> 構造体 "
9416 "(B<sigaction>(2) 参照) を tracee から tracer の I<data> のアドレスにコピーす"
9417 "る。 (I<addr> は無視される。)"
9420 #: build/C/man2/ptrace.2:305
9422 msgid "B<PTRACE_SETSIGINFO> (since Linux 2.3.99-pre6)"
9423 msgstr "B<PTRACE_SETSIGINFO> (Linux 2.3.99-pre6 以降)"
9426 #: build/C/man2/ptrace.2:321
9428 "Set signal information: copy a I<siginfo_t> structure from the address "
9429 "I<data> in the tracer to the tracee. This will affect only signals that "
9430 "would normally be delivered to the tracee and were caught by the tracer. It "
9431 "may be difficult to tell these normal signals from synthetic signals "
9432 "generated by B<ptrace>() itself. (I<addr> is ignored.)"
9434 "シグナル情報を設定する。 I<siginfo_t> 構造体を tracer のデータ I<data> のアド"
9435 "レスから tracee にコピーする。 この処理を行うことができるのは、 tracee に通常"
9436 "は配送されるはずで トレーサに捕捉されたシグナルについてだけである。 これらの"
9437 "通常のシグナルと B<ptrace>() 自身が発生するシグナルを見分けるのは難しいかも"
9438 "しれない。 (I<addr> は無視される。)"
9441 #: build/C/man2/ptrace.2:321
9443 msgid "B<PTRACE_PEEKSIGINFO> (since Linux 3.10)"
9444 msgstr "B<PTRACE_PEEKSIGINFO> (Linux 3.10 以降)"
9446 #. commit 84c751bd4aebbaae995fe32279d3dba48327bad4
9448 #: build/C/man2/ptrace.2:347
9450 "Retrieve I<siginfo_t> structures without removing signals from a queue. "
9451 "I<addr> points to a I<ptrace_peeksiginfo_args> structure that specifies the "
9452 "ordinal position from which copying of signals should start, and the number "
9453 "of signals to copy. I<siginfo_t> structures are copied into the buffer "
9454 "pointed to by I<data>. The return value contains the number of copied "
9455 "signals (zero indicates that there is no signal corresponding to the "
9456 "specified ordinal position). Within the returned I<siginfo> structures, the "
9457 "I<si_code> field includes information (B<__SI_CHLD>, B<__SI_FAULT>, etc.) "
9458 "that are not otherwise exposed to user space."
9462 #: build/C/man2/ptrace.2:356
9465 "struct ptrace_peeksiginfo_args {\n"
9466 " u64 off; /* Ordinal position in queue at which\n"
9467 " to start copying signals */\n"
9468 " u32 flags; /* PTRACE_PEEKSIGINFO_SHARED or 0 */\n"
9469 " s32 nr; /* Number of signals to copy */\n"
9474 #: build/C/man2/ptrace.2:363
9476 "Currently, there is only one flag, B<PTRACE_PEEKSIGINFO_SHARED>, for dumping "
9477 "signals from the process-wide signal queue. If this flag is not set, "
9478 "signals are read from the per-thread queue of the specified thread."
9482 #: build/C/man2/ptrace.2:365
9484 msgid "B<PTRACE_GETSIGMASK> (since Linux 3.11)"
9485 msgstr "B<PTRACE_GETSIGMASK> (Linux 3.11 以降)"
9487 #. commit 29000caecbe87b6b66f144f72111f0d02fbbf0c1
9489 #: build/C/man2/ptrace.2:380
9491 "Place a copy of the mask of blocked signals (see B<sigprocmask>(2)) in the "
9492 "buffer pointed to by I<data>, which should be a pointer to a buffer of type "
9493 "I<sigset_t>. The I<addr> argument contains the size of the buffer pointed "
9494 "to by I<data> (i.e., I<sizeof(sigset_t)>)."
9498 #: build/C/man2/ptrace.2:380
9500 msgid "B<PTRACE_SETSIGMASK> (since Linux 3.11)"
9501 msgstr "B<PTRACE_SETSIGMASK> (Linux 3.11 以降)"
9504 #: build/C/man2/ptrace.2:394
9506 "Change the mask of blocked signals (see B<sigprocmask>(2)) to the value "
9507 "specified in the buffer pointed to by I<data>, which should be a pointer to "
9508 "a buffer of type I<sigset_t>. The I<addr> argument contains the size of the "
9509 "buffer pointed to by I<data> (i.e., I<sizeof(sigset_t)>)."
9513 #: build/C/man2/ptrace.2:394
9515 msgid "B<PTRACE_SETOPTIONS> (since Linux 2.4.6; see BUGS for caveats)"
9516 msgstr "B<PTRACE_SETOPTIONS> (Linux 2.4.6 以降; バグの章にある警告も参照)"
9519 #: build/C/man2/ptrace.2:403
9521 "Set ptrace options from I<data>. (I<addr> is ignored.) I<data> is "
9522 "interpreted as a bit mask of options, which are specified by the following "
9525 "I<data> に基づいて ptrace のオプションを設定する (I<addr> は無視される)。 "
9526 "I<data> はオプションのビットマスクとして解釈され、 オプションには以下のフラグ"
9530 #: build/C/man2/ptrace.2:404
9532 msgid "B<PTRACE_O_EXITKILL> (since Linux 3.8)"
9533 msgstr " B<PTRACE_O_EXITKILL> (since Linux 3.8)"
9535 #. commit 992fb6e170639b0849bace8e49bf31bd37c4123
9537 #: build/C/man2/ptrace.2:412
9539 "If a tracer sets this flag, a B<SIGKILL> signal will be sent to every tracee "
9540 "if the tracer exits. This option is useful for ptrace jailers that want to "
9541 "ensure that tracees can never escape the tracer's control."
9545 #: build/C/man2/ptrace.2:412
9547 msgid "B<PTRACE_O_TRACECLONE> (since Linux 2.5.46)"
9548 msgstr "B<PTRACE_O_TRACECLONE> (Linux 2.5.46 以降)"
9551 #: build/C/man2/ptrace.2:429
9553 "Stop the tracee at the next B<clone>(2) and automatically start tracing the "
9554 "newly cloned process, which will start with a B<SIGSTOP>, or "
9555 "B<PTRACE_EVENT_STOP> if B<PTRACE_SEIZE> was used. A B<waitpid>(2) by the "
9556 "tracer will return a I<status> value such that"
9558 "次の B<clone>(2) 呼び出し時に tracee を停止し、 新しくクローンされたプロセス"
9559 "のトレースを自動的に開始し、 B<SIGSTOP> でプロセスの実行を開始する。 "
9560 "B<PTRACE_SEIZE> が使用された場合は B<PTRACE_EVENT_STOP> で開始する。 tracer "
9561 "による B<waitpid>(2) の呼び出しでは以下のような I<status> 値が返る。"
9564 #: build/C/man2/ptrace.2:432
9566 msgid " statusE<gt>E<gt>8 == (SIGTRAP | (PTRACE_EVENT_CLONEE<lt>E<lt>8))\n"
9567 msgstr " statusE<gt>E<gt>8 == (SIGTRAP | (PTRACE_EVENT_CLONEE<lt>E<lt>8))\n"
9570 #: build/C/man2/ptrace.2:436 build/C/man2/ptrace.2:522
9571 #: build/C/man2/ptrace.2:555
9572 msgid "The PID of the new process can be retrieved with B<PTRACE_GETEVENTMSG>."
9573 msgstr "新規のプロセスの PID は B<PTRACE_GETEVENTMSG> で取得できる。"
9576 #: build/C/man2/ptrace.2:457
9578 "This option may not catch B<clone>(2) calls in all cases. If the tracee "
9579 "calls B<clone>(2) with the B<CLONE_VFORK> flag, B<PTRACE_EVENT_VFORK> will "
9580 "be delivered instead if B<PTRACE_O_TRACEVFORK> is set; otherwise if the "
9581 "tracee calls B<clone>(2) with the exit signal set to B<SIGCHLD>, "
9582 "B<PTRACE_EVENT_FORK> will be delivered if B<PTRACE_O_TRACEFORK> is set."
9584 "このオプションで全ての B<clone>(2) コールを捕まえられるわけではない。 "
9585 "tracee が B<CLONE_VFORK> フラグ付きで B<clone>(2) を呼び出した場合、 "
9586 "B<PTRACE_O_TRACEVFORK> が設定されていれば代わりに B<PTRACE_EVENT_VFORK> が配"
9587 "送される。 また、 tracee が終了シグナルを B<SIGCHLD> に設定して B<clone>(2) "
9588 "を呼び出した場合は、 B<PTRACE_O_TRACEFORK> が設定されていれば "
9589 "B<PTRACE_EVENT_FORK> が配送される。"
9592 #: build/C/man2/ptrace.2:457
9594 msgid "B<PTRACE_O_TRACEEXEC> (since Linux 2.5.46)"
9595 msgstr "B<PTRACE_O_TRACEEXEC> (Linux 2.5.46 以降)"
9598 #: build/C/man2/ptrace.2:466
9600 "Stop the tracee at the next B<execve>(2). A B<waitpid>(2) by the tracer "
9601 "will return a I<status> value such that"
9605 #: build/C/man2/ptrace.2:469
9607 msgid " statusE<gt>E<gt>8 == (SIGTRAP | (PTRACE_EVENT_EXECE<lt>E<lt>8))\n"
9608 msgstr " statusE<gt>E<gt>8 == (SIGTRAP | (PTRACE_EVENT_EXECE<lt>E<lt>8))\n"
9611 #: build/C/man2/ptrace.2:475
9613 "If the execing thread is not a thread group leader, the thread ID is reset "
9614 "to thread group leader's ID before this stop. Since Linux 3.0, the former "
9615 "thread ID can be retrieved with B<PTRACE_GETEVENTMSG>."
9619 #: build/C/man2/ptrace.2:475
9621 msgid "B<PTRACE_O_TRACEEXIT> (since Linux 2.5.60)"
9622 msgstr "B<PTRACE_O_TRACEEXIT> (Linux 2.5.60 以降)"
9625 #: build/C/man2/ptrace.2:483
9627 "Stop the tracee at exit. A B<waitpid>(2) by the tracer will return a "
9628 "I<status> value such that"
9630 "exit 時に tracee を停止する。 tracer による B<waiting>(2) では以下のような "
9634 #: build/C/man2/ptrace.2:486
9636 msgid " statusE<gt>E<gt>8 == (SIGTRAP | (PTRACE_EVENT_EXITE<lt>E<lt>8))\n"
9637 msgstr " statusE<gt>E<gt>8 == (SIGTRAP | (PTRACE_EVENT_EXITE<lt>E<lt>8))\n"
9640 #: build/C/man2/ptrace.2:490
9641 msgid "The tracee's exit status can be retrieved with B<PTRACE_GETEVENTMSG>."
9642 msgstr "tracee の終了ステータスは B<PTRACE_GETEVENTMSG> で取得できる。"
9645 #: build/C/man2/ptrace.2:498
9647 "The tracee is stopped early during process exit, when registers are still "
9648 "available, allowing the tracer to see where the exit occurred, whereas the "
9649 "normal exit notification is done after the process is finished exiting. "
9650 "Even though context is available, the tracer cannot prevent the exit from "
9651 "happening at this point."
9653 "tracee の停止はレジスターがまだ参照可能であるプロセス終了処理の初期に行わ"
9654 "れ、 トレーサはどこで終了が発生したかを知ることができる。 通常の終了通知 "
9655 "(exit notification) はプロセスの終了処理が完了した後に 行われる。コンテキスト"
9656 "を参照することはできるにも関わらず、 トレーサはこの時点から終了を止めることは"
9660 #: build/C/man2/ptrace.2:498
9662 msgid "B<PTRACE_O_TRACEFORK> (since Linux 2.5.46)"
9663 msgstr "B<PTRACE_O_TRACEFORK> (Linux 2.5.46 以降)"
9666 #: build/C/man2/ptrace.2:515
9668 "Stop the tracee at the next B<fork>(2) and automatically start tracing the "
9669 "newly forked process, which will start with a B<SIGSTOP>, or "
9670 "B<PTRACE_EVENT_STOP> if B<PTRACE_SEIZE> was used. A B<waitpid>(2) by the "
9671 "tracer will return a I<status> value such that"
9673 "次の B<fork>(2) 呼び出し時に tracee を停止し、 新しく fork されたプロセスの"
9674 "トレースを自動的に開始し、 B<SIGSTOP> でそのプロセスの実行を開始する。 "
9675 "B<PTRACE_SEIZE> が使用された場合は B<PTRACE_EVENT_STOP> で実行を開始する。 "
9676 "tracer による B<waitpid>(2) の呼び出しでは以下のような I<status> 値が返る。"
9679 #: build/C/man2/ptrace.2:518
9681 msgid " statusE<gt>E<gt>8 == (SIGTRAP | (PTRACE_EVENT_FORKE<lt>E<lt>8))\n"
9682 msgstr " statusE<gt>E<gt>8 == (SIGTRAP | (PTRACE_EVENT_FORKE<lt>E<lt>8))\n"
9685 #: build/C/man2/ptrace.2:522
9687 msgid "B<PTRACE_O_TRACESYSGOOD> (since Linux 2.4.6)"
9688 msgstr "B<PTRACE_O_TRACESYSGOOD> (Linux 2.4.6 以降)"
9691 #: build/C/man2/ptrace.2:531
9693 "When delivering system call traps, set bit 7 in the signal number (i.e., "
9694 "deliver I<SIGTRAP|0x80>). This makes it easy for the tracer to distinguish "
9695 "normal traps from those caused by a system call. (B<PTRACE_O_TRACESYSGOOD> "
9696 "may not work on all architectures.)"
9698 "システムコールのトラップが配送されたときに、シグナル番号のビット 7 を設定す"
9699 "る (すなわち、I<SIGTRAP | 0x80> を配送する)。 これにより、トレーサが通常のト"
9700 "ラップとシステムコールによるトラップを区別しやすくなる。 "
9701 "(B<PTRACE_O_TRACESYSGOOD> はどのアーキテクチャーでも動作しない可能性がある。)"
9704 #: build/C/man2/ptrace.2:531
9706 msgid "B<PTRACE_O_TRACEVFORK> (since Linux 2.5.46)"
9707 msgstr "B<PTRACE_O_TRACEVFORK> (Linux 2.5.46 以降)"
9710 #: build/C/man2/ptrace.2:548
9712 "Stop the tracee at the next B<vfork>(2) and automatically start tracing the "
9713 "newly vforked process, which will start with a B<SIGSTOP>, or "
9714 "B<PTRACE_EVENT_STOP> if B<PTRACE_SEIZE> was used. A B<waitpid>(2) by the "
9715 "tracer will return a I<status> value such that"
9717 "次の B<vfork>(2) 呼び出し時に tracee を停止し、 新しく vfork されたプロセス"
9718 "のトレースを自動的に開始し、 B<SIGSTOP> でそのプロセスの実行を開始する。 "
9719 "B<PTRACE_SEIZE> が使用された場合は B<PTRACE_EVENT_STOP> で実行を開始する。 "
9720 "tracer による B<waitpid>(2) の呼び出しでは以下のような I<status> 値が返る。"
9723 #: build/C/man2/ptrace.2:551
9725 msgid " statusE<gt>E<gt>8 == (SIGTRAP | (PTRACE_EVENT_VFORKE<lt>E<lt>8))\n"
9726 msgstr " statusE<gt>E<gt>8 == (SIGTRAP | (PTRACE_EVENT_VFORKE<lt>E<lt>8))\n"
9729 #: build/C/man2/ptrace.2:555
9731 msgid "B<PTRACE_O_TRACEVFORKDONE> (since Linux 2.5.60)"
9732 msgstr "B<PTRACE_O_TRACEVFORKDONE> (Linux 2.5.60 以降)"
9735 #: build/C/man2/ptrace.2:564
9737 "Stop the tracee at the completion of the next B<vfork>(2). A B<waitpid>(2) "
9738 "by the tracer will return a I<status> value such that"
9742 #: build/C/man2/ptrace.2:567
9744 msgid " statusE<gt>E<gt>8 == (SIGTRAP | (PTRACE_EVENT_VFORK_DONEE<lt>E<lt>8))\n"
9748 #: build/C/man2/ptrace.2:571
9750 "The PID of the new process can (since Linux 2.6.18) be retrieved with "
9751 "B<PTRACE_GETEVENTMSG>."
9755 #: build/C/man2/ptrace.2:571
9757 msgid "B<PTRACE_O_TRACESECCOMP> (since Linux 3.5)"
9758 msgstr "B<PTRACE_O_TRACESECCOMP> (Linux 3.5 以降)"
9761 #: build/C/man2/ptrace.2:582
9763 "Stop the tracee when a B<seccomp>(2) B<SECCOMP_RET_TRACE> rule is "
9764 "triggered. A B<waitpid>(2) by the tracer will return a I<status> value "
9767 "B<seccomp>(2) B<SECCOMP_RET_TRACE> ルールが起動された場合に tracee を停止す"
9768 "る。 tracer による B<waitpid>(2) の呼び出しでは以下のような I<status> 値が返"
9772 #: build/C/man2/ptrace.2:585
9774 msgid " statusE<gt>E<gt>8 == (SIGTRAP | (PTRACE_EVENT_SECCOMPE<lt>E<lt>8))\n"
9775 msgstr " statusE<gt>E<gt>8 == (SIGTRAP | (PTRACE_EVENT_SECCOMPE<lt>E<lt>8))\n"
9778 #: build/C/man2/ptrace.2:595
9780 "While this triggers a B<PTRACE_EVENT> stop, it is similar to a syscall-enter-"
9781 "stop, in that the tracee has not yet entered the syscall that seccomp "
9782 "triggered on. The seccomp event message data (from the B<SECCOMP_RET_DATA> "
9783 "portion of the seccomp filter rule) can be retrieved with "
9784 "B<PTRACE_GETEVENTMSG>."
9788 #: build/C/man2/ptrace.2:596
9790 msgid "B<PTRACE_GETEVENTMSG> (since Linux 2.5.46)"
9791 msgstr "B<PTRACE_GETEVENTMSG> (Linux 2.5.46 以降)"
9794 #: build/C/man2/ptrace.2:623
9796 "Retrieve a message (as an I<unsigned long>) about the ptrace event that "
9797 "just happened, placing it at the address I<data> in the tracer. For "
9798 "B<PTRACE_EVENT_EXIT>, this is the tracee's exit status. For "
9799 "B<PTRACE_EVENT_FORK>, B<PTRACE_EVENT_VFORK>, B<PTRACE_EVENT_VFORK_DONE>, and "
9800 "B<PTRACE_EVENT_CLONE>, this is the PID of the new process. For "
9801 "B<PTRACE_EVENT_SECCOMP>, this is the B<seccomp>(2) filter's "
9802 "B<SECCOMP_RET_DATA> associated with the triggered rule. (I<addr> is "
9805 "発生したばかりの ptrace イベントに関するメッセージを (I<unsigned long> 型で) "
9806 "取得する。 取得したメッセージは tracer の I<data> のアドレスに格納される。 格"
9807 "納される内容は、 B<PTRACE_EVENT_EXIT> の場合は tracee の終了ステータスであ"
9808 "る。 B<PTRACE_EVENT_FORK>, B<PTRACE_EVENT_VFORK>, "
9809 "B<PTRACE_EVENT_VFORK_DONE>, B<PTRACE_EVENT_CLONE> の場合は新しいプロセスの "
9810 "PID が格納される。 B<PTRACE_EVENT_SECCOMP> の場合は、起動されたルールに関連付"
9811 "けられた B<seccomp>(2) フィルターの B<SECCOMP_RET_DATA> が格納される。 "
9815 #: build/C/man2/ptrace.2:623
9817 msgid "B<PTRACE_CONT>"
9818 msgstr "B<PTRACE_CONT>"
9821 #: build/C/man2/ptrace.2:635
9823 "Restart the stopped tracee process. If I<data> is nonzero, it is "
9824 "interpreted as the number of a signal to be delivered to the tracee; "
9825 "otherwise, no signal is delivered. Thus, for example, the tracer can "
9826 "control whether a signal sent to the tracee is delivered or not. (I<addr> "
9829 "停止した tracee の実行を再開させる。 I<data> がゼロでない場合、 tracee に配送"
9830 "されるシグナル数と解釈される。 ゼロの場合はシグナルは配送されない。 これを使"
9831 "うと、例えば、 tracer は tracee に送られたシグナルを実際に配送するかどうかを "
9832 "制御することができる。(I<addr> は無視される。)"
9835 #: build/C/man2/ptrace.2:635
9837 msgid "B<PTRACE_SYSCALL>, B<PTRACE_SINGLESTEP>"
9838 msgstr "B<PTRACE_SYSCALL>, B<PTRACE_SINGLESTEP>"
9841 #: build/C/man2/ptrace.2:659
9843 "Restart the stopped tracee as for B<PTRACE_CONT>, but arrange for the tracee "
9844 "to be stopped at the next entry to or exit from a system call, or after "
9845 "execution of a single instruction, respectively. (The tracee will also, as "
9846 "usual, be stopped upon receipt of a signal.) From the tracer's perspective, "
9847 "the tracee will appear to have been stopped by receipt of a B<SIGTRAP>. So, "
9848 "for B<PTRACE_SYSCALL>, for example, the idea is to inspect the arguments to "
9849 "the system call at the first stop, then do another B<PTRACE_SYSCALL> and "
9850 "inspect the return value of the system call at the second stop. The I<data> "
9851 "argument is treated as for B<PTRACE_CONT>. (I<addr> is ignored.)"
9853 "B<PTRACE_CONT> と同様に停止した tracee を再開する。ただし、 "
9854 "B<PTRACE_SYSCALL> の場合は tracee が 次にシステムコールに入るかシステムコール"
9855 "から抜けるかする時に、 B<PTRACE_SINGLESTEP> の場合は 1 命令 (instruction) 実"
9856 "行した後に停止させる (通常どおり、 tracee はシグナルを受け取った場合にも停止"
9857 "する)。 tracer から見ると、 tracee は B<SIGTRAP> を受信して停止したように見え"
9858 "る。そのため、例えば B<PTRACE_SYSCALL> を使うと、1回目の停止で引き数を調べて "
9859 "B<PTRACE_SYSCALL> を実行し、 2回目の停止でシステムコールの返り値を調べる、 と"
9860 "いうようなことができる。 引き数 I<data> は B<PTRACE_CONT> の場合と同じ様に解"
9861 "釈される。 (I<addr> は無視される。)"
9864 #: build/C/man2/ptrace.2:659
9866 msgid "B<PTRACE_SYSEMU>, B<PTRACE_SYSEMU_SINGLESTEP> (since Linux 2.6.14)"
9867 msgstr "B<PTRACE_SYSEMU>, B<PTRACE_SYSEMU_SINGLESTEP> (Linux 2.6.14 以降)"
9871 #: build/C/man2/ptrace.2:680
9873 "For B<PTRACE_SYSEMU>, continue and stop on entry to the next system call, "
9874 "which will not be executed. For B<PTRACE_SYSEMU_SINGLESTEP>, do the same "
9875 "but also singlestep if not a system call. This call is used by programs "
9876 "like User Mode Linux that want to emulate all the tracee's system calls. "
9877 "The I<data> argument is treated as for B<PTRACE_CONT>. The I<addr> argument "
9878 "is ignored. These requests are currently supported only on x86."
9880 "B<PTRACE_SYSEMU> は、実行を再開し、次のシステムコールに入る時に停止させる。 "
9881 "システムコールは実行されない。 B<PTRACE_SYSEMU_SINGLESTEP> も同様だが、システ"
9882 "ムコールでない場合には 1 命令 (singlestep) だけ実行した時点でも停止させる。 "
9883 "このコールは User Mode Linux のように tracee のシステムコールを全て エミュ"
9884 "レートしようとするプログラムで使用される。 引き数 I<data> は B<PTRACE_CONT> "
9885 "の場合と同じ様に解釈される。 I<addr> 引き数は無視される。 現在のところこれら"
9886 "の要求は x86 でのみサポートされている。"
9889 #: build/C/man2/ptrace.2:680
9891 msgid "B<PTRACE_LISTEN> (since Linux 3.4)"
9892 msgstr " B<PTRACE_LISTEN> (since Linux 3.4)"
9895 #: build/C/man2/ptrace.2:691
9897 "Restart the stopped tracee, but prevent it from executing. The resulting "
9898 "state of the tracee is similar to a process which has been stopped by a "
9899 "B<SIGSTOP> (or other stopping signal). See the \"group-stop\" subsection "
9900 "for additional information. B<PTRACE_LISTEN> works only on tracees attached "
9901 "by B<PTRACE_SEIZE>."
9905 #: build/C/man2/ptrace.2:691
9907 msgid "B<PTRACE_KILL>"
9908 msgstr "B<PTRACE_KILL>"
9911 #: build/C/man2/ptrace.2:700
9913 "Send the tracee a B<SIGKILL> to terminate it. (I<addr> and I<data> are "
9916 "tracee に B<SIGKILL> を送り終了させる。(I<addr> と I<data> は無視される。)"
9918 #. [Note from Denys Vlasenko:
9919 #. deprecation suggested by Oleg Nesterov. He prefers to deprecate it
9920 #. instead of describing (and needing to support) PTRACE_KILL's quirks.]
9922 #: build/C/man2/ptrace.2:719
9924 "I<This operation is deprecated; do not use it!> Instead, send a B<SIGKILL> "
9925 "directly using B<kill>(2) or B<tgkill>(2). The problem with B<PTRACE_KILL> "
9926 "is that it requires the tracee to be in signal-delivery-stop, otherwise it "
9927 "may not work (i.e., may complete successfully but won't kill the tracee). "
9928 "By contrast, sending a B<SIGKILL> directly has no such limitation."
9932 #: build/C/man2/ptrace.2:719
9934 msgid "B<PTRACE_INTERRUPT> (since Linux 3.4)"
9935 msgstr " B<PTRACE_INTERRUPT> (since Linux 3.4)"
9938 #: build/C/man2/ptrace.2:747
9940 "Stop a tracee. If the tracee is running or sleeping in kernel space and "
9941 "B<PTRACE_SYSCALL> is in effect, the system call is interrupted and syscall-"
9942 "exit-stop is reported. (The interrupted system call is restarted when the "
9943 "tracee is restarted.) If the tracee was already stopped by a signal and "
9944 "B<PTRACE_LISTEN> was sent to it, the tracee stops with B<PTRACE_EVENT_STOP> "
9945 "and I<WSTOPSIG(status)> returns the stop signal. If any other ptrace-stop "
9946 "is generated at the same time (for example, if a signal is sent to the "
9947 "tracee), this ptrace-stop happens. If none of the above applies (for "
9948 "example, if the tracee is running in user space), it stops with "
9949 "B<PTRACE_EVENT_STOP> with I<WSTOPSIG(status)> == B<SIGTRAP>. "
9950 "B<PTRACE_INTERRUPT> only works on tracees attached by B<PTRACE_SEIZE>."
9954 #: build/C/man2/ptrace.2:747
9956 msgid "B<PTRACE_ATTACH>"
9957 msgstr "B<PTRACE_ATTACH>"
9959 #. No longer true (removed by Denys Vlasenko, 2011, who remarks:
9960 #. "I think it isn't true in non-ancient 2.4 and in 2.6/3.x.
9961 #. Basically, it's not true for any Linux in practical use.
9962 #. ; the behavior of the tracee is as if it had done a
9963 #. .BR PTRACE_TRACEME .
9964 #. The calling process actually becomes the parent of the tracee
9965 #. process for most purposes (e.g., it will receive
9966 #. notification of tracee events and appears in
9968 #. output as the tracee's parent), but a
9970 #. by the tracee will still return the PID of the original parent.
9972 #: build/C/man2/ptrace.2:775
9974 "Attach to the process specified in I<pid>, making it a tracee of the calling "
9975 "process. The tracee is sent a B<SIGSTOP>, but will not necessarily have "
9976 "stopped by the completion of this call; use B<waitpid>(2) to wait for the "
9977 "tracee to stop. See the \"Attaching and detaching\" subsection for "
9978 "additional information. (I<addr> and I<data> are ignored.)"
9982 #: build/C/man2/ptrace.2:775
9984 msgid "B<PTRACE_SEIZE> (since Linux 3.4)"
9985 msgstr " B<PTRACE_SEIZE> (since Linux 3.4)"
9988 #: build/C/man2/ptrace.2:795
9990 "Attach to the process specified in I<pid>, making it a tracee of the calling "
9991 "process. Unlike B<PTRACE_ATTACH>, B<PTRACE_SEIZE> does not stop the "
9992 "process. Only a B<PTRACE_SEIZE>d process can accept B<PTRACE_INTERRUPT> and "
9993 "B<PTRACE_LISTEN> commands. I<addr> must be zero. I<data> contains a bit "
9994 "mask of ptrace options to activate immediately."
9998 #: build/C/man2/ptrace.2:795
10000 msgid "B<PTRACE_DETACH>"
10001 msgstr "B<PTRACE_DETACH>"
10003 #. type: Plain text
10004 #: build/C/man2/ptrace.2:804
10006 "Restart the stopped tracee as for B<PTRACE_CONT>, but first detach from it. "
10007 "Under Linux, a tracee can be detached in this way regardless of which method "
10008 "was used to initiate tracing. (I<addr> is ignored.)"
10010 "B<PTRACE_CONT> と同様に停止した tracee を再開するが、 まずそのプロセスからの"
10011 "分離 (detach) を行う。 Linux では、トレースされている tracee はどのような方法"
10012 "でトレースを開始されたとしても、この方法で分離 (detach) することができる。 "
10013 "(I<addr> は無視される。)"
10016 #: build/C/man2/ptrace.2:804
10018 msgid "Death under ptrace"
10021 #. type: Plain text
10022 #: build/C/man2/ptrace.2:813
10024 "When a (possibly multithreaded) process receives a killing signal (one whose "
10025 "disposition is set to B<SIG_DFL> and whose default action is to kill the "
10026 "process), all threads exit. Tracees report their death to their tracer(s). "
10027 "Notification of this event is delivered via B<waitpid>(2)."
10030 #. type: Plain text
10031 #: build/C/man2/ptrace.2:822
10033 "Note that the killing signal will first cause signal-delivery-stop (on one "
10034 "tracee only), and only after it is injected by the tracer (or after it was "
10035 "dispatched to a thread which isn't traced), will death from the signal "
10036 "happen on I<all> tracees within a multithreaded process. (The term \"signal-"
10037 "delivery-stop\" is explained below.)"
10040 #. type: Plain text
10041 #: build/C/man2/ptrace.2:834
10043 "B<SIGKILL> does not generate signal-delivery-stop and therefore the tracer "
10044 "can't suppress it. B<SIGKILL> kills even within system calls (syscall-exit-"
10045 "stop is not generated prior to death by B<SIGKILL>). The net effect is that "
10046 "B<SIGKILL> always kills the process (all its threads), even if some threads "
10047 "of the process are ptraced."
10050 #. type: Plain text
10051 #: build/C/man2/ptrace.2:839
10053 "When the tracee calls B<_exit>(2), it reports its death to its tracer. "
10054 "Other threads are not affected."
10057 #. type: Plain text
10058 #: build/C/man2/ptrace.2:843
10060 "When any thread executes B<exit_group>(2), every tracee in its thread group "
10061 "reports its death to its tracer."
10064 #. type: Plain text
10065 #: build/C/man2/ptrace.2:857
10067 "If the B<PTRACE_O_TRACEEXIT> option is on, B<PTRACE_EVENT_EXIT> will happen "
10068 "before actual death. This applies to exits via B<exit>(2), "
10069 "B<exit_group>(2), and signal deaths (except B<SIGKILL>), and when threads "
10070 "are torn down on B<execve>(2) in a multithreaded process."
10073 #. type: Plain text
10074 #: build/C/man2/ptrace.2:882
10076 "The tracer cannot assume that the ptrace-stopped tracee exists. There are "
10077 "many scenarios when the tracee may die while stopped (such as B<SIGKILL>). "
10078 "Therefore, the tracer must be prepared to handle an B<ESRCH> error on any "
10079 "ptrace operation. Unfortunately, the same error is returned if the tracee "
10080 "exists but is not ptrace-stopped (for commands which require a stopped "
10081 "tracee), or if it is not traced by the process which issued the ptrace "
10082 "call. The tracer needs to keep track of the stopped/running state of the "
10083 "tracee, and interpret B<ESRCH> as \"tracee died unexpectedly\" only if it "
10084 "knows that the tracee has been observed to enter ptrace-stop. Note that "
10085 "there is no guarantee that I<waitpid(WNOHANG)> will reliably report the "
10086 "tracee's death status if a ptrace operation returned B<ESRCH>. "
10087 "I<waitpid(WNOHANG)> may return 0 instead. In other words, the tracee may be "
10088 "\"not yet fully dead\", but already refusing ptrace requests."
10091 #. type: Plain text
10092 #: build/C/man2/ptrace.2:896
10094 "The tracer can't assume that the tracee I<always> ends its life by reporting "
10095 "I<WIFEXITED(status)> or I<WIFSIGNALED(status)>; there are cases where this "
10096 "does not occur. For example, if a thread other than thread group leader "
10097 "does an B<execve>(2), it disappears; its PID will never be seen again, and "
10098 "any subsequent ptrace stops will be reported under the thread group leader's "
10103 #: build/C/man2/ptrace.2:896
10105 msgid "Stopped states"
10108 #. type: Plain text
10109 #: build/C/man2/ptrace.2:918
10111 "A tracee can be in two states: running or stopped. For the purposes of "
10112 "ptrace, a tracee which is blocked in a system call (such as B<read>(2), "
10113 "B<pause>(2), etc.) is nevertheless considered to be running, even if the "
10114 "tracee is blocked for a long time. The state of the tracee after "
10115 "B<PTRACE_LISTEN> is somewhat of a gray area: it is not in any ptrace-stop "
10116 "(ptrace commands won't work on it, and it will deliver B<waitpid>(2) "
10117 "notifications), but it also may be considered \"stopped\" because it is not "
10118 "executing instructions (is not scheduled), and if it was in group-stop "
10119 "before B<PTRACE_LISTEN>, it will not respond to signals until B<SIGCONT> is "
10123 #. type: Plain text
10124 #: build/C/man2/ptrace.2:922
10126 "There are many kinds of states when the tracee is stopped, and in ptrace "
10127 "discussions they are often conflated. Therefore, it is important to use "
10131 #. type: Plain text
10132 #: build/C/man2/ptrace.2:933
10134 "In this manual page, any stopped state in which the tracee is ready to "
10135 "accept ptrace commands from the tracer is called I<ptrace-stop>. Ptrace-"
10136 "stops can be further subdivided into I<signal-delivery-stop>, I<group-stop>, "
10137 "I<syscall-stop>, and so on. These stopped states are described in detail "
10141 #. type: Plain text
10142 #: build/C/man2/ptrace.2:938
10144 "When the running tracee enters ptrace-stop, it notifies its tracer using "
10145 "B<waitpid>(2) (or one of the other \"wait\" system calls). Most of this "
10146 "manual page assumes that the tracer waits with:"
10149 #. type: Plain text
10150 #: build/C/man2/ptrace.2:940
10152 msgid " pid = waitpid(pid_or_minus_1, &status, __WALL);\n"
10156 #. Do we require __WALL usage, or will just using 0 be ok? (With 0,
10157 #. I am not 100% sure there aren't ugly corner cases.) Are the
10158 #. rules different if user wants to use waitid? Will waitid require
10160 #. type: Plain text
10161 #: build/C/man2/ptrace.2:952
10163 "Ptrace-stopped tracees are reported as returns with I<pid> greater than 0 "
10164 "and I<WIFSTOPPED(status)> true."
10167 #. type: Plain text
10168 #: build/C/man2/ptrace.2:960
10170 "The B<__WALL> flag does not include the B<WSTOPPED> and B<WEXITED> flags, "
10171 "but implies their functionality."
10174 #. type: Plain text
10175 #: build/C/man2/ptrace.2:967
10177 "Setting the B<WCONTINUED> flag when calling B<waitpid>(2) is not "
10178 "recommended: the \"continued\" state is per-process and consuming it can "
10179 "confuse the real parent of the tracee."
10182 #. type: Plain text
10183 #: build/C/man2/ptrace.2:975
10185 "Use of the B<WNOHANG> flag may cause B<waitpid>(2) to return 0 (\"no wait "
10186 "results available yet\") even if the tracer knows there should be a "
10187 "notification. Example:"
10190 #. type: Plain text
10191 #: build/C/man2/ptrace.2:984
10195 " ptrace(PTRACE_CONT, pid, 0L, 0L);\n"
10196 " if (errno == ESRCH) {\n"
10197 " /* tracee is dead */\n"
10198 " r = waitpid(tracee, &status, __WALL | WNOHANG);\n"
10199 " /* r can still be 0 here! */\n"
10203 #. type: Plain text
10204 #: build/C/man2/ptrace.2:1007
10206 "The following kinds of ptrace-stops exist: signal-delivery-stops, group-"
10207 "stops, B<PTRACE_EVENT> stops, syscall-stops. They all are reported by "
10208 "B<waitpid>(2) with I<WIFSTOPPED(status)> true. They may be differentiated "
10209 "by examining the value I<statusE<gt>E<gt>8>, and if there is ambiguity in "
10210 "that value, by querying B<PTRACE_GETSIGINFO>. (Note: the "
10211 "I<WSTOPSIG(status)> macro can't be used to perform this examination, because "
10212 "it returns the value I<(statusE<gt>E<gt>8)\\ &\\ 0xff>.)"
10216 #: build/C/man2/ptrace.2:1007
10218 msgid "Signal-delivery-stop"
10221 #. type: Plain text
10222 #: build/C/man2/ptrace.2:1027
10224 "When a (possibly multithreaded) process receives any signal except "
10225 "B<SIGKILL>, the kernel selects an arbitrary thread which handles the "
10226 "signal. (If the signal is generated with B<tgkill>(2), the target thread "
10227 "can be explicitly selected by the caller.) If the selected thread is "
10228 "traced, it enters signal-delivery-stop. At this point, the signal is not "
10229 "yet delivered to the process, and can be suppressed by the tracer. If the "
10230 "tracer doesn't suppress the signal, it passes the signal to the tracee in "
10231 "the next ptrace restart request. This second step of signal delivery is "
10232 "called I<signal injection> in this manual page. Note that if the signal is "
10233 "blocked, signal-delivery-stop doesn't happen until the signal is unblocked, "
10234 "with the usual exception that B<SIGSTOP> can't be blocked."
10237 #. type: Plain text
10238 #: build/C/man2/ptrace.2:1041
10240 "Signal-delivery-stop is observed by the tracer as B<waitpid>(2) returning "
10241 "with I<WIFSTOPPED(status)> true, with the signal returned by "
10242 "I<WSTOPSIG(status)>. If the signal is B<SIGTRAP>, this may be a different "
10243 "kind of ptrace-stop; see the \"Syscall-stops\" and \"execve\" sections below "
10244 "for details. If I<WSTOPSIG(status)> returns a stopping signal, this may be "
10245 "a group-stop; see below."
10249 #: build/C/man2/ptrace.2:1041
10251 msgid "Signal injection and suppression"
10254 #. type: Plain text
10255 #: build/C/man2/ptrace.2:1044
10257 "After signal-delivery-stop is observed by the tracer, the tracer should "
10258 "restart the tracee with the call"
10261 #. type: Plain text
10262 #: build/C/man2/ptrace.2:1046
10264 msgid " ptrace(PTRACE_restart, pid, 0, sig)\n"
10267 #. type: Plain text
10268 #: build/C/man2/ptrace.2:1059
10270 "where B<PTRACE_restart> is one of the restarting ptrace requests. If I<sig> "
10271 "is 0, then a signal is not delivered. Otherwise, the signal I<sig> is "
10272 "delivered. This operation is called I<signal injection> in this manual "
10273 "page, to distinguish it from signal-delivery-stop."
10276 #. type: Plain text
10277 #: build/C/man2/ptrace.2:1065
10279 "The I<sig> value may be different from the I<WSTOPSIG(status)> value: the "
10280 "tracer can cause a different signal to be injected."
10283 #. type: Plain text
10284 #: build/C/man2/ptrace.2:1081
10286 "Note that a suppressed signal still causes system calls to return "
10287 "prematurely. In this case, system calls will be restarted: the tracer will "
10288 "observe the tracee to reexecute the interrupted system call (or "
10289 "B<restart_syscall>(2) system call for a few system calls which use a "
10290 "different mechanism for restarting) if the tracer uses B<PTRACE_SYSCALL>. "
10291 "Even system calls (such as B<poll>(2)) which are not restartable after "
10292 "signal are restarted after signal is suppressed; however, kernel bugs exist "
10293 "which cause some system calls to fail with B<EINTR> even though no "
10294 "observable signal is injected to the tracee."
10297 #. type: Plain text
10298 #: build/C/man2/ptrace.2:1092
10300 "Restarting ptrace commands issued in ptrace-stops other than signal-delivery-"
10301 "stop are not guaranteed to inject a signal, even if I<sig> is nonzero. No "
10302 "error is reported; a nonzero I<sig> may simply be ignored. Ptrace users "
10303 "should not try to \"create a new signal\" this way: use B<tgkill>(2) "
10307 #. type: Plain text
10308 #: build/C/man2/ptrace.2:1099
10310 "The fact that signal injection requests may be ignored when restarting the "
10311 "tracee after ptrace stops that are not signal-delivery-stops is a cause of "
10312 "confusion among ptrace users. One typical scenario is that the tracer "
10313 "observes group-stop, mistakes it for signal-delivery-stop, restarts the "
10317 #. type: Plain text
10318 #: build/C/man2/ptrace.2:1101
10320 msgid " ptrace(PTRACE_restart, pid, 0, stopsig)\n"
10323 #. type: Plain text
10324 #: build/C/man2/ptrace.2:1107
10326 "with the intention of injecting I<stopsig>, but I<stopsig> gets ignored and "
10327 "the tracee continues to run."
10330 #. type: Plain text
10331 #: build/C/man2/ptrace.2:1127
10333 "The B<SIGCONT> signal has a side effect of waking up (all threads of) a "
10334 "group-stopped process. This side effect happens before signal-delivery-"
10335 "stop. The tracer can't suppress this side effect (it can only suppress "
10336 "signal injection, which only causes the B<SIGCONT> handler to not be "
10337 "executed in the tracee, if such a handler is installed). In fact, waking up "
10338 "from group-stop may be followed by signal-delivery-stop for signal(s) "
10339 "I<other than> B<SIGCONT>, if they were pending when B<SIGCONT> was "
10340 "delivered. In other words, B<SIGCONT> may be not the first signal observed "
10341 "by the tracee after it was sent."
10344 #. type: Plain text
10345 #: build/C/man2/ptrace.2:1131
10347 "Stopping signals cause (all threads of) a process to enter group-stop. This "
10348 "side effect happens after signal injection, and therefore can be suppressed "
10353 #. In the Linux 2.4 sources, in arch/i386/kernel/signal.c::do_signal(),
10355 #. /* The debugger continued. Ignore SIGSTOP. */
10356 #. if (signr == SIGSTOP)
10358 #. type: Plain text
10359 #: build/C/man2/ptrace.2:1141
10360 msgid "In Linux 2.4 and earlier, the B<SIGSTOP> signal can't be injected."
10363 #. type: Plain text
10364 #: build/C/man2/ptrace.2:1158
10366 "B<PTRACE_GETSIGINFO> can be used to retrieve a I<siginfo_t> structure which "
10367 "corresponds to the delivered signal. B<PTRACE_SETSIGINFO> may be used to "
10368 "modify it. If B<PTRACE_SETSIGINFO> has been used to alter I<siginfo_t>, the "
10369 "I<si_signo> field and the I<sig> parameter in the restarting command must "
10370 "match, otherwise the result is undefined."
10374 #: build/C/man2/ptrace.2:1158
10379 #. type: Plain text
10380 #: build/C/man2/ptrace.2:1170
10382 "When a (possibly multithreaded) process receives a stopping signal, all "
10383 "threads stop. If some threads are traced, they enter a group-stop. Note "
10384 "that the stopping signal will first cause signal-delivery-stop (on one "
10385 "tracee only), and only after it is injected by the tracer (or after it was "
10386 "dispatched to a thread which isn't traced), will group-stop be initiated on "
10387 "I<all> tracees within the multithreaded process. As usual, every tracee "
10388 "reports its group-stop separately to the corresponding tracer."
10391 #. type: Plain text
10392 #: build/C/man2/ptrace.2:1179
10394 "Group-stop is observed by the tracer as B<waitpid>(2) returning with "
10395 "I<WIFSTOPPED(status)> true, with the stopping signal available via "
10396 "I<WSTOPSIG(status)>. The same result is returned by some other classes of "
10397 "ptrace-stops, therefore the recommended practice is to perform the call"
10400 #. type: Plain text
10401 #: build/C/man2/ptrace.2:1181
10403 msgid " ptrace(PTRACE_GETSIGINFO, pid, 0, &siginfo)\n"
10406 #. type: Plain text
10407 #: build/C/man2/ptrace.2:1202
10409 "The call can be avoided if the signal is not B<SIGSTOP>, B<SIGTSTP>, "
10410 "B<SIGTTIN>, or B<SIGTTOU>; only these four signals are stopping signals. If "
10411 "the tracer sees something else, it can't be a group-stop. Otherwise, the "
10412 "tracer needs to call B<PTRACE_GETSIGINFO>. If B<PTRACE_GETSIGINFO> fails "
10413 "with B<EINVAL>, then it is definitely a group-stop. (Other failure codes "
10414 "are possible, such as B<ESRCH> (\"no such process\") if a B<SIGKILL> killed "
10418 #. type: Plain text
10419 #: build/C/man2/ptrace.2:1212
10421 "If tracee was attached using B<PTRACE_SEIZE>, group-stop is indicated by "
10422 "B<PTRACE_EVENT_STOP>: I<statusE<gt>E<gt>16 == PTRACE_EVENT_STOP>. This "
10423 "allows detection of group-stops without requiring an extra "
10424 "B<PTRACE_GETSIGINFO> call."
10427 #. type: Plain text
10428 #: build/C/man2/ptrace.2:1221
10430 "As of Linux 2.6.38, after the tracer sees the tracee ptrace-stop and until "
10431 "it restarts or kills it, the tracee will not run, and will not send "
10432 "notifications (except B<SIGKILL> death) to the tracer, even if the tracer "
10433 "enters into another B<waitpid>(2) call."
10436 #. type: Plain text
10437 #: build/C/man2/ptrace.2:1235
10439 "The kernel behavior described in the previous paragraph causes a problem "
10440 "with transparent handling of stopping signals. If the tracer restarts the "
10441 "tracee after group-stop, the stopping signal is effectively ignored\\(emthe "
10442 "tracee doesn't remain stopped, it runs. If the tracer doesn't restart the "
10443 "tracee before entering into the next B<waitpid>(2), future B<SIGCONT> "
10444 "signals will not be reported to the tracer; this would cause the B<SIGCONT> "
10445 "signals to have no effect on the tracee."
10448 #. type: Plain text
10449 #: build/C/man2/ptrace.2:1246
10451 "Since Linux 3.4, there is a method to overcome this problem: instead of "
10452 "B<PTRACE_CONT>, a B<PTRACE_LISTEN> command can be used to restart a tracee "
10453 "in a way where it does not execute, but waits for a new event which it can "
10454 "report via B<waitpid>(2) (such as when it is restarted by a B<SIGCONT>)."
10458 #: build/C/man2/ptrace.2:1246
10460 msgid "PTRACE_EVENT stops"
10463 #. type: Plain text
10464 #: build/C/man2/ptrace.2:1252
10466 "If the tracer sets B<PTRACE_O_TRACE_*> options, the tracee will enter ptrace-"
10467 "stops called B<PTRACE_EVENT> stops."
10470 #. type: Plain text
10471 #: build/C/man2/ptrace.2:1266
10473 "B<PTRACE_EVENT> stops are observed by the tracer as B<waitpid>(2) returning "
10474 "with I<WIFSTOPPED(status)>, and I<WSTOPSIG(status)> returns B<SIGTRAP>. An "
10475 "additional bit is set in the higher byte of the status word: the value "
10476 "I<statusE<gt>E<gt>8> will be"
10479 #. type: Plain text
10480 #: build/C/man2/ptrace.2:1268
10482 msgid " (SIGTRAP | PTRACE_EVENT_foo E<lt>E<lt> 8).\n"
10485 #. type: Plain text
10486 #: build/C/man2/ptrace.2:1270
10487 msgid "The following events exist:"
10491 #: build/C/man2/ptrace.2:1270
10493 msgid "B<PTRACE_EVENT_VFORK>"
10494 msgstr "B<PTRACE_EVENT_VFORK>"
10496 #. type: Plain text
10497 #: build/C/man2/ptrace.2:1283
10499 "Stop before return from B<vfork>(2) or B<clone>(2) with the B<CLONE_VFORK> "
10500 "flag. When the tracee is continued after this stop, it will wait for child "
10501 "to exit/exec before continuing its execution (in other words, the usual "
10502 "behavior on B<vfork>(2))."
10506 #: build/C/man2/ptrace.2:1283
10508 msgid "B<PTRACE_EVENT_FORK>"
10509 msgstr "B<PTRACE_EVENT_FORK>"
10511 #. type: Plain text
10512 #: build/C/man2/ptrace.2:1291
10514 "Stop before return from B<fork>(2) or B<clone>(2) with the exit signal set "
10519 #: build/C/man2/ptrace.2:1291
10521 msgid "B<PTRACE_EVENT_CLONE>"
10522 msgstr "B<PTRACE_EVENT_CLONE>"
10524 #. type: Plain text
10525 #: build/C/man2/ptrace.2:1295
10526 msgid "Stop before return from B<clone>(2)."
10530 #: build/C/man2/ptrace.2:1295
10532 msgid "B<PTRACE_EVENT_VFORK_DONE>"
10533 msgstr "B<PTRACE_EVENT_VFORK_DONE>"
10535 #. type: Plain text
10536 #: build/C/man2/ptrace.2:1305
10538 "Stop before return from B<vfork>(2) or B<clone>(2) with the B<CLONE_VFORK> "
10539 "flag, but after the child unblocked this tracee by exiting or execing."
10542 #. type: Plain text
10543 #: build/C/man2/ptrace.2:1311
10545 "For all four stops described above, the stop occurs in the parent (i.e., the "
10546 "tracee), not in the newly created thread. B<PTRACE_GETEVENTMSG> can be used "
10547 "to retrieve the new thread's ID."
10551 #: build/C/man2/ptrace.2:1311
10553 msgid "B<PTRACE_EVENT_EXEC>"
10554 msgstr "B<PTRACE_EVENT_EXEC>"
10556 #. type: Plain text
10557 #: build/C/man2/ptrace.2:1318
10559 "Stop before return from B<execve>(2). Since Linux 3.0, "
10560 "B<PTRACE_GETEVENTMSG> returns the former thread ID."
10564 #: build/C/man2/ptrace.2:1318
10566 msgid "B<PTRACE_EVENT_EXIT>"
10567 msgstr "B<PTRACE_EVENT_EXIT>"
10569 #. type: Plain text
10570 #: build/C/man2/ptrace.2:1334
10572 "Stop before exit (including death from B<exit_group>(2)), signal death, or "
10573 "exit caused by B<execve>(2) in a multithreaded process. "
10574 "B<PTRACE_GETEVENTMSG> returns the exit status. Registers can be examined "
10575 "(unlike when \"real\" exit happens). The tracee is still alive; it needs to "
10576 "be B<PTRACE_CONT>ed or B<PTRACE_DETACH>ed to finish exiting."
10580 #: build/C/man2/ptrace.2:1334
10582 msgid "B<PTRACE_EVENT_STOP>"
10583 msgstr "B<PTRACE_EVENT_STOP>"
10585 #. type: Plain text
10586 #: build/C/man2/ptrace.2:1346
10588 "Stop induced by B<PTRACE_INTERRUPT> command, or group-stop, or initial "
10589 "ptrace-stop when a new child is attached (only if attached using "
10590 "B<PTRACE_SEIZE>), or B<PTRACE_EVENT_STOP> if B<PTRACE_SEIZE> was used."
10594 #: build/C/man2/ptrace.2:1346
10596 msgid "B<PTRACE_EVENT_SECCOMP>"
10597 msgstr "B<PTRACE_EVENT_SECCOMP>"
10599 #. type: Plain text
10600 #: build/C/man2/ptrace.2:1357
10602 "Stop triggered by a B<seccomp>(2) rule on tracee syscall entry when "
10603 "B<PTRACE_O_TRACESECCOMP> has been set by the tracer. The seccomp event "
10604 "message data (from the B<SECCOMP_RET_DATA> portion of the seccomp filter "
10605 "rule) can be retrieved with B<PTRACE_GETEVENTMSG>."
10608 #. type: Plain text
10609 #: build/C/man2/ptrace.2:1369
10611 "B<PTRACE_GETSIGINFO> on B<PTRACE_EVENT> stops returns B<SIGTRAP> in "
10612 "I<si_signo>, with I<si_code> set to I<(eventE<lt>E<lt>8)\\ |\\ SIGTRAP>."
10616 #: build/C/man2/ptrace.2:1369
10618 msgid "Syscall-stops"
10621 #. type: Plain text
10622 #: build/C/man2/ptrace.2:1382
10624 "If the tracee was restarted by B<PTRACE_SYSCALL>, the tracee enters syscall-"
10625 "enter-stop just prior to entering any system call. If the tracer restarts "
10626 "the tracee with B<PTRACE_SYSCALL>, the tracee enters syscall-exit-stop when "
10627 "the system call is finished, or if it is interrupted by a signal. (That is, "
10628 "signal-delivery-stop never happens between syscall-enter-stop and syscall-"
10629 "exit-stop; it happens I<after> syscall-exit-stop.)"
10632 #. type: Plain text
10633 #: build/C/man2/ptrace.2:1396
10635 "Other possibilities are that the tracee may stop in a B<PTRACE_EVENT> stop, "
10636 "exit (if it entered B<_exit>(2) or B<exit_group>(2)), be killed by "
10637 "B<SIGKILL>, or die silently (if it is a thread group leader, the "
10638 "B<execve>(2) happened in another thread, and that thread is not traced by "
10639 "the same tracer; this situation is discussed later)."
10642 #. type: Plain text
10643 #: build/C/man2/ptrace.2:1411
10645 "Syscall-enter-stop and syscall-exit-stop are observed by the tracer as "
10646 "B<waitpid>(2) returning with I<WIFSTOPPED(status)> true, and "
10647 "I<WSTOPSIG(status)> giving B<SIGTRAP>. If the B<PTRACE_O_TRACESYSGOOD> "
10648 "option was set by the tracer, then I<WSTOPSIG(status)> will give the value "
10649 "I<(SIGTRAP\\ |\\ 0x80)>."
10652 #. type: Plain text
10653 #: build/C/man2/ptrace.2:1417
10655 "Syscall-stops can be distinguished from signal-delivery-stop with B<SIGTRAP> "
10656 "by querying B<PTRACE_GETSIGINFO> for the following cases:"
10660 #: build/C/man2/ptrace.2:1417
10662 msgid "I<si_code> E<lt>= 0"
10665 #. type: Plain text
10666 #: build/C/man2/ptrace.2:1429
10668 "B<SIGTRAP> was delivered as a result of a user-space action, for example, a "
10669 "system call (B<tgkill>(2), B<kill>(2), B<sigqueue>(3), etc.), expiration of "
10670 "a POSIX timer, change of state on a POSIX message queue, or completion of an "
10671 "asynchronous I/O request."
10675 #: build/C/man2/ptrace.2:1429
10677 msgid "I<si_code> == SI_KERNEL (0x80)"
10680 #. type: Plain text
10681 #: build/C/man2/ptrace.2:1433
10682 msgid "B<SIGTRAP> was sent by the kernel."
10686 #: build/C/man2/ptrace.2:1433
10688 msgid "I<si_code> == SIGTRAP or I<si_code> == (SIGTRAP|0x80)"
10691 #. type: Plain text
10692 #: build/C/man2/ptrace.2:1436
10693 msgid "This is a syscall-stop."
10696 #. type: Plain text
10697 #: build/C/man2/ptrace.2:1441
10699 "However, syscall-stops happen very often (twice per system call), and "
10700 "performing B<PTRACE_GETSIGINFO> for every syscall-stop may be somewhat "
10704 #. type: Plain text
10705 #: build/C/man2/ptrace.2:1464
10707 "Some architectures allow the cases to be distinguished by examining "
10708 "registers. For example, on x86, I<rax> == -B<ENOSYS> in syscall-enter-"
10709 "stop. Since B<SIGTRAP> (like any other signal) always happens I<after> "
10710 "syscall-exit-stop, and at this point I<rax> almost never contains -"
10711 "B<ENOSYS>, the B<SIGTRAP> looks like \"syscall-stop which is not syscall-"
10712 "enter-stop\"; in other words, it looks like a \"stray syscall-exit-stop\" "
10713 "and can be detected this way. But such detection is fragile and is best "
10717 #. type: Plain text
10718 #: build/C/man2/ptrace.2:1470
10720 "Using the B<PTRACE_O_TRACESYSGOOD> option is the recommended method to "
10721 "distinguish syscall-stops from other kinds of ptrace-stops, since it is "
10722 "reliable and does not incur a performance penalty."
10725 #. type: Plain text
10726 #: build/C/man2/ptrace.2:1481
10728 "Syscall-enter-stop and syscall-exit-stop are indistinguishable from each "
10729 "other by the tracer. The tracer needs to keep track of the sequence of "
10730 "ptrace-stops in order to not misinterpret syscall-enter-stop as syscall-exit-"
10731 "stop or vice versa. The rule is that syscall-enter-stop is always followed "
10732 "by syscall-exit-stop, B<PTRACE_EVENT> stop or the tracee's death; no other "
10733 "kinds of ptrace-stop can occur in between."
10736 #. type: Plain text
10737 #: build/C/man2/ptrace.2:1486
10739 "If after syscall-enter-stop, the tracer uses a restarting command other than "
10740 "B<PTRACE_SYSCALL>, syscall-exit-stop is not generated."
10743 #. type: Plain text
10744 #: build/C/man2/ptrace.2:1498
10746 "B<PTRACE_GETSIGINFO> on syscall-stops returns B<SIGTRAP> in I<si_signo>, "
10747 "with I<si_code> set to B<SIGTRAP> or I<(SIGTRAP|0x80)>."
10751 #: build/C/man2/ptrace.2:1498
10753 msgid "PTRACE_SINGLESTEP, PTRACE_SYSEMU, PTRACE_SYSEMU_SINGLESTEP stops"
10758 #. document stops occurring with PTRACE_SINGLESTEP, PTRACE_SYSEMU,
10759 #. PTRACE_SYSEMU_SINGLESTEP
10760 #. type: Plain text
10761 #: build/C/man2/ptrace.2:1504
10762 msgid "[Details of these kinds of stops are yet to be documented.]"
10766 #: build/C/man2/ptrace.2:1504
10768 msgid "Informational and restarting ptrace commands"
10771 #. type: Plain text
10772 #: build/C/man2/ptrace.2:1514
10774 "Most ptrace commands (all except B<PTRACE_ATTACH>, B<PTRACE_SEIZE>, "
10775 "B<PTRACE_TRACEME>, B<PTRACE_INTERRUPT>, and B<PTRACE_KILL>) require the "
10776 "tracee to be in a ptrace-stop, otherwise they fail with B<ESRCH>."
10779 #. type: Plain text
10780 #: build/C/man2/ptrace.2:1519
10782 "When the tracee is in ptrace-stop, the tracer can read and write data to the "
10783 "tracee using informational commands. These commands leave the tracee in "
10784 "ptrace-stopped state:"
10787 #. type: Plain text
10788 #: build/C/man2/ptrace.2:1531
10791 " ptrace(PTRACE_PEEKTEXT/PEEKDATA/PEEKUSER, pid, addr, 0);\n"
10792 " ptrace(PTRACE_POKETEXT/POKEDATA/POKEUSER, pid, addr, long_val);\n"
10793 " ptrace(PTRACE_GETREGS/GETFPREGS, pid, 0, &struct);\n"
10794 " ptrace(PTRACE_SETREGS/SETFPREGS, pid, 0, &struct);\n"
10795 " ptrace(PTRACE_GETREGSET, pid, NT_foo, &iov);\n"
10796 " ptrace(PTRACE_SETREGSET, pid, NT_foo, &iov);\n"
10797 " ptrace(PTRACE_GETSIGINFO, pid, 0, &siginfo);\n"
10798 " ptrace(PTRACE_SETSIGINFO, pid, 0, &siginfo);\n"
10799 " ptrace(PTRACE_GETEVENTMSG, pid, 0, &long_var);\n"
10800 " ptrace(PTRACE_SETOPTIONS, pid, 0, PTRACE_O_flags);\n"
10803 #. type: Plain text
10804 #: build/C/man2/ptrace.2:1543
10806 "Note that some errors are not reported. For example, setting signal "
10807 "information (I<siginfo>) may have no effect in some ptrace-stops, yet the "
10808 "call may succeed (return 0 and not set I<errno>); querying "
10809 "B<PTRACE_GETEVENTMSG> may succeed and return some random value if current "
10810 "ptrace-stop is not documented as returning a meaningful event message."
10813 #. type: Plain text
10814 #: build/C/man2/ptrace.2:1545
10818 #. type: Plain text
10819 #: build/C/man2/ptrace.2:1547
10821 msgid " ptrace(PTRACE_SETOPTIONS, pid, 0, PTRACE_O_flags);\n"
10824 #. type: Plain text
10825 #: build/C/man2/ptrace.2:1556
10827 "affects one tracee. The tracee's current flags are replaced. Flags are "
10828 "inherited by new tracees created and \"auto-attached\" via active "
10829 "B<PTRACE_O_TRACEFORK>, B<PTRACE_O_TRACEVFORK>, or B<PTRACE_O_TRACECLONE> "
10833 #. type: Plain text
10834 #: build/C/man2/ptrace.2:1559
10836 "Another group of commands makes the ptrace-stopped tracee run. They have "
10840 #. type: Plain text
10841 #: build/C/man2/ptrace.2:1561
10843 msgid " ptrace(cmd, pid, 0, sig);\n"
10846 #. type: Plain text
10847 #: build/C/man2/ptrace.2:1582
10849 "where I<cmd> is B<PTRACE_CONT>, B<PTRACE_LISTEN>, B<PTRACE_DETACH>, "
10850 "B<PTRACE_SYSCALL>, B<PTRACE_SINGLESTEP>, B<PTRACE_SYSEMU>, or "
10851 "B<PTRACE_SYSEMU_SINGLESTEP>. If the tracee is in signal-delivery-stop, "
10852 "I<sig> is the signal to be injected (if it is nonzero). Otherwise, I<sig> "
10853 "may be ignored. (When restarting a tracee from a ptrace-stop other than "
10854 "signal-delivery-stop, recommended practice is to always pass 0 in I<sig>.)"
10858 #: build/C/man2/ptrace.2:1582
10860 msgid "Attaching and detaching"
10863 #. type: Plain text
10864 #: build/C/man2/ptrace.2:1584
10865 msgid "A thread can be attached to the tracer using the call"
10868 #. type: Plain text
10869 #: build/C/man2/ptrace.2:1586
10871 msgid " ptrace(PTRACE_ATTACH, pid, 0, 0);\n"
10874 #. type: Plain text
10875 #: build/C/man2/ptrace.2:1588 build/C/man2/ptrace.2:2090
10879 #. type: Plain text
10880 #: build/C/man2/ptrace.2:1590
10882 msgid " ptrace(PTRACE_SEIZE, pid, 0, PTRACE_O_flags);\n"
10886 #. FIXME . Describe how to attach to a thread which is already group-stopped.
10887 #. type: Plain text
10888 #: build/C/man2/ptrace.2:1614
10890 "B<PTRACE_ATTACH> sends B<SIGSTOP> to this thread. If the tracer wants this "
10891 "B<SIGSTOP> to have no effect, it needs to suppress it. Note that if other "
10892 "signals are concurrently sent to this thread during attach, the tracer may "
10893 "see the tracee enter signal-delivery-stop with other signal(s) first! The "
10894 "usual practice is to reinject these signals until B<SIGSTOP> is seen, then "
10895 "suppress B<SIGSTOP> injection. The design bug here is that a ptrace attach "
10896 "and a concurrently delivered B<SIGSTOP> may race and the concurrent "
10897 "B<SIGSTOP> may be lost."
10900 #. type: Plain text
10901 #: build/C/man2/ptrace.2:1621
10903 "Since attaching sends B<SIGSTOP> and the tracer usually suppresses it, this "
10904 "may cause a stray B<EINTR> return from the currently executing system call "
10905 "in the tracee, as described in the \"Signal injection and suppression\" "
10909 #. type: Plain text
10910 #: build/C/man2/ptrace.2:1633
10912 "Since Linux 3.4, B<PTRACE_SEIZE> can be used instead of B<PTRACE_ATTACH>. "
10913 "B<PTRACE_SEIZE> does not stop the attached process. If you need to stop it "
10914 "after attach (or at any other time) without sending it any signals, use "
10915 "B<PTRACE_INTERRUPT> command."
10918 #. type: Plain text
10919 #: build/C/man2/ptrace.2:1635
10920 msgid "The request"
10923 #. type: Plain text
10924 #: build/C/man2/ptrace.2:1637
10926 msgid " ptrace(PTRACE_TRACEME, 0, 0, 0);\n"
10929 #. type: Plain text
10930 #: build/C/man2/ptrace.2:1643
10932 "turns the calling thread into a tracee. The thread continues to run "
10933 "(doesn't enter ptrace-stop). A common practice is to follow the "
10934 "B<PTRACE_TRACEME> with"
10937 #. type: Plain text
10938 #: build/C/man2/ptrace.2:1645
10940 msgid " raise(SIGSTOP);\n"
10943 #. type: Plain text
10944 #: build/C/man2/ptrace.2:1648
10946 "and allow the parent (which is our tracer now) to observe our signal-"
10950 #. type: Plain text
10951 #: build/C/man2/ptrace.2:1672
10953 "If the B<PTRACE_O_TRACEFORK>, B<PTRACE_O_TRACEVFORK>, or "
10954 "B<PTRACE_O_TRACECLONE> options are in effect, then children created by, "
10955 "respectively, B<vfork>(2) or B<clone>(2) with the B<CLONE_VFORK> flag, "
10956 "B<fork>(2) or B<clone>(2) with the exit signal set to B<SIGCHLD>, and "
10957 "other kinds of B<clone>(2), are automatically attached to the same tracer "
10958 "which traced their parent. B<SIGSTOP> is delivered to the children, causing "
10959 "them to enter signal-delivery-stop after they exit the system call which "
10963 #. type: Plain text
10964 #: build/C/man2/ptrace.2:1674
10965 msgid "Detaching of the tracee is performed by:"
10968 #. type: Plain text
10969 #: build/C/man2/ptrace.2:1676
10971 msgid " ptrace(PTRACE_DETACH, pid, 0, sig);\n"
10974 #. type: Plain text
10975 #: build/C/man2/ptrace.2:1684
10977 "B<PTRACE_DETACH> is a restarting operation; therefore it requires the tracee "
10978 "to be in ptrace-stop. If the tracee is in signal-delivery-stop, a signal "
10979 "can be injected. Otherwise, the I<sig> parameter may be silently ignored."
10982 #. FIXME . Describe how to detach from a group-stopped tracee so that it
10983 #. doesn't run, but continues to wait for SIGCONT.
10984 #. type: Plain text
10985 #: build/C/man2/ptrace.2:1708
10987 "If the tracee is running when the tracer wants to detach it, the usual "
10988 "solution is to send B<SIGSTOP> (using B<tgkill>(2), to make sure it goes to "
10989 "the correct thread), wait for the tracee to stop in signal-delivery-stop for "
10990 "B<SIGSTOP> and then detach it (suppressing B<SIGSTOP> injection). A design "
10991 "bug is that this can race with concurrent B<SIGSTOP>s. Another complication "
10992 "is that the tracee may enter other ptrace-stops and needs to be restarted "
10993 "and waited for again, until B<SIGSTOP> is seen. Yet another complication is "
10994 "to be sure that the tracee is not already ptrace-stopped, because no signal "
10995 "delivery happens while it is\\(emnot even B<SIGSTOP>."
10998 #. type: Plain text
10999 #: build/C/man2/ptrace.2:1716
11001 "If the tracer dies, all tracees are automatically detached and restarted, "
11002 "unless they were in group-stop. Handling of restart from group-stop is "
11003 "currently buggy, but the \"as planned\" behavior is to leave tracee stopped "
11004 "and waiting for B<SIGCONT>. If the tracee is restarted from signal-delivery-"
11005 "stop, the pending signal is injected."
11009 #: build/C/man2/ptrace.2:1716
11011 msgid "execve(2) under ptrace"
11015 #. clone(2) CLONE_THREAD says:
11016 #. If any of the threads in a thread group performs an execve(2),
11017 #. then all threads other than the thread group leader are terminated,
11018 #. and the new program is executed in the thread group leader.
11019 #. In kernel 3.1 sources, see fs/exec.c::de_thread()
11020 #. type: Plain text
11021 #: build/C/man2/ptrace.2:1735
11023 "When one thread in a multithreaded process calls B<execve>(2), the kernel "
11024 "destroys all other threads in the process, and resets the thread ID of the "
11025 "execing thread to the thread group ID (process ID). (Or, to put things "
11026 "another way, when a multithreaded process does an B<execve>(2), at "
11027 "completion of the call, it appears as though the B<execve>(2) occurred in "
11028 "the thread group leader, regardless of which thread did the B<execve>(2).) "
11029 "This resetting of the thread ID looks very confusing to tracers:"
11032 #. type: Plain text
11033 #: build/C/man2/ptrace.2:1745
11035 "All other threads stop in B<PTRACE_EVENT_EXIT> stop, if the "
11036 "B<PTRACE_O_TRACEEXIT> option was turned on. Then all other threads except "
11037 "the thread group leader report death as if they exited via B<_exit>(2) with "
11041 #. type: Plain text
11042 #: build/C/man2/ptrace.2:1753
11044 "The execing tracee changes its thread ID while it is in the B<execve>(2). "
11045 "(Remember, under ptrace, the \"pid\" returned from B<waitpid>(2), or fed "
11046 "into ptrace calls, is the tracee's thread ID.) That is, the tracee's thread "
11047 "ID is reset to be the same as its process ID, which is the same as the "
11048 "thread group leader's thread ID."
11051 #. type: Plain text
11052 #: build/C/man2/ptrace.2:1759
11054 "Then a B<PTRACE_EVENT_EXEC> stop happens, if the B<PTRACE_O_TRACEEXEC> "
11055 "option was turned on."
11058 #. type: Plain text
11059 #: build/C/man2/ptrace.2:1780
11061 "If the thread group leader has reported its B<PTRACE_EVENT_EXIT> stop by "
11062 "this time, it appears to the tracer that the dead thread leader \"reappears "
11063 "from nowhere\". (Note: the thread group leader does not report death via "
11064 "I<WIFEXITED(status)> until there is at least one other live thread. This "
11065 "eliminates the possibility that the tracer will see it dying and then "
11066 "reappearing.) If the thread group leader was still alive, for the tracer "
11067 "this may look as if thread group leader returns from a different system call "
11068 "than it entered, or even \"returned from a system call even though it was "
11069 "not in any system call\". If the thread group leader was not traced (or was "
11070 "traced by a different tracer), then during B<execve>(2) it will appear as "
11071 "if it has become a tracee of the tracer of the execing tracee."
11074 #. type: Plain text
11075 #: build/C/man2/ptrace.2:1783
11077 "All of the above effects are the artifacts of the thread ID change in the "
11081 #. type: Plain text
11082 #: build/C/man2/ptrace.2:1803
11084 "The B<PTRACE_O_TRACEEXEC> option is the recommended tool for dealing with "
11085 "this situation. First, it enables B<PTRACE_EVENT_EXEC> stop, which occurs "
11086 "before B<execve>(2) returns. In this stop, the tracer can use "
11087 "B<PTRACE_GETEVENTMSG> to retrieve the tracee's former thread ID. (This "
11088 "feature was introduced in Linux 3.0). Second, the B<PTRACE_O_TRACEEXEC> "
11089 "option disables legacy B<SIGTRAP> generation on B<execve>(2)."
11092 #. type: Plain text
11093 #: build/C/man2/ptrace.2:1809
11095 "When the tracer receives B<PTRACE_EVENT_EXEC> stop notification, it is "
11096 "guaranteed that except this tracee and the thread group leader, no other "
11097 "threads from the process are alive."
11100 #. type: Plain text
11101 #: build/C/man2/ptrace.2:1817
11103 "On receiving the B<PTRACE_EVENT_EXEC> stop notification, the tracer should "
11104 "clean up all its internal data structures describing the threads of this "
11105 "process, and retain only one data structure\\(emone which describes the "
11106 "single still running tracee, with"
11109 #. type: Plain text
11110 #: build/C/man2/ptrace.2:1819
11112 msgid " thread ID == thread group ID == process ID.\n"
11115 #. type: Plain text
11116 #: build/C/man2/ptrace.2:1823
11117 msgid "Example: two threads call B<execve>(2) at the same time:"
11120 #. type: Plain text
11121 #: build/C/man2/ptrace.2:1834
11124 "*** we get syscall-enter-stop in thread 1: **\n"
11125 "PID1 execve(\"/bin/foo\", \"foo\" E<lt>unfinished ...E<gt>\n"
11126 "*** we issue PTRACE_SYSCALL for thread 1 **\n"
11127 "*** we get syscall-enter-stop in thread 2: **\n"
11128 "PID2 execve(\"/bin/bar\", \"bar\" E<lt>unfinished ...E<gt>\n"
11129 "*** we issue PTRACE_SYSCALL for thread 2 **\n"
11130 "*** we get PTRACE_EVENT_EXEC for PID0, we issue PTRACE_SYSCALL **\n"
11131 "*** we get syscall-exit-stop for PID0: **\n"
11132 "PID0 E<lt>... execve resumedE<gt> ) = 0\n"
11135 #. type: Plain text
11136 #: build/C/man2/ptrace.2:1857
11138 "If the B<PTRACE_O_TRACEEXEC> option is I<not> in effect for the execing "
11139 "tracee, the kernel delivers an extra B<SIGTRAP> to the tracee after "
11140 "B<execve>(2) returns. This is an ordinary signal (similar to one which can "
11141 "be generated by I<kill -TRAP>), not a special kind of ptrace-stop. "
11142 "Employing B<PTRACE_GETSIGINFO> for this signal returns I<si_code> set to 0 "
11143 "(I<SI_USER>). This signal may be blocked by signal mask, and thus may be "
11144 "delivered (much) later."
11147 #. type: Plain text
11148 #: build/C/man2/ptrace.2:1876
11150 "Usually, the tracer (for example, B<strace>(1)) would not want to show this "
11151 "extra post-execve B<SIGTRAP> signal to the user, and would suppress its "
11152 "delivery to the tracee (if B<SIGTRAP> is set to B<SIG_DFL>, it is a killing "
11153 "signal). However, determining I<which> B<SIGTRAP> to suppress is not easy. "
11154 "Setting the B<PTRACE_O_TRACEEXEC> option and thus suppressing this extra "
11155 "B<SIGTRAP> is the recommended approach."
11159 #: build/C/man2/ptrace.2:1876
11161 msgid "Real parent"
11164 #. type: Plain text
11165 #: build/C/man2/ptrace.2:1883
11167 "The ptrace API (ab)uses the standard UNIX parent/child signaling over "
11168 "B<waitpid>(2). This used to cause the real parent of the process to stop "
11169 "receiving several kinds of B<waitpid>(2) notifications when the child "
11170 "process is traced by some other process."
11173 #. type: Plain text
11174 #: build/C/man2/ptrace.2:1886
11176 "Many of these bugs have been fixed, but as of Linux 2.6.38 several still "
11177 "exist; see BUGS below."
11180 #. type: Plain text
11181 #: build/C/man2/ptrace.2:1888
11182 msgid "As of Linux 2.6.38, the following is believed to work correctly:"
11185 #. type: Plain text
11186 #: build/C/man2/ptrace.2:1896
11188 "exit/death by signal is reported first to the tracer, then, when the tracer "
11189 "consumes the B<waitpid>(2) result, to the real parent (to the real parent "
11190 "only when the whole multithreaded process exits). If the tracer and the "
11191 "real parent are the same process, the report is sent only once."
11194 #. type: Plain text
11195 #: build/C/man2/ptrace.2:1901
11197 "On success, the B<PTRACE_PEEK*> requests return the requested data (but see "
11198 "NOTES), while other requests return zero."
11200 "成功すると B<PTRACE_PEEK*> の場合は要求したデータを返し (「注意」を参照)、 そ"
11203 #. type: Plain text
11204 #: build/C/man2/ptrace.2:1911
11206 "On error, all requests return -1, and I<errno> is set appropriately. Since "
11207 "the value returned by a successful B<PTRACE_PEEK*> request may be -1, the "
11208 "caller must clear I<errno> before the call, and then check it afterward to "
11209 "determine whether or not an error occurred."
11211 "エラーの場合は -1 を返し、 I<errno> が適切に設定される。 B<PTRACE_PEEK*> が成"
11212 "功して返す値も-1 になることがあるため、 呼び出し元は呼び出しを行う前に "
11213 "I<errno> をクリアして、 あとで I<errno> を調べ、エラーか発生したのかどうかを"
11216 #. type: Plain text
11217 #: build/C/man2/ptrace.2:1915
11219 "(i386 only) There was an error with allocating or freeing a debug register."
11220 msgstr "(i386 のみ) デバッグレジスターの確保または解放でエラーが発生した。"
11222 #. type: Plain text
11223 #: build/C/man2/ptrace.2:1926
11225 "There was an attempt to read from or write to an invalid area in the "
11226 "tracer's or the tracee's memory, probably because the area wasn't mapped or "
11227 "accessible. Unfortunately, under Linux, different variations of this fault "
11228 "will return B<EIO> or B<EFAULT> more or less arbitrarily."
11230 "tracer または tracee のメモリーの不正な領域に読み書きしようとした。 おそらく"
11231 "その領域がマッピングされていないか、 その領域へのアクセスが許されていないかで"
11232 "ある。 不運なことに、Linux ではこのようなエラーの場合、多かれ少なかれ 恣意的"
11233 "に B<EIO> を返したり B<EFAULT> を返したりすることがある。"
11235 #. type: Plain text
11236 #: build/C/man2/ptrace.2:1929
11237 msgid "An attempt was made to set an invalid option."
11238 msgstr "不正なオプションを設定しようとした。"
11240 #. type: Plain text
11241 #: build/C/man2/ptrace.2:1936
11243 "I<request> is invalid, or an attempt was made to read from or write to an "
11244 "invalid area in the tracer's or the tracee's memory, or there was a word-"
11245 "alignment violation, or an invalid signal was specified during a restart "
11248 "I<request> が不正である。 または、tracer または tracee のメモリーの 不正な領"
11249 "域に読み書きしようとした。 または、ワード境界違反があった。 または、実行再開"
11250 "の要求で不正なシグナルを指定した。"
11252 #. type: Plain text
11253 #: build/C/man2/ptrace.2:1949
11255 "The specified process cannot be traced. This could be because the tracer "
11256 "has insufficient privileges (the required capability is B<CAP_SYS_PTRACE>); "
11257 "unprivileged processes cannot trace processes that they cannot send signals "
11258 "to or those running set-user-ID/set-group-ID programs, for obvious reasons. "
11259 "Alternatively, the process may already be being traced, or (on kernels "
11260 "before 2.6.26) be B<init>(1) (PID 1)."
11262 "指定したプロセスをトレースすることができない。これは tracer が 必要な権限 (必"
11263 "要なケーパビリティは B<CAP_SYS_PTRACE>) を持っていないことが原因の場合があ"
11264 "る。 分かりやすい理由を挙げるなら、 非特権プロセスはシグナルを送ることができ"
11265 "ないプロセスをトレースできないし、 set-user-ID/set-group-ID プログラムを実行"
11266 "しているプロセスはトレースできない。 または、プロセスはすでにトレース中であ"
11267 "る、 または (カーネル 2.6.26 より前では) B<init>(1) プロセス (PID が 1) であ"
11270 #. type: Plain text
11271 #: build/C/man2/ptrace.2:1954
11273 "The specified process does not exist, or is not currently being traced by "
11274 "the caller, or is not stopped (for requests that require a stopped tracee)."
11276 "指定したプロセスが存在しない。 または、指定したプロセスは呼び出したプロセスが"
11277 "トレース中のプロセスではない。 または、指定したプロセスが停止していない "
11278 "(tracee が停止していることが必要な要求の場合)。"
11280 #. type: Plain text
11281 #: build/C/man2/ptrace.2:1956
11282 msgid "SVr4, 4.3BSD."
11283 msgstr "SVr4, 4.3BSD."
11285 #. type: Plain text
11286 #: build/C/man2/ptrace.2:1971
11288 "Although arguments to B<ptrace>() are interpreted according to the "
11289 "prototype given, glibc currently declares B<ptrace>() as a variadic "
11290 "function with only the I<request> argument fixed. It is recommended to "
11291 "always supply four arguments, even if the requested operation does not use "
11292 "them, setting unused/ignored arguments to I<0L> or I<(void\\ *)\\ 0>."
11294 "B<ptrace>() の引き数は上のようなプロトタイプに基づいて解釈されるが、 glibc "
11295 "では、現在のところ B<ptrace>() は I<request> 引き数だけが固定の可変長引き数"
11296 "関数として宣言されている。 要求する操作が引き数を使用しない場合であっても、 "
11297 "未使用や無視される引き数には I<0L> や I<(void\\ *)\\ 0> を設定して、 4 つの引"
11298 "き数を常に省略せずに指定することを推奨する。"
11300 #. See commit 00cd5c37afd5f431ac186dd131705048c0a11fdb
11301 #. type: Plain text
11302 #: build/C/man2/ptrace.2:1976
11304 "In Linux kernels before 2.6.26, B<init>(1), the process with PID 1, may not "
11307 "バージョン 2.6.26 より前の Linux カーネルでは、 B<init>(1) すなわち PID が 1 "
11308 "のプロセスはトレースすることができない。"
11310 #. See http://lkml.org/lkml/2008/5/8/375
11311 #. type: Plain text
11312 #: build/C/man2/ptrace.2:1983
11314 "The layout of the contents of memory and the USER area are quite operating-"
11315 "system- and architecture-specific. The offset supplied, and the data "
11316 "returned, might not entirely match with the definition of I<struct user>."
11318 "メモリーや USER 領域の内容や配置はオペレーティングシステムごと、アーキテク"
11319 "チャーごとに 非常に依存する。 オフセットが指定された場合、返されるデータは "
11320 "I<struct user> の定義と完全に一致しないこともありえる。"
11322 #. type: Plain text
11323 #: build/C/man2/ptrace.2:1986
11325 "The size of a \"word\" is determined by the operating-system variant (e.g., "
11326 "for 32-bit Linux it is 32 bits)."
11328 "「ワード (word) 」の大きさはオペレーティングシステムによって決まる。 (例え"
11329 "ば、32 ビットの Linux では 32 ビットである、など。)"
11331 #. type: Plain text
11332 #: build/C/man2/ptrace.2:1994
11334 "This page documents the way the B<ptrace>() call works currently in Linux. "
11335 "Its behavior differs significantly on other flavors of UNIX. In any case, "
11336 "use of B<ptrace>() is highly specific to the operating system and "
11339 "このマニュアルは現在の Linux における B<ptrace>() コールの動作について記述し"
11340 "ている。他の UNIX では その動作は著しく異なる。 いかなる場合も B<ptrace>() "
11341 "を使うとオペレーションシステムやアーキテクチャーに非常に依存したものになる。"
11344 #: build/C/man2/ptrace.2:1994
11346 msgid "C library/kernel ABI differences"
11347 msgstr "C ライブラリとカーネル ABI の違い"
11349 #. type: Plain text
11350 #: build/C/man2/ptrace.2:2006
11352 "At the system call level, the B<PTRACE_PEEKTEXT>, B<PTRACE_PEEKDATA>, and "
11353 "B<PTRACE_PEEKUSER> requests have a different API: they store the result at "
11354 "the address specified by the I<data> parameter, and the return value is the "
11355 "error flag. The glibc wrapper function provides the API given in "
11356 "DESCRIPTION above, with the result being returned via the function return "
11360 #. type: Plain text
11361 #: build/C/man2/ptrace.2:2017
11363 "On hosts with 2.6 kernel headers, B<PTRACE_SETOPTIONS> is declared with a "
11364 "different value than the one for 2.4. This leads to applications compiled "
11365 "with 2.6 kernel headers failing when run on 2.4 kernels. This can be worked "
11366 "around by redefining B<PTRACE_SETOPTIONS> to B<PTRACE_OLDSETOPTIONS>, if "
11369 "カーネル 2.6 のヘッダーがインストールされたホストでは、 B<PTRACE_SETOPTIONS> "
11370 "はカーネル 2.4 のヘッダーとは異なる値で宣言される。 このため、カーネル 2.6 の"
11371 "ヘッダーでコンパイルされたアプリケーションは カーネル 2.4 では正しく動作しな"
11372 "い。 この問題は、 B<PTRACE_SETOPTIONS> が定義されていた際は、 "
11373 "B<PTRACE_SETOPTIONS> を B<PTRACE_OLDSETOPTIONS> に定義し直すことで対処でき"
11376 #. type: Plain text
11377 #: build/C/man2/ptrace.2:2020
11379 "Group-stop notifications are sent to the tracer, but not to real parent. "
11380 "Last confirmed on 2.6.38.6."
11383 #. Note from Denys Vlasenko:
11384 #. Here "exits" means any kind of death - _exit, exit_group,
11385 #. signal death. Signal death and exit_group cases are trivial,
11386 #. though: since signal death and exit_group kill all other threads
11387 #. too, "until all other threads exit" thing happens rather soon
11388 #. in these cases. Therefore, only _exit presents observably
11389 #. puzzling behavior to ptrace users: thread leader _exit's,
11390 #. but WIFEXITED isn't reported! We are trying to explain here
11392 #. FIXME . need to test/verify this scenario
11393 #. type: Plain text
11394 #: build/C/man2/ptrace.2:2051
11396 "If a thread group leader is traced and exits by calling B<_exit>(2), a "
11397 "B<PTRACE_EVENT_EXIT> stop will happen for it (if requested), but the "
11398 "subsequent B<WIFEXITED> notification will not be delivered until all other "
11399 "threads exit. As explained above, if one of other threads calls "
11400 "B<execve>(2), the death of the thread group leader will I<never> be "
11401 "reported. If the execed thread is not traced by this tracer, the tracer "
11402 "will never know that B<execve>(2) happened. One possible workaround is to "
11403 "B<PTRACE_DETACH> the thread group leader instead of restarting it in this "
11404 "case. Last confirmed on 2.6.38.6."
11407 #. type: Plain text
11408 #: build/C/man2/ptrace.2:2061
11410 "A B<SIGKILL> signal may still cause a B<PTRACE_EVENT_EXIT> stop before "
11411 "actual signal death. This may be changed in the future; B<SIGKILL> is meant "
11412 "to always immediately kill tasks even under ptrace. Last confirmed on "
11416 #. type: Plain text
11417 #: build/C/man2/ptrace.2:2079
11419 "Some system calls return with B<EINTR> if a signal was sent to a tracee, but "
11420 "delivery was suppressed by the tracer. (This is very typical operation: it "
11421 "is usually done by debuggers on every attach, in order to not introduce a "
11422 "bogus B<SIGSTOP>). As of Linux 3.2.9, the following system calls are "
11423 "affected (this list is likely incomplete): B<epoll_wait>(2), and B<read>(2) "
11424 "from an B<inotify>(7) file descriptor. The usual symptom of this bug is "
11425 "that when you attach to a quiescent process with the command"
11428 #. type: Plain text
11429 #: build/C/man2/ptrace.2:2081
11431 msgid " strace -p E<lt>process-IDE<gt>\n"
11434 #. type: Plain text
11435 #: build/C/man2/ptrace.2:2084
11436 msgid "then, instead of the usual and expected one-line output such as"
11439 #. type: Plain text
11440 #: build/C/man2/ptrace.2:2087
11442 msgid " restart_syscall(E<lt>... resuming interrupted call ...E<gt>_\n"
11445 #. type: Plain text
11446 #: build/C/man2/ptrace.2:2093
11448 msgid " select(6, [5], NULL, [5], NULL_\n"
11451 #. type: Plain text
11452 #: build/C/man2/ptrace.2:2097
11454 "('_' denotes the cursor position), you observe more than one line. For "
11458 #. type: Plain text
11459 #: build/C/man2/ptrace.2:2101
11462 " clock_gettime(CLOCK_MONOTONIC, {15370, 690928118}) = 0\n"
11463 " epoll_wait(4,_\n"
11466 #. type: Plain text
11467 #: build/C/man2/ptrace.2:2122
11469 "What is not visible here is that the process was blocked in "
11470 "B<epoll_wait>(2) before B<strace>(1) has attached to it. Attaching caused "
11471 "B<epoll_wait>(2) to return to user space with the error B<EINTR>. In this "
11472 "particular case, the program reacted to B<EINTR> by checking the current "
11473 "time, and then executing B<epoll_wait>(2) again. (Programs which do not "
11474 "expect such \"stray\" B<EINTR> errors may behave in an unintended way upon "
11475 "an B<strace>(1) attach.)"
11478 #. type: Plain text
11479 #: build/C/man2/ptrace.2:2137
11481 "B<gdb>(1), B<strace>(1), B<clone>(2), B<execve>(2), B<fork>(2), "
11482 "B<gettid>(2), B<seccomp>(2), B<sigaction>(2), B<tgkill>(2), B<vfork>(2), "
11483 "B<waitpid>(2), B<exec>(3), B<capabilities>(7), B<signal>(7)"
11485 "B<gdb>(1), B<strace>(1), B<clone>(2), B<execve>(2), B<fork>(2), "
11486 "B<gettid>(2), B<seccomp>(2), B<sigaction>(2), B<tgkill>(2), B<vfork>(2), "
11487 "B<waitpid>(2), B<exec>(3), B<capabilities>(7), B<signal>(7)"
11490 #: build/C/man2/quotactl.2:27
11496 #: build/C/man2/quotactl.2:27
11499 msgstr "2010-06-16"
11501 #. type: Plain text
11502 #: build/C/man2/quotactl.2:30
11503 msgid "quotactl - manipulate disk quotas"
11504 msgstr "quotactl - ディスク quota を操作する"
11506 #. type: Plain text
11507 #: build/C/man2/quotactl.2:34
11510 "B<#include E<lt>sys/quota.hE<gt>>\n"
11511 "B<#include E<lt>xfs/xqm.hE<gt>>\n"
11513 "B<#include E<lt>sys/quota.hE<gt>>\n"
11514 "B<#include E<lt>xfs/xqm.hE<gt>>\n"
11516 #. type: Plain text
11517 #: build/C/man2/quotactl.2:37
11519 msgid "B<int quotactl(int >I<cmd>B<, const char *>I<special>B<, int >I<id>B<, caddr_t >I<addr>B<);>\n"
11520 msgstr "B<int quotactl(int >I<cmd>B<, const char *>I<special>B<, int >I<id>B<, caddr_t >I<addr>B<);>\n"
11522 #. type: Plain text
11523 #: build/C/man2/quotactl.2:49
11525 "The quota system can be used to set per-user and per-group limits on the "
11526 "amount of disk space used on a filesystem. For each user and/or group, a "
11527 "soft limit and a hard limit can be set for each filesystem. The hard limit "
11528 "can't be exceeded. The soft limit can be exceeded, but warnings will "
11529 "ensue. Moreover, the user can't exceed the soft limit for more than one "
11530 "week (by default) at a time; after this time, the soft limit counts as a "
11534 #. type: Plain text
11535 #: build/C/man2/quotactl.2:74
11537 "The B<quotactl>() call manipulates disk quotas. The I<cmd> argument "
11538 "indicates a command to be applied to the user or group ID specified in "
11539 "I<id>. To initialize the I<cmd> argument, use the I<QCMD(subcmd, type)> "
11540 "macro. The I<type> value is either B<USRQUOTA>, for user quotas, or "
11541 "B<GRPQUOTA>, for group quotas. The I<subcmd> value is described below."
11544 #. type: Plain text
11545 #: build/C/man2/quotactl.2:79
11547 "The I<special> argument is a pointer to a null-terminated string containing "
11548 "the pathname of the (mounted) block special device for the filesystem being "
11552 #. type: Plain text
11553 #: build/C/man2/quotactl.2:87
11555 "The I<addr> argument is the address of an optional, command-specific, data "
11556 "structure that is copied in or out of the system. The interpretation of "
11557 "I<addr> is given with each command below."
11560 #. type: Plain text
11561 #: build/C/man2/quotactl.2:91
11562 msgid "The I<subcmd> value is one of the following:"
11563 msgstr "I<subcmd> の値は以下のいずれかである"
11566 #: build/C/man2/quotactl.2:91
11568 msgid "B<Q_QUOTAON>"
11569 msgstr "B<Q_QUOTAON>"
11571 #. type: Plain text
11572 #: build/C/man2/quotactl.2:98
11574 "Turn on quotas for a filesystem. The I<id> argument is the identification "
11575 "number of the quota format to be used. Currently, there are three supported "
11580 #: build/C/man2/quotactl.2:99
11582 msgid "B<QFMT_VFS_OLD>"
11585 #. type: Plain text
11586 #: build/C/man2/quotactl.2:102
11587 msgid "The original quota format."
11591 #: build/C/man2/quotactl.2:102
11593 msgid "B<QFMT_VFS_V0>"
11596 #. type: Plain text
11597 #: build/C/man2/quotactl.2:106
11599 "The standard VFS v0 quota format, which can handle 32-bit UIDs and GIDs and "
11600 "quota limits up to 2^42 bytes and 2^32 inodes."
11604 #: build/C/man2/quotactl.2:106
11606 msgid "B<QFMT_VFS_V1>"
11609 #. type: Plain text
11610 #: build/C/man2/quotactl.2:110
11612 "A quota format that can handle 32-bit UIDs and GIDs and quota limits of 2^64 "
11613 "bytes and 2^64 inodes."
11616 #. type: Plain text
11617 #: build/C/man2/quotactl.2:121
11619 "The I<addr> argument points to the pathname of a file containing the quotas "
11620 "for the filesystem. The quota file must exist; it is normally created with "
11621 "the B<quotacheck>(8) program. This operation requires privilege "
11622 "(B<CAP_SYS_ADMIN>)."
11626 #: build/C/man2/quotactl.2:121
11628 msgid "B<Q_QUOTAOFF>"
11629 msgstr "B<Q_QUOTAOFF>"
11631 #. type: Plain text
11632 #: build/C/man2/quotactl.2:131
11634 "Turn off quotas for a filesystem. The I<addr> and I<id> arguments are "
11635 "ignored. This operation requires privilege (B<CAP_SYS_ADMIN>)."
11639 #: build/C/man2/quotactl.2:131
11641 msgid "B<Q_GETQUOTA>"
11642 msgstr "B<Q_GETQUOTA>"
11644 #. type: Plain text
11645 #: build/C/man2/quotactl.2:142
11647 "Get disk quota limits and current usage for user or group I<id>. The "
11648 "I<addr> argument is a pointer to a I<dqblk> structure defined in I<E<lt>sys/"
11649 "quota.hE<gt>> as follows:"
11652 #. type: Plain text
11653 #: build/C/man2/quotactl.2:147 build/C/man2/quotactl.2:234
11656 "/* uint64_t is an unsigned 64-bit integer;\n"
11657 " uint32_t is an unsigned 32-bit integer */\n"
11660 #. type: Plain text
11661 #: build/C/man2/quotactl.2:167
11664 "struct dqblk { /* Definition since Linux 2.4.22 */\n"
11665 " uint64_t dqb_bhardlimit; /* absolute limit on disk\n"
11666 " quota blocks alloc */\n"
11667 " uint64_t dqb_bsoftlimit; /* preferred limit on\n"
11668 " disk quota blocks */\n"
11669 " uint64_t dqb_curspace; /* current quota block\n"
11671 " uint64_t dqb_ihardlimit; /* maximum number of\n"
11672 " allocated inodes */\n"
11673 " uint64_t dqb_isoftlimit; /* preferred inode limit */\n"
11674 " uint64_t dqb_curinodes; /* current number of\n"
11675 " allocated inodes */\n"
11676 " uint64_t dqb_btime; /* time limit for excessive\n"
11678 " uint64_t dqb_itime; /* time limit for excessive\n"
11680 " uint32_t dqb_valid; /* bit mask of QIF_*\n"
11685 #. type: Plain text
11686 #: build/C/man2/quotactl.2:170
11689 "/* Flags in dqb_valid that indicate which fields in\n"
11690 " dqblk structure are valid. */\n"
11693 #. type: Plain text
11694 #: build/C/man2/quotactl.2:181
11697 "#define QIF_BLIMITS 1\n"
11698 "#define QIF_SPACE 2\n"
11699 "#define QIF_ILIMITS 4\n"
11700 "#define QIF_INODES 8\n"
11701 "#define QIF_BTIME 16\n"
11702 "#define QIF_ITIME 32\n"
11703 "#define QIF_LIMITS (QIF_BLIMITS | QIF_ILIMITS)\n"
11704 "#define QIF_USAGE (QIF_SPACE | QIF_INODES)\n"
11705 "#define QIF_TIMES (QIF_BTIME | QIF_ITIME)\n"
11706 "#define QIF_ALL (QIF_LIMITS | QIF_USAGE | QIF_TIMES)\n"
11709 #. type: Plain text
11710 #: build/C/man2/quotactl.2:198
11712 "The I<dqb_valid> field is a bit mask that is set to indicate the entries in "
11713 "the I<dqblk> structure that are valid. Currently, the kernel fills in all "
11714 "entries of the I<dqblk> structure and marks them as valid in the "
11715 "I<dqb_valid> field. Unprivileged users may retrieve only their own quotas; "
11716 "a privileged user (B<CAP_SYS_ADMIN>) can retrieve the quotas of any user."
11720 #: build/C/man2/quotactl.2:198
11722 msgid "B<Q_SETQUOTA>"
11723 msgstr "B<Q_SETQUOTA>"
11725 #. type: Plain text
11726 #: build/C/man2/quotactl.2:218
11728 "Set quota information for user or group I<id>, using the information "
11729 "supplied in the I<dqblk> structure pointed to by I<addr>. The I<dqb_valid> "
11730 "field of the I<dqblk> structure indicates which entries in the structure "
11731 "have been set by the caller. This operation supersedes the B<Q_SETQLIM> and "
11732 "B<Q_SETUSE> operations in the previous quota interfaces. This operation "
11733 "requires privilege (B<CAP_SYS_ADMIN>)."
11737 #: build/C/man2/quotactl.2:218
11739 msgid "B<Q_GETINFO>"
11740 msgstr "B<Q_GETINFO>"
11742 #. type: Plain text
11743 #: build/C/man2/quotactl.2:229
11745 "Get information (like grace times) about quotafile. The I<addr> argument "
11746 "should be a pointer to a I<dqinfo> structure. This structure is defined in "
11747 "I<E<lt>sys/quota.hE<gt>> as follows:"
11750 #. type: Plain text
11751 #: build/C/man2/quotactl.2:238
11754 "struct dqinfo { /* Defined since kernel 2.4.22 */\n"
11755 " uint64_t dqi_bgrace; /* Time before block soft limit\n"
11756 " becomes hard limit */\n"
11758 "struct dqinfo { /* Defined since kernel 2.4.22 */\n"
11759 " uint64_t dqi_bgrace; /* Time before block soft limit\n"
11760 " becomes hard limit */\n"
11762 #. type: Plain text
11763 #: build/C/man2/quotactl.2:245
11766 " uint64_t dqi_igrace; /* Time before inode soft limit\n"
11767 " becomes hard limit */\n"
11768 " uint32_t dqi_flags; /* Flags for quotafile\n"
11770 " uint32_t dqi_valid;\n"
11773 " uint64_t dqi_igrace; /* Time before inode soft limit\n"
11774 " becomes hard limit */\n"
11775 " uint32_t dqi_flags; /* Flags for quotafile\n"
11777 " uint32_t dqi_valid;\n"
11780 #. type: Plain text
11781 #: build/C/man2/quotactl.2:247
11783 msgid "/* Bits for dqi_flags */\n"
11784 msgstr "/* Bits for dqi_flags */\n"
11786 #. type: Plain text
11787 #: build/C/man2/quotactl.2:249
11789 msgid "/* Quota format QFMT_VFS_OLD */\n"
11790 msgstr "/* Quota format QFMT_VFS_OLD */\n"
11792 #. type: Plain text
11793 #: build/C/man2/quotactl.2:251
11795 msgid "#define V1_DQF_RSQUASH\t1 /* Root squash enabled */\n"
11796 msgstr "#define V1_DQF_RSQUASH\t1 /* Root squash enabled */\n"
11798 #. type: Plain text
11799 #: build/C/man2/quotactl.2:253
11801 msgid "/* Other quota formats have no dqi_flags bits defined */\n"
11802 msgstr "/* Other quota formats have no dqi_flags bits defined */\n"
11804 #. type: Plain text
11805 #: build/C/man2/quotactl.2:256
11808 "/* Flags in dqi_valid that indicate which fields in\n"
11809 " dqinfo structure are valid. */\n"
11811 "/* Flags in dqi_valid that indicate which fields in\n"
11812 " dqinfo structure are valid. */\n"
11814 #. type: Plain text
11815 #: build/C/man2/quotactl.2:261
11818 "# define IIF_BGRACE\t1\n"
11819 "# define IIF_IGRACE\t2\n"
11820 "# define IIF_FLAGS\t4\n"
11821 "# define IIF_ALL (IIF_BGRACE | IIF_IGRACE | IIF_FLAGS)\n"
11823 "# define IIF_BGRACE\t1\n"
11824 "# define IIF_IGRACE\t2\n"
11825 "# define IIF_FLAGS\t4\n"
11826 "# define IIF_ALL (IIF_BGRACE | IIF_IGRACE | IIF_FLAGS)\n"
11828 #. type: Plain text
11829 #: build/C/man2/quotactl.2:277
11831 "The I<dqi_valid> field in the I<dqinfo> structure indicates the entries in "
11832 "the structure that are valid. Currently, the kernel fills in all entries of "
11833 "the I<dqinfo> structure and marks them all as valid in the I<dqi_valid> "
11834 "field. The I<id> argument is ignored."
11838 #: build/C/man2/quotactl.2:277
11840 msgid "B<Q_SETINFO>"
11841 msgstr "B<Q_SETINFO>"
11843 #. type: Plain text
11844 #: build/C/man2/quotactl.2:301
11846 "Set information about quotafile. The I<addr> argument should be a pointer "
11847 "to a I<dqinfo> structure. The I<dqi_valid> field of the I<dqinfo> structure "
11848 "indicates the entries in the structure that have been set by the caller. "
11849 "This operation supersedes the B<Q_SETGRACE> and B<Q_SETFLAGS> operations in "
11850 "the previous quota interfaces. The I<id> argument is ignored. This "
11851 "operation requires privilege (B<CAP_SYS_ADMIN>)."
11855 #: build/C/man2/quotactl.2:301
11857 msgid "B<Q_GETFMT>"
11858 msgstr "B<Q_GETFMT>"
11860 #. type: Plain text
11861 #: build/C/man2/quotactl.2:308
11863 "Get quota format used on the specified filesystem. The I<addr> argument "
11864 "should be a pointer to a 4-byte buffer where the format number will be "
11869 #: build/C/man2/quotactl.2:308
11874 #. type: Plain text
11875 #: build/C/man2/quotactl.2:319
11877 "Update the on-disk copy of quota usages for a filesystem. If I<special> is "
11878 "NULL, then all filesystems with active quotas are sync'ed. The I<addr> and "
11879 "I<id> arguments are ignored."
11883 #: build/C/man2/quotactl.2:319
11885 msgid "B<Q_GETSTATS>"
11886 msgstr "B<Q_GETSTATS>"
11888 #. Q_GETSTATS was removed in kernel 2.4.22.
11889 #. type: Plain text
11890 #: build/C/man2/quotactl.2:339
11892 "Get statistics and other generic information about the quota subsystem. The "
11893 "I<addr> argument should be a pointer to a I<dqstats> structure in which data "
11894 "should be stored. This structure is defined in I<E<lt>sys/quota.hE<gt>>. "
11895 "The I<special> and I<id> arguments are ignored. This operation is obsolete "
11896 "and not supported by recent kernels. Files in I</proc/sys/fs/quota/> carry "
11897 "the information instead."
11900 #. type: Plain text
11901 #: build/C/man2/quotactl.2:342
11903 "For XFS filesystems making use of the XFS Quota Manager (XQM), the above "
11904 "commands are bypassed and the following commands are used:"
11908 #: build/C/man2/quotactl.2:342
11910 msgid "B<Q_XQUOTAON>"
11911 msgstr "B<Q_XQUOTAON>"
11913 #. type: Plain text
11914 #: build/C/man2/quotactl.2:363
11916 "Turn on quotas for an XFS filesystem. XFS provides the ability to turn on/"
11917 "off quota limit enforcement with quota accounting. Therefore, XFS expects "
11918 "I<addr> to be a pointer to an I<unsigned int> that contains either the flags "
11919 "B<XFS_QUOTA_UDQ_ACCT> and/or B<XFS_QUOTA_UDQ_ENFD> (for user quota), or "
11920 "B<XFS_QUOTA_GDQ_ACCT> and/or B<XFS_QUOTA_GDQ_ENFD> (for group quota), as "
11921 "defined in I<E<lt>xfs/xqm.hE<gt>>. This operation requires privilege "
11922 "(B<CAP_SYS_ADMIN>)."
11926 #: build/C/man2/quotactl.2:363
11928 msgid "B<Q_XQUOTAOFF>"
11929 msgstr "B<Q_XQUOTAOFF>"
11931 #. type: Plain text
11932 #: build/C/man2/quotactl.2:374
11934 "Turn off quotas for an XFS filesystem. As with B<Q_QUOTAON>, XFS "
11935 "filesystems expect a pointer to an I<unsigned int> that specifies whether "
11936 "quota accounting and/or limit enforcement need to be turned off. This "
11937 "operation requires privilege (B<CAP_SYS_ADMIN>)."
11941 #: build/C/man2/quotactl.2:374
11943 msgid "B<Q_XGETQUOTA>"
11944 msgstr "B<Q_XGETQUOTA>"
11946 #. type: Plain text
11947 #: build/C/man2/quotactl.2:388
11949 "Get disk quota limits and current usage for user I<id>. The I<addr> "
11950 "argument is a pointer to an I<fs_disk_quota> structure (defined in "
11951 "I<E<lt>xfs/xqm.hE<gt>>). Unprivileged users may retrieve only their own "
11952 "quotas; a privileged user (B<CAP_SYS_ADMIN>) may retrieve the quotas of any "
11957 #: build/C/man2/quotactl.2:388
11959 msgid "B<Q_XSETQLIM>"
11960 msgstr "B<Q_XSETQLIM>"
11962 #. type: Plain text
11963 #: build/C/man2/quotactl.2:400
11965 "Set disk quota limits for user I<id>. The I<addr> argument is a pointer to "
11966 "an I<fs_disk_quota> structure (defined in I<E<lt>xfs/xqm.hE<gt>>). This "
11967 "operation requires privilege (B<CAP_SYS_ADMIN>)."
11971 #: build/C/man2/quotactl.2:400
11973 msgid "B<Q_XGETQSTAT>"
11974 msgstr "B<Q_XGETQSTAT>"
11976 #. type: Plain text
11977 #: build/C/man2/quotactl.2:408
11979 "Returns an I<fs_quota_stat> structure containing XFS filesystem-specific "
11980 "quota information. This is useful for finding out how much space is used to "
11981 "store quota information, and also to get quotaon/off status of a given local "
11986 #: build/C/man2/quotactl.2:408
11988 msgid "B<Q_XQUOTARM>"
11989 msgstr "B<Q_XQUOTARM>"
11991 #. type: Plain text
11992 #: build/C/man2/quotactl.2:412
11994 "Free the disk space taken by disk quotas. Quotas must have already been "
11998 #. type: Plain text
11999 #: build/C/man2/quotactl.2:419
12001 "There is no command equivalent to B<Q_SYNC> for XFS since B<sync>(1) writes "
12002 "quota information to disk (in addition to the other filesystem metadata that "
12006 #. type: Plain text
12007 #: build/C/man2/quotactl.2:427
12009 "On success, B<quotactl>() returns 0; on error -1 is returned, and I<errno> "
12010 "is set to indicate the error."
12012 "成功すると、 B<quotactl>() は 0 を返す。\n"
12013 "エラーの場合、-1 を返し、 I<errno> をエラーを示す値に設定する。"
12015 #. type: Plain text
12016 #: build/C/man2/quotactl.2:434
12017 msgid "I<addr> or I<special> is invalid."
12020 #. type: Plain text
12021 #: build/C/man2/quotactl.2:440
12022 msgid "I<cmd> or I<type> is invalid."
12025 #. type: Plain text
12026 #: build/C/man2/quotactl.2:447
12027 msgid "The file specified by I<special> or I<addr> does not exist."
12030 #. type: Plain text
12031 #: build/C/man2/quotactl.2:452
12032 msgid "The kernel has not been compiled with the B<CONFIG_QUOTA> option."
12036 #: build/C/man2/quotactl.2:452
12039 msgstr "B<ENOTBLK>"
12041 #. type: Plain text
12042 #: build/C/man2/quotactl.2:456
12043 msgid "I<special> is not a block device."
12044 msgstr "I<special> がブロックデバイスではない。"
12046 #. type: Plain text
12047 #: build/C/man2/quotactl.2:461
12049 "The caller lacked the required privilege (B<CAP_SYS_ADMIN>) for the "
12050 "specified operation."
12053 #. type: Plain text
12054 #: build/C/man2/quotactl.2:465
12056 "No disk quota is found for the indicated user. Quotas have not been turned "
12057 "on for this filesystem."
12060 #. type: Plain text
12061 #: build/C/man2/quotactl.2:474
12062 msgid "If I<cmd> is B<Q_SETQUOTA>, B<quotactl>() may also set I<errno> to:"
12065 #. type: Plain text
12066 #: build/C/man2/quotactl.2:477
12067 msgid "Specified limits are out of range allowed by quota format."
12070 #. type: Plain text
12071 #: build/C/man2/quotactl.2:486
12072 msgid "If I<cmd> is B<Q_QUOTAON>, B<quotactl>() may also set I<errno> to:"
12075 #. type: Plain text
12076 #: build/C/man2/quotactl.2:495
12078 "The quota file pointed to by I<addr> exists, but is not a regular file; or, "
12079 "the quota file pointed to by I<addr> exists, but is not on the filesystem "
12080 "pointed to by I<special>."
12083 #. type: Plain text
12084 #: build/C/man2/quotactl.2:501
12086 "B<Q_QUOTAON> attempted, but another B<Q_QUOTAON> had already been performed."
12089 #. type: Plain text
12090 #: build/C/man2/quotactl.2:504
12091 msgid "The quota file is corrupted."
12092 msgstr "quota ファイルが壊れている。"
12094 #. type: Plain text
12095 #: build/C/man2/quotactl.2:507
12096 msgid "Specified quota format was not found."
12099 #. type: Plain text
12100 #: build/C/man2/quotactl.2:512
12101 msgid "B<quota>(1), B<getrlimit>(2), B<quotacheck>(8), B<quotaon>(8)"
12102 msgstr "B<quota>(1), B<getrlimit>(2), B<quotacheck>(8), B<quotaon>(8)"
12105 #: build/C/man2/sendfile.2:19
12111 #: build/C/man2/sendfile.2:19
12114 msgstr "2011-09-14"
12116 #. type: Plain text
12117 #: build/C/man2/sendfile.2:22
12118 msgid "sendfile - transfer data between file descriptors"
12119 msgstr "sendfile - ファイルディスクリプター間でデータを転送する"
12121 #. type: Plain text
12122 #: build/C/man2/sendfile.2:24
12123 msgid "B<#include E<lt>sys/sendfile.hE<gt>>"
12124 msgstr "B<#include E<lt>sys/sendfile.hE<gt>>"
12126 #. The below is too ugly. Comments about glibc versions belong
12127 #. in the notes, not in the header.
12128 #. .B #include <features.h>
12130 #. .B #if (__GLIBC__==2 && __GLIBC_MINOR__>=1) || __GLIBC__>2
12132 #. .B #include <sys/sendfile.h>
12136 #. .B #include <sys/types.h>
12138 #. .B /* No system prototype before glibc 2.1. */
12140 #. .BI "ssize_t sendfile(int" " out_fd" ", int" " in_fd" ", off_t *" #. offset ", size_t" " count" )
12143 #. type: Plain text
12144 #: build/C/man2/sendfile.2:47
12146 "B<ssize_t sendfile(int>I< out_fd>B<, int>I< in_fd>B<, off_t *>I<offset>B<, "
12147 "size_t>I< count>B<);>"
12149 "B<ssize_t sendfile(int>I< out_fd>B<, int>I< in_fd>B<, off_t *>I<offset>B<, "
12150 "size_t>I< count>B<);>"
12152 #. type: Plain text
12153 #: build/C/man2/sendfile.2:57
12155 "B<sendfile>() copies data between one file descriptor and another. Because "
12156 "this copying is done within the kernel, B<sendfile>() is more efficient "
12157 "than the combination of B<read>(2) and B<write>(2), which would require "
12158 "transferring data to and from user space."
12160 "B<sendfile>() は、あるファイルディスクリプターから別の ファイルディスクリプ"
12161 "ターへのデータのコピーを行う。 このコピーはカーネル内で行われるので、 "
12162 "B<sendfile>() は、 B<read>(2) と B<write>(2) を組み合わせるよりも効率がよ"
12163 "い。 B<read>(2) や B<write>(2) ではユーザー空間との間でデータの転送が必要と"
12166 #. type: Plain text
12167 #: build/C/man2/sendfile.2:62
12169 "I<in_fd> should be a file descriptor opened for reading and I<out_fd> should "
12170 "be a descriptor opened for writing."
12172 "I<in_fd> は読み込みのためにオープンされたファイルディスクリプター、 "
12173 "I<out_fd> は書き込みのためにオープンされたディスクリプターでなければならな"
12176 #. type: Plain text
12177 #: build/C/man2/sendfile.2:83
12179 "If I<offset> is not NULL, then it points to a variable holding the file "
12180 "offset from which B<sendfile>() will start reading data from I<in_fd>. "
12181 "When B<sendfile>() returns, this variable will be set to the offset of the "
12182 "byte following the last byte that was read. If I<offset> is not NULL, then "
12183 "B<sendfile>() does not modify the current file offset of I<in_fd>; "
12184 "otherwise the current file offset is adjusted to reflect the number of bytes "
12185 "read from I<in_fd>."
12187 "I<offset> が NULL でない場合、 I<offset> は B<sendfile>() が I<in_fd> のどこ"
12188 "からデータを読み始めるかを示すファイルオフセットを保持する変数への ポインター"
12189 "である。 B<sendfile>() は復帰する時、この変数に最後に読み込んだバイトの 次の"
12190 "バイトのオフセットを書き込む。 I<offset> が NULL でない場合、 B<sendfile>() "
12191 "は I<in_fd> のファイルオフセットの現在値を変更しない。 NULL の場合は、ファイ"
12192 "ルオフセットの現在値を I<in_fd> から読み込んだバイト数を反映した位置に調整す"
12195 #. type: Plain text
12196 #: build/C/man2/sendfile.2:90
12198 "If I<offset> is NULL, then data will be read from I<in_fd> starting at the "
12199 "current file offset, and the file offset will be updated by the call."
12201 "I<offset> が NULL の場合、データは I<in_fd> の現在のファイルオフセットから読"
12202 "み出され、 ファイルオフセットはこの呼び出しで更新される。"
12204 #. type: Plain text
12205 #: build/C/man2/sendfile.2:93
12206 msgid "I<count> is the number of bytes to copy between the file descriptors."
12207 msgstr "I<count> は、ファイルディスクリプター間でコピーするバイト数である。"
12209 #. type: Plain text
12210 #: build/C/man2/sendfile.2:100
12212 "The I<in_fd> argument must correspond to a file which supports B<mmap>(2)-"
12213 "like operations (i.e., it cannot be a socket)."
12215 "I<in_fd> 引き数は B<mmap>(2) 風の操作ができるファイルを指していなければなら"
12217 "い (ソケットを指定することはできない)。"
12219 #. type: Plain text
12220 #: build/C/man2/sendfile.2:108
12222 "In Linux kernels before 2.6.33, I<out_fd> must refer to a socket. Since "
12223 "Linux 2.6.33 it can be any file. If it is a regular file, then "
12224 "B<sendfile>() changes the file offset appropriately."
12226 "2.6.33 より前の Linux カーネルでは I<out_fd> はソケットを参照していなければ"
12228 "らない。Linux 2.6.33 以降では、任意のファイルを参照することができる。\n"
12229 "通常のファイルの場合には B<sendfile>() はファイルオフセットを適切に変更する。"
12231 #. type: Plain text
12232 #: build/C/man2/sendfile.2:115
12234 "If the transfer was successful, the number of bytes written to I<out_fd> is "
12235 "returned. On error, -1 is returned, and I<errno> is set appropriately."
12237 "転送に成功した場合、 I<out_fd> に書き込まれたバイト数を返す。エラーの場"
12238 "合、-1 を返し、 I<errno> に適切な値を設定する。"
12240 #. type: Plain text
12241 #: build/C/man2/sendfile.2:121
12243 "Nonblocking I/O has been selected using B<O_NONBLOCK> and the write would "
12246 "B<O_NONBLOCK> を用いて非ブロック I/O が選択されたが、書き込みがブロックされ"
12249 #. type: Plain text
12250 #: build/C/man2/sendfile.2:125
12252 "The input file was not opened for reading or the output file was not opened "
12255 "入力ファイルが読み込みのためにオープンされていないか、 出力ファイルが書き込み"
12258 #. type: Plain text
12259 #: build/C/man2/sendfile.2:128
12260 msgid "Bad address."
12261 msgstr "アドレスがおかしい。"
12263 #. type: Plain text
12264 #: build/C/man2/sendfile.2:134
12266 "Descriptor is not valid or locked, or an B<mmap>(2)-like operation is not "
12267 "available for I<in_fd>."
12269 "ディスクリプターが有効でないか、ロックされている。もしくは B<mmap>(2) 風の操"
12270 "作が I<in_fd> では利用できない。"
12272 #. type: Plain text
12273 #: build/C/man2/sendfile.2:138
12274 msgid "Unspecified error while reading from I<in_fd>."
12275 msgstr "I<in_fd> から読み込んでいるうちに予期しないエラーが起こった。"
12277 #. type: Plain text
12278 #: build/C/man2/sendfile.2:142
12279 msgid "Insufficient memory to read from I<in_fd>."
12280 msgstr "I<in_fd> から読み込むための十分なメモリーがない。"
12282 #. type: Plain text
12283 #: build/C/man2/sendfile.2:148
12285 "B<sendfile>() is a new feature in Linux 2.2. The include file I<E<lt>sys/"
12286 "sendfile.hE<gt>> is present since glibc 2.1."
12288 "B<sendfile> は Linux 2.2 の新しい機能である。 インクルードファイル "
12289 "I<E<lt>sys/sendfile.hE<gt>> は glibc 2.1 から存在している。"
12291 #. type: Plain text
12292 #: build/C/man2/sendfile.2:150
12293 msgid "Not specified in POSIX.1-2001, or other standards."
12294 msgstr "POSIX.1-2001 や他の標準では規定されていない。"
12296 #. type: Plain text
12297 #: build/C/man2/sendfile.2:155
12299 "Other UNIX systems implement B<sendfile>() with different semantics and "
12300 "prototypes. It should not be used in portable programs."
12302 "他の UNIX システムでは、異なった方式やプロトタイプで B<sendfile>() を実装し"
12303 "ている。移植性を考慮したプログラムでは使用すべきではない。"
12305 #. type: Plain text
12306 #: build/C/man2/sendfile.2:165
12308 "If you plan to use B<sendfile>() for sending files to a TCP socket, but "
12309 "need to send some header data in front of the file contents, you will find "
12310 "it useful to employ the B<TCP_CORK> option, described in B<tcp>(7), to "
12311 "minimize the number of packets and to tune performance."
12313 "B<sendfile>() を使って TCP ソケットにファイルを送ろうとしていて、 ファイルの"
12314 "内容の前にヘッダーデータを付け加える必要がある場合は、 パケット数を最小にして"
12315 "性能を上げるために B<tcp>(7) に記述されている B<TCP_CORK> オプションを使うと"
12318 #. type: Plain text
12319 #: build/C/man2/sendfile.2:171
12321 "In Linux 2.4 and earlier, I<out_fd> could also refer to a regular file, and "
12322 "B<sendfile>() changed the current offset of that file."
12324 "Linux 2.4 とそれ以前のバージョンでも、 I<out_fd> は通常のファイルを参照で"
12326 "B<sendfile>() はそのファイルのオフセットの現在値を変更していた。"
12328 #. type: Plain text
12329 #: build/C/man2/sendfile.2:183
12331 "The original Linux B<sendfile>() system call was not designed to handle "
12332 "large file offsets. Consequently, Linux 2.4 added B<sendfile64>(), with a "
12333 "wider type for the I<offset> argument. The glibc B<sendfile>() wrapper "
12334 "function transparently deals with the kernel differences."
12336 "元々の Linux B<sendfile>() システムコールは大きなファイルオフセットを\n"
12337 "扱えるように設計されていなかった。その結果、Linux 2.4 で、\n"
12338 "ビット幅の大きな I<offset> 引き数を持った B<sendfile64>() が追加された。\n"
12339 "glibc の B<sendfile>() のラッパー関数はカーネルによるこの違いを吸収している。"
12341 #. type: Plain text
12342 #: build/C/man2/sendfile.2:192
12344 "Applications may wish to fall back to B<read>(2)/B<write>(2) in the case "
12345 "where B<sendfile>() fails with B<EINVAL> or B<ENOSYS>."
12347 "B<sendfile>() が B<EINVAL> や B<ENOSYS> で失敗するような場合は、 アプリケー"
12348 "ションは B<read>(2)/B<write>(2) に戻すことを考えてもよいかもしれない。"
12350 #. type: Plain text
12351 #: build/C/man2/sendfile.2:197
12353 "The Linux-specific B<splice>(2) call supports transferring data between "
12354 "arbitrary files (e.g., a pair of sockets)."
12356 "Linux 固有の B<splice>(2) システムコールは、任意のファイル間 (例えば、\n"
12357 "ソケット同士) でのデータ転送をサポートしている。"
12359 #. type: Plain text
12360 #: build/C/man2/sendfile.2:202
12361 msgid "B<mmap>(2), B<open>(2), B<socket>(2), B<splice>(2)"
12362 msgstr "B<mmap>(2), B<open>(2), B<socket>(2), B<splice>(2)"
12365 #: build/C/man2/set_tid_address.2:25
12367 msgid "SET_TID_ADDRESS"
12368 msgstr "SET_TID_ADDRESS"
12371 #: build/C/man2/set_tid_address.2:25
12374 msgstr "2014-07-08"
12376 #. type: Plain text
12377 #: build/C/man2/set_tid_address.2:28
12378 msgid "set_tid_address - set pointer to thread ID"
12379 msgstr "set_tid_address - スレッド ID へのポインターを設定する"
12381 #. type: Plain text
12382 #: build/C/man2/set_tid_address.2:31
12384 msgid "B<#include E<lt>linux/unistd.hE<gt>>\n"
12385 msgstr "B<#include E<lt>linux/unistd.hE<gt>>\n"
12387 #. type: Plain text
12388 #: build/C/man2/set_tid_address.2:33
12390 msgid "B<long set_tid_address(int *>I<tidptr>B<);>\n"
12391 msgstr "B<long set_tid_address(int *>I<tidptr>B<);>\n"
12393 #. type: Plain text
12394 #: build/C/man2/set_tid_address.2:40
12396 "For each thread, the kernel maintains two attributes (addresses) called "
12397 "I<set_child_tid> and I<clear_child_tid>. These two attributes contain the "
12398 "value NULL by default."
12400 "各スレッドについて、カーネルは I<set_child_tid> と I<clear_child_tid> という "
12401 "2 つの属性を保持する。この 2 つの属性はデフォルトでは NULL である。"
12404 #: build/C/man2/set_tid_address.2:40
12406 msgid "I<set_child_tid>"
12407 msgstr "I<set_child_tid>"
12409 #. type: Plain text
12410 #: build/C/man2/set_tid_address.2:51
12412 "If a thread is started using B<clone>(2) with the B<CLONE_CHILD_SETTID> "
12413 "flag, I<set_child_tid> is set to the value passed in the I<ctid> argument of "
12414 "that system call."
12416 "スレッドが B<CLONE_CHILD_SETTID> フラグを指定した B<clone>(2) によって開始さ"
12417 "れた場合、 I<set_child_tid> は B<clone>(2) のシステムコールの I<ctid> 引き数"
12420 #. type: Plain text
12421 #: build/C/man2/set_tid_address.2:56
12423 "When I<set_child_tid> is set, the very first thing the new thread does is to "
12424 "write its thread ID at this address."
12426 "I<set_child_tid> が設定された場合、一番最初に新しいスレッドが行うことは、 こ"
12427 "のアドレスに自身のスレッド ID を書き込むことである。"
12430 #: build/C/man2/set_tid_address.2:56
12432 msgid "I<clear_child_tid>"
12433 msgstr "I<clear_child_tid>"
12435 #. type: Plain text
12436 #: build/C/man2/set_tid_address.2:67
12438 "If a thread is started using B<clone>(2) with the B<CLONE_CHILD_CLEARTID> "
12439 "flag, I<clear_child_tid> is set to the value passed in the I<ctid> argument "
12440 "of that system call."
12442 "スレッドが B<CLONE_CHILD_CLEARTID> フラグを指定した B<clone>(2) によって開始"
12443 "された場合、 I<clear_child_tid> は B<clone>(2) のシステムコールの I<ctid> 引"
12446 #. type: Plain text
12447 #: build/C/man2/set_tid_address.2:74
12449 "The system call B<set_tid_address>() sets the I<clear_child_tid> value for "
12450 "the calling thread to I<tidptr>."
12452 "システムコール B<set_tid_address>() は呼び出し元スレッドの "
12453 "I<clear_child_tid> の値を I<tidptr> に設定する。"
12455 #. type: Plain text
12456 #: build/C/man2/set_tid_address.2:82
12458 "When a thread whose I<clear_child_tid> is not NULL terminates, then, if the "
12459 "thread is sharing memory with other threads, then 0 is written at the "
12460 "address specified in I<clear_child_tid> and the kernel performs the "
12461 "following operation:"
12463 "I<clear_child_tid> が NULL でないスレッドが終了すると、そのスレッドが他のス"
12464 "レッドとメモリーを共有していれば、 I<clear_child_tid> で指定されたアドレスに "
12465 "0 が書き込まれ、カーネルは以下の処理を実行する。"
12467 #. type: Plain text
12468 #: build/C/man2/set_tid_address.2:84
12470 msgid " futex(clear_child_tid, FUTEX_WAKE, 1, NULL, NULL, 0);\n"
12471 msgstr " futex(clear_child_tid, FUTEX_WAKE, 1, NULL, NULL, 0);\n"
12473 #. type: Plain text
12474 #: build/C/man2/set_tid_address.2:88
12476 "The effect of this operation is to wake a single thread that is performing a "
12477 "futex wait on the memory location. Errors from the futex wake operation are "
12480 "この処理の結果、このメモリーアドレスに対する futex wait を実行しているスレッ"
12481 "ドを一つ起こす (wake)。 futex wake 操作でのエラーは無視される。"
12483 #. type: Plain text
12484 #: build/C/man2/set_tid_address.2:91
12485 msgid "B<set_tid_address>() always returns the caller's thread ID."
12486 msgstr "B<set_tid_address>() は常に呼び出し元のスレッド ID を返す。"
12488 #. type: Plain text
12489 #: build/C/man2/set_tid_address.2:94
12490 msgid "B<set_tid_address>() always succeeds."
12491 msgstr "B<set_tid_address>() は常に成功する。"
12493 #. type: Plain text
12494 #: build/C/man2/set_tid_address.2:97
12496 "This call is present since Linux 2.5.48. Details as given here are valid "
12497 "since Linux 2.5.49."
12499 "この呼び出しは Linux 2.5.48 以降で存在する。 ここで書かれた詳細は Linux "
12502 #. type: Plain text
12503 #: build/C/man2/set_tid_address.2:103
12504 msgid "B<clone>(2), B<futex>(2), B<gettid>(2)"
12505 msgstr "B<clone>(2), B<futex>(2), B<gettid>(2)"
12508 #: build/C/man2/splice.2:26
12514 #: build/C/man2/splice.2:26 build/C/man2/tee.2:26
12517 msgstr "2014-12-31"
12519 #. type: Plain text
12520 #: build/C/man2/splice.2:29
12521 msgid "splice - splice data to/from a pipe"
12522 msgstr "splice - パイプとの間でデータを継ぎ合わせる"
12524 #. type: Plain text
12525 #: build/C/man2/splice.2:33 build/C/man2/tee.2:33
12528 "B<#define _GNU_SOURCE> /* See feature_test_macros(7) */\n"
12529 "B<#include E<lt>fcntl.hE<gt>>\n"
12531 "B<#define _GNU_SOURCE> /* feature_test_macros(7) 参照 */\n"
12532 "B<#include E<lt>fcntl.hE<gt>>\n"
12534 #. Return type was long before glibc 2.7
12535 #. type: Plain text
12536 #: build/C/man2/splice.2:38
12539 "B<ssize_t splice(int >I<fd_in>B<, loff_t *>I<off_in>B<, int >I<fd_out>B<,>\n"
12540 "B< loff_t *>I<off_out>B<, size_t >I<len>B<, unsigned int >I<flags>B<);>\n"
12542 "B<ssize_t splice(int >I<fd_in>B<, loff_t *>I<off_in>B<, int >I<fd_out>B<,>\n"
12543 "B< loff_t *>I<off_out>B<, size_t >I<len>B<, unsigned int >I<flags>B<);>\n"
12545 #. type: Plain text
12546 #: build/C/man2/splice.2:50
12548 "B<splice>() moves data between two file descriptors without copying between "
12549 "kernel address space and user address space. It transfers up to I<len> "
12550 "bytes of data from the file descriptor I<fd_in> to the file descriptor "
12551 "I<fd_out>, where one of the descriptors must refer to a pipe."
12553 "B<splice>() は、カーネルアドレス空間とユーザーアドレス空間との間のコピーを伴"
12554 "わずに、 2 つのファイルディスクリプター間でデータの移動を行う。 ファイルディ"
12555 "スクリプター I<fd_in> からファイルディスクリプター I<fd_out> へ最大 I<len> バ"
12556 "イトを転送する。 2 つのファイルディスクリプターのうち一つは パイプを参照して"
12559 #. type: Plain text
12560 #: build/C/man2/splice.2:55
12561 msgid "The following semantics apply for I<fd_in> and I<off_in>:"
12562 msgstr "I<fd_in> と I<off_in> には以下のルールが適用される。"
12564 #. type: Plain text
12565 #: build/C/man2/splice.2:61
12566 msgid "If I<fd_in> refers to a pipe, then I<off_in> must be NULL."
12568 "I<fd_in> がパイプを参照している場合、 I<off_in> は NULL でなければならない。"
12570 #. type: Plain text
12571 #: build/C/man2/splice.2:70
12573 "If I<fd_in> does not refer to a pipe and I<off_in> is NULL, then bytes are "
12574 "read from I<fd_in> starting from the current file offset, and the current "
12575 "file offset is adjusted appropriately."
12577 "I<fd_in> がパイプを参照しておらず、かつ I<off_in> が NULL の場合、 バイトは "
12578 "I<fd_in> の現在のファイルオフセットから読み出され、 現在のファイルオフセット"
12581 #. type: Plain text
12582 #: build/C/man2/splice.2:83
12584 "If I<fd_in> does not refer to a pipe and I<off_in> is not NULL, then "
12585 "I<off_in> must point to a buffer which specifies the starting offset from "
12586 "which bytes will be read from I<fd_in>; in this case, the current file "
12587 "offset of I<fd_in> is not changed."
12589 "I<fd_in> がパイプを参照しておらず、 I<off_in> が NULL でない場合、 I<off_in> "
12590 "は I<fd_in> からのデータ読み出しを開始する先頭オフセットを格納したバッファー "
12591 "へのポインターでなければならない。この場合、 I<fd_in> の現在のファイルオフ"
12594 #. type: Plain text
12595 #: build/C/man2/splice.2:88
12596 msgid "Analogous statements apply for I<fd_out> and I<off_out>."
12597 msgstr "I<fd_out> と I<off_out> に関しても同様である。"
12599 #. type: Plain text
12600 #: build/C/man2/splice.2:93 build/C/man2/vmsplice.2:78
12602 "The I<flags> argument is a bit mask that is composed by ORing together zero "
12603 "or more of the following values:"
12605 "I<flags> 引き数には、以下の値の 0 個以上をビット毎の論理和の形で指定する。"
12608 #: build/C/man2/splice.2:93 build/C/man2/tee.2:62 build/C/man2/vmsplice.2:78
12610 msgid "B<SPLICE_F_MOVE>"
12611 msgstr "B<SPLICE_F_MOVE>"
12613 #. type: Plain text
12614 #: build/C/man2/splice.2:106
12616 "Attempt to move pages instead of copying. This is only a hint to the "
12617 "kernel: pages may still be copied if the kernel cannot move the pages from "
12618 "the pipe, or if the pipe buffers don't refer to full pages. The initial "
12619 "implementation of this flag was buggy: therefore starting in Linux 2.6.21 it "
12620 "is a no-op (but is still permitted in a B<splice>() call); in the future, a "
12621 "correct implementation may be restored."
12623 "ページのコピーでなく移動を試みる。 これはカーネルに対するヒントでしかない。 "
12624 "つまり、カーネルがパイプからページを移動できない場合や、 パイプバッファーが"
12625 "ページ全部を参照していない場合は、 ページのコピーが行われることもある。 この"
12626 "フラグの最初の実装にはバグがあった。そのため、 Linux 2.6.21 以降ではこのフラ"
12627 "グの操作はできないようになっている (ただし、 B<splice>() コールでこのフラグ"
12628 "を指定することは今も認められている)。 将来、正しい実装が行われることだろう。"
12631 #: build/C/man2/splice.2:106 build/C/man2/tee.2:68 build/C/man2/vmsplice.2:84
12633 msgid "B<SPLICE_F_NONBLOCK>"
12634 msgstr "B<SPLICE_F_NONBLOCK>"
12636 #. type: Plain text
12637 #: build/C/man2/splice.2:115
12639 "Do not block on I/O. This makes the splice pipe operations nonblocking, but "
12640 "B<splice>() may nevertheless block because the file descriptors that are "
12641 "spliced to/from may block (unless they have the B<O_NONBLOCK> flag set)."
12643 "入出力時に停止 (block) しない。 このフラグを指定すると、 splice によるパイプ"
12644 "操作を非停止モード (nonblocking) で 行おうとするが、その場合でも "
12645 "B<splice>() は停止することもある。なぜなら、データのやり取りを行う ファイル"
12646 "ディスクリプターは (B<O_NONBLOCK> フラグをセットされていない場合) 停止する可"
12650 #: build/C/man2/splice.2:115 build/C/man2/tee.2:73 build/C/man2/vmsplice.2:91
12652 msgid "B<SPLICE_F_MORE>"
12653 msgstr "B<SPLICE_F_MORE>"
12655 #. type: Plain text
12656 #: build/C/man2/splice.2:129
12658 "More data will be coming in a subsequent splice. This is a helpful hint "
12659 "when the I<fd_out> refers to a socket (see also the description of "
12660 "B<MSG_MORE> in B<send>(2), and the description of B<TCP_CORK> in B<tcp>(7))"
12662 "この後の splice でさらに転送されるデータがあることを示す。 このフラグは "
12663 "I<fd_out> がソケットを参照している場合に有用なヒントとなる (B<send>(2) の "
12664 "B<MSG_MORE> や B<tcp>(7) の B<TCP_CORK> の説明も参照)。"
12667 #: build/C/man2/splice.2:129 build/C/man2/tee.2:79 build/C/man2/vmsplice.2:97
12669 msgid "B<SPLICE_F_GIFT>"
12670 msgstr "B<SPLICE_F_GIFT>"
12672 #. type: Plain text
12673 #: build/C/man2/splice.2:135
12674 msgid "Unused for B<splice>(); see B<vmsplice>(2)."
12675 msgstr "B<splice>() では使用しない。 B<vmsplice>(2) 参照。"
12677 #. type: Plain text
12678 #: build/C/man2/splice.2:144
12680 "Upon successful completion, B<splice>() returns the number of bytes spliced "
12681 "to or from the pipe. A return value of 0 means that there was no data to "
12682 "transfer, and it would not make sense to block, because there are no writers "
12683 "connected to the write end of the pipe referred to by I<fd_in>."
12685 "成功して完了すると、 B<splice>() はパイプから出し入れしたバイト数を返す。 返"
12686 "り値 0 はデータの転送が行わなかったことを示す。 この場合、処理を停止 (block) "
12687 "しても無意味である。 なぜなら、 I<fd_in> が参照するパイプの書き込み側に接続さ"
12690 #. type: Plain text
12691 #: build/C/man2/splice.2:150
12693 "On error, B<splice>() returns -1 and I<errno> is set to indicate the error."
12695 "エラーの場合、 B<splice>() は -1 を返し、 I<errno> にエラーを示す値を設定す"
12698 #. type: Plain text
12699 #: build/C/man2/splice.2:157 build/C/man2/tee.2:107
12700 #: build/C/man2/vmsplice.2:133
12702 "B<SPLICE_F_NONBLOCK> was specified in I<flags>, and the operation would "
12705 "B<SPLICE_F_NONBLOCK> が I<flags> に指定されていて、かつ操作が停止するような状"
12708 #. type: Plain text
12709 #: build/C/man2/splice.2:161
12711 "One or both file descriptors are not valid, or do not have proper read-write "
12714 "ファイルディスクリプターの一方または両方が有効ではない、 もしくは適切な read-"
12717 #. The append-mode error is given since 2.6.27; in earlier kernels,
12718 #. splice() in append mode was broken
12719 #. type: Plain text
12720 #: build/C/man2/splice.2:169
12722 "Target filesystem doesn't support splicing; target file is opened in append "
12723 "mode; neither of the descriptors refers to a pipe; or offset given for "
12724 "nonseekable device."
12726 "対象のファイルシステムが splice に対応していない、 または対象のファイルが追記"
12727 "モードでオープンされている、 またはディスクリプターのどちらもパイプを参照して"
12728 "いない、 または seek できないデバイスに対してオフセットが指定された。"
12730 #. type: Plain text
12731 #: build/C/man2/splice.2:172 build/C/man2/tee.2:120
12732 #: build/C/man2/vmsplice.2:148
12733 msgid "Out of memory."
12737 #: build/C/man2/splice.2:172
12742 #. type: Plain text
12743 #: build/C/man2/splice.2:179
12745 "Either I<off_in> or I<off_out> was not NULL, but the corresponding file "
12746 "descriptor refers to a pipe."
12748 "I<off_in> か I<off_out> のいずれかが NULL ではないが、対応するファイルディス"
12749 "クリプターが パイプを参照している。"
12751 #. type: Plain text
12752 #: build/C/man2/splice.2:184
12754 "The B<splice>() system call first appeared in Linux 2.6.17; library support "
12755 "was added to glibc in version 2.5."
12757 "B<splice>() システムコールは Linux 2.6.17 で初めて登場した。\n"
12758 "ライブラリによるサポートは glibc バージョン 2.5 で追加された。"
12760 #. type: Plain text
12761 #: build/C/man2/splice.2:196
12763 "The three system calls B<splice>(), B<vmsplice>(2), and B<tee>(2), provide "
12764 "user-space programs with full control over an arbitrary kernel buffer, "
12765 "implemented within the kernel using the same type of buffer that is used for "
12766 "a pipe. In overview, these system calls perform the following tasks:"
12768 "3 つのシステムコール (B<splice>(), B<vmsplice>(2), B<tee>(2)) を使うと、ユー"
12769 "ザー空間プログラムは任意のカーネルバッファーに対する 完全な制御ができる。カー"
12770 "ネルバッファーは、パイプに使用されているのと 同種のバッファーを使ってカーネル"
12771 "内に実装されている。 大まかにいうと、これらのシステムコールは以下の仕事を行"
12775 #: build/C/man2/splice.2:196
12777 msgid "B<splice>()"
12778 msgstr "B<splice>()"
12780 #. type: Plain text
12781 #: build/C/man2/splice.2:200
12783 "moves data from the buffer to an arbitrary file descriptor, or vice versa, "
12784 "or from one buffer to another."
12786 "バッファーから任意のファイルディスクリプターや、その逆方向、 もしくはあるバッ"
12787 "ファーから別のバッファーへの、データ移動を行う。"
12790 #: build/C/man2/splice.2:200
12795 #. type: Plain text
12796 #: build/C/man2/splice.2:203
12797 msgid "\"copies\" the data from one buffer to another."
12798 msgstr "あるバッファーから別のバッファーへのデータ「コピー」を行う。"
12801 #: build/C/man2/splice.2:203
12803 msgid "B<vmsplice>(2)"
12804 msgstr "B<vmsplice>(2)"
12806 #. type: Plain text
12807 #: build/C/man2/splice.2:206
12808 msgid "\"copies\" data from user space into the buffer."
12809 msgstr "ユーザー空間からバッファーへのデータ「コピー」を行う。"
12811 #. Linus: Now, imagine using the above in a media server, for example.
12812 #. Let's say that a year or two has passed, so that the video drivers
12813 #. have been updated to be able to do the splice thing, and what can
12814 #. you do? You can:
12815 #. - splice from the (mpeg or whatever - let's just assume that the video
12816 #. input is either digital or does the encoding on its own - like they
12817 #. pretty much all do) video input into a pipe (remember: no copies - the
12818 #. video input will just DMA directly into memory, and splice will just
12819 #. set up the pages in the pipe buffer)
12820 #. - tee that pipe to split it up
12821 #. - splice one end to a file (ie "save the compressed stream to disk")
12822 #. - splice the other end to a real-time video decoder window for your
12823 #. real-time viewing pleasure.
12824 #. Linus: Now, the advantage of splice()/tee() is that you can
12825 #. do zero-copy movement of data, and unlike sendfile() you can
12826 #. do it on _arbitrary_ data (and, as shown by "tee()", it's more
12827 #. than just sending the data to somebody else: you can duplicate
12828 #. the data and choose to forward it to two or more different
12829 #. users - for things like logging etc.).
12830 #. type: Plain text
12831 #: build/C/man2/splice.2:237
12833 "Though we talk of copying, actual copies are generally avoided. The kernel "
12834 "does this by implementing a pipe buffer as a set of reference-counted "
12835 "pointers to pages of kernel memory. The kernel creates \"copies\" of pages "
12836 "in a buffer by creating new pointers (for the output buffer) referring to "
12837 "the pages, and increasing the reference counts for the pages: only pointers "
12838 "are copied, not the pages of the buffer."
12840 "ここではコピーの話をしているが、実際のコピーは一般的に回避される。 カーネル"
12841 "は、パイプバッファーをカーネルメモリーのページへのポインター集合として 実装"
12842 "し、ページへの参照回数を管理することで、これを実現している。 カーネルは、対象"
12843 "となるページを参照する (出力バッファー用の) ポインターを 新規に作成することで"
12844 "バッファー内のページの「コピー」を作成し、 そのページの参照回数を増やす。つま"
12845 "り、ポインターだけがコピーされ、 バッファーのページはコピーされない。"
12847 #. type: Plain text
12848 #: build/C/man2/splice.2:240
12849 msgid "See B<tee>(2)."
12850 msgstr "B<tee>(2) 参照。"
12852 #. type: Plain text
12853 #: build/C/man2/splice.2:244
12854 msgid "B<sendfile>(2), B<tee>(2), B<vmsplice>(2)"
12855 msgstr "B<sendfile>(2), B<tee>(2), B<vmsplice>(2)"
12858 #: build/C/man2/tee.2:26
12863 #. type: Plain text
12864 #: build/C/man2/tee.2:29
12865 msgid "tee - duplicating pipe content"
12866 msgstr "tee - パイプの中身を複製する"
12868 #. type: Plain text
12869 #: build/C/man2/tee.2:36
12871 msgid "B<ssize_t tee(int >I<fd_in>B<, int >I<fd_out>B<, size_t >I<len>B<, unsigned int >I<flags>B<);>\n"
12872 msgstr "B<ssize_t tee(int >I<fd_in>B<, int >I<fd_out>B<, size_t >I<len>B<, unsigned int >I<flags>B<);>\n"
12874 #. Example programs http://brick.kernel.dk/snaps
12875 #. add a "tee(in, out1, out2)" system call that duplicates the pages
12876 #. (again, incrementing their reference count, not copying the data) from
12877 #. one pipe to two other pipes.
12878 #. type: Plain text
12879 #: build/C/man2/tee.2:56
12881 "B<tee>() duplicates up to I<len> bytes of data from the pipe referred to by "
12882 "the file descriptor I<fd_in> to the pipe referred to by the file descriptor "
12883 "I<fd_out>. It does not consume the data that is duplicated from I<fd_in>; "
12884 "therefore, that data can be copied by a subsequent B<splice>(2)."
12886 "B<tee>() は、ファイルディスクリプター I<fd_in> が参照するパイプからファイル"
12887 "ディスクリプター I<fd_out> が参照するパイプへ最大 I<len> バイトのデータを複製"
12888 "する。 この操作では、複製されるデータは I<fd_in> からは消費されない。したがっ"
12889 "て、これらのデータをこの後の B<splice>(2) でコピーすることができる。"
12891 #. type: Plain text
12892 #: build/C/man2/tee.2:62
12894 "I<flags> is a series of modifier flags, which share the name space with "
12895 "B<splice>(2) and B<vmsplice>(2):"
12897 "I<flags> は一連の修飾フラグであり、 B<splice>(2) や B<vmsplice>(2) と共通の"
12900 #. type: Plain text
12901 #: build/C/man2/tee.2:68
12902 msgid "Currently has no effect for B<tee>(); see B<splice>(2)."
12903 msgstr "現在のところ B<tee>() では何の効果もない。 B<splice>(2) 参照。"
12905 #. Not used for vmsplice
12906 #. May be in the future -- therefore EAGAIN
12907 #. type: Plain text
12908 #: build/C/man2/tee.2:73 build/C/man2/vmsplice.2:91
12909 msgid "Do not block on I/O; see B<splice>(2) for further details."
12910 msgstr "入出力で停止 (block) しない。詳細は B<splice>(2) 参照。"
12912 #. type: Plain text
12913 #: build/C/man2/tee.2:79
12915 "Currently has no effect for B<tee>(), but may be implemented in the future; "
12916 "see B<splice>(2)."
12918 "現在のところ B<tee>() では何の効果もないが、将来的には実装される可能性があ"
12919 "る。 B<splice>(2) 参照。"
12921 #. type: Plain text
12922 #: build/C/man2/tee.2:85
12923 msgid "Unused for B<tee>(); see B<vmsplice>(2)."
12924 msgstr "B<tee>() では未使用。 B<vmsplice>(2) 参照。"
12926 #. type: Plain text
12927 #: build/C/man2/tee.2:94
12929 "Upon successful completion, B<tee>() returns the number of bytes that were "
12930 "duplicated between the input and output. A return value of 0 means that "
12931 "there was no data to transfer, and it would not make sense to block, because "
12932 "there are no writers connected to the write end of the pipe referred to by "
12935 "成功して完了すると、 B<tee>() は入出力間で複製されたバイト数を返す。 返り値 "
12936 "0 はデータの転送が行われなかったことを示す。 この場合、処理を停止 (block) し"
12937 "ても無意味である。 なぜなら、 I<fd_in> が参照するパイプの書き込み側に接続され"
12940 #. type: Plain text
12941 #: build/C/man2/tee.2:100
12943 "On error, B<tee>() returns -1 and I<errno> is set to indicate the error."
12945 "エラーの場合、 B<tee>() は -1 を返し、 I<errno> にエラーを示す値を設定する。"
12947 #. type: Plain text
12948 #: build/C/man2/tee.2:117
12950 "I<fd_in> or I<fd_out> does not refer to a pipe; or I<fd_in> and I<fd_out> "
12951 "refer to the same pipe."
12953 "I<fd_in> と I<fd_out> のどちらかがパイプを参照していない。もしくは I<fd_in> "
12954 "と I<fd_out> が同じパイプを参照している。"
12956 #. type: Plain text
12957 #: build/C/man2/tee.2:125
12959 "The B<tee>() system call first appeared in Linux 2.6.17; library support "
12960 "was added to glibc in version 2.5."
12962 "B<tee>() システムコールは Linux 2.6.17 で初めて登場した。\n"
12963 "ライブラリによるサポートは glibc バージョン 2.5 で追加された。"
12965 #. type: Plain text
12966 #: build/C/man2/tee.2:136
12968 "Conceptually, B<tee>() copies the data between the two pipes. In reality "
12969 "no real data copying takes place though: under the covers, B<tee>() assigns "
12970 "data in the output by merely grabbing a reference to the input."
12972 "概念としては、 B<tee>() は二つのパイプ間でデータのコピーを行う。 しかし、実"
12973 "際には実データのコピーは行われない。 内部では、 B<tee>() は入力側に対する参"
12974 "照だけを作成することで出力側にデータを 追加する。"
12976 #. type: Plain text
12977 #: build/C/man2/tee.2:143
12979 "The example below implements a basic B<tee>(1) program using the B<tee>() "
12980 "system call. Here is an example of its use:"
12982 "以下の例は、 B<tee>() システムコールを使って、 基本的な B<tee>(1) プログラ"
12983 "ムを実装したものである。 以下は利用例である。"
12985 #. type: Plain text
12986 #: build/C/man2/tee.2:150
12989 "$ B<date |./a.out out.log | cat>\n"
12990 "Tue Oct 28 10:06:00 CET 2014\n"
12991 "$ B<cat out.log>\n"
12992 "Tue Oct 28 10:06:00 CET 2014\n"
12994 "$ B<date |./a.out out.log | cat>\n"
12995 "Tue Oct 28 10:06:00 CET 2014\n"
12996 "$ B<cat out.log>\n"
12997 "Tue Oct 28 10:06:00 CET 2014\n"
13000 #: build/C/man2/tee.2:152
13002 msgid "Program source"
13005 #. type: Plain text
13006 #: build/C/man2/tee.2:162
13009 "#define _GNU_SOURCE\n"
13010 "#include E<lt>fcntl.hE<gt>\n"
13011 "#include E<lt>stdio.hE<gt>\n"
13012 "#include E<lt>stdlib.hE<gt>\n"
13013 "#include E<lt>unistd.hE<gt>\n"
13014 "#include E<lt>errno.hE<gt>\n"
13015 "#include E<lt>limits.hE<gt>\n"
13017 "#define _GNU_SOURCE\n"
13018 "#include E<lt>fcntl.hE<gt>\n"
13019 "#include E<lt>stdio.hE<gt>\n"
13020 "#include E<lt>stdlib.hE<gt>\n"
13021 "#include E<lt>unistd.hE<gt>\n"
13022 "#include E<lt>errno.hE<gt>\n"
13023 "#include E<lt>limits.hE<gt>\n"
13025 #. type: Plain text
13026 #: build/C/man2/tee.2:168
13030 "main(int argc, char *argv[])\n"
13033 " int len, slen;\n"
13036 "main(int argc, char *argv[])\n"
13039 " int len, slen;\n"
13041 #. type: Plain text
13042 #: build/C/man2/tee.2:173
13045 " if (argc != 2) {\n"
13046 " fprintf(stderr, \"Usage: %s E<lt>fileE<gt>\\en\", argv[0]);\n"
13047 " exit(EXIT_FAILURE);\n"
13050 " if (argc != 2) {\n"
13051 " fprintf(stderr, \"Usage: %s E<lt>fileE<gt>\\en\", argv[0]);\n"
13052 " exit(EXIT_FAILURE);\n"
13055 #. type: Plain text
13056 #: build/C/man2/tee.2:179
13059 " fd = open(argv[1], O_WRONLY | O_CREAT | O_TRUNC, 0644);\n"
13060 " if (fd == -1) {\n"
13061 " perror(\"open\");\n"
13062 " exit(EXIT_FAILURE);\n"
13065 " fd = open(argv[1], O_WRONLY | O_CREAT | O_TRUNC, 0644);\n"
13066 " if (fd == -1) {\n"
13067 " perror(\"open\");\n"
13068 " exit(EXIT_FAILURE);\n"
13071 #. type: Plain text
13072 #: build/C/man2/tee.2:186
13077 " * tee stdin to stdout.\n"
13079 " len = tee(STDIN_FILENO, STDOUT_FILENO,\n"
13080 " INT_MAX, SPLICE_F_NONBLOCK);\n"
13084 " * tee stdin to stdout.\n"
13086 " len = tee(STDIN_FILENO, STDOUT_FILENO,\n"
13087 " INT_MAX, SPLICE_F_NONBLOCK);\n"
13089 #. type: Plain text
13090 #: build/C/man2/tee.2:195
13093 " if (len E<lt> 0) {\n"
13094 " if (errno == EAGAIN)\n"
13096 " perror(\"tee\");\n"
13097 " exit(EXIT_FAILURE);\n"
13102 " if (len E<lt> 0) {\n"
13103 " if (errno == EAGAIN)\n"
13105 " perror(\"tee\");\n"
13106 " exit(EXIT_FAILURE);\n"
13111 #. type: Plain text
13112 #: build/C/man2/tee.2:209
13116 " * Consume stdin by splicing it to a file.\n"
13118 " while (len E<gt> 0) {\n"
13119 " slen = splice(STDIN_FILENO, NULL, fd, NULL,\n"
13120 " len, SPLICE_F_MOVE);\n"
13121 " if (slen E<lt> 0) {\n"
13122 " perror(\"splice\");\n"
13130 " * Consume stdin by splicing it to a file.\n"
13132 " while (len E<gt> 0) {\n"
13133 " slen = splice(STDIN_FILENO, NULL, fd, NULL,\n"
13134 " len, SPLICE_F_MOVE);\n"
13135 " if (slen E<lt> 0) {\n"
13136 " perror(\"splice\");\n"
13143 #. type: Plain text
13144 #: build/C/man2/tee.2:213
13148 " exit(EXIT_SUCCESS);\n"
13152 " exit(EXIT_SUCCESS);\n"
13155 #. type: Plain text
13156 #: build/C/man2/tee.2:217
13157 msgid "B<splice>(2), B<vmsplice>(2)"
13158 msgstr "B<splice>(2), B<vmsplice>(2)"
13161 #: build/C/man2/vm86.2:26
13167 #: build/C/man2/vm86.2:26
13170 msgstr "2009-02-20"
13172 #. type: Plain text
13173 #: build/C/man2/vm86.2:29
13174 msgid "vm86old, vm86 - enter virtual 8086 mode"
13175 msgstr "vm86old, vm86 - 仮想 8086 モードへ移行する"
13177 #. type: Plain text
13178 #: build/C/man2/vm86.2:31
13179 msgid "B<#include E<lt>sys/vm86.hE<gt>>"
13180 msgstr "B<#include E<lt>sys/vm86.hE<gt>>"
13182 #. type: Plain text
13183 #: build/C/man2/vm86.2:33
13184 msgid "B<int vm86old(struct vm86_struct *>I<info>B<);>"
13185 msgstr "B<int vm86old(struct vm86_struct *>I<info>B<);>"
13187 #. type: Plain text
13188 #: build/C/man2/vm86.2:35
13189 msgid "B<int vm86(unsigned long >I<fn>B<, struct vm86plus_struct *>I<v86>B<);>"
13191 "B<int vm86(unsigned long >I<fn>B<, struct vm86plus_struct *>I<v86>B<);>"
13193 #. type: Plain text
13194 #: build/C/man2/vm86.2:48
13196 "The system call B<vm86>() was introduced in Linux 0.97p2. In Linux 2.1.15 "
13197 "and 2.0.28, it was renamed to B<vm86old>(), and a new B<vm86>() was "
13198 "introduced. The definition of I<struct vm86_struct> was changed in 1.1.8 "
13201 "B<vm86>() システムコールは Linux 0.97p2 で導入された。 これは Linux 2.1.15 "
13202 "と 2.0.28 で B<vm86old>() に名前が変更され、 新しい B<vm86>() が導入され"
13203 "た。 I<struct vm86_struct> の定義は 1.1.8 と 1.1.9 で変更された。"
13205 #. type: Plain text
13206 #: build/C/man2/vm86.2:52
13208 "These calls cause the process to enter VM86 mode (virtual-8086 in Intel "
13209 "literature), and are used by B<dosemu>."
13211 "これらのコールによってプロセスは VM86 モード (Intel の文書では仮想 8086 モー"
13212 "ド) へと移行する。 これらのコールは B<dosemu> で使用される。"
13214 #. type: Plain text
13215 #: build/C/man2/vm86.2:54
13216 msgid "VM86 mode is an emulation of real mode within a protected mode task."
13218 "VM86 モードはプロテクトモードタスクにおける リアルモードのエミュレーションで"
13221 #. type: Plain text
13222 #: build/C/man2/vm86.2:64
13224 "This return value is specific to i386 and indicates a problem with getting "
13227 "この返り値は i386 固有のものであり、 ユーザー空間のデータを取得する際に問題が"
13230 #. type: Plain text
13231 #: build/C/man2/vm86.2:68
13233 "This return value indicates the call is not implemented on the present "
13236 "この返り値は、このコールが現在のアーキテクチャーで実装されていないことを示"
13239 #. type: Plain text
13240 #: build/C/man2/vm86.2:73
13242 "Saved kernel stack exists. (This is a kernel sanity check; the saved stack "
13243 "should exist only within vm86 mode itself.)"
13245 "保存されたカーネルスタックが既に存在している。(これはカーネルが通常の 状態で"
13246 "あるかをチェックしている。保存されたスタックは vm86 モードで しか存在しな"
13249 #. type: Plain text
13250 #: build/C/man2/vm86.2:76
13252 "This call is specific to Linux on 32-bit Intel processors, and should not be "
13253 "used in programs intended to be portable."
13255 "この関数は 32 ビット Intel プロセッサ上の Linux 特有の関数であり、 移植を意図"
13256 "したプログラムでは使用すべきでない。"
13259 #: build/C/man2/vmsplice.2:26
13265 #: build/C/man2/vmsplice.2:26
13268 msgstr "2014-10-02"
13270 #. type: Plain text
13271 #: build/C/man2/vmsplice.2:29
13272 msgid "vmsplice - splice user pages into a pipe"
13273 msgstr "vmsplice - ユーザーページをパイプに継ぎ合わせる"
13275 #. type: Plain text
13276 #: build/C/man2/vmsplice.2:34
13279 "B<#define _GNU_SOURCE> /* See feature_test_macros(7) */\n"
13280 "B<#include E<lt>fcntl.hE<gt>>\n"
13281 "B<#include E<lt>sys/uio.hE<gt>>\n"
13283 "B<#define _GNU_SOURCE> /* feature_test_macros(7) 参照 */\n"
13284 "B<#include E<lt>fcntl.hE<gt>>\n"
13285 "B<#include E<lt>sys/uio.hE<gt>>\n"
13287 #. type: Plain text
13288 #: build/C/man2/vmsplice.2:37
13291 "B<ssize_t vmsplice(int >I<fd>B<, const struct iovec *>I<iov>B<,>\n"
13292 "B< unsigned long >I<nr_segs>B<, unsigned int >I<flags>B<);>\n"
13294 "B<ssize_t vmsplice(int >I<fd>B<, const struct iovec *>I<iov>B<,>\n"
13295 "B< unsigned long >I<nr_segs>B<, unsigned int >I<flags>B<);>\n"
13297 #. Linus: vmsplice() system call to basically do a "write to
13298 #. the buffer", but using the reference counting and VM traversal
13299 #. to actually fill the buffer. This means that the user needs to
13300 #. be careful not to reuse the user-space buffer it spliced into
13301 #. the kernel-space one (contrast this to "write()", which copies
13302 #. the actual data, and you can thus reuse the buffer immediately
13303 #. after a successful write), but that is often easy to do.
13304 #. type: Plain text
13305 #: build/C/man2/vmsplice.2:57
13307 "The B<vmsplice>() system call maps I<nr_segs> ranges of user memory "
13308 "described by I<iov> into a pipe. The file descriptor I<fd> must refer to a "
13311 "B<vmsplice>() システムコールは、 I<iov> で指定されたユーザーメモリーの "
13312 "I<nr_segs> の範囲をパイプにマッピングする。 I<fd> はパイプを参照していなけれ"
13315 #. type: Plain text
13316 #: build/C/man2/vmsplice.2:64
13318 "The pointer I<iov> points to an array of I<iovec> structures as defined in "
13319 "I<E<lt>sys/uio.hE<gt>>:"
13321 "ポインター I<iov> は I<iovec> 構造体の配列を指す。 I<iovec> 構造体は "
13322 "I<E<lt>sys/uio.hE<gt>> で以下のように定義されている:"
13324 #. type: Plain text
13325 #: build/C/man2/vmsplice.2:71
13329 " void *iov_base; /* Starting address */\n"
13330 " size_t iov_len; /* Number of bytes */\n"
13334 " void *iov_base; /* 開始アドレス */\n"
13335 " size_t iov_len; /* バイト数 */\n"
13338 #. type: Plain text
13339 #: build/C/man2/vmsplice.2:84
13340 msgid "Unused for B<vmsplice>(); see B<splice>(2)."
13341 msgstr "B<vmsplice>() では未使用。 B<splice>(2) 参照。"
13343 #. type: Plain text
13344 #: build/C/man2/vmsplice.2:97
13346 "Currently has no effect for B<vmsplice>(), but may be implemented in the "
13347 "future; see B<splice>(2)."
13349 "現在のところ B<vmsplice>() では何の効果もないが、将来的には実装される可能性"
13350 "がある。 B<splice>(2) 参照。"
13352 #. FIXME . Explain the following line in a little more detail:
13354 #. It looks like the page-alignment requirement went away with
13355 #. commit bd1a68b59c8e3bce45fb76632c64e1e063c3962d
13356 #. .... if we expect to later SPLICE_F_MOVE to the cache.
13357 #. type: Plain text
13358 #: build/C/man2/vmsplice.2:117
13360 "The user pages are a gift to the kernel. The application may not modify "
13361 "this memory ever, or page cache and on-disk data may differ. Gifting pages "
13362 "to the kernel means that a subsequent B<splice>(2) B<SPLICE_F_MOVE> can "
13363 "successfully move the pages; if this flag is not specified, then a "
13364 "subsequent B<splice>(2) B<SPLICE_F_MOVE> must copy the pages. Data must "
13365 "also be properly page aligned, both in memory and length."
13367 "ユーザーページがカーネルへ渡すもの (gift) であることを示す。 アプリケーション"
13368 "はこのメモリーを絶対に変更してはならない。 さもなければ、ページキャッシュと"
13369 "ディスク上のデータは 一致しなくなるだろう。 ページをカーネルに渡すと、この次"
13370 "の B<splice>(2) B<SPLICE_F_MOVE> でそのページの移動を行うことができる。 この"
13371 "フラグが指定されなかった場合、この次の B<splice>(2) B<SPLICE_F_MOVE> でその"
13372 "ページのコピーを行わなければならない。 データはメモリー上でページ境界にあって"
13373 "いなければならず、 長さもページ境界の倍数でなければならない。"
13375 #. type: Plain text
13376 #: build/C/man2/vmsplice.2:126
13378 "Upon successful completion, B<vmsplice>() returns the number of bytes "
13379 "transferred to the pipe. On error, B<vmsplice>() returns -1 and I<errno> "
13380 "is set to indicate the error."
13382 "成功して完了すると、 B<vmsplice>() はパイプに転送したバイト数を返す。 エラー"
13383 "の場合、 B<vmplice>() は -1 を返し、 I<errno> をエラーを示す値に設定する。"
13385 #. type: Plain text
13386 #: build/C/man2/vmsplice.2:137
13387 msgid "I<fd> either not valid, or doesn't refer to a pipe."
13388 msgstr "I<fd> が有効でない、もしくはパイプを参照していない。"
13390 #. type: Plain text
13391 #: build/C/man2/vmsplice.2:145
13393 "I<nr_segs> is greater than B<IOV_MAX>; or memory not aligned if "
13394 "B<SPLICE_F_GIFT> set."
13396 "I<nr_segs> が B<IOV_MAX> よりも大きい。または B<SPLICE_F_GIFT> が設定されたが"
13397 "メモリーがページ境界にあっていない。"
13399 #. type: Plain text
13400 #: build/C/man2/vmsplice.2:153
13402 "The B<vmsplice>() system call first appeared in Linux 2.6.17; library "
13403 "support was added to glibc in version 2.5."
13405 "B<vmsplice>() システムコールは Linux 2.6.17 で初めて登場した。\n"
13406 "ライブラリによるサポートは glibc バージョン 2.5 で追加された。"
13408 #. type: Plain text
13409 #: build/C/man2/vmsplice.2:164
13411 "B<vmsplice>() follows the other vectorized read/write type functions when "
13412 "it comes to limitations on number of segments being passed in. This limit "
13413 "is B<IOV_MAX> as defined in I<E<lt>limits.hE<gt>>. At the time of this "
13414 "writing, that limit is 1024."
13416 "指定されたセグメント数が上限に達した場合、 B<vmsplice>() は他のベクトル形式"
13417 "の read/write を行う関数と同じ動作をする。 上限は B<IOV_MAX> であり、 "
13418 "I<E<lt>limits.hE<gt>> で定義されている。 このドキュメントを書いた時点での値"
13421 #. type: Plain text
13422 #: build/C/man2/vmsplice.2:167
13423 msgid "B<splice>(2), B<tee>(2)"
13424 msgstr "B<splice>(2), B<tee>(2)"
13427 #~ "B< struct kexec_segment *>I<segments>B<, unsigned long >I<flags>B<);>"
13429 #~ "B< struct kexec_segment *>I<segments>B<, unsigned long >I<flags>B<);>"
13431 #~ msgid "Execute the new kernel automatically on a system crash."
13432 #~ msgstr "システムのクラッシュ時に、新しいカーネルを自動的に実行する。"
13435 #~ "The kernel image defined by I<segments> is copied from the calling "
13436 #~ "process into previously reserved memory."
13438 #~ "I<segments> で定義されたカーネルイメージは、\n"
13439 #~ "呼び出したプロセスから予約済みメモリーにコピーされる。"
13441 #~ msgid "I<flags> is invalid; or I<nr_segments> is too large"
13442 #~ msgstr "I<flags> が無効である。 I<nr_segments> が大きすぎる。"
13445 #~ "The required constants are in the Linux kernel source file I<linux/kexec."
13446 #~ "h>, which is not currently exported to glibc. Therefore, these constants "
13447 #~ "must be defined manually."
13449 #~ "必要な定数は Linux カーネルのソースファイル I<linux/kexec.h> で定義されて"
13451 #~ "が、現在のところ glibc には公開されていない。\n"
13452 #~ "そのため、これらの定数は手動で定義しなければならない。"
13454 #~ msgid "2014-04-15"
13455 #~ msgstr "2014-04-15"