1 =================================== 1 ===================================
2 Documentation for /proc/sys/kernel/ 2 Documentation for /proc/sys/kernel/
3 =================================== 3 ===================================
4 4
5 .. See scripts/check-sysctl-docs to keep this 5 .. See scripts/check-sysctl-docs to keep this up to date
6 6
7 7
8 Copyright (c) 1998, 1999, Rik van Riel <riel@n 8 Copyright (c) 1998, 1999, Rik van Riel <riel@nl.linux.org>
9 9
10 Copyright (c) 2009, Shen Feng<shen@cn.fu 10 Copyright (c) 2009, Shen Feng<shen@cn.fujitsu.com>
11 11
12 For general info and legal blurb, please look !! 12 For general info and legal blurb, please look in :doc:`index`.
13 Documentation/admin-guide/sysctl/index.rst. <<
14 13
15 ---------------------------------------------- 14 ------------------------------------------------------------------------------
16 15
17 This file contains documentation for the sysct 16 This file contains documentation for the sysctl files in
18 ``/proc/sys/kernel/``. 17 ``/proc/sys/kernel/``.
19 18
20 The files in this directory can be used to tun 19 The files in this directory can be used to tune and monitor
21 miscellaneous and general things in the operat 20 miscellaneous and general things in the operation of the Linux
22 kernel. Since some of the files *can* be used 21 kernel. Since some of the files *can* be used to screw up your
23 system, it is advisable to read both documenta 22 system, it is advisable to read both documentation and source
24 before actually making adjustments. 23 before actually making adjustments.
25 24
26 Currently, these files might (depending on you 25 Currently, these files might (depending on your configuration)
27 show up in ``/proc/sys/kernel``: 26 show up in ``/proc/sys/kernel``:
28 27
29 .. contents:: :local: 28 .. contents:: :local:
30 29
31 30
32 acct 31 acct
33 ==== 32 ====
34 33
35 :: 34 ::
36 35
37 highwater lowwater frequency 36 highwater lowwater frequency
38 37
39 If BSD-style process accounting is enabled the 38 If BSD-style process accounting is enabled these values control
40 its behaviour. If free space on filesystem whe 39 its behaviour. If free space on filesystem where the log lives
41 goes below ``lowwater``\ % accounting suspends !! 40 goes below ``lowwater``% accounting suspends. If free space gets
42 above ``highwater``\ % accounting resumes. ``f !! 41 above ``highwater``% accounting resumes. ``frequency`` determines
43 how often do we check the amount of free space 42 how often do we check the amount of free space (value is in
44 seconds). Default: 43 seconds). Default:
45 44
46 :: 45 ::
47 46
48 4 2 30 47 4 2 30
49 48
50 That is, suspend accounting if free space drop 49 That is, suspend accounting if free space drops below 2%; resume it
51 if it increases to at least 4%; consider infor 50 if it increases to at least 4%; consider information about amount of
52 free space valid for 30 seconds. 51 free space valid for 30 seconds.
53 52
54 53
55 acpi_video_flags 54 acpi_video_flags
56 ================ 55 ================
57 56
58 See Documentation/power/video.rst. This allows !! 57 See :doc:`/power/video`. This allows the video resume mode to be set,
59 in a similar fashion to the ``acpi_sleep`` ker 58 in a similar fashion to the ``acpi_sleep`` kernel parameter, by
60 combining the following values: 59 combining the following values:
61 60
62 = ======= 61 = =======
63 1 s3_bios 62 1 s3_bios
64 2 s3_mode 63 2 s3_mode
65 4 s3_beep 64 4 s3_beep
66 = ======= 65 = =======
67 66
68 arch <<
69 ==== <<
70 <<
71 The machine hardware name, the same output as <<
72 (e.g. ``x86_64`` or ``aarch64``). <<
73 67
74 auto_msgmni 68 auto_msgmni
75 =========== 69 ===========
76 70
77 This variable has no effect and may be removed 71 This variable has no effect and may be removed in future kernel
78 releases. Reading it always returns 0. 72 releases. Reading it always returns 0.
79 Up to Linux 3.17, it enabled/disabled automati 73 Up to Linux 3.17, it enabled/disabled automatic recomputing of
80 `msgmni`_ 74 `msgmni`_
81 upon memory add/remove or upon IPC namespace c 75 upon memory add/remove or upon IPC namespace creation/removal.
82 Echoing "1" into this file enabled msgmni auto 76 Echoing "1" into this file enabled msgmni automatic recomputing.
83 Echoing "0" turned it off. The default value w 77 Echoing "0" turned it off. The default value was 1.
84 78
85 79
86 bootloader_type (x86 only) 80 bootloader_type (x86 only)
87 ========================== 81 ==========================
88 82
89 This gives the bootloader type number as indic 83 This gives the bootloader type number as indicated by the bootloader,
90 shifted left by 4, and OR'd with the low four 84 shifted left by 4, and OR'd with the low four bits of the bootloader
91 version. The reason for this encoding is that 85 version. The reason for this encoding is that this used to match the
92 ``type_of_loader`` field in the kernel header; 86 ``type_of_loader`` field in the kernel header; the encoding is kept for
93 backwards compatibility. That is, if the full 87 backwards compatibility. That is, if the full bootloader type number
94 is 0x15 and the full version number is 0x234, 88 is 0x15 and the full version number is 0x234, this file will contain
95 the value 340 = 0x154. 89 the value 340 = 0x154.
96 90
97 See the ``type_of_loader`` and ``ext_loader_ty 91 See the ``type_of_loader`` and ``ext_loader_type`` fields in
98 Documentation/arch/x86/boot.rst for additional !! 92 :doc:`/x86/boot` for additional information.
99 93
100 94
101 bootloader_version (x86 only) 95 bootloader_version (x86 only)
102 ============================= 96 =============================
103 97
104 The complete bootloader version number. In th 98 The complete bootloader version number. In the example above, this
105 file will contain the value 564 = 0x234. 99 file will contain the value 564 = 0x234.
106 100
107 See the ``type_of_loader`` and ``ext_loader_ve 101 See the ``type_of_loader`` and ``ext_loader_ver`` fields in
108 Documentation/arch/x86/boot.rst for additional !! 102 :doc:`/x86/boot` for additional information.
109 103
110 104
111 bpf_stats_enabled 105 bpf_stats_enabled
112 ================= 106 =================
113 107
114 Controls whether the kernel should collect sta 108 Controls whether the kernel should collect statistics on BPF programs
115 (total time spent running, number of times run 109 (total time spent running, number of times run...). Enabling
116 statistics causes a slight reduction in perfor 110 statistics causes a slight reduction in performance on each program
117 run. The statistics can be seen using ``bpftoo 111 run. The statistics can be seen using ``bpftool``.
118 112
119 = =================================== 113 = ===================================
120 0 Don't collect statistics (default). 114 0 Don't collect statistics (default).
121 1 Collect statistics. 115 1 Collect statistics.
122 = =================================== 116 = ===================================
123 117
124 118
125 cad_pid 119 cad_pid
126 ======= 120 =======
127 121
128 This is the pid which will be signalled on reb 122 This is the pid which will be signalled on reboot (notably, by
129 Ctrl-Alt-Delete). Writing a value to this file 123 Ctrl-Alt-Delete). Writing a value to this file which doesn't
130 correspond to a running process will result in 124 correspond to a running process will result in ``-ESRCH``.
131 125
132 See also `ctrl-alt-del`_. 126 See also `ctrl-alt-del`_.
133 127
134 128
135 cap_last_cap 129 cap_last_cap
136 ============ 130 ============
137 131
138 Highest valid capability of the running kernel 132 Highest valid capability of the running kernel. Exports
139 ``CAP_LAST_CAP`` from the kernel. 133 ``CAP_LAST_CAP`` from the kernel.
140 134
141 135
142 .. _core_pattern: <<
143 <<
144 core_pattern 136 core_pattern
145 ============ 137 ============
146 138
147 ``core_pattern`` is used to specify a core dum 139 ``core_pattern`` is used to specify a core dumpfile pattern name.
148 140
149 * max length 127 characters; default value is 141 * max length 127 characters; default value is "core"
150 * ``core_pattern`` is used as a pattern templa 142 * ``core_pattern`` is used as a pattern template for the output
151 filename; certain string patterns (beginning 143 filename; certain string patterns (beginning with '%') are
152 substituted with their actual values. 144 substituted with their actual values.
153 * backward compatibility with ``core_uses_pid` 145 * backward compatibility with ``core_uses_pid``:
154 146
155 If ``core_pattern`` does not include " 147 If ``core_pattern`` does not include "%p" (default does not)
156 and ``core_uses_pid`` is set, then .PI 148 and ``core_uses_pid`` is set, then .PID will be appended to
157 the filename. 149 the filename.
158 150
159 * corename format specifiers 151 * corename format specifiers
160 152
161 ======== ====================== 153 ======== ==========================================
162 %<NUL> '%' is dropped 154 %<NUL> '%' is dropped
163 %% output one '%' 155 %% output one '%'
164 %p pid 156 %p pid
165 %P global pid (init PID n 157 %P global pid (init PID namespace)
166 %i tid 158 %i tid
167 %I global tid (init PID n 159 %I global tid (init PID namespace)
168 %u uid (in initial user n 160 %u uid (in initial user namespace)
169 %g gid (in initial user n 161 %g gid (in initial user namespace)
170 %d dump mode, matches ``P 162 %d dump mode, matches ``PR_SET_DUMPABLE`` and
171 ``/proc/sys/fs/suid_du 163 ``/proc/sys/fs/suid_dumpable``
172 %s signal number 164 %s signal number
173 %t UNIX time of dump 165 %t UNIX time of dump
174 %h hostname 166 %h hostname
175 %e executable filename (m 167 %e executable filename (may be shortened, could be changed by prctl etc)
176 %f executable filename 168 %f executable filename
177 %E executable path 169 %E executable path
178 %c maximum size of core f 170 %c maximum size of core file by resource limit RLIMIT_CORE
179 %C CPU the task ran on <<
180 %<OTHER> both are dropped 171 %<OTHER> both are dropped
181 ======== ====================== 172 ======== ==========================================
182 173
183 * If the first character of the pattern is a ' 174 * If the first character of the pattern is a '|', the kernel will treat
184 the rest of the pattern as a command to run. 175 the rest of the pattern as a command to run. The core dump will be
185 written to the standard input of that progra 176 written to the standard input of that program instead of to a file.
186 177
187 178
188 core_pipe_limit 179 core_pipe_limit
189 =============== 180 ===============
190 181
191 This sysctl is only applicable when `core_patt 182 This sysctl is only applicable when `core_pattern`_ is configured to
192 pipe core files to a user space helper (when t 183 pipe core files to a user space helper (when the first character of
193 ``core_pattern`` is a '|', see above). 184 ``core_pattern`` is a '|', see above).
194 When collecting cores via a pipe to an applica 185 When collecting cores via a pipe to an application, it is occasionally
195 useful for the collecting application to gathe 186 useful for the collecting application to gather data about the
196 crashing process from its ``/proc/pid`` direct 187 crashing process from its ``/proc/pid`` directory.
197 In order to do this safely, the kernel must wa 188 In order to do this safely, the kernel must wait for the collecting
198 process to exit, so as not to remove the crash 189 process to exit, so as not to remove the crashing processes proc files
199 prematurely. 190 prematurely.
200 This in turn creates the possibility that a mi 191 This in turn creates the possibility that a misbehaving userspace
201 collecting process can block the reaping of a 192 collecting process can block the reaping of a crashed process simply
202 by never exiting. 193 by never exiting.
203 This sysctl defends against that. 194 This sysctl defends against that.
204 It defines how many concurrent crashing proces 195 It defines how many concurrent crashing processes may be piped to user
205 space applications in parallel. 196 space applications in parallel.
206 If this value is exceeded, then those crashing 197 If this value is exceeded, then those crashing processes above that
207 value are noted via the kernel log and their c 198 value are noted via the kernel log and their cores are skipped.
208 0 is a special value, indicating that unlimite 199 0 is a special value, indicating that unlimited processes may be
209 captured in parallel, but that no waiting will 200 captured in parallel, but that no waiting will take place (i.e. the
210 collecting process is not guaranteed access to 201 collecting process is not guaranteed access to ``/proc/<crashing
211 pid>/``). 202 pid>/``).
212 This value defaults to 0. 203 This value defaults to 0.
213 204
214 205
215 core_uses_pid 206 core_uses_pid
216 ============= 207 =============
217 208
218 The default coredump filename is "core". By s 209 The default coredump filename is "core". By setting
219 ``core_uses_pid`` to 1, the coredump filename 210 ``core_uses_pid`` to 1, the coredump filename becomes core.PID.
220 If `core_pattern`_ does not include "%p" (defa 211 If `core_pattern`_ does not include "%p" (default does not)
221 and ``core_uses_pid`` is set, then .PID will b 212 and ``core_uses_pid`` is set, then .PID will be appended to
222 the filename. 213 the filename.
223 214
224 215
225 ctrl-alt-del 216 ctrl-alt-del
226 ============ 217 ============
227 218
228 When the value in this file is 0, ctrl-alt-del 219 When the value in this file is 0, ctrl-alt-del is trapped and
229 sent to the ``init(1)`` program to handle a gr 220 sent to the ``init(1)`` program to handle a graceful restart.
230 When, however, the value is > 0, Linux's react 221 When, however, the value is > 0, Linux's reaction to a Vulcan
231 Nerve Pinch (tm) will be an immediate reboot, 222 Nerve Pinch (tm) will be an immediate reboot, without even
232 syncing its dirty buffers. 223 syncing its dirty buffers.
233 224
234 Note: 225 Note:
235 when a program (like dosemu) has the keyboar 226 when a program (like dosemu) has the keyboard in 'raw'
236 mode, the ctrl-alt-del is intercepted by the 227 mode, the ctrl-alt-del is intercepted by the program before it
237 ever reaches the kernel tty layer, and it's 228 ever reaches the kernel tty layer, and it's up to the program
238 to decide what to do with it. 229 to decide what to do with it.
239 230
240 231
241 dmesg_restrict 232 dmesg_restrict
242 ============== 233 ==============
243 234
244 This toggle indicates whether unprivileged use 235 This toggle indicates whether unprivileged users are prevented
245 from using ``dmesg(8)`` to view messages from 236 from using ``dmesg(8)`` to view messages from the kernel's log
246 buffer. 237 buffer.
247 When ``dmesg_restrict`` is set to 0 there are 238 When ``dmesg_restrict`` is set to 0 there are no restrictions.
248 When ``dmesg_restrict`` is set to 1, users mus 239 When ``dmesg_restrict`` is set to 1, users must have
249 ``CAP_SYSLOG`` to use ``dmesg(8)``. 240 ``CAP_SYSLOG`` to use ``dmesg(8)``.
250 241
251 The kernel config option ``CONFIG_SECURITY_DME 242 The kernel config option ``CONFIG_SECURITY_DMESG_RESTRICT`` sets the
252 default value of ``dmesg_restrict``. 243 default value of ``dmesg_restrict``.
253 244
254 245
255 domainname & hostname 246 domainname & hostname
256 ===================== 247 =====================
257 248
258 These files can be used to set the NIS/YP doma 249 These files can be used to set the NIS/YP domainname and the
259 hostname of your box in exactly the same way a 250 hostname of your box in exactly the same way as the commands
260 domainname and hostname, i.e.:: 251 domainname and hostname, i.e.::
261 252
262 # echo "darkstar" > /proc/sys/kernel/h 253 # echo "darkstar" > /proc/sys/kernel/hostname
263 # echo "mydomain" > /proc/sys/kernel/d 254 # echo "mydomain" > /proc/sys/kernel/domainname
264 255
265 has the same effect as:: 256 has the same effect as::
266 257
267 # hostname "darkstar" 258 # hostname "darkstar"
268 # domainname "mydomain" 259 # domainname "mydomain"
269 260
270 Note, however, that the classic darkstar.frop. 261 Note, however, that the classic darkstar.frop.org has the
271 hostname "darkstar" and DNS (Internet Domain N 262 hostname "darkstar" and DNS (Internet Domain Name Server)
272 domainname "frop.org", not to be confused with 263 domainname "frop.org", not to be confused with the NIS (Network
273 Information Service) or YP (Yellow Pages) doma 264 Information Service) or YP (Yellow Pages) domainname. These two
274 domain names are in general different. For a d 265 domain names are in general different. For a detailed discussion
275 see the ``hostname(1)`` man page. 266 see the ``hostname(1)`` man page.
276 267
277 268
278 firmware_config 269 firmware_config
279 =============== 270 ===============
280 271
281 See Documentation/driver-api/firmware/fallback !! 272 See :doc:`/driver-api/firmware/fallback-mechanisms`.
282 273
283 The entries in this directory allow the firmwa 274 The entries in this directory allow the firmware loader helper
284 fallback to be controlled: 275 fallback to be controlled:
285 276
286 * ``force_sysfs_fallback``, when set to 1, for 277 * ``force_sysfs_fallback``, when set to 1, forces the use of the
287 fallback; 278 fallback;
288 * ``ignore_sysfs_fallback``, when set to 1, ig 279 * ``ignore_sysfs_fallback``, when set to 1, ignores any fallback.
289 280
290 281
291 ftrace_dump_on_oops 282 ftrace_dump_on_oops
292 =================== 283 ===================
293 284
294 Determines whether ``ftrace_dump()`` should be 285 Determines whether ``ftrace_dump()`` should be called on an oops (or
295 kernel panic). This will output the contents o 286 kernel panic). This will output the contents of the ftrace buffers to
296 the console. This is very useful for capturin 287 the console. This is very useful for capturing traces that lead to
297 crashes and outputting them to a serial consol 288 crashes and outputting them to a serial console.
298 289
299 ======================= ====================== !! 290 = ===================================================
300 0 Disabled (default). !! 291 0 Disabled (default).
301 1 Dump buffers of all CP !! 292 1 Dump buffers of all CPUs.
302 2(orig_cpu) Dump the buffer of the !! 293 2 Dump the buffer of the CPU that triggered the oops.
303 oops. !! 294 = ===================================================
304 <instance> Dump the specific inst <<
305 <instance>=2(orig_cpu) Dump the specific inst <<
306 that triggered the oop <<
307 ======================= ====================== <<
308 <<
309 Multiple instance dump is also supported, and <<
310 by commas. If global buffer also needs to be d <<
311 the dump mode (1/2/orig_cpu) first for global <<
312 <<
313 So for example to dump "foo" and "bar" instanc <<
314 user can:: <<
315 <<
316 echo "foo,bar" > /proc/sys/kernel/ftrace_dum <<
317 <<
318 To dump global buffer and "foo" instance buffe <<
319 CPUs along with the "bar" instance buffer on C <<
320 oops, user can:: <<
321 295
322 echo "1,foo,bar=2" > /proc/sys/kernel/ftrace <<
323 296
324 ftrace_enabled, stack_tracer_enabled 297 ftrace_enabled, stack_tracer_enabled
325 ==================================== 298 ====================================
326 299
327 See Documentation/trace/ftrace.rst. !! 300 See :doc:`/trace/ftrace`.
328 301
329 302
330 hardlockup_all_cpu_backtrace 303 hardlockup_all_cpu_backtrace
331 ============================ 304 ============================
332 305
333 This value controls the hard lockup detector b 306 This value controls the hard lockup detector behavior when a hard
334 lockup condition is detected as to whether or 307 lockup condition is detected as to whether or not to gather further
335 debug information. If enabled, arch-specific a 308 debug information. If enabled, arch-specific all-CPU stack dumping
336 will be initiated. 309 will be initiated.
337 310
338 = ============================================ 311 = ============================================
339 0 Do nothing. This is the default behavior. 312 0 Do nothing. This is the default behavior.
340 1 On detection capture more debug information. 313 1 On detection capture more debug information.
341 = ============================================ 314 = ============================================
342 315
343 316
344 hardlockup_panic 317 hardlockup_panic
345 ================ 318 ================
346 319
347 This parameter can be used to control whether 320 This parameter can be used to control whether the kernel panics
348 when a hard lockup is detected. 321 when a hard lockup is detected.
349 322
350 = =========================== 323 = ===========================
351 0 Don't panic on hard lockup. 324 0 Don't panic on hard lockup.
352 1 Panic on hard lockup. 325 1 Panic on hard lockup.
353 = =========================== 326 = ===========================
354 327
355 See Documentation/admin-guide/lockup-watchdogs !! 328 See :doc:`/admin-guide/lockup-watchdogs` for more information.
356 This can also be set using the nmi_watchdog ke 329 This can also be set using the nmi_watchdog kernel parameter.
357 330
358 331
359 hotplug 332 hotplug
360 ======= 333 =======
361 334
362 Path for the hotplug policy agent. 335 Path for the hotplug policy agent.
363 Default value is ``CONFIG_UEVENT_HELPER_PATH`` !! 336 Default value is "``/sbin/hotplug``".
364 to the empty string. <<
365 <<
366 This file only exists when ``CONFIG_UEVENT_HEL <<
367 modern systems rely exclusively on the netlink <<
368 don't need this. <<
369 337
370 338
371 hung_task_all_cpu_backtrace 339 hung_task_all_cpu_backtrace
372 =========================== 340 ===========================
373 341
374 If this option is set, the kernel will send an 342 If this option is set, the kernel will send an NMI to all CPUs to dump
375 their backtraces when a hung task is detected. 343 their backtraces when a hung task is detected. This file shows up if
376 CONFIG_DETECT_HUNG_TASK and CONFIG_SMP are ena 344 CONFIG_DETECT_HUNG_TASK and CONFIG_SMP are enabled.
377 345
378 0: Won't show all CPUs backtraces when a hung 346 0: Won't show all CPUs backtraces when a hung task is detected.
379 This is the default behavior. 347 This is the default behavior.
380 348
381 1: Will non-maskably interrupt all CPUs and du 349 1: Will non-maskably interrupt all CPUs and dump their backtraces when
382 a hung task is detected. 350 a hung task is detected.
383 351
384 352
385 hung_task_panic 353 hung_task_panic
386 =============== 354 ===============
387 355
388 Controls the kernel's behavior when a hung tas 356 Controls the kernel's behavior when a hung task is detected.
389 This file shows up if ``CONFIG_DETECT_HUNG_TAS 357 This file shows up if ``CONFIG_DETECT_HUNG_TASK`` is enabled.
390 358
391 = ============================================ 359 = =================================================
392 0 Continue operation. This is the default beha 360 0 Continue operation. This is the default behavior.
393 1 Panic immediately. 361 1 Panic immediately.
394 = ============================================ 362 = =================================================
395 363
396 364
397 hung_task_check_count 365 hung_task_check_count
398 ===================== 366 =====================
399 367
400 The upper bound on the number of tasks that ar 368 The upper bound on the number of tasks that are checked.
401 This file shows up if ``CONFIG_DETECT_HUNG_TAS 369 This file shows up if ``CONFIG_DETECT_HUNG_TASK`` is enabled.
402 370
403 371
404 hung_task_timeout_secs 372 hung_task_timeout_secs
405 ====================== 373 ======================
406 374
407 When a task in D state did not get scheduled 375 When a task in D state did not get scheduled
408 for more than this value report a warning. 376 for more than this value report a warning.
409 This file shows up if ``CONFIG_DETECT_HUNG_TAS 377 This file shows up if ``CONFIG_DETECT_HUNG_TASK`` is enabled.
410 378
411 0 means infinite timeout, no checking is done. 379 0 means infinite timeout, no checking is done.
412 380
413 Possible values to set are in range {0:``LONG_ 381 Possible values to set are in range {0:``LONG_MAX``/``HZ``}.
414 382
415 383
416 hung_task_check_interval_secs 384 hung_task_check_interval_secs
417 ============================= 385 =============================
418 386
419 Hung task check interval. If hung task checkin 387 Hung task check interval. If hung task checking is enabled
420 (see `hung_task_timeout_secs`_), the check is 388 (see `hung_task_timeout_secs`_), the check is done every
421 ``hung_task_check_interval_secs`` seconds. 389 ``hung_task_check_interval_secs`` seconds.
422 This file shows up if ``CONFIG_DETECT_HUNG_TAS 390 This file shows up if ``CONFIG_DETECT_HUNG_TASK`` is enabled.
423 391
424 0 (default) means use ``hung_task_timeout_secs 392 0 (default) means use ``hung_task_timeout_secs`` as checking
425 interval. 393 interval.
426 394
427 Possible values to set are in range {0:``LONG_ 395 Possible values to set are in range {0:``LONG_MAX``/``HZ``}.
428 396
429 397
430 hung_task_warnings 398 hung_task_warnings
431 ================== 399 ==================
432 400
433 The maximum number of warnings to report. Duri 401 The maximum number of warnings to report. During a check interval
434 if a hung task is detected, this value is decr 402 if a hung task is detected, this value is decreased by 1.
435 When this value reaches 0, no more warnings wi 403 When this value reaches 0, no more warnings will be reported.
436 This file shows up if ``CONFIG_DETECT_HUNG_TAS 404 This file shows up if ``CONFIG_DETECT_HUNG_TASK`` is enabled.
437 405
438 -1: report an infinite number of warnings. 406 -1: report an infinite number of warnings.
439 407
440 408
441 hyperv_record_panic_msg 409 hyperv_record_panic_msg
442 ======================= 410 =======================
443 411
444 Controls whether the panic kmsg data should be 412 Controls whether the panic kmsg data should be reported to Hyper-V.
445 413
446 = ============================================ 414 = =========================================================
447 0 Do not report panic kmsg data. 415 0 Do not report panic kmsg data.
448 1 Report the panic kmsg data. This is the defa 416 1 Report the panic kmsg data. This is the default behavior.
449 = ============================================ 417 = =========================================================
450 418
451 419
452 ignore-unaligned-usertrap 420 ignore-unaligned-usertrap
453 ========================= 421 =========================
454 422
455 On architectures where unaligned accesses caus 423 On architectures where unaligned accesses cause traps, and where this
456 feature is supported (``CONFIG_SYSCTL_ARCH_UNA 424 feature is supported (``CONFIG_SYSCTL_ARCH_UNALIGN_NO_WARN``;
457 currently, ``arc``, ``parisc`` and ``loongarch !! 425 currently, ``arc`` and ``ia64``), controls whether all unaligned traps
458 unaligned traps are logged. !! 426 are logged.
459 427
460 = ============================================ 428 = =============================================================
461 0 Log all unaligned accesses. 429 0 Log all unaligned accesses.
462 1 Only warn the first time a process traps. Th 430 1 Only warn the first time a process traps. This is the default
463 setting. 431 setting.
464 = ============================================ 432 = =============================================================
465 433
466 See also `unaligned-trap`_. !! 434 See also `unaligned-trap`_ and `unaligned-dump-stack`_. On ``ia64``,
467 !! 435 this allows system administrators to override the
468 io_uring_disabled !! 436 ``IA64_THREAD_UAC_NOPRINT`` ``prctl`` and avoid logs being flooded.
469 ================= <<
470 <<
471 Prevents all processes from creating new io_ur <<
472 shrinks the kernel's attack surface. <<
473 <<
474 = ============================================ <<
475 0 All processes can create io_uring instances <<
476 default setting. <<
477 1 io_uring creation is disabled (io_uring_setu <<
478 -EPERM) for unprivileged processes not in th <<
479 Existing io_uring instances can still be use <<
480 documentation for io_uring_group for more in <<
481 2 io_uring creation is disabled for all proces <<
482 always fails with -EPERM. Existing io_uring <<
483 used. <<
484 = ============================================ <<
485 <<
486 <<
487 io_uring_group <<
488 ============== <<
489 <<
490 When io_uring_disabled is set to 1, a process <<
491 privileged (CAP_SYS_ADMIN) or be in the io_uri <<
492 to create an io_uring instance. If io_uring_g <<
493 default), only processes with the CAP_SYS_ADMI <<
494 io_uring instances. <<
495 437
496 438
497 kexec_load_disabled 439 kexec_load_disabled
498 =================== 440 ===================
499 441
500 A toggle indicating if the syscalls ``kexec_lo !! 442 A toggle indicating if the ``kexec_load`` syscall has been disabled.
501 ``kexec_file_load`` have been disabled. !! 443 This value defaults to 0 (false: ``kexec_load`` enabled), but can be
502 This value defaults to 0 (false: ``kexec_*load !! 444 set to 1 (true: ``kexec_load`` disabled).
503 set to 1 (true: ``kexec_*load`` disabled). <<
504 Once true, kexec can no longer be used, and th 445 Once true, kexec can no longer be used, and the toggle cannot be set
505 back to false. 446 back to false.
506 This allows a kexec image to be loaded before 447 This allows a kexec image to be loaded before disabling the syscall,
507 allowing a system to set up (and later use) an 448 allowing a system to set up (and later use) an image without it being
508 altered. 449 altered.
509 Generally used together with the `modules_disa 450 Generally used together with the `modules_disabled`_ sysctl.
510 451
511 kexec_load_limit_panic <<
512 ====================== <<
513 <<
514 This parameter specifies a limit to the number <<
515 ``kexec_load`` and ``kexec_file_load`` can be <<
516 image. It can only be set with a more restrict <<
517 current one. <<
518 <<
519 == =========================================== <<
520 -1 Unlimited calls to kexec. This is the defau <<
521 N Number of calls left. <<
522 == =========================================== <<
523 <<
524 kexec_load_limit_reboot <<
525 ======================= <<
526 <<
527 Similar functionality as ``kexec_load_limit_pa <<
528 image. <<
529 452
530 kptr_restrict 453 kptr_restrict
531 ============= 454 =============
532 455
533 This toggle indicates whether restrictions are 456 This toggle indicates whether restrictions are placed on
534 exposing kernel addresses via ``/proc`` and ot 457 exposing kernel addresses via ``/proc`` and other interfaces.
535 458
536 When ``kptr_restrict`` is set to 0 (the defaul 459 When ``kptr_restrict`` is set to 0 (the default) the address is hashed
537 before printing. 460 before printing.
538 (This is the equivalent to %p.) 461 (This is the equivalent to %p.)
539 462
540 When ``kptr_restrict`` is set to 1, kernel poi 463 When ``kptr_restrict`` is set to 1, kernel pointers printed using the
541 %pK format specifier will be replaced with 0s 464 %pK format specifier will be replaced with 0s unless the user has
542 ``CAP_SYSLOG`` and effective user and group id 465 ``CAP_SYSLOG`` and effective user and group ids are equal to the real
543 ids. 466 ids.
544 This is because %pK checks are done at read() 467 This is because %pK checks are done at read() time rather than open()
545 time, so if permissions are elevated between t 468 time, so if permissions are elevated between the open() and the read()
546 (e.g via a setuid binary) then %pK will not le 469 (e.g via a setuid binary) then %pK will not leak kernel pointers to
547 unprivileged users. 470 unprivileged users.
548 Note, this is a temporary solution only. 471 Note, this is a temporary solution only.
549 The correct long-term solution is to do the pe 472 The correct long-term solution is to do the permission checks at
550 open() time. 473 open() time.
551 Consider removing world read permissions from 474 Consider removing world read permissions from files that use %pK, and
552 using `dmesg_restrict`_ to protect against use 475 using `dmesg_restrict`_ to protect against uses of %pK in ``dmesg(8)``
553 if leaking kernel pointer values to unprivileg 476 if leaking kernel pointer values to unprivileged users is a concern.
554 477
555 When ``kptr_restrict`` is set to 2, kernel poi 478 When ``kptr_restrict`` is set to 2, kernel pointers printed using
556 %pK will be replaced with 0s regardless of pri 479 %pK will be replaced with 0s regardless of privileges.
557 480
558 481
559 modprobe 482 modprobe
560 ======== 483 ========
561 484
562 The full path to the usermode helper for autol 485 The full path to the usermode helper for autoloading kernel modules,
563 by default ``CONFIG_MODPROBE_PATH``, which in 486 by default ``CONFIG_MODPROBE_PATH``, which in turn defaults to
564 "/sbin/modprobe". This binary is executed whe 487 "/sbin/modprobe". This binary is executed when the kernel requests a
565 module. For example, if userspace passes an u 488 module. For example, if userspace passes an unknown filesystem type
566 to mount(), then the kernel will automatically 489 to mount(), then the kernel will automatically request the
567 corresponding filesystem module by executing t 490 corresponding filesystem module by executing this usermode helper.
568 This usermode helper should insert the needed 491 This usermode helper should insert the needed module into the kernel.
569 492
570 This sysctl only affects module autoloading. 493 This sysctl only affects module autoloading. It has no effect on the
571 ability to explicitly insert modules. 494 ability to explicitly insert modules.
572 495
573 This sysctl can be used to debug module loadin 496 This sysctl can be used to debug module loading requests::
574 497
575 echo '#! /bin/sh' > /tmp/modprobe 498 echo '#! /bin/sh' > /tmp/modprobe
576 echo 'echo "$@" >> /tmp/modprobe.log' >> / 499 echo 'echo "$@" >> /tmp/modprobe.log' >> /tmp/modprobe
577 echo 'exec /sbin/modprobe "$@"' >> /tmp/mo 500 echo 'exec /sbin/modprobe "$@"' >> /tmp/modprobe
578 chmod a+x /tmp/modprobe 501 chmod a+x /tmp/modprobe
579 echo /tmp/modprobe > /proc/sys/kernel/modp 502 echo /tmp/modprobe > /proc/sys/kernel/modprobe
580 503
581 Alternatively, if this sysctl is set to the em 504 Alternatively, if this sysctl is set to the empty string, then module
582 autoloading is completely disabled. The kerne 505 autoloading is completely disabled. The kernel will not try to
583 execute a usermode helper at all, nor will it 506 execute a usermode helper at all, nor will it call the
584 kernel_module_request LSM hook. 507 kernel_module_request LSM hook.
585 508
586 If CONFIG_STATIC_USERMODEHELPER=y is set in th 509 If CONFIG_STATIC_USERMODEHELPER=y is set in the kernel configuration,
587 then the configured static usermode helper ove 510 then the configured static usermode helper overrides this sysctl,
588 except that the empty string is still accepted 511 except that the empty string is still accepted to completely disable
589 module autoloading as described above. 512 module autoloading as described above.
590 513
591 modules_disabled 514 modules_disabled
592 ================ 515 ================
593 516
594 A toggle value indicating if modules are allow 517 A toggle value indicating if modules are allowed to be loaded
595 in an otherwise modular kernel. This toggle d 518 in an otherwise modular kernel. This toggle defaults to off
596 (0), but can be set true (1). Once true, modu 519 (0), but can be set true (1). Once true, modules can be
597 neither loaded nor unloaded, and the toggle ca 520 neither loaded nor unloaded, and the toggle cannot be set back
598 to false. Generally used with the `kexec_load 521 to false. Generally used with the `kexec_load_disabled`_ toggle.
599 522
600 523
601 .. _msgmni: 524 .. _msgmni:
602 525
603 msgmax, msgmnb, and msgmni 526 msgmax, msgmnb, and msgmni
604 ========================== 527 ==========================
605 528
606 ``msgmax`` is the maximum size of an IPC messa 529 ``msgmax`` is the maximum size of an IPC message, in bytes. 8192 by
607 default (``MSGMAX``). 530 default (``MSGMAX``).
608 531
609 ``msgmnb`` is the maximum size of an IPC queue 532 ``msgmnb`` is the maximum size of an IPC queue, in bytes. 16384 by
610 default (``MSGMNB``). 533 default (``MSGMNB``).
611 534
612 ``msgmni`` is the maximum number of IPC queues 535 ``msgmni`` is the maximum number of IPC queues. 32000 by default
613 (``MSGMNI``). 536 (``MSGMNI``).
614 537
615 All of these parameters are set per ipc namesp <<
616 in POSIX message queues is limited by ``RLIMIT <<
617 respected hierarchically in the each user name <<
618 538
619 msg_next_id, sem_next_id, and shm_next_id (Sys 539 msg_next_id, sem_next_id, and shm_next_id (System V IPC)
620 ============================================== 540 ========================================================
621 541
622 These three toggles allows to specify desired 542 These three toggles allows to specify desired id for next allocated IPC
623 object: message, semaphore or shared memory re 543 object: message, semaphore or shared memory respectively.
624 544
625 By default they are equal to -1, which means g 545 By default they are equal to -1, which means generic allocation logic.
626 Possible values to set are in range {0:``INT_M 546 Possible values to set are in range {0:``INT_MAX``}.
627 547
628 Notes: 548 Notes:
629 1) kernel doesn't guarantee, that new object 549 1) kernel doesn't guarantee, that new object will have desired id. So,
630 it's up to userspace, how to handle an ob 550 it's up to userspace, how to handle an object with "wrong" id.
631 2) Toggle with non-default value will be set 551 2) Toggle with non-default value will be set back to -1 by kernel after
632 successful IPC object allocation. If an I 552 successful IPC object allocation. If an IPC object allocation syscall
633 fails, it is undefined if the value remai 553 fails, it is undefined if the value remains unmodified or is reset to -1.
634 554
635 555
636 ngroups_max 556 ngroups_max
637 =========== 557 ===========
638 558
639 Maximum number of supplementary groups, _i.e._ 559 Maximum number of supplementary groups, _i.e._ the maximum size which
640 ``setgroups`` will accept. Exports ``NGROUPS_M 560 ``setgroups`` will accept. Exports ``NGROUPS_MAX`` from the kernel.
641 561
642 562
643 563
644 nmi_watchdog 564 nmi_watchdog
645 ============ 565 ============
646 566
647 This parameter can be used to control the NMI 567 This parameter can be used to control the NMI watchdog
648 (i.e. the hard lockup detector) on x86 systems 568 (i.e. the hard lockup detector) on x86 systems.
649 569
650 = ================================= 570 = =================================
651 0 Disable the hard lockup detector. 571 0 Disable the hard lockup detector.
652 1 Enable the hard lockup detector. 572 1 Enable the hard lockup detector.
653 = ================================= 573 = =================================
654 574
655 The hard lockup detector monitors each CPU for 575 The hard lockup detector monitors each CPU for its ability to respond to
656 timer interrupts. The mechanism utilizes CPU p 576 timer interrupts. The mechanism utilizes CPU performance counter registers
657 that are programmed to generate Non-Maskable I 577 that are programmed to generate Non-Maskable Interrupts (NMIs) periodically
658 while a CPU is busy. Hence, the alternative na 578 while a CPU is busy. Hence, the alternative name 'NMI watchdog'.
659 579
660 The NMI watchdog is disabled by default if the 580 The NMI watchdog is disabled by default if the kernel is running as a guest
661 in a KVM virtual machine. This default can be 581 in a KVM virtual machine. This default can be overridden by adding::
662 582
663 nmi_watchdog=1 583 nmi_watchdog=1
664 584
665 to the guest kernel command line (see !! 585 to the guest kernel command line (see :doc:`/admin-guide/kernel-parameters`).
666 Documentation/admin-guide/kernel-parameters.rs <<
667 <<
668 <<
669 nmi_wd_lpm_factor (PPC only) <<
670 ============================ <<
671 <<
672 Factor to apply to the NMI watchdog timeout (o <<
673 set to 1). This factor represents the percenta <<
674 ``watchdog_thresh`` when calculating the NMI w <<
675 LPM. The soft lockup timeout is not impacted. <<
676 <<
677 A value of 0 means no change. The default valu <<
678 watchdog is set to 30s (based on ``watchdog_th <<
679 586
680 587
681 numa_balancing 588 numa_balancing
682 ============== 589 ==============
683 590
684 Enables/disables and configures automatic page !! 591 Enables/disables automatic page fault based NUMA memory
685 balancing. Memory is moved automatically to n !! 592 balancing. Memory is moved automatically to nodes
686 The value to set can be the result of ORing th !! 593 that access it often.
687 !! 594
688 = ================================= !! 595 Enables/disables automatic NUMA memory balancing. On NUMA machines, there
689 0 NUMA_BALANCING_DISABLED !! 596 is a performance penalty if remote memory is accessed by a CPU. When this
690 1 NUMA_BALANCING_NORMAL !! 597 feature is enabled the kernel samples what task thread is accessing memory
691 2 NUMA_BALANCING_MEMORY_TIERING !! 598 by periodically unmapping pages and later trapping a page fault. At the
692 = ================================= !! 599 time of the page fault, it is determined if the data being accessed should
693 !! 600 be migrated to a local memory node.
694 Or NUMA_BALANCING_NORMAL to optimize page plac <<
695 NUMA nodes to reduce remote accessing. On NUM <<
696 performance penalty if remote memory is access <<
697 feature is enabled the kernel samples what tas <<
698 memory by periodically unmapping pages and lat <<
699 fault. At the time of the page fault, it is de <<
700 being accessed should be migrated to a local m <<
701 601
702 The unmapping of pages and trapping faults inc 602 The unmapping of pages and trapping faults incur additional overhead that
703 ideally is offset by improved memory locality 603 ideally is offset by improved memory locality but there is no universal
704 guarantee. If the target workload is already b 604 guarantee. If the target workload is already bound to NUMA nodes then this
705 feature should be disabled. !! 605 feature should be disabled. Otherwise, if the system overhead from the
>> 606 feature is too high then the rate the kernel samples for NUMA hinting
>> 607 faults may be controlled by the `numa_balancing_scan_period_min_ms,
>> 608 numa_balancing_scan_delay_ms, numa_balancing_scan_period_max_ms,
>> 609 numa_balancing_scan_size_mb`_, and numa_balancing_settle_count sysctls.
>> 610
>> 611
>> 612 numa_balancing_scan_period_min_ms, numa_balancing_scan_delay_ms, numa_balancing_scan_period_max_ms, numa_balancing_scan_size_mb
>> 613 ===============================================================================================================================
>> 614
>> 615
>> 616 Automatic NUMA balancing scans tasks address space and unmaps pages to
>> 617 detect if pages are properly placed or if the data should be migrated to a
>> 618 memory node local to where the task is running. Every "scan delay" the task
>> 619 scans the next "scan size" number of pages in its address space. When the
>> 620 end of the address space is reached the scanner restarts from the beginning.
>> 621
>> 622 In combination, the "scan delay" and "scan size" determine the scan rate.
>> 623 When "scan delay" decreases, the scan rate increases. The scan delay and
>> 624 hence the scan rate of every task is adaptive and depends on historical
>> 625 behaviour. If pages are properly placed then the scan delay increases,
>> 626 otherwise the scan delay decreases. The "scan size" is not adaptive but
>> 627 the higher the "scan size", the higher the scan rate.
>> 628
>> 629 Higher scan rates incur higher system overhead as page faults must be
>> 630 trapped and potentially data must be migrated. However, the higher the scan
>> 631 rate, the more quickly a tasks memory is migrated to a local node if the
>> 632 workload pattern changes and minimises performance impact due to remote
>> 633 memory accesses. These sysctls control the thresholds for scan delays and
>> 634 the number of pages scanned.
>> 635
>> 636 ``numa_balancing_scan_period_min_ms`` is the minimum time in milliseconds to
>> 637 scan a tasks virtual memory. It effectively controls the maximum scanning
>> 638 rate for each task.
>> 639
>> 640 ``numa_balancing_scan_delay_ms`` is the starting "scan delay" used for a task
>> 641 when it initially forks.
>> 642
>> 643 ``numa_balancing_scan_period_max_ms`` is the maximum time in milliseconds to
>> 644 scan a tasks virtual memory. It effectively controls the minimum scanning
>> 645 rate for each task.
706 646
707 Or NUMA_BALANCING_MEMORY_TIERING to optimize p !! 647 ``numa_balancing_scan_size_mb`` is how many megabytes worth of pages are
708 different types of memory (represented as diff !! 648 scanned for a given scan.
709 place the hot pages in the fast memory. This <<
710 unmapping and page fault too. <<
711 <<
712 numa_balancing_promote_rate_limit_MBps <<
713 ====================================== <<
714 <<
715 Too high promotion/demotion throughput between <<
716 may hurt application latency. This can be use <<
717 promotion throughput. The per-node max promot <<
718 will be limited to be no more than the set val <<
719 649
720 A rule of thumb is to set this to less than 1/ <<
721 write bandwidth. <<
722 650
723 oops_all_cpu_backtrace 651 oops_all_cpu_backtrace
724 ====================== 652 ======================
725 653
726 If this option is set, the kernel will send an 654 If this option is set, the kernel will send an NMI to all CPUs to dump
727 their backtraces when an oops event occurs. It 655 their backtraces when an oops event occurs. It should be used as a last
728 resort in case a panic cannot be triggered (to 656 resort in case a panic cannot be triggered (to protect VMs running, for
729 example) or kdump can't be collected. This fil 657 example) or kdump can't be collected. This file shows up if CONFIG_SMP
730 is enabled. 658 is enabled.
731 659
732 0: Won't show all CPUs backtraces when an oops 660 0: Won't show all CPUs backtraces when an oops is detected.
733 This is the default behavior. 661 This is the default behavior.
734 662
735 1: Will non-maskably interrupt all CPUs and du 663 1: Will non-maskably interrupt all CPUs and dump their backtraces when
736 an oops event is detected. 664 an oops event is detected.
737 665
738 666
739 oops_limit <<
740 ========== <<
741 <<
742 Number of kernel oopses after which the kernel <<
743 ``panic_on_oops`` is not set. Setting this to <<
744 the count. Setting this to 1 has the same eff <<
745 ``panic_on_oops=1``. The default value is 1000 <<
746 <<
747 <<
748 osrelease, ostype & version 667 osrelease, ostype & version
749 =========================== 668 ===========================
750 669
751 :: 670 ::
752 671
753 # cat osrelease 672 # cat osrelease
754 2.1.88 673 2.1.88
755 # cat ostype 674 # cat ostype
756 Linux 675 Linux
757 # cat version 676 # cat version
758 #5 Wed Feb 25 21:49:24 MET 1998 677 #5 Wed Feb 25 21:49:24 MET 1998
759 678
760 The files ``osrelease`` and ``ostype`` should 679 The files ``osrelease`` and ``ostype`` should be clear enough.
761 ``version`` 680 ``version``
762 needs a little more clarification however. The 681 needs a little more clarification however. The '#5' means that
763 this is the fifth kernel built from this sourc 682 this is the fifth kernel built from this source base and the
764 date behind it indicates the time the kernel w 683 date behind it indicates the time the kernel was built.
765 The only way to tune these values is to rebuil 684 The only way to tune these values is to rebuild the kernel :-)
766 685
767 686
768 overflowgid & overflowuid 687 overflowgid & overflowuid
769 ========================= 688 =========================
770 689
771 if your architecture did not always support 32 690 if your architecture did not always support 32-bit UIDs (i.e. arm,
772 i386, m68k, sh, and sparc32), a fixed UID and 691 i386, m68k, sh, and sparc32), a fixed UID and GID will be returned to
773 applications that use the old 16-bit UID/GID s 692 applications that use the old 16-bit UID/GID system calls, if the
774 actual UID or GID would exceed 65535. 693 actual UID or GID would exceed 65535.
775 694
776 These sysctls allow you to change the value of 695 These sysctls allow you to change the value of the fixed UID and GID.
777 The default is 65534. 696 The default is 65534.
778 697
779 698
780 panic 699 panic
781 ===== 700 =====
782 701
783 The value in this file determines the behaviou 702 The value in this file determines the behaviour of the kernel on a
784 panic: 703 panic:
785 704
786 * if zero, the kernel will loop forever; 705 * if zero, the kernel will loop forever;
787 * if negative, the kernel will reboot immediat 706 * if negative, the kernel will reboot immediately;
788 * if positive, the kernel will reboot after th 707 * if positive, the kernel will reboot after the corresponding number
789 of seconds. 708 of seconds.
790 709
791 When you use the software watchdog, the recomm 710 When you use the software watchdog, the recommended setting is 60.
792 711
793 712
794 panic_on_io_nmi 713 panic_on_io_nmi
795 =============== 714 ===============
796 715
797 Controls the kernel's behavior when a CPU rece 716 Controls the kernel's behavior when a CPU receives an NMI caused by
798 an IO error. 717 an IO error.
799 718
800 = ============================================ 719 = ==================================================================
801 0 Try to continue operation (default). 720 0 Try to continue operation (default).
802 1 Panic immediately. The IO error triggered an 721 1 Panic immediately. The IO error triggered an NMI. This indicates a
803 serious system condition which could result 722 serious system condition which could result in IO data corruption.
804 Rather than continuing, panicking might be a 723 Rather than continuing, panicking might be a better choice. Some
805 servers issue this sort of NMI when the dump 724 servers issue this sort of NMI when the dump button is pushed,
806 and you can use this option to take a crash 725 and you can use this option to take a crash dump.
807 = ============================================ 726 = ==================================================================
808 727
809 728
810 panic_on_oops 729 panic_on_oops
811 ============= 730 =============
812 731
813 Controls the kernel's behaviour when an oops o 732 Controls the kernel's behaviour when an oops or BUG is encountered.
814 733
815 = ============================================ 734 = ===================================================================
816 0 Try to continue operation. 735 0 Try to continue operation.
817 1 Panic immediately. If the `panic` sysctl is 736 1 Panic immediately. If the `panic` sysctl is also non-zero then the
818 machine will be rebooted. 737 machine will be rebooted.
819 = ============================================ 738 = ===================================================================
820 739
821 740
822 panic_on_stackoverflow 741 panic_on_stackoverflow
823 ====================== 742 ======================
824 743
825 Controls the kernel's behavior when detecting 744 Controls the kernel's behavior when detecting the overflows of
826 kernel, IRQ and exception stacks except a user 745 kernel, IRQ and exception stacks except a user stack.
827 This file shows up if ``CONFIG_DEBUG_STACKOVER 746 This file shows up if ``CONFIG_DEBUG_STACKOVERFLOW`` is enabled.
828 747
829 = ========================== 748 = ==========================
830 0 Try to continue operation. 749 0 Try to continue operation.
831 1 Panic immediately. 750 1 Panic immediately.
832 = ========================== 751 = ==========================
833 752
834 753
835 panic_on_unrecovered_nmi 754 panic_on_unrecovered_nmi
836 ======================== 755 ========================
837 756
838 The default Linux behaviour on an NMI of eithe 757 The default Linux behaviour on an NMI of either memory or unknown is
839 to continue operation. For many environments s 758 to continue operation. For many environments such as scientific
840 computing it is preferable that the box is tak 759 computing it is preferable that the box is taken out and the error
841 dealt with than an uncorrected parity/ECC erro 760 dealt with than an uncorrected parity/ECC error get propagated.
842 761
843 A small number of systems do generate NMIs for 762 A small number of systems do generate NMIs for bizarre random reasons
844 such as power management so the default is off 763 such as power management so the default is off. That sysctl works like
845 the existing panic controls already in that di 764 the existing panic controls already in that directory.
846 765
847 766
848 panic_on_warn 767 panic_on_warn
849 ============= 768 =============
850 769
851 Calls panic() in the WARN() path when set to 1 770 Calls panic() in the WARN() path when set to 1. This is useful to avoid
852 a kernel rebuild when attempting to kdump at t 771 a kernel rebuild when attempting to kdump at the location of a WARN().
853 772
854 = ============================================ 773 = ================================================
855 0 Only WARN(), default behaviour. 774 0 Only WARN(), default behaviour.
856 1 Call panic() after printing out WARN() locat 775 1 Call panic() after printing out WARN() location.
857 = ============================================ 776 = ================================================
858 777
859 778
860 panic_print 779 panic_print
861 =========== 780 ===========
862 781
863 Bitmask for printing system info when panic ha 782 Bitmask for printing system info when panic happens. User can chose
864 combination of the following bits: 783 combination of the following bits:
865 784
866 ===== ======================================= 785 ===== ============================================
867 bit 0 print all tasks info 786 bit 0 print all tasks info
868 bit 1 print system memory info 787 bit 1 print system memory info
869 bit 2 print timer info 788 bit 2 print timer info
870 bit 3 print locks info if ``CONFIG_LOCKDEP`` 789 bit 3 print locks info if ``CONFIG_LOCKDEP`` is on
871 bit 4 print ftrace buffer 790 bit 4 print ftrace buffer
872 bit 5 print all printk messages in buffer <<
873 bit 6 print all CPUs backtrace (if available <<
874 bit 7 print only tasks in uninterruptible (bl <<
875 ===== ======================================= 791 ===== ============================================
876 792
877 So for example to print tasks and memory info 793 So for example to print tasks and memory info on panic, user can::
878 794
879 echo 3 > /proc/sys/kernel/panic_print 795 echo 3 > /proc/sys/kernel/panic_print
880 796
881 797
882 panic_on_rcu_stall 798 panic_on_rcu_stall
883 ================== 799 ==================
884 800
885 When set to 1, calls panic() after RCU stall d 801 When set to 1, calls panic() after RCU stall detection messages. This
886 is useful to define the root cause of RCU stal 802 is useful to define the root cause of RCU stalls using a vmcore.
887 803
888 = ============================================ 804 = ============================================================
889 0 Do not panic() when RCU stall takes place, d 805 0 Do not panic() when RCU stall takes place, default behavior.
890 1 panic() after printing RCU stall messages. 806 1 panic() after printing RCU stall messages.
891 = ============================================ 807 = ============================================================
892 808
893 max_rcu_stall_to_panic <<
894 ====================== <<
895 <<
896 When ``panic_on_rcu_stall`` is set to 1, this <<
897 number of times that RCU can stall before pani <<
898 <<
899 When ``panic_on_rcu_stall`` is set to 0, this <<
900 809
901 perf_cpu_time_max_percent 810 perf_cpu_time_max_percent
902 ========================= 811 =========================
903 812
904 Hints to the kernel how much CPU time it shoul 813 Hints to the kernel how much CPU time it should be allowed to
905 use to handle perf sampling events. If the pe 814 use to handle perf sampling events. If the perf subsystem
906 is informed that its samples are exceeding thi 815 is informed that its samples are exceeding this limit, it
907 will drop its sampling frequency to attempt to 816 will drop its sampling frequency to attempt to reduce its CPU
908 usage. 817 usage.
909 818
910 Some perf sampling happens in NMIs. If these 819 Some perf sampling happens in NMIs. If these samples
911 unexpectedly take too long to execute, the NMI 820 unexpectedly take too long to execute, the NMIs can become
912 stacked up next to each other so much that not 821 stacked up next to each other so much that nothing else is
913 allowed to execute. 822 allowed to execute.
914 823
915 ===== ======================================== 824 ===== ========================================================
916 0 Disable the mechanism. Do not monitor o 825 0 Disable the mechanism. Do not monitor or correct perf's
917 sampling rate no matter how CPU time it 826 sampling rate no matter how CPU time it takes.
918 827
919 1-100 Attempt to throttle perf's sample rate t 828 1-100 Attempt to throttle perf's sample rate to this
920 percentage of CPU. Note: the kernel cal 829 percentage of CPU. Note: the kernel calculates an
921 "expected" length of each sample event. 830 "expected" length of each sample event. 100 here means
922 100% of that expected length. Even if t 831 100% of that expected length. Even if this is set to
923 100, you may still see sample throttling 832 100, you may still see sample throttling if this
924 length is exceeded. Set to 0 if you tru 833 length is exceeded. Set to 0 if you truly do not care
925 how much CPU is consumed. 834 how much CPU is consumed.
926 ===== ======================================== 835 ===== ========================================================
927 836
928 837
929 perf_event_paranoid 838 perf_event_paranoid
930 =================== 839 ===================
931 840
932 Controls use of the performance events system 841 Controls use of the performance events system by unprivileged
933 users (without CAP_PERFMON). The default valu 842 users (without CAP_PERFMON). The default value is 2.
934 843
935 For backward compatibility reasons access to s 844 For backward compatibility reasons access to system performance
936 monitoring and observability remains open for 845 monitoring and observability remains open for CAP_SYS_ADMIN
937 privileged processes but CAP_SYS_ADMIN usage f 846 privileged processes but CAP_SYS_ADMIN usage for secure system
938 performance monitoring and observability opera 847 performance monitoring and observability operations is discouraged
939 with respect to CAP_PERFMON use cases. 848 with respect to CAP_PERFMON use cases.
940 849
941 === ========================================= 850 === ==================================================================
942 -1 Allow use of (almost) all events by all u 851 -1 Allow use of (almost) all events by all users.
943 852
944 Ignore mlock limit after perf_event_mlock 853 Ignore mlock limit after perf_event_mlock_kb without
945 ``CAP_IPC_LOCK``. 854 ``CAP_IPC_LOCK``.
946 855
947 >=0 Disallow ftrace function tracepoint by us 856 >=0 Disallow ftrace function tracepoint by users without
948 ``CAP_PERFMON``. 857 ``CAP_PERFMON``.
949 858
950 Disallow raw tracepoint access by users w 859 Disallow raw tracepoint access by users without ``CAP_PERFMON``.
951 860
952 >=1 Disallow CPU event access by users withou 861 >=1 Disallow CPU event access by users without ``CAP_PERFMON``.
953 862
954 >=2 Disallow kernel profiling by users withou 863 >=2 Disallow kernel profiling by users without ``CAP_PERFMON``.
955 === ========================================= 864 === ==================================================================
956 865
957 866
958 perf_event_max_stack 867 perf_event_max_stack
959 ==================== 868 ====================
960 869
961 Controls maximum number of stack frames to cop 870 Controls maximum number of stack frames to copy for (``attr.sample_type &
962 PERF_SAMPLE_CALLCHAIN``) configured events, fo 871 PERF_SAMPLE_CALLCHAIN``) configured events, for instance, when using
963 '``perf record -g``' or '``perf trace --call-g 872 '``perf record -g``' or '``perf trace --call-graph fp``'.
964 873
965 This can only be done when no events are in us 874 This can only be done when no events are in use that have callchains
966 enabled, otherwise writing to this file will r 875 enabled, otherwise writing to this file will return ``-EBUSY``.
967 876
968 The default value is 127. 877 The default value is 127.
969 878
970 879
971 perf_event_mlock_kb 880 perf_event_mlock_kb
972 =================== 881 ===================
973 882
974 Control size of per-cpu ring buffer not counte 883 Control size of per-cpu ring buffer not counted against mlock limit.
975 884
976 The default value is 512 + 1 page 885 The default value is 512 + 1 page
977 886
978 887
979 perf_event_max_contexts_per_stack 888 perf_event_max_contexts_per_stack
980 ================================= 889 =================================
981 890
982 Controls maximum number of stack frame context 891 Controls maximum number of stack frame context entries for
983 (``attr.sample_type & PERF_SAMPLE_CALLCHAIN``) 892 (``attr.sample_type & PERF_SAMPLE_CALLCHAIN``) configured events, for
984 instance, when using '``perf record -g``' or ' 893 instance, when using '``perf record -g``' or '``perf trace --call-graph fp``'.
985 894
986 This can only be done when no events are in us 895 This can only be done when no events are in use that have callchains
987 enabled, otherwise writing to this file will r 896 enabled, otherwise writing to this file will return ``-EBUSY``.
988 897
989 The default value is 8. 898 The default value is 8.
990 899
991 900
992 perf_user_access (arm64 and riscv only) <<
993 ======================================= <<
994 <<
995 Controls user space access for reading perf ev <<
996 <<
997 arm64 <<
998 ===== <<
999 <<
1000 The default value is 0 (access disabled). <<
1001 <<
1002 When set to 1, user space can read performanc <<
1003 directly. <<
1004 <<
1005 See Documentation/arch/arm64/perf.rst for mor <<
1006 <<
1007 riscv <<
1008 ===== <<
1009 <<
1010 When set to 0, user space access is disabled. <<
1011 <<
1012 The default value is 1, user space can read p <<
1013 registers through perf, any direct access wit <<
1014 an illegal instruction. <<
1015 <<
1016 When set to 2, which enables legacy mode (use <<
1017 and insret CSRs only). Note that this legacy <<
1018 removed once all user space applications are <<
1019 <<
1020 Note that the time CSR is always directly acc <<
1021 <<
1022 pid_max 901 pid_max
1023 ======= 902 =======
1024 903
1025 PID allocation wrap value. When the kernel's 904 PID allocation wrap value. When the kernel's next PID value
1026 reaches this value, it wraps back to a minimu 905 reaches this value, it wraps back to a minimum PID value.
1027 PIDs of value ``pid_max`` or larger are not a 906 PIDs of value ``pid_max`` or larger are not allocated.
1028 907
1029 908
1030 ns_last_pid 909 ns_last_pid
1031 =========== 910 ===========
1032 911
1033 The last pid allocated in the current (the on 912 The last pid allocated in the current (the one task using this sysctl
1034 lives in) pid namespace. When selecting a pid 913 lives in) pid namespace. When selecting a pid for a next task on fork
1035 kernel tries to allocate a number starting fr 914 kernel tries to allocate a number starting from this one.
1036 915
1037 916
1038 powersave-nap (PPC only) 917 powersave-nap (PPC only)
1039 ======================== 918 ========================
1040 919
1041 If set, Linux-PPC will use the 'nap' mode of 920 If set, Linux-PPC will use the 'nap' mode of powersaving,
1042 otherwise the 'doze' mode will be used. 921 otherwise the 'doze' mode will be used.
1043 922
1044 923
1045 ============================================= 924 ==============================================================
1046 925
1047 printk 926 printk
1048 ====== 927 ======
1049 928
1050 The four values in printk denote: ``console_l 929 The four values in printk denote: ``console_loglevel``,
1051 ``default_message_loglevel``, ``minimum_conso 930 ``default_message_loglevel``, ``minimum_console_loglevel`` and
1052 ``default_console_loglevel`` respectively. 931 ``default_console_loglevel`` respectively.
1053 932
1054 These values influence printk() behavior when 933 These values influence printk() behavior when printing or
1055 logging error messages. See '``man 2 syslog`` 934 logging error messages. See '``man 2 syslog``' for more info on
1056 the different loglevels. 935 the different loglevels.
1057 936
1058 ======================== ==================== 937 ======================== =====================================
1059 console_loglevel messages with a high 938 console_loglevel messages with a higher priority than
1060 this will be printed 939 this will be printed to the console
1061 default_message_loglevel messages without an 940 default_message_loglevel messages without an explicit priority
1062 will be printed with 941 will be printed with this priority
1063 minimum_console_loglevel minimum (highest) va 942 minimum_console_loglevel minimum (highest) value to which
1064 console_loglevel can 943 console_loglevel can be set
1065 default_console_loglevel default value for co 944 default_console_loglevel default value for console_loglevel
1066 ======================== ==================== 945 ======================== =====================================
1067 946
1068 947
1069 printk_delay 948 printk_delay
1070 ============ 949 ============
1071 950
1072 Delay each printk message in ``printk_delay`` 951 Delay each printk message in ``printk_delay`` milliseconds
1073 952
1074 Value from 0 - 10000 is allowed. 953 Value from 0 - 10000 is allowed.
1075 954
1076 955
1077 printk_ratelimit 956 printk_ratelimit
1078 ================ 957 ================
1079 958
1080 Some warning messages are rate limited. ``pri 959 Some warning messages are rate limited. ``printk_ratelimit`` specifies
1081 the minimum length of time between these mess 960 the minimum length of time between these messages (in seconds).
1082 The default value is 5 seconds. 961 The default value is 5 seconds.
1083 962
1084 A value of 0 will disable rate limiting. 963 A value of 0 will disable rate limiting.
1085 964
1086 965
1087 printk_ratelimit_burst 966 printk_ratelimit_burst
1088 ====================== 967 ======================
1089 968
1090 While long term we enforce one message per `p 969 While long term we enforce one message per `printk_ratelimit`_
1091 seconds, we do allow a burst of messages to p 970 seconds, we do allow a burst of messages to pass through.
1092 ``printk_ratelimit_burst`` specifies the numb 971 ``printk_ratelimit_burst`` specifies the number of messages we can
1093 send before ratelimiting kicks in. 972 send before ratelimiting kicks in.
1094 973
1095 The default value is 10 messages. 974 The default value is 10 messages.
1096 975
1097 976
1098 printk_devkmsg 977 printk_devkmsg
1099 ============== 978 ==============
1100 979
1101 Control the logging to ``/dev/kmsg`` from use 980 Control the logging to ``/dev/kmsg`` from userspace:
1102 981
1103 ========= =================================== 982 ========= =============================================
1104 ratelimit default, ratelimited 983 ratelimit default, ratelimited
1105 on unlimited logging to /dev/kmsg from 984 on unlimited logging to /dev/kmsg from userspace
1106 off logging to /dev/kmsg disabled 985 off logging to /dev/kmsg disabled
1107 ========= =================================== 986 ========= =============================================
1108 987
1109 The kernel command line parameter ``printk.de 988 The kernel command line parameter ``printk.devkmsg=`` overrides this and is
1110 a one-time setting until next reboot: once se 989 a one-time setting until next reboot: once set, it cannot be changed by
1111 this sysctl interface anymore. 990 this sysctl interface anymore.
1112 991
1113 ============================================= 992 ==============================================================
1114 993
1115 994
1116 pty 995 pty
1117 === 996 ===
1118 997
1119 See Documentation/filesystems/devpts.rst. 998 See Documentation/filesystems/devpts.rst.
1120 999
1121 1000
1122 random 1001 random
1123 ====== 1002 ======
1124 1003
1125 This is a directory, with the following entri 1004 This is a directory, with the following entries:
1126 1005
1127 * ``boot_id``: a UUID generated the first tim 1006 * ``boot_id``: a UUID generated the first time this is retrieved, and
1128 unvarying after that; 1007 unvarying after that;
1129 1008
1130 * ``uuid``: a UUID generated every time this <<
1131 thus be used to generate UUIDs at will); <<
1132 <<
1133 * ``entropy_avail``: the pool's entropy count 1009 * ``entropy_avail``: the pool's entropy count, in bits;
1134 1010
1135 * ``poolsize``: the entropy pool size, in bit 1011 * ``poolsize``: the entropy pool size, in bits;
1136 1012
1137 * ``urandom_min_reseed_secs``: obsolete (used 1013 * ``urandom_min_reseed_secs``: obsolete (used to determine the minimum
1138 number of seconds between urandom pool rese !! 1014 number of seconds between urandom pool reseeding).
1139 writable for compatibility purposes, but wr !! 1015
1140 on any RNG behavior; !! 1016 * ``uuid``: a UUID generated every time this is retrieved (this can
>> 1017 thus be used to generate UUIDs at will);
1141 1018
1142 * ``write_wakeup_threshold``: when the entrop 1019 * ``write_wakeup_threshold``: when the entropy count drops below this
1143 (as a number of bits), processes waiting to 1020 (as a number of bits), processes waiting to write to ``/dev/random``
1144 are woken up. This file is writable for com !! 1021 are woken up.
1145 writing to it has no effect on any RNG beha !! 1022
>> 1023 If ``drivers/char/random.c`` is built with ``ADD_INTERRUPT_BENCH``
>> 1024 defined, these additional entries are present:
>> 1025
>> 1026 * ``add_interrupt_avg_cycles``: the average number of cycles between
>> 1027 interrupts used to feed the pool;
>> 1028
>> 1029 * ``add_interrupt_avg_deviation``: the standard deviation seen on the
>> 1030 number of cycles between interrupts used to feed the pool.
1146 1031
1147 1032
1148 randomize_va_space 1033 randomize_va_space
1149 ================== 1034 ==================
1150 1035
1151 This option can be used to select the type of 1036 This option can be used to select the type of process address
1152 space randomization that is used in the syste 1037 space randomization that is used in the system, for architectures
1153 that support this feature. 1038 that support this feature.
1154 1039
1155 == ========================================= 1040 == ===========================================================================
1156 0 Turn the process address space randomizat 1041 0 Turn the process address space randomization off. This is the
1157 default for architectures that do not sup 1042 default for architectures that do not support this feature anyways,
1158 and kernels that are booted with the "nor 1043 and kernels that are booted with the "norandmaps" parameter.
1159 1044
1160 1 Make the addresses of mmap base, stack an 1045 1 Make the addresses of mmap base, stack and VDSO page randomized.
1161 This, among other things, implies that sh 1046 This, among other things, implies that shared libraries will be
1162 loaded to random addresses. Also for PIE 1047 loaded to random addresses. Also for PIE-linked binaries, the
1163 location of code start is randomized. Th 1048 location of code start is randomized. This is the default if the
1164 ``CONFIG_COMPAT_BRK`` option is enabled. 1049 ``CONFIG_COMPAT_BRK`` option is enabled.
1165 1050
1166 2 Additionally enable heap randomization. 1051 2 Additionally enable heap randomization. This is the default if
1167 ``CONFIG_COMPAT_BRK`` is disabled. 1052 ``CONFIG_COMPAT_BRK`` is disabled.
1168 1053
1169 There are a few legacy applications out t 1054 There are a few legacy applications out there (such as some ancient
1170 versions of libc.so.5 from 1996) that ass 1055 versions of libc.so.5 from 1996) that assume that brk area starts
1171 just after the end of the code+bss. Thes 1056 just after the end of the code+bss. These applications break when
1172 start of the brk area is randomized. The 1057 start of the brk area is randomized. There are however no known
1173 non-legacy applications that would be bro 1058 non-legacy applications that would be broken this way, so for most
1174 systems it is safe to choose full randomi 1059 systems it is safe to choose full randomization.
1175 1060
1176 Systems with ancient and/or broken binari 1061 Systems with ancient and/or broken binaries should be configured
1177 with ``CONFIG_COMPAT_BRK`` enabled, which 1062 with ``CONFIG_COMPAT_BRK`` enabled, which excludes the heap from process
1178 address space randomization. 1063 address space randomization.
1179 == ========================================= 1064 == ===========================================================================
1180 1065
1181 1066
1182 real-root-dev 1067 real-root-dev
1183 ============= 1068 =============
1184 1069
1185 See Documentation/admin-guide/initrd.rst. !! 1070 See :doc:`/admin-guide/initrd`.
1186 1071
1187 1072
1188 reboot-cmd (SPARC only) 1073 reboot-cmd (SPARC only)
1189 ======================= 1074 =======================
1190 1075
1191 ??? This seems to be a way to give an argumen 1076 ??? This seems to be a way to give an argument to the Sparc
1192 ROM/Flash boot loader. Maybe to tell it what 1077 ROM/Flash boot loader. Maybe to tell it what to do after
1193 rebooting. ??? 1078 rebooting. ???
1194 1079
1195 1080
1196 sched_energy_aware 1081 sched_energy_aware
1197 ================== 1082 ==================
1198 1083
1199 Enables/disables Energy Aware Scheduling (EAS 1084 Enables/disables Energy Aware Scheduling (EAS). EAS starts
1200 automatically on platforms where it can run ( 1085 automatically on platforms where it can run (that is,
1201 platforms with asymmetric CPU topologies and 1086 platforms with asymmetric CPU topologies and having an Energy
1202 Model available). If your platform happens to 1087 Model available). If your platform happens to meet the
1203 requirements for EAS but you do not want to u 1088 requirements for EAS but you do not want to use it, change
1204 this value to 0. On Non-EAS platforms, write !! 1089 this value to 0.
1205 read doesn't return anything. <<
1206 1090
1207 task_delayacct <<
1208 =============== <<
1209 <<
1210 Enables/disables task delay accounting (see <<
1211 Documentation/accounting/delay-accounting.rst <<
1212 a small amount of overhead in the scheduler b <<
1213 and performance tuning. It is required by som <<
1214 1091
1215 sched_schedstats 1092 sched_schedstats
1216 ================ 1093 ================
1217 1094
1218 Enables/disables scheduler statistics. Enabli 1095 Enables/disables scheduler statistics. Enabling this feature
1219 incurs a small amount of overhead in the sche 1096 incurs a small amount of overhead in the scheduler but is
1220 useful for debugging and performance tuning. 1097 useful for debugging and performance tuning.
1221 1098
1222 sched_util_clamp_min 1099 sched_util_clamp_min
1223 ==================== 1100 ====================
1224 1101
1225 Max allowed *minimum* utilization. 1102 Max allowed *minimum* utilization.
1226 1103
1227 Default value is 1024, which is the maximum p 1104 Default value is 1024, which is the maximum possible value.
1228 1105
1229 It means that any requested uclamp.min value 1106 It means that any requested uclamp.min value cannot be greater than
1230 sched_util_clamp_min, i.e., it is restricted 1107 sched_util_clamp_min, i.e., it is restricted to the range
1231 [0:sched_util_clamp_min]. 1108 [0:sched_util_clamp_min].
1232 1109
1233 sched_util_clamp_max 1110 sched_util_clamp_max
1234 ==================== 1111 ====================
1235 1112
1236 Max allowed *maximum* utilization. 1113 Max allowed *maximum* utilization.
1237 1114
1238 Default value is 1024, which is the maximum p 1115 Default value is 1024, which is the maximum possible value.
1239 1116
1240 It means that any requested uclamp.max value 1117 It means that any requested uclamp.max value cannot be greater than
1241 sched_util_clamp_max, i.e., it is restricted 1118 sched_util_clamp_max, i.e., it is restricted to the range
1242 [0:sched_util_clamp_max]. 1119 [0:sched_util_clamp_max].
1243 1120
1244 sched_util_clamp_min_rt_default 1121 sched_util_clamp_min_rt_default
1245 =============================== 1122 ===============================
1246 1123
1247 By default Linux is tuned for performance. Wh 1124 By default Linux is tuned for performance. Which means that RT tasks always run
1248 at the highest frequency and most capable (hi 1125 at the highest frequency and most capable (highest capacity) CPU (in
1249 heterogeneous systems). 1126 heterogeneous systems).
1250 1127
1251 Uclamp achieves this by setting the requested 1128 Uclamp achieves this by setting the requested uclamp.min of all RT tasks to
1252 1024 by default, which effectively boosts the 1129 1024 by default, which effectively boosts the tasks to run at the highest
1253 frequency and biases them to run on the bigge 1130 frequency and biases them to run on the biggest CPU.
1254 1131
1255 This knob allows admins to change the default 1132 This knob allows admins to change the default behavior when uclamp is being
1256 used. In battery powered devices particularly 1133 used. In battery powered devices particularly, running at the maximum
1257 capacity and frequency will increase energy c 1134 capacity and frequency will increase energy consumption and shorten the battery
1258 life. 1135 life.
1259 1136
1260 This knob is only effective for RT tasks whic 1137 This knob is only effective for RT tasks which the user hasn't modified their
1261 requested uclamp.min value via sched_setattr( 1138 requested uclamp.min value via sched_setattr() syscall.
1262 1139
1263 This knob will not escape the range constrain 1140 This knob will not escape the range constraint imposed by sched_util_clamp_min
1264 defined above. 1141 defined above.
1265 1142
1266 For example if 1143 For example if
1267 1144
1268 sched_util_clamp_min_rt_default = 800 1145 sched_util_clamp_min_rt_default = 800
1269 sched_util_clamp_min = 600 1146 sched_util_clamp_min = 600
1270 1147
1271 Then the boost will be clamped to 600 because 1148 Then the boost will be clamped to 600 because 800 is outside of the permissible
1272 range of [0:600]. This could happen for insta 1149 range of [0:600]. This could happen for instance if a powersave mode will
1273 restrict all boosts temporarily by modifying 1150 restrict all boosts temporarily by modifying sched_util_clamp_min. As soon as
1274 this restriction is lifted, the requested sch 1151 this restriction is lifted, the requested sched_util_clamp_min_rt_default
1275 will take effect. 1152 will take effect.
1276 1153
1277 seccomp 1154 seccomp
1278 ======= 1155 =======
1279 1156
1280 See Documentation/userspace-api/seccomp_filte !! 1157 See :doc:`/userspace-api/seccomp_filter`.
1281 1158
1282 1159
1283 sg-big-buff 1160 sg-big-buff
1284 =========== 1161 ===========
1285 1162
1286 This file shows the size of the generic SCSI 1163 This file shows the size of the generic SCSI (sg) buffer.
1287 You can't tune it just yet, but you could cha 1164 You can't tune it just yet, but you could change it on
1288 compile time by editing ``include/scsi/sg.h`` 1165 compile time by editing ``include/scsi/sg.h`` and changing
1289 the value of ``SG_BIG_BUFF``. 1166 the value of ``SG_BIG_BUFF``.
1290 1167
1291 There shouldn't be any reason to change this 1168 There shouldn't be any reason to change this value. If
1292 you can come up with one, you probably know w 1169 you can come up with one, you probably know what you
1293 are doing anyway :) 1170 are doing anyway :)
1294 1171
1295 1172
1296 shmall 1173 shmall
1297 ====== 1174 ======
1298 1175
1299 This parameter sets the total amount of share !! 1176 This parameter sets the total amount of shared memory pages that
1300 inside ipc namespace. The shared memory pages !! 1177 can be used system wide. Hence, ``shmall`` should always be at least
1301 namespace separately and is not inherited. He !! 1178 ``ceil(shmmax/PAGE_SIZE)``.
1302 least ``ceil(shmmax/PAGE_SIZE)``. <<
1303 1179
1304 If you are not sure what the default ``PAGE_S 1180 If you are not sure what the default ``PAGE_SIZE`` is on your Linux
1305 system, you can run the following command:: 1181 system, you can run the following command::
1306 1182
1307 # getconf PAGE_SIZE 1183 # getconf PAGE_SIZE
1308 1184
1309 To reduce or disable the ability to allocate <<
1310 new ipc namespace, set this parameter to the <<
1311 creation of a new ipc namespace in the curren <<
1312 be used. <<
1313 1185
1314 shmmax 1186 shmmax
1315 ====== 1187 ======
1316 1188
1317 This value can be used to query and set the r 1189 This value can be used to query and set the run time limit
1318 on the maximum shared memory segment size tha 1190 on the maximum shared memory segment size that can be created.
1319 Shared memory segments up to 1Gb are now supp 1191 Shared memory segments up to 1Gb are now supported in the
1320 kernel. This value defaults to ``SHMMAX``. 1192 kernel. This value defaults to ``SHMMAX``.
1321 1193
1322 1194
1323 shmmni 1195 shmmni
1324 ====== 1196 ======
1325 1197
1326 This value determines the maximum number of s 1198 This value determines the maximum number of shared memory segments.
1327 4096 by default (``SHMMNI``). 1199 4096 by default (``SHMMNI``).
1328 1200
1329 1201
1330 shm_rmid_forced 1202 shm_rmid_forced
1331 =============== 1203 ===============
1332 1204
1333 Linux lets you set resource limits, including 1205 Linux lets you set resource limits, including how much memory one
1334 process can consume, via ``setrlimit(2)``. U 1206 process can consume, via ``setrlimit(2)``. Unfortunately, shared memory
1335 segments are allowed to exist without associa 1207 segments are allowed to exist without association with any process, and
1336 thus might not be counted against any resourc 1208 thus might not be counted against any resource limits. If enabled,
1337 shared memory segments are automatically dest 1209 shared memory segments are automatically destroyed when their attach
1338 count becomes zero after a detach or a proces 1210 count becomes zero after a detach or a process termination. It will
1339 also destroy segments that were created, but 1211 also destroy segments that were created, but never attached to, on exit
1340 from the process. The only use left for ``IP 1212 from the process. The only use left for ``IPC_RMID`` is to immediately
1341 destroy an unattached segment. Of course, th 1213 destroy an unattached segment. Of course, this breaks the way things are
1342 defined, so some applications might stop work 1214 defined, so some applications might stop working. Note that this
1343 feature will do you no good unless you also c 1215 feature will do you no good unless you also configure your resource
1344 limits (in particular, ``RLIMIT_AS`` and ``RL 1216 limits (in particular, ``RLIMIT_AS`` and ``RLIMIT_NPROC``). Most systems don't
1345 need this. 1217 need this.
1346 1218
1347 Note that if you change this from 0 to 1, alr 1219 Note that if you change this from 0 to 1, already created segments
1348 without users and with a dead originative pro 1220 without users and with a dead originative process will be destroyed.
1349 1221
1350 1222
1351 sysctl_writes_strict 1223 sysctl_writes_strict
1352 ==================== 1224 ====================
1353 1225
1354 Control how file position affects the behavio 1226 Control how file position affects the behavior of updating sysctl values
1355 via the ``/proc/sys`` interface: 1227 via the ``/proc/sys`` interface:
1356 1228
1357 == ====================================== 1229 == ======================================================================
1358 -1 Legacy per-write sysctl value handling 1230 -1 Legacy per-write sysctl value handling, with no printk warnings.
1359 Each write syscall must fully contain 1231 Each write syscall must fully contain the sysctl value to be
1360 written, and multiple writes on the sa 1232 written, and multiple writes on the same sysctl file descriptor
1361 will rewrite the sysctl value, regardl 1233 will rewrite the sysctl value, regardless of file position.
1362 0 Same behavior as above, but warn about 1234 0 Same behavior as above, but warn about processes that perform writes
1363 to a sysctl file descriptor when the f 1235 to a sysctl file descriptor when the file position is not 0.
1364 1 (default) Respect file position when w 1236 1 (default) Respect file position when writing sysctl strings. Multiple
1365 writes will append to the sysctl value 1237 writes will append to the sysctl value buffer. Anything past the max
1366 length of the sysctl value buffer will 1238 length of the sysctl value buffer will be ignored. Writes to numeric
1367 sysctl entries must always be at file 1239 sysctl entries must always be at file position 0 and the value must
1368 be fully contained in the buffer sent 1240 be fully contained in the buffer sent in the write syscall.
1369 == ====================================== 1241 == ======================================================================
1370 1242
1371 1243
1372 softlockup_all_cpu_backtrace 1244 softlockup_all_cpu_backtrace
1373 ============================ 1245 ============================
1374 1246
1375 This value controls the soft lockup detector 1247 This value controls the soft lockup detector thread's behavior
1376 when a soft lockup condition is detected as t 1248 when a soft lockup condition is detected as to whether or not
1377 to gather further debug information. If enabl 1249 to gather further debug information. If enabled, each cpu will
1378 be issued an NMI and instructed to capture st 1250 be issued an NMI and instructed to capture stack trace.
1379 1251
1380 This feature is only applicable for architect 1252 This feature is only applicable for architectures which support
1381 NMI. 1253 NMI.
1382 1254
1383 = =========================================== 1255 = ============================================
1384 0 Do nothing. This is the default behavior. 1256 0 Do nothing. This is the default behavior.
1385 1 On detection capture more debug information 1257 1 On detection capture more debug information.
1386 = =========================================== 1258 = ============================================
1387 1259
1388 1260
1389 softlockup_panic 1261 softlockup_panic
1390 ================= 1262 =================
1391 1263
1392 This parameter can be used to control whether 1264 This parameter can be used to control whether the kernel panics
1393 when a soft lockup is detected. 1265 when a soft lockup is detected.
1394 1266
1395 = =========================================== 1267 = ============================================
1396 0 Don't panic on soft lockup. 1268 0 Don't panic on soft lockup.
1397 1 Panic on soft lockup. 1269 1 Panic on soft lockup.
1398 = =========================================== 1270 = ============================================
1399 1271
1400 This can also be set using the softlockup_pan 1272 This can also be set using the softlockup_panic kernel parameter.
1401 1273
1402 1274
1403 soft_watchdog 1275 soft_watchdog
1404 ============= 1276 =============
1405 1277
1406 This parameter can be used to control the sof 1278 This parameter can be used to control the soft lockup detector.
1407 1279
1408 = ================================= 1280 = =================================
1409 0 Disable the soft lockup detector. 1281 0 Disable the soft lockup detector.
1410 1 Enable the soft lockup detector. 1282 1 Enable the soft lockup detector.
1411 = ================================= 1283 = =================================
1412 1284
1413 The soft lockup detector monitors CPUs for th 1285 The soft lockup detector monitors CPUs for threads that are hogging the CPUs
1414 without rescheduling voluntarily, and thus pr !! 1286 without rescheduling voluntarily, and thus prevent the 'watchdog/N' threads
1415 from running, causing the watchdog work fail !! 1287 from running. The mechanism depends on the CPUs ability to respond to timer
1416 on the CPUs ability to respond to timer inter !! 1288 interrupts which are needed for the 'watchdog/N' threads to be woken up by
1417 watchdog work to be queued by the watchdog ti !! 1289 the watchdog timer function, otherwise the NMI watchdog — if enabled — can
1418 watchdog — if enabled — can detect a hard !! 1290 detect a hard lockup condition.
1419 <<
1420 <<
1421 split_lock_mitigate (x86 only) <<
1422 ============================== <<
1423 <<
1424 On x86, each "split lock" imposes a system-wi <<
1425 systems, large numbers of split locks from un <<
1426 denials of service to well-behaved and potent <<
1427 <<
1428 The kernel mitigates these bad users by detec <<
1429 penalties: forcing them to wait and only allo <<
1430 locks at a time. <<
1431 <<
1432 These mitigations can make those bad applicat <<
1433 split_lock_mitigate=0 may restore some applic <<
1434 increase system exposure to denial of service <<
1435 <<
1436 = =========================================== <<
1437 0 Disable the mitigation mode - just warns th <<
1438 and exposes the system to denials of servic <<
1439 1 Enable the mitigation mode (this is the def <<
1440 lockers with intentional performance degrad <<
1441 = =========================================== <<
1442 1291
1443 1292
1444 stack_erasing 1293 stack_erasing
1445 ============= 1294 =============
1446 1295
1447 This parameter can be used to control kernel 1296 This parameter can be used to control kernel stack erasing at the end
1448 of syscalls for kernels built with ``CONFIG_G 1297 of syscalls for kernels built with ``CONFIG_GCC_PLUGIN_STACKLEAK``.
1449 1298
1450 That erasing reduces the information which ke 1299 That erasing reduces the information which kernel stack leak bugs
1451 can reveal and blocks some uninitialized stac 1300 can reveal and blocks some uninitialized stack variable attacks.
1452 The tradeoff is the performance impact: on a 1301 The tradeoff is the performance impact: on a single CPU system kernel
1453 compilation sees a 1% slowdown, other systems 1302 compilation sees a 1% slowdown, other systems and workloads may vary.
1454 1303
1455 = =========================================== 1304 = ====================================================================
1456 0 Kernel stack erasing is disabled, STACKLEAK 1305 0 Kernel stack erasing is disabled, STACKLEAK_METRICS are not updated.
1457 1 Kernel stack erasing is enabled (default), 1306 1 Kernel stack erasing is enabled (default), it is performed before
1458 returning to the userspace at the end of sy 1307 returning to the userspace at the end of syscalls.
1459 = =========================================== 1308 = ====================================================================
1460 1309
1461 1310
1462 stop-a (SPARC only) 1311 stop-a (SPARC only)
1463 =================== 1312 ===================
1464 1313
1465 Controls Stop-A: 1314 Controls Stop-A:
1466 1315
1467 = ==================================== 1316 = ====================================
1468 0 Stop-A has no effect. 1317 0 Stop-A has no effect.
1469 1 Stop-A breaks to the PROM (default). 1318 1 Stop-A breaks to the PROM (default).
1470 = ==================================== 1319 = ====================================
1471 1320
1472 Stop-A is always enabled on a panic, so that 1321 Stop-A is always enabled on a panic, so that the user can return to
1473 the boot PROM. 1322 the boot PROM.
1474 1323
1475 1324
1476 sysrq 1325 sysrq
1477 ===== 1326 =====
1478 1327
1479 See Documentation/admin-guide/sysrq.rst. !! 1328 See :doc:`/admin-guide/sysrq`.
1480 1329
1481 1330
1482 tainted 1331 tainted
1483 ======= 1332 =======
1484 1333
1485 Non-zero if the kernel has been tainted. Nume 1334 Non-zero if the kernel has been tainted. Numeric values, which can be
1486 ORed together. The letters are seen in "Taint 1335 ORed together. The letters are seen in "Tainted" line of Oops reports.
1487 1336
1488 ====== ===== ============================== 1337 ====== ===== ==============================================================
1489 1 `(P)` proprietary module was loaded 1338 1 `(P)` proprietary module was loaded
1490 2 `(F)` module was force loaded 1339 2 `(F)` module was force loaded
1491 4 `(S)` kernel running on an out of sp 1340 4 `(S)` kernel running on an out of specification system
1492 8 `(R)` module was force unloaded 1341 8 `(R)` module was force unloaded
1493 16 `(M)` processor reported a Machine C 1342 16 `(M)` processor reported a Machine Check Exception (MCE)
1494 32 `(B)` bad page referenced or some un 1343 32 `(B)` bad page referenced or some unexpected page flags
1495 64 `(U)` taint requested by userspace a 1344 64 `(U)` taint requested by userspace application
1496 128 `(D)` kernel died recently, i.e. the 1345 128 `(D)` kernel died recently, i.e. there was an OOPS or BUG
1497 256 `(A)` an ACPI table was overridden b 1346 256 `(A)` an ACPI table was overridden by user
1498 512 `(W)` kernel issued warning 1347 512 `(W)` kernel issued warning
1499 1024 `(C)` staging driver was loaded 1348 1024 `(C)` staging driver was loaded
1500 2048 `(I)` workaround for bug in platform 1349 2048 `(I)` workaround for bug in platform firmware applied
1501 4096 `(O)` externally-built ("out-of-tree 1350 4096 `(O)` externally-built ("out-of-tree") module was loaded
1502 8192 `(E)` unsigned module was loaded 1351 8192 `(E)` unsigned module was loaded
1503 16384 `(L)` soft lockup occurred 1352 16384 `(L)` soft lockup occurred
1504 32768 `(K)` kernel has been live patched 1353 32768 `(K)` kernel has been live patched
1505 65536 `(X)` Auxiliary taint, defined and u 1354 65536 `(X)` Auxiliary taint, defined and used by for distros
1506 131072 `(T)` The kernel was built with the 1355 131072 `(T)` The kernel was built with the struct randomization plugin
1507 ====== ===== ============================== 1356 ====== ===== ==============================================================
1508 1357
1509 See Documentation/admin-guide/tainted-kernels !! 1358 See :doc:`/admin-guide/tainted-kernels` for more information.
1510 1359
1511 Note: 1360 Note:
1512 writes to this sysctl interface will fail w 1361 writes to this sysctl interface will fail with ``EINVAL`` if the kernel is
1513 booted with the command line option ``panic 1362 booted with the command line option ``panic_on_taint=<bitmask>,nousertaint``
1514 and any of the ORed together values being w 1363 and any of the ORed together values being written to ``tainted`` match with
1515 the bitmask declared on panic_on_taint. 1364 the bitmask declared on panic_on_taint.
1516 See Documentation/admin-guide/kernel-parame !! 1365 See :doc:`/admin-guide/kernel-parameters` for more details on that particular
1517 that particular kernel command line option !! 1366 kernel command line option and its optional ``nousertaint`` switch.
1518 ``nousertaint`` switch. <<
1519 1367
1520 threads-max 1368 threads-max
1521 =========== 1369 ===========
1522 1370
1523 This value controls the maximum number of thr 1371 This value controls the maximum number of threads that can be created
1524 using ``fork()``. 1372 using ``fork()``.
1525 1373
1526 During initialization the kernel sets this va 1374 During initialization the kernel sets this value such that even if the
1527 maximum number of threads is created, the thr 1375 maximum number of threads is created, the thread structures occupy only
1528 a part (1/8th) of the available RAM pages. 1376 a part (1/8th) of the available RAM pages.
1529 1377
1530 The minimum value that can be written to ``th 1378 The minimum value that can be written to ``threads-max`` is 1.
1531 1379
1532 The maximum value that can be written to ``th 1380 The maximum value that can be written to ``threads-max`` is given by the
1533 constant ``FUTEX_TID_MASK`` (0x3fffffff). 1381 constant ``FUTEX_TID_MASK`` (0x3fffffff).
1534 1382
1535 If a value outside of this range is written t 1383 If a value outside of this range is written to ``threads-max`` an
1536 ``EINVAL`` error occurs. 1384 ``EINVAL`` error occurs.
1537 1385
1538 1386
1539 traceoff_on_warning 1387 traceoff_on_warning
1540 =================== 1388 ===================
1541 1389
1542 When set, disables tracing (see Documentation !! 1390 When set, disables tracing (see :doc:`/trace/ftrace`) when a
1543 ``WARN()`` is hit. 1391 ``WARN()`` is hit.
1544 1392
1545 1393
1546 tracepoint_printk 1394 tracepoint_printk
1547 ================= 1395 =================
1548 1396
1549 When tracepoints are sent to printk() (enable 1397 When tracepoints are sent to printk() (enabled by the ``tp_printk``
1550 boot parameter), this entry provides runtime 1398 boot parameter), this entry provides runtime control::
1551 1399
1552 echo 0 > /proc/sys/kernel/tracepoint_prin 1400 echo 0 > /proc/sys/kernel/tracepoint_printk
1553 1401
1554 will stop tracepoints from being sent to prin 1402 will stop tracepoints from being sent to printk(), and::
1555 1403
1556 echo 1 > /proc/sys/kernel/tracepoint_prin 1404 echo 1 > /proc/sys/kernel/tracepoint_printk
1557 1405
1558 will send them to printk() again. 1406 will send them to printk() again.
1559 1407
1560 This only works if the kernel was booted with 1408 This only works if the kernel was booted with ``tp_printk`` enabled.
1561 1409
1562 See Documentation/admin-guide/kernel-paramete !! 1410 See :doc:`/admin-guide/kernel-parameters` and
1563 Documentation/trace/boottime-trace.rst. !! 1411 :doc:`/trace/boottime-trace`.
>> 1412
>> 1413
>> 1414 .. _unaligned-dump-stack:
>> 1415
>> 1416 unaligned-dump-stack (ia64)
>> 1417 ===========================
>> 1418
>> 1419 When logging unaligned accesses, controls whether the stack is
>> 1420 dumped.
>> 1421
>> 1422 = ===================================================
>> 1423 0 Do not dump the stack. This is the default setting.
>> 1424 1 Dump the stack.
>> 1425 = ===================================================
>> 1426
>> 1427 See also `ignore-unaligned-usertrap`_.
1564 1428
1565 1429
1566 unaligned-trap 1430 unaligned-trap
1567 ============== 1431 ==============
1568 1432
1569 On architectures where unaligned accesses cau 1433 On architectures where unaligned accesses cause traps, and where this
1570 feature is supported (``CONFIG_SYSCTL_ARCH_UN 1434 feature is supported (``CONFIG_SYSCTL_ARCH_UNALIGN_ALLOW``; currently,
1571 ``arc``, ``parisc`` and ``loongarch``), contr !! 1435 ``arc`` and ``parisc``), controls whether unaligned traps are caught
1572 are caught and emulated (instead of failing). !! 1436 and emulated (instead of failing).
1573 1437
1574 = =========================================== 1438 = ========================================================
1575 0 Do not emulate unaligned accesses. 1439 0 Do not emulate unaligned accesses.
1576 1 Emulate unaligned accesses. This is the def 1440 1 Emulate unaligned accesses. This is the default setting.
1577 = =========================================== 1441 = ========================================================
1578 1442
1579 See also `ignore-unaligned-usertrap`_. 1443 See also `ignore-unaligned-usertrap`_.
1580 1444
1581 1445
1582 unknown_nmi_panic 1446 unknown_nmi_panic
1583 ================= 1447 =================
1584 1448
1585 The value in this file affects behavior of ha 1449 The value in this file affects behavior of handling NMI. When the
1586 value is non-zero, unknown NMI is trapped and 1450 value is non-zero, unknown NMI is trapped and then panic occurs. At
1587 that time, kernel debugging information is di 1451 that time, kernel debugging information is displayed on console.
1588 1452
1589 NMI switch that most IA32 servers have fires 1453 NMI switch that most IA32 servers have fires unknown NMI up, for
1590 example. If a system hangs up, try pressing 1454 example. If a system hangs up, try pressing the NMI switch.
1591 1455
1592 1456
1593 unprivileged_bpf_disabled 1457 unprivileged_bpf_disabled
1594 ========================= 1458 =========================
1595 1459
1596 Writing 1 to this entry will disable unprivil 1460 Writing 1 to this entry will disable unprivileged calls to ``bpf()``;
1597 once disabled, calling ``bpf()`` without ``CA 1461 once disabled, calling ``bpf()`` without ``CAP_SYS_ADMIN`` or ``CAP_BPF``
1598 will return ``-EPERM``. Once set to 1, this c 1462 will return ``-EPERM``. Once set to 1, this can't be cleared from the
1599 running kernel anymore. 1463 running kernel anymore.
1600 1464
1601 Writing 2 to this entry will also disable unp 1465 Writing 2 to this entry will also disable unprivileged calls to ``bpf()``,
1602 however, an admin can still change this setti 1466 however, an admin can still change this setting later on, if needed, by
1603 writing 0 or 1 to this entry. 1467 writing 0 or 1 to this entry.
1604 1468
1605 If ``BPF_UNPRIV_DEFAULT_OFF`` is enabled in t 1469 If ``BPF_UNPRIV_DEFAULT_OFF`` is enabled in the kernel config, then this
1606 entry will default to 2 instead of 0. 1470 entry will default to 2 instead of 0.
1607 1471
1608 = =========================================== 1472 = =============================================================
1609 0 Unprivileged calls to ``bpf()`` are enabled 1473 0 Unprivileged calls to ``bpf()`` are enabled
1610 1 Unprivileged calls to ``bpf()`` are disable 1474 1 Unprivileged calls to ``bpf()`` are disabled without recovery
1611 2 Unprivileged calls to ``bpf()`` are disable 1475 2 Unprivileged calls to ``bpf()`` are disabled
1612 = =========================================== 1476 = =============================================================
1613 <<
1614 <<
1615 warn_limit <<
1616 ========== <<
1617 <<
1618 Number of kernel warnings after which the ker <<
1619 ``panic_on_warn`` is not set. Setting this to <<
1620 the warning count. Setting this to 1 has the <<
1621 ``panic_on_warn=1``. The default value is 0. <<
1622 <<
1623 1477
1624 watchdog 1478 watchdog
1625 ======== 1479 ========
1626 1480
1627 This parameter can be used to disable or enab 1481 This parameter can be used to disable or enable the soft lockup detector
1628 *and* the NMI watchdog (i.e. the hard lockup 1482 *and* the NMI watchdog (i.e. the hard lockup detector) at the same time.
1629 1483
1630 = ============================== 1484 = ==============================
1631 0 Disable both lockup detectors. 1485 0 Disable both lockup detectors.
1632 1 Enable both lockup detectors. 1486 1 Enable both lockup detectors.
1633 = ============================== 1487 = ==============================
1634 1488
1635 The soft lockup detector and the NMI watchdog 1489 The soft lockup detector and the NMI watchdog can also be disabled or
1636 enabled individually, using the ``soft_watchd 1490 enabled individually, using the ``soft_watchdog`` and ``nmi_watchdog``
1637 parameters. 1491 parameters.
1638 If the ``watchdog`` parameter is read, for ex 1492 If the ``watchdog`` parameter is read, for example by executing::
1639 1493
1640 cat /proc/sys/kernel/watchdog 1494 cat /proc/sys/kernel/watchdog
1641 1495
1642 the output of this command (0 or 1) shows the 1496 the output of this command (0 or 1) shows the logical OR of
1643 ``soft_watchdog`` and ``nmi_watchdog``. 1497 ``soft_watchdog`` and ``nmi_watchdog``.
1644 1498
1645 1499
1646 watchdog_cpumask 1500 watchdog_cpumask
1647 ================ 1501 ================
1648 1502
1649 This value can be used to control on which cp 1503 This value can be used to control on which cpus the watchdog may run.
1650 The default cpumask is all possible cores, bu 1504 The default cpumask is all possible cores, but if ``NO_HZ_FULL`` is
1651 enabled in the kernel config, and cores are s 1505 enabled in the kernel config, and cores are specified with the
1652 ``nohz_full=`` boot argument, those cores are 1506 ``nohz_full=`` boot argument, those cores are excluded by default.
1653 Offline cores can be included in this mask, a 1507 Offline cores can be included in this mask, and if the core is later
1654 brought online, the watchdog will be started 1508 brought online, the watchdog will be started based on the mask value.
1655 1509
1656 Typically this value would only be touched in 1510 Typically this value would only be touched in the ``nohz_full`` case
1657 to re-enable cores that by default were not r 1511 to re-enable cores that by default were not running the watchdog,
1658 if a kernel lockup was suspected on those cor 1512 if a kernel lockup was suspected on those cores.
1659 1513
1660 The argument value is the standard cpulist fo 1514 The argument value is the standard cpulist format for cpumasks,
1661 so for example to enable the watchdog on core 1515 so for example to enable the watchdog on cores 0, 2, 3, and 4 you
1662 might say:: 1516 might say::
1663 1517
1664 echo 0,2-4 > /proc/sys/kernel/watchdog_cpum 1518 echo 0,2-4 > /proc/sys/kernel/watchdog_cpumask
1665 1519
1666 1520
1667 watchdog_thresh 1521 watchdog_thresh
1668 =============== 1522 ===============
1669 1523
1670 This value can be used to control the frequen 1524 This value can be used to control the frequency of hrtimer and NMI
1671 events and the soft and hard lockup threshold 1525 events and the soft and hard lockup thresholds. The default threshold
1672 is 10 seconds. 1526 is 10 seconds.
1673 1527
1674 The softlockup threshold is (``2 * watchdog_t 1528 The softlockup threshold is (``2 * watchdog_thresh``). Setting this
1675 tunable to zero will disable lockup detection 1529 tunable to zero will disable lockup detection altogether.
Linux® is a registered trademark of Linus Torvalds in the United States and other countries.
TOMOYO® is a registered trademark of NTT DATA CORPORATION.