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