1 accept_memory= [MM] !! 1 acpi= [HW,ACPI,X86,ARM64]
2 Format: { eager | lazy <<
3 default: lazy <<
4 By default, unaccepted <<
5 avoid prolonged boot t <<
6 some runtime overhead <<
7 accepted. In most case <<
8 For some workloads or <<
9 accept_memory=eager ca <<
10 at once during boot. <<
11 <<
12 acpi= [HW,ACPI,X86,ARM64,RIS <<
13 Advanced Configuration 2 Advanced Configuration and Power Interface
14 Format: { force | on | 3 Format: { force | on | off | strict | noirq | rsdt |
15 copy_dsdt | !! 4 copy_dsdt }
16 force -- enable ACPI i 5 force -- enable ACPI if default was off
17 on -- enable ACPI but !! 6 on -- enable ACPI but allow fallback to DT [arm64]
18 off -- disable ACPI if 7 off -- disable ACPI if default was on
19 noirq -- do not use AC 8 noirq -- do not use ACPI for IRQ routing
20 strict -- Be less tole 9 strict -- Be less tolerant of platforms that are not
21 strictly ACPI 10 strictly ACPI specification compliant.
22 rsdt -- prefer RSDT ov 11 rsdt -- prefer RSDT over (default) XSDT
23 copy_dsdt -- copy DSDT 12 copy_dsdt -- copy DSDT to memory
24 nospcr -- disable cons !! 13 For ARM64, ONLY "acpi=off", "acpi=on" or "acpi=force"
25 default _seria <<
26 For ARM64, ONLY "acpi= <<
27 "acpi=nospcr" are avai <<
28 For RISCV64, ONLY "acp <<
29 are available 14 are available
30 15
31 See also Documentation 16 See also Documentation/power/runtime_pm.rst, pci=noacpi
32 17
33 acpi_apic_instance= [ACPI,IOAPIC,E !! 18 acpi_apic_instance= [ACPI, IOAPIC]
34 Format: <int> 19 Format: <int>
35 2: use 2nd APIC table, 20 2: use 2nd APIC table, if available
36 1,0: use 1st APIC tabl 21 1,0: use 1st APIC table
37 default: 0 22 default: 0
38 23
39 acpi_backlight= [HW,ACPI] 24 acpi_backlight= [HW,ACPI]
40 { vendor | video | nat 25 { vendor | video | native | none }
41 If set to vendor, pref 26 If set to vendor, prefer vendor-specific driver
42 (e.g. thinkpad_acpi, s 27 (e.g. thinkpad_acpi, sony_acpi, etc.) instead
43 of the ACPI video.ko d 28 of the ACPI video.ko driver.
44 If set to video, use t 29 If set to video, use the ACPI video.ko driver.
45 If set to native, use 30 If set to native, use the device's native backlight mode.
46 If set to none, disabl 31 If set to none, disable the ACPI backlight interface.
47 32
48 acpi_force_32bit_fadt_addr [ACPI,EARLY !! 33 acpi_force_32bit_fadt_addr
49 force FADT to use 32 b 34 force FADT to use 32 bit addresses rather than the
50 64 bit X_* addresses. 35 64 bit X_* addresses. Some firmware have broken 64
51 bit addresses for forc 36 bit addresses for force ACPI ignore these and use
52 the older legacy 32 bi 37 the older legacy 32 bit addresses.
53 38
54 acpica_no_return_repair [HW, ACPI] 39 acpica_no_return_repair [HW, ACPI]
55 Disable AML predefined 40 Disable AML predefined validation mechanism
56 This mechanism can rep 41 This mechanism can repair the evaluation result to make
57 the return objects mor 42 the return objects more ACPI specification compliant.
58 This option is useful 43 This option is useful for developers to identify the
59 root cause of an AML i 44 root cause of an AML interpreter issue when the issue
60 has something to do wi 45 has something to do with the repair mechanism.
61 46
62 acpi.debug_layer= [HW,ACPI,ACPI_ 47 acpi.debug_layer= [HW,ACPI,ACPI_DEBUG]
63 acpi.debug_level= [HW,ACPI,ACPI_ 48 acpi.debug_level= [HW,ACPI,ACPI_DEBUG]
64 Format: <int> 49 Format: <int>
65 CONFIG_ACPI_DEBUG must 50 CONFIG_ACPI_DEBUG must be enabled to produce any ACPI
66 debug output. Bits in 51 debug output. Bits in debug_layer correspond to a
67 _COMPONENT in an ACPI 52 _COMPONENT in an ACPI source file, e.g.,
68 #define _COMPONENT 53 #define _COMPONENT ACPI_EVENTS
69 Bits in debug_level co 54 Bits in debug_level correspond to a level in
70 ACPI_DEBUG_PRINT state 55 ACPI_DEBUG_PRINT statements, e.g.,
71 ACPI_DEBUG_PRINT(( 56 ACPI_DEBUG_PRINT((ACPI_DB_INFO, ...
72 The debug_level mask d 57 The debug_level mask defaults to "info". See
73 Documentation/firmware 58 Documentation/firmware-guide/acpi/debug.rst for more information about
74 debug layers and level 59 debug layers and levels.
75 60
76 Enable processor drive 61 Enable processor driver info messages:
77 acpi.debug_layer=0 62 acpi.debug_layer=0x20000000
78 Enable AML "Debug" out 63 Enable AML "Debug" output, i.e., stores to the Debug
79 object while interpret 64 object while interpreting AML:
80 acpi.debug_layer=0 65 acpi.debug_layer=0xffffffff acpi.debug_level=0x2
81 Enable all messages re 66 Enable all messages related to ACPI hardware:
82 acpi.debug_layer=0 67 acpi.debug_layer=0x2 acpi.debug_level=0xffffffff
83 68
84 Some values produce so 69 Some values produce so much output that the system is
85 unusable. The "log_bu 70 unusable. The "log_buf_len" parameter may be useful
86 if you need to capture 71 if you need to capture more output.
87 72
88 acpi_enforce_resources= [ACPI] 73 acpi_enforce_resources= [ACPI]
89 { strict | lax | no } 74 { strict | lax | no }
90 Check for resource con 75 Check for resource conflicts between native drivers
91 and ACPI OperationRegi 76 and ACPI OperationRegions (SystemIO and SystemMemory
92 only). IO ports and me 77 only). IO ports and memory declared in ACPI might be
93 used by the ACPI subsy 78 used by the ACPI subsystem in arbitrary AML code and
94 can interfere with leg 79 can interfere with legacy drivers.
95 strict (default): acce 80 strict (default): access to resources claimed by ACPI
96 is denied; legacy driv 81 is denied; legacy drivers trying to access reserved
97 resources will fail to 82 resources will fail to bind to device using them.
98 lax: access to resourc 83 lax: access to resources claimed by ACPI is allowed;
99 legacy drivers trying 84 legacy drivers trying to access reserved resources
100 will bind successfully 85 will bind successfully but a warning message is logged.
101 no: ACPI OperationRegi 86 no: ACPI OperationRegions are not marked as reserved,
102 no further checks are 87 no further checks are performed.
103 88
104 acpi_force_table_verification [HW,AC !! 89 acpi_force_table_verification [HW,ACPI]
105 Enable table checksum 90 Enable table checksum verification during early stage.
106 By default, this is di 91 By default, this is disabled due to x86 early mapping
107 size limitation. 92 size limitation.
108 93
109 acpi_irq_balance [HW,ACPI] 94 acpi_irq_balance [HW,ACPI]
110 ACPI will balance acti 95 ACPI will balance active IRQs
111 default in APIC mode 96 default in APIC mode
112 97
113 acpi_irq_nobalance [HW,ACPI] 98 acpi_irq_nobalance [HW,ACPI]
114 ACPI will not move act 99 ACPI will not move active IRQs (default)
115 default in PIC mode 100 default in PIC mode
116 101
117 acpi_irq_isa= [HW,ACPI] If irq_balan 102 acpi_irq_isa= [HW,ACPI] If irq_balance, mark listed IRQs used by ISA
118 Format: <irq>,<irq>... 103 Format: <irq>,<irq>...
119 104
120 acpi_irq_pci= [HW,ACPI] If irq_balan 105 acpi_irq_pci= [HW,ACPI] If irq_balance, clear listed IRQs for
121 use by PCI 106 use by PCI
122 Format: <irq>,<irq>... 107 Format: <irq>,<irq>...
123 108
124 acpi_mask_gpe= [HW,ACPI] 109 acpi_mask_gpe= [HW,ACPI]
125 Due to the existence o 110 Due to the existence of _Lxx/_Exx, some GPEs triggered
126 by unsupported hardwar 111 by unsupported hardware/firmware features can result in
127 GPE floodings that can 112 GPE floodings that cannot be automatically disabled by
128 the GPE dispatcher. 113 the GPE dispatcher.
129 This facility can be u 114 This facility can be used to prevent such uncontrolled
130 GPE floodings. 115 GPE floodings.
131 Format: <byte> or <bit 116 Format: <byte> or <bitmap-list>
132 117
133 acpi_no_auto_serialize [HW,ACPI] 118 acpi_no_auto_serialize [HW,ACPI]
134 Disable auto-serializa 119 Disable auto-serialization of AML methods
135 AML control methods th 120 AML control methods that contain the opcodes to create
136 named objects will be 121 named objects will be marked as "Serialized" by the
137 auto-serialization fea 122 auto-serialization feature.
138 This feature is enable 123 This feature is enabled by default.
139 This option allows to 124 This option allows to turn off the feature.
140 125
141 acpi_no_memhotplug [ACPI] Disable memo 126 acpi_no_memhotplug [ACPI] Disable memory hotplug. Useful for kdump
142 kernels. 127 kernels.
143 128
144 acpi_no_static_ssdt [HW,ACPI,EARLY !! 129 acpi_no_static_ssdt [HW,ACPI]
145 Disable installation o 130 Disable installation of static SSDTs at early boot time
146 By default, SSDTs cont 131 By default, SSDTs contained in the RSDT/XSDT will be
147 installed automaticall 132 installed automatically and they will appear under
148 /sys/firmware/acpi/tab 133 /sys/firmware/acpi/tables.
149 This option turns off 134 This option turns off this feature.
150 Note that specifying t 135 Note that specifying this option does not affect
151 dynamic table installa 136 dynamic table installation which will install SSDT
152 tables to /sys/firmwar 137 tables to /sys/firmware/acpi/tables/dynamic.
153 138
154 acpi_no_watchdog [HW,ACPI,WDT] 139 acpi_no_watchdog [HW,ACPI,WDT]
155 Ignore the ACPI-based 140 Ignore the ACPI-based watchdog interface (WDAT) and let
156 a native driver contro 141 a native driver control the watchdog device instead.
157 142
158 acpi_rsdp= [ACPI,EFI,KEXEC,EARLY] !! 143 acpi_rsdp= [ACPI,EFI,KEXEC]
159 Pass the RSDP address 144 Pass the RSDP address to the kernel, mostly used
160 on machines running EF 145 on machines running EFI runtime service to boot the
161 second kernel for kdum 146 second kernel for kdump.
162 147
163 acpi_os_name= [HW,ACPI] Tell ACPI BI 148 acpi_os_name= [HW,ACPI] Tell ACPI BIOS the name of the OS
164 Format: To spoof as Wi 149 Format: To spoof as Windows 98: ="Microsoft Windows"
165 150
166 acpi_rev_override [ACPI] Override the 151 acpi_rev_override [ACPI] Override the _REV object to return 5 (instead
167 of 2 which is mandated 152 of 2 which is mandated by ACPI 6) as the supported ACPI
168 specification revision 153 specification revision (when using this switch, it may
169 be necessary to carry 154 be necessary to carry out a cold reboot _twice_ in a
170 row to make it take ef 155 row to make it take effect on the platform firmware).
171 156
172 acpi_osi= [HW,ACPI] Modify list 157 acpi_osi= [HW,ACPI] Modify list of supported OS interface strings
173 acpi_osi="string1" 158 acpi_osi="string1" # add string1
174 acpi_osi="!string2" 159 acpi_osi="!string2" # remove string2
175 acpi_osi=!* 160 acpi_osi=!* # remove all strings
176 acpi_osi=! 161 acpi_osi=! # disable all built-in OS vendor
177 162 strings
178 acpi_osi=!! 163 acpi_osi=!! # enable all built-in OS vendor
179 164 strings
180 acpi_osi= 165 acpi_osi= # disable all strings
181 166
182 'acpi_osi=!' can be us 167 'acpi_osi=!' can be used in combination with single or
183 multiple 'acpi_osi="st 168 multiple 'acpi_osi="string1"' to support specific OS
184 vendor string(s). Not 169 vendor string(s). Note that such command can only
185 affect the default sta 170 affect the default state of the OS vendor strings, thus
186 it cannot affect the d 171 it cannot affect the default state of the feature group
187 strings and the curren 172 strings and the current state of the OS vendor strings,
188 specifying it multiple 173 specifying it multiple times through kernel command line
189 is meaningless. This 174 is meaningless. This command is useful when one do not
190 care about the state o 175 care about the state of the feature group strings which
191 should be controlled b 176 should be controlled by the OSPM.
192 Examples: 177 Examples:
193 1. 'acpi_osi=! acpi_ 178 1. 'acpi_osi=! acpi_osi="Windows 2000"' is equivalent
194 to 'acpi_osi="Win 179 to 'acpi_osi="Windows 2000" acpi_osi=!', they all
195 can make '_OSI("W 180 can make '_OSI("Windows 2000")' TRUE.
196 181
197 'acpi_osi=' cannot be 182 'acpi_osi=' cannot be used in combination with other
198 'acpi_osi=' command li 183 'acpi_osi=' command lines, the _OSI method will not
199 exist in the ACPI name 184 exist in the ACPI namespace. NOTE that such command can
200 only affect the _OSI s 185 only affect the _OSI support state, thus specifying it
201 multiple times through 186 multiple times through kernel command line is also
202 meaningless. 187 meaningless.
203 Examples: 188 Examples:
204 1. 'acpi_osi=' can m 189 1. 'acpi_osi=' can make 'CondRefOf(_OSI, Local1)'
205 FALSE. 190 FALSE.
206 191
207 'acpi_osi=!*' can be u 192 'acpi_osi=!*' can be used in combination with single or
208 multiple 'acpi_osi="st 193 multiple 'acpi_osi="string1"' to support specific
209 string(s). Note that 194 string(s). Note that such command can affect the
210 current state of both 195 current state of both the OS vendor strings and the
211 feature group strings, 196 feature group strings, thus specifying it multiple times
212 through kernel command 197 through kernel command line is meaningful. But it may
213 still not able to affe 198 still not able to affect the final state of a string if
214 there are quirks relat 199 there are quirks related to this string. This command
215 is useful when one wan 200 is useful when one want to control the state of the
216 feature group strings 201 feature group strings to debug BIOS issues related to
217 the OSPM features. 202 the OSPM features.
218 Examples: 203 Examples:
219 1. 'acpi_osi="Module 204 1. 'acpi_osi="Module Device" acpi_osi=!*' can make
220 '_OSI("Module Dev 205 '_OSI("Module Device")' FALSE.
221 2. 'acpi_osi=!* acpi 206 2. 'acpi_osi=!* acpi_osi="Module Device"' can make
222 '_OSI("Module Dev 207 '_OSI("Module Device")' TRUE.
223 3. 'acpi_osi=! acpi_ 208 3. 'acpi_osi=! acpi_osi=!* acpi_osi="Windows 2000"' is
224 equivalent to 209 equivalent to
225 'acpi_osi=!* acpi 210 'acpi_osi=!* acpi_osi=! acpi_osi="Windows 2000"'
226 and 211 and
227 'acpi_osi=!* acpi 212 'acpi_osi=!* acpi_osi="Windows 2000" acpi_osi=!',
228 they all will mak 213 they all will make '_OSI("Windows 2000")' TRUE.
229 214
230 acpi_pm_good [X86] 215 acpi_pm_good [X86]
231 Override the pmtimer b 216 Override the pmtimer bug detection: force the kernel
232 to assume that this ma 217 to assume that this machine's pmtimer latches its value
233 and always returns goo 218 and always returns good values.
234 219
235 acpi_sci= [HW,ACPI,EARLY] ACPI S !! 220 acpi_sci= [HW,ACPI] ACPI System Control Interrupt trigger mode
236 Format: { level | edge 221 Format: { level | edge | high | low }
237 222
238 acpi_skip_timer_override [HW,ACPI,EARL !! 223 acpi_skip_timer_override [HW,ACPI]
239 Recognize and ignore I 224 Recognize and ignore IRQ0/pin2 Interrupt Override.
240 For broken nForce2 BIO 225 For broken nForce2 BIOS resulting in XT-PIC timer.
241 226
242 acpi_sleep= [HW,ACPI] Sleep option 227 acpi_sleep= [HW,ACPI] Sleep options
243 Format: { s3_bios, s3_ !! 228 Format: { s3_bios, s3_mode, s3_beep, s4_nohwsig,
244 s4_nohwsig, !! 229 old_ordering, nonvs, sci_force_enable, nobl }
245 sci_force_en <<
246 See Documentation/powe 230 See Documentation/power/video.rst for information on
247 s3_bios and s3_mode. 231 s3_bios and s3_mode.
248 s3_beep is for debuggi 232 s3_beep is for debugging; it makes the PC's speaker beep
249 as soon as the kernel' 233 as soon as the kernel's real-mode entry point is called.
250 s4_hwsig causes the ke <<
251 signature during resum <<
252 refuse to resume if it <<
253 the ACPI specification <<
254 Windows does not do th <<
255 on docking. So the def <<
256 and simply warn when t <<
257 s4_hwsig option is ena <<
258 s4_nohwsig prevents AC 234 s4_nohwsig prevents ACPI hardware signature from being
259 used (or even warned a !! 235 used during resume from hibernation.
260 old_ordering causes th 236 old_ordering causes the ACPI 1.0 ordering of the _PTS
261 control method, with r 237 control method, with respect to putting devices into
262 low power states, to b 238 low power states, to be enforced (the ACPI 2.0 ordering
263 of _PTS is used by def 239 of _PTS is used by default).
264 nonvs prevents the ker 240 nonvs prevents the kernel from saving/restoring the
265 ACPI NVS memory during 241 ACPI NVS memory during suspend/hibernation and resume.
266 sci_force_enable cause 242 sci_force_enable causes the kernel to set SCI_EN directly
267 on resume from S1/S3 ( 243 on resume from S1/S3 (which is against the ACPI spec,
268 but some broken system 244 but some broken systems don't work without it).
269 nobl causes the intern 245 nobl causes the internal blacklist of systems known to
270 behave incorrectly in 246 behave incorrectly in some ways with respect to system
271 suspend and resume to 247 suspend and resume to be ignored (use wisely).
272 248
273 acpi_use_timer_override [HW,ACPI,EARLY !! 249 acpi_use_timer_override [HW,ACPI]
274 Use timer override. Fo 250 Use timer override. For some broken Nvidia NF5 boards
275 that require a timer o 251 that require a timer override, but don't have HPET
276 252
277 add_efi_memmap [EFI,X86,EARLY] Includ !! 253 add_efi_memmap [EFI; X86] Include EFI memory map in
278 kernel's map of availa 254 kernel's map of available physical RAM.
279 255
280 agp= [AGP] 256 agp= [AGP]
281 { off | try_unsupporte 257 { off | try_unsupported }
282 off: disable AGP suppo 258 off: disable AGP support
283 try_unsupported: try t 259 try_unsupported: try to drive unsupported chipsets
284 (may crash com 260 (may crash computer or cause data corruption)
285 261
286 ALSA [HW,ALSA] 262 ALSA [HW,ALSA]
287 See Documentation/soun 263 See Documentation/sound/alsa-configuration.rst
288 264
289 alignment= [KNL,ARM] 265 alignment= [KNL,ARM]
290 Allow the default user 266 Allow the default userspace alignment fault handler
291 behaviour to be specif 267 behaviour to be specified. Bit 0 enables warnings,
292 bit 1 enables fixups, 268 bit 1 enables fixups, and bit 2 sends a segfault.
293 269
294 align_va_addr= [X86-64] 270 align_va_addr= [X86-64]
295 Align virtual addresse 271 Align virtual addresses by clearing slice [14:12] when
296 allocating a VMA at pr 272 allocating a VMA at process creation time. This option
297 gives you up to 3% per 273 gives you up to 3% performance improvement on AMD F15h
298 machines (where it is 274 machines (where it is enabled by default) for a
299 CPU-intensive style be 275 CPU-intensive style benchmark, and it can vary highly in
300 a microbenchmark depen 276 a microbenchmark depending on workload and compiler.
301 277
302 32: only for 32-bit pr 278 32: only for 32-bit processes
303 64: only for 64-bit pr 279 64: only for 64-bit processes
304 on: enable for both 32 280 on: enable for both 32- and 64-bit processes
305 off: disable for both 281 off: disable for both 32- and 64-bit processes
306 282
307 alloc_snapshot [FTRACE] 283 alloc_snapshot [FTRACE]
308 Allocate the ftrace sn 284 Allocate the ftrace snapshot buffer on boot up when the
309 main buffer is allocat 285 main buffer is allocated. This is handy if debugging
310 and you need to use tr 286 and you need to use tracing_snapshot() on boot up, and
311 do not want to use tra 287 do not want to use tracing_snapshot_alloc() as it needs
312 to be done where GFP_K 288 to be done where GFP_KERNEL allocations are allowed.
313 289
314 allow_mismatched_32bit_el0 [ARM64,EARL !! 290 allow_mismatched_32bit_el0 [ARM64]
315 Allow execve() of 32-b 291 Allow execve() of 32-bit applications and setting of the
316 PER_LINUX32 personalit 292 PER_LINUX32 personality on systems where only a strict
317 subset of the CPUs sup 293 subset of the CPUs support 32-bit EL0. When this
318 parameter is present, 294 parameter is present, the set of CPUs supporting 32-bit
319 EL0 is indicated by /s 295 EL0 is indicated by /sys/devices/system/cpu/aarch32_el0
320 and hot-unplug operati 296 and hot-unplug operations may be restricted.
321 297
322 See Documentation/arch !! 298 See Documentation/arm64/asymmetric-32bit.rst for more
323 information. 299 information.
324 300
325 amd_iommu= [HW,X86-64] 301 amd_iommu= [HW,X86-64]
326 Pass parameters to the 302 Pass parameters to the AMD IOMMU driver in the system.
327 Possible values are: 303 Possible values are:
328 fullflush - Deprecated 304 fullflush - Deprecated, equivalent to iommu.strict=1
329 off - do not ini 305 off - do not initialize any AMD IOMMU found in
330 the system 306 the system
331 force_isolation - Forc 307 force_isolation - Force device isolation for all
332 devi 308 devices. The IOMMU driver is not
333 allo 309 allowed anymore to lift isolation
334 requ 310 requirements as needed. This option
335 does 311 does not override iommu=pt
336 force_enable - Force e 312 force_enable - Force enable the IOMMU on platforms known
337 to be b 313 to be buggy with IOMMU enabled. Use this
338 option 314 option with care.
339 pgtbl_v1 - Use v1 <<
340 pgtbl_v2 - Use v2 <<
341 irtcachedis - Disable <<
342 315
343 amd_iommu_dump= [HW,X86-64] 316 amd_iommu_dump= [HW,X86-64]
344 Enable AMD IOMMU drive 317 Enable AMD IOMMU driver option to dump the ACPI table
345 for AMD IOMMU. With th 318 for AMD IOMMU. With this option enabled, AMD IOMMU
346 driver will print ACPI 319 driver will print ACPI tables for AMD IOMMU during
347 IOMMU initialization. 320 IOMMU initialization.
348 321
349 amd_iommu_intr= [HW,X86-64] 322 amd_iommu_intr= [HW,X86-64]
350 Specifies one of the f 323 Specifies one of the following AMD IOMMU interrupt
351 remapping modes: 324 remapping modes:
352 legacy - Use legac 325 legacy - Use legacy interrupt remapping mode.
353 vapic - Use virtu 326 vapic - Use virtual APIC mode, which allows IOMMU
354 to inject 327 to inject interrupts directly into guest.
355 This mode 328 This mode requires kvm-amd.avic=1.
356 (Default 329 (Default when IOMMU HW support is present.)
357 330
358 amd_pstate= [X86,EARLY] <<
359 disable <<
360 Do not enable amd_ps <<
361 scaling driver for t <<
362 passive <<
363 Use amd_pstate with <<
364 In this mode autonom <<
365 Driver requests a de <<
366 tries to match the s <<
367 satisfied by guarant <<
368 active <<
369 Use amd_pstate_epp d <<
370 driver provides a hi <<
371 to bias toward perfo <<
372 to the CPPC firmware <<
373 calculate the runtim <<
374 frequency. <<
375 guided <<
376 Activate guided auto <<
377 maximum performance <<
378 selects a performanc <<
379 to the current workl <<
380 <<
381 amd_prefcore= <<
382 [X86] <<
383 disable <<
384 Disable amd-pstate p <<
385 <<
386 amijoy.map= [HW,JOY] Amiga joystic 331 amijoy.map= [HW,JOY] Amiga joystick support
387 Map of devices attache 332 Map of devices attached to JOY0DAT and JOY1DAT
388 Format: <a>,<b> 333 Format: <a>,<b>
389 See also Documentation 334 See also Documentation/input/joydev/joystick.rst
390 335
391 analog.map= [HW,JOY] Analog joysti 336 analog.map= [HW,JOY] Analog joystick and gamepad support
392 Specifies type or capa 337 Specifies type or capabilities of an analog joystick
393 connected to one of 16 338 connected to one of 16 gameports
394 Format: <type1>,<type2 339 Format: <type1>,<type2>,..<type16>
395 340
396 apc= [HW,SPARC] 341 apc= [HW,SPARC]
397 Power management funct 342 Power management functions (SPARCstation-4/5 + deriv.)
398 Format: noidle 343 Format: noidle
399 Disable APC CPU standb 344 Disable APC CPU standby support. SPARCstation-Fox does
400 not play well with APC 345 not play well with APC CPU idle - disable it if you have
401 APC and your system cr 346 APC and your system crashes randomly.
402 347
403 apic= [APIC,X86,EARLY] Advan !! 348 apic= [APIC,X86] Advanced Programmable Interrupt Controller
404 Change the output verb 349 Change the output verbosity while booting
405 Format: { quiet (defau 350 Format: { quiet (default) | verbose | debug }
406 Change the amount of d 351 Change the amount of debugging information output
407 when initialising the 352 when initialising the APIC and IO-APIC components.
408 For X86-32, this can a 353 For X86-32, this can also be used to specify an APIC
409 driver name. 354 driver name.
410 Format: apic=driver_na 355 Format: apic=driver_name
411 Examples: apic=bigsmp 356 Examples: apic=bigsmp
412 357
413 apic_extnmi= [APIC,X86,EARLY] Exter !! 358 apic_extnmi= [APIC,X86] External NMI delivery setting
414 Format: { bsp (default 359 Format: { bsp (default) | all | none }
415 bsp: External NMI is 360 bsp: External NMI is delivered only to CPU 0
416 all: External NMIs ar 361 all: External NMIs are broadcast to all CPUs as a
417 backup of CPU 0 362 backup of CPU 0
418 none: External NMI is 363 none: External NMI is masked for all CPUs. This is
419 useful so that a 364 useful so that a dump capture kernel won't be
420 shot down by NMI 365 shot down by NMI
421 366
422 autoconf= [IPV6] 367 autoconf= [IPV6]
423 See Documentation/netw 368 See Documentation/networking/ipv6.rst.
424 369
>> 370 show_lapic= [APIC,X86] Advanced Programmable Interrupt Controller
>> 371 Limit apic dumping. The parameter defines the maximal
>> 372 number of local apics being dumped. Also it is possible
>> 373 to set it to "all" by meaning -- no limit here.
>> 374 Format: { 1 (default) | 2 | ... | all }.
>> 375 The parameter valid if only apic=debug or
>> 376 apic=verbose is specified.
>> 377 Example: apic=debug show_lapic=all
>> 378
425 apm= [APM] Advanced Power M 379 apm= [APM] Advanced Power Management
426 See header of arch/x86 380 See header of arch/x86/kernel/apm_32.c.
427 381
428 apparmor= [APPARMOR] Disable or <<
429 Format: { "0" | "1" } <<
430 See security/apparmor/ <<
431 0 -- disable. <<
432 1 -- enable. <<
433 Default value is set v <<
434 <<
435 arcrimi= [HW,NET] ARCnet - "RIM 382 arcrimi= [HW,NET] ARCnet - "RIM I" (entirely mem-mapped) cards
436 Format: <io>,<irq>,<no 383 Format: <io>,<irq>,<nodeID>
437 384
438 arm64.no32bit_el0 [ARM64] Unconditiona <<
439 32 bit applications. <<
440 <<
441 arm64.nobti [ARM64] Unconditionall 385 arm64.nobti [ARM64] Unconditionally disable Branch Target
442 Identification support 386 Identification support
443 387
444 arm64.nomops [ARM64] Unconditionall <<
445 Set instructions suppo <<
446 <<
447 arm64.nomte [ARM64] Unconditionall <<
448 support <<
449 <<
450 arm64.nopauth [ARM64] Unconditionall 388 arm64.nopauth [ARM64] Unconditionally disable Pointer Authentication
451 support 389 support
452 390
453 arm64.nosme [ARM64] Unconditionall !! 391 arm64.nomte [ARM64] Unconditionally disable Memory Tagging Extension
454 Extension support !! 392 support
455 <<
456 arm64.nosve [ARM64] Unconditionall <<
457 Extension support <<
458 393
459 ataflop= [HW,M68k] 394 ataflop= [HW,M68k]
460 395
461 atarimouse= [HW,MOUSE] Atari Mouse 396 atarimouse= [HW,MOUSE] Atari Mouse
462 397
463 atkbd.extra= [HW] Enable extra LEDs 398 atkbd.extra= [HW] Enable extra LEDs and keys on IBM RapidAccess,
464 EzKey and similar keyb 399 EzKey and similar keyboards
465 400
466 atkbd.reset= [HW] Reset keyboard du 401 atkbd.reset= [HW] Reset keyboard during initialization
467 402
468 atkbd.set= [HW] Select keyboard c 403 atkbd.set= [HW] Select keyboard code set
469 Format: <int> (2 = AT 404 Format: <int> (2 = AT (default), 3 = PS/2)
470 405
471 atkbd.scroll= [HW] Enable scroll whe 406 atkbd.scroll= [HW] Enable scroll wheel on MS Office and similar
472 keyboards 407 keyboards
473 408
474 atkbd.softraw= [HW] Choose between sy 409 atkbd.softraw= [HW] Choose between synthetic and real raw mode
475 Format: <bool> (0 = re 410 Format: <bool> (0 = real, 1 = synthetic (default))
476 411
477 atkbd.softrepeat= [HW] 412 atkbd.softrepeat= [HW]
478 Use software keyboard 413 Use software keyboard repeat
479 414
480 audit= [KNL] Enable the audit 415 audit= [KNL] Enable the audit sub-system
481 Format: { "0" | "1" | 416 Format: { "0" | "1" | "off" | "on" }
482 0 | off - kernel audit 417 0 | off - kernel audit is disabled and can not be
483 enabled until the 418 enabled until the next reboot
484 unset - kernel audit i 419 unset - kernel audit is initialized but disabled and
485 will be fully enab 420 will be fully enabled by the userspace auditd.
486 1 | on - kernel audit 421 1 | on - kernel audit is initialized and partially
487 enabled, storing a 422 enabled, storing at most audit_backlog_limit
488 messages in RAM un 423 messages in RAM until it is fully enabled by the
489 userspace auditd. 424 userspace auditd.
490 Default: unset 425 Default: unset
491 426
492 audit_backlog_limit= [KNL] Set the aud 427 audit_backlog_limit= [KNL] Set the audit queue size limit.
493 Format: <int> (must be 428 Format: <int> (must be >=0)
494 Default: 64 429 Default: 64
495 430
496 bau= [X86_UV] Enable the BA 431 bau= [X86_UV] Enable the BAU on SGI UV. The default
497 behavior is to disable 432 behavior is to disable the BAU (i.e. bau=0).
498 Format: { "0" | "1" } 433 Format: { "0" | "1" }
499 0 - Disable the BAU. 434 0 - Disable the BAU.
500 1 - Enable the BAU. 435 1 - Enable the BAU.
501 unset - Disable the BA 436 unset - Disable the BAU.
502 437
503 baycom_epp= [HW,AX25] 438 baycom_epp= [HW,AX25]
504 Format: <io>,<mode> 439 Format: <io>,<mode>
505 440
506 baycom_par= [HW,AX25] BayCom Paral 441 baycom_par= [HW,AX25] BayCom Parallel Port AX.25 Modem
507 Format: <io>,<mode> 442 Format: <io>,<mode>
508 See header of drivers/ 443 See header of drivers/net/hamradio/baycom_par.c.
509 444
510 baycom_ser_fdx= [HW,AX25] 445 baycom_ser_fdx= [HW,AX25]
511 BayCom Serial Port AX. 446 BayCom Serial Port AX.25 Modem (Full Duplex Mode)
512 Format: <io>,<irq>,<mo 447 Format: <io>,<irq>,<mode>[,<baud>]
513 See header of drivers/ 448 See header of drivers/net/hamradio/baycom_ser_fdx.c.
514 449
515 baycom_ser_hdx= [HW,AX25] 450 baycom_ser_hdx= [HW,AX25]
516 BayCom Serial Port AX. 451 BayCom Serial Port AX.25 Modem (Half Duplex Mode)
517 Format: <io>,<irq>,<mo 452 Format: <io>,<irq>,<mode>
518 See header of drivers/ 453 See header of drivers/net/hamradio/baycom_ser_hdx.c.
519 454
520 bert_disable [ACPI] <<
521 Disable BERT OS suppor <<
522 <<
523 bgrt_disable [ACPI,X86,EARLY] <<
524 Disable BGRT to avoid <<
525 <<
526 blkdevparts= Manual partition parsi 455 blkdevparts= Manual partition parsing of block device(s) for
527 embedded devices based 456 embedded devices based on command line input.
528 See Documentation/bloc 457 See Documentation/block/cmdline-partition.rst
529 458
530 boot_delay= [KNL,EARLY] !! 459 boot_delay= Milliseconds to delay each printk during boot.
531 Milliseconds to delay !! 460 Values larger than 10 seconds (10000) are changed to
532 Only works if CONFIG_B !! 461 no delay (0).
533 and you may also have <<
534 values larger than 10 <<
535 erroneous and ignored. <<
536 Format: integer 462 Format: integer
537 463
538 bootconfig [KNL,EARLY] !! 464 bootconfig [KNL]
539 Extended command line 465 Extended command line options can be added to an initrd
540 and this will cause th 466 and this will cause the kernel to look for it.
541 467
542 See Documentation/admi 468 See Documentation/admin-guide/bootconfig.rst
543 469
>> 470 bert_disable [ACPI]
>> 471 Disable BERT OS support on buggy BIOSes.
>> 472
>> 473 bgrt_disable [ACPI][X86]
>> 474 Disable BGRT to avoid flickering OEM logo.
>> 475
544 bttv.card= [HW,V4L] bttv (bt848 + 476 bttv.card= [HW,V4L] bttv (bt848 + bt878 based grabber cards)
545 bttv.radio= Most important insmod 477 bttv.radio= Most important insmod options are available as
546 kernel args too. 478 kernel args too.
547 bttv.pll= See Documentation/admi 479 bttv.pll= See Documentation/admin-guide/media/bttv.rst
548 bttv.tuner= 480 bttv.tuner=
549 481
550 bulk_remove=off [PPC] This parameter 482 bulk_remove=off [PPC] This parameter disables the use of the pSeries
551 firmware feature for f 483 firmware feature for flushing multiple hpte entries
552 at a time. 484 at a time.
553 485
554 c101= [NET] Moxa C101 synchr 486 c101= [NET] Moxa C101 synchronous serial card
555 487
556 cachesize= [BUGS=X86-32] Override 488 cachesize= [BUGS=X86-32] Override level 2 CPU cache size detection.
557 Sometimes CPU hardware 489 Sometimes CPU hardware bugs make them report the cache
558 size incorrectly. The 490 size incorrectly. The kernel will attempt work arounds
559 to fix known problems, 491 to fix known problems, but for some CPUs it is not
560 possible to determine 492 possible to determine what the correct size should be.
561 This option provides a 493 This option provides an override for these situations.
562 494
563 carrier_timeout= 495 carrier_timeout=
564 [NET] Specifies amount 496 [NET] Specifies amount of time (in seconds) that
565 the kernel should wait 497 the kernel should wait for a network carrier. By default
566 it waits 120 seconds. 498 it waits 120 seconds.
567 499
568 ca_keys= [KEYS] This parameter 500 ca_keys= [KEYS] This parameter identifies a specific key(s) on
569 the system trusted key 501 the system trusted keyring to be used for certificate
570 trust validation. 502 trust validation.
571 format: { id:<keyid> | 503 format: { id:<keyid> | builtin }
572 504
573 cca= [MIPS,EARLY] Override !! 505 cca= [MIPS] Override the kernel pages' cache coherency
574 algorithm. Accepted v 506 algorithm. Accepted values range from 0 to 7
575 inclusive. See arch/mi 507 inclusive. See arch/mips/include/asm/pgtable-bits.h
576 for platform specific 508 for platform specific values (SB1, Loongson3 and
577 others). 509 others).
578 510
579 ccw_timeout_log [S390] 511 ccw_timeout_log [S390]
580 See Documentation/arch !! 512 See Documentation/s390/common_io.rst for details.
581 513
582 cgroup_disable= [KNL] Disable a partic 514 cgroup_disable= [KNL] Disable a particular controller or optional feature
583 Format: {name of the c 515 Format: {name of the controller(s) or feature(s) to disable}
584 The effects of cgroup_ 516 The effects of cgroup_disable=foo are:
585 - foo isn't auto-mount 517 - foo isn't auto-mounted if you mount all cgroups in
586 a single hierarchy 518 a single hierarchy
587 - foo isn't visible as 519 - foo isn't visible as an individually mountable
588 subsystem 520 subsystem
589 - if foo is an optiona 521 - if foo is an optional feature then the feature is
590 disabled and corresp 522 disabled and corresponding cgroup files are not
591 created 523 created
592 {Currently only "memor 524 {Currently only "memory" controller deal with this and
593 cut the overhead, othe 525 cut the overhead, others just disable the usage. So
594 only cgroup_disable=me 526 only cgroup_disable=memory is actually worthy}
595 Specifying "pressure" 527 Specifying "pressure" disables per-cgroup pressure
596 stall information acco 528 stall information accounting feature
597 529
598 cgroup_no_v1= [KNL] Disable cgroup c 530 cgroup_no_v1= [KNL] Disable cgroup controllers and named hierarchies in v1
599 Format: { { controller 531 Format: { { controller | "all" | "named" }
600 [,{ controll 532 [,{ controller | "all" | "named" }...] }
601 Like cgroup_disable, b 533 Like cgroup_disable, but only applies to cgroup v1;
602 the blacklisted contro 534 the blacklisted controllers remain available in cgroup2.
603 "all" blacklists all c 535 "all" blacklists all controllers and "named" disables
604 named mounts. Specifyi 536 named mounts. Specifying both "all" and "named" disables
605 all v1 hierarchies. 537 all v1 hierarchies.
606 538
607 cgroup_favordynmods= [KNL] Enable or D <<
608 Format: { "true" | "fa <<
609 Defaults to the value <<
610 <<
611 cgroup.memory= [KNL] Pass options to 539 cgroup.memory= [KNL] Pass options to the cgroup memory controller.
612 Format: <string> 540 Format: <string>
613 nosocket -- Disable so 541 nosocket -- Disable socket memory accounting.
614 nokmem -- Disable kern 542 nokmem -- Disable kernel memory accounting.
615 nobpf -- Disable BPF m <<
616 543
617 checkreqprot= [SELINUX] Set initial !! 544 checkreqprot [SELINUX] Set initial checkreqprot flag value.
618 Format: { "0" | "1" } 545 Format: { "0" | "1" }
619 See security/selinux/K 546 See security/selinux/Kconfig help text.
620 0 -- check protection 547 0 -- check protection applied by kernel (includes
621 any implied ex 548 any implied execute protection).
622 1 -- check protection 549 1 -- check protection requested by application.
623 Default value is set v 550 Default value is set via a kernel config option.
624 Value can be changed a 551 Value can be changed at runtime via
625 /sys/fs/selinu 552 /sys/fs/selinux/checkreqprot.
626 Setting checkreqprot t 553 Setting checkreqprot to 1 is deprecated.
627 554
628 cio_ignore= [S390] 555 cio_ignore= [S390]
629 See Documentation/arch !! 556 See Documentation/s390/common_io.rst for details.
630 <<
631 clearcpuid=X[,X...] [X86] <<
632 Disable CPUID feature <<
633 arch/x86/include/asm/c <<
634 numbers X. Note the Li <<
635 stable over kernel opt <<
636 ones should be. <<
637 X can also be a string <<
638 in /proc/cpuinfo which <<
639 instability issue. How <<
640 in /proc/cpuinfo. <<
641 Note that using this o <<
642 Also note that user pr <<
643 or using the feature w <<
644 will still see it. Thi <<
645 being used by the kern <<
646 Also note the kernel m <<
647 some critical bits. <<
648 <<
649 clk_ignore_unused 557 clk_ignore_unused
650 [CLK] 558 [CLK]
651 Prevents the clock fra 559 Prevents the clock framework from automatically gating
652 clocks that have not b 560 clocks that have not been explicitly enabled by a Linux
653 device driver but are 561 device driver but are enabled in hardware at reset or
654 by the bootloader/firm 562 by the bootloader/firmware. Note that this does not
655 force such clocks to b 563 force such clocks to be always-on nor does it reserve
656 those clocks in any wa 564 those clocks in any way. This parameter is useful for
657 debug and development, 565 debug and development, but should not be needed on a
658 platform with proper d 566 platform with proper driver support. For more
659 information, see Docum 567 information, see Documentation/driver-api/clk.rst.
660 568
661 clock= [BUGS=X86-32, HW] gett 569 clock= [BUGS=X86-32, HW] gettimeofday clocksource override.
662 [Deprecated] 570 [Deprecated]
663 Forces specified clock 571 Forces specified clocksource (if available) to be used
664 when calculating getti 572 when calculating gettimeofday(). If specified
665 clocksource is not ava 573 clocksource is not available, it defaults to PIT.
666 Format: { pit | tsc | 574 Format: { pit | tsc | cyclone | pmtmr }
667 575
668 clocksource= Override the default c 576 clocksource= Override the default clocksource
669 Format: <string> 577 Format: <string>
670 Override the default c 578 Override the default clocksource and use the clocksource
671 with the name specifie 579 with the name specified.
672 Some clocksource names 580 Some clocksource names to choose from, depending on
673 the platform: 581 the platform:
674 [all] jiffies (this is 582 [all] jiffies (this is the base, fallback clocksource)
675 [ACPI] acpi_pm 583 [ACPI] acpi_pm
676 [ARM] imx_timer1,OSTS, 584 [ARM] imx_timer1,OSTS,netx_timer,mpu_timer2,
677 pxa_timer,time 585 pxa_timer,timer3,32k_counter,timer0_1
678 [X86-32] pit,hpet,tsc; 586 [X86-32] pit,hpet,tsc;
679 scx200_hrt on 587 scx200_hrt on Geode; cyclone on IBM x440
680 [MIPS] MIPS 588 [MIPS] MIPS
681 [PARISC] cr16 589 [PARISC] cr16
682 [S390] tod 590 [S390] tod
683 [SH] SuperH 591 [SH] SuperH
684 [SPARC64] tick 592 [SPARC64] tick
685 [X86-64] hpet,tsc 593 [X86-64] hpet,tsc
686 594
687 clocksource.arm_arch_timer.evtstrm= 595 clocksource.arm_arch_timer.evtstrm=
688 [ARM,ARM64,EARLY] !! 596 [ARM,ARM64]
689 Format: <bool> 597 Format: <bool>
690 Enable/disable the eve 598 Enable/disable the eventstream feature of the ARM
691 architected timer so t 599 architected timer so that code using WFE-based polling
692 loops can be debugged 600 loops can be debugged more effectively on production
693 systems. 601 systems.
694 602
695 clocksource.verify_n_cpus= [KNL] 603 clocksource.verify_n_cpus= [KNL]
696 Limit the number of CP 604 Limit the number of CPUs checked for clocksources
697 marked with CLOCK_SOUR 605 marked with CLOCK_SOURCE_VERIFY_PERCPU that
698 are marked unstable du 606 are marked unstable due to excessive skew.
699 A negative value says 607 A negative value says to check all CPUs, while
700 zero says not to check 608 zero says not to check any. Values larger than
701 nr_cpu_ids are silentl 609 nr_cpu_ids are silently truncated to nr_cpu_ids.
702 The actual CPUs are ch 610 The actual CPUs are chosen randomly, with
703 no replacement if the 611 no replacement if the same CPU is chosen twice.
704 612
705 clocksource-wdtest.holdoff= [KNL] 613 clocksource-wdtest.holdoff= [KNL]
706 Set the time in second 614 Set the time in seconds that the clocksource
707 watchdog test waits be 615 watchdog test waits before commencing its tests.
708 Defaults to zero when 616 Defaults to zero when built as a module and to
709 10 seconds when built 617 10 seconds when built into the kernel.
710 618
>> 619 clearcpuid=BITNUM[,BITNUM...] [X86]
>> 620 Disable CPUID feature X for the kernel. See
>> 621 arch/x86/include/asm/cpufeatures.h for the valid bit
>> 622 numbers. Note the Linux specific bits are not necessarily
>> 623 stable over kernel options, but the vendor specific
>> 624 ones should be.
>> 625 Also note that user programs calling CPUID directly
>> 626 or using the feature without checking anything
>> 627 will still see it. This just prevents it from
>> 628 being used by the kernel or shown in /proc/cpuinfo.
>> 629 Also note the kernel might malfunction if you disable
>> 630 some critical bits.
>> 631
711 cma=nn[MG]@[start[MG][-end[MG]]] 632 cma=nn[MG]@[start[MG][-end[MG]]]
712 [KNL,CMA,EARLY] !! 633 [KNL,CMA]
713 Sets the size of kerne 634 Sets the size of kernel global memory area for
714 contiguous memory allo 635 contiguous memory allocations and optionally the
715 placement constraint b 636 placement constraint by the physical address range of
716 memory allocations. A 637 memory allocations. A value of 0 disables CMA
717 altogether. For more i 638 altogether. For more information, see
718 kernel/dma/contiguous. 639 kernel/dma/contiguous.c
719 640
720 cma_pernuma=nn[MG] 641 cma_pernuma=nn[MG]
721 [KNL,CMA,EARLY] !! 642 [ARM64,KNL,CMA]
722 Sets the size of kerne 643 Sets the size of kernel per-numa memory area for
723 contiguous memory allo 644 contiguous memory allocations. A value of 0 disables
724 per-numa CMA altogethe 645 per-numa CMA altogether. And If this option is not
725 specified, the default !! 646 specificed, the default value is 0.
726 With per-numa CMA enab 647 With per-numa CMA enabled, DMA users on node nid will
727 first try to allocate 648 first try to allocate buffer from the pernuma area
728 which is located in no 649 which is located in node nid, if the allocation fails,
729 they will fallback to 650 they will fallback to the global default memory area.
730 651
731 numa_cma=<node>:nn[MG][,<node>:nn[MG]] <<
732 [KNL,CMA,EARLY] <<
733 Sets the size of kerne <<
734 contiguous memory allo <<
735 area for the specified <<
736 <<
737 With numa CMA enabled, <<
738 first try to allocate <<
739 which is located in no <<
740 they will fallback to <<
741 <<
742 cmo_free_hint= [PPC] Format: { yes | 652 cmo_free_hint= [PPC] Format: { yes | no }
743 Specify whether pages 653 Specify whether pages are marked as being inactive
744 when they are freed. 654 when they are freed. This is used in CMO environments
745 to determine OS memory 655 to determine OS memory pressure for page stealing by
746 a hypervisor. 656 a hypervisor.
747 Default: yes 657 Default: yes
748 658
749 coherent_pool=nn[KMG] [ARM,KNL,EARLY !! 659 coherent_pool=nn[KMG] [ARM,KNL]
750 Sets the size of memor 660 Sets the size of memory pool for coherent, atomic dma
751 allocations, by defaul 661 allocations, by default set to 256K.
752 662
753 com20020= [HW,NET] ARCnet - COM2 663 com20020= [HW,NET] ARCnet - COM20020 chipset
754 Format: 664 Format:
755 <io>[,<irq>[,<nodeID>[ 665 <io>[,<irq>[,<nodeID>[,<backplane>[,<ckp>[,<timeout>]]]]]
756 666
757 com90io= [HW,NET] ARCnet - COM9 667 com90io= [HW,NET] ARCnet - COM90xx chipset (IO-mapped buffers)
758 Format: <io>[,<irq>] 668 Format: <io>[,<irq>]
759 669
760 com90xx= [HW,NET] 670 com90xx= [HW,NET]
761 ARCnet - COM90xx chips 671 ARCnet - COM90xx chipset (memory-mapped buffers)
762 Format: <io>[,<irq>[,< 672 Format: <io>[,<irq>[,<memstart>]]
763 673
764 condev= [HW,S390] console devi 674 condev= [HW,S390] console device
765 conmode= 675 conmode=
766 676
767 con3215_drop= [S390,EARLY] 3215 cons <<
768 Format: y|n|Y|N|1|0 <<
769 When set to true, drop <<
770 the console buffer is <<
771 operator using a 3270 <<
772 x3270) does not have t <<
773 console output to adva <<
774 This leads to a much f <<
775 terminal emulator is a <<
776 emulator is used, this <<
777 <<
778 console= [KNL] Output console d 677 console= [KNL] Output console device and options.
779 678
780 tty<n> Use the virtual consol 679 tty<n> Use the virtual console device <n>.
781 680
782 ttyS<n>[,options] 681 ttyS<n>[,options]
783 ttyUSB0[,options] 682 ttyUSB0[,options]
784 Use the specified seri 683 Use the specified serial port. The options are of
785 the form "bbbbpnf", wh 684 the form "bbbbpnf", where "bbbb" is the baud rate,
786 "p" is parity ("n", "o 685 "p" is parity ("n", "o", or "e"), "n" is number of
787 bits, and "f" is flow 686 bits, and "f" is flow control ("r" for RTS or
788 omit it). Default is 687 omit it). Default is "9600n8".
789 688
790 See Documentation/admi 689 See Documentation/admin-guide/serial-console.rst for more
791 information. See 690 information. See
792 Documentation/networki 691 Documentation/networking/netconsole.rst for an
793 alternative. 692 alternative.
794 693
795 <DEVNAME>:<n>.<n>[,options] <<
796 Use the specified seri <<
797 The addressing uses DE <<
798 device, followed by th <<
799 and the serial port in <<
800 as documented for the <<
801 <<
802 The mapping of the ser <<
803 can be viewed with: <<
804 <<
805 $ ls -d /sys/bus/seria <<
806 /sys/bus/serial-base/d <<
807 <<
808 In the above example, <<
809 console=00:04:0.0. Not <<
810 way will only get adde <<
811 is ready. The use of a <<
812 the console may be des <<
813 <<
814 uart[8250],io,<addr>[,options] 694 uart[8250],io,<addr>[,options]
815 uart[8250],mmio,<addr>[,option 695 uart[8250],mmio,<addr>[,options]
816 uart[8250],mmio16,<addr>[,opti 696 uart[8250],mmio16,<addr>[,options]
817 uart[8250],mmio32,<addr>[,opti 697 uart[8250],mmio32,<addr>[,options]
818 uart[8250],0x<addr>[,options] 698 uart[8250],0x<addr>[,options]
819 Start an early, polled 699 Start an early, polled-mode console on the 8250/16550
820 UART at the specified 700 UART at the specified I/O port or MMIO address,
821 switching to the match 701 switching to the matching ttyS device later.
822 MMIO inter-register ad 702 MMIO inter-register address stride is either 8-bit
823 (mmio), 16-bit (mmio16 703 (mmio), 16-bit (mmio16), or 32-bit (mmio32).
824 If none of [io|mmio|mm 704 If none of [io|mmio|mmio16|mmio32], <addr> is assumed
825 to be equivalent to 'm 705 to be equivalent to 'mmio'. 'options' are specified in
826 the same format descri 706 the same format described for ttyS above; if unspecified,
827 the h/w is not re-init 707 the h/w is not re-initialized.
828 708
829 hvc<n> Use the hypervisor con 709 hvc<n> Use the hypervisor console device <n>. This is for
830 both Xen and PowerPC h 710 both Xen and PowerPC hypervisors.
831 711
832 { null | "" } <<
833 Use to disable console <<
834 console messages disca <<
835 This must be the only <<
836 kernel command line. <<
837 <<
838 If the device connected to the 712 If the device connected to the port is not a TTY but a braille
839 device, prepend "brl," before 713 device, prepend "brl," before the device type, for instance
840 console=brl,ttyS0 714 console=brl,ttyS0
841 For now, only VisioBraille is 715 For now, only VisioBraille is supported.
842 716
843 console_msg_format= 717 console_msg_format=
844 [KNL] Change console m 718 [KNL] Change console messages format
845 default 719 default
846 By default we print me 720 By default we print messages on consoles in
847 "[time stamp] text\n" 721 "[time stamp] text\n" format (time stamp may not be
848 printed, depending on 722 printed, depending on CONFIG_PRINTK_TIME or
849 `printk_time' param). 723 `printk_time' param).
850 syslog 724 syslog
851 Switch to syslog forma 725 Switch to syslog format: "<%u>[time stamp] text\n"
852 IOW, each message will 726 IOW, each message will have a facility and loglevel
853 prefix. The format is 727 prefix. The format is similar to one used by syslog()
854 syscall, or to executi 728 syscall, or to executing "dmesg -S --raw" or to reading
855 from /proc/kmsg. 729 from /proc/kmsg.
856 730
857 consoleblank= [KNL] The console blan 731 consoleblank= [KNL] The console blank (screen saver) timeout in
858 seconds. A value of 0 732 seconds. A value of 0 disables the blank timer.
859 Defaults to 0. 733 Defaults to 0.
860 734
861 coredump_filter= 735 coredump_filter=
862 [KNL] Change the defau 736 [KNL] Change the default value for
863 /proc/<pid>/coredump_f 737 /proc/<pid>/coredump_filter.
864 See also Documentation 738 See also Documentation/filesystems/proc.rst.
865 739
866 coresight_cpu_debug.enable 740 coresight_cpu_debug.enable
867 [ARM,ARM64] 741 [ARM,ARM64]
868 Format: <bool> 742 Format: <bool>
869 Enable/disable the CPU 743 Enable/disable the CPU sampling based debugging.
870 0: default value, disa 744 0: default value, disable debugging
871 1: enable debugging at 745 1: enable debugging at boot time
872 746
873 cpcihp_generic= [HW,PCI] Generic port <<
874 Format: <<
875 <first_slot>,<last_slo <<
876 <<
877 cpuidle.off=1 [CPU_IDLE] 747 cpuidle.off=1 [CPU_IDLE]
878 disable the cpuidle su 748 disable the cpuidle sub-system
879 749
880 cpuidle.governor= 750 cpuidle.governor=
881 [CPU_IDLE] Name of the 751 [CPU_IDLE] Name of the cpuidle governor to use.
882 752
883 cpufreq.off=1 [CPU_FREQ] 753 cpufreq.off=1 [CPU_FREQ]
884 disable the cpufreq su 754 disable the cpufreq sub-system
885 755
886 cpufreq.default_governor= 756 cpufreq.default_governor=
887 [CPU_FREQ] Name of the 757 [CPU_FREQ] Name of the default cpufreq governor or
888 policy to use. This go 758 policy to use. This governor must be registered in the
889 kernel before the cpuf 759 kernel before the cpufreq driver probes.
890 760
891 cpu_init_udelay=N 761 cpu_init_udelay=N
892 [X86,EARLY] Delay for !! 762 [X86] Delay for N microsec between assert and de-assert
893 of APIC INIT to start 763 of APIC INIT to start processors. This delay occurs
894 on every CPU online, s 764 on every CPU online, such as boot, and resume from suspend.
895 Default: 10000 765 Default: 10000
896 766
897 cpuhp.parallel= !! 767 cpcihp_generic= [HW,PCI] Generic port I/O CompactPCI driver
898 [SMP] Enable/disable p !! 768 Format:
899 Format: <bool> !! 769 <first_slot>,<last_slot>,<port>,<enum_bit>[,<debug>]
900 Default is enabled if <<
901 the parameter has no e <<
902 <<
903 crash_kexec_post_notifiers <<
904 Run kdump after runnin <<
905 kmsg. This only for th <<
906 succeeds in any situat <<
907 Note that this also in <<
908 because some panic not <<
909 kernel more unstable. <<
910 770
911 crashkernel=size[KMG][@offset[KMG]] 771 crashkernel=size[KMG][@offset[KMG]]
912 [KNL,EARLY] Using kexe !! 772 [KNL] Using kexec, Linux can switch to a 'crash kernel'
913 upon panic. This param 773 upon panic. This parameter reserves the physical
914 memory region [offset, 774 memory region [offset, offset + size] for that kernel
915 image. If '@offset' is 775 image. If '@offset' is omitted, then a suitable offset
916 is selected automatica 776 is selected automatically.
917 [KNL, X86-64, ARM64, R !! 777 [KNL, X86-64] Select a region under 4G first, and
918 under 4G first, and fa !! 778 fall back to reserve region above 4G when '@offset'
919 4G when '@offset' hasn !! 779 hasn't been specified.
920 See Documentation/admi 780 See Documentation/admin-guide/kdump/kdump.rst for further details.
921 781
922 crashkernel=range1:size1[,range2:size2 782 crashkernel=range1:size1[,range2:size2,...][@offset]
923 [KNL] Same as above, b 783 [KNL] Same as above, but depends on the memory
924 in the running system. 784 in the running system. The syntax of range is
925 start-[end] where star 785 start-[end] where start and end are both
926 a memory unit (amount[ 786 a memory unit (amount[KMG]). See also
927 Documentation/admin-gu 787 Documentation/admin-guide/kdump/kdump.rst for an example.
928 788
929 crashkernel=size[KMG],high 789 crashkernel=size[KMG],high
930 [KNL, X86-64, ARM64, R !! 790 [KNL, X86-64] range could be above 4G. Allow kernel
931 above 4G. !! 791 to allocate physical memory region from top, so could
932 Allow kernel to alloca !! 792 be above 4G if system have more than 4G ram installed.
933 so could be above 4G i !! 793 Otherwise memory region will be allocated below 4G, if
934 installed. Otherwise m !! 794 available.
935 below 4G, if available <<
936 It will be ignored if 795 It will be ignored if crashkernel=X is specified.
937 crashkernel=size[KMG],low 796 crashkernel=size[KMG],low
938 [KNL, X86-64, ARM64, R !! 797 [KNL, X86-64] range under 4G. When crashkernel=X,high
939 When crashkernel=X,hig !! 798 is passed, kernel could allocate physical memory region
940 physical memory region !! 799 above 4G, that cause second kernel crash on system
941 crash on system that r !! 800 that require some amount of low memory, e.g. swiotlb
942 e.g. swiotlb requires !! 801 requires at least 64M+32K low memory, also enough extra
943 enough extra low memor !! 802 low memory is needed to make sure DMA buffers for 32-bit
944 for 32-bit devices won !! 803 devices won't run out. Kernel would try to allocate at
945 default size of memory !! 804 at least 256M below 4G automatically.
946 size is platform depen !! 805 This one let user to specify own low range under 4G
947 --> x86: max(swiotlb <<
948 --> arm64: 128MiB <<
949 --> riscv: 128MiB <<
950 --> loongarch: 128Mi <<
951 This one lets the user <<
952 for second kernel inst 806 for second kernel instead.
953 0: to disable low allo 807 0: to disable low allocation.
954 It will be ignored whe 808 It will be ignored when crashkernel=X,high is not used
955 or memory reserved is 809 or memory reserved is below 4G.
956 810
957 cryptomgr.notests 811 cryptomgr.notests
958 [KNL] Disable crypto s 812 [KNL] Disable crypto self-tests
959 813
960 cs89x0_dma= [HW,NET] 814 cs89x0_dma= [HW,NET]
961 Format: <dma> 815 Format: <dma>
962 816
963 cs89x0_media= [HW,NET] 817 cs89x0_media= [HW,NET]
964 Format: { rj45 | aui | 818 Format: { rj45 | aui | bnc }
965 819
966 csdlock_debug= [KNL] Enable or disabl !! 820 csdlock_debug= [KNL] Enable debug add-ons of cross-CPU function call
967 function call handling !! 821 handling. When switched on, additional debug data is
968 additional debug data !! 822 printed to the console in case a hanging CPU is
969 in case a hanging CPU !! 823 detected, and that CPU is pinged again in order to try
970 CPU is pinged again in !! 824 to resolve the hang situation.
971 the hang situation. T !! 825 0: disable csdlock debugging (default)
972 option depends on the !! 826 1: enable basic csdlock debugging (minor impact)
973 Kconfig option. !! 827 ext: enable extended csdlock debugging (more impact,
>> 828 but more data)
974 829
975 dasd= [HW,NET] 830 dasd= [HW,NET]
976 See header of drivers/ 831 See header of drivers/s390/block/dasd_devmap.c.
977 832
978 db9.dev[2|3]= [HW,JOY] Multisystem j 833 db9.dev[2|3]= [HW,JOY] Multisystem joystick support via parallel port
979 (one device per port) 834 (one device per port)
980 Format: <port#>,<type> 835 Format: <port#>,<type>
981 See also Documentation 836 See also Documentation/input/devices/joystick-parport.rst
982 837
983 debug [KNL,EARLY] Enable ker !! 838 ddebug_query= [KNL,DYNAMIC_DEBUG] Enable debug messages at early boot
>> 839 time. See
>> 840 Documentation/admin-guide/dynamic-debug-howto.rst for
>> 841 details. Deprecated, see dyndbg.
>> 842
>> 843 debug [KNL] Enable kernel debugging (events log level).
984 844
985 debug_boot_weak_hash 845 debug_boot_weak_hash
986 [KNL,EARLY] Enable pri !! 846 [KNL] Enable printing [hashed] pointers early in the
987 boot sequence. If ena 847 boot sequence. If enabled, we use a weak hash instead
988 of siphash to hash poi 848 of siphash to hash pointers. Use this option if you are
989 seeing instances of '( 849 seeing instances of '(___ptrval___)') and need to see a
990 value (hashed pointer) 850 value (hashed pointer) instead. Cryptographically
991 insecure, please do no 851 insecure, please do not use on production kernels.
992 852
993 debug_locks_verbose= 853 debug_locks_verbose=
994 [KNL] verbose locking 854 [KNL] verbose locking self-tests
995 Format: <int> 855 Format: <int>
996 Print debugging info w 856 Print debugging info while doing the locking API
997 self-tests. 857 self-tests.
998 Bitmask for the variou 858 Bitmask for the various LOCKTYPE_ tests. Defaults to 0
999 (no extra messages), s 859 (no extra messages), setting it to -1 (all bits set)
1000 will print _a_lot_ mo 860 will print _a_lot_ more information - normally only
1001 useful to lockdep dev 861 useful to lockdep developers.
1002 862
1003 debug_objects [KNL,EARLY] Enable ob !! 863 debug_objects [KNL] Enable object debugging
>> 864
>> 865 no_debug_objects
>> 866 [KNL] Disable object debugging
1004 867
1005 debug_guardpage_minorder= 868 debug_guardpage_minorder=
1006 [KNL,EARLY] When CONF !! 869 [KNL] When CONFIG_DEBUG_PAGEALLOC is set, this
1007 parameter allows cont 870 parameter allows control of the order of pages that will
1008 be intentionally kept 871 be intentionally kept free (and hence protected) by the
1009 buddy allocator. Bigg 872 buddy allocator. Bigger value increase the probability
1010 of catching random me 873 of catching random memory corruption, but reduce the
1011 amount of memory for 874 amount of memory for normal system use. The maximum
1012 possible value is MAX !! 875 possible value is MAX_ORDER/2. Setting this parameter
1013 parameter to 1 or 2 s !! 876 to 1 or 2 should be enough to identify most random
1014 random memory corrupt !! 877 memory corruption problems caused by bugs in kernel or
1015 kernel or driver code !! 878 driver code when a CPU writes to (or reads from) a
1016 from) a random memory !! 879 random memory location. Note that there exists a class
1017 a class of memory cor !! 880 of memory corruptions problems caused by buggy H/W or
1018 H/W or F/W or by driv !! 881 F/W or by drivers badly programing DMA (basically when
1019 (basically when memor !! 882 memory is written at bus level and the CPU MMU is
1020 CPU MMU is bypassed) !! 883 bypassed) which are not detectable by
1021 CONFIG_DEBUG_PAGEALLO !! 884 CONFIG_DEBUG_PAGEALLOC, hence this option will not help
1022 help tracking down th !! 885 tracking down these problems.
1023 886
1024 debug_pagealloc= 887 debug_pagealloc=
1025 [KNL,EARLY] When CONF !! 888 [KNL] When CONFIG_DEBUG_PAGEALLOC is set, this parameter
1026 enables the feature a 889 enables the feature at boot time. By default, it is
1027 disabled and the syst 890 disabled and the system will work mostly the same as a
1028 kernel built without 891 kernel built without CONFIG_DEBUG_PAGEALLOC.
1029 Note: to get most of 892 Note: to get most of debug_pagealloc error reports, it's
1030 useful to also enable 893 useful to also enable the page_owner functionality.
1031 on: enable the featur 894 on: enable the feature
1032 895
1033 debugfs= [KNL,EARLY] This para !! 896 debugfs= [KNL] This parameter enables what is exposed to userspace
1034 userspace and debugfs !! 897 and debugfs internal clients.
1035 Format: { on, no-moun 898 Format: { on, no-mount, off }
1036 on: All functions 899 on: All functions are enabled.
1037 no-mount: 900 no-mount:
1038 Filesystem is 901 Filesystem is not registered but kernel clients can
1039 access APIs a 902 access APIs and a crashkernel can be used to read
1040 its content. 903 its content. There is nothing to mount.
1041 off: Filesystem is 904 off: Filesystem is not registered and clients
1042 get a -EPERM 905 get a -EPERM as result when trying to register files
1043 or directorie 906 or directories within debugfs.
1044 This is equiv 907 This is equivalent of the runtime functionality if
1045 debugfs was n 908 debugfs was not enabled in the kernel at all.
1046 Default value is set 909 Default value is set in build-time with a kernel configuration.
1047 910
1048 debugpat [X86] Enable PAT debu 911 debugpat [X86] Enable PAT debugging
1049 912
1050 default_hugepagesz= 913 default_hugepagesz=
1051 [HW] The size of the 914 [HW] The size of the default HugeTLB page. This is
1052 the size represented 915 the size represented by the legacy /proc/ hugepages
1053 APIs. In addition, t 916 APIs. In addition, this is the default hugetlb size
1054 used for shmget(), mm 917 used for shmget(), mmap() and mounting hugetlbfs
1055 filesystems. If not 918 filesystems. If not specified, defaults to the
1056 architecture's defaul 919 architecture's default huge page size. Huge page
1057 sizes are architectur 920 sizes are architecture dependent. See also
1058 Documentation/admin-g 921 Documentation/admin-guide/mm/hugetlbpage.rst.
1059 Format: size[KMG] 922 Format: size[KMG]
1060 923
1061 deferred_probe_timeout= 924 deferred_probe_timeout=
1062 [KNL] Debugging optio 925 [KNL] Debugging option to set a timeout in seconds for
1063 deferred probe to giv 926 deferred probe to give up waiting on dependencies to
1064 probe. Only specific 927 probe. Only specific dependencies (subsystems or
1065 drivers) that have op !! 928 drivers) that have opted in will be ignored. A timeout of 0
1066 of 0 will timeout at !! 929 will timeout at the end of initcalls. This option will also
1067 out hasn't expired, i <<
1068 successful driver reg <<
1069 dump out devices stil 930 dump out devices still on the deferred probe list after
1070 retrying. 931 retrying.
1071 932
1072 delayacct [KNL] Enable per-task <<
1073 <<
1074 dell_smm_hwmon.ignore_dmi= <<
1075 [HW] Continue probing <<
1076 indicates that the dr <<
1077 hardware. <<
1078 <<
1079 dell_smm_hwmon.force= <<
1080 [HW] Activate driver <<
1081 not match list of sup <<
1082 blacklisted features. <<
1083 <<
1084 dell_smm_hwmon.power_status= <<
1085 [HW] Report power sta <<
1086 (disabled by default) <<
1087 <<
1088 dell_smm_hwmon.restricted= <<
1089 [HW] Allow controllin <<
1090 capability is set. <<
1091 <<
1092 dell_smm_hwmon.fan_mult= <<
1093 [HW] Factor to multip <<
1094 <<
1095 dell_smm_hwmon.fan_max= <<
1096 [HW] Maximum configur <<
1097 <<
1098 dfltcc= [HW,S390] 933 dfltcc= [HW,S390]
1099 Format: { on | off | 934 Format: { on | off | def_only | inf_only | always }
1100 on: s390 zlib h 935 on: s390 zlib hardware support for compression on
1101 level 1 and 936 level 1 and decompression (default)
1102 off: No s390 zli 937 off: No s390 zlib hardware support
1103 def_only: s390 zlib h 938 def_only: s390 zlib hardware support for deflate
1104 only (compr 939 only (compression on level 1)
1105 inf_only: s390 zlib h 940 inf_only: s390 zlib hardware support for inflate
1106 only (decom 941 only (decompression)
1107 always: Same as 'on 942 always: Same as 'on' but ignores the selected compression
1108 level alway 943 level always using hardware support (used for debugging)
1109 944
1110 dhash_entries= [KNL] 945 dhash_entries= [KNL]
1111 Set number of hash bu 946 Set number of hash buckets for dentry cache.
1112 947
1113 disable_1tb_segments [PPC,EARLY] !! 948 disable_1tb_segments [PPC]
1114 Disables the use of 1 949 Disables the use of 1TB hash page table segments. This
1115 causes the kernel to 950 causes the kernel to fall back to 256MB segments which
1116 can be useful when de 951 can be useful when debugging issues that require an SLB
1117 miss to occur. 952 miss to occur.
1118 953
>> 954 stress_slb [PPC]
>> 955 Limits the number of kernel SLB entries, and flushes
>> 956 them frequently to increase the rate of SLB faults
>> 957 on kernel addresses.
>> 958
1119 disable= [IPV6] 959 disable= [IPV6]
1120 See Documentation/net 960 See Documentation/networking/ipv6.rst.
1121 961
1122 disable_radix [PPC,EARLY] !! 962 hardened_usercopy=
>> 963 [KNL] Under CONFIG_HARDENED_USERCOPY, whether
>> 964 hardening is enabled for this boot. Hardened
>> 965 usercopy checking is used to protect the kernel
>> 966 from reading or writing beyond known memory
>> 967 allocation boundaries as a proactive defense
>> 968 against bounds-checking flaws in the kernel's
>> 969 copy_to_user()/copy_from_user() interface.
>> 970 on Perform hardened usercopy checks (default).
>> 971 off Disable hardened usercopy checks.
>> 972
>> 973 disable_radix [PPC]
1123 Disable RADIX MMU mod 974 Disable RADIX MMU mode on POWER9
1124 975
>> 976 radix_hcall_invalidate=on [PPC/PSERIES]
>> 977 Disable RADIX GTSE feature and use hcall for TLB
>> 978 invalidate.
>> 979
1125 disable_tlbie [PPC] 980 disable_tlbie [PPC]
1126 Disable TLBIE instruc 981 Disable TLBIE instruction. Currently does not work
1127 with KVM, with HASH M 982 with KVM, with HASH MMU, or with coherent accelerators.
1128 983
1129 disable_ddw [PPC/PSERIES,EARLY] !! 984 disable_cpu_apicid= [X86,APIC,SMP]
>> 985 Format: <int>
>> 986 The number of initial APIC ID for the
>> 987 corresponding CPU to be disabled at boot,
>> 988 mostly used for the kdump 2nd kernel to
>> 989 disable BSP to wake up multiple CPUs without
>> 990 causing system reset or hang due to sending
>> 991 INIT from AP to BSP.
>> 992
>> 993 disable_ddw [PPC/PSERIES]
1130 Disable Dynamic DMA W 994 Disable Dynamic DMA Window support. Use this
1131 to workaround buggy f 995 to workaround buggy firmware.
1132 996
1133 disable_ipv6= [IPV6] 997 disable_ipv6= [IPV6]
1134 See Documentation/net 998 See Documentation/networking/ipv6.rst.
1135 999
1136 disable_mtrr_cleanup [X86,EARLY] !! 1000 disable_mtrr_cleanup [X86]
1137 The kernel tries to a 1001 The kernel tries to adjust MTRR layout from continuous
1138 to discrete, to make 1002 to discrete, to make X server driver able to add WB
1139 entry later. This par 1003 entry later. This parameter disables that.
1140 1004
1141 disable_mtrr_trim [X86, Intel and AMD !! 1005 disable_mtrr_trim [X86, Intel and AMD only]
1142 By default the kernel 1006 By default the kernel will trim any uncacheable
1143 memory out of your av 1007 memory out of your available memory pool based on
1144 MTRR settings. This 1008 MTRR settings. This parameter disables that behavior,
1145 possibly causing your 1009 possibly causing your machine to run very slowly.
1146 1010
1147 disable_timer_pin_1 [X86,EARLY] !! 1011 disable_timer_pin_1 [X86]
1148 Disable PIN 1 of APIC 1012 Disable PIN 1 of APIC timer
1149 Can be useful to work 1013 Can be useful to work around chipset bugs.
1150 1014
1151 dis_ucode_ldr [X86] Disable the mic 1015 dis_ucode_ldr [X86] Disable the microcode loader.
1152 1016
1153 dma_debug=off If the kernel is comp 1017 dma_debug=off If the kernel is compiled with DMA_API_DEBUG support,
1154 this option disables 1018 this option disables the debugging code at boot.
1155 1019
1156 dma_debug_entries=<number> 1020 dma_debug_entries=<number>
1157 This option allows to 1021 This option allows to tune the number of preallocated
1158 entries for DMA-API d 1022 entries for DMA-API debugging code. One entry is
1159 required per DMA-API 1023 required per DMA-API allocation. Use this if the
1160 DMA-API debugging cod 1024 DMA-API debugging code disables itself because the
1161 architectural default 1025 architectural default is too low.
1162 1026
1163 dma_debug_driver=<driver_name> 1027 dma_debug_driver=<driver_name>
1164 With this option the 1028 With this option the DMA-API debugging driver
1165 filter feature can be 1029 filter feature can be enabled at boot time. Just
1166 pass the driver to fi 1030 pass the driver to filter for as the parameter.
1167 The filter can be dis 1031 The filter can be disabled or changed to another
1168 driver later using sy 1032 driver later using sysfs.
1169 1033
1170 reg_file_data_sampling= 1034 reg_file_data_sampling=
1171 [X86] Controls mitiga 1035 [X86] Controls mitigation for Register File Data
1172 Sampling (RFDS) vulne 1036 Sampling (RFDS) vulnerability. RFDS is a CPU
1173 vulnerability which m 1037 vulnerability which may allow userspace to infer
1174 kernel data values pr 1038 kernel data values previously stored in floating point
1175 registers, vector reg 1039 registers, vector registers, or integer registers.
1176 RFDS only affects Int 1040 RFDS only affects Intel Atom processors.
1177 1041
1178 on: Turns ON the 1042 on: Turns ON the mitigation.
1179 off: Turns OFF the 1043 off: Turns OFF the mitigation.
1180 1044
1181 This parameter overri 1045 This parameter overrides the compile time default set
1182 by CONFIG_MITIGATION_ 1046 by CONFIG_MITIGATION_RFDS. Mitigation cannot be
1183 disabled when other V 1047 disabled when other VERW based mitigations (like MDS)
1184 are enabled. In order 1048 are enabled. In order to disable RFDS mitigation all
1185 VERW based mitigation 1049 VERW based mitigations need to be disabled.
1186 1050
1187 For details see: 1051 For details see:
1188 Documentation/admin-g 1052 Documentation/admin-guide/hw-vuln/reg-file-data-sampling.rst
1189 1053
1190 driver_async_probe= [KNL] 1054 driver_async_probe= [KNL]
1191 List of driver names !! 1055 List of driver names to be probed asynchronously.
1192 matches with all driv <<
1193 rest of the listed dr <<
1194 match the *. <<
1195 Format: <driver_name1 1056 Format: <driver_name1>,<driver_name2>...
1196 1057
1197 drm.edid_firmware=[<connector>:]<file 1058 drm.edid_firmware=[<connector>:]<file>[,[<connector>:]<file>]
1198 Broken monitors, grap 1059 Broken monitors, graphic adapters, KVMs and EDIDless
1199 panels may send no or 1060 panels may send no or incorrect EDID data sets.
1200 This parameter allows 1061 This parameter allows to specify an EDID data sets
1201 in the /lib/firmware 1062 in the /lib/firmware directory that are used instead.
1202 An EDID data set will !! 1063 Generic built-in EDID data sets are used, if one of
1203 connector, if its nam !! 1064 edid/1024x768.bin, edid/1280x1024.bin,
1204 the EDID name. Each c !! 1065 edid/1680x1050.bin, or edid/1920x1080.bin is given
1205 data set by separatin !! 1066 and no file with the same name exists. Details and
>> 1067 instructions how to build your own EDID data are
>> 1068 available in Documentation/admin-guide/edid.rst. An EDID
>> 1069 data set will only be used for a particular connector,
>> 1070 if its name and a colon are prepended to the EDID
>> 1071 name. Each connector may use a unique EDID data
>> 1072 set by separating the files with a comma. An EDID
1206 data set with no conn 1073 data set with no connector name will be used for
1207 any connectors not ex 1074 any connectors not explicitly specified.
1208 1075
1209 dscc4.setup= [NET] 1076 dscc4.setup= [NET]
1210 1077
1211 dt_cpu_ftrs= [PPC,EARLY] !! 1078 dt_cpu_ftrs= [PPC]
1212 Format: {"off" | "kno 1079 Format: {"off" | "known"}
1213 Control how the dt_cp 1080 Control how the dt_cpu_ftrs device-tree binding is
1214 used for CPU feature 1081 used for CPU feature discovery and setup (if it
1215 exists). 1082 exists).
1216 off: Do not use it, f 1083 off: Do not use it, fall back to legacy cpu table.
1217 known: Do not pass th 1084 known: Do not pass through unknown features to guests
1218 or userspace, only th 1085 or userspace, only those that the kernel is aware of.
1219 1086
1220 dump_apple_properties [X86] 1087 dump_apple_properties [X86]
1221 Dump name and content 1088 Dump name and content of EFI device properties on
1222 x86 Macs. Useful for 1089 x86 Macs. Useful for driver authors to determine
1223 what data is availabl 1090 what data is available or for reverse-engineering.
1224 1091
1225 dyndbg[="val"] [KNL,DYNAMIC_ 1092 dyndbg[="val"] [KNL,DYNAMIC_DEBUG]
1226 <module>.dyndbg[="val"] 1093 <module>.dyndbg[="val"]
1227 Enable debug messages 1094 Enable debug messages at boot time. See
1228 Documentation/admin-g 1095 Documentation/admin-guide/dynamic-debug-howto.rst
1229 for details. 1096 for details.
1230 1097
1231 early_ioremap_debug [KNL,EARLY] !! 1098 nopku [X86] Disable Memory Protection Keys CPU feature found
>> 1099 in some Intel CPUs.
>> 1100
>> 1101 <module>.async_probe[=<bool>] [KNL]
>> 1102 If no <bool> value is specified or if the value
>> 1103 specified is not a valid <bool>, enable asynchronous
>> 1104 probe on this module. Otherwise, enable/disable
>> 1105 asynchronous probe on this module as indicated by the
>> 1106 <bool> value. See also: module.async_probe
>> 1107
>> 1108 early_ioremap_debug [KNL]
1232 Enable debug messages 1109 Enable debug messages in early_ioremap support. This
1233 is useful for trackin 1110 is useful for tracking down temporary early mappings
1234 which are not unmappe 1111 which are not unmapped.
1235 1112
1236 earlycon= [KNL,EARLY] Output ea !! 1113 earlycon= [KNL] Output early console device and options.
1237 1114
1238 When used with no opt 1115 When used with no options, the early console is
1239 determined by stdout- 1116 determined by stdout-path property in device tree's
1240 chosen node or the AC 1117 chosen node or the ACPI SPCR table if supported by
1241 the platform. 1118 the platform.
1242 1119
1243 cdns,<addr>[,options] 1120 cdns,<addr>[,options]
1244 Start an early, polle 1121 Start an early, polled-mode console on a Cadence
1245 (xuartps) serial port 1122 (xuartps) serial port at the specified address. Only
1246 supported option is b 1123 supported option is baud rate. If baud rate is not
1247 specified, the serial 1124 specified, the serial port must already be setup and
1248 configured. 1125 configured.
1249 1126
1250 uart[8250],io,<addr>[,options !! 1127 uart[8250],io,<addr>[,options]
1251 uart[8250],mmio,<addr>[,optio !! 1128 uart[8250],mmio,<addr>[,options]
1252 uart[8250],mmio32,<addr>[,opt !! 1129 uart[8250],mmio32,<addr>[,options]
1253 uart[8250],mmio32be,<addr>[,o !! 1130 uart[8250],mmio32be,<addr>[,options]
1254 uart[8250],0x<addr>[,options] 1131 uart[8250],0x<addr>[,options]
1255 Start an early, polle 1132 Start an early, polled-mode console on the 8250/16550
1256 UART at the specified 1133 UART at the specified I/O port or MMIO address.
1257 MMIO inter-register a 1134 MMIO inter-register address stride is either 8-bit
1258 (mmio) or 32-bit (mmi 1135 (mmio) or 32-bit (mmio32 or mmio32be).
1259 If none of [io|mmio|m 1136 If none of [io|mmio|mmio32|mmio32be], <addr> is assumed
1260 to be equivalent to ' 1137 to be equivalent to 'mmio'. 'options' are specified
1261 in the same format de 1138 in the same format described for "console=ttyS<n>"; if
1262 unspecified, the h/w !! 1139 unspecified, the h/w is not initialized.
1263 the uart clock freque <<
1264 to 'BASE_BAUD' * 16. <<
1265 1140
1266 pl011,<addr> 1141 pl011,<addr>
1267 pl011,mmio32,<addr> 1142 pl011,mmio32,<addr>
1268 Start an early, polle 1143 Start an early, polled-mode console on a pl011 serial
1269 port at the specified 1144 port at the specified address. The pl011 serial port
1270 must already be setup 1145 must already be setup and configured. Options are not
1271 yet supported. If 'm 1146 yet supported. If 'mmio32' is specified, then only
1272 the driver will use o 1147 the driver will use only 32-bit accessors to read/write
1273 the device registers. 1148 the device registers.
1274 1149
1275 liteuart,<addr> 1150 liteuart,<addr>
1276 Start an early consol 1151 Start an early console on a litex serial port at the
1277 specified address. Th 1152 specified address. The serial port must already be
1278 setup and configured. 1153 setup and configured. Options are not yet supported.
1279 1154
1280 meson,<addr> 1155 meson,<addr>
1281 Start an early, polle 1156 Start an early, polled-mode console on a meson serial
1282 port at the specified 1157 port at the specified address. The serial port must
1283 already be setup and 1158 already be setup and configured. Options are not yet
1284 supported. 1159 supported.
1285 1160
1286 msm_serial,<addr> 1161 msm_serial,<addr>
1287 Start an early, polle 1162 Start an early, polled-mode console on an msm serial
1288 port at the specified 1163 port at the specified address. The serial port
1289 must already be setup 1164 must already be setup and configured. Options are not
1290 yet supported. 1165 yet supported.
1291 1166
1292 msm_serial_dm,<addr> 1167 msm_serial_dm,<addr>
1293 Start an early, polle 1168 Start an early, polled-mode console on an msm serial
1294 dm port at the specif 1169 dm port at the specified address. The serial port
1295 must already be setup 1170 must already be setup and configured. Options are not
1296 yet supported. 1171 yet supported.
1297 1172
1298 owl,<addr> 1173 owl,<addr>
1299 Start an early, polle 1174 Start an early, polled-mode console on a serial port
1300 of an Actions Semi So 1175 of an Actions Semi SoC, such as S500 or S900, at the
1301 specified address. Th 1176 specified address. The serial port must already be
1302 setup and configured. 1177 setup and configured. Options are not yet supported.
1303 1178
1304 rda,<addr> 1179 rda,<addr>
1305 Start an early, polle 1180 Start an early, polled-mode console on a serial port
1306 of an RDA Micro SoC, 1181 of an RDA Micro SoC, such as RDA8810PL, at the
1307 specified address. Th 1182 specified address. The serial port must already be
1308 setup and configured. 1183 setup and configured. Options are not yet supported.
1309 1184
1310 sbi 1185 sbi
1311 Use RISC-V SBI (Super 1186 Use RISC-V SBI (Supervisor Binary Interface) for early
1312 console. 1187 console.
1313 1188
1314 smh Use ARM semihosting c 1189 smh Use ARM semihosting calls for early console.
1315 1190
1316 s3c2410,<addr> 1191 s3c2410,<addr>
1317 s3c2412,<addr> 1192 s3c2412,<addr>
1318 s3c2440,<addr> 1193 s3c2440,<addr>
1319 s3c6400,<addr> 1194 s3c6400,<addr>
1320 s5pv210,<addr> 1195 s5pv210,<addr>
1321 exynos4210,<addr> 1196 exynos4210,<addr>
1322 Use early console pro 1197 Use early console provided by serial driver available
1323 on Samsung SoCs, requ 1198 on Samsung SoCs, requires selecting proper type and
1324 a correct base addres 1199 a correct base address of the selected UART port. The
1325 serial port must alre 1200 serial port must already be setup and configured.
1326 Options are not yet s 1201 Options are not yet supported.
1327 1202
1328 lantiq,<addr> 1203 lantiq,<addr>
1329 Start an early, polle 1204 Start an early, polled-mode console on a lantiq serial
1330 (lqasc) port at the s 1205 (lqasc) port at the specified address. The serial port
1331 must already be setup 1206 must already be setup and configured. Options are not
1332 yet supported. 1207 yet supported.
1333 1208
1334 lpuart,<addr> 1209 lpuart,<addr>
1335 lpuart32,<addr> 1210 lpuart32,<addr>
1336 Use early console pro 1211 Use early console provided by Freescale LP UART driver
1337 found on Freescale Vy 1212 found on Freescale Vybrid and QorIQ LS1021A processors.
1338 A valid base address 1213 A valid base address must be provided, and the serial
1339 port must already be 1214 port must already be setup and configured.
1340 1215
1341 ec_imx21,<addr> 1216 ec_imx21,<addr>
1342 ec_imx6q,<addr> 1217 ec_imx6q,<addr>
1343 Start an early, polle 1218 Start an early, polled-mode, output-only console on the
1344 Freescale i.MX UART a 1219 Freescale i.MX UART at the specified address. The UART
1345 must already be setup 1220 must already be setup and configured.
1346 1221
1347 ar3700_uart,<addr> 1222 ar3700_uart,<addr>
1348 Start an early, polle 1223 Start an early, polled-mode console on the
1349 Armada 3700 serial po 1224 Armada 3700 serial port at the specified
1350 address. The serial p 1225 address. The serial port must already be setup
1351 and configured. Optio 1226 and configured. Options are not yet supported.
1352 1227
1353 qcom_geni,<addr> 1228 qcom_geni,<addr>
1354 Start an early, polle 1229 Start an early, polled-mode console on a Qualcomm
1355 Generic Interface (GE 1230 Generic Interface (GENI) based serial port at the
1356 specified address. Th 1231 specified address. The serial port must already be
1357 setup and configured. 1232 setup and configured. Options are not yet supported.
1358 1233
1359 efifb,[options] 1234 efifb,[options]
1360 Start an early, unacc 1235 Start an early, unaccelerated console on the EFI
1361 memory mapped framebu 1236 memory mapped framebuffer (if available). On cache
1362 coherent non-x86 syst 1237 coherent non-x86 systems that use system memory for
1363 the framebuffer, pass 1238 the framebuffer, pass the 'ram' option so that it is
1364 mapped with the corre 1239 mapped with the correct attributes.
1365 1240
1366 linflex,<addr> 1241 linflex,<addr>
1367 Use early console pro 1242 Use early console provided by Freescale LINFlexD UART
1368 serial driver for NXP 1243 serial driver for NXP S32V234 SoCs. A valid base
1369 address must be provi 1244 address must be provided, and the serial port must
1370 already be setup and 1245 already be setup and configured.
1371 1246
1372 earlyprintk= [X86,SH,ARM,M68k,S390 !! 1247 earlyprintk= [X86,SH,ARM,M68k,S390]
1373 earlyprintk=vga 1248 earlyprintk=vga
1374 earlyprintk=sclp 1249 earlyprintk=sclp
1375 earlyprintk=xen 1250 earlyprintk=xen
1376 earlyprintk=serial[,t 1251 earlyprintk=serial[,ttySn[,baudrate]]
1377 earlyprintk=serial[,0 1252 earlyprintk=serial[,0x...[,baudrate]]
1378 earlyprintk=ttySn[,ba 1253 earlyprintk=ttySn[,baudrate]
1379 earlyprintk=dbgp[debu 1254 earlyprintk=dbgp[debugController#]
1380 earlyprintk=pciserial 1255 earlyprintk=pciserial[,force],bus:device.function[,baudrate]
1381 earlyprintk=xdbc[xhci 1256 earlyprintk=xdbc[xhciController#]
1382 earlyprintk=bios <<
1383 1257
1384 earlyprintk is useful 1258 earlyprintk is useful when the kernel crashes before
1385 the normal console is 1259 the normal console is initialized. It is not enabled by
1386 default because it ha 1260 default because it has some cosmetic problems.
1387 1261
1388 Append ",keep" to not 1262 Append ",keep" to not disable it when the real console
1389 takes over. 1263 takes over.
1390 1264
1391 Only one of vga, seri !! 1265 Only one of vga, efi, serial, or usb debug port can
1392 be used at a time. 1266 be used at a time.
1393 1267
1394 Currently only ttyS0 1268 Currently only ttyS0 and ttyS1 may be specified by
1395 name. Other I/O port 1269 name. Other I/O ports may be explicitly specified
1396 on some architectures 1270 on some architectures (x86 and arm at least) by
1397 replacing ttySn with 1271 replacing ttySn with an I/O port address, like this:
1398 earlyprintk=s 1272 earlyprintk=serial,0x1008,115200
1399 You can find the port 1273 You can find the port for a given device in
1400 /proc/tty/driver/seri 1274 /proc/tty/driver/serial:
1401 2: uart:ST166 1275 2: uart:ST16650V2 port:00001008 irq:18 ...
1402 1276
1403 Interaction with the 1277 Interaction with the standard serial driver is not
1404 very good. 1278 very good.
1405 1279
1406 The VGA output is eve !! 1280 The VGA and EFI output is eventually overwritten by
1407 the real console. 1281 the real console.
1408 1282
1409 The xen option can on 1283 The xen option can only be used in Xen domains.
1410 1284
1411 The sclp output can o 1285 The sclp output can only be used on s390.
1412 1286
1413 The bios output can o <<
1414 <<
1415 The optional "force" 1287 The optional "force" to "pciserial" enables use of a
1416 PCI device even when 1288 PCI device even when its classcode is not of the
1417 UART class. 1289 UART class.
1418 1290
1419 edac_report= [HW,EDAC] Control how 1291 edac_report= [HW,EDAC] Control how to report EDAC event
1420 Format: {"on" | "off" 1292 Format: {"on" | "off" | "force"}
1421 on: enable EDAC to re 1293 on: enable EDAC to report H/W event. May be overridden
1422 by other higher prior 1294 by other higher priority error reporting module.
1423 off: disable H/W even 1295 off: disable H/W event reporting through EDAC.
1424 force: enforce the us 1296 force: enforce the use of EDAC to report H/W event.
1425 default: on. 1297 default: on.
1426 1298
>> 1299 ekgdboc= [X86,KGDB] Allow early kernel console debugging
>> 1300 ekgdboc=kbd
>> 1301
>> 1302 This is designed to be used in conjunction with
>> 1303 the boot argument: earlyprintk=vga
>> 1304
>> 1305 This parameter works in place of the kgdboc parameter
>> 1306 but can only be used if the backing tty is available
>> 1307 very early in the boot process. For early debugging
>> 1308 via a serial port see kgdboc_earlycon instead.
>> 1309
1427 edd= [EDD] 1310 edd= [EDD]
1428 Format: {"off" | "on" 1311 Format: {"off" | "on" | "skip[mbr]"}
1429 1312
1430 efi= [EFI,EARLY] !! 1313 efi= [EFI]
1431 Format: { "debug", "d 1314 Format: { "debug", "disable_early_pci_dma",
1432 "nochunk", 1315 "nochunk", "noruntime", "nosoftreserve",
1433 "novamap", 1316 "novamap", "no_disable_early_pci_dma" }
1434 debug: enable misc de 1317 debug: enable misc debug output.
1435 disable_early_pci_dma 1318 disable_early_pci_dma: disable the busmaster bit on all
1436 PCI bridges while in 1319 PCI bridges while in the EFI boot stub.
1437 nochunk: disable read 1320 nochunk: disable reading files in "chunks" in the EFI
1438 boot stub, as chunkin 1321 boot stub, as chunking can cause problems with some
1439 firmware implementati 1322 firmware implementations.
1440 noruntime : disable E 1323 noruntime : disable EFI runtime services support
1441 nosoftreserve: The EF 1324 nosoftreserve: The EFI_MEMORY_SP (Specific Purpose)
1442 attribute may cause t 1325 attribute may cause the kernel to reserve the
1443 memory range for a me 1326 memory range for a memory mapping driver to
1444 claim. Specify efi=no 1327 claim. Specify efi=nosoftreserve to disable this
1445 reservation and treat 1328 reservation and treat the memory by its base type
1446 (i.e. EFI_CONVENTIONA 1329 (i.e. EFI_CONVENTIONAL_MEMORY / "System RAM").
1447 novamap: do not call 1330 novamap: do not call SetVirtualAddressMap().
1448 no_disable_early_pci_ 1331 no_disable_early_pci_dma: Leave the busmaster bit set
1449 on all PCI bridges wh 1332 on all PCI bridges while in the EFI boot stub
1450 1333
1451 efi_no_storage_paranoia [EFI,X86,EARL !! 1334 efi_no_storage_paranoia [EFI; X86]
1452 Using this parameter 1335 Using this parameter you can use more than 50% of
1453 your efi variable sto 1336 your efi variable storage. Use this parameter only if
1454 you are really sure t 1337 you are really sure that your UEFI does sane gc and
1455 fulfills the spec oth 1338 fulfills the spec otherwise your board may brick.
1456 1339
>> 1340 efi_fake_mem= nn[KMG]@ss[KMG]:aa[,nn[KMG]@ss[KMG]:aa,..] [EFI; X86]
>> 1341 Add arbitrary attribute to specific memory range by
>> 1342 updating original EFI memory map.
>> 1343 Region of memory which aa attribute is added to is
>> 1344 from ss to ss+nn.
>> 1345
>> 1346 If efi_fake_mem=2G@4G:0x10000,2G@0x10a0000000:0x10000
>> 1347 is specified, EFI_MEMORY_MORE_RELIABLE(0x10000)
>> 1348 attribute is added to range 0x100000000-0x180000000 and
>> 1349 0x10a0000000-0x1120000000.
>> 1350
>> 1351 If efi_fake_mem=8G@9G:0x40000 is specified, the
>> 1352 EFI_MEMORY_SP(0x40000) attribute is added to
>> 1353 range 0x240000000-0x43fffffff.
>> 1354
>> 1355 Using this parameter you can do debugging of EFI memmap
>> 1356 related features. For example, you can do debugging of
>> 1357 Address Range Mirroring feature even if your box
>> 1358 doesn't support it, or mark specific memory as
>> 1359 "soft reserved".
>> 1360
1457 efivar_ssdt= [EFI; X86] Name of an 1361 efivar_ssdt= [EFI; X86] Name of an EFI variable that contains an SSDT
1458 that is to be dynamic 1362 that is to be dynamically loaded by Linux. If there are
1459 multiple variables wi 1363 multiple variables with the same name but with different
1460 vendor GUIDs, all of 1364 vendor GUIDs, all of them will be loaded. See
1461 Documentation/admin-g 1365 Documentation/admin-guide/acpi/ssdt-overlays.rst for details.
1462 1366
1463 1367
1464 eisa_irq_edge= [PARISC,HW] 1368 eisa_irq_edge= [PARISC,HW]
1465 See header of drivers 1369 See header of drivers/parisc/eisa.c.
1466 1370
1467 ekgdboc= [X86,KGDB,EARLY] Allo <<
1468 Format: ekgdboc=kbd <<
1469 <<
1470 This is designed to b <<
1471 the boot argument: ea <<
1472 <<
1473 This parameter works <<
1474 but can only be used <<
1475 very early in the boo <<
1476 via a serial port see <<
1477 <<
1478 elanfreq= [X86-32] 1371 elanfreq= [X86-32]
1479 See comment before fu 1372 See comment before function elanfreq_setup() in
1480 arch/x86/kernel/cpu/c 1373 arch/x86/kernel/cpu/cpufreq/elanfreq.c.
1481 1374
1482 elfcorehdr=[size[KMG]@]offset[KMG] [P !! 1375 elfcorehdr=[size[KMG]@]offset[KMG] [IA64,PPC,SH,X86,S390]
1483 Specifies physical ad 1376 Specifies physical address of start of kernel core
1484 image elf header and 1377 image elf header and optionally the size. Generally
1485 kexec loader will pas 1378 kexec loader will pass this option to capture kernel.
1486 See Documentation/adm 1379 See Documentation/admin-guide/kdump/kdump.rst for details.
1487 1380
1488 enable_mtrr_cleanup [X86,EARLY] !! 1381 enable_mtrr_cleanup [X86]
1489 The kernel tries to a 1382 The kernel tries to adjust MTRR layout from continuous
1490 to discrete, to make 1383 to discrete, to make X server driver able to add WB
1491 entry later. This par 1384 entry later. This parameter enables that.
1492 1385
1493 enable_timer_pin_1 [X86] 1386 enable_timer_pin_1 [X86]
1494 Enable PIN 1 of APIC 1387 Enable PIN 1 of APIC timer
1495 Can be useful to work 1388 Can be useful to work around chipset bugs
1496 (in particular on som 1389 (in particular on some ATI chipsets).
1497 The kernel tries to s 1390 The kernel tries to set a reasonable default.
1498 1391
1499 enforcing= [SELINUX] Set initial !! 1392 enforcing [SELINUX] Set initial enforcing status.
1500 Format: {"0" | "1"} 1393 Format: {"0" | "1"}
1501 See security/selinux/ 1394 See security/selinux/Kconfig help text.
1502 0 -- permissive (log 1395 0 -- permissive (log only, no denials).
1503 1 -- enforcing (deny 1396 1 -- enforcing (deny and log).
1504 Default value is 0. 1397 Default value is 0.
1505 Value can be changed 1398 Value can be changed at runtime via
1506 /sys/fs/selinux/enfor 1399 /sys/fs/selinux/enforce.
1507 1400
1508 erst_disable [ACPI] 1401 erst_disable [ACPI]
1509 Disable Error Record 1402 Disable Error Record Serialization Table (ERST)
1510 support. 1403 support.
1511 1404
1512 ether= [HW,NET] Ethernet car 1405 ether= [HW,NET] Ethernet cards parameters
1513 This option is obsole 1406 This option is obsoleted by the "netdev=" option, which
1514 has equivalent usage. 1407 has equivalent usage. See its documentation for details.
1515 1408
1516 evm= [EVM] 1409 evm= [EVM]
1517 Format: { "fix" } 1410 Format: { "fix" }
1518 Permit 'security.evm' 1411 Permit 'security.evm' to be updated regardless of
1519 current integrity sta 1412 current integrity status.
1520 1413
1521 early_page_ext [KNL,EARLY] Enforces p <<
1522 stages so cover more <<
1523 Please note that as s <<
1524 might be disabled to <<
1525 memory initialization <<
1526 might take longer, es <<
1527 memory. Available wit <<
1528 <<
1529 failslab= 1414 failslab=
1530 fail_usercopy= 1415 fail_usercopy=
1531 fail_page_alloc= 1416 fail_page_alloc=
1532 fail_make_request=[KNL] 1417 fail_make_request=[KNL]
1533 General fault injecti 1418 General fault injection mechanism.
1534 Format: <interval>,<p 1419 Format: <interval>,<probability>,<space>,<times>
1535 See also Documentatio 1420 See also Documentation/fault-injection/.
1536 1421
1537 fb_tunnels= [NET] 1422 fb_tunnels= [NET]
1538 Format: { initns | no 1423 Format: { initns | none }
1539 See Documentation/adm 1424 See Documentation/admin-guide/sysctl/net.rst for
1540 fb_tunnels_only_for_i 1425 fb_tunnels_only_for_init_ns
1541 1426
1542 floppy= [HW] 1427 floppy= [HW]
1543 See Documentation/adm 1428 See Documentation/admin-guide/blockdev/floppy.rst.
1544 1429
>> 1430 force_pal_cache_flush
>> 1431 [IA-64] Avoid check_sal_cache_flush which may hang on
>> 1432 buggy SAL_CACHE_FLUSH implementations. Using this
>> 1433 parameter will force ia64_sal_cache_flush to call
>> 1434 ia64_pal_cache_flush instead of SAL_CACHE_FLUSH.
>> 1435
1545 forcepae [X86-32] 1436 forcepae [X86-32]
1546 Forcefully enable Phy 1437 Forcefully enable Physical Address Extension (PAE).
1547 Many Pentium M system 1438 Many Pentium M systems disable PAE but may have a
1548 functionally usable P 1439 functionally usable PAE implementation.
1549 Warning: use of this 1440 Warning: use of this parameter will taint the kernel
1550 and may cause unknown 1441 and may cause unknown problems.
1551 1442
1552 fred= [X86-64] <<
1553 Enable/disable Flexib <<
1554 Format: { on | off } <<
1555 on: enable FRED when <<
1556 off: disable FRED, th <<
1557 <<
1558 ftrace=[tracer] 1443 ftrace=[tracer]
1559 [FTRACE] will set and 1444 [FTRACE] will set and start the specified tracer
1560 as early as possible 1445 as early as possible in order to facilitate early
1561 boot debugging. 1446 boot debugging.
1562 1447
1563 ftrace_boot_snapshot !! 1448 ftrace_dump_on_oops[=orig_cpu]
1564 [FTRACE] On boot up, <<
1565 ftrace ring buffer th <<
1566 /sys/kernel/tracing/s <<
1567 This is useful if you <<
1568 boot up that is likel <<
1569 start up functionalit <<
1570 <<
1571 Optionally, the snaps <<
1572 instance that was cre <<
1573 line parameter. <<
1574 <<
1575 trace_instance=foo,sc <<
1576 <<
1577 The above will cause <<
1578 a snapshot at the end <<
1579 <<
1580 ftrace_dump_on_oops[=2(orig_cpu) | =< <<
1581 ,<instance>=2(orig_ <<
1582 [FTRACE] will dump th 1449 [FTRACE] will dump the trace buffers on oops.
1583 If no parameter is pa !! 1450 If no parameter is passed, ftrace will dump
1584 buffers of all CPUs, !! 1451 buffers of all CPUs, but if you pass orig_cpu, it will
1585 will dump only the bu !! 1452 dump only the buffer of the CPU that triggered the
1586 the oops, or the spec !! 1453 oops.
1587 its name is passed. M <<
1588 supported, and instan <<
1589 instance supports onl <<
1590 oops by passing 2 or <<
1591 <<
1592 ftrace_dump_on_oops=f <<
1593 <<
1594 The above will dump o <<
1595 on CPU that triggered <<
1596 <<
1597 ftrace_dump_on_oops,f <<
1598 <<
1599 The above will dump g <<
1600 buffer of "foo" insta <<
1601 of "bar" instance on <<
1602 1454
1603 ftrace_filter=[function-list] 1455 ftrace_filter=[function-list]
1604 [FTRACE] Limit the fu 1456 [FTRACE] Limit the functions traced by the function
1605 tracer at boot up. fu 1457 tracer at boot up. function-list is a comma-separated
1606 list of functions. Th 1458 list of functions. This list can be changed at run
1607 time by the set_ftrac 1459 time by the set_ftrace_filter file in the debugfs
1608 tracing directory. 1460 tracing directory.
1609 1461
1610 ftrace_notrace=[function-list] 1462 ftrace_notrace=[function-list]
1611 [FTRACE] Do not trace 1463 [FTRACE] Do not trace the functions specified in
1612 function-list. This l 1464 function-list. This list can be changed at run time
1613 by the set_ftrace_not 1465 by the set_ftrace_notrace file in the debugfs
1614 tracing directory. 1466 tracing directory.
1615 1467
1616 ftrace_graph_filter=[function-list] 1468 ftrace_graph_filter=[function-list]
1617 [FTRACE] Limit the to 1469 [FTRACE] Limit the top level callers functions traced
1618 by the function graph 1470 by the function graph tracer at boot up.
1619 function-list is a co 1471 function-list is a comma-separated list of functions
1620 that can be changed a 1472 that can be changed at run time by the
1621 set_graph_function fi 1473 set_graph_function file in the debugfs tracing directory.
1622 1474
1623 ftrace_graph_notrace=[function-list] 1475 ftrace_graph_notrace=[function-list]
1624 [FTRACE] Do not trace 1476 [FTRACE] Do not trace from the functions specified in
1625 function-list. This 1477 function-list. This list is a comma-separated list of
1626 functions that can be 1478 functions that can be changed at run time by the
1627 set_graph_notrace fil 1479 set_graph_notrace file in the debugfs tracing directory.
1628 1480
1629 ftrace_graph_max_depth=<uint> 1481 ftrace_graph_max_depth=<uint>
1630 [FTRACE] Used with th 1482 [FTRACE] Used with the function graph tracer. This is
1631 the max depth it will 1483 the max depth it will trace into a function. This value
1632 can be changed at run 1484 can be changed at run time by the max_graph_depth file
1633 in the tracefs tracin 1485 in the tracefs tracing directory. default: 0 (no limit)
1634 1486
1635 fw_devlink= [KNL,EARLY] Create de !! 1487 fw_devlink= [KNL] Create device links between consumer and supplier
1636 devices by scanning t 1488 devices by scanning the firmware to infer the
1637 consumer/supplier rel 1489 consumer/supplier relationships. This feature is
1638 especially useful whe 1490 especially useful when drivers are loaded as modules as
1639 it ensures proper ord 1491 it ensures proper ordering of tasks like device probing
1640 (suppliers first, the 1492 (suppliers first, then consumers), supplier boot state
1641 clean up (only after 1493 clean up (only after all consumers have probed),
1642 suspend/resume & runt 1494 suspend/resume & runtime PM (consumers first, then
1643 suppliers). 1495 suppliers).
1644 Format: { off | permi 1496 Format: { off | permissive | on | rpm }
1645 off -- Don't create 1497 off -- Don't create device links from firmware info.
1646 permissive -- Create 1498 permissive -- Create device links from firmware info
1647 but use it on 1499 but use it only for ordering boot state clean
1648 up (sync_stat 1500 up (sync_state() calls).
1649 on -- Create device 1501 on -- Create device links from firmware info and use it
1650 to enforce pr 1502 to enforce probe and suspend/resume ordering.
1651 rpm -- Like "on", bu 1503 rpm -- Like "on", but also use to order runtime PM.
1652 1504
1653 fw_devlink.strict=<bool> 1505 fw_devlink.strict=<bool>
1654 [KNL,EARLY] Treat all !! 1506 [KNL] Treat all inferred dependencies as mandatory
1655 dependencies. This on 1507 dependencies. This only applies for fw_devlink=on|rpm.
1656 Format: <bool> 1508 Format: <bool>
1657 1509
1658 fw_devlink.sync_state = <<
1659 [KNL,EARLY] When all <<
1660 probing, this paramet <<
1661 devices that haven't <<
1662 calls. <<
1663 Format: { strict | ti <<
1664 strict -- Default. Co <<
1665 probe success <<
1666 timeout -- Give up wa <<
1667 sync_state() <<
1668 received thei <<
1669 deferred_prob <<
1670 late_initcall <<
1671 <<
1672 gamecon.map[2|3]= 1510 gamecon.map[2|3]=
1673 [HW,JOY] Multisystem 1511 [HW,JOY] Multisystem joystick and NES/SNES/PSX pad
1674 support via parallel 1512 support via parallel port (up to 5 devices per port)
1675 Format: <port#>,<pad1 1513 Format: <port#>,<pad1>,<pad2>,<pad3>,<pad4>,<pad5>
1676 See also Documentatio 1514 See also Documentation/input/devices/joystick-parport.rst
1677 1515
1678 gamma= [HW,DRM] 1516 gamma= [HW,DRM]
1679 1517
1680 gart_fix_e820= [X86-64,EARLY] disabl !! 1518 gart_fix_e820= [X86-64] disable the fix e820 for K8 GART
1681 Format: off | on 1519 Format: off | on
1682 default: on 1520 default: on
1683 1521
1684 gather_data_sampling= 1522 gather_data_sampling=
1685 [X86,INTEL,EARLY] Con !! 1523 [X86,INTEL] Control the Gather Data Sampling (GDS)
1686 mitigation. 1524 mitigation.
1687 1525
1688 Gather Data Sampling 1526 Gather Data Sampling is a hardware vulnerability which
1689 allows unprivileged s 1527 allows unprivileged speculative access to data which was
1690 previously stored in 1528 previously stored in vector registers.
1691 1529
1692 This issue is mitigat 1530 This issue is mitigated by default in updated microcode.
1693 The mitigation may ha 1531 The mitigation may have a performance impact but can be
1694 disabled. On systems 1532 disabled. On systems without the microcode mitigation
1695 disabling AVX serves 1533 disabling AVX serves as a mitigation.
1696 1534
1697 force: Disable AVX t 1535 force: Disable AVX to mitigate systems without
1698 microcode mit 1536 microcode mitigation. No effect if the microcode
1699 mitigation is 1537 mitigation is present. Known to cause crashes in
1700 userspace wit 1538 userspace with buggy AVX enumeration.
1701 1539
1702 off: Disable GDS m !! 1540 off: Disable GDS mitigation.
1703 1541
1704 gcov_persist= [GCOV] When non-zero 1542 gcov_persist= [GCOV] When non-zero (default), profiling data for
1705 kernel modules is sav 1543 kernel modules is saved and remains accessible via
1706 debugfs, even when th 1544 debugfs, even when the module is unloaded/reloaded.
1707 When zero, profiling 1545 When zero, profiling data is discarded and associated
1708 debugfs files are rem 1546 debugfs files are removed at module unload time.
1709 1547
1710 goldfish [X86] Enable the gold 1548 goldfish [X86] Enable the goldfish android emulator platform.
1711 Don't use this when y 1549 Don't use this when you are not running on the
1712 android emulator 1550 android emulator
1713 1551
1714 gpio-mockup.gpio_mockup_ranges 1552 gpio-mockup.gpio_mockup_ranges
1715 [HW] Sets the ranges 1553 [HW] Sets the ranges of gpiochip of for this device.
1716 Format: <start1>,<end 1554 Format: <start1>,<end1>,<start2>,<end2>...
1717 gpio-mockup.gpio_mockup_named_lines 1555 gpio-mockup.gpio_mockup_named_lines
1718 [HW] Let the driver k 1556 [HW] Let the driver know GPIO lines should be named.
1719 1557
1720 gpt [EFI] Forces disk wit 1558 gpt [EFI] Forces disk with valid GPT signature but
1721 invalid Protective MB 1559 invalid Protective MBR to be treated as GPT. If the
1722 primary GPT is corrup 1560 primary GPT is corrupted, it enables the backup/alternate
1723 GPT to be used instea 1561 GPT to be used instead.
1724 1562
1725 grcan.enable0= [HW] Configuration of 1563 grcan.enable0= [HW] Configuration of physical interface 0. Determines
1726 the "Enable 0" bit of 1564 the "Enable 0" bit of the configuration register.
1727 Format: 0 | 1 1565 Format: 0 | 1
1728 Default: 0 1566 Default: 0
1729 grcan.enable1= [HW] Configuration of 1567 grcan.enable1= [HW] Configuration of physical interface 1. Determines
1730 the "Enable 0" bit of 1568 the "Enable 0" bit of the configuration register.
1731 Format: 0 | 1 1569 Format: 0 | 1
1732 Default: 0 1570 Default: 0
1733 grcan.select= [HW] Select which phy 1571 grcan.select= [HW] Select which physical interface to use.
1734 Format: 0 | 1 1572 Format: 0 | 1
1735 Default: 0 1573 Default: 0
1736 grcan.txsize= [HW] Sets the size of 1574 grcan.txsize= [HW] Sets the size of the tx buffer.
1737 Format: <unsigned int 1575 Format: <unsigned int> such that (txsize & ~0x1fffc0) == 0.
1738 Default: 1024 1576 Default: 1024
1739 grcan.rxsize= [HW] Sets the size of 1577 grcan.rxsize= [HW] Sets the size of the rx buffer.
1740 Format: <unsigned int 1578 Format: <unsigned int> such that (rxsize & ~0x1fffc0) == 0.
1741 Default: 1024 1579 Default: 1024
1742 1580
1743 hardened_usercopy= <<
1744 [KNL] Under CONFIG_HA <<
1745 hardening is enabled <<
1746 usercopy checking is <<
1747 from reading or writi <<
1748 allocation boundaries <<
1749 against bounds-checki <<
1750 copy_to_user()/copy_f <<
1751 on Perform hardened user <<
1752 off Disable hardened user <<
1753 <<
1754 hardlockup_all_cpu_backtrace= 1581 hardlockup_all_cpu_backtrace=
1755 [KNL] Should the hard 1582 [KNL] Should the hard-lockup detector generate
1756 backtraces on all cpu 1583 backtraces on all cpus.
1757 Format: 0 | 1 1584 Format: 0 | 1
1758 1585
1759 hashdist= [KNL,NUMA] Large hash 1586 hashdist= [KNL,NUMA] Large hashes allocated during boot
1760 are distributed acros 1587 are distributed across NUMA nodes. Defaults on
1761 for 64-bit NUMA, off 1588 for 64-bit NUMA, off otherwise.
1762 Format: 0 | 1 (for of 1589 Format: 0 | 1 (for off | on)
1763 1590
>> 1591 hcl= [IA-64] SGI's Hardware Graph compatibility layer
>> 1592
1764 hd= [EIDE] (E)IDE hard dr 1593 hd= [EIDE] (E)IDE hard drive subsystem geometry
1765 Format: <cyl>,<head>, 1594 Format: <cyl>,<head>,<sect>
1766 1595
1767 hest_disable [ACPI] 1596 hest_disable [ACPI]
1768 Disable Hardware Erro 1597 Disable Hardware Error Source Table (HEST) support;
1769 corresponding firmwar 1598 corresponding firmware-first mode error processing
1770 logic will be disable 1599 logic will be disabled.
1771 1600
1772 hibernate= [HIBERNATION] !! 1601 highmem=nn[KMG] [KNL,BOOT] forces the highmem zone to have an exact
1773 noresume Don't check i <<
1774 present durin <<
1775 nocompress Don't compres <<
1776 no Disable hiber <<
1777 protect_image Turn on image <<
1778 (that will se <<
1779 during restor <<
1780 <<
1781 hibernate.compressor= [HIBERNATION] <<
1782 used with hib <<
1783 Format: { lzo <<
1784 Default: lzo <<
1785 <<
1786 lzo: Select L <<
1787 compress/deco <<
1788 <<
1789 lz4: Select L <<
1790 compress/deco <<
1791 <<
1792 highmem=nn[KMG] [KNL,BOOT,EARLY] forc <<
1793 size of <nn>. This wo 1602 size of <nn>. This works even on boxes that have no
1794 highmem otherwise. Th 1603 highmem otherwise. This also works to reduce highmem
1795 size on bigger boxes. 1604 size on bigger boxes.
1796 1605
1797 highres= [KNL] Enable/disable 1606 highres= [KNL] Enable/disable high resolution timer mode.
1798 Valid parameters: "on 1607 Valid parameters: "on", "off"
1799 Default: "on" 1608 Default: "on"
1800 1609
1801 hlt [BUGS=ARM,SH] 1610 hlt [BUGS=ARM,SH]
1802 1611
1803 hostname= [KNL,EARLY] Set the h <<
1804 Format: <string> <<
1805 This allows setting t <<
1806 startup. This sets th <<
1807 Using this parameter <<
1808 possible to ensure th <<
1809 any userspace process <<
1810 that a process may ca <<
1811 has been explicitly s <<
1812 process getting an in <<
1813 not exceed the maximu <<
1814 64 characters) and wi <<
1815 <<
1816 hpet= [X86-32,HPET] option 1612 hpet= [X86-32,HPET] option to control HPET usage
1817 Format: { enable (def 1613 Format: { enable (default) | disable | force |
1818 verbose } 1614 verbose }
1819 disable: disable HPET 1615 disable: disable HPET and use PIT instead
1820 force: allow force en 1616 force: allow force enabled of undocumented chips (ICH4,
1821 VIA, nVidia) 1617 VIA, nVidia)
1822 verbose: show content 1618 verbose: show contents of HPET registers during setup
1823 1619
1824 hpet_mmap= [X86, HPET_MMAP] Allo 1620 hpet_mmap= [X86, HPET_MMAP] Allow userspace to mmap HPET
1825 registers. Default s 1621 registers. Default set by CONFIG_HPET_MMAP_DEFAULT.
1826 1622
>> 1623 hugetlb_cma= [HW,CMA] The size of a CMA area used for allocation
>> 1624 of gigantic hugepages.
>> 1625 Format: nn[KMGTPE]
>> 1626
>> 1627 Reserve a CMA area of given size and allocate gigantic
>> 1628 hugepages using the CMA allocator. If enabled, the
>> 1629 boot-time allocation of gigantic hugepages is skipped.
>> 1630
1827 hugepages= [HW] Number of HugeTL 1631 hugepages= [HW] Number of HugeTLB pages to allocate at boot.
1828 If this follows hugep 1632 If this follows hugepagesz (below), it specifies
1829 the number of pages o 1633 the number of pages of hugepagesz to be allocated.
1830 If this is the first 1634 If this is the first HugeTLB parameter on the command
1831 line, it specifies th 1635 line, it specifies the number of pages to allocate for
1832 the default huge page !! 1636 the default huge page size. See also
1833 number of pages to al !! 1637 Documentation/admin-guide/mm/hugetlbpage.rst.
1834 See also Documentatio !! 1638 Format: <integer>
1835 Format: <integer> or <<
1836 <node>:<integ <<
1837 1639
1838 hugepagesz= 1640 hugepagesz=
1839 [HW] The size of the 1641 [HW] The size of the HugeTLB pages. This is used in
1840 conjunction with huge 1642 conjunction with hugepages (above) to allocate huge
1841 pages of a specific s 1643 pages of a specific size at boot. The pair
1842 hugepagesz=X hugepage 1644 hugepagesz=X hugepages=Y can be specified once for
1843 each supported huge p 1645 each supported huge page size. Huge page sizes are
1844 architecture dependen 1646 architecture dependent. See also
1845 Documentation/admin-g 1647 Documentation/admin-guide/mm/hugetlbpage.rst.
1846 Format: size[KMG] 1648 Format: size[KMG]
1847 1649
1848 hugetlb_cma= [HW,CMA,EARLY] The si <<
1849 of gigantic hugepages <<
1850 of a CMA area per nod <<
1851 Format: nn[KMGTPE] or <<
1852 <node>:nn[KMG <<
1853 <<
1854 Reserve a CMA area of <<
1855 hugepages using the C <<
1856 boot-time allocation <<
1857 <<
1858 hugetlb_free_vmemmap= 1650 hugetlb_free_vmemmap=
1859 [KNL] Requires CONFIG !! 1651 [KNL] Reguires CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
1860 enabled. 1652 enabled.
1861 Control if HugeTLB Vm <<
1862 Allows heavy hugetlb 1653 Allows heavy hugetlb users to free up some more
1863 memory (7 * PAGE_SIZE !! 1654 memory (6 * PAGE_SIZE for each 2MB hugetlb page).
1864 Format: { on | off (d 1655 Format: { on | off (default) }
1865 1656
1866 on: enable HVO !! 1657 on: enable the feature
1867 off: disable HVO !! 1658 off: disable the feature
1868 1659
1869 Built with CONFIG_HUG !! 1660 Built with CONFIG_HUGETLB_PAGE_FREE_VMEMMAP_DEFAULT_ON=y,
1870 the default is on. 1661 the default is on.
1871 1662
1872 Note that the vmemmap !! 1663 This is not compatible with memory_hotplug.memmap_on_memory.
1873 memory block itself w !! 1664 If both parameters are enabled, hugetlb_free_vmemmap takes
1874 enabled, those vmemma !! 1665 precedence over memory_hotplug.memmap_on_memory.
1875 feature is enabled. <<
1876 the added memory bloc <<
1877 1666
1878 hung_task_panic= 1667 hung_task_panic=
1879 [KNL] Should the hung 1668 [KNL] Should the hung task detector generate panics.
1880 Format: 0 | 1 1669 Format: 0 | 1
1881 1670
1882 A value of 1 instruct 1671 A value of 1 instructs the kernel to panic when a
1883 hung task is detected 1672 hung task is detected. The default value is controlled
1884 by the CONFIG_BOOTPAR 1673 by the CONFIG_BOOTPARAM_HUNG_TASK_PANIC build-time
1885 option. The value sel 1674 option. The value selected by this boot parameter can
1886 be changed later by t 1675 be changed later by the kernel.hung_task_panic sysctl.
1887 1676
1888 hvc_iucv= [S390] Number of z/V 1677 hvc_iucv= [S390] Number of z/VM IUCV hypervisor console (HVC)
1889 terminal devi 1678 terminal devices. Valid values: 0..8
1890 hvc_iucv_allow= [S390] Comma-separat 1679 hvc_iucv_allow= [S390] Comma-separated list of z/VM user IDs.
1891 If specified, 1680 If specified, z/VM IUCV HVC accepts connections
1892 from listed z 1681 from listed z/VM user IDs only.
1893 1682
1894 hv_nopvspin [X86,HYPER_V,EARLY] !! 1683 hv_nopvspin [X86,HYPER_V] Disables the paravirt spinlock optimizations
1895 Disables the paravirt !! 1684 which allow the hypervisor to 'idle' the
1896 which allow the hyper !! 1685 guest on lock contention.
1897 on lock contention. !! 1686
>> 1687 keep_bootcon [KNL]
>> 1688 Do not unregister boot console at start. This is only
>> 1689 useful for debugging when something happens in the window
>> 1690 between unregistering the boot console and initializing
>> 1691 the real console.
1898 1692
1899 i2c_bus= [HW] Override the 1693 i2c_bus= [HW] Override the default board specific I2C bus speed
1900 or register a 1694 or register an additional I2C bus that is not
1901 registered fr 1695 registered from board initialization code.
1902 Format: 1696 Format:
1903 <bus_id>,<clk 1697 <bus_id>,<clkrate>
1904 1698
1905 i2c_touchscreen_props= [HW,ACPI,X86] <<
1906 Set device-properties <<
1907 touchscreen, to e.g. <<
1908 mounted touchscreens. <<
1909 submit a drivers/plat <<
1910 adding a DMI quirk fo <<
1911 <<
1912 Format: <<
1913 <ACPI_HW_ID>:<prop_na <<
1914 Where <val> is one of <<
1915 Omit "=<val>" entirel <<
1916 Unsigned number <<
1917 Anything else <<
1918 <<
1919 Examples (split over <<
1920 i2c_touchscreen_props <<
1921 touchscreen-inverted- <<
1922 <<
1923 i2c_touchscreen_props <<
1924 touchscreen-size-y=10 <<
1925 firmware-name=gsl1680 <<
1926 <<
1927 i8042.debug [HW] Toggle i8042 deb 1699 i8042.debug [HW] Toggle i8042 debug mode
1928 i8042.unmask_kbd_data 1700 i8042.unmask_kbd_data
1929 [HW] Enable printing 1701 [HW] Enable printing of interrupt data from the KBD port
1930 (disabled by def 1702 (disabled by default, and as a pre-condition
1931 requires that i8 1703 requires that i8042.debug=1 be enabled)
1932 i8042.direct [HW] Put keyboard por 1704 i8042.direct [HW] Put keyboard port into non-translated mode
1933 i8042.dumbkbd [HW] Pretend that con 1705 i8042.dumbkbd [HW] Pretend that controller can only read data from
1934 keyboard and can 1706 keyboard and cannot control its state
1935 (Don't attempt t 1707 (Don't attempt to blink the leds)
1936 i8042.noaux [HW] Don't check for 1708 i8042.noaux [HW] Don't check for auxiliary (== mouse) port
1937 i8042.nokbd [HW] Don't check/crea 1709 i8042.nokbd [HW] Don't check/create keyboard port
1938 i8042.noloop [HW] Disable the AUX 1710 i8042.noloop [HW] Disable the AUX Loopback command while probing
1939 for the AUX port 1711 for the AUX port
1940 i8042.nomux [HW] Don't check pres 1712 i8042.nomux [HW] Don't check presence of an active multiplexing
1941 controller 1713 controller
1942 i8042.nopnp [HW] Don't use ACPIPn 1714 i8042.nopnp [HW] Don't use ACPIPnP / PnPBIOS to discover KBD/AUX
1943 controllers 1715 controllers
1944 i8042.notimeout [HW] Ignore timeout c 1716 i8042.notimeout [HW] Ignore timeout condition signalled by controller
1945 i8042.reset [HW] Reset the contro 1717 i8042.reset [HW] Reset the controller during init, cleanup and
1946 suspend-to-ram t 1718 suspend-to-ram transitions, only during s2r
1947 transitions, or 1719 transitions, or never reset
1948 Format: { 1 | Y | y | 1720 Format: { 1 | Y | y | 0 | N | n }
1949 1, Y, y: always reset 1721 1, Y, y: always reset controller
1950 0, N, n: don't ever r 1722 0, N, n: don't ever reset controller
1951 Default: only on s2r 1723 Default: only on s2r transitions on x86; most other
1952 architectures force r 1724 architectures force reset to be always executed
1953 i8042.unlock [HW] Unlock (ignore) 1725 i8042.unlock [HW] Unlock (ignore) the keylock
1954 i8042.kbdreset [HW] Reset device con 1726 i8042.kbdreset [HW] Reset device connected to KBD port
1955 i8042.probe_defer 1727 i8042.probe_defer
1956 [HW] Allow deferred p 1728 [HW] Allow deferred probing upon i8042 probe errors
1957 1729
1958 i810= [HW,DRM] 1730 i810= [HW,DRM]
1959 1731
>> 1732 i8k.ignore_dmi [HW] Continue probing hardware even if DMI data
>> 1733 indicates that the driver is running on unsupported
>> 1734 hardware.
>> 1735 i8k.force [HW] Activate i8k driver even if SMM BIOS signature
>> 1736 does not match list of supported models.
>> 1737 i8k.power_status
>> 1738 [HW] Report power status in /proc/i8k
>> 1739 (disabled by default)
>> 1740 i8k.restricted [HW] Allow controlling fans only if SYS_ADMIN
>> 1741 capability is set.
>> 1742
1960 i915.invert_brightness= 1743 i915.invert_brightness=
1961 [DRM] Invert the sens 1744 [DRM] Invert the sense of the variable that is used to
1962 set the brightness of 1745 set the brightness of the panel backlight. Normally a
1963 brightness value of 0 1746 brightness value of 0 indicates backlight switched off,
1964 and the maximum of th 1747 and the maximum of the brightness value sets the backlight
1965 to maximum brightness 1748 to maximum brightness. If this parameter is set to 0
1966 (default) and the mac 1749 (default) and the machine requires it, or this parameter
1967 is set to 1, a bright 1750 is set to 1, a brightness value of 0 sets the backlight
1968 to maximum brightness 1751 to maximum brightness, and the maximum of the brightness
1969 value switches the ba 1752 value switches the backlight off.
1970 -1 -- never invert br 1753 -1 -- never invert brightness
1971 0 -- machine default 1754 0 -- machine default
1972 1 -- force brightnes 1755 1 -- force brightness inversion
1973 1756
1974 ia32_emulation= [X86-64] <<
1975 Format: <bool> <<
1976 When true, allows loa <<
1977 syscalls, essentially <<
1978 boot time. When false <<
1979 <<
1980 icn= [HW,ISDN] 1757 icn= [HW,ISDN]
1981 Format: <io>[,<membas 1758 Format: <io>[,<membase>[,<icn_id>[,<icn_id2>]]]
1982 1759
>> 1760 ide-core.nodma= [HW] (E)IDE subsystem
>> 1761 Format: =0.0 to prevent dma on hda, =0.1 hdb =1.0 hdc
>> 1762 .vlb_clock .pci_clock .noflush .nohpa .noprobe .nowerr
>> 1763 .cdrom .chs .ignore_cable are additional options
>> 1764 See Documentation/ide/ide.rst.
1983 1765
1984 idle= [X86,EARLY] !! 1766 ide-generic.probe-mask= [HW] (E)IDE subsystem
>> 1767 Format: <int>
>> 1768 Probe mask for legacy ISA IDE ports. Depending on
>> 1769 platform up to 6 ports are supported, enabled by
>> 1770 setting corresponding bits in the mask to 1. The
>> 1771 default value is 0x0, which has a special meaning.
>> 1772 On systems that have PCI, it triggers scanning the
>> 1773 PCI bus for the first and the second port, which
>> 1774 are then probed. On systems without PCI the value
>> 1775 of 0x0 enables probing the two first ports as if it
>> 1776 was 0x3.
>> 1777
>> 1778 ide-pci-generic.all-generic-ide [HW] (E)IDE subsystem
>> 1779 Claim all unknown PCI IDE storage controllers.
>> 1780
>> 1781 idle= [X86]
1985 Format: idle=poll, id 1782 Format: idle=poll, idle=halt, idle=nomwait
1986 Poll forces a polling 1783 Poll forces a polling idle loop that can slightly
1987 improve the performan 1784 improve the performance of waking up a idle CPU, but
1988 will use a lot of pow 1785 will use a lot of power and make the system run hot.
1989 Not recommended. 1786 Not recommended.
1990 idle=halt: Halt is fo 1787 idle=halt: Halt is forced to be used for CPU idle.
1991 In such case C2/C3 wo 1788 In such case C2/C3 won't be used again.
1992 idle=nomwait: Disable 1789 idle=nomwait: Disable mwait for CPU C-states
1993 1790
1994 idxd.sva= [HW] 1791 idxd.sva= [HW]
1995 Format: <bool> 1792 Format: <bool>
1996 Allow force disabling 1793 Allow force disabling of Shared Virtual Memory (SVA)
1997 support for the idxd 1794 support for the idxd driver. By default it is set to
1998 true (1). 1795 true (1).
1999 1796
2000 idxd.tc_override= [HW] 1797 idxd.tc_override= [HW]
2001 Format: <bool> 1798 Format: <bool>
2002 Allow override of def 1799 Allow override of default traffic class configuration
2003 for the device. By de 1800 for the device. By default it is set to false (0).
2004 1801
2005 ieee754= [MIPS] Select IEEE St 1802 ieee754= [MIPS] Select IEEE Std 754 conformance mode
2006 Format: { strict | le !! 1803 Format: { strict | legacy | 2008 | relaxed }
2007 Default: strict 1804 Default: strict
2008 1805
2009 Choose which programs 1806 Choose which programs will be accepted for execution
2010 based on the IEEE 754 1807 based on the IEEE 754 NaN encoding(s) supported by
2011 the FPU and the NaN e 1808 the FPU and the NaN encoding requested with the value
2012 of an ELF file header 1809 of an ELF file header flag individually set by each
2013 binary. Hardware imp 1810 binary. Hardware implementations are permitted to
2014 support either or bot 1811 support either or both of the legacy and the 2008 NaN
2015 encoding mode. 1812 encoding mode.
2016 1813
2017 Available settings ar 1814 Available settings are as follows:
2018 strict accept binari 1815 strict accept binaries that request a NaN encoding
2019 supported by 1816 supported by the FPU
2020 legacy only accept l 1817 legacy only accept legacy-NaN binaries, if supported
2021 by the FPU 1818 by the FPU
2022 2008 only accept 2 1819 2008 only accept 2008-NaN binaries, if supported
2023 by the FPU 1820 by the FPU
2024 relaxed accept any bi 1821 relaxed accept any binaries regardless of whether
2025 supported by 1822 supported by the FPU
2026 emulated accept any b <<
2027 if binary mod <<
2028 1823
2029 The FPU emulator is a 1824 The FPU emulator is always able to support both NaN
2030 encodings, so if no F 1825 encodings, so if no FPU hardware is present or it has
2031 been disabled with 'n 1826 been disabled with 'nofpu', then the settings of
2032 'legacy' and '2008' s 1827 'legacy' and '2008' strap the emulator accordingly,
2033 'relaxed' straps the 1828 'relaxed' straps the emulator for both legacy-NaN and
2034 2008-NaN, whereas 'st 1829 2008-NaN, whereas 'strict' enables legacy-NaN only on
2035 legacy processors and 1830 legacy processors and both NaN encodings on MIPS32 or
2036 MIPS64 CPUs. 1831 MIPS64 CPUs.
2037 1832
2038 The setting for ABS.f 1833 The setting for ABS.fmt/NEG.fmt instruction execution
2039 mode generally follow 1834 mode generally follows that for the NaN encoding,
2040 except where unsuppor 1835 except where unsupported by hardware.
2041 1836
2042 ignore_loglevel [KNL,EARLY] !! 1837 ignore_loglevel [KNL]
2043 Ignore loglevel setti 1838 Ignore loglevel setting - this will print /all/
2044 kernel messages to th 1839 kernel messages to the console. Useful for debugging.
2045 We also add it as pri 1840 We also add it as printk module parameter, so users
2046 could change it dynam 1841 could change it dynamically, usually by
2047 /sys/module/printk/pa 1842 /sys/module/printk/parameters/ignore_loglevel.
2048 1843
2049 ignore_rlimit_data 1844 ignore_rlimit_data
2050 Ignore RLIMIT_DATA se 1845 Ignore RLIMIT_DATA setting for data mappings,
2051 print warning at firs 1846 print warning at first misuse. Can be changed via
2052 /sys/module/kernel/pa 1847 /sys/module/kernel/parameters/ignore_rlimit_data.
2053 1848
2054 ihash_entries= [KNL] 1849 ihash_entries= [KNL]
2055 Set number of hash bu 1850 Set number of hash buckets for inode cache.
2056 1851
2057 ima_appraise= [IMA] appraise integr 1852 ima_appraise= [IMA] appraise integrity measurements
2058 Format: { "off" | "en 1853 Format: { "off" | "enforce" | "fix" | "log" }
2059 default: "enforce" 1854 default: "enforce"
2060 1855
2061 ima_appraise_tcb [IMA] Deprecated. U 1856 ima_appraise_tcb [IMA] Deprecated. Use ima_policy= instead.
2062 The builtin appraise 1857 The builtin appraise policy appraises all files
2063 owned by uid=0. 1858 owned by uid=0.
2064 1859
2065 ima_canonical_fmt [IMA] 1860 ima_canonical_fmt [IMA]
2066 Use the canonical for 1861 Use the canonical format for the binary runtime
2067 measurements, instead 1862 measurements, instead of host native format.
2068 1863
2069 ima_hash= [IMA] 1864 ima_hash= [IMA]
2070 Format: { md5 | sha1 1865 Format: { md5 | sha1 | rmd160 | sha256 | sha384
2071 | sha512 | 1866 | sha512 | ... }
2072 default: "sha1" 1867 default: "sha1"
2073 1868
2074 The list of supported 1869 The list of supported hash algorithms is defined
2075 in crypto/hash_info.h 1870 in crypto/hash_info.h.
2076 1871
2077 ima_policy= [IMA] 1872 ima_policy= [IMA]
2078 The builtin policies 1873 The builtin policies to load during IMA setup.
2079 Format: "tcb | apprai 1874 Format: "tcb | appraise_tcb | secure_boot |
2080 fail_securel 1875 fail_securely | critical_data"
2081 1876
2082 The "tcb" policy meas 1877 The "tcb" policy measures all programs exec'd, files
2083 mmap'd for exec, and 1878 mmap'd for exec, and all files opened with the read
2084 mode bit set by eithe 1879 mode bit set by either the effective uid (euid=0) or
2085 uid=0. 1880 uid=0.
2086 1881
2087 The "appraise_tcb" po 1882 The "appraise_tcb" policy appraises the integrity of
2088 all files owned by ro 1883 all files owned by root.
2089 1884
2090 The "secure_boot" pol 1885 The "secure_boot" policy appraises the integrity
2091 of files (eg. kexec k 1886 of files (eg. kexec kernel image, kernel modules,
2092 firmware, policy, etc 1887 firmware, policy, etc) based on file signatures.
2093 1888
2094 The "fail_securely" p 1889 The "fail_securely" policy forces file signature
2095 verification failure 1890 verification failure also on privileged mounted
2096 filesystems with the 1891 filesystems with the SB_I_UNVERIFIABLE_SIGNATURE
2097 flag. 1892 flag.
2098 1893
2099 The "critical_data" p 1894 The "critical_data" policy measures kernel integrity
2100 critical data. 1895 critical data.
2101 1896
2102 ima_tcb [IMA] Deprecated. Us 1897 ima_tcb [IMA] Deprecated. Use ima_policy= instead.
2103 Load a policy which m 1898 Load a policy which meets the needs of the Trusted
2104 Computing Base. This 1899 Computing Base. This means IMA will measure all
2105 programs exec'd, file 1900 programs exec'd, files mmap'd for exec, and all files
2106 opened for read by ui 1901 opened for read by uid=0.
2107 1902
2108 ima_template= [IMA] 1903 ima_template= [IMA]
2109 Select one of defined 1904 Select one of defined IMA measurements template formats.
2110 Formats: { "ima" | "i !! 1905 Formats: { "ima" | "ima-ng" | "ima-sig" }
2111 "ima-sigv2 <<
2112 Default: "ima-ng" 1906 Default: "ima-ng"
2113 1907
2114 ima_template_fmt= 1908 ima_template_fmt=
2115 [IMA] Define a custom 1909 [IMA] Define a custom template format.
2116 Format: { "field1|... 1910 Format: { "field1|...|fieldN" }
2117 1911
2118 ima.ahash_minsize= [IMA] Minimum file 1912 ima.ahash_minsize= [IMA] Minimum file size for asynchronous hash usage
2119 Format: <min_file_siz 1913 Format: <min_file_size>
2120 Set the minimal file 1914 Set the minimal file size for using asynchronous hash.
2121 If left unspecified, 1915 If left unspecified, ahash usage is disabled.
2122 1916
2123 ahash performance var 1917 ahash performance varies for different data sizes on
2124 different crypto acce 1918 different crypto accelerators. This option can be used
2125 to achieve the best p 1919 to achieve the best performance for a particular HW.
2126 1920
2127 ima.ahash_bufsize= [IMA] Asynchronous 1921 ima.ahash_bufsize= [IMA] Asynchronous hash buffer size
2128 Format: <bufsize> 1922 Format: <bufsize>
2129 Set hashing buffer si 1923 Set hashing buffer size. Default: 4k.
2130 1924
2131 ahash performance var 1925 ahash performance varies for different chunk sizes on
2132 different crypto acce 1926 different crypto accelerators. This option can be used
2133 to achieve best perfo 1927 to achieve best performance for particular HW.
2134 1928
2135 init= [KNL] 1929 init= [KNL]
2136 Format: <full_path> 1930 Format: <full_path>
2137 Run specified binary 1931 Run specified binary instead of /sbin/init as init
2138 process. 1932 process.
2139 1933
2140 initcall_debug [KNL] Trace initcalls 1934 initcall_debug [KNL] Trace initcalls as they are executed. Useful
2141 for working out where 1935 for working out where the kernel is dying during
2142 startup. 1936 startup.
2143 1937
2144 initcall_blacklist= [KNL] Do not exe 1938 initcall_blacklist= [KNL] Do not execute a comma-separated list of
2145 initcall functions. 1939 initcall functions. Useful for debugging built-in
2146 modules and initcalls 1940 modules and initcalls.
2147 1941
2148 initramfs_async= [KNL] 1942 initramfs_async= [KNL]
2149 Format: <bool> 1943 Format: <bool>
2150 Default: 1 1944 Default: 1
2151 This parameter contro 1945 This parameter controls whether the initramfs
2152 image is unpacked asy 1946 image is unpacked asynchronously, concurrently
2153 with devices being pr 1947 with devices being probed and
2154 initialized. This sho 1948 initialized. This should normally just work,
2155 but as a debugging ai 1949 but as a debugging aid, one can get the
2156 historical behaviour 1950 historical behaviour of the initramfs
2157 unpacking being compl 1951 unpacking being completed before device_ and
2158 late_ initcalls. 1952 late_ initcalls.
2159 1953
2160 initrd= [BOOT,EARLY] Specify !! 1954 initrd= [BOOT] Specify the location of the initial ramdisk
2161 1955
2162 initrdmem= [KNL,EARLY] Specify a !! 1956 initrdmem= [KNL] Specify a physical address and size from which to
2163 load the initrd. If a 1957 load the initrd. If an initrd is compiled in or
2164 specified in the boot 1958 specified in the bootparams, it takes priority over this
2165 setting. 1959 setting.
2166 Format: ss[KMG],nn[KM 1960 Format: ss[KMG],nn[KMG]
2167 Default is 0, 0 1961 Default is 0, 0
2168 1962
2169 init_on_alloc= [MM,EARLY] Fill newly !! 1963 init_on_alloc= [MM] Fill newly allocated pages and heap objects with
2170 zeroes. 1964 zeroes.
2171 Format: 0 | 1 1965 Format: 0 | 1
2172 Default set by CONFIG 1966 Default set by CONFIG_INIT_ON_ALLOC_DEFAULT_ON.
2173 1967
2174 init_on_free= [MM,EARLY] Fill freed !! 1968 init_on_free= [MM] Fill freed pages and heap objects with zeroes.
2175 Format: 0 | 1 1969 Format: 0 | 1
2176 Default set by CONFIG 1970 Default set by CONFIG_INIT_ON_FREE_DEFAULT_ON.
2177 1971
2178 init_pkru= [X86] Specify the def 1972 init_pkru= [X86] Specify the default memory protection keys rights
2179 register contents for 1973 register contents for all processes. 0x55555554 by
2180 default (disallow acc 1974 default (disallow access to all but pkey 0). Can
2181 override in debugfs a 1975 override in debugfs after boot.
2182 1976
2183 inport.irq= [HW] Inport (ATI XL a 1977 inport.irq= [HW] Inport (ATI XL and Microsoft) busmouse driver
2184 Format: <irq> 1978 Format: <irq>
2185 1979
2186 int_pln_enable [X86] Enable power li 1980 int_pln_enable [X86] Enable power limit notification interrupt
2187 1981
2188 integrity_audit=[IMA] 1982 integrity_audit=[IMA]
2189 Format: { "0" | "1" } 1983 Format: { "0" | "1" }
2190 0 -- basic integrity 1984 0 -- basic integrity auditing messages. (Default)
2191 1 -- additional integ 1985 1 -- additional integrity auditing messages.
2192 1986
2193 intel_iommu= [DMAR] Intel IOMMU dr 1987 intel_iommu= [DMAR] Intel IOMMU driver (DMAR) option
2194 on 1988 on
2195 Enable intel iommu dr 1989 Enable intel iommu driver.
2196 off 1990 off
2197 Disable intel iommu d 1991 Disable intel iommu driver.
2198 igfx_off [Default Off] 1992 igfx_off [Default Off]
2199 By default, gfx is ma 1993 By default, gfx is mapped as normal device. If a gfx
2200 device has a dedicate 1994 device has a dedicated DMAR unit, the DMAR unit is
2201 bypassed by not enabl 1995 bypassed by not enabling DMAR with this option. In
2202 this case, gfx device 1996 this case, gfx device will use physical address for
2203 DMA. 1997 DMA.
2204 strict [Default Off] 1998 strict [Default Off]
2205 Deprecated, equivalen 1999 Deprecated, equivalent to iommu.strict=1.
2206 sp_off [Default Off] 2000 sp_off [Default Off]
2207 By default, super pag 2001 By default, super page will be supported if Intel IOMMU
2208 has the capability. W 2002 has the capability. With this option, super page will
2209 not be supported. 2003 not be supported.
2210 sm_on 2004 sm_on
2211 Enable the Intel IOMM 2005 Enable the Intel IOMMU scalable mode if the hardware
2212 advertises that it ha 2006 advertises that it has support for the scalable mode
2213 translation. 2007 translation.
2214 sm_off 2008 sm_off
2215 Disallow use of the I 2009 Disallow use of the Intel IOMMU scalable mode.
2216 tboot_noforce [Default Off] 2010 tboot_noforce [Default Off]
2217 Do not force the Inte 2011 Do not force the Intel IOMMU enabled under tboot.
2218 By default, tboot wil 2012 By default, tboot will force Intel IOMMU on, which
2219 could harm performanc 2013 could harm performance of some high-throughput
2220 devices like 40GBit n 2014 devices like 40GBit network cards, even if identity
2221 mapping is enabled. 2015 mapping is enabled.
2222 Note that using this 2016 Note that using this option lowers the security
2223 provided by tboot bec 2017 provided by tboot because it makes the system
2224 vulnerable to DMA att 2018 vulnerable to DMA attacks.
2225 2019
2226 intel_idle.max_cstate= [KNL,HW,ACPI, 2020 intel_idle.max_cstate= [KNL,HW,ACPI,X86]
2227 0 disables inte 2021 0 disables intel_idle and fall back on acpi_idle.
2228 1 to 9 specify maxim 2022 1 to 9 specify maximum depth of C-state.
2229 2023
2230 intel_pstate= [X86,EARLY] !! 2024 intel_pstate= [X86]
2231 disable 2025 disable
2232 Do not enable intel 2026 Do not enable intel_pstate as the default
2233 scaling driver for 2027 scaling driver for the supported processors
2234 active <<
2235 Use intel_pstate dr <<
2236 governors layer of <<
2237 algorithms for p-st <<
2238 P-state selection a <<
2239 intel_pstate in the <<
2240 performance. The w <<
2241 on whether or not t <<
2242 (HWP) feature has b <<
2243 and possibly on the <<
2244 passive 2028 passive
2245 Use intel_pstate as 2029 Use intel_pstate as a scaling driver, but configure it
2246 to work with generi 2030 to work with generic cpufreq governors (instead of
2247 enabling its intern 2031 enabling its internal governor). This mode cannot be
2248 used along with the 2032 used along with the hardware-managed P-states (HWP)
2249 feature. 2033 feature.
2250 force 2034 force
2251 Enable intel_pstate 2035 Enable intel_pstate on systems that prohibit it by default
2252 in favor of acpi-cp 2036 in favor of acpi-cpufreq. Forcing the intel_pstate driver
2253 instead of acpi-cpu 2037 instead of acpi-cpufreq may disable platform features, such
2254 as thermal controls 2038 as thermal controls and power capping, that rely on ACPI
2255 P-States informatio 2039 P-States information being indicated to OSPM and therefore
2256 should be used with 2040 should be used with caution. This option does not work with
2257 processors that are 2041 processors that aren't supported by the intel_pstate driver
2258 or on platforms tha 2042 or on platforms that use pcc-cpufreq instead of acpi-cpufreq.
2259 no_hwp 2043 no_hwp
2260 Do not enable hardw 2044 Do not enable hardware P state control (HWP)
2261 if available. 2045 if available.
2262 hwp_only 2046 hwp_only
2263 Only load intel_pst 2047 Only load intel_pstate on systems which support
2264 hardware P state co 2048 hardware P state control (HWP) if available.
2265 support_acpi_ppc 2049 support_acpi_ppc
2266 Enforce ACPI _PPC p 2050 Enforce ACPI _PPC performance limits. If the Fixed ACPI
2267 Description Table, 2051 Description Table, specifies preferred power management
2268 profile as "Enterpr 2052 profile as "Enterprise Server" or "Performance Server",
2269 then this feature i 2053 then this feature is turned on by default.
2270 per_cpu_perf_limits 2054 per_cpu_perf_limits
2271 Allow per-logical-C 2055 Allow per-logical-CPU P-State performance control limits using
2272 cpufreq sysfs inter 2056 cpufreq sysfs interface
2273 2057
2274 intremap= [X86-64,Intel-IOMMU,E !! 2058 intremap= [X86-64, Intel-IOMMU]
2275 on enable Interr 2059 on enable Interrupt Remapping (default)
2276 off disable Inter 2060 off disable Interrupt Remapping
2277 nosid disable Sourc 2061 nosid disable Source ID checking
2278 no_x2apic_optout 2062 no_x2apic_optout
2279 BIOS x2APIC o 2063 BIOS x2APIC opt-out request will be ignored
2280 nopost disable Inter 2064 nopost disable Interrupt Posting
2281 posted_msi <<
2282 enable MSIs d <<
2283 2065
2284 iomem= Disable strict checki 2066 iomem= Disable strict checking of access to MMIO memory
2285 strict regions from userspac 2067 strict regions from userspace.
2286 relaxed 2068 relaxed
2287 2069
2288 iommu= [X86,EARLY] !! 2070 iommu= [X86]
2289 off 2071 off
2290 force 2072 force
2291 noforce 2073 noforce
2292 biomerge 2074 biomerge
2293 panic 2075 panic
2294 nopanic 2076 nopanic
2295 merge 2077 merge
2296 nomerge 2078 nomerge
2297 soft 2079 soft
2298 pt [X86] 2080 pt [X86]
2299 nopt [X86] 2081 nopt [X86]
2300 nobypass [PPC/POWERNV] 2082 nobypass [PPC/POWERNV]
2301 Disable IOMMU bypass, 2083 Disable IOMMU bypass, using IOMMU for PCI devices.
2302 2084
2303 iommu.forcedac= [ARM64,X86,EARLY] Con !! 2085 iommu.forcedac= [ARM64, X86] Control IOVA allocation for PCI devices.
2304 Format: { "0" | "1" } 2086 Format: { "0" | "1" }
2305 0 - Try to allocate a 2087 0 - Try to allocate a 32-bit DMA address first, before
2306 falling back to the 2088 falling back to the full range if needed.
2307 1 - Allocate directly 2089 1 - Allocate directly from the full usable range,
2308 forcing Dual Addres 2090 forcing Dual Address Cycle for PCI cards supporting
2309 greater than 32-bit 2091 greater than 32-bit addressing.
2310 2092
2311 iommu.strict= [ARM64,X86,S390,EARLY !! 2093 iommu.strict= [ARM64, X86] Configure TLB invalidation behaviour
2312 Format: { "0" | "1" } 2094 Format: { "0" | "1" }
2313 0 - Lazy mode. 2095 0 - Lazy mode.
2314 Request that DMA un 2096 Request that DMA unmap operations use deferred
2315 invalidation of har 2097 invalidation of hardware TLBs, for increased
2316 throughput at the c 2098 throughput at the cost of reduced device isolation.
2317 Will fall back to s 2099 Will fall back to strict mode if not supported by
2318 the relevant IOMMU 2100 the relevant IOMMU driver.
2319 1 - Strict mode. 2101 1 - Strict mode.
2320 DMA unmap operation 2102 DMA unmap operations invalidate IOMMU hardware TLBs
2321 synchronously. 2103 synchronously.
2322 unset - Use value of 2104 unset - Use value of CONFIG_IOMMU_DEFAULT_DMA_{LAZY,STRICT}.
2323 Note: on x86, strict 2105 Note: on x86, strict mode specified via one of the
2324 legacy driver-specifi 2106 legacy driver-specific options takes precedence.
2325 2107
2326 iommu.passthrough= 2108 iommu.passthrough=
2327 [ARM64,X86,EARLY] Con !! 2109 [ARM64, X86] Configure DMA to bypass the IOMMU by default.
2328 Format: { "0" | "1" } 2110 Format: { "0" | "1" }
2329 0 - Use IOMMU transla 2111 0 - Use IOMMU translation for DMA.
2330 1 - Bypass the IOMMU 2112 1 - Bypass the IOMMU for DMA.
2331 unset - Use value of 2113 unset - Use value of CONFIG_IOMMU_DEFAULT_PASSTHROUGH.
2332 2114
2333 io7= [HW] IO7 for Marvel-b 2115 io7= [HW] IO7 for Marvel-based Alpha systems
2334 See comment before ma 2116 See comment before marvel_specify_io7 in
2335 arch/alpha/kernel/cor 2117 arch/alpha/kernel/core_marvel.c.
2336 2118
2337 io_delay= [X86,EARLY] I/O delay !! 2119 io_delay= [X86] I/O delay method
2338 0x80 2120 0x80
2339 Standard port 0x80 ba 2121 Standard port 0x80 based delay
2340 0xed 2122 0xed
2341 Alternate port 0xed b 2123 Alternate port 0xed based delay (needed on some systems)
2342 udelay 2124 udelay
2343 Simple two microsecon 2125 Simple two microseconds delay
2344 none 2126 none
2345 No delay 2127 No delay
2346 2128
2347 ip= [IP_PNP] 2129 ip= [IP_PNP]
2348 See Documentation/adm 2130 See Documentation/admin-guide/nfs/nfsroot.rst.
2349 2131
2350 ipcmni_extend [KNL,EARLY] Extend th !! 2132 ipcmni_extend [KNL] Extend the maximum number of unique System V
2351 IPC identifiers from 2133 IPC identifiers from 32,768 to 16,777,216.
2352 2134
2353 irqaffinity= [SMP] Set the default 2135 irqaffinity= [SMP] Set the default irq affinity mask
2354 The argument is a cpu 2136 The argument is a cpu list, as described above.
2355 2137
2356 irqchip.gicv2_force_probe= 2138 irqchip.gicv2_force_probe=
2357 [ARM,ARM64,EARLY] !! 2139 [ARM, ARM64]
2358 Format: <bool> 2140 Format: <bool>
2359 Force the kernel to l 2141 Force the kernel to look for the second 4kB page
2360 of a GICv2 controller 2142 of a GICv2 controller even if the memory range
2361 exposed by the device 2143 exposed by the device tree is too small.
2362 2144
2363 irqchip.gicv3_nolpi= 2145 irqchip.gicv3_nolpi=
2364 [ARM,ARM64,EARLY] !! 2146 [ARM, ARM64]
2365 Force the kernel to i 2147 Force the kernel to ignore the availability of
2366 LPIs (and by conseque 2148 LPIs (and by consequence ITSs). Intended for system
2367 that use the kernel a 2149 that use the kernel as a bootloader, and thus want
2368 to let secondary kern 2150 to let secondary kernels in charge of setting up
2369 LPIs. 2151 LPIs.
2370 2152
2371 irqchip.gicv3_pseudo_nmi= [ARM64,EARL !! 2153 irqchip.gicv3_pseudo_nmi= [ARM64]
2372 Enables support for p 2154 Enables support for pseudo-NMIs in the kernel. This
2373 requires the kernel t 2155 requires the kernel to be built with
2374 CONFIG_ARM64_PSEUDO_N 2156 CONFIG_ARM64_PSEUDO_NMI.
2375 2157
2376 irqfixup [HW] 2158 irqfixup [HW]
2377 When an interrupt is 2159 When an interrupt is not handled search all handlers
2378 for it. Intended to g 2160 for it. Intended to get systems with badly broken
2379 firmware running. 2161 firmware running.
2380 2162
2381 irqpoll [HW] 2163 irqpoll [HW]
2382 When an interrupt is 2164 When an interrupt is not handled search all handlers
2383 for it. Also check al 2165 for it. Also check all handlers each timer
2384 interrupt. Intended t 2166 interrupt. Intended to get systems with badly broken
2385 firmware running. 2167 firmware running.
2386 2168
2387 isapnp= [ISAPNP] 2169 isapnp= [ISAPNP]
2388 Format: <RDP>,<reset> 2170 Format: <RDP>,<reset>,<pci_scan>,<verbosity>
2389 2171
2390 isolcpus= [KNL,SMP,ISOL] Isolat 2172 isolcpus= [KNL,SMP,ISOL] Isolate a given set of CPUs from disturbance.
2391 [Deprecated - use cpu 2173 [Deprecated - use cpusets instead]
2392 Format: [flag-list,]< 2174 Format: [flag-list,]<cpu-list>
2393 2175
2394 Specify one or more C 2176 Specify one or more CPUs to isolate from disturbances
2395 specified in the flag 2177 specified in the flag list (default: domain):
2396 2178
2397 nohz 2179 nohz
2398 Disable the tick wh 2180 Disable the tick when a single task runs.
2399 2181
2400 A residual 1Hz tick 2182 A residual 1Hz tick is offloaded to workqueues, which you
2401 need to affine to h 2183 need to affine to housekeeping through the global
2402 workqueue's affinit 2184 workqueue's affinity configured via the
2403 /sys/devices/virtua 2185 /sys/devices/virtual/workqueue/cpumask sysfs file, or
2404 by using the 'domai 2186 by using the 'domain' flag described below.
2405 2187
2406 NOTE: by default th 2188 NOTE: by default the global workqueue runs on all CPUs,
2407 so to protect indiv 2189 so to protect individual CPUs the 'cpumask' file has to
2408 be configured manua 2190 be configured manually after bootup.
2409 2191
2410 domain 2192 domain
2411 Isolate from the ge 2193 Isolate from the general SMP balancing and scheduling
2412 algorithms. Note th 2194 algorithms. Note that performing domain isolation this way
2413 is irreversible: it 2195 is irreversible: it's not possible to bring back a CPU to
2414 the domains once is 2196 the domains once isolated through isolcpus. It's strongly
2415 advised to use cpus 2197 advised to use cpusets instead to disable scheduler load
2416 balancing through t 2198 balancing through the "cpuset.sched_load_balance" file.
2417 It offers a much mo 2199 It offers a much more flexible interface where CPUs can
2418 move in and out of 2200 move in and out of an isolated set anytime.
2419 2201
2420 You can move a proc 2202 You can move a process onto or off an "isolated" CPU via
2421 the CPU affinity sy 2203 the CPU affinity syscalls or cpuset.
2422 <cpu number> begins 2204 <cpu number> begins at 0 and the maximum value is
2423 "number of CPUs in 2205 "number of CPUs in system - 1".
2424 2206
2425 managed_irq 2207 managed_irq
2426 2208
2427 Isolate from being 2209 Isolate from being targeted by managed interrupts
2428 which have an inter 2210 which have an interrupt mask containing isolated
2429 CPUs. The affinity 2211 CPUs. The affinity of managed interrupts is
2430 handled by the kern 2212 handled by the kernel and cannot be changed via
2431 the /proc/irq/* int 2213 the /proc/irq/* interfaces.
2432 2214
2433 This isolation is b 2215 This isolation is best effort and only effective
2434 if the automaticall 2216 if the automatically assigned interrupt mask of a
2435 device queue contai 2217 device queue contains isolated and housekeeping
2436 CPUs. If housekeepi 2218 CPUs. If housekeeping CPUs are online then such
2437 interrupts are dire 2219 interrupts are directed to the housekeeping CPU
2438 so that IO submitte 2220 so that IO submitted on the housekeeping CPU
2439 cannot disturb the 2221 cannot disturb the isolated CPU.
2440 2222
2441 If a queue's affini 2223 If a queue's affinity mask contains only isolated
2442 CPUs then this para 2224 CPUs then this parameter has no effect on the
2443 interrupt routing d 2225 interrupt routing decision, though interrupts are
2444 only delivered when 2226 only delivered when tasks running on those
2445 isolated CPUs submi 2227 isolated CPUs submit IO. IO submitted on
2446 housekeeping CPUs h 2228 housekeeping CPUs has no influence on those
2447 queues. 2229 queues.
2448 2230
2449 The format of <cpu-li 2231 The format of <cpu-list> is described above.
2450 2232
2451 iucv= [HW,NET] 2233 iucv= [HW,NET]
2452 2234
2453 ivrs_ioapic [HW,X86-64] 2235 ivrs_ioapic [HW,X86-64]
2454 Provide an override t 2236 Provide an override to the IOAPIC-ID<->DEVICE-ID
2455 mapping provided in t 2237 mapping provided in the IVRS ACPI table.
2456 By default, PCI segme 2238 By default, PCI segment is 0, and can be omitted.
2457 2239
2458 For example, to map I 2240 For example, to map IOAPIC-ID decimal 10 to
2459 PCI segment 0x1 and P 2241 PCI segment 0x1 and PCI device 00:14.0,
2460 write the parameter a 2242 write the parameter as:
2461 ivrs_ioapic=1 2243 ivrs_ioapic=10@0001:00:14.0
2462 2244
2463 Deprecated formats: 2245 Deprecated formats:
2464 * To map IOAPIC-ID de 2246 * To map IOAPIC-ID decimal 10 to PCI device 00:14.0
2465 write the parameter 2247 write the parameter as:
2466 ivrs_ioapic[1 2248 ivrs_ioapic[10]=00:14.0
2467 * To map IOAPIC-ID de 2249 * To map IOAPIC-ID decimal 10 to PCI segment 0x1 and
2468 PCI device 00:14.0 2250 PCI device 00:14.0 write the parameter as:
2469 ivrs_ioapic[1 2251 ivrs_ioapic[10]=0001:00:14.0
2470 2252
2471 ivrs_hpet [HW,X86-64] 2253 ivrs_hpet [HW,X86-64]
2472 Provide an override t 2254 Provide an override to the HPET-ID<->DEVICE-ID
2473 mapping provided in t 2255 mapping provided in the IVRS ACPI table.
2474 By default, PCI segme 2256 By default, PCI segment is 0, and can be omitted.
2475 2257
2476 For example, to map H 2258 For example, to map HPET-ID decimal 10 to
2477 PCI segment 0x1 and P 2259 PCI segment 0x1 and PCI device 00:14.0,
2478 write the parameter a 2260 write the parameter as:
2479 ivrs_hpet=10@ 2261 ivrs_hpet=10@0001:00:14.0
2480 2262
2481 Deprecated formats: 2263 Deprecated formats:
2482 * To map HPET-ID deci 2264 * To map HPET-ID decimal 0 to PCI device 00:14.0
2483 write the parameter 2265 write the parameter as:
2484 ivrs_hpet[0]= 2266 ivrs_hpet[0]=00:14.0
2485 * To map HPET-ID deci 2267 * To map HPET-ID decimal 10 to PCI segment 0x1 and
2486 PCI device 00:14.0 2268 PCI device 00:14.0 write the parameter as:
2487 ivrs_ioapic[1 2269 ivrs_ioapic[10]=0001:00:14.0
2488 2270
2489 ivrs_acpihid [HW,X86-64] 2271 ivrs_acpihid [HW,X86-64]
2490 Provide an override t 2272 Provide an override to the ACPI-HID:UID<->DEVICE-ID
2491 mapping provided in t 2273 mapping provided in the IVRS ACPI table.
2492 By default, PCI segme 2274 By default, PCI segment is 0, and can be omitted.
2493 2275
2494 For example, to map U 2276 For example, to map UART-HID:UID AMD0020:0 to
2495 PCI segment 0x1 and P 2277 PCI segment 0x1 and PCI device ID 00:14.5,
2496 write the parameter a 2278 write the parameter as:
2497 ivrs_acpihid= 2279 ivrs_acpihid=AMD0020:0@0001:00:14.5
2498 2280
2499 Deprecated formats: 2281 Deprecated formats:
2500 * To map UART-HID:UID 2282 * To map UART-HID:UID AMD0020:0 to PCI segment is 0,
2501 PCI device ID 00:14 2283 PCI device ID 00:14.5, write the parameter as:
2502 ivrs_acpihid[ 2284 ivrs_acpihid[00:14.5]=AMD0020:0
2503 * To map UART-HID:UID 2285 * To map UART-HID:UID AMD0020:0 to PCI segment 0x1 and
2504 PCI device ID 00:14 2286 PCI device ID 00:14.5, write the parameter as:
2505 ivrs_acpihid[ 2287 ivrs_acpihid[0001:00:14.5]=AMD0020:0
2506 2288
2507 js= [HW,JOY] Analog joyst 2289 js= [HW,JOY] Analog joystick
2508 See Documentation/inp 2290 See Documentation/input/joydev/joystick.rst.
2509 2291
>> 2292 nokaslr [KNL]
>> 2293 When CONFIG_RANDOMIZE_BASE is set, this disables
>> 2294 kernel and module base offset ASLR (Address Space
>> 2295 Layout Randomization).
>> 2296
2510 kasan_multi_shot 2297 kasan_multi_shot
2511 [KNL] Enforce KASAN ( 2298 [KNL] Enforce KASAN (Kernel Address Sanitizer) to print
2512 report on every inval 2299 report on every invalid memory access. Without this
2513 parameter KASAN will 2300 parameter KASAN will print report only for the first
2514 invalid access. 2301 invalid access.
2515 2302
2516 keep_bootcon [KNL,EARLY] !! 2303 keepinitrd [HW,ARM]
2517 Do not unregister boo <<
2518 useful for debugging <<
2519 between unregistering <<
2520 the real console. <<
2521 2304
2522 keepinitrd [HW,ARM] See retain_i !! 2305 kernelcore= [KNL,X86,IA-64,PPC]
2523 <<
2524 kernelcore= [KNL,X86,PPC,EARLY] <<
2525 Format: nn[KMGTPE] | 2306 Format: nn[KMGTPE] | nn% | "mirror"
2526 This parameter specif 2307 This parameter specifies the amount of memory usable by
2527 the kernel for non-mo 2308 the kernel for non-movable allocations. The requested
2528 amount is spread even 2309 amount is spread evenly throughout all nodes in the
2529 system as ZONE_NORMAL 2310 system as ZONE_NORMAL. The remaining memory is used for
2530 movable memory in its 2311 movable memory in its own zone, ZONE_MOVABLE. In the
2531 event, a node is too 2312 event, a node is too small to have both ZONE_NORMAL and
2532 ZONE_MOVABLE, kernelc 2313 ZONE_MOVABLE, kernelcore memory will take priority and
2533 other nodes will have 2314 other nodes will have a larger ZONE_MOVABLE.
2534 2315
2535 ZONE_MOVABLE is used 2316 ZONE_MOVABLE is used for the allocation of pages that
2536 may be reclaimed or m 2317 may be reclaimed or moved by the page migration
2537 subsystem. Note that 2318 subsystem. Note that allocations like PTEs-from-HighMem
2538 still use the HighMem 2319 still use the HighMem zone if it exists, and the Normal
2539 zone if it does not. 2320 zone if it does not.
2540 2321
2541 It is possible to spe 2322 It is possible to specify the exact amount of memory in
2542 the form of "nn[KMGTP 2323 the form of "nn[KMGTPE]", a percentage of total system
2543 memory in the form of 2324 memory in the form of "nn%", or "mirror". If "mirror"
2544 option is specified, 2325 option is specified, mirrored (reliable) memory is used
2545 for non-movable alloc 2326 for non-movable allocations and remaining memory is used
2546 for Movable pages. " 2327 for Movable pages. "nn[KMGTPE]", "nn%", and "mirror"
2547 are exclusive, so you 2328 are exclusive, so you cannot specify multiple forms.
2548 2329
2549 kgdbdbgp= [KGDB,HW,EARLY] kgdb !! 2330 kgdbdbgp= [KGDB,HW] kgdb over EHCI usb debug port.
2550 Format: <Controller#> 2331 Format: <Controller#>[,poll interval]
2551 The controller # is t 2332 The controller # is the number of the ehci usb debug
2552 port as it is probed 2333 port as it is probed via PCI. The poll interval is
2553 optional and is the n 2334 optional and is the number seconds in between
2554 each poll cycle to th 2335 each poll cycle to the debug port in case you need
2555 the functionality for 2336 the functionality for interrupting the kernel with
2556 gdb or control-c on t 2337 gdb or control-c on the dbgp connection. When
2557 not using this parame 2338 not using this parameter you use sysrq-g to break into
2558 the kernel debugger. 2339 the kernel debugger.
2559 2340
2560 kgdboc= [KGDB,HW] kgdb over c 2341 kgdboc= [KGDB,HW] kgdb over consoles.
2561 Requires a tty driver 2342 Requires a tty driver that supports console polling,
2562 or a supported pollin 2343 or a supported polling keyboard driver (non-usb).
2563 Serial only format: 2344 Serial only format: <serial_device>[,baud]
2564 keyboard only format 2345 keyboard only format: kbd
2565 keyboard and serial 2346 keyboard and serial format: kbd,<serial_device>[,baud]
2566 Optional Kernel mode 2347 Optional Kernel mode setting:
2567 kms, kbd format: kms 2348 kms, kbd format: kms,kbd
2568 kms, kbd and serial 2349 kms, kbd and serial format: kms,kbd,<ser_dev>[,baud]
2569 2350
2570 kgdboc_earlycon= [KGDB,HW,EARL !! 2351 kgdboc_earlycon= [KGDB,HW]
2571 If the boot console p 2352 If the boot console provides the ability to read
2572 characters and can wo 2353 characters and can work in polling mode, you can use
2573 this parameter to tel 2354 this parameter to tell kgdb to use it as a backend
2574 until the normal cons 2355 until the normal console is registered. Intended to
2575 be used together with 2356 be used together with the kgdboc parameter which
2576 specifies the normal 2357 specifies the normal console to transition to.
2577 2358
2578 The name of the early 2359 The name of the early console should be specified
2579 as the value of this 2360 as the value of this parameter. Note that the name of
2580 the early console mig 2361 the early console might be different than the tty
2581 name passed to kgdboc 2362 name passed to kgdboc. It's OK to leave the value
2582 blank and the first b 2363 blank and the first boot console that implements
2583 read() will be picked 2364 read() will be picked.
2584 2365
2585 kgdbwait [KGDB,EARLY] Stop ker !! 2366 kgdbwait [KGDB] Stop kernel execution and enter the
2586 kernel debugger at th 2367 kernel debugger at the earliest opportunity.
2587 2368
2588 kmac= [MIPS] Korina etherne 2369 kmac= [MIPS] Korina ethernet MAC address.
2589 Configure the RouterB 2370 Configure the RouterBoard 532 series on-chip
2590 Ethernet adapter MAC 2371 Ethernet adapter MAC address.
2591 2372
2592 kmemleak= [KNL,EARLY] Boot-time !! 2373 kmemleak= [KNL] Boot-time kmemleak enable/disable
2593 Valid arguments: on, 2374 Valid arguments: on, off
2594 Default: on 2375 Default: on
2595 Built with CONFIG_DEB 2376 Built with CONFIG_DEBUG_KMEMLEAK_DEFAULT_OFF=y,
2596 the default is off. 2377 the default is off.
2597 2378
2598 kprobe_event=[probe-list] 2379 kprobe_event=[probe-list]
2599 [FTRACE] Add kprobe e 2380 [FTRACE] Add kprobe events and enable at boot time.
2600 The probe-list is a s 2381 The probe-list is a semicolon delimited list of probe
2601 definitions. Each def 2382 definitions. Each definition is same as kprobe_events
2602 interface, but the pa 2383 interface, but the parameters are comma delimited.
2603 For example, to add a 2384 For example, to add a kprobe event on vfs_read with
2604 arg1 and arg2, add to 2385 arg1 and arg2, add to the command line;
2605 2386
2606 kprobe_event=p, 2387 kprobe_event=p,vfs_read,$arg1,$arg2
2607 2388
2608 See also Documentatio 2389 See also Documentation/trace/kprobetrace.rst "Kernel
2609 Boot Parameter" secti 2390 Boot Parameter" section.
2610 2391
2611 kpti= [ARM64,EARLY] Control !! 2392 kpti= [ARM64] Control page table isolation of user
2612 user and kernel addre !! 2393 and kernel address spaces.
2613 Default: enabled on c 2394 Default: enabled on cores which need mitigation.
2614 0: force disabled 2395 0: force disabled
2615 1: force enabled 2396 1: force enabled
2616 2397
2617 kunit.enable= [KUNIT] Enable execut <<
2618 CONFIG_KUNIT to be se <<
2619 default value can be <<
2620 KUNIT_DEFAULT_ENABLED <<
2621 Default is 1 (enabled <<
2622 <<
2623 kvm.ignore_msrs=[KVM] Ignore guest ac 2398 kvm.ignore_msrs=[KVM] Ignore guest accesses to unhandled MSRs.
2624 Default is 0 (don't i 2399 Default is 0 (don't ignore, but inject #GP)
2625 2400
2626 kvm.eager_page_split= <<
2627 [KVM,X86] Controls wh <<
2628 proactively split all <<
2629 Eager page splitting <<
2630 execution by eliminat <<
2631 and MMU lock contenti <<
2632 required to split hug <<
2633 <<
2634 VM workloads that rar <<
2635 only to a small regio <<
2636 disabling eager page <<
2637 still be used for rea <<
2638 <<
2639 The behavior of eager <<
2640 KVM_DIRTY_LOG_INITIAL <<
2641 disabled, all huge pa <<
2642 split when dirty logg <<
2643 enabled, eager page s <<
2644 the KVM_CLEAR_DIRTY i <<
2645 cleared. <<
2646 <<
2647 Eager page splitting <<
2648 <<
2649 Default is Y (on). <<
2650 <<
2651 kvm.enable_vmware_backdoor=[KVM] Supp 2401 kvm.enable_vmware_backdoor=[KVM] Support VMware backdoor PV interface.
2652 Default is 2402 Default is false (don't support).
2653 2403
>> 2404 kvm.mmu_audit= [KVM] This is a R/W parameter which allows audit
>> 2405 KVM MMU at runtime.
>> 2406 Default is 0 (off)
>> 2407
2654 kvm.nx_huge_pages= 2408 kvm.nx_huge_pages=
2655 [KVM] Controls the so 2409 [KVM] Controls the software workaround for the
2656 X86_BUG_ITLB_MULTIHIT 2410 X86_BUG_ITLB_MULTIHIT bug.
2657 force : Always depl 2411 force : Always deploy workaround.
2658 off : Never deplo 2412 off : Never deploy workaround.
2659 auto : Deploy work 2413 auto : Deploy workaround based on the presence of
2660 X86_BUG_ITL 2414 X86_BUG_ITLB_MULTIHIT.
2661 2415
2662 Default is 'auto'. 2416 Default is 'auto'.
2663 2417
2664 If the software worka 2418 If the software workaround is enabled for the host,
2665 guests do need not to 2419 guests do need not to enable it for nested guests.
2666 2420
2667 kvm.nx_huge_pages_recovery_ratio= 2421 kvm.nx_huge_pages_recovery_ratio=
2668 [KVM] Controls how ma 2422 [KVM] Controls how many 4KiB pages are periodically zapped
2669 back to huge pages. 2423 back to huge pages. 0 disables the recovery, otherwise if
2670 the value is N KVM wi 2424 the value is N KVM will zap 1/Nth of the 4KiB pages every
2671 period (see below). !! 2425 minute. The default is 60.
2672 2426
2673 kvm.nx_huge_pages_recovery_period_ms= !! 2427 kvm-amd.nested= [KVM,AMD] Allow nested virtualization in KVM/SVM.
2674 [KVM] Controls the ti !! 2428 Default is 1 (enabled)
2675 back to huge pages. I <<
2676 zap a portion (see ra <<
2677 If the value is 0 (th <<
2678 on the ratio, such th <<
2679 <<
2680 kvm-amd.nested= [KVM,AMD] Control nes <<
2681 KVM/SVM. Default is 1 <<
2682 <<
2683 kvm-amd.npt= [KVM,AMD] Control KVM <<
2684 a.k.a. Two-Dimensiona <<
2685 (enabled). Disable by <<
2686 for NPT. <<
2687 2429
2688 kvm-arm.mode= !! 2430 kvm-amd.npt= [KVM,AMD] Disable nested paging (virtualized MMU)
2689 [KVM,ARM,EARLY] Selec !! 2431 for all guests.
2690 operation. !! 2432 Default is 1 (enabled) if in 64-bit or 32-bit PAE mode.
2691 2433
2692 none: Forcefully disa !! 2434 kvm-arm.mode=
>> 2435 [KVM,ARM] Select one of KVM/arm64's modes of operation.
2693 2436
2694 nvhe: Standard nVHE-b 2437 nvhe: Standard nVHE-based mode, without support for
2695 protected guest 2438 protected guests.
2696 2439
2697 protected: nVHE-based 2440 protected: nVHE-based mode with support for guests whose
2698 state is k 2441 state is kept private from the host.
>> 2442 Not valid if the kernel is running in EL2.
2699 2443
2700 nested: VHE-based mod !! 2444 Defaults to VHE/nVHE based on hardware support.
2701 virtualizatio <<
2702 hardware. <<
2703 <<
2704 Defaults to VHE/nVHE <<
2705 mode to "protected" w <<
2706 for the host. "nested <<
2707 used with extreme cau <<
2708 2445
2709 kvm-arm.vgic_v3_group0_trap= 2446 kvm-arm.vgic_v3_group0_trap=
2710 [KVM,ARM,EARLY] Trap !! 2447 [KVM,ARM] Trap guest accesses to GICv3 group-0
2711 system registers 2448 system registers
2712 2449
2713 kvm-arm.vgic_v3_group1_trap= 2450 kvm-arm.vgic_v3_group1_trap=
2714 [KVM,ARM,EARLY] Trap !! 2451 [KVM,ARM] Trap guest accesses to GICv3 group-1
2715 system registers 2452 system registers
2716 2453
2717 kvm-arm.vgic_v3_common_trap= 2454 kvm-arm.vgic_v3_common_trap=
2718 [KVM,ARM,EARLY] Trap !! 2455 [KVM,ARM] Trap guest accesses to GICv3 common
2719 system registers 2456 system registers
2720 2457
2721 kvm-arm.vgic_v4_enable= 2458 kvm-arm.vgic_v4_enable=
2722 [KVM,ARM,EARLY] Allow !! 2459 [KVM,ARM] Allow use of GICv4 for direct injection of
2723 injection of LPIs. !! 2460 LPIs.
2724 <<
2725 kvm-arm.wfe_trap_policy= <<
2726 [KVM,ARM] Control whe <<
2727 KVM VMs. Traps are al <<
2728 CPU architecture. <<
2729 <<
2730 trap: set WFE instruc <<
2731 <<
2732 notrap: clear WFE ins <<
2733 <<
2734 kvm-arm.wfi_trap_policy= <<
2735 [KVM,ARM] Control whe <<
2736 KVM VMs. Traps are al <<
2737 CPU architecture. <<
2738 <<
2739 trap: set WFI instruc <<
2740 <<
2741 notrap: clear WFI ins <<
2742 2461
2743 kvm_cma_resv_ratio=n [PPC,EARLY] !! 2462 kvm_cma_resv_ratio=n [PPC]
2744 Reserves given percen 2463 Reserves given percentage from system memory area for
2745 contiguous memory all 2464 contiguous memory allocation for KVM hash pagetable
2746 allocation. 2465 allocation.
2747 By default it reserve 2466 By default it reserves 5% of total system memory.
2748 Format: <integer> 2467 Format: <integer>
2749 Default: 5 2468 Default: 5
2750 2469
2751 kvm-intel.ept= [KVM,Intel] Control K !! 2470 kvm-intel.ept= [KVM,Intel] Disable extended page tables
2752 a.k.a. Two-Dimensiona !! 2471 (virtualized MMU) support on capable Intel chips.
2753 (enabled). Disable by !! 2472 Default is 1 (enabled)
2754 for EPT. <<
2755 2473
2756 kvm-intel.emulate_invalid_guest_state 2474 kvm-intel.emulate_invalid_guest_state=
2757 [KVM,Intel] Control w !! 2475 [KVM,Intel] Disable emulation of invalid guest state.
2758 state. Ignored if kvm !! 2476 Ignored if kvm-intel.enable_unrestricted_guest=1, as
2759 as guest state is nev !! 2477 guest state is never invalid for unrestricted guests.
2760 guests. This param do !! 2478 This param doesn't apply to nested guests (L2), as KVM
2761 as KVM never emulates !! 2479 never emulates invalid L2 guest state.
2762 Default is 1 (enabled !! 2480 Default is 1 (enabled)
2763 2481
2764 kvm-intel.flexpriority= 2482 kvm-intel.flexpriority=
2765 [KVM,Intel] Control K !! 2483 [KVM,Intel] Disable FlexPriority feature (TPR shadow).
2766 (TPR shadow). Default !! 2484 Default is 1 (enabled)
2767 hardware lacks suppor <<
2768 2485
2769 kvm-intel.nested= 2486 kvm-intel.nested=
2770 [KVM,Intel] Control n !! 2487 [KVM,Intel] Enable VMX nesting (nVMX).
2771 KVM/VMX. Default is 1 !! 2488 Default is 0 (disabled)
2772 2489
2773 kvm-intel.unrestricted_guest= 2490 kvm-intel.unrestricted_guest=
2774 [KVM,Intel] Control K !! 2491 [KVM,Intel] Disable unrestricted guest feature
2775 feature (virtualized !! 2492 (virtualized real and unpaged mode) on capable
2776 is 1 (enabled). Disab !! 2493 Intel chips. Default is 1 (enabled)
2777 hardware lacks suppor <<
2778 2494
2779 kvm-intel.vmentry_l1d_flush=[KVM,Inte 2495 kvm-intel.vmentry_l1d_flush=[KVM,Intel] Mitigation for L1 Terminal Fault
2780 CVE-2018-3620. 2496 CVE-2018-3620.
2781 2497
2782 Valid arguments: neve 2498 Valid arguments: never, cond, always
2783 2499
2784 always: L1D cache flu 2500 always: L1D cache flush on every VMENTER.
2785 cond: Flush L1D on 2501 cond: Flush L1D on VMENTER only when the code between
2786 VMEXIT and VM 2502 VMEXIT and VMENTER can leak host memory.
2787 never: Disables the 2503 never: Disables the mitigation
2788 2504
2789 Default is cond (do L 2505 Default is cond (do L1 cache flush in specific instances)
2790 2506
2791 kvm-intel.vpid= [KVM,Intel] Control K !! 2507 kvm-intel.vpid= [KVM,Intel] Disable Virtual Processor Identification
2792 Identification featur !! 2508 feature (tagged TLBs) on capable Intel chips.
2793 (enabled). Disable by !! 2509 Default is 1 (enabled)
2794 for it. <<
2795 2510
2796 l1d_flush= [X86,INTEL,EARLY] !! 2511 l1d_flush= [X86,INTEL]
2797 Control mitigation fo 2512 Control mitigation for L1D based snooping vulnerability.
2798 2513
2799 Certain CPUs are vuln 2514 Certain CPUs are vulnerable to an exploit against CPU
2800 internal buffers whic 2515 internal buffers which can forward information to a
2801 disclosure gadget und 2516 disclosure gadget under certain conditions.
2802 2517
2803 In vulnerable process 2518 In vulnerable processors, the speculatively
2804 forwarded data can be 2519 forwarded data can be used in a cache side channel
2805 attack, to access dat 2520 attack, to access data to which the attacker does
2806 not have direct acces 2521 not have direct access.
2807 2522
2808 This parameter contro 2523 This parameter controls the mitigation. The
2809 options are: 2524 options are:
2810 2525
2811 on - enable t 2526 on - enable the interface for the mitigation
2812 2527
2813 l1tf= [X86,EARLY] Control m !! 2528 l1tf= [X86] Control mitigation of the L1TF vulnerability on
2814 affected CPUs 2529 affected CPUs
2815 2530
2816 The kernel PTE invers 2531 The kernel PTE inversion protection is unconditionally
2817 enabled and cannot be 2532 enabled and cannot be disabled.
2818 2533
2819 full 2534 full
2820 Provides all 2535 Provides all available mitigations for the
2821 L1TF vulnerab 2536 L1TF vulnerability. Disables SMT and
2822 enables all m 2537 enables all mitigations in the
2823 hypervisors, 2538 hypervisors, i.e. unconditional L1D flush.
2824 2539
2825 SMT control a 2540 SMT control and L1D flush control via the
2826 sysfs interfa 2541 sysfs interface is still possible after
2827 boot. Hyperv 2542 boot. Hypervisors will issue a warning
2828 when the firs 2543 when the first VM is started in a
2829 potentially i 2544 potentially insecure configuration,
2830 i.e. SMT enab 2545 i.e. SMT enabled or L1D flush disabled.
2831 2546
2832 full,force 2547 full,force
2833 Same as 'full 2548 Same as 'full', but disables SMT and L1D
2834 flush runtime 2549 flush runtime control. Implies the
2835 'nosmt=force' 2550 'nosmt=force' command line option.
2836 (i.e. sysfs c 2551 (i.e. sysfs control of SMT is disabled.)
2837 2552
2838 flush 2553 flush
2839 Leaves SMT en 2554 Leaves SMT enabled and enables the default
2840 hypervisor mi 2555 hypervisor mitigation, i.e. conditional
2841 L1D flush. 2556 L1D flush.
2842 2557
2843 SMT control a 2558 SMT control and L1D flush control via the
2844 sysfs interfa 2559 sysfs interface is still possible after
2845 boot. Hyperv 2560 boot. Hypervisors will issue a warning
2846 when the firs 2561 when the first VM is started in a
2847 potentially i 2562 potentially insecure configuration,
2848 i.e. SMT enab 2563 i.e. SMT enabled or L1D flush disabled.
2849 2564
2850 flush,nosmt 2565 flush,nosmt
2851 2566
2852 Disables SMT 2567 Disables SMT and enables the default
2853 hypervisor mi 2568 hypervisor mitigation.
2854 2569
2855 SMT control a 2570 SMT control and L1D flush control via the
2856 sysfs interfa 2571 sysfs interface is still possible after
2857 boot. Hyperv 2572 boot. Hypervisors will issue a warning
2858 when the firs 2573 when the first VM is started in a
2859 potentially i 2574 potentially insecure configuration,
2860 i.e. SMT enab 2575 i.e. SMT enabled or L1D flush disabled.
2861 2576
2862 flush,nowarn 2577 flush,nowarn
2863 Same as 'flus 2578 Same as 'flush', but hypervisors will not
2864 warn when a V 2579 warn when a VM is started in a potentially
2865 insecure conf 2580 insecure configuration.
2866 2581
2867 off 2582 off
2868 Disables hype 2583 Disables hypervisor mitigations and doesn't
2869 emit any warn 2584 emit any warnings.
2870 It also drops 2585 It also drops the swap size and available
2871 RAM limit res 2586 RAM limit restriction on both hypervisor and
2872 bare metal. 2587 bare metal.
2873 2588
2874 Default is 'flush'. 2589 Default is 'flush'.
2875 2590
2876 For details see: Docu 2591 For details see: Documentation/admin-guide/hw-vuln/l1tf.rst
2877 2592
2878 l2cr= [PPC] 2593 l2cr= [PPC]
2879 2594
2880 l3cr= [PPC] 2595 l3cr= [PPC]
2881 2596
2882 lapic [X86-32,APIC,EARLY] E !! 2597 lapic [X86-32,APIC] Enable the local APIC even if BIOS
2883 disabled it. 2598 disabled it.
2884 2599
2885 lapic= [X86,APIC] Do not use 2600 lapic= [X86,APIC] Do not use TSC deadline
2886 value for LAPIC timer 2601 value for LAPIC timer one-shot implementation. Default
2887 back to the programma 2602 back to the programmable timer unit in the LAPIC.
2888 Format: notscdeadline 2603 Format: notscdeadline
2889 2604
2890 lapic_timer_c2_ok [X86,APIC,EAR !! 2605 lapic_timer_c2_ok [X86,APIC] trust the local apic timer
2891 in C2 power state. 2606 in C2 power state.
2892 2607
2893 libata.dma= [LIBATA] DMA control 2608 libata.dma= [LIBATA] DMA control
2894 libata.dma=0 Dis 2609 libata.dma=0 Disable all PATA and SATA DMA
2895 libata.dma=1 PAT 2610 libata.dma=1 PATA and SATA Disk DMA only
2896 libata.dma=2 ATA 2611 libata.dma=2 ATAPI (CDROM) DMA only
2897 libata.dma=4 Com 2612 libata.dma=4 Compact Flash DMA only
2898 Combinations also wor 2613 Combinations also work, so libata.dma=3 enables DMA
2899 for disks and CDROMs, 2614 for disks and CDROMs, but not CFs.
2900 2615
2901 libata.ignore_hpa= [LIBATA] Igno 2616 libata.ignore_hpa= [LIBATA] Ignore HPA limit
2902 libata.ignore_hpa=0 2617 libata.ignore_hpa=0 keep BIOS limits (default)
2903 libata.ignore_hpa=1 2618 libata.ignore_hpa=1 ignore limits, using full disk
2904 2619
2905 libata.noacpi [LIBATA] Disables use 2620 libata.noacpi [LIBATA] Disables use of ACPI in libata suspend/resume
2906 when set. 2621 when set.
2907 Format: <int> 2622 Format: <int>
2908 2623
2909 libata.force= [LIBATA] Force config !! 2624 libata.force= [LIBATA] Force configurations. The format is comma-
2910 separated list of "[I !! 2625 separated list of "[ID:]VAL" where ID is
2911 PORT and DEVICE are d !! 2626 PORT[.DEVICE]. PORT and DEVICE are decimal numbers
2912 or device. Basically !! 2627 matching port, link or device. Basically, it matches
2913 printed on console by !! 2628 the ATA ID string printed on console by libata. If
2914 omitted, the last POR !! 2629 the whole ID part is omitted, the last PORT and DEVICE
2915 ID hasn't been specif !! 2630 values are used. If ID hasn't been specified yet, the
2916 to all ports, links a !! 2631 configuration applies to all ports, links and devices.
2917 2632
2918 If only DEVICE is omi 2633 If only DEVICE is omitted, the parameter applies to
2919 the port and all link 2634 the port and all links and devices behind it. DEVICE
2920 number of 0 either se 2635 number of 0 either selects the first device or the
2921 first fan-out link be 2636 first fan-out link behind PMP device. It does not
2922 select the host link. 2637 select the host link. DEVICE number of 15 selects the
2923 host link and device 2638 host link and device attached to it.
2924 2639
2925 The VAL specifies the 2640 The VAL specifies the configuration to force. As long
2926 as there is no ambigu !! 2641 as there's no ambiguity shortcut notation is allowed.
2927 For example, both 1.5 2642 For example, both 1.5 and 1.5G would work for 1.5Gbps.
2928 The following configu 2643 The following configurations can be forced.
2929 2644
2930 * Cable type: 40c, 80 2645 * Cable type: 40c, 80c, short40c, unk, ign or sata.
2931 Any ID with matchin 2646 Any ID with matching PORT is used.
2932 2647
2933 * SATA link speed lim 2648 * SATA link speed limit: 1.5Gbps or 3.0Gbps.
2934 2649
2935 * Transfer mode: pio[ 2650 * Transfer mode: pio[0-7], mwdma[0-4] and udma[0-7].
2936 udma[/][16,25,33,44 2651 udma[/][16,25,33,44,66,100,133] notation is also
2937 allowed. 2652 allowed.
2938 2653
2939 * nohrst, nosrst, nor <<
2940 resets. <<
2941 <<
2942 * rstonce: only attem <<
2943 link recovery. <<
2944 <<
2945 * [no]dbdelay: Enable <<
2946 before debouncing a <<
2947 detection. <<
2948 <<
2949 * [no]ncq: Turn on or 2654 * [no]ncq: Turn on or off NCQ.
2950 2655
2951 * [no]ncqtrim: Enable !! 2656 * [no]ncqtrim: Turn off queued DSM TRIM.
2952 <<
2953 * [no]ncqati: Enable <<
2954 <<
2955 * [no]trim: Enable or <<
2956 <<
2957 * trim_zero: Indicate <<
2958 <<
2959 * max_trim_128m: Set <<
2960 <<
2961 * [no]dma: Turn on or <<
2962 <<
2963 * atapi_dmadir: Enabl <<
2964 <<
2965 * atapi_mod16_dma: En <<
2966 commands that are n <<
2967 <<
2968 * [no]dmalog: Enable <<
2969 READ LOG DMA EXT co <<
2970 <<
2971 * [no]iddevlog: Enabl <<
2972 identify device dat <<
2973 <<
2974 * [no]logdir: Enable <<
2975 purpose log directo <<
2976 <<
2977 * max_sec_128: Set tr <<
2978 <<
2979 * max_sec_1024: Set o <<
2980 1024 sectors. <<
2981 <<
2982 * max_sec_lba48: Set <<
2983 65535 sectors. <<
2984 2657
2985 * [no]lpm: Enable or !! 2658 * nohrst, nosrst, norst: suppress hard, soft
>> 2659 and both resets.
2986 2660
2987 * [no]setxfer: Indica !! 2661 * rstonce: only attempt one reset during
2988 should be skipped. !! 2662 hot-unplug link recovery
2989 2663
2990 * [no]fua: Disable or !! 2664 * dump_id: dump IDENTIFY data.
2991 support for devices <<
2992 2665
2993 * dump_id: Dump IDENT !! 2666 * atapi_dmadir: Enable ATAPI DMADIR bridge support
2994 2667
2995 * disable: Disable th 2668 * disable: Disable this device.
2996 2669
2997 If there are multiple 2670 If there are multiple matching configurations changing
2998 the same attribute, t 2671 the same attribute, the last one is used.
2999 2672
>> 2673 memblock=debug [KNL] Enable memblock debug messages.
>> 2674
3000 load_ramdisk= [RAM] [Deprecated] 2675 load_ramdisk= [RAM] [Deprecated]
3001 2676
3002 lockd.nlm_grace_period=P [NFS] Assig 2677 lockd.nlm_grace_period=P [NFS] Assign grace period.
3003 Format: <integer> 2678 Format: <integer>
3004 2679
3005 lockd.nlm_tcpport=N [NFS] Assign 2680 lockd.nlm_tcpport=N [NFS] Assign TCP port.
3006 Format: <integer> 2681 Format: <integer>
3007 2682
3008 lockd.nlm_timeout=T [NFS] Assign 2683 lockd.nlm_timeout=T [NFS] Assign timeout value.
3009 Format: <integer> 2684 Format: <integer>
3010 2685
3011 lockd.nlm_udpport=M [NFS] Assign 2686 lockd.nlm_udpport=M [NFS] Assign UDP port.
3012 Format: <integer> 2687 Format: <integer>
3013 2688
3014 lockdown= [SECURITY,EARLY] !! 2689 lockdown= [SECURITY]
3015 { integrity | confide 2690 { integrity | confidentiality }
3016 Enable the kernel loc 2691 Enable the kernel lockdown feature. If set to
3017 integrity, kernel fea 2692 integrity, kernel features that allow userland to
3018 modify the running ke 2693 modify the running kernel are disabled. If set to
3019 confidentiality, kern 2694 confidentiality, kernel features that allow userland
3020 to extract confidenti 2695 to extract confidential information from the kernel
3021 are also disabled. 2696 are also disabled.
3022 2697
3023 locktorture.acq_writer_lim= [KNL] <<
3024 Set the time limit in <<
3025 acquisition. Acquisi <<
3026 will result in a spla <<
3027 <<
3028 locktorture.bind_readers= [KNL] <<
3029 Specify the list of C <<
3030 to be bound. <<
3031 <<
3032 locktorture.bind_writers= [KNL] <<
3033 Specify the list of C <<
3034 to be bound. <<
3035 <<
3036 locktorture.call_rcu_chains= [KNL] <<
3037 Specify the number of <<
3038 chains to set up. Th <<
3039 there is a high proba <<
3040 in progress at any gi <<
3041 which disables these <<
3042 <<
3043 locktorture.long_hold= [KNL] <<
3044 Specify the duration <<
3045 occasional long-durat <<
3046 to 100 milliseconds. <<
3047 <<
3048 locktorture.nested_locks= [KNL] <<
3049 Specify the maximum l <<
3050 locktorture is to exe <<
3051 (MAX_NESTED_LOCKS). <<
3052 Note that this parame <<
3053 of locks that do not <<
3054 <<
3055 locktorture.nreaders_stress= [KNL] 2698 locktorture.nreaders_stress= [KNL]
3056 Set the number of loc 2699 Set the number of locking read-acquisition kthreads.
3057 Defaults to being aut 2700 Defaults to being automatically set based on the
3058 number of online CPUs 2701 number of online CPUs.
3059 2702
3060 locktorture.nwriters_stress= [KNL] 2703 locktorture.nwriters_stress= [KNL]
3061 Set the number of loc 2704 Set the number of locking write-acquisition kthreads.
3062 2705
3063 locktorture.onoff_holdoff= [KNL] 2706 locktorture.onoff_holdoff= [KNL]
3064 Set time (s) after bo 2707 Set time (s) after boot for CPU-hotplug testing.
3065 2708
3066 locktorture.onoff_interval= [KNL] 2709 locktorture.onoff_interval= [KNL]
3067 Set time (s) between 2710 Set time (s) between CPU-hotplug operations, or
3068 zero to disable CPU-h 2711 zero to disable CPU-hotplug testing.
3069 2712
3070 locktorture.rt_boost= [KNL] <<
3071 Do periodic testing o <<
3072 boosting. Select 0 t <<
3073 only rt_mutex, and 2 <<
3074 Defaults to 2, which <<
3075 odd choice, but which <<
3076 non-real-time spinloc <<
3077 of preemption. Note <<
3078 disable boosting. <<
3079 <<
3080 locktorture.rt_boost_factor= [KNL] <<
3081 Number that determine <<
3082 long priority boostin <<
3083 scaled down by the nu <<
3084 number of boosts per <<
3085 constant as the numbe <<
3086 On the other hand, th <<
3087 increases with the nu <<
3088 <<
3089 locktorture.shuffle_interval= [KNL] 2713 locktorture.shuffle_interval= [KNL]
3090 Set task-shuffle inte 2714 Set task-shuffle interval (jiffies). Shuffling
3091 tasks allows some CPU 2715 tasks allows some CPUs to go into dyntick-idle
3092 mode during the lockt 2716 mode during the locktorture test.
3093 2717
3094 locktorture.shutdown_secs= [KNL] 2718 locktorture.shutdown_secs= [KNL]
3095 Set time (s) after bo 2719 Set time (s) after boot system shutdown. This
3096 is useful for hands-o 2720 is useful for hands-off automated testing.
3097 2721
3098 locktorture.stat_interval= [KNL] 2722 locktorture.stat_interval= [KNL]
3099 Time (s) between stat 2723 Time (s) between statistics printk()s.
3100 2724
3101 locktorture.stutter= [KNL] 2725 locktorture.stutter= [KNL]
3102 Time (s) to stutter t 2726 Time (s) to stutter testing, for example,
3103 specifying five secon 2727 specifying five seconds causes the test to run for
3104 five seconds, wait fo 2728 five seconds, wait for five seconds, and so on.
3105 This tests the lockin 2729 This tests the locking primitive's ability to
3106 transition abruptly t 2730 transition abruptly to and from idle.
3107 2731
3108 locktorture.torture_type= [KNL] 2732 locktorture.torture_type= [KNL]
3109 Specify the locking i 2733 Specify the locking implementation to test.
3110 2734
3111 locktorture.verbose= [KNL] 2735 locktorture.verbose= [KNL]
3112 Enable additional pri 2736 Enable additional printk() statements.
3113 2737
3114 locktorture.writer_fifo= [KNL] <<
3115 Run the write-side lo <<
3116 sched_set_fifo() real <<
3117 <<
3118 logibm.irq= [HW,MOUSE] Logitech B 2738 logibm.irq= [HW,MOUSE] Logitech Bus Mouse Driver
3119 Format: <irq> 2739 Format: <irq>
3120 2740
3121 loglevel= [KNL,EARLY] !! 2741 loglevel= All Kernel Messages with a loglevel smaller than the
3122 All Kernel Messages w <<
3123 console loglevel will 2742 console loglevel will be printed to the console. It can
3124 also be changed with 2743 also be changed with klogd or other programs. The
3125 loglevels are defined 2744 loglevels are defined as follows:
3126 2745
3127 0 (KERN_EMERG) 2746 0 (KERN_EMERG) system is unusable
3128 1 (KERN_ALERT) 2747 1 (KERN_ALERT) action must be taken immediately
3129 2 (KERN_CRIT) 2748 2 (KERN_CRIT) critical conditions
3130 3 (KERN_ERR) 2749 3 (KERN_ERR) error conditions
3131 4 (KERN_WARNING) 2750 4 (KERN_WARNING) warning conditions
3132 5 (KERN_NOTICE) 2751 5 (KERN_NOTICE) normal but significant condition
3133 6 (KERN_INFO) 2752 6 (KERN_INFO) informational
3134 7 (KERN_DEBUG) 2753 7 (KERN_DEBUG) debug-level messages
3135 2754
3136 log_buf_len=n[KMG] [KNL,EARLY] !! 2755 log_buf_len=n[KMG] Sets the size of the printk ring buffer,
3137 Sets the size of the !! 2756 in bytes. n must be a power of two and greater
3138 n must be a power of !! 2757 than the minimal size. The minimal size is defined
3139 minimal size. The min !! 2758 by LOG_BUF_SHIFT kernel config parameter. There is
3140 LOG_BUF_SHIFT kernel !! 2759 also CONFIG_LOG_CPU_MAX_BUF_SHIFT config parameter
3141 is also CONFIG_LOG_CP !! 2760 that allows to increase the default size depending on
3142 parameter that allows !! 2761 the number of CPUs. See init/Kconfig for more details.
3143 depending on the numb <<
3144 for more details. <<
3145 2762
3146 logo.nologo [FB] Disables display 2763 logo.nologo [FB] Disables display of the built-in Linux logo.
3147 This may be used to p 2764 This may be used to provide more screen space for
3148 kernel log messages a 2765 kernel log messages and is useful when debugging
3149 kernel boot problems. 2766 kernel boot problems.
3150 2767
3151 lp=0 [LP] Specify paral 2768 lp=0 [LP] Specify parallel ports to use, e.g,
3152 lp=port[,port...] lp=none,parpo 2769 lp=port[,port...] lp=none,parport0 (lp0 not configured, lp1 uses
3153 lp=reset first paralle 2770 lp=reset first parallel port). 'lp=0' disables the
3154 lp=auto printer drive 2771 lp=auto printer driver. 'lp=reset' (which can be
3155 specified in 2772 specified in addition to the ports) causes
3156 attached prin 2773 attached printers to be reset. Using
3157 lp=port1,port 2774 lp=port1,port2,... specifies the parallel ports
3158 to associate 2775 to associate lp devices with, starting with
3159 lp0. A port s 2776 lp0. A port specification may be 'none' to skip
3160 that lp devic 2777 that lp device, or a parport name such as
3161 'parport0'. S 2778 'parport0'. Specifying 'lp=auto' instead of a
3162 port specific 2779 port specification list means that device IDs
3163 from each por 2780 from each port should be examined, to see if
3164 an IEEE 1284- 2781 an IEEE 1284-compliant printer is attached; if
3165 so, the drive 2782 so, the driver will manage that printer.
3166 See also head 2783 See also header of drivers/char/lp.c.
3167 2784
3168 lpj=n [KNL] 2785 lpj=n [KNL]
3169 Sets loops_per_jiffy 2786 Sets loops_per_jiffy to given constant, thus avoiding
3170 time-consuming boot-t 2787 time-consuming boot-time autodetection (up to 250 ms per
3171 CPU). 0 enables autod 2788 CPU). 0 enables autodetection (default). To determine
3172 the correct value for 2789 the correct value for your kernel, boot with normal
3173 autodetection and see 2790 autodetection and see what value is printed. Note that
3174 on SMP systems the pr 2791 on SMP systems the preset will be applied to all CPUs,
3175 which is likely to ca 2792 which is likely to cause problems if your CPUs need
3176 significantly diverge 2793 significantly divergent settings. An incorrect value
3177 will cause delays in 2794 will cause delays in the kernel to be wrong, leading to
3178 unpredictable I/O err 2795 unpredictable I/O errors and other breakage. Although
3179 unlikely, in the extr 2796 unlikely, in the extreme case this might damage your
3180 hardware. 2797 hardware.
3181 2798
>> 2799 ltpc= [NET]
>> 2800 Format: <io>,<irq>,<dma>
>> 2801
3182 lsm.debug [SECURITY] Enable LSM 2802 lsm.debug [SECURITY] Enable LSM initialization debugging output.
3183 2803
3184 lsm=lsm1,...,lsmN 2804 lsm=lsm1,...,lsmN
3185 [SECURITY] Choose ord 2805 [SECURITY] Choose order of LSM initialization. This
3186 overrides CONFIG_LSM, 2806 overrides CONFIG_LSM, and the "security=" parameter.
3187 2807
>> 2808 machvec= [IA-64] Force the use of a particular machine-vector
>> 2809 (machvec) in a generic kernel.
>> 2810 Example: machvec=hpzx1
>> 2811
3188 machtype= [Loongson] Share the 2812 machtype= [Loongson] Share the same kernel image file between
3189 different yeeloong la 2813 different yeeloong laptops.
3190 Example: machtype=lem 2814 Example: machtype=lemote-yeeloong-2f-7inch
3191 2815
3192 maxcpus= [SMP,EARLY] Maximum n !! 2816 max_addr=nn[KMG] [KNL,BOOT,ia64] All physical memory greater
>> 2817 than or equal to this physical address is ignored.
>> 2818
>> 2819 maxcpus= [SMP] Maximum number of processors that an SMP kernel
3193 will bring up during 2820 will bring up during bootup. maxcpus=n : n >= 0 limits
3194 the kernel to bring u 2821 the kernel to bring up 'n' processors. Surely after
3195 bootup you can bring 2822 bootup you can bring up the other plugged cpu by executing
3196 "echo 1 > /sys/device 2823 "echo 1 > /sys/devices/system/cpu/cpuX/online". So maxcpus
3197 only takes effect dur 2824 only takes effect during system bootup.
3198 While n=0 is a specia 2825 While n=0 is a special case, it is equivalent to "nosmp",
3199 which also disables t 2826 which also disables the IO APIC.
3200 2827
3201 max_loop= [LOOP] The number of 2828 max_loop= [LOOP] The number of loop block devices that get
3202 (loop.max_loop) unconditionally pre-c 2829 (loop.max_loop) unconditionally pre-created at init time. The default
3203 number is configured 2830 number is configured by BLK_DEV_LOOP_MIN_COUNT. Instead
3204 of statically allocat 2831 of statically allocating a predefined number, loop
3205 devices can be reques 2832 devices can be requested on-demand with the
3206 /dev/loop-control int 2833 /dev/loop-control interface.
3207 2834
3208 mce [X86-32] Machine Chec 2835 mce [X86-32] Machine Check Exception
3209 2836
3210 mce=option [X86-64] See Document !! 2837 mce=option [X86-64] See Documentation/x86/x86_64/boot-options.rst
3211 2838
3212 md= [HW] RAID subsystems 2839 md= [HW] RAID subsystems devices and level
3213 See Documentation/adm 2840 See Documentation/admin-guide/md.rst.
3214 2841
3215 mdacon= [MDA] 2842 mdacon= [MDA]
3216 Format: <first>,<last 2843 Format: <first>,<last>
3217 Specifies range of co 2844 Specifies range of consoles to be captured by the MDA.
3218 2845
3219 mds= [X86,INTEL,EARLY] !! 2846 mds= [X86,INTEL]
3220 Control mitigation fo 2847 Control mitigation for the Micro-architectural Data
3221 Sampling (MDS) vulner 2848 Sampling (MDS) vulnerability.
3222 2849
3223 Certain CPUs are vuln 2850 Certain CPUs are vulnerable to an exploit against CPU
3224 internal buffers whic 2851 internal buffers which can forward information to a
3225 disclosure gadget und 2852 disclosure gadget under certain conditions.
3226 2853
3227 In vulnerable process 2854 In vulnerable processors, the speculatively
3228 forwarded data can be 2855 forwarded data can be used in a cache side channel
3229 attack, to access dat 2856 attack, to access data to which the attacker does
3230 not have direct acces 2857 not have direct access.
3231 2858
3232 This parameter contro 2859 This parameter controls the MDS mitigation. The
3233 options are: 2860 options are:
3234 2861
3235 full - Enable M 2862 full - Enable MDS mitigation on vulnerable CPUs
3236 full,nosmt - Enable M 2863 full,nosmt - Enable MDS mitigation and disable
3237 SMT on v 2864 SMT on vulnerable CPUs
3238 off - Uncondit 2865 off - Unconditionally disable MDS mitigation
3239 2866
3240 On TAA-affected machi 2867 On TAA-affected machines, mds=off can be prevented by
3241 an active TAA mitigat 2868 an active TAA mitigation as both vulnerabilities are
3242 mitigated with the sa 2869 mitigated with the same mechanism so in order to disable
3243 this mitigation, you 2870 this mitigation, you need to specify tsx_async_abort=off
3244 too. 2871 too.
3245 2872
3246 Not specifying this o 2873 Not specifying this option is equivalent to
3247 mds=full. 2874 mds=full.
3248 2875
3249 For details see: Docu 2876 For details see: Documentation/admin-guide/hw-vuln/mds.rst
3250 2877
3251 mem=nn[KMG] [HEXAGON,EARLY] Set t !! 2878 mem=nn[KMG] [KNL,BOOT] Force usage of a specific amount of memory
3252 Must be specified, ot !! 2879 Amount of memory to be used in cases as follows:
3253 <<
3254 mem=nn[KMG] [KNL,BOOT,EARLY] Forc <<
3255 of memory Amount of m <<
3256 as follows: <<
3257 2880
3258 1 for test; 2881 1 for test;
3259 2 when the kernel is 2882 2 when the kernel is not able to see the whole system memory;
3260 3 memory that lies af 2883 3 memory that lies after 'mem=' boundary is excluded from
3261 the hypervisor, then 2884 the hypervisor, then assigned to KVM guests.
3262 4 to limit the memory <<
3263 <<
3264 [ARC,MICROBLAZE] - th <<
3265 high memory is not af <<
3266 <<
3267 [ARM64] - only limits <<
3268 mapping. The NOMAP re <<
3269 2885
3270 [X86] Work as limitin 2886 [X86] Work as limiting max address. Use together
3271 with memmap= to avoid 2887 with memmap= to avoid physical address space collisions.
3272 Without memmap= PCI d 2888 Without memmap= PCI devices could be placed at addresses
3273 belonging to unused R 2889 belonging to unused RAM.
3274 2890
3275 Note that this only t 2891 Note that this only takes effects during boot time since
3276 in above case 3, memo 2892 in above case 3, memory may need be hot added after boot
3277 if system memory of h 2893 if system memory of hypervisor is not sufficient.
3278 2894
3279 mem=nn[KMG]@ss[KMG] <<
3280 [ARM,MIPS,EARLY] - ov <<
3281 reported by firmware. <<
3282 Define a memory regio <<
3283 ss[KMG]. <<
3284 Multiple different re <<
3285 multiple mem= paramet <<
3286 <<
3287 mem=nopentium [BUGS=X86-32] Disable 2895 mem=nopentium [BUGS=X86-32] Disable usage of 4MB pages for kernel
3288 memory. 2896 memory.
3289 2897
3290 memblock=debug [KNL,EARLY] Enable me <<
3291 <<
3292 memchunk=nn[KMG] 2898 memchunk=nn[KMG]
3293 [KNL,SH] Allow user t 2899 [KNL,SH] Allow user to override the default size for
3294 per-device physically 2900 per-device physically contiguous DMA buffers.
3295 2901
3296 memhp_default_state=online/offline/on !! 2902 memhp_default_state=online/offline
3297 [KNL] Set the initial 2903 [KNL] Set the initial state for the memory hotplug
3298 onlining policy. If n 2904 onlining policy. If not specified, the default value is
3299 set according to the 2905 set according to the
3300 CONFIG_MEMORY_HOTPLUG 2906 CONFIG_MEMORY_HOTPLUG_DEFAULT_ONLINE kernel config
3301 option. 2907 option.
3302 See Documentation/adm 2908 See Documentation/admin-guide/mm/memory-hotplug.rst.
3303 2909
3304 memmap=exactmap [KNL,X86,EARLY] Enabl !! 2910 memmap=exactmap [KNL,X86] Enable setting of an exact
3305 E820 memory map, as s 2911 E820 memory map, as specified by the user.
3306 Such memmap=exactmap 2912 Such memmap=exactmap lines can be constructed based on
3307 BIOS output or other 2913 BIOS output or other requirements. See the memmap=nn@ss
3308 option description. 2914 option description.
3309 2915
3310 memmap=nn[KMG]@ss[KMG] 2916 memmap=nn[KMG]@ss[KMG]
3311 [KNL, X86,MIPS,XTENSA !! 2917 [KNL, X86, MIPS, XTENSA] Force usage of a specific region of memory.
3312 Region of memory to b 2918 Region of memory to be used is from ss to ss+nn.
3313 If @ss[KMG] is omitte 2919 If @ss[KMG] is omitted, it is equivalent to mem=nn[KMG],
3314 which limits max addr 2920 which limits max address to nn[KMG].
3315 Multiple different re 2921 Multiple different regions can be specified,
3316 comma delimited. 2922 comma delimited.
3317 Example: 2923 Example:
3318 memmap=100M@2 2924 memmap=100M@2G,100M#3G,1G!1024G
3319 2925
3320 memmap=nn[KMG]#ss[KMG] 2926 memmap=nn[KMG]#ss[KMG]
3321 [KNL,ACPI,EARLY] Mark !! 2927 [KNL,ACPI] Mark specific memory as ACPI data.
3322 Region of memory to b 2928 Region of memory to be marked is from ss to ss+nn.
3323 2929
3324 memmap=nn[KMG]$ss[KMG] 2930 memmap=nn[KMG]$ss[KMG]
3325 [KNL,ACPI,EARLY] Mark !! 2931 [KNL,ACPI] Mark specific memory as reserved.
3326 Region of memory to b 2932 Region of memory to be reserved is from ss to ss+nn.
3327 Example: Exclude memo 2933 Example: Exclude memory from 0x18690000-0x1869ffff
3328 memmap=64K$0 2934 memmap=64K$0x18690000
3329 or 2935 or
3330 memmap=0x100 2936 memmap=0x10000$0x18690000
3331 Some bootloaders may 2937 Some bootloaders may need an escape character before '$',
3332 like Grub2, otherwise 2938 like Grub2, otherwise '$' and the following number
3333 will be eaten. 2939 will be eaten.
3334 2940
3335 memmap=nn[KMG]!ss[KMG,EARLY] !! 2941 memmap=nn[KMG]!ss[KMG]
3336 [KNL,X86] Mark specif 2942 [KNL,X86] Mark specific memory as protected.
3337 Region of memory to b 2943 Region of memory to be used, from ss to ss+nn.
3338 The memory region may 2944 The memory region may be marked as e820 type 12 (0xc)
3339 and is NVDIMM or ADR 2945 and is NVDIMM or ADR memory.
3340 2946
3341 memmap=<size>%<offset>-<oldtype>+<new 2947 memmap=<size>%<offset>-<oldtype>+<newtype>
3342 [KNL,ACPI,EARLY] Conv !! 2948 [KNL,ACPI] Convert memory within the specified region
3343 from <oldtype> to <ne 2949 from <oldtype> to <newtype>. If "-<oldtype>" is left
3344 out, the whole region 2950 out, the whole region will be marked as <newtype>,
3345 even if previously un 2951 even if previously unavailable. If "+<newtype>" is left
3346 out, matching memory 2952 out, matching memory will be removed. Types are
3347 specified as e820 typ 2953 specified as e820 types, e.g., 1 = RAM, 2 = reserved,
3348 3 = ACPI, 12 = PRAM. 2954 3 = ACPI, 12 = PRAM.
3349 2955
3350 memory_corruption_check=0/1 [X86,EARL !! 2956 memory_corruption_check=0/1 [X86]
3351 Some BIOSes seem to c 2957 Some BIOSes seem to corrupt the first 64k of
3352 memory when doing thi 2958 memory when doing things like suspend/resume.
3353 Setting this option w 2959 Setting this option will scan the memory
3354 looking for corruptio 2960 looking for corruption. Enabling this will
3355 both detect corruptio 2961 both detect corruption and prevent the kernel
3356 from using the memory 2962 from using the memory being corrupted.
3357 However, its intended 2963 However, its intended as a diagnostic tool; if
3358 repeatable BIOS-origi 2964 repeatable BIOS-originated corruption always
3359 affects the same memo 2965 affects the same memory, you can use memmap=
3360 to prevent the kernel 2966 to prevent the kernel from using that memory.
3361 2967
3362 memory_corruption_check_size=size [X8 !! 2968 memory_corruption_check_size=size [X86]
3363 By default it checks 2969 By default it checks for corruption in the low
3364 64k, making this memo 2970 64k, making this memory unavailable for normal
3365 use. Use this parame 2971 use. Use this parameter to scan for
3366 corruption in more or 2972 corruption in more or less memory.
3367 2973
3368 memory_corruption_check_period=second !! 2974 memory_corruption_check_period=seconds [X86]
3369 By default it checks 2975 By default it checks for corruption every 60
3370 seconds. Use this pa 2976 seconds. Use this parameter to check at some
3371 other rate. 0 disabl 2977 other rate. 0 disables periodic checking.
3372 2978
3373 memory_hotplug.memmap_on_memory 2979 memory_hotplug.memmap_on_memory
3374 [KNL,X86,ARM] Boolean 2980 [KNL,X86,ARM] Boolean flag to enable this feature.
3375 Format: {on | off (de 2981 Format: {on | off (default)}
3376 When enabled, runtime 2982 When enabled, runtime hotplugged memory will
3377 allocate its internal !! 2983 allocate its internal metadata (struct pages)
3378 those vmemmap pages c !! 2984 from the hotadded memory which will allow to
3379 if hugetlb_free_vmemm !! 2985 hotadd a lot of memory without requiring
3380 hotadded memory which !! 2986 additional memory to do so.
3381 lot of memory without <<
3382 memory to do so. <<
3383 This feature is disab 2987 This feature is disabled by default because it
3384 has some implication 2988 has some implication on large (e.g. GB)
3385 allocations in some c 2989 allocations in some configurations (e.g. small
3386 memory blocks). 2990 memory blocks).
3387 The state of the flag 2991 The state of the flag can be read in
3388 /sys/module/memory_ho 2992 /sys/module/memory_hotplug/parameters/memmap_on_memory.
3389 Note that even when e 2993 Note that even when enabled, there are a few cases where
3390 the feature is not ef 2994 the feature is not effective.
3391 2995
3392 memtest= [KNL,X86,ARM,M68K,PPC !! 2996 This is not compatible with hugetlb_free_vmemmap. If
>> 2997 both parameters are enabled, hugetlb_free_vmemmap takes
>> 2998 precedence over memory_hotplug.memmap_on_memory.
>> 2999
>> 3000 memtest= [KNL,X86,ARM,PPC,RISCV] Enable memtest
3393 Format: <integer> 3001 Format: <integer>
3394 default : 0 <disable> 3002 default : 0 <disable>
3395 Specifies the number 3003 Specifies the number of memtest passes to be
3396 performed. Each pass 3004 performed. Each pass selects another test
3397 pattern from a given 3005 pattern from a given set of patterns. Memtest
3398 fills the memory with 3006 fills the memory with this pattern, validates
3399 memory contents and r 3007 memory contents and reserves bad memory
3400 regions that are dete 3008 regions that are detected.
3401 3009
3402 mem_encrypt= [X86-64] AMD Secure M 3010 mem_encrypt= [X86-64] AMD Secure Memory Encryption (SME) control
3403 Valid arguments: on, 3011 Valid arguments: on, off
3404 Default: off !! 3012 Default (depends on kernel configuration option):
>> 3013 on (CONFIG_AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT=y)
>> 3014 off (CONFIG_AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT=n)
3405 mem_encrypt=on: 3015 mem_encrypt=on: Activate SME
3406 mem_encrypt=off: 3016 mem_encrypt=off: Do not activate SME
3407 3017
3408 Refer to Documentatio !! 3018 Refer to Documentation/virt/kvm/amd-memory-encryption.rst
3409 for details on when m 3019 for details on when memory encryption can be activated.
3410 3020
3411 mem_sleep_default= [SUSPEND] Def 3021 mem_sleep_default= [SUSPEND] Default system suspend mode:
3412 s2idle - Suspend-To- 3022 s2idle - Suspend-To-Idle
3413 shallow - Power-On Su 3023 shallow - Power-On Suspend or equivalent (if supported)
3414 deep - Suspend-To- 3024 deep - Suspend-To-RAM or equivalent (if supported)
3415 See Documentation/adm 3025 See Documentation/admin-guide/pm/sleep-states.rst.
3416 3026
>> 3027 meye.*= [HW] Set MotionEye Camera parameters
>> 3028 See Documentation/admin-guide/media/meye.rst.
>> 3029
>> 3030 mfgpt_irq= [IA-32] Specify the IRQ to use for the
>> 3031 Multi-Function General Purpose Timers on AMD Geode
>> 3032 platforms.
>> 3033
3417 mfgptfix [X86-32] Fix MFGPT ti 3034 mfgptfix [X86-32] Fix MFGPT timers on AMD Geode platforms when
3418 the BIOS has incorrec 3035 the BIOS has incorrectly applied a workaround. TinyBIOS
3419 version 0.98 is known 3036 version 0.98 is known to be affected, 0.99 fixes the
3420 problem by letting th 3037 problem by letting the user disable the workaround.
3421 3038
3422 mga= [HW,DRM] 3039 mga= [HW,DRM]
3423 3040
3424 microcode.force_minrev= [X86] !! 3041 min_addr=nn[KMG] [KNL,BOOT,ia64] All physical memory below this
3425 Format: <bool> !! 3042 physical address is ignored.
3426 Enable or disable the <<
3427 enforcement for the r <<
3428 3043
3429 mini2440= [ARM,HW,KNL] 3044 mini2440= [ARM,HW,KNL]
3430 Format:[0..2][b][c][t 3045 Format:[0..2][b][c][t]
3431 Default: "0tb" 3046 Default: "0tb"
3432 MINI2440 configuratio 3047 MINI2440 configuration specification:
3433 0 - The attached scre 3048 0 - The attached screen is the 3.5" TFT
3434 1 - The attached scre 3049 1 - The attached screen is the 7" TFT
3435 2 - The VGA Shield is 3050 2 - The VGA Shield is attached (1024x768)
3436 Leaving out the scree 3051 Leaving out the screen size parameter will not load
3437 the TFT driver, and t 3052 the TFT driver, and the framebuffer will be left
3438 unconfigured. 3053 unconfigured.
3439 b - Enable backlight. 3054 b - Enable backlight. The TFT backlight pin will be
3440 linked to the kernel 3055 linked to the kernel VESA blanking code and a GPIO
3441 LED. This parameter i 3056 LED. This parameter is not necessary when using the
3442 VGA shield. 3057 VGA shield.
3443 c - Enable the s3c ca 3058 c - Enable the s3c camera interface.
3444 t - Reserved for enab 3059 t - Reserved for enabling touchscreen support. The
3445 touchscreen support i 3060 touchscreen support is not enabled in the mainstream
3446 kernel as of 2.6.30, 3061 kernel as of 2.6.30, a preliminary port can be found
3447 in the "bleeding edge 3062 in the "bleeding edge" mini2440 support kernel at
3448 https://repo.or.cz/w/ 3063 https://repo.or.cz/w/linux-2.6/mini2440.git
3449 3064
3450 mitigations= 3065 mitigations=
3451 [X86,PPC,S390,ARM64,E !! 3066 [X86,PPC,S390,ARM64] Control optional mitigations for
3452 CPU vulnerabilities. 3067 CPU vulnerabilities. This is a set of curated,
3453 arch-independent opti 3068 arch-independent options, each of which is an
3454 aggregation of existi 3069 aggregation of existing arch-specific options.
3455 3070
3456 Note, "mitigations" i <<
3457 kernel was built with <<
3458 <<
3459 off 3071 off
3460 Disable all o 3072 Disable all optional CPU mitigations. This
3461 improves syst 3073 improves system performance, but it may also
3462 expose users 3074 expose users to several CPU vulnerabilities.
3463 Equivalent to !! 3075 Equivalent to: gather_data_sampling=off [X86]
3464 !! 3076 kpti=0 [ARM64]
3465 3077 kvm.nx_huge_pages=off [X86]
3466 3078 l1tf=off [X86]
3467 3079 mds=off [X86]
3468 3080 mmio_stale_data=off [X86]
3469 3081 no_entry_flush [PPC]
3470 3082 no_uaccess_flush [PPC]
3471 3083 nobp=0 [S390]
3472 3084 nopti [X86,PPC]
3473 <<
3474 3085 nospectre_v1 [X86,PPC]
3475 3086 nospectre_v2 [X86,PPC,S390,ARM64]
3476 3087 reg_file_data_sampling=off [X86]
3477 3088 retbleed=off [X86]
3478 <<
3479 3089 spec_store_bypass_disable=off [X86,PPC]
3480 3090 spectre_bhi=off [X86]
3481 3091 spectre_v2_user=off [X86]
3482 <<
3483 3092 ssbd=force-off [ARM64]
3484 3093 tsx_async_abort=off [X86]
3485 3094
3486 Exceptions: 3095 Exceptions:
3487 3096 This does not have any effect on
3488 3097 kvm.nx_huge_pages when
3489 3098 kvm.nx_huge_pages=force.
3490 3099
3491 auto (default) 3100 auto (default)
3492 Mitigate all 3101 Mitigate all CPU vulnerabilities, but leave SMT
3493 enabled, even 3102 enabled, even if it's vulnerable. This is for
3494 users who don 3103 users who don't want to be surprised by SMT
3495 getting disab 3104 getting disabled across kernel upgrades, or who
3496 have other wa 3105 have other ways of avoiding SMT-based attacks.
3497 Equivalent to 3106 Equivalent to: (default behavior)
3498 3107
3499 auto,nosmt 3108 auto,nosmt
3500 Mitigate all 3109 Mitigate all CPU vulnerabilities, disabling SMT
3501 if needed. T 3110 if needed. This is for users who always want to
3502 be fully miti 3111 be fully mitigated, even if it means losing SMT.
3503 Equivalent to 3112 Equivalent to: l1tf=flush,nosmt [X86]
3504 3113 mds=full,nosmt [X86]
3505 3114 tsx_async_abort=full,nosmt [X86]
3506 3115 mmio_stale_data=full,nosmt [X86]
3507 3116 retbleed=auto,nosmt [X86]
3508 3117
3509 mminit_loglevel= 3118 mminit_loglevel=
3510 [KNL,EARLY] When CONF !! 3119 [KNL] When CONFIG_DEBUG_MEMORY_INIT is set, this
3511 parameter allows cont 3120 parameter allows control of the logging verbosity for
3512 the additional memory 3121 the additional memory initialisation checks. A value
3513 of 0 disables mminit 3122 of 0 disables mminit logging and a level of 4 will
3514 log everything. Infor 3123 log everything. Information is printed at KERN_DEBUG
3515 so loglevel=8 may als 3124 so loglevel=8 may also need to be specified.
3516 3125
3517 mmio_stale_data= 3126 mmio_stale_data=
3518 [X86,INTEL,EARLY] Con !! 3127 [X86,INTEL] Control mitigation for the Processor
3519 MMIO Stale Data vulne 3128 MMIO Stale Data vulnerabilities.
3520 3129
3521 Processor MMIO Stale 3130 Processor MMIO Stale Data is a class of
3522 vulnerabilities that 3131 vulnerabilities that may expose data after an MMIO
3523 operation. Exposed da 3132 operation. Exposed data could originate or end in
3524 the same CPU buffers 3133 the same CPU buffers as affected by MDS and TAA.
3525 Therefore, similar to 3134 Therefore, similar to MDS and TAA, the mitigation
3526 is to clear the affec 3135 is to clear the affected CPU buffers.
3527 3136
3528 This parameter contro 3137 This parameter controls the mitigation. The
3529 options are: 3138 options are:
3530 3139
3531 full - Enable m 3140 full - Enable mitigation on vulnerable CPUs
3532 3141
3533 full,nosmt - Enable m 3142 full,nosmt - Enable mitigation and disable SMT on
3534 vulnerab 3143 vulnerable CPUs.
3535 3144
3536 off - Uncondit 3145 off - Unconditionally disable mitigation
3537 3146
3538 On MDS or TAA affecte 3147 On MDS or TAA affected machines,
3539 mmio_stale_data=off c 3148 mmio_stale_data=off can be prevented by an active
3540 MDS or TAA mitigation 3149 MDS or TAA mitigation as these vulnerabilities are
3541 mitigated with the sa 3150 mitigated with the same mechanism so in order to
3542 disable this mitigati 3151 disable this mitigation, you need to specify
3543 mds=off and tsx_async 3152 mds=off and tsx_async_abort=off too.
3544 3153
3545 Not specifying this o 3154 Not specifying this option is equivalent to
3546 mmio_stale_data=full. 3155 mmio_stale_data=full.
3547 3156
3548 For details see: 3157 For details see:
3549 Documentation/admin-g 3158 Documentation/admin-guide/hw-vuln/processor_mmio_stale_data.rst
3550 3159
3551 <module>.async_probe[=<bool>] [KNL] <<
3552 If no <bool> value is <<
3553 specified is not a va <<
3554 probe on this module. <<
3555 asynchronous probe on <<
3556 <bool> value. See als <<
3557 <<
3558 module.async_probe=<bool> 3160 module.async_probe=<bool>
3559 [KNL] When set to tru 3161 [KNL] When set to true, modules will use async probing
3560 by default. To enable 3162 by default. To enable/disable async probing for a
3561 specific module, use 3163 specific module, use the module specific control that
3562 is documented under < 3164 is documented under <module>.async_probe. When both
3563 module.async_probe an 3165 module.async_probe and <module>.async_probe are
3564 specified, <module>.a 3166 specified, <module>.async_probe takes precedence for
3565 the specific module. 3167 the specific module.
3566 3168
3567 module.enable_dups_trace <<
3568 [KNL] When CONFIG_MOD <<
3569 this means that dupli <<
3570 trigger a WARN_ON() i <<
3571 if MODULE_DEBUG_AUTOL <<
3572 will always be issued <<
3573 module.sig_enforce 3169 module.sig_enforce
3574 [KNL] When CONFIG_MOD 3170 [KNL] When CONFIG_MODULE_SIG is set, this means that
3575 modules without (vali 3171 modules without (valid) signatures will fail to load.
3576 Note that if CONFIG_M 3172 Note that if CONFIG_MODULE_SIG_FORCE is set, that
3577 is always true, so th 3173 is always true, so this option does nothing.
3578 3174
3579 module_blacklist= [KNL] Do not load 3175 module_blacklist= [KNL] Do not load a comma-separated list of
3580 modules. Useful for 3176 modules. Useful for debugging problem modules.
3581 3177
3582 mousedev.tap_time= 3178 mousedev.tap_time=
3583 [MOUSE] Maximum time 3179 [MOUSE] Maximum time between finger touching and
3584 leaving touchpad surf 3180 leaving touchpad surface for touch to be considered
3585 a tap and be reported 3181 a tap and be reported as a left button click (for
3586 touchpads working in 3182 touchpads working in absolute mode only).
3587 Format: <msecs> 3183 Format: <msecs>
3588 mousedev.xres= [MOUSE] Horizontal sc 3184 mousedev.xres= [MOUSE] Horizontal screen resolution, used for devices
3589 reporting absolute co 3185 reporting absolute coordinates, such as tablets
3590 mousedev.yres= [MOUSE] Vertical scre 3186 mousedev.yres= [MOUSE] Vertical screen resolution, used for devices
3591 reporting absolute co 3187 reporting absolute coordinates, such as tablets
3592 3188
3593 movablecore= [KNL,X86,PPC,EARLY] !! 3189 movablecore= [KNL,X86,IA-64,PPC]
3594 Format: nn[KMGTPE] | 3190 Format: nn[KMGTPE] | nn%
3595 This parameter is the 3191 This parameter is the complement to kernelcore=, it
3596 specifies the amount 3192 specifies the amount of memory used for migratable
3597 allocations. If both 3193 allocations. If both kernelcore and movablecore is
3598 specified, then kerne 3194 specified, then kernelcore will be at *least* the
3599 specified value but m 3195 specified value but may be more. If movablecore on its
3600 own is specified, the 3196 own is specified, the administrator must be careful
3601 that the amount of me 3197 that the amount of memory usable for all allocations
3602 is not too small. 3198 is not too small.
3603 3199
3604 movable_node [KNL,EARLY] Boot-time !! 3200 movable_node [KNL] Boot-time switch to make hotplugable memory
3605 NUMA nodes to be mova 3201 NUMA nodes to be movable. This means that the memory
3606 of such nodes will be 3202 of such nodes will be usable only for movable
3607 allocations which rul 3203 allocations which rules out almost all kernel
3608 allocations. Use with 3204 allocations. Use with caution!
3609 3205
3610 MTD_Partition= [MTD] 3206 MTD_Partition= [MTD]
3611 Format: <name>,<regio 3207 Format: <name>,<region-number>,<size>,<offset>
3612 3208
3613 MTD_Region= [MTD] Format: 3209 MTD_Region= [MTD] Format:
3614 <name>,<region-number 3210 <name>,<region-number>[,<base>,<size>,<buswidth>,<altbuswidth>]
3615 3211
3616 mtdparts= [MTD] 3212 mtdparts= [MTD]
3617 See drivers/mtd/parse 3213 See drivers/mtd/parsers/cmdlinepart.c
3618 3214
>> 3215 multitce=off [PPC] This parameter disables the use of the pSeries
>> 3216 firmware feature for updating multiple TCE entries
>> 3217 at a time.
>> 3218
>> 3219 onenand.bdry= [HW,MTD] Flex-OneNAND Boundary Configuration
>> 3220
>> 3221 Format: [die0_boundary][,die0_lock][,die1_boundary][,die1_lock]
>> 3222
>> 3223 boundary - index of last SLC block on Flex-OneNAND.
>> 3224 The remaining blocks are configured as MLC blocks.
>> 3225 lock - Configure if Flex-OneNAND boundary should be locked.
>> 3226 Once locked, the boundary cannot be changed.
>> 3227 1 indicates lock status, 0 indicates unlock status.
>> 3228
>> 3229 mtdset= [ARM]
>> 3230 ARM/S3C2412 JIVE boot control
>> 3231
>> 3232 See arch/arm/mach-s3c/mach-jive.c
>> 3233
3619 mtouchusb.raw_coordinates= 3234 mtouchusb.raw_coordinates=
3620 [HW] Make the MicroTo 3235 [HW] Make the MicroTouch USB driver use raw coordinates
3621 ('y', default) or coo 3236 ('y', default) or cooked coordinates ('n')
3622 3237
3623 mtrr=debug [X86,EARLY] !! 3238 mtrr_chunk_size=nn[KMG] [X86]
3624 Enable printing debug <<
3625 registers at boot tim <<
3626 <<
3627 mtrr_chunk_size=nn[KMG,X86,EARLY] <<
3628 used for mtrr cleanup 3239 used for mtrr cleanup. It is largest continuous chunk
3629 that could hold holes 3240 that could hold holes aka. UC entries.
3630 3241
3631 mtrr_gran_size=nn[KMG,X86,EARLY] !! 3242 mtrr_gran_size=nn[KMG] [X86]
3632 Used for mtrr cleanup 3243 Used for mtrr cleanup. It is granularity of mtrr block.
3633 Default is 1. 3244 Default is 1.
3634 Large value could pre 3245 Large value could prevent small alignment from
3635 using up MTRRs. 3246 using up MTRRs.
3636 3247
3637 mtrr_spare_reg_nr=n [X86,EARLY] !! 3248 mtrr_spare_reg_nr=n [X86]
3638 Format: <integer> 3249 Format: <integer>
3639 Range: 0,7 : spare re 3250 Range: 0,7 : spare reg number
3640 Default : 1 3251 Default : 1
3641 Used for mtrr cleanup 3252 Used for mtrr cleanup. It is spare mtrr entries number.
3642 Set to 2 or more if y 3253 Set to 2 or more if your graphical card needs more.
3643 3254
3644 multitce=off [PPC] This parameter <<
3645 firmware feature for <<
3646 at a time. <<
3647 <<
3648 n2= [NET] SDL Inc. RISCom 3255 n2= [NET] SDL Inc. RISCom/N2 synchronous serial card
3649 3256
3650 netdev= [NET] Network devices 3257 netdev= [NET] Network devices parameters
3651 Format: <irq>,<io>,<m 3258 Format: <irq>,<io>,<mem_start>,<mem_end>,<name>
3652 Note that mem_start i 3259 Note that mem_start is often overloaded to mean
3653 something different a 3260 something different and driver-specific.
3654 This usage is only do 3261 This usage is only documented in each driver source
3655 file if at all. 3262 file if at all.
3656 3263
3657 netpoll.carrier_timeout= <<
3658 [NET] Specifies amoun <<
3659 netpoll should wait f <<
3660 waits 4 seconds. <<
3661 <<
3662 nf_conntrack.acct= 3264 nf_conntrack.acct=
3663 [NETFILTER] Enable co 3265 [NETFILTER] Enable connection tracking flow accounting
3664 0 to disable accounti 3266 0 to disable accounting
3665 1 to enable accountin 3267 1 to enable accounting
3666 Default value is 0. 3268 Default value is 0.
3667 3269
3668 nfs.cache_getent= !! 3270 nfsaddrs= [NFS] Deprecated. Use ip= instead.
3669 [NFS] sets the pathna !! 3271 See Documentation/admin-guide/nfs/nfsroot.rst.
3670 to update the NFS cli <<
3671 3272
3672 nfs.cache_getent_timeout= !! 3273 nfsroot= [NFS] nfs root filesystem for disk-less boxes.
3673 [NFS] sets the timeou !! 3274 See Documentation/admin-guide/nfs/nfsroot.rst.
3674 update a cache entry !! 3275
>> 3276 nfsrootdebug [NFS] enable nfsroot debugging messages.
>> 3277 See Documentation/admin-guide/nfs/nfsroot.rst.
3675 3278
3676 nfs.callback_nr_threads= 3279 nfs.callback_nr_threads=
3677 [NFSv4] set the total 3280 [NFSv4] set the total number of threads that the
3678 NFS client will assig 3281 NFS client will assign to service NFSv4 callback
3679 requests. 3282 requests.
3680 3283
3681 nfs.callback_tcpport= 3284 nfs.callback_tcpport=
3682 [NFS] set the TCP por 3285 [NFS] set the TCP port on which the NFSv4 callback
3683 channel should listen 3286 channel should listen.
3684 3287
3685 nfs.delay_retrans= !! 3288 nfs.cache_getent=
3686 [NFS] specifies the n !! 3289 [NFS] sets the pathname to the program which is used
3687 retries the request b !! 3290 to update the NFS client cache entries.
3688 after a reply of NFS4 !! 3291
3689 Only applies if the s !! 3292 nfs.cache_getent_timeout=
3690 and the specified val !! 3293 [NFS] sets the timeout after which an attempt to
>> 3294 update a cache entry is deemed to have failed.
>> 3295
>> 3296 nfs.idmap_cache_timeout=
>> 3297 [NFS] set the maximum lifetime for idmapper cache
>> 3298 entries.
3691 3299
3692 nfs.enable_ino64= 3300 nfs.enable_ino64=
3693 [NFS] enable 64-bit i 3301 [NFS] enable 64-bit inode numbers.
3694 If zero, the NFS clie 3302 If zero, the NFS client will fake up a 32-bit inode
3695 number for the readdi 3303 number for the readdir() and stat() syscalls instead
3696 of returning the full 3304 of returning the full 64-bit number.
3697 The default is to ret 3305 The default is to return 64-bit inode numbers.
3698 3306
3699 nfs.idmap_cache_timeout= <<
3700 [NFS] set the maximum <<
3701 entries. <<
3702 <<
3703 nfs.max_session_cb_slots= 3307 nfs.max_session_cb_slots=
3704 [NFSv4.1] Sets the ma 3308 [NFSv4.1] Sets the maximum number of session
3705 slots the client will 3309 slots the client will assign to the callback
3706 channel. This determi 3310 channel. This determines the maximum number of
3707 callbacks the client 3311 callbacks the client will process in parallel for
3708 a particular server. 3312 a particular server.
3709 3313
3710 nfs.max_session_slots= 3314 nfs.max_session_slots=
3711 [NFSv4.1] Sets the ma 3315 [NFSv4.1] Sets the maximum number of session slots
3712 the client will attem 3316 the client will attempt to negotiate with the server.
3713 This limits the numbe 3317 This limits the number of simultaneous RPC requests
3714 that the client can s 3318 that the client can send to the NFSv4.1 server.
3715 Note that there is li 3319 Note that there is little point in setting this
3716 value higher than the 3320 value higher than the max_tcp_slot_table_limit.
3717 3321
3718 nfs.nfs4_disable_idmapping= 3322 nfs.nfs4_disable_idmapping=
3719 [NFSv4] When set to t 3323 [NFSv4] When set to the default of '1', this option
3720 ensures that both the 3324 ensures that both the RPC level authentication
3721 scheme and the NFS le 3325 scheme and the NFS level operations agree to use
3722 numeric uids/gids if 3326 numeric uids/gids if the mount is using the
3723 'sec=sys' security fl 3327 'sec=sys' security flavour. In effect it is
3724 disabling idmapping, 3328 disabling idmapping, which can make migration from
3725 legacy NFSv2/v3 syste 3329 legacy NFSv2/v3 systems to NFSv4 easier.
3726 Servers that do not s 3330 Servers that do not support this mode of operation
3727 will be autodetected 3331 will be autodetected by the client, and it will fall
3728 back to using the idm 3332 back to using the idmapper.
3729 To turn off this beha 3333 To turn off this behaviour, set the value to '0'.
3730 <<
3731 nfs.nfs4_unique_id= 3334 nfs.nfs4_unique_id=
3732 [NFS4] Specify an add 3335 [NFS4] Specify an additional fixed unique ident-
3733 ification string that 3336 ification string that NFSv4 clients can insert into
3734 their nfs_client_id4 3337 their nfs_client_id4 string. This is typically a
3735 UUID that is generate 3338 UUID that is generated at system install time.
3736 3339
3737 nfs.recover_lost_locks= !! 3340 nfs.send_implementation_id =
>> 3341 [NFSv4.1] Send client implementation identification
>> 3342 information in exchange_id requests.
>> 3343 If zero, no implementation identification information
>> 3344 will be sent.
>> 3345 The default is to send the implementation identification
>> 3346 information.
>> 3347
>> 3348 nfs.recover_lost_locks =
3738 [NFSv4] Attempt to re 3349 [NFSv4] Attempt to recover locks that were lost due
3739 to a lease timeout on 3350 to a lease timeout on the server. Please note that
3740 doing this risks data 3351 doing this risks data corruption, since there are
3741 no guarantees that th 3352 no guarantees that the file will remain unchanged
3742 after the locks are l 3353 after the locks are lost.
3743 If you want to enable 3354 If you want to enable the kernel legacy behaviour of
3744 attempting to recover 3355 attempting to recover these locks, then set this
3745 parameter to '1'. 3356 parameter to '1'.
3746 The default parameter 3357 The default parameter value of '0' causes the kernel
3747 not to attempt recove 3358 not to attempt recovery of lost locks.
3748 3359
3749 nfs.send_implementation_id= !! 3360 nfs4.layoutstats_timer =
3750 [NFSv4.1] Send client <<
3751 information in exchan <<
3752 If zero, no implement <<
3753 will be sent. <<
3754 The default is to sen <<
3755 information. <<
3756 <<
3757 nfs4.layoutstats_timer= <<
3758 [NFSv4.2] Change the 3361 [NFSv4.2] Change the rate at which the kernel sends
3759 layoutstats to the pN 3362 layoutstats to the pNFS metadata server.
3760 3363
3761 Setting this to value 3364 Setting this to value to 0 causes the kernel to use
3762 whatever value is the 3365 whatever value is the default set by the layout
3763 driver. A non-zero va 3366 driver. A non-zero value sets the minimum interval
3764 in seconds between la 3367 in seconds between layoutstats transmissions.
3765 3368
3766 nfsd.inter_copy_offload_enable= <<
3767 [NFSv4.2] When set to <<
3768 server-to-server copi <<
3769 the destination of th <<
3770 <<
3771 nfsd.nfs4_disable_idmapping= 3369 nfsd.nfs4_disable_idmapping=
3772 [NFSv4] When set to t 3370 [NFSv4] When set to the default of '1', the NFSv4
3773 server will return on 3371 server will return only numeric uids and gids to
3774 clients using auth_sy 3372 clients using auth_sys, and will accept numeric uids
3775 and gids from such cl 3373 and gids from such clients. This is intended to ease
3776 migration from NFSv2/ 3374 migration from NFSv2/v3.
3777 3375
3778 nfsd.nfsd4_ssc_umount_timeout= <<
3779 [NFSv4.2] When used a <<
3780 server-to-server copy <<
3781 the source server. I <<
3782 it will be needed aga <<
3783 used for the number o <<
3784 this parameter. <<
3785 <<
3786 nfsaddrs= [NFS] Deprecated. Us <<
3787 See Documentation/adm <<
3788 <<
3789 nfsroot= [NFS] nfs root filesy <<
3790 See Documentation/adm <<
3791 <<
3792 nfsrootdebug [NFS] enable nfsroot <<
3793 See Documentation/adm <<
3794 <<
3795 nmi_backtrace.backtrace_idle [KNL] 3376 nmi_backtrace.backtrace_idle [KNL]
3796 Dump stacks even of i 3377 Dump stacks even of idle CPUs in response to an
3797 NMI stack-backtrace r 3378 NMI stack-backtrace request.
3798 3379
3799 nmi_debug= [KNL,SH] Specify one 3380 nmi_debug= [KNL,SH] Specify one or more actions to take
3800 when a NMI is trigger 3381 when a NMI is triggered.
3801 Format: [state][,regs 3382 Format: [state][,regs][,debounce][,die]
3802 3383
3803 nmi_watchdog= [KNL,BUGS=X86] Debugg 3384 nmi_watchdog= [KNL,BUGS=X86] Debugging features for SMP kernels
3804 Format: [panic,][nopa !! 3385 Format: [panic,][nopanic,][num]
3805 Valid num: 0 or 1 3386 Valid num: 0 or 1
3806 0 - turn hardlockup d 3387 0 - turn hardlockup detector in nmi_watchdog off
3807 1 - turn hardlockup d 3388 1 - turn hardlockup detector in nmi_watchdog on
3808 rNNN - configure the <<
3809 <<
3810 When panic is specifi 3389 When panic is specified, panic when an NMI watchdog
3811 timeout occurs (or 'n 3390 timeout occurs (or 'nopanic' to not panic on an NMI
3812 watchdog, if CONFIG_B 3391 watchdog, if CONFIG_BOOTPARAM_HARDLOCKUP_PANIC is set)
3813 To disable both hard 3392 To disable both hard and soft lockup detectors,
3814 please see 'nowatchdo 3393 please see 'nowatchdog'.
3815 This is useful when y 3394 This is useful when you use a panic=... timeout and
3816 need the box quickly 3395 need the box quickly up again.
3817 3396
3818 These settings can be 3397 These settings can be accessed at runtime via
3819 the nmi_watchdog and 3398 the nmi_watchdog and hardlockup_panic sysctls.
3820 3399
>> 3400 netpoll.carrier_timeout=
>> 3401 [NET] Specifies amount of time (in seconds) that
>> 3402 netpoll should wait for a carrier. By default netpoll
>> 3403 waits 4 seconds.
>> 3404
3821 no387 [BUGS=X86-32] Tells t 3405 no387 [BUGS=X86-32] Tells the kernel to use the 387 maths
3822 emulation library eve 3406 emulation library even if a 387 maths coprocessor
3823 is present. 3407 is present.
3824 3408
3825 no4lvl [RISCV,EARLY] Disable !! 3409 no5lvl [X86-64] Disable 5-level paging mode. Forces
3826 Forces kernel to use <<
3827 <<
3828 no5lvl [X86-64,RISCV,EARLY] <<
3829 kernel to use 4-level 3410 kernel to use 4-level paging instead.
3830 3411
3831 noalign [KNL,ARM] !! 3412 nofsgsbase [X86] Disables FSGSBASE instructions.
3832 <<
3833 noapic [SMP,APIC,EARLY] Tell <<
3834 IOAPICs that may be p <<
3835 <<
3836 noautogroup Disable scheduler aut <<
3837 <<
3838 nocache [ARM,EARLY] <<
3839 3413
3840 no_console_suspend 3414 no_console_suspend
3841 [HW] Never suspend th 3415 [HW] Never suspend the console
3842 Disable suspending of 3416 Disable suspending of consoles during suspend and
3843 hibernate operations. 3417 hibernate operations. Once disabled, debugging
3844 messages can reach va 3418 messages can reach various consoles while the rest
3845 of the system is bein 3419 of the system is being put to sleep (ie, while
3846 debugging driver susp 3420 debugging driver suspend/resume hooks). This may
3847 not work reliably wit 3421 not work reliably with all consoles, but is known
3848 to work with serial a 3422 to work with serial and VGA consoles.
3849 To facilitate more fl 3423 To facilitate more flexible debugging, we also add
3850 console_suspend, a pr 3424 console_suspend, a printk module parameter to control
3851 it. Users could use c 3425 it. Users could use console_suspend (usually
3852 /sys/module/printk/pa 3426 /sys/module/printk/parameters/console_suspend) to
3853 turn on/off it dynami 3427 turn on/off it dynamically.
3854 3428
3855 no_debug_objects !! 3429 novmcoredd [KNL,KDUMP]
3856 [KNL,EARLY] Disable o !! 3430 Disable device dump. Device dump allows drivers to
>> 3431 append dump data to vmcore so you can collect driver
>> 3432 specified debug info. Drivers can append the data
>> 3433 without any limit and this data is stored in memory,
>> 3434 so this may cause significant memory stress. Disabling
>> 3435 device dump can help save memory but the driver debug
>> 3436 data will be no longer available. This parameter
>> 3437 is only available when CONFIG_PROC_VMCORE_DEVICE_DUMP
>> 3438 is set.
>> 3439
>> 3440 noaliencache [MM, NUMA, SLAB] Disables the allocation of alien
>> 3441 caches in the slab allocator. Saves per-node memory,
>> 3442 but will impact performance.
>> 3443
>> 3444 noalign [KNL,ARM]
>> 3445
>> 3446 noaltinstr [S390] Disables alternative instructions patching
>> 3447 (CPU alternatives feature).
>> 3448
>> 3449 noapic [SMP,APIC] Tells the kernel to not make use of any
>> 3450 IOAPICs that may be present in the system.
>> 3451
>> 3452 noautogroup Disable scheduler automatic task group creation.
>> 3453
>> 3454 nocache [ARM]
>> 3455
>> 3456 noclflush [BUGS=X86] Don't use the CLFLUSH instruction
>> 3457
>> 3458 delayacct [KNL] Enable per-task delay accounting
3857 3459
3858 nodsp [SH] Disable hardware 3460 nodsp [SH] Disable hardware DSP at boot time.
3859 3461
3860 noefi [EFI,EARLY] Disable E !! 3462 noefi Disable EFI runtime services support.
>> 3463
>> 3464 no_entry_flush [PPC] Don't flush the L1-D cache when entering the kernel.
3861 3465
3862 no_entry_flush [PPC,EARLY] Don't flu !! 3466 noexec [IA-64]
>> 3467
>> 3468 noexec [X86]
>> 3469 On X86-32 available only on PAE configured kernels.
>> 3470 noexec=on: enable non-executable mappings (default)
>> 3471 noexec=off: disable non-executable mappings
>> 3472
>> 3473 nosmap [X86,PPC]
>> 3474 Disable SMAP (Supervisor Mode Access Prevention)
>> 3475 even if it is supported by processor.
>> 3476
>> 3477 nosmep [X86,PPC]
>> 3478 Disable SMEP (Supervisor Mode Execution Prevention)
>> 3479 even if it is supported by processor.
3863 3480
3864 noexec32 [X86-64] 3481 noexec32 [X86-64]
3865 This affects only 32- 3482 This affects only 32-bit executables.
3866 noexec32=on: enable n 3483 noexec32=on: enable non-executable mappings (default)
3867 read doesn't 3484 read doesn't imply executable mappings
3868 noexec32=off: disable 3485 noexec32=off: disable non-executable mappings
3869 read implies 3486 read implies executable mappings
3870 3487
3871 no_file_caps Tells the kernel not <<
3872 only way then for a f <<
3873 is to be setuid root <<
3874 <<
3875 nofpu [MIPS,SH] Disable har 3488 nofpu [MIPS,SH] Disable hardware FPU at boot time.
3876 3489
3877 nofsgsbase [X86] Disables FSGSBA <<
3878 <<
3879 nofxsr [BUGS=X86-32] Disable 3490 nofxsr [BUGS=X86-32] Disables x86 floating point extended
3880 register save and res 3491 register save and restore. The kernel will only save
3881 legacy floating-point 3492 legacy floating-point registers on task switch.
3882 3493
>> 3494 nohugeiomap [KNL,X86,PPC,ARM64] Disable kernel huge I/O mappings.
>> 3495
>> 3496 nohugevmalloc [PPC] Disable kernel huge vmalloc mappings.
>> 3497
>> 3498 nosmt [KNL,S390] Disable symmetric multithreading (SMT).
>> 3499 Equivalent to smt=1.
>> 3500
>> 3501 [KNL,X86] Disable symmetric multithreading (SMT).
>> 3502 nosmt=force: Force disable SMT, cannot be undone
>> 3503 via the sysfs control file.
>> 3504
>> 3505 nospectre_v1 [X86,PPC] Disable mitigations for Spectre Variant 1
>> 3506 (bounds check bypass). With this option data leaks are
>> 3507 possible in the system.
>> 3508
>> 3509 nospectre_v2 [X86,PPC_FSL_BOOK3E,ARM64] Disable all mitigations for
>> 3510 the Spectre variant 2 (indirect branch prediction)
>> 3511 vulnerability. System may allow data leaks with this
>> 3512 option.
>> 3513
>> 3514 nospec_store_bypass_disable
>> 3515 [HW] Disable all mitigations for the Speculative Store Bypass vulnerability
>> 3516
>> 3517 no_uaccess_flush
>> 3518 [PPC] Don't flush the L1-D cache after accessing user data.
>> 3519
>> 3520 noxsave [BUGS=X86] Disables x86 extended register state save
>> 3521 and restore using xsave. The kernel will fallback to
>> 3522 enabling legacy floating-point and sse state.
>> 3523
>> 3524 noxsaveopt [X86] Disables xsaveopt used in saving x86 extended
>> 3525 register states. The kernel will fall back to use
>> 3526 xsave to save the states. By using this parameter,
>> 3527 performance of saving the states is degraded because
>> 3528 xsave doesn't support modified optimization while
>> 3529 xsaveopt supports it on xsaveopt enabled systems.
>> 3530
>> 3531 noxsaves [X86] Disables xsaves and xrstors used in saving and
>> 3532 restoring x86 extended register state in compacted
>> 3533 form of xsave area. The kernel will fall back to use
>> 3534 xsaveopt and xrstor to save and restore the states
>> 3535 in standard form of xsave area. By using this
>> 3536 parameter, xsave area per process might occupy more
>> 3537 memory on xsaves enabled systems.
>> 3538
>> 3539 nohlt [ARM,ARM64,MICROBLAZE,SH] Forces the kernel to busy wait
>> 3540 in do_idle() and not use the arch_cpu_idle()
>> 3541 implementation; requires CONFIG_GENERIC_IDLE_POLL_SETUP
>> 3542 to be effective. This is useful on platforms where the
>> 3543 sleep(SH) or wfi(ARM,ARM64) instructions do not work
>> 3544 correctly or when doing power measurements to evalute
>> 3545 the impact of the sleep instructions. This is also
>> 3546 useful when using JTAG debugger.
>> 3547
>> 3548 no_file_caps Tells the kernel not to honor file capabilities. The
>> 3549 only way then for a file to be executed with privilege
>> 3550 is to be setuid root or executed by root.
>> 3551
>> 3552 nohalt [IA-64] Tells the kernel not to use the power saving
>> 3553 function PAL_HALT_LIGHT when idle. This increases
>> 3554 power-consumption. On the positive side, it reduces
>> 3555 interrupt wake-up latency, which may improve performance
>> 3556 in certain environments such as networked servers or
>> 3557 real-time systems.
>> 3558
3883 no_hash_pointers 3559 no_hash_pointers
3884 [KNL,EARLY] <<
3885 Force pointers printe 3560 Force pointers printed to the console or buffers to be
3886 unhashed. By default 3561 unhashed. By default, when a pointer is printed via %p
3887 format string, that p 3562 format string, that pointer is "hashed", i.e. obscured
3888 by hashing the pointe 3563 by hashing the pointer value. This is a security feature
3889 that hides actual ker 3564 that hides actual kernel addresses from unprivileged
3890 users, but it also ma 3565 users, but it also makes debugging the kernel more
3891 difficult since unequ 3566 difficult since unequal pointers can no longer be
3892 compared. However, i 3567 compared. However, if this command-line option is
3893 specified, then all n 3568 specified, then all normal pointers will have their true
3894 value printed. This o 3569 value printed. This option should only be specified when
3895 debugging the kernel. 3570 debugging the kernel. Please do not use on production
3896 kernels. 3571 kernels.
3897 3572
3898 nohibernate [HIBERNATION] Disable 3573 nohibernate [HIBERNATION] Disable hibernation and resume.
3899 3574
3900 nohlt [ARM,ARM64,MICROBLAZE <<
3901 busy wait in do_idle( <<
3902 implementation; requi <<
3903 to be effective. This <<
3904 sleep(SH) or wfi(ARM, <<
3905 correctly or when doi <<
3906 the impact of the sle <<
3907 useful when using JTA <<
3908 <<
3909 nohugeiomap [KNL,X86,PPC,ARM64,EA <<
3910 <<
3911 nohugevmalloc [KNL,X86,PPC,ARM64,EA <<
3912 <<
3913 nohz= [KNL] Boottime enable 3575 nohz= [KNL] Boottime enable/disable dynamic ticks
3914 Valid arguments: on, 3576 Valid arguments: on, off
3915 Default: on 3577 Default: on
3916 3578
3917 nohz_full= [KNL,BOOT,SMP,ISOL] 3579 nohz_full= [KNL,BOOT,SMP,ISOL]
3918 The argument is a cpu 3580 The argument is a cpu list, as described above.
3919 In kernels built with 3581 In kernels built with CONFIG_NO_HZ_FULL=y, set
3920 the specified list of 3582 the specified list of CPUs whose tick will be stopped
3921 whenever possible. Th 3583 whenever possible. The boot CPU will be forced outside
3922 the range to maintain 3584 the range to maintain the timekeeping. Any CPUs
3923 in this list will hav 3585 in this list will have their RCU callbacks offloaded,
3924 just as if they had a 3586 just as if they had also been called out in the
3925 rcu_nocbs= boot param 3587 rcu_nocbs= boot parameter.
3926 3588
3927 Note that this argume !! 3589 noiotrap [SH] Disables trapped I/O port accesses.
3928 the CONFIG_RCU_NOCB_C !! 3590
>> 3591 noirqdebug [X86-32] Disables the code which attempts to detect and
>> 3592 disable unhandled interrupt sources.
>> 3593
>> 3594 no_timer_check [X86,APIC] Disables the code which tests for
>> 3595 broken timer IRQ sources.
>> 3596
>> 3597 noisapnp [ISAPNP] Disables ISA PnP code.
3929 3598
3930 noinitrd [RAM] Tells the kerne 3599 noinitrd [RAM] Tells the kernel not to load any configured
3931 initial RAM disk. 3600 initial RAM disk.
3932 3601
3933 nointremap [X86-64,Intel-IOMMU,E !! 3602 nointremap [X86-64, Intel-IOMMU] Do not enable interrupt
3934 remapping. 3603 remapping.
3935 [Deprecated - use int 3604 [Deprecated - use intremap=off]
3936 3605
3937 noinvpcid [X86,EARLY] Disable t !! 3606 nointroute [IA-64]
3938 3607
3939 noiotrap [SH] Disables trapped !! 3608 noinvpcid [X86] Disable the INVPCID cpu feature.
3940 3609
3941 noirqdebug [X86-32] Disables the !! 3610 nojitter [IA-64] Disables jitter checking for ITC timers.
3942 disable unhandled int <<
3943 3611
3944 noisapnp [ISAPNP] Disables ISA !! 3612 no-kvmclock [X86,KVM] Disable paravirtualized KVM clock driver
3945 <<
3946 nokaslr [KNL,EARLY] <<
3947 When CONFIG_RANDOMIZE <<
3948 kernel and module bas <<
3949 Layout Randomization) <<
3950 3613
3951 no-kvmapf [X86,KVM,EARLY] Disab !! 3614 no-kvmapf [X86,KVM] Disable paravirtualized asynchronous page
3952 fault handling. 3615 fault handling.
3953 3616
3954 no-kvmclock [X86,KVM,EARLY] Disab !! 3617 no-vmw-sched-clock
>> 3618 [X86,PV_OPS] Disable paravirtualized VMware scheduler
>> 3619 clock and use the default one.
>> 3620
>> 3621 no-steal-acc [X86,PV_OPS,ARM64] Disable paravirtualized steal time
>> 3622 accounting. steal time is computed, but won't
>> 3623 influence scheduler behaviour
3955 3624
3956 nolapic [X86-32,APIC,EARLY] D !! 3625 nolapic [X86-32,APIC] Do not enable or use the local APIC.
3957 3626
3958 nolapic_timer [X86-32,APIC,EARLY] D !! 3627 nolapic_timer [X86-32,APIC] Do not use the local APIC timer.
>> 3628
>> 3629 nomca [IA-64] Disable machine check abort handling
3959 3630
3960 nomce [X86-32] Disable Mach 3631 nomce [X86-32] Disable Machine Check Exception
3961 3632
3962 nomfgpt [X86-32] Disable Mult 3633 nomfgpt [X86-32] Disable Multi-Function General Purpose
3963 Timer usage (for AMD 3634 Timer usage (for AMD Geode machines).
3964 3635
3965 nomodeset Disable kernel modese <<
3966 sets up a display mod <<
3967 for output. With nomo <<
3968 not load if they coul <<
3969 initialized output. O <<
3970 be available for use. <<
3971 perform display-mode <<
3972 <<
3973 Useful as error fallb <<
3974 <<
3975 nomodule Disable module load <<
3976 <<
3977 nonmi_ipi [X86] Disable using N 3636 nonmi_ipi [X86] Disable using NMI IPIs during panic/reboot to
3978 shutdown the other cp 3637 shutdown the other cpus. Instead use the REBOOT_VECTOR
3979 irq. 3638 irq.
3980 3639
3981 nopat [X86,EARLY] Disable P !! 3640 nomodule Disable module load
3982 pagetables) support. <<
3983 <<
3984 nopcid [X86-64,EARLY] Disabl <<
3985 <<
3986 nopku [X86] Disable Memory <<
3987 in some Intel CPUs. <<
3988 <<
3989 nopti [X86-64,EARLY] <<
3990 Equivalent to pti=off <<
3991 3641
3992 nopv= [X86,XEN,KVM,HYPER_V, !! 3642 nopat [X86] Disable PAT (page attribute table extension of
3993 Disables the PV optim !! 3643 pagetables) support.
3994 as generic guest with <<
3995 XEN HVM, KVM, HYPER_V <<
3996 3644
3997 nopvspin [X86,XEN,KVM,EARLY] !! 3645 nopcid [X86-64] Disable the PCID cpu feature.
3998 Disables the qspinloc <<
3999 which allow the hyper <<
4000 contention. <<
4001 3646
4002 norandmaps Don't use address spa 3647 norandmaps Don't use address space randomization. Equivalent to
4003 echo 0 > /proc/sys/ke 3648 echo 0 > /proc/sys/kernel/randomize_va_space
4004 3649
4005 noreplace-smp [X86-32,SMP] Don't re 3650 noreplace-smp [X86-32,SMP] Don't replace SMP instructions
4006 with UP alternatives 3651 with UP alternatives
4007 3652
>> 3653 nordrand [X86] Disable kernel use of the RDRAND and
>> 3654 RDSEED instructions even if they are supported
>> 3655 by the processor. RDRAND and RDSEED are still
>> 3656 available to user space applications.
>> 3657
4008 noresume [SWSUSP] Disables res 3658 noresume [SWSUSP] Disables resume and restores original swap
4009 space. 3659 space.
4010 3660
4011 no-scroll [VGA] Disables scroll 3661 no-scroll [VGA] Disables scrollback.
4012 This is required for 3662 This is required for the Braillex ib80-piezo Braille
4013 reader made by F.H. P 3663 reader made by F.H. Papenmeier (Germany).
4014 3664
4015 nosgx [X86-64,SGX,EARLY] Di !! 3665 nosbagart [IA-64]
4016 3666
4017 nosmap [PPC,EARLY] !! 3667 nosep [BUGS=X86-32] Disables x86 SYSENTER/SYSEXIT support.
4018 Disable SMAP (Supervi <<
4019 even if it is support <<
4020 3668
4021 nosmep [PPC64s,EARLY] !! 3669 nosgx [X86-64,SGX] Disables Intel SGX kernel support.
4022 Disable SMEP (Supervi <<
4023 even if it is support <<
4024 3670
4025 nosmp [SMP,EARLY] Tells an !! 3671 nosmp [SMP] Tells an SMP kernel to act as a UP kernel,
4026 and disable the IO AP 3672 and disable the IO APIC. legacy for "maxcpus=0".
4027 3673
4028 nosmt [KNL,MIPS,PPC,S390,EA <<
4029 Equivalent to smt=1. <<
4030 <<
4031 [KNL,X86,PPC] Disable <<
4032 nosmt=force: Force di <<
4033 via the <<
4034 <<
4035 nosoftlockup [KNL] Disable the sof 3674 nosoftlockup [KNL] Disable the soft-lockup detector.
4036 3675
4037 nospec_store_bypass_disable <<
4038 [HW,EARLY] Disable al <<
4039 Store Bypass vulnerab <<
4040 <<
4041 nospectre_bhb [ARM64,EARLY] Disable <<
4042 history injection) vu <<
4043 with this option. <<
4044 <<
4045 nospectre_v1 [X86,PPC,EARLY] Disab <<
4046 (bounds check bypass) <<
4047 possible in the syste <<
4048 <<
4049 nospectre_v2 [X86,PPC_E500,ARM64,E <<
4050 for the Spectre varia <<
4051 prediction) vulnerabi <<
4052 leaks with this optio <<
4053 <<
4054 no-steal-acc [X86,PV_OPS,ARM64,PPC <<
4055 Disable paravirtualiz <<
4056 is computed, but won' <<
4057 <<
4058 nosync [HW,M68K] Disables sy 3676 nosync [HW,M68K] Disables sync negotiation for all devices.
4059 3677
4060 no_timer_check [X86,APIC] Disables t <<
4061 broken timer IRQ sour <<
4062 <<
4063 no_uaccess_flush <<
4064 [PPC,EARLY] Don't flu <<
4065 <<
4066 novmcoredd [KNL,KDUMP] <<
4067 Disable device dump. <<
4068 append dump data to v <<
4069 specified debug info. <<
4070 without any limit and <<
4071 so this may cause sig <<
4072 device dump can help <<
4073 data will be no longe <<
4074 is only available whe <<
4075 is set. <<
4076 <<
4077 no-vmw-sched-clock <<
4078 [X86,PV_OPS,EARLY] Di <<
4079 scheduler clock and u <<
4080 <<
4081 nowatchdog [KNL] Disable both lo 3678 nowatchdog [KNL] Disable both lockup detectors, i.e.
4082 soft-lockup and NMI w 3679 soft-lockup and NMI watchdog (hard-lockup).
4083 3680
4084 nowb [ARM,EARLY] !! 3681 nowb [ARM]
4085 <<
4086 nox2apic [X86-64,APIC,EARLY] D <<
4087 3682
4088 NOTE: this parameter !! 3683 nox2apic [X86-64,APIC] Do not enable x2APIC mode.
4089 LEGACY_XAPIC_DISABLED <<
4090 IA32_XAPIC_DISABLE_ST <<
4091 3684
4092 noxsave [BUGS=X86] Disables x !! 3685 cpu0_hotplug [X86] Turn on CPU0 hotplug feature when
4093 and restore using xsa !! 3686 CONFIG_BOOTPARAM_HOTPLUG_CPU0 is off.
4094 enabling legacy float !! 3687 Some features depend on CPU0. Known dependencies are:
4095 !! 3688 1. Resume from suspend/hibernate depends on CPU0.
4096 noxsaveopt [X86] Disables xsaveo !! 3689 Suspend/hibernate will fail if CPU0 is offline and you
4097 register states. The !! 3690 need to online CPU0 before suspend/hibernate.
4098 xsave to save the sta !! 3691 2. PIC interrupts also depend on CPU0. CPU0 can't be
4099 performance of saving !! 3692 removed if a PIC interrupt is detected.
4100 xsave doesn't support !! 3693 It's said poweroff/reboot may depend on CPU0 on some
4101 xsaveopt supports it !! 3694 machines although I haven't seen such issues so far
4102 !! 3695 after CPU0 is offline on a few tested machines.
4103 noxsaves [X86] Disables xsaves !! 3696 If the dependencies are under your control, you can
4104 restoring x86 extende !! 3697 turn on cpu0_hotplug.
4105 form of xsave area. T !! 3698
4106 xsaveopt and xrstor t !! 3699 nps_mtm_hs_ctr= [KNL,ARC]
4107 in standard form of x !! 3700 This parameter sets the maximum duration, in
4108 parameter, xsave area !! 3701 cycles, each HW thread of the CTOP can run
4109 memory on xsaves enab !! 3702 without interruptions, before HW switches it.
>> 3703 The actual maximum duration is 16 times this
>> 3704 parameter's value.
>> 3705 Format: integer between 1 and 255
>> 3706 Default: 255
>> 3707
>> 3708 nptcg= [IA-64] Override max number of concurrent global TLB
>> 3709 purges which is reported from either PAL_VM_SUMMARY or
>> 3710 SAL PALO.
4110 3711
4111 nr_cpus= [SMP,EARLY] Maximum n !! 3712 nr_cpus= [SMP] Maximum number of processors that an SMP kernel
4112 could support. nr_cp 3713 could support. nr_cpus=n : n >= 1 limits the kernel to
4113 support 'n' processor 3714 support 'n' processors. It could be larger than the
4114 number of already plu 3715 number of already plugged CPU during bootup, later in
4115 runtime you can physi 3716 runtime you can physically add extra cpu until it reaches
4116 n. So during boot up 3717 n. So during boot up some boot time memory for per-cpu
4117 variables need be pre 3718 variables need be pre-allocated for later physical cpu
4118 hot plugging. 3719 hot plugging.
4119 3720
4120 nr_uarts= [SERIAL] maximum numb 3721 nr_uarts= [SERIAL] maximum number of UARTs to be registered.
4121 3722
4122 numa=off [KNL, ARM64, PPC, RIS !! 3723 numa=off [KNL, ARM64, PPC, RISCV, SPARC, X86] Disable NUMA, Only
4123 Disable NUMA, Only se !! 3724 set up a single NUMA node spanning all memory.
4124 spanning all memory. <<
4125 3725
4126 numa_balancing= [KNL,ARM64,PPC,RISCV, 3726 numa_balancing= [KNL,ARM64,PPC,RISCV,S390,X86] Enable or disable automatic
4127 NUMA balancing. 3727 NUMA balancing.
4128 Allowed values are en 3728 Allowed values are enable and disable
4129 3729
4130 numa_zonelist_order= [KNL, BOOT] Sele 3730 numa_zonelist_order= [KNL, BOOT] Select zonelist order for NUMA.
4131 'node', 'default' can 3731 'node', 'default' can be specified
4132 This can be set from 3732 This can be set from sysctl after boot.
4133 See Documentation/adm 3733 See Documentation/admin-guide/sysctl/vm.rst for details.
4134 3734
4135 ohci1394_dma=early [HW,EARLY] en !! 3735 ohci1394_dma=early [HW] enable debugging via the ohci1394 driver.
4136 See Documentation/cor 3736 See Documentation/core-api/debugging-via-ohci1394.rst for more
4137 info. 3737 info.
4138 3738
4139 olpc_ec_timeout= [OLPC] ms delay when 3739 olpc_ec_timeout= [OLPC] ms delay when issuing EC commands
4140 Rather than timing ou 3740 Rather than timing out after 20 ms if an EC
4141 command is not proper 3741 command is not properly ACKed, override the length
4142 of the timeout. We h 3742 of the timeout. We have interrupts disabled while
4143 waiting for the ACK, 3743 waiting for the ACK, so if this is set too high
4144 interrupts *may* be l 3744 interrupts *may* be lost!
4145 3745
4146 omap_mux= [OMAP] Override bootl 3746 omap_mux= [OMAP] Override bootloader pin multiplexing.
4147 Format: <mux_mode0.mo 3747 Format: <mux_mode0.mode_name=value>...
4148 For example, to overr 3748 For example, to override I2C bus2:
4149 omap_mux=i2c2_scl.i2c 3749 omap_mux=i2c2_scl.i2c2_scl=0x100,i2c2_sda.i2c2_sda=0x100
4150 3750
4151 onenand.bdry= [HW,MTD] Flex-OneNAND !! 3751 oops=panic Always panic on oopses. Default is to just kill the
4152 <<
4153 Format: [die0_boundar <<
4154 <<
4155 boundary - index of l <<
4156 The remain <<
4157 lock - Configure <<
4158 Once locke <<
4159 1 indicate <<
4160 <<
4161 oops=panic [KNL,EARLY] <<
4162 Always panic on oopse <<
4163 process, but there is 3752 process, but there is a small probability of
4164 deadlocking the machi 3753 deadlocking the machine.
4165 This will also cause 3754 This will also cause panics on machine check exceptions.
4166 Useful together with 3755 Useful together with panic=30 to trigger a reboot.
4167 3756
4168 page_alloc.shuffle= 3757 page_alloc.shuffle=
4169 [KNL] Boolean flag to 3758 [KNL] Boolean flag to control whether the page allocator
4170 should randomize its !! 3759 should randomize its free lists. The randomization may
4171 used to enable/disabl !! 3760 be automatically enabled if the kernel detects it is
4172 the flag can be read !! 3761 running on a platform with a direct-mapped memory-side
>> 3762 cache, and this parameter can be used to
>> 3763 override/disable that behavior. The state of the flag
>> 3764 can be read from sysfs at:
4173 /sys/module/page_allo 3765 /sys/module/page_alloc/parameters/shuffle.
4174 This parameter is onl <<
4175 3766
4176 page_owner= [KNL,EARLY] Boot-time !! 3767 page_owner= [KNL] Boot-time page_owner enabling option.
4177 Storage of the inform 3768 Storage of the information about who allocated
4178 each page is disabled 3769 each page is disabled in default. With this switch,
4179 we can turn it on. 3770 we can turn it on.
4180 on: enable the featur 3771 on: enable the feature
4181 3772
4182 page_poison= [KNL,EARLY] Boot-time !! 3773 page_poison= [KNL] Boot-time parameter changing the state of
4183 poisoning on the budd 3774 poisoning on the buddy allocator, available with
4184 CONFIG_PAGE_POISONING 3775 CONFIG_PAGE_POISONING=y.
4185 off: turn off poisoni 3776 off: turn off poisoning (default)
4186 on: turn on poisoning 3777 on: turn on poisoning
4187 3778
4188 page_reporting.page_reporting_order= 3779 page_reporting.page_reporting_order=
4189 [KNL] Minimal page re 3780 [KNL] Minimal page reporting order
4190 Format: <integer> 3781 Format: <integer>
4191 Adjust the minimal pa 3782 Adjust the minimal page reporting order. The page
4192 reporting is disabled !! 3783 reporting is disabled when it exceeds (MAX_ORDER-1).
4193 3784
4194 panic= [KNL] Kernel behaviou 3785 panic= [KNL] Kernel behaviour on panic: delay <timeout>
4195 timeout > 0: seconds 3786 timeout > 0: seconds before rebooting
4196 timeout = 0: wait for 3787 timeout = 0: wait forever
4197 timeout < 0: reboot i 3788 timeout < 0: reboot immediately
4198 Format: <timeout> 3789 Format: <timeout>
4199 3790
4200 panic_on_taint= [KNL,EARLY] !! 3791 panic_print= Bitmask for printing system info when panic happens.
4201 Bitmask for condition !! 3792 User can chose combination of the following bits:
>> 3793 bit 0: print all tasks info
>> 3794 bit 1: print system memory info
>> 3795 bit 2: print timer info
>> 3796 bit 3: print locks info if CONFIG_LOCKDEP is on
>> 3797 bit 4: print ftrace buffer
>> 3798 bit 5: print all printk messages in buffer
>> 3799
>> 3800 panic_on_taint= Bitmask for conditionally calling panic() in add_taint()
4202 Format: <hex>[,nouser 3801 Format: <hex>[,nousertaint]
4203 Hexadecimal bitmask r 3802 Hexadecimal bitmask representing the set of TAINT flags
4204 that will cause the k 3803 that will cause the kernel to panic when add_taint() is
4205 called with any of th 3804 called with any of the flags in this set.
4206 The optional switch " 3805 The optional switch "nousertaint" can be utilized to
4207 prevent userspace for 3806 prevent userspace forced crashes by writing to sysctl
4208 /proc/sys/kernel/tain 3807 /proc/sys/kernel/tainted any flagset matching with the
4209 bitmask set on panic_ 3808 bitmask set on panic_on_taint.
4210 See Documentation/adm 3809 See Documentation/admin-guide/tainted-kernels.rst for
4211 extra details on the 3810 extra details on the taint flags that users can pick
4212 to compose the bitmas 3811 to compose the bitmask to assign to panic_on_taint.
4213 3812
4214 panic_on_warn=1 panic() instead of WA !! 3813 panic_on_warn panic() instead of WARN(). Useful to cause kdump
4215 on a WARN(). 3814 on a WARN().
4216 3815
4217 panic_print= Bitmask for printing !! 3816 crash_kexec_post_notifiers
4218 User can chose combin !! 3817 Run kdump after running panic-notifiers and dumping
4219 bit 0: print all task !! 3818 kmsg. This only for the users who doubt kdump always
4220 bit 1: print system m !! 3819 succeeds in any situation.
4221 bit 2: print timer in !! 3820 Note that this also increases risks of kdump failure,
4222 bit 3: print locks in !! 3821 because some panic notifiers can make the crashed
4223 bit 4: print ftrace b !! 3822 kernel more unstable.
4224 bit 5: print all prin <<
4225 bit 6: print all CPUs <<
4226 bit 7: print only tas <<
4227 *Be aware* that this <<
4228 so there are risks of <<
4229 Use this option caref <<
4230 bigger log buffer wit <<
4231 3823
4232 parkbd.port= [HW] Parallel port nu 3824 parkbd.port= [HW] Parallel port number the keyboard adapter is
4233 connected to, default 3825 connected to, default is 0.
4234 Format: <parport#> 3826 Format: <parport#>
4235 parkbd.mode= [HW] Parallel port ke 3827 parkbd.mode= [HW] Parallel port keyboard adapter mode of operation,
4236 0 for XT, 1 for AT (d 3828 0 for XT, 1 for AT (default is AT).
4237 Format: <mode> 3829 Format: <mode>
4238 3830
4239 parport= [HW,PPT] Specify para 3831 parport= [HW,PPT] Specify parallel ports. 0 disables.
4240 Format: { 0 | auto | 3832 Format: { 0 | auto | 0xBBB[,IRQ[,DMA]] }
4241 Use 'auto' to force t 3833 Use 'auto' to force the driver to use any
4242 IRQ/DMA settings dete 3834 IRQ/DMA settings detected (the default is to
4243 ignore detected IRQ/D 3835 ignore detected IRQ/DMA settings because of
4244 possible conflicts). 3836 possible conflicts). You can specify the base
4245 address, IRQ, and DMA 3837 address, IRQ, and DMA settings; IRQ and DMA
4246 should be numbers, or 3838 should be numbers, or 'auto' (for using detected
4247 settings on that part 3839 settings on that particular port), or 'nofifo'
4248 (to avoid using a FIF 3840 (to avoid using a FIFO even if it is detected).
4249 Parallel ports are as 3841 Parallel ports are assigned in the order they
4250 are specified on the 3842 are specified on the command line, starting
4251 with parport0. 3843 with parport0.
4252 3844
4253 parport_init_mode= [HW,PPT] 3845 parport_init_mode= [HW,PPT]
4254 Configure VIA paralle 3846 Configure VIA parallel port to operate in
4255 a specific mode. This 3847 a specific mode. This is necessary on Pegasos
4256 computer where firmwa 3848 computer where firmware has no options for setting
4257 up parallel port mode 3849 up parallel port mode and sets it to spp.
4258 Currently this functi 3850 Currently this function knows 686a and 8231 chips.
4259 Format: [spp|ps2|epp| 3851 Format: [spp|ps2|epp|ecp|ecpepp]
4260 3852
4261 pata_legacy.all= [HW,LIBATA] 3853 pata_legacy.all= [HW,LIBATA]
4262 Format: <int> 3854 Format: <int>
4263 Set to non-zero to pr 3855 Set to non-zero to probe primary and secondary ISA
4264 port ranges on PCI sy 3856 port ranges on PCI systems where no PCI PATA device
4265 has been found at eit 3857 has been found at either range. Disabled by default.
4266 3858
4267 pata_legacy.autospeed= [HW,LIBATA] 3859 pata_legacy.autospeed= [HW,LIBATA]
4268 Format: <int> 3860 Format: <int>
4269 Set to non-zero if a 3861 Set to non-zero if a chip is present that snoops speed
4270 changes. Disabled by 3862 changes. Disabled by default.
4271 3863
4272 pata_legacy.ht6560a= [HW,LIBATA] 3864 pata_legacy.ht6560a= [HW,LIBATA]
4273 Format: <int> 3865 Format: <int>
4274 Set to 1, 2, or 3 for 3866 Set to 1, 2, or 3 for HT 6560A on the primary channel,
4275 the secondary channel 3867 the secondary channel, or both channels respectively.
4276 Disabled by default. 3868 Disabled by default.
4277 3869
4278 pata_legacy.ht6560b= [HW,LIBATA] 3870 pata_legacy.ht6560b= [HW,LIBATA]
4279 Format: <int> 3871 Format: <int>
4280 Set to 1, 2, or 3 for 3872 Set to 1, 2, or 3 for HT 6560B on the primary channel,
4281 the secondary channel 3873 the secondary channel, or both channels respectively.
4282 Disabled by default. 3874 Disabled by default.
4283 3875
4284 pata_legacy.iordy_mask= [HW,LIBATA] 3876 pata_legacy.iordy_mask= [HW,LIBATA]
4285 Format: <int> 3877 Format: <int>
4286 IORDY enable mask. S 3878 IORDY enable mask. Set individual bits to allow IORDY
4287 for the respective ch 3879 for the respective channel. Bit 0 is for the first
4288 legacy channel handle 3880 legacy channel handled by this driver, bit 1 is for
4289 the second channel, a 3881 the second channel, and so on. The sequence will often
4290 correspond to the pri 3882 correspond to the primary legacy channel, the secondary
4291 legacy channel, and s 3883 legacy channel, and so on, but the handling of a PCI
4292 bus and the use of ot 3884 bus and the use of other driver options may interfere
4293 with the sequence. B 3885 with the sequence. By default IORDY is allowed across
4294 all channels. 3886 all channels.
4295 3887
4296 pata_legacy.opti82c46x= [HW,LIBATA] 3888 pata_legacy.opti82c46x= [HW,LIBATA]
4297 Format: <int> 3889 Format: <int>
4298 Set to 1, 2, or 3 for 3890 Set to 1, 2, or 3 for Opti 82c611A on the primary
4299 channel, the secondar 3891 channel, the secondary channel, or both channels
4300 respectively. Disabl 3892 respectively. Disabled by default.
4301 3893
4302 pata_legacy.opti82c611a= [HW,L 3894 pata_legacy.opti82c611a= [HW,LIBATA]
4303 Format: <int> 3895 Format: <int>
4304 Set to 1, 2, or 3 for 3896 Set to 1, 2, or 3 for Opti 82c465MV on the primary
4305 channel, the secondar 3897 channel, the secondary channel, or both channels
4306 respectively. Disabl 3898 respectively. Disabled by default.
4307 3899
4308 pata_legacy.pio_mask= [HW,LIBATA] 3900 pata_legacy.pio_mask= [HW,LIBATA]
4309 Format: <int> 3901 Format: <int>
4310 PIO mode mask for aut 3902 PIO mode mask for autospeed devices. Set individual
4311 bits to allow the use 3903 bits to allow the use of the respective PIO modes.
4312 Bit 0 is for mode 0, 3904 Bit 0 is for mode 0, bit 1 is for mode 1, and so on.
4313 All modes allowed by 3905 All modes allowed by default.
4314 3906
4315 pata_legacy.probe_all= [HW,LIBATA] 3907 pata_legacy.probe_all= [HW,LIBATA]
4316 Format: <int> 3908 Format: <int>
4317 Set to non-zero to pr 3909 Set to non-zero to probe tertiary and further ISA
4318 port ranges on PCI sy 3910 port ranges on PCI systems. Disabled by default.
4319 3911
4320 pata_legacy.probe_mask= [HW,LIBATA] 3912 pata_legacy.probe_mask= [HW,LIBATA]
4321 Format: <int> 3913 Format: <int>
4322 Probe mask for legacy 3914 Probe mask for legacy ISA PATA ports. Depending on
4323 platform configuratio 3915 platform configuration and the use of other driver
4324 options up to 6 legac 3916 options up to 6 legacy ports are supported: 0x1f0,
4325 0x170, 0x1e8, 0x168, 3917 0x170, 0x1e8, 0x168, 0x1e0, 0x160, however probing
4326 of individual ports c 3918 of individual ports can be disabled by setting the
4327 corresponding bits in 3919 corresponding bits in the mask to 1. Bit 0 is for
4328 the first port in the 3920 the first port in the list above (0x1f0), and so on.
4329 By default all suppor 3921 By default all supported ports are probed.
4330 3922
4331 pata_legacy.qdi= [HW,LIBATA] 3923 pata_legacy.qdi= [HW,LIBATA]
4332 Format: <int> 3924 Format: <int>
4333 Set to non-zero to pr 3925 Set to non-zero to probe QDI controllers. By default
4334 set to 1 if CONFIG_PA 3926 set to 1 if CONFIG_PATA_QDI_MODULE, 0 otherwise.
4335 3927
4336 pata_legacy.winbond= [HW,LIBATA] 3928 pata_legacy.winbond= [HW,LIBATA]
4337 Format: <int> 3929 Format: <int>
4338 Set to non-zero to pr 3930 Set to non-zero to probe Winbond controllers. Use
4339 the standard I/O port 3931 the standard I/O port (0x130) if 1, otherwise the
4340 value given is the I/ 3932 value given is the I/O port to use (typically 0x1b0).
4341 By default set to 1 i 3933 By default set to 1 if CONFIG_PATA_WINBOND_VLB_MODULE,
4342 0 otherwise. 3934 0 otherwise.
4343 3935
4344 pata_platform.pio_mask= [HW,LIBATA] 3936 pata_platform.pio_mask= [HW,LIBATA]
4345 Format: <int> 3937 Format: <int>
4346 Supported PIO mode ma 3938 Supported PIO mode mask. Set individual bits to allow
4347 the use of the respec 3939 the use of the respective PIO modes. Bit 0 is for
4348 mode 0, bit 1 is for 3940 mode 0, bit 1 is for mode 1, and so on. Mode 0 only
4349 allowed by default. 3941 allowed by default.
4350 3942
4351 pause_on_oops=<int> !! 3943 pause_on_oops=
4352 Halt all CPUs after t 3944 Halt all CPUs after the first oops has been printed for
4353 the specified number 3945 the specified number of seconds. This is to be used if
4354 your oopses keep scro 3946 your oopses keep scrolling off the screen.
4355 3947
4356 pcbit= [HW,ISDN] 3948 pcbit= [HW,ISDN]
4357 3949
4358 pci=option[,option...] [PCI,EARLY] v !! 3950 pcd. [PARIDE]
>> 3951 See header of drivers/block/paride/pcd.c.
>> 3952 See also Documentation/admin-guide/blockdev/paride.rst.
>> 3953
>> 3954 pci=option[,option...] [PCI] various PCI subsystem options.
4359 3955
4360 Some options 3956 Some options herein operate on a specific device
4361 or a set of d 3957 or a set of devices (<pci_dev>). These are
4362 specified in 3958 specified in one of the following formats:
4363 3959
4364 [<domain>:]<b 3960 [<domain>:]<bus>:<dev>.<func>[/<dev>.<func>]*
4365 pci:<vendor>: 3961 pci:<vendor>:<device>[:<subvendor>:<subdevice>]
4366 3962
4367 Note: the fir 3963 Note: the first format specifies a PCI
4368 bus/device/fu 3964 bus/device/function address which may change
4369 if new hardwa 3965 if new hardware is inserted, if motherboard
4370 firmware chan 3966 firmware changes, or due to changes caused
4371 by other kern 3967 by other kernel parameters. If the
4372 domain is lef 3968 domain is left unspecified, it is
4373 taken to be z 3969 taken to be zero. Optionally, a path
4374 to a device t 3970 to a device through multiple device/function
4375 addresses can 3971 addresses can be specified after the base
4376 address (this 3972 address (this is more robust against
4377 renumbering i 3973 renumbering issues). The second format
4378 selects devic 3974 selects devices using IDs from the
4379 configuration 3975 configuration space which may match multiple
4380 devices in th 3976 devices in the system.
4381 3977
4382 earlydump dump PCI conf 3978 earlydump dump PCI config space before the kernel
4383 changes anyth 3979 changes anything
4384 off [X86] don't p 3980 off [X86] don't probe for the PCI bus
4385 bios [X86-32] forc 3981 bios [X86-32] force use of PCI BIOS, don't access
4386 the hardware 3982 the hardware directly. Use this if your machine
4387 has a non-sta 3983 has a non-standard PCI host bridge.
4388 nobios [X86-32] disa 3984 nobios [X86-32] disallow use of PCI BIOS, only direct
4389 hardware acce 3985 hardware access methods are allowed. Use this
4390 if you experi 3986 if you experience crashes upon bootup and you
4391 suspect they 3987 suspect they are caused by the BIOS.
4392 conf1 [X86] Force u 3988 conf1 [X86] Force use of PCI Configuration Access
4393 Mechanism 1 ( 3989 Mechanism 1 (config address in IO port 0xCF8,
4394 data in IO po 3990 data in IO port 0xCFC, both 32-bit).
4395 conf2 [X86] Force u 3991 conf2 [X86] Force use of PCI Configuration Access
4396 Mechanism 2 ( 3992 Mechanism 2 (IO port 0xCF8 is an 8-bit port for
4397 the function, 3993 the function, IO port 0xCFA, also 8-bit, sets
4398 bus number. T 3994 bus number. The config space is then accessed
4399 through ports 3995 through ports 0xC000-0xCFFF).
4400 See http://wi 3996 See http://wiki.osdev.org/PCI for more info
4401 on the config 3997 on the configuration access mechanisms.
4402 noaer [PCIE] If the 3998 noaer [PCIE] If the PCIEAER kernel config parameter is
4403 enabled, this 3999 enabled, this kernel boot option can be used to
4404 disable the u 4000 disable the use of PCIE advanced error reporting.
4405 nodomains [PCI] Disable 4001 nodomains [PCI] Disable support for multiple PCI
4406 root domains 4002 root domains (aka PCI segments, in ACPI-speak).
4407 nommconf [X86] Disable 4003 nommconf [X86] Disable use of MMCONFIG for PCI
4408 Configuration 4004 Configuration
4409 check_enable_amd_mmconf [X86] 4005 check_enable_amd_mmconf [X86] check for and enable
4410 properly conf 4006 properly configured MMIO access to PCI
4411 config space 4007 config space on AMD family 10h CPU
4412 nomsi [MSI] If the 4008 nomsi [MSI] If the PCI_MSI kernel config parameter is
4413 enabled, this 4009 enabled, this kernel boot option can be used to
4414 disable the u 4010 disable the use of MSI interrupts system-wide.
4415 noioapicquirk [APIC] Disabl 4011 noioapicquirk [APIC] Disable all boot interrupt quirks.
4416 Safety option 4012 Safety option to keep boot IRQs enabled. This
4417 should never 4013 should never be necessary.
4418 ioapicreroute [APIC] Enable 4014 ioapicreroute [APIC] Enable rerouting of boot IRQs to the
4419 primary IO-AP 4015 primary IO-APIC for bridges that cannot disable
4420 boot IRQs. Th 4016 boot IRQs. This fixes a source of spurious IRQs
4421 when the syst 4017 when the system masks IRQs.
4422 noioapicreroute [APIC] Disabl 4018 noioapicreroute [APIC] Disable workaround that uses the
4423 boot IRQ equi 4019 boot IRQ equivalent of an IRQ that connects to
4424 a chipset whe 4020 a chipset where boot IRQs cannot be disabled.
4425 The opposite 4021 The opposite of ioapicreroute.
4426 biosirq [X86-32] Use 4022 biosirq [X86-32] Use PCI BIOS calls to get the interrupt
4427 routing table 4023 routing table. These calls are known to be buggy
4428 on several ma 4024 on several machines and they hang the machine
4429 when used, bu 4025 when used, but on other computers it's the only
4430 way to get th 4026 way to get the interrupt routing table. Try
4431 this option i 4027 this option if the kernel is unable to allocate
4432 IRQs or disco 4028 IRQs or discover secondary PCI buses on your
4433 motherboard. 4029 motherboard.
4434 rom [X86] Assign 4030 rom [X86] Assign address space to expansion ROMs.
4435 Use with caut 4031 Use with caution as certain devices share
4436 address decod 4032 address decoders between ROMs and other
4437 resources. 4033 resources.
4438 norom [X86] Do not 4034 norom [X86] Do not assign address space to
4439 expansion ROM 4035 expansion ROMs that do not already have
4440 BIOS assigned 4036 BIOS assigned address ranges.
4441 nobar [X86] Do not 4037 nobar [X86] Do not assign address space to the
4442 BARs that wer 4038 BARs that weren't assigned by the BIOS.
4443 irqmask=0xMMMM [X86] Set a b 4039 irqmask=0xMMMM [X86] Set a bit mask of IRQs allowed to be
4444 assigned auto 4040 assigned automatically to PCI devices. You can
4445 make the kern 4041 make the kernel exclude IRQs of your ISA cards
4446 this way. 4042 this way.
4447 pirqaddr=0xAAAAA [X86] 4043 pirqaddr=0xAAAAA [X86] Specify the physical address
4448 of the PIRQ t 4044 of the PIRQ table (normally generated
4449 by the BIOS) 4045 by the BIOS) if it is outside the
4450 F0000h-100000 4046 F0000h-100000h range.
4451 lastbus=N [X86] Scan al 4047 lastbus=N [X86] Scan all buses thru bus #N. Can be
4452 useful if the 4048 useful if the kernel is unable to find your
4453 secondary bus 4049 secondary buses and you want to tell it
4454 explicitly wh 4050 explicitly which ones they are.
4455 assign-busses [X86] Always 4051 assign-busses [X86] Always assign all PCI bus
4456 numbers ourse 4052 numbers ourselves, overriding
4457 whatever the 4053 whatever the firmware may have done.
4458 usepirqmask [X86] Honor t 4054 usepirqmask [X86] Honor the possible IRQ mask stored
4459 in the BIOS $ 4055 in the BIOS $PIR table. This is needed on
4460 some systems 4056 some systems with broken BIOSes, notably
4461 some HP Pavil 4057 some HP Pavilion N5400 and Omnibook XE3
4462 notebooks. Th 4058 notebooks. This will have no effect if ACPI
4463 IRQ routing i 4059 IRQ routing is enabled.
4464 noacpi [X86] Do not 4060 noacpi [X86] Do not use ACPI for IRQ routing
4465 or for PCI sc 4061 or for PCI scanning.
4466 use_crs [X86] Use PCI 4062 use_crs [X86] Use PCI host bridge window information
4467 from ACPI. O 4063 from ACPI. On BIOSes from 2008 or later, this
4468 is enabled by 4064 is enabled by default. If you need to use this,
4469 please report 4065 please report a bug.
4470 nocrs [X86] Ignore 4066 nocrs [X86] Ignore PCI host bridge windows from ACPI.
4471 If you need t 4067 If you need to use this, please report a bug.
4472 use_e820 [X86] Use E82 <<
4473 PCI host brid <<
4474 for BIOS defe <<
4475 If you need t <<
4476 <linux-pci@vge <<
4477 no_e820 [X86] Ignore <<
4478 bridge window <<
4479 hardware. If <<
4480 a bug to <linu <<
4481 routeirq Do IRQ routin 4068 routeirq Do IRQ routing for all PCI devices.
4482 This is norma 4069 This is normally done in pci_enable_device(),
4483 so this optio 4070 so this option is a temporary workaround
4484 for broken dr 4071 for broken drivers that don't call it.
4485 skip_isa_align [X86] do not 4072 skip_isa_align [X86] do not align io start addr, so can
4486 handle more p 4073 handle more pci cards
4487 noearly [X86] Don't d 4074 noearly [X86] Don't do any early type 1 scanning.
4488 This might he 4075 This might help on some broken boards which
4489 machine check 4076 machine check when some devices' config space
4490 is read. But 4077 is read. But various workarounds are disabled
4491 and some IOMM 4078 and some IOMMU drivers will not work.
4492 bfsort Sort PCI devi 4079 bfsort Sort PCI devices into breadth-first order.
4493 This sorting 4080 This sorting is done to get a device
4494 order compati 4081 order compatible with older (<= 2.4) kernels.
4495 nobfsort Don't sort PC 4082 nobfsort Don't sort PCI devices into breadth-first order.
4496 pcie_bus_tune_off Disab 4083 pcie_bus_tune_off Disable PCIe MPS (Max Payload Size)
4497 tuning and us 4084 tuning and use the BIOS-configured MPS defaults.
4498 pcie_bus_safe Set every dev 4085 pcie_bus_safe Set every device's MPS to the largest value
4499 supported by 4086 supported by all devices below the root complex.
4500 pcie_bus_perf Set device MP 4087 pcie_bus_perf Set device MPS to the largest allowable MPS
4501 based on its 4088 based on its parent bus. Also set MRRS (Max
4502 Read Request 4089 Read Request Size) to the largest supported
4503 value (no lar 4090 value (no larger than the MPS that the device
4504 or bus can su 4091 or bus can support) for best performance.
4505 pcie_bus_peer2peer Set e 4092 pcie_bus_peer2peer Set every device's MPS to 128B, which
4506 every device 4093 every device is guaranteed to support. This
4507 configuration 4094 configuration allows peer-to-peer DMA between
4508 any pair of d 4095 any pair of devices, possibly at the cost of
4509 reduced perfo 4096 reduced performance. This also guarantees
4510 that hot-adde 4097 that hot-added devices will work.
4511 cbiosize=nn[KMG] The f 4098 cbiosize=nn[KMG] The fixed amount of bus space which is
4512 reserved for 4099 reserved for the CardBus bridge's IO window.
4513 The default v 4100 The default value is 256 bytes.
4514 cbmemsize=nn[KMG] The f 4101 cbmemsize=nn[KMG] The fixed amount of bus space which is
4515 reserved for 4102 reserved for the CardBus bridge's memory
4516 window. The d 4103 window. The default value is 64 megabytes.
4517 resource_alignment= 4104 resource_alignment=
4518 Format: 4105 Format:
4519 [<order of ali 4106 [<order of align>@]<pci_dev>[; ...]
4520 Specifies ali 4107 Specifies alignment and device to reassign
4521 aligned memor 4108 aligned memory resources. How to
4522 specify the d 4109 specify the device is described above.
4523 If <order of 4110 If <order of align> is not specified,
4524 PAGE_SIZE is 4111 PAGE_SIZE is used as alignment.
4525 A PCI-PCI bri 4112 A PCI-PCI bridge can be specified if resource
4526 windows need 4113 windows need to be expanded.
4527 To specify th 4114 To specify the alignment for several
4528 instances of 4115 instances of a device, the PCI vendor,
4529 device, subve 4116 device, subvendor, and subdevice may be
4530 specified, e. 4117 specified, e.g., 12@pci:8086:9c22:103c:198f
4531 for 4096-byte 4118 for 4096-byte alignment.
4532 ecrc= Enable/disabl 4119 ecrc= Enable/disable PCIe ECRC (transaction layer
4533 end-to-end CR !! 4120 end-to-end CRC checking).
4534 OS has native <<
4535 ACPI _OSC or <<
4536 bios: Use BIO 4121 bios: Use BIOS/firmware settings. This is the
4537 the default. 4122 the default.
4538 off: Turn ECR 4123 off: Turn ECRC off
4539 on: Turn ECRC 4124 on: Turn ECRC on.
4540 hpiosize=nn[KMG] The f 4125 hpiosize=nn[KMG] The fixed amount of bus space which is
4541 reserved for 4126 reserved for hotplug bridge's IO window.
4542 Default size 4127 Default size is 256 bytes.
4543 hpmmiosize=nn[KMG] The f 4128 hpmmiosize=nn[KMG] The fixed amount of bus space which is
4544 reserved for 4129 reserved for hotplug bridge's MMIO window.
4545 Default size 4130 Default size is 2 megabytes.
4546 hpmmioprefsize=nn[KMG] The f 4131 hpmmioprefsize=nn[KMG] The fixed amount of bus space which is
4547 reserved for 4132 reserved for hotplug bridge's MMIO_PREF window.
4548 Default size 4133 Default size is 2 megabytes.
4549 hpmemsize=nn[KMG] The f 4134 hpmemsize=nn[KMG] The fixed amount of bus space which is
4550 reserved for 4135 reserved for hotplug bridge's MMIO and
4551 MMIO_PREF win 4136 MMIO_PREF window.
4552 Default size 4137 Default size is 2 megabytes.
4553 hpbussize=nn The minimum a 4138 hpbussize=nn The minimum amount of additional bus numbers
4554 reserved for 4139 reserved for buses below a hotplug bridge.
4555 Default is 1. 4140 Default is 1.
4556 realloc= Enable/disabl 4141 realloc= Enable/disable reallocating PCI bridge resources
4557 if allocation 4142 if allocations done by BIOS are too small to
4558 accommodate r 4143 accommodate resources required by all child
4559 devices. 4144 devices.
4560 off: Turn rea 4145 off: Turn realloc off
4561 on: Turn real 4146 on: Turn realloc on
4562 realloc same as reall 4147 realloc same as realloc=on
4563 noari do not use PC 4148 noari do not use PCIe ARI.
4564 noats [PCIE, Intel- 4149 noats [PCIE, Intel-IOMMU, AMD-IOMMU]
4565 do not use PC 4150 do not use PCIe ATS (and IOMMU device IOTLB).
4566 pcie_scan_all Scan all poss 4151 pcie_scan_all Scan all possible PCIe devices. Otherwise we
4567 only look for 4152 only look for one device below a PCIe downstream
4568 port. 4153 port.
4569 big_root_window Try to add a 4154 big_root_window Try to add a big 64bit memory window to the PCIe
4570 root complex 4155 root complex on AMD CPUs. Some GFX hardware
4571 can resize a 4156 can resize a BAR to allow access to all VRAM.
4572 Adding the wi 4157 Adding the window is slightly risky (it may
4573 conflict with 4158 conflict with unreported devices), so this
4574 taints the ke 4159 taints the kernel.
4575 disable_acs_redir=<pci_dev>[; 4160 disable_acs_redir=<pci_dev>[; ...]
4576 Specify one o 4161 Specify one or more PCI devices (in the format
4577 specified abo 4162 specified above) separated by semicolons.
4578 Each device s 4163 Each device specified will have the PCI ACS
4579 redirect capa 4164 redirect capabilities forced off which will
4580 allow P2P tra 4165 allow P2P traffic between devices through
4581 bridges witho 4166 bridges without forcing it upstream. Note:
4582 this removes 4167 this removes isolation between devices and
4583 may put more 4168 may put more devices in an IOMMU group.
4584 config_acs= <<
4585 Format: <<
4586 <ACS flags>@<p <<
4587 Specify one o <<
4588 specified abo <<
4589 and separated <<
4590 capabilities <<
4591 unchanged bas <<
4592 flags. <<
4593 <<
4594 ACS Flags is <<
4595 bit-0 : ACS <<
4596 bit-1 : ACS <<
4597 bit-2 : ACS <<
4598 bit-3 : ACS <<
4599 bit-4 : ACS <<
4600 bit-5 : ACS <<
4601 bit-6 : ACS <<
4602 Each bit can <<
4603 '0' – for <<
4604 '1' – for <<
4605 'x' – unc <<
4606 For example, <<
4607 pci=config_ <<
4608 would configu <<
4609 ACS to enable <<
4610 Translation B <<
4611 Validation un <<
4612 or firmware s <<
4613 <<
4614 Note: this ma <<
4615 and may put m <<
4616 force_floating [S390] Force 4169 force_floating [S390] Force usage of floating interrupts.
4617 nomio [S390] Do not 4170 nomio [S390] Do not use MIO instructions.
4618 norid [S390] ignore 4171 norid [S390] ignore the RID field and force use of
4619 one PCI domai 4172 one PCI domain per PCI function
4620 4173
4621 pcie_aspm= [PCIE] Forcibly enabl !! 4174 pcie_aspm= [PCIE] Forcibly enable or disable PCIe Active State Power
4622 Management. 4175 Management.
4623 off Don't touch ASPM conf !! 4176 off Disable ASPM.
4624 configuration done by <<
4625 force Enable ASPM even on d 4177 force Enable ASPM even on devices that claim not to support it.
4626 WARNING: Forcing ASPM 4178 WARNING: Forcing ASPM on may cause system lockups.
4627 4179
4628 pcie_ports= [PCIE] PCIe port serv 4180 pcie_ports= [PCIE] PCIe port services handling:
4629 native Use native PCIe servi 4181 native Use native PCIe services (PME, AER, DPC, PCIe hotplug)
4630 even if the platform 4182 even if the platform doesn't give the OS permission to
4631 use them. This may c 4183 use them. This may cause conflicts if the platform
4632 also tries to use the 4184 also tries to use these services.
4633 dpc-native Use native PC 4185 dpc-native Use native PCIe service for DPC only. May
4634 cause conflic 4186 cause conflicts if firmware uses AER or DPC.
4635 compat Disable native PCIe s 4187 compat Disable native PCIe services (PME, AER, DPC, PCIe
4636 hotplug). 4188 hotplug).
4637 4189
4638 pcie_port_pm= [PCIE] PCIe port powe 4190 pcie_port_pm= [PCIE] PCIe port power management handling:
4639 off Disable power managem 4191 off Disable power management of all PCIe ports
4640 force Forcibly enable power 4192 force Forcibly enable power management of all PCIe ports
4641 4193
4642 pcie_pme= [PCIE,PM] Native PCIe 4194 pcie_pme= [PCIE,PM] Native PCIe PME signaling options:
4643 nomsi Do not use MSI for na 4195 nomsi Do not use MSI for native PCIe PME signaling (this makes
4644 all PCIe root ports u 4196 all PCIe root ports use INTx for all services).
4645 4197
4646 pcmv= [HW,PCMCIA] BadgePAD 4198 pcmv= [HW,PCMCIA] BadgePAD 4
4647 4199
4648 pd_ignore_unused 4200 pd_ignore_unused
4649 [PM] 4201 [PM]
4650 Keep all power-domain 4202 Keep all power-domains already enabled by bootloader on,
4651 even if no driver has 4203 even if no driver has claimed them. This is useful
4652 for debug and develop 4204 for debug and development, but should not be
4653 needed on a platform 4205 needed on a platform with proper driver support.
4654 4206
>> 4207 pd. [PARIDE]
>> 4208 See Documentation/admin-guide/blockdev/paride.rst.
>> 4209
4655 pdcchassis= [PARISC,HW] Disable/E 4210 pdcchassis= [PARISC,HW] Disable/Enable PDC Chassis Status codes at
4656 boot time. 4211 boot time.
4657 Format: { 0 | 1 } 4212 Format: { 0 | 1 }
4658 See arch/parisc/kerne 4213 See arch/parisc/kernel/pdc_chassis.c
4659 4214
4660 percpu_alloc= [MM,EARLY] !! 4215 percpu_alloc= Select which percpu first chunk allocator to use.
4661 Select which percpu f <<
4662 Currently supported v 4216 Currently supported values are "embed" and "page".
4663 Archs may support sub 4217 Archs may support subset or none of the selections.
4664 See comments in mm/pe 4218 See comments in mm/percpu.c for details on each
4665 allocator. This para 4219 allocator. This parameter is primarily for debugging
4666 and performance compa 4220 and performance comparison.
4667 4221
>> 4222 pf. [PARIDE]
>> 4223 See Documentation/admin-guide/blockdev/paride.rst.
>> 4224
>> 4225 pg. [PARIDE]
>> 4226 See Documentation/admin-guide/blockdev/paride.rst.
>> 4227
4668 pirq= [SMP,APIC] Manual mp- 4228 pirq= [SMP,APIC] Manual mp-table setup
4669 See Documentation/arc !! 4229 See Documentation/x86/i386/IO-APIC.rst.
4670 4230
4671 plip= [PPT,NET] Parallel po 4231 plip= [PPT,NET] Parallel port network link
4672 Format: { parport<nr> 4232 Format: { parport<nr> | timid | 0 }
4673 See also Documentatio 4233 See also Documentation/admin-guide/parport.rst.
4674 4234
4675 pmtmr= [X86] Manual setup of 4235 pmtmr= [X86] Manual setup of pmtmr I/O Port.
4676 Override pmtimer IOPo 4236 Override pmtimer IOPort with a hex value.
4677 e.g. pmtmr=0x508 4237 e.g. pmtmr=0x508
4678 4238
4679 pmu_override= [PPC] Override the PM <<
4680 This option takes ove <<
4681 longer usable by perf <<
4682 PMU counters by setti <<
4683 cleared). If a number <<
4684 that number, otherwis <<
4685 remains 0. <<
4686 <<
4687 pm_debug_messages [SUSPEND,KNL] 4239 pm_debug_messages [SUSPEND,KNL]
4688 Enable suspend/resume 4240 Enable suspend/resume debug messages during boot up.
4689 4241
4690 pnp.debug=1 [PNP] 4242 pnp.debug=1 [PNP]
4691 Enable PNP debug mess 4243 Enable PNP debug messages (depends on the
4692 CONFIG_PNP_DEBUG_MESS 4244 CONFIG_PNP_DEBUG_MESSAGES option). Change at run-time
4693 via /sys/module/pnp/p 4245 via /sys/module/pnp/parameters/debug. We always show
4694 current resource usag 4246 current resource usage; turning this on also shows
4695 possible settings and 4247 possible settings and some assignment information.
4696 4248
4697 pnpacpi= [ACPI] 4249 pnpacpi= [ACPI]
4698 { off } 4250 { off }
4699 4251
4700 pnpbios= [ISAPNP] 4252 pnpbios= [ISAPNP]
4701 { on | off | curr | r 4253 { on | off | curr | res | no-curr | no-res }
4702 4254
4703 pnp_reserve_irq= 4255 pnp_reserve_irq=
4704 [ISAPNP] Exclude IRQs 4256 [ISAPNP] Exclude IRQs for the autoconfiguration
4705 4257
4706 pnp_reserve_dma= 4258 pnp_reserve_dma=
4707 [ISAPNP] Exclude DMAs 4259 [ISAPNP] Exclude DMAs for the autoconfiguration
4708 4260
4709 pnp_reserve_io= [ISAPNP] Exclude I/O 4261 pnp_reserve_io= [ISAPNP] Exclude I/O ports for the autoconfiguration
4710 Ranges are in pairs ( 4262 Ranges are in pairs (I/O port base and size).
4711 4263
4712 pnp_reserve_mem= 4264 pnp_reserve_mem=
4713 [ISAPNP] Exclude memo 4265 [ISAPNP] Exclude memory regions for the
4714 autoconfiguration. 4266 autoconfiguration.
4715 Ranges are in pairs ( 4267 Ranges are in pairs (memory base and size).
4716 4268
4717 ports= [IP_VS_FTP] IPVS ftp 4269 ports= [IP_VS_FTP] IPVS ftp helper module
4718 Default is 21. 4270 Default is 21.
4719 Up to 8 (IP_VS_APP_MA 4271 Up to 8 (IP_VS_APP_MAX_PORTS) ports
4720 may be specified. 4272 may be specified.
4721 Format: <port>,<port> 4273 Format: <port>,<port>....
4722 4274
4723 possible_cpus= [SMP,S390,X86] <<
4724 Format: <unsigned int <<
4725 Set the number of pos <<
4726 regular discovery mec <<
4727 <<
4728 powersave=off [PPC] This option dis 4275 powersave=off [PPC] This option disables power saving features.
4729 It specifically disab 4276 It specifically disables cpuidle and sets the
4730 platform machine desc 4277 platform machine description specific power_save
4731 function to NULL. On 4278 function to NULL. On Idle the CPU just reduces
4732 execution priority. 4279 execution priority.
4733 4280
4734 ppc_strict_facility_enable 4281 ppc_strict_facility_enable
4735 [PPC,ENABLE] This opt !! 4282 [PPC] This option catches any kernel floating point,
4736 Altivec, VSX and SPE 4283 Altivec, VSX and SPE outside of regions specifically
4737 allowed (eg kernel_en 4284 allowed (eg kernel_enable_fpu()/kernel_disable_fpu()).
4738 There is some perform 4285 There is some performance impact when enabling this.
4739 4286
4740 ppc_tm= [PPC,EARLY] !! 4287 ppc_tm= [PPC]
4741 Format: {"off"} 4288 Format: {"off"}
4742 Disable Hardware Tran 4289 Disable Hardware Transactional Memory
4743 4290
4744 preempt= [KNL] 4291 preempt= [KNL]
4745 Select preemption mod 4292 Select preemption mode if you have CONFIG_PREEMPT_DYNAMIC
4746 none - Limited to con 4293 none - Limited to cond_resched() calls
4747 voluntary - Limited t 4294 voluntary - Limited to cond_resched() and might_sleep() calls
4748 full - Any section th 4295 full - Any section that isn't explicitly preempt disabled
4749 can be preempt !! 4296 can be preempted anytime.
4750 contended spin <<
4751 explicitly pre <<
4752 4297
4753 print-fatal-signals= 4298 print-fatal-signals=
4754 [KNL] debug: print fa 4299 [KNL] debug: print fatal signals
4755 4300
4756 If enabled, warn abou 4301 If enabled, warn about various signal handling
4757 related application a 4302 related application anomalies: too many signals,
4758 too many POSIX.1 time 4303 too many POSIX.1 timers, fatal signals causing a
4759 coredump - etc. 4304 coredump - etc.
4760 4305
4761 If you hit the warnin 4306 If you hit the warning due to signal overflow,
4762 you might want to try 4307 you might want to try "ulimit -i unlimited".
4763 4308
4764 default: off. 4309 default: off.
4765 4310
4766 printk.always_kmsg_dump= 4311 printk.always_kmsg_dump=
4767 Trigger kmsg_dump for 4312 Trigger kmsg_dump for cases other than kernel oops or
4768 panics 4313 panics
4769 Format: <bool> (1/Y/ 4314 Format: <bool> (1/Y/y=enable, 0/N/n=disable)
4770 default: disabled 4315 default: disabled
4771 4316
4772 printk.console_no_auto_verbose= 4317 printk.console_no_auto_verbose=
4773 Disable console logle 4318 Disable console loglevel raise on oops, panic
4774 or lockdep-detected i 4319 or lockdep-detected issues (only if lock debug is on).
4775 With an exception to 4320 With an exception to setups with low baudrate on
4776 serial console, keepi 4321 serial console, keeping this 0 is a good choice
4777 in order to provide m 4322 in order to provide more debug information.
4778 Format: <bool> 4323 Format: <bool>
4779 default: 0 (auto_verb 4324 default: 0 (auto_verbose is enabled)
4780 4325
4781 printk.devkmsg={on,off,ratelimit} 4326 printk.devkmsg={on,off,ratelimit}
4782 Control writing to /d 4327 Control writing to /dev/kmsg.
4783 on - unlimited loggin 4328 on - unlimited logging to /dev/kmsg from userspace
4784 off - logging to /dev 4329 off - logging to /dev/kmsg disabled
4785 ratelimit - ratelimit 4330 ratelimit - ratelimit the logging
4786 Default: ratelimit 4331 Default: ratelimit
4787 4332
4788 printk.time= Show timing data pref 4333 printk.time= Show timing data prefixed to each printk message line
4789 Format: <bool> (1/Y/ 4334 Format: <bool> (1/Y/y=enable, 0/N/n=disable)
4790 4335
4791 proc_mem.force_override= [KNL] 4336 proc_mem.force_override= [KNL]
4792 Format: {always | ptr 4337 Format: {always | ptrace | never}
4793 Traditionally /proc/p 4338 Traditionally /proc/pid/mem allows memory permissions to be
4794 overridden without re 4339 overridden without restrictions. This option may be set to
4795 restrict that. Can be 4340 restrict that. Can be one of:
4796 - 'always': tradition 4341 - 'always': traditional behavior always allows mem overrides.
4797 - 'ptrace': only allo 4342 - 'ptrace': only allow mem overrides for active ptracers.
4798 - 'never': never all 4343 - 'never': never allow mem overrides.
4799 If not specified, def 4344 If not specified, default is the CONFIG_PROC_MEM_* choice.
4800 4345
4801 processor.max_cstate= [HW,ACPI] 4346 processor.max_cstate= [HW,ACPI]
4802 Limit processor to ma 4347 Limit processor to maximum C-state
4803 max_cstate=9 override 4348 max_cstate=9 overrides any DMI blacklist limit.
4804 4349
4805 processor.nocst [HW,ACPI] 4350 processor.nocst [HW,ACPI]
4806 Ignore the _CST metho 4351 Ignore the _CST method to determine C-states,
4807 instead using the leg 4352 instead using the legacy FADT method
4808 4353
4809 profile= [KNL] Enable kernel p 4354 profile= [KNL] Enable kernel profiling via /proc/profile
4810 Format: [<profiletype 4355 Format: [<profiletype>,]<number>
4811 Param: <profiletype>: 4356 Param: <profiletype>: "schedule" or "kvm"
4812 [defaults to 4357 [defaults to kernel profiling]
4813 Param: "schedule" - p 4358 Param: "schedule" - profile schedule points.
4814 Param: "kvm" - profil 4359 Param: "kvm" - profile VM exits.
4815 Param: <number> - ste 4360 Param: <number> - step/bucket size as a power of 2 for
4816 statistical t 4361 statistical time based profiling.
4817 4362
4818 prompt_ramdisk= [RAM] [Deprecated] 4363 prompt_ramdisk= [RAM] [Deprecated]
4819 4364
4820 prot_virt= [S390] enable hosting 4365 prot_virt= [S390] enable hosting protected virtual machines
4821 isolated from the hyp 4366 isolated from the hypervisor (if hardware supports
4822 that). If enabled, th !! 4367 that).
4823 might be overridden e <<
4824 Layout Randomization <<
4825 Format: <bool> 4368 Format: <bool>
4826 4369
4827 psi= [KNL] Enable or disab 4370 psi= [KNL] Enable or disable pressure stall information
4828 tracking. 4371 tracking.
4829 Format: <bool> 4372 Format: <bool>
4830 4373
4831 psmouse.proto= [HW,MOUSE] Highest PS 4374 psmouse.proto= [HW,MOUSE] Highest PS2 mouse protocol extension to
4832 probe for; one of (ba 4375 probe for; one of (bare|imps|exps|lifebook|any).
4833 psmouse.rate= [HW,MOUSE] Set desire 4376 psmouse.rate= [HW,MOUSE] Set desired mouse report rate, in reports
4834 per second. 4377 per second.
4835 psmouse.resetafter= [HW,MOUSE] 4378 psmouse.resetafter= [HW,MOUSE]
4836 Try to reset the devi 4379 Try to reset the device after so many bad packets
4837 (0 = never). 4380 (0 = never).
4838 psmouse.resolution= 4381 psmouse.resolution=
4839 [HW,MOUSE] Set desire 4382 [HW,MOUSE] Set desired mouse resolution, in dpi.
4840 psmouse.smartscroll= 4383 psmouse.smartscroll=
4841 [HW,MOUSE] Controls L 4384 [HW,MOUSE] Controls Logitech smartscroll autorepeat.
4842 0 = disabled, 1 = ena 4385 0 = disabled, 1 = enabled (default).
4843 4386
4844 pstore.backend= Specify the name of t 4387 pstore.backend= Specify the name of the pstore backend to use
4845 4388
>> 4389 pt. [PARIDE]
>> 4390 See Documentation/admin-guide/blockdev/paride.rst.
>> 4391
4846 pti= [X86-64] Control Page 4392 pti= [X86-64] Control Page Table Isolation of user and
4847 kernel address spaces 4393 kernel address spaces. Disabling this feature
4848 removes hardening, bu 4394 removes hardening, but improves performance of
4849 system calls and inte 4395 system calls and interrupts.
4850 4396
4851 on - unconditionall 4397 on - unconditionally enable
4852 off - unconditionall 4398 off - unconditionally disable
4853 auto - kernel detects 4399 auto - kernel detects whether your CPU model is
4854 vulnerable to 4400 vulnerable to issues that PTI mitigates
4855 4401
4856 Not specifying this o 4402 Not specifying this option is equivalent to pti=auto.
4857 4403
>> 4404 nopti [X86-64]
>> 4405 Equivalent to pti=off
>> 4406
4858 pty.legacy_count= 4407 pty.legacy_count=
4859 [KNL] Number of legac 4408 [KNL] Number of legacy pty's. Overwrites compiled-in
4860 default number. 4409 default number.
4861 4410
4862 quiet [KNL,EARLY] Disable m !! 4411 quiet [KNL] Disable most log messages
4863 4412
4864 r128= [HW,DRM] 4413 r128= [HW,DRM]
4865 4414
4866 radix_hcall_invalidate=on [PPC/PSERI <<
4867 Disable RADIX GTSE fe <<
4868 invalidate. <<
4869 <<
4870 raid= [HW,RAID] 4415 raid= [HW,RAID]
4871 See Documentation/adm 4416 See Documentation/admin-guide/md.rst.
4872 4417
4873 ramdisk_size= [RAM] Sizes of RAM di 4418 ramdisk_size= [RAM] Sizes of RAM disks in kilobytes
4874 See Documentation/adm 4419 See Documentation/admin-guide/blockdev/ramdisk.rst.
4875 4420
4876 ramdisk_start= [RAM] RAM disk image 4421 ramdisk_start= [RAM] RAM disk image start address
4877 4422
4878 random.trust_cpu=off !! 4423 random.trust_cpu={on,off}
4879 [KNL,EARLY] Disable t !! 4424 [KNL] Enable or disable trusting the use of the
4880 random number generat !! 4425 CPU's random number generator (if available) to
4881 initialize the kernel !! 4426 fully seed the kernel's CRNG. Default is controlled
4882 !! 4427 by CONFIG_RANDOM_TRUST_CPU.
4883 random.trust_bootloader=off !! 4428
4884 [KNL,EARLY] Disable t !! 4429 random.trust_bootloader={on,off}
4885 passed by the bootloa !! 4430 [KNL] Enable or disable trusting the use of a
4886 initialize the kernel !! 4431 seed passed by the bootloader (if available) to
>> 4432 fully seed the kernel's CRNG. Default is controlled
>> 4433 by CONFIG_RANDOM_TRUST_BOOTLOADER.
4887 4434
4888 randomize_kstack_offset= 4435 randomize_kstack_offset=
4889 [KNL,EARLY] Enable or !! 4436 [KNL] Enable or disable kernel stack offset
4890 randomization, which 4437 randomization, which provides roughly 5 bits of
4891 entropy, frustrating 4438 entropy, frustrating memory corruption attacks
4892 that depend on stack 4439 that depend on stack address determinism or
4893 cross-syscall address 4440 cross-syscall address exposures. This is only
4894 available on architec 4441 available on architectures that have defined
4895 CONFIG_HAVE_ARCH_RAND 4442 CONFIG_HAVE_ARCH_RANDOMIZE_KSTACK_OFFSET.
4896 Format: <bool> (1/Y/ 4443 Format: <bool> (1/Y/y=enable, 0/N/n=disable)
4897 Default is CONFIG_RAN 4444 Default is CONFIG_RANDOMIZE_KSTACK_OFFSET_DEFAULT.
4898 4445
4899 ras=option[,option,...] [KNL] RAS-spe 4446 ras=option[,option,...] [KNL] RAS-specific options
4900 4447
4901 cec_disable [X86] 4448 cec_disable [X86]
4902 Disable the C 4449 Disable the Correctable Errors Collector,
4903 see CONFIG_RA 4450 see CONFIG_RAS_CEC help text.
4904 4451
4905 rcu_nocbs[=cpu-list] !! 4452 rcu_nocbs= [KNL]
4906 [KNL] The optional ar !! 4453 The argument is a cpu list, as described above.
4907 as described above. <<
4908 <<
4909 In kernels built with <<
4910 enable the no-callbac <<
4911 such CPUs' callbacks <<
4912 softirq context. Inv <<
4913 callbacks will instea <<
4914 kthreads created for <<
4915 "p" for RCU-preempt, <<
4916 for the kthreads that <<
4917 "N" is the CPU number <<
4918 the offloaded CPUs, w <<
4919 and real-time workloa <<
4920 energy efficiency for <<
4921 <<
4922 If a cpulist is passe <<
4923 list of CPUs is set t <<
4924 <<
4925 Otherwise, if the '=' <<
4926 arguments are omitted <<
4927 no-callback mode from <<
4928 toggled at runtime vi <<
4929 4454
4930 Note that this argume !! 4455 In kernels built with CONFIG_RCU_NOCB_CPU=y, set
4931 the CONFIG_RCU_NOCB_C !! 4456 the specified list of CPUs to be no-callback CPUs.
>> 4457 Invocation of these CPUs' RCU callbacks will be
>> 4458 offloaded to "rcuox/N" kthreads created for that
>> 4459 purpose, where "x" is "p" for RCU-preempt, and
>> 4460 "s" for RCU-sched, and "N" is the CPU number.
>> 4461 This reduces OS jitter on the offloaded CPUs,
>> 4462 which can be useful for HPC and real-time
>> 4463 workloads. It can also improve energy efficiency
>> 4464 for asymmetric multiprocessors.
4932 4465
4933 rcu_nocb_poll [KNL] 4466 rcu_nocb_poll [KNL]
4934 Rather than requiring 4467 Rather than requiring that offloaded CPUs
4935 (specified by rcu_noc 4468 (specified by rcu_nocbs= above) explicitly
4936 awaken the correspond 4469 awaken the corresponding "rcuoN" kthreads,
4937 make these kthreads p 4470 make these kthreads poll for callbacks.
4938 This improves the rea 4471 This improves the real-time response for the
4939 offloaded CPUs by rel 4472 offloaded CPUs by relieving them of the need to
4940 wake up the correspon 4473 wake up the corresponding kthread, but degrades
4941 energy efficiency by 4474 energy efficiency by requiring that the kthreads
4942 periodically wake up 4475 periodically wake up to do the polling.
4943 4476
4944 rcutree.blimit= [KNL] 4477 rcutree.blimit= [KNL]
4945 Set maximum number of 4478 Set maximum number of finished RCU callbacks to
4946 process in one batch. 4479 process in one batch.
4947 4480
4948 rcutree.do_rcu_barrier= [KNL] <<
4949 Request a call to rcu <<
4950 throttled so that use <<
4951 hammer on the sysfs v <<
4952 If triggered before t <<
4953 is fully active, this <<
4954 <<
4955 rcutree.dump_tree= [KNL] 4481 rcutree.dump_tree= [KNL]
4956 Dump the structure of 4482 Dump the structure of the rcu_node combining tree
4957 out at early boot. T 4483 out at early boot. This is used for diagnostic
4958 purposes, to verify c 4484 purposes, to verify correct tree setup.
4959 4485
4960 rcutree.gp_cleanup_delay= [KNL] 4486 rcutree.gp_cleanup_delay= [KNL]
4961 Set the number of jif 4487 Set the number of jiffies to delay each step of
4962 RCU grace-period clea 4488 RCU grace-period cleanup.
4963 4489
4964 rcutree.gp_init_delay= [KNL] 4490 rcutree.gp_init_delay= [KNL]
4965 Set the number of jif 4491 Set the number of jiffies to delay each step of
4966 RCU grace-period init 4492 RCU grace-period initialization.
4967 4493
4968 rcutree.gp_preinit_delay= [KNL] 4494 rcutree.gp_preinit_delay= [KNL]
4969 Set the number of jif 4495 Set the number of jiffies to delay each step of
4970 RCU grace-period pre- 4496 RCU grace-period pre-initialization, that is,
4971 the propagation of re 4497 the propagation of recent CPU-hotplug changes up
4972 the rcu_node combinin 4498 the rcu_node combining tree.
4973 4499
>> 4500 rcutree.use_softirq= [KNL]
>> 4501 If set to zero, move all RCU_SOFTIRQ processing to
>> 4502 per-CPU rcuc kthreads. Defaults to a non-zero
>> 4503 value, meaning that RCU_SOFTIRQ is used by default.
>> 4504 Specify rcutree.use_softirq=0 to use rcuc kthreads.
>> 4505
>> 4506 But note that CONFIG_PREEMPT_RT=y kernels disable
>> 4507 this kernel boot parameter, forcibly setting it
>> 4508 to zero.
>> 4509
>> 4510 rcutree.rcu_fanout_exact= [KNL]
>> 4511 Disable autobalancing of the rcu_node combining
>> 4512 tree. This is used by rcutorture, and might
>> 4513 possibly be useful for architectures having high
>> 4514 cache-to-cache transfer latencies.
>> 4515
>> 4516 rcutree.rcu_fanout_leaf= [KNL]
>> 4517 Change the number of CPUs assigned to each
>> 4518 leaf rcu_node structure. Useful for very
>> 4519 large systems, which will choose the value 64,
>> 4520 and for NUMA systems with large remote-access
>> 4521 latencies, which will choose a value aligned
>> 4522 with the appropriate hardware boundaries.
>> 4523
>> 4524 rcutree.rcu_min_cached_objs= [KNL]
>> 4525 Minimum number of objects which are cached and
>> 4526 maintained per one CPU. Object size is equal
>> 4527 to PAGE_SIZE. The cache allows to reduce the
>> 4528 pressure to page allocator, also it makes the
>> 4529 whole algorithm to behave better in low memory
>> 4530 condition.
>> 4531
>> 4532 rcutree.rcu_delay_page_cache_fill_msec= [KNL]
>> 4533 Set the page-cache refill delay (in milliseconds)
>> 4534 in response to low-memory conditions. The range
>> 4535 of permitted values is in the range 0:100000.
>> 4536
4974 rcutree.jiffies_till_first_fqs= [KNL] 4537 rcutree.jiffies_till_first_fqs= [KNL]
4975 Set delay from grace- 4538 Set delay from grace-period initialization to
4976 first attempt to forc 4539 first attempt to force quiescent states.
4977 Units are jiffies, mi 4540 Units are jiffies, minimum value is zero,
4978 and maximum value is 4541 and maximum value is HZ.
4979 4542
4980 rcutree.jiffies_till_next_fqs= [KNL] 4543 rcutree.jiffies_till_next_fqs= [KNL]
4981 Set delay between sub 4544 Set delay between subsequent attempts to force
4982 quiescent states. Un 4545 quiescent states. Units are jiffies, minimum
4983 value is one, and max 4546 value is one, and maximum value is HZ.
4984 4547
4985 rcutree.jiffies_till_sched_qs= [KNL] 4548 rcutree.jiffies_till_sched_qs= [KNL]
4986 Set required age in j 4549 Set required age in jiffies for a
4987 given grace period be 4550 given grace period before RCU starts
4988 soliciting quiescent- 4551 soliciting quiescent-state help from
4989 rcu_note_context_swit 4552 rcu_note_context_switch() and cond_resched().
4990 If not specified, the 4553 If not specified, the kernel will calculate
4991 a value based on the 4554 a value based on the most recent settings
4992 of rcutree.jiffies_ti 4555 of rcutree.jiffies_till_first_fqs
4993 and rcutree.jiffies_t 4556 and rcutree.jiffies_till_next_fqs.
4994 This calculated value 4557 This calculated value may be viewed in
4995 rcutree.jiffies_to_sc 4558 rcutree.jiffies_to_sched_qs. Any attempt to set
4996 rcutree.jiffies_to_sc 4559 rcutree.jiffies_to_sched_qs will be cheerfully
4997 overwritten. 4560 overwritten.
4998 4561
4999 rcutree.kthread_prio= [KNL,BOOT] 4562 rcutree.kthread_prio= [KNL,BOOT]
5000 Set the SCHED_FIFO pr 4563 Set the SCHED_FIFO priority of the RCU per-CPU
5001 kthreads (rcuc/N). Th 4564 kthreads (rcuc/N). This value is also used for
5002 the priority of the R 4565 the priority of the RCU boost threads (rcub/N)
5003 and for the RCU grace 4566 and for the RCU grace-period kthreads (rcu_bh,
5004 rcu_preempt, and rcu_ 4567 rcu_preempt, and rcu_sched). If RCU_BOOST is
5005 set, valid values are 4568 set, valid values are 1-99 and the default is 1
5006 (the least-favored pr 4569 (the least-favored priority). Otherwise, when
5007 RCU_BOOST is not set, 4570 RCU_BOOST is not set, valid values are 0-99 and
5008 the default is zero ( 4571 the default is zero (non-realtime operation).
5009 When RCU_NOCB_CPU is <<
5010 priority of NOCB call <<
5011 4572
5012 rcutree.nocb_nobypass_lim_per_jiffy= !! 4573 rcutree.rcu_nocb_gp_stride= [KNL]
5013 On callback-offloaded !! 4574 Set the number of NOCB callback kthreads in
5014 RCU reduces the lock !! 4575 each group, which defaults to the square root
5015 otherwise be caused b !! 4576 of the number of CPUs. Larger numbers reduce
5016 use of the ->nocb_byp !! 4577 the wakeup overhead on the global grace-period
5017 common non-flooded ca !! 4578 kthread, but increases that same overhead on
5018 the main ->cblist in !! 4579 each group's NOCB grace-period kthread.
5019 overhead of the ->noc <<
5020 But if there are too <<
5021 a single jiffy, RCU p <<
5022 the ->nocb_bypass que <<
5023 many" is supplied by <<
5024 <<
5025 rcutree.nohz_full_patience_delay= [KN <<
5026 On callback-offloaded <<
5027 disturbing RCU unless <<
5028 reached the specified <<
5029 Defaults to zero. La <<
5030 at five seconds. All <<
5031 to the nearest value <<
5032 4580
5033 rcutree.qhimark= [KNL] 4581 rcutree.qhimark= [KNL]
5034 Set threshold of queu 4582 Set threshold of queued RCU callbacks beyond which
5035 batch limiting is dis 4583 batch limiting is disabled.
5036 4584
5037 rcutree.qlowmark= [KNL] 4585 rcutree.qlowmark= [KNL]
5038 Set threshold of queu 4586 Set threshold of queued RCU callbacks below which
5039 batch limiting is re- 4587 batch limiting is re-enabled.
5040 4588
5041 rcutree.qovld= [KNL] 4589 rcutree.qovld= [KNL]
5042 Set threshold of queu 4590 Set threshold of queued RCU callbacks beyond which
5043 RCU's force-quiescent 4591 RCU's force-quiescent-state scan will aggressively
5044 enlist help from cond 4592 enlist help from cond_resched() and sched IPIs to
5045 help CPUs more quickl 4593 help CPUs more quickly reach quiescent states.
5046 Set to less than zero 4594 Set to less than zero to make this be set based
5047 on rcutree.qhimark at 4595 on rcutree.qhimark at boot time and to zero to
5048 disable more aggressi 4596 disable more aggressive help enlistment.
5049 4597
5050 rcutree.rcu_delay_page_cache_fill_mse !! 4598 rcutree.rcu_idle_gp_delay= [KNL]
5051 Set the page-cache re !! 4599 Set wakeup interval for idle CPUs that have
5052 in response to low-me !! 4600 RCU callbacks (RCU_FAST_NO_HZ=y).
5053 of permitted values i <<
5054 <<
5055 rcutree.rcu_divisor= [KNL] <<
5056 Set the shift-right c <<
5057 the callback-invocati <<
5058 the number of callbac <<
5059 The result will be bo <<
5060 the rcutree.blimit ke <<
5061 callbacks, the softir <<
5062 order to allow the CP <<
5063 <<
5064 Please note that this <<
5065 limit applies only to <<
5066 invocation. Offloade <<
5067 invoked in the contex <<
5068 scheduler will preemp <<
5069 <<
5070 rcutree.rcu_fanout_exact= [KNL] <<
5071 Disable autobalancing <<
5072 tree. This is used b <<
5073 possibly be useful fo <<
5074 cache-to-cache transf <<
5075 <<
5076 rcutree.rcu_fanout_leaf= [KNL] <<
5077 Change the number of <<
5078 leaf rcu_node structu <<
5079 large systems, which <<
5080 and for NUMA systems <<
5081 latencies, which will <<
5082 with the appropriate <<
5083 <<
5084 rcutree.rcu_min_cached_objs= [KNL] <<
5085 Minimum number of obj <<
5086 maintained per one CP <<
5087 to PAGE_SIZE. The cac <<
5088 pressure to page allo <<
5089 whole algorithm to be <<
5090 condition. <<
5091 <<
5092 rcutree.rcu_nocb_gp_stride= [KNL] <<
5093 Set the number of NOC <<
5094 each group, which def <<
5095 of the number of CPUs <<
5096 the wakeup overhead o <<
5097 kthread, but increase <<
5098 each group's NOCB gra <<
5099 4601
5100 rcutree.rcu_kick_kthreads= [KNL] 4602 rcutree.rcu_kick_kthreads= [KNL]
5101 Cause the grace-perio 4603 Cause the grace-period kthread to get an extra
5102 wake_up() if it sleep 4604 wake_up() if it sleeps three times longer than
5103 it should at force-qu 4605 it should at force-quiescent-state time.
5104 This wake_up() will b 4606 This wake_up() will be accompanied by a
5105 WARN_ONCE() splat and 4607 WARN_ONCE() splat and an ftrace_dump().
5106 4608
5107 rcutree.rcu_resched_ns= [KNL] <<
5108 Limit the time spend <<
5109 callbacks to the spec <<
5110 By default, this limi <<
5111 every 32 callbacks in <<
5112 inflicted by local_cl <<
5113 <<
5114 rcutree.rcu_unlock_delay= [KNL] 4609 rcutree.rcu_unlock_delay= [KNL]
5115 In CONFIG_RCU_STRICT_ 4610 In CONFIG_RCU_STRICT_GRACE_PERIOD=y kernels,
5116 this specifies an rcu 4611 this specifies an rcu_read_unlock()-time delay
5117 in microseconds. Thi 4612 in microseconds. This defaults to zero.
5118 Larger delays increas 4613 Larger delays increase the probability of
5119 catching RCU pointer 4614 catching RCU pointer leaks, that is, buggy use
5120 of RCU-protected poin 4615 of RCU-protected pointers after the relevant
5121 rcu_read_unlock() has 4616 rcu_read_unlock() has completed.
5122 4617
5123 rcutree.sysrq_rcu= [KNL] 4618 rcutree.sysrq_rcu= [KNL]
5124 Commandeer a sysrq ke 4619 Commandeer a sysrq key to dump out Tree RCU's
5125 rcu_node tree with an 4620 rcu_node tree with an eye towards determining
5126 why a new grace perio 4621 why a new grace period has not yet started.
5127 4622
5128 rcutree.use_softirq= [KNL] <<
5129 If set to zero, move <<
5130 per-CPU rcuc kthreads <<
5131 value, meaning that R <<
5132 Specify rcutree.use_s <<
5133 <<
5134 But note that CONFIG_ <<
5135 this kernel boot para <<
5136 to zero. <<
5137 <<
5138 rcutree.enable_rcu_lazy= [KNL] <<
5139 To save power, batch <<
5140 delay, memory pressur <<
5141 big. <<
5142 <<
5143 rcutree.rcu_normal_wake_from_gp= [KNL <<
5144 Reduces a latency of <<
5145 maintains its own tra <<
5146 does not interact wit <<
5147 use a call_rcu[_hurry <<
5148 normal grace period. <<
5149 <<
5150 How to enable it: <<
5151 <<
5152 echo 1 > /sys/module/ <<
5153 or pass a boot parame <<
5154 <<
5155 Default is 0. <<
5156 <<
5157 rcuscale.gp_async= [KNL] 4623 rcuscale.gp_async= [KNL]
5158 Measure performance o 4624 Measure performance of asynchronous
5159 grace-period primitiv 4625 grace-period primitives such as call_rcu().
5160 4626
5161 rcuscale.gp_async_max= [KNL] 4627 rcuscale.gp_async_max= [KNL]
5162 Specify the maximum n 4628 Specify the maximum number of outstanding
5163 callbacks per writer 4629 callbacks per writer thread. When a writer
5164 thread exceeds this l 4630 thread exceeds this limit, it invokes the
5165 corresponding flavor 4631 corresponding flavor of rcu_barrier() to allow
5166 previously posted cal 4632 previously posted callbacks to drain.
5167 4633
5168 rcuscale.gp_exp= [KNL] 4634 rcuscale.gp_exp= [KNL]
5169 Measure performance o 4635 Measure performance of expedited synchronous
5170 grace-period primitiv 4636 grace-period primitives.
5171 4637
5172 rcuscale.holdoff= [KNL] 4638 rcuscale.holdoff= [KNL]
5173 Set test-start holdof 4639 Set test-start holdoff period. The purpose of
5174 this parameter is to 4640 this parameter is to delay the start of the
5175 test until boot compl 4641 test until boot completes in order to avoid
5176 interference. 4642 interference.
5177 4643
5178 rcuscale.kfree_by_call_rcu= [KNL] <<
5179 In kernels built with <<
5180 call_rcu() instead of <<
5181 <<
5182 rcuscale.kfree_mult= [KNL] <<
5183 Instead of allocating <<
5184 allocate one of kfree <<
5185 Defaults to 1. <<
5186 <<
5187 rcuscale.kfree_rcu_test= [KNL] 4644 rcuscale.kfree_rcu_test= [KNL]
5188 Set to measure perfor 4645 Set to measure performance of kfree_rcu() flooding.
5189 4646
5190 rcuscale.kfree_rcu_test_double= [KNL] 4647 rcuscale.kfree_rcu_test_double= [KNL]
5191 Test the double-argum 4648 Test the double-argument variant of kfree_rcu().
5192 If this parameter has 4649 If this parameter has the same value as
5193 rcuscale.kfree_rcu_te 4650 rcuscale.kfree_rcu_test_single, both the single-
5194 and double-argument v 4651 and double-argument variants are tested.
5195 4652
5196 rcuscale.kfree_rcu_test_single= [KNL] 4653 rcuscale.kfree_rcu_test_single= [KNL]
5197 Test the single-argum 4654 Test the single-argument variant of kfree_rcu().
5198 If this parameter has 4655 If this parameter has the same value as
5199 rcuscale.kfree_rcu_te 4656 rcuscale.kfree_rcu_test_double, both the single-
5200 and double-argument v 4657 and double-argument variants are tested.
5201 4658
5202 rcuscale.kfree_nthreads= [KNL] 4659 rcuscale.kfree_nthreads= [KNL]
5203 The number of threads 4660 The number of threads running loops of kfree_rcu().
5204 4661
5205 rcuscale.kfree_alloc_num= [KNL] 4662 rcuscale.kfree_alloc_num= [KNL]
5206 Number of allocations 4663 Number of allocations and frees done in an iteration.
5207 4664
5208 rcuscale.kfree_loops= [KNL] 4665 rcuscale.kfree_loops= [KNL]
5209 Number of loops doing 4666 Number of loops doing rcuscale.kfree_alloc_num number
5210 of allocations and fr 4667 of allocations and frees.
5211 4668
5212 rcuscale.minruntime= [KNL] <<
5213 Set the minimum test <<
5214 does not affect the d <<
5215 but instead allows be <<
5216 like CPU consumption. <<
5217 <<
5218 rcuscale.nreaders= [KNL] 4669 rcuscale.nreaders= [KNL]
5219 Set number of RCU rea 4670 Set number of RCU readers. The value -1 selects
5220 N, where N is the num 4671 N, where N is the number of CPUs. A value
5221 "n" less than -1 sele 4672 "n" less than -1 selects N-n+1, where N is again
5222 the number of CPUs. 4673 the number of CPUs. For example, -2 selects N
5223 (the number of CPUs), 4674 (the number of CPUs), -3 selects N+1, and so on.
5224 A value of "n" less t 4675 A value of "n" less than or equal to -N selects
5225 a single reader. 4676 a single reader.
5226 4677
5227 rcuscale.nwriters= [KNL] 4678 rcuscale.nwriters= [KNL]
5228 Set number of RCU wri 4679 Set number of RCU writers. The values operate
5229 the same as for rcusc 4680 the same as for rcuscale.nreaders.
5230 N, where N is the num 4681 N, where N is the number of CPUs
5231 4682
5232 rcuscale.scale_type= [KNL] !! 4683 rcuscale.perf_type= [KNL]
5233 Specify the RCU imple 4684 Specify the RCU implementation to test.
5234 4685
5235 rcuscale.shutdown= [KNL] 4686 rcuscale.shutdown= [KNL]
5236 Shut the system down 4687 Shut the system down after performance tests
5237 complete. This is us 4688 complete. This is useful for hands-off automated
5238 testing. 4689 testing.
5239 4690
5240 rcuscale.verbose= [KNL] 4691 rcuscale.verbose= [KNL]
5241 Enable additional pri 4692 Enable additional printk() statements.
5242 4693
5243 rcuscale.writer_holdoff= [KNL] 4694 rcuscale.writer_holdoff= [KNL]
5244 Write-side holdoff be 4695 Write-side holdoff between grace periods,
5245 in microseconds. The 4696 in microseconds. The default of zero says
5246 no holdoff. 4697 no holdoff.
5247 4698
5248 rcuscale.writer_holdoff_jiffies= [KNL <<
5249 Additional write-side <<
5250 periods, but in jiffi <<
5251 says no holdoff. <<
5252 <<
5253 rcutorture.fqs_duration= [KNL] 4699 rcutorture.fqs_duration= [KNL]
5254 Set duration of force 4700 Set duration of force_quiescent_state bursts
5255 in microseconds. 4701 in microseconds.
5256 4702
5257 rcutorture.fqs_holdoff= [KNL] 4703 rcutorture.fqs_holdoff= [KNL]
5258 Set holdoff time with 4704 Set holdoff time within force_quiescent_state bursts
5259 in microseconds. 4705 in microseconds.
5260 4706
5261 rcutorture.fqs_stutter= [KNL] 4707 rcutorture.fqs_stutter= [KNL]
5262 Set wait time between 4708 Set wait time between force_quiescent_state bursts
5263 in seconds. 4709 in seconds.
5264 4710
5265 rcutorture.fwd_progress= [KNL] 4711 rcutorture.fwd_progress= [KNL]
5266 Specifies the number !! 4712 Enable RCU grace-period forward-progress testing
5267 for RCU grace-period <<
5268 for the types of RCU 4713 for the types of RCU supporting this notion.
5269 Defaults to 1 kthread <<
5270 greater than the numb <<
5271 of CPUs to be used. <<
5272 4714
5273 rcutorture.fwd_progress_div= [KNL] 4715 rcutorture.fwd_progress_div= [KNL]
5274 Specify the fraction 4716 Specify the fraction of a CPU-stall-warning
5275 period to do tight-lo 4717 period to do tight-loop forward-progress testing.
5276 4718
5277 rcutorture.fwd_progress_holdoff= [KNL 4719 rcutorture.fwd_progress_holdoff= [KNL]
5278 Number of seconds to 4720 Number of seconds to wait between successive
5279 forward-progress test 4721 forward-progress tests.
5280 4722
5281 rcutorture.fwd_progress_need_resched= 4723 rcutorture.fwd_progress_need_resched= [KNL]
5282 Enclose cond_resched( 4724 Enclose cond_resched() calls within checks for
5283 need_resched() during 4725 need_resched() during tight-loop forward-progress
5284 testing. 4726 testing.
5285 4727
5286 rcutorture.gp_cond= [KNL] 4728 rcutorture.gp_cond= [KNL]
5287 Use conditional/async 4729 Use conditional/asynchronous update-side
5288 primitives, if availa 4730 primitives, if available.
5289 4731
5290 rcutorture.gp_exp= [KNL] 4732 rcutorture.gp_exp= [KNL]
5291 Use expedited update- 4733 Use expedited update-side primitives, if available.
5292 4734
5293 rcutorture.gp_normal= [KNL] 4735 rcutorture.gp_normal= [KNL]
5294 Use normal (non-exped 4736 Use normal (non-expedited) asynchronous
5295 update-side primitive 4737 update-side primitives, if available.
5296 4738
5297 rcutorture.gp_sync= [KNL] 4739 rcutorture.gp_sync= [KNL]
5298 Use normal (non-exped 4740 Use normal (non-expedited) synchronous
5299 update-side primitive 4741 update-side primitives, if available. If all
5300 of rcutorture.gp_cond 4742 of rcutorture.gp_cond=, rcutorture.gp_exp=,
5301 rcutorture.gp_normal= 4743 rcutorture.gp_normal=, and rcutorture.gp_sync=
5302 are zero, rcutorture 4744 are zero, rcutorture acts as if is interpreted
5303 they are all non-zero 4745 they are all non-zero.
5304 4746
5305 rcutorture.irqreader= [KNL] 4747 rcutorture.irqreader= [KNL]
5306 Run RCU readers from 4748 Run RCU readers from irq handlers, or, more
5307 accurately, from a ti 4749 accurately, from a timer handler. Not all RCU
5308 flavors take kindly t 4750 flavors take kindly to this sort of thing.
5309 4751
5310 rcutorture.leakpointer= [KNL] 4752 rcutorture.leakpointer= [KNL]
5311 Leak an RCU-protected 4753 Leak an RCU-protected pointer out of the reader.
5312 This can of course re 4754 This can of course result in splats, and is
5313 intended to test the 4755 intended to test the ability of things like
5314 CONFIG_RCU_STRICT_GRA 4756 CONFIG_RCU_STRICT_GRACE_PERIOD=y to detect
5315 such leaks. 4757 such leaks.
5316 4758
5317 rcutorture.n_barrier_cbs= [KNL] 4759 rcutorture.n_barrier_cbs= [KNL]
5318 Set callbacks/threads 4760 Set callbacks/threads for rcu_barrier() testing.
5319 4761
5320 rcutorture.nfakewriters= [KNL] 4762 rcutorture.nfakewriters= [KNL]
5321 Set number of concurr 4763 Set number of concurrent RCU writers. These just
5322 stress RCU, they don' 4764 stress RCU, they don't participate in the actual
5323 test, hence the "fake 4765 test, hence the "fake".
5324 4766
5325 rcutorture.nocbs_nthreads= [KNL] 4767 rcutorture.nocbs_nthreads= [KNL]
5326 Set number of RCU cal 4768 Set number of RCU callback-offload togglers.
5327 Zero (the default) di 4769 Zero (the default) disables toggling.
5328 4770
5329 rcutorture.nocbs_toggle= [KNL] 4771 rcutorture.nocbs_toggle= [KNL]
5330 Set the delay in mill 4772 Set the delay in milliseconds between successive
5331 callback-offload togg 4773 callback-offload toggling attempts.
5332 4774
5333 rcutorture.nreaders= [KNL] 4775 rcutorture.nreaders= [KNL]
5334 Set number of RCU rea 4776 Set number of RCU readers. The value -1 selects
5335 N-1, where N is the n 4777 N-1, where N is the number of CPUs. A value
5336 "n" less than -1 sele 4778 "n" less than -1 selects N-n-2, where N is again
5337 the number of CPUs. 4779 the number of CPUs. For example, -2 selects N
5338 (the number of CPUs), 4780 (the number of CPUs), -3 selects N+1, and so on.
5339 4781
5340 rcutorture.object_debug= [KNL] 4782 rcutorture.object_debug= [KNL]
5341 Enable debug-object d 4783 Enable debug-object double-call_rcu() testing.
5342 4784
5343 rcutorture.onoff_holdoff= [KNL] 4785 rcutorture.onoff_holdoff= [KNL]
5344 Set time (s) after bo 4786 Set time (s) after boot for CPU-hotplug testing.
5345 4787
5346 rcutorture.onoff_interval= [KNL] 4788 rcutorture.onoff_interval= [KNL]
5347 Set time (jiffies) be 4789 Set time (jiffies) between CPU-hotplug operations,
5348 or zero to disable CP 4790 or zero to disable CPU-hotplug testing.
5349 4791
5350 rcutorture.read_exit= [KNL] 4792 rcutorture.read_exit= [KNL]
5351 Set the number of rea 4793 Set the number of read-then-exit kthreads used
5352 to test the interacti 4794 to test the interaction of RCU updaters and
5353 task-exit processing. 4795 task-exit processing.
5354 4796
5355 rcutorture.read_exit_burst= [KNL] 4797 rcutorture.read_exit_burst= [KNL]
5356 The number of times i 4798 The number of times in a given read-then-exit
5357 episode that a set of 4799 episode that a set of read-then-exit kthreads
5358 is spawned. 4800 is spawned.
5359 4801
5360 rcutorture.read_exit_delay= [KNL] 4802 rcutorture.read_exit_delay= [KNL]
5361 The delay, in seconds 4803 The delay, in seconds, between successive
5362 read-then-exit testin 4804 read-then-exit testing episodes.
5363 4805
5364 rcutorture.shuffle_interval= [KNL] 4806 rcutorture.shuffle_interval= [KNL]
5365 Set task-shuffle inte 4807 Set task-shuffle interval (s). Shuffling tasks
5366 allows some CPUs to g 4808 allows some CPUs to go into dyntick-idle mode
5367 during the rcutorture 4809 during the rcutorture test.
5368 4810
5369 rcutorture.shutdown_secs= [KNL] 4811 rcutorture.shutdown_secs= [KNL]
5370 Set time (s) after bo 4812 Set time (s) after boot system shutdown. This
5371 is useful for hands-o 4813 is useful for hands-off automated testing.
5372 4814
5373 rcutorture.stall_cpu= [KNL] 4815 rcutorture.stall_cpu= [KNL]
5374 Duration of CPU stall 4816 Duration of CPU stall (s) to test RCU CPU stall
5375 warnings, zero to dis 4817 warnings, zero to disable.
5376 4818
5377 rcutorture.stall_cpu_block= [KNL] 4819 rcutorture.stall_cpu_block= [KNL]
5378 Sleep while stalling 4820 Sleep while stalling if set. This will result
5379 in warnings from pree !! 4821 in warnings from preemptible RCU in addition
5380 any other stall-relat !! 4822 to any other stall-related activity.
5381 in kernels built with <<
5382 CONFIG_PREEMPT_COUNT= <<
5383 cause the CPU to pass <<
5384 Given CONFIG_PREEMPTI <<
5385 RCU CPU stall warning <<
5386 in scheduling-while-a <<
5387 <<
5388 Use of this module pa <<
5389 <<
5390 4823
5391 rcutorture.stall_cpu_holdoff= [KNL] 4824 rcutorture.stall_cpu_holdoff= [KNL]
5392 Time to wait (s) afte 4825 Time to wait (s) after boot before inducing stall.
5393 4826
5394 rcutorture.stall_cpu_irqsoff= [KNL] 4827 rcutorture.stall_cpu_irqsoff= [KNL]
5395 Disable interrupts wh 4828 Disable interrupts while stalling if set.
5396 4829
5397 rcutorture.stall_gp_kthread= [KNL] 4830 rcutorture.stall_gp_kthread= [KNL]
5398 Duration (s) of force 4831 Duration (s) of forced sleep within RCU
5399 grace-period kthread 4832 grace-period kthread to test RCU CPU stall
5400 warnings, zero to dis 4833 warnings, zero to disable. If both stall_cpu
5401 and stall_gp_kthread 4834 and stall_gp_kthread are specified, the
5402 kthread is starved fi 4835 kthread is starved first, then the CPU.
5403 4836
5404 rcutorture.stat_interval= [KNL] 4837 rcutorture.stat_interval= [KNL]
5405 Time (s) between stat 4838 Time (s) between statistics printk()s.
5406 4839
5407 rcutorture.stutter= [KNL] 4840 rcutorture.stutter= [KNL]
5408 Time (s) to stutter t 4841 Time (s) to stutter testing, for example, specifying
5409 five seconds causes t 4842 five seconds causes the test to run for five seconds,
5410 wait for five seconds 4843 wait for five seconds, and so on. This tests RCU's
5411 ability to transition 4844 ability to transition abruptly to and from idle.
5412 4845
5413 rcutorture.test_boost= [KNL] 4846 rcutorture.test_boost= [KNL]
5414 Test RCU priority boo 4847 Test RCU priority boosting? 0=no, 1=maybe, 2=yes.
5415 "Maybe" means test if 4848 "Maybe" means test if the RCU implementation
5416 under test support RC 4849 under test support RCU priority boosting.
5417 4850
5418 rcutorture.test_boost_duration= [KNL] 4851 rcutorture.test_boost_duration= [KNL]
5419 Duration (s) of each 4852 Duration (s) of each individual boost test.
5420 4853
5421 rcutorture.test_boost_interval= [KNL] 4854 rcutorture.test_boost_interval= [KNL]
5422 Interval (s) between 4855 Interval (s) between each boost test.
5423 4856
5424 rcutorture.test_no_idle_hz= [KNL] 4857 rcutorture.test_no_idle_hz= [KNL]
5425 Test RCU's dyntick-id 4858 Test RCU's dyntick-idle handling. See also the
5426 rcutorture.shuffle_in 4859 rcutorture.shuffle_interval parameter.
5427 4860
5428 rcutorture.torture_type= [KNL] 4861 rcutorture.torture_type= [KNL]
5429 Specify the RCU imple 4862 Specify the RCU implementation to test.
5430 4863
5431 rcutorture.verbose= [KNL] 4864 rcutorture.verbose= [KNL]
5432 Enable additional pri 4865 Enable additional printk() statements.
5433 4866
5434 rcupdate.rcu_cpu_stall_ftrace_dump= [ 4867 rcupdate.rcu_cpu_stall_ftrace_dump= [KNL]
5435 Dump ftrace buffer af 4868 Dump ftrace buffer after reporting RCU CPU
5436 stall warning. 4869 stall warning.
5437 4870
5438 rcupdate.rcu_cpu_stall_notifiers= [KN <<
5439 Provide RCU CPU stall <<
5440 warnings in the RCU_C <<
5441 option's help text. <<
5442 do not want rcupdate. <<
5443 <<
5444 rcupdate.rcu_cpu_stall_suppress= [KNL 4871 rcupdate.rcu_cpu_stall_suppress= [KNL]
5445 Suppress RCU CPU stal 4872 Suppress RCU CPU stall warning messages.
5446 4873
5447 rcupdate.rcu_cpu_stall_suppress_at_bo 4874 rcupdate.rcu_cpu_stall_suppress_at_boot= [KNL]
5448 Suppress RCU CPU stal 4875 Suppress RCU CPU stall warning messages and
5449 rcutorture writer sta 4876 rcutorture writer stall warnings that occur
5450 during early boot, th 4877 during early boot, that is, during the time
5451 before the init task 4878 before the init task is spawned.
5452 4879
5453 rcupdate.rcu_cpu_stall_timeout= [KNL] 4880 rcupdate.rcu_cpu_stall_timeout= [KNL]
5454 Set timeout for RCU C 4881 Set timeout for RCU CPU stall warning messages.
5455 The value is in secon <<
5456 value is 300 seconds. <<
5457 <<
5458 rcupdate.rcu_exp_cpu_stall_timeout= [ <<
5459 Set timeout for exped <<
5460 messages. The value <<
5461 and the maximum allow <<
5462 milliseconds. Please <<
5463 adjusted to an arch t <<
5464 Setting this to zero <<
5465 rcupdate.rcu_cpu_stal <<
5466 conversion from secon <<
5467 <<
5468 rcupdate.rcu_cpu_stall_cputime= [KNL] <<
5469 Provide statistics on <<
5470 interrupts and tasks <<
5471 multiple continuous R <<
5472 begin at half of the <<
5473 <<
5474 rcupdate.rcu_exp_stall_task_details= <<
5475 Print stack dumps of <<
5476 current expedited RCU <<
5477 expedited RCU CPU sta <<
5478 4882
5479 rcupdate.rcu_expedited= [KNL] 4883 rcupdate.rcu_expedited= [KNL]
5480 Use expedited grace-p 4884 Use expedited grace-period primitives, for
5481 example, synchronize_ 4885 example, synchronize_rcu_expedited() instead
5482 of synchronize_rcu(). 4886 of synchronize_rcu(). This reduces latency,
5483 but can increase CPU 4887 but can increase CPU utilization, degrade
5484 real-time latency, an 4888 real-time latency, and degrade energy efficiency.
5485 No effect on CONFIG_T 4889 No effect on CONFIG_TINY_RCU kernels.
5486 4890
5487 rcupdate.rcu_normal= [KNL] 4891 rcupdate.rcu_normal= [KNL]
5488 Use only normal grace 4892 Use only normal grace-period primitives,
5489 for example, synchron 4893 for example, synchronize_rcu() instead of
5490 synchronize_rcu_exped 4894 synchronize_rcu_expedited(). This improves
5491 real-time latency, CP 4895 real-time latency, CPU utilization, and
5492 energy efficiency, bu 4896 energy efficiency, but can expose users to
5493 increased grace-perio 4897 increased grace-period latency. This parameter
5494 overrides rcupdate.rc 4898 overrides rcupdate.rcu_expedited. No effect on
5495 CONFIG_TINY_RCU kerne 4899 CONFIG_TINY_RCU kernels.
5496 4900
5497 rcupdate.rcu_normal_after_boot= [KNL] 4901 rcupdate.rcu_normal_after_boot= [KNL]
5498 Once boot has complet 4902 Once boot has completed (that is, after
5499 rcu_end_inkernel_boot 4903 rcu_end_inkernel_boot() has been invoked), use
5500 only normal grace-per 4904 only normal grace-period primitives. No effect
5501 on CONFIG_TINY_RCU ke 4905 on CONFIG_TINY_RCU kernels.
5502 4906
5503 But note that CONFIG_ 4907 But note that CONFIG_PREEMPT_RT=y kernels enables
5504 this kernel boot para 4908 this kernel boot parameter, forcibly setting
5505 it to the value one, 4909 it to the value one, that is, converting any
5506 post-boot attempt at 4910 post-boot attempt at an expedited RCU grace
5507 period to instead use 4911 period to instead use normal non-expedited
5508 grace-period processi 4912 grace-period processing.
5509 4913
5510 rcupdate.rcu_task_collapse_lim= [KNL] <<
5511 Set the maximum numbe <<
5512 at the beginning of a <<
5513 the RCU Tasks flavors <<
5514 a single callback que <<
5515 occurs when rcupdate. <<
5516 set to the default va <<
5517 <<
5518 rcupdate.rcu_task_contend_lim= [KNL] <<
5519 Set the minimum numbe <<
5520 lock-contention event <<
5521 cause the RCU Tasks f <<
5522 callback queuing. Th <<
5523 when rcupdate.rcu_tas <<
5524 the default value of <<
5525 <<
5526 rcupdate.rcu_task_enqueue_lim= [KNL] <<
5527 Set the number of cal <<
5528 RCU Tasks family of R <<
5529 of -1 allows this to <<
5530 dynamically) adjusted <<
5531 for use in testing. <<
5532 <<
5533 rcupdate.rcu_task_ipi_delay= [KNL] 4914 rcupdate.rcu_task_ipi_delay= [KNL]
5534 Set time in jiffies d 4915 Set time in jiffies during which RCU tasks will
5535 avoid sending IPIs, s 4916 avoid sending IPIs, starting with the beginning
5536 of a given grace peri 4917 of a given grace period. Setting a large
5537 number avoids disturb 4918 number avoids disturbing real-time workloads,
5538 but lengthens grace p 4919 but lengthens grace periods.
5539 4920
5540 rcupdate.rcu_task_lazy_lim= [KNL] <<
5541 Number of callbacks o <<
5542 cancel laziness on th <<
5543 cancellation of lazin <<
5544 doing so increases th <<
5545 callback flooding. <<
5546 <<
5547 rcupdate.rcu_task_stall_info= [KNL] <<
5548 Set initial timeout i <<
5549 informational message <<
5550 of the problem for th <<
5551 wait for ten minutes. <<
5552 only printed prior to <<
5553 for a given grace per <<
5554 less than or equal to <<
5555 seconds. A change in <<
5556 until the beginning o <<
5557 <<
5558 rcupdate.rcu_task_stall_info_mult= [K <<
5559 Multiplier for time i <<
5560 RCU task stall inform <<
5561 RCU tasks grace perio <<
5562 to one through ten, i <<
5563 the value three, so t <<
5564 message is printed 10 <<
5565 period, the second at <<
5566 160 seconds, and then <<
5567 seconds would prevent <<
5568 <<
5569 rcupdate.rcu_task_stall_timeout= [KNL 4921 rcupdate.rcu_task_stall_timeout= [KNL]
5570 Set timeout in jiffie !! 4922 Set timeout in jiffies for RCU task stall warning
5571 warning messages. Di !! 4923 messages. Disable with a value less than or equal
5572 than or equal to zero !! 4924 to zero.
5573 A change in value doe <<
5574 the beginning of the <<
5575 <<
5576 rcupdate.rcu_tasks_lazy_ms= [KNL] <<
5577 Set timeout in millis <<
5578 callback batching for <<
5579 A negative value will <<
5580 of zero will disable <<
5581 always disabled for s <<
5582 <<
5583 rcupdate.rcu_tasks_rude_lazy_ms= [KNL <<
5584 Set timeout in millis <<
5585 Rude asynchronous cal <<
5586 call_rcu_tasks_rude() <<
5587 will take the default <<
5588 disable batching. Ba <<
5589 for synchronize_rcu_t <<
5590 <<
5591 rcupdate.rcu_tasks_trace_lazy_ms= [KN <<
5592 Set timeout in millis <<
5593 Trace asynchronous ca <<
5594 call_rcu_tasks_trace( <<
5595 will take the default <<
5596 disable batching. Ba <<
5597 for synchronize_rcu_t <<
5598 4925
5599 rcupdate.rcu_self_test= [KNL] 4926 rcupdate.rcu_self_test= [KNL]
5600 Run the RCU early boo 4927 Run the RCU early boot self tests
5601 4928
5602 rdinit= [KNL] 4929 rdinit= [KNL]
5603 Format: <full_path> 4930 Format: <full_path>
5604 Run specified binary 4931 Run specified binary instead of /init from the ramdisk,
5605 used for early usersp 4932 used for early userspace startup. See initrd.
5606 4933
5607 rdrand= [X86,EARLY] !! 4934 rdrand= [X86]
5608 force - Override the 4935 force - Override the decision by the kernel to hide the
5609 advertisement 4936 advertisement of RDRAND support (this affects
5610 certain AMD p 4937 certain AMD processors because of buggy BIOS
5611 support, spec 4938 support, specifically around the suspend/resume
5612 path). 4939 path).
5613 4940
5614 rdt= [HW,X86,RDT] 4941 rdt= [HW,X86,RDT]
5615 Turn on/off individua 4942 Turn on/off individual RDT features. List is:
5616 cmt, mbmtotal, mbmloc 4943 cmt, mbmtotal, mbmlocal, l3cat, l3cdp, l2cat, l2cdp,
5617 mba, smba, bmec. !! 4944 mba.
5618 E.g. to turn on cmt a 4945 E.g. to turn on cmt and turn off mba use:
5619 rdt=cmt,!mba 4946 rdt=cmt,!mba
5620 4947
5621 reboot= [KNL] 4948 reboot= [KNL]
5622 Format (x86 or x86_64 4949 Format (x86 or x86_64):
5623 [w[arm] | c[o 4950 [w[arm] | c[old] | h[ard] | s[oft] | g[pio]] | d[efault] \
5624 [[,]s[mp]#### 4951 [[,]s[mp]#### \
5625 [[,]b[ios] | 4952 [[,]b[ios] | a[cpi] | k[bd] | t[riple] | e[fi] | p[ci]] \
5626 [[,]f[orce] 4953 [[,]f[orce]
5627 Where reboot_mode is 4954 Where reboot_mode is one of warm (soft) or cold (hard) or gpio
5628 (pref 4955 (prefix with 'panic_' to set mode for panic
5629 reboo 4956 reboot only),
5630 reboot_type is 4957 reboot_type is one of bios, acpi, kbd, triple, efi, or pci,
5631 reboot_force is 4958 reboot_force is either force or not specified,
5632 reboot_cpu is s 4959 reboot_cpu is s[mp]#### with #### being the processor
5633 to be 4960 to be used for rebooting.
5634 4961
5635 refscale.holdoff= [KNL] 4962 refscale.holdoff= [KNL]
5636 Set test-start holdof 4963 Set test-start holdoff period. The purpose of
5637 this parameter is to 4964 this parameter is to delay the start of the
5638 test until boot compl 4965 test until boot completes in order to avoid
5639 interference. 4966 interference.
5640 4967
5641 refscale.lookup_instances= [KNL] <<
5642 Number of data elemen <<
5643 SLAB_TYPESAFE_BY_RCU <<
5644 is negated and multip <<
5645 zero specifies nr_cpu <<
5646 <<
5647 refscale.loops= [KNL] 4968 refscale.loops= [KNL]
5648 Set the number of loo 4969 Set the number of loops over the synchronization
5649 primitive under test. 4970 primitive under test. Increasing this number
5650 reduces noise due to 4971 reduces noise due to loop start/end overhead,
5651 but the default has a 4972 but the default has already reduced the per-pass
5652 noise to a handful of 4973 noise to a handful of picoseconds on ca. 2020
5653 x86 laptops. 4974 x86 laptops.
5654 4975
5655 refscale.nreaders= [KNL] 4976 refscale.nreaders= [KNL]
5656 Set number of readers 4977 Set number of readers. The default value of -1
5657 selects N, where N is 4978 selects N, where N is roughly 75% of the number
5658 of CPUs. A value of 4979 of CPUs. A value of zero is an interesting choice.
5659 4980
5660 refscale.nruns= [KNL] 4981 refscale.nruns= [KNL]
5661 Set number of runs, e 4982 Set number of runs, each of which is dumped onto
5662 the console log. 4983 the console log.
5663 4984
5664 refscale.readdelay= [KNL] 4985 refscale.readdelay= [KNL]
5665 Set the read-side cri 4986 Set the read-side critical-section duration,
5666 measured in microseco 4987 measured in microseconds.
5667 4988
5668 refscale.scale_type= [KNL] 4989 refscale.scale_type= [KNL]
5669 Specify the read-prot 4990 Specify the read-protection implementation to test.
5670 4991
5671 refscale.shutdown= [KNL] 4992 refscale.shutdown= [KNL]
5672 Shut down the system 4993 Shut down the system at the end of the performance
5673 test. This defaults 4994 test. This defaults to 1 (shut it down) when
5674 refscale is built int 4995 refscale is built into the kernel and to 0 (leave
5675 it running) when refs 4996 it running) when refscale is built as a module.
5676 4997
5677 refscale.verbose= [KNL] 4998 refscale.verbose= [KNL]
5678 Enable additional pri 4999 Enable additional printk() statements.
5679 5000
5680 refscale.verbose_batched= [KNL] 5001 refscale.verbose_batched= [KNL]
5681 Batch the additional 5002 Batch the additional printk() statements. If zero
5682 (the default) or nega 5003 (the default) or negative, print everything. Otherwise,
5683 print every Nth verbo 5004 print every Nth verbose statement, where N is the value
5684 specified. 5005 specified.
5685 5006
5686 regulator_ignore_unused <<
5687 [REGULATOR] <<
5688 Prevents regulator fr <<
5689 that are unused, due <<
5690 be useful for debug a <<
5691 needed on a platform <<
5692 <<
5693 relax_domain_level= 5007 relax_domain_level=
5694 [KNL, SMP] Set schedu 5008 [KNL, SMP] Set scheduler's default relax_domain_level.
5695 See Documentation/adm 5009 See Documentation/admin-guide/cgroup-v1/cpusets.rst.
5696 5010
5697 reserve= [KNL,BUGS] Force kern 5011 reserve= [KNL,BUGS] Force kernel to ignore I/O ports or memory
5698 Format: <base1>,<size 5012 Format: <base1>,<size1>[,<base2>,<size2>,...]
5699 Reserve I/O ports or 5013 Reserve I/O ports or memory so the kernel won't use
5700 them. If <base> is l 5014 them. If <base> is less than 0x10000, the region
5701 is assumed to be I/O 5015 is assumed to be I/O ports; otherwise it is memory.
5702 5016
5703 reserve_mem= [RAM] !! 5017 reservetop= [X86-32]
5704 Format: nn[KNG]:<alig <<
5705 Reserve physical memo <<
5706 other subsystems can <<
5707 used for systems that <<
5708 line will try to rese <<
5709 soft reboots. Note, i <<
5710 location. For example <<
5711 or if booting a diffe <<
5712 places the kernel at <<
5713 was from a previous b <<
5714 different location. <<
5715 Any subsystem using t <<
5716 that the contents of <<
5717 boot, as there may be <<
5718 located at the same l <<
5719 <<
5720 The format is size:al <<
5721 12 megabytes of 4096 <<
5722 <<
5723 reserve_mem=12M:4096: <<
5724 <<
5725 reservetop= [X86-32,EARLY] <<
5726 Format: nn[KMG] 5018 Format: nn[KMG]
5727 Reserves a hole at th 5019 Reserves a hole at the top of the kernel virtual
5728 address space. 5020 address space.
5729 5021
5730 reset_devices [KNL] Force drivers t 5022 reset_devices [KNL] Force drivers to reset the underlying device
5731 during initialization 5023 during initialization.
5732 5024
5733 resume= [SWSUSP] 5025 resume= [SWSUSP]
5734 Specify the partition 5026 Specify the partition device for software suspend
5735 Format: 5027 Format:
5736 {/dev/<dev> | PARTUUI 5028 {/dev/<dev> | PARTUUID=<uuid> | <int>:<int> | <hex>}
5737 5029
5738 resume_offset= [SWSUSP] 5030 resume_offset= [SWSUSP]
5739 Specify the offset fr 5031 Specify the offset from the beginning of the partition
5740 given by "resume=" at 5032 given by "resume=" at which the swap header is located,
5741 in <PAGE_SIZE> units 5033 in <PAGE_SIZE> units (needed only for swap files).
5742 See Documentation/po 5034 See Documentation/power/swsusp-and-swap-files.rst
5743 5035
5744 resumedelay= [HIBERNATION] Delay ( 5036 resumedelay= [HIBERNATION] Delay (in seconds) to pause before attempting to
5745 read the resume files 5037 read the resume files
5746 5038
5747 resumewait [HIBERNATION] Wait (i 5039 resumewait [HIBERNATION] Wait (indefinitely) for resume device to show up.
5748 Useful for devices th 5040 Useful for devices that are detected asynchronously
5749 (e.g. USB and MMC dev 5041 (e.g. USB and MMC devices).
5750 5042
5751 retain_initrd [RAM] Keep initrd mem !! 5043 hibernate= [HIBERNATION]
5752 be accessible via /sy !! 5044 noresume Don't check if there's a hibernation image
>> 5045 present during boot.
>> 5046 nocompress Don't compress/decompress hibernation images.
>> 5047 no Disable hibernation and resume.
>> 5048 protect_image Turn on image protection during restoration
>> 5049 (that will set all pages holding image data
>> 5050 during restoration read-only).
>> 5051
>> 5052 retain_initrd [RAM] Keep initrd memory after extraction
5753 5053
5754 retbleed= [X86] Control mitigat 5054 retbleed= [X86] Control mitigation of RETBleed (Arbitrary
5755 Speculative Code Exec 5055 Speculative Code Execution with Return Instructions)
5756 vulnerability. 5056 vulnerability.
5757 5057
5758 AMD-based UNRET and I 5058 AMD-based UNRET and IBPB mitigations alone do not stop
5759 sibling threads from 5059 sibling threads from influencing the predictions of other
5760 sibling threads. For 5060 sibling threads. For that reason, STIBP is used on pro-
5761 cessors that support 5061 cessors that support it, and mitigate SMT on processors
5762 that don't. 5062 that don't.
5763 5063
5764 off - no mit 5064 off - no mitigation
5765 auto - automa 5065 auto - automatically select a migitation
5766 auto,nosmt - automa 5066 auto,nosmt - automatically select a mitigation,
5767 disabl 5067 disabling SMT if necessary for
5768 the fu 5068 the full mitigation (only on Zen1
5769 and ol 5069 and older without STIBP).
5770 ibpb - On AMD 5070 ibpb - On AMD, mitigate short speculation
5771 window 5071 windows on basic block boundaries too.
5772 Safe, 5072 Safe, highest perf impact. It also
5773 enable 5073 enables STIBP if present. Not suitable
5774 on Int 5074 on Intel.
5775 ibpb,nosmt - Like " 5075 ibpb,nosmt - Like "ibpb" above but will disable SMT
5776 when S 5076 when STIBP is not available. This is
5777 the al 5077 the alternative for systems which do not
5778 have S 5078 have STIBP.
5779 unret - Force 5079 unret - Force enable untrained return thunks,
5780 only e 5080 only effective on AMD f15h-f17h based
5781 system 5081 systems.
5782 unret,nosmt - Like u 5082 unret,nosmt - Like unret, but will disable SMT when STIBP
5783 is not 5083 is not available. This is the alternative for
5784 system 5084 systems which do not have STIBP.
5785 5085
5786 Selecting 'auto' will 5086 Selecting 'auto' will choose a mitigation method at run
5787 time according to the 5087 time according to the CPU.
5788 5088
5789 Not specifying this o 5089 Not specifying this option is equivalent to retbleed=auto.
5790 5090
5791 rfkill.default_state= 5091 rfkill.default_state=
5792 0 "airplane mode". All 5092 0 "airplane mode". All wifi, bluetooth, wimax, gps, fm,
5793 etc. communication is 5093 etc. communication is blocked by default.
5794 1 Unblocked. 5094 1 Unblocked.
5795 5095
5796 rfkill.master_switch_mode= 5096 rfkill.master_switch_mode=
5797 0 The "airplane mode" b 5097 0 The "airplane mode" button does nothing.
5798 1 The "airplane mode" b 5098 1 The "airplane mode" button toggles between everything
5799 blocked and the previ 5099 blocked and the previous configuration.
5800 2 The "airplane mode" b 5100 2 The "airplane mode" button toggles between everything
5801 blocked and everythin 5101 blocked and everything unblocked.
5802 5102
>> 5103 rhash_entries= [KNL,NET]
>> 5104 Set number of hash buckets for route cache
>> 5105
5803 ring3mwait=disable 5106 ring3mwait=disable
5804 [KNL] Disable ring 3 5107 [KNL] Disable ring 3 MONITOR/MWAIT feature on supported
5805 CPUs. 5108 CPUs.
5806 5109
5807 riscv_isa_fallback [RISCV,EARLY] <<
5808 When CONFIG_RISCV_ISA <<
5809 falling back to detec <<
5810 "riscv,isa" property <<
5811 replacement propertie <<
5812 entry for RISCV_ISA_F <<
5813 <<
5814 ro [KNL] Mount root devi 5110 ro [KNL] Mount root device read-only on boot
5815 5111
5816 rodata= [KNL,EARLY] !! 5112 rodata= [KNL]
5817 on Mark read-only kernel 5113 on Mark read-only kernel memory as read-only (default).
5818 off Leave read-only kerne 5114 off Leave read-only kernel memory writable for debugging.
5819 full Mark read-only kernel <<
5820 [arm64] <<
5821 5115
5822 rockchip.usb_uart 5116 rockchip.usb_uart
5823 [EARLY] <<
5824 Enable the uart passt 5117 Enable the uart passthrough on the designated usb port
5825 on Rockchip SoCs. Whe 5118 on Rockchip SoCs. When active, the signals of the
5826 debug-uart get routed 5119 debug-uart get routed to the D+ and D- pins of the usb
5827 port and the regular 5120 port and the regular usb controller gets disabled.
5828 5121
5829 root= [KNL] Root filesystem 5122 root= [KNL] Root filesystem
5830 Usually this a a bloc !! 5123 See name_to_dev_t comment in init/do_mounts.c.
5831 see the early_lookup_ <<
5832 block/early-lookup.c <<
5833 Alternatively this ca <<
5834 ramdisk, "nfs" and "c <<
5835 system, or "mtd" and <<
5836 5124
5837 rootdelay= [KNL] Delay (in secon 5125 rootdelay= [KNL] Delay (in seconds) to pause before attempting to
5838 mount the root filesy 5126 mount the root filesystem
5839 5127
5840 rootflags= [KNL] Set root filesy 5128 rootflags= [KNL] Set root filesystem mount option string
5841 5129
5842 rootfstype= [KNL] Set root filesy 5130 rootfstype= [KNL] Set root filesystem type
5843 5131
5844 rootwait [KNL] Wait (indefinit 5132 rootwait [KNL] Wait (indefinitely) for root device to show up.
5845 Useful for devices th 5133 Useful for devices that are detected asynchronously
5846 (e.g. USB and MMC dev 5134 (e.g. USB and MMC devices).
5847 5135
5848 rootwait= [KNL] Maximum time (i <<
5849 to show up before att <<
5850 filesystem. <<
5851 <<
5852 rproc_mem=nn[KMG][@address] 5136 rproc_mem=nn[KMG][@address]
5853 [KNL,ARM,CMA] Remotep 5137 [KNL,ARM,CMA] Remoteproc physical memory block.
5854 Memory area to be use 5138 Memory area to be used by remote processor image,
5855 managed by CMA. 5139 managed by CMA.
5856 5140
5857 rw [KNL] Mount root devi 5141 rw [KNL] Mount root device read-write on boot
5858 5142
5859 S [KNL] Run init in sin 5143 S [KNL] Run init in single mode
5860 5144
5861 s390_iommu= [HW,S390] 5145 s390_iommu= [HW,S390]
5862 Set s390 IOTLB flushi 5146 Set s390 IOTLB flushing mode
5863 strict 5147 strict
5864 With strict flushing !! 5148 With strict flushing every unmap operation will result in
5865 in an IOTLB flush. De !! 5149 an IOTLB flush. Default is lazy flushing before reuse,
5866 reuse, which is faste !! 5150 which is faster.
5867 iommu.strict=1. <<
5868 <<
5869 s390_iommu_aperture= [KNL,S390] <<
5870 Specifies the size of <<
5871 accessible through th <<
5872 factor of the size of <<
5873 The default is 1 mean <<
5874 as many DMA addresses <<
5875 if supported by hardw <<
5876 once. With a value of <<
5877 and so on. As a speci <<
5878 restrictions other th <<
5879 cost of significant a <<
5880 5151
5881 sa1100ir [NET] 5152 sa1100ir [NET]
5882 See drivers/net/irda/ 5153 See drivers/net/irda/sa1100_ir.c.
5883 5154
5884 sched_verbose [KNL,EARLY] Enables v !! 5155 sched_verbose [KNL] Enables verbose scheduler debug messages.
5885 5156
5886 schedstats= [KNL,X86] Enable or d 5157 schedstats= [KNL,X86] Enable or disable scheduled statistics.
5887 Allowed values are en 5158 Allowed values are enable and disable. This feature
5888 incurs a small amount 5159 incurs a small amount of overhead in the scheduler
5889 but is useful for deb 5160 but is useful for debugging and performance tuning.
5890 5161
5891 sched_thermal_decay_shift= 5162 sched_thermal_decay_shift=
5892 [Deprecated] <<
5893 [KNL, SMP] Set a deca 5163 [KNL, SMP] Set a decay shift for scheduler thermal
5894 pressure signal. Ther 5164 pressure signal. Thermal pressure signal follows the
5895 default decay period 5165 default decay period of other scheduler pelt
5896 signals(usually 32 ms 5166 signals(usually 32 ms but configurable). Setting
5897 sched_thermal_decay_s 5167 sched_thermal_decay_shift will left shift the decay
5898 period for the therma 5168 period for the thermal pressure signal by the shift
5899 value. 5169 value.
5900 i.e. with the default 5170 i.e. with the default pelt decay period of 32 ms
5901 sched_thermal_decay_s 5171 sched_thermal_decay_shift thermal pressure decay pr
5902 1 5172 1 64 ms
5903 2 5173 2 128 ms
5904 and so on. 5174 and so on.
5905 Format: integer betwe 5175 Format: integer between 0 and 10
5906 Default is 0. 5176 Default is 0.
5907 5177
5908 scftorture.holdoff= [KNL] 5178 scftorture.holdoff= [KNL]
5909 Number of seconds to 5179 Number of seconds to hold off before starting
5910 test. Defaults to ze 5180 test. Defaults to zero for module insertion and
5911 to 10 seconds for bui 5181 to 10 seconds for built-in smp_call_function()
5912 tests. 5182 tests.
5913 5183
5914 scftorture.longwait= [KNL] 5184 scftorture.longwait= [KNL]
5915 Request ridiculously 5185 Request ridiculously long waits randomly selected
5916 up to the chosen limi 5186 up to the chosen limit in seconds. Zero (the
5917 default) disables thi 5187 default) disables this feature. Please note
5918 that requesting even 5188 that requesting even small non-zero numbers of
5919 seconds can result in 5189 seconds can result in RCU CPU stall warnings,
5920 softlockup complaints 5190 softlockup complaints, and so on.
5921 5191
5922 scftorture.nthreads= [KNL] 5192 scftorture.nthreads= [KNL]
5923 Number of kthreads to 5193 Number of kthreads to spawn to invoke the
5924 smp_call_function() f 5194 smp_call_function() family of functions.
5925 The default of -1 spe 5195 The default of -1 specifies a number of kthreads
5926 equal to the number o 5196 equal to the number of CPUs.
5927 5197
5928 scftorture.onoff_holdoff= [KNL] 5198 scftorture.onoff_holdoff= [KNL]
5929 Number seconds to wai 5199 Number seconds to wait after the start of the
5930 test before initiatin 5200 test before initiating CPU-hotplug operations.
5931 5201
5932 scftorture.onoff_interval= [KNL] 5202 scftorture.onoff_interval= [KNL]
5933 Number seconds to wai 5203 Number seconds to wait between successive
5934 CPU-hotplug operation 5204 CPU-hotplug operations. Specifying zero (which
5935 is the default) disab 5205 is the default) disables CPU-hotplug operations.
5936 5206
5937 scftorture.shutdown_secs= [KNL] 5207 scftorture.shutdown_secs= [KNL]
5938 The number of seconds 5208 The number of seconds following the start of the
5939 test after which to s 5209 test after which to shut down the system. The
5940 default of zero avoid 5210 default of zero avoids shutting down the system.
5941 Non-zero values are u 5211 Non-zero values are useful for automated tests.
5942 5212
5943 scftorture.stat_interval= [KNL] 5213 scftorture.stat_interval= [KNL]
5944 The number of seconds 5214 The number of seconds between outputting the
5945 current test statisti 5215 current test statistics to the console. A value
5946 of zero disables stat 5216 of zero disables statistics output.
5947 5217
5948 scftorture.stutter_cpus= [KNL] 5218 scftorture.stutter_cpus= [KNL]
5949 The number of jiffies 5219 The number of jiffies to wait between each change
5950 to the set of CPUs un 5220 to the set of CPUs under test.
5951 5221
5952 scftorture.use_cpus_read_lock= [KNL] 5222 scftorture.use_cpus_read_lock= [KNL]
5953 Use use_cpus_read_loc 5223 Use use_cpus_read_lock() instead of the default
5954 preempt_disable() to 5224 preempt_disable() to disable CPU hotplug
5955 while invoking one of 5225 while invoking one of the smp_call_function*()
5956 functions. 5226 functions.
5957 5227
5958 scftorture.verbose= [KNL] 5228 scftorture.verbose= [KNL]
5959 Enable additional pri 5229 Enable additional printk() statements.
5960 5230
5961 scftorture.weight_single= [KNL] 5231 scftorture.weight_single= [KNL]
5962 The probability weigh 5232 The probability weighting to use for the
5963 smp_call_function_sin 5233 smp_call_function_single() function with a zero
5964 "wait" parameter. A 5234 "wait" parameter. A value of -1 selects the
5965 default if all other 5235 default if all other weights are -1. However,
5966 if at least one weigh 5236 if at least one weight has some other value, a
5967 value of -1 will inst 5237 value of -1 will instead select a weight of zero.
5968 5238
5969 scftorture.weight_single_wait= [KNL] 5239 scftorture.weight_single_wait= [KNL]
5970 The probability weigh 5240 The probability weighting to use for the
5971 smp_call_function_sin 5241 smp_call_function_single() function with a
5972 non-zero "wait" param 5242 non-zero "wait" parameter. See weight_single.
5973 5243
5974 scftorture.weight_many= [KNL] 5244 scftorture.weight_many= [KNL]
5975 The probability weigh 5245 The probability weighting to use for the
5976 smp_call_function_man 5246 smp_call_function_many() function with a zero
5977 "wait" parameter. Se 5247 "wait" parameter. See weight_single.
5978 Note well that settin 5248 Note well that setting a high probability for
5979 this weighting can pl 5249 this weighting can place serious IPI load
5980 on the system. 5250 on the system.
5981 5251
5982 scftorture.weight_many_wait= [KNL] 5252 scftorture.weight_many_wait= [KNL]
5983 The probability weigh 5253 The probability weighting to use for the
5984 smp_call_function_man 5254 smp_call_function_many() function with a
5985 non-zero "wait" param 5255 non-zero "wait" parameter. See weight_single
5986 and weight_many. 5256 and weight_many.
5987 5257
5988 scftorture.weight_all= [KNL] 5258 scftorture.weight_all= [KNL]
5989 The probability weigh 5259 The probability weighting to use for the
5990 smp_call_function_all 5260 smp_call_function_all() function with a zero
5991 "wait" parameter. Se 5261 "wait" parameter. See weight_single and
5992 weight_many. 5262 weight_many.
5993 5263
5994 scftorture.weight_all_wait= [KNL] 5264 scftorture.weight_all_wait= [KNL]
5995 The probability weigh 5265 The probability weighting to use for the
5996 smp_call_function_all 5266 smp_call_function_all() function with a
5997 non-zero "wait" param 5267 non-zero "wait" parameter. See weight_single
5998 and weight_many. 5268 and weight_many.
5999 5269
6000 skew_tick= [KNL,EARLY] Offset th !! 5270 skew_tick= [KNL] Offset the periodic timer tick per cpu to mitigate
6001 xtime_lock contention 5271 xtime_lock contention on larger systems, and/or RCU lock
6002 contention on all sys 5272 contention on all systems with CONFIG_MAXSMP set.
6003 Format: { "0" | "1" } 5273 Format: { "0" | "1" }
6004 0 -- disable. (may be 5274 0 -- disable. (may be 1 via CONFIG_CMDLINE="skew_tick=1"
6005 1 -- enable. 5275 1 -- enable.
6006 Note: increases power 5276 Note: increases power consumption, thus should only be
6007 enabled if running ji 5277 enabled if running jitter sensitive (HPC/RT) workloads.
6008 5278
6009 security= [SECURITY] Choose a l 5279 security= [SECURITY] Choose a legacy "major" security module to
6010 enable at boot. This 5280 enable at boot. This has been deprecated by the
6011 "lsm=" parameter. 5281 "lsm=" parameter.
6012 5282
6013 selinux= [SELINUX] Disable or 5283 selinux= [SELINUX] Disable or enable SELinux at boot time.
6014 Format: { "0" | "1" } 5284 Format: { "0" | "1" }
6015 See security/selinux/ 5285 See security/selinux/Kconfig help text.
6016 0 -- disable. 5286 0 -- disable.
6017 1 -- enable. 5287 1 -- enable.
6018 Default value is 1. 5288 Default value is 1.
6019 5289
6020 serialnumber [BUGS=X86-32] !! 5290 apparmor= [APPARMOR] Disable or enable AppArmor at boot time
>> 5291 Format: { "0" | "1" }
>> 5292 See security/apparmor/Kconfig help text
>> 5293 0 -- disable.
>> 5294 1 -- enable.
>> 5295 Default value is set via kernel config option.
6021 5296
6022 sev=option[,option...] [X86-64] See D !! 5297 serialnumber [BUGS=X86-32]
6023 5298
6024 shapers= [NET] 5299 shapers= [NET]
6025 Maximal number of sha 5300 Maximal number of shapers.
6026 5301
6027 show_lapic= [APIC,X86] Advanced P !! 5302 simeth= [IA-64]
6028 Limit apic dumping. T !! 5303 simscsi=
6029 number of local apics <<
6030 to set it to "all" by <<
6031 Format: { 1 (default) <<
6032 The parameter valid i <<
6033 apic=verbose is speci <<
6034 Example: apic=debug s <<
6035 <<
6036 slab_debug[=options[,slabs][;[options <<
6037 Enabling slab_debug a <<
6038 culprit if slab objec <<
6039 slab_debug can create <<
6040 may poison objects wh <<
6041 last alloc / free. Fo <<
6042 Documentation/mm/slub <<
6043 (slub_debug legacy na <<
6044 5304
6045 slab_max_order= [MM] !! 5305 slram= [HW,MTD]
6046 Determines the maximu <<
6047 A high setting may ca <<
6048 fragmentation. For mo <<
6049 Documentation/mm/slub <<
6050 (slub_max_order legac <<
6051 5306
6052 slab_merge [MM] 5307 slab_merge [MM]
6053 Enable merging of sla 5308 Enable merging of slabs with similar size when the
6054 kernel is built witho 5309 kernel is built without CONFIG_SLAB_MERGE_DEFAULT.
6055 (slub_merge legacy na <<
6056 <<
6057 slab_min_objects= [MM] <<
6058 The minimum number of <<
6059 increase the slab ord <<
6060 generate a sufficient <<
6061 the number of objects <<
6062 of objects the smalle <<
6063 and the less frequent <<
6064 For more information <<
6065 (slub_min_objects leg <<
6066 <<
6067 slab_min_order= [MM] <<
6068 Determines the minimu <<
6069 lower or equal to sla <<
6070 Documentation/mm/slub <<
6071 (slub_min_order legac <<
6072 5310
6073 slab_nomerge [MM] 5311 slab_nomerge [MM]
6074 Disable merging of sl 5312 Disable merging of slabs with similar size. May be
6075 necessary if there is 5313 necessary if there is some reason to distinguish
6076 allocs to different s 5314 allocs to different slabs, especially in hardened
6077 environments where th 5315 environments where the risk of heap overflows and
6078 layout control by att 5316 layout control by attackers can usually be
6079 frustrated by disabli 5317 frustrated by disabling merging. This will reduce
6080 most of the exposure 5318 most of the exposure of a heap attack to a single
6081 cache (risks via meta 5319 cache (risks via metadata attacks are mostly
6082 unchanged). Debug opt 5320 unchanged). Debug options disable merging on their
6083 own. 5321 own.
6084 For more information !! 5322 For more information see Documentation/vm/slub.rst.
6085 (slub_nomerge legacy <<
6086 5323
6087 slram= [HW,MTD] !! 5324 slab_max_order= [MM, SLAB]
>> 5325 Determines the maximum allowed order for slabs.
>> 5326 A high setting may cause OOMs due to memory
>> 5327 fragmentation. Defaults to 1 for systems with
>> 5328 more than 32MB of RAM, 0 otherwise.
>> 5329
>> 5330 slub_debug[=options[,slabs][;[options[,slabs]]...] [MM, SLUB]
>> 5331 Enabling slub_debug allows one to determine the
>> 5332 culprit if slab objects become corrupted. Enabling
>> 5333 slub_debug can create guard zones around objects and
>> 5334 may poison objects when not in use. Also tracks the
>> 5335 last alloc / free. For more information see
>> 5336 Documentation/vm/slub.rst.
>> 5337
>> 5338 slub_max_order= [MM, SLUB]
>> 5339 Determines the maximum allowed order for slabs.
>> 5340 A high setting may cause OOMs due to memory
>> 5341 fragmentation. For more information see
>> 5342 Documentation/vm/slub.rst.
>> 5343
>> 5344 slub_min_objects= [MM, SLUB]
>> 5345 The minimum number of objects per slab. SLUB will
>> 5346 increase the slab order up to slub_max_order to
>> 5347 generate a sufficiently large slab able to contain
>> 5348 the number of objects indicated. The higher the number
>> 5349 of objects the smaller the overhead of tracking slabs
>> 5350 and the less frequently locks need to be acquired.
>> 5351 For more information see Documentation/vm/slub.rst.
>> 5352
>> 5353 slub_min_order= [MM, SLUB]
>> 5354 Determines the minimum page order for slabs. Must be
>> 5355 lower than slub_max_order.
>> 5356 For more information see Documentation/vm/slub.rst.
>> 5357
>> 5358 slub_merge [MM, SLUB]
>> 5359 Same with slab_merge.
>> 5360
>> 5361 slub_nomerge [MM, SLUB]
>> 5362 Same with slab_nomerge. This is supported for legacy.
>> 5363 See slab_nomerge for more information.
6088 5364
6089 smart2= [HW] 5365 smart2= [HW]
6090 Format: <io1>[,<io2>[ 5366 Format: <io1>[,<io2>[,...,<io8>]]
6091 5367
6092 smp.csd_lock_timeout= [KNL] <<
6093 Specify the period of <<
6094 that smp_call_functio <<
6095 for a CPU to release <<
6096 useful when diagnosin <<
6097 disabling interrupts <<
6098 of time. Defaults to <<
6099 setting a value of ze <<
6100 This feature may be m <<
6101 using the csdlock_deb <<
6102 <<
6103 smp.panic_on_ipistall= [KNL] <<
6104 If a csd_lock_timeout <<
6105 the specified number <<
6106 system. By default, <<
6107 take as long as they <<
6108 for this value provid <<
6109 <<
6110 smsc-ircc2.nopnp [HW] Don't us 5368 smsc-ircc2.nopnp [HW] Don't use PNP to discover SMC devices
6111 smsc-ircc2.ircc_cfg= [HW] Device c 5369 smsc-ircc2.ircc_cfg= [HW] Device configuration I/O port
6112 smsc-ircc2.ircc_sir= [HW] SIR base 5370 smsc-ircc2.ircc_sir= [HW] SIR base I/O port
6113 smsc-ircc2.ircc_fir= [HW] FIR base 5371 smsc-ircc2.ircc_fir= [HW] FIR base I/O port
6114 smsc-ircc2.ircc_irq= [HW] IRQ line 5372 smsc-ircc2.ircc_irq= [HW] IRQ line
6115 smsc-ircc2.ircc_dma= [HW] DMA chan 5373 smsc-ircc2.ircc_dma= [HW] DMA channel
6116 smsc-ircc2.ircc_transceiver= [HW] Tra 5374 smsc-ircc2.ircc_transceiver= [HW] Transceiver type:
6117 0: Toshiba Sa 5375 0: Toshiba Satellite 1800 (GP data pin select)
6118 1: Fast pin s 5376 1: Fast pin select (default)
6119 2: ATC IRMode 5377 2: ATC IRMode
6120 5378
6121 smt= [KNL,MIPS,S390,EARLY] !! 5379 smt [KNL,S390] Set the maximum number of threads (logical
6122 (logical CPUs) to use !! 5380 CPUs) to use per physical CPU on systems capable of
6123 capable of symmetric !! 5381 symmetric multithreading (SMT). Will be capped to the
6124 be capped to the actu !! 5382 actual hardware limit.
6125 Format: <integer> 5383 Format: <integer>
6126 Default: -1 (no limit 5384 Default: -1 (no limit)
6127 5385
6128 softlockup_panic= 5386 softlockup_panic=
6129 [KNL] Should the soft 5387 [KNL] Should the soft-lockup detector generate panics.
6130 Format: 0 | 1 5388 Format: 0 | 1
6131 5389
6132 A value of 1 instruct 5390 A value of 1 instructs the soft-lockup detector
6133 to panic the machine 5391 to panic the machine when a soft-lockup occurs. It is
6134 also controlled by th 5392 also controlled by the kernel.softlockup_panic sysctl
6135 and CONFIG_BOOTPARAM_ 5393 and CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC, which is the
6136 respective build-time 5394 respective build-time switch to that functionality.
6137 5395
6138 softlockup_all_cpu_backtrace= 5396 softlockup_all_cpu_backtrace=
6139 [KNL] Should the soft 5397 [KNL] Should the soft-lockup detector generate
6140 backtraces on all cpu 5398 backtraces on all cpus.
6141 Format: 0 | 1 5399 Format: 0 | 1
6142 5400
6143 sonypi.*= [HW] Sony Programmabl 5401 sonypi.*= [HW] Sony Programmable I/O Control Device driver
6144 See Documentation/adm 5402 See Documentation/admin-guide/laptops/sonypi.rst
6145 5403
6146 spectre_bhi= [X86] Control mitigat 5404 spectre_bhi= [X86] Control mitigation of Branch History Injection
6147 (BHI) vulnerability. 5405 (BHI) vulnerability. This setting affects the
6148 deployment of the HW 5406 deployment of the HW BHI control and the SW BHB
6149 clearing sequence. 5407 clearing sequence.
6150 5408
6151 on - (default) En !! 5409 on - (default) Enable the HW or SW mitigation
6152 needed. Thi !! 5410 as needed.
6153 both syscall !! 5411 off - Disable the mitigation.
6154 vmexit - On systems w <<
6155 available, e <<
6156 ONLY. On su <<
6157 protected fr <<
6158 may still be <<
6159 off - Disable the <<
6160 5412
6161 spectre_v2= [X86,EARLY] Control m !! 5413 spectre_v2= [X86] Control mitigation of Spectre variant 2
6162 (indirect branch spec 5414 (indirect branch speculation) vulnerability.
6163 The default operation 5415 The default operation protects the kernel from
6164 user space attacks. 5416 user space attacks.
6165 5417
6166 on - unconditionall 5418 on - unconditionally enable, implies
6167 spectre_v2_use 5419 spectre_v2_user=on
6168 off - unconditionall 5420 off - unconditionally disable, implies
6169 spectre_v2_use 5421 spectre_v2_user=off
6170 auto - kernel detects 5422 auto - kernel detects whether your CPU model is
6171 vulnerable 5423 vulnerable
6172 5424
6173 Selecting 'on' will, 5425 Selecting 'on' will, and 'auto' may, choose a
6174 mitigation method at 5426 mitigation method at run time according to the
6175 CPU, the available mi 5427 CPU, the available microcode, the setting of the
6176 CONFIG_MITIGATION_RET !! 5428 CONFIG_RETPOLINE configuration option, and the
6177 and the compiler with !! 5429 compiler with which the kernel was built.
6178 5430
6179 Selecting 'on' will a 5431 Selecting 'on' will also enable the mitigation
6180 against user space to 5432 against user space to user space task attacks.
6181 5433
6182 Selecting 'off' will 5434 Selecting 'off' will disable both the kernel and
6183 the user space protec 5435 the user space protections.
6184 5436
6185 Specific mitigations 5437 Specific mitigations can also be selected manually:
6186 5438
6187 retpoline - r 5439 retpoline - replace indirect branches
6188 retpoline,generic - R 5440 retpoline,generic - Retpolines
6189 retpoline,lfence - L 5441 retpoline,lfence - LFENCE; indirect branch
6190 retpoline,amd - a 5442 retpoline,amd - alias for retpoline,lfence
6191 eibrs - E 5443 eibrs - Enhanced/Auto IBRS
6192 eibrs,retpoline - E 5444 eibrs,retpoline - Enhanced/Auto IBRS + Retpolines
6193 eibrs,lfence - E 5445 eibrs,lfence - Enhanced/Auto IBRS + LFENCE
6194 ibrs - u 5446 ibrs - use IBRS to protect kernel
6195 5447
6196 Not specifying this o 5448 Not specifying this option is equivalent to
6197 spectre_v2=auto. 5449 spectre_v2=auto.
6198 5450
6199 spectre_v2_user= 5451 spectre_v2_user=
6200 [X86] Control mitigat 5452 [X86] Control mitigation of Spectre variant 2
6201 (indirect branch spec 5453 (indirect branch speculation) vulnerability between
6202 user space tasks 5454 user space tasks
6203 5455
6204 on - Uncondition 5456 on - Unconditionally enable mitigations. Is
6205 enforced by 5457 enforced by spectre_v2=on
6206 5458
6207 off - Uncondition 5459 off - Unconditionally disable mitigations. Is
6208 enforced by 5460 enforced by spectre_v2=off
6209 5461
6210 prctl - Indirect br 5462 prctl - Indirect branch speculation is enabled,
6211 but mitigat 5463 but mitigation can be enabled via prctl
6212 per thread. 5464 per thread. The mitigation control state
6213 is inherite 5465 is inherited on fork.
6214 5466
6215 prctl,ibpb 5467 prctl,ibpb
6216 - Like "prctl 5468 - Like "prctl" above, but only STIBP is
6217 controlled 5469 controlled per thread. IBPB is issued
6218 always when 5470 always when switching between different user
6219 space proce 5471 space processes.
6220 5472
6221 seccomp 5473 seccomp
6222 - Same as "pr 5474 - Same as "prctl" above, but all seccomp
6223 threads wil 5475 threads will enable the mitigation unless
6224 they explic 5476 they explicitly opt out.
6225 5477
6226 seccomp,ibpb 5478 seccomp,ibpb
6227 - Like "secco 5479 - Like "seccomp" above, but only STIBP is
6228 controlled 5480 controlled per thread. IBPB is issued
6229 always when 5481 always when switching between different
6230 user space 5482 user space processes.
6231 5483
6232 auto - Kernel sele 5484 auto - Kernel selects the mitigation depending on
6233 the availab 5485 the available CPU features and vulnerability.
6234 5486
6235 Default mitigation: " !! 5487 Default mitigation:
>> 5488 If CONFIG_SECCOMP=y then "seccomp", otherwise "prctl"
6236 5489
6237 Not specifying this o 5490 Not specifying this option is equivalent to
6238 spectre_v2_user=auto. 5491 spectre_v2_user=auto.
6239 5492
6240 spec_rstack_overflow= 5493 spec_rstack_overflow=
6241 [X86,EARLY] Control R !! 5494 [X86] Control RAS overflow mitigation on AMD Zen CPUs
6242 5495
6243 off - Dis 5496 off - Disable mitigation
6244 microcode - Ena 5497 microcode - Enable microcode mitigation only
6245 safe-ret - Ena 5498 safe-ret - Enable sw-only safe RET mitigation (default)
6246 ibpb - Ena 5499 ibpb - Enable mitigation by issuing IBPB on
6247 ker 5500 kernel entry
6248 ibpb-vmexit - Iss 5501 ibpb-vmexit - Issue IBPB only on VMEXIT
6249 (cl 5502 (cloud-specific mitigation)
6250 5503
6251 spec_store_bypass_disable= 5504 spec_store_bypass_disable=
6252 [HW,EARLY] Control Sp !! 5505 [HW] Control Speculative Store Bypass (SSB) Disable mitigation
6253 (Speculative Store By 5506 (Speculative Store Bypass vulnerability)
6254 5507
6255 Certain CPUs are vuln 5508 Certain CPUs are vulnerable to an exploit against a
6256 a common industry wid 5509 a common industry wide performance optimization known
6257 as "Speculative Store 5510 as "Speculative Store Bypass" in which recent stores
6258 to the same memory lo 5511 to the same memory location may not be observed by
6259 later loads during sp 5512 later loads during speculative execution. The idea
6260 is that such stores a 5513 is that such stores are unlikely and that they can
6261 be detected prior to 5514 be detected prior to instruction retirement at the
6262 end of a particular s 5515 end of a particular speculation execution window.
6263 5516
6264 In vulnerable process 5517 In vulnerable processors, the speculatively forwarded
6265 store can be used in 5518 store can be used in a cache side channel attack, for
6266 example to read memor 5519 example to read memory to which the attacker does not
6267 directly have access 5520 directly have access (e.g. inside sandboxed code).
6268 5521
6269 This parameter contro 5522 This parameter controls whether the Speculative Store
6270 Bypass optimization i 5523 Bypass optimization is used.
6271 5524
6272 On x86 the options ar 5525 On x86 the options are:
6273 5526
6274 on - Uncondition 5527 on - Unconditionally disable Speculative Store Bypass
6275 off - Uncondition 5528 off - Unconditionally enable Speculative Store Bypass
6276 auto - Kernel dete 5529 auto - Kernel detects whether the CPU model contains an
6277 implementat 5530 implementation of Speculative Store Bypass and
6278 picks the m 5531 picks the most appropriate mitigation. If the
6279 CPU is not 5532 CPU is not vulnerable, "off" is selected. If the
6280 CPU is vuln 5533 CPU is vulnerable the default mitigation is
6281 architectur 5534 architecture and Kconfig dependent. See below.
6282 prctl - Control Spe 5535 prctl - Control Speculative Store Bypass per thread
6283 via prctl. 5536 via prctl. Speculative Store Bypass is enabled
6284 for a proce 5537 for a process by default. The state of the control
6285 is inherite 5538 is inherited on fork.
6286 seccomp - Same as "pr 5539 seccomp - Same as "prctl" above, but all seccomp threads
6287 will disabl 5540 will disable SSB unless they explicitly opt out.
6288 5541
6289 Default mitigations: 5542 Default mitigations:
6290 X86: "prctl" !! 5543 X86: If CONFIG_SECCOMP=y "seccomp", otherwise "prctl"
6291 5544
6292 On powerpc the option 5545 On powerpc the options are:
6293 5546
6294 on,auto - On Power8 a 5547 on,auto - On Power8 and Power9 insert a store-forwarding
6295 barrier on 5548 barrier on kernel entry and exit. On Power7
6296 perform a s 5549 perform a software flush on kernel entry and
6297 exit. 5550 exit.
6298 off - No action. 5551 off - No action.
6299 5552
6300 Not specifying this o 5553 Not specifying this option is equivalent to
6301 spec_store_bypass_dis 5554 spec_store_bypass_disable=auto.
6302 5555
>> 5556 spia_io_base= [HW,MTD]
>> 5557 spia_fio_base=
>> 5558 spia_pedr=
>> 5559 spia_peddr=
>> 5560
6303 split_lock_detect= 5561 split_lock_detect=
6304 [X86] Enable split lo 5562 [X86] Enable split lock detection or bus lock detection
6305 5563
6306 When enabled (and if 5564 When enabled (and if hardware support is present), atomic
6307 instructions that acc 5565 instructions that access data across cache line
6308 boundaries will resul 5566 boundaries will result in an alignment check exception
6309 for split lock detect 5567 for split lock detection or a debug exception for
6310 bus lock detection. 5568 bus lock detection.
6311 5569
6312 off - not enabled 5570 off - not enabled
6313 5571
6314 warn - the kernel 5572 warn - the kernel will emit rate-limited warnings
6315 about appli 5573 about applications triggering the #AC
6316 exception o 5574 exception or the #DB exception. This mode is
6317 the default 5575 the default on CPUs that support split lock
6318 detection o 5576 detection or bus lock detection. Default
6319 behavior is 5577 behavior is by #AC if both features are
6320 enabled in 5578 enabled in hardware.
6321 5579
6322 fatal - the kernel 5580 fatal - the kernel will send SIGBUS to applications
6323 that trigge 5581 that trigger the #AC exception or the #DB
6324 exception. 5582 exception. Default behavior is by #AC if
6325 both featur 5583 both features are enabled in hardware.
6326 5584
6327 ratelimit:N - 5585 ratelimit:N -
6328 Set system 5586 Set system wide rate limit to N bus locks
6329 per second 5587 per second for bus lock detection.
6330 0 < N <= 10 5588 0 < N <= 1000.
6331 5589
6332 N/A for spl 5590 N/A for split lock detection.
6333 5591
6334 5592
6335 If an #AC exception i 5593 If an #AC exception is hit in the kernel or in
6336 firmware (i.e. not wh 5594 firmware (i.e. not while executing in user mode)
6337 the kernel will oops 5595 the kernel will oops in either "warn" or "fatal"
6338 mode. 5596 mode.
6339 5597
6340 #DB exception for bus 5598 #DB exception for bus lock is triggered only when
6341 CPL > 0. 5599 CPL > 0.
6342 5600
6343 srbds= [X86,INTEL,EARLY] !! 5601 srbds= [X86,INTEL]
6344 Control the Special R 5602 Control the Special Register Buffer Data Sampling
6345 (SRBDS) mitigation. 5603 (SRBDS) mitigation.
6346 5604
6347 Certain CPUs are vuln 5605 Certain CPUs are vulnerable to an MDS-like
6348 exploit which can lea 5606 exploit which can leak bits from the random
6349 number generator. 5607 number generator.
6350 5608
6351 By default, this issu 5609 By default, this issue is mitigated by
6352 microcode. However, 5610 microcode. However, the microcode fix can cause
6353 the RDRAND and RDSEED 5611 the RDRAND and RDSEED instructions to become
6354 much slower. Among o 5612 much slower. Among other effects, this will
6355 result in reduced thr 5613 result in reduced throughput from /dev/urandom.
6356 5614
6357 The microcode mitigat 5615 The microcode mitigation can be disabled with
6358 the following option: 5616 the following option:
6359 5617
6360 off: Disable mitig 5618 off: Disable mitigation and remove
6361 performance i 5619 performance impact to RDRAND and RDSEED
6362 5620
6363 srcutree.big_cpu_lim [KNL] <<
6364 Specifies the number <<
6365 large system, such th <<
6366 should immediately al <<
6367 This kernel-boot para <<
6368 but takes effect only <<
6369 bits of srcutree.conv <<
6370 (decide at boot). <<
6371 <<
6372 srcutree.convert_to_big [KNL] <<
6373 Specifies under what <<
6374 srcu_struct structure <<
6375 form, that is, with a <<
6376 <<
6377 0: Never. <<
6378 1: At ini <<
6379 2: When r <<
6380 3: Decide <<
6381 0x1X: Above <<
6382 <<
6383 Either way, the srcu_ <<
6384 on the actual runtime <<
6385 instead of the compil <<
6386 <<
6387 srcutree.counter_wrap_check [KNL] 5621 srcutree.counter_wrap_check [KNL]
6388 Specifies how frequen 5622 Specifies how frequently to check for
6389 grace-period sequence 5623 grace-period sequence counter wrap for the
6390 srcu_data structure's 5624 srcu_data structure's ->srcu_gp_seq_needed field.
6391 The greater the numbe 5625 The greater the number of bits set in this kernel
6392 parameter, the less f 5626 parameter, the less frequently counter wrap will
6393 be checked for. Note 5627 be checked for. Note that the bottom two bits
6394 are ignored. 5628 are ignored.
6395 5629
6396 srcutree.exp_holdoff [KNL] 5630 srcutree.exp_holdoff [KNL]
6397 Specifies how many na 5631 Specifies how many nanoseconds must elapse
6398 since the end of the 5632 since the end of the last SRCU grace period for
6399 a given srcu_struct u 5633 a given srcu_struct until the next normal SRCU
6400 grace period will be 5634 grace period will be considered for automatic
6401 expediting. Set to z 5635 expediting. Set to zero to disable automatic
6402 expediting. 5636 expediting.
6403 5637
6404 srcutree.srcu_max_nodelay [KNL] !! 5638 ssbd= [ARM64,HW]
6405 Specifies the number <<
6406 per jiffy for which t <<
6407 worker thread will be <<
6408 delay. Beyond this li <<
6409 be rescheduled with a <<
6410 <<
6411 srcutree.srcu_max_nodelay_phase [KNL] <<
6412 Specifies the per-gra <<
6413 non-sleeping polls of <<
6414 grace period worker t <<
6415 with a sleep delay of <<
6416 rescan of the readers <<
6417 <<
6418 srcutree.srcu_retry_check_delay [KNL] <<
6419 Specifies number of m <<
6420 delay between each no <<
6421 <<
6422 srcutree.small_contention_lim [KNL] <<
6423 Specifies the number <<
6424 events per jiffy will <<
6425 initiating a conversi <<
6426 structure to big form <<
6427 srcutree.convert_to_b <<
6428 set for contention-ba <<
6429 <<
6430 ssbd= [ARM64,HW,EARLY] <<
6431 Speculative Store Byp 5639 Speculative Store Bypass Disable control
6432 5640
6433 On CPUs that are vuln 5641 On CPUs that are vulnerable to the Speculative
6434 Store Bypass vulnerab 5642 Store Bypass vulnerability and offer a
6435 firmware based mitiga 5643 firmware based mitigation, this parameter
6436 indicates how the mit 5644 indicates how the mitigation should be used:
6437 5645
6438 force-on: Unconditio 5646 force-on: Unconditionally enable mitigation for
6439 for both k 5647 for both kernel and userspace
6440 force-off: Unconditio 5648 force-off: Unconditionally disable mitigation for
6441 for both k 5649 for both kernel and userspace
6442 kernel: Always ena 5650 kernel: Always enable mitigation in the
6443 kernel, an 5651 kernel, and offer a prctl interface
6444 to allow u 5652 to allow userspace to register its
6445 interest i 5653 interest in being mitigated too.
6446 5654
6447 stack_guard_gap= [MM] 5655 stack_guard_gap= [MM]
6448 override the default 5656 override the default stack gap protection. The value
6449 is in page units and 5657 is in page units and it defines how many pages prior
6450 to (for stacks growin 5658 to (for stacks growing down) resp. after (for stacks
6451 growing up) the main 5659 growing up) the main stack are reserved for no other
6452 mapping. Default valu 5660 mapping. Default value is 256 pages.
6453 5661
6454 stack_depot_disable= [KNL,EARLY] !! 5662 stack_depot_disable= [KNL]
6455 Setting this to true 5663 Setting this to true through kernel command line will
6456 disable the stack dep 5664 disable the stack depot thereby saving the static memory
6457 consumed by the stack 5665 consumed by the stack hash table. By default this is set
6458 to false. 5666 to false.
6459 5667
6460 stacktrace [FTRACE] 5668 stacktrace [FTRACE]
6461 Enabled the stack tra 5669 Enabled the stack tracer on boot up.
6462 5670
6463 stacktrace_filter=[function-list] 5671 stacktrace_filter=[function-list]
6464 [FTRACE] Limit the fu 5672 [FTRACE] Limit the functions that the stack tracer
6465 will trace at boot up 5673 will trace at boot up. function-list is a comma-separated
6466 list of functions. Th 5674 list of functions. This list can be changed at run
6467 time by the stack_tra 5675 time by the stack_trace_filter file in the debugfs
6468 tracing directory. No 5676 tracing directory. Note, this enables stack tracing
6469 and the stacktrace ab 5677 and the stacktrace above is not needed.
6470 5678
6471 sti= [PARISC,HW] 5679 sti= [PARISC,HW]
6472 Format: <num> 5680 Format: <num>
6473 Set the STI (builtin 5681 Set the STI (builtin display/keyboard on the HP-PARISC
6474 machines) console (gr 5682 machines) console (graphic card) which should be used
6475 as the initial boot-c 5683 as the initial boot-console.
6476 See also comment in d 5684 See also comment in drivers/video/console/sticore.c.
6477 5685
6478 sti_font= [HW] 5686 sti_font= [HW]
6479 See comment in driver 5687 See comment in drivers/video/console/sticore.c.
6480 5688
6481 stifb= [HW] 5689 stifb= [HW]
6482 Format: bpp:<bpp1>[:< 5690 Format: bpp:<bpp1>[:<bpp2>[:<bpp3>...]]
6483 5691
6484 strict_sas_size= <<
6485 [X86] <<
6486 Format: <bool> <<
6487 Enable or disable str <<
6488 against the required <<
6489 depends on the suppor <<
6490 be used to filter out <<
6491 not yet been made awa <<
6492 <<
6493 stress_hpt [PPC,EARLY] <<
6494 Limits the number of <<
6495 page table to increas <<
6496 faults on kernel addr <<
6497 <<
6498 stress_slb [PPC,EARLY] <<
6499 Limits the number of <<
6500 them frequently to in <<
6501 on kernel addresses. <<
6502 <<
6503 sunrpc.min_resvport= 5692 sunrpc.min_resvport=
6504 sunrpc.max_resvport= 5693 sunrpc.max_resvport=
6505 [NFS,SUNRPC] 5694 [NFS,SUNRPC]
6506 SunRPC servers often 5695 SunRPC servers often require that client requests
6507 originate from a priv 5696 originate from a privileged port (i.e. a port in the
6508 range 0 < portnr < 10 5697 range 0 < portnr < 1024).
6509 An administrator who 5698 An administrator who wishes to reserve some of these
6510 ports for other uses 5699 ports for other uses may adjust the range that the
6511 kernel's sunrpc clien 5700 kernel's sunrpc client considers to be privileged
6512 using these two param 5701 using these two parameters to set the minimum and
6513 maximum port values. 5702 maximum port values.
6514 5703
6515 sunrpc.svc_rpc_per_connection_limit= 5704 sunrpc.svc_rpc_per_connection_limit=
6516 [NFS,SUNRPC] 5705 [NFS,SUNRPC]
6517 Limit the number of r 5706 Limit the number of requests that the server will
6518 process in parallel f 5707 process in parallel from a single connection.
6519 The default value is 5708 The default value is 0 (no limit).
6520 5709
6521 sunrpc.pool_mode= 5710 sunrpc.pool_mode=
6522 [NFS] 5711 [NFS]
6523 Control how the NFS s 5712 Control how the NFS server code allocates CPUs to
6524 service thread pools. 5713 service thread pools. Depending on how many NICs
6525 you have and where th 5714 you have and where their interrupts are bound, this
6526 option will affect wh 5715 option will affect which CPUs will do NFS serving.
6527 Note: this parameter 5716 Note: this parameter cannot be changed while the
6528 NFS server is running 5717 NFS server is running.
6529 5718
6530 auto the serve 5719 auto the server chooses an appropriate mode
6531 automatic 5720 automatically using heuristics
6532 global a single 5721 global a single global pool contains all CPUs
6533 percpu one pool 5722 percpu one pool for each CPU
6534 pernode one pool 5723 pernode one pool for each NUMA node (equivalent
6535 to global 5724 to global on non-NUMA machines)
6536 5725
6537 sunrpc.tcp_slot_table_entries= 5726 sunrpc.tcp_slot_table_entries=
6538 sunrpc.udp_slot_table_entries= 5727 sunrpc.udp_slot_table_entries=
6539 [NFS,SUNRPC] 5728 [NFS,SUNRPC]
6540 Sets the upper limit 5729 Sets the upper limit on the number of simultaneous
6541 RPC calls that can be 5730 RPC calls that can be sent from the client to a
6542 server. Increasing th 5731 server. Increasing these values may allow you to
6543 improve throughput, b 5732 improve throughput, but will also increase the
6544 amount of memory rese 5733 amount of memory reserved for use by the client.
6545 5734
6546 suspend.pm_test_delay= 5735 suspend.pm_test_delay=
6547 [SUSPEND] 5736 [SUSPEND]
6548 Sets the number of se 5737 Sets the number of seconds to remain in a suspend test
6549 mode before resuming 5738 mode before resuming the system (see
6550 /sys/power/pm_test). 5739 /sys/power/pm_test). Only available when CONFIG_PM_DEBUG
6551 is set. Default value 5740 is set. Default value is 5.
6552 5741
6553 svm= [PPC] 5742 svm= [PPC]
6554 Format: { on | off | 5743 Format: { on | off | y | n | 1 | 0 }
6555 This parameter contro 5744 This parameter controls use of the Protected
6556 Execution Facility on 5745 Execution Facility on pSeries.
6557 5746
6558 swiotlb= [ARM,PPC,MIPS,X86,S39 !! 5747 swapaccount=[0|1]
6559 Format: { <int> [,<in !! 5748 [KNL] Enable accounting of swap in memory resource
>> 5749 controller if no parameter or 1 is given or disable
>> 5750 it if 0 is given (See Documentation/admin-guide/cgroup-v1/memory.rst)
>> 5751
>> 5752 swiotlb= [ARM,IA-64,PPC,MIPS,X86]
>> 5753 Format: { <int> | force | noforce }
6560 <int> -- Number of I/ 5754 <int> -- Number of I/O TLB slabs
6561 <int> -- Second integ <<
6562 areas with t <<
6563 to a power o <<
6564 force -- force using 5755 force -- force using of bounce buffers even if they
6565 wouldn't be 5756 wouldn't be automatically used by the kernel
6566 noforce -- Never use 5757 noforce -- Never use bounce buffers (for debugging)
6567 5758
6568 switches= [HW,M68k,EARLY] !! 5759 switches= [HW,M68k]
6569 5760
6570 sysctl.*= [KNL] 5761 sysctl.*= [KNL]
6571 Set a sysctl paramete 5762 Set a sysctl parameter, right before loading the init
6572 process, as if the va 5763 process, as if the value was written to the respective
6573 /proc/sys/... file. B 5764 /proc/sys/... file. Both '.' and '/' are recognized as
6574 separators. Unrecogni 5765 separators. Unrecognized parameters and invalid values
6575 are reported in the k 5766 are reported in the kernel log. Sysctls registered
6576 later by a loaded mod 5767 later by a loaded module cannot be set this way.
6577 Example: sysctl.vm.sw 5768 Example: sysctl.vm.swappiness=40
6578 5769
>> 5770 sysfs.deprecated=0|1 [KNL]
>> 5771 Enable/disable old style sysfs layout for old udev
>> 5772 on older distributions. When this option is enabled
>> 5773 very new udev will not work anymore. When this option
>> 5774 is disabled (or CONFIG_SYSFS_DEPRECATED not compiled)
>> 5775 in older udev will not work anymore.
>> 5776 Default depends on CONFIG_SYSFS_DEPRECATED_V2 set in
>> 5777 the kernel configuration.
>> 5778
6579 sysrq_always_enabled 5779 sysrq_always_enabled
6580 [KNL] 5780 [KNL]
6581 Ignore sysrq setting 5781 Ignore sysrq setting - this boot parameter will
6582 neutralize any effect 5782 neutralize any effect of /proc/sys/kernel/sysrq.
6583 Useful for debugging. 5783 Useful for debugging.
6584 5784
6585 tcpmhash_entries= [KNL,NET] 5785 tcpmhash_entries= [KNL,NET]
6586 Set the number of tcp 5786 Set the number of tcp_metrics_hash slots.
6587 Default value is 8192 5787 Default value is 8192 or 16384 depending on total
6588 ram pages. This is us 5788 ram pages. This is used to specify the TCP metrics
6589 cache size. See Docum 5789 cache size. See Documentation/networking/ip-sysctl.rst
6590 "tcp_no_metrics_save" 5790 "tcp_no_metrics_save" section for more details.
6591 5791
6592 tdfx= [HW,DRM] 5792 tdfx= [HW,DRM]
6593 5793
6594 test_suspend= [SUSPEND] !! 5794 test_suspend= [SUSPEND][,N]
6595 Format: { "mem" | "st <<
6596 Specify "mem" (for Su 5795 Specify "mem" (for Suspend-to-RAM) or "standby" (for
6597 standby suspend) or " 5796 standby suspend) or "freeze" (for suspend type freeze)
6598 as the system sleep s 5797 as the system sleep state during system startup with
6599 the optional capabili 5798 the optional capability to repeat N number of times.
6600 The system is woken f 5799 The system is woken from this state using a
6601 wakeup-capable RTC al 5800 wakeup-capable RTC alarm.
6602 5801
6603 thash_entries= [KNL,NET] 5802 thash_entries= [KNL,NET]
6604 Set number of hash bu 5803 Set number of hash buckets for TCP connection
6605 5804
6606 thermal.act= [HW,ACPI] 5805 thermal.act= [HW,ACPI]
6607 -1: disable all activ 5806 -1: disable all active trip points in all thermal zones
6608 <degrees C>: override 5807 <degrees C>: override all lowest active trip points
6609 5808
6610 thermal.crt= [HW,ACPI] 5809 thermal.crt= [HW,ACPI]
6611 -1: disable all criti 5810 -1: disable all critical trip points in all thermal zones
6612 <degrees C>: override 5811 <degrees C>: override all critical trip points
6613 5812
6614 thermal.off= [HW,ACPI] 5813 thermal.off= [HW,ACPI]
6615 1: disable ACPI therm 5814 1: disable ACPI thermal control
6616 5815
6617 thermal.psv= [HW,ACPI] 5816 thermal.psv= [HW,ACPI]
6618 -1: disable all passi 5817 -1: disable all passive trip points
6619 <degrees C>: override 5818 <degrees C>: override all passive trip points to this
6620 value 5819 value
6621 5820
6622 thermal.tzp= [HW,ACPI] 5821 thermal.tzp= [HW,ACPI]
6623 Specify global defaul 5822 Specify global default ACPI thermal zone polling rate
6624 <deci-seconds>: poll 5823 <deci-seconds>: poll all this frequency
6625 0: no polling (defaul 5824 0: no polling (default)
6626 5825
6627 threadirqs [KNL,EARLY] !! 5826 threadirqs [KNL]
6628 Force threading of al 5827 Force threading of all interrupt handlers except those
6629 marked explicitly IRQ 5828 marked explicitly IRQF_NO_THREAD.
6630 5829
6631 topology= [S390,EARLY] !! 5830 topology= [S390]
6632 Format: {off | on} 5831 Format: {off | on}
6633 Specify if the kernel 5832 Specify if the kernel should make use of the cpu
6634 topology information 5833 topology information if the hardware supports this.
6635 The scheduler will ma 5834 The scheduler will make use of this information and
6636 e.g. base its process 5835 e.g. base its process migration decisions on it.
6637 Default is on. 5836 Default is on.
6638 5837
>> 5838 topology_updates= [KNL, PPC, NUMA]
>> 5839 Format: {off}
>> 5840 Specify if the kernel should ignore (off)
>> 5841 topology updates sent by the hypervisor to this
>> 5842 LPAR.
>> 5843
6639 torture.disable_onoff_at_boot= [KNL] 5844 torture.disable_onoff_at_boot= [KNL]
6640 Prevent the CPU-hotpl 5845 Prevent the CPU-hotplug component of torturing
6641 until after init has 5846 until after init has spawned.
6642 5847
6643 torture.ftrace_dump_at_shutdown= [KNL 5848 torture.ftrace_dump_at_shutdown= [KNL]
6644 Dump the ftrace buffe 5849 Dump the ftrace buffer at torture-test shutdown,
6645 even if there were no 5850 even if there were no errors. This can be a
6646 very costly operation 5851 very costly operation when many torture tests
6647 are running concurren 5852 are running concurrently, especially on systems
6648 with rotating-rust st 5853 with rotating-rust storage.
6649 5854
6650 torture.verbose_sleep_frequency= [KNL 5855 torture.verbose_sleep_frequency= [KNL]
6651 Specifies how many ve 5856 Specifies how many verbose printk()s should be
6652 emitted between each 5857 emitted between each sleep. The default of zero
6653 disables verbose-prin 5858 disables verbose-printk() sleeping.
6654 5859
6655 torture.verbose_sleep_duration= [KNL] 5860 torture.verbose_sleep_duration= [KNL]
6656 Duration of each verb 5861 Duration of each verbose-printk() sleep in jiffies.
6657 5862
>> 5863 tp720= [HW,PS2]
>> 5864
6658 tpm_suspend_pcr=[HW,TPM] 5865 tpm_suspend_pcr=[HW,TPM]
6659 Format: integer pcr i 5866 Format: integer pcr id
6660 Specify that at suspe 5867 Specify that at suspend time, the tpm driver
6661 should extend the spe 5868 should extend the specified pcr with zeros,
6662 as a workaround for s 5869 as a workaround for some chips which fail to
6663 flush the last writte 5870 flush the last written pcr on TPM_SaveState.
6664 This will guarantee t 5871 This will guarantee that all the other pcrs
6665 are saved. 5872 are saved.
6666 5873
6667 tpm_tis.interrupts= [HW,TPM] <<
6668 Enable interrupts for <<
6669 for the FIFO interfac <<
6670 (0). For more informa <<
6671 defined by Trusted Co <<
6672 https://trustedcomput <<
6673 <<
6674 tp_printk [FTRACE] <<
6675 Have the tracepoints <<
6676 tracing ring buffer. <<
6677 where the system hang <<
6678 option for reading th <<
6679 ftrace_dump_on_oops. <<
6680 <<
6681 To turn off having tr <<
6682 echo 0 > /proc/sys/k <<
6683 Note, echoing 1 into <<
6684 tp_printk kernel cmdl <<
6685 <<
6686 The tp_printk_stop_on <<
6687 to stop the printing <<
6688 late_initcall_sync. <<
6689 <<
6690 ** CAUTION ** <<
6691 <<
6692 Having tracepoints se <<
6693 frequency tracepoints <<
6694 the system to live lo <<
6695 <<
6696 tp_printk_stop_on_boot [FTRACE] <<
6697 When tp_printk (above <<
6698 on the console. It ma <<
6699 printing of events du <<
6700 make the system inope <<
6701 <<
6702 This command line opt <<
6703 to console at the lat <<
6704 <<
6705 trace_buf_size=nn[KMG] 5874 trace_buf_size=nn[KMG]
6706 [FTRACE] will set tra 5875 [FTRACE] will set tracing buffer size on each cpu.
6707 5876
6708 trace_clock= [FTRACE] Set the cloc <<
6709 at boot up. <<
6710 local - Use the per C <<
6711 (converted in <<
6712 depending on <<
6713 in sync betwe <<
6714 global - Event time s <<
6715 CPUs. May be <<
6716 but better fo <<
6717 counter - Simple coun <<
6718 note, some co <<
6719 infrastructur <<
6720 once per even <<
6721 uptime - Use jiffies <<
6722 perf - Use the same c <<
6723 mono - Use ktime_get_ <<
6724 mono_raw - Use ktime_ <<
6725 stamps. <<
6726 boot - Use ktime_get_ <<
6727 Architectures may add <<
6728 Documentation/trace/f <<
6729 <<
6730 trace_event=[event-list] 5877 trace_event=[event-list]
6731 [FTRACE] Set and star 5878 [FTRACE] Set and start specified trace events in order
6732 to facilitate early b 5879 to facilitate early boot debugging. The event-list is a
6733 comma-separated list 5880 comma-separated list of trace events to enable. See
6734 also Documentation/tr 5881 also Documentation/trace/events.rst
6735 5882
6736 trace_instance=[instance-info] <<
6737 [FTRACE] Create a rin <<
6738 This will be listed i <<
6739 <<
6740 /sys/kernel/t <<
6741 <<
6742 Events can be enabled <<
6743 via: <<
6744 <<
6745 trace_instanc <<
6746 <<
6747 Note, the "<system*>: <<
6748 unique. <<
6749 <<
6750 trace_instanc <<
6751 <<
6752 will enable the "sche <<
6753 the same thing would <<
6754 event, and all events <<
6755 <<
6756 trace_options=[option-list] 5883 trace_options=[option-list]
6757 [FTRACE] Enable or di 5884 [FTRACE] Enable or disable tracer options at boot.
6758 The option-list is a 5885 The option-list is a comma delimited list of options
6759 that can be enabled o 5886 that can be enabled or disabled just as if you were
6760 to echo the option na 5887 to echo the option name into
6761 5888
6762 /sys/kernel/traci !! 5889 /sys/kernel/debug/tracing/trace_options
6763 5890
6764 For example, to enabl 5891 For example, to enable stacktrace option (to dump the
6765 stack trace of each e 5892 stack trace of each event), add to the command line:
6766 5893
6767 trace_options=s 5894 trace_options=stacktrace
6768 5895
6769 See also Documentatio 5896 See also Documentation/trace/ftrace.rst "trace options"
6770 section. 5897 section.
6771 5898
6772 trace_trigger=[trigger-list] !! 5899 tp_printk[FTRACE]
6773 [FTRACE] Add a event !! 5900 Have the tracepoints sent to printk as well as the
6774 Set a trigger on top !! 5901 tracing ring buffer. This is useful for early boot up
6775 filter. !! 5902 where the system hangs or reboots and does not give the
>> 5903 option for reading the tracing buffer or performing a
>> 5904 ftrace_dump_on_oops.
6776 5905
6777 The format is is "tra !! 5906 To turn off having tracepoints sent to printk,
6778 Where more than one t !! 5907 echo 0 > /proc/sys/kernel/tracepoint_printk
>> 5908 Note, echoing 1 into this file without the
>> 5909 tracepoint_printk kernel cmdline option has no effect.
6779 5910
6780 For example: !! 5911 The tp_printk_stop_on_boot (see below) can also be used
>> 5912 to stop the printing of events to console at
>> 5913 late_initcall_sync.
6781 5914
6782 trace_trigger="sche !! 5915 ** CAUTION **
6783 5916
6784 The above will enable !! 5917 Having tracepoints sent to printk() and activating high
6785 event but only trigge !! 5918 frequency tracepoints such as irq or sched, can cause
6786 event is "2" (TASK_UN !! 5919 the system to live lock.
6787 5920
6788 See also "Event trigg !! 5921 tp_printk_stop_on_boot[FTRACE]
>> 5922 When tp_printk (above) is set, it can cause a lot of noise
>> 5923 on the console. It may be useful to only include the
>> 5924 printing of events during boot up, as user space may
>> 5925 make the system inoperable.
6789 5926
>> 5927 This command line option will stop the printing of events
>> 5928 to console at the late_initcall_sync() time frame.
6790 5929
6791 traceoff_on_warning 5930 traceoff_on_warning
6792 [FTRACE] enable this 5931 [FTRACE] enable this option to disable tracing when a
6793 warning is hit. This 5932 warning is hit. This turns off "tracing_on". Tracing can
6794 be enabled again by e 5933 be enabled again by echoing '1' into the "tracing_on"
6795 file located in /sys/ !! 5934 file located in /sys/kernel/debug/tracing/
6796 5935
6797 This option is useful 5936 This option is useful, as it disables the trace before
6798 the WARNING dump is c 5937 the WARNING dump is called, which prevents the trace to
6799 be filled with conten 5938 be filled with content caused by the warning output.
6800 5939
6801 This option can also 5940 This option can also be set at run time via the sysctl
6802 option: kernel/trace 5941 option: kernel/traceoff_on_warning
6803 5942
6804 transparent_hugepage= 5943 transparent_hugepage=
6805 [KNL] 5944 [KNL]
6806 Format: [always|madvi 5945 Format: [always|madvise|never]
6807 Can be used to contro 5946 Can be used to control the default behavior of the system
6808 with respect to trans 5947 with respect to transparent hugepages.
6809 See Documentation/adm 5948 See Documentation/admin-guide/mm/transhuge.rst
6810 for more details. 5949 for more details.
6811 5950
6812 trusted.source= [KEYS] 5951 trusted.source= [KEYS]
6813 Format: <string> 5952 Format: <string>
6814 This parameter identi 5953 This parameter identifies the trust source as a backend
6815 for trusted keys impl 5954 for trusted keys implementation. Supported trust
6816 sources: 5955 sources:
6817 - "tpm" 5956 - "tpm"
6818 - "tee" 5957 - "tee"
6819 - "caam" <<
6820 - "dcp" <<
6821 If not specified then 5958 If not specified then it defaults to iterating through
6822 the trust source list 5959 the trust source list starting with TPM and assigns the
6823 first trust source as 5960 first trust source as a backend which is initialized
6824 successfully during i 5961 successfully during iteration.
6825 5962
6826 trusted.rng= [KEYS] 5963 trusted.rng= [KEYS]
6827 Format: <string> 5964 Format: <string>
6828 The RNG used to gener 5965 The RNG used to generate key material for trusted keys.
6829 Can be one of: 5966 Can be one of:
6830 - "kernel" 5967 - "kernel"
6831 - the same value as t 5968 - the same value as trusted.source: "tpm" or "tee"
6832 - "default" 5969 - "default"
6833 If not specified, "de 5970 If not specified, "default" is used. In this case,
6834 the RNG's choice is l 5971 the RNG's choice is left to each individual trust source.
6835 5972
6836 trusted.dcp_use_otp_key <<
6837 This is intended to b <<
6838 trusted.source=dcp an <<
6839 instead of the DCP UN <<
6840 <<
6841 trusted.dcp_skip_zk_test <<
6842 This is intended to b <<
6843 trusted.source=dcp an <<
6844 blob key is all zeros <<
6845 having this key zero' <<
6846 scenarios. <<
6847 <<
6848 tsc= Disable clocksource s 5973 tsc= Disable clocksource stability checks for TSC.
6849 Format: <string> 5974 Format: <string>
6850 [x86] reliable: mark 5975 [x86] reliable: mark tsc clocksource as reliable, this
6851 disables clocksource 5976 disables clocksource verification at runtime, as well
6852 as the stability chec 5977 as the stability checks done at bootup. Used to enable
6853 high-resolution timer 5978 high-resolution timer mode on older hardware, and in
6854 virtualized environme 5979 virtualized environment.
6855 [x86] noirqtime: Do n 5980 [x86] noirqtime: Do not use TSC to do irq accounting.
6856 Used to run time disa 5981 Used to run time disable IRQ_TIME_ACCOUNTING on any
6857 platforms where RDTSC 5982 platforms where RDTSC is slow and this accounting
6858 can add overhead. 5983 can add overhead.
6859 [x86] unstable: mark 5984 [x86] unstable: mark the TSC clocksource as unstable, this
6860 marks the TSC uncondi 5985 marks the TSC unconditionally unstable at bootup and
6861 avoids any further wo 5986 avoids any further wobbles once the TSC watchdog notices.
6862 [x86] nowatchdog: dis 5987 [x86] nowatchdog: disable clocksource watchdog. Used
6863 in situations with st 5988 in situations with strict latency requirements (where
6864 interruptions from cl 5989 interruptions from clocksource watchdog are not
6865 acceptable). 5990 acceptable).
6866 [x86] recalibrate: fo <<
6867 (HPET or PM timer) on <<
6868 obtained from HW or F <<
6869 Warn if the differenc <<
6870 [x86] watchdog: Use T <<
6871 which to check other <<
6872 only on systems where <<
6873 This will be suppress <<
6874 can be overridden by <<
6875 message will flag any <<
6876 5991
6877 tsc_early_khz= [X86,EARLY] Skip earl !! 5992 tsc_early_khz= [X86] Skip early TSC calibration and use the given
6878 value instead. Useful 5993 value instead. Useful when the early TSC frequency discovery
6879 procedure is not reli 5994 procedure is not reliable, such as on overclocked systems
6880 with CPUID.16h suppor 5995 with CPUID.16h support and partial CPUID.15h support.
6881 Format: <unsigned int 5996 Format: <unsigned int>
6882 5997
6883 tsx= [X86] Control Transac 5998 tsx= [X86] Control Transactional Synchronization
6884 Extensions (TSX) feat 5999 Extensions (TSX) feature in Intel processors that
6885 support TSX control. 6000 support TSX control.
6886 6001
6887 This parameter contro 6002 This parameter controls the TSX feature. The options are:
6888 6003
6889 on - Enable TSX 6004 on - Enable TSX on the system. Although there are
6890 mitigations f 6005 mitigations for all known security vulnerabilities,
6891 TSX has been 6006 TSX has been known to be an accelerator for
6892 several previ 6007 several previous speculation-related CVEs, and
6893 so there may 6008 so there may be unknown security risks associated
6894 with leaving 6009 with leaving it enabled.
6895 6010
6896 off - Disable TSX 6011 off - Disable TSX on the system. (Note that this
6897 option takes 6012 option takes effect only on newer CPUs which are
6898 not vulnerabl 6013 not vulnerable to MDS, i.e., have
6899 MSR_IA32_ARCH 6014 MSR_IA32_ARCH_CAPABILITIES.MDS_NO=1 and which get
6900 the new IA32_ 6015 the new IA32_TSX_CTRL MSR through a microcode
6901 update. This 6016 update. This new MSR allows for the reliable
6902 deactivation 6017 deactivation of the TSX functionality.)
6903 6018
6904 auto - Disable TSX 6019 auto - Disable TSX if X86_BUG_TAA is present,
6905 otherwise e 6020 otherwise enable TSX on the system.
6906 6021
6907 Not specifying this o 6022 Not specifying this option is equivalent to tsx=off.
6908 6023
6909 See Documentation/adm 6024 See Documentation/admin-guide/hw-vuln/tsx_async_abort.rst
6910 for more details. 6025 for more details.
6911 6026
6912 tsx_async_abort= [X86,INTEL,EARLY] Co !! 6027 tsx_async_abort= [X86,INTEL] Control mitigation for the TSX Async
6913 Abort (TAA) vulnerabi 6028 Abort (TAA) vulnerability.
6914 6029
6915 Similar to Micro-arch 6030 Similar to Micro-architectural Data Sampling (MDS)
6916 certain CPUs that sup 6031 certain CPUs that support Transactional
6917 Synchronization Exten 6032 Synchronization Extensions (TSX) are vulnerable to an
6918 exploit against CPU i 6033 exploit against CPU internal buffers which can forward
6919 information to a disc 6034 information to a disclosure gadget under certain
6920 conditions. 6035 conditions.
6921 6036
6922 In vulnerable process 6037 In vulnerable processors, the speculatively forwarded
6923 data can be used in a 6038 data can be used in a cache side channel attack, to
6924 access data to which 6039 access data to which the attacker does not have direct
6925 access. 6040 access.
6926 6041
6927 This parameter contro 6042 This parameter controls the TAA mitigation. The
6928 options are: 6043 options are:
6929 6044
6930 full - Enable T 6045 full - Enable TAA mitigation on vulnerable CPUs
6931 if TSX i 6046 if TSX is enabled.
6932 6047
6933 full,nosmt - Enable T 6048 full,nosmt - Enable TAA mitigation and disable SMT on
6934 vulnerab 6049 vulnerable CPUs. If TSX is disabled, SMT
6935 is not d 6050 is not disabled because CPU is not
6936 vulnerab 6051 vulnerable to cross-thread TAA attacks.
6937 off - Uncondit 6052 off - Unconditionally disable TAA mitigation
6938 6053
6939 On MDS-affected machi 6054 On MDS-affected machines, tsx_async_abort=off can be
6940 prevented by an activ 6055 prevented by an active MDS mitigation as both vulnerabilities
6941 are mitigated with th 6056 are mitigated with the same mechanism so in order to disable
6942 this mitigation, you 6057 this mitigation, you need to specify mds=off too.
6943 6058
6944 Not specifying this o 6059 Not specifying this option is equivalent to
6945 tsx_async_abort=full. 6060 tsx_async_abort=full. On CPUs which are MDS affected
6946 and deploy MDS mitiga 6061 and deploy MDS mitigation, TAA mitigation is not
6947 required and doesn't 6062 required and doesn't provide any additional
6948 mitigation. 6063 mitigation.
6949 6064
6950 For details see: 6065 For details see:
6951 Documentation/admin-g 6066 Documentation/admin-guide/hw-vuln/tsx_async_abort.rst
6952 6067
6953 turbografx.map[2|3]= [HW,JOY] 6068 turbografx.map[2|3]= [HW,JOY]
6954 TurboGraFX parallel p 6069 TurboGraFX parallel port interface
6955 Format: 6070 Format:
6956 <port#>,<js1>,<js2>,< 6071 <port#>,<js1>,<js2>,<js3>,<js4>,<js5>,<js6>,<js7>
6957 See also Documentatio 6072 See also Documentation/input/devices/joystick-parport.rst
6958 6073
6959 udbg-immortal [PPC] When debugging 6074 udbg-immortal [PPC] When debugging early kernel crashes that
6960 happen after console_ 6075 happen after console_init() and before a proper
6961 console driver takes 6076 console driver takes over, this boot options might
6962 help "seeing" what's 6077 help "seeing" what's going on.
6963 6078
6964 uhash_entries= [KNL,NET] 6079 uhash_entries= [KNL,NET]
6965 Set number of hash bu 6080 Set number of hash buckets for UDP/UDP-Lite connections
6966 6081
6967 uhci-hcd.ignore_oc= 6082 uhci-hcd.ignore_oc=
6968 [USB] Ignore overcurr 6083 [USB] Ignore overcurrent events (default N).
6969 Some badly-designed m 6084 Some badly-designed motherboards generate lots of
6970 bogus events, for por 6085 bogus events, for ports that aren't wired to
6971 anything. Set this p 6086 anything. Set this parameter to avoid log spamming.
6972 Note that genuine ove 6087 Note that genuine overcurrent events won't be
6973 reported either. 6088 reported either.
6974 6089
6975 unknown_nmi_panic 6090 unknown_nmi_panic
6976 [X86] Cause panic on 6091 [X86] Cause panic on unknown NMI.
6977 6092
6978 unwind_debug [X86-64,EARLY] <<
6979 Enable unwinder debug <<
6980 useful for debugging <<
6981 conditions, including <<
6982 bad/missing unwinder <<
6983 <<
6984 usbcore.authorized_default= 6093 usbcore.authorized_default=
6985 [USB] Default USB dev 6094 [USB] Default USB device authorization:
6986 (default -1 = authori !! 6095 (default -1 = authorized except for wireless USB,
6987 0 = not authorized, 1 6096 0 = not authorized, 1 = authorized, 2 = authorized
6988 if device connected t 6097 if device connected to internal port)
6989 6098
6990 usbcore.autosuspend= 6099 usbcore.autosuspend=
6991 [USB] The autosuspend 6100 [USB] The autosuspend time delay (in seconds) used
6992 for newly-detected US 6101 for newly-detected USB devices (default 2). This
6993 is the time required 6102 is the time required before an idle device will be
6994 autosuspended. Devic 6103 autosuspended. Devices for which the delay is set
6995 to a negative value w 6104 to a negative value won't be autosuspended at all.
6996 6105
6997 usbcore.usbfs_snoop= 6106 usbcore.usbfs_snoop=
6998 [USB] Set to log all 6107 [USB] Set to log all usbfs traffic (default 0 = off).
6999 6108
7000 usbcore.usbfs_snoop_max= 6109 usbcore.usbfs_snoop_max=
7001 [USB] Maximum number 6110 [USB] Maximum number of bytes to snoop in each URB
7002 (default = 65536). 6111 (default = 65536).
7003 6112
7004 usbcore.blinkenlights= 6113 usbcore.blinkenlights=
7005 [USB] Set to cycle le 6114 [USB] Set to cycle leds on hubs (default 0 = off).
7006 6115
7007 usbcore.old_scheme_first= 6116 usbcore.old_scheme_first=
7008 [USB] Start with the 6117 [USB] Start with the old device initialization
7009 scheme (default 0 = o 6118 scheme (default 0 = off).
7010 6119
7011 usbcore.usbfs_memory_mb= 6120 usbcore.usbfs_memory_mb=
7012 [USB] Memory limit (i 6121 [USB] Memory limit (in MB) for buffers allocated by
7013 usbfs (default = 16, 6122 usbfs (default = 16, 0 = max = 2047).
7014 6123
7015 usbcore.use_both_schemes= 6124 usbcore.use_both_schemes=
7016 [USB] Try the other d 6125 [USB] Try the other device initialization scheme
7017 if the first one fail 6126 if the first one fails (default 1 = enabled).
7018 6127
7019 usbcore.initial_descriptor_timeout= 6128 usbcore.initial_descriptor_timeout=
7020 [USB] Specifies timeo 6129 [USB] Specifies timeout for the initial 64-byte
7021 USB_REQ_GET_DESCRIPTO 6130 USB_REQ_GET_DESCRIPTOR request in milliseconds
7022 (default 5000 = 5.0 s 6131 (default 5000 = 5.0 seconds).
7023 6132
7024 usbcore.nousb [USB] Disable the USB 6133 usbcore.nousb [USB] Disable the USB subsystem
7025 6134
7026 usbcore.quirks= 6135 usbcore.quirks=
7027 [USB] A list of quirk 6136 [USB] A list of quirk entries to augment the built-in
7028 usb core quirk list. 6137 usb core quirk list. List entries are separated by
7029 commas. Each entry ha 6138 commas. Each entry has the form
7030 VendorID:ProductID:Fl 6139 VendorID:ProductID:Flags. The IDs are 4-digit hex
7031 numbers and Flags is 6140 numbers and Flags is a set of letters. Each letter
7032 will change the built 6141 will change the built-in quirk; setting it if it is
7033 clear and clearing it 6142 clear and clearing it if it is set. The letters have
7034 the following meaning 6143 the following meanings:
7035 a = USB_QUIRK 6144 a = USB_QUIRK_STRING_FETCH_255 (string
7036 descr 6145 descriptors must not be fetched using
7037 a 255 6146 a 255-byte read);
7038 b = USB_QUIRK 6147 b = USB_QUIRK_RESET_RESUME (device can't resume
7039 corre 6148 correctly so reset it instead);
7040 c = USB_QUIRK 6149 c = USB_QUIRK_NO_SET_INTF (device can't handle
7041 Set-I 6150 Set-Interface requests);
7042 d = USB_QUIRK 6151 d = USB_QUIRK_CONFIG_INTF_STRINGS (device can't
7043 handl 6152 handle its Configuration or Interface
7044 strin 6153 strings);
7045 e = USB_QUIRK 6154 e = USB_QUIRK_RESET (device can't be reset
7046 (e.g 6155 (e.g morph devices), don't use reset);
7047 f = USB_QUIRK 6156 f = USB_QUIRK_HONOR_BNUMINTERFACES (device has
7048 more 6157 more interface descriptions than the
7049 bNumI 6158 bNumInterfaces count, and can't handle
7050 talki 6159 talking to these interfaces);
7051 g = USB_QUIRK 6160 g = USB_QUIRK_DELAY_INIT (device needs a pause
7052 durin 6161 during initialization, after we read
7053 the d 6162 the device descriptor);
7054 h = USB_QUIRK 6163 h = USB_QUIRK_LINEAR_UFRAME_INTR_BINTERVAL (For
7055 high 6164 high speed and super speed interrupt
7056 endpo 6165 endpoints, the USB 2.0 and USB 3.0 spec
7057 requi 6166 require the interval in microframes (1
7058 micro 6167 microframe = 125 microseconds) to be
7059 calcu 6168 calculated as interval = 2 ^
7060 (bInt 6169 (bInterval-1).
7061 Devic 6170 Devices with this quirk report their
7062 bInte 6171 bInterval as the result of this
7063 calcu 6172 calculation instead of the exponent
7064 varia 6173 variable used in the calculation);
7065 i = USB_QUIRK 6174 i = USB_QUIRK_DEVICE_QUALIFIER (device can't
7066 handl 6175 handle device_qualifier descriptor
7067 reque 6176 requests);
7068 j = USB_QUIRK 6177 j = USB_QUIRK_IGNORE_REMOTE_WAKEUP (device
7069 gener 6178 generates spurious wakeup, ignore
7070 remot 6179 remote wakeup capability);
7071 k = USB_QUIRK 6180 k = USB_QUIRK_NO_LPM (device can't handle Link
7072 Power 6181 Power Management);
7073 l = USB_QUIRK 6182 l = USB_QUIRK_LINEAR_FRAME_INTR_BINTERVAL
7074 (Devi 6183 (Device reports its bInterval as linear
7075 frame 6184 frames instead of the USB 2.0
7076 calcu 6185 calculation);
7077 m = USB_QUIRK 6186 m = USB_QUIRK_DISCONNECT_SUSPEND (Device needs
7078 to be 6187 to be disconnected before suspend to
7079 preve 6188 prevent spurious wakeup);
7080 n = USB_QUIRK 6189 n = USB_QUIRK_DELAY_CTRL_MSG (Device needs a
7081 pause 6190 pause after every control message);
7082 o = USB_QUIRK 6191 o = USB_QUIRK_HUB_SLOW_RESET (Hub needs extra
7083 delay 6192 delay after resetting its port);
7084 p = USB_QUIRK <<
7085 (Redu <<
7086 reque <<
7087 Example: quirks=0781: 6193 Example: quirks=0781:5580:bk,0a5c:5834:gij
7088 6194
7089 usbhid.mousepoll= 6195 usbhid.mousepoll=
7090 [USBHID] The interval 6196 [USBHID] The interval which mice are to be polled at.
7091 6197
7092 usbhid.jspoll= 6198 usbhid.jspoll=
7093 [USBHID] The interval 6199 [USBHID] The interval which joysticks are to be polled at.
7094 6200
7095 usbhid.kbpoll= 6201 usbhid.kbpoll=
7096 [USBHID] The interval 6202 [USBHID] The interval which keyboards are to be polled at.
7097 6203
7098 usb-storage.delay_use= 6204 usb-storage.delay_use=
7099 [UMS] The delay in se 6205 [UMS] The delay in seconds before a new device is
7100 scanned for Logical U 6206 scanned for Logical Units (default 1).
7101 Optionally the delay <<
7102 suffix with "ms". <<
7103 Example: delay_use=25 <<
7104 6207
7105 usb-storage.quirks= 6208 usb-storage.quirks=
7106 [UMS] A list of quirk 6209 [UMS] A list of quirks entries to supplement or
7107 override the built-in 6210 override the built-in unusual_devs list. List
7108 entries are separated 6211 entries are separated by commas. Each entry has
7109 the form VID:PID:Flag 6212 the form VID:PID:Flags where VID and PID are Vendor
7110 and Product ID values 6213 and Product ID values (4-digit hex numbers) and
7111 Flags is a set of cha 6214 Flags is a set of characters, each corresponding
7112 to a common usb-stora 6215 to a common usb-storage quirk flag as follows:
7113 a = SANE_SENS 6216 a = SANE_SENSE (collect more than 18 bytes
7114 of se 6217 of sense data, not on uas);
7115 b = BAD_SENSE 6218 b = BAD_SENSE (don't collect more than 18
7116 bytes 6219 bytes of sense data, not on uas);
7117 c = FIX_CAPAC 6220 c = FIX_CAPACITY (decrease the reported
7118 devic 6221 device capacity by one sector);
7119 d = NO_READ_D 6222 d = NO_READ_DISC_INFO (don't use
7120 READ_ 6223 READ_DISC_INFO command, not on uas);
7121 e = NO_READ_C 6224 e = NO_READ_CAPACITY_16 (don't use
7122 READ_ 6225 READ_CAPACITY_16 command);
7123 f = NO_REPORT 6226 f = NO_REPORT_OPCODES (don't use report opcodes
7124 comma 6227 command, uas only);
7125 g = MAX_SECTO 6228 g = MAX_SECTORS_240 (don't transfer more than
7126 240 s 6229 240 sectors at a time, uas only);
7127 h = CAPACITY_ 6230 h = CAPACITY_HEURISTICS (decrease the
7128 repor 6231 reported device capacity by one
7129 secto 6232 sector if the number is odd);
7130 i = IGNORE_DE 6233 i = IGNORE_DEVICE (don't bind to this
7131 devic 6234 device);
7132 j = NO_REPORT 6235 j = NO_REPORT_LUNS (don't use report luns
7133 comma 6236 command, uas only);
7134 k = NO_SAME ( 6237 k = NO_SAME (do not use WRITE_SAME, uas only)
7135 l = NOT_LOCKA 6238 l = NOT_LOCKABLE (don't try to lock and
7136 unloc 6239 unlock ejectable media, not on uas);
7137 m = MAX_SECTO 6240 m = MAX_SECTORS_64 (don't transfer more
7138 than 6241 than 64 sectors = 32 KB at a time,
7139 not o 6242 not on uas);
7140 n = INITIAL_R 6243 n = INITIAL_READ10 (force a retry of the
7141 initi 6244 initial READ(10) command, not on uas);
7142 o = CAPACITY_ 6245 o = CAPACITY_OK (accept the capacity
7143 repor 6246 reported by the device, not on uas);
7144 p = WRITE_CAC 6247 p = WRITE_CACHE (the device cache is ON
7145 by de 6248 by default, not on uas);
7146 r = IGNORE_RE 6249 r = IGNORE_RESIDUE (the device reports
7147 bogus 6250 bogus residue values, not on uas);
7148 s = SINGLE_LU 6251 s = SINGLE_LUN (the device has only one
7149 Logic 6252 Logical Unit);
7150 t = NO_ATA_1X 6253 t = NO_ATA_1X (don't allow ATA(12) and ATA(16)
7151 comma 6254 commands, uas only);
7152 u = IGNORE_UA 6255 u = IGNORE_UAS (don't bind to the uas driver);
7153 w = NO_WP_DET 6256 w = NO_WP_DETECT (don't test whether the
7154 mediu 6257 medium is write-protected).
7155 y = ALWAYS_SY 6258 y = ALWAYS_SYNC (issue a SYNCHRONIZE_CACHE
7156 even 6259 even if the device claims no cache,
7157 not o 6260 not on uas)
7158 Example: quirks=0419: 6261 Example: quirks=0419:aaf5:rl,0421:0433:rc
7159 6262
7160 user_debug= [KNL,ARM] 6263 user_debug= [KNL,ARM]
7161 Format: <int> 6264 Format: <int>
7162 See arch/arm/Kconfig. 6265 See arch/arm/Kconfig.debug help text.
7163 1 - undefine 6266 1 - undefined instruction events
7164 2 - system c 6267 2 - system calls
7165 4 - invalid 6268 4 - invalid data aborts
7166 8 - SIGSEGV 6269 8 - SIGSEGV faults
7167 16 - SIGBUS f 6270 16 - SIGBUS faults
7168 Example: user_debug=3 6271 Example: user_debug=31
7169 6272
7170 userpte= 6273 userpte=
7171 [X86,EARLY] Flags con !! 6274 [X86] Flags controlling user PTE allocations.
7172 6275
7173 nohigh = do n 6276 nohigh = do not allocate PTE pages in
7174 HIGHM 6277 HIGHMEM regardless of setting
7175 of CO 6278 of CONFIG_HIGHPTE.
7176 6279
7177 vdso= [X86,SH,SPARC] !! 6280 vdso= [X86,SH]
7178 On X86_32, this is an 6281 On X86_32, this is an alias for vdso32=. Otherwise:
7179 6282
7180 vdso=1: enable VDSO ( 6283 vdso=1: enable VDSO (the default)
7181 vdso=0: disable VDSO 6284 vdso=0: disable VDSO mapping
7182 6285
7183 vdso32= [X86] Control the 32- 6286 vdso32= [X86] Control the 32-bit vDSO
7184 vdso32=1: enable 32-b 6287 vdso32=1: enable 32-bit VDSO
7185 vdso32=0 or vdso32=2: 6288 vdso32=0 or vdso32=2: disable 32-bit VDSO
7186 6289
7187 See the help text for 6290 See the help text for CONFIG_COMPAT_VDSO for more
7188 details. If CONFIG_C 6291 details. If CONFIG_COMPAT_VDSO is set, the default is
7189 vdso32=0; otherwise, 6292 vdso32=0; otherwise, the default is vdso32=1.
7190 6293
7191 For compatibility wit 6294 For compatibility with older kernels, vdso32=2 is an
7192 alias for vdso32=0. 6295 alias for vdso32=0.
7193 6296
7194 Try vdso32=0 if you e 6297 Try vdso32=0 if you encounter an error that says:
7195 dl_main: Assertion `( 6298 dl_main: Assertion `(void *) ph->p_vaddr == _rtld_local._dl_sysinfo_dso' failed!
7196 6299
7197 video= [FB,EARLY] Frame buff !! 6300 vector= [IA-64,SMP]
>> 6301 vector=percpu: enable percpu vector domain
>> 6302
>> 6303 video= [FB] Frame buffer configuration
7198 See Documentation/fb/ 6304 See Documentation/fb/modedb.rst.
7199 6305
7200 video.brightness_switch_enabled= [ACP !! 6306 video.brightness_switch_enabled= [0,1]
7201 Format: [0|1] <<
7202 If set to 1, on recei 6307 If set to 1, on receiving an ACPI notify event
7203 generated by hotkey, 6308 generated by hotkey, video driver will adjust brightness
7204 level and then send o 6309 level and then send out the event to user space through
7205 the allocated input d !! 6310 the allocated input device; If set to 0, video driver
7206 will only send out th 6311 will only send out the event without touching backlight
7207 brightness level. 6312 brightness level.
7208 default: 1 6313 default: 1
7209 6314
7210 virtio_mmio.device= 6315 virtio_mmio.device=
7211 [VMMIO] Memory mapped 6316 [VMMIO] Memory mapped virtio (platform) device.
7212 6317
7213 <size>@<basead 6318 <size>@<baseaddr>:<irq>[:<id>]
7214 where: 6319 where:
7215 <size> := 6320 <size> := size (can use standard suffixes
7216 6321 like K, M and G)
7217 <baseaddr> := 6322 <baseaddr> := physical base address
7218 <irq> := 6323 <irq> := interrupt number (as passed to
7219 6324 request_irq())
7220 <id> := 6325 <id> := (optional) platform device id
7221 example: 6326 example:
7222 virtio_mmio.d 6327 virtio_mmio.device=1K@0x100b0000:48:7
7223 6328
7224 Can be used multiple 6329 Can be used multiple times for multiple devices.
7225 6330
7226 vga= [BOOT,X86-32] Select 6331 vga= [BOOT,X86-32] Select a particular video mode
7227 See Documentation/arc !! 6332 See Documentation/x86/boot.rst and
7228 Documentation/admin-g 6333 Documentation/admin-guide/svga.rst.
7229 Use vga=ask for menu. 6334 Use vga=ask for menu.
7230 This is actually a bo 6335 This is actually a boot loader parameter; the value is
7231 passed to the kernel 6336 passed to the kernel using a special protocol.
7232 6337
7233 vm_debug[=options] [KNL] Availab 6338 vm_debug[=options] [KNL] Available with CONFIG_DEBUG_VM=y.
7234 May slow down system 6339 May slow down system boot speed, especially when
7235 enabled on systems wi 6340 enabled on systems with a large amount of memory.
7236 All options are enabl 6341 All options are enabled by default, and this
7237 interface is meant to 6342 interface is meant to allow for selectively
7238 enabling or disabling 6343 enabling or disabling specific virtual memory
7239 debugging features. 6344 debugging features.
7240 6345
7241 Available options are 6346 Available options are:
7242 P Enable page s 6347 P Enable page structure init time poisoning
7243 - Disable all o 6348 - Disable all of the above options
7244 6349
7245 vmalloc=nn[KMG] [KNL,BOOT,EARLY] Forc !! 6350 vmalloc=nn[KMG] [KNL,BOOT] Forces the vmalloc area to have an exact
7246 exact size of <nn>. T !! 6351 size of <nn>. This can be used to increase the
7247 the minimum size (128 !! 6352 minimum size (128MB on x86). It can also be used to
7248 It can also be used t !! 6353 decrease the size and leave more room for directly
7249 for directly mapped k !! 6354 mapped kernel RAM.
7250 not exist on many oth <<
7251 loongarch, arc, csky, <<
7252 parisc, m64k, powerpc <<
7253 6355
7254 vmcp_cma=nn[MG] [KNL,S390,EARLY] !! 6356 vmcp_cma=nn[MG] [KNL,S390]
7255 Sets the memory size 6357 Sets the memory size reserved for contiguous memory
7256 allocations for the v 6358 allocations for the vmcp device driver.
7257 6359
7258 vmhalt= [KNL,S390] Perform z/ 6360 vmhalt= [KNL,S390] Perform z/VM CP command after system halt.
7259 Format: <command> 6361 Format: <command>
7260 6362
7261 vmpanic= [KNL,S390] Perform z/ 6363 vmpanic= [KNL,S390] Perform z/VM CP command after kernel panic.
7262 Format: <command> 6364 Format: <command>
7263 6365
7264 vmpoff= [KNL,S390] Perform z/ 6366 vmpoff= [KNL,S390] Perform z/VM CP command after power off.
7265 Format: <command> 6367 Format: <command>
7266 6368
7267 vsyscall= [X86-64,EARLY] !! 6369 vsyscall= [X86-64]
7268 Controls the behavior 6370 Controls the behavior of vsyscalls (i.e. calls to
7269 fixed addresses of 0x 6371 fixed addresses of 0xffffffffff600x00 from legacy
7270 code). Most statical 6372 code). Most statically-linked binaries and older
7271 versions of glibc use 6373 versions of glibc use these calls. Because these
7272 functions are at fixe 6374 functions are at fixed addresses, they make nice
7273 targets for exploits 6375 targets for exploits that can control RIP.
7274 6376
7275 emulate Vsyscalls !! 6377 emulate [default] Vsyscalls turn into traps and are
7276 reasonabl !! 6378 emulated reasonably safely. The vsyscall
7277 readable. !! 6379 page is readable.
7278 6380
7279 xonly [default] !! 6381 xonly Vsyscalls turn into traps and are
7280 emulated 6382 emulated reasonably safely. The vsyscall
7281 page is n 6383 page is not readable.
7282 6384
7283 none Vsyscalls 6385 none Vsyscalls don't work at all. This makes
7284 them quit 6386 them quite hard to use for exploits but
7285 might bre 6387 might break your system.
7286 6388
7287 vt.color= [VT] Default text col 6389 vt.color= [VT] Default text color.
7288 Format: 0xYX, X = for 6390 Format: 0xYX, X = foreground, Y = background.
7289 Default: 0x07 = light 6391 Default: 0x07 = light gray on black.
7290 6392
7291 vt.cur_default= [VT] Default cursor s 6393 vt.cur_default= [VT] Default cursor shape.
7292 Format: 0xCCBBAA, whe 6394 Format: 0xCCBBAA, where AA, BB, and CC are the same as
7293 the parameters of the 6395 the parameters of the <Esc>[?A;B;Cc escape sequence;
7294 see VGA-softcursor.tx 6396 see VGA-softcursor.txt. Default: 2 = underline.
7295 6397
7296 vt.default_blu= [VT] 6398 vt.default_blu= [VT]
7297 Format: <blue0>,<blue 6399 Format: <blue0>,<blue1>,<blue2>,...,<blue15>
7298 Change the default bl 6400 Change the default blue palette of the console.
7299 This is a 16-member a 6401 This is a 16-member array composed of values
7300 ranging from 0-255. 6402 ranging from 0-255.
7301 6403
7302 vt.default_grn= [VT] 6404 vt.default_grn= [VT]
7303 Format: <green0>,<gre 6405 Format: <green0>,<green1>,<green2>,...,<green15>
7304 Change the default gr 6406 Change the default green palette of the console.
7305 This is a 16-member a 6407 This is a 16-member array composed of values
7306 ranging from 0-255. 6408 ranging from 0-255.
7307 6409
7308 vt.default_red= [VT] 6410 vt.default_red= [VT]
7309 Format: <red0>,<red1> 6411 Format: <red0>,<red1>,<red2>,...,<red15>
7310 Change the default re 6412 Change the default red palette of the console.
7311 This is a 16-member a 6413 This is a 16-member array composed of values
7312 ranging from 0-255. 6414 ranging from 0-255.
7313 6415
7314 vt.default_utf8= 6416 vt.default_utf8=
7315 [VT] 6417 [VT]
7316 Format=<0|1> 6418 Format=<0|1>
7317 Set system-wide defau 6419 Set system-wide default UTF-8 mode for all tty's.
7318 Default is 1, i.e. UT 6420 Default is 1, i.e. UTF-8 mode is enabled for all
7319 newly opened terminal 6421 newly opened terminals.
7320 6422
7321 vt.global_cursor_default= 6423 vt.global_cursor_default=
7322 [VT] 6424 [VT]
7323 Format=<-1|0|1> 6425 Format=<-1|0|1>
7324 Set system-wide defau 6426 Set system-wide default for whether a cursor
7325 is shown on new VTs. 6427 is shown on new VTs. Default is -1,
7326 i.e. cursors will be 6428 i.e. cursors will be created by default unless
7327 overridden by individ 6429 overridden by individual drivers. 0 will hide
7328 cursors, 1 will displ 6430 cursors, 1 will display them.
7329 6431
7330 vt.italic= [VT] Default color fo 6432 vt.italic= [VT] Default color for italic text; 0-15.
7331 Default: 2 = green. 6433 Default: 2 = green.
7332 6434
7333 vt.underline= [VT] Default color fo 6435 vt.underline= [VT] Default color for underlined text; 0-15.
7334 Default: 3 = cyan. 6436 Default: 3 = cyan.
7335 6437
7336 watchdog timers [HW,WDT] For informat 6438 watchdog timers [HW,WDT] For information on watchdog timers,
7337 see Documentation/wat 6439 see Documentation/watchdog/watchdog-parameters.rst
7338 or other driver-speci 6440 or other driver-specific files in the
7339 Documentation/watchdo 6441 Documentation/watchdog/ directory.
7340 6442
7341 watchdog_thresh= 6443 watchdog_thresh=
7342 [KNL] 6444 [KNL]
7343 Set the hard lockup d 6445 Set the hard lockup detector stall duration
7344 threshold in seconds. 6446 threshold in seconds. The soft lockup detector
7345 threshold is set to t 6447 threshold is set to twice the value. A value of 0
7346 disables both lockup 6448 disables both lockup detectors. Default is 10
7347 seconds. 6449 seconds.
7348 6450
7349 workqueue.unbound_cpus= <<
7350 [KNL,SMP] Specify to <<
7351 to use in unbound wor <<
7352 Format: <cpu-list> <<
7353 By default, all onlin <<
7354 unbound workqueues. <<
7355 <<
7356 workqueue.watchdog_thresh= 6451 workqueue.watchdog_thresh=
7357 If CONFIG_WQ_WATCHDOG 6452 If CONFIG_WQ_WATCHDOG is configured, workqueue can
7358 warn stall conditions 6453 warn stall conditions and dump internal state to
7359 help debugging. 0 di 6454 help debugging. 0 disables workqueue stall
7360 detection; otherwise, 6455 detection; otherwise, it's the stall threshold
7361 duration in seconds. 6456 duration in seconds. The default value is 30 and
7362 it can be updated at 6457 it can be updated at runtime by writing to the
7363 corresponding sysfs f 6458 corresponding sysfs file.
7364 6459
7365 workqueue.cpu_intensive_thresh_us= !! 6460 workqueue.disable_numa
7366 Per-cpu work items wh !! 6461 By default, all work items queued to unbound
7367 threshold are automat !! 6462 workqueues are affine to the NUMA nodes they're
7368 and excluded from con !! 6463 issued on, which results in better behavior in
7369 them from noticeably !! 6464 general. If NUMA affinity needs to be disabled for
7370 items. Default is 100 !! 6465 whatever reason, this option can be used. Note
7371 !! 6466 that this also can be controlled per-workqueue for
7372 If CONFIG_WQ_CPU_INTE !! 6467 workqueues visible under /sys/bus/workqueue/.
7373 will report the work <<
7374 threshold repeatedly. <<
7375 candidates for using <<
7376 <<
7377 workqueue.cpu_intensive_warning_thres <<
7378 If CONFIG_WQ_CPU_INTE <<
7379 will report the work <<
7380 intensive_threshold_u <<
7381 spurious warnings, st <<
7382 function has violated <<
7383 <<
7384 The default is 4 time <<
7385 6468
7386 workqueue.power_efficient 6469 workqueue.power_efficient
7387 Per-cpu workqueues ar 6470 Per-cpu workqueues are generally preferred because
7388 they show better perf 6471 they show better performance thanks to cache
7389 locality; unfortunate 6472 locality; unfortunately, per-cpu workqueues tend to
7390 be more power hungry 6473 be more power hungry than unbound workqueues.
7391 6474
7392 Enabling this makes t 6475 Enabling this makes the per-cpu workqueues which
7393 were observed to cont 6476 were observed to contribute significantly to power
7394 consumption unbound, 6477 consumption unbound, leading to measurably lower
7395 power usage at the co 6478 power usage at the cost of small performance
7396 overhead. 6479 overhead.
7397 6480
7398 The default value of 6481 The default value of this parameter is determined by
7399 the config option CON 6482 the config option CONFIG_WQ_POWER_EFFICIENT_DEFAULT.
7400 6483
7401 workqueue.default_affinity_scope= <<
7402 Select the default af <<
7403 workqueues. Can be on <<
7404 "numa" and "system". <<
7405 information, see the <<
7406 Documentation/core-ap <<
7407 <<
7408 This can be changed a <<
7409 matching /sys/module/ <<
7410 workqueues with the " <<
7411 updated accordingly. <<
7412 <<
7413 workqueue.debug_force_rr_cpu 6484 workqueue.debug_force_rr_cpu
7414 Workqueue used to imp 6485 Workqueue used to implicitly guarantee that work
7415 items queued without 6486 items queued without explicit CPU specified are put
7416 on the local CPU. Th 6487 on the local CPU. This guarantee is no longer true
7417 and while local CPU i 6488 and while local CPU is still preferred work items
7418 may be put on foreign 6489 may be put on foreign CPUs. This debug option
7419 forces round-robin CP 6490 forces round-robin CPU selection to flush out
7420 usages which depend o 6491 usages which depend on the now broken guarantee.
7421 When enabled, memory 6492 When enabled, memory and cache locality will be
7422 impacted. 6493 impacted.
7423 6494
7424 writecombine= [LOONGARCH,EARLY] Con !! 6495 x2apic_phys [X86-64,APIC] Use x2apic physical mode instead of
7425 Type) of ioremap_wc() <<
7426 <<
7427 on - Enable writeco <<
7428 off - Disable writec <<
7429 <<
7430 x2apic_phys [X86-64,APIC,EARLY] U <<
7431 default x2apic cluste 6496 default x2apic cluster mode on platforms
7432 supporting x2apic. 6497 supporting x2apic.
7433 6498
7434 xen_512gb_limit [KNL,X86-64,X 6499 xen_512gb_limit [KNL,X86-64,XEN]
7435 Restricts the kernel 6500 Restricts the kernel running paravirtualized under Xen
7436 to use only up to 512 6501 to use only up to 512 GB of RAM. The reason to do so is
7437 crash analysis tools 6502 crash analysis tools and Xen tools for doing domain
7438 save/restore/migratio 6503 save/restore/migration must be enabled to handle larger
7439 domains. 6504 domains.
7440 6505
7441 xen_emul_unplug= [HW,X !! 6506 xen_emul_unplug= [HW,X86,XEN]
7442 Unplug Xen emulated d 6507 Unplug Xen emulated devices
7443 Format: [unplug0,][un 6508 Format: [unplug0,][unplug1]
7444 ide-disks -- unplug p 6509 ide-disks -- unplug primary master IDE devices
7445 aux-ide-disks -- unpl 6510 aux-ide-disks -- unplug non-primary-master IDE devices
7446 nics -- unplug networ 6511 nics -- unplug network devices
7447 all -- unplug all emu 6512 all -- unplug all emulated devices (NICs and IDE disks)
7448 unnecessary -- unplug 6513 unnecessary -- unplugging emulated devices is
7449 unnecessary e 6514 unnecessary even if the host did not respond to
7450 the unplug pr 6515 the unplug protocol
7451 never -- do not unplu 6516 never -- do not unplug even if version check succeeds
7452 6517
7453 xen_legacy_crash [X86,XEN,EARL !! 6518 xen_legacy_crash [X86,XEN]
7454 Crash from Xen panic 6519 Crash from Xen panic notifier, without executing late
7455 panic() code such as 6520 panic() code such as dumping handler.
7456 6521
7457 xen_mc_debug [X86,XEN,EARLY] !! 6522 xen_nopvspin [X86,XEN]
7458 Enable multicall debu !! 6523 Disables the qspinlock slowpath using Xen PV optimizations.
7459 Enabling this feature !! 6524 This parameter is obsoleted by "nopvspin" parameter, which
7460 bit, so it should onl !! 6525 has equivalent effect for XEN platform.
7461 debug data in case of <<
7462 <<
7463 xen_msr_safe= [X86,XEN,EARLY] <<
7464 Format: <bool> <<
7465 Select whether to alw <<
7466 access functions when <<
7467 default value is cont <<
7468 6526
7469 xen_nopv [X86] 6527 xen_nopv [X86]
7470 Disables the PV optim 6528 Disables the PV optimizations forcing the HVM guest to
7471 run as generic HVM gu 6529 run as generic HVM guest with no PV drivers.
7472 This option is obsole 6530 This option is obsoleted by the "nopv" option, which
7473 has equivalent effect 6531 has equivalent effect for XEN platform.
7474 6532
7475 xen_no_vector_callback 6533 xen_no_vector_callback
7476 [KNL,X86,XEN,EARLY] D !! 6534 [KNL,X86,XEN] Disable the vector callback for Xen
7477 event channel interru 6535 event channel interrupts.
7478 6536
7479 xen_scrub_pages= [XEN] 6537 xen_scrub_pages= [XEN]
7480 Boolean option to con 6538 Boolean option to control scrubbing pages before giving them back
7481 to Xen, for use by ot 6539 to Xen, for use by other domains. Can be also changed at runtime
7482 with /sys/devices/sys 6540 with /sys/devices/system/xen_memory/xen_memory0/scrub_pages.
7483 Default value control 6541 Default value controlled with CONFIG_XEN_SCRUB_PAGES_DEFAULT.
7484 6542
7485 xen_timer_slop= [X86-64,XEN,EARLY] !! 6543 xen_timer_slop= [X86-64,XEN]
7486 Set the timer slop (i 6544 Set the timer slop (in nanoseconds) for the virtual Xen
7487 timers (default is 10 6545 timers (default is 100000). This adjusts the minimum
7488 delta of virtualized 6546 delta of virtualized Xen timers, where lower values
7489 improve timer resolut 6547 improve timer resolution at the expense of processing
7490 more timer interrupts 6548 more timer interrupts.
7491 6549
7492 xen.balloon_boot_timeout= [XEN] 6550 xen.balloon_boot_timeout= [XEN]
7493 The time (in seconds) 6551 The time (in seconds) to wait before giving up to boot
7494 in case initial ballo 6552 in case initial ballooning fails to free enough memory.
7495 Applies only when run 6553 Applies only when running as HVM or PVH guest and
7496 started with less mem 6554 started with less memory configured than allowed at
7497 max. Default is 180. 6555 max. Default is 180.
7498 6556
7499 xen.event_eoi_delay= [XEN] 6557 xen.event_eoi_delay= [XEN]
7500 How long to delay EOI 6558 How long to delay EOI handling in case of event
7501 storms (jiffies). Def 6559 storms (jiffies). Default is 10.
7502 6560
7503 xen.event_loop_timeout= [XEN] 6561 xen.event_loop_timeout= [XEN]
7504 After which time (jif 6562 After which time (jiffies) the event handling loop
7505 should start to delay 6563 should start to delay EOI handling. Default is 2.
7506 6564
7507 xen.fifo_events= [XEN] 6565 xen.fifo_events= [XEN]
7508 Boolean parameter to 6566 Boolean parameter to disable using fifo event handling
7509 even if available. No 6567 even if available. Normally fifo event handling is
7510 preferred over the 2- 6568 preferred over the 2-level event handling, as it is
7511 fairer and the number 6569 fairer and the number of possible event channels is
7512 much higher. Default 6570 much higher. Default is on (use fifo events).
7513 6571
>> 6572 nopv= [X86,XEN,KVM,HYPER_V,VMWARE]
>> 6573 Disables the PV optimizations forcing the guest to run
>> 6574 as generic guest with no PV drivers. Currently support
>> 6575 XEN HVM, KVM, HYPER_V and VMWARE guest.
>> 6576
>> 6577 nopvspin [X86,XEN,KVM]
>> 6578 Disables the qspinlock slow path using PV optimizations
>> 6579 which allow the hypervisor to 'idle' the guest on lock
>> 6580 contention.
>> 6581
7514 xirc2ps_cs= [NET,PCMCIA] 6582 xirc2ps_cs= [NET,PCMCIA]
7515 Format: 6583 Format:
7516 <irq>,<irq_mask>,<io> 6584 <irq>,<irq_mask>,<io>,<full_duplex>,<do_sound>,<lockup_hack>[,<irq2>[,<irq3>[,<irq4>]]]
7517 6585
7518 xive= [PPC] 6586 xive= [PPC]
7519 By default on POWER9 6587 By default on POWER9 and above, the kernel will
7520 natively use the XIVE 6588 natively use the XIVE interrupt controller. This option
7521 allows the fallback f 6589 allows the fallback firmware mode to be used:
7522 6590
7523 off Fallback to 6591 off Fallback to firmware control of XIVE interrupt
7524 controller 6592 controller on both pseries and powernv
7525 platforms. 6593 platforms. Only useful on POWER9 and above.
7526 6594
7527 xive.store-eoi=off [PPC] <<
7528 By default on POWER10 <<
7529 stores for EOI handli <<
7530 is active. This optio <<
7531 loads instead, as on <<
7532 <<
7533 xhci-hcd.quirks [USB,KNL] 6595 xhci-hcd.quirks [USB,KNL]
7534 A hex value specifyin 6596 A hex value specifying bitmask with supplemental xhci
7535 host controller quirk 6597 host controller quirks. Meaning of each bit can be
7536 consulted in header d 6598 consulted in header drivers/usb/host/xhci.h.
7537 6599
7538 xmon [PPC,EARLY] !! 6600 xmon [PPC]
7539 Format: { early | on 6601 Format: { early | on | rw | ro | off }
7540 Controls if xmon debu 6602 Controls if xmon debugger is enabled. Default is off.
7541 Passing only "xmon" i 6603 Passing only "xmon" is equivalent to "xmon=early".
7542 early Call xmon as 6604 early Call xmon as early as possible on boot; xmon
7543 debugger is c 6605 debugger is called from setup_arch().
7544 on xmon debugger 6606 on xmon debugger hooks will be installed so xmon
7545 is only calle 6607 is only called on a kernel crash. Default mode,
7546 i.e. either " 6608 i.e. either "ro" or "rw" mode, is controlled
7547 with CONFIG_X 6609 with CONFIG_XMON_DEFAULT_RO_MODE.
7548 rw xmon debugger 6610 rw xmon debugger hooks will be installed so xmon
7549 is called onl 6611 is called only on a kernel crash, mode is write,
7550 meaning SPR r 6612 meaning SPR registers, memory and, other data
7551 can be writte 6613 can be written using xmon commands.
7552 ro same as "rw" 6614 ro same as "rw" option above but SPR registers,
7553 memory, and o 6615 memory, and other data can't be written using
7554 xmon commands 6616 xmon commands.
7555 off xmon is disab 6617 off xmon is disabled.
Linux® is a registered trademark of Linus Torvalds in the United States and other countries.
TOMOYO® is a registered trademark of NTT DATA CORPORATION.