1 accept_memory= [MM] !! 1 acpi= [HW,ACPI,X86,ARM64,RISCV64]
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,riscv64]
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 and RISCV64, ONLY "acpi=off", "acpi=on" or
25 default _seria !! 14 "acpi=force" are available
26 For ARM64, ONLY "acpi= <<
27 "acpi=nospcr" are avai <<
28 For RISCV64, ONLY "acp <<
29 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_hwsig,
244 s4_nohwsig, 229 s4_nohwsig, old_ordering, nonvs,
245 sci_force_en 230 sci_force_enable, nobl }
246 See Documentation/powe 231 See Documentation/power/video.rst for information on
247 s3_bios and s3_mode. 232 s3_bios and s3_mode.
248 s3_beep is for debuggi 233 s3_beep is for debugging; it makes the PC's speaker beep
249 as soon as the kernel' 234 as soon as the kernel's real-mode entry point is called.
250 s4_hwsig causes the ke 235 s4_hwsig causes the kernel to check the ACPI hardware
251 signature during resum 236 signature during resume from hibernation, and gracefully
252 refuse to resume if it 237 refuse to resume if it has changed. This complies with
253 the ACPI specification 238 the ACPI specification but not with reality, since
254 Windows does not do th 239 Windows does not do this and many laptops do change it
255 on docking. So the def 240 on docking. So the default behaviour is to allow resume
256 and simply warn when t 241 and simply warn when the signature changes, unless the
257 s4_hwsig option is ena 242 s4_hwsig option is enabled.
258 s4_nohwsig prevents AC 243 s4_nohwsig prevents ACPI hardware signature from being
259 used (or even warned a 244 used (or even warned about) during resume.
260 old_ordering causes th 245 old_ordering causes the ACPI 1.0 ordering of the _PTS
261 control method, with r 246 control method, with respect to putting devices into
262 low power states, to b 247 low power states, to be enforced (the ACPI 2.0 ordering
263 of _PTS is used by def 248 of _PTS is used by default).
264 nonvs prevents the ker 249 nonvs prevents the kernel from saving/restoring the
265 ACPI NVS memory during 250 ACPI NVS memory during suspend/hibernation and resume.
266 sci_force_enable cause 251 sci_force_enable causes the kernel to set SCI_EN directly
267 on resume from S1/S3 ( 252 on resume from S1/S3 (which is against the ACPI spec,
268 but some broken system 253 but some broken systems don't work without it).
269 nobl causes the intern 254 nobl causes the internal blacklist of systems known to
270 behave incorrectly in 255 behave incorrectly in some ways with respect to system
271 suspend and resume to 256 suspend and resume to be ignored (use wisely).
272 257
273 acpi_use_timer_override [HW,ACPI,EARLY !! 258 acpi_use_timer_override [HW,ACPI]
274 Use timer override. Fo 259 Use timer override. For some broken Nvidia NF5 boards
275 that require a timer o 260 that require a timer override, but don't have HPET
276 261
277 add_efi_memmap [EFI,X86,EARLY] Includ !! 262 add_efi_memmap [EFI; X86] Include EFI memory map in
278 kernel's map of availa 263 kernel's map of available physical RAM.
279 264
280 agp= [AGP] 265 agp= [AGP]
281 { off | try_unsupporte 266 { off | try_unsupported }
282 off: disable AGP suppo 267 off: disable AGP support
283 try_unsupported: try t 268 try_unsupported: try to drive unsupported chipsets
284 (may crash com 269 (may crash computer or cause data corruption)
285 270
286 ALSA [HW,ALSA] 271 ALSA [HW,ALSA]
287 See Documentation/soun 272 See Documentation/sound/alsa-configuration.rst
288 273
289 alignment= [KNL,ARM] 274 alignment= [KNL,ARM]
290 Allow the default user 275 Allow the default userspace alignment fault handler
291 behaviour to be specif 276 behaviour to be specified. Bit 0 enables warnings,
292 bit 1 enables fixups, 277 bit 1 enables fixups, and bit 2 sends a segfault.
293 278
294 align_va_addr= [X86-64] 279 align_va_addr= [X86-64]
295 Align virtual addresse 280 Align virtual addresses by clearing slice [14:12] when
296 allocating a VMA at pr 281 allocating a VMA at process creation time. This option
297 gives you up to 3% per 282 gives you up to 3% performance improvement on AMD F15h
298 machines (where it is 283 machines (where it is enabled by default) for a
299 CPU-intensive style be 284 CPU-intensive style benchmark, and it can vary highly in
300 a microbenchmark depen 285 a microbenchmark depending on workload and compiler.
301 286
302 32: only for 32-bit pr 287 32: only for 32-bit processes
303 64: only for 64-bit pr 288 64: only for 64-bit processes
304 on: enable for both 32 289 on: enable for both 32- and 64-bit processes
305 off: disable for both 290 off: disable for both 32- and 64-bit processes
306 291
307 alloc_snapshot [FTRACE] 292 alloc_snapshot [FTRACE]
308 Allocate the ftrace sn 293 Allocate the ftrace snapshot buffer on boot up when the
309 main buffer is allocat 294 main buffer is allocated. This is handy if debugging
310 and you need to use tr 295 and you need to use tracing_snapshot() on boot up, and
311 do not want to use tra 296 do not want to use tracing_snapshot_alloc() as it needs
312 to be done where GFP_K 297 to be done where GFP_KERNEL allocations are allowed.
313 298
314 allow_mismatched_32bit_el0 [ARM64,EARL !! 299 allow_mismatched_32bit_el0 [ARM64]
315 Allow execve() of 32-b 300 Allow execve() of 32-bit applications and setting of the
316 PER_LINUX32 personalit 301 PER_LINUX32 personality on systems where only a strict
317 subset of the CPUs sup 302 subset of the CPUs support 32-bit EL0. When this
318 parameter is present, 303 parameter is present, the set of CPUs supporting 32-bit
319 EL0 is indicated by /s 304 EL0 is indicated by /sys/devices/system/cpu/aarch32_el0
320 and hot-unplug operati 305 and hot-unplug operations may be restricted.
321 306
322 See Documentation/arch 307 See Documentation/arch/arm64/asymmetric-32bit.rst for more
323 information. 308 information.
324 309
325 amd_iommu= [HW,X86-64] 310 amd_iommu= [HW,X86-64]
326 Pass parameters to the 311 Pass parameters to the AMD IOMMU driver in the system.
327 Possible values are: 312 Possible values are:
328 fullflush - Deprecated 313 fullflush - Deprecated, equivalent to iommu.strict=1
329 off - do not ini 314 off - do not initialize any AMD IOMMU found in
330 the system 315 the system
331 force_isolation - Forc 316 force_isolation - Force device isolation for all
332 devi 317 devices. The IOMMU driver is not
333 allo 318 allowed anymore to lift isolation
334 requ 319 requirements as needed. This option
335 does 320 does not override iommu=pt
336 force_enable - Force e 321 force_enable - Force enable the IOMMU on platforms known
337 to be b 322 to be buggy with IOMMU enabled. Use this
338 option 323 option with care.
339 pgtbl_v1 - Use v1 324 pgtbl_v1 - Use v1 page table for DMA-API (Default).
340 pgtbl_v2 - Use v2 325 pgtbl_v2 - Use v2 page table for DMA-API.
341 irtcachedis - Disable 326 irtcachedis - Disable Interrupt Remapping Table (IRT) caching.
342 327
343 amd_iommu_dump= [HW,X86-64] 328 amd_iommu_dump= [HW,X86-64]
344 Enable AMD IOMMU drive 329 Enable AMD IOMMU driver option to dump the ACPI table
345 for AMD IOMMU. With th 330 for AMD IOMMU. With this option enabled, AMD IOMMU
346 driver will print ACPI 331 driver will print ACPI tables for AMD IOMMU during
347 IOMMU initialization. 332 IOMMU initialization.
348 333
349 amd_iommu_intr= [HW,X86-64] 334 amd_iommu_intr= [HW,X86-64]
350 Specifies one of the f 335 Specifies one of the following AMD IOMMU interrupt
351 remapping modes: 336 remapping modes:
352 legacy - Use legac 337 legacy - Use legacy interrupt remapping mode.
353 vapic - Use virtu 338 vapic - Use virtual APIC mode, which allows IOMMU
354 to inject 339 to inject interrupts directly into guest.
355 This mode 340 This mode requires kvm-amd.avic=1.
356 (Default 341 (Default when IOMMU HW support is present.)
357 342
358 amd_pstate= [X86,EARLY] !! 343 amd_pstate= [X86]
359 disable 344 disable
360 Do not enable amd_ps 345 Do not enable amd_pstate as the default
361 scaling driver for t 346 scaling driver for the supported processors
362 passive 347 passive
363 Use amd_pstate with 348 Use amd_pstate with passive mode as a scaling driver.
364 In this mode autonom 349 In this mode autonomous selection is disabled.
365 Driver requests a de 350 Driver requests a desired performance level and platform
366 tries to match the s 351 tries to match the same performance level if it is
367 satisfied by guarant 352 satisfied by guaranteed performance level.
368 active 353 active
369 Use amd_pstate_epp d 354 Use amd_pstate_epp driver instance as the scaling driver,
370 driver provides a hi 355 driver provides a hint to the hardware if software wants
371 to bias toward perfo 356 to bias toward performance (0x0) or energy efficiency (0xff)
372 to the CPPC firmware 357 to the CPPC firmware. then CPPC power algorithm will
373 calculate the runtim 358 calculate the runtime workload and adjust the realtime cores
374 frequency. 359 frequency.
375 guided 360 guided
376 Activate guided auto 361 Activate guided autonomous mode. Driver requests minimum and
377 maximum performance 362 maximum performance level and the platform autonomously
378 selects a performanc 363 selects a performance level in this range and appropriate
379 to the current workl 364 to the current workload.
380 365
381 amd_prefcore= <<
382 [X86] <<
383 disable <<
384 Disable amd-pstate p <<
385 <<
386 amijoy.map= [HW,JOY] Amiga joystic 366 amijoy.map= [HW,JOY] Amiga joystick support
387 Map of devices attache 367 Map of devices attached to JOY0DAT and JOY1DAT
388 Format: <a>,<b> 368 Format: <a>,<b>
389 See also Documentation 369 See also Documentation/input/joydev/joystick.rst
390 370
391 analog.map= [HW,JOY] Analog joysti 371 analog.map= [HW,JOY] Analog joystick and gamepad support
392 Specifies type or capa 372 Specifies type or capabilities of an analog joystick
393 connected to one of 16 373 connected to one of 16 gameports
394 Format: <type1>,<type2 374 Format: <type1>,<type2>,..<type16>
395 375
396 apc= [HW,SPARC] 376 apc= [HW,SPARC]
397 Power management funct 377 Power management functions (SPARCstation-4/5 + deriv.)
398 Format: noidle 378 Format: noidle
399 Disable APC CPU standb 379 Disable APC CPU standby support. SPARCstation-Fox does
400 not play well with APC 380 not play well with APC CPU idle - disable it if you have
401 APC and your system cr 381 APC and your system crashes randomly.
402 382
403 apic= [APIC,X86,EARLY] Advan !! 383 apic= [APIC,X86] Advanced Programmable Interrupt Controller
404 Change the output verb 384 Change the output verbosity while booting
405 Format: { quiet (defau 385 Format: { quiet (default) | verbose | debug }
406 Change the amount of d 386 Change the amount of debugging information output
407 when initialising the 387 when initialising the APIC and IO-APIC components.
408 For X86-32, this can a 388 For X86-32, this can also be used to specify an APIC
409 driver name. 389 driver name.
410 Format: apic=driver_na 390 Format: apic=driver_name
411 Examples: apic=bigsmp 391 Examples: apic=bigsmp
412 392
413 apic_extnmi= [APIC,X86,EARLY] Exter !! 393 apic_extnmi= [APIC,X86] External NMI delivery setting
414 Format: { bsp (default 394 Format: { bsp (default) | all | none }
415 bsp: External NMI is 395 bsp: External NMI is delivered only to CPU 0
416 all: External NMIs ar 396 all: External NMIs are broadcast to all CPUs as a
417 backup of CPU 0 397 backup of CPU 0
418 none: External NMI is 398 none: External NMI is masked for all CPUs. This is
419 useful so that a 399 useful so that a dump capture kernel won't be
420 shot down by NMI 400 shot down by NMI
421 401
422 autoconf= [IPV6] 402 autoconf= [IPV6]
423 See Documentation/netw 403 See Documentation/networking/ipv6.rst.
424 404
425 apm= [APM] Advanced Power M 405 apm= [APM] Advanced Power Management
426 See header of arch/x86 406 See header of arch/x86/kernel/apm_32.c.
427 407
428 apparmor= [APPARMOR] Disable or 408 apparmor= [APPARMOR] Disable or enable AppArmor at boot time
429 Format: { "0" | "1" } 409 Format: { "0" | "1" }
430 See security/apparmor/ 410 See security/apparmor/Kconfig help text
431 0 -- disable. 411 0 -- disable.
432 1 -- enable. 412 1 -- enable.
433 Default value is set v 413 Default value is set via kernel config option.
434 414
435 arcrimi= [HW,NET] ARCnet - "RIM 415 arcrimi= [HW,NET] ARCnet - "RIM I" (entirely mem-mapped) cards
436 Format: <io>,<irq>,<no 416 Format: <io>,<irq>,<nodeID>
437 417
438 arm64.no32bit_el0 [ARM64] Unconditiona <<
439 32 bit applications. <<
440 <<
441 arm64.nobti [ARM64] Unconditionall 418 arm64.nobti [ARM64] Unconditionally disable Branch Target
442 Identification support 419 Identification support
443 420
444 arm64.nomops [ARM64] Unconditionall 421 arm64.nomops [ARM64] Unconditionally disable Memory Copy and Memory
445 Set instructions suppo 422 Set instructions support
446 423
447 arm64.nomte [ARM64] Unconditionall 424 arm64.nomte [ARM64] Unconditionally disable Memory Tagging Extension
448 support 425 support
449 426
450 arm64.nopauth [ARM64] Unconditionall 427 arm64.nopauth [ARM64] Unconditionally disable Pointer Authentication
451 support 428 support
452 429
453 arm64.nosme [ARM64] Unconditionall 430 arm64.nosme [ARM64] Unconditionally disable Scalable Matrix
454 Extension support 431 Extension support
455 432
456 arm64.nosve [ARM64] Unconditionall 433 arm64.nosve [ARM64] Unconditionally disable Scalable Vector
457 Extension support 434 Extension support
458 435
459 ataflop= [HW,M68k] 436 ataflop= [HW,M68k]
460 437
461 atarimouse= [HW,MOUSE] Atari Mouse 438 atarimouse= [HW,MOUSE] Atari Mouse
462 439
463 atkbd.extra= [HW] Enable extra LEDs 440 atkbd.extra= [HW] Enable extra LEDs and keys on IBM RapidAccess,
464 EzKey and similar keyb 441 EzKey and similar keyboards
465 442
466 atkbd.reset= [HW] Reset keyboard du 443 atkbd.reset= [HW] Reset keyboard during initialization
467 444
468 atkbd.set= [HW] Select keyboard c 445 atkbd.set= [HW] Select keyboard code set
469 Format: <int> (2 = AT 446 Format: <int> (2 = AT (default), 3 = PS/2)
470 447
471 atkbd.scroll= [HW] Enable scroll whe 448 atkbd.scroll= [HW] Enable scroll wheel on MS Office and similar
472 keyboards 449 keyboards
473 450
474 atkbd.softraw= [HW] Choose between sy 451 atkbd.softraw= [HW] Choose between synthetic and real raw mode
475 Format: <bool> (0 = re 452 Format: <bool> (0 = real, 1 = synthetic (default))
476 453
477 atkbd.softrepeat= [HW] 454 atkbd.softrepeat= [HW]
478 Use software keyboard 455 Use software keyboard repeat
479 456
480 audit= [KNL] Enable the audit 457 audit= [KNL] Enable the audit sub-system
481 Format: { "0" | "1" | 458 Format: { "0" | "1" | "off" | "on" }
482 0 | off - kernel audit 459 0 | off - kernel audit is disabled and can not be
483 enabled until the 460 enabled until the next reboot
484 unset - kernel audit i 461 unset - kernel audit is initialized but disabled and
485 will be fully enab 462 will be fully enabled by the userspace auditd.
486 1 | on - kernel audit 463 1 | on - kernel audit is initialized and partially
487 enabled, storing a 464 enabled, storing at most audit_backlog_limit
488 messages in RAM un 465 messages in RAM until it is fully enabled by the
489 userspace auditd. 466 userspace auditd.
490 Default: unset 467 Default: unset
491 468
492 audit_backlog_limit= [KNL] Set the aud 469 audit_backlog_limit= [KNL] Set the audit queue size limit.
493 Format: <int> (must be 470 Format: <int> (must be >=0)
494 Default: 64 471 Default: 64
495 472
496 bau= [X86_UV] Enable the BA 473 bau= [X86_UV] Enable the BAU on SGI UV. The default
497 behavior is to disable 474 behavior is to disable the BAU (i.e. bau=0).
498 Format: { "0" | "1" } 475 Format: { "0" | "1" }
499 0 - Disable the BAU. 476 0 - Disable the BAU.
500 1 - Enable the BAU. 477 1 - Enable the BAU.
501 unset - Disable the BA 478 unset - Disable the BAU.
502 479
503 baycom_epp= [HW,AX25] 480 baycom_epp= [HW,AX25]
504 Format: <io>,<mode> 481 Format: <io>,<mode>
505 482
506 baycom_par= [HW,AX25] BayCom Paral 483 baycom_par= [HW,AX25] BayCom Parallel Port AX.25 Modem
507 Format: <io>,<mode> 484 Format: <io>,<mode>
508 See header of drivers/ 485 See header of drivers/net/hamradio/baycom_par.c.
509 486
510 baycom_ser_fdx= [HW,AX25] 487 baycom_ser_fdx= [HW,AX25]
511 BayCom Serial Port AX. 488 BayCom Serial Port AX.25 Modem (Full Duplex Mode)
512 Format: <io>,<irq>,<mo 489 Format: <io>,<irq>,<mode>[,<baud>]
513 See header of drivers/ 490 See header of drivers/net/hamradio/baycom_ser_fdx.c.
514 491
515 baycom_ser_hdx= [HW,AX25] 492 baycom_ser_hdx= [HW,AX25]
516 BayCom Serial Port AX. 493 BayCom Serial Port AX.25 Modem (Half Duplex Mode)
517 Format: <io>,<irq>,<mo 494 Format: <io>,<irq>,<mode>
518 See header of drivers/ 495 See header of drivers/net/hamradio/baycom_ser_hdx.c.
519 496
520 bert_disable [ACPI] 497 bert_disable [ACPI]
521 Disable BERT OS suppor 498 Disable BERT OS support on buggy BIOSes.
522 499
523 bgrt_disable [ACPI,X86,EARLY] !! 500 bgrt_disable [ACPI][X86]
524 Disable BGRT to avoid 501 Disable BGRT to avoid flickering OEM logo.
525 502
526 blkdevparts= Manual partition parsi 503 blkdevparts= Manual partition parsing of block device(s) for
527 embedded devices based 504 embedded devices based on command line input.
528 See Documentation/bloc 505 See Documentation/block/cmdline-partition.rst
529 506
530 boot_delay= [KNL,EARLY] !! 507 boot_delay= Milliseconds to delay each printk during boot.
531 Milliseconds to delay <<
532 Only works if CONFIG_B 508 Only works if CONFIG_BOOT_PRINTK_DELAY is enabled,
533 and you may also have 509 and you may also have to specify "lpj=". Boot_delay
534 values larger than 10 510 values larger than 10 seconds (10000) are assumed
535 erroneous and ignored. 511 erroneous and ignored.
536 Format: integer 512 Format: integer
537 513
538 bootconfig [KNL,EARLY] !! 514 bootconfig [KNL]
539 Extended command line 515 Extended command line options can be added to an initrd
540 and this will cause th 516 and this will cause the kernel to look for it.
541 517
542 See Documentation/admi 518 See Documentation/admin-guide/bootconfig.rst
543 519
544 bttv.card= [HW,V4L] bttv (bt848 + 520 bttv.card= [HW,V4L] bttv (bt848 + bt878 based grabber cards)
545 bttv.radio= Most important insmod 521 bttv.radio= Most important insmod options are available as
546 kernel args too. 522 kernel args too.
547 bttv.pll= See Documentation/admi 523 bttv.pll= See Documentation/admin-guide/media/bttv.rst
548 bttv.tuner= 524 bttv.tuner=
549 525
550 bulk_remove=off [PPC] This parameter 526 bulk_remove=off [PPC] This parameter disables the use of the pSeries
551 firmware feature for f 527 firmware feature for flushing multiple hpte entries
552 at a time. 528 at a time.
553 529
554 c101= [NET] Moxa C101 synchr 530 c101= [NET] Moxa C101 synchronous serial card
555 531
556 cachesize= [BUGS=X86-32] Override 532 cachesize= [BUGS=X86-32] Override level 2 CPU cache size detection.
557 Sometimes CPU hardware 533 Sometimes CPU hardware bugs make them report the cache
558 size incorrectly. The 534 size incorrectly. The kernel will attempt work arounds
559 to fix known problems, 535 to fix known problems, but for some CPUs it is not
560 possible to determine 536 possible to determine what the correct size should be.
561 This option provides a 537 This option provides an override for these situations.
562 538
563 carrier_timeout= 539 carrier_timeout=
564 [NET] Specifies amount 540 [NET] Specifies amount of time (in seconds) that
565 the kernel should wait 541 the kernel should wait for a network carrier. By default
566 it waits 120 seconds. 542 it waits 120 seconds.
567 543
568 ca_keys= [KEYS] This parameter 544 ca_keys= [KEYS] This parameter identifies a specific key(s) on
569 the system trusted key 545 the system trusted keyring to be used for certificate
570 trust validation. 546 trust validation.
571 format: { id:<keyid> | 547 format: { id:<keyid> | builtin }
572 548
573 cca= [MIPS,EARLY] Override !! 549 cca= [MIPS] Override the kernel pages' cache coherency
574 algorithm. Accepted v 550 algorithm. Accepted values range from 0 to 7
575 inclusive. See arch/mi 551 inclusive. See arch/mips/include/asm/pgtable-bits.h
576 for platform specific 552 for platform specific values (SB1, Loongson3 and
577 others). 553 others).
578 554
579 ccw_timeout_log [S390] 555 ccw_timeout_log [S390]
580 See Documentation/arch 556 See Documentation/arch/s390/common_io.rst for details.
581 557
582 cgroup_disable= [KNL] Disable a partic 558 cgroup_disable= [KNL] Disable a particular controller or optional feature
583 Format: {name of the c 559 Format: {name of the controller(s) or feature(s) to disable}
584 The effects of cgroup_ 560 The effects of cgroup_disable=foo are:
585 - foo isn't auto-mount 561 - foo isn't auto-mounted if you mount all cgroups in
586 a single hierarchy 562 a single hierarchy
587 - foo isn't visible as 563 - foo isn't visible as an individually mountable
588 subsystem 564 subsystem
589 - if foo is an optiona 565 - if foo is an optional feature then the feature is
590 disabled and corresp 566 disabled and corresponding cgroup files are not
591 created 567 created
592 {Currently only "memor 568 {Currently only "memory" controller deal with this and
593 cut the overhead, othe 569 cut the overhead, others just disable the usage. So
594 only cgroup_disable=me 570 only cgroup_disable=memory is actually worthy}
595 Specifying "pressure" 571 Specifying "pressure" disables per-cgroup pressure
596 stall information acco 572 stall information accounting feature
597 573
598 cgroup_no_v1= [KNL] Disable cgroup c 574 cgroup_no_v1= [KNL] Disable cgroup controllers and named hierarchies in v1
599 Format: { { controller 575 Format: { { controller | "all" | "named" }
600 [,{ controll 576 [,{ controller | "all" | "named" }...] }
601 Like cgroup_disable, b 577 Like cgroup_disable, but only applies to cgroup v1;
602 the blacklisted contro 578 the blacklisted controllers remain available in cgroup2.
603 "all" blacklists all c 579 "all" blacklists all controllers and "named" disables
604 named mounts. Specifyi 580 named mounts. Specifying both "all" and "named" disables
605 all v1 hierarchies. 581 all v1 hierarchies.
606 582
607 cgroup_favordynmods= [KNL] Enable or D <<
608 Format: { "true" | "fa <<
609 Defaults to the value <<
610 <<
611 cgroup.memory= [KNL] Pass options to 583 cgroup.memory= [KNL] Pass options to the cgroup memory controller.
612 Format: <string> 584 Format: <string>
613 nosocket -- Disable so 585 nosocket -- Disable socket memory accounting.
614 nokmem -- Disable kern 586 nokmem -- Disable kernel memory accounting.
615 nobpf -- Disable BPF m 587 nobpf -- Disable BPF memory accounting.
616 588
617 checkreqprot= [SELINUX] Set initial 589 checkreqprot= [SELINUX] Set initial checkreqprot flag value.
618 Format: { "0" | "1" } 590 Format: { "0" | "1" }
619 See security/selinux/K 591 See security/selinux/Kconfig help text.
620 0 -- check protection 592 0 -- check protection applied by kernel (includes
621 any implied ex 593 any implied execute protection).
622 1 -- check protection 594 1 -- check protection requested by application.
623 Default value is set v 595 Default value is set via a kernel config option.
624 Value can be changed a 596 Value can be changed at runtime via
625 /sys/fs/selinu 597 /sys/fs/selinux/checkreqprot.
626 Setting checkreqprot t 598 Setting checkreqprot to 1 is deprecated.
627 599
628 cio_ignore= [S390] 600 cio_ignore= [S390]
629 See Documentation/arch 601 See Documentation/arch/s390/common_io.rst for details.
630 602
631 clearcpuid=X[,X...] [X86] 603 clearcpuid=X[,X...] [X86]
632 Disable CPUID feature 604 Disable CPUID feature X for the kernel. See
633 arch/x86/include/asm/c 605 arch/x86/include/asm/cpufeatures.h for the valid bit
634 numbers X. Note the Li 606 numbers X. Note the Linux-specific bits are not necessarily
635 stable over kernel opt 607 stable over kernel options, but the vendor-specific
636 ones should be. 608 ones should be.
637 X can also be a string 609 X can also be a string as appearing in the flags: line
638 in /proc/cpuinfo which 610 in /proc/cpuinfo which does not have the above
639 instability issue. How 611 instability issue. However, not all features have names
640 in /proc/cpuinfo. 612 in /proc/cpuinfo.
641 Note that using this o 613 Note that using this option will taint your kernel.
642 Also note that user pr 614 Also note that user programs calling CPUID directly
643 or using the feature w 615 or using the feature without checking anything
644 will still see it. Thi 616 will still see it. This just prevents it from
645 being used by the kern 617 being used by the kernel or shown in /proc/cpuinfo.
646 Also note the kernel m 618 Also note the kernel might malfunction if you disable
647 some critical bits. 619 some critical bits.
648 620
649 clk_ignore_unused 621 clk_ignore_unused
650 [CLK] 622 [CLK]
651 Prevents the clock fra 623 Prevents the clock framework from automatically gating
652 clocks that have not b 624 clocks that have not been explicitly enabled by a Linux
653 device driver but are 625 device driver but are enabled in hardware at reset or
654 by the bootloader/firm 626 by the bootloader/firmware. Note that this does not
655 force such clocks to b 627 force such clocks to be always-on nor does it reserve
656 those clocks in any wa 628 those clocks in any way. This parameter is useful for
657 debug and development, 629 debug and development, but should not be needed on a
658 platform with proper d 630 platform with proper driver support. For more
659 information, see Docum 631 information, see Documentation/driver-api/clk.rst.
660 632
661 clock= [BUGS=X86-32, HW] gett 633 clock= [BUGS=X86-32, HW] gettimeofday clocksource override.
662 [Deprecated] 634 [Deprecated]
663 Forces specified clock 635 Forces specified clocksource (if available) to be used
664 when calculating getti 636 when calculating gettimeofday(). If specified
665 clocksource is not ava 637 clocksource is not available, it defaults to PIT.
666 Format: { pit | tsc | 638 Format: { pit | tsc | cyclone | pmtmr }
667 639
668 clocksource= Override the default c 640 clocksource= Override the default clocksource
669 Format: <string> 641 Format: <string>
670 Override the default c 642 Override the default clocksource and use the clocksource
671 with the name specifie 643 with the name specified.
672 Some clocksource names 644 Some clocksource names to choose from, depending on
673 the platform: 645 the platform:
674 [all] jiffies (this is 646 [all] jiffies (this is the base, fallback clocksource)
675 [ACPI] acpi_pm 647 [ACPI] acpi_pm
676 [ARM] imx_timer1,OSTS, 648 [ARM] imx_timer1,OSTS,netx_timer,mpu_timer2,
677 pxa_timer,time 649 pxa_timer,timer3,32k_counter,timer0_1
678 [X86-32] pit,hpet,tsc; 650 [X86-32] pit,hpet,tsc;
679 scx200_hrt on 651 scx200_hrt on Geode; cyclone on IBM x440
680 [MIPS] MIPS 652 [MIPS] MIPS
681 [PARISC] cr16 653 [PARISC] cr16
682 [S390] tod 654 [S390] tod
683 [SH] SuperH 655 [SH] SuperH
684 [SPARC64] tick 656 [SPARC64] tick
685 [X86-64] hpet,tsc 657 [X86-64] hpet,tsc
686 658
687 clocksource.arm_arch_timer.evtstrm= 659 clocksource.arm_arch_timer.evtstrm=
688 [ARM,ARM64,EARLY] !! 660 [ARM,ARM64]
689 Format: <bool> 661 Format: <bool>
690 Enable/disable the eve 662 Enable/disable the eventstream feature of the ARM
691 architected timer so t 663 architected timer so that code using WFE-based polling
692 loops can be debugged 664 loops can be debugged more effectively on production
693 systems. 665 systems.
694 666
695 clocksource.verify_n_cpus= [KNL] 667 clocksource.verify_n_cpus= [KNL]
696 Limit the number of CP 668 Limit the number of CPUs checked for clocksources
697 marked with CLOCK_SOUR 669 marked with CLOCK_SOURCE_VERIFY_PERCPU that
698 are marked unstable du 670 are marked unstable due to excessive skew.
699 A negative value says 671 A negative value says to check all CPUs, while
700 zero says not to check 672 zero says not to check any. Values larger than
701 nr_cpu_ids are silentl 673 nr_cpu_ids are silently truncated to nr_cpu_ids.
702 The actual CPUs are ch 674 The actual CPUs are chosen randomly, with
703 no replacement if the 675 no replacement if the same CPU is chosen twice.
704 676
705 clocksource-wdtest.holdoff= [KNL] 677 clocksource-wdtest.holdoff= [KNL]
706 Set the time in second 678 Set the time in seconds that the clocksource
707 watchdog test waits be 679 watchdog test waits before commencing its tests.
708 Defaults to zero when 680 Defaults to zero when built as a module and to
709 10 seconds when built 681 10 seconds when built into the kernel.
710 682
711 cma=nn[MG]@[start[MG][-end[MG]]] 683 cma=nn[MG]@[start[MG][-end[MG]]]
712 [KNL,CMA,EARLY] !! 684 [KNL,CMA]
713 Sets the size of kerne 685 Sets the size of kernel global memory area for
714 contiguous memory allo 686 contiguous memory allocations and optionally the
715 placement constraint b 687 placement constraint by the physical address range of
716 memory allocations. A 688 memory allocations. A value of 0 disables CMA
717 altogether. For more i 689 altogether. For more information, see
718 kernel/dma/contiguous. 690 kernel/dma/contiguous.c
719 691
720 cma_pernuma=nn[MG] 692 cma_pernuma=nn[MG]
721 [KNL,CMA,EARLY] !! 693 [KNL,CMA]
722 Sets the size of kerne 694 Sets the size of kernel per-numa memory area for
723 contiguous memory allo 695 contiguous memory allocations. A value of 0 disables
724 per-numa CMA altogethe 696 per-numa CMA altogether. And If this option is not
725 specified, the default 697 specified, the default value is 0.
726 With per-numa CMA enab 698 With per-numa CMA enabled, DMA users on node nid will
727 first try to allocate 699 first try to allocate buffer from the pernuma area
728 which is located in no 700 which is located in node nid, if the allocation fails,
729 they will fallback to 701 they will fallback to the global default memory area.
730 702
731 numa_cma=<node>:nn[MG][,<node>:nn[MG]] 703 numa_cma=<node>:nn[MG][,<node>:nn[MG]]
732 [KNL,CMA,EARLY] !! 704 [KNL,CMA]
733 Sets the size of kerne 705 Sets the size of kernel numa memory area for
734 contiguous memory allo 706 contiguous memory allocations. It will reserve CMA
735 area for the specified 707 area for the specified node.
736 708
737 With numa CMA enabled, 709 With numa CMA enabled, DMA users on node nid will
738 first try to allocate 710 first try to allocate buffer from the numa area
739 which is located in no 711 which is located in node nid, if the allocation fails,
740 they will fallback to 712 they will fallback to the global default memory area.
741 713
742 cmo_free_hint= [PPC] Format: { yes | 714 cmo_free_hint= [PPC] Format: { yes | no }
743 Specify whether pages 715 Specify whether pages are marked as being inactive
744 when they are freed. 716 when they are freed. This is used in CMO environments
745 to determine OS memory 717 to determine OS memory pressure for page stealing by
746 a hypervisor. 718 a hypervisor.
747 Default: yes 719 Default: yes
748 720
749 coherent_pool=nn[KMG] [ARM,KNL,EARLY !! 721 coherent_pool=nn[KMG] [ARM,KNL]
750 Sets the size of memor 722 Sets the size of memory pool for coherent, atomic dma
751 allocations, by defaul 723 allocations, by default set to 256K.
752 724
753 com20020= [HW,NET] ARCnet - COM2 725 com20020= [HW,NET] ARCnet - COM20020 chipset
754 Format: 726 Format:
755 <io>[,<irq>[,<nodeID>[ 727 <io>[,<irq>[,<nodeID>[,<backplane>[,<ckp>[,<timeout>]]]]]
756 728
757 com90io= [HW,NET] ARCnet - COM9 729 com90io= [HW,NET] ARCnet - COM90xx chipset (IO-mapped buffers)
758 Format: <io>[,<irq>] 730 Format: <io>[,<irq>]
759 731
760 com90xx= [HW,NET] 732 com90xx= [HW,NET]
761 ARCnet - COM90xx chips 733 ARCnet - COM90xx chipset (memory-mapped buffers)
762 Format: <io>[,<irq>[,< 734 Format: <io>[,<irq>[,<memstart>]]
763 735
764 condev= [HW,S390] console devi 736 condev= [HW,S390] console device
765 conmode= 737 conmode=
766 738
767 con3215_drop= [S390,EARLY] 3215 cons !! 739 con3215_drop= [S390] 3215 console drop mode.
768 Format: y|n|Y|N|1|0 740 Format: y|n|Y|N|1|0
769 When set to true, drop 741 When set to true, drop data on the 3215 console when
770 the console buffer is 742 the console buffer is full. In this case the
771 operator using a 3270 743 operator using a 3270 terminal emulator (for example
772 x3270) does not have t 744 x3270) does not have to enter the clear key for the
773 console output to adva 745 console output to advance and the kernel to continue.
774 This leads to a much f 746 This leads to a much faster boot time when a 3270
775 terminal emulator is a 747 terminal emulator is active. If no 3270 terminal
776 emulator is used, this 748 emulator is used, this parameter has no effect.
777 749
778 console= [KNL] Output console d 750 console= [KNL] Output console device and options.
779 751
780 tty<n> Use the virtual consol 752 tty<n> Use the virtual console device <n>.
781 753
782 ttyS<n>[,options] 754 ttyS<n>[,options]
783 ttyUSB0[,options] 755 ttyUSB0[,options]
784 Use the specified seri 756 Use the specified serial port. The options are of
785 the form "bbbbpnf", wh 757 the form "bbbbpnf", where "bbbb" is the baud rate,
786 "p" is parity ("n", "o 758 "p" is parity ("n", "o", or "e"), "n" is number of
787 bits, and "f" is flow 759 bits, and "f" is flow control ("r" for RTS or
788 omit it). Default is 760 omit it). Default is "9600n8".
789 761
790 See Documentation/admi 762 See Documentation/admin-guide/serial-console.rst for more
791 information. See 763 information. See
792 Documentation/networki 764 Documentation/networking/netconsole.rst for an
793 alternative. 765 alternative.
794 766
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] 767 uart[8250],io,<addr>[,options]
815 uart[8250],mmio,<addr>[,option 768 uart[8250],mmio,<addr>[,options]
816 uart[8250],mmio16,<addr>[,opti 769 uart[8250],mmio16,<addr>[,options]
817 uart[8250],mmio32,<addr>[,opti 770 uart[8250],mmio32,<addr>[,options]
818 uart[8250],0x<addr>[,options] 771 uart[8250],0x<addr>[,options]
819 Start an early, polled 772 Start an early, polled-mode console on the 8250/16550
820 UART at the specified 773 UART at the specified I/O port or MMIO address,
821 switching to the match 774 switching to the matching ttyS device later.
822 MMIO inter-register ad 775 MMIO inter-register address stride is either 8-bit
823 (mmio), 16-bit (mmio16 776 (mmio), 16-bit (mmio16), or 32-bit (mmio32).
824 If none of [io|mmio|mm 777 If none of [io|mmio|mmio16|mmio32], <addr> is assumed
825 to be equivalent to 'm 778 to be equivalent to 'mmio'. 'options' are specified in
826 the same format descri 779 the same format described for ttyS above; if unspecified,
827 the h/w is not re-init 780 the h/w is not re-initialized.
828 781
829 hvc<n> Use the hypervisor con 782 hvc<n> Use the hypervisor console device <n>. This is for
830 both Xen and PowerPC h 783 both Xen and PowerPC hypervisors.
831 784
832 { null | "" } 785 { null | "" }
833 Use to disable console 786 Use to disable console output, i.e., to have kernel
834 console messages disca 787 console messages discarded.
835 This must be the only 788 This must be the only console= parameter used on the
836 kernel command line. 789 kernel command line.
837 790
838 If the device connected to the 791 If the device connected to the port is not a TTY but a braille
839 device, prepend "brl," before 792 device, prepend "brl," before the device type, for instance
840 console=brl,ttyS0 793 console=brl,ttyS0
841 For now, only VisioBraille is 794 For now, only VisioBraille is supported.
842 795
843 console_msg_format= 796 console_msg_format=
844 [KNL] Change console m 797 [KNL] Change console messages format
845 default 798 default
846 By default we print me 799 By default we print messages on consoles in
847 "[time stamp] text\n" 800 "[time stamp] text\n" format (time stamp may not be
848 printed, depending on 801 printed, depending on CONFIG_PRINTK_TIME or
849 `printk_time' param). 802 `printk_time' param).
850 syslog 803 syslog
851 Switch to syslog forma 804 Switch to syslog format: "<%u>[time stamp] text\n"
852 IOW, each message will 805 IOW, each message will have a facility and loglevel
853 prefix. The format is 806 prefix. The format is similar to one used by syslog()
854 syscall, or to executi 807 syscall, or to executing "dmesg -S --raw" or to reading
855 from /proc/kmsg. 808 from /proc/kmsg.
856 809
857 consoleblank= [KNL] The console blan 810 consoleblank= [KNL] The console blank (screen saver) timeout in
858 seconds. A value of 0 811 seconds. A value of 0 disables the blank timer.
859 Defaults to 0. 812 Defaults to 0.
860 813
861 coredump_filter= 814 coredump_filter=
862 [KNL] Change the defau 815 [KNL] Change the default value for
863 /proc/<pid>/coredump_f 816 /proc/<pid>/coredump_filter.
864 See also Documentation 817 See also Documentation/filesystems/proc.rst.
865 818
866 coresight_cpu_debug.enable 819 coresight_cpu_debug.enable
867 [ARM,ARM64] 820 [ARM,ARM64]
868 Format: <bool> 821 Format: <bool>
869 Enable/disable the CPU 822 Enable/disable the CPU sampling based debugging.
870 0: default value, disa 823 0: default value, disable debugging
871 1: enable debugging at 824 1: enable debugging at boot time
872 825
873 cpcihp_generic= [HW,PCI] Generic port 826 cpcihp_generic= [HW,PCI] Generic port I/O CompactPCI driver
874 Format: 827 Format:
875 <first_slot>,<last_slo 828 <first_slot>,<last_slot>,<port>,<enum_bit>[,<debug>]
876 829
877 cpuidle.off=1 [CPU_IDLE] 830 cpuidle.off=1 [CPU_IDLE]
878 disable the cpuidle su 831 disable the cpuidle sub-system
879 832
880 cpuidle.governor= 833 cpuidle.governor=
881 [CPU_IDLE] Name of the 834 [CPU_IDLE] Name of the cpuidle governor to use.
882 835
883 cpufreq.off=1 [CPU_FREQ] 836 cpufreq.off=1 [CPU_FREQ]
884 disable the cpufreq su 837 disable the cpufreq sub-system
885 838
886 cpufreq.default_governor= 839 cpufreq.default_governor=
887 [CPU_FREQ] Name of the 840 [CPU_FREQ] Name of the default cpufreq governor or
888 policy to use. This go 841 policy to use. This governor must be registered in the
889 kernel before the cpuf 842 kernel before the cpufreq driver probes.
890 843
891 cpu_init_udelay=N 844 cpu_init_udelay=N
892 [X86,EARLY] Delay for !! 845 [X86] Delay for N microsec between assert and de-assert
893 of APIC INIT to start 846 of APIC INIT to start processors. This delay occurs
894 on every CPU online, s 847 on every CPU online, such as boot, and resume from suspend.
895 Default: 10000 848 Default: 10000
896 849
897 cpuhp.parallel= 850 cpuhp.parallel=
898 [SMP] Enable/disable p 851 [SMP] Enable/disable parallel bringup of secondary CPUs
899 Format: <bool> 852 Format: <bool>
900 Default is enabled if 853 Default is enabled if CONFIG_HOTPLUG_PARALLEL=y. Otherwise
901 the parameter has no e 854 the parameter has no effect.
902 855
903 crash_kexec_post_notifiers 856 crash_kexec_post_notifiers
904 Run kdump after runnin 857 Run kdump after running panic-notifiers and dumping
905 kmsg. This only for th 858 kmsg. This only for the users who doubt kdump always
906 succeeds in any situat 859 succeeds in any situation.
907 Note that this also in 860 Note that this also increases risks of kdump failure,
908 because some panic not 861 because some panic notifiers can make the crashed
909 kernel more unstable. 862 kernel more unstable.
910 863
911 crashkernel=size[KMG][@offset[KMG]] 864 crashkernel=size[KMG][@offset[KMG]]
912 [KNL,EARLY] Using kexe !! 865 [KNL] Using kexec, Linux can switch to a 'crash kernel'
913 upon panic. This param 866 upon panic. This parameter reserves the physical
914 memory region [offset, 867 memory region [offset, offset + size] for that kernel
915 image. If '@offset' is 868 image. If '@offset' is omitted, then a suitable offset
916 is selected automatica 869 is selected automatically.
917 [KNL, X86-64, ARM64, R !! 870 [KNL, X86-64, ARM64, RISCV] Select a region under 4G first, and
918 under 4G first, and fa !! 871 fall back to reserve region above 4G when '@offset'
919 4G when '@offset' hasn !! 872 hasn't been specified.
920 See Documentation/admi 873 See Documentation/admin-guide/kdump/kdump.rst for further details.
921 874
922 crashkernel=range1:size1[,range2:size2 875 crashkernel=range1:size1[,range2:size2,...][@offset]
923 [KNL] Same as above, b 876 [KNL] Same as above, but depends on the memory
924 in the running system. 877 in the running system. The syntax of range is
925 start-[end] where star 878 start-[end] where start and end are both
926 a memory unit (amount[ 879 a memory unit (amount[KMG]). See also
927 Documentation/admin-gu 880 Documentation/admin-guide/kdump/kdump.rst for an example.
928 881
929 crashkernel=size[KMG],high 882 crashkernel=size[KMG],high
930 [KNL, X86-64, ARM64, R !! 883 [KNL, X86-64, ARM64, RISCV] range could be above 4G.
931 above 4G. <<
932 Allow kernel to alloca 884 Allow kernel to allocate physical memory region from top,
933 so could be above 4G i 885 so could be above 4G if system have more than 4G ram
934 installed. Otherwise m 886 installed. Otherwise memory region will be allocated
935 below 4G, if available 887 below 4G, if available.
936 It will be ignored if 888 It will be ignored if crashkernel=X is specified.
937 crashkernel=size[KMG],low 889 crashkernel=size[KMG],low
938 [KNL, X86-64, ARM64, R !! 890 [KNL, X86-64, ARM64, RISCV] range under 4G. When crashkernel=X,high
939 When crashkernel=X,hig !! 891 is passed, kernel could allocate physical memory region
940 physical memory region !! 892 above 4G, that cause second kernel crash on system
941 crash on system that r !! 893 that require some amount of low memory, e.g. swiotlb
942 e.g. swiotlb requires !! 894 requires at least 64M+32K low memory, also enough extra
943 enough extra low memor !! 895 low memory is needed to make sure DMA buffers for 32-bit
944 for 32-bit devices won !! 896 devices won't run out. Kernel would try to allocate
945 default size of memory 897 default size of memory below 4G automatically. The default
946 size is platform depen 898 size is platform dependent.
947 --> x86: max(swiotlb 899 --> x86: max(swiotlb_size_or_default() + 8MiB, 256MiB)
948 --> arm64: 128MiB 900 --> arm64: 128MiB
949 --> riscv: 128MiB 901 --> riscv: 128MiB
950 --> loongarch: 128Mi <<
951 This one lets the user 902 This one lets the user specify own low range under 4G
952 for second kernel inst 903 for second kernel instead.
953 0: to disable low allo 904 0: to disable low allocation.
954 It will be ignored whe 905 It will be ignored when crashkernel=X,high is not used
955 or memory reserved is 906 or memory reserved is below 4G.
956 907
957 cryptomgr.notests 908 cryptomgr.notests
958 [KNL] Disable crypto s 909 [KNL] Disable crypto self-tests
959 910
960 cs89x0_dma= [HW,NET] 911 cs89x0_dma= [HW,NET]
961 Format: <dma> 912 Format: <dma>
962 913
963 cs89x0_media= [HW,NET] 914 cs89x0_media= [HW,NET]
964 Format: { rj45 | aui | 915 Format: { rj45 | aui | bnc }
965 916
966 csdlock_debug= [KNL] Enable or disabl 917 csdlock_debug= [KNL] Enable or disable debug add-ons of cross-CPU
967 function call handling 918 function call handling. When switched on,
968 additional debug data 919 additional debug data is printed to the console
969 in case a hanging CPU 920 in case a hanging CPU is detected, and that
970 CPU is pinged again in 921 CPU is pinged again in order to try to resolve
971 the hang situation. T 922 the hang situation. The default value of this
972 option depends on the 923 option depends on the CSD_LOCK_WAIT_DEBUG_DEFAULT
973 Kconfig option. 924 Kconfig option.
974 925
975 dasd= [HW,NET] 926 dasd= [HW,NET]
976 See header of drivers/ 927 See header of drivers/s390/block/dasd_devmap.c.
977 928
978 db9.dev[2|3]= [HW,JOY] Multisystem j 929 db9.dev[2|3]= [HW,JOY] Multisystem joystick support via parallel port
979 (one device per port) 930 (one device per port)
980 Format: <port#>,<type> 931 Format: <port#>,<type>
981 See also Documentation 932 See also Documentation/input/devices/joystick-parport.rst
982 933
983 debug [KNL,EARLY] Enable ker !! 934 debug [KNL] Enable kernel debugging (events log level).
984 935
985 debug_boot_weak_hash 936 debug_boot_weak_hash
986 [KNL,EARLY] Enable pri !! 937 [KNL] Enable printing [hashed] pointers early in the
987 boot sequence. If ena 938 boot sequence. If enabled, we use a weak hash instead
988 of siphash to hash poi 939 of siphash to hash pointers. Use this option if you are
989 seeing instances of '( 940 seeing instances of '(___ptrval___)') and need to see a
990 value (hashed pointer) 941 value (hashed pointer) instead. Cryptographically
991 insecure, please do no 942 insecure, please do not use on production kernels.
992 943
993 debug_locks_verbose= 944 debug_locks_verbose=
994 [KNL] verbose locking 945 [KNL] verbose locking self-tests
995 Format: <int> 946 Format: <int>
996 Print debugging info w 947 Print debugging info while doing the locking API
997 self-tests. 948 self-tests.
998 Bitmask for the variou 949 Bitmask for the various LOCKTYPE_ tests. Defaults to 0
999 (no extra messages), s 950 (no extra messages), setting it to -1 (all bits set)
1000 will print _a_lot_ mo 951 will print _a_lot_ more information - normally only
1001 useful to lockdep dev 952 useful to lockdep developers.
1002 953
1003 debug_objects [KNL,EARLY] Enable ob !! 954 debug_objects [KNL] Enable object debugging
1004 955
1005 debug_guardpage_minorder= 956 debug_guardpage_minorder=
1006 [KNL,EARLY] When CONF !! 957 [KNL] When CONFIG_DEBUG_PAGEALLOC is set, this
1007 parameter allows cont 958 parameter allows control of the order of pages that will
1008 be intentionally kept 959 be intentionally kept free (and hence protected) by the
1009 buddy allocator. Bigg 960 buddy allocator. Bigger value increase the probability
1010 of catching random me 961 of catching random memory corruption, but reduce the
1011 amount of memory for 962 amount of memory for normal system use. The maximum
1012 possible value is MAX !! 963 possible value is MAX_ORDER/2. Setting this parameter
1013 parameter to 1 or 2 s !! 964 to 1 or 2 should be enough to identify most random
1014 random memory corrupt !! 965 memory corruption problems caused by bugs in kernel or
1015 kernel or driver code !! 966 driver code when a CPU writes to (or reads from) a
1016 from) a random memory !! 967 random memory location. Note that there exists a class
1017 a class of memory cor !! 968 of memory corruptions problems caused by buggy H/W or
1018 H/W or F/W or by driv !! 969 F/W or by drivers badly programming DMA (basically when
1019 (basically when memor !! 970 memory is written at bus level and the CPU MMU is
1020 CPU MMU is bypassed) !! 971 bypassed) which are not detectable by
1021 CONFIG_DEBUG_PAGEALLO !! 972 CONFIG_DEBUG_PAGEALLOC, hence this option will not help
1022 help tracking down th !! 973 tracking down these problems.
1023 974
1024 debug_pagealloc= 975 debug_pagealloc=
1025 [KNL,EARLY] When CONF !! 976 [KNL] When CONFIG_DEBUG_PAGEALLOC is set, this parameter
1026 enables the feature a 977 enables the feature at boot time. By default, it is
1027 disabled and the syst 978 disabled and the system will work mostly the same as a
1028 kernel built without 979 kernel built without CONFIG_DEBUG_PAGEALLOC.
1029 Note: to get most of 980 Note: to get most of debug_pagealloc error reports, it's
1030 useful to also enable 981 useful to also enable the page_owner functionality.
1031 on: enable the featur 982 on: enable the feature
1032 983
1033 debugfs= [KNL,EARLY] This para !! 984 debugfs= [KNL] This parameter enables what is exposed to userspace
1034 userspace and debugfs !! 985 and debugfs internal clients.
1035 Format: { on, no-moun 986 Format: { on, no-mount, off }
1036 on: All functions 987 on: All functions are enabled.
1037 no-mount: 988 no-mount:
1038 Filesystem is 989 Filesystem is not registered but kernel clients can
1039 access APIs a 990 access APIs and a crashkernel can be used to read
1040 its content. 991 its content. There is nothing to mount.
1041 off: Filesystem is 992 off: Filesystem is not registered and clients
1042 get a -EPERM 993 get a -EPERM as result when trying to register files
1043 or directorie 994 or directories within debugfs.
1044 This is equiv 995 This is equivalent of the runtime functionality if
1045 debugfs was n 996 debugfs was not enabled in the kernel at all.
1046 Default value is set 997 Default value is set in build-time with a kernel configuration.
1047 998
1048 debugpat [X86] Enable PAT debu 999 debugpat [X86] Enable PAT debugging
1049 1000
1050 default_hugepagesz= 1001 default_hugepagesz=
1051 [HW] The size of the 1002 [HW] The size of the default HugeTLB page. This is
1052 the size represented 1003 the size represented by the legacy /proc/ hugepages
1053 APIs. In addition, t 1004 APIs. In addition, this is the default hugetlb size
1054 used for shmget(), mm 1005 used for shmget(), mmap() and mounting hugetlbfs
1055 filesystems. If not 1006 filesystems. If not specified, defaults to the
1056 architecture's defaul 1007 architecture's default huge page size. Huge page
1057 sizes are architectur 1008 sizes are architecture dependent. See also
1058 Documentation/admin-g 1009 Documentation/admin-guide/mm/hugetlbpage.rst.
1059 Format: size[KMG] 1010 Format: size[KMG]
1060 1011
1061 deferred_probe_timeout= 1012 deferred_probe_timeout=
1062 [KNL] Debugging optio 1013 [KNL] Debugging option to set a timeout in seconds for
1063 deferred probe to giv 1014 deferred probe to give up waiting on dependencies to
1064 probe. Only specific 1015 probe. Only specific dependencies (subsystems or
1065 drivers) that have op 1016 drivers) that have opted in will be ignored. A timeout
1066 of 0 will timeout at 1017 of 0 will timeout at the end of initcalls. If the time
1067 out hasn't expired, i 1018 out hasn't expired, it'll be restarted by each
1068 successful driver reg 1019 successful driver registration. This option will also
1069 dump out devices stil 1020 dump out devices still on the deferred probe list after
1070 retrying. 1021 retrying.
1071 1022
1072 delayacct [KNL] Enable per-task 1023 delayacct [KNL] Enable per-task delay accounting
1073 1024
1074 dell_smm_hwmon.ignore_dmi= 1025 dell_smm_hwmon.ignore_dmi=
1075 [HW] Continue probing 1026 [HW] Continue probing hardware even if DMI data
1076 indicates that the dr 1027 indicates that the driver is running on unsupported
1077 hardware. 1028 hardware.
1078 1029
1079 dell_smm_hwmon.force= 1030 dell_smm_hwmon.force=
1080 [HW] Activate driver 1031 [HW] Activate driver even if SMM BIOS signature does
1081 not match list of sup 1032 not match list of supported models and enable otherwise
1082 blacklisted features. 1033 blacklisted features.
1083 1034
1084 dell_smm_hwmon.power_status= 1035 dell_smm_hwmon.power_status=
1085 [HW] Report power sta 1036 [HW] Report power status in /proc/i8k
1086 (disabled by default) 1037 (disabled by default).
1087 1038
1088 dell_smm_hwmon.restricted= 1039 dell_smm_hwmon.restricted=
1089 [HW] Allow controllin 1040 [HW] Allow controlling fans only if SYS_ADMIN
1090 capability is set. 1041 capability is set.
1091 1042
1092 dell_smm_hwmon.fan_mult= 1043 dell_smm_hwmon.fan_mult=
1093 [HW] Factor to multip 1044 [HW] Factor to multiply fan speed with.
1094 1045
1095 dell_smm_hwmon.fan_max= 1046 dell_smm_hwmon.fan_max=
1096 [HW] Maximum configur 1047 [HW] Maximum configurable fan speed.
1097 1048
1098 dfltcc= [HW,S390] 1049 dfltcc= [HW,S390]
1099 Format: { on | off | 1050 Format: { on | off | def_only | inf_only | always }
1100 on: s390 zlib h 1051 on: s390 zlib hardware support for compression on
1101 level 1 and 1052 level 1 and decompression (default)
1102 off: No s390 zli 1053 off: No s390 zlib hardware support
1103 def_only: s390 zlib h 1054 def_only: s390 zlib hardware support for deflate
1104 only (compr 1055 only (compression on level 1)
1105 inf_only: s390 zlib h 1056 inf_only: s390 zlib hardware support for inflate
1106 only (decom 1057 only (decompression)
1107 always: Same as 'on 1058 always: Same as 'on' but ignores the selected compression
1108 level alway 1059 level always using hardware support (used for debugging)
1109 1060
1110 dhash_entries= [KNL] 1061 dhash_entries= [KNL]
1111 Set number of hash bu 1062 Set number of hash buckets for dentry cache.
1112 1063
1113 disable_1tb_segments [PPC,EARLY] !! 1064 disable_1tb_segments [PPC]
1114 Disables the use of 1 1065 Disables the use of 1TB hash page table segments. This
1115 causes the kernel to 1066 causes the kernel to fall back to 256MB segments which
1116 can be useful when de 1067 can be useful when debugging issues that require an SLB
1117 miss to occur. 1068 miss to occur.
1118 1069
1119 disable= [IPV6] 1070 disable= [IPV6]
1120 See Documentation/net 1071 See Documentation/networking/ipv6.rst.
1121 1072
1122 disable_radix [PPC,EARLY] !! 1073 disable_radix [PPC]
1123 Disable RADIX MMU mod 1074 Disable RADIX MMU mode on POWER9
1124 1075
1125 disable_tlbie [PPC] 1076 disable_tlbie [PPC]
1126 Disable TLBIE instruc 1077 Disable TLBIE instruction. Currently does not work
1127 with KVM, with HASH M 1078 with KVM, with HASH MMU, or with coherent accelerators.
1128 1079
1129 disable_ddw [PPC/PSERIES,EARLY] !! 1080 disable_cpu_apicid= [X86,APIC,SMP]
>> 1081 Format: <int>
>> 1082 The number of initial APIC ID for the
>> 1083 corresponding CPU to be disabled at boot,
>> 1084 mostly used for the kdump 2nd kernel to
>> 1085 disable BSP to wake up multiple CPUs without
>> 1086 causing system reset or hang due to sending
>> 1087 INIT from AP to BSP.
>> 1088
>> 1089 disable_ddw [PPC/PSERIES]
1130 Disable Dynamic DMA W 1090 Disable Dynamic DMA Window support. Use this
1131 to workaround buggy f 1091 to workaround buggy firmware.
1132 1092
1133 disable_ipv6= [IPV6] 1093 disable_ipv6= [IPV6]
1134 See Documentation/net 1094 See Documentation/networking/ipv6.rst.
1135 1095
1136 disable_mtrr_cleanup [X86,EARLY] !! 1096 disable_mtrr_cleanup [X86]
1137 The kernel tries to a 1097 The kernel tries to adjust MTRR layout from continuous
1138 to discrete, to make 1098 to discrete, to make X server driver able to add WB
1139 entry later. This par 1099 entry later. This parameter disables that.
1140 1100
1141 disable_mtrr_trim [X86, Intel and AMD !! 1101 disable_mtrr_trim [X86, Intel and AMD only]
1142 By default the kernel 1102 By default the kernel will trim any uncacheable
1143 memory out of your av 1103 memory out of your available memory pool based on
1144 MTRR settings. This 1104 MTRR settings. This parameter disables that behavior,
1145 possibly causing your 1105 possibly causing your machine to run very slowly.
1146 1106
1147 disable_timer_pin_1 [X86,EARLY] !! 1107 disable_timer_pin_1 [X86]
1148 Disable PIN 1 of APIC 1108 Disable PIN 1 of APIC timer
1149 Can be useful to work 1109 Can be useful to work around chipset bugs.
1150 1110
1151 dis_ucode_ldr [X86] Disable the mic 1111 dis_ucode_ldr [X86] Disable the microcode loader.
1152 1112
1153 dma_debug=off If the kernel is comp 1113 dma_debug=off If the kernel is compiled with DMA_API_DEBUG support,
1154 this option disables 1114 this option disables the debugging code at boot.
1155 1115
1156 dma_debug_entries=<number> 1116 dma_debug_entries=<number>
1157 This option allows to 1117 This option allows to tune the number of preallocated
1158 entries for DMA-API d 1118 entries for DMA-API debugging code. One entry is
1159 required per DMA-API 1119 required per DMA-API allocation. Use this if the
1160 DMA-API debugging cod 1120 DMA-API debugging code disables itself because the
1161 architectural default 1121 architectural default is too low.
1162 1122
1163 dma_debug_driver=<driver_name> 1123 dma_debug_driver=<driver_name>
1164 With this option the 1124 With this option the DMA-API debugging driver
1165 filter feature can be 1125 filter feature can be enabled at boot time. Just
1166 pass the driver to fi 1126 pass the driver to filter for as the parameter.
1167 The filter can be dis 1127 The filter can be disabled or changed to another
1168 driver later using sy 1128 driver later using sysfs.
1169 1129
1170 reg_file_data_sampling= 1130 reg_file_data_sampling=
1171 [X86] Controls mitiga 1131 [X86] Controls mitigation for Register File Data
1172 Sampling (RFDS) vulne 1132 Sampling (RFDS) vulnerability. RFDS is a CPU
1173 vulnerability which m 1133 vulnerability which may allow userspace to infer
1174 kernel data values pr 1134 kernel data values previously stored in floating point
1175 registers, vector reg 1135 registers, vector registers, or integer registers.
1176 RFDS only affects Int 1136 RFDS only affects Intel Atom processors.
1177 1137
1178 on: Turns ON the 1138 on: Turns ON the mitigation.
1179 off: Turns OFF the 1139 off: Turns OFF the mitigation.
1180 1140
1181 This parameter overri 1141 This parameter overrides the compile time default set
1182 by CONFIG_MITIGATION_ 1142 by CONFIG_MITIGATION_RFDS. Mitigation cannot be
1183 disabled when other V 1143 disabled when other VERW based mitigations (like MDS)
1184 are enabled. In order 1144 are enabled. In order to disable RFDS mitigation all
1185 VERW based mitigation 1145 VERW based mitigations need to be disabled.
1186 1146
1187 For details see: 1147 For details see:
1188 Documentation/admin-g 1148 Documentation/admin-guide/hw-vuln/reg-file-data-sampling.rst
1189 1149
1190 driver_async_probe= [KNL] 1150 driver_async_probe= [KNL]
1191 List of driver names 1151 List of driver names to be probed asynchronously. *
1192 matches with all driv 1152 matches with all driver names. If * is specified, the
1193 rest of the listed dr 1153 rest of the listed driver names are those that will NOT
1194 match the *. 1154 match the *.
1195 Format: <driver_name1 1155 Format: <driver_name1>,<driver_name2>...
1196 1156
1197 drm.edid_firmware=[<connector>:]<file 1157 drm.edid_firmware=[<connector>:]<file>[,[<connector>:]<file>]
1198 Broken monitors, grap 1158 Broken monitors, graphic adapters, KVMs and EDIDless
1199 panels may send no or 1159 panels may send no or incorrect EDID data sets.
1200 This parameter allows 1160 This parameter allows to specify an EDID data sets
1201 in the /lib/firmware 1161 in the /lib/firmware directory that are used instead.
1202 An EDID data set will !! 1162 Generic built-in EDID data sets are used, if one of
1203 connector, if its nam !! 1163 edid/1024x768.bin, edid/1280x1024.bin,
1204 the EDID name. Each c !! 1164 edid/1680x1050.bin, or edid/1920x1080.bin is given
1205 data set by separatin !! 1165 and no file with the same name exists. Details and
>> 1166 instructions how to build your own EDID data are
>> 1167 available in Documentation/admin-guide/edid.rst. An EDID
>> 1168 data set will only be used for a particular connector,
>> 1169 if its name and a colon are prepended to the EDID
>> 1170 name. Each connector may use a unique EDID data
>> 1171 set by separating the files with a comma. An EDID
1206 data set with no conn 1172 data set with no connector name will be used for
1207 any connectors not ex 1173 any connectors not explicitly specified.
1208 1174
1209 dscc4.setup= [NET] 1175 dscc4.setup= [NET]
1210 1176
1211 dt_cpu_ftrs= [PPC,EARLY] !! 1177 dt_cpu_ftrs= [PPC]
1212 Format: {"off" | "kno 1178 Format: {"off" | "known"}
1213 Control how the dt_cp 1179 Control how the dt_cpu_ftrs device-tree binding is
1214 used for CPU feature 1180 used for CPU feature discovery and setup (if it
1215 exists). 1181 exists).
1216 off: Do not use it, f 1182 off: Do not use it, fall back to legacy cpu table.
1217 known: Do not pass th 1183 known: Do not pass through unknown features to guests
1218 or userspace, only th 1184 or userspace, only those that the kernel is aware of.
1219 1185
1220 dump_apple_properties [X86] 1186 dump_apple_properties [X86]
1221 Dump name and content 1187 Dump name and content of EFI device properties on
1222 x86 Macs. Useful for 1188 x86 Macs. Useful for driver authors to determine
1223 what data is availabl 1189 what data is available or for reverse-engineering.
1224 1190
1225 dyndbg[="val"] [KNL,DYNAMIC_ 1191 dyndbg[="val"] [KNL,DYNAMIC_DEBUG]
1226 <module>.dyndbg[="val"] 1192 <module>.dyndbg[="val"]
1227 Enable debug messages 1193 Enable debug messages at boot time. See
1228 Documentation/admin-g 1194 Documentation/admin-guide/dynamic-debug-howto.rst
1229 for details. 1195 for details.
1230 1196
1231 early_ioremap_debug [KNL,EARLY] !! 1197 early_ioremap_debug [KNL]
1232 Enable debug messages 1198 Enable debug messages in early_ioremap support. This
1233 is useful for trackin 1199 is useful for tracking down temporary early mappings
1234 which are not unmappe 1200 which are not unmapped.
1235 1201
1236 earlycon= [KNL,EARLY] Output ea !! 1202 earlycon= [KNL] Output early console device and options.
1237 1203
1238 When used with no opt 1204 When used with no options, the early console is
1239 determined by stdout- 1205 determined by stdout-path property in device tree's
1240 chosen node or the AC 1206 chosen node or the ACPI SPCR table if supported by
1241 the platform. 1207 the platform.
1242 1208
1243 cdns,<addr>[,options] 1209 cdns,<addr>[,options]
1244 Start an early, polle 1210 Start an early, polled-mode console on a Cadence
1245 (xuartps) serial port 1211 (xuartps) serial port at the specified address. Only
1246 supported option is b 1212 supported option is baud rate. If baud rate is not
1247 specified, the serial 1213 specified, the serial port must already be setup and
1248 configured. 1214 configured.
1249 1215
1250 uart[8250],io,<addr>[,options 1216 uart[8250],io,<addr>[,options[,uartclk]]
1251 uart[8250],mmio,<addr>[,optio 1217 uart[8250],mmio,<addr>[,options[,uartclk]]
1252 uart[8250],mmio32,<addr>[,opt 1218 uart[8250],mmio32,<addr>[,options[,uartclk]]
1253 uart[8250],mmio32be,<addr>[,o 1219 uart[8250],mmio32be,<addr>[,options[,uartclk]]
1254 uart[8250],0x<addr>[,options] 1220 uart[8250],0x<addr>[,options]
1255 Start an early, polle 1221 Start an early, polled-mode console on the 8250/16550
1256 UART at the specified 1222 UART at the specified I/O port or MMIO address.
1257 MMIO inter-register a 1223 MMIO inter-register address stride is either 8-bit
1258 (mmio) or 32-bit (mmi 1224 (mmio) or 32-bit (mmio32 or mmio32be).
1259 If none of [io|mmio|m 1225 If none of [io|mmio|mmio32|mmio32be], <addr> is assumed
1260 to be equivalent to ' 1226 to be equivalent to 'mmio'. 'options' are specified
1261 in the same format de 1227 in the same format described for "console=ttyS<n>"; if
1262 unspecified, the h/w 1228 unspecified, the h/w is not initialized. 'uartclk' is
1263 the uart clock freque 1229 the uart clock frequency; if unspecified, it is set
1264 to 'BASE_BAUD' * 16. 1230 to 'BASE_BAUD' * 16.
1265 1231
1266 pl011,<addr> 1232 pl011,<addr>
1267 pl011,mmio32,<addr> 1233 pl011,mmio32,<addr>
1268 Start an early, polle 1234 Start an early, polled-mode console on a pl011 serial
1269 port at the specified 1235 port at the specified address. The pl011 serial port
1270 must already be setup 1236 must already be setup and configured. Options are not
1271 yet supported. If 'm 1237 yet supported. If 'mmio32' is specified, then only
1272 the driver will use o 1238 the driver will use only 32-bit accessors to read/write
1273 the device registers. 1239 the device registers.
1274 1240
1275 liteuart,<addr> 1241 liteuart,<addr>
1276 Start an early consol 1242 Start an early console on a litex serial port at the
1277 specified address. Th 1243 specified address. The serial port must already be
1278 setup and configured. 1244 setup and configured. Options are not yet supported.
1279 1245
1280 meson,<addr> 1246 meson,<addr>
1281 Start an early, polle 1247 Start an early, polled-mode console on a meson serial
1282 port at the specified 1248 port at the specified address. The serial port must
1283 already be setup and 1249 already be setup and configured. Options are not yet
1284 supported. 1250 supported.
1285 1251
1286 msm_serial,<addr> 1252 msm_serial,<addr>
1287 Start an early, polle 1253 Start an early, polled-mode console on an msm serial
1288 port at the specified 1254 port at the specified address. The serial port
1289 must already be setup 1255 must already be setup and configured. Options are not
1290 yet supported. 1256 yet supported.
1291 1257
1292 msm_serial_dm,<addr> 1258 msm_serial_dm,<addr>
1293 Start an early, polle 1259 Start an early, polled-mode console on an msm serial
1294 dm port at the specif 1260 dm port at the specified address. The serial port
1295 must already be setup 1261 must already be setup and configured. Options are not
1296 yet supported. 1262 yet supported.
1297 1263
1298 owl,<addr> 1264 owl,<addr>
1299 Start an early, polle 1265 Start an early, polled-mode console on a serial port
1300 of an Actions Semi So 1266 of an Actions Semi SoC, such as S500 or S900, at the
1301 specified address. Th 1267 specified address. The serial port must already be
1302 setup and configured. 1268 setup and configured. Options are not yet supported.
1303 1269
1304 rda,<addr> 1270 rda,<addr>
1305 Start an early, polle 1271 Start an early, polled-mode console on a serial port
1306 of an RDA Micro SoC, 1272 of an RDA Micro SoC, such as RDA8810PL, at the
1307 specified address. Th 1273 specified address. The serial port must already be
1308 setup and configured. 1274 setup and configured. Options are not yet supported.
1309 1275
1310 sbi 1276 sbi
1311 Use RISC-V SBI (Super 1277 Use RISC-V SBI (Supervisor Binary Interface) for early
1312 console. 1278 console.
1313 1279
1314 smh Use ARM semihosting c 1280 smh Use ARM semihosting calls for early console.
1315 1281
1316 s3c2410,<addr> 1282 s3c2410,<addr>
1317 s3c2412,<addr> 1283 s3c2412,<addr>
1318 s3c2440,<addr> 1284 s3c2440,<addr>
1319 s3c6400,<addr> 1285 s3c6400,<addr>
1320 s5pv210,<addr> 1286 s5pv210,<addr>
1321 exynos4210,<addr> 1287 exynos4210,<addr>
1322 Use early console pro 1288 Use early console provided by serial driver available
1323 on Samsung SoCs, requ 1289 on Samsung SoCs, requires selecting proper type and
1324 a correct base addres 1290 a correct base address of the selected UART port. The
1325 serial port must alre 1291 serial port must already be setup and configured.
1326 Options are not yet s 1292 Options are not yet supported.
1327 1293
1328 lantiq,<addr> 1294 lantiq,<addr>
1329 Start an early, polle 1295 Start an early, polled-mode console on a lantiq serial
1330 (lqasc) port at the s 1296 (lqasc) port at the specified address. The serial port
1331 must already be setup 1297 must already be setup and configured. Options are not
1332 yet supported. 1298 yet supported.
1333 1299
1334 lpuart,<addr> 1300 lpuart,<addr>
1335 lpuart32,<addr> 1301 lpuart32,<addr>
1336 Use early console pro 1302 Use early console provided by Freescale LP UART driver
1337 found on Freescale Vy 1303 found on Freescale Vybrid and QorIQ LS1021A processors.
1338 A valid base address 1304 A valid base address must be provided, and the serial
1339 port must already be 1305 port must already be setup and configured.
1340 1306
1341 ec_imx21,<addr> 1307 ec_imx21,<addr>
1342 ec_imx6q,<addr> 1308 ec_imx6q,<addr>
1343 Start an early, polle 1309 Start an early, polled-mode, output-only console on the
1344 Freescale i.MX UART a 1310 Freescale i.MX UART at the specified address. The UART
1345 must already be setup 1311 must already be setup and configured.
1346 1312
1347 ar3700_uart,<addr> 1313 ar3700_uart,<addr>
1348 Start an early, polle 1314 Start an early, polled-mode console on the
1349 Armada 3700 serial po 1315 Armada 3700 serial port at the specified
1350 address. The serial p 1316 address. The serial port must already be setup
1351 and configured. Optio 1317 and configured. Options are not yet supported.
1352 1318
1353 qcom_geni,<addr> 1319 qcom_geni,<addr>
1354 Start an early, polle 1320 Start an early, polled-mode console on a Qualcomm
1355 Generic Interface (GE 1321 Generic Interface (GENI) based serial port at the
1356 specified address. Th 1322 specified address. The serial port must already be
1357 setup and configured. 1323 setup and configured. Options are not yet supported.
1358 1324
1359 efifb,[options] 1325 efifb,[options]
1360 Start an early, unacc 1326 Start an early, unaccelerated console on the EFI
1361 memory mapped framebu 1327 memory mapped framebuffer (if available). On cache
1362 coherent non-x86 syst 1328 coherent non-x86 systems that use system memory for
1363 the framebuffer, pass 1329 the framebuffer, pass the 'ram' option so that it is
1364 mapped with the corre 1330 mapped with the correct attributes.
1365 1331
1366 linflex,<addr> 1332 linflex,<addr>
1367 Use early console pro 1333 Use early console provided by Freescale LINFlexD UART
1368 serial driver for NXP 1334 serial driver for NXP S32V234 SoCs. A valid base
1369 address must be provi 1335 address must be provided, and the serial port must
1370 already be setup and 1336 already be setup and configured.
1371 1337
1372 earlyprintk= [X86,SH,ARM,M68k,S390 !! 1338 earlyprintk= [X86,SH,ARM,M68k,S390]
1373 earlyprintk=vga 1339 earlyprintk=vga
1374 earlyprintk=sclp 1340 earlyprintk=sclp
1375 earlyprintk=xen 1341 earlyprintk=xen
1376 earlyprintk=serial[,t 1342 earlyprintk=serial[,ttySn[,baudrate]]
1377 earlyprintk=serial[,0 1343 earlyprintk=serial[,0x...[,baudrate]]
1378 earlyprintk=ttySn[,ba 1344 earlyprintk=ttySn[,baudrate]
1379 earlyprintk=dbgp[debu 1345 earlyprintk=dbgp[debugController#]
1380 earlyprintk=pciserial 1346 earlyprintk=pciserial[,force],bus:device.function[,baudrate]
1381 earlyprintk=xdbc[xhci 1347 earlyprintk=xdbc[xhciController#]
1382 earlyprintk=bios <<
1383 1348
1384 earlyprintk is useful 1349 earlyprintk is useful when the kernel crashes before
1385 the normal console is 1350 the normal console is initialized. It is not enabled by
1386 default because it ha 1351 default because it has some cosmetic problems.
1387 1352
1388 Append ",keep" to not 1353 Append ",keep" to not disable it when the real console
1389 takes over. 1354 takes over.
1390 1355
1391 Only one of vga, seri 1356 Only one of vga, serial, or usb debug port can
1392 be used at a time. 1357 be used at a time.
1393 1358
1394 Currently only ttyS0 1359 Currently only ttyS0 and ttyS1 may be specified by
1395 name. Other I/O port 1360 name. Other I/O ports may be explicitly specified
1396 on some architectures 1361 on some architectures (x86 and arm at least) by
1397 replacing ttySn with 1362 replacing ttySn with an I/O port address, like this:
1398 earlyprintk=s 1363 earlyprintk=serial,0x1008,115200
1399 You can find the port 1364 You can find the port for a given device in
1400 /proc/tty/driver/seri 1365 /proc/tty/driver/serial:
1401 2: uart:ST166 1366 2: uart:ST16650V2 port:00001008 irq:18 ...
1402 1367
1403 Interaction with the 1368 Interaction with the standard serial driver is not
1404 very good. 1369 very good.
1405 1370
1406 The VGA output is eve 1371 The VGA output is eventually overwritten by
1407 the real console. 1372 the real console.
1408 1373
1409 The xen option can on 1374 The xen option can only be used in Xen domains.
1410 1375
1411 The sclp output can o 1376 The sclp output can only be used on s390.
1412 1377
1413 The bios output can o <<
1414 <<
1415 The optional "force" 1378 The optional "force" to "pciserial" enables use of a
1416 PCI device even when 1379 PCI device even when its classcode is not of the
1417 UART class. 1380 UART class.
1418 1381
1419 edac_report= [HW,EDAC] Control how 1382 edac_report= [HW,EDAC] Control how to report EDAC event
1420 Format: {"on" | "off" 1383 Format: {"on" | "off" | "force"}
1421 on: enable EDAC to re 1384 on: enable EDAC to report H/W event. May be overridden
1422 by other higher prior 1385 by other higher priority error reporting module.
1423 off: disable H/W even 1386 off: disable H/W event reporting through EDAC.
1424 force: enforce the us 1387 force: enforce the use of EDAC to report H/W event.
1425 default: on. 1388 default: on.
1426 1389
1427 edd= [EDD] 1390 edd= [EDD]
1428 Format: {"off" | "on" 1391 Format: {"off" | "on" | "skip[mbr]"}
1429 1392
1430 efi= [EFI,EARLY] !! 1393 efi= [EFI]
1431 Format: { "debug", "d 1394 Format: { "debug", "disable_early_pci_dma",
1432 "nochunk", 1395 "nochunk", "noruntime", "nosoftreserve",
1433 "novamap", 1396 "novamap", "no_disable_early_pci_dma" }
1434 debug: enable misc de 1397 debug: enable misc debug output.
1435 disable_early_pci_dma 1398 disable_early_pci_dma: disable the busmaster bit on all
1436 PCI bridges while in 1399 PCI bridges while in the EFI boot stub.
1437 nochunk: disable read 1400 nochunk: disable reading files in "chunks" in the EFI
1438 boot stub, as chunkin 1401 boot stub, as chunking can cause problems with some
1439 firmware implementati 1402 firmware implementations.
1440 noruntime : disable E 1403 noruntime : disable EFI runtime services support
1441 nosoftreserve: The EF 1404 nosoftreserve: The EFI_MEMORY_SP (Specific Purpose)
1442 attribute may cause t 1405 attribute may cause the kernel to reserve the
1443 memory range for a me 1406 memory range for a memory mapping driver to
1444 claim. Specify efi=no 1407 claim. Specify efi=nosoftreserve to disable this
1445 reservation and treat 1408 reservation and treat the memory by its base type
1446 (i.e. EFI_CONVENTIONA 1409 (i.e. EFI_CONVENTIONAL_MEMORY / "System RAM").
1447 novamap: do not call 1410 novamap: do not call SetVirtualAddressMap().
1448 no_disable_early_pci_ 1411 no_disable_early_pci_dma: Leave the busmaster bit set
1449 on all PCI bridges wh 1412 on all PCI bridges while in the EFI boot stub
1450 1413
1451 efi_no_storage_paranoia [EFI,X86,EARL !! 1414 efi_no_storage_paranoia [EFI; X86]
1452 Using this parameter 1415 Using this parameter you can use more than 50% of
1453 your efi variable sto 1416 your efi variable storage. Use this parameter only if
1454 you are really sure t 1417 you are really sure that your UEFI does sane gc and
1455 fulfills the spec oth 1418 fulfills the spec otherwise your board may brick.
1456 1419
>> 1420 efi_fake_mem= nn[KMG]@ss[KMG]:aa[,nn[KMG]@ss[KMG]:aa,..] [EFI; X86]
>> 1421 Add arbitrary attribute to specific memory range by
>> 1422 updating original EFI memory map.
>> 1423 Region of memory which aa attribute is added to is
>> 1424 from ss to ss+nn.
>> 1425
>> 1426 If efi_fake_mem=2G@4G:0x10000,2G@0x10a0000000:0x10000
>> 1427 is specified, EFI_MEMORY_MORE_RELIABLE(0x10000)
>> 1428 attribute is added to range 0x100000000-0x180000000 and
>> 1429 0x10a0000000-0x1120000000.
>> 1430
>> 1431 If efi_fake_mem=8G@9G:0x40000 is specified, the
>> 1432 EFI_MEMORY_SP(0x40000) attribute is added to
>> 1433 range 0x240000000-0x43fffffff.
>> 1434
>> 1435 Using this parameter you can do debugging of EFI memmap
>> 1436 related features. For example, you can do debugging of
>> 1437 Address Range Mirroring feature even if your box
>> 1438 doesn't support it, or mark specific memory as
>> 1439 "soft reserved".
>> 1440
1457 efivar_ssdt= [EFI; X86] Name of an 1441 efivar_ssdt= [EFI; X86] Name of an EFI variable that contains an SSDT
1458 that is to be dynamic 1442 that is to be dynamically loaded by Linux. If there are
1459 multiple variables wi 1443 multiple variables with the same name but with different
1460 vendor GUIDs, all of 1444 vendor GUIDs, all of them will be loaded. See
1461 Documentation/admin-g 1445 Documentation/admin-guide/acpi/ssdt-overlays.rst for details.
1462 1446
1463 1447
1464 eisa_irq_edge= [PARISC,HW] 1448 eisa_irq_edge= [PARISC,HW]
1465 See header of drivers 1449 See header of drivers/parisc/eisa.c.
1466 1450
1467 ekgdboc= [X86,KGDB,EARLY] Allo !! 1451 ekgdboc= [X86,KGDB] Allow early kernel console debugging
1468 Format: ekgdboc=kbd 1452 Format: ekgdboc=kbd
1469 1453
1470 This is designed to b 1454 This is designed to be used in conjunction with
1471 the boot argument: ea 1455 the boot argument: earlyprintk=vga
1472 1456
1473 This parameter works 1457 This parameter works in place of the kgdboc parameter
1474 but can only be used 1458 but can only be used if the backing tty is available
1475 very early in the boo 1459 very early in the boot process. For early debugging
1476 via a serial port see 1460 via a serial port see kgdboc_earlycon instead.
1477 1461
1478 elanfreq= [X86-32] 1462 elanfreq= [X86-32]
1479 See comment before fu 1463 See comment before function elanfreq_setup() in
1480 arch/x86/kernel/cpu/c 1464 arch/x86/kernel/cpu/cpufreq/elanfreq.c.
1481 1465
1482 elfcorehdr=[size[KMG]@]offset[KMG] [P !! 1466 elfcorehdr=[size[KMG]@]offset[KMG] [IA64,PPC,SH,X86,S390]
1483 Specifies physical ad 1467 Specifies physical address of start of kernel core
1484 image elf header and 1468 image elf header and optionally the size. Generally
1485 kexec loader will pas 1469 kexec loader will pass this option to capture kernel.
1486 See Documentation/adm 1470 See Documentation/admin-guide/kdump/kdump.rst for details.
1487 1471
1488 enable_mtrr_cleanup [X86,EARLY] !! 1472 enable_mtrr_cleanup [X86]
1489 The kernel tries to a 1473 The kernel tries to adjust MTRR layout from continuous
1490 to discrete, to make 1474 to discrete, to make X server driver able to add WB
1491 entry later. This par 1475 entry later. This parameter enables that.
1492 1476
1493 enable_timer_pin_1 [X86] 1477 enable_timer_pin_1 [X86]
1494 Enable PIN 1 of APIC 1478 Enable PIN 1 of APIC timer
1495 Can be useful to work 1479 Can be useful to work around chipset bugs
1496 (in particular on som 1480 (in particular on some ATI chipsets).
1497 The kernel tries to s 1481 The kernel tries to set a reasonable default.
1498 1482
1499 enforcing= [SELINUX] Set initial 1483 enforcing= [SELINUX] Set initial enforcing status.
1500 Format: {"0" | "1"} 1484 Format: {"0" | "1"}
1501 See security/selinux/ 1485 See security/selinux/Kconfig help text.
1502 0 -- permissive (log 1486 0 -- permissive (log only, no denials).
1503 1 -- enforcing (deny 1487 1 -- enforcing (deny and log).
1504 Default value is 0. 1488 Default value is 0.
1505 Value can be changed 1489 Value can be changed at runtime via
1506 /sys/fs/selinux/enfor 1490 /sys/fs/selinux/enforce.
1507 1491
1508 erst_disable [ACPI] 1492 erst_disable [ACPI]
1509 Disable Error Record 1493 Disable Error Record Serialization Table (ERST)
1510 support. 1494 support.
1511 1495
1512 ether= [HW,NET] Ethernet car 1496 ether= [HW,NET] Ethernet cards parameters
1513 This option is obsole 1497 This option is obsoleted by the "netdev=" option, which
1514 has equivalent usage. 1498 has equivalent usage. See its documentation for details.
1515 1499
1516 evm= [EVM] 1500 evm= [EVM]
1517 Format: { "fix" } 1501 Format: { "fix" }
1518 Permit 'security.evm' 1502 Permit 'security.evm' to be updated regardless of
1519 current integrity sta 1503 current integrity status.
1520 1504
1521 early_page_ext [KNL,EARLY] Enforces p !! 1505 early_page_ext [KNL] Enforces page_ext initialization to earlier
1522 stages so cover more 1506 stages so cover more early boot allocations.
1523 Please note that as s 1507 Please note that as side effect some optimizations
1524 might be disabled to 1508 might be disabled to achieve that (e.g. parallelized
1525 memory initialization 1509 memory initialization is disabled) so the boot process
1526 might take longer, es 1510 might take longer, especially on systems with a lot of
1527 memory. Available wit 1511 memory. Available with CONFIG_PAGE_EXTENSION=y.
1528 1512
1529 failslab= 1513 failslab=
1530 fail_usercopy= 1514 fail_usercopy=
1531 fail_page_alloc= 1515 fail_page_alloc=
1532 fail_make_request=[KNL] 1516 fail_make_request=[KNL]
1533 General fault injecti 1517 General fault injection mechanism.
1534 Format: <interval>,<p 1518 Format: <interval>,<probability>,<space>,<times>
1535 See also Documentatio 1519 See also Documentation/fault-injection/.
1536 1520
1537 fb_tunnels= [NET] 1521 fb_tunnels= [NET]
1538 Format: { initns | no 1522 Format: { initns | none }
1539 See Documentation/adm 1523 See Documentation/admin-guide/sysctl/net.rst for
1540 fb_tunnels_only_for_i 1524 fb_tunnels_only_for_init_ns
1541 1525
1542 floppy= [HW] 1526 floppy= [HW]
1543 See Documentation/adm 1527 See Documentation/admin-guide/blockdev/floppy.rst.
1544 1528
>> 1529 force_pal_cache_flush
>> 1530 [IA-64] Avoid check_sal_cache_flush which may hang on
>> 1531 buggy SAL_CACHE_FLUSH implementations. Using this
>> 1532 parameter will force ia64_sal_cache_flush to call
>> 1533 ia64_pal_cache_flush instead of SAL_CACHE_FLUSH.
>> 1534
1545 forcepae [X86-32] 1535 forcepae [X86-32]
1546 Forcefully enable Phy 1536 Forcefully enable Physical Address Extension (PAE).
1547 Many Pentium M system 1537 Many Pentium M systems disable PAE but may have a
1548 functionally usable P 1538 functionally usable PAE implementation.
1549 Warning: use of this 1539 Warning: use of this parameter will taint the kernel
1550 and may cause unknown 1540 and may cause unknown problems.
1551 1541
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] 1542 ftrace=[tracer]
1559 [FTRACE] will set and 1543 [FTRACE] will set and start the specified tracer
1560 as early as possible 1544 as early as possible in order to facilitate early
1561 boot debugging. 1545 boot debugging.
1562 1546
1563 ftrace_boot_snapshot 1547 ftrace_boot_snapshot
1564 [FTRACE] On boot up, 1548 [FTRACE] On boot up, a snapshot will be taken of the
1565 ftrace ring buffer th 1549 ftrace ring buffer that can be read at:
1566 /sys/kernel/tracing/s 1550 /sys/kernel/tracing/snapshot.
1567 This is useful if you 1551 This is useful if you need tracing information from kernel
1568 boot up that is likel 1552 boot up that is likely to be overridden by user space
1569 start up functionalit 1553 start up functionality.
1570 1554
1571 Optionally, the snaps 1555 Optionally, the snapshot can also be defined for a tracing
1572 instance that was cre 1556 instance that was created by the trace_instance= command
1573 line parameter. 1557 line parameter.
1574 1558
1575 trace_instance=foo,sc 1559 trace_instance=foo,sched_switch ftrace_boot_snapshot=foo
1576 1560
1577 The above will cause 1561 The above will cause the "foo" tracing instance to trigger
1578 a snapshot at the end 1562 a snapshot at the end of boot up.
1579 1563
1580 ftrace_dump_on_oops[=2(orig_cpu) | =< !! 1564 ftrace_dump_on_oops[=orig_cpu]
1581 ,<instance>=2(orig_ <<
1582 [FTRACE] will dump th 1565 [FTRACE] will dump the trace buffers on oops.
1583 If no parameter is pa !! 1566 If no parameter is passed, ftrace will dump
1584 buffers of all CPUs, !! 1567 buffers of all CPUs, but if you pass orig_cpu, it will
1585 will dump only the bu !! 1568 dump only the buffer of the CPU that triggered the
1586 the oops, or the spec !! 1569 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 1570
1603 ftrace_filter=[function-list] 1571 ftrace_filter=[function-list]
1604 [FTRACE] Limit the fu 1572 [FTRACE] Limit the functions traced by the function
1605 tracer at boot up. fu 1573 tracer at boot up. function-list is a comma-separated
1606 list of functions. Th 1574 list of functions. This list can be changed at run
1607 time by the set_ftrac 1575 time by the set_ftrace_filter file in the debugfs
1608 tracing directory. 1576 tracing directory.
1609 1577
1610 ftrace_notrace=[function-list] 1578 ftrace_notrace=[function-list]
1611 [FTRACE] Do not trace 1579 [FTRACE] Do not trace the functions specified in
1612 function-list. This l 1580 function-list. This list can be changed at run time
1613 by the set_ftrace_not 1581 by the set_ftrace_notrace file in the debugfs
1614 tracing directory. 1582 tracing directory.
1615 1583
1616 ftrace_graph_filter=[function-list] 1584 ftrace_graph_filter=[function-list]
1617 [FTRACE] Limit the to 1585 [FTRACE] Limit the top level callers functions traced
1618 by the function graph 1586 by the function graph tracer at boot up.
1619 function-list is a co 1587 function-list is a comma-separated list of functions
1620 that can be changed a 1588 that can be changed at run time by the
1621 set_graph_function fi 1589 set_graph_function file in the debugfs tracing directory.
1622 1590
1623 ftrace_graph_notrace=[function-list] 1591 ftrace_graph_notrace=[function-list]
1624 [FTRACE] Do not trace 1592 [FTRACE] Do not trace from the functions specified in
1625 function-list. This 1593 function-list. This list is a comma-separated list of
1626 functions that can be 1594 functions that can be changed at run time by the
1627 set_graph_notrace fil 1595 set_graph_notrace file in the debugfs tracing directory.
1628 1596
1629 ftrace_graph_max_depth=<uint> 1597 ftrace_graph_max_depth=<uint>
1630 [FTRACE] Used with th 1598 [FTRACE] Used with the function graph tracer. This is
1631 the max depth it will 1599 the max depth it will trace into a function. This value
1632 can be changed at run 1600 can be changed at run time by the max_graph_depth file
1633 in the tracefs tracin 1601 in the tracefs tracing directory. default: 0 (no limit)
1634 1602
1635 fw_devlink= [KNL,EARLY] Create de !! 1603 fw_devlink= [KNL] Create device links between consumer and supplier
1636 devices by scanning t 1604 devices by scanning the firmware to infer the
1637 consumer/supplier rel 1605 consumer/supplier relationships. This feature is
1638 especially useful whe 1606 especially useful when drivers are loaded as modules as
1639 it ensures proper ord 1607 it ensures proper ordering of tasks like device probing
1640 (suppliers first, the 1608 (suppliers first, then consumers), supplier boot state
1641 clean up (only after 1609 clean up (only after all consumers have probed),
1642 suspend/resume & runt 1610 suspend/resume & runtime PM (consumers first, then
1643 suppliers). 1611 suppliers).
1644 Format: { off | permi 1612 Format: { off | permissive | on | rpm }
1645 off -- Don't create 1613 off -- Don't create device links from firmware info.
1646 permissive -- Create 1614 permissive -- Create device links from firmware info
1647 but use it on 1615 but use it only for ordering boot state clean
1648 up (sync_stat 1616 up (sync_state() calls).
1649 on -- Create device 1617 on -- Create device links from firmware info and use it
1650 to enforce pr 1618 to enforce probe and suspend/resume ordering.
1651 rpm -- Like "on", bu 1619 rpm -- Like "on", but also use to order runtime PM.
1652 1620
1653 fw_devlink.strict=<bool> 1621 fw_devlink.strict=<bool>
1654 [KNL,EARLY] Treat all !! 1622 [KNL] Treat all inferred dependencies as mandatory
1655 dependencies. This on 1623 dependencies. This only applies for fw_devlink=on|rpm.
1656 Format: <bool> 1624 Format: <bool>
1657 1625
1658 fw_devlink.sync_state = 1626 fw_devlink.sync_state =
1659 [KNL,EARLY] When all !! 1627 [KNL] When all devices that could probe have finished
1660 probing, this paramet 1628 probing, this parameter controls what to do with
1661 devices that haven't 1629 devices that haven't yet received their sync_state()
1662 calls. 1630 calls.
1663 Format: { strict | ti 1631 Format: { strict | timeout }
1664 strict -- Default. Co 1632 strict -- Default. Continue waiting on consumers to
1665 probe success 1633 probe successfully.
1666 timeout -- Give up wa 1634 timeout -- Give up waiting on consumers and call
1667 sync_state() 1635 sync_state() on any devices that haven't yet
1668 received thei 1636 received their sync_state() calls after
1669 deferred_prob 1637 deferred_probe_timeout has expired or by
1670 late_initcall 1638 late_initcall() if !CONFIG_MODULES.
1671 1639
1672 gamecon.map[2|3]= 1640 gamecon.map[2|3]=
1673 [HW,JOY] Multisystem 1641 [HW,JOY] Multisystem joystick and NES/SNES/PSX pad
1674 support via parallel 1642 support via parallel port (up to 5 devices per port)
1675 Format: <port#>,<pad1 1643 Format: <port#>,<pad1>,<pad2>,<pad3>,<pad4>,<pad5>
1676 See also Documentatio 1644 See also Documentation/input/devices/joystick-parport.rst
1677 1645
1678 gamma= [HW,DRM] 1646 gamma= [HW,DRM]
1679 1647
1680 gart_fix_e820= [X86-64,EARLY] disabl !! 1648 gart_fix_e820= [X86-64] disable the fix e820 for K8 GART
1681 Format: off | on 1649 Format: off | on
1682 default: on 1650 default: on
1683 1651
1684 gather_data_sampling= 1652 gather_data_sampling=
1685 [X86,INTEL,EARLY] Con !! 1653 [X86,INTEL] Control the Gather Data Sampling (GDS)
1686 mitigation. 1654 mitigation.
1687 1655
1688 Gather Data Sampling 1656 Gather Data Sampling is a hardware vulnerability which
1689 allows unprivileged s 1657 allows unprivileged speculative access to data which was
1690 previously stored in 1658 previously stored in vector registers.
1691 1659
1692 This issue is mitigat 1660 This issue is mitigated by default in updated microcode.
1693 The mitigation may ha 1661 The mitigation may have a performance impact but can be
1694 disabled. On systems 1662 disabled. On systems without the microcode mitigation
1695 disabling AVX serves 1663 disabling AVX serves as a mitigation.
1696 1664
1697 force: Disable AVX t 1665 force: Disable AVX to mitigate systems without
1698 microcode mit 1666 microcode mitigation. No effect if the microcode
1699 mitigation is 1667 mitigation is present. Known to cause crashes in
1700 userspace wit 1668 userspace with buggy AVX enumeration.
1701 1669
1702 off: Disable GDS m 1670 off: Disable GDS mitigation.
1703 1671
1704 gcov_persist= [GCOV] When non-zero 1672 gcov_persist= [GCOV] When non-zero (default), profiling data for
1705 kernel modules is sav 1673 kernel modules is saved and remains accessible via
1706 debugfs, even when th 1674 debugfs, even when the module is unloaded/reloaded.
1707 When zero, profiling 1675 When zero, profiling data is discarded and associated
1708 debugfs files are rem 1676 debugfs files are removed at module unload time.
1709 1677
1710 goldfish [X86] Enable the gold 1678 goldfish [X86] Enable the goldfish android emulator platform.
1711 Don't use this when y 1679 Don't use this when you are not running on the
1712 android emulator 1680 android emulator
1713 1681
1714 gpio-mockup.gpio_mockup_ranges 1682 gpio-mockup.gpio_mockup_ranges
1715 [HW] Sets the ranges 1683 [HW] Sets the ranges of gpiochip of for this device.
1716 Format: <start1>,<end 1684 Format: <start1>,<end1>,<start2>,<end2>...
1717 gpio-mockup.gpio_mockup_named_lines 1685 gpio-mockup.gpio_mockup_named_lines
1718 [HW] Let the driver k 1686 [HW] Let the driver know GPIO lines should be named.
1719 1687
1720 gpt [EFI] Forces disk wit 1688 gpt [EFI] Forces disk with valid GPT signature but
1721 invalid Protective MB 1689 invalid Protective MBR to be treated as GPT. If the
1722 primary GPT is corrup 1690 primary GPT is corrupted, it enables the backup/alternate
1723 GPT to be used instea 1691 GPT to be used instead.
1724 1692
1725 grcan.enable0= [HW] Configuration of 1693 grcan.enable0= [HW] Configuration of physical interface 0. Determines
1726 the "Enable 0" bit of 1694 the "Enable 0" bit of the configuration register.
1727 Format: 0 | 1 1695 Format: 0 | 1
1728 Default: 0 1696 Default: 0
1729 grcan.enable1= [HW] Configuration of 1697 grcan.enable1= [HW] Configuration of physical interface 1. Determines
1730 the "Enable 0" bit of 1698 the "Enable 0" bit of the configuration register.
1731 Format: 0 | 1 1699 Format: 0 | 1
1732 Default: 0 1700 Default: 0
1733 grcan.select= [HW] Select which phy 1701 grcan.select= [HW] Select which physical interface to use.
1734 Format: 0 | 1 1702 Format: 0 | 1
1735 Default: 0 1703 Default: 0
1736 grcan.txsize= [HW] Sets the size of 1704 grcan.txsize= [HW] Sets the size of the tx buffer.
1737 Format: <unsigned int 1705 Format: <unsigned int> such that (txsize & ~0x1fffc0) == 0.
1738 Default: 1024 1706 Default: 1024
1739 grcan.rxsize= [HW] Sets the size of 1707 grcan.rxsize= [HW] Sets the size of the rx buffer.
1740 Format: <unsigned int 1708 Format: <unsigned int> such that (rxsize & ~0x1fffc0) == 0.
1741 Default: 1024 1709 Default: 1024
1742 1710
1743 hardened_usercopy= 1711 hardened_usercopy=
1744 [KNL] Under CONFIG_HA 1712 [KNL] Under CONFIG_HARDENED_USERCOPY, whether
1745 hardening is enabled 1713 hardening is enabled for this boot. Hardened
1746 usercopy checking is 1714 usercopy checking is used to protect the kernel
1747 from reading or writi 1715 from reading or writing beyond known memory
1748 allocation boundaries 1716 allocation boundaries as a proactive defense
1749 against bounds-checki 1717 against bounds-checking flaws in the kernel's
1750 copy_to_user()/copy_f 1718 copy_to_user()/copy_from_user() interface.
1751 on Perform hardened user 1719 on Perform hardened usercopy checks (default).
1752 off Disable hardened user 1720 off Disable hardened usercopy checks.
1753 1721
1754 hardlockup_all_cpu_backtrace= 1722 hardlockup_all_cpu_backtrace=
1755 [KNL] Should the hard 1723 [KNL] Should the hard-lockup detector generate
1756 backtraces on all cpu 1724 backtraces on all cpus.
1757 Format: 0 | 1 1725 Format: 0 | 1
1758 1726
1759 hashdist= [KNL,NUMA] Large hash 1727 hashdist= [KNL,NUMA] Large hashes allocated during boot
1760 are distributed acros 1728 are distributed across NUMA nodes. Defaults on
1761 for 64-bit NUMA, off 1729 for 64-bit NUMA, off otherwise.
1762 Format: 0 | 1 (for of 1730 Format: 0 | 1 (for off | on)
1763 1731
>> 1732 hcl= [IA-64] SGI's Hardware Graph compatibility layer
>> 1733
1764 hd= [EIDE] (E)IDE hard dr 1734 hd= [EIDE] (E)IDE hard drive subsystem geometry
1765 Format: <cyl>,<head>, 1735 Format: <cyl>,<head>,<sect>
1766 1736
1767 hest_disable [ACPI] 1737 hest_disable [ACPI]
1768 Disable Hardware Erro 1738 Disable Hardware Error Source Table (HEST) support;
1769 corresponding firmwar 1739 corresponding firmware-first mode error processing
1770 logic will be disable 1740 logic will be disabled.
1771 1741
1772 hibernate= [HIBERNATION] 1742 hibernate= [HIBERNATION]
1773 noresume Don't check i 1743 noresume Don't check if there's a hibernation image
1774 present durin 1744 present during boot.
1775 nocompress Don't compres 1745 nocompress Don't compress/decompress hibernation images.
1776 no Disable hiber 1746 no Disable hibernation and resume.
1777 protect_image Turn on image 1747 protect_image Turn on image protection during restoration
1778 (that will se 1748 (that will set all pages holding image data
1779 during restor 1749 during restoration read-only).
1780 1750
1781 hibernate.compressor= [HIBERNATION] !! 1751 highmem=nn[KMG] [KNL,BOOT] forces the highmem zone to have an exact
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 1752 size of <nn>. This works even on boxes that have no
1794 highmem otherwise. Th 1753 highmem otherwise. This also works to reduce highmem
1795 size on bigger boxes. 1754 size on bigger boxes.
1796 1755
1797 highres= [KNL] Enable/disable 1756 highres= [KNL] Enable/disable high resolution timer mode.
1798 Valid parameters: "on 1757 Valid parameters: "on", "off"
1799 Default: "on" 1758 Default: "on"
1800 1759
1801 hlt [BUGS=ARM,SH] 1760 hlt [BUGS=ARM,SH]
1802 1761
1803 hostname= [KNL,EARLY] Set the h !! 1762 hostname= [KNL] Set the hostname (aka UTS nodename).
1804 Format: <string> 1763 Format: <string>
1805 This allows setting t 1764 This allows setting the system's hostname during early
1806 startup. This sets th 1765 startup. This sets the name returned by gethostname.
1807 Using this parameter 1766 Using this parameter to set the hostname makes it
1808 possible to ensure th 1767 possible to ensure the hostname is correctly set before
1809 any userspace process 1768 any userspace processes run, avoiding the possibility
1810 that a process may ca 1769 that a process may call gethostname before the hostname
1811 has been explicitly s 1770 has been explicitly set, resulting in the calling
1812 process getting an in 1771 process getting an incorrect result. The string must
1813 not exceed the maximu 1772 not exceed the maximum allowed hostname length (usually
1814 64 characters) and wi 1773 64 characters) and will be truncated otherwise.
1815 1774
1816 hpet= [X86-32,HPET] option 1775 hpet= [X86-32,HPET] option to control HPET usage
1817 Format: { enable (def 1776 Format: { enable (default) | disable | force |
1818 verbose } 1777 verbose }
1819 disable: disable HPET 1778 disable: disable HPET and use PIT instead
1820 force: allow force en 1779 force: allow force enabled of undocumented chips (ICH4,
1821 VIA, nVidia) 1780 VIA, nVidia)
1822 verbose: show content 1781 verbose: show contents of HPET registers during setup
1823 1782
1824 hpet_mmap= [X86, HPET_MMAP] Allo 1783 hpet_mmap= [X86, HPET_MMAP] Allow userspace to mmap HPET
1825 registers. Default s 1784 registers. Default set by CONFIG_HPET_MMAP_DEFAULT.
1826 1785
1827 hugepages= [HW] Number of HugeTL 1786 hugepages= [HW] Number of HugeTLB pages to allocate at boot.
1828 If this follows hugep 1787 If this follows hugepagesz (below), it specifies
1829 the number of pages o 1788 the number of pages of hugepagesz to be allocated.
1830 If this is the first 1789 If this is the first HugeTLB parameter on the command
1831 line, it specifies th 1790 line, it specifies the number of pages to allocate for
1832 the default huge page 1791 the default huge page size. If using node format, the
1833 number of pages to al 1792 number of pages to allocate per-node can be specified.
1834 See also Documentatio 1793 See also Documentation/admin-guide/mm/hugetlbpage.rst.
1835 Format: <integer> or 1794 Format: <integer> or (node format)
1836 <node>:<integ 1795 <node>:<integer>[,<node>:<integer>]
1837 1796
1838 hugepagesz= 1797 hugepagesz=
1839 [HW] The size of the 1798 [HW] The size of the HugeTLB pages. This is used in
1840 conjunction with huge 1799 conjunction with hugepages (above) to allocate huge
1841 pages of a specific s 1800 pages of a specific size at boot. The pair
1842 hugepagesz=X hugepage 1801 hugepagesz=X hugepages=Y can be specified once for
1843 each supported huge p 1802 each supported huge page size. Huge page sizes are
1844 architecture dependen 1803 architecture dependent. See also
1845 Documentation/admin-g 1804 Documentation/admin-guide/mm/hugetlbpage.rst.
1846 Format: size[KMG] 1805 Format: size[KMG]
1847 1806
1848 hugetlb_cma= [HW,CMA,EARLY] The si !! 1807 hugetlb_cma= [HW,CMA] The size of a CMA area used for allocation
1849 of gigantic hugepages 1808 of gigantic hugepages. Or using node format, the size
1850 of a CMA area per nod 1809 of a CMA area per node can be specified.
1851 Format: nn[KMGTPE] or 1810 Format: nn[KMGTPE] or (node format)
1852 <node>:nn[KMG 1811 <node>:nn[KMGTPE][,<node>:nn[KMGTPE]]
1853 1812
1854 Reserve a CMA area of 1813 Reserve a CMA area of given size and allocate gigantic
1855 hugepages using the C 1814 hugepages using the CMA allocator. If enabled, the
1856 boot-time allocation 1815 boot-time allocation of gigantic hugepages is skipped.
1857 1816
1858 hugetlb_free_vmemmap= 1817 hugetlb_free_vmemmap=
1859 [KNL] Requires CONFIG 1818 [KNL] Requires CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP
1860 enabled. 1819 enabled.
1861 Control if HugeTLB Vm 1820 Control if HugeTLB Vmemmap Optimization (HVO) is enabled.
1862 Allows heavy hugetlb 1821 Allows heavy hugetlb users to free up some more
1863 memory (7 * PAGE_SIZE 1822 memory (7 * PAGE_SIZE for each 2MB hugetlb page).
1864 Format: { on | off (d 1823 Format: { on | off (default) }
1865 1824
1866 on: enable HVO 1825 on: enable HVO
1867 off: disable HVO 1826 off: disable HVO
1868 1827
1869 Built with CONFIG_HUG 1828 Built with CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP_DEFAULT_ON=y,
1870 the default is on. 1829 the default is on.
1871 1830
1872 Note that the vmemmap 1831 Note that the vmemmap pages may be allocated from the added
1873 memory block itself w 1832 memory block itself when memory_hotplug.memmap_on_memory is
1874 enabled, those vmemma 1833 enabled, those vmemmap pages cannot be optimized even if this
1875 feature is enabled. 1834 feature is enabled. Other vmemmap pages not allocated from
1876 the added memory bloc 1835 the added memory block itself do not be affected.
1877 1836
1878 hung_task_panic= 1837 hung_task_panic=
1879 [KNL] Should the hung 1838 [KNL] Should the hung task detector generate panics.
1880 Format: 0 | 1 1839 Format: 0 | 1
1881 1840
1882 A value of 1 instruct 1841 A value of 1 instructs the kernel to panic when a
1883 hung task is detected 1842 hung task is detected. The default value is controlled
1884 by the CONFIG_BOOTPAR 1843 by the CONFIG_BOOTPARAM_HUNG_TASK_PANIC build-time
1885 option. The value sel 1844 option. The value selected by this boot parameter can
1886 be changed later by t 1845 be changed later by the kernel.hung_task_panic sysctl.
1887 1846
1888 hvc_iucv= [S390] Number of z/V 1847 hvc_iucv= [S390] Number of z/VM IUCV hypervisor console (HVC)
1889 terminal devi 1848 terminal devices. Valid values: 0..8
1890 hvc_iucv_allow= [S390] Comma-separat 1849 hvc_iucv_allow= [S390] Comma-separated list of z/VM user IDs.
1891 If specified, 1850 If specified, z/VM IUCV HVC accepts connections
1892 from listed z 1851 from listed z/VM user IDs only.
1893 1852
1894 hv_nopvspin [X86,HYPER_V,EARLY] !! 1853 hv_nopvspin [X86,HYPER_V] Disables the paravirt spinlock optimizations
1895 Disables the paravirt !! 1854 which allow the hypervisor to 'idle' the
1896 which allow the hyper !! 1855 guest on lock contention.
1897 on lock contention. <<
1898 1856
1899 i2c_bus= [HW] Override the 1857 i2c_bus= [HW] Override the default board specific I2C bus speed
1900 or register a 1858 or register an additional I2C bus that is not
1901 registered fr 1859 registered from board initialization code.
1902 Format: 1860 Format:
1903 <bus_id>,<clk 1861 <bus_id>,<clkrate>
1904 1862
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 1863 i8042.debug [HW] Toggle i8042 debug mode
1928 i8042.unmask_kbd_data 1864 i8042.unmask_kbd_data
1929 [HW] Enable printing 1865 [HW] Enable printing of interrupt data from the KBD port
1930 (disabled by def 1866 (disabled by default, and as a pre-condition
1931 requires that i8 1867 requires that i8042.debug=1 be enabled)
1932 i8042.direct [HW] Put keyboard por 1868 i8042.direct [HW] Put keyboard port into non-translated mode
1933 i8042.dumbkbd [HW] Pretend that con 1869 i8042.dumbkbd [HW] Pretend that controller can only read data from
1934 keyboard and can 1870 keyboard and cannot control its state
1935 (Don't attempt t 1871 (Don't attempt to blink the leds)
1936 i8042.noaux [HW] Don't check for 1872 i8042.noaux [HW] Don't check for auxiliary (== mouse) port
1937 i8042.nokbd [HW] Don't check/crea 1873 i8042.nokbd [HW] Don't check/create keyboard port
1938 i8042.noloop [HW] Disable the AUX 1874 i8042.noloop [HW] Disable the AUX Loopback command while probing
1939 for the AUX port 1875 for the AUX port
1940 i8042.nomux [HW] Don't check pres 1876 i8042.nomux [HW] Don't check presence of an active multiplexing
1941 controller 1877 controller
1942 i8042.nopnp [HW] Don't use ACPIPn 1878 i8042.nopnp [HW] Don't use ACPIPnP / PnPBIOS to discover KBD/AUX
1943 controllers 1879 controllers
1944 i8042.notimeout [HW] Ignore timeout c 1880 i8042.notimeout [HW] Ignore timeout condition signalled by controller
1945 i8042.reset [HW] Reset the contro 1881 i8042.reset [HW] Reset the controller during init, cleanup and
1946 suspend-to-ram t 1882 suspend-to-ram transitions, only during s2r
1947 transitions, or 1883 transitions, or never reset
1948 Format: { 1 | Y | y | 1884 Format: { 1 | Y | y | 0 | N | n }
1949 1, Y, y: always reset 1885 1, Y, y: always reset controller
1950 0, N, n: don't ever r 1886 0, N, n: don't ever reset controller
1951 Default: only on s2r 1887 Default: only on s2r transitions on x86; most other
1952 architectures force r 1888 architectures force reset to be always executed
1953 i8042.unlock [HW] Unlock (ignore) 1889 i8042.unlock [HW] Unlock (ignore) the keylock
1954 i8042.kbdreset [HW] Reset device con 1890 i8042.kbdreset [HW] Reset device connected to KBD port
1955 i8042.probe_defer 1891 i8042.probe_defer
1956 [HW] Allow deferred p 1892 [HW] Allow deferred probing upon i8042 probe errors
1957 1893
1958 i810= [HW,DRM] 1894 i810= [HW,DRM]
1959 1895
1960 i915.invert_brightness= 1896 i915.invert_brightness=
1961 [DRM] Invert the sens 1897 [DRM] Invert the sense of the variable that is used to
1962 set the brightness of 1898 set the brightness of the panel backlight. Normally a
1963 brightness value of 0 1899 brightness value of 0 indicates backlight switched off,
1964 and the maximum of th 1900 and the maximum of the brightness value sets the backlight
1965 to maximum brightness 1901 to maximum brightness. If this parameter is set to 0
1966 (default) and the mac 1902 (default) and the machine requires it, or this parameter
1967 is set to 1, a bright 1903 is set to 1, a brightness value of 0 sets the backlight
1968 to maximum brightness 1904 to maximum brightness, and the maximum of the brightness
1969 value switches the ba 1905 value switches the backlight off.
1970 -1 -- never invert br 1906 -1 -- never invert brightness
1971 0 -- machine default 1907 0 -- machine default
1972 1 -- force brightnes 1908 1 -- force brightness inversion
1973 1909
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] 1910 icn= [HW,ISDN]
1981 Format: <io>[,<membas 1911 Format: <io>[,<membase>[,<icn_id>[,<icn_id2>]]]
1982 1912
1983 1913
1984 idle= [X86,EARLY] !! 1914 idle= [X86]
1985 Format: idle=poll, id 1915 Format: idle=poll, idle=halt, idle=nomwait
1986 Poll forces a polling 1916 Poll forces a polling idle loop that can slightly
1987 improve the performan 1917 improve the performance of waking up a idle CPU, but
1988 will use a lot of pow 1918 will use a lot of power and make the system run hot.
1989 Not recommended. 1919 Not recommended.
1990 idle=halt: Halt is fo 1920 idle=halt: Halt is forced to be used for CPU idle.
1991 In such case C2/C3 wo 1921 In such case C2/C3 won't be used again.
1992 idle=nomwait: Disable 1922 idle=nomwait: Disable mwait for CPU C-states
1993 1923
1994 idxd.sva= [HW] 1924 idxd.sva= [HW]
1995 Format: <bool> 1925 Format: <bool>
1996 Allow force disabling 1926 Allow force disabling of Shared Virtual Memory (SVA)
1997 support for the idxd 1927 support for the idxd driver. By default it is set to
1998 true (1). 1928 true (1).
1999 1929
2000 idxd.tc_override= [HW] 1930 idxd.tc_override= [HW]
2001 Format: <bool> 1931 Format: <bool>
2002 Allow override of def 1932 Allow override of default traffic class configuration
2003 for the device. By de 1933 for the device. By default it is set to false (0).
2004 1934
2005 ieee754= [MIPS] Select IEEE St 1935 ieee754= [MIPS] Select IEEE Std 754 conformance mode
2006 Format: { strict | le !! 1936 Format: { strict | legacy | 2008 | relaxed }
2007 Default: strict 1937 Default: strict
2008 1938
2009 Choose which programs 1939 Choose which programs will be accepted for execution
2010 based on the IEEE 754 1940 based on the IEEE 754 NaN encoding(s) supported by
2011 the FPU and the NaN e 1941 the FPU and the NaN encoding requested with the value
2012 of an ELF file header 1942 of an ELF file header flag individually set by each
2013 binary. Hardware imp 1943 binary. Hardware implementations are permitted to
2014 support either or bot 1944 support either or both of the legacy and the 2008 NaN
2015 encoding mode. 1945 encoding mode.
2016 1946
2017 Available settings ar 1947 Available settings are as follows:
2018 strict accept binari 1948 strict accept binaries that request a NaN encoding
2019 supported by 1949 supported by the FPU
2020 legacy only accept l 1950 legacy only accept legacy-NaN binaries, if supported
2021 by the FPU 1951 by the FPU
2022 2008 only accept 2 1952 2008 only accept 2008-NaN binaries, if supported
2023 by the FPU 1953 by the FPU
2024 relaxed accept any bi 1954 relaxed accept any binaries regardless of whether
2025 supported by 1955 supported by the FPU
2026 emulated accept any b <<
2027 if binary mod <<
2028 1956
2029 The FPU emulator is a 1957 The FPU emulator is always able to support both NaN
2030 encodings, so if no F 1958 encodings, so if no FPU hardware is present or it has
2031 been disabled with 'n 1959 been disabled with 'nofpu', then the settings of
2032 'legacy' and '2008' s 1960 'legacy' and '2008' strap the emulator accordingly,
2033 'relaxed' straps the 1961 'relaxed' straps the emulator for both legacy-NaN and
2034 2008-NaN, whereas 'st 1962 2008-NaN, whereas 'strict' enables legacy-NaN only on
2035 legacy processors and 1963 legacy processors and both NaN encodings on MIPS32 or
2036 MIPS64 CPUs. 1964 MIPS64 CPUs.
2037 1965
2038 The setting for ABS.f 1966 The setting for ABS.fmt/NEG.fmt instruction execution
2039 mode generally follow 1967 mode generally follows that for the NaN encoding,
2040 except where unsuppor 1968 except where unsupported by hardware.
2041 1969
2042 ignore_loglevel [KNL,EARLY] !! 1970 ignore_loglevel [KNL]
2043 Ignore loglevel setti 1971 Ignore loglevel setting - this will print /all/
2044 kernel messages to th 1972 kernel messages to the console. Useful for debugging.
2045 We also add it as pri 1973 We also add it as printk module parameter, so users
2046 could change it dynam 1974 could change it dynamically, usually by
2047 /sys/module/printk/pa 1975 /sys/module/printk/parameters/ignore_loglevel.
2048 1976
2049 ignore_rlimit_data 1977 ignore_rlimit_data
2050 Ignore RLIMIT_DATA se 1978 Ignore RLIMIT_DATA setting for data mappings,
2051 print warning at firs 1979 print warning at first misuse. Can be changed via
2052 /sys/module/kernel/pa 1980 /sys/module/kernel/parameters/ignore_rlimit_data.
2053 1981
2054 ihash_entries= [KNL] 1982 ihash_entries= [KNL]
2055 Set number of hash bu 1983 Set number of hash buckets for inode cache.
2056 1984
2057 ima_appraise= [IMA] appraise integr 1985 ima_appraise= [IMA] appraise integrity measurements
2058 Format: { "off" | "en 1986 Format: { "off" | "enforce" | "fix" | "log" }
2059 default: "enforce" 1987 default: "enforce"
2060 1988
2061 ima_appraise_tcb [IMA] Deprecated. U 1989 ima_appraise_tcb [IMA] Deprecated. Use ima_policy= instead.
2062 The builtin appraise 1990 The builtin appraise policy appraises all files
2063 owned by uid=0. 1991 owned by uid=0.
2064 1992
2065 ima_canonical_fmt [IMA] 1993 ima_canonical_fmt [IMA]
2066 Use the canonical for 1994 Use the canonical format for the binary runtime
2067 measurements, instead 1995 measurements, instead of host native format.
2068 1996
2069 ima_hash= [IMA] 1997 ima_hash= [IMA]
2070 Format: { md5 | sha1 1998 Format: { md5 | sha1 | rmd160 | sha256 | sha384
2071 | sha512 | 1999 | sha512 | ... }
2072 default: "sha1" 2000 default: "sha1"
2073 2001
2074 The list of supported 2002 The list of supported hash algorithms is defined
2075 in crypto/hash_info.h 2003 in crypto/hash_info.h.
2076 2004
2077 ima_policy= [IMA] 2005 ima_policy= [IMA]
2078 The builtin policies 2006 The builtin policies to load during IMA setup.
2079 Format: "tcb | apprai 2007 Format: "tcb | appraise_tcb | secure_boot |
2080 fail_securel 2008 fail_securely | critical_data"
2081 2009
2082 The "tcb" policy meas 2010 The "tcb" policy measures all programs exec'd, files
2083 mmap'd for exec, and 2011 mmap'd for exec, and all files opened with the read
2084 mode bit set by eithe 2012 mode bit set by either the effective uid (euid=0) or
2085 uid=0. 2013 uid=0.
2086 2014
2087 The "appraise_tcb" po 2015 The "appraise_tcb" policy appraises the integrity of
2088 all files owned by ro 2016 all files owned by root.
2089 2017
2090 The "secure_boot" pol 2018 The "secure_boot" policy appraises the integrity
2091 of files (eg. kexec k 2019 of files (eg. kexec kernel image, kernel modules,
2092 firmware, policy, etc 2020 firmware, policy, etc) based on file signatures.
2093 2021
2094 The "fail_securely" p 2022 The "fail_securely" policy forces file signature
2095 verification failure 2023 verification failure also on privileged mounted
2096 filesystems with the 2024 filesystems with the SB_I_UNVERIFIABLE_SIGNATURE
2097 flag. 2025 flag.
2098 2026
2099 The "critical_data" p 2027 The "critical_data" policy measures kernel integrity
2100 critical data. 2028 critical data.
2101 2029
2102 ima_tcb [IMA] Deprecated. Us 2030 ima_tcb [IMA] Deprecated. Use ima_policy= instead.
2103 Load a policy which m 2031 Load a policy which meets the needs of the Trusted
2104 Computing Base. This 2032 Computing Base. This means IMA will measure all
2105 programs exec'd, file 2033 programs exec'd, files mmap'd for exec, and all files
2106 opened for read by ui 2034 opened for read by uid=0.
2107 2035
2108 ima_template= [IMA] 2036 ima_template= [IMA]
2109 Select one of defined 2037 Select one of defined IMA measurements template formats.
2110 Formats: { "ima" | "i 2038 Formats: { "ima" | "ima-ng" | "ima-ngv2" | "ima-sig" |
2111 "ima-sigv2 2039 "ima-sigv2" }
2112 Default: "ima-ng" 2040 Default: "ima-ng"
2113 2041
2114 ima_template_fmt= 2042 ima_template_fmt=
2115 [IMA] Define a custom 2043 [IMA] Define a custom template format.
2116 Format: { "field1|... 2044 Format: { "field1|...|fieldN" }
2117 2045
2118 ima.ahash_minsize= [IMA] Minimum file 2046 ima.ahash_minsize= [IMA] Minimum file size for asynchronous hash usage
2119 Format: <min_file_siz 2047 Format: <min_file_size>
2120 Set the minimal file 2048 Set the minimal file size for using asynchronous hash.
2121 If left unspecified, 2049 If left unspecified, ahash usage is disabled.
2122 2050
2123 ahash performance var 2051 ahash performance varies for different data sizes on
2124 different crypto acce 2052 different crypto accelerators. This option can be used
2125 to achieve the best p 2053 to achieve the best performance for a particular HW.
2126 2054
2127 ima.ahash_bufsize= [IMA] Asynchronous 2055 ima.ahash_bufsize= [IMA] Asynchronous hash buffer size
2128 Format: <bufsize> 2056 Format: <bufsize>
2129 Set hashing buffer si 2057 Set hashing buffer size. Default: 4k.
2130 2058
2131 ahash performance var 2059 ahash performance varies for different chunk sizes on
2132 different crypto acce 2060 different crypto accelerators. This option can be used
2133 to achieve best perfo 2061 to achieve best performance for particular HW.
2134 2062
2135 init= [KNL] 2063 init= [KNL]
2136 Format: <full_path> 2064 Format: <full_path>
2137 Run specified binary 2065 Run specified binary instead of /sbin/init as init
2138 process. 2066 process.
2139 2067
2140 initcall_debug [KNL] Trace initcalls 2068 initcall_debug [KNL] Trace initcalls as they are executed. Useful
2141 for working out where 2069 for working out where the kernel is dying during
2142 startup. 2070 startup.
2143 2071
2144 initcall_blacklist= [KNL] Do not exe 2072 initcall_blacklist= [KNL] Do not execute a comma-separated list of
2145 initcall functions. 2073 initcall functions. Useful for debugging built-in
2146 modules and initcalls 2074 modules and initcalls.
2147 2075
2148 initramfs_async= [KNL] 2076 initramfs_async= [KNL]
2149 Format: <bool> 2077 Format: <bool>
2150 Default: 1 2078 Default: 1
2151 This parameter contro 2079 This parameter controls whether the initramfs
2152 image is unpacked asy 2080 image is unpacked asynchronously, concurrently
2153 with devices being pr 2081 with devices being probed and
2154 initialized. This sho 2082 initialized. This should normally just work,
2155 but as a debugging ai 2083 but as a debugging aid, one can get the
2156 historical behaviour 2084 historical behaviour of the initramfs
2157 unpacking being compl 2085 unpacking being completed before device_ and
2158 late_ initcalls. 2086 late_ initcalls.
2159 2087
2160 initrd= [BOOT,EARLY] Specify !! 2088 initrd= [BOOT] Specify the location of the initial ramdisk
2161 2089
2162 initrdmem= [KNL,EARLY] Specify a !! 2090 initrdmem= [KNL] Specify a physical address and size from which to
2163 load the initrd. If a 2091 load the initrd. If an initrd is compiled in or
2164 specified in the boot 2092 specified in the bootparams, it takes priority over this
2165 setting. 2093 setting.
2166 Format: ss[KMG],nn[KM 2094 Format: ss[KMG],nn[KMG]
2167 Default is 0, 0 2095 Default is 0, 0
2168 2096
2169 init_on_alloc= [MM,EARLY] Fill newly !! 2097 init_on_alloc= [MM] Fill newly allocated pages and heap objects with
2170 zeroes. 2098 zeroes.
2171 Format: 0 | 1 2099 Format: 0 | 1
2172 Default set by CONFIG 2100 Default set by CONFIG_INIT_ON_ALLOC_DEFAULT_ON.
2173 2101
2174 init_on_free= [MM,EARLY] Fill freed !! 2102 init_on_free= [MM] Fill freed pages and heap objects with zeroes.
2175 Format: 0 | 1 2103 Format: 0 | 1
2176 Default set by CONFIG 2104 Default set by CONFIG_INIT_ON_FREE_DEFAULT_ON.
2177 2105
2178 init_pkru= [X86] Specify the def 2106 init_pkru= [X86] Specify the default memory protection keys rights
2179 register contents for 2107 register contents for all processes. 0x55555554 by
2180 default (disallow acc 2108 default (disallow access to all but pkey 0). Can
2181 override in debugfs a 2109 override in debugfs after boot.
2182 2110
2183 inport.irq= [HW] Inport (ATI XL a 2111 inport.irq= [HW] Inport (ATI XL and Microsoft) busmouse driver
2184 Format: <irq> 2112 Format: <irq>
2185 2113
2186 int_pln_enable [X86] Enable power li 2114 int_pln_enable [X86] Enable power limit notification interrupt
2187 2115
2188 integrity_audit=[IMA] 2116 integrity_audit=[IMA]
2189 Format: { "0" | "1" } 2117 Format: { "0" | "1" }
2190 0 -- basic integrity 2118 0 -- basic integrity auditing messages. (Default)
2191 1 -- additional integ 2119 1 -- additional integrity auditing messages.
2192 2120
2193 intel_iommu= [DMAR] Intel IOMMU dr 2121 intel_iommu= [DMAR] Intel IOMMU driver (DMAR) option
2194 on 2122 on
2195 Enable intel iommu dr 2123 Enable intel iommu driver.
2196 off 2124 off
2197 Disable intel iommu d 2125 Disable intel iommu driver.
2198 igfx_off [Default Off] 2126 igfx_off [Default Off]
2199 By default, gfx is ma 2127 By default, gfx is mapped as normal device. If a gfx
2200 device has a dedicate 2128 device has a dedicated DMAR unit, the DMAR unit is
2201 bypassed by not enabl 2129 bypassed by not enabling DMAR with this option. In
2202 this case, gfx device 2130 this case, gfx device will use physical address for
2203 DMA. 2131 DMA.
2204 strict [Default Off] 2132 strict [Default Off]
2205 Deprecated, equivalen 2133 Deprecated, equivalent to iommu.strict=1.
2206 sp_off [Default Off] 2134 sp_off [Default Off]
2207 By default, super pag 2135 By default, super page will be supported if Intel IOMMU
2208 has the capability. W 2136 has the capability. With this option, super page will
2209 not be supported. 2137 not be supported.
2210 sm_on 2138 sm_on
2211 Enable the Intel IOMM 2139 Enable the Intel IOMMU scalable mode if the hardware
2212 advertises that it ha 2140 advertises that it has support for the scalable mode
2213 translation. 2141 translation.
2214 sm_off 2142 sm_off
2215 Disallow use of the I 2143 Disallow use of the Intel IOMMU scalable mode.
2216 tboot_noforce [Default Off] 2144 tboot_noforce [Default Off]
2217 Do not force the Inte 2145 Do not force the Intel IOMMU enabled under tboot.
2218 By default, tboot wil 2146 By default, tboot will force Intel IOMMU on, which
2219 could harm performanc 2147 could harm performance of some high-throughput
2220 devices like 40GBit n 2148 devices like 40GBit network cards, even if identity
2221 mapping is enabled. 2149 mapping is enabled.
2222 Note that using this 2150 Note that using this option lowers the security
2223 provided by tboot bec 2151 provided by tboot because it makes the system
2224 vulnerable to DMA att 2152 vulnerable to DMA attacks.
2225 2153
2226 intel_idle.max_cstate= [KNL,HW,ACPI, 2154 intel_idle.max_cstate= [KNL,HW,ACPI,X86]
2227 0 disables inte 2155 0 disables intel_idle and fall back on acpi_idle.
2228 1 to 9 specify maxim 2156 1 to 9 specify maximum depth of C-state.
2229 2157
2230 intel_pstate= [X86,EARLY] !! 2158 intel_pstate= [X86]
2231 disable 2159 disable
2232 Do not enable intel 2160 Do not enable intel_pstate as the default
2233 scaling driver for 2161 scaling driver for the supported processors
2234 active 2162 active
2235 Use intel_pstate dr 2163 Use intel_pstate driver to bypass the scaling
2236 governors layer of 2164 governors layer of cpufreq and provides it own
2237 algorithms for p-st 2165 algorithms for p-state selection. There are two
2238 P-state selection a 2166 P-state selection algorithms provided by
2239 intel_pstate in the 2167 intel_pstate in the active mode: powersave and
2240 performance. The w 2168 performance. The way they both operate depends
2241 on whether or not t 2169 on whether or not the hardware managed P-states
2242 (HWP) feature has b 2170 (HWP) feature has been enabled in the processor
2243 and possibly on the 2171 and possibly on the processor model.
2244 passive 2172 passive
2245 Use intel_pstate as 2173 Use intel_pstate as a scaling driver, but configure it
2246 to work with generi 2174 to work with generic cpufreq governors (instead of
2247 enabling its intern 2175 enabling its internal governor). This mode cannot be
2248 used along with the 2176 used along with the hardware-managed P-states (HWP)
2249 feature. 2177 feature.
2250 force 2178 force
2251 Enable intel_pstate 2179 Enable intel_pstate on systems that prohibit it by default
2252 in favor of acpi-cp 2180 in favor of acpi-cpufreq. Forcing the intel_pstate driver
2253 instead of acpi-cpu 2181 instead of acpi-cpufreq may disable platform features, such
2254 as thermal controls 2182 as thermal controls and power capping, that rely on ACPI
2255 P-States informatio 2183 P-States information being indicated to OSPM and therefore
2256 should be used with 2184 should be used with caution. This option does not work with
2257 processors that are 2185 processors that aren't supported by the intel_pstate driver
2258 or on platforms tha 2186 or on platforms that use pcc-cpufreq instead of acpi-cpufreq.
2259 no_hwp 2187 no_hwp
2260 Do not enable hardw 2188 Do not enable hardware P state control (HWP)
2261 if available. 2189 if available.
2262 hwp_only 2190 hwp_only
2263 Only load intel_pst 2191 Only load intel_pstate on systems which support
2264 hardware P state co 2192 hardware P state control (HWP) if available.
2265 support_acpi_ppc 2193 support_acpi_ppc
2266 Enforce ACPI _PPC p 2194 Enforce ACPI _PPC performance limits. If the Fixed ACPI
2267 Description Table, 2195 Description Table, specifies preferred power management
2268 profile as "Enterpr 2196 profile as "Enterprise Server" or "Performance Server",
2269 then this feature i 2197 then this feature is turned on by default.
2270 per_cpu_perf_limits 2198 per_cpu_perf_limits
2271 Allow per-logical-C 2199 Allow per-logical-CPU P-State performance control limits using
2272 cpufreq sysfs inter 2200 cpufreq sysfs interface
2273 2201
2274 intremap= [X86-64,Intel-IOMMU,E !! 2202 intremap= [X86-64, Intel-IOMMU]
2275 on enable Interr 2203 on enable Interrupt Remapping (default)
2276 off disable Inter 2204 off disable Interrupt Remapping
2277 nosid disable Sourc 2205 nosid disable Source ID checking
2278 no_x2apic_optout 2206 no_x2apic_optout
2279 BIOS x2APIC o 2207 BIOS x2APIC opt-out request will be ignored
2280 nopost disable Inter 2208 nopost disable Interrupt Posting
2281 posted_msi <<
2282 enable MSIs d <<
2283 2209
2284 iomem= Disable strict checki 2210 iomem= Disable strict checking of access to MMIO memory
2285 strict regions from userspac 2211 strict regions from userspace.
2286 relaxed 2212 relaxed
2287 2213
2288 iommu= [X86,EARLY] !! 2214 iommu= [X86]
2289 off 2215 off
2290 force 2216 force
2291 noforce 2217 noforce
2292 biomerge 2218 biomerge
2293 panic 2219 panic
2294 nopanic 2220 nopanic
2295 merge 2221 merge
2296 nomerge 2222 nomerge
2297 soft 2223 soft
2298 pt [X86] 2224 pt [X86]
2299 nopt [X86] 2225 nopt [X86]
2300 nobypass [PPC/POWERNV] 2226 nobypass [PPC/POWERNV]
2301 Disable IOMMU bypass, 2227 Disable IOMMU bypass, using IOMMU for PCI devices.
2302 2228
2303 iommu.forcedac= [ARM64,X86,EARLY] Con !! 2229 iommu.forcedac= [ARM64, X86] Control IOVA allocation for PCI devices.
2304 Format: { "0" | "1" } 2230 Format: { "0" | "1" }
2305 0 - Try to allocate a 2231 0 - Try to allocate a 32-bit DMA address first, before
2306 falling back to the 2232 falling back to the full range if needed.
2307 1 - Allocate directly 2233 1 - Allocate directly from the full usable range,
2308 forcing Dual Addres 2234 forcing Dual Address Cycle for PCI cards supporting
2309 greater than 32-bit 2235 greater than 32-bit addressing.
2310 2236
2311 iommu.strict= [ARM64,X86,S390,EARLY !! 2237 iommu.strict= [ARM64, X86] Configure TLB invalidation behaviour
2312 Format: { "0" | "1" } 2238 Format: { "0" | "1" }
2313 0 - Lazy mode. 2239 0 - Lazy mode.
2314 Request that DMA un 2240 Request that DMA unmap operations use deferred
2315 invalidation of har 2241 invalidation of hardware TLBs, for increased
2316 throughput at the c 2242 throughput at the cost of reduced device isolation.
2317 Will fall back to s 2243 Will fall back to strict mode if not supported by
2318 the relevant IOMMU 2244 the relevant IOMMU driver.
2319 1 - Strict mode. 2245 1 - Strict mode.
2320 DMA unmap operation 2246 DMA unmap operations invalidate IOMMU hardware TLBs
2321 synchronously. 2247 synchronously.
2322 unset - Use value of 2248 unset - Use value of CONFIG_IOMMU_DEFAULT_DMA_{LAZY,STRICT}.
2323 Note: on x86, strict 2249 Note: on x86, strict mode specified via one of the
2324 legacy driver-specifi 2250 legacy driver-specific options takes precedence.
2325 2251
2326 iommu.passthrough= 2252 iommu.passthrough=
2327 [ARM64,X86,EARLY] Con !! 2253 [ARM64, X86] Configure DMA to bypass the IOMMU by default.
2328 Format: { "0" | "1" } 2254 Format: { "0" | "1" }
2329 0 - Use IOMMU transla 2255 0 - Use IOMMU translation for DMA.
2330 1 - Bypass the IOMMU 2256 1 - Bypass the IOMMU for DMA.
2331 unset - Use value of 2257 unset - Use value of CONFIG_IOMMU_DEFAULT_PASSTHROUGH.
2332 2258
2333 io7= [HW] IO7 for Marvel-b 2259 io7= [HW] IO7 for Marvel-based Alpha systems
2334 See comment before ma 2260 See comment before marvel_specify_io7 in
2335 arch/alpha/kernel/cor 2261 arch/alpha/kernel/core_marvel.c.
2336 2262
2337 io_delay= [X86,EARLY] I/O delay !! 2263 io_delay= [X86] I/O delay method
2338 0x80 2264 0x80
2339 Standard port 0x80 ba 2265 Standard port 0x80 based delay
2340 0xed 2266 0xed
2341 Alternate port 0xed b 2267 Alternate port 0xed based delay (needed on some systems)
2342 udelay 2268 udelay
2343 Simple two microsecon 2269 Simple two microseconds delay
2344 none 2270 none
2345 No delay 2271 No delay
2346 2272
2347 ip= [IP_PNP] 2273 ip= [IP_PNP]
2348 See Documentation/adm 2274 See Documentation/admin-guide/nfs/nfsroot.rst.
2349 2275
2350 ipcmni_extend [KNL,EARLY] Extend th !! 2276 ipcmni_extend [KNL] Extend the maximum number of unique System V
2351 IPC identifiers from 2277 IPC identifiers from 32,768 to 16,777,216.
2352 2278
2353 irqaffinity= [SMP] Set the default 2279 irqaffinity= [SMP] Set the default irq affinity mask
2354 The argument is a cpu 2280 The argument is a cpu list, as described above.
2355 2281
2356 irqchip.gicv2_force_probe= 2282 irqchip.gicv2_force_probe=
2357 [ARM,ARM64,EARLY] !! 2283 [ARM, ARM64]
2358 Format: <bool> 2284 Format: <bool>
2359 Force the kernel to l 2285 Force the kernel to look for the second 4kB page
2360 of a GICv2 controller 2286 of a GICv2 controller even if the memory range
2361 exposed by the device 2287 exposed by the device tree is too small.
2362 2288
2363 irqchip.gicv3_nolpi= 2289 irqchip.gicv3_nolpi=
2364 [ARM,ARM64,EARLY] !! 2290 [ARM, ARM64]
2365 Force the kernel to i 2291 Force the kernel to ignore the availability of
2366 LPIs (and by conseque 2292 LPIs (and by consequence ITSs). Intended for system
2367 that use the kernel a 2293 that use the kernel as a bootloader, and thus want
2368 to let secondary kern 2294 to let secondary kernels in charge of setting up
2369 LPIs. 2295 LPIs.
2370 2296
2371 irqchip.gicv3_pseudo_nmi= [ARM64,EARL !! 2297 irqchip.gicv3_pseudo_nmi= [ARM64]
2372 Enables support for p 2298 Enables support for pseudo-NMIs in the kernel. This
2373 requires the kernel t 2299 requires the kernel to be built with
2374 CONFIG_ARM64_PSEUDO_N 2300 CONFIG_ARM64_PSEUDO_NMI.
2375 2301
2376 irqfixup [HW] 2302 irqfixup [HW]
2377 When an interrupt is 2303 When an interrupt is not handled search all handlers
2378 for it. Intended to g 2304 for it. Intended to get systems with badly broken
2379 firmware running. 2305 firmware running.
2380 2306
2381 irqpoll [HW] 2307 irqpoll [HW]
2382 When an interrupt is 2308 When an interrupt is not handled search all handlers
2383 for it. Also check al 2309 for it. Also check all handlers each timer
2384 interrupt. Intended t 2310 interrupt. Intended to get systems with badly broken
2385 firmware running. 2311 firmware running.
2386 2312
2387 isapnp= [ISAPNP] 2313 isapnp= [ISAPNP]
2388 Format: <RDP>,<reset> 2314 Format: <RDP>,<reset>,<pci_scan>,<verbosity>
2389 2315
2390 isolcpus= [KNL,SMP,ISOL] Isolat 2316 isolcpus= [KNL,SMP,ISOL] Isolate a given set of CPUs from disturbance.
2391 [Deprecated - use cpu 2317 [Deprecated - use cpusets instead]
2392 Format: [flag-list,]< 2318 Format: [flag-list,]<cpu-list>
2393 2319
2394 Specify one or more C 2320 Specify one or more CPUs to isolate from disturbances
2395 specified in the flag 2321 specified in the flag list (default: domain):
2396 2322
2397 nohz 2323 nohz
2398 Disable the tick wh 2324 Disable the tick when a single task runs.
2399 2325
2400 A residual 1Hz tick 2326 A residual 1Hz tick is offloaded to workqueues, which you
2401 need to affine to h 2327 need to affine to housekeeping through the global
2402 workqueue's affinit 2328 workqueue's affinity configured via the
2403 /sys/devices/virtua 2329 /sys/devices/virtual/workqueue/cpumask sysfs file, or
2404 by using the 'domai 2330 by using the 'domain' flag described below.
2405 2331
2406 NOTE: by default th 2332 NOTE: by default the global workqueue runs on all CPUs,
2407 so to protect indiv 2333 so to protect individual CPUs the 'cpumask' file has to
2408 be configured manua 2334 be configured manually after bootup.
2409 2335
2410 domain 2336 domain
2411 Isolate from the ge 2337 Isolate from the general SMP balancing and scheduling
2412 algorithms. Note th 2338 algorithms. Note that performing domain isolation this way
2413 is irreversible: it 2339 is irreversible: it's not possible to bring back a CPU to
2414 the domains once is 2340 the domains once isolated through isolcpus. It's strongly
2415 advised to use cpus 2341 advised to use cpusets instead to disable scheduler load
2416 balancing through t 2342 balancing through the "cpuset.sched_load_balance" file.
2417 It offers a much mo 2343 It offers a much more flexible interface where CPUs can
2418 move in and out of 2344 move in and out of an isolated set anytime.
2419 2345
2420 You can move a proc 2346 You can move a process onto or off an "isolated" CPU via
2421 the CPU affinity sy 2347 the CPU affinity syscalls or cpuset.
2422 <cpu number> begins 2348 <cpu number> begins at 0 and the maximum value is
2423 "number of CPUs in 2349 "number of CPUs in system - 1".
2424 2350
2425 managed_irq 2351 managed_irq
2426 2352
2427 Isolate from being 2353 Isolate from being targeted by managed interrupts
2428 which have an inter 2354 which have an interrupt mask containing isolated
2429 CPUs. The affinity 2355 CPUs. The affinity of managed interrupts is
2430 handled by the kern 2356 handled by the kernel and cannot be changed via
2431 the /proc/irq/* int 2357 the /proc/irq/* interfaces.
2432 2358
2433 This isolation is b 2359 This isolation is best effort and only effective
2434 if the automaticall 2360 if the automatically assigned interrupt mask of a
2435 device queue contai 2361 device queue contains isolated and housekeeping
2436 CPUs. If housekeepi 2362 CPUs. If housekeeping CPUs are online then such
2437 interrupts are dire 2363 interrupts are directed to the housekeeping CPU
2438 so that IO submitte 2364 so that IO submitted on the housekeeping CPU
2439 cannot disturb the 2365 cannot disturb the isolated CPU.
2440 2366
2441 If a queue's affini 2367 If a queue's affinity mask contains only isolated
2442 CPUs then this para 2368 CPUs then this parameter has no effect on the
2443 interrupt routing d 2369 interrupt routing decision, though interrupts are
2444 only delivered when 2370 only delivered when tasks running on those
2445 isolated CPUs submi 2371 isolated CPUs submit IO. IO submitted on
2446 housekeeping CPUs h 2372 housekeeping CPUs has no influence on those
2447 queues. 2373 queues.
2448 2374
2449 The format of <cpu-li 2375 The format of <cpu-list> is described above.
2450 2376
2451 iucv= [HW,NET] 2377 iucv= [HW,NET]
2452 2378
2453 ivrs_ioapic [HW,X86-64] 2379 ivrs_ioapic [HW,X86-64]
2454 Provide an override t 2380 Provide an override to the IOAPIC-ID<->DEVICE-ID
2455 mapping provided in t 2381 mapping provided in the IVRS ACPI table.
2456 By default, PCI segme 2382 By default, PCI segment is 0, and can be omitted.
2457 2383
2458 For example, to map I 2384 For example, to map IOAPIC-ID decimal 10 to
2459 PCI segment 0x1 and P 2385 PCI segment 0x1 and PCI device 00:14.0,
2460 write the parameter a 2386 write the parameter as:
2461 ivrs_ioapic=1 2387 ivrs_ioapic=10@0001:00:14.0
2462 2388
2463 Deprecated formats: 2389 Deprecated formats:
2464 * To map IOAPIC-ID de 2390 * To map IOAPIC-ID decimal 10 to PCI device 00:14.0
2465 write the parameter 2391 write the parameter as:
2466 ivrs_ioapic[1 2392 ivrs_ioapic[10]=00:14.0
2467 * To map IOAPIC-ID de 2393 * To map IOAPIC-ID decimal 10 to PCI segment 0x1 and
2468 PCI device 00:14.0 2394 PCI device 00:14.0 write the parameter as:
2469 ivrs_ioapic[1 2395 ivrs_ioapic[10]=0001:00:14.0
2470 2396
2471 ivrs_hpet [HW,X86-64] 2397 ivrs_hpet [HW,X86-64]
2472 Provide an override t 2398 Provide an override to the HPET-ID<->DEVICE-ID
2473 mapping provided in t 2399 mapping provided in the IVRS ACPI table.
2474 By default, PCI segme 2400 By default, PCI segment is 0, and can be omitted.
2475 2401
2476 For example, to map H 2402 For example, to map HPET-ID decimal 10 to
2477 PCI segment 0x1 and P 2403 PCI segment 0x1 and PCI device 00:14.0,
2478 write the parameter a 2404 write the parameter as:
2479 ivrs_hpet=10@ 2405 ivrs_hpet=10@0001:00:14.0
2480 2406
2481 Deprecated formats: 2407 Deprecated formats:
2482 * To map HPET-ID deci 2408 * To map HPET-ID decimal 0 to PCI device 00:14.0
2483 write the parameter 2409 write the parameter as:
2484 ivrs_hpet[0]= 2410 ivrs_hpet[0]=00:14.0
2485 * To map HPET-ID deci 2411 * To map HPET-ID decimal 10 to PCI segment 0x1 and
2486 PCI device 00:14.0 2412 PCI device 00:14.0 write the parameter as:
2487 ivrs_ioapic[1 2413 ivrs_ioapic[10]=0001:00:14.0
2488 2414
2489 ivrs_acpihid [HW,X86-64] 2415 ivrs_acpihid [HW,X86-64]
2490 Provide an override t 2416 Provide an override to the ACPI-HID:UID<->DEVICE-ID
2491 mapping provided in t 2417 mapping provided in the IVRS ACPI table.
2492 By default, PCI segme 2418 By default, PCI segment is 0, and can be omitted.
2493 2419
2494 For example, to map U 2420 For example, to map UART-HID:UID AMD0020:0 to
2495 PCI segment 0x1 and P 2421 PCI segment 0x1 and PCI device ID 00:14.5,
2496 write the parameter a 2422 write the parameter as:
2497 ivrs_acpihid= 2423 ivrs_acpihid=AMD0020:0@0001:00:14.5
2498 2424
2499 Deprecated formats: 2425 Deprecated formats:
2500 * To map UART-HID:UID 2426 * To map UART-HID:UID AMD0020:0 to PCI segment is 0,
2501 PCI device ID 00:14 2427 PCI device ID 00:14.5, write the parameter as:
2502 ivrs_acpihid[ 2428 ivrs_acpihid[00:14.5]=AMD0020:0
2503 * To map UART-HID:UID 2429 * To map UART-HID:UID AMD0020:0 to PCI segment 0x1 and
2504 PCI device ID 00:14 2430 PCI device ID 00:14.5, write the parameter as:
2505 ivrs_acpihid[ 2431 ivrs_acpihid[0001:00:14.5]=AMD0020:0
2506 2432
2507 js= [HW,JOY] Analog joyst 2433 js= [HW,JOY] Analog joystick
2508 See Documentation/inp 2434 See Documentation/input/joydev/joystick.rst.
2509 2435
2510 kasan_multi_shot 2436 kasan_multi_shot
2511 [KNL] Enforce KASAN ( 2437 [KNL] Enforce KASAN (Kernel Address Sanitizer) to print
2512 report on every inval 2438 report on every invalid memory access. Without this
2513 parameter KASAN will 2439 parameter KASAN will print report only for the first
2514 invalid access. 2440 invalid access.
2515 2441
2516 keep_bootcon [KNL,EARLY] !! 2442 keep_bootcon [KNL]
2517 Do not unregister boo 2443 Do not unregister boot console at start. This is only
2518 useful for debugging 2444 useful for debugging when something happens in the window
2519 between unregistering 2445 between unregistering the boot console and initializing
2520 the real console. 2446 the real console.
2521 2447
2522 keepinitrd [HW,ARM] See retain_i !! 2448 keepinitrd [HW,ARM]
2523 2449
2524 kernelcore= [KNL,X86,PPC,EARLY] !! 2450 kernelcore= [KNL,X86,IA-64,PPC]
2525 Format: nn[KMGTPE] | 2451 Format: nn[KMGTPE] | nn% | "mirror"
2526 This parameter specif 2452 This parameter specifies the amount of memory usable by
2527 the kernel for non-mo 2453 the kernel for non-movable allocations. The requested
2528 amount is spread even 2454 amount is spread evenly throughout all nodes in the
2529 system as ZONE_NORMAL 2455 system as ZONE_NORMAL. The remaining memory is used for
2530 movable memory in its 2456 movable memory in its own zone, ZONE_MOVABLE. In the
2531 event, a node is too 2457 event, a node is too small to have both ZONE_NORMAL and
2532 ZONE_MOVABLE, kernelc 2458 ZONE_MOVABLE, kernelcore memory will take priority and
2533 other nodes will have 2459 other nodes will have a larger ZONE_MOVABLE.
2534 2460
2535 ZONE_MOVABLE is used 2461 ZONE_MOVABLE is used for the allocation of pages that
2536 may be reclaimed or m 2462 may be reclaimed or moved by the page migration
2537 subsystem. Note that 2463 subsystem. Note that allocations like PTEs-from-HighMem
2538 still use the HighMem 2464 still use the HighMem zone if it exists, and the Normal
2539 zone if it does not. 2465 zone if it does not.
2540 2466
2541 It is possible to spe 2467 It is possible to specify the exact amount of memory in
2542 the form of "nn[KMGTP 2468 the form of "nn[KMGTPE]", a percentage of total system
2543 memory in the form of 2469 memory in the form of "nn%", or "mirror". If "mirror"
2544 option is specified, 2470 option is specified, mirrored (reliable) memory is used
2545 for non-movable alloc 2471 for non-movable allocations and remaining memory is used
2546 for Movable pages. " 2472 for Movable pages. "nn[KMGTPE]", "nn%", and "mirror"
2547 are exclusive, so you 2473 are exclusive, so you cannot specify multiple forms.
2548 2474
2549 kgdbdbgp= [KGDB,HW,EARLY] kgdb !! 2475 kgdbdbgp= [KGDB,HW] kgdb over EHCI usb debug port.
2550 Format: <Controller#> 2476 Format: <Controller#>[,poll interval]
2551 The controller # is t 2477 The controller # is the number of the ehci usb debug
2552 port as it is probed 2478 port as it is probed via PCI. The poll interval is
2553 optional and is the n 2479 optional and is the number seconds in between
2554 each poll cycle to th 2480 each poll cycle to the debug port in case you need
2555 the functionality for 2481 the functionality for interrupting the kernel with
2556 gdb or control-c on t 2482 gdb or control-c on the dbgp connection. When
2557 not using this parame 2483 not using this parameter you use sysrq-g to break into
2558 the kernel debugger. 2484 the kernel debugger.
2559 2485
2560 kgdboc= [KGDB,HW] kgdb over c 2486 kgdboc= [KGDB,HW] kgdb over consoles.
2561 Requires a tty driver 2487 Requires a tty driver that supports console polling,
2562 or a supported pollin 2488 or a supported polling keyboard driver (non-usb).
2563 Serial only format: 2489 Serial only format: <serial_device>[,baud]
2564 keyboard only format 2490 keyboard only format: kbd
2565 keyboard and serial 2491 keyboard and serial format: kbd,<serial_device>[,baud]
2566 Optional Kernel mode 2492 Optional Kernel mode setting:
2567 kms, kbd format: kms 2493 kms, kbd format: kms,kbd
2568 kms, kbd and serial 2494 kms, kbd and serial format: kms,kbd,<ser_dev>[,baud]
2569 2495
2570 kgdboc_earlycon= [KGDB,HW,EARL !! 2496 kgdboc_earlycon= [KGDB,HW]
2571 If the boot console p 2497 If the boot console provides the ability to read
2572 characters and can wo 2498 characters and can work in polling mode, you can use
2573 this parameter to tel 2499 this parameter to tell kgdb to use it as a backend
2574 until the normal cons 2500 until the normal console is registered. Intended to
2575 be used together with 2501 be used together with the kgdboc parameter which
2576 specifies the normal 2502 specifies the normal console to transition to.
2577 2503
2578 The name of the early 2504 The name of the early console should be specified
2579 as the value of this 2505 as the value of this parameter. Note that the name of
2580 the early console mig 2506 the early console might be different than the tty
2581 name passed to kgdboc 2507 name passed to kgdboc. It's OK to leave the value
2582 blank and the first b 2508 blank and the first boot console that implements
2583 read() will be picked 2509 read() will be picked.
2584 2510
2585 kgdbwait [KGDB,EARLY] Stop ker !! 2511 kgdbwait [KGDB] Stop kernel execution and enter the
2586 kernel debugger at th 2512 kernel debugger at the earliest opportunity.
2587 2513
2588 kmac= [MIPS] Korina etherne 2514 kmac= [MIPS] Korina ethernet MAC address.
2589 Configure the RouterB 2515 Configure the RouterBoard 532 series on-chip
2590 Ethernet adapter MAC 2516 Ethernet adapter MAC address.
2591 2517
2592 kmemleak= [KNL,EARLY] Boot-time !! 2518 kmemleak= [KNL] Boot-time kmemleak enable/disable
2593 Valid arguments: on, 2519 Valid arguments: on, off
2594 Default: on 2520 Default: on
2595 Built with CONFIG_DEB 2521 Built with CONFIG_DEBUG_KMEMLEAK_DEFAULT_OFF=y,
2596 the default is off. 2522 the default is off.
2597 2523
2598 kprobe_event=[probe-list] 2524 kprobe_event=[probe-list]
2599 [FTRACE] Add kprobe e 2525 [FTRACE] Add kprobe events and enable at boot time.
2600 The probe-list is a s 2526 The probe-list is a semicolon delimited list of probe
2601 definitions. Each def 2527 definitions. Each definition is same as kprobe_events
2602 interface, but the pa 2528 interface, but the parameters are comma delimited.
2603 For example, to add a 2529 For example, to add a kprobe event on vfs_read with
2604 arg1 and arg2, add to 2530 arg1 and arg2, add to the command line;
2605 2531
2606 kprobe_event=p, 2532 kprobe_event=p,vfs_read,$arg1,$arg2
2607 2533
2608 See also Documentatio 2534 See also Documentation/trace/kprobetrace.rst "Kernel
2609 Boot Parameter" secti 2535 Boot Parameter" section.
2610 2536
2611 kpti= [ARM64,EARLY] Control !! 2537 kpti= [ARM64] Control page table isolation of user
2612 user and kernel addre !! 2538 and kernel address spaces.
2613 Default: enabled on c 2539 Default: enabled on cores which need mitigation.
2614 0: force disabled 2540 0: force disabled
2615 1: force enabled 2541 1: force enabled
2616 2542
2617 kunit.enable= [KUNIT] Enable execut 2543 kunit.enable= [KUNIT] Enable executing KUnit tests. Requires
2618 CONFIG_KUNIT to be se 2544 CONFIG_KUNIT to be set to be fully enabled. The
2619 default value can be 2545 default value can be overridden via
2620 KUNIT_DEFAULT_ENABLED 2546 KUNIT_DEFAULT_ENABLED.
2621 Default is 1 (enabled 2547 Default is 1 (enabled)
2622 2548
2623 kvm.ignore_msrs=[KVM] Ignore guest ac 2549 kvm.ignore_msrs=[KVM] Ignore guest accesses to unhandled MSRs.
2624 Default is 0 (don't i 2550 Default is 0 (don't ignore, but inject #GP)
2625 2551
2626 kvm.eager_page_split= 2552 kvm.eager_page_split=
2627 [KVM,X86] Controls wh 2553 [KVM,X86] Controls whether or not KVM will try to
2628 proactively split all 2554 proactively split all huge pages during dirty logging.
2629 Eager page splitting 2555 Eager page splitting reduces interruptions to vCPU
2630 execution by eliminat 2556 execution by eliminating the write-protection faults
2631 and MMU lock contenti 2557 and MMU lock contention that would otherwise be
2632 required to split hug 2558 required to split huge pages lazily.
2633 2559
2634 VM workloads that rar 2560 VM workloads that rarely perform writes or that write
2635 only to a small regio 2561 only to a small region of VM memory may benefit from
2636 disabling eager page 2562 disabling eager page splitting to allow huge pages to
2637 still be used for rea 2563 still be used for reads.
2638 2564
2639 The behavior of eager 2565 The behavior of eager page splitting depends on whether
2640 KVM_DIRTY_LOG_INITIAL 2566 KVM_DIRTY_LOG_INITIALLY_SET is enabled or disabled. If
2641 disabled, all huge pa 2567 disabled, all huge pages in a memslot will be eagerly
2642 split when dirty logg 2568 split when dirty logging is enabled on that memslot. If
2643 enabled, eager page s 2569 enabled, eager page splitting will be performed during
2644 the KVM_CLEAR_DIRTY i 2570 the KVM_CLEAR_DIRTY ioctl, and only for the pages being
2645 cleared. 2571 cleared.
2646 2572
2647 Eager page splitting 2573 Eager page splitting is only supported when kvm.tdp_mmu=Y.
2648 2574
2649 Default is Y (on). 2575 Default is Y (on).
2650 2576
2651 kvm.enable_vmware_backdoor=[KVM] Supp 2577 kvm.enable_vmware_backdoor=[KVM] Support VMware backdoor PV interface.
2652 Default is 2578 Default is false (don't support).
2653 2579
2654 kvm.nx_huge_pages= 2580 kvm.nx_huge_pages=
2655 [KVM] Controls the so 2581 [KVM] Controls the software workaround for the
2656 X86_BUG_ITLB_MULTIHIT 2582 X86_BUG_ITLB_MULTIHIT bug.
2657 force : Always depl 2583 force : Always deploy workaround.
2658 off : Never deplo 2584 off : Never deploy workaround.
2659 auto : Deploy work 2585 auto : Deploy workaround based on the presence of
2660 X86_BUG_ITL 2586 X86_BUG_ITLB_MULTIHIT.
2661 2587
2662 Default is 'auto'. 2588 Default is 'auto'.
2663 2589
2664 If the software worka 2590 If the software workaround is enabled for the host,
2665 guests do need not to 2591 guests do need not to enable it for nested guests.
2666 2592
2667 kvm.nx_huge_pages_recovery_ratio= 2593 kvm.nx_huge_pages_recovery_ratio=
2668 [KVM] Controls how ma 2594 [KVM] Controls how many 4KiB pages are periodically zapped
2669 back to huge pages. 2595 back to huge pages. 0 disables the recovery, otherwise if
2670 the value is N KVM wi 2596 the value is N KVM will zap 1/Nth of the 4KiB pages every
2671 period (see below). 2597 period (see below). The default is 60.
2672 2598
2673 kvm.nx_huge_pages_recovery_period_ms= 2599 kvm.nx_huge_pages_recovery_period_ms=
2674 [KVM] Controls the ti 2600 [KVM] Controls the time period at which KVM zaps 4KiB pages
2675 back to huge pages. I 2601 back to huge pages. If the value is a non-zero N, KVM will
2676 zap a portion (see ra 2602 zap a portion (see ratio above) of the pages every N msecs.
2677 If the value is 0 (th 2603 If the value is 0 (the default), KVM will pick a period based
2678 on the ratio, such th 2604 on the ratio, such that a page is zapped after 1 hour on average.
2679 2605
2680 kvm-amd.nested= [KVM,AMD] Control nes 2606 kvm-amd.nested= [KVM,AMD] Control nested virtualization feature in
2681 KVM/SVM. Default is 1 2607 KVM/SVM. Default is 1 (enabled).
2682 2608
2683 kvm-amd.npt= [KVM,AMD] Control KVM 2609 kvm-amd.npt= [KVM,AMD] Control KVM's use of Nested Page Tables,
2684 a.k.a. Two-Dimensiona 2610 a.k.a. Two-Dimensional Page Tables. Default is 1
2685 (enabled). Disable by 2611 (enabled). Disable by KVM if hardware lacks support
2686 for NPT. 2612 for NPT.
2687 2613
2688 kvm-arm.mode= 2614 kvm-arm.mode=
2689 [KVM,ARM,EARLY] Selec !! 2615 [KVM,ARM] Select one of KVM/arm64's modes of operation.
2690 operation. <<
2691 2616
2692 none: Forcefully disa 2617 none: Forcefully disable KVM.
2693 2618
2694 nvhe: Standard nVHE-b 2619 nvhe: Standard nVHE-based mode, without support for
2695 protected guest 2620 protected guests.
2696 2621
2697 protected: nVHE-based 2622 protected: nVHE-based mode with support for guests whose
2698 state is k 2623 state is kept private from the host.
2699 2624
2700 nested: VHE-based mod 2625 nested: VHE-based mode with support for nested
2701 virtualizatio 2626 virtualization. Requires at least ARMv8.3
2702 hardware. 2627 hardware.
2703 2628
2704 Defaults to VHE/nVHE 2629 Defaults to VHE/nVHE based on hardware support. Setting
2705 mode to "protected" w 2630 mode to "protected" will disable kexec and hibernation
2706 for the host. "nested 2631 for the host. "nested" is experimental and should be
2707 used with extreme cau 2632 used with extreme caution.
2708 2633
2709 kvm-arm.vgic_v3_group0_trap= 2634 kvm-arm.vgic_v3_group0_trap=
2710 [KVM,ARM,EARLY] Trap !! 2635 [KVM,ARM] Trap guest accesses to GICv3 group-0
2711 system registers 2636 system registers
2712 2637
2713 kvm-arm.vgic_v3_group1_trap= 2638 kvm-arm.vgic_v3_group1_trap=
2714 [KVM,ARM,EARLY] Trap !! 2639 [KVM,ARM] Trap guest accesses to GICv3 group-1
2715 system registers 2640 system registers
2716 2641
2717 kvm-arm.vgic_v3_common_trap= 2642 kvm-arm.vgic_v3_common_trap=
2718 [KVM,ARM,EARLY] Trap !! 2643 [KVM,ARM] Trap guest accesses to GICv3 common
2719 system registers 2644 system registers
2720 2645
2721 kvm-arm.vgic_v4_enable= 2646 kvm-arm.vgic_v4_enable=
2722 [KVM,ARM,EARLY] Allow !! 2647 [KVM,ARM] Allow use of GICv4 for direct injection of
2723 injection of LPIs. !! 2648 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 2649
2743 kvm_cma_resv_ratio=n [PPC,EARLY] !! 2650 kvm_cma_resv_ratio=n [PPC]
2744 Reserves given percen 2651 Reserves given percentage from system memory area for
2745 contiguous memory all 2652 contiguous memory allocation for KVM hash pagetable
2746 allocation. 2653 allocation.
2747 By default it reserve 2654 By default it reserves 5% of total system memory.
2748 Format: <integer> 2655 Format: <integer>
2749 Default: 5 2656 Default: 5
2750 2657
2751 kvm-intel.ept= [KVM,Intel] Control K 2658 kvm-intel.ept= [KVM,Intel] Control KVM's use of Extended Page Tables,
2752 a.k.a. Two-Dimensiona 2659 a.k.a. Two-Dimensional Page Tables. Default is 1
2753 (enabled). Disable by 2660 (enabled). Disable by KVM if hardware lacks support
2754 for EPT. 2661 for EPT.
2755 2662
2756 kvm-intel.emulate_invalid_guest_state 2663 kvm-intel.emulate_invalid_guest_state=
2757 [KVM,Intel] Control w 2664 [KVM,Intel] Control whether to emulate invalid guest
2758 state. Ignored if kvm 2665 state. Ignored if kvm-intel.enable_unrestricted_guest=1,
2759 as guest state is nev 2666 as guest state is never invalid for unrestricted
2760 guests. This param do 2667 guests. This param doesn't apply to nested guests (L2),
2761 as KVM never emulates 2668 as KVM never emulates invalid L2 guest state.
2762 Default is 1 (enabled 2669 Default is 1 (enabled).
2763 2670
2764 kvm-intel.flexpriority= 2671 kvm-intel.flexpriority=
2765 [KVM,Intel] Control K 2672 [KVM,Intel] Control KVM's use of FlexPriority feature
2766 (TPR shadow). Default 2673 (TPR shadow). Default is 1 (enabled). Disable by KVM if
2767 hardware lacks suppor 2674 hardware lacks support for it.
2768 2675
2769 kvm-intel.nested= 2676 kvm-intel.nested=
2770 [KVM,Intel] Control n 2677 [KVM,Intel] Control nested virtualization feature in
2771 KVM/VMX. Default is 1 2678 KVM/VMX. Default is 1 (enabled).
2772 2679
2773 kvm-intel.unrestricted_guest= 2680 kvm-intel.unrestricted_guest=
2774 [KVM,Intel] Control K 2681 [KVM,Intel] Control KVM's use of unrestricted guest
2775 feature (virtualized 2682 feature (virtualized real and unpaged mode). Default
2776 is 1 (enabled). Disab 2683 is 1 (enabled). Disable by KVM if EPT is disabled or
2777 hardware lacks suppor 2684 hardware lacks support for it.
2778 2685
2779 kvm-intel.vmentry_l1d_flush=[KVM,Inte 2686 kvm-intel.vmentry_l1d_flush=[KVM,Intel] Mitigation for L1 Terminal Fault
2780 CVE-2018-3620. 2687 CVE-2018-3620.
2781 2688
2782 Valid arguments: neve 2689 Valid arguments: never, cond, always
2783 2690
2784 always: L1D cache flu 2691 always: L1D cache flush on every VMENTER.
2785 cond: Flush L1D on 2692 cond: Flush L1D on VMENTER only when the code between
2786 VMEXIT and VM 2693 VMEXIT and VMENTER can leak host memory.
2787 never: Disables the 2694 never: Disables the mitigation
2788 2695
2789 Default is cond (do L 2696 Default is cond (do L1 cache flush in specific instances)
2790 2697
2791 kvm-intel.vpid= [KVM,Intel] Control K 2698 kvm-intel.vpid= [KVM,Intel] Control KVM's use of Virtual Processor
2792 Identification featur 2699 Identification feature (tagged TLBs). Default is 1
2793 (enabled). Disable by 2700 (enabled). Disable by KVM if hardware lacks support
2794 for it. 2701 for it.
2795 2702
2796 l1d_flush= [X86,INTEL,EARLY] !! 2703 l1d_flush= [X86,INTEL]
2797 Control mitigation fo 2704 Control mitigation for L1D based snooping vulnerability.
2798 2705
2799 Certain CPUs are vuln 2706 Certain CPUs are vulnerable to an exploit against CPU
2800 internal buffers whic 2707 internal buffers which can forward information to a
2801 disclosure gadget und 2708 disclosure gadget under certain conditions.
2802 2709
2803 In vulnerable process 2710 In vulnerable processors, the speculatively
2804 forwarded data can be 2711 forwarded data can be used in a cache side channel
2805 attack, to access dat 2712 attack, to access data to which the attacker does
2806 not have direct acces 2713 not have direct access.
2807 2714
2808 This parameter contro 2715 This parameter controls the mitigation. The
2809 options are: 2716 options are:
2810 2717
2811 on - enable t 2718 on - enable the interface for the mitigation
2812 2719
2813 l1tf= [X86,EARLY] Control m !! 2720 l1tf= [X86] Control mitigation of the L1TF vulnerability on
2814 affected CPUs 2721 affected CPUs
2815 2722
2816 The kernel PTE invers 2723 The kernel PTE inversion protection is unconditionally
2817 enabled and cannot be 2724 enabled and cannot be disabled.
2818 2725
2819 full 2726 full
2820 Provides all 2727 Provides all available mitigations for the
2821 L1TF vulnerab 2728 L1TF vulnerability. Disables SMT and
2822 enables all m 2729 enables all mitigations in the
2823 hypervisors, 2730 hypervisors, i.e. unconditional L1D flush.
2824 2731
2825 SMT control a 2732 SMT control and L1D flush control via the
2826 sysfs interfa 2733 sysfs interface is still possible after
2827 boot. Hyperv 2734 boot. Hypervisors will issue a warning
2828 when the firs 2735 when the first VM is started in a
2829 potentially i 2736 potentially insecure configuration,
2830 i.e. SMT enab 2737 i.e. SMT enabled or L1D flush disabled.
2831 2738
2832 full,force 2739 full,force
2833 Same as 'full 2740 Same as 'full', but disables SMT and L1D
2834 flush runtime 2741 flush runtime control. Implies the
2835 'nosmt=force' 2742 'nosmt=force' command line option.
2836 (i.e. sysfs c 2743 (i.e. sysfs control of SMT is disabled.)
2837 2744
2838 flush 2745 flush
2839 Leaves SMT en 2746 Leaves SMT enabled and enables the default
2840 hypervisor mi 2747 hypervisor mitigation, i.e. conditional
2841 L1D flush. 2748 L1D flush.
2842 2749
2843 SMT control a 2750 SMT control and L1D flush control via the
2844 sysfs interfa 2751 sysfs interface is still possible after
2845 boot. Hyperv 2752 boot. Hypervisors will issue a warning
2846 when the firs 2753 when the first VM is started in a
2847 potentially i 2754 potentially insecure configuration,
2848 i.e. SMT enab 2755 i.e. SMT enabled or L1D flush disabled.
2849 2756
2850 flush,nosmt 2757 flush,nosmt
2851 2758
2852 Disables SMT 2759 Disables SMT and enables the default
2853 hypervisor mi 2760 hypervisor mitigation.
2854 2761
2855 SMT control a 2762 SMT control and L1D flush control via the
2856 sysfs interfa 2763 sysfs interface is still possible after
2857 boot. Hyperv 2764 boot. Hypervisors will issue a warning
2858 when the firs 2765 when the first VM is started in a
2859 potentially i 2766 potentially insecure configuration,
2860 i.e. SMT enab 2767 i.e. SMT enabled or L1D flush disabled.
2861 2768
2862 flush,nowarn 2769 flush,nowarn
2863 Same as 'flus 2770 Same as 'flush', but hypervisors will not
2864 warn when a V 2771 warn when a VM is started in a potentially
2865 insecure conf 2772 insecure configuration.
2866 2773
2867 off 2774 off
2868 Disables hype 2775 Disables hypervisor mitigations and doesn't
2869 emit any warn 2776 emit any warnings.
2870 It also drops 2777 It also drops the swap size and available
2871 RAM limit res 2778 RAM limit restriction on both hypervisor and
2872 bare metal. 2779 bare metal.
2873 2780
2874 Default is 'flush'. 2781 Default is 'flush'.
2875 2782
2876 For details see: Docu 2783 For details see: Documentation/admin-guide/hw-vuln/l1tf.rst
2877 2784
2878 l2cr= [PPC] 2785 l2cr= [PPC]
2879 2786
2880 l3cr= [PPC] 2787 l3cr= [PPC]
2881 2788
2882 lapic [X86-32,APIC,EARLY] E !! 2789 lapic [X86-32,APIC] Enable the local APIC even if BIOS
2883 disabled it. 2790 disabled it.
2884 2791
2885 lapic= [X86,APIC] Do not use 2792 lapic= [X86,APIC] Do not use TSC deadline
2886 value for LAPIC timer 2793 value for LAPIC timer one-shot implementation. Default
2887 back to the programma 2794 back to the programmable timer unit in the LAPIC.
2888 Format: notscdeadline 2795 Format: notscdeadline
2889 2796
2890 lapic_timer_c2_ok [X86,APIC,EAR !! 2797 lapic_timer_c2_ok [X86,APIC] trust the local apic timer
2891 in C2 power state. 2798 in C2 power state.
2892 2799
2893 libata.dma= [LIBATA] DMA control 2800 libata.dma= [LIBATA] DMA control
2894 libata.dma=0 Dis 2801 libata.dma=0 Disable all PATA and SATA DMA
2895 libata.dma=1 PAT 2802 libata.dma=1 PATA and SATA Disk DMA only
2896 libata.dma=2 ATA 2803 libata.dma=2 ATAPI (CDROM) DMA only
2897 libata.dma=4 Com 2804 libata.dma=4 Compact Flash DMA only
2898 Combinations also wor 2805 Combinations also work, so libata.dma=3 enables DMA
2899 for disks and CDROMs, 2806 for disks and CDROMs, but not CFs.
2900 2807
2901 libata.ignore_hpa= [LIBATA] Igno 2808 libata.ignore_hpa= [LIBATA] Ignore HPA limit
2902 libata.ignore_hpa=0 2809 libata.ignore_hpa=0 keep BIOS limits (default)
2903 libata.ignore_hpa=1 2810 libata.ignore_hpa=1 ignore limits, using full disk
2904 2811
2905 libata.noacpi [LIBATA] Disables use 2812 libata.noacpi [LIBATA] Disables use of ACPI in libata suspend/resume
2906 when set. 2813 when set.
2907 Format: <int> 2814 Format: <int>
2908 2815
2909 libata.force= [LIBATA] Force config 2816 libata.force= [LIBATA] Force configurations. The format is a comma-
2910 separated list of "[I 2817 separated list of "[ID:]VAL" where ID is PORT[.DEVICE].
2911 PORT and DEVICE are d 2818 PORT and DEVICE are decimal numbers matching port, link
2912 or device. Basically 2819 or device. Basically, it matches the ATA ID string
2913 printed on console by 2820 printed on console by libata. If the whole ID part is
2914 omitted, the last POR 2821 omitted, the last PORT and DEVICE values are used. If
2915 ID hasn't been specif 2822 ID hasn't been specified yet, the configuration applies
2916 to all ports, links a 2823 to all ports, links and devices.
2917 2824
2918 If only DEVICE is omi 2825 If only DEVICE is omitted, the parameter applies to
2919 the port and all link 2826 the port and all links and devices behind it. DEVICE
2920 number of 0 either se 2827 number of 0 either selects the first device or the
2921 first fan-out link be 2828 first fan-out link behind PMP device. It does not
2922 select the host link. 2829 select the host link. DEVICE number of 15 selects the
2923 host link and device 2830 host link and device attached to it.
2924 2831
2925 The VAL specifies the 2832 The VAL specifies the configuration to force. As long
2926 as there is no ambigu 2833 as there is no ambiguity, shortcut notation is allowed.
2927 For example, both 1.5 2834 For example, both 1.5 and 1.5G would work for 1.5Gbps.
2928 The following configu 2835 The following configurations can be forced.
2929 2836
2930 * Cable type: 40c, 80 2837 * Cable type: 40c, 80c, short40c, unk, ign or sata.
2931 Any ID with matchin 2838 Any ID with matching PORT is used.
2932 2839
2933 * SATA link speed lim 2840 * SATA link speed limit: 1.5Gbps or 3.0Gbps.
2934 2841
2935 * Transfer mode: pio[ 2842 * Transfer mode: pio[0-7], mwdma[0-4] and udma[0-7].
2936 udma[/][16,25,33,44 2843 udma[/][16,25,33,44,66,100,133] notation is also
2937 allowed. 2844 allowed.
2938 2845
2939 * nohrst, nosrst, nor 2846 * nohrst, nosrst, norst: suppress hard, soft and both
2940 resets. 2847 resets.
2941 2848
2942 * rstonce: only attem 2849 * rstonce: only attempt one reset during hot-unplug
2943 link recovery. 2850 link recovery.
2944 2851
2945 * [no]dbdelay: Enable 2852 * [no]dbdelay: Enable or disable the extra 200ms delay
2946 before debouncing a 2853 before debouncing a link PHY and device presence
2947 detection. 2854 detection.
2948 2855
2949 * [no]ncq: Turn on or 2856 * [no]ncq: Turn on or off NCQ.
2950 2857
2951 * [no]ncqtrim: Enable 2858 * [no]ncqtrim: Enable or disable queued DSM TRIM.
2952 2859
2953 * [no]ncqati: Enable 2860 * [no]ncqati: Enable or disable NCQ trim on ATI chipset.
2954 2861
2955 * [no]trim: Enable or 2862 * [no]trim: Enable or disable (unqueued) TRIM.
2956 2863
2957 * trim_zero: Indicate 2864 * trim_zero: Indicate that TRIM command zeroes data.
2958 2865
2959 * max_trim_128m: Set 2866 * max_trim_128m: Set 128M maximum trim size limit.
2960 2867
2961 * [no]dma: Turn on or 2868 * [no]dma: Turn on or off DMA transfers.
2962 2869
2963 * atapi_dmadir: Enabl 2870 * atapi_dmadir: Enable ATAPI DMADIR bridge support.
2964 2871
2965 * atapi_mod16_dma: En 2872 * atapi_mod16_dma: Enable the use of ATAPI DMA for
2966 commands that are n 2873 commands that are not a multiple of 16 bytes.
2967 2874
2968 * [no]dmalog: Enable 2875 * [no]dmalog: Enable or disable the use of the
2969 READ LOG DMA EXT co 2876 READ LOG DMA EXT command to access logs.
2970 2877
2971 * [no]iddevlog: Enabl 2878 * [no]iddevlog: Enable or disable access to the
2972 identify device dat 2879 identify device data log.
2973 2880
2974 * [no]logdir: Enable 2881 * [no]logdir: Enable or disable access to the general
2975 purpose log directo 2882 purpose log directory.
2976 2883
2977 * max_sec_128: Set tr 2884 * max_sec_128: Set transfer size limit to 128 sectors.
2978 2885
2979 * max_sec_1024: Set o 2886 * max_sec_1024: Set or clear transfer size limit to
2980 1024 sectors. 2887 1024 sectors.
2981 2888
2982 * max_sec_lba48: Set 2889 * max_sec_lba48: Set or clear transfer size limit to
2983 65535 sectors. 2890 65535 sectors.
2984 2891
2985 * [no]lpm: Enable or 2892 * [no]lpm: Enable or disable link power management.
2986 2893
2987 * [no]setxfer: Indica 2894 * [no]setxfer: Indicate if transfer speed mode setting
2988 should be skipped. 2895 should be skipped.
2989 2896
2990 * [no]fua: Disable or 2897 * [no]fua: Disable or enable FUA (Force Unit Access)
2991 support for devices 2898 support for devices supporting this feature.
2992 2899
2993 * dump_id: Dump IDENT 2900 * dump_id: Dump IDENTIFY data.
2994 2901
2995 * disable: Disable th 2902 * disable: Disable this device.
2996 2903
2997 If there are multiple 2904 If there are multiple matching configurations changing
2998 the same attribute, t 2905 the same attribute, the last one is used.
2999 2906
3000 load_ramdisk= [RAM] [Deprecated] 2907 load_ramdisk= [RAM] [Deprecated]
3001 2908
3002 lockd.nlm_grace_period=P [NFS] Assig 2909 lockd.nlm_grace_period=P [NFS] Assign grace period.
3003 Format: <integer> 2910 Format: <integer>
3004 2911
3005 lockd.nlm_tcpport=N [NFS] Assign 2912 lockd.nlm_tcpport=N [NFS] Assign TCP port.
3006 Format: <integer> 2913 Format: <integer>
3007 2914
3008 lockd.nlm_timeout=T [NFS] Assign 2915 lockd.nlm_timeout=T [NFS] Assign timeout value.
3009 Format: <integer> 2916 Format: <integer>
3010 2917
3011 lockd.nlm_udpport=M [NFS] Assign 2918 lockd.nlm_udpport=M [NFS] Assign UDP port.
3012 Format: <integer> 2919 Format: <integer>
3013 2920
3014 lockdown= [SECURITY,EARLY] !! 2921 lockdown= [SECURITY]
3015 { integrity | confide 2922 { integrity | confidentiality }
3016 Enable the kernel loc 2923 Enable the kernel lockdown feature. If set to
3017 integrity, kernel fea 2924 integrity, kernel features that allow userland to
3018 modify the running ke 2925 modify the running kernel are disabled. If set to
3019 confidentiality, kern 2926 confidentiality, kernel features that allow userland
3020 to extract confidenti 2927 to extract confidential information from the kernel
3021 are also disabled. 2928 are also disabled.
3022 2929
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] 2930 locktorture.nreaders_stress= [KNL]
3056 Set the number of loc 2931 Set the number of locking read-acquisition kthreads.
3057 Defaults to being aut 2932 Defaults to being automatically set based on the
3058 number of online CPUs 2933 number of online CPUs.
3059 2934
3060 locktorture.nwriters_stress= [KNL] 2935 locktorture.nwriters_stress= [KNL]
3061 Set the number of loc 2936 Set the number of locking write-acquisition kthreads.
3062 2937
3063 locktorture.onoff_holdoff= [KNL] 2938 locktorture.onoff_holdoff= [KNL]
3064 Set time (s) after bo 2939 Set time (s) after boot for CPU-hotplug testing.
3065 2940
3066 locktorture.onoff_interval= [KNL] 2941 locktorture.onoff_interval= [KNL]
3067 Set time (s) between 2942 Set time (s) between CPU-hotplug operations, or
3068 zero to disable CPU-h 2943 zero to disable CPU-hotplug testing.
3069 2944
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] 2945 locktorture.shuffle_interval= [KNL]
3090 Set task-shuffle inte 2946 Set task-shuffle interval (jiffies). Shuffling
3091 tasks allows some CPU 2947 tasks allows some CPUs to go into dyntick-idle
3092 mode during the lockt 2948 mode during the locktorture test.
3093 2949
3094 locktorture.shutdown_secs= [KNL] 2950 locktorture.shutdown_secs= [KNL]
3095 Set time (s) after bo 2951 Set time (s) after boot system shutdown. This
3096 is useful for hands-o 2952 is useful for hands-off automated testing.
3097 2953
3098 locktorture.stat_interval= [KNL] 2954 locktorture.stat_interval= [KNL]
3099 Time (s) between stat 2955 Time (s) between statistics printk()s.
3100 2956
3101 locktorture.stutter= [KNL] 2957 locktorture.stutter= [KNL]
3102 Time (s) to stutter t 2958 Time (s) to stutter testing, for example,
3103 specifying five secon 2959 specifying five seconds causes the test to run for
3104 five seconds, wait fo 2960 five seconds, wait for five seconds, and so on.
3105 This tests the lockin 2961 This tests the locking primitive's ability to
3106 transition abruptly t 2962 transition abruptly to and from idle.
3107 2963
3108 locktorture.torture_type= [KNL] 2964 locktorture.torture_type= [KNL]
3109 Specify the locking i 2965 Specify the locking implementation to test.
3110 2966
3111 locktorture.verbose= [KNL] <<
3112 Enable additional pri <<
3113 <<
3114 locktorture.writer_fifo= [KNL] 2967 locktorture.writer_fifo= [KNL]
3115 Run the write-side lo 2968 Run the write-side locktorture kthreads at
3116 sched_set_fifo() real 2969 sched_set_fifo() real-time priority.
3117 2970
>> 2971 locktorture.verbose= [KNL]
>> 2972 Enable additional printk() statements.
>> 2973
3118 logibm.irq= [HW,MOUSE] Logitech B 2974 logibm.irq= [HW,MOUSE] Logitech Bus Mouse Driver
3119 Format: <irq> 2975 Format: <irq>
3120 2976
3121 loglevel= [KNL,EARLY] !! 2977 loglevel= All Kernel Messages with a loglevel smaller than the
3122 All Kernel Messages w <<
3123 console loglevel will 2978 console loglevel will be printed to the console. It can
3124 also be changed with 2979 also be changed with klogd or other programs. The
3125 loglevels are defined 2980 loglevels are defined as follows:
3126 2981
3127 0 (KERN_EMERG) 2982 0 (KERN_EMERG) system is unusable
3128 1 (KERN_ALERT) 2983 1 (KERN_ALERT) action must be taken immediately
3129 2 (KERN_CRIT) 2984 2 (KERN_CRIT) critical conditions
3130 3 (KERN_ERR) 2985 3 (KERN_ERR) error conditions
3131 4 (KERN_WARNING) 2986 4 (KERN_WARNING) warning conditions
3132 5 (KERN_NOTICE) 2987 5 (KERN_NOTICE) normal but significant condition
3133 6 (KERN_INFO) 2988 6 (KERN_INFO) informational
3134 7 (KERN_DEBUG) 2989 7 (KERN_DEBUG) debug-level messages
3135 2990
3136 log_buf_len=n[KMG] [KNL,EARLY] !! 2991 log_buf_len=n[KMG] Sets the size of the printk ring buffer,
3137 Sets the size of the !! 2992 in bytes. n must be a power of two and greater
3138 n must be a power of !! 2993 than the minimal size. The minimal size is defined
3139 minimal size. The min !! 2994 by LOG_BUF_SHIFT kernel config parameter. There is
3140 LOG_BUF_SHIFT kernel !! 2995 also CONFIG_LOG_CPU_MAX_BUF_SHIFT config parameter
3141 is also CONFIG_LOG_CP !! 2996 that allows to increase the default size depending on
3142 parameter that allows !! 2997 the number of CPUs. See init/Kconfig for more details.
3143 depending on the numb <<
3144 for more details. <<
3145 2998
3146 logo.nologo [FB] Disables display 2999 logo.nologo [FB] Disables display of the built-in Linux logo.
3147 This may be used to p 3000 This may be used to provide more screen space for
3148 kernel log messages a 3001 kernel log messages and is useful when debugging
3149 kernel boot problems. 3002 kernel boot problems.
3150 3003
3151 lp=0 [LP] Specify paral 3004 lp=0 [LP] Specify parallel ports to use, e.g,
3152 lp=port[,port...] lp=none,parpo 3005 lp=port[,port...] lp=none,parport0 (lp0 not configured, lp1 uses
3153 lp=reset first paralle 3006 lp=reset first parallel port). 'lp=0' disables the
3154 lp=auto printer drive 3007 lp=auto printer driver. 'lp=reset' (which can be
3155 specified in 3008 specified in addition to the ports) causes
3156 attached prin 3009 attached printers to be reset. Using
3157 lp=port1,port 3010 lp=port1,port2,... specifies the parallel ports
3158 to associate 3011 to associate lp devices with, starting with
3159 lp0. A port s 3012 lp0. A port specification may be 'none' to skip
3160 that lp devic 3013 that lp device, or a parport name such as
3161 'parport0'. S 3014 'parport0'. Specifying 'lp=auto' instead of a
3162 port specific 3015 port specification list means that device IDs
3163 from each por 3016 from each port should be examined, to see if
3164 an IEEE 1284- 3017 an IEEE 1284-compliant printer is attached; if
3165 so, the drive 3018 so, the driver will manage that printer.
3166 See also head 3019 See also header of drivers/char/lp.c.
3167 3020
3168 lpj=n [KNL] 3021 lpj=n [KNL]
3169 Sets loops_per_jiffy 3022 Sets loops_per_jiffy to given constant, thus avoiding
3170 time-consuming boot-t 3023 time-consuming boot-time autodetection (up to 250 ms per
3171 CPU). 0 enables autod 3024 CPU). 0 enables autodetection (default). To determine
3172 the correct value for 3025 the correct value for your kernel, boot with normal
3173 autodetection and see 3026 autodetection and see what value is printed. Note that
3174 on SMP systems the pr 3027 on SMP systems the preset will be applied to all CPUs,
3175 which is likely to ca 3028 which is likely to cause problems if your CPUs need
3176 significantly diverge 3029 significantly divergent settings. An incorrect value
3177 will cause delays in 3030 will cause delays in the kernel to be wrong, leading to
3178 unpredictable I/O err 3031 unpredictable I/O errors and other breakage. Although
3179 unlikely, in the extr 3032 unlikely, in the extreme case this might damage your
3180 hardware. 3033 hardware.
3181 3034
>> 3035 ltpc= [NET]
>> 3036 Format: <io>,<irq>,<dma>
>> 3037
3182 lsm.debug [SECURITY] Enable LSM 3038 lsm.debug [SECURITY] Enable LSM initialization debugging output.
3183 3039
3184 lsm=lsm1,...,lsmN 3040 lsm=lsm1,...,lsmN
3185 [SECURITY] Choose ord 3041 [SECURITY] Choose order of LSM initialization. This
3186 overrides CONFIG_LSM, 3042 overrides CONFIG_LSM, and the "security=" parameter.
3187 3043
>> 3044 machvec= [IA-64] Force the use of a particular machine-vector
>> 3045 (machvec) in a generic kernel.
>> 3046 Example: machvec=hpzx1
>> 3047
3188 machtype= [Loongson] Share the 3048 machtype= [Loongson] Share the same kernel image file between
3189 different yeeloong la 3049 different yeeloong laptops.
3190 Example: machtype=lem 3050 Example: machtype=lemote-yeeloong-2f-7inch
3191 3051
3192 maxcpus= [SMP,EARLY] Maximum n !! 3052 max_addr=nn[KMG] [KNL,BOOT,IA-64] All physical memory greater
>> 3053 than or equal to this physical address is ignored.
>> 3054
>> 3055 maxcpus= [SMP] Maximum number of processors that an SMP kernel
3193 will bring up during 3056 will bring up during bootup. maxcpus=n : n >= 0 limits
3194 the kernel to bring u 3057 the kernel to bring up 'n' processors. Surely after
3195 bootup you can bring 3058 bootup you can bring up the other plugged cpu by executing
3196 "echo 1 > /sys/device 3059 "echo 1 > /sys/devices/system/cpu/cpuX/online". So maxcpus
3197 only takes effect dur 3060 only takes effect during system bootup.
3198 While n=0 is a specia 3061 While n=0 is a special case, it is equivalent to "nosmp",
3199 which also disables t 3062 which also disables the IO APIC.
3200 3063
3201 max_loop= [LOOP] The number of 3064 max_loop= [LOOP] The number of loop block devices that get
3202 (loop.max_loop) unconditionally pre-c 3065 (loop.max_loop) unconditionally pre-created at init time. The default
3203 number is configured 3066 number is configured by BLK_DEV_LOOP_MIN_COUNT. Instead
3204 of statically allocat 3067 of statically allocating a predefined number, loop
3205 devices can be reques 3068 devices can be requested on-demand with the
3206 /dev/loop-control int 3069 /dev/loop-control interface.
3207 3070
3208 mce [X86-32] Machine Chec 3071 mce [X86-32] Machine Check Exception
3209 3072
3210 mce=option [X86-64] See Document 3073 mce=option [X86-64] See Documentation/arch/x86/x86_64/boot-options.rst
3211 3074
3212 md= [HW] RAID subsystems 3075 md= [HW] RAID subsystems devices and level
3213 See Documentation/adm 3076 See Documentation/admin-guide/md.rst.
3214 3077
3215 mdacon= [MDA] 3078 mdacon= [MDA]
3216 Format: <first>,<last 3079 Format: <first>,<last>
3217 Specifies range of co 3080 Specifies range of consoles to be captured by the MDA.
3218 3081
3219 mds= [X86,INTEL,EARLY] !! 3082 mds= [X86,INTEL]
3220 Control mitigation fo 3083 Control mitigation for the Micro-architectural Data
3221 Sampling (MDS) vulner 3084 Sampling (MDS) vulnerability.
3222 3085
3223 Certain CPUs are vuln 3086 Certain CPUs are vulnerable to an exploit against CPU
3224 internal buffers whic 3087 internal buffers which can forward information to a
3225 disclosure gadget und 3088 disclosure gadget under certain conditions.
3226 3089
3227 In vulnerable process 3090 In vulnerable processors, the speculatively
3228 forwarded data can be 3091 forwarded data can be used in a cache side channel
3229 attack, to access dat 3092 attack, to access data to which the attacker does
3230 not have direct acces 3093 not have direct access.
3231 3094
3232 This parameter contro 3095 This parameter controls the MDS mitigation. The
3233 options are: 3096 options are:
3234 3097
3235 full - Enable M 3098 full - Enable MDS mitigation on vulnerable CPUs
3236 full,nosmt - Enable M 3099 full,nosmt - Enable MDS mitigation and disable
3237 SMT on v 3100 SMT on vulnerable CPUs
3238 off - Uncondit 3101 off - Unconditionally disable MDS mitigation
3239 3102
3240 On TAA-affected machi 3103 On TAA-affected machines, mds=off can be prevented by
3241 an active TAA mitigat 3104 an active TAA mitigation as both vulnerabilities are
3242 mitigated with the sa 3105 mitigated with the same mechanism so in order to disable
3243 this mitigation, you 3106 this mitigation, you need to specify tsx_async_abort=off
3244 too. 3107 too.
3245 3108
3246 Not specifying this o 3109 Not specifying this option is equivalent to
3247 mds=full. 3110 mds=full.
3248 3111
3249 For details see: Docu 3112 For details see: Documentation/admin-guide/hw-vuln/mds.rst
3250 3113
3251 mem=nn[KMG] [HEXAGON,EARLY] Set t !! 3114 mem=nn[KMG] [HEXAGON] Set the memory size.
3252 Must be specified, ot 3115 Must be specified, otherwise memory size will be 0.
3253 3116
3254 mem=nn[KMG] [KNL,BOOT,EARLY] Forc !! 3117 mem=nn[KMG] [KNL,BOOT] Force usage of a specific amount of memory
3255 of memory Amount of m !! 3118 Amount of memory to be used in cases as follows:
3256 as follows: <<
3257 3119
3258 1 for test; 3120 1 for test;
3259 2 when the kernel is 3121 2 when the kernel is not able to see the whole system memory;
3260 3 memory that lies af 3122 3 memory that lies after 'mem=' boundary is excluded from
3261 the hypervisor, then 3123 the hypervisor, then assigned to KVM guests.
3262 4 to limit the memory 3124 4 to limit the memory available for kdump kernel.
3263 3125
3264 [ARC,MICROBLAZE] - th 3126 [ARC,MICROBLAZE] - the limit applies only to low memory,
3265 high memory is not af 3127 high memory is not affected.
3266 3128
3267 [ARM64] - only limits 3129 [ARM64] - only limits memory covered by the linear
3268 mapping. The NOMAP re 3130 mapping. The NOMAP regions are not affected.
3269 3131
3270 [X86] Work as limitin 3132 [X86] Work as limiting max address. Use together
3271 with memmap= to avoid 3133 with memmap= to avoid physical address space collisions.
3272 Without memmap= PCI d 3134 Without memmap= PCI devices could be placed at addresses
3273 belonging to unused R 3135 belonging to unused RAM.
3274 3136
3275 Note that this only t 3137 Note that this only takes effects during boot time since
3276 in above case 3, memo 3138 in above case 3, memory may need be hot added after boot
3277 if system memory of h 3139 if system memory of hypervisor is not sufficient.
3278 3140
3279 mem=nn[KMG]@ss[KMG] 3141 mem=nn[KMG]@ss[KMG]
3280 [ARM,MIPS,EARLY] - ov !! 3142 [ARM,MIPS] - override the memory layout reported by
3281 reported by firmware. !! 3143 firmware.
3282 Define a memory regio 3144 Define a memory region of size nn[KMG] starting at
3283 ss[KMG]. 3145 ss[KMG].
3284 Multiple different re 3146 Multiple different regions can be specified with
3285 multiple mem= paramet 3147 multiple mem= parameters on the command line.
3286 3148
3287 mem=nopentium [BUGS=X86-32] Disable 3149 mem=nopentium [BUGS=X86-32] Disable usage of 4MB pages for kernel
3288 memory. 3150 memory.
3289 3151
3290 memblock=debug [KNL,EARLY] Enable me !! 3152 memblock=debug [KNL] Enable memblock debug messages.
3291 3153
3292 memchunk=nn[KMG] 3154 memchunk=nn[KMG]
3293 [KNL,SH] Allow user t 3155 [KNL,SH] Allow user to override the default size for
3294 per-device physically 3156 per-device physically contiguous DMA buffers.
3295 3157
3296 memhp_default_state=online/offline/on 3158 memhp_default_state=online/offline/online_kernel/online_movable
3297 [KNL] Set the initial 3159 [KNL] Set the initial state for the memory hotplug
3298 onlining policy. If n 3160 onlining policy. If not specified, the default value is
3299 set according to the 3161 set according to the
3300 CONFIG_MEMORY_HOTPLUG 3162 CONFIG_MEMORY_HOTPLUG_DEFAULT_ONLINE kernel config
3301 option. 3163 option.
3302 See Documentation/adm 3164 See Documentation/admin-guide/mm/memory-hotplug.rst.
3303 3165
3304 memmap=exactmap [KNL,X86,EARLY] Enabl !! 3166 memmap=exactmap [KNL,X86] Enable setting of an exact
3305 E820 memory map, as s 3167 E820 memory map, as specified by the user.
3306 Such memmap=exactmap 3168 Such memmap=exactmap lines can be constructed based on
3307 BIOS output or other 3169 BIOS output or other requirements. See the memmap=nn@ss
3308 option description. 3170 option description.
3309 3171
3310 memmap=nn[KMG]@ss[KMG] 3172 memmap=nn[KMG]@ss[KMG]
3311 [KNL, X86,MIPS,XTENSA !! 3173 [KNL, X86, MIPS, XTENSA] Force usage of a specific region of memory.
3312 Region of memory to b 3174 Region of memory to be used is from ss to ss+nn.
3313 If @ss[KMG] is omitte 3175 If @ss[KMG] is omitted, it is equivalent to mem=nn[KMG],
3314 which limits max addr 3176 which limits max address to nn[KMG].
3315 Multiple different re 3177 Multiple different regions can be specified,
3316 comma delimited. 3178 comma delimited.
3317 Example: 3179 Example:
3318 memmap=100M@2 3180 memmap=100M@2G,100M#3G,1G!1024G
3319 3181
3320 memmap=nn[KMG]#ss[KMG] 3182 memmap=nn[KMG]#ss[KMG]
3321 [KNL,ACPI,EARLY] Mark !! 3183 [KNL,ACPI] Mark specific memory as ACPI data.
3322 Region of memory to b 3184 Region of memory to be marked is from ss to ss+nn.
3323 3185
3324 memmap=nn[KMG]$ss[KMG] 3186 memmap=nn[KMG]$ss[KMG]
3325 [KNL,ACPI,EARLY] Mark !! 3187 [KNL,ACPI] Mark specific memory as reserved.
3326 Region of memory to b 3188 Region of memory to be reserved is from ss to ss+nn.
3327 Example: Exclude memo 3189 Example: Exclude memory from 0x18690000-0x1869ffff
3328 memmap=64K$0 3190 memmap=64K$0x18690000
3329 or 3191 or
3330 memmap=0x100 3192 memmap=0x10000$0x18690000
3331 Some bootloaders may 3193 Some bootloaders may need an escape character before '$',
3332 like Grub2, otherwise 3194 like Grub2, otherwise '$' and the following number
3333 will be eaten. 3195 will be eaten.
3334 3196
3335 memmap=nn[KMG]!ss[KMG,EARLY] !! 3197 memmap=nn[KMG]!ss[KMG]
3336 [KNL,X86] Mark specif 3198 [KNL,X86] Mark specific memory as protected.
3337 Region of memory to b 3199 Region of memory to be used, from ss to ss+nn.
3338 The memory region may 3200 The memory region may be marked as e820 type 12 (0xc)
3339 and is NVDIMM or ADR 3201 and is NVDIMM or ADR memory.
3340 3202
3341 memmap=<size>%<offset>-<oldtype>+<new 3203 memmap=<size>%<offset>-<oldtype>+<newtype>
3342 [KNL,ACPI,EARLY] Conv !! 3204 [KNL,ACPI] Convert memory within the specified region
3343 from <oldtype> to <ne 3205 from <oldtype> to <newtype>. If "-<oldtype>" is left
3344 out, the whole region 3206 out, the whole region will be marked as <newtype>,
3345 even if previously un 3207 even if previously unavailable. If "+<newtype>" is left
3346 out, matching memory 3208 out, matching memory will be removed. Types are
3347 specified as e820 typ 3209 specified as e820 types, e.g., 1 = RAM, 2 = reserved,
3348 3 = ACPI, 12 = PRAM. 3210 3 = ACPI, 12 = PRAM.
3349 3211
3350 memory_corruption_check=0/1 [X86,EARL !! 3212 memory_corruption_check=0/1 [X86]
3351 Some BIOSes seem to c 3213 Some BIOSes seem to corrupt the first 64k of
3352 memory when doing thi 3214 memory when doing things like suspend/resume.
3353 Setting this option w 3215 Setting this option will scan the memory
3354 looking for corruptio 3216 looking for corruption. Enabling this will
3355 both detect corruptio 3217 both detect corruption and prevent the kernel
3356 from using the memory 3218 from using the memory being corrupted.
3357 However, its intended 3219 However, its intended as a diagnostic tool; if
3358 repeatable BIOS-origi 3220 repeatable BIOS-originated corruption always
3359 affects the same memo 3221 affects the same memory, you can use memmap=
3360 to prevent the kernel 3222 to prevent the kernel from using that memory.
3361 3223
3362 memory_corruption_check_size=size [X8 !! 3224 memory_corruption_check_size=size [X86]
3363 By default it checks 3225 By default it checks for corruption in the low
3364 64k, making this memo 3226 64k, making this memory unavailable for normal
3365 use. Use this parame 3227 use. Use this parameter to scan for
3366 corruption in more or 3228 corruption in more or less memory.
3367 3229
3368 memory_corruption_check_period=second !! 3230 memory_corruption_check_period=seconds [X86]
3369 By default it checks 3231 By default it checks for corruption every 60
3370 seconds. Use this pa 3232 seconds. Use this parameter to check at some
3371 other rate. 0 disabl 3233 other rate. 0 disables periodic checking.
3372 3234
3373 memory_hotplug.memmap_on_memory 3235 memory_hotplug.memmap_on_memory
3374 [KNL,X86,ARM] Boolean 3236 [KNL,X86,ARM] Boolean flag to enable this feature.
3375 Format: {on | off (de 3237 Format: {on | off (default)}
3376 When enabled, runtime 3238 When enabled, runtime hotplugged memory will
3377 allocate its internal 3239 allocate its internal metadata (struct pages,
3378 those vmemmap pages c 3240 those vmemmap pages cannot be optimized even
3379 if hugetlb_free_vmemm 3241 if hugetlb_free_vmemmap is enabled) from the
3380 hotadded memory which 3242 hotadded memory which will allow to hotadd a
3381 lot of memory without 3243 lot of memory without requiring additional
3382 memory to do so. 3244 memory to do so.
3383 This feature is disab 3245 This feature is disabled by default because it
3384 has some implication 3246 has some implication on large (e.g. GB)
3385 allocations in some c 3247 allocations in some configurations (e.g. small
3386 memory blocks). 3248 memory blocks).
3387 The state of the flag 3249 The state of the flag can be read in
3388 /sys/module/memory_ho 3250 /sys/module/memory_hotplug/parameters/memmap_on_memory.
3389 Note that even when e 3251 Note that even when enabled, there are a few cases where
3390 the feature is not ef 3252 the feature is not effective.
3391 3253
3392 memtest= [KNL,X86,ARM,M68K,PPC !! 3254 memtest= [KNL,X86,ARM,M68K,PPC,RISCV] Enable memtest
3393 Format: <integer> 3255 Format: <integer>
3394 default : 0 <disable> 3256 default : 0 <disable>
3395 Specifies the number 3257 Specifies the number of memtest passes to be
3396 performed. Each pass 3258 performed. Each pass selects another test
3397 pattern from a given 3259 pattern from a given set of patterns. Memtest
3398 fills the memory with 3260 fills the memory with this pattern, validates
3399 memory contents and r 3261 memory contents and reserves bad memory
3400 regions that are dete 3262 regions that are detected.
3401 3263
3402 mem_encrypt= [X86-64] AMD Secure M 3264 mem_encrypt= [X86-64] AMD Secure Memory Encryption (SME) control
3403 Valid arguments: on, 3265 Valid arguments: on, off
3404 Default: off 3266 Default: off
3405 mem_encrypt=on: 3267 mem_encrypt=on: Activate SME
3406 mem_encrypt=off: 3268 mem_encrypt=off: Do not activate SME
3407 3269
3408 Refer to Documentatio 3270 Refer to Documentation/virt/kvm/x86/amd-memory-encryption.rst
3409 for details on when m 3271 for details on when memory encryption can be activated.
3410 3272
3411 mem_sleep_default= [SUSPEND] Def 3273 mem_sleep_default= [SUSPEND] Default system suspend mode:
3412 s2idle - Suspend-To- 3274 s2idle - Suspend-To-Idle
3413 shallow - Power-On Su 3275 shallow - Power-On Suspend or equivalent (if supported)
3414 deep - Suspend-To- 3276 deep - Suspend-To-RAM or equivalent (if supported)
3415 See Documentation/adm 3277 See Documentation/admin-guide/pm/sleep-states.rst.
3416 3278
>> 3279 mfgpt_irq= [IA-32] Specify the IRQ to use for the
>> 3280 Multi-Function General Purpose Timers on AMD Geode
>> 3281 platforms.
>> 3282
3417 mfgptfix [X86-32] Fix MFGPT ti 3283 mfgptfix [X86-32] Fix MFGPT timers on AMD Geode platforms when
3418 the BIOS has incorrec 3284 the BIOS has incorrectly applied a workaround. TinyBIOS
3419 version 0.98 is known 3285 version 0.98 is known to be affected, 0.99 fixes the
3420 problem by letting th 3286 problem by letting the user disable the workaround.
3421 3287
3422 mga= [HW,DRM] 3288 mga= [HW,DRM]
3423 3289
3424 microcode.force_minrev= [X86] !! 3290 min_addr=nn[KMG] [KNL,BOOT,IA-64] All physical memory below this
3425 Format: <bool> !! 3291 physical address is ignored.
3426 Enable or disable the <<
3427 enforcement for the r <<
3428 3292
3429 mini2440= [ARM,HW,KNL] 3293 mini2440= [ARM,HW,KNL]
3430 Format:[0..2][b][c][t 3294 Format:[0..2][b][c][t]
3431 Default: "0tb" 3295 Default: "0tb"
3432 MINI2440 configuratio 3296 MINI2440 configuration specification:
3433 0 - The attached scre 3297 0 - The attached screen is the 3.5" TFT
3434 1 - The attached scre 3298 1 - The attached screen is the 7" TFT
3435 2 - The VGA Shield is 3299 2 - The VGA Shield is attached (1024x768)
3436 Leaving out the scree 3300 Leaving out the screen size parameter will not load
3437 the TFT driver, and t 3301 the TFT driver, and the framebuffer will be left
3438 unconfigured. 3302 unconfigured.
3439 b - Enable backlight. 3303 b - Enable backlight. The TFT backlight pin will be
3440 linked to the kernel 3304 linked to the kernel VESA blanking code and a GPIO
3441 LED. This parameter i 3305 LED. This parameter is not necessary when using the
3442 VGA shield. 3306 VGA shield.
3443 c - Enable the s3c ca 3307 c - Enable the s3c camera interface.
3444 t - Reserved for enab 3308 t - Reserved for enabling touchscreen support. The
3445 touchscreen support i 3309 touchscreen support is not enabled in the mainstream
3446 kernel as of 2.6.30, 3310 kernel as of 2.6.30, a preliminary port can be found
3447 in the "bleeding edge 3311 in the "bleeding edge" mini2440 support kernel at
3448 https://repo.or.cz/w/ 3312 https://repo.or.cz/w/linux-2.6/mini2440.git
3449 3313
3450 mitigations= 3314 mitigations=
3451 [X86,PPC,S390,ARM64,E !! 3315 [X86,PPC,S390,ARM64] Control optional mitigations for
3452 CPU vulnerabilities. 3316 CPU vulnerabilities. This is a set of curated,
3453 arch-independent opti 3317 arch-independent options, each of which is an
3454 aggregation of existi 3318 aggregation of existing arch-specific options.
3455 3319
3456 Note, "mitigations" i 3320 Note, "mitigations" is supported if and only if the
3457 kernel was built with 3321 kernel was built with CPU_MITIGATIONS=y.
3458 3322
3459 off 3323 off
3460 Disable all o 3324 Disable all optional CPU mitigations. This
3461 improves syst 3325 improves system performance, but it may also
3462 expose users 3326 expose users to several CPU vulnerabilities.
3463 Equivalent to 3327 Equivalent to: if nokaslr then kpti=0 [ARM64]
3464 3328 gather_data_sampling=off [X86]
3465 3329 kvm.nx_huge_pages=off [X86]
3466 3330 l1tf=off [X86]
3467 3331 mds=off [X86]
3468 3332 mmio_stale_data=off [X86]
3469 3333 no_entry_flush [PPC]
3470 3334 no_uaccess_flush [PPC]
3471 3335 nobp=0 [S390]
3472 3336 nopti [X86,PPC]
3473 3337 nospectre_bhb [ARM64]
3474 3338 nospectre_v1 [X86,PPC]
3475 3339 nospectre_v2 [X86,PPC,S390,ARM64]
3476 3340 reg_file_data_sampling=off [X86]
3477 3341 retbleed=off [X86]
3478 <<
3479 3342 spec_store_bypass_disable=off [X86,PPC]
3480 3343 spectre_bhi=off [X86]
3481 3344 spectre_v2_user=off [X86]
3482 3345 srbds=off [X86,INTEL]
3483 3346 ssbd=force-off [ARM64]
3484 3347 tsx_async_abort=off [X86]
3485 3348
3486 Exceptions: 3349 Exceptions:
3487 3350 This does not have any effect on
3488 3351 kvm.nx_huge_pages when
3489 3352 kvm.nx_huge_pages=force.
3490 3353
3491 auto (default) 3354 auto (default)
3492 Mitigate all 3355 Mitigate all CPU vulnerabilities, but leave SMT
3493 enabled, even 3356 enabled, even if it's vulnerable. This is for
3494 users who don 3357 users who don't want to be surprised by SMT
3495 getting disab 3358 getting disabled across kernel upgrades, or who
3496 have other wa 3359 have other ways of avoiding SMT-based attacks.
3497 Equivalent to 3360 Equivalent to: (default behavior)
3498 3361
3499 auto,nosmt 3362 auto,nosmt
3500 Mitigate all 3363 Mitigate all CPU vulnerabilities, disabling SMT
3501 if needed. T 3364 if needed. This is for users who always want to
3502 be fully miti 3365 be fully mitigated, even if it means losing SMT.
3503 Equivalent to 3366 Equivalent to: l1tf=flush,nosmt [X86]
3504 3367 mds=full,nosmt [X86]
3505 3368 tsx_async_abort=full,nosmt [X86]
3506 3369 mmio_stale_data=full,nosmt [X86]
3507 3370 retbleed=auto,nosmt [X86]
3508 3371
3509 mminit_loglevel= 3372 mminit_loglevel=
3510 [KNL,EARLY] When CONF !! 3373 [KNL] When CONFIG_DEBUG_MEMORY_INIT is set, this
3511 parameter allows cont 3374 parameter allows control of the logging verbosity for
3512 the additional memory 3375 the additional memory initialisation checks. A value
3513 of 0 disables mminit 3376 of 0 disables mminit logging and a level of 4 will
3514 log everything. Infor 3377 log everything. Information is printed at KERN_DEBUG
3515 so loglevel=8 may als 3378 so loglevel=8 may also need to be specified.
3516 3379
3517 mmio_stale_data= 3380 mmio_stale_data=
3518 [X86,INTEL,EARLY] Con !! 3381 [X86,INTEL] Control mitigation for the Processor
3519 MMIO Stale Data vulne 3382 MMIO Stale Data vulnerabilities.
3520 3383
3521 Processor MMIO Stale 3384 Processor MMIO Stale Data is a class of
3522 vulnerabilities that 3385 vulnerabilities that may expose data after an MMIO
3523 operation. Exposed da 3386 operation. Exposed data could originate or end in
3524 the same CPU buffers 3387 the same CPU buffers as affected by MDS and TAA.
3525 Therefore, similar to 3388 Therefore, similar to MDS and TAA, the mitigation
3526 is to clear the affec 3389 is to clear the affected CPU buffers.
3527 3390
3528 This parameter contro 3391 This parameter controls the mitigation. The
3529 options are: 3392 options are:
3530 3393
3531 full - Enable m 3394 full - Enable mitigation on vulnerable CPUs
3532 3395
3533 full,nosmt - Enable m 3396 full,nosmt - Enable mitigation and disable SMT on
3534 vulnerab 3397 vulnerable CPUs.
3535 3398
3536 off - Uncondit 3399 off - Unconditionally disable mitigation
3537 3400
3538 On MDS or TAA affecte 3401 On MDS or TAA affected machines,
3539 mmio_stale_data=off c 3402 mmio_stale_data=off can be prevented by an active
3540 MDS or TAA mitigation 3403 MDS or TAA mitigation as these vulnerabilities are
3541 mitigated with the sa 3404 mitigated with the same mechanism so in order to
3542 disable this mitigati 3405 disable this mitigation, you need to specify
3543 mds=off and tsx_async 3406 mds=off and tsx_async_abort=off too.
3544 3407
3545 Not specifying this o 3408 Not specifying this option is equivalent to
3546 mmio_stale_data=full. 3409 mmio_stale_data=full.
3547 3410
3548 For details see: 3411 For details see:
3549 Documentation/admin-g 3412 Documentation/admin-guide/hw-vuln/processor_mmio_stale_data.rst
3550 3413
3551 <module>.async_probe[=<bool>] [KNL] 3414 <module>.async_probe[=<bool>] [KNL]
3552 If no <bool> value is 3415 If no <bool> value is specified or if the value
3553 specified is not a va 3416 specified is not a valid <bool>, enable asynchronous
3554 probe on this module. 3417 probe on this module. Otherwise, enable/disable
3555 asynchronous probe on 3418 asynchronous probe on this module as indicated by the
3556 <bool> value. See als 3419 <bool> value. See also: module.async_probe
3557 3420
3558 module.async_probe=<bool> 3421 module.async_probe=<bool>
3559 [KNL] When set to tru 3422 [KNL] When set to true, modules will use async probing
3560 by default. To enable 3423 by default. To enable/disable async probing for a
3561 specific module, use 3424 specific module, use the module specific control that
3562 is documented under < 3425 is documented under <module>.async_probe. When both
3563 module.async_probe an 3426 module.async_probe and <module>.async_probe are
3564 specified, <module>.a 3427 specified, <module>.async_probe takes precedence for
3565 the specific module. 3428 the specific module.
3566 3429
3567 module.enable_dups_trace 3430 module.enable_dups_trace
3568 [KNL] When CONFIG_MOD 3431 [KNL] When CONFIG_MODULE_DEBUG_AUTOLOAD_DUPS is set,
3569 this means that dupli 3432 this means that duplicate request_module() calls will
3570 trigger a WARN_ON() i 3433 trigger a WARN_ON() instead of a pr_warn(). Note that
3571 if MODULE_DEBUG_AUTOL 3434 if MODULE_DEBUG_AUTOLOAD_DUPS_TRACE is set, WARN_ON()s
3572 will always be issued 3435 will always be issued and this option does nothing.
3573 module.sig_enforce 3436 module.sig_enforce
3574 [KNL] When CONFIG_MOD 3437 [KNL] When CONFIG_MODULE_SIG is set, this means that
3575 modules without (vali 3438 modules without (valid) signatures will fail to load.
3576 Note that if CONFIG_M 3439 Note that if CONFIG_MODULE_SIG_FORCE is set, that
3577 is always true, so th 3440 is always true, so this option does nothing.
3578 3441
3579 module_blacklist= [KNL] Do not load 3442 module_blacklist= [KNL] Do not load a comma-separated list of
3580 modules. Useful for 3443 modules. Useful for debugging problem modules.
3581 3444
3582 mousedev.tap_time= 3445 mousedev.tap_time=
3583 [MOUSE] Maximum time 3446 [MOUSE] Maximum time between finger touching and
3584 leaving touchpad surf 3447 leaving touchpad surface for touch to be considered
3585 a tap and be reported 3448 a tap and be reported as a left button click (for
3586 touchpads working in 3449 touchpads working in absolute mode only).
3587 Format: <msecs> 3450 Format: <msecs>
3588 mousedev.xres= [MOUSE] Horizontal sc 3451 mousedev.xres= [MOUSE] Horizontal screen resolution, used for devices
3589 reporting absolute co 3452 reporting absolute coordinates, such as tablets
3590 mousedev.yres= [MOUSE] Vertical scre 3453 mousedev.yres= [MOUSE] Vertical screen resolution, used for devices
3591 reporting absolute co 3454 reporting absolute coordinates, such as tablets
3592 3455
3593 movablecore= [KNL,X86,PPC,EARLY] !! 3456 movablecore= [KNL,X86,IA-64,PPC]
3594 Format: nn[KMGTPE] | 3457 Format: nn[KMGTPE] | nn%
3595 This parameter is the 3458 This parameter is the complement to kernelcore=, it
3596 specifies the amount 3459 specifies the amount of memory used for migratable
3597 allocations. If both 3460 allocations. If both kernelcore and movablecore is
3598 specified, then kerne 3461 specified, then kernelcore will be at *least* the
3599 specified value but m 3462 specified value but may be more. If movablecore on its
3600 own is specified, the 3463 own is specified, the administrator must be careful
3601 that the amount of me 3464 that the amount of memory usable for all allocations
3602 is not too small. 3465 is not too small.
3603 3466
3604 movable_node [KNL,EARLY] Boot-time !! 3467 movable_node [KNL] Boot-time switch to make hotplugable memory
3605 NUMA nodes to be mova 3468 NUMA nodes to be movable. This means that the memory
3606 of such nodes will be 3469 of such nodes will be usable only for movable
3607 allocations which rul 3470 allocations which rules out almost all kernel
3608 allocations. Use with 3471 allocations. Use with caution!
3609 3472
3610 MTD_Partition= [MTD] 3473 MTD_Partition= [MTD]
3611 Format: <name>,<regio 3474 Format: <name>,<region-number>,<size>,<offset>
3612 3475
3613 MTD_Region= [MTD] Format: 3476 MTD_Region= [MTD] Format:
3614 <name>,<region-number 3477 <name>,<region-number>[,<base>,<size>,<buswidth>,<altbuswidth>]
3615 3478
3616 mtdparts= [MTD] 3479 mtdparts= [MTD]
3617 See drivers/mtd/parse 3480 See drivers/mtd/parsers/cmdlinepart.c
3618 3481
>> 3482 mtdset= [ARM]
>> 3483 ARM/S3C2412 JIVE boot control
>> 3484
>> 3485 See arch/arm/mach-s3c/mach-jive.c
>> 3486
3619 mtouchusb.raw_coordinates= 3487 mtouchusb.raw_coordinates=
3620 [HW] Make the MicroTo 3488 [HW] Make the MicroTouch USB driver use raw coordinates
3621 ('y', default) or coo 3489 ('y', default) or cooked coordinates ('n')
3622 3490
3623 mtrr=debug [X86,EARLY] !! 3491 mtrr=debug [X86]
3624 Enable printing debug 3492 Enable printing debug information related to MTRR
3625 registers at boot tim 3493 registers at boot time.
3626 3494
3627 mtrr_chunk_size=nn[KMG,X86,EARLY] !! 3495 mtrr_chunk_size=nn[KMG] [X86]
3628 used for mtrr cleanup 3496 used for mtrr cleanup. It is largest continuous chunk
3629 that could hold holes 3497 that could hold holes aka. UC entries.
3630 3498
3631 mtrr_gran_size=nn[KMG,X86,EARLY] !! 3499 mtrr_gran_size=nn[KMG] [X86]
3632 Used for mtrr cleanup 3500 Used for mtrr cleanup. It is granularity of mtrr block.
3633 Default is 1. 3501 Default is 1.
3634 Large value could pre 3502 Large value could prevent small alignment from
3635 using up MTRRs. 3503 using up MTRRs.
3636 3504
3637 mtrr_spare_reg_nr=n [X86,EARLY] !! 3505 mtrr_spare_reg_nr=n [X86]
3638 Format: <integer> 3506 Format: <integer>
3639 Range: 0,7 : spare re 3507 Range: 0,7 : spare reg number
3640 Default : 1 3508 Default : 1
3641 Used for mtrr cleanup 3509 Used for mtrr cleanup. It is spare mtrr entries number.
3642 Set to 2 or more if y 3510 Set to 2 or more if your graphical card needs more.
3643 3511
3644 multitce=off [PPC] This parameter 3512 multitce=off [PPC] This parameter disables the use of the pSeries
3645 firmware feature for 3513 firmware feature for updating multiple TCE entries
3646 at a time. 3514 at a time.
3647 3515
3648 n2= [NET] SDL Inc. RISCom 3516 n2= [NET] SDL Inc. RISCom/N2 synchronous serial card
3649 3517
3650 netdev= [NET] Network devices 3518 netdev= [NET] Network devices parameters
3651 Format: <irq>,<io>,<m 3519 Format: <irq>,<io>,<mem_start>,<mem_end>,<name>
3652 Note that mem_start i 3520 Note that mem_start is often overloaded to mean
3653 something different a 3521 something different and driver-specific.
3654 This usage is only do 3522 This usage is only documented in each driver source
3655 file if at all. 3523 file if at all.
3656 3524
3657 netpoll.carrier_timeout= 3525 netpoll.carrier_timeout=
3658 [NET] Specifies amoun 3526 [NET] Specifies amount of time (in seconds) that
3659 netpoll should wait f 3527 netpoll should wait for a carrier. By default netpoll
3660 waits 4 seconds. 3528 waits 4 seconds.
3661 3529
3662 nf_conntrack.acct= 3530 nf_conntrack.acct=
3663 [NETFILTER] Enable co 3531 [NETFILTER] Enable connection tracking flow accounting
3664 0 to disable accounti 3532 0 to disable accounting
3665 1 to enable accountin 3533 1 to enable accounting
3666 Default value is 0. 3534 Default value is 0.
3667 3535
3668 nfs.cache_getent= 3536 nfs.cache_getent=
3669 [NFS] sets the pathna 3537 [NFS] sets the pathname to the program which is used
3670 to update the NFS cli 3538 to update the NFS client cache entries.
3671 3539
3672 nfs.cache_getent_timeout= 3540 nfs.cache_getent_timeout=
3673 [NFS] sets the timeou 3541 [NFS] sets the timeout after which an attempt to
3674 update a cache entry 3542 update a cache entry is deemed to have failed.
3675 3543
3676 nfs.callback_nr_threads= 3544 nfs.callback_nr_threads=
3677 [NFSv4] set the total 3545 [NFSv4] set the total number of threads that the
3678 NFS client will assig 3546 NFS client will assign to service NFSv4 callback
3679 requests. 3547 requests.
3680 3548
3681 nfs.callback_tcpport= 3549 nfs.callback_tcpport=
3682 [NFS] set the TCP por 3550 [NFS] set the TCP port on which the NFSv4 callback
3683 channel should listen 3551 channel should listen.
3684 3552
3685 nfs.delay_retrans= <<
3686 [NFS] specifies the n <<
3687 retries the request b <<
3688 after a reply of NFS4 <<
3689 Only applies if the s <<
3690 and the specified val <<
3691 <<
3692 nfs.enable_ino64= 3553 nfs.enable_ino64=
3693 [NFS] enable 64-bit i 3554 [NFS] enable 64-bit inode numbers.
3694 If zero, the NFS clie 3555 If zero, the NFS client will fake up a 32-bit inode
3695 number for the readdi 3556 number for the readdir() and stat() syscalls instead
3696 of returning the full 3557 of returning the full 64-bit number.
3697 The default is to ret 3558 The default is to return 64-bit inode numbers.
3698 3559
3699 nfs.idmap_cache_timeout= 3560 nfs.idmap_cache_timeout=
3700 [NFS] set the maximum 3561 [NFS] set the maximum lifetime for idmapper cache
3701 entries. 3562 entries.
3702 3563
3703 nfs.max_session_cb_slots= 3564 nfs.max_session_cb_slots=
3704 [NFSv4.1] Sets the ma 3565 [NFSv4.1] Sets the maximum number of session
3705 slots the client will 3566 slots the client will assign to the callback
3706 channel. This determi 3567 channel. This determines the maximum number of
3707 callbacks the client 3568 callbacks the client will process in parallel for
3708 a particular server. 3569 a particular server.
3709 3570
3710 nfs.max_session_slots= 3571 nfs.max_session_slots=
3711 [NFSv4.1] Sets the ma 3572 [NFSv4.1] Sets the maximum number of session slots
3712 the client will attem 3573 the client will attempt to negotiate with the server.
3713 This limits the numbe 3574 This limits the number of simultaneous RPC requests
3714 that the client can s 3575 that the client can send to the NFSv4.1 server.
3715 Note that there is li 3576 Note that there is little point in setting this
3716 value higher than the 3577 value higher than the max_tcp_slot_table_limit.
3717 3578
3718 nfs.nfs4_disable_idmapping= 3579 nfs.nfs4_disable_idmapping=
3719 [NFSv4] When set to t 3580 [NFSv4] When set to the default of '1', this option
3720 ensures that both the 3581 ensures that both the RPC level authentication
3721 scheme and the NFS le 3582 scheme and the NFS level operations agree to use
3722 numeric uids/gids if 3583 numeric uids/gids if the mount is using the
3723 'sec=sys' security fl 3584 'sec=sys' security flavour. In effect it is
3724 disabling idmapping, 3585 disabling idmapping, which can make migration from
3725 legacy NFSv2/v3 syste 3586 legacy NFSv2/v3 systems to NFSv4 easier.
3726 Servers that do not s 3587 Servers that do not support this mode of operation
3727 will be autodetected 3588 will be autodetected by the client, and it will fall
3728 back to using the idm 3589 back to using the idmapper.
3729 To turn off this beha 3590 To turn off this behaviour, set the value to '0'.
3730 3591
3731 nfs.nfs4_unique_id= 3592 nfs.nfs4_unique_id=
3732 [NFS4] Specify an add 3593 [NFS4] Specify an additional fixed unique ident-
3733 ification string that 3594 ification string that NFSv4 clients can insert into
3734 their nfs_client_id4 3595 their nfs_client_id4 string. This is typically a
3735 UUID that is generate 3596 UUID that is generated at system install time.
3736 3597
3737 nfs.recover_lost_locks= 3598 nfs.recover_lost_locks=
3738 [NFSv4] Attempt to re 3599 [NFSv4] Attempt to recover locks that were lost due
3739 to a lease timeout on 3600 to a lease timeout on the server. Please note that
3740 doing this risks data 3601 doing this risks data corruption, since there are
3741 no guarantees that th 3602 no guarantees that the file will remain unchanged
3742 after the locks are l 3603 after the locks are lost.
3743 If you want to enable 3604 If you want to enable the kernel legacy behaviour of
3744 attempting to recover 3605 attempting to recover these locks, then set this
3745 parameter to '1'. 3606 parameter to '1'.
3746 The default parameter 3607 The default parameter value of '0' causes the kernel
3747 not to attempt recove 3608 not to attempt recovery of lost locks.
3748 3609
3749 nfs.send_implementation_id= 3610 nfs.send_implementation_id=
3750 [NFSv4.1] Send client 3611 [NFSv4.1] Send client implementation identification
3751 information in exchan 3612 information in exchange_id requests.
3752 If zero, no implement 3613 If zero, no implementation identification information
3753 will be sent. 3614 will be sent.
3754 The default is to sen 3615 The default is to send the implementation identification
3755 information. 3616 information.
3756 3617
3757 nfs4.layoutstats_timer= 3618 nfs4.layoutstats_timer=
3758 [NFSv4.2] Change the 3619 [NFSv4.2] Change the rate at which the kernel sends
3759 layoutstats to the pN 3620 layoutstats to the pNFS metadata server.
3760 3621
3761 Setting this to value 3622 Setting this to value to 0 causes the kernel to use
3762 whatever value is the 3623 whatever value is the default set by the layout
3763 driver. A non-zero va 3624 driver. A non-zero value sets the minimum interval
3764 in seconds between la 3625 in seconds between layoutstats transmissions.
3765 3626
3766 nfsd.inter_copy_offload_enable= 3627 nfsd.inter_copy_offload_enable=
3767 [NFSv4.2] When set to 3628 [NFSv4.2] When set to 1, the server will support
3768 server-to-server copi 3629 server-to-server copies for which this server is
3769 the destination of th 3630 the destination of the copy.
3770 3631
3771 nfsd.nfs4_disable_idmapping= 3632 nfsd.nfs4_disable_idmapping=
3772 [NFSv4] When set to t 3633 [NFSv4] When set to the default of '1', the NFSv4
3773 server will return on 3634 server will return only numeric uids and gids to
3774 clients using auth_sy 3635 clients using auth_sys, and will accept numeric uids
3775 and gids from such cl 3636 and gids from such clients. This is intended to ease
3776 migration from NFSv2/ 3637 migration from NFSv2/v3.
3777 3638
3778 nfsd.nfsd4_ssc_umount_timeout= 3639 nfsd.nfsd4_ssc_umount_timeout=
3779 [NFSv4.2] When used a 3640 [NFSv4.2] When used as the destination of a
3780 server-to-server copy 3641 server-to-server copy, knfsd temporarily mounts
3781 the source server. I 3642 the source server. It caches the mount in case
3782 it will be needed aga 3643 it will be needed again, and discards it if not
3783 used for the number o 3644 used for the number of milliseconds specified by
3784 this parameter. 3645 this parameter.
3785 3646
3786 nfsaddrs= [NFS] Deprecated. Us 3647 nfsaddrs= [NFS] Deprecated. Use ip= instead.
3787 See Documentation/adm 3648 See Documentation/admin-guide/nfs/nfsroot.rst.
3788 3649
3789 nfsroot= [NFS] nfs root filesy 3650 nfsroot= [NFS] nfs root filesystem for disk-less boxes.
3790 See Documentation/adm 3651 See Documentation/admin-guide/nfs/nfsroot.rst.
3791 3652
3792 nfsrootdebug [NFS] enable nfsroot 3653 nfsrootdebug [NFS] enable nfsroot debugging messages.
3793 See Documentation/adm 3654 See Documentation/admin-guide/nfs/nfsroot.rst.
3794 3655
3795 nmi_backtrace.backtrace_idle [KNL] 3656 nmi_backtrace.backtrace_idle [KNL]
3796 Dump stacks even of i 3657 Dump stacks even of idle CPUs in response to an
3797 NMI stack-backtrace r 3658 NMI stack-backtrace request.
3798 3659
3799 nmi_debug= [KNL,SH] Specify one 3660 nmi_debug= [KNL,SH] Specify one or more actions to take
3800 when a NMI is trigger 3661 when a NMI is triggered.
3801 Format: [state][,regs 3662 Format: [state][,regs][,debounce][,die]
3802 3663
3803 nmi_watchdog= [KNL,BUGS=X86] Debugg 3664 nmi_watchdog= [KNL,BUGS=X86] Debugging features for SMP kernels
3804 Format: [panic,][nopa !! 3665 Format: [panic,][nopanic,][num]
3805 Valid num: 0 or 1 3666 Valid num: 0 or 1
3806 0 - turn hardlockup d 3667 0 - turn hardlockup detector in nmi_watchdog off
3807 1 - turn hardlockup d 3668 1 - turn hardlockup detector in nmi_watchdog on
3808 rNNN - configure the <<
3809 <<
3810 When panic is specifi 3669 When panic is specified, panic when an NMI watchdog
3811 timeout occurs (or 'n 3670 timeout occurs (or 'nopanic' to not panic on an NMI
3812 watchdog, if CONFIG_B 3671 watchdog, if CONFIG_BOOTPARAM_HARDLOCKUP_PANIC is set)
3813 To disable both hard 3672 To disable both hard and soft lockup detectors,
3814 please see 'nowatchdo 3673 please see 'nowatchdog'.
3815 This is useful when y 3674 This is useful when you use a panic=... timeout and
3816 need the box quickly 3675 need the box quickly up again.
3817 3676
3818 These settings can be 3677 These settings can be accessed at runtime via
3819 the nmi_watchdog and 3678 the nmi_watchdog and hardlockup_panic sysctls.
3820 3679
3821 no387 [BUGS=X86-32] Tells t 3680 no387 [BUGS=X86-32] Tells the kernel to use the 387 maths
3822 emulation library eve 3681 emulation library even if a 387 maths coprocessor
3823 is present. 3682 is present.
3824 3683
3825 no4lvl [RISCV,EARLY] Disable !! 3684 no4lvl [RISCV] Disable 4-level and 5-level paging modes. Forces
3826 Forces kernel to use !! 3685 kernel to use 3-level paging instead.
3827 3686
3828 no5lvl [X86-64,RISCV,EARLY] !! 3687 no5lvl [X86-64,RISCV] Disable 5-level paging mode. Forces
3829 kernel to use 4-level 3688 kernel to use 4-level paging instead.
3830 3689
>> 3690 noaliencache [MM, NUMA, SLAB] Disables the allocation of alien
>> 3691 caches in the slab allocator. Saves per-node memory,
>> 3692 but will impact performance.
>> 3693
3831 noalign [KNL,ARM] 3694 noalign [KNL,ARM]
3832 3695
3833 noapic [SMP,APIC,EARLY] Tell !! 3696 noaltinstr [S390] Disables alternative instructions patching
>> 3697 (CPU alternatives feature).
>> 3698
>> 3699 noapic [SMP,APIC] Tells the kernel to not make use of any
3834 IOAPICs that may be p 3700 IOAPICs that may be present in the system.
3835 3701
3836 noautogroup Disable scheduler aut 3702 noautogroup Disable scheduler automatic task group creation.
3837 3703
3838 nocache [ARM,EARLY] !! 3704 nocache [ARM]
3839 3705
3840 no_console_suspend 3706 no_console_suspend
3841 [HW] Never suspend th 3707 [HW] Never suspend the console
3842 Disable suspending of 3708 Disable suspending of consoles during suspend and
3843 hibernate operations. 3709 hibernate operations. Once disabled, debugging
3844 messages can reach va 3710 messages can reach various consoles while the rest
3845 of the system is bein 3711 of the system is being put to sleep (ie, while
3846 debugging driver susp 3712 debugging driver suspend/resume hooks). This may
3847 not work reliably wit 3713 not work reliably with all consoles, but is known
3848 to work with serial a 3714 to work with serial and VGA consoles.
3849 To facilitate more fl 3715 To facilitate more flexible debugging, we also add
3850 console_suspend, a pr 3716 console_suspend, a printk module parameter to control
3851 it. Users could use c 3717 it. Users could use console_suspend (usually
3852 /sys/module/printk/pa 3718 /sys/module/printk/parameters/console_suspend) to
3853 turn on/off it dynami 3719 turn on/off it dynamically.
3854 3720
3855 no_debug_objects 3721 no_debug_objects
3856 [KNL,EARLY] Disable o !! 3722 [KNL] Disable object debugging
3857 3723
3858 nodsp [SH] Disable hardware 3724 nodsp [SH] Disable hardware DSP at boot time.
3859 3725
3860 noefi [EFI,EARLY] Disable E !! 3726 noefi Disable EFI runtime services support.
>> 3727
>> 3728 no_entry_flush [PPC] Don't flush the L1-D cache when entering the kernel.
3861 3729
3862 no_entry_flush [PPC,EARLY] Don't flu !! 3730 noexec [IA-64]
3863 3731
3864 noexec32 [X86-64] 3732 noexec32 [X86-64]
3865 This affects only 32- 3733 This affects only 32-bit executables.
3866 noexec32=on: enable n 3734 noexec32=on: enable non-executable mappings (default)
3867 read doesn't 3735 read doesn't imply executable mappings
3868 noexec32=off: disable 3736 noexec32=off: disable non-executable mappings
3869 read implies 3737 read implies executable mappings
3870 3738
3871 no_file_caps Tells the kernel not 3739 no_file_caps Tells the kernel not to honor file capabilities. The
3872 only way then for a f 3740 only way then for a file to be executed with privilege
3873 is to be setuid root 3741 is to be setuid root or executed by root.
3874 3742
3875 nofpu [MIPS,SH] Disable har 3743 nofpu [MIPS,SH] Disable hardware FPU at boot time.
3876 3744
3877 nofsgsbase [X86] Disables FSGSBA 3745 nofsgsbase [X86] Disables FSGSBASE instructions.
3878 3746
3879 nofxsr [BUGS=X86-32] Disable 3747 nofxsr [BUGS=X86-32] Disables x86 floating point extended
3880 register save and res 3748 register save and restore. The kernel will only save
3881 legacy floating-point 3749 legacy floating-point registers on task switch.
3882 3750
>> 3751 nohalt [IA-64] Tells the kernel not to use the power saving
>> 3752 function PAL_HALT_LIGHT when idle. This increases
>> 3753 power-consumption. On the positive side, it reduces
>> 3754 interrupt wake-up latency, which may improve performance
>> 3755 in certain environments such as networked servers or
>> 3756 real-time systems.
>> 3757
3883 no_hash_pointers 3758 no_hash_pointers
3884 [KNL,EARLY] <<
3885 Force pointers printe 3759 Force pointers printed to the console or buffers to be
3886 unhashed. By default 3760 unhashed. By default, when a pointer is printed via %p
3887 format string, that p 3761 format string, that pointer is "hashed", i.e. obscured
3888 by hashing the pointe 3762 by hashing the pointer value. This is a security feature
3889 that hides actual ker 3763 that hides actual kernel addresses from unprivileged
3890 users, but it also ma 3764 users, but it also makes debugging the kernel more
3891 difficult since unequ 3765 difficult since unequal pointers can no longer be
3892 compared. However, i 3766 compared. However, if this command-line option is
3893 specified, then all n 3767 specified, then all normal pointers will have their true
3894 value printed. This o 3768 value printed. This option should only be specified when
3895 debugging the kernel. 3769 debugging the kernel. Please do not use on production
3896 kernels. 3770 kernels.
3897 3771
3898 nohibernate [HIBERNATION] Disable 3772 nohibernate [HIBERNATION] Disable hibernation and resume.
3899 3773
3900 nohlt [ARM,ARM64,MICROBLAZE !! 3774 nohlt [ARM,ARM64,MICROBLAZE,MIPS,PPC,SH] Forces the kernel to
3901 busy wait in do_idle( 3775 busy wait in do_idle() and not use the arch_cpu_idle()
3902 implementation; requi 3776 implementation; requires CONFIG_GENERIC_IDLE_POLL_SETUP
3903 to be effective. This 3777 to be effective. This is useful on platforms where the
3904 sleep(SH) or wfi(ARM, 3778 sleep(SH) or wfi(ARM,ARM64) instructions do not work
3905 correctly or when doi 3779 correctly or when doing power measurements to evaluate
3906 the impact of the sle 3780 the impact of the sleep instructions. This is also
3907 useful when using JTA 3781 useful when using JTAG debugger.
3908 3782
3909 nohugeiomap [KNL,X86,PPC,ARM64,EA !! 3783 nohugeiomap [KNL,X86,PPC,ARM64] Disable kernel huge I/O mappings.
3910 3784
3911 nohugevmalloc [KNL,X86,PPC,ARM64,EA !! 3785 nohugevmalloc [KNL,X86,PPC,ARM64] Disable kernel huge vmalloc mappings.
3912 3786
3913 nohz= [KNL] Boottime enable 3787 nohz= [KNL] Boottime enable/disable dynamic ticks
3914 Valid arguments: on, 3788 Valid arguments: on, off
3915 Default: on 3789 Default: on
3916 3790
3917 nohz_full= [KNL,BOOT,SMP,ISOL] 3791 nohz_full= [KNL,BOOT,SMP,ISOL]
3918 The argument is a cpu 3792 The argument is a cpu list, as described above.
3919 In kernels built with 3793 In kernels built with CONFIG_NO_HZ_FULL=y, set
3920 the specified list of 3794 the specified list of CPUs whose tick will be stopped
3921 whenever possible. Th 3795 whenever possible. The boot CPU will be forced outside
3922 the range to maintain 3796 the range to maintain the timekeeping. Any CPUs
3923 in this list will hav 3797 in this list will have their RCU callbacks offloaded,
3924 just as if they had a 3798 just as if they had also been called out in the
3925 rcu_nocbs= boot param 3799 rcu_nocbs= boot parameter.
3926 3800
3927 Note that this argume 3801 Note that this argument takes precedence over
3928 the CONFIG_RCU_NOCB_C 3802 the CONFIG_RCU_NOCB_CPU_DEFAULT_ALL option.
3929 3803
3930 noinitrd [RAM] Tells the kerne 3804 noinitrd [RAM] Tells the kernel not to load any configured
3931 initial RAM disk. 3805 initial RAM disk.
3932 3806
3933 nointremap [X86-64,Intel-IOMMU,E !! 3807 nointremap [X86-64, Intel-IOMMU] Do not enable interrupt
3934 remapping. 3808 remapping.
3935 [Deprecated - use int 3809 [Deprecated - use intremap=off]
3936 3810
3937 noinvpcid [X86,EARLY] Disable t !! 3811 nointroute [IA-64]
>> 3812
>> 3813 noinvpcid [X86] Disable the INVPCID cpu feature.
3938 3814
3939 noiotrap [SH] Disables trapped 3815 noiotrap [SH] Disables trapped I/O port accesses.
3940 3816
3941 noirqdebug [X86-32] Disables the 3817 noirqdebug [X86-32] Disables the code which attempts to detect and
3942 disable unhandled int 3818 disable unhandled interrupt sources.
3943 3819
3944 noisapnp [ISAPNP] Disables ISA 3820 noisapnp [ISAPNP] Disables ISA PnP code.
3945 3821
3946 nokaslr [KNL,EARLY] !! 3822 nojitter [IA-64] Disables jitter checking for ITC timers.
>> 3823
>> 3824 nokaslr [KNL]
3947 When CONFIG_RANDOMIZE 3825 When CONFIG_RANDOMIZE_BASE is set, this disables
3948 kernel and module bas 3826 kernel and module base offset ASLR (Address Space
3949 Layout Randomization) 3827 Layout Randomization).
3950 3828
3951 no-kvmapf [X86,KVM,EARLY] Disab !! 3829 no-kvmapf [X86,KVM] Disable paravirtualized asynchronous page
3952 fault handling. 3830 fault handling.
3953 3831
3954 no-kvmclock [X86,KVM,EARLY] Disab !! 3832 no-kvmclock [X86,KVM] Disable paravirtualized KVM clock driver
>> 3833
>> 3834 nolapic [X86-32,APIC] Do not enable or use the local APIC.
3955 3835
3956 nolapic [X86-32,APIC,EARLY] D !! 3836 nolapic_timer [X86-32,APIC] Do not use the local APIC timer.
3957 3837
3958 nolapic_timer [X86-32,APIC,EARLY] D !! 3838 nomca [IA-64] Disable machine check abort handling
3959 3839
3960 nomce [X86-32] Disable Mach 3840 nomce [X86-32] Disable Machine Check Exception
3961 3841
3962 nomfgpt [X86-32] Disable Mult 3842 nomfgpt [X86-32] Disable Multi-Function General Purpose
3963 Timer usage (for AMD 3843 Timer usage (for AMD Geode machines).
3964 3844
3965 nomodeset Disable kernel modese 3845 nomodeset Disable kernel modesetting. Most systems' firmware
3966 sets up a display mod 3846 sets up a display mode and provides framebuffer memory
3967 for output. With nomo 3847 for output. With nomodeset, DRM and fbdev drivers will
3968 not load if they coul 3848 not load if they could possibly displace the pre-
3969 initialized output. O 3849 initialized output. Only the system framebuffer will
3970 be available for use. 3850 be available for use. The respective drivers will not
3971 perform display-mode 3851 perform display-mode changes or accelerated rendering.
3972 3852
3973 Useful as error fallb 3853 Useful as error fallback, or for testing and debugging.
3974 3854
3975 nomodule Disable module load 3855 nomodule Disable module load
3976 3856
3977 nonmi_ipi [X86] Disable using N 3857 nonmi_ipi [X86] Disable using NMI IPIs during panic/reboot to
3978 shutdown the other cp 3858 shutdown the other cpus. Instead use the REBOOT_VECTOR
3979 irq. 3859 irq.
3980 3860
3981 nopat [X86,EARLY] Disable P !! 3861 nopat [X86] Disable PAT (page attribute table extension of
3982 pagetables) support. 3862 pagetables) support.
3983 3863
3984 nopcid [X86-64,EARLY] Disabl !! 3864 nopcid [X86-64] Disable the PCID cpu feature.
3985 3865
3986 nopku [X86] Disable Memory 3866 nopku [X86] Disable Memory Protection Keys CPU feature found
3987 in some Intel CPUs. 3867 in some Intel CPUs.
3988 3868
3989 nopti [X86-64,EARLY] !! 3869 nopti [X86-64]
3990 Equivalent to pti=off 3870 Equivalent to pti=off
3991 3871
3992 nopv= [X86,XEN,KVM,HYPER_V, !! 3872 nopv= [X86,XEN,KVM,HYPER_V,VMWARE]
3993 Disables the PV optim 3873 Disables the PV optimizations forcing the guest to run
3994 as generic guest with 3874 as generic guest with no PV drivers. Currently support
3995 XEN HVM, KVM, HYPER_V 3875 XEN HVM, KVM, HYPER_V and VMWARE guest.
3996 3876
3997 nopvspin [X86,XEN,KVM,EARLY] !! 3877 nopvspin [X86,XEN,KVM]
3998 Disables the qspinloc 3878 Disables the qspinlock slow path using PV optimizations
3999 which allow the hyper 3879 which allow the hypervisor to 'idle' the guest on lock
4000 contention. 3880 contention.
4001 3881
4002 norandmaps Don't use address spa 3882 norandmaps Don't use address space randomization. Equivalent to
4003 echo 0 > /proc/sys/ke 3883 echo 0 > /proc/sys/kernel/randomize_va_space
4004 3884
4005 noreplace-smp [X86-32,SMP] Don't re 3885 noreplace-smp [X86-32,SMP] Don't replace SMP instructions
4006 with UP alternatives 3886 with UP alternatives
4007 3887
4008 noresume [SWSUSP] Disables res 3888 noresume [SWSUSP] Disables resume and restores original swap
4009 space. 3889 space.
4010 3890
>> 3891 nosbagart [IA-64]
>> 3892
4011 no-scroll [VGA] Disables scroll 3893 no-scroll [VGA] Disables scrollback.
4012 This is required for 3894 This is required for the Braillex ib80-piezo Braille
4013 reader made by F.H. P 3895 reader made by F.H. Papenmeier (Germany).
4014 3896
4015 nosgx [X86-64,SGX,EARLY] Di !! 3897 nosgx [X86-64,SGX] Disables Intel SGX kernel support.
4016 3898
4017 nosmap [PPC,EARLY] !! 3899 nosmap [PPC]
4018 Disable SMAP (Supervi 3900 Disable SMAP (Supervisor Mode Access Prevention)
4019 even if it is support 3901 even if it is supported by processor.
4020 3902
4021 nosmep [PPC64s,EARLY] !! 3903 nosmep [PPC64s]
4022 Disable SMEP (Supervi 3904 Disable SMEP (Supervisor Mode Execution Prevention)
4023 even if it is support 3905 even if it is supported by processor.
4024 3906
4025 nosmp [SMP,EARLY] Tells an !! 3907 nosmp [SMP] Tells an SMP kernel to act as a UP kernel,
4026 and disable the IO AP 3908 and disable the IO APIC. legacy for "maxcpus=0".
4027 3909
4028 nosmt [KNL,MIPS,PPC,S390,EA !! 3910 nosmt [KNL,MIPS,PPC,S390] Disable symmetric multithreading (SMT).
4029 Equivalent to smt=1. 3911 Equivalent to smt=1.
4030 3912
4031 [KNL,X86,PPC] Disable 3913 [KNL,X86,PPC] Disable symmetric multithreading (SMT).
4032 nosmt=force: Force di 3914 nosmt=force: Force disable SMT, cannot be undone
4033 via the 3915 via the sysfs control file.
4034 3916
4035 nosoftlockup [KNL] Disable the sof 3917 nosoftlockup [KNL] Disable the soft-lockup detector.
4036 3918
4037 nospec_store_bypass_disable 3919 nospec_store_bypass_disable
4038 [HW,EARLY] Disable al !! 3920 [HW] Disable all mitigations for the Speculative Store Bypass vulnerability
4039 Store Bypass vulnerab <<
4040 3921
4041 nospectre_bhb [ARM64,EARLY] Disable !! 3922 nospectre_bhb [ARM64] Disable all mitigations for Spectre-BHB (branch
4042 history injection) vu 3923 history injection) vulnerability. System may allow data leaks
4043 with this option. 3924 with this option.
4044 3925
4045 nospectre_v1 [X86,PPC,EARLY] Disab !! 3926 nospectre_v1 [X86,PPC] Disable mitigations for Spectre Variant 1
4046 (bounds check bypass) 3927 (bounds check bypass). With this option data leaks are
4047 possible in the syste 3928 possible in the system.
4048 3929
4049 nospectre_v2 [X86,PPC_E500,ARM64,E !! 3930 nospectre_v2 [X86,PPC_E500,ARM64] Disable all mitigations for
4050 for the Spectre varia !! 3931 the Spectre variant 2 (indirect branch prediction)
4051 prediction) vulnerabi !! 3932 vulnerability. System may allow data leaks with this
4052 leaks with this optio !! 3933 option.
4053 !! 3934
4054 no-steal-acc [X86,PV_OPS,ARM64,PPC !! 3935 no-steal-acc [X86,PV_OPS,ARM64,PPC/PSERIES] Disable paravirtualized
4055 Disable paravirtualiz !! 3936 steal time accounting. steal time is computed, but
4056 is computed, but won' !! 3937 won't influence scheduler behaviour
4057 3938
4058 nosync [HW,M68K] Disables sy 3939 nosync [HW,M68K] Disables sync negotiation for all devices.
4059 3940
4060 no_timer_check [X86,APIC] Disables t 3941 no_timer_check [X86,APIC] Disables the code which tests for
4061 broken timer IRQ sour 3942 broken timer IRQ sources.
4062 3943
4063 no_uaccess_flush 3944 no_uaccess_flush
4064 [PPC,EARLY] Don't flu !! 3945 [PPC] Don't flush the L1-D cache after accessing user data.
4065 3946
4066 novmcoredd [KNL,KDUMP] 3947 novmcoredd [KNL,KDUMP]
4067 Disable device dump. 3948 Disable device dump. Device dump allows drivers to
4068 append dump data to v 3949 append dump data to vmcore so you can collect driver
4069 specified debug info. 3950 specified debug info. Drivers can append the data
4070 without any limit and 3951 without any limit and this data is stored in memory,
4071 so this may cause sig 3952 so this may cause significant memory stress. Disabling
4072 device dump can help 3953 device dump can help save memory but the driver debug
4073 data will be no longe 3954 data will be no longer available. This parameter
4074 is only available whe 3955 is only available when CONFIG_PROC_VMCORE_DEVICE_DUMP
4075 is set. 3956 is set.
4076 3957
4077 no-vmw-sched-clock 3958 no-vmw-sched-clock
4078 [X86,PV_OPS,EARLY] Di !! 3959 [X86,PV_OPS] Disable paravirtualized VMware scheduler
4079 scheduler clock and u !! 3960 clock and use the default one.
4080 3961
4081 nowatchdog [KNL] Disable both lo 3962 nowatchdog [KNL] Disable both lockup detectors, i.e.
4082 soft-lockup and NMI w 3963 soft-lockup and NMI watchdog (hard-lockup).
4083 3964
4084 nowb [ARM,EARLY] !! 3965 nowb [ARM]
4085 3966
4086 nox2apic [X86-64,APIC,EARLY] D !! 3967 nox2apic [X86-64,APIC] Do not enable x2APIC mode.
4087 3968
4088 NOTE: this parameter 3969 NOTE: this parameter will be ignored on systems with the
4089 LEGACY_XAPIC_DISABLED 3970 LEGACY_XAPIC_DISABLED bit set in the
4090 IA32_XAPIC_DISABLE_ST 3971 IA32_XAPIC_DISABLE_STATUS MSR.
4091 3972
4092 noxsave [BUGS=X86] Disables x 3973 noxsave [BUGS=X86] Disables x86 extended register state save
4093 and restore using xsa 3974 and restore using xsave. The kernel will fallback to
4094 enabling legacy float 3975 enabling legacy floating-point and sse state.
4095 3976
4096 noxsaveopt [X86] Disables xsaveo 3977 noxsaveopt [X86] Disables xsaveopt used in saving x86 extended
4097 register states. The 3978 register states. The kernel will fall back to use
4098 xsave to save the sta 3979 xsave to save the states. By using this parameter,
4099 performance of saving 3980 performance of saving the states is degraded because
4100 xsave doesn't support 3981 xsave doesn't support modified optimization while
4101 xsaveopt supports it 3982 xsaveopt supports it on xsaveopt enabled systems.
4102 3983
4103 noxsaves [X86] Disables xsaves 3984 noxsaves [X86] Disables xsaves and xrstors used in saving and
4104 restoring x86 extende 3985 restoring x86 extended register state in compacted
4105 form of xsave area. T 3986 form of xsave area. The kernel will fall back to use
4106 xsaveopt and xrstor t 3987 xsaveopt and xrstor to save and restore the states
4107 in standard form of x 3988 in standard form of xsave area. By using this
4108 parameter, xsave area 3989 parameter, xsave area per process might occupy more
4109 memory on xsaves enab 3990 memory on xsaves enabled systems.
4110 3991
4111 nr_cpus= [SMP,EARLY] Maximum n !! 3992 nps_mtm_hs_ctr= [KNL,ARC]
>> 3993 This parameter sets the maximum duration, in
>> 3994 cycles, each HW thread of the CTOP can run
>> 3995 without interruptions, before HW switches it.
>> 3996 The actual maximum duration is 16 times this
>> 3997 parameter's value.
>> 3998 Format: integer between 1 and 255
>> 3999 Default: 255
>> 4000
>> 4001 nptcg= [IA-64] Override max number of concurrent global TLB
>> 4002 purges which is reported from either PAL_VM_SUMMARY or
>> 4003 SAL PALO.
>> 4004
>> 4005 nr_cpus= [SMP] Maximum number of processors that an SMP kernel
4112 could support. nr_cp 4006 could support. nr_cpus=n : n >= 1 limits the kernel to
4113 support 'n' processor 4007 support 'n' processors. It could be larger than the
4114 number of already plu 4008 number of already plugged CPU during bootup, later in
4115 runtime you can physi 4009 runtime you can physically add extra cpu until it reaches
4116 n. So during boot up 4010 n. So during boot up some boot time memory for per-cpu
4117 variables need be pre 4011 variables need be pre-allocated for later physical cpu
4118 hot plugging. 4012 hot plugging.
4119 4013
4120 nr_uarts= [SERIAL] maximum numb 4014 nr_uarts= [SERIAL] maximum number of UARTs to be registered.
4121 4015
4122 numa=off [KNL, ARM64, PPC, RIS !! 4016 numa=off [KNL, ARM64, PPC, RISCV, SPARC, X86] Disable NUMA, Only
4123 Disable NUMA, Only se !! 4017 set up a single NUMA node spanning all memory.
4124 spanning all memory. <<
4125 4018
4126 numa_balancing= [KNL,ARM64,PPC,RISCV, 4019 numa_balancing= [KNL,ARM64,PPC,RISCV,S390,X86] Enable or disable automatic
4127 NUMA balancing. 4020 NUMA balancing.
4128 Allowed values are en 4021 Allowed values are enable and disable
4129 4022
4130 numa_zonelist_order= [KNL, BOOT] Sele 4023 numa_zonelist_order= [KNL, BOOT] Select zonelist order for NUMA.
4131 'node', 'default' can 4024 'node', 'default' can be specified
4132 This can be set from 4025 This can be set from sysctl after boot.
4133 See Documentation/adm 4026 See Documentation/admin-guide/sysctl/vm.rst for details.
4134 4027
4135 ohci1394_dma=early [HW,EARLY] en !! 4028 ohci1394_dma=early [HW] enable debugging via the ohci1394 driver.
4136 See Documentation/cor 4029 See Documentation/core-api/debugging-via-ohci1394.rst for more
4137 info. 4030 info.
4138 4031
4139 olpc_ec_timeout= [OLPC] ms delay when 4032 olpc_ec_timeout= [OLPC] ms delay when issuing EC commands
4140 Rather than timing ou 4033 Rather than timing out after 20 ms if an EC
4141 command is not proper 4034 command is not properly ACKed, override the length
4142 of the timeout. We h 4035 of the timeout. We have interrupts disabled while
4143 waiting for the ACK, 4036 waiting for the ACK, so if this is set too high
4144 interrupts *may* be l 4037 interrupts *may* be lost!
4145 4038
4146 omap_mux= [OMAP] Override bootl 4039 omap_mux= [OMAP] Override bootloader pin multiplexing.
4147 Format: <mux_mode0.mo 4040 Format: <mux_mode0.mode_name=value>...
4148 For example, to overr 4041 For example, to override I2C bus2:
4149 omap_mux=i2c2_scl.i2c 4042 omap_mux=i2c2_scl.i2c2_scl=0x100,i2c2_sda.i2c2_sda=0x100
4150 4043
4151 onenand.bdry= [HW,MTD] Flex-OneNAND 4044 onenand.bdry= [HW,MTD] Flex-OneNAND Boundary Configuration
4152 4045
4153 Format: [die0_boundar 4046 Format: [die0_boundary][,die0_lock][,die1_boundary][,die1_lock]
4154 4047
4155 boundary - index of l 4048 boundary - index of last SLC block on Flex-OneNAND.
4156 The remain 4049 The remaining blocks are configured as MLC blocks.
4157 lock - Configure 4050 lock - Configure if Flex-OneNAND boundary should be locked.
4158 Once locke 4051 Once locked, the boundary cannot be changed.
4159 1 indicate 4052 1 indicates lock status, 0 indicates unlock status.
4160 4053
4161 oops=panic [KNL,EARLY] !! 4054 oops=panic Always panic on oopses. Default is to just kill the
4162 Always panic on oopse <<
4163 process, but there is 4055 process, but there is a small probability of
4164 deadlocking the machi 4056 deadlocking the machine.
4165 This will also cause 4057 This will also cause panics on machine check exceptions.
4166 Useful together with 4058 Useful together with panic=30 to trigger a reboot.
4167 4059
4168 page_alloc.shuffle= 4060 page_alloc.shuffle=
4169 [KNL] Boolean flag to 4061 [KNL] Boolean flag to control whether the page allocator
4170 should randomize its !! 4062 should randomize its free lists. The randomization may
4171 used to enable/disabl !! 4063 be automatically enabled if the kernel detects it is
4172 the flag can be read !! 4064 running on a platform with a direct-mapped memory-side
>> 4065 cache, and this parameter can be used to
>> 4066 override/disable that behavior. The state of the flag
>> 4067 can be read from sysfs at:
4173 /sys/module/page_allo 4068 /sys/module/page_alloc/parameters/shuffle.
4174 This parameter is onl <<
4175 4069
4176 page_owner= [KNL,EARLY] Boot-time !! 4070 page_owner= [KNL] Boot-time page_owner enabling option.
4177 Storage of the inform 4071 Storage of the information about who allocated
4178 each page is disabled 4072 each page is disabled in default. With this switch,
4179 we can turn it on. 4073 we can turn it on.
4180 on: enable the featur 4074 on: enable the feature
4181 4075
4182 page_poison= [KNL,EARLY] Boot-time !! 4076 page_poison= [KNL] Boot-time parameter changing the state of
4183 poisoning on the budd 4077 poisoning on the buddy allocator, available with
4184 CONFIG_PAGE_POISONING 4078 CONFIG_PAGE_POISONING=y.
4185 off: turn off poisoni 4079 off: turn off poisoning (default)
4186 on: turn on poisoning 4080 on: turn on poisoning
4187 4081
4188 page_reporting.page_reporting_order= 4082 page_reporting.page_reporting_order=
4189 [KNL] Minimal page re 4083 [KNL] Minimal page reporting order
4190 Format: <integer> 4084 Format: <integer>
4191 Adjust the minimal pa 4085 Adjust the minimal page reporting order. The page
4192 reporting is disabled !! 4086 reporting is disabled when it exceeds MAX_ORDER.
4193 4087
4194 panic= [KNL] Kernel behaviou 4088 panic= [KNL] Kernel behaviour on panic: delay <timeout>
4195 timeout > 0: seconds 4089 timeout > 0: seconds before rebooting
4196 timeout = 0: wait for 4090 timeout = 0: wait forever
4197 timeout < 0: reboot i 4091 timeout < 0: reboot immediately
4198 Format: <timeout> 4092 Format: <timeout>
4199 4093
4200 panic_on_taint= [KNL,EARLY] !! 4094 panic_on_taint= Bitmask for conditionally calling panic() in add_taint()
4201 Bitmask for condition <<
4202 Format: <hex>[,nouser 4095 Format: <hex>[,nousertaint]
4203 Hexadecimal bitmask r 4096 Hexadecimal bitmask representing the set of TAINT flags
4204 that will cause the k 4097 that will cause the kernel to panic when add_taint() is
4205 called with any of th 4098 called with any of the flags in this set.
4206 The optional switch " 4099 The optional switch "nousertaint" can be utilized to
4207 prevent userspace for 4100 prevent userspace forced crashes by writing to sysctl
4208 /proc/sys/kernel/tain 4101 /proc/sys/kernel/tainted any flagset matching with the
4209 bitmask set on panic_ 4102 bitmask set on panic_on_taint.
4210 See Documentation/adm 4103 See Documentation/admin-guide/tainted-kernels.rst for
4211 extra details on the 4104 extra details on the taint flags that users can pick
4212 to compose the bitmas 4105 to compose the bitmask to assign to panic_on_taint.
4213 4106
4214 panic_on_warn=1 panic() instead of WA 4107 panic_on_warn=1 panic() instead of WARN(). Useful to cause kdump
4215 on a WARN(). 4108 on a WARN().
4216 4109
4217 panic_print= Bitmask for printing 4110 panic_print= Bitmask for printing system info when panic happens.
4218 User can chose combin 4111 User can chose combination of the following bits:
4219 bit 0: print all task 4112 bit 0: print all tasks info
4220 bit 1: print system m 4113 bit 1: print system memory info
4221 bit 2: print timer in 4114 bit 2: print timer info
4222 bit 3: print locks in 4115 bit 3: print locks info if CONFIG_LOCKDEP is on
4223 bit 4: print ftrace b 4116 bit 4: print ftrace buffer
4224 bit 5: print all prin 4117 bit 5: print all printk messages in buffer
4225 bit 6: print all CPUs 4118 bit 6: print all CPUs backtrace (if available in the arch)
4226 bit 7: print only tas <<
4227 *Be aware* that this 4119 *Be aware* that this option may print a _lot_ of lines,
4228 so there are risks of 4120 so there are risks of losing older messages in the log.
4229 Use this option caref 4121 Use this option carefully, maybe worth to setup a
4230 bigger log buffer wit 4122 bigger log buffer with "log_buf_len" along with this.
4231 4123
4232 parkbd.port= [HW] Parallel port nu 4124 parkbd.port= [HW] Parallel port number the keyboard adapter is
4233 connected to, default 4125 connected to, default is 0.
4234 Format: <parport#> 4126 Format: <parport#>
4235 parkbd.mode= [HW] Parallel port ke 4127 parkbd.mode= [HW] Parallel port keyboard adapter mode of operation,
4236 0 for XT, 1 for AT (d 4128 0 for XT, 1 for AT (default is AT).
4237 Format: <mode> 4129 Format: <mode>
4238 4130
4239 parport= [HW,PPT] Specify para 4131 parport= [HW,PPT] Specify parallel ports. 0 disables.
4240 Format: { 0 | auto | 4132 Format: { 0 | auto | 0xBBB[,IRQ[,DMA]] }
4241 Use 'auto' to force t 4133 Use 'auto' to force the driver to use any
4242 IRQ/DMA settings dete 4134 IRQ/DMA settings detected (the default is to
4243 ignore detected IRQ/D 4135 ignore detected IRQ/DMA settings because of
4244 possible conflicts). 4136 possible conflicts). You can specify the base
4245 address, IRQ, and DMA 4137 address, IRQ, and DMA settings; IRQ and DMA
4246 should be numbers, or 4138 should be numbers, or 'auto' (for using detected
4247 settings on that part 4139 settings on that particular port), or 'nofifo'
4248 (to avoid using a FIF 4140 (to avoid using a FIFO even if it is detected).
4249 Parallel ports are as 4141 Parallel ports are assigned in the order they
4250 are specified on the 4142 are specified on the command line, starting
4251 with parport0. 4143 with parport0.
4252 4144
4253 parport_init_mode= [HW,PPT] 4145 parport_init_mode= [HW,PPT]
4254 Configure VIA paralle 4146 Configure VIA parallel port to operate in
4255 a specific mode. This 4147 a specific mode. This is necessary on Pegasos
4256 computer where firmwa 4148 computer where firmware has no options for setting
4257 up parallel port mode 4149 up parallel port mode and sets it to spp.
4258 Currently this functi 4150 Currently this function knows 686a and 8231 chips.
4259 Format: [spp|ps2|epp| 4151 Format: [spp|ps2|epp|ecp|ecpepp]
4260 4152
4261 pata_legacy.all= [HW,LIBATA] 4153 pata_legacy.all= [HW,LIBATA]
4262 Format: <int> 4154 Format: <int>
4263 Set to non-zero to pr 4155 Set to non-zero to probe primary and secondary ISA
4264 port ranges on PCI sy 4156 port ranges on PCI systems where no PCI PATA device
4265 has been found at eit 4157 has been found at either range. Disabled by default.
4266 4158
4267 pata_legacy.autospeed= [HW,LIBATA] 4159 pata_legacy.autospeed= [HW,LIBATA]
4268 Format: <int> 4160 Format: <int>
4269 Set to non-zero if a 4161 Set to non-zero if a chip is present that snoops speed
4270 changes. Disabled by 4162 changes. Disabled by default.
4271 4163
4272 pata_legacy.ht6560a= [HW,LIBATA] 4164 pata_legacy.ht6560a= [HW,LIBATA]
4273 Format: <int> 4165 Format: <int>
4274 Set to 1, 2, or 3 for 4166 Set to 1, 2, or 3 for HT 6560A on the primary channel,
4275 the secondary channel 4167 the secondary channel, or both channels respectively.
4276 Disabled by default. 4168 Disabled by default.
4277 4169
4278 pata_legacy.ht6560b= [HW,LIBATA] 4170 pata_legacy.ht6560b= [HW,LIBATA]
4279 Format: <int> 4171 Format: <int>
4280 Set to 1, 2, or 3 for 4172 Set to 1, 2, or 3 for HT 6560B on the primary channel,
4281 the secondary channel 4173 the secondary channel, or both channels respectively.
4282 Disabled by default. 4174 Disabled by default.
4283 4175
4284 pata_legacy.iordy_mask= [HW,LIBATA] 4176 pata_legacy.iordy_mask= [HW,LIBATA]
4285 Format: <int> 4177 Format: <int>
4286 IORDY enable mask. S 4178 IORDY enable mask. Set individual bits to allow IORDY
4287 for the respective ch 4179 for the respective channel. Bit 0 is for the first
4288 legacy channel handle 4180 legacy channel handled by this driver, bit 1 is for
4289 the second channel, a 4181 the second channel, and so on. The sequence will often
4290 correspond to the pri 4182 correspond to the primary legacy channel, the secondary
4291 legacy channel, and s 4183 legacy channel, and so on, but the handling of a PCI
4292 bus and the use of ot 4184 bus and the use of other driver options may interfere
4293 with the sequence. B 4185 with the sequence. By default IORDY is allowed across
4294 all channels. 4186 all channels.
4295 4187
4296 pata_legacy.opti82c46x= [HW,LIBATA] 4188 pata_legacy.opti82c46x= [HW,LIBATA]
4297 Format: <int> 4189 Format: <int>
4298 Set to 1, 2, or 3 for 4190 Set to 1, 2, or 3 for Opti 82c611A on the primary
4299 channel, the secondar 4191 channel, the secondary channel, or both channels
4300 respectively. Disabl 4192 respectively. Disabled by default.
4301 4193
4302 pata_legacy.opti82c611a= [HW,L 4194 pata_legacy.opti82c611a= [HW,LIBATA]
4303 Format: <int> 4195 Format: <int>
4304 Set to 1, 2, or 3 for 4196 Set to 1, 2, or 3 for Opti 82c465MV on the primary
4305 channel, the secondar 4197 channel, the secondary channel, or both channels
4306 respectively. Disabl 4198 respectively. Disabled by default.
4307 4199
4308 pata_legacy.pio_mask= [HW,LIBATA] 4200 pata_legacy.pio_mask= [HW,LIBATA]
4309 Format: <int> 4201 Format: <int>
4310 PIO mode mask for aut 4202 PIO mode mask for autospeed devices. Set individual
4311 bits to allow the use 4203 bits to allow the use of the respective PIO modes.
4312 Bit 0 is for mode 0, 4204 Bit 0 is for mode 0, bit 1 is for mode 1, and so on.
4313 All modes allowed by 4205 All modes allowed by default.
4314 4206
4315 pata_legacy.probe_all= [HW,LIBATA] 4207 pata_legacy.probe_all= [HW,LIBATA]
4316 Format: <int> 4208 Format: <int>
4317 Set to non-zero to pr 4209 Set to non-zero to probe tertiary and further ISA
4318 port ranges on PCI sy 4210 port ranges on PCI systems. Disabled by default.
4319 4211
4320 pata_legacy.probe_mask= [HW,LIBATA] 4212 pata_legacy.probe_mask= [HW,LIBATA]
4321 Format: <int> 4213 Format: <int>
4322 Probe mask for legacy 4214 Probe mask for legacy ISA PATA ports. Depending on
4323 platform configuratio 4215 platform configuration and the use of other driver
4324 options up to 6 legac 4216 options up to 6 legacy ports are supported: 0x1f0,
4325 0x170, 0x1e8, 0x168, 4217 0x170, 0x1e8, 0x168, 0x1e0, 0x160, however probing
4326 of individual ports c 4218 of individual ports can be disabled by setting the
4327 corresponding bits in 4219 corresponding bits in the mask to 1. Bit 0 is for
4328 the first port in the 4220 the first port in the list above (0x1f0), and so on.
4329 By default all suppor 4221 By default all supported ports are probed.
4330 4222
4331 pata_legacy.qdi= [HW,LIBATA] 4223 pata_legacy.qdi= [HW,LIBATA]
4332 Format: <int> 4224 Format: <int>
4333 Set to non-zero to pr 4225 Set to non-zero to probe QDI controllers. By default
4334 set to 1 if CONFIG_PA 4226 set to 1 if CONFIG_PATA_QDI_MODULE, 0 otherwise.
4335 4227
4336 pata_legacy.winbond= [HW,LIBATA] 4228 pata_legacy.winbond= [HW,LIBATA]
4337 Format: <int> 4229 Format: <int>
4338 Set to non-zero to pr 4230 Set to non-zero to probe Winbond controllers. Use
4339 the standard I/O port 4231 the standard I/O port (0x130) if 1, otherwise the
4340 value given is the I/ 4232 value given is the I/O port to use (typically 0x1b0).
4341 By default set to 1 i 4233 By default set to 1 if CONFIG_PATA_WINBOND_VLB_MODULE,
4342 0 otherwise. 4234 0 otherwise.
4343 4235
4344 pata_platform.pio_mask= [HW,LIBATA] 4236 pata_platform.pio_mask= [HW,LIBATA]
4345 Format: <int> 4237 Format: <int>
4346 Supported PIO mode ma 4238 Supported PIO mode mask. Set individual bits to allow
4347 the use of the respec 4239 the use of the respective PIO modes. Bit 0 is for
4348 mode 0, bit 1 is for 4240 mode 0, bit 1 is for mode 1, and so on. Mode 0 only
4349 allowed by default. 4241 allowed by default.
4350 4242
4351 pause_on_oops=<int> 4243 pause_on_oops=<int>
4352 Halt all CPUs after t 4244 Halt all CPUs after the first oops has been printed for
4353 the specified number 4245 the specified number of seconds. This is to be used if
4354 your oopses keep scro 4246 your oopses keep scrolling off the screen.
4355 4247
4356 pcbit= [HW,ISDN] 4248 pcbit= [HW,ISDN]
4357 4249
4358 pci=option[,option...] [PCI,EARLY] v !! 4250 pci=option[,option...] [PCI] various PCI subsystem options.
4359 4251
4360 Some options 4252 Some options herein operate on a specific device
4361 or a set of d 4253 or a set of devices (<pci_dev>). These are
4362 specified in 4254 specified in one of the following formats:
4363 4255
4364 [<domain>:]<b 4256 [<domain>:]<bus>:<dev>.<func>[/<dev>.<func>]*
4365 pci:<vendor>: 4257 pci:<vendor>:<device>[:<subvendor>:<subdevice>]
4366 4258
4367 Note: the fir 4259 Note: the first format specifies a PCI
4368 bus/device/fu 4260 bus/device/function address which may change
4369 if new hardwa 4261 if new hardware is inserted, if motherboard
4370 firmware chan 4262 firmware changes, or due to changes caused
4371 by other kern 4263 by other kernel parameters. If the
4372 domain is lef 4264 domain is left unspecified, it is
4373 taken to be z 4265 taken to be zero. Optionally, a path
4374 to a device t 4266 to a device through multiple device/function
4375 addresses can 4267 addresses can be specified after the base
4376 address (this 4268 address (this is more robust against
4377 renumbering i 4269 renumbering issues). The second format
4378 selects devic 4270 selects devices using IDs from the
4379 configuration 4271 configuration space which may match multiple
4380 devices in th 4272 devices in the system.
4381 4273
4382 earlydump dump PCI conf 4274 earlydump dump PCI config space before the kernel
4383 changes anyth 4275 changes anything
4384 off [X86] don't p 4276 off [X86] don't probe for the PCI bus
4385 bios [X86-32] forc 4277 bios [X86-32] force use of PCI BIOS, don't access
4386 the hardware 4278 the hardware directly. Use this if your machine
4387 has a non-sta 4279 has a non-standard PCI host bridge.
4388 nobios [X86-32] disa 4280 nobios [X86-32] disallow use of PCI BIOS, only direct
4389 hardware acce 4281 hardware access methods are allowed. Use this
4390 if you experi 4282 if you experience crashes upon bootup and you
4391 suspect they 4283 suspect they are caused by the BIOS.
4392 conf1 [X86] Force u 4284 conf1 [X86] Force use of PCI Configuration Access
4393 Mechanism 1 ( 4285 Mechanism 1 (config address in IO port 0xCF8,
4394 data in IO po 4286 data in IO port 0xCFC, both 32-bit).
4395 conf2 [X86] Force u 4287 conf2 [X86] Force use of PCI Configuration Access
4396 Mechanism 2 ( 4288 Mechanism 2 (IO port 0xCF8 is an 8-bit port for
4397 the function, 4289 the function, IO port 0xCFA, also 8-bit, sets
4398 bus number. T 4290 bus number. The config space is then accessed
4399 through ports 4291 through ports 0xC000-0xCFFF).
4400 See http://wi 4292 See http://wiki.osdev.org/PCI for more info
4401 on the config 4293 on the configuration access mechanisms.
4402 noaer [PCIE] If the 4294 noaer [PCIE] If the PCIEAER kernel config parameter is
4403 enabled, this 4295 enabled, this kernel boot option can be used to
4404 disable the u 4296 disable the use of PCIE advanced error reporting.
4405 nodomains [PCI] Disable 4297 nodomains [PCI] Disable support for multiple PCI
4406 root domains 4298 root domains (aka PCI segments, in ACPI-speak).
4407 nommconf [X86] Disable 4299 nommconf [X86] Disable use of MMCONFIG for PCI
4408 Configuration 4300 Configuration
4409 check_enable_amd_mmconf [X86] 4301 check_enable_amd_mmconf [X86] check for and enable
4410 properly conf 4302 properly configured MMIO access to PCI
4411 config space 4303 config space on AMD family 10h CPU
4412 nomsi [MSI] If the 4304 nomsi [MSI] If the PCI_MSI kernel config parameter is
4413 enabled, this 4305 enabled, this kernel boot option can be used to
4414 disable the u 4306 disable the use of MSI interrupts system-wide.
4415 noioapicquirk [APIC] Disabl 4307 noioapicquirk [APIC] Disable all boot interrupt quirks.
4416 Safety option 4308 Safety option to keep boot IRQs enabled. This
4417 should never 4309 should never be necessary.
4418 ioapicreroute [APIC] Enable 4310 ioapicreroute [APIC] Enable rerouting of boot IRQs to the
4419 primary IO-AP 4311 primary IO-APIC for bridges that cannot disable
4420 boot IRQs. Th 4312 boot IRQs. This fixes a source of spurious IRQs
4421 when the syst 4313 when the system masks IRQs.
4422 noioapicreroute [APIC] Disabl 4314 noioapicreroute [APIC] Disable workaround that uses the
4423 boot IRQ equi 4315 boot IRQ equivalent of an IRQ that connects to
4424 a chipset whe 4316 a chipset where boot IRQs cannot be disabled.
4425 The opposite 4317 The opposite of ioapicreroute.
4426 biosirq [X86-32] Use 4318 biosirq [X86-32] Use PCI BIOS calls to get the interrupt
4427 routing table 4319 routing table. These calls are known to be buggy
4428 on several ma 4320 on several machines and they hang the machine
4429 when used, bu 4321 when used, but on other computers it's the only
4430 way to get th 4322 way to get the interrupt routing table. Try
4431 this option i 4323 this option if the kernel is unable to allocate
4432 IRQs or disco 4324 IRQs or discover secondary PCI buses on your
4433 motherboard. 4325 motherboard.
4434 rom [X86] Assign 4326 rom [X86] Assign address space to expansion ROMs.
4435 Use with caut 4327 Use with caution as certain devices share
4436 address decod 4328 address decoders between ROMs and other
4437 resources. 4329 resources.
4438 norom [X86] Do not 4330 norom [X86] Do not assign address space to
4439 expansion ROM 4331 expansion ROMs that do not already have
4440 BIOS assigned 4332 BIOS assigned address ranges.
4441 nobar [X86] Do not 4333 nobar [X86] Do not assign address space to the
4442 BARs that wer 4334 BARs that weren't assigned by the BIOS.
4443 irqmask=0xMMMM [X86] Set a b 4335 irqmask=0xMMMM [X86] Set a bit mask of IRQs allowed to be
4444 assigned auto 4336 assigned automatically to PCI devices. You can
4445 make the kern 4337 make the kernel exclude IRQs of your ISA cards
4446 this way. 4338 this way.
4447 pirqaddr=0xAAAAA [X86] 4339 pirqaddr=0xAAAAA [X86] Specify the physical address
4448 of the PIRQ t 4340 of the PIRQ table (normally generated
4449 by the BIOS) 4341 by the BIOS) if it is outside the
4450 F0000h-100000 4342 F0000h-100000h range.
4451 lastbus=N [X86] Scan al 4343 lastbus=N [X86] Scan all buses thru bus #N. Can be
4452 useful if the 4344 useful if the kernel is unable to find your
4453 secondary bus 4345 secondary buses and you want to tell it
4454 explicitly wh 4346 explicitly which ones they are.
4455 assign-busses [X86] Always 4347 assign-busses [X86] Always assign all PCI bus
4456 numbers ourse 4348 numbers ourselves, overriding
4457 whatever the 4349 whatever the firmware may have done.
4458 usepirqmask [X86] Honor t 4350 usepirqmask [X86] Honor the possible IRQ mask stored
4459 in the BIOS $ 4351 in the BIOS $PIR table. This is needed on
4460 some systems 4352 some systems with broken BIOSes, notably
4461 some HP Pavil 4353 some HP Pavilion N5400 and Omnibook XE3
4462 notebooks. Th 4354 notebooks. This will have no effect if ACPI
4463 IRQ routing i 4355 IRQ routing is enabled.
4464 noacpi [X86] Do not 4356 noacpi [X86] Do not use ACPI for IRQ routing
4465 or for PCI sc 4357 or for PCI scanning.
4466 use_crs [X86] Use PCI 4358 use_crs [X86] Use PCI host bridge window information
4467 from ACPI. O 4359 from ACPI. On BIOSes from 2008 or later, this
4468 is enabled by 4360 is enabled by default. If you need to use this,
4469 please report 4361 please report a bug.
4470 nocrs [X86] Ignore 4362 nocrs [X86] Ignore PCI host bridge windows from ACPI.
4471 If you need t 4363 If you need to use this, please report a bug.
4472 use_e820 [X86] Use E82 4364 use_e820 [X86] Use E820 reservations to exclude parts of
4473 PCI host brid 4365 PCI host bridge windows. This is a workaround
4474 for BIOS defe 4366 for BIOS defects in host bridge _CRS methods.
4475 If you need t 4367 If you need to use this, please report a bug to
4476 <linux-pci@vge 4368 <linux-pci@vger.kernel.org>.
4477 no_e820 [X86] Ignore 4369 no_e820 [X86] Ignore E820 reservations for PCI host
4478 bridge window 4370 bridge windows. This is the default on modern
4479 hardware. If 4371 hardware. If you need to use this, please report
4480 a bug to <linu 4372 a bug to <linux-pci@vger.kernel.org>.
4481 routeirq Do IRQ routin 4373 routeirq Do IRQ routing for all PCI devices.
4482 This is norma 4374 This is normally done in pci_enable_device(),
4483 so this optio 4375 so this option is a temporary workaround
4484 for broken dr 4376 for broken drivers that don't call it.
4485 skip_isa_align [X86] do not 4377 skip_isa_align [X86] do not align io start addr, so can
4486 handle more p 4378 handle more pci cards
4487 noearly [X86] Don't d 4379 noearly [X86] Don't do any early type 1 scanning.
4488 This might he 4380 This might help on some broken boards which
4489 machine check 4381 machine check when some devices' config space
4490 is read. But 4382 is read. But various workarounds are disabled
4491 and some IOMM 4383 and some IOMMU drivers will not work.
4492 bfsort Sort PCI devi 4384 bfsort Sort PCI devices into breadth-first order.
4493 This sorting 4385 This sorting is done to get a device
4494 order compati 4386 order compatible with older (<= 2.4) kernels.
4495 nobfsort Don't sort PC 4387 nobfsort Don't sort PCI devices into breadth-first order.
4496 pcie_bus_tune_off Disab 4388 pcie_bus_tune_off Disable PCIe MPS (Max Payload Size)
4497 tuning and us 4389 tuning and use the BIOS-configured MPS defaults.
4498 pcie_bus_safe Set every dev 4390 pcie_bus_safe Set every device's MPS to the largest value
4499 supported by 4391 supported by all devices below the root complex.
4500 pcie_bus_perf Set device MP 4392 pcie_bus_perf Set device MPS to the largest allowable MPS
4501 based on its 4393 based on its parent bus. Also set MRRS (Max
4502 Read Request 4394 Read Request Size) to the largest supported
4503 value (no lar 4395 value (no larger than the MPS that the device
4504 or bus can su 4396 or bus can support) for best performance.
4505 pcie_bus_peer2peer Set e 4397 pcie_bus_peer2peer Set every device's MPS to 128B, which
4506 every device 4398 every device is guaranteed to support. This
4507 configuration 4399 configuration allows peer-to-peer DMA between
4508 any pair of d 4400 any pair of devices, possibly at the cost of
4509 reduced perfo 4401 reduced performance. This also guarantees
4510 that hot-adde 4402 that hot-added devices will work.
4511 cbiosize=nn[KMG] The f 4403 cbiosize=nn[KMG] The fixed amount of bus space which is
4512 reserved for 4404 reserved for the CardBus bridge's IO window.
4513 The default v 4405 The default value is 256 bytes.
4514 cbmemsize=nn[KMG] The f 4406 cbmemsize=nn[KMG] The fixed amount of bus space which is
4515 reserved for 4407 reserved for the CardBus bridge's memory
4516 window. The d 4408 window. The default value is 64 megabytes.
4517 resource_alignment= 4409 resource_alignment=
4518 Format: 4410 Format:
4519 [<order of ali 4411 [<order of align>@]<pci_dev>[; ...]
4520 Specifies ali 4412 Specifies alignment and device to reassign
4521 aligned memor 4413 aligned memory resources. How to
4522 specify the d 4414 specify the device is described above.
4523 If <order of 4415 If <order of align> is not specified,
4524 PAGE_SIZE is 4416 PAGE_SIZE is used as alignment.
4525 A PCI-PCI bri 4417 A PCI-PCI bridge can be specified if resource
4526 windows need 4418 windows need to be expanded.
4527 To specify th 4419 To specify the alignment for several
4528 instances of 4420 instances of a device, the PCI vendor,
4529 device, subve 4421 device, subvendor, and subdevice may be
4530 specified, e. 4422 specified, e.g., 12@pci:8086:9c22:103c:198f
4531 for 4096-byte 4423 for 4096-byte alignment.
4532 ecrc= Enable/disabl 4424 ecrc= Enable/disable PCIe ECRC (transaction layer
4533 end-to-end CR 4425 end-to-end CRC checking). Only effective if
4534 OS has native 4426 OS has native AER control (either granted by
4535 ACPI _OSC or 4427 ACPI _OSC or forced via "pcie_ports=native")
4536 bios: Use BIO 4428 bios: Use BIOS/firmware settings. This is the
4537 the default. 4429 the default.
4538 off: Turn ECR 4430 off: Turn ECRC off
4539 on: Turn ECRC 4431 on: Turn ECRC on.
4540 hpiosize=nn[KMG] The f 4432 hpiosize=nn[KMG] The fixed amount of bus space which is
4541 reserved for 4433 reserved for hotplug bridge's IO window.
4542 Default size 4434 Default size is 256 bytes.
4543 hpmmiosize=nn[KMG] The f 4435 hpmmiosize=nn[KMG] The fixed amount of bus space which is
4544 reserved for 4436 reserved for hotplug bridge's MMIO window.
4545 Default size 4437 Default size is 2 megabytes.
4546 hpmmioprefsize=nn[KMG] The f 4438 hpmmioprefsize=nn[KMG] The fixed amount of bus space which is
4547 reserved for 4439 reserved for hotplug bridge's MMIO_PREF window.
4548 Default size 4440 Default size is 2 megabytes.
4549 hpmemsize=nn[KMG] The f 4441 hpmemsize=nn[KMG] The fixed amount of bus space which is
4550 reserved for 4442 reserved for hotplug bridge's MMIO and
4551 MMIO_PREF win 4443 MMIO_PREF window.
4552 Default size 4444 Default size is 2 megabytes.
4553 hpbussize=nn The minimum a 4445 hpbussize=nn The minimum amount of additional bus numbers
4554 reserved for 4446 reserved for buses below a hotplug bridge.
4555 Default is 1. 4447 Default is 1.
4556 realloc= Enable/disabl 4448 realloc= Enable/disable reallocating PCI bridge resources
4557 if allocation 4449 if allocations done by BIOS are too small to
4558 accommodate r 4450 accommodate resources required by all child
4559 devices. 4451 devices.
4560 off: Turn rea 4452 off: Turn realloc off
4561 on: Turn real 4453 on: Turn realloc on
4562 realloc same as reall 4454 realloc same as realloc=on
4563 noari do not use PC 4455 noari do not use PCIe ARI.
4564 noats [PCIE, Intel- 4456 noats [PCIE, Intel-IOMMU, AMD-IOMMU]
4565 do not use PC 4457 do not use PCIe ATS (and IOMMU device IOTLB).
4566 pcie_scan_all Scan all poss 4458 pcie_scan_all Scan all possible PCIe devices. Otherwise we
4567 only look for 4459 only look for one device below a PCIe downstream
4568 port. 4460 port.
4569 big_root_window Try to add a 4461 big_root_window Try to add a big 64bit memory window to the PCIe
4570 root complex 4462 root complex on AMD CPUs. Some GFX hardware
4571 can resize a 4463 can resize a BAR to allow access to all VRAM.
4572 Adding the wi 4464 Adding the window is slightly risky (it may
4573 conflict with 4465 conflict with unreported devices), so this
4574 taints the ke 4466 taints the kernel.
4575 disable_acs_redir=<pci_dev>[; 4467 disable_acs_redir=<pci_dev>[; ...]
4576 Specify one o 4468 Specify one or more PCI devices (in the format
4577 specified abo 4469 specified above) separated by semicolons.
4578 Each device s 4470 Each device specified will have the PCI ACS
4579 redirect capa 4471 redirect capabilities forced off which will
4580 allow P2P tra 4472 allow P2P traffic between devices through
4581 bridges witho 4473 bridges without forcing it upstream. Note:
4582 this removes 4474 this removes isolation between devices and
4583 may put more 4475 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 4476 force_floating [S390] Force usage of floating interrupts.
4617 nomio [S390] Do not 4477 nomio [S390] Do not use MIO instructions.
4618 norid [S390] ignore 4478 norid [S390] ignore the RID field and force use of
4619 one PCI domai 4479 one PCI domain per PCI function
4620 4480
4621 pcie_aspm= [PCIE] Forcibly enabl !! 4481 pcie_aspm= [PCIE] Forcibly enable or disable PCIe Active State Power
4622 Management. 4482 Management.
4623 off Don't touch ASPM conf !! 4483 off Disable ASPM.
4624 configuration done by <<
4625 force Enable ASPM even on d 4484 force Enable ASPM even on devices that claim not to support it.
4626 WARNING: Forcing ASPM 4485 WARNING: Forcing ASPM on may cause system lockups.
4627 4486
4628 pcie_ports= [PCIE] PCIe port serv 4487 pcie_ports= [PCIE] PCIe port services handling:
4629 native Use native PCIe servi 4488 native Use native PCIe services (PME, AER, DPC, PCIe hotplug)
4630 even if the platform 4489 even if the platform doesn't give the OS permission to
4631 use them. This may c 4490 use them. This may cause conflicts if the platform
4632 also tries to use the 4491 also tries to use these services.
4633 dpc-native Use native PC 4492 dpc-native Use native PCIe service for DPC only. May
4634 cause conflic 4493 cause conflicts if firmware uses AER or DPC.
4635 compat Disable native PCIe s 4494 compat Disable native PCIe services (PME, AER, DPC, PCIe
4636 hotplug). 4495 hotplug).
4637 4496
4638 pcie_port_pm= [PCIE] PCIe port powe 4497 pcie_port_pm= [PCIE] PCIe port power management handling:
4639 off Disable power managem 4498 off Disable power management of all PCIe ports
4640 force Forcibly enable power 4499 force Forcibly enable power management of all PCIe ports
4641 4500
4642 pcie_pme= [PCIE,PM] Native PCIe 4501 pcie_pme= [PCIE,PM] Native PCIe PME signaling options:
4643 nomsi Do not use MSI for na 4502 nomsi Do not use MSI for native PCIe PME signaling (this makes
4644 all PCIe root ports u 4503 all PCIe root ports use INTx for all services).
4645 4504
4646 pcmv= [HW,PCMCIA] BadgePAD 4505 pcmv= [HW,PCMCIA] BadgePAD 4
4647 4506
4648 pd_ignore_unused 4507 pd_ignore_unused
4649 [PM] 4508 [PM]
4650 Keep all power-domain 4509 Keep all power-domains already enabled by bootloader on,
4651 even if no driver has 4510 even if no driver has claimed them. This is useful
4652 for debug and develop 4511 for debug and development, but should not be
4653 needed on a platform 4512 needed on a platform with proper driver support.
4654 4513
4655 pdcchassis= [PARISC,HW] Disable/E 4514 pdcchassis= [PARISC,HW] Disable/Enable PDC Chassis Status codes at
4656 boot time. 4515 boot time.
4657 Format: { 0 | 1 } 4516 Format: { 0 | 1 }
4658 See arch/parisc/kerne 4517 See arch/parisc/kernel/pdc_chassis.c
4659 4518
4660 percpu_alloc= [MM,EARLY] !! 4519 percpu_alloc= Select which percpu first chunk allocator to use.
4661 Select which percpu f <<
4662 Currently supported v 4520 Currently supported values are "embed" and "page".
4663 Archs may support sub 4521 Archs may support subset or none of the selections.
4664 See comments in mm/pe 4522 See comments in mm/percpu.c for details on each
4665 allocator. This para 4523 allocator. This parameter is primarily for debugging
4666 and performance compa 4524 and performance comparison.
4667 4525
4668 pirq= [SMP,APIC] Manual mp- 4526 pirq= [SMP,APIC] Manual mp-table setup
4669 See Documentation/arc 4527 See Documentation/arch/x86/i386/IO-APIC.rst.
4670 4528
4671 plip= [PPT,NET] Parallel po 4529 plip= [PPT,NET] Parallel port network link
4672 Format: { parport<nr> 4530 Format: { parport<nr> | timid | 0 }
4673 See also Documentatio 4531 See also Documentation/admin-guide/parport.rst.
4674 4532
4675 pmtmr= [X86] Manual setup of 4533 pmtmr= [X86] Manual setup of pmtmr I/O Port.
4676 Override pmtimer IOPo 4534 Override pmtimer IOPort with a hex value.
4677 e.g. pmtmr=0x508 4535 e.g. pmtmr=0x508
4678 4536
4679 pmu_override= [PPC] Override the PM 4537 pmu_override= [PPC] Override the PMU.
4680 This option takes ove 4538 This option takes over the PMU facility, so it is no
4681 longer usable by perf 4539 longer usable by perf. Setting this option starts the
4682 PMU counters by setti 4540 PMU counters by setting MMCR0 to 0 (the FC bit is
4683 cleared). If a number 4541 cleared). If a number is given, then MMCR1 is set to
4684 that number, otherwis 4542 that number, otherwise (e.g., 'pmu_override=on'), MMCR1
4685 remains 0. 4543 remains 0.
4686 4544
4687 pm_debug_messages [SUSPEND,KNL] 4545 pm_debug_messages [SUSPEND,KNL]
4688 Enable suspend/resume 4546 Enable suspend/resume debug messages during boot up.
4689 4547
4690 pnp.debug=1 [PNP] 4548 pnp.debug=1 [PNP]
4691 Enable PNP debug mess 4549 Enable PNP debug messages (depends on the
4692 CONFIG_PNP_DEBUG_MESS 4550 CONFIG_PNP_DEBUG_MESSAGES option). Change at run-time
4693 via /sys/module/pnp/p 4551 via /sys/module/pnp/parameters/debug. We always show
4694 current resource usag 4552 current resource usage; turning this on also shows
4695 possible settings and 4553 possible settings and some assignment information.
4696 4554
4697 pnpacpi= [ACPI] 4555 pnpacpi= [ACPI]
4698 { off } 4556 { off }
4699 4557
4700 pnpbios= [ISAPNP] 4558 pnpbios= [ISAPNP]
4701 { on | off | curr | r 4559 { on | off | curr | res | no-curr | no-res }
4702 4560
4703 pnp_reserve_irq= 4561 pnp_reserve_irq=
4704 [ISAPNP] Exclude IRQs 4562 [ISAPNP] Exclude IRQs for the autoconfiguration
4705 4563
4706 pnp_reserve_dma= 4564 pnp_reserve_dma=
4707 [ISAPNP] Exclude DMAs 4565 [ISAPNP] Exclude DMAs for the autoconfiguration
4708 4566
4709 pnp_reserve_io= [ISAPNP] Exclude I/O 4567 pnp_reserve_io= [ISAPNP] Exclude I/O ports for the autoconfiguration
4710 Ranges are in pairs ( 4568 Ranges are in pairs (I/O port base and size).
4711 4569
4712 pnp_reserve_mem= 4570 pnp_reserve_mem=
4713 [ISAPNP] Exclude memo 4571 [ISAPNP] Exclude memory regions for the
4714 autoconfiguration. 4572 autoconfiguration.
4715 Ranges are in pairs ( 4573 Ranges are in pairs (memory base and size).
4716 4574
4717 ports= [IP_VS_FTP] IPVS ftp 4575 ports= [IP_VS_FTP] IPVS ftp helper module
4718 Default is 21. 4576 Default is 21.
4719 Up to 8 (IP_VS_APP_MA 4577 Up to 8 (IP_VS_APP_MAX_PORTS) ports
4720 may be specified. 4578 may be specified.
4721 Format: <port>,<port> 4579 Format: <port>,<port>....
4722 4580
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 4581 powersave=off [PPC] This option disables power saving features.
4729 It specifically disab 4582 It specifically disables cpuidle and sets the
4730 platform machine desc 4583 platform machine description specific power_save
4731 function to NULL. On 4584 function to NULL. On Idle the CPU just reduces
4732 execution priority. 4585 execution priority.
4733 4586
4734 ppc_strict_facility_enable 4587 ppc_strict_facility_enable
4735 [PPC,ENABLE] This opt !! 4588 [PPC] This option catches any kernel floating point,
4736 Altivec, VSX and SPE 4589 Altivec, VSX and SPE outside of regions specifically
4737 allowed (eg kernel_en 4590 allowed (eg kernel_enable_fpu()/kernel_disable_fpu()).
4738 There is some perform 4591 There is some performance impact when enabling this.
4739 4592
4740 ppc_tm= [PPC,EARLY] !! 4593 ppc_tm= [PPC]
4741 Format: {"off"} 4594 Format: {"off"}
4742 Disable Hardware Tran 4595 Disable Hardware Transactional Memory
4743 4596
4744 preempt= [KNL] 4597 preempt= [KNL]
4745 Select preemption mod 4598 Select preemption mode if you have CONFIG_PREEMPT_DYNAMIC
4746 none - Limited to con 4599 none - Limited to cond_resched() calls
4747 voluntary - Limited t 4600 voluntary - Limited to cond_resched() and might_sleep() calls
4748 full - Any section th 4601 full - Any section that isn't explicitly preempt disabled
4749 can be preempt !! 4602 can be preempted anytime.
4750 contended spin <<
4751 explicitly pre <<
4752 4603
4753 print-fatal-signals= 4604 print-fatal-signals=
4754 [KNL] debug: print fa 4605 [KNL] debug: print fatal signals
4755 4606
4756 If enabled, warn abou 4607 If enabled, warn about various signal handling
4757 related application a 4608 related application anomalies: too many signals,
4758 too many POSIX.1 time 4609 too many POSIX.1 timers, fatal signals causing a
4759 coredump - etc. 4610 coredump - etc.
4760 4611
4761 If you hit the warnin 4612 If you hit the warning due to signal overflow,
4762 you might want to try 4613 you might want to try "ulimit -i unlimited".
4763 4614
4764 default: off. 4615 default: off.
4765 4616
4766 printk.always_kmsg_dump= 4617 printk.always_kmsg_dump=
4767 Trigger kmsg_dump for 4618 Trigger kmsg_dump for cases other than kernel oops or
4768 panics 4619 panics
4769 Format: <bool> (1/Y/ 4620 Format: <bool> (1/Y/y=enable, 0/N/n=disable)
4770 default: disabled 4621 default: disabled
4771 4622
4772 printk.console_no_auto_verbose= 4623 printk.console_no_auto_verbose=
4773 Disable console logle 4624 Disable console loglevel raise on oops, panic
4774 or lockdep-detected i 4625 or lockdep-detected issues (only if lock debug is on).
4775 With an exception to 4626 With an exception to setups with low baudrate on
4776 serial console, keepi 4627 serial console, keeping this 0 is a good choice
4777 in order to provide m 4628 in order to provide more debug information.
4778 Format: <bool> 4629 Format: <bool>
4779 default: 0 (auto_verb 4630 default: 0 (auto_verbose is enabled)
4780 4631
4781 printk.devkmsg={on,off,ratelimit} 4632 printk.devkmsg={on,off,ratelimit}
4782 Control writing to /d 4633 Control writing to /dev/kmsg.
4783 on - unlimited loggin 4634 on - unlimited logging to /dev/kmsg from userspace
4784 off - logging to /dev 4635 off - logging to /dev/kmsg disabled
4785 ratelimit - ratelimit 4636 ratelimit - ratelimit the logging
4786 Default: ratelimit 4637 Default: ratelimit
4787 4638
4788 printk.time= Show timing data pref 4639 printk.time= Show timing data prefixed to each printk message line
4789 Format: <bool> (1/Y/ 4640 Format: <bool> (1/Y/y=enable, 0/N/n=disable)
4790 4641
4791 proc_mem.force_override= [KNL] 4642 proc_mem.force_override= [KNL]
4792 Format: {always | ptr 4643 Format: {always | ptrace | never}
4793 Traditionally /proc/p 4644 Traditionally /proc/pid/mem allows memory permissions to be
4794 overridden without re 4645 overridden without restrictions. This option may be set to
4795 restrict that. Can be 4646 restrict that. Can be one of:
4796 - 'always': tradition 4647 - 'always': traditional behavior always allows mem overrides.
4797 - 'ptrace': only allo 4648 - 'ptrace': only allow mem overrides for active ptracers.
4798 - 'never': never all 4649 - 'never': never allow mem overrides.
4799 If not specified, def 4650 If not specified, default is the CONFIG_PROC_MEM_* choice.
4800 4651
4801 processor.max_cstate= [HW,ACPI] 4652 processor.max_cstate= [HW,ACPI]
4802 Limit processor to ma 4653 Limit processor to maximum C-state
4803 max_cstate=9 override 4654 max_cstate=9 overrides any DMI blacklist limit.
4804 4655
4805 processor.nocst [HW,ACPI] 4656 processor.nocst [HW,ACPI]
4806 Ignore the _CST metho 4657 Ignore the _CST method to determine C-states,
4807 instead using the leg 4658 instead using the legacy FADT method
4808 4659
4809 profile= [KNL] Enable kernel p 4660 profile= [KNL] Enable kernel profiling via /proc/profile
4810 Format: [<profiletype 4661 Format: [<profiletype>,]<number>
4811 Param: <profiletype>: 4662 Param: <profiletype>: "schedule" or "kvm"
4812 [defaults to 4663 [defaults to kernel profiling]
4813 Param: "schedule" - p 4664 Param: "schedule" - profile schedule points.
4814 Param: "kvm" - profil 4665 Param: "kvm" - profile VM exits.
4815 Param: <number> - ste 4666 Param: <number> - step/bucket size as a power of 2 for
4816 statistical t 4667 statistical time based profiling.
4817 4668
4818 prompt_ramdisk= [RAM] [Deprecated] 4669 prompt_ramdisk= [RAM] [Deprecated]
4819 4670
4820 prot_virt= [S390] enable hosting 4671 prot_virt= [S390] enable hosting protected virtual machines
4821 isolated from the hyp 4672 isolated from the hypervisor (if hardware supports
4822 that). If enabled, th !! 4673 that).
4823 might be overridden e <<
4824 Layout Randomization <<
4825 Format: <bool> 4674 Format: <bool>
4826 4675
4827 psi= [KNL] Enable or disab 4676 psi= [KNL] Enable or disable pressure stall information
4828 tracking. 4677 tracking.
4829 Format: <bool> 4678 Format: <bool>
4830 4679
4831 psmouse.proto= [HW,MOUSE] Highest PS 4680 psmouse.proto= [HW,MOUSE] Highest PS2 mouse protocol extension to
4832 probe for; one of (ba 4681 probe for; one of (bare|imps|exps|lifebook|any).
4833 psmouse.rate= [HW,MOUSE] Set desire 4682 psmouse.rate= [HW,MOUSE] Set desired mouse report rate, in reports
4834 per second. 4683 per second.
4835 psmouse.resetafter= [HW,MOUSE] 4684 psmouse.resetafter= [HW,MOUSE]
4836 Try to reset the devi 4685 Try to reset the device after so many bad packets
4837 (0 = never). 4686 (0 = never).
4838 psmouse.resolution= 4687 psmouse.resolution=
4839 [HW,MOUSE] Set desire 4688 [HW,MOUSE] Set desired mouse resolution, in dpi.
4840 psmouse.smartscroll= 4689 psmouse.smartscroll=
4841 [HW,MOUSE] Controls L 4690 [HW,MOUSE] Controls Logitech smartscroll autorepeat.
4842 0 = disabled, 1 = ena 4691 0 = disabled, 1 = enabled (default).
4843 4692
4844 pstore.backend= Specify the name of t 4693 pstore.backend= Specify the name of the pstore backend to use
4845 4694
4846 pti= [X86-64] Control Page 4695 pti= [X86-64] Control Page Table Isolation of user and
4847 kernel address spaces 4696 kernel address spaces. Disabling this feature
4848 removes hardening, bu 4697 removes hardening, but improves performance of
4849 system calls and inte 4698 system calls and interrupts.
4850 4699
4851 on - unconditionall 4700 on - unconditionally enable
4852 off - unconditionall 4701 off - unconditionally disable
4853 auto - kernel detects 4702 auto - kernel detects whether your CPU model is
4854 vulnerable to 4703 vulnerable to issues that PTI mitigates
4855 4704
4856 Not specifying this o 4705 Not specifying this option is equivalent to pti=auto.
4857 4706
4858 pty.legacy_count= 4707 pty.legacy_count=
4859 [KNL] Number of legac 4708 [KNL] Number of legacy pty's. Overwrites compiled-in
4860 default number. 4709 default number.
4861 4710
4862 quiet [KNL,EARLY] Disable m !! 4711 quiet [KNL] Disable most log messages
4863 4712
4864 r128= [HW,DRM] 4713 r128= [HW,DRM]
4865 4714
4866 radix_hcall_invalidate=on [PPC/PSERI 4715 radix_hcall_invalidate=on [PPC/PSERIES]
4867 Disable RADIX GTSE fe 4716 Disable RADIX GTSE feature and use hcall for TLB
4868 invalidate. 4717 invalidate.
4869 4718
4870 raid= [HW,RAID] 4719 raid= [HW,RAID]
4871 See Documentation/adm 4720 See Documentation/admin-guide/md.rst.
4872 4721
4873 ramdisk_size= [RAM] Sizes of RAM di 4722 ramdisk_size= [RAM] Sizes of RAM disks in kilobytes
4874 See Documentation/adm 4723 See Documentation/admin-guide/blockdev/ramdisk.rst.
4875 4724
4876 ramdisk_start= [RAM] RAM disk image 4725 ramdisk_start= [RAM] RAM disk image start address
4877 4726
4878 random.trust_cpu=off 4727 random.trust_cpu=off
4879 [KNL,EARLY] Disable t !! 4728 [KNL] Disable trusting the use of the CPU's
4880 random number generat 4729 random number generator (if available) to
4881 initialize the kernel 4730 initialize the kernel's RNG.
4882 4731
4883 random.trust_bootloader=off 4732 random.trust_bootloader=off
4884 [KNL,EARLY] Disable t !! 4733 [KNL] Disable trusting the use of the a seed
4885 passed by the bootloa 4734 passed by the bootloader (if available) to
4886 initialize the kernel 4735 initialize the kernel's RNG.
4887 4736
4888 randomize_kstack_offset= 4737 randomize_kstack_offset=
4889 [KNL,EARLY] Enable or !! 4738 [KNL] Enable or disable kernel stack offset
4890 randomization, which 4739 randomization, which provides roughly 5 bits of
4891 entropy, frustrating 4740 entropy, frustrating memory corruption attacks
4892 that depend on stack 4741 that depend on stack address determinism or
4893 cross-syscall address 4742 cross-syscall address exposures. This is only
4894 available on architec 4743 available on architectures that have defined
4895 CONFIG_HAVE_ARCH_RAND 4744 CONFIG_HAVE_ARCH_RANDOMIZE_KSTACK_OFFSET.
4896 Format: <bool> (1/Y/ 4745 Format: <bool> (1/Y/y=enable, 0/N/n=disable)
4897 Default is CONFIG_RAN 4746 Default is CONFIG_RANDOMIZE_KSTACK_OFFSET_DEFAULT.
4898 4747
4899 ras=option[,option,...] [KNL] RAS-spe 4748 ras=option[,option,...] [KNL] RAS-specific options
4900 4749
4901 cec_disable [X86] 4750 cec_disable [X86]
4902 Disable the C 4751 Disable the Correctable Errors Collector,
4903 see CONFIG_RA 4752 see CONFIG_RAS_CEC help text.
4904 4753
4905 rcu_nocbs[=cpu-list] 4754 rcu_nocbs[=cpu-list]
4906 [KNL] The optional ar 4755 [KNL] The optional argument is a cpu list,
4907 as described above. 4756 as described above.
4908 4757
4909 In kernels built with 4758 In kernels built with CONFIG_RCU_NOCB_CPU=y,
4910 enable the no-callbac 4759 enable the no-callback CPU mode, which prevents
4911 such CPUs' callbacks 4760 such CPUs' callbacks from being invoked in
4912 softirq context. Inv 4761 softirq context. Invocation of such CPUs' RCU
4913 callbacks will instea 4762 callbacks will instead be offloaded to "rcuox/N"
4914 kthreads created for 4763 kthreads created for that purpose, where "x" is
4915 "p" for RCU-preempt, 4764 "p" for RCU-preempt, "s" for RCU-sched, and "g"
4916 for the kthreads that 4765 for the kthreads that mediate grace periods; and
4917 "N" is the CPU number 4766 "N" is the CPU number. This reduces OS jitter on
4918 the offloaded CPUs, w 4767 the offloaded CPUs, which can be useful for HPC
4919 and real-time workloa 4768 and real-time workloads. It can also improve
4920 energy efficiency for 4769 energy efficiency for asymmetric multiprocessors.
4921 4770
4922 If a cpulist is passe 4771 If a cpulist is passed as an argument, the specified
4923 list of CPUs is set t 4772 list of CPUs is set to no-callback mode from boot.
4924 4773
4925 Otherwise, if the '=' 4774 Otherwise, if the '=' sign and the cpulist
4926 arguments are omitted 4775 arguments are omitted, no CPU will be set to
4927 no-callback mode from 4776 no-callback mode from boot but the mode may be
4928 toggled at runtime vi 4777 toggled at runtime via cpusets.
4929 4778
4930 Note that this argume 4779 Note that this argument takes precedence over
4931 the CONFIG_RCU_NOCB_C 4780 the CONFIG_RCU_NOCB_CPU_DEFAULT_ALL option.
4932 4781
4933 rcu_nocb_poll [KNL] 4782 rcu_nocb_poll [KNL]
4934 Rather than requiring 4783 Rather than requiring that offloaded CPUs
4935 (specified by rcu_noc 4784 (specified by rcu_nocbs= above) explicitly
4936 awaken the correspond 4785 awaken the corresponding "rcuoN" kthreads,
4937 make these kthreads p 4786 make these kthreads poll for callbacks.
4938 This improves the rea 4787 This improves the real-time response for the
4939 offloaded CPUs by rel 4788 offloaded CPUs by relieving them of the need to
4940 wake up the correspon 4789 wake up the corresponding kthread, but degrades
4941 energy efficiency by 4790 energy efficiency by requiring that the kthreads
4942 periodically wake up 4791 periodically wake up to do the polling.
4943 4792
4944 rcutree.blimit= [KNL] 4793 rcutree.blimit= [KNL]
4945 Set maximum number of 4794 Set maximum number of finished RCU callbacks to
4946 process in one batch. 4795 process in one batch.
4947 4796
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] 4797 rcutree.dump_tree= [KNL]
4956 Dump the structure of 4798 Dump the structure of the rcu_node combining tree
4957 out at early boot. T 4799 out at early boot. This is used for diagnostic
4958 purposes, to verify c 4800 purposes, to verify correct tree setup.
4959 4801
4960 rcutree.gp_cleanup_delay= [KNL] 4802 rcutree.gp_cleanup_delay= [KNL]
4961 Set the number of jif 4803 Set the number of jiffies to delay each step of
4962 RCU grace-period clea 4804 RCU grace-period cleanup.
4963 4805
4964 rcutree.gp_init_delay= [KNL] 4806 rcutree.gp_init_delay= [KNL]
4965 Set the number of jif 4807 Set the number of jiffies to delay each step of
4966 RCU grace-period init 4808 RCU grace-period initialization.
4967 4809
4968 rcutree.gp_preinit_delay= [KNL] 4810 rcutree.gp_preinit_delay= [KNL]
4969 Set the number of jif 4811 Set the number of jiffies to delay each step of
4970 RCU grace-period pre- 4812 RCU grace-period pre-initialization, that is,
4971 the propagation of re 4813 the propagation of recent CPU-hotplug changes up
4972 the rcu_node combinin 4814 the rcu_node combining tree.
4973 4815
4974 rcutree.jiffies_till_first_fqs= [KNL] 4816 rcutree.jiffies_till_first_fqs= [KNL]
4975 Set delay from grace- 4817 Set delay from grace-period initialization to
4976 first attempt to forc 4818 first attempt to force quiescent states.
4977 Units are jiffies, mi 4819 Units are jiffies, minimum value is zero,
4978 and maximum value is 4820 and maximum value is HZ.
4979 4821
4980 rcutree.jiffies_till_next_fqs= [KNL] 4822 rcutree.jiffies_till_next_fqs= [KNL]
4981 Set delay between sub 4823 Set delay between subsequent attempts to force
4982 quiescent states. Un 4824 quiescent states. Units are jiffies, minimum
4983 value is one, and max 4825 value is one, and maximum value is HZ.
4984 4826
4985 rcutree.jiffies_till_sched_qs= [KNL] 4827 rcutree.jiffies_till_sched_qs= [KNL]
4986 Set required age in j 4828 Set required age in jiffies for a
4987 given grace period be 4829 given grace period before RCU starts
4988 soliciting quiescent- 4830 soliciting quiescent-state help from
4989 rcu_note_context_swit 4831 rcu_note_context_switch() and cond_resched().
4990 If not specified, the 4832 If not specified, the kernel will calculate
4991 a value based on the 4833 a value based on the most recent settings
4992 of rcutree.jiffies_ti 4834 of rcutree.jiffies_till_first_fqs
4993 and rcutree.jiffies_t 4835 and rcutree.jiffies_till_next_fqs.
4994 This calculated value 4836 This calculated value may be viewed in
4995 rcutree.jiffies_to_sc 4837 rcutree.jiffies_to_sched_qs. Any attempt to set
4996 rcutree.jiffies_to_sc 4838 rcutree.jiffies_to_sched_qs will be cheerfully
4997 overwritten. 4839 overwritten.
4998 4840
4999 rcutree.kthread_prio= [KNL,BOOT] 4841 rcutree.kthread_prio= [KNL,BOOT]
5000 Set the SCHED_FIFO pr 4842 Set the SCHED_FIFO priority of the RCU per-CPU
5001 kthreads (rcuc/N). Th 4843 kthreads (rcuc/N). This value is also used for
5002 the priority of the R 4844 the priority of the RCU boost threads (rcub/N)
5003 and for the RCU grace 4845 and for the RCU grace-period kthreads (rcu_bh,
5004 rcu_preempt, and rcu_ 4846 rcu_preempt, and rcu_sched). If RCU_BOOST is
5005 set, valid values are 4847 set, valid values are 1-99 and the default is 1
5006 (the least-favored pr 4848 (the least-favored priority). Otherwise, when
5007 RCU_BOOST is not set, 4849 RCU_BOOST is not set, valid values are 0-99 and
5008 the default is zero ( 4850 the default is zero (non-realtime operation).
5009 When RCU_NOCB_CPU is 4851 When RCU_NOCB_CPU is set, also adjust the
5010 priority of NOCB call 4852 priority of NOCB callback kthreads.
5011 4853
5012 rcutree.nocb_nobypass_lim_per_jiffy= 4854 rcutree.nocb_nobypass_lim_per_jiffy= [KNL]
5013 On callback-offloaded 4855 On callback-offloaded (rcu_nocbs) CPUs,
5014 RCU reduces the lock 4856 RCU reduces the lock contention that would
5015 otherwise be caused b 4857 otherwise be caused by callback floods through
5016 use of the ->nocb_byp 4858 use of the ->nocb_bypass list. However, in the
5017 common non-flooded ca 4859 common non-flooded case, RCU queues directly to
5018 the main ->cblist in 4860 the main ->cblist in order to avoid the extra
5019 overhead of the ->noc 4861 overhead of the ->nocb_bypass list and its lock.
5020 But if there are too 4862 But if there are too many callbacks queued during
5021 a single jiffy, RCU p 4863 a single jiffy, RCU pre-queues the callbacks into
5022 the ->nocb_bypass que 4864 the ->nocb_bypass queue. The definition of "too
5023 many" is supplied by 4865 many" is supplied by this kernel boot parameter.
5024 4866
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 <<
5033 rcutree.qhimark= [KNL] 4867 rcutree.qhimark= [KNL]
5034 Set threshold of queu 4868 Set threshold of queued RCU callbacks beyond which
5035 batch limiting is dis 4869 batch limiting is disabled.
5036 4870
5037 rcutree.qlowmark= [KNL] 4871 rcutree.qlowmark= [KNL]
5038 Set threshold of queu 4872 Set threshold of queued RCU callbacks below which
5039 batch limiting is re- 4873 batch limiting is re-enabled.
5040 4874
5041 rcutree.qovld= [KNL] 4875 rcutree.qovld= [KNL]
5042 Set threshold of queu 4876 Set threshold of queued RCU callbacks beyond which
5043 RCU's force-quiescent 4877 RCU's force-quiescent-state scan will aggressively
5044 enlist help from cond 4878 enlist help from cond_resched() and sched IPIs to
5045 help CPUs more quickl 4879 help CPUs more quickly reach quiescent states.
5046 Set to less than zero 4880 Set to less than zero to make this be set based
5047 on rcutree.qhimark at 4881 on rcutree.qhimark at boot time and to zero to
5048 disable more aggressi 4882 disable more aggressive help enlistment.
5049 4883
5050 rcutree.rcu_delay_page_cache_fill_mse 4884 rcutree.rcu_delay_page_cache_fill_msec= [KNL]
5051 Set the page-cache re 4885 Set the page-cache refill delay (in milliseconds)
5052 in response to low-me 4886 in response to low-memory conditions. The range
5053 of permitted values i 4887 of permitted values is in the range 0:100000.
5054 4888
5055 rcutree.rcu_divisor= [KNL] 4889 rcutree.rcu_divisor= [KNL]
5056 Set the shift-right c 4890 Set the shift-right count to use to compute
5057 the callback-invocati 4891 the callback-invocation batch limit bl from
5058 the number of callbac 4892 the number of callbacks queued on this CPU.
5059 The result will be bo 4893 The result will be bounded below by the value of
5060 the rcutree.blimit ke 4894 the rcutree.blimit kernel parameter. Every bl
5061 callbacks, the softir 4895 callbacks, the softirq handler will exit in
5062 order to allow the CP 4896 order to allow the CPU to do other work.
5063 4897
5064 Please note that this 4898 Please note that this callback-invocation batch
5065 limit applies only to 4899 limit applies only to non-offloaded callback
5066 invocation. Offloade 4900 invocation. Offloaded callbacks are instead
5067 invoked in the contex 4901 invoked in the context of an rcuoc kthread, which
5068 scheduler will preemp 4902 scheduler will preempt as it does any other task.
5069 4903
5070 rcutree.rcu_fanout_exact= [KNL] 4904 rcutree.rcu_fanout_exact= [KNL]
5071 Disable autobalancing 4905 Disable autobalancing of the rcu_node combining
5072 tree. This is used b 4906 tree. This is used by rcutorture, and might
5073 possibly be useful fo 4907 possibly be useful for architectures having high
5074 cache-to-cache transf 4908 cache-to-cache transfer latencies.
5075 4909
5076 rcutree.rcu_fanout_leaf= [KNL] 4910 rcutree.rcu_fanout_leaf= [KNL]
5077 Change the number of 4911 Change the number of CPUs assigned to each
5078 leaf rcu_node structu 4912 leaf rcu_node structure. Useful for very
5079 large systems, which 4913 large systems, which will choose the value 64,
5080 and for NUMA systems 4914 and for NUMA systems with large remote-access
5081 latencies, which will 4915 latencies, which will choose a value aligned
5082 with the appropriate 4916 with the appropriate hardware boundaries.
5083 4917
5084 rcutree.rcu_min_cached_objs= [KNL] 4918 rcutree.rcu_min_cached_objs= [KNL]
5085 Minimum number of obj 4919 Minimum number of objects which are cached and
5086 maintained per one CP 4920 maintained per one CPU. Object size is equal
5087 to PAGE_SIZE. The cac 4921 to PAGE_SIZE. The cache allows to reduce the
5088 pressure to page allo 4922 pressure to page allocator, also it makes the
5089 whole algorithm to be 4923 whole algorithm to behave better in low memory
5090 condition. 4924 condition.
5091 4925
5092 rcutree.rcu_nocb_gp_stride= [KNL] 4926 rcutree.rcu_nocb_gp_stride= [KNL]
5093 Set the number of NOC 4927 Set the number of NOCB callback kthreads in
5094 each group, which def 4928 each group, which defaults to the square root
5095 of the number of CPUs 4929 of the number of CPUs. Larger numbers reduce
5096 the wakeup overhead o 4930 the wakeup overhead on the global grace-period
5097 kthread, but increase 4931 kthread, but increases that same overhead on
5098 each group's NOCB gra 4932 each group's NOCB grace-period kthread.
5099 4933
5100 rcutree.rcu_kick_kthreads= [KNL] 4934 rcutree.rcu_kick_kthreads= [KNL]
5101 Cause the grace-perio 4935 Cause the grace-period kthread to get an extra
5102 wake_up() if it sleep 4936 wake_up() if it sleeps three times longer than
5103 it should at force-qu 4937 it should at force-quiescent-state time.
5104 This wake_up() will b 4938 This wake_up() will be accompanied by a
5105 WARN_ONCE() splat and 4939 WARN_ONCE() splat and an ftrace_dump().
5106 4940
5107 rcutree.rcu_resched_ns= [KNL] 4941 rcutree.rcu_resched_ns= [KNL]
5108 Limit the time spend 4942 Limit the time spend invoking a batch of RCU
5109 callbacks to the spec 4943 callbacks to the specified number of nanoseconds.
5110 By default, this limi 4944 By default, this limit is checked only once
5111 every 32 callbacks in 4945 every 32 callbacks in order to limit the pain
5112 inflicted by local_cl 4946 inflicted by local_clock() overhead.
5113 4947
5114 rcutree.rcu_unlock_delay= [KNL] 4948 rcutree.rcu_unlock_delay= [KNL]
5115 In CONFIG_RCU_STRICT_ 4949 In CONFIG_RCU_STRICT_GRACE_PERIOD=y kernels,
5116 this specifies an rcu 4950 this specifies an rcu_read_unlock()-time delay
5117 in microseconds. Thi 4951 in microseconds. This defaults to zero.
5118 Larger delays increas 4952 Larger delays increase the probability of
5119 catching RCU pointer 4953 catching RCU pointer leaks, that is, buggy use
5120 of RCU-protected poin 4954 of RCU-protected pointers after the relevant
5121 rcu_read_unlock() has 4955 rcu_read_unlock() has completed.
5122 4956
5123 rcutree.sysrq_rcu= [KNL] 4957 rcutree.sysrq_rcu= [KNL]
5124 Commandeer a sysrq ke 4958 Commandeer a sysrq key to dump out Tree RCU's
5125 rcu_node tree with an 4959 rcu_node tree with an eye towards determining
5126 why a new grace perio 4960 why a new grace period has not yet started.
5127 4961
5128 rcutree.use_softirq= [KNL] 4962 rcutree.use_softirq= [KNL]
5129 If set to zero, move 4963 If set to zero, move all RCU_SOFTIRQ processing to
5130 per-CPU rcuc kthreads 4964 per-CPU rcuc kthreads. Defaults to a non-zero
5131 value, meaning that R 4965 value, meaning that RCU_SOFTIRQ is used by default.
5132 Specify rcutree.use_s 4966 Specify rcutree.use_softirq=0 to use rcuc kthreads.
5133 4967
5134 But note that CONFIG_ 4968 But note that CONFIG_PREEMPT_RT=y kernels disable
5135 this kernel boot para 4969 this kernel boot parameter, forcibly setting it
5136 to zero. 4970 to zero.
5137 4971
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] 4972 rcuscale.gp_async= [KNL]
5158 Measure performance o 4973 Measure performance of asynchronous
5159 grace-period primitiv 4974 grace-period primitives such as call_rcu().
5160 4975
5161 rcuscale.gp_async_max= [KNL] 4976 rcuscale.gp_async_max= [KNL]
5162 Specify the maximum n 4977 Specify the maximum number of outstanding
5163 callbacks per writer 4978 callbacks per writer thread. When a writer
5164 thread exceeds this l 4979 thread exceeds this limit, it invokes the
5165 corresponding flavor 4980 corresponding flavor of rcu_barrier() to allow
5166 previously posted cal 4981 previously posted callbacks to drain.
5167 4982
5168 rcuscale.gp_exp= [KNL] 4983 rcuscale.gp_exp= [KNL]
5169 Measure performance o 4984 Measure performance of expedited synchronous
5170 grace-period primitiv 4985 grace-period primitives.
5171 4986
5172 rcuscale.holdoff= [KNL] 4987 rcuscale.holdoff= [KNL]
5173 Set test-start holdof 4988 Set test-start holdoff period. The purpose of
5174 this parameter is to 4989 this parameter is to delay the start of the
5175 test until boot compl 4990 test until boot completes in order to avoid
5176 interference. 4991 interference.
5177 4992
5178 rcuscale.kfree_by_call_rcu= [KNL] 4993 rcuscale.kfree_by_call_rcu= [KNL]
5179 In kernels built with 4994 In kernels built with CONFIG_RCU_LAZY=y, test
5180 call_rcu() instead of 4995 call_rcu() instead of kfree_rcu().
5181 4996
5182 rcuscale.kfree_mult= [KNL] 4997 rcuscale.kfree_mult= [KNL]
5183 Instead of allocating 4998 Instead of allocating an object of size kfree_obj,
5184 allocate one of kfree 4999 allocate one of kfree_mult * sizeof(kfree_obj).
5185 Defaults to 1. 5000 Defaults to 1.
5186 5001
5187 rcuscale.kfree_rcu_test= [KNL] 5002 rcuscale.kfree_rcu_test= [KNL]
5188 Set to measure perfor 5003 Set to measure performance of kfree_rcu() flooding.
5189 5004
5190 rcuscale.kfree_rcu_test_double= [KNL] 5005 rcuscale.kfree_rcu_test_double= [KNL]
5191 Test the double-argum 5006 Test the double-argument variant of kfree_rcu().
5192 If this parameter has 5007 If this parameter has the same value as
5193 rcuscale.kfree_rcu_te 5008 rcuscale.kfree_rcu_test_single, both the single-
5194 and double-argument v 5009 and double-argument variants are tested.
5195 5010
5196 rcuscale.kfree_rcu_test_single= [KNL] 5011 rcuscale.kfree_rcu_test_single= [KNL]
5197 Test the single-argum 5012 Test the single-argument variant of kfree_rcu().
5198 If this parameter has 5013 If this parameter has the same value as
5199 rcuscale.kfree_rcu_te 5014 rcuscale.kfree_rcu_test_double, both the single-
5200 and double-argument v 5015 and double-argument variants are tested.
5201 5016
5202 rcuscale.kfree_nthreads= [KNL] 5017 rcuscale.kfree_nthreads= [KNL]
5203 The number of threads 5018 The number of threads running loops of kfree_rcu().
5204 5019
5205 rcuscale.kfree_alloc_num= [KNL] 5020 rcuscale.kfree_alloc_num= [KNL]
5206 Number of allocations 5021 Number of allocations and frees done in an iteration.
5207 5022
5208 rcuscale.kfree_loops= [KNL] 5023 rcuscale.kfree_loops= [KNL]
5209 Number of loops doing 5024 Number of loops doing rcuscale.kfree_alloc_num number
5210 of allocations and fr 5025 of allocations and frees.
5211 5026
5212 rcuscale.minruntime= [KNL] 5027 rcuscale.minruntime= [KNL]
5213 Set the minimum test 5028 Set the minimum test run time in seconds. This
5214 does not affect the d 5029 does not affect the data-collection interval,
5215 but instead allows be 5030 but instead allows better measurement of things
5216 like CPU consumption. 5031 like CPU consumption.
5217 5032
5218 rcuscale.nreaders= [KNL] 5033 rcuscale.nreaders= [KNL]
5219 Set number of RCU rea 5034 Set number of RCU readers. The value -1 selects
5220 N, where N is the num 5035 N, where N is the number of CPUs. A value
5221 "n" less than -1 sele 5036 "n" less than -1 selects N-n+1, where N is again
5222 the number of CPUs. 5037 the number of CPUs. For example, -2 selects N
5223 (the number of CPUs), 5038 (the number of CPUs), -3 selects N+1, and so on.
5224 A value of "n" less t 5039 A value of "n" less than or equal to -N selects
5225 a single reader. 5040 a single reader.
5226 5041
5227 rcuscale.nwriters= [KNL] 5042 rcuscale.nwriters= [KNL]
5228 Set number of RCU wri 5043 Set number of RCU writers. The values operate
5229 the same as for rcusc 5044 the same as for rcuscale.nreaders.
5230 N, where N is the num 5045 N, where N is the number of CPUs
5231 5046
5232 rcuscale.scale_type= [KNL] 5047 rcuscale.scale_type= [KNL]
5233 Specify the RCU imple 5048 Specify the RCU implementation to test.
5234 5049
5235 rcuscale.shutdown= [KNL] 5050 rcuscale.shutdown= [KNL]
5236 Shut the system down 5051 Shut the system down after performance tests
5237 complete. This is us 5052 complete. This is useful for hands-off automated
5238 testing. 5053 testing.
5239 5054
5240 rcuscale.verbose= [KNL] 5055 rcuscale.verbose= [KNL]
5241 Enable additional pri 5056 Enable additional printk() statements.
5242 5057
5243 rcuscale.writer_holdoff= [KNL] 5058 rcuscale.writer_holdoff= [KNL]
5244 Write-side holdoff be 5059 Write-side holdoff between grace periods,
5245 in microseconds. The 5060 in microseconds. The default of zero says
5246 no holdoff. 5061 no holdoff.
5247 5062
5248 rcuscale.writer_holdoff_jiffies= [KNL 5063 rcuscale.writer_holdoff_jiffies= [KNL]
5249 Additional write-side 5064 Additional write-side holdoff between grace
5250 periods, but in jiffi 5065 periods, but in jiffies. The default of zero
5251 says no holdoff. 5066 says no holdoff.
5252 5067
5253 rcutorture.fqs_duration= [KNL] 5068 rcutorture.fqs_duration= [KNL]
5254 Set duration of force 5069 Set duration of force_quiescent_state bursts
5255 in microseconds. 5070 in microseconds.
5256 5071
5257 rcutorture.fqs_holdoff= [KNL] 5072 rcutorture.fqs_holdoff= [KNL]
5258 Set holdoff time with 5073 Set holdoff time within force_quiescent_state bursts
5259 in microseconds. 5074 in microseconds.
5260 5075
5261 rcutorture.fqs_stutter= [KNL] 5076 rcutorture.fqs_stutter= [KNL]
5262 Set wait time between 5077 Set wait time between force_quiescent_state bursts
5263 in seconds. 5078 in seconds.
5264 5079
5265 rcutorture.fwd_progress= [KNL] 5080 rcutorture.fwd_progress= [KNL]
5266 Specifies the number 5081 Specifies the number of kthreads to be used
5267 for RCU grace-period 5082 for RCU grace-period forward-progress testing
5268 for the types of RCU 5083 for the types of RCU supporting this notion.
5269 Defaults to 1 kthread 5084 Defaults to 1 kthread, values less than zero or
5270 greater than the numb 5085 greater than the number of CPUs cause the number
5271 of CPUs to be used. 5086 of CPUs to be used.
5272 5087
5273 rcutorture.fwd_progress_div= [KNL] 5088 rcutorture.fwd_progress_div= [KNL]
5274 Specify the fraction 5089 Specify the fraction of a CPU-stall-warning
5275 period to do tight-lo 5090 period to do tight-loop forward-progress testing.
5276 5091
5277 rcutorture.fwd_progress_holdoff= [KNL 5092 rcutorture.fwd_progress_holdoff= [KNL]
5278 Number of seconds to 5093 Number of seconds to wait between successive
5279 forward-progress test 5094 forward-progress tests.
5280 5095
5281 rcutorture.fwd_progress_need_resched= 5096 rcutorture.fwd_progress_need_resched= [KNL]
5282 Enclose cond_resched( 5097 Enclose cond_resched() calls within checks for
5283 need_resched() during 5098 need_resched() during tight-loop forward-progress
5284 testing. 5099 testing.
5285 5100
5286 rcutorture.gp_cond= [KNL] 5101 rcutorture.gp_cond= [KNL]
5287 Use conditional/async 5102 Use conditional/asynchronous update-side
5288 primitives, if availa 5103 primitives, if available.
5289 5104
5290 rcutorture.gp_exp= [KNL] 5105 rcutorture.gp_exp= [KNL]
5291 Use expedited update- 5106 Use expedited update-side primitives, if available.
5292 5107
5293 rcutorture.gp_normal= [KNL] 5108 rcutorture.gp_normal= [KNL]
5294 Use normal (non-exped 5109 Use normal (non-expedited) asynchronous
5295 update-side primitive 5110 update-side primitives, if available.
5296 5111
5297 rcutorture.gp_sync= [KNL] 5112 rcutorture.gp_sync= [KNL]
5298 Use normal (non-exped 5113 Use normal (non-expedited) synchronous
5299 update-side primitive 5114 update-side primitives, if available. If all
5300 of rcutorture.gp_cond 5115 of rcutorture.gp_cond=, rcutorture.gp_exp=,
5301 rcutorture.gp_normal= 5116 rcutorture.gp_normal=, and rcutorture.gp_sync=
5302 are zero, rcutorture 5117 are zero, rcutorture acts as if is interpreted
5303 they are all non-zero 5118 they are all non-zero.
5304 5119
5305 rcutorture.irqreader= [KNL] 5120 rcutorture.irqreader= [KNL]
5306 Run RCU readers from 5121 Run RCU readers from irq handlers, or, more
5307 accurately, from a ti 5122 accurately, from a timer handler. Not all RCU
5308 flavors take kindly t 5123 flavors take kindly to this sort of thing.
5309 5124
5310 rcutorture.leakpointer= [KNL] 5125 rcutorture.leakpointer= [KNL]
5311 Leak an RCU-protected 5126 Leak an RCU-protected pointer out of the reader.
5312 This can of course re 5127 This can of course result in splats, and is
5313 intended to test the 5128 intended to test the ability of things like
5314 CONFIG_RCU_STRICT_GRA 5129 CONFIG_RCU_STRICT_GRACE_PERIOD=y to detect
5315 such leaks. 5130 such leaks.
5316 5131
5317 rcutorture.n_barrier_cbs= [KNL] 5132 rcutorture.n_barrier_cbs= [KNL]
5318 Set callbacks/threads 5133 Set callbacks/threads for rcu_barrier() testing.
5319 5134
5320 rcutorture.nfakewriters= [KNL] 5135 rcutorture.nfakewriters= [KNL]
5321 Set number of concurr 5136 Set number of concurrent RCU writers. These just
5322 stress RCU, they don' 5137 stress RCU, they don't participate in the actual
5323 test, hence the "fake 5138 test, hence the "fake".
5324 5139
5325 rcutorture.nocbs_nthreads= [KNL] 5140 rcutorture.nocbs_nthreads= [KNL]
5326 Set number of RCU cal 5141 Set number of RCU callback-offload togglers.
5327 Zero (the default) di 5142 Zero (the default) disables toggling.
5328 5143
5329 rcutorture.nocbs_toggle= [KNL] 5144 rcutorture.nocbs_toggle= [KNL]
5330 Set the delay in mill 5145 Set the delay in milliseconds between successive
5331 callback-offload togg 5146 callback-offload toggling attempts.
5332 5147
5333 rcutorture.nreaders= [KNL] 5148 rcutorture.nreaders= [KNL]
5334 Set number of RCU rea 5149 Set number of RCU readers. The value -1 selects
5335 N-1, where N is the n 5150 N-1, where N is the number of CPUs. A value
5336 "n" less than -1 sele 5151 "n" less than -1 selects N-n-2, where N is again
5337 the number of CPUs. 5152 the number of CPUs. For example, -2 selects N
5338 (the number of CPUs), 5153 (the number of CPUs), -3 selects N+1, and so on.
5339 5154
5340 rcutorture.object_debug= [KNL] 5155 rcutorture.object_debug= [KNL]
5341 Enable debug-object d 5156 Enable debug-object double-call_rcu() testing.
5342 5157
5343 rcutorture.onoff_holdoff= [KNL] 5158 rcutorture.onoff_holdoff= [KNL]
5344 Set time (s) after bo 5159 Set time (s) after boot for CPU-hotplug testing.
5345 5160
5346 rcutorture.onoff_interval= [KNL] 5161 rcutorture.onoff_interval= [KNL]
5347 Set time (jiffies) be 5162 Set time (jiffies) between CPU-hotplug operations,
5348 or zero to disable CP 5163 or zero to disable CPU-hotplug testing.
5349 5164
5350 rcutorture.read_exit= [KNL] 5165 rcutorture.read_exit= [KNL]
5351 Set the number of rea 5166 Set the number of read-then-exit kthreads used
5352 to test the interacti 5167 to test the interaction of RCU updaters and
5353 task-exit processing. 5168 task-exit processing.
5354 5169
5355 rcutorture.read_exit_burst= [KNL] 5170 rcutorture.read_exit_burst= [KNL]
5356 The number of times i 5171 The number of times in a given read-then-exit
5357 episode that a set of 5172 episode that a set of read-then-exit kthreads
5358 is spawned. 5173 is spawned.
5359 5174
5360 rcutorture.read_exit_delay= [KNL] 5175 rcutorture.read_exit_delay= [KNL]
5361 The delay, in seconds 5176 The delay, in seconds, between successive
5362 read-then-exit testin 5177 read-then-exit testing episodes.
5363 5178
5364 rcutorture.shuffle_interval= [KNL] 5179 rcutorture.shuffle_interval= [KNL]
5365 Set task-shuffle inte 5180 Set task-shuffle interval (s). Shuffling tasks
5366 allows some CPUs to g 5181 allows some CPUs to go into dyntick-idle mode
5367 during the rcutorture 5182 during the rcutorture test.
5368 5183
5369 rcutorture.shutdown_secs= [KNL] 5184 rcutorture.shutdown_secs= [KNL]
5370 Set time (s) after bo 5185 Set time (s) after boot system shutdown. This
5371 is useful for hands-o 5186 is useful for hands-off automated testing.
5372 5187
5373 rcutorture.stall_cpu= [KNL] 5188 rcutorture.stall_cpu= [KNL]
5374 Duration of CPU stall 5189 Duration of CPU stall (s) to test RCU CPU stall
5375 warnings, zero to dis 5190 warnings, zero to disable.
5376 5191
5377 rcutorture.stall_cpu_block= [KNL] 5192 rcutorture.stall_cpu_block= [KNL]
5378 Sleep while stalling 5193 Sleep while stalling if set. This will result
5379 in warnings from pree 5194 in warnings from preemptible RCU in addition to
5380 any other stall-relat 5195 any other stall-related activity. Note that
5381 in kernels built with 5196 in kernels built with CONFIG_PREEMPTION=n and
5382 CONFIG_PREEMPT_COUNT= 5197 CONFIG_PREEMPT_COUNT=y, this parameter will
5383 cause the CPU to pass 5198 cause the CPU to pass through a quiescent state.
5384 Given CONFIG_PREEMPTI 5199 Given CONFIG_PREEMPTION=n, this will suppress
5385 RCU CPU stall warning 5200 RCU CPU stall warnings, but will instead result
5386 in scheduling-while-a 5201 in scheduling-while-atomic splats.
5387 5202
5388 Use of this module pa 5203 Use of this module parameter results in splats.
5389 5204
5390 5205
5391 rcutorture.stall_cpu_holdoff= [KNL] 5206 rcutorture.stall_cpu_holdoff= [KNL]
5392 Time to wait (s) afte 5207 Time to wait (s) after boot before inducing stall.
5393 5208
5394 rcutorture.stall_cpu_irqsoff= [KNL] 5209 rcutorture.stall_cpu_irqsoff= [KNL]
5395 Disable interrupts wh 5210 Disable interrupts while stalling if set.
5396 5211
5397 rcutorture.stall_gp_kthread= [KNL] 5212 rcutorture.stall_gp_kthread= [KNL]
5398 Duration (s) of force 5213 Duration (s) of forced sleep within RCU
5399 grace-period kthread 5214 grace-period kthread to test RCU CPU stall
5400 warnings, zero to dis 5215 warnings, zero to disable. If both stall_cpu
5401 and stall_gp_kthread 5216 and stall_gp_kthread are specified, the
5402 kthread is starved fi 5217 kthread is starved first, then the CPU.
5403 5218
5404 rcutorture.stat_interval= [KNL] 5219 rcutorture.stat_interval= [KNL]
5405 Time (s) between stat 5220 Time (s) between statistics printk()s.
5406 5221
5407 rcutorture.stutter= [KNL] 5222 rcutorture.stutter= [KNL]
5408 Time (s) to stutter t 5223 Time (s) to stutter testing, for example, specifying
5409 five seconds causes t 5224 five seconds causes the test to run for five seconds,
5410 wait for five seconds 5225 wait for five seconds, and so on. This tests RCU's
5411 ability to transition 5226 ability to transition abruptly to and from idle.
5412 5227
5413 rcutorture.test_boost= [KNL] 5228 rcutorture.test_boost= [KNL]
5414 Test RCU priority boo 5229 Test RCU priority boosting? 0=no, 1=maybe, 2=yes.
5415 "Maybe" means test if 5230 "Maybe" means test if the RCU implementation
5416 under test support RC 5231 under test support RCU priority boosting.
5417 5232
5418 rcutorture.test_boost_duration= [KNL] 5233 rcutorture.test_boost_duration= [KNL]
5419 Duration (s) of each 5234 Duration (s) of each individual boost test.
5420 5235
5421 rcutorture.test_boost_interval= [KNL] 5236 rcutorture.test_boost_interval= [KNL]
5422 Interval (s) between 5237 Interval (s) between each boost test.
5423 5238
5424 rcutorture.test_no_idle_hz= [KNL] 5239 rcutorture.test_no_idle_hz= [KNL]
5425 Test RCU's dyntick-id 5240 Test RCU's dyntick-idle handling. See also the
5426 rcutorture.shuffle_in 5241 rcutorture.shuffle_interval parameter.
5427 5242
5428 rcutorture.torture_type= [KNL] 5243 rcutorture.torture_type= [KNL]
5429 Specify the RCU imple 5244 Specify the RCU implementation to test.
5430 5245
5431 rcutorture.verbose= [KNL] 5246 rcutorture.verbose= [KNL]
5432 Enable additional pri 5247 Enable additional printk() statements.
5433 5248
5434 rcupdate.rcu_cpu_stall_ftrace_dump= [ 5249 rcupdate.rcu_cpu_stall_ftrace_dump= [KNL]
5435 Dump ftrace buffer af 5250 Dump ftrace buffer after reporting RCU CPU
5436 stall warning. 5251 stall warning.
5437 5252
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 5253 rcupdate.rcu_cpu_stall_suppress= [KNL]
5445 Suppress RCU CPU stal 5254 Suppress RCU CPU stall warning messages.
5446 5255
5447 rcupdate.rcu_cpu_stall_suppress_at_bo 5256 rcupdate.rcu_cpu_stall_suppress_at_boot= [KNL]
5448 Suppress RCU CPU stal 5257 Suppress RCU CPU stall warning messages and
5449 rcutorture writer sta 5258 rcutorture writer stall warnings that occur
5450 during early boot, th 5259 during early boot, that is, during the time
5451 before the init task 5260 before the init task is spawned.
5452 5261
5453 rcupdate.rcu_cpu_stall_timeout= [KNL] 5262 rcupdate.rcu_cpu_stall_timeout= [KNL]
5454 Set timeout for RCU C 5263 Set timeout for RCU CPU stall warning messages.
5455 The value is in secon 5264 The value is in seconds and the maximum allowed
5456 value is 300 seconds. 5265 value is 300 seconds.
5457 5266
5458 rcupdate.rcu_exp_cpu_stall_timeout= [ 5267 rcupdate.rcu_exp_cpu_stall_timeout= [KNL]
5459 Set timeout for exped 5268 Set timeout for expedited RCU CPU stall warning
5460 messages. The value 5269 messages. The value is in milliseconds
5461 and the maximum allow 5270 and the maximum allowed value is 21000
5462 milliseconds. Please 5271 milliseconds. Please note that this value is
5463 adjusted to an arch t 5272 adjusted to an arch timer tick resolution.
5464 Setting this to zero 5273 Setting this to zero causes the value from
5465 rcupdate.rcu_cpu_stal 5274 rcupdate.rcu_cpu_stall_timeout to be used (after
5466 conversion from secon 5275 conversion from seconds to milliseconds).
5467 5276
5468 rcupdate.rcu_cpu_stall_cputime= [KNL] 5277 rcupdate.rcu_cpu_stall_cputime= [KNL]
5469 Provide statistics on 5278 Provide statistics on the cputime and count of
5470 interrupts and tasks 5279 interrupts and tasks during the sampling period. For
5471 multiple continuous R 5280 multiple continuous RCU stalls, all sampling periods
5472 begin at half of the 5281 begin at half of the first RCU stall timeout.
5473 5282
5474 rcupdate.rcu_exp_stall_task_details= 5283 rcupdate.rcu_exp_stall_task_details= [KNL]
5475 Print stack dumps of 5284 Print stack dumps of any tasks blocking the
5476 current expedited RCU 5285 current expedited RCU grace period during an
5477 expedited RCU CPU sta 5286 expedited RCU CPU stall warning.
5478 5287
5479 rcupdate.rcu_expedited= [KNL] 5288 rcupdate.rcu_expedited= [KNL]
5480 Use expedited grace-p 5289 Use expedited grace-period primitives, for
5481 example, synchronize_ 5290 example, synchronize_rcu_expedited() instead
5482 of synchronize_rcu(). 5291 of synchronize_rcu(). This reduces latency,
5483 but can increase CPU 5292 but can increase CPU utilization, degrade
5484 real-time latency, an 5293 real-time latency, and degrade energy efficiency.
5485 No effect on CONFIG_T 5294 No effect on CONFIG_TINY_RCU kernels.
5486 5295
5487 rcupdate.rcu_normal= [KNL] 5296 rcupdate.rcu_normal= [KNL]
5488 Use only normal grace 5297 Use only normal grace-period primitives,
5489 for example, synchron 5298 for example, synchronize_rcu() instead of
5490 synchronize_rcu_exped 5299 synchronize_rcu_expedited(). This improves
5491 real-time latency, CP 5300 real-time latency, CPU utilization, and
5492 energy efficiency, bu 5301 energy efficiency, but can expose users to
5493 increased grace-perio 5302 increased grace-period latency. This parameter
5494 overrides rcupdate.rc 5303 overrides rcupdate.rcu_expedited. No effect on
5495 CONFIG_TINY_RCU kerne 5304 CONFIG_TINY_RCU kernels.
5496 5305
5497 rcupdate.rcu_normal_after_boot= [KNL] 5306 rcupdate.rcu_normal_after_boot= [KNL]
5498 Once boot has complet 5307 Once boot has completed (that is, after
5499 rcu_end_inkernel_boot 5308 rcu_end_inkernel_boot() has been invoked), use
5500 only normal grace-per 5309 only normal grace-period primitives. No effect
5501 on CONFIG_TINY_RCU ke 5310 on CONFIG_TINY_RCU kernels.
5502 5311
5503 But note that CONFIG_ 5312 But note that CONFIG_PREEMPT_RT=y kernels enables
5504 this kernel boot para 5313 this kernel boot parameter, forcibly setting
5505 it to the value one, 5314 it to the value one, that is, converting any
5506 post-boot attempt at 5315 post-boot attempt at an expedited RCU grace
5507 period to instead use 5316 period to instead use normal non-expedited
5508 grace-period processi 5317 grace-period processing.
5509 5318
5510 rcupdate.rcu_task_collapse_lim= [KNL] 5319 rcupdate.rcu_task_collapse_lim= [KNL]
5511 Set the maximum numbe 5320 Set the maximum number of callbacks present
5512 at the beginning of a 5321 at the beginning of a grace period that allows
5513 the RCU Tasks flavors 5322 the RCU Tasks flavors to collapse back to using
5514 a single callback que 5323 a single callback queue. This switching only
5515 occurs when rcupdate. 5324 occurs when rcupdate.rcu_task_enqueue_lim is
5516 set to the default va 5325 set to the default value of -1.
5517 5326
5518 rcupdate.rcu_task_contend_lim= [KNL] 5327 rcupdate.rcu_task_contend_lim= [KNL]
5519 Set the minimum numbe 5328 Set the minimum number of callback-queuing-time
5520 lock-contention event 5329 lock-contention events per jiffy required to
5521 cause the RCU Tasks f 5330 cause the RCU Tasks flavors to switch to per-CPU
5522 callback queuing. Th 5331 callback queuing. This switching only occurs
5523 when rcupdate.rcu_tas 5332 when rcupdate.rcu_task_enqueue_lim is set to
5524 the default value of 5333 the default value of -1.
5525 5334
5526 rcupdate.rcu_task_enqueue_lim= [KNL] 5335 rcupdate.rcu_task_enqueue_lim= [KNL]
5527 Set the number of cal 5336 Set the number of callback queues to use for the
5528 RCU Tasks family of R 5337 RCU Tasks family of RCU flavors. The default
5529 of -1 allows this to 5338 of -1 allows this to be automatically (and
5530 dynamically) adjusted 5339 dynamically) adjusted. This parameter is intended
5531 for use in testing. 5340 for use in testing.
5532 5341
5533 rcupdate.rcu_task_ipi_delay= [KNL] 5342 rcupdate.rcu_task_ipi_delay= [KNL]
5534 Set time in jiffies d 5343 Set time in jiffies during which RCU tasks will
5535 avoid sending IPIs, s 5344 avoid sending IPIs, starting with the beginning
5536 of a given grace peri 5345 of a given grace period. Setting a large
5537 number avoids disturb 5346 number avoids disturbing real-time workloads,
5538 but lengthens grace p 5347 but lengthens grace periods.
5539 5348
5540 rcupdate.rcu_task_lazy_lim= [KNL] 5349 rcupdate.rcu_task_lazy_lim= [KNL]
5541 Number of callbacks o 5350 Number of callbacks on a given CPU that will
5542 cancel laziness on th 5351 cancel laziness on that CPU. Use -1 to disable
5543 cancellation of lazin 5352 cancellation of laziness, but be advised that
5544 doing so increases th 5353 doing so increases the danger of OOM due to
5545 callback flooding. 5354 callback flooding.
5546 5355
5547 rcupdate.rcu_task_stall_info= [KNL] 5356 rcupdate.rcu_task_stall_info= [KNL]
5548 Set initial timeout i 5357 Set initial timeout in jiffies for RCU task stall
5549 informational message 5358 informational messages, which give some indication
5550 of the problem for th 5359 of the problem for those not patient enough to
5551 wait for ten minutes. 5360 wait for ten minutes. Informational messages are
5552 only printed prior to 5361 only printed prior to the stall-warning message
5553 for a given grace per 5362 for a given grace period. Disable with a value
5554 less than or equal to 5363 less than or equal to zero. Defaults to ten
5555 seconds. A change in 5364 seconds. A change in value does not take effect
5556 until the beginning o 5365 until the beginning of the next grace period.
5557 5366
5558 rcupdate.rcu_task_stall_info_mult= [K 5367 rcupdate.rcu_task_stall_info_mult= [KNL]
5559 Multiplier for time i 5368 Multiplier for time interval between successive
5560 RCU task stall inform 5369 RCU task stall informational messages for a given
5561 RCU tasks grace perio 5370 RCU tasks grace period. This value is clamped
5562 to one through ten, i 5371 to one through ten, inclusive. It defaults to
5563 the value three, so t 5372 the value three, so that the first informational
5564 message is printed 10 5373 message is printed 10 seconds into the grace
5565 period, the second at 5374 period, the second at 40 seconds, the third at
5566 160 seconds, and then 5375 160 seconds, and then the stall warning at 600
5567 seconds would prevent 5376 seconds would prevent a fourth at 640 seconds.
5568 5377
5569 rcupdate.rcu_task_stall_timeout= [KNL 5378 rcupdate.rcu_task_stall_timeout= [KNL]
5570 Set timeout in jiffie 5379 Set timeout in jiffies for RCU task stall
5571 warning messages. Di 5380 warning messages. Disable with a value less
5572 than or equal to zero 5381 than or equal to zero. Defaults to ten minutes.
5573 A change in value doe 5382 A change in value does not take effect until
5574 the beginning of the 5383 the beginning of the next grace period.
5575 5384
5576 rcupdate.rcu_tasks_lazy_ms= [KNL] 5385 rcupdate.rcu_tasks_lazy_ms= [KNL]
5577 Set timeout in millis 5386 Set timeout in milliseconds RCU Tasks asynchronous
5578 callback batching for 5387 callback batching for call_rcu_tasks().
5579 A negative value will 5388 A negative value will take the default. A value
5580 of zero will disable 5389 of zero will disable batching. Batching is
5581 always disabled for s 5390 always disabled for synchronize_rcu_tasks().
5582 5391
5583 rcupdate.rcu_tasks_rude_lazy_ms= [KNL 5392 rcupdate.rcu_tasks_rude_lazy_ms= [KNL]
5584 Set timeout in millis 5393 Set timeout in milliseconds RCU Tasks
5585 Rude asynchronous cal 5394 Rude asynchronous callback batching for
5586 call_rcu_tasks_rude() 5395 call_rcu_tasks_rude(). A negative value
5587 will take the default 5396 will take the default. A value of zero will
5588 disable batching. Ba 5397 disable batching. Batching is always disabled
5589 for synchronize_rcu_t 5398 for synchronize_rcu_tasks_rude().
5590 5399
5591 rcupdate.rcu_tasks_trace_lazy_ms= [KN 5400 rcupdate.rcu_tasks_trace_lazy_ms= [KNL]
5592 Set timeout in millis 5401 Set timeout in milliseconds RCU Tasks
5593 Trace asynchronous ca 5402 Trace asynchronous callback batching for
5594 call_rcu_tasks_trace( 5403 call_rcu_tasks_trace(). A negative value
5595 will take the default 5404 will take the default. A value of zero will
5596 disable batching. Ba 5405 disable batching. Batching is always disabled
5597 for synchronize_rcu_t 5406 for synchronize_rcu_tasks_trace().
5598 5407
5599 rcupdate.rcu_self_test= [KNL] 5408 rcupdate.rcu_self_test= [KNL]
5600 Run the RCU early boo 5409 Run the RCU early boot self tests
5601 5410
5602 rdinit= [KNL] 5411 rdinit= [KNL]
5603 Format: <full_path> 5412 Format: <full_path>
5604 Run specified binary 5413 Run specified binary instead of /init from the ramdisk,
5605 used for early usersp 5414 used for early userspace startup. See initrd.
5606 5415
5607 rdrand= [X86,EARLY] !! 5416 rdrand= [X86]
5608 force - Override the 5417 force - Override the decision by the kernel to hide the
5609 advertisement 5418 advertisement of RDRAND support (this affects
5610 certain AMD p 5419 certain AMD processors because of buggy BIOS
5611 support, spec 5420 support, specifically around the suspend/resume
5612 path). 5421 path).
5613 5422
5614 rdt= [HW,X86,RDT] 5423 rdt= [HW,X86,RDT]
5615 Turn on/off individua 5424 Turn on/off individual RDT features. List is:
5616 cmt, mbmtotal, mbmloc 5425 cmt, mbmtotal, mbmlocal, l3cat, l3cdp, l2cat, l2cdp,
5617 mba, smba, bmec. 5426 mba, smba, bmec.
5618 E.g. to turn on cmt a 5427 E.g. to turn on cmt and turn off mba use:
5619 rdt=cmt,!mba 5428 rdt=cmt,!mba
5620 5429
5621 reboot= [KNL] 5430 reboot= [KNL]
5622 Format (x86 or x86_64 5431 Format (x86 or x86_64):
5623 [w[arm] | c[o 5432 [w[arm] | c[old] | h[ard] | s[oft] | g[pio]] | d[efault] \
5624 [[,]s[mp]#### 5433 [[,]s[mp]#### \
5625 [[,]b[ios] | 5434 [[,]b[ios] | a[cpi] | k[bd] | t[riple] | e[fi] | p[ci]] \
5626 [[,]f[orce] 5435 [[,]f[orce]
5627 Where reboot_mode is 5436 Where reboot_mode is one of warm (soft) or cold (hard) or gpio
5628 (pref 5437 (prefix with 'panic_' to set mode for panic
5629 reboo 5438 reboot only),
5630 reboot_type is 5439 reboot_type is one of bios, acpi, kbd, triple, efi, or pci,
5631 reboot_force is 5440 reboot_force is either force or not specified,
5632 reboot_cpu is s 5441 reboot_cpu is s[mp]#### with #### being the processor
5633 to be 5442 to be used for rebooting.
5634 5443
5635 refscale.holdoff= [KNL] 5444 refscale.holdoff= [KNL]
5636 Set test-start holdof 5445 Set test-start holdoff period. The purpose of
5637 this parameter is to 5446 this parameter is to delay the start of the
5638 test until boot compl 5447 test until boot completes in order to avoid
5639 interference. 5448 interference.
5640 5449
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] 5450 refscale.loops= [KNL]
5648 Set the number of loo 5451 Set the number of loops over the synchronization
5649 primitive under test. 5452 primitive under test. Increasing this number
5650 reduces noise due to 5453 reduces noise due to loop start/end overhead,
5651 but the default has a 5454 but the default has already reduced the per-pass
5652 noise to a handful of 5455 noise to a handful of picoseconds on ca. 2020
5653 x86 laptops. 5456 x86 laptops.
5654 5457
5655 refscale.nreaders= [KNL] 5458 refscale.nreaders= [KNL]
5656 Set number of readers 5459 Set number of readers. The default value of -1
5657 selects N, where N is 5460 selects N, where N is roughly 75% of the number
5658 of CPUs. A value of 5461 of CPUs. A value of zero is an interesting choice.
5659 5462
5660 refscale.nruns= [KNL] 5463 refscale.nruns= [KNL]
5661 Set number of runs, e 5464 Set number of runs, each of which is dumped onto
5662 the console log. 5465 the console log.
5663 5466
5664 refscale.readdelay= [KNL] 5467 refscale.readdelay= [KNL]
5665 Set the read-side cri 5468 Set the read-side critical-section duration,
5666 measured in microseco 5469 measured in microseconds.
5667 5470
5668 refscale.scale_type= [KNL] 5471 refscale.scale_type= [KNL]
5669 Specify the read-prot 5472 Specify the read-protection implementation to test.
5670 5473
5671 refscale.shutdown= [KNL] 5474 refscale.shutdown= [KNL]
5672 Shut down the system 5475 Shut down the system at the end of the performance
5673 test. This defaults 5476 test. This defaults to 1 (shut it down) when
5674 refscale is built int 5477 refscale is built into the kernel and to 0 (leave
5675 it running) when refs 5478 it running) when refscale is built as a module.
5676 5479
5677 refscale.verbose= [KNL] 5480 refscale.verbose= [KNL]
5678 Enable additional pri 5481 Enable additional printk() statements.
5679 5482
5680 refscale.verbose_batched= [KNL] 5483 refscale.verbose_batched= [KNL]
5681 Batch the additional 5484 Batch the additional printk() statements. If zero
5682 (the default) or nega 5485 (the default) or negative, print everything. Otherwise,
5683 print every Nth verbo 5486 print every Nth verbose statement, where N is the value
5684 specified. 5487 specified.
5685 5488
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= 5489 relax_domain_level=
5694 [KNL, SMP] Set schedu 5490 [KNL, SMP] Set scheduler's default relax_domain_level.
5695 See Documentation/adm 5491 See Documentation/admin-guide/cgroup-v1/cpusets.rst.
5696 5492
5697 reserve= [KNL,BUGS] Force kern 5493 reserve= [KNL,BUGS] Force kernel to ignore I/O ports or memory
5698 Format: <base1>,<size 5494 Format: <base1>,<size1>[,<base2>,<size2>,...]
5699 Reserve I/O ports or 5495 Reserve I/O ports or memory so the kernel won't use
5700 them. If <base> is l 5496 them. If <base> is less than 0x10000, the region
5701 is assumed to be I/O 5497 is assumed to be I/O ports; otherwise it is memory.
5702 5498
5703 reserve_mem= [RAM] !! 5499 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] 5500 Format: nn[KMG]
5727 Reserves a hole at th 5501 Reserves a hole at the top of the kernel virtual
5728 address space. 5502 address space.
5729 5503
5730 reset_devices [KNL] Force drivers t 5504 reset_devices [KNL] Force drivers to reset the underlying device
5731 during initialization 5505 during initialization.
5732 5506
5733 resume= [SWSUSP] 5507 resume= [SWSUSP]
5734 Specify the partition 5508 Specify the partition device for software suspend
5735 Format: 5509 Format:
5736 {/dev/<dev> | PARTUUI 5510 {/dev/<dev> | PARTUUID=<uuid> | <int>:<int> | <hex>}
5737 5511
5738 resume_offset= [SWSUSP] 5512 resume_offset= [SWSUSP]
5739 Specify the offset fr 5513 Specify the offset from the beginning of the partition
5740 given by "resume=" at 5514 given by "resume=" at which the swap header is located,
5741 in <PAGE_SIZE> units 5515 in <PAGE_SIZE> units (needed only for swap files).
5742 See Documentation/po 5516 See Documentation/power/swsusp-and-swap-files.rst
5743 5517
5744 resumedelay= [HIBERNATION] Delay ( 5518 resumedelay= [HIBERNATION] Delay (in seconds) to pause before attempting to
5745 read the resume files 5519 read the resume files
5746 5520
5747 resumewait [HIBERNATION] Wait (i 5521 resumewait [HIBERNATION] Wait (indefinitely) for resume device to show up.
5748 Useful for devices th 5522 Useful for devices that are detected asynchronously
5749 (e.g. USB and MMC dev 5523 (e.g. USB and MMC devices).
5750 5524
5751 retain_initrd [RAM] Keep initrd mem !! 5525 retain_initrd [RAM] Keep initrd memory after extraction
5752 be accessible via /sy <<
5753 5526
5754 retbleed= [X86] Control mitigat 5527 retbleed= [X86] Control mitigation of RETBleed (Arbitrary
5755 Speculative Code Exec 5528 Speculative Code Execution with Return Instructions)
5756 vulnerability. 5529 vulnerability.
5757 5530
5758 AMD-based UNRET and I 5531 AMD-based UNRET and IBPB mitigations alone do not stop
5759 sibling threads from 5532 sibling threads from influencing the predictions of other
5760 sibling threads. For 5533 sibling threads. For that reason, STIBP is used on pro-
5761 cessors that support 5534 cessors that support it, and mitigate SMT on processors
5762 that don't. 5535 that don't.
5763 5536
5764 off - no mit 5537 off - no mitigation
5765 auto - automa 5538 auto - automatically select a migitation
5766 auto,nosmt - automa 5539 auto,nosmt - automatically select a mitigation,
5767 disabl 5540 disabling SMT if necessary for
5768 the fu 5541 the full mitigation (only on Zen1
5769 and ol 5542 and older without STIBP).
5770 ibpb - On AMD 5543 ibpb - On AMD, mitigate short speculation
5771 window 5544 windows on basic block boundaries too.
5772 Safe, 5545 Safe, highest perf impact. It also
5773 enable 5546 enables STIBP if present. Not suitable
5774 on Int 5547 on Intel.
5775 ibpb,nosmt - Like " 5548 ibpb,nosmt - Like "ibpb" above but will disable SMT
5776 when S 5549 when STIBP is not available. This is
5777 the al 5550 the alternative for systems which do not
5778 have S 5551 have STIBP.
5779 unret - Force 5552 unret - Force enable untrained return thunks,
5780 only e 5553 only effective on AMD f15h-f17h based
5781 system 5554 systems.
5782 unret,nosmt - Like u 5555 unret,nosmt - Like unret, but will disable SMT when STIBP
5783 is not 5556 is not available. This is the alternative for
5784 system 5557 systems which do not have STIBP.
5785 5558
5786 Selecting 'auto' will 5559 Selecting 'auto' will choose a mitigation method at run
5787 time according to the 5560 time according to the CPU.
5788 5561
5789 Not specifying this o 5562 Not specifying this option is equivalent to retbleed=auto.
5790 5563
5791 rfkill.default_state= 5564 rfkill.default_state=
5792 0 "airplane mode". All 5565 0 "airplane mode". All wifi, bluetooth, wimax, gps, fm,
5793 etc. communication is 5566 etc. communication is blocked by default.
5794 1 Unblocked. 5567 1 Unblocked.
5795 5568
5796 rfkill.master_switch_mode= 5569 rfkill.master_switch_mode=
5797 0 The "airplane mode" b 5570 0 The "airplane mode" button does nothing.
5798 1 The "airplane mode" b 5571 1 The "airplane mode" button toggles between everything
5799 blocked and the previ 5572 blocked and the previous configuration.
5800 2 The "airplane mode" b 5573 2 The "airplane mode" button toggles between everything
5801 blocked and everythin 5574 blocked and everything unblocked.
5802 5575
>> 5576 rhash_entries= [KNL,NET]
>> 5577 Set number of hash buckets for route cache
>> 5578
5803 ring3mwait=disable 5579 ring3mwait=disable
5804 [KNL] Disable ring 3 5580 [KNL] Disable ring 3 MONITOR/MWAIT feature on supported
5805 CPUs. 5581 CPUs.
5806 5582
5807 riscv_isa_fallback [RISCV,EARLY] !! 5583 riscv_isa_fallback [RISCV]
5808 When CONFIG_RISCV_ISA 5584 When CONFIG_RISCV_ISA_FALLBACK is not enabled, permit
5809 falling back to detec 5585 falling back to detecting extension support by parsing
5810 "riscv,isa" property 5586 "riscv,isa" property on devicetree systems when the
5811 replacement propertie 5587 replacement properties are not found. See the Kconfig
5812 entry for RISCV_ISA_F 5588 entry for RISCV_ISA_FALLBACK.
5813 5589
5814 ro [KNL] Mount root devi 5590 ro [KNL] Mount root device read-only on boot
5815 5591
5816 rodata= [KNL,EARLY] !! 5592 rodata= [KNL]
5817 on Mark read-only kernel 5593 on Mark read-only kernel memory as read-only (default).
5818 off Leave read-only kerne 5594 off Leave read-only kernel memory writable for debugging.
5819 full Mark read-only kernel 5595 full Mark read-only kernel memory and aliases as read-only
5820 [arm64] 5596 [arm64]
5821 5597
5822 rockchip.usb_uart 5598 rockchip.usb_uart
5823 [EARLY] <<
5824 Enable the uart passt 5599 Enable the uart passthrough on the designated usb port
5825 on Rockchip SoCs. Whe 5600 on Rockchip SoCs. When active, the signals of the
5826 debug-uart get routed 5601 debug-uart get routed to the D+ and D- pins of the usb
5827 port and the regular 5602 port and the regular usb controller gets disabled.
5828 5603
5829 root= [KNL] Root filesystem 5604 root= [KNL] Root filesystem
5830 Usually this a a bloc 5605 Usually this a a block device specifier of some kind,
5831 see the early_lookup_ 5606 see the early_lookup_bdev comment in
5832 block/early-lookup.c 5607 block/early-lookup.c for details.
5833 Alternatively this ca 5608 Alternatively this can be "ram" for the legacy initial
5834 ramdisk, "nfs" and "c 5609 ramdisk, "nfs" and "cifs" for root on a network file
5835 system, or "mtd" and 5610 system, or "mtd" and "ubi" for mounting from raw flash.
5836 5611
5837 rootdelay= [KNL] Delay (in secon 5612 rootdelay= [KNL] Delay (in seconds) to pause before attempting to
5838 mount the root filesy 5613 mount the root filesystem
5839 5614
5840 rootflags= [KNL] Set root filesy 5615 rootflags= [KNL] Set root filesystem mount option string
5841 5616
5842 rootfstype= [KNL] Set root filesy 5617 rootfstype= [KNL] Set root filesystem type
5843 5618
5844 rootwait [KNL] Wait (indefinit 5619 rootwait [KNL] Wait (indefinitely) for root device to show up.
5845 Useful for devices th 5620 Useful for devices that are detected asynchronously
5846 (e.g. USB and MMC dev 5621 (e.g. USB and MMC devices).
5847 5622
5848 rootwait= [KNL] Maximum time (i 5623 rootwait= [KNL] Maximum time (in seconds) to wait for root device
5849 to show up before att 5624 to show up before attempting to mount the root
5850 filesystem. 5625 filesystem.
5851 5626
5852 rproc_mem=nn[KMG][@address] 5627 rproc_mem=nn[KMG][@address]
5853 [KNL,ARM,CMA] Remotep 5628 [KNL,ARM,CMA] Remoteproc physical memory block.
5854 Memory area to be use 5629 Memory area to be used by remote processor image,
5855 managed by CMA. 5630 managed by CMA.
5856 5631
5857 rw [KNL] Mount root devi 5632 rw [KNL] Mount root device read-write on boot
5858 5633
5859 S [KNL] Run init in sin 5634 S [KNL] Run init in single mode
5860 5635
5861 s390_iommu= [HW,S390] 5636 s390_iommu= [HW,S390]
5862 Set s390 IOTLB flushi 5637 Set s390 IOTLB flushing mode
5863 strict 5638 strict
5864 With strict flushing !! 5639 With strict flushing every unmap operation will result in
5865 in an IOTLB flush. De !! 5640 an IOTLB flush. Default is lazy flushing before reuse,
5866 reuse, which is faste !! 5641 which is faster.
5867 iommu.strict=1. <<
5868 5642
5869 s390_iommu_aperture= [KNL,S390] 5643 s390_iommu_aperture= [KNL,S390]
5870 Specifies the size of 5644 Specifies the size of the per device DMA address space
5871 accessible through th 5645 accessible through the DMA and IOMMU APIs as a decimal
5872 factor of the size of 5646 factor of the size of main memory.
5873 The default is 1 mean 5647 The default is 1 meaning that one can concurrently use
5874 as many DMA addresses 5648 as many DMA addresses as physical memory is installed,
5875 if supported by hardw 5649 if supported by hardware, and thus map all of memory
5876 once. With a value of 5650 once. With a value of 2 one can map all of memory twice
5877 and so on. As a speci 5651 and so on. As a special case a factor of 0 imposes no
5878 restrictions other th 5652 restrictions other than those given by hardware at the
5879 cost of significant a 5653 cost of significant additional memory use for tables.
5880 5654
5881 sa1100ir [NET] 5655 sa1100ir [NET]
5882 See drivers/net/irda/ 5656 See drivers/net/irda/sa1100_ir.c.
5883 5657
5884 sched_verbose [KNL,EARLY] Enables v !! 5658 sched_verbose [KNL] Enables verbose scheduler debug messages.
5885 5659
5886 schedstats= [KNL,X86] Enable or d 5660 schedstats= [KNL,X86] Enable or disable scheduled statistics.
5887 Allowed values are en 5661 Allowed values are enable and disable. This feature
5888 incurs a small amount 5662 incurs a small amount of overhead in the scheduler
5889 but is useful for deb 5663 but is useful for debugging and performance tuning.
5890 5664
5891 sched_thermal_decay_shift= 5665 sched_thermal_decay_shift=
5892 [Deprecated] <<
5893 [KNL, SMP] Set a deca 5666 [KNL, SMP] Set a decay shift for scheduler thermal
5894 pressure signal. Ther 5667 pressure signal. Thermal pressure signal follows the
5895 default decay period 5668 default decay period of other scheduler pelt
5896 signals(usually 32 ms 5669 signals(usually 32 ms but configurable). Setting
5897 sched_thermal_decay_s 5670 sched_thermal_decay_shift will left shift the decay
5898 period for the therma 5671 period for the thermal pressure signal by the shift
5899 value. 5672 value.
5900 i.e. with the default 5673 i.e. with the default pelt decay period of 32 ms
5901 sched_thermal_decay_s 5674 sched_thermal_decay_shift thermal pressure decay pr
5902 1 5675 1 64 ms
5903 2 5676 2 128 ms
5904 and so on. 5677 and so on.
5905 Format: integer betwe 5678 Format: integer between 0 and 10
5906 Default is 0. 5679 Default is 0.
5907 5680
5908 scftorture.holdoff= [KNL] 5681 scftorture.holdoff= [KNL]
5909 Number of seconds to 5682 Number of seconds to hold off before starting
5910 test. Defaults to ze 5683 test. Defaults to zero for module insertion and
5911 to 10 seconds for bui 5684 to 10 seconds for built-in smp_call_function()
5912 tests. 5685 tests.
5913 5686
5914 scftorture.longwait= [KNL] 5687 scftorture.longwait= [KNL]
5915 Request ridiculously 5688 Request ridiculously long waits randomly selected
5916 up to the chosen limi 5689 up to the chosen limit in seconds. Zero (the
5917 default) disables thi 5690 default) disables this feature. Please note
5918 that requesting even 5691 that requesting even small non-zero numbers of
5919 seconds can result in 5692 seconds can result in RCU CPU stall warnings,
5920 softlockup complaints 5693 softlockup complaints, and so on.
5921 5694
5922 scftorture.nthreads= [KNL] 5695 scftorture.nthreads= [KNL]
5923 Number of kthreads to 5696 Number of kthreads to spawn to invoke the
5924 smp_call_function() f 5697 smp_call_function() family of functions.
5925 The default of -1 spe 5698 The default of -1 specifies a number of kthreads
5926 equal to the number o 5699 equal to the number of CPUs.
5927 5700
5928 scftorture.onoff_holdoff= [KNL] 5701 scftorture.onoff_holdoff= [KNL]
5929 Number seconds to wai 5702 Number seconds to wait after the start of the
5930 test before initiatin 5703 test before initiating CPU-hotplug operations.
5931 5704
5932 scftorture.onoff_interval= [KNL] 5705 scftorture.onoff_interval= [KNL]
5933 Number seconds to wai 5706 Number seconds to wait between successive
5934 CPU-hotplug operation 5707 CPU-hotplug operations. Specifying zero (which
5935 is the default) disab 5708 is the default) disables CPU-hotplug operations.
5936 5709
5937 scftorture.shutdown_secs= [KNL] 5710 scftorture.shutdown_secs= [KNL]
5938 The number of seconds 5711 The number of seconds following the start of the
5939 test after which to s 5712 test after which to shut down the system. The
5940 default of zero avoid 5713 default of zero avoids shutting down the system.
5941 Non-zero values are u 5714 Non-zero values are useful for automated tests.
5942 5715
5943 scftorture.stat_interval= [KNL] 5716 scftorture.stat_interval= [KNL]
5944 The number of seconds 5717 The number of seconds between outputting the
5945 current test statisti 5718 current test statistics to the console. A value
5946 of zero disables stat 5719 of zero disables statistics output.
5947 5720
5948 scftorture.stutter_cpus= [KNL] 5721 scftorture.stutter_cpus= [KNL]
5949 The number of jiffies 5722 The number of jiffies to wait between each change
5950 to the set of CPUs un 5723 to the set of CPUs under test.
5951 5724
5952 scftorture.use_cpus_read_lock= [KNL] 5725 scftorture.use_cpus_read_lock= [KNL]
5953 Use use_cpus_read_loc 5726 Use use_cpus_read_lock() instead of the default
5954 preempt_disable() to 5727 preempt_disable() to disable CPU hotplug
5955 while invoking one of 5728 while invoking one of the smp_call_function*()
5956 functions. 5729 functions.
5957 5730
5958 scftorture.verbose= [KNL] 5731 scftorture.verbose= [KNL]
5959 Enable additional pri 5732 Enable additional printk() statements.
5960 5733
5961 scftorture.weight_single= [KNL] 5734 scftorture.weight_single= [KNL]
5962 The probability weigh 5735 The probability weighting to use for the
5963 smp_call_function_sin 5736 smp_call_function_single() function with a zero
5964 "wait" parameter. A 5737 "wait" parameter. A value of -1 selects the
5965 default if all other 5738 default if all other weights are -1. However,
5966 if at least one weigh 5739 if at least one weight has some other value, a
5967 value of -1 will inst 5740 value of -1 will instead select a weight of zero.
5968 5741
5969 scftorture.weight_single_wait= [KNL] 5742 scftorture.weight_single_wait= [KNL]
5970 The probability weigh 5743 The probability weighting to use for the
5971 smp_call_function_sin 5744 smp_call_function_single() function with a
5972 non-zero "wait" param 5745 non-zero "wait" parameter. See weight_single.
5973 5746
5974 scftorture.weight_many= [KNL] 5747 scftorture.weight_many= [KNL]
5975 The probability weigh 5748 The probability weighting to use for the
5976 smp_call_function_man 5749 smp_call_function_many() function with a zero
5977 "wait" parameter. Se 5750 "wait" parameter. See weight_single.
5978 Note well that settin 5751 Note well that setting a high probability for
5979 this weighting can pl 5752 this weighting can place serious IPI load
5980 on the system. 5753 on the system.
5981 5754
5982 scftorture.weight_many_wait= [KNL] 5755 scftorture.weight_many_wait= [KNL]
5983 The probability weigh 5756 The probability weighting to use for the
5984 smp_call_function_man 5757 smp_call_function_many() function with a
5985 non-zero "wait" param 5758 non-zero "wait" parameter. See weight_single
5986 and weight_many. 5759 and weight_many.
5987 5760
5988 scftorture.weight_all= [KNL] 5761 scftorture.weight_all= [KNL]
5989 The probability weigh 5762 The probability weighting to use for the
5990 smp_call_function_all 5763 smp_call_function_all() function with a zero
5991 "wait" parameter. Se 5764 "wait" parameter. See weight_single and
5992 weight_many. 5765 weight_many.
5993 5766
5994 scftorture.weight_all_wait= [KNL] 5767 scftorture.weight_all_wait= [KNL]
5995 The probability weigh 5768 The probability weighting to use for the
5996 smp_call_function_all 5769 smp_call_function_all() function with a
5997 non-zero "wait" param 5770 non-zero "wait" parameter. See weight_single
5998 and weight_many. 5771 and weight_many.
5999 5772
6000 skew_tick= [KNL,EARLY] Offset th !! 5773 skew_tick= [KNL] Offset the periodic timer tick per cpu to mitigate
6001 xtime_lock contention 5774 xtime_lock contention on larger systems, and/or RCU lock
6002 contention on all sys 5775 contention on all systems with CONFIG_MAXSMP set.
6003 Format: { "0" | "1" } 5776 Format: { "0" | "1" }
6004 0 -- disable. (may be 5777 0 -- disable. (may be 1 via CONFIG_CMDLINE="skew_tick=1"
6005 1 -- enable. 5778 1 -- enable.
6006 Note: increases power 5779 Note: increases power consumption, thus should only be
6007 enabled if running ji 5780 enabled if running jitter sensitive (HPC/RT) workloads.
6008 5781
6009 security= [SECURITY] Choose a l 5782 security= [SECURITY] Choose a legacy "major" security module to
6010 enable at boot. This 5783 enable at boot. This has been deprecated by the
6011 "lsm=" parameter. 5784 "lsm=" parameter.
6012 5785
6013 selinux= [SELINUX] Disable or 5786 selinux= [SELINUX] Disable or enable SELinux at boot time.
6014 Format: { "0" | "1" } 5787 Format: { "0" | "1" }
6015 See security/selinux/ 5788 See security/selinux/Kconfig help text.
6016 0 -- disable. 5789 0 -- disable.
6017 1 -- enable. 5790 1 -- enable.
6018 Default value is 1. 5791 Default value is 1.
6019 5792
6020 serialnumber [BUGS=X86-32] 5793 serialnumber [BUGS=X86-32]
6021 5794
6022 sev=option[,option...] [X86-64] See D 5795 sev=option[,option...] [X86-64] See Documentation/arch/x86/x86_64/boot-options.rst
6023 5796
6024 shapers= [NET] 5797 shapers= [NET]
6025 Maximal number of sha 5798 Maximal number of shapers.
6026 5799
6027 show_lapic= [APIC,X86] Advanced P 5800 show_lapic= [APIC,X86] Advanced Programmable Interrupt Controller
6028 Limit apic dumping. T 5801 Limit apic dumping. The parameter defines the maximal
6029 number of local apics 5802 number of local apics being dumped. Also it is possible
6030 to set it to "all" by 5803 to set it to "all" by meaning -- no limit here.
6031 Format: { 1 (default) 5804 Format: { 1 (default) | 2 | ... | all }.
6032 The parameter valid i 5805 The parameter valid if only apic=debug or
6033 apic=verbose is speci 5806 apic=verbose is specified.
6034 Example: apic=debug s 5807 Example: apic=debug show_lapic=all
6035 5808
6036 slab_debug[=options[,slabs][;[options !! 5809 simeth= [IA-64]
6037 Enabling slab_debug a !! 5810 simscsi=
>> 5811
>> 5812 slram= [HW,MTD]
>> 5813
>> 5814 slab_merge [MM]
>> 5815 Enable merging of slabs with similar size when the
>> 5816 kernel is built without CONFIG_SLAB_MERGE_DEFAULT.
>> 5817
>> 5818 slab_nomerge [MM]
>> 5819 Disable merging of slabs with similar size. May be
>> 5820 necessary if there is some reason to distinguish
>> 5821 allocs to different slabs, especially in hardened
>> 5822 environments where the risk of heap overflows and
>> 5823 layout control by attackers can usually be
>> 5824 frustrated by disabling merging. This will reduce
>> 5825 most of the exposure of a heap attack to a single
>> 5826 cache (risks via metadata attacks are mostly
>> 5827 unchanged). Debug options disable merging on their
>> 5828 own.
>> 5829 For more information see Documentation/mm/slub.rst.
>> 5830
>> 5831 slab_max_order= [MM, SLAB]
>> 5832 Determines the maximum allowed order for slabs.
>> 5833 A high setting may cause OOMs due to memory
>> 5834 fragmentation. Defaults to 1 for systems with
>> 5835 more than 32MB of RAM, 0 otherwise.
>> 5836
>> 5837 slub_debug[=options[,slabs][;[options[,slabs]]...] [MM, SLUB]
>> 5838 Enabling slub_debug allows one to determine the
6038 culprit if slab objec 5839 culprit if slab objects become corrupted. Enabling
6039 slab_debug can create !! 5840 slub_debug can create guard zones around objects and
6040 may poison objects wh 5841 may poison objects when not in use. Also tracks the
6041 last alloc / free. Fo 5842 last alloc / free. For more information see
6042 Documentation/mm/slub 5843 Documentation/mm/slub.rst.
6043 (slub_debug legacy na <<
6044 5844
6045 slab_max_order= [MM] !! 5845 slub_max_order= [MM, SLUB]
6046 Determines the maximu 5846 Determines the maximum allowed order for slabs.
6047 A high setting may ca 5847 A high setting may cause OOMs due to memory
6048 fragmentation. For mo 5848 fragmentation. For more information see
6049 Documentation/mm/slub 5849 Documentation/mm/slub.rst.
6050 (slub_max_order legac <<
6051 5850
6052 slab_merge [MM] !! 5851 slub_min_objects= [MM, SLUB]
6053 Enable merging of sla <<
6054 kernel is built witho <<
6055 (slub_merge legacy na <<
6056 <<
6057 slab_min_objects= [MM] <<
6058 The minimum number of 5852 The minimum number of objects per slab. SLUB will
6059 increase the slab ord !! 5853 increase the slab order up to slub_max_order to
6060 generate a sufficient 5854 generate a sufficiently large slab able to contain
6061 the number of objects 5855 the number of objects indicated. The higher the number
6062 of objects the smalle 5856 of objects the smaller the overhead of tracking slabs
6063 and the less frequent 5857 and the less frequently locks need to be acquired.
6064 For more information 5858 For more information see Documentation/mm/slub.rst.
6065 (slub_min_objects leg <<
6066 5859
6067 slab_min_order= [MM] !! 5860 slub_min_order= [MM, SLUB]
6068 Determines the minimu 5861 Determines the minimum page order for slabs. Must be
6069 lower or equal to sla !! 5862 lower than slub_max_order.
6070 Documentation/mm/slub <<
6071 (slub_min_order legac <<
6072 <<
6073 slab_nomerge [MM] <<
6074 Disable merging of sl <<
6075 necessary if there is <<
6076 allocs to different s <<
6077 environments where th <<
6078 layout control by att <<
6079 frustrated by disabli <<
6080 most of the exposure <<
6081 cache (risks via meta <<
6082 unchanged). Debug opt <<
6083 own. <<
6084 For more information 5863 For more information see Documentation/mm/slub.rst.
6085 (slub_nomerge legacy <<
6086 5864
6087 slram= [HW,MTD] !! 5865 slub_merge [MM, SLUB]
>> 5866 Same with slab_merge.
>> 5867
>> 5868 slub_nomerge [MM, SLUB]
>> 5869 Same with slab_nomerge. This is supported for legacy.
>> 5870 See slab_nomerge for more information.
6088 5871
6089 smart2= [HW] 5872 smart2= [HW]
6090 Format: <io1>[,<io2>[ 5873 Format: <io1>[,<io2>[,...,<io8>]]
6091 5874
6092 smp.csd_lock_timeout= [KNL] 5875 smp.csd_lock_timeout= [KNL]
6093 Specify the period of 5876 Specify the period of time in milliseconds
6094 that smp_call_functio 5877 that smp_call_function() and friends will wait
6095 for a CPU to release 5878 for a CPU to release the CSD lock. This is
6096 useful when diagnosin 5879 useful when diagnosing bugs involving CPUs
6097 disabling interrupts 5880 disabling interrupts for extended periods
6098 of time. Defaults to 5881 of time. Defaults to 5,000 milliseconds, and
6099 setting a value of ze 5882 setting a value of zero disables this feature.
6100 This feature may be m 5883 This feature may be more efficiently disabled
6101 using the csdlock_deb 5884 using the csdlock_debug- kernel parameter.
6102 5885
6103 smp.panic_on_ipistall= [KNL] 5886 smp.panic_on_ipistall= [KNL]
6104 If a csd_lock_timeout 5887 If a csd_lock_timeout extends for more than
6105 the specified number 5888 the specified number of milliseconds, panic the
6106 system. By default, 5889 system. By default, let CSD-lock acquisition
6107 take as long as they 5890 take as long as they take. Specifying 300,000
6108 for this value provid 5891 for this value provides a 5-minute timeout.
6109 5892
6110 smsc-ircc2.nopnp [HW] Don't us 5893 smsc-ircc2.nopnp [HW] Don't use PNP to discover SMC devices
6111 smsc-ircc2.ircc_cfg= [HW] Device c 5894 smsc-ircc2.ircc_cfg= [HW] Device configuration I/O port
6112 smsc-ircc2.ircc_sir= [HW] SIR base 5895 smsc-ircc2.ircc_sir= [HW] SIR base I/O port
6113 smsc-ircc2.ircc_fir= [HW] FIR base 5896 smsc-ircc2.ircc_fir= [HW] FIR base I/O port
6114 smsc-ircc2.ircc_irq= [HW] IRQ line 5897 smsc-ircc2.ircc_irq= [HW] IRQ line
6115 smsc-ircc2.ircc_dma= [HW] DMA chan 5898 smsc-ircc2.ircc_dma= [HW] DMA channel
6116 smsc-ircc2.ircc_transceiver= [HW] Tra 5899 smsc-ircc2.ircc_transceiver= [HW] Transceiver type:
6117 0: Toshiba Sa 5900 0: Toshiba Satellite 1800 (GP data pin select)
6118 1: Fast pin s 5901 1: Fast pin select (default)
6119 2: ATC IRMode 5902 2: ATC IRMode
6120 5903
6121 smt= [KNL,MIPS,S390,EARLY] !! 5904 smt= [KNL,MIPS,S390] Set the maximum number of threads (logical
6122 (logical CPUs) to use !! 5905 CPUs) to use per physical CPU on systems capable of
6123 capable of symmetric !! 5906 symmetric multithreading (SMT). Will be capped to the
6124 be capped to the actu !! 5907 actual hardware limit.
6125 Format: <integer> 5908 Format: <integer>
6126 Default: -1 (no limit 5909 Default: -1 (no limit)
6127 5910
6128 softlockup_panic= 5911 softlockup_panic=
6129 [KNL] Should the soft 5912 [KNL] Should the soft-lockup detector generate panics.
6130 Format: 0 | 1 5913 Format: 0 | 1
6131 5914
6132 A value of 1 instruct 5915 A value of 1 instructs the soft-lockup detector
6133 to panic the machine 5916 to panic the machine when a soft-lockup occurs. It is
6134 also controlled by th 5917 also controlled by the kernel.softlockup_panic sysctl
6135 and CONFIG_BOOTPARAM_ 5918 and CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC, which is the
6136 respective build-time 5919 respective build-time switch to that functionality.
6137 5920
6138 softlockup_all_cpu_backtrace= 5921 softlockup_all_cpu_backtrace=
6139 [KNL] Should the soft 5922 [KNL] Should the soft-lockup detector generate
6140 backtraces on all cpu 5923 backtraces on all cpus.
6141 Format: 0 | 1 5924 Format: 0 | 1
6142 5925
6143 sonypi.*= [HW] Sony Programmabl 5926 sonypi.*= [HW] Sony Programmable I/O Control Device driver
6144 See Documentation/adm 5927 See Documentation/admin-guide/laptops/sonypi.rst
6145 5928
6146 spectre_bhi= [X86] Control mitigat 5929 spectre_bhi= [X86] Control mitigation of Branch History Injection
6147 (BHI) vulnerability. 5930 (BHI) vulnerability. This setting affects the
6148 deployment of the HW 5931 deployment of the HW BHI control and the SW BHB
6149 clearing sequence. 5932 clearing sequence.
6150 5933
6151 on - (default) En !! 5934 on - (default) Enable the HW or SW mitigation
6152 needed. Thi !! 5935 as needed.
6153 both syscall !! 5936 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 5937
6161 spectre_v2= [X86,EARLY] Control m !! 5938 spectre_v2= [X86] Control mitigation of Spectre variant 2
6162 (indirect branch spec 5939 (indirect branch speculation) vulnerability.
6163 The default operation 5940 The default operation protects the kernel from
6164 user space attacks. 5941 user space attacks.
6165 5942
6166 on - unconditionall 5943 on - unconditionally enable, implies
6167 spectre_v2_use 5944 spectre_v2_user=on
6168 off - unconditionall 5945 off - unconditionally disable, implies
6169 spectre_v2_use 5946 spectre_v2_user=off
6170 auto - kernel detects 5947 auto - kernel detects whether your CPU model is
6171 vulnerable 5948 vulnerable
6172 5949
6173 Selecting 'on' will, 5950 Selecting 'on' will, and 'auto' may, choose a
6174 mitigation method at 5951 mitigation method at run time according to the
6175 CPU, the available mi 5952 CPU, the available microcode, the setting of the
6176 CONFIG_MITIGATION_RET !! 5953 CONFIG_RETPOLINE configuration option, and the
6177 and the compiler with !! 5954 compiler with which the kernel was built.
6178 5955
6179 Selecting 'on' will a 5956 Selecting 'on' will also enable the mitigation
6180 against user space to 5957 against user space to user space task attacks.
6181 5958
6182 Selecting 'off' will 5959 Selecting 'off' will disable both the kernel and
6183 the user space protec 5960 the user space protections.
6184 5961
6185 Specific mitigations 5962 Specific mitigations can also be selected manually:
6186 5963
6187 retpoline - r 5964 retpoline - replace indirect branches
6188 retpoline,generic - R 5965 retpoline,generic - Retpolines
6189 retpoline,lfence - L 5966 retpoline,lfence - LFENCE; indirect branch
6190 retpoline,amd - a 5967 retpoline,amd - alias for retpoline,lfence
6191 eibrs - E 5968 eibrs - Enhanced/Auto IBRS
6192 eibrs,retpoline - E 5969 eibrs,retpoline - Enhanced/Auto IBRS + Retpolines
6193 eibrs,lfence - E 5970 eibrs,lfence - Enhanced/Auto IBRS + LFENCE
6194 ibrs - u 5971 ibrs - use IBRS to protect kernel
6195 5972
6196 Not specifying this o 5973 Not specifying this option is equivalent to
6197 spectre_v2=auto. 5974 spectre_v2=auto.
6198 5975
6199 spectre_v2_user= 5976 spectre_v2_user=
6200 [X86] Control mitigat 5977 [X86] Control mitigation of Spectre variant 2
6201 (indirect branch spec 5978 (indirect branch speculation) vulnerability between
6202 user space tasks 5979 user space tasks
6203 5980
6204 on - Uncondition 5981 on - Unconditionally enable mitigations. Is
6205 enforced by 5982 enforced by spectre_v2=on
6206 5983
6207 off - Uncondition 5984 off - Unconditionally disable mitigations. Is
6208 enforced by 5985 enforced by spectre_v2=off
6209 5986
6210 prctl - Indirect br 5987 prctl - Indirect branch speculation is enabled,
6211 but mitigat 5988 but mitigation can be enabled via prctl
6212 per thread. 5989 per thread. The mitigation control state
6213 is inherite 5990 is inherited on fork.
6214 5991
6215 prctl,ibpb 5992 prctl,ibpb
6216 - Like "prctl 5993 - Like "prctl" above, but only STIBP is
6217 controlled 5994 controlled per thread. IBPB is issued
6218 always when 5995 always when switching between different user
6219 space proce 5996 space processes.
6220 5997
6221 seccomp 5998 seccomp
6222 - Same as "pr 5999 - Same as "prctl" above, but all seccomp
6223 threads wil 6000 threads will enable the mitigation unless
6224 they explic 6001 they explicitly opt out.
6225 6002
6226 seccomp,ibpb 6003 seccomp,ibpb
6227 - Like "secco 6004 - Like "seccomp" above, but only STIBP is
6228 controlled 6005 controlled per thread. IBPB is issued
6229 always when 6006 always when switching between different
6230 user space 6007 user space processes.
6231 6008
6232 auto - Kernel sele 6009 auto - Kernel selects the mitigation depending on
6233 the availab 6010 the available CPU features and vulnerability.
6234 6011
6235 Default mitigation: " 6012 Default mitigation: "prctl"
6236 6013
6237 Not specifying this o 6014 Not specifying this option is equivalent to
6238 spectre_v2_user=auto. 6015 spectre_v2_user=auto.
6239 6016
6240 spec_rstack_overflow= 6017 spec_rstack_overflow=
6241 [X86,EARLY] Control R !! 6018 [X86] Control RAS overflow mitigation on AMD Zen CPUs
6242 6019
6243 off - Dis 6020 off - Disable mitigation
6244 microcode - Ena 6021 microcode - Enable microcode mitigation only
6245 safe-ret - Ena 6022 safe-ret - Enable sw-only safe RET mitigation (default)
6246 ibpb - Ena 6023 ibpb - Enable mitigation by issuing IBPB on
6247 ker 6024 kernel entry
6248 ibpb-vmexit - Iss 6025 ibpb-vmexit - Issue IBPB only on VMEXIT
6249 (cl 6026 (cloud-specific mitigation)
6250 6027
6251 spec_store_bypass_disable= 6028 spec_store_bypass_disable=
6252 [HW,EARLY] Control Sp !! 6029 [HW] Control Speculative Store Bypass (SSB) Disable mitigation
6253 (Speculative Store By 6030 (Speculative Store Bypass vulnerability)
6254 6031
6255 Certain CPUs are vuln 6032 Certain CPUs are vulnerable to an exploit against a
6256 a common industry wid 6033 a common industry wide performance optimization known
6257 as "Speculative Store 6034 as "Speculative Store Bypass" in which recent stores
6258 to the same memory lo 6035 to the same memory location may not be observed by
6259 later loads during sp 6036 later loads during speculative execution. The idea
6260 is that such stores a 6037 is that such stores are unlikely and that they can
6261 be detected prior to 6038 be detected prior to instruction retirement at the
6262 end of a particular s 6039 end of a particular speculation execution window.
6263 6040
6264 In vulnerable process 6041 In vulnerable processors, the speculatively forwarded
6265 store can be used in 6042 store can be used in a cache side channel attack, for
6266 example to read memor 6043 example to read memory to which the attacker does not
6267 directly have access 6044 directly have access (e.g. inside sandboxed code).
6268 6045
6269 This parameter contro 6046 This parameter controls whether the Speculative Store
6270 Bypass optimization i 6047 Bypass optimization is used.
6271 6048
6272 On x86 the options ar 6049 On x86 the options are:
6273 6050
6274 on - Uncondition 6051 on - Unconditionally disable Speculative Store Bypass
6275 off - Uncondition 6052 off - Unconditionally enable Speculative Store Bypass
6276 auto - Kernel dete 6053 auto - Kernel detects whether the CPU model contains an
6277 implementat 6054 implementation of Speculative Store Bypass and
6278 picks the m 6055 picks the most appropriate mitigation. If the
6279 CPU is not 6056 CPU is not vulnerable, "off" is selected. If the
6280 CPU is vuln 6057 CPU is vulnerable the default mitigation is
6281 architectur 6058 architecture and Kconfig dependent. See below.
6282 prctl - Control Spe 6059 prctl - Control Speculative Store Bypass per thread
6283 via prctl. 6060 via prctl. Speculative Store Bypass is enabled
6284 for a proce 6061 for a process by default. The state of the control
6285 is inherite 6062 is inherited on fork.
6286 seccomp - Same as "pr 6063 seccomp - Same as "prctl" above, but all seccomp threads
6287 will disabl 6064 will disable SSB unless they explicitly opt out.
6288 6065
6289 Default mitigations: 6066 Default mitigations:
6290 X86: "prctl" 6067 X86: "prctl"
6291 6068
6292 On powerpc the option 6069 On powerpc the options are:
6293 6070
6294 on,auto - On Power8 a 6071 on,auto - On Power8 and Power9 insert a store-forwarding
6295 barrier on 6072 barrier on kernel entry and exit. On Power7
6296 perform a s 6073 perform a software flush on kernel entry and
6297 exit. 6074 exit.
6298 off - No action. 6075 off - No action.
6299 6076
6300 Not specifying this o 6077 Not specifying this option is equivalent to
6301 spec_store_bypass_dis 6078 spec_store_bypass_disable=auto.
6302 6079
>> 6080 spia_io_base= [HW,MTD]
>> 6081 spia_fio_base=
>> 6082 spia_pedr=
>> 6083 spia_peddr=
>> 6084
6303 split_lock_detect= 6085 split_lock_detect=
6304 [X86] Enable split lo 6086 [X86] Enable split lock detection or bus lock detection
6305 6087
6306 When enabled (and if 6088 When enabled (and if hardware support is present), atomic
6307 instructions that acc 6089 instructions that access data across cache line
6308 boundaries will resul 6090 boundaries will result in an alignment check exception
6309 for split lock detect 6091 for split lock detection or a debug exception for
6310 bus lock detection. 6092 bus lock detection.
6311 6093
6312 off - not enabled 6094 off - not enabled
6313 6095
6314 warn - the kernel 6096 warn - the kernel will emit rate-limited warnings
6315 about appli 6097 about applications triggering the #AC
6316 exception o 6098 exception or the #DB exception. This mode is
6317 the default 6099 the default on CPUs that support split lock
6318 detection o 6100 detection or bus lock detection. Default
6319 behavior is 6101 behavior is by #AC if both features are
6320 enabled in 6102 enabled in hardware.
6321 6103
6322 fatal - the kernel 6104 fatal - the kernel will send SIGBUS to applications
6323 that trigge 6105 that trigger the #AC exception or the #DB
6324 exception. 6106 exception. Default behavior is by #AC if
6325 both featur 6107 both features are enabled in hardware.
6326 6108
6327 ratelimit:N - 6109 ratelimit:N -
6328 Set system 6110 Set system wide rate limit to N bus locks
6329 per second 6111 per second for bus lock detection.
6330 0 < N <= 10 6112 0 < N <= 1000.
6331 6113
6332 N/A for spl 6114 N/A for split lock detection.
6333 6115
6334 6116
6335 If an #AC exception i 6117 If an #AC exception is hit in the kernel or in
6336 firmware (i.e. not wh 6118 firmware (i.e. not while executing in user mode)
6337 the kernel will oops 6119 the kernel will oops in either "warn" or "fatal"
6338 mode. 6120 mode.
6339 6121
6340 #DB exception for bus 6122 #DB exception for bus lock is triggered only when
6341 CPL > 0. 6123 CPL > 0.
6342 6124
6343 srbds= [X86,INTEL,EARLY] !! 6125 srbds= [X86,INTEL]
6344 Control the Special R 6126 Control the Special Register Buffer Data Sampling
6345 (SRBDS) mitigation. 6127 (SRBDS) mitigation.
6346 6128
6347 Certain CPUs are vuln 6129 Certain CPUs are vulnerable to an MDS-like
6348 exploit which can lea 6130 exploit which can leak bits from the random
6349 number generator. 6131 number generator.
6350 6132
6351 By default, this issu 6133 By default, this issue is mitigated by
6352 microcode. However, 6134 microcode. However, the microcode fix can cause
6353 the RDRAND and RDSEED 6135 the RDRAND and RDSEED instructions to become
6354 much slower. Among o 6136 much slower. Among other effects, this will
6355 result in reduced thr 6137 result in reduced throughput from /dev/urandom.
6356 6138
6357 The microcode mitigat 6139 The microcode mitigation can be disabled with
6358 the following option: 6140 the following option:
6359 6141
6360 off: Disable mitig 6142 off: Disable mitigation and remove
6361 performance i 6143 performance impact to RDRAND and RDSEED
6362 6144
6363 srcutree.big_cpu_lim [KNL] 6145 srcutree.big_cpu_lim [KNL]
6364 Specifies the number 6146 Specifies the number of CPUs constituting a
6365 large system, such th 6147 large system, such that srcu_struct structures
6366 should immediately al 6148 should immediately allocate an srcu_node array.
6367 This kernel-boot para 6149 This kernel-boot parameter defaults to 128,
6368 but takes effect only 6150 but takes effect only when the low-order four
6369 bits of srcutree.conv 6151 bits of srcutree.convert_to_big is equal to 3
6370 (decide at boot). 6152 (decide at boot).
6371 6153
6372 srcutree.convert_to_big [KNL] 6154 srcutree.convert_to_big [KNL]
6373 Specifies under what 6155 Specifies under what conditions an SRCU tree
6374 srcu_struct structure 6156 srcu_struct structure will be converted to big
6375 form, that is, with a 6157 form, that is, with an rcu_node tree:
6376 6158
6377 0: Never. 6159 0: Never.
6378 1: At ini 6160 1: At init_srcu_struct() time.
6379 2: When r 6161 2: When rcutorture decides to.
6380 3: Decide 6162 3: Decide at boot time (default).
6381 0x1X: Above 6163 0x1X: Above plus if high contention.
6382 6164
6383 Either way, the srcu_ 6165 Either way, the srcu_node tree will be sized based
6384 on the actual runtime 6166 on the actual runtime number of CPUs (nr_cpu_ids)
6385 instead of the compil 6167 instead of the compile-time CONFIG_NR_CPUS.
6386 6168
6387 srcutree.counter_wrap_check [KNL] 6169 srcutree.counter_wrap_check [KNL]
6388 Specifies how frequen 6170 Specifies how frequently to check for
6389 grace-period sequence 6171 grace-period sequence counter wrap for the
6390 srcu_data structure's 6172 srcu_data structure's ->srcu_gp_seq_needed field.
6391 The greater the numbe 6173 The greater the number of bits set in this kernel
6392 parameter, the less f 6174 parameter, the less frequently counter wrap will
6393 be checked for. Note 6175 be checked for. Note that the bottom two bits
6394 are ignored. 6176 are ignored.
6395 6177
6396 srcutree.exp_holdoff [KNL] 6178 srcutree.exp_holdoff [KNL]
6397 Specifies how many na 6179 Specifies how many nanoseconds must elapse
6398 since the end of the 6180 since the end of the last SRCU grace period for
6399 a given srcu_struct u 6181 a given srcu_struct until the next normal SRCU
6400 grace period will be 6182 grace period will be considered for automatic
6401 expediting. Set to z 6183 expediting. Set to zero to disable automatic
6402 expediting. 6184 expediting.
6403 6185
6404 srcutree.srcu_max_nodelay [KNL] 6186 srcutree.srcu_max_nodelay [KNL]
6405 Specifies the number 6187 Specifies the number of no-delay instances
6406 per jiffy for which t 6188 per jiffy for which the SRCU grace period
6407 worker thread will be 6189 worker thread will be rescheduled with zero
6408 delay. Beyond this li 6190 delay. Beyond this limit, worker thread will
6409 be rescheduled with a 6191 be rescheduled with a sleep delay of one jiffy.
6410 6192
6411 srcutree.srcu_max_nodelay_phase [KNL] 6193 srcutree.srcu_max_nodelay_phase [KNL]
6412 Specifies the per-gra 6194 Specifies the per-grace-period phase, number of
6413 non-sleeping polls of 6195 non-sleeping polls of readers. Beyond this limit,
6414 grace period worker t 6196 grace period worker thread will be rescheduled
6415 with a sleep delay of 6197 with a sleep delay of one jiffy, between each
6416 rescan of the readers 6198 rescan of the readers, for a grace period phase.
6417 6199
6418 srcutree.srcu_retry_check_delay [KNL] 6200 srcutree.srcu_retry_check_delay [KNL]
6419 Specifies number of m 6201 Specifies number of microseconds of non-sleeping
6420 delay between each no 6202 delay between each non-sleeping poll of readers.
6421 6203
6422 srcutree.small_contention_lim [KNL] 6204 srcutree.small_contention_lim [KNL]
6423 Specifies the number 6205 Specifies the number of update-side contention
6424 events per jiffy will 6206 events per jiffy will be tolerated before
6425 initiating a conversi 6207 initiating a conversion of an srcu_struct
6426 structure to big form 6208 structure to big form. Note that the value of
6427 srcutree.convert_to_b 6209 srcutree.convert_to_big must have the 0x10 bit
6428 set for contention-ba 6210 set for contention-based conversions to occur.
6429 6211
6430 ssbd= [ARM64,HW,EARLY] !! 6212 ssbd= [ARM64,HW]
6431 Speculative Store Byp 6213 Speculative Store Bypass Disable control
6432 6214
6433 On CPUs that are vuln 6215 On CPUs that are vulnerable to the Speculative
6434 Store Bypass vulnerab 6216 Store Bypass vulnerability and offer a
6435 firmware based mitiga 6217 firmware based mitigation, this parameter
6436 indicates how the mit 6218 indicates how the mitigation should be used:
6437 6219
6438 force-on: Unconditio 6220 force-on: Unconditionally enable mitigation for
6439 for both k 6221 for both kernel and userspace
6440 force-off: Unconditio 6222 force-off: Unconditionally disable mitigation for
6441 for both k 6223 for both kernel and userspace
6442 kernel: Always ena 6224 kernel: Always enable mitigation in the
6443 kernel, an 6225 kernel, and offer a prctl interface
6444 to allow u 6226 to allow userspace to register its
6445 interest i 6227 interest in being mitigated too.
6446 6228
6447 stack_guard_gap= [MM] 6229 stack_guard_gap= [MM]
6448 override the default 6230 override the default stack gap protection. The value
6449 is in page units and 6231 is in page units and it defines how many pages prior
6450 to (for stacks growin 6232 to (for stacks growing down) resp. after (for stacks
6451 growing up) the main 6233 growing up) the main stack are reserved for no other
6452 mapping. Default valu 6234 mapping. Default value is 256 pages.
6453 6235
6454 stack_depot_disable= [KNL,EARLY] !! 6236 stack_depot_disable= [KNL]
6455 Setting this to true 6237 Setting this to true through kernel command line will
6456 disable the stack dep 6238 disable the stack depot thereby saving the static memory
6457 consumed by the stack 6239 consumed by the stack hash table. By default this is set
6458 to false. 6240 to false.
6459 6241
6460 stacktrace [FTRACE] 6242 stacktrace [FTRACE]
6461 Enabled the stack tra 6243 Enabled the stack tracer on boot up.
6462 6244
6463 stacktrace_filter=[function-list] 6245 stacktrace_filter=[function-list]
6464 [FTRACE] Limit the fu 6246 [FTRACE] Limit the functions that the stack tracer
6465 will trace at boot up 6247 will trace at boot up. function-list is a comma-separated
6466 list of functions. Th 6248 list of functions. This list can be changed at run
6467 time by the stack_tra 6249 time by the stack_trace_filter file in the debugfs
6468 tracing directory. No 6250 tracing directory. Note, this enables stack tracing
6469 and the stacktrace ab 6251 and the stacktrace above is not needed.
6470 6252
6471 sti= [PARISC,HW] 6253 sti= [PARISC,HW]
6472 Format: <num> 6254 Format: <num>
6473 Set the STI (builtin 6255 Set the STI (builtin display/keyboard on the HP-PARISC
6474 machines) console (gr 6256 machines) console (graphic card) which should be used
6475 as the initial boot-c 6257 as the initial boot-console.
6476 See also comment in d 6258 See also comment in drivers/video/console/sticore.c.
6477 6259
6478 sti_font= [HW] 6260 sti_font= [HW]
6479 See comment in driver 6261 See comment in drivers/video/console/sticore.c.
6480 6262
6481 stifb= [HW] 6263 stifb= [HW]
6482 Format: bpp:<bpp1>[:< 6264 Format: bpp:<bpp1>[:<bpp2>[:<bpp3>...]]
6483 6265
6484 strict_sas_size= 6266 strict_sas_size=
6485 [X86] 6267 [X86]
6486 Format: <bool> 6268 Format: <bool>
6487 Enable or disable str 6269 Enable or disable strict sigaltstack size checks
6488 against the required 6270 against the required signal frame size which
6489 depends on the suppor 6271 depends on the supported FPU features. This can
6490 be used to filter out 6272 be used to filter out binaries which have
6491 not yet been made awa 6273 not yet been made aware of AT_MINSIGSTKSZ.
6492 6274
6493 stress_hpt [PPC,EARLY] !! 6275 stress_hpt [PPC]
6494 Limits the number of 6276 Limits the number of kernel HPT entries in the hash
6495 page table to increas 6277 page table to increase the rate of hash page table
6496 faults on kernel addr 6278 faults on kernel addresses.
6497 6279
6498 stress_slb [PPC,EARLY] !! 6280 stress_slb [PPC]
6499 Limits the number of 6281 Limits the number of kernel SLB entries, and flushes
6500 them frequently to in 6282 them frequently to increase the rate of SLB faults
6501 on kernel addresses. 6283 on kernel addresses.
6502 6284
6503 sunrpc.min_resvport= 6285 sunrpc.min_resvport=
6504 sunrpc.max_resvport= 6286 sunrpc.max_resvport=
6505 [NFS,SUNRPC] 6287 [NFS,SUNRPC]
6506 SunRPC servers often 6288 SunRPC servers often require that client requests
6507 originate from a priv 6289 originate from a privileged port (i.e. a port in the
6508 range 0 < portnr < 10 6290 range 0 < portnr < 1024).
6509 An administrator who 6291 An administrator who wishes to reserve some of these
6510 ports for other uses 6292 ports for other uses may adjust the range that the
6511 kernel's sunrpc clien 6293 kernel's sunrpc client considers to be privileged
6512 using these two param 6294 using these two parameters to set the minimum and
6513 maximum port values. 6295 maximum port values.
6514 6296
6515 sunrpc.svc_rpc_per_connection_limit= 6297 sunrpc.svc_rpc_per_connection_limit=
6516 [NFS,SUNRPC] 6298 [NFS,SUNRPC]
6517 Limit the number of r 6299 Limit the number of requests that the server will
6518 process in parallel f 6300 process in parallel from a single connection.
6519 The default value is 6301 The default value is 0 (no limit).
6520 6302
6521 sunrpc.pool_mode= 6303 sunrpc.pool_mode=
6522 [NFS] 6304 [NFS]
6523 Control how the NFS s 6305 Control how the NFS server code allocates CPUs to
6524 service thread pools. 6306 service thread pools. Depending on how many NICs
6525 you have and where th 6307 you have and where their interrupts are bound, this
6526 option will affect wh 6308 option will affect which CPUs will do NFS serving.
6527 Note: this parameter 6309 Note: this parameter cannot be changed while the
6528 NFS server is running 6310 NFS server is running.
6529 6311
6530 auto the serve 6312 auto the server chooses an appropriate mode
6531 automatic 6313 automatically using heuristics
6532 global a single 6314 global a single global pool contains all CPUs
6533 percpu one pool 6315 percpu one pool for each CPU
6534 pernode one pool 6316 pernode one pool for each NUMA node (equivalent
6535 to global 6317 to global on non-NUMA machines)
6536 6318
6537 sunrpc.tcp_slot_table_entries= 6319 sunrpc.tcp_slot_table_entries=
6538 sunrpc.udp_slot_table_entries= 6320 sunrpc.udp_slot_table_entries=
6539 [NFS,SUNRPC] 6321 [NFS,SUNRPC]
6540 Sets the upper limit 6322 Sets the upper limit on the number of simultaneous
6541 RPC calls that can be 6323 RPC calls that can be sent from the client to a
6542 server. Increasing th 6324 server. Increasing these values may allow you to
6543 improve throughput, b 6325 improve throughput, but will also increase the
6544 amount of memory rese 6326 amount of memory reserved for use by the client.
6545 6327
6546 suspend.pm_test_delay= 6328 suspend.pm_test_delay=
6547 [SUSPEND] 6329 [SUSPEND]
6548 Sets the number of se 6330 Sets the number of seconds to remain in a suspend test
6549 mode before resuming 6331 mode before resuming the system (see
6550 /sys/power/pm_test). 6332 /sys/power/pm_test). Only available when CONFIG_PM_DEBUG
6551 is set. Default value 6333 is set. Default value is 5.
6552 6334
6553 svm= [PPC] 6335 svm= [PPC]
6554 Format: { on | off | 6336 Format: { on | off | y | n | 1 | 0 }
6555 This parameter contro 6337 This parameter controls use of the Protected
6556 Execution Facility on 6338 Execution Facility on pSeries.
6557 6339
6558 swiotlb= [ARM,PPC,MIPS,X86,S39 !! 6340 swiotlb= [ARM,IA-64,PPC,MIPS,X86]
6559 Format: { <int> [,<in 6341 Format: { <int> [,<int>] | force | noforce }
6560 <int> -- Number of I/ 6342 <int> -- Number of I/O TLB slabs
6561 <int> -- Second integ 6343 <int> -- Second integer after comma. Number of swiotlb
6562 areas with t 6344 areas with their own lock. Will be rounded up
6563 to a power o 6345 to a power of 2.
6564 force -- force using 6346 force -- force using of bounce buffers even if they
6565 wouldn't be 6347 wouldn't be automatically used by the kernel
6566 noforce -- Never use 6348 noforce -- Never use bounce buffers (for debugging)
6567 6349
6568 switches= [HW,M68k,EARLY] !! 6350 switches= [HW,M68k]
6569 6351
6570 sysctl.*= [KNL] 6352 sysctl.*= [KNL]
6571 Set a sysctl paramete 6353 Set a sysctl parameter, right before loading the init
6572 process, as if the va 6354 process, as if the value was written to the respective
6573 /proc/sys/... file. B 6355 /proc/sys/... file. Both '.' and '/' are recognized as
6574 separators. Unrecogni 6356 separators. Unrecognized parameters and invalid values
6575 are reported in the k 6357 are reported in the kernel log. Sysctls registered
6576 later by a loaded mod 6358 later by a loaded module cannot be set this way.
6577 Example: sysctl.vm.sw 6359 Example: sysctl.vm.swappiness=40
6578 6360
6579 sysrq_always_enabled 6361 sysrq_always_enabled
6580 [KNL] 6362 [KNL]
6581 Ignore sysrq setting 6363 Ignore sysrq setting - this boot parameter will
6582 neutralize any effect 6364 neutralize any effect of /proc/sys/kernel/sysrq.
6583 Useful for debugging. 6365 Useful for debugging.
6584 6366
6585 tcpmhash_entries= [KNL,NET] 6367 tcpmhash_entries= [KNL,NET]
6586 Set the number of tcp 6368 Set the number of tcp_metrics_hash slots.
6587 Default value is 8192 6369 Default value is 8192 or 16384 depending on total
6588 ram pages. This is us 6370 ram pages. This is used to specify the TCP metrics
6589 cache size. See Docum 6371 cache size. See Documentation/networking/ip-sysctl.rst
6590 "tcp_no_metrics_save" 6372 "tcp_no_metrics_save" section for more details.
6591 6373
6592 tdfx= [HW,DRM] 6374 tdfx= [HW,DRM]
6593 6375
6594 test_suspend= [SUSPEND] 6376 test_suspend= [SUSPEND]
6595 Format: { "mem" | "st 6377 Format: { "mem" | "standby" | "freeze" }[,N]
6596 Specify "mem" (for Su 6378 Specify "mem" (for Suspend-to-RAM) or "standby" (for
6597 standby suspend) or " 6379 standby suspend) or "freeze" (for suspend type freeze)
6598 as the system sleep s 6380 as the system sleep state during system startup with
6599 the optional capabili 6381 the optional capability to repeat N number of times.
6600 The system is woken f 6382 The system is woken from this state using a
6601 wakeup-capable RTC al 6383 wakeup-capable RTC alarm.
6602 6384
6603 thash_entries= [KNL,NET] 6385 thash_entries= [KNL,NET]
6604 Set number of hash bu 6386 Set number of hash buckets for TCP connection
6605 6387
6606 thermal.act= [HW,ACPI] 6388 thermal.act= [HW,ACPI]
6607 -1: disable all activ 6389 -1: disable all active trip points in all thermal zones
6608 <degrees C>: override 6390 <degrees C>: override all lowest active trip points
6609 6391
6610 thermal.crt= [HW,ACPI] 6392 thermal.crt= [HW,ACPI]
6611 -1: disable all criti 6393 -1: disable all critical trip points in all thermal zones
6612 <degrees C>: override 6394 <degrees C>: override all critical trip points
6613 6395
6614 thermal.off= [HW,ACPI] 6396 thermal.off= [HW,ACPI]
6615 1: disable ACPI therm 6397 1: disable ACPI thermal control
6616 6398
6617 thermal.psv= [HW,ACPI] 6399 thermal.psv= [HW,ACPI]
6618 -1: disable all passi 6400 -1: disable all passive trip points
6619 <degrees C>: override 6401 <degrees C>: override all passive trip points to this
6620 value 6402 value
6621 6403
6622 thermal.tzp= [HW,ACPI] 6404 thermal.tzp= [HW,ACPI]
6623 Specify global defaul 6405 Specify global default ACPI thermal zone polling rate
6624 <deci-seconds>: poll 6406 <deci-seconds>: poll all this frequency
6625 0: no polling (defaul 6407 0: no polling (default)
6626 6408
6627 threadirqs [KNL,EARLY] !! 6409 threadirqs [KNL]
6628 Force threading of al 6410 Force threading of all interrupt handlers except those
6629 marked explicitly IRQ 6411 marked explicitly IRQF_NO_THREAD.
6630 6412
6631 topology= [S390,EARLY] !! 6413 topology= [S390]
6632 Format: {off | on} 6414 Format: {off | on}
6633 Specify if the kernel 6415 Specify if the kernel should make use of the cpu
6634 topology information 6416 topology information if the hardware supports this.
6635 The scheduler will ma 6417 The scheduler will make use of this information and
6636 e.g. base its process 6418 e.g. base its process migration decisions on it.
6637 Default is on. 6419 Default is on.
6638 6420
>> 6421 topology_updates= [KNL, PPC, NUMA]
>> 6422 Format: {off}
>> 6423 Specify if the kernel should ignore (off)
>> 6424 topology updates sent by the hypervisor to this
>> 6425 LPAR.
>> 6426
6639 torture.disable_onoff_at_boot= [KNL] 6427 torture.disable_onoff_at_boot= [KNL]
6640 Prevent the CPU-hotpl 6428 Prevent the CPU-hotplug component of torturing
6641 until after init has 6429 until after init has spawned.
6642 6430
6643 torture.ftrace_dump_at_shutdown= [KNL 6431 torture.ftrace_dump_at_shutdown= [KNL]
6644 Dump the ftrace buffe 6432 Dump the ftrace buffer at torture-test shutdown,
6645 even if there were no 6433 even if there were no errors. This can be a
6646 very costly operation 6434 very costly operation when many torture tests
6647 are running concurren 6435 are running concurrently, especially on systems
6648 with rotating-rust st 6436 with rotating-rust storage.
6649 6437
6650 torture.verbose_sleep_frequency= [KNL 6438 torture.verbose_sleep_frequency= [KNL]
6651 Specifies how many ve 6439 Specifies how many verbose printk()s should be
6652 emitted between each 6440 emitted between each sleep. The default of zero
6653 disables verbose-prin 6441 disables verbose-printk() sleeping.
6654 6442
6655 torture.verbose_sleep_duration= [KNL] 6443 torture.verbose_sleep_duration= [KNL]
6656 Duration of each verb 6444 Duration of each verbose-printk() sleep in jiffies.
6657 6445
>> 6446 tp720= [HW,PS2]
>> 6447
6658 tpm_suspend_pcr=[HW,TPM] 6448 tpm_suspend_pcr=[HW,TPM]
6659 Format: integer pcr i 6449 Format: integer pcr id
6660 Specify that at suspe 6450 Specify that at suspend time, the tpm driver
6661 should extend the spe 6451 should extend the specified pcr with zeros,
6662 as a workaround for s 6452 as a workaround for some chips which fail to
6663 flush the last writte 6453 flush the last written pcr on TPM_SaveState.
6664 This will guarantee t 6454 This will guarantee that all the other pcrs
6665 are saved. 6455 are saved.
6666 6456
6667 tpm_tis.interrupts= [HW,TPM] 6457 tpm_tis.interrupts= [HW,TPM]
6668 Enable interrupts for 6458 Enable interrupts for the MMIO based physical layer
6669 for the FIFO interfac 6459 for the FIFO interface. By default it is set to false
6670 (0). For more informa 6460 (0). For more information about TPM hardware interfaces
6671 defined by Trusted Co 6461 defined by Trusted Computing Group (TCG) see
6672 https://trustedcomput 6462 https://trustedcomputinggroup.org/resource/pc-client-platform-tpm-profile-ptp-specification/
6673 6463
6674 tp_printk [FTRACE] 6464 tp_printk [FTRACE]
6675 Have the tracepoints 6465 Have the tracepoints sent to printk as well as the
6676 tracing ring buffer. 6466 tracing ring buffer. This is useful for early boot up
6677 where the system hang 6467 where the system hangs or reboots and does not give the
6678 option for reading th 6468 option for reading the tracing buffer or performing a
6679 ftrace_dump_on_oops. 6469 ftrace_dump_on_oops.
6680 6470
6681 To turn off having tr 6471 To turn off having tracepoints sent to printk,
6682 echo 0 > /proc/sys/k 6472 echo 0 > /proc/sys/kernel/tracepoint_printk
6683 Note, echoing 1 into 6473 Note, echoing 1 into this file without the
6684 tp_printk kernel cmdl !! 6474 tracepoint_printk kernel cmdline option has no effect.
6685 6475
6686 The tp_printk_stop_on 6476 The tp_printk_stop_on_boot (see below) can also be used
6687 to stop the printing 6477 to stop the printing of events to console at
6688 late_initcall_sync. 6478 late_initcall_sync.
6689 6479
6690 ** CAUTION ** 6480 ** CAUTION **
6691 6481
6692 Having tracepoints se 6482 Having tracepoints sent to printk() and activating high
6693 frequency tracepoints 6483 frequency tracepoints such as irq or sched, can cause
6694 the system to live lo 6484 the system to live lock.
6695 6485
6696 tp_printk_stop_on_boot [FTRACE] 6486 tp_printk_stop_on_boot [FTRACE]
6697 When tp_printk (above 6487 When tp_printk (above) is set, it can cause a lot of noise
6698 on the console. It ma 6488 on the console. It may be useful to only include the
6699 printing of events du 6489 printing of events during boot up, as user space may
6700 make the system inope 6490 make the system inoperable.
6701 6491
6702 This command line opt 6492 This command line option will stop the printing of events
6703 to console at the lat 6493 to console at the late_initcall_sync() time frame.
6704 6494
6705 trace_buf_size=nn[KMG] 6495 trace_buf_size=nn[KMG]
6706 [FTRACE] will set tra 6496 [FTRACE] will set tracing buffer size on each cpu.
6707 6497
6708 trace_clock= [FTRACE] Set the cloc 6498 trace_clock= [FTRACE] Set the clock used for tracing events
6709 at boot up. 6499 at boot up.
6710 local - Use the per C 6500 local - Use the per CPU time stamp counter
6711 (converted in 6501 (converted into nanoseconds). Fast, but
6712 depending on 6502 depending on the architecture, may not be
6713 in sync betwe 6503 in sync between CPUs.
6714 global - Event time s 6504 global - Event time stamps are synchronize across
6715 CPUs. May be 6505 CPUs. May be slower than the local clock,
6716 but better fo 6506 but better for some race conditions.
6717 counter - Simple coun 6507 counter - Simple counting of events (1, 2, ..)
6718 note, some co 6508 note, some counts may be skipped due to the
6719 infrastructur 6509 infrastructure grabbing the clock more than
6720 once per even 6510 once per event.
6721 uptime - Use jiffies 6511 uptime - Use jiffies as the time stamp.
6722 perf - Use the same c 6512 perf - Use the same clock that perf uses.
6723 mono - Use ktime_get_ 6513 mono - Use ktime_get_mono_fast_ns() for time stamps.
6724 mono_raw - Use ktime_ 6514 mono_raw - Use ktime_get_raw_fast_ns() for time
6725 stamps. 6515 stamps.
6726 boot - Use ktime_get_ 6516 boot - Use ktime_get_boot_fast_ns() for time stamps.
6727 Architectures may add 6517 Architectures may add more clocks. See
6728 Documentation/trace/f 6518 Documentation/trace/ftrace.rst for more details.
6729 6519
6730 trace_event=[event-list] 6520 trace_event=[event-list]
6731 [FTRACE] Set and star 6521 [FTRACE] Set and start specified trace events in order
6732 to facilitate early b 6522 to facilitate early boot debugging. The event-list is a
6733 comma-separated list 6523 comma-separated list of trace events to enable. See
6734 also Documentation/tr 6524 also Documentation/trace/events.rst
6735 6525
6736 trace_instance=[instance-info] 6526 trace_instance=[instance-info]
6737 [FTRACE] Create a rin 6527 [FTRACE] Create a ring buffer instance early in boot up.
6738 This will be listed i 6528 This will be listed in:
6739 6529
6740 /sys/kernel/t 6530 /sys/kernel/tracing/instances
6741 6531
6742 Events can be enabled 6532 Events can be enabled at the time the instance is created
6743 via: 6533 via:
6744 6534
6745 trace_instanc 6535 trace_instance=<name>,<system1>:<event1>,<system2>:<event2>
6746 6536
6747 Note, the "<system*>: 6537 Note, the "<system*>:" portion is optional if the event is
6748 unique. 6538 unique.
6749 6539
6750 trace_instanc 6540 trace_instance=foo,sched:sched_switch,irq_handler_entry,initcall
6751 6541
6752 will enable the "sche 6542 will enable the "sched_switch" event (note, the "sched:" is optional, and
6753 the same thing would 6543 the same thing would happen if it was left off). The irq_handler_entry
6754 event, and all events 6544 event, and all events under the "initcall" system.
6755 6545
6756 trace_options=[option-list] 6546 trace_options=[option-list]
6757 [FTRACE] Enable or di 6547 [FTRACE] Enable or disable tracer options at boot.
6758 The option-list is a 6548 The option-list is a comma delimited list of options
6759 that can be enabled o 6549 that can be enabled or disabled just as if you were
6760 to echo the option na 6550 to echo the option name into
6761 6551
6762 /sys/kernel/traci 6552 /sys/kernel/tracing/trace_options
6763 6553
6764 For example, to enabl 6554 For example, to enable stacktrace option (to dump the
6765 stack trace of each e 6555 stack trace of each event), add to the command line:
6766 6556
6767 trace_options=s 6557 trace_options=stacktrace
6768 6558
6769 See also Documentatio 6559 See also Documentation/trace/ftrace.rst "trace options"
6770 section. 6560 section.
6771 6561
6772 trace_trigger=[trigger-list] 6562 trace_trigger=[trigger-list]
6773 [FTRACE] Add a event 6563 [FTRACE] Add a event trigger on specific events.
6774 Set a trigger on top 6564 Set a trigger on top of a specific event, with an optional
6775 filter. 6565 filter.
6776 6566
6777 The format is is "tra 6567 The format is is "trace_trigger=<event>.<trigger>[ if <filter>],..."
6778 Where more than one t 6568 Where more than one trigger may be specified that are comma deliminated.
6779 6569
6780 For example: 6570 For example:
6781 6571
6782 trace_trigger="sche 6572 trace_trigger="sched_switch.stacktrace if prev_state == 2"
6783 6573
6784 The above will enable 6574 The above will enable the "stacktrace" trigger on the "sched_switch"
6785 event but only trigge 6575 event but only trigger it if the "prev_state" of the "sched_switch"
6786 event is "2" (TASK_UN 6576 event is "2" (TASK_UNINTERUPTIBLE).
6787 6577
6788 See also "Event trigg 6578 See also "Event triggers" in Documentation/trace/events.rst
6789 6579
6790 6580
6791 traceoff_on_warning 6581 traceoff_on_warning
6792 [FTRACE] enable this 6582 [FTRACE] enable this option to disable tracing when a
6793 warning is hit. This 6583 warning is hit. This turns off "tracing_on". Tracing can
6794 be enabled again by e 6584 be enabled again by echoing '1' into the "tracing_on"
6795 file located in /sys/ 6585 file located in /sys/kernel/tracing/
6796 6586
6797 This option is useful 6587 This option is useful, as it disables the trace before
6798 the WARNING dump is c 6588 the WARNING dump is called, which prevents the trace to
6799 be filled with conten 6589 be filled with content caused by the warning output.
6800 6590
6801 This option can also 6591 This option can also be set at run time via the sysctl
6802 option: kernel/trace 6592 option: kernel/traceoff_on_warning
6803 6593
6804 transparent_hugepage= 6594 transparent_hugepage=
6805 [KNL] 6595 [KNL]
6806 Format: [always|madvi 6596 Format: [always|madvise|never]
6807 Can be used to contro 6597 Can be used to control the default behavior of the system
6808 with respect to trans 6598 with respect to transparent hugepages.
6809 See Documentation/adm 6599 See Documentation/admin-guide/mm/transhuge.rst
6810 for more details. 6600 for more details.
6811 6601
6812 trusted.source= [KEYS] 6602 trusted.source= [KEYS]
6813 Format: <string> 6603 Format: <string>
6814 This parameter identi 6604 This parameter identifies the trust source as a backend
6815 for trusted keys impl 6605 for trusted keys implementation. Supported trust
6816 sources: 6606 sources:
6817 - "tpm" 6607 - "tpm"
6818 - "tee" 6608 - "tee"
6819 - "caam" 6609 - "caam"
6820 - "dcp" <<
6821 If not specified then 6610 If not specified then it defaults to iterating through
6822 the trust source list 6611 the trust source list starting with TPM and assigns the
6823 first trust source as 6612 first trust source as a backend which is initialized
6824 successfully during i 6613 successfully during iteration.
6825 6614
6826 trusted.rng= [KEYS] 6615 trusted.rng= [KEYS]
6827 Format: <string> 6616 Format: <string>
6828 The RNG used to gener 6617 The RNG used to generate key material for trusted keys.
6829 Can be one of: 6618 Can be one of:
6830 - "kernel" 6619 - "kernel"
6831 - the same value as t 6620 - the same value as trusted.source: "tpm" or "tee"
6832 - "default" 6621 - "default"
6833 If not specified, "de 6622 If not specified, "default" is used. In this case,
6834 the RNG's choice is l 6623 the RNG's choice is left to each individual trust source.
6835 6624
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 6625 tsc= Disable clocksource stability checks for TSC.
6849 Format: <string> 6626 Format: <string>
6850 [x86] reliable: mark 6627 [x86] reliable: mark tsc clocksource as reliable, this
6851 disables clocksource 6628 disables clocksource verification at runtime, as well
6852 as the stability chec 6629 as the stability checks done at bootup. Used to enable
6853 high-resolution timer 6630 high-resolution timer mode on older hardware, and in
6854 virtualized environme 6631 virtualized environment.
6855 [x86] noirqtime: Do n 6632 [x86] noirqtime: Do not use TSC to do irq accounting.
6856 Used to run time disa 6633 Used to run time disable IRQ_TIME_ACCOUNTING on any
6857 platforms where RDTSC 6634 platforms where RDTSC is slow and this accounting
6858 can add overhead. 6635 can add overhead.
6859 [x86] unstable: mark 6636 [x86] unstable: mark the TSC clocksource as unstable, this
6860 marks the TSC uncondi 6637 marks the TSC unconditionally unstable at bootup and
6861 avoids any further wo 6638 avoids any further wobbles once the TSC watchdog notices.
6862 [x86] nowatchdog: dis 6639 [x86] nowatchdog: disable clocksource watchdog. Used
6863 in situations with st 6640 in situations with strict latency requirements (where
6864 interruptions from cl 6641 interruptions from clocksource watchdog are not
6865 acceptable). 6642 acceptable).
6866 [x86] recalibrate: fo 6643 [x86] recalibrate: force recalibration against a HW timer
6867 (HPET or PM timer) on 6644 (HPET or PM timer) on systems whose TSC frequency was
6868 obtained from HW or F 6645 obtained from HW or FW using either an MSR or CPUID(0x15).
6869 Warn if the differenc 6646 Warn if the difference is more than 500 ppm.
6870 [x86] watchdog: Use T 6647 [x86] watchdog: Use TSC as the watchdog clocksource with
6871 which to check other 6648 which to check other HW timers (HPET or PM timer), but
6872 only on systems where 6649 only on systems where TSC has been deemed trustworthy.
6873 This will be suppress 6650 This will be suppressed by an earlier tsc=nowatchdog and
6874 can be overridden by 6651 can be overridden by a later tsc=nowatchdog. A console
6875 message will flag any 6652 message will flag any such suppression or overriding.
6876 6653
6877 tsc_early_khz= [X86,EARLY] Skip earl !! 6654 tsc_early_khz= [X86] Skip early TSC calibration and use the given
6878 value instead. Useful 6655 value instead. Useful when the early TSC frequency discovery
6879 procedure is not reli 6656 procedure is not reliable, such as on overclocked systems
6880 with CPUID.16h suppor 6657 with CPUID.16h support and partial CPUID.15h support.
6881 Format: <unsigned int 6658 Format: <unsigned int>
6882 6659
6883 tsx= [X86] Control Transac 6660 tsx= [X86] Control Transactional Synchronization
6884 Extensions (TSX) feat 6661 Extensions (TSX) feature in Intel processors that
6885 support TSX control. 6662 support TSX control.
6886 6663
6887 This parameter contro 6664 This parameter controls the TSX feature. The options are:
6888 6665
6889 on - Enable TSX 6666 on - Enable TSX on the system. Although there are
6890 mitigations f 6667 mitigations for all known security vulnerabilities,
6891 TSX has been 6668 TSX has been known to be an accelerator for
6892 several previ 6669 several previous speculation-related CVEs, and
6893 so there may 6670 so there may be unknown security risks associated
6894 with leaving 6671 with leaving it enabled.
6895 6672
6896 off - Disable TSX 6673 off - Disable TSX on the system. (Note that this
6897 option takes 6674 option takes effect only on newer CPUs which are
6898 not vulnerabl 6675 not vulnerable to MDS, i.e., have
6899 MSR_IA32_ARCH 6676 MSR_IA32_ARCH_CAPABILITIES.MDS_NO=1 and which get
6900 the new IA32_ 6677 the new IA32_TSX_CTRL MSR through a microcode
6901 update. This 6678 update. This new MSR allows for the reliable
6902 deactivation 6679 deactivation of the TSX functionality.)
6903 6680
6904 auto - Disable TSX 6681 auto - Disable TSX if X86_BUG_TAA is present,
6905 otherwise e 6682 otherwise enable TSX on the system.
6906 6683
6907 Not specifying this o 6684 Not specifying this option is equivalent to tsx=off.
6908 6685
6909 See Documentation/adm 6686 See Documentation/admin-guide/hw-vuln/tsx_async_abort.rst
6910 for more details. 6687 for more details.
6911 6688
6912 tsx_async_abort= [X86,INTEL,EARLY] Co !! 6689 tsx_async_abort= [X86,INTEL] Control mitigation for the TSX Async
6913 Abort (TAA) vulnerabi 6690 Abort (TAA) vulnerability.
6914 6691
6915 Similar to Micro-arch 6692 Similar to Micro-architectural Data Sampling (MDS)
6916 certain CPUs that sup 6693 certain CPUs that support Transactional
6917 Synchronization Exten 6694 Synchronization Extensions (TSX) are vulnerable to an
6918 exploit against CPU i 6695 exploit against CPU internal buffers which can forward
6919 information to a disc 6696 information to a disclosure gadget under certain
6920 conditions. 6697 conditions.
6921 6698
6922 In vulnerable process 6699 In vulnerable processors, the speculatively forwarded
6923 data can be used in a 6700 data can be used in a cache side channel attack, to
6924 access data to which 6701 access data to which the attacker does not have direct
6925 access. 6702 access.
6926 6703
6927 This parameter contro 6704 This parameter controls the TAA mitigation. The
6928 options are: 6705 options are:
6929 6706
6930 full - Enable T 6707 full - Enable TAA mitigation on vulnerable CPUs
6931 if TSX i 6708 if TSX is enabled.
6932 6709
6933 full,nosmt - Enable T 6710 full,nosmt - Enable TAA mitigation and disable SMT on
6934 vulnerab 6711 vulnerable CPUs. If TSX is disabled, SMT
6935 is not d 6712 is not disabled because CPU is not
6936 vulnerab 6713 vulnerable to cross-thread TAA attacks.
6937 off - Uncondit 6714 off - Unconditionally disable TAA mitigation
6938 6715
6939 On MDS-affected machi 6716 On MDS-affected machines, tsx_async_abort=off can be
6940 prevented by an activ 6717 prevented by an active MDS mitigation as both vulnerabilities
6941 are mitigated with th 6718 are mitigated with the same mechanism so in order to disable
6942 this mitigation, you 6719 this mitigation, you need to specify mds=off too.
6943 6720
6944 Not specifying this o 6721 Not specifying this option is equivalent to
6945 tsx_async_abort=full. 6722 tsx_async_abort=full. On CPUs which are MDS affected
6946 and deploy MDS mitiga 6723 and deploy MDS mitigation, TAA mitigation is not
6947 required and doesn't 6724 required and doesn't provide any additional
6948 mitigation. 6725 mitigation.
6949 6726
6950 For details see: 6727 For details see:
6951 Documentation/admin-g 6728 Documentation/admin-guide/hw-vuln/tsx_async_abort.rst
6952 6729
6953 turbografx.map[2|3]= [HW,JOY] 6730 turbografx.map[2|3]= [HW,JOY]
6954 TurboGraFX parallel p 6731 TurboGraFX parallel port interface
6955 Format: 6732 Format:
6956 <port#>,<js1>,<js2>,< 6733 <port#>,<js1>,<js2>,<js3>,<js4>,<js5>,<js6>,<js7>
6957 See also Documentatio 6734 See also Documentation/input/devices/joystick-parport.rst
6958 6735
6959 udbg-immortal [PPC] When debugging 6736 udbg-immortal [PPC] When debugging early kernel crashes that
6960 happen after console_ 6737 happen after console_init() and before a proper
6961 console driver takes 6738 console driver takes over, this boot options might
6962 help "seeing" what's 6739 help "seeing" what's going on.
6963 6740
6964 uhash_entries= [KNL,NET] 6741 uhash_entries= [KNL,NET]
6965 Set number of hash bu 6742 Set number of hash buckets for UDP/UDP-Lite connections
6966 6743
6967 uhci-hcd.ignore_oc= 6744 uhci-hcd.ignore_oc=
6968 [USB] Ignore overcurr 6745 [USB] Ignore overcurrent events (default N).
6969 Some badly-designed m 6746 Some badly-designed motherboards generate lots of
6970 bogus events, for por 6747 bogus events, for ports that aren't wired to
6971 anything. Set this p 6748 anything. Set this parameter to avoid log spamming.
6972 Note that genuine ove 6749 Note that genuine overcurrent events won't be
6973 reported either. 6750 reported either.
6974 6751
6975 unknown_nmi_panic 6752 unknown_nmi_panic
6976 [X86] Cause panic on 6753 [X86] Cause panic on unknown NMI.
6977 6754
6978 unwind_debug [X86-64,EARLY] !! 6755 unwind_debug [X86-64]
6979 Enable unwinder debug 6756 Enable unwinder debug output. This can be
6980 useful for debugging 6757 useful for debugging certain unwinder error
6981 conditions, including 6758 conditions, including corrupt stacks and
6982 bad/missing unwinder 6759 bad/missing unwinder metadata.
6983 6760
6984 usbcore.authorized_default= 6761 usbcore.authorized_default=
6985 [USB] Default USB dev 6762 [USB] Default USB device authorization:
6986 (default -1 = authori 6763 (default -1 = authorized (same as 1),
6987 0 = not authorized, 1 6764 0 = not authorized, 1 = authorized, 2 = authorized
6988 if device connected t 6765 if device connected to internal port)
6989 6766
6990 usbcore.autosuspend= 6767 usbcore.autosuspend=
6991 [USB] The autosuspend 6768 [USB] The autosuspend time delay (in seconds) used
6992 for newly-detected US 6769 for newly-detected USB devices (default 2). This
6993 is the time required 6770 is the time required before an idle device will be
6994 autosuspended. Devic 6771 autosuspended. Devices for which the delay is set
6995 to a negative value w 6772 to a negative value won't be autosuspended at all.
6996 6773
6997 usbcore.usbfs_snoop= 6774 usbcore.usbfs_snoop=
6998 [USB] Set to log all 6775 [USB] Set to log all usbfs traffic (default 0 = off).
6999 6776
7000 usbcore.usbfs_snoop_max= 6777 usbcore.usbfs_snoop_max=
7001 [USB] Maximum number 6778 [USB] Maximum number of bytes to snoop in each URB
7002 (default = 65536). 6779 (default = 65536).
7003 6780
7004 usbcore.blinkenlights= 6781 usbcore.blinkenlights=
7005 [USB] Set to cycle le 6782 [USB] Set to cycle leds on hubs (default 0 = off).
7006 6783
7007 usbcore.old_scheme_first= 6784 usbcore.old_scheme_first=
7008 [USB] Start with the 6785 [USB] Start with the old device initialization
7009 scheme (default 0 = o 6786 scheme (default 0 = off).
7010 6787
7011 usbcore.usbfs_memory_mb= 6788 usbcore.usbfs_memory_mb=
7012 [USB] Memory limit (i 6789 [USB] Memory limit (in MB) for buffers allocated by
7013 usbfs (default = 16, 6790 usbfs (default = 16, 0 = max = 2047).
7014 6791
7015 usbcore.use_both_schemes= 6792 usbcore.use_both_schemes=
7016 [USB] Try the other d 6793 [USB] Try the other device initialization scheme
7017 if the first one fail 6794 if the first one fails (default 1 = enabled).
7018 6795
7019 usbcore.initial_descriptor_timeout= 6796 usbcore.initial_descriptor_timeout=
7020 [USB] Specifies timeo 6797 [USB] Specifies timeout for the initial 64-byte
7021 USB_REQ_GET_DESCRIPTO 6798 USB_REQ_GET_DESCRIPTOR request in milliseconds
7022 (default 5000 = 5.0 s 6799 (default 5000 = 5.0 seconds).
7023 6800
7024 usbcore.nousb [USB] Disable the USB 6801 usbcore.nousb [USB] Disable the USB subsystem
7025 6802
7026 usbcore.quirks= 6803 usbcore.quirks=
7027 [USB] A list of quirk 6804 [USB] A list of quirk entries to augment the built-in
7028 usb core quirk list. 6805 usb core quirk list. List entries are separated by
7029 commas. Each entry ha 6806 commas. Each entry has the form
7030 VendorID:ProductID:Fl 6807 VendorID:ProductID:Flags. The IDs are 4-digit hex
7031 numbers and Flags is 6808 numbers and Flags is a set of letters. Each letter
7032 will change the built 6809 will change the built-in quirk; setting it if it is
7033 clear and clearing it 6810 clear and clearing it if it is set. The letters have
7034 the following meaning 6811 the following meanings:
7035 a = USB_QUIRK 6812 a = USB_QUIRK_STRING_FETCH_255 (string
7036 descr 6813 descriptors must not be fetched using
7037 a 255 6814 a 255-byte read);
7038 b = USB_QUIRK 6815 b = USB_QUIRK_RESET_RESUME (device can't resume
7039 corre 6816 correctly so reset it instead);
7040 c = USB_QUIRK 6817 c = USB_QUIRK_NO_SET_INTF (device can't handle
7041 Set-I 6818 Set-Interface requests);
7042 d = USB_QUIRK 6819 d = USB_QUIRK_CONFIG_INTF_STRINGS (device can't
7043 handl 6820 handle its Configuration or Interface
7044 strin 6821 strings);
7045 e = USB_QUIRK 6822 e = USB_QUIRK_RESET (device can't be reset
7046 (e.g 6823 (e.g morph devices), don't use reset);
7047 f = USB_QUIRK 6824 f = USB_QUIRK_HONOR_BNUMINTERFACES (device has
7048 more 6825 more interface descriptions than the
7049 bNumI 6826 bNumInterfaces count, and can't handle
7050 talki 6827 talking to these interfaces);
7051 g = USB_QUIRK 6828 g = USB_QUIRK_DELAY_INIT (device needs a pause
7052 durin 6829 during initialization, after we read
7053 the d 6830 the device descriptor);
7054 h = USB_QUIRK 6831 h = USB_QUIRK_LINEAR_UFRAME_INTR_BINTERVAL (For
7055 high 6832 high speed and super speed interrupt
7056 endpo 6833 endpoints, the USB 2.0 and USB 3.0 spec
7057 requi 6834 require the interval in microframes (1
7058 micro 6835 microframe = 125 microseconds) to be
7059 calcu 6836 calculated as interval = 2 ^
7060 (bInt 6837 (bInterval-1).
7061 Devic 6838 Devices with this quirk report their
7062 bInte 6839 bInterval as the result of this
7063 calcu 6840 calculation instead of the exponent
7064 varia 6841 variable used in the calculation);
7065 i = USB_QUIRK 6842 i = USB_QUIRK_DEVICE_QUALIFIER (device can't
7066 handl 6843 handle device_qualifier descriptor
7067 reque 6844 requests);
7068 j = USB_QUIRK 6845 j = USB_QUIRK_IGNORE_REMOTE_WAKEUP (device
7069 gener 6846 generates spurious wakeup, ignore
7070 remot 6847 remote wakeup capability);
7071 k = USB_QUIRK 6848 k = USB_QUIRK_NO_LPM (device can't handle Link
7072 Power 6849 Power Management);
7073 l = USB_QUIRK 6850 l = USB_QUIRK_LINEAR_FRAME_INTR_BINTERVAL
7074 (Devi 6851 (Device reports its bInterval as linear
7075 frame 6852 frames instead of the USB 2.0
7076 calcu 6853 calculation);
7077 m = USB_QUIRK 6854 m = USB_QUIRK_DISCONNECT_SUSPEND (Device needs
7078 to be 6855 to be disconnected before suspend to
7079 preve 6856 prevent spurious wakeup);
7080 n = USB_QUIRK 6857 n = USB_QUIRK_DELAY_CTRL_MSG (Device needs a
7081 pause 6858 pause after every control message);
7082 o = USB_QUIRK 6859 o = USB_QUIRK_HUB_SLOW_RESET (Hub needs extra
7083 delay 6860 delay after resetting its port);
7084 p = USB_QUIRK 6861 p = USB_QUIRK_SHORT_SET_ADDRESS_REQ_TIMEOUT
7085 (Redu 6862 (Reduce timeout of the SET_ADDRESS
7086 reque 6863 request from 5000 ms to 500 ms);
7087 Example: quirks=0781: 6864 Example: quirks=0781:5580:bk,0a5c:5834:gij
7088 6865
7089 usbhid.mousepoll= 6866 usbhid.mousepoll=
7090 [USBHID] The interval 6867 [USBHID] The interval which mice are to be polled at.
7091 6868
7092 usbhid.jspoll= 6869 usbhid.jspoll=
7093 [USBHID] The interval 6870 [USBHID] The interval which joysticks are to be polled at.
7094 6871
7095 usbhid.kbpoll= 6872 usbhid.kbpoll=
7096 [USBHID] The interval 6873 [USBHID] The interval which keyboards are to be polled at.
7097 6874
7098 usb-storage.delay_use= 6875 usb-storage.delay_use=
7099 [UMS] The delay in se 6876 [UMS] The delay in seconds before a new device is
7100 scanned for Logical U 6877 scanned for Logical Units (default 1).
7101 Optionally the delay <<
7102 suffix with "ms". <<
7103 Example: delay_use=25 <<
7104 6878
7105 usb-storage.quirks= 6879 usb-storage.quirks=
7106 [UMS] A list of quirk 6880 [UMS] A list of quirks entries to supplement or
7107 override the built-in 6881 override the built-in unusual_devs list. List
7108 entries are separated 6882 entries are separated by commas. Each entry has
7109 the form VID:PID:Flag 6883 the form VID:PID:Flags where VID and PID are Vendor
7110 and Product ID values 6884 and Product ID values (4-digit hex numbers) and
7111 Flags is a set of cha 6885 Flags is a set of characters, each corresponding
7112 to a common usb-stora 6886 to a common usb-storage quirk flag as follows:
7113 a = SANE_SENS 6887 a = SANE_SENSE (collect more than 18 bytes
7114 of se 6888 of sense data, not on uas);
7115 b = BAD_SENSE 6889 b = BAD_SENSE (don't collect more than 18
7116 bytes 6890 bytes of sense data, not on uas);
7117 c = FIX_CAPAC 6891 c = FIX_CAPACITY (decrease the reported
7118 devic 6892 device capacity by one sector);
7119 d = NO_READ_D 6893 d = NO_READ_DISC_INFO (don't use
7120 READ_ 6894 READ_DISC_INFO command, not on uas);
7121 e = NO_READ_C 6895 e = NO_READ_CAPACITY_16 (don't use
7122 READ_ 6896 READ_CAPACITY_16 command);
7123 f = NO_REPORT 6897 f = NO_REPORT_OPCODES (don't use report opcodes
7124 comma 6898 command, uas only);
7125 g = MAX_SECTO 6899 g = MAX_SECTORS_240 (don't transfer more than
7126 240 s 6900 240 sectors at a time, uas only);
7127 h = CAPACITY_ 6901 h = CAPACITY_HEURISTICS (decrease the
7128 repor 6902 reported device capacity by one
7129 secto 6903 sector if the number is odd);
7130 i = IGNORE_DE 6904 i = IGNORE_DEVICE (don't bind to this
7131 devic 6905 device);
7132 j = NO_REPORT 6906 j = NO_REPORT_LUNS (don't use report luns
7133 comma 6907 command, uas only);
7134 k = NO_SAME ( 6908 k = NO_SAME (do not use WRITE_SAME, uas only)
7135 l = NOT_LOCKA 6909 l = NOT_LOCKABLE (don't try to lock and
7136 unloc 6910 unlock ejectable media, not on uas);
7137 m = MAX_SECTO 6911 m = MAX_SECTORS_64 (don't transfer more
7138 than 6912 than 64 sectors = 32 KB at a time,
7139 not o 6913 not on uas);
7140 n = INITIAL_R 6914 n = INITIAL_READ10 (force a retry of the
7141 initi 6915 initial READ(10) command, not on uas);
7142 o = CAPACITY_ 6916 o = CAPACITY_OK (accept the capacity
7143 repor 6917 reported by the device, not on uas);
7144 p = WRITE_CAC 6918 p = WRITE_CACHE (the device cache is ON
7145 by de 6919 by default, not on uas);
7146 r = IGNORE_RE 6920 r = IGNORE_RESIDUE (the device reports
7147 bogus 6921 bogus residue values, not on uas);
7148 s = SINGLE_LU 6922 s = SINGLE_LUN (the device has only one
7149 Logic 6923 Logical Unit);
7150 t = NO_ATA_1X 6924 t = NO_ATA_1X (don't allow ATA(12) and ATA(16)
7151 comma 6925 commands, uas only);
7152 u = IGNORE_UA 6926 u = IGNORE_UAS (don't bind to the uas driver);
7153 w = NO_WP_DET 6927 w = NO_WP_DETECT (don't test whether the
7154 mediu 6928 medium is write-protected).
7155 y = ALWAYS_SY 6929 y = ALWAYS_SYNC (issue a SYNCHRONIZE_CACHE
7156 even 6930 even if the device claims no cache,
7157 not o 6931 not on uas)
7158 Example: quirks=0419: 6932 Example: quirks=0419:aaf5:rl,0421:0433:rc
7159 6933
7160 user_debug= [KNL,ARM] 6934 user_debug= [KNL,ARM]
7161 Format: <int> 6935 Format: <int>
7162 See arch/arm/Kconfig. 6936 See arch/arm/Kconfig.debug help text.
7163 1 - undefine 6937 1 - undefined instruction events
7164 2 - system c 6938 2 - system calls
7165 4 - invalid 6939 4 - invalid data aborts
7166 8 - SIGSEGV 6940 8 - SIGSEGV faults
7167 16 - SIGBUS f 6941 16 - SIGBUS faults
7168 Example: user_debug=3 6942 Example: user_debug=31
7169 6943
7170 userpte= 6944 userpte=
7171 [X86,EARLY] Flags con !! 6945 [X86] Flags controlling user PTE allocations.
7172 6946
7173 nohigh = do n 6947 nohigh = do not allocate PTE pages in
7174 HIGHM 6948 HIGHMEM regardless of setting
7175 of CO 6949 of CONFIG_HIGHPTE.
7176 6950
7177 vdso= [X86,SH,SPARC] 6951 vdso= [X86,SH,SPARC]
7178 On X86_32, this is an 6952 On X86_32, this is an alias for vdso32=. Otherwise:
7179 6953
7180 vdso=1: enable VDSO ( 6954 vdso=1: enable VDSO (the default)
7181 vdso=0: disable VDSO 6955 vdso=0: disable VDSO mapping
7182 6956
7183 vdso32= [X86] Control the 32- 6957 vdso32= [X86] Control the 32-bit vDSO
7184 vdso32=1: enable 32-b 6958 vdso32=1: enable 32-bit VDSO
7185 vdso32=0 or vdso32=2: 6959 vdso32=0 or vdso32=2: disable 32-bit VDSO
7186 6960
7187 See the help text for 6961 See the help text for CONFIG_COMPAT_VDSO for more
7188 details. If CONFIG_C 6962 details. If CONFIG_COMPAT_VDSO is set, the default is
7189 vdso32=0; otherwise, 6963 vdso32=0; otherwise, the default is vdso32=1.
7190 6964
7191 For compatibility wit 6965 For compatibility with older kernels, vdso32=2 is an
7192 alias for vdso32=0. 6966 alias for vdso32=0.
7193 6967
7194 Try vdso32=0 if you e 6968 Try vdso32=0 if you encounter an error that says:
7195 dl_main: Assertion `( 6969 dl_main: Assertion `(void *) ph->p_vaddr == _rtld_local._dl_sysinfo_dso' failed!
7196 6970
7197 video= [FB,EARLY] Frame buff !! 6971 vector= [IA-64,SMP]
>> 6972 vector=percpu: enable percpu vector domain
>> 6973
>> 6974 video= [FB] Frame buffer configuration
7198 See Documentation/fb/ 6975 See Documentation/fb/modedb.rst.
7199 6976
7200 video.brightness_switch_enabled= [ACP 6977 video.brightness_switch_enabled= [ACPI]
7201 Format: [0|1] 6978 Format: [0|1]
7202 If set to 1, on recei 6979 If set to 1, on receiving an ACPI notify event
7203 generated by hotkey, 6980 generated by hotkey, video driver will adjust brightness
7204 level and then send o 6981 level and then send out the event to user space through
7205 the allocated input d 6982 the allocated input device. If set to 0, video driver
7206 will only send out th 6983 will only send out the event without touching backlight
7207 brightness level. 6984 brightness level.
7208 default: 1 6985 default: 1
7209 6986
7210 virtio_mmio.device= 6987 virtio_mmio.device=
7211 [VMMIO] Memory mapped 6988 [VMMIO] Memory mapped virtio (platform) device.
7212 6989
7213 <size>@<basead 6990 <size>@<baseaddr>:<irq>[:<id>]
7214 where: 6991 where:
7215 <size> := 6992 <size> := size (can use standard suffixes
7216 6993 like K, M and G)
7217 <baseaddr> := 6994 <baseaddr> := physical base address
7218 <irq> := 6995 <irq> := interrupt number (as passed to
7219 6996 request_irq())
7220 <id> := 6997 <id> := (optional) platform device id
7221 example: 6998 example:
7222 virtio_mmio.d 6999 virtio_mmio.device=1K@0x100b0000:48:7
7223 7000
7224 Can be used multiple 7001 Can be used multiple times for multiple devices.
7225 7002
7226 vga= [BOOT,X86-32] Select 7003 vga= [BOOT,X86-32] Select a particular video mode
7227 See Documentation/arc 7004 See Documentation/arch/x86/boot.rst and
7228 Documentation/admin-g 7005 Documentation/admin-guide/svga.rst.
7229 Use vga=ask for menu. 7006 Use vga=ask for menu.
7230 This is actually a bo 7007 This is actually a boot loader parameter; the value is
7231 passed to the kernel 7008 passed to the kernel using a special protocol.
7232 7009
7233 vm_debug[=options] [KNL] Availab 7010 vm_debug[=options] [KNL] Available with CONFIG_DEBUG_VM=y.
7234 May slow down system 7011 May slow down system boot speed, especially when
7235 enabled on systems wi 7012 enabled on systems with a large amount of memory.
7236 All options are enabl 7013 All options are enabled by default, and this
7237 interface is meant to 7014 interface is meant to allow for selectively
7238 enabling or disabling 7015 enabling or disabling specific virtual memory
7239 debugging features. 7016 debugging features.
7240 7017
7241 Available options are 7018 Available options are:
7242 P Enable page s 7019 P Enable page structure init time poisoning
7243 - Disable all o 7020 - Disable all of the above options
7244 7021
7245 vmalloc=nn[KMG] [KNL,BOOT,EARLY] Forc !! 7022 vmalloc=nn[KMG] [KNL,BOOT] Forces the vmalloc area to have an exact
7246 exact size of <nn>. T !! 7023 size of <nn>. This can be used to increase the
7247 the minimum size (128 !! 7024 minimum size (128MB on x86). It can also be used to
7248 It can also be used t !! 7025 decrease the size and leave more room for directly
7249 for directly mapped k !! 7026 mapped kernel RAM.
7250 not exist on many oth <<
7251 loongarch, arc, csky, <<
7252 parisc, m64k, powerpc <<
7253 7027
7254 vmcp_cma=nn[MG] [KNL,S390,EARLY] !! 7028 vmcp_cma=nn[MG] [KNL,S390]
7255 Sets the memory size 7029 Sets the memory size reserved for contiguous memory
7256 allocations for the v 7030 allocations for the vmcp device driver.
7257 7031
7258 vmhalt= [KNL,S390] Perform z/ 7032 vmhalt= [KNL,S390] Perform z/VM CP command after system halt.
7259 Format: <command> 7033 Format: <command>
7260 7034
7261 vmpanic= [KNL,S390] Perform z/ 7035 vmpanic= [KNL,S390] Perform z/VM CP command after kernel panic.
7262 Format: <command> 7036 Format: <command>
7263 7037
7264 vmpoff= [KNL,S390] Perform z/ 7038 vmpoff= [KNL,S390] Perform z/VM CP command after power off.
7265 Format: <command> 7039 Format: <command>
7266 7040
7267 vsyscall= [X86-64,EARLY] !! 7041 vsyscall= [X86-64]
7268 Controls the behavior 7042 Controls the behavior of vsyscalls (i.e. calls to
7269 fixed addresses of 0x 7043 fixed addresses of 0xffffffffff600x00 from legacy
7270 code). Most statical 7044 code). Most statically-linked binaries and older
7271 versions of glibc use 7045 versions of glibc use these calls. Because these
7272 functions are at fixe 7046 functions are at fixed addresses, they make nice
7273 targets for exploits 7047 targets for exploits that can control RIP.
7274 7048
7275 emulate Vsyscalls 7049 emulate Vsyscalls turn into traps and are emulated
7276 reasonabl 7050 reasonably safely. The vsyscall page is
7277 readable. 7051 readable.
7278 7052
7279 xonly [default] 7053 xonly [default] Vsyscalls turn into traps and are
7280 emulated 7054 emulated reasonably safely. The vsyscall
7281 page is n 7055 page is not readable.
7282 7056
7283 none Vsyscalls 7057 none Vsyscalls don't work at all. This makes
7284 them quit 7058 them quite hard to use for exploits but
7285 might bre 7059 might break your system.
7286 7060
7287 vt.color= [VT] Default text col 7061 vt.color= [VT] Default text color.
7288 Format: 0xYX, X = for 7062 Format: 0xYX, X = foreground, Y = background.
7289 Default: 0x07 = light 7063 Default: 0x07 = light gray on black.
7290 7064
7291 vt.cur_default= [VT] Default cursor s 7065 vt.cur_default= [VT] Default cursor shape.
7292 Format: 0xCCBBAA, whe 7066 Format: 0xCCBBAA, where AA, BB, and CC are the same as
7293 the parameters of the 7067 the parameters of the <Esc>[?A;B;Cc escape sequence;
7294 see VGA-softcursor.tx 7068 see VGA-softcursor.txt. Default: 2 = underline.
7295 7069
7296 vt.default_blu= [VT] 7070 vt.default_blu= [VT]
7297 Format: <blue0>,<blue 7071 Format: <blue0>,<blue1>,<blue2>,...,<blue15>
7298 Change the default bl 7072 Change the default blue palette of the console.
7299 This is a 16-member a 7073 This is a 16-member array composed of values
7300 ranging from 0-255. 7074 ranging from 0-255.
7301 7075
7302 vt.default_grn= [VT] 7076 vt.default_grn= [VT]
7303 Format: <green0>,<gre 7077 Format: <green0>,<green1>,<green2>,...,<green15>
7304 Change the default gr 7078 Change the default green palette of the console.
7305 This is a 16-member a 7079 This is a 16-member array composed of values
7306 ranging from 0-255. 7080 ranging from 0-255.
7307 7081
7308 vt.default_red= [VT] 7082 vt.default_red= [VT]
7309 Format: <red0>,<red1> 7083 Format: <red0>,<red1>,<red2>,...,<red15>
7310 Change the default re 7084 Change the default red palette of the console.
7311 This is a 16-member a 7085 This is a 16-member array composed of values
7312 ranging from 0-255. 7086 ranging from 0-255.
7313 7087
7314 vt.default_utf8= 7088 vt.default_utf8=
7315 [VT] 7089 [VT]
7316 Format=<0|1> 7090 Format=<0|1>
7317 Set system-wide defau 7091 Set system-wide default UTF-8 mode for all tty's.
7318 Default is 1, i.e. UT 7092 Default is 1, i.e. UTF-8 mode is enabled for all
7319 newly opened terminal 7093 newly opened terminals.
7320 7094
7321 vt.global_cursor_default= 7095 vt.global_cursor_default=
7322 [VT] 7096 [VT]
7323 Format=<-1|0|1> 7097 Format=<-1|0|1>
7324 Set system-wide defau 7098 Set system-wide default for whether a cursor
7325 is shown on new VTs. 7099 is shown on new VTs. Default is -1,
7326 i.e. cursors will be 7100 i.e. cursors will be created by default unless
7327 overridden by individ 7101 overridden by individual drivers. 0 will hide
7328 cursors, 1 will displ 7102 cursors, 1 will display them.
7329 7103
7330 vt.italic= [VT] Default color fo 7104 vt.italic= [VT] Default color for italic text; 0-15.
7331 Default: 2 = green. 7105 Default: 2 = green.
7332 7106
7333 vt.underline= [VT] Default color fo 7107 vt.underline= [VT] Default color for underlined text; 0-15.
7334 Default: 3 = cyan. 7108 Default: 3 = cyan.
7335 7109
7336 watchdog timers [HW,WDT] For informat 7110 watchdog timers [HW,WDT] For information on watchdog timers,
7337 see Documentation/wat 7111 see Documentation/watchdog/watchdog-parameters.rst
7338 or other driver-speci 7112 or other driver-specific files in the
7339 Documentation/watchdo 7113 Documentation/watchdog/ directory.
7340 7114
7341 watchdog_thresh= 7115 watchdog_thresh=
7342 [KNL] 7116 [KNL]
7343 Set the hard lockup d 7117 Set the hard lockup detector stall duration
7344 threshold in seconds. 7118 threshold in seconds. The soft lockup detector
7345 threshold is set to t 7119 threshold is set to twice the value. A value of 0
7346 disables both lockup 7120 disables both lockup detectors. Default is 10
7347 seconds. 7121 seconds.
7348 7122
7349 workqueue.unbound_cpus= 7123 workqueue.unbound_cpus=
7350 [KNL,SMP] Specify to 7124 [KNL,SMP] Specify to constrain one or some CPUs
7351 to use in unbound wor 7125 to use in unbound workqueues.
7352 Format: <cpu-list> 7126 Format: <cpu-list>
7353 By default, all onlin 7127 By default, all online CPUs are available for
7354 unbound workqueues. 7128 unbound workqueues.
7355 7129
7356 workqueue.watchdog_thresh= 7130 workqueue.watchdog_thresh=
7357 If CONFIG_WQ_WATCHDOG 7131 If CONFIG_WQ_WATCHDOG is configured, workqueue can
7358 warn stall conditions 7132 warn stall conditions and dump internal state to
7359 help debugging. 0 di 7133 help debugging. 0 disables workqueue stall
7360 detection; otherwise, 7134 detection; otherwise, it's the stall threshold
7361 duration in seconds. 7135 duration in seconds. The default value is 30 and
7362 it can be updated at 7136 it can be updated at runtime by writing to the
7363 corresponding sysfs f 7137 corresponding sysfs file.
7364 7138
7365 workqueue.cpu_intensive_thresh_us= 7139 workqueue.cpu_intensive_thresh_us=
7366 Per-cpu work items wh 7140 Per-cpu work items which run for longer than this
7367 threshold are automat 7141 threshold are automatically considered CPU intensive
7368 and excluded from con 7142 and excluded from concurrency management to prevent
7369 them from noticeably 7143 them from noticeably delaying other per-cpu work
7370 items. Default is 100 7144 items. Default is 10000 (10ms).
7371 7145
7372 If CONFIG_WQ_CPU_INTE 7146 If CONFIG_WQ_CPU_INTENSIVE_REPORT is set, the kernel
7373 will report the work 7147 will report the work functions which violate this
7374 threshold repeatedly. 7148 threshold repeatedly. They are likely good
7375 candidates for using 7149 candidates for using WQ_UNBOUND workqueues instead.
7376 7150
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 <<
7386 workqueue.power_efficient 7151 workqueue.power_efficient
7387 Per-cpu workqueues ar 7152 Per-cpu workqueues are generally preferred because
7388 they show better perf 7153 they show better performance thanks to cache
7389 locality; unfortunate 7154 locality; unfortunately, per-cpu workqueues tend to
7390 be more power hungry 7155 be more power hungry than unbound workqueues.
7391 7156
7392 Enabling this makes t 7157 Enabling this makes the per-cpu workqueues which
7393 were observed to cont 7158 were observed to contribute significantly to power
7394 consumption unbound, 7159 consumption unbound, leading to measurably lower
7395 power usage at the co 7160 power usage at the cost of small performance
7396 overhead. 7161 overhead.
7397 7162
7398 The default value of 7163 The default value of this parameter is determined by
7399 the config option CON 7164 the config option CONFIG_WQ_POWER_EFFICIENT_DEFAULT.
7400 7165
7401 workqueue.default_affinity_scope= 7166 workqueue.default_affinity_scope=
7402 Select the default af 7167 Select the default affinity scope to use for unbound
7403 workqueues. Can be on 7168 workqueues. Can be one of "cpu", "smt", "cache",
7404 "numa" and "system". 7169 "numa" and "system". Default is "cache". For more
7405 information, see the 7170 information, see the Affinity Scopes section in
7406 Documentation/core-ap 7171 Documentation/core-api/workqueue.rst.
7407 7172
7408 This can be changed a 7173 This can be changed after boot by writing to the
7409 matching /sys/module/ 7174 matching /sys/module/workqueue/parameters file. All
7410 workqueues with the " 7175 workqueues with the "default" affinity scope will be
7411 updated accordingly. !! 7176 updated accordignly.
7412 7177
7413 workqueue.debug_force_rr_cpu 7178 workqueue.debug_force_rr_cpu
7414 Workqueue used to imp 7179 Workqueue used to implicitly guarantee that work
7415 items queued without 7180 items queued without explicit CPU specified are put
7416 on the local CPU. Th 7181 on the local CPU. This guarantee is no longer true
7417 and while local CPU i 7182 and while local CPU is still preferred work items
7418 may be put on foreign 7183 may be put on foreign CPUs. This debug option
7419 forces round-robin CP 7184 forces round-robin CPU selection to flush out
7420 usages which depend o 7185 usages which depend on the now broken guarantee.
7421 When enabled, memory 7186 When enabled, memory and cache locality will be
7422 impacted. 7187 impacted.
7423 7188
7424 writecombine= [LOONGARCH,EARLY] Con !! 7189 writecombine= [LOONGARCH] Control the MAT (Memory Access Type) of
7425 Type) of ioremap_wc() !! 7190 ioremap_wc().
7426 7191
7427 on - Enable writeco 7192 on - Enable writecombine, use WUC for ioremap_wc()
7428 off - Disable writec 7193 off - Disable writecombine, use SUC for ioremap_wc()
7429 7194
7430 x2apic_phys [X86-64,APIC,EARLY] U !! 7195 x2apic_phys [X86-64,APIC] Use x2apic physical mode instead of
7431 default x2apic cluste 7196 default x2apic cluster mode on platforms
7432 supporting x2apic. 7197 supporting x2apic.
7433 7198
7434 xen_512gb_limit [KNL,X86-64,X 7199 xen_512gb_limit [KNL,X86-64,XEN]
7435 Restricts the kernel 7200 Restricts the kernel running paravirtualized under Xen
7436 to use only up to 512 7201 to use only up to 512 GB of RAM. The reason to do so is
7437 crash analysis tools 7202 crash analysis tools and Xen tools for doing domain
7438 save/restore/migratio 7203 save/restore/migration must be enabled to handle larger
7439 domains. 7204 domains.
7440 7205
7441 xen_emul_unplug= [HW,X !! 7206 xen_emul_unplug= [HW,X86,XEN]
7442 Unplug Xen emulated d 7207 Unplug Xen emulated devices
7443 Format: [unplug0,][un 7208 Format: [unplug0,][unplug1]
7444 ide-disks -- unplug p 7209 ide-disks -- unplug primary master IDE devices
7445 aux-ide-disks -- unpl 7210 aux-ide-disks -- unplug non-primary-master IDE devices
7446 nics -- unplug networ 7211 nics -- unplug network devices
7447 all -- unplug all emu 7212 all -- unplug all emulated devices (NICs and IDE disks)
7448 unnecessary -- unplug 7213 unnecessary -- unplugging emulated devices is
7449 unnecessary e 7214 unnecessary even if the host did not respond to
7450 the unplug pr 7215 the unplug protocol
7451 never -- do not unplu 7216 never -- do not unplug even if version check succeeds
7452 7217
7453 xen_legacy_crash [X86,XEN,EARL !! 7218 xen_legacy_crash [X86,XEN]
7454 Crash from Xen panic 7219 Crash from Xen panic notifier, without executing late
7455 panic() code such as 7220 panic() code such as dumping handler.
7456 7221
7457 xen_mc_debug [X86,XEN,EARLY] !! 7222 xen_msr_safe= [X86,XEN]
7458 Enable multicall debu <<
7459 Enabling this feature <<
7460 bit, so it should onl <<
7461 debug data in case of <<
7462 <<
7463 xen_msr_safe= [X86,XEN,EARLY] <<
7464 Format: <bool> 7223 Format: <bool>
7465 Select whether to alw 7224 Select whether to always use non-faulting (safe) MSR
7466 access functions when 7225 access functions when running as Xen PV guest. The
7467 default value is cont 7226 default value is controlled by CONFIG_XEN_PV_MSR_SAFE.
7468 7227
>> 7228 xen_nopvspin [X86,XEN]
>> 7229 Disables the qspinlock slowpath using Xen PV optimizations.
>> 7230 This parameter is obsoleted by "nopvspin" parameter, which
>> 7231 has equivalent effect for XEN platform.
>> 7232
7469 xen_nopv [X86] 7233 xen_nopv [X86]
7470 Disables the PV optim 7234 Disables the PV optimizations forcing the HVM guest to
7471 run as generic HVM gu 7235 run as generic HVM guest with no PV drivers.
7472 This option is obsole 7236 This option is obsoleted by the "nopv" option, which
7473 has equivalent effect 7237 has equivalent effect for XEN platform.
7474 7238
7475 xen_no_vector_callback 7239 xen_no_vector_callback
7476 [KNL,X86,XEN,EARLY] D !! 7240 [KNL,X86,XEN] Disable the vector callback for Xen
7477 event channel interru 7241 event channel interrupts.
7478 7242
7479 xen_scrub_pages= [XEN] 7243 xen_scrub_pages= [XEN]
7480 Boolean option to con 7244 Boolean option to control scrubbing pages before giving them back
7481 to Xen, for use by ot 7245 to Xen, for use by other domains. Can be also changed at runtime
7482 with /sys/devices/sys 7246 with /sys/devices/system/xen_memory/xen_memory0/scrub_pages.
7483 Default value control 7247 Default value controlled with CONFIG_XEN_SCRUB_PAGES_DEFAULT.
7484 7248
7485 xen_timer_slop= [X86-64,XEN,EARLY] !! 7249 xen_timer_slop= [X86-64,XEN]
7486 Set the timer slop (i 7250 Set the timer slop (in nanoseconds) for the virtual Xen
7487 timers (default is 10 7251 timers (default is 100000). This adjusts the minimum
7488 delta of virtualized 7252 delta of virtualized Xen timers, where lower values
7489 improve timer resolut 7253 improve timer resolution at the expense of processing
7490 more timer interrupts 7254 more timer interrupts.
7491 7255
7492 xen.balloon_boot_timeout= [XEN] 7256 xen.balloon_boot_timeout= [XEN]
7493 The time (in seconds) 7257 The time (in seconds) to wait before giving up to boot
7494 in case initial ballo 7258 in case initial ballooning fails to free enough memory.
7495 Applies only when run 7259 Applies only when running as HVM or PVH guest and
7496 started with less mem 7260 started with less memory configured than allowed at
7497 max. Default is 180. 7261 max. Default is 180.
7498 7262
7499 xen.event_eoi_delay= [XEN] 7263 xen.event_eoi_delay= [XEN]
7500 How long to delay EOI 7264 How long to delay EOI handling in case of event
7501 storms (jiffies). Def 7265 storms (jiffies). Default is 10.
7502 7266
7503 xen.event_loop_timeout= [XEN] 7267 xen.event_loop_timeout= [XEN]
7504 After which time (jif 7268 After which time (jiffies) the event handling loop
7505 should start to delay 7269 should start to delay EOI handling. Default is 2.
7506 7270
7507 xen.fifo_events= [XEN] 7271 xen.fifo_events= [XEN]
7508 Boolean parameter to 7272 Boolean parameter to disable using fifo event handling
7509 even if available. No 7273 even if available. Normally fifo event handling is
7510 preferred over the 2- 7274 preferred over the 2-level event handling, as it is
7511 fairer and the number 7275 fairer and the number of possible event channels is
7512 much higher. Default 7276 much higher. Default is on (use fifo events).
7513 7277
7514 xirc2ps_cs= [NET,PCMCIA] 7278 xirc2ps_cs= [NET,PCMCIA]
7515 Format: 7279 Format:
7516 <irq>,<irq_mask>,<io> 7280 <irq>,<irq_mask>,<io>,<full_duplex>,<do_sound>,<lockup_hack>[,<irq2>[,<irq3>[,<irq4>]]]
7517 7281
7518 xive= [PPC] 7282 xive= [PPC]
7519 By default on POWER9 7283 By default on POWER9 and above, the kernel will
7520 natively use the XIVE 7284 natively use the XIVE interrupt controller. This option
7521 allows the fallback f 7285 allows the fallback firmware mode to be used:
7522 7286
7523 off Fallback to 7287 off Fallback to firmware control of XIVE interrupt
7524 controller 7288 controller on both pseries and powernv
7525 platforms. 7289 platforms. Only useful on POWER9 and above.
7526 7290
7527 xive.store-eoi=off [PPC] 7291 xive.store-eoi=off [PPC]
7528 By default on POWER10 7292 By default on POWER10 and above, the kernel will use
7529 stores for EOI handli 7293 stores for EOI handling when the XIVE interrupt mode
7530 is active. This optio 7294 is active. This option allows the XIVE driver to use
7531 loads instead, as on 7295 loads instead, as on POWER9.
7532 7296
7533 xhci-hcd.quirks [USB,KNL] 7297 xhci-hcd.quirks [USB,KNL]
7534 A hex value specifyin 7298 A hex value specifying bitmask with supplemental xhci
7535 host controller quirk 7299 host controller quirks. Meaning of each bit can be
7536 consulted in header d 7300 consulted in header drivers/usb/host/xhci.h.
7537 7301
7538 xmon [PPC,EARLY] !! 7302 xmon [PPC]
7539 Format: { early | on 7303 Format: { early | on | rw | ro | off }
7540 Controls if xmon debu 7304 Controls if xmon debugger is enabled. Default is off.
7541 Passing only "xmon" i 7305 Passing only "xmon" is equivalent to "xmon=early".
7542 early Call xmon as 7306 early Call xmon as early as possible on boot; xmon
7543 debugger is c 7307 debugger is called from setup_arch().
7544 on xmon debugger 7308 on xmon debugger hooks will be installed so xmon
7545 is only calle 7309 is only called on a kernel crash. Default mode,
7546 i.e. either " 7310 i.e. either "ro" or "rw" mode, is controlled
7547 with CONFIG_X 7311 with CONFIG_XMON_DEFAULT_RO_MODE.
7548 rw xmon debugger 7312 rw xmon debugger hooks will be installed so xmon
7549 is called onl 7313 is called only on a kernel crash, mode is write,
7550 meaning SPR r 7314 meaning SPR registers, memory and, other data
7551 can be writte 7315 can be written using xmon commands.
7552 ro same as "rw" 7316 ro same as "rw" option above but SPR registers,
7553 memory, and o 7317 memory, and other data can't be written using
7554 xmon commands 7318 xmon commands.
7555 off xmon is disab 7319 off xmon is disabled.
>> 7320
Linux® is a registered trademark of Linus Torvalds in the United States and other countries.
TOMOYO® is a registered trademark of NTT DATA CORPORATION.