1 accept_memory= [MM] 1 accept_memory= [MM] 2 Format: { eager | lazy 2 Format: { eager | lazy } 3 default: lazy 3 default: lazy 4 By default, unaccepted 4 By default, unaccepted memory is accepted lazily to 5 avoid prolonged boot t 5 avoid prolonged boot times. The lazy option will add 6 some runtime overhead 6 some runtime overhead until all memory is eventually 7 accepted. In most case 7 accepted. In most cases the overhead is negligible. 8 For some workloads or 8 For some workloads or for debugging purposes 9 accept_memory=eager ca 9 accept_memory=eager can be used to accept all memory 10 at once during boot. 10 at once during boot. 11 11 12 acpi= [HW,ACPI,X86,ARM64,RIS !! 12 acpi= [HW,ACPI,X86,ARM64,RISCV64] 13 Advanced Configuration 13 Advanced Configuration and Power Interface 14 Format: { force | on | 14 Format: { force | on | off | strict | noirq | rsdt | 15 copy_dsdt | !! 15 copy_dsdt } 16 force -- enable ACPI i 16 force -- enable ACPI if default was off 17 on -- enable ACPI but 17 on -- enable ACPI but allow fallback to DT [arm64,riscv64] 18 off -- disable ACPI if 18 off -- disable ACPI if default was on 19 noirq -- do not use AC 19 noirq -- do not use ACPI for IRQ routing 20 strict -- Be less tole 20 strict -- Be less tolerant of platforms that are not 21 strictly ACPI 21 strictly ACPI specification compliant. 22 rsdt -- prefer RSDT ov 22 rsdt -- prefer RSDT over (default) XSDT 23 copy_dsdt -- copy DSDT 23 copy_dsdt -- copy DSDT to memory 24 nospcr -- disable cons !! 24 For ARM64 and RISCV64, ONLY "acpi=off", "acpi=on" or 25 default _seria !! 25 "acpi=force" are available 26 For ARM64, ONLY "acpi= << 27 "acpi=nospcr" are avai << 28 For RISCV64, ONLY "acp << 29 are available << 30 26 31 See also Documentation 27 See also Documentation/power/runtime_pm.rst, pci=noacpi 32 28 33 acpi_apic_instance= [ACPI,IOAPIC,E !! 29 acpi_apic_instance= [ACPI, IOAPIC] 34 Format: <int> 30 Format: <int> 35 2: use 2nd APIC table, 31 2: use 2nd APIC table, if available 36 1,0: use 1st APIC tabl 32 1,0: use 1st APIC table 37 default: 0 33 default: 0 38 34 39 acpi_backlight= [HW,ACPI] 35 acpi_backlight= [HW,ACPI] 40 { vendor | video | nat 36 { vendor | video | native | none } 41 If set to vendor, pref 37 If set to vendor, prefer vendor-specific driver 42 (e.g. thinkpad_acpi, s 38 (e.g. thinkpad_acpi, sony_acpi, etc.) instead 43 of the ACPI video.ko d 39 of the ACPI video.ko driver. 44 If set to video, use t 40 If set to video, use the ACPI video.ko driver. 45 If set to native, use 41 If set to native, use the device's native backlight mode. 46 If set to none, disabl 42 If set to none, disable the ACPI backlight interface. 47 43 48 acpi_force_32bit_fadt_addr [ACPI,EARLY !! 44 acpi_force_32bit_fadt_addr 49 force FADT to use 32 b 45 force FADT to use 32 bit addresses rather than the 50 64 bit X_* addresses. 46 64 bit X_* addresses. Some firmware have broken 64 51 bit addresses for forc 47 bit addresses for force ACPI ignore these and use 52 the older legacy 32 bi 48 the older legacy 32 bit addresses. 53 49 54 acpica_no_return_repair [HW, ACPI] 50 acpica_no_return_repair [HW, ACPI] 55 Disable AML predefined 51 Disable AML predefined validation mechanism 56 This mechanism can rep 52 This mechanism can repair the evaluation result to make 57 the return objects mor 53 the return objects more ACPI specification compliant. 58 This option is useful 54 This option is useful for developers to identify the 59 root cause of an AML i 55 root cause of an AML interpreter issue when the issue 60 has something to do wi 56 has something to do with the repair mechanism. 61 57 62 acpi.debug_layer= [HW,ACPI,ACPI_ 58 acpi.debug_layer= [HW,ACPI,ACPI_DEBUG] 63 acpi.debug_level= [HW,ACPI,ACPI_ 59 acpi.debug_level= [HW,ACPI,ACPI_DEBUG] 64 Format: <int> 60 Format: <int> 65 CONFIG_ACPI_DEBUG must 61 CONFIG_ACPI_DEBUG must be enabled to produce any ACPI 66 debug output. Bits in 62 debug output. Bits in debug_layer correspond to a 67 _COMPONENT in an ACPI 63 _COMPONENT in an ACPI source file, e.g., 68 #define _COMPONENT 64 #define _COMPONENT ACPI_EVENTS 69 Bits in debug_level co 65 Bits in debug_level correspond to a level in 70 ACPI_DEBUG_PRINT state 66 ACPI_DEBUG_PRINT statements, e.g., 71 ACPI_DEBUG_PRINT(( 67 ACPI_DEBUG_PRINT((ACPI_DB_INFO, ... 72 The debug_level mask d 68 The debug_level mask defaults to "info". See 73 Documentation/firmware 69 Documentation/firmware-guide/acpi/debug.rst for more information about 74 debug layers and level 70 debug layers and levels. 75 71 76 Enable processor drive 72 Enable processor driver info messages: 77 acpi.debug_layer=0 73 acpi.debug_layer=0x20000000 78 Enable AML "Debug" out 74 Enable AML "Debug" output, i.e., stores to the Debug 79 object while interpret 75 object while interpreting AML: 80 acpi.debug_layer=0 76 acpi.debug_layer=0xffffffff acpi.debug_level=0x2 81 Enable all messages re 77 Enable all messages related to ACPI hardware: 82 acpi.debug_layer=0 78 acpi.debug_layer=0x2 acpi.debug_level=0xffffffff 83 79 84 Some values produce so 80 Some values produce so much output that the system is 85 unusable. The "log_bu 81 unusable. The "log_buf_len" parameter may be useful 86 if you need to capture 82 if you need to capture more output. 87 83 88 acpi_enforce_resources= [ACPI] 84 acpi_enforce_resources= [ACPI] 89 { strict | lax | no } 85 { strict | lax | no } 90 Check for resource con 86 Check for resource conflicts between native drivers 91 and ACPI OperationRegi 87 and ACPI OperationRegions (SystemIO and SystemMemory 92 only). IO ports and me 88 only). IO ports and memory declared in ACPI might be 93 used by the ACPI subsy 89 used by the ACPI subsystem in arbitrary AML code and 94 can interfere with leg 90 can interfere with legacy drivers. 95 strict (default): acce 91 strict (default): access to resources claimed by ACPI 96 is denied; legacy driv 92 is denied; legacy drivers trying to access reserved 97 resources will fail to 93 resources will fail to bind to device using them. 98 lax: access to resourc 94 lax: access to resources claimed by ACPI is allowed; 99 legacy drivers trying 95 legacy drivers trying to access reserved resources 100 will bind successfully 96 will bind successfully but a warning message is logged. 101 no: ACPI OperationRegi 97 no: ACPI OperationRegions are not marked as reserved, 102 no further checks are 98 no further checks are performed. 103 99 104 acpi_force_table_verification [HW,AC !! 100 acpi_force_table_verification [HW,ACPI] 105 Enable table checksum 101 Enable table checksum verification during early stage. 106 By default, this is di 102 By default, this is disabled due to x86 early mapping 107 size limitation. 103 size limitation. 108 104 109 acpi_irq_balance [HW,ACPI] 105 acpi_irq_balance [HW,ACPI] 110 ACPI will balance acti 106 ACPI will balance active IRQs 111 default in APIC mode 107 default in APIC mode 112 108 113 acpi_irq_nobalance [HW,ACPI] 109 acpi_irq_nobalance [HW,ACPI] 114 ACPI will not move act 110 ACPI will not move active IRQs (default) 115 default in PIC mode 111 default in PIC mode 116 112 117 acpi_irq_isa= [HW,ACPI] If irq_balan 113 acpi_irq_isa= [HW,ACPI] If irq_balance, mark listed IRQs used by ISA 118 Format: <irq>,<irq>... 114 Format: <irq>,<irq>... 119 115 120 acpi_irq_pci= [HW,ACPI] If irq_balan 116 acpi_irq_pci= [HW,ACPI] If irq_balance, clear listed IRQs for 121 use by PCI 117 use by PCI 122 Format: <irq>,<irq>... 118 Format: <irq>,<irq>... 123 119 124 acpi_mask_gpe= [HW,ACPI] 120 acpi_mask_gpe= [HW,ACPI] 125 Due to the existence o 121 Due to the existence of _Lxx/_Exx, some GPEs triggered 126 by unsupported hardwar 122 by unsupported hardware/firmware features can result in 127 GPE floodings that can 123 GPE floodings that cannot be automatically disabled by 128 the GPE dispatcher. 124 the GPE dispatcher. 129 This facility can be u 125 This facility can be used to prevent such uncontrolled 130 GPE floodings. 126 GPE floodings. 131 Format: <byte> or <bit 127 Format: <byte> or <bitmap-list> 132 128 133 acpi_no_auto_serialize [HW,ACPI] 129 acpi_no_auto_serialize [HW,ACPI] 134 Disable auto-serializa 130 Disable auto-serialization of AML methods 135 AML control methods th 131 AML control methods that contain the opcodes to create 136 named objects will be 132 named objects will be marked as "Serialized" by the 137 auto-serialization fea 133 auto-serialization feature. 138 This feature is enable 134 This feature is enabled by default. 139 This option allows to 135 This option allows to turn off the feature. 140 136 141 acpi_no_memhotplug [ACPI] Disable memo 137 acpi_no_memhotplug [ACPI] Disable memory hotplug. Useful for kdump 142 kernels. 138 kernels. 143 139 144 acpi_no_static_ssdt [HW,ACPI,EARLY !! 140 acpi_no_static_ssdt [HW,ACPI] 145 Disable installation o 141 Disable installation of static SSDTs at early boot time 146 By default, SSDTs cont 142 By default, SSDTs contained in the RSDT/XSDT will be 147 installed automaticall 143 installed automatically and they will appear under 148 /sys/firmware/acpi/tab 144 /sys/firmware/acpi/tables. 149 This option turns off 145 This option turns off this feature. 150 Note that specifying t 146 Note that specifying this option does not affect 151 dynamic table installa 147 dynamic table installation which will install SSDT 152 tables to /sys/firmwar 148 tables to /sys/firmware/acpi/tables/dynamic. 153 149 154 acpi_no_watchdog [HW,ACPI,WDT] 150 acpi_no_watchdog [HW,ACPI,WDT] 155 Ignore the ACPI-based 151 Ignore the ACPI-based watchdog interface (WDAT) and let 156 a native driver contro 152 a native driver control the watchdog device instead. 157 153 158 acpi_rsdp= [ACPI,EFI,KEXEC,EARLY] !! 154 acpi_rsdp= [ACPI,EFI,KEXEC] 159 Pass the RSDP address 155 Pass the RSDP address to the kernel, mostly used 160 on machines running EF 156 on machines running EFI runtime service to boot the 161 second kernel for kdum 157 second kernel for kdump. 162 158 163 acpi_os_name= [HW,ACPI] Tell ACPI BI 159 acpi_os_name= [HW,ACPI] Tell ACPI BIOS the name of the OS 164 Format: To spoof as Wi 160 Format: To spoof as Windows 98: ="Microsoft Windows" 165 161 166 acpi_rev_override [ACPI] Override the 162 acpi_rev_override [ACPI] Override the _REV object to return 5 (instead 167 of 2 which is mandated 163 of 2 which is mandated by ACPI 6) as the supported ACPI 168 specification revision 164 specification revision (when using this switch, it may 169 be necessary to carry 165 be necessary to carry out a cold reboot _twice_ in a 170 row to make it take ef 166 row to make it take effect on the platform firmware). 171 167 172 acpi_osi= [HW,ACPI] Modify list 168 acpi_osi= [HW,ACPI] Modify list of supported OS interface strings 173 acpi_osi="string1" 169 acpi_osi="string1" # add string1 174 acpi_osi="!string2" 170 acpi_osi="!string2" # remove string2 175 acpi_osi=!* 171 acpi_osi=!* # remove all strings 176 acpi_osi=! 172 acpi_osi=! # disable all built-in OS vendor 177 173 strings 178 acpi_osi=!! 174 acpi_osi=!! # enable all built-in OS vendor 179 175 strings 180 acpi_osi= 176 acpi_osi= # disable all strings 181 177 182 'acpi_osi=!' can be us 178 'acpi_osi=!' can be used in combination with single or 183 multiple 'acpi_osi="st 179 multiple 'acpi_osi="string1"' to support specific OS 184 vendor string(s). Not 180 vendor string(s). Note that such command can only 185 affect the default sta 181 affect the default state of the OS vendor strings, thus 186 it cannot affect the d 182 it cannot affect the default state of the feature group 187 strings and the curren 183 strings and the current state of the OS vendor strings, 188 specifying it multiple 184 specifying it multiple times through kernel command line 189 is meaningless. This 185 is meaningless. This command is useful when one do not 190 care about the state o 186 care about the state of the feature group strings which 191 should be controlled b 187 should be controlled by the OSPM. 192 Examples: 188 Examples: 193 1. 'acpi_osi=! acpi_ 189 1. 'acpi_osi=! acpi_osi="Windows 2000"' is equivalent 194 to 'acpi_osi="Win 190 to 'acpi_osi="Windows 2000" acpi_osi=!', they all 195 can make '_OSI("W 191 can make '_OSI("Windows 2000")' TRUE. 196 192 197 'acpi_osi=' cannot be 193 'acpi_osi=' cannot be used in combination with other 198 'acpi_osi=' command li 194 'acpi_osi=' command lines, the _OSI method will not 199 exist in the ACPI name 195 exist in the ACPI namespace. NOTE that such command can 200 only affect the _OSI s 196 only affect the _OSI support state, thus specifying it 201 multiple times through 197 multiple times through kernel command line is also 202 meaningless. 198 meaningless. 203 Examples: 199 Examples: 204 1. 'acpi_osi=' can m 200 1. 'acpi_osi=' can make 'CondRefOf(_OSI, Local1)' 205 FALSE. 201 FALSE. 206 202 207 'acpi_osi=!*' can be u 203 'acpi_osi=!*' can be used in combination with single or 208 multiple 'acpi_osi="st 204 multiple 'acpi_osi="string1"' to support specific 209 string(s). Note that 205 string(s). Note that such command can affect the 210 current state of both 206 current state of both the OS vendor strings and the 211 feature group strings, 207 feature group strings, thus specifying it multiple times 212 through kernel command 208 through kernel command line is meaningful. But it may 213 still not able to affe 209 still not able to affect the final state of a string if 214 there are quirks relat 210 there are quirks related to this string. This command 215 is useful when one wan 211 is useful when one want to control the state of the 216 feature group strings 212 feature group strings to debug BIOS issues related to 217 the OSPM features. 213 the OSPM features. 218 Examples: 214 Examples: 219 1. 'acpi_osi="Module 215 1. 'acpi_osi="Module Device" acpi_osi=!*' can make 220 '_OSI("Module Dev 216 '_OSI("Module Device")' FALSE. 221 2. 'acpi_osi=!* acpi 217 2. 'acpi_osi=!* acpi_osi="Module Device"' can make 222 '_OSI("Module Dev 218 '_OSI("Module Device")' TRUE. 223 3. 'acpi_osi=! acpi_ 219 3. 'acpi_osi=! acpi_osi=!* acpi_osi="Windows 2000"' is 224 equivalent to 220 equivalent to 225 'acpi_osi=!* acpi 221 'acpi_osi=!* acpi_osi=! acpi_osi="Windows 2000"' 226 and 222 and 227 'acpi_osi=!* acpi 223 'acpi_osi=!* acpi_osi="Windows 2000" acpi_osi=!', 228 they all will mak 224 they all will make '_OSI("Windows 2000")' TRUE. 229 225 230 acpi_pm_good [X86] 226 acpi_pm_good [X86] 231 Override the pmtimer b 227 Override the pmtimer bug detection: force the kernel 232 to assume that this ma 228 to assume that this machine's pmtimer latches its value 233 and always returns goo 229 and always returns good values. 234 230 235 acpi_sci= [HW,ACPI,EARLY] ACPI S !! 231 acpi_sci= [HW,ACPI] ACPI System Control Interrupt trigger mode 236 Format: { level | edge 232 Format: { level | edge | high | low } 237 233 238 acpi_skip_timer_override [HW,ACPI,EARL !! 234 acpi_skip_timer_override [HW,ACPI] 239 Recognize and ignore I 235 Recognize and ignore IRQ0/pin2 Interrupt Override. 240 For broken nForce2 BIO 236 For broken nForce2 BIOS resulting in XT-PIC timer. 241 237 242 acpi_sleep= [HW,ACPI] Sleep option 238 acpi_sleep= [HW,ACPI] Sleep options 243 Format: { s3_bios, s3_ 239 Format: { s3_bios, s3_mode, s3_beep, s4_hwsig, 244 s4_nohwsig, 240 s4_nohwsig, old_ordering, nonvs, 245 sci_force_en 241 sci_force_enable, nobl } 246 See Documentation/powe 242 See Documentation/power/video.rst for information on 247 s3_bios and s3_mode. 243 s3_bios and s3_mode. 248 s3_beep is for debuggi 244 s3_beep is for debugging; it makes the PC's speaker beep 249 as soon as the kernel' 245 as soon as the kernel's real-mode entry point is called. 250 s4_hwsig causes the ke 246 s4_hwsig causes the kernel to check the ACPI hardware 251 signature during resum 247 signature during resume from hibernation, and gracefully 252 refuse to resume if it 248 refuse to resume if it has changed. This complies with 253 the ACPI specification 249 the ACPI specification but not with reality, since 254 Windows does not do th 250 Windows does not do this and many laptops do change it 255 on docking. So the def 251 on docking. So the default behaviour is to allow resume 256 and simply warn when t 252 and simply warn when the signature changes, unless the 257 s4_hwsig option is ena 253 s4_hwsig option is enabled. 258 s4_nohwsig prevents AC 254 s4_nohwsig prevents ACPI hardware signature from being 259 used (or even warned a 255 used (or even warned about) during resume. 260 old_ordering causes th 256 old_ordering causes the ACPI 1.0 ordering of the _PTS 261 control method, with r 257 control method, with respect to putting devices into 262 low power states, to b 258 low power states, to be enforced (the ACPI 2.0 ordering 263 of _PTS is used by def 259 of _PTS is used by default). 264 nonvs prevents the ker 260 nonvs prevents the kernel from saving/restoring the 265 ACPI NVS memory during 261 ACPI NVS memory during suspend/hibernation and resume. 266 sci_force_enable cause 262 sci_force_enable causes the kernel to set SCI_EN directly 267 on resume from S1/S3 ( 263 on resume from S1/S3 (which is against the ACPI spec, 268 but some broken system 264 but some broken systems don't work without it). 269 nobl causes the intern 265 nobl causes the internal blacklist of systems known to 270 behave incorrectly in 266 behave incorrectly in some ways with respect to system 271 suspend and resume to 267 suspend and resume to be ignored (use wisely). 272 268 273 acpi_use_timer_override [HW,ACPI,EARLY !! 269 acpi_use_timer_override [HW,ACPI] 274 Use timer override. Fo 270 Use timer override. For some broken Nvidia NF5 boards 275 that require a timer o 271 that require a timer override, but don't have HPET 276 272 277 add_efi_memmap [EFI,X86,EARLY] Includ !! 273 add_efi_memmap [EFI; X86] Include EFI memory map in 278 kernel's map of availa 274 kernel's map of available physical RAM. 279 275 280 agp= [AGP] 276 agp= [AGP] 281 { off | try_unsupporte 277 { off | try_unsupported } 282 off: disable AGP suppo 278 off: disable AGP support 283 try_unsupported: try t 279 try_unsupported: try to drive unsupported chipsets 284 (may crash com 280 (may crash computer or cause data corruption) 285 281 286 ALSA [HW,ALSA] 282 ALSA [HW,ALSA] 287 See Documentation/soun 283 See Documentation/sound/alsa-configuration.rst 288 284 289 alignment= [KNL,ARM] 285 alignment= [KNL,ARM] 290 Allow the default user 286 Allow the default userspace alignment fault handler 291 behaviour to be specif 287 behaviour to be specified. Bit 0 enables warnings, 292 bit 1 enables fixups, 288 bit 1 enables fixups, and bit 2 sends a segfault. 293 289 294 align_va_addr= [X86-64] 290 align_va_addr= [X86-64] 295 Align virtual addresse 291 Align virtual addresses by clearing slice [14:12] when 296 allocating a VMA at pr 292 allocating a VMA at process creation time. This option 297 gives you up to 3% per 293 gives you up to 3% performance improvement on AMD F15h 298 machines (where it is 294 machines (where it is enabled by default) for a 299 CPU-intensive style be 295 CPU-intensive style benchmark, and it can vary highly in 300 a microbenchmark depen 296 a microbenchmark depending on workload and compiler. 301 297 302 32: only for 32-bit pr 298 32: only for 32-bit processes 303 64: only for 64-bit pr 299 64: only for 64-bit processes 304 on: enable for both 32 300 on: enable for both 32- and 64-bit processes 305 off: disable for both 301 off: disable for both 32- and 64-bit processes 306 302 307 alloc_snapshot [FTRACE] 303 alloc_snapshot [FTRACE] 308 Allocate the ftrace sn 304 Allocate the ftrace snapshot buffer on boot up when the 309 main buffer is allocat 305 main buffer is allocated. This is handy if debugging 310 and you need to use tr 306 and you need to use tracing_snapshot() on boot up, and 311 do not want to use tra 307 do not want to use tracing_snapshot_alloc() as it needs 312 to be done where GFP_K 308 to be done where GFP_KERNEL allocations are allowed. 313 309 314 allow_mismatched_32bit_el0 [ARM64,EARL !! 310 allow_mismatched_32bit_el0 [ARM64] 315 Allow execve() of 32-b 311 Allow execve() of 32-bit applications and setting of the 316 PER_LINUX32 personalit 312 PER_LINUX32 personality on systems where only a strict 317 subset of the CPUs sup 313 subset of the CPUs support 32-bit EL0. When this 318 parameter is present, 314 parameter is present, the set of CPUs supporting 32-bit 319 EL0 is indicated by /s 315 EL0 is indicated by /sys/devices/system/cpu/aarch32_el0 320 and hot-unplug operati 316 and hot-unplug operations may be restricted. 321 317 322 See Documentation/arch 318 See Documentation/arch/arm64/asymmetric-32bit.rst for more 323 information. 319 information. 324 320 325 amd_iommu= [HW,X86-64] 321 amd_iommu= [HW,X86-64] 326 Pass parameters to the 322 Pass parameters to the AMD IOMMU driver in the system. 327 Possible values are: 323 Possible values are: 328 fullflush - Deprecated 324 fullflush - Deprecated, equivalent to iommu.strict=1 329 off - do not ini 325 off - do not initialize any AMD IOMMU found in 330 the system 326 the system 331 force_isolation - Forc 327 force_isolation - Force device isolation for all 332 devi 328 devices. The IOMMU driver is not 333 allo 329 allowed anymore to lift isolation 334 requ 330 requirements as needed. This option 335 does 331 does not override iommu=pt 336 force_enable - Force e 332 force_enable - Force enable the IOMMU on platforms known 337 to be b 333 to be buggy with IOMMU enabled. Use this 338 option 334 option with care. 339 pgtbl_v1 - Use v1 335 pgtbl_v1 - Use v1 page table for DMA-API (Default). 340 pgtbl_v2 - Use v2 336 pgtbl_v2 - Use v2 page table for DMA-API. 341 irtcachedis - Disable 337 irtcachedis - Disable Interrupt Remapping Table (IRT) caching. 342 338 343 amd_iommu_dump= [HW,X86-64] 339 amd_iommu_dump= [HW,X86-64] 344 Enable AMD IOMMU drive 340 Enable AMD IOMMU driver option to dump the ACPI table 345 for AMD IOMMU. With th 341 for AMD IOMMU. With this option enabled, AMD IOMMU 346 driver will print ACPI 342 driver will print ACPI tables for AMD IOMMU during 347 IOMMU initialization. 343 IOMMU initialization. 348 344 349 amd_iommu_intr= [HW,X86-64] 345 amd_iommu_intr= [HW,X86-64] 350 Specifies one of the f 346 Specifies one of the following AMD IOMMU interrupt 351 remapping modes: 347 remapping modes: 352 legacy - Use legac 348 legacy - Use legacy interrupt remapping mode. 353 vapic - Use virtu 349 vapic - Use virtual APIC mode, which allows IOMMU 354 to inject 350 to inject interrupts directly into guest. 355 This mode 351 This mode requires kvm-amd.avic=1. 356 (Default 352 (Default when IOMMU HW support is present.) 357 353 358 amd_pstate= [X86,EARLY] !! 354 amd_pstate= [X86] 359 disable 355 disable 360 Do not enable amd_ps 356 Do not enable amd_pstate as the default 361 scaling driver for t 357 scaling driver for the supported processors 362 passive 358 passive 363 Use amd_pstate with 359 Use amd_pstate with passive mode as a scaling driver. 364 In this mode autonom 360 In this mode autonomous selection is disabled. 365 Driver requests a de 361 Driver requests a desired performance level and platform 366 tries to match the s 362 tries to match the same performance level if it is 367 satisfied by guarant 363 satisfied by guaranteed performance level. 368 active 364 active 369 Use amd_pstate_epp d 365 Use amd_pstate_epp driver instance as the scaling driver, 370 driver provides a hi 366 driver provides a hint to the hardware if software wants 371 to bias toward perfo 367 to bias toward performance (0x0) or energy efficiency (0xff) 372 to the CPPC firmware 368 to the CPPC firmware. then CPPC power algorithm will 373 calculate the runtim 369 calculate the runtime workload and adjust the realtime cores 374 frequency. 370 frequency. 375 guided 371 guided 376 Activate guided auto 372 Activate guided autonomous mode. Driver requests minimum and 377 maximum performance 373 maximum performance level and the platform autonomously 378 selects a performanc 374 selects a performance level in this range and appropriate 379 to the current workl 375 to the current workload. 380 376 381 amd_prefcore= << 382 [X86] << 383 disable << 384 Disable amd-pstate p << 385 << 386 amijoy.map= [HW,JOY] Amiga joystic 377 amijoy.map= [HW,JOY] Amiga joystick support 387 Map of devices attache 378 Map of devices attached to JOY0DAT and JOY1DAT 388 Format: <a>,<b> 379 Format: <a>,<b> 389 See also Documentation 380 See also Documentation/input/joydev/joystick.rst 390 381 391 analog.map= [HW,JOY] Analog joysti 382 analog.map= [HW,JOY] Analog joystick and gamepad support 392 Specifies type or capa 383 Specifies type or capabilities of an analog joystick 393 connected to one of 16 384 connected to one of 16 gameports 394 Format: <type1>,<type2 385 Format: <type1>,<type2>,..<type16> 395 386 396 apc= [HW,SPARC] 387 apc= [HW,SPARC] 397 Power management funct 388 Power management functions (SPARCstation-4/5 + deriv.) 398 Format: noidle 389 Format: noidle 399 Disable APC CPU standb 390 Disable APC CPU standby support. SPARCstation-Fox does 400 not play well with APC 391 not play well with APC CPU idle - disable it if you have 401 APC and your system cr 392 APC and your system crashes randomly. 402 393 403 apic= [APIC,X86,EARLY] Advan !! 394 apic= [APIC,X86] Advanced Programmable Interrupt Controller 404 Change the output verb 395 Change the output verbosity while booting 405 Format: { quiet (defau 396 Format: { quiet (default) | verbose | debug } 406 Change the amount of d 397 Change the amount of debugging information output 407 when initialising the 398 when initialising the APIC and IO-APIC components. 408 For X86-32, this can a 399 For X86-32, this can also be used to specify an APIC 409 driver name. 400 driver name. 410 Format: apic=driver_na 401 Format: apic=driver_name 411 Examples: apic=bigsmp 402 Examples: apic=bigsmp 412 403 413 apic_extnmi= [APIC,X86,EARLY] Exter !! 404 apic_extnmi= [APIC,X86] External NMI delivery setting 414 Format: { bsp (default 405 Format: { bsp (default) | all | none } 415 bsp: External NMI is 406 bsp: External NMI is delivered only to CPU 0 416 all: External NMIs ar 407 all: External NMIs are broadcast to all CPUs as a 417 backup of CPU 0 408 backup of CPU 0 418 none: External NMI is 409 none: External NMI is masked for all CPUs. This is 419 useful so that a 410 useful so that a dump capture kernel won't be 420 shot down by NMI 411 shot down by NMI 421 412 422 autoconf= [IPV6] 413 autoconf= [IPV6] 423 See Documentation/netw 414 See Documentation/networking/ipv6.rst. 424 415 425 apm= [APM] Advanced Power M 416 apm= [APM] Advanced Power Management 426 See header of arch/x86 417 See header of arch/x86/kernel/apm_32.c. 427 418 428 apparmor= [APPARMOR] Disable or 419 apparmor= [APPARMOR] Disable or enable AppArmor at boot time 429 Format: { "0" | "1" } 420 Format: { "0" | "1" } 430 See security/apparmor/ 421 See security/apparmor/Kconfig help text 431 0 -- disable. 422 0 -- disable. 432 1 -- enable. 423 1 -- enable. 433 Default value is set v 424 Default value is set via kernel config option. 434 425 435 arcrimi= [HW,NET] ARCnet - "RIM 426 arcrimi= [HW,NET] ARCnet - "RIM I" (entirely mem-mapped) cards 436 Format: <io>,<irq>,<no 427 Format: <io>,<irq>,<nodeID> 437 428 438 arm64.no32bit_el0 [ARM64] Unconditiona << 439 32 bit applications. << 440 << 441 arm64.nobti [ARM64] Unconditionall 429 arm64.nobti [ARM64] Unconditionally disable Branch Target 442 Identification support 430 Identification support 443 431 444 arm64.nomops [ARM64] Unconditionall 432 arm64.nomops [ARM64] Unconditionally disable Memory Copy and Memory 445 Set instructions suppo 433 Set instructions support 446 434 447 arm64.nomte [ARM64] Unconditionall 435 arm64.nomte [ARM64] Unconditionally disable Memory Tagging Extension 448 support 436 support 449 437 450 arm64.nopauth [ARM64] Unconditionall 438 arm64.nopauth [ARM64] Unconditionally disable Pointer Authentication 451 support 439 support 452 440 453 arm64.nosme [ARM64] Unconditionall 441 arm64.nosme [ARM64] Unconditionally disable Scalable Matrix 454 Extension support 442 Extension support 455 443 456 arm64.nosve [ARM64] Unconditionall 444 arm64.nosve [ARM64] Unconditionally disable Scalable Vector 457 Extension support 445 Extension support 458 446 459 ataflop= [HW,M68k] 447 ataflop= [HW,M68k] 460 448 461 atarimouse= [HW,MOUSE] Atari Mouse 449 atarimouse= [HW,MOUSE] Atari Mouse 462 450 463 atkbd.extra= [HW] Enable extra LEDs 451 atkbd.extra= [HW] Enable extra LEDs and keys on IBM RapidAccess, 464 EzKey and similar keyb 452 EzKey and similar keyboards 465 453 466 atkbd.reset= [HW] Reset keyboard du 454 atkbd.reset= [HW] Reset keyboard during initialization 467 455 468 atkbd.set= [HW] Select keyboard c 456 atkbd.set= [HW] Select keyboard code set 469 Format: <int> (2 = AT 457 Format: <int> (2 = AT (default), 3 = PS/2) 470 458 471 atkbd.scroll= [HW] Enable scroll whe 459 atkbd.scroll= [HW] Enable scroll wheel on MS Office and similar 472 keyboards 460 keyboards 473 461 474 atkbd.softraw= [HW] Choose between sy 462 atkbd.softraw= [HW] Choose between synthetic and real raw mode 475 Format: <bool> (0 = re 463 Format: <bool> (0 = real, 1 = synthetic (default)) 476 464 477 atkbd.softrepeat= [HW] 465 atkbd.softrepeat= [HW] 478 Use software keyboard 466 Use software keyboard repeat 479 467 480 audit= [KNL] Enable the audit 468 audit= [KNL] Enable the audit sub-system 481 Format: { "0" | "1" | 469 Format: { "0" | "1" | "off" | "on" } 482 0 | off - kernel audit 470 0 | off - kernel audit is disabled and can not be 483 enabled until the 471 enabled until the next reboot 484 unset - kernel audit i 472 unset - kernel audit is initialized but disabled and 485 will be fully enab 473 will be fully enabled by the userspace auditd. 486 1 | on - kernel audit 474 1 | on - kernel audit is initialized and partially 487 enabled, storing a 475 enabled, storing at most audit_backlog_limit 488 messages in RAM un 476 messages in RAM until it is fully enabled by the 489 userspace auditd. 477 userspace auditd. 490 Default: unset 478 Default: unset 491 479 492 audit_backlog_limit= [KNL] Set the aud 480 audit_backlog_limit= [KNL] Set the audit queue size limit. 493 Format: <int> (must be 481 Format: <int> (must be >=0) 494 Default: 64 482 Default: 64 495 483 496 bau= [X86_UV] Enable the BA 484 bau= [X86_UV] Enable the BAU on SGI UV. The default 497 behavior is to disable 485 behavior is to disable the BAU (i.e. bau=0). 498 Format: { "0" | "1" } 486 Format: { "0" | "1" } 499 0 - Disable the BAU. 487 0 - Disable the BAU. 500 1 - Enable the BAU. 488 1 - Enable the BAU. 501 unset - Disable the BA 489 unset - Disable the BAU. 502 490 503 baycom_epp= [HW,AX25] 491 baycom_epp= [HW,AX25] 504 Format: <io>,<mode> 492 Format: <io>,<mode> 505 493 506 baycom_par= [HW,AX25] BayCom Paral 494 baycom_par= [HW,AX25] BayCom Parallel Port AX.25 Modem 507 Format: <io>,<mode> 495 Format: <io>,<mode> 508 See header of drivers/ 496 See header of drivers/net/hamradio/baycom_par.c. 509 497 510 baycom_ser_fdx= [HW,AX25] 498 baycom_ser_fdx= [HW,AX25] 511 BayCom Serial Port AX. 499 BayCom Serial Port AX.25 Modem (Full Duplex Mode) 512 Format: <io>,<irq>,<mo 500 Format: <io>,<irq>,<mode>[,<baud>] 513 See header of drivers/ 501 See header of drivers/net/hamradio/baycom_ser_fdx.c. 514 502 515 baycom_ser_hdx= [HW,AX25] 503 baycom_ser_hdx= [HW,AX25] 516 BayCom Serial Port AX. 504 BayCom Serial Port AX.25 Modem (Half Duplex Mode) 517 Format: <io>,<irq>,<mo 505 Format: <io>,<irq>,<mode> 518 See header of drivers/ 506 See header of drivers/net/hamradio/baycom_ser_hdx.c. 519 507 520 bert_disable [ACPI] 508 bert_disable [ACPI] 521 Disable BERT OS suppor 509 Disable BERT OS support on buggy BIOSes. 522 510 523 bgrt_disable [ACPI,X86,EARLY] !! 511 bgrt_disable [ACPI][X86] 524 Disable BGRT to avoid 512 Disable BGRT to avoid flickering OEM logo. 525 513 526 blkdevparts= Manual partition parsi 514 blkdevparts= Manual partition parsing of block device(s) for 527 embedded devices based 515 embedded devices based on command line input. 528 See Documentation/bloc 516 See Documentation/block/cmdline-partition.rst 529 517 530 boot_delay= [KNL,EARLY] !! 518 boot_delay= Milliseconds to delay each printk during boot. 531 Milliseconds to delay << 532 Only works if CONFIG_B 519 Only works if CONFIG_BOOT_PRINTK_DELAY is enabled, 533 and you may also have 520 and you may also have to specify "lpj=". Boot_delay 534 values larger than 10 521 values larger than 10 seconds (10000) are assumed 535 erroneous and ignored. 522 erroneous and ignored. 536 Format: integer 523 Format: integer 537 524 538 bootconfig [KNL,EARLY] !! 525 bootconfig [KNL] 539 Extended command line 526 Extended command line options can be added to an initrd 540 and this will cause th 527 and this will cause the kernel to look for it. 541 528 542 See Documentation/admi 529 See Documentation/admin-guide/bootconfig.rst 543 530 544 bttv.card= [HW,V4L] bttv (bt848 + 531 bttv.card= [HW,V4L] bttv (bt848 + bt878 based grabber cards) 545 bttv.radio= Most important insmod 532 bttv.radio= Most important insmod options are available as 546 kernel args too. 533 kernel args too. 547 bttv.pll= See Documentation/admi 534 bttv.pll= See Documentation/admin-guide/media/bttv.rst 548 bttv.tuner= 535 bttv.tuner= 549 536 550 bulk_remove=off [PPC] This parameter 537 bulk_remove=off [PPC] This parameter disables the use of the pSeries 551 firmware feature for f 538 firmware feature for flushing multiple hpte entries 552 at a time. 539 at a time. 553 540 554 c101= [NET] Moxa C101 synchr 541 c101= [NET] Moxa C101 synchronous serial card 555 542 556 cachesize= [BUGS=X86-32] Override 543 cachesize= [BUGS=X86-32] Override level 2 CPU cache size detection. 557 Sometimes CPU hardware 544 Sometimes CPU hardware bugs make them report the cache 558 size incorrectly. The 545 size incorrectly. The kernel will attempt work arounds 559 to fix known problems, 546 to fix known problems, but for some CPUs it is not 560 possible to determine 547 possible to determine what the correct size should be. 561 This option provides a 548 This option provides an override for these situations. 562 549 563 carrier_timeout= 550 carrier_timeout= 564 [NET] Specifies amount 551 [NET] Specifies amount of time (in seconds) that 565 the kernel should wait 552 the kernel should wait for a network carrier. By default 566 it waits 120 seconds. 553 it waits 120 seconds. 567 554 568 ca_keys= [KEYS] This parameter 555 ca_keys= [KEYS] This parameter identifies a specific key(s) on 569 the system trusted key 556 the system trusted keyring to be used for certificate 570 trust validation. 557 trust validation. 571 format: { id:<keyid> | 558 format: { id:<keyid> | builtin } 572 559 573 cca= [MIPS,EARLY] Override !! 560 cca= [MIPS] Override the kernel pages' cache coherency 574 algorithm. Accepted v 561 algorithm. Accepted values range from 0 to 7 575 inclusive. See arch/mi 562 inclusive. See arch/mips/include/asm/pgtable-bits.h 576 for platform specific 563 for platform specific values (SB1, Loongson3 and 577 others). 564 others). 578 565 579 ccw_timeout_log [S390] 566 ccw_timeout_log [S390] 580 See Documentation/arch 567 See Documentation/arch/s390/common_io.rst for details. 581 568 582 cgroup_disable= [KNL] Disable a partic 569 cgroup_disable= [KNL] Disable a particular controller or optional feature 583 Format: {name of the c 570 Format: {name of the controller(s) or feature(s) to disable} 584 The effects of cgroup_ 571 The effects of cgroup_disable=foo are: 585 - foo isn't auto-mount 572 - foo isn't auto-mounted if you mount all cgroups in 586 a single hierarchy 573 a single hierarchy 587 - foo isn't visible as 574 - foo isn't visible as an individually mountable 588 subsystem 575 subsystem 589 - if foo is an optiona 576 - if foo is an optional feature then the feature is 590 disabled and corresp 577 disabled and corresponding cgroup files are not 591 created 578 created 592 {Currently only "memor 579 {Currently only "memory" controller deal with this and 593 cut the overhead, othe 580 cut the overhead, others just disable the usage. So 594 only cgroup_disable=me 581 only cgroup_disable=memory is actually worthy} 595 Specifying "pressure" 582 Specifying "pressure" disables per-cgroup pressure 596 stall information acco 583 stall information accounting feature 597 584 598 cgroup_no_v1= [KNL] Disable cgroup c 585 cgroup_no_v1= [KNL] Disable cgroup controllers and named hierarchies in v1 599 Format: { { controller 586 Format: { { controller | "all" | "named" } 600 [,{ controll 587 [,{ controller | "all" | "named" }...] } 601 Like cgroup_disable, b 588 Like cgroup_disable, but only applies to cgroup v1; 602 the blacklisted contro 589 the blacklisted controllers remain available in cgroup2. 603 "all" blacklists all c 590 "all" blacklists all controllers and "named" disables 604 named mounts. Specifyi 591 named mounts. Specifying both "all" and "named" disables 605 all v1 hierarchies. 592 all v1 hierarchies. 606 593 607 cgroup_favordynmods= [KNL] Enable or D 594 cgroup_favordynmods= [KNL] Enable or Disable favordynmods. 608 Format: { "true" | "fa 595 Format: { "true" | "false" } 609 Defaults to the value 596 Defaults to the value of CONFIG_CGROUP_FAVOR_DYNMODS. 610 597 611 cgroup.memory= [KNL] Pass options to 598 cgroup.memory= [KNL] Pass options to the cgroup memory controller. 612 Format: <string> 599 Format: <string> 613 nosocket -- Disable so 600 nosocket -- Disable socket memory accounting. 614 nokmem -- Disable kern 601 nokmem -- Disable kernel memory accounting. 615 nobpf -- Disable BPF m 602 nobpf -- Disable BPF memory accounting. 616 603 617 checkreqprot= [SELINUX] Set initial 604 checkreqprot= [SELINUX] Set initial checkreqprot flag value. 618 Format: { "0" | "1" } 605 Format: { "0" | "1" } 619 See security/selinux/K 606 See security/selinux/Kconfig help text. 620 0 -- check protection 607 0 -- check protection applied by kernel (includes 621 any implied ex 608 any implied execute protection). 622 1 -- check protection 609 1 -- check protection requested by application. 623 Default value is set v 610 Default value is set via a kernel config option. 624 Value can be changed a 611 Value can be changed at runtime via 625 /sys/fs/selinu 612 /sys/fs/selinux/checkreqprot. 626 Setting checkreqprot t 613 Setting checkreqprot to 1 is deprecated. 627 614 628 cio_ignore= [S390] 615 cio_ignore= [S390] 629 See Documentation/arch 616 See Documentation/arch/s390/common_io.rst for details. 630 617 631 clearcpuid=X[,X...] [X86] 618 clearcpuid=X[,X...] [X86] 632 Disable CPUID feature 619 Disable CPUID feature X for the kernel. See 633 arch/x86/include/asm/c 620 arch/x86/include/asm/cpufeatures.h for the valid bit 634 numbers X. Note the Li 621 numbers X. Note the Linux-specific bits are not necessarily 635 stable over kernel opt 622 stable over kernel options, but the vendor-specific 636 ones should be. 623 ones should be. 637 X can also be a string 624 X can also be a string as appearing in the flags: line 638 in /proc/cpuinfo which 625 in /proc/cpuinfo which does not have the above 639 instability issue. How 626 instability issue. However, not all features have names 640 in /proc/cpuinfo. 627 in /proc/cpuinfo. 641 Note that using this o 628 Note that using this option will taint your kernel. 642 Also note that user pr 629 Also note that user programs calling CPUID directly 643 or using the feature w 630 or using the feature without checking anything 644 will still see it. Thi 631 will still see it. This just prevents it from 645 being used by the kern 632 being used by the kernel or shown in /proc/cpuinfo. 646 Also note the kernel m 633 Also note the kernel might malfunction if you disable 647 some critical bits. 634 some critical bits. 648 635 649 clk_ignore_unused 636 clk_ignore_unused 650 [CLK] 637 [CLK] 651 Prevents the clock fra 638 Prevents the clock framework from automatically gating 652 clocks that have not b 639 clocks that have not been explicitly enabled by a Linux 653 device driver but are 640 device driver but are enabled in hardware at reset or 654 by the bootloader/firm 641 by the bootloader/firmware. Note that this does not 655 force such clocks to b 642 force such clocks to be always-on nor does it reserve 656 those clocks in any wa 643 those clocks in any way. This parameter is useful for 657 debug and development, 644 debug and development, but should not be needed on a 658 platform with proper d 645 platform with proper driver support. For more 659 information, see Docum 646 information, see Documentation/driver-api/clk.rst. 660 647 661 clock= [BUGS=X86-32, HW] gett 648 clock= [BUGS=X86-32, HW] gettimeofday clocksource override. 662 [Deprecated] 649 [Deprecated] 663 Forces specified clock 650 Forces specified clocksource (if available) to be used 664 when calculating getti 651 when calculating gettimeofday(). If specified 665 clocksource is not ava 652 clocksource is not available, it defaults to PIT. 666 Format: { pit | tsc | 653 Format: { pit | tsc | cyclone | pmtmr } 667 654 668 clocksource= Override the default c 655 clocksource= Override the default clocksource 669 Format: <string> 656 Format: <string> 670 Override the default c 657 Override the default clocksource and use the clocksource 671 with the name specifie 658 with the name specified. 672 Some clocksource names 659 Some clocksource names to choose from, depending on 673 the platform: 660 the platform: 674 [all] jiffies (this is 661 [all] jiffies (this is the base, fallback clocksource) 675 [ACPI] acpi_pm 662 [ACPI] acpi_pm 676 [ARM] imx_timer1,OSTS, 663 [ARM] imx_timer1,OSTS,netx_timer,mpu_timer2, 677 pxa_timer,time 664 pxa_timer,timer3,32k_counter,timer0_1 678 [X86-32] pit,hpet,tsc; 665 [X86-32] pit,hpet,tsc; 679 scx200_hrt on 666 scx200_hrt on Geode; cyclone on IBM x440 680 [MIPS] MIPS 667 [MIPS] MIPS 681 [PARISC] cr16 668 [PARISC] cr16 682 [S390] tod 669 [S390] tod 683 [SH] SuperH 670 [SH] SuperH 684 [SPARC64] tick 671 [SPARC64] tick 685 [X86-64] hpet,tsc 672 [X86-64] hpet,tsc 686 673 687 clocksource.arm_arch_timer.evtstrm= 674 clocksource.arm_arch_timer.evtstrm= 688 [ARM,ARM64,EARLY] !! 675 [ARM,ARM64] 689 Format: <bool> 676 Format: <bool> 690 Enable/disable the eve 677 Enable/disable the eventstream feature of the ARM 691 architected timer so t 678 architected timer so that code using WFE-based polling 692 loops can be debugged 679 loops can be debugged more effectively on production 693 systems. 680 systems. 694 681 >> 682 clocksource.max_cswd_read_retries= [KNL] >> 683 Number of clocksource_watchdog() retries due to >> 684 external delays before the clock will be marked >> 685 unstable. Defaults to two retries, that is, >> 686 three attempts to read the clock under test. >> 687 695 clocksource.verify_n_cpus= [KNL] 688 clocksource.verify_n_cpus= [KNL] 696 Limit the number of CP 689 Limit the number of CPUs checked for clocksources 697 marked with CLOCK_SOUR 690 marked with CLOCK_SOURCE_VERIFY_PERCPU that 698 are marked unstable du 691 are marked unstable due to excessive skew. 699 A negative value says 692 A negative value says to check all CPUs, while 700 zero says not to check 693 zero says not to check any. Values larger than 701 nr_cpu_ids are silentl 694 nr_cpu_ids are silently truncated to nr_cpu_ids. 702 The actual CPUs are ch 695 The actual CPUs are chosen randomly, with 703 no replacement if the 696 no replacement if the same CPU is chosen twice. 704 697 705 clocksource-wdtest.holdoff= [KNL] 698 clocksource-wdtest.holdoff= [KNL] 706 Set the time in second 699 Set the time in seconds that the clocksource 707 watchdog test waits be 700 watchdog test waits before commencing its tests. 708 Defaults to zero when 701 Defaults to zero when built as a module and to 709 10 seconds when built 702 10 seconds when built into the kernel. 710 703 711 cma=nn[MG]@[start[MG][-end[MG]]] 704 cma=nn[MG]@[start[MG][-end[MG]]] 712 [KNL,CMA,EARLY] !! 705 [KNL,CMA] 713 Sets the size of kerne 706 Sets the size of kernel global memory area for 714 contiguous memory allo 707 contiguous memory allocations and optionally the 715 placement constraint b 708 placement constraint by the physical address range of 716 memory allocations. A 709 memory allocations. A value of 0 disables CMA 717 altogether. For more i 710 altogether. For more information, see 718 kernel/dma/contiguous. 711 kernel/dma/contiguous.c 719 712 720 cma_pernuma=nn[MG] 713 cma_pernuma=nn[MG] 721 [KNL,CMA,EARLY] !! 714 [KNL,CMA] 722 Sets the size of kerne 715 Sets the size of kernel per-numa memory area for 723 contiguous memory allo 716 contiguous memory allocations. A value of 0 disables 724 per-numa CMA altogethe 717 per-numa CMA altogether. And If this option is not 725 specified, the default 718 specified, the default value is 0. 726 With per-numa CMA enab 719 With per-numa CMA enabled, DMA users on node nid will 727 first try to allocate 720 first try to allocate buffer from the pernuma area 728 which is located in no 721 which is located in node nid, if the allocation fails, 729 they will fallback to 722 they will fallback to the global default memory area. 730 723 731 numa_cma=<node>:nn[MG][,<node>:nn[MG]] 724 numa_cma=<node>:nn[MG][,<node>:nn[MG]] 732 [KNL,CMA,EARLY] !! 725 [KNL,CMA] 733 Sets the size of kerne 726 Sets the size of kernel numa memory area for 734 contiguous memory allo 727 contiguous memory allocations. It will reserve CMA 735 area for the specified 728 area for the specified node. 736 729 737 With numa CMA enabled, 730 With numa CMA enabled, DMA users on node nid will 738 first try to allocate 731 first try to allocate buffer from the numa area 739 which is located in no 732 which is located in node nid, if the allocation fails, 740 they will fallback to 733 they will fallback to the global default memory area. 741 734 742 cmo_free_hint= [PPC] Format: { yes | 735 cmo_free_hint= [PPC] Format: { yes | no } 743 Specify whether pages 736 Specify whether pages are marked as being inactive 744 when they are freed. 737 when they are freed. This is used in CMO environments 745 to determine OS memory 738 to determine OS memory pressure for page stealing by 746 a hypervisor. 739 a hypervisor. 747 Default: yes 740 Default: yes 748 741 749 coherent_pool=nn[KMG] [ARM,KNL,EARLY !! 742 coherent_pool=nn[KMG] [ARM,KNL] 750 Sets the size of memor 743 Sets the size of memory pool for coherent, atomic dma 751 allocations, by defaul 744 allocations, by default set to 256K. 752 745 753 com20020= [HW,NET] ARCnet - COM2 746 com20020= [HW,NET] ARCnet - COM20020 chipset 754 Format: 747 Format: 755 <io>[,<irq>[,<nodeID>[ 748 <io>[,<irq>[,<nodeID>[,<backplane>[,<ckp>[,<timeout>]]]]] 756 749 757 com90io= [HW,NET] ARCnet - COM9 750 com90io= [HW,NET] ARCnet - COM90xx chipset (IO-mapped buffers) 758 Format: <io>[,<irq>] 751 Format: <io>[,<irq>] 759 752 760 com90xx= [HW,NET] 753 com90xx= [HW,NET] 761 ARCnet - COM90xx chips 754 ARCnet - COM90xx chipset (memory-mapped buffers) 762 Format: <io>[,<irq>[,< 755 Format: <io>[,<irq>[,<memstart>]] 763 756 764 condev= [HW,S390] console devi 757 condev= [HW,S390] console device 765 conmode= 758 conmode= 766 759 767 con3215_drop= [S390,EARLY] 3215 cons !! 760 con3215_drop= [S390] 3215 console drop mode. 768 Format: y|n|Y|N|1|0 761 Format: y|n|Y|N|1|0 769 When set to true, drop 762 When set to true, drop data on the 3215 console when 770 the console buffer is 763 the console buffer is full. In this case the 771 operator using a 3270 764 operator using a 3270 terminal emulator (for example 772 x3270) does not have t 765 x3270) does not have to enter the clear key for the 773 console output to adva 766 console output to advance and the kernel to continue. 774 This leads to a much f 767 This leads to a much faster boot time when a 3270 775 terminal emulator is a 768 terminal emulator is active. If no 3270 terminal 776 emulator is used, this 769 emulator is used, this parameter has no effect. 777 770 778 console= [KNL] Output console d 771 console= [KNL] Output console device and options. 779 772 780 tty<n> Use the virtual consol 773 tty<n> Use the virtual console device <n>. 781 774 782 ttyS<n>[,options] 775 ttyS<n>[,options] 783 ttyUSB0[,options] 776 ttyUSB0[,options] 784 Use the specified seri 777 Use the specified serial port. The options are of 785 the form "bbbbpnf", wh 778 the form "bbbbpnf", where "bbbb" is the baud rate, 786 "p" is parity ("n", "o 779 "p" is parity ("n", "o", or "e"), "n" is number of 787 bits, and "f" is flow 780 bits, and "f" is flow control ("r" for RTS or 788 omit it). Default is 781 omit it). Default is "9600n8". 789 782 790 See Documentation/admi 783 See Documentation/admin-guide/serial-console.rst for more 791 information. See 784 information. See 792 Documentation/networki 785 Documentation/networking/netconsole.rst for an 793 alternative. 786 alternative. 794 787 795 <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] 788 uart[8250],io,<addr>[,options] 815 uart[8250],mmio,<addr>[,option 789 uart[8250],mmio,<addr>[,options] 816 uart[8250],mmio16,<addr>[,opti 790 uart[8250],mmio16,<addr>[,options] 817 uart[8250],mmio32,<addr>[,opti 791 uart[8250],mmio32,<addr>[,options] 818 uart[8250],0x<addr>[,options] 792 uart[8250],0x<addr>[,options] 819 Start an early, polled 793 Start an early, polled-mode console on the 8250/16550 820 UART at the specified 794 UART at the specified I/O port or MMIO address, 821 switching to the match 795 switching to the matching ttyS device later. 822 MMIO inter-register ad 796 MMIO inter-register address stride is either 8-bit 823 (mmio), 16-bit (mmio16 797 (mmio), 16-bit (mmio16), or 32-bit (mmio32). 824 If none of [io|mmio|mm 798 If none of [io|mmio|mmio16|mmio32], <addr> is assumed 825 to be equivalent to 'm 799 to be equivalent to 'mmio'. 'options' are specified in 826 the same format descri 800 the same format described for ttyS above; if unspecified, 827 the h/w is not re-init 801 the h/w is not re-initialized. 828 802 829 hvc<n> Use the hypervisor con 803 hvc<n> Use the hypervisor console device <n>. This is for 830 both Xen and PowerPC h 804 both Xen and PowerPC hypervisors. 831 805 832 { null | "" } 806 { null | "" } 833 Use to disable console 807 Use to disable console output, i.e., to have kernel 834 console messages disca 808 console messages discarded. 835 This must be the only 809 This must be the only console= parameter used on the 836 kernel command line. 810 kernel command line. 837 811 838 If the device connected to the 812 If the device connected to the port is not a TTY but a braille 839 device, prepend "brl," before 813 device, prepend "brl," before the device type, for instance 840 console=brl,ttyS0 814 console=brl,ttyS0 841 For now, only VisioBraille is 815 For now, only VisioBraille is supported. 842 816 843 console_msg_format= 817 console_msg_format= 844 [KNL] Change console m 818 [KNL] Change console messages format 845 default 819 default 846 By default we print me 820 By default we print messages on consoles in 847 "[time stamp] text\n" 821 "[time stamp] text\n" format (time stamp may not be 848 printed, depending on 822 printed, depending on CONFIG_PRINTK_TIME or 849 `printk_time' param). 823 `printk_time' param). 850 syslog 824 syslog 851 Switch to syslog forma 825 Switch to syslog format: "<%u>[time stamp] text\n" 852 IOW, each message will 826 IOW, each message will have a facility and loglevel 853 prefix. The format is 827 prefix. The format is similar to one used by syslog() 854 syscall, or to executi 828 syscall, or to executing "dmesg -S --raw" or to reading 855 from /proc/kmsg. 829 from /proc/kmsg. 856 830 857 consoleblank= [KNL] The console blan 831 consoleblank= [KNL] The console blank (screen saver) timeout in 858 seconds. A value of 0 832 seconds. A value of 0 disables the blank timer. 859 Defaults to 0. 833 Defaults to 0. 860 834 861 coredump_filter= 835 coredump_filter= 862 [KNL] Change the defau 836 [KNL] Change the default value for 863 /proc/<pid>/coredump_f 837 /proc/<pid>/coredump_filter. 864 See also Documentation 838 See also Documentation/filesystems/proc.rst. 865 839 866 coresight_cpu_debug.enable 840 coresight_cpu_debug.enable 867 [ARM,ARM64] 841 [ARM,ARM64] 868 Format: <bool> 842 Format: <bool> 869 Enable/disable the CPU 843 Enable/disable the CPU sampling based debugging. 870 0: default value, disa 844 0: default value, disable debugging 871 1: enable debugging at 845 1: enable debugging at boot time 872 846 873 cpcihp_generic= [HW,PCI] Generic port 847 cpcihp_generic= [HW,PCI] Generic port I/O CompactPCI driver 874 Format: 848 Format: 875 <first_slot>,<last_slo 849 <first_slot>,<last_slot>,<port>,<enum_bit>[,<debug>] 876 850 877 cpuidle.off=1 [CPU_IDLE] 851 cpuidle.off=1 [CPU_IDLE] 878 disable the cpuidle su 852 disable the cpuidle sub-system 879 853 880 cpuidle.governor= 854 cpuidle.governor= 881 [CPU_IDLE] Name of the 855 [CPU_IDLE] Name of the cpuidle governor to use. 882 856 883 cpufreq.off=1 [CPU_FREQ] 857 cpufreq.off=1 [CPU_FREQ] 884 disable the cpufreq su 858 disable the cpufreq sub-system 885 859 886 cpufreq.default_governor= 860 cpufreq.default_governor= 887 [CPU_FREQ] Name of the 861 [CPU_FREQ] Name of the default cpufreq governor or 888 policy to use. This go 862 policy to use. This governor must be registered in the 889 kernel before the cpuf 863 kernel before the cpufreq driver probes. 890 864 891 cpu_init_udelay=N 865 cpu_init_udelay=N 892 [X86,EARLY] Delay for !! 866 [X86] Delay for N microsec between assert and de-assert 893 of APIC INIT to start 867 of APIC INIT to start processors. This delay occurs 894 on every CPU online, s 868 on every CPU online, such as boot, and resume from suspend. 895 Default: 10000 869 Default: 10000 896 870 897 cpuhp.parallel= 871 cpuhp.parallel= 898 [SMP] Enable/disable p 872 [SMP] Enable/disable parallel bringup of secondary CPUs 899 Format: <bool> 873 Format: <bool> 900 Default is enabled if 874 Default is enabled if CONFIG_HOTPLUG_PARALLEL=y. Otherwise 901 the parameter has no e 875 the parameter has no effect. 902 876 903 crash_kexec_post_notifiers 877 crash_kexec_post_notifiers 904 Run kdump after runnin 878 Run kdump after running panic-notifiers and dumping 905 kmsg. This only for th 879 kmsg. This only for the users who doubt kdump always 906 succeeds in any situat 880 succeeds in any situation. 907 Note that this also in 881 Note that this also increases risks of kdump failure, 908 because some panic not 882 because some panic notifiers can make the crashed 909 kernel more unstable. 883 kernel more unstable. 910 884 911 crashkernel=size[KMG][@offset[KMG]] 885 crashkernel=size[KMG][@offset[KMG]] 912 [KNL,EARLY] Using kexe !! 886 [KNL] Using kexec, Linux can switch to a 'crash kernel' 913 upon panic. This param 887 upon panic. This parameter reserves the physical 914 memory region [offset, 888 memory region [offset, offset + size] for that kernel 915 image. If '@offset' is 889 image. If '@offset' is omitted, then a suitable offset 916 is selected automatica 890 is selected automatically. 917 [KNL, X86-64, ARM64, R 891 [KNL, X86-64, ARM64, RISCV, LoongArch] Select a region 918 under 4G first, and fa 892 under 4G first, and fall back to reserve region above 919 4G when '@offset' hasn 893 4G when '@offset' hasn't been specified. 920 See Documentation/admi 894 See Documentation/admin-guide/kdump/kdump.rst for further details. 921 895 922 crashkernel=range1:size1[,range2:size2 896 crashkernel=range1:size1[,range2:size2,...][@offset] 923 [KNL] Same as above, b 897 [KNL] Same as above, but depends on the memory 924 in the running system. 898 in the running system. The syntax of range is 925 start-[end] where star 899 start-[end] where start and end are both 926 a memory unit (amount[ 900 a memory unit (amount[KMG]). See also 927 Documentation/admin-gu 901 Documentation/admin-guide/kdump/kdump.rst for an example. 928 902 929 crashkernel=size[KMG],high 903 crashkernel=size[KMG],high 930 [KNL, X86-64, ARM64, R 904 [KNL, X86-64, ARM64, RISCV, LoongArch] range could be 931 above 4G. 905 above 4G. 932 Allow kernel to alloca 906 Allow kernel to allocate physical memory region from top, 933 so could be above 4G i 907 so could be above 4G if system have more than 4G ram 934 installed. Otherwise m 908 installed. Otherwise memory region will be allocated 935 below 4G, if available 909 below 4G, if available. 936 It will be ignored if 910 It will be ignored if crashkernel=X is specified. 937 crashkernel=size[KMG],low 911 crashkernel=size[KMG],low 938 [KNL, X86-64, ARM64, R 912 [KNL, X86-64, ARM64, RISCV, LoongArch] range under 4G. 939 When crashkernel=X,hig 913 When crashkernel=X,high is passed, kernel could allocate 940 physical memory region 914 physical memory region above 4G, that cause second kernel 941 crash on system that r 915 crash on system that require some amount of low memory, 942 e.g. swiotlb requires 916 e.g. swiotlb requires at least 64M+32K low memory, also 943 enough extra low memor 917 enough extra low memory is needed to make sure DMA buffers 944 for 32-bit devices won 918 for 32-bit devices won't run out. Kernel would try to allocate 945 default size of memory 919 default size of memory below 4G automatically. The default 946 size is platform depen 920 size is platform dependent. 947 --> x86: max(swiotlb 921 --> x86: max(swiotlb_size_or_default() + 8MiB, 256MiB) 948 --> arm64: 128MiB 922 --> arm64: 128MiB 949 --> riscv: 128MiB 923 --> riscv: 128MiB 950 --> loongarch: 128Mi 924 --> loongarch: 128MiB 951 This one lets the user 925 This one lets the user specify own low range under 4G 952 for second kernel inst 926 for second kernel instead. 953 0: to disable low allo 927 0: to disable low allocation. 954 It will be ignored whe 928 It will be ignored when crashkernel=X,high is not used 955 or memory reserved is 929 or memory reserved is below 4G. 956 930 957 cryptomgr.notests 931 cryptomgr.notests 958 [KNL] Disable crypto s 932 [KNL] Disable crypto self-tests 959 933 960 cs89x0_dma= [HW,NET] 934 cs89x0_dma= [HW,NET] 961 Format: <dma> 935 Format: <dma> 962 936 963 cs89x0_media= [HW,NET] 937 cs89x0_media= [HW,NET] 964 Format: { rj45 | aui | 938 Format: { rj45 | aui | bnc } 965 939 966 csdlock_debug= [KNL] Enable or disabl 940 csdlock_debug= [KNL] Enable or disable debug add-ons of cross-CPU 967 function call handling 941 function call handling. When switched on, 968 additional debug data 942 additional debug data is printed to the console 969 in case a hanging CPU 943 in case a hanging CPU is detected, and that 970 CPU is pinged again in 944 CPU is pinged again in order to try to resolve 971 the hang situation. T 945 the hang situation. The default value of this 972 option depends on the 946 option depends on the CSD_LOCK_WAIT_DEBUG_DEFAULT 973 Kconfig option. 947 Kconfig option. 974 948 975 dasd= [HW,NET] 949 dasd= [HW,NET] 976 See header of drivers/ 950 See header of drivers/s390/block/dasd_devmap.c. 977 951 978 db9.dev[2|3]= [HW,JOY] Multisystem j 952 db9.dev[2|3]= [HW,JOY] Multisystem joystick support via parallel port 979 (one device per port) 953 (one device per port) 980 Format: <port#>,<type> 954 Format: <port#>,<type> 981 See also Documentation 955 See also Documentation/input/devices/joystick-parport.rst 982 956 983 debug [KNL,EARLY] Enable ker !! 957 debug [KNL] Enable kernel debugging (events log level). 984 958 985 debug_boot_weak_hash 959 debug_boot_weak_hash 986 [KNL,EARLY] Enable pri !! 960 [KNL] Enable printing [hashed] pointers early in the 987 boot sequence. If ena 961 boot sequence. If enabled, we use a weak hash instead 988 of siphash to hash poi 962 of siphash to hash pointers. Use this option if you are 989 seeing instances of '( 963 seeing instances of '(___ptrval___)') and need to see a 990 value (hashed pointer) 964 value (hashed pointer) instead. Cryptographically 991 insecure, please do no 965 insecure, please do not use on production kernels. 992 966 993 debug_locks_verbose= 967 debug_locks_verbose= 994 [KNL] verbose locking 968 [KNL] verbose locking self-tests 995 Format: <int> 969 Format: <int> 996 Print debugging info w 970 Print debugging info while doing the locking API 997 self-tests. 971 self-tests. 998 Bitmask for the variou 972 Bitmask for the various LOCKTYPE_ tests. Defaults to 0 999 (no extra messages), s 973 (no extra messages), setting it to -1 (all bits set) 1000 will print _a_lot_ mo 974 will print _a_lot_ more information - normally only 1001 useful to lockdep dev 975 useful to lockdep developers. 1002 976 1003 debug_objects [KNL,EARLY] Enable ob !! 977 debug_objects [KNL] Enable object debugging 1004 978 1005 debug_guardpage_minorder= 979 debug_guardpage_minorder= 1006 [KNL,EARLY] When CONF !! 980 [KNL] When CONFIG_DEBUG_PAGEALLOC is set, this 1007 parameter allows cont 981 parameter allows control of the order of pages that will 1008 be intentionally kept 982 be intentionally kept free (and hence protected) by the 1009 buddy allocator. Bigg 983 buddy allocator. Bigger value increase the probability 1010 of catching random me 984 of catching random memory corruption, but reduce the 1011 amount of memory for 985 amount of memory for normal system use. The maximum 1012 possible value is MAX 986 possible value is MAX_PAGE_ORDER/2. Setting this 1013 parameter to 1 or 2 s 987 parameter to 1 or 2 should be enough to identify most 1014 random memory corrupt 988 random memory corruption problems caused by bugs in 1015 kernel or driver code 989 kernel or driver code when a CPU writes to (or reads 1016 from) a random memory 990 from) a random memory location. Note that there exists 1017 a class of memory cor 991 a class of memory corruptions problems caused by buggy 1018 H/W or F/W or by driv 992 H/W or F/W or by drivers badly programming DMA 1019 (basically when memor 993 (basically when memory is written at bus level and the 1020 CPU MMU is bypassed) 994 CPU MMU is bypassed) which are not detectable by 1021 CONFIG_DEBUG_PAGEALLO 995 CONFIG_DEBUG_PAGEALLOC, hence this option will not 1022 help tracking down th 996 help tracking down these problems. 1023 997 1024 debug_pagealloc= 998 debug_pagealloc= 1025 [KNL,EARLY] When CONF !! 999 [KNL] When CONFIG_DEBUG_PAGEALLOC is set, this parameter 1026 enables the feature a 1000 enables the feature at boot time. By default, it is 1027 disabled and the syst 1001 disabled and the system will work mostly the same as a 1028 kernel built without 1002 kernel built without CONFIG_DEBUG_PAGEALLOC. 1029 Note: to get most of 1003 Note: to get most of debug_pagealloc error reports, it's 1030 useful to also enable 1004 useful to also enable the page_owner functionality. 1031 on: enable the featur 1005 on: enable the feature 1032 1006 1033 debugfs= [KNL,EARLY] This para !! 1007 debugfs= [KNL] This parameter enables what is exposed to userspace 1034 userspace and debugfs !! 1008 and debugfs internal clients. 1035 Format: { on, no-moun 1009 Format: { on, no-mount, off } 1036 on: All functions 1010 on: All functions are enabled. 1037 no-mount: 1011 no-mount: 1038 Filesystem is 1012 Filesystem is not registered but kernel clients can 1039 access APIs a 1013 access APIs and a crashkernel can be used to read 1040 its content. 1014 its content. There is nothing to mount. 1041 off: Filesystem is 1015 off: Filesystem is not registered and clients 1042 get a -EPERM 1016 get a -EPERM as result when trying to register files 1043 or directorie 1017 or directories within debugfs. 1044 This is equiv 1018 This is equivalent of the runtime functionality if 1045 debugfs was n 1019 debugfs was not enabled in the kernel at all. 1046 Default value is set 1020 Default value is set in build-time with a kernel configuration. 1047 1021 1048 debugpat [X86] Enable PAT debu 1022 debugpat [X86] Enable PAT debugging 1049 1023 1050 default_hugepagesz= 1024 default_hugepagesz= 1051 [HW] The size of the 1025 [HW] The size of the default HugeTLB page. This is 1052 the size represented 1026 the size represented by the legacy /proc/ hugepages 1053 APIs. In addition, t 1027 APIs. In addition, this is the default hugetlb size 1054 used for shmget(), mm 1028 used for shmget(), mmap() and mounting hugetlbfs 1055 filesystems. If not 1029 filesystems. If not specified, defaults to the 1056 architecture's defaul 1030 architecture's default huge page size. Huge page 1057 sizes are architectur 1031 sizes are architecture dependent. See also 1058 Documentation/admin-g 1032 Documentation/admin-guide/mm/hugetlbpage.rst. 1059 Format: size[KMG] 1033 Format: size[KMG] 1060 1034 1061 deferred_probe_timeout= 1035 deferred_probe_timeout= 1062 [KNL] Debugging optio 1036 [KNL] Debugging option to set a timeout in seconds for 1063 deferred probe to giv 1037 deferred probe to give up waiting on dependencies to 1064 probe. Only specific 1038 probe. Only specific dependencies (subsystems or 1065 drivers) that have op 1039 drivers) that have opted in will be ignored. A timeout 1066 of 0 will timeout at 1040 of 0 will timeout at the end of initcalls. If the time 1067 out hasn't expired, i 1041 out hasn't expired, it'll be restarted by each 1068 successful driver reg 1042 successful driver registration. This option will also 1069 dump out devices stil 1043 dump out devices still on the deferred probe list after 1070 retrying. 1044 retrying. 1071 1045 1072 delayacct [KNL] Enable per-task 1046 delayacct [KNL] Enable per-task delay accounting 1073 1047 1074 dell_smm_hwmon.ignore_dmi= 1048 dell_smm_hwmon.ignore_dmi= 1075 [HW] Continue probing 1049 [HW] Continue probing hardware even if DMI data 1076 indicates that the dr 1050 indicates that the driver is running on unsupported 1077 hardware. 1051 hardware. 1078 1052 1079 dell_smm_hwmon.force= 1053 dell_smm_hwmon.force= 1080 [HW] Activate driver 1054 [HW] Activate driver even if SMM BIOS signature does 1081 not match list of sup 1055 not match list of supported models and enable otherwise 1082 blacklisted features. 1056 blacklisted features. 1083 1057 1084 dell_smm_hwmon.power_status= 1058 dell_smm_hwmon.power_status= 1085 [HW] Report power sta 1059 [HW] Report power status in /proc/i8k 1086 (disabled by default) 1060 (disabled by default). 1087 1061 1088 dell_smm_hwmon.restricted= 1062 dell_smm_hwmon.restricted= 1089 [HW] Allow controllin 1063 [HW] Allow controlling fans only if SYS_ADMIN 1090 capability is set. 1064 capability is set. 1091 1065 1092 dell_smm_hwmon.fan_mult= 1066 dell_smm_hwmon.fan_mult= 1093 [HW] Factor to multip 1067 [HW] Factor to multiply fan speed with. 1094 1068 1095 dell_smm_hwmon.fan_max= 1069 dell_smm_hwmon.fan_max= 1096 [HW] Maximum configur 1070 [HW] Maximum configurable fan speed. 1097 1071 1098 dfltcc= [HW,S390] 1072 dfltcc= [HW,S390] 1099 Format: { on | off | 1073 Format: { on | off | def_only | inf_only | always } 1100 on: s390 zlib h 1074 on: s390 zlib hardware support for compression on 1101 level 1 and 1075 level 1 and decompression (default) 1102 off: No s390 zli 1076 off: No s390 zlib hardware support 1103 def_only: s390 zlib h 1077 def_only: s390 zlib hardware support for deflate 1104 only (compr 1078 only (compression on level 1) 1105 inf_only: s390 zlib h 1079 inf_only: s390 zlib hardware support for inflate 1106 only (decom 1080 only (decompression) 1107 always: Same as 'on 1081 always: Same as 'on' but ignores the selected compression 1108 level alway 1082 level always using hardware support (used for debugging) 1109 1083 1110 dhash_entries= [KNL] 1084 dhash_entries= [KNL] 1111 Set number of hash bu 1085 Set number of hash buckets for dentry cache. 1112 1086 1113 disable_1tb_segments [PPC,EARLY] !! 1087 disable_1tb_segments [PPC] 1114 Disables the use of 1 1088 Disables the use of 1TB hash page table segments. This 1115 causes the kernel to 1089 causes the kernel to fall back to 256MB segments which 1116 can be useful when de 1090 can be useful when debugging issues that require an SLB 1117 miss to occur. 1091 miss to occur. 1118 1092 1119 disable= [IPV6] 1093 disable= [IPV6] 1120 See Documentation/net 1094 See Documentation/networking/ipv6.rst. 1121 1095 1122 disable_radix [PPC,EARLY] !! 1096 disable_radix [PPC] 1123 Disable RADIX MMU mod 1097 Disable RADIX MMU mode on POWER9 1124 1098 1125 disable_tlbie [PPC] 1099 disable_tlbie [PPC] 1126 Disable TLBIE instruc 1100 Disable TLBIE instruction. Currently does not work 1127 with KVM, with HASH M 1101 with KVM, with HASH MMU, or with coherent accelerators. 1128 1102 1129 disable_ddw [PPC/PSERIES,EARLY] !! 1103 disable_cpu_apicid= [X86,APIC,SMP] >> 1104 Format: <int> >> 1105 The number of initial APIC ID for the >> 1106 corresponding CPU to be disabled at boot, >> 1107 mostly used for the kdump 2nd kernel to >> 1108 disable BSP to wake up multiple CPUs without >> 1109 causing system reset or hang due to sending >> 1110 INIT from AP to BSP. >> 1111 >> 1112 disable_ddw [PPC/PSERIES] 1130 Disable Dynamic DMA W 1113 Disable Dynamic DMA Window support. Use this 1131 to workaround buggy f 1114 to workaround buggy firmware. 1132 1115 1133 disable_ipv6= [IPV6] 1116 disable_ipv6= [IPV6] 1134 See Documentation/net 1117 See Documentation/networking/ipv6.rst. 1135 1118 1136 disable_mtrr_cleanup [X86,EARLY] !! 1119 disable_mtrr_cleanup [X86] 1137 The kernel tries to a 1120 The kernel tries to adjust MTRR layout from continuous 1138 to discrete, to make 1121 to discrete, to make X server driver able to add WB 1139 entry later. This par 1122 entry later. This parameter disables that. 1140 1123 1141 disable_mtrr_trim [X86, Intel and AMD !! 1124 disable_mtrr_trim [X86, Intel and AMD only] 1142 By default the kernel 1125 By default the kernel will trim any uncacheable 1143 memory out of your av 1126 memory out of your available memory pool based on 1144 MTRR settings. This 1127 MTRR settings. This parameter disables that behavior, 1145 possibly causing your 1128 possibly causing your machine to run very slowly. 1146 1129 1147 disable_timer_pin_1 [X86,EARLY] !! 1130 disable_timer_pin_1 [X86] 1148 Disable PIN 1 of APIC 1131 Disable PIN 1 of APIC timer 1149 Can be useful to work 1132 Can be useful to work around chipset bugs. 1150 1133 1151 dis_ucode_ldr [X86] Disable the mic 1134 dis_ucode_ldr [X86] Disable the microcode loader. 1152 1135 1153 dma_debug=off If the kernel is comp 1136 dma_debug=off If the kernel is compiled with DMA_API_DEBUG support, 1154 this option disables 1137 this option disables the debugging code at boot. 1155 1138 1156 dma_debug_entries=<number> 1139 dma_debug_entries=<number> 1157 This option allows to 1140 This option allows to tune the number of preallocated 1158 entries for DMA-API d 1141 entries for DMA-API debugging code. One entry is 1159 required per DMA-API 1142 required per DMA-API allocation. Use this if the 1160 DMA-API debugging cod 1143 DMA-API debugging code disables itself because the 1161 architectural default 1144 architectural default is too low. 1162 1145 1163 dma_debug_driver=<driver_name> 1146 dma_debug_driver=<driver_name> 1164 With this option the 1147 With this option the DMA-API debugging driver 1165 filter feature can be 1148 filter feature can be enabled at boot time. Just 1166 pass the driver to fi 1149 pass the driver to filter for as the parameter. 1167 The filter can be dis 1150 The filter can be disabled or changed to another 1168 driver later using sy 1151 driver later using sysfs. 1169 1152 1170 reg_file_data_sampling= 1153 reg_file_data_sampling= 1171 [X86] Controls mitiga 1154 [X86] Controls mitigation for Register File Data 1172 Sampling (RFDS) vulne 1155 Sampling (RFDS) vulnerability. RFDS is a CPU 1173 vulnerability which m 1156 vulnerability which may allow userspace to infer 1174 kernel data values pr 1157 kernel data values previously stored in floating point 1175 registers, vector reg 1158 registers, vector registers, or integer registers. 1176 RFDS only affects Int 1159 RFDS only affects Intel Atom processors. 1177 1160 1178 on: Turns ON the 1161 on: Turns ON the mitigation. 1179 off: Turns OFF the 1162 off: Turns OFF the mitigation. 1180 1163 1181 This parameter overri 1164 This parameter overrides the compile time default set 1182 by CONFIG_MITIGATION_ 1165 by CONFIG_MITIGATION_RFDS. Mitigation cannot be 1183 disabled when other V 1166 disabled when other VERW based mitigations (like MDS) 1184 are enabled. In order 1167 are enabled. In order to disable RFDS mitigation all 1185 VERW based mitigation 1168 VERW based mitigations need to be disabled. 1186 1169 1187 For details see: 1170 For details see: 1188 Documentation/admin-g 1171 Documentation/admin-guide/hw-vuln/reg-file-data-sampling.rst 1189 1172 1190 driver_async_probe= [KNL] 1173 driver_async_probe= [KNL] 1191 List of driver names 1174 List of driver names to be probed asynchronously. * 1192 matches with all driv 1175 matches with all driver names. If * is specified, the 1193 rest of the listed dr 1176 rest of the listed driver names are those that will NOT 1194 match the *. 1177 match the *. 1195 Format: <driver_name1 1178 Format: <driver_name1>,<driver_name2>... 1196 1179 1197 drm.edid_firmware=[<connector>:]<file 1180 drm.edid_firmware=[<connector>:]<file>[,[<connector>:]<file>] 1198 Broken monitors, grap 1181 Broken monitors, graphic adapters, KVMs and EDIDless 1199 panels may send no or 1182 panels may send no or incorrect EDID data sets. 1200 This parameter allows 1183 This parameter allows to specify an EDID data sets 1201 in the /lib/firmware 1184 in the /lib/firmware directory that are used instead. 1202 An EDID data set will !! 1185 Generic built-in EDID data sets are used, if one of 1203 connector, if its nam !! 1186 edid/1024x768.bin, edid/1280x1024.bin, 1204 the EDID name. Each c !! 1187 edid/1680x1050.bin, or edid/1920x1080.bin is given 1205 data set by separatin !! 1188 and no file with the same name exists. Details and >> 1189 instructions how to build your own EDID data are >> 1190 available in Documentation/admin-guide/edid.rst. An EDID >> 1191 data set will only be used for a particular connector, >> 1192 if its name and a colon are prepended to the EDID >> 1193 name. Each connector may use a unique EDID data >> 1194 set by separating the files with a comma. An EDID 1206 data set with no conn 1195 data set with no connector name will be used for 1207 any connectors not ex 1196 any connectors not explicitly specified. 1208 1197 1209 dscc4.setup= [NET] 1198 dscc4.setup= [NET] 1210 1199 1211 dt_cpu_ftrs= [PPC,EARLY] !! 1200 dt_cpu_ftrs= [PPC] 1212 Format: {"off" | "kno 1201 Format: {"off" | "known"} 1213 Control how the dt_cp 1202 Control how the dt_cpu_ftrs device-tree binding is 1214 used for CPU feature 1203 used for CPU feature discovery and setup (if it 1215 exists). 1204 exists). 1216 off: Do not use it, f 1205 off: Do not use it, fall back to legacy cpu table. 1217 known: Do not pass th 1206 known: Do not pass through unknown features to guests 1218 or userspace, only th 1207 or userspace, only those that the kernel is aware of. 1219 1208 1220 dump_apple_properties [X86] 1209 dump_apple_properties [X86] 1221 Dump name and content 1210 Dump name and content of EFI device properties on 1222 x86 Macs. Useful for 1211 x86 Macs. Useful for driver authors to determine 1223 what data is availabl 1212 what data is available or for reverse-engineering. 1224 1213 1225 dyndbg[="val"] [KNL,DYNAMIC_ 1214 dyndbg[="val"] [KNL,DYNAMIC_DEBUG] 1226 <module>.dyndbg[="val"] 1215 <module>.dyndbg[="val"] 1227 Enable debug messages 1216 Enable debug messages at boot time. See 1228 Documentation/admin-g 1217 Documentation/admin-guide/dynamic-debug-howto.rst 1229 for details. 1218 for details. 1230 1219 1231 early_ioremap_debug [KNL,EARLY] !! 1220 early_ioremap_debug [KNL] 1232 Enable debug messages 1221 Enable debug messages in early_ioremap support. This 1233 is useful for trackin 1222 is useful for tracking down temporary early mappings 1234 which are not unmappe 1223 which are not unmapped. 1235 1224 1236 earlycon= [KNL,EARLY] Output ea !! 1225 earlycon= [KNL] Output early console device and options. 1237 1226 1238 When used with no opt 1227 When used with no options, the early console is 1239 determined by stdout- 1228 determined by stdout-path property in device tree's 1240 chosen node or the AC 1229 chosen node or the ACPI SPCR table if supported by 1241 the platform. 1230 the platform. 1242 1231 1243 cdns,<addr>[,options] 1232 cdns,<addr>[,options] 1244 Start an early, polle 1233 Start an early, polled-mode console on a Cadence 1245 (xuartps) serial port 1234 (xuartps) serial port at the specified address. Only 1246 supported option is b 1235 supported option is baud rate. If baud rate is not 1247 specified, the serial 1236 specified, the serial port must already be setup and 1248 configured. 1237 configured. 1249 1238 1250 uart[8250],io,<addr>[,options 1239 uart[8250],io,<addr>[,options[,uartclk]] 1251 uart[8250],mmio,<addr>[,optio 1240 uart[8250],mmio,<addr>[,options[,uartclk]] 1252 uart[8250],mmio32,<addr>[,opt 1241 uart[8250],mmio32,<addr>[,options[,uartclk]] 1253 uart[8250],mmio32be,<addr>[,o 1242 uart[8250],mmio32be,<addr>[,options[,uartclk]] 1254 uart[8250],0x<addr>[,options] 1243 uart[8250],0x<addr>[,options] 1255 Start an early, polle 1244 Start an early, polled-mode console on the 8250/16550 1256 UART at the specified 1245 UART at the specified I/O port or MMIO address. 1257 MMIO inter-register a 1246 MMIO inter-register address stride is either 8-bit 1258 (mmio) or 32-bit (mmi 1247 (mmio) or 32-bit (mmio32 or mmio32be). 1259 If none of [io|mmio|m 1248 If none of [io|mmio|mmio32|mmio32be], <addr> is assumed 1260 to be equivalent to ' 1249 to be equivalent to 'mmio'. 'options' are specified 1261 in the same format de 1250 in the same format described for "console=ttyS<n>"; if 1262 unspecified, the h/w 1251 unspecified, the h/w is not initialized. 'uartclk' is 1263 the uart clock freque 1252 the uart clock frequency; if unspecified, it is set 1264 to 'BASE_BAUD' * 16. 1253 to 'BASE_BAUD' * 16. 1265 1254 1266 pl011,<addr> 1255 pl011,<addr> 1267 pl011,mmio32,<addr> 1256 pl011,mmio32,<addr> 1268 Start an early, polle 1257 Start an early, polled-mode console on a pl011 serial 1269 port at the specified 1258 port at the specified address. The pl011 serial port 1270 must already be setup 1259 must already be setup and configured. Options are not 1271 yet supported. If 'm 1260 yet supported. If 'mmio32' is specified, then only 1272 the driver will use o 1261 the driver will use only 32-bit accessors to read/write 1273 the device registers. 1262 the device registers. 1274 1263 1275 liteuart,<addr> 1264 liteuart,<addr> 1276 Start an early consol 1265 Start an early console on a litex serial port at the 1277 specified address. Th 1266 specified address. The serial port must already be 1278 setup and configured. 1267 setup and configured. Options are not yet supported. 1279 1268 1280 meson,<addr> 1269 meson,<addr> 1281 Start an early, polle 1270 Start an early, polled-mode console on a meson serial 1282 port at the specified 1271 port at the specified address. The serial port must 1283 already be setup and 1272 already be setup and configured. Options are not yet 1284 supported. 1273 supported. 1285 1274 1286 msm_serial,<addr> 1275 msm_serial,<addr> 1287 Start an early, polle 1276 Start an early, polled-mode console on an msm serial 1288 port at the specified 1277 port at the specified address. The serial port 1289 must already be setup 1278 must already be setup and configured. Options are not 1290 yet supported. 1279 yet supported. 1291 1280 1292 msm_serial_dm,<addr> 1281 msm_serial_dm,<addr> 1293 Start an early, polle 1282 Start an early, polled-mode console on an msm serial 1294 dm port at the specif 1283 dm port at the specified address. The serial port 1295 must already be setup 1284 must already be setup and configured. Options are not 1296 yet supported. 1285 yet supported. 1297 1286 1298 owl,<addr> 1287 owl,<addr> 1299 Start an early, polle 1288 Start an early, polled-mode console on a serial port 1300 of an Actions Semi So 1289 of an Actions Semi SoC, such as S500 or S900, at the 1301 specified address. Th 1290 specified address. The serial port must already be 1302 setup and configured. 1291 setup and configured. Options are not yet supported. 1303 1292 1304 rda,<addr> 1293 rda,<addr> 1305 Start an early, polle 1294 Start an early, polled-mode console on a serial port 1306 of an RDA Micro SoC, 1295 of an RDA Micro SoC, such as RDA8810PL, at the 1307 specified address. Th 1296 specified address. The serial port must already be 1308 setup and configured. 1297 setup and configured. Options are not yet supported. 1309 1298 1310 sbi 1299 sbi 1311 Use RISC-V SBI (Super 1300 Use RISC-V SBI (Supervisor Binary Interface) for early 1312 console. 1301 console. 1313 1302 1314 smh Use ARM semihosting c 1303 smh Use ARM semihosting calls for early console. 1315 1304 1316 s3c2410,<addr> 1305 s3c2410,<addr> 1317 s3c2412,<addr> 1306 s3c2412,<addr> 1318 s3c2440,<addr> 1307 s3c2440,<addr> 1319 s3c6400,<addr> 1308 s3c6400,<addr> 1320 s5pv210,<addr> 1309 s5pv210,<addr> 1321 exynos4210,<addr> 1310 exynos4210,<addr> 1322 Use early console pro 1311 Use early console provided by serial driver available 1323 on Samsung SoCs, requ 1312 on Samsung SoCs, requires selecting proper type and 1324 a correct base addres 1313 a correct base address of the selected UART port. The 1325 serial port must alre 1314 serial port must already be setup and configured. 1326 Options are not yet s 1315 Options are not yet supported. 1327 1316 1328 lantiq,<addr> 1317 lantiq,<addr> 1329 Start an early, polle 1318 Start an early, polled-mode console on a lantiq serial 1330 (lqasc) port at the s 1319 (lqasc) port at the specified address. The serial port 1331 must already be setup 1320 must already be setup and configured. Options are not 1332 yet supported. 1321 yet supported. 1333 1322 1334 lpuart,<addr> 1323 lpuart,<addr> 1335 lpuart32,<addr> 1324 lpuart32,<addr> 1336 Use early console pro 1325 Use early console provided by Freescale LP UART driver 1337 found on Freescale Vy 1326 found on Freescale Vybrid and QorIQ LS1021A processors. 1338 A valid base address 1327 A valid base address must be provided, and the serial 1339 port must already be 1328 port must already be setup and configured. 1340 1329 1341 ec_imx21,<addr> 1330 ec_imx21,<addr> 1342 ec_imx6q,<addr> 1331 ec_imx6q,<addr> 1343 Start an early, polle 1332 Start an early, polled-mode, output-only console on the 1344 Freescale i.MX UART a 1333 Freescale i.MX UART at the specified address. The UART 1345 must already be setup 1334 must already be setup and configured. 1346 1335 1347 ar3700_uart,<addr> 1336 ar3700_uart,<addr> 1348 Start an early, polle 1337 Start an early, polled-mode console on the 1349 Armada 3700 serial po 1338 Armada 3700 serial port at the specified 1350 address. The serial p 1339 address. The serial port must already be setup 1351 and configured. Optio 1340 and configured. Options are not yet supported. 1352 1341 1353 qcom_geni,<addr> 1342 qcom_geni,<addr> 1354 Start an early, polle 1343 Start an early, polled-mode console on a Qualcomm 1355 Generic Interface (GE 1344 Generic Interface (GENI) based serial port at the 1356 specified address. Th 1345 specified address. The serial port must already be 1357 setup and configured. 1346 setup and configured. Options are not yet supported. 1358 1347 1359 efifb,[options] 1348 efifb,[options] 1360 Start an early, unacc 1349 Start an early, unaccelerated console on the EFI 1361 memory mapped framebu 1350 memory mapped framebuffer (if available). On cache 1362 coherent non-x86 syst 1351 coherent non-x86 systems that use system memory for 1363 the framebuffer, pass 1352 the framebuffer, pass the 'ram' option so that it is 1364 mapped with the corre 1353 mapped with the correct attributes. 1365 1354 1366 linflex,<addr> 1355 linflex,<addr> 1367 Use early console pro 1356 Use early console provided by Freescale LINFlexD UART 1368 serial driver for NXP 1357 serial driver for NXP S32V234 SoCs. A valid base 1369 address must be provi 1358 address must be provided, and the serial port must 1370 already be setup and 1359 already be setup and configured. 1371 1360 1372 earlyprintk= [X86,SH,ARM,M68k,S390 !! 1361 earlyprintk= [X86,SH,ARM,M68k,S390] 1373 earlyprintk=vga 1362 earlyprintk=vga 1374 earlyprintk=sclp 1363 earlyprintk=sclp 1375 earlyprintk=xen 1364 earlyprintk=xen 1376 earlyprintk=serial[,t 1365 earlyprintk=serial[,ttySn[,baudrate]] 1377 earlyprintk=serial[,0 1366 earlyprintk=serial[,0x...[,baudrate]] 1378 earlyprintk=ttySn[,ba 1367 earlyprintk=ttySn[,baudrate] 1379 earlyprintk=dbgp[debu 1368 earlyprintk=dbgp[debugController#] 1380 earlyprintk=pciserial 1369 earlyprintk=pciserial[,force],bus:device.function[,baudrate] 1381 earlyprintk=xdbc[xhci 1370 earlyprintk=xdbc[xhciController#] 1382 earlyprintk=bios 1371 earlyprintk=bios 1383 1372 1384 earlyprintk is useful 1373 earlyprintk is useful when the kernel crashes before 1385 the normal console is 1374 the normal console is initialized. It is not enabled by 1386 default because it ha 1375 default because it has some cosmetic problems. 1387 1376 1388 Append ",keep" to not 1377 Append ",keep" to not disable it when the real console 1389 takes over. 1378 takes over. 1390 1379 1391 Only one of vga, seri 1380 Only one of vga, serial, or usb debug port can 1392 be used at a time. 1381 be used at a time. 1393 1382 1394 Currently only ttyS0 1383 Currently only ttyS0 and ttyS1 may be specified by 1395 name. Other I/O port 1384 name. Other I/O ports may be explicitly specified 1396 on some architectures 1385 on some architectures (x86 and arm at least) by 1397 replacing ttySn with 1386 replacing ttySn with an I/O port address, like this: 1398 earlyprintk=s 1387 earlyprintk=serial,0x1008,115200 1399 You can find the port 1388 You can find the port for a given device in 1400 /proc/tty/driver/seri 1389 /proc/tty/driver/serial: 1401 2: uart:ST166 1390 2: uart:ST16650V2 port:00001008 irq:18 ... 1402 1391 1403 Interaction with the 1392 Interaction with the standard serial driver is not 1404 very good. 1393 very good. 1405 1394 1406 The VGA output is eve 1395 The VGA output is eventually overwritten by 1407 the real console. 1396 the real console. 1408 1397 1409 The xen option can on 1398 The xen option can only be used in Xen domains. 1410 1399 1411 The sclp output can o 1400 The sclp output can only be used on s390. 1412 1401 1413 The bios output can o 1402 The bios output can only be used on SuperH. 1414 1403 1415 The optional "force" 1404 The optional "force" to "pciserial" enables use of a 1416 PCI device even when 1405 PCI device even when its classcode is not of the 1417 UART class. 1406 UART class. 1418 1407 1419 edac_report= [HW,EDAC] Control how 1408 edac_report= [HW,EDAC] Control how to report EDAC event 1420 Format: {"on" | "off" 1409 Format: {"on" | "off" | "force"} 1421 on: enable EDAC to re 1410 on: enable EDAC to report H/W event. May be overridden 1422 by other higher prior 1411 by other higher priority error reporting module. 1423 off: disable H/W even 1412 off: disable H/W event reporting through EDAC. 1424 force: enforce the us 1413 force: enforce the use of EDAC to report H/W event. 1425 default: on. 1414 default: on. 1426 1415 1427 edd= [EDD] 1416 edd= [EDD] 1428 Format: {"off" | "on" 1417 Format: {"off" | "on" | "skip[mbr]"} 1429 1418 1430 efi= [EFI,EARLY] !! 1419 efi= [EFI] 1431 Format: { "debug", "d 1420 Format: { "debug", "disable_early_pci_dma", 1432 "nochunk", 1421 "nochunk", "noruntime", "nosoftreserve", 1433 "novamap", 1422 "novamap", "no_disable_early_pci_dma" } 1434 debug: enable misc de 1423 debug: enable misc debug output. 1435 disable_early_pci_dma 1424 disable_early_pci_dma: disable the busmaster bit on all 1436 PCI bridges while in 1425 PCI bridges while in the EFI boot stub. 1437 nochunk: disable read 1426 nochunk: disable reading files in "chunks" in the EFI 1438 boot stub, as chunkin 1427 boot stub, as chunking can cause problems with some 1439 firmware implementati 1428 firmware implementations. 1440 noruntime : disable E 1429 noruntime : disable EFI runtime services support 1441 nosoftreserve: The EF 1430 nosoftreserve: The EFI_MEMORY_SP (Specific Purpose) 1442 attribute may cause t 1431 attribute may cause the kernel to reserve the 1443 memory range for a me 1432 memory range for a memory mapping driver to 1444 claim. Specify efi=no 1433 claim. Specify efi=nosoftreserve to disable this 1445 reservation and treat 1434 reservation and treat the memory by its base type 1446 (i.e. EFI_CONVENTIONA 1435 (i.e. EFI_CONVENTIONAL_MEMORY / "System RAM"). 1447 novamap: do not call 1436 novamap: do not call SetVirtualAddressMap(). 1448 no_disable_early_pci_ 1437 no_disable_early_pci_dma: Leave the busmaster bit set 1449 on all PCI bridges wh 1438 on all PCI bridges while in the EFI boot stub 1450 1439 1451 efi_no_storage_paranoia [EFI,X86,EARL !! 1440 efi_no_storage_paranoia [EFI; X86] 1452 Using this parameter 1441 Using this parameter you can use more than 50% of 1453 your efi variable sto 1442 your efi variable storage. Use this parameter only if 1454 you are really sure t 1443 you are really sure that your UEFI does sane gc and 1455 fulfills the spec oth 1444 fulfills the spec otherwise your board may brick. 1456 1445 >> 1446 efi_fake_mem= nn[KMG]@ss[KMG]:aa[,nn[KMG]@ss[KMG]:aa,..] [EFI; X86] >> 1447 Add arbitrary attribute to specific memory range by >> 1448 updating original EFI memory map. >> 1449 Region of memory which aa attribute is added to is >> 1450 from ss to ss+nn. >> 1451 >> 1452 If efi_fake_mem=2G@4G:0x10000,2G@0x10a0000000:0x10000 >> 1453 is specified, EFI_MEMORY_MORE_RELIABLE(0x10000) >> 1454 attribute is added to range 0x100000000-0x180000000 and >> 1455 0x10a0000000-0x1120000000. >> 1456 >> 1457 If efi_fake_mem=8G@9G:0x40000 is specified, the >> 1458 EFI_MEMORY_SP(0x40000) attribute is added to >> 1459 range 0x240000000-0x43fffffff. >> 1460 >> 1461 Using this parameter you can do debugging of EFI memmap >> 1462 related features. For example, you can do debugging of >> 1463 Address Range Mirroring feature even if your box >> 1464 doesn't support it, or mark specific memory as >> 1465 "soft reserved". >> 1466 1457 efivar_ssdt= [EFI; X86] Name of an 1467 efivar_ssdt= [EFI; X86] Name of an EFI variable that contains an SSDT 1458 that is to be dynamic 1468 that is to be dynamically loaded by Linux. If there are 1459 multiple variables wi 1469 multiple variables with the same name but with different 1460 vendor GUIDs, all of 1470 vendor GUIDs, all of them will be loaded. See 1461 Documentation/admin-g 1471 Documentation/admin-guide/acpi/ssdt-overlays.rst for details. 1462 1472 1463 1473 1464 eisa_irq_edge= [PARISC,HW] 1474 eisa_irq_edge= [PARISC,HW] 1465 See header of drivers 1475 See header of drivers/parisc/eisa.c. 1466 1476 1467 ekgdboc= [X86,KGDB,EARLY] Allo !! 1477 ekgdboc= [X86,KGDB] Allow early kernel console debugging 1468 Format: ekgdboc=kbd 1478 Format: ekgdboc=kbd 1469 1479 1470 This is designed to b 1480 This is designed to be used in conjunction with 1471 the boot argument: ea 1481 the boot argument: earlyprintk=vga 1472 1482 1473 This parameter works 1483 This parameter works in place of the kgdboc parameter 1474 but can only be used 1484 but can only be used if the backing tty is available 1475 very early in the boo 1485 very early in the boot process. For early debugging 1476 via a serial port see 1486 via a serial port see kgdboc_earlycon instead. 1477 1487 1478 elanfreq= [X86-32] 1488 elanfreq= [X86-32] 1479 See comment before fu 1489 See comment before function elanfreq_setup() in 1480 arch/x86/kernel/cpu/c 1490 arch/x86/kernel/cpu/cpufreq/elanfreq.c. 1481 1491 1482 elfcorehdr=[size[KMG]@]offset[KMG] [P !! 1492 elfcorehdr=[size[KMG]@]offset[KMG] [PPC,SH,X86,S390] 1483 Specifies physical ad 1493 Specifies physical address of start of kernel core 1484 image elf header and 1494 image elf header and optionally the size. Generally 1485 kexec loader will pas 1495 kexec loader will pass this option to capture kernel. 1486 See Documentation/adm 1496 See Documentation/admin-guide/kdump/kdump.rst for details. 1487 1497 1488 enable_mtrr_cleanup [X86,EARLY] !! 1498 enable_mtrr_cleanup [X86] 1489 The kernel tries to a 1499 The kernel tries to adjust MTRR layout from continuous 1490 to discrete, to make 1500 to discrete, to make X server driver able to add WB 1491 entry later. This par 1501 entry later. This parameter enables that. 1492 1502 1493 enable_timer_pin_1 [X86] 1503 enable_timer_pin_1 [X86] 1494 Enable PIN 1 of APIC 1504 Enable PIN 1 of APIC timer 1495 Can be useful to work 1505 Can be useful to work around chipset bugs 1496 (in particular on som 1506 (in particular on some ATI chipsets). 1497 The kernel tries to s 1507 The kernel tries to set a reasonable default. 1498 1508 1499 enforcing= [SELINUX] Set initial 1509 enforcing= [SELINUX] Set initial enforcing status. 1500 Format: {"0" | "1"} 1510 Format: {"0" | "1"} 1501 See security/selinux/ 1511 See security/selinux/Kconfig help text. 1502 0 -- permissive (log 1512 0 -- permissive (log only, no denials). 1503 1 -- enforcing (deny 1513 1 -- enforcing (deny and log). 1504 Default value is 0. 1514 Default value is 0. 1505 Value can be changed 1515 Value can be changed at runtime via 1506 /sys/fs/selinux/enfor 1516 /sys/fs/selinux/enforce. 1507 1517 1508 erst_disable [ACPI] 1518 erst_disable [ACPI] 1509 Disable Error Record 1519 Disable Error Record Serialization Table (ERST) 1510 support. 1520 support. 1511 1521 1512 ether= [HW,NET] Ethernet car 1522 ether= [HW,NET] Ethernet cards parameters 1513 This option is obsole 1523 This option is obsoleted by the "netdev=" option, which 1514 has equivalent usage. 1524 has equivalent usage. See its documentation for details. 1515 1525 1516 evm= [EVM] 1526 evm= [EVM] 1517 Format: { "fix" } 1527 Format: { "fix" } 1518 Permit 'security.evm' 1528 Permit 'security.evm' to be updated regardless of 1519 current integrity sta 1529 current integrity status. 1520 1530 1521 early_page_ext [KNL,EARLY] Enforces p !! 1531 early_page_ext [KNL] Enforces page_ext initialization to earlier 1522 stages so cover more 1532 stages so cover more early boot allocations. 1523 Please note that as s 1533 Please note that as side effect some optimizations 1524 might be disabled to 1534 might be disabled to achieve that (e.g. parallelized 1525 memory initialization 1535 memory initialization is disabled) so the boot process 1526 might take longer, es 1536 might take longer, especially on systems with a lot of 1527 memory. Available wit 1537 memory. Available with CONFIG_PAGE_EXTENSION=y. 1528 1538 1529 failslab= 1539 failslab= 1530 fail_usercopy= 1540 fail_usercopy= 1531 fail_page_alloc= 1541 fail_page_alloc= 1532 fail_make_request=[KNL] 1542 fail_make_request=[KNL] 1533 General fault injecti 1543 General fault injection mechanism. 1534 Format: <interval>,<p 1544 Format: <interval>,<probability>,<space>,<times> 1535 See also Documentatio 1545 See also Documentation/fault-injection/. 1536 1546 1537 fb_tunnels= [NET] 1547 fb_tunnels= [NET] 1538 Format: { initns | no 1548 Format: { initns | none } 1539 See Documentation/adm 1549 See Documentation/admin-guide/sysctl/net.rst for 1540 fb_tunnels_only_for_i 1550 fb_tunnels_only_for_init_ns 1541 1551 1542 floppy= [HW] 1552 floppy= [HW] 1543 See Documentation/adm 1553 See Documentation/admin-guide/blockdev/floppy.rst. 1544 1554 1545 forcepae [X86-32] 1555 forcepae [X86-32] 1546 Forcefully enable Phy 1556 Forcefully enable Physical Address Extension (PAE). 1547 Many Pentium M system 1557 Many Pentium M systems disable PAE but may have a 1548 functionally usable P 1558 functionally usable PAE implementation. 1549 Warning: use of this 1559 Warning: use of this parameter will taint the kernel 1550 and may cause unknown 1560 and may cause unknown problems. 1551 1561 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] 1562 ftrace=[tracer] 1559 [FTRACE] will set and 1563 [FTRACE] will set and start the specified tracer 1560 as early as possible 1564 as early as possible in order to facilitate early 1561 boot debugging. 1565 boot debugging. 1562 1566 1563 ftrace_boot_snapshot 1567 ftrace_boot_snapshot 1564 [FTRACE] On boot up, 1568 [FTRACE] On boot up, a snapshot will be taken of the 1565 ftrace ring buffer th 1569 ftrace ring buffer that can be read at: 1566 /sys/kernel/tracing/s 1570 /sys/kernel/tracing/snapshot. 1567 This is useful if you 1571 This is useful if you need tracing information from kernel 1568 boot up that is likel 1572 boot up that is likely to be overridden by user space 1569 start up functionalit 1573 start up functionality. 1570 1574 1571 Optionally, the snaps 1575 Optionally, the snapshot can also be defined for a tracing 1572 instance that was cre 1576 instance that was created by the trace_instance= command 1573 line parameter. 1577 line parameter. 1574 1578 1575 trace_instance=foo,sc 1579 trace_instance=foo,sched_switch ftrace_boot_snapshot=foo 1576 1580 1577 The above will cause 1581 The above will cause the "foo" tracing instance to trigger 1578 a snapshot at the end 1582 a snapshot at the end of boot up. 1579 1583 1580 ftrace_dump_on_oops[=2(orig_cpu) | =< !! 1584 ftrace_dump_on_oops[=orig_cpu] 1581 ,<instance>=2(orig_ << 1582 [FTRACE] will dump th 1585 [FTRACE] will dump the trace buffers on oops. 1583 If no parameter is pa !! 1586 If no parameter is passed, ftrace will dump 1584 buffers of all CPUs, !! 1587 buffers of all CPUs, but if you pass orig_cpu, it will 1585 will dump only the bu !! 1588 dump only the buffer of the CPU that triggered the 1586 the oops, or the spec !! 1589 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 1590 1603 ftrace_filter=[function-list] 1591 ftrace_filter=[function-list] 1604 [FTRACE] Limit the fu 1592 [FTRACE] Limit the functions traced by the function 1605 tracer at boot up. fu 1593 tracer at boot up. function-list is a comma-separated 1606 list of functions. Th 1594 list of functions. This list can be changed at run 1607 time by the set_ftrac 1595 time by the set_ftrace_filter file in the debugfs 1608 tracing directory. 1596 tracing directory. 1609 1597 1610 ftrace_notrace=[function-list] 1598 ftrace_notrace=[function-list] 1611 [FTRACE] Do not trace 1599 [FTRACE] Do not trace the functions specified in 1612 function-list. This l 1600 function-list. This list can be changed at run time 1613 by the set_ftrace_not 1601 by the set_ftrace_notrace file in the debugfs 1614 tracing directory. 1602 tracing directory. 1615 1603 1616 ftrace_graph_filter=[function-list] 1604 ftrace_graph_filter=[function-list] 1617 [FTRACE] Limit the to 1605 [FTRACE] Limit the top level callers functions traced 1618 by the function graph 1606 by the function graph tracer at boot up. 1619 function-list is a co 1607 function-list is a comma-separated list of functions 1620 that can be changed a 1608 that can be changed at run time by the 1621 set_graph_function fi 1609 set_graph_function file in the debugfs tracing directory. 1622 1610 1623 ftrace_graph_notrace=[function-list] 1611 ftrace_graph_notrace=[function-list] 1624 [FTRACE] Do not trace 1612 [FTRACE] Do not trace from the functions specified in 1625 function-list. This 1613 function-list. This list is a comma-separated list of 1626 functions that can be 1614 functions that can be changed at run time by the 1627 set_graph_notrace fil 1615 set_graph_notrace file in the debugfs tracing directory. 1628 1616 1629 ftrace_graph_max_depth=<uint> 1617 ftrace_graph_max_depth=<uint> 1630 [FTRACE] Used with th 1618 [FTRACE] Used with the function graph tracer. This is 1631 the max depth it will 1619 the max depth it will trace into a function. This value 1632 can be changed at run 1620 can be changed at run time by the max_graph_depth file 1633 in the tracefs tracin 1621 in the tracefs tracing directory. default: 0 (no limit) 1634 1622 1635 fw_devlink= [KNL,EARLY] Create de !! 1623 fw_devlink= [KNL] Create device links between consumer and supplier 1636 devices by scanning t 1624 devices by scanning the firmware to infer the 1637 consumer/supplier rel 1625 consumer/supplier relationships. This feature is 1638 especially useful whe 1626 especially useful when drivers are loaded as modules as 1639 it ensures proper ord 1627 it ensures proper ordering of tasks like device probing 1640 (suppliers first, the 1628 (suppliers first, then consumers), supplier boot state 1641 clean up (only after 1629 clean up (only after all consumers have probed), 1642 suspend/resume & runt 1630 suspend/resume & runtime PM (consumers first, then 1643 suppliers). 1631 suppliers). 1644 Format: { off | permi 1632 Format: { off | permissive | on | rpm } 1645 off -- Don't create 1633 off -- Don't create device links from firmware info. 1646 permissive -- Create 1634 permissive -- Create device links from firmware info 1647 but use it on 1635 but use it only for ordering boot state clean 1648 up (sync_stat 1636 up (sync_state() calls). 1649 on -- Create device 1637 on -- Create device links from firmware info and use it 1650 to enforce pr 1638 to enforce probe and suspend/resume ordering. 1651 rpm -- Like "on", bu 1639 rpm -- Like "on", but also use to order runtime PM. 1652 1640 1653 fw_devlink.strict=<bool> 1641 fw_devlink.strict=<bool> 1654 [KNL,EARLY] Treat all !! 1642 [KNL] Treat all inferred dependencies as mandatory 1655 dependencies. This on 1643 dependencies. This only applies for fw_devlink=on|rpm. 1656 Format: <bool> 1644 Format: <bool> 1657 1645 1658 fw_devlink.sync_state = 1646 fw_devlink.sync_state = 1659 [KNL,EARLY] When all !! 1647 [KNL] When all devices that could probe have finished 1660 probing, this paramet 1648 probing, this parameter controls what to do with 1661 devices that haven't 1649 devices that haven't yet received their sync_state() 1662 calls. 1650 calls. 1663 Format: { strict | ti 1651 Format: { strict | timeout } 1664 strict -- Default. Co 1652 strict -- Default. Continue waiting on consumers to 1665 probe success 1653 probe successfully. 1666 timeout -- Give up wa 1654 timeout -- Give up waiting on consumers and call 1667 sync_state() 1655 sync_state() on any devices that haven't yet 1668 received thei 1656 received their sync_state() calls after 1669 deferred_prob 1657 deferred_probe_timeout has expired or by 1670 late_initcall 1658 late_initcall() if !CONFIG_MODULES. 1671 1659 1672 gamecon.map[2|3]= 1660 gamecon.map[2|3]= 1673 [HW,JOY] Multisystem 1661 [HW,JOY] Multisystem joystick and NES/SNES/PSX pad 1674 support via parallel 1662 support via parallel port (up to 5 devices per port) 1675 Format: <port#>,<pad1 1663 Format: <port#>,<pad1>,<pad2>,<pad3>,<pad4>,<pad5> 1676 See also Documentatio 1664 See also Documentation/input/devices/joystick-parport.rst 1677 1665 1678 gamma= [HW,DRM] 1666 gamma= [HW,DRM] 1679 1667 1680 gart_fix_e820= [X86-64,EARLY] disabl !! 1668 gart_fix_e820= [X86-64] disable the fix e820 for K8 GART 1681 Format: off | on 1669 Format: off | on 1682 default: on 1670 default: on 1683 1671 1684 gather_data_sampling= 1672 gather_data_sampling= 1685 [X86,INTEL,EARLY] Con !! 1673 [X86,INTEL] Control the Gather Data Sampling (GDS) 1686 mitigation. 1674 mitigation. 1687 1675 1688 Gather Data Sampling 1676 Gather Data Sampling is a hardware vulnerability which 1689 allows unprivileged s 1677 allows unprivileged speculative access to data which was 1690 previously stored in 1678 previously stored in vector registers. 1691 1679 1692 This issue is mitigat 1680 This issue is mitigated by default in updated microcode. 1693 The mitigation may ha 1681 The mitigation may have a performance impact but can be 1694 disabled. On systems 1682 disabled. On systems without the microcode mitigation 1695 disabling AVX serves 1683 disabling AVX serves as a mitigation. 1696 1684 1697 force: Disable AVX t 1685 force: Disable AVX to mitigate systems without 1698 microcode mit 1686 microcode mitigation. No effect if the microcode 1699 mitigation is 1687 mitigation is present. Known to cause crashes in 1700 userspace wit 1688 userspace with buggy AVX enumeration. 1701 1689 1702 off: Disable GDS m 1690 off: Disable GDS mitigation. 1703 1691 1704 gcov_persist= [GCOV] When non-zero 1692 gcov_persist= [GCOV] When non-zero (default), profiling data for 1705 kernel modules is sav 1693 kernel modules is saved and remains accessible via 1706 debugfs, even when th 1694 debugfs, even when the module is unloaded/reloaded. 1707 When zero, profiling 1695 When zero, profiling data is discarded and associated 1708 debugfs files are rem 1696 debugfs files are removed at module unload time. 1709 1697 1710 goldfish [X86] Enable the gold 1698 goldfish [X86] Enable the goldfish android emulator platform. 1711 Don't use this when y 1699 Don't use this when you are not running on the 1712 android emulator 1700 android emulator 1713 1701 1714 gpio-mockup.gpio_mockup_ranges 1702 gpio-mockup.gpio_mockup_ranges 1715 [HW] Sets the ranges 1703 [HW] Sets the ranges of gpiochip of for this device. 1716 Format: <start1>,<end 1704 Format: <start1>,<end1>,<start2>,<end2>... 1717 gpio-mockup.gpio_mockup_named_lines 1705 gpio-mockup.gpio_mockup_named_lines 1718 [HW] Let the driver k 1706 [HW] Let the driver know GPIO lines should be named. 1719 1707 1720 gpt [EFI] Forces disk wit 1708 gpt [EFI] Forces disk with valid GPT signature but 1721 invalid Protective MB 1709 invalid Protective MBR to be treated as GPT. If the 1722 primary GPT is corrup 1710 primary GPT is corrupted, it enables the backup/alternate 1723 GPT to be used instea 1711 GPT to be used instead. 1724 1712 1725 grcan.enable0= [HW] Configuration of 1713 grcan.enable0= [HW] Configuration of physical interface 0. Determines 1726 the "Enable 0" bit of 1714 the "Enable 0" bit of the configuration register. 1727 Format: 0 | 1 1715 Format: 0 | 1 1728 Default: 0 1716 Default: 0 1729 grcan.enable1= [HW] Configuration of 1717 grcan.enable1= [HW] Configuration of physical interface 1. Determines 1730 the "Enable 0" bit of 1718 the "Enable 0" bit of the configuration register. 1731 Format: 0 | 1 1719 Format: 0 | 1 1732 Default: 0 1720 Default: 0 1733 grcan.select= [HW] Select which phy 1721 grcan.select= [HW] Select which physical interface to use. 1734 Format: 0 | 1 1722 Format: 0 | 1 1735 Default: 0 1723 Default: 0 1736 grcan.txsize= [HW] Sets the size of 1724 grcan.txsize= [HW] Sets the size of the tx buffer. 1737 Format: <unsigned int 1725 Format: <unsigned int> such that (txsize & ~0x1fffc0) == 0. 1738 Default: 1024 1726 Default: 1024 1739 grcan.rxsize= [HW] Sets the size of 1727 grcan.rxsize= [HW] Sets the size of the rx buffer. 1740 Format: <unsigned int 1728 Format: <unsigned int> such that (rxsize & ~0x1fffc0) == 0. 1741 Default: 1024 1729 Default: 1024 1742 1730 1743 hardened_usercopy= 1731 hardened_usercopy= 1744 [KNL] Under CONFIG_HA 1732 [KNL] Under CONFIG_HARDENED_USERCOPY, whether 1745 hardening is enabled 1733 hardening is enabled for this boot. Hardened 1746 usercopy checking is 1734 usercopy checking is used to protect the kernel 1747 from reading or writi 1735 from reading or writing beyond known memory 1748 allocation boundaries 1736 allocation boundaries as a proactive defense 1749 against bounds-checki 1737 against bounds-checking flaws in the kernel's 1750 copy_to_user()/copy_f 1738 copy_to_user()/copy_from_user() interface. 1751 on Perform hardened user 1739 on Perform hardened usercopy checks (default). 1752 off Disable hardened user 1740 off Disable hardened usercopy checks. 1753 1741 1754 hardlockup_all_cpu_backtrace= 1742 hardlockup_all_cpu_backtrace= 1755 [KNL] Should the hard 1743 [KNL] Should the hard-lockup detector generate 1756 backtraces on all cpu 1744 backtraces on all cpus. 1757 Format: 0 | 1 1745 Format: 0 | 1 1758 1746 1759 hashdist= [KNL,NUMA] Large hash 1747 hashdist= [KNL,NUMA] Large hashes allocated during boot 1760 are distributed acros 1748 are distributed across NUMA nodes. Defaults on 1761 for 64-bit NUMA, off 1749 for 64-bit NUMA, off otherwise. 1762 Format: 0 | 1 (for of 1750 Format: 0 | 1 (for off | on) 1763 1751 >> 1752 hcl= [IA-64] SGI's Hardware Graph compatibility layer >> 1753 1764 hd= [EIDE] (E)IDE hard dr 1754 hd= [EIDE] (E)IDE hard drive subsystem geometry 1765 Format: <cyl>,<head>, 1755 Format: <cyl>,<head>,<sect> 1766 1756 1767 hest_disable [ACPI] 1757 hest_disable [ACPI] 1768 Disable Hardware Erro 1758 Disable Hardware Error Source Table (HEST) support; 1769 corresponding firmwar 1759 corresponding firmware-first mode error processing 1770 logic will be disable 1760 logic will be disabled. 1771 1761 1772 hibernate= [HIBERNATION] 1762 hibernate= [HIBERNATION] 1773 noresume Don't check i 1763 noresume Don't check if there's a hibernation image 1774 present durin 1764 present during boot. 1775 nocompress Don't compres 1765 nocompress Don't compress/decompress hibernation images. 1776 no Disable hiber 1766 no Disable hibernation and resume. 1777 protect_image Turn on image 1767 protect_image Turn on image protection during restoration 1778 (that will se 1768 (that will set all pages holding image data 1779 during restor 1769 during restoration read-only). 1780 1770 1781 hibernate.compressor= [HIBERNATION] !! 1771 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 1772 size of <nn>. This works even on boxes that have no 1794 highmem otherwise. Th 1773 highmem otherwise. This also works to reduce highmem 1795 size on bigger boxes. 1774 size on bigger boxes. 1796 1775 1797 highres= [KNL] Enable/disable 1776 highres= [KNL] Enable/disable high resolution timer mode. 1798 Valid parameters: "on 1777 Valid parameters: "on", "off" 1799 Default: "on" 1778 Default: "on" 1800 1779 1801 hlt [BUGS=ARM,SH] 1780 hlt [BUGS=ARM,SH] 1802 1781 1803 hostname= [KNL,EARLY] Set the h !! 1782 hostname= [KNL] Set the hostname (aka UTS nodename). 1804 Format: <string> 1783 Format: <string> 1805 This allows setting t 1784 This allows setting the system's hostname during early 1806 startup. This sets th 1785 startup. This sets the name returned by gethostname. 1807 Using this parameter 1786 Using this parameter to set the hostname makes it 1808 possible to ensure th 1787 possible to ensure the hostname is correctly set before 1809 any userspace process 1788 any userspace processes run, avoiding the possibility 1810 that a process may ca 1789 that a process may call gethostname before the hostname 1811 has been explicitly s 1790 has been explicitly set, resulting in the calling 1812 process getting an in 1791 process getting an incorrect result. The string must 1813 not exceed the maximu 1792 not exceed the maximum allowed hostname length (usually 1814 64 characters) and wi 1793 64 characters) and will be truncated otherwise. 1815 1794 1816 hpet= [X86-32,HPET] option 1795 hpet= [X86-32,HPET] option to control HPET usage 1817 Format: { enable (def 1796 Format: { enable (default) | disable | force | 1818 verbose } 1797 verbose } 1819 disable: disable HPET 1798 disable: disable HPET and use PIT instead 1820 force: allow force en 1799 force: allow force enabled of undocumented chips (ICH4, 1821 VIA, nVidia) 1800 VIA, nVidia) 1822 verbose: show content 1801 verbose: show contents of HPET registers during setup 1823 1802 1824 hpet_mmap= [X86, HPET_MMAP] Allo 1803 hpet_mmap= [X86, HPET_MMAP] Allow userspace to mmap HPET 1825 registers. Default s 1804 registers. Default set by CONFIG_HPET_MMAP_DEFAULT. 1826 1805 1827 hugepages= [HW] Number of HugeTL 1806 hugepages= [HW] Number of HugeTLB pages to allocate at boot. 1828 If this follows hugep 1807 If this follows hugepagesz (below), it specifies 1829 the number of pages o 1808 the number of pages of hugepagesz to be allocated. 1830 If this is the first 1809 If this is the first HugeTLB parameter on the command 1831 line, it specifies th 1810 line, it specifies the number of pages to allocate for 1832 the default huge page 1811 the default huge page size. If using node format, the 1833 number of pages to al 1812 number of pages to allocate per-node can be specified. 1834 See also Documentatio 1813 See also Documentation/admin-guide/mm/hugetlbpage.rst. 1835 Format: <integer> or 1814 Format: <integer> or (node format) 1836 <node>:<integ 1815 <node>:<integer>[,<node>:<integer>] 1837 1816 1838 hugepagesz= 1817 hugepagesz= 1839 [HW] The size of the 1818 [HW] The size of the HugeTLB pages. This is used in 1840 conjunction with huge 1819 conjunction with hugepages (above) to allocate huge 1841 pages of a specific s 1820 pages of a specific size at boot. The pair 1842 hugepagesz=X hugepage 1821 hugepagesz=X hugepages=Y can be specified once for 1843 each supported huge p 1822 each supported huge page size. Huge page sizes are 1844 architecture dependen 1823 architecture dependent. See also 1845 Documentation/admin-g 1824 Documentation/admin-guide/mm/hugetlbpage.rst. 1846 Format: size[KMG] 1825 Format: size[KMG] 1847 1826 1848 hugetlb_cma= [HW,CMA,EARLY] The si !! 1827 hugetlb_cma= [HW,CMA] The size of a CMA area used for allocation 1849 of gigantic hugepages 1828 of gigantic hugepages. Or using node format, the size 1850 of a CMA area per nod 1829 of a CMA area per node can be specified. 1851 Format: nn[KMGTPE] or 1830 Format: nn[KMGTPE] or (node format) 1852 <node>:nn[KMG 1831 <node>:nn[KMGTPE][,<node>:nn[KMGTPE]] 1853 1832 1854 Reserve a CMA area of 1833 Reserve a CMA area of given size and allocate gigantic 1855 hugepages using the C 1834 hugepages using the CMA allocator. If enabled, the 1856 boot-time allocation 1835 boot-time allocation of gigantic hugepages is skipped. 1857 1836 1858 hugetlb_free_vmemmap= 1837 hugetlb_free_vmemmap= 1859 [KNL] Requires CONFIG 1838 [KNL] Requires CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP 1860 enabled. 1839 enabled. 1861 Control if HugeTLB Vm 1840 Control if HugeTLB Vmemmap Optimization (HVO) is enabled. 1862 Allows heavy hugetlb 1841 Allows heavy hugetlb users to free up some more 1863 memory (7 * PAGE_SIZE 1842 memory (7 * PAGE_SIZE for each 2MB hugetlb page). 1864 Format: { on | off (d 1843 Format: { on | off (default) } 1865 1844 1866 on: enable HVO 1845 on: enable HVO 1867 off: disable HVO 1846 off: disable HVO 1868 1847 1869 Built with CONFIG_HUG 1848 Built with CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP_DEFAULT_ON=y, 1870 the default is on. 1849 the default is on. 1871 1850 1872 Note that the vmemmap 1851 Note that the vmemmap pages may be allocated from the added 1873 memory block itself w 1852 memory block itself when memory_hotplug.memmap_on_memory is 1874 enabled, those vmemma 1853 enabled, those vmemmap pages cannot be optimized even if this 1875 feature is enabled. 1854 feature is enabled. Other vmemmap pages not allocated from 1876 the added memory bloc 1855 the added memory block itself do not be affected. 1877 1856 1878 hung_task_panic= 1857 hung_task_panic= 1879 [KNL] Should the hung 1858 [KNL] Should the hung task detector generate panics. 1880 Format: 0 | 1 1859 Format: 0 | 1 1881 1860 1882 A value of 1 instruct 1861 A value of 1 instructs the kernel to panic when a 1883 hung task is detected 1862 hung task is detected. The default value is controlled 1884 by the CONFIG_BOOTPAR 1863 by the CONFIG_BOOTPARAM_HUNG_TASK_PANIC build-time 1885 option. The value sel 1864 option. The value selected by this boot parameter can 1886 be changed later by t 1865 be changed later by the kernel.hung_task_panic sysctl. 1887 1866 1888 hvc_iucv= [S390] Number of z/V 1867 hvc_iucv= [S390] Number of z/VM IUCV hypervisor console (HVC) 1889 terminal devi 1868 terminal devices. Valid values: 0..8 1890 hvc_iucv_allow= [S390] Comma-separat 1869 hvc_iucv_allow= [S390] Comma-separated list of z/VM user IDs. 1891 If specified, 1870 If specified, z/VM IUCV HVC accepts connections 1892 from listed z 1871 from listed z/VM user IDs only. 1893 1872 1894 hv_nopvspin [X86,HYPER_V,EARLY] !! 1873 hv_nopvspin [X86,HYPER_V] Disables the paravirt spinlock optimizations 1895 Disables the paravirt !! 1874 which allow the hypervisor to 'idle' the 1896 which allow the hyper !! 1875 guest on lock contention. 1897 on lock contention. << 1898 1876 1899 i2c_bus= [HW] Override the 1877 i2c_bus= [HW] Override the default board specific I2C bus speed 1900 or register a 1878 or register an additional I2C bus that is not 1901 registered fr 1879 registered from board initialization code. 1902 Format: 1880 Format: 1903 <bus_id>,<clk 1881 <bus_id>,<clkrate> 1904 1882 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 1883 i8042.debug [HW] Toggle i8042 debug mode 1928 i8042.unmask_kbd_data 1884 i8042.unmask_kbd_data 1929 [HW] Enable printing 1885 [HW] Enable printing of interrupt data from the KBD port 1930 (disabled by def 1886 (disabled by default, and as a pre-condition 1931 requires that i8 1887 requires that i8042.debug=1 be enabled) 1932 i8042.direct [HW] Put keyboard por 1888 i8042.direct [HW] Put keyboard port into non-translated mode 1933 i8042.dumbkbd [HW] Pretend that con 1889 i8042.dumbkbd [HW] Pretend that controller can only read data from 1934 keyboard and can 1890 keyboard and cannot control its state 1935 (Don't attempt t 1891 (Don't attempt to blink the leds) 1936 i8042.noaux [HW] Don't check for 1892 i8042.noaux [HW] Don't check for auxiliary (== mouse) port 1937 i8042.nokbd [HW] Don't check/crea 1893 i8042.nokbd [HW] Don't check/create keyboard port 1938 i8042.noloop [HW] Disable the AUX 1894 i8042.noloop [HW] Disable the AUX Loopback command while probing 1939 for the AUX port 1895 for the AUX port 1940 i8042.nomux [HW] Don't check pres 1896 i8042.nomux [HW] Don't check presence of an active multiplexing 1941 controller 1897 controller 1942 i8042.nopnp [HW] Don't use ACPIPn 1898 i8042.nopnp [HW] Don't use ACPIPnP / PnPBIOS to discover KBD/AUX 1943 controllers 1899 controllers 1944 i8042.notimeout [HW] Ignore timeout c 1900 i8042.notimeout [HW] Ignore timeout condition signalled by controller 1945 i8042.reset [HW] Reset the contro 1901 i8042.reset [HW] Reset the controller during init, cleanup and 1946 suspend-to-ram t 1902 suspend-to-ram transitions, only during s2r 1947 transitions, or 1903 transitions, or never reset 1948 Format: { 1 | Y | y | 1904 Format: { 1 | Y | y | 0 | N | n } 1949 1, Y, y: always reset 1905 1, Y, y: always reset controller 1950 0, N, n: don't ever r 1906 0, N, n: don't ever reset controller 1951 Default: only on s2r 1907 Default: only on s2r transitions on x86; most other 1952 architectures force r 1908 architectures force reset to be always executed 1953 i8042.unlock [HW] Unlock (ignore) 1909 i8042.unlock [HW] Unlock (ignore) the keylock 1954 i8042.kbdreset [HW] Reset device con 1910 i8042.kbdreset [HW] Reset device connected to KBD port 1955 i8042.probe_defer 1911 i8042.probe_defer 1956 [HW] Allow deferred p 1912 [HW] Allow deferred probing upon i8042 probe errors 1957 1913 1958 i810= [HW,DRM] 1914 i810= [HW,DRM] 1959 1915 1960 i915.invert_brightness= 1916 i915.invert_brightness= 1961 [DRM] Invert the sens 1917 [DRM] Invert the sense of the variable that is used to 1962 set the brightness of 1918 set the brightness of the panel backlight. Normally a 1963 brightness value of 0 1919 brightness value of 0 indicates backlight switched off, 1964 and the maximum of th 1920 and the maximum of the brightness value sets the backlight 1965 to maximum brightness 1921 to maximum brightness. If this parameter is set to 0 1966 (default) and the mac 1922 (default) and the machine requires it, or this parameter 1967 is set to 1, a bright 1923 is set to 1, a brightness value of 0 sets the backlight 1968 to maximum brightness 1924 to maximum brightness, and the maximum of the brightness 1969 value switches the ba 1925 value switches the backlight off. 1970 -1 -- never invert br 1926 -1 -- never invert brightness 1971 0 -- machine default 1927 0 -- machine default 1972 1 -- force brightnes 1928 1 -- force brightness inversion 1973 1929 1974 ia32_emulation= [X86-64] 1930 ia32_emulation= [X86-64] 1975 Format: <bool> 1931 Format: <bool> 1976 When true, allows loa 1932 When true, allows loading 32-bit programs and executing 32-bit 1977 syscalls, essentially 1933 syscalls, essentially overriding IA32_EMULATION_DEFAULT_DISABLED at 1978 boot time. When false 1934 boot time. When false, unconditionally disables IA32 emulation. 1979 1935 1980 icn= [HW,ISDN] 1936 icn= [HW,ISDN] 1981 Format: <io>[,<membas 1937 Format: <io>[,<membase>[,<icn_id>[,<icn_id2>]]] 1982 1938 1983 1939 1984 idle= [X86,EARLY] !! 1940 idle= [X86] 1985 Format: idle=poll, id 1941 Format: idle=poll, idle=halt, idle=nomwait 1986 Poll forces a polling 1942 Poll forces a polling idle loop that can slightly 1987 improve the performan 1943 improve the performance of waking up a idle CPU, but 1988 will use a lot of pow 1944 will use a lot of power and make the system run hot. 1989 Not recommended. 1945 Not recommended. 1990 idle=halt: Halt is fo 1946 idle=halt: Halt is forced to be used for CPU idle. 1991 In such case C2/C3 wo 1947 In such case C2/C3 won't be used again. 1992 idle=nomwait: Disable 1948 idle=nomwait: Disable mwait for CPU C-states 1993 1949 1994 idxd.sva= [HW] 1950 idxd.sva= [HW] 1995 Format: <bool> 1951 Format: <bool> 1996 Allow force disabling 1952 Allow force disabling of Shared Virtual Memory (SVA) 1997 support for the idxd 1953 support for the idxd driver. By default it is set to 1998 true (1). 1954 true (1). 1999 1955 2000 idxd.tc_override= [HW] 1956 idxd.tc_override= [HW] 2001 Format: <bool> 1957 Format: <bool> 2002 Allow override of def 1958 Allow override of default traffic class configuration 2003 for the device. By de 1959 for the device. By default it is set to false (0). 2004 1960 2005 ieee754= [MIPS] Select IEEE St 1961 ieee754= [MIPS] Select IEEE Std 754 conformance mode 2006 Format: { strict | le !! 1962 Format: { strict | legacy | 2008 | relaxed } 2007 Default: strict 1963 Default: strict 2008 1964 2009 Choose which programs 1965 Choose which programs will be accepted for execution 2010 based on the IEEE 754 1966 based on the IEEE 754 NaN encoding(s) supported by 2011 the FPU and the NaN e 1967 the FPU and the NaN encoding requested with the value 2012 of an ELF file header 1968 of an ELF file header flag individually set by each 2013 binary. Hardware imp 1969 binary. Hardware implementations are permitted to 2014 support either or bot 1970 support either or both of the legacy and the 2008 NaN 2015 encoding mode. 1971 encoding mode. 2016 1972 2017 Available settings ar 1973 Available settings are as follows: 2018 strict accept binari 1974 strict accept binaries that request a NaN encoding 2019 supported by 1975 supported by the FPU 2020 legacy only accept l 1976 legacy only accept legacy-NaN binaries, if supported 2021 by the FPU 1977 by the FPU 2022 2008 only accept 2 1978 2008 only accept 2008-NaN binaries, if supported 2023 by the FPU 1979 by the FPU 2024 relaxed accept any bi 1980 relaxed accept any binaries regardless of whether 2025 supported by 1981 supported by the FPU 2026 emulated accept any b << 2027 if binary mod << 2028 1982 2029 The FPU emulator is a 1983 The FPU emulator is always able to support both NaN 2030 encodings, so if no F 1984 encodings, so if no FPU hardware is present or it has 2031 been disabled with 'n 1985 been disabled with 'nofpu', then the settings of 2032 'legacy' and '2008' s 1986 'legacy' and '2008' strap the emulator accordingly, 2033 'relaxed' straps the 1987 'relaxed' straps the emulator for both legacy-NaN and 2034 2008-NaN, whereas 'st 1988 2008-NaN, whereas 'strict' enables legacy-NaN only on 2035 legacy processors and 1989 legacy processors and both NaN encodings on MIPS32 or 2036 MIPS64 CPUs. 1990 MIPS64 CPUs. 2037 1991 2038 The setting for ABS.f 1992 The setting for ABS.fmt/NEG.fmt instruction execution 2039 mode generally follow 1993 mode generally follows that for the NaN encoding, 2040 except where unsuppor 1994 except where unsupported by hardware. 2041 1995 2042 ignore_loglevel [KNL,EARLY] !! 1996 ignore_loglevel [KNL] 2043 Ignore loglevel setti 1997 Ignore loglevel setting - this will print /all/ 2044 kernel messages to th 1998 kernel messages to the console. Useful for debugging. 2045 We also add it as pri 1999 We also add it as printk module parameter, so users 2046 could change it dynam 2000 could change it dynamically, usually by 2047 /sys/module/printk/pa 2001 /sys/module/printk/parameters/ignore_loglevel. 2048 2002 2049 ignore_rlimit_data 2003 ignore_rlimit_data 2050 Ignore RLIMIT_DATA se 2004 Ignore RLIMIT_DATA setting for data mappings, 2051 print warning at firs 2005 print warning at first misuse. Can be changed via 2052 /sys/module/kernel/pa 2006 /sys/module/kernel/parameters/ignore_rlimit_data. 2053 2007 2054 ihash_entries= [KNL] 2008 ihash_entries= [KNL] 2055 Set number of hash bu 2009 Set number of hash buckets for inode cache. 2056 2010 2057 ima_appraise= [IMA] appraise integr 2011 ima_appraise= [IMA] appraise integrity measurements 2058 Format: { "off" | "en 2012 Format: { "off" | "enforce" | "fix" | "log" } 2059 default: "enforce" 2013 default: "enforce" 2060 2014 2061 ima_appraise_tcb [IMA] Deprecated. U 2015 ima_appraise_tcb [IMA] Deprecated. Use ima_policy= instead. 2062 The builtin appraise 2016 The builtin appraise policy appraises all files 2063 owned by uid=0. 2017 owned by uid=0. 2064 2018 2065 ima_canonical_fmt [IMA] 2019 ima_canonical_fmt [IMA] 2066 Use the canonical for 2020 Use the canonical format for the binary runtime 2067 measurements, instead 2021 measurements, instead of host native format. 2068 2022 2069 ima_hash= [IMA] 2023 ima_hash= [IMA] 2070 Format: { md5 | sha1 2024 Format: { md5 | sha1 | rmd160 | sha256 | sha384 2071 | sha512 | 2025 | sha512 | ... } 2072 default: "sha1" 2026 default: "sha1" 2073 2027 2074 The list of supported 2028 The list of supported hash algorithms is defined 2075 in crypto/hash_info.h 2029 in crypto/hash_info.h. 2076 2030 2077 ima_policy= [IMA] 2031 ima_policy= [IMA] 2078 The builtin policies 2032 The builtin policies to load during IMA setup. 2079 Format: "tcb | apprai 2033 Format: "tcb | appraise_tcb | secure_boot | 2080 fail_securel 2034 fail_securely | critical_data" 2081 2035 2082 The "tcb" policy meas 2036 The "tcb" policy measures all programs exec'd, files 2083 mmap'd for exec, and 2037 mmap'd for exec, and all files opened with the read 2084 mode bit set by eithe 2038 mode bit set by either the effective uid (euid=0) or 2085 uid=0. 2039 uid=0. 2086 2040 2087 The "appraise_tcb" po 2041 The "appraise_tcb" policy appraises the integrity of 2088 all files owned by ro 2042 all files owned by root. 2089 2043 2090 The "secure_boot" pol 2044 The "secure_boot" policy appraises the integrity 2091 of files (eg. kexec k 2045 of files (eg. kexec kernel image, kernel modules, 2092 firmware, policy, etc 2046 firmware, policy, etc) based on file signatures. 2093 2047 2094 The "fail_securely" p 2048 The "fail_securely" policy forces file signature 2095 verification failure 2049 verification failure also on privileged mounted 2096 filesystems with the 2050 filesystems with the SB_I_UNVERIFIABLE_SIGNATURE 2097 flag. 2051 flag. 2098 2052 2099 The "critical_data" p 2053 The "critical_data" policy measures kernel integrity 2100 critical data. 2054 critical data. 2101 2055 2102 ima_tcb [IMA] Deprecated. Us 2056 ima_tcb [IMA] Deprecated. Use ima_policy= instead. 2103 Load a policy which m 2057 Load a policy which meets the needs of the Trusted 2104 Computing Base. This 2058 Computing Base. This means IMA will measure all 2105 programs exec'd, file 2059 programs exec'd, files mmap'd for exec, and all files 2106 opened for read by ui 2060 opened for read by uid=0. 2107 2061 2108 ima_template= [IMA] 2062 ima_template= [IMA] 2109 Select one of defined 2063 Select one of defined IMA measurements template formats. 2110 Formats: { "ima" | "i 2064 Formats: { "ima" | "ima-ng" | "ima-ngv2" | "ima-sig" | 2111 "ima-sigv2 2065 "ima-sigv2" } 2112 Default: "ima-ng" 2066 Default: "ima-ng" 2113 2067 2114 ima_template_fmt= 2068 ima_template_fmt= 2115 [IMA] Define a custom 2069 [IMA] Define a custom template format. 2116 Format: { "field1|... 2070 Format: { "field1|...|fieldN" } 2117 2071 2118 ima.ahash_minsize= [IMA] Minimum file 2072 ima.ahash_minsize= [IMA] Minimum file size for asynchronous hash usage 2119 Format: <min_file_siz 2073 Format: <min_file_size> 2120 Set the minimal file 2074 Set the minimal file size for using asynchronous hash. 2121 If left unspecified, 2075 If left unspecified, ahash usage is disabled. 2122 2076 2123 ahash performance var 2077 ahash performance varies for different data sizes on 2124 different crypto acce 2078 different crypto accelerators. This option can be used 2125 to achieve the best p 2079 to achieve the best performance for a particular HW. 2126 2080 2127 ima.ahash_bufsize= [IMA] Asynchronous 2081 ima.ahash_bufsize= [IMA] Asynchronous hash buffer size 2128 Format: <bufsize> 2082 Format: <bufsize> 2129 Set hashing buffer si 2083 Set hashing buffer size. Default: 4k. 2130 2084 2131 ahash performance var 2085 ahash performance varies for different chunk sizes on 2132 different crypto acce 2086 different crypto accelerators. This option can be used 2133 to achieve best perfo 2087 to achieve best performance for particular HW. 2134 2088 2135 init= [KNL] 2089 init= [KNL] 2136 Format: <full_path> 2090 Format: <full_path> 2137 Run specified binary 2091 Run specified binary instead of /sbin/init as init 2138 process. 2092 process. 2139 2093 2140 initcall_debug [KNL] Trace initcalls 2094 initcall_debug [KNL] Trace initcalls as they are executed. Useful 2141 for working out where 2095 for working out where the kernel is dying during 2142 startup. 2096 startup. 2143 2097 2144 initcall_blacklist= [KNL] Do not exe 2098 initcall_blacklist= [KNL] Do not execute a comma-separated list of 2145 initcall functions. 2099 initcall functions. Useful for debugging built-in 2146 modules and initcalls 2100 modules and initcalls. 2147 2101 2148 initramfs_async= [KNL] 2102 initramfs_async= [KNL] 2149 Format: <bool> 2103 Format: <bool> 2150 Default: 1 2104 Default: 1 2151 This parameter contro 2105 This parameter controls whether the initramfs 2152 image is unpacked asy 2106 image is unpacked asynchronously, concurrently 2153 with devices being pr 2107 with devices being probed and 2154 initialized. This sho 2108 initialized. This should normally just work, 2155 but as a debugging ai 2109 but as a debugging aid, one can get the 2156 historical behaviour 2110 historical behaviour of the initramfs 2157 unpacking being compl 2111 unpacking being completed before device_ and 2158 late_ initcalls. 2112 late_ initcalls. 2159 2113 2160 initrd= [BOOT,EARLY] Specify !! 2114 initrd= [BOOT] Specify the location of the initial ramdisk 2161 2115 2162 initrdmem= [KNL,EARLY] Specify a !! 2116 initrdmem= [KNL] Specify a physical address and size from which to 2163 load the initrd. If a 2117 load the initrd. If an initrd is compiled in or 2164 specified in the boot 2118 specified in the bootparams, it takes priority over this 2165 setting. 2119 setting. 2166 Format: ss[KMG],nn[KM 2120 Format: ss[KMG],nn[KMG] 2167 Default is 0, 0 2121 Default is 0, 0 2168 2122 2169 init_on_alloc= [MM,EARLY] Fill newly !! 2123 init_on_alloc= [MM] Fill newly allocated pages and heap objects with 2170 zeroes. 2124 zeroes. 2171 Format: 0 | 1 2125 Format: 0 | 1 2172 Default set by CONFIG 2126 Default set by CONFIG_INIT_ON_ALLOC_DEFAULT_ON. 2173 2127 2174 init_on_free= [MM,EARLY] Fill freed !! 2128 init_on_free= [MM] Fill freed pages and heap objects with zeroes. 2175 Format: 0 | 1 2129 Format: 0 | 1 2176 Default set by CONFIG 2130 Default set by CONFIG_INIT_ON_FREE_DEFAULT_ON. 2177 2131 2178 init_pkru= [X86] Specify the def 2132 init_pkru= [X86] Specify the default memory protection keys rights 2179 register contents for 2133 register contents for all processes. 0x55555554 by 2180 default (disallow acc 2134 default (disallow access to all but pkey 0). Can 2181 override in debugfs a 2135 override in debugfs after boot. 2182 2136 2183 inport.irq= [HW] Inport (ATI XL a 2137 inport.irq= [HW] Inport (ATI XL and Microsoft) busmouse driver 2184 Format: <irq> 2138 Format: <irq> 2185 2139 2186 int_pln_enable [X86] Enable power li 2140 int_pln_enable [X86] Enable power limit notification interrupt 2187 2141 2188 integrity_audit=[IMA] 2142 integrity_audit=[IMA] 2189 Format: { "0" | "1" } 2143 Format: { "0" | "1" } 2190 0 -- basic integrity 2144 0 -- basic integrity auditing messages. (Default) 2191 1 -- additional integ 2145 1 -- additional integrity auditing messages. 2192 2146 2193 intel_iommu= [DMAR] Intel IOMMU dr 2147 intel_iommu= [DMAR] Intel IOMMU driver (DMAR) option 2194 on 2148 on 2195 Enable intel iommu dr 2149 Enable intel iommu driver. 2196 off 2150 off 2197 Disable intel iommu d 2151 Disable intel iommu driver. 2198 igfx_off [Default Off] 2152 igfx_off [Default Off] 2199 By default, gfx is ma 2153 By default, gfx is mapped as normal device. If a gfx 2200 device has a dedicate 2154 device has a dedicated DMAR unit, the DMAR unit is 2201 bypassed by not enabl 2155 bypassed by not enabling DMAR with this option. In 2202 this case, gfx device 2156 this case, gfx device will use physical address for 2203 DMA. 2157 DMA. 2204 strict [Default Off] 2158 strict [Default Off] 2205 Deprecated, equivalen 2159 Deprecated, equivalent to iommu.strict=1. 2206 sp_off [Default Off] 2160 sp_off [Default Off] 2207 By default, super pag 2161 By default, super page will be supported if Intel IOMMU 2208 has the capability. W 2162 has the capability. With this option, super page will 2209 not be supported. 2163 not be supported. 2210 sm_on 2164 sm_on 2211 Enable the Intel IOMM 2165 Enable the Intel IOMMU scalable mode if the hardware 2212 advertises that it ha 2166 advertises that it has support for the scalable mode 2213 translation. 2167 translation. 2214 sm_off 2168 sm_off 2215 Disallow use of the I 2169 Disallow use of the Intel IOMMU scalable mode. 2216 tboot_noforce [Default Off] 2170 tboot_noforce [Default Off] 2217 Do not force the Inte 2171 Do not force the Intel IOMMU enabled under tboot. 2218 By default, tboot wil 2172 By default, tboot will force Intel IOMMU on, which 2219 could harm performanc 2173 could harm performance of some high-throughput 2220 devices like 40GBit n 2174 devices like 40GBit network cards, even if identity 2221 mapping is enabled. 2175 mapping is enabled. 2222 Note that using this 2176 Note that using this option lowers the security 2223 provided by tboot bec 2177 provided by tboot because it makes the system 2224 vulnerable to DMA att 2178 vulnerable to DMA attacks. 2225 2179 2226 intel_idle.max_cstate= [KNL,HW,ACPI, 2180 intel_idle.max_cstate= [KNL,HW,ACPI,X86] 2227 0 disables inte 2181 0 disables intel_idle and fall back on acpi_idle. 2228 1 to 9 specify maxim 2182 1 to 9 specify maximum depth of C-state. 2229 2183 2230 intel_pstate= [X86,EARLY] !! 2184 intel_pstate= [X86] 2231 disable 2185 disable 2232 Do not enable intel 2186 Do not enable intel_pstate as the default 2233 scaling driver for 2187 scaling driver for the supported processors 2234 active 2188 active 2235 Use intel_pstate dr 2189 Use intel_pstate driver to bypass the scaling 2236 governors layer of 2190 governors layer of cpufreq and provides it own 2237 algorithms for p-st 2191 algorithms for p-state selection. There are two 2238 P-state selection a 2192 P-state selection algorithms provided by 2239 intel_pstate in the 2193 intel_pstate in the active mode: powersave and 2240 performance. The w 2194 performance. The way they both operate depends 2241 on whether or not t 2195 on whether or not the hardware managed P-states 2242 (HWP) feature has b 2196 (HWP) feature has been enabled in the processor 2243 and possibly on the 2197 and possibly on the processor model. 2244 passive 2198 passive 2245 Use intel_pstate as 2199 Use intel_pstate as a scaling driver, but configure it 2246 to work with generi 2200 to work with generic cpufreq governors (instead of 2247 enabling its intern 2201 enabling its internal governor). This mode cannot be 2248 used along with the 2202 used along with the hardware-managed P-states (HWP) 2249 feature. 2203 feature. 2250 force 2204 force 2251 Enable intel_pstate 2205 Enable intel_pstate on systems that prohibit it by default 2252 in favor of acpi-cp 2206 in favor of acpi-cpufreq. Forcing the intel_pstate driver 2253 instead of acpi-cpu 2207 instead of acpi-cpufreq may disable platform features, such 2254 as thermal controls 2208 as thermal controls and power capping, that rely on ACPI 2255 P-States informatio 2209 P-States information being indicated to OSPM and therefore 2256 should be used with 2210 should be used with caution. This option does not work with 2257 processors that are 2211 processors that aren't supported by the intel_pstate driver 2258 or on platforms tha 2212 or on platforms that use pcc-cpufreq instead of acpi-cpufreq. 2259 no_hwp 2213 no_hwp 2260 Do not enable hardw 2214 Do not enable hardware P state control (HWP) 2261 if available. 2215 if available. 2262 hwp_only 2216 hwp_only 2263 Only load intel_pst 2217 Only load intel_pstate on systems which support 2264 hardware P state co 2218 hardware P state control (HWP) if available. 2265 support_acpi_ppc 2219 support_acpi_ppc 2266 Enforce ACPI _PPC p 2220 Enforce ACPI _PPC performance limits. If the Fixed ACPI 2267 Description Table, 2221 Description Table, specifies preferred power management 2268 profile as "Enterpr 2222 profile as "Enterprise Server" or "Performance Server", 2269 then this feature i 2223 then this feature is turned on by default. 2270 per_cpu_perf_limits 2224 per_cpu_perf_limits 2271 Allow per-logical-C 2225 Allow per-logical-CPU P-State performance control limits using 2272 cpufreq sysfs inter 2226 cpufreq sysfs interface 2273 2227 2274 intremap= [X86-64,Intel-IOMMU,E !! 2228 intremap= [X86-64, Intel-IOMMU] 2275 on enable Interr 2229 on enable Interrupt Remapping (default) 2276 off disable Inter 2230 off disable Interrupt Remapping 2277 nosid disable Sourc 2231 nosid disable Source ID checking 2278 no_x2apic_optout 2232 no_x2apic_optout 2279 BIOS x2APIC o 2233 BIOS x2APIC opt-out request will be ignored 2280 nopost disable Inter 2234 nopost disable Interrupt Posting 2281 posted_msi << 2282 enable MSIs d << 2283 2235 2284 iomem= Disable strict checki 2236 iomem= Disable strict checking of access to MMIO memory 2285 strict regions from userspac 2237 strict regions from userspace. 2286 relaxed 2238 relaxed 2287 2239 2288 iommu= [X86,EARLY] !! 2240 iommu= [X86] 2289 off 2241 off 2290 force 2242 force 2291 noforce 2243 noforce 2292 biomerge 2244 biomerge 2293 panic 2245 panic 2294 nopanic 2246 nopanic 2295 merge 2247 merge 2296 nomerge 2248 nomerge 2297 soft 2249 soft 2298 pt [X86] 2250 pt [X86] 2299 nopt [X86] 2251 nopt [X86] 2300 nobypass [PPC/POWERNV] 2252 nobypass [PPC/POWERNV] 2301 Disable IOMMU bypass, 2253 Disable IOMMU bypass, using IOMMU for PCI devices. 2302 2254 2303 iommu.forcedac= [ARM64,X86,EARLY] Con !! 2255 iommu.forcedac= [ARM64, X86] Control IOVA allocation for PCI devices. 2304 Format: { "0" | "1" } 2256 Format: { "0" | "1" } 2305 0 - Try to allocate a 2257 0 - Try to allocate a 32-bit DMA address first, before 2306 falling back to the 2258 falling back to the full range if needed. 2307 1 - Allocate directly 2259 1 - Allocate directly from the full usable range, 2308 forcing Dual Addres 2260 forcing Dual Address Cycle for PCI cards supporting 2309 greater than 32-bit 2261 greater than 32-bit addressing. 2310 2262 2311 iommu.strict= [ARM64,X86,S390,EARLY !! 2263 iommu.strict= [ARM64, X86, S390] Configure TLB invalidation behaviour 2312 Format: { "0" | "1" } 2264 Format: { "0" | "1" } 2313 0 - Lazy mode. 2265 0 - Lazy mode. 2314 Request that DMA un 2266 Request that DMA unmap operations use deferred 2315 invalidation of har 2267 invalidation of hardware TLBs, for increased 2316 throughput at the c 2268 throughput at the cost of reduced device isolation. 2317 Will fall back to s 2269 Will fall back to strict mode if not supported by 2318 the relevant IOMMU 2270 the relevant IOMMU driver. 2319 1 - Strict mode. 2271 1 - Strict mode. 2320 DMA unmap operation 2272 DMA unmap operations invalidate IOMMU hardware TLBs 2321 synchronously. 2273 synchronously. 2322 unset - Use value of 2274 unset - Use value of CONFIG_IOMMU_DEFAULT_DMA_{LAZY,STRICT}. 2323 Note: on x86, strict 2275 Note: on x86, strict mode specified via one of the 2324 legacy driver-specifi 2276 legacy driver-specific options takes precedence. 2325 2277 2326 iommu.passthrough= 2278 iommu.passthrough= 2327 [ARM64,X86,EARLY] Con !! 2279 [ARM64, X86] Configure DMA to bypass the IOMMU by default. 2328 Format: { "0" | "1" } 2280 Format: { "0" | "1" } 2329 0 - Use IOMMU transla 2281 0 - Use IOMMU translation for DMA. 2330 1 - Bypass the IOMMU 2282 1 - Bypass the IOMMU for DMA. 2331 unset - Use value of 2283 unset - Use value of CONFIG_IOMMU_DEFAULT_PASSTHROUGH. 2332 2284 2333 io7= [HW] IO7 for Marvel-b 2285 io7= [HW] IO7 for Marvel-based Alpha systems 2334 See comment before ma 2286 See comment before marvel_specify_io7 in 2335 arch/alpha/kernel/cor 2287 arch/alpha/kernel/core_marvel.c. 2336 2288 2337 io_delay= [X86,EARLY] I/O delay !! 2289 io_delay= [X86] I/O delay method 2338 0x80 2290 0x80 2339 Standard port 0x80 ba 2291 Standard port 0x80 based delay 2340 0xed 2292 0xed 2341 Alternate port 0xed b 2293 Alternate port 0xed based delay (needed on some systems) 2342 udelay 2294 udelay 2343 Simple two microsecon 2295 Simple two microseconds delay 2344 none 2296 none 2345 No delay 2297 No delay 2346 2298 2347 ip= [IP_PNP] 2299 ip= [IP_PNP] 2348 See Documentation/adm 2300 See Documentation/admin-guide/nfs/nfsroot.rst. 2349 2301 2350 ipcmni_extend [KNL,EARLY] Extend th !! 2302 ipcmni_extend [KNL] Extend the maximum number of unique System V 2351 IPC identifiers from 2303 IPC identifiers from 32,768 to 16,777,216. 2352 2304 2353 irqaffinity= [SMP] Set the default 2305 irqaffinity= [SMP] Set the default irq affinity mask 2354 The argument is a cpu 2306 The argument is a cpu list, as described above. 2355 2307 2356 irqchip.gicv2_force_probe= 2308 irqchip.gicv2_force_probe= 2357 [ARM,ARM64,EARLY] !! 2309 [ARM, ARM64] 2358 Format: <bool> 2310 Format: <bool> 2359 Force the kernel to l 2311 Force the kernel to look for the second 4kB page 2360 of a GICv2 controller 2312 of a GICv2 controller even if the memory range 2361 exposed by the device 2313 exposed by the device tree is too small. 2362 2314 2363 irqchip.gicv3_nolpi= 2315 irqchip.gicv3_nolpi= 2364 [ARM,ARM64,EARLY] !! 2316 [ARM, ARM64] 2365 Force the kernel to i 2317 Force the kernel to ignore the availability of 2366 LPIs (and by conseque 2318 LPIs (and by consequence ITSs). Intended for system 2367 that use the kernel a 2319 that use the kernel as a bootloader, and thus want 2368 to let secondary kern 2320 to let secondary kernels in charge of setting up 2369 LPIs. 2321 LPIs. 2370 2322 2371 irqchip.gicv3_pseudo_nmi= [ARM64,EARL !! 2323 irqchip.gicv3_pseudo_nmi= [ARM64] 2372 Enables support for p 2324 Enables support for pseudo-NMIs in the kernel. This 2373 requires the kernel t 2325 requires the kernel to be built with 2374 CONFIG_ARM64_PSEUDO_N 2326 CONFIG_ARM64_PSEUDO_NMI. 2375 2327 2376 irqfixup [HW] 2328 irqfixup [HW] 2377 When an interrupt is 2329 When an interrupt is not handled search all handlers 2378 for it. Intended to g 2330 for it. Intended to get systems with badly broken 2379 firmware running. 2331 firmware running. 2380 2332 2381 irqpoll [HW] 2333 irqpoll [HW] 2382 When an interrupt is 2334 When an interrupt is not handled search all handlers 2383 for it. Also check al 2335 for it. Also check all handlers each timer 2384 interrupt. Intended t 2336 interrupt. Intended to get systems with badly broken 2385 firmware running. 2337 firmware running. 2386 2338 2387 isapnp= [ISAPNP] 2339 isapnp= [ISAPNP] 2388 Format: <RDP>,<reset> 2340 Format: <RDP>,<reset>,<pci_scan>,<verbosity> 2389 2341 2390 isolcpus= [KNL,SMP,ISOL] Isolat 2342 isolcpus= [KNL,SMP,ISOL] Isolate a given set of CPUs from disturbance. 2391 [Deprecated - use cpu 2343 [Deprecated - use cpusets instead] 2392 Format: [flag-list,]< 2344 Format: [flag-list,]<cpu-list> 2393 2345 2394 Specify one or more C 2346 Specify one or more CPUs to isolate from disturbances 2395 specified in the flag 2347 specified in the flag list (default: domain): 2396 2348 2397 nohz 2349 nohz 2398 Disable the tick wh 2350 Disable the tick when a single task runs. 2399 2351 2400 A residual 1Hz tick 2352 A residual 1Hz tick is offloaded to workqueues, which you 2401 need to affine to h 2353 need to affine to housekeeping through the global 2402 workqueue's affinit 2354 workqueue's affinity configured via the 2403 /sys/devices/virtua 2355 /sys/devices/virtual/workqueue/cpumask sysfs file, or 2404 by using the 'domai 2356 by using the 'domain' flag described below. 2405 2357 2406 NOTE: by default th 2358 NOTE: by default the global workqueue runs on all CPUs, 2407 so to protect indiv 2359 so to protect individual CPUs the 'cpumask' file has to 2408 be configured manua 2360 be configured manually after bootup. 2409 2361 2410 domain 2362 domain 2411 Isolate from the ge 2363 Isolate from the general SMP balancing and scheduling 2412 algorithms. Note th 2364 algorithms. Note that performing domain isolation this way 2413 is irreversible: it 2365 is irreversible: it's not possible to bring back a CPU to 2414 the domains once is 2366 the domains once isolated through isolcpus. It's strongly 2415 advised to use cpus 2367 advised to use cpusets instead to disable scheduler load 2416 balancing through t 2368 balancing through the "cpuset.sched_load_balance" file. 2417 It offers a much mo 2369 It offers a much more flexible interface where CPUs can 2418 move in and out of 2370 move in and out of an isolated set anytime. 2419 2371 2420 You can move a proc 2372 You can move a process onto or off an "isolated" CPU via 2421 the CPU affinity sy 2373 the CPU affinity syscalls or cpuset. 2422 <cpu number> begins 2374 <cpu number> begins at 0 and the maximum value is 2423 "number of CPUs in 2375 "number of CPUs in system - 1". 2424 2376 2425 managed_irq 2377 managed_irq 2426 2378 2427 Isolate from being 2379 Isolate from being targeted by managed interrupts 2428 which have an inter 2380 which have an interrupt mask containing isolated 2429 CPUs. The affinity 2381 CPUs. The affinity of managed interrupts is 2430 handled by the kern 2382 handled by the kernel and cannot be changed via 2431 the /proc/irq/* int 2383 the /proc/irq/* interfaces. 2432 2384 2433 This isolation is b 2385 This isolation is best effort and only effective 2434 if the automaticall 2386 if the automatically assigned interrupt mask of a 2435 device queue contai 2387 device queue contains isolated and housekeeping 2436 CPUs. If housekeepi 2388 CPUs. If housekeeping CPUs are online then such 2437 interrupts are dire 2389 interrupts are directed to the housekeeping CPU 2438 so that IO submitte 2390 so that IO submitted on the housekeeping CPU 2439 cannot disturb the 2391 cannot disturb the isolated CPU. 2440 2392 2441 If a queue's affini 2393 If a queue's affinity mask contains only isolated 2442 CPUs then this para 2394 CPUs then this parameter has no effect on the 2443 interrupt routing d 2395 interrupt routing decision, though interrupts are 2444 only delivered when 2396 only delivered when tasks running on those 2445 isolated CPUs submi 2397 isolated CPUs submit IO. IO submitted on 2446 housekeeping CPUs h 2398 housekeeping CPUs has no influence on those 2447 queues. 2399 queues. 2448 2400 2449 The format of <cpu-li 2401 The format of <cpu-list> is described above. 2450 2402 2451 iucv= [HW,NET] 2403 iucv= [HW,NET] 2452 2404 2453 ivrs_ioapic [HW,X86-64] 2405 ivrs_ioapic [HW,X86-64] 2454 Provide an override t 2406 Provide an override to the IOAPIC-ID<->DEVICE-ID 2455 mapping provided in t 2407 mapping provided in the IVRS ACPI table. 2456 By default, PCI segme 2408 By default, PCI segment is 0, and can be omitted. 2457 2409 2458 For example, to map I 2410 For example, to map IOAPIC-ID decimal 10 to 2459 PCI segment 0x1 and P 2411 PCI segment 0x1 and PCI device 00:14.0, 2460 write the parameter a 2412 write the parameter as: 2461 ivrs_ioapic=1 2413 ivrs_ioapic=10@0001:00:14.0 2462 2414 2463 Deprecated formats: 2415 Deprecated formats: 2464 * To map IOAPIC-ID de 2416 * To map IOAPIC-ID decimal 10 to PCI device 00:14.0 2465 write the parameter 2417 write the parameter as: 2466 ivrs_ioapic[1 2418 ivrs_ioapic[10]=00:14.0 2467 * To map IOAPIC-ID de 2419 * To map IOAPIC-ID decimal 10 to PCI segment 0x1 and 2468 PCI device 00:14.0 2420 PCI device 00:14.0 write the parameter as: 2469 ivrs_ioapic[1 2421 ivrs_ioapic[10]=0001:00:14.0 2470 2422 2471 ivrs_hpet [HW,X86-64] 2423 ivrs_hpet [HW,X86-64] 2472 Provide an override t 2424 Provide an override to the HPET-ID<->DEVICE-ID 2473 mapping provided in t 2425 mapping provided in the IVRS ACPI table. 2474 By default, PCI segme 2426 By default, PCI segment is 0, and can be omitted. 2475 2427 2476 For example, to map H 2428 For example, to map HPET-ID decimal 10 to 2477 PCI segment 0x1 and P 2429 PCI segment 0x1 and PCI device 00:14.0, 2478 write the parameter a 2430 write the parameter as: 2479 ivrs_hpet=10@ 2431 ivrs_hpet=10@0001:00:14.0 2480 2432 2481 Deprecated formats: 2433 Deprecated formats: 2482 * To map HPET-ID deci 2434 * To map HPET-ID decimal 0 to PCI device 00:14.0 2483 write the parameter 2435 write the parameter as: 2484 ivrs_hpet[0]= 2436 ivrs_hpet[0]=00:14.0 2485 * To map HPET-ID deci 2437 * To map HPET-ID decimal 10 to PCI segment 0x1 and 2486 PCI device 00:14.0 2438 PCI device 00:14.0 write the parameter as: 2487 ivrs_ioapic[1 2439 ivrs_ioapic[10]=0001:00:14.0 2488 2440 2489 ivrs_acpihid [HW,X86-64] 2441 ivrs_acpihid [HW,X86-64] 2490 Provide an override t 2442 Provide an override to the ACPI-HID:UID<->DEVICE-ID 2491 mapping provided in t 2443 mapping provided in the IVRS ACPI table. 2492 By default, PCI segme 2444 By default, PCI segment is 0, and can be omitted. 2493 2445 2494 For example, to map U 2446 For example, to map UART-HID:UID AMD0020:0 to 2495 PCI segment 0x1 and P 2447 PCI segment 0x1 and PCI device ID 00:14.5, 2496 write the parameter a 2448 write the parameter as: 2497 ivrs_acpihid= 2449 ivrs_acpihid=AMD0020:0@0001:00:14.5 2498 2450 2499 Deprecated formats: 2451 Deprecated formats: 2500 * To map UART-HID:UID 2452 * To map UART-HID:UID AMD0020:0 to PCI segment is 0, 2501 PCI device ID 00:14 2453 PCI device ID 00:14.5, write the parameter as: 2502 ivrs_acpihid[ 2454 ivrs_acpihid[00:14.5]=AMD0020:0 2503 * To map UART-HID:UID 2455 * To map UART-HID:UID AMD0020:0 to PCI segment 0x1 and 2504 PCI device ID 00:14 2456 PCI device ID 00:14.5, write the parameter as: 2505 ivrs_acpihid[ 2457 ivrs_acpihid[0001:00:14.5]=AMD0020:0 2506 2458 2507 js= [HW,JOY] Analog joyst 2459 js= [HW,JOY] Analog joystick 2508 See Documentation/inp 2460 See Documentation/input/joydev/joystick.rst. 2509 2461 2510 kasan_multi_shot 2462 kasan_multi_shot 2511 [KNL] Enforce KASAN ( 2463 [KNL] Enforce KASAN (Kernel Address Sanitizer) to print 2512 report on every inval 2464 report on every invalid memory access. Without this 2513 parameter KASAN will 2465 parameter KASAN will print report only for the first 2514 invalid access. 2466 invalid access. 2515 2467 2516 keep_bootcon [KNL,EARLY] !! 2468 keep_bootcon [KNL] 2517 Do not unregister boo 2469 Do not unregister boot console at start. This is only 2518 useful for debugging 2470 useful for debugging when something happens in the window 2519 between unregistering 2471 between unregistering the boot console and initializing 2520 the real console. 2472 the real console. 2521 2473 2522 keepinitrd [HW,ARM] See retain_i 2474 keepinitrd [HW,ARM] See retain_initrd. 2523 2475 2524 kernelcore= [KNL,X86,PPC,EARLY] !! 2476 kernelcore= [KNL,X86,IA-64,PPC] 2525 Format: nn[KMGTPE] | 2477 Format: nn[KMGTPE] | nn% | "mirror" 2526 This parameter specif 2478 This parameter specifies the amount of memory usable by 2527 the kernel for non-mo 2479 the kernel for non-movable allocations. The requested 2528 amount is spread even 2480 amount is spread evenly throughout all nodes in the 2529 system as ZONE_NORMAL 2481 system as ZONE_NORMAL. The remaining memory is used for 2530 movable memory in its 2482 movable memory in its own zone, ZONE_MOVABLE. In the 2531 event, a node is too 2483 event, a node is too small to have both ZONE_NORMAL and 2532 ZONE_MOVABLE, kernelc 2484 ZONE_MOVABLE, kernelcore memory will take priority and 2533 other nodes will have 2485 other nodes will have a larger ZONE_MOVABLE. 2534 2486 2535 ZONE_MOVABLE is used 2487 ZONE_MOVABLE is used for the allocation of pages that 2536 may be reclaimed or m 2488 may be reclaimed or moved by the page migration 2537 subsystem. Note that 2489 subsystem. Note that allocations like PTEs-from-HighMem 2538 still use the HighMem 2490 still use the HighMem zone if it exists, and the Normal 2539 zone if it does not. 2491 zone if it does not. 2540 2492 2541 It is possible to spe 2493 It is possible to specify the exact amount of memory in 2542 the form of "nn[KMGTP 2494 the form of "nn[KMGTPE]", a percentage of total system 2543 memory in the form of 2495 memory in the form of "nn%", or "mirror". If "mirror" 2544 option is specified, 2496 option is specified, mirrored (reliable) memory is used 2545 for non-movable alloc 2497 for non-movable allocations and remaining memory is used 2546 for Movable pages. " 2498 for Movable pages. "nn[KMGTPE]", "nn%", and "mirror" 2547 are exclusive, so you 2499 are exclusive, so you cannot specify multiple forms. 2548 2500 2549 kgdbdbgp= [KGDB,HW,EARLY] kgdb !! 2501 kgdbdbgp= [KGDB,HW] kgdb over EHCI usb debug port. 2550 Format: <Controller#> 2502 Format: <Controller#>[,poll interval] 2551 The controller # is t 2503 The controller # is the number of the ehci usb debug 2552 port as it is probed 2504 port as it is probed via PCI. The poll interval is 2553 optional and is the n 2505 optional and is the number seconds in between 2554 each poll cycle to th 2506 each poll cycle to the debug port in case you need 2555 the functionality for 2507 the functionality for interrupting the kernel with 2556 gdb or control-c on t 2508 gdb or control-c on the dbgp connection. When 2557 not using this parame 2509 not using this parameter you use sysrq-g to break into 2558 the kernel debugger. 2510 the kernel debugger. 2559 2511 2560 kgdboc= [KGDB,HW] kgdb over c 2512 kgdboc= [KGDB,HW] kgdb over consoles. 2561 Requires a tty driver 2513 Requires a tty driver that supports console polling, 2562 or a supported pollin 2514 or a supported polling keyboard driver (non-usb). 2563 Serial only format: 2515 Serial only format: <serial_device>[,baud] 2564 keyboard only format 2516 keyboard only format: kbd 2565 keyboard and serial 2517 keyboard and serial format: kbd,<serial_device>[,baud] 2566 Optional Kernel mode 2518 Optional Kernel mode setting: 2567 kms, kbd format: kms 2519 kms, kbd format: kms,kbd 2568 kms, kbd and serial 2520 kms, kbd and serial format: kms,kbd,<ser_dev>[,baud] 2569 2521 2570 kgdboc_earlycon= [KGDB,HW,EARL !! 2522 kgdboc_earlycon= [KGDB,HW] 2571 If the boot console p 2523 If the boot console provides the ability to read 2572 characters and can wo 2524 characters and can work in polling mode, you can use 2573 this parameter to tel 2525 this parameter to tell kgdb to use it as a backend 2574 until the normal cons 2526 until the normal console is registered. Intended to 2575 be used together with 2527 be used together with the kgdboc parameter which 2576 specifies the normal 2528 specifies the normal console to transition to. 2577 2529 2578 The name of the early 2530 The name of the early console should be specified 2579 as the value of this 2531 as the value of this parameter. Note that the name of 2580 the early console mig 2532 the early console might be different than the tty 2581 name passed to kgdboc 2533 name passed to kgdboc. It's OK to leave the value 2582 blank and the first b 2534 blank and the first boot console that implements 2583 read() will be picked 2535 read() will be picked. 2584 2536 2585 kgdbwait [KGDB,EARLY] Stop ker !! 2537 kgdbwait [KGDB] Stop kernel execution and enter the 2586 kernel debugger at th 2538 kernel debugger at the earliest opportunity. 2587 2539 2588 kmac= [MIPS] Korina etherne 2540 kmac= [MIPS] Korina ethernet MAC address. 2589 Configure the RouterB 2541 Configure the RouterBoard 532 series on-chip 2590 Ethernet adapter MAC 2542 Ethernet adapter MAC address. 2591 2543 2592 kmemleak= [KNL,EARLY] Boot-time !! 2544 kmemleak= [KNL] Boot-time kmemleak enable/disable 2593 Valid arguments: on, 2545 Valid arguments: on, off 2594 Default: on 2546 Default: on 2595 Built with CONFIG_DEB 2547 Built with CONFIG_DEBUG_KMEMLEAK_DEFAULT_OFF=y, 2596 the default is off. 2548 the default is off. 2597 2549 2598 kprobe_event=[probe-list] 2550 kprobe_event=[probe-list] 2599 [FTRACE] Add kprobe e 2551 [FTRACE] Add kprobe events and enable at boot time. 2600 The probe-list is a s 2552 The probe-list is a semicolon delimited list of probe 2601 definitions. Each def 2553 definitions. Each definition is same as kprobe_events 2602 interface, but the pa 2554 interface, but the parameters are comma delimited. 2603 For example, to add a 2555 For example, to add a kprobe event on vfs_read with 2604 arg1 and arg2, add to 2556 arg1 and arg2, add to the command line; 2605 2557 2606 kprobe_event=p, 2558 kprobe_event=p,vfs_read,$arg1,$arg2 2607 2559 2608 See also Documentatio 2560 See also Documentation/trace/kprobetrace.rst "Kernel 2609 Boot Parameter" secti 2561 Boot Parameter" section. 2610 2562 2611 kpti= [ARM64,EARLY] Control !! 2563 kpti= [ARM64] Control page table isolation of user 2612 user and kernel addre !! 2564 and kernel address spaces. 2613 Default: enabled on c 2565 Default: enabled on cores which need mitigation. 2614 0: force disabled 2566 0: force disabled 2615 1: force enabled 2567 1: force enabled 2616 2568 2617 kunit.enable= [KUNIT] Enable execut 2569 kunit.enable= [KUNIT] Enable executing KUnit tests. Requires 2618 CONFIG_KUNIT to be se 2570 CONFIG_KUNIT to be set to be fully enabled. The 2619 default value can be 2571 default value can be overridden via 2620 KUNIT_DEFAULT_ENABLED 2572 KUNIT_DEFAULT_ENABLED. 2621 Default is 1 (enabled 2573 Default is 1 (enabled) 2622 2574 2623 kvm.ignore_msrs=[KVM] Ignore guest ac 2575 kvm.ignore_msrs=[KVM] Ignore guest accesses to unhandled MSRs. 2624 Default is 0 (don't i 2576 Default is 0 (don't ignore, but inject #GP) 2625 2577 2626 kvm.eager_page_split= 2578 kvm.eager_page_split= 2627 [KVM,X86] Controls wh 2579 [KVM,X86] Controls whether or not KVM will try to 2628 proactively split all 2580 proactively split all huge pages during dirty logging. 2629 Eager page splitting 2581 Eager page splitting reduces interruptions to vCPU 2630 execution by eliminat 2582 execution by eliminating the write-protection faults 2631 and MMU lock contenti 2583 and MMU lock contention that would otherwise be 2632 required to split hug 2584 required to split huge pages lazily. 2633 2585 2634 VM workloads that rar 2586 VM workloads that rarely perform writes or that write 2635 only to a small regio 2587 only to a small region of VM memory may benefit from 2636 disabling eager page 2588 disabling eager page splitting to allow huge pages to 2637 still be used for rea 2589 still be used for reads. 2638 2590 2639 The behavior of eager 2591 The behavior of eager page splitting depends on whether 2640 KVM_DIRTY_LOG_INITIAL 2592 KVM_DIRTY_LOG_INITIALLY_SET is enabled or disabled. If 2641 disabled, all huge pa 2593 disabled, all huge pages in a memslot will be eagerly 2642 split when dirty logg 2594 split when dirty logging is enabled on that memslot. If 2643 enabled, eager page s 2595 enabled, eager page splitting will be performed during 2644 the KVM_CLEAR_DIRTY i 2596 the KVM_CLEAR_DIRTY ioctl, and only for the pages being 2645 cleared. 2597 cleared. 2646 2598 2647 Eager page splitting 2599 Eager page splitting is only supported when kvm.tdp_mmu=Y. 2648 2600 2649 Default is Y (on). 2601 Default is Y (on). 2650 2602 2651 kvm.enable_vmware_backdoor=[KVM] Supp 2603 kvm.enable_vmware_backdoor=[KVM] Support VMware backdoor PV interface. 2652 Default is 2604 Default is false (don't support). 2653 2605 2654 kvm.nx_huge_pages= 2606 kvm.nx_huge_pages= 2655 [KVM] Controls the so 2607 [KVM] Controls the software workaround for the 2656 X86_BUG_ITLB_MULTIHIT 2608 X86_BUG_ITLB_MULTIHIT bug. 2657 force : Always depl 2609 force : Always deploy workaround. 2658 off : Never deplo 2610 off : Never deploy workaround. 2659 auto : Deploy work 2611 auto : Deploy workaround based on the presence of 2660 X86_BUG_ITL 2612 X86_BUG_ITLB_MULTIHIT. 2661 2613 2662 Default is 'auto'. 2614 Default is 'auto'. 2663 2615 2664 If the software worka 2616 If the software workaround is enabled for the host, 2665 guests do need not to 2617 guests do need not to enable it for nested guests. 2666 2618 2667 kvm.nx_huge_pages_recovery_ratio= 2619 kvm.nx_huge_pages_recovery_ratio= 2668 [KVM] Controls how ma 2620 [KVM] Controls how many 4KiB pages are periodically zapped 2669 back to huge pages. 2621 back to huge pages. 0 disables the recovery, otherwise if 2670 the value is N KVM wi 2622 the value is N KVM will zap 1/Nth of the 4KiB pages every 2671 period (see below). 2623 period (see below). The default is 60. 2672 2624 2673 kvm.nx_huge_pages_recovery_period_ms= 2625 kvm.nx_huge_pages_recovery_period_ms= 2674 [KVM] Controls the ti 2626 [KVM] Controls the time period at which KVM zaps 4KiB pages 2675 back to huge pages. I 2627 back to huge pages. If the value is a non-zero N, KVM will 2676 zap a portion (see ra 2628 zap a portion (see ratio above) of the pages every N msecs. 2677 If the value is 0 (th 2629 If the value is 0 (the default), KVM will pick a period based 2678 on the ratio, such th 2630 on the ratio, such that a page is zapped after 1 hour on average. 2679 2631 2680 kvm-amd.nested= [KVM,AMD] Control nes 2632 kvm-amd.nested= [KVM,AMD] Control nested virtualization feature in 2681 KVM/SVM. Default is 1 2633 KVM/SVM. Default is 1 (enabled). 2682 2634 2683 kvm-amd.npt= [KVM,AMD] Control KVM 2635 kvm-amd.npt= [KVM,AMD] Control KVM's use of Nested Page Tables, 2684 a.k.a. Two-Dimensiona 2636 a.k.a. Two-Dimensional Page Tables. Default is 1 2685 (enabled). Disable by 2637 (enabled). Disable by KVM if hardware lacks support 2686 for NPT. 2638 for NPT. 2687 2639 2688 kvm-arm.mode= 2640 kvm-arm.mode= 2689 [KVM,ARM,EARLY] Selec !! 2641 [KVM,ARM] Select one of KVM/arm64's modes of operation. 2690 operation. << 2691 2642 2692 none: Forcefully disa 2643 none: Forcefully disable KVM. 2693 2644 2694 nvhe: Standard nVHE-b 2645 nvhe: Standard nVHE-based mode, without support for 2695 protected guest 2646 protected guests. 2696 2647 2697 protected: nVHE-based 2648 protected: nVHE-based mode with support for guests whose 2698 state is k 2649 state is kept private from the host. 2699 2650 2700 nested: VHE-based mod 2651 nested: VHE-based mode with support for nested 2701 virtualizatio 2652 virtualization. Requires at least ARMv8.3 2702 hardware. 2653 hardware. 2703 2654 2704 Defaults to VHE/nVHE 2655 Defaults to VHE/nVHE based on hardware support. Setting 2705 mode to "protected" w 2656 mode to "protected" will disable kexec and hibernation 2706 for the host. "nested 2657 for the host. "nested" is experimental and should be 2707 used with extreme cau 2658 used with extreme caution. 2708 2659 2709 kvm-arm.vgic_v3_group0_trap= 2660 kvm-arm.vgic_v3_group0_trap= 2710 [KVM,ARM,EARLY] Trap !! 2661 [KVM,ARM] Trap guest accesses to GICv3 group-0 2711 system registers 2662 system registers 2712 2663 2713 kvm-arm.vgic_v3_group1_trap= 2664 kvm-arm.vgic_v3_group1_trap= 2714 [KVM,ARM,EARLY] Trap !! 2665 [KVM,ARM] Trap guest accesses to GICv3 group-1 2715 system registers 2666 system registers 2716 2667 2717 kvm-arm.vgic_v3_common_trap= 2668 kvm-arm.vgic_v3_common_trap= 2718 [KVM,ARM,EARLY] Trap !! 2669 [KVM,ARM] Trap guest accesses to GICv3 common 2719 system registers 2670 system registers 2720 2671 2721 kvm-arm.vgic_v4_enable= 2672 kvm-arm.vgic_v4_enable= 2722 [KVM,ARM,EARLY] Allow !! 2673 [KVM,ARM] Allow use of GICv4 for direct injection of 2723 injection of LPIs. !! 2674 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 2675 2743 kvm_cma_resv_ratio=n [PPC,EARLY] !! 2676 kvm_cma_resv_ratio=n [PPC] 2744 Reserves given percen 2677 Reserves given percentage from system memory area for 2745 contiguous memory all 2678 contiguous memory allocation for KVM hash pagetable 2746 allocation. 2679 allocation. 2747 By default it reserve 2680 By default it reserves 5% of total system memory. 2748 Format: <integer> 2681 Format: <integer> 2749 Default: 5 2682 Default: 5 2750 2683 2751 kvm-intel.ept= [KVM,Intel] Control K 2684 kvm-intel.ept= [KVM,Intel] Control KVM's use of Extended Page Tables, 2752 a.k.a. Two-Dimensiona 2685 a.k.a. Two-Dimensional Page Tables. Default is 1 2753 (enabled). Disable by 2686 (enabled). Disable by KVM if hardware lacks support 2754 for EPT. 2687 for EPT. 2755 2688 2756 kvm-intel.emulate_invalid_guest_state 2689 kvm-intel.emulate_invalid_guest_state= 2757 [KVM,Intel] Control w 2690 [KVM,Intel] Control whether to emulate invalid guest 2758 state. Ignored if kvm 2691 state. Ignored if kvm-intel.enable_unrestricted_guest=1, 2759 as guest state is nev 2692 as guest state is never invalid for unrestricted 2760 guests. This param do 2693 guests. This param doesn't apply to nested guests (L2), 2761 as KVM never emulates 2694 as KVM never emulates invalid L2 guest state. 2762 Default is 1 (enabled 2695 Default is 1 (enabled). 2763 2696 2764 kvm-intel.flexpriority= 2697 kvm-intel.flexpriority= 2765 [KVM,Intel] Control K 2698 [KVM,Intel] Control KVM's use of FlexPriority feature 2766 (TPR shadow). Default 2699 (TPR shadow). Default is 1 (enabled). Disable by KVM if 2767 hardware lacks suppor 2700 hardware lacks support for it. 2768 2701 2769 kvm-intel.nested= 2702 kvm-intel.nested= 2770 [KVM,Intel] Control n 2703 [KVM,Intel] Control nested virtualization feature in 2771 KVM/VMX. Default is 1 2704 KVM/VMX. Default is 1 (enabled). 2772 2705 2773 kvm-intel.unrestricted_guest= 2706 kvm-intel.unrestricted_guest= 2774 [KVM,Intel] Control K 2707 [KVM,Intel] Control KVM's use of unrestricted guest 2775 feature (virtualized 2708 feature (virtualized real and unpaged mode). Default 2776 is 1 (enabled). Disab 2709 is 1 (enabled). Disable by KVM if EPT is disabled or 2777 hardware lacks suppor 2710 hardware lacks support for it. 2778 2711 2779 kvm-intel.vmentry_l1d_flush=[KVM,Inte 2712 kvm-intel.vmentry_l1d_flush=[KVM,Intel] Mitigation for L1 Terminal Fault 2780 CVE-2018-3620. 2713 CVE-2018-3620. 2781 2714 2782 Valid arguments: neve 2715 Valid arguments: never, cond, always 2783 2716 2784 always: L1D cache flu 2717 always: L1D cache flush on every VMENTER. 2785 cond: Flush L1D on 2718 cond: Flush L1D on VMENTER only when the code between 2786 VMEXIT and VM 2719 VMEXIT and VMENTER can leak host memory. 2787 never: Disables the 2720 never: Disables the mitigation 2788 2721 2789 Default is cond (do L 2722 Default is cond (do L1 cache flush in specific instances) 2790 2723 2791 kvm-intel.vpid= [KVM,Intel] Control K 2724 kvm-intel.vpid= [KVM,Intel] Control KVM's use of Virtual Processor 2792 Identification featur 2725 Identification feature (tagged TLBs). Default is 1 2793 (enabled). Disable by 2726 (enabled). Disable by KVM if hardware lacks support 2794 for it. 2727 for it. 2795 2728 2796 l1d_flush= [X86,INTEL,EARLY] !! 2729 l1d_flush= [X86,INTEL] 2797 Control mitigation fo 2730 Control mitigation for L1D based snooping vulnerability. 2798 2731 2799 Certain CPUs are vuln 2732 Certain CPUs are vulnerable to an exploit against CPU 2800 internal buffers whic 2733 internal buffers which can forward information to a 2801 disclosure gadget und 2734 disclosure gadget under certain conditions. 2802 2735 2803 In vulnerable process 2736 In vulnerable processors, the speculatively 2804 forwarded data can be 2737 forwarded data can be used in a cache side channel 2805 attack, to access dat 2738 attack, to access data to which the attacker does 2806 not have direct acces 2739 not have direct access. 2807 2740 2808 This parameter contro 2741 This parameter controls the mitigation. The 2809 options are: 2742 options are: 2810 2743 2811 on - enable t 2744 on - enable the interface for the mitigation 2812 2745 2813 l1tf= [X86,EARLY] Control m !! 2746 l1tf= [X86] Control mitigation of the L1TF vulnerability on 2814 affected CPUs 2747 affected CPUs 2815 2748 2816 The kernel PTE invers 2749 The kernel PTE inversion protection is unconditionally 2817 enabled and cannot be 2750 enabled and cannot be disabled. 2818 2751 2819 full 2752 full 2820 Provides all 2753 Provides all available mitigations for the 2821 L1TF vulnerab 2754 L1TF vulnerability. Disables SMT and 2822 enables all m 2755 enables all mitigations in the 2823 hypervisors, 2756 hypervisors, i.e. unconditional L1D flush. 2824 2757 2825 SMT control a 2758 SMT control and L1D flush control via the 2826 sysfs interfa 2759 sysfs interface is still possible after 2827 boot. Hyperv 2760 boot. Hypervisors will issue a warning 2828 when the firs 2761 when the first VM is started in a 2829 potentially i 2762 potentially insecure configuration, 2830 i.e. SMT enab 2763 i.e. SMT enabled or L1D flush disabled. 2831 2764 2832 full,force 2765 full,force 2833 Same as 'full 2766 Same as 'full', but disables SMT and L1D 2834 flush runtime 2767 flush runtime control. Implies the 2835 'nosmt=force' 2768 'nosmt=force' command line option. 2836 (i.e. sysfs c 2769 (i.e. sysfs control of SMT is disabled.) 2837 2770 2838 flush 2771 flush 2839 Leaves SMT en 2772 Leaves SMT enabled and enables the default 2840 hypervisor mi 2773 hypervisor mitigation, i.e. conditional 2841 L1D flush. 2774 L1D flush. 2842 2775 2843 SMT control a 2776 SMT control and L1D flush control via the 2844 sysfs interfa 2777 sysfs interface is still possible after 2845 boot. Hyperv 2778 boot. Hypervisors will issue a warning 2846 when the firs 2779 when the first VM is started in a 2847 potentially i 2780 potentially insecure configuration, 2848 i.e. SMT enab 2781 i.e. SMT enabled or L1D flush disabled. 2849 2782 2850 flush,nosmt 2783 flush,nosmt 2851 2784 2852 Disables SMT 2785 Disables SMT and enables the default 2853 hypervisor mi 2786 hypervisor mitigation. 2854 2787 2855 SMT control a 2788 SMT control and L1D flush control via the 2856 sysfs interfa 2789 sysfs interface is still possible after 2857 boot. Hyperv 2790 boot. Hypervisors will issue a warning 2858 when the firs 2791 when the first VM is started in a 2859 potentially i 2792 potentially insecure configuration, 2860 i.e. SMT enab 2793 i.e. SMT enabled or L1D flush disabled. 2861 2794 2862 flush,nowarn 2795 flush,nowarn 2863 Same as 'flus 2796 Same as 'flush', but hypervisors will not 2864 warn when a V 2797 warn when a VM is started in a potentially 2865 insecure conf 2798 insecure configuration. 2866 2799 2867 off 2800 off 2868 Disables hype 2801 Disables hypervisor mitigations and doesn't 2869 emit any warn 2802 emit any warnings. 2870 It also drops 2803 It also drops the swap size and available 2871 RAM limit res 2804 RAM limit restriction on both hypervisor and 2872 bare metal. 2805 bare metal. 2873 2806 2874 Default is 'flush'. 2807 Default is 'flush'. 2875 2808 2876 For details see: Docu 2809 For details see: Documentation/admin-guide/hw-vuln/l1tf.rst 2877 2810 2878 l2cr= [PPC] 2811 l2cr= [PPC] 2879 2812 2880 l3cr= [PPC] 2813 l3cr= [PPC] 2881 2814 2882 lapic [X86-32,APIC,EARLY] E !! 2815 lapic [X86-32,APIC] Enable the local APIC even if BIOS 2883 disabled it. 2816 disabled it. 2884 2817 2885 lapic= [X86,APIC] Do not use 2818 lapic= [X86,APIC] Do not use TSC deadline 2886 value for LAPIC timer 2819 value for LAPIC timer one-shot implementation. Default 2887 back to the programma 2820 back to the programmable timer unit in the LAPIC. 2888 Format: notscdeadline 2821 Format: notscdeadline 2889 2822 2890 lapic_timer_c2_ok [X86,APIC,EAR !! 2823 lapic_timer_c2_ok [X86,APIC] trust the local apic timer 2891 in C2 power state. 2824 in C2 power state. 2892 2825 2893 libata.dma= [LIBATA] DMA control 2826 libata.dma= [LIBATA] DMA control 2894 libata.dma=0 Dis 2827 libata.dma=0 Disable all PATA and SATA DMA 2895 libata.dma=1 PAT 2828 libata.dma=1 PATA and SATA Disk DMA only 2896 libata.dma=2 ATA 2829 libata.dma=2 ATAPI (CDROM) DMA only 2897 libata.dma=4 Com 2830 libata.dma=4 Compact Flash DMA only 2898 Combinations also wor 2831 Combinations also work, so libata.dma=3 enables DMA 2899 for disks and CDROMs, 2832 for disks and CDROMs, but not CFs. 2900 2833 2901 libata.ignore_hpa= [LIBATA] Igno 2834 libata.ignore_hpa= [LIBATA] Ignore HPA limit 2902 libata.ignore_hpa=0 2835 libata.ignore_hpa=0 keep BIOS limits (default) 2903 libata.ignore_hpa=1 2836 libata.ignore_hpa=1 ignore limits, using full disk 2904 2837 2905 libata.noacpi [LIBATA] Disables use 2838 libata.noacpi [LIBATA] Disables use of ACPI in libata suspend/resume 2906 when set. 2839 when set. 2907 Format: <int> 2840 Format: <int> 2908 2841 2909 libata.force= [LIBATA] Force config 2842 libata.force= [LIBATA] Force configurations. The format is a comma- 2910 separated list of "[I 2843 separated list of "[ID:]VAL" where ID is PORT[.DEVICE]. 2911 PORT and DEVICE are d 2844 PORT and DEVICE are decimal numbers matching port, link 2912 or device. Basically 2845 or device. Basically, it matches the ATA ID string 2913 printed on console by 2846 printed on console by libata. If the whole ID part is 2914 omitted, the last POR 2847 omitted, the last PORT and DEVICE values are used. If 2915 ID hasn't been specif 2848 ID hasn't been specified yet, the configuration applies 2916 to all ports, links a 2849 to all ports, links and devices. 2917 2850 2918 If only DEVICE is omi 2851 If only DEVICE is omitted, the parameter applies to 2919 the port and all link 2852 the port and all links and devices behind it. DEVICE 2920 number of 0 either se 2853 number of 0 either selects the first device or the 2921 first fan-out link be 2854 first fan-out link behind PMP device. It does not 2922 select the host link. 2855 select the host link. DEVICE number of 15 selects the 2923 host link and device 2856 host link and device attached to it. 2924 2857 2925 The VAL specifies the 2858 The VAL specifies the configuration to force. As long 2926 as there is no ambigu 2859 as there is no ambiguity, shortcut notation is allowed. 2927 For example, both 1.5 2860 For example, both 1.5 and 1.5G would work for 1.5Gbps. 2928 The following configu 2861 The following configurations can be forced. 2929 2862 2930 * Cable type: 40c, 80 2863 * Cable type: 40c, 80c, short40c, unk, ign or sata. 2931 Any ID with matchin 2864 Any ID with matching PORT is used. 2932 2865 2933 * SATA link speed lim 2866 * SATA link speed limit: 1.5Gbps or 3.0Gbps. 2934 2867 2935 * Transfer mode: pio[ 2868 * Transfer mode: pio[0-7], mwdma[0-4] and udma[0-7]. 2936 udma[/][16,25,33,44 2869 udma[/][16,25,33,44,66,100,133] notation is also 2937 allowed. 2870 allowed. 2938 2871 2939 * nohrst, nosrst, nor 2872 * nohrst, nosrst, norst: suppress hard, soft and both 2940 resets. 2873 resets. 2941 2874 2942 * rstonce: only attem 2875 * rstonce: only attempt one reset during hot-unplug 2943 link recovery. 2876 link recovery. 2944 2877 2945 * [no]dbdelay: Enable 2878 * [no]dbdelay: Enable or disable the extra 200ms delay 2946 before debouncing a 2879 before debouncing a link PHY and device presence 2947 detection. 2880 detection. 2948 2881 2949 * [no]ncq: Turn on or 2882 * [no]ncq: Turn on or off NCQ. 2950 2883 2951 * [no]ncqtrim: Enable 2884 * [no]ncqtrim: Enable or disable queued DSM TRIM. 2952 2885 2953 * [no]ncqati: Enable 2886 * [no]ncqati: Enable or disable NCQ trim on ATI chipset. 2954 2887 2955 * [no]trim: Enable or 2888 * [no]trim: Enable or disable (unqueued) TRIM. 2956 2889 2957 * trim_zero: Indicate 2890 * trim_zero: Indicate that TRIM command zeroes data. 2958 2891 2959 * max_trim_128m: Set 2892 * max_trim_128m: Set 128M maximum trim size limit. 2960 2893 2961 * [no]dma: Turn on or 2894 * [no]dma: Turn on or off DMA transfers. 2962 2895 2963 * atapi_dmadir: Enabl 2896 * atapi_dmadir: Enable ATAPI DMADIR bridge support. 2964 2897 2965 * atapi_mod16_dma: En 2898 * atapi_mod16_dma: Enable the use of ATAPI DMA for 2966 commands that are n 2899 commands that are not a multiple of 16 bytes. 2967 2900 2968 * [no]dmalog: Enable 2901 * [no]dmalog: Enable or disable the use of the 2969 READ LOG DMA EXT co 2902 READ LOG DMA EXT command to access logs. 2970 2903 2971 * [no]iddevlog: Enabl 2904 * [no]iddevlog: Enable or disable access to the 2972 identify device dat 2905 identify device data log. 2973 2906 2974 * [no]logdir: Enable 2907 * [no]logdir: Enable or disable access to the general 2975 purpose log directo 2908 purpose log directory. 2976 2909 2977 * max_sec_128: Set tr 2910 * max_sec_128: Set transfer size limit to 128 sectors. 2978 2911 2979 * max_sec_1024: Set o 2912 * max_sec_1024: Set or clear transfer size limit to 2980 1024 sectors. 2913 1024 sectors. 2981 2914 2982 * max_sec_lba48: Set 2915 * max_sec_lba48: Set or clear transfer size limit to 2983 65535 sectors. 2916 65535 sectors. 2984 2917 2985 * [no]lpm: Enable or 2918 * [no]lpm: Enable or disable link power management. 2986 2919 2987 * [no]setxfer: Indica 2920 * [no]setxfer: Indicate if transfer speed mode setting 2988 should be skipped. 2921 should be skipped. 2989 2922 2990 * [no]fua: Disable or 2923 * [no]fua: Disable or enable FUA (Force Unit Access) 2991 support for devices 2924 support for devices supporting this feature. 2992 2925 2993 * dump_id: Dump IDENT 2926 * dump_id: Dump IDENTIFY data. 2994 2927 2995 * disable: Disable th 2928 * disable: Disable this device. 2996 2929 2997 If there are multiple 2930 If there are multiple matching configurations changing 2998 the same attribute, t 2931 the same attribute, the last one is used. 2999 2932 3000 load_ramdisk= [RAM] [Deprecated] 2933 load_ramdisk= [RAM] [Deprecated] 3001 2934 3002 lockd.nlm_grace_period=P [NFS] Assig 2935 lockd.nlm_grace_period=P [NFS] Assign grace period. 3003 Format: <integer> 2936 Format: <integer> 3004 2937 3005 lockd.nlm_tcpport=N [NFS] Assign 2938 lockd.nlm_tcpport=N [NFS] Assign TCP port. 3006 Format: <integer> 2939 Format: <integer> 3007 2940 3008 lockd.nlm_timeout=T [NFS] Assign 2941 lockd.nlm_timeout=T [NFS] Assign timeout value. 3009 Format: <integer> 2942 Format: <integer> 3010 2943 3011 lockd.nlm_udpport=M [NFS] Assign 2944 lockd.nlm_udpport=M [NFS] Assign UDP port. 3012 Format: <integer> 2945 Format: <integer> 3013 2946 3014 lockdown= [SECURITY,EARLY] !! 2947 lockdown= [SECURITY] 3015 { integrity | confide 2948 { integrity | confidentiality } 3016 Enable the kernel loc 2949 Enable the kernel lockdown feature. If set to 3017 integrity, kernel fea 2950 integrity, kernel features that allow userland to 3018 modify the running ke 2951 modify the running kernel are disabled. If set to 3019 confidentiality, kern 2952 confidentiality, kernel features that allow userland 3020 to extract confidenti 2953 to extract confidential information from the kernel 3021 are also disabled. 2954 are also disabled. 3022 2955 3023 locktorture.acq_writer_lim= [KNL] 2956 locktorture.acq_writer_lim= [KNL] 3024 Set the time limit in 2957 Set the time limit in jiffies for a lock 3025 acquisition. Acquisi 2958 acquisition. Acquisitions exceeding this limit 3026 will result in a spla 2959 will result in a splat once they do complete. 3027 2960 3028 locktorture.bind_readers= [KNL] 2961 locktorture.bind_readers= [KNL] 3029 Specify the list of C 2962 Specify the list of CPUs to which the readers are 3030 to be bound. 2963 to be bound. 3031 2964 3032 locktorture.bind_writers= [KNL] 2965 locktorture.bind_writers= [KNL] 3033 Specify the list of C 2966 Specify the list of CPUs to which the writers are 3034 to be bound. 2967 to be bound. 3035 2968 3036 locktorture.call_rcu_chains= [KNL] 2969 locktorture.call_rcu_chains= [KNL] 3037 Specify the number of 2970 Specify the number of self-propagating call_rcu() 3038 chains to set up. Th 2971 chains to set up. These are used to ensure that 3039 there is a high proba 2972 there is a high probability of an RCU grace period 3040 in progress at any gi 2973 in progress at any given time. Defaults to 0, 3041 which disables these 2974 which disables these call_rcu() chains. 3042 2975 3043 locktorture.long_hold= [KNL] 2976 locktorture.long_hold= [KNL] 3044 Specify the duration 2977 Specify the duration in milliseconds for the 3045 occasional long-durat 2978 occasional long-duration lock hold time. Defaults 3046 to 100 milliseconds. 2979 to 100 milliseconds. Select 0 to disable. 3047 2980 3048 locktorture.nested_locks= [KNL] 2981 locktorture.nested_locks= [KNL] 3049 Specify the maximum l 2982 Specify the maximum lock nesting depth that 3050 locktorture is to exe 2983 locktorture is to exercise, up to a limit of 8 3051 (MAX_NESTED_LOCKS). 2984 (MAX_NESTED_LOCKS). Specify zero to disable. 3052 Note that this parame 2985 Note that this parameter is ineffective on types 3053 of locks that do not 2986 of locks that do not support nested acquisition. 3054 2987 3055 locktorture.nreaders_stress= [KNL] 2988 locktorture.nreaders_stress= [KNL] 3056 Set the number of loc 2989 Set the number of locking read-acquisition kthreads. 3057 Defaults to being aut 2990 Defaults to being automatically set based on the 3058 number of online CPUs 2991 number of online CPUs. 3059 2992 3060 locktorture.nwriters_stress= [KNL] 2993 locktorture.nwriters_stress= [KNL] 3061 Set the number of loc 2994 Set the number of locking write-acquisition kthreads. 3062 2995 3063 locktorture.onoff_holdoff= [KNL] 2996 locktorture.onoff_holdoff= [KNL] 3064 Set time (s) after bo 2997 Set time (s) after boot for CPU-hotplug testing. 3065 2998 3066 locktorture.onoff_interval= [KNL] 2999 locktorture.onoff_interval= [KNL] 3067 Set time (s) between 3000 Set time (s) between CPU-hotplug operations, or 3068 zero to disable CPU-h 3001 zero to disable CPU-hotplug testing. 3069 3002 3070 locktorture.rt_boost= [KNL] 3003 locktorture.rt_boost= [KNL] 3071 Do periodic testing o 3004 Do periodic testing of real-time lock priority 3072 boosting. Select 0 t 3005 boosting. Select 0 to disable, 1 to boost 3073 only rt_mutex, and 2 3006 only rt_mutex, and 2 to boost unconditionally. 3074 Defaults to 2, which 3007 Defaults to 2, which might seem to be an 3075 odd choice, but which 3008 odd choice, but which should be harmless for 3076 non-real-time spinloc 3009 non-real-time spinlocks, due to their disabling 3077 of preemption. Note 3010 of preemption. Note that non-realtime mutexes 3078 disable boosting. 3011 disable boosting. 3079 3012 3080 locktorture.rt_boost_factor= [KNL] 3013 locktorture.rt_boost_factor= [KNL] 3081 Number that determine 3014 Number that determines how often and for how 3082 long priority boostin 3015 long priority boosting is exercised. This is 3083 scaled down by the nu 3016 scaled down by the number of writers, so that the 3084 number of boosts per 3017 number of boosts per unit time remains roughly 3085 constant as the numbe 3018 constant as the number of writers increases. 3086 On the other hand, th 3019 On the other hand, the duration of each boost 3087 increases with the nu 3020 increases with the number of writers. 3088 3021 3089 locktorture.shuffle_interval= [KNL] 3022 locktorture.shuffle_interval= [KNL] 3090 Set task-shuffle inte 3023 Set task-shuffle interval (jiffies). Shuffling 3091 tasks allows some CPU 3024 tasks allows some CPUs to go into dyntick-idle 3092 mode during the lockt 3025 mode during the locktorture test. 3093 3026 3094 locktorture.shutdown_secs= [KNL] 3027 locktorture.shutdown_secs= [KNL] 3095 Set time (s) after bo 3028 Set time (s) after boot system shutdown. This 3096 is useful for hands-o 3029 is useful for hands-off automated testing. 3097 3030 3098 locktorture.stat_interval= [KNL] 3031 locktorture.stat_interval= [KNL] 3099 Time (s) between stat 3032 Time (s) between statistics printk()s. 3100 3033 3101 locktorture.stutter= [KNL] 3034 locktorture.stutter= [KNL] 3102 Time (s) to stutter t 3035 Time (s) to stutter testing, for example, 3103 specifying five secon 3036 specifying five seconds causes the test to run for 3104 five seconds, wait fo 3037 five seconds, wait for five seconds, and so on. 3105 This tests the lockin 3038 This tests the locking primitive's ability to 3106 transition abruptly t 3039 transition abruptly to and from idle. 3107 3040 3108 locktorture.torture_type= [KNL] 3041 locktorture.torture_type= [KNL] 3109 Specify the locking i 3042 Specify the locking implementation to test. 3110 3043 3111 locktorture.verbose= [KNL] 3044 locktorture.verbose= [KNL] 3112 Enable additional pri 3045 Enable additional printk() statements. 3113 3046 3114 locktorture.writer_fifo= [KNL] 3047 locktorture.writer_fifo= [KNL] 3115 Run the write-side lo 3048 Run the write-side locktorture kthreads at 3116 sched_set_fifo() real 3049 sched_set_fifo() real-time priority. 3117 3050 3118 logibm.irq= [HW,MOUSE] Logitech B 3051 logibm.irq= [HW,MOUSE] Logitech Bus Mouse Driver 3119 Format: <irq> 3052 Format: <irq> 3120 3053 3121 loglevel= [KNL,EARLY] !! 3054 loglevel= All Kernel Messages with a loglevel smaller than the 3122 All Kernel Messages w << 3123 console loglevel will 3055 console loglevel will be printed to the console. It can 3124 also be changed with 3056 also be changed with klogd or other programs. The 3125 loglevels are defined 3057 loglevels are defined as follows: 3126 3058 3127 0 (KERN_EMERG) 3059 0 (KERN_EMERG) system is unusable 3128 1 (KERN_ALERT) 3060 1 (KERN_ALERT) action must be taken immediately 3129 2 (KERN_CRIT) 3061 2 (KERN_CRIT) critical conditions 3130 3 (KERN_ERR) 3062 3 (KERN_ERR) error conditions 3131 4 (KERN_WARNING) 3063 4 (KERN_WARNING) warning conditions 3132 5 (KERN_NOTICE) 3064 5 (KERN_NOTICE) normal but significant condition 3133 6 (KERN_INFO) 3065 6 (KERN_INFO) informational 3134 7 (KERN_DEBUG) 3066 7 (KERN_DEBUG) debug-level messages 3135 3067 3136 log_buf_len=n[KMG] [KNL,EARLY] !! 3068 log_buf_len=n[KMG] Sets the size of the printk ring buffer, 3137 Sets the size of the !! 3069 in bytes. n must be a power of two and greater 3138 n must be a power of !! 3070 than the minimal size. The minimal size is defined 3139 minimal size. The min !! 3071 by LOG_BUF_SHIFT kernel config parameter. There is 3140 LOG_BUF_SHIFT kernel !! 3072 also CONFIG_LOG_CPU_MAX_BUF_SHIFT config parameter 3141 is also CONFIG_LOG_CP !! 3073 that allows to increase the default size depending on 3142 parameter that allows !! 3074 the number of CPUs. See init/Kconfig for more details. 3143 depending on the numb << 3144 for more details. << 3145 3075 3146 logo.nologo [FB] Disables display 3076 logo.nologo [FB] Disables display of the built-in Linux logo. 3147 This may be used to p 3077 This may be used to provide more screen space for 3148 kernel log messages a 3078 kernel log messages and is useful when debugging 3149 kernel boot problems. 3079 kernel boot problems. 3150 3080 3151 lp=0 [LP] Specify paral 3081 lp=0 [LP] Specify parallel ports to use, e.g, 3152 lp=port[,port...] lp=none,parpo 3082 lp=port[,port...] lp=none,parport0 (lp0 not configured, lp1 uses 3153 lp=reset first paralle 3083 lp=reset first parallel port). 'lp=0' disables the 3154 lp=auto printer drive 3084 lp=auto printer driver. 'lp=reset' (which can be 3155 specified in 3085 specified in addition to the ports) causes 3156 attached prin 3086 attached printers to be reset. Using 3157 lp=port1,port 3087 lp=port1,port2,... specifies the parallel ports 3158 to associate 3088 to associate lp devices with, starting with 3159 lp0. A port s 3089 lp0. A port specification may be 'none' to skip 3160 that lp devic 3090 that lp device, or a parport name such as 3161 'parport0'. S 3091 'parport0'. Specifying 'lp=auto' instead of a 3162 port specific 3092 port specification list means that device IDs 3163 from each por 3093 from each port should be examined, to see if 3164 an IEEE 1284- 3094 an IEEE 1284-compliant printer is attached; if 3165 so, the drive 3095 so, the driver will manage that printer. 3166 See also head 3096 See also header of drivers/char/lp.c. 3167 3097 3168 lpj=n [KNL] 3098 lpj=n [KNL] 3169 Sets loops_per_jiffy 3099 Sets loops_per_jiffy to given constant, thus avoiding 3170 time-consuming boot-t 3100 time-consuming boot-time autodetection (up to 250 ms per 3171 CPU). 0 enables autod 3101 CPU). 0 enables autodetection (default). To determine 3172 the correct value for 3102 the correct value for your kernel, boot with normal 3173 autodetection and see 3103 autodetection and see what value is printed. Note that 3174 on SMP systems the pr 3104 on SMP systems the preset will be applied to all CPUs, 3175 which is likely to ca 3105 which is likely to cause problems if your CPUs need 3176 significantly diverge 3106 significantly divergent settings. An incorrect value 3177 will cause delays in 3107 will cause delays in the kernel to be wrong, leading to 3178 unpredictable I/O err 3108 unpredictable I/O errors and other breakage. Although 3179 unlikely, in the extr 3109 unlikely, in the extreme case this might damage your 3180 hardware. 3110 hardware. 3181 3111 >> 3112 ltpc= [NET] >> 3113 Format: <io>,<irq>,<dma> >> 3114 3182 lsm.debug [SECURITY] Enable LSM 3115 lsm.debug [SECURITY] Enable LSM initialization debugging output. 3183 3116 3184 lsm=lsm1,...,lsmN 3117 lsm=lsm1,...,lsmN 3185 [SECURITY] Choose ord 3118 [SECURITY] Choose order of LSM initialization. This 3186 overrides CONFIG_LSM, 3119 overrides CONFIG_LSM, and the "security=" parameter. 3187 3120 >> 3121 machvec= [IA-64] Force the use of a particular machine-vector >> 3122 (machvec) in a generic kernel. >> 3123 Example: machvec=hpzx1 >> 3124 3188 machtype= [Loongson] Share the 3125 machtype= [Loongson] Share the same kernel image file between 3189 different yeeloong la 3126 different yeeloong laptops. 3190 Example: machtype=lem 3127 Example: machtype=lemote-yeeloong-2f-7inch 3191 3128 3192 maxcpus= [SMP,EARLY] Maximum n !! 3129 max_addr=nn[KMG] [KNL,BOOT,IA-64] All physical memory greater >> 3130 than or equal to this physical address is ignored. >> 3131 >> 3132 maxcpus= [SMP] Maximum number of processors that an SMP kernel 3193 will bring up during 3133 will bring up during bootup. maxcpus=n : n >= 0 limits 3194 the kernel to bring u 3134 the kernel to bring up 'n' processors. Surely after 3195 bootup you can bring 3135 bootup you can bring up the other plugged cpu by executing 3196 "echo 1 > /sys/device 3136 "echo 1 > /sys/devices/system/cpu/cpuX/online". So maxcpus 3197 only takes effect dur 3137 only takes effect during system bootup. 3198 While n=0 is a specia 3138 While n=0 is a special case, it is equivalent to "nosmp", 3199 which also disables t 3139 which also disables the IO APIC. 3200 3140 3201 max_loop= [LOOP] The number of 3141 max_loop= [LOOP] The number of loop block devices that get 3202 (loop.max_loop) unconditionally pre-c 3142 (loop.max_loop) unconditionally pre-created at init time. The default 3203 number is configured 3143 number is configured by BLK_DEV_LOOP_MIN_COUNT. Instead 3204 of statically allocat 3144 of statically allocating a predefined number, loop 3205 devices can be reques 3145 devices can be requested on-demand with the 3206 /dev/loop-control int 3146 /dev/loop-control interface. 3207 3147 3208 mce [X86-32] Machine Chec 3148 mce [X86-32] Machine Check Exception 3209 3149 3210 mce=option [X86-64] See Document 3150 mce=option [X86-64] See Documentation/arch/x86/x86_64/boot-options.rst 3211 3151 3212 md= [HW] RAID subsystems 3152 md= [HW] RAID subsystems devices and level 3213 See Documentation/adm 3153 See Documentation/admin-guide/md.rst. 3214 3154 3215 mdacon= [MDA] 3155 mdacon= [MDA] 3216 Format: <first>,<last 3156 Format: <first>,<last> 3217 Specifies range of co 3157 Specifies range of consoles to be captured by the MDA. 3218 3158 3219 mds= [X86,INTEL,EARLY] !! 3159 mds= [X86,INTEL] 3220 Control mitigation fo 3160 Control mitigation for the Micro-architectural Data 3221 Sampling (MDS) vulner 3161 Sampling (MDS) vulnerability. 3222 3162 3223 Certain CPUs are vuln 3163 Certain CPUs are vulnerable to an exploit against CPU 3224 internal buffers whic 3164 internal buffers which can forward information to a 3225 disclosure gadget und 3165 disclosure gadget under certain conditions. 3226 3166 3227 In vulnerable process 3167 In vulnerable processors, the speculatively 3228 forwarded data can be 3168 forwarded data can be used in a cache side channel 3229 attack, to access dat 3169 attack, to access data to which the attacker does 3230 not have direct acces 3170 not have direct access. 3231 3171 3232 This parameter contro 3172 This parameter controls the MDS mitigation. The 3233 options are: 3173 options are: 3234 3174 3235 full - Enable M 3175 full - Enable MDS mitigation on vulnerable CPUs 3236 full,nosmt - Enable M 3176 full,nosmt - Enable MDS mitigation and disable 3237 SMT on v 3177 SMT on vulnerable CPUs 3238 off - Uncondit 3178 off - Unconditionally disable MDS mitigation 3239 3179 3240 On TAA-affected machi 3180 On TAA-affected machines, mds=off can be prevented by 3241 an active TAA mitigat 3181 an active TAA mitigation as both vulnerabilities are 3242 mitigated with the sa 3182 mitigated with the same mechanism so in order to disable 3243 this mitigation, you 3183 this mitigation, you need to specify tsx_async_abort=off 3244 too. 3184 too. 3245 3185 3246 Not specifying this o 3186 Not specifying this option is equivalent to 3247 mds=full. 3187 mds=full. 3248 3188 3249 For details see: Docu 3189 For details see: Documentation/admin-guide/hw-vuln/mds.rst 3250 3190 3251 mem=nn[KMG] [HEXAGON,EARLY] Set t !! 3191 mem=nn[KMG] [HEXAGON] Set the memory size. 3252 Must be specified, ot 3192 Must be specified, otherwise memory size will be 0. 3253 3193 3254 mem=nn[KMG] [KNL,BOOT,EARLY] Forc !! 3194 mem=nn[KMG] [KNL,BOOT] Force usage of a specific amount of memory 3255 of memory Amount of m !! 3195 Amount of memory to be used in cases as follows: 3256 as follows: << 3257 3196 3258 1 for test; 3197 1 for test; 3259 2 when the kernel is 3198 2 when the kernel is not able to see the whole system memory; 3260 3 memory that lies af 3199 3 memory that lies after 'mem=' boundary is excluded from 3261 the hypervisor, then 3200 the hypervisor, then assigned to KVM guests. 3262 4 to limit the memory 3201 4 to limit the memory available for kdump kernel. 3263 3202 3264 [ARC,MICROBLAZE] - th 3203 [ARC,MICROBLAZE] - the limit applies only to low memory, 3265 high memory is not af 3204 high memory is not affected. 3266 3205 3267 [ARM64] - only limits 3206 [ARM64] - only limits memory covered by the linear 3268 mapping. The NOMAP re 3207 mapping. The NOMAP regions are not affected. 3269 3208 3270 [X86] Work as limitin 3209 [X86] Work as limiting max address. Use together 3271 with memmap= to avoid 3210 with memmap= to avoid physical address space collisions. 3272 Without memmap= PCI d 3211 Without memmap= PCI devices could be placed at addresses 3273 belonging to unused R 3212 belonging to unused RAM. 3274 3213 3275 Note that this only t 3214 Note that this only takes effects during boot time since 3276 in above case 3, memo 3215 in above case 3, memory may need be hot added after boot 3277 if system memory of h 3216 if system memory of hypervisor is not sufficient. 3278 3217 3279 mem=nn[KMG]@ss[KMG] 3218 mem=nn[KMG]@ss[KMG] 3280 [ARM,MIPS,EARLY] - ov !! 3219 [ARM,MIPS] - override the memory layout reported by 3281 reported by firmware. !! 3220 firmware. 3282 Define a memory regio 3221 Define a memory region of size nn[KMG] starting at 3283 ss[KMG]. 3222 ss[KMG]. 3284 Multiple different re 3223 Multiple different regions can be specified with 3285 multiple mem= paramet 3224 multiple mem= parameters on the command line. 3286 3225 3287 mem=nopentium [BUGS=X86-32] Disable 3226 mem=nopentium [BUGS=X86-32] Disable usage of 4MB pages for kernel 3288 memory. 3227 memory. 3289 3228 3290 memblock=debug [KNL,EARLY] Enable me !! 3229 memblock=debug [KNL] Enable memblock debug messages. 3291 3230 3292 memchunk=nn[KMG] 3231 memchunk=nn[KMG] 3293 [KNL,SH] Allow user t 3232 [KNL,SH] Allow user to override the default size for 3294 per-device physically 3233 per-device physically contiguous DMA buffers. 3295 3234 3296 memhp_default_state=online/offline/on 3235 memhp_default_state=online/offline/online_kernel/online_movable 3297 [KNL] Set the initial 3236 [KNL] Set the initial state for the memory hotplug 3298 onlining policy. If n 3237 onlining policy. If not specified, the default value is 3299 set according to the 3238 set according to the 3300 CONFIG_MEMORY_HOTPLUG 3239 CONFIG_MEMORY_HOTPLUG_DEFAULT_ONLINE kernel config 3301 option. 3240 option. 3302 See Documentation/adm 3241 See Documentation/admin-guide/mm/memory-hotplug.rst. 3303 3242 3304 memmap=exactmap [KNL,X86,EARLY] Enabl !! 3243 memmap=exactmap [KNL,X86] Enable setting of an exact 3305 E820 memory map, as s 3244 E820 memory map, as specified by the user. 3306 Such memmap=exactmap 3245 Such memmap=exactmap lines can be constructed based on 3307 BIOS output or other 3246 BIOS output or other requirements. See the memmap=nn@ss 3308 option description. 3247 option description. 3309 3248 3310 memmap=nn[KMG]@ss[KMG] 3249 memmap=nn[KMG]@ss[KMG] 3311 [KNL, X86,MIPS,XTENSA !! 3250 [KNL, X86, MIPS, XTENSA] Force usage of a specific region of memory. 3312 Region of memory to b 3251 Region of memory to be used is from ss to ss+nn. 3313 If @ss[KMG] is omitte 3252 If @ss[KMG] is omitted, it is equivalent to mem=nn[KMG], 3314 which limits max addr 3253 which limits max address to nn[KMG]. 3315 Multiple different re 3254 Multiple different regions can be specified, 3316 comma delimited. 3255 comma delimited. 3317 Example: 3256 Example: 3318 memmap=100M@2 3257 memmap=100M@2G,100M#3G,1G!1024G 3319 3258 3320 memmap=nn[KMG]#ss[KMG] 3259 memmap=nn[KMG]#ss[KMG] 3321 [KNL,ACPI,EARLY] Mark !! 3260 [KNL,ACPI] Mark specific memory as ACPI data. 3322 Region of memory to b 3261 Region of memory to be marked is from ss to ss+nn. 3323 3262 3324 memmap=nn[KMG]$ss[KMG] 3263 memmap=nn[KMG]$ss[KMG] 3325 [KNL,ACPI,EARLY] Mark !! 3264 [KNL,ACPI] Mark specific memory as reserved. 3326 Region of memory to b 3265 Region of memory to be reserved is from ss to ss+nn. 3327 Example: Exclude memo 3266 Example: Exclude memory from 0x18690000-0x1869ffff 3328 memmap=64K$0 3267 memmap=64K$0x18690000 3329 or 3268 or 3330 memmap=0x100 3269 memmap=0x10000$0x18690000 3331 Some bootloaders may 3270 Some bootloaders may need an escape character before '$', 3332 like Grub2, otherwise 3271 like Grub2, otherwise '$' and the following number 3333 will be eaten. 3272 will be eaten. 3334 3273 3335 memmap=nn[KMG]!ss[KMG,EARLY] !! 3274 memmap=nn[KMG]!ss[KMG] 3336 [KNL,X86] Mark specif 3275 [KNL,X86] Mark specific memory as protected. 3337 Region of memory to b 3276 Region of memory to be used, from ss to ss+nn. 3338 The memory region may 3277 The memory region may be marked as e820 type 12 (0xc) 3339 and is NVDIMM or ADR 3278 and is NVDIMM or ADR memory. 3340 3279 3341 memmap=<size>%<offset>-<oldtype>+<new 3280 memmap=<size>%<offset>-<oldtype>+<newtype> 3342 [KNL,ACPI,EARLY] Conv !! 3281 [KNL,ACPI] Convert memory within the specified region 3343 from <oldtype> to <ne 3282 from <oldtype> to <newtype>. If "-<oldtype>" is left 3344 out, the whole region 3283 out, the whole region will be marked as <newtype>, 3345 even if previously un 3284 even if previously unavailable. If "+<newtype>" is left 3346 out, matching memory 3285 out, matching memory will be removed. Types are 3347 specified as e820 typ 3286 specified as e820 types, e.g., 1 = RAM, 2 = reserved, 3348 3 = ACPI, 12 = PRAM. 3287 3 = ACPI, 12 = PRAM. 3349 3288 3350 memory_corruption_check=0/1 [X86,EARL !! 3289 memory_corruption_check=0/1 [X86] 3351 Some BIOSes seem to c 3290 Some BIOSes seem to corrupt the first 64k of 3352 memory when doing thi 3291 memory when doing things like suspend/resume. 3353 Setting this option w 3292 Setting this option will scan the memory 3354 looking for corruptio 3293 looking for corruption. Enabling this will 3355 both detect corruptio 3294 both detect corruption and prevent the kernel 3356 from using the memory 3295 from using the memory being corrupted. 3357 However, its intended 3296 However, its intended as a diagnostic tool; if 3358 repeatable BIOS-origi 3297 repeatable BIOS-originated corruption always 3359 affects the same memo 3298 affects the same memory, you can use memmap= 3360 to prevent the kernel 3299 to prevent the kernel from using that memory. 3361 3300 3362 memory_corruption_check_size=size [X8 !! 3301 memory_corruption_check_size=size [X86] 3363 By default it checks 3302 By default it checks for corruption in the low 3364 64k, making this memo 3303 64k, making this memory unavailable for normal 3365 use. Use this parame 3304 use. Use this parameter to scan for 3366 corruption in more or 3305 corruption in more or less memory. 3367 3306 3368 memory_corruption_check_period=second !! 3307 memory_corruption_check_period=seconds [X86] 3369 By default it checks 3308 By default it checks for corruption every 60 3370 seconds. Use this pa 3309 seconds. Use this parameter to check at some 3371 other rate. 0 disabl 3310 other rate. 0 disables periodic checking. 3372 3311 3373 memory_hotplug.memmap_on_memory 3312 memory_hotplug.memmap_on_memory 3374 [KNL,X86,ARM] Boolean 3313 [KNL,X86,ARM] Boolean flag to enable this feature. 3375 Format: {on | off (de 3314 Format: {on | off (default)} 3376 When enabled, runtime 3315 When enabled, runtime hotplugged memory will 3377 allocate its internal 3316 allocate its internal metadata (struct pages, 3378 those vmemmap pages c 3317 those vmemmap pages cannot be optimized even 3379 if hugetlb_free_vmemm 3318 if hugetlb_free_vmemmap is enabled) from the 3380 hotadded memory which 3319 hotadded memory which will allow to hotadd a 3381 lot of memory without 3320 lot of memory without requiring additional 3382 memory to do so. 3321 memory to do so. 3383 This feature is disab 3322 This feature is disabled by default because it 3384 has some implication 3323 has some implication on large (e.g. GB) 3385 allocations in some c 3324 allocations in some configurations (e.g. small 3386 memory blocks). 3325 memory blocks). 3387 The state of the flag 3326 The state of the flag can be read in 3388 /sys/module/memory_ho 3327 /sys/module/memory_hotplug/parameters/memmap_on_memory. 3389 Note that even when e 3328 Note that even when enabled, there are a few cases where 3390 the feature is not ef 3329 the feature is not effective. 3391 3330 3392 memtest= [KNL,X86,ARM,M68K,PPC !! 3331 memtest= [KNL,X86,ARM,M68K,PPC,RISCV] Enable memtest 3393 Format: <integer> 3332 Format: <integer> 3394 default : 0 <disable> 3333 default : 0 <disable> 3395 Specifies the number 3334 Specifies the number of memtest passes to be 3396 performed. Each pass 3335 performed. Each pass selects another test 3397 pattern from a given 3336 pattern from a given set of patterns. Memtest 3398 fills the memory with 3337 fills the memory with this pattern, validates 3399 memory contents and r 3338 memory contents and reserves bad memory 3400 regions that are dete 3339 regions that are detected. 3401 3340 3402 mem_encrypt= [X86-64] AMD Secure M 3341 mem_encrypt= [X86-64] AMD Secure Memory Encryption (SME) control 3403 Valid arguments: on, 3342 Valid arguments: on, off 3404 Default: off 3343 Default: off 3405 mem_encrypt=on: 3344 mem_encrypt=on: Activate SME 3406 mem_encrypt=off: 3345 mem_encrypt=off: Do not activate SME 3407 3346 3408 Refer to Documentatio 3347 Refer to Documentation/virt/kvm/x86/amd-memory-encryption.rst 3409 for details on when m 3348 for details on when memory encryption can be activated. 3410 3349 3411 mem_sleep_default= [SUSPEND] Def 3350 mem_sleep_default= [SUSPEND] Default system suspend mode: 3412 s2idle - Suspend-To- 3351 s2idle - Suspend-To-Idle 3413 shallow - Power-On Su 3352 shallow - Power-On Suspend or equivalent (if supported) 3414 deep - Suspend-To- 3353 deep - Suspend-To-RAM or equivalent (if supported) 3415 See Documentation/adm 3354 See Documentation/admin-guide/pm/sleep-states.rst. 3416 3355 >> 3356 mfgpt_irq= [IA-32] Specify the IRQ to use for the >> 3357 Multi-Function General Purpose Timers on AMD Geode >> 3358 platforms. >> 3359 3417 mfgptfix [X86-32] Fix MFGPT ti 3360 mfgptfix [X86-32] Fix MFGPT timers on AMD Geode platforms when 3418 the BIOS has incorrec 3361 the BIOS has incorrectly applied a workaround. TinyBIOS 3419 version 0.98 is known 3362 version 0.98 is known to be affected, 0.99 fixes the 3420 problem by letting th 3363 problem by letting the user disable the workaround. 3421 3364 3422 mga= [HW,DRM] 3365 mga= [HW,DRM] 3423 3366 3424 microcode.force_minrev= [X86] 3367 microcode.force_minrev= [X86] 3425 Format: <bool> 3368 Format: <bool> 3426 Enable or disable the 3369 Enable or disable the microcode minimal revision 3427 enforcement for the r 3370 enforcement for the runtime microcode loader. 3428 3371 >> 3372 min_addr=nn[KMG] [KNL,BOOT,IA-64] All physical memory below this >> 3373 physical address is ignored. >> 3374 3429 mini2440= [ARM,HW,KNL] 3375 mini2440= [ARM,HW,KNL] 3430 Format:[0..2][b][c][t 3376 Format:[0..2][b][c][t] 3431 Default: "0tb" 3377 Default: "0tb" 3432 MINI2440 configuratio 3378 MINI2440 configuration specification: 3433 0 - The attached scre 3379 0 - The attached screen is the 3.5" TFT 3434 1 - The attached scre 3380 1 - The attached screen is the 7" TFT 3435 2 - The VGA Shield is 3381 2 - The VGA Shield is attached (1024x768) 3436 Leaving out the scree 3382 Leaving out the screen size parameter will not load 3437 the TFT driver, and t 3383 the TFT driver, and the framebuffer will be left 3438 unconfigured. 3384 unconfigured. 3439 b - Enable backlight. 3385 b - Enable backlight. The TFT backlight pin will be 3440 linked to the kernel 3386 linked to the kernel VESA blanking code and a GPIO 3441 LED. This parameter i 3387 LED. This parameter is not necessary when using the 3442 VGA shield. 3388 VGA shield. 3443 c - Enable the s3c ca 3389 c - Enable the s3c camera interface. 3444 t - Reserved for enab 3390 t - Reserved for enabling touchscreen support. The 3445 touchscreen support i 3391 touchscreen support is not enabled in the mainstream 3446 kernel as of 2.6.30, 3392 kernel as of 2.6.30, a preliminary port can be found 3447 in the "bleeding edge 3393 in the "bleeding edge" mini2440 support kernel at 3448 https://repo.or.cz/w/ 3394 https://repo.or.cz/w/linux-2.6/mini2440.git 3449 3395 3450 mitigations= 3396 mitigations= 3451 [X86,PPC,S390,ARM64,E !! 3397 [X86,PPC,S390,ARM64] Control optional mitigations for 3452 CPU vulnerabilities. 3398 CPU vulnerabilities. This is a set of curated, 3453 arch-independent opti 3399 arch-independent options, each of which is an 3454 aggregation of existi 3400 aggregation of existing arch-specific options. 3455 3401 3456 Note, "mitigations" i 3402 Note, "mitigations" is supported if and only if the 3457 kernel was built with 3403 kernel was built with CPU_MITIGATIONS=y. 3458 3404 3459 off 3405 off 3460 Disable all o 3406 Disable all optional CPU mitigations. This 3461 improves syst 3407 improves system performance, but it may also 3462 expose users 3408 expose users to several CPU vulnerabilities. 3463 Equivalent to 3409 Equivalent to: if nokaslr then kpti=0 [ARM64] 3464 3410 gather_data_sampling=off [X86] 3465 3411 kvm.nx_huge_pages=off [X86] 3466 3412 l1tf=off [X86] 3467 3413 mds=off [X86] 3468 3414 mmio_stale_data=off [X86] 3469 3415 no_entry_flush [PPC] 3470 3416 no_uaccess_flush [PPC] 3471 3417 nobp=0 [S390] 3472 3418 nopti [X86,PPC] 3473 3419 nospectre_bhb [ARM64] 3474 3420 nospectre_v1 [X86,PPC] 3475 3421 nospectre_v2 [X86,PPC,S390,ARM64] 3476 3422 reg_file_data_sampling=off [X86] 3477 3423 retbleed=off [X86] 3478 << 3479 3424 spec_store_bypass_disable=off [X86,PPC] 3480 3425 spectre_bhi=off [X86] 3481 3426 spectre_v2_user=off [X86] 3482 3427 srbds=off [X86,INTEL] 3483 3428 ssbd=force-off [ARM64] 3484 3429 tsx_async_abort=off [X86] 3485 3430 3486 Exceptions: 3431 Exceptions: 3487 3432 This does not have any effect on 3488 3433 kvm.nx_huge_pages when 3489 3434 kvm.nx_huge_pages=force. 3490 3435 3491 auto (default) 3436 auto (default) 3492 Mitigate all 3437 Mitigate all CPU vulnerabilities, but leave SMT 3493 enabled, even 3438 enabled, even if it's vulnerable. This is for 3494 users who don 3439 users who don't want to be surprised by SMT 3495 getting disab 3440 getting disabled across kernel upgrades, or who 3496 have other wa 3441 have other ways of avoiding SMT-based attacks. 3497 Equivalent to 3442 Equivalent to: (default behavior) 3498 3443 3499 auto,nosmt 3444 auto,nosmt 3500 Mitigate all 3445 Mitigate all CPU vulnerabilities, disabling SMT 3501 if needed. T 3446 if needed. This is for users who always want to 3502 be fully miti 3447 be fully mitigated, even if it means losing SMT. 3503 Equivalent to 3448 Equivalent to: l1tf=flush,nosmt [X86] 3504 3449 mds=full,nosmt [X86] 3505 3450 tsx_async_abort=full,nosmt [X86] 3506 3451 mmio_stale_data=full,nosmt [X86] 3507 3452 retbleed=auto,nosmt [X86] 3508 3453 3509 mminit_loglevel= 3454 mminit_loglevel= 3510 [KNL,EARLY] When CONF !! 3455 [KNL] When CONFIG_DEBUG_MEMORY_INIT is set, this 3511 parameter allows cont 3456 parameter allows control of the logging verbosity for 3512 the additional memory 3457 the additional memory initialisation checks. A value 3513 of 0 disables mminit 3458 of 0 disables mminit logging and a level of 4 will 3514 log everything. Infor 3459 log everything. Information is printed at KERN_DEBUG 3515 so loglevel=8 may als 3460 so loglevel=8 may also need to be specified. 3516 3461 3517 mmio_stale_data= 3462 mmio_stale_data= 3518 [X86,INTEL,EARLY] Con !! 3463 [X86,INTEL] Control mitigation for the Processor 3519 MMIO Stale Data vulne 3464 MMIO Stale Data vulnerabilities. 3520 3465 3521 Processor MMIO Stale 3466 Processor MMIO Stale Data is a class of 3522 vulnerabilities that 3467 vulnerabilities that may expose data after an MMIO 3523 operation. Exposed da 3468 operation. Exposed data could originate or end in 3524 the same CPU buffers 3469 the same CPU buffers as affected by MDS and TAA. 3525 Therefore, similar to 3470 Therefore, similar to MDS and TAA, the mitigation 3526 is to clear the affec 3471 is to clear the affected CPU buffers. 3527 3472 3528 This parameter contro 3473 This parameter controls the mitigation. The 3529 options are: 3474 options are: 3530 3475 3531 full - Enable m 3476 full - Enable mitigation on vulnerable CPUs 3532 3477 3533 full,nosmt - Enable m 3478 full,nosmt - Enable mitigation and disable SMT on 3534 vulnerab 3479 vulnerable CPUs. 3535 3480 3536 off - Uncondit 3481 off - Unconditionally disable mitigation 3537 3482 3538 On MDS or TAA affecte 3483 On MDS or TAA affected machines, 3539 mmio_stale_data=off c 3484 mmio_stale_data=off can be prevented by an active 3540 MDS or TAA mitigation 3485 MDS or TAA mitigation as these vulnerabilities are 3541 mitigated with the sa 3486 mitigated with the same mechanism so in order to 3542 disable this mitigati 3487 disable this mitigation, you need to specify 3543 mds=off and tsx_async 3488 mds=off and tsx_async_abort=off too. 3544 3489 3545 Not specifying this o 3490 Not specifying this option is equivalent to 3546 mmio_stale_data=full. 3491 mmio_stale_data=full. 3547 3492 3548 For details see: 3493 For details see: 3549 Documentation/admin-g 3494 Documentation/admin-guide/hw-vuln/processor_mmio_stale_data.rst 3550 3495 3551 <module>.async_probe[=<bool>] [KNL] 3496 <module>.async_probe[=<bool>] [KNL] 3552 If no <bool> value is 3497 If no <bool> value is specified or if the value 3553 specified is not a va 3498 specified is not a valid <bool>, enable asynchronous 3554 probe on this module. 3499 probe on this module. Otherwise, enable/disable 3555 asynchronous probe on 3500 asynchronous probe on this module as indicated by the 3556 <bool> value. See als 3501 <bool> value. See also: module.async_probe 3557 3502 3558 module.async_probe=<bool> 3503 module.async_probe=<bool> 3559 [KNL] When set to tru 3504 [KNL] When set to true, modules will use async probing 3560 by default. To enable 3505 by default. To enable/disable async probing for a 3561 specific module, use 3506 specific module, use the module specific control that 3562 is documented under < 3507 is documented under <module>.async_probe. When both 3563 module.async_probe an 3508 module.async_probe and <module>.async_probe are 3564 specified, <module>.a 3509 specified, <module>.async_probe takes precedence for 3565 the specific module. 3510 the specific module. 3566 3511 3567 module.enable_dups_trace 3512 module.enable_dups_trace 3568 [KNL] When CONFIG_MOD 3513 [KNL] When CONFIG_MODULE_DEBUG_AUTOLOAD_DUPS is set, 3569 this means that dupli 3514 this means that duplicate request_module() calls will 3570 trigger a WARN_ON() i 3515 trigger a WARN_ON() instead of a pr_warn(). Note that 3571 if MODULE_DEBUG_AUTOL 3516 if MODULE_DEBUG_AUTOLOAD_DUPS_TRACE is set, WARN_ON()s 3572 will always be issued 3517 will always be issued and this option does nothing. 3573 module.sig_enforce 3518 module.sig_enforce 3574 [KNL] When CONFIG_MOD 3519 [KNL] When CONFIG_MODULE_SIG is set, this means that 3575 modules without (vali 3520 modules without (valid) signatures will fail to load. 3576 Note that if CONFIG_M 3521 Note that if CONFIG_MODULE_SIG_FORCE is set, that 3577 is always true, so th 3522 is always true, so this option does nothing. 3578 3523 3579 module_blacklist= [KNL] Do not load 3524 module_blacklist= [KNL] Do not load a comma-separated list of 3580 modules. Useful for 3525 modules. Useful for debugging problem modules. 3581 3526 3582 mousedev.tap_time= 3527 mousedev.tap_time= 3583 [MOUSE] Maximum time 3528 [MOUSE] Maximum time between finger touching and 3584 leaving touchpad surf 3529 leaving touchpad surface for touch to be considered 3585 a tap and be reported 3530 a tap and be reported as a left button click (for 3586 touchpads working in 3531 touchpads working in absolute mode only). 3587 Format: <msecs> 3532 Format: <msecs> 3588 mousedev.xres= [MOUSE] Horizontal sc 3533 mousedev.xres= [MOUSE] Horizontal screen resolution, used for devices 3589 reporting absolute co 3534 reporting absolute coordinates, such as tablets 3590 mousedev.yres= [MOUSE] Vertical scre 3535 mousedev.yres= [MOUSE] Vertical screen resolution, used for devices 3591 reporting absolute co 3536 reporting absolute coordinates, such as tablets 3592 3537 3593 movablecore= [KNL,X86,PPC,EARLY] !! 3538 movablecore= [KNL,X86,IA-64,PPC] 3594 Format: nn[KMGTPE] | 3539 Format: nn[KMGTPE] | nn% 3595 This parameter is the 3540 This parameter is the complement to kernelcore=, it 3596 specifies the amount 3541 specifies the amount of memory used for migratable 3597 allocations. If both 3542 allocations. If both kernelcore and movablecore is 3598 specified, then kerne 3543 specified, then kernelcore will be at *least* the 3599 specified value but m 3544 specified value but may be more. If movablecore on its 3600 own is specified, the 3545 own is specified, the administrator must be careful 3601 that the amount of me 3546 that the amount of memory usable for all allocations 3602 is not too small. 3547 is not too small. 3603 3548 3604 movable_node [KNL,EARLY] Boot-time !! 3549 movable_node [KNL] Boot-time switch to make hotplugable memory 3605 NUMA nodes to be mova 3550 NUMA nodes to be movable. This means that the memory 3606 of such nodes will be 3551 of such nodes will be usable only for movable 3607 allocations which rul 3552 allocations which rules out almost all kernel 3608 allocations. Use with 3553 allocations. Use with caution! 3609 3554 3610 MTD_Partition= [MTD] 3555 MTD_Partition= [MTD] 3611 Format: <name>,<regio 3556 Format: <name>,<region-number>,<size>,<offset> 3612 3557 3613 MTD_Region= [MTD] Format: 3558 MTD_Region= [MTD] Format: 3614 <name>,<region-number 3559 <name>,<region-number>[,<base>,<size>,<buswidth>,<altbuswidth>] 3615 3560 3616 mtdparts= [MTD] 3561 mtdparts= [MTD] 3617 See drivers/mtd/parse 3562 See drivers/mtd/parsers/cmdlinepart.c 3618 3563 >> 3564 mtdset= [ARM] >> 3565 ARM/S3C2412 JIVE boot control >> 3566 >> 3567 See arch/arm/mach-s3c/mach-jive.c >> 3568 3619 mtouchusb.raw_coordinates= 3569 mtouchusb.raw_coordinates= 3620 [HW] Make the MicroTo 3570 [HW] Make the MicroTouch USB driver use raw coordinates 3621 ('y', default) or coo 3571 ('y', default) or cooked coordinates ('n') 3622 3572 3623 mtrr=debug [X86,EARLY] !! 3573 mtrr=debug [X86] 3624 Enable printing debug 3574 Enable printing debug information related to MTRR 3625 registers at boot tim 3575 registers at boot time. 3626 3576 3627 mtrr_chunk_size=nn[KMG,X86,EARLY] !! 3577 mtrr_chunk_size=nn[KMG] [X86] 3628 used for mtrr cleanup 3578 used for mtrr cleanup. It is largest continuous chunk 3629 that could hold holes 3579 that could hold holes aka. UC entries. 3630 3580 3631 mtrr_gran_size=nn[KMG,X86,EARLY] !! 3581 mtrr_gran_size=nn[KMG] [X86] 3632 Used for mtrr cleanup 3582 Used for mtrr cleanup. It is granularity of mtrr block. 3633 Default is 1. 3583 Default is 1. 3634 Large value could pre 3584 Large value could prevent small alignment from 3635 using up MTRRs. 3585 using up MTRRs. 3636 3586 3637 mtrr_spare_reg_nr=n [X86,EARLY] !! 3587 mtrr_spare_reg_nr=n [X86] 3638 Format: <integer> 3588 Format: <integer> 3639 Range: 0,7 : spare re 3589 Range: 0,7 : spare reg number 3640 Default : 1 3590 Default : 1 3641 Used for mtrr cleanup 3591 Used for mtrr cleanup. It is spare mtrr entries number. 3642 Set to 2 or more if y 3592 Set to 2 or more if your graphical card needs more. 3643 3593 3644 multitce=off [PPC] This parameter 3594 multitce=off [PPC] This parameter disables the use of the pSeries 3645 firmware feature for 3595 firmware feature for updating multiple TCE entries 3646 at a time. 3596 at a time. 3647 3597 3648 n2= [NET] SDL Inc. RISCom 3598 n2= [NET] SDL Inc. RISCom/N2 synchronous serial card 3649 3599 3650 netdev= [NET] Network devices 3600 netdev= [NET] Network devices parameters 3651 Format: <irq>,<io>,<m 3601 Format: <irq>,<io>,<mem_start>,<mem_end>,<name> 3652 Note that mem_start i 3602 Note that mem_start is often overloaded to mean 3653 something different a 3603 something different and driver-specific. 3654 This usage is only do 3604 This usage is only documented in each driver source 3655 file if at all. 3605 file if at all. 3656 3606 3657 netpoll.carrier_timeout= 3607 netpoll.carrier_timeout= 3658 [NET] Specifies amoun 3608 [NET] Specifies amount of time (in seconds) that 3659 netpoll should wait f 3609 netpoll should wait for a carrier. By default netpoll 3660 waits 4 seconds. 3610 waits 4 seconds. 3661 3611 3662 nf_conntrack.acct= 3612 nf_conntrack.acct= 3663 [NETFILTER] Enable co 3613 [NETFILTER] Enable connection tracking flow accounting 3664 0 to disable accounti 3614 0 to disable accounting 3665 1 to enable accountin 3615 1 to enable accounting 3666 Default value is 0. 3616 Default value is 0. 3667 3617 3668 nfs.cache_getent= 3618 nfs.cache_getent= 3669 [NFS] sets the pathna 3619 [NFS] sets the pathname to the program which is used 3670 to update the NFS cli 3620 to update the NFS client cache entries. 3671 3621 3672 nfs.cache_getent_timeout= 3622 nfs.cache_getent_timeout= 3673 [NFS] sets the timeou 3623 [NFS] sets the timeout after which an attempt to 3674 update a cache entry 3624 update a cache entry is deemed to have failed. 3675 3625 3676 nfs.callback_nr_threads= 3626 nfs.callback_nr_threads= 3677 [NFSv4] set the total 3627 [NFSv4] set the total number of threads that the 3678 NFS client will assig 3628 NFS client will assign to service NFSv4 callback 3679 requests. 3629 requests. 3680 3630 3681 nfs.callback_tcpport= 3631 nfs.callback_tcpport= 3682 [NFS] set the TCP por 3632 [NFS] set the TCP port on which the NFSv4 callback 3683 channel should listen 3633 channel should listen. 3684 3634 3685 nfs.delay_retrans= 3635 nfs.delay_retrans= 3686 [NFS] specifies the n 3636 [NFS] specifies the number of times the NFSv4 client 3687 retries the request b 3637 retries the request before returning an EAGAIN error, 3688 after a reply of NFS4 3638 after a reply of NFS4ERR_DELAY from the server. 3689 Only applies if the s 3639 Only applies if the softerr mount option is enabled, 3690 and the specified val 3640 and the specified value is >= 0. 3691 3641 3692 nfs.enable_ino64= 3642 nfs.enable_ino64= 3693 [NFS] enable 64-bit i 3643 [NFS] enable 64-bit inode numbers. 3694 If zero, the NFS clie 3644 If zero, the NFS client will fake up a 32-bit inode 3695 number for the readdi 3645 number for the readdir() and stat() syscalls instead 3696 of returning the full 3646 of returning the full 64-bit number. 3697 The default is to ret 3647 The default is to return 64-bit inode numbers. 3698 3648 3699 nfs.idmap_cache_timeout= 3649 nfs.idmap_cache_timeout= 3700 [NFS] set the maximum 3650 [NFS] set the maximum lifetime for idmapper cache 3701 entries. 3651 entries. 3702 3652 3703 nfs.max_session_cb_slots= 3653 nfs.max_session_cb_slots= 3704 [NFSv4.1] Sets the ma 3654 [NFSv4.1] Sets the maximum number of session 3705 slots the client will 3655 slots the client will assign to the callback 3706 channel. This determi 3656 channel. This determines the maximum number of 3707 callbacks the client 3657 callbacks the client will process in parallel for 3708 a particular server. 3658 a particular server. 3709 3659 3710 nfs.max_session_slots= 3660 nfs.max_session_slots= 3711 [NFSv4.1] Sets the ma 3661 [NFSv4.1] Sets the maximum number of session slots 3712 the client will attem 3662 the client will attempt to negotiate with the server. 3713 This limits the numbe 3663 This limits the number of simultaneous RPC requests 3714 that the client can s 3664 that the client can send to the NFSv4.1 server. 3715 Note that there is li 3665 Note that there is little point in setting this 3716 value higher than the 3666 value higher than the max_tcp_slot_table_limit. 3717 3667 3718 nfs.nfs4_disable_idmapping= 3668 nfs.nfs4_disable_idmapping= 3719 [NFSv4] When set to t 3669 [NFSv4] When set to the default of '1', this option 3720 ensures that both the 3670 ensures that both the RPC level authentication 3721 scheme and the NFS le 3671 scheme and the NFS level operations agree to use 3722 numeric uids/gids if 3672 numeric uids/gids if the mount is using the 3723 'sec=sys' security fl 3673 'sec=sys' security flavour. In effect it is 3724 disabling idmapping, 3674 disabling idmapping, which can make migration from 3725 legacy NFSv2/v3 syste 3675 legacy NFSv2/v3 systems to NFSv4 easier. 3726 Servers that do not s 3676 Servers that do not support this mode of operation 3727 will be autodetected 3677 will be autodetected by the client, and it will fall 3728 back to using the idm 3678 back to using the idmapper. 3729 To turn off this beha 3679 To turn off this behaviour, set the value to '0'. 3730 3680 3731 nfs.nfs4_unique_id= 3681 nfs.nfs4_unique_id= 3732 [NFS4] Specify an add 3682 [NFS4] Specify an additional fixed unique ident- 3733 ification string that 3683 ification string that NFSv4 clients can insert into 3734 their nfs_client_id4 3684 their nfs_client_id4 string. This is typically a 3735 UUID that is generate 3685 UUID that is generated at system install time. 3736 3686 3737 nfs.recover_lost_locks= 3687 nfs.recover_lost_locks= 3738 [NFSv4] Attempt to re 3688 [NFSv4] Attempt to recover locks that were lost due 3739 to a lease timeout on 3689 to a lease timeout on the server. Please note that 3740 doing this risks data 3690 doing this risks data corruption, since there are 3741 no guarantees that th 3691 no guarantees that the file will remain unchanged 3742 after the locks are l 3692 after the locks are lost. 3743 If you want to enable 3693 If you want to enable the kernel legacy behaviour of 3744 attempting to recover 3694 attempting to recover these locks, then set this 3745 parameter to '1'. 3695 parameter to '1'. 3746 The default parameter 3696 The default parameter value of '0' causes the kernel 3747 not to attempt recove 3697 not to attempt recovery of lost locks. 3748 3698 3749 nfs.send_implementation_id= 3699 nfs.send_implementation_id= 3750 [NFSv4.1] Send client 3700 [NFSv4.1] Send client implementation identification 3751 information in exchan 3701 information in exchange_id requests. 3752 If zero, no implement 3702 If zero, no implementation identification information 3753 will be sent. 3703 will be sent. 3754 The default is to sen 3704 The default is to send the implementation identification 3755 information. 3705 information. 3756 3706 3757 nfs4.layoutstats_timer= 3707 nfs4.layoutstats_timer= 3758 [NFSv4.2] Change the 3708 [NFSv4.2] Change the rate at which the kernel sends 3759 layoutstats to the pN 3709 layoutstats to the pNFS metadata server. 3760 3710 3761 Setting this to value 3711 Setting this to value to 0 causes the kernel to use 3762 whatever value is the 3712 whatever value is the default set by the layout 3763 driver. A non-zero va 3713 driver. A non-zero value sets the minimum interval 3764 in seconds between la 3714 in seconds between layoutstats transmissions. 3765 3715 3766 nfsd.inter_copy_offload_enable= 3716 nfsd.inter_copy_offload_enable= 3767 [NFSv4.2] When set to 3717 [NFSv4.2] When set to 1, the server will support 3768 server-to-server copi 3718 server-to-server copies for which this server is 3769 the destination of th 3719 the destination of the copy. 3770 3720 3771 nfsd.nfs4_disable_idmapping= 3721 nfsd.nfs4_disable_idmapping= 3772 [NFSv4] When set to t 3722 [NFSv4] When set to the default of '1', the NFSv4 3773 server will return on 3723 server will return only numeric uids and gids to 3774 clients using auth_sy 3724 clients using auth_sys, and will accept numeric uids 3775 and gids from such cl 3725 and gids from such clients. This is intended to ease 3776 migration from NFSv2/ 3726 migration from NFSv2/v3. 3777 3727 3778 nfsd.nfsd4_ssc_umount_timeout= 3728 nfsd.nfsd4_ssc_umount_timeout= 3779 [NFSv4.2] When used a 3729 [NFSv4.2] When used as the destination of a 3780 server-to-server copy 3730 server-to-server copy, knfsd temporarily mounts 3781 the source server. I 3731 the source server. It caches the mount in case 3782 it will be needed aga 3732 it will be needed again, and discards it if not 3783 used for the number o 3733 used for the number of milliseconds specified by 3784 this parameter. 3734 this parameter. 3785 3735 3786 nfsaddrs= [NFS] Deprecated. Us 3736 nfsaddrs= [NFS] Deprecated. Use ip= instead. 3787 See Documentation/adm 3737 See Documentation/admin-guide/nfs/nfsroot.rst. 3788 3738 3789 nfsroot= [NFS] nfs root filesy 3739 nfsroot= [NFS] nfs root filesystem for disk-less boxes. 3790 See Documentation/adm 3740 See Documentation/admin-guide/nfs/nfsroot.rst. 3791 3741 3792 nfsrootdebug [NFS] enable nfsroot 3742 nfsrootdebug [NFS] enable nfsroot debugging messages. 3793 See Documentation/adm 3743 See Documentation/admin-guide/nfs/nfsroot.rst. 3794 3744 3795 nmi_backtrace.backtrace_idle [KNL] 3745 nmi_backtrace.backtrace_idle [KNL] 3796 Dump stacks even of i 3746 Dump stacks even of idle CPUs in response to an 3797 NMI stack-backtrace r 3747 NMI stack-backtrace request. 3798 3748 3799 nmi_debug= [KNL,SH] Specify one 3749 nmi_debug= [KNL,SH] Specify one or more actions to take 3800 when a NMI is trigger 3750 when a NMI is triggered. 3801 Format: [state][,regs 3751 Format: [state][,regs][,debounce][,die] 3802 3752 3803 nmi_watchdog= [KNL,BUGS=X86] Debugg 3753 nmi_watchdog= [KNL,BUGS=X86] Debugging features for SMP kernels 3804 Format: [panic,][nopa !! 3754 Format: [panic,][nopanic,][num] 3805 Valid num: 0 or 1 3755 Valid num: 0 or 1 3806 0 - turn hardlockup d 3756 0 - turn hardlockup detector in nmi_watchdog off 3807 1 - turn hardlockup d 3757 1 - turn hardlockup detector in nmi_watchdog on 3808 rNNN - configure the << 3809 << 3810 When panic is specifi 3758 When panic is specified, panic when an NMI watchdog 3811 timeout occurs (or 'n 3759 timeout occurs (or 'nopanic' to not panic on an NMI 3812 watchdog, if CONFIG_B 3760 watchdog, if CONFIG_BOOTPARAM_HARDLOCKUP_PANIC is set) 3813 To disable both hard 3761 To disable both hard and soft lockup detectors, 3814 please see 'nowatchdo 3762 please see 'nowatchdog'. 3815 This is useful when y 3763 This is useful when you use a panic=... timeout and 3816 need the box quickly 3764 need the box quickly up again. 3817 3765 3818 These settings can be 3766 These settings can be accessed at runtime via 3819 the nmi_watchdog and 3767 the nmi_watchdog and hardlockup_panic sysctls. 3820 3768 3821 no387 [BUGS=X86-32] Tells t 3769 no387 [BUGS=X86-32] Tells the kernel to use the 387 maths 3822 emulation library eve 3770 emulation library even if a 387 maths coprocessor 3823 is present. 3771 is present. 3824 3772 3825 no4lvl [RISCV,EARLY] Disable !! 3773 no4lvl [RISCV] Disable 4-level and 5-level paging modes. Forces 3826 Forces kernel to use !! 3774 kernel to use 3-level paging instead. 3827 3775 3828 no5lvl [X86-64,RISCV,EARLY] !! 3776 no5lvl [X86-64,RISCV] Disable 5-level paging mode. Forces 3829 kernel to use 4-level 3777 kernel to use 4-level paging instead. 3830 3778 >> 3779 noaliencache [MM, NUMA, SLAB] Disables the allocation of alien >> 3780 caches in the slab allocator. Saves per-node memory, >> 3781 but will impact performance. >> 3782 3831 noalign [KNL,ARM] 3783 noalign [KNL,ARM] 3832 3784 3833 noapic [SMP,APIC,EARLY] Tell !! 3785 noaltinstr [S390] Disables alternative instructions patching >> 3786 (CPU alternatives feature). >> 3787 >> 3788 noapic [SMP,APIC] Tells the kernel to not make use of any 3834 IOAPICs that may be p 3789 IOAPICs that may be present in the system. 3835 3790 3836 noautogroup Disable scheduler aut 3791 noautogroup Disable scheduler automatic task group creation. 3837 3792 3838 nocache [ARM,EARLY] !! 3793 nocache [ARM] 3839 3794 3840 no_console_suspend 3795 no_console_suspend 3841 [HW] Never suspend th 3796 [HW] Never suspend the console 3842 Disable suspending of 3797 Disable suspending of consoles during suspend and 3843 hibernate operations. 3798 hibernate operations. Once disabled, debugging 3844 messages can reach va 3799 messages can reach various consoles while the rest 3845 of the system is bein 3800 of the system is being put to sleep (ie, while 3846 debugging driver susp 3801 debugging driver suspend/resume hooks). This may 3847 not work reliably wit 3802 not work reliably with all consoles, but is known 3848 to work with serial a 3803 to work with serial and VGA consoles. 3849 To facilitate more fl 3804 To facilitate more flexible debugging, we also add 3850 console_suspend, a pr 3805 console_suspend, a printk module parameter to control 3851 it. Users could use c 3806 it. Users could use console_suspend (usually 3852 /sys/module/printk/pa 3807 /sys/module/printk/parameters/console_suspend) to 3853 turn on/off it dynami 3808 turn on/off it dynamically. 3854 3809 3855 no_debug_objects 3810 no_debug_objects 3856 [KNL,EARLY] Disable o !! 3811 [KNL] Disable object debugging 3857 3812 3858 nodsp [SH] Disable hardware 3813 nodsp [SH] Disable hardware DSP at boot time. 3859 3814 3860 noefi [EFI,EARLY] Disable E !! 3815 noefi Disable EFI runtime services support. >> 3816 >> 3817 no_entry_flush [PPC] Don't flush the L1-D cache when entering the kernel. 3861 3818 3862 no_entry_flush [PPC,EARLY] Don't flu !! 3819 noexec [IA-64] 3863 3820 3864 noexec32 [X86-64] 3821 noexec32 [X86-64] 3865 This affects only 32- 3822 This affects only 32-bit executables. 3866 noexec32=on: enable n 3823 noexec32=on: enable non-executable mappings (default) 3867 read doesn't 3824 read doesn't imply executable mappings 3868 noexec32=off: disable 3825 noexec32=off: disable non-executable mappings 3869 read implies 3826 read implies executable mappings 3870 3827 3871 no_file_caps Tells the kernel not 3828 no_file_caps Tells the kernel not to honor file capabilities. The 3872 only way then for a f 3829 only way then for a file to be executed with privilege 3873 is to be setuid root 3830 is to be setuid root or executed by root. 3874 3831 3875 nofpu [MIPS,SH] Disable har 3832 nofpu [MIPS,SH] Disable hardware FPU at boot time. 3876 3833 3877 nofsgsbase [X86] Disables FSGSBA 3834 nofsgsbase [X86] Disables FSGSBASE instructions. 3878 3835 3879 nofxsr [BUGS=X86-32] Disable 3836 nofxsr [BUGS=X86-32] Disables x86 floating point extended 3880 register save and res 3837 register save and restore. The kernel will only save 3881 legacy floating-point 3838 legacy floating-point registers on task switch. 3882 3839 >> 3840 nohalt [IA-64] Tells the kernel not to use the power saving >> 3841 function PAL_HALT_LIGHT when idle. This increases >> 3842 power-consumption. On the positive side, it reduces >> 3843 interrupt wake-up latency, which may improve performance >> 3844 in certain environments such as networked servers or >> 3845 real-time systems. >> 3846 3883 no_hash_pointers 3847 no_hash_pointers 3884 [KNL,EARLY] << 3885 Force pointers printe 3848 Force pointers printed to the console or buffers to be 3886 unhashed. By default 3849 unhashed. By default, when a pointer is printed via %p 3887 format string, that p 3850 format string, that pointer is "hashed", i.e. obscured 3888 by hashing the pointe 3851 by hashing the pointer value. This is a security feature 3889 that hides actual ker 3852 that hides actual kernel addresses from unprivileged 3890 users, but it also ma 3853 users, but it also makes debugging the kernel more 3891 difficult since unequ 3854 difficult since unequal pointers can no longer be 3892 compared. However, i 3855 compared. However, if this command-line option is 3893 specified, then all n 3856 specified, then all normal pointers will have their true 3894 value printed. This o 3857 value printed. This option should only be specified when 3895 debugging the kernel. 3858 debugging the kernel. Please do not use on production 3896 kernels. 3859 kernels. 3897 3860 3898 nohibernate [HIBERNATION] Disable 3861 nohibernate [HIBERNATION] Disable hibernation and resume. 3899 3862 3900 nohlt [ARM,ARM64,MICROBLAZE !! 3863 nohlt [ARM,ARM64,MICROBLAZE,MIPS,PPC,SH] Forces the kernel to 3901 busy wait in do_idle( 3864 busy wait in do_idle() and not use the arch_cpu_idle() 3902 implementation; requi 3865 implementation; requires CONFIG_GENERIC_IDLE_POLL_SETUP 3903 to be effective. This 3866 to be effective. This is useful on platforms where the 3904 sleep(SH) or wfi(ARM, 3867 sleep(SH) or wfi(ARM,ARM64) instructions do not work 3905 correctly or when doi 3868 correctly or when doing power measurements to evaluate 3906 the impact of the sle 3869 the impact of the sleep instructions. This is also 3907 useful when using JTA 3870 useful when using JTAG debugger. 3908 3871 3909 nohugeiomap [KNL,X86,PPC,ARM64,EA !! 3872 nohugeiomap [KNL,X86,PPC,ARM64] Disable kernel huge I/O mappings. 3910 3873 3911 nohugevmalloc [KNL,X86,PPC,ARM64,EA !! 3874 nohugevmalloc [KNL,X86,PPC,ARM64] Disable kernel huge vmalloc mappings. 3912 3875 3913 nohz= [KNL] Boottime enable 3876 nohz= [KNL] Boottime enable/disable dynamic ticks 3914 Valid arguments: on, 3877 Valid arguments: on, off 3915 Default: on 3878 Default: on 3916 3879 3917 nohz_full= [KNL,BOOT,SMP,ISOL] 3880 nohz_full= [KNL,BOOT,SMP,ISOL] 3918 The argument is a cpu 3881 The argument is a cpu list, as described above. 3919 In kernels built with 3882 In kernels built with CONFIG_NO_HZ_FULL=y, set 3920 the specified list of 3883 the specified list of CPUs whose tick will be stopped 3921 whenever possible. Th 3884 whenever possible. The boot CPU will be forced outside 3922 the range to maintain 3885 the range to maintain the timekeeping. Any CPUs 3923 in this list will hav 3886 in this list will have their RCU callbacks offloaded, 3924 just as if they had a 3887 just as if they had also been called out in the 3925 rcu_nocbs= boot param 3888 rcu_nocbs= boot parameter. 3926 3889 3927 Note that this argume 3890 Note that this argument takes precedence over 3928 the CONFIG_RCU_NOCB_C 3891 the CONFIG_RCU_NOCB_CPU_DEFAULT_ALL option. 3929 3892 3930 noinitrd [RAM] Tells the kerne 3893 noinitrd [RAM] Tells the kernel not to load any configured 3931 initial RAM disk. 3894 initial RAM disk. 3932 3895 3933 nointremap [X86-64,Intel-IOMMU,E !! 3896 nointremap [X86-64, Intel-IOMMU] Do not enable interrupt 3934 remapping. 3897 remapping. 3935 [Deprecated - use int 3898 [Deprecated - use intremap=off] 3936 3899 3937 noinvpcid [X86,EARLY] Disable t !! 3900 nointroute [IA-64] >> 3901 >> 3902 noinvpcid [X86] Disable the INVPCID cpu feature. 3938 3903 3939 noiotrap [SH] Disables trapped 3904 noiotrap [SH] Disables trapped I/O port accesses. 3940 3905 3941 noirqdebug [X86-32] Disables the 3906 noirqdebug [X86-32] Disables the code which attempts to detect and 3942 disable unhandled int 3907 disable unhandled interrupt sources. 3943 3908 3944 noisapnp [ISAPNP] Disables ISA 3909 noisapnp [ISAPNP] Disables ISA PnP code. 3945 3910 3946 nokaslr [KNL,EARLY] !! 3911 nojitter [IA-64] Disables jitter checking for ITC timers. >> 3912 >> 3913 nokaslr [KNL] 3947 When CONFIG_RANDOMIZE 3914 When CONFIG_RANDOMIZE_BASE is set, this disables 3948 kernel and module bas 3915 kernel and module base offset ASLR (Address Space 3949 Layout Randomization) 3916 Layout Randomization). 3950 3917 3951 no-kvmapf [X86,KVM,EARLY] Disab !! 3918 no-kvmapf [X86,KVM] Disable paravirtualized asynchronous page 3952 fault handling. 3919 fault handling. 3953 3920 3954 no-kvmclock [X86,KVM,EARLY] Disab !! 3921 no-kvmclock [X86,KVM] Disable paravirtualized KVM clock driver >> 3922 >> 3923 nolapic [X86-32,APIC] Do not enable or use the local APIC. 3955 3924 3956 nolapic [X86-32,APIC,EARLY] D !! 3925 nolapic_timer [X86-32,APIC] Do not use the local APIC timer. 3957 3926 3958 nolapic_timer [X86-32,APIC,EARLY] D !! 3927 nomca [IA-64] Disable machine check abort handling 3959 3928 3960 nomce [X86-32] Disable Mach 3929 nomce [X86-32] Disable Machine Check Exception 3961 3930 3962 nomfgpt [X86-32] Disable Mult 3931 nomfgpt [X86-32] Disable Multi-Function General Purpose 3963 Timer usage (for AMD 3932 Timer usage (for AMD Geode machines). 3964 3933 3965 nomodeset Disable kernel modese 3934 nomodeset Disable kernel modesetting. Most systems' firmware 3966 sets up a display mod 3935 sets up a display mode and provides framebuffer memory 3967 for output. With nomo 3936 for output. With nomodeset, DRM and fbdev drivers will 3968 not load if they coul 3937 not load if they could possibly displace the pre- 3969 initialized output. O 3938 initialized output. Only the system framebuffer will 3970 be available for use. 3939 be available for use. The respective drivers will not 3971 perform display-mode 3940 perform display-mode changes or accelerated rendering. 3972 3941 3973 Useful as error fallb 3942 Useful as error fallback, or for testing and debugging. 3974 3943 3975 nomodule Disable module load 3944 nomodule Disable module load 3976 3945 3977 nonmi_ipi [X86] Disable using N 3946 nonmi_ipi [X86] Disable using NMI IPIs during panic/reboot to 3978 shutdown the other cp 3947 shutdown the other cpus. Instead use the REBOOT_VECTOR 3979 irq. 3948 irq. 3980 3949 3981 nopat [X86,EARLY] Disable P !! 3950 nopat [X86] Disable PAT (page attribute table extension of 3982 pagetables) support. 3951 pagetables) support. 3983 3952 3984 nopcid [X86-64,EARLY] Disabl !! 3953 nopcid [X86-64] Disable the PCID cpu feature. 3985 3954 3986 nopku [X86] Disable Memory 3955 nopku [X86] Disable Memory Protection Keys CPU feature found 3987 in some Intel CPUs. 3956 in some Intel CPUs. 3988 3957 3989 nopti [X86-64,EARLY] !! 3958 nopti [X86-64] 3990 Equivalent to pti=off 3959 Equivalent to pti=off 3991 3960 3992 nopv= [X86,XEN,KVM,HYPER_V, !! 3961 nopv= [X86,XEN,KVM,HYPER_V,VMWARE] 3993 Disables the PV optim 3962 Disables the PV optimizations forcing the guest to run 3994 as generic guest with 3963 as generic guest with no PV drivers. Currently support 3995 XEN HVM, KVM, HYPER_V 3964 XEN HVM, KVM, HYPER_V and VMWARE guest. 3996 3965 3997 nopvspin [X86,XEN,KVM,EARLY] !! 3966 nopvspin [X86,XEN,KVM] 3998 Disables the qspinloc 3967 Disables the qspinlock slow path using PV optimizations 3999 which allow the hyper 3968 which allow the hypervisor to 'idle' the guest on lock 4000 contention. 3969 contention. 4001 3970 4002 norandmaps Don't use address spa 3971 norandmaps Don't use address space randomization. Equivalent to 4003 echo 0 > /proc/sys/ke 3972 echo 0 > /proc/sys/kernel/randomize_va_space 4004 3973 4005 noreplace-smp [X86-32,SMP] Don't re 3974 noreplace-smp [X86-32,SMP] Don't replace SMP instructions 4006 with UP alternatives 3975 with UP alternatives 4007 3976 4008 noresume [SWSUSP] Disables res 3977 noresume [SWSUSP] Disables resume and restores original swap 4009 space. 3978 space. 4010 3979 >> 3980 nosbagart [IA-64] >> 3981 4011 no-scroll [VGA] Disables scroll 3982 no-scroll [VGA] Disables scrollback. 4012 This is required for 3983 This is required for the Braillex ib80-piezo Braille 4013 reader made by F.H. P 3984 reader made by F.H. Papenmeier (Germany). 4014 3985 4015 nosgx [X86-64,SGX,EARLY] Di !! 3986 nosgx [X86-64,SGX] Disables Intel SGX kernel support. 4016 3987 4017 nosmap [PPC,EARLY] !! 3988 nosmap [PPC] 4018 Disable SMAP (Supervi 3989 Disable SMAP (Supervisor Mode Access Prevention) 4019 even if it is support 3990 even if it is supported by processor. 4020 3991 4021 nosmep [PPC64s,EARLY] !! 3992 nosmep [PPC64s] 4022 Disable SMEP (Supervi 3993 Disable SMEP (Supervisor Mode Execution Prevention) 4023 even if it is support 3994 even if it is supported by processor. 4024 3995 4025 nosmp [SMP,EARLY] Tells an !! 3996 nosmp [SMP] Tells an SMP kernel to act as a UP kernel, 4026 and disable the IO AP 3997 and disable the IO APIC. legacy for "maxcpus=0". 4027 3998 4028 nosmt [KNL,MIPS,PPC,S390,EA !! 3999 nosmt [KNL,MIPS,PPC,S390] Disable symmetric multithreading (SMT). 4029 Equivalent to smt=1. 4000 Equivalent to smt=1. 4030 4001 4031 [KNL,X86,PPC] Disable 4002 [KNL,X86,PPC] Disable symmetric multithreading (SMT). 4032 nosmt=force: Force di 4003 nosmt=force: Force disable SMT, cannot be undone 4033 via the 4004 via the sysfs control file. 4034 4005 4035 nosoftlockup [KNL] Disable the sof 4006 nosoftlockup [KNL] Disable the soft-lockup detector. 4036 4007 4037 nospec_store_bypass_disable 4008 nospec_store_bypass_disable 4038 [HW,EARLY] Disable al !! 4009 [HW] Disable all mitigations for the Speculative Store Bypass vulnerability 4039 Store Bypass vulnerab << 4040 4010 4041 nospectre_bhb [ARM64,EARLY] Disable !! 4011 nospectre_bhb [ARM64] Disable all mitigations for Spectre-BHB (branch 4042 history injection) vu 4012 history injection) vulnerability. System may allow data leaks 4043 with this option. 4013 with this option. 4044 4014 4045 nospectre_v1 [X86,PPC,EARLY] Disab !! 4015 nospectre_v1 [X86,PPC] Disable mitigations for Spectre Variant 1 4046 (bounds check bypass) 4016 (bounds check bypass). With this option data leaks are 4047 possible in the syste 4017 possible in the system. 4048 4018 4049 nospectre_v2 [X86,PPC_E500,ARM64,E !! 4019 nospectre_v2 [X86,PPC_E500,ARM64] Disable all mitigations for 4050 for the Spectre varia !! 4020 the Spectre variant 2 (indirect branch prediction) 4051 prediction) vulnerabi !! 4021 vulnerability. System may allow data leaks with this 4052 leaks with this optio !! 4022 option. 4053 !! 4023 4054 no-steal-acc [X86,PV_OPS,ARM64,PPC !! 4024 no-steal-acc [X86,PV_OPS,ARM64,PPC/PSERIES,RISCV] Disable 4055 Disable paravirtualiz !! 4025 paravirtualized steal time accounting. steal time is 4056 is computed, but won' !! 4026 computed, but won't influence scheduler behaviour 4057 4027 4058 nosync [HW,M68K] Disables sy 4028 nosync [HW,M68K] Disables sync negotiation for all devices. 4059 4029 4060 no_timer_check [X86,APIC] Disables t 4030 no_timer_check [X86,APIC] Disables the code which tests for 4061 broken timer IRQ sour 4031 broken timer IRQ sources. 4062 4032 4063 no_uaccess_flush 4033 no_uaccess_flush 4064 [PPC,EARLY] Don't flu !! 4034 [PPC] Don't flush the L1-D cache after accessing user data. 4065 4035 4066 novmcoredd [KNL,KDUMP] 4036 novmcoredd [KNL,KDUMP] 4067 Disable device dump. 4037 Disable device dump. Device dump allows drivers to 4068 append dump data to v 4038 append dump data to vmcore so you can collect driver 4069 specified debug info. 4039 specified debug info. Drivers can append the data 4070 without any limit and 4040 without any limit and this data is stored in memory, 4071 so this may cause sig 4041 so this may cause significant memory stress. Disabling 4072 device dump can help 4042 device dump can help save memory but the driver debug 4073 data will be no longe 4043 data will be no longer available. This parameter 4074 is only available whe 4044 is only available when CONFIG_PROC_VMCORE_DEVICE_DUMP 4075 is set. 4045 is set. 4076 4046 4077 no-vmw-sched-clock 4047 no-vmw-sched-clock 4078 [X86,PV_OPS,EARLY] Di !! 4048 [X86,PV_OPS] Disable paravirtualized VMware scheduler 4079 scheduler clock and u !! 4049 clock and use the default one. 4080 4050 4081 nowatchdog [KNL] Disable both lo 4051 nowatchdog [KNL] Disable both lockup detectors, i.e. 4082 soft-lockup and NMI w 4052 soft-lockup and NMI watchdog (hard-lockup). 4083 4053 4084 nowb [ARM,EARLY] !! 4054 nowb [ARM] 4085 4055 4086 nox2apic [X86-64,APIC,EARLY] D !! 4056 nox2apic [X86-64,APIC] Do not enable x2APIC mode. 4087 4057 4088 NOTE: this parameter 4058 NOTE: this parameter will be ignored on systems with the 4089 LEGACY_XAPIC_DISABLED 4059 LEGACY_XAPIC_DISABLED bit set in the 4090 IA32_XAPIC_DISABLE_ST 4060 IA32_XAPIC_DISABLE_STATUS MSR. 4091 4061 4092 noxsave [BUGS=X86] Disables x 4062 noxsave [BUGS=X86] Disables x86 extended register state save 4093 and restore using xsa 4063 and restore using xsave. The kernel will fallback to 4094 enabling legacy float 4064 enabling legacy floating-point and sse state. 4095 4065 4096 noxsaveopt [X86] Disables xsaveo 4066 noxsaveopt [X86] Disables xsaveopt used in saving x86 extended 4097 register states. The 4067 register states. The kernel will fall back to use 4098 xsave to save the sta 4068 xsave to save the states. By using this parameter, 4099 performance of saving 4069 performance of saving the states is degraded because 4100 xsave doesn't support 4070 xsave doesn't support modified optimization while 4101 xsaveopt supports it 4071 xsaveopt supports it on xsaveopt enabled systems. 4102 4072 4103 noxsaves [X86] Disables xsaves 4073 noxsaves [X86] Disables xsaves and xrstors used in saving and 4104 restoring x86 extende 4074 restoring x86 extended register state in compacted 4105 form of xsave area. T 4075 form of xsave area. The kernel will fall back to use 4106 xsaveopt and xrstor t 4076 xsaveopt and xrstor to save and restore the states 4107 in standard form of x 4077 in standard form of xsave area. By using this 4108 parameter, xsave area 4078 parameter, xsave area per process might occupy more 4109 memory on xsaves enab 4079 memory on xsaves enabled systems. 4110 4080 4111 nr_cpus= [SMP,EARLY] Maximum n !! 4081 nps_mtm_hs_ctr= [KNL,ARC] >> 4082 This parameter sets the maximum duration, in >> 4083 cycles, each HW thread of the CTOP can run >> 4084 without interruptions, before HW switches it. >> 4085 The actual maximum duration is 16 times this >> 4086 parameter's value. >> 4087 Format: integer between 1 and 255 >> 4088 Default: 255 >> 4089 >> 4090 nptcg= [IA-64] Override max number of concurrent global TLB >> 4091 purges which is reported from either PAL_VM_SUMMARY or >> 4092 SAL PALO. >> 4093 >> 4094 nr_cpus= [SMP] Maximum number of processors that an SMP kernel 4112 could support. nr_cp 4095 could support. nr_cpus=n : n >= 1 limits the kernel to 4113 support 'n' processor 4096 support 'n' processors. It could be larger than the 4114 number of already plu 4097 number of already plugged CPU during bootup, later in 4115 runtime you can physi 4098 runtime you can physically add extra cpu until it reaches 4116 n. So during boot up 4099 n. So during boot up some boot time memory for per-cpu 4117 variables need be pre 4100 variables need be pre-allocated for later physical cpu 4118 hot plugging. 4101 hot plugging. 4119 4102 4120 nr_uarts= [SERIAL] maximum numb 4103 nr_uarts= [SERIAL] maximum number of UARTs to be registered. 4121 4104 4122 numa=off [KNL, ARM64, PPC, RIS !! 4105 numa=off [KNL, ARM64, PPC, RISCV, SPARC, X86] Disable NUMA, Only 4123 Disable NUMA, Only se !! 4106 set up a single NUMA node spanning all memory. 4124 spanning all memory. << 4125 4107 4126 numa_balancing= [KNL,ARM64,PPC,RISCV, 4108 numa_balancing= [KNL,ARM64,PPC,RISCV,S390,X86] Enable or disable automatic 4127 NUMA balancing. 4109 NUMA balancing. 4128 Allowed values are en 4110 Allowed values are enable and disable 4129 4111 4130 numa_zonelist_order= [KNL, BOOT] Sele 4112 numa_zonelist_order= [KNL, BOOT] Select zonelist order for NUMA. 4131 'node', 'default' can 4113 'node', 'default' can be specified 4132 This can be set from 4114 This can be set from sysctl after boot. 4133 See Documentation/adm 4115 See Documentation/admin-guide/sysctl/vm.rst for details. 4134 4116 4135 ohci1394_dma=early [HW,EARLY] en !! 4117 ohci1394_dma=early [HW] enable debugging via the ohci1394 driver. 4136 See Documentation/cor 4118 See Documentation/core-api/debugging-via-ohci1394.rst for more 4137 info. 4119 info. 4138 4120 4139 olpc_ec_timeout= [OLPC] ms delay when 4121 olpc_ec_timeout= [OLPC] ms delay when issuing EC commands 4140 Rather than timing ou 4122 Rather than timing out after 20 ms if an EC 4141 command is not proper 4123 command is not properly ACKed, override the length 4142 of the timeout. We h 4124 of the timeout. We have interrupts disabled while 4143 waiting for the ACK, 4125 waiting for the ACK, so if this is set too high 4144 interrupts *may* be l 4126 interrupts *may* be lost! 4145 4127 4146 omap_mux= [OMAP] Override bootl 4128 omap_mux= [OMAP] Override bootloader pin multiplexing. 4147 Format: <mux_mode0.mo 4129 Format: <mux_mode0.mode_name=value>... 4148 For example, to overr 4130 For example, to override I2C bus2: 4149 omap_mux=i2c2_scl.i2c 4131 omap_mux=i2c2_scl.i2c2_scl=0x100,i2c2_sda.i2c2_sda=0x100 4150 4132 4151 onenand.bdry= [HW,MTD] Flex-OneNAND 4133 onenand.bdry= [HW,MTD] Flex-OneNAND Boundary Configuration 4152 4134 4153 Format: [die0_boundar 4135 Format: [die0_boundary][,die0_lock][,die1_boundary][,die1_lock] 4154 4136 4155 boundary - index of l 4137 boundary - index of last SLC block on Flex-OneNAND. 4156 The remain 4138 The remaining blocks are configured as MLC blocks. 4157 lock - Configure 4139 lock - Configure if Flex-OneNAND boundary should be locked. 4158 Once locke 4140 Once locked, the boundary cannot be changed. 4159 1 indicate 4141 1 indicates lock status, 0 indicates unlock status. 4160 4142 4161 oops=panic [KNL,EARLY] !! 4143 oops=panic Always panic on oopses. Default is to just kill the 4162 Always panic on oopse << 4163 process, but there is 4144 process, but there is a small probability of 4164 deadlocking the machi 4145 deadlocking the machine. 4165 This will also cause 4146 This will also cause panics on machine check exceptions. 4166 Useful together with 4147 Useful together with panic=30 to trigger a reboot. 4167 4148 4168 page_alloc.shuffle= 4149 page_alloc.shuffle= 4169 [KNL] Boolean flag to 4150 [KNL] Boolean flag to control whether the page allocator 4170 should randomize its !! 4151 should randomize its free lists. The randomization may 4171 used to enable/disabl !! 4152 be automatically enabled if the kernel detects it is 4172 the flag can be read !! 4153 running on a platform with a direct-mapped memory-side >> 4154 cache, and this parameter can be used to >> 4155 override/disable that behavior. The state of the flag >> 4156 can be read from sysfs at: 4173 /sys/module/page_allo 4157 /sys/module/page_alloc/parameters/shuffle. 4174 This parameter is onl << 4175 4158 4176 page_owner= [KNL,EARLY] Boot-time !! 4159 page_owner= [KNL] Boot-time page_owner enabling option. 4177 Storage of the inform 4160 Storage of the information about who allocated 4178 each page is disabled 4161 each page is disabled in default. With this switch, 4179 we can turn it on. 4162 we can turn it on. 4180 on: enable the featur 4163 on: enable the feature 4181 4164 4182 page_poison= [KNL,EARLY] Boot-time !! 4165 page_poison= [KNL] Boot-time parameter changing the state of 4183 poisoning on the budd 4166 poisoning on the buddy allocator, available with 4184 CONFIG_PAGE_POISONING 4167 CONFIG_PAGE_POISONING=y. 4185 off: turn off poisoni 4168 off: turn off poisoning (default) 4186 on: turn on poisoning 4169 on: turn on poisoning 4187 4170 4188 page_reporting.page_reporting_order= 4171 page_reporting.page_reporting_order= 4189 [KNL] Minimal page re 4172 [KNL] Minimal page reporting order 4190 Format: <integer> 4173 Format: <integer> 4191 Adjust the minimal pa 4174 Adjust the minimal page reporting order. The page 4192 reporting is disabled 4175 reporting is disabled when it exceeds MAX_PAGE_ORDER. 4193 4176 4194 panic= [KNL] Kernel behaviou 4177 panic= [KNL] Kernel behaviour on panic: delay <timeout> 4195 timeout > 0: seconds 4178 timeout > 0: seconds before rebooting 4196 timeout = 0: wait for 4179 timeout = 0: wait forever 4197 timeout < 0: reboot i 4180 timeout < 0: reboot immediately 4198 Format: <timeout> 4181 Format: <timeout> 4199 4182 4200 panic_on_taint= [KNL,EARLY] !! 4183 panic_on_taint= Bitmask for conditionally calling panic() in add_taint() 4201 Bitmask for condition << 4202 Format: <hex>[,nouser 4184 Format: <hex>[,nousertaint] 4203 Hexadecimal bitmask r 4185 Hexadecimal bitmask representing the set of TAINT flags 4204 that will cause the k 4186 that will cause the kernel to panic when add_taint() is 4205 called with any of th 4187 called with any of the flags in this set. 4206 The optional switch " 4188 The optional switch "nousertaint" can be utilized to 4207 prevent userspace for 4189 prevent userspace forced crashes by writing to sysctl 4208 /proc/sys/kernel/tain 4190 /proc/sys/kernel/tainted any flagset matching with the 4209 bitmask set on panic_ 4191 bitmask set on panic_on_taint. 4210 See Documentation/adm 4192 See Documentation/admin-guide/tainted-kernels.rst for 4211 extra details on the 4193 extra details on the taint flags that users can pick 4212 to compose the bitmas 4194 to compose the bitmask to assign to panic_on_taint. 4213 4195 4214 panic_on_warn=1 panic() instead of WA 4196 panic_on_warn=1 panic() instead of WARN(). Useful to cause kdump 4215 on a WARN(). 4197 on a WARN(). 4216 4198 4217 panic_print= Bitmask for printing 4199 panic_print= Bitmask for printing system info when panic happens. 4218 User can chose combin 4200 User can chose combination of the following bits: 4219 bit 0: print all task 4201 bit 0: print all tasks info 4220 bit 1: print system m 4202 bit 1: print system memory info 4221 bit 2: print timer in 4203 bit 2: print timer info 4222 bit 3: print locks in 4204 bit 3: print locks info if CONFIG_LOCKDEP is on 4223 bit 4: print ftrace b 4205 bit 4: print ftrace buffer 4224 bit 5: print all prin 4206 bit 5: print all printk messages in buffer 4225 bit 6: print all CPUs 4207 bit 6: print all CPUs backtrace (if available in the arch) 4226 bit 7: print only tas << 4227 *Be aware* that this 4208 *Be aware* that this option may print a _lot_ of lines, 4228 so there are risks of 4209 so there are risks of losing older messages in the log. 4229 Use this option caref 4210 Use this option carefully, maybe worth to setup a 4230 bigger log buffer wit 4211 bigger log buffer with "log_buf_len" along with this. 4231 4212 4232 parkbd.port= [HW] Parallel port nu 4213 parkbd.port= [HW] Parallel port number the keyboard adapter is 4233 connected to, default 4214 connected to, default is 0. 4234 Format: <parport#> 4215 Format: <parport#> 4235 parkbd.mode= [HW] Parallel port ke 4216 parkbd.mode= [HW] Parallel port keyboard adapter mode of operation, 4236 0 for XT, 1 for AT (d 4217 0 for XT, 1 for AT (default is AT). 4237 Format: <mode> 4218 Format: <mode> 4238 4219 4239 parport= [HW,PPT] Specify para 4220 parport= [HW,PPT] Specify parallel ports. 0 disables. 4240 Format: { 0 | auto | 4221 Format: { 0 | auto | 0xBBB[,IRQ[,DMA]] } 4241 Use 'auto' to force t 4222 Use 'auto' to force the driver to use any 4242 IRQ/DMA settings dete 4223 IRQ/DMA settings detected (the default is to 4243 ignore detected IRQ/D 4224 ignore detected IRQ/DMA settings because of 4244 possible conflicts). 4225 possible conflicts). You can specify the base 4245 address, IRQ, and DMA 4226 address, IRQ, and DMA settings; IRQ and DMA 4246 should be numbers, or 4227 should be numbers, or 'auto' (for using detected 4247 settings on that part 4228 settings on that particular port), or 'nofifo' 4248 (to avoid using a FIF 4229 (to avoid using a FIFO even if it is detected). 4249 Parallel ports are as 4230 Parallel ports are assigned in the order they 4250 are specified on the 4231 are specified on the command line, starting 4251 with parport0. 4232 with parport0. 4252 4233 4253 parport_init_mode= [HW,PPT] 4234 parport_init_mode= [HW,PPT] 4254 Configure VIA paralle 4235 Configure VIA parallel port to operate in 4255 a specific mode. This 4236 a specific mode. This is necessary on Pegasos 4256 computer where firmwa 4237 computer where firmware has no options for setting 4257 up parallel port mode 4238 up parallel port mode and sets it to spp. 4258 Currently this functi 4239 Currently this function knows 686a and 8231 chips. 4259 Format: [spp|ps2|epp| 4240 Format: [spp|ps2|epp|ecp|ecpepp] 4260 4241 4261 pata_legacy.all= [HW,LIBATA] 4242 pata_legacy.all= [HW,LIBATA] 4262 Format: <int> 4243 Format: <int> 4263 Set to non-zero to pr 4244 Set to non-zero to probe primary and secondary ISA 4264 port ranges on PCI sy 4245 port ranges on PCI systems where no PCI PATA device 4265 has been found at eit 4246 has been found at either range. Disabled by default. 4266 4247 4267 pata_legacy.autospeed= [HW,LIBATA] 4248 pata_legacy.autospeed= [HW,LIBATA] 4268 Format: <int> 4249 Format: <int> 4269 Set to non-zero if a 4250 Set to non-zero if a chip is present that snoops speed 4270 changes. Disabled by 4251 changes. Disabled by default. 4271 4252 4272 pata_legacy.ht6560a= [HW,LIBATA] 4253 pata_legacy.ht6560a= [HW,LIBATA] 4273 Format: <int> 4254 Format: <int> 4274 Set to 1, 2, or 3 for 4255 Set to 1, 2, or 3 for HT 6560A on the primary channel, 4275 the secondary channel 4256 the secondary channel, or both channels respectively. 4276 Disabled by default. 4257 Disabled by default. 4277 4258 4278 pata_legacy.ht6560b= [HW,LIBATA] 4259 pata_legacy.ht6560b= [HW,LIBATA] 4279 Format: <int> 4260 Format: <int> 4280 Set to 1, 2, or 3 for 4261 Set to 1, 2, or 3 for HT 6560B on the primary channel, 4281 the secondary channel 4262 the secondary channel, or both channels respectively. 4282 Disabled by default. 4263 Disabled by default. 4283 4264 4284 pata_legacy.iordy_mask= [HW,LIBATA] 4265 pata_legacy.iordy_mask= [HW,LIBATA] 4285 Format: <int> 4266 Format: <int> 4286 IORDY enable mask. S 4267 IORDY enable mask. Set individual bits to allow IORDY 4287 for the respective ch 4268 for the respective channel. Bit 0 is for the first 4288 legacy channel handle 4269 legacy channel handled by this driver, bit 1 is for 4289 the second channel, a 4270 the second channel, and so on. The sequence will often 4290 correspond to the pri 4271 correspond to the primary legacy channel, the secondary 4291 legacy channel, and s 4272 legacy channel, and so on, but the handling of a PCI 4292 bus and the use of ot 4273 bus and the use of other driver options may interfere 4293 with the sequence. B 4274 with the sequence. By default IORDY is allowed across 4294 all channels. 4275 all channels. 4295 4276 4296 pata_legacy.opti82c46x= [HW,LIBATA] 4277 pata_legacy.opti82c46x= [HW,LIBATA] 4297 Format: <int> 4278 Format: <int> 4298 Set to 1, 2, or 3 for 4279 Set to 1, 2, or 3 for Opti 82c611A on the primary 4299 channel, the secondar 4280 channel, the secondary channel, or both channels 4300 respectively. Disabl 4281 respectively. Disabled by default. 4301 4282 4302 pata_legacy.opti82c611a= [HW,L 4283 pata_legacy.opti82c611a= [HW,LIBATA] 4303 Format: <int> 4284 Format: <int> 4304 Set to 1, 2, or 3 for 4285 Set to 1, 2, or 3 for Opti 82c465MV on the primary 4305 channel, the secondar 4286 channel, the secondary channel, or both channels 4306 respectively. Disabl 4287 respectively. Disabled by default. 4307 4288 4308 pata_legacy.pio_mask= [HW,LIBATA] 4289 pata_legacy.pio_mask= [HW,LIBATA] 4309 Format: <int> 4290 Format: <int> 4310 PIO mode mask for aut 4291 PIO mode mask for autospeed devices. Set individual 4311 bits to allow the use 4292 bits to allow the use of the respective PIO modes. 4312 Bit 0 is for mode 0, 4293 Bit 0 is for mode 0, bit 1 is for mode 1, and so on. 4313 All modes allowed by 4294 All modes allowed by default. 4314 4295 4315 pata_legacy.probe_all= [HW,LIBATA] 4296 pata_legacy.probe_all= [HW,LIBATA] 4316 Format: <int> 4297 Format: <int> 4317 Set to non-zero to pr 4298 Set to non-zero to probe tertiary and further ISA 4318 port ranges on PCI sy 4299 port ranges on PCI systems. Disabled by default. 4319 4300 4320 pata_legacy.probe_mask= [HW,LIBATA] 4301 pata_legacy.probe_mask= [HW,LIBATA] 4321 Format: <int> 4302 Format: <int> 4322 Probe mask for legacy 4303 Probe mask for legacy ISA PATA ports. Depending on 4323 platform configuratio 4304 platform configuration and the use of other driver 4324 options up to 6 legac 4305 options up to 6 legacy ports are supported: 0x1f0, 4325 0x170, 0x1e8, 0x168, 4306 0x170, 0x1e8, 0x168, 0x1e0, 0x160, however probing 4326 of individual ports c 4307 of individual ports can be disabled by setting the 4327 corresponding bits in 4308 corresponding bits in the mask to 1. Bit 0 is for 4328 the first port in the 4309 the first port in the list above (0x1f0), and so on. 4329 By default all suppor 4310 By default all supported ports are probed. 4330 4311 4331 pata_legacy.qdi= [HW,LIBATA] 4312 pata_legacy.qdi= [HW,LIBATA] 4332 Format: <int> 4313 Format: <int> 4333 Set to non-zero to pr 4314 Set to non-zero to probe QDI controllers. By default 4334 set to 1 if CONFIG_PA 4315 set to 1 if CONFIG_PATA_QDI_MODULE, 0 otherwise. 4335 4316 4336 pata_legacy.winbond= [HW,LIBATA] 4317 pata_legacy.winbond= [HW,LIBATA] 4337 Format: <int> 4318 Format: <int> 4338 Set to non-zero to pr 4319 Set to non-zero to probe Winbond controllers. Use 4339 the standard I/O port 4320 the standard I/O port (0x130) if 1, otherwise the 4340 value given is the I/ 4321 value given is the I/O port to use (typically 0x1b0). 4341 By default set to 1 i 4322 By default set to 1 if CONFIG_PATA_WINBOND_VLB_MODULE, 4342 0 otherwise. 4323 0 otherwise. 4343 4324 4344 pata_platform.pio_mask= [HW,LIBATA] 4325 pata_platform.pio_mask= [HW,LIBATA] 4345 Format: <int> 4326 Format: <int> 4346 Supported PIO mode ma 4327 Supported PIO mode mask. Set individual bits to allow 4347 the use of the respec 4328 the use of the respective PIO modes. Bit 0 is for 4348 mode 0, bit 1 is for 4329 mode 0, bit 1 is for mode 1, and so on. Mode 0 only 4349 allowed by default. 4330 allowed by default. 4350 4331 4351 pause_on_oops=<int> 4332 pause_on_oops=<int> 4352 Halt all CPUs after t 4333 Halt all CPUs after the first oops has been printed for 4353 the specified number 4334 the specified number of seconds. This is to be used if 4354 your oopses keep scro 4335 your oopses keep scrolling off the screen. 4355 4336 4356 pcbit= [HW,ISDN] 4337 pcbit= [HW,ISDN] 4357 4338 4358 pci=option[,option...] [PCI,EARLY] v !! 4339 pci=option[,option...] [PCI] various PCI subsystem options. 4359 4340 4360 Some options 4341 Some options herein operate on a specific device 4361 or a set of d 4342 or a set of devices (<pci_dev>). These are 4362 specified in 4343 specified in one of the following formats: 4363 4344 4364 [<domain>:]<b 4345 [<domain>:]<bus>:<dev>.<func>[/<dev>.<func>]* 4365 pci:<vendor>: 4346 pci:<vendor>:<device>[:<subvendor>:<subdevice>] 4366 4347 4367 Note: the fir 4348 Note: the first format specifies a PCI 4368 bus/device/fu 4349 bus/device/function address which may change 4369 if new hardwa 4350 if new hardware is inserted, if motherboard 4370 firmware chan 4351 firmware changes, or due to changes caused 4371 by other kern 4352 by other kernel parameters. If the 4372 domain is lef 4353 domain is left unspecified, it is 4373 taken to be z 4354 taken to be zero. Optionally, a path 4374 to a device t 4355 to a device through multiple device/function 4375 addresses can 4356 addresses can be specified after the base 4376 address (this 4357 address (this is more robust against 4377 renumbering i 4358 renumbering issues). The second format 4378 selects devic 4359 selects devices using IDs from the 4379 configuration 4360 configuration space which may match multiple 4380 devices in th 4361 devices in the system. 4381 4362 4382 earlydump dump PCI conf 4363 earlydump dump PCI config space before the kernel 4383 changes anyth 4364 changes anything 4384 off [X86] don't p 4365 off [X86] don't probe for the PCI bus 4385 bios [X86-32] forc 4366 bios [X86-32] force use of PCI BIOS, don't access 4386 the hardware 4367 the hardware directly. Use this if your machine 4387 has a non-sta 4368 has a non-standard PCI host bridge. 4388 nobios [X86-32] disa 4369 nobios [X86-32] disallow use of PCI BIOS, only direct 4389 hardware acce 4370 hardware access methods are allowed. Use this 4390 if you experi 4371 if you experience crashes upon bootup and you 4391 suspect they 4372 suspect they are caused by the BIOS. 4392 conf1 [X86] Force u 4373 conf1 [X86] Force use of PCI Configuration Access 4393 Mechanism 1 ( 4374 Mechanism 1 (config address in IO port 0xCF8, 4394 data in IO po 4375 data in IO port 0xCFC, both 32-bit). 4395 conf2 [X86] Force u 4376 conf2 [X86] Force use of PCI Configuration Access 4396 Mechanism 2 ( 4377 Mechanism 2 (IO port 0xCF8 is an 8-bit port for 4397 the function, 4378 the function, IO port 0xCFA, also 8-bit, sets 4398 bus number. T 4379 bus number. The config space is then accessed 4399 through ports 4380 through ports 0xC000-0xCFFF). 4400 See http://wi 4381 See http://wiki.osdev.org/PCI for more info 4401 on the config 4382 on the configuration access mechanisms. 4402 noaer [PCIE] If the 4383 noaer [PCIE] If the PCIEAER kernel config parameter is 4403 enabled, this 4384 enabled, this kernel boot option can be used to 4404 disable the u 4385 disable the use of PCIE advanced error reporting. 4405 nodomains [PCI] Disable 4386 nodomains [PCI] Disable support for multiple PCI 4406 root domains 4387 root domains (aka PCI segments, in ACPI-speak). 4407 nommconf [X86] Disable 4388 nommconf [X86] Disable use of MMCONFIG for PCI 4408 Configuration 4389 Configuration 4409 check_enable_amd_mmconf [X86] 4390 check_enable_amd_mmconf [X86] check for and enable 4410 properly conf 4391 properly configured MMIO access to PCI 4411 config space 4392 config space on AMD family 10h CPU 4412 nomsi [MSI] If the 4393 nomsi [MSI] If the PCI_MSI kernel config parameter is 4413 enabled, this 4394 enabled, this kernel boot option can be used to 4414 disable the u 4395 disable the use of MSI interrupts system-wide. 4415 noioapicquirk [APIC] Disabl 4396 noioapicquirk [APIC] Disable all boot interrupt quirks. 4416 Safety option 4397 Safety option to keep boot IRQs enabled. This 4417 should never 4398 should never be necessary. 4418 ioapicreroute [APIC] Enable 4399 ioapicreroute [APIC] Enable rerouting of boot IRQs to the 4419 primary IO-AP 4400 primary IO-APIC for bridges that cannot disable 4420 boot IRQs. Th 4401 boot IRQs. This fixes a source of spurious IRQs 4421 when the syst 4402 when the system masks IRQs. 4422 noioapicreroute [APIC] Disabl 4403 noioapicreroute [APIC] Disable workaround that uses the 4423 boot IRQ equi 4404 boot IRQ equivalent of an IRQ that connects to 4424 a chipset whe 4405 a chipset where boot IRQs cannot be disabled. 4425 The opposite 4406 The opposite of ioapicreroute. 4426 biosirq [X86-32] Use 4407 biosirq [X86-32] Use PCI BIOS calls to get the interrupt 4427 routing table 4408 routing table. These calls are known to be buggy 4428 on several ma 4409 on several machines and they hang the machine 4429 when used, bu 4410 when used, but on other computers it's the only 4430 way to get th 4411 way to get the interrupt routing table. Try 4431 this option i 4412 this option if the kernel is unable to allocate 4432 IRQs or disco 4413 IRQs or discover secondary PCI buses on your 4433 motherboard. 4414 motherboard. 4434 rom [X86] Assign 4415 rom [X86] Assign address space to expansion ROMs. 4435 Use with caut 4416 Use with caution as certain devices share 4436 address decod 4417 address decoders between ROMs and other 4437 resources. 4418 resources. 4438 norom [X86] Do not 4419 norom [X86] Do not assign address space to 4439 expansion ROM 4420 expansion ROMs that do not already have 4440 BIOS assigned 4421 BIOS assigned address ranges. 4441 nobar [X86] Do not 4422 nobar [X86] Do not assign address space to the 4442 BARs that wer 4423 BARs that weren't assigned by the BIOS. 4443 irqmask=0xMMMM [X86] Set a b 4424 irqmask=0xMMMM [X86] Set a bit mask of IRQs allowed to be 4444 assigned auto 4425 assigned automatically to PCI devices. You can 4445 make the kern 4426 make the kernel exclude IRQs of your ISA cards 4446 this way. 4427 this way. 4447 pirqaddr=0xAAAAA [X86] 4428 pirqaddr=0xAAAAA [X86] Specify the physical address 4448 of the PIRQ t 4429 of the PIRQ table (normally generated 4449 by the BIOS) 4430 by the BIOS) if it is outside the 4450 F0000h-100000 4431 F0000h-100000h range. 4451 lastbus=N [X86] Scan al 4432 lastbus=N [X86] Scan all buses thru bus #N. Can be 4452 useful if the 4433 useful if the kernel is unable to find your 4453 secondary bus 4434 secondary buses and you want to tell it 4454 explicitly wh 4435 explicitly which ones they are. 4455 assign-busses [X86] Always 4436 assign-busses [X86] Always assign all PCI bus 4456 numbers ourse 4437 numbers ourselves, overriding 4457 whatever the 4438 whatever the firmware may have done. 4458 usepirqmask [X86] Honor t 4439 usepirqmask [X86] Honor the possible IRQ mask stored 4459 in the BIOS $ 4440 in the BIOS $PIR table. This is needed on 4460 some systems 4441 some systems with broken BIOSes, notably 4461 some HP Pavil 4442 some HP Pavilion N5400 and Omnibook XE3 4462 notebooks. Th 4443 notebooks. This will have no effect if ACPI 4463 IRQ routing i 4444 IRQ routing is enabled. 4464 noacpi [X86] Do not 4445 noacpi [X86] Do not use ACPI for IRQ routing 4465 or for PCI sc 4446 or for PCI scanning. 4466 use_crs [X86] Use PCI 4447 use_crs [X86] Use PCI host bridge window information 4467 from ACPI. O 4448 from ACPI. On BIOSes from 2008 or later, this 4468 is enabled by 4449 is enabled by default. If you need to use this, 4469 please report 4450 please report a bug. 4470 nocrs [X86] Ignore 4451 nocrs [X86] Ignore PCI host bridge windows from ACPI. 4471 If you need t 4452 If you need to use this, please report a bug. 4472 use_e820 [X86] Use E82 4453 use_e820 [X86] Use E820 reservations to exclude parts of 4473 PCI host brid 4454 PCI host bridge windows. This is a workaround 4474 for BIOS defe 4455 for BIOS defects in host bridge _CRS methods. 4475 If you need t 4456 If you need to use this, please report a bug to 4476 <linux-pci@vge 4457 <linux-pci@vger.kernel.org>. 4477 no_e820 [X86] Ignore 4458 no_e820 [X86] Ignore E820 reservations for PCI host 4478 bridge window 4459 bridge windows. This is the default on modern 4479 hardware. If 4460 hardware. If you need to use this, please report 4480 a bug to <linu 4461 a bug to <linux-pci@vger.kernel.org>. 4481 routeirq Do IRQ routin 4462 routeirq Do IRQ routing for all PCI devices. 4482 This is norma 4463 This is normally done in pci_enable_device(), 4483 so this optio 4464 so this option is a temporary workaround 4484 for broken dr 4465 for broken drivers that don't call it. 4485 skip_isa_align [X86] do not 4466 skip_isa_align [X86] do not align io start addr, so can 4486 handle more p 4467 handle more pci cards 4487 noearly [X86] Don't d 4468 noearly [X86] Don't do any early type 1 scanning. 4488 This might he 4469 This might help on some broken boards which 4489 machine check 4470 machine check when some devices' config space 4490 is read. But 4471 is read. But various workarounds are disabled 4491 and some IOMM 4472 and some IOMMU drivers will not work. 4492 bfsort Sort PCI devi 4473 bfsort Sort PCI devices into breadth-first order. 4493 This sorting 4474 This sorting is done to get a device 4494 order compati 4475 order compatible with older (<= 2.4) kernels. 4495 nobfsort Don't sort PC 4476 nobfsort Don't sort PCI devices into breadth-first order. 4496 pcie_bus_tune_off Disab 4477 pcie_bus_tune_off Disable PCIe MPS (Max Payload Size) 4497 tuning and us 4478 tuning and use the BIOS-configured MPS defaults. 4498 pcie_bus_safe Set every dev 4479 pcie_bus_safe Set every device's MPS to the largest value 4499 supported by 4480 supported by all devices below the root complex. 4500 pcie_bus_perf Set device MP 4481 pcie_bus_perf Set device MPS to the largest allowable MPS 4501 based on its 4482 based on its parent bus. Also set MRRS (Max 4502 Read Request 4483 Read Request Size) to the largest supported 4503 value (no lar 4484 value (no larger than the MPS that the device 4504 or bus can su 4485 or bus can support) for best performance. 4505 pcie_bus_peer2peer Set e 4486 pcie_bus_peer2peer Set every device's MPS to 128B, which 4506 every device 4487 every device is guaranteed to support. This 4507 configuration 4488 configuration allows peer-to-peer DMA between 4508 any pair of d 4489 any pair of devices, possibly at the cost of 4509 reduced perfo 4490 reduced performance. This also guarantees 4510 that hot-adde 4491 that hot-added devices will work. 4511 cbiosize=nn[KMG] The f 4492 cbiosize=nn[KMG] The fixed amount of bus space which is 4512 reserved for 4493 reserved for the CardBus bridge's IO window. 4513 The default v 4494 The default value is 256 bytes. 4514 cbmemsize=nn[KMG] The f 4495 cbmemsize=nn[KMG] The fixed amount of bus space which is 4515 reserved for 4496 reserved for the CardBus bridge's memory 4516 window. The d 4497 window. The default value is 64 megabytes. 4517 resource_alignment= 4498 resource_alignment= 4518 Format: 4499 Format: 4519 [<order of ali 4500 [<order of align>@]<pci_dev>[; ...] 4520 Specifies ali 4501 Specifies alignment and device to reassign 4521 aligned memor 4502 aligned memory resources. How to 4522 specify the d 4503 specify the device is described above. 4523 If <order of 4504 If <order of align> is not specified, 4524 PAGE_SIZE is 4505 PAGE_SIZE is used as alignment. 4525 A PCI-PCI bri 4506 A PCI-PCI bridge can be specified if resource 4526 windows need 4507 windows need to be expanded. 4527 To specify th 4508 To specify the alignment for several 4528 instances of 4509 instances of a device, the PCI vendor, 4529 device, subve 4510 device, subvendor, and subdevice may be 4530 specified, e. 4511 specified, e.g., 12@pci:8086:9c22:103c:198f 4531 for 4096-byte 4512 for 4096-byte alignment. 4532 ecrc= Enable/disabl 4513 ecrc= Enable/disable PCIe ECRC (transaction layer 4533 end-to-end CR 4514 end-to-end CRC checking). Only effective if 4534 OS has native 4515 OS has native AER control (either granted by 4535 ACPI _OSC or 4516 ACPI _OSC or forced via "pcie_ports=native") 4536 bios: Use BIO 4517 bios: Use BIOS/firmware settings. This is the 4537 the default. 4518 the default. 4538 off: Turn ECR 4519 off: Turn ECRC off 4539 on: Turn ECRC 4520 on: Turn ECRC on. 4540 hpiosize=nn[KMG] The f 4521 hpiosize=nn[KMG] The fixed amount of bus space which is 4541 reserved for 4522 reserved for hotplug bridge's IO window. 4542 Default size 4523 Default size is 256 bytes. 4543 hpmmiosize=nn[KMG] The f 4524 hpmmiosize=nn[KMG] The fixed amount of bus space which is 4544 reserved for 4525 reserved for hotplug bridge's MMIO window. 4545 Default size 4526 Default size is 2 megabytes. 4546 hpmmioprefsize=nn[KMG] The f 4527 hpmmioprefsize=nn[KMG] The fixed amount of bus space which is 4547 reserved for 4528 reserved for hotplug bridge's MMIO_PREF window. 4548 Default size 4529 Default size is 2 megabytes. 4549 hpmemsize=nn[KMG] The f 4530 hpmemsize=nn[KMG] The fixed amount of bus space which is 4550 reserved for 4531 reserved for hotplug bridge's MMIO and 4551 MMIO_PREF win 4532 MMIO_PREF window. 4552 Default size 4533 Default size is 2 megabytes. 4553 hpbussize=nn The minimum a 4534 hpbussize=nn The minimum amount of additional bus numbers 4554 reserved for 4535 reserved for buses below a hotplug bridge. 4555 Default is 1. 4536 Default is 1. 4556 realloc= Enable/disabl 4537 realloc= Enable/disable reallocating PCI bridge resources 4557 if allocation 4538 if allocations done by BIOS are too small to 4558 accommodate r 4539 accommodate resources required by all child 4559 devices. 4540 devices. 4560 off: Turn rea 4541 off: Turn realloc off 4561 on: Turn real 4542 on: Turn realloc on 4562 realloc same as reall 4543 realloc same as realloc=on 4563 noari do not use PC 4544 noari do not use PCIe ARI. 4564 noats [PCIE, Intel- 4545 noats [PCIE, Intel-IOMMU, AMD-IOMMU] 4565 do not use PC 4546 do not use PCIe ATS (and IOMMU device IOTLB). 4566 pcie_scan_all Scan all poss 4547 pcie_scan_all Scan all possible PCIe devices. Otherwise we 4567 only look for 4548 only look for one device below a PCIe downstream 4568 port. 4549 port. 4569 big_root_window Try to add a 4550 big_root_window Try to add a big 64bit memory window to the PCIe 4570 root complex 4551 root complex on AMD CPUs. Some GFX hardware 4571 can resize a 4552 can resize a BAR to allow access to all VRAM. 4572 Adding the wi 4553 Adding the window is slightly risky (it may 4573 conflict with 4554 conflict with unreported devices), so this 4574 taints the ke 4555 taints the kernel. 4575 disable_acs_redir=<pci_dev>[; 4556 disable_acs_redir=<pci_dev>[; ...] 4576 Specify one o 4557 Specify one or more PCI devices (in the format 4577 specified abo 4558 specified above) separated by semicolons. 4578 Each device s 4559 Each device specified will have the PCI ACS 4579 redirect capa 4560 redirect capabilities forced off which will 4580 allow P2P tra 4561 allow P2P traffic between devices through 4581 bridges witho 4562 bridges without forcing it upstream. Note: 4582 this removes 4563 this removes isolation between devices and 4583 may put more 4564 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 4565 force_floating [S390] Force usage of floating interrupts. 4617 nomio [S390] Do not 4566 nomio [S390] Do not use MIO instructions. 4618 norid [S390] ignore 4567 norid [S390] ignore the RID field and force use of 4619 one PCI domai 4568 one PCI domain per PCI function 4620 4569 4621 pcie_aspm= [PCIE] Forcibly enabl !! 4570 pcie_aspm= [PCIE] Forcibly enable or disable PCIe Active State Power 4622 Management. 4571 Management. 4623 off Don't touch ASPM conf !! 4572 off Disable ASPM. 4624 configuration done by << 4625 force Enable ASPM even on d 4573 force Enable ASPM even on devices that claim not to support it. 4626 WARNING: Forcing ASPM 4574 WARNING: Forcing ASPM on may cause system lockups. 4627 4575 4628 pcie_ports= [PCIE] PCIe port serv 4576 pcie_ports= [PCIE] PCIe port services handling: 4629 native Use native PCIe servi 4577 native Use native PCIe services (PME, AER, DPC, PCIe hotplug) 4630 even if the platform 4578 even if the platform doesn't give the OS permission to 4631 use them. This may c 4579 use them. This may cause conflicts if the platform 4632 also tries to use the 4580 also tries to use these services. 4633 dpc-native Use native PC 4581 dpc-native Use native PCIe service for DPC only. May 4634 cause conflic 4582 cause conflicts if firmware uses AER or DPC. 4635 compat Disable native PCIe s 4583 compat Disable native PCIe services (PME, AER, DPC, PCIe 4636 hotplug). 4584 hotplug). 4637 4585 4638 pcie_port_pm= [PCIE] PCIe port powe 4586 pcie_port_pm= [PCIE] PCIe port power management handling: 4639 off Disable power managem 4587 off Disable power management of all PCIe ports 4640 force Forcibly enable power 4588 force Forcibly enable power management of all PCIe ports 4641 4589 4642 pcie_pme= [PCIE,PM] Native PCIe 4590 pcie_pme= [PCIE,PM] Native PCIe PME signaling options: 4643 nomsi Do not use MSI for na 4591 nomsi Do not use MSI for native PCIe PME signaling (this makes 4644 all PCIe root ports u 4592 all PCIe root ports use INTx for all services). 4645 4593 4646 pcmv= [HW,PCMCIA] BadgePAD 4594 pcmv= [HW,PCMCIA] BadgePAD 4 4647 4595 4648 pd_ignore_unused 4596 pd_ignore_unused 4649 [PM] 4597 [PM] 4650 Keep all power-domain 4598 Keep all power-domains already enabled by bootloader on, 4651 even if no driver has 4599 even if no driver has claimed them. This is useful 4652 for debug and develop 4600 for debug and development, but should not be 4653 needed on a platform 4601 needed on a platform with proper driver support. 4654 4602 4655 pdcchassis= [PARISC,HW] Disable/E 4603 pdcchassis= [PARISC,HW] Disable/Enable PDC Chassis Status codes at 4656 boot time. 4604 boot time. 4657 Format: { 0 | 1 } 4605 Format: { 0 | 1 } 4658 See arch/parisc/kerne 4606 See arch/parisc/kernel/pdc_chassis.c 4659 4607 4660 percpu_alloc= [MM,EARLY] !! 4608 percpu_alloc= Select which percpu first chunk allocator to use. 4661 Select which percpu f << 4662 Currently supported v 4609 Currently supported values are "embed" and "page". 4663 Archs may support sub 4610 Archs may support subset or none of the selections. 4664 See comments in mm/pe 4611 See comments in mm/percpu.c for details on each 4665 allocator. This para 4612 allocator. This parameter is primarily for debugging 4666 and performance compa 4613 and performance comparison. 4667 4614 4668 pirq= [SMP,APIC] Manual mp- 4615 pirq= [SMP,APIC] Manual mp-table setup 4669 See Documentation/arc 4616 See Documentation/arch/x86/i386/IO-APIC.rst. 4670 4617 4671 plip= [PPT,NET] Parallel po 4618 plip= [PPT,NET] Parallel port network link 4672 Format: { parport<nr> 4619 Format: { parport<nr> | timid | 0 } 4673 See also Documentatio 4620 See also Documentation/admin-guide/parport.rst. 4674 4621 4675 pmtmr= [X86] Manual setup of 4622 pmtmr= [X86] Manual setup of pmtmr I/O Port. 4676 Override pmtimer IOPo 4623 Override pmtimer IOPort with a hex value. 4677 e.g. pmtmr=0x508 4624 e.g. pmtmr=0x508 4678 4625 4679 pmu_override= [PPC] Override the PM 4626 pmu_override= [PPC] Override the PMU. 4680 This option takes ove 4627 This option takes over the PMU facility, so it is no 4681 longer usable by perf 4628 longer usable by perf. Setting this option starts the 4682 PMU counters by setti 4629 PMU counters by setting MMCR0 to 0 (the FC bit is 4683 cleared). If a number 4630 cleared). If a number is given, then MMCR1 is set to 4684 that number, otherwis 4631 that number, otherwise (e.g., 'pmu_override=on'), MMCR1 4685 remains 0. 4632 remains 0. 4686 4633 4687 pm_debug_messages [SUSPEND,KNL] 4634 pm_debug_messages [SUSPEND,KNL] 4688 Enable suspend/resume 4635 Enable suspend/resume debug messages during boot up. 4689 4636 4690 pnp.debug=1 [PNP] 4637 pnp.debug=1 [PNP] 4691 Enable PNP debug mess 4638 Enable PNP debug messages (depends on the 4692 CONFIG_PNP_DEBUG_MESS 4639 CONFIG_PNP_DEBUG_MESSAGES option). Change at run-time 4693 via /sys/module/pnp/p 4640 via /sys/module/pnp/parameters/debug. We always show 4694 current resource usag 4641 current resource usage; turning this on also shows 4695 possible settings and 4642 possible settings and some assignment information. 4696 4643 4697 pnpacpi= [ACPI] 4644 pnpacpi= [ACPI] 4698 { off } 4645 { off } 4699 4646 4700 pnpbios= [ISAPNP] 4647 pnpbios= [ISAPNP] 4701 { on | off | curr | r 4648 { on | off | curr | res | no-curr | no-res } 4702 4649 4703 pnp_reserve_irq= 4650 pnp_reserve_irq= 4704 [ISAPNP] Exclude IRQs 4651 [ISAPNP] Exclude IRQs for the autoconfiguration 4705 4652 4706 pnp_reserve_dma= 4653 pnp_reserve_dma= 4707 [ISAPNP] Exclude DMAs 4654 [ISAPNP] Exclude DMAs for the autoconfiguration 4708 4655 4709 pnp_reserve_io= [ISAPNP] Exclude I/O 4656 pnp_reserve_io= [ISAPNP] Exclude I/O ports for the autoconfiguration 4710 Ranges are in pairs ( 4657 Ranges are in pairs (I/O port base and size). 4711 4658 4712 pnp_reserve_mem= 4659 pnp_reserve_mem= 4713 [ISAPNP] Exclude memo 4660 [ISAPNP] Exclude memory regions for the 4714 autoconfiguration. 4661 autoconfiguration. 4715 Ranges are in pairs ( 4662 Ranges are in pairs (memory base and size). 4716 4663 4717 ports= [IP_VS_FTP] IPVS ftp 4664 ports= [IP_VS_FTP] IPVS ftp helper module 4718 Default is 21. 4665 Default is 21. 4719 Up to 8 (IP_VS_APP_MA 4666 Up to 8 (IP_VS_APP_MAX_PORTS) ports 4720 may be specified. 4667 may be specified. 4721 Format: <port>,<port> 4668 Format: <port>,<port>.... 4722 4669 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 4670 powersave=off [PPC] This option disables power saving features. 4729 It specifically disab 4671 It specifically disables cpuidle and sets the 4730 platform machine desc 4672 platform machine description specific power_save 4731 function to NULL. On 4673 function to NULL. On Idle the CPU just reduces 4732 execution priority. 4674 execution priority. 4733 4675 4734 ppc_strict_facility_enable 4676 ppc_strict_facility_enable 4735 [PPC,ENABLE] This opt !! 4677 [PPC] This option catches any kernel floating point, 4736 Altivec, VSX and SPE 4678 Altivec, VSX and SPE outside of regions specifically 4737 allowed (eg kernel_en 4679 allowed (eg kernel_enable_fpu()/kernel_disable_fpu()). 4738 There is some perform 4680 There is some performance impact when enabling this. 4739 4681 4740 ppc_tm= [PPC,EARLY] !! 4682 ppc_tm= [PPC] 4741 Format: {"off"} 4683 Format: {"off"} 4742 Disable Hardware Tran 4684 Disable Hardware Transactional Memory 4743 4685 4744 preempt= [KNL] 4686 preempt= [KNL] 4745 Select preemption mod 4687 Select preemption mode if you have CONFIG_PREEMPT_DYNAMIC 4746 none - Limited to con 4688 none - Limited to cond_resched() calls 4747 voluntary - Limited t 4689 voluntary - Limited to cond_resched() and might_sleep() calls 4748 full - Any section th 4690 full - Any section that isn't explicitly preempt disabled 4749 can be preempt !! 4691 can be preempted anytime. 4750 contended spin << 4751 explicitly pre << 4752 4692 4753 print-fatal-signals= 4693 print-fatal-signals= 4754 [KNL] debug: print fa 4694 [KNL] debug: print fatal signals 4755 4695 4756 If enabled, warn abou 4696 If enabled, warn about various signal handling 4757 related application a 4697 related application anomalies: too many signals, 4758 too many POSIX.1 time 4698 too many POSIX.1 timers, fatal signals causing a 4759 coredump - etc. 4699 coredump - etc. 4760 4700 4761 If you hit the warnin 4701 If you hit the warning due to signal overflow, 4762 you might want to try 4702 you might want to try "ulimit -i unlimited". 4763 4703 4764 default: off. 4704 default: off. 4765 4705 4766 printk.always_kmsg_dump= 4706 printk.always_kmsg_dump= 4767 Trigger kmsg_dump for 4707 Trigger kmsg_dump for cases other than kernel oops or 4768 panics 4708 panics 4769 Format: <bool> (1/Y/ 4709 Format: <bool> (1/Y/y=enable, 0/N/n=disable) 4770 default: disabled 4710 default: disabled 4771 4711 4772 printk.console_no_auto_verbose= 4712 printk.console_no_auto_verbose= 4773 Disable console logle 4713 Disable console loglevel raise on oops, panic 4774 or lockdep-detected i 4714 or lockdep-detected issues (only if lock debug is on). 4775 With an exception to 4715 With an exception to setups with low baudrate on 4776 serial console, keepi 4716 serial console, keeping this 0 is a good choice 4777 in order to provide m 4717 in order to provide more debug information. 4778 Format: <bool> 4718 Format: <bool> 4779 default: 0 (auto_verb 4719 default: 0 (auto_verbose is enabled) 4780 4720 4781 printk.devkmsg={on,off,ratelimit} 4721 printk.devkmsg={on,off,ratelimit} 4782 Control writing to /d 4722 Control writing to /dev/kmsg. 4783 on - unlimited loggin 4723 on - unlimited logging to /dev/kmsg from userspace 4784 off - logging to /dev 4724 off - logging to /dev/kmsg disabled 4785 ratelimit - ratelimit 4725 ratelimit - ratelimit the logging 4786 Default: ratelimit 4726 Default: ratelimit 4787 4727 4788 printk.time= Show timing data pref 4728 printk.time= Show timing data prefixed to each printk message line 4789 Format: <bool> (1/Y/ 4729 Format: <bool> (1/Y/y=enable, 0/N/n=disable) 4790 4730 4791 proc_mem.force_override= [KNL] << 4792 Format: {always | ptr << 4793 Traditionally /proc/p << 4794 overridden without re << 4795 restrict that. Can be << 4796 - 'always': tradition << 4797 - 'ptrace': only allo << 4798 - 'never': never all << 4799 If not specified, def << 4800 << 4801 processor.max_cstate= [HW,ACPI] 4731 processor.max_cstate= [HW,ACPI] 4802 Limit processor to ma 4732 Limit processor to maximum C-state 4803 max_cstate=9 override 4733 max_cstate=9 overrides any DMI blacklist limit. 4804 4734 4805 processor.nocst [HW,ACPI] 4735 processor.nocst [HW,ACPI] 4806 Ignore the _CST metho 4736 Ignore the _CST method to determine C-states, 4807 instead using the leg 4737 instead using the legacy FADT method 4808 4738 4809 profile= [KNL] Enable kernel p 4739 profile= [KNL] Enable kernel profiling via /proc/profile 4810 Format: [<profiletype 4740 Format: [<profiletype>,]<number> 4811 Param: <profiletype>: !! 4741 Param: <profiletype>: "schedule", "sleep", or "kvm" 4812 [defaults to 4742 [defaults to kernel profiling] 4813 Param: "schedule" - p 4743 Param: "schedule" - profile schedule points. >> 4744 Param: "sleep" - profile D-state sleeping (millisecs). >> 4745 Requires CONFIG_SCHEDSTATS 4814 Param: "kvm" - profil 4746 Param: "kvm" - profile VM exits. 4815 Param: <number> - ste 4747 Param: <number> - step/bucket size as a power of 2 for 4816 statistical t 4748 statistical time based profiling. 4817 4749 4818 prompt_ramdisk= [RAM] [Deprecated] 4750 prompt_ramdisk= [RAM] [Deprecated] 4819 4751 4820 prot_virt= [S390] enable hosting 4752 prot_virt= [S390] enable hosting protected virtual machines 4821 isolated from the hyp 4753 isolated from the hypervisor (if hardware supports 4822 that). If enabled, th !! 4754 that). 4823 might be overridden e << 4824 Layout Randomization << 4825 Format: <bool> 4755 Format: <bool> 4826 4756 4827 psi= [KNL] Enable or disab 4757 psi= [KNL] Enable or disable pressure stall information 4828 tracking. 4758 tracking. 4829 Format: <bool> 4759 Format: <bool> 4830 4760 4831 psmouse.proto= [HW,MOUSE] Highest PS 4761 psmouse.proto= [HW,MOUSE] Highest PS2 mouse protocol extension to 4832 probe for; one of (ba 4762 probe for; one of (bare|imps|exps|lifebook|any). 4833 psmouse.rate= [HW,MOUSE] Set desire 4763 psmouse.rate= [HW,MOUSE] Set desired mouse report rate, in reports 4834 per second. 4764 per second. 4835 psmouse.resetafter= [HW,MOUSE] 4765 psmouse.resetafter= [HW,MOUSE] 4836 Try to reset the devi 4766 Try to reset the device after so many bad packets 4837 (0 = never). 4767 (0 = never). 4838 psmouse.resolution= 4768 psmouse.resolution= 4839 [HW,MOUSE] Set desire 4769 [HW,MOUSE] Set desired mouse resolution, in dpi. 4840 psmouse.smartscroll= 4770 psmouse.smartscroll= 4841 [HW,MOUSE] Controls L 4771 [HW,MOUSE] Controls Logitech smartscroll autorepeat. 4842 0 = disabled, 1 = ena 4772 0 = disabled, 1 = enabled (default). 4843 4773 4844 pstore.backend= Specify the name of t 4774 pstore.backend= Specify the name of the pstore backend to use 4845 4775 4846 pti= [X86-64] Control Page 4776 pti= [X86-64] Control Page Table Isolation of user and 4847 kernel address spaces 4777 kernel address spaces. Disabling this feature 4848 removes hardening, bu 4778 removes hardening, but improves performance of 4849 system calls and inte 4779 system calls and interrupts. 4850 4780 4851 on - unconditionall 4781 on - unconditionally enable 4852 off - unconditionall 4782 off - unconditionally disable 4853 auto - kernel detects 4783 auto - kernel detects whether your CPU model is 4854 vulnerable to 4784 vulnerable to issues that PTI mitigates 4855 4785 4856 Not specifying this o 4786 Not specifying this option is equivalent to pti=auto. 4857 4787 4858 pty.legacy_count= 4788 pty.legacy_count= 4859 [KNL] Number of legac 4789 [KNL] Number of legacy pty's. Overwrites compiled-in 4860 default number. 4790 default number. 4861 4791 4862 quiet [KNL,EARLY] Disable m !! 4792 quiet [KNL] Disable most log messages 4863 4793 4864 r128= [HW,DRM] 4794 r128= [HW,DRM] 4865 4795 4866 radix_hcall_invalidate=on [PPC/PSERI 4796 radix_hcall_invalidate=on [PPC/PSERIES] 4867 Disable RADIX GTSE fe 4797 Disable RADIX GTSE feature and use hcall for TLB 4868 invalidate. 4798 invalidate. 4869 4799 4870 raid= [HW,RAID] 4800 raid= [HW,RAID] 4871 See Documentation/adm 4801 See Documentation/admin-guide/md.rst. 4872 4802 4873 ramdisk_size= [RAM] Sizes of RAM di 4803 ramdisk_size= [RAM] Sizes of RAM disks in kilobytes 4874 See Documentation/adm 4804 See Documentation/admin-guide/blockdev/ramdisk.rst. 4875 4805 4876 ramdisk_start= [RAM] RAM disk image 4806 ramdisk_start= [RAM] RAM disk image start address 4877 4807 4878 random.trust_cpu=off 4808 random.trust_cpu=off 4879 [KNL,EARLY] Disable t !! 4809 [KNL] Disable trusting the use of the CPU's 4880 random number generat 4810 random number generator (if available) to 4881 initialize the kernel 4811 initialize the kernel's RNG. 4882 4812 4883 random.trust_bootloader=off 4813 random.trust_bootloader=off 4884 [KNL,EARLY] Disable t !! 4814 [KNL] Disable trusting the use of the a seed 4885 passed by the bootloa 4815 passed by the bootloader (if available) to 4886 initialize the kernel 4816 initialize the kernel's RNG. 4887 4817 4888 randomize_kstack_offset= 4818 randomize_kstack_offset= 4889 [KNL,EARLY] Enable or !! 4819 [KNL] Enable or disable kernel stack offset 4890 randomization, which 4820 randomization, which provides roughly 5 bits of 4891 entropy, frustrating 4821 entropy, frustrating memory corruption attacks 4892 that depend on stack 4822 that depend on stack address determinism or 4893 cross-syscall address 4823 cross-syscall address exposures. This is only 4894 available on architec 4824 available on architectures that have defined 4895 CONFIG_HAVE_ARCH_RAND 4825 CONFIG_HAVE_ARCH_RANDOMIZE_KSTACK_OFFSET. 4896 Format: <bool> (1/Y/ 4826 Format: <bool> (1/Y/y=enable, 0/N/n=disable) 4897 Default is CONFIG_RAN 4827 Default is CONFIG_RANDOMIZE_KSTACK_OFFSET_DEFAULT. 4898 4828 4899 ras=option[,option,...] [KNL] RAS-spe 4829 ras=option[,option,...] [KNL] RAS-specific options 4900 4830 4901 cec_disable [X86] 4831 cec_disable [X86] 4902 Disable the C 4832 Disable the Correctable Errors Collector, 4903 see CONFIG_RA 4833 see CONFIG_RAS_CEC help text. 4904 4834 4905 rcu_nocbs[=cpu-list] 4835 rcu_nocbs[=cpu-list] 4906 [KNL] The optional ar 4836 [KNL] The optional argument is a cpu list, 4907 as described above. 4837 as described above. 4908 4838 4909 In kernels built with 4839 In kernels built with CONFIG_RCU_NOCB_CPU=y, 4910 enable the no-callbac 4840 enable the no-callback CPU mode, which prevents 4911 such CPUs' callbacks 4841 such CPUs' callbacks from being invoked in 4912 softirq context. Inv 4842 softirq context. Invocation of such CPUs' RCU 4913 callbacks will instea 4843 callbacks will instead be offloaded to "rcuox/N" 4914 kthreads created for 4844 kthreads created for that purpose, where "x" is 4915 "p" for RCU-preempt, 4845 "p" for RCU-preempt, "s" for RCU-sched, and "g" 4916 for the kthreads that 4846 for the kthreads that mediate grace periods; and 4917 "N" is the CPU number 4847 "N" is the CPU number. This reduces OS jitter on 4918 the offloaded CPUs, w 4848 the offloaded CPUs, which can be useful for HPC 4919 and real-time workloa 4849 and real-time workloads. It can also improve 4920 energy efficiency for 4850 energy efficiency for asymmetric multiprocessors. 4921 4851 4922 If a cpulist is passe 4852 If a cpulist is passed as an argument, the specified 4923 list of CPUs is set t 4853 list of CPUs is set to no-callback mode from boot. 4924 4854 4925 Otherwise, if the '=' 4855 Otherwise, if the '=' sign and the cpulist 4926 arguments are omitted 4856 arguments are omitted, no CPU will be set to 4927 no-callback mode from 4857 no-callback mode from boot but the mode may be 4928 toggled at runtime vi 4858 toggled at runtime via cpusets. 4929 4859 4930 Note that this argume 4860 Note that this argument takes precedence over 4931 the CONFIG_RCU_NOCB_C 4861 the CONFIG_RCU_NOCB_CPU_DEFAULT_ALL option. 4932 4862 4933 rcu_nocb_poll [KNL] 4863 rcu_nocb_poll [KNL] 4934 Rather than requiring 4864 Rather than requiring that offloaded CPUs 4935 (specified by rcu_noc 4865 (specified by rcu_nocbs= above) explicitly 4936 awaken the correspond 4866 awaken the corresponding "rcuoN" kthreads, 4937 make these kthreads p 4867 make these kthreads poll for callbacks. 4938 This improves the rea 4868 This improves the real-time response for the 4939 offloaded CPUs by rel 4869 offloaded CPUs by relieving them of the need to 4940 wake up the correspon 4870 wake up the corresponding kthread, but degrades 4941 energy efficiency by 4871 energy efficiency by requiring that the kthreads 4942 periodically wake up 4872 periodically wake up to do the polling. 4943 4873 4944 rcutree.blimit= [KNL] 4874 rcutree.blimit= [KNL] 4945 Set maximum number of 4875 Set maximum number of finished RCU callbacks to 4946 process in one batch. 4876 process in one batch. 4947 4877 4948 rcutree.do_rcu_barrier= [KNL] 4878 rcutree.do_rcu_barrier= [KNL] 4949 Request a call to rcu 4879 Request a call to rcu_barrier(). This is 4950 throttled so that use 4880 throttled so that userspace tests can safely 4951 hammer on the sysfs v 4881 hammer on the sysfs variable if they so choose. 4952 If triggered before t 4882 If triggered before the RCU grace-period machinery 4953 is fully active, this 4883 is fully active, this will error out with EAGAIN. 4954 4884 4955 rcutree.dump_tree= [KNL] 4885 rcutree.dump_tree= [KNL] 4956 Dump the structure of 4886 Dump the structure of the rcu_node combining tree 4957 out at early boot. T 4887 out at early boot. This is used for diagnostic 4958 purposes, to verify c 4888 purposes, to verify correct tree setup. 4959 4889 4960 rcutree.gp_cleanup_delay= [KNL] 4890 rcutree.gp_cleanup_delay= [KNL] 4961 Set the number of jif 4891 Set the number of jiffies to delay each step of 4962 RCU grace-period clea 4892 RCU grace-period cleanup. 4963 4893 4964 rcutree.gp_init_delay= [KNL] 4894 rcutree.gp_init_delay= [KNL] 4965 Set the number of jif 4895 Set the number of jiffies to delay each step of 4966 RCU grace-period init 4896 RCU grace-period initialization. 4967 4897 4968 rcutree.gp_preinit_delay= [KNL] 4898 rcutree.gp_preinit_delay= [KNL] 4969 Set the number of jif 4899 Set the number of jiffies to delay each step of 4970 RCU grace-period pre- 4900 RCU grace-period pre-initialization, that is, 4971 the propagation of re 4901 the propagation of recent CPU-hotplug changes up 4972 the rcu_node combinin 4902 the rcu_node combining tree. 4973 4903 4974 rcutree.jiffies_till_first_fqs= [KNL] 4904 rcutree.jiffies_till_first_fqs= [KNL] 4975 Set delay from grace- 4905 Set delay from grace-period initialization to 4976 first attempt to forc 4906 first attempt to force quiescent states. 4977 Units are jiffies, mi 4907 Units are jiffies, minimum value is zero, 4978 and maximum value is 4908 and maximum value is HZ. 4979 4909 4980 rcutree.jiffies_till_next_fqs= [KNL] 4910 rcutree.jiffies_till_next_fqs= [KNL] 4981 Set delay between sub 4911 Set delay between subsequent attempts to force 4982 quiescent states. Un 4912 quiescent states. Units are jiffies, minimum 4983 value is one, and max 4913 value is one, and maximum value is HZ. 4984 4914 4985 rcutree.jiffies_till_sched_qs= [KNL] 4915 rcutree.jiffies_till_sched_qs= [KNL] 4986 Set required age in j 4916 Set required age in jiffies for a 4987 given grace period be 4917 given grace period before RCU starts 4988 soliciting quiescent- 4918 soliciting quiescent-state help from 4989 rcu_note_context_swit 4919 rcu_note_context_switch() and cond_resched(). 4990 If not specified, the 4920 If not specified, the kernel will calculate 4991 a value based on the 4921 a value based on the most recent settings 4992 of rcutree.jiffies_ti 4922 of rcutree.jiffies_till_first_fqs 4993 and rcutree.jiffies_t 4923 and rcutree.jiffies_till_next_fqs. 4994 This calculated value 4924 This calculated value may be viewed in 4995 rcutree.jiffies_to_sc 4925 rcutree.jiffies_to_sched_qs. Any attempt to set 4996 rcutree.jiffies_to_sc 4926 rcutree.jiffies_to_sched_qs will be cheerfully 4997 overwritten. 4927 overwritten. 4998 4928 4999 rcutree.kthread_prio= [KNL,BOOT] 4929 rcutree.kthread_prio= [KNL,BOOT] 5000 Set the SCHED_FIFO pr 4930 Set the SCHED_FIFO priority of the RCU per-CPU 5001 kthreads (rcuc/N). Th 4931 kthreads (rcuc/N). This value is also used for 5002 the priority of the R 4932 the priority of the RCU boost threads (rcub/N) 5003 and for the RCU grace 4933 and for the RCU grace-period kthreads (rcu_bh, 5004 rcu_preempt, and rcu_ 4934 rcu_preempt, and rcu_sched). If RCU_BOOST is 5005 set, valid values are 4935 set, valid values are 1-99 and the default is 1 5006 (the least-favored pr 4936 (the least-favored priority). Otherwise, when 5007 RCU_BOOST is not set, 4937 RCU_BOOST is not set, valid values are 0-99 and 5008 the default is zero ( 4938 the default is zero (non-realtime operation). 5009 When RCU_NOCB_CPU is 4939 When RCU_NOCB_CPU is set, also adjust the 5010 priority of NOCB call 4940 priority of NOCB callback kthreads. 5011 4941 5012 rcutree.nocb_nobypass_lim_per_jiffy= 4942 rcutree.nocb_nobypass_lim_per_jiffy= [KNL] 5013 On callback-offloaded 4943 On callback-offloaded (rcu_nocbs) CPUs, 5014 RCU reduces the lock 4944 RCU reduces the lock contention that would 5015 otherwise be caused b 4945 otherwise be caused by callback floods through 5016 use of the ->nocb_byp 4946 use of the ->nocb_bypass list. However, in the 5017 common non-flooded ca 4947 common non-flooded case, RCU queues directly to 5018 the main ->cblist in 4948 the main ->cblist in order to avoid the extra 5019 overhead of the ->noc 4949 overhead of the ->nocb_bypass list and its lock. 5020 But if there are too 4950 But if there are too many callbacks queued during 5021 a single jiffy, RCU p 4951 a single jiffy, RCU pre-queues the callbacks into 5022 the ->nocb_bypass que 4952 the ->nocb_bypass queue. The definition of "too 5023 many" is supplied by 4953 many" is supplied by this kernel boot parameter. 5024 4954 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] 4955 rcutree.qhimark= [KNL] 5034 Set threshold of queu 4956 Set threshold of queued RCU callbacks beyond which 5035 batch limiting is dis 4957 batch limiting is disabled. 5036 4958 5037 rcutree.qlowmark= [KNL] 4959 rcutree.qlowmark= [KNL] 5038 Set threshold of queu 4960 Set threshold of queued RCU callbacks below which 5039 batch limiting is re- 4961 batch limiting is re-enabled. 5040 4962 5041 rcutree.qovld= [KNL] 4963 rcutree.qovld= [KNL] 5042 Set threshold of queu 4964 Set threshold of queued RCU callbacks beyond which 5043 RCU's force-quiescent 4965 RCU's force-quiescent-state scan will aggressively 5044 enlist help from cond 4966 enlist help from cond_resched() and sched IPIs to 5045 help CPUs more quickl 4967 help CPUs more quickly reach quiescent states. 5046 Set to less than zero 4968 Set to less than zero to make this be set based 5047 on rcutree.qhimark at 4969 on rcutree.qhimark at boot time and to zero to 5048 disable more aggressi 4970 disable more aggressive help enlistment. 5049 4971 5050 rcutree.rcu_delay_page_cache_fill_mse 4972 rcutree.rcu_delay_page_cache_fill_msec= [KNL] 5051 Set the page-cache re 4973 Set the page-cache refill delay (in milliseconds) 5052 in response to low-me 4974 in response to low-memory conditions. The range 5053 of permitted values i 4975 of permitted values is in the range 0:100000. 5054 4976 5055 rcutree.rcu_divisor= [KNL] 4977 rcutree.rcu_divisor= [KNL] 5056 Set the shift-right c 4978 Set the shift-right count to use to compute 5057 the callback-invocati 4979 the callback-invocation batch limit bl from 5058 the number of callbac 4980 the number of callbacks queued on this CPU. 5059 The result will be bo 4981 The result will be bounded below by the value of 5060 the rcutree.blimit ke 4982 the rcutree.blimit kernel parameter. Every bl 5061 callbacks, the softir 4983 callbacks, the softirq handler will exit in 5062 order to allow the CP 4984 order to allow the CPU to do other work. 5063 4985 5064 Please note that this 4986 Please note that this callback-invocation batch 5065 limit applies only to 4987 limit applies only to non-offloaded callback 5066 invocation. Offloade 4988 invocation. Offloaded callbacks are instead 5067 invoked in the contex 4989 invoked in the context of an rcuoc kthread, which 5068 scheduler will preemp 4990 scheduler will preempt as it does any other task. 5069 4991 5070 rcutree.rcu_fanout_exact= [KNL] 4992 rcutree.rcu_fanout_exact= [KNL] 5071 Disable autobalancing 4993 Disable autobalancing of the rcu_node combining 5072 tree. This is used b 4994 tree. This is used by rcutorture, and might 5073 possibly be useful fo 4995 possibly be useful for architectures having high 5074 cache-to-cache transf 4996 cache-to-cache transfer latencies. 5075 4997 5076 rcutree.rcu_fanout_leaf= [KNL] 4998 rcutree.rcu_fanout_leaf= [KNL] 5077 Change the number of 4999 Change the number of CPUs assigned to each 5078 leaf rcu_node structu 5000 leaf rcu_node structure. Useful for very 5079 large systems, which 5001 large systems, which will choose the value 64, 5080 and for NUMA systems 5002 and for NUMA systems with large remote-access 5081 latencies, which will 5003 latencies, which will choose a value aligned 5082 with the appropriate 5004 with the appropriate hardware boundaries. 5083 5005 5084 rcutree.rcu_min_cached_objs= [KNL] 5006 rcutree.rcu_min_cached_objs= [KNL] 5085 Minimum number of obj 5007 Minimum number of objects which are cached and 5086 maintained per one CP 5008 maintained per one CPU. Object size is equal 5087 to PAGE_SIZE. The cac 5009 to PAGE_SIZE. The cache allows to reduce the 5088 pressure to page allo 5010 pressure to page allocator, also it makes the 5089 whole algorithm to be 5011 whole algorithm to behave better in low memory 5090 condition. 5012 condition. 5091 5013 5092 rcutree.rcu_nocb_gp_stride= [KNL] 5014 rcutree.rcu_nocb_gp_stride= [KNL] 5093 Set the number of NOC 5015 Set the number of NOCB callback kthreads in 5094 each group, which def 5016 each group, which defaults to the square root 5095 of the number of CPUs 5017 of the number of CPUs. Larger numbers reduce 5096 the wakeup overhead o 5018 the wakeup overhead on the global grace-period 5097 kthread, but increase 5019 kthread, but increases that same overhead on 5098 each group's NOCB gra 5020 each group's NOCB grace-period kthread. 5099 5021 5100 rcutree.rcu_kick_kthreads= [KNL] 5022 rcutree.rcu_kick_kthreads= [KNL] 5101 Cause the grace-perio 5023 Cause the grace-period kthread to get an extra 5102 wake_up() if it sleep 5024 wake_up() if it sleeps three times longer than 5103 it should at force-qu 5025 it should at force-quiescent-state time. 5104 This wake_up() will b 5026 This wake_up() will be accompanied by a 5105 WARN_ONCE() splat and 5027 WARN_ONCE() splat and an ftrace_dump(). 5106 5028 5107 rcutree.rcu_resched_ns= [KNL] 5029 rcutree.rcu_resched_ns= [KNL] 5108 Limit the time spend 5030 Limit the time spend invoking a batch of RCU 5109 callbacks to the spec 5031 callbacks to the specified number of nanoseconds. 5110 By default, this limi 5032 By default, this limit is checked only once 5111 every 32 callbacks in 5033 every 32 callbacks in order to limit the pain 5112 inflicted by local_cl 5034 inflicted by local_clock() overhead. 5113 5035 5114 rcutree.rcu_unlock_delay= [KNL] 5036 rcutree.rcu_unlock_delay= [KNL] 5115 In CONFIG_RCU_STRICT_ 5037 In CONFIG_RCU_STRICT_GRACE_PERIOD=y kernels, 5116 this specifies an rcu 5038 this specifies an rcu_read_unlock()-time delay 5117 in microseconds. Thi 5039 in microseconds. This defaults to zero. 5118 Larger delays increas 5040 Larger delays increase the probability of 5119 catching RCU pointer 5041 catching RCU pointer leaks, that is, buggy use 5120 of RCU-protected poin 5042 of RCU-protected pointers after the relevant 5121 rcu_read_unlock() has 5043 rcu_read_unlock() has completed. 5122 5044 5123 rcutree.sysrq_rcu= [KNL] 5045 rcutree.sysrq_rcu= [KNL] 5124 Commandeer a sysrq ke 5046 Commandeer a sysrq key to dump out Tree RCU's 5125 rcu_node tree with an 5047 rcu_node tree with an eye towards determining 5126 why a new grace perio 5048 why a new grace period has not yet started. 5127 5049 5128 rcutree.use_softirq= [KNL] 5050 rcutree.use_softirq= [KNL] 5129 If set to zero, move 5051 If set to zero, move all RCU_SOFTIRQ processing to 5130 per-CPU rcuc kthreads 5052 per-CPU rcuc kthreads. Defaults to a non-zero 5131 value, meaning that R 5053 value, meaning that RCU_SOFTIRQ is used by default. 5132 Specify rcutree.use_s 5054 Specify rcutree.use_softirq=0 to use rcuc kthreads. 5133 5055 5134 But note that CONFIG_ 5056 But note that CONFIG_PREEMPT_RT=y kernels disable 5135 this kernel boot para 5057 this kernel boot parameter, forcibly setting it 5136 to zero. 5058 to zero. 5137 5059 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] 5060 rcuscale.gp_async= [KNL] 5158 Measure performance o 5061 Measure performance of asynchronous 5159 grace-period primitiv 5062 grace-period primitives such as call_rcu(). 5160 5063 5161 rcuscale.gp_async_max= [KNL] 5064 rcuscale.gp_async_max= [KNL] 5162 Specify the maximum n 5065 Specify the maximum number of outstanding 5163 callbacks per writer 5066 callbacks per writer thread. When a writer 5164 thread exceeds this l 5067 thread exceeds this limit, it invokes the 5165 corresponding flavor 5068 corresponding flavor of rcu_barrier() to allow 5166 previously posted cal 5069 previously posted callbacks to drain. 5167 5070 5168 rcuscale.gp_exp= [KNL] 5071 rcuscale.gp_exp= [KNL] 5169 Measure performance o 5072 Measure performance of expedited synchronous 5170 grace-period primitiv 5073 grace-period primitives. 5171 5074 5172 rcuscale.holdoff= [KNL] 5075 rcuscale.holdoff= [KNL] 5173 Set test-start holdof 5076 Set test-start holdoff period. The purpose of 5174 this parameter is to 5077 this parameter is to delay the start of the 5175 test until boot compl 5078 test until boot completes in order to avoid 5176 interference. 5079 interference. 5177 5080 5178 rcuscale.kfree_by_call_rcu= [KNL] 5081 rcuscale.kfree_by_call_rcu= [KNL] 5179 In kernels built with 5082 In kernels built with CONFIG_RCU_LAZY=y, test 5180 call_rcu() instead of 5083 call_rcu() instead of kfree_rcu(). 5181 5084 5182 rcuscale.kfree_mult= [KNL] 5085 rcuscale.kfree_mult= [KNL] 5183 Instead of allocating 5086 Instead of allocating an object of size kfree_obj, 5184 allocate one of kfree 5087 allocate one of kfree_mult * sizeof(kfree_obj). 5185 Defaults to 1. 5088 Defaults to 1. 5186 5089 5187 rcuscale.kfree_rcu_test= [KNL] 5090 rcuscale.kfree_rcu_test= [KNL] 5188 Set to measure perfor 5091 Set to measure performance of kfree_rcu() flooding. 5189 5092 5190 rcuscale.kfree_rcu_test_double= [KNL] 5093 rcuscale.kfree_rcu_test_double= [KNL] 5191 Test the double-argum 5094 Test the double-argument variant of kfree_rcu(). 5192 If this parameter has 5095 If this parameter has the same value as 5193 rcuscale.kfree_rcu_te 5096 rcuscale.kfree_rcu_test_single, both the single- 5194 and double-argument v 5097 and double-argument variants are tested. 5195 5098 5196 rcuscale.kfree_rcu_test_single= [KNL] 5099 rcuscale.kfree_rcu_test_single= [KNL] 5197 Test the single-argum 5100 Test the single-argument variant of kfree_rcu(). 5198 If this parameter has 5101 If this parameter has the same value as 5199 rcuscale.kfree_rcu_te 5102 rcuscale.kfree_rcu_test_double, both the single- 5200 and double-argument v 5103 and double-argument variants are tested. 5201 5104 5202 rcuscale.kfree_nthreads= [KNL] 5105 rcuscale.kfree_nthreads= [KNL] 5203 The number of threads 5106 The number of threads running loops of kfree_rcu(). 5204 5107 5205 rcuscale.kfree_alloc_num= [KNL] 5108 rcuscale.kfree_alloc_num= [KNL] 5206 Number of allocations 5109 Number of allocations and frees done in an iteration. 5207 5110 5208 rcuscale.kfree_loops= [KNL] 5111 rcuscale.kfree_loops= [KNL] 5209 Number of loops doing 5112 Number of loops doing rcuscale.kfree_alloc_num number 5210 of allocations and fr 5113 of allocations and frees. 5211 5114 5212 rcuscale.minruntime= [KNL] 5115 rcuscale.minruntime= [KNL] 5213 Set the minimum test 5116 Set the minimum test run time in seconds. This 5214 does not affect the d 5117 does not affect the data-collection interval, 5215 but instead allows be 5118 but instead allows better measurement of things 5216 like CPU consumption. 5119 like CPU consumption. 5217 5120 5218 rcuscale.nreaders= [KNL] 5121 rcuscale.nreaders= [KNL] 5219 Set number of RCU rea 5122 Set number of RCU readers. The value -1 selects 5220 N, where N is the num 5123 N, where N is the number of CPUs. A value 5221 "n" less than -1 sele 5124 "n" less than -1 selects N-n+1, where N is again 5222 the number of CPUs. 5125 the number of CPUs. For example, -2 selects N 5223 (the number of CPUs), 5126 (the number of CPUs), -3 selects N+1, and so on. 5224 A value of "n" less t 5127 A value of "n" less than or equal to -N selects 5225 a single reader. 5128 a single reader. 5226 5129 5227 rcuscale.nwriters= [KNL] 5130 rcuscale.nwriters= [KNL] 5228 Set number of RCU wri 5131 Set number of RCU writers. The values operate 5229 the same as for rcusc 5132 the same as for rcuscale.nreaders. 5230 N, where N is the num 5133 N, where N is the number of CPUs 5231 5134 5232 rcuscale.scale_type= [KNL] 5135 rcuscale.scale_type= [KNL] 5233 Specify the RCU imple 5136 Specify the RCU implementation to test. 5234 5137 5235 rcuscale.shutdown= [KNL] 5138 rcuscale.shutdown= [KNL] 5236 Shut the system down 5139 Shut the system down after performance tests 5237 complete. This is us 5140 complete. This is useful for hands-off automated 5238 testing. 5141 testing. 5239 5142 5240 rcuscale.verbose= [KNL] 5143 rcuscale.verbose= [KNL] 5241 Enable additional pri 5144 Enable additional printk() statements. 5242 5145 5243 rcuscale.writer_holdoff= [KNL] 5146 rcuscale.writer_holdoff= [KNL] 5244 Write-side holdoff be 5147 Write-side holdoff between grace periods, 5245 in microseconds. The 5148 in microseconds. The default of zero says 5246 no holdoff. 5149 no holdoff. 5247 5150 5248 rcuscale.writer_holdoff_jiffies= [KNL 5151 rcuscale.writer_holdoff_jiffies= [KNL] 5249 Additional write-side 5152 Additional write-side holdoff between grace 5250 periods, but in jiffi 5153 periods, but in jiffies. The default of zero 5251 says no holdoff. 5154 says no holdoff. 5252 5155 5253 rcutorture.fqs_duration= [KNL] 5156 rcutorture.fqs_duration= [KNL] 5254 Set duration of force 5157 Set duration of force_quiescent_state bursts 5255 in microseconds. 5158 in microseconds. 5256 5159 5257 rcutorture.fqs_holdoff= [KNL] 5160 rcutorture.fqs_holdoff= [KNL] 5258 Set holdoff time with 5161 Set holdoff time within force_quiescent_state bursts 5259 in microseconds. 5162 in microseconds. 5260 5163 5261 rcutorture.fqs_stutter= [KNL] 5164 rcutorture.fqs_stutter= [KNL] 5262 Set wait time between 5165 Set wait time between force_quiescent_state bursts 5263 in seconds. 5166 in seconds. 5264 5167 5265 rcutorture.fwd_progress= [KNL] 5168 rcutorture.fwd_progress= [KNL] 5266 Specifies the number 5169 Specifies the number of kthreads to be used 5267 for RCU grace-period 5170 for RCU grace-period forward-progress testing 5268 for the types of RCU 5171 for the types of RCU supporting this notion. 5269 Defaults to 1 kthread 5172 Defaults to 1 kthread, values less than zero or 5270 greater than the numb 5173 greater than the number of CPUs cause the number 5271 of CPUs to be used. 5174 of CPUs to be used. 5272 5175 5273 rcutorture.fwd_progress_div= [KNL] 5176 rcutorture.fwd_progress_div= [KNL] 5274 Specify the fraction 5177 Specify the fraction of a CPU-stall-warning 5275 period to do tight-lo 5178 period to do tight-loop forward-progress testing. 5276 5179 5277 rcutorture.fwd_progress_holdoff= [KNL 5180 rcutorture.fwd_progress_holdoff= [KNL] 5278 Number of seconds to 5181 Number of seconds to wait between successive 5279 forward-progress test 5182 forward-progress tests. 5280 5183 5281 rcutorture.fwd_progress_need_resched= 5184 rcutorture.fwd_progress_need_resched= [KNL] 5282 Enclose cond_resched( 5185 Enclose cond_resched() calls within checks for 5283 need_resched() during 5186 need_resched() during tight-loop forward-progress 5284 testing. 5187 testing. 5285 5188 5286 rcutorture.gp_cond= [KNL] 5189 rcutorture.gp_cond= [KNL] 5287 Use conditional/async 5190 Use conditional/asynchronous update-side 5288 primitives, if availa 5191 primitives, if available. 5289 5192 5290 rcutorture.gp_exp= [KNL] 5193 rcutorture.gp_exp= [KNL] 5291 Use expedited update- 5194 Use expedited update-side primitives, if available. 5292 5195 5293 rcutorture.gp_normal= [KNL] 5196 rcutorture.gp_normal= [KNL] 5294 Use normal (non-exped 5197 Use normal (non-expedited) asynchronous 5295 update-side primitive 5198 update-side primitives, if available. 5296 5199 5297 rcutorture.gp_sync= [KNL] 5200 rcutorture.gp_sync= [KNL] 5298 Use normal (non-exped 5201 Use normal (non-expedited) synchronous 5299 update-side primitive 5202 update-side primitives, if available. If all 5300 of rcutorture.gp_cond 5203 of rcutorture.gp_cond=, rcutorture.gp_exp=, 5301 rcutorture.gp_normal= 5204 rcutorture.gp_normal=, and rcutorture.gp_sync= 5302 are zero, rcutorture 5205 are zero, rcutorture acts as if is interpreted 5303 they are all non-zero 5206 they are all non-zero. 5304 5207 5305 rcutorture.irqreader= [KNL] 5208 rcutorture.irqreader= [KNL] 5306 Run RCU readers from 5209 Run RCU readers from irq handlers, or, more 5307 accurately, from a ti 5210 accurately, from a timer handler. Not all RCU 5308 flavors take kindly t 5211 flavors take kindly to this sort of thing. 5309 5212 5310 rcutorture.leakpointer= [KNL] 5213 rcutorture.leakpointer= [KNL] 5311 Leak an RCU-protected 5214 Leak an RCU-protected pointer out of the reader. 5312 This can of course re 5215 This can of course result in splats, and is 5313 intended to test the 5216 intended to test the ability of things like 5314 CONFIG_RCU_STRICT_GRA 5217 CONFIG_RCU_STRICT_GRACE_PERIOD=y to detect 5315 such leaks. 5218 such leaks. 5316 5219 5317 rcutorture.n_barrier_cbs= [KNL] 5220 rcutorture.n_barrier_cbs= [KNL] 5318 Set callbacks/threads 5221 Set callbacks/threads for rcu_barrier() testing. 5319 5222 5320 rcutorture.nfakewriters= [KNL] 5223 rcutorture.nfakewriters= [KNL] 5321 Set number of concurr 5224 Set number of concurrent RCU writers. These just 5322 stress RCU, they don' 5225 stress RCU, they don't participate in the actual 5323 test, hence the "fake 5226 test, hence the "fake". 5324 5227 5325 rcutorture.nocbs_nthreads= [KNL] 5228 rcutorture.nocbs_nthreads= [KNL] 5326 Set number of RCU cal 5229 Set number of RCU callback-offload togglers. 5327 Zero (the default) di 5230 Zero (the default) disables toggling. 5328 5231 5329 rcutorture.nocbs_toggle= [KNL] 5232 rcutorture.nocbs_toggle= [KNL] 5330 Set the delay in mill 5233 Set the delay in milliseconds between successive 5331 callback-offload togg 5234 callback-offload toggling attempts. 5332 5235 5333 rcutorture.nreaders= [KNL] 5236 rcutorture.nreaders= [KNL] 5334 Set number of RCU rea 5237 Set number of RCU readers. The value -1 selects 5335 N-1, where N is the n 5238 N-1, where N is the number of CPUs. A value 5336 "n" less than -1 sele 5239 "n" less than -1 selects N-n-2, where N is again 5337 the number of CPUs. 5240 the number of CPUs. For example, -2 selects N 5338 (the number of CPUs), 5241 (the number of CPUs), -3 selects N+1, and so on. 5339 5242 5340 rcutorture.object_debug= [KNL] 5243 rcutorture.object_debug= [KNL] 5341 Enable debug-object d 5244 Enable debug-object double-call_rcu() testing. 5342 5245 5343 rcutorture.onoff_holdoff= [KNL] 5246 rcutorture.onoff_holdoff= [KNL] 5344 Set time (s) after bo 5247 Set time (s) after boot for CPU-hotplug testing. 5345 5248 5346 rcutorture.onoff_interval= [KNL] 5249 rcutorture.onoff_interval= [KNL] 5347 Set time (jiffies) be 5250 Set time (jiffies) between CPU-hotplug operations, 5348 or zero to disable CP 5251 or zero to disable CPU-hotplug testing. 5349 5252 5350 rcutorture.read_exit= [KNL] 5253 rcutorture.read_exit= [KNL] 5351 Set the number of rea 5254 Set the number of read-then-exit kthreads used 5352 to test the interacti 5255 to test the interaction of RCU updaters and 5353 task-exit processing. 5256 task-exit processing. 5354 5257 5355 rcutorture.read_exit_burst= [KNL] 5258 rcutorture.read_exit_burst= [KNL] 5356 The number of times i 5259 The number of times in a given read-then-exit 5357 episode that a set of 5260 episode that a set of read-then-exit kthreads 5358 is spawned. 5261 is spawned. 5359 5262 5360 rcutorture.read_exit_delay= [KNL] 5263 rcutorture.read_exit_delay= [KNL] 5361 The delay, in seconds 5264 The delay, in seconds, between successive 5362 read-then-exit testin 5265 read-then-exit testing episodes. 5363 5266 5364 rcutorture.shuffle_interval= [KNL] 5267 rcutorture.shuffle_interval= [KNL] 5365 Set task-shuffle inte 5268 Set task-shuffle interval (s). Shuffling tasks 5366 allows some CPUs to g 5269 allows some CPUs to go into dyntick-idle mode 5367 during the rcutorture 5270 during the rcutorture test. 5368 5271 5369 rcutorture.shutdown_secs= [KNL] 5272 rcutorture.shutdown_secs= [KNL] 5370 Set time (s) after bo 5273 Set time (s) after boot system shutdown. This 5371 is useful for hands-o 5274 is useful for hands-off automated testing. 5372 5275 5373 rcutorture.stall_cpu= [KNL] 5276 rcutorture.stall_cpu= [KNL] 5374 Duration of CPU stall 5277 Duration of CPU stall (s) to test RCU CPU stall 5375 warnings, zero to dis 5278 warnings, zero to disable. 5376 5279 5377 rcutorture.stall_cpu_block= [KNL] 5280 rcutorture.stall_cpu_block= [KNL] 5378 Sleep while stalling 5281 Sleep while stalling if set. This will result 5379 in warnings from pree 5282 in warnings from preemptible RCU in addition to 5380 any other stall-relat 5283 any other stall-related activity. Note that 5381 in kernels built with 5284 in kernels built with CONFIG_PREEMPTION=n and 5382 CONFIG_PREEMPT_COUNT= 5285 CONFIG_PREEMPT_COUNT=y, this parameter will 5383 cause the CPU to pass 5286 cause the CPU to pass through a quiescent state. 5384 Given CONFIG_PREEMPTI 5287 Given CONFIG_PREEMPTION=n, this will suppress 5385 RCU CPU stall warning 5288 RCU CPU stall warnings, but will instead result 5386 in scheduling-while-a 5289 in scheduling-while-atomic splats. 5387 5290 5388 Use of this module pa 5291 Use of this module parameter results in splats. 5389 5292 5390 5293 5391 rcutorture.stall_cpu_holdoff= [KNL] 5294 rcutorture.stall_cpu_holdoff= [KNL] 5392 Time to wait (s) afte 5295 Time to wait (s) after boot before inducing stall. 5393 5296 5394 rcutorture.stall_cpu_irqsoff= [KNL] 5297 rcutorture.stall_cpu_irqsoff= [KNL] 5395 Disable interrupts wh 5298 Disable interrupts while stalling if set. 5396 5299 5397 rcutorture.stall_gp_kthread= [KNL] 5300 rcutorture.stall_gp_kthread= [KNL] 5398 Duration (s) of force 5301 Duration (s) of forced sleep within RCU 5399 grace-period kthread 5302 grace-period kthread to test RCU CPU stall 5400 warnings, zero to dis 5303 warnings, zero to disable. If both stall_cpu 5401 and stall_gp_kthread 5304 and stall_gp_kthread are specified, the 5402 kthread is starved fi 5305 kthread is starved first, then the CPU. 5403 5306 5404 rcutorture.stat_interval= [KNL] 5307 rcutorture.stat_interval= [KNL] 5405 Time (s) between stat 5308 Time (s) between statistics printk()s. 5406 5309 5407 rcutorture.stutter= [KNL] 5310 rcutorture.stutter= [KNL] 5408 Time (s) to stutter t 5311 Time (s) to stutter testing, for example, specifying 5409 five seconds causes t 5312 five seconds causes the test to run for five seconds, 5410 wait for five seconds 5313 wait for five seconds, and so on. This tests RCU's 5411 ability to transition 5314 ability to transition abruptly to and from idle. 5412 5315 5413 rcutorture.test_boost= [KNL] 5316 rcutorture.test_boost= [KNL] 5414 Test RCU priority boo 5317 Test RCU priority boosting? 0=no, 1=maybe, 2=yes. 5415 "Maybe" means test if 5318 "Maybe" means test if the RCU implementation 5416 under test support RC 5319 under test support RCU priority boosting. 5417 5320 5418 rcutorture.test_boost_duration= [KNL] 5321 rcutorture.test_boost_duration= [KNL] 5419 Duration (s) of each 5322 Duration (s) of each individual boost test. 5420 5323 5421 rcutorture.test_boost_interval= [KNL] 5324 rcutorture.test_boost_interval= [KNL] 5422 Interval (s) between 5325 Interval (s) between each boost test. 5423 5326 5424 rcutorture.test_no_idle_hz= [KNL] 5327 rcutorture.test_no_idle_hz= [KNL] 5425 Test RCU's dyntick-id 5328 Test RCU's dyntick-idle handling. See also the 5426 rcutorture.shuffle_in 5329 rcutorture.shuffle_interval parameter. 5427 5330 5428 rcutorture.torture_type= [KNL] 5331 rcutorture.torture_type= [KNL] 5429 Specify the RCU imple 5332 Specify the RCU implementation to test. 5430 5333 5431 rcutorture.verbose= [KNL] 5334 rcutorture.verbose= [KNL] 5432 Enable additional pri 5335 Enable additional printk() statements. 5433 5336 5434 rcupdate.rcu_cpu_stall_ftrace_dump= [ 5337 rcupdate.rcu_cpu_stall_ftrace_dump= [KNL] 5435 Dump ftrace buffer af 5338 Dump ftrace buffer after reporting RCU CPU 5436 stall warning. 5339 stall warning. 5437 5340 5438 rcupdate.rcu_cpu_stall_notifiers= [KN 5341 rcupdate.rcu_cpu_stall_notifiers= [KNL] 5439 Provide RCU CPU stall 5342 Provide RCU CPU stall notifiers, but see the 5440 warnings in the RCU_C 5343 warnings in the RCU_CPU_STALL_NOTIFIER Kconfig 5441 option's help text. 5344 option's help text. TL;DR: You almost certainly 5442 do not want rcupdate. 5345 do not want rcupdate.rcu_cpu_stall_notifiers. 5443 5346 5444 rcupdate.rcu_cpu_stall_suppress= [KNL 5347 rcupdate.rcu_cpu_stall_suppress= [KNL] 5445 Suppress RCU CPU stal 5348 Suppress RCU CPU stall warning messages. 5446 5349 5447 rcupdate.rcu_cpu_stall_suppress_at_bo 5350 rcupdate.rcu_cpu_stall_suppress_at_boot= [KNL] 5448 Suppress RCU CPU stal 5351 Suppress RCU CPU stall warning messages and 5449 rcutorture writer sta 5352 rcutorture writer stall warnings that occur 5450 during early boot, th 5353 during early boot, that is, during the time 5451 before the init task 5354 before the init task is spawned. 5452 5355 5453 rcupdate.rcu_cpu_stall_timeout= [KNL] 5356 rcupdate.rcu_cpu_stall_timeout= [KNL] 5454 Set timeout for RCU C 5357 Set timeout for RCU CPU stall warning messages. 5455 The value is in secon 5358 The value is in seconds and the maximum allowed 5456 value is 300 seconds. 5359 value is 300 seconds. 5457 5360 5458 rcupdate.rcu_exp_cpu_stall_timeout= [ 5361 rcupdate.rcu_exp_cpu_stall_timeout= [KNL] 5459 Set timeout for exped 5362 Set timeout for expedited RCU CPU stall warning 5460 messages. The value 5363 messages. The value is in milliseconds 5461 and the maximum allow 5364 and the maximum allowed value is 21000 5462 milliseconds. Please 5365 milliseconds. Please note that this value is 5463 adjusted to an arch t 5366 adjusted to an arch timer tick resolution. 5464 Setting this to zero 5367 Setting this to zero causes the value from 5465 rcupdate.rcu_cpu_stal 5368 rcupdate.rcu_cpu_stall_timeout to be used (after 5466 conversion from secon 5369 conversion from seconds to milliseconds). 5467 5370 5468 rcupdate.rcu_cpu_stall_cputime= [KNL] 5371 rcupdate.rcu_cpu_stall_cputime= [KNL] 5469 Provide statistics on 5372 Provide statistics on the cputime and count of 5470 interrupts and tasks 5373 interrupts and tasks during the sampling period. For 5471 multiple continuous R 5374 multiple continuous RCU stalls, all sampling periods 5472 begin at half of the 5375 begin at half of the first RCU stall timeout. 5473 5376 5474 rcupdate.rcu_exp_stall_task_details= 5377 rcupdate.rcu_exp_stall_task_details= [KNL] 5475 Print stack dumps of 5378 Print stack dumps of any tasks blocking the 5476 current expedited RCU 5379 current expedited RCU grace period during an 5477 expedited RCU CPU sta 5380 expedited RCU CPU stall warning. 5478 5381 5479 rcupdate.rcu_expedited= [KNL] 5382 rcupdate.rcu_expedited= [KNL] 5480 Use expedited grace-p 5383 Use expedited grace-period primitives, for 5481 example, synchronize_ 5384 example, synchronize_rcu_expedited() instead 5482 of synchronize_rcu(). 5385 of synchronize_rcu(). This reduces latency, 5483 but can increase CPU 5386 but can increase CPU utilization, degrade 5484 real-time latency, an 5387 real-time latency, and degrade energy efficiency. 5485 No effect on CONFIG_T 5388 No effect on CONFIG_TINY_RCU kernels. 5486 5389 5487 rcupdate.rcu_normal= [KNL] 5390 rcupdate.rcu_normal= [KNL] 5488 Use only normal grace 5391 Use only normal grace-period primitives, 5489 for example, synchron 5392 for example, synchronize_rcu() instead of 5490 synchronize_rcu_exped 5393 synchronize_rcu_expedited(). This improves 5491 real-time latency, CP 5394 real-time latency, CPU utilization, and 5492 energy efficiency, bu 5395 energy efficiency, but can expose users to 5493 increased grace-perio 5396 increased grace-period latency. This parameter 5494 overrides rcupdate.rc 5397 overrides rcupdate.rcu_expedited. No effect on 5495 CONFIG_TINY_RCU kerne 5398 CONFIG_TINY_RCU kernels. 5496 5399 5497 rcupdate.rcu_normal_after_boot= [KNL] 5400 rcupdate.rcu_normal_after_boot= [KNL] 5498 Once boot has complet 5401 Once boot has completed (that is, after 5499 rcu_end_inkernel_boot 5402 rcu_end_inkernel_boot() has been invoked), use 5500 only normal grace-per 5403 only normal grace-period primitives. No effect 5501 on CONFIG_TINY_RCU ke 5404 on CONFIG_TINY_RCU kernels. 5502 5405 5503 But note that CONFIG_ 5406 But note that CONFIG_PREEMPT_RT=y kernels enables 5504 this kernel boot para 5407 this kernel boot parameter, forcibly setting 5505 it to the value one, 5408 it to the value one, that is, converting any 5506 post-boot attempt at 5409 post-boot attempt at an expedited RCU grace 5507 period to instead use 5410 period to instead use normal non-expedited 5508 grace-period processi 5411 grace-period processing. 5509 5412 5510 rcupdate.rcu_task_collapse_lim= [KNL] 5413 rcupdate.rcu_task_collapse_lim= [KNL] 5511 Set the maximum numbe 5414 Set the maximum number of callbacks present 5512 at the beginning of a 5415 at the beginning of a grace period that allows 5513 the RCU Tasks flavors 5416 the RCU Tasks flavors to collapse back to using 5514 a single callback que 5417 a single callback queue. This switching only 5515 occurs when rcupdate. 5418 occurs when rcupdate.rcu_task_enqueue_lim is 5516 set to the default va 5419 set to the default value of -1. 5517 5420 5518 rcupdate.rcu_task_contend_lim= [KNL] 5421 rcupdate.rcu_task_contend_lim= [KNL] 5519 Set the minimum numbe 5422 Set the minimum number of callback-queuing-time 5520 lock-contention event 5423 lock-contention events per jiffy required to 5521 cause the RCU Tasks f 5424 cause the RCU Tasks flavors to switch to per-CPU 5522 callback queuing. Th 5425 callback queuing. This switching only occurs 5523 when rcupdate.rcu_tas 5426 when rcupdate.rcu_task_enqueue_lim is set to 5524 the default value of 5427 the default value of -1. 5525 5428 5526 rcupdate.rcu_task_enqueue_lim= [KNL] 5429 rcupdate.rcu_task_enqueue_lim= [KNL] 5527 Set the number of cal 5430 Set the number of callback queues to use for the 5528 RCU Tasks family of R 5431 RCU Tasks family of RCU flavors. The default 5529 of -1 allows this to 5432 of -1 allows this to be automatically (and 5530 dynamically) adjusted 5433 dynamically) adjusted. This parameter is intended 5531 for use in testing. 5434 for use in testing. 5532 5435 5533 rcupdate.rcu_task_ipi_delay= [KNL] 5436 rcupdate.rcu_task_ipi_delay= [KNL] 5534 Set time in jiffies d 5437 Set time in jiffies during which RCU tasks will 5535 avoid sending IPIs, s 5438 avoid sending IPIs, starting with the beginning 5536 of a given grace peri 5439 of a given grace period. Setting a large 5537 number avoids disturb 5440 number avoids disturbing real-time workloads, 5538 but lengthens grace p 5441 but lengthens grace periods. 5539 5442 5540 rcupdate.rcu_task_lazy_lim= [KNL] 5443 rcupdate.rcu_task_lazy_lim= [KNL] 5541 Number of callbacks o 5444 Number of callbacks on a given CPU that will 5542 cancel laziness on th 5445 cancel laziness on that CPU. Use -1 to disable 5543 cancellation of lazin 5446 cancellation of laziness, but be advised that 5544 doing so increases th 5447 doing so increases the danger of OOM due to 5545 callback flooding. 5448 callback flooding. 5546 5449 5547 rcupdate.rcu_task_stall_info= [KNL] 5450 rcupdate.rcu_task_stall_info= [KNL] 5548 Set initial timeout i 5451 Set initial timeout in jiffies for RCU task stall 5549 informational message 5452 informational messages, which give some indication 5550 of the problem for th 5453 of the problem for those not patient enough to 5551 wait for ten minutes. 5454 wait for ten minutes. Informational messages are 5552 only printed prior to 5455 only printed prior to the stall-warning message 5553 for a given grace per 5456 for a given grace period. Disable with a value 5554 less than or equal to 5457 less than or equal to zero. Defaults to ten 5555 seconds. A change in 5458 seconds. A change in value does not take effect 5556 until the beginning o 5459 until the beginning of the next grace period. 5557 5460 5558 rcupdate.rcu_task_stall_info_mult= [K 5461 rcupdate.rcu_task_stall_info_mult= [KNL] 5559 Multiplier for time i 5462 Multiplier for time interval between successive 5560 RCU task stall inform 5463 RCU task stall informational messages for a given 5561 RCU tasks grace perio 5464 RCU tasks grace period. This value is clamped 5562 to one through ten, i 5465 to one through ten, inclusive. It defaults to 5563 the value three, so t 5466 the value three, so that the first informational 5564 message is printed 10 5467 message is printed 10 seconds into the grace 5565 period, the second at 5468 period, the second at 40 seconds, the third at 5566 160 seconds, and then 5469 160 seconds, and then the stall warning at 600 5567 seconds would prevent 5470 seconds would prevent a fourth at 640 seconds. 5568 5471 5569 rcupdate.rcu_task_stall_timeout= [KNL 5472 rcupdate.rcu_task_stall_timeout= [KNL] 5570 Set timeout in jiffie 5473 Set timeout in jiffies for RCU task stall 5571 warning messages. Di 5474 warning messages. Disable with a value less 5572 than or equal to zero 5475 than or equal to zero. Defaults to ten minutes. 5573 A change in value doe 5476 A change in value does not take effect until 5574 the beginning of the 5477 the beginning of the next grace period. 5575 5478 5576 rcupdate.rcu_tasks_lazy_ms= [KNL] 5479 rcupdate.rcu_tasks_lazy_ms= [KNL] 5577 Set timeout in millis 5480 Set timeout in milliseconds RCU Tasks asynchronous 5578 callback batching for 5481 callback batching for call_rcu_tasks(). 5579 A negative value will 5482 A negative value will take the default. A value 5580 of zero will disable 5483 of zero will disable batching. Batching is 5581 always disabled for s 5484 always disabled for synchronize_rcu_tasks(). 5582 5485 5583 rcupdate.rcu_tasks_rude_lazy_ms= [KNL 5486 rcupdate.rcu_tasks_rude_lazy_ms= [KNL] 5584 Set timeout in millis 5487 Set timeout in milliseconds RCU Tasks 5585 Rude asynchronous cal 5488 Rude asynchronous callback batching for 5586 call_rcu_tasks_rude() 5489 call_rcu_tasks_rude(). A negative value 5587 will take the default 5490 will take the default. A value of zero will 5588 disable batching. Ba 5491 disable batching. Batching is always disabled 5589 for synchronize_rcu_t 5492 for synchronize_rcu_tasks_rude(). 5590 5493 5591 rcupdate.rcu_tasks_trace_lazy_ms= [KN 5494 rcupdate.rcu_tasks_trace_lazy_ms= [KNL] 5592 Set timeout in millis 5495 Set timeout in milliseconds RCU Tasks 5593 Trace asynchronous ca 5496 Trace asynchronous callback batching for 5594 call_rcu_tasks_trace( 5497 call_rcu_tasks_trace(). A negative value 5595 will take the default 5498 will take the default. A value of zero will 5596 disable batching. Ba 5499 disable batching. Batching is always disabled 5597 for synchronize_rcu_t 5500 for synchronize_rcu_tasks_trace(). 5598 5501 5599 rcupdate.rcu_self_test= [KNL] 5502 rcupdate.rcu_self_test= [KNL] 5600 Run the RCU early boo 5503 Run the RCU early boot self tests 5601 5504 5602 rdinit= [KNL] 5505 rdinit= [KNL] 5603 Format: <full_path> 5506 Format: <full_path> 5604 Run specified binary 5507 Run specified binary instead of /init from the ramdisk, 5605 used for early usersp 5508 used for early userspace startup. See initrd. 5606 5509 5607 rdrand= [X86,EARLY] !! 5510 rdrand= [X86] 5608 force - Override the 5511 force - Override the decision by the kernel to hide the 5609 advertisement 5512 advertisement of RDRAND support (this affects 5610 certain AMD p 5513 certain AMD processors because of buggy BIOS 5611 support, spec 5514 support, specifically around the suspend/resume 5612 path). 5515 path). 5613 5516 5614 rdt= [HW,X86,RDT] 5517 rdt= [HW,X86,RDT] 5615 Turn on/off individua 5518 Turn on/off individual RDT features. List is: 5616 cmt, mbmtotal, mbmloc 5519 cmt, mbmtotal, mbmlocal, l3cat, l3cdp, l2cat, l2cdp, 5617 mba, smba, bmec. 5520 mba, smba, bmec. 5618 E.g. to turn on cmt a 5521 E.g. to turn on cmt and turn off mba use: 5619 rdt=cmt,!mba 5522 rdt=cmt,!mba 5620 5523 5621 reboot= [KNL] 5524 reboot= [KNL] 5622 Format (x86 or x86_64 5525 Format (x86 or x86_64): 5623 [w[arm] | c[o 5526 [w[arm] | c[old] | h[ard] | s[oft] | g[pio]] | d[efault] \ 5624 [[,]s[mp]#### 5527 [[,]s[mp]#### \ 5625 [[,]b[ios] | 5528 [[,]b[ios] | a[cpi] | k[bd] | t[riple] | e[fi] | p[ci]] \ 5626 [[,]f[orce] 5529 [[,]f[orce] 5627 Where reboot_mode is 5530 Where reboot_mode is one of warm (soft) or cold (hard) or gpio 5628 (pref 5531 (prefix with 'panic_' to set mode for panic 5629 reboo 5532 reboot only), 5630 reboot_type is 5533 reboot_type is one of bios, acpi, kbd, triple, efi, or pci, 5631 reboot_force is 5534 reboot_force is either force or not specified, 5632 reboot_cpu is s 5535 reboot_cpu is s[mp]#### with #### being the processor 5633 to be 5536 to be used for rebooting. 5634 5537 5635 refscale.holdoff= [KNL] 5538 refscale.holdoff= [KNL] 5636 Set test-start holdof 5539 Set test-start holdoff period. The purpose of 5637 this parameter is to 5540 this parameter is to delay the start of the 5638 test until boot compl 5541 test until boot completes in order to avoid 5639 interference. 5542 interference. 5640 5543 5641 refscale.lookup_instances= [KNL] 5544 refscale.lookup_instances= [KNL] 5642 Number of data elemen 5545 Number of data elements to use for the forms of 5643 SLAB_TYPESAFE_BY_RCU 5546 SLAB_TYPESAFE_BY_RCU testing. A negative number 5644 is negated and multip 5547 is negated and multiplied by nr_cpu_ids, while 5645 zero specifies nr_cpu 5548 zero specifies nr_cpu_ids. 5646 5549 5647 refscale.loops= [KNL] 5550 refscale.loops= [KNL] 5648 Set the number of loo 5551 Set the number of loops over the synchronization 5649 primitive under test. 5552 primitive under test. Increasing this number 5650 reduces noise due to 5553 reduces noise due to loop start/end overhead, 5651 but the default has a 5554 but the default has already reduced the per-pass 5652 noise to a handful of 5555 noise to a handful of picoseconds on ca. 2020 5653 x86 laptops. 5556 x86 laptops. 5654 5557 5655 refscale.nreaders= [KNL] 5558 refscale.nreaders= [KNL] 5656 Set number of readers 5559 Set number of readers. The default value of -1 5657 selects N, where N is 5560 selects N, where N is roughly 75% of the number 5658 of CPUs. A value of 5561 of CPUs. A value of zero is an interesting choice. 5659 5562 5660 refscale.nruns= [KNL] 5563 refscale.nruns= [KNL] 5661 Set number of runs, e 5564 Set number of runs, each of which is dumped onto 5662 the console log. 5565 the console log. 5663 5566 5664 refscale.readdelay= [KNL] 5567 refscale.readdelay= [KNL] 5665 Set the read-side cri 5568 Set the read-side critical-section duration, 5666 measured in microseco 5569 measured in microseconds. 5667 5570 5668 refscale.scale_type= [KNL] 5571 refscale.scale_type= [KNL] 5669 Specify the read-prot 5572 Specify the read-protection implementation to test. 5670 5573 5671 refscale.shutdown= [KNL] 5574 refscale.shutdown= [KNL] 5672 Shut down the system 5575 Shut down the system at the end of the performance 5673 test. This defaults 5576 test. This defaults to 1 (shut it down) when 5674 refscale is built int 5577 refscale is built into the kernel and to 0 (leave 5675 it running) when refs 5578 it running) when refscale is built as a module. 5676 5579 5677 refscale.verbose= [KNL] 5580 refscale.verbose= [KNL] 5678 Enable additional pri 5581 Enable additional printk() statements. 5679 5582 5680 refscale.verbose_batched= [KNL] 5583 refscale.verbose_batched= [KNL] 5681 Batch the additional 5584 Batch the additional printk() statements. If zero 5682 (the default) or nega 5585 (the default) or negative, print everything. Otherwise, 5683 print every Nth verbo 5586 print every Nth verbose statement, where N is the value 5684 specified. 5587 specified. 5685 5588 5686 regulator_ignore_unused 5589 regulator_ignore_unused 5687 [REGULATOR] 5590 [REGULATOR] 5688 Prevents regulator fr 5591 Prevents regulator framework from disabling regulators 5689 that are unused, due 5592 that are unused, due no driver claiming them. This may 5690 be useful for debug a 5593 be useful for debug and development, but should not be 5691 needed on a platform 5594 needed on a platform with proper driver support. 5692 5595 5693 relax_domain_level= 5596 relax_domain_level= 5694 [KNL, SMP] Set schedu 5597 [KNL, SMP] Set scheduler's default relax_domain_level. 5695 See Documentation/adm 5598 See Documentation/admin-guide/cgroup-v1/cpusets.rst. 5696 5599 5697 reserve= [KNL,BUGS] Force kern 5600 reserve= [KNL,BUGS] Force kernel to ignore I/O ports or memory 5698 Format: <base1>,<size 5601 Format: <base1>,<size1>[,<base2>,<size2>,...] 5699 Reserve I/O ports or 5602 Reserve I/O ports or memory so the kernel won't use 5700 them. If <base> is l 5603 them. If <base> is less than 0x10000, the region 5701 is assumed to be I/O 5604 is assumed to be I/O ports; otherwise it is memory. 5702 5605 5703 reserve_mem= [RAM] !! 5606 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] 5607 Format: nn[KMG] 5727 Reserves a hole at th 5608 Reserves a hole at the top of the kernel virtual 5728 address space. 5609 address space. 5729 5610 5730 reset_devices [KNL] Force drivers t 5611 reset_devices [KNL] Force drivers to reset the underlying device 5731 during initialization 5612 during initialization. 5732 5613 5733 resume= [SWSUSP] 5614 resume= [SWSUSP] 5734 Specify the partition 5615 Specify the partition device for software suspend 5735 Format: 5616 Format: 5736 {/dev/<dev> | PARTUUI 5617 {/dev/<dev> | PARTUUID=<uuid> | <int>:<int> | <hex>} 5737 5618 5738 resume_offset= [SWSUSP] 5619 resume_offset= [SWSUSP] 5739 Specify the offset fr 5620 Specify the offset from the beginning of the partition 5740 given by "resume=" at 5621 given by "resume=" at which the swap header is located, 5741 in <PAGE_SIZE> units 5622 in <PAGE_SIZE> units (needed only for swap files). 5742 See Documentation/po 5623 See Documentation/power/swsusp-and-swap-files.rst 5743 5624 5744 resumedelay= [HIBERNATION] Delay ( 5625 resumedelay= [HIBERNATION] Delay (in seconds) to pause before attempting to 5745 read the resume files 5626 read the resume files 5746 5627 5747 resumewait [HIBERNATION] Wait (i 5628 resumewait [HIBERNATION] Wait (indefinitely) for resume device to show up. 5748 Useful for devices th 5629 Useful for devices that are detected asynchronously 5749 (e.g. USB and MMC dev 5630 (e.g. USB and MMC devices). 5750 5631 5751 retain_initrd [RAM] Keep initrd mem 5632 retain_initrd [RAM] Keep initrd memory after extraction. After boot, it will 5752 be accessible via /sy 5633 be accessible via /sys/firmware/initrd. 5753 5634 5754 retbleed= [X86] Control mitigat 5635 retbleed= [X86] Control mitigation of RETBleed (Arbitrary 5755 Speculative Code Exec 5636 Speculative Code Execution with Return Instructions) 5756 vulnerability. 5637 vulnerability. 5757 5638 5758 AMD-based UNRET and I 5639 AMD-based UNRET and IBPB mitigations alone do not stop 5759 sibling threads from 5640 sibling threads from influencing the predictions of other 5760 sibling threads. For 5641 sibling threads. For that reason, STIBP is used on pro- 5761 cessors that support 5642 cessors that support it, and mitigate SMT on processors 5762 that don't. 5643 that don't. 5763 5644 5764 off - no mit 5645 off - no mitigation 5765 auto - automa 5646 auto - automatically select a migitation 5766 auto,nosmt - automa 5647 auto,nosmt - automatically select a mitigation, 5767 disabl 5648 disabling SMT if necessary for 5768 the fu 5649 the full mitigation (only on Zen1 5769 and ol 5650 and older without STIBP). 5770 ibpb - On AMD 5651 ibpb - On AMD, mitigate short speculation 5771 window 5652 windows on basic block boundaries too. 5772 Safe, 5653 Safe, highest perf impact. It also 5773 enable 5654 enables STIBP if present. Not suitable 5774 on Int 5655 on Intel. 5775 ibpb,nosmt - Like " 5656 ibpb,nosmt - Like "ibpb" above but will disable SMT 5776 when S 5657 when STIBP is not available. This is 5777 the al 5658 the alternative for systems which do not 5778 have S 5659 have STIBP. 5779 unret - Force 5660 unret - Force enable untrained return thunks, 5780 only e 5661 only effective on AMD f15h-f17h based 5781 system 5662 systems. 5782 unret,nosmt - Like u 5663 unret,nosmt - Like unret, but will disable SMT when STIBP 5783 is not 5664 is not available. This is the alternative for 5784 system 5665 systems which do not have STIBP. 5785 5666 5786 Selecting 'auto' will 5667 Selecting 'auto' will choose a mitigation method at run 5787 time according to the 5668 time according to the CPU. 5788 5669 5789 Not specifying this o 5670 Not specifying this option is equivalent to retbleed=auto. 5790 5671 5791 rfkill.default_state= 5672 rfkill.default_state= 5792 0 "airplane mode". All 5673 0 "airplane mode". All wifi, bluetooth, wimax, gps, fm, 5793 etc. communication is 5674 etc. communication is blocked by default. 5794 1 Unblocked. 5675 1 Unblocked. 5795 5676 5796 rfkill.master_switch_mode= 5677 rfkill.master_switch_mode= 5797 0 The "airplane mode" b 5678 0 The "airplane mode" button does nothing. 5798 1 The "airplane mode" b 5679 1 The "airplane mode" button toggles between everything 5799 blocked and the previ 5680 blocked and the previous configuration. 5800 2 The "airplane mode" b 5681 2 The "airplane mode" button toggles between everything 5801 blocked and everythin 5682 blocked and everything unblocked. 5802 5683 >> 5684 rhash_entries= [KNL,NET] >> 5685 Set number of hash buckets for route cache >> 5686 5803 ring3mwait=disable 5687 ring3mwait=disable 5804 [KNL] Disable ring 3 5688 [KNL] Disable ring 3 MONITOR/MWAIT feature on supported 5805 CPUs. 5689 CPUs. 5806 5690 5807 riscv_isa_fallback [RISCV,EARLY] !! 5691 riscv_isa_fallback [RISCV] 5808 When CONFIG_RISCV_ISA 5692 When CONFIG_RISCV_ISA_FALLBACK is not enabled, permit 5809 falling back to detec 5693 falling back to detecting extension support by parsing 5810 "riscv,isa" property 5694 "riscv,isa" property on devicetree systems when the 5811 replacement propertie 5695 replacement properties are not found. See the Kconfig 5812 entry for RISCV_ISA_F 5696 entry for RISCV_ISA_FALLBACK. 5813 5697 5814 ro [KNL] Mount root devi 5698 ro [KNL] Mount root device read-only on boot 5815 5699 5816 rodata= [KNL,EARLY] !! 5700 rodata= [KNL] 5817 on Mark read-only kernel 5701 on Mark read-only kernel memory as read-only (default). 5818 off Leave read-only kerne 5702 off Leave read-only kernel memory writable for debugging. 5819 full Mark read-only kernel 5703 full Mark read-only kernel memory and aliases as read-only 5820 [arm64] 5704 [arm64] 5821 5705 5822 rockchip.usb_uart 5706 rockchip.usb_uart 5823 [EARLY] << 5824 Enable the uart passt 5707 Enable the uart passthrough on the designated usb port 5825 on Rockchip SoCs. Whe 5708 on Rockchip SoCs. When active, the signals of the 5826 debug-uart get routed 5709 debug-uart get routed to the D+ and D- pins of the usb 5827 port and the regular 5710 port and the regular usb controller gets disabled. 5828 5711 5829 root= [KNL] Root filesystem 5712 root= [KNL] Root filesystem 5830 Usually this a a bloc 5713 Usually this a a block device specifier of some kind, 5831 see the early_lookup_ 5714 see the early_lookup_bdev comment in 5832 block/early-lookup.c 5715 block/early-lookup.c for details. 5833 Alternatively this ca 5716 Alternatively this can be "ram" for the legacy initial 5834 ramdisk, "nfs" and "c 5717 ramdisk, "nfs" and "cifs" for root on a network file 5835 system, or "mtd" and 5718 system, or "mtd" and "ubi" for mounting from raw flash. 5836 5719 5837 rootdelay= [KNL] Delay (in secon 5720 rootdelay= [KNL] Delay (in seconds) to pause before attempting to 5838 mount the root filesy 5721 mount the root filesystem 5839 5722 5840 rootflags= [KNL] Set root filesy 5723 rootflags= [KNL] Set root filesystem mount option string 5841 5724 5842 rootfstype= [KNL] Set root filesy 5725 rootfstype= [KNL] Set root filesystem type 5843 5726 5844 rootwait [KNL] Wait (indefinit 5727 rootwait [KNL] Wait (indefinitely) for root device to show up. 5845 Useful for devices th 5728 Useful for devices that are detected asynchronously 5846 (e.g. USB and MMC dev 5729 (e.g. USB and MMC devices). 5847 5730 5848 rootwait= [KNL] Maximum time (i 5731 rootwait= [KNL] Maximum time (in seconds) to wait for root device 5849 to show up before att 5732 to show up before attempting to mount the root 5850 filesystem. 5733 filesystem. 5851 5734 5852 rproc_mem=nn[KMG][@address] 5735 rproc_mem=nn[KMG][@address] 5853 [KNL,ARM,CMA] Remotep 5736 [KNL,ARM,CMA] Remoteproc physical memory block. 5854 Memory area to be use 5737 Memory area to be used by remote processor image, 5855 managed by CMA. 5738 managed by CMA. 5856 5739 5857 rw [KNL] Mount root devi 5740 rw [KNL] Mount root device read-write on boot 5858 5741 5859 S [KNL] Run init in sin 5742 S [KNL] Run init in single mode 5860 5743 5861 s390_iommu= [HW,S390] 5744 s390_iommu= [HW,S390] 5862 Set s390 IOTLB flushi 5745 Set s390 IOTLB flushing mode 5863 strict 5746 strict 5864 With strict flushing 5747 With strict flushing every unmap operation will result 5865 in an IOTLB flush. De 5748 in an IOTLB flush. Default is lazy flushing before 5866 reuse, which is faste 5749 reuse, which is faster. Deprecated, equivalent to 5867 iommu.strict=1. 5750 iommu.strict=1. 5868 5751 5869 s390_iommu_aperture= [KNL,S390] 5752 s390_iommu_aperture= [KNL,S390] 5870 Specifies the size of 5753 Specifies the size of the per device DMA address space 5871 accessible through th 5754 accessible through the DMA and IOMMU APIs as a decimal 5872 factor of the size of 5755 factor of the size of main memory. 5873 The default is 1 mean 5756 The default is 1 meaning that one can concurrently use 5874 as many DMA addresses 5757 as many DMA addresses as physical memory is installed, 5875 if supported by hardw 5758 if supported by hardware, and thus map all of memory 5876 once. With a value of 5759 once. With a value of 2 one can map all of memory twice 5877 and so on. As a speci 5760 and so on. As a special case a factor of 0 imposes no 5878 restrictions other th 5761 restrictions other than those given by hardware at the 5879 cost of significant a 5762 cost of significant additional memory use for tables. 5880 5763 5881 sa1100ir [NET] 5764 sa1100ir [NET] 5882 See drivers/net/irda/ 5765 See drivers/net/irda/sa1100_ir.c. 5883 5766 5884 sched_verbose [KNL,EARLY] Enables v !! 5767 sched_verbose [KNL] Enables verbose scheduler debug messages. 5885 5768 5886 schedstats= [KNL,X86] Enable or d 5769 schedstats= [KNL,X86] Enable or disable scheduled statistics. 5887 Allowed values are en 5770 Allowed values are enable and disable. This feature 5888 incurs a small amount 5771 incurs a small amount of overhead in the scheduler 5889 but is useful for deb 5772 but is useful for debugging and performance tuning. 5890 5773 5891 sched_thermal_decay_shift= 5774 sched_thermal_decay_shift= 5892 [Deprecated] << 5893 [KNL, SMP] Set a deca 5775 [KNL, SMP] Set a decay shift for scheduler thermal 5894 pressure signal. Ther 5776 pressure signal. Thermal pressure signal follows the 5895 default decay period 5777 default decay period of other scheduler pelt 5896 signals(usually 32 ms 5778 signals(usually 32 ms but configurable). Setting 5897 sched_thermal_decay_s 5779 sched_thermal_decay_shift will left shift the decay 5898 period for the therma 5780 period for the thermal pressure signal by the shift 5899 value. 5781 value. 5900 i.e. with the default 5782 i.e. with the default pelt decay period of 32 ms 5901 sched_thermal_decay_s 5783 sched_thermal_decay_shift thermal pressure decay pr 5902 1 5784 1 64 ms 5903 2 5785 2 128 ms 5904 and so on. 5786 and so on. 5905 Format: integer betwe 5787 Format: integer between 0 and 10 5906 Default is 0. 5788 Default is 0. 5907 5789 5908 scftorture.holdoff= [KNL] 5790 scftorture.holdoff= [KNL] 5909 Number of seconds to 5791 Number of seconds to hold off before starting 5910 test. Defaults to ze 5792 test. Defaults to zero for module insertion and 5911 to 10 seconds for bui 5793 to 10 seconds for built-in smp_call_function() 5912 tests. 5794 tests. 5913 5795 5914 scftorture.longwait= [KNL] 5796 scftorture.longwait= [KNL] 5915 Request ridiculously 5797 Request ridiculously long waits randomly selected 5916 up to the chosen limi 5798 up to the chosen limit in seconds. Zero (the 5917 default) disables thi 5799 default) disables this feature. Please note 5918 that requesting even 5800 that requesting even small non-zero numbers of 5919 seconds can result in 5801 seconds can result in RCU CPU stall warnings, 5920 softlockup complaints 5802 softlockup complaints, and so on. 5921 5803 5922 scftorture.nthreads= [KNL] 5804 scftorture.nthreads= [KNL] 5923 Number of kthreads to 5805 Number of kthreads to spawn to invoke the 5924 smp_call_function() f 5806 smp_call_function() family of functions. 5925 The default of -1 spe 5807 The default of -1 specifies a number of kthreads 5926 equal to the number o 5808 equal to the number of CPUs. 5927 5809 5928 scftorture.onoff_holdoff= [KNL] 5810 scftorture.onoff_holdoff= [KNL] 5929 Number seconds to wai 5811 Number seconds to wait after the start of the 5930 test before initiatin 5812 test before initiating CPU-hotplug operations. 5931 5813 5932 scftorture.onoff_interval= [KNL] 5814 scftorture.onoff_interval= [KNL] 5933 Number seconds to wai 5815 Number seconds to wait between successive 5934 CPU-hotplug operation 5816 CPU-hotplug operations. Specifying zero (which 5935 is the default) disab 5817 is the default) disables CPU-hotplug operations. 5936 5818 5937 scftorture.shutdown_secs= [KNL] 5819 scftorture.shutdown_secs= [KNL] 5938 The number of seconds 5820 The number of seconds following the start of the 5939 test after which to s 5821 test after which to shut down the system. The 5940 default of zero avoid 5822 default of zero avoids shutting down the system. 5941 Non-zero values are u 5823 Non-zero values are useful for automated tests. 5942 5824 5943 scftorture.stat_interval= [KNL] 5825 scftorture.stat_interval= [KNL] 5944 The number of seconds 5826 The number of seconds between outputting the 5945 current test statisti 5827 current test statistics to the console. A value 5946 of zero disables stat 5828 of zero disables statistics output. 5947 5829 5948 scftorture.stutter_cpus= [KNL] 5830 scftorture.stutter_cpus= [KNL] 5949 The number of jiffies 5831 The number of jiffies to wait between each change 5950 to the set of CPUs un 5832 to the set of CPUs under test. 5951 5833 5952 scftorture.use_cpus_read_lock= [KNL] 5834 scftorture.use_cpus_read_lock= [KNL] 5953 Use use_cpus_read_loc 5835 Use use_cpus_read_lock() instead of the default 5954 preempt_disable() to 5836 preempt_disable() to disable CPU hotplug 5955 while invoking one of 5837 while invoking one of the smp_call_function*() 5956 functions. 5838 functions. 5957 5839 5958 scftorture.verbose= [KNL] 5840 scftorture.verbose= [KNL] 5959 Enable additional pri 5841 Enable additional printk() statements. 5960 5842 5961 scftorture.weight_single= [KNL] 5843 scftorture.weight_single= [KNL] 5962 The probability weigh 5844 The probability weighting to use for the 5963 smp_call_function_sin 5845 smp_call_function_single() function with a zero 5964 "wait" parameter. A 5846 "wait" parameter. A value of -1 selects the 5965 default if all other 5847 default if all other weights are -1. However, 5966 if at least one weigh 5848 if at least one weight has some other value, a 5967 value of -1 will inst 5849 value of -1 will instead select a weight of zero. 5968 5850 5969 scftorture.weight_single_wait= [KNL] 5851 scftorture.weight_single_wait= [KNL] 5970 The probability weigh 5852 The probability weighting to use for the 5971 smp_call_function_sin 5853 smp_call_function_single() function with a 5972 non-zero "wait" param 5854 non-zero "wait" parameter. See weight_single. 5973 5855 5974 scftorture.weight_many= [KNL] 5856 scftorture.weight_many= [KNL] 5975 The probability weigh 5857 The probability weighting to use for the 5976 smp_call_function_man 5858 smp_call_function_many() function with a zero 5977 "wait" parameter. Se 5859 "wait" parameter. See weight_single. 5978 Note well that settin 5860 Note well that setting a high probability for 5979 this weighting can pl 5861 this weighting can place serious IPI load 5980 on the system. 5862 on the system. 5981 5863 5982 scftorture.weight_many_wait= [KNL] 5864 scftorture.weight_many_wait= [KNL] 5983 The probability weigh 5865 The probability weighting to use for the 5984 smp_call_function_man 5866 smp_call_function_many() function with a 5985 non-zero "wait" param 5867 non-zero "wait" parameter. See weight_single 5986 and weight_many. 5868 and weight_many. 5987 5869 5988 scftorture.weight_all= [KNL] 5870 scftorture.weight_all= [KNL] 5989 The probability weigh 5871 The probability weighting to use for the 5990 smp_call_function_all 5872 smp_call_function_all() function with a zero 5991 "wait" parameter. Se 5873 "wait" parameter. See weight_single and 5992 weight_many. 5874 weight_many. 5993 5875 5994 scftorture.weight_all_wait= [KNL] 5876 scftorture.weight_all_wait= [KNL] 5995 The probability weigh 5877 The probability weighting to use for the 5996 smp_call_function_all 5878 smp_call_function_all() function with a 5997 non-zero "wait" param 5879 non-zero "wait" parameter. See weight_single 5998 and weight_many. 5880 and weight_many. 5999 5881 6000 skew_tick= [KNL,EARLY] Offset th !! 5882 skew_tick= [KNL] Offset the periodic timer tick per cpu to mitigate 6001 xtime_lock contention 5883 xtime_lock contention on larger systems, and/or RCU lock 6002 contention on all sys 5884 contention on all systems with CONFIG_MAXSMP set. 6003 Format: { "0" | "1" } 5885 Format: { "0" | "1" } 6004 0 -- disable. (may be 5886 0 -- disable. (may be 1 via CONFIG_CMDLINE="skew_tick=1" 6005 1 -- enable. 5887 1 -- enable. 6006 Note: increases power 5888 Note: increases power consumption, thus should only be 6007 enabled if running ji 5889 enabled if running jitter sensitive (HPC/RT) workloads. 6008 5890 6009 security= [SECURITY] Choose a l 5891 security= [SECURITY] Choose a legacy "major" security module to 6010 enable at boot. This 5892 enable at boot. This has been deprecated by the 6011 "lsm=" parameter. 5893 "lsm=" parameter. 6012 5894 6013 selinux= [SELINUX] Disable or 5895 selinux= [SELINUX] Disable or enable SELinux at boot time. 6014 Format: { "0" | "1" } 5896 Format: { "0" | "1" } 6015 See security/selinux/ 5897 See security/selinux/Kconfig help text. 6016 0 -- disable. 5898 0 -- disable. 6017 1 -- enable. 5899 1 -- enable. 6018 Default value is 1. 5900 Default value is 1. 6019 5901 6020 serialnumber [BUGS=X86-32] 5902 serialnumber [BUGS=X86-32] 6021 5903 6022 sev=option[,option...] [X86-64] See D 5904 sev=option[,option...] [X86-64] See Documentation/arch/x86/x86_64/boot-options.rst 6023 5905 6024 shapers= [NET] 5906 shapers= [NET] 6025 Maximal number of sha 5907 Maximal number of shapers. 6026 5908 6027 show_lapic= [APIC,X86] Advanced P 5909 show_lapic= [APIC,X86] Advanced Programmable Interrupt Controller 6028 Limit apic dumping. T 5910 Limit apic dumping. The parameter defines the maximal 6029 number of local apics 5911 number of local apics being dumped. Also it is possible 6030 to set it to "all" by 5912 to set it to "all" by meaning -- no limit here. 6031 Format: { 1 (default) 5913 Format: { 1 (default) | 2 | ... | all }. 6032 The parameter valid i 5914 The parameter valid if only apic=debug or 6033 apic=verbose is speci 5915 apic=verbose is specified. 6034 Example: apic=debug s 5916 Example: apic=debug show_lapic=all 6035 5917 6036 slab_debug[=options[,slabs][;[options !! 5918 simeth= [IA-64] 6037 Enabling slab_debug a !! 5919 simscsi= >> 5920 >> 5921 slram= [HW,MTD] >> 5922 >> 5923 slab_merge [MM] >> 5924 Enable merging of slabs with similar size when the >> 5925 kernel is built without CONFIG_SLAB_MERGE_DEFAULT. >> 5926 >> 5927 slab_nomerge [MM] >> 5928 Disable merging of slabs with similar size. May be >> 5929 necessary if there is some reason to distinguish >> 5930 allocs to different slabs, especially in hardened >> 5931 environments where the risk of heap overflows and >> 5932 layout control by attackers can usually be >> 5933 frustrated by disabling merging. This will reduce >> 5934 most of the exposure of a heap attack to a single >> 5935 cache (risks via metadata attacks are mostly >> 5936 unchanged). Debug options disable merging on their >> 5937 own. >> 5938 For more information see Documentation/mm/slub.rst. >> 5939 >> 5940 slab_max_order= [MM, SLAB] >> 5941 Determines the maximum allowed order for slabs. >> 5942 A high setting may cause OOMs due to memory >> 5943 fragmentation. Defaults to 1 for systems with >> 5944 more than 32MB of RAM, 0 otherwise. >> 5945 >> 5946 slub_debug[=options[,slabs][;[options[,slabs]]...] [MM, SLUB] >> 5947 Enabling slub_debug allows one to determine the 6038 culprit if slab objec 5948 culprit if slab objects become corrupted. Enabling 6039 slab_debug can create !! 5949 slub_debug can create guard zones around objects and 6040 may poison objects wh 5950 may poison objects when not in use. Also tracks the 6041 last alloc / free. Fo 5951 last alloc / free. For more information see 6042 Documentation/mm/slub 5952 Documentation/mm/slub.rst. 6043 (slub_debug legacy na << 6044 5953 6045 slab_max_order= [MM] !! 5954 slub_max_order= [MM, SLUB] 6046 Determines the maximu 5955 Determines the maximum allowed order for slabs. 6047 A high setting may ca 5956 A high setting may cause OOMs due to memory 6048 fragmentation. For mo 5957 fragmentation. For more information see 6049 Documentation/mm/slub 5958 Documentation/mm/slub.rst. 6050 (slub_max_order legac << 6051 << 6052 slab_merge [MM] << 6053 Enable merging of sla << 6054 kernel is built witho << 6055 (slub_merge legacy na << 6056 5959 6057 slab_min_objects= [MM] !! 5960 slub_min_objects= [MM, SLUB] 6058 The minimum number of 5961 The minimum number of objects per slab. SLUB will 6059 increase the slab ord !! 5962 increase the slab order up to slub_max_order to 6060 generate a sufficient 5963 generate a sufficiently large slab able to contain 6061 the number of objects 5964 the number of objects indicated. The higher the number 6062 of objects the smalle 5965 of objects the smaller the overhead of tracking slabs 6063 and the less frequent 5966 and the less frequently locks need to be acquired. 6064 For more information 5967 For more information see Documentation/mm/slub.rst. 6065 (slub_min_objects leg << 6066 5968 6067 slab_min_order= [MM] !! 5969 slub_min_order= [MM, SLUB] 6068 Determines the minimu 5970 Determines the minimum page order for slabs. Must be 6069 lower or equal to sla !! 5971 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 5972 For more information see Documentation/mm/slub.rst. 6085 (slub_nomerge legacy << 6086 5973 6087 slram= [HW,MTD] !! 5974 slub_merge [MM, SLUB] >> 5975 Same with slab_merge. >> 5976 >> 5977 slub_nomerge [MM, SLUB] >> 5978 Same with slab_nomerge. This is supported for legacy. >> 5979 See slab_nomerge for more information. 6088 5980 6089 smart2= [HW] 5981 smart2= [HW] 6090 Format: <io1>[,<io2>[ 5982 Format: <io1>[,<io2>[,...,<io8>]] 6091 5983 6092 smp.csd_lock_timeout= [KNL] 5984 smp.csd_lock_timeout= [KNL] 6093 Specify the period of 5985 Specify the period of time in milliseconds 6094 that smp_call_functio 5986 that smp_call_function() and friends will wait 6095 for a CPU to release 5987 for a CPU to release the CSD lock. This is 6096 useful when diagnosin 5988 useful when diagnosing bugs involving CPUs 6097 disabling interrupts 5989 disabling interrupts for extended periods 6098 of time. Defaults to 5990 of time. Defaults to 5,000 milliseconds, and 6099 setting a value of ze 5991 setting a value of zero disables this feature. 6100 This feature may be m 5992 This feature may be more efficiently disabled 6101 using the csdlock_deb 5993 using the csdlock_debug- kernel parameter. 6102 5994 6103 smp.panic_on_ipistall= [KNL] 5995 smp.panic_on_ipistall= [KNL] 6104 If a csd_lock_timeout 5996 If a csd_lock_timeout extends for more than 6105 the specified number 5997 the specified number of milliseconds, panic the 6106 system. By default, 5998 system. By default, let CSD-lock acquisition 6107 take as long as they 5999 take as long as they take. Specifying 300,000 6108 for this value provid 6000 for this value provides a 5-minute timeout. 6109 6001 6110 smsc-ircc2.nopnp [HW] Don't us 6002 smsc-ircc2.nopnp [HW] Don't use PNP to discover SMC devices 6111 smsc-ircc2.ircc_cfg= [HW] Device c 6003 smsc-ircc2.ircc_cfg= [HW] Device configuration I/O port 6112 smsc-ircc2.ircc_sir= [HW] SIR base 6004 smsc-ircc2.ircc_sir= [HW] SIR base I/O port 6113 smsc-ircc2.ircc_fir= [HW] FIR base 6005 smsc-ircc2.ircc_fir= [HW] FIR base I/O port 6114 smsc-ircc2.ircc_irq= [HW] IRQ line 6006 smsc-ircc2.ircc_irq= [HW] IRQ line 6115 smsc-ircc2.ircc_dma= [HW] DMA chan 6007 smsc-ircc2.ircc_dma= [HW] DMA channel 6116 smsc-ircc2.ircc_transceiver= [HW] Tra 6008 smsc-ircc2.ircc_transceiver= [HW] Transceiver type: 6117 0: Toshiba Sa 6009 0: Toshiba Satellite 1800 (GP data pin select) 6118 1: Fast pin s 6010 1: Fast pin select (default) 6119 2: ATC IRMode 6011 2: ATC IRMode 6120 6012 6121 smt= [KNL,MIPS,S390,EARLY] !! 6013 smt= [KNL,MIPS,S390] Set the maximum number of threads (logical 6122 (logical CPUs) to use !! 6014 CPUs) to use per physical CPU on systems capable of 6123 capable of symmetric !! 6015 symmetric multithreading (SMT). Will be capped to the 6124 be capped to the actu !! 6016 actual hardware limit. 6125 Format: <integer> 6017 Format: <integer> 6126 Default: -1 (no limit 6018 Default: -1 (no limit) 6127 6019 6128 softlockup_panic= 6020 softlockup_panic= 6129 [KNL] Should the soft 6021 [KNL] Should the soft-lockup detector generate panics. 6130 Format: 0 | 1 6022 Format: 0 | 1 6131 6023 6132 A value of 1 instruct 6024 A value of 1 instructs the soft-lockup detector 6133 to panic the machine 6025 to panic the machine when a soft-lockup occurs. It is 6134 also controlled by th 6026 also controlled by the kernel.softlockup_panic sysctl 6135 and CONFIG_BOOTPARAM_ 6027 and CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC, which is the 6136 respective build-time 6028 respective build-time switch to that functionality. 6137 6029 6138 softlockup_all_cpu_backtrace= 6030 softlockup_all_cpu_backtrace= 6139 [KNL] Should the soft 6031 [KNL] Should the soft-lockup detector generate 6140 backtraces on all cpu 6032 backtraces on all cpus. 6141 Format: 0 | 1 6033 Format: 0 | 1 6142 6034 6143 sonypi.*= [HW] Sony Programmabl 6035 sonypi.*= [HW] Sony Programmable I/O Control Device driver 6144 See Documentation/adm 6036 See Documentation/admin-guide/laptops/sonypi.rst 6145 6037 6146 spectre_bhi= [X86] Control mitigat 6038 spectre_bhi= [X86] Control mitigation of Branch History Injection 6147 (BHI) vulnerability. 6039 (BHI) vulnerability. This setting affects the 6148 deployment of the HW 6040 deployment of the HW BHI control and the SW BHB 6149 clearing sequence. 6041 clearing sequence. 6150 6042 6151 on - (default) En !! 6043 on - (default) Enable the HW or SW mitigation 6152 needed. Thi !! 6044 as needed. 6153 both syscall !! 6045 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 6046 6161 spectre_v2= [X86,EARLY] Control m !! 6047 spectre_v2= [X86] Control mitigation of Spectre variant 2 6162 (indirect branch spec 6048 (indirect branch speculation) vulnerability. 6163 The default operation 6049 The default operation protects the kernel from 6164 user space attacks. 6050 user space attacks. 6165 6051 6166 on - unconditionall 6052 on - unconditionally enable, implies 6167 spectre_v2_use 6053 spectre_v2_user=on 6168 off - unconditionall 6054 off - unconditionally disable, implies 6169 spectre_v2_use 6055 spectre_v2_user=off 6170 auto - kernel detects 6056 auto - kernel detects whether your CPU model is 6171 vulnerable 6057 vulnerable 6172 6058 6173 Selecting 'on' will, 6059 Selecting 'on' will, and 'auto' may, choose a 6174 mitigation method at 6060 mitigation method at run time according to the 6175 CPU, the available mi 6061 CPU, the available microcode, the setting of the 6176 CONFIG_MITIGATION_RET !! 6062 CONFIG_RETPOLINE configuration option, and the 6177 and the compiler with !! 6063 compiler with which the kernel was built. 6178 6064 6179 Selecting 'on' will a 6065 Selecting 'on' will also enable the mitigation 6180 against user space to 6066 against user space to user space task attacks. 6181 6067 6182 Selecting 'off' will 6068 Selecting 'off' will disable both the kernel and 6183 the user space protec 6069 the user space protections. 6184 6070 6185 Specific mitigations 6071 Specific mitigations can also be selected manually: 6186 6072 6187 retpoline - r 6073 retpoline - replace indirect branches 6188 retpoline,generic - R 6074 retpoline,generic - Retpolines 6189 retpoline,lfence - L 6075 retpoline,lfence - LFENCE; indirect branch 6190 retpoline,amd - a 6076 retpoline,amd - alias for retpoline,lfence 6191 eibrs - E 6077 eibrs - Enhanced/Auto IBRS 6192 eibrs,retpoline - E 6078 eibrs,retpoline - Enhanced/Auto IBRS + Retpolines 6193 eibrs,lfence - E 6079 eibrs,lfence - Enhanced/Auto IBRS + LFENCE 6194 ibrs - u 6080 ibrs - use IBRS to protect kernel 6195 6081 6196 Not specifying this o 6082 Not specifying this option is equivalent to 6197 spectre_v2=auto. 6083 spectre_v2=auto. 6198 6084 6199 spectre_v2_user= 6085 spectre_v2_user= 6200 [X86] Control mitigat 6086 [X86] Control mitigation of Spectre variant 2 6201 (indirect branch spec 6087 (indirect branch speculation) vulnerability between 6202 user space tasks 6088 user space tasks 6203 6089 6204 on - Uncondition 6090 on - Unconditionally enable mitigations. Is 6205 enforced by 6091 enforced by spectre_v2=on 6206 6092 6207 off - Uncondition 6093 off - Unconditionally disable mitigations. Is 6208 enforced by 6094 enforced by spectre_v2=off 6209 6095 6210 prctl - Indirect br 6096 prctl - Indirect branch speculation is enabled, 6211 but mitigat 6097 but mitigation can be enabled via prctl 6212 per thread. 6098 per thread. The mitigation control state 6213 is inherite 6099 is inherited on fork. 6214 6100 6215 prctl,ibpb 6101 prctl,ibpb 6216 - Like "prctl 6102 - Like "prctl" above, but only STIBP is 6217 controlled 6103 controlled per thread. IBPB is issued 6218 always when 6104 always when switching between different user 6219 space proce 6105 space processes. 6220 6106 6221 seccomp 6107 seccomp 6222 - Same as "pr 6108 - Same as "prctl" above, but all seccomp 6223 threads wil 6109 threads will enable the mitigation unless 6224 they explic 6110 they explicitly opt out. 6225 6111 6226 seccomp,ibpb 6112 seccomp,ibpb 6227 - Like "secco 6113 - Like "seccomp" above, but only STIBP is 6228 controlled 6114 controlled per thread. IBPB is issued 6229 always when 6115 always when switching between different 6230 user space 6116 user space processes. 6231 6117 6232 auto - Kernel sele 6118 auto - Kernel selects the mitigation depending on 6233 the availab 6119 the available CPU features and vulnerability. 6234 6120 6235 Default mitigation: " 6121 Default mitigation: "prctl" 6236 6122 6237 Not specifying this o 6123 Not specifying this option is equivalent to 6238 spectre_v2_user=auto. 6124 spectre_v2_user=auto. 6239 6125 6240 spec_rstack_overflow= 6126 spec_rstack_overflow= 6241 [X86,EARLY] Control R !! 6127 [X86] Control RAS overflow mitigation on AMD Zen CPUs 6242 6128 6243 off - Dis 6129 off - Disable mitigation 6244 microcode - Ena 6130 microcode - Enable microcode mitigation only 6245 safe-ret - Ena 6131 safe-ret - Enable sw-only safe RET mitigation (default) 6246 ibpb - Ena 6132 ibpb - Enable mitigation by issuing IBPB on 6247 ker 6133 kernel entry 6248 ibpb-vmexit - Iss 6134 ibpb-vmexit - Issue IBPB only on VMEXIT 6249 (cl 6135 (cloud-specific mitigation) 6250 6136 6251 spec_store_bypass_disable= 6137 spec_store_bypass_disable= 6252 [HW,EARLY] Control Sp !! 6138 [HW] Control Speculative Store Bypass (SSB) Disable mitigation 6253 (Speculative Store By 6139 (Speculative Store Bypass vulnerability) 6254 6140 6255 Certain CPUs are vuln 6141 Certain CPUs are vulnerable to an exploit against a 6256 a common industry wid 6142 a common industry wide performance optimization known 6257 as "Speculative Store 6143 as "Speculative Store Bypass" in which recent stores 6258 to the same memory lo 6144 to the same memory location may not be observed by 6259 later loads during sp 6145 later loads during speculative execution. The idea 6260 is that such stores a 6146 is that such stores are unlikely and that they can 6261 be detected prior to 6147 be detected prior to instruction retirement at the 6262 end of a particular s 6148 end of a particular speculation execution window. 6263 6149 6264 In vulnerable process 6150 In vulnerable processors, the speculatively forwarded 6265 store can be used in 6151 store can be used in a cache side channel attack, for 6266 example to read memor 6152 example to read memory to which the attacker does not 6267 directly have access 6153 directly have access (e.g. inside sandboxed code). 6268 6154 6269 This parameter contro 6155 This parameter controls whether the Speculative Store 6270 Bypass optimization i 6156 Bypass optimization is used. 6271 6157 6272 On x86 the options ar 6158 On x86 the options are: 6273 6159 6274 on - Uncondition 6160 on - Unconditionally disable Speculative Store Bypass 6275 off - Uncondition 6161 off - Unconditionally enable Speculative Store Bypass 6276 auto - Kernel dete 6162 auto - Kernel detects whether the CPU model contains an 6277 implementat 6163 implementation of Speculative Store Bypass and 6278 picks the m 6164 picks the most appropriate mitigation. If the 6279 CPU is not 6165 CPU is not vulnerable, "off" is selected. If the 6280 CPU is vuln 6166 CPU is vulnerable the default mitigation is 6281 architectur 6167 architecture and Kconfig dependent. See below. 6282 prctl - Control Spe 6168 prctl - Control Speculative Store Bypass per thread 6283 via prctl. 6169 via prctl. Speculative Store Bypass is enabled 6284 for a proce 6170 for a process by default. The state of the control 6285 is inherite 6171 is inherited on fork. 6286 seccomp - Same as "pr 6172 seccomp - Same as "prctl" above, but all seccomp threads 6287 will disabl 6173 will disable SSB unless they explicitly opt out. 6288 6174 6289 Default mitigations: 6175 Default mitigations: 6290 X86: "prctl" 6176 X86: "prctl" 6291 6177 6292 On powerpc the option 6178 On powerpc the options are: 6293 6179 6294 on,auto - On Power8 a 6180 on,auto - On Power8 and Power9 insert a store-forwarding 6295 barrier on 6181 barrier on kernel entry and exit. On Power7 6296 perform a s 6182 perform a software flush on kernel entry and 6297 exit. 6183 exit. 6298 off - No action. 6184 off - No action. 6299 6185 6300 Not specifying this o 6186 Not specifying this option is equivalent to 6301 spec_store_bypass_dis 6187 spec_store_bypass_disable=auto. 6302 6188 >> 6189 spia_io_base= [HW,MTD] >> 6190 spia_fio_base= >> 6191 spia_pedr= >> 6192 spia_peddr= >> 6193 6303 split_lock_detect= 6194 split_lock_detect= 6304 [X86] Enable split lo 6195 [X86] Enable split lock detection or bus lock detection 6305 6196 6306 When enabled (and if 6197 When enabled (and if hardware support is present), atomic 6307 instructions that acc 6198 instructions that access data across cache line 6308 boundaries will resul 6199 boundaries will result in an alignment check exception 6309 for split lock detect 6200 for split lock detection or a debug exception for 6310 bus lock detection. 6201 bus lock detection. 6311 6202 6312 off - not enabled 6203 off - not enabled 6313 6204 6314 warn - the kernel 6205 warn - the kernel will emit rate-limited warnings 6315 about appli 6206 about applications triggering the #AC 6316 exception o 6207 exception or the #DB exception. This mode is 6317 the default 6208 the default on CPUs that support split lock 6318 detection o 6209 detection or bus lock detection. Default 6319 behavior is 6210 behavior is by #AC if both features are 6320 enabled in 6211 enabled in hardware. 6321 6212 6322 fatal - the kernel 6213 fatal - the kernel will send SIGBUS to applications 6323 that trigge 6214 that trigger the #AC exception or the #DB 6324 exception. 6215 exception. Default behavior is by #AC if 6325 both featur 6216 both features are enabled in hardware. 6326 6217 6327 ratelimit:N - 6218 ratelimit:N - 6328 Set system 6219 Set system wide rate limit to N bus locks 6329 per second 6220 per second for bus lock detection. 6330 0 < N <= 10 6221 0 < N <= 1000. 6331 6222 6332 N/A for spl 6223 N/A for split lock detection. 6333 6224 6334 6225 6335 If an #AC exception i 6226 If an #AC exception is hit in the kernel or in 6336 firmware (i.e. not wh 6227 firmware (i.e. not while executing in user mode) 6337 the kernel will oops 6228 the kernel will oops in either "warn" or "fatal" 6338 mode. 6229 mode. 6339 6230 6340 #DB exception for bus 6231 #DB exception for bus lock is triggered only when 6341 CPL > 0. 6232 CPL > 0. 6342 6233 6343 srbds= [X86,INTEL,EARLY] !! 6234 srbds= [X86,INTEL] 6344 Control the Special R 6235 Control the Special Register Buffer Data Sampling 6345 (SRBDS) mitigation. 6236 (SRBDS) mitigation. 6346 6237 6347 Certain CPUs are vuln 6238 Certain CPUs are vulnerable to an MDS-like 6348 exploit which can lea 6239 exploit which can leak bits from the random 6349 number generator. 6240 number generator. 6350 6241 6351 By default, this issu 6242 By default, this issue is mitigated by 6352 microcode. However, 6243 microcode. However, the microcode fix can cause 6353 the RDRAND and RDSEED 6244 the RDRAND and RDSEED instructions to become 6354 much slower. Among o 6245 much slower. Among other effects, this will 6355 result in reduced thr 6246 result in reduced throughput from /dev/urandom. 6356 6247 6357 The microcode mitigat 6248 The microcode mitigation can be disabled with 6358 the following option: 6249 the following option: 6359 6250 6360 off: Disable mitig 6251 off: Disable mitigation and remove 6361 performance i 6252 performance impact to RDRAND and RDSEED 6362 6253 6363 srcutree.big_cpu_lim [KNL] 6254 srcutree.big_cpu_lim [KNL] 6364 Specifies the number 6255 Specifies the number of CPUs constituting a 6365 large system, such th 6256 large system, such that srcu_struct structures 6366 should immediately al 6257 should immediately allocate an srcu_node array. 6367 This kernel-boot para 6258 This kernel-boot parameter defaults to 128, 6368 but takes effect only 6259 but takes effect only when the low-order four 6369 bits of srcutree.conv 6260 bits of srcutree.convert_to_big is equal to 3 6370 (decide at boot). 6261 (decide at boot). 6371 6262 6372 srcutree.convert_to_big [KNL] 6263 srcutree.convert_to_big [KNL] 6373 Specifies under what 6264 Specifies under what conditions an SRCU tree 6374 srcu_struct structure 6265 srcu_struct structure will be converted to big 6375 form, that is, with a 6266 form, that is, with an rcu_node tree: 6376 6267 6377 0: Never. 6268 0: Never. 6378 1: At ini 6269 1: At init_srcu_struct() time. 6379 2: When r 6270 2: When rcutorture decides to. 6380 3: Decide 6271 3: Decide at boot time (default). 6381 0x1X: Above 6272 0x1X: Above plus if high contention. 6382 6273 6383 Either way, the srcu_ 6274 Either way, the srcu_node tree will be sized based 6384 on the actual runtime 6275 on the actual runtime number of CPUs (nr_cpu_ids) 6385 instead of the compil 6276 instead of the compile-time CONFIG_NR_CPUS. 6386 6277 6387 srcutree.counter_wrap_check [KNL] 6278 srcutree.counter_wrap_check [KNL] 6388 Specifies how frequen 6279 Specifies how frequently to check for 6389 grace-period sequence 6280 grace-period sequence counter wrap for the 6390 srcu_data structure's 6281 srcu_data structure's ->srcu_gp_seq_needed field. 6391 The greater the numbe 6282 The greater the number of bits set in this kernel 6392 parameter, the less f 6283 parameter, the less frequently counter wrap will 6393 be checked for. Note 6284 be checked for. Note that the bottom two bits 6394 are ignored. 6285 are ignored. 6395 6286 6396 srcutree.exp_holdoff [KNL] 6287 srcutree.exp_holdoff [KNL] 6397 Specifies how many na 6288 Specifies how many nanoseconds must elapse 6398 since the end of the 6289 since the end of the last SRCU grace period for 6399 a given srcu_struct u 6290 a given srcu_struct until the next normal SRCU 6400 grace period will be 6291 grace period will be considered for automatic 6401 expediting. Set to z 6292 expediting. Set to zero to disable automatic 6402 expediting. 6293 expediting. 6403 6294 6404 srcutree.srcu_max_nodelay [KNL] 6295 srcutree.srcu_max_nodelay [KNL] 6405 Specifies the number 6296 Specifies the number of no-delay instances 6406 per jiffy for which t 6297 per jiffy for which the SRCU grace period 6407 worker thread will be 6298 worker thread will be rescheduled with zero 6408 delay. Beyond this li 6299 delay. Beyond this limit, worker thread will 6409 be rescheduled with a 6300 be rescheduled with a sleep delay of one jiffy. 6410 6301 6411 srcutree.srcu_max_nodelay_phase [KNL] 6302 srcutree.srcu_max_nodelay_phase [KNL] 6412 Specifies the per-gra 6303 Specifies the per-grace-period phase, number of 6413 non-sleeping polls of 6304 non-sleeping polls of readers. Beyond this limit, 6414 grace period worker t 6305 grace period worker thread will be rescheduled 6415 with a sleep delay of 6306 with a sleep delay of one jiffy, between each 6416 rescan of the readers 6307 rescan of the readers, for a grace period phase. 6417 6308 6418 srcutree.srcu_retry_check_delay [KNL] 6309 srcutree.srcu_retry_check_delay [KNL] 6419 Specifies number of m 6310 Specifies number of microseconds of non-sleeping 6420 delay between each no 6311 delay between each non-sleeping poll of readers. 6421 6312 6422 srcutree.small_contention_lim [KNL] 6313 srcutree.small_contention_lim [KNL] 6423 Specifies the number 6314 Specifies the number of update-side contention 6424 events per jiffy will 6315 events per jiffy will be tolerated before 6425 initiating a conversi 6316 initiating a conversion of an srcu_struct 6426 structure to big form 6317 structure to big form. Note that the value of 6427 srcutree.convert_to_b 6318 srcutree.convert_to_big must have the 0x10 bit 6428 set for contention-ba 6319 set for contention-based conversions to occur. 6429 6320 6430 ssbd= [ARM64,HW,EARLY] !! 6321 ssbd= [ARM64,HW] 6431 Speculative Store Byp 6322 Speculative Store Bypass Disable control 6432 6323 6433 On CPUs that are vuln 6324 On CPUs that are vulnerable to the Speculative 6434 Store Bypass vulnerab 6325 Store Bypass vulnerability and offer a 6435 firmware based mitiga 6326 firmware based mitigation, this parameter 6436 indicates how the mit 6327 indicates how the mitigation should be used: 6437 6328 6438 force-on: Unconditio 6329 force-on: Unconditionally enable mitigation for 6439 for both k 6330 for both kernel and userspace 6440 force-off: Unconditio 6331 force-off: Unconditionally disable mitigation for 6441 for both k 6332 for both kernel and userspace 6442 kernel: Always ena 6333 kernel: Always enable mitigation in the 6443 kernel, an 6334 kernel, and offer a prctl interface 6444 to allow u 6335 to allow userspace to register its 6445 interest i 6336 interest in being mitigated too. 6446 6337 6447 stack_guard_gap= [MM] 6338 stack_guard_gap= [MM] 6448 override the default 6339 override the default stack gap protection. The value 6449 is in page units and 6340 is in page units and it defines how many pages prior 6450 to (for stacks growin 6341 to (for stacks growing down) resp. after (for stacks 6451 growing up) the main 6342 growing up) the main stack are reserved for no other 6452 mapping. Default valu 6343 mapping. Default value is 256 pages. 6453 6344 6454 stack_depot_disable= [KNL,EARLY] !! 6345 stack_depot_disable= [KNL] 6455 Setting this to true 6346 Setting this to true through kernel command line will 6456 disable the stack dep 6347 disable the stack depot thereby saving the static memory 6457 consumed by the stack 6348 consumed by the stack hash table. By default this is set 6458 to false. 6349 to false. 6459 6350 6460 stacktrace [FTRACE] 6351 stacktrace [FTRACE] 6461 Enabled the stack tra 6352 Enabled the stack tracer on boot up. 6462 6353 6463 stacktrace_filter=[function-list] 6354 stacktrace_filter=[function-list] 6464 [FTRACE] Limit the fu 6355 [FTRACE] Limit the functions that the stack tracer 6465 will trace at boot up 6356 will trace at boot up. function-list is a comma-separated 6466 list of functions. Th 6357 list of functions. This list can be changed at run 6467 time by the stack_tra 6358 time by the stack_trace_filter file in the debugfs 6468 tracing directory. No 6359 tracing directory. Note, this enables stack tracing 6469 and the stacktrace ab 6360 and the stacktrace above is not needed. 6470 6361 6471 sti= [PARISC,HW] 6362 sti= [PARISC,HW] 6472 Format: <num> 6363 Format: <num> 6473 Set the STI (builtin 6364 Set the STI (builtin display/keyboard on the HP-PARISC 6474 machines) console (gr 6365 machines) console (graphic card) which should be used 6475 as the initial boot-c 6366 as the initial boot-console. 6476 See also comment in d 6367 See also comment in drivers/video/console/sticore.c. 6477 6368 6478 sti_font= [HW] 6369 sti_font= [HW] 6479 See comment in driver 6370 See comment in drivers/video/console/sticore.c. 6480 6371 6481 stifb= [HW] 6372 stifb= [HW] 6482 Format: bpp:<bpp1>[:< 6373 Format: bpp:<bpp1>[:<bpp2>[:<bpp3>...]] 6483 6374 6484 strict_sas_size= 6375 strict_sas_size= 6485 [X86] 6376 [X86] 6486 Format: <bool> 6377 Format: <bool> 6487 Enable or disable str 6378 Enable or disable strict sigaltstack size checks 6488 against the required 6379 against the required signal frame size which 6489 depends on the suppor 6380 depends on the supported FPU features. This can 6490 be used to filter out 6381 be used to filter out binaries which have 6491 not yet been made awa 6382 not yet been made aware of AT_MINSIGSTKSZ. 6492 6383 6493 stress_hpt [PPC,EARLY] !! 6384 stress_hpt [PPC] 6494 Limits the number of 6385 Limits the number of kernel HPT entries in the hash 6495 page table to increas 6386 page table to increase the rate of hash page table 6496 faults on kernel addr 6387 faults on kernel addresses. 6497 6388 6498 stress_slb [PPC,EARLY] !! 6389 stress_slb [PPC] 6499 Limits the number of 6390 Limits the number of kernel SLB entries, and flushes 6500 them frequently to in 6391 them frequently to increase the rate of SLB faults 6501 on kernel addresses. 6392 on kernel addresses. 6502 6393 6503 sunrpc.min_resvport= 6394 sunrpc.min_resvport= 6504 sunrpc.max_resvport= 6395 sunrpc.max_resvport= 6505 [NFS,SUNRPC] 6396 [NFS,SUNRPC] 6506 SunRPC servers often 6397 SunRPC servers often require that client requests 6507 originate from a priv 6398 originate from a privileged port (i.e. a port in the 6508 range 0 < portnr < 10 6399 range 0 < portnr < 1024). 6509 An administrator who 6400 An administrator who wishes to reserve some of these 6510 ports for other uses 6401 ports for other uses may adjust the range that the 6511 kernel's sunrpc clien 6402 kernel's sunrpc client considers to be privileged 6512 using these two param 6403 using these two parameters to set the minimum and 6513 maximum port values. 6404 maximum port values. 6514 6405 6515 sunrpc.svc_rpc_per_connection_limit= 6406 sunrpc.svc_rpc_per_connection_limit= 6516 [NFS,SUNRPC] 6407 [NFS,SUNRPC] 6517 Limit the number of r 6408 Limit the number of requests that the server will 6518 process in parallel f 6409 process in parallel from a single connection. 6519 The default value is 6410 The default value is 0 (no limit). 6520 6411 6521 sunrpc.pool_mode= 6412 sunrpc.pool_mode= 6522 [NFS] 6413 [NFS] 6523 Control how the NFS s 6414 Control how the NFS server code allocates CPUs to 6524 service thread pools. 6415 service thread pools. Depending on how many NICs 6525 you have and where th 6416 you have and where their interrupts are bound, this 6526 option will affect wh 6417 option will affect which CPUs will do NFS serving. 6527 Note: this parameter 6418 Note: this parameter cannot be changed while the 6528 NFS server is running 6419 NFS server is running. 6529 6420 6530 auto the serve 6421 auto the server chooses an appropriate mode 6531 automatic 6422 automatically using heuristics 6532 global a single 6423 global a single global pool contains all CPUs 6533 percpu one pool 6424 percpu one pool for each CPU 6534 pernode one pool 6425 pernode one pool for each NUMA node (equivalent 6535 to global 6426 to global on non-NUMA machines) 6536 6427 6537 sunrpc.tcp_slot_table_entries= 6428 sunrpc.tcp_slot_table_entries= 6538 sunrpc.udp_slot_table_entries= 6429 sunrpc.udp_slot_table_entries= 6539 [NFS,SUNRPC] 6430 [NFS,SUNRPC] 6540 Sets the upper limit 6431 Sets the upper limit on the number of simultaneous 6541 RPC calls that can be 6432 RPC calls that can be sent from the client to a 6542 server. Increasing th 6433 server. Increasing these values may allow you to 6543 improve throughput, b 6434 improve throughput, but will also increase the 6544 amount of memory rese 6435 amount of memory reserved for use by the client. 6545 6436 6546 suspend.pm_test_delay= 6437 suspend.pm_test_delay= 6547 [SUSPEND] 6438 [SUSPEND] 6548 Sets the number of se 6439 Sets the number of seconds to remain in a suspend test 6549 mode before resuming 6440 mode before resuming the system (see 6550 /sys/power/pm_test). 6441 /sys/power/pm_test). Only available when CONFIG_PM_DEBUG 6551 is set. Default value 6442 is set. Default value is 5. 6552 6443 6553 svm= [PPC] 6444 svm= [PPC] 6554 Format: { on | off | 6445 Format: { on | off | y | n | 1 | 0 } 6555 This parameter contro 6446 This parameter controls use of the Protected 6556 Execution Facility on 6447 Execution Facility on pSeries. 6557 6448 6558 swiotlb= [ARM,PPC,MIPS,X86,S39 !! 6449 swiotlb= [ARM,IA-64,PPC,MIPS,X86] 6559 Format: { <int> [,<in 6450 Format: { <int> [,<int>] | force | noforce } 6560 <int> -- Number of I/ 6451 <int> -- Number of I/O TLB slabs 6561 <int> -- Second integ 6452 <int> -- Second integer after comma. Number of swiotlb 6562 areas with t 6453 areas with their own lock. Will be rounded up 6563 to a power o 6454 to a power of 2. 6564 force -- force using 6455 force -- force using of bounce buffers even if they 6565 wouldn't be 6456 wouldn't be automatically used by the kernel 6566 noforce -- Never use 6457 noforce -- Never use bounce buffers (for debugging) 6567 6458 6568 switches= [HW,M68k,EARLY] !! 6459 switches= [HW,M68k] 6569 6460 6570 sysctl.*= [KNL] 6461 sysctl.*= [KNL] 6571 Set a sysctl paramete 6462 Set a sysctl parameter, right before loading the init 6572 process, as if the va 6463 process, as if the value was written to the respective 6573 /proc/sys/... file. B 6464 /proc/sys/... file. Both '.' and '/' are recognized as 6574 separators. Unrecogni 6465 separators. Unrecognized parameters and invalid values 6575 are reported in the k 6466 are reported in the kernel log. Sysctls registered 6576 later by a loaded mod 6467 later by a loaded module cannot be set this way. 6577 Example: sysctl.vm.sw 6468 Example: sysctl.vm.swappiness=40 6578 6469 6579 sysrq_always_enabled 6470 sysrq_always_enabled 6580 [KNL] 6471 [KNL] 6581 Ignore sysrq setting 6472 Ignore sysrq setting - this boot parameter will 6582 neutralize any effect 6473 neutralize any effect of /proc/sys/kernel/sysrq. 6583 Useful for debugging. 6474 Useful for debugging. 6584 6475 6585 tcpmhash_entries= [KNL,NET] 6476 tcpmhash_entries= [KNL,NET] 6586 Set the number of tcp 6477 Set the number of tcp_metrics_hash slots. 6587 Default value is 8192 6478 Default value is 8192 or 16384 depending on total 6588 ram pages. This is us 6479 ram pages. This is used to specify the TCP metrics 6589 cache size. See Docum 6480 cache size. See Documentation/networking/ip-sysctl.rst 6590 "tcp_no_metrics_save" 6481 "tcp_no_metrics_save" section for more details. 6591 6482 6592 tdfx= [HW,DRM] 6483 tdfx= [HW,DRM] 6593 6484 6594 test_suspend= [SUSPEND] 6485 test_suspend= [SUSPEND] 6595 Format: { "mem" | "st 6486 Format: { "mem" | "standby" | "freeze" }[,N] 6596 Specify "mem" (for Su 6487 Specify "mem" (for Suspend-to-RAM) or "standby" (for 6597 standby suspend) or " 6488 standby suspend) or "freeze" (for suspend type freeze) 6598 as the system sleep s 6489 as the system sleep state during system startup with 6599 the optional capabili 6490 the optional capability to repeat N number of times. 6600 The system is woken f 6491 The system is woken from this state using a 6601 wakeup-capable RTC al 6492 wakeup-capable RTC alarm. 6602 6493 6603 thash_entries= [KNL,NET] 6494 thash_entries= [KNL,NET] 6604 Set number of hash bu 6495 Set number of hash buckets for TCP connection 6605 6496 6606 thermal.act= [HW,ACPI] 6497 thermal.act= [HW,ACPI] 6607 -1: disable all activ 6498 -1: disable all active trip points in all thermal zones 6608 <degrees C>: override 6499 <degrees C>: override all lowest active trip points 6609 6500 6610 thermal.crt= [HW,ACPI] 6501 thermal.crt= [HW,ACPI] 6611 -1: disable all criti 6502 -1: disable all critical trip points in all thermal zones 6612 <degrees C>: override 6503 <degrees C>: override all critical trip points 6613 6504 6614 thermal.off= [HW,ACPI] 6505 thermal.off= [HW,ACPI] 6615 1: disable ACPI therm 6506 1: disable ACPI thermal control 6616 6507 6617 thermal.psv= [HW,ACPI] 6508 thermal.psv= [HW,ACPI] 6618 -1: disable all passi 6509 -1: disable all passive trip points 6619 <degrees C>: override 6510 <degrees C>: override all passive trip points to this 6620 value 6511 value 6621 6512 6622 thermal.tzp= [HW,ACPI] 6513 thermal.tzp= [HW,ACPI] 6623 Specify global defaul 6514 Specify global default ACPI thermal zone polling rate 6624 <deci-seconds>: poll 6515 <deci-seconds>: poll all this frequency 6625 0: no polling (defaul 6516 0: no polling (default) 6626 6517 6627 threadirqs [KNL,EARLY] !! 6518 threadirqs [KNL] 6628 Force threading of al 6519 Force threading of all interrupt handlers except those 6629 marked explicitly IRQ 6520 marked explicitly IRQF_NO_THREAD. 6630 6521 6631 topology= [S390,EARLY] !! 6522 topology= [S390] 6632 Format: {off | on} 6523 Format: {off | on} 6633 Specify if the kernel 6524 Specify if the kernel should make use of the cpu 6634 topology information 6525 topology information if the hardware supports this. 6635 The scheduler will ma 6526 The scheduler will make use of this information and 6636 e.g. base its process 6527 e.g. base its process migration decisions on it. 6637 Default is on. 6528 Default is on. 6638 6529 >> 6530 topology_updates= [KNL, PPC, NUMA] >> 6531 Format: {off} >> 6532 Specify if the kernel should ignore (off) >> 6533 topology updates sent by the hypervisor to this >> 6534 LPAR. >> 6535 6639 torture.disable_onoff_at_boot= [KNL] 6536 torture.disable_onoff_at_boot= [KNL] 6640 Prevent the CPU-hotpl 6537 Prevent the CPU-hotplug component of torturing 6641 until after init has 6538 until after init has spawned. 6642 6539 6643 torture.ftrace_dump_at_shutdown= [KNL 6540 torture.ftrace_dump_at_shutdown= [KNL] 6644 Dump the ftrace buffe 6541 Dump the ftrace buffer at torture-test shutdown, 6645 even if there were no 6542 even if there were no errors. This can be a 6646 very costly operation 6543 very costly operation when many torture tests 6647 are running concurren 6544 are running concurrently, especially on systems 6648 with rotating-rust st 6545 with rotating-rust storage. 6649 6546 6650 torture.verbose_sleep_frequency= [KNL 6547 torture.verbose_sleep_frequency= [KNL] 6651 Specifies how many ve 6548 Specifies how many verbose printk()s should be 6652 emitted between each 6549 emitted between each sleep. The default of zero 6653 disables verbose-prin 6550 disables verbose-printk() sleeping. 6654 6551 6655 torture.verbose_sleep_duration= [KNL] 6552 torture.verbose_sleep_duration= [KNL] 6656 Duration of each verb 6553 Duration of each verbose-printk() sleep in jiffies. 6657 6554 >> 6555 tp720= [HW,PS2] >> 6556 6658 tpm_suspend_pcr=[HW,TPM] 6557 tpm_suspend_pcr=[HW,TPM] 6659 Format: integer pcr i 6558 Format: integer pcr id 6660 Specify that at suspe 6559 Specify that at suspend time, the tpm driver 6661 should extend the spe 6560 should extend the specified pcr with zeros, 6662 as a workaround for s 6561 as a workaround for some chips which fail to 6663 flush the last writte 6562 flush the last written pcr on TPM_SaveState. 6664 This will guarantee t 6563 This will guarantee that all the other pcrs 6665 are saved. 6564 are saved. 6666 6565 6667 tpm_tis.interrupts= [HW,TPM] 6566 tpm_tis.interrupts= [HW,TPM] 6668 Enable interrupts for 6567 Enable interrupts for the MMIO based physical layer 6669 for the FIFO interfac 6568 for the FIFO interface. By default it is set to false 6670 (0). For more informa 6569 (0). For more information about TPM hardware interfaces 6671 defined by Trusted Co 6570 defined by Trusted Computing Group (TCG) see 6672 https://trustedcomput 6571 https://trustedcomputinggroup.org/resource/pc-client-platform-tpm-profile-ptp-specification/ 6673 6572 6674 tp_printk [FTRACE] 6573 tp_printk [FTRACE] 6675 Have the tracepoints 6574 Have the tracepoints sent to printk as well as the 6676 tracing ring buffer. 6575 tracing ring buffer. This is useful for early boot up 6677 where the system hang 6576 where the system hangs or reboots and does not give the 6678 option for reading th 6577 option for reading the tracing buffer or performing a 6679 ftrace_dump_on_oops. 6578 ftrace_dump_on_oops. 6680 6579 6681 To turn off having tr 6580 To turn off having tracepoints sent to printk, 6682 echo 0 > /proc/sys/k 6581 echo 0 > /proc/sys/kernel/tracepoint_printk 6683 Note, echoing 1 into 6582 Note, echoing 1 into this file without the 6684 tp_printk kernel cmdl !! 6583 tracepoint_printk kernel cmdline option has no effect. 6685 6584 6686 The tp_printk_stop_on 6585 The tp_printk_stop_on_boot (see below) can also be used 6687 to stop the printing 6586 to stop the printing of events to console at 6688 late_initcall_sync. 6587 late_initcall_sync. 6689 6588 6690 ** CAUTION ** 6589 ** CAUTION ** 6691 6590 6692 Having tracepoints se 6591 Having tracepoints sent to printk() and activating high 6693 frequency tracepoints 6592 frequency tracepoints such as irq or sched, can cause 6694 the system to live lo 6593 the system to live lock. 6695 6594 6696 tp_printk_stop_on_boot [FTRACE] 6595 tp_printk_stop_on_boot [FTRACE] 6697 When tp_printk (above 6596 When tp_printk (above) is set, it can cause a lot of noise 6698 on the console. It ma 6597 on the console. It may be useful to only include the 6699 printing of events du 6598 printing of events during boot up, as user space may 6700 make the system inope 6599 make the system inoperable. 6701 6600 6702 This command line opt 6601 This command line option will stop the printing of events 6703 to console at the lat 6602 to console at the late_initcall_sync() time frame. 6704 6603 6705 trace_buf_size=nn[KMG] 6604 trace_buf_size=nn[KMG] 6706 [FTRACE] will set tra 6605 [FTRACE] will set tracing buffer size on each cpu. 6707 6606 6708 trace_clock= [FTRACE] Set the cloc 6607 trace_clock= [FTRACE] Set the clock used for tracing events 6709 at boot up. 6608 at boot up. 6710 local - Use the per C 6609 local - Use the per CPU time stamp counter 6711 (converted in 6610 (converted into nanoseconds). Fast, but 6712 depending on 6611 depending on the architecture, may not be 6713 in sync betwe 6612 in sync between CPUs. 6714 global - Event time s 6613 global - Event time stamps are synchronize across 6715 CPUs. May be 6614 CPUs. May be slower than the local clock, 6716 but better fo 6615 but better for some race conditions. 6717 counter - Simple coun 6616 counter - Simple counting of events (1, 2, ..) 6718 note, some co 6617 note, some counts may be skipped due to the 6719 infrastructur 6618 infrastructure grabbing the clock more than 6720 once per even 6619 once per event. 6721 uptime - Use jiffies 6620 uptime - Use jiffies as the time stamp. 6722 perf - Use the same c 6621 perf - Use the same clock that perf uses. 6723 mono - Use ktime_get_ 6622 mono - Use ktime_get_mono_fast_ns() for time stamps. 6724 mono_raw - Use ktime_ 6623 mono_raw - Use ktime_get_raw_fast_ns() for time 6725 stamps. 6624 stamps. 6726 boot - Use ktime_get_ 6625 boot - Use ktime_get_boot_fast_ns() for time stamps. 6727 Architectures may add 6626 Architectures may add more clocks. See 6728 Documentation/trace/f 6627 Documentation/trace/ftrace.rst for more details. 6729 6628 6730 trace_event=[event-list] 6629 trace_event=[event-list] 6731 [FTRACE] Set and star 6630 [FTRACE] Set and start specified trace events in order 6732 to facilitate early b 6631 to facilitate early boot debugging. The event-list is a 6733 comma-separated list 6632 comma-separated list of trace events to enable. See 6734 also Documentation/tr 6633 also Documentation/trace/events.rst 6735 6634 6736 trace_instance=[instance-info] 6635 trace_instance=[instance-info] 6737 [FTRACE] Create a rin 6636 [FTRACE] Create a ring buffer instance early in boot up. 6738 This will be listed i 6637 This will be listed in: 6739 6638 6740 /sys/kernel/t 6639 /sys/kernel/tracing/instances 6741 6640 6742 Events can be enabled 6641 Events can be enabled at the time the instance is created 6743 via: 6642 via: 6744 6643 6745 trace_instanc 6644 trace_instance=<name>,<system1>:<event1>,<system2>:<event2> 6746 6645 6747 Note, the "<system*>: 6646 Note, the "<system*>:" portion is optional if the event is 6748 unique. 6647 unique. 6749 6648 6750 trace_instanc 6649 trace_instance=foo,sched:sched_switch,irq_handler_entry,initcall 6751 6650 6752 will enable the "sche 6651 will enable the "sched_switch" event (note, the "sched:" is optional, and 6753 the same thing would 6652 the same thing would happen if it was left off). The irq_handler_entry 6754 event, and all events 6653 event, and all events under the "initcall" system. 6755 6654 6756 trace_options=[option-list] 6655 trace_options=[option-list] 6757 [FTRACE] Enable or di 6656 [FTRACE] Enable or disable tracer options at boot. 6758 The option-list is a 6657 The option-list is a comma delimited list of options 6759 that can be enabled o 6658 that can be enabled or disabled just as if you were 6760 to echo the option na 6659 to echo the option name into 6761 6660 6762 /sys/kernel/traci 6661 /sys/kernel/tracing/trace_options 6763 6662 6764 For example, to enabl 6663 For example, to enable stacktrace option (to dump the 6765 stack trace of each e 6664 stack trace of each event), add to the command line: 6766 6665 6767 trace_options=s 6666 trace_options=stacktrace 6768 6667 6769 See also Documentatio 6668 See also Documentation/trace/ftrace.rst "trace options" 6770 section. 6669 section. 6771 6670 6772 trace_trigger=[trigger-list] 6671 trace_trigger=[trigger-list] 6773 [FTRACE] Add a event 6672 [FTRACE] Add a event trigger on specific events. 6774 Set a trigger on top 6673 Set a trigger on top of a specific event, with an optional 6775 filter. 6674 filter. 6776 6675 6777 The format is is "tra 6676 The format is is "trace_trigger=<event>.<trigger>[ if <filter>],..." 6778 Where more than one t 6677 Where more than one trigger may be specified that are comma deliminated. 6779 6678 6780 For example: 6679 For example: 6781 6680 6782 trace_trigger="sche 6681 trace_trigger="sched_switch.stacktrace if prev_state == 2" 6783 6682 6784 The above will enable 6683 The above will enable the "stacktrace" trigger on the "sched_switch" 6785 event but only trigge 6684 event but only trigger it if the "prev_state" of the "sched_switch" 6786 event is "2" (TASK_UN 6685 event is "2" (TASK_UNINTERUPTIBLE). 6787 6686 6788 See also "Event trigg 6687 See also "Event triggers" in Documentation/trace/events.rst 6789 6688 6790 6689 6791 traceoff_on_warning 6690 traceoff_on_warning 6792 [FTRACE] enable this 6691 [FTRACE] enable this option to disable tracing when a 6793 warning is hit. This 6692 warning is hit. This turns off "tracing_on". Tracing can 6794 be enabled again by e 6693 be enabled again by echoing '1' into the "tracing_on" 6795 file located in /sys/ 6694 file located in /sys/kernel/tracing/ 6796 6695 6797 This option is useful 6696 This option is useful, as it disables the trace before 6798 the WARNING dump is c 6697 the WARNING dump is called, which prevents the trace to 6799 be filled with conten 6698 be filled with content caused by the warning output. 6800 6699 6801 This option can also 6700 This option can also be set at run time via the sysctl 6802 option: kernel/trace 6701 option: kernel/traceoff_on_warning 6803 6702 6804 transparent_hugepage= 6703 transparent_hugepage= 6805 [KNL] 6704 [KNL] 6806 Format: [always|madvi 6705 Format: [always|madvise|never] 6807 Can be used to contro 6706 Can be used to control the default behavior of the system 6808 with respect to trans 6707 with respect to transparent hugepages. 6809 See Documentation/adm 6708 See Documentation/admin-guide/mm/transhuge.rst 6810 for more details. 6709 for more details. 6811 6710 6812 trusted.source= [KEYS] 6711 trusted.source= [KEYS] 6813 Format: <string> 6712 Format: <string> 6814 This parameter identi 6713 This parameter identifies the trust source as a backend 6815 for trusted keys impl 6714 for trusted keys implementation. Supported trust 6816 sources: 6715 sources: 6817 - "tpm" 6716 - "tpm" 6818 - "tee" 6717 - "tee" 6819 - "caam" 6718 - "caam" 6820 - "dcp" << 6821 If not specified then 6719 If not specified then it defaults to iterating through 6822 the trust source list 6720 the trust source list starting with TPM and assigns the 6823 first trust source as 6721 first trust source as a backend which is initialized 6824 successfully during i 6722 successfully during iteration. 6825 6723 6826 trusted.rng= [KEYS] 6724 trusted.rng= [KEYS] 6827 Format: <string> 6725 Format: <string> 6828 The RNG used to gener 6726 The RNG used to generate key material for trusted keys. 6829 Can be one of: 6727 Can be one of: 6830 - "kernel" 6728 - "kernel" 6831 - the same value as t 6729 - the same value as trusted.source: "tpm" or "tee" 6832 - "default" 6730 - "default" 6833 If not specified, "de 6731 If not specified, "default" is used. In this case, 6834 the RNG's choice is l 6732 the RNG's choice is left to each individual trust source. 6835 6733 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 6734 tsc= Disable clocksource stability checks for TSC. 6849 Format: <string> 6735 Format: <string> 6850 [x86] reliable: mark 6736 [x86] reliable: mark tsc clocksource as reliable, this 6851 disables clocksource 6737 disables clocksource verification at runtime, as well 6852 as the stability chec 6738 as the stability checks done at bootup. Used to enable 6853 high-resolution timer 6739 high-resolution timer mode on older hardware, and in 6854 virtualized environme 6740 virtualized environment. 6855 [x86] noirqtime: Do n 6741 [x86] noirqtime: Do not use TSC to do irq accounting. 6856 Used to run time disa 6742 Used to run time disable IRQ_TIME_ACCOUNTING on any 6857 platforms where RDTSC 6743 platforms where RDTSC is slow and this accounting 6858 can add overhead. 6744 can add overhead. 6859 [x86] unstable: mark 6745 [x86] unstable: mark the TSC clocksource as unstable, this 6860 marks the TSC uncondi 6746 marks the TSC unconditionally unstable at bootup and 6861 avoids any further wo 6747 avoids any further wobbles once the TSC watchdog notices. 6862 [x86] nowatchdog: dis 6748 [x86] nowatchdog: disable clocksource watchdog. Used 6863 in situations with st 6749 in situations with strict latency requirements (where 6864 interruptions from cl 6750 interruptions from clocksource watchdog are not 6865 acceptable). 6751 acceptable). 6866 [x86] recalibrate: fo 6752 [x86] recalibrate: force recalibration against a HW timer 6867 (HPET or PM timer) on 6753 (HPET or PM timer) on systems whose TSC frequency was 6868 obtained from HW or F 6754 obtained from HW or FW using either an MSR or CPUID(0x15). 6869 Warn if the differenc 6755 Warn if the difference is more than 500 ppm. 6870 [x86] watchdog: Use T 6756 [x86] watchdog: Use TSC as the watchdog clocksource with 6871 which to check other 6757 which to check other HW timers (HPET or PM timer), but 6872 only on systems where 6758 only on systems where TSC has been deemed trustworthy. 6873 This will be suppress 6759 This will be suppressed by an earlier tsc=nowatchdog and 6874 can be overridden by 6760 can be overridden by a later tsc=nowatchdog. A console 6875 message will flag any 6761 message will flag any such suppression or overriding. 6876 6762 6877 tsc_early_khz= [X86,EARLY] Skip earl !! 6763 tsc_early_khz= [X86] Skip early TSC calibration and use the given 6878 value instead. Useful 6764 value instead. Useful when the early TSC frequency discovery 6879 procedure is not reli 6765 procedure is not reliable, such as on overclocked systems 6880 with CPUID.16h suppor 6766 with CPUID.16h support and partial CPUID.15h support. 6881 Format: <unsigned int 6767 Format: <unsigned int> 6882 6768 6883 tsx= [X86] Control Transac 6769 tsx= [X86] Control Transactional Synchronization 6884 Extensions (TSX) feat 6770 Extensions (TSX) feature in Intel processors that 6885 support TSX control. 6771 support TSX control. 6886 6772 6887 This parameter contro 6773 This parameter controls the TSX feature. The options are: 6888 6774 6889 on - Enable TSX 6775 on - Enable TSX on the system. Although there are 6890 mitigations f 6776 mitigations for all known security vulnerabilities, 6891 TSX has been 6777 TSX has been known to be an accelerator for 6892 several previ 6778 several previous speculation-related CVEs, and 6893 so there may 6779 so there may be unknown security risks associated 6894 with leaving 6780 with leaving it enabled. 6895 6781 6896 off - Disable TSX 6782 off - Disable TSX on the system. (Note that this 6897 option takes 6783 option takes effect only on newer CPUs which are 6898 not vulnerabl 6784 not vulnerable to MDS, i.e., have 6899 MSR_IA32_ARCH 6785 MSR_IA32_ARCH_CAPABILITIES.MDS_NO=1 and which get 6900 the new IA32_ 6786 the new IA32_TSX_CTRL MSR through a microcode 6901 update. This 6787 update. This new MSR allows for the reliable 6902 deactivation 6788 deactivation of the TSX functionality.) 6903 6789 6904 auto - Disable TSX 6790 auto - Disable TSX if X86_BUG_TAA is present, 6905 otherwise e 6791 otherwise enable TSX on the system. 6906 6792 6907 Not specifying this o 6793 Not specifying this option is equivalent to tsx=off. 6908 6794 6909 See Documentation/adm 6795 See Documentation/admin-guide/hw-vuln/tsx_async_abort.rst 6910 for more details. 6796 for more details. 6911 6797 6912 tsx_async_abort= [X86,INTEL,EARLY] Co !! 6798 tsx_async_abort= [X86,INTEL] Control mitigation for the TSX Async 6913 Abort (TAA) vulnerabi 6799 Abort (TAA) vulnerability. 6914 6800 6915 Similar to Micro-arch 6801 Similar to Micro-architectural Data Sampling (MDS) 6916 certain CPUs that sup 6802 certain CPUs that support Transactional 6917 Synchronization Exten 6803 Synchronization Extensions (TSX) are vulnerable to an 6918 exploit against CPU i 6804 exploit against CPU internal buffers which can forward 6919 information to a disc 6805 information to a disclosure gadget under certain 6920 conditions. 6806 conditions. 6921 6807 6922 In vulnerable process 6808 In vulnerable processors, the speculatively forwarded 6923 data can be used in a 6809 data can be used in a cache side channel attack, to 6924 access data to which 6810 access data to which the attacker does not have direct 6925 access. 6811 access. 6926 6812 6927 This parameter contro 6813 This parameter controls the TAA mitigation. The 6928 options are: 6814 options are: 6929 6815 6930 full - Enable T 6816 full - Enable TAA mitigation on vulnerable CPUs 6931 if TSX i 6817 if TSX is enabled. 6932 6818 6933 full,nosmt - Enable T 6819 full,nosmt - Enable TAA mitigation and disable SMT on 6934 vulnerab 6820 vulnerable CPUs. If TSX is disabled, SMT 6935 is not d 6821 is not disabled because CPU is not 6936 vulnerab 6822 vulnerable to cross-thread TAA attacks. 6937 off - Uncondit 6823 off - Unconditionally disable TAA mitigation 6938 6824 6939 On MDS-affected machi 6825 On MDS-affected machines, tsx_async_abort=off can be 6940 prevented by an activ 6826 prevented by an active MDS mitigation as both vulnerabilities 6941 are mitigated with th 6827 are mitigated with the same mechanism so in order to disable 6942 this mitigation, you 6828 this mitigation, you need to specify mds=off too. 6943 6829 6944 Not specifying this o 6830 Not specifying this option is equivalent to 6945 tsx_async_abort=full. 6831 tsx_async_abort=full. On CPUs which are MDS affected 6946 and deploy MDS mitiga 6832 and deploy MDS mitigation, TAA mitigation is not 6947 required and doesn't 6833 required and doesn't provide any additional 6948 mitigation. 6834 mitigation. 6949 6835 6950 For details see: 6836 For details see: 6951 Documentation/admin-g 6837 Documentation/admin-guide/hw-vuln/tsx_async_abort.rst 6952 6838 6953 turbografx.map[2|3]= [HW,JOY] 6839 turbografx.map[2|3]= [HW,JOY] 6954 TurboGraFX parallel p 6840 TurboGraFX parallel port interface 6955 Format: 6841 Format: 6956 <port#>,<js1>,<js2>,< 6842 <port#>,<js1>,<js2>,<js3>,<js4>,<js5>,<js6>,<js7> 6957 See also Documentatio 6843 See also Documentation/input/devices/joystick-parport.rst 6958 6844 6959 udbg-immortal [PPC] When debugging 6845 udbg-immortal [PPC] When debugging early kernel crashes that 6960 happen after console_ 6846 happen after console_init() and before a proper 6961 console driver takes 6847 console driver takes over, this boot options might 6962 help "seeing" what's 6848 help "seeing" what's going on. 6963 6849 6964 uhash_entries= [KNL,NET] 6850 uhash_entries= [KNL,NET] 6965 Set number of hash bu 6851 Set number of hash buckets for UDP/UDP-Lite connections 6966 6852 6967 uhci-hcd.ignore_oc= 6853 uhci-hcd.ignore_oc= 6968 [USB] Ignore overcurr 6854 [USB] Ignore overcurrent events (default N). 6969 Some badly-designed m 6855 Some badly-designed motherboards generate lots of 6970 bogus events, for por 6856 bogus events, for ports that aren't wired to 6971 anything. Set this p 6857 anything. Set this parameter to avoid log spamming. 6972 Note that genuine ove 6858 Note that genuine overcurrent events won't be 6973 reported either. 6859 reported either. 6974 6860 6975 unknown_nmi_panic 6861 unknown_nmi_panic 6976 [X86] Cause panic on 6862 [X86] Cause panic on unknown NMI. 6977 6863 6978 unwind_debug [X86-64,EARLY] !! 6864 unwind_debug [X86-64] 6979 Enable unwinder debug 6865 Enable unwinder debug output. This can be 6980 useful for debugging 6866 useful for debugging certain unwinder error 6981 conditions, including 6867 conditions, including corrupt stacks and 6982 bad/missing unwinder 6868 bad/missing unwinder metadata. 6983 6869 6984 usbcore.authorized_default= 6870 usbcore.authorized_default= 6985 [USB] Default USB dev 6871 [USB] Default USB device authorization: 6986 (default -1 = authori 6872 (default -1 = authorized (same as 1), 6987 0 = not authorized, 1 6873 0 = not authorized, 1 = authorized, 2 = authorized 6988 if device connected t 6874 if device connected to internal port) 6989 6875 6990 usbcore.autosuspend= 6876 usbcore.autosuspend= 6991 [USB] The autosuspend 6877 [USB] The autosuspend time delay (in seconds) used 6992 for newly-detected US 6878 for newly-detected USB devices (default 2). This 6993 is the time required 6879 is the time required before an idle device will be 6994 autosuspended. Devic 6880 autosuspended. Devices for which the delay is set 6995 to a negative value w 6881 to a negative value won't be autosuspended at all. 6996 6882 6997 usbcore.usbfs_snoop= 6883 usbcore.usbfs_snoop= 6998 [USB] Set to log all 6884 [USB] Set to log all usbfs traffic (default 0 = off). 6999 6885 7000 usbcore.usbfs_snoop_max= 6886 usbcore.usbfs_snoop_max= 7001 [USB] Maximum number 6887 [USB] Maximum number of bytes to snoop in each URB 7002 (default = 65536). 6888 (default = 65536). 7003 6889 7004 usbcore.blinkenlights= 6890 usbcore.blinkenlights= 7005 [USB] Set to cycle le 6891 [USB] Set to cycle leds on hubs (default 0 = off). 7006 6892 7007 usbcore.old_scheme_first= 6893 usbcore.old_scheme_first= 7008 [USB] Start with the 6894 [USB] Start with the old device initialization 7009 scheme (default 0 = o 6895 scheme (default 0 = off). 7010 6896 7011 usbcore.usbfs_memory_mb= 6897 usbcore.usbfs_memory_mb= 7012 [USB] Memory limit (i 6898 [USB] Memory limit (in MB) for buffers allocated by 7013 usbfs (default = 16, 6899 usbfs (default = 16, 0 = max = 2047). 7014 6900 7015 usbcore.use_both_schemes= 6901 usbcore.use_both_schemes= 7016 [USB] Try the other d 6902 [USB] Try the other device initialization scheme 7017 if the first one fail 6903 if the first one fails (default 1 = enabled). 7018 6904 7019 usbcore.initial_descriptor_timeout= 6905 usbcore.initial_descriptor_timeout= 7020 [USB] Specifies timeo 6906 [USB] Specifies timeout for the initial 64-byte 7021 USB_REQ_GET_DESCRIPTO 6907 USB_REQ_GET_DESCRIPTOR request in milliseconds 7022 (default 5000 = 5.0 s 6908 (default 5000 = 5.0 seconds). 7023 6909 7024 usbcore.nousb [USB] Disable the USB 6910 usbcore.nousb [USB] Disable the USB subsystem 7025 6911 7026 usbcore.quirks= 6912 usbcore.quirks= 7027 [USB] A list of quirk 6913 [USB] A list of quirk entries to augment the built-in 7028 usb core quirk list. 6914 usb core quirk list. List entries are separated by 7029 commas. Each entry ha 6915 commas. Each entry has the form 7030 VendorID:ProductID:Fl 6916 VendorID:ProductID:Flags. The IDs are 4-digit hex 7031 numbers and Flags is 6917 numbers and Flags is a set of letters. Each letter 7032 will change the built 6918 will change the built-in quirk; setting it if it is 7033 clear and clearing it 6919 clear and clearing it if it is set. The letters have 7034 the following meaning 6920 the following meanings: 7035 a = USB_QUIRK 6921 a = USB_QUIRK_STRING_FETCH_255 (string 7036 descr 6922 descriptors must not be fetched using 7037 a 255 6923 a 255-byte read); 7038 b = USB_QUIRK 6924 b = USB_QUIRK_RESET_RESUME (device can't resume 7039 corre 6925 correctly so reset it instead); 7040 c = USB_QUIRK 6926 c = USB_QUIRK_NO_SET_INTF (device can't handle 7041 Set-I 6927 Set-Interface requests); 7042 d = USB_QUIRK 6928 d = USB_QUIRK_CONFIG_INTF_STRINGS (device can't 7043 handl 6929 handle its Configuration or Interface 7044 strin 6930 strings); 7045 e = USB_QUIRK 6931 e = USB_QUIRK_RESET (device can't be reset 7046 (e.g 6932 (e.g morph devices), don't use reset); 7047 f = USB_QUIRK 6933 f = USB_QUIRK_HONOR_BNUMINTERFACES (device has 7048 more 6934 more interface descriptions than the 7049 bNumI 6935 bNumInterfaces count, and can't handle 7050 talki 6936 talking to these interfaces); 7051 g = USB_QUIRK 6937 g = USB_QUIRK_DELAY_INIT (device needs a pause 7052 durin 6938 during initialization, after we read 7053 the d 6939 the device descriptor); 7054 h = USB_QUIRK 6940 h = USB_QUIRK_LINEAR_UFRAME_INTR_BINTERVAL (For 7055 high 6941 high speed and super speed interrupt 7056 endpo 6942 endpoints, the USB 2.0 and USB 3.0 spec 7057 requi 6943 require the interval in microframes (1 7058 micro 6944 microframe = 125 microseconds) to be 7059 calcu 6945 calculated as interval = 2 ^ 7060 (bInt 6946 (bInterval-1). 7061 Devic 6947 Devices with this quirk report their 7062 bInte 6948 bInterval as the result of this 7063 calcu 6949 calculation instead of the exponent 7064 varia 6950 variable used in the calculation); 7065 i = USB_QUIRK 6951 i = USB_QUIRK_DEVICE_QUALIFIER (device can't 7066 handl 6952 handle device_qualifier descriptor 7067 reque 6953 requests); 7068 j = USB_QUIRK 6954 j = USB_QUIRK_IGNORE_REMOTE_WAKEUP (device 7069 gener 6955 generates spurious wakeup, ignore 7070 remot 6956 remote wakeup capability); 7071 k = USB_QUIRK 6957 k = USB_QUIRK_NO_LPM (device can't handle Link 7072 Power 6958 Power Management); 7073 l = USB_QUIRK 6959 l = USB_QUIRK_LINEAR_FRAME_INTR_BINTERVAL 7074 (Devi 6960 (Device reports its bInterval as linear 7075 frame 6961 frames instead of the USB 2.0 7076 calcu 6962 calculation); 7077 m = USB_QUIRK 6963 m = USB_QUIRK_DISCONNECT_SUSPEND (Device needs 7078 to be 6964 to be disconnected before suspend to 7079 preve 6965 prevent spurious wakeup); 7080 n = USB_QUIRK 6966 n = USB_QUIRK_DELAY_CTRL_MSG (Device needs a 7081 pause 6967 pause after every control message); 7082 o = USB_QUIRK 6968 o = USB_QUIRK_HUB_SLOW_RESET (Hub needs extra 7083 delay 6969 delay after resetting its port); 7084 p = USB_QUIRK 6970 p = USB_QUIRK_SHORT_SET_ADDRESS_REQ_TIMEOUT 7085 (Redu 6971 (Reduce timeout of the SET_ADDRESS 7086 reque 6972 request from 5000 ms to 500 ms); 7087 Example: quirks=0781: 6973 Example: quirks=0781:5580:bk,0a5c:5834:gij 7088 6974 7089 usbhid.mousepoll= 6975 usbhid.mousepoll= 7090 [USBHID] The interval 6976 [USBHID] The interval which mice are to be polled at. 7091 6977 7092 usbhid.jspoll= 6978 usbhid.jspoll= 7093 [USBHID] The interval 6979 [USBHID] The interval which joysticks are to be polled at. 7094 6980 7095 usbhid.kbpoll= 6981 usbhid.kbpoll= 7096 [USBHID] The interval 6982 [USBHID] The interval which keyboards are to be polled at. 7097 6983 7098 usb-storage.delay_use= 6984 usb-storage.delay_use= 7099 [UMS] The delay in se 6985 [UMS] The delay in seconds before a new device is 7100 scanned for Logical U 6986 scanned for Logical Units (default 1). 7101 Optionally the delay << 7102 suffix with "ms". << 7103 Example: delay_use=25 << 7104 6987 7105 usb-storage.quirks= 6988 usb-storage.quirks= 7106 [UMS] A list of quirk 6989 [UMS] A list of quirks entries to supplement or 7107 override the built-in 6990 override the built-in unusual_devs list. List 7108 entries are separated 6991 entries are separated by commas. Each entry has 7109 the form VID:PID:Flag 6992 the form VID:PID:Flags where VID and PID are Vendor 7110 and Product ID values 6993 and Product ID values (4-digit hex numbers) and 7111 Flags is a set of cha 6994 Flags is a set of characters, each corresponding 7112 to a common usb-stora 6995 to a common usb-storage quirk flag as follows: 7113 a = SANE_SENS 6996 a = SANE_SENSE (collect more than 18 bytes 7114 of se 6997 of sense data, not on uas); 7115 b = BAD_SENSE 6998 b = BAD_SENSE (don't collect more than 18 7116 bytes 6999 bytes of sense data, not on uas); 7117 c = FIX_CAPAC 7000 c = FIX_CAPACITY (decrease the reported 7118 devic 7001 device capacity by one sector); 7119 d = NO_READ_D 7002 d = NO_READ_DISC_INFO (don't use 7120 READ_ 7003 READ_DISC_INFO command, not on uas); 7121 e = NO_READ_C 7004 e = NO_READ_CAPACITY_16 (don't use 7122 READ_ 7005 READ_CAPACITY_16 command); 7123 f = NO_REPORT 7006 f = NO_REPORT_OPCODES (don't use report opcodes 7124 comma 7007 command, uas only); 7125 g = MAX_SECTO 7008 g = MAX_SECTORS_240 (don't transfer more than 7126 240 s 7009 240 sectors at a time, uas only); 7127 h = CAPACITY_ 7010 h = CAPACITY_HEURISTICS (decrease the 7128 repor 7011 reported device capacity by one 7129 secto 7012 sector if the number is odd); 7130 i = IGNORE_DE 7013 i = IGNORE_DEVICE (don't bind to this 7131 devic 7014 device); 7132 j = NO_REPORT 7015 j = NO_REPORT_LUNS (don't use report luns 7133 comma 7016 command, uas only); 7134 k = NO_SAME ( 7017 k = NO_SAME (do not use WRITE_SAME, uas only) 7135 l = NOT_LOCKA 7018 l = NOT_LOCKABLE (don't try to lock and 7136 unloc 7019 unlock ejectable media, not on uas); 7137 m = MAX_SECTO 7020 m = MAX_SECTORS_64 (don't transfer more 7138 than 7021 than 64 sectors = 32 KB at a time, 7139 not o 7022 not on uas); 7140 n = INITIAL_R 7023 n = INITIAL_READ10 (force a retry of the 7141 initi 7024 initial READ(10) command, not on uas); 7142 o = CAPACITY_ 7025 o = CAPACITY_OK (accept the capacity 7143 repor 7026 reported by the device, not on uas); 7144 p = WRITE_CAC 7027 p = WRITE_CACHE (the device cache is ON 7145 by de 7028 by default, not on uas); 7146 r = IGNORE_RE 7029 r = IGNORE_RESIDUE (the device reports 7147 bogus 7030 bogus residue values, not on uas); 7148 s = SINGLE_LU 7031 s = SINGLE_LUN (the device has only one 7149 Logic 7032 Logical Unit); 7150 t = NO_ATA_1X 7033 t = NO_ATA_1X (don't allow ATA(12) and ATA(16) 7151 comma 7034 commands, uas only); 7152 u = IGNORE_UA 7035 u = IGNORE_UAS (don't bind to the uas driver); 7153 w = NO_WP_DET 7036 w = NO_WP_DETECT (don't test whether the 7154 mediu 7037 medium is write-protected). 7155 y = ALWAYS_SY 7038 y = ALWAYS_SYNC (issue a SYNCHRONIZE_CACHE 7156 even 7039 even if the device claims no cache, 7157 not o 7040 not on uas) 7158 Example: quirks=0419: 7041 Example: quirks=0419:aaf5:rl,0421:0433:rc 7159 7042 7160 user_debug= [KNL,ARM] 7043 user_debug= [KNL,ARM] 7161 Format: <int> 7044 Format: <int> 7162 See arch/arm/Kconfig. 7045 See arch/arm/Kconfig.debug help text. 7163 1 - undefine 7046 1 - undefined instruction events 7164 2 - system c 7047 2 - system calls 7165 4 - invalid 7048 4 - invalid data aborts 7166 8 - SIGSEGV 7049 8 - SIGSEGV faults 7167 16 - SIGBUS f 7050 16 - SIGBUS faults 7168 Example: user_debug=3 7051 Example: user_debug=31 7169 7052 7170 userpte= 7053 userpte= 7171 [X86,EARLY] Flags con !! 7054 [X86] Flags controlling user PTE allocations. 7172 7055 7173 nohigh = do n 7056 nohigh = do not allocate PTE pages in 7174 HIGHM 7057 HIGHMEM regardless of setting 7175 of CO 7058 of CONFIG_HIGHPTE. 7176 7059 7177 vdso= [X86,SH,SPARC] 7060 vdso= [X86,SH,SPARC] 7178 On X86_32, this is an 7061 On X86_32, this is an alias for vdso32=. Otherwise: 7179 7062 7180 vdso=1: enable VDSO ( 7063 vdso=1: enable VDSO (the default) 7181 vdso=0: disable VDSO 7064 vdso=0: disable VDSO mapping 7182 7065 7183 vdso32= [X86] Control the 32- 7066 vdso32= [X86] Control the 32-bit vDSO 7184 vdso32=1: enable 32-b 7067 vdso32=1: enable 32-bit VDSO 7185 vdso32=0 or vdso32=2: 7068 vdso32=0 or vdso32=2: disable 32-bit VDSO 7186 7069 7187 See the help text for 7070 See the help text for CONFIG_COMPAT_VDSO for more 7188 details. If CONFIG_C 7071 details. If CONFIG_COMPAT_VDSO is set, the default is 7189 vdso32=0; otherwise, 7072 vdso32=0; otherwise, the default is vdso32=1. 7190 7073 7191 For compatibility wit 7074 For compatibility with older kernels, vdso32=2 is an 7192 alias for vdso32=0. 7075 alias for vdso32=0. 7193 7076 7194 Try vdso32=0 if you e 7077 Try vdso32=0 if you encounter an error that says: 7195 dl_main: Assertion `( 7078 dl_main: Assertion `(void *) ph->p_vaddr == _rtld_local._dl_sysinfo_dso' failed! 7196 7079 7197 video= [FB,EARLY] Frame buff !! 7080 vector= [IA-64,SMP] >> 7081 vector=percpu: enable percpu vector domain >> 7082 >> 7083 video= [FB] Frame buffer configuration 7198 See Documentation/fb/ 7084 See Documentation/fb/modedb.rst. 7199 7085 7200 video.brightness_switch_enabled= [ACP 7086 video.brightness_switch_enabled= [ACPI] 7201 Format: [0|1] 7087 Format: [0|1] 7202 If set to 1, on recei 7088 If set to 1, on receiving an ACPI notify event 7203 generated by hotkey, 7089 generated by hotkey, video driver will adjust brightness 7204 level and then send o 7090 level and then send out the event to user space through 7205 the allocated input d 7091 the allocated input device. If set to 0, video driver 7206 will only send out th 7092 will only send out the event without touching backlight 7207 brightness level. 7093 brightness level. 7208 default: 1 7094 default: 1 7209 7095 7210 virtio_mmio.device= 7096 virtio_mmio.device= 7211 [VMMIO] Memory mapped 7097 [VMMIO] Memory mapped virtio (platform) device. 7212 7098 7213 <size>@<basead 7099 <size>@<baseaddr>:<irq>[:<id>] 7214 where: 7100 where: 7215 <size> := 7101 <size> := size (can use standard suffixes 7216 7102 like K, M and G) 7217 <baseaddr> := 7103 <baseaddr> := physical base address 7218 <irq> := 7104 <irq> := interrupt number (as passed to 7219 7105 request_irq()) 7220 <id> := 7106 <id> := (optional) platform device id 7221 example: 7107 example: 7222 virtio_mmio.d 7108 virtio_mmio.device=1K@0x100b0000:48:7 7223 7109 7224 Can be used multiple 7110 Can be used multiple times for multiple devices. 7225 7111 7226 vga= [BOOT,X86-32] Select 7112 vga= [BOOT,X86-32] Select a particular video mode 7227 See Documentation/arc 7113 See Documentation/arch/x86/boot.rst and 7228 Documentation/admin-g 7114 Documentation/admin-guide/svga.rst. 7229 Use vga=ask for menu. 7115 Use vga=ask for menu. 7230 This is actually a bo 7116 This is actually a boot loader parameter; the value is 7231 passed to the kernel 7117 passed to the kernel using a special protocol. 7232 7118 7233 vm_debug[=options] [KNL] Availab 7119 vm_debug[=options] [KNL] Available with CONFIG_DEBUG_VM=y. 7234 May slow down system 7120 May slow down system boot speed, especially when 7235 enabled on systems wi 7121 enabled on systems with a large amount of memory. 7236 All options are enabl 7122 All options are enabled by default, and this 7237 interface is meant to 7123 interface is meant to allow for selectively 7238 enabling or disabling 7124 enabling or disabling specific virtual memory 7239 debugging features. 7125 debugging features. 7240 7126 7241 Available options are 7127 Available options are: 7242 P Enable page s 7128 P Enable page structure init time poisoning 7243 - Disable all o 7129 - Disable all of the above options 7244 7130 7245 vmalloc=nn[KMG] [KNL,BOOT,EARLY] Forc !! 7131 vmalloc=nn[KMG] [KNL,BOOT] Forces the vmalloc area to have an exact 7246 exact size of <nn>. T !! 7132 size of <nn>. This can be used to increase the 7247 the minimum size (128 !! 7133 minimum size (128MB on x86). It can also be used to 7248 It can also be used t !! 7134 decrease the size and leave more room for directly 7249 for directly mapped k !! 7135 mapped kernel RAM. 7250 not exist on many oth << 7251 loongarch, arc, csky, << 7252 parisc, m64k, powerpc << 7253 7136 7254 vmcp_cma=nn[MG] [KNL,S390,EARLY] !! 7137 vmcp_cma=nn[MG] [KNL,S390] 7255 Sets the memory size 7138 Sets the memory size reserved for contiguous memory 7256 allocations for the v 7139 allocations for the vmcp device driver. 7257 7140 7258 vmhalt= [KNL,S390] Perform z/ 7141 vmhalt= [KNL,S390] Perform z/VM CP command after system halt. 7259 Format: <command> 7142 Format: <command> 7260 7143 7261 vmpanic= [KNL,S390] Perform z/ 7144 vmpanic= [KNL,S390] Perform z/VM CP command after kernel panic. 7262 Format: <command> 7145 Format: <command> 7263 7146 7264 vmpoff= [KNL,S390] Perform z/ 7147 vmpoff= [KNL,S390] Perform z/VM CP command after power off. 7265 Format: <command> 7148 Format: <command> 7266 7149 7267 vsyscall= [X86-64,EARLY] !! 7150 vsyscall= [X86-64] 7268 Controls the behavior 7151 Controls the behavior of vsyscalls (i.e. calls to 7269 fixed addresses of 0x 7152 fixed addresses of 0xffffffffff600x00 from legacy 7270 code). Most statical 7153 code). Most statically-linked binaries and older 7271 versions of glibc use 7154 versions of glibc use these calls. Because these 7272 functions are at fixe 7155 functions are at fixed addresses, they make nice 7273 targets for exploits 7156 targets for exploits that can control RIP. 7274 7157 7275 emulate Vsyscalls 7158 emulate Vsyscalls turn into traps and are emulated 7276 reasonabl 7159 reasonably safely. The vsyscall page is 7277 readable. 7160 readable. 7278 7161 7279 xonly [default] 7162 xonly [default] Vsyscalls turn into traps and are 7280 emulated 7163 emulated reasonably safely. The vsyscall 7281 page is n 7164 page is not readable. 7282 7165 7283 none Vsyscalls 7166 none Vsyscalls don't work at all. This makes 7284 them quit 7167 them quite hard to use for exploits but 7285 might bre 7168 might break your system. 7286 7169 7287 vt.color= [VT] Default text col 7170 vt.color= [VT] Default text color. 7288 Format: 0xYX, X = for 7171 Format: 0xYX, X = foreground, Y = background. 7289 Default: 0x07 = light 7172 Default: 0x07 = light gray on black. 7290 7173 7291 vt.cur_default= [VT] Default cursor s 7174 vt.cur_default= [VT] Default cursor shape. 7292 Format: 0xCCBBAA, whe 7175 Format: 0xCCBBAA, where AA, BB, and CC are the same as 7293 the parameters of the 7176 the parameters of the <Esc>[?A;B;Cc escape sequence; 7294 see VGA-softcursor.tx 7177 see VGA-softcursor.txt. Default: 2 = underline. 7295 7178 7296 vt.default_blu= [VT] 7179 vt.default_blu= [VT] 7297 Format: <blue0>,<blue 7180 Format: <blue0>,<blue1>,<blue2>,...,<blue15> 7298 Change the default bl 7181 Change the default blue palette of the console. 7299 This is a 16-member a 7182 This is a 16-member array composed of values 7300 ranging from 0-255. 7183 ranging from 0-255. 7301 7184 7302 vt.default_grn= [VT] 7185 vt.default_grn= [VT] 7303 Format: <green0>,<gre 7186 Format: <green0>,<green1>,<green2>,...,<green15> 7304 Change the default gr 7187 Change the default green palette of the console. 7305 This is a 16-member a 7188 This is a 16-member array composed of values 7306 ranging from 0-255. 7189 ranging from 0-255. 7307 7190 7308 vt.default_red= [VT] 7191 vt.default_red= [VT] 7309 Format: <red0>,<red1> 7192 Format: <red0>,<red1>,<red2>,...,<red15> 7310 Change the default re 7193 Change the default red palette of the console. 7311 This is a 16-member a 7194 This is a 16-member array composed of values 7312 ranging from 0-255. 7195 ranging from 0-255. 7313 7196 7314 vt.default_utf8= 7197 vt.default_utf8= 7315 [VT] 7198 [VT] 7316 Format=<0|1> 7199 Format=<0|1> 7317 Set system-wide defau 7200 Set system-wide default UTF-8 mode for all tty's. 7318 Default is 1, i.e. UT 7201 Default is 1, i.e. UTF-8 mode is enabled for all 7319 newly opened terminal 7202 newly opened terminals. 7320 7203 7321 vt.global_cursor_default= 7204 vt.global_cursor_default= 7322 [VT] 7205 [VT] 7323 Format=<-1|0|1> 7206 Format=<-1|0|1> 7324 Set system-wide defau 7207 Set system-wide default for whether a cursor 7325 is shown on new VTs. 7208 is shown on new VTs. Default is -1, 7326 i.e. cursors will be 7209 i.e. cursors will be created by default unless 7327 overridden by individ 7210 overridden by individual drivers. 0 will hide 7328 cursors, 1 will displ 7211 cursors, 1 will display them. 7329 7212 7330 vt.italic= [VT] Default color fo 7213 vt.italic= [VT] Default color for italic text; 0-15. 7331 Default: 2 = green. 7214 Default: 2 = green. 7332 7215 7333 vt.underline= [VT] Default color fo 7216 vt.underline= [VT] Default color for underlined text; 0-15. 7334 Default: 3 = cyan. 7217 Default: 3 = cyan. 7335 7218 7336 watchdog timers [HW,WDT] For informat 7219 watchdog timers [HW,WDT] For information on watchdog timers, 7337 see Documentation/wat 7220 see Documentation/watchdog/watchdog-parameters.rst 7338 or other driver-speci 7221 or other driver-specific files in the 7339 Documentation/watchdo 7222 Documentation/watchdog/ directory. 7340 7223 7341 watchdog_thresh= 7224 watchdog_thresh= 7342 [KNL] 7225 [KNL] 7343 Set the hard lockup d 7226 Set the hard lockup detector stall duration 7344 threshold in seconds. 7227 threshold in seconds. The soft lockup detector 7345 threshold is set to t 7228 threshold is set to twice the value. A value of 0 7346 disables both lockup 7229 disables both lockup detectors. Default is 10 7347 seconds. 7230 seconds. 7348 7231 7349 workqueue.unbound_cpus= 7232 workqueue.unbound_cpus= 7350 [KNL,SMP] Specify to 7233 [KNL,SMP] Specify to constrain one or some CPUs 7351 to use in unbound wor 7234 to use in unbound workqueues. 7352 Format: <cpu-list> 7235 Format: <cpu-list> 7353 By default, all onlin 7236 By default, all online CPUs are available for 7354 unbound workqueues. 7237 unbound workqueues. 7355 7238 7356 workqueue.watchdog_thresh= 7239 workqueue.watchdog_thresh= 7357 If CONFIG_WQ_WATCHDOG 7240 If CONFIG_WQ_WATCHDOG is configured, workqueue can 7358 warn stall conditions 7241 warn stall conditions and dump internal state to 7359 help debugging. 0 di 7242 help debugging. 0 disables workqueue stall 7360 detection; otherwise, 7243 detection; otherwise, it's the stall threshold 7361 duration in seconds. 7244 duration in seconds. The default value is 30 and 7362 it can be updated at 7245 it can be updated at runtime by writing to the 7363 corresponding sysfs f 7246 corresponding sysfs file. 7364 7247 7365 workqueue.cpu_intensive_thresh_us= 7248 workqueue.cpu_intensive_thresh_us= 7366 Per-cpu work items wh 7249 Per-cpu work items which run for longer than this 7367 threshold are automat 7250 threshold are automatically considered CPU intensive 7368 and excluded from con 7251 and excluded from concurrency management to prevent 7369 them from noticeably 7252 them from noticeably delaying other per-cpu work 7370 items. Default is 100 7253 items. Default is 10000 (10ms). 7371 7254 7372 If CONFIG_WQ_CPU_INTE 7255 If CONFIG_WQ_CPU_INTENSIVE_REPORT is set, the kernel 7373 will report the work 7256 will report the work functions which violate this 7374 threshold repeatedly. 7257 threshold repeatedly. They are likely good 7375 candidates for using 7258 candidates for using WQ_UNBOUND workqueues instead. 7376 7259 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 7260 workqueue.power_efficient 7387 Per-cpu workqueues ar 7261 Per-cpu workqueues are generally preferred because 7388 they show better perf 7262 they show better performance thanks to cache 7389 locality; unfortunate 7263 locality; unfortunately, per-cpu workqueues tend to 7390 be more power hungry 7264 be more power hungry than unbound workqueues. 7391 7265 7392 Enabling this makes t 7266 Enabling this makes the per-cpu workqueues which 7393 were observed to cont 7267 were observed to contribute significantly to power 7394 consumption unbound, 7268 consumption unbound, leading to measurably lower 7395 power usage at the co 7269 power usage at the cost of small performance 7396 overhead. 7270 overhead. 7397 7271 7398 The default value of 7272 The default value of this parameter is determined by 7399 the config option CON 7273 the config option CONFIG_WQ_POWER_EFFICIENT_DEFAULT. 7400 7274 7401 workqueue.default_affinity_scope= 7275 workqueue.default_affinity_scope= 7402 Select the default af 7276 Select the default affinity scope to use for unbound 7403 workqueues. Can be on 7277 workqueues. Can be one of "cpu", "smt", "cache", 7404 "numa" and "system". 7278 "numa" and "system". Default is "cache". For more 7405 information, see the 7279 information, see the Affinity Scopes section in 7406 Documentation/core-ap 7280 Documentation/core-api/workqueue.rst. 7407 7281 7408 This can be changed a 7282 This can be changed after boot by writing to the 7409 matching /sys/module/ 7283 matching /sys/module/workqueue/parameters file. All 7410 workqueues with the " 7284 workqueues with the "default" affinity scope will be 7411 updated accordingly. !! 7285 updated accordignly. 7412 7286 7413 workqueue.debug_force_rr_cpu 7287 workqueue.debug_force_rr_cpu 7414 Workqueue used to imp 7288 Workqueue used to implicitly guarantee that work 7415 items queued without 7289 items queued without explicit CPU specified are put 7416 on the local CPU. Th 7290 on the local CPU. This guarantee is no longer true 7417 and while local CPU i 7291 and while local CPU is still preferred work items 7418 may be put on foreign 7292 may be put on foreign CPUs. This debug option 7419 forces round-robin CP 7293 forces round-robin CPU selection to flush out 7420 usages which depend o 7294 usages which depend on the now broken guarantee. 7421 When enabled, memory 7295 When enabled, memory and cache locality will be 7422 impacted. 7296 impacted. 7423 7297 7424 writecombine= [LOONGARCH,EARLY] Con !! 7298 writecombine= [LOONGARCH] Control the MAT (Memory Access Type) of 7425 Type) of ioremap_wc() !! 7299 ioremap_wc(). 7426 7300 7427 on - Enable writeco 7301 on - Enable writecombine, use WUC for ioremap_wc() 7428 off - Disable writec 7302 off - Disable writecombine, use SUC for ioremap_wc() 7429 7303 7430 x2apic_phys [X86-64,APIC,EARLY] U !! 7304 x2apic_phys [X86-64,APIC] Use x2apic physical mode instead of 7431 default x2apic cluste 7305 default x2apic cluster mode on platforms 7432 supporting x2apic. 7306 supporting x2apic. 7433 7307 7434 xen_512gb_limit [KNL,X86-64,X 7308 xen_512gb_limit [KNL,X86-64,XEN] 7435 Restricts the kernel 7309 Restricts the kernel running paravirtualized under Xen 7436 to use only up to 512 7310 to use only up to 512 GB of RAM. The reason to do so is 7437 crash analysis tools 7311 crash analysis tools and Xen tools for doing domain 7438 save/restore/migratio 7312 save/restore/migration must be enabled to handle larger 7439 domains. 7313 domains. 7440 7314 7441 xen_emul_unplug= [HW,X !! 7315 xen_emul_unplug= [HW,X86,XEN] 7442 Unplug Xen emulated d 7316 Unplug Xen emulated devices 7443 Format: [unplug0,][un 7317 Format: [unplug0,][unplug1] 7444 ide-disks -- unplug p 7318 ide-disks -- unplug primary master IDE devices 7445 aux-ide-disks -- unpl 7319 aux-ide-disks -- unplug non-primary-master IDE devices 7446 nics -- unplug networ 7320 nics -- unplug network devices 7447 all -- unplug all emu 7321 all -- unplug all emulated devices (NICs and IDE disks) 7448 unnecessary -- unplug 7322 unnecessary -- unplugging emulated devices is 7449 unnecessary e 7323 unnecessary even if the host did not respond to 7450 the unplug pr 7324 the unplug protocol 7451 never -- do not unplu 7325 never -- do not unplug even if version check succeeds 7452 7326 7453 xen_legacy_crash [X86,XEN,EARL !! 7327 xen_legacy_crash [X86,XEN] 7454 Crash from Xen panic 7328 Crash from Xen panic notifier, without executing late 7455 panic() code such as 7329 panic() code such as dumping handler. 7456 7330 7457 xen_mc_debug [X86,XEN,EARLY] !! 7331 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> 7332 Format: <bool> 7465 Select whether to alw 7333 Select whether to always use non-faulting (safe) MSR 7466 access functions when 7334 access functions when running as Xen PV guest. The 7467 default value is cont 7335 default value is controlled by CONFIG_XEN_PV_MSR_SAFE. 7468 7336 >> 7337 xen_nopvspin [X86,XEN] >> 7338 Disables the qspinlock slowpath using Xen PV optimizations. >> 7339 This parameter is obsoleted by "nopvspin" parameter, which >> 7340 has equivalent effect for XEN platform. >> 7341 7469 xen_nopv [X86] 7342 xen_nopv [X86] 7470 Disables the PV optim 7343 Disables the PV optimizations forcing the HVM guest to 7471 run as generic HVM gu 7344 run as generic HVM guest with no PV drivers. 7472 This option is obsole 7345 This option is obsoleted by the "nopv" option, which 7473 has equivalent effect 7346 has equivalent effect for XEN platform. 7474 7347 7475 xen_no_vector_callback 7348 xen_no_vector_callback 7476 [KNL,X86,XEN,EARLY] D !! 7349 [KNL,X86,XEN] Disable the vector callback for Xen 7477 event channel interru 7350 event channel interrupts. 7478 7351 7479 xen_scrub_pages= [XEN] 7352 xen_scrub_pages= [XEN] 7480 Boolean option to con 7353 Boolean option to control scrubbing pages before giving them back 7481 to Xen, for use by ot 7354 to Xen, for use by other domains. Can be also changed at runtime 7482 with /sys/devices/sys 7355 with /sys/devices/system/xen_memory/xen_memory0/scrub_pages. 7483 Default value control 7356 Default value controlled with CONFIG_XEN_SCRUB_PAGES_DEFAULT. 7484 7357 7485 xen_timer_slop= [X86-64,XEN,EARLY] !! 7358 xen_timer_slop= [X86-64,XEN] 7486 Set the timer slop (i 7359 Set the timer slop (in nanoseconds) for the virtual Xen 7487 timers (default is 10 7360 timers (default is 100000). This adjusts the minimum 7488 delta of virtualized 7361 delta of virtualized Xen timers, where lower values 7489 improve timer resolut 7362 improve timer resolution at the expense of processing 7490 more timer interrupts 7363 more timer interrupts. 7491 7364 7492 xen.balloon_boot_timeout= [XEN] 7365 xen.balloon_boot_timeout= [XEN] 7493 The time (in seconds) 7366 The time (in seconds) to wait before giving up to boot 7494 in case initial ballo 7367 in case initial ballooning fails to free enough memory. 7495 Applies only when run 7368 Applies only when running as HVM or PVH guest and 7496 started with less mem 7369 started with less memory configured than allowed at 7497 max. Default is 180. 7370 max. Default is 180. 7498 7371 7499 xen.event_eoi_delay= [XEN] 7372 xen.event_eoi_delay= [XEN] 7500 How long to delay EOI 7373 How long to delay EOI handling in case of event 7501 storms (jiffies). Def 7374 storms (jiffies). Default is 10. 7502 7375 7503 xen.event_loop_timeout= [XEN] 7376 xen.event_loop_timeout= [XEN] 7504 After which time (jif 7377 After which time (jiffies) the event handling loop 7505 should start to delay 7378 should start to delay EOI handling. Default is 2. 7506 7379 7507 xen.fifo_events= [XEN] 7380 xen.fifo_events= [XEN] 7508 Boolean parameter to 7381 Boolean parameter to disable using fifo event handling 7509 even if available. No 7382 even if available. Normally fifo event handling is 7510 preferred over the 2- 7383 preferred over the 2-level event handling, as it is 7511 fairer and the number 7384 fairer and the number of possible event channels is 7512 much higher. Default 7385 much higher. Default is on (use fifo events). 7513 7386 7514 xirc2ps_cs= [NET,PCMCIA] 7387 xirc2ps_cs= [NET,PCMCIA] 7515 Format: 7388 Format: 7516 <irq>,<irq_mask>,<io> 7389 <irq>,<irq_mask>,<io>,<full_duplex>,<do_sound>,<lockup_hack>[,<irq2>[,<irq3>[,<irq4>]]] 7517 7390 7518 xive= [PPC] 7391 xive= [PPC] 7519 By default on POWER9 7392 By default on POWER9 and above, the kernel will 7520 natively use the XIVE 7393 natively use the XIVE interrupt controller. This option 7521 allows the fallback f 7394 allows the fallback firmware mode to be used: 7522 7395 7523 off Fallback to 7396 off Fallback to firmware control of XIVE interrupt 7524 controller 7397 controller on both pseries and powernv 7525 platforms. 7398 platforms. Only useful on POWER9 and above. 7526 7399 7527 xive.store-eoi=off [PPC] 7400 xive.store-eoi=off [PPC] 7528 By default on POWER10 7401 By default on POWER10 and above, the kernel will use 7529 stores for EOI handli 7402 stores for EOI handling when the XIVE interrupt mode 7530 is active. This optio 7403 is active. This option allows the XIVE driver to use 7531 loads instead, as on 7404 loads instead, as on POWER9. 7532 7405 7533 xhci-hcd.quirks [USB,KNL] 7406 xhci-hcd.quirks [USB,KNL] 7534 A hex value specifyin 7407 A hex value specifying bitmask with supplemental xhci 7535 host controller quirk 7408 host controller quirks. Meaning of each bit can be 7536 consulted in header d 7409 consulted in header drivers/usb/host/xhci.h. 7537 7410 7538 xmon [PPC,EARLY] !! 7411 xmon [PPC] 7539 Format: { early | on 7412 Format: { early | on | rw | ro | off } 7540 Controls if xmon debu 7413 Controls if xmon debugger is enabled. Default is off. 7541 Passing only "xmon" i 7414 Passing only "xmon" is equivalent to "xmon=early". 7542 early Call xmon as 7415 early Call xmon as early as possible on boot; xmon 7543 debugger is c 7416 debugger is called from setup_arch(). 7544 on xmon debugger 7417 on xmon debugger hooks will be installed so xmon 7545 is only calle 7418 is only called on a kernel crash. Default mode, 7546 i.e. either " 7419 i.e. either "ro" or "rw" mode, is controlled 7547 with CONFIG_X 7420 with CONFIG_XMON_DEFAULT_RO_MODE. 7548 rw xmon debugger 7421 rw xmon debugger hooks will be installed so xmon 7549 is called onl 7422 is called only on a kernel crash, mode is write, 7550 meaning SPR r 7423 meaning SPR registers, memory and, other data 7551 can be writte 7424 can be written using xmon commands. 7552 ro same as "rw" 7425 ro same as "rw" option above but SPR registers, 7553 memory, and o 7426 memory, and other data can't be written using 7554 xmon commands 7427 xmon commands. 7555 off xmon is disab 7428 off xmon is disabled. >> 7429
Linux® is a registered trademark of Linus Torvalds in the United States and other countries.
TOMOYO® is a registered trademark of NTT DATA CORPORATION.