1 ACPI ACPI support is enabled. 2 AGP AGP (Accelerated Graphics Port) is enabled. 3 ALSA ALSA sound support is enabled. 4 APIC APIC support is enabled. 5 APM Advanced Power Management support is enabled. 6 APPARMOR AppArmor support is enabled. 7 ARM ARM architecture is enabled. 8 ARM64 ARM64 architecture is enabled. 9 AX25 Appropriate AX.25 support is enabled. 10 CLK Common clock infrastructure is enabled. 11 CMA Contiguous Memory Area support is enabled. 12 DRM Direct Rendering Management support is enabled. 13 DYNAMIC_DEBUG Build in debug messages and enable them at runtime 14 EARLY Parameter processed too early to be embedded in initrd. 15 EDD BIOS Enhanced Disk Drive Services (EDD) is enabled 16 EFI EFI Partitioning (GPT) is enabled 17 EVM Extended Verification Module 18 FB The frame buffer device is enabled. 19 FTRACE Function tracing enabled. 20 GCOV GCOV profiling is enabled. 21 HIBERNATION HIBERNATION is enabled. 22 HW Appropriate hardware is enabled. 23 HYPER_V HYPERV support is enabled. 24 IMA Integrity measurement architecture is enabled. 25 IP_PNP IP DHCP, BOOTP, or RARP is enabled. 26 IPV6 IPv6 support is enabled. 27 ISAPNP ISA PnP code is enabled. 28 ISDN Appropriate ISDN support is enabled. 29 ISOL CPU Isolation is enabled. 30 JOY Appropriate joystick support is enabled. 31 KGDB Kernel debugger support is enabled. 32 KVM Kernel Virtual Machine support is enabled. 33 LIBATA Libata driver is enabled 34 LOONGARCH LoongArch architecture is enabled. 35 LOOP Loopback device support is enabled. 36 LP Printer support is enabled. 37 M68k M68k architecture is enabled. 38 These options have more detailed description inside of 39 Documentation/arch/m68k/kernel-options.rst. 40 MDA MDA console support is enabled. 41 MIPS MIPS architecture is enabled. 42 MOUSE Appropriate mouse support is enabled. 43 MSI Message Signaled Interrupts (PCI). 44 MTD MTD (Memory Technology Device) support is enabled. 45 NET Appropriate network support is enabled. 46 NFS Appropriate NFS support is enabled. 47 NUMA NUMA support is enabled. 48 OF Devicetree is enabled. 49 PARISC The PA-RISC architecture is enabled. 50 PCI PCI bus support is enabled. 51 PCIE PCI Express support is enabled. 52 PCMCIA The PCMCIA subsystem is enabled. 53 PNP Plug & Play support is enabled. 54 PPC PowerPC architecture is enabled. 55 PPT Parallel port support is enabled. 56 PS2 Appropriate PS/2 support is enabled. 57 PV_OPS A paravirtualized kernel is enabled. 58 RAM RAM disk support is enabled. 59 RDT Intel Resource Director Technology. 60 RISCV RISCV architecture is enabled. 61 S390 S390 architecture is enabled. 62 SCSI Appropriate SCSI support is enabled. 63 A lot of drivers have their options described inside 64 the Documentation/scsi/ sub-directory. 65 SDW SoundWire support is enabled. 66 SECURITY Different security models are enabled. 67 SELINUX SELinux support is enabled. 68 SERIAL Serial support is enabled. 69 SH SuperH architecture is enabled. 70 SMP The kernel is an SMP kernel. 71 SPARC Sparc architecture is enabled. 72 SUSPEND System suspend states are enabled. 73 SWSUSP Software suspend (hibernation) is enabled. 74 TPM TPM drivers are enabled. 75 UMS USB Mass Storage support is enabled. 76 USB USB support is enabled. 77 NVME NVMe support is enabled 78 USBHID USB Human Interface Device support is enabled. 79 V4L Video For Linux support is enabled. 80 VGA The VGA console has been enabled. 81 VMMIO Driver for memory mapped virtio devices is enabled. 82 VT Virtual terminal support is enabled. 83 WDT Watchdog support is enabled. 84 X86-32 X86-32, aka i386 architecture is enabled. 85 X86-64 X86-64 architecture is enabled. 86 X86 Either 32-bit or 64-bit x86 (same as X86-32+X86-64) 87 X86_UV SGI UV support is enabled. 88 XEN Xen support is enabled 89 XTENSA xtensa architecture is enabled. 90 91In addition, the following text indicates that the option 92 93 BOOT Is a boot loader parameter. 94 BUGS= Relates to possible processor bugs on the said processor. 95 KNL Is a kernel start-up parameter. 96 97 98Kernel parameters 99 100 accept_memory= [MM] 101 Format: { eager | lazy } 102 default: lazy 103 By default, unaccepted memory is accepted lazily to 104 avoid prolonged boot times. The lazy option will add 105 some runtime overhead until all memory is eventually 106 accepted. In most cases the overhead is negligible. 107 For some workloads or for debugging purposes 108 accept_memory=eager can be used to accept all memory 109 at once during boot. 110 111 acpi= [HW,ACPI,X86,ARM64,RISCV64,EARLY] 112 Advanced Configuration and Power Interface 113 Format: { force | on | off | strict | noirq | rsdt | 114 copy_dsdt | nospcr } 115 force -- enable ACPI if default was off 116 on -- enable ACPI but allow fallback to DT [arm64,riscv64] 117 off -- disable ACPI if default was on 118 noirq -- do not use ACPI for IRQ routing 119 strict -- Be less tolerant of platforms that are not 120 strictly ACPI specification compliant. 121 rsdt -- prefer RSDT over (default) XSDT 122 copy_dsdt -- copy DSDT to memory 123 nocmcff -- Disable firmware first mode for corrected 124 errors. This disables parsing the HEST CMC error 125 source to check if firmware has set the FF flag. This 126 may result in duplicate corrected error reports. 127 nospcr -- disable console in ACPI SPCR table as 128 default _serial_ console on ARM64 129 spcr -- enable console in ACPI SPCR table as 130 default _serial_ console on x86 131 For ARM64, ONLY "acpi=off", "acpi=on", "acpi=force" or 132 "acpi=nospcr" are available 133 For RISCV64, ONLY "acpi=off", "acpi=on" or "acpi=force" 134 are available 135 136 See also Documentation/power/runtime_pm.rst, pci=noacpi 137 138 acpi_apic_instance= [ACPI,IOAPIC,EARLY] 139 Format: <int> 140 2: use 2nd APIC table, if available 141 1,0: use 1st APIC table 142 default: 0 143 144 acpi_backlight= [HW,ACPI] 145 { vendor | video | native | none } 146 If set to vendor, prefer vendor-specific driver 147 (e.g. thinkpad_acpi, sony_acpi, etc.) instead 148 of the ACPI video.ko driver. 149 If set to video, use the ACPI video.ko driver. 150 If set to native, use the device's native backlight mode. 151 If set to none, disable the ACPI backlight interface. 152 153 acpi_force_32bit_fadt_addr [ACPI,EARLY] 154 force FADT to use 32 bit addresses rather than the 155 64 bit X_* addresses. Some firmware have broken 64 156 bit addresses for force ACPI ignore these and use 157 the older legacy 32 bit addresses. 158 159 acpica_no_return_repair [HW, ACPI] 160 Disable AML predefined validation mechanism 161 This mechanism can repair the evaluation result to make 162 the return objects more ACPI specification compliant. 163 This option is useful for developers to identify the 164 root cause of an AML interpreter issue when the issue 165 has something to do with the repair mechanism. 166 167 acpi.debug_layer= [HW,ACPI,ACPI_DEBUG] 168 acpi.debug_level= [HW,ACPI,ACPI_DEBUG] 169 Format: <int> 170 CONFIG_ACPI_DEBUG must be enabled to produce any ACPI 171 debug output. Bits in debug_layer correspond to a 172 _COMPONENT in an ACPI source file, e.g., 173 #define _COMPONENT ACPI_EVENTS 174 Bits in debug_level correspond to a level in 175 ACPI_DEBUG_PRINT statements, e.g., 176 ACPI_DEBUG_PRINT((ACPI_DB_INFO, ... 177 The debug_level mask defaults to "info". See 178 Documentation/firmware-guide/acpi/debug.rst for more information about 179 debug layers and levels. 180 181 Enable processor driver info messages: 182 acpi.debug_layer=0x20000000 183 Enable AML "Debug" output, i.e., stores to the Debug 184 object while interpreting AML: 185 acpi.debug_layer=0xffffffff acpi.debug_level=0x2 186 Enable all messages related to ACPI hardware: 187 acpi.debug_layer=0x2 acpi.debug_level=0xffffffff 188 189 Some values produce so much output that the system is 190 unusable. The "log_buf_len" parameter may be useful 191 if you need to capture more output. 192 193 acpi.poweroff_on_fatal= [ACPI] 194 {0 | 1} 195 Causes the system to poweroff when the ACPI bytecode signals 196 a fatal error. The default value of this setting is 1. 197 Overriding this value should only be done for diagnosing 198 ACPI firmware problems, as the system might behave erratically 199 after having encountered a fatal ACPI error. 200 201 acpi_enforce_resources= [ACPI] 202 { strict | lax | no } 203 Check for resource conflicts between native drivers 204 and ACPI OperationRegions (SystemIO and SystemMemory 205 only). IO ports and memory declared in ACPI might be 206 used by the ACPI subsystem in arbitrary AML code and 207 can interfere with legacy drivers. 208 strict (default): access to resources claimed by ACPI 209 is denied; legacy drivers trying to access reserved 210 resources will fail to bind to device using them. 211 lax: access to resources claimed by ACPI is allowed; 212 legacy drivers trying to access reserved resources 213 will bind successfully but a warning message is logged. 214 no: ACPI OperationRegions are not marked as reserved, 215 no further checks are performed. 216 217 acpi_force_table_verification [HW,ACPI,EARLY] 218 Enable table checksum verification during early stage. 219 By default, this is disabled due to x86 early mapping 220 size limitation. 221 222 acpi_irq_balance [HW,ACPI] 223 ACPI will balance active IRQs 224 default in APIC mode 225 226 acpi_irq_nobalance [HW,ACPI] 227 ACPI will not move active IRQs (default) 228 default in PIC mode 229 230 acpi_irq_isa= [HW,ACPI] If irq_balance, mark listed IRQs used by ISA 231 Format: <irq>,<irq>... 232 233 acpi_irq_pci= [HW,ACPI] If irq_balance, clear listed IRQs for 234 use by PCI 235 Format: <irq>,<irq>... 236 237 acpi_mask_gpe= [HW,ACPI] 238 Due to the existence of _Lxx/_Exx, some GPEs triggered 239 by unsupported hardware/firmware features can result in 240 GPE floodings that cannot be automatically disabled by 241 the GPE dispatcher. 242 This facility can be used to prevent such uncontrolled 243 GPE floodings. 244 Format: <byte> or <bitmap-list> 245 246 acpi_no_auto_serialize [HW,ACPI] 247 Disable auto-serialization of AML methods 248 AML control methods that contain the opcodes to create 249 named objects will be marked as "Serialized" by the 250 auto-serialization feature. 251 This feature is enabled by default. 252 This option allows to turn off the feature. 253 254 acpi_no_memhotplug [ACPI] Disable memory hotplug. Useful for kdump 255 kernels. 256 257 acpi_no_static_ssdt [HW,ACPI,EARLY] 258 Disable installation of static SSDTs at early boot time 259 By default, SSDTs contained in the RSDT/XSDT will be 260 installed automatically and they will appear under 261 /sys/firmware/acpi/tables. 262 This option turns off this feature. 263 Note that specifying this option does not affect 264 dynamic table installation which will install SSDT 265 tables to /sys/firmware/acpi/tables/dynamic. 266 267 acpi_no_watchdog [HW,ACPI,WDT] 268 Ignore the ACPI-based watchdog interface (WDAT) and let 269 a native driver control the watchdog device instead. 270 271 acpi_rsdp= [ACPI,EFI,KEXEC,EARLY] 272 Pass the RSDP address to the kernel, mostly used 273 on machines running EFI runtime service to boot the 274 second kernel for kdump. 275 276 acpi_os_name= [HW,ACPI] Tell ACPI BIOS the name of the OS 277 Format: To spoof as Windows 98: ="Microsoft Windows" 278 279 acpi_rev_override [ACPI] Override the _REV object to return 5 (instead 280 of 2 which is mandated by ACPI 6) as the supported ACPI 281 specification revision (when using this switch, it may 282 be necessary to carry out a cold reboot _twice_ in a 283 row to make it take effect on the platform firmware). 284 285 acpi_osi= [HW,ACPI] Modify list of supported OS interface strings 286 acpi_osi="string1" # add string1 287 acpi_osi="!string2" # remove string2 288 acpi_osi=!* # remove all strings 289 acpi_osi=! # disable all built-in OS vendor 290 strings 291 acpi_osi=!! # enable all built-in OS vendor 292 strings 293 acpi_osi= # disable all strings 294 295 'acpi_osi=!' can be used in combination with single or 296 multiple 'acpi_osi="string1"' to support specific OS 297 vendor string(s). Note that such command can only 298 affect the default state of the OS vendor strings, thus 299 it cannot affect the default state of the feature group 300 strings and the current state of the OS vendor strings, 301 specifying it multiple times through kernel command line 302 is meaningless. This command is useful when one do not 303 care about the state of the feature group strings which 304 should be controlled by the OSPM. 305 Examples: 306 1. 'acpi_osi=! acpi_osi="Windows 2000"' is equivalent 307 to 'acpi_osi="Windows 2000" acpi_osi=!', they all 308 can make '_OSI("Windows 2000")' TRUE. 309 310 'acpi_osi=' cannot be used in combination with other 311 'acpi_osi=' command lines, the _OSI method will not 312 exist in the ACPI namespace. NOTE that such command can 313 only affect the _OSI support state, thus specifying it 314 multiple times through kernel command line is also 315 meaningless. 316 Examples: 317 1. 'acpi_osi=' can make 'CondRefOf(_OSI, Local1)' 318 FALSE. 319 320 'acpi_osi=!*' can be used in combination with single or 321 multiple 'acpi_osi="string1"' to support specific 322 string(s). Note that such command can affect the 323 current state of both the OS vendor strings and the 324 feature group strings, thus specifying it multiple times 325 through kernel command line is meaningful. But it may 326 still not able to affect the final state of a string if 327 there are quirks related to this string. This command 328 is useful when one want to control the state of the 329 feature group strings to debug BIOS issues related to 330 the OSPM features. 331 Examples: 332 1. 'acpi_osi="Module Device" acpi_osi=!*' can make 333 '_OSI("Module Device")' FALSE. 334 2. 'acpi_osi=!* acpi_osi="Module Device"' can make 335 '_OSI("Module Device")' TRUE. 336 3. 'acpi_osi=! acpi_osi=!* acpi_osi="Windows 2000"' is 337 equivalent to 338 'acpi_osi=!* acpi_osi=! acpi_osi="Windows 2000"' 339 and 340 'acpi_osi=!* acpi_osi="Windows 2000" acpi_osi=!', 341 they all will make '_OSI("Windows 2000")' TRUE. 342 343 acpi_pm_good [X86] 344 Override the pmtimer bug detection: force the kernel 345 to assume that this machine's pmtimer latches its value 346 and always returns good values. 347 348 acpi_sci= [HW,ACPI,EARLY] ACPI System Control Interrupt trigger mode 349 Format: { level | edge | high | low } 350 351 acpi_skip_timer_override [HW,ACPI,EARLY] 352 Recognize and ignore IRQ0/pin2 Interrupt Override. 353 For broken nForce2 BIOS resulting in XT-PIC timer. 354 355 acpi_sleep= [HW,ACPI] Sleep options 356 Format: { s3_bios, s3_mode, s3_beep, s4_hwsig, 357 s4_nohwsig, old_ordering, nonvs, 358 sci_force_enable, nobl } 359 See Documentation/power/video.rst for information on 360 s3_bios and s3_mode. 361 s3_beep is for debugging; it makes the PC's speaker beep 362 as soon as the kernel's real-mode entry point is called. 363 s4_hwsig causes the kernel to check the ACPI hardware 364 signature during resume from hibernation, and gracefully 365 refuse to resume if it has changed. This complies with 366 the ACPI specification but not with reality, since 367 Windows does not do this and many laptops do change it 368 on docking. So the default behaviour is to allow resume 369 and simply warn when the signature changes, unless the 370 s4_hwsig option is enabled. 371 s4_nohwsig prevents ACPI hardware signature from being 372 used (or even warned about) during resume. 373 old_ordering causes the ACPI 1.0 ordering of the _PTS 374 control method, with respect to putting devices into 375 low power states, to be enforced (the ACPI 2.0 ordering 376 of _PTS is used by default). 377 nonvs prevents the kernel from saving/restoring the 378 ACPI NVS memory during suspend/hibernation and resume. 379 sci_force_enable causes the kernel to set SCI_EN directly 380 on resume from S1/S3 (which is against the ACPI spec, 381 but some broken systems don't work without it). 382 nobl causes the internal blacklist of systems known to 383 behave incorrectly in some ways with respect to system 384 suspend and resume to be ignored (use wisely). 385 386 acpi_use_timer_override [HW,ACPI,EARLY] 387 Use timer override. For some broken Nvidia NF5 boards 388 that require a timer override, but don't have HPET 389 390 add_efi_memmap [EFI,X86,EARLY] Include EFI memory map in 391 kernel's map of available physical RAM. 392 393 agp= [AGP] 394 { off | try_unsupported } 395 off: disable AGP support 396 try_unsupported: try to drive unsupported chipsets 397 (may crash computer or cause data corruption) 398 399 ALSA [HW,ALSA] 400 See Documentation/sound/alsa-configuration.rst 401 402 alignment= [KNL,ARM] 403 Allow the default userspace alignment fault handler 404 behaviour to be specified. Bit 0 enables warnings, 405 bit 1 enables fixups, and bit 2 sends a segfault. 406 407 align_va_addr= [X86-64] 408 Align virtual addresses by clearing slice [14:12] when 409 allocating a VMA at process creation time. This option 410 gives you up to 3% performance improvement on AMD F15h 411 machines (where it is enabled by default) for a 412 CPU-intensive style benchmark, and it can vary highly in 413 a microbenchmark depending on workload and compiler. 414 415 32: only for 32-bit processes 416 64: only for 64-bit processes 417 on: enable for both 32- and 64-bit processes 418 off: disable for both 32- and 64-bit processes 419 420 alloc_snapshot [FTRACE] 421 Allocate the ftrace snapshot buffer on boot up when the 422 main buffer is allocated. This is handy if debugging 423 and you need to use tracing_snapshot() on boot up, and 424 do not want to use tracing_snapshot_alloc() as it needs 425 to be done where GFP_KERNEL allocations are allowed. 426 427 allow_mismatched_32bit_el0 [ARM64,EARLY] 428 Allow execve() of 32-bit applications and setting of the 429 PER_LINUX32 personality on systems where only a strict 430 subset of the CPUs support 32-bit EL0. When this 431 parameter is present, the set of CPUs supporting 32-bit 432 EL0 is indicated by /sys/devices/system/cpu/aarch32_el0 433 and hot-unplug operations may be restricted. 434 435 See Documentation/arch/arm64/asymmetric-32bit.rst for more 436 information. 437 438 amd_iommu= [HW,X86-64] 439 Pass parameters to the AMD IOMMU driver in the system. 440 Possible values are: 441 fullflush - Deprecated, equivalent to iommu.strict=1 442 off - do not initialize any AMD IOMMU found in 443 the system 444 force_isolation - Force device isolation for all 445 devices. The IOMMU driver is not 446 allowed anymore to lift isolation 447 requirements as needed. This option 448 does not override iommu=pt 449 force_enable - Force enable the IOMMU on platforms known 450 to be buggy with IOMMU enabled. Use this 451 option with care. 452 pgtbl_v1 - Use v1 page table for DMA-API (Default). 453 pgtbl_v2 - Use v2 page table for DMA-API. 454 irtcachedis - Disable Interrupt Remapping Table (IRT) caching. 455 nohugepages - Limit page-sizes used for v1 page-tables 456 to 4 KiB. 457 v2_pgsizes_only - Limit page-sizes used for v1 page-tables 458 to 4KiB/2Mib/1GiB. 459 460 461 amd_iommu_dump= [HW,X86-64] 462 Enable AMD IOMMU driver option to dump the ACPI table 463 for AMD IOMMU. With this option enabled, AMD IOMMU 464 driver will print ACPI tables for AMD IOMMU during 465 IOMMU initialization. 466 467 amd_iommu_intr= [HW,X86-64] 468 Specifies one of the following AMD IOMMU interrupt 469 remapping modes: 470 legacy - Use legacy interrupt remapping mode. 471 vapic - Use virtual APIC mode, which allows IOMMU 472 to inject interrupts directly into guest. 473 This mode requires kvm-amd.avic=1. 474 (Default when IOMMU HW support is present.) 475 476 amd_pstate= [X86,EARLY] 477 disable 478 Do not enable amd_pstate as the default 479 scaling driver for the supported processors 480 passive 481 Use amd_pstate with passive mode as a scaling driver. 482 In this mode autonomous selection is disabled. 483 Driver requests a desired performance level and platform 484 tries to match the same performance level if it is 485 satisfied by guaranteed performance level. 486 active 487 Use amd_pstate_epp driver instance as the scaling driver, 488 driver provides a hint to the hardware if software wants 489 to bias toward performance (0x0) or energy efficiency (0xff) 490 to the CPPC firmware. then CPPC power algorithm will 491 calculate the runtime workload and adjust the realtime cores 492 frequency. 493 guided 494 Activate guided autonomous mode. Driver requests minimum and 495 maximum performance level and the platform autonomously 496 selects a performance level in this range and appropriate 497 to the current workload. 498 499 amd_prefcore= 500 [X86] 501 disable 502 Disable amd-pstate preferred core. 503 504 amd_dynamic_epp= 505 [X86] 506 disable 507 Disable amd-pstate dynamic EPP. 508 enable 509 Enable amd-pstate dynamic EPP. 510 511 amijoy.map= [HW,JOY] Amiga joystick support 512 Map of devices attached to JOY0DAT and JOY1DAT 513 Format: <a>,<b> 514 See also Documentation/input/joydev/joystick.rst 515 516 analog.map= [HW,JOY] Analog joystick and gamepad support 517 Specifies type or capabilities of an analog joystick 518 connected to one of 16 gameports 519 Format: <type1>,<type2>,..<type16> 520 521 apc= [HW,SPARC] 522 Power management functions (SPARCstation-4/5 + deriv.) 523 Format: noidle 524 Disable APC CPU standby support. SPARCstation-Fox does 525 not play well with APC CPU idle - disable it if you have 526 APC and your system crashes randomly. 527 528 apic [APIC,X86-64] Use IO-APIC. Default. 529 530 apic= [APIC,X86,EARLY] Advanced Programmable Interrupt Controller 531 Change the output verbosity while booting 532 Format: { quiet (default) | verbose | debug } 533 Change the amount of debugging information output 534 when initialising the APIC and IO-APIC components. 535 536 apic_extnmi= [APIC,X86,EARLY] External NMI delivery setting 537 Format: { bsp (default) | all | none } 538 bsp: External NMI is delivered only to CPU 0 539 all: External NMIs are broadcast to all CPUs as a 540 backup of CPU 0 541 none: External NMI is masked for all CPUs. This is 542 useful so that a dump capture kernel won't be 543 shot down by NMI 544 545 apicpmtimer Do APIC timer calibration using the pmtimer. Implies 546 apicmaintimer. Useful when your PIT timer is totally 547 broken. 548 549 autoconf= [IPV6] 550 See Documentation/networking/ipv6.rst. 551 552 apm= [APM] Advanced Power Management 553 See header of arch/x86/kernel/apm_32.c. 554 555 apparmor= [APPARMOR] Disable or enable AppArmor at boot time 556 Format: { "0" | "1" } 557 See security/apparmor/Kconfig help text 558 0 -- disable. 559 1 -- enable. 560 Default value is set via kernel config option. 561 562 arcrimi= [HW,NET] ARCnet - "RIM I" (entirely mem-mapped) cards 563 Format: <io>,<irq>,<nodeID> 564 565 arm64.no32bit_el0 [ARM64] Unconditionally disable the execution of 566 32 bit applications. 567 568 arm64.nobti [ARM64] Unconditionally disable Branch Target 569 Identification support 570 571 arm64.nogcs [ARM64] Unconditionally disable Guarded Control Stack 572 support 573 574 arm64.nomops [ARM64] Unconditionally disable Memory Copy and Memory 575 Set instructions support 576 577 arm64.nompam [ARM64] Unconditionally disable Memory Partitioning And 578 Monitoring support 579 580 arm64.nomte [ARM64] Unconditionally disable Memory Tagging Extension 581 support 582 583 arm64.nopauth [ARM64] Unconditionally disable Pointer Authentication 584 support 585 586 arm64.nosme [ARM64] Unconditionally disable Scalable Matrix 587 Extension support 588 589 arm64.nosve [ARM64] Unconditionally disable Scalable Vector 590 Extension support 591 592 ataflop= [HW,M68k] 593 594 atarimouse= [HW,MOUSE] Atari Mouse 595 596 atkbd.extra= [HW] Enable extra LEDs and keys on IBM RapidAccess, 597 EzKey and similar keyboards 598 599 atkbd.reset= [HW] Reset keyboard during initialization 600 601 atkbd.set= [HW] Select keyboard code set 602 Format: <int> (2 = AT (default), 3 = PS/2) 603 604 atkbd.scroll= [HW] Enable scroll wheel on MS Office and similar 605 keyboards 606 607 atkbd.softraw= [HW] Choose between synthetic and real raw mode 608 Format: <bool> (0 = real, 1 = synthetic (default)) 609 610 atkbd.softrepeat= [HW] 611 Use software keyboard repeat 612 613 audit= [KNL] Enable the audit sub-system 614 Format: { "0" | "1" | "off" | "on" } 615 0 | off - kernel audit is disabled and can not be 616 enabled until the next reboot 617 unset - kernel audit is initialized but disabled and 618 will be fully enabled by the userspace auditd. 619 1 | on - kernel audit is initialized and partially 620 enabled, storing at most audit_backlog_limit 621 messages in RAM until it is fully enabled by the 622 userspace auditd. 623 Default: unset 624 625 audit_backlog_limit= [KNL] Set the audit queue size limit. 626 Format: <int> (must be >=0) 627 Default: 64 628 629 bau= [X86_UV] Enable the BAU on SGI UV. The default 630 behavior is to disable the BAU (i.e. bau=0). 631 Format: { "0" | "1" } 632 0 - Disable the BAU. 633 1 - Enable the BAU. 634 unset - Disable the BAU. 635 636 baycom_epp= [HW,AX25] 637 Format: <io>,<mode> 638 639 baycom_par= [HW,AX25] BayCom Parallel Port AX.25 Modem 640 Format: <io>,<mode> 641 See header of drivers/net/hamradio/baycom_par.c. 642 643 baycom_ser_fdx= [HW,AX25] 644 BayCom Serial Port AX.25 Modem (Full Duplex Mode) 645 Format: <io>,<irq>,<mode>[,<baud>] 646 See header of drivers/net/hamradio/baycom_ser_fdx.c. 647 648 baycom_ser_hdx= [HW,AX25] 649 BayCom Serial Port AX.25 Modem (Half Duplex Mode) 650 Format: <io>,<irq>,<mode> 651 See header of drivers/net/hamradio/baycom_ser_hdx.c. 652 653 bdev_allow_write_mounted= 654 Format: <bool> 655 Control the ability to open a mounted block device 656 for writing, i.e., allow / disallow writes that bypass 657 the FS. This was implemented as a means to prevent 658 fuzzers from crashing the kernel by overwriting the 659 metadata underneath a mounted FS without its awareness. 660 This also prevents destructive formatting of mounted 661 filesystems by naive storage tooling that don't use 662 O_EXCL. Default is Y and can be changed through the 663 Kconfig option CONFIG_BLK_DEV_WRITE_MOUNTED. 664 665 bert_disable [ACPI] 666 Disable BERT OS support on buggy BIOSes. 667 668 bgrt_disable [ACPI,X86,EARLY] 669 Disable BGRT to avoid flickering OEM logo. 670 671 blkdevparts= Manual partition parsing of block device(s) for 672 embedded devices based on command line input. 673 See Documentation/block/cmdline-partition.rst 674 675 boot_delay= [KNL,EARLY] 676 Milliseconds to delay each printk during boot. 677 Only works if CONFIG_BOOT_PRINTK_DELAY is enabled, 678 and you may also have to specify "lpj=". Boot_delay 679 values larger than 10 seconds (10000) are assumed 680 erroneous and ignored. 681 Format: integer 682 683 bootconfig [KNL,EARLY] 684 Extended command line options can be added to an initrd 685 and this will cause the kernel to look for it. 686 687 See Documentation/admin-guide/bootconfig.rst 688 689 bttv.card= [HW,V4L] bttv (bt848 + bt878 based grabber cards) 690 bttv.radio= Most important insmod options are available as 691 kernel args too. 692 bttv.pll= See Documentation/admin-guide/media/bttv.rst 693 bttv.tuner= 694 695 bulk_remove=off [PPC] This parameter disables the use of the pSeries 696 firmware feature for flushing multiple hpte entries 697 at a time. 698 699 c101= [NET] Moxa C101 synchronous serial card 700 701 cachesize= [BUGS=X86-32] Override level 2 CPU cache size detection. 702 Sometimes CPU hardware bugs make them report the cache 703 size incorrectly. The kernel will attempt work arounds 704 to fix known problems, but for some CPUs it is not 705 possible to determine what the correct size should be. 706 This option provides an override for these situations. 707 708 carrier_timeout= 709 [NET] Specifies amount of time (in seconds) that 710 the kernel should wait for a network carrier. By default 711 it waits 120 seconds. 712 713 ca_keys= [KEYS] This parameter identifies a specific key(s) on 714 the system trusted keyring to be used for certificate 715 trust validation. 716 format: { id:<keyid> | builtin } 717 718 cca= [MIPS,EARLY] Override the kernel pages' cache coherency 719 algorithm. Accepted values range from 0 to 7 720 inclusive. See arch/mips/include/asm/pgtable-bits.h 721 for platform specific values (SB1, Loongson3 and 722 others). 723 724 ccw_timeout_log [S390] 725 See Documentation/arch/s390/common_io.rst for details. 726 727 cfi= [X86-64] Set Control Flow Integrity checking features 728 when CONFIG_FINEIBT is enabled. 729 Format: feature[,feature...] 730 Default: auto 731 732 auto: Use FineIBT if IBT available, otherwise kCFI. 733 Under FineIBT, enable "paranoid" mode when 734 FRED is not available. 735 off: Turn off CFI checking. 736 kcfi: Use kCFI (disable FineIBT). 737 fineibt: Use FineIBT (even if IBT not available). 738 norand: Do not re-randomize CFI hashes. 739 paranoid: Add caller hash checking under FineIBT. 740 bhi: Enable register poisoning to stop speculation 741 across FineIBT. (Disabled by default.) 742 warn: Do not enforce CFI checking: warn only. 743 debug: Report CFI initialization details. 744 745 cgroup_disable= [KNL] Disable a particular controller or optional feature 746 Format: {name of the controller(s) or feature(s) to disable} 747 The effects of cgroup_disable=foo are: 748 - foo isn't auto-mounted if you mount all cgroups in 749 a single hierarchy 750 - foo isn't visible as an individually mountable 751 subsystem 752 - if foo is an optional feature then the feature is 753 disabled and corresponding cgroup files are not 754 created 755 {Currently only "memory" controller deal with this and 756 cut the overhead, others just disable the usage. So 757 only cgroup_disable=memory is actually worthy} 758 Specifying "pressure" disables per-cgroup pressure 759 stall information accounting feature 760 761 cgroup_no_v1= [KNL] Disable cgroup controllers and named hierarchies in v1 762 Format: { { controller | "all" | "named" } 763 [,{ controller | "all" | "named" }...] } 764 Like cgroup_disable, but only applies to cgroup v1; 765 the blacklisted controllers remain available in cgroup2. 766 "all" blacklists all controllers and "named" disables 767 named mounts. Specifying both "all" and "named" disables 768 all v1 hierarchies. 769 770 cgroup_v1_proc= [KNL] Show also missing controllers in /proc/cgroups 771 Format: { "true" | "false" } 772 /proc/cgroups lists only v1 controllers by default. 773 This compatibility option enables listing also v2 774 controllers (whose v1 code is not compiled!), so that 775 semi-legacy software can check this file to decide 776 about usage of v2 (sic) controllers. 777 778 cgroup_favordynmods= [KNL] Enable or Disable favordynmods. 779 Format: { "true" | "false" } 780 Defaults to the value of CONFIG_CGROUP_FAVOR_DYNMODS. 781 782 cgroup.memory= [KNL] Pass options to the cgroup memory controller. 783 Format: <string> 784 nosocket -- Disable socket memory accounting. 785 nokmem -- Disable kernel memory accounting. 786 nobpf -- Disable BPF memory accounting. 787 788 check_pages= [MM,EARLY] Enable sanity checking of pages after 789 allocations / before freeing. This adds checks to catch 790 double-frees, use-after-frees, and other sources of 791 page corruption by inspecting page internals (flags, 792 mapcount/refcount, memcg_data, etc.). 793 Format: { "0" | "1" } 794 Default: 0 (1 if CONFIG_DEBUG_VM is set) 795 796 checkreqprot= [SELINUX] Set initial checkreqprot flag value. 797 Format: { "0" | "1" } 798 See security/selinux/Kconfig help text. 799 0 -- check protection applied by kernel (includes 800 any implied execute protection). 801 1 -- check protection requested by application. 802 Default value is set via a kernel config option. 803 Value can be changed at runtime via 804 /sys/fs/selinux/checkreqprot. 805 Setting checkreqprot to 1 is deprecated. 806 807 cio_ignore= [S390] 808 See Documentation/arch/s390/common_io.rst for details. 809 810 clearcpuid=X[,X...] [X86] 811 Disable CPUID feature X for the kernel. See 812 arch/x86/include/asm/cpufeatures.h for the valid bit 813 numbers X. Note the Linux-specific bits are not necessarily 814 stable over kernel options, but the vendor-specific 815 ones should be. 816 X can also be a string as appearing in the flags: line 817 in /proc/cpuinfo which does not have the above 818 instability issue. However, not all features have names 819 in /proc/cpuinfo. 820 Note that using this option will taint your kernel. 821 Also note that user programs calling CPUID directly 822 or using the feature without checking anything 823 will still see it. This just prevents it from 824 being used by the kernel or shown in /proc/cpuinfo. 825 Also note the kernel might malfunction if you disable 826 some critical bits. 827 828 clk_ignore_unused 829 [CLK] 830 Prevents the clock framework from automatically gating 831 clocks that have not been explicitly enabled by a Linux 832 device driver but are enabled in hardware at reset or 833 by the bootloader/firmware. Note that this does not 834 force such clocks to be always-on nor does it reserve 835 those clocks in any way. This parameter is useful for 836 debug and development, but should not be needed on a 837 platform with proper driver support. For more 838 information, see Documentation/driver-api/clk.rst. 839 840 clock= [BUGS=X86-32, HW] gettimeofday clocksource override. 841 [Deprecated] 842 Forces specified clocksource (if available) to be used 843 when calculating gettimeofday(). If specified 844 clocksource is not available, it defaults to PIT. 845 Format: { pit | tsc | cyclone | pmtmr } 846 847 clocksource= Override the default clocksource 848 Format: <string> 849 Override the default clocksource and use the clocksource 850 with the name specified. 851 Some clocksource names to choose from, depending on 852 the platform: 853 [all] jiffies (this is the base, fallback clocksource) 854 [ACPI] acpi_pm 855 [ARM] imx_timer1,OSTS,netx_timer,mpu_timer2, 856 pxa_timer,timer3,32k_counter,timer0_1 857 [X86-32] pit,hpet,tsc; 858 scx200_hrt on Geode; cyclone on IBM x440 859 [MIPS] MIPS 860 [PARISC] cr16 861 [S390] tod 862 [SH] SuperH 863 [SPARC64] tick 864 [X86-64] hpet,tsc 865 866 clocksource.arm_arch_timer.evtstrm= 867 [ARM,ARM64,EARLY] 868 Format: <bool> 869 Enable/disable the eventstream feature of the ARM 870 architected timer so that code using WFE-based polling 871 loops can be debugged more effectively on production 872 systems. 873 874 clocksource.verify_n_cpus= [KNL] 875 Limit the number of CPUs checked for clocksources 876 marked with CLOCK_SOURCE_VERIFY_PERCPU that 877 are marked unstable due to excessive skew. 878 A negative value says to check all CPUs, while 879 zero says not to check any. Values larger than 880 nr_cpu_ids are silently truncated to nr_cpu_ids. 881 The actual CPUs are chosen randomly, with 882 no replacement if the same CPU is chosen twice. 883 884 clocksource-wdtest.holdoff= [KNL] 885 Set the time in seconds that the clocksource 886 watchdog test waits before commencing its tests. 887 Defaults to zero when built as a module and to 888 10 seconds when built into the kernel. 889 890 cma=nn[MG]@[start[MG][-end[MG]]] 891 [KNL,CMA,EARLY] 892 Sets the size of kernel global memory area for 893 contiguous memory allocations and optionally the 894 placement constraint by the physical address range of 895 memory allocations. A value of 0 disables CMA 896 altogether. For more information, see 897 kernel/dma/contiguous.c 898 899 cma_pernuma=nn[MG] 900 [KNL,CMA,EARLY] 901 Sets the size of kernel per-numa memory area for 902 contiguous memory allocations. A value of 0 disables 903 per-numa CMA altogether. And If this option is not 904 specified, the default value is 0. 905 With per-numa CMA enabled, DMA users on node nid will 906 first try to allocate buffer from the pernuma area 907 which is located in node nid, if the allocation fails, 908 they will fallback to the global default memory area. 909 910 numa_cma=<node>:nn[MG][,<node>:nn[MG]] 911 [KNL,CMA,EARLY] 912 Sets the size of kernel numa memory area for 913 contiguous memory allocations. It will reserve CMA 914 area for the specified node. 915 916 With numa CMA enabled, DMA users on node nid will 917 first try to allocate buffer from the numa area 918 which is located in node nid, if the allocation fails, 919 they will fallback to the global default memory area. 920 921 cmo_free_hint= [PPC] Format: { yes | no } 922 Specify whether pages are marked as being inactive 923 when they are freed. This is used in CMO environments 924 to determine OS memory pressure for page stealing by 925 a hypervisor. 926 Default: yes 927 928 coherent_pool=nn[KMG] [ARM,KNL,EARLY] 929 Sets the size of memory pool for coherent, atomic dma 930 allocations, by default set to 256K. 931 932 com20020= [HW,NET] ARCnet - COM20020 chipset 933 Format: 934 <io>[,<irq>[,<nodeID>[,<backplane>[,<ckp>[,<timeout>]]]]] 935 936 com90io= [HW,NET] ARCnet - COM90xx chipset (IO-mapped buffers) 937 Format: <io>[,<irq>] 938 939 com90xx= [HW,NET] 940 ARCnet - COM90xx chipset (memory-mapped buffers) 941 Format: <io>[,<irq>[,<memstart>]] 942 943 condev= [HW,S390] console device 944 conmode= 945 946 con3215_drop= [S390,EARLY] 3215 console drop mode. 947 Format: y|n|Y|N|1|0 948 When set to true, drop data on the 3215 console when 949 the console buffer is full. In this case the 950 operator using a 3270 terminal emulator (for example 951 x3270) does not have to enter the clear key for the 952 console output to advance and the kernel to continue. 953 This leads to a much faster boot time when a 3270 954 terminal emulator is active. If no 3270 terminal 955 emulator is used, this parameter has no effect. 956 957 console= [KNL] Output console device and options. 958 959 tty<n> Use the virtual console device <n>. 960 961 ttyS<n>[,options] 962 ttyUSB0[,options] 963 Use the specified serial port. The options are of 964 the form "bbbbpnf", where "bbbb" is the baud rate, 965 "p" is parity ("n", "o", or "e"), "n" is number of 966 bits, and "f" is flow control ("r" for RTS or 967 omit it). Default is "9600n8". 968 969 See Documentation/admin-guide/serial-console.rst for more 970 information. See 971 Documentation/networking/netconsole.rst for an 972 alternative. 973 974 <DEVNAME>:<n>.<n>[,options] 975 Use the specified serial port on the serial core bus. 976 The addressing uses DEVNAME of the physical serial port 977 device, followed by the serial core controller instance, 978 and the serial port instance. The options are the same 979 as documented for the ttyS addressing above. 980 981 The mapping of the serial ports to the tty instances 982 can be viewed with: 983 984 $ ls -d /sys/bus/serial-base/devices/*:*.*/tty/* 985 /sys/bus/serial-base/devices/00:04:0.0/tty/ttyS0 986 987 In the above example, the console can be addressed with 988 console=00:04:0.0. Note that a console addressed this 989 way will only get added when the related device driver 990 is ready. The use of an earlycon parameter in addition to 991 the console may be desired for console output early on. 992 993 uart[8250],io,<addr>[,options] 994 uart[8250],mmio,<addr>[,options] 995 uart[8250],mmio16,<addr>[,options] 996 uart[8250],mmio32,<addr>[,options] 997 uart[8250],0x<addr>[,options] 998 Start an early, polled-mode console on the 8250/16550 999 UART at the specified I/O port or MMIO address, 1000 switching to the matching ttyS device later. 1001 MMIO inter-register address stride is either 8-bit 1002 (mmio), 16-bit (mmio16), or 32-bit (mmio32). 1003 If none of [io|mmio|mmio16|mmio32], <addr> is assumed 1004 to be equivalent to 'mmio'. 'options' are specified in 1005 the same format described for ttyS above; if unspecified, 1006 the h/w is not re-initialized. 1007 1008 hvc<n> Use the hypervisor console device <n>. This is for 1009 both Xen and PowerPC hypervisors. 1010 1011 { null | "" } 1012 Use to disable console output, i.e., to have kernel 1013 console messages discarded. 1014 This must be the only console= parameter used on the 1015 kernel command line. 1016 1017 If the device connected to the port is not a TTY but a braille 1018 device, prepend "brl," before the device type, for instance 1019 console=brl,ttyS0 1020 For now, only VisioBraille is supported. 1021 1022 console_msg_format= 1023 [KNL] Change console messages format 1024 default 1025 By default we print messages on consoles in 1026 "[time stamp] text\n" format (time stamp may not be 1027 printed, depending on CONFIG_PRINTK_TIME or 1028 `printk_time' param). 1029 syslog 1030 Switch to syslog format: "<%u>[time stamp] text\n" 1031 IOW, each message will have a facility and loglevel 1032 prefix. The format is similar to one used by syslog() 1033 syscall, or to executing "dmesg -S --raw" or to reading 1034 from /proc/kmsg. 1035 1036 consoleblank= [KNL] The console blank (screen saver) timeout in 1037 seconds. A value of 0 disables the blank timer. 1038 Defaults to 0. 1039 1040 coredump_filter= 1041 [KNL] Change the default value for 1042 /proc/<pid>/coredump_filter. 1043 See also Documentation/filesystems/proc.rst. 1044 1045 coresight_cpu_debug.enable 1046 [ARM,ARM64] 1047 Format: <bool> 1048 Enable/disable the CPU sampling based debugging. 1049 0: default value, disable debugging 1050 1: enable debugging at boot time 1051 1052 cpcihp_generic= [HW,PCI] Generic port I/O CompactPCI driver 1053 Format: 1054 <first_slot>,<last_slot>,<port>,<enum_bit>[,<debug>] 1055 1056 cpuidle.off=1 [CPU_IDLE] 1057 disable the cpuidle sub-system 1058 1059 cpuidle.governor= 1060 [CPU_IDLE] Name of the cpuidle governor to use. 1061 1062 cpufreq.off=1 [CPU_FREQ] 1063 disable the cpufreq sub-system 1064 1065 cpufreq.default_governor= 1066 [CPU_FREQ] Name of the default cpufreq governor or 1067 policy to use. This governor must be registered in the 1068 kernel before the cpufreq driver probes. 1069 1070 cpu_init_udelay=N 1071 [X86,EARLY] Delay for N microsec between assert and de-assert 1072 of APIC INIT to start processors. This delay occurs 1073 on every CPU online, such as boot, and resume from suspend. 1074 Default: 10000 1075 1076 cpuhp.parallel= 1077 [SMP] Enable/disable parallel bringup of secondary CPUs 1078 Format: <bool> 1079 Default is enabled if CONFIG_HOTPLUG_PARALLEL=y. Otherwise 1080 the parameter has no effect. 1081 1082 crash_kexec_post_notifiers 1083 Only jump to kdump kernel after running the panic 1084 notifiers and dumping kmsg. This option increases 1085 the risks of a kdump failure, since some panic 1086 notifiers can make the crashed kernel more unstable. 1087 In configurations where kdump may not be reliable, 1088 running the panic notifiers could allow collecting 1089 more data on dmesg, like stack traces from other CPUS 1090 or extra data dumped by panic_print. Note that some 1091 configurations enable this option unconditionally, 1092 like Hyper-V, PowerPC (fadump) and AMD SEV-SNP. 1093 1094 crashkernel=size[KMG][@offset[KMG]] 1095 [KNL,EARLY] Using kexec, Linux can switch to a 'crash kernel' 1096 upon panic. This parameter reserves the physical 1097 memory region [offset, offset + size] for that kernel 1098 image. If '@offset' is omitted, then a suitable offset 1099 is selected automatically. 1100 [KNL, X86-64, ARM64, RISCV, LoongArch] Select a region 1101 under 4G first, and fall back to reserve region above 1102 4G when '@offset' hasn't been specified. 1103 See Documentation/admin-guide/kdump/kdump.rst for further details. 1104 1105 crashkernel=range1:size1[,range2:size2,...][@offset] 1106 [KNL] Same as above, but depends on the memory 1107 in the running system. The syntax of range is 1108 start-[end] where start and end are both 1109 a memory unit (amount[KMG]). See also 1110 Documentation/admin-guide/kdump/kdump.rst for an example. 1111 1112 crashkernel=size[KMG],high 1113 [KNL, X86-64, ARM64, RISCV, LoongArch] range could be 1114 above 4G. 1115 Allow kernel to allocate physical memory region from top, 1116 so could be above 4G if system have more than 4G ram 1117 installed. Otherwise memory region will be allocated 1118 below 4G, if available. 1119 It will be ignored if crashkernel=X is specified. 1120 crashkernel=size[KMG],low 1121 [KNL, X86-64, ARM64, RISCV, LoongArch] range under 4G. 1122 When crashkernel=X,high is passed, kernel could allocate 1123 physical memory region above 4G, that cause second kernel 1124 crash on system that require some amount of low memory, 1125 e.g. swiotlb requires at least 64M+32K low memory, also 1126 enough extra low memory is needed to make sure DMA buffers 1127 for 32-bit devices won't run out. Kernel would try to allocate 1128 default size of memory below 4G automatically. The default 1129 size is platform dependent. 1130 --> x86: max(swiotlb_size_or_default() + 8MiB, 256MiB) 1131 --> arm64: 128MiB 1132 --> riscv: 128MiB 1133 --> loongarch: 128MiB 1134 This one lets the user specify own low range under 4G 1135 for second kernel instead. 1136 0: to disable low allocation. 1137 It will be ignored when crashkernel=X,high is not used 1138 or memory reserved is below 4G. 1139 crashkernel=size[KMG],cma 1140 [KNL, X86, ppc] Reserve additional crash kernel memory from 1141 CMA. This reservation is usable by the first system's 1142 userspace memory and kernel movable allocations (memory 1143 balloon, zswap). Pages allocated from this memory range 1144 will not be included in the vmcore so this should not 1145 be used if dumping of userspace memory is intended and 1146 it has to be expected that some movable kernel pages 1147 may be missing from the dump. 1148 1149 A standard crashkernel reservation, as described above, 1150 is still needed to hold the crash kernel and initrd. 1151 1152 This option increases the risk of a kdump failure: DMA 1153 transfers configured by the first kernel may end up 1154 corrupting the second kernel's memory. 1155 1156 This reservation method is intended for systems that 1157 can't afford to sacrifice enough memory for standard 1158 crashkernel reservation and where less reliable and 1159 possibly incomplete kdump is preferable to no kdump at 1160 all. 1161 1162 cryptomgr.notests 1163 [KNL] Disable crypto self-tests 1164 1165 cs89x0_dma= [HW,NET] 1166 Format: <dma> 1167 1168 cs89x0_media= [HW,NET] 1169 Format: { rj45 | aui | bnc } 1170 1171 csdlock_debug= [KNL] Enable or disable debug add-ons of cross-CPU 1172 function call handling. When switched on, 1173 additional debug data is printed to the console 1174 in case a hanging CPU is detected, and that 1175 CPU is pinged again in order to try to resolve 1176 the hang situation. The default value of this 1177 option depends on the CSD_LOCK_WAIT_DEBUG_DEFAULT 1178 Kconfig option. 1179 1180 dasd= [HW,NET] 1181 See header of drivers/s390/block/dasd_devmap.c. 1182 1183 db9.dev[2|3]= [HW,JOY] Multisystem joystick support via parallel port 1184 (one device per port) 1185 Format: <port#>,<type> 1186 See also Documentation/input/devices/joystick-parport.rst 1187 1188 debug [KNL,EARLY] Enable kernel debugging (events log level). 1189 1190 debug_boot_weak_hash 1191 [KNL,EARLY] Enable printing [hashed] pointers early in the 1192 boot sequence. If enabled, we use a weak hash instead 1193 of siphash to hash pointers. Use this option if you are 1194 seeing instances of '(___ptrval___)') and need to see a 1195 value (hashed pointer) instead. Cryptographically 1196 insecure, please do not use on production kernels. 1197 1198 debug_locks_verbose= 1199 [KNL] verbose locking self-tests 1200 Format: <int> 1201 Print debugging info while doing the locking API 1202 self-tests. 1203 Bitmask for the various LOCKTYPE_ tests. Defaults to 0 1204 (no extra messages), setting it to -1 (all bits set) 1205 will print _a_lot_ more information - normally only 1206 useful to lockdep developers. 1207 1208 debug_objects [KNL,EARLY] Enable object debugging 1209 1210 debug_guardpage_minorder= 1211 [KNL,EARLY] When CONFIG_DEBUG_PAGEALLOC is set, this 1212 parameter allows control of the order of pages that will 1213 be intentionally kept free (and hence protected) by the 1214 buddy allocator. Bigger value increase the probability 1215 of catching random memory corruption, but reduce the 1216 amount of memory for normal system use. The maximum 1217 possible value is MAX_PAGE_ORDER/2. Setting this 1218 parameter to 1 or 2 should be enough to identify most 1219 random memory corruption problems caused by bugs in 1220 kernel or driver code when a CPU writes to (or reads 1221 from) a random memory location. Note that there exists 1222 a class of memory corruptions problems caused by buggy 1223 H/W or F/W or by drivers badly programming DMA 1224 (basically when memory is written at bus level and the 1225 CPU MMU is bypassed) which are not detectable by 1226 CONFIG_DEBUG_PAGEALLOC, hence this option will not 1227 help tracking down these problems. 1228 1229 debug_pagealloc= 1230 [KNL,EARLY] When CONFIG_DEBUG_PAGEALLOC is set, this parameter 1231 enables the feature at boot time. By default, it is 1232 disabled and the system will work mostly the same as a 1233 kernel built without CONFIG_DEBUG_PAGEALLOC. 1234 Note: to get most of debug_pagealloc error reports, it's 1235 useful to also enable the page_owner functionality. 1236 on: enable the feature 1237 1238 debugfs= [KNL,EARLY] This parameter enables what is exposed to 1239 userspace and debugfs internal clients. 1240 Format: { on, off } 1241 on: All functions are enabled. 1242 off: Filesystem is not registered and clients 1243 get a -EPERM as result when trying to register files 1244 or directories within debugfs. 1245 This is equivalent of the runtime functionality if 1246 debugfs was not enabled in the kernel at all. 1247 Default value is set in build-time with a kernel configuration. 1248 1249 debugpat [X86] Enable PAT debugging 1250 1251 default_hugepagesz= 1252 [HW] The size of the default HugeTLB page. This is 1253 the size represented by the legacy /proc/ hugepages 1254 APIs. In addition, this is the default hugetlb size 1255 used for shmget(), mmap() and mounting hugetlbfs 1256 filesystems. If not specified, defaults to the 1257 architecture's default huge page size. Huge page 1258 sizes are architecture dependent. See also 1259 Documentation/admin-guide/mm/hugetlbpage.rst. 1260 Format: size[KMG] 1261 1262 deferred_probe_timeout= 1263 [KNL] Debugging option to set a timeout in seconds for 1264 deferred probe to give up waiting on dependencies to 1265 probe. Only specific dependencies (subsystems or 1266 drivers) that have opted in will be ignored. A timeout 1267 of 0 will timeout at the end of initcalls. If the time 1268 out hasn't expired, it'll be restarted by each 1269 successful driver registration. This option will also 1270 dump out devices still on the deferred probe list after 1271 retrying. 1272 1273 delayacct [KNL] Enable per-task delay accounting 1274 1275 dell_smm_hwmon.ignore_dmi= 1276 [HW] Continue probing hardware even if DMI data 1277 indicates that the driver is running on unsupported 1278 hardware. 1279 1280 dell_smm_hwmon.force= 1281 [HW] Activate driver even if SMM BIOS signature does 1282 not match list of supported models and enable otherwise 1283 blacklisted features. 1284 1285 dell_smm_hwmon.power_status= 1286 [HW] Report power status in /proc/i8k 1287 (disabled by default). 1288 1289 dell_smm_hwmon.restricted= 1290 [HW] Allow controlling fans only if SYS_ADMIN 1291 capability is set. 1292 1293 dell_smm_hwmon.fan_mult= 1294 [HW] Factor to multiply fan speed with. 1295 1296 dell_smm_hwmon.fan_max= 1297 [HW] Maximum configurable fan speed. 1298 1299 dfltcc= [HW,S390] 1300 Format: { on | off | def_only | inf_only | always } 1301 on: s390 zlib hardware support for compression on 1302 level 1 and decompression (default) 1303 off: No s390 zlib hardware support 1304 def_only: s390 zlib hardware support for deflate 1305 only (compression on level 1) 1306 inf_only: s390 zlib hardware support for inflate 1307 only (decompression) 1308 always: Same as 'on' but ignores the selected compression 1309 level always using hardware support (used for debugging) 1310 1311 dhash_entries= [KNL] 1312 Set number of hash buckets for dentry cache. 1313 1314 disable_1tb_segments [PPC,EARLY] 1315 Disables the use of 1TB hash page table segments. This 1316 causes the kernel to fall back to 256MB segments which 1317 can be useful when debugging issues that require an SLB 1318 miss to occur. 1319 1320 disable= [IPV6] 1321 See Documentation/networking/ipv6.rst. 1322 1323 disable_radix [PPC,EARLY] 1324 Disable RADIX MMU mode on POWER9 1325 1326 disable_tlbie [PPC] 1327 Disable TLBIE instruction. Currently does not work 1328 with KVM, with HASH MMU, or with coherent accelerators. 1329 1330 disable_ddw [PPC/PSERIES,EARLY] 1331 Disable Dynamic DMA Window support. Use this 1332 to workaround buggy firmware. 1333 1334 disable_ipv6= [IPV6] 1335 See Documentation/networking/ipv6.rst. 1336 1337 disable_mtrr_cleanup [X86,EARLY] 1338 The kernel tries to adjust MTRR layout from continuous 1339 to discrete, to make X server driver able to add WB 1340 entry later. This parameter disables that. 1341 1342 disable_mtrr_trim [X86, Intel and AMD only,EARLY] 1343 By default the kernel will trim any uncacheable 1344 memory out of your available memory pool based on 1345 MTRR settings. This parameter disables that behavior, 1346 possibly causing your machine to run very slowly. 1347 1348 disable_timer_pin_1 [X86,EARLY] 1349 Disable PIN 1 of APIC timer 1350 Can be useful to work around chipset bugs. 1351 1352 dis_ucode_ldr [X86] Disable the microcode loader. 1353 1354 dma_debug=off If the kernel is compiled with DMA_API_DEBUG support, 1355 this option disables the debugging code at boot. 1356 1357 dma_debug_entries=<number> 1358 This option allows to tune the number of preallocated 1359 entries for DMA-API debugging code. One entry is 1360 required per DMA-API allocation. Use this if the 1361 DMA-API debugging code disables itself because the 1362 architectural default is too low. 1363 1364 dma_debug_driver=<driver_name> 1365 With this option the DMA-API debugging driver 1366 filter feature can be enabled at boot time. Just 1367 pass the driver to filter for as the parameter. 1368 The filter can be disabled or changed to another 1369 driver later using sysfs. 1370 1371 reg_file_data_sampling= 1372 [X86] Controls mitigation for Register File Data 1373 Sampling (RFDS) vulnerability. RFDS is a CPU 1374 vulnerability which may allow userspace to infer 1375 kernel data values previously stored in floating point 1376 registers, vector registers, or integer registers. 1377 RFDS only affects Intel Atom processors. 1378 1379 on: Turns ON the mitigation. 1380 off: Turns OFF the mitigation. 1381 1382 This parameter overrides the compile time default set 1383 by CONFIG_MITIGATION_RFDS. Mitigation cannot be 1384 disabled when other VERW based mitigations (like MDS) 1385 are enabled. In order to disable RFDS mitigation all 1386 VERW based mitigations need to be disabled. 1387 1388 For details see: 1389 Documentation/admin-guide/hw-vuln/reg-file-data-sampling.rst 1390 1391 dm_verity.keyring_unsealed= 1392 [KNL] When set to 1, leave the dm-verity keyring 1393 unsealed after initialization so userspace can 1394 provision keys. Once the keyring is restricted 1395 it becomes active and is searched during signature 1396 verification. 1397 1398 driver_async_probe= [KNL] 1399 List of driver names to be probed asynchronously. * 1400 matches with all driver names. If * is specified, the 1401 rest of the listed driver names are those that will NOT 1402 match the *. 1403 Format: <driver_name1>,<driver_name2>... 1404 1405 drm.edid_firmware=[<connector>:]<file>[,[<connector>:]<file>] 1406 Broken monitors, graphic adapters, KVMs and EDIDless 1407 panels may send no or incorrect EDID data sets. 1408 This parameter allows to specify an EDID data sets 1409 in the /lib/firmware directory that are used instead. 1410 An EDID data set will only be used for a particular 1411 connector, if its name and a colon are prepended to 1412 the EDID name. Each connector may use a unique EDID 1413 data set by separating the files with a comma. An EDID 1414 data set with no connector name will be used for 1415 any connectors not explicitly specified. 1416 1417 dscc4.setup= [NET] 1418 1419 dt_cpu_ftrs= [PPC,EARLY] 1420 Format: {"off" | "known"} 1421 Control how the dt_cpu_ftrs device-tree binding is 1422 used for CPU feature discovery and setup (if it 1423 exists). 1424 off: Do not use it, fall back to legacy cpu table. 1425 known: Do not pass through unknown features to guests 1426 or userspace, only those that the kernel is aware of. 1427 1428 dump_apple_properties [X86] 1429 Dump name and content of EFI device properties on 1430 x86 Macs. Useful for driver authors to determine 1431 what data is available or for reverse-engineering. 1432 1433 dyndbg[="val"] [KNL,DYNAMIC_DEBUG] 1434 <module>.dyndbg[="val"] 1435 Enable debug messages at boot time. See 1436 Documentation/admin-guide/dynamic-debug-howto.rst 1437 for details. 1438 1439 early_ioremap_debug [KNL,EARLY] 1440 Enable debug messages in early_ioremap support. This 1441 is useful for tracking down temporary early mappings 1442 which are not unmapped. 1443 1444 earlycon= [KNL,EARLY] Output early console device and options. 1445 1446 When used with no options, the early console is 1447 determined by stdout-path property in device tree's 1448 chosen node or the ACPI SPCR table if supported by 1449 the platform. 1450 1451 cdns,<addr>[,options] 1452 Start an early, polled-mode console on a Cadence 1453 (xuartps) serial port at the specified address. Only 1454 supported option is baud rate. If baud rate is not 1455 specified, the serial port must already be setup and 1456 configured. 1457 1458 uart[8250],io,<addr>[,options[,uartclk]] 1459 uart[8250],mmio,<addr>[,options[,uartclk]] 1460 uart[8250],mmio32,<addr>[,options[,uartclk]] 1461 uart[8250],mmio32be,<addr>[,options[,uartclk]] 1462 uart[8250],0x<addr>[,options] 1463 Start an early, polled-mode console on the 8250/16550 1464 UART at the specified I/O port or MMIO address. 1465 MMIO inter-register address stride is either 8-bit 1466 (mmio) or 32-bit (mmio32 or mmio32be). 1467 If none of [io|mmio|mmio32|mmio32be], <addr> is assumed 1468 to be equivalent to 'mmio'. 'options' are specified 1469 in the same format described for "console=ttyS<n>"; if 1470 unspecified, the h/w is not initialized. 'uartclk' is 1471 the uart clock frequency; if unspecified, it is set 1472 to 'BASE_BAUD' * 16. 1473 1474 pl011,<addr> 1475 pl011,mmio32,<addr> 1476 Start an early, polled-mode console on a pl011 serial 1477 port at the specified address. The pl011 serial port 1478 must already be setup and configured. Options are not 1479 yet supported. If 'mmio32' is specified, then only 1480 the driver will use only 32-bit accessors to read/write 1481 the device registers. 1482 1483 liteuart,<addr> 1484 Start an early console on a litex serial port at the 1485 specified address. The serial port must already be 1486 setup and configured. Options are not yet supported. 1487 1488 meson,<addr> 1489 Start an early, polled-mode console on a meson serial 1490 port at the specified address. The serial port must 1491 already be setup and configured. Options are not yet 1492 supported. 1493 1494 msm_serial,<addr> 1495 Start an early, polled-mode console on an msm serial 1496 port at the specified address. The serial port 1497 must already be setup and configured. Options are not 1498 yet supported. 1499 1500 msm_serial_dm,<addr> 1501 Start an early, polled-mode console on an msm serial 1502 dm port at the specified address. The serial port 1503 must already be setup and configured. Options are not 1504 yet supported. 1505 1506 owl,<addr> 1507 Start an early, polled-mode console on a serial port 1508 of an Actions Semi SoC, such as S500 or S900, at the 1509 specified address. The serial port must already be 1510 setup and configured. Options are not yet supported. 1511 1512 rda,<addr> 1513 Start an early, polled-mode console on a serial port 1514 of an RDA Micro SoC, such as RDA8810PL, at the 1515 specified address. The serial port must already be 1516 setup and configured. Options are not yet supported. 1517 1518 sbi 1519 Use RISC-V SBI (Supervisor Binary Interface) for early 1520 console. 1521 1522 smh Use ARM semihosting calls for early console. 1523 1524 s3c2410,<addr> 1525 s3c2412,<addr> 1526 s3c2440,<addr> 1527 s3c6400,<addr> 1528 s5pv210,<addr> 1529 exynos4210,<addr> 1530 Use early console provided by serial driver available 1531 on Samsung SoCs, requires selecting proper type and 1532 a correct base address of the selected UART port. The 1533 serial port must already be setup and configured. 1534 Options are not yet supported. 1535 1536 lantiq,<addr> 1537 Start an early, polled-mode console on a lantiq serial 1538 (lqasc) port at the specified address. The serial port 1539 must already be setup and configured. Options are not 1540 yet supported. 1541 1542 lpuart,<addr> 1543 lpuart32,<addr> 1544 Use early console provided by Freescale LP UART driver 1545 found on Freescale Vybrid and QorIQ LS1021A processors. 1546 A valid base address must be provided, and the serial 1547 port must already be setup and configured. 1548 1549 ec_imx21,<addr> 1550 ec_imx6q,<addr> 1551 Start an early, polled-mode, output-only console on the 1552 Freescale i.MX UART at the specified address. The UART 1553 must already be setup and configured. 1554 1555 ar3700_uart,<addr> 1556 Start an early, polled-mode console on the 1557 Armada 3700 serial port at the specified 1558 address. The serial port must already be setup 1559 and configured. Options are not yet supported. 1560 1561 qcom_geni,<addr> 1562 Start an early, polled-mode console on a Qualcomm 1563 Generic Interface (GENI) based serial port at the 1564 specified address. The serial port must already be 1565 setup and configured. Options are not yet supported. 1566 1567 efifb,[options] 1568 Start an early, unaccelerated console on the EFI 1569 memory mapped framebuffer (if available). On cache 1570 coherent non-x86 systems that use system memory for 1571 the framebuffer, pass the 'ram' option so that it is 1572 mapped with the correct attributes. 1573 1574 linflex,<addr> 1575 Use early console provided by Freescale LINFlexD UART 1576 serial driver for NXP S32V234 SoCs. A valid base 1577 address must be provided, and the serial port must 1578 already be setup and configured. 1579 1580 earlyprintk= [X86,SH,ARM,M68k,S390,UM,EARLY] 1581 earlyprintk=vga 1582 earlyprintk=sclp 1583 earlyprintk=xen 1584 earlyprintk=serial[,ttySn[,baudrate]] 1585 earlyprintk=serial[,0x...[,baudrate]] 1586 earlyprintk=ttySn[,baudrate] 1587 earlyprintk=dbgp[debugController#] 1588 earlyprintk=mmio32,membase[,{nocfg|baudrate}] 1589 earlyprintk=pciserial[,force],bus:device.function[,{nocfg|baudrate}] 1590 earlyprintk=xdbc[xhciController#] 1591 earlyprintk=bios 1592 1593 earlyprintk is useful when the kernel crashes before 1594 the normal console is initialized. It is not enabled by 1595 default because it has some cosmetic problems. 1596 1597 Use "nocfg" to skip UART configuration, assume 1598 BIOS/firmware has configured UART correctly. 1599 1600 Append ",keep" to not disable it when the real console 1601 takes over. 1602 1603 Only one of vga, serial, or usb debug port can 1604 be used at a time. 1605 1606 Currently only ttyS0 and ttyS1 may be specified by 1607 name. Other I/O ports may be explicitly specified 1608 on some architectures (x86 and arm at least) by 1609 replacing ttySn with an I/O port address, like this: 1610 earlyprintk=serial,0x1008,115200 1611 You can find the port for a given device in 1612 /proc/tty/driver/serial: 1613 2: uart:ST16650V2 port:00001008 irq:18 ... 1614 1615 Interaction with the standard serial driver is not 1616 very good. 1617 1618 The VGA output is eventually overwritten by 1619 the real console. 1620 1621 The xen option can only be used in Xen domains. 1622 1623 The sclp output can only be used on s390. 1624 1625 The bios output can only be used on SuperH. 1626 1627 The optional "force" to "pciserial" enables use of a 1628 PCI device even when its classcode is not of the 1629 UART class. 1630 1631 edac_report= [HW,EDAC] Control how to report EDAC event 1632 Format: {"on" | "off" | "force"} 1633 on: enable EDAC to report H/W event. May be overridden 1634 by other higher priority error reporting module. 1635 off: disable H/W event reporting through EDAC. 1636 force: enforce the use of EDAC to report H/W event. 1637 default: on. 1638 1639 edd= [EDD] 1640 Format: {"off" | "on" | "skip[mbr]"} 1641 1642 efi= [EFI,EARLY] 1643 Format: { "debug", "disable_early_pci_dma", 1644 "nochunk", "noruntime", "nosoftreserve", 1645 "novamap", "no_disable_early_pci_dma" } 1646 debug: enable misc debug output. 1647 disable_early_pci_dma: disable the busmaster bit on all 1648 PCI bridges while in the EFI boot stub. 1649 nochunk: disable reading files in "chunks" in the EFI 1650 boot stub, as chunking can cause problems with some 1651 firmware implementations. 1652 noruntime : disable EFI runtime services support 1653 nosoftreserve: The EFI_MEMORY_SP (Specific Purpose) 1654 attribute may cause the kernel to reserve the 1655 memory range for a memory mapping driver to 1656 claim. Specify efi=nosoftreserve to disable this 1657 reservation and treat the memory by its base type 1658 (i.e. EFI_CONVENTIONAL_MEMORY / "System RAM"). 1659 novamap: do not call SetVirtualAddressMap(). 1660 no_disable_early_pci_dma: Leave the busmaster bit set 1661 on all PCI bridges while in the EFI boot stub 1662 1663 efi_no_storage_paranoia [EFI,X86,EARLY] 1664 Using this parameter you can use more than 50% of 1665 your efi variable storage. Use this parameter only if 1666 you are really sure that your UEFI does sane gc and 1667 fulfills the spec otherwise your board may brick. 1668 1669 efivar_ssdt= [EFI; X86] Name of an EFI variable that contains an SSDT 1670 that is to be dynamically loaded by Linux. If there are 1671 multiple variables with the same name but with different 1672 vendor GUIDs, all of them will be loaded. See 1673 Documentation/admin-guide/acpi/ssdt-overlays.rst for details. 1674 1675 1676 eisa_irq_edge= [PARISC,HW] 1677 See header of drivers/parisc/eisa.c. 1678 1679 ekgdboc= [X86,KGDB,EARLY] Allow early kernel console debugging 1680 Format: ekgdboc=kbd 1681 1682 This is designed to be used in conjunction with 1683 the boot argument: earlyprintk=vga 1684 1685 This parameter works in place of the kgdboc parameter 1686 but can only be used if the backing tty is available 1687 very early in the boot process. For early debugging 1688 via a serial port see kgdboc_earlycon instead. 1689 1690 elanfreq= [X86-32] 1691 See comment before function elanfreq_setup() in 1692 arch/x86/kernel/cpu/cpufreq/elanfreq.c. 1693 1694 elfcorehdr=[size[KMG]@]offset[KMG] [PPC,SH,X86,S390,EARLY] 1695 Specifies physical address of start of kernel core 1696 image elf header and optionally the size. Generally 1697 kexec loader will pass this option to capture kernel. 1698 See Documentation/admin-guide/kdump/kdump.rst for details. 1699 1700 enable_mtrr_cleanup [X86,EARLY] 1701 The kernel tries to adjust MTRR layout from continuous 1702 to discrete, to make X server driver able to add WB 1703 entry later. This parameter enables that. 1704 1705 enable_timer_pin_1 [X86] 1706 Enable PIN 1 of APIC timer 1707 Can be useful to work around chipset bugs 1708 (in particular on some ATI chipsets). 1709 The kernel tries to set a reasonable default. 1710 1711 enforcing= [SELINUX] Set initial enforcing status. 1712 Format: {"0" | "1"} 1713 See security/selinux/Kconfig help text. 1714 0 -- permissive (log only, no denials). 1715 1 -- enforcing (deny and log). 1716 Default value is 0. 1717 Value can be changed at runtime via 1718 /sys/fs/selinux/enforce. 1719 1720 erst_disable [ACPI] 1721 Disable Error Record Serialization Table (ERST) 1722 support. 1723 1724 ether= [HW,NET] Ethernet cards parameters 1725 This option is obsoleted by the "netdev=" option, which 1726 has equivalent usage. See its documentation for details. 1727 1728 evm= [EVM] 1729 Format: { "fix" } 1730 Permit 'security.evm' to be updated regardless of 1731 current integrity status. 1732 1733 early_page_ext [KNL,EARLY] Enforces page_ext initialization to earlier 1734 stages so cover more early boot allocations. 1735 Please note that as side effect some optimizations 1736 might be disabled to achieve that (e.g. parallelized 1737 memory initialization is disabled) so the boot process 1738 might take longer, especially on systems with a lot of 1739 memory. Available with CONFIG_PAGE_EXTENSION=y. 1740 1741 failslab= 1742 fail_usercopy= 1743 fail_page_alloc= 1744 fail_skb_realloc= 1745 fail_make_request=[KNL] 1746 General fault injection mechanism. 1747 Format: <interval>,<probability>,<space>,<times> 1748 See also Documentation/fault-injection/. 1749 1750 fb_tunnels= [NET] 1751 Format: { initns | none } 1752 See Documentation/admin-guide/sysctl/net.rst for 1753 fb_tunnels_only_for_init_ns 1754 1755 floppy= [HW] 1756 See Documentation/admin-guide/blockdev/floppy.rst. 1757 1758 forcepae [X86-32] 1759 Forcefully enable Physical Address Extension (PAE). 1760 Many Pentium M systems disable PAE but may have a 1761 functionally usable PAE implementation. 1762 Warning: use of this parameter will taint the kernel 1763 and may cause unknown problems. 1764 1765 fred= [X86-64] 1766 Enable/disable Flexible Return and Event Delivery. 1767 Format: { on | off } 1768 on: enable FRED when it's present, the default setting. 1769 off: disable FRED. 1770 1771 ftrace=[tracer] 1772 [FTRACE] will set and start the specified tracer 1773 as early as possible in order to facilitate early 1774 boot debugging. 1775 1776 ftrace_boot_snapshot 1777 [FTRACE] On boot up, a snapshot will be taken of the 1778 ftrace ring buffer that can be read at: 1779 /sys/kernel/tracing/snapshot. 1780 This is useful if you need tracing information from kernel 1781 boot up that is likely to be overridden by user space 1782 start up functionality. 1783 1784 Optionally, the snapshot can also be defined for a tracing 1785 instance that was created by the trace_instance= command 1786 line parameter. 1787 1788 trace_instance=foo,sched_switch ftrace_boot_snapshot=foo 1789 1790 The above will cause the "foo" tracing instance to trigger 1791 a snapshot at the end of boot up. 1792 1793 ftrace_dump_on_oops[=2(orig_cpu) | =<instance>][,<instance> | 1794 ,<instance>=2(orig_cpu)] 1795 [FTRACE] will dump the trace buffers on oops. 1796 If no parameter is passed, ftrace will dump global 1797 buffers of all CPUs, if you pass 2 or orig_cpu, it 1798 will dump only the buffer of the CPU that triggered 1799 the oops, or the specific instance will be dumped if 1800 its name is passed. Multiple instance dump is also 1801 supported, and instances are separated by commas. Each 1802 instance supports only dump on CPU that triggered the 1803 oops by passing 2 or orig_cpu to it. 1804 1805 ftrace_dump_on_oops=foo=orig_cpu 1806 1807 The above will dump only the buffer of "foo" instance 1808 on CPU that triggered the oops. 1809 1810 ftrace_dump_on_oops,foo,bar=orig_cpu 1811 1812 The above will dump global buffer on all CPUs, the 1813 buffer of "foo" instance on all CPUs and the buffer 1814 of "bar" instance on CPU that triggered the oops. 1815 1816 ftrace_filter=[function-list] 1817 [FTRACE] Limit the functions traced by the function 1818 tracer at boot up. function-list is a comma-separated 1819 list of functions. This list can be changed at run 1820 time by the set_ftrace_filter file in the debugfs 1821 tracing directory. 1822 1823 ftrace_notrace=[function-list] 1824 [FTRACE] Do not trace the functions specified in 1825 function-list. This list can be changed at run time 1826 by the set_ftrace_notrace file in the debugfs 1827 tracing directory. 1828 1829 ftrace_graph_filter=[function-list] 1830 [FTRACE] Limit the top level callers functions traced 1831 by the function graph tracer at boot up. 1832 function-list is a comma-separated list of functions 1833 that can be changed at run time by the 1834 set_graph_function file in the debugfs tracing directory. 1835 1836 ftrace_graph_notrace=[function-list] 1837 [FTRACE] Do not trace from the functions specified in 1838 function-list. This list is a comma-separated list of 1839 functions that can be changed at run time by the 1840 set_graph_notrace file in the debugfs tracing directory. 1841 1842 ftrace_graph_max_depth=<uint> 1843 [FTRACE] Used with the function graph tracer. This is 1844 the max depth it will trace into a function. This value 1845 can be changed at run time by the max_graph_depth file 1846 in the tracefs tracing directory. default: 0 (no limit) 1847 1848 fw_devlink= [KNL,EARLY] Create device links between consumer and supplier 1849 devices by scanning the firmware to infer the 1850 consumer/supplier relationships. This feature is 1851 especially useful when drivers are loaded as modules as 1852 it ensures proper ordering of tasks like device probing 1853 (suppliers first, then consumers), supplier boot state 1854 clean up (only after all consumers have probed), 1855 suspend/resume & runtime PM (consumers first, then 1856 suppliers). 1857 Format: { off | permissive | on | rpm } 1858 off -- Don't create device links from firmware info. 1859 permissive -- Create device links from firmware info 1860 but use it only for ordering boot state clean 1861 up (sync_state() calls). 1862 on -- Create device links from firmware info and use it 1863 to enforce probe and suspend/resume ordering. 1864 rpm -- Like "on", but also use to order runtime PM. 1865 1866 fw_devlink.strict=<bool> 1867 [KNL,EARLY] Treat all inferred dependencies as mandatory 1868 dependencies. This only applies for fw_devlink=on|rpm. 1869 Format: <bool> 1870 1871 fw_devlink.sync_state = 1872 [KNL,EARLY] When all devices that could probe have finished 1873 probing, this parameter controls what to do with 1874 devices that haven't yet received their sync_state() 1875 calls. 1876 Format: { strict | timeout } 1877 strict -- Default. Continue waiting on consumers to 1878 probe successfully. 1879 timeout -- Give up waiting on consumers and call 1880 sync_state() on any devices that haven't yet 1881 received their sync_state() calls after 1882 deferred_probe_timeout has expired or by 1883 late_initcall() if !CONFIG_MODULES. 1884 1885 gamecon.map[2|3]= 1886 [HW,JOY] Multisystem joystick and NES/SNES/PSX pad 1887 support via parallel port (up to 5 devices per port) 1888 Format: <port#>,<pad1>,<pad2>,<pad3>,<pad4>,<pad5> 1889 See also Documentation/input/devices/joystick-parport.rst 1890 1891 gamma= [HW,DRM] 1892 1893 gart_fix_e820= [X86-64,EARLY] disable the fix e820 for K8 GART 1894 Format: off | on 1895 default: on 1896 1897 gather_data_sampling= 1898 [X86,INTEL,EARLY] Control the Gather Data Sampling (GDS) 1899 mitigation. 1900 1901 Gather Data Sampling is a hardware vulnerability which 1902 allows unprivileged speculative access to data which was 1903 previously stored in vector registers. 1904 1905 This issue is mitigated by default in updated microcode. 1906 The mitigation may have a performance impact but can be 1907 disabled. On systems without the microcode mitigation 1908 disabling AVX serves as a mitigation. 1909 1910 force: Disable AVX to mitigate systems without 1911 microcode mitigation. No effect if the microcode 1912 mitigation is present. Known to cause crashes in 1913 userspace with buggy AVX enumeration. 1914 1915 off: Disable GDS mitigation. 1916 1917 gbpages [X86] Use GB pages for kernel direct mappings. 1918 1919 gcov_persist= [GCOV] When non-zero (default), profiling data for 1920 kernel modules is saved and remains accessible via 1921 debugfs, even when the module is unloaded/reloaded. 1922 When zero, profiling data is discarded and associated 1923 debugfs files are removed at module unload time. 1924 1925 goldfish [X86] Enable the goldfish android emulator platform. 1926 Don't use this when you are not running on the 1927 android emulator 1928 1929 gpio-mockup.gpio_mockup_ranges 1930 [HW] Sets the ranges of gpiochip of for this device. 1931 Format: <start1>,<end1>,<start2>,<end2>... 1932 gpio-mockup.gpio_mockup_named_lines 1933 [HW] Let the driver know GPIO lines should be named. 1934 1935 gpt [EFI] Forces disk with valid GPT signature but 1936 invalid Protective MBR to be treated as GPT. If the 1937 primary GPT is corrupted, it enables the backup/alternate 1938 GPT to be used instead. 1939 1940 grcan.enable0= [HW] Configuration of physical interface 0. Determines 1941 the "Enable 0" bit of the configuration register. 1942 Format: 0 | 1 1943 Default: 0 1944 grcan.enable1= [HW] Configuration of physical interface 1. Determines 1945 the "Enable 0" bit of the configuration register. 1946 Format: 0 | 1 1947 Default: 0 1948 grcan.select= [HW] Select which physical interface to use. 1949 Format: 0 | 1 1950 Default: 0 1951 grcan.txsize= [HW] Sets the size of the tx buffer. 1952 Format: <unsigned int> such that (txsize & ~0x1fffc0) == 0. 1953 Default: 1024 1954 grcan.rxsize= [HW] Sets the size of the rx buffer. 1955 Format: <unsigned int> such that (rxsize & ~0x1fffc0) == 0. 1956 Default: 1024 1957 1958 hardened_usercopy= 1959 [KNL] Under CONFIG_HARDENED_USERCOPY, whether 1960 hardening is enabled for this boot. Hardened 1961 usercopy checking is used to protect the kernel 1962 from reading or writing beyond known memory 1963 allocation boundaries as a proactive defense 1964 against bounds-checking flaws in the kernel's 1965 copy_to_user()/copy_from_user() interface. 1966 The default is determined by 1967 CONFIG_HARDENED_USERCOPY_DEFAULT_ON. 1968 on Perform hardened usercopy checks. 1969 off Disable hardened usercopy checks. 1970 1971 hardlockup_all_cpu_backtrace= 1972 [KNL] Should the hard-lockup detector generate 1973 backtraces on all cpus. 1974 Format: 0 | 1 1975 1976 hash_pointers= 1977 [KNL,EARLY] 1978 By default, when pointers are printed to the console 1979 or buffers via the %p format string, that pointer is 1980 "hashed", i.e. obscured by hashing the pointer value. 1981 This is a security feature that hides actual kernel 1982 addresses from unprivileged users, but it also makes 1983 debugging the kernel more difficult since unequal 1984 pointers can no longer be compared. The choices are: 1985 Format: { auto | always | never } 1986 Default: auto 1987 1988 auto - Hash pointers unless slab_debug is enabled. 1989 always - Always hash pointers (even if slab_debug is 1990 enabled). 1991 never - Never hash pointers. This option should only 1992 be specified when debugging the kernel. Do 1993 not use on production kernels. The boot 1994 param "no_hash_pointers" is an alias for 1995 this mode. 1996 1997 For controlling hashing dynamically at runtime, 1998 use the "kernel.kptr_restrict" sysctl instead. 1999 2000 hashdist= [KNL,NUMA] Large hashes allocated during boot 2001 are distributed across NUMA nodes. Defaults on 2002 for 64-bit NUMA, off otherwise. 2003 Format: 0 | 1 (for off | on) 2004 2005 hd= [EIDE] (E)IDE hard drive subsystem geometry 2006 Format: <cyl>,<head>,<sect> 2007 2008 hest_disable [ACPI] 2009 Disable Hardware Error Source Table (HEST) support; 2010 corresponding firmware-first mode error processing 2011 logic will be disabled. 2012 2013 hibernate= [HIBERNATION] 2014 noresume Don't check if there's a hibernation image 2015 present during boot. 2016 nocompress Don't compress/decompress hibernation images. 2017 no Disable hibernation and resume. 2018 protect_image Turn on image protection during restoration 2019 (that will set all pages holding image data 2020 during restoration read-only). 2021 2022 hibernate.compressor= [HIBERNATION] Compression algorithm to be 2023 used with hibernation. 2024 Format: { lzo | lz4 } 2025 Default: lzo 2026 2027 lzo: Select LZO compression algorithm to 2028 compress/decompress hibernation image. 2029 2030 lz4: Select LZ4 compression algorithm to 2031 compress/decompress hibernation image. 2032 2033 hibernate.pm_test_delay= 2034 [HIBERNATION] 2035 Sets the number of seconds to remain in a hibernation test 2036 mode before resuming the system (see 2037 /sys/power/pm_test). Only available when CONFIG_PM_DEBUG 2038 is set. Default value is 5. 2039 2040 hibernate_compression_threads= 2041 [HIBERNATION] 2042 Set the number of threads used for compressing or decompressing 2043 hibernation images. 2044 2045 Format: <integer> 2046 Default: 3 2047 Minimum: 1 2048 Example: hibernate_compression_threads=4 2049 2050 highmem=nn[KMG] [KNL,BOOT,EARLY] forces the highmem zone to have an exact 2051 size of <nn>. This works even on boxes that have no 2052 highmem otherwise. This also works to reduce highmem 2053 size on bigger boxes. 2054 2055 highres= [KNL] Enable/disable high resolution timer mode. 2056 Valid parameters: "on", "off" 2057 Default: "on" 2058 2059 hlt [BUGS=ARM,SH] 2060 2061 hostname= [KNL,EARLY] Set the hostname (aka UTS nodename). 2062 Format: <string> 2063 This allows setting the system's hostname during early 2064 startup. This sets the name returned by gethostname. 2065 Using this parameter to set the hostname makes it 2066 possible to ensure the hostname is correctly set before 2067 any userspace processes run, avoiding the possibility 2068 that a process may call gethostname before the hostname 2069 has been explicitly set, resulting in the calling 2070 process getting an incorrect result. The string must 2071 not exceed the maximum allowed hostname length (usually 2072 64 characters) and will be truncated otherwise. 2073 2074 hpet= [X86-32,HPET] option to control HPET usage 2075 Format: { enable (default) | disable | force | 2076 verbose } 2077 disable: disable HPET and use PIT instead 2078 force: allow force enabled of undocumented chips (ICH4, 2079 VIA, nVidia) 2080 verbose: show contents of HPET registers during setup 2081 2082 hpet_mmap= [X86, HPET_MMAP] Allow userspace to mmap HPET 2083 registers. Default set by CONFIG_HPET_MMAP_DEFAULT. 2084 2085 hugepages= [HW,EARLY] Number of HugeTLB pages to allocate at boot. 2086 If this follows hugepagesz (below), it specifies 2087 the number of pages of hugepagesz to be allocated. 2088 If this is the first HugeTLB parameter on the command 2089 line, it specifies the number of pages to allocate for 2090 the default huge page size. If using node format, the 2091 number of pages to allocate per-node can be specified. 2092 See also Documentation/admin-guide/mm/hugetlbpage.rst. 2093 Format: <integer> or (node format) 2094 <node>:<integer>[,<node>:<integer>] 2095 2096 hugepagesz= 2097 [HW,EARLY] The size of the HugeTLB pages. This is 2098 used in conjunction with hugepages (above) to 2099 allocate huge pages of a specific size at boot. The 2100 pair hugepagesz=X hugepages=Y can be specified once 2101 for each supported huge page size. Huge page sizes 2102 are architecture dependent. See also 2103 Documentation/admin-guide/mm/hugetlbpage.rst. 2104 Format: size[KMG] 2105 2106 hugepage_alloc_threads= 2107 [HW] The number of threads that should be used to 2108 allocate hugepages during boot. This option can be 2109 used to improve system bootup time when allocating 2110 a large amount of huge pages. 2111 The default value is 25% of the available hardware threads. 2112 2113 Note that this parameter only applies to non-gigantic huge pages. 2114 2115 hugetlb_cma= [HW,CMA,EARLY] The size of a CMA area used for allocation 2116 of gigantic hugepages. Or using node format, the size 2117 of a CMA area per node can be specified. 2118 Format: nn[KMGTPE] or (node format) 2119 <node>:nn[KMGTPE][,<node>:nn[KMGTPE]] 2120 2121 Reserve a CMA area of given size and allocate gigantic 2122 hugepages using the CMA allocator. If enabled, the 2123 boot-time allocation of gigantic hugepages is skipped. 2124 2125 hugetlb_cma_only= 2126 [HW,CMA,EARLY] When allocating new HugeTLB pages, only 2127 try to allocate from the CMA areas. 2128 2129 This option does nothing if hugetlb_cma= is not also 2130 specified. 2131 2132 hugetlb_free_vmemmap= 2133 [KNL] Requires CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP 2134 enabled. 2135 Control if HugeTLB Vmemmap Optimization (HVO) is enabled. 2136 Allows heavy hugetlb users to free up some more 2137 memory (7 * PAGE_SIZE for each 2MB hugetlb page). 2138 Format: { on | off (default) } 2139 2140 on: enable HVO 2141 off: disable HVO 2142 2143 Built with CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP_DEFAULT_ON=y, 2144 the default is on. 2145 2146 Note that the vmemmap pages may be allocated from the added 2147 memory block itself when memory_hotplug.memmap_on_memory is 2148 enabled, those vmemmap pages cannot be optimized even if this 2149 feature is enabled. Other vmemmap pages not allocated from 2150 the added memory block itself do not be affected. 2151 2152 hung_task_panic= 2153 [KNL] Number of hung tasks to trigger kernel panic. 2154 Format: <int> 2155 2156 When set to a non-zero value, a kernel panic will be triggered if 2157 the number of detected hung tasks reaches this value. 2158 2159 0: don't panic 2160 1: panic immediately on first hung task 2161 N: panic after N hung tasks are detected in a single scan 2162 2163 The default value is controlled by the 2164 CONFIG_BOOTPARAM_HUNG_TASK_PANIC build-time option. The value 2165 selected by this boot parameter can be changed later by the 2166 kernel.hung_task_panic sysctl. 2167 2168 hvc_iucv= [S390] Number of z/VM IUCV hypervisor console (HVC) 2169 terminal devices. Valid values: 0..8 2170 hvc_iucv_allow= [S390] Comma-separated list of z/VM user IDs. 2171 If specified, z/VM IUCV HVC accepts connections 2172 from listed z/VM user IDs only. 2173 2174 hv_nopvspin [X86,HYPER_V,EARLY] 2175 Disables the paravirt spinlock optimizations 2176 which allow the hypervisor to 'idle' the guest 2177 on lock contention. 2178 2179 hw_protection= [HW] 2180 Format: reboot | shutdown 2181 2182 Hardware protection action taken on critical events like 2183 overtemperature or imminent voltage loss. 2184 2185 i2c_bus= [HW] Override the default board specific I2C bus speed 2186 or register an additional I2C bus that is not 2187 registered from board initialization code. 2188 Format: 2189 <bus_id>,<clkrate> 2190 2191 i2c_touchscreen_props= [HW,ACPI,X86] 2192 Set device-properties for ACPI-enumerated I2C-attached 2193 touchscreen, to e.g. fix coordinates of upside-down 2194 mounted touchscreens. If you need this option please 2195 submit a drivers/platform/x86/touchscreen_dmi.c patch 2196 adding a DMI quirk for this. 2197 2198 Format: 2199 <ACPI_HW_ID>:<prop_name>=<val>[:prop_name=val][:...] 2200 Where <val> is one of: 2201 Omit "=<val>" entirely Set a boolean device-property 2202 Unsigned number Set a u32 device-property 2203 Anything else Set a string device-property 2204 2205 Examples (split over multiple lines): 2206 i2c_touchscreen_props=GDIX1001:touchscreen-inverted-x: 2207 touchscreen-inverted-y 2208 2209 i2c_touchscreen_props=MSSL1680:touchscreen-size-x=1920: 2210 touchscreen-size-y=1080:touchscreen-inverted-y: 2211 firmware-name=gsl1680-vendor-model.fw:silead,home-button 2212 2213 i8042.debug [HW] Toggle i8042 debug mode 2214 i8042.unmask_kbd_data 2215 [HW] Enable printing of interrupt data from the KBD port 2216 (disabled by default, and as a pre-condition 2217 requires that i8042.debug=1 be enabled) 2218 i8042.direct [HW] Put keyboard port into non-translated mode 2219 i8042.dumbkbd [HW] Pretend that controller can only read data from 2220 keyboard and cannot control its state 2221 (Don't attempt to blink the leds) 2222 i8042.noaux [HW] Don't check for auxiliary (== mouse) port 2223 i8042.nokbd [HW] Don't check/create keyboard port 2224 i8042.noloop [HW] Disable the AUX Loopback command while probing 2225 for the AUX port 2226 i8042.nomux [HW] Don't check presence of an active multiplexing 2227 controller 2228 i8042.nopnp [HW] Don't use ACPIPnP / PnPBIOS to discover KBD/AUX 2229 controllers 2230 i8042.notimeout [HW] Ignore timeout condition signalled by controller 2231 i8042.reset [HW] Reset the controller during init, cleanup and 2232 suspend-to-ram transitions, only during s2r 2233 transitions, or never reset 2234 Format: { 1 | Y | y | 0 | N | n } 2235 1, Y, y: always reset controller 2236 0, N, n: don't ever reset controller 2237 Default: only on s2r transitions on x86; most other 2238 architectures force reset to be always executed 2239 i8042.unlock [HW] Unlock (ignore) the keylock 2240 i8042.kbdreset [HW] Reset device connected to KBD port 2241 i8042.probe_defer 2242 [HW] Allow deferred probing upon i8042 probe errors 2243 2244 i810= [HW,DRM] 2245 2246 i915.invert_brightness= 2247 [DRM] Invert the sense of the variable that is used to 2248 set the brightness of the panel backlight. Normally a 2249 brightness value of 0 indicates backlight switched off, 2250 and the maximum of the brightness value sets the backlight 2251 to maximum brightness. If this parameter is set to 0 2252 (default) and the machine requires it, or this parameter 2253 is set to 1, a brightness value of 0 sets the backlight 2254 to maximum brightness, and the maximum of the brightness 2255 value switches the backlight off. 2256 -1 -- never invert brightness 2257 0 -- machine default 2258 1 -- force brightness inversion 2259 2260 ia32_emulation= [X86-64] 2261 Format: <bool> 2262 When true, allows loading 32-bit programs and executing 32-bit 2263 syscalls, essentially overriding IA32_EMULATION_DEFAULT_DISABLED at 2264 boot time. When false, unconditionally disables IA32 emulation. 2265 2266 icn= [HW,ISDN] 2267 Format: <io>[,<membase>[,<icn_id>[,<icn_id2>]]] 2268 2269 2270 idle= [X86,EARLY] 2271 Format: idle=poll, idle=halt, idle=nomwait 2272 2273 idle=poll: Don't do power saving in the idle loop 2274 using HLT, but poll for rescheduling event. This will 2275 make the CPUs eat a lot more power, but may be useful 2276 to get slightly better performance in multiprocessor 2277 benchmarks. It also makes some profiling using 2278 performance counters more accurate. Please note that 2279 on systems with MONITOR/MWAIT support (like Intel 2280 EM64T CPUs) this option has no performance advantage 2281 over the normal idle loop. It may also interact badly 2282 with hyperthreading. 2283 2284 idle=halt: Halt is forced to be used for CPU idle. 2285 In such case C2/C3 won't be used again. 2286 2287 idle=nomwait: Disable mwait for CPU C-states 2288 2289 idxd.sva= [HW] 2290 Format: <bool> 2291 Allow force disabling of Shared Virtual Memory (SVA) 2292 support for the idxd driver. By default it is set to 2293 true (1). 2294 2295 idxd.tc_override= [HW] 2296 Format: <bool> 2297 Allow override of default traffic class configuration 2298 for the device. By default it is set to false (0). 2299 2300 ieee754= [MIPS] Select IEEE Std 754 conformance mode 2301 Format: { strict | legacy | 2008 | relaxed | emulated } 2302 Default: strict 2303 2304 Choose which programs will be accepted for execution 2305 based on the IEEE 754 NaN encoding(s) supported by 2306 the FPU and the NaN encoding requested with the value 2307 of an ELF file header flag individually set by each 2308 binary. Hardware implementations are permitted to 2309 support either or both of the legacy and the 2008 NaN 2310 encoding mode. 2311 2312 Available settings are as follows: 2313 strict accept binaries that request a NaN encoding 2314 supported by the FPU 2315 legacy only accept legacy-NaN binaries, if supported 2316 by the FPU 2317 2008 only accept 2008-NaN binaries, if supported 2318 by the FPU 2319 relaxed accept any binaries regardless of whether 2320 supported by the FPU 2321 emulated accept any binaries but enable FPU emulator 2322 if binary mode is unsupported by the FPU. 2323 2324 The FPU emulator is always able to support both NaN 2325 encodings, so if no FPU hardware is present or it has 2326 been disabled with 'nofpu', then the settings of 2327 'legacy' and '2008' strap the emulator accordingly, 2328 'relaxed' straps the emulator for both legacy-NaN and 2329 2008-NaN, whereas 'strict' enables legacy-NaN only on 2330 legacy processors and both NaN encodings on MIPS32 or 2331 MIPS64 CPUs. 2332 2333 The setting for ABS.fmt/NEG.fmt instruction execution 2334 mode generally follows that for the NaN encoding, 2335 except where unsupported by hardware. 2336 2337 ignore_loglevel [KNL,EARLY] 2338 Ignore loglevel setting - this will print /all/ 2339 kernel messages to the console. Useful for debugging. 2340 We also add it as printk module parameter, so users 2341 could change it dynamically, usually by 2342 /sys/module/printk/parameters/ignore_loglevel. 2343 2344 ignore_rlimit_data 2345 Ignore RLIMIT_DATA setting for data mappings, 2346 print warning at first misuse. Can be changed via 2347 /sys/module/kernel/parameters/ignore_rlimit_data. 2348 2349 ihash_entries= [KNL] 2350 Set number of hash buckets for inode cache. 2351 2352 ima_appraise= [IMA] appraise integrity measurements 2353 Format: { "off" | "enforce" | "fix" | "log" } 2354 default: "enforce" 2355 2356 ima_appraise_tcb [IMA] Deprecated. Use ima_policy= instead. 2357 The builtin appraise policy appraises all files 2358 owned by uid=0. 2359 2360 ima_canonical_fmt [IMA] 2361 Use the canonical format for the binary runtime 2362 measurements, instead of host native format. 2363 2364 ima_hash= [IMA] 2365 Format: { md5 | sha1 | rmd160 | sha256 | sha384 2366 | sha512 | ... } 2367 default: "sha1" 2368 2369 The list of supported hash algorithms is defined 2370 in crypto/hash_info.h. 2371 2372 ima_policy= [IMA] 2373 The builtin policies to load during IMA setup. 2374 Format: "tcb | appraise_tcb | secure_boot | 2375 fail_securely | critical_data" 2376 2377 The "tcb" policy measures all programs exec'd, files 2378 mmap'd for exec, and all files opened with the read 2379 mode bit set by either the effective uid (euid=0) or 2380 uid=0. 2381 2382 The "appraise_tcb" policy appraises the integrity of 2383 all files owned by root. 2384 2385 The "secure_boot" policy appraises the integrity 2386 of files (eg. kexec kernel image, kernel modules, 2387 firmware, policy, etc) based on file signatures. 2388 2389 The "fail_securely" policy forces file signature 2390 verification failure also on privileged mounted 2391 filesystems with the SB_I_UNVERIFIABLE_SIGNATURE 2392 flag. 2393 2394 The "critical_data" policy measures kernel integrity 2395 critical data. 2396 2397 ima_tcb [IMA] Deprecated. Use ima_policy= instead. 2398 Load a policy which meets the needs of the Trusted 2399 Computing Base. This means IMA will measure all 2400 programs exec'd, files mmap'd for exec, and all files 2401 opened for read by uid=0. 2402 2403 ima_template= [IMA] 2404 Select one of defined IMA measurements template formats. 2405 Formats: { "ima" | "ima-ng" | "ima-ngv2" | "ima-sig" | 2406 "ima-sigv2" } 2407 Default: "ima-ng" 2408 2409 ima_template_fmt= 2410 [IMA] Define a custom template format. 2411 Format: { "field1|...|fieldN" } 2412 2413 ima= [IMA] Enable or disable IMA 2414 Format: { "off" | "on" } 2415 Default: "on" 2416 Note that disabling IMA is limited to kdump kernel. 2417 2418 indirect_target_selection= [X86,Intel] Mitigation control for Indirect 2419 Target Selection(ITS) bug in Intel CPUs. Updated 2420 microcode is also required for a fix in IBPB. 2421 2422 on: Enable mitigation (default). 2423 off: Disable mitigation. 2424 force: Force the ITS bug and deploy default 2425 mitigation. 2426 vmexit: Only deploy mitigation if CPU is affected by 2427 guest/host isolation part of ITS. 2428 stuff: Deploy RSB-fill mitigation when retpoline is 2429 also deployed. Otherwise, deploy the default 2430 mitigation. 2431 2432 For details see: 2433 Documentation/admin-guide/hw-vuln/indirect-target-selection.rst 2434 2435 init= [KNL] 2436 Format: <full_path> 2437 Run specified binary instead of /sbin/init as init 2438 process. 2439 2440 initcall_debug [KNL] Trace initcalls as they are executed. Useful 2441 for working out where the kernel is dying during 2442 startup. 2443 2444 initcall_blacklist= [KNL] Do not execute a comma-separated list of 2445 initcall functions. Useful for debugging built-in 2446 modules and initcalls. 2447 2448 initramfs_async= [KNL] 2449 Format: <bool> 2450 Default: 1 2451 This parameter controls whether the initramfs 2452 image is unpacked asynchronously, concurrently 2453 with devices being probed and 2454 initialized. This should normally just work, 2455 but as a debugging aid, one can get the 2456 historical behaviour of the initramfs 2457 unpacking being completed before device_ and 2458 late_ initcalls. 2459 2460 initrd= [BOOT,EARLY] Specify the location of the initial ramdisk 2461 2462 initrdmem= [KNL,EARLY] Specify a physical address and size from which to 2463 load the initrd. If an initrd is compiled in or 2464 specified in the bootparams, it takes priority over this 2465 setting. 2466 Format: ss[KMG],nn[KMG] 2467 Default is 0, 0 2468 2469 init_on_alloc= [MM,EARLY] Fill newly allocated pages and heap objects with 2470 zeroes. 2471 Format: 0 | 1 2472 Default set by CONFIG_INIT_ON_ALLOC_DEFAULT_ON. 2473 2474 init_on_free= [MM,EARLY] Fill freed pages and heap objects with zeroes. 2475 Format: 0 | 1 2476 Default set by CONFIG_INIT_ON_FREE_DEFAULT_ON. 2477 2478 init_pkru= [X86] Specify the default memory protection keys rights 2479 register contents for all processes. 0x55555554 by 2480 default (disallow access to all but pkey 0). Can 2481 override in debugfs after boot. 2482 2483 inport.irq= [HW] Inport (ATI XL and Microsoft) busmouse driver 2484 Format: <irq> 2485 2486 int_pln_enable [X86] Enable power limit notification interrupt 2487 2488 integrity_audit=[IMA] 2489 Format: { "0" | "1" } 2490 0 -- basic integrity auditing messages. (Default) 2491 1 -- additional integrity auditing messages. 2492 2493 intel_iommu= [DMAR] Intel IOMMU driver (DMAR) option 2494 on 2495 Enable intel iommu driver. 2496 off 2497 Disable intel iommu driver. 2498 igfx_off [Default Off] 2499 By default, gfx is mapped as normal device. If a gfx 2500 device has a dedicated DMAR unit, the DMAR unit is 2501 bypassed by not enabling DMAR with this option. In 2502 this case, gfx device will use physical address for 2503 DMA. 2504 strict [Default Off] 2505 Deprecated, equivalent to iommu.strict=1. 2506 sp_off [Default Off] 2507 By default, super page will be supported if Intel IOMMU 2508 has the capability. With this option, super page will 2509 not be supported. 2510 sm_on 2511 Enable the Intel IOMMU scalable mode if the hardware 2512 advertises that it has support for the scalable mode 2513 translation. 2514 sm_off 2515 Disallow use of the Intel IOMMU scalable mode. 2516 tboot_noforce [Default Off] 2517 Do not force the Intel IOMMU enabled under tboot. 2518 By default, tboot will force Intel IOMMU on, which 2519 could harm performance of some high-throughput 2520 devices like 40GBit network cards, even if identity 2521 mapping is enabled. 2522 Note that using this option lowers the security 2523 provided by tboot because it makes the system 2524 vulnerable to DMA attacks. 2525 2526 intel_idle.max_cstate= [KNL,HW,ACPI,X86] 2527 0 disables intel_idle and fall back on acpi_idle. 2528 1 to 9 specify maximum depth of C-state. 2529 2530 intel_pstate= [X86,EARLY] 2531 disable 2532 Do not enable intel_pstate as the default 2533 scaling driver for the supported processors 2534 active 2535 Use intel_pstate driver to bypass the scaling 2536 governors layer of cpufreq and provides it own 2537 algorithms for p-state selection. There are two 2538 P-state selection algorithms provided by 2539 intel_pstate in the active mode: powersave and 2540 performance. The way they both operate depends 2541 on whether or not the hardware managed P-states 2542 (HWP) feature has been enabled in the processor 2543 and possibly on the processor model. 2544 passive 2545 Use intel_pstate as a scaling driver, but configure it 2546 to work with generic cpufreq governors (instead of 2547 enabling its internal governor). This mode cannot be 2548 used along with the hardware-managed P-states (HWP) 2549 feature. 2550 force 2551 Enable intel_pstate on systems that prohibit it by default 2552 in favor of acpi-cpufreq. Forcing the intel_pstate driver 2553 instead of acpi-cpufreq may disable platform features, such 2554 as thermal controls and power capping, that rely on ACPI 2555 P-States information being indicated to OSPM and therefore 2556 should be used with caution. This option does not work with 2557 processors that aren't supported by the intel_pstate driver 2558 or on platforms that use pcc-cpufreq instead of acpi-cpufreq. 2559 no_hwp 2560 Do not enable hardware P state control (HWP) 2561 if available. 2562 hwp_only 2563 Only load intel_pstate on systems which support 2564 hardware P state control (HWP) if available. 2565 support_acpi_ppc 2566 Enforce ACPI _PPC performance limits. If the Fixed ACPI 2567 Description Table, specifies preferred power management 2568 profile as "Enterprise Server" or "Performance Server", 2569 then this feature is turned on by default. 2570 per_cpu_perf_limits 2571 Allow per-logical-CPU P-State performance control limits using 2572 cpufreq sysfs interface 2573 no_cas 2574 Do not enable capacity-aware scheduling (CAS) on 2575 hybrid systems 2576 2577 intremap= [X86-64,Intel-IOMMU,EARLY] 2578 on enable Interrupt Remapping (default) 2579 off disable Interrupt Remapping 2580 nosid disable Source ID checking 2581 no_x2apic_optout 2582 BIOS x2APIC opt-out request will be ignored 2583 nopost disable Interrupt Posting 2584 posted_msi 2585 enable MSIs delivered as posted interrupts 2586 2587 iomem= Disable strict checking of access to MMIO memory 2588 strict regions from userspace. 2589 relaxed 2590 2591 iommu= [X86,EARLY] 2592 2593 off 2594 Don't initialize and use any kind of IOMMU. 2595 2596 force 2597 Force the use of the hardware IOMMU even when 2598 it is not actually needed (e.g. because < 3 GB 2599 memory). 2600 2601 noforce 2602 Don't force hardware IOMMU usage when it is not 2603 needed. (default). 2604 2605 biomerge 2606 panic 2607 nopanic 2608 merge 2609 nomerge 2610 2611 soft 2612 Use software bounce buffering (SWIOTLB) (default for 2613 Intel machines). This can be used to prevent the usage 2614 of an available hardware IOMMU. 2615 2616 pt 2617 nopt 2618 nobypass [PPC/POWERNV] 2619 Disable IOMMU bypass, using IOMMU for PCI devices. 2620 2621 AMD Gart HW IOMMU-specific options: 2622 2623 <size> 2624 Set the size of the remapping area in bytes. 2625 2626 allowed 2627 Overwrite iommu off workarounds for specific chipsets 2628 2629 fullflush 2630 Flush IOMMU on each allocation (default). 2631 2632 nofullflush 2633 Don't use IOMMU fullflush. 2634 2635 memaper[=<order>] 2636 Allocate an own aperture over RAM with size 2637 32MB<<order. (default: order=1, i.e. 64MB) 2638 2639 merge 2640 Do scatter-gather (SG) merging. Implies "force" 2641 (experimental). 2642 2643 nomerge 2644 Don't do scatter-gather (SG) merging. 2645 2646 noaperture 2647 Ask the IOMMU not to touch the aperture for AGP. 2648 2649 noagp 2650 Don't initialize the AGP driver and use full aperture. 2651 2652 panic 2653 Always panic when IOMMU overflows. 2654 2655 iommu.forcedac= [ARM64,X86,EARLY] Control IOVA allocation for PCI devices. 2656 Format: { "0" | "1" } 2657 0 - Try to allocate a 32-bit DMA address first, before 2658 falling back to the full range if needed. 2659 1 - Allocate directly from the full usable range, 2660 forcing Dual Address Cycle for PCI cards supporting 2661 greater than 32-bit addressing. 2662 2663 iommu.strict= [ARM64,X86,S390,EARLY] Configure TLB invalidation behaviour 2664 Format: { "0" | "1" } 2665 0 - Lazy mode. 2666 Request that DMA unmap operations use deferred 2667 invalidation of hardware TLBs, for increased 2668 throughput at the cost of reduced device isolation. 2669 Will fall back to strict mode if not supported by 2670 the relevant IOMMU driver. 2671 1 - Strict mode. 2672 DMA unmap operations invalidate IOMMU hardware TLBs 2673 synchronously. 2674 unset - Use value of CONFIG_IOMMU_DEFAULT_DMA_{LAZY,STRICT}. 2675 Note: on x86, strict mode specified via one of the 2676 legacy driver-specific options takes precedence. 2677 2678 iommu.passthrough= 2679 [ARM64,X86,EARLY] Configure DMA to bypass the IOMMU by default. 2680 Format: { "0" | "1" } 2681 0 - Use IOMMU translation for DMA. 2682 1 - Bypass the IOMMU for DMA. 2683 unset - Use value of CONFIG_IOMMU_DEFAULT_PASSTHROUGH. 2684 2685 iommu.debug_pagealloc= 2686 [KNL,EARLY] When CONFIG_IOMMU_DEBUG_PAGEALLOC is set, this 2687 parameter enables the feature at boot time. By default, it 2688 is disabled and the system behaves the same way as a kernel 2689 built without CONFIG_IOMMU_DEBUG_PAGEALLOC. 2690 Format: { "0" | "1" } 2691 0 - Sanitizer disabled. 2692 1 - Sanitizer enabled, expect runtime overhead. 2693 2694 io7= [HW] IO7 for Marvel-based Alpha systems 2695 See comment before marvel_specify_io7 in 2696 arch/alpha/kernel/core_marvel.c. 2697 2698 io_delay= [X86,EARLY] I/O delay method 2699 0x80 2700 Standard port 0x80 based delay 2701 0xed 2702 Alternate port 0xed based delay (needed on some systems) 2703 udelay 2704 Simple two microseconds delay 2705 none 2706 No delay 2707 2708 ip= [IP_PNP] 2709 See Documentation/admin-guide/nfs/nfsroot.rst. 2710 2711 ipcmni_extend [KNL,EARLY] Extend the maximum number of unique System V 2712 IPC identifiers from 32,768 to 16,777,216. 2713 2714 ipe.enforce= [IPE] 2715 Format: <bool> 2716 Determine whether IPE starts in permissive (0) or 2717 enforce (1) mode. The default is enforce. 2718 2719 ipe.success_audit= 2720 [IPE] 2721 Format: <bool> 2722 Start IPE with success auditing enabled, emitting 2723 an audit event when a binary is allowed. The default 2724 is 0. 2725 2726 irqaffinity= [SMP] Set the default irq affinity mask 2727 The argument is a cpu list, as described above. 2728 2729 irqchip.gicv2_force_probe= 2730 [ARM,ARM64,EARLY] 2731 Format: <bool> 2732 Force the kernel to look for the second 4kB page 2733 of a GICv2 controller even if the memory range 2734 exposed by the device tree is too small. 2735 2736 irqchip.gicv3_nolpi= 2737 [ARM,ARM64,EARLY] 2738 Force the kernel to ignore the availability of 2739 LPIs (and by consequence ITSs). Intended for system 2740 that use the kernel as a bootloader, and thus want 2741 to let secondary kernels in charge of setting up 2742 LPIs. 2743 2744 irqchip.gicv3_pseudo_nmi= [ARM64,EARLY] 2745 Enables support for pseudo-NMIs in the kernel. This 2746 requires the kernel to be built with 2747 CONFIG_ARM64_PSEUDO_NMI. 2748 2749 irqchip.riscv_imsic_noipi 2750 [RISC-V,EARLY] 2751 Force the kernel to not use IMSIC software injected MSIs 2752 as IPIs. Intended for system where IMSIC is trap-n-emulated, 2753 and thus want to reduce MMIO traps when triggering IPIs 2754 to multiple harts. 2755 2756 irqfixup [HW] 2757 When an interrupt is not handled search all handlers 2758 for it. Intended to get systems with badly broken 2759 firmware running. 2760 2761 irqhandler.duration_warn_us= [KNL] 2762 Warn if an IRQ handler exceeds the specified duration 2763 threshold in microseconds. Useful for identifying 2764 long-running IRQs in the system. 2765 2766 irqpoll [HW] 2767 When an interrupt is not handled search all handlers 2768 for it. Also check all handlers each timer 2769 interrupt. Intended to get systems with badly broken 2770 firmware running. 2771 2772 isapnp= [ISAPNP] 2773 Format: <RDP>,<reset>,<pci_scan>,<verbosity> 2774 2775 isolcpus= [KNL,SMP,ISOL] Isolate a given set of CPUs from disturbance. 2776 [Deprecated - use cpusets instead] 2777 Format: [flag-list,]<cpu-list> 2778 2779 Specify one or more CPUs to isolate from disturbances 2780 specified in the flag list (default: domain): 2781 2782 nohz 2783 Disable the tick when a single task runs as well as 2784 disabling other kernel noises like having RCU callbacks 2785 offloaded. This is equivalent to the nohz_full parameter. 2786 2787 A residual 1Hz tick is offloaded to workqueues, which you 2788 need to affine to housekeeping through the global 2789 workqueue's affinity configured via the 2790 /sys/devices/virtual/workqueue/cpumask sysfs file, or 2791 by using the 'domain' flag described below. 2792 2793 NOTE: by default the global workqueue runs on all CPUs, 2794 so to protect individual CPUs the 'cpumask' file has to 2795 be configured manually after bootup. 2796 2797 domain 2798 Isolate from the general SMP balancing and scheduling 2799 algorithms. Note that performing domain isolation this way 2800 is irreversible: it's not possible to bring back a CPU to 2801 the domains once isolated through isolcpus. It's strongly 2802 advised to use cpusets instead to disable scheduler load 2803 balancing through the "cpuset.sched_load_balance" file. 2804 It offers a much more flexible interface where CPUs can 2805 move in and out of an isolated set anytime. 2806 2807 You can move a process onto or off an "isolated" CPU via 2808 the CPU affinity syscalls or cpuset. 2809 <cpu number> begins at 0 and the maximum value is 2810 "number of CPUs in system - 1". 2811 2812 managed_irq 2813 2814 Isolate from being targeted by managed interrupts 2815 which have an interrupt mask containing isolated 2816 CPUs. The affinity of managed interrupts is 2817 handled by the kernel and cannot be changed via 2818 the /proc/irq/* interfaces. 2819 2820 This isolation is best effort and only effective 2821 if the automatically assigned interrupt mask of a 2822 device queue contains isolated and housekeeping 2823 CPUs. If housekeeping CPUs are online then such 2824 interrupts are directed to the housekeeping CPU 2825 so that IO submitted on the housekeeping CPU 2826 cannot disturb the isolated CPU. 2827 2828 If a queue's affinity mask contains only isolated 2829 CPUs then this parameter has no effect on the 2830 interrupt routing decision, though interrupts are 2831 only delivered when tasks running on those 2832 isolated CPUs submit IO. IO submitted on 2833 housekeeping CPUs has no influence on those 2834 queues. 2835 2836 The format of <cpu-list> is described above. 2837 2838 iucv= [HW,NET] 2839 2840 ivrs_ioapic [HW,X86-64] 2841 Provide an override to the IOAPIC-ID<->DEVICE-ID 2842 mapping provided in the IVRS ACPI table. 2843 By default, PCI segment is 0, and can be omitted. 2844 2845 For example, to map IOAPIC-ID decimal 10 to 2846 PCI segment 0x1 and PCI device 00:14.0, 2847 write the parameter as: 2848 ivrs_ioapic=10@0001:00:14.0 2849 2850 Deprecated formats: 2851 * To map IOAPIC-ID decimal 10 to PCI device 00:14.0 2852 write the parameter as: 2853 ivrs_ioapic[10]=00:14.0 2854 * To map IOAPIC-ID decimal 10 to PCI segment 0x1 and 2855 PCI device 00:14.0 write the parameter as: 2856 ivrs_ioapic[10]=0001:00:14.0 2857 2858 ivrs_hpet [HW,X86-64] 2859 Provide an override to the HPET-ID<->DEVICE-ID 2860 mapping provided in the IVRS ACPI table. 2861 By default, PCI segment is 0, and can be omitted. 2862 2863 For example, to map HPET-ID decimal 10 to 2864 PCI segment 0x1 and PCI device 00:14.0, 2865 write the parameter as: 2866 ivrs_hpet=10@0001:00:14.0 2867 2868 Deprecated formats: 2869 * To map HPET-ID decimal 0 to PCI device 00:14.0 2870 write the parameter as: 2871 ivrs_hpet[0]=00:14.0 2872 * To map HPET-ID decimal 10 to PCI segment 0x1 and 2873 PCI device 00:14.0 write the parameter as: 2874 ivrs_ioapic[10]=0001:00:14.0 2875 2876 ivrs_acpihid [HW,X86-64] 2877 Provide an override to the ACPI-HID:UID<->DEVICE-ID 2878 mapping provided in the IVRS ACPI table. 2879 By default, PCI segment is 0, and can be omitted. 2880 2881 For example, to map UART-HID:UID AMD0020:0 to 2882 PCI segment 0x1 and PCI device ID 00:14.5, 2883 write the parameter as: 2884 ivrs_acpihid=AMD0020:0@0001:00:14.5 2885 2886 Deprecated formats: 2887 * To map UART-HID:UID AMD0020:0 to PCI segment is 0, 2888 PCI device ID 00:14.5, write the parameter as: 2889 ivrs_acpihid[00:14.5]=AMD0020:0 2890 * To map UART-HID:UID AMD0020:0 to PCI segment 0x1 and 2891 PCI device ID 00:14.5, write the parameter as: 2892 ivrs_acpihid[0001:00:14.5]=AMD0020:0 2893 2894 js= [HW,JOY] Analog joystick 2895 See Documentation/input/joydev/joystick.rst. 2896 2897 kasan_multi_shot 2898 [KNL] Enforce KASAN (Kernel Address Sanitizer) to print 2899 report on every invalid memory access. Without this 2900 parameter KASAN will print report only for the first 2901 invalid access. 2902 2903 keep_bootcon [KNL,EARLY] 2904 Do not unregister boot console at start. This is only 2905 useful for debugging when something happens in the window 2906 between unregistering the boot console and initializing 2907 the real console. 2908 2909 keepinitrd [HW,ARM] See retain_initrd. 2910 2911 kernelcore= [KNL,X86,PPC,EARLY] 2912 Format: nn[KMGTPE] | nn% | "mirror" 2913 This parameter specifies the amount of memory usable by 2914 the kernel for non-movable allocations. The requested 2915 amount is spread evenly throughout all nodes in the 2916 system as ZONE_NORMAL. The remaining memory is used for 2917 movable memory in its own zone, ZONE_MOVABLE. In the 2918 event, a node is too small to have both ZONE_NORMAL and 2919 ZONE_MOVABLE, kernelcore memory will take priority and 2920 other nodes will have a larger ZONE_MOVABLE. 2921 2922 ZONE_MOVABLE is used for the allocation of pages that 2923 may be reclaimed or moved by the page migration 2924 subsystem. Note that allocations like PTEs-from-HighMem 2925 still use the HighMem zone if it exists, and the Normal 2926 zone if it does not. 2927 2928 It is possible to specify the exact amount of memory in 2929 the form of "nn[KMGTPE]", a percentage of total system 2930 memory in the form of "nn%", or "mirror". If "mirror" 2931 option is specified, mirrored (reliable) memory is used 2932 for non-movable allocations and remaining memory is used 2933 for Movable pages. "nn[KMGTPE]", "nn%", and "mirror" 2934 are exclusive, so you cannot specify multiple forms. 2935 2936 kfence.burst= [MM,KFENCE] The number of additional successive 2937 allocations to be attempted through KFENCE for each 2938 sample interval. 2939 Format: <unsigned integer> 2940 Default: 0 2941 2942 kfence.check_on_panic= 2943 [MM,KFENCE] Whether to check all KFENCE-managed objects' 2944 canaries on panic. 2945 Format: <bool> 2946 Default: false 2947 2948 kfence.deferrable= 2949 [MM,KFENCE] Whether to use a deferrable timer to trigger 2950 allocations. This avoids forcing CPU wake-ups if the 2951 system is idle, at the risk of a less predictable 2952 sample interval. 2953 Format: <bool> 2954 Default: CONFIG_KFENCE_DEFERRABLE 2955 2956 kfence.fault= [MM,KFENCE] Controls the behavior when a KFENCE 2957 error is detected. 2958 report - print the error report and continue (default). 2959 oops - print the error report and oops. 2960 panic - print the error report and panic. 2961 2962 kfence.sample_interval= 2963 [MM,KFENCE] KFENCE's sample interval in milliseconds. 2964 Format: <unsigned integer> 2965 0 - Disable KFENCE. 2966 >0 - Enabled KFENCE with given sample interval. 2967 Default: CONFIG_KFENCE_SAMPLE_INTERVAL 2968 2969 kfence.skip_covered_thresh= 2970 [MM,KFENCE] If pool utilization reaches this threshold 2971 (pool usage%), KFENCE limits currently covered 2972 allocations of the same source from further filling 2973 up the pool. 2974 Format: <unsigned integer> 2975 Default: 75 2976 2977 kgdbdbgp= [KGDB,HW,EARLY] kgdb over EHCI usb debug port. 2978 Format: <Controller#>[,poll interval] 2979 The controller # is the number of the ehci usb debug 2980 port as it is probed via PCI. The poll interval is 2981 optional and is the number seconds in between 2982 each poll cycle to the debug port in case you need 2983 the functionality for interrupting the kernel with 2984 gdb or control-c on the dbgp connection. When 2985 not using this parameter you use sysrq-g to break into 2986 the kernel debugger. 2987 2988 kgdboc= [KGDB,HW] kgdb over consoles. 2989 Requires a tty driver that supports console polling, 2990 or a supported polling keyboard driver (non-usb). 2991 Serial only format: <serial_device>[,baud] 2992 keyboard only format: kbd 2993 keyboard and serial format: kbd,<serial_device>[,baud] 2994 Optional Kernel mode setting: 2995 kms, kbd format: kms,kbd 2996 kms, kbd and serial format: kms,kbd,<ser_dev>[,baud] 2997 2998 kgdboc_earlycon= [KGDB,HW,EARLY] 2999 If the boot console provides the ability to read 3000 characters and can work in polling mode, you can use 3001 this parameter to tell kgdb to use it as a backend 3002 until the normal console is registered. Intended to 3003 be used together with the kgdboc parameter which 3004 specifies the normal console to transition to. 3005 3006 The name of the early console should be specified 3007 as the value of this parameter. Note that the name of 3008 the early console might be different than the tty 3009 name passed to kgdboc. It's OK to leave the value 3010 blank and the first boot console that implements 3011 read() will be picked. 3012 3013 kgdbwait [KGDB,EARLY] Stop kernel execution and enter the 3014 kernel debugger at the earliest opportunity. 3015 3016 kho= [KEXEC,EARLY] 3017 Format: { "0" | "1" | "off" | "on" | "y" | "n" } 3018 Enables or disables Kexec HandOver. 3019 "0" | "off" | "n" - kexec handover is disabled 3020 "1" | "on" | "y" - kexec handover is enabled 3021 3022 kho_scratch= [KEXEC,EARLY] 3023 Format: ll[KMG],mm[KMG],nn[KMG] | nn% 3024 Defines the size of the KHO scratch region. The KHO 3025 scratch regions are physically contiguous memory 3026 ranges that can only be used for non-kernel 3027 allocations. That way, even when memory is heavily 3028 fragmented with handed over memory, the kexeced 3029 kernel will always have enough contiguous ranges to 3030 bootstrap itself. 3031 3032 It is possible to specify the exact amount of 3033 memory in the form of "ll[KMG],mm[KMG],nn[KMG]" 3034 where the first parameter defines the size of a low 3035 memory scratch area, the second parameter defines 3036 the size of a global scratch area and the third 3037 parameter defines the size of additional per-node 3038 scratch areas. The form "nn%" defines scale factor 3039 (in percents) of memory that was used during boot. 3040 3041 kmac= [MIPS] Korina ethernet MAC address. 3042 Configure the RouterBoard 532 series on-chip 3043 Ethernet adapter MAC address. 3044 3045 kmemleak= [KNL,EARLY] Boot-time kmemleak enable/disable 3046 Valid arguments: on, off 3047 Default: on 3048 Built with CONFIG_DEBUG_KMEMLEAK_DEFAULT_OFF=y, 3049 the default is off. 3050 3051 kprobe_event=[probe-list] 3052 [FTRACE] Add kprobe events and enable at boot time. 3053 The probe-list is a semicolon delimited list of probe 3054 definitions. Each definition is same as kprobe_events 3055 interface, but the parameters are comma delimited. 3056 For example, to add a kprobe event on vfs_read with 3057 arg1 and arg2, add to the command line; 3058 3059 kprobe_event=p,vfs_read,$arg1,$arg2 3060 3061 See also Documentation/trace/kprobetrace.rst "Kernel 3062 Boot Parameter" section. 3063 3064 kpti= [ARM64,EARLY] Control page table isolation of 3065 user and kernel address spaces. 3066 Default: enabled on cores which need mitigation. 3067 0: force disabled 3068 1: force enabled 3069 3070 kunit.enable= [KUNIT] Enable executing KUnit tests. Requires 3071 CONFIG_KUNIT to be set to be fully enabled. The 3072 default value can be overridden via 3073 KUNIT_DEFAULT_ENABLED. 3074 Default is 1 (enabled) 3075 3076 kvm.ignore_msrs=[KVM] Ignore guest accesses to unhandled MSRs. 3077 Default is 0 (don't ignore, but inject #GP) 3078 3079 kvm.eager_page_split= 3080 [KVM,X86] Controls whether or not KVM will try to 3081 proactively split all huge pages during dirty logging. 3082 Eager page splitting reduces interruptions to vCPU 3083 execution by eliminating the write-protection faults 3084 and MMU lock contention that would otherwise be 3085 required to split huge pages lazily. 3086 3087 VM workloads that rarely perform writes or that write 3088 only to a small region of VM memory may benefit from 3089 disabling eager page splitting to allow huge pages to 3090 still be used for reads. 3091 3092 The behavior of eager page splitting depends on whether 3093 KVM_DIRTY_LOG_INITIALLY_SET is enabled or disabled. If 3094 disabled, all huge pages in a memslot will be eagerly 3095 split when dirty logging is enabled on that memslot. If 3096 enabled, eager page splitting will be performed during 3097 the KVM_CLEAR_DIRTY ioctl, and only for the pages being 3098 cleared. 3099 3100 Eager page splitting is only supported when kvm.tdp_mmu=Y. 3101 3102 Default is Y (on). 3103 3104 kvm.enable_pmu=[KVM,X86] 3105 If enabled, KVM will virtualize PMU functionality based 3106 on the virtual CPU model defined by userspace. This 3107 can be overridden on a per-VM basis via 3108 KVM_CAP_PMU_CAPABILITY. 3109 3110 If disabled, KVM will not virtualize PMU functionality, 3111 e.g. MSRs, PMCs, PMIs, etc., even if userspace defines 3112 a virtual CPU model that contains PMU assets. 3113 3114 Note, KVM's vPMU support implicitly requires running 3115 with an in-kernel local APIC, e.g. to deliver PMIs to 3116 the guest. Running without an in-kernel local APIC is 3117 not supported, though KVM will allow such a combination 3118 (with severely degraded functionality). 3119 3120 See also enable_mediated_pmu. 3121 3122 Default is Y (on). 3123 3124 kvm.enable_virt_at_load=[KVM,ARM64,LOONGARCH,MIPS,RISCV,X86] 3125 If enabled, KVM will enable virtualization in hardware 3126 when KVM is loaded, and disable virtualization when KVM 3127 is unloaded (if KVM is built as a module). 3128 3129 If disabled, KVM will dynamically enable and disable 3130 virtualization on-demand when creating and destroying 3131 VMs, i.e. on the 0=>1 and 1=>0 transitions of the 3132 number of VMs. 3133 3134 Enabling virtualization at module load avoids potential 3135 latency for creation of the 0=>1 VM, as KVM serializes 3136 virtualization enabling across all online CPUs. The 3137 "cost" of enabling virtualization when KVM is loaded, 3138 is that doing so may interfere with using out-of-tree 3139 hypervisors that want to "own" virtualization hardware. 3140 3141 kvm.enable_vmware_backdoor=[KVM] Support VMware backdoor PV interface. 3142 Default is false (don't support). 3143 3144 kvm.nx_huge_pages= 3145 [KVM] Controls the software workaround for the 3146 X86_BUG_ITLB_MULTIHIT bug. 3147 force : Always deploy workaround. 3148 off : Never deploy workaround. 3149 auto : Deploy workaround based on the presence of 3150 X86_BUG_ITLB_MULTIHIT. 3151 3152 Default is 'auto'. 3153 3154 If the software workaround is enabled for the host, 3155 guests do need not to enable it for nested guests. 3156 3157 kvm.nx_huge_pages_recovery_ratio= 3158 [KVM] Controls how many 4KiB pages are periodically zapped 3159 back to huge pages. 0 disables the recovery, otherwise if 3160 the value is N KVM will zap 1/Nth of the 4KiB pages every 3161 period (see below). The default is 60. 3162 3163 kvm.nx_huge_pages_recovery_period_ms= 3164 [KVM] Controls the time period at which KVM zaps 4KiB pages 3165 back to huge pages. If the value is a non-zero N, KVM will 3166 zap a portion (see ratio above) of the pages every N msecs. 3167 If the value is 0 (the default), KVM will pick a period based 3168 on the ratio, such that a page is zapped after 1 hour on average. 3169 3170 kvm-{amd,intel}.enable_mediated_pmu=[KVM,AMD,INTEL] 3171 If enabled, KVM will provide a mediated virtual PMU, 3172 instead of the default perf-based virtual PMU (if 3173 kvm.enable_pmu is true and PMU is enumerated via the 3174 virtual CPU model). 3175 3176 With a perf-based vPMU, KVM operates as a user of perf, 3177 i.e. emulates guest PMU counters using perf events. 3178 KVM-created perf events are managed by perf as regular 3179 (guest-only) events, e.g. are scheduled in/out, contend 3180 for hardware resources, etc. Using a perf-based vPMU 3181 allows guest and host usage of the PMU to co-exist, but 3182 incurs non-trivial overhead and can result in silently 3183 dropped guest events (due to resource contention). 3184 3185 With a mediated vPMU, hardware PMU state is context 3186 switched around the world switch to/from the guest. 3187 KVM mediates which events the guest can utilize, but 3188 gives the guest direct access to all other PMU assets 3189 when possible (KVM may intercept some accesses if the 3190 virtual CPU model provides a subset of hardware PMU 3191 functionality). Using a mediated vPMU significantly 3192 reduces PMU virtualization overhead and eliminates lost 3193 guest events, but is mutually exclusive with using perf 3194 to profile KVM guests and adds latency to most VM-Exits 3195 (to context switch PMU state). 3196 3197 Default is N (off). 3198 3199 kvm-amd.nested= [KVM,AMD] Control nested virtualization feature in 3200 KVM/SVM. Default is 1 (enabled). 3201 3202 kvm-amd.npt= [KVM,AMD] Control KVM's use of Nested Page Tables, 3203 a.k.a. Two-Dimensional Page Tables. Default is 1 3204 (enabled). Disable by KVM if hardware lacks support 3205 for NPT. 3206 3207 kvm-amd.ciphertext_hiding_asids= 3208 [KVM,AMD] Ciphertext hiding prevents disallowed accesses 3209 to SNP private memory from reading ciphertext. Instead, 3210 reads will see constant default values (0xff). 3211 3212 If ciphertext hiding is enabled, the joint SEV-ES and 3213 SEV-SNP ASID space is partitioned into separate SEV-ES 3214 and SEV-SNP ASID ranges, with the SEV-SNP range being 3215 [1..max_snp_asid] and the SEV-ES range being 3216 (max_snp_asid..min_sev_asid), where min_sev_asid is 3217 enumerated by CPUID.0x.8000_001F[EDX]. 3218 3219 A non-zero value enables SEV-SNP ciphertext hiding and 3220 adjusts the ASID ranges for SEV-ES and SEV-SNP guests. 3221 KVM caps the number of SEV-SNP ASIDs at the maximum 3222 possible value, e.g. specifying -1u will assign all 3223 joint SEV-ES and SEV-SNP ASIDs to SEV-SNP. Note, 3224 assigning all joint ASIDs to SEV-SNP, i.e. configuring 3225 max_snp_asid == min_sev_asid-1, will effectively make 3226 SEV-ES unusable. 3227 3228 kvm-arm.mode= 3229 [KVM,ARM,EARLY] Select one of KVM/arm64's modes of 3230 operation. 3231 3232 none: Forcefully disable KVM. 3233 3234 nvhe: Standard nVHE-based mode, without support for 3235 protected guests. 3236 3237 protected: Mode with support for guests whose state is 3238 kept private from the host, using VHE or 3239 nVHE depending on HW support. 3240 3241 nested: VHE-based mode with support for nested 3242 virtualization. Requires at least ARMv8.4 3243 hardware (with FEAT_NV2). 3244 3245 Defaults to VHE/nVHE based on hardware support. Setting 3246 mode to "protected" will disable kexec and hibernation 3247 for the host. To force nVHE on VHE hardware, add 3248 "arm64_sw.hvhe=0 id_aa64mmfr1.vh=0" to the 3249 command-line. 3250 "nested" and "protected" are experimental and should be 3251 used with extreme caution. 3252 3253 kvm-arm.vgic_v3_group0_trap= 3254 [KVM,ARM,EARLY] Trap guest accesses to GICv3 group-0 3255 system registers 3256 3257 kvm-arm.vgic_v3_group1_trap= 3258 [KVM,ARM,EARLY] Trap guest accesses to GICv3 group-1 3259 system registers 3260 3261 kvm-arm.vgic_v3_common_trap= 3262 [KVM,ARM,EARLY] Trap guest accesses to GICv3 common 3263 system registers 3264 3265 kvm-arm.vgic_v4_enable= 3266 [KVM,ARM,EARLY] Allow use of GICv4 for direct 3267 injection of LPIs. 3268 3269 kvm-arm.wfe_trap_policy= 3270 [KVM,ARM] Control when to set WFE instruction trap for 3271 KVM VMs. Traps are allowed but not guaranteed by the 3272 CPU architecture. 3273 3274 trap: set WFE instruction trap 3275 3276 notrap: clear WFE instruction trap 3277 3278 kvm-arm.wfi_trap_policy= 3279 [KVM,ARM] Control when to set WFI instruction trap for 3280 KVM VMs. Traps are allowed but not guaranteed by the 3281 CPU architecture. 3282 3283 trap: set WFI instruction trap 3284 3285 notrap: clear WFI instruction trap 3286 3287 kvm_cma_resv_ratio=n [PPC,EARLY] 3288 Reserves given percentage from system memory area for 3289 contiguous memory allocation for KVM hash pagetable 3290 allocation. 3291 By default it reserves 5% of total system memory. 3292 Format: <integer> 3293 Default: 5 3294 3295 kvm-intel.ept= [KVM,Intel] Control KVM's use of Extended Page Tables, 3296 a.k.a. Two-Dimensional Page Tables. Default is 1 3297 (enabled). Disable by KVM if hardware lacks support 3298 for EPT. 3299 3300 kvm-intel.emulate_invalid_guest_state= 3301 [KVM,Intel] Control whether to emulate invalid guest 3302 state. Ignored if kvm-intel.enable_unrestricted_guest=1, 3303 as guest state is never invalid for unrestricted 3304 guests. This param doesn't apply to nested guests (L2), 3305 as KVM never emulates invalid L2 guest state. 3306 Default is 1 (enabled). 3307 3308 kvm-intel.flexpriority= 3309 [KVM,Intel] Control KVM's use of FlexPriority feature 3310 (TPR shadow). Default is 1 (enabled). Disable by KVM if 3311 hardware lacks support for it. 3312 3313 kvm-intel.nested= 3314 [KVM,Intel] Control nested virtualization feature in 3315 KVM/VMX. Default is 1 (enabled). 3316 3317 kvm-intel.unrestricted_guest= 3318 [KVM,Intel] Control KVM's use of unrestricted guest 3319 feature (virtualized real and unpaged mode). Default 3320 is 1 (enabled). Disable by KVM if EPT is disabled or 3321 hardware lacks support for it. 3322 3323 kvm-intel.vmentry_l1d_flush=[KVM,Intel] Mitigation for L1 Terminal Fault 3324 CVE-2018-3620. 3325 3326 Valid arguments: never, cond, always 3327 3328 always: L1D cache flush on every VMENTER. 3329 cond: Flush L1D on VMENTER only when the code between 3330 VMEXIT and VMENTER can leak host memory. 3331 never: Disables the mitigation 3332 3333 Default is cond (do L1 cache flush in specific instances) 3334 3335 kvm-intel.vpid= [KVM,Intel] Control KVM's use of Virtual Processor 3336 Identification feature (tagged TLBs). Default is 1 3337 (enabled). Disable by KVM if hardware lacks support 3338 for it. 3339 3340 l1d_flush= [X86,INTEL,EARLY] 3341 Control mitigation for L1D based snooping vulnerability. 3342 3343 Certain CPUs are vulnerable to an exploit against CPU 3344 internal buffers which can forward information to a 3345 disclosure gadget under certain conditions. 3346 3347 In vulnerable processors, the speculatively 3348 forwarded data can be used in a cache side channel 3349 attack, to access data to which the attacker does 3350 not have direct access. 3351 3352 This parameter controls the mitigation. The 3353 options are: 3354 3355 on - enable the interface for the mitigation 3356 3357 l1tf= [X86,EARLY] Control mitigation of the L1TF vulnerability on 3358 affected CPUs 3359 3360 The kernel PTE inversion protection is unconditionally 3361 enabled and cannot be disabled. 3362 3363 full 3364 Provides all available mitigations for the 3365 L1TF vulnerability. Disables SMT and 3366 enables all mitigations in the 3367 hypervisors, i.e. unconditional L1D flush. 3368 3369 SMT control and L1D flush control via the 3370 sysfs interface is still possible after 3371 boot. Hypervisors will issue a warning 3372 when the first VM is started in a 3373 potentially insecure configuration, 3374 i.e. SMT enabled or L1D flush disabled. 3375 3376 full,force 3377 Same as 'full', but disables SMT and L1D 3378 flush runtime control. Implies the 3379 'nosmt=force' command line option. 3380 (i.e. sysfs control of SMT is disabled.) 3381 3382 flush 3383 Leaves SMT enabled and enables the default 3384 hypervisor mitigation, i.e. conditional 3385 L1D flush. 3386 3387 SMT control and L1D flush control via the 3388 sysfs interface is still possible after 3389 boot. Hypervisors will issue a warning 3390 when the first VM is started in a 3391 potentially insecure configuration, 3392 i.e. SMT enabled or L1D flush disabled. 3393 3394 flush,nosmt 3395 3396 Disables SMT and enables the default 3397 hypervisor mitigation. 3398 3399 SMT control and L1D flush control via the 3400 sysfs interface is still possible after 3401 boot. Hypervisors will issue a warning 3402 when the first VM is started in a 3403 potentially insecure configuration, 3404 i.e. SMT enabled or L1D flush disabled. 3405 3406 flush,nowarn 3407 Same as 'flush', but hypervisors will not 3408 warn when a VM is started in a potentially 3409 insecure configuration. 3410 3411 off 3412 Disables hypervisor mitigations and doesn't 3413 emit any warnings. 3414 It also drops the swap size and available 3415 RAM limit restriction on both hypervisor and 3416 bare metal. 3417 3418 Default is 'flush'. 3419 3420 For details see: Documentation/admin-guide/hw-vuln/l1tf.rst 3421 3422 l2cr= [PPC] 3423 3424 l3cr= [PPC] 3425 3426 lapic [X86-32,APIC,EARLY] Enable the local APIC even if BIOS 3427 disabled it. 3428 3429 lapic= [X86,APIC] Do not use TSC deadline 3430 value for LAPIC timer one-shot implementation. Default 3431 back to the programmable timer unit in the LAPIC. 3432 Format: notscdeadline 3433 3434 lapic_timer_c2_ok [X86,APIC,EARLY] trust the local apic timer 3435 in C2 power state. 3436 3437 libata.dma= [LIBATA] DMA control 3438 libata.dma=0 Disable all PATA and SATA DMA 3439 libata.dma=1 PATA and SATA Disk DMA only 3440 libata.dma=2 ATAPI (CDROM) DMA only 3441 libata.dma=4 Compact Flash DMA only 3442 Combinations also work, so libata.dma=3 enables DMA 3443 for disks and CDROMs, but not CFs. 3444 3445 libata.ignore_hpa= [LIBATA] Ignore HPA limit 3446 libata.ignore_hpa=0 keep BIOS limits (default) 3447 libata.ignore_hpa=1 ignore limits, using full disk 3448 3449 libata.noacpi [LIBATA] Disables use of ACPI in libata suspend/resume 3450 when set. 3451 Format: <int> 3452 3453 libata.force= [LIBATA] Force configurations. The format is a comma- 3454 separated list of "[ID:]VAL" where ID is PORT[.DEVICE]. 3455 PORT and DEVICE are decimal numbers matching port, link 3456 or device. Basically, it matches the ATA ID string 3457 printed on console by libata. If the whole ID part is 3458 omitted, the last PORT and DEVICE values are used. If 3459 ID hasn't been specified yet, the configuration applies 3460 to all ports, links and devices. 3461 3462 If only DEVICE is omitted, the parameter applies to 3463 the port and all links and devices behind it. DEVICE 3464 number of 0 either selects the first device or the 3465 first fan-out link behind PMP device. It does not 3466 select the host link. DEVICE number of 15 selects the 3467 host link and device attached to it. 3468 3469 The VAL specifies the configuration to force. As long 3470 as there is no ambiguity, shortcut notation is allowed. 3471 For example, both 1.5 and 1.5G would work for 1.5Gbps. 3472 The following configurations can be forced. 3473 3474 * Cable type: 40c, 80c, short40c, unk, ign or sata. 3475 Any ID with matching PORT is used. 3476 3477 * SATA link speed limit: 1.5Gbps or 3.0Gbps. 3478 3479 * Transfer mode: pio[0-7], mwdma[0-4] and udma[0-7]. 3480 udma[/][16,25,33,44,66,100,133] notation is also 3481 allowed. 3482 3483 * nohrst, nosrst, norst: suppress hard, soft and both 3484 resets. 3485 3486 * rstonce: only attempt one reset during hot-unplug 3487 link recovery. 3488 3489 * [no]dbdelay: Enable or disable the extra 200ms delay 3490 before debouncing a link PHY and device presence 3491 detection. 3492 3493 * [no]ncq: Turn on or off NCQ. 3494 3495 * [no]ncqtrim: Enable or disable queued DSM TRIM. 3496 3497 * [no]ncqati: Enable or disable NCQ trim on ATI chipset. 3498 3499 * [no]trim: Enable or disable (unqueued) TRIM. 3500 3501 * trim_zero: Indicate that TRIM command zeroes data. 3502 3503 * max_trim_128m: Set 128M maximum trim size limit. 3504 3505 * [no]dma: Turn on or off DMA transfers. 3506 3507 * atapi_dmadir: Enable ATAPI DMADIR bridge support. 3508 3509 * atapi_mod16_dma: Enable the use of ATAPI DMA for 3510 commands that are not a multiple of 16 bytes. 3511 3512 * [no]dmalog: Enable or disable the use of the 3513 READ LOG DMA EXT command to access logs. 3514 3515 * [no]iddevlog: Enable or disable access to the 3516 identify device data log. 3517 3518 * [no]logdir: Enable or disable access to the general 3519 purpose log directory. 3520 3521 * max_sec=<sectors>: Set the transfer size limit, in 3522 number of 512-byte sectors, to the value specified in 3523 <sectors>. The value specified in <sectors> has to be 3524 a non-zero positive integer. 3525 3526 * max_sec_128: Set transfer size limit to 128 sectors. 3527 3528 * max_sec_1024: Set or clear transfer size limit to 3529 1024 sectors. 3530 3531 * max_sec_lba48: Set or clear transfer size limit to 3532 65535 sectors. 3533 3534 * external: Mark port as external (hotplug-capable). 3535 3536 * [no]lpm: Enable or disable link power management. 3537 3538 * [no]setxfer: Indicate if transfer speed mode setting 3539 should be skipped. 3540 3541 * [no]fua: Disable or enable FUA (Force Unit Access) 3542 support for devices supporting this feature. 3543 3544 * dump_id: Dump IDENTIFY data. 3545 3546 * disable: Disable this device. 3547 3548 If there are multiple matching configurations changing 3549 the same attribute, the last one is used. 3550 3551 liveupdate= [KNL,EARLY] 3552 Format: <bool> 3553 Enable Live Update Orchestrator (LUO). 3554 Default: off. 3555 3556 lockd.nlm_grace_period=P [NFS] Assign grace period. 3557 Format: <integer> 3558 3559 lockd.nlm_tcpport=N [NFS] Assign TCP port. 3560 Format: <integer> 3561 3562 lockd.nlm_timeout=T [NFS] Assign timeout value. 3563 Format: <integer> 3564 3565 lockd.nlm_udpport=M [NFS] Assign UDP port. 3566 Format: <integer> 3567 3568 lockdown= [SECURITY,EARLY] 3569 { integrity | confidentiality } 3570 Enable the kernel lockdown feature. If set to 3571 integrity, kernel features that allow userland to 3572 modify the running kernel are disabled. If set to 3573 confidentiality, kernel features that allow userland 3574 to extract confidential information from the kernel 3575 are also disabled. 3576 3577 locktorture.acq_writer_lim= [KNL] 3578 Set the time limit in jiffies for a lock 3579 acquisition. Acquisitions exceeding this limit 3580 will result in a splat once they do complete. 3581 3582 locktorture.bind_readers= [KNL] 3583 Specify the list of CPUs to which the readers are 3584 to be bound. 3585 3586 locktorture.bind_writers= [KNL] 3587 Specify the list of CPUs to which the writers are 3588 to be bound. 3589 3590 locktorture.call_rcu_chains= [KNL] 3591 Specify the number of self-propagating call_rcu() 3592 chains to set up. These are used to ensure that 3593 there is a high probability of an RCU grace period 3594 in progress at any given time. Defaults to 0, 3595 which disables these call_rcu() chains. 3596 3597 locktorture.long_hold= [KNL] 3598 Specify the duration in milliseconds for the 3599 occasional long-duration lock hold time. Defaults 3600 to 100 milliseconds. Select 0 to disable. 3601 3602 locktorture.nested_locks= [KNL] 3603 Specify the maximum lock nesting depth that 3604 locktorture is to exercise, up to a limit of 8 3605 (MAX_NESTED_LOCKS). Specify zero to disable. 3606 Note that this parameter is ineffective on types 3607 of locks that do not support nested acquisition. 3608 3609 locktorture.nreaders_stress= [KNL] 3610 Set the number of locking read-acquisition kthreads. 3611 Defaults to being automatically set based on the 3612 number of online CPUs. 3613 3614 locktorture.nwriters_stress= [KNL] 3615 Set the number of locking write-acquisition kthreads. 3616 3617 locktorture.onoff_holdoff= [KNL] 3618 Set time (s) after boot for CPU-hotplug testing. 3619 3620 locktorture.onoff_interval= [KNL] 3621 Set time (s) between CPU-hotplug operations, or 3622 zero to disable CPU-hotplug testing. 3623 3624 locktorture.rt_boost= [KNL] 3625 Do periodic testing of real-time lock priority 3626 boosting. Select 0 to disable, 1 to boost 3627 only rt_mutex, and 2 to boost unconditionally. 3628 Defaults to 2, which might seem to be an 3629 odd choice, but which should be harmless for 3630 non-real-time spinlocks, due to their disabling 3631 of preemption. Note that non-realtime mutexes 3632 disable boosting. 3633 3634 locktorture.rt_boost_factor= [KNL] 3635 Number that determines how often and for how 3636 long priority boosting is exercised. This is 3637 scaled down by the number of writers, so that the 3638 number of boosts per unit time remains roughly 3639 constant as the number of writers increases. 3640 On the other hand, the duration of each boost 3641 increases with the number of writers. 3642 3643 locktorture.shuffle_interval= [KNL] 3644 Set task-shuffle interval (jiffies). Shuffling 3645 tasks allows some CPUs to go into dyntick-idle 3646 mode during the locktorture test. 3647 3648 locktorture.shutdown_secs= [KNL] 3649 Set time (s) after boot system shutdown. This 3650 is useful for hands-off automated testing. 3651 3652 locktorture.stat_interval= [KNL] 3653 Time (s) between statistics printk()s. 3654 3655 locktorture.stutter= [KNL] 3656 Time (s) to stutter testing, for example, 3657 specifying five seconds causes the test to run for 3658 five seconds, wait for five seconds, and so on. 3659 This tests the locking primitive's ability to 3660 transition abruptly to and from idle. 3661 3662 locktorture.torture_type= [KNL] 3663 Specify the locking implementation to test. 3664 3665 locktorture.verbose= [KNL] 3666 Enable additional printk() statements. 3667 3668 locktorture.writer_fifo= [KNL] 3669 Run the write-side locktorture kthreads at 3670 sched_set_fifo() real-time priority. 3671 3672 logibm.irq= [HW,MOUSE] Logitech Bus Mouse Driver 3673 Format: <irq> 3674 3675 loglevel= [KNL,EARLY] 3676 All Kernel Messages with a loglevel smaller than the 3677 console loglevel will be printed to the console. It can 3678 also be changed with klogd or other programs. The 3679 loglevels are defined as follows: 3680 3681 0 (KERN_EMERG) system is unusable 3682 1 (KERN_ALERT) action must be taken immediately 3683 2 (KERN_CRIT) critical conditions 3684 3 (KERN_ERR) error conditions 3685 4 (KERN_WARNING) warning conditions 3686 5 (KERN_NOTICE) normal but significant condition 3687 6 (KERN_INFO) informational 3688 7 (KERN_DEBUG) debug-level messages 3689 3690 log_buf_len=n[KMG] [KNL,EARLY] 3691 Sets the size of the printk ring buffer, in bytes. 3692 n must be a power of two and greater than the 3693 minimal size. The minimal size is defined by 3694 LOG_BUF_SHIFT kernel config parameter. There 3695 is also CONFIG_LOG_CPU_MAX_BUF_SHIFT config 3696 parameter that allows to increase the default size 3697 depending on the number of CPUs. See init/Kconfig 3698 for more details. 3699 3700 logo.nologo [FB] Disables display of the built-in Linux logo. 3701 This may be used to provide more screen space for 3702 kernel log messages and is useful when debugging 3703 kernel boot problems. 3704 3705 lp=0 [LP] Specify parallel ports to use, e.g, 3706 lp=port[,port...] lp=none,parport0 (lp0 not configured, lp1 uses 3707 lp=reset first parallel port). 'lp=0' disables the 3708 lp=auto printer driver. 'lp=reset' (which can be 3709 specified in addition to the ports) causes 3710 attached printers to be reset. Using 3711 lp=port1,port2,... specifies the parallel ports 3712 to associate lp devices with, starting with 3713 lp0. A port specification may be 'none' to skip 3714 that lp device, or a parport name such as 3715 'parport0'. Specifying 'lp=auto' instead of a 3716 port specification list means that device IDs 3717 from each port should be examined, to see if 3718 an IEEE 1284-compliant printer is attached; if 3719 so, the driver will manage that printer. 3720 See also header of drivers/char/lp.c. 3721 3722 lpj=n [KNL] 3723 Sets loops_per_jiffy to given constant, thus avoiding 3724 time-consuming boot-time autodetection (up to 250 ms per 3725 CPU). 0 enables autodetection (default). To determine 3726 the correct value for your kernel, boot with normal 3727 autodetection and see what value is printed. Note that 3728 on SMP systems the preset will be applied to all CPUs, 3729 which is likely to cause problems if your CPUs need 3730 significantly divergent settings. An incorrect value 3731 will cause delays in the kernel to be wrong, leading to 3732 unpredictable I/O errors and other breakage. Although 3733 unlikely, in the extreme case this might damage your 3734 hardware. 3735 3736 lsm.debug [SECURITY] Enable LSM initialization debugging output. 3737 3738 lsm=lsm1,...,lsmN 3739 [SECURITY] Choose order of LSM initialization. This 3740 overrides CONFIG_LSM, and the "security=" parameter. 3741 3742 machtype= [Loongson] Share the same kernel image file between 3743 different yeeloong laptops. 3744 Example: machtype=lemote-yeeloong-2f-7inch 3745 3746 maxcpus= [SMP,EARLY] Maximum number of processors that an SMP kernel 3747 will bring up during bootup. maxcpus=n : n >= 0 limits 3748 the kernel to bring up 'n' processors. Surely after 3749 bootup you can bring up the other plugged cpu by executing 3750 "echo 1 > /sys/devices/system/cpu/cpuX/online". So maxcpus 3751 only takes effect during system bootup. 3752 While n=0 is a special case, it is equivalent to "nosmp", 3753 which also disables the IO APIC. 3754 3755 max_loop= [LOOP] The number of loop block devices that get 3756 (loop.max_loop) unconditionally pre-created at init time. The default 3757 number is configured by BLK_DEV_LOOP_MIN_COUNT. Instead 3758 of statically allocating a predefined number, loop 3759 devices can be requested on-demand with the 3760 /dev/loop-control interface. 3761 3762 mce= [X86-{32,64}] 3763 3764 Please see Documentation/arch/x86/x86_64/machinecheck.rst for sysfs runtime tunables. 3765 3766 off 3767 disable machine check 3768 3769 no_cmci 3770 disable CMCI(Corrected Machine Check Interrupt) that 3771 Intel processor supports. Usually this disablement is 3772 not recommended, but it might be handy if your 3773 hardware is misbehaving. 3774 3775 Note that you'll get more problems without CMCI than 3776 with due to the shared banks, i.e. you might get 3777 duplicated error logs. 3778 3779 dont_log_ce 3780 don't make logs for corrected errors. All events 3781 reported as corrected are silently cleared by OS. This 3782 option will be useful if you have no interest in any 3783 of corrected errors. 3784 3785 ignore_ce 3786 disable features for corrected errors, e.g. 3787 polling timer and CMCI. All events reported as 3788 corrected are not cleared by OS and remained in its 3789 error banks. 3790 3791 Usually this disablement is not recommended, however 3792 if there is an agent checking/clearing corrected 3793 errors (e.g. BIOS or hardware monitoring 3794 applications), conflicting with OS's error handling, 3795 and you cannot deactivate the agent, then this option 3796 will be a help. 3797 3798 no_lmce 3799 do not opt-in to Local MCE delivery. Use legacy method 3800 to broadcast MCEs. 3801 3802 bootlog 3803 enable logging of machine checks left over from 3804 booting. Disabled by default on AMD Fam10h and older 3805 because some BIOS leave bogus ones. 3806 3807 If your BIOS doesn't do that it's a good idea to 3808 enable though to make sure you log even machine check 3809 events that result in a reboot. On Intel systems it is 3810 enabled by default. 3811 3812 nobootlog 3813 disable boot machine check logging. 3814 3815 monarchtimeout (number) 3816 sets the time in us to wait for other CPUs on machine 3817 checks. 0 to disable. 3818 3819 bios_cmci_threshold 3820 don't overwrite the bios-set CMCI threshold. This boot 3821 option prevents Linux from overwriting the CMCI 3822 threshold set by the bios. Without this option, Linux 3823 always sets the CMCI threshold to 1. Enabling this may 3824 make memory predictive failure analysis less effective 3825 if the bios sets thresholds for memory errors since we 3826 will not see details for all errors. 3827 3828 recovery 3829 force-enable recoverable machine check code paths 3830 3831 Everything else is in sysfs now. 3832 3833 3834 md= [HW] RAID subsystems devices and level 3835 See Documentation/admin-guide/md.rst. 3836 3837 mdacon= [MDA] 3838 Format: <first>,<last> 3839 Specifies range of consoles to be captured by the MDA. 3840 3841 mds= [X86,INTEL,EARLY] 3842 Control mitigation for the Micro-architectural Data 3843 Sampling (MDS) vulnerability. 3844 3845 Certain CPUs are vulnerable to an exploit against CPU 3846 internal buffers which can forward information to a 3847 disclosure gadget under certain conditions. 3848 3849 In vulnerable processors, the speculatively 3850 forwarded data can be used in a cache side channel 3851 attack, to access data to which the attacker does 3852 not have direct access. 3853 3854 This parameter controls the MDS mitigation. The 3855 options are: 3856 3857 full - Enable MDS mitigation on vulnerable CPUs 3858 full,nosmt - Enable MDS mitigation and disable 3859 SMT on vulnerable CPUs 3860 off - Unconditionally disable MDS mitigation 3861 3862 On TAA-affected machines, mds=off can be prevented by 3863 an active TAA mitigation as both vulnerabilities are 3864 mitigated with the same mechanism so in order to disable 3865 this mitigation, you need to specify tsx_async_abort=off 3866 too. 3867 3868 Not specifying this option is equivalent to 3869 mds=full. 3870 3871 For details see: Documentation/admin-guide/hw-vuln/mds.rst 3872 3873 mem=nn[KMG] [HEXAGON,EARLY] Set the memory size. 3874 Must be specified, otherwise memory size will be 0. 3875 3876 mem=nn[KMG] [KNL,BOOT,EARLY] Force usage of a specific amount 3877 of memory Amount of memory to be used in cases 3878 as follows: 3879 3880 1 for test; 3881 2 when the kernel is not able to see the whole system memory; 3882 3 memory that lies after 'mem=' boundary is excluded from 3883 the hypervisor, then assigned to KVM guests. 3884 4 to limit the memory available for kdump kernel. 3885 3886 [ARC,MICROBLAZE] - the limit applies only to low memory, 3887 high memory is not affected. 3888 3889 [ARM64] - only limits memory covered by the linear 3890 mapping. The NOMAP regions are not affected. 3891 3892 [X86] Work as limiting max address. Use together 3893 with memmap= to avoid physical address space collisions. 3894 Without memmap= PCI devices could be placed at addresses 3895 belonging to unused RAM. 3896 3897 Note that this only takes effects during boot time since 3898 in above case 3, memory may need be hot added after boot 3899 if system memory of hypervisor is not sufficient. 3900 3901 mem=nn[KMG]@ss[KMG] 3902 [ARM,MIPS,EARLY] - override the memory layout 3903 reported by firmware. 3904 Define a memory region of size nn[KMG] starting at 3905 ss[KMG]. 3906 Multiple different regions can be specified with 3907 multiple mem= parameters on the command line. 3908 3909 mem=nopentium [BUGS=X86-32] Disable usage of 4MB pages for kernel 3910 memory. 3911 3912 memblock=debug [KNL,EARLY] Enable memblock debug messages. 3913 3914 memchunk=nn[KMG] 3915 [KNL,SH] Allow user to override the default size for 3916 per-device physically contiguous DMA buffers. 3917 3918 memhp_default_state=online/offline/online_kernel/online_movable 3919 [KNL] Set the initial state for the memory hotplug 3920 onlining policy. If not specified, the default value is 3921 set according to the 3922 CONFIG_MHP_DEFAULT_ONLINE_TYPE kernel config 3923 options. 3924 See Documentation/admin-guide/mm/memory-hotplug.rst. 3925 3926 memmap=exactmap [KNL,X86,EARLY] Enable setting of an exact 3927 E820 memory map, as specified by the user. 3928 Such memmap=exactmap lines can be constructed based on 3929 BIOS output or other requirements. See the memmap=nn@ss 3930 option description. 3931 3932 memmap=nn[KMG]@ss[KMG] 3933 [KNL, X86,MIPS,XTENSA,EARLY] Force usage of a specific region of memory. 3934 Region of memory to be used is from ss to ss+nn. 3935 If @ss[KMG] is omitted, it is equivalent to mem=nn[KMG], 3936 which limits max address to nn[KMG]. 3937 Multiple different regions can be specified, 3938 comma delimited. 3939 Example: 3940 memmap=100M@2G,100M#3G,1G!1024G 3941 3942 memmap=nn[KMG]#ss[KMG] 3943 [KNL,ACPI,EARLY] Mark specific memory as ACPI data. 3944 Region of memory to be marked is from ss to ss+nn. 3945 3946 memmap=nn[KMG]$ss[KMG] 3947 [KNL,ACPI,EARLY] Mark specific memory as reserved. 3948 Region of memory to be reserved is from ss to ss+nn. 3949 Example: Exclude memory from 0x18690000-0x1869ffff 3950 memmap=64K$0x18690000 3951 or 3952 memmap=0x10000$0x18690000 3953 Some bootloaders may need an escape character before '$', 3954 like Grub2, otherwise '$' and the following number 3955 will be eaten. 3956 3957 memmap=nn[KMG]!ss[KMG,EARLY] 3958 [KNL,X86] Mark specific memory as protected. 3959 Region of memory to be used, from ss to ss+nn. 3960 The memory region may be marked as e820 type 12 (0xc) 3961 and is NVDIMM or ADR memory. 3962 3963 memmap=<size>%<offset>-<oldtype>+<newtype> 3964 [KNL,ACPI,EARLY] Convert memory within the specified region 3965 from <oldtype> to <newtype>. If "-<oldtype>" is left 3966 out, the whole region will be marked as <newtype>, 3967 even if previously unavailable. If "+<newtype>" is left 3968 out, matching memory will be removed. Types are 3969 specified as e820 types, e.g., 1 = RAM, 2 = reserved, 3970 3 = ACPI, 12 = PRAM. 3971 3972 memory_corruption_check=0/1 [X86,EARLY] 3973 Some BIOSes seem to corrupt the first 64k of 3974 memory when doing things like suspend/resume. 3975 Setting this option will scan the memory 3976 looking for corruption. Enabling this will 3977 both detect corruption and prevent the kernel 3978 from using the memory being corrupted. 3979 However, it's intended as a diagnostic tool; if 3980 repeatable BIOS-originated corruption always 3981 affects the same memory, you can use memmap= 3982 to prevent the kernel from using that memory. 3983 3984 memory_corruption_check_size=size [X86,EARLY] 3985 By default it checks for corruption in the low 3986 64k, making this memory unavailable for normal 3987 use. Use this parameter to scan for 3988 corruption in more or less memory. 3989 3990 memory_corruption_check_period=seconds [X86,EARLY] 3991 By default it checks for corruption every 60 3992 seconds. Use this parameter to check at some 3993 other rate. 0 disables periodic checking. 3994 3995 memory_hotplug.memmap_on_memory 3996 [KNL,X86,ARM] Boolean flag to enable this feature. 3997 Format: {on | off (default)} 3998 When enabled, runtime hotplugged memory will 3999 allocate its internal metadata (struct pages, 4000 those vmemmap pages cannot be optimized even 4001 if hugetlb_free_vmemmap is enabled) from the 4002 hotadded memory which will allow to hotadd a 4003 lot of memory without requiring additional 4004 memory to do so. 4005 This feature is disabled by default because it 4006 has some implication on large (e.g. GB) 4007 allocations in some configurations (e.g. small 4008 memory blocks). 4009 The state of the flag can be read in 4010 /sys/module/memory_hotplug/parameters/memmap_on_memory. 4011 Note that even when enabled, there are a few cases where 4012 the feature is not effective. 4013 4014 memtest= [KNL,X86,ARM,M68K,PPC,RISCV,EARLY] Enable memtest 4015 Format: <integer> 4016 default : 0 <disable> 4017 Specifies the number of memtest passes to be 4018 performed. Each pass selects another test 4019 pattern from a given set of patterns. Memtest 4020 fills the memory with this pattern, validates 4021 memory contents and reserves bad memory 4022 regions that are detected. 4023 4024 mem_encrypt= [X86-64] AMD Secure Memory Encryption (SME) control 4025 Valid arguments: on, off 4026 Default: off 4027 mem_encrypt=on: Activate SME 4028 mem_encrypt=off: Do not activate SME 4029 4030 Refer to Documentation/virt/kvm/x86/amd-memory-encryption.rst 4031 for details on when memory encryption can be activated. 4032 4033 mem_sleep_default= [SUSPEND] Default system suspend mode: 4034 s2idle - Suspend-To-Idle 4035 shallow - Power-On Suspend or equivalent (if supported) 4036 deep - Suspend-To-RAM or equivalent (if supported) 4037 See Documentation/admin-guide/pm/sleep-states.rst. 4038 4039 mfgptfix [X86-32] Fix MFGPT timers on AMD Geode platforms when 4040 the BIOS has incorrectly applied a workaround. TinyBIOS 4041 version 0.98 is known to be affected, 0.99 fixes the 4042 problem by letting the user disable the workaround. 4043 4044 mga= [HW,DRM] 4045 4046 microcode= [X86] Control the behavior of the microcode loader. 4047 Available options, comma separated: 4048 4049 base_rev=X - with <X> with format: <u32> 4050 Set the base microcode revision of each thread when in 4051 debug mode. 4052 4053 dis_ucode_ldr: disable the microcode loader 4054 4055 force_minrev: 4056 Enable or disable the microcode minimal revision 4057 enforcement for the runtime microcode loader. 4058 4059 mini2440= [ARM,HW,KNL] 4060 Format:[0..2][b][c][t] 4061 Default: "0tb" 4062 MINI2440 configuration specification: 4063 0 - The attached screen is the 3.5" TFT 4064 1 - The attached screen is the 7" TFT 4065 2 - The VGA Shield is attached (1024x768) 4066 Leaving out the screen size parameter will not load 4067 the TFT driver, and the framebuffer will be left 4068 unconfigured. 4069 b - Enable backlight. The TFT backlight pin will be 4070 linked to the kernel VESA blanking code and a GPIO 4071 LED. This parameter is not necessary when using the 4072 VGA shield. 4073 c - Enable the s3c camera interface. 4074 t - Reserved for enabling touchscreen support. The 4075 touchscreen support is not enabled in the mainstream 4076 kernel as of 2.6.30, a preliminary port can be found 4077 in the "bleeding edge" mini2440 support kernel at 4078 https://repo.or.cz/w/linux-2.6/mini2440.git 4079 4080 mitigations= 4081 [X86,PPC,S390,ARM64,EARLY] Control optional mitigations for 4082 CPU vulnerabilities. This is a set of curated, 4083 arch-independent options, each of which is an 4084 aggregation of existing arch-specific options. 4085 4086 Note, "mitigations" is supported if and only if the 4087 kernel was built with CPU_MITIGATIONS=y. 4088 4089 off 4090 Disable all optional CPU mitigations. This 4091 improves system performance, but it may also 4092 expose users to several CPU vulnerabilities. 4093 Equivalent to: if nokaslr then kpti=0 [ARM64] 4094 gather_data_sampling=off [X86] 4095 indirect_target_selection=off [X86] 4096 kvm.nx_huge_pages=off [X86] 4097 l1tf=off [X86] 4098 mds=off [X86] 4099 mmio_stale_data=off [X86] 4100 no_entry_flush [PPC] 4101 no_uaccess_flush [PPC] 4102 nobp=0 [S390] 4103 nopti [X86,PPC] 4104 nospectre_bhb [ARM64] 4105 nospectre_v1 [X86,PPC] 4106 nospectre_v2 [X86,PPC,S390,ARM64] 4107 reg_file_data_sampling=off [X86] 4108 retbleed=off [X86] 4109 spec_rstack_overflow=off [X86] 4110 spec_store_bypass_disable=off [X86,PPC] 4111 spectre_bhi=off [X86] 4112 spectre_v2_user=off [X86] 4113 srbds=off [X86,INTEL] 4114 ssbd=force-off [ARM64] 4115 tsa=off [X86,AMD] 4116 tsx_async_abort=off [X86] 4117 vmscape=off [X86] 4118 4119 Exceptions: 4120 This does not have any effect on 4121 kvm.nx_huge_pages when 4122 kvm.nx_huge_pages=force. 4123 4124 auto (default) 4125 Mitigate all CPU vulnerabilities, but leave SMT 4126 enabled, even if it's vulnerable. This is for 4127 users who don't want to be surprised by SMT 4128 getting disabled across kernel upgrades, or who 4129 have other ways of avoiding SMT-based attacks. 4130 Equivalent to: (default behavior) 4131 4132 auto,nosmt 4133 Mitigate all CPU vulnerabilities, disabling SMT 4134 if needed. This is for users who always want to 4135 be fully mitigated, even if it means losing SMT. 4136 Equivalent to: l1tf=flush,nosmt [X86] 4137 mds=full,nosmt [X86] 4138 tsx_async_abort=full,nosmt [X86] 4139 mmio_stale_data=full,nosmt [X86] 4140 retbleed=auto,nosmt [X86] 4141 4142 [X86] After one of the above options, additionally 4143 supports attack-vector based controls as documented in 4144 Documentation/admin-guide/hw-vuln/attack_vector_controls.rst 4145 4146 mminit_loglevel= 4147 [KNL,EARLY] When CONFIG_DEBUG_MEMORY_INIT is set, this 4148 parameter allows control of the logging verbosity for 4149 the additional memory initialisation checks. A value 4150 of 0 disables mminit logging and a level of 4 will 4151 log everything. Information is printed at KERN_DEBUG 4152 so loglevel=8 may also need to be specified. 4153 4154 mmio_stale_data= 4155 [X86,INTEL,EARLY] Control mitigation for the Processor 4156 MMIO Stale Data vulnerabilities. 4157 4158 Processor MMIO Stale Data is a class of 4159 vulnerabilities that may expose data after an MMIO 4160 operation. Exposed data could originate or end in 4161 the same CPU buffers as affected by MDS and TAA. 4162 Therefore, similar to MDS and TAA, the mitigation 4163 is to clear the affected CPU buffers. 4164 4165 This parameter controls the mitigation. The 4166 options are: 4167 4168 full - Enable mitigation on vulnerable CPUs 4169 4170 full,nosmt - Enable mitigation and disable SMT on 4171 vulnerable CPUs. 4172 4173 off - Unconditionally disable mitigation 4174 4175 On MDS or TAA affected machines, 4176 mmio_stale_data=off can be prevented by an active 4177 MDS or TAA mitigation as these vulnerabilities are 4178 mitigated with the same mechanism so in order to 4179 disable this mitigation, you need to specify 4180 mds=off and tsx_async_abort=off too. 4181 4182 Not specifying this option is equivalent to 4183 mmio_stale_data=full. 4184 4185 For details see: 4186 Documentation/admin-guide/hw-vuln/processor_mmio_stale_data.rst 4187 4188 <module>.async_probe[=<bool>] [KNL] 4189 If no <bool> value is specified or if the value 4190 specified is not a valid <bool>, enable asynchronous 4191 probe on this module. Otherwise, enable/disable 4192 asynchronous probe on this module as indicated by the 4193 <bool> value. See also: module.async_probe 4194 4195 module.async_probe=<bool> 4196 [KNL] When set to true, modules will use async probing 4197 by default. To enable/disable async probing for a 4198 specific module, use the module specific control that 4199 is documented under <module>.async_probe. When both 4200 module.async_probe and <module>.async_probe are 4201 specified, <module>.async_probe takes precedence for 4202 the specific module. 4203 4204 module.enable_dups_trace 4205 [KNL] When CONFIG_MODULE_DEBUG_AUTOLOAD_DUPS is set, 4206 this means that duplicate request_module() calls will 4207 trigger a WARN_ON() instead of a pr_warn(). Note that 4208 if MODULE_DEBUG_AUTOLOAD_DUPS_TRACE is set, WARN_ON()s 4209 will always be issued and this option does nothing. 4210 module.sig_enforce 4211 [KNL] When CONFIG_MODULE_SIG is set, this means that 4212 modules without (valid) signatures will fail to load. 4213 Note that if CONFIG_MODULE_SIG_FORCE is set, that 4214 is always true, so this option does nothing. 4215 4216 module_blacklist= [KNL] Do not load a comma-separated list of 4217 modules. Useful for debugging problem modules. 4218 4219 mousedev.tap_time= 4220 [MOUSE] Maximum time between finger touching and 4221 leaving touchpad surface for touch to be considered 4222 a tap and be reported as a left button click (for 4223 touchpads working in absolute mode only). 4224 Format: <msecs> 4225 mousedev.xres= [MOUSE] Horizontal screen resolution, used for devices 4226 reporting absolute coordinates, such as tablets 4227 mousedev.yres= [MOUSE] Vertical screen resolution, used for devices 4228 reporting absolute coordinates, such as tablets 4229 4230 movablecore= [KNL,X86,PPC,EARLY] 4231 Format: nn[KMGTPE] | nn% 4232 This parameter is the complement to kernelcore=, it 4233 specifies the amount of memory used for migratable 4234 allocations. If both kernelcore and movablecore is 4235 specified, then kernelcore will be at *least* the 4236 specified value but may be more. If movablecore on its 4237 own is specified, the administrator must be careful 4238 that the amount of memory usable for all allocations 4239 is not too small. 4240 4241 movable_node [KNL,EARLY] Boot-time switch to make hotplugable memory 4242 NUMA nodes to be movable. This means that the memory 4243 of such nodes will be usable only for movable 4244 allocations which rules out almost all kernel 4245 allocations. Use with caution! 4246 4247 MTD_Partition= [MTD] 4248 Format: <name>,<region-number>,<size>,<offset> 4249 4250 MTD_Region= [MTD] Format: 4251 <name>,<region-number>[,<base>,<size>,<buswidth>,<altbuswidth>] 4252 4253 mtdparts= [MTD] 4254 See drivers/mtd/parsers/cmdlinepart.c 4255 4256 mtouchusb.raw_coordinates= 4257 [HW] Make the MicroTouch USB driver use raw coordinates 4258 ('y', default) or cooked coordinates ('n') 4259 4260 mtrr=debug [X86,EARLY] 4261 Enable printing debug information related to MTRR 4262 registers at boot time. 4263 4264 mtrr_chunk_size=nn[KMG,X86,EARLY] 4265 used for mtrr cleanup. It is largest continuous chunk 4266 that could hold holes aka. UC entries. 4267 4268 mtrr_gran_size=nn[KMG,X86,EARLY] 4269 Used for mtrr cleanup. It is granularity of mtrr block. 4270 Default is 1. 4271 Large value could prevent small alignment from 4272 using up MTRRs. 4273 4274 mtrr_spare_reg_nr=n [X86,EARLY] 4275 Format: <integer> 4276 Range: 0,7 : spare reg number 4277 Default : 1 4278 Used for mtrr cleanup. It is spare mtrr entries number. 4279 Set to 2 or more if your graphical card needs more. 4280 4281 multitce=off [PPC] This parameter disables the use of the pSeries 4282 firmware feature for updating multiple TCE entries 4283 at a time. 4284 4285 n2= [NET] SDL Inc. RISCom/N2 synchronous serial card 4286 4287 netdev= [NET] Network devices parameters 4288 Format: <irq>,<io>,<mem_start>,<mem_end>,<name> 4289 Note that mem_start is often overloaded to mean 4290 something different and driver-specific. 4291 This usage is only documented in each driver source 4292 file if at all. 4293 4294 netpoll.carrier_timeout= 4295 [NET] Specifies amount of time (in seconds) that 4296 netpoll should wait for a carrier. By default netpoll 4297 waits 4 seconds. 4298 4299 nf_conntrack.acct= 4300 [NETFILTER] Enable connection tracking flow accounting 4301 0 to disable accounting 4302 1 to enable accounting 4303 Default value is 0. 4304 4305 nfs.cache_getent= 4306 [NFS] sets the pathname to the program which is used 4307 to update the NFS client cache entries. 4308 4309 nfs.cache_getent_timeout= 4310 [NFS] sets the timeout after which an attempt to 4311 update a cache entry is deemed to have failed. 4312 4313 nfs.callback_nr_threads= 4314 [NFSv4] set the total number of threads that the 4315 NFS client will assign to service NFSv4 callback 4316 requests. 4317 4318 nfs.callback_tcpport= 4319 [NFS] set the TCP port on which the NFSv4 callback 4320 channel should listen. 4321 4322 nfs.delay_retrans= 4323 [NFS] specifies the number of times the NFSv4 client 4324 retries the request before returning an EAGAIN error, 4325 after a reply of NFS4ERR_DELAY from the server. 4326 Only applies if the softerr mount option is enabled, 4327 and the specified value is >= 0. 4328 4329 nfs.enable_ino64= 4330 [NFS] enable 64-bit inode numbers. 4331 If zero, the NFS client will fake up a 32-bit inode 4332 number for the readdir() and stat() syscalls instead 4333 of returning the full 64-bit number. 4334 The default is to return 64-bit inode numbers. 4335 4336 nfs.idmap_cache_timeout= 4337 [NFS] set the maximum lifetime for idmapper cache 4338 entries. 4339 4340 nfs.max_session_cb_slots= 4341 [NFSv4.1] Sets the maximum number of session 4342 slots the client will assign to the callback 4343 channel. This determines the maximum number of 4344 callbacks the client will process in parallel for 4345 a particular server. 4346 4347 nfs.max_session_slots= 4348 [NFSv4.1] Sets the maximum number of session slots 4349 the client will attempt to negotiate with the server. 4350 This limits the number of simultaneous RPC requests 4351 that the client can send to the NFSv4.1 server. 4352 Note that there is little point in setting this 4353 value higher than the max_tcp_slot_table_limit. 4354 4355 nfs.nfs4_disable_idmapping= 4356 [NFSv4] When set to the default of '1', this option 4357 ensures that both the RPC level authentication 4358 scheme and the NFS level operations agree to use 4359 numeric uids/gids if the mount is using the 4360 'sec=sys' security flavour. In effect it is 4361 disabling idmapping, which can make migration from 4362 legacy NFSv2/v3 systems to NFSv4 easier. 4363 Servers that do not support this mode of operation 4364 will be autodetected by the client, and it will fall 4365 back to using the idmapper. 4366 To turn off this behaviour, set the value to '0'. 4367 4368 nfs.nfs4_unique_id= 4369 [NFS4] Specify an additional fixed unique ident- 4370 ification string that NFSv4 clients can insert into 4371 their nfs_client_id4 string. This is typically a 4372 UUID that is generated at system install time. 4373 4374 nfs.recover_lost_locks= 4375 [NFSv4] Attempt to recover locks that were lost due 4376 to a lease timeout on the server. Please note that 4377 doing this risks data corruption, since there are 4378 no guarantees that the file will remain unchanged 4379 after the locks are lost. 4380 If you want to enable the kernel legacy behaviour of 4381 attempting to recover these locks, then set this 4382 parameter to '1'. 4383 The default parameter value of '0' causes the kernel 4384 not to attempt recovery of lost locks. 4385 4386 nfs.send_implementation_id= 4387 [NFSv4.1] Send client implementation identification 4388 information in exchange_id requests. 4389 If zero, no implementation identification information 4390 will be sent. 4391 The default is to send the implementation identification 4392 information. 4393 4394 nfs4.layoutstats_timer= 4395 [NFSv4.2] Change the rate at which the kernel sends 4396 layoutstats to the pNFS metadata server. 4397 4398 Setting this to value to 0 causes the kernel to use 4399 whatever value is the default set by the layout 4400 driver. A non-zero value sets the minimum interval 4401 in seconds between layoutstats transmissions. 4402 4403 nfsd.inter_copy_offload_enable= 4404 [NFSv4.2] When set to 1, the server will support 4405 server-to-server copies for which this server is 4406 the destination of the copy. 4407 4408 nfsd.nfs4_disable_idmapping= 4409 [NFSv4] When set to the default of '1', the NFSv4 4410 server will return only numeric uids and gids to 4411 clients using auth_sys, and will accept numeric uids 4412 and gids from such clients. This is intended to ease 4413 migration from NFSv2/v3. 4414 4415 nfsd.nfsd4_ssc_umount_timeout= 4416 [NFSv4.2] When used as the destination of a 4417 server-to-server copy, knfsd temporarily mounts 4418 the source server. It caches the mount in case 4419 it will be needed again, and discards it if not 4420 used for the number of milliseconds specified by 4421 this parameter. 4422 4423 nfsaddrs= [NFS] Deprecated. Use ip= instead. 4424 See Documentation/admin-guide/nfs/nfsroot.rst. 4425 4426 nfsroot= [NFS] nfs root filesystem for disk-less boxes. 4427 See Documentation/admin-guide/nfs/nfsroot.rst. 4428 4429 nfsrootdebug [NFS] enable nfsroot debugging messages. 4430 See Documentation/admin-guide/nfs/nfsroot.rst. 4431 4432 nmi_backtrace.backtrace_idle [KNL] 4433 Dump stacks even of idle CPUs in response to an 4434 NMI stack-backtrace request. 4435 4436 nmi_debug= [KNL,SH] Specify one or more actions to take 4437 when a NMI is triggered. 4438 Format: [state][,regs][,debounce][,die] 4439 4440 nmi_watchdog= [KNL,BUGS=X86] Debugging features for SMP kernels 4441 Format: [panic,][nopanic,][rNNN,][num] 4442 Valid num: 0 or 1 4443 0 - turn hardlockup detector in nmi_watchdog off 4444 1 - turn hardlockup detector in nmi_watchdog on 4445 rNNN - configure the watchdog with raw perf event 0xNNN 4446 4447 When panic is specified, panic when an NMI watchdog 4448 timeout occurs (or 'nopanic' to not panic on an NMI 4449 watchdog, if CONFIG_BOOTPARAM_HARDLOCKUP_PANIC is set) 4450 To disable both hard and soft lockup detectors, 4451 please see 'nowatchdog'. 4452 This is useful when you use a panic=... timeout and 4453 need the box quickly up again. 4454 4455 These settings can be accessed at runtime via 4456 the nmi_watchdog and hardlockup_panic sysctls. 4457 4458 no387 [BUGS=X86-32] Tells the kernel to use the 387 maths 4459 emulation library even if a 387 maths coprocessor 4460 is present. 4461 4462 no4lvl [RISCV,EARLY] Disable 4-level and 5-level paging modes. 4463 Forces kernel to use 3-level paging instead. 4464 4465 no5lvl [X86-64,RISCV,EARLY] Disable 5-level paging mode. Forces 4466 kernel to use 4-level paging instead. 4467 4468 noalign [KNL,ARM] 4469 4470 noapic [SMP,APIC,EARLY] Tells the kernel to not make use of any 4471 IOAPICs that may be present in the system. 4472 4473 noapictimer [APIC,X86] Don't set up the APIC timer 4474 4475 noautogroup Disable scheduler automatic task group creation. 4476 4477 nocache [ARM,EARLY] 4478 4479 no_console_suspend 4480 [HW] Never suspend the console 4481 Disable suspending of consoles during suspend and 4482 hibernate operations. Once disabled, debugging 4483 messages can reach various consoles while the rest 4484 of the system is being put to sleep (ie, while 4485 debugging driver suspend/resume hooks). This may 4486 not work reliably with all consoles, but is known 4487 to work with serial and VGA consoles. 4488 To facilitate more flexible debugging, we also add 4489 console_suspend, a printk module parameter to control 4490 it. Users could use console_suspend (usually 4491 /sys/module/printk/parameters/console_suspend) to 4492 turn on/off it dynamically. 4493 4494 no_debug_objects 4495 [KNL,EARLY] Disable object debugging 4496 4497 nodsp [SH] Disable hardware DSP at boot time. 4498 4499 noefi [EFI,EARLY] Disable EFI runtime services support. 4500 4501 no_entry_flush [PPC,EARLY] Don't flush the L1-D cache when entering the kernel. 4502 4503 noexec32 [X86-64] 4504 This affects only 32-bit executables. 4505 noexec32=on: enable non-executable mappings (default) 4506 read doesn't imply executable mappings 4507 noexec32=off: disable non-executable mappings 4508 read implies executable mappings 4509 4510 no_file_caps Tells the kernel not to honor file capabilities. The 4511 only way then for a file to be executed with privilege 4512 is to be setuid root or executed by root. 4513 4514 nofpu [MIPS,SH] Disable hardware FPU at boot time. 4515 4516 nofsgsbase [X86] Disables FSGSBASE instructions. 4517 4518 nofxsr [BUGS=X86-32] Disables x86 floating point extended 4519 register save and restore. The kernel will only save 4520 legacy floating-point registers on task switch. 4521 4522 nogbpages [X86] Do not use GB pages for kernel direct mappings. 4523 4524 no_hash_pointers 4525 [KNL,EARLY] 4526 Alias for "hash_pointers=never". 4527 4528 nohibernate [HIBERNATION] Disable hibernation and resume. 4529 4530 nohlt [ARM,ARM64,MICROBLAZE,MIPS,PPC,RISCV,SH] Forces the kernel to 4531 busy wait in do_idle() and not use the arch_cpu_idle() 4532 implementation; requires CONFIG_GENERIC_IDLE_POLL_SETUP 4533 to be effective. This is useful on platforms where the 4534 sleep(SH) or wfi(ARM,ARM64) instructions do not work 4535 correctly or when doing power measurements to evaluate 4536 the impact of the sleep instructions. This is also 4537 useful when using JTAG debugger. 4538 4539 nohpet [X86] Don't use the HPET timer. 4540 4541 nohugeiomap [KNL,X86,PPC,ARM64,EARLY] Disable kernel huge I/O mappings. 4542 4543 nohugevmalloc [KNL,X86,PPC,ARM64,EARLY] Disable kernel huge vmalloc mappings. 4544 4545 nohz= [KNL] Boottime enable/disable dynamic ticks 4546 Valid arguments: on, off 4547 Default: on 4548 4549 nohz_full= [KNL,BOOT,SMP,ISOL] 4550 The argument is a cpu list, as described above. 4551 In kernels built with CONFIG_NO_HZ_FULL=y, set 4552 the specified list of CPUs whose tick will be stopped 4553 whenever possible. The boot CPU will be forced outside 4554 the range to maintain the timekeeping. Any CPUs 4555 in this list will have their RCU callbacks offloaded, 4556 just as if they had also been called out in the 4557 rcu_nocbs= boot parameter. 4558 4559 Note that this argument takes precedence over 4560 the CONFIG_RCU_NOCB_CPU_DEFAULT_ALL option. 4561 4562 noinitrd [Deprecated,RAM] Tells the kernel not to load any configured 4563 initial RAM disk. Currently this parameter applies to 4564 initrd only, not to initramfs. But it applies to both 4565 in EFI mode. 4566 4567 nointremap [X86-64,Intel-IOMMU,EARLY] Do not enable interrupt 4568 remapping. 4569 [Deprecated - use intremap=off] 4570 4571 noinvpcid [X86,EARLY] Disable the INVPCID cpu feature. 4572 4573 noiotrap [SH] Disables trapped I/O port accesses. 4574 4575 noirqdebug [X86-32] Disables the code which attempts to detect and 4576 disable unhandled interrupt sources. 4577 4578 noisapnp [ISAPNP] Disables ISA PnP code. 4579 4580 nokaslr [KNL,EARLY] 4581 When CONFIG_RANDOMIZE_BASE is set, this disables 4582 kernel and module base offset ASLR (Address Space 4583 Layout Randomization). 4584 4585 no-kvmapf [X86,KVM,EARLY] Disable paravirtualized asynchronous page 4586 fault handling. 4587 4588 no-kvmclock [X86,KVM,EARLY] Disable paravirtualized KVM clock driver 4589 4590 nolapic [X86-32,APIC,EARLY] Do not enable or use the local APIC. 4591 4592 nolapic_timer [X86-32,APIC,EARLY] Do not use the local APIC timer. 4593 4594 nomce [X86-32] Disable Machine Check Exception 4595 4596 nomfgpt [X86-32] Disable Multi-Function General Purpose 4597 Timer usage (for AMD Geode machines). 4598 4599 nomodeset Disable kernel modesetting. Most systems' firmware 4600 sets up a display mode and provides framebuffer memory 4601 for output. With nomodeset, DRM and fbdev drivers will 4602 not load if they could possibly displace the pre- 4603 initialized output. Only the system framebuffer will 4604 be available for use. The respective drivers will not 4605 perform display-mode changes or accelerated rendering. 4606 4607 Useful as error fallback, or for testing and debugging. 4608 4609 nomodule Disable module load 4610 4611 nonmi_ipi [X86] Disable using NMI IPIs during panic/reboot to 4612 shutdown the other cpus. Instead use the REBOOT_VECTOR 4613 irq. 4614 4615 nopat [X86,EARLY] Disable PAT (page attribute table extension of 4616 pagetables) support. 4617 4618 nopcid [X86-64,EARLY] Disable the PCID cpu feature. 4619 4620 nopku [X86] Disable Memory Protection Keys CPU feature found 4621 in some Intel CPUs. 4622 4623 nopti [X86-64,EARLY] 4624 Equivalent to pti=off 4625 4626 nopv= [X86,XEN,KVM,HYPER_V,VMWARE,EARLY] 4627 Disables the PV optimizations forcing the guest to run 4628 as generic guest with no PV drivers. Currently support 4629 XEN HVM, KVM, HYPER_V and VMWARE guest. 4630 4631 nopvspin [X86,XEN,KVM,EARLY] 4632 Disables the qspinlock slow path using PV optimizations 4633 which allow the hypervisor to 'idle' the guest on lock 4634 contention. 4635 4636 norandmaps Don't use address space randomization. Equivalent to 4637 echo 0 > /proc/sys/kernel/randomize_va_space 4638 4639 noreplace-smp [X86-32,SMP] Don't replace SMP instructions 4640 with UP alternatives 4641 4642 noresume [SWSUSP] Disables resume and restores original swap 4643 space. 4644 4645 no-scroll [VGA] Disables scrollback. 4646 This is required for the Braillex ib80-piezo Braille 4647 reader made by F.H. Papenmeier (Germany). 4648 4649 nosgx [X86-64,SGX,EARLY] Disables Intel SGX kernel support. 4650 4651 nosmap [PPC,EARLY] 4652 Disable SMAP (Supervisor Mode Access Prevention) 4653 even if it is supported by processor. 4654 4655 nosmep [PPC64s,EARLY] 4656 Disable SMEP (Supervisor Mode Execution Prevention) 4657 even if it is supported by processor. 4658 4659 nosmp [SMP,EARLY] Tells an SMP kernel to act as a UP kernel, 4660 and disable the IO APIC. legacy for "maxcpus=0". 4661 4662 nosmt [KNL,MIPS,PPC,EARLY] Disable symmetric multithreading (SMT). 4663 Equivalent to smt=1. 4664 4665 [KNL,LOONGARCH,X86,PPC,S390] Disable symmetric multithreading (SMT). 4666 nosmt=force: Force disable SMT, cannot be undone 4667 via the sysfs control file. 4668 4669 nosoftlockup [KNL] Disable the soft-lockup detector. 4670 4671 nospec_store_bypass_disable 4672 [HW,EARLY] Disable all mitigations for the Speculative 4673 Store Bypass vulnerability 4674 4675 nospectre_bhb [ARM64,EARLY] Disable all mitigations for Spectre-BHB (branch 4676 history injection) vulnerability. System may allow data leaks 4677 with this option. 4678 4679 nospectre_v1 [X86,PPC,EARLY] Disable mitigations for Spectre Variant 1 4680 (bounds check bypass). With this option data leaks are 4681 possible in the system. 4682 4683 nospectre_v2 [X86,PPC_E500,ARM64,EARLY] Disable all mitigations 4684 for the Spectre variant 2 (indirect branch 4685 prediction) vulnerability. System may allow data 4686 leaks with this option. 4687 4688 no-steal-acc [X86,PV_OPS,ARM64,PPC/PSERIES,RISCV,LOONGARCH,EARLY] 4689 Disable paravirtualized steal time accounting. steal time 4690 is computed, but won't influence scheduler behaviour 4691 4692 nosync [HW,M68K] Disables sync negotiation for all devices. 4693 4694 no_timer_check [X86,APIC] Disables the code which tests for broken 4695 timer IRQ sources, i.e., the IO-APIC timer. This can 4696 work around problems with incorrect timer 4697 initialization on some boards. 4698 4699 no_uaccess_flush 4700 [PPC,EARLY] Don't flush the L1-D cache after accessing user data. 4701 4702 novmcoredd [KNL,KDUMP] 4703 Disable device dump. Device dump allows drivers to 4704 append dump data to vmcore so you can collect driver 4705 specified debug info. Drivers can append the data 4706 without any limit and this data is stored in memory, 4707 so this may cause significant memory stress. Disabling 4708 device dump can help save memory but the driver debug 4709 data will be no longer available. This parameter 4710 is only available when CONFIG_PROC_VMCORE_DEVICE_DUMP 4711 is set. 4712 4713 no-vmw-sched-clock 4714 [X86,PV_OPS,EARLY] Disable paravirtualized VMware 4715 scheduler clock and use the default one. 4716 4717 nowatchdog [KNL] Disable both lockup detectors, i.e. 4718 soft-lockup and NMI watchdog (hard-lockup). 4719 4720 nowb [ARM,EARLY] 4721 4722 nox2apic [X86-64,APIC,EARLY] Do not enable x2APIC mode. 4723 4724 NOTE: this parameter will be ignored on systems with the 4725 LEGACY_XAPIC_DISABLED bit set in the 4726 IA32_XAPIC_DISABLE_STATUS MSR. 4727 4728 noxsave [BUGS=X86] Disables x86 extended register state save 4729 and restore using xsave. The kernel will fallback to 4730 enabling legacy floating-point and sse state. 4731 4732 noxsaveopt [X86] Disables xsaveopt used in saving x86 extended 4733 register states. The kernel will fall back to use 4734 xsave to save the states. By using this parameter, 4735 performance of saving the states is degraded because 4736 xsave doesn't support modified optimization while 4737 xsaveopt supports it on xsaveopt enabled systems. 4738 4739 noxsaves [X86] Disables xsaves and xrstors used in saving and 4740 restoring x86 extended register state in compacted 4741 form of xsave area. The kernel will fall back to use 4742 xsaveopt and xrstor to save and restore the states 4743 in standard form of xsave area. By using this 4744 parameter, xsave area per process might occupy more 4745 memory on xsaves enabled systems. 4746 4747 nr_cpus= [SMP,EARLY] Maximum number of processors that an SMP kernel 4748 could support. nr_cpus=n : n >= 1 limits the kernel to 4749 support 'n' processors. It could be larger than the 4750 number of already plugged CPU during bootup, later in 4751 runtime you can physically add extra cpu until it reaches 4752 n. So during boot up some boot time memory for per-cpu 4753 variables need be pre-allocated for later physical cpu 4754 hot plugging. 4755 4756 nr_uarts= [SERIAL] maximum number of UARTs to be registered. 4757 4758 numa=off [KNL, ARM64, PPC, RISCV, SPARC, X86, EARLY] 4759 Disable NUMA, Only set up a single NUMA node 4760 spanning all memory. 4761 4762 numa=fake=<size>[MG] 4763 [KNL, ARM64, RISCV, X86, EARLY] 4764 If given as a memory unit, fills all system RAM with 4765 nodes of size interleaved over physical nodes. 4766 4767 numa=fake=<N> 4768 [KNL, ARM64, RISCV, X86, EARLY] 4769 If given as an integer, fills all system RAM with N 4770 fake nodes interleaved over physical nodes. 4771 4772 numa=fake=<N>U 4773 [KNL, ARM64, RISCV, X86, EARLY] 4774 If given as an integer followed by 'U', it will 4775 divide each physical node into N emulated nodes. 4776 4777 numa=noacpi [X86] Don't parse the SRAT table for NUMA setup 4778 4779 numa=nohmat [X86] Don't parse the HMAT table for NUMA setup, or 4780 soft-reserved memory partitioning. 4781 4782 numa_balancing= [KNL,ARM64,PPC,RISCV,S390,X86] Enable or disable automatic 4783 NUMA balancing. 4784 Allowed values are enable and disable 4785 4786 numa_zonelist_order= [KNL, BOOT] Select zonelist order for NUMA. 4787 'node', 'default' can be specified 4788 This can be set from sysctl after boot. 4789 See Documentation/admin-guide/sysctl/vm.rst for details. 4790 4791 nvme.quirks= [NVME] A list of quirk entries to augment the built-in 4792 nvme quirk list. List entries are separated by a 4793 '-' character. 4794 Each entry has the form VendorID:ProductID:quirk_names. 4795 The IDs are 4-digits hex numbers and quirk_names is a 4796 list of quirk names separated by commas. A quirk name 4797 can be prefixed by '^', meaning that the specified 4798 quirk must be disabled. 4799 4800 Example: 4801 nvme.quirks=7710:2267:bogus_nid,^identify_cns-9900:7711:broken_msi 4802 4803 ohci1394_dma=early [HW,EARLY] enable debugging via the ohci1394 driver. 4804 See Documentation/core-api/debugging-via-ohci1394.rst for more 4805 info. 4806 4807 olpc_ec_timeout= [OLPC] ms delay when issuing EC commands 4808 Rather than timing out after 20 ms if an EC 4809 command is not properly ACKed, override the length 4810 of the timeout. We have interrupts disabled while 4811 waiting for the ACK, so if this is set too high 4812 interrupts *may* be lost! 4813 4814 omap_mux= [OMAP] Override bootloader pin multiplexing. 4815 Format: <mux_mode0.mode_name=value>... 4816 For example, to override I2C bus2: 4817 omap_mux=i2c2_scl.i2c2_scl=0x100,i2c2_sda.i2c2_sda=0x100 4818 4819 onenand.bdry= [HW,MTD] Flex-OneNAND Boundary Configuration 4820 4821 Format: [die0_boundary][,die0_lock][,die1_boundary][,die1_lock] 4822 4823 boundary - index of last SLC block on Flex-OneNAND. 4824 The remaining blocks are configured as MLC blocks. 4825 lock - Configure if Flex-OneNAND boundary should be locked. 4826 Once locked, the boundary cannot be changed. 4827 1 indicates lock status, 0 indicates unlock status. 4828 4829 oops=panic [KNL,EARLY] 4830 Always panic on oopses. Default is to just kill the 4831 process, but there is a small probability of 4832 deadlocking the machine. 4833 This will also cause panics on machine check exceptions. 4834 Useful together with panic=30 to trigger a reboot. 4835 4836 page_alloc.shuffle= 4837 [KNL] Boolean flag to control whether the page allocator 4838 should randomize its free lists. This parameter can be 4839 used to enable/disable page randomization. The state of 4840 the flag can be read from sysfs at: 4841 /sys/module/page_alloc/parameters/shuffle. 4842 This parameter is only available if CONFIG_SHUFFLE_PAGE_ALLOCATOR=y. 4843 4844 page_owner= [KNL,EARLY] Boot-time page_owner enabling option. 4845 Storage of the information about who allocated 4846 each page is disabled in default. With this switch, 4847 we can turn it on. 4848 on: enable the feature 4849 4850 page_poison= [KNL,EARLY] Boot-time parameter changing the state of 4851 poisoning on the buddy allocator, available with 4852 CONFIG_PAGE_POISONING=y. 4853 off: turn off poisoning (default) 4854 on: turn on poisoning 4855 4856 page_reporting.page_reporting_order= 4857 [KNL] Minimal page reporting order 4858 Format: <integer> 4859 Adjust the minimal page reporting order. The page 4860 reporting is disabled when it exceeds MAX_PAGE_ORDER. 4861 4862 panic= [KNL] Kernel behaviour on panic: delay <timeout> 4863 timeout > 0: seconds before rebooting 4864 timeout = 0: wait forever 4865 timeout < 0: reboot immediately 4866 Format: <timeout> 4867 4868 panic_on_taint= [KNL,EARLY] 4869 Bitmask for conditionally calling panic() in add_taint() 4870 Format: <hex>[,nousertaint] 4871 Hexadecimal bitmask representing the set of TAINT flags 4872 that will cause the kernel to panic when add_taint() is 4873 called with any of the flags in this set. 4874 The optional switch "nousertaint" can be utilized to 4875 prevent userspace forced crashes by writing to sysctl 4876 /proc/sys/kernel/tainted any flagset matching with the 4877 bitmask set on panic_on_taint. 4878 See Documentation/admin-guide/tainted-kernels.rst for 4879 extra details on the taint flags that users can pick 4880 to compose the bitmask to assign to panic_on_taint. 4881 4882 panic_on_warn=1 panic() instead of WARN(). Useful to cause kdump 4883 on a WARN(). 4884 4885 panic_force_cpu= 4886 [KNL,SMP] Force panic handling to execute on a specific CPU. 4887 Format: <cpu number> 4888 Some platforms require panic handling to occur on a 4889 specific CPU for the crash kernel to function correctly. 4890 This can be due to firmware limitations, interrupt routing 4891 constraints, or platform-specific requirements where only 4892 a particular CPU can safely enter the crash kernel. 4893 When set, panic() will redirect execution to the specified 4894 CPU before proceeding with the normal panic and kexec flow. 4895 If the target CPU is offline or unavailable, panic proceeds 4896 on the current CPU. 4897 This option should only be used for systems with the above 4898 constraints as it might cause the panic operation to be less reliable. 4899 4900 panic_print= Bitmask for printing system info when panic happens. 4901 User can chose combination of the following bits: 4902 bit 0: print all tasks info 4903 bit 1: print system memory info 4904 bit 2: print timer info 4905 bit 3: print locks info if CONFIG_LOCKDEP is on 4906 bit 4: print ftrace buffer 4907 bit 5: replay all kernel messages on consoles at the end of panic 4908 bit 6: print all CPUs backtrace (if available in the arch) 4909 bit 7: print only tasks in uninterruptible (blocked) state 4910 *Be aware* that this option may print a _lot_ of lines, 4911 so there are risks of losing older messages in the log. 4912 Use this option carefully, maybe worth to setup a 4913 bigger log buffer with "log_buf_len" along with this. 4914 4915 panic_sys_info= A comma separated list of extra information to be dumped 4916 on panic. 4917 Format: val[,val...] 4918 Where @val can be any of the following: 4919 4920 tasks: print all tasks info 4921 mem: print system memory info 4922 timers: print timers info 4923 locks: print locks info if CONFIG_LOCKDEP is on 4924 ftrace: print ftrace buffer 4925 all_bt: print all CPUs backtrace (if available in the arch) 4926 blocked_tasks: print only tasks in uninterruptible (blocked) state 4927 4928 This is a human readable alternative to the 'panic_print' option. 4929 4930 panic_console_replay 4931 When panic happens, replay all kernel messages on 4932 consoles at the end of panic. 4933 4934 parkbd.port= [HW] Parallel port number the keyboard adapter is 4935 connected to, default is 0. 4936 Format: <parport#> 4937 parkbd.mode= [HW] Parallel port keyboard adapter mode of operation, 4938 0 for XT, 1 for AT (default is AT). 4939 Format: <mode> 4940 4941 parport= [HW,PPT] Specify parallel ports. 0 disables. 4942 Format: { 0 | auto | 0xBBB[,IRQ[,DMA]] } 4943 Use 'auto' to force the driver to use any 4944 IRQ/DMA settings detected (the default is to 4945 ignore detected IRQ/DMA settings because of 4946 possible conflicts). You can specify the base 4947 address, IRQ, and DMA settings; IRQ and DMA 4948 should be numbers, or 'auto' (for using detected 4949 settings on that particular port), or 'nofifo' 4950 (to avoid using a FIFO even if it is detected). 4951 Parallel ports are assigned in the order they 4952 are specified on the command line, starting 4953 with parport0. 4954 4955 parport_init_mode= [HW,PPT] 4956 Configure VIA parallel port to operate in 4957 a specific mode. This is necessary on Pegasos 4958 computer where firmware has no options for setting 4959 up parallel port mode and sets it to spp. 4960 Currently this function knows 686a and 8231 chips. 4961 Format: [spp|ps2|epp|ecp|ecpepp] 4962 4963 pata_legacy.all= [HW,LIBATA] 4964 Format: <int> 4965 Set to non-zero to probe primary and secondary ISA 4966 port ranges on PCI systems where no PCI PATA device 4967 has been found at either range. Disabled by default. 4968 4969 pata_legacy.autospeed= [HW,LIBATA] 4970 Format: <int> 4971 Set to non-zero if a chip is present that snoops speed 4972 changes. Disabled by default. 4973 4974 pata_legacy.ht6560a= [HW,LIBATA] 4975 Format: <int> 4976 Set to 1, 2, or 3 for HT 6560A on the primary channel, 4977 the secondary channel, or both channels respectively. 4978 Disabled by default. 4979 4980 pata_legacy.ht6560b= [HW,LIBATA] 4981 Format: <int> 4982 Set to 1, 2, or 3 for HT 6560B on the primary channel, 4983 the secondary channel, or both channels respectively. 4984 Disabled by default. 4985 4986 pata_legacy.iordy_mask= [HW,LIBATA] 4987 Format: <int> 4988 IORDY enable mask. Set individual bits to allow IORDY 4989 for the respective channel. Bit 0 is for the first 4990 legacy channel handled by this driver, bit 1 is for 4991 the second channel, and so on. The sequence will often 4992 correspond to the primary legacy channel, the secondary 4993 legacy channel, and so on, but the handling of a PCI 4994 bus and the use of other driver options may interfere 4995 with the sequence. By default IORDY is allowed across 4996 all channels. 4997 4998 pata_legacy.opti82c46x= [HW,LIBATA] 4999 Format: <int> 5000 Set to 1, 2, or 3 for Opti 82c611A on the primary 5001 channel, the secondary channel, or both channels 5002 respectively. Disabled by default. 5003 5004 pata_legacy.opti82c611a= [HW,LIBATA] 5005 Format: <int> 5006 Set to 1, 2, or 3 for Opti 82c465MV on the primary 5007 channel, the secondary channel, or both channels 5008 respectively. Disabled by default. 5009 5010 pata_legacy.pio_mask= [HW,LIBATA] 5011 Format: <int> 5012 PIO mode mask for autospeed devices. Set individual 5013 bits to allow the use of the respective PIO modes. 5014 Bit 0 is for mode 0, bit 1 is for mode 1, and so on. 5015 All modes allowed by default. 5016 5017 pata_legacy.probe_all= [HW,LIBATA] 5018 Format: <int> 5019 Set to non-zero to probe tertiary and further ISA 5020 port ranges on PCI systems. Disabled by default. 5021 5022 pata_legacy.probe_mask= [HW,LIBATA] 5023 Format: <int> 5024 Probe mask for legacy ISA PATA ports. Depending on 5025 platform configuration and the use of other driver 5026 options up to 6 legacy ports are supported: 0x1f0, 5027 0x170, 0x1e8, 0x168, 0x1e0, 0x160, however probing 5028 of individual ports can be disabled by setting the 5029 corresponding bits in the mask to 1. Bit 0 is for 5030 the first port in the list above (0x1f0), and so on. 5031 By default all supported ports are probed. 5032 5033 pata_legacy.qdi= [HW,LIBATA] 5034 Format: <int> 5035 Set to non-zero to probe QDI controllers. By default 5036 set to 1 if CONFIG_PATA_QDI_MODULE, 0 otherwise. 5037 5038 pata_legacy.winbond= [HW,LIBATA] 5039 Format: <int> 5040 Set to non-zero to probe Winbond controllers. Use 5041 the standard I/O port (0x130) if 1, otherwise the 5042 value given is the I/O port to use (typically 0x1b0). 5043 By default set to 1 if CONFIG_PATA_WINBOND_VLB_MODULE, 5044 0 otherwise. 5045 5046 pata_platform.pio_mask= [HW,LIBATA] 5047 Format: <int> 5048 Supported PIO mode mask. Set individual bits to allow 5049 the use of the respective PIO modes. Bit 0 is for 5050 mode 0, bit 1 is for mode 1, and so on. Mode 0 only 5051 allowed by default. 5052 5053 pause_on_oops=<int> 5054 Halt all CPUs after the first oops has been printed for 5055 the specified number of seconds. This is to be used if 5056 your oopses keep scrolling off the screen. 5057 5058 pcbit= [HW,ISDN] 5059 5060 pci=option[,option...] [PCI,EARLY] various PCI subsystem options. 5061 5062 Some options herein operate on a specific device 5063 or a set of devices (<pci_dev>). These are 5064 specified in one of the following formats: 5065 5066 [<domain>:]<bus>:<dev>.<func>[/<dev>.<func>]* 5067 pci:<vendor>:<device>[:<subvendor>:<subdevice>] 5068 5069 Note: the first format specifies a PCI 5070 bus/device/function address which may change 5071 if new hardware is inserted, if motherboard 5072 firmware changes, or due to changes caused 5073 by other kernel parameters. If the 5074 domain is left unspecified, it is 5075 taken to be zero. Optionally, a path 5076 to a device through multiple device/function 5077 addresses can be specified after the base 5078 address (this is more robust against 5079 renumbering issues). The second format 5080 selects devices using IDs from the 5081 configuration space which may match multiple 5082 devices in the system. 5083 5084 earlydump dump PCI config space before the kernel 5085 changes anything 5086 off [X86] don't probe for the PCI bus 5087 bios [X86-32] force use of PCI BIOS, don't access 5088 the hardware directly. Use this if your machine 5089 has a non-standard PCI host bridge. 5090 nobios [X86-32] disallow use of PCI BIOS, only direct 5091 hardware access methods are allowed. Use this 5092 if you experience crashes upon bootup and you 5093 suspect they are caused by the BIOS. 5094 conf1 [X86] Force use of PCI Configuration Access 5095 Mechanism 1 (config address in IO port 0xCF8, 5096 data in IO port 0xCFC, both 32-bit). 5097 conf2 [X86] Force use of PCI Configuration Access 5098 Mechanism 2 (IO port 0xCF8 is an 8-bit port for 5099 the function, IO port 0xCFA, also 8-bit, sets 5100 bus number. The config space is then accessed 5101 through ports 0xC000-0xCFFF). 5102 See http://wiki.osdev.org/PCI for more info 5103 on the configuration access mechanisms. 5104 noaer [PCIE] If the PCIEAER kernel config parameter is 5105 enabled, this kernel boot option can be used to 5106 disable the use of PCIE advanced error reporting. 5107 nodomains [PCI] Disable support for multiple PCI 5108 root domains (aka PCI segments, in ACPI-speak). 5109 nommconf [X86] Disable use of MMCONFIG for PCI 5110 Configuration 5111 check_enable_amd_mmconf [X86] check for and enable 5112 properly configured MMIO access to PCI 5113 config space on AMD family 10h CPU 5114 nomsi [MSI] If the PCI_MSI kernel config parameter is 5115 enabled, this kernel boot option can be used to 5116 disable the use of MSI interrupts system-wide. 5117 noioapicquirk [APIC] Disable all boot interrupt quirks. 5118 Safety option to keep boot IRQs enabled. This 5119 should never be necessary. 5120 ioapicreroute [APIC] Enable rerouting of boot IRQs to the 5121 primary IO-APIC for bridges that cannot disable 5122 boot IRQs. This fixes a source of spurious IRQs 5123 when the system masks IRQs. 5124 noioapicreroute [APIC] Disable workaround that uses the 5125 boot IRQ equivalent of an IRQ that connects to 5126 a chipset where boot IRQs cannot be disabled. 5127 The opposite of ioapicreroute. 5128 biosirq [X86-32] Use PCI BIOS calls to get the interrupt 5129 routing table. These calls are known to be buggy 5130 on several machines and they hang the machine 5131 when used, but on other computers it's the only 5132 way to get the interrupt routing table. Try 5133 this option if the kernel is unable to allocate 5134 IRQs or discover secondary PCI buses on your 5135 motherboard. 5136 rom [X86] Assign address space to expansion ROMs. 5137 Use with caution as certain devices share 5138 address decoders between ROMs and other 5139 resources. 5140 norom [X86] Do not assign address space to 5141 expansion ROMs that do not already have 5142 BIOS assigned address ranges. 5143 nobar [X86] Do not assign address space to the 5144 BARs that weren't assigned by the BIOS. 5145 irqmask=0xMMMM [X86] Set a bit mask of IRQs allowed to be 5146 assigned automatically to PCI devices. You can 5147 make the kernel exclude IRQs of your ISA cards 5148 this way. 5149 pirqaddr=0xAAAAA [X86] Specify the physical address 5150 of the PIRQ table (normally generated 5151 by the BIOS) if it is outside the 5152 F0000h-100000h range. 5153 lastbus=N [X86] Scan all buses thru bus #N. Can be 5154 useful if the kernel is unable to find your 5155 secondary buses and you want to tell it 5156 explicitly which ones they are. 5157 assign-busses [X86] Always assign all PCI bus 5158 numbers ourselves, overriding 5159 whatever the firmware may have done. 5160 usepirqmask [X86] Honor the possible IRQ mask stored 5161 in the BIOS $PIR table. This is needed on 5162 some systems with broken BIOSes, notably 5163 some HP Pavilion N5400 and Omnibook XE3 5164 notebooks. This will have no effect if ACPI 5165 IRQ routing is enabled. 5166 noacpi [X86] Do not use ACPI for IRQ routing 5167 or for PCI scanning. 5168 use_crs [X86] Use PCI host bridge window information 5169 from ACPI. On BIOSes from 2008 or later, this 5170 is enabled by default. If you need to use this, 5171 please report a bug. 5172 nocrs [X86] Ignore PCI host bridge windows from ACPI. 5173 If you need to use this, please report a bug. 5174 use_e820 [X86] Use E820 reservations to exclude parts of 5175 PCI host bridge windows. This is a workaround 5176 for BIOS defects in host bridge _CRS methods. 5177 If you need to use this, please report a bug to 5178 <linux-pci@vger.kernel.org>. 5179 no_e820 [X86] Ignore E820 reservations for PCI host 5180 bridge windows. This is the default on modern 5181 hardware. If you need to use this, please report 5182 a bug to <linux-pci@vger.kernel.org>. 5183 routeirq Do IRQ routing for all PCI devices. 5184 This is normally done in pci_enable_device(), 5185 so this option is a temporary workaround 5186 for broken drivers that don't call it. 5187 skip_isa_align [X86] do not align io start addr, so can 5188 handle more pci cards 5189 noearly [X86] Don't do any early type 1 scanning. 5190 This might help on some broken boards which 5191 machine check when some devices' config space 5192 is read. But various workarounds are disabled 5193 and some IOMMU drivers will not work. 5194 bfsort Sort PCI devices into breadth-first order. 5195 This sorting is done to get a device 5196 order compatible with older (<= 2.4) kernels. 5197 nobfsort Don't sort PCI devices into breadth-first order. 5198 pcie_bus_tune_off Disable PCIe MPS (Max Payload Size) 5199 tuning and use the BIOS-configured MPS defaults. 5200 pcie_bus_safe Set every device's MPS to the largest value 5201 supported by all devices below the root complex. 5202 pcie_bus_perf Set device MPS to the largest allowable MPS 5203 based on its parent bus. Also set MRRS (Max 5204 Read Request Size) to the largest supported 5205 value (no larger than the MPS that the device 5206 or bus can support) for best performance. 5207 pcie_bus_peer2peer Set every device's MPS to 128B, which 5208 every device is guaranteed to support. This 5209 configuration allows peer-to-peer DMA between 5210 any pair of devices, possibly at the cost of 5211 reduced performance. This also guarantees 5212 that hot-added devices will work. 5213 cbiosize=nn[KMG] The fixed amount of bus space which is 5214 reserved for the CardBus bridge's IO window. 5215 The default value is 256 bytes. 5216 cbmemsize=nn[KMG] The fixed amount of bus space which is 5217 reserved for the CardBus bridge's memory 5218 window. The default value is 64 megabytes. 5219 resource_alignment= 5220 Format: 5221 [<order of align>@]<pci_dev>[; ...] 5222 Specifies alignment and device to reassign 5223 aligned memory resources. How to 5224 specify the device is described above. 5225 If <order of align> is not specified, 5226 PAGE_SIZE is used as alignment. 5227 A PCI-PCI bridge can be specified if resource 5228 windows need to be expanded. 5229 To specify the alignment for several 5230 instances of a device, the PCI vendor, 5231 device, subvendor, and subdevice may be 5232 specified, e.g., 12@pci:8086:9c22:103c:198f 5233 for 4096-byte alignment. 5234 ecrc= Enable/disable PCIe ECRC (transaction layer 5235 end-to-end CRC checking). Only effective if 5236 OS has native AER control (either granted by 5237 ACPI _OSC or forced via "pcie_ports=native") 5238 bios: Use BIOS/firmware settings. This is the 5239 the default. 5240 off: Turn ECRC off 5241 on: Turn ECRC on. 5242 hpiosize=nn[KMG] The fixed amount of bus space which is 5243 reserved for hotplug bridge's IO window. 5244 Default size is 256 bytes. 5245 hpmmiosize=nn[KMG] The fixed amount of bus space which is 5246 reserved for hotplug bridge's MMIO window. 5247 Default size is 2 megabytes. 5248 hpmmioprefsize=nn[KMG] The fixed amount of bus space which is 5249 reserved for hotplug bridge's MMIO_PREF window. 5250 Default size is 2 megabytes. 5251 hpmemsize=nn[KMG] The fixed amount of bus space which is 5252 reserved for hotplug bridge's MMIO and 5253 MMIO_PREF window. 5254 Default size is 2 megabytes. 5255 hpbussize=nn The minimum amount of additional bus numbers 5256 reserved for buses below a hotplug bridge. 5257 Default is 1. 5258 realloc= Enable/disable reallocating PCI bridge resources 5259 if allocations done by BIOS are too small to 5260 accommodate resources required by all child 5261 devices. 5262 off: Turn realloc off 5263 on: Turn realloc on 5264 realloc same as realloc=on 5265 noari do not use PCIe ARI. 5266 noats [PCIE, Intel-IOMMU, AMD-IOMMU] 5267 do not use PCIe ATS (and IOMMU device IOTLB). 5268 pcie_scan_all Scan all possible PCIe devices. Otherwise we 5269 only look for one device below a PCIe downstream 5270 port. 5271 big_root_window Try to add a big 64bit memory window to the PCIe 5272 root complex on AMD CPUs. Some GFX hardware 5273 can resize a BAR to allow access to all VRAM. 5274 Adding the window is slightly risky (it may 5275 conflict with unreported devices), so this 5276 taints the kernel. 5277 disable_acs_redir=<pci_dev>[; ...] 5278 Specify one or more PCI devices (in the format 5279 specified above) separated by semicolons. 5280 Each device specified will have the PCI ACS 5281 redirect capabilities forced off which will 5282 allow P2P traffic between devices through 5283 bridges without forcing it upstream. Note: 5284 this removes isolation between devices and 5285 may put more devices in an IOMMU group. 5286 config_acs= 5287 Format: 5288 <ACS flags>@<pci_dev>[; ...] 5289 Specify one or more PCI devices (in the format 5290 specified above) optionally prepended with flags 5291 and separated by semicolons. The respective 5292 capabilities will be enabled, disabled or 5293 unchanged based on what is specified in 5294 flags. 5295 5296 ACS Flags is defined as follows: 5297 bit-0 : ACS Source Validation 5298 bit-1 : ACS Translation Blocking 5299 bit-2 : ACS P2P Request Redirect 5300 bit-3 : ACS P2P Completion Redirect 5301 bit-4 : ACS Upstream Forwarding 5302 bit-5 : ACS P2P Egress Control 5303 bit-6 : ACS Direct Translated P2P 5304 Each bit can be marked as: 5305 '0' – force disabled 5306 '1' – force enabled 5307 'x' – unchanged 5308 For example, 5309 pci=config_acs=10x@pci:0:0 5310 would configure all devices that support 5311 ACS to enable P2P Request Redirect, disable 5312 Translation Blocking, and leave Source 5313 Validation unchanged from whatever power-up 5314 or firmware set it to. 5315 5316 Note: this may remove isolation between devices 5317 and may put more devices in an IOMMU group. 5318 force_floating [S390] Force usage of floating interrupts. 5319 nomio [S390] Do not use MIO instructions. 5320 norid [S390] ignore the RID field and force use of 5321 one PCI domain per PCI function 5322 notph [PCIE] If the PCIE_TPH kernel config parameter 5323 is enabled, this kernel boot option can be used 5324 to disable PCIe TLP Processing Hints support 5325 system-wide. 5326 5327 pcie_aspm= [PCIE] Forcibly enable or ignore PCIe Active State Power 5328 Management. 5329 off Don't touch ASPM configuration at all. Leave any 5330 configuration done by firmware unchanged. 5331 force Enable ASPM even on devices that claim not to support it. 5332 WARNING: Forcing ASPM on may cause system lockups. 5333 5334 pcie_ports= [PCIE] PCIe port services handling: 5335 native Use native PCIe services (PME, AER, DPC, PCIe hotplug) 5336 even if the platform doesn't give the OS permission to 5337 use them. This may cause conflicts if the platform 5338 also tries to use these services. 5339 dpc-native Use native PCIe service for DPC only. May 5340 cause conflicts if firmware uses AER or DPC. 5341 compat Disable native PCIe services (PME, AER, DPC, PCIe 5342 hotplug). 5343 5344 pcie_port_pm= [PCIE] PCIe port power management handling: 5345 off Disable power management of all PCIe ports 5346 force Forcibly enable power management of all PCIe ports 5347 5348 pcie_pme= [PCIE,PM] Native PCIe PME signaling options: 5349 nomsi Do not use MSI for native PCIe PME signaling (this makes 5350 all PCIe root ports use INTx for all services). 5351 5352 pcmv= [HW,PCMCIA] BadgePAD 4 5353 5354 pd_ignore_unused 5355 [PM] 5356 Keep all power-domains already enabled by bootloader on, 5357 even if no driver has claimed them. This is useful 5358 for debug and development, but should not be 5359 needed on a platform with proper driver support. 5360 5361 pdcchassis= [PARISC,HW] Disable/Enable PDC Chassis Status codes at 5362 boot time. 5363 Format: { 0 | 1 } 5364 See arch/parisc/kernel/pdc_chassis.c 5365 5366 percpu_alloc= [MM,EARLY] 5367 Select which percpu first chunk allocator to use. 5368 Currently supported values are "embed" and "page". 5369 Archs may support subset or none of the selections. 5370 See comments in mm/percpu.c for details on each 5371 allocator. This parameter is primarily for debugging 5372 and performance comparison. 5373 5374 pirq= [SMP,APIC] Manual mp-table setup 5375 See Documentation/arch/x86/i386/IO-APIC.rst. 5376 5377 plip= [PPT,NET] Parallel port network link 5378 Format: { parport<nr> | timid | 0 } 5379 See also Documentation/admin-guide/parport.rst. 5380 5381 pmtmr= [X86] Manual setup of pmtmr I/O Port. 5382 Override pmtimer IOPort with a hex value. 5383 e.g. pmtmr=0x508 5384 5385 pmu_override= [PPC] Override the PMU. 5386 This option takes over the PMU facility, so it is no 5387 longer usable by perf. Setting this option starts the 5388 PMU counters by setting MMCR0 to 0 (the FC bit is 5389 cleared). If a number is given, then MMCR1 is set to 5390 that number, otherwise (e.g., 'pmu_override=on'), MMCR1 5391 remains 0. 5392 5393 pm_async= [PM] 5394 Format: off 5395 This parameter sets the initial value of the 5396 /sys/power/pm_async sysfs knob at boot time. 5397 If set to "off", disables asynchronous suspend and 5398 resume of devices during system-wide power transitions. 5399 This can be useful on platforms where device 5400 dependencies are not well-defined, or for debugging 5401 power management issues. Asynchronous operations are 5402 enabled by default. 5403 5404 5405 pm_debug_messages [SUSPEND,KNL] 5406 Enable suspend/resume debug messages during boot up. 5407 5408 pnp.debug=1 [PNP] 5409 Enable PNP debug messages (depends on the 5410 CONFIG_PNP_DEBUG_MESSAGES option). Change at run-time 5411 via /sys/module/pnp/parameters/debug. We always show 5412 current resource usage; turning this on also shows 5413 possible settings and some assignment information. 5414 5415 pnpacpi= [ACPI] 5416 { off } 5417 5418 pnpbios= [ISAPNP] 5419 { on | off | curr | res | no-curr | no-res } 5420 5421 pnp_reserve_irq= 5422 [ISAPNP] Exclude IRQs for the autoconfiguration 5423 5424 pnp_reserve_dma= 5425 [ISAPNP] Exclude DMAs for the autoconfiguration 5426 5427 pnp_reserve_io= [ISAPNP] Exclude I/O ports for the autoconfiguration 5428 Ranges are in pairs (I/O port base and size). 5429 5430 pnp_reserve_mem= 5431 [ISAPNP] Exclude memory regions for the 5432 autoconfiguration. 5433 Ranges are in pairs (memory base and size). 5434 5435 ports= [IP_VS_FTP] IPVS ftp helper module 5436 Default is 21. 5437 Up to 8 (IP_VS_APP_MAX_PORTS) ports 5438 may be specified. 5439 Format: <port>,<port>.... 5440 5441 possible_cpus= [SMP,S390,X86] 5442 Format: <unsigned int> 5443 Set the number of possible CPUs, overriding the 5444 regular discovery mechanisms (such as ACPI/FW, etc). 5445 5446 powersave=off [PPC] This option disables power saving features. 5447 It specifically disables cpuidle and sets the 5448 platform machine description specific power_save 5449 function to NULL. On Idle the CPU just reduces 5450 execution priority. 5451 5452 ppc_strict_facility_enable 5453 [PPC,ENABLE] This option catches any kernel floating point, 5454 Altivec, VSX and SPE outside of regions specifically 5455 allowed (eg kernel_enable_fpu()/kernel_disable_fpu()). 5456 There is some performance impact when enabling this. 5457 5458 ppc_tm= [PPC,EARLY] 5459 Format: {"off"} 5460 Disable Hardware Transactional Memory 5461 5462 preempt= [KNL] 5463 Select preemption mode if you have CONFIG_PREEMPT_DYNAMIC 5464 none - Limited to cond_resched() calls 5465 voluntary - Limited to cond_resched() and might_sleep() calls 5466 full - Any section that isn't explicitly preempt disabled 5467 can be preempted anytime. Tasks will also yield 5468 contended spinlocks (if the critical section isn't 5469 explicitly preempt disabled beyond the lock itself). 5470 lazy - Scheduler controlled. Similar to full but instead 5471 of preempting the task immediately, the task gets 5472 one HZ tick time to yield itself before the 5473 preemption will be forced. One preemption is when the 5474 task returns to user space. 5475 5476 print-fatal-signals= 5477 [KNL] debug: print fatal signals 5478 5479 If enabled, warn about various signal handling 5480 related application anomalies: too many signals, 5481 too many POSIX.1 timers, fatal signals causing a 5482 coredump - etc. 5483 5484 If you hit the warning due to signal overflow, 5485 you might want to try "ulimit -i unlimited". 5486 5487 default: off. 5488 5489 printk.always_kmsg_dump= 5490 Trigger kmsg_dump for cases other than kernel oops or 5491 panics 5492 Format: <bool> (1/Y/y=enable, 0/N/n=disable) 5493 default: disabled 5494 5495 printk.console_no_auto_verbose= 5496 Disable console loglevel raise on oops, panic 5497 or lockdep-detected issues (only if lock debug is on). 5498 With an exception to setups with low baudrate on 5499 serial console, keeping this 0 is a good choice 5500 in order to provide more debug information. 5501 Format: <bool> 5502 default: 0 (auto_verbose is enabled) 5503 5504 printk.debug_non_panic_cpus= 5505 Allows storing messages from non-panic CPUs into 5506 the printk log buffer during panic(). They are 5507 flushed to consoles by the panic-CPU on 5508 a best-effort basis. 5509 Format: <bool> (1/Y/y=enable, 0/N/n=disable) 5510 Default: disabled 5511 5512 printk.devkmsg={on,off,ratelimit} 5513 Control writing to /dev/kmsg. 5514 on - unlimited logging to /dev/kmsg from userspace 5515 off - logging to /dev/kmsg disabled 5516 ratelimit - ratelimit the logging 5517 Default: ratelimit 5518 5519 printk.time= Show timing data prefixed to each printk message line 5520 Format: <bool> (1/Y/y=enable, 0/N/n=disable) 5521 5522 proc_mem.force_override= [KNL] 5523 Format: {always | ptrace | never} 5524 Traditionally /proc/pid/mem allows memory permissions to be 5525 overridden without restrictions. This option may be set to 5526 restrict that. Can be one of: 5527 - 'always': traditional behavior always allows mem overrides. 5528 - 'ptrace': only allow mem overrides for active ptracers. 5529 - 'never': never allow mem overrides. 5530 If not specified, default is the CONFIG_PROC_MEM_* choice. 5531 5532 processor.max_cstate= [HW,ACPI] 5533 Limit processor to maximum C-state 5534 max_cstate=9 overrides any DMI blacklist limit. 5535 5536 processor.nocst [HW,ACPI] 5537 Ignore the _CST method to determine C-states, 5538 instead using the legacy FADT method 5539 5540 profile= [KNL] Enable kernel profiling via /proc/profile 5541 Format: [<profiletype>,]<number> 5542 Param: <profiletype>: "schedule" or "kvm" 5543 [defaults to kernel profiling] 5544 Param: "schedule" - profile schedule points. 5545 Param: "kvm" - profile VM exits. 5546 Param: <number> - step/bucket size as a power of 2 for 5547 statistical time based profiling. 5548 5549 prot_virt= [S390] enable hosting protected virtual machines 5550 isolated from the hypervisor (if hardware supports 5551 that). If enabled, the default kernel base address 5552 might be overridden even when Kernel Address Space 5553 Layout Randomization is disabled. 5554 Format: <bool> 5555 5556 psi= [KNL] Enable or disable pressure stall information 5557 tracking. 5558 Format: <bool> 5559 5560 psmouse.proto= [HW,MOUSE] Highest PS2 mouse protocol extension to 5561 probe for; one of (bare|imps|exps|lifebook|any). 5562 psmouse.rate= [HW,MOUSE] Set desired mouse report rate, in reports 5563 per second. 5564 psmouse.resetafter= [HW,MOUSE] 5565 Try to reset the device after so many bad packets 5566 (0 = never). 5567 psmouse.resolution= 5568 [HW,MOUSE] Set desired mouse resolution, in dpi. 5569 psmouse.smartscroll= 5570 [HW,MOUSE] Controls Logitech smartscroll autorepeat. 5571 0 = disabled, 1 = enabled (default). 5572 5573 pstore.backend= Specify the name of the pstore backend to use 5574 5575 pti= [X86-64] Control Page Table Isolation of user and 5576 kernel address spaces. Disabling this feature 5577 removes hardening, but improves performance of 5578 system calls and interrupts. 5579 5580 on - unconditionally enable 5581 off - unconditionally disable 5582 auto - kernel detects whether your CPU model is 5583 vulnerable to issues that PTI mitigates 5584 5585 Not specifying this option is equivalent to pti=auto. 5586 5587 pty.legacy_count= 5588 [KNL] Number of legacy pty's. Overwrites compiled-in 5589 default number. 5590 5591 quiet [KNL,EARLY] Disable most log messages 5592 5593 r128= [HW,DRM] 5594 5595 radix_hcall_invalidate=on [PPC/PSERIES] 5596 Disable RADIX GTSE feature and use hcall for TLB 5597 invalidate. 5598 5599 raid= [HW,RAID] 5600 See Documentation/admin-guide/md.rst. 5601 5602 ramdisk_size= [RAM] Sizes of RAM disks in kilobytes 5603 See Documentation/admin-guide/blockdev/ramdisk.rst. 5604 5605 ramdisk_start= [Deprecated,RAM] RAM disk image start address 5606 5607 random.trust_cpu=off 5608 [KNL,EARLY] Disable trusting the use of the CPU's 5609 random number generator (if available) to 5610 initialize the kernel's RNG. 5611 5612 random.trust_bootloader=off 5613 [KNL,EARLY] Disable trusting the use of the a seed 5614 passed by the bootloader (if available) to 5615 initialize the kernel's RNG. 5616 5617 randomize_kstack_offset= 5618 [KNL,EARLY] Enable or disable kernel stack offset 5619 randomization, which provides roughly 5 bits of 5620 entropy, frustrating memory corruption attacks 5621 that depend on stack address determinism or 5622 cross-syscall address exposures. This is only 5623 available on architectures that have defined 5624 CONFIG_HAVE_ARCH_RANDOMIZE_KSTACK_OFFSET. 5625 Format: <bool> (1/Y/y=enable, 0/N/n=disable) 5626 Default is CONFIG_RANDOMIZE_KSTACK_OFFSET_DEFAULT. 5627 5628 ras=option[,option,...] [KNL] RAS-specific options 5629 5630 cec_disable [X86] 5631 Disable the Correctable Errors Collector, 5632 see CONFIG_RAS_CEC help text. 5633 5634 rcu_nocbs[=cpu-list] 5635 [KNL] The optional argument is a cpu list, 5636 as described above. 5637 5638 In kernels built with CONFIG_RCU_NOCB_CPU=y, 5639 enable the no-callback CPU mode, which prevents 5640 such CPUs' callbacks from being invoked in 5641 softirq context. Invocation of such CPUs' RCU 5642 callbacks will instead be offloaded to "rcuox/N" 5643 kthreads created for that purpose, where "x" is 5644 "p" for RCU-preempt, "s" for RCU-sched, and "g" 5645 for the kthreads that mediate grace periods; and 5646 "N" is the CPU number. This reduces OS jitter on 5647 the offloaded CPUs, which can be useful for HPC 5648 and real-time workloads. It can also improve 5649 energy efficiency for asymmetric multiprocessors. 5650 5651 If a cpulist is passed as an argument, the specified 5652 list of CPUs is set to no-callback mode from boot. 5653 5654 Otherwise, if the '=' sign and the cpulist 5655 arguments are omitted, no CPU will be set to 5656 no-callback mode from boot but the mode may be 5657 toggled at runtime via cpusets. 5658 5659 Note that this argument takes precedence over 5660 the CONFIG_RCU_NOCB_CPU_DEFAULT_ALL option. 5661 5662 rcu_nocb_poll [KNL] 5663 Rather than requiring that offloaded CPUs 5664 (specified by rcu_nocbs= above) explicitly 5665 awaken the corresponding "rcuoN" kthreads, 5666 make these kthreads poll for callbacks. 5667 This improves the real-time response for the 5668 offloaded CPUs by relieving them of the need to 5669 wake up the corresponding kthread, but degrades 5670 energy efficiency by requiring that the kthreads 5671 periodically wake up to do the polling. 5672 5673 rcutree.blimit= [KNL] 5674 Set maximum number of finished RCU callbacks to 5675 process in one batch. 5676 5677 rcutree.csd_lock_suppress_rcu_stall= [KNL] 5678 Do only a one-line RCU CPU stall warning when 5679 there is an ongoing too-long CSD-lock wait. 5680 5681 rcutree.do_rcu_barrier= [KNL] 5682 Request a call to rcu_barrier(). This is 5683 throttled so that userspace tests can safely 5684 hammer on the sysfs variable if they so choose. 5685 If triggered before the RCU grace-period machinery 5686 is fully active, this will error out with EAGAIN. 5687 5688 rcutree.dump_tree= [KNL] 5689 Dump the structure of the rcu_node combining tree 5690 out at early boot. This is used for diagnostic 5691 purposes, to verify correct tree setup. 5692 5693 rcutree.gp_cleanup_delay= [KNL] 5694 Set the number of jiffies to delay each step of 5695 RCU grace-period cleanup. 5696 5697 rcutree.gp_init_delay= [KNL] 5698 Set the number of jiffies to delay each step of 5699 RCU grace-period initialization. 5700 5701 rcutree.gp_preinit_delay= [KNL] 5702 Set the number of jiffies to delay each step of 5703 RCU grace-period pre-initialization, that is, 5704 the propagation of recent CPU-hotplug changes up 5705 the rcu_node combining tree. 5706 5707 rcutree.jiffies_till_first_fqs= [KNL] 5708 Set delay from grace-period initialization to 5709 first attempt to force quiescent states. 5710 Units are jiffies, minimum value is zero, 5711 and maximum value is HZ. 5712 5713 rcutree.jiffies_till_next_fqs= [KNL] 5714 Set delay between subsequent attempts to force 5715 quiescent states. Units are jiffies, minimum 5716 value is one, and maximum value is HZ. 5717 5718 rcutree.jiffies_till_sched_qs= [KNL] 5719 Set required age in jiffies for a 5720 given grace period before RCU starts 5721 soliciting quiescent-state help from 5722 rcu_note_context_switch() and cond_resched(). 5723 If not specified, the kernel will calculate 5724 a value based on the most recent settings 5725 of rcutree.jiffies_till_first_fqs 5726 and rcutree.jiffies_till_next_fqs. 5727 This calculated value may be viewed in 5728 rcutree.jiffies_to_sched_qs. Any attempt to set 5729 rcutree.jiffies_to_sched_qs will be cheerfully 5730 overwritten. 5731 5732 rcutree.kthread_prio= [KNL,BOOT] 5733 Set the SCHED_FIFO priority of the RCU per-CPU 5734 kthreads (rcuc/N). This value is also used for 5735 the priority of the RCU boost threads (rcub/N) 5736 and for the RCU grace-period kthreads (rcu_bh, 5737 rcu_preempt, and rcu_sched). If RCU_BOOST is 5738 set, valid values are 1-99 and the default is 1 5739 (the least-favored priority). Otherwise, when 5740 RCU_BOOST is not set, valid values are 0-99 and 5741 the default is zero (non-realtime operation). 5742 When RCU_NOCB_CPU is set, also adjust the 5743 priority of NOCB callback kthreads. 5744 5745 rcutree.nocb_nobypass_lim_per_jiffy= [KNL] 5746 On callback-offloaded (rcu_nocbs) CPUs, 5747 RCU reduces the lock contention that would 5748 otherwise be caused by callback floods through 5749 use of the ->nocb_bypass list. However, in the 5750 common non-flooded case, RCU queues directly to 5751 the main ->cblist in order to avoid the extra 5752 overhead of the ->nocb_bypass list and its lock. 5753 But if there are too many callbacks queued during 5754 a single jiffy, RCU pre-queues the callbacks into 5755 the ->nocb_bypass queue. The definition of "too 5756 many" is supplied by this kernel boot parameter. 5757 5758 rcutree.nohz_full_patience_delay= [KNL] 5759 On callback-offloaded (rcu_nocbs) CPUs, avoid 5760 disturbing RCU unless the grace period has 5761 reached the specified age in milliseconds. 5762 Defaults to zero. Large values will be capped 5763 at five seconds. All values will be rounded down 5764 to the nearest value representable by jiffies. 5765 5766 rcutree.qhimark= [KNL] 5767 Set threshold of queued RCU callbacks beyond which 5768 batch limiting is disabled. 5769 5770 rcutree.qlowmark= [KNL] 5771 Set threshold of queued RCU callbacks below which 5772 batch limiting is re-enabled. 5773 5774 rcutree.qovld= [KNL] 5775 Set threshold of queued RCU callbacks beyond which 5776 RCU's force-quiescent-state scan will aggressively 5777 enlist help from cond_resched() and sched IPIs to 5778 help CPUs more quickly reach quiescent states. 5779 Set to less than zero to make this be set based 5780 on rcutree.qhimark at boot time and to zero to 5781 disable more aggressive help enlistment. 5782 5783 rcutree.rcu_delay_page_cache_fill_msec= [KNL] 5784 Set the page-cache refill delay (in milliseconds) 5785 in response to low-memory conditions. The range 5786 of permitted values is in the range 0:100000. 5787 5788 rcutree.rcu_divisor= [KNL] 5789 Set the shift-right count to use to compute 5790 the callback-invocation batch limit bl from 5791 the number of callbacks queued on this CPU. 5792 The result will be bounded below by the value of 5793 the rcutree.blimit kernel parameter. Every bl 5794 callbacks, the softirq handler will exit in 5795 order to allow the CPU to do other work. 5796 5797 Please note that this callback-invocation batch 5798 limit applies only to non-offloaded callback 5799 invocation. Offloaded callbacks are instead 5800 invoked in the context of an rcuoc kthread, which 5801 scheduler will preempt as it does any other task. 5802 5803 rcutree.rcu_fanout_exact= [KNL] 5804 Disable autobalancing of the rcu_node combining 5805 tree. This is used by rcutorture, and might 5806 possibly be useful for architectures having high 5807 cache-to-cache transfer latencies. 5808 5809 rcutree.rcu_fanout_leaf= [KNL] 5810 Change the number of CPUs assigned to each 5811 leaf rcu_node structure. Useful for very 5812 large systems, which will choose the value 64, 5813 and for NUMA systems with large remote-access 5814 latencies, which will choose a value aligned 5815 with the appropriate hardware boundaries. 5816 5817 rcutree.rcu_min_cached_objs= [KNL] 5818 Minimum number of objects which are cached and 5819 maintained per one CPU. Object size is equal 5820 to PAGE_SIZE. The cache allows to reduce the 5821 pressure to page allocator, also it makes the 5822 whole algorithm to behave better in low memory 5823 condition. 5824 5825 rcutree.rcu_nocb_gp_stride= [KNL] 5826 Set the number of NOCB callback kthreads in 5827 each group, which defaults to the square root 5828 of the number of CPUs. Larger numbers reduce 5829 the wakeup overhead on the global grace-period 5830 kthread, but increases that same overhead on 5831 each group's NOCB grace-period kthread. 5832 5833 rcutree.rcu_kick_kthreads= [KNL] 5834 Cause the grace-period kthread to get an extra 5835 wake_up() if it sleeps three times longer than 5836 it should at force-quiescent-state time. 5837 This wake_up() will be accompanied by a 5838 WARN_ONCE() splat and an ftrace_dump(). 5839 5840 rcutree.rcu_resched_ns= [KNL] 5841 Limit the time spend invoking a batch of RCU 5842 callbacks to the specified number of nanoseconds. 5843 By default, this limit is checked only once 5844 every 32 callbacks in order to limit the pain 5845 inflicted by local_clock() overhead. 5846 5847 rcutree.rcu_unlock_delay= [KNL] 5848 In CONFIG_RCU_STRICT_GRACE_PERIOD=y kernels, 5849 this specifies an rcu_read_unlock()-time delay 5850 in microseconds. This defaults to zero. 5851 Larger delays increase the probability of 5852 catching RCU pointer leaks, that is, buggy use 5853 of RCU-protected pointers after the relevant 5854 rcu_read_unlock() has completed. 5855 5856 rcutree.sysrq_rcu= [KNL] 5857 Commandeer a sysrq key to dump out Tree RCU's 5858 rcu_node tree with an eye towards determining 5859 why a new grace period has not yet started. 5860 5861 rcutree.use_softirq= [KNL] 5862 If set to zero, move all RCU_SOFTIRQ processing to 5863 per-CPU rcuc kthreads. Defaults to a non-zero 5864 value, meaning that RCU_SOFTIRQ is used by default. 5865 Specify rcutree.use_softirq=0 to use rcuc kthreads. 5866 5867 But note that CONFIG_PREEMPT_RT=y kernels disable 5868 this kernel boot parameter, forcibly setting it 5869 to zero. 5870 5871 rcutree.enable_rcu_lazy= [KNL] 5872 To save power, batch RCU callbacks and flush after 5873 delay, memory pressure or callback list growing too 5874 big. 5875 5876 rcutree.rcu_normal_wake_from_gp= [KNL] 5877 Reduces a latency of synchronize_rcu() call. This approach 5878 maintains its own track of synchronize_rcu() callers, so it 5879 does not interact with regular callbacks because it does not 5880 use a call_rcu[_hurry]() path. Please note, this is for a 5881 normal grace period. 5882 5883 How to enable it: 5884 5885 echo 1 > /sys/module/rcutree/parameters/rcu_normal_wake_from_gp 5886 or pass a boot parameter "rcutree.rcu_normal_wake_from_gp=1" 5887 5888 Default is 1 if num_possible_cpus() <= 16 and it is not explicitly 5889 disabled by the boot parameter passing 0. 5890 5891 rcuscale.gp_async= [KNL] 5892 Measure performance of asynchronous 5893 grace-period primitives such as call_rcu(). 5894 5895 rcuscale.gp_async_max= [KNL] 5896 Specify the maximum number of outstanding 5897 callbacks per writer thread. When a writer 5898 thread exceeds this limit, it invokes the 5899 corresponding flavor of rcu_barrier() to allow 5900 previously posted callbacks to drain. 5901 5902 rcuscale.gp_exp= [KNL] 5903 Measure performance of expedited synchronous 5904 grace-period primitives. 5905 5906 rcuscale.holdoff= [KNL] 5907 Set test-start holdoff period. The purpose of 5908 this parameter is to delay the start of the 5909 test until boot completes in order to avoid 5910 interference. 5911 5912 rcuscale.kfree_by_call_rcu= [KNL] 5913 In kernels built with CONFIG_RCU_LAZY=y, test 5914 call_rcu() instead of kfree_rcu(). 5915 5916 rcuscale.kfree_mult= [KNL] 5917 Instead of allocating an object of size kfree_obj, 5918 allocate one of kfree_mult * sizeof(kfree_obj). 5919 Defaults to 1. 5920 5921 rcuscale.kfree_rcu_test= [KNL] 5922 Set to measure performance of kfree_rcu() flooding. 5923 5924 rcuscale.kfree_rcu_test_double= [KNL] 5925 Test the double-argument variant of kfree_rcu(). 5926 If this parameter has the same value as 5927 rcuscale.kfree_rcu_test_single, both the single- 5928 and double-argument variants are tested. 5929 5930 rcuscale.kfree_rcu_test_single= [KNL] 5931 Test the single-argument variant of kfree_rcu(). 5932 If this parameter has the same value as 5933 rcuscale.kfree_rcu_test_double, both the single- 5934 and double-argument variants are tested. 5935 5936 rcuscale.kfree_nthreads= [KNL] 5937 The number of threads running loops of kfree_rcu(). 5938 5939 rcuscale.kfree_alloc_num= [KNL] 5940 Number of allocations and frees done in an iteration. 5941 5942 rcuscale.kfree_loops= [KNL] 5943 Number of loops doing rcuscale.kfree_alloc_num number 5944 of allocations and frees. 5945 5946 rcuscale.minruntime= [KNL] 5947 Set the minimum test run time in seconds. This 5948 does not affect the data-collection interval, 5949 but instead allows better measurement of things 5950 like CPU consumption. 5951 5952 rcuscale.nreaders= [KNL] 5953 Set number of RCU readers. The value -1 selects 5954 N, where N is the number of CPUs. A value 5955 "n" less than -1 selects N-n+1, where N is again 5956 the number of CPUs. For example, -2 selects N 5957 (the number of CPUs), -3 selects N+1, and so on. 5958 A value of "n" less than or equal to -N selects 5959 a single reader. 5960 5961 rcuscale.nwriters= [KNL] 5962 Set number of RCU writers. The values operate 5963 the same as for rcuscale.nreaders. 5964 N, where N is the number of CPUs 5965 5966 rcuscale.scale_type= [KNL] 5967 Specify the RCU implementation to test. 5968 5969 rcuscale.shutdown= [KNL] 5970 Shut the system down after performance tests 5971 complete. This is useful for hands-off automated 5972 testing. 5973 5974 rcuscale.verbose= [KNL] 5975 Enable additional printk() statements. 5976 5977 rcuscale.writer_holdoff= [KNL] 5978 Write-side holdoff between grace periods, 5979 in microseconds. The default of zero says 5980 no holdoff. 5981 5982 rcuscale.writer_holdoff_jiffies= [KNL] 5983 Additional write-side holdoff between grace 5984 periods, but in jiffies. The default of zero 5985 says no holdoff. 5986 5987 rcutorture.fqs_duration= [KNL] 5988 Set duration of force_quiescent_state bursts 5989 in microseconds. 5990 5991 rcutorture.fqs_holdoff= [KNL] 5992 Set holdoff time within force_quiescent_state bursts 5993 in microseconds. 5994 5995 rcutorture.fqs_stutter= [KNL] 5996 Set wait time between force_quiescent_state bursts 5997 in seconds. 5998 5999 rcutorture.fwd_progress= [KNL] 6000 Specifies the number of kthreads to be used 6001 for RCU grace-period forward-progress testing 6002 for the types of RCU supporting this notion. 6003 Defaults to 1 kthread, values less than zero or 6004 greater than the number of CPUs cause the number 6005 of CPUs to be used. 6006 6007 rcutorture.fwd_progress_div= [KNL] 6008 Specify the fraction of a CPU-stall-warning 6009 period to do tight-loop forward-progress testing. 6010 6011 rcutorture.fwd_progress_holdoff= [KNL] 6012 Number of seconds to wait between successive 6013 forward-progress tests. 6014 6015 rcutorture.fwd_progress_need_resched= [KNL] 6016 Enclose cond_resched() calls within checks for 6017 need_resched() during tight-loop forward-progress 6018 testing. 6019 6020 rcutorture.gp_cond= [KNL] 6021 Use conditional/asynchronous update-side 6022 normal-grace-period primitives, if available. 6023 6024 rcutorture.gp_cond_exp= [KNL] 6025 Use conditional/asynchronous update-side 6026 expedited-grace-period primitives, if available. 6027 6028 rcutorture.gp_cond_full= [KNL] 6029 Use conditional/asynchronous update-side 6030 normal-grace-period primitives that also take 6031 concurrent expedited grace periods into account, 6032 if available. 6033 6034 rcutorture.gp_cond_exp_full= [KNL] 6035 Use conditional/asynchronous update-side 6036 expedited-grace-period primitives that also take 6037 concurrent normal grace periods into account, 6038 if available. 6039 6040 rcutorture.gp_cond_wi= [KNL] 6041 Nominal wait interval for normal conditional 6042 grace periods (specified by rcutorture's 6043 gp_cond and gp_cond_full module parameters), 6044 in microseconds. The actual wait interval will 6045 be randomly selected to nanosecond granularity up 6046 to this wait interval. Defaults to 16 jiffies, 6047 for example, 16,000 microseconds on a system 6048 with HZ=1000. 6049 6050 rcutorture.gp_cond_wi_exp= [KNL] 6051 Nominal wait interval for expedited conditional 6052 grace periods (specified by rcutorture's 6053 gp_cond_exp and gp_cond_exp_full module 6054 parameters), in microseconds. The actual wait 6055 interval will be randomly selected to nanosecond 6056 granularity up to this wait interval. Defaults to 6057 128 microseconds. 6058 6059 rcutorture.gp_exp= [KNL] 6060 Use expedited update-side primitives, if available. 6061 6062 rcutorture.gp_normal= [KNL] 6063 Use normal (non-expedited) asynchronous 6064 update-side primitives, if available. 6065 6066 rcutorture.gp_poll= [KNL] 6067 Use polled update-side normal-grace-period 6068 primitives, if available. 6069 6070 rcutorture.gp_poll_exp= [KNL] 6071 Use polled update-side expedited-grace-period 6072 primitives, if available. 6073 6074 rcutorture.gp_poll_full= [KNL] 6075 Use polled update-side normal-grace-period 6076 primitives that also take concurrent expedited 6077 grace periods into account, if available. 6078 6079 rcutorture.gp_poll_exp_full= [KNL] 6080 Use polled update-side expedited-grace-period 6081 primitives that also take concurrent normal 6082 grace periods into account, if available. 6083 6084 rcutorture.gp_poll_wi= [KNL] 6085 Nominal wait interval for normal conditional 6086 grace periods (specified by rcutorture's 6087 gp_poll and gp_poll_full module parameters), 6088 in microseconds. The actual wait interval will 6089 be randomly selected to nanosecond granularity up 6090 to this wait interval. Defaults to 16 jiffies, 6091 for example, 16,000 microseconds on a system 6092 with HZ=1000. 6093 6094 rcutorture.gp_poll_wi_exp= [KNL] 6095 Nominal wait interval for expedited conditional 6096 grace periods (specified by rcutorture's 6097 gp_poll_exp and gp_poll_exp_full module 6098 parameters), in microseconds. The actual wait 6099 interval will be randomly selected to nanosecond 6100 granularity up to this wait interval. Defaults to 6101 128 microseconds. 6102 6103 rcutorture.gp_sync= [KNL] 6104 Use normal (non-expedited) synchronous 6105 update-side primitives, if available. If all 6106 of rcutorture.gp_cond=, rcutorture.gp_exp=, 6107 rcutorture.gp_normal=, and rcutorture.gp_sync= 6108 are zero, rcutorture acts as if is interpreted 6109 they are all non-zero. 6110 6111 rcutorture.gpwrap_lag= [KNL] 6112 Enable grace-period wrap lag testing. Setting 6113 to false prevents the gpwrap lag test from 6114 running. Default is true. 6115 6116 rcutorture.gpwrap_lag_gps= [KNL] 6117 Set the value for grace-period wrap lag during 6118 active lag testing periods. This controls how many 6119 grace periods differences we tolerate between 6120 rdp and rnp's gp_seq before setting overflow flag. 6121 The default is always set to 8. 6122 6123 rcutorture.gpwrap_lag_cycle_mins= [KNL] 6124 Set the total cycle duration for gpwrap lag 6125 testing in minutes. This is the total time for 6126 one complete cycle of active and inactive 6127 testing periods. Default is 30 minutes. 6128 6129 rcutorture.gpwrap_lag_active_mins= [KNL] 6130 Set the duration for which gpwrap lag is active 6131 within each cycle, in minutes. During this time, 6132 the grace-period wrap lag will be set to the 6133 value specified by gpwrap_lag_gps. Default is 6134 5 minutes. 6135 6136 rcutorture.irqreader= [KNL] 6137 Run RCU readers from irq handlers, or, more 6138 accurately, from a timer handler. Not all RCU 6139 flavors take kindly to this sort of thing. 6140 6141 rcutorture.leakpointer= [KNL] 6142 Leak an RCU-protected pointer out of the reader. 6143 This can of course result in splats, and is 6144 intended to test the ability of things like 6145 CONFIG_RCU_STRICT_GRACE_PERIOD=y to detect 6146 such leaks. 6147 6148 rcutorture.n_barrier_cbs= [KNL] 6149 Set callbacks/threads for rcu_barrier() testing. 6150 6151 rcutorture.nfakewriters= [KNL] 6152 Set number of concurrent RCU writers. These just 6153 stress RCU, they don't participate in the actual 6154 test, hence the "fake". 6155 6156 rcutorture.nocbs_nthreads= [KNL] 6157 Set number of RCU callback-offload togglers. 6158 Zero (the default) disables toggling. 6159 6160 rcutorture.nocbs_toggle= [KNL] 6161 Set the delay in milliseconds between successive 6162 callback-offload toggling attempts. 6163 6164 rcutorture.nreaders= [KNL] 6165 Set number of RCU readers. The value -1 selects 6166 N-1, where N is the number of CPUs. A value 6167 "n" less than -1 selects N-n-2, where N is again 6168 the number of CPUs. For example, -2 selects N 6169 (the number of CPUs), -3 selects N+1, and so on. 6170 6171 rcutorture.object_debug= [KNL] 6172 Enable debug-object double-call_rcu() testing. 6173 6174 rcutorture.onoff_holdoff= [KNL] 6175 Set time (s) after boot for CPU-hotplug testing. 6176 6177 rcutorture.onoff_interval= [KNL] 6178 Set time (jiffies) between CPU-hotplug operations, 6179 or zero to disable CPU-hotplug testing. 6180 6181 rcutorture.preempt_duration= [KNL] 6182 Set duration (in milliseconds) of preemptions 6183 by a high-priority FIFO real-time task. Set to 6184 zero (the default) to disable. The CPUs to 6185 preempt are selected randomly from the set that 6186 are online at a given point in time. Races with 6187 CPUs going offline are ignored, with that attempt 6188 at preemption skipped. 6189 6190 rcutorture.preempt_interval= [KNL] 6191 Set interval (in milliseconds, defaulting to one 6192 second) between preemptions by a high-priority 6193 FIFO real-time task. This delay is mediated 6194 by an hrtimer and is further fuzzed to avoid 6195 inadvertent synchronizations. 6196 6197 rcutorture.read_exit_burst= [KNL] 6198 The number of times in a given read-then-exit 6199 episode that a set of read-then-exit kthreads 6200 is spawned. 6201 6202 rcutorture.read_exit_delay= [KNL] 6203 The delay, in seconds, between successive 6204 read-then-exit testing episodes. 6205 6206 rcutorture.reader_flavor= [KNL] 6207 A bit mask indicating which readers to use. 6208 If there is more than one bit set, the readers 6209 are entered from low-order bit up, and are 6210 exited in the opposite order. For SRCU, the 6211 0x1 bit is normal readers, 0x2 NMI-safe readers, 6212 and 0x4 light-weight readers. 6213 6214 rcutorture.shuffle_interval= [KNL] 6215 Set task-shuffle interval (s). Shuffling tasks 6216 allows some CPUs to go into dyntick-idle mode 6217 during the rcutorture test. 6218 6219 rcutorture.shutdown_secs= [KNL] 6220 Set time (s) after boot system shutdown. This 6221 is useful for hands-off automated testing. 6222 6223 rcutorture.stall_cpu= [KNL] 6224 Duration of CPU stall (s) to test RCU CPU stall 6225 warnings, zero to disable. 6226 6227 rcutorture.stall_cpu_block= [KNL] 6228 Sleep while stalling if set. This will result 6229 in warnings from preemptible RCU in addition to 6230 any other stall-related activity. Note that 6231 in kernels built with CONFIG_PREEMPTION=n and 6232 CONFIG_PREEMPT_COUNT=y, this parameter will 6233 cause the CPU to pass through a quiescent state. 6234 Given CONFIG_PREEMPTION=n, this will suppress 6235 RCU CPU stall warnings, but will instead result 6236 in scheduling-while-atomic splats. 6237 6238 Use of this module parameter results in splats. 6239 6240 6241 rcutorture.stall_cpu_holdoff= [KNL] 6242 Time to wait (s) after boot before inducing stall. 6243 6244 rcutorture.stall_cpu_irqsoff= [KNL] 6245 Disable interrupts while stalling if set, but only 6246 on the first stall in the set. 6247 6248 rcutorture.stall_cpu_repeat= [KNL] 6249 Number of times to repeat the stall sequence, 6250 so that rcutorture.stall_cpu_repeat=3 will result 6251 in four stall sequences. 6252 6253 rcutorture.stall_gp_kthread= [KNL] 6254 Duration (s) of forced sleep within RCU 6255 grace-period kthread to test RCU CPU stall 6256 warnings, zero to disable. If both stall_cpu 6257 and stall_gp_kthread are specified, the 6258 kthread is starved first, then the CPU. 6259 6260 rcutorture.stat_interval= [KNL] 6261 Time (s) between statistics printk()s. 6262 6263 rcutorture.stutter= [KNL] 6264 Time (s) to stutter testing, for example, specifying 6265 five seconds causes the test to run for five seconds, 6266 wait for five seconds, and so on. This tests RCU's 6267 ability to transition abruptly to and from idle. 6268 6269 rcutorture.test_boost= [KNL] 6270 Test RCU priority boosting? 0=no, 1=maybe, 2=yes. 6271 "Maybe" means test if the RCU implementation 6272 under test support RCU priority boosting. 6273 6274 rcutorture.test_boost_duration= [KNL] 6275 Duration (s) of each individual boost test. 6276 6277 rcutorture.test_boost_holdoff= [KNL] 6278 Holdoff time (s) from start of test to the start 6279 of RCU priority-boost testing. Defaults to zero, 6280 that is, no holdoff. 6281 6282 rcutorture.test_boost_interval= [KNL] 6283 Interval (s) between each boost test. 6284 6285 rcutorture.test_no_idle_hz= [KNL] 6286 Test RCU's dyntick-idle handling. See also the 6287 rcutorture.shuffle_interval parameter. 6288 6289 rcutorture.torture_type= [KNL] 6290 Specify the RCU implementation to test. 6291 6292 rcutorture.verbose= [KNL] 6293 Enable additional printk() statements. 6294 6295 rcupdate.rcu_cpu_stall_ftrace_dump= [KNL] 6296 Dump ftrace buffer after reporting RCU CPU 6297 stall warning. 6298 6299 rcupdate.rcu_cpu_stall_notifiers= [KNL] 6300 Provide RCU CPU stall notifiers, but see the 6301 warnings in the RCU_CPU_STALL_NOTIFIER Kconfig 6302 option's help text. TL;DR: You almost certainly 6303 do not want rcupdate.rcu_cpu_stall_notifiers. 6304 6305 rcupdate.rcu_cpu_stall_suppress= [KNL] 6306 Suppress RCU CPU stall warning messages. 6307 6308 rcupdate.rcu_cpu_stall_suppress_at_boot= [KNL] 6309 Suppress RCU CPU stall warning messages and 6310 rcutorture writer stall warnings that occur 6311 during early boot, that is, during the time 6312 before the init task is spawned. 6313 6314 rcupdate.rcu_cpu_stall_timeout= [KNL] 6315 Set timeout for RCU CPU stall warning messages. 6316 The value is in seconds and the maximum allowed 6317 value is 300 seconds. 6318 6319 rcupdate.rcu_exp_cpu_stall_timeout= [KNL] 6320 Set timeout for expedited RCU CPU stall warning 6321 messages. The value is in milliseconds 6322 and the maximum allowed value is 21000 6323 milliseconds. Please note that this value is 6324 adjusted to an arch timer tick resolution. 6325 Setting this to zero causes the value from 6326 rcupdate.rcu_cpu_stall_timeout to be used (after 6327 conversion from seconds to milliseconds). 6328 6329 rcupdate.rcu_cpu_stall_cputime= [KNL] 6330 Provide statistics on the cputime and count of 6331 interrupts and tasks during the sampling period. For 6332 multiple continuous RCU stalls, all sampling periods 6333 begin at half of the first RCU stall timeout. 6334 6335 rcupdate.rcu_exp_stall_task_details= [KNL] 6336 Print stack dumps of any tasks blocking the 6337 current expedited RCU grace period during an 6338 expedited RCU CPU stall warning. 6339 6340 rcupdate.rcu_expedited= [KNL] 6341 Use expedited grace-period primitives, for 6342 example, synchronize_rcu_expedited() instead 6343 of synchronize_rcu(). This reduces latency, 6344 but can increase CPU utilization, degrade 6345 real-time latency, and degrade energy efficiency. 6346 No effect on CONFIG_TINY_RCU kernels. 6347 6348 rcupdate.rcu_normal= [KNL] 6349 Use only normal grace-period primitives, 6350 for example, synchronize_rcu() instead of 6351 synchronize_rcu_expedited(). This improves 6352 real-time latency, CPU utilization, and 6353 energy efficiency, but can expose users to 6354 increased grace-period latency. This parameter 6355 overrides rcupdate.rcu_expedited. No effect on 6356 CONFIG_TINY_RCU kernels. 6357 6358 rcupdate.rcu_normal_after_boot= [KNL] 6359 Once boot has completed (that is, after 6360 rcu_end_inkernel_boot() has been invoked), use 6361 only normal grace-period primitives. No effect 6362 on CONFIG_TINY_RCU kernels. 6363 6364 But note that CONFIG_PREEMPT_RT=y kernels enables 6365 this kernel boot parameter, forcibly setting 6366 it to the value one, that is, converting any 6367 post-boot attempt at an expedited RCU grace 6368 period to instead use normal non-expedited 6369 grace-period processing. 6370 6371 rcupdate.rcu_task_collapse_lim= [KNL] 6372 Set the maximum number of callbacks present 6373 at the beginning of a grace period that allows 6374 the RCU Tasks flavors to collapse back to using 6375 a single callback queue. This switching only 6376 occurs when rcupdate.rcu_task_enqueue_lim is 6377 set to the default value of -1. 6378 6379 rcupdate.rcu_task_contend_lim= [KNL] 6380 Set the minimum number of callback-queuing-time 6381 lock-contention events per jiffy required to 6382 cause the RCU Tasks flavors to switch to per-CPU 6383 callback queuing. This switching only occurs 6384 when rcupdate.rcu_task_enqueue_lim is set to 6385 the default value of -1. 6386 6387 rcupdate.rcu_task_enqueue_lim= [KNL] 6388 Set the number of callback queues to use for the 6389 RCU Tasks family of RCU flavors. The default 6390 of -1 allows this to be automatically (and 6391 dynamically) adjusted. This parameter is intended 6392 for use in testing. 6393 6394 rcupdate.rcu_task_lazy_lim= [KNL] 6395 Number of callbacks on a given CPU that will 6396 cancel laziness on that CPU. Use -1 to disable 6397 cancellation of laziness, but be advised that 6398 doing so increases the danger of OOM due to 6399 callback flooding. 6400 6401 rcupdate.rcu_task_stall_info= [KNL] 6402 Set initial timeout in jiffies for RCU task stall 6403 informational messages, which give some indication 6404 of the problem for those not patient enough to 6405 wait for ten minutes. Informational messages are 6406 only printed prior to the stall-warning message 6407 for a given grace period. Disable with a value 6408 less than or equal to zero. Defaults to ten 6409 seconds. A change in value does not take effect 6410 until the beginning of the next grace period. 6411 6412 rcupdate.rcu_task_stall_info_mult= [KNL] 6413 Multiplier for time interval between successive 6414 RCU task stall informational messages for a given 6415 RCU tasks grace period. This value is clamped 6416 to one through ten, inclusive. It defaults to 6417 the value three, so that the first informational 6418 message is printed 10 seconds into the grace 6419 period, the second at 40 seconds, the third at 6420 160 seconds, and then the stall warning at 600 6421 seconds would prevent a fourth at 640 seconds. 6422 6423 rcupdate.rcu_task_stall_timeout= [KNL] 6424 Set timeout in jiffies for RCU task stall 6425 warning messages. Disable with a value less 6426 than or equal to zero. Defaults to ten minutes. 6427 A change in value does not take effect until 6428 the beginning of the next grace period. 6429 6430 rcupdate.rcu_tasks_lazy_ms= [KNL] 6431 Set timeout in milliseconds RCU Tasks asynchronous 6432 callback batching for call_rcu_tasks(). 6433 A negative value will take the default. A value 6434 of zero will disable batching. Batching is 6435 always disabled for synchronize_rcu_tasks(). 6436 6437 rcupdate.rcu_self_test= [KNL] 6438 Run the RCU early boot self tests 6439 6440 rdinit= [KNL] 6441 Format: <full_path> 6442 Run specified binary instead of /init from the ramdisk, 6443 used for early userspace startup. See initrd. 6444 6445 rdrand= [X86,EARLY] 6446 force - Override the decision by the kernel to hide the 6447 advertisement of RDRAND support (this affects 6448 certain AMD processors because of buggy BIOS 6449 support, specifically around the suspend/resume 6450 path). 6451 6452 rdt= [HW,X86,RDT] 6453 Turn on/off individual RDT features. List is: 6454 cmt, mbmtotal, mbmlocal, l3cat, l3cdp, l2cat, l2cdp, 6455 mba, smba, bmec, abmc, sdciae, energy[:guid], 6456 perf[:guid]. 6457 E.g. to turn on cmt and turn off mba use: 6458 rdt=cmt,!mba 6459 To turn off all energy telemetry monitoring and ensure that 6460 perf telemetry monitoring associated with guid 0x12345 6461 is enabled use: 6462 rdt=!energy,perf:0x12345 6463 6464 reboot= [KNL] 6465 Format (x86 or x86_64): 6466 [w[arm] | c[old] | h[ard] | s[oft] | g[pio]] | d[efault] \ 6467 [[,]s[mp]#### \ 6468 [[,]b[ios] | a[cpi] | k[bd] | t[riple] | e[fi] | p[ci]] \ 6469 [[,]f[orce] 6470 Where reboot_mode is one of warm (soft) or cold (hard) or gpio 6471 (prefix with 'panic_' to set mode for panic 6472 reboot only), 6473 reboot_type is one of bios, acpi, kbd, triple, efi, or pci, 6474 reboot_force is either force or not specified, 6475 reboot_cpu is s[mp]#### with #### being the processor 6476 to be used for rebooting. 6477 6478 acpi 6479 Use the ACPI RESET_REG in the FADT. If ACPI is not 6480 configured or the ACPI reset does not work, the reboot 6481 path attempts the reset using the keyboard controller. 6482 6483 bios 6484 Use the CPU reboot vector for warm reset 6485 6486 cold 6487 Set the cold reboot flag 6488 6489 default 6490 There are some built-in platform specific "quirks" 6491 - you may see: "reboot: <name> series board detected. 6492 Selecting <type> for reboots." In the case where you 6493 think the quirk is in error (e.g. you have newer BIOS, 6494 or newer board) using this option will ignore the 6495 built-in quirk table, and use the generic default 6496 reboot actions. 6497 6498 efi 6499 Use efi reset_system runtime service. If EFI is not 6500 configured or the EFI reset does not work, the reboot 6501 path attempts the reset using the keyboard controller. 6502 6503 force 6504 Don't stop other CPUs on reboot. This can make reboot 6505 more reliable in some cases. 6506 6507 kbd 6508 Use the keyboard controller. cold reset (default) 6509 6510 pci 6511 Use a write to the PCI config space register 0xcf9 to 6512 trigger reboot. 6513 6514 triple 6515 Force a triple fault (init) 6516 6517 warm 6518 Don't set the cold reboot flag 6519 6520 Using warm reset will be much faster especially on big 6521 memory systems because the BIOS will not go through 6522 the memory check. Disadvantage is that not all 6523 hardware will be completely reinitialized on reboot so 6524 there may be boot problems on some systems. 6525 6526 6527 refscale.holdoff= [KNL] 6528 Set test-start holdoff period. The purpose of 6529 this parameter is to delay the start of the 6530 test until boot completes in order to avoid 6531 interference. 6532 6533 refscale.lookup_instances= [KNL] 6534 Number of data elements to use for the forms of 6535 SLAB_TYPESAFE_BY_RCU testing. A negative number 6536 is negated and multiplied by nr_cpu_ids, while 6537 zero specifies nr_cpu_ids. 6538 6539 refscale.loops= [KNL] 6540 Set the number of loops over the synchronization 6541 primitive under test. Increasing this number 6542 reduces noise due to loop start/end overhead, 6543 but the default has already reduced the per-pass 6544 noise to a handful of picoseconds on ca. 2020 6545 x86 laptops. 6546 6547 refscale.nreaders= [KNL] 6548 Set number of readers. The default value of -1 6549 selects N, where N is roughly 75% of the number 6550 of CPUs. A value of zero is an interesting choice. 6551 6552 refscale.nruns= [KNL] 6553 Set number of runs, each of which is dumped onto 6554 the console log. 6555 6556 refscale.readdelay= [KNL] 6557 Set the read-side critical-section duration, 6558 measured in microseconds. 6559 6560 refscale.scale_type= [KNL] 6561 Specify the read-protection implementation to test. 6562 6563 refscale.shutdown= [KNL] 6564 Shut down the system at the end of the performance 6565 test. This defaults to 1 (shut it down) when 6566 refscale is built into the kernel and to 0 (leave 6567 it running) when refscale is built as a module. 6568 6569 refscale.verbose= [KNL] 6570 Enable additional printk() statements. 6571 6572 refscale.verbose_batched= [KNL] 6573 Batch the additional printk() statements. If zero 6574 (the default) or negative, print everything. Otherwise, 6575 print every Nth verbose statement, where N is the value 6576 specified. 6577 6578 regulator_ignore_unused 6579 [REGULATOR] 6580 Prevents regulator framework from disabling regulators 6581 that are unused, due no driver claiming them. This may 6582 be useful for debug and development, but should not be 6583 needed on a platform with proper driver support. 6584 6585 relax_domain_level= 6586 [KNL, SMP] Set scheduler's default relax_domain_level. 6587 See Documentation/admin-guide/cgroup-v1/cpusets.rst. 6588 6589 reserve= [KNL,BUGS] Force kernel to ignore I/O ports or memory 6590 Format: <base1>,<size1>[,<base2>,<size2>,...] 6591 Reserve I/O ports or memory so the kernel won't use 6592 them. If <base> is less than 0x10000, the region 6593 is assumed to be I/O ports; otherwise it is memory. 6594 6595 reserve_mem= [RAM] 6596 Format: nn[KMG]:<align>:<label> 6597 Reserve physical memory and label it with a name that 6598 other subsystems can use to access it. This is typically 6599 used for systems that do not wipe the RAM, and this command 6600 line will try to reserve the same physical memory on 6601 soft reboots. Note, it is not guaranteed to be the same 6602 location. For example, if anything about the system changes 6603 or if booting a different kernel. It can also fail if KASLR 6604 places the kernel at the location of where the RAM reservation 6605 was from a previous boot, the new reservation will be at a 6606 different location. 6607 Any subsystem using this feature must add a way to verify 6608 that the contents of the physical memory is from a previous 6609 boot, as there may be cases where the memory will not be 6610 located at the same location. 6611 6612 The format is size:align:label for example, to request 6613 12 megabytes of 4096 alignment for ramoops: 6614 6615 reserve_mem=12M:4096:oops ramoops.mem_name=oops 6616 6617 reservetop= [X86-32,EARLY] 6618 Format: nn[KMG] 6619 Reserves a hole at the top of the kernel virtual 6620 address space. 6621 6622 reset_devices [KNL] Force drivers to reset the underlying device 6623 during initialization. 6624 6625 resume= [SWSUSP] 6626 Specify the partition device for software suspend 6627 Format: 6628 {/dev/<dev> | PARTUUID=<uuid> | <int>:<int> | <hex>} 6629 6630 resume_offset= [SWSUSP] 6631 Specify the offset from the beginning of the partition 6632 given by "resume=" at which the swap header is located, 6633 in <PAGE_SIZE> units (needed only for swap files). 6634 See Documentation/power/swsusp-and-swap-files.rst 6635 6636 resumedelay= [HIBERNATION] Delay (in seconds) to pause before attempting to 6637 read the resume files 6638 6639 resumewait [HIBERNATION] Wait (indefinitely) for resume device to show up. 6640 Useful for devices that are detected asynchronously 6641 (e.g. USB and MMC devices). 6642 6643 retain_initrd [RAM] Keep initrd memory after extraction. After boot, it will 6644 be accessible via /sys/firmware/initrd. 6645 6646 retbleed= [X86] Control mitigation of RETBleed (Arbitrary 6647 Speculative Code Execution with Return Instructions) 6648 vulnerability. 6649 6650 AMD-based UNRET and IBPB mitigations alone do not stop 6651 sibling threads from influencing the predictions of other 6652 sibling threads. For that reason, STIBP is used on pro- 6653 cessors that support it, and mitigate SMT on processors 6654 that don't. 6655 6656 off - no mitigation 6657 auto - automatically select a mitigation 6658 auto,nosmt - automatically select a mitigation, 6659 disabling SMT if necessary for 6660 the full mitigation (only on Zen1 6661 and older without STIBP). 6662 ibpb - On AMD, mitigate short speculation 6663 windows on basic block boundaries too. 6664 Safe, highest perf impact. It also 6665 enables STIBP if present. Not suitable 6666 on Intel. 6667 ibpb,nosmt - Like "ibpb" above but will disable SMT 6668 when STIBP is not available. This is 6669 the alternative for systems which do not 6670 have STIBP. 6671 unret - Force enable untrained return thunks, 6672 only effective on AMD f15h-f17h based 6673 systems. 6674 unret,nosmt - Like unret, but will disable SMT when STIBP 6675 is not available. This is the alternative for 6676 systems which do not have STIBP. 6677 6678 Selecting 'auto' will choose a mitigation method at run 6679 time according to the CPU. 6680 6681 Not specifying this option is equivalent to retbleed=auto. 6682 6683 rfkill.default_state= 6684 0 "airplane mode". All wifi, bluetooth, wimax, gps, fm, 6685 etc. communication is blocked by default. 6686 1 Unblocked. 6687 6688 rfkill.master_switch_mode= 6689 0 The "airplane mode" button does nothing. 6690 1 The "airplane mode" button toggles between everything 6691 blocked and the previous configuration. 6692 2 The "airplane mode" button toggles between everything 6693 blocked and everything unblocked. 6694 6695 ring3mwait=disable 6696 [KNL] Disable ring 3 MONITOR/MWAIT feature on supported 6697 CPUs. 6698 6699 riscv_isa_fallback [RISCV,EARLY] 6700 When CONFIG_RISCV_ISA_FALLBACK is not enabled, permit 6701 falling back to detecting extension support by parsing 6702 "riscv,isa" property on devicetree systems when the 6703 replacement properties are not found. See the Kconfig 6704 entry for RISCV_ISA_FALLBACK. 6705 6706 riscv_nousercfi= 6707 all Disable user CFI ABI to userspace even if cpu extension 6708 are available. 6709 bcfi Disable user backward CFI ABI to userspace even if 6710 the shadow stack extension is available. 6711 fcfi Disable user forward CFI ABI to userspace even if the 6712 landing pad extension is available. 6713 6714 ro [KNL] Mount root device read-only on boot 6715 6716 rodata= [KNL,EARLY] 6717 on Mark read-only kernel memory as read-only (default). 6718 off Leave read-only kernel memory writable for debugging. 6719 noalias Mark read-only kernel memory as read-only but retain 6720 writable aliases in the direct map for regions outside 6721 of the kernel image. [arm64] 6722 6723 rockchip.usb_uart 6724 [EARLY] 6725 Enable the uart passthrough on the designated usb port 6726 on Rockchip SoCs. When active, the signals of the 6727 debug-uart get routed to the D+ and D- pins of the usb 6728 port and the regular usb controller gets disabled. 6729 6730 root= [KNL] Root filesystem 6731 Usually this is a block device specifier of some kind, 6732 see the early_lookup_bdev comment in 6733 block/early-lookup.c for details. 6734 Alternatively this can be "ram" for the legacy initial 6735 ramdisk, "nfs" and "cifs" for root on a network file 6736 system, or "mtd" and "ubi" for mounting from raw flash. 6737 6738 rootdelay= [KNL] Delay (in seconds) to pause before attempting to 6739 mount the root filesystem 6740 6741 rootflags= [KNL] Set root filesystem mount option string 6742 6743 rseq_slice_ext= [KNL] RSEQ based time slice extension 6744 Format: boolean 6745 Control enablement of RSEQ based time slice extension. 6746 Default is 'on'. 6747 6748 initramfs_options= [KNL] 6749 Specify mount options for the initramfs mount. 6750 6751 rootfstype= [KNL] Set root filesystem type 6752 6753 rootwait [KNL] Wait (indefinitely) for root device to show up. 6754 Useful for devices that are detected asynchronously 6755 (e.g. USB and MMC devices). 6756 6757 rootwait= [KNL] Maximum time (in seconds) to wait for root device 6758 to show up before attempting to mount the root 6759 filesystem. 6760 6761 rproc_mem=nn[KMG][@address] 6762 [KNL,ARM,CMA] Remoteproc physical memory block. 6763 Memory area to be used by remote processor image, 6764 managed by CMA. 6765 6766 rseq_debug= [KNL] Enable or disable restartable sequence 6767 debug mode. Defaults to CONFIG_RSEQ_DEBUG_DEFAULT_ENABLE. 6768 Format: <bool> 6769 6770 rt_group_sched= [KNL] Enable or disable SCHED_RR/FIFO group scheduling 6771 when CONFIG_RT_GROUP_SCHED=y. Defaults to 6772 !CONFIG_RT_GROUP_SCHED_DEFAULT_DISABLED. 6773 Format: <bool> 6774 6775 rw [KNL] Mount root device read-write on boot 6776 6777 S [KNL] Run init in single mode 6778 6779 s390_iommu= [HW,S390] 6780 Set s390 IOTLB flushing mode 6781 strict 6782 With strict flushing every unmap operation will result 6783 in an IOTLB flush. Default is lazy flushing before 6784 reuse, which is faster. Deprecated, equivalent to 6785 iommu.strict=1. 6786 6787 s390_iommu_aperture= [KNL,S390] 6788 Specifies the size of the per device DMA address space 6789 accessible through the DMA and IOMMU APIs as a decimal 6790 factor of the size of main memory. 6791 The default is 1 meaning that one can concurrently use 6792 as many DMA addresses as physical memory is installed, 6793 if supported by hardware, and thus map all of memory 6794 once. With a value of 2 one can map all of memory twice 6795 and so on. As a special case a factor of 0 imposes no 6796 restrictions other than those given by hardware at the 6797 cost of significant additional memory use for tables. 6798 6799 sa1100ir [NET] 6800 See drivers/net/irda/sa1100_ir.c. 6801 6802 sched_proxy_exec= [KNL] 6803 Enables or disables "proxy execution" style 6804 solution to mutex-based priority inversion. 6805 Format: <bool> 6806 6807 sched_verbose [KNL,EARLY] Enables verbose scheduler debug messages. 6808 6809 schedstats= [KNL,X86] Enable or disable scheduled statistics. 6810 Allowed values are enable and disable. This feature 6811 incurs a small amount of overhead in the scheduler 6812 but is useful for debugging and performance tuning. 6813 6814 sched_thermal_decay_shift= 6815 [Deprecated] 6816 [KNL, SMP] Set a decay shift for scheduler thermal 6817 pressure signal. Thermal pressure signal follows the 6818 default decay period of other scheduler pelt 6819 signals(usually 32 ms but configurable). Setting 6820 sched_thermal_decay_shift will left shift the decay 6821 period for the thermal pressure signal by the shift 6822 value. 6823 i.e. with the default pelt decay period of 32 ms 6824 sched_thermal_decay_shift thermal pressure decay pr 6825 1 64 ms 6826 2 128 ms 6827 and so on. 6828 Format: integer between 0 and 10 6829 Default is 0. 6830 6831 scftorture.holdoff= [KNL] 6832 Number of seconds to hold off before starting 6833 test. Defaults to zero for module insertion and 6834 to 10 seconds for built-in smp_call_function() 6835 tests. 6836 6837 scftorture.longwait= [KNL] 6838 Request ridiculously long waits randomly selected 6839 up to the chosen limit in seconds. Zero (the 6840 default) disables this feature. Please note 6841 that requesting even small non-zero numbers of 6842 seconds can result in RCU CPU stall warnings, 6843 softlockup complaints, and so on. 6844 6845 scftorture.nthreads= [KNL] 6846 Number of kthreads to spawn to invoke the 6847 smp_call_function() family of functions. 6848 The default of -1 specifies a number of kthreads 6849 equal to the number of CPUs. 6850 6851 scftorture.onoff_holdoff= [KNL] 6852 Number seconds to wait after the start of the 6853 test before initiating CPU-hotplug operations. 6854 6855 scftorture.onoff_interval= [KNL] 6856 Number seconds to wait between successive 6857 CPU-hotplug operations. Specifying zero (which 6858 is the default) disables CPU-hotplug operations. 6859 6860 scftorture.shutdown_secs= [KNL] 6861 The number of seconds following the start of the 6862 test after which to shut down the system. The 6863 default of zero avoids shutting down the system. 6864 Non-zero values are useful for automated tests. 6865 6866 scftorture.stat_interval= [KNL] 6867 The number of seconds between outputting the 6868 current test statistics to the console. A value 6869 of zero disables statistics output. 6870 6871 scftorture.stutter_cpus= [KNL] 6872 The number of jiffies to wait between each change 6873 to the set of CPUs under test. 6874 6875 scftorture.use_cpus_read_lock= [KNL] 6876 Use use_cpus_read_lock() instead of the default 6877 preempt_disable() to disable CPU hotplug 6878 while invoking one of the smp_call_function*() 6879 functions. 6880 6881 scftorture.verbose= [KNL] 6882 Enable additional printk() statements. 6883 6884 scftorture.weight_single= [KNL] 6885 The probability weighting to use for the 6886 smp_call_function_single() function with a zero 6887 "wait" parameter. A value of -1 selects the 6888 default if all other weights are -1. However, 6889 if at least one weight has some other value, a 6890 value of -1 will instead select a weight of zero. 6891 6892 scftorture.weight_single_wait= [KNL] 6893 The probability weighting to use for the 6894 smp_call_function_single() function with a 6895 non-zero "wait" parameter. See weight_single. 6896 6897 scftorture.weight_many= [KNL] 6898 The probability weighting to use for the 6899 smp_call_function_many() function with a zero 6900 "wait" parameter. See weight_single. 6901 Note well that setting a high probability for 6902 this weighting can place serious IPI load 6903 on the system. 6904 6905 scftorture.weight_many_wait= [KNL] 6906 The probability weighting to use for the 6907 smp_call_function_many() function with a 6908 non-zero "wait" parameter. See weight_single 6909 and weight_many. 6910 6911 scftorture.weight_all= [KNL] 6912 The probability weighting to use for the 6913 smp_call_function_all() function with a zero 6914 "wait" parameter. See weight_single and 6915 weight_many. 6916 6917 scftorture.weight_all_wait= [KNL] 6918 The probability weighting to use for the 6919 smp_call_function_all() function with a 6920 non-zero "wait" parameter. See weight_single 6921 and weight_many. 6922 6923 sdw_mclk_divider=[SDW] 6924 Specify the MCLK divider for Intel SoundWire buses in 6925 case the BIOS does not provide the clock rate properly. 6926 6927 skew_tick= [KNL,EARLY] Offset the periodic timer tick per cpu to mitigate 6928 xtime_lock contention on larger systems, and/or RCU lock 6929 contention on all systems with CONFIG_MAXSMP set. 6930 Format: { "0" | "1" } 6931 0 -- disable. (may be 1 via CONFIG_CMDLINE="skew_tick=1" 6932 1 -- enable. 6933 Note: increases power consumption, thus should only be 6934 enabled if running jitter sensitive (HPC/RT) workloads. 6935 6936 security= [SECURITY] Choose a legacy "major" security module to 6937 enable at boot. This has been deprecated by the 6938 "lsm=" parameter. 6939 6940 selinux= [SELINUX] Disable or enable SELinux at boot time. 6941 Format: { "0" | "1" } 6942 See security/selinux/Kconfig help text. 6943 0 -- disable. 6944 1 -- enable. 6945 Default value is 1. 6946 6947 serialnumber [BUGS=X86-32] 6948 6949 sev=option[,option...] [X86-64] 6950 6951 debug 6952 Enable debug messages. 6953 6954 nosnp 6955 Do not enable SEV-SNP (applies to host/hypervisor 6956 only). Setting 'nosnp' avoids the RMP check overhead 6957 in memory accesses when users do not want to run 6958 SEV-SNP guests. 6959 6960 shapers= [NET] 6961 Maximal number of shapers. 6962 6963 show_lapic= [APIC,X86] Advanced Programmable Interrupt Controller 6964 Limit apic dumping. The parameter defines the maximal 6965 number of local apics being dumped. Also it is possible 6966 to set it to "all" by meaning -- no limit here. 6967 Format: { 1 (default) | 2 | ... | all }. 6968 The parameter valid if only apic=debug or 6969 apic=verbose is specified. 6970 Example: apic=debug show_lapic=all 6971 6972 slab_debug[=options[,slabs][;[options[,slabs]]...] [MM] 6973 Enabling slab_debug allows one to determine the 6974 culprit if slab objects become corrupted. Enabling 6975 slab_debug can create guard zones around objects and 6976 may poison objects when not in use. Also tracks the 6977 last alloc / free. For more information see 6978 Documentation/admin-guide/mm/slab.rst. 6979 (slub_debug legacy name also accepted for now) 6980 6981 Using this option implies the "no_hash_pointers" 6982 option which can be undone by adding the 6983 "hash_pointers=always" option. 6984 6985 slab_max_order= [MM] 6986 Determines the maximum allowed order for slabs. 6987 A high setting may cause OOMs due to memory 6988 fragmentation. For more information see 6989 Documentation/admin-guide/mm/slab.rst. 6990 (slub_max_order legacy name also accepted for now) 6991 6992 slab_merge [MM] 6993 Enable merging of slabs with similar size when the 6994 kernel is built without CONFIG_SLAB_MERGE_DEFAULT. 6995 (slub_merge legacy name also accepted for now) 6996 6997 slab_min_objects= [MM] 6998 The minimum number of objects per slab. SLUB will 6999 increase the slab order up to slab_max_order to 7000 generate a sufficiently large slab able to contain 7001 the number of objects indicated. The higher the number 7002 of objects the smaller the overhead of tracking slabs 7003 and the less frequently locks need to be acquired. 7004 For more information see 7005 Documentation/admin-guide/mm/slab.rst. 7006 (slub_min_objects legacy name also accepted for now) 7007 7008 slab_min_order= [MM] 7009 Determines the minimum page order for slabs. Must be 7010 lower or equal to slab_max_order. For more information see 7011 Documentation/admin-guide/mm/slab.rst. 7012 (slub_min_order legacy name also accepted for now) 7013 7014 slab_nomerge [MM] 7015 Disable merging of slabs with similar size. May be 7016 necessary if there is some reason to distinguish 7017 allocs to different slabs, especially in hardened 7018 environments where the risk of heap overflows and 7019 layout control by attackers can usually be 7020 frustrated by disabling merging. This will reduce 7021 most of the exposure of a heap attack to a single 7022 cache (risks via metadata attacks are mostly 7023 unchanged). Debug options disable merging on their 7024 own. 7025 For more information see 7026 Documentation/admin-guide/mm/slab.rst. 7027 (slub_nomerge legacy name also accepted for now) 7028 7029 slab_strict_numa [MM] 7030 Support memory policies on a per object level 7031 in the slab allocator. The default is for memory 7032 policies to be applied at the folio level when 7033 a new folio is needed or a partial folio is 7034 retrieved from the lists. Increases overhead 7035 in the slab fastpaths but gains more accurate 7036 NUMA kernel object placement which helps with slow 7037 interconnects in NUMA systems. 7038 7039 slram= [HW,MTD] 7040 7041 smart2= [HW] 7042 Format: <io1>[,<io2>[,...,<io8>]] 7043 7044 smp.csd_lock_timeout= [KNL] 7045 Specify the period of time in milliseconds 7046 that smp_call_function() and friends will wait 7047 for a CPU to release the CSD lock. This is 7048 useful when diagnosing bugs involving CPUs 7049 disabling interrupts for extended periods 7050 of time. Defaults to 5,000 milliseconds, and 7051 setting a value of zero disables this feature. 7052 This feature may be more efficiently disabled 7053 using the csdlock_debug- kernel parameter. 7054 7055 smp.panic_on_ipistall= [KNL] 7056 If a csd_lock_timeout extends for more than 7057 the specified number of milliseconds, panic the 7058 system. By default, let CSD-lock acquisition 7059 take as long as they take. Specifying 300,000 7060 for this value provides a 5-minute timeout. 7061 7062 smsc-ircc2.nopnp [HW] Don't use PNP to discover SMC devices 7063 smsc-ircc2.ircc_cfg= [HW] Device configuration I/O port 7064 smsc-ircc2.ircc_sir= [HW] SIR base I/O port 7065 smsc-ircc2.ircc_fir= [HW] FIR base I/O port 7066 smsc-ircc2.ircc_irq= [HW] IRQ line 7067 smsc-ircc2.ircc_dma= [HW] DMA channel 7068 smsc-ircc2.ircc_transceiver= [HW] Transceiver type: 7069 0: Toshiba Satellite 1800 (GP data pin select) 7070 1: Fast pin select (default) 7071 2: ATC IRMode 7072 7073 smt= [KNL,MIPS,S390,EARLY] Set the maximum number of threads 7074 (logical CPUs) to use per physical CPU on systems 7075 capable of symmetric multithreading (SMT). Will 7076 be capped to the actual hardware limit. 7077 Format: <integer> 7078 Default: -1 (no limit) 7079 7080 softlockup_panic= 7081 [KNL] Should the soft-lockup detector generate panics. 7082 Format: <int> 7083 7084 A value of non-zero instructs the soft-lockup detector 7085 to panic the machine when a soft-lockup duration exceeds 7086 N thresholds. It is also controlled by the kernel.softlockup_panic 7087 sysctl and CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC, which is the 7088 respective build-time switch to that functionality. 7089 7090 softlockup_all_cpu_backtrace= 7091 [KNL] Should the soft-lockup detector generate 7092 backtraces on all cpus. 7093 Format: 0 | 1 7094 7095 sonypi.*= [HW] Sony Programmable I/O Control Device driver 7096 See Documentation/admin-guide/laptops/sonypi.rst 7097 7098 spectre_bhi= [X86] Control mitigation of Branch History Injection 7099 (BHI) vulnerability. This setting affects the 7100 deployment of the HW BHI control and the SW BHB 7101 clearing sequence. 7102 7103 on - (default) Enable the HW or SW mitigation as 7104 needed. This protects the kernel from 7105 both syscalls and VMs. 7106 vmexit - On systems which don't have the HW mitigation 7107 available, enable the SW mitigation on vmexit 7108 ONLY. On such systems, the host kernel is 7109 protected from VM-originated BHI attacks, but 7110 may still be vulnerable to syscall attacks. 7111 off - Disable the mitigation. 7112 7113 spectre_v2= [X86,EARLY] Control mitigation of Spectre variant 2 7114 (indirect branch speculation) vulnerability. 7115 The default operation protects the kernel from 7116 user space attacks. 7117 7118 on - unconditionally enable, implies 7119 spectre_v2_user=on 7120 off - unconditionally disable, implies 7121 spectre_v2_user=off 7122 auto - kernel detects whether your CPU model is 7123 vulnerable 7124 7125 Selecting 'on' will, and 'auto' may, choose a 7126 mitigation method at run time according to the 7127 CPU, the available microcode, the setting of the 7128 CONFIG_MITIGATION_RETPOLINE configuration option, 7129 and the compiler with which the kernel was built. 7130 7131 Selecting 'on' will also enable the mitigation 7132 against user space to user space task attacks. 7133 Selecting specific mitigation does not force enable 7134 user mitigations. 7135 7136 Selecting 'off' will disable both the kernel and 7137 the user space protections. 7138 7139 Specific mitigations can also be selected manually: 7140 7141 retpoline - replace indirect branches 7142 retpoline,generic - Retpolines 7143 retpoline,lfence - LFENCE; indirect branch 7144 retpoline,amd - alias for retpoline,lfence 7145 eibrs - Enhanced/Auto IBRS 7146 eibrs,retpoline - Enhanced/Auto IBRS + Retpolines 7147 eibrs,lfence - Enhanced/Auto IBRS + LFENCE 7148 ibrs - use IBRS to protect kernel 7149 7150 Not specifying this option is equivalent to 7151 spectre_v2=auto. 7152 7153 spectre_v2_user= 7154 [X86] Control mitigation of Spectre variant 2 7155 (indirect branch speculation) vulnerability between 7156 user space tasks 7157 7158 on - Unconditionally enable mitigations. Is 7159 enforced by spectre_v2=on 7160 7161 off - Unconditionally disable mitigations. Is 7162 enforced by spectre_v2=off 7163 7164 prctl - Indirect branch speculation is enabled, 7165 but mitigation can be enabled via prctl 7166 per thread. The mitigation control state 7167 is inherited on fork. 7168 7169 prctl,ibpb 7170 - Like "prctl" above, but only STIBP is 7171 controlled per thread. IBPB is issued 7172 always when switching between different user 7173 space processes. 7174 7175 seccomp 7176 - Same as "prctl" above, but all seccomp 7177 threads will enable the mitigation unless 7178 they explicitly opt out. 7179 7180 seccomp,ibpb 7181 - Like "seccomp" above, but only STIBP is 7182 controlled per thread. IBPB is issued 7183 always when switching between different 7184 user space processes. 7185 7186 auto - Kernel selects the mitigation depending on 7187 the available CPU features and vulnerability. 7188 7189 Default mitigation: "prctl" 7190 7191 Not specifying this option is equivalent to 7192 spectre_v2_user=auto. 7193 7194 spec_rstack_overflow= 7195 [X86,EARLY] Control RAS overflow mitigation on AMD Zen CPUs 7196 7197 off - Disable mitigation 7198 microcode - Enable microcode mitigation only 7199 safe-ret - Enable sw-only safe RET mitigation (default) 7200 ibpb - Enable mitigation by issuing IBPB on 7201 kernel entry 7202 ibpb-vmexit - Issue IBPB only on VMEXIT 7203 (cloud-specific mitigation) 7204 7205 spec_store_bypass_disable= 7206 [HW,EARLY] Control Speculative Store Bypass (SSB) Disable mitigation 7207 (Speculative Store Bypass vulnerability) 7208 7209 Certain CPUs are vulnerable to an exploit against a 7210 a common industry wide performance optimization known 7211 as "Speculative Store Bypass" in which recent stores 7212 to the same memory location may not be observed by 7213 later loads during speculative execution. The idea 7214 is that such stores are unlikely and that they can 7215 be detected prior to instruction retirement at the 7216 end of a particular speculation execution window. 7217 7218 In vulnerable processors, the speculatively forwarded 7219 store can be used in a cache side channel attack, for 7220 example to read memory to which the attacker does not 7221 directly have access (e.g. inside sandboxed code). 7222 7223 This parameter controls whether the Speculative Store 7224 Bypass optimization is used. 7225 7226 On x86 the options are: 7227 7228 on - Unconditionally disable Speculative Store Bypass 7229 off - Unconditionally enable Speculative Store Bypass 7230 auto - Kernel detects whether the CPU model contains an 7231 implementation of Speculative Store Bypass and 7232 picks the most appropriate mitigation. If the 7233 CPU is not vulnerable, "off" is selected. If the 7234 CPU is vulnerable the default mitigation is 7235 architecture and Kconfig dependent. See below. 7236 prctl - Control Speculative Store Bypass per thread 7237 via prctl. Speculative Store Bypass is enabled 7238 for a process by default. The state of the control 7239 is inherited on fork. 7240 seccomp - Same as "prctl" above, but all seccomp threads 7241 will disable SSB unless they explicitly opt out. 7242 7243 Default mitigations: 7244 X86: "prctl" 7245 7246 On powerpc the options are: 7247 7248 on,auto - On Power8 and Power9 insert a store-forwarding 7249 barrier on kernel entry and exit. On Power7 7250 perform a software flush on kernel entry and 7251 exit. 7252 off - No action. 7253 7254 Not specifying this option is equivalent to 7255 spec_store_bypass_disable=auto. 7256 7257 split_lock_detect= 7258 [X86] Enable split lock detection or bus lock detection 7259 7260 When enabled (and if hardware support is present), atomic 7261 instructions that access data across cache line 7262 boundaries will result in an alignment check exception 7263 for split lock detection or a debug exception for 7264 bus lock detection. 7265 7266 off - not enabled 7267 7268 warn - the kernel will emit rate-limited warnings 7269 about applications triggering the #AC 7270 exception or the #DB exception. This mode is 7271 the default on CPUs that support split lock 7272 detection or bus lock detection. Default 7273 behavior is by #AC if both features are 7274 enabled in hardware. 7275 7276 fatal - the kernel will send SIGBUS to applications 7277 that trigger the #AC exception or the #DB 7278 exception. Default behavior is by #AC if 7279 both features are enabled in hardware. 7280 7281 ratelimit:N - 7282 Set system wide rate limit to N bus locks 7283 per second for bus lock detection. 7284 0 < N <= 1000. 7285 7286 N/A for split lock detection. 7287 7288 7289 If an #AC exception is hit in the kernel or in 7290 firmware (i.e. not while executing in user mode) 7291 the kernel will oops in either "warn" or "fatal" 7292 mode. 7293 7294 #DB exception for bus lock is triggered only when 7295 CPL > 0. 7296 7297 srbds= [X86,INTEL,EARLY] 7298 Control the Special Register Buffer Data Sampling 7299 (SRBDS) mitigation. 7300 7301 Certain CPUs are vulnerable to an MDS-like 7302 exploit which can leak bits from the random 7303 number generator. 7304 7305 By default, this issue is mitigated by 7306 microcode. However, the microcode fix can cause 7307 the RDRAND and RDSEED instructions to become 7308 much slower. Among other effects, this will 7309 result in reduced throughput from /dev/urandom. 7310 7311 The microcode mitigation can be disabled with 7312 the following option: 7313 7314 off: Disable mitigation and remove 7315 performance impact to RDRAND and RDSEED 7316 7317 srcutree.big_cpu_lim [KNL] 7318 Specifies the number of CPUs constituting a 7319 large system, such that srcu_struct structures 7320 should immediately allocate an srcu_node array. 7321 This kernel-boot parameter defaults to 128, 7322 but takes effect only when the low-order four 7323 bits of srcutree.convert_to_big is equal to 3 7324 (decide at boot). 7325 7326 srcutree.convert_to_big [KNL] 7327 Specifies under what conditions an SRCU tree 7328 srcu_struct structure will be converted to big 7329 form, that is, with an rcu_node tree: 7330 7331 0: Never. 7332 1: At init_srcu_struct() time. 7333 2: When rcutorture decides to. 7334 3: Decide at boot time (default). 7335 0x1X: Above plus if high contention. 7336 7337 Either way, the srcu_node tree will be sized based 7338 on the actual runtime number of CPUs (nr_cpu_ids) 7339 instead of the compile-time CONFIG_NR_CPUS. 7340 7341 srcutree.counter_wrap_check [KNL] 7342 Specifies how frequently to check for 7343 grace-period sequence counter wrap for the 7344 srcu_data structure's ->srcu_gp_seq_needed field. 7345 The greater the number of bits set in this kernel 7346 parameter, the less frequently counter wrap will 7347 be checked for. Note that the bottom two bits 7348 are ignored. 7349 7350 srcutree.exp_holdoff [KNL] 7351 Specifies how many nanoseconds must elapse 7352 since the end of the last SRCU grace period for 7353 a given srcu_struct until the next normal SRCU 7354 grace period will be considered for automatic 7355 expediting. Set to zero to disable automatic 7356 expediting. 7357 7358 srcutree.srcu_max_nodelay [KNL] 7359 Specifies the number of no-delay instances 7360 per jiffy for which the SRCU grace period 7361 worker thread will be rescheduled with zero 7362 delay. Beyond this limit, worker thread will 7363 be rescheduled with a sleep delay of one jiffy. 7364 7365 srcutree.srcu_max_nodelay_phase [KNL] 7366 Specifies the per-grace-period phase, number of 7367 non-sleeping polls of readers. Beyond this limit, 7368 grace period worker thread will be rescheduled 7369 with a sleep delay of one jiffy, between each 7370 rescan of the readers, for a grace period phase. 7371 7372 srcutree.srcu_retry_check_delay [KNL] 7373 Specifies number of microseconds of non-sleeping 7374 delay between each non-sleeping poll of readers. 7375 7376 srcutree.small_contention_lim [KNL] 7377 Specifies the number of update-side contention 7378 events per jiffy will be tolerated before 7379 initiating a conversion of an srcu_struct 7380 structure to big form. Note that the value of 7381 srcutree.convert_to_big must have the 0x10 bit 7382 set for contention-based conversions to occur. 7383 7384 ssbd= [ARM64,HW,EARLY] 7385 Speculative Store Bypass Disable control 7386 7387 On CPUs that are vulnerable to the Speculative 7388 Store Bypass vulnerability and offer a 7389 firmware based mitigation, this parameter 7390 indicates how the mitigation should be used: 7391 7392 force-on: Unconditionally enable mitigation for 7393 for both kernel and userspace 7394 force-off: Unconditionally disable mitigation for 7395 for both kernel and userspace 7396 kernel: Always enable mitigation in the 7397 kernel, and offer a prctl interface 7398 to allow userspace to register its 7399 interest in being mitigated too. 7400 7401 stack_guard_gap= [MM] 7402 override the default stack gap protection. The value 7403 is in page units and it defines how many pages prior 7404 to (for stacks growing down) resp. after (for stacks 7405 growing up) the main stack are reserved for no other 7406 mapping. Default value is 256 pages. 7407 7408 stack_depot_disable= [KNL,EARLY] 7409 Setting this to true through kernel command line will 7410 disable the stack depot thereby saving the static memory 7411 consumed by the stack hash table. By default this is set 7412 to false. 7413 7414 stack_depot_max_pools= [KNL,EARLY] 7415 Specify the maximum number of pools to use for storing 7416 stack traces. Pools are allocated on-demand up to this 7417 limit. Default value is 8191 pools. 7418 7419 stacktrace [FTRACE] 7420 Enable the stack tracer on boot up. 7421 7422 stacktrace_filter=[function-list] 7423 [FTRACE] Limit the functions that the stack tracer 7424 will trace at boot up. function-list is a comma-separated 7425 list of functions. This list can be changed at run 7426 time by the stack_trace_filter file in the debugfs 7427 tracing directory. Note, this enables stack tracing 7428 and the stacktrace above is not needed. 7429 7430 sti= [PARISC,HW] 7431 Format: <num> 7432 Set the STI (builtin display/keyboard on the HP-PARISC 7433 machines) console (graphic card) which should be used 7434 as the initial boot-console. 7435 See also comment in drivers/video/console/sticore.c. 7436 7437 sti_font= [HW] 7438 See comment in drivers/video/console/sticore.c. 7439 7440 stifb= [HW] 7441 Format: bpp:<bpp1>[:<bpp2>[:<bpp3>...]] 7442 7443 strict_sas_size= 7444 [X86] 7445 Format: <bool> 7446 Enable or disable strict sigaltstack size checks 7447 against the required signal frame size which 7448 depends on the supported FPU features. This can 7449 be used to filter out binaries which have 7450 not yet been made aware of AT_MINSIGSTKSZ. 7451 7452 stress_hpt [PPC,EARLY] 7453 Limits the number of kernel HPT entries in the hash 7454 page table to increase the rate of hash page table 7455 faults on kernel addresses. 7456 7457 stress_slb [PPC,EARLY] 7458 Limits the number of kernel SLB entries, and flushes 7459 them frequently to increase the rate of SLB faults 7460 on kernel addresses. 7461 7462 no_slb_preload [PPC,EARLY] 7463 Disables slb preloading for userspace. 7464 7465 sunrpc.min_resvport= 7466 sunrpc.max_resvport= 7467 [NFS,SUNRPC] 7468 SunRPC servers often require that client requests 7469 originate from a privileged port (i.e. a port in the 7470 range 0 < portnr < 1024). 7471 An administrator who wishes to reserve some of these 7472 ports for other uses may adjust the range that the 7473 kernel's sunrpc client considers to be privileged 7474 using these two parameters to set the minimum and 7475 maximum port values. 7476 7477 sunrpc.svc_rpc_per_connection_limit= 7478 [NFS,SUNRPC] 7479 Limit the number of requests that the server will 7480 process in parallel from a single connection. 7481 The default value is 0 (no limit). 7482 7483 sunrpc.pool_mode= 7484 [NFS] 7485 Control how the NFS server code allocates CPUs to 7486 service thread pools. Depending on how many NICs 7487 you have and where their interrupts are bound, this 7488 option will affect which CPUs will do NFS serving. 7489 Note: this parameter cannot be changed while the 7490 NFS server is running. 7491 7492 auto the server chooses an appropriate mode 7493 automatically using heuristics 7494 global a single global pool contains all CPUs 7495 percpu one pool for each CPU 7496 pernode one pool for each NUMA node (equivalent 7497 to global on non-NUMA machines) 7498 7499 sunrpc.tcp_slot_table_entries= 7500 sunrpc.udp_slot_table_entries= 7501 [NFS,SUNRPC] 7502 Sets the upper limit on the number of simultaneous 7503 RPC calls that can be sent from the client to a 7504 server. Increasing these values may allow you to 7505 improve throughput, but will also increase the 7506 amount of memory reserved for use by the client. 7507 7508 suspend.pm_test_delay= 7509 [SUSPEND] 7510 Sets the number of seconds to remain in a suspend test 7511 mode before resuming the system (see 7512 /sys/power/pm_test). Only available when CONFIG_PM_DEBUG 7513 is set. Default value is 5. 7514 7515 svm= [PPC] 7516 Format: { on | off | y | n | 1 | 0 } 7517 This parameter controls use of the Protected 7518 Execution Facility on pSeries. 7519 7520 swiotlb= [ARM,PPC,MIPS,X86,S390,EARLY] 7521 Format: { <int> [,<int>] | force | noforce } 7522 <int> -- Number of I/O TLB slabs 7523 <int> -- Second integer after comma. Number of swiotlb 7524 areas with their own lock. Will be rounded up 7525 to a power of 2. 7526 force -- force using of bounce buffers even if they 7527 wouldn't be automatically used by the kernel 7528 noforce -- Never use bounce buffers (for debugging) 7529 7530 switches= [HW,M68k,EARLY] 7531 7532 sysctl.*= [KNL] 7533 Set a sysctl parameter, right before loading the init 7534 process, as if the value was written to the respective 7535 /proc/sys/... file. Both '.' and '/' are recognized as 7536 separators. Unrecognized parameters and invalid values 7537 are reported in the kernel log. Sysctls registered 7538 later by a loaded module cannot be set this way. 7539 Example: sysctl.vm.swappiness=40 7540 7541 sysrq_always_enabled 7542 [KNL] 7543 Ignore sysrq setting - this boot parameter will 7544 neutralize any effect of /proc/sys/kernel/sysrq. 7545 Useful for debugging. 7546 7547 tcpmhash_entries= [KNL,NET] 7548 Set the number of tcp_metrics_hash slots. 7549 Default value is 8192 or 16384 depending on total 7550 ram pages. This is used to specify the TCP metrics 7551 cache size. See Documentation/networking/ip-sysctl.rst 7552 "tcp_no_metrics_save" section for more details. 7553 7554 tdfx= [HW,DRM] 7555 7556 test_suspend= [SUSPEND] 7557 Format: { "mem" | "standby" | "freeze" }[,N] 7558 Specify "mem" (for Suspend-to-RAM) or "standby" (for 7559 standby suspend) or "freeze" (for suspend type freeze) 7560 as the system sleep state during system startup with 7561 the optional capability to repeat N number of times. 7562 The system is woken from this state using a 7563 wakeup-capable RTC alarm. 7564 7565 thash_entries= [KNL,NET] 7566 Set number of hash buckets for TCP connection 7567 7568 thermal.act= [HW,ACPI] 7569 -1: disable all active trip points in all thermal zones 7570 <degrees C>: override all lowest active trip points 7571 7572 thermal.crt= [HW,ACPI] 7573 -1: disable all critical trip points in all thermal zones 7574 <degrees C>: override all critical trip points 7575 7576 thermal.off= [HW,ACPI] 7577 1: disable ACPI thermal control 7578 7579 thermal.psv= [HW,ACPI] 7580 -1: disable all passive trip points 7581 <degrees C>: override all passive trip points to this 7582 value 7583 7584 thermal.tzp= [HW,ACPI] 7585 Specify global default ACPI thermal zone polling rate 7586 <deci-seconds>: poll all this frequency 7587 0: no polling (default) 7588 7589 thp_anon= [KNL] 7590 Format: <size>[KMG],<size>[KMG]:<state>;<size>[KMG]-<size>[KMG]:<state> 7591 state is one of "always", "madvise", "never" or "inherit". 7592 Control the default behavior of the system with respect 7593 to anonymous transparent hugepages. 7594 Can be used multiple times for multiple anon THP sizes. 7595 See Documentation/admin-guide/mm/transhuge.rst for more 7596 details. 7597 7598 threadirqs [KNL,EARLY] 7599 Force threading of all interrupt handlers except those 7600 marked explicitly IRQF_NO_THREAD. 7601 7602 thp_shmem= [KNL] 7603 Format: <size>[KMG],<size>[KMG]:<policy>;<size>[KMG]-<size>[KMG]:<policy> 7604 Control the default policy of each hugepage size for the 7605 internal shmem mount. <policy> is one of policies available 7606 for the shmem mount ("always", "inherit", "never", "within_size", 7607 and "advise"). 7608 It can be used multiple times for multiple shmem THP sizes. 7609 See Documentation/admin-guide/mm/transhuge.rst for more 7610 details. 7611 7612 topology= [S390,EARLY] 7613 Format: {off | on} 7614 Specify if the kernel should make use of the cpu 7615 topology information if the hardware supports this. 7616 The scheduler will make use of this information and 7617 e.g. base its process migration decisions on it. 7618 Default is on. 7619 7620 torture.disable_onoff_at_boot= [KNL] 7621 Prevent the CPU-hotplug component of torturing 7622 until after init has spawned. 7623 7624 torture.ftrace_dump_at_shutdown= [KNL] 7625 Dump the ftrace buffer at torture-test shutdown, 7626 even if there were no errors. This can be a 7627 very costly operation when many torture tests 7628 are running concurrently, especially on systems 7629 with rotating-rust storage. 7630 7631 torture.verbose_sleep_frequency= [KNL] 7632 Specifies how many verbose printk()s should be 7633 emitted between each sleep. The default of zero 7634 disables verbose-printk() sleeping. 7635 7636 torture.verbose_sleep_duration= [KNL] 7637 Duration of each verbose-printk() sleep in jiffies. 7638 7639 tpm.disable_pcr_integrity= [HW,TPM] 7640 Do not protect PCR registers from unintended physical 7641 access, or interposers in the bus by the means of 7642 having an integrity protected session wrapped around 7643 TPM2_PCR_Extend command. Consider this in a situation 7644 where TPM is heavily utilized by IMA, thus protection 7645 causing a major performance hit, and the space where 7646 machines are deployed is by other means guarded. 7647 7648 tpm_crb_ffa.busy_timeout_ms= [ARM64,TPM] 7649 Maximum time in milliseconds to retry sending a message 7650 to the TPM service before giving up. This parameter controls 7651 how long the system will continue retrying when the TPM 7652 service is busy. 7653 Format: <unsigned int> 7654 Default: 2000 (2 seconds) 7655 7656 tpm_suspend_pcr=[HW,TPM] 7657 Format: integer pcr id 7658 Specify that at suspend time, the tpm driver 7659 should extend the specified pcr with zeros, 7660 as a workaround for some chips which fail to 7661 flush the last written pcr on TPM_SaveState. 7662 This will guarantee that all the other pcrs 7663 are saved. 7664 7665 tpm_tis.interrupts= [HW,TPM] 7666 Enable interrupts for the MMIO based physical layer 7667 for the FIFO interface. By default it is set to false 7668 (0). For more information about TPM hardware interfaces 7669 defined by Trusted Computing Group (TCG) see 7670 https://trustedcomputinggroup.org/resource/pc-client-platform-tpm-profile-ptp-specification/ 7671 7672 tp_printk [FTRACE] 7673 Have the tracepoints sent to printk as well as the 7674 tracing ring buffer. This is useful for early boot up 7675 where the system hangs or reboots and does not give the 7676 option for reading the tracing buffer or performing a 7677 ftrace_dump_on_oops. 7678 7679 To turn off having tracepoints sent to printk, 7680 echo 0 > /proc/sys/kernel/tracepoint_printk 7681 Note, echoing 1 into this file without the 7682 tp_printk kernel cmdline option has no effect. 7683 7684 The tp_printk_stop_on_boot (see below) can also be used 7685 to stop the printing of events to console at 7686 late_initcall_sync. 7687 7688 ** CAUTION ** 7689 7690 Having tracepoints sent to printk() and activating high 7691 frequency tracepoints such as irq or sched, can cause 7692 the system to live lock. 7693 7694 tp_printk_stop_on_boot [FTRACE] 7695 When tp_printk (above) is set, it can cause a lot of noise 7696 on the console. It may be useful to only include the 7697 printing of events during boot up, as user space may 7698 make the system inoperable. 7699 7700 This command line option will stop the printing of events 7701 to console at the late_initcall_sync() time frame. 7702 7703 trace_buf_size=nn[KMG] 7704 [FTRACE] will set tracing buffer size on each cpu. 7705 7706 trace_clock= [FTRACE] Set the clock used for tracing events 7707 at boot up. 7708 local - Use the per CPU time stamp counter 7709 (converted into nanoseconds). Fast, but 7710 depending on the architecture, may not be 7711 in sync between CPUs. 7712 global - Event time stamps are synchronized across 7713 CPUs. May be slower than the local clock, 7714 but better for some race conditions. 7715 counter - Simple counting of events (1, 2, ..) 7716 note, some counts may be skipped due to the 7717 infrastructure grabbing the clock more than 7718 once per event. 7719 uptime - Use jiffies as the time stamp. 7720 perf - Use the same clock that perf uses. 7721 mono - Use ktime_get_mono_fast_ns() for time stamps. 7722 mono_raw - Use ktime_get_raw_fast_ns() for time 7723 stamps. 7724 boot - Use ktime_get_boot_fast_ns() for time stamps. 7725 Architectures may add more clocks. See 7726 Documentation/trace/ftrace.rst for more details. 7727 7728 trace_event=[event-list] 7729 [FTRACE] Set and start specified trace events in order 7730 to facilitate early boot debugging. The event-list is a 7731 comma-separated list of trace events to enable. See 7732 also Documentation/trace/events.rst 7733 7734 To enable modules, use :mod: keyword: 7735 7736 trace_event=:mod:<module> 7737 7738 The value before :mod: will only enable specific events 7739 that are part of the module. See the above mentioned 7740 document for more information. 7741 7742 trace_instance=[instance-info] 7743 [FTRACE] Create a ring buffer instance early in boot up. 7744 This will be listed in: 7745 7746 /sys/kernel/tracing/instances 7747 7748 Events can be enabled at the time the instance is created 7749 via: 7750 7751 trace_instance=<name>,<system1>:<event1>,<system2>:<event2> 7752 7753 Note, the "<system*>:" portion is optional if the event is 7754 unique. 7755 7756 trace_instance=foo,sched:sched_switch,irq_handler_entry,initcall 7757 7758 will enable the "sched_switch" event (note, the "sched:" is optional, and 7759 the same thing would happen if it was left off). The irq_handler_entry 7760 event, and all events under the "initcall" system. 7761 7762 Flags can be added to the instance to modify its behavior when it is 7763 created. The flags are separated by '^'. 7764 7765 The available flags are: 7766 7767 traceoff - Have the tracing instance tracing disabled after it is created. 7768 traceprintk - Have trace_printk() write into this trace instance 7769 (note, "printk" and "trace_printk" can also be used) 7770 7771 trace_instance=foo^traceoff^traceprintk,sched,irq 7772 7773 The flags must come before the defined events. 7774 7775 If memory has been reserved (see memmap for x86), the instance 7776 can use that memory: 7777 7778 memmap=12M$0x284500000 trace_instance=boot_map@0x284500000:12M 7779 7780 The above will create a "boot_map" instance that uses the physical 7781 memory at 0x284500000 that is 12Megs. The per CPU buffers of that 7782 instance will be split up accordingly. 7783 7784 Alternatively, the memory can be reserved by the reserve_mem option: 7785 7786 reserve_mem=12M:4096:trace trace_instance=boot_map@trace 7787 7788 This will reserve 12 megabytes at boot up with a 4096 byte alignment 7789 and place the ring buffer in this memory. Note that due to KASLR, the 7790 memory may not be the same location each time, which will not preserve 7791 the buffer content. 7792 7793 Also note that the layout of the ring buffer data may change between 7794 kernel versions where the validator will fail and reset the ring buffer 7795 if the layout is not the same as the previous kernel. 7796 7797 If the ring buffer is used for persistent bootups and has events enabled, 7798 it is recommend to disable tracing so that events from a previous boot do not 7799 mix with events of the current boot (unless you are debugging a random crash 7800 at boot up). 7801 7802 reserve_mem=12M:4096:trace trace_instance=boot_map^traceoff^traceprintk@trace,sched,irq 7803 7804 Note, saving the trace buffer across reboots does require that the system 7805 is set up to not wipe memory. For instance, CONFIG_RESET_ATTACK_MITIGATION 7806 can force a memory reset on boot which will clear any trace that was stored. 7807 This is just one of many ways that can clear memory. Make sure your system 7808 keeps the content of memory across reboots before relying on this option. 7809 7810 NB: Both the mapped address and size must be page aligned for the architecture. 7811 7812 See also Documentation/trace/debugging.rst 7813 7814 7815 trace_options=[option-list] 7816 [FTRACE] Enable or disable tracer options at boot. 7817 The option-list is a comma delimited list of options 7818 that can be enabled or disabled just as if you were 7819 to echo the option name into 7820 7821 /sys/kernel/tracing/trace_options 7822 7823 For example, to enable stacktrace option (to dump the 7824 stack trace of each event), add to the command line: 7825 7826 trace_options=stacktrace 7827 7828 See also Documentation/trace/ftrace.rst "trace options" 7829 section. 7830 7831 trace_trigger=[trigger-list] 7832 [FTRACE] Add an event trigger on specific events. 7833 Set a trigger on top of a specific event, with an optional 7834 filter. 7835 7836 The format is "trace_trigger=<event>.<trigger>[ if <filter>],..." 7837 Where more than one trigger may be specified that are comma delimited. 7838 7839 For example: 7840 7841 trace_trigger="sched_switch.stacktrace if prev_state == 2" 7842 7843 The above will enable the "stacktrace" trigger on the "sched_switch" 7844 event but only trigger it if the "prev_state" of the "sched_switch" 7845 event is "2" (TASK_UNINTERRUPTIBLE). 7846 7847 See also "Event triggers" in Documentation/trace/events.rst 7848 7849 7850 traceoff_after_boot 7851 [FTRACE] Sometimes tracing is used to debug issues 7852 during the boot process. Since the trace buffer has a 7853 limited amount of storage, it may be prudent to 7854 disable tracing after the boot is finished, otherwise 7855 the critical information may be overwritten. With this 7856 option, the main tracing buffer will be turned off at 7857 the end of the boot process. 7858 7859 traceoff_on_warning 7860 [FTRACE] enable this option to disable tracing when a 7861 warning is hit. This turns off "tracing_on". Tracing can 7862 be enabled again by echoing '1' into the "tracing_on" 7863 file located in /sys/kernel/tracing/ 7864 7865 This option is useful, as it disables the trace before 7866 the WARNING dump is called, which prevents the trace to 7867 be filled with content caused by the warning output. 7868 7869 This option can also be set at run time via the sysctl 7870 option: kernel/traceoff_on_warning 7871 7872 transparent_hugepage= 7873 [KNL] 7874 Format: [always|madvise|never] 7875 Can be used to control the default behavior of the system 7876 with respect to transparent hugepages. 7877 See Documentation/admin-guide/mm/transhuge.rst 7878 for more details. 7879 7880 transparent_hugepage_shmem= [KNL] 7881 Format: [always|within_size|advise|never|deny|force] 7882 Can be used to control the hugepage allocation policy for 7883 the internal shmem mount. 7884 See Documentation/admin-guide/mm/transhuge.rst 7885 for more details. 7886 7887 transparent_hugepage_tmpfs= [KNL] 7888 Format: [always|within_size|advise|never] 7889 Can be used to control the default hugepage allocation policy 7890 for the tmpfs mount. 7891 See Documentation/admin-guide/mm/transhuge.rst 7892 for more details. 7893 7894 trusted.source= [KEYS] 7895 Format: <string> 7896 This parameter identifies the trust source as a backend 7897 for trusted keys implementation. Supported trust 7898 sources: 7899 - "tpm" 7900 - "tee" 7901 - "caam" 7902 - "dcp" 7903 - "pkwm" 7904 If not specified then it defaults to iterating through 7905 the trust source list starting with TPM and assigns the 7906 first trust source as a backend which is initialized 7907 successfully during iteration. 7908 7909 trusted.rng= [KEYS] 7910 Format: <string> 7911 The RNG used to generate key material for trusted keys. 7912 Can be one of: 7913 - "kernel" 7914 - the same value as trusted.source: "tpm" or "tee" 7915 - "default" 7916 If not specified, "default" is used. In this case, 7917 the RNG's choice is left to each individual trust source. 7918 7919 trusted.dcp_use_otp_key 7920 This is intended to be used in combination with 7921 trusted.source=dcp and will select the DCP OTP key 7922 instead of the DCP UNIQUE key blob encryption. 7923 7924 trusted.dcp_skip_zk_test 7925 This is intended to be used in combination with 7926 trusted.source=dcp and will disable the check if the 7927 blob key is all zeros. This is helpful for situations where 7928 having this key zero'ed is acceptable. E.g. in testing 7929 scenarios. 7930 7931 tsa= [X86] Control mitigation for Transient Scheduler 7932 Attacks on AMD CPUs. Search the following in your 7933 favourite search engine for more details: 7934 7935 "Technical guidance for mitigating transient scheduler 7936 attacks". 7937 7938 off - disable the mitigation 7939 on - enable the mitigation (default) 7940 user - mitigate only user/kernel transitions 7941 vm - mitigate only guest/host transitions 7942 7943 7944 tsc= Disable clocksource stability checks for TSC. 7945 Format: <string> 7946 [x86] reliable: mark tsc clocksource as reliable, this 7947 disables clocksource verification at runtime, as well 7948 as the stability checks done at bootup. Used to enable 7949 high-resolution timer mode on older hardware, and in 7950 virtualized environment. 7951 [x86] noirqtime: Do not use TSC to do irq accounting. 7952 Used to run time disable IRQ_TIME_ACCOUNTING on any 7953 platforms where RDTSC is slow and this accounting 7954 can add overhead. 7955 [x86] unstable: mark the TSC clocksource as unstable, this 7956 marks the TSC unconditionally unstable at bootup and 7957 avoids any further wobbles once the TSC watchdog notices. 7958 [x86] nowatchdog: disable clocksource watchdog. Used 7959 in situations with strict latency requirements (where 7960 interruptions from clocksource watchdog are not 7961 acceptable). 7962 [x86] recalibrate: force recalibration against a HW timer 7963 (HPET or PM timer) on systems whose TSC frequency was 7964 obtained from HW or FW using either an MSR or CPUID(0x15). 7965 Warn if the difference is more than 500 ppm. 7966 [x86] watchdog: Enforce the clocksource watchdog on TSC 7967 7968 tsc_early_khz= [X86,EARLY] Skip early TSC calibration and use the given 7969 value instead. Useful when the early TSC frequency discovery 7970 procedure is not reliable, such as on overclocked systems 7971 with CPUID.16h support and partial CPUID.15h support. 7972 Format: <unsigned int> 7973 7974 tsx= [X86] Control Transactional Synchronization 7975 Extensions (TSX) feature in Intel processors that 7976 support TSX control. 7977 7978 This parameter controls the TSX feature. The options are: 7979 7980 on - Enable TSX on the system. Although there are 7981 mitigations for all known security vulnerabilities, 7982 TSX has been known to be an accelerator for 7983 several previous speculation-related CVEs, and 7984 so there may be unknown security risks associated 7985 with leaving it enabled. 7986 7987 off - Disable TSX on the system. (Note that this 7988 option takes effect only on newer CPUs which are 7989 not vulnerable to MDS, i.e., have 7990 MSR_IA32_ARCH_CAPABILITIES.MDS_NO=1 and which get 7991 the new IA32_TSX_CTRL MSR through a microcode 7992 update. This new MSR allows for the reliable 7993 deactivation of the TSX functionality.) 7994 7995 auto - Disable TSX if X86_BUG_TAA is present, 7996 otherwise enable TSX on the system. 7997 7998 Not specifying this option is equivalent to tsx=off. 7999 8000 See Documentation/admin-guide/hw-vuln/tsx_async_abort.rst 8001 for more details. 8002 8003 tsx_async_abort= [X86,INTEL,EARLY] Control mitigation for the TSX Async 8004 Abort (TAA) vulnerability. 8005 8006 Similar to Micro-architectural Data Sampling (MDS) 8007 certain CPUs that support Transactional 8008 Synchronization Extensions (TSX) are vulnerable to an 8009 exploit against CPU internal buffers which can forward 8010 information to a disclosure gadget under certain 8011 conditions. 8012 8013 In vulnerable processors, the speculatively forwarded 8014 data can be used in a cache side channel attack, to 8015 access data to which the attacker does not have direct 8016 access. 8017 8018 This parameter controls the TAA mitigation. The 8019 options are: 8020 8021 full - Enable TAA mitigation on vulnerable CPUs 8022 if TSX is enabled. 8023 8024 full,nosmt - Enable TAA mitigation and disable SMT on 8025 vulnerable CPUs. If TSX is disabled, SMT 8026 is not disabled because CPU is not 8027 vulnerable to cross-thread TAA attacks. 8028 off - Unconditionally disable TAA mitigation 8029 8030 On MDS-affected machines, tsx_async_abort=off can be 8031 prevented by an active MDS mitigation as both vulnerabilities 8032 are mitigated with the same mechanism so in order to disable 8033 this mitigation, you need to specify mds=off too. 8034 8035 Not specifying this option is equivalent to 8036 tsx_async_abort=full. On CPUs which are MDS affected 8037 and deploy MDS mitigation, TAA mitigation is not 8038 required and doesn't provide any additional 8039 mitigation. 8040 8041 For details see: 8042 Documentation/admin-guide/hw-vuln/tsx_async_abort.rst 8043 8044 turbografx.map[2|3]= [HW,JOY] 8045 TurboGraFX parallel port interface 8046 Format: 8047 <port#>,<js1>,<js2>,<js3>,<js4>,<js5>,<js6>,<js7> 8048 See also Documentation/input/devices/joystick-parport.rst 8049 8050 udbg-immortal [PPC] When debugging early kernel crashes that 8051 happen after console_init() and before a proper 8052 console driver takes over, this boot options might 8053 help "seeing" what's going on. 8054 8055 uhash_entries= [KNL,NET] 8056 Set number of hash buckets for UDP/UDP-Lite connections 8057 8058 uhci-hcd.ignore_oc= 8059 [USB] Ignore overcurrent events (default N). 8060 Some badly-designed motherboards generate lots of 8061 bogus events, for ports that aren't wired to 8062 anything. Set this parameter to avoid log spamming. 8063 Note that genuine overcurrent events won't be 8064 reported either. 8065 8066 unaligned_scalar_speed= 8067 [RISCV] 8068 Format: {slow | fast | unsupported} 8069 Allow skipping scalar unaligned access speed tests. This 8070 is useful for testing alternative code paths and to skip 8071 the tests in environments where they run too slowly. All 8072 CPUs must have the same scalar unaligned access speed. 8073 8074 unaligned_vector_speed= 8075 [RISCV] 8076 Format: {slow | fast | unsupported} 8077 Allow skipping vector unaligned access speed tests. This 8078 is useful for testing alternative code paths and to skip 8079 the tests in environments where they run too slowly. All 8080 CPUs must have the same vector unaligned access speed. 8081 8082 unknown_nmi_panic 8083 [X86] Cause panic on unknown NMI. 8084 8085 unwind_debug [X86-64,EARLY] 8086 Enable unwinder debug output. This can be 8087 useful for debugging certain unwinder error 8088 conditions, including corrupt stacks and 8089 bad/missing unwinder metadata. 8090 8091 usbcore.authorized_default= 8092 [USB] Default USB device authorization: 8093 (default -1 = authorized (same as 1), 8094 0 = not authorized, 1 = authorized, 2 = authorized 8095 if device connected to internal port) 8096 8097 usbcore.autosuspend= 8098 [USB] The autosuspend time delay (in seconds) used 8099 for newly-detected USB devices (default 2). This 8100 is the time required before an idle device will be 8101 autosuspended. Devices for which the delay is set 8102 to a negative value won't be autosuspended at all. 8103 8104 usbcore.usbfs_snoop= 8105 [USB] Set to log all usbfs traffic (default 0 = off). 8106 8107 usbcore.usbfs_snoop_max= 8108 [USB] Maximum number of bytes to snoop in each URB 8109 (default = 65536). 8110 8111 usbcore.blinkenlights= 8112 [USB] Set to cycle leds on hubs (default 0 = off). 8113 8114 usbcore.old_scheme_first= 8115 [USB] Start with the old device initialization 8116 scheme (default 0 = off). 8117 8118 usbcore.usbfs_memory_mb= 8119 [USB] Memory limit (in MB) for buffers allocated by 8120 usbfs (default = 16, 0 = max = 2047). 8121 8122 usbcore.use_both_schemes= 8123 [USB] Try the other device initialization scheme 8124 if the first one fails (default 1 = enabled). 8125 8126 usbcore.initial_descriptor_timeout= 8127 [USB] Specifies timeout for the initial 64-byte 8128 USB_REQ_GET_DESCRIPTOR request in milliseconds 8129 (default 5000 = 5.0 seconds). 8130 8131 usbcore.nousb [USB] Disable the USB subsystem 8132 8133 usbcore.quirks= 8134 [USB] A list of quirk entries to augment the built-in 8135 usb core quirk list. List entries are separated by 8136 commas. Each entry has the form 8137 VendorID:ProductID:Flags. The IDs are 4-digit hex 8138 numbers and Flags is a set of letters. Each letter 8139 will change the built-in quirk; setting it if it is 8140 clear and clearing it if it is set. The letters have 8141 the following meanings: 8142 a = USB_QUIRK_STRING_FETCH_255 (string 8143 descriptors must not be fetched using 8144 a 255-byte read); 8145 b = USB_QUIRK_RESET_RESUME (device can't resume 8146 correctly so reset it instead); 8147 c = USB_QUIRK_NO_SET_INTF (device can't handle 8148 Set-Interface requests); 8149 d = USB_QUIRK_CONFIG_INTF_STRINGS (device can't 8150 handle its Configuration or Interface 8151 strings); 8152 e = USB_QUIRK_RESET (device can't be reset 8153 (e.g morph devices), don't use reset); 8154 f = USB_QUIRK_HONOR_BNUMINTERFACES (device has 8155 more interface descriptions than the 8156 bNumInterfaces count, and can't handle 8157 talking to these interfaces); 8158 g = USB_QUIRK_DELAY_INIT (device needs a pause 8159 during initialization, after we read 8160 the device descriptor); 8161 h = USB_QUIRK_LINEAR_UFRAME_INTR_BINTERVAL (For 8162 high speed and super speed interrupt 8163 endpoints, the USB 2.0 and USB 3.0 spec 8164 require the interval in microframes (1 8165 microframe = 125 microseconds) to be 8166 calculated as interval = 2 ^ 8167 (bInterval-1). 8168 Devices with this quirk report their 8169 bInterval as the result of this 8170 calculation instead of the exponent 8171 variable used in the calculation); 8172 i = USB_QUIRK_DEVICE_QUALIFIER (device can't 8173 handle device_qualifier descriptor 8174 requests); 8175 j = USB_QUIRK_IGNORE_REMOTE_WAKEUP (device 8176 generates spurious wakeup, ignore 8177 remote wakeup capability); 8178 k = USB_QUIRK_NO_LPM (device can't handle Link 8179 Power Management); 8180 l = USB_QUIRK_LINEAR_FRAME_INTR_BINTERVAL 8181 (Device reports its bInterval as linear 8182 frames instead of the USB 2.0 8183 calculation); 8184 m = USB_QUIRK_DISCONNECT_SUSPEND (Device needs 8185 to be disconnected before suspend to 8186 prevent spurious wakeup); 8187 n = USB_QUIRK_DELAY_CTRL_MSG (Device needs a 8188 pause after every control message); 8189 o = USB_QUIRK_HUB_SLOW_RESET (Hub needs extra 8190 delay after resetting its port); 8191 p = USB_QUIRK_SHORT_SET_ADDRESS_REQ_TIMEOUT 8192 (Reduce timeout of the SET_ADDRESS 8193 request from 5000 ms to 500 ms); 8194 q = USB_QUIRK_FORCE_ONE_CONFIG (Device 8195 claims zero configurations, 8196 forcing to 1); 8197 Example: quirks=0781:5580:bk,0a5c:5834:gij 8198 8199 usbhid.mousepoll= 8200 [USBHID] The interval which mice are to be polled at. 8201 8202 usbhid.jspoll= 8203 [USBHID] The interval which joysticks are to be polled at. 8204 8205 usbhid.kbpoll= 8206 [USBHID] The interval which keyboards are to be polled at. 8207 8208 usb-storage.delay_use= 8209 [UMS] The delay in seconds before a new device is 8210 scanned for Logical Units (default 1). 8211 Optionally the delay in milliseconds if the value has 8212 suffix with "ms". 8213 Example: delay_use=2567ms 8214 8215 usb-storage.quirks= 8216 [UMS] A list of quirks entries to supplement or 8217 override the built-in unusual_devs list. List 8218 entries are separated by commas. Each entry has 8219 the form VID:PID:Flags where VID and PID are Vendor 8220 and Product ID values (4-digit hex numbers) and 8221 Flags is a set of characters, each corresponding 8222 to a common usb-storage quirk flag as follows: 8223 a = SANE_SENSE (collect more than 18 bytes 8224 of sense data, not on uas); 8225 b = BAD_SENSE (don't collect more than 18 8226 bytes of sense data, not on uas); 8227 c = FIX_CAPACITY (decrease the reported 8228 device capacity by one sector); 8229 d = NO_READ_DISC_INFO (don't use 8230 READ_DISC_INFO command, not on uas); 8231 e = NO_READ_CAPACITY_16 (don't use 8232 READ_CAPACITY_16 command); 8233 f = NO_REPORT_OPCODES (don't use report opcodes 8234 command, uas only); 8235 g = MAX_SECTORS_240 (don't transfer more than 8236 240 sectors at a time, uas only); 8237 h = CAPACITY_HEURISTICS (decrease the 8238 reported device capacity by one 8239 sector if the number is odd); 8240 i = IGNORE_DEVICE (don't bind to this 8241 device); 8242 j = NO_REPORT_LUNS (don't use report luns 8243 command, uas only); 8244 k = NO_SAME (do not use WRITE_SAME, uas only) 8245 l = NOT_LOCKABLE (don't try to lock and 8246 unlock ejectable media, not on uas); 8247 m = MAX_SECTORS_64 (don't transfer more 8248 than 64 sectors = 32 KB at a time, 8249 not on uas); 8250 n = INITIAL_READ10 (force a retry of the 8251 initial READ(10) command, not on uas); 8252 o = CAPACITY_OK (accept the capacity 8253 reported by the device, not on uas); 8254 p = WRITE_CACHE (the device cache is ON 8255 by default, not on uas); 8256 r = IGNORE_RESIDUE (the device reports 8257 bogus residue values, not on uas); 8258 s = SINGLE_LUN (the device has only one 8259 Logical Unit); 8260 t = NO_ATA_1X (don't allow ATA(12) and ATA(16) 8261 commands, uas only); 8262 u = IGNORE_UAS (don't bind to the uas driver); 8263 w = NO_WP_DETECT (don't test whether the 8264 medium is write-protected). 8265 y = ALWAYS_SYNC (issue a SYNCHRONIZE_CACHE 8266 even if the device claims no cache, 8267 not on uas) 8268 Example: quirks=0419:aaf5:rl,0421:0433:rc 8269 8270 user_debug= [KNL,ARM] 8271 Format: <int> 8272 See arch/arm/Kconfig.debug help text. 8273 1 - undefined instruction events 8274 2 - system calls 8275 4 - invalid data aborts 8276 8 - SIGSEGV faults 8277 16 - SIGBUS faults 8278 Example: user_debug=31 8279 8280 vdso= [X86,SH,SPARC] 8281 On X86_32, this is an alias for vdso32=. Otherwise: 8282 8283 vdso=1: enable VDSO (the default) 8284 vdso=0: disable VDSO mapping 8285 8286 vdso32= [X86] Control the 32-bit vDSO 8287 vdso32=1: enable 32-bit VDSO 8288 vdso32=0 or vdso32=2: disable 32-bit VDSO 8289 8290 See the help text for CONFIG_COMPAT_VDSO for more 8291 details. If CONFIG_COMPAT_VDSO is set, the default is 8292 vdso32=0; otherwise, the default is vdso32=1. 8293 8294 For compatibility with older kernels, vdso32=2 is an 8295 alias for vdso32=0. 8296 8297 Try vdso32=0 if you encounter an error that says: 8298 dl_main: Assertion `(void *) ph->p_vaddr == _rtld_local._dl_sysinfo_dso' failed! 8299 8300 video= [FB,EARLY] Frame buffer configuration 8301 See Documentation/fb/modedb.rst. 8302 8303 video.brightness_switch_enabled= [ACPI] 8304 Format: [0|1] 8305 If set to 1, on receiving an ACPI notify event 8306 generated by hotkey, video driver will adjust brightness 8307 level and then send out the event to user space through 8308 the allocated input device. If set to 0, video driver 8309 will only send out the event without touching backlight 8310 brightness level. 8311 default: 1 8312 8313 virtio_mmio.device= 8314 [VMMIO] Memory mapped virtio (platform) device. 8315 8316 <size>@<baseaddr>:<irq>[:<id>] 8317 where: 8318 <size> := size (can use standard suffixes 8319 like K, M and G) 8320 <baseaddr> := physical base address 8321 <irq> := interrupt number (as passed to 8322 request_irq()) 8323 <id> := (optional) platform device id 8324 example: 8325 virtio_mmio.device=1K@0x100b0000:48:7 8326 8327 Can be used multiple times for multiple devices. 8328 8329 vga= [BOOT,X86-32] Select a particular video mode 8330 See Documentation/arch/x86/boot.rst and 8331 Documentation/admin-guide/svga.rst. 8332 Use vga=ask for menu. 8333 This is actually a boot loader parameter; the value is 8334 passed to the kernel using a special protocol. 8335 8336 vm_debug[=options] [KNL] Available with CONFIG_DEBUG_VM=y. 8337 May slow down system boot speed, especially when 8338 enabled on systems with a large amount of memory. 8339 All options are enabled by default, and this 8340 interface is meant to allow for selectively 8341 enabling or disabling specific virtual memory 8342 debugging features. 8343 8344 Available options are: 8345 P Enable page structure init time poisoning 8346 - Disable all of the above options 8347 8348 vmalloc=nn[KMG] [KNL,BOOT,EARLY] Forces the vmalloc area to have an 8349 exact size of <nn>. This can be used to increase 8350 the minimum size (128MB on x86, arm32 platforms). 8351 It can also be used to decrease the size and leave more room 8352 for directly mapped kernel RAM. Note that this parameter does 8353 not exist on many other platforms (including arm64, alpha, 8354 loongarch, arc, csky, hexagon, microblaze, mips, nios2, openrisc, 8355 parisc, m64k, powerpc, riscv, sh, um, xtensa, s390, sparc). 8356 8357 vmcp_cma=nn[MG] [KNL,S390,EARLY] 8358 Sets the memory size reserved for contiguous memory 8359 allocations for the vmcp device driver. 8360 8361 vmhalt= [KNL,S390] Perform z/VM CP command after system halt. 8362 Format: <command> 8363 8364 vmpanic= [KNL,S390] Perform z/VM CP command after kernel panic. 8365 Format: <command> 8366 8367 vmpoff= [KNL,S390] Perform z/VM CP command after power off. 8368 Format: <command> 8369 8370 vmscape= [X86] Controls mitigation for VMscape attacks. 8371 VMscape attacks can leak information from a userspace 8372 hypervisor to a guest via speculative side-channels. 8373 8374 off - disable the mitigation 8375 ibpb - use Indirect Branch Prediction Barrier 8376 (IBPB) mitigation (default) 8377 force - force vulnerability detection even on 8378 unaffected processors 8379 8380 vsyscall= [X86-64,EARLY] 8381 Controls the behavior of vsyscalls (i.e. calls to 8382 fixed addresses of 0xffffffffff600x00 from legacy 8383 code). Most statically-linked binaries and older 8384 versions of glibc use these calls. Because these 8385 functions are at fixed addresses, they make nice 8386 targets for exploits that can control RIP. 8387 8388 emulate Vsyscalls turn into traps and are emulated 8389 reasonably safely. The vsyscall page is 8390 readable. This disables the Linear 8391 Address Space Separation (LASS) security 8392 feature and makes the system less secure. 8393 8394 xonly [default] Vsyscalls turn into traps and are 8395 emulated reasonably safely. The vsyscall 8396 page is not readable. 8397 8398 none Vsyscalls don't work at all. This makes 8399 them quite hard to use for exploits but 8400 might break your system. 8401 8402 vt.color= [VT] Default text color. 8403 Format: 0xYX, X = foreground, Y = background. 8404 Default: 0x07 = light gray on black. 8405 8406 vt.cur_default= [VT] Default cursor shape. 8407 Format: 0xCCBBAA, where AA, BB, and CC are the same as 8408 the parameters of the <Esc>[?A;B;Cc escape sequence; 8409 see vga-softcursor.rst. Default: 2 = underline. 8410 8411 vt.default_blu= [VT] 8412 Format: <blue0>,<blue1>,<blue2>,...,<blue15> 8413 Change the default blue palette of the console. 8414 This is a 16-member array composed of values 8415 ranging from 0-255. 8416 8417 vt.default_grn= [VT] 8418 Format: <green0>,<green1>,<green2>,...,<green15> 8419 Change the default green palette of the console. 8420 This is a 16-member array composed of values 8421 ranging from 0-255. 8422 8423 vt.default_red= [VT] 8424 Format: <red0>,<red1>,<red2>,...,<red15> 8425 Change the default red palette of the console. 8426 This is a 16-member array composed of values 8427 ranging from 0-255. 8428 8429 vt.default_utf8= 8430 [VT] 8431 Format=<0|1> 8432 Set system-wide default UTF-8 mode for all tty's. 8433 Default is 1, i.e. UTF-8 mode is enabled for all 8434 newly opened terminals. 8435 8436 vt.global_cursor_default= 8437 [VT] 8438 Format=<-1|0|1> 8439 Set system-wide default for whether a cursor 8440 is shown on new VTs. Default is -1, 8441 i.e. cursors will be created by default unless 8442 overridden by individual drivers. 0 will hide 8443 cursors, 1 will display them. 8444 8445 vt.italic= [VT] Default color for italic text; 0-15. 8446 Default: 2 = green. 8447 8448 vt.underline= [VT] Default color for underlined text; 0-15. 8449 Default: 3 = cyan. 8450 8451 watchdog timers [HW,WDT] For information on watchdog timers, 8452 see Documentation/watchdog/watchdog-parameters.rst 8453 or other driver-specific files in the 8454 Documentation/watchdog/ directory. 8455 8456 watchdog_thresh= 8457 [KNL] 8458 Set the hard lockup detector stall duration 8459 threshold in seconds. The soft lockup detector 8460 threshold is set to twice the value. A value of 0 8461 disables both lockup detectors. Default is 10 8462 seconds. 8463 8464 workqueue.unbound_cpus= 8465 [KNL,SMP] Specify to constrain one or some CPUs 8466 to use in unbound workqueues. 8467 Format: <cpu-list> 8468 By default, all online CPUs are available for 8469 unbound workqueues. 8470 8471 workqueue.watchdog_thresh= 8472 If CONFIG_WQ_WATCHDOG is configured, workqueue can 8473 warn stall conditions and dump internal state to 8474 help debugging. 0 disables workqueue stall 8475 detection; otherwise, it's the stall threshold 8476 duration in seconds. The default value is 30 and 8477 it can be updated at runtime by writing to the 8478 corresponding sysfs file. 8479 8480 workqueue.panic_on_stall=<uint> 8481 Panic when workqueue stall is detected by 8482 CONFIG_WQ_WATCHDOG. It sets the number times of the 8483 stall to trigger panic. 8484 8485 The default is set by CONFIG_BOOTPARAM_WQ_STALL_PANIC, 8486 which is 0 (disabled) if not configured. 8487 8488 workqueue.panic_on_stall_time=<uint> 8489 Panic when a workqueue stall has been continuous for 8490 the specified number of seconds. Unlike panic_on_stall 8491 which counts accumulated stall events, this triggers 8492 based on the duration of a single continuous stall. 8493 8494 The default is 0, which disables the time-based panic. 8495 8496 workqueue.cpu_intensive_thresh_us= 8497 Per-cpu work items which run for longer than this 8498 threshold are automatically considered CPU intensive 8499 and excluded from concurrency management to prevent 8500 them from noticeably delaying other per-cpu work 8501 items. Default is 10000 (10ms). 8502 8503 If CONFIG_WQ_CPU_INTENSIVE_REPORT is set, the kernel 8504 will report the work functions which violate this 8505 threshold repeatedly. They are likely good 8506 candidates for using WQ_UNBOUND workqueues instead. 8507 8508 workqueue.cpu_intensive_warning_thresh=<uint> 8509 If CONFIG_WQ_CPU_INTENSIVE_REPORT is set, the kernel 8510 will report the work functions which violate the 8511 intensive_threshold_us repeatedly. In order to prevent 8512 spurious warnings, start printing only after a work 8513 function has violated this threshold number of times. 8514 8515 The default is 4 times. 0 disables the warning. 8516 8517 workqueue.power_efficient 8518 Per-cpu workqueues are generally preferred because 8519 they show better performance thanks to cache 8520 locality; unfortunately, per-cpu workqueues tend to 8521 be more power hungry than unbound workqueues. 8522 8523 Enabling this makes the per-cpu workqueues which 8524 were observed to contribute significantly to power 8525 consumption unbound, leading to measurably lower 8526 power usage at the cost of small performance 8527 overhead. 8528 8529 The default value of this parameter is determined by 8530 the config option CONFIG_WQ_POWER_EFFICIENT_DEFAULT. 8531 8532 workqueue.default_affinity_scope= 8533 Select the default affinity scope to use for unbound 8534 workqueues. Can be one of "cpu", "smt", "cache", 8535 "cache_shard", "numa" and "system". Default is 8536 "cache_shard". For more 8537 information, see the Affinity Scopes section in 8538 Documentation/core-api/workqueue.rst. 8539 8540 This can be changed after boot by writing to the 8541 matching /sys/module/workqueue/parameters file. All 8542 workqueues with the "default" affinity scope will be 8543 updated accordingly. 8544 8545 workqueue.debug_force_rr_cpu 8546 Workqueue used to implicitly guarantee that work 8547 items queued without explicit CPU specified are put 8548 on the local CPU. This guarantee is no longer true 8549 and while local CPU is still preferred work items 8550 may be put on foreign CPUs. This debug option 8551 forces round-robin CPU selection to flush out 8552 usages which depend on the now broken guarantee. 8553 When enabled, memory and cache locality will be 8554 impacted. 8555 8556 writecombine= [LOONGARCH,EARLY] Control the MAT (Memory Access 8557 Type) of ioremap_wc(). 8558 8559 on - Enable writecombine, use WUC for ioremap_wc() 8560 off - Disable writecombine, use SUC for ioremap_wc() 8561 8562 x2apic_phys [X86-64,APIC,EARLY] Use x2apic physical mode instead of 8563 default x2apic cluster mode on platforms 8564 supporting x2apic. 8565 8566 xen_512gb_limit [KNL,X86-64,XEN] 8567 Restricts the kernel running paravirtualized under Xen 8568 to use only up to 512 GB of RAM. The reason to do so is 8569 crash analysis tools and Xen tools for doing domain 8570 save/restore/migration must be enabled to handle larger 8571 domains. 8572 8573 xen_console_io [XEN,EARLY] 8574 Boolean option to enable/disable the usage of the Xen 8575 console_io hypercalls to read and write to the console. 8576 Mostly useful for debugging and development. 8577 8578 xen_emul_unplug= [HW,X86,XEN,EARLY] 8579 Unplug Xen emulated devices 8580 Format: [unplug0,][unplug1] 8581 ide-disks -- unplug primary master IDE devices 8582 aux-ide-disks -- unplug non-primary-master IDE devices 8583 nics -- unplug network devices 8584 all -- unplug all emulated devices (NICs and IDE disks) 8585 unnecessary -- unplugging emulated devices is 8586 unnecessary even if the host did not respond to 8587 the unplug protocol 8588 never -- do not unplug even if version check succeeds 8589 8590 xen_legacy_crash [X86,XEN,EARLY] 8591 Crash from Xen panic notifier, without executing late 8592 panic() code such as dumping handler. 8593 8594 xen_mc_debug [X86,XEN,EARLY] 8595 Enable multicall debugging when running as a Xen PV guest. 8596 Enabling this feature will reduce performance a little 8597 bit, so it should only be enabled for obtaining extended 8598 debug data in case of multicall errors. 8599 8600 xen_msr_safe= [X86,XEN,EARLY] 8601 Format: <bool> 8602 Select whether to always use non-faulting (safe) MSR 8603 access functions when running as Xen PV guest. The 8604 default value is controlled by CONFIG_XEN_PV_MSR_SAFE. 8605 8606 xen_nopv [X86] 8607 Disables the PV optimizations forcing the HVM guest to 8608 run as generic HVM guest with no PV drivers. 8609 This option is obsoleted by the "nopv" option, which 8610 has equivalent effect for XEN platform. 8611 8612 xen_no_vector_callback 8613 [KNL,X86,XEN,EARLY] Disable the vector callback for Xen 8614 event channel interrupts. 8615 8616 xen_scrub_pages= [XEN] 8617 Boolean option to control scrubbing pages before giving them back 8618 to Xen, for use by other domains. Can be also changed at runtime 8619 with /sys/devices/system/xen_memory/xen_memory0/scrub_pages. 8620 Default value controlled with CONFIG_XEN_SCRUB_PAGES_DEFAULT. 8621 8622 xen_timer_slop= [X86-64,XEN,EARLY] 8623 Set the timer slop (in nanoseconds) for the virtual Xen 8624 timers (default is 100000). This adjusts the minimum 8625 delta of virtualized Xen timers, where lower values 8626 improve timer resolution at the expense of processing 8627 more timer interrupts. 8628 8629 xen.balloon_boot_timeout= [XEN] 8630 The time (in seconds) to wait before giving up to boot 8631 in case initial ballooning fails to free enough memory. 8632 Applies only when running as HVM or PVH guest and 8633 started with less memory configured than allowed at 8634 max. Default is 180. 8635 8636 xen.event_eoi_delay= [XEN] 8637 How long to delay EOI handling in case of event 8638 storms (jiffies). Default is 10. 8639 8640 xen.event_loop_timeout= [XEN] 8641 After which time (jiffies) the event handling loop 8642 should start to delay EOI handling. Default is 2. 8643 8644 xen.fifo_events= [XEN] 8645 Boolean parameter to disable using fifo event handling 8646 even if available. Normally fifo event handling is 8647 preferred over the 2-level event handling, as it is 8648 fairer and the number of possible event channels is 8649 much higher. Default is on (use fifo events). 8650 8651 xirc2ps_cs= [NET,PCMCIA] 8652 Format: 8653 <irq>,<irq_mask>,<io>,<full_duplex>,<do_sound>,<lockup_hack>[,<irq2>[,<irq3>[,<irq4>]]] 8654 8655 xive= [PPC] 8656 By default on POWER9 and above, the kernel will 8657 natively use the XIVE interrupt controller. This option 8658 allows the fallback firmware mode to be used: 8659 8660 off Fallback to firmware control of XIVE interrupt 8661 controller on both pseries and powernv 8662 platforms. Only useful on POWER9 and above. 8663 8664 xive.store-eoi=off [PPC] 8665 By default on POWER10 and above, the kernel will use 8666 stores for EOI handling when the XIVE interrupt mode 8667 is active. This option allows the XIVE driver to use 8668 loads instead, as on POWER9. 8669 8670 xhci-hcd.quirks [USB,KNL] 8671 A hex value specifying bitmask with supplemental xhci 8672 host controller quirks. Meaning of each bit can be 8673 consulted in header drivers/usb/host/xhci.h. 8674 8675 xmon [PPC,EARLY] 8676 Format: { early | on | rw | ro | off } 8677 Controls if xmon debugger is enabled. Default is off. 8678 Passing only "xmon" is equivalent to "xmon=early". 8679 early Call xmon as early as possible on boot; xmon 8680 debugger is called from setup_arch(). 8681 on xmon debugger hooks will be installed so xmon 8682 is only called on a kernel crash. Default mode, 8683 i.e. either "ro" or "rw" mode, is controlled 8684 with CONFIG_XMON_DEFAULT_RO_MODE. 8685 rw xmon debugger hooks will be installed so xmon 8686 is called only on a kernel crash, mode is write, 8687 meaning SPR registers, memory and, other data 8688 can be written using xmon commands. 8689 ro same as "rw" option above but SPR registers, 8690 memory, and other data can't be written using 8691 xmon commands. 8692 off xmon is disabled. 8693