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 CLK Common clock infrastructure is enabled. 10 CMA Contiguous Memory Area support is enabled. 11 DRM Direct Rendering Management support is enabled. 12 DYNAMIC_DEBUG Build in debug messages and enable them at runtime 13 EARLY Parameter processed too early to be embedded in initrd. 14 EDD BIOS Enhanced Disk Drive Services (EDD) is enabled 15 EFI EFI Partitioning (GPT) is enabled 16 EVM Extended Verification Module 17 FB The frame buffer device is enabled. 18 FTRACE Function tracing enabled. 19 GCOV GCOV profiling is enabled. 20 HIBERNATION HIBERNATION is enabled. 21 HW Appropriate hardware is enabled. 22 HYPER_V HYPERV support is enabled. 23 IMA Integrity measurement architecture is enabled. 24 IP_PNP IP DHCP, BOOTP, or RARP is enabled. 25 IPV6 IPv6 support is enabled. 26 ISAPNP ISA PnP code is enabled. 27 ISDN Appropriate ISDN support is enabled. 28 ISOL CPU Isolation is enabled. 29 JOY Appropriate joystick support is enabled. 30 KGDB Kernel debugger support is enabled. 31 KVM Kernel Virtual Machine support is enabled. 32 LIBATA Libata driver is enabled 33 LOONGARCH LoongArch architecture is enabled. 34 LOOP Loopback device support is enabled. 35 LP Printer support is enabled. 36 M68k M68k architecture is enabled. 37 These options have more detailed description inside of 38 Documentation/arch/m68k/kernel-options.rst. 39 MDA MDA console support is enabled. 40 MIPS MIPS architecture is enabled. 41 MOUSE Appropriate mouse support is enabled. 42 MSI Message Signaled Interrupts (PCI). 43 MTD MTD (Memory Technology Device) support is enabled. 44 NET Appropriate network support is enabled. 45 NFS Appropriate NFS support is enabled. 46 NUMA NUMA support is enabled. 47 OF Devicetree is enabled. 48 PARISC The PA-RISC architecture is enabled. 49 PCI PCI bus support is enabled. 50 PCIE PCI Express support is enabled. 51 PCMCIA The PCMCIA subsystem is enabled. 52 PNP Plug & Play support is enabled. 53 PPC PowerPC architecture is enabled. 54 PPT Parallel port support is enabled. 55 PS2 Appropriate PS/2 support is enabled. 56 PV_OPS A paravirtualized kernel is enabled. 57 RAM RAM disk support is enabled. 58 RDT Intel Resource Director Technology. 59 RISCV RISCV architecture is enabled. 60 S390 S390 architecture is enabled. 61 SCSI Appropriate SCSI support is enabled. 62 A lot of drivers have their options described inside 63 the Documentation/scsi/ sub-directory. 64 SDW SoundWire support is enabled. 65 SECURITY Different security models are enabled. 66 SELINUX SELinux support is enabled. 67 SERIAL Serial support is enabled. 68 SH SuperH architecture is enabled. 69 SMP The kernel is an SMP kernel. 70 SPARC Sparc architecture is enabled. 71 SUSPEND System suspend states are enabled. 72 SWSUSP Software suspend (hibernation) is enabled. 73 TPM TPM drivers are enabled. 74 UMS USB Mass Storage support is enabled. 75 USB USB support is enabled. 76 NVME NVMe support is enabled 77 USBHID USB Human Interface Device support is enabled. 78 V4L Video For Linux support is enabled. 79 VGA The VGA console has been enabled. 80 VMMIO Driver for memory mapped virtio devices is enabled. 81 VT Virtual terminal support is enabled. 82 WDT Watchdog support is enabled. 83 X86-32 X86-32, aka i386 architecture is enabled. 84 X86-64 X86-64 architecture is enabled. 85 X86 Either 32-bit or 64-bit x86 (same as X86-32+X86-64) 86 X86_UV SGI UV support is enabled. 87 XEN Xen support is enabled 88 XTENSA xtensa architecture is enabled. 89 90In addition, the following text indicates that the option 91 92 BOOT Is a boot loader parameter. 93 BUGS= Relates to possible processor bugs on the said processor. 94 KNL Is a kernel start-up parameter. 95 96 97Kernel parameters 98 99 accept_memory= [MM] 100 Format: { eager | lazy } 101 default: lazy 102 By default, unaccepted memory is accepted lazily to 103 avoid prolonged boot times. The lazy option will add 104 some runtime overhead until all memory is eventually 105 accepted. In most cases the overhead is negligible. 106 For some workloads or for debugging purposes 107 accept_memory=eager can be used to accept all memory 108 at once during boot. 109 110 acpi= [HW,ACPI,X86,ARM64,RISCV64,EARLY] 111 Advanced Configuration and Power Interface 112 Format: { force | on | off | strict | noirq | rsdt | 113 copy_dsdt | nospcr } 114 force -- enable ACPI if default was off 115 on -- enable ACPI but allow fallback to DT [arm64,riscv64] 116 off -- disable ACPI if default was on 117 noirq -- do not use ACPI for IRQ routing 118 strict -- Be less tolerant of platforms that are not 119 strictly ACPI specification compliant. 120 rsdt -- prefer RSDT over (default) XSDT 121 copy_dsdt -- copy DSDT to memory 122 nocmcff -- Disable firmware first mode for corrected 123 errors. This disables parsing the HEST CMC error 124 source to check if firmware has set the FF flag. This 125 may result in duplicate corrected error reports. 126 nospcr -- disable console in ACPI SPCR table as 127 default _serial_ console on ARM64 128 spcr -- enable console in ACPI SPCR table as 129 default _serial_ console on x86 130 For ARM64, ONLY "acpi=off", "acpi=on", "acpi=force" or 131 "acpi=nospcr" are available 132 For RISCV64, ONLY "acpi=off", "acpi=on" or "acpi=force" 133 are available 134 135 See also Documentation/power/runtime_pm.rst, pci=noacpi 136 137 acpi_apic_instance= [ACPI,IOAPIC,EARLY] 138 Format: <int> 139 2: use 2nd APIC table, if available 140 1,0: use 1st APIC table 141 default: 0 142 143 acpi_backlight= [HW,ACPI] 144 { vendor | video | native | none } 145 If set to vendor, prefer vendor-specific driver 146 (e.g. thinkpad_acpi, sony_acpi, etc.) instead 147 of the ACPI video.ko driver. 148 If set to video, use the ACPI video.ko driver. 149 If set to native, use the device's native backlight mode. 150 If set to none, disable the ACPI backlight interface. 151 152 acpi_force_32bit_fadt_addr [ACPI,EARLY] 153 force FADT to use 32 bit addresses rather than the 154 64 bit X_* addresses. Some firmware have broken 64 155 bit addresses for force ACPI ignore these and use 156 the older legacy 32 bit addresses. 157 158 acpica_no_return_repair [HW, ACPI] 159 Disable AML predefined validation mechanism 160 This mechanism can repair the evaluation result to make 161 the return objects more ACPI specification compliant. 162 This option is useful for developers to identify the 163 root cause of an AML interpreter issue when the issue 164 has something to do with the repair mechanism. 165 166 acpi.debug_layer= [HW,ACPI,ACPI_DEBUG] 167 acpi.debug_level= [HW,ACPI,ACPI_DEBUG] 168 Format: <int> 169 CONFIG_ACPI_DEBUG must be enabled to produce any ACPI 170 debug output. Bits in debug_layer correspond to a 171 _COMPONENT in an ACPI source file, e.g., 172 #define _COMPONENT ACPI_EVENTS 173 Bits in debug_level correspond to a level in 174 ACPI_DEBUG_PRINT statements, e.g., 175 ACPI_DEBUG_PRINT((ACPI_DB_INFO, ... 176 The debug_level mask defaults to "info". See 177 Documentation/firmware-guide/acpi/debug.rst for more information about 178 debug layers and levels. 179 180 Enable processor driver info messages: 181 acpi.debug_layer=0x20000000 182 Enable AML "Debug" output, i.e., stores to the Debug 183 object while interpreting AML: 184 acpi.debug_layer=0xffffffff acpi.debug_level=0x2 185 Enable all messages related to ACPI hardware: 186 acpi.debug_layer=0x2 acpi.debug_level=0xffffffff 187 188 Some values produce so much output that the system is 189 unusable. The "log_buf_len" parameter may be useful 190 if you need to capture more output. 191 192 acpi.poweroff_on_fatal= [ACPI] 193 {0 | 1} 194 Causes the system to poweroff when the ACPI bytecode signals 195 a fatal error. The default value of this setting is 1. 196 Overriding this value should only be done for diagnosing 197 ACPI firmware problems, as the system might behave erratically 198 after having encountered a fatal ACPI error. 199 200 acpi_enforce_resources= [ACPI] 201 { strict | lax | no } 202 Check for resource conflicts between native drivers 203 and ACPI OperationRegions (SystemIO and SystemMemory 204 only). IO ports and memory declared in ACPI might be 205 used by the ACPI subsystem in arbitrary AML code and 206 can interfere with legacy drivers. 207 strict (default): access to resources claimed by ACPI 208 is denied; legacy drivers trying to access reserved 209 resources will fail to bind to device using them. 210 lax: access to resources claimed by ACPI is allowed; 211 legacy drivers trying to access reserved resources 212 will bind successfully but a warning message is logged. 213 no: ACPI OperationRegions are not marked as reserved, 214 no further checks are performed. 215 216 acpi_force_table_verification [HW,ACPI,EARLY] 217 Enable table checksum verification during early stage. 218 By default, this is disabled due to x86 early mapping 219 size limitation. 220 221 acpi_irq_balance [HW,ACPI] 222 ACPI will balance active IRQs 223 default in APIC mode 224 225 acpi_irq_nobalance [HW,ACPI] 226 ACPI will not move active IRQs (default) 227 default in PIC mode 228 229 acpi_irq_isa= [HW,ACPI] If irq_balance, mark listed IRQs used by ISA 230 Format: <irq>,<irq>... 231 232 acpi_irq_pci= [HW,ACPI] If irq_balance, clear listed IRQs for 233 use by PCI 234 Format: <irq>,<irq>... 235 236 acpi_mask_gpe= [HW,ACPI] 237 Due to the existence of _Lxx/_Exx, some GPEs triggered 238 by unsupported hardware/firmware features can result in 239 GPE floodings that cannot be automatically disabled by 240 the GPE dispatcher. 241 This facility can be used to prevent such uncontrolled 242 GPE floodings. 243 Format: <byte> or <bitmap-list> 244 245 acpi_no_auto_serialize [HW,ACPI] 246 Disable auto-serialization of AML methods 247 AML control methods that contain the opcodes to create 248 named objects will be marked as "Serialized" by the 249 auto-serialization feature. 250 This feature is enabled by default. 251 This option allows to turn off the feature. 252 253 acpi_no_memhotplug [ACPI] Disable memory hotplug. Useful for kdump 254 kernels. 255 256 acpi_no_static_ssdt [HW,ACPI,EARLY] 257 Disable installation of static SSDTs at early boot time 258 By default, SSDTs contained in the RSDT/XSDT will be 259 installed automatically and they will appear under 260 /sys/firmware/acpi/tables. 261 This option turns off this feature. 262 Note that specifying this option does not affect 263 dynamic table installation which will install SSDT 264 tables to /sys/firmware/acpi/tables/dynamic. 265 266 acpi_no_watchdog [HW,ACPI,WDT] 267 Ignore the ACPI-based watchdog interface (WDAT) and let 268 a native driver control the watchdog device instead. 269 270 acpi_rsdp= [ACPI,EFI,KEXEC,EARLY] 271 Pass the RSDP address to the kernel, mostly used 272 on machines running EFI runtime service to boot the 273 second kernel for kdump. 274 275 acpi_os_name= [HW,ACPI] Tell ACPI BIOS the name of the OS 276 Format: To spoof as Windows 98: ="Microsoft Windows" 277 278 acpi_rev_override [ACPI] Override the _REV object to return 5 (instead 279 of 2 which is mandated by ACPI 6) as the supported ACPI 280 specification revision (when using this switch, it may 281 be necessary to carry out a cold reboot _twice_ in a 282 row to make it take effect on the platform firmware). 283 284 acpi_osi= [HW,ACPI] Modify list of supported OS interface strings 285 acpi_osi="string1" # add string1 286 acpi_osi="!string2" # remove string2 287 acpi_osi=!* # remove all strings 288 acpi_osi=! # disable all built-in OS vendor 289 strings 290 acpi_osi=!! # enable all built-in OS vendor 291 strings 292 acpi_osi= # disable all strings 293 294 'acpi_osi=!' can be used in combination with single or 295 multiple 'acpi_osi="string1"' to support specific OS 296 vendor string(s). Note that such command can only 297 affect the default state of the OS vendor strings, thus 298 it cannot affect the default state of the feature group 299 strings and the current state of the OS vendor strings, 300 specifying it multiple times through kernel command line 301 is meaningless. This command is useful when one do not 302 care about the state of the feature group strings which 303 should be controlled by the OSPM. 304 Examples: 305 1. 'acpi_osi=! acpi_osi="Windows 2000"' is equivalent 306 to 'acpi_osi="Windows 2000" acpi_osi=!', they all 307 can make '_OSI("Windows 2000")' TRUE. 308 309 'acpi_osi=' cannot be used in combination with other 310 'acpi_osi=' command lines, the _OSI method will not 311 exist in the ACPI namespace. NOTE that such command can 312 only affect the _OSI support state, thus specifying it 313 multiple times through kernel command line is also 314 meaningless. 315 Examples: 316 1. 'acpi_osi=' can make 'CondRefOf(_OSI, Local1)' 317 FALSE. 318 319 'acpi_osi=!*' can be used in combination with single or 320 multiple 'acpi_osi="string1"' to support specific 321 string(s). Note that such command can affect the 322 current state of both the OS vendor strings and the 323 feature group strings, thus specifying it multiple times 324 through kernel command line is meaningful. But it may 325 still not able to affect the final state of a string if 326 there are quirks related to this string. This command 327 is useful when one want to control the state of the 328 feature group strings to debug BIOS issues related to 329 the OSPM features. 330 Examples: 331 1. 'acpi_osi="Module Device" acpi_osi=!*' can make 332 '_OSI("Module Device")' FALSE. 333 2. 'acpi_osi=!* acpi_osi="Module Device"' can make 334 '_OSI("Module Device")' TRUE. 335 3. 'acpi_osi=! acpi_osi=!* acpi_osi="Windows 2000"' is 336 equivalent to 337 'acpi_osi=!* acpi_osi=! acpi_osi="Windows 2000"' 338 and 339 'acpi_osi=!* acpi_osi="Windows 2000" acpi_osi=!', 340 they all will make '_OSI("Windows 2000")' TRUE. 341 342 acpi_pm_good [X86] 343 Override the pmtimer bug detection: force the kernel 344 to assume that this machine's pmtimer latches its value 345 and always returns good values. 346 347 acpi_sci= [HW,ACPI,EARLY] ACPI System Control Interrupt trigger mode 348 Format: { level | edge | high | low } 349 350 acpi_skip_timer_override [HW,ACPI,EARLY] 351 Recognize and ignore IRQ0/pin2 Interrupt Override. 352 For broken nForce2 BIOS resulting in XT-PIC timer. 353 354 acpi_sleep= [HW,ACPI] Sleep options 355 Format: { s3_bios, s3_mode, s3_beep, s4_hwsig, 356 s4_nohwsig, old_ordering, nonvs, 357 sci_force_enable, nobl } 358 See Documentation/power/video.rst for information on 359 s3_bios and s3_mode. 360 s3_beep is for debugging; it makes the PC's speaker beep 361 as soon as the kernel's real-mode entry point is called. 362 s4_hwsig causes the kernel to check the ACPI hardware 363 signature during resume from hibernation, and gracefully 364 refuse to resume if it has changed. This complies with 365 the ACPI specification but not with reality, since 366 Windows does not do this and many laptops do change it 367 on docking. So the default behaviour is to allow resume 368 and simply warn when the signature changes, unless the 369 s4_hwsig option is enabled. 370 s4_nohwsig prevents ACPI hardware signature from being 371 used (or even warned about) during resume. 372 old_ordering causes the ACPI 1.0 ordering of the _PTS 373 control method, with respect to putting devices into 374 low power states, to be enforced (the ACPI 2.0 ordering 375 of _PTS is used by default). 376 nonvs prevents the kernel from saving/restoring the 377 ACPI NVS memory during suspend/hibernation and resume. 378 sci_force_enable causes the kernel to set SCI_EN directly 379 on resume from S1/S3 (which is against the ACPI spec, 380 but some broken systems don't work without it). 381 nobl causes the internal blacklist of systems known to 382 behave incorrectly in some ways with respect to system 383 suspend and resume to be ignored (use wisely). 384 385 acpi_use_timer_override [HW,ACPI,EARLY] 386 Use timer override. For some broken Nvidia NF5 boards 387 that require a timer override, but don't have HPET 388 389 add_efi_memmap [EFI,X86,EARLY] Include EFI memory map in 390 kernel's map of available physical RAM. 391 392 agp= [AGP] 393 { off | try_unsupported } 394 off: disable AGP support 395 try_unsupported: try to drive unsupported chipsets 396 (may crash computer or cause data corruption) 397 398 ALSA [HW,ALSA] 399 See Documentation/sound/alsa-configuration.rst 400 401 alignment= [KNL,ARM] 402 Allow the default userspace alignment fault handler 403 behaviour to be specified. Bit 0 enables warnings, 404 bit 1 enables fixups, and bit 2 sends a segfault. 405 406 align_va_addr= [X86-64] 407 Align virtual addresses by clearing slice [14:12] when 408 allocating a VMA at process creation time. This option 409 gives you up to 3% performance improvement on AMD F15h 410 machines (where it is enabled by default) for a 411 CPU-intensive style benchmark, and it can vary highly in 412 a microbenchmark depending on workload and compiler. 413 414 32: only for 32-bit processes 415 64: only for 64-bit processes 416 on: enable for both 32- and 64-bit processes 417 off: disable for both 32- and 64-bit processes 418 419 alloc_snapshot [FTRACE] 420 Allocate the ftrace snapshot buffer on boot up when the 421 main buffer is allocated. This is handy if debugging 422 and you need to use tracing_snapshot() on boot up, and 423 do not want to use tracing_snapshot_alloc() as it needs 424 to be done where GFP_KERNEL allocations are allowed. 425 426 allow_mismatched_32bit_el0 [ARM64,EARLY] 427 Allow execve() of 32-bit applications and setting of the 428 PER_LINUX32 personality on systems where only a strict 429 subset of the CPUs support 32-bit EL0. When this 430 parameter is present, the set of CPUs supporting 32-bit 431 EL0 is indicated by /sys/devices/system/cpu/aarch32_el0 432 and hot-unplug operations may be restricted. 433 434 See Documentation/arch/arm64/asymmetric-32bit.rst for more 435 information. 436 437 amd_iommu= [HW,X86-64] 438 Pass parameters to the AMD IOMMU driver in the system. 439 Possible values are: 440 fullflush - Deprecated, equivalent to iommu.strict=1 441 off - do not initialize any AMD IOMMU found in 442 the system 443 force_isolation - Force device isolation for all 444 devices. The IOMMU driver is not 445 allowed anymore to lift isolation 446 requirements as needed. This option 447 does not override iommu=pt 448 force_enable - Force enable the IOMMU on platforms known 449 to be buggy with IOMMU enabled. Use this 450 option with care. 451 pgtbl_v1 - Use v1 page table for DMA-API (Default). 452 pgtbl_v2 - Use v2 page table for DMA-API. 453 irtcachedis - Disable Interrupt Remapping Table (IRT) caching. 454 nohugepages - Limit page-sizes used for v1 page-tables 455 to 4 KiB. 456 v2_pgsizes_only - Limit page-sizes used for v1 page-tables 457 to 4KiB/2Mib/1GiB. 458 459 460 amd_iommu_dump= [HW,X86-64] 461 Enable AMD IOMMU driver option to dump the ACPI table 462 for AMD IOMMU. With this option enabled, AMD IOMMU 463 driver will print ACPI tables for AMD IOMMU during 464 IOMMU initialization. 465 466 amd_iommu_intr= [HW,X86-64] 467 Specifies one of the following AMD IOMMU interrupt 468 remapping modes: 469 legacy - Use legacy interrupt remapping mode. 470 vapic - Use virtual APIC mode, which allows IOMMU 471 to inject interrupts directly into guest. 472 This mode requires kvm-amd.avic=1. 473 (Default when IOMMU HW support is present.) 474 475 amd_pstate= [X86,EARLY] 476 disable 477 Do not enable amd_pstate as the default 478 scaling driver for the supported processors 479 passive 480 Use amd_pstate with passive mode as a scaling driver. 481 In this mode autonomous selection is disabled. 482 Driver requests a desired performance level and platform 483 tries to match the same performance level if it is 484 satisfied by guaranteed performance level. 485 active 486 Use amd_pstate_epp driver instance as the scaling driver, 487 driver provides a hint to the hardware if software wants 488 to bias toward performance (0x0) or energy efficiency (0xff) 489 to the CPPC firmware. then CPPC power algorithm will 490 calculate the runtime workload and adjust the realtime cores 491 frequency. 492 guided 493 Activate guided autonomous mode. Driver requests minimum and 494 maximum performance level and the platform autonomously 495 selects a performance level in this range and appropriate 496 to the current workload. 497 498 amd_prefcore= 499 [X86] 500 disable 501 Disable amd-pstate preferred core. 502 503 amd_dynamic_epp= 504 [X86] 505 disable 506 Disable amd-pstate dynamic EPP. 507 enable 508 Enable amd-pstate dynamic EPP. 509 510 amijoy.map= [HW,JOY] Amiga joystick support 511 Map of devices attached to JOY0DAT and JOY1DAT 512 Format: <a>,<b> 513 See also Documentation/input/joydev/joystick.rst 514 515 analog.map= [HW,JOY] Analog joystick and gamepad support 516 Specifies type or capabilities of an analog joystick 517 connected to one of 16 gameports 518 Format: <type1>,<type2>,..<type16> 519 520 apc= [HW,SPARC] 521 Power management functions (SPARCstation-4/5 + deriv.) 522 Format: noidle 523 Disable APC CPU standby support. SPARCstation-Fox does 524 not play well with APC CPU idle - disable it if you have 525 APC and your system crashes randomly. 526 527 apic [APIC,X86-64] Use IO-APIC. Default. 528 529 apic= [APIC,X86,EARLY] Advanced Programmable Interrupt Controller 530 Change the output verbosity while booting 531 Format: { quiet (default) | verbose | debug } 532 Change the amount of debugging information output 533 when initialising the APIC and IO-APIC components. 534 535 apic_extnmi= [APIC,X86,EARLY] External NMI delivery setting 536 Format: { bsp (default) | all | none } 537 bsp: External NMI is delivered only to CPU 0 538 all: External NMIs are broadcast to all CPUs as a 539 backup of CPU 0 540 none: External NMI is masked for all CPUs. This is 541 useful so that a dump capture kernel won't be 542 shot down by NMI 543 544 apicpmtimer Do APIC timer calibration using the pmtimer. Implies 545 apicmaintimer. Useful when your PIT timer is totally 546 broken. 547 548 autoconf= [IPV6] 549 See Documentation/networking/ipv6.rst. 550 551 apm= [APM] Advanced Power Management 552 See header of arch/x86/kernel/apm_32.c. 553 554 apparmor= [APPARMOR] Disable or enable AppArmor at boot time 555 Format: { "0" | "1" } 556 See security/apparmor/Kconfig help text 557 0 -- disable. 558 1 -- enable. 559 Default value is set via kernel config option. 560 561 arm64.no32bit_el0 [ARM64] Unconditionally disable the execution of 562 32 bit applications. 563 564 arm64.nobti [ARM64] Unconditionally disable Branch Target 565 Identification support 566 567 arm64.nogcs [ARM64] Unconditionally disable Guarded Control Stack 568 support 569 570 arm64.nomops [ARM64] Unconditionally disable Memory Copy and Memory 571 Set instructions support 572 573 arm64.nompam [ARM64] Unconditionally disable Memory Partitioning And 574 Monitoring support 575 576 arm64.nomte [ARM64] Unconditionally disable Memory Tagging Extension 577 support 578 579 arm64.nopauth [ARM64] Unconditionally disable Pointer Authentication 580 support 581 582 arm64.nosme [ARM64] Unconditionally disable Scalable Matrix 583 Extension support 584 585 arm64.nosve [ARM64] Unconditionally disable Scalable Vector 586 Extension support 587 588 ataflop= [HW,M68k] 589 590 atarimouse= [HW,MOUSE] Atari Mouse 591 592 atkbd.extra= [HW] Enable extra LEDs and keys on IBM RapidAccess, 593 EzKey and similar keyboards 594 595 atkbd.reset= [HW] Reset keyboard during initialization 596 597 atkbd.set= [HW] Select keyboard code set 598 Format: <int> (2 = AT (default), 3 = PS/2) 599 600 atkbd.scroll= [HW] Enable scroll wheel on MS Office and similar 601 keyboards 602 603 atkbd.softraw= [HW] Choose between synthetic and real raw mode 604 Format: <bool> (0 = real, 1 = synthetic (default)) 605 606 atkbd.softrepeat= [HW] 607 Use software keyboard repeat 608 609 audit= [KNL] Enable the audit sub-system 610 Format: { "0" | "1" | "off" | "on" } 611 0 | off - kernel audit is disabled and can not be 612 enabled until the next reboot 613 unset - kernel audit is initialized but disabled and 614 will be fully enabled by the userspace auditd. 615 1 | on - kernel audit is initialized and partially 616 enabled, storing at most audit_backlog_limit 617 messages in RAM until it is fully enabled by the 618 userspace auditd. 619 Default: unset 620 621 audit_backlog_limit= [KNL] Set the audit queue size limit. 622 Format: <int> (must be >=0) 623 Default: 64 624 625 bau= [X86_UV] Enable the BAU on SGI UV. The default 626 behavior is to disable the BAU (i.e. bau=0). 627 Format: { "0" | "1" } 628 0 - Disable the BAU. 629 1 - Enable the BAU. 630 unset - Disable the BAU. 631 632 bdev_allow_write_mounted= 633 Format: <bool> 634 Control the ability to open a mounted block device 635 for writing, i.e., allow / disallow writes that bypass 636 the FS. This was implemented as a means to prevent 637 fuzzers from crashing the kernel by overwriting the 638 metadata underneath a mounted FS without its awareness. 639 This also prevents destructive formatting of mounted 640 filesystems by naive storage tooling that don't use 641 O_EXCL. Default is Y and can be changed through the 642 Kconfig option CONFIG_BLK_DEV_WRITE_MOUNTED. 643 644 bert_disable [ACPI] 645 Disable BERT OS support on buggy BIOSes. 646 647 bgrt_disable [ACPI,X86,EARLY] 648 Disable BGRT to avoid flickering OEM logo. 649 650 blkdevparts= Manual partition parsing of block device(s) for 651 embedded devices based on command line input. 652 See Documentation/block/cmdline-partition.rst 653 654 boot_delay= [KNL,EARLY] 655 Milliseconds to delay each printk during boot. 656 Only works if CONFIG_BOOT_PRINTK_DELAY is enabled, 657 and you may also have to specify "lpj=". Boot_delay 658 values larger than 10 seconds (10000) are assumed 659 erroneous and ignored. 660 Format: integer 661 662 bootconfig [KNL,EARLY] 663 Extended command line options can be added to an initrd 664 and this will cause the kernel to look for it. 665 666 See Documentation/admin-guide/bootconfig.rst 667 668 bttv.card= [HW,V4L] bttv (bt848 + bt878 based grabber cards) 669 bttv.radio= Most important insmod options are available as 670 kernel args too. 671 bttv.pll= See Documentation/admin-guide/media/bttv.rst 672 bttv.tuner= 673 674 bulk_remove=off [PPC] This parameter disables the use of the pSeries 675 firmware feature for flushing multiple hpte entries 676 at a time. 677 678 c101= [NET] Moxa C101 synchronous serial card 679 680 cachesize= [BUGS=X86-32] Override level 2 CPU cache size detection. 681 Sometimes CPU hardware bugs make them report the cache 682 size incorrectly. The kernel will attempt work arounds 683 to fix known problems, but for some CPUs it is not 684 possible to determine what the correct size should be. 685 This option provides an override for these situations. 686 687 carrier_timeout= 688 [NET] Specifies amount of time (in seconds) that 689 the kernel should wait for a network carrier. By default 690 it waits 120 seconds. 691 692 ca_keys= [KEYS] This parameter identifies a specific key(s) on 693 the system trusted keyring to be used for certificate 694 trust validation. 695 format: { id:<keyid> | builtin } 696 697 cca= [MIPS,EARLY] Override the kernel pages' cache coherency 698 algorithm. Accepted values range from 0 to 7 699 inclusive. See arch/mips/include/asm/pgtable-bits.h 700 for platform specific values (SB1, Loongson3 and 701 others). 702 703 ccw_timeout_log [S390] 704 See Documentation/arch/s390/common_io.rst for details. 705 706 cfi= [X86-64] Set Control Flow Integrity checking features 707 when CONFIG_FINEIBT is enabled. 708 Format: feature[,feature...] 709 Default: auto 710 711 auto: Use FineIBT if IBT available, otherwise kCFI. 712 Under FineIBT, enable "paranoid" mode when 713 FRED is not available. 714 off: Turn off CFI checking. 715 kcfi: Use kCFI (disable FineIBT). 716 fineibt: Use FineIBT (even if IBT not available). 717 norand: Do not re-randomize CFI hashes. 718 paranoid: Add caller hash checking under FineIBT. 719 bhi: Enable register poisoning to stop speculation 720 across FineIBT. (Disabled by default.) 721 warn: Do not enforce CFI checking: warn only. 722 debug: Report CFI initialization details. 723 724 cgroup_disable= [KNL] Disable a particular controller or optional feature 725 Format: {name of the controller(s) or feature(s) to disable} 726 The effects of cgroup_disable=foo are: 727 - foo isn't auto-mounted if you mount all cgroups in 728 a single hierarchy 729 - foo isn't visible as an individually mountable 730 subsystem 731 - if foo is an optional feature then the feature is 732 disabled and corresponding cgroup files are not 733 created 734 {Currently only "memory" controller deal with this and 735 cut the overhead, others just disable the usage. So 736 only cgroup_disable=memory is actually worthy} 737 Specifying "pressure" disables per-cgroup pressure 738 stall information accounting feature 739 740 cgroup_no_v1= [KNL] Disable cgroup controllers and named hierarchies in v1 741 Format: { { controller | "all" | "named" } 742 [,{ controller | "all" | "named" }...] } 743 Like cgroup_disable, but only applies to cgroup v1; 744 the blacklisted controllers remain available in cgroup2. 745 "all" blacklists all controllers and "named" disables 746 named mounts. Specifying both "all" and "named" disables 747 all v1 hierarchies. 748 749 cgroup_v1_proc= [KNL] Show also missing controllers in /proc/cgroups 750 Format: { "true" | "false" } 751 /proc/cgroups lists only v1 controllers by default. 752 This compatibility option enables listing also v2 753 controllers (whose v1 code is not compiled!), so that 754 semi-legacy software can check this file to decide 755 about usage of v2 (sic) controllers. 756 757 cgroup_favordynmods= [KNL] Enable or Disable favordynmods. 758 Format: { "true" | "false" } 759 Defaults to the value of CONFIG_CGROUP_FAVOR_DYNMODS. 760 761 cgroup.memory= [KNL] Pass options to the cgroup memory controller. 762 Format: <string> 763 nosocket -- Disable socket memory accounting. 764 nokmem -- Disable kernel memory accounting. 765 nobpf -- Disable BPF memory accounting. 766 767 check_pages= [MM,EARLY] Enable sanity checking of pages after 768 allocations / before freeing. This adds checks to catch 769 double-frees, use-after-frees, and other sources of 770 page corruption by inspecting page internals (flags, 771 mapcount/refcount, memcg_data, etc.). 772 Format: { "0" | "1" } 773 Default: 0 (1 if CONFIG_DEBUG_VM is set) 774 775 checkreqprot= [SELINUX] Set initial checkreqprot flag value. 776 Format: { "0" | "1" } 777 See security/selinux/Kconfig help text. 778 0 -- check protection applied by kernel (includes 779 any implied execute protection). 780 1 -- check protection requested by application. 781 Default value is set via a kernel config option. 782 Value can be changed at runtime via 783 /sys/fs/selinux/checkreqprot. 784 Setting checkreqprot to 1 is deprecated. 785 786 cio_ignore= [S390] 787 See Documentation/arch/s390/common_io.rst for details. 788 789 clk_ignore_unused 790 [CLK] 791 Prevents the clock framework from automatically gating 792 clocks that have not been explicitly enabled by a Linux 793 device driver but are enabled in hardware at reset or 794 by the bootloader/firmware. Note that this does not 795 force such clocks to be always-on nor does it reserve 796 those clocks in any way. This parameter is useful for 797 debug and development, but should not be needed on a 798 platform with proper driver support. For more 799 information, see Documentation/driver-api/clk.rst. 800 801 clock= [BUGS=X86-32, HW] gettimeofday clocksource override. 802 [Deprecated] 803 Forces specified clocksource (if available) to be used 804 when calculating gettimeofday(). If specified 805 clocksource is not available, it defaults to PIT. 806 Format: { pit | tsc | cyclone | pmtmr } 807 808 clocksource= Override the default clocksource 809 Format: <string> 810 Override the default clocksource and use the clocksource 811 with the name specified. 812 Some clocksource names to choose from, depending on 813 the platform: 814 [all] jiffies (this is the base, fallback clocksource) 815 [ACPI] acpi_pm 816 [ARM] imx_timer1,OSTS,netx_timer,mpu_timer2, 817 pxa_timer,timer3,32k_counter,timer0_1 818 [X86-32] pit,hpet,tsc; 819 scx200_hrt on Geode; cyclone on IBM x440 820 [MIPS] MIPS 821 [PARISC] cr16 822 [S390] tod 823 [SH] SuperH 824 [SPARC64] tick 825 [X86-64] hpet,tsc 826 827 clocksource.arm_arch_timer.evtstrm= 828 [ARM,ARM64,EARLY] 829 Format: <bool> 830 Enable/disable the eventstream feature of the ARM 831 architected timer so that code using WFE-based polling 832 loops can be debugged more effectively on production 833 systems. 834 835 clocksource.verify_n_cpus= [KNL] 836 Limit the number of CPUs checked for clocksources 837 marked with CLOCK_SOURCE_VERIFY_PERCPU that 838 are marked unstable due to excessive skew. 839 A negative value says to check all CPUs, while 840 zero says not to check any. Values larger than 841 nr_cpu_ids are silently truncated to nr_cpu_ids. 842 The actual CPUs are chosen randomly, with 843 no replacement if the same CPU is chosen twice. 844 845 clocksource-wdtest.holdoff= [KNL] 846 Set the time in seconds that the clocksource 847 watchdog test waits before commencing its tests. 848 Defaults to zero when built as a module and to 849 10 seconds when built into the kernel. 850 851 cma=nn[MG]@[start[MG][-end[MG]]] 852 [KNL,CMA,EARLY] 853 Sets the size of kernel global memory area for 854 contiguous memory allocations and optionally the 855 placement constraint by the physical address range of 856 memory allocations. A value of 0 disables CMA 857 altogether. For more information, see 858 kernel/dma/contiguous.c 859 860 cma_pernuma=nn[MG] 861 [KNL,CMA,EARLY] 862 Sets the size of kernel per-numa memory area for 863 contiguous memory allocations. A value of 0 disables 864 per-numa CMA altogether. And If this option is not 865 specified, the default value is 0. 866 With per-numa CMA enabled, DMA users on node nid will 867 first try to allocate buffer from the pernuma area 868 which is located in node nid, if the allocation fails, 869 they will fallback to the global default memory area. 870 871 numa_cma=<node>:nn[MG][,<node>:nn[MG]] 872 [KNL,CMA,EARLY] 873 Sets the size of kernel numa memory area for 874 contiguous memory allocations. It will reserve CMA 875 area for the specified node. 876 877 With numa CMA enabled, DMA users on node nid will 878 first try to allocate buffer from the numa area 879 which is located in node nid, if the allocation fails, 880 they will fallback to the global default memory area. 881 882 cmo_free_hint= [PPC] Format: { yes | no } 883 Specify whether pages are marked as being inactive 884 when they are freed. This is used in CMO environments 885 to determine OS memory pressure for page stealing by 886 a hypervisor. 887 Default: yes 888 889 coherent_pool=nn[KMG] [ARM,KNL,EARLY] 890 Sets the size of memory pool for coherent, atomic dma 891 allocations, by default set to 256K. 892 893 condev= [HW,S390] console device 894 conmode= 895 896 con3215_drop= [S390,EARLY] 3215 console drop mode. 897 Format: y|n|Y|N|1|0 898 When set to true, drop data on the 3215 console when 899 the console buffer is full. In this case the 900 operator using a 3270 terminal emulator (for example 901 x3270) does not have to enter the clear key for the 902 console output to advance and the kernel to continue. 903 This leads to a much faster boot time when a 3270 904 terminal emulator is active. If no 3270 terminal 905 emulator is used, this parameter has no effect. 906 907 console= [KNL] Output console device and options. 908 909 tty<n> Use the virtual console device <n>. 910 911 ttyS<n>[,options] 912 ttyUSB0[,options] 913 Use the specified serial port. The options are of 914 the form "bbbbpnf", where "bbbb" is the baud rate, 915 "p" is parity ("n", "o", or "e"), "n" is number of 916 bits, and "f" is flow control ("r" for RTS or 917 omit it). Default is "9600n8". 918 919 See Documentation/admin-guide/serial-console.rst for more 920 information. See 921 Documentation/networking/netconsole.rst for an 922 alternative. 923 924 <DEVNAME>:<n>.<n>[,options] 925 Use the specified serial port on the serial core bus. 926 The addressing uses DEVNAME of the physical serial port 927 device, followed by the serial core controller instance, 928 and the serial port instance. The options are the same 929 as documented for the ttyS addressing above. 930 931 The mapping of the serial ports to the tty instances 932 can be viewed with: 933 934 $ ls -d /sys/bus/serial-base/devices/*:*.*/tty/* 935 /sys/bus/serial-base/devices/00:04:0.0/tty/ttyS0 936 937 In the above example, the console can be addressed with 938 console=00:04:0.0. Note that a console addressed this 939 way will only get added when the related device driver 940 is ready. The use of an earlycon parameter in addition to 941 the console may be desired for console output early on. 942 943 uart[8250],io,<addr>[,options] 944 uart[8250],mmio,<addr>[,options] 945 uart[8250],mmio16,<addr>[,options] 946 uart[8250],mmio32,<addr>[,options] 947 uart[8250],0x<addr>[,options] 948 Start an early, polled-mode console on the 8250/16550 949 UART at the specified I/O port or MMIO address, 950 switching to the matching ttyS device later. 951 MMIO inter-register address stride is either 8-bit 952 (mmio), 16-bit (mmio16), or 32-bit (mmio32). 953 If none of [io|mmio|mmio16|mmio32], <addr> is assumed 954 to be equivalent to 'mmio'. 'options' are specified in 955 the same format described for ttyS above; if unspecified, 956 the h/w is not re-initialized. 957 958 hvc<n> Use the hypervisor console device <n>. This is for 959 both Xen and PowerPC hypervisors. 960 961 { null | "" } 962 Use to disable console output, i.e., to have kernel 963 console messages discarded. 964 This must be the only console= parameter used on the 965 kernel command line. 966 967 If the device connected to the port is not a TTY but a braille 968 device, prepend "brl," before the device type, for instance 969 console=brl,ttyS0 970 For now, only VisioBraille is supported. 971 972 console_msg_format= 973 [KNL] Change console messages format 974 default 975 By default we print messages on consoles in 976 "[time stamp] text\n" format (time stamp may not be 977 printed, depending on CONFIG_PRINTK_TIME or 978 `printk_time' param). 979 syslog 980 Switch to syslog format: "<%u>[time stamp] text\n" 981 IOW, each message will have a facility and loglevel 982 prefix. The format is similar to one used by syslog() 983 syscall, or to executing "dmesg -S --raw" or to reading 984 from /proc/kmsg. 985 986 consoleblank= [KNL] The console blank (screen saver) timeout in 987 seconds. A value of 0 disables the blank timer. 988 Defaults to 0. 989 990 coredump_filter= 991 [KNL] Change the default value for 992 /proc/<pid>/coredump_filter. 993 See also Documentation/filesystems/proc.rst. 994 995 coresight_cpu_debug.enable 996 [ARM,ARM64] 997 Format: <bool> 998 Enable/disable the CPU sampling based debugging. 999 0: default value, disable debugging 1000 1: enable debugging at boot time 1001 1002 cpcihp_generic= [HW,PCI] Generic port I/O CompactPCI driver 1003 Format: 1004 <first_slot>,<last_slot>,<port>,<enum_bit>[,<debug>] 1005 1006 cpuidle.off=1 [CPU_IDLE] 1007 disable the cpuidle sub-system 1008 1009 cpuidle.governor= 1010 [CPU_IDLE] Name of the cpuidle governor to use. 1011 1012 cpufreq.off=1 [CPU_FREQ] 1013 disable the cpufreq sub-system 1014 1015 cpufreq.default_governor= 1016 [CPU_FREQ] Name of the default cpufreq governor or 1017 policy to use. This governor must be registered in the 1018 kernel before the cpufreq driver probes. 1019 1020 cpu_init_udelay=N 1021 [X86,EARLY] Delay for N microsec between assert and de-assert 1022 of APIC INIT to start processors. This delay occurs 1023 on every CPU online, such as boot, and resume from suspend. 1024 Default: 10000 1025 1026 cpuhp.parallel= 1027 [SMP] Enable/disable parallel bringup of secondary CPUs 1028 Format: <bool> 1029 Default is enabled if CONFIG_HOTPLUG_PARALLEL=y. Otherwise 1030 the parameter has no effect. 1031 1032 crash_kexec_post_notifiers 1033 Only jump to kdump kernel after running the panic 1034 notifiers and dumping kmsg. This option increases 1035 the risks of a kdump failure, since some panic 1036 notifiers can make the crashed kernel more unstable. 1037 In configurations where kdump may not be reliable, 1038 running the panic notifiers could allow collecting 1039 more data on dmesg, like stack traces from other CPUS 1040 or extra data dumped by panic_print. Note that some 1041 configurations enable this option unconditionally, 1042 like Hyper-V, PowerPC (fadump) and AMD SEV-SNP. 1043 1044 crashkernel=size[KMG][@offset[KMG]] 1045 [KNL,EARLY] Using kexec, Linux can switch to a 'crash kernel' 1046 upon panic. This parameter reserves the physical 1047 memory region [offset, offset + size] for that kernel 1048 image. If '@offset' is omitted, then a suitable offset 1049 is selected automatically. 1050 [KNL, X86-64, ARM64, RISCV, LoongArch] Select a region 1051 under 4G first, and fall back to reserve region above 1052 4G when '@offset' hasn't been specified. 1053 See Documentation/admin-guide/kdump/kdump.rst for further details. 1054 1055 crashkernel=range1:size1[,range2:size2,...][@offset] 1056 [KNL] Same as above, but depends on the memory 1057 in the running system. The syntax of range is 1058 start-[end] where start and end are both 1059 a memory unit (amount[KMG]). See also 1060 Documentation/admin-guide/kdump/kdump.rst for an example. 1061 1062 crashkernel=size[KMG],high 1063 [KNL, X86-64, ARM64, RISCV, LoongArch] range could be 1064 above 4G. 1065 Allow kernel to allocate physical memory region from top, 1066 so could be above 4G if system have more than 4G ram 1067 installed. Otherwise memory region will be allocated 1068 below 4G, if available. 1069 It will be ignored if crashkernel=X is specified. 1070 crashkernel=size[KMG],low 1071 [KNL, X86-64, ARM64, RISCV, LoongArch] range under 4G. 1072 When crashkernel=X,high is passed, kernel could allocate 1073 physical memory region above 4G, that cause second kernel 1074 crash on system that require some amount of low memory, 1075 e.g. swiotlb requires at least 64M+32K low memory, also 1076 enough extra low memory is needed to make sure DMA buffers 1077 for 32-bit devices won't run out. Kernel would try to allocate 1078 default size of memory below 4G automatically. The default 1079 size is platform dependent. 1080 --> x86: max(swiotlb_size_or_default() + 8MiB, 256MiB) 1081 --> arm64: 128MiB 1082 --> riscv: 128MiB 1083 --> loongarch: 128MiB 1084 This one lets the user specify own low range under 4G 1085 for second kernel instead. 1086 0: to disable low allocation. 1087 It will be ignored when crashkernel=X,high is not used 1088 or memory reserved is below 4G. 1089 crashkernel=size[KMG],cma 1090 [KNL, X86, ppc] Reserve additional crash kernel memory from 1091 CMA. This reservation is usable by the first system's 1092 userspace memory and kernel movable allocations (memory 1093 balloon, zswap). Pages allocated from this memory range 1094 will not be included in the vmcore so this should not 1095 be used if dumping of userspace memory is intended and 1096 it has to be expected that some movable kernel pages 1097 may be missing from the dump. 1098 1099 A standard crashkernel reservation, as described above, 1100 is still needed to hold the crash kernel and initrd. 1101 1102 This option increases the risk of a kdump failure: DMA 1103 transfers configured by the first kernel may end up 1104 corrupting the second kernel's memory. 1105 1106 This reservation method is intended for systems that 1107 can't afford to sacrifice enough memory for standard 1108 crashkernel reservation and where less reliable and 1109 possibly incomplete kdump is preferable to no kdump at 1110 all. 1111 1112 cryptomgr.notests 1113 [KNL] Disable crypto self-tests 1114 1115 cs89x0_dma= [HW,NET] 1116 Format: <dma> 1117 1118 cs89x0_media= [HW,NET] 1119 Format: { rj45 | aui | bnc } 1120 1121 csdlock_debug= [KNL] Enable or disable debug add-ons of cross-CPU 1122 function call handling. When switched on, 1123 additional debug data is printed to the console 1124 in case a hanging CPU is detected, and that 1125 CPU is pinged again in order to try to resolve 1126 the hang situation. The default value of this 1127 option depends on the CSD_LOCK_WAIT_DEBUG_DEFAULT 1128 Kconfig option. 1129 1130 dasd= [HW,NET] 1131 See header of drivers/s390/block/dasd_devmap.c. 1132 1133 db9.dev[2|3]= [HW,JOY] Multisystem joystick support via parallel port 1134 (one device per port) 1135 Format: <port#>,<type> 1136 See also Documentation/input/devices/joystick-parport.rst 1137 1138 debug [KNL,EARLY] Enable kernel debugging (events log level). 1139 1140 debug_boot_weak_hash 1141 [KNL,EARLY] Enable printing [hashed] pointers early in the 1142 boot sequence. If enabled, we use a weak hash instead 1143 of siphash to hash pointers. Use this option if you are 1144 seeing instances of '(___ptrval___)') and need to see a 1145 value (hashed pointer) instead. Cryptographically 1146 insecure, please do not use on production kernels. 1147 1148 debug_locks_verbose= 1149 [KNL] verbose locking self-tests 1150 Format: <int> 1151 Print debugging info while doing the locking API 1152 self-tests. 1153 Bitmask for the various LOCKTYPE_ tests. Defaults to 0 1154 (no extra messages), setting it to -1 (all bits set) 1155 will print _a_lot_ more information - normally only 1156 useful to lockdep developers. 1157 1158 debug_objects [KNL,EARLY] Enable object debugging 1159 1160 debug_guardpage_minorder= 1161 [KNL,EARLY] When CONFIG_DEBUG_PAGEALLOC is set, this 1162 parameter allows control of the order of pages that will 1163 be intentionally kept free (and hence protected) by the 1164 buddy allocator. Bigger value increase the probability 1165 of catching random memory corruption, but reduce the 1166 amount of memory for normal system use. The maximum 1167 possible value is MAX_PAGE_ORDER/2. Setting this 1168 parameter to 1 or 2 should be enough to identify most 1169 random memory corruption problems caused by bugs in 1170 kernel or driver code when a CPU writes to (or reads 1171 from) a random memory location. Note that there exists 1172 a class of memory corruptions problems caused by buggy 1173 H/W or F/W or by drivers badly programming DMA 1174 (basically when memory is written at bus level and the 1175 CPU MMU is bypassed) which are not detectable by 1176 CONFIG_DEBUG_PAGEALLOC, hence this option will not 1177 help tracking down these problems. 1178 1179 debug_pagealloc= 1180 [KNL,EARLY] When CONFIG_DEBUG_PAGEALLOC is set, this parameter 1181 enables the feature at boot time. By default, it is 1182 disabled and the system will work mostly the same as a 1183 kernel built without CONFIG_DEBUG_PAGEALLOC. 1184 Note: to get most of debug_pagealloc error reports, it's 1185 useful to also enable the page_owner functionality. 1186 on: enable the feature 1187 1188 debugfs= [KNL,EARLY] This parameter enables what is exposed to 1189 userspace and debugfs internal clients. 1190 Format: { on, off } 1191 on: All functions are enabled. 1192 off: Filesystem is not registered and clients 1193 get a -EPERM as result when trying to register files 1194 or directories within debugfs. 1195 This is equivalent of the runtime functionality if 1196 debugfs was not enabled in the kernel at all. 1197 Default value is set in build-time with a kernel configuration. 1198 1199 debugpat [X86] Enable PAT debugging 1200 1201 default_hugepagesz= 1202 [HW] The size of the default HugeTLB page. This is 1203 the size represented by the legacy /proc/ hugepages 1204 APIs. In addition, this is the default hugetlb size 1205 used for shmget(), mmap() and mounting hugetlbfs 1206 filesystems. If not specified, defaults to the 1207 architecture's default huge page size. Huge page 1208 sizes are architecture dependent. See also 1209 Documentation/admin-guide/mm/hugetlbpage.rst. 1210 Format: size[KMG] 1211 1212 deferred_probe_timeout= 1213 [KNL] Debugging option to set a timeout in seconds for 1214 deferred probe to give up waiting on dependencies to 1215 probe. Only specific dependencies (subsystems or 1216 drivers) that have opted in will be ignored. A timeout 1217 of 0 will timeout at the end of initcalls. If the time 1218 out hasn't expired, it'll be restarted by each 1219 successful driver registration. This option will also 1220 dump out devices still on the deferred probe list after 1221 retrying. 1222 1223 delayacct [KNL] Enable per-task delay accounting 1224 1225 dell_smm_hwmon.ignore_dmi= 1226 [HW] Continue probing hardware even if DMI data 1227 indicates that the driver is running on unsupported 1228 hardware. 1229 1230 dell_smm_hwmon.force= 1231 [HW] Activate driver even if SMM BIOS signature does 1232 not match list of supported models and enable otherwise 1233 blacklisted features. 1234 1235 dell_smm_hwmon.power_status= 1236 [HW] Report power status in /proc/i8k 1237 (disabled by default). 1238 1239 dell_smm_hwmon.restricted= 1240 [HW] Allow controlling fans only if SYS_ADMIN 1241 capability is set. 1242 1243 dell_smm_hwmon.fan_mult= 1244 [HW] Factor to multiply fan speed with. 1245 1246 dell_smm_hwmon.fan_max= 1247 [HW] Maximum configurable fan speed. 1248 1249 dfltcc= [HW,S390] 1250 Format: { on | off | def_only | inf_only | always } 1251 on: s390 zlib hardware support for compression on 1252 level 1 and decompression (default) 1253 off: No s390 zlib hardware support 1254 def_only: s390 zlib hardware support for deflate 1255 only (compression on level 1) 1256 inf_only: s390 zlib hardware support for inflate 1257 only (decompression) 1258 always: Same as 'on' but ignores the selected compression 1259 level always using hardware support (used for debugging) 1260 1261 dhash_entries= [KNL] 1262 Set number of hash buckets for dentry cache. 1263 1264 disable_1tb_segments [PPC,EARLY] 1265 Disables the use of 1TB hash page table segments. This 1266 causes the kernel to fall back to 256MB segments which 1267 can be useful when debugging issues that require an SLB 1268 miss to occur. 1269 1270 disable= [IPV6] 1271 See Documentation/networking/ipv6.rst. 1272 1273 disable_radix [PPC,EARLY] 1274 Disable RADIX MMU mode on POWER9 1275 1276 disable_tlbie [PPC] 1277 Disable TLBIE instruction. Currently does not work 1278 with KVM, with HASH MMU, or with coherent accelerators. 1279 1280 disable_ddw [PPC/PSERIES,EARLY] 1281 Disable Dynamic DMA Window support. Use this 1282 to workaround buggy firmware. 1283 1284 disable_ipv6= [IPV6] 1285 See Documentation/networking/ipv6.rst. 1286 1287 disable_mtrr_cleanup [X86,EARLY] 1288 The kernel tries to adjust MTRR layout from continuous 1289 to discrete, to make X server driver able to add WB 1290 entry later. This parameter disables that. 1291 1292 disable_mtrr_trim [X86, Intel and AMD only,EARLY] 1293 By default the kernel will trim any uncacheable 1294 memory out of your available memory pool based on 1295 MTRR settings. This parameter disables that behavior, 1296 possibly causing your machine to run very slowly. 1297 1298 disable_timer_pin_1 [X86,EARLY] 1299 Disable PIN 1 of APIC timer 1300 Can be useful to work around chipset bugs. 1301 1302 dis_ucode_ldr [X86] Disable the microcode loader. 1303 1304 dma_debug=off If the kernel is compiled with DMA_API_DEBUG support, 1305 this option disables the debugging code at boot. 1306 1307 dma_debug_entries=<number> 1308 This option allows to tune the number of preallocated 1309 entries for DMA-API debugging code. One entry is 1310 required per DMA-API allocation. Use this if the 1311 DMA-API debugging code disables itself because the 1312 architectural default is too low. 1313 1314 dma_debug_driver=<driver_name> 1315 With this option the DMA-API debugging driver 1316 filter feature can be enabled at boot time. Just 1317 pass the driver to filter for as the parameter. 1318 The filter can be disabled or changed to another 1319 driver later using sysfs. 1320 1321 reg_file_data_sampling= 1322 [X86] Controls mitigation for Register File Data 1323 Sampling (RFDS) vulnerability. RFDS is a CPU 1324 vulnerability which may allow userspace to infer 1325 kernel data values previously stored in floating point 1326 registers, vector registers, or integer registers. 1327 RFDS only affects Intel Atom processors. 1328 1329 on: Turns ON the mitigation. 1330 off: Turns OFF the mitigation. 1331 1332 This parameter overrides the compile time default set 1333 by CONFIG_MITIGATION_RFDS. Mitigation cannot be 1334 disabled when other VERW based mitigations (like MDS) 1335 are enabled. In order to disable RFDS mitigation all 1336 VERW based mitigations need to be disabled. 1337 1338 For details see: 1339 Documentation/admin-guide/hw-vuln/reg-file-data-sampling.rst 1340 1341 dm_verity.keyring_unsealed= 1342 [KNL] When set to 1, leave the dm-verity keyring 1343 unsealed after initialization so userspace can 1344 provision keys. Once the keyring is restricted 1345 it becomes active and is searched during signature 1346 verification. 1347 1348 driver_async_probe= [KNL] 1349 List of driver names to be probed asynchronously. * 1350 matches with all driver names. If * is specified, the 1351 rest of the listed driver names are those that will NOT 1352 match the *. 1353 Format: <driver_name1>,<driver_name2>... 1354 1355 drm.edid_firmware=[<connector>:]<file>[,[<connector>:]<file>] 1356 Broken monitors, graphic adapters, KVMs and EDIDless 1357 panels may send no or incorrect EDID data sets. 1358 This parameter allows to specify an EDID data sets 1359 in the /lib/firmware directory that are used instead. 1360 An EDID data set will only be used for a particular 1361 connector, if its name and a colon are prepended to 1362 the EDID name. Each connector may use a unique EDID 1363 data set by separating the files with a comma. An EDID 1364 data set with no connector name will be used for 1365 any connectors not explicitly specified. 1366 1367 dscc4.setup= [NET] 1368 1369 dt_cpu_ftrs= [PPC,EARLY] 1370 Format: {"off" | "known"} 1371 Control how the dt_cpu_ftrs device-tree binding is 1372 used for CPU feature discovery and setup (if it 1373 exists). 1374 off: Do not use it, fall back to legacy cpu table. 1375 known: Do not pass through unknown features to guests 1376 or userspace, only those that the kernel is aware of. 1377 1378 dump_apple_properties [X86] 1379 Dump name and content of EFI device properties on 1380 x86 Macs. Useful for driver authors to determine 1381 what data is available or for reverse-engineering. 1382 1383 dyndbg[="val"] [KNL,DYNAMIC_DEBUG] 1384 <module>.dyndbg[="val"] 1385 Enable debug messages at boot time. See 1386 Documentation/admin-guide/dynamic-debug-howto.rst 1387 for details. 1388 1389 early_ioremap_debug [KNL,EARLY] 1390 Enable debug messages in early_ioremap support. This 1391 is useful for tracking down temporary early mappings 1392 which are not unmapped. 1393 1394 earlycon= [KNL,EARLY] Output early console device and options. 1395 1396 When used with no options, the early console is 1397 determined by stdout-path property in device tree's 1398 chosen node or the ACPI SPCR table if supported by 1399 the platform. 1400 1401 cdns,<addr>[,options] 1402 Start an early, polled-mode console on a Cadence 1403 (xuartps) serial port at the specified address. Only 1404 supported option is baud rate. If baud rate is not 1405 specified, the serial port must already be setup and 1406 configured. 1407 1408 uart[8250],io,<addr>[,options[,uartclk]] 1409 uart[8250],mmio,<addr>[,options[,uartclk]] 1410 uart[8250],mmio32,<addr>[,options[,uartclk]] 1411 uart[8250],mmio32be,<addr>[,options[,uartclk]] 1412 uart[8250],0x<addr>[,options] 1413 Start an early, polled-mode console on the 8250/16550 1414 UART at the specified I/O port or MMIO address. 1415 MMIO inter-register address stride is either 8-bit 1416 (mmio) or 32-bit (mmio32 or mmio32be). 1417 If none of [io|mmio|mmio32|mmio32be], <addr> is assumed 1418 to be equivalent to 'mmio'. 'options' are specified 1419 in the same format described for "console=ttyS<n>"; if 1420 unspecified, the h/w is not initialized. 'uartclk' is 1421 the uart clock frequency; if unspecified, it is set 1422 to 'BASE_BAUD' * 16. 1423 1424 pl011,<addr> 1425 pl011,mmio32,<addr> 1426 Start an early, polled-mode console on a pl011 serial 1427 port at the specified address. The pl011 serial port 1428 must already be setup and configured. Options are not 1429 yet supported. If 'mmio32' is specified, then only 1430 the driver will use only 32-bit accessors to read/write 1431 the device registers. 1432 1433 liteuart,<addr> 1434 Start an early console on a litex serial port at the 1435 specified address. The serial port must already be 1436 setup and configured. Options are not yet supported. 1437 1438 meson,<addr> 1439 Start an early, polled-mode console on a meson serial 1440 port at the specified address. The serial port must 1441 already be setup and configured. Options are not yet 1442 supported. 1443 1444 msm_serial,<addr> 1445 Start an early, polled-mode console on an msm serial 1446 port at the specified address. The serial port 1447 must already be setup and configured. Options are not 1448 yet supported. 1449 1450 msm_serial_dm,<addr> 1451 Start an early, polled-mode console on an msm serial 1452 dm port at the specified address. The serial port 1453 must already be setup and configured. Options are not 1454 yet supported. 1455 1456 owl,<addr> 1457 Start an early, polled-mode console on a serial port 1458 of an Actions Semi SoC, such as S500 or S900, at the 1459 specified address. The serial port must already be 1460 setup and configured. Options are not yet supported. 1461 1462 rda,<addr> 1463 Start an early, polled-mode console on a serial port 1464 of an RDA Micro SoC, such as RDA8810PL, at the 1465 specified address. The serial port must already be 1466 setup and configured. Options are not yet supported. 1467 1468 sbi 1469 Use RISC-V SBI (Supervisor Binary Interface) for early 1470 console. 1471 1472 smh Use ARM semihosting calls for early console. 1473 1474 s3c2410,<addr> 1475 s3c2412,<addr> 1476 s3c2440,<addr> 1477 s3c6400,<addr> 1478 s5pv210,<addr> 1479 exynos4210,<addr> 1480 Use early console provided by serial driver available 1481 on Samsung SoCs, requires selecting proper type and 1482 a correct base address of the selected UART port. The 1483 serial port must already be setup and configured. 1484 Options are not yet supported. 1485 1486 lantiq,<addr> 1487 Start an early, polled-mode console on a lantiq serial 1488 (lqasc) port at the specified address. The serial port 1489 must already be setup and configured. Options are not 1490 yet supported. 1491 1492 lpuart,<addr> 1493 lpuart32,<addr> 1494 Use early console provided by Freescale LP UART driver 1495 found on Freescale Vybrid and QorIQ LS1021A processors. 1496 A valid base address must be provided, and the serial 1497 port must already be setup and configured. 1498 1499 ec_imx21,<addr> 1500 ec_imx6q,<addr> 1501 Start an early, polled-mode, output-only console on the 1502 Freescale i.MX UART at the specified address. The UART 1503 must already be setup and configured. 1504 1505 ar3700_uart,<addr> 1506 Start an early, polled-mode console on the 1507 Armada 3700 serial port at the specified 1508 address. The serial port must already be setup 1509 and configured. Options are not yet supported. 1510 1511 qcom_geni,<addr> 1512 Start an early, polled-mode console on a Qualcomm 1513 Generic Interface (GENI) based serial port at the 1514 specified address. The serial port must already be 1515 setup and configured. Options are not yet supported. 1516 1517 efifb,[options] 1518 Start an early, unaccelerated console on the EFI 1519 memory mapped framebuffer (if available). On cache 1520 coherent non-x86 systems that use system memory for 1521 the framebuffer, pass the 'ram' option so that it is 1522 mapped with the correct attributes. 1523 1524 linflex,<addr> 1525 Use early console provided by Freescale LINFlexD UART 1526 serial driver for NXP S32V234 SoCs. A valid base 1527 address must be provided, and the serial port must 1528 already be setup and configured. 1529 1530 earlyprintk= [X86,SH,ARM,M68k,S390,UM,EARLY] 1531 earlyprintk=vga 1532 earlyprintk=sclp 1533 earlyprintk=xen 1534 earlyprintk=serial[,ttySn[,baudrate]] 1535 earlyprintk=serial[,0x...[,baudrate]] 1536 earlyprintk=ttySn[,baudrate] 1537 earlyprintk=dbgp[debugController#] 1538 earlyprintk=mmio32,membase[,{nocfg|baudrate}] 1539 earlyprintk=pciserial[,force],bus:device.function[,{nocfg|baudrate}] 1540 earlyprintk=xdbc[xhciController#] 1541 earlyprintk=bios 1542 1543 earlyprintk is useful when the kernel crashes before 1544 the normal console is initialized. It is not enabled by 1545 default because it has some cosmetic problems. 1546 1547 Use "nocfg" to skip UART configuration, assume 1548 BIOS/firmware has configured UART correctly. 1549 1550 Append ",keep" to not disable it when the real console 1551 takes over. 1552 1553 Only one of vga, serial, or usb debug port can 1554 be used at a time. 1555 1556 Currently only ttyS0 and ttyS1 may be specified by 1557 name. Other I/O ports may be explicitly specified 1558 on some architectures (x86 and arm at least) by 1559 replacing ttySn with an I/O port address, like this: 1560 earlyprintk=serial,0x1008,115200 1561 You can find the port for a given device in 1562 /proc/tty/driver/serial: 1563 2: uart:ST16650V2 port:00001008 irq:18 ... 1564 1565 Interaction with the standard serial driver is not 1566 very good. 1567 1568 The VGA output is eventually overwritten by 1569 the real console. 1570 1571 The xen option can only be used in Xen domains. 1572 1573 The sclp output can only be used on s390. 1574 1575 The bios output can only be used on SuperH. 1576 1577 The optional "force" to "pciserial" enables use of a 1578 PCI device even when its classcode is not of the 1579 UART class. 1580 1581 edac_report= [HW,EDAC] Control how to report EDAC event 1582 Format: {"on" | "off" | "force"} 1583 on: enable EDAC to report H/W event. May be overridden 1584 by other higher priority error reporting module. 1585 off: disable H/W event reporting through EDAC. 1586 force: enforce the use of EDAC to report H/W event. 1587 default: on. 1588 1589 edd= [EDD] 1590 Format: {"off" | "on" | "skip[mbr]"} 1591 1592 efi= [EFI,EARLY] 1593 Format: { "debug", "disable_early_pci_dma", 1594 "nochunk", "noruntime", "nosoftreserve", 1595 "novamap", "no_disable_early_pci_dma" } 1596 debug: enable misc debug output. 1597 disable_early_pci_dma: disable the busmaster bit on all 1598 PCI bridges while in the EFI boot stub. 1599 nochunk: disable reading files in "chunks" in the EFI 1600 boot stub, as chunking can cause problems with some 1601 firmware implementations. 1602 noruntime : disable EFI runtime services support 1603 nosoftreserve: The EFI_MEMORY_SP (Specific Purpose) 1604 attribute may cause the kernel to reserve the 1605 memory range for a memory mapping driver to 1606 claim. Specify efi=nosoftreserve to disable this 1607 reservation and treat the memory by its base type 1608 (i.e. EFI_CONVENTIONAL_MEMORY / "System RAM"). 1609 novamap: do not call SetVirtualAddressMap(). 1610 no_disable_early_pci_dma: Leave the busmaster bit set 1611 on all PCI bridges while in the EFI boot stub 1612 1613 efi_no_storage_paranoia [EFI,X86,EARLY] 1614 Using this parameter you can use more than 50% of 1615 your efi variable storage. Use this parameter only if 1616 you are really sure that your UEFI does sane gc and 1617 fulfills the spec otherwise your board may brick. 1618 1619 efivar_ssdt= [EFI; X86] Name of an EFI variable that contains an SSDT 1620 that is to be dynamically loaded by Linux. If there are 1621 multiple variables with the same name but with different 1622 vendor GUIDs, all of them will be loaded. See 1623 Documentation/admin-guide/acpi/ssdt-overlays.rst for details. 1624 1625 1626 eisa_irq_edge= [PARISC,HW] 1627 See header of drivers/parisc/eisa.c. 1628 1629 ekgdboc= [X86,KGDB,EARLY] Allow early kernel console debugging 1630 Format: ekgdboc=kbd 1631 1632 This is designed to be used in conjunction with 1633 the boot argument: earlyprintk=vga 1634 1635 This parameter works in place of the kgdboc parameter 1636 but can only be used if the backing tty is available 1637 very early in the boot process. For early debugging 1638 via a serial port see kgdboc_earlycon instead. 1639 1640 elanfreq= [X86-32] 1641 See comment before function elanfreq_setup() in 1642 arch/x86/kernel/cpu/cpufreq/elanfreq.c. 1643 1644 elfcorehdr=[size[KMG]@]offset[KMG] [PPC,SH,X86,S390,EARLY] 1645 Specifies physical address of start of kernel core 1646 image elf header and optionally the size. Generally 1647 kexec loader will pass this option to capture kernel. 1648 See Documentation/admin-guide/kdump/kdump.rst for details. 1649 1650 enable_mtrr_cleanup [X86,EARLY] 1651 The kernel tries to adjust MTRR layout from continuous 1652 to discrete, to make X server driver able to add WB 1653 entry later. This parameter enables that. 1654 1655 enable_timer_pin_1 [X86] 1656 Enable PIN 1 of APIC timer 1657 Can be useful to work around chipset bugs 1658 (in particular on some ATI chipsets). 1659 The kernel tries to set a reasonable default. 1660 1661 enforcing= [SELINUX] Set initial enforcing status. 1662 Format: {"0" | "1"} 1663 See security/selinux/Kconfig help text. 1664 0 -- permissive (log only, no denials). 1665 1 -- enforcing (deny and log). 1666 Default value is 0. 1667 Value can be changed at runtime via 1668 /sys/fs/selinux/enforce. 1669 1670 erst_disable [ACPI] 1671 Disable Error Record Serialization Table (ERST) 1672 support. 1673 1674 ether= [HW,NET] Ethernet cards parameters 1675 This option is obsoleted by the "netdev=" option, which 1676 has equivalent usage. See its documentation for details. 1677 1678 evm= [EVM] 1679 Format: { "fix" } 1680 Permit 'security.evm' to be updated regardless of 1681 current integrity status. 1682 1683 early_page_ext [KNL,EARLY] Enforces page_ext initialization to earlier 1684 stages so cover more early boot allocations. 1685 Please note that as side effect some optimizations 1686 might be disabled to achieve that (e.g. parallelized 1687 memory initialization is disabled) so the boot process 1688 might take longer, especially on systems with a lot of 1689 memory. Available with CONFIG_PAGE_EXTENSION=y. 1690 1691 failslab= 1692 fail_usercopy= 1693 fail_page_alloc= 1694 fail_skb_realloc= 1695 fail_make_request=[KNL] 1696 General fault injection mechanism. 1697 Format: <interval>,<probability>,<space>,<times> 1698 See also Documentation/fault-injection/. 1699 1700 fb_tunnels= [NET] 1701 Format: { initns | none } 1702 See Documentation/admin-guide/sysctl/net.rst for 1703 fb_tunnels_only_for_init_ns 1704 1705 floppy= [HW] 1706 See Documentation/admin-guide/blockdev/floppy.rst. 1707 1708 forcepae [X86-32] 1709 Forcefully enable Physical Address Extension (PAE). 1710 Many Pentium M systems disable PAE but may have a 1711 functionally usable PAE implementation. 1712 Warning: use of this parameter will taint the kernel 1713 and may cause unknown problems. 1714 1715 fred= [X86-64] 1716 Enable/disable Flexible Return and Event Delivery. 1717 Format: { on | off } 1718 on: enable FRED when it's present, the default setting. 1719 off: disable FRED. 1720 1721 ftrace=[tracer] 1722 [FTRACE] will set and start the specified tracer 1723 as early as possible in order to facilitate early 1724 boot debugging. 1725 1726 ftrace_boot_snapshot 1727 [FTRACE] On boot up, a snapshot will be taken of the 1728 ftrace ring buffer that can be read at: 1729 /sys/kernel/tracing/snapshot. 1730 This is useful if you need tracing information from kernel 1731 boot up that is likely to be overridden by user space 1732 start up functionality. 1733 1734 Optionally, the snapshot can also be defined for a tracing 1735 instance that was created by the trace_instance= command 1736 line parameter. 1737 1738 trace_instance=foo,sched_switch ftrace_boot_snapshot=foo 1739 1740 The above will cause the "foo" tracing instance to trigger 1741 a snapshot at the end of boot up. 1742 1743 ftrace_dump_on_oops[=2(orig_cpu) | =<instance>][,<instance> | 1744 ,<instance>=2(orig_cpu)] 1745 [FTRACE] will dump the trace buffers on oops. 1746 If no parameter is passed, ftrace will dump global 1747 buffers of all CPUs, if you pass 2 or orig_cpu, it 1748 will dump only the buffer of the CPU that triggered 1749 the oops, or the specific instance will be dumped if 1750 its name is passed. Multiple instance dump is also 1751 supported, and instances are separated by commas. Each 1752 instance supports only dump on CPU that triggered the 1753 oops by passing 2 or orig_cpu to it. 1754 1755 ftrace_dump_on_oops=foo=orig_cpu 1756 1757 The above will dump only the buffer of "foo" instance 1758 on CPU that triggered the oops. 1759 1760 ftrace_dump_on_oops,foo,bar=orig_cpu 1761 1762 The above will dump global buffer on all CPUs, the 1763 buffer of "foo" instance on all CPUs and the buffer 1764 of "bar" instance on CPU that triggered the oops. 1765 1766 ftrace_filter=[function-list] 1767 [FTRACE] Limit the functions traced by the function 1768 tracer at boot up. function-list is a comma-separated 1769 list of functions. This list can be changed at run 1770 time by the set_ftrace_filter file in the debugfs 1771 tracing directory. 1772 1773 ftrace_notrace=[function-list] 1774 [FTRACE] Do not trace the functions specified in 1775 function-list. This list can be changed at run time 1776 by the set_ftrace_notrace file in the debugfs 1777 tracing directory. 1778 1779 ftrace_graph_filter=[function-list] 1780 [FTRACE] Limit the top level callers functions traced 1781 by the function graph tracer at boot up. 1782 function-list is a comma-separated list of functions 1783 that can be changed at run time by the 1784 set_graph_function file in the debugfs tracing directory. 1785 1786 ftrace_graph_notrace=[function-list] 1787 [FTRACE] Do not trace from the functions specified in 1788 function-list. This list is a comma-separated list of 1789 functions that can be changed at run time by the 1790 set_graph_notrace file in the debugfs tracing directory. 1791 1792 ftrace_graph_max_depth=<uint> 1793 [FTRACE] Used with the function graph tracer. This is 1794 the max depth it will trace into a function. This value 1795 can be changed at run time by the max_graph_depth file 1796 in the tracefs tracing directory. default: 0 (no limit) 1797 1798 fw_devlink= [KNL,EARLY] Create device links between consumer and supplier 1799 devices by scanning the firmware to infer the 1800 consumer/supplier relationships. This feature is 1801 especially useful when drivers are loaded as modules as 1802 it ensures proper ordering of tasks like device probing 1803 (suppliers first, then consumers), supplier boot state 1804 clean up (only after all consumers have probed), 1805 suspend/resume & runtime PM (consumers first, then 1806 suppliers). 1807 Format: { off | permissive | on | rpm } 1808 off -- Don't create device links from firmware info. 1809 permissive -- Create device links from firmware info 1810 but use it only for ordering boot state clean 1811 up (sync_state() calls). 1812 on -- Create device links from firmware info and use it 1813 to enforce probe and suspend/resume ordering. 1814 rpm -- Like "on", but also use to order runtime PM. 1815 1816 fw_devlink.strict=<bool> 1817 [KNL,EARLY] Treat all inferred dependencies as mandatory 1818 dependencies. This only applies for fw_devlink=on|rpm. 1819 Format: <bool> 1820 1821 fw_devlink.sync_state = 1822 [KNL,EARLY] When all devices that could probe have finished 1823 probing, this parameter controls what to do with 1824 devices that haven't yet received their sync_state() 1825 calls. 1826 Format: { strict | timeout } 1827 strict -- Default. Continue waiting on consumers to 1828 probe successfully. 1829 timeout -- Give up waiting on consumers and call 1830 sync_state() on any devices that haven't yet 1831 received their sync_state() calls after 1832 deferred_probe_timeout has expired or by 1833 late_initcall() if !CONFIG_MODULES. 1834 1835 gamecon.map[2|3]= 1836 [HW,JOY] Multisystem joystick and NES/SNES/PSX pad 1837 support via parallel port (up to 5 devices per port) 1838 Format: <port#>,<pad1>,<pad2>,<pad3>,<pad4>,<pad5> 1839 See also Documentation/input/devices/joystick-parport.rst 1840 1841 gamma= [HW,DRM] 1842 1843 gart_fix_e820= [X86-64,EARLY] disable the fix e820 for K8 GART 1844 Format: off | on 1845 default: on 1846 1847 gather_data_sampling= 1848 [X86,INTEL,EARLY] Control the Gather Data Sampling (GDS) 1849 mitigation. 1850 1851 Gather Data Sampling is a hardware vulnerability which 1852 allows unprivileged speculative access to data which was 1853 previously stored in vector registers. 1854 1855 This issue is mitigated by default in updated microcode. 1856 The mitigation may have a performance impact but can be 1857 disabled. On systems without the microcode mitigation 1858 disabling AVX serves as a mitigation. 1859 1860 force: Disable AVX to mitigate systems without 1861 microcode mitigation. No effect if the microcode 1862 mitigation is present. Known to cause crashes in 1863 userspace with buggy AVX enumeration. 1864 1865 off: Disable GDS mitigation. 1866 1867 gbpages [X86] Use GB pages for kernel direct mappings. 1868 1869 gcov_persist= [GCOV] When non-zero (default), profiling data for 1870 kernel modules is saved and remains accessible via 1871 debugfs, even when the module is unloaded/reloaded. 1872 When zero, profiling data is discarded and associated 1873 debugfs files are removed at module unload time. 1874 1875 goldfish [X86] Enable the goldfish android emulator platform. 1876 Don't use this when you are not running on the 1877 android emulator 1878 1879 gpio-mockup.gpio_mockup_ranges 1880 [HW] Sets the ranges of gpiochip of for this device. 1881 Format: <start1>,<end1>,<start2>,<end2>... 1882 gpio-mockup.gpio_mockup_named_lines 1883 [HW] Let the driver know GPIO lines should be named. 1884 1885 gpt [EFI] Forces disk with valid GPT signature but 1886 invalid Protective MBR to be treated as GPT. If the 1887 primary GPT is corrupted, it enables the backup/alternate 1888 GPT to be used instead. 1889 1890 grcan.enable0= [HW] Configuration of physical interface 0. Determines 1891 the "Enable 0" bit of the configuration register. 1892 Format: 0 | 1 1893 Default: 0 1894 grcan.enable1= [HW] Configuration of physical interface 1. Determines 1895 the "Enable 0" bit of the configuration register. 1896 Format: 0 | 1 1897 Default: 0 1898 grcan.select= [HW] Select which physical interface to use. 1899 Format: 0 | 1 1900 Default: 0 1901 grcan.txsize= [HW] Sets the size of the tx buffer. 1902 Format: <unsigned int> such that (txsize & ~0x1fffc0) == 0. 1903 Default: 1024 1904 grcan.rxsize= [HW] Sets the size of the rx buffer. 1905 Format: <unsigned int> such that (rxsize & ~0x1fffc0) == 0. 1906 Default: 1024 1907 1908 hardened_usercopy= 1909 [KNL] Under CONFIG_HARDENED_USERCOPY, whether 1910 hardening is enabled for this boot. Hardened 1911 usercopy checking is used to protect the kernel 1912 from reading or writing beyond known memory 1913 allocation boundaries as a proactive defense 1914 against bounds-checking flaws in the kernel's 1915 copy_to_user()/copy_from_user() interface. 1916 The default is determined by 1917 CONFIG_HARDENED_USERCOPY_DEFAULT_ON. 1918 on Perform hardened usercopy checks. 1919 off Disable hardened usercopy checks. 1920 1921 hardlockup_all_cpu_backtrace= 1922 [KNL] Should the hard-lockup detector generate 1923 backtraces on all cpus. 1924 Format: 0 | 1 1925 1926 hash_pointers= 1927 [KNL,EARLY] 1928 By default, when pointers are printed to the console 1929 or buffers via the %p format string, that pointer is 1930 "hashed", i.e. obscured by hashing the pointer value. 1931 This is a security feature that hides actual kernel 1932 addresses from unprivileged users, but it also makes 1933 debugging the kernel more difficult since unequal 1934 pointers can no longer be compared. The choices are: 1935 Format: { auto | always | never } 1936 Default: auto 1937 1938 auto - Hash pointers unless slab_debug is enabled. 1939 always - Always hash pointers (even if slab_debug is 1940 enabled). 1941 never - Never hash pointers. This option should only 1942 be specified when debugging the kernel. Do 1943 not use on production kernels. The boot 1944 param "no_hash_pointers" is an alias for 1945 this mode. 1946 1947 For controlling hashing dynamically at runtime, 1948 use the "kernel.kptr_restrict" sysctl instead. 1949 1950 hashdist= [KNL,NUMA] Large hashes allocated during boot 1951 are distributed across NUMA nodes. Defaults on 1952 for 64-bit NUMA, off otherwise. 1953 Format: 0 | 1 (for off | on) 1954 1955 hd= [EIDE] (E)IDE hard drive subsystem geometry 1956 Format: <cyl>,<head>,<sect> 1957 1958 hest_disable [ACPI] 1959 Disable Hardware Error Source Table (HEST) support; 1960 corresponding firmware-first mode error processing 1961 logic will be disabled. 1962 1963 hibernate= [HIBERNATION] 1964 noresume Don't check if there's a hibernation image 1965 present during boot. 1966 nocompress Don't compress/decompress hibernation images. 1967 no Disable hibernation and resume. 1968 protect_image Turn on image protection during restoration 1969 (that will set all pages holding image data 1970 during restoration read-only). 1971 1972 hibernate.compressor= [HIBERNATION] Compression algorithm to be 1973 used with hibernation. 1974 Format: { lzo | lz4 } 1975 Default: lzo 1976 1977 lzo: Select LZO compression algorithm to 1978 compress/decompress hibernation image. 1979 1980 lz4: Select LZ4 compression algorithm to 1981 compress/decompress hibernation image. 1982 1983 hibernate.pm_test_delay= 1984 [HIBERNATION] 1985 Sets the number of seconds to remain in a hibernation test 1986 mode before resuming the system (see 1987 /sys/power/pm_test). Only available when CONFIG_PM_DEBUG 1988 is set. Default value is 5. 1989 1990 hibernate_compression_threads= 1991 [HIBERNATION] 1992 Set the number of threads used for compressing or decompressing 1993 hibernation images. 1994 1995 Format: <integer> 1996 Default: 3 1997 Minimum: 1 1998 Example: hibernate_compression_threads=4 1999 2000 highmem=nn[KMG] [KNL,BOOT,EARLY] forces the highmem zone to have an exact 2001 size of <nn>. This works even on boxes that have no 2002 highmem otherwise. This also works to reduce highmem 2003 size on bigger boxes. 2004 2005 highres= [KNL] Enable/disable high resolution timer mode. 2006 Valid parameters: "on", "off" 2007 Default: "on" 2008 2009 hlt [BUGS=ARM,SH] 2010 2011 hostname= [KNL,EARLY] Set the hostname (aka UTS nodename). 2012 Format: <string> 2013 This allows setting the system's hostname during early 2014 startup. This sets the name returned by gethostname. 2015 Using this parameter to set the hostname makes it 2016 possible to ensure the hostname is correctly set before 2017 any userspace processes run, avoiding the possibility 2018 that a process may call gethostname before the hostname 2019 has been explicitly set, resulting in the calling 2020 process getting an incorrect result. The string must 2021 not exceed the maximum allowed hostname length (usually 2022 64 characters) and will be truncated otherwise. 2023 2024 hpet= [X86-32,HPET] option to control HPET usage 2025 Format: { enable (default) | disable | force | 2026 verbose } 2027 disable: disable HPET and use PIT instead 2028 force: allow force enabled of undocumented chips (ICH4, 2029 VIA, nVidia) 2030 verbose: show contents of HPET registers during setup 2031 2032 hpet_mmap= [X86, HPET_MMAP] Allow userspace to mmap HPET 2033 registers. Default set by CONFIG_HPET_MMAP_DEFAULT. 2034 2035 hugepages= [HW,EARLY] Number of HugeTLB pages to allocate at boot. 2036 If this follows hugepagesz (below), it specifies 2037 the number of pages of hugepagesz to be allocated. 2038 If this is the first HugeTLB parameter on the command 2039 line, it specifies the number of pages to allocate for 2040 the default huge page size. If using node format, the 2041 number of pages to allocate per-node can be specified. 2042 See also Documentation/admin-guide/mm/hugetlbpage.rst. 2043 Format: <integer> or (node format) 2044 <node>:<integer>[,<node>:<integer>] 2045 2046 hugepagesz= 2047 [HW,EARLY] The size of the HugeTLB pages. This is 2048 used in conjunction with hugepages (above) to 2049 allocate huge pages of a specific size at boot. The 2050 pair hugepagesz=X hugepages=Y can be specified once 2051 for each supported huge page size. Huge page sizes 2052 are architecture dependent. See also 2053 Documentation/admin-guide/mm/hugetlbpage.rst. 2054 Format: size[KMG] 2055 2056 hugepage_alloc_threads= 2057 [HW] The number of threads that should be used to 2058 allocate hugepages during boot. This option can be 2059 used to improve system bootup time when allocating 2060 a large amount of huge pages. 2061 The default value is 25% of the available hardware threads. 2062 2063 Note that this parameter only applies to non-gigantic huge pages. 2064 2065 hugetlb_cma= [HW,CMA,EARLY] The size of a CMA area used for allocation 2066 of gigantic hugepages. Or using node format, the size 2067 of a CMA area per node can be specified. 2068 Format: nn[KMGTPE] or (node format) 2069 <node>:nn[KMGTPE][,<node>:nn[KMGTPE]] 2070 2071 Reserve a CMA area of given size and allocate gigantic 2072 hugepages using the CMA allocator. If enabled, the 2073 boot-time allocation of gigantic hugepages is skipped. 2074 2075 hugetlb_cma_only= 2076 [HW,CMA,EARLY] When allocating new HugeTLB pages, only 2077 try to allocate from the CMA areas. 2078 2079 This option does nothing if hugetlb_cma= is not also 2080 specified. 2081 2082 hugetlb_free_vmemmap= 2083 [KNL] Requires CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP 2084 enabled. 2085 Control if HugeTLB Vmemmap Optimization (HVO) is enabled. 2086 Allows heavy hugetlb users to free up some more 2087 memory (7 * PAGE_SIZE for each 2MB hugetlb page). 2088 Format: { on | off (default) } 2089 2090 on: enable HVO 2091 off: disable HVO 2092 2093 Built with CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP_DEFAULT_ON=y, 2094 the default is on. 2095 2096 Note that the vmemmap pages may be allocated from the added 2097 memory block itself when memory_hotplug.memmap_on_memory is 2098 enabled, those vmemmap pages cannot be optimized even if this 2099 feature is enabled. Other vmemmap pages not allocated from 2100 the added memory block itself do not be affected. 2101 2102 hung_task_panic= 2103 [KNL] Number of hung tasks to trigger kernel panic. 2104 Format: <int> 2105 2106 When set to a non-zero value, a kernel panic will be triggered if 2107 the number of detected hung tasks reaches this value. 2108 2109 0: don't panic 2110 1: panic immediately on first hung task 2111 N: panic after N hung tasks are detected in a single scan 2112 2113 The default value is controlled by the 2114 CONFIG_BOOTPARAM_HUNG_TASK_PANIC build-time option. The value 2115 selected by this boot parameter can be changed later by the 2116 kernel.hung_task_panic sysctl. 2117 2118 hvc_iucv= [S390] Number of z/VM IUCV hypervisor console (HVC) 2119 terminal devices. Valid values: 0..8 2120 hvc_iucv_allow= [S390] Comma-separated list of z/VM user IDs. 2121 If specified, z/VM IUCV HVC accepts connections 2122 from listed z/VM user IDs only. 2123 2124 hv_nopvspin [X86,HYPER_V,EARLY] 2125 Disables the paravirt spinlock optimizations 2126 which allow the hypervisor to 'idle' the guest 2127 on lock contention. 2128 2129 hw_protection= [HW] 2130 Format: reboot | shutdown 2131 2132 Hardware protection action taken on critical events like 2133 overtemperature or imminent voltage loss. 2134 2135 i2c_bus= [HW] Override the default board specific I2C bus speed 2136 or register an additional I2C bus that is not 2137 registered from board initialization code. 2138 Format: 2139 <bus_id>,<clkrate> 2140 2141 i2c_touchscreen_props= [HW,ACPI,X86] 2142 Set device-properties for ACPI-enumerated I2C-attached 2143 touchscreen, to e.g. fix coordinates of upside-down 2144 mounted touchscreens. If you need this option please 2145 submit a drivers/platform/x86/touchscreen_dmi.c patch 2146 adding a DMI quirk for this. 2147 2148 Format: 2149 <ACPI_HW_ID>:<prop_name>=<val>[:prop_name=val][:...] 2150 Where <val> is one of: 2151 Omit "=<val>" entirely Set a boolean device-property 2152 Unsigned number Set a u32 device-property 2153 Anything else Set a string device-property 2154 2155 Examples (split over multiple lines): 2156 i2c_touchscreen_props=GDIX1001:touchscreen-inverted-x: 2157 touchscreen-inverted-y 2158 2159 i2c_touchscreen_props=MSSL1680:touchscreen-size-x=1920: 2160 touchscreen-size-y=1080:touchscreen-inverted-y: 2161 firmware-name=gsl1680-vendor-model.fw:silead,home-button 2162 2163 i8042.debug [HW] Toggle i8042 debug mode 2164 i8042.unmask_kbd_data 2165 [HW] Enable printing of interrupt data from the KBD port 2166 (disabled by default, and as a pre-condition 2167 requires that i8042.debug=1 be enabled) 2168 i8042.direct [HW] Put keyboard port into non-translated mode 2169 i8042.dumbkbd [HW] Pretend that controller can only read data from 2170 keyboard and cannot control its state 2171 (Don't attempt to blink the leds) 2172 i8042.noaux [HW] Don't check for auxiliary (== mouse) port 2173 i8042.nokbd [HW] Don't check/create keyboard port 2174 i8042.noloop [HW] Disable the AUX Loopback command while probing 2175 for the AUX port 2176 i8042.nomux [HW] Don't check presence of an active multiplexing 2177 controller 2178 i8042.nopnp [HW] Don't use ACPIPnP / PnPBIOS to discover KBD/AUX 2179 controllers 2180 i8042.notimeout [HW] Ignore timeout condition signalled by controller 2181 i8042.reset [HW] Reset the controller during init, cleanup and 2182 suspend-to-ram transitions, only during s2r 2183 transitions, or never reset 2184 Format: { 1 | Y | y | 0 | N | n } 2185 1, Y, y: always reset controller 2186 0, N, n: don't ever reset controller 2187 Default: only on s2r transitions on x86; most other 2188 architectures force reset to be always executed 2189 i8042.unlock [HW] Unlock (ignore) the keylock 2190 i8042.kbdreset [HW] Reset device connected to KBD port 2191 i8042.probe_defer 2192 [HW] Allow deferred probing upon i8042 probe errors 2193 2194 i810= [HW,DRM] 2195 2196 i915.invert_brightness= 2197 [DRM] Invert the sense of the variable that is used to 2198 set the brightness of the panel backlight. Normally a 2199 brightness value of 0 indicates backlight switched off, 2200 and the maximum of the brightness value sets the backlight 2201 to maximum brightness. If this parameter is set to 0 2202 (default) and the machine requires it, or this parameter 2203 is set to 1, a brightness value of 0 sets the backlight 2204 to maximum brightness, and the maximum of the brightness 2205 value switches the backlight off. 2206 -1 -- never invert brightness 2207 0 -- machine default 2208 1 -- force brightness inversion 2209 2210 ia32_emulation= [X86-64] 2211 Format: <bool> 2212 When true, allows loading 32-bit programs and executing 32-bit 2213 syscalls, essentially overriding IA32_EMULATION_DEFAULT_DISABLED at 2214 boot time. When false, unconditionally disables IA32 emulation. 2215 2216 icn= [HW,ISDN] 2217 Format: <io>[,<membase>[,<icn_id>[,<icn_id2>]]] 2218 2219 2220 idle= [X86,EARLY] 2221 Format: idle=poll, idle=halt, idle=nomwait 2222 2223 idle=poll: Don't do power saving in the idle loop 2224 using HLT, but poll for rescheduling event. This will 2225 make the CPUs eat a lot more power, but may be useful 2226 to get slightly better performance in multiprocessor 2227 benchmarks. It also makes some profiling using 2228 performance counters more accurate. Please note that 2229 on systems with MONITOR/MWAIT support (like Intel 2230 EM64T CPUs) this option has no performance advantage 2231 over the normal idle loop. It may also interact badly 2232 with hyperthreading. 2233 2234 idle=halt: Halt is forced to be used for CPU idle. 2235 In such case C2/C3 won't be used again. 2236 2237 idle=nomwait: Disable mwait for CPU C-states 2238 2239 idxd.sva= [HW] 2240 Format: <bool> 2241 Allow force disabling of Shared Virtual Memory (SVA) 2242 support for the idxd driver. By default it is set to 2243 true (1). 2244 2245 idxd.tc_override= [HW] 2246 Format: <bool> 2247 Allow override of default traffic class configuration 2248 for the device. By default it is set to false (0). 2249 2250 ieee754= [MIPS] Select IEEE Std 754 conformance mode 2251 Format: { strict | legacy | 2008 | relaxed | emulated } 2252 Default: strict 2253 2254 Choose which programs will be accepted for execution 2255 based on the IEEE 754 NaN encoding(s) supported by 2256 the FPU and the NaN encoding requested with the value 2257 of an ELF file header flag individually set by each 2258 binary. Hardware implementations are permitted to 2259 support either or both of the legacy and the 2008 NaN 2260 encoding mode. 2261 2262 Available settings are as follows: 2263 strict accept binaries that request a NaN encoding 2264 supported by the FPU 2265 legacy only accept legacy-NaN binaries, if supported 2266 by the FPU 2267 2008 only accept 2008-NaN binaries, if supported 2268 by the FPU 2269 relaxed accept any binaries regardless of whether 2270 supported by the FPU 2271 emulated accept any binaries but enable FPU emulator 2272 if binary mode is unsupported by the FPU. 2273 2274 The FPU emulator is always able to support both NaN 2275 encodings, so if no FPU hardware is present or it has 2276 been disabled with 'nofpu', then the settings of 2277 'legacy' and '2008' strap the emulator accordingly, 2278 'relaxed' straps the emulator for both legacy-NaN and 2279 2008-NaN, whereas 'strict' enables legacy-NaN only on 2280 legacy processors and both NaN encodings on MIPS32 or 2281 MIPS64 CPUs. 2282 2283 The setting for ABS.fmt/NEG.fmt instruction execution 2284 mode generally follows that for the NaN encoding, 2285 except where unsupported by hardware. 2286 2287 ignore_loglevel [KNL,EARLY] 2288 Ignore loglevel setting - this will print /all/ 2289 kernel messages to the console. Useful for debugging. 2290 We also add it as printk module parameter, so users 2291 could change it dynamically, usually by 2292 /sys/module/printk/parameters/ignore_loglevel. 2293 2294 ignore_rlimit_data 2295 Ignore RLIMIT_DATA setting for data mappings, 2296 print warning at first misuse. Can be changed via 2297 /sys/module/kernel/parameters/ignore_rlimit_data. 2298 2299 ihash_entries= [KNL] 2300 Set number of hash buckets for inode cache. 2301 2302 ima_appraise= [IMA] appraise integrity measurements 2303 Format: { "off" | "enforce" | "fix" | "log" } 2304 default: "enforce" 2305 2306 ima_appraise_tcb [IMA] Deprecated. Use ima_policy= instead. 2307 The builtin appraise policy appraises all files 2308 owned by uid=0. 2309 2310 ima_canonical_fmt [IMA] 2311 Use the canonical format for the binary runtime 2312 measurements, instead of host native format. 2313 2314 ima_hash= [IMA] 2315 Format: { md5 | sha1 | rmd160 | sha256 | sha384 2316 | sha512 | ... } 2317 default: "sha1" 2318 2319 The list of supported hash algorithms is defined 2320 in crypto/hash_info.h. 2321 2322 ima_policy= [IMA] 2323 The builtin policies to load during IMA setup. 2324 Format: "tcb | appraise_tcb | secure_boot | 2325 fail_securely | critical_data" 2326 2327 The "tcb" policy measures all programs exec'd, files 2328 mmap'd for exec, and all files opened with the read 2329 mode bit set by either the effective uid (euid=0) or 2330 uid=0. 2331 2332 The "appraise_tcb" policy appraises the integrity of 2333 all files owned by root. 2334 2335 The "secure_boot" policy appraises the integrity 2336 of files (eg. kexec kernel image, kernel modules, 2337 firmware, policy, etc) based on file signatures. 2338 2339 The "fail_securely" policy forces file signature 2340 verification failure also on privileged mounted 2341 filesystems with the SB_I_UNVERIFIABLE_SIGNATURE 2342 flag. 2343 2344 The "critical_data" policy measures kernel integrity 2345 critical data. 2346 2347 ima_tcb [IMA] Deprecated. Use ima_policy= instead. 2348 Load a policy which meets the needs of the Trusted 2349 Computing Base. This means IMA will measure all 2350 programs exec'd, files mmap'd for exec, and all files 2351 opened for read by uid=0. 2352 2353 ima_template= [IMA] 2354 Select one of defined IMA measurements template formats. 2355 Formats: { "ima" | "ima-ng" | "ima-ngv2" | "ima-sig" | 2356 "ima-sigv2" } 2357 Default: "ima-ng" 2358 2359 ima_template_fmt= 2360 [IMA] Define a custom template format. 2361 Format: { "field1|...|fieldN" } 2362 2363 ima= [IMA] Enable or disable IMA 2364 Format: { "off" | "on" } 2365 Default: "on" 2366 Note that disabling IMA is limited to kdump kernel. 2367 2368 indirect_target_selection= [X86,Intel] Mitigation control for Indirect 2369 Target Selection(ITS) bug in Intel CPUs. Updated 2370 microcode is also required for a fix in IBPB. 2371 2372 on: Enable mitigation (default). 2373 off: Disable mitigation. 2374 force: Force the ITS bug and deploy default 2375 mitigation. 2376 vmexit: Only deploy mitigation if CPU is affected by 2377 guest/host isolation part of ITS. 2378 stuff: Deploy RSB-fill mitigation when retpoline is 2379 also deployed. Otherwise, deploy the default 2380 mitigation. 2381 2382 For details see: 2383 Documentation/admin-guide/hw-vuln/indirect-target-selection.rst 2384 2385 init= [KNL] 2386 Format: <full_path> 2387 Run specified binary instead of /sbin/init as init 2388 process. 2389 2390 initcall_debug [KNL] Trace initcalls as they are executed. Useful 2391 for working out where the kernel is dying during 2392 startup. 2393 2394 initcall_blacklist= [KNL] Do not execute a comma-separated list of 2395 initcall functions. Useful for debugging built-in 2396 modules and initcalls. 2397 2398 initramfs_async= [KNL] 2399 Format: <bool> 2400 Default: 1 2401 This parameter controls whether the initramfs 2402 image is unpacked asynchronously, concurrently 2403 with devices being probed and 2404 initialized. This should normally just work, 2405 but as a debugging aid, one can get the 2406 historical behaviour of the initramfs 2407 unpacking being completed before device_ and 2408 late_ initcalls. 2409 2410 initrd= [BOOT,EARLY] Specify the location of the initial ramdisk 2411 2412 initrdmem= [KNL,EARLY] Specify a physical address and size from which to 2413 load the initrd. If an initrd is compiled in or 2414 specified in the bootparams, it takes priority over this 2415 setting. 2416 Format: ss[KMG],nn[KMG] 2417 Default is 0, 0 2418 2419 init_on_alloc= [MM,EARLY] Fill newly allocated pages and heap objects with 2420 zeroes. 2421 Format: 0 | 1 2422 Default set by CONFIG_INIT_ON_ALLOC_DEFAULT_ON. 2423 2424 init_on_free= [MM,EARLY] Fill freed pages and heap objects with zeroes. 2425 Format: 0 | 1 2426 Default set by CONFIG_INIT_ON_FREE_DEFAULT_ON. 2427 2428 init_pkru= [X86] Specify the default memory protection keys rights 2429 register contents for all processes. 0x55555554 by 2430 default (disallow access to all but pkey 0). Can 2431 override in debugfs after boot. 2432 2433 inport.irq= [HW] Inport (ATI XL and Microsoft) busmouse driver 2434 Format: <irq> 2435 2436 int_pln_enable [X86] Enable power limit notification interrupt 2437 2438 integrity_audit=[IMA] 2439 Format: { "0" | "1" } 2440 0 -- basic integrity auditing messages. (Default) 2441 1 -- additional integrity auditing messages. 2442 2443 intel_iommu= [DMAR] Intel IOMMU driver (DMAR) option 2444 on 2445 Enable intel iommu driver. 2446 off 2447 Disable intel iommu driver. 2448 igfx_off [Default Off] 2449 By default, gfx is mapped as normal device. If a gfx 2450 device has a dedicated DMAR unit, the DMAR unit is 2451 bypassed by not enabling DMAR with this option. In 2452 this case, gfx device will use physical address for 2453 DMA. 2454 strict [Default Off] 2455 Deprecated, equivalent to iommu.strict=1. 2456 sp_off [Default Off] 2457 By default, super page will be supported if Intel IOMMU 2458 has the capability. With this option, super page will 2459 not be supported. 2460 sm_on 2461 Enable the Intel IOMMU scalable mode if the hardware 2462 advertises that it has support for the scalable mode 2463 translation. 2464 sm_off 2465 Disallow use of the Intel IOMMU scalable mode. 2466 tboot_noforce [Default Off] 2467 Do not force the Intel IOMMU enabled under tboot. 2468 By default, tboot will force Intel IOMMU on, which 2469 could harm performance of some high-throughput 2470 devices like 40GBit network cards, even if identity 2471 mapping is enabled. 2472 Note that using this option lowers the security 2473 provided by tboot because it makes the system 2474 vulnerable to DMA attacks. 2475 2476 intel_idle.max_cstate= [KNL,HW,ACPI,X86] 2477 0 disables intel_idle and fall back on acpi_idle. 2478 1 to 9 specify maximum depth of C-state. 2479 2480 intel_pstate= [X86,EARLY] 2481 disable 2482 Do not enable intel_pstate as the default 2483 scaling driver for the supported processors 2484 active 2485 Use intel_pstate driver to bypass the scaling 2486 governors layer of cpufreq and provides it own 2487 algorithms for p-state selection. There are two 2488 P-state selection algorithms provided by 2489 intel_pstate in the active mode: powersave and 2490 performance. The way they both operate depends 2491 on whether or not the hardware managed P-states 2492 (HWP) feature has been enabled in the processor 2493 and possibly on the processor model. 2494 passive 2495 Use intel_pstate as a scaling driver, but configure it 2496 to work with generic cpufreq governors (instead of 2497 enabling its internal governor). This mode cannot be 2498 used along with the hardware-managed P-states (HWP) 2499 feature. 2500 force 2501 Enable intel_pstate on systems that prohibit it by default 2502 in favor of acpi-cpufreq. Forcing the intel_pstate driver 2503 instead of acpi-cpufreq may disable platform features, such 2504 as thermal controls and power capping, that rely on ACPI 2505 P-States information being indicated to OSPM and therefore 2506 should be used with caution. This option does not work with 2507 processors that aren't supported by the intel_pstate driver 2508 or on platforms that use pcc-cpufreq instead of acpi-cpufreq. 2509 no_hwp 2510 Do not enable hardware P state control (HWP) 2511 if available. 2512 hwp_only 2513 Only load intel_pstate on systems which support 2514 hardware P state control (HWP) if available. 2515 support_acpi_ppc 2516 Enforce ACPI _PPC performance limits. If the Fixed ACPI 2517 Description Table, specifies preferred power management 2518 profile as "Enterprise Server" or "Performance Server", 2519 then this feature is turned on by default. 2520 per_cpu_perf_limits 2521 Allow per-logical-CPU P-State performance control limits using 2522 cpufreq sysfs interface 2523 no_cas 2524 Do not enable capacity-aware scheduling (CAS) on 2525 hybrid systems 2526 2527 intremap= [X86-64,Intel-IOMMU,EARLY] 2528 on enable Interrupt Remapping (default) 2529 off disable Interrupt Remapping 2530 nosid disable Source ID checking 2531 no_x2apic_optout 2532 BIOS x2APIC opt-out request will be ignored 2533 nopost disable Interrupt Posting 2534 posted_msi 2535 enable MSIs delivered as posted interrupts 2536 2537 iomem= Disable strict checking of access to MMIO memory 2538 strict regions from userspace. 2539 relaxed 2540 2541 iommu= [X86,EARLY] 2542 2543 off 2544 Don't initialize and use any kind of IOMMU. 2545 2546 force 2547 Force the use of the hardware IOMMU even when 2548 it is not actually needed (e.g. because < 3 GB 2549 memory). 2550 2551 noforce 2552 Don't force hardware IOMMU usage when it is not 2553 needed. (default). 2554 2555 biomerge 2556 panic 2557 nopanic 2558 merge 2559 nomerge 2560 2561 soft 2562 Use software bounce buffering (SWIOTLB) (default for 2563 Intel machines). This can be used to prevent the usage 2564 of an available hardware IOMMU. 2565 2566 pt 2567 nopt 2568 nobypass [PPC/POWERNV] 2569 Disable IOMMU bypass, using IOMMU for PCI devices. 2570 2571 AMD Gart HW IOMMU-specific options: 2572 2573 <size> 2574 Set the size of the remapping area in bytes. 2575 2576 allowed 2577 Overwrite iommu off workarounds for specific chipsets 2578 2579 fullflush 2580 Flush IOMMU on each allocation (default). 2581 2582 nofullflush 2583 Don't use IOMMU fullflush. 2584 2585 memaper[=<order>] 2586 Allocate an own aperture over RAM with size 2587 32MB<<order. (default: order=1, i.e. 64MB) 2588 2589 merge 2590 Do scatter-gather (SG) merging. Implies "force" 2591 (experimental). 2592 2593 nomerge 2594 Don't do scatter-gather (SG) merging. 2595 2596 noaperture 2597 Ask the IOMMU not to touch the aperture for AGP. 2598 2599 noagp 2600 Don't initialize the AGP driver and use full aperture. 2601 2602 panic 2603 Always panic when IOMMU overflows. 2604 2605 iommu.forcedac= [ARM64,X86,EARLY] Control IOVA allocation for PCI devices. 2606 Format: { "0" | "1" } 2607 0 - Try to allocate a 32-bit DMA address first, before 2608 falling back to the full range if needed. 2609 1 - Allocate directly from the full usable range, 2610 forcing Dual Address Cycle for PCI cards supporting 2611 greater than 32-bit addressing. 2612 2613 iommu.strict= [ARM64,X86,S390,EARLY] Configure TLB invalidation behaviour 2614 Format: { "0" | "1" } 2615 0 - Lazy mode. 2616 Request that DMA unmap operations use deferred 2617 invalidation of hardware TLBs, for increased 2618 throughput at the cost of reduced device isolation. 2619 Will fall back to strict mode if not supported by 2620 the relevant IOMMU driver. 2621 1 - Strict mode. 2622 DMA unmap operations invalidate IOMMU hardware TLBs 2623 synchronously. 2624 unset - Use value of CONFIG_IOMMU_DEFAULT_DMA_{LAZY,STRICT}. 2625 Note: on x86, strict mode specified via one of the 2626 legacy driver-specific options takes precedence. 2627 2628 iommu.passthrough= 2629 [ARM64,X86,EARLY] Configure DMA to bypass the IOMMU by default. 2630 Format: { "0" | "1" } 2631 0 - Use IOMMU translation for DMA. 2632 1 - Bypass the IOMMU for DMA. 2633 unset - Use value of CONFIG_IOMMU_DEFAULT_PASSTHROUGH. 2634 2635 iommu.debug_pagealloc= 2636 [KNL,EARLY] When CONFIG_IOMMU_DEBUG_PAGEALLOC is set, this 2637 parameter enables the feature at boot time. By default, it 2638 is disabled and the system behaves the same way as a kernel 2639 built without CONFIG_IOMMU_DEBUG_PAGEALLOC. 2640 Format: { "0" | "1" } 2641 0 - Sanitizer disabled. 2642 1 - Sanitizer enabled, expect runtime overhead. 2643 2644 io7= [HW] IO7 for Marvel-based Alpha systems 2645 See comment before marvel_specify_io7 in 2646 arch/alpha/kernel/core_marvel.c. 2647 2648 io_delay= [X86,EARLY] I/O delay method 2649 0x80 2650 Standard port 0x80 based delay 2651 0xed 2652 Alternate port 0xed based delay (needed on some systems) 2653 udelay 2654 Simple two microseconds delay 2655 none 2656 No delay 2657 2658 ip= [IP_PNP] 2659 See Documentation/admin-guide/nfs/nfsroot.rst. 2660 2661 ipcmni_extend [KNL,EARLY] Extend the maximum number of unique System V 2662 IPC identifiers from 32,768 to 16,777,216. 2663 2664 ipe.enforce= [IPE] 2665 Format: <bool> 2666 Determine whether IPE starts in permissive (0) or 2667 enforce (1) mode. The default is enforce. 2668 2669 ipe.success_audit= 2670 [IPE] 2671 Format: <bool> 2672 Start IPE with success auditing enabled, emitting 2673 an audit event when a binary is allowed. The default 2674 is 0. 2675 2676 irqaffinity= [SMP] Set the default irq affinity mask 2677 The argument is a cpu list, as described above. 2678 2679 irqchip.gicv2_force_probe= 2680 [ARM,ARM64,EARLY] 2681 Format: <bool> 2682 Force the kernel to look for the second 4kB page 2683 of a GICv2 controller even if the memory range 2684 exposed by the device tree is too small. 2685 2686 irqchip.gicv3_nolpi= 2687 [ARM,ARM64,EARLY] 2688 Force the kernel to ignore the availability of 2689 LPIs (and by consequence ITSs). Intended for system 2690 that use the kernel as a bootloader, and thus want 2691 to let secondary kernels in charge of setting up 2692 LPIs. 2693 2694 irqchip.gicv3_pseudo_nmi= [ARM64,EARLY] 2695 Enables support for pseudo-NMIs in the kernel. This 2696 requires the kernel to be built with 2697 CONFIG_ARM64_PSEUDO_NMI. 2698 2699 irqchip.riscv_imsic_noipi 2700 [RISC-V,EARLY] 2701 Force the kernel to not use IMSIC software injected MSIs 2702 as IPIs. Intended for system where IMSIC is trap-n-emulated, 2703 and thus want to reduce MMIO traps when triggering IPIs 2704 to multiple harts. 2705 2706 irqfixup [HW] 2707 When an interrupt is not handled search all handlers 2708 for it. Intended to get systems with badly broken 2709 firmware running. 2710 2711 irqhandler.duration_warn_us= [KNL] 2712 Warn if an IRQ handler exceeds the specified duration 2713 threshold in microseconds. Useful for identifying 2714 long-running IRQs in the system. 2715 2716 irqpoll [HW] 2717 When an interrupt is not handled search all handlers 2718 for it. Also check all handlers each timer 2719 interrupt. Intended to get systems with badly broken 2720 firmware running. 2721 2722 isapnp= [ISAPNP] 2723 Format: <RDP>,<reset>,<pci_scan>,<verbosity> 2724 2725 isolcpus= [KNL,SMP,ISOL] Isolate a given set of CPUs from disturbance. 2726 [Deprecated - use cpusets instead] 2727 Format: [flag-list,]<cpu-list> 2728 2729 Specify one or more CPUs to isolate from disturbances 2730 specified in the flag list (default: domain): 2731 2732 nohz 2733 Disable the tick when a single task runs as well as 2734 disabling other kernel noises like having RCU callbacks 2735 offloaded. This is equivalent to the nohz_full parameter. 2736 2737 A residual 1Hz tick is offloaded to workqueues, which you 2738 need to affine to housekeeping through the global 2739 workqueue's affinity configured via the 2740 /sys/devices/virtual/workqueue/cpumask sysfs file, or 2741 by using the 'domain' flag described below. 2742 2743 NOTE: by default the global workqueue runs on all CPUs, 2744 so to protect individual CPUs the 'cpumask' file has to 2745 be configured manually after bootup. 2746 2747 domain 2748 Isolate from the general SMP balancing and scheduling 2749 algorithms. Note that performing domain isolation this way 2750 is irreversible: it's not possible to bring back a CPU to 2751 the domains once isolated through isolcpus. It's strongly 2752 advised to use cpusets instead to disable scheduler load 2753 balancing through the "cpuset.sched_load_balance" file. 2754 It offers a much more flexible interface where CPUs can 2755 move in and out of an isolated set anytime. 2756 2757 You can move a process onto or off an "isolated" CPU via 2758 the CPU affinity syscalls or cpuset. 2759 <cpu number> begins at 0 and the maximum value is 2760 "number of CPUs in system - 1". 2761 2762 managed_irq 2763 2764 Isolate from being targeted by managed interrupts 2765 which have an interrupt mask containing isolated 2766 CPUs. The affinity of managed interrupts is 2767 handled by the kernel and cannot be changed via 2768 the /proc/irq/* interfaces. 2769 2770 This isolation is best effort and only effective 2771 if the automatically assigned interrupt mask of a 2772 device queue contains isolated and housekeeping 2773 CPUs. If housekeeping CPUs are online then such 2774 interrupts are directed to the housekeeping CPU 2775 so that IO submitted on the housekeeping CPU 2776 cannot disturb the isolated CPU. 2777 2778 If a queue's affinity mask contains only isolated 2779 CPUs then this parameter has no effect on the 2780 interrupt routing decision, though interrupts are 2781 only delivered when tasks running on those 2782 isolated CPUs submit IO. IO submitted on 2783 housekeeping CPUs has no influence on those 2784 queues. 2785 2786 The format of <cpu-list> is described above. 2787 2788 iucv= [HW,NET] 2789 2790 ivrs_ioapic [HW,X86-64] 2791 Provide an override to the IOAPIC-ID<->DEVICE-ID 2792 mapping provided in the IVRS ACPI table. 2793 By default, PCI segment is 0, and can be omitted. 2794 2795 For example, to map IOAPIC-ID decimal 10 to 2796 PCI segment 0x1 and PCI device 00:14.0, 2797 write the parameter as: 2798 ivrs_ioapic=10@0001:00:14.0 2799 2800 Deprecated formats: 2801 * To map IOAPIC-ID decimal 10 to PCI device 00:14.0 2802 write the parameter as: 2803 ivrs_ioapic[10]=00:14.0 2804 * To map IOAPIC-ID decimal 10 to PCI segment 0x1 and 2805 PCI device 00:14.0 write the parameter as: 2806 ivrs_ioapic[10]=0001:00:14.0 2807 2808 ivrs_hpet [HW,X86-64] 2809 Provide an override to the HPET-ID<->DEVICE-ID 2810 mapping provided in the IVRS ACPI table. 2811 By default, PCI segment is 0, and can be omitted. 2812 2813 For example, to map HPET-ID decimal 10 to 2814 PCI segment 0x1 and PCI device 00:14.0, 2815 write the parameter as: 2816 ivrs_hpet=10@0001:00:14.0 2817 2818 Deprecated formats: 2819 * To map HPET-ID decimal 0 to PCI device 00:14.0 2820 write the parameter as: 2821 ivrs_hpet[0]=00:14.0 2822 * To map HPET-ID decimal 10 to PCI segment 0x1 and 2823 PCI device 00:14.0 write the parameter as: 2824 ivrs_ioapic[10]=0001:00:14.0 2825 2826 ivrs_acpihid [HW,X86-64] 2827 Provide an override to the ACPI-HID:UID<->DEVICE-ID 2828 mapping provided in the IVRS ACPI table. 2829 By default, PCI segment is 0, and can be omitted. 2830 2831 For example, to map UART-HID:UID AMD0020:0 to 2832 PCI segment 0x1 and PCI device ID 00:14.5, 2833 write the parameter as: 2834 ivrs_acpihid=AMD0020:0@0001:00:14.5 2835 2836 Deprecated formats: 2837 * To map UART-HID:UID AMD0020:0 to PCI segment is 0, 2838 PCI device ID 00:14.5, write the parameter as: 2839 ivrs_acpihid[00:14.5]=AMD0020:0 2840 * To map UART-HID:UID AMD0020:0 to PCI segment 0x1 and 2841 PCI device ID 00:14.5, write the parameter as: 2842 ivrs_acpihid[0001:00:14.5]=AMD0020:0 2843 2844 js= [HW,JOY] Analog joystick 2845 See Documentation/input/joydev/joystick.rst. 2846 2847 kasan_multi_shot 2848 [KNL] Enforce KASAN (Kernel Address Sanitizer) to print 2849 report on every invalid memory access. Without this 2850 parameter KASAN will print report only for the first 2851 invalid access. 2852 2853 keep_bootcon [KNL,EARLY] 2854 Do not unregister boot console at start. This is only 2855 useful for debugging when something happens in the window 2856 between unregistering the boot console and initializing 2857 the real console. 2858 2859 keepinitrd [HW,ARM] See retain_initrd. 2860 2861 kernelcore= [KNL,X86,PPC,EARLY] 2862 Format: nn[KMGTPE] | nn% | "mirror" 2863 This parameter specifies the amount of memory usable by 2864 the kernel for non-movable allocations. The requested 2865 amount is spread evenly throughout all nodes in the 2866 system as ZONE_NORMAL. The remaining memory is used for 2867 movable memory in its own zone, ZONE_MOVABLE. In the 2868 event, a node is too small to have both ZONE_NORMAL and 2869 ZONE_MOVABLE, kernelcore memory will take priority and 2870 other nodes will have a larger ZONE_MOVABLE. 2871 2872 ZONE_MOVABLE is used for the allocation of pages that 2873 may be reclaimed or moved by the page migration 2874 subsystem. Note that allocations like PTEs-from-HighMem 2875 still use the HighMem zone if it exists, and the Normal 2876 zone if it does not. 2877 2878 It is possible to specify the exact amount of memory in 2879 the form of "nn[KMGTPE]", a percentage of total system 2880 memory in the form of "nn%", or "mirror". If "mirror" 2881 option is specified, mirrored (reliable) memory is used 2882 for non-movable allocations and remaining memory is used 2883 for Movable pages. "nn[KMGTPE]", "nn%", and "mirror" 2884 are exclusive, so you cannot specify multiple forms. 2885 2886 kfence.burst= [MM,KFENCE] The number of additional successive 2887 allocations to be attempted through KFENCE for each 2888 sample interval. 2889 Format: <unsigned integer> 2890 Default: 0 2891 2892 kfence.check_on_panic= 2893 [MM,KFENCE] Whether to check all KFENCE-managed objects' 2894 canaries on panic. 2895 Format: <bool> 2896 Default: false 2897 2898 kfence.deferrable= 2899 [MM,KFENCE] Whether to use a deferrable timer to trigger 2900 allocations. This avoids forcing CPU wake-ups if the 2901 system is idle, at the risk of a less predictable 2902 sample interval. 2903 Format: <bool> 2904 Default: CONFIG_KFENCE_DEFERRABLE 2905 2906 kfence.fault= [MM,KFENCE] Controls the behavior when a KFENCE 2907 error is detected. 2908 report - print the error report and continue (default). 2909 oops - print the error report and oops. 2910 panic - print the error report and panic. 2911 2912 kfence.sample_interval= 2913 [MM,KFENCE] KFENCE's sample interval in milliseconds. 2914 Format: <unsigned integer> 2915 0 - Disable KFENCE. 2916 >0 - Enabled KFENCE with given sample interval. 2917 Default: CONFIG_KFENCE_SAMPLE_INTERVAL 2918 2919 kfence.skip_covered_thresh= 2920 [MM,KFENCE] If pool utilization reaches this threshold 2921 (pool usage%), KFENCE limits currently covered 2922 allocations of the same source from further filling 2923 up the pool. 2924 Format: <unsigned integer> 2925 Default: 75 2926 2927 kgdbdbgp= [KGDB,HW,EARLY] kgdb over EHCI usb debug port. 2928 Format: <Controller#>[,poll interval] 2929 The controller # is the number of the ehci usb debug 2930 port as it is probed via PCI. The poll interval is 2931 optional and is the number seconds in between 2932 each poll cycle to the debug port in case you need 2933 the functionality for interrupting the kernel with 2934 gdb or control-c on the dbgp connection. When 2935 not using this parameter you use sysrq-g to break into 2936 the kernel debugger. 2937 2938 kgdboc= [KGDB,HW] kgdb over consoles. 2939 Requires a tty driver that supports console polling, 2940 or a supported polling keyboard driver (non-usb). 2941 Serial only format: <serial_device>[,baud] 2942 keyboard only format: kbd 2943 keyboard and serial format: kbd,<serial_device>[,baud] 2944 Optional Kernel mode setting: 2945 kms, kbd format: kms,kbd 2946 kms, kbd and serial format: kms,kbd,<ser_dev>[,baud] 2947 2948 kgdboc_earlycon= [KGDB,HW,EARLY] 2949 If the boot console provides the ability to read 2950 characters and can work in polling mode, you can use 2951 this parameter to tell kgdb to use it as a backend 2952 until the normal console is registered. Intended to 2953 be used together with the kgdboc parameter which 2954 specifies the normal console to transition to. 2955 2956 The name of the early console should be specified 2957 as the value of this parameter. Note that the name of 2958 the early console might be different than the tty 2959 name passed to kgdboc. It's OK to leave the value 2960 blank and the first boot console that implements 2961 read() will be picked. 2962 2963 kgdbwait [KGDB,EARLY] Stop kernel execution and enter the 2964 kernel debugger at the earliest opportunity. 2965 2966 kho= [KEXEC,EARLY] 2967 Format: { "0" | "1" | "off" | "on" | "y" | "n" } 2968 Enables or disables Kexec HandOver. 2969 "0" | "off" | "n" - kexec handover is disabled 2970 "1" | "on" | "y" - kexec handover is enabled 2971 2972 kho_scratch= [KEXEC,EARLY] 2973 Format: ll[KMG],mm[KMG],nn[KMG] | nn% 2974 Defines the size of the KHO scratch region. The KHO 2975 scratch regions are physically contiguous memory 2976 ranges that can only be used for non-kernel 2977 allocations. That way, even when memory is heavily 2978 fragmented with handed over memory, the kexeced 2979 kernel will always have enough contiguous ranges to 2980 bootstrap itself. 2981 2982 It is possible to specify the exact amount of 2983 memory in the form of "ll[KMG],mm[KMG],nn[KMG]" 2984 where the first parameter defines the size of a low 2985 memory scratch area, the second parameter defines 2986 the size of a global scratch area and the third 2987 parameter defines the size of additional per-node 2988 scratch areas. The form "nn%" defines scale factor 2989 (in percents) of memory that was used during boot. 2990 2991 kmac= [MIPS] Korina ethernet MAC address. 2992 Configure the RouterBoard 532 series on-chip 2993 Ethernet adapter MAC address. 2994 2995 kmemleak= [KNL,EARLY] Boot-time kmemleak enable/disable 2996 Valid arguments: on, off 2997 Default: on 2998 Built with CONFIG_DEBUG_KMEMLEAK_DEFAULT_OFF=y, 2999 the default is off. 3000 3001 kprobe_event=[probe-list] 3002 [FTRACE] Add kprobe events and enable at boot time. 3003 The probe-list is a semicolon delimited list of probe 3004 definitions. Each definition is same as kprobe_events 3005 interface, but the parameters are comma delimited. 3006 For example, to add a kprobe event on vfs_read with 3007 arg1 and arg2, add to the command line; 3008 3009 kprobe_event=p,vfs_read,$arg1,$arg2 3010 3011 See also Documentation/trace/kprobetrace.rst "Kernel 3012 Boot Parameter" section. 3013 3014 kpti= [ARM64,EARLY] Control page table isolation of 3015 user and kernel address spaces. 3016 Default: enabled on cores which need mitigation. 3017 0: force disabled 3018 1: force enabled 3019 3020 kunit.enable= [KUNIT] Enable executing KUnit tests. Requires 3021 CONFIG_KUNIT to be set to be fully enabled. The 3022 default value can be overridden via 3023 KUNIT_DEFAULT_ENABLED. 3024 Default is 1 (enabled) 3025 3026 kvm.ignore_msrs=[KVM] Ignore guest accesses to unhandled MSRs. 3027 Default is 0 (don't ignore, but inject #GP) 3028 3029 kvm.eager_page_split= 3030 [KVM,X86] Controls whether or not KVM will try to 3031 proactively split all huge pages during dirty logging. 3032 Eager page splitting reduces interruptions to vCPU 3033 execution by eliminating the write-protection faults 3034 and MMU lock contention that would otherwise be 3035 required to split huge pages lazily. 3036 3037 VM workloads that rarely perform writes or that write 3038 only to a small region of VM memory may benefit from 3039 disabling eager page splitting to allow huge pages to 3040 still be used for reads. 3041 3042 The behavior of eager page splitting depends on whether 3043 KVM_DIRTY_LOG_INITIALLY_SET is enabled or disabled. If 3044 disabled, all huge pages in a memslot will be eagerly 3045 split when dirty logging is enabled on that memslot. If 3046 enabled, eager page splitting will be performed during 3047 the KVM_CLEAR_DIRTY ioctl, and only for the pages being 3048 cleared. 3049 3050 Eager page splitting is only supported when kvm.tdp_mmu=Y. 3051 3052 Default is Y (on). 3053 3054 kvm.enable_pmu=[KVM,X86] 3055 If enabled, KVM will virtualize PMU functionality based 3056 on the virtual CPU model defined by userspace. This 3057 can be overridden on a per-VM basis via 3058 KVM_CAP_PMU_CAPABILITY. 3059 3060 If disabled, KVM will not virtualize PMU functionality, 3061 e.g. MSRs, PMCs, PMIs, etc., even if userspace defines 3062 a virtual CPU model that contains PMU assets. 3063 3064 Note, KVM's vPMU support implicitly requires running 3065 with an in-kernel local APIC, e.g. to deliver PMIs to 3066 the guest. Running without an in-kernel local APIC is 3067 not supported, though KVM will allow such a combination 3068 (with severely degraded functionality). 3069 3070 See also enable_mediated_pmu. 3071 3072 Default is Y (on). 3073 3074 kvm.enable_virt_at_load=[KVM,ARM64,LOONGARCH,MIPS,RISCV,X86] 3075 If enabled, KVM will enable virtualization in hardware 3076 when KVM is loaded, and disable virtualization when KVM 3077 is unloaded (if KVM is built as a module). 3078 3079 If disabled, KVM will dynamically enable and disable 3080 virtualization on-demand when creating and destroying 3081 VMs, i.e. on the 0=>1 and 1=>0 transitions of the 3082 number of VMs. 3083 3084 Enabling virtualization at module load avoids potential 3085 latency for creation of the 0=>1 VM, as KVM serializes 3086 virtualization enabling across all online CPUs. The 3087 "cost" of enabling virtualization when KVM is loaded, 3088 is that doing so may interfere with using out-of-tree 3089 hypervisors that want to "own" virtualization hardware. 3090 3091 kvm.enable_vmware_backdoor=[KVM] Support VMware backdoor PV interface. 3092 Default is false (don't support). 3093 3094 kvm.nx_huge_pages= 3095 [KVM] Controls the software workaround for the 3096 X86_BUG_ITLB_MULTIHIT bug. 3097 force : Always deploy workaround. 3098 off : Never deploy workaround. 3099 auto : Deploy workaround based on the presence of 3100 X86_BUG_ITLB_MULTIHIT. 3101 3102 Default is 'auto'. 3103 3104 If the software workaround is enabled for the host, 3105 guests do need not to enable it for nested guests. 3106 3107 kvm.nx_huge_pages_recovery_ratio= 3108 [KVM] Controls how many 4KiB pages are periodically zapped 3109 back to huge pages. 0 disables the recovery, otherwise if 3110 the value is N KVM will zap 1/Nth of the 4KiB pages every 3111 period (see below). The default is 60. 3112 3113 kvm.nx_huge_pages_recovery_period_ms= 3114 [KVM] Controls the time period at which KVM zaps 4KiB pages 3115 back to huge pages. If the value is a non-zero N, KVM will 3116 zap a portion (see ratio above) of the pages every N msecs. 3117 If the value is 0 (the default), KVM will pick a period based 3118 on the ratio, such that a page is zapped after 1 hour on average. 3119 3120 kvm-{amd,intel}.enable_mediated_pmu=[KVM,AMD,INTEL] 3121 If enabled, KVM will provide a mediated virtual PMU, 3122 instead of the default perf-based virtual PMU (if 3123 kvm.enable_pmu is true and PMU is enumerated via the 3124 virtual CPU model). 3125 3126 With a perf-based vPMU, KVM operates as a user of perf, 3127 i.e. emulates guest PMU counters using perf events. 3128 KVM-created perf events are managed by perf as regular 3129 (guest-only) events, e.g. are scheduled in/out, contend 3130 for hardware resources, etc. Using a perf-based vPMU 3131 allows guest and host usage of the PMU to co-exist, but 3132 incurs non-trivial overhead and can result in silently 3133 dropped guest events (due to resource contention). 3134 3135 With a mediated vPMU, hardware PMU state is context 3136 switched around the world switch to/from the guest. 3137 KVM mediates which events the guest can utilize, but 3138 gives the guest direct access to all other PMU assets 3139 when possible (KVM may intercept some accesses if the 3140 virtual CPU model provides a subset of hardware PMU 3141 functionality). Using a mediated vPMU significantly 3142 reduces PMU virtualization overhead and eliminates lost 3143 guest events, but is mutually exclusive with using perf 3144 to profile KVM guests and adds latency to most VM-Exits 3145 (to context switch PMU state). 3146 3147 Default is N (off). 3148 3149 kvm-amd.nested= [KVM,AMD] Control nested virtualization feature in 3150 KVM/SVM. Default is 1 (enabled). 3151 3152 kvm-amd.npt= [KVM,AMD] Control KVM's use of Nested Page Tables, 3153 a.k.a. Two-Dimensional Page Tables. Default is 1 3154 (enabled). Disable by KVM if hardware lacks support 3155 for NPT. 3156 3157 kvm-amd.ciphertext_hiding_asids= 3158 [KVM,AMD] Ciphertext hiding prevents disallowed accesses 3159 to SNP private memory from reading ciphertext. Instead, 3160 reads will see constant default values (0xff). 3161 3162 If ciphertext hiding is enabled, the joint SEV-ES and 3163 SEV-SNP ASID space is partitioned into separate SEV-ES 3164 and SEV-SNP ASID ranges, with the SEV-SNP range being 3165 [1..max_snp_asid] and the SEV-ES range being 3166 (max_snp_asid..min_sev_asid), where min_sev_asid is 3167 enumerated by CPUID.0x.8000_001F[EDX]. 3168 3169 A non-zero value enables SEV-SNP ciphertext hiding and 3170 adjusts the ASID ranges for SEV-ES and SEV-SNP guests. 3171 KVM caps the number of SEV-SNP ASIDs at the maximum 3172 possible value, e.g. specifying -1u will assign all 3173 joint SEV-ES and SEV-SNP ASIDs to SEV-SNP. Note, 3174 assigning all joint ASIDs to SEV-SNP, i.e. configuring 3175 max_snp_asid == min_sev_asid-1, will effectively make 3176 SEV-ES unusable. 3177 3178 kvm-arm.mode= 3179 [KVM,ARM,EARLY] Select one of KVM/arm64's modes of 3180 operation. 3181 3182 none: Forcefully disable KVM. 3183 3184 nvhe: Standard nVHE-based mode, without support for 3185 protected guests. 3186 3187 protected: Mode with support for guests whose state is 3188 kept private from the host, using VHE or 3189 nVHE depending on HW support. 3190 3191 nested: VHE-based mode with support for nested 3192 virtualization. Requires at least ARMv8.4 3193 hardware (with FEAT_NV2). 3194 3195 Defaults to VHE/nVHE based on hardware support. Setting 3196 mode to "protected" will disable kexec and hibernation 3197 for the host. To force nVHE on VHE hardware, add 3198 "arm64_sw.hvhe=0 id_aa64mmfr1.vh=0" to the 3199 command-line. 3200 "nested" and "protected" are experimental and should be 3201 used with extreme caution. 3202 3203 kvm-arm.vgic_v3_group0_trap= 3204 [KVM,ARM,EARLY] Trap guest accesses to GICv3 group-0 3205 system registers 3206 3207 kvm-arm.vgic_v3_group1_trap= 3208 [KVM,ARM,EARLY] Trap guest accesses to GICv3 group-1 3209 system registers 3210 3211 kvm-arm.vgic_v3_common_trap= 3212 [KVM,ARM,EARLY] Trap guest accesses to GICv3 common 3213 system registers 3214 3215 kvm-arm.vgic_v4_enable= 3216 [KVM,ARM,EARLY] Allow use of GICv4 for direct 3217 injection of LPIs. 3218 3219 kvm-arm.wfe_trap_policy= 3220 [KVM,ARM] Control when to set WFE instruction trap for 3221 KVM VMs. Traps are allowed but not guaranteed by the 3222 CPU architecture. 3223 3224 trap: set WFE instruction trap 3225 3226 notrap: clear WFE instruction trap 3227 3228 kvm-arm.wfi_trap_policy= 3229 [KVM,ARM] Control when to set WFI instruction trap for 3230 KVM VMs. Traps are allowed but not guaranteed by the 3231 CPU architecture. 3232 3233 trap: set WFI instruction trap 3234 3235 notrap: clear WFI instruction trap 3236 3237 kvm_cma_resv_ratio=n [PPC,EARLY] 3238 Reserves given percentage from system memory area for 3239 contiguous memory allocation for KVM hash pagetable 3240 allocation. 3241 By default it reserves 5% of total system memory. 3242 Format: <integer> 3243 Default: 5 3244 3245 kvm-intel.ept= [KVM,Intel] Control KVM's use of Extended Page Tables, 3246 a.k.a. Two-Dimensional Page Tables. Default is 1 3247 (enabled). Disable by KVM if hardware lacks support 3248 for EPT. 3249 3250 kvm-intel.emulate_invalid_guest_state= 3251 [KVM,Intel] Control whether to emulate invalid guest 3252 state. Ignored if kvm-intel.enable_unrestricted_guest=1, 3253 as guest state is never invalid for unrestricted 3254 guests. This param doesn't apply to nested guests (L2), 3255 as KVM never emulates invalid L2 guest state. 3256 Default is 1 (enabled). 3257 3258 kvm-intel.flexpriority= 3259 [KVM,Intel] Control KVM's use of FlexPriority feature 3260 (TPR shadow). Default is 1 (enabled). Disable by KVM if 3261 hardware lacks support for it. 3262 3263 kvm-intel.nested= 3264 [KVM,Intel] Control nested virtualization feature in 3265 KVM/VMX. Default is 1 (enabled). 3266 3267 kvm-intel.unrestricted_guest= 3268 [KVM,Intel] Control KVM's use of unrestricted guest 3269 feature (virtualized real and unpaged mode). Default 3270 is 1 (enabled). Disable by KVM if EPT is disabled or 3271 hardware lacks support for it. 3272 3273 kvm-intel.vmentry_l1d_flush=[KVM,Intel] Mitigation for L1 Terminal Fault 3274 CVE-2018-3620. 3275 3276 Valid arguments: never, cond, always 3277 3278 always: L1D cache flush on every VMENTER. 3279 cond: Flush L1D on VMENTER only when the code between 3280 VMEXIT and VMENTER can leak host memory. 3281 never: Disables the mitigation 3282 3283 Default is cond (do L1 cache flush in specific instances) 3284 3285 kvm-intel.vpid= [KVM,Intel] Control KVM's use of Virtual Processor 3286 Identification feature (tagged TLBs). Default is 1 3287 (enabled). Disable by KVM if hardware lacks support 3288 for it. 3289 3290 l1d_flush= [X86,INTEL,EARLY] 3291 Control mitigation for L1D based snooping vulnerability. 3292 3293 Certain CPUs are vulnerable to an exploit against CPU 3294 internal buffers which can forward information to a 3295 disclosure gadget under certain conditions. 3296 3297 In vulnerable processors, the speculatively 3298 forwarded data can be used in a cache side channel 3299 attack, to access data to which the attacker does 3300 not have direct access. 3301 3302 This parameter controls the mitigation. The 3303 options are: 3304 3305 on - enable the interface for the mitigation 3306 3307 l1tf= [X86,EARLY] Control mitigation of the L1TF vulnerability on 3308 affected CPUs 3309 3310 The kernel PTE inversion protection is unconditionally 3311 enabled and cannot be disabled. 3312 3313 full 3314 Provides all available mitigations for the 3315 L1TF vulnerability. Disables SMT and 3316 enables all mitigations in the 3317 hypervisors, i.e. unconditional L1D flush. 3318 3319 SMT control and L1D flush control via the 3320 sysfs interface is still possible after 3321 boot. Hypervisors will issue a warning 3322 when the first VM is started in a 3323 potentially insecure configuration, 3324 i.e. SMT enabled or L1D flush disabled. 3325 3326 full,force 3327 Same as 'full', but disables SMT and L1D 3328 flush runtime control. Implies the 3329 'nosmt=force' command line option. 3330 (i.e. sysfs control of SMT is disabled.) 3331 3332 flush 3333 Leaves SMT enabled and enables the default 3334 hypervisor mitigation, i.e. conditional 3335 L1D flush. 3336 3337 SMT control and L1D flush control via the 3338 sysfs interface is still possible after 3339 boot. Hypervisors will issue a warning 3340 when the first VM is started in a 3341 potentially insecure configuration, 3342 i.e. SMT enabled or L1D flush disabled. 3343 3344 flush,nosmt 3345 3346 Disables SMT and enables the default 3347 hypervisor mitigation. 3348 3349 SMT control and L1D flush control via the 3350 sysfs interface is still possible after 3351 boot. Hypervisors will issue a warning 3352 when the first VM is started in a 3353 potentially insecure configuration, 3354 i.e. SMT enabled or L1D flush disabled. 3355 3356 flush,nowarn 3357 Same as 'flush', but hypervisors will not 3358 warn when a VM is started in a potentially 3359 insecure configuration. 3360 3361 off 3362 Disables hypervisor mitigations and doesn't 3363 emit any warnings. 3364 It also drops the swap size and available 3365 RAM limit restriction on both hypervisor and 3366 bare metal. 3367 3368 Default is 'flush'. 3369 3370 For details see: Documentation/admin-guide/hw-vuln/l1tf.rst 3371 3372 l2cr= [PPC] 3373 3374 l3cr= [PPC] 3375 3376 lapic [X86-32,APIC,EARLY] Enable the local APIC even if BIOS 3377 disabled it. 3378 3379 lapic= [X86,APIC] Do not use TSC deadline 3380 value for LAPIC timer one-shot implementation. Default 3381 back to the programmable timer unit in the LAPIC. 3382 Format: notscdeadline 3383 3384 lapic_timer_c2_ok [X86,APIC,EARLY] trust the local apic timer 3385 in C2 power state. 3386 3387 libata.dma= [LIBATA] DMA control 3388 libata.dma=0 Disable all PATA and SATA DMA 3389 libata.dma=1 PATA and SATA Disk DMA only 3390 libata.dma=2 ATAPI (CDROM) DMA only 3391 libata.dma=4 Compact Flash DMA only 3392 Combinations also work, so libata.dma=3 enables DMA 3393 for disks and CDROMs, but not CFs. 3394 3395 libata.ignore_hpa= [LIBATA] Ignore HPA limit 3396 libata.ignore_hpa=0 keep BIOS limits (default) 3397 libata.ignore_hpa=1 ignore limits, using full disk 3398 3399 libata.noacpi [LIBATA] Disables use of ACPI in libata suspend/resume 3400 when set. 3401 Format: <int> 3402 3403 libata.force= [LIBATA] Force configurations. The format is a comma- 3404 separated list of "[ID:]VAL" where ID is PORT[.DEVICE]. 3405 PORT and DEVICE are decimal numbers matching port, link 3406 or device. Basically, it matches the ATA ID string 3407 printed on console by libata. If the whole ID part is 3408 omitted, the last PORT and DEVICE values are used. If 3409 ID hasn't been specified yet, the configuration applies 3410 to all ports, links and devices. 3411 3412 If only DEVICE is omitted, the parameter applies to 3413 the port and all links and devices behind it. DEVICE 3414 number of 0 either selects the first device or the 3415 first fan-out link behind PMP device. It does not 3416 select the host link. DEVICE number of 15 selects the 3417 host link and device attached to it. 3418 3419 The VAL specifies the configuration to force. As long 3420 as there is no ambiguity, shortcut notation is allowed. 3421 For example, both 1.5 and 1.5G would work for 1.5Gbps. 3422 The following configurations can be forced. 3423 3424 * Cable type: 40c, 80c, short40c, unk, ign or sata. 3425 Any ID with matching PORT is used. 3426 3427 * SATA link speed limit: 1.5Gbps or 3.0Gbps. 3428 3429 * Transfer mode: pio[0-7], mwdma[0-4] and udma[0-7]. 3430 udma[/][16,25,33,44,66,100,133] notation is also 3431 allowed. 3432 3433 * nohrst, nosrst, norst: suppress hard, soft and both 3434 resets. 3435 3436 * rstonce: only attempt one reset during hot-unplug 3437 link recovery. 3438 3439 * [no]dbdelay: Enable or disable the extra 200ms delay 3440 before debouncing a link PHY and device presence 3441 detection. 3442 3443 * [no]ncq: Turn on or off NCQ. 3444 3445 * [no]ncqtrim: Enable or disable queued DSM TRIM. 3446 3447 * [no]ncqati: Enable or disable NCQ trim on ATI chipset. 3448 3449 * [no]trim: Enable or disable (unqueued) TRIM. 3450 3451 * trim_zero: Indicate that TRIM command zeroes data. 3452 3453 * max_trim_128m: Set 128M maximum trim size limit. 3454 3455 * [no]dma: Turn on or off DMA transfers. 3456 3457 * atapi_dmadir: Enable ATAPI DMADIR bridge support. 3458 3459 * atapi_mod16_dma: Enable the use of ATAPI DMA for 3460 commands that are not a multiple of 16 bytes. 3461 3462 * [no]dmalog: Enable or disable the use of the 3463 READ LOG DMA EXT command to access logs. 3464 3465 * [no]iddevlog: Enable or disable access to the 3466 identify device data log. 3467 3468 * [no]logdir: Enable or disable access to the general 3469 purpose log directory. 3470 3471 * max_sec=<sectors>: Set the transfer size limit, in 3472 number of 512-byte sectors, to the value specified in 3473 <sectors>. The value specified in <sectors> has to be 3474 a non-zero positive integer. 3475 3476 * max_sec_128: Set transfer size limit to 128 sectors. 3477 3478 * max_sec_1024: Set or clear transfer size limit to 3479 1024 sectors. 3480 3481 * max_sec_lba48: Set or clear transfer size limit to 3482 65535 sectors. 3483 3484 * external: Mark port as external (hotplug-capable). 3485 3486 * [no]lpm: Enable or disable link power management. 3487 3488 * [no]setxfer: Indicate if transfer speed mode setting 3489 should be skipped. 3490 3491 * [no]fua: Disable or enable FUA (Force Unit Access) 3492 support for devices supporting this feature. 3493 3494 * dump_id: Dump IDENTIFY data. 3495 3496 * disable: Disable this device. 3497 3498 If there are multiple matching configurations changing 3499 the same attribute, the last one is used. 3500 3501 liveupdate= [KNL,EARLY] 3502 Format: <bool> 3503 Enable Live Update Orchestrator (LUO). 3504 Default: off. 3505 3506 lockd.nlm_grace_period=P [NFS] Assign grace period. 3507 Format: <integer> 3508 3509 lockd.nlm_tcpport=N [NFS] Assign TCP port. 3510 Format: <integer> 3511 3512 lockd.nlm_timeout=T [NFS] Assign timeout value. 3513 Format: <integer> 3514 3515 lockd.nlm_udpport=M [NFS] Assign UDP port. 3516 Format: <integer> 3517 3518 lockdown= [SECURITY,EARLY] 3519 { integrity | confidentiality } 3520 Enable the kernel lockdown feature. If set to 3521 integrity, kernel features that allow userland to 3522 modify the running kernel are disabled. If set to 3523 confidentiality, kernel features that allow userland 3524 to extract confidential information from the kernel 3525 are also disabled. 3526 3527 locktorture.acq_writer_lim= [KNL] 3528 Set the time limit in jiffies for a lock 3529 acquisition. Acquisitions exceeding this limit 3530 will result in a splat once they do complete. 3531 3532 locktorture.bind_readers= [KNL] 3533 Specify the list of CPUs to which the readers are 3534 to be bound. 3535 3536 locktorture.bind_writers= [KNL] 3537 Specify the list of CPUs to which the writers are 3538 to be bound. 3539 3540 locktorture.call_rcu_chains= [KNL] 3541 Specify the number of self-propagating call_rcu() 3542 chains to set up. These are used to ensure that 3543 there is a high probability of an RCU grace period 3544 in progress at any given time. Defaults to 0, 3545 which disables these call_rcu() chains. 3546 3547 locktorture.long_hold= [KNL] 3548 Specify the duration in milliseconds for the 3549 occasional long-duration lock hold time. Defaults 3550 to 100 milliseconds. Select 0 to disable. 3551 3552 locktorture.nested_locks= [KNL] 3553 Specify the maximum lock nesting depth that 3554 locktorture is to exercise, up to a limit of 8 3555 (MAX_NESTED_LOCKS). Specify zero to disable. 3556 Note that this parameter is ineffective on types 3557 of locks that do not support nested acquisition. 3558 3559 locktorture.nreaders_stress= [KNL] 3560 Set the number of locking read-acquisition kthreads. 3561 Defaults to being automatically set based on the 3562 number of online CPUs. 3563 3564 locktorture.nwriters_stress= [KNL] 3565 Set the number of locking write-acquisition kthreads. 3566 3567 locktorture.onoff_holdoff= [KNL] 3568 Set time (s) after boot for CPU-hotplug testing. 3569 3570 locktorture.onoff_interval= [KNL] 3571 Set time (s) between CPU-hotplug operations, or 3572 zero to disable CPU-hotplug testing. 3573 3574 locktorture.rt_boost= [KNL] 3575 Do periodic testing of real-time lock priority 3576 boosting. Select 0 to disable, 1 to boost 3577 only rt_mutex, and 2 to boost unconditionally. 3578 Defaults to 2, which might seem to be an 3579 odd choice, but which should be harmless for 3580 non-real-time spinlocks, due to their disabling 3581 of preemption. Note that non-realtime mutexes 3582 disable boosting. 3583 3584 locktorture.rt_boost_factor= [KNL] 3585 Number that determines how often and for how 3586 long priority boosting is exercised. This is 3587 scaled down by the number of writers, so that the 3588 number of boosts per unit time remains roughly 3589 constant as the number of writers increases. 3590 On the other hand, the duration of each boost 3591 increases with the number of writers. 3592 3593 locktorture.shuffle_interval= [KNL] 3594 Set task-shuffle interval (jiffies). Shuffling 3595 tasks allows some CPUs to go into dyntick-idle 3596 mode during the locktorture test. 3597 3598 locktorture.shutdown_secs= [KNL] 3599 Set time (s) after boot system shutdown. This 3600 is useful for hands-off automated testing. 3601 3602 locktorture.stat_interval= [KNL] 3603 Time (s) between statistics printk()s. 3604 3605 locktorture.stutter= [KNL] 3606 Time (s) to stutter testing, for example, 3607 specifying five seconds causes the test to run for 3608 five seconds, wait for five seconds, and so on. 3609 This tests the locking primitive's ability to 3610 transition abruptly to and from idle. 3611 3612 locktorture.torture_type= [KNL] 3613 Specify the locking implementation to test. 3614 3615 locktorture.verbose= [KNL] 3616 Enable additional printk() statements. 3617 3618 locktorture.writer_fifo= [KNL] 3619 Run the write-side locktorture kthreads at 3620 sched_set_fifo() real-time priority. 3621 3622 logibm.irq= [HW,MOUSE] Logitech Bus Mouse Driver 3623 Format: <irq> 3624 3625 loglevel= [KNL,EARLY] 3626 All Kernel Messages with a loglevel smaller than the 3627 console loglevel will be printed to the console. It can 3628 also be changed with klogd or other programs. The 3629 loglevels are defined as follows: 3630 3631 0 (KERN_EMERG) system is unusable 3632 1 (KERN_ALERT) action must be taken immediately 3633 2 (KERN_CRIT) critical conditions 3634 3 (KERN_ERR) error conditions 3635 4 (KERN_WARNING) warning conditions 3636 5 (KERN_NOTICE) normal but significant condition 3637 6 (KERN_INFO) informational 3638 7 (KERN_DEBUG) debug-level messages 3639 3640 log_buf_len=n[KMG] [KNL,EARLY] 3641 Sets the size of the printk ring buffer, in bytes. 3642 n must be a power of two and greater than the 3643 minimal size. The minimal size is defined by 3644 LOG_BUF_SHIFT kernel config parameter. There 3645 is also CONFIG_LOG_CPU_MAX_BUF_SHIFT config 3646 parameter that allows to increase the default size 3647 depending on the number of CPUs. See init/Kconfig 3648 for more details. 3649 3650 logo.nologo [FB] Disables display of the built-in Linux logo. 3651 This may be used to provide more screen space for 3652 kernel log messages and is useful when debugging 3653 kernel boot problems. 3654 3655 lp=0 [LP] Specify parallel ports to use, e.g, 3656 lp=port[,port...] lp=none,parport0 (lp0 not configured, lp1 uses 3657 lp=reset first parallel port). 'lp=0' disables the 3658 lp=auto printer driver. 'lp=reset' (which can be 3659 specified in addition to the ports) causes 3660 attached printers to be reset. Using 3661 lp=port1,port2,... specifies the parallel ports 3662 to associate lp devices with, starting with 3663 lp0. A port specification may be 'none' to skip 3664 that lp device, or a parport name such as 3665 'parport0'. Specifying 'lp=auto' instead of a 3666 port specification list means that device IDs 3667 from each port should be examined, to see if 3668 an IEEE 1284-compliant printer is attached; if 3669 so, the driver will manage that printer. 3670 See also header of drivers/char/lp.c. 3671 3672 lpj=n [KNL] 3673 Sets loops_per_jiffy to given constant, thus avoiding 3674 time-consuming boot-time autodetection (up to 250 ms per 3675 CPU). 0 enables autodetection (default). To determine 3676 the correct value for your kernel, boot with normal 3677 autodetection and see what value is printed. Note that 3678 on SMP systems the preset will be applied to all CPUs, 3679 which is likely to cause problems if your CPUs need 3680 significantly divergent settings. An incorrect value 3681 will cause delays in the kernel to be wrong, leading to 3682 unpredictable I/O errors and other breakage. Although 3683 unlikely, in the extreme case this might damage your 3684 hardware. 3685 3686 lsm.debug [SECURITY] Enable LSM initialization debugging output. 3687 3688 lsm=lsm1,...,lsmN 3689 [SECURITY] Choose order of LSM initialization. This 3690 overrides CONFIG_LSM, and the "security=" parameter. 3691 3692 machtype= [Loongson] Share the same kernel image file between 3693 different yeeloong laptops. 3694 Example: machtype=lemote-yeeloong-2f-7inch 3695 3696 maxcpus= [SMP,EARLY] Maximum number of processors that an SMP kernel 3697 will bring up during bootup. maxcpus=n : n >= 0 limits 3698 the kernel to bring up 'n' processors. Surely after 3699 bootup you can bring up the other plugged cpu by executing 3700 "echo 1 > /sys/devices/system/cpu/cpuX/online". So maxcpus 3701 only takes effect during system bootup. 3702 While n=0 is a special case, it is equivalent to "nosmp", 3703 which also disables the IO APIC. 3704 3705 max_loop= [LOOP] The number of loop block devices that get 3706 (loop.max_loop) unconditionally pre-created at init time. The default 3707 number is configured by BLK_DEV_LOOP_MIN_COUNT. Instead 3708 of statically allocating a predefined number, loop 3709 devices can be requested on-demand with the 3710 /dev/loop-control interface. 3711 3712 mce= [X86-{32,64}] 3713 3714 Please see Documentation/arch/x86/x86_64/machinecheck.rst for sysfs runtime tunables. 3715 3716 off 3717 disable machine check 3718 3719 no_cmci 3720 disable CMCI(Corrected Machine Check Interrupt) that 3721 Intel processor supports. Usually this disablement is 3722 not recommended, but it might be handy if your 3723 hardware is misbehaving. 3724 3725 Note that you'll get more problems without CMCI than 3726 with due to the shared banks, i.e. you might get 3727 duplicated error logs. 3728 3729 dont_log_ce 3730 don't make logs for corrected errors. All events 3731 reported as corrected are silently cleared by OS. This 3732 option will be useful if you have no interest in any 3733 of corrected errors. 3734 3735 ignore_ce 3736 disable features for corrected errors, e.g. 3737 polling timer and CMCI. All events reported as 3738 corrected are not cleared by OS and remained in its 3739 error banks. 3740 3741 Usually this disablement is not recommended, however 3742 if there is an agent checking/clearing corrected 3743 errors (e.g. BIOS or hardware monitoring 3744 applications), conflicting with OS's error handling, 3745 and you cannot deactivate the agent, then this option 3746 will be a help. 3747 3748 no_lmce 3749 do not opt-in to Local MCE delivery. Use legacy method 3750 to broadcast MCEs. 3751 3752 bootlog 3753 enable logging of machine checks left over from 3754 booting. Disabled by default on AMD Fam10h and older 3755 because some BIOS leave bogus ones. 3756 3757 If your BIOS doesn't do that it's a good idea to 3758 enable though to make sure you log even machine check 3759 events that result in a reboot. On Intel systems it is 3760 enabled by default. 3761 3762 nobootlog 3763 disable boot machine check logging. 3764 3765 monarchtimeout (number) 3766 sets the time in us to wait for other CPUs on machine 3767 checks. 0 to disable. 3768 3769 bios_cmci_threshold 3770 don't overwrite the bios-set CMCI threshold. This boot 3771 option prevents Linux from overwriting the CMCI 3772 threshold set by the bios. Without this option, Linux 3773 always sets the CMCI threshold to 1. Enabling this may 3774 make memory predictive failure analysis less effective 3775 if the bios sets thresholds for memory errors since we 3776 will not see details for all errors. 3777 3778 recovery 3779 force-enable recoverable machine check code paths 3780 3781 Everything else is in sysfs now. 3782 3783 3784 md= [HW] RAID subsystems devices and level 3785 See Documentation/admin-guide/md.rst. 3786 3787 mdacon= [MDA] 3788 Format: <first>,<last> 3789 Specifies range of consoles to be captured by the MDA. 3790 3791 mds= [X86,INTEL,EARLY] 3792 Control mitigation for the Micro-architectural Data 3793 Sampling (MDS) vulnerability. 3794 3795 Certain CPUs are vulnerable to an exploit against CPU 3796 internal buffers which can forward information to a 3797 disclosure gadget under certain conditions. 3798 3799 In vulnerable processors, the speculatively 3800 forwarded data can be used in a cache side channel 3801 attack, to access data to which the attacker does 3802 not have direct access. 3803 3804 This parameter controls the MDS mitigation. The 3805 options are: 3806 3807 full - Enable MDS mitigation on vulnerable CPUs 3808 full,nosmt - Enable MDS mitigation and disable 3809 SMT on vulnerable CPUs 3810 off - Unconditionally disable MDS mitigation 3811 3812 On TAA-affected machines, mds=off can be prevented by 3813 an active TAA mitigation as both vulnerabilities are 3814 mitigated with the same mechanism so in order to disable 3815 this mitigation, you need to specify tsx_async_abort=off 3816 too. 3817 3818 Not specifying this option is equivalent to 3819 mds=full. 3820 3821 For details see: Documentation/admin-guide/hw-vuln/mds.rst 3822 3823 mem=nn[KMG] [HEXAGON,EARLY] Set the memory size. 3824 Must be specified, otherwise memory size will be 0. 3825 3826 mem=nn[KMG] [KNL,BOOT,EARLY] Force usage of a specific amount 3827 of memory Amount of memory to be used in cases 3828 as follows: 3829 3830 1 for test; 3831 2 when the kernel is not able to see the whole system memory; 3832 3 memory that lies after 'mem=' boundary is excluded from 3833 the hypervisor, then assigned to KVM guests. 3834 4 to limit the memory available for kdump kernel. 3835 3836 [ARC,MICROBLAZE] - the limit applies only to low memory, 3837 high memory is not affected. 3838 3839 [ARM64] - only limits memory covered by the linear 3840 mapping. The NOMAP regions are not affected. 3841 3842 [X86] Work as limiting max address. Use together 3843 with memmap= to avoid physical address space collisions. 3844 Without memmap= PCI devices could be placed at addresses 3845 belonging to unused RAM. 3846 3847 Note that this only takes effects during boot time since 3848 in above case 3, memory may need be hot added after boot 3849 if system memory of hypervisor is not sufficient. 3850 3851 mem=nn[KMG]@ss[KMG] 3852 [ARM,MIPS,EARLY] - override the memory layout 3853 reported by firmware. 3854 Define a memory region of size nn[KMG] starting at 3855 ss[KMG]. 3856 Multiple different regions can be specified with 3857 multiple mem= parameters on the command line. 3858 3859 mem=nopentium [BUGS=X86-32] Disable usage of 4MB pages for kernel 3860 memory. 3861 3862 memblock=debug [KNL,EARLY] Enable memblock debug messages. 3863 3864 memchunk=nn[KMG] 3865 [KNL,SH] Allow user to override the default size for 3866 per-device physically contiguous DMA buffers. 3867 3868 memhp_default_state=online/offline/online_kernel/online_movable 3869 [KNL] Set the initial state for the memory hotplug 3870 onlining policy. If not specified, the default value is 3871 set according to the 3872 CONFIG_MHP_DEFAULT_ONLINE_TYPE kernel config 3873 options. 3874 See Documentation/admin-guide/mm/memory-hotplug.rst. 3875 3876 memmap=exactmap [KNL,X86,EARLY] Enable setting of an exact 3877 E820 memory map, as specified by the user. 3878 Such memmap=exactmap lines can be constructed based on 3879 BIOS output or other requirements. See the memmap=nn@ss 3880 option description. 3881 3882 memmap=nn[KMG]@ss[KMG] 3883 [KNL, X86,MIPS,XTENSA,EARLY] Force usage of a specific region of memory. 3884 Region of memory to be used is from ss to ss+nn. 3885 If @ss[KMG] is omitted, it is equivalent to mem=nn[KMG], 3886 which limits max address to nn[KMG]. 3887 Multiple different regions can be specified, 3888 comma delimited. 3889 Example: 3890 memmap=100M@2G,100M#3G,1G!1024G 3891 3892 memmap=nn[KMG]#ss[KMG] 3893 [KNL,ACPI,EARLY] Mark specific memory as ACPI data. 3894 Region of memory to be marked is from ss to ss+nn. 3895 3896 memmap=nn[KMG]$ss[KMG] 3897 [KNL,ACPI,EARLY] Mark specific memory as reserved. 3898 Region of memory to be reserved is from ss to ss+nn. 3899 Example: Exclude memory from 0x18690000-0x1869ffff 3900 memmap=64K$0x18690000 3901 or 3902 memmap=0x10000$0x18690000 3903 Some bootloaders may need an escape character before '$', 3904 like Grub2, otherwise '$' and the following number 3905 will be eaten. 3906 3907 memmap=nn[KMG]!ss[KMG,EARLY] 3908 [KNL,X86] Mark specific memory as protected. 3909 Region of memory to be used, from ss to ss+nn. 3910 The memory region may be marked as e820 type 12 (0xc) 3911 and is NVDIMM or ADR memory. 3912 3913 memmap=<size>%<offset>-<oldtype>+<newtype> 3914 [KNL,ACPI,EARLY] Convert memory within the specified region 3915 from <oldtype> to <newtype>. If "-<oldtype>" is left 3916 out, the whole region will be marked as <newtype>, 3917 even if previously unavailable. If "+<newtype>" is left 3918 out, matching memory will be removed. Types are 3919 specified as e820 types, e.g., 1 = RAM, 2 = reserved, 3920 3 = ACPI, 12 = PRAM. 3921 3922 memory_corruption_check=0/1 [X86,EARLY] 3923 Some BIOSes seem to corrupt the first 64k of 3924 memory when doing things like suspend/resume. 3925 Setting this option will scan the memory 3926 looking for corruption. Enabling this will 3927 both detect corruption and prevent the kernel 3928 from using the memory being corrupted. 3929 However, it's intended as a diagnostic tool; if 3930 repeatable BIOS-originated corruption always 3931 affects the same memory, you can use memmap= 3932 to prevent the kernel from using that memory. 3933 3934 memory_corruption_check_size=size [X86,EARLY] 3935 By default it checks for corruption in the low 3936 64k, making this memory unavailable for normal 3937 use. Use this parameter to scan for 3938 corruption in more or less memory. 3939 3940 memory_corruption_check_period=seconds [X86,EARLY] 3941 By default it checks for corruption every 60 3942 seconds. Use this parameter to check at some 3943 other rate. 0 disables periodic checking. 3944 3945 memory_hotplug.memmap_on_memory 3946 [KNL,X86,ARM] Boolean flag to enable this feature. 3947 Format: {on | off (default)} 3948 When enabled, runtime hotplugged memory will 3949 allocate its internal metadata (struct pages, 3950 those vmemmap pages cannot be optimized even 3951 if hugetlb_free_vmemmap is enabled) from the 3952 hotadded memory which will allow to hotadd a 3953 lot of memory without requiring additional 3954 memory to do so. 3955 This feature is disabled by default because it 3956 has some implication on large (e.g. GB) 3957 allocations in some configurations (e.g. small 3958 memory blocks). 3959 The state of the flag can be read in 3960 /sys/module/memory_hotplug/parameters/memmap_on_memory. 3961 Note that even when enabled, there are a few cases where 3962 the feature is not effective. 3963 3964 memtest= [KNL,X86,ARM,M68K,PPC,RISCV,EARLY] Enable memtest 3965 Format: <integer> 3966 default : 0 <disable> 3967 Specifies the number of memtest passes to be 3968 performed. Each pass selects another test 3969 pattern from a given set of patterns. Memtest 3970 fills the memory with this pattern, validates 3971 memory contents and reserves bad memory 3972 regions that are detected. 3973 3974 mem_encrypt= [X86-64] AMD Secure Memory Encryption (SME) control 3975 Valid arguments: on, off 3976 Default: off 3977 mem_encrypt=on: Activate SME 3978 mem_encrypt=off: Do not activate SME 3979 3980 Refer to Documentation/virt/kvm/x86/amd-memory-encryption.rst 3981 for details on when memory encryption can be activated. 3982 3983 mem_sleep_default= [SUSPEND] Default system suspend mode: 3984 s2idle - Suspend-To-Idle 3985 shallow - Power-On Suspend or equivalent (if supported) 3986 deep - Suspend-To-RAM or equivalent (if supported) 3987 See Documentation/admin-guide/pm/sleep-states.rst. 3988 3989 mfgptfix [X86-32] Fix MFGPT timers on AMD Geode platforms when 3990 the BIOS has incorrectly applied a workaround. TinyBIOS 3991 version 0.98 is known to be affected, 0.99 fixes the 3992 problem by letting the user disable the workaround. 3993 3994 mga= [HW,DRM] 3995 3996 microcode= [X86] Control the behavior of the microcode loader. 3997 Available options, comma separated: 3998 3999 base_rev=X - with <X> with format: <u32> 4000 Set the base microcode revision of each thread when in 4001 debug mode. 4002 4003 dis_ucode_ldr: disable the microcode loader 4004 4005 force_minrev: 4006 Enable or disable the microcode minimal revision 4007 enforcement for the runtime microcode loader. 4008 4009 mini2440= [ARM,HW,KNL] 4010 Format:[0..2][b][c][t] 4011 Default: "0tb" 4012 MINI2440 configuration specification: 4013 0 - The attached screen is the 3.5" TFT 4014 1 - The attached screen is the 7" TFT 4015 2 - The VGA Shield is attached (1024x768) 4016 Leaving out the screen size parameter will not load 4017 the TFT driver, and the framebuffer will be left 4018 unconfigured. 4019 b - Enable backlight. The TFT backlight pin will be 4020 linked to the kernel VESA blanking code and a GPIO 4021 LED. This parameter is not necessary when using the 4022 VGA shield. 4023 c - Enable the s3c camera interface. 4024 t - Reserved for enabling touchscreen support. The 4025 touchscreen support is not enabled in the mainstream 4026 kernel as of 2.6.30, a preliminary port can be found 4027 in the "bleeding edge" mini2440 support kernel at 4028 https://repo.or.cz/w/linux-2.6/mini2440.git 4029 4030 mitigations= 4031 [X86,PPC,S390,ARM64,EARLY] Control optional mitigations for 4032 CPU vulnerabilities. This is a set of curated, 4033 arch-independent options, each of which is an 4034 aggregation of existing arch-specific options. 4035 4036 Note, "mitigations" is supported if and only if the 4037 kernel was built with CPU_MITIGATIONS=y. 4038 4039 off 4040 Disable all optional CPU mitigations. This 4041 improves system performance, but it may also 4042 expose users to several CPU vulnerabilities. 4043 Equivalent to: if nokaslr then kpti=0 [ARM64] 4044 gather_data_sampling=off [X86] 4045 indirect_target_selection=off [X86] 4046 kvm.nx_huge_pages=off [X86] 4047 l1tf=off [X86] 4048 mds=off [X86] 4049 mmio_stale_data=off [X86] 4050 no_entry_flush [PPC] 4051 no_uaccess_flush [PPC] 4052 nobp=0 [S390] 4053 nopti [X86,PPC] 4054 nospectre_bhb [ARM64] 4055 nospectre_v1 [X86,PPC] 4056 nospectre_v2 [X86,PPC,S390,ARM64] 4057 reg_file_data_sampling=off [X86] 4058 retbleed=off [X86] 4059 spec_rstack_overflow=off [X86] 4060 spec_store_bypass_disable=off [X86,PPC] 4061 spectre_bhi=off [X86] 4062 spectre_v2_user=off [X86] 4063 srbds=off [X86,INTEL] 4064 ssbd=force-off [ARM64] 4065 tsa=off [X86,AMD] 4066 tsx_async_abort=off [X86] 4067 vmscape=off [X86] 4068 4069 Exceptions: 4070 This does not have any effect on 4071 kvm.nx_huge_pages when 4072 kvm.nx_huge_pages=force. 4073 4074 auto (default) 4075 Mitigate all CPU vulnerabilities, but leave SMT 4076 enabled, even if it's vulnerable. This is for 4077 users who don't want to be surprised by SMT 4078 getting disabled across kernel upgrades, or who 4079 have other ways of avoiding SMT-based attacks. 4080 Equivalent to: (default behavior) 4081 4082 auto,nosmt 4083 Mitigate all CPU vulnerabilities, disabling SMT 4084 if needed. This is for users who always want to 4085 be fully mitigated, even if it means losing SMT. 4086 Equivalent to: l1tf=flush,nosmt [X86] 4087 mds=full,nosmt [X86] 4088 tsx_async_abort=full,nosmt [X86] 4089 mmio_stale_data=full,nosmt [X86] 4090 retbleed=auto,nosmt [X86] 4091 4092 [X86] After one of the above options, additionally 4093 supports attack-vector based controls as documented in 4094 Documentation/admin-guide/hw-vuln/attack_vector_controls.rst 4095 4096 mminit_loglevel= 4097 [KNL,EARLY] When CONFIG_DEBUG_MEMORY_INIT is set, this 4098 parameter allows control of the logging verbosity for 4099 the additional memory initialisation checks. A value 4100 of 0 disables mminit logging and a level of 4 will 4101 log everything. Information is printed at KERN_DEBUG 4102 so loglevel=8 may also need to be specified. 4103 4104 mmio_stale_data= 4105 [X86,INTEL,EARLY] Control mitigation for the Processor 4106 MMIO Stale Data vulnerabilities. 4107 4108 Processor MMIO Stale Data is a class of 4109 vulnerabilities that may expose data after an MMIO 4110 operation. Exposed data could originate or end in 4111 the same CPU buffers as affected by MDS and TAA. 4112 Therefore, similar to MDS and TAA, the mitigation 4113 is to clear the affected CPU buffers. 4114 4115 This parameter controls the mitigation. The 4116 options are: 4117 4118 full - Enable mitigation on vulnerable CPUs 4119 4120 full,nosmt - Enable mitigation and disable SMT on 4121 vulnerable CPUs. 4122 4123 off - Unconditionally disable mitigation 4124 4125 On MDS or TAA affected machines, 4126 mmio_stale_data=off can be prevented by an active 4127 MDS or TAA mitigation as these vulnerabilities are 4128 mitigated with the same mechanism so in order to 4129 disable this mitigation, you need to specify 4130 mds=off and tsx_async_abort=off too. 4131 4132 Not specifying this option is equivalent to 4133 mmio_stale_data=full. 4134 4135 For details see: 4136 Documentation/admin-guide/hw-vuln/processor_mmio_stale_data.rst 4137 4138 <module>.async_probe[=<bool>] [KNL] 4139 If no <bool> value is specified or if the value 4140 specified is not a valid <bool>, enable asynchronous 4141 probe on this module. Otherwise, enable/disable 4142 asynchronous probe on this module as indicated by the 4143 <bool> value. See also: module.async_probe 4144 4145 module.async_probe=<bool> 4146 [KNL] When set to true, modules will use async probing 4147 by default. To enable/disable async probing for a 4148 specific module, use the module specific control that 4149 is documented under <module>.async_probe. When both 4150 module.async_probe and <module>.async_probe are 4151 specified, <module>.async_probe takes precedence for 4152 the specific module. 4153 4154 module.enable_dups_trace 4155 [KNL] When CONFIG_MODULE_DEBUG_AUTOLOAD_DUPS is set, 4156 this means that duplicate request_module() calls will 4157 trigger a WARN_ON() instead of a pr_warn(). Note that 4158 if MODULE_DEBUG_AUTOLOAD_DUPS_TRACE is set, WARN_ON()s 4159 will always be issued and this option does nothing. 4160 module.sig_enforce 4161 [KNL] When CONFIG_MODULE_SIG is set, this means that 4162 modules without (valid) signatures will fail to load. 4163 Note that if CONFIG_MODULE_SIG_FORCE is set, that 4164 is always true, so this option does nothing. 4165 4166 module_blacklist= [KNL] Do not load a comma-separated list of 4167 modules. Useful for debugging problem modules. 4168 4169 mousedev.tap_time= 4170 [MOUSE] Maximum time between finger touching and 4171 leaving touchpad surface for touch to be considered 4172 a tap and be reported as a left button click (for 4173 touchpads working in absolute mode only). 4174 Format: <msecs> 4175 mousedev.xres= [MOUSE] Horizontal screen resolution, used for devices 4176 reporting absolute coordinates, such as tablets 4177 mousedev.yres= [MOUSE] Vertical screen resolution, used for devices 4178 reporting absolute coordinates, such as tablets 4179 4180 movablecore= [KNL,X86,PPC,EARLY] 4181 Format: nn[KMGTPE] | nn% 4182 This parameter is the complement to kernelcore=, it 4183 specifies the amount of memory used for migratable 4184 allocations. If both kernelcore and movablecore is 4185 specified, then kernelcore will be at *least* the 4186 specified value but may be more. If movablecore on its 4187 own is specified, the administrator must be careful 4188 that the amount of memory usable for all allocations 4189 is not too small. 4190 4191 movable_node [KNL,EARLY] Boot-time switch to make hotplugable memory 4192 NUMA nodes to be movable. This means that the memory 4193 of such nodes will be usable only for movable 4194 allocations which rules out almost all kernel 4195 allocations. Use with caution! 4196 4197 MTD_Partition= [MTD] 4198 Format: <name>,<region-number>,<size>,<offset> 4199 4200 MTD_Region= [MTD] Format: 4201 <name>,<region-number>[,<base>,<size>,<buswidth>,<altbuswidth>] 4202 4203 mtdparts= [MTD] 4204 See drivers/mtd/parsers/cmdlinepart.c 4205 4206 mtouchusb.raw_coordinates= 4207 [HW] Make the MicroTouch USB driver use raw coordinates 4208 ('y', default) or cooked coordinates ('n') 4209 4210 mtrr=debug [X86,EARLY] 4211 Enable printing debug information related to MTRR 4212 registers at boot time. 4213 4214 mtrr_chunk_size=nn[KMG,X86,EARLY] 4215 used for mtrr cleanup. It is largest continuous chunk 4216 that could hold holes aka. UC entries. 4217 4218 mtrr_gran_size=nn[KMG,X86,EARLY] 4219 Used for mtrr cleanup. It is granularity of mtrr block. 4220 Default is 1. 4221 Large value could prevent small alignment from 4222 using up MTRRs. 4223 4224 mtrr_spare_reg_nr=n [X86,EARLY] 4225 Format: <integer> 4226 Range: 0,7 : spare reg number 4227 Default : 1 4228 Used for mtrr cleanup. It is spare mtrr entries number. 4229 Set to 2 or more if your graphical card needs more. 4230 4231 multitce=off [PPC] This parameter disables the use of the pSeries 4232 firmware feature for updating multiple TCE entries 4233 at a time. 4234 4235 n2= [NET] SDL Inc. RISCom/N2 synchronous serial card 4236 4237 netdev= [NET] NE2000 ISA network devices parameters 4238 Format: <irq>,<io>,<mem_start>,<mem_end>,<name> 4239 4240 netpoll.carrier_timeout= 4241 [NET] Specifies amount of time (in seconds) that 4242 netpoll should wait for a carrier. By default netpoll 4243 waits 4 seconds. 4244 4245 nf_conntrack.acct= 4246 [NETFILTER] Enable connection tracking flow accounting 4247 0 to disable accounting 4248 1 to enable accounting 4249 Default value is 0. 4250 4251 nfs.cache_getent= 4252 [NFS] sets the pathname to the program which is used 4253 to update the NFS client cache entries. 4254 4255 nfs.cache_getent_timeout= 4256 [NFS] sets the timeout after which an attempt to 4257 update a cache entry is deemed to have failed. 4258 4259 nfs.callback_nr_threads= 4260 [NFSv4] set the total number of threads that the 4261 NFS client will assign to service NFSv4 callback 4262 requests. 4263 4264 nfs.callback_tcpport= 4265 [NFS] set the TCP port on which the NFSv4 callback 4266 channel should listen. 4267 4268 nfs.delay_retrans= 4269 [NFS] specifies the number of times the NFSv4 client 4270 retries the request before returning an EAGAIN error, 4271 after a reply of NFS4ERR_DELAY from the server. 4272 Only applies if the softerr mount option is enabled, 4273 and the specified value is >= 0. 4274 4275 nfs.enable_ino64= 4276 [NFS] enable 64-bit inode numbers. 4277 If zero, the NFS client will fake up a 32-bit inode 4278 number for the readdir() and stat() syscalls instead 4279 of returning the full 64-bit number. 4280 The default is to return 64-bit inode numbers. 4281 4282 nfs.idmap_cache_timeout= 4283 [NFS] set the maximum lifetime for idmapper cache 4284 entries. 4285 4286 nfs.max_session_cb_slots= 4287 [NFSv4.1] Sets the maximum number of session 4288 slots the client will assign to the callback 4289 channel. This determines the maximum number of 4290 callbacks the client will process in parallel for 4291 a particular server. 4292 4293 nfs.max_session_slots= 4294 [NFSv4.1] Sets the maximum number of session slots 4295 the client will attempt to negotiate with the server. 4296 This limits the number of simultaneous RPC requests 4297 that the client can send to the NFSv4.1 server. 4298 Note that there is little point in setting this 4299 value higher than the max_tcp_slot_table_limit. 4300 4301 nfs.nfs4_disable_idmapping= 4302 [NFSv4] When set to the default of '1', this option 4303 ensures that both the RPC level authentication 4304 scheme and the NFS level operations agree to use 4305 numeric uids/gids if the mount is using the 4306 'sec=sys' security flavour. In effect it is 4307 disabling idmapping, which can make migration from 4308 legacy NFSv2/v3 systems to NFSv4 easier. 4309 Servers that do not support this mode of operation 4310 will be autodetected by the client, and it will fall 4311 back to using the idmapper. 4312 To turn off this behaviour, set the value to '0'. 4313 4314 nfs.nfs4_unique_id= 4315 [NFS4] Specify an additional fixed unique ident- 4316 ification string that NFSv4 clients can insert into 4317 their nfs_client_id4 string. This is typically a 4318 UUID that is generated at system install time. 4319 4320 nfs.recover_lost_locks= 4321 [NFSv4] Attempt to recover locks that were lost due 4322 to a lease timeout on the server. Please note that 4323 doing this risks data corruption, since there are 4324 no guarantees that the file will remain unchanged 4325 after the locks are lost. 4326 If you want to enable the kernel legacy behaviour of 4327 attempting to recover these locks, then set this 4328 parameter to '1'. 4329 The default parameter value of '0' causes the kernel 4330 not to attempt recovery of lost locks. 4331 4332 nfs.send_implementation_id= 4333 [NFSv4.1] Send client implementation identification 4334 information in exchange_id requests. 4335 If zero, no implementation identification information 4336 will be sent. 4337 The default is to send the implementation identification 4338 information. 4339 4340 nfs4.layoutstats_timer= 4341 [NFSv4.2] Change the rate at which the kernel sends 4342 layoutstats to the pNFS metadata server. 4343 4344 Setting this to value to 0 causes the kernel to use 4345 whatever value is the default set by the layout 4346 driver. A non-zero value sets the minimum interval 4347 in seconds between layoutstats transmissions. 4348 4349 nfsd.inter_copy_offload_enable= 4350 [NFSv4.2] When set to 1, the server will support 4351 server-to-server copies for which this server is 4352 the destination of the copy. 4353 4354 nfsd.nfs4_disable_idmapping= 4355 [NFSv4] When set to the default of '1', the NFSv4 4356 server will return only numeric uids and gids to 4357 clients using auth_sys, and will accept numeric uids 4358 and gids from such clients. This is intended to ease 4359 migration from NFSv2/v3. 4360 4361 nfsd.nfsd4_ssc_umount_timeout= 4362 [NFSv4.2] When used as the destination of a 4363 server-to-server copy, knfsd temporarily mounts 4364 the source server. It caches the mount in case 4365 it will be needed again, and discards it if not 4366 used for the number of milliseconds specified by 4367 this parameter. 4368 4369 nfsaddrs= [NFS] Deprecated. Use ip= instead. 4370 See Documentation/admin-guide/nfs/nfsroot.rst. 4371 4372 nfsroot= [NFS] nfs root filesystem for disk-less boxes. 4373 See Documentation/admin-guide/nfs/nfsroot.rst. 4374 4375 nfsrootdebug [NFS] enable nfsroot debugging messages. 4376 See Documentation/admin-guide/nfs/nfsroot.rst. 4377 4378 nmi_backtrace.backtrace_idle [KNL] 4379 Dump stacks even of idle CPUs in response to an 4380 NMI stack-backtrace request. 4381 4382 nmi_debug= [KNL,SH] Specify one or more actions to take 4383 when a NMI is triggered. 4384 Format: [state][,regs][,debounce][,die] 4385 4386 nmi_watchdog= [KNL,BUGS=X86] Debugging features for SMP kernels 4387 Format: [panic,][nopanic,][rNNN,][num] 4388 Valid num: 0 or 1 4389 0 - turn hardlockup detector in nmi_watchdog off 4390 1 - turn hardlockup detector in nmi_watchdog on 4391 rNNN - configure the watchdog with raw perf event 0xNNN 4392 4393 When panic is specified, panic when an NMI watchdog 4394 timeout occurs (or 'nopanic' to not panic on an NMI 4395 watchdog, if CONFIG_BOOTPARAM_HARDLOCKUP_PANIC is set) 4396 To disable both hard and soft lockup detectors, 4397 please see 'nowatchdog'. 4398 This is useful when you use a panic=... timeout and 4399 need the box quickly up again. 4400 4401 These settings can be accessed at runtime via 4402 the nmi_watchdog and hardlockup_panic sysctls. 4403 4404 no387 [BUGS=X86-32] Tells the kernel to use the 387 maths 4405 emulation library even if a 387 maths coprocessor 4406 is present. 4407 4408 no4lvl [RISCV,EARLY] Disable 4-level and 5-level paging modes. 4409 Forces kernel to use 3-level paging instead. 4410 4411 no5lvl [X86-64,RISCV,EARLY] Disable 5-level paging mode. Forces 4412 kernel to use 4-level paging instead. 4413 4414 noalign [KNL,ARM] 4415 4416 noapic [SMP,APIC,EARLY] Tells the kernel to not make use of any 4417 IOAPICs that may be present in the system. 4418 4419 noapictimer [APIC,X86] Don't set up the APIC timer 4420 4421 noautogroup Disable scheduler automatic task group creation. 4422 4423 nocache [ARM,EARLY] 4424 4425 no_console_suspend 4426 [HW] Never suspend the console 4427 Disable suspending of consoles during suspend and 4428 hibernate operations. Once disabled, debugging 4429 messages can reach various consoles while the rest 4430 of the system is being put to sleep (ie, while 4431 debugging driver suspend/resume hooks). This may 4432 not work reliably with all consoles, but is known 4433 to work with serial and VGA consoles. 4434 To facilitate more flexible debugging, we also add 4435 console_suspend, a printk module parameter to control 4436 it. Users could use console_suspend (usually 4437 /sys/module/printk/parameters/console_suspend) to 4438 turn on/off it dynamically. 4439 4440 no_debug_objects 4441 [KNL,EARLY] Disable object debugging 4442 4443 nodsp [SH] Disable hardware DSP at boot time. 4444 4445 noefi [EFI,EARLY] Disable EFI runtime services support. 4446 4447 no_entry_flush [PPC,EARLY] Don't flush the L1-D cache when entering the kernel. 4448 4449 noexec32 [X86-64] 4450 This affects only 32-bit executables. 4451 noexec32=on: enable non-executable mappings (default) 4452 read doesn't imply executable mappings 4453 noexec32=off: disable non-executable mappings 4454 read implies executable mappings 4455 4456 no_file_caps Tells the kernel not to honor file capabilities. The 4457 only way then for a file to be executed with privilege 4458 is to be setuid root or executed by root. 4459 4460 nofpu [MIPS,SH] Disable hardware FPU at boot time. 4461 4462 nofsgsbase [X86] Disables FSGSBASE instructions. 4463 4464 nofxsr [BUGS=X86-32] Disables x86 floating point extended 4465 register save and restore. The kernel will only save 4466 legacy floating-point registers on task switch. 4467 4468 nogbpages [X86] Do not use GB pages for kernel direct mappings. 4469 4470 no_hash_pointers 4471 [KNL,EARLY] 4472 Alias for "hash_pointers=never". 4473 4474 nohibernate [HIBERNATION] Disable hibernation and resume. 4475 4476 nohlt [ARM,ARM64,MICROBLAZE,MIPS,PPC,RISCV,SH] Forces the kernel to 4477 busy wait in do_idle() and not use the arch_cpu_idle() 4478 implementation; requires CONFIG_GENERIC_IDLE_POLL_SETUP 4479 to be effective. This is useful on platforms where the 4480 sleep(SH) or wfi(ARM,ARM64) instructions do not work 4481 correctly or when doing power measurements to evaluate 4482 the impact of the sleep instructions. This is also 4483 useful when using JTAG debugger. 4484 4485 nohpet [X86] Don't use the HPET timer. 4486 4487 nohugeiomap [KNL,X86,PPC,ARM64,EARLY] Disable kernel huge I/O mappings. 4488 4489 nohugevmalloc [KNL,X86,PPC,ARM64,EARLY] Disable kernel huge vmalloc mappings. 4490 4491 nohz= [KNL] Boottime enable/disable dynamic ticks 4492 Valid arguments: on, off 4493 Default: on 4494 4495 nohz_full= [KNL,BOOT,SMP,ISOL] 4496 The argument is a cpu list, as described above. 4497 In kernels built with CONFIG_NO_HZ_FULL=y, set 4498 the specified list of CPUs whose tick will be stopped 4499 whenever possible. The boot CPU will be forced outside 4500 the range to maintain the timekeeping. Any CPUs 4501 in this list will have their RCU callbacks offloaded, 4502 just as if they had also been called out in the 4503 rcu_nocbs= boot parameter. 4504 4505 Note that this argument takes precedence over 4506 the CONFIG_RCU_NOCB_CPU_DEFAULT_ALL option. 4507 4508 noinitrd [Deprecated,RAM] Tells the kernel not to load any configured 4509 initial RAM disk. Currently this parameter applies to 4510 initrd only, not to initramfs. But it applies to both 4511 in EFI mode. 4512 4513 nointremap [X86-64,Intel-IOMMU,EARLY] Do not enable interrupt 4514 remapping. 4515 [Deprecated - use intremap=off] 4516 4517 noinvpcid [X86,EARLY] Disable the INVPCID cpu feature. 4518 4519 noiotrap [SH] Disables trapped I/O port accesses. 4520 4521 noirqdebug [X86-32] Disables the code which attempts to detect and 4522 disable unhandled interrupt sources. 4523 4524 noisapnp [ISAPNP] Disables ISA PnP code. 4525 4526 nokaslr [KNL,EARLY] 4527 When CONFIG_RANDOMIZE_BASE is set, this disables 4528 kernel and module base offset ASLR (Address Space 4529 Layout Randomization). 4530 4531 no-kvmapf [X86,KVM,EARLY] Disable paravirtualized asynchronous page 4532 fault handling. 4533 4534 no-kvmclock [X86,KVM,EARLY] Disable paravirtualized KVM clock driver 4535 4536 nolapic [X86-32,APIC,EARLY] Do not enable or use the local APIC. 4537 4538 nolapic_timer [X86-32,APIC,EARLY] Do not use the local APIC timer. 4539 4540 nomce [X86-32] Disable Machine Check Exception 4541 4542 nomfgpt [X86-32] Disable Multi-Function General Purpose 4543 Timer usage (for AMD Geode machines). 4544 4545 nomodeset Disable kernel modesetting. Most systems' firmware 4546 sets up a display mode and provides framebuffer memory 4547 for output. With nomodeset, DRM and fbdev drivers will 4548 not load if they could possibly displace the pre- 4549 initialized output. Only the system framebuffer will 4550 be available for use. The respective drivers will not 4551 perform display-mode changes or accelerated rendering. 4552 4553 Useful as error fallback, or for testing and debugging. 4554 4555 nomodule Disable module load 4556 4557 nonmi_ipi [X86] Disable using NMI IPIs during panic/reboot to 4558 shutdown the other cpus. Instead use the REBOOT_VECTOR 4559 irq. 4560 4561 nopat [X86,EARLY] Disable PAT (page attribute table extension of 4562 pagetables) support. 4563 4564 nopcid [X86-64,EARLY] Disable the PCID cpu feature. 4565 4566 nopku [X86] Disable Memory Protection Keys CPU feature found 4567 in some Intel CPUs. 4568 4569 nopti [X86-64,EARLY] 4570 Equivalent to pti=off 4571 4572 nopv= [X86,XEN,KVM,HYPER_V,VMWARE,EARLY] 4573 Disables the PV optimizations forcing the guest to run 4574 as generic guest with no PV drivers. Currently support 4575 XEN HVM, KVM, HYPER_V and VMWARE guest. 4576 4577 nopvspin [X86,XEN,KVM,EARLY] 4578 Disables the qspinlock slow path using PV optimizations 4579 which allow the hypervisor to 'idle' the guest on lock 4580 contention. 4581 4582 norandmaps Don't use address space randomization. Equivalent to 4583 echo 0 > /proc/sys/kernel/randomize_va_space 4584 4585 noreplace-smp [X86-32,SMP] Don't replace SMP instructions 4586 with UP alternatives 4587 4588 noresume [SWSUSP] Disables resume and restores original swap 4589 space. 4590 4591 no-scroll [VGA] Disables scrollback. 4592 This is required for the Braillex ib80-piezo Braille 4593 reader made by F.H. Papenmeier (Germany). 4594 4595 nosgx [X86-64,SGX,EARLY] Disables Intel SGX kernel support. 4596 4597 nosmap [PPC,EARLY] 4598 Disable SMAP (Supervisor Mode Access Prevention) 4599 even if it is supported by processor. 4600 4601 nosmep [PPC64s,EARLY] 4602 Disable SMEP (Supervisor Mode Execution Prevention) 4603 even if it is supported by processor. 4604 4605 nosmp [SMP,EARLY] Tells an SMP kernel to act as a UP kernel, 4606 and disable the IO APIC. legacy for "maxcpus=0". 4607 4608 nosmt [KNL,MIPS,PPC,EARLY] Disable symmetric multithreading (SMT). 4609 Equivalent to smt=1. 4610 4611 [KNL,LOONGARCH,X86,PPC,S390] Disable symmetric multithreading (SMT). 4612 nosmt=force: Force disable SMT, cannot be undone 4613 via the sysfs control file. 4614 4615 nosoftlockup [KNL] Disable the soft-lockup detector. 4616 4617 nospec_store_bypass_disable 4618 [HW,EARLY] Disable all mitigations for the Speculative 4619 Store Bypass vulnerability 4620 4621 nospectre_bhb [ARM64,EARLY] Disable all mitigations for Spectre-BHB (branch 4622 history injection) vulnerability. System may allow data leaks 4623 with this option. 4624 4625 nospectre_v1 [X86,PPC,EARLY] Disable mitigations for Spectre Variant 1 4626 (bounds check bypass). With this option data leaks are 4627 possible in the system. 4628 4629 nospectre_v2 [X86,PPC_E500,ARM64,EARLY] Disable all mitigations 4630 for the Spectre variant 2 (indirect branch 4631 prediction) vulnerability. System may allow data 4632 leaks with this option. 4633 4634 no-steal-acc [X86,PV_OPS,ARM64,PPC/PSERIES,RISCV,LOONGARCH,EARLY] 4635 Disable paravirtualized steal time accounting. steal time 4636 is computed, but won't influence scheduler behaviour 4637 4638 nosync [HW,M68K] Disables sync negotiation for all devices. 4639 4640 no_timer_check [X86,APIC] Disables the code which tests for broken 4641 timer IRQ sources, i.e., the IO-APIC timer. This can 4642 work around problems with incorrect timer 4643 initialization on some boards. 4644 4645 no_uaccess_flush 4646 [PPC,EARLY] Don't flush the L1-D cache after accessing user data. 4647 4648 novmcoredd [KNL,KDUMP] 4649 Disable device dump. Device dump allows drivers to 4650 append dump data to vmcore so you can collect driver 4651 specified debug info. Drivers can append the data 4652 without any limit and this data is stored in memory, 4653 so this may cause significant memory stress. Disabling 4654 device dump can help save memory but the driver debug 4655 data will be no longer available. This parameter 4656 is only available when CONFIG_PROC_VMCORE_DEVICE_DUMP 4657 is set. 4658 4659 no-vmw-sched-clock 4660 [X86,PV_OPS,EARLY] Disable paravirtualized VMware 4661 scheduler clock and use the default one. 4662 4663 nowatchdog [KNL] Disable both lockup detectors, i.e. 4664 soft-lockup and NMI watchdog (hard-lockup). 4665 4666 nowb [ARM,EARLY] 4667 4668 nox2apic [X86-64,APIC,EARLY] Do not enable x2APIC mode. 4669 4670 NOTE: this parameter will be ignored on systems with the 4671 LEGACY_XAPIC_DISABLED bit set in the 4672 IA32_XAPIC_DISABLE_STATUS MSR. 4673 4674 noxsave [BUGS=X86] Disables x86 extended register state save 4675 and restore using xsave. The kernel will fallback to 4676 enabling legacy floating-point and sse state. 4677 4678 noxsaveopt [X86] Disables xsaveopt used in saving x86 extended 4679 register states. The kernel will fall back to use 4680 xsave to save the states. By using this parameter, 4681 performance of saving the states is degraded because 4682 xsave doesn't support modified optimization while 4683 xsaveopt supports it on xsaveopt enabled systems. 4684 4685 noxsaves [X86] Disables xsaves and xrstors used in saving and 4686 restoring x86 extended register state in compacted 4687 form of xsave area. The kernel will fall back to use 4688 xsaveopt and xrstor to save and restore the states 4689 in standard form of xsave area. By using this 4690 parameter, xsave area per process might occupy more 4691 memory on xsaves enabled systems. 4692 4693 nr_cpus= [SMP,EARLY] Maximum number of processors that an SMP kernel 4694 could support. nr_cpus=n : n >= 1 limits the kernel to 4695 support 'n' processors. It could be larger than the 4696 number of already plugged CPU during bootup, later in 4697 runtime you can physically add extra cpu until it reaches 4698 n. So during boot up some boot time memory for per-cpu 4699 variables need be pre-allocated for later physical cpu 4700 hot plugging. 4701 4702 nr_uarts= [SERIAL] maximum number of UARTs to be registered. 4703 4704 numa=off [KNL, ARM64, PPC, RISCV, SPARC, X86, EARLY] 4705 Disable NUMA, Only set up a single NUMA node 4706 spanning all memory. 4707 4708 numa=fake=<size>[MG] 4709 [KNL, ARM64, RISCV, X86, EARLY] 4710 If given as a memory unit, fills all system RAM with 4711 nodes of size interleaved over physical nodes. 4712 4713 numa=fake=<N> 4714 [KNL, ARM64, RISCV, X86, EARLY] 4715 If given as an integer, fills all system RAM with N 4716 fake nodes interleaved over physical nodes. 4717 4718 numa=fake=<N>U 4719 [KNL, ARM64, RISCV, X86, EARLY] 4720 If given as an integer followed by 'U', it will 4721 divide each physical node into N emulated nodes. 4722 4723 numa=noacpi [X86] Don't parse the SRAT table for NUMA setup 4724 4725 numa=nohmat [X86] Don't parse the HMAT table for NUMA setup, or 4726 soft-reserved memory partitioning. 4727 4728 numa_balancing= [KNL,ARM64,PPC,RISCV,S390,X86] Enable or disable automatic 4729 NUMA balancing. 4730 Allowed values are enable and disable 4731 4732 numa_zonelist_order= [KNL, BOOT] Select zonelist order for NUMA. 4733 'node', 'default' can be specified 4734 This can be set from sysctl after boot. 4735 See Documentation/admin-guide/sysctl/vm.rst for details. 4736 4737 nvme.quirks= [NVME] A list of quirk entries to augment the built-in 4738 nvme quirk list. List entries are separated by a 4739 '-' character. 4740 Each entry has the form VendorID:ProductID:quirk_names. 4741 The IDs are 4-digits hex numbers and quirk_names is a 4742 list of quirk names separated by commas. A quirk name 4743 can be prefixed by '^', meaning that the specified 4744 quirk must be disabled. 4745 4746 Example: 4747 nvme.quirks=7710:2267:bogus_nid,^identify_cns-9900:7711:broken_msi 4748 4749 ohci1394_dma=early [HW,EARLY] enable debugging via the ohci1394 driver. 4750 See Documentation/core-api/debugging-via-ohci1394.rst for more 4751 info. 4752 4753 olpc_ec_timeout= [OLPC] ms delay when issuing EC commands 4754 Rather than timing out after 20 ms if an EC 4755 command is not properly ACKed, override the length 4756 of the timeout. We have interrupts disabled while 4757 waiting for the ACK, so if this is set too high 4758 interrupts *may* be lost! 4759 4760 omap_mux= [OMAP] Override bootloader pin multiplexing. 4761 Format: <mux_mode0.mode_name=value>... 4762 For example, to override I2C bus2: 4763 omap_mux=i2c2_scl.i2c2_scl=0x100,i2c2_sda.i2c2_sda=0x100 4764 4765 onenand.bdry= [HW,MTD] Flex-OneNAND Boundary Configuration 4766 4767 Format: [die0_boundary][,die0_lock][,die1_boundary][,die1_lock] 4768 4769 boundary - index of last SLC block on Flex-OneNAND. 4770 The remaining blocks are configured as MLC blocks. 4771 lock - Configure if Flex-OneNAND boundary should be locked. 4772 Once locked, the boundary cannot be changed. 4773 1 indicates lock status, 0 indicates unlock status. 4774 4775 oops=panic [KNL,EARLY] 4776 Always panic on oopses. Default is to just kill the 4777 process, but there is a small probability of 4778 deadlocking the machine. 4779 This will also cause panics on machine check exceptions. 4780 Useful together with panic=30 to trigger a reboot. 4781 4782 page_alloc.shuffle= 4783 [KNL] Boolean flag to control whether the page allocator 4784 should randomize its free lists. This parameter can be 4785 used to enable/disable page randomization. The state of 4786 the flag can be read from sysfs at: 4787 /sys/module/page_alloc/parameters/shuffle. 4788 This parameter is only available if CONFIG_SHUFFLE_PAGE_ALLOCATOR=y. 4789 4790 page_owner= [KNL,EARLY] Boot-time page_owner enabling option. 4791 Storage of the information about who allocated 4792 each page is disabled in default. With this switch, 4793 we can turn it on. 4794 on: enable the feature 4795 4796 page_poison= [KNL,EARLY] Boot-time parameter changing the state of 4797 poisoning on the buddy allocator, available with 4798 CONFIG_PAGE_POISONING=y. 4799 off: turn off poisoning (default) 4800 on: turn on poisoning 4801 4802 page_reporting.page_reporting_order= 4803 [KNL] Minimal page reporting order 4804 Format: <integer> 4805 Adjust the minimal page reporting order. The page 4806 reporting is disabled when it exceeds MAX_PAGE_ORDER. 4807 4808 panic= [KNL] Kernel behaviour on panic: delay <timeout> 4809 timeout > 0: seconds before rebooting 4810 timeout = 0: wait forever 4811 timeout < 0: reboot immediately 4812 Format: <timeout> 4813 4814 panic_on_taint= [KNL,EARLY] 4815 Bitmask for conditionally calling panic() in add_taint() 4816 Format: <hex>[,nousertaint] 4817 Hexadecimal bitmask representing the set of TAINT flags 4818 that will cause the kernel to panic when add_taint() is 4819 called with any of the flags in this set. 4820 The optional switch "nousertaint" can be utilized to 4821 prevent userspace forced crashes by writing to sysctl 4822 /proc/sys/kernel/tainted any flagset matching with the 4823 bitmask set on panic_on_taint. 4824 See Documentation/admin-guide/tainted-kernels.rst for 4825 extra details on the taint flags that users can pick 4826 to compose the bitmask to assign to panic_on_taint. 4827 4828 panic_on_warn=1 panic() instead of WARN(). Useful to cause kdump 4829 on a WARN(). 4830 4831 panic_force_cpu= 4832 [KNL,SMP] Force panic handling to execute on a specific CPU. 4833 Format: <cpu number> 4834 Some platforms require panic handling to occur on a 4835 specific CPU for the crash kernel to function correctly. 4836 This can be due to firmware limitations, interrupt routing 4837 constraints, or platform-specific requirements where only 4838 a particular CPU can safely enter the crash kernel. 4839 When set, panic() will redirect execution to the specified 4840 CPU before proceeding with the normal panic and kexec flow. 4841 If the target CPU is offline or unavailable, panic proceeds 4842 on the current CPU. 4843 This option should only be used for systems with the above 4844 constraints as it might cause the panic operation to be less reliable. 4845 4846 panic_print= Bitmask for printing system info when panic happens. 4847 User can chose combination of the following bits: 4848 bit 0: print all tasks info 4849 bit 1: print system memory info 4850 bit 2: print timer info 4851 bit 3: print locks info if CONFIG_LOCKDEP is on 4852 bit 4: print ftrace buffer 4853 bit 5: replay all kernel messages on consoles at the end of panic 4854 bit 6: print all CPUs backtrace (if available in the arch) 4855 bit 7: print only tasks in uninterruptible (blocked) state 4856 *Be aware* that this option may print a _lot_ of lines, 4857 so there are risks of losing older messages in the log. 4858 Use this option carefully, maybe worth to setup a 4859 bigger log buffer with "log_buf_len" along with this. 4860 4861 panic_sys_info= A comma separated list of extra information to be dumped 4862 on panic. 4863 Format: val[,val...] 4864 Where @val can be any of the following: 4865 4866 tasks: print all tasks info 4867 mem: print system memory info 4868 timers: print timers info 4869 locks: print locks info if CONFIG_LOCKDEP is on 4870 ftrace: print ftrace buffer 4871 all_bt: print all CPUs backtrace (if available in the arch) 4872 blocked_tasks: print only tasks in uninterruptible (blocked) state 4873 4874 This is a human readable alternative to the 'panic_print' option. 4875 4876 panic_console_replay 4877 When panic happens, replay all kernel messages on 4878 consoles at the end of panic. 4879 4880 parkbd.port= [HW] Parallel port number the keyboard adapter is 4881 connected to, default is 0. 4882 Format: <parport#> 4883 parkbd.mode= [HW] Parallel port keyboard adapter mode of operation, 4884 0 for XT, 1 for AT (default is AT). 4885 Format: <mode> 4886 4887 parport= [HW,PPT] Specify parallel ports. 0 disables. 4888 Format: { 0 | auto | 0xBBB[,IRQ[,DMA]] } 4889 Use 'auto' to force the driver to use any 4890 IRQ/DMA settings detected (the default is to 4891 ignore detected IRQ/DMA settings because of 4892 possible conflicts). You can specify the base 4893 address, IRQ, and DMA settings; IRQ and DMA 4894 should be numbers, or 'auto' (for using detected 4895 settings on that particular port), or 'nofifo' 4896 (to avoid using a FIFO even if it is detected). 4897 Parallel ports are assigned in the order they 4898 are specified on the command line, starting 4899 with parport0. 4900 4901 parport_init_mode= [HW,PPT] 4902 Configure VIA parallel port to operate in 4903 a specific mode. This is necessary on Pegasos 4904 computer where firmware has no options for setting 4905 up parallel port mode and sets it to spp. 4906 Currently this function knows 686a and 8231 chips. 4907 Format: [spp|ps2|epp|ecp|ecpepp] 4908 4909 pata_legacy.all= [HW,LIBATA] 4910 Format: <int> 4911 Set to non-zero to probe primary and secondary ISA 4912 port ranges on PCI systems where no PCI PATA device 4913 has been found at either range. Disabled by default. 4914 4915 pata_legacy.autospeed= [HW,LIBATA] 4916 Format: <int> 4917 Set to non-zero if a chip is present that snoops speed 4918 changes. Disabled by default. 4919 4920 pata_legacy.ht6560a= [HW,LIBATA] 4921 Format: <int> 4922 Set to 1, 2, or 3 for HT 6560A on the primary channel, 4923 the secondary channel, or both channels respectively. 4924 Disabled by default. 4925 4926 pata_legacy.ht6560b= [HW,LIBATA] 4927 Format: <int> 4928 Set to 1, 2, or 3 for HT 6560B on the primary channel, 4929 the secondary channel, or both channels respectively. 4930 Disabled by default. 4931 4932 pata_legacy.iordy_mask= [HW,LIBATA] 4933 Format: <int> 4934 IORDY enable mask. Set individual bits to allow IORDY 4935 for the respective channel. Bit 0 is for the first 4936 legacy channel handled by this driver, bit 1 is for 4937 the second channel, and so on. The sequence will often 4938 correspond to the primary legacy channel, the secondary 4939 legacy channel, and so on, but the handling of a PCI 4940 bus and the use of other driver options may interfere 4941 with the sequence. By default IORDY is allowed across 4942 all channels. 4943 4944 pata_legacy.opti82c46x= [HW,LIBATA] 4945 Format: <int> 4946 Set to 1, 2, or 3 for Opti 82c611A on the primary 4947 channel, the secondary channel, or both channels 4948 respectively. Disabled by default. 4949 4950 pata_legacy.opti82c611a= [HW,LIBATA] 4951 Format: <int> 4952 Set to 1, 2, or 3 for Opti 82c465MV on the primary 4953 channel, the secondary channel, or both channels 4954 respectively. Disabled by default. 4955 4956 pata_legacy.pio_mask= [HW,LIBATA] 4957 Format: <int> 4958 PIO mode mask for autospeed devices. Set individual 4959 bits to allow the use of the respective PIO modes. 4960 Bit 0 is for mode 0, bit 1 is for mode 1, and so on. 4961 All modes allowed by default. 4962 4963 pata_legacy.probe_all= [HW,LIBATA] 4964 Format: <int> 4965 Set to non-zero to probe tertiary and further ISA 4966 port ranges on PCI systems. Disabled by default. 4967 4968 pata_legacy.probe_mask= [HW,LIBATA] 4969 Format: <int> 4970 Probe mask for legacy ISA PATA ports. Depending on 4971 platform configuration and the use of other driver 4972 options up to 6 legacy ports are supported: 0x1f0, 4973 0x170, 0x1e8, 0x168, 0x1e0, 0x160, however probing 4974 of individual ports can be disabled by setting the 4975 corresponding bits in the mask to 1. Bit 0 is for 4976 the first port in the list above (0x1f0), and so on. 4977 By default all supported ports are probed. 4978 4979 pata_legacy.qdi= [HW,LIBATA] 4980 Format: <int> 4981 Set to non-zero to probe QDI controllers. By default 4982 set to 1 if CONFIG_PATA_QDI_MODULE, 0 otherwise. 4983 4984 pata_legacy.winbond= [HW,LIBATA] 4985 Format: <int> 4986 Set to non-zero to probe Winbond controllers. Use 4987 the standard I/O port (0x130) if 1, otherwise the 4988 value given is the I/O port to use (typically 0x1b0). 4989 By default set to 1 if CONFIG_PATA_WINBOND_VLB_MODULE, 4990 0 otherwise. 4991 4992 pata_platform.pio_mask= [HW,LIBATA] 4993 Format: <int> 4994 Supported PIO mode mask. Set individual bits to allow 4995 the use of the respective PIO modes. Bit 0 is for 4996 mode 0, bit 1 is for mode 1, and so on. Mode 0 only 4997 allowed by default. 4998 4999 pause_on_oops=<int> 5000 Halt all CPUs after the first oops has been printed for 5001 the specified number of seconds. This is to be used if 5002 your oopses keep scrolling off the screen. 5003 5004 pcbit= [HW,ISDN] 5005 5006 pci=option[,option...] [PCI,EARLY] various PCI subsystem options. 5007 5008 Some options herein operate on a specific device 5009 or a set of devices (<pci_dev>). These are 5010 specified in one of the following formats: 5011 5012 [<domain>:]<bus>:<dev>.<func>[/<dev>.<func>]* 5013 pci:<vendor>:<device>[:<subvendor>:<subdevice>] 5014 5015 Note: the first format specifies a PCI 5016 bus/device/function address which may change 5017 if new hardware is inserted, if motherboard 5018 firmware changes, or due to changes caused 5019 by other kernel parameters. If the 5020 domain is left unspecified, it is 5021 taken to be zero. Optionally, a path 5022 to a device through multiple device/function 5023 addresses can be specified after the base 5024 address (this is more robust against 5025 renumbering issues). The second format 5026 selects devices using IDs from the 5027 configuration space which may match multiple 5028 devices in the system. 5029 5030 earlydump dump PCI config space before the kernel 5031 changes anything 5032 off [X86] don't probe for the PCI bus 5033 bios [X86-32] force use of PCI BIOS, don't access 5034 the hardware directly. Use this if your machine 5035 has a non-standard PCI host bridge. 5036 nobios [X86-32] disallow use of PCI BIOS, only direct 5037 hardware access methods are allowed. Use this 5038 if you experience crashes upon bootup and you 5039 suspect they are caused by the BIOS. 5040 conf1 [X86] Force use of PCI Configuration Access 5041 Mechanism 1 (config address in IO port 0xCF8, 5042 data in IO port 0xCFC, both 32-bit). 5043 conf2 [X86] Force use of PCI Configuration Access 5044 Mechanism 2 (IO port 0xCF8 is an 8-bit port for 5045 the function, IO port 0xCFA, also 8-bit, sets 5046 bus number. The config space is then accessed 5047 through ports 0xC000-0xCFFF). 5048 See http://wiki.osdev.org/PCI for more info 5049 on the configuration access mechanisms. 5050 noaer [PCIE] If the PCIEAER kernel config parameter is 5051 enabled, this kernel boot option can be used to 5052 disable the use of PCIE advanced error reporting. 5053 nodomains [PCI] Disable support for multiple PCI 5054 root domains (aka PCI segments, in ACPI-speak). 5055 nommconf [X86] Disable use of MMCONFIG for PCI 5056 Configuration 5057 check_enable_amd_mmconf [X86] check for and enable 5058 properly configured MMIO access to PCI 5059 config space on AMD family 10h CPU 5060 nomsi [MSI] If the PCI_MSI kernel config parameter is 5061 enabled, this kernel boot option can be used to 5062 disable the use of MSI interrupts system-wide. 5063 noioapicquirk [APIC] Disable all boot interrupt quirks. 5064 Safety option to keep boot IRQs enabled. This 5065 should never be necessary. 5066 ioapicreroute [APIC] Enable rerouting of boot IRQs to the 5067 primary IO-APIC for bridges that cannot disable 5068 boot IRQs. This fixes a source of spurious IRQs 5069 when the system masks IRQs. 5070 noioapicreroute [APIC] Disable workaround that uses the 5071 boot IRQ equivalent of an IRQ that connects to 5072 a chipset where boot IRQs cannot be disabled. 5073 The opposite of ioapicreroute. 5074 biosirq [X86-32] Use PCI BIOS calls to get the interrupt 5075 routing table. These calls are known to be buggy 5076 on several machines and they hang the machine 5077 when used, but on other computers it's the only 5078 way to get the interrupt routing table. Try 5079 this option if the kernel is unable to allocate 5080 IRQs or discover secondary PCI buses on your 5081 motherboard. 5082 rom [X86] Assign address space to expansion ROMs. 5083 Use with caution as certain devices share 5084 address decoders between ROMs and other 5085 resources. 5086 norom [X86] Do not assign address space to 5087 expansion ROMs that do not already have 5088 BIOS assigned address ranges. 5089 nobar [X86] Do not assign address space to the 5090 BARs that weren't assigned by the BIOS. 5091 irqmask=0xMMMM [X86] Set a bit mask of IRQs allowed to be 5092 assigned automatically to PCI devices. You can 5093 make the kernel exclude IRQs of your ISA cards 5094 this way. 5095 pirqaddr=0xAAAAA [X86] Specify the physical address 5096 of the PIRQ table (normally generated 5097 by the BIOS) if it is outside the 5098 F0000h-100000h range. 5099 lastbus=N [X86] Scan all buses thru bus #N. Can be 5100 useful if the kernel is unable to find your 5101 secondary buses and you want to tell it 5102 explicitly which ones they are. 5103 assign-busses [X86] Always assign all PCI bus 5104 numbers ourselves, overriding 5105 whatever the firmware may have done. 5106 usepirqmask [X86] Honor the possible IRQ mask stored 5107 in the BIOS $PIR table. This is needed on 5108 some systems with broken BIOSes, notably 5109 some HP Pavilion N5400 and Omnibook XE3 5110 notebooks. This will have no effect if ACPI 5111 IRQ routing is enabled. 5112 noacpi [X86] Do not use ACPI for IRQ routing 5113 or for PCI scanning. 5114 use_crs [X86] Use PCI host bridge window information 5115 from ACPI. On BIOSes from 2008 or later, this 5116 is enabled by default. If you need to use this, 5117 please report a bug. 5118 nocrs [X86] Ignore PCI host bridge windows from ACPI. 5119 If you need to use this, please report a bug. 5120 use_e820 [X86] Use E820 reservations to exclude parts of 5121 PCI host bridge windows. This is a workaround 5122 for BIOS defects in host bridge _CRS methods. 5123 If you need to use this, please report a bug to 5124 <linux-pci@vger.kernel.org>. 5125 no_e820 [X86] Ignore E820 reservations for PCI host 5126 bridge windows. This is the default on modern 5127 hardware. If you need to use this, please report 5128 a bug to <linux-pci@vger.kernel.org>. 5129 routeirq Do IRQ routing for all PCI devices. 5130 This is normally done in pci_enable_device(), 5131 so this option is a temporary workaround 5132 for broken drivers that don't call it. 5133 skip_isa_align [X86] do not align io start addr, so can 5134 handle more pci cards 5135 noearly [X86] Don't do any early type 1 scanning. 5136 This might help on some broken boards which 5137 machine check when some devices' config space 5138 is read. But various workarounds are disabled 5139 and some IOMMU drivers will not work. 5140 bfsort Sort PCI devices into breadth-first order. 5141 This sorting is done to get a device 5142 order compatible with older (<= 2.4) kernels. 5143 nobfsort Don't sort PCI devices into breadth-first order. 5144 pcie_bus_tune_off Disable PCIe MPS (Max Payload Size) 5145 tuning and use the BIOS-configured MPS defaults. 5146 pcie_bus_safe Set every device's MPS to the largest value 5147 supported by all devices below the root complex. 5148 pcie_bus_perf Set device MPS to the largest allowable MPS 5149 based on its parent bus. Also set MRRS (Max 5150 Read Request Size) to the largest supported 5151 value (no larger than the MPS that the device 5152 or bus can support) for best performance. 5153 pcie_bus_peer2peer Set every device's MPS to 128B, which 5154 every device is guaranteed to support. This 5155 configuration allows peer-to-peer DMA between 5156 any pair of devices, possibly at the cost of 5157 reduced performance. This also guarantees 5158 that hot-added devices will work. 5159 cbiosize=nn[KMG] The fixed amount of bus space which is 5160 reserved for the CardBus bridge's IO window. 5161 The default value is 256 bytes. 5162 cbmemsize=nn[KMG] The fixed amount of bus space which is 5163 reserved for the CardBus bridge's memory 5164 window. The default value is 64 megabytes. 5165 resource_alignment= 5166 Format: 5167 [<order of align>@]<pci_dev>[; ...] 5168 Specifies alignment and device to reassign 5169 aligned memory resources. How to 5170 specify the device is described above. 5171 If <order of align> is not specified, 5172 PAGE_SIZE is used as alignment. 5173 A PCI-PCI bridge can be specified if resource 5174 windows need to be expanded. 5175 To specify the alignment for several 5176 instances of a device, the PCI vendor, 5177 device, subvendor, and subdevice may be 5178 specified, e.g., 12@pci:8086:9c22:103c:198f 5179 for 4096-byte alignment. 5180 ecrc= Enable/disable PCIe ECRC (transaction layer 5181 end-to-end CRC checking). Only effective if 5182 OS has native AER control (either granted by 5183 ACPI _OSC or forced via "pcie_ports=native") 5184 bios: Use BIOS/firmware settings. This is the 5185 the default. 5186 off: Turn ECRC off 5187 on: Turn ECRC on. 5188 hpiosize=nn[KMG] The fixed amount of bus space which is 5189 reserved for hotplug bridge's IO window. 5190 Default size is 256 bytes. 5191 hpmmiosize=nn[KMG] The fixed amount of bus space which is 5192 reserved for hotplug bridge's MMIO window. 5193 Default size is 2 megabytes. 5194 hpmmioprefsize=nn[KMG] The fixed amount of bus space which is 5195 reserved for hotplug bridge's MMIO_PREF window. 5196 Default size is 2 megabytes. 5197 hpmemsize=nn[KMG] The fixed amount of bus space which is 5198 reserved for hotplug bridge's MMIO and 5199 MMIO_PREF window. 5200 Default size is 2 megabytes. 5201 hpbussize=nn The minimum amount of additional bus numbers 5202 reserved for buses below a hotplug bridge. 5203 Default is 1. 5204 realloc= Enable/disable reallocating PCI bridge resources 5205 if allocations done by BIOS are too small to 5206 accommodate resources required by all child 5207 devices. 5208 off: Turn realloc off 5209 on: Turn realloc on 5210 realloc same as realloc=on 5211 noari do not use PCIe ARI. 5212 noats [PCIE, Intel-IOMMU, AMD-IOMMU] 5213 do not use PCIe ATS (and IOMMU device IOTLB). 5214 pcie_scan_all Scan all possible PCIe devices. Otherwise we 5215 only look for one device below a PCIe downstream 5216 port. 5217 big_root_window Try to add a big 64bit memory window to the PCIe 5218 root complex on AMD CPUs. Some GFX hardware 5219 can resize a BAR to allow access to all VRAM. 5220 Adding the window is slightly risky (it may 5221 conflict with unreported devices), so this 5222 taints the kernel. 5223 disable_acs_redir=<pci_dev>[; ...] 5224 Specify one or more PCI devices (in the format 5225 specified above) separated by semicolons. 5226 Each device specified will have the PCI ACS 5227 redirect capabilities forced off which will 5228 allow P2P traffic between devices through 5229 bridges without forcing it upstream. Note: 5230 this removes isolation between devices and 5231 may put more devices in an IOMMU group. 5232 config_acs= 5233 Format: 5234 <ACS flags>@<pci_dev>[; ...] 5235 Specify one or more PCI devices (in the format 5236 specified above) optionally prepended with flags 5237 and separated by semicolons. The respective 5238 capabilities will be enabled, disabled or 5239 unchanged based on what is specified in 5240 flags. 5241 5242 ACS Flags is defined as follows: 5243 bit-0 : ACS Source Validation 5244 bit-1 : ACS Translation Blocking 5245 bit-2 : ACS P2P Request Redirect 5246 bit-3 : ACS P2P Completion Redirect 5247 bit-4 : ACS Upstream Forwarding 5248 bit-5 : ACS P2P Egress Control 5249 bit-6 : ACS Direct Translated P2P 5250 Each bit can be marked as: 5251 '0' – force disabled 5252 '1' – force enabled 5253 'x' – unchanged 5254 For example, 5255 pci=config_acs=10x@pci:0:0 5256 would configure all devices that support 5257 ACS to enable P2P Request Redirect, disable 5258 Translation Blocking, and leave Source 5259 Validation unchanged from whatever power-up 5260 or firmware set it to. 5261 5262 Note: this may remove isolation between devices 5263 and may put more devices in an IOMMU group. 5264 force_floating [S390] Force usage of floating interrupts. 5265 nomio [S390] Do not use MIO instructions. 5266 norid [S390] ignore the RID field and force use of 5267 one PCI domain per PCI function 5268 notph [PCIE] If the PCIE_TPH kernel config parameter 5269 is enabled, this kernel boot option can be used 5270 to disable PCIe TLP Processing Hints support 5271 system-wide. 5272 5273 pcie_aspm= [PCIE] Forcibly enable or ignore PCIe Active State Power 5274 Management. 5275 off Don't touch ASPM configuration at all. Leave any 5276 configuration done by firmware unchanged. 5277 force Enable ASPM even on devices that claim not to support it. 5278 WARNING: Forcing ASPM on may cause system lockups. 5279 5280 pcie_ports= [PCIE] PCIe port services handling: 5281 native Use native PCIe services (PME, AER, DPC, PCIe hotplug) 5282 even if the platform doesn't give the OS permission to 5283 use them. This may cause conflicts if the platform 5284 also tries to use these services. 5285 dpc-native Use native PCIe service for DPC only. May 5286 cause conflicts if firmware uses AER or DPC. 5287 compat Disable native PCIe services (PME, AER, DPC, PCIe 5288 hotplug). 5289 5290 pcie_port_pm= [PCIE] PCIe port power management handling: 5291 off Disable power management of all PCIe ports 5292 force Forcibly enable power management of all PCIe ports 5293 5294 pcie_pme= [PCIE,PM] Native PCIe PME signaling options: 5295 nomsi Do not use MSI for native PCIe PME signaling (this makes 5296 all PCIe root ports use INTx for all services). 5297 5298 pcmv= [HW,PCMCIA] BadgePAD 4 5299 5300 pd_ignore_unused 5301 [PM] 5302 Keep all power-domains already enabled by bootloader on, 5303 even if no driver has claimed them. This is useful 5304 for debug and development, but should not be 5305 needed on a platform with proper driver support. 5306 5307 pdcchassis= [PARISC,HW] Disable/Enable PDC Chassis Status codes at 5308 boot time. 5309 Format: { 0 | 1 } 5310 See arch/parisc/kernel/pdc_chassis.c 5311 5312 percpu_alloc= [MM,EARLY] 5313 Select which percpu first chunk allocator to use. 5314 Currently supported values are "embed" and "page". 5315 Archs may support subset or none of the selections. 5316 See comments in mm/percpu.c for details on each 5317 allocator. This parameter is primarily for debugging 5318 and performance comparison. 5319 5320 pirq= [SMP,APIC] Manual mp-table setup 5321 See Documentation/arch/x86/i386/IO-APIC.rst. 5322 5323 plip= [PPT,NET] Parallel port network link 5324 Format: { parport<nr> | timid | 0 } 5325 See also Documentation/admin-guide/parport.rst. 5326 5327 pmtmr= [X86] Manual setup of pmtmr I/O Port. 5328 Override pmtimer IOPort with a hex value. 5329 e.g. pmtmr=0x508 5330 5331 pmu_override= [PPC] Override the PMU. 5332 This option takes over the PMU facility, so it is no 5333 longer usable by perf. Setting this option starts the 5334 PMU counters by setting MMCR0 to 0 (the FC bit is 5335 cleared). If a number is given, then MMCR1 is set to 5336 that number, otherwise (e.g., 'pmu_override=on'), MMCR1 5337 remains 0. 5338 5339 pm_async= [PM] 5340 Format: off 5341 This parameter sets the initial value of the 5342 /sys/power/pm_async sysfs knob at boot time. 5343 If set to "off", disables asynchronous suspend and 5344 resume of devices during system-wide power transitions. 5345 This can be useful on platforms where device 5346 dependencies are not well-defined, or for debugging 5347 power management issues. Asynchronous operations are 5348 enabled by default. 5349 5350 5351 pm_debug_messages [SUSPEND,KNL] 5352 Enable suspend/resume debug messages during boot up. 5353 5354 pnp.debug=1 [PNP] 5355 Enable PNP debug messages (depends on the 5356 CONFIG_PNP_DEBUG_MESSAGES option). Change at run-time 5357 via /sys/module/pnp/parameters/debug. We always show 5358 current resource usage; turning this on also shows 5359 possible settings and some assignment information. 5360 5361 pnpacpi= [ACPI] 5362 { off } 5363 5364 pnpbios= [ISAPNP] 5365 { on | off | curr | res | no-curr | no-res } 5366 5367 pnp_reserve_irq= 5368 [ISAPNP] Exclude IRQs for the autoconfiguration 5369 5370 pnp_reserve_dma= 5371 [ISAPNP] Exclude DMAs for the autoconfiguration 5372 5373 pnp_reserve_io= [ISAPNP] Exclude I/O ports for the autoconfiguration 5374 Ranges are in pairs (I/O port base and size). 5375 5376 pnp_reserve_mem= 5377 [ISAPNP] Exclude memory regions for the 5378 autoconfiguration. 5379 Ranges are in pairs (memory base and size). 5380 5381 ports= [IP_VS_FTP] IPVS ftp helper module 5382 Default is 21. 5383 Up to 8 (IP_VS_APP_MAX_PORTS) ports 5384 may be specified. 5385 Format: <port>,<port>.... 5386 5387 possible_cpus= [SMP,S390,X86] 5388 Format: <unsigned int> 5389 Set the number of possible CPUs, overriding the 5390 regular discovery mechanisms (such as ACPI/FW, etc). 5391 5392 powersave=off [PPC] This option disables power saving features. 5393 It specifically disables cpuidle and sets the 5394 platform machine description specific power_save 5395 function to NULL. On Idle the CPU just reduces 5396 execution priority. 5397 5398 ppc_strict_facility_enable 5399 [PPC,ENABLE] This option catches any kernel floating point, 5400 Altivec, VSX and SPE outside of regions specifically 5401 allowed (eg kernel_enable_fpu()/kernel_disable_fpu()). 5402 There is some performance impact when enabling this. 5403 5404 ppc_tm= [PPC,EARLY] 5405 Format: {"off"} 5406 Disable Hardware Transactional Memory 5407 5408 preempt= [KNL] 5409 Select preemption mode if you have CONFIG_PREEMPT_DYNAMIC 5410 none - Limited to cond_resched() calls 5411 voluntary - Limited to cond_resched() and might_sleep() calls 5412 full - Any section that isn't explicitly preempt disabled 5413 can be preempted anytime. Tasks will also yield 5414 contended spinlocks (if the critical section isn't 5415 explicitly preempt disabled beyond the lock itself). 5416 lazy - Scheduler controlled. Similar to full but instead 5417 of preempting the task immediately, the task gets 5418 one HZ tick time to yield itself before the 5419 preemption will be forced. One preemption is when the 5420 task returns to user space. 5421 5422 print-fatal-signals= 5423 [KNL] debug: print fatal signals 5424 5425 If enabled, warn about various signal handling 5426 related application anomalies: too many signals, 5427 too many POSIX.1 timers, fatal signals causing a 5428 coredump - etc. 5429 5430 If you hit the warning due to signal overflow, 5431 you might want to try "ulimit -i unlimited". 5432 5433 default: off. 5434 5435 printk.always_kmsg_dump= 5436 Trigger kmsg_dump for cases other than kernel oops or 5437 panics 5438 Format: <bool> (1/Y/y=enable, 0/N/n=disable) 5439 default: disabled 5440 5441 printk.console_no_auto_verbose= 5442 Disable console loglevel raise on oops, panic 5443 or lockdep-detected issues (only if lock debug is on). 5444 With an exception to setups with low baudrate on 5445 serial console, keeping this 0 is a good choice 5446 in order to provide more debug information. 5447 Format: <bool> 5448 default: 0 (auto_verbose is enabled) 5449 5450 printk.debug_non_panic_cpus= 5451 Allows storing messages from non-panic CPUs into 5452 the printk log buffer during panic(). They are 5453 flushed to consoles by the panic-CPU on 5454 a best-effort basis. 5455 Format: <bool> (1/Y/y=enable, 0/N/n=disable) 5456 Default: disabled 5457 5458 printk.devkmsg={on,off,ratelimit} 5459 Control writing to /dev/kmsg. 5460 on - unlimited logging to /dev/kmsg from userspace 5461 off - logging to /dev/kmsg disabled 5462 ratelimit - ratelimit the logging 5463 Default: ratelimit 5464 5465 printk.time= Show timing data prefixed to each printk message line 5466 Format: <bool> (1/Y/y=enable, 0/N/n=disable) 5467 5468 proc_mem.force_override= [KNL] 5469 Format: {always | ptrace | never} 5470 Traditionally /proc/pid/mem allows memory permissions to be 5471 overridden without restrictions. This option may be set to 5472 restrict that. Can be one of: 5473 - 'always': traditional behavior always allows mem overrides. 5474 - 'ptrace': only allow mem overrides for active ptracers. 5475 - 'never': never allow mem overrides. 5476 If not specified, default is the CONFIG_PROC_MEM_* choice. 5477 5478 processor.max_cstate= [HW,ACPI] 5479 Limit processor to maximum C-state 5480 max_cstate=9 overrides any DMI blacklist limit. 5481 5482 processor.nocst [HW,ACPI] 5483 Ignore the _CST method to determine C-states, 5484 instead using the legacy FADT method 5485 5486 profile= [KNL] Enable kernel profiling via /proc/profile 5487 Format: [<profiletype>,]<number> 5488 Param: <profiletype>: "schedule" or "kvm" 5489 [defaults to kernel profiling] 5490 Param: "schedule" - profile schedule points. 5491 Param: "kvm" - profile VM exits. 5492 Param: <number> - step/bucket size as a power of 2 for 5493 statistical time based profiling. 5494 5495 prot_virt= [S390] enable hosting protected virtual machines 5496 isolated from the hypervisor (if hardware supports 5497 that). If enabled, the default kernel base address 5498 might be overridden even when Kernel Address Space 5499 Layout Randomization is disabled. 5500 Format: <bool> 5501 5502 psi= [KNL] Enable or disable pressure stall information 5503 tracking. 5504 Format: <bool> 5505 5506 psmouse.proto= [HW,MOUSE] Highest PS2 mouse protocol extension to 5507 probe for; one of (bare|imps|exps|lifebook|any). 5508 psmouse.rate= [HW,MOUSE] Set desired mouse report rate, in reports 5509 per second. 5510 psmouse.resetafter= [HW,MOUSE] 5511 Try to reset the device after so many bad packets 5512 (0 = never). 5513 psmouse.resolution= 5514 [HW,MOUSE] Set desired mouse resolution, in dpi. 5515 psmouse.smartscroll= 5516 [HW,MOUSE] Controls Logitech smartscroll autorepeat. 5517 0 = disabled, 1 = enabled (default). 5518 5519 pstore.backend= Specify the name of the pstore backend to use 5520 5521 pti= [X86-64] Control Page Table Isolation of user and 5522 kernel address spaces. Disabling this feature 5523 removes hardening, but improves performance of 5524 system calls and interrupts. 5525 5526 on - unconditionally enable 5527 off - unconditionally disable 5528 auto - kernel detects whether your CPU model is 5529 vulnerable to issues that PTI mitigates 5530 5531 Not specifying this option is equivalent to pti=auto. 5532 5533 pty.legacy_count= 5534 [KNL] Number of legacy pty's. Overwrites compiled-in 5535 default number. 5536 5537 quiet [KNL,EARLY] Disable most log messages 5538 5539 r128= [HW,DRM] 5540 5541 radix_hcall_invalidate=on [PPC/PSERIES] 5542 Disable RADIX GTSE feature and use hcall for TLB 5543 invalidate. 5544 5545 raid= [HW,RAID] 5546 See Documentation/admin-guide/md.rst. 5547 5548 ramdisk_size= [RAM] Sizes of RAM disks in kilobytes 5549 See Documentation/admin-guide/blockdev/ramdisk.rst. 5550 5551 ramdisk_start= [Deprecated,RAM] RAM disk image start address 5552 5553 random.trust_cpu=off 5554 [KNL,EARLY] Disable trusting the use of the CPU's 5555 random number generator (if available) to 5556 initialize the kernel's RNG. 5557 5558 random.trust_bootloader=off 5559 [KNL,EARLY] Disable trusting the use of the a seed 5560 passed by the bootloader (if available) to 5561 initialize the kernel's RNG. 5562 5563 randomize_kstack_offset= 5564 [KNL,EARLY] Enable or disable kernel stack offset 5565 randomization, which provides roughly 5 bits of 5566 entropy, frustrating memory corruption attacks 5567 that depend on stack address determinism or 5568 cross-syscall address exposures. This is only 5569 available on architectures that have defined 5570 CONFIG_HAVE_ARCH_RANDOMIZE_KSTACK_OFFSET. 5571 Format: <bool> (1/Y/y=enable, 0/N/n=disable) 5572 Default is CONFIG_RANDOMIZE_KSTACK_OFFSET_DEFAULT. 5573 5574 ras=option[,option,...] [KNL] RAS-specific options 5575 5576 cec_disable [X86] 5577 Disable the Correctable Errors Collector, 5578 see CONFIG_RAS_CEC help text. 5579 5580 rcu_nocbs[=cpu-list] 5581 [KNL] The optional argument is a cpu list, 5582 as described above. 5583 5584 In kernels built with CONFIG_RCU_NOCB_CPU=y, 5585 enable the no-callback CPU mode, which prevents 5586 such CPUs' callbacks from being invoked in 5587 softirq context. Invocation of such CPUs' RCU 5588 callbacks will instead be offloaded to "rcuox/N" 5589 kthreads created for that purpose, where "x" is 5590 "p" for RCU-preempt, "s" for RCU-sched, and "g" 5591 for the kthreads that mediate grace periods; and 5592 "N" is the CPU number. This reduces OS jitter on 5593 the offloaded CPUs, which can be useful for HPC 5594 and real-time workloads. It can also improve 5595 energy efficiency for asymmetric multiprocessors. 5596 5597 If a cpulist is passed as an argument, the specified 5598 list of CPUs is set to no-callback mode from boot. 5599 5600 Otherwise, if the '=' sign and the cpulist 5601 arguments are omitted, no CPU will be set to 5602 no-callback mode from boot but the mode may be 5603 toggled at runtime via cpusets. 5604 5605 Note that this argument takes precedence over 5606 the CONFIG_RCU_NOCB_CPU_DEFAULT_ALL option. 5607 5608 rcu_nocb_poll [KNL] 5609 Rather than requiring that offloaded CPUs 5610 (specified by rcu_nocbs= above) explicitly 5611 awaken the corresponding "rcuoN" kthreads, 5612 make these kthreads poll for callbacks. 5613 This improves the real-time response for the 5614 offloaded CPUs by relieving them of the need to 5615 wake up the corresponding kthread, but degrades 5616 energy efficiency by requiring that the kthreads 5617 periodically wake up to do the polling. 5618 5619 rcutree.blimit= [KNL] 5620 Set maximum number of finished RCU callbacks to 5621 process in one batch. 5622 5623 rcutree.csd_lock_suppress_rcu_stall= [KNL] 5624 Do only a one-line RCU CPU stall warning when 5625 there is an ongoing too-long CSD-lock wait. 5626 5627 rcutree.do_rcu_barrier= [KNL] 5628 Request a call to rcu_barrier(). This is 5629 throttled so that userspace tests can safely 5630 hammer on the sysfs variable if they so choose. 5631 If triggered before the RCU grace-period machinery 5632 is fully active, this will error out with EAGAIN. 5633 5634 rcutree.dump_tree= [KNL] 5635 Dump the structure of the rcu_node combining tree 5636 out at early boot. This is used for diagnostic 5637 purposes, to verify correct tree setup. 5638 5639 rcutree.gp_cleanup_delay= [KNL] 5640 Set the number of jiffies to delay each step of 5641 RCU grace-period cleanup. 5642 5643 rcutree.gp_init_delay= [KNL] 5644 Set the number of jiffies to delay each step of 5645 RCU grace-period initialization. 5646 5647 rcutree.gp_preinit_delay= [KNL] 5648 Set the number of jiffies to delay each step of 5649 RCU grace-period pre-initialization, that is, 5650 the propagation of recent CPU-hotplug changes up 5651 the rcu_node combining tree. 5652 5653 rcutree.jiffies_till_first_fqs= [KNL] 5654 Set delay from grace-period initialization to 5655 first attempt to force quiescent states. 5656 Units are jiffies, minimum value is zero, 5657 and maximum value is HZ. 5658 5659 rcutree.jiffies_till_next_fqs= [KNL] 5660 Set delay between subsequent attempts to force 5661 quiescent states. Units are jiffies, minimum 5662 value is one, and maximum value is HZ. 5663 5664 rcutree.jiffies_till_sched_qs= [KNL] 5665 Set required age in jiffies for a 5666 given grace period before RCU starts 5667 soliciting quiescent-state help from 5668 rcu_note_context_switch() and cond_resched(). 5669 If not specified, the kernel will calculate 5670 a value based on the most recent settings 5671 of rcutree.jiffies_till_first_fqs 5672 and rcutree.jiffies_till_next_fqs. 5673 This calculated value may be viewed in 5674 rcutree.jiffies_to_sched_qs. Any attempt to set 5675 rcutree.jiffies_to_sched_qs will be cheerfully 5676 overwritten. 5677 5678 rcutree.kthread_prio= [KNL,BOOT] 5679 Set the SCHED_FIFO priority of the RCU per-CPU 5680 kthreads (rcuc/N). This value is also used for 5681 the priority of the RCU boost threads (rcub/N) 5682 and for the RCU grace-period kthreads (rcu_bh, 5683 rcu_preempt, and rcu_sched). If RCU_BOOST is 5684 set, valid values are 1-99 and the default is 1 5685 (the least-favored priority). Otherwise, when 5686 RCU_BOOST is not set, valid values are 0-99 and 5687 the default is zero (non-realtime operation). 5688 When RCU_NOCB_CPU is set, also adjust the 5689 priority of NOCB callback kthreads. 5690 5691 rcutree.nocb_nobypass_lim_per_jiffy= [KNL] 5692 On callback-offloaded (rcu_nocbs) CPUs, 5693 RCU reduces the lock contention that would 5694 otherwise be caused by callback floods through 5695 use of the ->nocb_bypass list. However, in the 5696 common non-flooded case, RCU queues directly to 5697 the main ->cblist in order to avoid the extra 5698 overhead of the ->nocb_bypass list and its lock. 5699 But if there are too many callbacks queued during 5700 a single jiffy, RCU pre-queues the callbacks into 5701 the ->nocb_bypass queue. The definition of "too 5702 many" is supplied by this kernel boot parameter. 5703 5704 rcutree.nohz_full_patience_delay= [KNL] 5705 On callback-offloaded (rcu_nocbs) CPUs, avoid 5706 disturbing RCU unless the grace period has 5707 reached the specified age in milliseconds. 5708 Defaults to zero. Large values will be capped 5709 at five seconds. All values will be rounded down 5710 to the nearest value representable by jiffies. 5711 5712 rcutree.qhimark= [KNL] 5713 Set threshold of queued RCU callbacks beyond which 5714 batch limiting is disabled. 5715 5716 rcutree.qlowmark= [KNL] 5717 Set threshold of queued RCU callbacks below which 5718 batch limiting is re-enabled. 5719 5720 rcutree.qovld= [KNL] 5721 Set threshold of queued RCU callbacks beyond which 5722 RCU's force-quiescent-state scan will aggressively 5723 enlist help from cond_resched() and sched IPIs to 5724 help CPUs more quickly reach quiescent states. 5725 Set to less than zero to make this be set based 5726 on rcutree.qhimark at boot time and to zero to 5727 disable more aggressive help enlistment. 5728 5729 rcutree.rcu_delay_page_cache_fill_msec= [KNL] 5730 Set the page-cache refill delay (in milliseconds) 5731 in response to low-memory conditions. The range 5732 of permitted values is in the range 0:100000. 5733 5734 rcutree.rcu_divisor= [KNL] 5735 Set the shift-right count to use to compute 5736 the callback-invocation batch limit bl from 5737 the number of callbacks queued on this CPU. 5738 The result will be bounded below by the value of 5739 the rcutree.blimit kernel parameter. Every bl 5740 callbacks, the softirq handler will exit in 5741 order to allow the CPU to do other work. 5742 5743 Please note that this callback-invocation batch 5744 limit applies only to non-offloaded callback 5745 invocation. Offloaded callbacks are instead 5746 invoked in the context of an rcuoc kthread, which 5747 scheduler will preempt as it does any other task. 5748 5749 rcutree.rcu_fanout_exact= [KNL] 5750 Disable autobalancing of the rcu_node combining 5751 tree. This is used by rcutorture, and might 5752 possibly be useful for architectures having high 5753 cache-to-cache transfer latencies. 5754 5755 rcutree.rcu_fanout_leaf= [KNL] 5756 Change the number of CPUs assigned to each 5757 leaf rcu_node structure. Useful for very 5758 large systems, which will choose the value 64, 5759 and for NUMA systems with large remote-access 5760 latencies, which will choose a value aligned 5761 with the appropriate hardware boundaries. 5762 5763 rcutree.rcu_min_cached_objs= [KNL] 5764 Minimum number of objects which are cached and 5765 maintained per one CPU. Object size is equal 5766 to PAGE_SIZE. The cache allows to reduce the 5767 pressure to page allocator, also it makes the 5768 whole algorithm to behave better in low memory 5769 condition. 5770 5771 rcutree.rcu_nocb_gp_stride= [KNL] 5772 Set the number of NOCB callback kthreads in 5773 each group, which defaults to the square root 5774 of the number of CPUs. Larger numbers reduce 5775 the wakeup overhead on the global grace-period 5776 kthread, but increases that same overhead on 5777 each group's NOCB grace-period kthread. 5778 5779 rcutree.rcu_kick_kthreads= [KNL] 5780 Cause the grace-period kthread to get an extra 5781 wake_up() if it sleeps three times longer than 5782 it should at force-quiescent-state time. 5783 This wake_up() will be accompanied by a 5784 WARN_ONCE() splat and an ftrace_dump(). 5785 5786 rcutree.rcu_resched_ns= [KNL] 5787 Limit the time spend invoking a batch of RCU 5788 callbacks to the specified number of nanoseconds. 5789 By default, this limit is checked only once 5790 every 32 callbacks in order to limit the pain 5791 inflicted by local_clock() overhead. 5792 5793 rcutree.rcu_unlock_delay= [KNL] 5794 In CONFIG_RCU_STRICT_GRACE_PERIOD=y kernels, 5795 this specifies an rcu_read_unlock()-time delay 5796 in microseconds. This defaults to zero. 5797 Larger delays increase the probability of 5798 catching RCU pointer leaks, that is, buggy use 5799 of RCU-protected pointers after the relevant 5800 rcu_read_unlock() has completed. 5801 5802 rcutree.sysrq_rcu= [KNL] 5803 Commandeer a sysrq key to dump out Tree RCU's 5804 rcu_node tree with an eye towards determining 5805 why a new grace period has not yet started. 5806 5807 rcutree.use_softirq= [KNL] 5808 If set to zero, move all RCU_SOFTIRQ processing to 5809 per-CPU rcuc kthreads. Defaults to a non-zero 5810 value, meaning that RCU_SOFTIRQ is used by default. 5811 Specify rcutree.use_softirq=0 to use rcuc kthreads. 5812 5813 But note that CONFIG_PREEMPT_RT=y kernels disable 5814 this kernel boot parameter, forcibly setting it 5815 to zero. 5816 5817 rcutree.enable_rcu_lazy= [KNL] 5818 To save power, batch RCU callbacks and flush after 5819 delay, memory pressure or callback list growing too 5820 big. 5821 5822 rcutree.rcu_normal_wake_from_gp= [KNL] 5823 Reduces a latency of synchronize_rcu() call. This approach 5824 maintains its own track of synchronize_rcu() callers, so it 5825 does not interact with regular callbacks because it does not 5826 use a call_rcu[_hurry]() path. Please note, this is for a 5827 normal grace period. 5828 5829 How to enable it: 5830 5831 echo 1 > /sys/module/rcutree/parameters/rcu_normal_wake_from_gp 5832 or pass a boot parameter "rcutree.rcu_normal_wake_from_gp=1" 5833 5834 Default is 1 if num_possible_cpus() <= 16 and it is not explicitly 5835 disabled by the boot parameter passing 0. 5836 5837 rcuscale.gp_async= [KNL] 5838 Measure performance of asynchronous 5839 grace-period primitives such as call_rcu(). 5840 5841 rcuscale.gp_async_max= [KNL] 5842 Specify the maximum number of outstanding 5843 callbacks per writer thread. When a writer 5844 thread exceeds this limit, it invokes the 5845 corresponding flavor of rcu_barrier() to allow 5846 previously posted callbacks to drain. 5847 5848 rcuscale.gp_exp= [KNL] 5849 Measure performance of expedited synchronous 5850 grace-period primitives. 5851 5852 rcuscale.holdoff= [KNL] 5853 Set test-start holdoff period. The purpose of 5854 this parameter is to delay the start of the 5855 test until boot completes in order to avoid 5856 interference. 5857 5858 rcuscale.kfree_by_call_rcu= [KNL] 5859 In kernels built with CONFIG_RCU_LAZY=y, test 5860 call_rcu() instead of kfree_rcu(). 5861 5862 rcuscale.kfree_mult= [KNL] 5863 Instead of allocating an object of size kfree_obj, 5864 allocate one of kfree_mult * sizeof(kfree_obj). 5865 Defaults to 1. 5866 5867 rcuscale.kfree_rcu_test= [KNL] 5868 Set to measure performance of kfree_rcu() flooding. 5869 5870 rcuscale.kfree_rcu_test_double= [KNL] 5871 Test the double-argument variant of kfree_rcu(). 5872 If this parameter has the same value as 5873 rcuscale.kfree_rcu_test_single, both the single- 5874 and double-argument variants are tested. 5875 5876 rcuscale.kfree_rcu_test_single= [KNL] 5877 Test the single-argument variant of kfree_rcu(). 5878 If this parameter has the same value as 5879 rcuscale.kfree_rcu_test_double, both the single- 5880 and double-argument variants are tested. 5881 5882 rcuscale.kfree_nthreads= [KNL] 5883 The number of threads running loops of kfree_rcu(). 5884 5885 rcuscale.kfree_alloc_num= [KNL] 5886 Number of allocations and frees done in an iteration. 5887 5888 rcuscale.kfree_loops= [KNL] 5889 Number of loops doing rcuscale.kfree_alloc_num number 5890 of allocations and frees. 5891 5892 rcuscale.minruntime= [KNL] 5893 Set the minimum test run time in seconds. This 5894 does not affect the data-collection interval, 5895 but instead allows better measurement of things 5896 like CPU consumption. 5897 5898 rcuscale.nreaders= [KNL] 5899 Set number of RCU readers. The value -1 selects 5900 N, where N is the number of CPUs. A value 5901 "n" less than -1 selects N-n+1, where N is again 5902 the number of CPUs. For example, -2 selects N 5903 (the number of CPUs), -3 selects N+1, and so on. 5904 A value of "n" less than or equal to -N selects 5905 a single reader. 5906 5907 rcuscale.nwriters= [KNL] 5908 Set number of RCU writers. The values operate 5909 the same as for rcuscale.nreaders. 5910 N, where N is the number of CPUs 5911 5912 rcuscale.scale_type= [KNL] 5913 Specify the RCU implementation to test. 5914 5915 rcuscale.shutdown= [KNL] 5916 Shut the system down after performance tests 5917 complete. This is useful for hands-off automated 5918 testing. 5919 5920 rcuscale.verbose= [KNL] 5921 Enable additional printk() statements. 5922 5923 rcuscale.writer_holdoff= [KNL] 5924 Write-side holdoff between grace periods, 5925 in microseconds. The default of zero says 5926 no holdoff. 5927 5928 rcuscale.writer_holdoff_jiffies= [KNL] 5929 Additional write-side holdoff between grace 5930 periods, but in jiffies. The default of zero 5931 says no holdoff. 5932 5933 rcutorture.fqs_duration= [KNL] 5934 Set duration of force_quiescent_state bursts 5935 in microseconds. 5936 5937 rcutorture.fqs_holdoff= [KNL] 5938 Set holdoff time within force_quiescent_state bursts 5939 in microseconds. 5940 5941 rcutorture.fqs_stutter= [KNL] 5942 Set wait time between force_quiescent_state bursts 5943 in seconds. 5944 5945 rcutorture.fwd_progress= [KNL] 5946 Specifies the number of kthreads to be used 5947 for RCU grace-period forward-progress testing 5948 for the types of RCU supporting this notion. 5949 Defaults to 1 kthread, values less than zero or 5950 greater than the number of CPUs cause the number 5951 of CPUs to be used. 5952 5953 rcutorture.fwd_progress_div= [KNL] 5954 Specify the fraction of a CPU-stall-warning 5955 period to do tight-loop forward-progress testing. 5956 5957 rcutorture.fwd_progress_holdoff= [KNL] 5958 Number of seconds to wait between successive 5959 forward-progress tests. 5960 5961 rcutorture.fwd_progress_need_resched= [KNL] 5962 Enclose cond_resched() calls within checks for 5963 need_resched() during tight-loop forward-progress 5964 testing. 5965 5966 rcutorture.gp_cond= [KNL] 5967 Use conditional/asynchronous update-side 5968 normal-grace-period primitives, if available. 5969 5970 rcutorture.gp_cond_exp= [KNL] 5971 Use conditional/asynchronous update-side 5972 expedited-grace-period primitives, if available. 5973 5974 rcutorture.gp_cond_full= [KNL] 5975 Use conditional/asynchronous update-side 5976 normal-grace-period primitives that also take 5977 concurrent expedited grace periods into account, 5978 if available. 5979 5980 rcutorture.gp_cond_exp_full= [KNL] 5981 Use conditional/asynchronous update-side 5982 expedited-grace-period primitives that also take 5983 concurrent normal grace periods into account, 5984 if available. 5985 5986 rcutorture.gp_cond_wi= [KNL] 5987 Nominal wait interval for normal conditional 5988 grace periods (specified by rcutorture's 5989 gp_cond and gp_cond_full module parameters), 5990 in microseconds. The actual wait interval will 5991 be randomly selected to nanosecond granularity up 5992 to this wait interval. Defaults to 16 jiffies, 5993 for example, 16,000 microseconds on a system 5994 with HZ=1000. 5995 5996 rcutorture.gp_cond_wi_exp= [KNL] 5997 Nominal wait interval for expedited conditional 5998 grace periods (specified by rcutorture's 5999 gp_cond_exp and gp_cond_exp_full module 6000 parameters), in microseconds. The actual wait 6001 interval will be randomly selected to nanosecond 6002 granularity up to this wait interval. Defaults to 6003 128 microseconds. 6004 6005 rcutorture.gp_exp= [KNL] 6006 Use expedited update-side primitives, if available. 6007 6008 rcutorture.gp_normal= [KNL] 6009 Use normal (non-expedited) asynchronous 6010 update-side primitives, if available. 6011 6012 rcutorture.gp_poll= [KNL] 6013 Use polled update-side normal-grace-period 6014 primitives, if available. 6015 6016 rcutorture.gp_poll_exp= [KNL] 6017 Use polled update-side expedited-grace-period 6018 primitives, if available. 6019 6020 rcutorture.gp_poll_full= [KNL] 6021 Use polled update-side normal-grace-period 6022 primitives that also take concurrent expedited 6023 grace periods into account, if available. 6024 6025 rcutorture.gp_poll_exp_full= [KNL] 6026 Use polled update-side expedited-grace-period 6027 primitives that also take concurrent normal 6028 grace periods into account, if available. 6029 6030 rcutorture.gp_poll_wi= [KNL] 6031 Nominal wait interval for normal conditional 6032 grace periods (specified by rcutorture's 6033 gp_poll and gp_poll_full module parameters), 6034 in microseconds. The actual wait interval will 6035 be randomly selected to nanosecond granularity up 6036 to this wait interval. Defaults to 16 jiffies, 6037 for example, 16,000 microseconds on a system 6038 with HZ=1000. 6039 6040 rcutorture.gp_poll_wi_exp= [KNL] 6041 Nominal wait interval for expedited conditional 6042 grace periods (specified by rcutorture's 6043 gp_poll_exp and gp_poll_exp_full module 6044 parameters), in microseconds. The actual wait 6045 interval will be randomly selected to nanosecond 6046 granularity up to this wait interval. Defaults to 6047 128 microseconds. 6048 6049 rcutorture.gp_sync= [KNL] 6050 Use normal (non-expedited) synchronous 6051 update-side primitives, if available. If all 6052 of rcutorture.gp_cond=, rcutorture.gp_exp=, 6053 rcutorture.gp_normal=, and rcutorture.gp_sync= 6054 are zero, rcutorture acts as if is interpreted 6055 they are all non-zero. 6056 6057 rcutorture.gpwrap_lag= [KNL] 6058 Enable grace-period wrap lag testing. Setting 6059 to false prevents the gpwrap lag test from 6060 running. Default is true. 6061 6062 rcutorture.gpwrap_lag_gps= [KNL] 6063 Set the value for grace-period wrap lag during 6064 active lag testing periods. This controls how many 6065 grace periods differences we tolerate between 6066 rdp and rnp's gp_seq before setting overflow flag. 6067 The default is always set to 8. 6068 6069 rcutorture.gpwrap_lag_cycle_mins= [KNL] 6070 Set the total cycle duration for gpwrap lag 6071 testing in minutes. This is the total time for 6072 one complete cycle of active and inactive 6073 testing periods. Default is 30 minutes. 6074 6075 rcutorture.gpwrap_lag_active_mins= [KNL] 6076 Set the duration for which gpwrap lag is active 6077 within each cycle, in minutes. During this time, 6078 the grace-period wrap lag will be set to the 6079 value specified by gpwrap_lag_gps. Default is 6080 5 minutes. 6081 6082 rcutorture.irqreader= [KNL] 6083 Run RCU readers from irq handlers, or, more 6084 accurately, from a timer handler. Not all RCU 6085 flavors take kindly to this sort of thing. 6086 6087 rcutorture.leakpointer= [KNL] 6088 Leak an RCU-protected pointer out of the reader. 6089 This can of course result in splats, and is 6090 intended to test the ability of things like 6091 CONFIG_RCU_STRICT_GRACE_PERIOD=y to detect 6092 such leaks. 6093 6094 rcutorture.n_barrier_cbs= [KNL] 6095 Set callbacks/threads for rcu_barrier() testing. 6096 6097 rcutorture.nfakewriters= [KNL] 6098 Set number of concurrent RCU writers. These just 6099 stress RCU, they don't participate in the actual 6100 test, hence the "fake". 6101 6102 rcutorture.nocbs_nthreads= [KNL] 6103 Set number of RCU callback-offload togglers. 6104 Zero (the default) disables toggling. 6105 6106 rcutorture.nocbs_toggle= [KNL] 6107 Set the delay in milliseconds between successive 6108 callback-offload toggling attempts. 6109 6110 rcutorture.nreaders= [KNL] 6111 Set number of RCU readers. The value -1 selects 6112 N-1, where N is the number of CPUs. A value 6113 "n" less than -1 selects N-n-2, where N is again 6114 the number of CPUs. For example, -2 selects N 6115 (the number of CPUs), -3 selects N+1, and so on. 6116 6117 rcutorture.object_debug= [KNL] 6118 Enable debug-object double-call_rcu() testing. 6119 6120 rcutorture.onoff_holdoff= [KNL] 6121 Set time (s) after boot for CPU-hotplug testing. 6122 6123 rcutorture.onoff_interval= [KNL] 6124 Set time (jiffies) between CPU-hotplug operations, 6125 or zero to disable CPU-hotplug testing. 6126 6127 rcutorture.preempt_duration= [KNL] 6128 Set duration (in milliseconds) of preemptions 6129 by a high-priority FIFO real-time task. Set to 6130 zero (the default) to disable. The CPUs to 6131 preempt are selected randomly from the set that 6132 are online at a given point in time. Races with 6133 CPUs going offline are ignored, with that attempt 6134 at preemption skipped. 6135 6136 rcutorture.preempt_interval= [KNL] 6137 Set interval (in milliseconds, defaulting to one 6138 second) between preemptions by a high-priority 6139 FIFO real-time task. This delay is mediated 6140 by an hrtimer and is further fuzzed to avoid 6141 inadvertent synchronizations. 6142 6143 rcutorture.read_exit_burst= [KNL] 6144 The number of times in a given read-then-exit 6145 episode that a set of read-then-exit kthreads 6146 is spawned. 6147 6148 rcutorture.read_exit_delay= [KNL] 6149 The delay, in seconds, between successive 6150 read-then-exit testing episodes. 6151 6152 rcutorture.reader_flavor= [KNL] 6153 A bit mask indicating which readers to use. 6154 If there is more than one bit set, the readers 6155 are entered from low-order bit up, and are 6156 exited in the opposite order. For SRCU, the 6157 0x1 bit is normal readers, 0x2 NMI-safe readers, 6158 and 0x4 light-weight readers. 6159 6160 rcutorture.shuffle_interval= [KNL] 6161 Set task-shuffle interval (s). Shuffling tasks 6162 allows some CPUs to go into dyntick-idle mode 6163 during the rcutorture test. 6164 6165 rcutorture.shutdown_secs= [KNL] 6166 Set time (s) after boot system shutdown. This 6167 is useful for hands-off automated testing. 6168 6169 rcutorture.stall_cpu= [KNL] 6170 Duration of CPU stall (s) to test RCU CPU stall 6171 warnings, zero to disable. 6172 6173 rcutorture.stall_cpu_block= [KNL] 6174 Sleep while stalling if set. This will result 6175 in warnings from preemptible RCU in addition to 6176 any other stall-related activity. Note that 6177 in kernels built with CONFIG_PREEMPTION=n and 6178 CONFIG_PREEMPT_COUNT=y, this parameter will 6179 cause the CPU to pass through a quiescent state. 6180 Given CONFIG_PREEMPTION=n, this will suppress 6181 RCU CPU stall warnings, but will instead result 6182 in scheduling-while-atomic splats. 6183 6184 Use of this module parameter results in splats. 6185 6186 6187 rcutorture.stall_cpu_holdoff= [KNL] 6188 Time to wait (s) after boot before inducing stall. 6189 6190 rcutorture.stall_cpu_irqsoff= [KNL] 6191 Disable interrupts while stalling if set, but only 6192 on the first stall in the set. 6193 6194 rcutorture.stall_cpu_repeat= [KNL] 6195 Number of times to repeat the stall sequence, 6196 so that rcutorture.stall_cpu_repeat=3 will result 6197 in four stall sequences. 6198 6199 rcutorture.stall_gp_kthread= [KNL] 6200 Duration (s) of forced sleep within RCU 6201 grace-period kthread to test RCU CPU stall 6202 warnings, zero to disable. If both stall_cpu 6203 and stall_gp_kthread are specified, the 6204 kthread is starved first, then the CPU. 6205 6206 rcutorture.stat_interval= [KNL] 6207 Time (s) between statistics printk()s. 6208 6209 rcutorture.stutter= [KNL] 6210 Time (s) to stutter testing, for example, specifying 6211 five seconds causes the test to run for five seconds, 6212 wait for five seconds, and so on. This tests RCU's 6213 ability to transition abruptly to and from idle. 6214 6215 rcutorture.test_boost= [KNL] 6216 Test RCU priority boosting? 0=no, 1=maybe, 2=yes. 6217 "Maybe" means test if the RCU implementation 6218 under test support RCU priority boosting. 6219 6220 rcutorture.test_boost_duration= [KNL] 6221 Duration (s) of each individual boost test. 6222 6223 rcutorture.test_boost_holdoff= [KNL] 6224 Holdoff time (s) from start of test to the start 6225 of RCU priority-boost testing. Defaults to zero, 6226 that is, no holdoff. 6227 6228 rcutorture.test_boost_interval= [KNL] 6229 Interval (s) between each boost test. 6230 6231 rcutorture.test_no_idle_hz= [KNL] 6232 Test RCU's dyntick-idle handling. See also the 6233 rcutorture.shuffle_interval parameter. 6234 6235 rcutorture.torture_type= [KNL] 6236 Specify the RCU implementation to test. 6237 6238 rcutorture.verbose= [KNL] 6239 Enable additional printk() statements. 6240 6241 rcupdate.rcu_cpu_stall_ftrace_dump= [KNL] 6242 Dump ftrace buffer after reporting RCU CPU 6243 stall warning. 6244 6245 rcupdate.rcu_cpu_stall_notifiers= [KNL] 6246 Provide RCU CPU stall notifiers, but see the 6247 warnings in the RCU_CPU_STALL_NOTIFIER Kconfig 6248 option's help text. TL;DR: You almost certainly 6249 do not want rcupdate.rcu_cpu_stall_notifiers. 6250 6251 rcupdate.rcu_cpu_stall_suppress= [KNL] 6252 Suppress RCU CPU stall warning messages. 6253 6254 rcupdate.rcu_cpu_stall_suppress_at_boot= [KNL] 6255 Suppress RCU CPU stall warning messages and 6256 rcutorture writer stall warnings that occur 6257 during early boot, that is, during the time 6258 before the init task is spawned. 6259 6260 rcupdate.rcu_cpu_stall_timeout= [KNL] 6261 Set timeout for RCU CPU stall warning messages. 6262 The value is in seconds and the maximum allowed 6263 value is 300 seconds. 6264 6265 rcupdate.rcu_exp_cpu_stall_timeout= [KNL] 6266 Set timeout for expedited RCU CPU stall warning 6267 messages. The value is in milliseconds 6268 and the maximum allowed value is 21000 6269 milliseconds. Please note that this value is 6270 adjusted to an arch timer tick resolution. 6271 Setting this to zero causes the value from 6272 rcupdate.rcu_cpu_stall_timeout to be used (after 6273 conversion from seconds to milliseconds). 6274 6275 rcupdate.rcu_cpu_stall_cputime= [KNL] 6276 Provide statistics on the cputime and count of 6277 interrupts and tasks during the sampling period. For 6278 multiple continuous RCU stalls, all sampling periods 6279 begin at half of the first RCU stall timeout. 6280 6281 rcupdate.rcu_exp_stall_task_details= [KNL] 6282 Print stack dumps of any tasks blocking the 6283 current expedited RCU grace period during an 6284 expedited RCU CPU stall warning. 6285 6286 rcupdate.rcu_expedited= [KNL] 6287 Use expedited grace-period primitives, for 6288 example, synchronize_rcu_expedited() instead 6289 of synchronize_rcu(). This reduces latency, 6290 but can increase CPU utilization, degrade 6291 real-time latency, and degrade energy efficiency. 6292 No effect on CONFIG_TINY_RCU kernels. 6293 6294 rcupdate.rcu_normal= [KNL] 6295 Use only normal grace-period primitives, 6296 for example, synchronize_rcu() instead of 6297 synchronize_rcu_expedited(). This improves 6298 real-time latency, CPU utilization, and 6299 energy efficiency, but can expose users to 6300 increased grace-period latency. This parameter 6301 overrides rcupdate.rcu_expedited. No effect on 6302 CONFIG_TINY_RCU kernels. 6303 6304 rcupdate.rcu_normal_after_boot= [KNL] 6305 Once boot has completed (that is, after 6306 rcu_end_inkernel_boot() has been invoked), use 6307 only normal grace-period primitives. No effect 6308 on CONFIG_TINY_RCU kernels. 6309 6310 But note that CONFIG_PREEMPT_RT=y kernels enables 6311 this kernel boot parameter, forcibly setting 6312 it to the value one, that is, converting any 6313 post-boot attempt at an expedited RCU grace 6314 period to instead use normal non-expedited 6315 grace-period processing. 6316 6317 rcupdate.rcu_task_collapse_lim= [KNL] 6318 Set the maximum number of callbacks present 6319 at the beginning of a grace period that allows 6320 the RCU Tasks flavors to collapse back to using 6321 a single callback queue. This switching only 6322 occurs when rcupdate.rcu_task_enqueue_lim is 6323 set to the default value of -1. 6324 6325 rcupdate.rcu_task_contend_lim= [KNL] 6326 Set the minimum number of callback-queuing-time 6327 lock-contention events per jiffy required to 6328 cause the RCU Tasks flavors to switch to per-CPU 6329 callback queuing. This switching only occurs 6330 when rcupdate.rcu_task_enqueue_lim is set to 6331 the default value of -1. 6332 6333 rcupdate.rcu_task_enqueue_lim= [KNL] 6334 Set the number of callback queues to use for the 6335 RCU Tasks family of RCU flavors. The default 6336 of -1 allows this to be automatically (and 6337 dynamically) adjusted. This parameter is intended 6338 for use in testing. 6339 6340 rcupdate.rcu_task_lazy_lim= [KNL] 6341 Number of callbacks on a given CPU that will 6342 cancel laziness on that CPU. Use -1 to disable 6343 cancellation of laziness, but be advised that 6344 doing so increases the danger of OOM due to 6345 callback flooding. 6346 6347 rcupdate.rcu_task_stall_info= [KNL] 6348 Set initial timeout in jiffies for RCU task stall 6349 informational messages, which give some indication 6350 of the problem for those not patient enough to 6351 wait for ten minutes. Informational messages are 6352 only printed prior to the stall-warning message 6353 for a given grace period. Disable with a value 6354 less than or equal to zero. Defaults to ten 6355 seconds. A change in value does not take effect 6356 until the beginning of the next grace period. 6357 6358 rcupdate.rcu_task_stall_info_mult= [KNL] 6359 Multiplier for time interval between successive 6360 RCU task stall informational messages for a given 6361 RCU tasks grace period. This value is clamped 6362 to one through ten, inclusive. It defaults to 6363 the value three, so that the first informational 6364 message is printed 10 seconds into the grace 6365 period, the second at 40 seconds, the third at 6366 160 seconds, and then the stall warning at 600 6367 seconds would prevent a fourth at 640 seconds. 6368 6369 rcupdate.rcu_task_stall_timeout= [KNL] 6370 Set timeout in jiffies for RCU task stall 6371 warning messages. Disable with a value less 6372 than or equal to zero. Defaults to ten minutes. 6373 A change in value does not take effect until 6374 the beginning of the next grace period. 6375 6376 rcupdate.rcu_tasks_lazy_ms= [KNL] 6377 Set timeout in milliseconds RCU Tasks asynchronous 6378 callback batching for call_rcu_tasks(). 6379 A negative value will take the default. A value 6380 of zero will disable batching. Batching is 6381 always disabled for synchronize_rcu_tasks(). 6382 6383 rcupdate.rcu_self_test= [KNL] 6384 Run the RCU early boot self tests 6385 6386 rdinit= [KNL] 6387 Format: <full_path> 6388 Run specified binary instead of /init from the ramdisk, 6389 used for early userspace startup. See initrd. 6390 6391 rdrand= [X86,EARLY] 6392 force - Override the decision by the kernel to hide the 6393 advertisement of RDRAND support (this affects 6394 certain AMD processors because of buggy BIOS 6395 support, specifically around the suspend/resume 6396 path). 6397 6398 rdt= [HW,X86,RDT] 6399 Turn on/off individual RDT features. List is: 6400 cmt, mbmtotal, mbmlocal, l3cat, l3cdp, l2cat, l2cdp, 6401 mba, smba, bmec, abmc, sdciae, energy[:guid], 6402 perf[:guid]. 6403 E.g. to turn on cmt and turn off mba use: 6404 rdt=cmt,!mba 6405 To turn off all energy telemetry monitoring and ensure that 6406 perf telemetry monitoring associated with guid 0x12345 6407 is enabled use: 6408 rdt=!energy,perf:0x12345 6409 6410 reboot= [KNL] 6411 Format (x86 or x86_64): 6412 [w[arm] | c[old] | h[ard] | s[oft] | g[pio]] | d[efault] \ 6413 [[,]s[mp]#### \ 6414 [[,]b[ios] | a[cpi] | k[bd] | t[riple] | e[fi] | p[ci]] \ 6415 [[,]f[orce] 6416 Where reboot_mode is one of warm (soft) or cold (hard) or gpio 6417 (prefix with 'panic_' to set mode for panic 6418 reboot only), 6419 reboot_type is one of bios, acpi, kbd, triple, efi, or pci, 6420 reboot_force is either force or not specified, 6421 reboot_cpu is s[mp]#### with #### being the processor 6422 to be used for rebooting. 6423 6424 acpi 6425 Use the ACPI RESET_REG in the FADT. If ACPI is not 6426 configured or the ACPI reset does not work, the reboot 6427 path attempts the reset using the keyboard controller. 6428 6429 bios 6430 Use the CPU reboot vector for warm reset 6431 6432 cold 6433 Set the cold reboot flag 6434 6435 default 6436 There are some built-in platform specific "quirks" 6437 - you may see: "reboot: <name> series board detected. 6438 Selecting <type> for reboots." In the case where you 6439 think the quirk is in error (e.g. you have newer BIOS, 6440 or newer board) using this option will ignore the 6441 built-in quirk table, and use the generic default 6442 reboot actions. 6443 6444 efi 6445 Use efi reset_system runtime service. If EFI is not 6446 configured or the EFI reset does not work, the reboot 6447 path attempts the reset using the keyboard controller. 6448 6449 force 6450 Don't stop other CPUs on reboot. This can make reboot 6451 more reliable in some cases. 6452 6453 kbd 6454 Use the keyboard controller. cold reset (default) 6455 6456 pci 6457 Use a write to the PCI config space register 0xcf9 to 6458 trigger reboot. 6459 6460 triple 6461 Force a triple fault (init) 6462 6463 warm 6464 Don't set the cold reboot flag 6465 6466 Using warm reset will be much faster especially on big 6467 memory systems because the BIOS will not go through 6468 the memory check. Disadvantage is that not all 6469 hardware will be completely reinitialized on reboot so 6470 there may be boot problems on some systems. 6471 6472 6473 refscale.holdoff= [KNL] 6474 Set test-start holdoff period. The purpose of 6475 this parameter is to delay the start of the 6476 test until boot completes in order to avoid 6477 interference. 6478 6479 refscale.lookup_instances= [KNL] 6480 Number of data elements to use for the forms of 6481 SLAB_TYPESAFE_BY_RCU testing. A negative number 6482 is negated and multiplied by nr_cpu_ids, while 6483 zero specifies nr_cpu_ids. 6484 6485 refscale.loops= [KNL] 6486 Set the number of loops over the synchronization 6487 primitive under test. Increasing this number 6488 reduces noise due to loop start/end overhead, 6489 but the default has already reduced the per-pass 6490 noise to a handful of picoseconds on ca. 2020 6491 x86 laptops. 6492 6493 refscale.nreaders= [KNL] 6494 Set number of readers. The default value of -1 6495 selects N, where N is roughly 75% of the number 6496 of CPUs. A value of zero is an interesting choice. 6497 6498 refscale.nruns= [KNL] 6499 Set number of runs, each of which is dumped onto 6500 the console log. 6501 6502 refscale.readdelay= [KNL] 6503 Set the read-side critical-section duration, 6504 measured in microseconds. 6505 6506 refscale.scale_type= [KNL] 6507 Specify the read-protection implementation to test. 6508 6509 refscale.shutdown= [KNL] 6510 Shut down the system at the end of the performance 6511 test. This defaults to 1 (shut it down) when 6512 refscale is built into the kernel and to 0 (leave 6513 it running) when refscale is built as a module. 6514 6515 refscale.verbose= [KNL] 6516 Enable additional printk() statements. 6517 6518 refscale.verbose_batched= [KNL] 6519 Batch the additional printk() statements. If zero 6520 (the default) or negative, print everything. Otherwise, 6521 print every Nth verbose statement, where N is the value 6522 specified. 6523 6524 regulator_ignore_unused 6525 [REGULATOR] 6526 Prevents regulator framework from disabling regulators 6527 that are unused, due no driver claiming them. This may 6528 be useful for debug and development, but should not be 6529 needed on a platform with proper driver support. 6530 6531 relax_domain_level= 6532 [KNL, SMP] Set scheduler's default relax_domain_level. 6533 See Documentation/admin-guide/cgroup-v1/cpusets.rst. 6534 6535 reserve= [KNL,BUGS] Force kernel to ignore I/O ports or memory 6536 Format: <base1>,<size1>[,<base2>,<size2>,...] 6537 Reserve I/O ports or memory so the kernel won't use 6538 them. If <base> is less than 0x10000, the region 6539 is assumed to be I/O ports; otherwise it is memory. 6540 6541 reserve_mem= [RAM] 6542 Format: nn[KMG]:<align>:<label> 6543 Reserve physical memory and label it with a name that 6544 other subsystems can use to access it. This is typically 6545 used for systems that do not wipe the RAM, and this command 6546 line will try to reserve the same physical memory on 6547 soft reboots. Note, it is not guaranteed to be the same 6548 location. For example, if anything about the system changes 6549 or if booting a different kernel. It can also fail if KASLR 6550 places the kernel at the location of where the RAM reservation 6551 was from a previous boot, the new reservation will be at a 6552 different location. 6553 Any subsystem using this feature must add a way to verify 6554 that the contents of the physical memory is from a previous 6555 boot, as there may be cases where the memory will not be 6556 located at the same location. 6557 6558 The format is size:align:label for example, to request 6559 12 megabytes of 4096 alignment for ramoops: 6560 6561 reserve_mem=12M:4096:oops ramoops.mem_name=oops 6562 6563 reservetop= [X86-32,EARLY] 6564 Format: nn[KMG] 6565 Reserves a hole at the top of the kernel virtual 6566 address space. 6567 6568 reset_devices [KNL] Force drivers to reset the underlying device 6569 during initialization. 6570 6571 resume= [SWSUSP] 6572 Specify the partition device for software suspend 6573 Format: 6574 {/dev/<dev> | PARTUUID=<uuid> | <int>:<int> | <hex>} 6575 6576 resume_offset= [SWSUSP] 6577 Specify the offset from the beginning of the partition 6578 given by "resume=" at which the swap header is located, 6579 in <PAGE_SIZE> units (needed only for swap files). 6580 See Documentation/power/swsusp-and-swap-files.rst 6581 6582 resumedelay= [HIBERNATION] Delay (in seconds) to pause before attempting to 6583 read the resume files 6584 6585 resumewait [HIBERNATION] Wait (indefinitely) for resume device to show up. 6586 Useful for devices that are detected asynchronously 6587 (e.g. USB and MMC devices). 6588 6589 retain_initrd [RAM] Keep initrd memory after extraction. After boot, it will 6590 be accessible via /sys/firmware/initrd. 6591 6592 retbleed= [X86] Control mitigation of RETBleed (Arbitrary 6593 Speculative Code Execution with Return Instructions) 6594 vulnerability. 6595 6596 AMD-based UNRET and IBPB mitigations alone do not stop 6597 sibling threads from influencing the predictions of other 6598 sibling threads. For that reason, STIBP is used on pro- 6599 cessors that support it, and mitigate SMT on processors 6600 that don't. 6601 6602 off - no mitigation 6603 auto - automatically select a mitigation 6604 auto,nosmt - automatically select a mitigation, 6605 disabling SMT if necessary for 6606 the full mitigation (only on Zen1 6607 and older without STIBP). 6608 ibpb - On AMD, mitigate short speculation 6609 windows on basic block boundaries too. 6610 Safe, highest perf impact. It also 6611 enables STIBP if present. Not suitable 6612 on Intel. 6613 ibpb,nosmt - Like "ibpb" above but will disable SMT 6614 when STIBP is not available. This is 6615 the alternative for systems which do not 6616 have STIBP. 6617 unret - Force enable untrained return thunks, 6618 only effective on AMD f15h-f17h based 6619 systems. 6620 unret,nosmt - Like unret, but will disable SMT when STIBP 6621 is not available. This is the alternative for 6622 systems which do not have STIBP. 6623 6624 Selecting 'auto' will choose a mitigation method at run 6625 time according to the CPU. 6626 6627 Not specifying this option is equivalent to retbleed=auto. 6628 6629 rfkill.default_state= 6630 0 "airplane mode". All wifi, bluetooth, wimax, gps, fm, 6631 etc. communication is blocked by default. 6632 1 Unblocked. 6633 6634 rfkill.master_switch_mode= 6635 0 The "airplane mode" button does nothing. 6636 1 The "airplane mode" button toggles between everything 6637 blocked and the previous configuration. 6638 2 The "airplane mode" button toggles between everything 6639 blocked and everything unblocked. 6640 6641 ring3mwait=disable 6642 [KNL] Disable ring 3 MONITOR/MWAIT feature on supported 6643 CPUs. 6644 6645 riscv_isa_fallback [RISCV,EARLY] 6646 When CONFIG_RISCV_ISA_FALLBACK is not enabled, permit 6647 falling back to detecting extension support by parsing 6648 "riscv,isa" property on devicetree systems when the 6649 replacement properties are not found. See the Kconfig 6650 entry for RISCV_ISA_FALLBACK. 6651 6652 riscv_nousercfi= 6653 all Disable user CFI ABI to userspace even if cpu extension 6654 are available. 6655 bcfi Disable user backward CFI ABI to userspace even if 6656 the shadow stack extension is available. 6657 fcfi Disable user forward CFI ABI to userspace even if the 6658 landing pad extension is available. 6659 6660 ro [KNL] Mount root device read-only on boot 6661 6662 rodata= [KNL,EARLY] 6663 on Mark read-only kernel memory as read-only (default). 6664 off Leave read-only kernel memory writable for debugging. 6665 noalias Mark read-only kernel memory as read-only but retain 6666 writable aliases in the direct map for regions outside 6667 of the kernel image. [arm64] 6668 6669 rockchip.usb_uart 6670 [EARLY] 6671 Enable the uart passthrough on the designated usb port 6672 on Rockchip SoCs. When active, the signals of the 6673 debug-uart get routed to the D+ and D- pins of the usb 6674 port and the regular usb controller gets disabled. 6675 6676 root= [KNL] Root filesystem 6677 Usually this is a block device specifier of some kind, 6678 see the early_lookup_bdev comment in 6679 block/early-lookup.c for details. 6680 Alternatively this can be "ram" for the legacy initial 6681 ramdisk, "nfs" and "cifs" for root on a network file 6682 system, or "mtd" and "ubi" for mounting from raw flash. 6683 6684 rootdelay= [KNL] Delay (in seconds) to pause before attempting to 6685 mount the root filesystem 6686 6687 rootflags= [KNL] Set root filesystem mount option string 6688 6689 rseq_slice_ext= [KNL] RSEQ based time slice extension 6690 Format: boolean 6691 Control enablement of RSEQ based time slice extension. 6692 Default is 'on'. 6693 6694 initramfs_options= [KNL] 6695 Specify mount options for the initramfs mount. 6696 6697 rootfstype= [KNL] Set root filesystem type 6698 6699 rootwait [KNL] Wait (indefinitely) for root device to show up. 6700 Useful for devices that are detected asynchronously 6701 (e.g. USB and MMC devices). 6702 6703 rootwait= [KNL] Maximum time (in seconds) to wait for root device 6704 to show up before attempting to mount the root 6705 filesystem. 6706 6707 rproc_mem=nn[KMG][@address] 6708 [KNL,ARM,CMA] Remoteproc physical memory block. 6709 Memory area to be used by remote processor image, 6710 managed by CMA. 6711 6712 rseq_debug= [KNL] Enable or disable restartable sequence 6713 debug mode. Defaults to CONFIG_RSEQ_DEBUG_DEFAULT_ENABLE. 6714 Format: <bool> 6715 6716 rt_group_sched= [KNL] Enable or disable SCHED_RR/FIFO group scheduling 6717 when CONFIG_RT_GROUP_SCHED=y. Defaults to 6718 !CONFIG_RT_GROUP_SCHED_DEFAULT_DISABLED. 6719 Format: <bool> 6720 6721 rw [KNL] Mount root device read-write on boot 6722 6723 S [KNL] Run init in single mode 6724 6725 s390_iommu= [HW,S390] 6726 Set s390 IOTLB flushing mode 6727 strict 6728 With strict flushing every unmap operation will result 6729 in an IOTLB flush. Default is lazy flushing before 6730 reuse, which is faster. Deprecated, equivalent to 6731 iommu.strict=1. 6732 6733 s390_iommu_aperture= [KNL,S390] 6734 Specifies the size of the per device DMA address space 6735 accessible through the DMA and IOMMU APIs as a decimal 6736 factor of the size of main memory. 6737 The default is 1 meaning that one can concurrently use 6738 as many DMA addresses as physical memory is installed, 6739 if supported by hardware, and thus map all of memory 6740 once. With a value of 2 one can map all of memory twice 6741 and so on. As a special case a factor of 0 imposes no 6742 restrictions other than those given by hardware at the 6743 cost of significant additional memory use for tables. 6744 6745 sa1100ir [NET] 6746 See drivers/net/irda/sa1100_ir.c. 6747 6748 sched_proxy_exec= [KNL] 6749 Enables or disables "proxy execution" style 6750 solution to mutex-based priority inversion. 6751 Format: <bool> 6752 6753 sched_verbose [KNL,EARLY] Enables verbose scheduler debug messages. 6754 6755 schedstats= [KNL,X86] Enable or disable scheduled statistics. 6756 Allowed values are enable and disable. This feature 6757 incurs a small amount of overhead in the scheduler 6758 but is useful for debugging and performance tuning. 6759 6760 sched_thermal_decay_shift= 6761 [Deprecated] 6762 [KNL, SMP] Set a decay shift for scheduler thermal 6763 pressure signal. Thermal pressure signal follows the 6764 default decay period of other scheduler pelt 6765 signals(usually 32 ms but configurable). Setting 6766 sched_thermal_decay_shift will left shift the decay 6767 period for the thermal pressure signal by the shift 6768 value. 6769 i.e. with the default pelt decay period of 32 ms 6770 sched_thermal_decay_shift thermal pressure decay pr 6771 1 64 ms 6772 2 128 ms 6773 and so on. 6774 Format: integer between 0 and 10 6775 Default is 0. 6776 6777 scftorture.holdoff= [KNL] 6778 Number of seconds to hold off before starting 6779 test. Defaults to zero for module insertion and 6780 to 10 seconds for built-in smp_call_function() 6781 tests. 6782 6783 scftorture.longwait= [KNL] 6784 Request ridiculously long waits randomly selected 6785 up to the chosen limit in seconds. Zero (the 6786 default) disables this feature. Please note 6787 that requesting even small non-zero numbers of 6788 seconds can result in RCU CPU stall warnings, 6789 softlockup complaints, and so on. 6790 6791 scftorture.nthreads= [KNL] 6792 Number of kthreads to spawn to invoke the 6793 smp_call_function() family of functions. 6794 The default of -1 specifies a number of kthreads 6795 equal to the number of CPUs. 6796 6797 scftorture.onoff_holdoff= [KNL] 6798 Number seconds to wait after the start of the 6799 test before initiating CPU-hotplug operations. 6800 6801 scftorture.onoff_interval= [KNL] 6802 Number seconds to wait between successive 6803 CPU-hotplug operations. Specifying zero (which 6804 is the default) disables CPU-hotplug operations. 6805 6806 scftorture.shutdown_secs= [KNL] 6807 The number of seconds following the start of the 6808 test after which to shut down the system. The 6809 default of zero avoids shutting down the system. 6810 Non-zero values are useful for automated tests. 6811 6812 scftorture.stat_interval= [KNL] 6813 The number of seconds between outputting the 6814 current test statistics to the console. A value 6815 of zero disables statistics output. 6816 6817 scftorture.stutter_cpus= [KNL] 6818 The number of jiffies to wait between each change 6819 to the set of CPUs under test. 6820 6821 scftorture.use_cpus_read_lock= [KNL] 6822 Use use_cpus_read_lock() instead of the default 6823 preempt_disable() to disable CPU hotplug 6824 while invoking one of the smp_call_function*() 6825 functions. 6826 6827 scftorture.verbose= [KNL] 6828 Enable additional printk() statements. 6829 6830 scftorture.weight_single= [KNL] 6831 The probability weighting to use for the 6832 smp_call_function_single() function with a zero 6833 "wait" parameter. A value of -1 selects the 6834 default if all other weights are -1. However, 6835 if at least one weight has some other value, a 6836 value of -1 will instead select a weight of zero. 6837 6838 scftorture.weight_single_wait= [KNL] 6839 The probability weighting to use for the 6840 smp_call_function_single() function with a 6841 non-zero "wait" parameter. See weight_single. 6842 6843 scftorture.weight_many= [KNL] 6844 The probability weighting to use for the 6845 smp_call_function_many() function with a zero 6846 "wait" parameter. See weight_single. 6847 Note well that setting a high probability for 6848 this weighting can place serious IPI load 6849 on the system. 6850 6851 scftorture.weight_many_wait= [KNL] 6852 The probability weighting to use for the 6853 smp_call_function_many() function with a 6854 non-zero "wait" parameter. See weight_single 6855 and weight_many. 6856 6857 scftorture.weight_all= [KNL] 6858 The probability weighting to use for the 6859 smp_call_function_all() function with a zero 6860 "wait" parameter. See weight_single and 6861 weight_many. 6862 6863 scftorture.weight_all_wait= [KNL] 6864 The probability weighting to use for the 6865 smp_call_function_all() function with a 6866 non-zero "wait" parameter. See weight_single 6867 and weight_many. 6868 6869 sdw_mclk_divider=[SDW] 6870 Specify the MCLK divider for Intel SoundWire buses in 6871 case the BIOS does not provide the clock rate properly. 6872 6873 skew_tick= [KNL,EARLY] Offset the periodic timer tick per cpu to mitigate 6874 xtime_lock contention on larger systems, and/or RCU lock 6875 contention on all systems with CONFIG_MAXSMP set. 6876 Format: { "0" | "1" } 6877 0 -- disable. (may be 1 via CONFIG_CMDLINE="skew_tick=1" 6878 1 -- enable. 6879 Note: increases power consumption, thus should only be 6880 enabled if running jitter sensitive (HPC/RT) workloads. 6881 6882 security= [SECURITY] Choose a legacy "major" security module to 6883 enable at boot. This has been deprecated by the 6884 "lsm=" parameter. 6885 6886 selinux= [SELINUX] Disable or enable SELinux at boot time. 6887 Format: { "0" | "1" } 6888 See security/selinux/Kconfig help text. 6889 0 -- disable. 6890 1 -- enable. 6891 Default value is 1. 6892 6893 serialnumber [BUGS=X86-32] 6894 6895 sev=option[,option...] [X86-64] 6896 6897 debug 6898 Enable debug messages. 6899 6900 nosnp 6901 Do not enable SEV-SNP (applies to host/hypervisor 6902 only). Setting 'nosnp' avoids the RMP check overhead 6903 in memory accesses when users do not want to run 6904 SEV-SNP guests. 6905 6906 shapers= [NET] 6907 Maximal number of shapers. 6908 6909 show_lapic= [APIC,X86] Advanced Programmable Interrupt Controller 6910 Limit apic dumping. The parameter defines the maximal 6911 number of local apics being dumped. Also it is possible 6912 to set it to "all" by meaning -- no limit here. 6913 Format: { 1 (default) | 2 | ... | all }. 6914 The parameter valid if only apic=debug or 6915 apic=verbose is specified. 6916 Example: apic=debug show_lapic=all 6917 6918 slab_debug[=options[,slabs][;[options[,slabs]]...] [MM] 6919 Enabling slab_debug allows one to determine the 6920 culprit if slab objects become corrupted. Enabling 6921 slab_debug can create guard zones around objects and 6922 may poison objects when not in use. Also tracks the 6923 last alloc / free. For more information see 6924 Documentation/admin-guide/mm/slab.rst. 6925 (slub_debug legacy name also accepted for now) 6926 6927 Using this option implies the "no_hash_pointers" 6928 option which can be undone by adding the 6929 "hash_pointers=always" option. 6930 6931 slab_max_order= [MM] 6932 Determines the maximum allowed order for slabs. 6933 A high setting may cause OOMs due to memory 6934 fragmentation. For more information see 6935 Documentation/admin-guide/mm/slab.rst. 6936 (slub_max_order legacy name also accepted for now) 6937 6938 slab_merge [MM] 6939 Enable merging of slabs with similar size when the 6940 kernel is built without CONFIG_SLAB_MERGE_DEFAULT. 6941 (slub_merge legacy name also accepted for now) 6942 6943 slab_min_objects= [MM] 6944 The minimum number of objects per slab. SLUB will 6945 increase the slab order up to slab_max_order to 6946 generate a sufficiently large slab able to contain 6947 the number of objects indicated. The higher the number 6948 of objects the smaller the overhead of tracking slabs 6949 and the less frequently locks need to be acquired. 6950 For more information see 6951 Documentation/admin-guide/mm/slab.rst. 6952 (slub_min_objects legacy name also accepted for now) 6953 6954 slab_min_order= [MM] 6955 Determines the minimum page order for slabs. Must be 6956 lower or equal to slab_max_order. For more information see 6957 Documentation/admin-guide/mm/slab.rst. 6958 (slub_min_order legacy name also accepted for now) 6959 6960 slab_nomerge [MM] 6961 Disable merging of slabs with similar size. May be 6962 necessary if there is some reason to distinguish 6963 allocs to different slabs, especially in hardened 6964 environments where the risk of heap overflows and 6965 layout control by attackers can usually be 6966 frustrated by disabling merging. This will reduce 6967 most of the exposure of a heap attack to a single 6968 cache (risks via metadata attacks are mostly 6969 unchanged). Debug options disable merging on their 6970 own. 6971 For more information see 6972 Documentation/admin-guide/mm/slab.rst. 6973 (slub_nomerge legacy name also accepted for now) 6974 6975 slab_strict_numa [MM] 6976 Support memory policies on a per object level 6977 in the slab allocator. The default is for memory 6978 policies to be applied at the folio level when 6979 a new folio is needed or a partial folio is 6980 retrieved from the lists. Increases overhead 6981 in the slab fastpaths but gains more accurate 6982 NUMA kernel object placement which helps with slow 6983 interconnects in NUMA systems. 6984 6985 slram= [HW,MTD] 6986 6987 smart2= [HW] 6988 Format: <io1>[,<io2>[,...,<io8>]] 6989 6990 smp.csd_lock_timeout= [KNL] 6991 Specify the period of time in milliseconds 6992 that smp_call_function() and friends will wait 6993 for a CPU to release the CSD lock. This is 6994 useful when diagnosing bugs involving CPUs 6995 disabling interrupts for extended periods 6996 of time. Defaults to 5,000 milliseconds, and 6997 setting a value of zero disables this feature. 6998 This feature may be more efficiently disabled 6999 using the csdlock_debug- kernel parameter. 7000 7001 smp.panic_on_ipistall= [KNL] 7002 If a csd_lock_timeout extends for more than 7003 the specified number of milliseconds, panic the 7004 system. By default, let CSD-lock acquisition 7005 take as long as they take. Specifying 300,000 7006 for this value provides a 5-minute timeout. 7007 7008 smsc-ircc2.nopnp [HW] Don't use PNP to discover SMC devices 7009 smsc-ircc2.ircc_cfg= [HW] Device configuration I/O port 7010 smsc-ircc2.ircc_sir= [HW] SIR base I/O port 7011 smsc-ircc2.ircc_fir= [HW] FIR base I/O port 7012 smsc-ircc2.ircc_irq= [HW] IRQ line 7013 smsc-ircc2.ircc_dma= [HW] DMA channel 7014 smsc-ircc2.ircc_transceiver= [HW] Transceiver type: 7015 0: Toshiba Satellite 1800 (GP data pin select) 7016 1: Fast pin select (default) 7017 2: ATC IRMode 7018 7019 smt= [KNL,MIPS,S390,EARLY] Set the maximum number of threads 7020 (logical CPUs) to use per physical CPU on systems 7021 capable of symmetric multithreading (SMT). Will 7022 be capped to the actual hardware limit. 7023 Format: <integer> 7024 Default: -1 (no limit) 7025 7026 softlockup_panic= 7027 [KNL] Should the soft-lockup detector generate panics. 7028 Format: <int> 7029 7030 A value of non-zero instructs the soft-lockup detector 7031 to panic the machine when a soft-lockup duration exceeds 7032 N thresholds. It is also controlled by the kernel.softlockup_panic 7033 sysctl and CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC, which is the 7034 respective build-time switch to that functionality. 7035 7036 softlockup_all_cpu_backtrace= 7037 [KNL] Should the soft-lockup detector generate 7038 backtraces on all cpus. 7039 Format: 0 | 1 7040 7041 sonypi.*= [HW] Sony Programmable I/O Control Device driver 7042 See Documentation/admin-guide/laptops/sonypi.rst 7043 7044 spectre_bhi= [X86] Control mitigation of Branch History Injection 7045 (BHI) vulnerability. This setting affects the 7046 deployment of the HW BHI control and the SW BHB 7047 clearing sequence. 7048 7049 on - (default) Enable the HW or SW mitigation as 7050 needed. This protects the kernel from 7051 both syscalls and VMs. 7052 vmexit - On systems which don't have the HW mitigation 7053 available, enable the SW mitigation on vmexit 7054 ONLY. On such systems, the host kernel is 7055 protected from VM-originated BHI attacks, but 7056 may still be vulnerable to syscall attacks. 7057 off - Disable the mitigation. 7058 7059 spectre_v2= [X86,EARLY] Control mitigation of Spectre variant 2 7060 (indirect branch speculation) vulnerability. 7061 The default operation protects the kernel from 7062 user space attacks. 7063 7064 on - unconditionally enable, implies 7065 spectre_v2_user=on 7066 off - unconditionally disable, implies 7067 spectre_v2_user=off 7068 auto - kernel detects whether your CPU model is 7069 vulnerable 7070 7071 Selecting 'on' will, and 'auto' may, choose a 7072 mitigation method at run time according to the 7073 CPU, the available microcode, the setting of the 7074 CONFIG_MITIGATION_RETPOLINE configuration option, 7075 and the compiler with which the kernel was built. 7076 7077 Selecting 'on' will also enable the mitigation 7078 against user space to user space task attacks. 7079 Selecting specific mitigation does not force enable 7080 user mitigations. 7081 7082 Selecting 'off' will disable both the kernel and 7083 the user space protections. 7084 7085 Specific mitigations can also be selected manually: 7086 7087 retpoline - replace indirect branches 7088 retpoline,generic - Retpolines 7089 retpoline,lfence - LFENCE; indirect branch 7090 retpoline,amd - alias for retpoline,lfence 7091 eibrs - Enhanced/Auto IBRS 7092 eibrs,retpoline - Enhanced/Auto IBRS + Retpolines 7093 eibrs,lfence - Enhanced/Auto IBRS + LFENCE 7094 ibrs - use IBRS to protect kernel 7095 7096 Not specifying this option is equivalent to 7097 spectre_v2=auto. 7098 7099 spectre_v2_user= 7100 [X86] Control mitigation of Spectre variant 2 7101 (indirect branch speculation) vulnerability between 7102 user space tasks 7103 7104 on - Unconditionally enable mitigations. Is 7105 enforced by spectre_v2=on 7106 7107 off - Unconditionally disable mitigations. Is 7108 enforced by spectre_v2=off 7109 7110 prctl - Indirect branch speculation is enabled, 7111 but mitigation can be enabled via prctl 7112 per thread. The mitigation control state 7113 is inherited on fork. 7114 7115 prctl,ibpb 7116 - Like "prctl" above, but only STIBP is 7117 controlled per thread. IBPB is issued 7118 always when switching between different user 7119 space processes. 7120 7121 seccomp 7122 - Same as "prctl" above, but all seccomp 7123 threads will enable the mitigation unless 7124 they explicitly opt out. 7125 7126 seccomp,ibpb 7127 - Like "seccomp" above, but only STIBP is 7128 controlled per thread. IBPB is issued 7129 always when switching between different 7130 user space processes. 7131 7132 auto - Kernel selects the mitigation depending on 7133 the available CPU features and vulnerability. 7134 7135 Default mitigation: "prctl" 7136 7137 Not specifying this option is equivalent to 7138 spectre_v2_user=auto. 7139 7140 spec_rstack_overflow= 7141 [X86,EARLY] Control RAS overflow mitigation on AMD Zen CPUs 7142 7143 off - Disable mitigation 7144 microcode - Enable microcode mitigation only 7145 safe-ret - Enable sw-only safe RET mitigation (default) 7146 ibpb - Enable mitigation by issuing IBPB on 7147 kernel entry 7148 ibpb-vmexit - Issue IBPB only on VMEXIT 7149 (cloud-specific mitigation) 7150 7151 spec_store_bypass_disable= 7152 [HW,EARLY] Control Speculative Store Bypass (SSB) Disable mitigation 7153 (Speculative Store Bypass vulnerability) 7154 7155 Certain CPUs are vulnerable to an exploit against a 7156 a common industry wide performance optimization known 7157 as "Speculative Store Bypass" in which recent stores 7158 to the same memory location may not be observed by 7159 later loads during speculative execution. The idea 7160 is that such stores are unlikely and that they can 7161 be detected prior to instruction retirement at the 7162 end of a particular speculation execution window. 7163 7164 In vulnerable processors, the speculatively forwarded 7165 store can be used in a cache side channel attack, for 7166 example to read memory to which the attacker does not 7167 directly have access (e.g. inside sandboxed code). 7168 7169 This parameter controls whether the Speculative Store 7170 Bypass optimization is used. 7171 7172 On x86 the options are: 7173 7174 on - Unconditionally disable Speculative Store Bypass 7175 off - Unconditionally enable Speculative Store Bypass 7176 auto - Kernel detects whether the CPU model contains an 7177 implementation of Speculative Store Bypass and 7178 picks the most appropriate mitigation. If the 7179 CPU is not vulnerable, "off" is selected. If the 7180 CPU is vulnerable the default mitigation is 7181 architecture and Kconfig dependent. See below. 7182 prctl - Control Speculative Store Bypass per thread 7183 via prctl. Speculative Store Bypass is enabled 7184 for a process by default. The state of the control 7185 is inherited on fork. 7186 seccomp - Same as "prctl" above, but all seccomp threads 7187 will disable SSB unless they explicitly opt out. 7188 7189 Default mitigations: 7190 X86: "prctl" 7191 7192 On powerpc the options are: 7193 7194 on,auto - On Power8 and Power9 insert a store-forwarding 7195 barrier on kernel entry and exit. On Power7 7196 perform a software flush on kernel entry and 7197 exit. 7198 off - No action. 7199 7200 Not specifying this option is equivalent to 7201 spec_store_bypass_disable=auto. 7202 7203 split_lock_detect= 7204 [X86] Enable split lock detection or bus lock detection 7205 7206 When enabled (and if hardware support is present), atomic 7207 instructions that access data across cache line 7208 boundaries will result in an alignment check exception 7209 for split lock detection or a debug exception for 7210 bus lock detection. 7211 7212 off - not enabled 7213 7214 warn - the kernel will emit rate-limited warnings 7215 about applications triggering the #AC 7216 exception or the #DB exception. This mode is 7217 the default on CPUs that support split lock 7218 detection or bus lock detection. Default 7219 behavior is by #AC if both features are 7220 enabled in hardware. 7221 7222 fatal - the kernel will send SIGBUS to applications 7223 that trigger the #AC exception or the #DB 7224 exception. Default behavior is by #AC if 7225 both features are enabled in hardware. 7226 7227 ratelimit:N - 7228 Set system wide rate limit to N bus locks 7229 per second for bus lock detection. 7230 0 < N <= 1000. 7231 7232 N/A for split lock detection. 7233 7234 7235 If an #AC exception is hit in the kernel or in 7236 firmware (i.e. not while executing in user mode) 7237 the kernel will oops in either "warn" or "fatal" 7238 mode. 7239 7240 #DB exception for bus lock is triggered only when 7241 CPL > 0. 7242 7243 srbds= [X86,INTEL,EARLY] 7244 Control the Special Register Buffer Data Sampling 7245 (SRBDS) mitigation. 7246 7247 Certain CPUs are vulnerable to an MDS-like 7248 exploit which can leak bits from the random 7249 number generator. 7250 7251 By default, this issue is mitigated by 7252 microcode. However, the microcode fix can cause 7253 the RDRAND and RDSEED instructions to become 7254 much slower. Among other effects, this will 7255 result in reduced throughput from /dev/urandom. 7256 7257 The microcode mitigation can be disabled with 7258 the following option: 7259 7260 off: Disable mitigation and remove 7261 performance impact to RDRAND and RDSEED 7262 7263 srcutree.big_cpu_lim [KNL] 7264 Specifies the number of CPUs constituting a 7265 large system, such that srcu_struct structures 7266 should immediately allocate an srcu_node array. 7267 This kernel-boot parameter defaults to 128, 7268 but takes effect only when the low-order four 7269 bits of srcutree.convert_to_big is equal to 3 7270 (decide at boot). 7271 7272 srcutree.convert_to_big [KNL] 7273 Specifies under what conditions an SRCU tree 7274 srcu_struct structure will be converted to big 7275 form, that is, with an rcu_node tree: 7276 7277 0: Never. 7278 1: At init_srcu_struct() time. 7279 2: When rcutorture decides to. 7280 3: Decide at boot time (default). 7281 0x1X: Above plus if high contention. 7282 7283 Either way, the srcu_node tree will be sized based 7284 on the actual runtime number of CPUs (nr_cpu_ids) 7285 instead of the compile-time CONFIG_NR_CPUS. 7286 7287 srcutree.counter_wrap_check [KNL] 7288 Specifies how frequently to check for 7289 grace-period sequence counter wrap for the 7290 srcu_data structure's ->srcu_gp_seq_needed field. 7291 The greater the number of bits set in this kernel 7292 parameter, the less frequently counter wrap will 7293 be checked for. Note that the bottom two bits 7294 are ignored. 7295 7296 srcutree.exp_holdoff [KNL] 7297 Specifies how many nanoseconds must elapse 7298 since the end of the last SRCU grace period for 7299 a given srcu_struct until the next normal SRCU 7300 grace period will be considered for automatic 7301 expediting. Set to zero to disable automatic 7302 expediting. 7303 7304 srcutree.srcu_max_nodelay [KNL] 7305 Specifies the number of no-delay instances 7306 per jiffy for which the SRCU grace period 7307 worker thread will be rescheduled with zero 7308 delay. Beyond this limit, worker thread will 7309 be rescheduled with a sleep delay of one jiffy. 7310 7311 srcutree.srcu_max_nodelay_phase [KNL] 7312 Specifies the per-grace-period phase, number of 7313 non-sleeping polls of readers. Beyond this limit, 7314 grace period worker thread will be rescheduled 7315 with a sleep delay of one jiffy, between each 7316 rescan of the readers, for a grace period phase. 7317 7318 srcutree.srcu_retry_check_delay [KNL] 7319 Specifies number of microseconds of non-sleeping 7320 delay between each non-sleeping poll of readers. 7321 7322 srcutree.small_contention_lim [KNL] 7323 Specifies the number of update-side contention 7324 events per jiffy will be tolerated before 7325 initiating a conversion of an srcu_struct 7326 structure to big form. Note that the value of 7327 srcutree.convert_to_big must have the 0x10 bit 7328 set for contention-based conversions to occur. 7329 7330 ssbd= [ARM64,HW,EARLY] 7331 Speculative Store Bypass Disable control 7332 7333 On CPUs that are vulnerable to the Speculative 7334 Store Bypass vulnerability and offer a 7335 firmware based mitigation, this parameter 7336 indicates how the mitigation should be used: 7337 7338 force-on: Unconditionally enable mitigation for 7339 for both kernel and userspace 7340 force-off: Unconditionally disable mitigation for 7341 for both kernel and userspace 7342 kernel: Always enable mitigation in the 7343 kernel, and offer a prctl interface 7344 to allow userspace to register its 7345 interest in being mitigated too. 7346 7347 stack_guard_gap= [MM] 7348 override the default stack gap protection. The value 7349 is in page units and it defines how many pages prior 7350 to (for stacks growing down) resp. after (for stacks 7351 growing up) the main stack are reserved for no other 7352 mapping. Default value is 256 pages. 7353 7354 stack_depot_disable= [KNL,EARLY] 7355 Setting this to true through kernel command line will 7356 disable the stack depot thereby saving the static memory 7357 consumed by the stack hash table. By default this is set 7358 to false. 7359 7360 stack_depot_max_pools= [KNL,EARLY] 7361 Specify the maximum number of pools to use for storing 7362 stack traces. Pools are allocated on-demand up to this 7363 limit. Default value is 8191 pools. 7364 7365 stacktrace [FTRACE] 7366 Enable the stack tracer on boot up. 7367 7368 stacktrace_filter=[function-list] 7369 [FTRACE] Limit the functions that the stack tracer 7370 will trace at boot up. function-list is a comma-separated 7371 list of functions. This list can be changed at run 7372 time by the stack_trace_filter file in the debugfs 7373 tracing directory. Note, this enables stack tracing 7374 and the stacktrace above is not needed. 7375 7376 sti= [PARISC,HW] 7377 Format: <num> 7378 Set the STI (builtin display/keyboard on the HP-PARISC 7379 machines) console (graphic card) which should be used 7380 as the initial boot-console. 7381 See also comment in drivers/video/console/sticore.c. 7382 7383 sti_font= [HW] 7384 See comment in drivers/video/console/sticore.c. 7385 7386 stifb= [HW] 7387 Format: bpp:<bpp1>[:<bpp2>[:<bpp3>...]] 7388 7389 strict_sas_size= 7390 [X86] 7391 Format: <bool> 7392 Enable or disable strict sigaltstack size checks 7393 against the required signal frame size which 7394 depends on the supported FPU features. This can 7395 be used to filter out binaries which have 7396 not yet been made aware of AT_MINSIGSTKSZ. 7397 7398 stress_hpt [PPC,EARLY] 7399 Limits the number of kernel HPT entries in the hash 7400 page table to increase the rate of hash page table 7401 faults on kernel addresses. 7402 7403 stress_slb [PPC,EARLY] 7404 Limits the number of kernel SLB entries, and flushes 7405 them frequently to increase the rate of SLB faults 7406 on kernel addresses. 7407 7408 no_slb_preload [PPC,EARLY] 7409 Disables slb preloading for userspace. 7410 7411 sunrpc.min_resvport= 7412 sunrpc.max_resvport= 7413 [NFS,SUNRPC] 7414 SunRPC servers often require that client requests 7415 originate from a privileged port (i.e. a port in the 7416 range 0 < portnr < 1024). 7417 An administrator who wishes to reserve some of these 7418 ports for other uses may adjust the range that the 7419 kernel's sunrpc client considers to be privileged 7420 using these two parameters to set the minimum and 7421 maximum port values. 7422 7423 sunrpc.svc_rpc_per_connection_limit= 7424 [NFS,SUNRPC] 7425 Limit the number of requests that the server will 7426 process in parallel from a single connection. 7427 The default value is 0 (no limit). 7428 7429 sunrpc.pool_mode= 7430 [NFS] 7431 Control how the NFS server code allocates CPUs to 7432 service thread pools. Depending on how many NICs 7433 you have and where their interrupts are bound, this 7434 option will affect which CPUs will do NFS serving. 7435 Note: this parameter cannot be changed while the 7436 NFS server is running. 7437 7438 auto the server chooses an appropriate mode 7439 automatically using heuristics 7440 global a single global pool contains all CPUs 7441 percpu one pool for each CPU 7442 pernode one pool for each NUMA node (equivalent 7443 to global on non-NUMA machines) 7444 7445 sunrpc.tcp_slot_table_entries= 7446 sunrpc.udp_slot_table_entries= 7447 [NFS,SUNRPC] 7448 Sets the upper limit on the number of simultaneous 7449 RPC calls that can be sent from the client to a 7450 server. Increasing these values may allow you to 7451 improve throughput, but will also increase the 7452 amount of memory reserved for use by the client. 7453 7454 suspend.pm_test_delay= 7455 [SUSPEND] 7456 Sets the number of seconds to remain in a suspend test 7457 mode before resuming the system (see 7458 /sys/power/pm_test). Only available when CONFIG_PM_DEBUG 7459 is set. Default value is 5. 7460 7461 svm= [PPC] 7462 Format: { on | off | y | n | 1 | 0 } 7463 This parameter controls use of the Protected 7464 Execution Facility on pSeries. 7465 7466 swiotlb= [ARM,PPC,MIPS,X86,S390,EARLY] 7467 Format: { <int> [,<int>] | force | noforce } 7468 <int> -- Number of I/O TLB slabs 7469 <int> -- Second integer after comma. Number of swiotlb 7470 areas with their own lock. Will be rounded up 7471 to a power of 2. 7472 force -- force using of bounce buffers even if they 7473 wouldn't be automatically used by the kernel 7474 noforce -- Never use bounce buffers (for debugging) 7475 7476 switches= [HW,M68k,EARLY] 7477 7478 sysctl.*= [KNL] 7479 Set a sysctl parameter, right before loading the init 7480 process, as if the value was written to the respective 7481 /proc/sys/... file. Both '.' and '/' are recognized as 7482 separators. Unrecognized parameters and invalid values 7483 are reported in the kernel log. Sysctls registered 7484 later by a loaded module cannot be set this way. 7485 Example: sysctl.vm.swappiness=40 7486 7487 sysrq_always_enabled 7488 [KNL] 7489 Ignore sysrq setting - this boot parameter will 7490 neutralize any effect of /proc/sys/kernel/sysrq. 7491 Useful for debugging. 7492 7493 tcpmhash_entries= [KNL,NET] 7494 Set the number of tcp_metrics_hash slots. 7495 Default value is 8192 or 16384 depending on total 7496 ram pages. This is used to specify the TCP metrics 7497 cache size. See Documentation/networking/ip-sysctl.rst 7498 "tcp_no_metrics_save" section for more details. 7499 7500 tdfx= [HW,DRM] 7501 7502 test_suspend= [SUSPEND] 7503 Format: { "mem" | "standby" | "freeze" }[,N] 7504 Specify "mem" (for Suspend-to-RAM) or "standby" (for 7505 standby suspend) or "freeze" (for suspend type freeze) 7506 as the system sleep state during system startup with 7507 the optional capability to repeat N number of times. 7508 The system is woken from this state using a 7509 wakeup-capable RTC alarm. 7510 7511 thash_entries= [KNL,NET] 7512 Set number of hash buckets for TCP connection 7513 7514 thermal.act= [HW,ACPI] 7515 -1: disable all active trip points in all thermal zones 7516 <degrees C>: override all lowest active trip points 7517 7518 thermal.crt= [HW,ACPI] 7519 -1: disable all critical trip points in all thermal zones 7520 <degrees C>: override all critical trip points 7521 7522 thermal.off= [HW,ACPI] 7523 1: disable ACPI thermal control 7524 7525 thermal.psv= [HW,ACPI] 7526 -1: disable all passive trip points 7527 <degrees C>: override all passive trip points to this 7528 value 7529 7530 thermal.tzp= [HW,ACPI] 7531 Specify global default ACPI thermal zone polling rate 7532 <deci-seconds>: poll all this frequency 7533 0: no polling (default) 7534 7535 thp_anon= [KNL] 7536 Format: <size>[KMG],<size>[KMG]:<state>;<size>[KMG]-<size>[KMG]:<state> 7537 state is one of "always", "madvise", "never" or "inherit". 7538 Control the default behavior of the system with respect 7539 to anonymous transparent hugepages. 7540 Can be used multiple times for multiple anon THP sizes. 7541 See Documentation/admin-guide/mm/transhuge.rst for more 7542 details. 7543 7544 threadirqs [KNL,EARLY] 7545 Force threading of all interrupt handlers except those 7546 marked explicitly IRQF_NO_THREAD. 7547 7548 thp_shmem= [KNL] 7549 Format: <size>[KMG],<size>[KMG]:<policy>;<size>[KMG]-<size>[KMG]:<policy> 7550 Control the default policy of each hugepage size for the 7551 internal shmem mount. <policy> is one of policies available 7552 for the shmem mount ("always", "inherit", "never", "within_size", 7553 and "advise"). 7554 It can be used multiple times for multiple shmem THP sizes. 7555 See Documentation/admin-guide/mm/transhuge.rst for more 7556 details. 7557 7558 topology= [S390,EARLY] 7559 Format: {off | on} 7560 Specify if the kernel should make use of the cpu 7561 topology information if the hardware supports this. 7562 The scheduler will make use of this information and 7563 e.g. base its process migration decisions on it. 7564 Default is on. 7565 7566 torture.disable_onoff_at_boot= [KNL] 7567 Prevent the CPU-hotplug component of torturing 7568 until after init has spawned. 7569 7570 torture.ftrace_dump_at_shutdown= [KNL] 7571 Dump the ftrace buffer at torture-test shutdown, 7572 even if there were no errors. This can be a 7573 very costly operation when many torture tests 7574 are running concurrently, especially on systems 7575 with rotating-rust storage. 7576 7577 torture.verbose_sleep_frequency= [KNL] 7578 Specifies how many verbose printk()s should be 7579 emitted between each sleep. The default of zero 7580 disables verbose-printk() sleeping. 7581 7582 torture.verbose_sleep_duration= [KNL] 7583 Duration of each verbose-printk() sleep in jiffies. 7584 7585 tpm.disable_pcr_integrity= [HW,TPM] 7586 Do not protect PCR registers from unintended physical 7587 access, or interposers in the bus by the means of 7588 having an integrity protected session wrapped around 7589 TPM2_PCR_Extend command. Consider this in a situation 7590 where TPM is heavily utilized by IMA, thus protection 7591 causing a major performance hit, and the space where 7592 machines are deployed is by other means guarded. 7593 7594 tpm_crb_ffa.busy_timeout_ms= [ARM64,TPM] 7595 Maximum time in milliseconds to retry sending a message 7596 to the TPM service before giving up. This parameter controls 7597 how long the system will continue retrying when the TPM 7598 service is busy. 7599 Format: <unsigned int> 7600 Default: 2000 (2 seconds) 7601 7602 tpm_suspend_pcr=[HW,TPM] 7603 Format: integer pcr id 7604 Specify that at suspend time, the tpm driver 7605 should extend the specified pcr with zeros, 7606 as a workaround for some chips which fail to 7607 flush the last written pcr on TPM_SaveState. 7608 This will guarantee that all the other pcrs 7609 are saved. 7610 7611 tpm_tis.interrupts= [HW,TPM] 7612 Enable interrupts for the MMIO based physical layer 7613 for the FIFO interface. By default it is set to false 7614 (0). For more information about TPM hardware interfaces 7615 defined by Trusted Computing Group (TCG) see 7616 https://trustedcomputinggroup.org/resource/pc-client-platform-tpm-profile-ptp-specification/ 7617 7618 tp_printk [FTRACE] 7619 Have the tracepoints sent to printk as well as the 7620 tracing ring buffer. This is useful for early boot up 7621 where the system hangs or reboots and does not give the 7622 option for reading the tracing buffer or performing a 7623 ftrace_dump_on_oops. 7624 7625 To turn off having tracepoints sent to printk, 7626 echo 0 > /proc/sys/kernel/tracepoint_printk 7627 Note, echoing 1 into this file without the 7628 tp_printk kernel cmdline option has no effect. 7629 7630 The tp_printk_stop_on_boot (see below) can also be used 7631 to stop the printing of events to console at 7632 late_initcall_sync. 7633 7634 ** CAUTION ** 7635 7636 Having tracepoints sent to printk() and activating high 7637 frequency tracepoints such as irq or sched, can cause 7638 the system to live lock. 7639 7640 tp_printk_stop_on_boot [FTRACE] 7641 When tp_printk (above) is set, it can cause a lot of noise 7642 on the console. It may be useful to only include the 7643 printing of events during boot up, as user space may 7644 make the system inoperable. 7645 7646 This command line option will stop the printing of events 7647 to console at the late_initcall_sync() time frame. 7648 7649 trace_buf_size=nn[KMG] 7650 [FTRACE] will set tracing buffer size on each cpu. 7651 7652 trace_clock= [FTRACE] Set the clock used for tracing events 7653 at boot up. 7654 local - Use the per CPU time stamp counter 7655 (converted into nanoseconds). Fast, but 7656 depending on the architecture, may not be 7657 in sync between CPUs. 7658 global - Event time stamps are synchronized across 7659 CPUs. May be slower than the local clock, 7660 but better for some race conditions. 7661 counter - Simple counting of events (1, 2, ..) 7662 note, some counts may be skipped due to the 7663 infrastructure grabbing the clock more than 7664 once per event. 7665 uptime - Use jiffies as the time stamp. 7666 perf - Use the same clock that perf uses. 7667 mono - Use ktime_get_mono_fast_ns() for time stamps. 7668 mono_raw - Use ktime_get_raw_fast_ns() for time 7669 stamps. 7670 boot - Use ktime_get_boot_fast_ns() for time stamps. 7671 Architectures may add more clocks. See 7672 Documentation/trace/ftrace.rst for more details. 7673 7674 trace_event=[event-list] 7675 [FTRACE] Set and start specified trace events in order 7676 to facilitate early boot debugging. The event-list is a 7677 comma-separated list of trace events to enable. See 7678 also Documentation/trace/events.rst 7679 7680 To enable modules, use :mod: keyword: 7681 7682 trace_event=:mod:<module> 7683 7684 The value before :mod: will only enable specific events 7685 that are part of the module. See the above mentioned 7686 document for more information. 7687 7688 trace_instance=[instance-info] 7689 [FTRACE] Create a ring buffer instance early in boot up. 7690 This will be listed in: 7691 7692 /sys/kernel/tracing/instances 7693 7694 Events can be enabled at the time the instance is created 7695 via: 7696 7697 trace_instance=<name>,<system1>:<event1>,<system2>:<event2> 7698 7699 Note, the "<system*>:" portion is optional if the event is 7700 unique. 7701 7702 trace_instance=foo,sched:sched_switch,irq_handler_entry,initcall 7703 7704 will enable the "sched_switch" event (note, the "sched:" is optional, and 7705 the same thing would happen if it was left off). The irq_handler_entry 7706 event, and all events under the "initcall" system. 7707 7708 Flags can be added to the instance to modify its behavior when it is 7709 created. The flags are separated by '^'. 7710 7711 The available flags are: 7712 7713 traceoff - Have the tracing instance tracing disabled after it is created. 7714 traceprintk - Have trace_printk() write into this trace instance 7715 (note, "printk" and "trace_printk" can also be used) 7716 7717 trace_instance=foo^traceoff^traceprintk,sched,irq 7718 7719 The flags must come before the defined events. 7720 7721 If memory has been reserved (see memmap for x86), the instance 7722 can use that memory: 7723 7724 memmap=12M$0x284500000 trace_instance=boot_map@0x284500000:12M 7725 7726 The above will create a "boot_map" instance that uses the physical 7727 memory at 0x284500000 that is 12Megs. The per CPU buffers of that 7728 instance will be split up accordingly. 7729 7730 Alternatively, the memory can be reserved by the reserve_mem option: 7731 7732 reserve_mem=12M:4096:trace trace_instance=boot_map@trace 7733 7734 This will reserve 12 megabytes at boot up with a 4096 byte alignment 7735 and place the ring buffer in this memory. Note that due to KASLR, the 7736 memory may not be the same location each time, which will not preserve 7737 the buffer content. 7738 7739 Also note that the layout of the ring buffer data may change between 7740 kernel versions where the validator will fail and reset the ring buffer 7741 if the layout is not the same as the previous kernel. 7742 7743 If the ring buffer is used for persistent bootups and has events enabled, 7744 it is recommend to disable tracing so that events from a previous boot do not 7745 mix with events of the current boot (unless you are debugging a random crash 7746 at boot up). 7747 7748 reserve_mem=12M:4096:trace trace_instance=boot_map^traceoff^traceprintk@trace,sched,irq 7749 7750 Note, saving the trace buffer across reboots does require that the system 7751 is set up to not wipe memory. For instance, CONFIG_RESET_ATTACK_MITIGATION 7752 can force a memory reset on boot which will clear any trace that was stored. 7753 This is just one of many ways that can clear memory. Make sure your system 7754 keeps the content of memory across reboots before relying on this option. 7755 7756 NB: Both the mapped address and size must be page aligned for the architecture. 7757 7758 See also Documentation/trace/debugging.rst 7759 7760 7761 trace_options=[option-list] 7762 [FTRACE] Enable or disable tracer options at boot. 7763 The option-list is a comma delimited list of options 7764 that can be enabled or disabled just as if you were 7765 to echo the option name into 7766 7767 /sys/kernel/tracing/trace_options 7768 7769 For example, to enable stacktrace option (to dump the 7770 stack trace of each event), add to the command line: 7771 7772 trace_options=stacktrace 7773 7774 See also Documentation/trace/ftrace.rst "trace options" 7775 section. 7776 7777 trace_trigger=[trigger-list] 7778 [FTRACE] Add an event trigger on specific events. 7779 Set a trigger on top of a specific event, with an optional 7780 filter. 7781 7782 The format is "trace_trigger=<event>.<trigger>[ if <filter>],..." 7783 Where more than one trigger may be specified that are comma delimited. 7784 7785 For example: 7786 7787 trace_trigger="sched_switch.stacktrace if prev_state == 2" 7788 7789 The above will enable the "stacktrace" trigger on the "sched_switch" 7790 event but only trigger it if the "prev_state" of the "sched_switch" 7791 event is "2" (TASK_UNINTERRUPTIBLE). 7792 7793 See also "Event triggers" in Documentation/trace/events.rst 7794 7795 7796 traceoff_after_boot 7797 [FTRACE] Sometimes tracing is used to debug issues 7798 during the boot process. Since the trace buffer has a 7799 limited amount of storage, it may be prudent to 7800 disable tracing after the boot is finished, otherwise 7801 the critical information may be overwritten. With this 7802 option, the main tracing buffer will be turned off at 7803 the end of the boot process. 7804 7805 traceoff_on_warning 7806 [FTRACE] enable this option to disable tracing when a 7807 warning is hit. This turns off "tracing_on". Tracing can 7808 be enabled again by echoing '1' into the "tracing_on" 7809 file located in /sys/kernel/tracing/ 7810 7811 This option is useful, as it disables the trace before 7812 the WARNING dump is called, which prevents the trace to 7813 be filled with content caused by the warning output. 7814 7815 This option can also be set at run time via the sysctl 7816 option: kernel/traceoff_on_warning 7817 7818 transparent_hugepage= 7819 [KNL] 7820 Format: [always|madvise|never] 7821 Can be used to control the default behavior of the system 7822 with respect to transparent hugepages. 7823 See Documentation/admin-guide/mm/transhuge.rst 7824 for more details. 7825 7826 transparent_hugepage_shmem= [KNL] 7827 Format: [always|within_size|advise|never|deny|force] 7828 Can be used to control the hugepage allocation policy for 7829 the internal shmem mount. 7830 See Documentation/admin-guide/mm/transhuge.rst 7831 for more details. 7832 7833 transparent_hugepage_tmpfs= [KNL] 7834 Format: [always|within_size|advise|never] 7835 Can be used to control the default hugepage allocation policy 7836 for the tmpfs mount. 7837 See Documentation/admin-guide/mm/transhuge.rst 7838 for more details. 7839 7840 trusted.source= [KEYS] 7841 Format: <string> 7842 This parameter identifies the trust source as a backend 7843 for trusted keys implementation. Supported trust 7844 sources: 7845 - "tpm" 7846 - "tee" 7847 - "caam" 7848 - "dcp" 7849 - "pkwm" 7850 If not specified then it defaults to iterating through 7851 the trust source list starting with TPM and assigns the 7852 first trust source as a backend which is initialized 7853 successfully during iteration. 7854 7855 trusted.rng= [KEYS] 7856 Format: <string> 7857 The RNG used to generate key material for trusted keys. 7858 Can be one of: 7859 - "kernel" 7860 - the same value as trusted.source: "tpm" or "tee" 7861 - "default" 7862 If not specified, "default" is used. In this case, 7863 the RNG's choice is left to each individual trust source. 7864 7865 trusted.dcp_use_otp_key 7866 This is intended to be used in combination with 7867 trusted.source=dcp and will select the DCP OTP key 7868 instead of the DCP UNIQUE key blob encryption. 7869 7870 trusted.dcp_skip_zk_test 7871 This is intended to be used in combination with 7872 trusted.source=dcp and will disable the check if the 7873 blob key is all zeros. This is helpful for situations where 7874 having this key zero'ed is acceptable. E.g. in testing 7875 scenarios. 7876 7877 tsa= [X86] Control mitigation for Transient Scheduler 7878 Attacks on AMD CPUs. Search the following in your 7879 favourite search engine for more details: 7880 7881 "Technical guidance for mitigating transient scheduler 7882 attacks". 7883 7884 off - disable the mitigation 7885 on - enable the mitigation (default) 7886 user - mitigate only user/kernel transitions 7887 vm - mitigate only guest/host transitions 7888 7889 7890 tsc= Disable clocksource stability checks for TSC. 7891 Format: <string> 7892 [x86] reliable: mark tsc clocksource as reliable, this 7893 disables clocksource verification at runtime, as well 7894 as the stability checks done at bootup. Used to enable 7895 high-resolution timer mode on older hardware, and in 7896 virtualized environment. 7897 [x86] noirqtime: Do not use TSC to do irq accounting. 7898 Used to run time disable IRQ_TIME_ACCOUNTING on any 7899 platforms where RDTSC is slow and this accounting 7900 can add overhead. 7901 [x86] unstable: mark the TSC clocksource as unstable, this 7902 marks the TSC unconditionally unstable at bootup and 7903 avoids any further wobbles once the TSC watchdog notices. 7904 [x86] nowatchdog: disable clocksource watchdog. Used 7905 in situations with strict latency requirements (where 7906 interruptions from clocksource watchdog are not 7907 acceptable). 7908 [x86] recalibrate: force recalibration against a HW timer 7909 (HPET or PM timer) on systems whose TSC frequency was 7910 obtained from HW or FW using either an MSR or CPUID(0x15). 7911 Warn if the difference is more than 500 ppm. 7912 [x86] watchdog: Enforce the clocksource watchdog on TSC 7913 7914 tsc_early_khz= [X86,EARLY] Skip early TSC calibration and use the given 7915 value instead. Useful when the early TSC frequency discovery 7916 procedure is not reliable, such as on overclocked systems 7917 with CPUID.16h support and partial CPUID.15h support. 7918 Format: <unsigned int> 7919 7920 tsx= [X86] Control Transactional Synchronization 7921 Extensions (TSX) feature in Intel processors that 7922 support TSX control. 7923 7924 This parameter controls the TSX feature. The options are: 7925 7926 on - Enable TSX on the system. Although there are 7927 mitigations for all known security vulnerabilities, 7928 TSX has been known to be an accelerator for 7929 several previous speculation-related CVEs, and 7930 so there may be unknown security risks associated 7931 with leaving it enabled. 7932 7933 off - Disable TSX on the system. (Note that this 7934 option takes effect only on newer CPUs which are 7935 not vulnerable to MDS, i.e., have 7936 MSR_IA32_ARCH_CAPABILITIES.MDS_NO=1 and which get 7937 the new IA32_TSX_CTRL MSR through a microcode 7938 update. This new MSR allows for the reliable 7939 deactivation of the TSX functionality.) 7940 7941 auto - Disable TSX if X86_BUG_TAA is present, 7942 otherwise enable TSX on the system. 7943 7944 Not specifying this option is equivalent to tsx=off. 7945 7946 See Documentation/admin-guide/hw-vuln/tsx_async_abort.rst 7947 for more details. 7948 7949 tsx_async_abort= [X86,INTEL,EARLY] Control mitigation for the TSX Async 7950 Abort (TAA) vulnerability. 7951 7952 Similar to Micro-architectural Data Sampling (MDS) 7953 certain CPUs that support Transactional 7954 Synchronization Extensions (TSX) are vulnerable to an 7955 exploit against CPU internal buffers which can forward 7956 information to a disclosure gadget under certain 7957 conditions. 7958 7959 In vulnerable processors, the speculatively forwarded 7960 data can be used in a cache side channel attack, to 7961 access data to which the attacker does not have direct 7962 access. 7963 7964 This parameter controls the TAA mitigation. The 7965 options are: 7966 7967 full - Enable TAA mitigation on vulnerable CPUs 7968 if TSX is enabled. 7969 7970 full,nosmt - Enable TAA mitigation and disable SMT on 7971 vulnerable CPUs. If TSX is disabled, SMT 7972 is not disabled because CPU is not 7973 vulnerable to cross-thread TAA attacks. 7974 off - Unconditionally disable TAA mitigation 7975 7976 On MDS-affected machines, tsx_async_abort=off can be 7977 prevented by an active MDS mitigation as both vulnerabilities 7978 are mitigated with the same mechanism so in order to disable 7979 this mitigation, you need to specify mds=off too. 7980 7981 Not specifying this option is equivalent to 7982 tsx_async_abort=full. On CPUs which are MDS affected 7983 and deploy MDS mitigation, TAA mitigation is not 7984 required and doesn't provide any additional 7985 mitigation. 7986 7987 For details see: 7988 Documentation/admin-guide/hw-vuln/tsx_async_abort.rst 7989 7990 turbografx.map[2|3]= [HW,JOY] 7991 TurboGraFX parallel port interface 7992 Format: 7993 <port#>,<js1>,<js2>,<js3>,<js4>,<js5>,<js6>,<js7> 7994 See also Documentation/input/devices/joystick-parport.rst 7995 7996 udbg-immortal [PPC] When debugging early kernel crashes that 7997 happen after console_init() and before a proper 7998 console driver takes over, this boot options might 7999 help "seeing" what's going on. 8000 8001 uhash_entries= [KNL,NET] 8002 Set number of hash buckets for UDP/UDP-Lite connections 8003 8004 uhci-hcd.ignore_oc= 8005 [USB] Ignore overcurrent events (default N). 8006 Some badly-designed motherboards generate lots of 8007 bogus events, for ports that aren't wired to 8008 anything. Set this parameter to avoid log spamming. 8009 Note that genuine overcurrent events won't be 8010 reported either. 8011 8012 unaligned_scalar_speed= 8013 [RISCV] 8014 Format: {slow | fast | unsupported} 8015 Allow skipping scalar unaligned access speed tests. This 8016 is useful for testing alternative code paths and to skip 8017 the tests in environments where they run too slowly. All 8018 CPUs must have the same scalar unaligned access speed. 8019 8020 unaligned_vector_speed= 8021 [RISCV] 8022 Format: {slow | fast | unsupported} 8023 Allow skipping vector unaligned access speed tests. This 8024 is useful for testing alternative code paths and to skip 8025 the tests in environments where they run too slowly. All 8026 CPUs must have the same vector unaligned access speed. 8027 8028 unknown_nmi_panic 8029 [X86] Cause panic on unknown NMI. 8030 8031 unwind_debug [X86-64,EARLY] 8032 Enable unwinder debug output. This can be 8033 useful for debugging certain unwinder error 8034 conditions, including corrupt stacks and 8035 bad/missing unwinder metadata. 8036 8037 usbcore.authorized_default= 8038 [USB] Default USB device authorization: 8039 (default -1 = authorized (same as 1), 8040 0 = not authorized, 1 = authorized, 2 = authorized 8041 if device connected to internal port) 8042 8043 usbcore.autosuspend= 8044 [USB] The autosuspend time delay (in seconds) used 8045 for newly-detected USB devices (default 2). This 8046 is the time required before an idle device will be 8047 autosuspended. Devices for which the delay is set 8048 to a negative value won't be autosuspended at all. 8049 8050 usbcore.usbfs_snoop= 8051 [USB] Set to log all usbfs traffic (default 0 = off). 8052 8053 usbcore.usbfs_snoop_max= 8054 [USB] Maximum number of bytes to snoop in each URB 8055 (default = 65536). 8056 8057 usbcore.blinkenlights= 8058 [USB] Set to cycle leds on hubs (default 0 = off). 8059 8060 usbcore.old_scheme_first= 8061 [USB] Start with the old device initialization 8062 scheme (default 0 = off). 8063 8064 usbcore.usbfs_memory_mb= 8065 [USB] Memory limit (in MB) for buffers allocated by 8066 usbfs (default = 16, 0 = max = 2047). 8067 8068 usbcore.use_both_schemes= 8069 [USB] Try the other device initialization scheme 8070 if the first one fails (default 1 = enabled). 8071 8072 usbcore.initial_descriptor_timeout= 8073 [USB] Specifies timeout for the initial 64-byte 8074 USB_REQ_GET_DESCRIPTOR request in milliseconds 8075 (default 5000 = 5.0 seconds). 8076 8077 usbcore.nousb [USB] Disable the USB subsystem 8078 8079 usbcore.quirks= 8080 [USB] A list of quirk entries to augment the built-in 8081 usb core quirk list. List entries are separated by 8082 commas. Each entry has the form 8083 VendorID:ProductID:Flags. The IDs are 4-digit hex 8084 numbers and Flags is a set of letters. Each letter 8085 will change the built-in quirk; setting it if it is 8086 clear and clearing it if it is set. The letters have 8087 the following meanings: 8088 a = USB_QUIRK_STRING_FETCH_255 (string 8089 descriptors must not be fetched using 8090 a 255-byte read); 8091 b = USB_QUIRK_RESET_RESUME (device can't resume 8092 correctly so reset it instead); 8093 c = USB_QUIRK_NO_SET_INTF (device can't handle 8094 Set-Interface requests); 8095 d = USB_QUIRK_CONFIG_INTF_STRINGS (device can't 8096 handle its Configuration or Interface 8097 strings); 8098 e = USB_QUIRK_RESET (device can't be reset 8099 (e.g morph devices), don't use reset); 8100 f = USB_QUIRK_HONOR_BNUMINTERFACES (device has 8101 more interface descriptions than the 8102 bNumInterfaces count, and can't handle 8103 talking to these interfaces); 8104 g = USB_QUIRK_DELAY_INIT (device needs a pause 8105 during initialization, after we read 8106 the device descriptor); 8107 h = USB_QUIRK_LINEAR_UFRAME_INTR_BINTERVAL (For 8108 high speed and super speed interrupt 8109 endpoints, the USB 2.0 and USB 3.0 spec 8110 require the interval in microframes (1 8111 microframe = 125 microseconds) to be 8112 calculated as interval = 2 ^ 8113 (bInterval-1). 8114 Devices with this quirk report their 8115 bInterval as the result of this 8116 calculation instead of the exponent 8117 variable used in the calculation); 8118 i = USB_QUIRK_DEVICE_QUALIFIER (device can't 8119 handle device_qualifier descriptor 8120 requests); 8121 j = USB_QUIRK_IGNORE_REMOTE_WAKEUP (device 8122 generates spurious wakeup, ignore 8123 remote wakeup capability); 8124 k = USB_QUIRK_NO_LPM (device can't handle Link 8125 Power Management); 8126 l = USB_QUIRK_LINEAR_FRAME_INTR_BINTERVAL 8127 (Device reports its bInterval as linear 8128 frames instead of the USB 2.0 8129 calculation); 8130 m = USB_QUIRK_DISCONNECT_SUSPEND (Device needs 8131 to be disconnected before suspend to 8132 prevent spurious wakeup); 8133 n = USB_QUIRK_DELAY_CTRL_MSG (Device needs a 8134 pause after every control message); 8135 o = USB_QUIRK_HUB_SLOW_RESET (Hub needs extra 8136 delay after resetting its port); 8137 p = USB_QUIRK_SHORT_SET_ADDRESS_REQ_TIMEOUT 8138 (Reduce timeout of the SET_ADDRESS 8139 request from 5000 ms to 500 ms); 8140 q = USB_QUIRK_FORCE_ONE_CONFIG (Device 8141 claims zero configurations, 8142 forcing to 1); 8143 Example: quirks=0781:5580:bk,0a5c:5834:gij 8144 8145 usbhid.mousepoll= 8146 [USBHID] The interval which mice are to be polled at. 8147 8148 usbhid.jspoll= 8149 [USBHID] The interval which joysticks are to be polled at. 8150 8151 usbhid.kbpoll= 8152 [USBHID] The interval which keyboards are to be polled at. 8153 8154 usb-storage.delay_use= 8155 [UMS] The delay in seconds before a new device is 8156 scanned for Logical Units (default 1). 8157 Optionally the delay in milliseconds if the value has 8158 suffix with "ms". 8159 Example: delay_use=2567ms 8160 8161 usb-storage.quirks= 8162 [UMS] A list of quirks entries to supplement or 8163 override the built-in unusual_devs list. List 8164 entries are separated by commas. Each entry has 8165 the form VID:PID:Flags where VID and PID are Vendor 8166 and Product ID values (4-digit hex numbers) and 8167 Flags is a set of characters, each corresponding 8168 to a common usb-storage quirk flag as follows: 8169 a = SANE_SENSE (collect more than 18 bytes 8170 of sense data, not on uas); 8171 b = BAD_SENSE (don't collect more than 18 8172 bytes of sense data, not on uas); 8173 c = FIX_CAPACITY (decrease the reported 8174 device capacity by one sector); 8175 d = NO_READ_DISC_INFO (don't use 8176 READ_DISC_INFO command, not on uas); 8177 e = NO_READ_CAPACITY_16 (don't use 8178 READ_CAPACITY_16 command); 8179 f = NO_REPORT_OPCODES (don't use report opcodes 8180 command, uas only); 8181 g = MAX_SECTORS_240 (don't transfer more than 8182 240 sectors at a time, uas only); 8183 h = CAPACITY_HEURISTICS (decrease the 8184 reported device capacity by one 8185 sector if the number is odd); 8186 i = IGNORE_DEVICE (don't bind to this 8187 device); 8188 j = NO_REPORT_LUNS (don't use report luns 8189 command, uas only); 8190 k = NO_SAME (do not use WRITE_SAME, uas only) 8191 l = NOT_LOCKABLE (don't try to lock and 8192 unlock ejectable media, not on uas); 8193 m = MAX_SECTORS_64 (don't transfer more 8194 than 64 sectors = 32 KB at a time, 8195 not on uas); 8196 n = INITIAL_READ10 (force a retry of the 8197 initial READ(10) command, not on uas); 8198 o = CAPACITY_OK (accept the capacity 8199 reported by the device, not on uas); 8200 p = WRITE_CACHE (the device cache is ON 8201 by default, not on uas); 8202 r = IGNORE_RESIDUE (the device reports 8203 bogus residue values, not on uas); 8204 s = SINGLE_LUN (the device has only one 8205 Logical Unit); 8206 t = NO_ATA_1X (don't allow ATA(12) and ATA(16) 8207 commands, uas only); 8208 u = IGNORE_UAS (don't bind to the uas driver); 8209 w = NO_WP_DETECT (don't test whether the 8210 medium is write-protected). 8211 y = ALWAYS_SYNC (issue a SYNCHRONIZE_CACHE 8212 even if the device claims no cache, 8213 not on uas) 8214 Example: quirks=0419:aaf5:rl,0421:0433:rc 8215 8216 user_debug= [KNL,ARM] 8217 Format: <int> 8218 See arch/arm/Kconfig.debug help text. 8219 1 - undefined instruction events 8220 2 - system calls 8221 4 - invalid data aborts 8222 8 - SIGSEGV faults 8223 16 - SIGBUS faults 8224 Example: user_debug=31 8225 8226 vdso= [X86,SH,SPARC] 8227 On X86_32, this is an alias for vdso32=. Otherwise: 8228 8229 vdso=1: enable VDSO (the default) 8230 vdso=0: disable VDSO mapping 8231 8232 vdso32= [X86] Control the 32-bit vDSO 8233 vdso32=1: enable 32-bit VDSO 8234 vdso32=0 or vdso32=2: disable 32-bit VDSO 8235 8236 See the help text for CONFIG_COMPAT_VDSO for more 8237 details. If CONFIG_COMPAT_VDSO is set, the default is 8238 vdso32=0; otherwise, the default is vdso32=1. 8239 8240 For compatibility with older kernels, vdso32=2 is an 8241 alias for vdso32=0. 8242 8243 Try vdso32=0 if you encounter an error that says: 8244 dl_main: Assertion `(void *) ph->p_vaddr == _rtld_local._dl_sysinfo_dso' failed! 8245 8246 video= [FB,EARLY] Frame buffer configuration 8247 See Documentation/fb/modedb.rst. 8248 8249 video.brightness_switch_enabled= [ACPI] 8250 Format: [0|1] 8251 If set to 1, on receiving an ACPI notify event 8252 generated by hotkey, video driver will adjust brightness 8253 level and then send out the event to user space through 8254 the allocated input device. If set to 0, video driver 8255 will only send out the event without touching backlight 8256 brightness level. 8257 default: 1 8258 8259 virtio_mmio.device= 8260 [VMMIO] Memory mapped virtio (platform) device. 8261 8262 <size>@<baseaddr>:<irq>[:<id>] 8263 where: 8264 <size> := size (can use standard suffixes 8265 like K, M and G) 8266 <baseaddr> := physical base address 8267 <irq> := interrupt number (as passed to 8268 request_irq()) 8269 <id> := (optional) platform device id 8270 example: 8271 virtio_mmio.device=1K@0x100b0000:48:7 8272 8273 Can be used multiple times for multiple devices. 8274 8275 vga= [BOOT,X86-32] Select a particular video mode 8276 See Documentation/arch/x86/boot.rst and 8277 Documentation/admin-guide/svga.rst. 8278 Use vga=ask for menu. 8279 This is actually a boot loader parameter; the value is 8280 passed to the kernel using a special protocol. 8281 8282 vm_debug[=options] [KNL] Available with CONFIG_DEBUG_VM=y. 8283 May slow down system boot speed, especially when 8284 enabled on systems with a large amount of memory. 8285 All options are enabled by default, and this 8286 interface is meant to allow for selectively 8287 enabling or disabling specific virtual memory 8288 debugging features. 8289 8290 Available options are: 8291 P Enable page structure init time poisoning 8292 - Disable all of the above options 8293 8294 vmalloc=nn[KMG] [KNL,BOOT,EARLY] Forces the vmalloc area to have an 8295 exact size of <nn>. This can be used to increase 8296 the minimum size (128MB on x86, arm32 platforms). 8297 It can also be used to decrease the size and leave more room 8298 for directly mapped kernel RAM. Note that this parameter does 8299 not exist on many other platforms (including arm64, alpha, 8300 loongarch, arc, csky, hexagon, microblaze, mips, nios2, openrisc, 8301 parisc, m64k, powerpc, riscv, sh, um, xtensa, s390, sparc). 8302 8303 vmcp_cma=nn[MG] [KNL,S390,EARLY] 8304 Sets the memory size reserved for contiguous memory 8305 allocations for the vmcp device driver. 8306 8307 vmhalt= [KNL,S390] Perform z/VM CP command after system halt. 8308 Format: <command> 8309 8310 vmpanic= [KNL,S390] Perform z/VM CP command after kernel panic. 8311 Format: <command> 8312 8313 vmpoff= [KNL,S390] Perform z/VM CP command after power off. 8314 Format: <command> 8315 8316 vmscape= [X86] Controls mitigation for VMscape attacks. 8317 VMscape attacks can leak information from a userspace 8318 hypervisor to a guest via speculative side-channels. 8319 8320 off - disable the mitigation 8321 ibpb - use Indirect Branch Prediction Barrier 8322 (IBPB) mitigation (default) 8323 force - force vulnerability detection even on 8324 unaffected processors 8325 8326 vsyscall= [X86-64,EARLY] 8327 Controls the behavior of vsyscalls (i.e. calls to 8328 fixed addresses of 0xffffffffff600x00 from legacy 8329 code). Most statically-linked binaries and older 8330 versions of glibc use these calls. Because these 8331 functions are at fixed addresses, they make nice 8332 targets for exploits that can control RIP. 8333 8334 emulate Vsyscalls turn into traps and are emulated 8335 reasonably safely. The vsyscall page is 8336 readable. This disables the Linear 8337 Address Space Separation (LASS) security 8338 feature and makes the system less secure. 8339 8340 xonly [default] Vsyscalls turn into traps and are 8341 emulated reasonably safely. The vsyscall 8342 page is not readable. 8343 8344 none Vsyscalls don't work at all. This makes 8345 them quite hard to use for exploits but 8346 might break your system. 8347 8348 vt.color= [VT] Default text color. 8349 Format: 0xYX, X = foreground, Y = background. 8350 Default: 0x07 = light gray on black. 8351 8352 vt.cur_default= [VT] Default cursor shape. 8353 Format: 0xCCBBAA, where AA, BB, and CC are the same as 8354 the parameters of the <Esc>[?A;B;Cc escape sequence; 8355 see vga-softcursor.rst. Default: 2 = underline. 8356 8357 vt.default_blu= [VT] 8358 Format: <blue0>,<blue1>,<blue2>,...,<blue15> 8359 Change the default blue palette of the console. 8360 This is a 16-member array composed of values 8361 ranging from 0-255. 8362 8363 vt.default_grn= [VT] 8364 Format: <green0>,<green1>,<green2>,...,<green15> 8365 Change the default green palette of the console. 8366 This is a 16-member array composed of values 8367 ranging from 0-255. 8368 8369 vt.default_red= [VT] 8370 Format: <red0>,<red1>,<red2>,...,<red15> 8371 Change the default red palette of the console. 8372 This is a 16-member array composed of values 8373 ranging from 0-255. 8374 8375 vt.default_utf8= 8376 [VT] 8377 Format=<0|1> 8378 Set system-wide default UTF-8 mode for all tty's. 8379 Default is 1, i.e. UTF-8 mode is enabled for all 8380 newly opened terminals. 8381 8382 vt.global_cursor_default= 8383 [VT] 8384 Format=<-1|0|1> 8385 Set system-wide default for whether a cursor 8386 is shown on new VTs. Default is -1, 8387 i.e. cursors will be created by default unless 8388 overridden by individual drivers. 0 will hide 8389 cursors, 1 will display them. 8390 8391 vt.italic= [VT] Default color for italic text; 0-15. 8392 Default: 2 = green. 8393 8394 vt.underline= [VT] Default color for underlined text; 0-15. 8395 Default: 3 = cyan. 8396 8397 watchdog timers [HW,WDT] For information on watchdog timers, 8398 see Documentation/watchdog/watchdog-parameters.rst 8399 or other driver-specific files in the 8400 Documentation/watchdog/ directory. 8401 8402 watchdog_thresh= 8403 [KNL] 8404 Set the hard lockup detector stall duration 8405 threshold in seconds. The soft lockup detector 8406 threshold is set to twice the value. A value of 0 8407 disables both lockup detectors. Default is 10 8408 seconds. 8409 8410 workqueue.unbound_cpus= 8411 [KNL,SMP] Specify to constrain one or some CPUs 8412 to use in unbound workqueues. 8413 Format: <cpu-list> 8414 By default, all online CPUs are available for 8415 unbound workqueues. 8416 8417 workqueue.watchdog_thresh= 8418 If CONFIG_WQ_WATCHDOG is configured, workqueue can 8419 warn stall conditions and dump internal state to 8420 help debugging. 0 disables workqueue stall 8421 detection; otherwise, it's the stall threshold 8422 duration in seconds. The default value is 30 and 8423 it can be updated at runtime by writing to the 8424 corresponding sysfs file. 8425 8426 workqueue.panic_on_stall=<uint> 8427 Panic when workqueue stall is detected by 8428 CONFIG_WQ_WATCHDOG. It sets the number times of the 8429 stall to trigger panic. 8430 8431 The default is set by CONFIG_BOOTPARAM_WQ_STALL_PANIC, 8432 which is 0 (disabled) if not configured. 8433 8434 workqueue.panic_on_stall_time=<uint> 8435 Panic when a workqueue stall has been continuous for 8436 the specified number of seconds. Unlike panic_on_stall 8437 which counts accumulated stall events, this triggers 8438 based on the duration of a single continuous stall. 8439 8440 The default is 0, which disables the time-based panic. 8441 8442 workqueue.cpu_intensive_thresh_us= 8443 Per-cpu work items which run for longer than this 8444 threshold are automatically considered CPU intensive 8445 and excluded from concurrency management to prevent 8446 them from noticeably delaying other per-cpu work 8447 items. Default is 10000 (10ms). 8448 8449 If CONFIG_WQ_CPU_INTENSIVE_REPORT is set, the kernel 8450 will report the work functions which violate this 8451 threshold repeatedly. They are likely good 8452 candidates for using WQ_UNBOUND workqueues instead. 8453 8454 workqueue.cpu_intensive_warning_thresh=<uint> 8455 If CONFIG_WQ_CPU_INTENSIVE_REPORT is set, the kernel 8456 will report the work functions which violate the 8457 intensive_threshold_us repeatedly. In order to prevent 8458 spurious warnings, start printing only after a work 8459 function has violated this threshold number of times. 8460 8461 The default is 4 times. 0 disables the warning. 8462 8463 workqueue.power_efficient 8464 Per-cpu workqueues are generally preferred because 8465 they show better performance thanks to cache 8466 locality; unfortunately, per-cpu workqueues tend to 8467 be more power hungry than unbound workqueues. 8468 8469 Enabling this makes the per-cpu workqueues which 8470 were observed to contribute significantly to power 8471 consumption unbound, leading to measurably lower 8472 power usage at the cost of small performance 8473 overhead. 8474 8475 The default value of this parameter is determined by 8476 the config option CONFIG_WQ_POWER_EFFICIENT_DEFAULT. 8477 8478 workqueue.default_affinity_scope= 8479 Select the default affinity scope to use for unbound 8480 workqueues. Can be one of "cpu", "smt", "cache", 8481 "cache_shard", "numa" and "system". Default is 8482 "cache_shard". For more 8483 information, see the Affinity Scopes section in 8484 Documentation/core-api/workqueue.rst. 8485 8486 This can be changed after boot by writing to the 8487 matching /sys/module/workqueue/parameters file. All 8488 workqueues with the "default" affinity scope will be 8489 updated accordingly. 8490 8491 workqueue.debug_force_rr_cpu 8492 Workqueue used to implicitly guarantee that work 8493 items queued without explicit CPU specified are put 8494 on the local CPU. This guarantee is no longer true 8495 and while local CPU is still preferred work items 8496 may be put on foreign CPUs. This debug option 8497 forces round-robin CPU selection to flush out 8498 usages which depend on the now broken guarantee. 8499 When enabled, memory and cache locality will be 8500 impacted. 8501 8502 writecombine= [LOONGARCH,EARLY] Control the MAT (Memory Access 8503 Type) of ioremap_wc(). 8504 8505 on - Enable writecombine, use WUC for ioremap_wc() 8506 off - Disable writecombine, use SUC for ioremap_wc() 8507 8508 x2apic_phys [X86-64,APIC,EARLY] Use x2apic physical mode instead of 8509 default x2apic cluster mode on platforms 8510 supporting x2apic. 8511 8512 xen_512gb_limit [KNL,X86-64,XEN] 8513 Restricts the kernel running paravirtualized under Xen 8514 to use only up to 512 GB of RAM. The reason to do so is 8515 crash analysis tools and Xen tools for doing domain 8516 save/restore/migration must be enabled to handle larger 8517 domains. 8518 8519 xen_console_io [XEN,EARLY] 8520 Boolean option to enable/disable the usage of the Xen 8521 console_io hypercalls to read and write to the console. 8522 Mostly useful for debugging and development. 8523 8524 xen_emul_unplug= [HW,X86,XEN,EARLY] 8525 Unplug Xen emulated devices 8526 Format: [unplug0,][unplug1] 8527 ide-disks -- unplug primary master IDE devices 8528 aux-ide-disks -- unplug non-primary-master IDE devices 8529 nics -- unplug network devices 8530 all -- unplug all emulated devices (NICs and IDE disks) 8531 unnecessary -- unplugging emulated devices is 8532 unnecessary even if the host did not respond to 8533 the unplug protocol 8534 never -- do not unplug even if version check succeeds 8535 8536 xen_legacy_crash [X86,XEN,EARLY] 8537 Crash from Xen panic notifier, without executing late 8538 panic() code such as dumping handler. 8539 8540 xen_mc_debug [X86,XEN,EARLY] 8541 Enable multicall debugging when running as a Xen PV guest. 8542 Enabling this feature will reduce performance a little 8543 bit, so it should only be enabled for obtaining extended 8544 debug data in case of multicall errors. 8545 8546 xen_msr_safe= [X86,XEN,EARLY] 8547 Format: <bool> 8548 Select whether to always use non-faulting (safe) MSR 8549 access functions when running as Xen PV guest. The 8550 default value is controlled by CONFIG_XEN_PV_MSR_SAFE. 8551 8552 xen_nopv [X86] 8553 Disables the PV optimizations forcing the HVM guest to 8554 run as generic HVM guest with no PV drivers. 8555 This option is obsoleted by the "nopv" option, which 8556 has equivalent effect for XEN platform. 8557 8558 xen_no_vector_callback 8559 [KNL,X86,XEN,EARLY] Disable the vector callback for Xen 8560 event channel interrupts. 8561 8562 xen_scrub_pages= [XEN] 8563 Boolean option to control scrubbing pages before giving them back 8564 to Xen, for use by other domains. Can be also changed at runtime 8565 with /sys/devices/system/xen_memory/xen_memory0/scrub_pages. 8566 Default value controlled with CONFIG_XEN_SCRUB_PAGES_DEFAULT. 8567 8568 xen_timer_slop= [X86-64,XEN,EARLY] 8569 Set the timer slop (in nanoseconds) for the virtual Xen 8570 timers (default is 100000). This adjusts the minimum 8571 delta of virtualized Xen timers, where lower values 8572 improve timer resolution at the expense of processing 8573 more timer interrupts. 8574 8575 xen.balloon_boot_timeout= [XEN] 8576 The time (in seconds) to wait before giving up to boot 8577 in case initial ballooning fails to free enough memory. 8578 Applies only when running as HVM or PVH guest and 8579 started with less memory configured than allowed at 8580 max. Default is 180. 8581 8582 xen.event_eoi_delay= [XEN] 8583 How long to delay EOI handling in case of event 8584 storms (jiffies). Default is 10. 8585 8586 xen.event_loop_timeout= [XEN] 8587 After which time (jiffies) the event handling loop 8588 should start to delay EOI handling. Default is 2. 8589 8590 xen.fifo_events= [XEN] 8591 Boolean parameter to disable using fifo event handling 8592 even if available. Normally fifo event handling is 8593 preferred over the 2-level event handling, as it is 8594 fairer and the number of possible event channels is 8595 much higher. Default is on (use fifo events). 8596 8597 xirc2ps_cs= [NET,PCMCIA] 8598 Format: 8599 <irq>,<irq_mask>,<io>,<full_duplex>,<do_sound>,<lockup_hack>[,<irq2>[,<irq3>[,<irq4>]]] 8600 8601 xive= [PPC] 8602 By default on POWER9 and above, the kernel will 8603 natively use the XIVE interrupt controller. This option 8604 allows the fallback firmware mode to be used: 8605 8606 off Fallback to firmware control of XIVE interrupt 8607 controller on both pseries and powernv 8608 platforms. Only useful on POWER9 and above. 8609 8610 xive.store-eoi=off [PPC] 8611 By default on POWER10 and above, the kernel will use 8612 stores for EOI handling when the XIVE interrupt mode 8613 is active. This option allows the XIVE driver to use 8614 loads instead, as on POWER9. 8615 8616 xhci-hcd.quirks [USB,KNL] 8617 A hex value specifying bitmask with supplemental xhci 8618 host controller quirks. Meaning of each bit can be 8619 consulted in header drivers/usb/host/xhci.h. 8620 8621 xmon [PPC,EARLY] 8622 Format: { early | on | rw | ro | off } 8623 Controls if xmon debugger is enabled. Default is off. 8624 Passing only "xmon" is equivalent to "xmon=early". 8625 early Call xmon as early as possible on boot; xmon 8626 debugger is called from setup_arch(). 8627 on xmon debugger hooks will be installed so xmon 8628 is only called on a kernel crash. Default mode, 8629 i.e. either "ro" or "rw" mode, is controlled 8630 with CONFIG_XMON_DEFAULT_RO_MODE. 8631 rw xmon debugger hooks will be installed so xmon 8632 is called only on a kernel crash, mode is write, 8633 meaning SPR registers, memory and, other data 8634 can be written using xmon commands. 8635 ro same as "rw" option above but SPR registers, 8636 memory, and other data can't be written using 8637 xmon commands. 8638 off xmon is disabled. 8639