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