1 ACPI ACPI support is enabled. 2 AGP AGP (Accelerated Graphics Port) is enabled. 3 ALSA ALSA sound support is enabled. 4 APIC APIC support is enabled. 5 APM Advanced Power Management support is enabled. 6 APPARMOR AppArmor support is enabled. 7 ARM ARM architecture is enabled. 8 ARM64 ARM64 architecture is enabled. 9 AX25 Appropriate AX.25 support is enabled. 10 CLK Common clock infrastructure is enabled. 11 CMA Contiguous Memory Area support is enabled. 12 DRM Direct Rendering Management support is enabled. 13 DYNAMIC_DEBUG Build in debug messages and enable them at runtime 14 EARLY Parameter processed too early to be embedded in initrd. 15 EDD BIOS Enhanced Disk Drive Services (EDD) is enabled 16 EFI EFI Partitioning (GPT) is enabled 17 EVM Extended Verification Module 18 FB The frame buffer device is enabled. 19 FTRACE Function tracing enabled. 20 GCOV GCOV profiling is enabled. 21 HIBERNATION HIBERNATION is enabled. 22 HW Appropriate hardware is enabled. 23 HYPER_V HYPERV support is enabled. 24 IMA Integrity measurement architecture is enabled. 25 IP_PNP IP DHCP, BOOTP, or RARP is enabled. 26 IPV6 IPv6 support is enabled. 27 ISAPNP ISA PnP code is enabled. 28 ISDN Appropriate ISDN support is enabled. 29 ISOL CPU Isolation is enabled. 30 JOY Appropriate joystick support is enabled. 31 KGDB Kernel debugger support is enabled. 32 KVM Kernel Virtual Machine support is enabled. 33 LIBATA Libata driver is enabled 34 LOONGARCH LoongArch architecture is enabled. 35 LOOP Loopback device support is enabled. 36 LP Printer support is enabled. 37 M68k M68k architecture is enabled. 38 These options have more detailed description inside of 39 Documentation/arch/m68k/kernel-options.rst. 40 MDA MDA console support is enabled. 41 MIPS MIPS architecture is enabled. 42 MOUSE Appropriate mouse support is enabled. 43 MSI Message Signaled Interrupts (PCI). 44 MTD MTD (Memory Technology Device) support is enabled. 45 NET Appropriate network support is enabled. 46 NFS Appropriate NFS support is enabled. 47 NUMA NUMA support is enabled. 48 OF Devicetree is enabled. 49 PARISC The PA-RISC architecture is enabled. 50 PCI PCI bus support is enabled. 51 PCIE PCI Express support is enabled. 52 PCMCIA The PCMCIA subsystem is enabled. 53 PNP Plug & Play support is enabled. 54 PPC PowerPC architecture is enabled. 55 PPT Parallel port support is enabled. 56 PS2 Appropriate PS/2 support is enabled. 57 PV_OPS A paravirtualized kernel is enabled. 58 RAM RAM disk support is enabled. 59 RDT Intel Resource Director Technology. 60 RISCV RISCV architecture is enabled. 61 S390 S390 architecture is enabled. 62 SCSI Appropriate SCSI support is enabled. 63 A lot of drivers have their options described inside 64 the Documentation/scsi/ sub-directory. 65 SDW SoundWire support is enabled. 66 SECURITY Different security models are enabled. 67 SELINUX SELinux support is enabled. 68 SERIAL Serial support is enabled. 69 SH SuperH architecture is enabled. 70 SMP The kernel is an SMP kernel. 71 SPARC Sparc architecture is enabled. 72 SUSPEND System suspend states are enabled. 73 SWSUSP Software suspend (hibernation) is enabled. 74 TPM TPM drivers are enabled. 75 UMS USB Mass Storage support is enabled. 76 USB USB support is enabled. 77 NVME NVMe support is enabled 78 USBHID USB Human Interface Device support is enabled. 79 V4L Video For Linux support is enabled. 80 VGA The VGA console has been enabled. 81 VMMIO Driver for memory mapped virtio devices is enabled. 82 VT Virtual terminal support is enabled. 83 WDT Watchdog support is enabled. 84 X86-32 X86-32, aka i386 architecture is enabled. 85 X86-64 X86-64 architecture is enabled. 86 X86 Either 32-bit or 64-bit x86 (same as X86-32+X86-64) 87 X86_UV SGI UV support is enabled. 88 XEN Xen support is enabled 89 XTENSA xtensa architecture is enabled. 90 91In addition, the following text indicates that the option 92 93 BOOT Is a boot loader parameter. 94 BUGS= Relates to possible processor bugs on the said processor. 95 KNL Is a kernel start-up parameter. 96 97 98Kernel parameters 99 100 accept_memory= [MM] 101 Format: { eager | lazy } 102 default: lazy 103 By default, unaccepted memory is accepted lazily to 104 avoid prolonged boot times. The lazy option will add 105 some runtime overhead until all memory is eventually 106 accepted. In most cases the overhead is negligible. 107 For some workloads or for debugging purposes 108 accept_memory=eager can be used to accept all memory 109 at once during boot. 110 111 acpi= [HW,ACPI,X86,ARM64,RISCV64,EARLY] 112 Advanced Configuration and Power Interface 113 Format: { force | on | off | strict | noirq | rsdt | 114 copy_dsdt | nospcr } 115 force -- enable ACPI if default was off 116 on -- enable ACPI but allow fallback to DT [arm64,riscv64] 117 off -- disable ACPI if default was on 118 noirq -- do not use ACPI for IRQ routing 119 strict -- Be less tolerant of platforms that are not 120 strictly ACPI specification compliant. 121 rsdt -- prefer RSDT over (default) XSDT 122 copy_dsdt -- copy DSDT to memory 123 nocmcff -- Disable firmware first mode for corrected 124 errors. This disables parsing the HEST CMC error 125 source to check if firmware has set the FF flag. This 126 may result in duplicate corrected error reports. 127 nospcr -- disable console in ACPI SPCR table as 128 default _serial_ console on ARM64 129 spcr -- enable console in ACPI SPCR table as 130 default _serial_ console on x86 131 For ARM64, ONLY "acpi=off", "acpi=on", "acpi=force" or 132 "acpi=nospcr" are available 133 For RISCV64, ONLY "acpi=off", "acpi=on" or "acpi=force" 134 are available 135 136 See also Documentation/power/runtime_pm.rst, pci=noacpi 137 138 acpi_apic_instance= [ACPI,IOAPIC,EARLY] 139 Format: <int> 140 2: use 2nd APIC table, if available 141 1,0: use 1st APIC table 142 default: 0 143 144 acpi_backlight= [HW,ACPI] 145 { vendor | video | native | none } 146 If set to vendor, prefer vendor-specific driver 147 (e.g. thinkpad_acpi, sony_acpi, etc.) instead 148 of the ACPI video.ko driver. 149 If set to video, use the ACPI video.ko driver. 150 If set to native, use the device's native backlight mode. 151 If set to none, disable the ACPI backlight interface. 152 153 acpi_force_32bit_fadt_addr [ACPI,EARLY] 154 force FADT to use 32 bit addresses rather than the 155 64 bit X_* addresses. Some firmware have broken 64 156 bit addresses for force ACPI ignore these and use 157 the older legacy 32 bit addresses. 158 159 acpica_no_return_repair [HW, ACPI] 160 Disable AML predefined validation mechanism 161 This mechanism can repair the evaluation result to make 162 the return objects more ACPI specification compliant. 163 This option is useful for developers to identify the 164 root cause of an AML interpreter issue when the issue 165 has something to do with the repair mechanism. 166 167 acpi.debug_layer= [HW,ACPI,ACPI_DEBUG] 168 acpi.debug_level= [HW,ACPI,ACPI_DEBUG] 169 Format: <int> 170 CONFIG_ACPI_DEBUG must be enabled to produce any ACPI 171 debug output. Bits in debug_layer correspond to a 172 _COMPONENT in an ACPI source file, e.g., 173 #define _COMPONENT ACPI_EVENTS 174 Bits in debug_level correspond to a level in 175 ACPI_DEBUG_PRINT statements, e.g., 176 ACPI_DEBUG_PRINT((ACPI_DB_INFO, ... 177 The debug_level mask defaults to "info". See 178 Documentation/firmware-guide/acpi/debug.rst for more information about 179 debug layers and levels. 180 181 Enable processor driver info messages: 182 acpi.debug_layer=0x20000000 183 Enable AML "Debug" output, i.e., stores to the Debug 184 object while interpreting AML: 185 acpi.debug_layer=0xffffffff acpi.debug_level=0x2 186 Enable all messages related to ACPI hardware: 187 acpi.debug_layer=0x2 acpi.debug_level=0xffffffff 188 189 Some values produce so much output that the system is 190 unusable. The "log_buf_len" parameter may be useful 191 if you need to capture more output. 192 193 acpi.poweroff_on_fatal= [ACPI] 194 {0 | 1} 195 Causes the system to poweroff when the ACPI bytecode signals 196 a fatal error. The default value of this setting is 1. 197 Overriding this value should only be done for diagnosing 198 ACPI firmware problems, as the system might behave erratically 199 after having encountered a fatal ACPI error. 200 201 acpi_enforce_resources= [ACPI] 202 { strict | lax | no } 203 Check for resource conflicts between native drivers 204 and ACPI OperationRegions (SystemIO and SystemMemory 205 only). IO ports and memory declared in ACPI might be 206 used by the ACPI subsystem in arbitrary AML code and 207 can interfere with legacy drivers. 208 strict (default): access to resources claimed by ACPI 209 is denied; legacy drivers trying to access reserved 210 resources will fail to bind to device using them. 211 lax: access to resources claimed by ACPI is allowed; 212 legacy drivers trying to access reserved resources 213 will bind successfully but a warning message is logged. 214 no: ACPI OperationRegions are not marked as reserved, 215 no further checks are performed. 216 217 acpi_force_table_verification [HW,ACPI,EARLY] 218 Enable table checksum verification during early stage. 219 By default, this is disabled due to x86 early mapping 220 size limitation. 221 222 acpi_irq_balance [HW,ACPI] 223 ACPI will balance active IRQs 224 default in APIC mode 225 226 acpi_irq_nobalance [HW,ACPI] 227 ACPI will not move active IRQs (default) 228 default in PIC mode 229 230 acpi_irq_isa= [HW,ACPI] If irq_balance, mark listed IRQs used by ISA 231 Format: <irq>,<irq>... 232 233 acpi_irq_pci= [HW,ACPI] If irq_balance, clear listed IRQs for 234 use by PCI 235 Format: <irq>,<irq>... 236 237 acpi_mask_gpe= [HW,ACPI] 238 Due to the existence of _Lxx/_Exx, some GPEs triggered 239 by unsupported hardware/firmware features can result in 240 GPE floodings that cannot be automatically disabled by 241 the GPE dispatcher. 242 This facility can be used to prevent such uncontrolled 243 GPE floodings. 244 Format: <byte> or <bitmap-list> 245 246 acpi_no_auto_serialize [HW,ACPI] 247 Disable auto-serialization of AML methods 248 AML control methods that contain the opcodes to create 249 named objects will be marked as "Serialized" by the 250 auto-serialization feature. 251 This feature is enabled by default. 252 This option allows to turn off the feature. 253 254 acpi_no_memhotplug [ACPI] Disable memory hotplug. Useful for kdump 255 kernels. 256 257 acpi_no_static_ssdt [HW,ACPI,EARLY] 258 Disable installation of static SSDTs at early boot time 259 By default, SSDTs contained in the RSDT/XSDT will be 260 installed automatically and they will appear under 261 /sys/firmware/acpi/tables. 262 This option turns off this feature. 263 Note that specifying this option does not affect 264 dynamic table installation which will install SSDT 265 tables to /sys/firmware/acpi/tables/dynamic. 266 267 acpi_no_watchdog [HW,ACPI,WDT] 268 Ignore the ACPI-based watchdog interface (WDAT) and let 269 a native driver control the watchdog device instead. 270 271 acpi_rsdp= [ACPI,EFI,KEXEC,EARLY] 272 Pass the RSDP address to the kernel, mostly used 273 on machines running EFI runtime service to boot the 274 second kernel for kdump. 275 276 acpi_os_name= [HW,ACPI] Tell ACPI BIOS the name of the OS 277 Format: To spoof as Windows 98: ="Microsoft Windows" 278 279 acpi_rev_override [ACPI] Override the _REV object to return 5 (instead 280 of 2 which is mandated by ACPI 6) as the supported ACPI 281 specification revision (when using this switch, it may 282 be necessary to carry out a cold reboot _twice_ in a 283 row to make it take effect on the platform firmware). 284 285 acpi_osi= [HW,ACPI] Modify list of supported OS interface strings 286 acpi_osi="string1" # add string1 287 acpi_osi="!string2" # remove string2 288 acpi_osi=!* # remove all strings 289 acpi_osi=! # disable all built-in OS vendor 290 strings 291 acpi_osi=!! # enable all built-in OS vendor 292 strings 293 acpi_osi= # disable all strings 294 295 'acpi_osi=!' can be used in combination with single or 296 multiple 'acpi_osi="string1"' to support specific OS 297 vendor string(s). Note that such command can only 298 affect the default state of the OS vendor strings, thus 299 it cannot affect the default state of the feature group 300 strings and the current state of the OS vendor strings, 301 specifying it multiple times through kernel command line 302 is meaningless. This command is useful when one do not 303 care about the state of the feature group strings which 304 should be controlled by the OSPM. 305 Examples: 306 1. 'acpi_osi=! acpi_osi="Windows 2000"' is equivalent 307 to 'acpi_osi="Windows 2000" acpi_osi=!', they all 308 can make '_OSI("Windows 2000")' TRUE. 309 310 'acpi_osi=' cannot be used in combination with other 311 'acpi_osi=' command lines, the _OSI method will not 312 exist in the ACPI namespace. NOTE that such command can 313 only affect the _OSI support state, thus specifying it 314 multiple times through kernel command line is also 315 meaningless. 316 Examples: 317 1. 'acpi_osi=' can make 'CondRefOf(_OSI, Local1)' 318 FALSE. 319 320 'acpi_osi=!*' can be used in combination with single or 321 multiple 'acpi_osi="string1"' to support specific 322 string(s). Note that such command can affect the 323 current state of both the OS vendor strings and the 324 feature group strings, thus specifying it multiple times 325 through kernel command line is meaningful. But it may 326 still not able to affect the final state of a string if 327 there are quirks related to this string. This command 328 is useful when one want to control the state of the 329 feature group strings to debug BIOS issues related to 330 the OSPM features. 331 Examples: 332 1. 'acpi_osi="Module Device" acpi_osi=!*' can make 333 '_OSI("Module Device")' FALSE. 334 2. 'acpi_osi=!* acpi_osi="Module Device"' can make 335 '_OSI("Module Device")' TRUE. 336 3. 'acpi_osi=! acpi_osi=!* acpi_osi="Windows 2000"' is 337 equivalent to 338 'acpi_osi=!* acpi_osi=! acpi_osi="Windows 2000"' 339 and 340 'acpi_osi=!* acpi_osi="Windows 2000" acpi_osi=!', 341 they all will make '_OSI("Windows 2000")' TRUE. 342 343 acpi_pm_good [X86] 344 Override the pmtimer bug detection: force the kernel 345 to assume that this machine's pmtimer latches its value 346 and always returns good values. 347 348 acpi_sci= [HW,ACPI,EARLY] ACPI System Control Interrupt trigger mode 349 Format: { level | edge | high | low } 350 351 acpi_skip_timer_override [HW,ACPI,EARLY] 352 Recognize and ignore IRQ0/pin2 Interrupt Override. 353 For broken nForce2 BIOS resulting in XT-PIC timer. 354 355 acpi_sleep= [HW,ACPI] Sleep options 356 Format: { s3_bios, s3_mode, s3_beep, s4_hwsig, 357 s4_nohwsig, old_ordering, nonvs, 358 sci_force_enable, nobl } 359 See Documentation/power/video.rst for information on 360 s3_bios and s3_mode. 361 s3_beep is for debugging; it makes the PC's speaker beep 362 as soon as the kernel's real-mode entry point is called. 363 s4_hwsig causes the kernel to check the ACPI hardware 364 signature during resume from hibernation, and gracefully 365 refuse to resume if it has changed. This complies with 366 the ACPI specification but not with reality, since 367 Windows does not do this and many laptops do change it 368 on docking. So the default behaviour is to allow resume 369 and simply warn when the signature changes, unless the 370 s4_hwsig option is enabled. 371 s4_nohwsig prevents ACPI hardware signature from being 372 used (or even warned about) during resume. 373 old_ordering causes the ACPI 1.0 ordering of the _PTS 374 control method, with respect to putting devices into 375 low power states, to be enforced (the ACPI 2.0 ordering 376 of _PTS is used by default). 377 nonvs prevents the kernel from saving/restoring the 378 ACPI NVS memory during suspend/hibernation and resume. 379 sci_force_enable causes the kernel to set SCI_EN directly 380 on resume from S1/S3 (which is against the ACPI spec, 381 but some broken systems don't work without it). 382 nobl causes the internal blacklist of systems known to 383 behave incorrectly in some ways with respect to system 384 suspend and resume to be ignored (use wisely). 385 386 acpi_use_timer_override [HW,ACPI,EARLY] 387 Use timer override. For some broken Nvidia NF5 boards 388 that require a timer override, but don't have HPET 389 390 add_efi_memmap [EFI,X86,EARLY] Include EFI memory map in 391 kernel's map of available physical RAM. 392 393 agp= [AGP] 394 { off | try_unsupported } 395 off: disable AGP support 396 try_unsupported: try to drive unsupported chipsets 397 (may crash computer or cause data corruption) 398 399 ALSA [HW,ALSA] 400 See Documentation/sound/alsa-configuration.rst 401 402 alignment= [KNL,ARM] 403 Allow the default userspace alignment fault handler 404 behaviour to be specified. Bit 0 enables warnings, 405 bit 1 enables fixups, and bit 2 sends a segfault. 406 407 align_va_addr= [X86-64] 408 Align virtual addresses by clearing slice [14:12] when 409 allocating a VMA at process creation time. This option 410 gives you up to 3% performance improvement on AMD F15h 411 machines (where it is enabled by default) for a 412 CPU-intensive style benchmark, and it can vary highly in 413 a microbenchmark depending on workload and compiler. 414 415 32: only for 32-bit processes 416 64: only for 64-bit processes 417 on: enable for both 32- and 64-bit processes 418 off: disable for both 32- and 64-bit processes 419 420 alloc_snapshot [FTRACE] 421 Allocate the ftrace snapshot buffer on boot up when the 422 main buffer is allocated. This is handy if debugging 423 and you need to use tracing_snapshot() on boot up, and 424 do not want to use tracing_snapshot_alloc() as it needs 425 to be done where GFP_KERNEL allocations are allowed. 426 427 allow_mismatched_32bit_el0 [ARM64,EARLY] 428 Allow execve() of 32-bit applications and setting of the 429 PER_LINUX32 personality on systems where only a strict 430 subset of the CPUs support 32-bit EL0. When this 431 parameter is present, the set of CPUs supporting 32-bit 432 EL0 is indicated by /sys/devices/system/cpu/aarch32_el0 433 and hot-unplug operations may be restricted. 434 435 See Documentation/arch/arm64/asymmetric-32bit.rst for more 436 information. 437 438 amd_iommu= [HW,X86-64] 439 Pass parameters to the AMD IOMMU driver in the system. 440 Possible values are: 441 fullflush - Deprecated, equivalent to iommu.strict=1 442 off - do not initialize any AMD IOMMU found in 443 the system 444 force_isolation - Force device isolation for all 445 devices. The IOMMU driver is not 446 allowed anymore to lift isolation 447 requirements as needed. This option 448 does not override iommu=pt 449 force_enable - Force enable the IOMMU on platforms known 450 to be buggy with IOMMU enabled. Use this 451 option with care. 452 pgtbl_v1 - Use v1 page table for DMA-API (Default). 453 pgtbl_v2 - Use v2 page table for DMA-API. 454 irtcachedis - Disable Interrupt Remapping Table (IRT) caching. 455 nohugepages - Limit page-sizes used for v1 page-tables 456 to 4 KiB. 457 v2_pgsizes_only - Limit page-sizes used for v1 page-tables 458 to 4KiB/2Mib/1GiB. 459 460 461 amd_iommu_dump= [HW,X86-64] 462 Enable AMD IOMMU driver option to dump the ACPI table 463 for AMD IOMMU. With this option enabled, AMD IOMMU 464 driver will print ACPI tables for AMD IOMMU during 465 IOMMU initialization. 466 467 amd_iommu_intr= [HW,X86-64] 468 Specifies one of the following AMD IOMMU interrupt 469 remapping modes: 470 legacy - Use legacy interrupt remapping mode. 471 vapic - Use virtual APIC mode, which allows IOMMU 472 to inject interrupts directly into guest. 473 This mode requires kvm-amd.avic=1. 474 (Default when IOMMU HW support is present.) 475 476 amd_pstate= [X86,EARLY] 477 disable 478 Do not enable amd_pstate as the default 479 scaling driver for the supported processors 480 passive 481 Use amd_pstate with passive mode as a scaling driver. 482 In this mode autonomous selection is disabled. 483 Driver requests a desired performance level and platform 484 tries to match the same performance level if it is 485 satisfied by guaranteed performance level. 486 active 487 Use amd_pstate_epp driver instance as the scaling driver, 488 driver provides a hint to the hardware if software wants 489 to bias toward performance (0x0) or energy efficiency (0xff) 490 to the CPPC firmware. then CPPC power algorithm will 491 calculate the runtime workload and adjust the realtime cores 492 frequency. 493 guided 494 Activate guided autonomous mode. Driver requests minimum and 495 maximum performance level and the platform autonomously 496 selects a performance level in this range and appropriate 497 to the current workload. 498 499 amd_prefcore= 500 [X86] 501 disable 502 Disable amd-pstate preferred core. 503 504 amd_dynamic_epp= 505 [X86] 506 disable 507 Disable amd-pstate dynamic EPP. 508 enable 509 Enable amd-pstate dynamic EPP. 510 511 amijoy.map= [HW,JOY] Amiga joystick support 512 Map of devices attached to JOY0DAT and JOY1DAT 513 Format: <a>,<b> 514 See also Documentation/input/joydev/joystick.rst 515 516 analog.map= [HW,JOY] Analog joystick and gamepad support 517 Specifies type or capabilities of an analog joystick 518 connected to one of 16 gameports 519 Format: <type1>,<type2>,..<type16> 520 521 apc= [HW,SPARC] 522 Power management functions (SPARCstation-4/5 + deriv.) 523 Format: noidle 524 Disable APC CPU standby support. SPARCstation-Fox does 525 not play well with APC CPU idle - disable it if you have 526 APC and your system crashes randomly. 527 528 apic [APIC,X86-64] Use IO-APIC. Default. 529 530 apic= [APIC,X86,EARLY] Advanced Programmable Interrupt Controller 531 Change the output verbosity while booting 532 Format: { quiet (default) | verbose | debug } 533 Change the amount of debugging information output 534 when initialising the APIC and IO-APIC components. 535 536 apic_extnmi= [APIC,X86,EARLY] External NMI delivery setting 537 Format: { bsp (default) | all | none } 538 bsp: External NMI is delivered only to CPU 0 539 all: External NMIs are broadcast to all CPUs as a 540 backup of CPU 0 541 none: External NMI is masked for all CPUs. This is 542 useful so that a dump capture kernel won't be 543 shot down by NMI 544 545 apicpmtimer Do APIC timer calibration using the pmtimer. Implies 546 apicmaintimer. Useful when your PIT timer is totally 547 broken. 548 549 autoconf= [IPV6] 550 See Documentation/networking/ipv6.rst. 551 552 apm= [APM] Advanced Power Management 553 See header of arch/x86/kernel/apm_32.c. 554 555 apparmor= [APPARMOR] Disable or enable AppArmor at boot time 556 Format: { "0" | "1" } 557 See security/apparmor/Kconfig help text 558 0 -- disable. 559 1 -- enable. 560 Default value is set via kernel config option. 561 562 arcrimi= [HW,NET] ARCnet - "RIM I" (entirely mem-mapped) cards 563 Format: <io>,<irq>,<nodeID> 564 565 arm64.no32bit_el0 [ARM64] Unconditionally disable the execution of 566 32 bit applications. 567 568 arm64.nobti [ARM64] Unconditionally disable Branch Target 569 Identification support 570 571 arm64.nogcs [ARM64] Unconditionally disable Guarded Control Stack 572 support 573 574 arm64.nomops [ARM64] Unconditionally disable Memory Copy and Memory 575 Set instructions support 576 577 arm64.nompam [ARM64] Unconditionally disable Memory Partitioning And 578 Monitoring support 579 580 arm64.nomte [ARM64] Unconditionally disable Memory Tagging Extension 581 support 582 583 arm64.nopauth [ARM64] Unconditionally disable Pointer Authentication 584 support 585 586 arm64.nosme [ARM64] Unconditionally disable Scalable Matrix 587 Extension support 588 589 arm64.nosve [ARM64] Unconditionally disable Scalable Vector 590 Extension support 591 592 ataflop= [HW,M68k] 593 594 atarimouse= [HW,MOUSE] Atari Mouse 595 596 atkbd.extra= [HW] Enable extra LEDs and keys on IBM RapidAccess, 597 EzKey and similar keyboards 598 599 atkbd.reset= [HW] Reset keyboard during initialization 600 601 atkbd.set= [HW] Select keyboard code set 602 Format: <int> (2 = AT (default), 3 = PS/2) 603 604 atkbd.scroll= [HW] Enable scroll wheel on MS Office and similar 605 keyboards 606 607 atkbd.softraw= [HW] Choose between synthetic and real raw mode 608 Format: <bool> (0 = real, 1 = synthetic (default)) 609 610 atkbd.softrepeat= [HW] 611 Use software keyboard repeat 612 613 audit= [KNL] Enable the audit sub-system 614 Format: { "0" | "1" | "off" | "on" } 615 0 | off - kernel audit is disabled and can not be 616 enabled until the next reboot 617 unset - kernel audit is initialized but disabled and 618 will be fully enabled by the userspace auditd. 619 1 | on - kernel audit is initialized and partially 620 enabled, storing at most audit_backlog_limit 621 messages in RAM until it is fully enabled by the 622 userspace auditd. 623 Default: unset 624 625 audit_backlog_limit= [KNL] Set the audit queue size limit. 626 Format: <int> (must be >=0) 627 Default: 64 628 629 bau= [X86_UV] Enable the BAU on SGI UV. The default 630 behavior is to disable the BAU (i.e. bau=0). 631 Format: { "0" | "1" } 632 0 - Disable the BAU. 633 1 - Enable the BAU. 634 unset - Disable the BAU. 635 636 baycom_epp= [HW,AX25] 637 Format: <io>,<mode> 638 639 baycom_par= [HW,AX25] BayCom Parallel Port AX.25 Modem 640 Format: <io>,<mode> 641 See header of drivers/net/hamradio/baycom_par.c. 642 643 baycom_ser_fdx= [HW,AX25] 644 BayCom Serial Port AX.25 Modem (Full Duplex Mode) 645 Format: <io>,<irq>,<mode>[,<baud>] 646 See header of drivers/net/hamradio/baycom_ser_fdx.c. 647 648 baycom_ser_hdx= [HW,AX25] 649 BayCom Serial Port AX.25 Modem (Half Duplex Mode) 650 Format: <io>,<irq>,<mode> 651 See header of drivers/net/hamradio/baycom_ser_hdx.c. 652 653 bdev_allow_write_mounted= 654 Format: <bool> 655 Control the ability to open a mounted block device 656 for writing, i.e., allow / disallow writes that bypass 657 the FS. This was implemented as a means to prevent 658 fuzzers from crashing the kernel by overwriting the 659 metadata underneath a mounted FS without its awareness. 660 This also prevents destructive formatting of mounted 661 filesystems by naive storage tooling that don't use 662 O_EXCL. Default is Y and can be changed through the 663 Kconfig option CONFIG_BLK_DEV_WRITE_MOUNTED. 664 665 bert_disable [ACPI] 666 Disable BERT OS support on buggy BIOSes. 667 668 bgrt_disable [ACPI,X86,EARLY] 669 Disable BGRT to avoid flickering OEM logo. 670 671 blkdevparts= Manual partition parsing of block device(s) for 672 embedded devices based on command line input. 673 See Documentation/block/cmdline-partition.rst 674 675 boot_delay= [KNL,EARLY] 676 Milliseconds to delay each printk during boot. 677 Only works if CONFIG_BOOT_PRINTK_DELAY is enabled, 678 and you may also have to specify "lpj=". Boot_delay 679 values larger than 10 seconds (10000) are assumed 680 erroneous and ignored. 681 Format: integer 682 683 bootconfig [KNL,EARLY] 684 Extended command line options can be added to an initrd 685 and this will cause the kernel to look for it. 686 687 See Documentation/admin-guide/bootconfig.rst 688 689 bttv.card= [HW,V4L] bttv (bt848 + bt878 based grabber cards) 690 bttv.radio= Most important insmod options are available as 691 kernel args too. 692 bttv.pll= See Documentation/admin-guide/media/bttv.rst 693 bttv.tuner= 694 695 bulk_remove=off [PPC] This parameter disables the use of the pSeries 696 firmware feature for flushing multiple hpte entries 697 at a time. 698 699 c101= [NET] Moxa C101 synchronous serial card 700 701 cachesize= [BUGS=X86-32] Override level 2 CPU cache size detection. 702 Sometimes CPU hardware bugs make them report the cache 703 size incorrectly. The kernel will attempt work arounds 704 to fix known problems, but for some CPUs it is not 705 possible to determine what the correct size should be. 706 This option provides an override for these situations. 707 708 carrier_timeout= 709 [NET] Specifies amount of time (in seconds) that 710 the kernel should wait for a network carrier. By default 711 it waits 120 seconds. 712 713 ca_keys= [KEYS] This parameter identifies a specific key(s) on 714 the system trusted keyring to be used for certificate 715 trust validation. 716 format: { id:<keyid> | builtin } 717 718 cca= [MIPS,EARLY] Override the kernel pages' cache coherency 719 algorithm. Accepted values range from 0 to 7 720 inclusive. See arch/mips/include/asm/pgtable-bits.h 721 for platform specific values (SB1, Loongson3 and 722 others). 723 724 ccw_timeout_log [S390] 725 See Documentation/arch/s390/common_io.rst for details. 726 727 cfi= [X86-64] Set Control Flow Integrity checking features 728 when CONFIG_FINEIBT is enabled. 729 Format: feature[,feature...] 730 Default: auto 731 732 auto: Use FineIBT if IBT available, otherwise kCFI. 733 Under FineIBT, enable "paranoid" mode when 734 FRED is not available. 735 off: Turn off CFI checking. 736 kcfi: Use kCFI (disable FineIBT). 737 fineibt: Use FineIBT (even if IBT not available). 738 norand: Do not re-randomize CFI hashes. 739 paranoid: Add caller hash checking under FineIBT. 740 bhi: Enable register poisoning to stop speculation 741 across FineIBT. (Disabled by default.) 742 warn: Do not enforce CFI checking: warn only. 743 debug: Report CFI initialization details. 744 745 cgroup_disable= [KNL] Disable a particular controller or optional feature 746 Format: {name of the controller(s) or feature(s) to disable} 747 The effects of cgroup_disable=foo are: 748 - foo isn't auto-mounted if you mount all cgroups in 749 a single hierarchy 750 - foo isn't visible as an individually mountable 751 subsystem 752 - if foo is an optional feature then the feature is 753 disabled and corresponding cgroup files are not 754 created 755 {Currently only "memory" controller deal with this and 756 cut the overhead, others just disable the usage. So 757 only cgroup_disable=memory is actually worthy} 758 Specifying "pressure" disables per-cgroup pressure 759 stall information accounting feature 760 761 cgroup_no_v1= [KNL] Disable cgroup controllers and named hierarchies in v1 762 Format: { { controller | "all" | "named" } 763 [,{ controller | "all" | "named" }...] } 764 Like cgroup_disable, but only applies to cgroup v1; 765 the blacklisted controllers remain available in cgroup2. 766 "all" blacklists all controllers and "named" disables 767 named mounts. Specifying both "all" and "named" disables 768 all v1 hierarchies. 769 770 cgroup_v1_proc= [KNL] Show also missing controllers in /proc/cgroups 771 Format: { "true" | "false" } 772 /proc/cgroups lists only v1 controllers by default. 773 This compatibility option enables listing also v2 774 controllers (whose v1 code is not compiled!), so that 775 semi-legacy software can check this file to decide 776 about usage of v2 (sic) controllers. 777 778 cgroup_favordynmods= [KNL] Enable or Disable favordynmods. 779 Format: { "true" | "false" } 780 Defaults to the value of CONFIG_CGROUP_FAVOR_DYNMODS. 781 782 cgroup.memory= [KNL] Pass options to the cgroup memory controller. 783 Format: <string> 784 nosocket -- Disable socket memory accounting. 785 nokmem -- Disable kernel memory accounting. 786 nobpf -- Disable BPF memory accounting. 787 788 check_pages= [MM,EARLY] Enable sanity checking of pages after 789 allocations / before freeing. This adds checks to catch 790 double-frees, use-after-frees, and other sources of 791 page corruption by inspecting page internals (flags, 792 mapcount/refcount, memcg_data, etc.). 793 Format: { "0" | "1" } 794 Default: 0 (1 if CONFIG_DEBUG_VM is set) 795 796 checkreqprot= [SELINUX] Set initial checkreqprot flag value. 797 Format: { "0" | "1" } 798 See security/selinux/Kconfig help text. 799 0 -- check protection applied by kernel (includes 800 any implied execute protection). 801 1 -- check protection requested by application. 802 Default value is set via a kernel config option. 803 Value can be changed at runtime via 804 /sys/fs/selinux/checkreqprot. 805 Setting checkreqprot to 1 is deprecated. 806 807 cio_ignore= [S390] 808 See Documentation/arch/s390/common_io.rst for details. 809 810 clearcpuid=X[,X...] [X86] 811 Disable CPUID feature X for the kernel. See 812 arch/x86/include/asm/cpufeatures.h for the valid bit 813 numbers X. Note the Linux-specific bits are not necessarily 814 stable over kernel options, but the vendor-specific 815 ones should be. 816 X can also be a string as appearing in the flags: line 817 in /proc/cpuinfo which does not have the above 818 instability issue. However, not all features have names 819 in /proc/cpuinfo. 820 Note that using this option will taint your kernel. 821 Also note that user programs calling CPUID directly 822 or using the feature without checking anything 823 will still see it. This just prevents it from 824 being used by the kernel or shown in /proc/cpuinfo. 825 Also note the kernel might malfunction if you disable 826 some critical bits. 827 828 clk_ignore_unused 829 [CLK] 830 Prevents the clock framework from automatically gating 831 clocks that have not been explicitly enabled by a Linux 832 device driver but are enabled in hardware at reset or 833 by the bootloader/firmware. Note that this does not 834 force such clocks to be always-on nor does it reserve 835 those clocks in any way. This parameter is useful for 836 debug and development, but should not be needed on a 837 platform with proper driver support. For more 838 information, see Documentation/driver-api/clk.rst. 839 840 clock= [BUGS=X86-32, HW] gettimeofday clocksource override. 841 [Deprecated] 842 Forces specified clocksource (if available) to be used 843 when calculating gettimeofday(). If specified 844 clocksource is not available, it defaults to PIT. 845 Format: { pit | tsc | cyclone | pmtmr } 846 847 clocksource= Override the default clocksource 848 Format: <string> 849 Override the default clocksource and use the clocksource 850 with the name specified. 851 Some clocksource names to choose from, depending on 852 the platform: 853 [all] jiffies (this is the base, fallback clocksource) 854 [ACPI] acpi_pm 855 [ARM] imx_timer1,OSTS,netx_timer,mpu_timer2, 856 pxa_timer,timer3,32k_counter,timer0_1 857 [X86-32] pit,hpet,tsc; 858 scx200_hrt on Geode; cyclone on IBM x440 859 [MIPS] MIPS 860 [PARISC] cr16 861 [S390] tod 862 [SH] SuperH 863 [SPARC64] tick 864 [X86-64] hpet,tsc 865 866 clocksource.arm_arch_timer.evtstrm= 867 [ARM,ARM64,EARLY] 868 Format: <bool> 869 Enable/disable the eventstream feature of the ARM 870 architected timer so that code using WFE-based polling 871 loops can be debugged more effectively on production 872 systems. 873 874 clocksource.verify_n_cpus= [KNL] 875 Limit the number of CPUs checked for clocksources 876 marked with CLOCK_SOURCE_VERIFY_PERCPU that 877 are marked unstable due to excessive skew. 878 A negative value says to check all CPUs, while 879 zero says not to check any. Values larger than 880 nr_cpu_ids are silently truncated to nr_cpu_ids. 881 The actual CPUs are chosen randomly, with 882 no replacement if the same CPU is chosen twice. 883 884 clocksource-wdtest.holdoff= [KNL] 885 Set the time in seconds that the clocksource 886 watchdog test waits before commencing its tests. 887 Defaults to zero when built as a module and to 888 10 seconds when built into the kernel. 889 890 cma=nn[MG]@[start[MG][-end[MG]]] 891 [KNL,CMA,EARLY] 892 Sets the size of kernel global memory area for 893 contiguous memory allocations and optionally the 894 placement constraint by the physical address range of 895 memory allocations. A value of 0 disables CMA 896 altogether. For more information, see 897 kernel/dma/contiguous.c 898 899 cma_pernuma=nn[MG] 900 [KNL,CMA,EARLY] 901 Sets the size of kernel per-numa memory area for 902 contiguous memory allocations. A value of 0 disables 903 per-numa CMA altogether. And If this option is not 904 specified, the default value is 0. 905 With per-numa CMA enabled, DMA users on node nid will 906 first try to allocate buffer from the pernuma area 907 which is located in node nid, if the allocation fails, 908 they will fallback to the global default memory area. 909 910 numa_cma=<node>:nn[MG][,<node>:nn[MG]] 911 [KNL,CMA,EARLY] 912 Sets the size of kernel numa memory area for 913 contiguous memory allocations. It will reserve CMA 914 area for the specified node. 915 916 With numa CMA enabled, DMA users on node nid will 917 first try to allocate buffer from the numa area 918 which is located in node nid, if the allocation fails, 919 they will fallback to the global default memory area. 920 921 cmo_free_hint= [PPC] Format: { yes | no } 922 Specify whether pages are marked as being inactive 923 when they are freed. This is used in CMO environments 924 to determine OS memory pressure for page stealing by 925 a hypervisor. 926 Default: yes 927 928 coherent_pool=nn[KMG] [ARM,KNL,EARLY] 929 Sets the size of memory pool for coherent, atomic dma 930 allocations, by default set to 256K. 931 932 com20020= [HW,NET] ARCnet - COM20020 chipset 933 Format: 934 <io>[,<irq>[,<nodeID>[,<backplane>[,<ckp>[,<timeout>]]]]] 935 936 com90io= [HW,NET] ARCnet - COM90xx chipset (IO-mapped buffers) 937 Format: <io>[,<irq>] 938 939 com90xx= [HW,NET] 940 ARCnet - COM90xx chipset (memory-mapped buffers) 941 Format: <io>[,<irq>[,<memstart>]] 942 943 condev= [HW,S390] console device 944 conmode= 945 946 con3215_drop= [S390,EARLY] 3215 console drop mode. 947 Format: y|n|Y|N|1|0 948 When set to true, drop data on the 3215 console when 949 the console buffer is full. In this case the 950 operator using a 3270 terminal emulator (for example 951 x3270) does not have to enter the clear key for the 952 console output to advance and the kernel to continue. 953 This leads to a much faster boot time when a 3270 954 terminal emulator is active. If no 3270 terminal 955 emulator is used, this parameter has no effect. 956 957 console= [KNL] Output console device and options. 958 959 tty<n> Use the virtual console device <n>. 960 961 ttyS<n>[,options] 962 ttyUSB0[,options] 963 Use the specified serial port. The options are of 964 the form "bbbbpnf", where "bbbb" is the baud rate, 965 "p" is parity ("n", "o", or "e"), "n" is number of 966 bits, and "f" is flow control ("r" for RTS or 967 omit it). Default is "9600n8". 968 969 See Documentation/admin-guide/serial-console.rst for more 970 information. See 971 Documentation/networking/netconsole.rst for an 972 alternative. 973 974 <DEVNAME>:<n>.<n>[,options] 975 Use the specified serial port on the serial core bus. 976 The addressing uses DEVNAME of the physical serial port 977 device, followed by the serial core controller instance, 978 and the serial port instance. The options are the same 979 as documented for the ttyS addressing above. 980 981 The mapping of the serial ports to the tty instances 982 can be viewed with: 983 984 $ ls -d /sys/bus/serial-base/devices/*:*.*/tty/* 985 /sys/bus/serial-base/devices/00:04:0.0/tty/ttyS0 986 987 In the above example, the console can be addressed with 988 console=00:04:0.0. Note that a console addressed this 989 way will only get added when the related device driver 990 is ready. The use of an earlycon parameter in addition to 991 the console may be desired for console output early on. 992 993 uart[8250],io,<addr>[,options] 994 uart[8250],mmio,<addr>[,options] 995 uart[8250],mmio16,<addr>[,options] 996 uart[8250],mmio32,<addr>[,options] 997 uart[8250],0x<addr>[,options] 998 Start an early, polled-mode console on the 8250/16550 999 UART at the specified I/O port or MMIO address, 1000 switching to the matching ttyS device later. 1001 MMIO inter-register address stride is either 8-bit 1002 (mmio), 16-bit (mmio16), or 32-bit (mmio32). 1003 If none of [io|mmio|mmio16|mmio32], <addr> is assumed 1004 to be equivalent to 'mmio'. 'options' are specified in 1005 the same format described for ttyS above; if unspecified, 1006 the h/w is not re-initialized. 1007 1008 hvc<n> Use the hypervisor console device <n>. This is for 1009 both Xen and PowerPC hypervisors. 1010 1011 { null | "" } 1012 Use to disable console output, i.e., to have kernel 1013 console messages discarded. 1014 This must be the only console= parameter used on the 1015 kernel command line. 1016 1017 If the device connected to the port is not a TTY but a braille 1018 device, prepend "brl," before the device type, for instance 1019 console=brl,ttyS0 1020 For now, only VisioBraille is supported. 1021 1022 console_msg_format= 1023 [KNL] Change console messages format 1024 default 1025 By default we print messages on consoles in 1026 "[time stamp] text\n" format (time stamp may not be 1027 printed, depending on CONFIG_PRINTK_TIME or 1028 `printk_time' param). 1029 syslog 1030 Switch to syslog format: "<%u>[time stamp] text\n" 1031 IOW, each message will have a facility and loglevel 1032 prefix. The format is similar to one used by syslog() 1033 syscall, or to executing "dmesg -S --raw" or to reading 1034 from /proc/kmsg. 1035 1036 consoleblank= [KNL] The console blank (screen saver) timeout in 1037 seconds. A value of 0 disables the blank timer. 1038 Defaults to 0. 1039 1040 coredump_filter= 1041 [KNL] Change the default value for 1042 /proc/<pid>/coredump_filter. 1043 See also Documentation/filesystems/proc.rst. 1044 1045 coresight_cpu_debug.enable 1046 [ARM,ARM64] 1047 Format: <bool> 1048 Enable/disable the CPU sampling based debugging. 1049 0: default value, disable debugging 1050 1: enable debugging at boot time 1051 1052 cpcihp_generic= [HW,PCI] Generic port I/O CompactPCI driver 1053 Format: 1054 <first_slot>,<last_slot>,<port>,<enum_bit>[,<debug>] 1055 1056 cpuidle.off=1 [CPU_IDLE] 1057 disable the cpuidle sub-system 1058 1059 cpuidle.governor= 1060 [CPU_IDLE] Name of the cpuidle governor to use. 1061 1062 cpufreq.off=1 [CPU_FREQ] 1063 disable the cpufreq sub-system 1064 1065 cpufreq.default_governor= 1066 [CPU_FREQ] Name of the default cpufreq governor or 1067 policy to use. This governor must be registered in the 1068 kernel before the cpufreq driver probes. 1069 1070 cpu_init_udelay=N 1071 [X86,EARLY] Delay for N microsec between assert and de-assert 1072 of APIC INIT to start processors. This delay occurs 1073 on every CPU online, such as boot, and resume from suspend. 1074 Default: 10000 1075 1076 cpuhp.parallel= 1077 [SMP] Enable/disable parallel bringup of secondary CPUs 1078 Format: <bool> 1079 Default is enabled if CONFIG_HOTPLUG_PARALLEL=y. Otherwise 1080 the parameter has no effect. 1081 1082 crash_kexec_post_notifiers 1083 Only jump to kdump kernel after running the panic 1084 notifiers and dumping kmsg. This option increases 1085 the risks of a kdump failure, since some panic 1086 notifiers can make the crashed kernel more unstable. 1087 In configurations where kdump may not be reliable, 1088 running the panic notifiers could allow collecting 1089 more data on dmesg, like stack traces from other CPUS 1090 or extra data dumped by panic_print. Note that some 1091 configurations enable this option unconditionally, 1092 like Hyper-V, PowerPC (fadump) and AMD SEV-SNP. 1093 1094 crashkernel=size[KMG][@offset[KMG]] 1095 [KNL,EARLY] Using kexec, Linux can switch to a 'crash kernel' 1096 upon panic. This parameter reserves the physical 1097 memory region [offset, offset + size] for that kernel 1098 image. If '@offset' is omitted, then a suitable offset 1099 is selected automatically. 1100 [KNL, X86-64, ARM64, RISCV, LoongArch] Select a region 1101 under 4G first, and fall back to reserve region above 1102 4G when '@offset' hasn't been specified. 1103 See Documentation/admin-guide/kdump/kdump.rst for further details. 1104 1105 crashkernel=range1:size1[,range2:size2,...][@offset] 1106 [KNL] Same as above, but depends on the memory 1107 in the running system. The syntax of range is 1108 start-[end] where start and end are both 1109 a memory unit (amount[KMG]). See also 1110 Documentation/admin-guide/kdump/kdump.rst for an example. 1111 1112 crashkernel=size[KMG],high 1113 [KNL, X86-64, ARM64, RISCV, LoongArch] range could be 1114 above 4G. 1115 Allow kernel to allocate physical memory region from top, 1116 so could be above 4G if system have more than 4G ram 1117 installed. Otherwise memory region will be allocated 1118 below 4G, if available. 1119 It will be ignored if crashkernel=X is specified. 1120 crashkernel=size[KMG],low 1121 [KNL, X86-64, ARM64, RISCV, LoongArch] range under 4G. 1122 When crashkernel=X,high is passed, kernel could allocate 1123 physical memory region above 4G, that cause second kernel 1124 crash on system that require some amount of low memory, 1125 e.g. swiotlb requires at least 64M+32K low memory, also 1126 enough extra low memory is needed to make sure DMA buffers 1127 for 32-bit devices won't run out. Kernel would try to allocate 1128 default size of memory below 4G automatically. The default 1129 size is platform dependent. 1130 --> x86: max(swiotlb_size_or_default() + 8MiB, 256MiB) 1131 --> arm64: 128MiB 1132 --> riscv: 128MiB 1133 --> loongarch: 128MiB 1134 This one lets the user specify own low range under 4G 1135 for second kernel instead. 1136 0: to disable low allocation. 1137 It will be ignored when crashkernel=X,high is not used 1138 or memory reserved is below 4G. 1139 crashkernel=size[KMG],cma 1140 [KNL, X86, ppc] Reserve additional crash kernel memory from 1141 CMA. This reservation is usable by the first system's 1142 userspace memory and kernel movable allocations (memory 1143 balloon, zswap). Pages allocated from this memory range 1144 will not be included in the vmcore so this should not 1145 be used if dumping of userspace memory is intended and 1146 it has to be expected that some movable kernel pages 1147 may be missing from the dump. 1148 1149 A standard crashkernel reservation, as described above, 1150 is still needed to hold the crash kernel and initrd. 1151 1152 This option increases the risk of a kdump failure: DMA 1153 transfers configured by the first kernel may end up 1154 corrupting the second kernel's memory. 1155 1156 This reservation method is intended for systems that 1157 can't afford to sacrifice enough memory for standard 1158 crashkernel reservation and where less reliable and 1159 possibly incomplete kdump is preferable to no kdump at 1160 all. 1161 1162 cryptomgr.notests 1163 [KNL] Disable crypto self-tests 1164 1165 cs89x0_dma= [HW,NET] 1166 Format: <dma> 1167 1168 cs89x0_media= [HW,NET] 1169 Format: { rj45 | aui | bnc } 1170 1171 csdlock_debug= [KNL] Enable or disable debug add-ons of cross-CPU 1172 function call handling. When switched on, 1173 additional debug data is printed to the console 1174 in case a hanging CPU is detected, and that 1175 CPU is pinged again in order to try to resolve 1176 the hang situation. The default value of this 1177 option depends on the CSD_LOCK_WAIT_DEBUG_DEFAULT 1178 Kconfig option. 1179 1180 dasd= [HW,NET] 1181 See header of drivers/s390/block/dasd_devmap.c. 1182 1183 db9.dev[2|3]= [HW,JOY] Multisystem joystick support via parallel port 1184 (one device per port) 1185 Format: <port#>,<type> 1186 See also Documentation/input/devices/joystick-parport.rst 1187 1188 debug [KNL,EARLY] Enable kernel debugging (events log level). 1189 1190 debug_boot_weak_hash 1191 [KNL,EARLY] Enable printing [hashed] pointers early in the 1192 boot sequence. If enabled, we use a weak hash instead 1193 of siphash to hash pointers. Use this option if you are 1194 seeing instances of '(___ptrval___)') and need to see a 1195 value (hashed pointer) instead. Cryptographically 1196 insecure, please do not use on production kernels. 1197 1198 debug_locks_verbose= 1199 [KNL] verbose locking self-tests 1200 Format: <int> 1201 Print debugging info while doing the locking API 1202 self-tests. 1203 Bitmask for the various LOCKTYPE_ tests. Defaults to 0 1204 (no extra messages), setting it to -1 (all bits set) 1205 will print _a_lot_ more information - normally only 1206 useful to lockdep developers. 1207 1208 debug_objects [KNL,EARLY] Enable object debugging 1209 1210 debug_guardpage_minorder= 1211 [KNL,EARLY] When CONFIG_DEBUG_PAGEALLOC is set, this 1212 parameter allows control of the order of pages that will 1213 be intentionally kept free (and hence protected) by the 1214 buddy allocator. Bigger value increase the probability 1215 of catching random memory corruption, but reduce the 1216 amount of memory for normal system use. The maximum 1217 possible value is MAX_PAGE_ORDER/2. Setting this 1218 parameter to 1 or 2 should be enough to identify most 1219 random memory corruption problems caused by bugs in 1220 kernel or driver code when a CPU writes to (or reads 1221 from) a random memory location. Note that there exists 1222 a class of memory corruptions problems caused by buggy 1223 H/W or F/W or by drivers badly programming DMA 1224 (basically when memory is written at bus level and the 1225 CPU MMU is bypassed) which are not detectable by 1226 CONFIG_DEBUG_PAGEALLOC, hence this option will not 1227 help tracking down these problems. 1228 1229 debug_pagealloc= 1230 [KNL,EARLY] When CONFIG_DEBUG_PAGEALLOC is set, this parameter 1231 enables the feature at boot time. By default, it is 1232 disabled and the system will work mostly the same as a 1233 kernel built without CONFIG_DEBUG_PAGEALLOC. 1234 Note: to get most of debug_pagealloc error reports, it's 1235 useful to also enable the page_owner functionality. 1236 on: enable the feature 1237 1238 debugfs= [KNL,EARLY] This parameter enables what is exposed to 1239 userspace and debugfs internal clients. 1240 Format: { on, off } 1241 on: All functions are enabled. 1242 off: Filesystem is not registered and clients 1243 get a -EPERM as result when trying to register files 1244 or directories within debugfs. 1245 This is equivalent of the runtime functionality if 1246 debugfs was not enabled in the kernel at all. 1247 Default value is set in build-time with a kernel configuration. 1248 1249 debugpat [X86] Enable PAT debugging 1250 1251 default_hugepagesz= 1252 [HW] The size of the default HugeTLB page. This is 1253 the size represented by the legacy /proc/ hugepages 1254 APIs. In addition, this is the default hugetlb size 1255 used for shmget(), mmap() and mounting hugetlbfs 1256 filesystems. If not specified, defaults to the 1257 architecture's default huge page size. Huge page 1258 sizes are architecture dependent. See also 1259 Documentation/admin-guide/mm/hugetlbpage.rst. 1260 Format: size[KMG] 1261 1262 deferred_probe_timeout= 1263 [KNL] Debugging option to set a timeout in seconds for 1264 deferred probe to give up waiting on dependencies to 1265 probe. Only specific dependencies (subsystems or 1266 drivers) that have opted in will be ignored. A timeout 1267 of 0 will timeout at the end of initcalls. If the time 1268 out hasn't expired, it'll be restarted by each 1269 successful driver registration. This option will also 1270 dump out devices still on the deferred probe list after 1271 retrying. 1272 1273 delayacct [KNL] Enable per-task delay accounting 1274 1275 dell_smm_hwmon.ignore_dmi= 1276 [HW] Continue probing hardware even if DMI data 1277 indicates that the driver is running on unsupported 1278 hardware. 1279 1280 dell_smm_hwmon.force= 1281 [HW] Activate driver even if SMM BIOS signature does 1282 not match list of supported models and enable otherwise 1283 blacklisted features. 1284 1285 dell_smm_hwmon.power_status= 1286 [HW] Report power status in /proc/i8k 1287 (disabled by default). 1288 1289 dell_smm_hwmon.restricted= 1290 [HW] Allow controlling fans only if SYS_ADMIN 1291 capability is set. 1292 1293 dell_smm_hwmon.fan_mult= 1294 [HW] Factor to multiply fan speed with. 1295 1296 dell_smm_hwmon.fan_max= 1297 [HW] Maximum configurable fan speed. 1298 1299 dfltcc= [HW,S390] 1300 Format: { on | off | def_only | inf_only | always } 1301 on: s390 zlib hardware support for compression on 1302 level 1 and decompression (default) 1303 off: No s390 zlib hardware support 1304 def_only: s390 zlib hardware support for deflate 1305 only (compression on level 1) 1306 inf_only: s390 zlib hardware support for inflate 1307 only (decompression) 1308 always: Same as 'on' but ignores the selected compression 1309 level always using hardware support (used for debugging) 1310 1311 dhash_entries= [KNL] 1312 Set number of hash buckets for dentry cache. 1313 1314 disable_1tb_segments [PPC,EARLY] 1315 Disables the use of 1TB hash page table segments. This 1316 causes the kernel to fall back to 256MB segments which 1317 can be useful when debugging issues that require an SLB 1318 miss to occur. 1319 1320 disable= [IPV6] 1321 See Documentation/networking/ipv6.rst. 1322 1323 disable_radix [PPC,EARLY] 1324 Disable RADIX MMU mode on POWER9 1325 1326 disable_tlbie [PPC] 1327 Disable TLBIE instruction. Currently does not work 1328 with KVM, with HASH MMU, or with coherent accelerators. 1329 1330 disable_ddw [PPC/PSERIES,EARLY] 1331 Disable Dynamic DMA Window support. Use this 1332 to workaround buggy firmware. 1333 1334 disable_ipv6= [IPV6] 1335 See Documentation/networking/ipv6.rst. 1336 1337 disable_mtrr_cleanup [X86,EARLY] 1338 The kernel tries to adjust MTRR layout from continuous 1339 to discrete, to make X server driver able to add WB 1340 entry later. This parameter disables that. 1341 1342 disable_mtrr_trim [X86, Intel and AMD only,EARLY] 1343 By default the kernel will trim any uncacheable 1344 memory out of your available memory pool based on 1345 MTRR settings. This parameter disables that behavior, 1346 possibly causing your machine to run very slowly. 1347 1348 disable_timer_pin_1 [X86,EARLY] 1349 Disable PIN 1 of APIC timer 1350 Can be useful to work around chipset bugs. 1351 1352 dis_ucode_ldr [X86] Disable the microcode loader. 1353 1354 dma_debug=off If the kernel is compiled with DMA_API_DEBUG support, 1355 this option disables the debugging code at boot. 1356 1357 dma_debug_entries=<number> 1358 This option allows to tune the number of preallocated 1359 entries for DMA-API debugging code. One entry is 1360 required per DMA-API allocation. Use this if the 1361 DMA-API debugging code disables itself because the 1362 architectural default is too low. 1363 1364 dma_debug_driver=<driver_name> 1365 With this option the DMA-API debugging driver 1366 filter feature can be enabled at boot time. Just 1367 pass the driver to filter for as the parameter. 1368 The filter can be disabled or changed to another 1369 driver later using sysfs. 1370 1371 reg_file_data_sampling= 1372 [X86] Controls mitigation for Register File Data 1373 Sampling (RFDS) vulnerability. RFDS is a CPU 1374 vulnerability which may allow userspace to infer 1375 kernel data values previously stored in floating point 1376 registers, vector registers, or integer registers. 1377 RFDS only affects Intel Atom processors. 1378 1379 on: Turns ON the mitigation. 1380 off: Turns OFF the mitigation. 1381 1382 This parameter overrides the compile time default set 1383 by CONFIG_MITIGATION_RFDS. Mitigation cannot be 1384 disabled when other VERW based mitigations (like MDS) 1385 are enabled. In order to disable RFDS mitigation all 1386 VERW based mitigations need to be disabled. 1387 1388 For details see: 1389 Documentation/admin-guide/hw-vuln/reg-file-data-sampling.rst 1390 1391 dm_verity.keyring_unsealed= 1392 [KNL] When set to 1, leave the dm-verity keyring 1393 unsealed after initialization so userspace can 1394 provision keys. Once the keyring is restricted 1395 it becomes active and is searched during signature 1396 verification. 1397 1398 driver_async_probe= [KNL] 1399 List of driver names to be probed asynchronously. * 1400 matches with all driver names. If * is specified, the 1401 rest of the listed driver names are those that will NOT 1402 match the *. 1403 Format: <driver_name1>,<driver_name2>... 1404 1405 drm.edid_firmware=[<connector>:]<file>[,[<connector>:]<file>] 1406 Broken monitors, graphic adapters, KVMs and EDIDless 1407 panels may send no or incorrect EDID data sets. 1408 This parameter allows to specify an EDID data sets 1409 in the /lib/firmware directory that are used instead. 1410 An EDID data set will only be used for a particular 1411 connector, if its name and a colon are prepended to 1412 the EDID name. Each connector may use a unique EDID 1413 data set by separating the files with a comma. An EDID 1414 data set with no connector name will be used for 1415 any connectors not explicitly specified. 1416 1417 dscc4.setup= [NET] 1418 1419 dt_cpu_ftrs= [PPC,EARLY] 1420 Format: {"off" | "known"} 1421 Control how the dt_cpu_ftrs device-tree binding is 1422 used for CPU feature discovery and setup (if it 1423 exists). 1424 off: Do not use it, fall back to legacy cpu table. 1425 known: Do not pass through unknown features to guests 1426 or userspace, only those that the kernel is aware of. 1427 1428 dump_apple_properties [X86] 1429 Dump name and content of EFI device properties on 1430 x86 Macs. Useful for driver authors to determine 1431 what data is available or for reverse-engineering. 1432 1433 dyndbg[="val"] [KNL,DYNAMIC_DEBUG] 1434 <module>.dyndbg[="val"] 1435 Enable debug messages at boot time. See 1436 Documentation/admin-guide/dynamic-debug-howto.rst 1437 for details. 1438 1439 early_ioremap_debug [KNL,EARLY] 1440 Enable debug messages in early_ioremap support. This 1441 is useful for tracking down temporary early mappings 1442 which are not unmapped. 1443 1444 earlycon= [KNL,EARLY] Output early console device and options. 1445 1446 When used with no options, the early console is 1447 determined by stdout-path property in device tree's 1448 chosen node or the ACPI SPCR table if supported by 1449 the platform. 1450 1451 cdns,<addr>[,options] 1452 Start an early, polled-mode console on a Cadence 1453 (xuartps) serial port at the specified address. Only 1454 supported option is baud rate. If baud rate is not 1455 specified, the serial port must already be setup and 1456 configured. 1457 1458 uart[8250],io,<addr>[,options[,uartclk]] 1459 uart[8250],mmio,<addr>[,options[,uartclk]] 1460 uart[8250],mmio32,<addr>[,options[,uartclk]] 1461 uart[8250],mmio32be,<addr>[,options[,uartclk]] 1462 uart[8250],0x<addr>[,options] 1463 Start an early, polled-mode console on the 8250/16550 1464 UART at the specified I/O port or MMIO address. 1465 MMIO inter-register address stride is either 8-bit 1466 (mmio) or 32-bit (mmio32 or mmio32be). 1467 If none of [io|mmio|mmio32|mmio32be], <addr> is assumed 1468 to be equivalent to 'mmio'. 'options' are specified 1469 in the same format described for "console=ttyS<n>"; if 1470 unspecified, the h/w is not initialized. 'uartclk' is 1471 the uart clock frequency; if unspecified, it is set 1472 to 'BASE_BAUD' * 16. 1473 1474 pl011,<addr> 1475 pl011,mmio32,<addr> 1476 Start an early, polled-mode console on a pl011 serial 1477 port at the specified address. The pl011 serial port 1478 must already be setup and configured. Options are not 1479 yet supported. If 'mmio32' is specified, then only 1480 the driver will use only 32-bit accessors to read/write 1481 the device registers. 1482 1483 liteuart,<addr> 1484 Start an early console on a litex serial port at the 1485 specified address. The serial port must already be 1486 setup and configured. Options are not yet supported. 1487 1488 meson,<addr> 1489 Start an early, polled-mode console on a meson serial 1490 port at the specified address. The serial port must 1491 already be setup and configured. Options are not yet 1492 supported. 1493 1494 msm_serial,<addr> 1495 Start an early, polled-mode console on an msm serial 1496 port at the specified address. The serial port 1497 must already be setup and configured. Options are not 1498 yet supported. 1499 1500 msm_serial_dm,<addr> 1501 Start an early, polled-mode console on an msm serial 1502 dm port at the specified address. The serial port 1503 must already be setup and configured. Options are not 1504 yet supported. 1505 1506 owl,<addr> 1507 Start an early, polled-mode console on a serial port 1508 of an Actions Semi SoC, such as S500 or S900, at the 1509 specified address. The serial port must already be 1510 setup and configured. Options are not yet supported. 1511 1512 rda,<addr> 1513 Start an early, polled-mode console on a serial port 1514 of an RDA Micro SoC, such as RDA8810PL, at the 1515 specified address. The serial port must already be 1516 setup and configured. Options are not yet supported. 1517 1518 sbi 1519 Use RISC-V SBI (Supervisor Binary Interface) for early 1520 console. 1521 1522 smh Use ARM semihosting calls for early console. 1523 1524 s3c2410,<addr> 1525 s3c2412,<addr> 1526 s3c2440,<addr> 1527 s3c6400,<addr> 1528 s5pv210,<addr> 1529 exynos4210,<addr> 1530 Use early console provided by serial driver available 1531 on Samsung SoCs, requires selecting proper type and 1532 a correct base address of the selected UART port. The 1533 serial port must already be setup and configured. 1534 Options are not yet supported. 1535 1536 lantiq,<addr> 1537 Start an early, polled-mode console on a lantiq serial 1538 (lqasc) port at the specified address. The serial port 1539 must already be setup and configured. Options are not 1540 yet supported. 1541 1542 lpuart,<addr> 1543 lpuart32,<addr> 1544 Use early console provided by Freescale LP UART driver 1545 found on Freescale Vybrid and QorIQ LS1021A processors. 1546 A valid base address must be provided, and the serial 1547 port must already be setup and configured. 1548 1549 ec_imx21,<addr> 1550 ec_imx6q,<addr> 1551 Start an early, polled-mode, output-only console on the 1552 Freescale i.MX UART at the specified address. The UART 1553 must already be setup and configured. 1554 1555 ar3700_uart,<addr> 1556 Start an early, polled-mode console on the 1557 Armada 3700 serial port at the specified 1558 address. The serial port must already be setup 1559 and configured. Options are not yet supported. 1560 1561 qcom_geni,<addr> 1562 Start an early, polled-mode console on a Qualcomm 1563 Generic Interface (GENI) based serial port at the 1564 specified address. The serial port must already be 1565 setup and configured. Options are not yet supported. 1566 1567 efifb,[options] 1568 Start an early, unaccelerated console on the EFI 1569 memory mapped framebuffer (if available). On cache 1570 coherent non-x86 systems that use system memory for 1571 the framebuffer, pass the 'ram' option so that it is 1572 mapped with the correct attributes. 1573 1574 linflex,<addr> 1575 Use early console provided by Freescale LINFlexD UART 1576 serial driver for NXP S32V234 SoCs. A valid base 1577 address must be provided, and the serial port must 1578 already be setup and configured. 1579 1580 earlyprintk= [X86,SH,ARM,M68k,S390,UM,EARLY] 1581 earlyprintk=vga 1582 earlyprintk=sclp 1583 earlyprintk=xen 1584 earlyprintk=serial[,ttySn[,baudrate]] 1585 earlyprintk=serial[,0x...[,baudrate]] 1586 earlyprintk=ttySn[,baudrate] 1587 earlyprintk=dbgp[debugController#] 1588 earlyprintk=mmio32,membase[,{nocfg|baudrate}] 1589 earlyprintk=pciserial[,force],bus:device.function[,{nocfg|baudrate}] 1590 earlyprintk=xdbc[xhciController#] 1591 earlyprintk=bios 1592 1593 earlyprintk is useful when the kernel crashes before 1594 the normal console is initialized. It is not enabled by 1595 default because it has some cosmetic problems. 1596 1597 Use "nocfg" to skip UART configuration, assume 1598 BIOS/firmware has configured UART correctly. 1599 1600 Append ",keep" to not disable it when the real console 1601 takes over. 1602 1603 Only one of vga, serial, or usb debug port can 1604 be used at a time. 1605 1606 Currently only ttyS0 and ttyS1 may be specified by 1607 name. Other I/O ports may be explicitly specified 1608 on some architectures (x86 and arm at least) by 1609 replacing ttySn with an I/O port address, like this: 1610 earlyprintk=serial,0x1008,115200 1611 You can find the port for a given device in 1612 /proc/tty/driver/serial: 1613 2: uart:ST16650V2 port:00001008 irq:18 ... 1614 1615 Interaction with the standard serial driver is not 1616 very good. 1617 1618 The VGA output is eventually overwritten by 1619 the real console. 1620 1621 The xen option can only be used in Xen domains. 1622 1623 The sclp output can only be used on s390. 1624 1625 The bios output can only be used on SuperH. 1626 1627 The optional "force" to "pciserial" enables use of a 1628 PCI device even when its classcode is not of the 1629 UART class. 1630 1631 edac_report= [HW,EDAC] Control how to report EDAC event 1632 Format: {"on" | "off" | "force"} 1633 on: enable EDAC to report H/W event. May be overridden 1634 by other higher priority error reporting module. 1635 off: disable H/W event reporting through EDAC. 1636 force: enforce the use of EDAC to report H/W event. 1637 default: on. 1638 1639 edd= [EDD] 1640 Format: {"off" | "on" | "skip[mbr]"} 1641 1642 efi= [EFI,EARLY] 1643 Format: { "debug", "disable_early_pci_dma", 1644 "nochunk", "noruntime", "nosoftreserve", 1645 "novamap", "no_disable_early_pci_dma" } 1646 debug: enable misc debug output. 1647 disable_early_pci_dma: disable the busmaster bit on all 1648 PCI bridges while in the EFI boot stub. 1649 nochunk: disable reading files in "chunks" in the EFI 1650 boot stub, as chunking can cause problems with some 1651 firmware implementations. 1652 noruntime : disable EFI runtime services support 1653 nosoftreserve: The EFI_MEMORY_SP (Specific Purpose) 1654 attribute may cause the kernel to reserve the 1655 memory range for a memory mapping driver to 1656 claim. Specify efi=nosoftreserve to disable this 1657 reservation and treat the memory by its base type 1658 (i.e. EFI_CONVENTIONAL_MEMORY / "System RAM"). 1659 novamap: do not call SetVirtualAddressMap(). 1660 no_disable_early_pci_dma: Leave the busmaster bit set 1661 on all PCI bridges while in the EFI boot stub 1662 1663 efi_no_storage_paranoia [EFI,X86,EARLY] 1664 Using this parameter you can use more than 50% of 1665 your efi variable storage. Use this parameter only if 1666 you are really sure that your UEFI does sane gc and 1667 fulfills the spec otherwise your board may brick. 1668 1669 efivar_ssdt= [EFI; X86] Name of an EFI variable that contains an SSDT 1670 that is to be dynamically loaded by Linux. If there are 1671 multiple variables with the same name but with different 1672 vendor GUIDs, all of them will be loaded. See 1673 Documentation/admin-guide/acpi/ssdt-overlays.rst for details. 1674 1675 1676 eisa_irq_edge= [PARISC,HW] 1677 See header of drivers/parisc/eisa.c. 1678 1679 ekgdboc= [X86,KGDB,EARLY] Allow early kernel console debugging 1680 Format: ekgdboc=kbd 1681 1682 This is designed to be used in conjunction with 1683 the boot argument: earlyprintk=vga 1684 1685 This parameter works in place of the kgdboc parameter 1686 but can only be used if the backing tty is available 1687 very early in the boot process. For early debugging 1688 via a serial port see kgdboc_earlycon instead. 1689 1690 elanfreq= [X86-32] 1691 See comment before function elanfreq_setup() in 1692 arch/x86/kernel/cpu/cpufreq/elanfreq.c. 1693 1694 elfcorehdr=[size[KMG]@]offset[KMG] [PPC,SH,X86,S390,EARLY] 1695 Specifies physical address of start of kernel core 1696 image elf header and optionally the size. Generally 1697 kexec loader will pass this option to capture kernel. 1698 See Documentation/admin-guide/kdump/kdump.rst for details. 1699 1700 enable_mtrr_cleanup [X86,EARLY] 1701 The kernel tries to adjust MTRR layout from continuous 1702 to discrete, to make X server driver able to add WB 1703 entry later. This parameter enables that. 1704 1705 enable_timer_pin_1 [X86] 1706 Enable PIN 1 of APIC timer 1707 Can be useful to work around chipset bugs 1708 (in particular on some ATI chipsets). 1709 The kernel tries to set a reasonable default. 1710 1711 enforcing= [SELINUX] Set initial enforcing status. 1712 Format: {"0" | "1"} 1713 See security/selinux/Kconfig help text. 1714 0 -- permissive (log only, no denials). 1715 1 -- enforcing (deny and log). 1716 Default value is 0. 1717 Value can be changed at runtime via 1718 /sys/fs/selinux/enforce. 1719 1720 erst_disable [ACPI] 1721 Disable Error Record Serialization Table (ERST) 1722 support. 1723 1724 ether= [HW,NET] Ethernet cards parameters 1725 This option is obsoleted by the "netdev=" option, which 1726 has equivalent usage. See its documentation for details. 1727 1728 evm= [EVM] 1729 Format: { "fix" } 1730 Permit 'security.evm' to be updated regardless of 1731 current integrity status. 1732 1733 early_page_ext [KNL,EARLY] Enforces page_ext initialization to earlier 1734 stages so cover more early boot allocations. 1735 Please note that as side effect some optimizations 1736 might be disabled to achieve that (e.g. parallelized 1737 memory initialization is disabled) so the boot process 1738 might take longer, especially on systems with a lot of 1739 memory. Available with CONFIG_PAGE_EXTENSION=y. 1740 1741 failslab= 1742 fail_usercopy= 1743 fail_page_alloc= 1744 fail_skb_realloc= 1745 fail_make_request=[KNL] 1746 General fault injection mechanism. 1747 Format: <interval>,<probability>,<space>,<times> 1748 See also Documentation/fault-injection/. 1749 1750 fb_tunnels= [NET] 1751 Format: { initns | none } 1752 See Documentation/admin-guide/sysctl/net.rst for 1753 fb_tunnels_only_for_init_ns 1754 1755 floppy= [HW] 1756 See Documentation/admin-guide/blockdev/floppy.rst. 1757 1758 forcepae [X86-32] 1759 Forcefully enable Physical Address Extension (PAE). 1760 Many Pentium M systems disable PAE but may have a 1761 functionally usable PAE implementation. 1762 Warning: use of this parameter will taint the kernel 1763 and may cause unknown problems. 1764 1765 fred= [X86-64] 1766 Enable/disable Flexible Return and Event Delivery. 1767 Format: { on | off } 1768 on: enable FRED when it's present. 1769 off: disable FRED, the default setting. 1770 1771 ftrace=[tracer] 1772 [FTRACE] will set and start the specified tracer 1773 as early as possible in order to facilitate early 1774 boot debugging. 1775 1776 ftrace_boot_snapshot 1777 [FTRACE] On boot up, a snapshot will be taken of the 1778 ftrace ring buffer that can be read at: 1779 /sys/kernel/tracing/snapshot. 1780 This is useful if you need tracing information from kernel 1781 boot up that is likely to be overridden by user space 1782 start up functionality. 1783 1784 Optionally, the snapshot can also be defined for a tracing 1785 instance that was created by the trace_instance= command 1786 line parameter. 1787 1788 trace_instance=foo,sched_switch ftrace_boot_snapshot=foo 1789 1790 The above will cause the "foo" tracing instance to trigger 1791 a snapshot at the end of boot up. 1792 1793 ftrace_dump_on_oops[=2(orig_cpu) | =<instance>][,<instance> | 1794 ,<instance>=2(orig_cpu)] 1795 [FTRACE] will dump the trace buffers on oops. 1796 If no parameter is passed, ftrace will dump global 1797 buffers of all CPUs, if you pass 2 or orig_cpu, it 1798 will dump only the buffer of the CPU that triggered 1799 the oops, or the specific instance will be dumped if 1800 its name is passed. Multiple instance dump is also 1801 supported, and instances are separated by commas. Each 1802 instance supports only dump on CPU that triggered the 1803 oops by passing 2 or orig_cpu to it. 1804 1805 ftrace_dump_on_oops=foo=orig_cpu 1806 1807 The above will dump only the buffer of "foo" instance 1808 on CPU that triggered the oops. 1809 1810 ftrace_dump_on_oops,foo,bar=orig_cpu 1811 1812 The above will dump global buffer on all CPUs, the 1813 buffer of "foo" instance on all CPUs and the buffer 1814 of "bar" instance on CPU that triggered the oops. 1815 1816 ftrace_filter=[function-list] 1817 [FTRACE] Limit the functions traced by the function 1818 tracer at boot up. function-list is a comma-separated 1819 list of functions. This list can be changed at run 1820 time by the set_ftrace_filter file in the debugfs 1821 tracing directory. 1822 1823 ftrace_notrace=[function-list] 1824 [FTRACE] Do not trace the functions specified in 1825 function-list. This list can be changed at run time 1826 by the set_ftrace_notrace file in the debugfs 1827 tracing directory. 1828 1829 ftrace_graph_filter=[function-list] 1830 [FTRACE] Limit the top level callers functions traced 1831 by the function graph tracer at boot up. 1832 function-list is a comma-separated list of functions 1833 that can be changed at run time by the 1834 set_graph_function file in the debugfs tracing directory. 1835 1836 ftrace_graph_notrace=[function-list] 1837 [FTRACE] Do not trace from the functions specified in 1838 function-list. This list is a comma-separated list of 1839 functions that can be changed at run time by the 1840 set_graph_notrace file in the debugfs tracing directory. 1841 1842 ftrace_graph_max_depth=<uint> 1843 [FTRACE] Used with the function graph tracer. This is 1844 the max depth it will trace into a function. This value 1845 can be changed at run time by the max_graph_depth file 1846 in the tracefs tracing directory. default: 0 (no limit) 1847 1848 fw_devlink= [KNL,EARLY] Create device links between consumer and supplier 1849 devices by scanning the firmware to infer the 1850 consumer/supplier relationships. This feature is 1851 especially useful when drivers are loaded as modules as 1852 it ensures proper ordering of tasks like device probing 1853 (suppliers first, then consumers), supplier boot state 1854 clean up (only after all consumers have probed), 1855 suspend/resume & runtime PM (consumers first, then 1856 suppliers). 1857 Format: { off | permissive | on | rpm } 1858 off -- Don't create device links from firmware info. 1859 permissive -- Create device links from firmware info 1860 but use it only for ordering boot state clean 1861 up (sync_state() calls). 1862 on -- Create device links from firmware info and use it 1863 to enforce probe and suspend/resume ordering. 1864 rpm -- Like "on", but also use to order runtime PM. 1865 1866 fw_devlink.strict=<bool> 1867 [KNL,EARLY] Treat all inferred dependencies as mandatory 1868 dependencies. This only applies for fw_devlink=on|rpm. 1869 Format: <bool> 1870 1871 fw_devlink.sync_state = 1872 [KNL,EARLY] When all devices that could probe have finished 1873 probing, this parameter controls what to do with 1874 devices that haven't yet received their sync_state() 1875 calls. 1876 Format: { strict | timeout } 1877 strict -- Default. Continue waiting on consumers to 1878 probe successfully. 1879 timeout -- Give up waiting on consumers and call 1880 sync_state() on any devices that haven't yet 1881 received their sync_state() calls after 1882 deferred_probe_timeout has expired or by 1883 late_initcall() if !CONFIG_MODULES. 1884 1885 gamecon.map[2|3]= 1886 [HW,JOY] Multisystem joystick and NES/SNES/PSX pad 1887 support via parallel port (up to 5 devices per port) 1888 Format: <port#>,<pad1>,<pad2>,<pad3>,<pad4>,<pad5> 1889 See also Documentation/input/devices/joystick-parport.rst 1890 1891 gamma= [HW,DRM] 1892 1893 gart_fix_e820= [X86-64,EARLY] disable the fix e820 for K8 GART 1894 Format: off | on 1895 default: on 1896 1897 gather_data_sampling= 1898 [X86,INTEL,EARLY] Control the Gather Data Sampling (GDS) 1899 mitigation. 1900 1901 Gather Data Sampling is a hardware vulnerability which 1902 allows unprivileged speculative access to data which was 1903 previously stored in vector registers. 1904 1905 This issue is mitigated by default in updated microcode. 1906 The mitigation may have a performance impact but can be 1907 disabled. On systems without the microcode mitigation 1908 disabling AVX serves as a mitigation. 1909 1910 force: Disable AVX to mitigate systems without 1911 microcode mitigation. No effect if the microcode 1912 mitigation is present. Known to cause crashes in 1913 userspace with buggy AVX enumeration. 1914 1915 off: Disable GDS mitigation. 1916 1917 gbpages [X86] Use GB pages for kernel direct mappings. 1918 1919 gcov_persist= [GCOV] When non-zero (default), profiling data for 1920 kernel modules is saved and remains accessible via 1921 debugfs, even when the module is unloaded/reloaded. 1922 When zero, profiling data is discarded and associated 1923 debugfs files are removed at module unload time. 1924 1925 goldfish [X86] Enable the goldfish android emulator platform. 1926 Don't use this when you are not running on the 1927 android emulator 1928 1929 gpio-mockup.gpio_mockup_ranges 1930 [HW] Sets the ranges of gpiochip of for this device. 1931 Format: <start1>,<end1>,<start2>,<end2>... 1932 gpio-mockup.gpio_mockup_named_lines 1933 [HW] Let the driver know GPIO lines should be named. 1934 1935 gpt [EFI] Forces disk with valid GPT signature but 1936 invalid Protective MBR to be treated as GPT. If the 1937 primary GPT is corrupted, it enables the backup/alternate 1938 GPT to be used instead. 1939 1940 grcan.enable0= [HW] Configuration of physical interface 0. Determines 1941 the "Enable 0" bit of the configuration register. 1942 Format: 0 | 1 1943 Default: 0 1944 grcan.enable1= [HW] Configuration of physical interface 1. Determines 1945 the "Enable 0" bit of the configuration register. 1946 Format: 0 | 1 1947 Default: 0 1948 grcan.select= [HW] Select which physical interface to use. 1949 Format: 0 | 1 1950 Default: 0 1951 grcan.txsize= [HW] Sets the size of the tx buffer. 1952 Format: <unsigned int> such that (txsize & ~0x1fffc0) == 0. 1953 Default: 1024 1954 grcan.rxsize= [HW] Sets the size of the rx buffer. 1955 Format: <unsigned int> such that (rxsize & ~0x1fffc0) == 0. 1956 Default: 1024 1957 1958 hardened_usercopy= 1959 [KNL] Under CONFIG_HARDENED_USERCOPY, whether 1960 hardening is enabled for this boot. Hardened 1961 usercopy checking is used to protect the kernel 1962 from reading or writing beyond known memory 1963 allocation boundaries as a proactive defense 1964 against bounds-checking flaws in the kernel's 1965 copy_to_user()/copy_from_user() interface. 1966 The default is determined by 1967 CONFIG_HARDENED_USERCOPY_DEFAULT_ON. 1968 on Perform hardened usercopy checks. 1969 off Disable hardened usercopy checks. 1970 1971 hardlockup_all_cpu_backtrace= 1972 [KNL] Should the hard-lockup detector generate 1973 backtraces on all cpus. 1974 Format: 0 | 1 1975 1976 hash_pointers= 1977 [KNL,EARLY] 1978 By default, when pointers are printed to the console 1979 or buffers via the %p format string, that pointer is 1980 "hashed", i.e. obscured by hashing the pointer value. 1981 This is a security feature that hides actual kernel 1982 addresses from unprivileged users, but it also makes 1983 debugging the kernel more difficult since unequal 1984 pointers can no longer be compared. The choices are: 1985 Format: { auto | always | never } 1986 Default: auto 1987 1988 auto - Hash pointers unless slab_debug is enabled. 1989 always - Always hash pointers (even if slab_debug is 1990 enabled). 1991 never - Never hash pointers. This option should only 1992 be specified when debugging the kernel. Do 1993 not use on production kernels. The boot 1994 param "no_hash_pointers" is an alias for 1995 this mode. 1996 1997 For controlling hashing dynamically at runtime, 1998 use the "kernel.kptr_restrict" sysctl instead. 1999 2000 hashdist= [KNL,NUMA] Large hashes allocated during boot 2001 are distributed across NUMA nodes. Defaults on 2002 for 64-bit NUMA, off otherwise. 2003 Format: 0 | 1 (for off | on) 2004 2005 hd= [EIDE] (E)IDE hard drive subsystem geometry 2006 Format: <cyl>,<head>,<sect> 2007 2008 hest_disable [ACPI] 2009 Disable Hardware Error Source Table (HEST) support; 2010 corresponding firmware-first mode error processing 2011 logic will be disabled. 2012 2013 hibernate= [HIBERNATION] 2014 noresume Don't check if there's a hibernation image 2015 present during boot. 2016 nocompress Don't compress/decompress hibernation images. 2017 no Disable hibernation and resume. 2018 protect_image Turn on image protection during restoration 2019 (that will set all pages holding image data 2020 during restoration read-only). 2021 2022 hibernate.compressor= [HIBERNATION] Compression algorithm to be 2023 used with hibernation. 2024 Format: { lzo | lz4 } 2025 Default: lzo 2026 2027 lzo: Select LZO compression algorithm to 2028 compress/decompress hibernation image. 2029 2030 lz4: Select LZ4 compression algorithm to 2031 compress/decompress hibernation image. 2032 2033 hibernate.pm_test_delay= 2034 [HIBERNATION] 2035 Sets the number of seconds to remain in a hibernation test 2036 mode before resuming the system (see 2037 /sys/power/pm_test). Only available when CONFIG_PM_DEBUG 2038 is set. Default value is 5. 2039 2040 hibernate_compression_threads= 2041 [HIBERNATION] 2042 Set the number of threads used for compressing or decompressing 2043 hibernation images. 2044 2045 Format: <integer> 2046 Default: 3 2047 Minimum: 1 2048 Example: hibernate_compression_threads=4 2049 2050 highmem=nn[KMG] [KNL,BOOT,EARLY] forces the highmem zone to have an exact 2051 size of <nn>. This works even on boxes that have no 2052 highmem otherwise. This also works to reduce highmem 2053 size on bigger boxes. 2054 2055 highres= [KNL] Enable/disable high resolution timer mode. 2056 Valid parameters: "on", "off" 2057 Default: "on" 2058 2059 hlt [BUGS=ARM,SH] 2060 2061 hostname= [KNL,EARLY] Set the hostname (aka UTS nodename). 2062 Format: <string> 2063 This allows setting the system's hostname during early 2064 startup. This sets the name returned by gethostname. 2065 Using this parameter to set the hostname makes it 2066 possible to ensure the hostname is correctly set before 2067 any userspace processes run, avoiding the possibility 2068 that a process may call gethostname before the hostname 2069 has been explicitly set, resulting in the calling 2070 process getting an incorrect result. The string must 2071 not exceed the maximum allowed hostname length (usually 2072 64 characters) and will be truncated otherwise. 2073 2074 hpet= [X86-32,HPET] option to control HPET usage 2075 Format: { enable (default) | disable | force | 2076 verbose } 2077 disable: disable HPET and use PIT instead 2078 force: allow force enabled of undocumented chips (ICH4, 2079 VIA, nVidia) 2080 verbose: show contents of HPET registers during setup 2081 2082 hpet_mmap= [X86, HPET_MMAP] Allow userspace to mmap HPET 2083 registers. Default set by CONFIG_HPET_MMAP_DEFAULT. 2084 2085 hugepages= [HW,EARLY] Number of HugeTLB pages to allocate at boot. 2086 If this follows hugepagesz (below), it specifies 2087 the number of pages of hugepagesz to be allocated. 2088 If this is the first HugeTLB parameter on the command 2089 line, it specifies the number of pages to allocate for 2090 the default huge page size. If using node format, the 2091 number of pages to allocate per-node can be specified. 2092 See also Documentation/admin-guide/mm/hugetlbpage.rst. 2093 Format: <integer> or (node format) 2094 <node>:<integer>[,<node>:<integer>] 2095 2096 hugepagesz= 2097 [HW,EARLY] The size of the HugeTLB pages. This is 2098 used in conjunction with hugepages (above) to 2099 allocate huge pages of a specific size at boot. The 2100 pair hugepagesz=X hugepages=Y can be specified once 2101 for each supported huge page size. Huge page sizes 2102 are architecture dependent. See also 2103 Documentation/admin-guide/mm/hugetlbpage.rst. 2104 Format: size[KMG] 2105 2106 hugepage_alloc_threads= 2107 [HW] The number of threads that should be used to 2108 allocate hugepages during boot. This option can be 2109 used to improve system bootup time when allocating 2110 a large amount of huge pages. 2111 The default value is 25% of the available hardware threads. 2112 2113 Note that this parameter only applies to non-gigantic huge pages. 2114 2115 hugetlb_cma= [HW,CMA,EARLY] The size of a CMA area used for allocation 2116 of gigantic hugepages. Or using node format, the size 2117 of a CMA area per node can be specified. 2118 Format: nn[KMGTPE] or (node format) 2119 <node>:nn[KMGTPE][,<node>:nn[KMGTPE]] 2120 2121 Reserve a CMA area of given size and allocate gigantic 2122 hugepages using the CMA allocator. If enabled, the 2123 boot-time allocation of gigantic hugepages is skipped. 2124 2125 hugetlb_cma_only= 2126 [HW,CMA,EARLY] When allocating new HugeTLB pages, only 2127 try to allocate from the CMA areas. 2128 2129 This option does nothing if hugetlb_cma= is not also 2130 specified. 2131 2132 hugetlb_free_vmemmap= 2133 [KNL] Requires CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP 2134 enabled. 2135 Control if HugeTLB Vmemmap Optimization (HVO) is enabled. 2136 Allows heavy hugetlb users to free up some more 2137 memory (7 * PAGE_SIZE for each 2MB hugetlb page). 2138 Format: { on | off (default) } 2139 2140 on: enable HVO 2141 off: disable HVO 2142 2143 Built with CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP_DEFAULT_ON=y, 2144 the default is on. 2145 2146 Note that the vmemmap pages may be allocated from the added 2147 memory block itself when memory_hotplug.memmap_on_memory is 2148 enabled, those vmemmap pages cannot be optimized even if this 2149 feature is enabled. Other vmemmap pages not allocated from 2150 the added memory block itself do not be affected. 2151 2152 hung_task_panic= 2153 [KNL] Number of hung tasks to trigger kernel panic. 2154 Format: <int> 2155 2156 When set to a non-zero value, a kernel panic will be triggered if 2157 the number of detected hung tasks reaches this value. 2158 2159 0: don't panic 2160 1: panic immediately on first hung task 2161 N: panic after N hung tasks are detected in a single scan 2162 2163 The default value is controlled by the 2164 CONFIG_BOOTPARAM_HUNG_TASK_PANIC build-time option. The value 2165 selected by this boot parameter can be changed later by the 2166 kernel.hung_task_panic sysctl. 2167 2168 hvc_iucv= [S390] Number of z/VM IUCV hypervisor console (HVC) 2169 terminal devices. Valid values: 0..8 2170 hvc_iucv_allow= [S390] Comma-separated list of z/VM user IDs. 2171 If specified, z/VM IUCV HVC accepts connections 2172 from listed z/VM user IDs only. 2173 2174 hv_nopvspin [X86,HYPER_V,EARLY] 2175 Disables the paravirt spinlock optimizations 2176 which allow the hypervisor to 'idle' the guest 2177 on lock contention. 2178 2179 hw_protection= [HW] 2180 Format: reboot | shutdown 2181 2182 Hardware protection action taken on critical events like 2183 overtemperature or imminent voltage loss. 2184 2185 i2c_bus= [HW] Override the default board specific I2C bus speed 2186 or register an additional I2C bus that is not 2187 registered from board initialization code. 2188 Format: 2189 <bus_id>,<clkrate> 2190 2191 i2c_touchscreen_props= [HW,ACPI,X86] 2192 Set device-properties for ACPI-enumerated I2C-attached 2193 touchscreen, to e.g. fix coordinates of upside-down 2194 mounted touchscreens. If you need this option please 2195 submit a drivers/platform/x86/touchscreen_dmi.c patch 2196 adding a DMI quirk for this. 2197 2198 Format: 2199 <ACPI_HW_ID>:<prop_name>=<val>[:prop_name=val][:...] 2200 Where <val> is one of: 2201 Omit "=<val>" entirely Set a boolean device-property 2202 Unsigned number Set a u32 device-property 2203 Anything else Set a string device-property 2204 2205 Examples (split over multiple lines): 2206 i2c_touchscreen_props=GDIX1001:touchscreen-inverted-x: 2207 touchscreen-inverted-y 2208 2209 i2c_touchscreen_props=MSSL1680:touchscreen-size-x=1920: 2210 touchscreen-size-y=1080:touchscreen-inverted-y: 2211 firmware-name=gsl1680-vendor-model.fw:silead,home-button 2212 2213 i8042.debug [HW] Toggle i8042 debug mode 2214 i8042.unmask_kbd_data 2215 [HW] Enable printing of interrupt data from the KBD port 2216 (disabled by default, and as a pre-condition 2217 requires that i8042.debug=1 be enabled) 2218 i8042.direct [HW] Put keyboard port into non-translated mode 2219 i8042.dumbkbd [HW] Pretend that controller can only read data from 2220 keyboard and cannot control its state 2221 (Don't attempt to blink the leds) 2222 i8042.noaux [HW] Don't check for auxiliary (== mouse) port 2223 i8042.nokbd [HW] Don't check/create keyboard port 2224 i8042.noloop [HW] Disable the AUX Loopback command while probing 2225 for the AUX port 2226 i8042.nomux [HW] Don't check presence of an active multiplexing 2227 controller 2228 i8042.nopnp [HW] Don't use ACPIPnP / PnPBIOS to discover KBD/AUX 2229 controllers 2230 i8042.notimeout [HW] Ignore timeout condition signalled by controller 2231 i8042.reset [HW] Reset the controller during init, cleanup and 2232 suspend-to-ram transitions, only during s2r 2233 transitions, or never reset 2234 Format: { 1 | Y | y | 0 | N | n } 2235 1, Y, y: always reset controller 2236 0, N, n: don't ever reset controller 2237 Default: only on s2r transitions on x86; most other 2238 architectures force reset to be always executed 2239 i8042.unlock [HW] Unlock (ignore) the keylock 2240 i8042.kbdreset [HW] Reset device connected to KBD port 2241 i8042.probe_defer 2242 [HW] Allow deferred probing upon i8042 probe errors 2243 2244 i810= [HW,DRM] 2245 2246 i915.invert_brightness= 2247 [DRM] Invert the sense of the variable that is used to 2248 set the brightness of the panel backlight. Normally a 2249 brightness value of 0 indicates backlight switched off, 2250 and the maximum of the brightness value sets the backlight 2251 to maximum brightness. If this parameter is set to 0 2252 (default) and the machine requires it, or this parameter 2253 is set to 1, a brightness value of 0 sets the backlight 2254 to maximum brightness, and the maximum of the brightness 2255 value switches the backlight off. 2256 -1 -- never invert brightness 2257 0 -- machine default 2258 1 -- force brightness inversion 2259 2260 ia32_emulation= [X86-64] 2261 Format: <bool> 2262 When true, allows loading 32-bit programs and executing 32-bit 2263 syscalls, essentially overriding IA32_EMULATION_DEFAULT_DISABLED at 2264 boot time. When false, unconditionally disables IA32 emulation. 2265 2266 icn= [HW,ISDN] 2267 Format: <io>[,<membase>[,<icn_id>[,<icn_id2>]]] 2268 2269 2270 idle= [X86,EARLY] 2271 Format: idle=poll, idle=halt, idle=nomwait 2272 2273 idle=poll: Don't do power saving in the idle loop 2274 using HLT, but poll for rescheduling event. This will 2275 make the CPUs eat a lot more power, but may be useful 2276 to get slightly better performance in multiprocessor 2277 benchmarks. It also makes some profiling using 2278 performance counters more accurate. Please note that 2279 on systems with MONITOR/MWAIT support (like Intel 2280 EM64T CPUs) this option has no performance advantage 2281 over the normal idle loop. It may also interact badly 2282 with hyperthreading. 2283 2284 idle=halt: Halt is forced to be used for CPU idle. 2285 In such case C2/C3 won't be used again. 2286 2287 idle=nomwait: Disable mwait for CPU C-states 2288 2289 idxd.sva= [HW] 2290 Format: <bool> 2291 Allow force disabling of Shared Virtual Memory (SVA) 2292 support for the idxd driver. By default it is set to 2293 true (1). 2294 2295 idxd.tc_override= [HW] 2296 Format: <bool> 2297 Allow override of default traffic class configuration 2298 for the device. By default it is set to false (0). 2299 2300 ieee754= [MIPS] Select IEEE Std 754 conformance mode 2301 Format: { strict | legacy | 2008 | relaxed | emulated } 2302 Default: strict 2303 2304 Choose which programs will be accepted for execution 2305 based on the IEEE 754 NaN encoding(s) supported by 2306 the FPU and the NaN encoding requested with the value 2307 of an ELF file header flag individually set by each 2308 binary. Hardware implementations are permitted to 2309 support either or both of the legacy and the 2008 NaN 2310 encoding mode. 2311 2312 Available settings are as follows: 2313 strict accept binaries that request a NaN encoding 2314 supported by the FPU 2315 legacy only accept legacy-NaN binaries, if supported 2316 by the FPU 2317 2008 only accept 2008-NaN binaries, if supported 2318 by the FPU 2319 relaxed accept any binaries regardless of whether 2320 supported by the FPU 2321 emulated accept any binaries but enable FPU emulator 2322 if binary mode is unsupported by the FPU. 2323 2324 The FPU emulator is always able to support both NaN 2325 encodings, so if no FPU hardware is present or it has 2326 been disabled with 'nofpu', then the settings of 2327 'legacy' and '2008' strap the emulator accordingly, 2328 'relaxed' straps the emulator for both legacy-NaN and 2329 2008-NaN, whereas 'strict' enables legacy-NaN only on 2330 legacy processors and both NaN encodings on MIPS32 or 2331 MIPS64 CPUs. 2332 2333 The setting for ABS.fmt/NEG.fmt instruction execution 2334 mode generally follows that for the NaN encoding, 2335 except where unsupported by hardware. 2336 2337 ignore_loglevel [KNL,EARLY] 2338 Ignore loglevel setting - this will print /all/ 2339 kernel messages to the console. Useful for debugging. 2340 We also add it as printk module parameter, so users 2341 could change it dynamically, usually by 2342 /sys/module/printk/parameters/ignore_loglevel. 2343 2344 ignore_rlimit_data 2345 Ignore RLIMIT_DATA setting for data mappings, 2346 print warning at first misuse. Can be changed via 2347 /sys/module/kernel/parameters/ignore_rlimit_data. 2348 2349 ihash_entries= [KNL] 2350 Set number of hash buckets for inode cache. 2351 2352 ima_appraise= [IMA] appraise integrity measurements 2353 Format: { "off" | "enforce" | "fix" | "log" } 2354 default: "enforce" 2355 2356 ima_appraise_tcb [IMA] Deprecated. Use ima_policy= instead. 2357 The builtin appraise policy appraises all files 2358 owned by uid=0. 2359 2360 ima_canonical_fmt [IMA] 2361 Use the canonical format for the binary runtime 2362 measurements, instead of host native format. 2363 2364 ima_hash= [IMA] 2365 Format: { md5 | sha1 | rmd160 | sha256 | sha384 2366 | sha512 | ... } 2367 default: "sha1" 2368 2369 The list of supported hash algorithms is defined 2370 in crypto/hash_info.h. 2371 2372 ima_policy= [IMA] 2373 The builtin policies to load during IMA setup. 2374 Format: "tcb | appraise_tcb | secure_boot | 2375 fail_securely | critical_data" 2376 2377 The "tcb" policy measures all programs exec'd, files 2378 mmap'd for exec, and all files opened with the read 2379 mode bit set by either the effective uid (euid=0) or 2380 uid=0. 2381 2382 The "appraise_tcb" policy appraises the integrity of 2383 all files owned by root. 2384 2385 The "secure_boot" policy appraises the integrity 2386 of files (eg. kexec kernel image, kernel modules, 2387 firmware, policy, etc) based on file signatures. 2388 2389 The "fail_securely" policy forces file signature 2390 verification failure also on privileged mounted 2391 filesystems with the SB_I_UNVERIFIABLE_SIGNATURE 2392 flag. 2393 2394 The "critical_data" policy measures kernel integrity 2395 critical data. 2396 2397 ima_tcb [IMA] Deprecated. Use ima_policy= instead. 2398 Load a policy which meets the needs of the Trusted 2399 Computing Base. This means IMA will measure all 2400 programs exec'd, files mmap'd for exec, and all files 2401 opened for read by uid=0. 2402 2403 ima_template= [IMA] 2404 Select one of defined IMA measurements template formats. 2405 Formats: { "ima" | "ima-ng" | "ima-ngv2" | "ima-sig" | 2406 "ima-sigv2" } 2407 Default: "ima-ng" 2408 2409 ima_template_fmt= 2410 [IMA] Define a custom template format. 2411 Format: { "field1|...|fieldN" } 2412 2413 ima.ahash_minsize= [IMA] Minimum file size for asynchronous hash usage 2414 Format: <min_file_size> 2415 Set the minimal file size for using asynchronous hash. 2416 If left unspecified, ahash usage is disabled. 2417 2418 ahash performance varies for different data sizes on 2419 different crypto accelerators. This option can be used 2420 to achieve the best performance for a particular HW. 2421 2422 ima.ahash_bufsize= [IMA] Asynchronous hash buffer size 2423 Format: <bufsize> 2424 Set hashing buffer size. Default: 4k. 2425 2426 ahash performance varies for different chunk sizes on 2427 different crypto accelerators. This option can be used 2428 to achieve best performance for particular HW. 2429 2430 ima= [IMA] Enable or disable IMA 2431 Format: { "off" | "on" } 2432 Default: "on" 2433 Note that disabling IMA is limited to kdump kernel. 2434 2435 indirect_target_selection= [X86,Intel] Mitigation control for Indirect 2436 Target Selection(ITS) bug in Intel CPUs. Updated 2437 microcode is also required for a fix in IBPB. 2438 2439 on: Enable mitigation (default). 2440 off: Disable mitigation. 2441 force: Force the ITS bug and deploy default 2442 mitigation. 2443 vmexit: Only deploy mitigation if CPU is affected by 2444 guest/host isolation part of ITS. 2445 stuff: Deploy RSB-fill mitigation when retpoline is 2446 also deployed. Otherwise, deploy the default 2447 mitigation. 2448 2449 For details see: 2450 Documentation/admin-guide/hw-vuln/indirect-target-selection.rst 2451 2452 init= [KNL] 2453 Format: <full_path> 2454 Run specified binary instead of /sbin/init as init 2455 process. 2456 2457 initcall_debug [KNL] Trace initcalls as they are executed. Useful 2458 for working out where the kernel is dying during 2459 startup. 2460 2461 initcall_blacklist= [KNL] Do not execute a comma-separated list of 2462 initcall functions. Useful for debugging built-in 2463 modules and initcalls. 2464 2465 initramfs_async= [KNL] 2466 Format: <bool> 2467 Default: 1 2468 This parameter controls whether the initramfs 2469 image is unpacked asynchronously, concurrently 2470 with devices being probed and 2471 initialized. This should normally just work, 2472 but as a debugging aid, one can get the 2473 historical behaviour of the initramfs 2474 unpacking being completed before device_ and 2475 late_ initcalls. 2476 2477 initrd= [BOOT,EARLY] Specify the location of the initial ramdisk 2478 2479 initrdmem= [KNL,EARLY] Specify a physical address and size from which to 2480 load the initrd. If an initrd is compiled in or 2481 specified in the bootparams, it takes priority over this 2482 setting. 2483 Format: ss[KMG],nn[KMG] 2484 Default is 0, 0 2485 2486 init_on_alloc= [MM,EARLY] Fill newly allocated pages and heap objects with 2487 zeroes. 2488 Format: 0 | 1 2489 Default set by CONFIG_INIT_ON_ALLOC_DEFAULT_ON. 2490 2491 init_on_free= [MM,EARLY] Fill freed pages and heap objects with zeroes. 2492 Format: 0 | 1 2493 Default set by CONFIG_INIT_ON_FREE_DEFAULT_ON. 2494 2495 init_pkru= [X86] Specify the default memory protection keys rights 2496 register contents for all processes. 0x55555554 by 2497 default (disallow access to all but pkey 0). Can 2498 override in debugfs after boot. 2499 2500 inport.irq= [HW] Inport (ATI XL and Microsoft) busmouse driver 2501 Format: <irq> 2502 2503 int_pln_enable [X86] Enable power limit notification interrupt 2504 2505 integrity_audit=[IMA] 2506 Format: { "0" | "1" } 2507 0 -- basic integrity auditing messages. (Default) 2508 1 -- additional integrity auditing messages. 2509 2510 intel_iommu= [DMAR] Intel IOMMU driver (DMAR) option 2511 on 2512 Enable intel iommu driver. 2513 off 2514 Disable intel iommu driver. 2515 igfx_off [Default Off] 2516 By default, gfx is mapped as normal device. If a gfx 2517 device has a dedicated DMAR unit, the DMAR unit is 2518 bypassed by not enabling DMAR with this option. In 2519 this case, gfx device will use physical address for 2520 DMA. 2521 strict [Default Off] 2522 Deprecated, equivalent to iommu.strict=1. 2523 sp_off [Default Off] 2524 By default, super page will be supported if Intel IOMMU 2525 has the capability. With this option, super page will 2526 not be supported. 2527 sm_on 2528 Enable the Intel IOMMU scalable mode if the hardware 2529 advertises that it has support for the scalable mode 2530 translation. 2531 sm_off 2532 Disallow use of the Intel IOMMU scalable mode. 2533 tboot_noforce [Default Off] 2534 Do not force the Intel IOMMU enabled under tboot. 2535 By default, tboot will force Intel IOMMU on, which 2536 could harm performance of some high-throughput 2537 devices like 40GBit network cards, even if identity 2538 mapping is enabled. 2539 Note that using this option lowers the security 2540 provided by tboot because it makes the system 2541 vulnerable to DMA attacks. 2542 2543 intel_idle.max_cstate= [KNL,HW,ACPI,X86] 2544 0 disables intel_idle and fall back on acpi_idle. 2545 1 to 9 specify maximum depth of C-state. 2546 2547 intel_pstate= [X86,EARLY] 2548 disable 2549 Do not enable intel_pstate as the default 2550 scaling driver for the supported processors 2551 active 2552 Use intel_pstate driver to bypass the scaling 2553 governors layer of cpufreq and provides it own 2554 algorithms for p-state selection. There are two 2555 P-state selection algorithms provided by 2556 intel_pstate in the active mode: powersave and 2557 performance. The way they both operate depends 2558 on whether or not the hardware managed P-states 2559 (HWP) feature has been enabled in the processor 2560 and possibly on the processor model. 2561 passive 2562 Use intel_pstate as a scaling driver, but configure it 2563 to work with generic cpufreq governors (instead of 2564 enabling its internal governor). This mode cannot be 2565 used along with the hardware-managed P-states (HWP) 2566 feature. 2567 force 2568 Enable intel_pstate on systems that prohibit it by default 2569 in favor of acpi-cpufreq. Forcing the intel_pstate driver 2570 instead of acpi-cpufreq may disable platform features, such 2571 as thermal controls and power capping, that rely on ACPI 2572 P-States information being indicated to OSPM and therefore 2573 should be used with caution. This option does not work with 2574 processors that aren't supported by the intel_pstate driver 2575 or on platforms that use pcc-cpufreq instead of acpi-cpufreq. 2576 no_hwp 2577 Do not enable hardware P state control (HWP) 2578 if available. 2579 hwp_only 2580 Only load intel_pstate on systems which support 2581 hardware P state control (HWP) if available. 2582 support_acpi_ppc 2583 Enforce ACPI _PPC performance limits. If the Fixed ACPI 2584 Description Table, specifies preferred power management 2585 profile as "Enterprise Server" or "Performance Server", 2586 then this feature is turned on by default. 2587 per_cpu_perf_limits 2588 Allow per-logical-CPU P-State performance control limits using 2589 cpufreq sysfs interface 2590 no_cas 2591 Do not enable capacity-aware scheduling (CAS) on 2592 hybrid systems 2593 2594 intremap= [X86-64,Intel-IOMMU,EARLY] 2595 on enable Interrupt Remapping (default) 2596 off disable Interrupt Remapping 2597 nosid disable Source ID checking 2598 no_x2apic_optout 2599 BIOS x2APIC opt-out request will be ignored 2600 nopost disable Interrupt Posting 2601 posted_msi 2602 enable MSIs delivered as posted interrupts 2603 2604 iomem= Disable strict checking of access to MMIO memory 2605 strict regions from userspace. 2606 relaxed 2607 2608 iommu= [X86,EARLY] 2609 2610 off 2611 Don't initialize and use any kind of IOMMU. 2612 2613 force 2614 Force the use of the hardware IOMMU even when 2615 it is not actually needed (e.g. because < 3 GB 2616 memory). 2617 2618 noforce 2619 Don't force hardware IOMMU usage when it is not 2620 needed. (default). 2621 2622 biomerge 2623 panic 2624 nopanic 2625 merge 2626 nomerge 2627 2628 soft 2629 Use software bounce buffering (SWIOTLB) (default for 2630 Intel machines). This can be used to prevent the usage 2631 of an available hardware IOMMU. 2632 2633 pt 2634 nopt 2635 nobypass [PPC/POWERNV] 2636 Disable IOMMU bypass, using IOMMU for PCI devices. 2637 2638 AMD Gart HW IOMMU-specific options: 2639 2640 <size> 2641 Set the size of the remapping area in bytes. 2642 2643 allowed 2644 Overwrite iommu off workarounds for specific chipsets 2645 2646 fullflush 2647 Flush IOMMU on each allocation (default). 2648 2649 nofullflush 2650 Don't use IOMMU fullflush. 2651 2652 memaper[=<order>] 2653 Allocate an own aperture over RAM with size 2654 32MB<<order. (default: order=1, i.e. 64MB) 2655 2656 merge 2657 Do scatter-gather (SG) merging. Implies "force" 2658 (experimental). 2659 2660 nomerge 2661 Don't do scatter-gather (SG) merging. 2662 2663 noaperture 2664 Ask the IOMMU not to touch the aperture for AGP. 2665 2666 noagp 2667 Don't initialize the AGP driver and use full aperture. 2668 2669 panic 2670 Always panic when IOMMU overflows. 2671 2672 iommu.forcedac= [ARM64,X86,EARLY] Control IOVA allocation for PCI devices. 2673 Format: { "0" | "1" } 2674 0 - Try to allocate a 32-bit DMA address first, before 2675 falling back to the full range if needed. 2676 1 - Allocate directly from the full usable range, 2677 forcing Dual Address Cycle for PCI cards supporting 2678 greater than 32-bit addressing. 2679 2680 iommu.strict= [ARM64,X86,S390,EARLY] Configure TLB invalidation behaviour 2681 Format: { "0" | "1" } 2682 0 - Lazy mode. 2683 Request that DMA unmap operations use deferred 2684 invalidation of hardware TLBs, for increased 2685 throughput at the cost of reduced device isolation. 2686 Will fall back to strict mode if not supported by 2687 the relevant IOMMU driver. 2688 1 - Strict mode. 2689 DMA unmap operations invalidate IOMMU hardware TLBs 2690 synchronously. 2691 unset - Use value of CONFIG_IOMMU_DEFAULT_DMA_{LAZY,STRICT}. 2692 Note: on x86, strict mode specified via one of the 2693 legacy driver-specific options takes precedence. 2694 2695 iommu.passthrough= 2696 [ARM64,X86,EARLY] Configure DMA to bypass the IOMMU by default. 2697 Format: { "0" | "1" } 2698 0 - Use IOMMU translation for DMA. 2699 1 - Bypass the IOMMU for DMA. 2700 unset - Use value of CONFIG_IOMMU_DEFAULT_PASSTHROUGH. 2701 2702 iommu.debug_pagealloc= 2703 [KNL,EARLY] When CONFIG_IOMMU_DEBUG_PAGEALLOC is set, this 2704 parameter enables the feature at boot time. By default, it 2705 is disabled and the system behaves the same way as a kernel 2706 built without CONFIG_IOMMU_DEBUG_PAGEALLOC. 2707 Format: { "0" | "1" } 2708 0 - Sanitizer disabled. 2709 1 - Sanitizer enabled, expect runtime overhead. 2710 2711 io7= [HW] IO7 for Marvel-based Alpha systems 2712 See comment before marvel_specify_io7 in 2713 arch/alpha/kernel/core_marvel.c. 2714 2715 io_delay= [X86,EARLY] I/O delay method 2716 0x80 2717 Standard port 0x80 based delay 2718 0xed 2719 Alternate port 0xed based delay (needed on some systems) 2720 udelay 2721 Simple two microseconds delay 2722 none 2723 No delay 2724 2725 ip= [IP_PNP] 2726 See Documentation/admin-guide/nfs/nfsroot.rst. 2727 2728 ipcmni_extend [KNL,EARLY] Extend the maximum number of unique System V 2729 IPC identifiers from 32,768 to 16,777,216. 2730 2731 ipe.enforce= [IPE] 2732 Format: <bool> 2733 Determine whether IPE starts in permissive (0) or 2734 enforce (1) mode. The default is enforce. 2735 2736 ipe.success_audit= 2737 [IPE] 2738 Format: <bool> 2739 Start IPE with success auditing enabled, emitting 2740 an audit event when a binary is allowed. The default 2741 is 0. 2742 2743 irqaffinity= [SMP] Set the default irq affinity mask 2744 The argument is a cpu list, as described above. 2745 2746 irqchip.gicv2_force_probe= 2747 [ARM,ARM64,EARLY] 2748 Format: <bool> 2749 Force the kernel to look for the second 4kB page 2750 of a GICv2 controller even if the memory range 2751 exposed by the device tree is too small. 2752 2753 irqchip.gicv3_nolpi= 2754 [ARM,ARM64,EARLY] 2755 Force the kernel to ignore the availability of 2756 LPIs (and by consequence ITSs). Intended for system 2757 that use the kernel as a bootloader, and thus want 2758 to let secondary kernels in charge of setting up 2759 LPIs. 2760 2761 irqchip.gicv3_pseudo_nmi= [ARM64,EARLY] 2762 Enables support for pseudo-NMIs in the kernel. This 2763 requires the kernel to be built with 2764 CONFIG_ARM64_PSEUDO_NMI. 2765 2766 irqchip.riscv_imsic_noipi 2767 [RISC-V,EARLY] 2768 Force the kernel to not use IMSIC software injected MSIs 2769 as IPIs. Intended for system where IMSIC is trap-n-emulated, 2770 and thus want to reduce MMIO traps when triggering IPIs 2771 to multiple harts. 2772 2773 irqfixup [HW] 2774 When an interrupt is not handled search all handlers 2775 for it. Intended to get systems with badly broken 2776 firmware running. 2777 2778 irqhandler.duration_warn_us= [KNL] 2779 Warn if an IRQ handler exceeds the specified duration 2780 threshold in microseconds. Useful for identifying 2781 long-running IRQs in the system. 2782 2783 irqpoll [HW] 2784 When an interrupt is not handled search all handlers 2785 for it. Also check all handlers each timer 2786 interrupt. Intended to get systems with badly broken 2787 firmware running. 2788 2789 isapnp= [ISAPNP] 2790 Format: <RDP>,<reset>,<pci_scan>,<verbosity> 2791 2792 isolcpus= [KNL,SMP,ISOL] Isolate a given set of CPUs from disturbance. 2793 [Deprecated - use cpusets instead] 2794 Format: [flag-list,]<cpu-list> 2795 2796 Specify one or more CPUs to isolate from disturbances 2797 specified in the flag list (default: domain): 2798 2799 nohz 2800 Disable the tick when a single task runs as well as 2801 disabling other kernel noises like having RCU callbacks 2802 offloaded. This is equivalent to the nohz_full parameter. 2803 2804 A residual 1Hz tick is offloaded to workqueues, which you 2805 need to affine to housekeeping through the global 2806 workqueue's affinity configured via the 2807 /sys/devices/virtual/workqueue/cpumask sysfs file, or 2808 by using the 'domain' flag described below. 2809 2810 NOTE: by default the global workqueue runs on all CPUs, 2811 so to protect individual CPUs the 'cpumask' file has to 2812 be configured manually after bootup. 2813 2814 domain 2815 Isolate from the general SMP balancing and scheduling 2816 algorithms. Note that performing domain isolation this way 2817 is irreversible: it's not possible to bring back a CPU to 2818 the domains once isolated through isolcpus. It's strongly 2819 advised to use cpusets instead to disable scheduler load 2820 balancing through the "cpuset.sched_load_balance" file. 2821 It offers a much more flexible interface where CPUs can 2822 move in and out of an isolated set anytime. 2823 2824 You can move a process onto or off an "isolated" CPU via 2825 the CPU affinity syscalls or cpuset. 2826 <cpu number> begins at 0 and the maximum value is 2827 "number of CPUs in system - 1". 2828 2829 managed_irq 2830 2831 Isolate from being targeted by managed interrupts 2832 which have an interrupt mask containing isolated 2833 CPUs. The affinity of managed interrupts is 2834 handled by the kernel and cannot be changed via 2835 the /proc/irq/* interfaces. 2836 2837 This isolation is best effort and only effective 2838 if the automatically assigned interrupt mask of a 2839 device queue contains isolated and housekeeping 2840 CPUs. If housekeeping CPUs are online then such 2841 interrupts are directed to the housekeeping CPU 2842 so that IO submitted on the housekeeping CPU 2843 cannot disturb the isolated CPU. 2844 2845 If a queue's affinity mask contains only isolated 2846 CPUs then this parameter has no effect on the 2847 interrupt routing decision, though interrupts are 2848 only delivered when tasks running on those 2849 isolated CPUs submit IO. IO submitted on 2850 housekeeping CPUs has no influence on those 2851 queues. 2852 2853 The format of <cpu-list> is described above. 2854 2855 iucv= [HW,NET] 2856 2857 ivrs_ioapic [HW,X86-64] 2858 Provide an override to the IOAPIC-ID<->DEVICE-ID 2859 mapping provided in the IVRS ACPI table. 2860 By default, PCI segment is 0, and can be omitted. 2861 2862 For example, to map IOAPIC-ID decimal 10 to 2863 PCI segment 0x1 and PCI device 00:14.0, 2864 write the parameter as: 2865 ivrs_ioapic=10@0001:00:14.0 2866 2867 Deprecated formats: 2868 * To map IOAPIC-ID decimal 10 to PCI device 00:14.0 2869 write the parameter as: 2870 ivrs_ioapic[10]=00:14.0 2871 * To map IOAPIC-ID decimal 10 to PCI segment 0x1 and 2872 PCI device 00:14.0 write the parameter as: 2873 ivrs_ioapic[10]=0001:00:14.0 2874 2875 ivrs_hpet [HW,X86-64] 2876 Provide an override to the HPET-ID<->DEVICE-ID 2877 mapping provided in the IVRS ACPI table. 2878 By default, PCI segment is 0, and can be omitted. 2879 2880 For example, to map HPET-ID decimal 10 to 2881 PCI segment 0x1 and PCI device 00:14.0, 2882 write the parameter as: 2883 ivrs_hpet=10@0001:00:14.0 2884 2885 Deprecated formats: 2886 * To map HPET-ID decimal 0 to PCI device 00:14.0 2887 write the parameter as: 2888 ivrs_hpet[0]=00:14.0 2889 * To map HPET-ID decimal 10 to PCI segment 0x1 and 2890 PCI device 00:14.0 write the parameter as: 2891 ivrs_ioapic[10]=0001:00:14.0 2892 2893 ivrs_acpihid [HW,X86-64] 2894 Provide an override to the ACPI-HID:UID<->DEVICE-ID 2895 mapping provided in the IVRS ACPI table. 2896 By default, PCI segment is 0, and can be omitted. 2897 2898 For example, to map UART-HID:UID AMD0020:0 to 2899 PCI segment 0x1 and PCI device ID 00:14.5, 2900 write the parameter as: 2901 ivrs_acpihid=AMD0020:0@0001:00:14.5 2902 2903 Deprecated formats: 2904 * To map UART-HID:UID AMD0020:0 to PCI segment is 0, 2905 PCI device ID 00:14.5, write the parameter as: 2906 ivrs_acpihid[00:14.5]=AMD0020:0 2907 * To map UART-HID:UID AMD0020:0 to PCI segment 0x1 and 2908 PCI device ID 00:14.5, write the parameter as: 2909 ivrs_acpihid[0001:00:14.5]=AMD0020:0 2910 2911 js= [HW,JOY] Analog joystick 2912 See Documentation/input/joydev/joystick.rst. 2913 2914 kasan_multi_shot 2915 [KNL] Enforce KASAN (Kernel Address Sanitizer) to print 2916 report on every invalid memory access. Without this 2917 parameter KASAN will print report only for the first 2918 invalid access. 2919 2920 keep_bootcon [KNL,EARLY] 2921 Do not unregister boot console at start. This is only 2922 useful for debugging when something happens in the window 2923 between unregistering the boot console and initializing 2924 the real console. 2925 2926 keepinitrd [HW,ARM] See retain_initrd. 2927 2928 kernelcore= [KNL,X86,PPC,EARLY] 2929 Format: nn[KMGTPE] | nn% | "mirror" 2930 This parameter specifies the amount of memory usable by 2931 the kernel for non-movable allocations. The requested 2932 amount is spread evenly throughout all nodes in the 2933 system as ZONE_NORMAL. The remaining memory is used for 2934 movable memory in its own zone, ZONE_MOVABLE. In the 2935 event, a node is too small to have both ZONE_NORMAL and 2936 ZONE_MOVABLE, kernelcore memory will take priority and 2937 other nodes will have a larger ZONE_MOVABLE. 2938 2939 ZONE_MOVABLE is used for the allocation of pages that 2940 may be reclaimed or moved by the page migration 2941 subsystem. Note that allocations like PTEs-from-HighMem 2942 still use the HighMem zone if it exists, and the Normal 2943 zone if it does not. 2944 2945 It is possible to specify the exact amount of memory in 2946 the form of "nn[KMGTPE]", a percentage of total system 2947 memory in the form of "nn%", or "mirror". If "mirror" 2948 option is specified, mirrored (reliable) memory is used 2949 for non-movable allocations and remaining memory is used 2950 for Movable pages. "nn[KMGTPE]", "nn%", and "mirror" 2951 are exclusive, so you cannot specify multiple forms. 2952 2953 kfence.burst= [MM,KFENCE] The number of additional successive 2954 allocations to be attempted through KFENCE for each 2955 sample interval. 2956 Format: <unsigned integer> 2957 Default: 0 2958 2959 kfence.check_on_panic= 2960 [MM,KFENCE] Whether to check all KFENCE-managed objects' 2961 canaries on panic. 2962 Format: <bool> 2963 Default: false 2964 2965 kfence.deferrable= 2966 [MM,KFENCE] Whether to use a deferrable timer to trigger 2967 allocations. This avoids forcing CPU wake-ups if the 2968 system is idle, at the risk of a less predictable 2969 sample interval. 2970 Format: <bool> 2971 Default: CONFIG_KFENCE_DEFERRABLE 2972 2973 kfence.sample_interval= 2974 [MM,KFENCE] KFENCE's sample interval in milliseconds. 2975 Format: <unsigned integer> 2976 0 - Disable KFENCE. 2977 >0 - Enabled KFENCE with given sample interval. 2978 Default: CONFIG_KFENCE_SAMPLE_INTERVAL 2979 2980 kfence.skip_covered_thresh= 2981 [MM,KFENCE] If pool utilization reaches this threshold 2982 (pool usage%), KFENCE limits currently covered 2983 allocations of the same source from further filling 2984 up the pool. 2985 Format: <unsigned integer> 2986 Default: 75 2987 2988 kgdbdbgp= [KGDB,HW,EARLY] kgdb over EHCI usb debug port. 2989 Format: <Controller#>[,poll interval] 2990 The controller # is the number of the ehci usb debug 2991 port as it is probed via PCI. The poll interval is 2992 optional and is the number seconds in between 2993 each poll cycle to the debug port in case you need 2994 the functionality for interrupting the kernel with 2995 gdb or control-c on the dbgp connection. When 2996 not using this parameter you use sysrq-g to break into 2997 the kernel debugger. 2998 2999 kgdboc= [KGDB,HW] kgdb over consoles. 3000 Requires a tty driver that supports console polling, 3001 or a supported polling keyboard driver (non-usb). 3002 Serial only format: <serial_device>[,baud] 3003 keyboard only format: kbd 3004 keyboard and serial format: kbd,<serial_device>[,baud] 3005 Optional Kernel mode setting: 3006 kms, kbd format: kms,kbd 3007 kms, kbd and serial format: kms,kbd,<ser_dev>[,baud] 3008 3009 kgdboc_earlycon= [KGDB,HW,EARLY] 3010 If the boot console provides the ability to read 3011 characters and can work in polling mode, you can use 3012 this parameter to tell kgdb to use it as a backend 3013 until the normal console is registered. Intended to 3014 be used together with the kgdboc parameter which 3015 specifies the normal console to transition to. 3016 3017 The name of the early console should be specified 3018 as the value of this parameter. Note that the name of 3019 the early console might be different than the tty 3020 name passed to kgdboc. It's OK to leave the value 3021 blank and the first boot console that implements 3022 read() will be picked. 3023 3024 kgdbwait [KGDB,EARLY] Stop kernel execution and enter the 3025 kernel debugger at the earliest opportunity. 3026 3027 kho= [KEXEC,EARLY] 3028 Format: { "0" | "1" | "off" | "on" | "y" | "n" } 3029 Enables or disables Kexec HandOver. 3030 "0" | "off" | "n" - kexec handover is disabled 3031 "1" | "on" | "y" - kexec handover is enabled 3032 3033 kho_scratch= [KEXEC,EARLY] 3034 Format: ll[KMG],mm[KMG],nn[KMG] | nn% 3035 Defines the size of the KHO scratch region. The KHO 3036 scratch regions are physically contiguous memory 3037 ranges that can only be used for non-kernel 3038 allocations. That way, even when memory is heavily 3039 fragmented with handed over memory, the kexeced 3040 kernel will always have enough contiguous ranges to 3041 bootstrap itself. 3042 3043 It is possible to specify the exact amount of 3044 memory in the form of "ll[KMG],mm[KMG],nn[KMG]" 3045 where the first parameter defines the size of a low 3046 memory scratch area, the second parameter defines 3047 the size of a global scratch area and the third 3048 parameter defines the size of additional per-node 3049 scratch areas. The form "nn%" defines scale factor 3050 (in percents) of memory that was used during boot. 3051 3052 kmac= [MIPS] Korina ethernet MAC address. 3053 Configure the RouterBoard 532 series on-chip 3054 Ethernet adapter MAC address. 3055 3056 kmemleak= [KNL,EARLY] Boot-time kmemleak enable/disable 3057 Valid arguments: on, off 3058 Default: on 3059 Built with CONFIG_DEBUG_KMEMLEAK_DEFAULT_OFF=y, 3060 the default is off. 3061 3062 kprobe_event=[probe-list] 3063 [FTRACE] Add kprobe events and enable at boot time. 3064 The probe-list is a semicolon delimited list of probe 3065 definitions. Each definition is same as kprobe_events 3066 interface, but the parameters are comma delimited. 3067 For example, to add a kprobe event on vfs_read with 3068 arg1 and arg2, add to the command line; 3069 3070 kprobe_event=p,vfs_read,$arg1,$arg2 3071 3072 See also Documentation/trace/kprobetrace.rst "Kernel 3073 Boot Parameter" section. 3074 3075 kpti= [ARM64,EARLY] Control page table isolation of 3076 user and kernel address spaces. 3077 Default: enabled on cores which need mitigation. 3078 0: force disabled 3079 1: force enabled 3080 3081 kunit.enable= [KUNIT] Enable executing KUnit tests. Requires 3082 CONFIG_KUNIT to be set to be fully enabled. The 3083 default value can be overridden via 3084 KUNIT_DEFAULT_ENABLED. 3085 Default is 1 (enabled) 3086 3087 kvm.ignore_msrs=[KVM] Ignore guest accesses to unhandled MSRs. 3088 Default is 0 (don't ignore, but inject #GP) 3089 3090 kvm.eager_page_split= 3091 [KVM,X86] Controls whether or not KVM will try to 3092 proactively split all huge pages during dirty logging. 3093 Eager page splitting reduces interruptions to vCPU 3094 execution by eliminating the write-protection faults 3095 and MMU lock contention that would otherwise be 3096 required to split huge pages lazily. 3097 3098 VM workloads that rarely perform writes or that write 3099 only to a small region of VM memory may benefit from 3100 disabling eager page splitting to allow huge pages to 3101 still be used for reads. 3102 3103 The behavior of eager page splitting depends on whether 3104 KVM_DIRTY_LOG_INITIALLY_SET is enabled or disabled. If 3105 disabled, all huge pages in a memslot will be eagerly 3106 split when dirty logging is enabled on that memslot. If 3107 enabled, eager page splitting will be performed during 3108 the KVM_CLEAR_DIRTY ioctl, and only for the pages being 3109 cleared. 3110 3111 Eager page splitting is only supported when kvm.tdp_mmu=Y. 3112 3113 Default is Y (on). 3114 3115 kvm.enable_pmu=[KVM,X86] 3116 If enabled, KVM will virtualize PMU functionality based 3117 on the virtual CPU model defined by userspace. This 3118 can be overridden on a per-VM basis via 3119 KVM_CAP_PMU_CAPABILITY. 3120 3121 If disabled, KVM will not virtualize PMU functionality, 3122 e.g. MSRs, PMCs, PMIs, etc., even if userspace defines 3123 a virtual CPU model that contains PMU assets. 3124 3125 Note, KVM's vPMU support implicitly requires running 3126 with an in-kernel local APIC, e.g. to deliver PMIs to 3127 the guest. Running without an in-kernel local APIC is 3128 not supported, though KVM will allow such a combination 3129 (with severely degraded functionality). 3130 3131 See also enable_mediated_pmu. 3132 3133 Default is Y (on). 3134 3135 kvm.enable_virt_at_load=[KVM,ARM64,LOONGARCH,MIPS,RISCV,X86] 3136 If enabled, KVM will enable virtualization in hardware 3137 when KVM is loaded, and disable virtualization when KVM 3138 is unloaded (if KVM is built as a module). 3139 3140 If disabled, KVM will dynamically enable and disable 3141 virtualization on-demand when creating and destroying 3142 VMs, i.e. on the 0=>1 and 1=>0 transitions of the 3143 number of VMs. 3144 3145 Enabling virtualization at module load avoids potential 3146 latency for creation of the 0=>1 VM, as KVM serializes 3147 virtualization enabling across all online CPUs. The 3148 "cost" of enabling virtualization when KVM is loaded, 3149 is that doing so may interfere with using out-of-tree 3150 hypervisors that want to "own" virtualization hardware. 3151 3152 kvm.enable_vmware_backdoor=[KVM] Support VMware backdoor PV interface. 3153 Default is false (don't support). 3154 3155 kvm.nx_huge_pages= 3156 [KVM] Controls the software workaround for the 3157 X86_BUG_ITLB_MULTIHIT bug. 3158 force : Always deploy workaround. 3159 off : Never deploy workaround. 3160 auto : Deploy workaround based on the presence of 3161 X86_BUG_ITLB_MULTIHIT. 3162 3163 Default is 'auto'. 3164 3165 If the software workaround is enabled for the host, 3166 guests do need not to enable it for nested guests. 3167 3168 kvm.nx_huge_pages_recovery_ratio= 3169 [KVM] Controls how many 4KiB pages are periodically zapped 3170 back to huge pages. 0 disables the recovery, otherwise if 3171 the value is N KVM will zap 1/Nth of the 4KiB pages every 3172 period (see below). The default is 60. 3173 3174 kvm.nx_huge_pages_recovery_period_ms= 3175 [KVM] Controls the time period at which KVM zaps 4KiB pages 3176 back to huge pages. If the value is a non-zero N, KVM will 3177 zap a portion (see ratio above) of the pages every N msecs. 3178 If the value is 0 (the default), KVM will pick a period based 3179 on the ratio, such that a page is zapped after 1 hour on average. 3180 3181 kvm-{amd,intel}.enable_mediated_pmu=[KVM,AMD,INTEL] 3182 If enabled, KVM will provide a mediated virtual PMU, 3183 instead of the default perf-based virtual PMU (if 3184 kvm.enable_pmu is true and PMU is enumerated via the 3185 virtual CPU model). 3186 3187 With a perf-based vPMU, KVM operates as a user of perf, 3188 i.e. emulates guest PMU counters using perf events. 3189 KVM-created perf events are managed by perf as regular 3190 (guest-only) events, e.g. are scheduled in/out, contend 3191 for hardware resources, etc. Using a perf-based vPMU 3192 allows guest and host usage of the PMU to co-exist, but 3193 incurs non-trivial overhead and can result in silently 3194 dropped guest events (due to resource contention). 3195 3196 With a mediated vPMU, hardware PMU state is context 3197 switched around the world switch to/from the guest. 3198 KVM mediates which events the guest can utilize, but 3199 gives the guest direct access to all other PMU assets 3200 when possible (KVM may intercept some accesses if the 3201 virtual CPU model provides a subset of hardware PMU 3202 functionality). Using a mediated vPMU significantly 3203 reduces PMU virtualization overhead and eliminates lost 3204 guest events, but is mutually exclusive with using perf 3205 to profile KVM guests and adds latency to most VM-Exits 3206 (to context switch PMU state). 3207 3208 Default is N (off). 3209 3210 kvm-amd.nested= [KVM,AMD] Control nested virtualization feature in 3211 KVM/SVM. Default is 1 (enabled). 3212 3213 kvm-amd.npt= [KVM,AMD] Control KVM's use of Nested Page Tables, 3214 a.k.a. Two-Dimensional Page Tables. Default is 1 3215 (enabled). Disable by KVM if hardware lacks support 3216 for NPT. 3217 3218 kvm-amd.ciphertext_hiding_asids= 3219 [KVM,AMD] Ciphertext hiding prevents disallowed accesses 3220 to SNP private memory from reading ciphertext. Instead, 3221 reads will see constant default values (0xff). 3222 3223 If ciphertext hiding is enabled, the joint SEV-ES and 3224 SEV-SNP ASID space is partitioned into separate SEV-ES 3225 and SEV-SNP ASID ranges, with the SEV-SNP range being 3226 [1..max_snp_asid] and the SEV-ES range being 3227 (max_snp_asid..min_sev_asid), where min_sev_asid is 3228 enumerated by CPUID.0x.8000_001F[EDX]. 3229 3230 A non-zero value enables SEV-SNP ciphertext hiding and 3231 adjusts the ASID ranges for SEV-ES and SEV-SNP guests. 3232 KVM caps the number of SEV-SNP ASIDs at the maximum 3233 possible value, e.g. specifying -1u will assign all 3234 joint SEV-ES and SEV-SNP ASIDs to SEV-SNP. Note, 3235 assigning all joint ASIDs to SEV-SNP, i.e. configuring 3236 max_snp_asid == min_sev_asid-1, will effectively make 3237 SEV-ES unusable. 3238 3239 kvm-arm.mode= 3240 [KVM,ARM,EARLY] Select one of KVM/arm64's modes of 3241 operation. 3242 3243 none: Forcefully disable KVM. 3244 3245 nvhe: Standard nVHE-based mode, without support for 3246 protected guests. 3247 3248 protected: Mode with support for guests whose state is 3249 kept private from the host, using VHE or 3250 nVHE depending on HW support. 3251 3252 nested: VHE-based mode with support for nested 3253 virtualization. Requires at least ARMv8.4 3254 hardware (with FEAT_NV2). 3255 3256 Defaults to VHE/nVHE based on hardware support. Setting 3257 mode to "protected" will disable kexec and hibernation 3258 for the host. To force nVHE on VHE hardware, add 3259 "arm64_sw.hvhe=0 id_aa64mmfr1.vh=0" to the 3260 command-line. 3261 "nested" is experimental and should be used with 3262 extreme caution. 3263 3264 kvm-arm.vgic_v3_group0_trap= 3265 [KVM,ARM,EARLY] Trap guest accesses to GICv3 group-0 3266 system registers 3267 3268 kvm-arm.vgic_v3_group1_trap= 3269 [KVM,ARM,EARLY] Trap guest accesses to GICv3 group-1 3270 system registers 3271 3272 kvm-arm.vgic_v3_common_trap= 3273 [KVM,ARM,EARLY] Trap guest accesses to GICv3 common 3274 system registers 3275 3276 kvm-arm.vgic_v4_enable= 3277 [KVM,ARM,EARLY] Allow use of GICv4 for direct 3278 injection of LPIs. 3279 3280 kvm-arm.wfe_trap_policy= 3281 [KVM,ARM] Control when to set WFE instruction trap for 3282 KVM VMs. Traps are allowed but not guaranteed by the 3283 CPU architecture. 3284 3285 trap: set WFE instruction trap 3286 3287 notrap: clear WFE instruction trap 3288 3289 kvm-arm.wfi_trap_policy= 3290 [KVM,ARM] Control when to set WFI instruction trap for 3291 KVM VMs. Traps are allowed but not guaranteed by the 3292 CPU architecture. 3293 3294 trap: set WFI instruction trap 3295 3296 notrap: clear WFI instruction trap 3297 3298 kvm_cma_resv_ratio=n [PPC,EARLY] 3299 Reserves given percentage from system memory area for 3300 contiguous memory allocation for KVM hash pagetable 3301 allocation. 3302 By default it reserves 5% of total system memory. 3303 Format: <integer> 3304 Default: 5 3305 3306 kvm-intel.ept= [KVM,Intel] Control KVM's use of Extended Page Tables, 3307 a.k.a. Two-Dimensional Page Tables. Default is 1 3308 (enabled). Disable by KVM if hardware lacks support 3309 for EPT. 3310 3311 kvm-intel.emulate_invalid_guest_state= 3312 [KVM,Intel] Control whether to emulate invalid guest 3313 state. Ignored if kvm-intel.enable_unrestricted_guest=1, 3314 as guest state is never invalid for unrestricted 3315 guests. This param doesn't apply to nested guests (L2), 3316 as KVM never emulates invalid L2 guest state. 3317 Default is 1 (enabled). 3318 3319 kvm-intel.flexpriority= 3320 [KVM,Intel] Control KVM's use of FlexPriority feature 3321 (TPR shadow). Default is 1 (enabled). Disable by KVM if 3322 hardware lacks support for it. 3323 3324 kvm-intel.nested= 3325 [KVM,Intel] Control nested virtualization feature in 3326 KVM/VMX. Default is 1 (enabled). 3327 3328 kvm-intel.unrestricted_guest= 3329 [KVM,Intel] Control KVM's use of unrestricted guest 3330 feature (virtualized real and unpaged mode). Default 3331 is 1 (enabled). Disable by KVM if EPT is disabled or 3332 hardware lacks support for it. 3333 3334 kvm-intel.vmentry_l1d_flush=[KVM,Intel] Mitigation for L1 Terminal Fault 3335 CVE-2018-3620. 3336 3337 Valid arguments: never, cond, always 3338 3339 always: L1D cache flush on every VMENTER. 3340 cond: Flush L1D on VMENTER only when the code between 3341 VMEXIT and VMENTER can leak host memory. 3342 never: Disables the mitigation 3343 3344 Default is cond (do L1 cache flush in specific instances) 3345 3346 kvm-intel.vpid= [KVM,Intel] Control KVM's use of Virtual Processor 3347 Identification feature (tagged TLBs). Default is 1 3348 (enabled). Disable by KVM if hardware lacks support 3349 for it. 3350 3351 l1d_flush= [X86,INTEL,EARLY] 3352 Control mitigation for L1D based snooping vulnerability. 3353 3354 Certain CPUs are vulnerable to an exploit against CPU 3355 internal buffers which can forward information to a 3356 disclosure gadget under certain conditions. 3357 3358 In vulnerable processors, the speculatively 3359 forwarded data can be used in a cache side channel 3360 attack, to access data to which the attacker does 3361 not have direct access. 3362 3363 This parameter controls the mitigation. The 3364 options are: 3365 3366 on - enable the interface for the mitigation 3367 3368 l1tf= [X86,EARLY] Control mitigation of the L1TF vulnerability on 3369 affected CPUs 3370 3371 The kernel PTE inversion protection is unconditionally 3372 enabled and cannot be disabled. 3373 3374 full 3375 Provides all available mitigations for the 3376 L1TF vulnerability. Disables SMT and 3377 enables all mitigations in the 3378 hypervisors, i.e. unconditional L1D flush. 3379 3380 SMT control and L1D flush control via the 3381 sysfs interface is still possible after 3382 boot. Hypervisors will issue a warning 3383 when the first VM is started in a 3384 potentially insecure configuration, 3385 i.e. SMT enabled or L1D flush disabled. 3386 3387 full,force 3388 Same as 'full', but disables SMT and L1D 3389 flush runtime control. Implies the 3390 'nosmt=force' command line option. 3391 (i.e. sysfs control of SMT is disabled.) 3392 3393 flush 3394 Leaves SMT enabled and enables the default 3395 hypervisor mitigation, i.e. conditional 3396 L1D flush. 3397 3398 SMT control and L1D flush control via the 3399 sysfs interface is still possible after 3400 boot. Hypervisors will issue a warning 3401 when the first VM is started in a 3402 potentially insecure configuration, 3403 i.e. SMT enabled or L1D flush disabled. 3404 3405 flush,nosmt 3406 3407 Disables SMT and enables the default 3408 hypervisor mitigation. 3409 3410 SMT control and L1D flush control via the 3411 sysfs interface is still possible after 3412 boot. Hypervisors will issue a warning 3413 when the first VM is started in a 3414 potentially insecure configuration, 3415 i.e. SMT enabled or L1D flush disabled. 3416 3417 flush,nowarn 3418 Same as 'flush', but hypervisors will not 3419 warn when a VM is started in a potentially 3420 insecure configuration. 3421 3422 off 3423 Disables hypervisor mitigations and doesn't 3424 emit any warnings. 3425 It also drops the swap size and available 3426 RAM limit restriction on both hypervisor and 3427 bare metal. 3428 3429 Default is 'flush'. 3430 3431 For details see: Documentation/admin-guide/hw-vuln/l1tf.rst 3432 3433 l2cr= [PPC] 3434 3435 l3cr= [PPC] 3436 3437 lapic [X86-32,APIC,EARLY] Enable the local APIC even if BIOS 3438 disabled it. 3439 3440 lapic= [X86,APIC] Do not use TSC deadline 3441 value for LAPIC timer one-shot implementation. Default 3442 back to the programmable timer unit in the LAPIC. 3443 Format: notscdeadline 3444 3445 lapic_timer_c2_ok [X86,APIC,EARLY] trust the local apic timer 3446 in C2 power state. 3447 3448 libata.dma= [LIBATA] DMA control 3449 libata.dma=0 Disable all PATA and SATA DMA 3450 libata.dma=1 PATA and SATA Disk DMA only 3451 libata.dma=2 ATAPI (CDROM) DMA only 3452 libata.dma=4 Compact Flash DMA only 3453 Combinations also work, so libata.dma=3 enables DMA 3454 for disks and CDROMs, but not CFs. 3455 3456 libata.ignore_hpa= [LIBATA] Ignore HPA limit 3457 libata.ignore_hpa=0 keep BIOS limits (default) 3458 libata.ignore_hpa=1 ignore limits, using full disk 3459 3460 libata.noacpi [LIBATA] Disables use of ACPI in libata suspend/resume 3461 when set. 3462 Format: <int> 3463 3464 libata.force= [LIBATA] Force configurations. The format is a comma- 3465 separated list of "[ID:]VAL" where ID is PORT[.DEVICE]. 3466 PORT and DEVICE are decimal numbers matching port, link 3467 or device. Basically, it matches the ATA ID string 3468 printed on console by libata. If the whole ID part is 3469 omitted, the last PORT and DEVICE values are used. If 3470 ID hasn't been specified yet, the configuration applies 3471 to all ports, links and devices. 3472 3473 If only DEVICE is omitted, the parameter applies to 3474 the port and all links and devices behind it. DEVICE 3475 number of 0 either selects the first device or the 3476 first fan-out link behind PMP device. It does not 3477 select the host link. DEVICE number of 15 selects the 3478 host link and device attached to it. 3479 3480 The VAL specifies the configuration to force. As long 3481 as there is no ambiguity, shortcut notation is allowed. 3482 For example, both 1.5 and 1.5G would work for 1.5Gbps. 3483 The following configurations can be forced. 3484 3485 * Cable type: 40c, 80c, short40c, unk, ign or sata. 3486 Any ID with matching PORT is used. 3487 3488 * SATA link speed limit: 1.5Gbps or 3.0Gbps. 3489 3490 * Transfer mode: pio[0-7], mwdma[0-4] and udma[0-7]. 3491 udma[/][16,25,33,44,66,100,133] notation is also 3492 allowed. 3493 3494 * nohrst, nosrst, norst: suppress hard, soft and both 3495 resets. 3496 3497 * rstonce: only attempt one reset during hot-unplug 3498 link recovery. 3499 3500 * [no]dbdelay: Enable or disable the extra 200ms delay 3501 before debouncing a link PHY and device presence 3502 detection. 3503 3504 * [no]ncq: Turn on or off NCQ. 3505 3506 * [no]ncqtrim: Enable or disable queued DSM TRIM. 3507 3508 * [no]ncqati: Enable or disable NCQ trim on ATI chipset. 3509 3510 * [no]trim: Enable or disable (unqueued) TRIM. 3511 3512 * trim_zero: Indicate that TRIM command zeroes data. 3513 3514 * max_trim_128m: Set 128M maximum trim size limit. 3515 3516 * [no]dma: Turn on or off DMA transfers. 3517 3518 * atapi_dmadir: Enable ATAPI DMADIR bridge support. 3519 3520 * atapi_mod16_dma: Enable the use of ATAPI DMA for 3521 commands that are not a multiple of 16 bytes. 3522 3523 * [no]dmalog: Enable or disable the use of the 3524 READ LOG DMA EXT command to access logs. 3525 3526 * [no]iddevlog: Enable or disable access to the 3527 identify device data log. 3528 3529 * [no]logdir: Enable or disable access to the general 3530 purpose log directory. 3531 3532 * max_sec=<sectors>: Set the transfer size limit, in 3533 number of 512-byte sectors, to the value specified in 3534 <sectors>. The value specified in <sectors> has to be 3535 a non-zero positive integer. 3536 3537 * max_sec_128: Set transfer size limit to 128 sectors. 3538 3539 * max_sec_1024: Set or clear transfer size limit to 3540 1024 sectors. 3541 3542 * max_sec_lba48: Set or clear transfer size limit to 3543 65535 sectors. 3544 3545 * external: Mark port as external (hotplug-capable). 3546 3547 * [no]lpm: Enable or disable link power management. 3548 3549 * [no]setxfer: Indicate if transfer speed mode setting 3550 should be skipped. 3551 3552 * [no]fua: Disable or enable FUA (Force Unit Access) 3553 support for devices supporting this feature. 3554 3555 * dump_id: Dump IDENTIFY data. 3556 3557 * disable: Disable this device. 3558 3559 If there are multiple matching configurations changing 3560 the same attribute, the last one is used. 3561 3562 liveupdate= [KNL,EARLY] 3563 Format: <bool> 3564 Enable Live Update Orchestrator (LUO). 3565 Default: off. 3566 3567 lockd.nlm_grace_period=P [NFS] Assign grace period. 3568 Format: <integer> 3569 3570 lockd.nlm_tcpport=N [NFS] Assign TCP port. 3571 Format: <integer> 3572 3573 lockd.nlm_timeout=T [NFS] Assign timeout value. 3574 Format: <integer> 3575 3576 lockd.nlm_udpport=M [NFS] Assign UDP port. 3577 Format: <integer> 3578 3579 lockdown= [SECURITY,EARLY] 3580 { integrity | confidentiality } 3581 Enable the kernel lockdown feature. If set to 3582 integrity, kernel features that allow userland to 3583 modify the running kernel are disabled. If set to 3584 confidentiality, kernel features that allow userland 3585 to extract confidential information from the kernel 3586 are also disabled. 3587 3588 locktorture.acq_writer_lim= [KNL] 3589 Set the time limit in jiffies for a lock 3590 acquisition. Acquisitions exceeding this limit 3591 will result in a splat once they do complete. 3592 3593 locktorture.bind_readers= [KNL] 3594 Specify the list of CPUs to which the readers are 3595 to be bound. 3596 3597 locktorture.bind_writers= [KNL] 3598 Specify the list of CPUs to which the writers are 3599 to be bound. 3600 3601 locktorture.call_rcu_chains= [KNL] 3602 Specify the number of self-propagating call_rcu() 3603 chains to set up. These are used to ensure that 3604 there is a high probability of an RCU grace period 3605 in progress at any given time. Defaults to 0, 3606 which disables these call_rcu() chains. 3607 3608 locktorture.long_hold= [KNL] 3609 Specify the duration in milliseconds for the 3610 occasional long-duration lock hold time. Defaults 3611 to 100 milliseconds. Select 0 to disable. 3612 3613 locktorture.nested_locks= [KNL] 3614 Specify the maximum lock nesting depth that 3615 locktorture is to exercise, up to a limit of 8 3616 (MAX_NESTED_LOCKS). Specify zero to disable. 3617 Note that this parameter is ineffective on types 3618 of locks that do not support nested acquisition. 3619 3620 locktorture.nreaders_stress= [KNL] 3621 Set the number of locking read-acquisition kthreads. 3622 Defaults to being automatically set based on the 3623 number of online CPUs. 3624 3625 locktorture.nwriters_stress= [KNL] 3626 Set the number of locking write-acquisition kthreads. 3627 3628 locktorture.onoff_holdoff= [KNL] 3629 Set time (s) after boot for CPU-hotplug testing. 3630 3631 locktorture.onoff_interval= [KNL] 3632 Set time (s) between CPU-hotplug operations, or 3633 zero to disable CPU-hotplug testing. 3634 3635 locktorture.rt_boost= [KNL] 3636 Do periodic testing of real-time lock priority 3637 boosting. Select 0 to disable, 1 to boost 3638 only rt_mutex, and 2 to boost unconditionally. 3639 Defaults to 2, which might seem to be an 3640 odd choice, but which should be harmless for 3641 non-real-time spinlocks, due to their disabling 3642 of preemption. Note that non-realtime mutexes 3643 disable boosting. 3644 3645 locktorture.rt_boost_factor= [KNL] 3646 Number that determines how often and for how 3647 long priority boosting is exercised. This is 3648 scaled down by the number of writers, so that the 3649 number of boosts per unit time remains roughly 3650 constant as the number of writers increases. 3651 On the other hand, the duration of each boost 3652 increases with the number of writers. 3653 3654 locktorture.shuffle_interval= [KNL] 3655 Set task-shuffle interval (jiffies). Shuffling 3656 tasks allows some CPUs to go into dyntick-idle 3657 mode during the locktorture test. 3658 3659 locktorture.shutdown_secs= [KNL] 3660 Set time (s) after boot system shutdown. This 3661 is useful for hands-off automated testing. 3662 3663 locktorture.stat_interval= [KNL] 3664 Time (s) between statistics printk()s. 3665 3666 locktorture.stutter= [KNL] 3667 Time (s) to stutter testing, for example, 3668 specifying five seconds causes the test to run for 3669 five seconds, wait for five seconds, and so on. 3670 This tests the locking primitive's ability to 3671 transition abruptly to and from idle. 3672 3673 locktorture.torture_type= [KNL] 3674 Specify the locking implementation to test. 3675 3676 locktorture.verbose= [KNL] 3677 Enable additional printk() statements. 3678 3679 locktorture.writer_fifo= [KNL] 3680 Run the write-side locktorture kthreads at 3681 sched_set_fifo() real-time priority. 3682 3683 logibm.irq= [HW,MOUSE] Logitech Bus Mouse Driver 3684 Format: <irq> 3685 3686 loglevel= [KNL,EARLY] 3687 All Kernel Messages with a loglevel smaller than the 3688 console loglevel will be printed to the console. It can 3689 also be changed with klogd or other programs. The 3690 loglevels are defined as follows: 3691 3692 0 (KERN_EMERG) system is unusable 3693 1 (KERN_ALERT) action must be taken immediately 3694 2 (KERN_CRIT) critical conditions 3695 3 (KERN_ERR) error conditions 3696 4 (KERN_WARNING) warning conditions 3697 5 (KERN_NOTICE) normal but significant condition 3698 6 (KERN_INFO) informational 3699 7 (KERN_DEBUG) debug-level messages 3700 3701 log_buf_len=n[KMG] [KNL,EARLY] 3702 Sets the size of the printk ring buffer, in bytes. 3703 n must be a power of two and greater than the 3704 minimal size. The minimal size is defined by 3705 LOG_BUF_SHIFT kernel config parameter. There 3706 is also CONFIG_LOG_CPU_MAX_BUF_SHIFT config 3707 parameter that allows to increase the default size 3708 depending on the number of CPUs. See init/Kconfig 3709 for more details. 3710 3711 logo.nologo [FB] Disables display of the built-in Linux logo. 3712 This may be used to provide more screen space for 3713 kernel log messages and is useful when debugging 3714 kernel boot problems. 3715 3716 lp=0 [LP] Specify parallel ports to use, e.g, 3717 lp=port[,port...] lp=none,parport0 (lp0 not configured, lp1 uses 3718 lp=reset first parallel port). 'lp=0' disables the 3719 lp=auto printer driver. 'lp=reset' (which can be 3720 specified in addition to the ports) causes 3721 attached printers to be reset. Using 3722 lp=port1,port2,... specifies the parallel ports 3723 to associate lp devices with, starting with 3724 lp0. A port specification may be 'none' to skip 3725 that lp device, or a parport name such as 3726 'parport0'. Specifying 'lp=auto' instead of a 3727 port specification list means that device IDs 3728 from each port should be examined, to see if 3729 an IEEE 1284-compliant printer is attached; if 3730 so, the driver will manage that printer. 3731 See also header of drivers/char/lp.c. 3732 3733 lpj=n [KNL] 3734 Sets loops_per_jiffy to given constant, thus avoiding 3735 time-consuming boot-time autodetection (up to 250 ms per 3736 CPU). 0 enables autodetection (default). To determine 3737 the correct value for your kernel, boot with normal 3738 autodetection and see what value is printed. Note that 3739 on SMP systems the preset will be applied to all CPUs, 3740 which is likely to cause problems if your CPUs need 3741 significantly divergent settings. An incorrect value 3742 will cause delays in the kernel to be wrong, leading to 3743 unpredictable I/O errors and other breakage. Although 3744 unlikely, in the extreme case this might damage your 3745 hardware. 3746 3747 lsm.debug [SECURITY] Enable LSM initialization debugging output. 3748 3749 lsm=lsm1,...,lsmN 3750 [SECURITY] Choose order of LSM initialization. This 3751 overrides CONFIG_LSM, and the "security=" parameter. 3752 3753 machtype= [Loongson] Share the same kernel image file between 3754 different yeeloong laptops. 3755 Example: machtype=lemote-yeeloong-2f-7inch 3756 3757 maxcpus= [SMP,EARLY] Maximum number of processors that an SMP kernel 3758 will bring up during bootup. maxcpus=n : n >= 0 limits 3759 the kernel to bring up 'n' processors. Surely after 3760 bootup you can bring up the other plugged cpu by executing 3761 "echo 1 > /sys/devices/system/cpu/cpuX/online". So maxcpus 3762 only takes effect during system bootup. 3763 While n=0 is a special case, it is equivalent to "nosmp", 3764 which also disables the IO APIC. 3765 3766 max_loop= [LOOP] The number of loop block devices that get 3767 (loop.max_loop) unconditionally pre-created at init time. The default 3768 number is configured by BLK_DEV_LOOP_MIN_COUNT. Instead 3769 of statically allocating a predefined number, loop 3770 devices can be requested on-demand with the 3771 /dev/loop-control interface. 3772 3773 mce= [X86-{32,64}] 3774 3775 Please see Documentation/arch/x86/x86_64/machinecheck.rst for sysfs runtime tunables. 3776 3777 off 3778 disable machine check 3779 3780 no_cmci 3781 disable CMCI(Corrected Machine Check Interrupt) that 3782 Intel processor supports. Usually this disablement is 3783 not recommended, but it might be handy if your 3784 hardware is misbehaving. 3785 3786 Note that you'll get more problems without CMCI than 3787 with due to the shared banks, i.e. you might get 3788 duplicated error logs. 3789 3790 dont_log_ce 3791 don't make logs for corrected errors. All events 3792 reported as corrected are silently cleared by OS. This 3793 option will be useful if you have no interest in any 3794 of corrected errors. 3795 3796 ignore_ce 3797 disable features for corrected errors, e.g. 3798 polling timer and CMCI. All events reported as 3799 corrected are not cleared by OS and remained in its 3800 error banks. 3801 3802 Usually this disablement is not recommended, however 3803 if there is an agent checking/clearing corrected 3804 errors (e.g. BIOS or hardware monitoring 3805 applications), conflicting with OS's error handling, 3806 and you cannot deactivate the agent, then this option 3807 will be a help. 3808 3809 no_lmce 3810 do not opt-in to Local MCE delivery. Use legacy method 3811 to broadcast MCEs. 3812 3813 bootlog 3814 enable logging of machine checks left over from 3815 booting. Disabled by default on AMD Fam10h and older 3816 because some BIOS leave bogus ones. 3817 3818 If your BIOS doesn't do that it's a good idea to 3819 enable though to make sure you log even machine check 3820 events that result in a reboot. On Intel systems it is 3821 enabled by default. 3822 3823 nobootlog 3824 disable boot machine check logging. 3825 3826 monarchtimeout (number) 3827 sets the time in us to wait for other CPUs on machine 3828 checks. 0 to disable. 3829 3830 bios_cmci_threshold 3831 don't overwrite the bios-set CMCI threshold. This boot 3832 option prevents Linux from overwriting the CMCI 3833 threshold set by the bios. Without this option, Linux 3834 always sets the CMCI threshold to 1. Enabling this may 3835 make memory predictive failure analysis less effective 3836 if the bios sets thresholds for memory errors since we 3837 will not see details for all errors. 3838 3839 recovery 3840 force-enable recoverable machine check code paths 3841 3842 Everything else is in sysfs now. 3843 3844 3845 md= [HW] RAID subsystems devices and level 3846 See Documentation/admin-guide/md.rst. 3847 3848 mdacon= [MDA] 3849 Format: <first>,<last> 3850 Specifies range of consoles to be captured by the MDA. 3851 3852 mds= [X86,INTEL,EARLY] 3853 Control mitigation for the Micro-architectural Data 3854 Sampling (MDS) vulnerability. 3855 3856 Certain CPUs are vulnerable to an exploit against CPU 3857 internal buffers which can forward information to a 3858 disclosure gadget under certain conditions. 3859 3860 In vulnerable processors, the speculatively 3861 forwarded data can be used in a cache side channel 3862 attack, to access data to which the attacker does 3863 not have direct access. 3864 3865 This parameter controls the MDS mitigation. The 3866 options are: 3867 3868 full - Enable MDS mitigation on vulnerable CPUs 3869 full,nosmt - Enable MDS mitigation and disable 3870 SMT on vulnerable CPUs 3871 off - Unconditionally disable MDS mitigation 3872 3873 On TAA-affected machines, mds=off can be prevented by 3874 an active TAA mitigation as both vulnerabilities are 3875 mitigated with the same mechanism so in order to disable 3876 this mitigation, you need to specify tsx_async_abort=off 3877 too. 3878 3879 Not specifying this option is equivalent to 3880 mds=full. 3881 3882 For details see: Documentation/admin-guide/hw-vuln/mds.rst 3883 3884 mem=nn[KMG] [HEXAGON,EARLY] Set the memory size. 3885 Must be specified, otherwise memory size will be 0. 3886 3887 mem=nn[KMG] [KNL,BOOT,EARLY] Force usage of a specific amount 3888 of memory Amount of memory to be used in cases 3889 as follows: 3890 3891 1 for test; 3892 2 when the kernel is not able to see the whole system memory; 3893 3 memory that lies after 'mem=' boundary is excluded from 3894 the hypervisor, then assigned to KVM guests. 3895 4 to limit the memory available for kdump kernel. 3896 3897 [ARC,MICROBLAZE] - the limit applies only to low memory, 3898 high memory is not affected. 3899 3900 [ARM64] - only limits memory covered by the linear 3901 mapping. The NOMAP regions are not affected. 3902 3903 [X86] Work as limiting max address. Use together 3904 with memmap= to avoid physical address space collisions. 3905 Without memmap= PCI devices could be placed at addresses 3906 belonging to unused RAM. 3907 3908 Note that this only takes effects during boot time since 3909 in above case 3, memory may need be hot added after boot 3910 if system memory of hypervisor is not sufficient. 3911 3912 mem=nn[KMG]@ss[KMG] 3913 [ARM,MIPS,EARLY] - override the memory layout 3914 reported by firmware. 3915 Define a memory region of size nn[KMG] starting at 3916 ss[KMG]. 3917 Multiple different regions can be specified with 3918 multiple mem= parameters on the command line. 3919 3920 mem=nopentium [BUGS=X86-32] Disable usage of 4MB pages for kernel 3921 memory. 3922 3923 memblock=debug [KNL,EARLY] Enable memblock debug messages. 3924 3925 memchunk=nn[KMG] 3926 [KNL,SH] Allow user to override the default size for 3927 per-device physically contiguous DMA buffers. 3928 3929 memhp_default_state=online/offline/online_kernel/online_movable 3930 [KNL] Set the initial state for the memory hotplug 3931 onlining policy. If not specified, the default value is 3932 set according to the 3933 CONFIG_MHP_DEFAULT_ONLINE_TYPE kernel config 3934 options. 3935 See Documentation/admin-guide/mm/memory-hotplug.rst. 3936 3937 memmap=exactmap [KNL,X86,EARLY] Enable setting of an exact 3938 E820 memory map, as specified by the user. 3939 Such memmap=exactmap lines can be constructed based on 3940 BIOS output or other requirements. See the memmap=nn@ss 3941 option description. 3942 3943 memmap=nn[KMG]@ss[KMG] 3944 [KNL, X86,MIPS,XTENSA,EARLY] Force usage of a specific region of memory. 3945 Region of memory to be used is from ss to ss+nn. 3946 If @ss[KMG] is omitted, it is equivalent to mem=nn[KMG], 3947 which limits max address to nn[KMG]. 3948 Multiple different regions can be specified, 3949 comma delimited. 3950 Example: 3951 memmap=100M@2G,100M#3G,1G!1024G 3952 3953 memmap=nn[KMG]#ss[KMG] 3954 [KNL,ACPI,EARLY] Mark specific memory as ACPI data. 3955 Region of memory to be marked is from ss to ss+nn. 3956 3957 memmap=nn[KMG]$ss[KMG] 3958 [KNL,ACPI,EARLY] Mark specific memory as reserved. 3959 Region of memory to be reserved is from ss to ss+nn. 3960 Example: Exclude memory from 0x18690000-0x1869ffff 3961 memmap=64K$0x18690000 3962 or 3963 memmap=0x10000$0x18690000 3964 Some bootloaders may need an escape character before '$', 3965 like Grub2, otherwise '$' and the following number 3966 will be eaten. 3967 3968 memmap=nn[KMG]!ss[KMG,EARLY] 3969 [KNL,X86] Mark specific memory as protected. 3970 Region of memory to be used, from ss to ss+nn. 3971 The memory region may be marked as e820 type 12 (0xc) 3972 and is NVDIMM or ADR memory. 3973 3974 memmap=<size>%<offset>-<oldtype>+<newtype> 3975 [KNL,ACPI,EARLY] Convert memory within the specified region 3976 from <oldtype> to <newtype>. If "-<oldtype>" is left 3977 out, the whole region will be marked as <newtype>, 3978 even if previously unavailable. If "+<newtype>" is left 3979 out, matching memory will be removed. Types are 3980 specified as e820 types, e.g., 1 = RAM, 2 = reserved, 3981 3 = ACPI, 12 = PRAM. 3982 3983 memory_corruption_check=0/1 [X86,EARLY] 3984 Some BIOSes seem to corrupt the first 64k of 3985 memory when doing things like suspend/resume. 3986 Setting this option will scan the memory 3987 looking for corruption. Enabling this will 3988 both detect corruption and prevent the kernel 3989 from using the memory being corrupted. 3990 However, it's intended as a diagnostic tool; if 3991 repeatable BIOS-originated corruption always 3992 affects the same memory, you can use memmap= 3993 to prevent the kernel from using that memory. 3994 3995 memory_corruption_check_size=size [X86,EARLY] 3996 By default it checks for corruption in the low 3997 64k, making this memory unavailable for normal 3998 use. Use this parameter to scan for 3999 corruption in more or less memory. 4000 4001 memory_corruption_check_period=seconds [X86,EARLY] 4002 By default it checks for corruption every 60 4003 seconds. Use this parameter to check at some 4004 other rate. 0 disables periodic checking. 4005 4006 memory_hotplug.memmap_on_memory 4007 [KNL,X86,ARM] Boolean flag to enable this feature. 4008 Format: {on | off (default)} 4009 When enabled, runtime hotplugged memory will 4010 allocate its internal metadata (struct pages, 4011 those vmemmap pages cannot be optimized even 4012 if hugetlb_free_vmemmap is enabled) from the 4013 hotadded memory which will allow to hotadd a 4014 lot of memory without requiring additional 4015 memory to do so. 4016 This feature is disabled by default because it 4017 has some implication on large (e.g. GB) 4018 allocations in some configurations (e.g. small 4019 memory blocks). 4020 The state of the flag can be read in 4021 /sys/module/memory_hotplug/parameters/memmap_on_memory. 4022 Note that even when enabled, there are a few cases where 4023 the feature is not effective. 4024 4025 memtest= [KNL,X86,ARM,M68K,PPC,RISCV,EARLY] Enable memtest 4026 Format: <integer> 4027 default : 0 <disable> 4028 Specifies the number of memtest passes to be 4029 performed. Each pass selects another test 4030 pattern from a given set of patterns. Memtest 4031 fills the memory with this pattern, validates 4032 memory contents and reserves bad memory 4033 regions that are detected. 4034 4035 mem_encrypt= [X86-64] AMD Secure Memory Encryption (SME) control 4036 Valid arguments: on, off 4037 Default: off 4038 mem_encrypt=on: Activate SME 4039 mem_encrypt=off: Do not activate SME 4040 4041 Refer to Documentation/virt/kvm/x86/amd-memory-encryption.rst 4042 for details on when memory encryption can be activated. 4043 4044 mem_sleep_default= [SUSPEND] Default system suspend mode: 4045 s2idle - Suspend-To-Idle 4046 shallow - Power-On Suspend or equivalent (if supported) 4047 deep - Suspend-To-RAM or equivalent (if supported) 4048 See Documentation/admin-guide/pm/sleep-states.rst. 4049 4050 mfgptfix [X86-32] Fix MFGPT timers on AMD Geode platforms when 4051 the BIOS has incorrectly applied a workaround. TinyBIOS 4052 version 0.98 is known to be affected, 0.99 fixes the 4053 problem by letting the user disable the workaround. 4054 4055 mga= [HW,DRM] 4056 4057 microcode= [X86] Control the behavior of the microcode loader. 4058 Available options, comma separated: 4059 4060 base_rev=X - with <X> with format: <u32> 4061 Set the base microcode revision of each thread when in 4062 debug mode. 4063 4064 dis_ucode_ldr: disable the microcode loader 4065 4066 force_minrev: 4067 Enable or disable the microcode minimal revision 4068 enforcement for the runtime microcode loader. 4069 4070 mini2440= [ARM,HW,KNL] 4071 Format:[0..2][b][c][t] 4072 Default: "0tb" 4073 MINI2440 configuration specification: 4074 0 - The attached screen is the 3.5" TFT 4075 1 - The attached screen is the 7" TFT 4076 2 - The VGA Shield is attached (1024x768) 4077 Leaving out the screen size parameter will not load 4078 the TFT driver, and the framebuffer will be left 4079 unconfigured. 4080 b - Enable backlight. The TFT backlight pin will be 4081 linked to the kernel VESA blanking code and a GPIO 4082 LED. This parameter is not necessary when using the 4083 VGA shield. 4084 c - Enable the s3c camera interface. 4085 t - Reserved for enabling touchscreen support. The 4086 touchscreen support is not enabled in the mainstream 4087 kernel as of 2.6.30, a preliminary port can be found 4088 in the "bleeding edge" mini2440 support kernel at 4089 https://repo.or.cz/w/linux-2.6/mini2440.git 4090 4091 mitigations= 4092 [X86,PPC,S390,ARM64,EARLY] Control optional mitigations for 4093 CPU vulnerabilities. This is a set of curated, 4094 arch-independent options, each of which is an 4095 aggregation of existing arch-specific options. 4096 4097 Note, "mitigations" is supported if and only if the 4098 kernel was built with CPU_MITIGATIONS=y. 4099 4100 off 4101 Disable all optional CPU mitigations. This 4102 improves system performance, but it may also 4103 expose users to several CPU vulnerabilities. 4104 Equivalent to: if nokaslr then kpti=0 [ARM64] 4105 gather_data_sampling=off [X86] 4106 indirect_target_selection=off [X86] 4107 kvm.nx_huge_pages=off [X86] 4108 l1tf=off [X86] 4109 mds=off [X86] 4110 mmio_stale_data=off [X86] 4111 no_entry_flush [PPC] 4112 no_uaccess_flush [PPC] 4113 nobp=0 [S390] 4114 nopti [X86,PPC] 4115 nospectre_bhb [ARM64] 4116 nospectre_v1 [X86,PPC] 4117 nospectre_v2 [X86,PPC,S390,ARM64] 4118 reg_file_data_sampling=off [X86] 4119 retbleed=off [X86] 4120 spec_rstack_overflow=off [X86] 4121 spec_store_bypass_disable=off [X86,PPC] 4122 spectre_bhi=off [X86] 4123 spectre_v2_user=off [X86] 4124 srbds=off [X86,INTEL] 4125 ssbd=force-off [ARM64] 4126 tsa=off [X86,AMD] 4127 tsx_async_abort=off [X86] 4128 vmscape=off [X86] 4129 4130 Exceptions: 4131 This does not have any effect on 4132 kvm.nx_huge_pages when 4133 kvm.nx_huge_pages=force. 4134 4135 auto (default) 4136 Mitigate all CPU vulnerabilities, but leave SMT 4137 enabled, even if it's vulnerable. This is for 4138 users who don't want to be surprised by SMT 4139 getting disabled across kernel upgrades, or who 4140 have other ways of avoiding SMT-based attacks. 4141 Equivalent to: (default behavior) 4142 4143 auto,nosmt 4144 Mitigate all CPU vulnerabilities, disabling SMT 4145 if needed. This is for users who always want to 4146 be fully mitigated, even if it means losing SMT. 4147 Equivalent to: l1tf=flush,nosmt [X86] 4148 mds=full,nosmt [X86] 4149 tsx_async_abort=full,nosmt [X86] 4150 mmio_stale_data=full,nosmt [X86] 4151 retbleed=auto,nosmt [X86] 4152 4153 [X86] After one of the above options, additionally 4154 supports attack-vector based controls as documented in 4155 Documentation/admin-guide/hw-vuln/attack_vector_controls.rst 4156 4157 mminit_loglevel= 4158 [KNL,EARLY] When CONFIG_DEBUG_MEMORY_INIT is set, this 4159 parameter allows control of the logging verbosity for 4160 the additional memory initialisation checks. A value 4161 of 0 disables mminit logging and a level of 4 will 4162 log everything. Information is printed at KERN_DEBUG 4163 so loglevel=8 may also need to be specified. 4164 4165 mmio_stale_data= 4166 [X86,INTEL,EARLY] Control mitigation for the Processor 4167 MMIO Stale Data vulnerabilities. 4168 4169 Processor MMIO Stale Data is a class of 4170 vulnerabilities that may expose data after an MMIO 4171 operation. Exposed data could originate or end in 4172 the same CPU buffers as affected by MDS and TAA. 4173 Therefore, similar to MDS and TAA, the mitigation 4174 is to clear the affected CPU buffers. 4175 4176 This parameter controls the mitigation. The 4177 options are: 4178 4179 full - Enable mitigation on vulnerable CPUs 4180 4181 full,nosmt - Enable mitigation and disable SMT on 4182 vulnerable CPUs. 4183 4184 off - Unconditionally disable mitigation 4185 4186 On MDS or TAA affected machines, 4187 mmio_stale_data=off can be prevented by an active 4188 MDS or TAA mitigation as these vulnerabilities are 4189 mitigated with the same mechanism so in order to 4190 disable this mitigation, you need to specify 4191 mds=off and tsx_async_abort=off too. 4192 4193 Not specifying this option is equivalent to 4194 mmio_stale_data=full. 4195 4196 For details see: 4197 Documentation/admin-guide/hw-vuln/processor_mmio_stale_data.rst 4198 4199 <module>.async_probe[=<bool>] [KNL] 4200 If no <bool> value is specified or if the value 4201 specified is not a valid <bool>, enable asynchronous 4202 probe on this module. Otherwise, enable/disable 4203 asynchronous probe on this module as indicated by the 4204 <bool> value. See also: module.async_probe 4205 4206 module.async_probe=<bool> 4207 [KNL] When set to true, modules will use async probing 4208 by default. To enable/disable async probing for a 4209 specific module, use the module specific control that 4210 is documented under <module>.async_probe. When both 4211 module.async_probe and <module>.async_probe are 4212 specified, <module>.async_probe takes precedence for 4213 the specific module. 4214 4215 module.enable_dups_trace 4216 [KNL] When CONFIG_MODULE_DEBUG_AUTOLOAD_DUPS is set, 4217 this means that duplicate request_module() calls will 4218 trigger a WARN_ON() instead of a pr_warn(). Note that 4219 if MODULE_DEBUG_AUTOLOAD_DUPS_TRACE is set, WARN_ON()s 4220 will always be issued and this option does nothing. 4221 module.sig_enforce 4222 [KNL] When CONFIG_MODULE_SIG is set, this means that 4223 modules without (valid) signatures will fail to load. 4224 Note that if CONFIG_MODULE_SIG_FORCE is set, that 4225 is always true, so this option does nothing. 4226 4227 module_blacklist= [KNL] Do not load a comma-separated list of 4228 modules. Useful for debugging problem modules. 4229 4230 mousedev.tap_time= 4231 [MOUSE] Maximum time between finger touching and 4232 leaving touchpad surface for touch to be considered 4233 a tap and be reported as a left button click (for 4234 touchpads working in absolute mode only). 4235 Format: <msecs> 4236 mousedev.xres= [MOUSE] Horizontal screen resolution, used for devices 4237 reporting absolute coordinates, such as tablets 4238 mousedev.yres= [MOUSE] Vertical screen resolution, used for devices 4239 reporting absolute coordinates, such as tablets 4240 4241 movablecore= [KNL,X86,PPC,EARLY] 4242 Format: nn[KMGTPE] | nn% 4243 This parameter is the complement to kernelcore=, it 4244 specifies the amount of memory used for migratable 4245 allocations. If both kernelcore and movablecore is 4246 specified, then kernelcore will be at *least* the 4247 specified value but may be more. If movablecore on its 4248 own is specified, the administrator must be careful 4249 that the amount of memory usable for all allocations 4250 is not too small. 4251 4252 movable_node [KNL,EARLY] Boot-time switch to make hotplugable memory 4253 NUMA nodes to be movable. This means that the memory 4254 of such nodes will be usable only for movable 4255 allocations which rules out almost all kernel 4256 allocations. Use with caution! 4257 4258 MTD_Partition= [MTD] 4259 Format: <name>,<region-number>,<size>,<offset> 4260 4261 MTD_Region= [MTD] Format: 4262 <name>,<region-number>[,<base>,<size>,<buswidth>,<altbuswidth>] 4263 4264 mtdparts= [MTD] 4265 See drivers/mtd/parsers/cmdlinepart.c 4266 4267 mtouchusb.raw_coordinates= 4268 [HW] Make the MicroTouch USB driver use raw coordinates 4269 ('y', default) or cooked coordinates ('n') 4270 4271 mtrr=debug [X86,EARLY] 4272 Enable printing debug information related to MTRR 4273 registers at boot time. 4274 4275 mtrr_chunk_size=nn[KMG,X86,EARLY] 4276 used for mtrr cleanup. It is largest continuous chunk 4277 that could hold holes aka. UC entries. 4278 4279 mtrr_gran_size=nn[KMG,X86,EARLY] 4280 Used for mtrr cleanup. It is granularity of mtrr block. 4281 Default is 1. 4282 Large value could prevent small alignment from 4283 using up MTRRs. 4284 4285 mtrr_spare_reg_nr=n [X86,EARLY] 4286 Format: <integer> 4287 Range: 0,7 : spare reg number 4288 Default : 1 4289 Used for mtrr cleanup. It is spare mtrr entries number. 4290 Set to 2 or more if your graphical card needs more. 4291 4292 multitce=off [PPC] This parameter disables the use of the pSeries 4293 firmware feature for updating multiple TCE entries 4294 at a time. 4295 4296 n2= [NET] SDL Inc. RISCom/N2 synchronous serial card 4297 4298 netdev= [NET] Network devices parameters 4299 Format: <irq>,<io>,<mem_start>,<mem_end>,<name> 4300 Note that mem_start is often overloaded to mean 4301 something different and driver-specific. 4302 This usage is only documented in each driver source 4303 file if at all. 4304 4305 netpoll.carrier_timeout= 4306 [NET] Specifies amount of time (in seconds) that 4307 netpoll should wait for a carrier. By default netpoll 4308 waits 4 seconds. 4309 4310 nf_conntrack.acct= 4311 [NETFILTER] Enable connection tracking flow accounting 4312 0 to disable accounting 4313 1 to enable accounting 4314 Default value is 0. 4315 4316 nfs.cache_getent= 4317 [NFS] sets the pathname to the program which is used 4318 to update the NFS client cache entries. 4319 4320 nfs.cache_getent_timeout= 4321 [NFS] sets the timeout after which an attempt to 4322 update a cache entry is deemed to have failed. 4323 4324 nfs.callback_nr_threads= 4325 [NFSv4] set the total number of threads that the 4326 NFS client will assign to service NFSv4 callback 4327 requests. 4328 4329 nfs.callback_tcpport= 4330 [NFS] set the TCP port on which the NFSv4 callback 4331 channel should listen. 4332 4333 nfs.delay_retrans= 4334 [NFS] specifies the number of times the NFSv4 client 4335 retries the request before returning an EAGAIN error, 4336 after a reply of NFS4ERR_DELAY from the server. 4337 Only applies if the softerr mount option is enabled, 4338 and the specified value is >= 0. 4339 4340 nfs.enable_ino64= 4341 [NFS] enable 64-bit inode numbers. 4342 If zero, the NFS client will fake up a 32-bit inode 4343 number for the readdir() and stat() syscalls instead 4344 of returning the full 64-bit number. 4345 The default is to return 64-bit inode numbers. 4346 4347 nfs.idmap_cache_timeout= 4348 [NFS] set the maximum lifetime for idmapper cache 4349 entries. 4350 4351 nfs.max_session_cb_slots= 4352 [NFSv4.1] Sets the maximum number of session 4353 slots the client will assign to the callback 4354 channel. This determines the maximum number of 4355 callbacks the client will process in parallel for 4356 a particular server. 4357 4358 nfs.max_session_slots= 4359 [NFSv4.1] Sets the maximum number of session slots 4360 the client will attempt to negotiate with the server. 4361 This limits the number of simultaneous RPC requests 4362 that the client can send to the NFSv4.1 server. 4363 Note that there is little point in setting this 4364 value higher than the max_tcp_slot_table_limit. 4365 4366 nfs.nfs4_disable_idmapping= 4367 [NFSv4] When set to the default of '1', this option 4368 ensures that both the RPC level authentication 4369 scheme and the NFS level operations agree to use 4370 numeric uids/gids if the mount is using the 4371 'sec=sys' security flavour. In effect it is 4372 disabling idmapping, which can make migration from 4373 legacy NFSv2/v3 systems to NFSv4 easier. 4374 Servers that do not support this mode of operation 4375 will be autodetected by the client, and it will fall 4376 back to using the idmapper. 4377 To turn off this behaviour, set the value to '0'. 4378 4379 nfs.nfs4_unique_id= 4380 [NFS4] Specify an additional fixed unique ident- 4381 ification string that NFSv4 clients can insert into 4382 their nfs_client_id4 string. This is typically a 4383 UUID that is generated at system install time. 4384 4385 nfs.recover_lost_locks= 4386 [NFSv4] Attempt to recover locks that were lost due 4387 to a lease timeout on the server. Please note that 4388 doing this risks data corruption, since there are 4389 no guarantees that the file will remain unchanged 4390 after the locks are lost. 4391 If you want to enable the kernel legacy behaviour of 4392 attempting to recover these locks, then set this 4393 parameter to '1'. 4394 The default parameter value of '0' causes the kernel 4395 not to attempt recovery of lost locks. 4396 4397 nfs.send_implementation_id= 4398 [NFSv4.1] Send client implementation identification 4399 information in exchange_id requests. 4400 If zero, no implementation identification information 4401 will be sent. 4402 The default is to send the implementation identification 4403 information. 4404 4405 nfs4.layoutstats_timer= 4406 [NFSv4.2] Change the rate at which the kernel sends 4407 layoutstats to the pNFS metadata server. 4408 4409 Setting this to value to 0 causes the kernel to use 4410 whatever value is the default set by the layout 4411 driver. A non-zero value sets the minimum interval 4412 in seconds between layoutstats transmissions. 4413 4414 nfsd.inter_copy_offload_enable= 4415 [NFSv4.2] When set to 1, the server will support 4416 server-to-server copies for which this server is 4417 the destination of the copy. 4418 4419 nfsd.nfs4_disable_idmapping= 4420 [NFSv4] When set to the default of '1', the NFSv4 4421 server will return only numeric uids and gids to 4422 clients using auth_sys, and will accept numeric uids 4423 and gids from such clients. This is intended to ease 4424 migration from NFSv2/v3. 4425 4426 nfsd.nfsd4_ssc_umount_timeout= 4427 [NFSv4.2] When used as the destination of a 4428 server-to-server copy, knfsd temporarily mounts 4429 the source server. It caches the mount in case 4430 it will be needed again, and discards it if not 4431 used for the number of milliseconds specified by 4432 this parameter. 4433 4434 nfsaddrs= [NFS] Deprecated. Use ip= instead. 4435 See Documentation/admin-guide/nfs/nfsroot.rst. 4436 4437 nfsroot= [NFS] nfs root filesystem for disk-less boxes. 4438 See Documentation/admin-guide/nfs/nfsroot.rst. 4439 4440 nfsrootdebug [NFS] enable nfsroot debugging messages. 4441 See Documentation/admin-guide/nfs/nfsroot.rst. 4442 4443 nmi_backtrace.backtrace_idle [KNL] 4444 Dump stacks even of idle CPUs in response to an 4445 NMI stack-backtrace request. 4446 4447 nmi_debug= [KNL,SH] Specify one or more actions to take 4448 when a NMI is triggered. 4449 Format: [state][,regs][,debounce][,die] 4450 4451 nmi_watchdog= [KNL,BUGS=X86] Debugging features for SMP kernels 4452 Format: [panic,][nopanic,][rNNN,][num] 4453 Valid num: 0 or 1 4454 0 - turn hardlockup detector in nmi_watchdog off 4455 1 - turn hardlockup detector in nmi_watchdog on 4456 rNNN - configure the watchdog with raw perf event 0xNNN 4457 4458 When panic is specified, panic when an NMI watchdog 4459 timeout occurs (or 'nopanic' to not panic on an NMI 4460 watchdog, if CONFIG_BOOTPARAM_HARDLOCKUP_PANIC is set) 4461 To disable both hard and soft lockup detectors, 4462 please see 'nowatchdog'. 4463 This is useful when you use a panic=... timeout and 4464 need the box quickly up again. 4465 4466 These settings can be accessed at runtime via 4467 the nmi_watchdog and hardlockup_panic sysctls. 4468 4469 no387 [BUGS=X86-32] Tells the kernel to use the 387 maths 4470 emulation library even if a 387 maths coprocessor 4471 is present. 4472 4473 no4lvl [RISCV,EARLY] Disable 4-level and 5-level paging modes. 4474 Forces kernel to use 3-level paging instead. 4475 4476 no5lvl [X86-64,RISCV,EARLY] Disable 5-level paging mode. Forces 4477 kernel to use 4-level paging instead. 4478 4479 noalign [KNL,ARM] 4480 4481 noapic [SMP,APIC,EARLY] Tells the kernel to not make use of any 4482 IOAPICs that may be present in the system. 4483 4484 noapictimer [APIC,X86] Don't set up the APIC timer 4485 4486 noautogroup Disable scheduler automatic task group creation. 4487 4488 nocache [ARM,EARLY] 4489 4490 no_console_suspend 4491 [HW] Never suspend the console 4492 Disable suspending of consoles during suspend and 4493 hibernate operations. Once disabled, debugging 4494 messages can reach various consoles while the rest 4495 of the system is being put to sleep (ie, while 4496 debugging driver suspend/resume hooks). This may 4497 not work reliably with all consoles, but is known 4498 to work with serial and VGA consoles. 4499 To facilitate more flexible debugging, we also add 4500 console_suspend, a printk module parameter to control 4501 it. Users could use console_suspend (usually 4502 /sys/module/printk/parameters/console_suspend) to 4503 turn on/off it dynamically. 4504 4505 no_debug_objects 4506 [KNL,EARLY] Disable object debugging 4507 4508 nodsp [SH] Disable hardware DSP at boot time. 4509 4510 noefi [EFI,EARLY] Disable EFI runtime services support. 4511 4512 no_entry_flush [PPC,EARLY] Don't flush the L1-D cache when entering the kernel. 4513 4514 noexec32 [X86-64] 4515 This affects only 32-bit executables. 4516 noexec32=on: enable non-executable mappings (default) 4517 read doesn't imply executable mappings 4518 noexec32=off: disable non-executable mappings 4519 read implies executable mappings 4520 4521 no_file_caps Tells the kernel not to honor file capabilities. The 4522 only way then for a file to be executed with privilege 4523 is to be setuid root or executed by root. 4524 4525 nofpu [MIPS,SH] Disable hardware FPU at boot time. 4526 4527 nofsgsbase [X86] Disables FSGSBASE instructions. 4528 4529 nofxsr [BUGS=X86-32] Disables x86 floating point extended 4530 register save and restore. The kernel will only save 4531 legacy floating-point registers on task switch. 4532 4533 nogbpages [X86] Do not use GB pages for kernel direct mappings. 4534 4535 no_hash_pointers 4536 [KNL,EARLY] 4537 Alias for "hash_pointers=never". 4538 4539 nohibernate [HIBERNATION] Disable hibernation and resume. 4540 4541 nohlt [ARM,ARM64,MICROBLAZE,MIPS,PPC,RISCV,SH] Forces the kernel to 4542 busy wait in do_idle() and not use the arch_cpu_idle() 4543 implementation; requires CONFIG_GENERIC_IDLE_POLL_SETUP 4544 to be effective. This is useful on platforms where the 4545 sleep(SH) or wfi(ARM,ARM64) instructions do not work 4546 correctly or when doing power measurements to evaluate 4547 the impact of the sleep instructions. This is also 4548 useful when using JTAG debugger. 4549 4550 nohpet [X86] Don't use the HPET timer. 4551 4552 nohugeiomap [KNL,X86,PPC,ARM64,EARLY] Disable kernel huge I/O mappings. 4553 4554 nohugevmalloc [KNL,X86,PPC,ARM64,EARLY] Disable kernel huge vmalloc mappings. 4555 4556 nohz= [KNL] Boottime enable/disable dynamic ticks 4557 Valid arguments: on, off 4558 Default: on 4559 4560 nohz_full= [KNL,BOOT,SMP,ISOL] 4561 The argument is a cpu list, as described above. 4562 In kernels built with CONFIG_NO_HZ_FULL=y, set 4563 the specified list of CPUs whose tick will be stopped 4564 whenever possible. The boot CPU will be forced outside 4565 the range to maintain the timekeeping. Any CPUs 4566 in this list will have their RCU callbacks offloaded, 4567 just as if they had also been called out in the 4568 rcu_nocbs= boot parameter. 4569 4570 Note that this argument takes precedence over 4571 the CONFIG_RCU_NOCB_CPU_DEFAULT_ALL option. 4572 4573 noinitrd [Deprecated,RAM] Tells the kernel not to load any configured 4574 initial RAM disk. Currently this parameter applies to 4575 initrd only, not to initramfs. But it applies to both 4576 in EFI mode. 4577 4578 nointremap [X86-64,Intel-IOMMU,EARLY] Do not enable interrupt 4579 remapping. 4580 [Deprecated - use intremap=off] 4581 4582 noinvpcid [X86,EARLY] Disable the INVPCID cpu feature. 4583 4584 noiotrap [SH] Disables trapped I/O port accesses. 4585 4586 noirqdebug [X86-32] Disables the code which attempts to detect and 4587 disable unhandled interrupt sources. 4588 4589 noisapnp [ISAPNP] Disables ISA PnP code. 4590 4591 nokaslr [KNL,EARLY] 4592 When CONFIG_RANDOMIZE_BASE is set, this disables 4593 kernel and module base offset ASLR (Address Space 4594 Layout Randomization). 4595 4596 no-kvmapf [X86,KVM,EARLY] Disable paravirtualized asynchronous page 4597 fault handling. 4598 4599 no-kvmclock [X86,KVM,EARLY] Disable paravirtualized KVM clock driver 4600 4601 nolapic [X86-32,APIC,EARLY] Do not enable or use the local APIC. 4602 4603 nolapic_timer [X86-32,APIC,EARLY] Do not use the local APIC timer. 4604 4605 nomce [X86-32] Disable Machine Check Exception 4606 4607 nomfgpt [X86-32] Disable Multi-Function General Purpose 4608 Timer usage (for AMD Geode machines). 4609 4610 nomodeset Disable kernel modesetting. Most systems' firmware 4611 sets up a display mode and provides framebuffer memory 4612 for output. With nomodeset, DRM and fbdev drivers will 4613 not load if they could possibly displace the pre- 4614 initialized output. Only the system framebuffer will 4615 be available for use. The respective drivers will not 4616 perform display-mode changes or accelerated rendering. 4617 4618 Useful as error fallback, or for testing and debugging. 4619 4620 nomodule Disable module load 4621 4622 nonmi_ipi [X86] Disable using NMI IPIs during panic/reboot to 4623 shutdown the other cpus. Instead use the REBOOT_VECTOR 4624 irq. 4625 4626 nopat [X86,EARLY] Disable PAT (page attribute table extension of 4627 pagetables) support. 4628 4629 nopcid [X86-64,EARLY] Disable the PCID cpu feature. 4630 4631 nopku [X86] Disable Memory Protection Keys CPU feature found 4632 in some Intel CPUs. 4633 4634 nopti [X86-64,EARLY] 4635 Equivalent to pti=off 4636 4637 nopv= [X86,XEN,KVM,HYPER_V,VMWARE,EARLY] 4638 Disables the PV optimizations forcing the guest to run 4639 as generic guest with no PV drivers. Currently support 4640 XEN HVM, KVM, HYPER_V and VMWARE guest. 4641 4642 nopvspin [X86,XEN,KVM,EARLY] 4643 Disables the qspinlock slow path using PV optimizations 4644 which allow the hypervisor to 'idle' the guest on lock 4645 contention. 4646 4647 norandmaps Don't use address space randomization. Equivalent to 4648 echo 0 > /proc/sys/kernel/randomize_va_space 4649 4650 noreplace-smp [X86-32,SMP] Don't replace SMP instructions 4651 with UP alternatives 4652 4653 noresume [SWSUSP] Disables resume and restores original swap 4654 space. 4655 4656 no-scroll [VGA] Disables scrollback. 4657 This is required for the Braillex ib80-piezo Braille 4658 reader made by F.H. Papenmeier (Germany). 4659 4660 nosgx [X86-64,SGX,EARLY] Disables Intel SGX kernel support. 4661 4662 nosmap [PPC,EARLY] 4663 Disable SMAP (Supervisor Mode Access Prevention) 4664 even if it is supported by processor. 4665 4666 nosmep [PPC64s,EARLY] 4667 Disable SMEP (Supervisor Mode Execution Prevention) 4668 even if it is supported by processor. 4669 4670 nosmp [SMP,EARLY] Tells an SMP kernel to act as a UP kernel, 4671 and disable the IO APIC. legacy for "maxcpus=0". 4672 4673 nosmt [KNL,MIPS,PPC,EARLY] Disable symmetric multithreading (SMT). 4674 Equivalent to smt=1. 4675 4676 [KNL,LOONGARCH,X86,PPC,S390] Disable symmetric multithreading (SMT). 4677 nosmt=force: Force disable SMT, cannot be undone 4678 via the sysfs control file. 4679 4680 nosoftlockup [KNL] Disable the soft-lockup detector. 4681 4682 nospec_store_bypass_disable 4683 [HW,EARLY] Disable all mitigations for the Speculative 4684 Store Bypass vulnerability 4685 4686 nospectre_bhb [ARM64,EARLY] Disable all mitigations for Spectre-BHB (branch 4687 history injection) vulnerability. System may allow data leaks 4688 with this option. 4689 4690 nospectre_v1 [X86,PPC,EARLY] Disable mitigations for Spectre Variant 1 4691 (bounds check bypass). With this option data leaks are 4692 possible in the system. 4693 4694 nospectre_v2 [X86,PPC_E500,ARM64,EARLY] Disable all mitigations 4695 for the Spectre variant 2 (indirect branch 4696 prediction) vulnerability. System may allow data 4697 leaks with this option. 4698 4699 no-steal-acc [X86,PV_OPS,ARM64,PPC/PSERIES,RISCV,LOONGARCH,EARLY] 4700 Disable paravirtualized steal time accounting. steal time 4701 is computed, but won't influence scheduler behaviour 4702 4703 nosync [HW,M68K] Disables sync negotiation for all devices. 4704 4705 no_timer_check [X86,APIC] Disables the code which tests for broken 4706 timer IRQ sources, i.e., the IO-APIC timer. This can 4707 work around problems with incorrect timer 4708 initialization on some boards. 4709 4710 no_uaccess_flush 4711 [PPC,EARLY] Don't flush the L1-D cache after accessing user data. 4712 4713 novmcoredd [KNL,KDUMP] 4714 Disable device dump. Device dump allows drivers to 4715 append dump data to vmcore so you can collect driver 4716 specified debug info. Drivers can append the data 4717 without any limit and this data is stored in memory, 4718 so this may cause significant memory stress. Disabling 4719 device dump can help save memory but the driver debug 4720 data will be no longer available. This parameter 4721 is only available when CONFIG_PROC_VMCORE_DEVICE_DUMP 4722 is set. 4723 4724 no-vmw-sched-clock 4725 [X86,PV_OPS,EARLY] Disable paravirtualized VMware 4726 scheduler clock and use the default one. 4727 4728 nowatchdog [KNL] Disable both lockup detectors, i.e. 4729 soft-lockup and NMI watchdog (hard-lockup). 4730 4731 nowb [ARM,EARLY] 4732 4733 nox2apic [X86-64,APIC,EARLY] Do not enable x2APIC mode. 4734 4735 NOTE: this parameter will be ignored on systems with the 4736 LEGACY_XAPIC_DISABLED bit set in the 4737 IA32_XAPIC_DISABLE_STATUS MSR. 4738 4739 noxsave [BUGS=X86] Disables x86 extended register state save 4740 and restore using xsave. The kernel will fallback to 4741 enabling legacy floating-point and sse state. 4742 4743 noxsaveopt [X86] Disables xsaveopt used in saving x86 extended 4744 register states. The kernel will fall back to use 4745 xsave to save the states. By using this parameter, 4746 performance of saving the states is degraded because 4747 xsave doesn't support modified optimization while 4748 xsaveopt supports it on xsaveopt enabled systems. 4749 4750 noxsaves [X86] Disables xsaves and xrstors used in saving and 4751 restoring x86 extended register state in compacted 4752 form of xsave area. The kernel will fall back to use 4753 xsaveopt and xrstor to save and restore the states 4754 in standard form of xsave area. By using this 4755 parameter, xsave area per process might occupy more 4756 memory on xsaves enabled systems. 4757 4758 nr_cpus= [SMP,EARLY] Maximum number of processors that an SMP kernel 4759 could support. nr_cpus=n : n >= 1 limits the kernel to 4760 support 'n' processors. It could be larger than the 4761 number of already plugged CPU during bootup, later in 4762 runtime you can physically add extra cpu until it reaches 4763 n. So during boot up some boot time memory for per-cpu 4764 variables need be pre-allocated for later physical cpu 4765 hot plugging. 4766 4767 nr_uarts= [SERIAL] maximum number of UARTs to be registered. 4768 4769 numa=off [KNL, ARM64, PPC, RISCV, SPARC, X86, EARLY] 4770 Disable NUMA, Only set up a single NUMA node 4771 spanning all memory. 4772 4773 numa=fake=<size>[MG] 4774 [KNL, ARM64, RISCV, X86, EARLY] 4775 If given as a memory unit, fills all system RAM with 4776 nodes of size interleaved over physical nodes. 4777 4778 numa=fake=<N> 4779 [KNL, ARM64, RISCV, X86, EARLY] 4780 If given as an integer, fills all system RAM with N 4781 fake nodes interleaved over physical nodes. 4782 4783 numa=fake=<N>U 4784 [KNL, ARM64, RISCV, X86, EARLY] 4785 If given as an integer followed by 'U', it will 4786 divide each physical node into N emulated nodes. 4787 4788 numa=noacpi [X86] Don't parse the SRAT table for NUMA setup 4789 4790 numa=nohmat [X86] Don't parse the HMAT table for NUMA setup, or 4791 soft-reserved memory partitioning. 4792 4793 numa_balancing= [KNL,ARM64,PPC,RISCV,S390,X86] Enable or disable automatic 4794 NUMA balancing. 4795 Allowed values are enable and disable 4796 4797 numa_zonelist_order= [KNL, BOOT] Select zonelist order for NUMA. 4798 'node', 'default' can be specified 4799 This can be set from sysctl after boot. 4800 See Documentation/admin-guide/sysctl/vm.rst for details. 4801 4802 nvme.quirks= [NVME] A list of quirk entries to augment the built-in 4803 nvme quirk list. List entries are separated by a 4804 '-' character. 4805 Each entry has the form VendorID:ProductID:quirk_names. 4806 The IDs are 4-digits hex numbers and quirk_names is a 4807 list of quirk names separated by commas. A quirk name 4808 can be prefixed by '^', meaning that the specified 4809 quirk must be disabled. 4810 4811 Example: 4812 nvme.quirks=7710:2267:bogus_nid,^identify_cns-9900:7711:broken_msi 4813 4814 ohci1394_dma=early [HW,EARLY] enable debugging via the ohci1394 driver. 4815 See Documentation/core-api/debugging-via-ohci1394.rst for more 4816 info. 4817 4818 olpc_ec_timeout= [OLPC] ms delay when issuing EC commands 4819 Rather than timing out after 20 ms if an EC 4820 command is not properly ACKed, override the length 4821 of the timeout. We have interrupts disabled while 4822 waiting for the ACK, so if this is set too high 4823 interrupts *may* be lost! 4824 4825 omap_mux= [OMAP] Override bootloader pin multiplexing. 4826 Format: <mux_mode0.mode_name=value>... 4827 For example, to override I2C bus2: 4828 omap_mux=i2c2_scl.i2c2_scl=0x100,i2c2_sda.i2c2_sda=0x100 4829 4830 onenand.bdry= [HW,MTD] Flex-OneNAND Boundary Configuration 4831 4832 Format: [die0_boundary][,die0_lock][,die1_boundary][,die1_lock] 4833 4834 boundary - index of last SLC block on Flex-OneNAND. 4835 The remaining blocks are configured as MLC blocks. 4836 lock - Configure if Flex-OneNAND boundary should be locked. 4837 Once locked, the boundary cannot be changed. 4838 1 indicates lock status, 0 indicates unlock status. 4839 4840 oops=panic [KNL,EARLY] 4841 Always panic on oopses. Default is to just kill the 4842 process, but there is a small probability of 4843 deadlocking the machine. 4844 This will also cause panics on machine check exceptions. 4845 Useful together with panic=30 to trigger a reboot. 4846 4847 page_alloc.shuffle= 4848 [KNL] Boolean flag to control whether the page allocator 4849 should randomize its free lists. This parameter can be 4850 used to enable/disable page randomization. The state of 4851 the flag can be read from sysfs at: 4852 /sys/module/page_alloc/parameters/shuffle. 4853 This parameter is only available if CONFIG_SHUFFLE_PAGE_ALLOCATOR=y. 4854 4855 page_owner= [KNL,EARLY] Boot-time page_owner enabling option. 4856 Storage of the information about who allocated 4857 each page is disabled in default. With this switch, 4858 we can turn it on. 4859 on: enable the feature 4860 4861 page_poison= [KNL,EARLY] Boot-time parameter changing the state of 4862 poisoning on the buddy allocator, available with 4863 CONFIG_PAGE_POISONING=y. 4864 off: turn off poisoning (default) 4865 on: turn on poisoning 4866 4867 page_reporting.page_reporting_order= 4868 [KNL] Minimal page reporting order 4869 Format: <integer> 4870 Adjust the minimal page reporting order. The page 4871 reporting is disabled when it exceeds MAX_PAGE_ORDER. 4872 4873 panic= [KNL] Kernel behaviour on panic: delay <timeout> 4874 timeout > 0: seconds before rebooting 4875 timeout = 0: wait forever 4876 timeout < 0: reboot immediately 4877 Format: <timeout> 4878 4879 panic_on_taint= [KNL,EARLY] 4880 Bitmask for conditionally calling panic() in add_taint() 4881 Format: <hex>[,nousertaint] 4882 Hexadecimal bitmask representing the set of TAINT flags 4883 that will cause the kernel to panic when add_taint() is 4884 called with any of the flags in this set. 4885 The optional switch "nousertaint" can be utilized to 4886 prevent userspace forced crashes by writing to sysctl 4887 /proc/sys/kernel/tainted any flagset matching with the 4888 bitmask set on panic_on_taint. 4889 See Documentation/admin-guide/tainted-kernels.rst for 4890 extra details on the taint flags that users can pick 4891 to compose the bitmask to assign to panic_on_taint. 4892 4893 panic_on_warn=1 panic() instead of WARN(). Useful to cause kdump 4894 on a WARN(). 4895 4896 panic_force_cpu= 4897 [KNL,SMP] Force panic handling to execute on a specific CPU. 4898 Format: <cpu number> 4899 Some platforms require panic handling to occur on a 4900 specific CPU for the crash kernel to function correctly. 4901 This can be due to firmware limitations, interrupt routing 4902 constraints, or platform-specific requirements where only 4903 a particular CPU can safely enter the crash kernel. 4904 When set, panic() will redirect execution to the specified 4905 CPU before proceeding with the normal panic and kexec flow. 4906 If the target CPU is offline or unavailable, panic proceeds 4907 on the current CPU. 4908 This option should only be used for systems with the above 4909 constraints as it might cause the panic operation to be less reliable. 4910 4911 panic_print= Bitmask for printing system info when panic happens. 4912 User can chose combination of the following bits: 4913 bit 0: print all tasks info 4914 bit 1: print system memory info 4915 bit 2: print timer info 4916 bit 3: print locks info if CONFIG_LOCKDEP is on 4917 bit 4: print ftrace buffer 4918 bit 5: replay all kernel messages on consoles at the end of panic 4919 bit 6: print all CPUs backtrace (if available in the arch) 4920 bit 7: print only tasks in uninterruptible (blocked) state 4921 *Be aware* that this option may print a _lot_ of lines, 4922 so there are risks of losing older messages in the log. 4923 Use this option carefully, maybe worth to setup a 4924 bigger log buffer with "log_buf_len" along with this. 4925 4926 panic_sys_info= A comma separated list of extra information to be dumped 4927 on panic. 4928 Format: val[,val...] 4929 Where @val can be any of the following: 4930 4931 tasks: print all tasks info 4932 mem: print system memory info 4933 timers: print timers info 4934 locks: print locks info if CONFIG_LOCKDEP is on 4935 ftrace: print ftrace buffer 4936 all_bt: print all CPUs backtrace (if available in the arch) 4937 blocked_tasks: print only tasks in uninterruptible (blocked) state 4938 4939 This is a human readable alternative to the 'panic_print' option. 4940 4941 panic_console_replay 4942 When panic happens, replay all kernel messages on 4943 consoles at the end of panic. 4944 4945 parkbd.port= [HW] Parallel port number the keyboard adapter is 4946 connected to, default is 0. 4947 Format: <parport#> 4948 parkbd.mode= [HW] Parallel port keyboard adapter mode of operation, 4949 0 for XT, 1 for AT (default is AT). 4950 Format: <mode> 4951 4952 parport= [HW,PPT] Specify parallel ports. 0 disables. 4953 Format: { 0 | auto | 0xBBB[,IRQ[,DMA]] } 4954 Use 'auto' to force the driver to use any 4955 IRQ/DMA settings detected (the default is to 4956 ignore detected IRQ/DMA settings because of 4957 possible conflicts). You can specify the base 4958 address, IRQ, and DMA settings; IRQ and DMA 4959 should be numbers, or 'auto' (for using detected 4960 settings on that particular port), or 'nofifo' 4961 (to avoid using a FIFO even if it is detected). 4962 Parallel ports are assigned in the order they 4963 are specified on the command line, starting 4964 with parport0. 4965 4966 parport_init_mode= [HW,PPT] 4967 Configure VIA parallel port to operate in 4968 a specific mode. This is necessary on Pegasos 4969 computer where firmware has no options for setting 4970 up parallel port mode and sets it to spp. 4971 Currently this function knows 686a and 8231 chips. 4972 Format: [spp|ps2|epp|ecp|ecpepp] 4973 4974 pata_legacy.all= [HW,LIBATA] 4975 Format: <int> 4976 Set to non-zero to probe primary and secondary ISA 4977 port ranges on PCI systems where no PCI PATA device 4978 has been found at either range. Disabled by default. 4979 4980 pata_legacy.autospeed= [HW,LIBATA] 4981 Format: <int> 4982 Set to non-zero if a chip is present that snoops speed 4983 changes. Disabled by default. 4984 4985 pata_legacy.ht6560a= [HW,LIBATA] 4986 Format: <int> 4987 Set to 1, 2, or 3 for HT 6560A on the primary channel, 4988 the secondary channel, or both channels respectively. 4989 Disabled by default. 4990 4991 pata_legacy.ht6560b= [HW,LIBATA] 4992 Format: <int> 4993 Set to 1, 2, or 3 for HT 6560B on the primary channel, 4994 the secondary channel, or both channels respectively. 4995 Disabled by default. 4996 4997 pata_legacy.iordy_mask= [HW,LIBATA] 4998 Format: <int> 4999 IORDY enable mask. Set individual bits to allow IORDY 5000 for the respective channel. Bit 0 is for the first 5001 legacy channel handled by this driver, bit 1 is for 5002 the second channel, and so on. The sequence will often 5003 correspond to the primary legacy channel, the secondary 5004 legacy channel, and so on, but the handling of a PCI 5005 bus and the use of other driver options may interfere 5006 with the sequence. By default IORDY is allowed across 5007 all channels. 5008 5009 pata_legacy.opti82c46x= [HW,LIBATA] 5010 Format: <int> 5011 Set to 1, 2, or 3 for Opti 82c611A on the primary 5012 channel, the secondary channel, or both channels 5013 respectively. Disabled by default. 5014 5015 pata_legacy.opti82c611a= [HW,LIBATA] 5016 Format: <int> 5017 Set to 1, 2, or 3 for Opti 82c465MV on the primary 5018 channel, the secondary channel, or both channels 5019 respectively. Disabled by default. 5020 5021 pata_legacy.pio_mask= [HW,LIBATA] 5022 Format: <int> 5023 PIO mode mask for autospeed devices. Set individual 5024 bits to allow the use of the respective PIO modes. 5025 Bit 0 is for mode 0, bit 1 is for mode 1, and so on. 5026 All modes allowed by default. 5027 5028 pata_legacy.probe_all= [HW,LIBATA] 5029 Format: <int> 5030 Set to non-zero to probe tertiary and further ISA 5031 port ranges on PCI systems. Disabled by default. 5032 5033 pata_legacy.probe_mask= [HW,LIBATA] 5034 Format: <int> 5035 Probe mask for legacy ISA PATA ports. Depending on 5036 platform configuration and the use of other driver 5037 options up to 6 legacy ports are supported: 0x1f0, 5038 0x170, 0x1e8, 0x168, 0x1e0, 0x160, however probing 5039 of individual ports can be disabled by setting the 5040 corresponding bits in the mask to 1. Bit 0 is for 5041 the first port in the list above (0x1f0), and so on. 5042 By default all supported ports are probed. 5043 5044 pata_legacy.qdi= [HW,LIBATA] 5045 Format: <int> 5046 Set to non-zero to probe QDI controllers. By default 5047 set to 1 if CONFIG_PATA_QDI_MODULE, 0 otherwise. 5048 5049 pata_legacy.winbond= [HW,LIBATA] 5050 Format: <int> 5051 Set to non-zero to probe Winbond controllers. Use 5052 the standard I/O port (0x130) if 1, otherwise the 5053 value given is the I/O port to use (typically 0x1b0). 5054 By default set to 1 if CONFIG_PATA_WINBOND_VLB_MODULE, 5055 0 otherwise. 5056 5057 pata_platform.pio_mask= [HW,LIBATA] 5058 Format: <int> 5059 Supported PIO mode mask. Set individual bits to allow 5060 the use of the respective PIO modes. Bit 0 is for 5061 mode 0, bit 1 is for mode 1, and so on. Mode 0 only 5062 allowed by default. 5063 5064 pause_on_oops=<int> 5065 Halt all CPUs after the first oops has been printed for 5066 the specified number of seconds. This is to be used if 5067 your oopses keep scrolling off the screen. 5068 5069 pcbit= [HW,ISDN] 5070 5071 pci=option[,option...] [PCI,EARLY] various PCI subsystem options. 5072 5073 Some options herein operate on a specific device 5074 or a set of devices (<pci_dev>). These are 5075 specified in one of the following formats: 5076 5077 [<domain>:]<bus>:<dev>.<func>[/<dev>.<func>]* 5078 pci:<vendor>:<device>[:<subvendor>:<subdevice>] 5079 5080 Note: the first format specifies a PCI 5081 bus/device/function address which may change 5082 if new hardware is inserted, if motherboard 5083 firmware changes, or due to changes caused 5084 by other kernel parameters. If the 5085 domain is left unspecified, it is 5086 taken to be zero. Optionally, a path 5087 to a device through multiple device/function 5088 addresses can be specified after the base 5089 address (this is more robust against 5090 renumbering issues). The second format 5091 selects devices using IDs from the 5092 configuration space which may match multiple 5093 devices in the system. 5094 5095 earlydump dump PCI config space before the kernel 5096 changes anything 5097 off [X86] don't probe for the PCI bus 5098 bios [X86-32] force use of PCI BIOS, don't access 5099 the hardware directly. Use this if your machine 5100 has a non-standard PCI host bridge. 5101 nobios [X86-32] disallow use of PCI BIOS, only direct 5102 hardware access methods are allowed. Use this 5103 if you experience crashes upon bootup and you 5104 suspect they are caused by the BIOS. 5105 conf1 [X86] Force use of PCI Configuration Access 5106 Mechanism 1 (config address in IO port 0xCF8, 5107 data in IO port 0xCFC, both 32-bit). 5108 conf2 [X86] Force use of PCI Configuration Access 5109 Mechanism 2 (IO port 0xCF8 is an 8-bit port for 5110 the function, IO port 0xCFA, also 8-bit, sets 5111 bus number. The config space is then accessed 5112 through ports 0xC000-0xCFFF). 5113 See http://wiki.osdev.org/PCI for more info 5114 on the configuration access mechanisms. 5115 noaer [PCIE] If the PCIEAER kernel config parameter is 5116 enabled, this kernel boot option can be used to 5117 disable the use of PCIE advanced error reporting. 5118 nodomains [PCI] Disable support for multiple PCI 5119 root domains (aka PCI segments, in ACPI-speak). 5120 nommconf [X86] Disable use of MMCONFIG for PCI 5121 Configuration 5122 check_enable_amd_mmconf [X86] check for and enable 5123 properly configured MMIO access to PCI 5124 config space on AMD family 10h CPU 5125 nomsi [MSI] If the PCI_MSI kernel config parameter is 5126 enabled, this kernel boot option can be used to 5127 disable the use of MSI interrupts system-wide. 5128 noioapicquirk [APIC] Disable all boot interrupt quirks. 5129 Safety option to keep boot IRQs enabled. This 5130 should never be necessary. 5131 ioapicreroute [APIC] Enable rerouting of boot IRQs to the 5132 primary IO-APIC for bridges that cannot disable 5133 boot IRQs. This fixes a source of spurious IRQs 5134 when the system masks IRQs. 5135 noioapicreroute [APIC] Disable workaround that uses the 5136 boot IRQ equivalent of an IRQ that connects to 5137 a chipset where boot IRQs cannot be disabled. 5138 The opposite of ioapicreroute. 5139 biosirq [X86-32] Use PCI BIOS calls to get the interrupt 5140 routing table. These calls are known to be buggy 5141 on several machines and they hang the machine 5142 when used, but on other computers it's the only 5143 way to get the interrupt routing table. Try 5144 this option if the kernel is unable to allocate 5145 IRQs or discover secondary PCI buses on your 5146 motherboard. 5147 rom [X86] Assign address space to expansion ROMs. 5148 Use with caution as certain devices share 5149 address decoders between ROMs and other 5150 resources. 5151 norom [X86] Do not assign address space to 5152 expansion ROMs that do not already have 5153 BIOS assigned address ranges. 5154 nobar [X86] Do not assign address space to the 5155 BARs that weren't assigned by the BIOS. 5156 irqmask=0xMMMM [X86] Set a bit mask of IRQs allowed to be 5157 assigned automatically to PCI devices. You can 5158 make the kernel exclude IRQs of your ISA cards 5159 this way. 5160 pirqaddr=0xAAAAA [X86] Specify the physical address 5161 of the PIRQ table (normally generated 5162 by the BIOS) if it is outside the 5163 F0000h-100000h range. 5164 lastbus=N [X86] Scan all buses thru bus #N. Can be 5165 useful if the kernel is unable to find your 5166 secondary buses and you want to tell it 5167 explicitly which ones they are. 5168 assign-busses [X86] Always assign all PCI bus 5169 numbers ourselves, overriding 5170 whatever the firmware may have done. 5171 usepirqmask [X86] Honor the possible IRQ mask stored 5172 in the BIOS $PIR table. This is needed on 5173 some systems with broken BIOSes, notably 5174 some HP Pavilion N5400 and Omnibook XE3 5175 notebooks. This will have no effect if ACPI 5176 IRQ routing is enabled. 5177 noacpi [X86] Do not use ACPI for IRQ routing 5178 or for PCI scanning. 5179 use_crs [X86] Use PCI host bridge window information 5180 from ACPI. On BIOSes from 2008 or later, this 5181 is enabled by default. If you need to use this, 5182 please report a bug. 5183 nocrs [X86] Ignore PCI host bridge windows from ACPI. 5184 If you need to use this, please report a bug. 5185 use_e820 [X86] Use E820 reservations to exclude parts of 5186 PCI host bridge windows. This is a workaround 5187 for BIOS defects in host bridge _CRS methods. 5188 If you need to use this, please report a bug to 5189 <linux-pci@vger.kernel.org>. 5190 no_e820 [X86] Ignore E820 reservations for PCI host 5191 bridge windows. This is the default on modern 5192 hardware. If you need to use this, please report 5193 a bug to <linux-pci@vger.kernel.org>. 5194 routeirq Do IRQ routing for all PCI devices. 5195 This is normally done in pci_enable_device(), 5196 so this option is a temporary workaround 5197 for broken drivers that don't call it. 5198 skip_isa_align [X86] do not align io start addr, so can 5199 handle more pci cards 5200 noearly [X86] Don't do any early type 1 scanning. 5201 This might help on some broken boards which 5202 machine check when some devices' config space 5203 is read. But various workarounds are disabled 5204 and some IOMMU drivers will not work. 5205 bfsort Sort PCI devices into breadth-first order. 5206 This sorting is done to get a device 5207 order compatible with older (<= 2.4) kernels. 5208 nobfsort Don't sort PCI devices into breadth-first order. 5209 pcie_bus_tune_off Disable PCIe MPS (Max Payload Size) 5210 tuning and use the BIOS-configured MPS defaults. 5211 pcie_bus_safe Set every device's MPS to the largest value 5212 supported by all devices below the root complex. 5213 pcie_bus_perf Set device MPS to the largest allowable MPS 5214 based on its parent bus. Also set MRRS (Max 5215 Read Request Size) to the largest supported 5216 value (no larger than the MPS that the device 5217 or bus can support) for best performance. 5218 pcie_bus_peer2peer Set every device's MPS to 128B, which 5219 every device is guaranteed to support. This 5220 configuration allows peer-to-peer DMA between 5221 any pair of devices, possibly at the cost of 5222 reduced performance. This also guarantees 5223 that hot-added devices will work. 5224 cbiosize=nn[KMG] The fixed amount of bus space which is 5225 reserved for the CardBus bridge's IO window. 5226 The default value is 256 bytes. 5227 cbmemsize=nn[KMG] The fixed amount of bus space which is 5228 reserved for the CardBus bridge's memory 5229 window. The default value is 64 megabytes. 5230 resource_alignment= 5231 Format: 5232 [<order of align>@]<pci_dev>[; ...] 5233 Specifies alignment and device to reassign 5234 aligned memory resources. How to 5235 specify the device is described above. 5236 If <order of align> is not specified, 5237 PAGE_SIZE is used as alignment. 5238 A PCI-PCI bridge can be specified if resource 5239 windows need to be expanded. 5240 To specify the alignment for several 5241 instances of a device, the PCI vendor, 5242 device, subvendor, and subdevice may be 5243 specified, e.g., 12@pci:8086:9c22:103c:198f 5244 for 4096-byte alignment. 5245 ecrc= Enable/disable PCIe ECRC (transaction layer 5246 end-to-end CRC checking). Only effective if 5247 OS has native AER control (either granted by 5248 ACPI _OSC or forced via "pcie_ports=native") 5249 bios: Use BIOS/firmware settings. This is the 5250 the default. 5251 off: Turn ECRC off 5252 on: Turn ECRC on. 5253 hpiosize=nn[KMG] The fixed amount of bus space which is 5254 reserved for hotplug bridge's IO window. 5255 Default size is 256 bytes. 5256 hpmmiosize=nn[KMG] The fixed amount of bus space which is 5257 reserved for hotplug bridge's MMIO window. 5258 Default size is 2 megabytes. 5259 hpmmioprefsize=nn[KMG] The fixed amount of bus space which is 5260 reserved for hotplug bridge's MMIO_PREF window. 5261 Default size is 2 megabytes. 5262 hpmemsize=nn[KMG] The fixed amount of bus space which is 5263 reserved for hotplug bridge's MMIO and 5264 MMIO_PREF window. 5265 Default size is 2 megabytes. 5266 hpbussize=nn The minimum amount of additional bus numbers 5267 reserved for buses below a hotplug bridge. 5268 Default is 1. 5269 realloc= Enable/disable reallocating PCI bridge resources 5270 if allocations done by BIOS are too small to 5271 accommodate resources required by all child 5272 devices. 5273 off: Turn realloc off 5274 on: Turn realloc on 5275 realloc same as realloc=on 5276 noari do not use PCIe ARI. 5277 noats [PCIE, Intel-IOMMU, AMD-IOMMU] 5278 do not use PCIe ATS (and IOMMU device IOTLB). 5279 pcie_scan_all Scan all possible PCIe devices. Otherwise we 5280 only look for one device below a PCIe downstream 5281 port. 5282 big_root_window Try to add a big 64bit memory window to the PCIe 5283 root complex on AMD CPUs. Some GFX hardware 5284 can resize a BAR to allow access to all VRAM. 5285 Adding the window is slightly risky (it may 5286 conflict with unreported devices), so this 5287 taints the kernel. 5288 disable_acs_redir=<pci_dev>[; ...] 5289 Specify one or more PCI devices (in the format 5290 specified above) separated by semicolons. 5291 Each device specified will have the PCI ACS 5292 redirect capabilities forced off which will 5293 allow P2P traffic between devices through 5294 bridges without forcing it upstream. Note: 5295 this removes isolation between devices and 5296 may put more devices in an IOMMU group. 5297 config_acs= 5298 Format: 5299 <ACS flags>@<pci_dev>[; ...] 5300 Specify one or more PCI devices (in the format 5301 specified above) optionally prepended with flags 5302 and separated by semicolons. The respective 5303 capabilities will be enabled, disabled or 5304 unchanged based on what is specified in 5305 flags. 5306 5307 ACS Flags is defined as follows: 5308 bit-0 : ACS Source Validation 5309 bit-1 : ACS Translation Blocking 5310 bit-2 : ACS P2P Request Redirect 5311 bit-3 : ACS P2P Completion Redirect 5312 bit-4 : ACS Upstream Forwarding 5313 bit-5 : ACS P2P Egress Control 5314 bit-6 : ACS Direct Translated P2P 5315 Each bit can be marked as: 5316 '0' – force disabled 5317 '1' – force enabled 5318 'x' – unchanged 5319 For example, 5320 pci=config_acs=10x@pci:0:0 5321 would configure all devices that support 5322 ACS to enable P2P Request Redirect, disable 5323 Translation Blocking, and leave Source 5324 Validation unchanged from whatever power-up 5325 or firmware set it to. 5326 5327 Note: this may remove isolation between devices 5328 and may put more devices in an IOMMU group. 5329 force_floating [S390] Force usage of floating interrupts. 5330 nomio [S390] Do not use MIO instructions. 5331 norid [S390] ignore the RID field and force use of 5332 one PCI domain per PCI function 5333 notph [PCIE] If the PCIE_TPH kernel config parameter 5334 is enabled, this kernel boot option can be used 5335 to disable PCIe TLP Processing Hints support 5336 system-wide. 5337 5338 pcie_aspm= [PCIE] Forcibly enable or ignore PCIe Active State Power 5339 Management. 5340 off Don't touch ASPM configuration at all. Leave any 5341 configuration done by firmware unchanged. 5342 force Enable ASPM even on devices that claim not to support it. 5343 WARNING: Forcing ASPM on may cause system lockups. 5344 5345 pcie_ports= [PCIE] PCIe port services handling: 5346 native Use native PCIe services (PME, AER, DPC, PCIe hotplug) 5347 even if the platform doesn't give the OS permission to 5348 use them. This may cause conflicts if the platform 5349 also tries to use these services. 5350 dpc-native Use native PCIe service for DPC only. May 5351 cause conflicts if firmware uses AER or DPC. 5352 compat Disable native PCIe services (PME, AER, DPC, PCIe 5353 hotplug). 5354 5355 pcie_port_pm= [PCIE] PCIe port power management handling: 5356 off Disable power management of all PCIe ports 5357 force Forcibly enable power management of all PCIe ports 5358 5359 pcie_pme= [PCIE,PM] Native PCIe PME signaling options: 5360 nomsi Do not use MSI for native PCIe PME signaling (this makes 5361 all PCIe root ports use INTx for all services). 5362 5363 pcmv= [HW,PCMCIA] BadgePAD 4 5364 5365 pd_ignore_unused 5366 [PM] 5367 Keep all power-domains already enabled by bootloader on, 5368 even if no driver has claimed them. This is useful 5369 for debug and development, but should not be 5370 needed on a platform with proper driver support. 5371 5372 pdcchassis= [PARISC,HW] Disable/Enable PDC Chassis Status codes at 5373 boot time. 5374 Format: { 0 | 1 } 5375 See arch/parisc/kernel/pdc_chassis.c 5376 5377 percpu_alloc= [MM,EARLY] 5378 Select which percpu first chunk allocator to use. 5379 Currently supported values are "embed" and "page". 5380 Archs may support subset or none of the selections. 5381 See comments in mm/percpu.c for details on each 5382 allocator. This parameter is primarily for debugging 5383 and performance comparison. 5384 5385 pirq= [SMP,APIC] Manual mp-table setup 5386 See Documentation/arch/x86/i386/IO-APIC.rst. 5387 5388 plip= [PPT,NET] Parallel port network link 5389 Format: { parport<nr> | timid | 0 } 5390 See also Documentation/admin-guide/parport.rst. 5391 5392 pmtmr= [X86] Manual setup of pmtmr I/O Port. 5393 Override pmtimer IOPort with a hex value. 5394 e.g. pmtmr=0x508 5395 5396 pmu_override= [PPC] Override the PMU. 5397 This option takes over the PMU facility, so it is no 5398 longer usable by perf. Setting this option starts the 5399 PMU counters by setting MMCR0 to 0 (the FC bit is 5400 cleared). If a number is given, then MMCR1 is set to 5401 that number, otherwise (e.g., 'pmu_override=on'), MMCR1 5402 remains 0. 5403 5404 pm_async= [PM] 5405 Format: off 5406 This parameter sets the initial value of the 5407 /sys/power/pm_async sysfs knob at boot time. 5408 If set to "off", disables asynchronous suspend and 5409 resume of devices during system-wide power transitions. 5410 This can be useful on platforms where device 5411 dependencies are not well-defined, or for debugging 5412 power management issues. Asynchronous operations are 5413 enabled by default. 5414 5415 5416 pm_debug_messages [SUSPEND,KNL] 5417 Enable suspend/resume debug messages during boot up. 5418 5419 pnp.debug=1 [PNP] 5420 Enable PNP debug messages (depends on the 5421 CONFIG_PNP_DEBUG_MESSAGES option). Change at run-time 5422 via /sys/module/pnp/parameters/debug. We always show 5423 current resource usage; turning this on also shows 5424 possible settings and some assignment information. 5425 5426 pnpacpi= [ACPI] 5427 { off } 5428 5429 pnpbios= [ISAPNP] 5430 { on | off | curr | res | no-curr | no-res } 5431 5432 pnp_reserve_irq= 5433 [ISAPNP] Exclude IRQs for the autoconfiguration 5434 5435 pnp_reserve_dma= 5436 [ISAPNP] Exclude DMAs for the autoconfiguration 5437 5438 pnp_reserve_io= [ISAPNP] Exclude I/O ports for the autoconfiguration 5439 Ranges are in pairs (I/O port base and size). 5440 5441 pnp_reserve_mem= 5442 [ISAPNP] Exclude memory regions for the 5443 autoconfiguration. 5444 Ranges are in pairs (memory base and size). 5445 5446 ports= [IP_VS_FTP] IPVS ftp helper module 5447 Default is 21. 5448 Up to 8 (IP_VS_APP_MAX_PORTS) ports 5449 may be specified. 5450 Format: <port>,<port>.... 5451 5452 possible_cpus= [SMP,S390,X86] 5453 Format: <unsigned int> 5454 Set the number of possible CPUs, overriding the 5455 regular discovery mechanisms (such as ACPI/FW, etc). 5456 5457 powersave=off [PPC] This option disables power saving features. 5458 It specifically disables cpuidle and sets the 5459 platform machine description specific power_save 5460 function to NULL. On Idle the CPU just reduces 5461 execution priority. 5462 5463 ppc_strict_facility_enable 5464 [PPC,ENABLE] This option catches any kernel floating point, 5465 Altivec, VSX and SPE outside of regions specifically 5466 allowed (eg kernel_enable_fpu()/kernel_disable_fpu()). 5467 There is some performance impact when enabling this. 5468 5469 ppc_tm= [PPC,EARLY] 5470 Format: {"off"} 5471 Disable Hardware Transactional Memory 5472 5473 preempt= [KNL] 5474 Select preemption mode if you have CONFIG_PREEMPT_DYNAMIC 5475 none - Limited to cond_resched() calls 5476 voluntary - Limited to cond_resched() and might_sleep() calls 5477 full - Any section that isn't explicitly preempt disabled 5478 can be preempted anytime. Tasks will also yield 5479 contended spinlocks (if the critical section isn't 5480 explicitly preempt disabled beyond the lock itself). 5481 lazy - Scheduler controlled. Similar to full but instead 5482 of preempting the task immediately, the task gets 5483 one HZ tick time to yield itself before the 5484 preemption will be forced. One preemption is when the 5485 task returns to user space. 5486 5487 print-fatal-signals= 5488 [KNL] debug: print fatal signals 5489 5490 If enabled, warn about various signal handling 5491 related application anomalies: too many signals, 5492 too many POSIX.1 timers, fatal signals causing a 5493 coredump - etc. 5494 5495 If you hit the warning due to signal overflow, 5496 you might want to try "ulimit -i unlimited". 5497 5498 default: off. 5499 5500 printk.always_kmsg_dump= 5501 Trigger kmsg_dump for cases other than kernel oops or 5502 panics 5503 Format: <bool> (1/Y/y=enable, 0/N/n=disable) 5504 default: disabled 5505 5506 printk.console_no_auto_verbose= 5507 Disable console loglevel raise on oops, panic 5508 or lockdep-detected issues (only if lock debug is on). 5509 With an exception to setups with low baudrate on 5510 serial console, keeping this 0 is a good choice 5511 in order to provide more debug information. 5512 Format: <bool> 5513 default: 0 (auto_verbose is enabled) 5514 5515 printk.debug_non_panic_cpus= 5516 Allows storing messages from non-panic CPUs into 5517 the printk log buffer during panic(). They are 5518 flushed to consoles by the panic-CPU on 5519 a best-effort basis. 5520 Format: <bool> (1/Y/y=enable, 0/N/n=disable) 5521 Default: disabled 5522 5523 printk.devkmsg={on,off,ratelimit} 5524 Control writing to /dev/kmsg. 5525 on - unlimited logging to /dev/kmsg from userspace 5526 off - logging to /dev/kmsg disabled 5527 ratelimit - ratelimit the logging 5528 Default: ratelimit 5529 5530 printk.time= Show timing data prefixed to each printk message line 5531 Format: <bool> (1/Y/y=enable, 0/N/n=disable) 5532 5533 proc_mem.force_override= [KNL] 5534 Format: {always | ptrace | never} 5535 Traditionally /proc/pid/mem allows memory permissions to be 5536 overridden without restrictions. This option may be set to 5537 restrict that. Can be one of: 5538 - 'always': traditional behavior always allows mem overrides. 5539 - 'ptrace': only allow mem overrides for active ptracers. 5540 - 'never': never allow mem overrides. 5541 If not specified, default is the CONFIG_PROC_MEM_* choice. 5542 5543 processor.max_cstate= [HW,ACPI] 5544 Limit processor to maximum C-state 5545 max_cstate=9 overrides any DMI blacklist limit. 5546 5547 processor.nocst [HW,ACPI] 5548 Ignore the _CST method to determine C-states, 5549 instead using the legacy FADT method 5550 5551 profile= [KNL] Enable kernel profiling via /proc/profile 5552 Format: [<profiletype>,]<number> 5553 Param: <profiletype>: "schedule" or "kvm" 5554 [defaults to kernel profiling] 5555 Param: "schedule" - profile schedule points. 5556 Param: "kvm" - profile VM exits. 5557 Param: <number> - step/bucket size as a power of 2 for 5558 statistical time based profiling. 5559 5560 prot_virt= [S390] enable hosting protected virtual machines 5561 isolated from the hypervisor (if hardware supports 5562 that). If enabled, the default kernel base address 5563 might be overridden even when Kernel Address Space 5564 Layout Randomization is disabled. 5565 Format: <bool> 5566 5567 psi= [KNL] Enable or disable pressure stall information 5568 tracking. 5569 Format: <bool> 5570 5571 psmouse.proto= [HW,MOUSE] Highest PS2 mouse protocol extension to 5572 probe for; one of (bare|imps|exps|lifebook|any). 5573 psmouse.rate= [HW,MOUSE] Set desired mouse report rate, in reports 5574 per second. 5575 psmouse.resetafter= [HW,MOUSE] 5576 Try to reset the device after so many bad packets 5577 (0 = never). 5578 psmouse.resolution= 5579 [HW,MOUSE] Set desired mouse resolution, in dpi. 5580 psmouse.smartscroll= 5581 [HW,MOUSE] Controls Logitech smartscroll autorepeat. 5582 0 = disabled, 1 = enabled (default). 5583 5584 pstore.backend= Specify the name of the pstore backend to use 5585 5586 pti= [X86-64] Control Page Table Isolation of user and 5587 kernel address spaces. Disabling this feature 5588 removes hardening, but improves performance of 5589 system calls and interrupts. 5590 5591 on - unconditionally enable 5592 off - unconditionally disable 5593 auto - kernel detects whether your CPU model is 5594 vulnerable to issues that PTI mitigates 5595 5596 Not specifying this option is equivalent to pti=auto. 5597 5598 pty.legacy_count= 5599 [KNL] Number of legacy pty's. Overwrites compiled-in 5600 default number. 5601 5602 quiet [KNL,EARLY] Disable most log messages 5603 5604 r128= [HW,DRM] 5605 5606 radix_hcall_invalidate=on [PPC/PSERIES] 5607 Disable RADIX GTSE feature and use hcall for TLB 5608 invalidate. 5609 5610 raid= [HW,RAID] 5611 See Documentation/admin-guide/md.rst. 5612 5613 ramdisk_size= [RAM] Sizes of RAM disks in kilobytes 5614 See Documentation/admin-guide/blockdev/ramdisk.rst. 5615 5616 ramdisk_start= [Deprecated,RAM] RAM disk image start address 5617 5618 random.trust_cpu=off 5619 [KNL,EARLY] Disable trusting the use of the CPU's 5620 random number generator (if available) to 5621 initialize the kernel's RNG. 5622 5623 random.trust_bootloader=off 5624 [KNL,EARLY] Disable trusting the use of the a seed 5625 passed by the bootloader (if available) to 5626 initialize the kernel's RNG. 5627 5628 randomize_kstack_offset= 5629 [KNL,EARLY] Enable or disable kernel stack offset 5630 randomization, which provides roughly 5 bits of 5631 entropy, frustrating memory corruption attacks 5632 that depend on stack address determinism or 5633 cross-syscall address exposures. This is only 5634 available on architectures that have defined 5635 CONFIG_HAVE_ARCH_RANDOMIZE_KSTACK_OFFSET. 5636 Format: <bool> (1/Y/y=enable, 0/N/n=disable) 5637 Default is CONFIG_RANDOMIZE_KSTACK_OFFSET_DEFAULT. 5638 5639 ras=option[,option,...] [KNL] RAS-specific options 5640 5641 cec_disable [X86] 5642 Disable the Correctable Errors Collector, 5643 see CONFIG_RAS_CEC help text. 5644 5645 rcu_nocbs[=cpu-list] 5646 [KNL] The optional argument is a cpu list, 5647 as described above. 5648 5649 In kernels built with CONFIG_RCU_NOCB_CPU=y, 5650 enable the no-callback CPU mode, which prevents 5651 such CPUs' callbacks from being invoked in 5652 softirq context. Invocation of such CPUs' RCU 5653 callbacks will instead be offloaded to "rcuox/N" 5654 kthreads created for that purpose, where "x" is 5655 "p" for RCU-preempt, "s" for RCU-sched, and "g" 5656 for the kthreads that mediate grace periods; and 5657 "N" is the CPU number. This reduces OS jitter on 5658 the offloaded CPUs, which can be useful for HPC 5659 and real-time workloads. It can also improve 5660 energy efficiency for asymmetric multiprocessors. 5661 5662 If a cpulist is passed as an argument, the specified 5663 list of CPUs is set to no-callback mode from boot. 5664 5665 Otherwise, if the '=' sign and the cpulist 5666 arguments are omitted, no CPU will be set to 5667 no-callback mode from boot but the mode may be 5668 toggled at runtime via cpusets. 5669 5670 Note that this argument takes precedence over 5671 the CONFIG_RCU_NOCB_CPU_DEFAULT_ALL option. 5672 5673 rcu_nocb_poll [KNL] 5674 Rather than requiring that offloaded CPUs 5675 (specified by rcu_nocbs= above) explicitly 5676 awaken the corresponding "rcuoN" kthreads, 5677 make these kthreads poll for callbacks. 5678 This improves the real-time response for the 5679 offloaded CPUs by relieving them of the need to 5680 wake up the corresponding kthread, but degrades 5681 energy efficiency by requiring that the kthreads 5682 periodically wake up to do the polling. 5683 5684 rcutree.blimit= [KNL] 5685 Set maximum number of finished RCU callbacks to 5686 process in one batch. 5687 5688 rcutree.csd_lock_suppress_rcu_stall= [KNL] 5689 Do only a one-line RCU CPU stall warning when 5690 there is an ongoing too-long CSD-lock wait. 5691 5692 rcutree.do_rcu_barrier= [KNL] 5693 Request a call to rcu_barrier(). This is 5694 throttled so that userspace tests can safely 5695 hammer on the sysfs variable if they so choose. 5696 If triggered before the RCU grace-period machinery 5697 is fully active, this will error out with EAGAIN. 5698 5699 rcutree.dump_tree= [KNL] 5700 Dump the structure of the rcu_node combining tree 5701 out at early boot. This is used for diagnostic 5702 purposes, to verify correct tree setup. 5703 5704 rcutree.gp_cleanup_delay= [KNL] 5705 Set the number of jiffies to delay each step of 5706 RCU grace-period cleanup. 5707 5708 rcutree.gp_init_delay= [KNL] 5709 Set the number of jiffies to delay each step of 5710 RCU grace-period initialization. 5711 5712 rcutree.gp_preinit_delay= [KNL] 5713 Set the number of jiffies to delay each step of 5714 RCU grace-period pre-initialization, that is, 5715 the propagation of recent CPU-hotplug changes up 5716 the rcu_node combining tree. 5717 5718 rcutree.jiffies_till_first_fqs= [KNL] 5719 Set delay from grace-period initialization to 5720 first attempt to force quiescent states. 5721 Units are jiffies, minimum value is zero, 5722 and maximum value is HZ. 5723 5724 rcutree.jiffies_till_next_fqs= [KNL] 5725 Set delay between subsequent attempts to force 5726 quiescent states. Units are jiffies, minimum 5727 value is one, and maximum value is HZ. 5728 5729 rcutree.jiffies_till_sched_qs= [KNL] 5730 Set required age in jiffies for a 5731 given grace period before RCU starts 5732 soliciting quiescent-state help from 5733 rcu_note_context_switch() and cond_resched(). 5734 If not specified, the kernel will calculate 5735 a value based on the most recent settings 5736 of rcutree.jiffies_till_first_fqs 5737 and rcutree.jiffies_till_next_fqs. 5738 This calculated value may be viewed in 5739 rcutree.jiffies_to_sched_qs. Any attempt to set 5740 rcutree.jiffies_to_sched_qs will be cheerfully 5741 overwritten. 5742 5743 rcutree.kthread_prio= [KNL,BOOT] 5744 Set the SCHED_FIFO priority of the RCU per-CPU 5745 kthreads (rcuc/N). This value is also used for 5746 the priority of the RCU boost threads (rcub/N) 5747 and for the RCU grace-period kthreads (rcu_bh, 5748 rcu_preempt, and rcu_sched). If RCU_BOOST is 5749 set, valid values are 1-99 and the default is 1 5750 (the least-favored priority). Otherwise, when 5751 RCU_BOOST is not set, valid values are 0-99 and 5752 the default is zero (non-realtime operation). 5753 When RCU_NOCB_CPU is set, also adjust the 5754 priority of NOCB callback kthreads. 5755 5756 rcutree.nocb_nobypass_lim_per_jiffy= [KNL] 5757 On callback-offloaded (rcu_nocbs) CPUs, 5758 RCU reduces the lock contention that would 5759 otherwise be caused by callback floods through 5760 use of the ->nocb_bypass list. However, in the 5761 common non-flooded case, RCU queues directly to 5762 the main ->cblist in order to avoid the extra 5763 overhead of the ->nocb_bypass list and its lock. 5764 But if there are too many callbacks queued during 5765 a single jiffy, RCU pre-queues the callbacks into 5766 the ->nocb_bypass queue. The definition of "too 5767 many" is supplied by this kernel boot parameter. 5768 5769 rcutree.nohz_full_patience_delay= [KNL] 5770 On callback-offloaded (rcu_nocbs) CPUs, avoid 5771 disturbing RCU unless the grace period has 5772 reached the specified age in milliseconds. 5773 Defaults to zero. Large values will be capped 5774 at five seconds. All values will be rounded down 5775 to the nearest value representable by jiffies. 5776 5777 rcutree.qhimark= [KNL] 5778 Set threshold of queued RCU callbacks beyond which 5779 batch limiting is disabled. 5780 5781 rcutree.qlowmark= [KNL] 5782 Set threshold of queued RCU callbacks below which 5783 batch limiting is re-enabled. 5784 5785 rcutree.qovld= [KNL] 5786 Set threshold of queued RCU callbacks beyond which 5787 RCU's force-quiescent-state scan will aggressively 5788 enlist help from cond_resched() and sched IPIs to 5789 help CPUs more quickly reach quiescent states. 5790 Set to less than zero to make this be set based 5791 on rcutree.qhimark at boot time and to zero to 5792 disable more aggressive help enlistment. 5793 5794 rcutree.rcu_delay_page_cache_fill_msec= [KNL] 5795 Set the page-cache refill delay (in milliseconds) 5796 in response to low-memory conditions. The range 5797 of permitted values is in the range 0:100000. 5798 5799 rcutree.rcu_divisor= [KNL] 5800 Set the shift-right count to use to compute 5801 the callback-invocation batch limit bl from 5802 the number of callbacks queued on this CPU. 5803 The result will be bounded below by the value of 5804 the rcutree.blimit kernel parameter. Every bl 5805 callbacks, the softirq handler will exit in 5806 order to allow the CPU to do other work. 5807 5808 Please note that this callback-invocation batch 5809 limit applies only to non-offloaded callback 5810 invocation. Offloaded callbacks are instead 5811 invoked in the context of an rcuoc kthread, which 5812 scheduler will preempt as it does any other task. 5813 5814 rcutree.rcu_fanout_exact= [KNL] 5815 Disable autobalancing of the rcu_node combining 5816 tree. This is used by rcutorture, and might 5817 possibly be useful for architectures having high 5818 cache-to-cache transfer latencies. 5819 5820 rcutree.rcu_fanout_leaf= [KNL] 5821 Change the number of CPUs assigned to each 5822 leaf rcu_node structure. Useful for very 5823 large systems, which will choose the value 64, 5824 and for NUMA systems with large remote-access 5825 latencies, which will choose a value aligned 5826 with the appropriate hardware boundaries. 5827 5828 rcutree.rcu_min_cached_objs= [KNL] 5829 Minimum number of objects which are cached and 5830 maintained per one CPU. Object size is equal 5831 to PAGE_SIZE. The cache allows to reduce the 5832 pressure to page allocator, also it makes the 5833 whole algorithm to behave better in low memory 5834 condition. 5835 5836 rcutree.rcu_nocb_gp_stride= [KNL] 5837 Set the number of NOCB callback kthreads in 5838 each group, which defaults to the square root 5839 of the number of CPUs. Larger numbers reduce 5840 the wakeup overhead on the global grace-period 5841 kthread, but increases that same overhead on 5842 each group's NOCB grace-period kthread. 5843 5844 rcutree.rcu_kick_kthreads= [KNL] 5845 Cause the grace-period kthread to get an extra 5846 wake_up() if it sleeps three times longer than 5847 it should at force-quiescent-state time. 5848 This wake_up() will be accompanied by a 5849 WARN_ONCE() splat and an ftrace_dump(). 5850 5851 rcutree.rcu_resched_ns= [KNL] 5852 Limit the time spend invoking a batch of RCU 5853 callbacks to the specified number of nanoseconds. 5854 By default, this limit is checked only once 5855 every 32 callbacks in order to limit the pain 5856 inflicted by local_clock() overhead. 5857 5858 rcutree.rcu_unlock_delay= [KNL] 5859 In CONFIG_RCU_STRICT_GRACE_PERIOD=y kernels, 5860 this specifies an rcu_read_unlock()-time delay 5861 in microseconds. This defaults to zero. 5862 Larger delays increase the probability of 5863 catching RCU pointer leaks, that is, buggy use 5864 of RCU-protected pointers after the relevant 5865 rcu_read_unlock() has completed. 5866 5867 rcutree.sysrq_rcu= [KNL] 5868 Commandeer a sysrq key to dump out Tree RCU's 5869 rcu_node tree with an eye towards determining 5870 why a new grace period has not yet started. 5871 5872 rcutree.use_softirq= [KNL] 5873 If set to zero, move all RCU_SOFTIRQ processing to 5874 per-CPU rcuc kthreads. Defaults to a non-zero 5875 value, meaning that RCU_SOFTIRQ is used by default. 5876 Specify rcutree.use_softirq=0 to use rcuc kthreads. 5877 5878 But note that CONFIG_PREEMPT_RT=y kernels disable 5879 this kernel boot parameter, forcibly setting it 5880 to zero. 5881 5882 rcutree.enable_rcu_lazy= [KNL] 5883 To save power, batch RCU callbacks and flush after 5884 delay, memory pressure or callback list growing too 5885 big. 5886 5887 rcutree.rcu_normal_wake_from_gp= [KNL] 5888 Reduces a latency of synchronize_rcu() call. This approach 5889 maintains its own track of synchronize_rcu() callers, so it 5890 does not interact with regular callbacks because it does not 5891 use a call_rcu[_hurry]() path. Please note, this is for a 5892 normal grace period. 5893 5894 How to enable it: 5895 5896 echo 1 > /sys/module/rcutree/parameters/rcu_normal_wake_from_gp 5897 or pass a boot parameter "rcutree.rcu_normal_wake_from_gp=1" 5898 5899 Default is 1 if num_possible_cpus() <= 16 and it is not explicitly 5900 disabled by the boot parameter passing 0. 5901 5902 rcuscale.gp_async= [KNL] 5903 Measure performance of asynchronous 5904 grace-period primitives such as call_rcu(). 5905 5906 rcuscale.gp_async_max= [KNL] 5907 Specify the maximum number of outstanding 5908 callbacks per writer thread. When a writer 5909 thread exceeds this limit, it invokes the 5910 corresponding flavor of rcu_barrier() to allow 5911 previously posted callbacks to drain. 5912 5913 rcuscale.gp_exp= [KNL] 5914 Measure performance of expedited synchronous 5915 grace-period primitives. 5916 5917 rcuscale.holdoff= [KNL] 5918 Set test-start holdoff period. The purpose of 5919 this parameter is to delay the start of the 5920 test until boot completes in order to avoid 5921 interference. 5922 5923 rcuscale.kfree_by_call_rcu= [KNL] 5924 In kernels built with CONFIG_RCU_LAZY=y, test 5925 call_rcu() instead of kfree_rcu(). 5926 5927 rcuscale.kfree_mult= [KNL] 5928 Instead of allocating an object of size kfree_obj, 5929 allocate one of kfree_mult * sizeof(kfree_obj). 5930 Defaults to 1. 5931 5932 rcuscale.kfree_rcu_test= [KNL] 5933 Set to measure performance of kfree_rcu() flooding. 5934 5935 rcuscale.kfree_rcu_test_double= [KNL] 5936 Test the double-argument variant of kfree_rcu(). 5937 If this parameter has the same value as 5938 rcuscale.kfree_rcu_test_single, both the single- 5939 and double-argument variants are tested. 5940 5941 rcuscale.kfree_rcu_test_single= [KNL] 5942 Test the single-argument variant of kfree_rcu(). 5943 If this parameter has the same value as 5944 rcuscale.kfree_rcu_test_double, both the single- 5945 and double-argument variants are tested. 5946 5947 rcuscale.kfree_nthreads= [KNL] 5948 The number of threads running loops of kfree_rcu(). 5949 5950 rcuscale.kfree_alloc_num= [KNL] 5951 Number of allocations and frees done in an iteration. 5952 5953 rcuscale.kfree_loops= [KNL] 5954 Number of loops doing rcuscale.kfree_alloc_num number 5955 of allocations and frees. 5956 5957 rcuscale.minruntime= [KNL] 5958 Set the minimum test run time in seconds. This 5959 does not affect the data-collection interval, 5960 but instead allows better measurement of things 5961 like CPU consumption. 5962 5963 rcuscale.nreaders= [KNL] 5964 Set number of RCU readers. The value -1 selects 5965 N, where N is the number of CPUs. A value 5966 "n" less than -1 selects N-n+1, where N is again 5967 the number of CPUs. For example, -2 selects N 5968 (the number of CPUs), -3 selects N+1, and so on. 5969 A value of "n" less than or equal to -N selects 5970 a single reader. 5971 5972 rcuscale.nwriters= [KNL] 5973 Set number of RCU writers. The values operate 5974 the same as for rcuscale.nreaders. 5975 N, where N is the number of CPUs 5976 5977 rcuscale.scale_type= [KNL] 5978 Specify the RCU implementation to test. 5979 5980 rcuscale.shutdown= [KNL] 5981 Shut the system down after performance tests 5982 complete. This is useful for hands-off automated 5983 testing. 5984 5985 rcuscale.verbose= [KNL] 5986 Enable additional printk() statements. 5987 5988 rcuscale.writer_holdoff= [KNL] 5989 Write-side holdoff between grace periods, 5990 in microseconds. The default of zero says 5991 no holdoff. 5992 5993 rcuscale.writer_holdoff_jiffies= [KNL] 5994 Additional write-side holdoff between grace 5995 periods, but in jiffies. The default of zero 5996 says no holdoff. 5997 5998 rcutorture.fqs_duration= [KNL] 5999 Set duration of force_quiescent_state bursts 6000 in microseconds. 6001 6002 rcutorture.fqs_holdoff= [KNL] 6003 Set holdoff time within force_quiescent_state bursts 6004 in microseconds. 6005 6006 rcutorture.fqs_stutter= [KNL] 6007 Set wait time between force_quiescent_state bursts 6008 in seconds. 6009 6010 rcutorture.fwd_progress= [KNL] 6011 Specifies the number of kthreads to be used 6012 for RCU grace-period forward-progress testing 6013 for the types of RCU supporting this notion. 6014 Defaults to 1 kthread, values less than zero or 6015 greater than the number of CPUs cause the number 6016 of CPUs to be used. 6017 6018 rcutorture.fwd_progress_div= [KNL] 6019 Specify the fraction of a CPU-stall-warning 6020 period to do tight-loop forward-progress testing. 6021 6022 rcutorture.fwd_progress_holdoff= [KNL] 6023 Number of seconds to wait between successive 6024 forward-progress tests. 6025 6026 rcutorture.fwd_progress_need_resched= [KNL] 6027 Enclose cond_resched() calls within checks for 6028 need_resched() during tight-loop forward-progress 6029 testing. 6030 6031 rcutorture.gp_cond= [KNL] 6032 Use conditional/asynchronous update-side 6033 normal-grace-period primitives, if available. 6034 6035 rcutorture.gp_cond_exp= [KNL] 6036 Use conditional/asynchronous update-side 6037 expedited-grace-period primitives, if available. 6038 6039 rcutorture.gp_cond_full= [KNL] 6040 Use conditional/asynchronous update-side 6041 normal-grace-period primitives that also take 6042 concurrent expedited grace periods into account, 6043 if available. 6044 6045 rcutorture.gp_cond_exp_full= [KNL] 6046 Use conditional/asynchronous update-side 6047 expedited-grace-period primitives that also take 6048 concurrent normal grace periods into account, 6049 if available. 6050 6051 rcutorture.gp_cond_wi= [KNL] 6052 Nominal wait interval for normal conditional 6053 grace periods (specified by rcutorture's 6054 gp_cond and gp_cond_full module parameters), 6055 in microseconds. The actual wait interval will 6056 be randomly selected to nanosecond granularity up 6057 to this wait interval. Defaults to 16 jiffies, 6058 for example, 16,000 microseconds on a system 6059 with HZ=1000. 6060 6061 rcutorture.gp_cond_wi_exp= [KNL] 6062 Nominal wait interval for expedited conditional 6063 grace periods (specified by rcutorture's 6064 gp_cond_exp and gp_cond_exp_full module 6065 parameters), in microseconds. The actual wait 6066 interval will be randomly selected to nanosecond 6067 granularity up to this wait interval. Defaults to 6068 128 microseconds. 6069 6070 rcutorture.gp_exp= [KNL] 6071 Use expedited update-side primitives, if available. 6072 6073 rcutorture.gp_normal= [KNL] 6074 Use normal (non-expedited) asynchronous 6075 update-side primitives, if available. 6076 6077 rcutorture.gp_poll= [KNL] 6078 Use polled update-side normal-grace-period 6079 primitives, if available. 6080 6081 rcutorture.gp_poll_exp= [KNL] 6082 Use polled update-side expedited-grace-period 6083 primitives, if available. 6084 6085 rcutorture.gp_poll_full= [KNL] 6086 Use polled update-side normal-grace-period 6087 primitives that also take concurrent expedited 6088 grace periods into account, if available. 6089 6090 rcutorture.gp_poll_exp_full= [KNL] 6091 Use polled update-side expedited-grace-period 6092 primitives that also take concurrent normal 6093 grace periods into account, if available. 6094 6095 rcutorture.gp_poll_wi= [KNL] 6096 Nominal wait interval for normal conditional 6097 grace periods (specified by rcutorture's 6098 gp_poll and gp_poll_full module parameters), 6099 in microseconds. The actual wait interval will 6100 be randomly selected to nanosecond granularity up 6101 to this wait interval. Defaults to 16 jiffies, 6102 for example, 16,000 microseconds on a system 6103 with HZ=1000. 6104 6105 rcutorture.gp_poll_wi_exp= [KNL] 6106 Nominal wait interval for expedited conditional 6107 grace periods (specified by rcutorture's 6108 gp_poll_exp and gp_poll_exp_full module 6109 parameters), in microseconds. The actual wait 6110 interval will be randomly selected to nanosecond 6111 granularity up to this wait interval. Defaults to 6112 128 microseconds. 6113 6114 rcutorture.gp_sync= [KNL] 6115 Use normal (non-expedited) synchronous 6116 update-side primitives, if available. If all 6117 of rcutorture.gp_cond=, rcutorture.gp_exp=, 6118 rcutorture.gp_normal=, and rcutorture.gp_sync= 6119 are zero, rcutorture acts as if is interpreted 6120 they are all non-zero. 6121 6122 rcutorture.gpwrap_lag= [KNL] 6123 Enable grace-period wrap lag testing. Setting 6124 to false prevents the gpwrap lag test from 6125 running. Default is true. 6126 6127 rcutorture.gpwrap_lag_gps= [KNL] 6128 Set the value for grace-period wrap lag during 6129 active lag testing periods. This controls how many 6130 grace periods differences we tolerate between 6131 rdp and rnp's gp_seq before setting overflow flag. 6132 The default is always set to 8. 6133 6134 rcutorture.gpwrap_lag_cycle_mins= [KNL] 6135 Set the total cycle duration for gpwrap lag 6136 testing in minutes. This is the total time for 6137 one complete cycle of active and inactive 6138 testing periods. Default is 30 minutes. 6139 6140 rcutorture.gpwrap_lag_active_mins= [KNL] 6141 Set the duration for which gpwrap lag is active 6142 within each cycle, in minutes. During this time, 6143 the grace-period wrap lag will be set to the 6144 value specified by gpwrap_lag_gps. Default is 6145 5 minutes. 6146 6147 rcutorture.irqreader= [KNL] 6148 Run RCU readers from irq handlers, or, more 6149 accurately, from a timer handler. Not all RCU 6150 flavors take kindly to this sort of thing. 6151 6152 rcutorture.leakpointer= [KNL] 6153 Leak an RCU-protected pointer out of the reader. 6154 This can of course result in splats, and is 6155 intended to test the ability of things like 6156 CONFIG_RCU_STRICT_GRACE_PERIOD=y to detect 6157 such leaks. 6158 6159 rcutorture.n_barrier_cbs= [KNL] 6160 Set callbacks/threads for rcu_barrier() testing. 6161 6162 rcutorture.nfakewriters= [KNL] 6163 Set number of concurrent RCU writers. These just 6164 stress RCU, they don't participate in the actual 6165 test, hence the "fake". 6166 6167 rcutorture.nocbs_nthreads= [KNL] 6168 Set number of RCU callback-offload togglers. 6169 Zero (the default) disables toggling. 6170 6171 rcutorture.nocbs_toggle= [KNL] 6172 Set the delay in milliseconds between successive 6173 callback-offload toggling attempts. 6174 6175 rcutorture.nreaders= [KNL] 6176 Set number of RCU readers. The value -1 selects 6177 N-1, where N is the number of CPUs. A value 6178 "n" less than -1 selects N-n-2, where N is again 6179 the number of CPUs. For example, -2 selects N 6180 (the number of CPUs), -3 selects N+1, and so on. 6181 6182 rcutorture.object_debug= [KNL] 6183 Enable debug-object double-call_rcu() testing. 6184 6185 rcutorture.onoff_holdoff= [KNL] 6186 Set time (s) after boot for CPU-hotplug testing. 6187 6188 rcutorture.onoff_interval= [KNL] 6189 Set time (jiffies) between CPU-hotplug operations, 6190 or zero to disable CPU-hotplug testing. 6191 6192 rcutorture.preempt_duration= [KNL] 6193 Set duration (in milliseconds) of preemptions 6194 by a high-priority FIFO real-time task. Set to 6195 zero (the default) to disable. The CPUs to 6196 preempt are selected randomly from the set that 6197 are online at a given point in time. Races with 6198 CPUs going offline are ignored, with that attempt 6199 at preemption skipped. 6200 6201 rcutorture.preempt_interval= [KNL] 6202 Set interval (in milliseconds, defaulting to one 6203 second) between preemptions by a high-priority 6204 FIFO real-time task. This delay is mediated 6205 by an hrtimer and is further fuzzed to avoid 6206 inadvertent synchronizations. 6207 6208 rcutorture.read_exit_burst= [KNL] 6209 The number of times in a given read-then-exit 6210 episode that a set of read-then-exit kthreads 6211 is spawned. 6212 6213 rcutorture.read_exit_delay= [KNL] 6214 The delay, in seconds, between successive 6215 read-then-exit testing episodes. 6216 6217 rcutorture.reader_flavor= [KNL] 6218 A bit mask indicating which readers to use. 6219 If there is more than one bit set, the readers 6220 are entered from low-order bit up, and are 6221 exited in the opposite order. For SRCU, the 6222 0x1 bit is normal readers, 0x2 NMI-safe readers, 6223 and 0x4 light-weight readers. 6224 6225 rcutorture.shuffle_interval= [KNL] 6226 Set task-shuffle interval (s). Shuffling tasks 6227 allows some CPUs to go into dyntick-idle mode 6228 during the rcutorture test. 6229 6230 rcutorture.shutdown_secs= [KNL] 6231 Set time (s) after boot system shutdown. This 6232 is useful for hands-off automated testing. 6233 6234 rcutorture.stall_cpu= [KNL] 6235 Duration of CPU stall (s) to test RCU CPU stall 6236 warnings, zero to disable. 6237 6238 rcutorture.stall_cpu_block= [KNL] 6239 Sleep while stalling if set. This will result 6240 in warnings from preemptible RCU in addition to 6241 any other stall-related activity. Note that 6242 in kernels built with CONFIG_PREEMPTION=n and 6243 CONFIG_PREEMPT_COUNT=y, this parameter will 6244 cause the CPU to pass through a quiescent state. 6245 Given CONFIG_PREEMPTION=n, this will suppress 6246 RCU CPU stall warnings, but will instead result 6247 in scheduling-while-atomic splats. 6248 6249 Use of this module parameter results in splats. 6250 6251 6252 rcutorture.stall_cpu_holdoff= [KNL] 6253 Time to wait (s) after boot before inducing stall. 6254 6255 rcutorture.stall_cpu_irqsoff= [KNL] 6256 Disable interrupts while stalling if set, but only 6257 on the first stall in the set. 6258 6259 rcutorture.stall_cpu_repeat= [KNL] 6260 Number of times to repeat the stall sequence, 6261 so that rcutorture.stall_cpu_repeat=3 will result 6262 in four stall sequences. 6263 6264 rcutorture.stall_gp_kthread= [KNL] 6265 Duration (s) of forced sleep within RCU 6266 grace-period kthread to test RCU CPU stall 6267 warnings, zero to disable. If both stall_cpu 6268 and stall_gp_kthread are specified, the 6269 kthread is starved first, then the CPU. 6270 6271 rcutorture.stat_interval= [KNL] 6272 Time (s) between statistics printk()s. 6273 6274 rcutorture.stutter= [KNL] 6275 Time (s) to stutter testing, for example, specifying 6276 five seconds causes the test to run for five seconds, 6277 wait for five seconds, and so on. This tests RCU's 6278 ability to transition abruptly to and from idle. 6279 6280 rcutorture.test_boost= [KNL] 6281 Test RCU priority boosting? 0=no, 1=maybe, 2=yes. 6282 "Maybe" means test if the RCU implementation 6283 under test support RCU priority boosting. 6284 6285 rcutorture.test_boost_duration= [KNL] 6286 Duration (s) of each individual boost test. 6287 6288 rcutorture.test_boost_holdoff= [KNL] 6289 Holdoff time (s) from start of test to the start 6290 of RCU priority-boost testing. Defaults to zero, 6291 that is, no holdoff. 6292 6293 rcutorture.test_boost_interval= [KNL] 6294 Interval (s) between each boost test. 6295 6296 rcutorture.test_no_idle_hz= [KNL] 6297 Test RCU's dyntick-idle handling. See also the 6298 rcutorture.shuffle_interval parameter. 6299 6300 rcutorture.torture_type= [KNL] 6301 Specify the RCU implementation to test. 6302 6303 rcutorture.verbose= [KNL] 6304 Enable additional printk() statements. 6305 6306 rcupdate.rcu_cpu_stall_ftrace_dump= [KNL] 6307 Dump ftrace buffer after reporting RCU CPU 6308 stall warning. 6309 6310 rcupdate.rcu_cpu_stall_notifiers= [KNL] 6311 Provide RCU CPU stall notifiers, but see the 6312 warnings in the RCU_CPU_STALL_NOTIFIER Kconfig 6313 option's help text. TL;DR: You almost certainly 6314 do not want rcupdate.rcu_cpu_stall_notifiers. 6315 6316 rcupdate.rcu_cpu_stall_suppress= [KNL] 6317 Suppress RCU CPU stall warning messages. 6318 6319 rcupdate.rcu_cpu_stall_suppress_at_boot= [KNL] 6320 Suppress RCU CPU stall warning messages and 6321 rcutorture writer stall warnings that occur 6322 during early boot, that is, during the time 6323 before the init task is spawned. 6324 6325 rcupdate.rcu_cpu_stall_timeout= [KNL] 6326 Set timeout for RCU CPU stall warning messages. 6327 The value is in seconds and the maximum allowed 6328 value is 300 seconds. 6329 6330 rcupdate.rcu_exp_cpu_stall_timeout= [KNL] 6331 Set timeout for expedited RCU CPU stall warning 6332 messages. The value is in milliseconds 6333 and the maximum allowed value is 21000 6334 milliseconds. Please note that this value is 6335 adjusted to an arch timer tick resolution. 6336 Setting this to zero causes the value from 6337 rcupdate.rcu_cpu_stall_timeout to be used (after 6338 conversion from seconds to milliseconds). 6339 6340 rcupdate.rcu_cpu_stall_cputime= [KNL] 6341 Provide statistics on the cputime and count of 6342 interrupts and tasks during the sampling period. For 6343 multiple continuous RCU stalls, all sampling periods 6344 begin at half of the first RCU stall timeout. 6345 6346 rcupdate.rcu_exp_stall_task_details= [KNL] 6347 Print stack dumps of any tasks blocking the 6348 current expedited RCU grace period during an 6349 expedited RCU CPU stall warning. 6350 6351 rcupdate.rcu_expedited= [KNL] 6352 Use expedited grace-period primitives, for 6353 example, synchronize_rcu_expedited() instead 6354 of synchronize_rcu(). This reduces latency, 6355 but can increase CPU utilization, degrade 6356 real-time latency, and degrade energy efficiency. 6357 No effect on CONFIG_TINY_RCU kernels. 6358 6359 rcupdate.rcu_normal= [KNL] 6360 Use only normal grace-period primitives, 6361 for example, synchronize_rcu() instead of 6362 synchronize_rcu_expedited(). This improves 6363 real-time latency, CPU utilization, and 6364 energy efficiency, but can expose users to 6365 increased grace-period latency. This parameter 6366 overrides rcupdate.rcu_expedited. No effect on 6367 CONFIG_TINY_RCU kernels. 6368 6369 rcupdate.rcu_normal_after_boot= [KNL] 6370 Once boot has completed (that is, after 6371 rcu_end_inkernel_boot() has been invoked), use 6372 only normal grace-period primitives. No effect 6373 on CONFIG_TINY_RCU kernels. 6374 6375 But note that CONFIG_PREEMPT_RT=y kernels enables 6376 this kernel boot parameter, forcibly setting 6377 it to the value one, that is, converting any 6378 post-boot attempt at an expedited RCU grace 6379 period to instead use normal non-expedited 6380 grace-period processing. 6381 6382 rcupdate.rcu_task_collapse_lim= [KNL] 6383 Set the maximum number of callbacks present 6384 at the beginning of a grace period that allows 6385 the RCU Tasks flavors to collapse back to using 6386 a single callback queue. This switching only 6387 occurs when rcupdate.rcu_task_enqueue_lim is 6388 set to the default value of -1. 6389 6390 rcupdate.rcu_task_contend_lim= [KNL] 6391 Set the minimum number of callback-queuing-time 6392 lock-contention events per jiffy required to 6393 cause the RCU Tasks flavors to switch to per-CPU 6394 callback queuing. This switching only occurs 6395 when rcupdate.rcu_task_enqueue_lim is set to 6396 the default value of -1. 6397 6398 rcupdate.rcu_task_enqueue_lim= [KNL] 6399 Set the number of callback queues to use for the 6400 RCU Tasks family of RCU flavors. The default 6401 of -1 allows this to be automatically (and 6402 dynamically) adjusted. This parameter is intended 6403 for use in testing. 6404 6405 rcupdate.rcu_task_lazy_lim= [KNL] 6406 Number of callbacks on a given CPU that will 6407 cancel laziness on that CPU. Use -1 to disable 6408 cancellation of laziness, but be advised that 6409 doing so increases the danger of OOM due to 6410 callback flooding. 6411 6412 rcupdate.rcu_task_stall_info= [KNL] 6413 Set initial timeout in jiffies for RCU task stall 6414 informational messages, which give some indication 6415 of the problem for those not patient enough to 6416 wait for ten minutes. Informational messages are 6417 only printed prior to the stall-warning message 6418 for a given grace period. Disable with a value 6419 less than or equal to zero. Defaults to ten 6420 seconds. A change in value does not take effect 6421 until the beginning of the next grace period. 6422 6423 rcupdate.rcu_task_stall_info_mult= [KNL] 6424 Multiplier for time interval between successive 6425 RCU task stall informational messages for a given 6426 RCU tasks grace period. This value is clamped 6427 to one through ten, inclusive. It defaults to 6428 the value three, so that the first informational 6429 message is printed 10 seconds into the grace 6430 period, the second at 40 seconds, the third at 6431 160 seconds, and then the stall warning at 600 6432 seconds would prevent a fourth at 640 seconds. 6433 6434 rcupdate.rcu_task_stall_timeout= [KNL] 6435 Set timeout in jiffies for RCU task stall 6436 warning messages. Disable with a value less 6437 than or equal to zero. Defaults to ten minutes. 6438 A change in value does not take effect until 6439 the beginning of the next grace period. 6440 6441 rcupdate.rcu_tasks_lazy_ms= [KNL] 6442 Set timeout in milliseconds RCU Tasks asynchronous 6443 callback batching for call_rcu_tasks(). 6444 A negative value will take the default. A value 6445 of zero will disable batching. Batching is 6446 always disabled for synchronize_rcu_tasks(). 6447 6448 rcupdate.rcu_self_test= [KNL] 6449 Run the RCU early boot self tests 6450 6451 rdinit= [KNL] 6452 Format: <full_path> 6453 Run specified binary instead of /init from the ramdisk, 6454 used for early userspace startup. See initrd. 6455 6456 rdrand= [X86,EARLY] 6457 force - Override the decision by the kernel to hide the 6458 advertisement of RDRAND support (this affects 6459 certain AMD processors because of buggy BIOS 6460 support, specifically around the suspend/resume 6461 path). 6462 6463 rdt= [HW,X86,RDT] 6464 Turn on/off individual RDT features. List is: 6465 cmt, mbmtotal, mbmlocal, l3cat, l3cdp, l2cat, l2cdp, 6466 mba, smba, bmec, abmc, sdciae, energy[:guid], 6467 perf[:guid]. 6468 E.g. to turn on cmt and turn off mba use: 6469 rdt=cmt,!mba 6470 To turn off all energy telemetry monitoring and ensure that 6471 perf telemetry monitoring associated with guid 0x12345 6472 is enabled use: 6473 rdt=!energy,perf:0x12345 6474 6475 reboot= [KNL] 6476 Format (x86 or x86_64): 6477 [w[arm] | c[old] | h[ard] | s[oft] | g[pio]] | d[efault] \ 6478 [[,]s[mp]#### \ 6479 [[,]b[ios] | a[cpi] | k[bd] | t[riple] | e[fi] | p[ci]] \ 6480 [[,]f[orce] 6481 Where reboot_mode is one of warm (soft) or cold (hard) or gpio 6482 (prefix with 'panic_' to set mode for panic 6483 reboot only), 6484 reboot_type is one of bios, acpi, kbd, triple, efi, or pci, 6485 reboot_force is either force or not specified, 6486 reboot_cpu is s[mp]#### with #### being the processor 6487 to be used for rebooting. 6488 6489 acpi 6490 Use the ACPI RESET_REG in the FADT. If ACPI is not 6491 configured or the ACPI reset does not work, the reboot 6492 path attempts the reset using the keyboard controller. 6493 6494 bios 6495 Use the CPU reboot vector for warm reset 6496 6497 cold 6498 Set the cold reboot flag 6499 6500 default 6501 There are some built-in platform specific "quirks" 6502 - you may see: "reboot: <name> series board detected. 6503 Selecting <type> for reboots." In the case where you 6504 think the quirk is in error (e.g. you have newer BIOS, 6505 or newer board) using this option will ignore the 6506 built-in quirk table, and use the generic default 6507 reboot actions. 6508 6509 efi 6510 Use efi reset_system runtime service. If EFI is not 6511 configured or the EFI reset does not work, the reboot 6512 path attempts the reset using the keyboard controller. 6513 6514 force 6515 Don't stop other CPUs on reboot. This can make reboot 6516 more reliable in some cases. 6517 6518 kbd 6519 Use the keyboard controller. cold reset (default) 6520 6521 pci 6522 Use a write to the PCI config space register 0xcf9 to 6523 trigger reboot. 6524 6525 triple 6526 Force a triple fault (init) 6527 6528 warm 6529 Don't set the cold reboot flag 6530 6531 Using warm reset will be much faster especially on big 6532 memory systems because the BIOS will not go through 6533 the memory check. Disadvantage is that not all 6534 hardware will be completely reinitialized on reboot so 6535 there may be boot problems on some systems. 6536 6537 6538 refscale.holdoff= [KNL] 6539 Set test-start holdoff period. The purpose of 6540 this parameter is to delay the start of the 6541 test until boot completes in order to avoid 6542 interference. 6543 6544 refscale.lookup_instances= [KNL] 6545 Number of data elements to use for the forms of 6546 SLAB_TYPESAFE_BY_RCU testing. A negative number 6547 is negated and multiplied by nr_cpu_ids, while 6548 zero specifies nr_cpu_ids. 6549 6550 refscale.loops= [KNL] 6551 Set the number of loops over the synchronization 6552 primitive under test. Increasing this number 6553 reduces noise due to loop start/end overhead, 6554 but the default has already reduced the per-pass 6555 noise to a handful of picoseconds on ca. 2020 6556 x86 laptops. 6557 6558 refscale.nreaders= [KNL] 6559 Set number of readers. The default value of -1 6560 selects N, where N is roughly 75% of the number 6561 of CPUs. A value of zero is an interesting choice. 6562 6563 refscale.nruns= [KNL] 6564 Set number of runs, each of which is dumped onto 6565 the console log. 6566 6567 refscale.readdelay= [KNL] 6568 Set the read-side critical-section duration, 6569 measured in microseconds. 6570 6571 refscale.scale_type= [KNL] 6572 Specify the read-protection implementation to test. 6573 6574 refscale.shutdown= [KNL] 6575 Shut down the system at the end of the performance 6576 test. This defaults to 1 (shut it down) when 6577 refscale is built into the kernel and to 0 (leave 6578 it running) when refscale is built as a module. 6579 6580 refscale.verbose= [KNL] 6581 Enable additional printk() statements. 6582 6583 refscale.verbose_batched= [KNL] 6584 Batch the additional printk() statements. If zero 6585 (the default) or negative, print everything. Otherwise, 6586 print every Nth verbose statement, where N is the value 6587 specified. 6588 6589 regulator_ignore_unused 6590 [REGULATOR] 6591 Prevents regulator framework from disabling regulators 6592 that are unused, due no driver claiming them. This may 6593 be useful for debug and development, but should not be 6594 needed on a platform with proper driver support. 6595 6596 relax_domain_level= 6597 [KNL, SMP] Set scheduler's default relax_domain_level. 6598 See Documentation/admin-guide/cgroup-v1/cpusets.rst. 6599 6600 reserve= [KNL,BUGS] Force kernel to ignore I/O ports or memory 6601 Format: <base1>,<size1>[,<base2>,<size2>,...] 6602 Reserve I/O ports or memory so the kernel won't use 6603 them. If <base> is less than 0x10000, the region 6604 is assumed to be I/O ports; otherwise it is memory. 6605 6606 reserve_mem= [RAM] 6607 Format: nn[KMG]:<align>:<label> 6608 Reserve physical memory and label it with a name that 6609 other subsystems can use to access it. This is typically 6610 used for systems that do not wipe the RAM, and this command 6611 line will try to reserve the same physical memory on 6612 soft reboots. Note, it is not guaranteed to be the same 6613 location. For example, if anything about the system changes 6614 or if booting a different kernel. It can also fail if KASLR 6615 places the kernel at the location of where the RAM reservation 6616 was from a previous boot, the new reservation will be at a 6617 different location. 6618 Any subsystem using this feature must add a way to verify 6619 that the contents of the physical memory is from a previous 6620 boot, as there may be cases where the memory will not be 6621 located at the same location. 6622 6623 The format is size:align:label for example, to request 6624 12 megabytes of 4096 alignment for ramoops: 6625 6626 reserve_mem=12M:4096:oops ramoops.mem_name=oops 6627 6628 reservetop= [X86-32,EARLY] 6629 Format: nn[KMG] 6630 Reserves a hole at the top of the kernel virtual 6631 address space. 6632 6633 reset_devices [KNL] Force drivers to reset the underlying device 6634 during initialization. 6635 6636 resume= [SWSUSP] 6637 Specify the partition device for software suspend 6638 Format: 6639 {/dev/<dev> | PARTUUID=<uuid> | <int>:<int> | <hex>} 6640 6641 resume_offset= [SWSUSP] 6642 Specify the offset from the beginning of the partition 6643 given by "resume=" at which the swap header is located, 6644 in <PAGE_SIZE> units (needed only for swap files). 6645 See Documentation/power/swsusp-and-swap-files.rst 6646 6647 resumedelay= [HIBERNATION] Delay (in seconds) to pause before attempting to 6648 read the resume files 6649 6650 resumewait [HIBERNATION] Wait (indefinitely) for resume device to show up. 6651 Useful for devices that are detected asynchronously 6652 (e.g. USB and MMC devices). 6653 6654 retain_initrd [RAM] Keep initrd memory after extraction. After boot, it will 6655 be accessible via /sys/firmware/initrd. 6656 6657 retbleed= [X86] Control mitigation of RETBleed (Arbitrary 6658 Speculative Code Execution with Return Instructions) 6659 vulnerability. 6660 6661 AMD-based UNRET and IBPB mitigations alone do not stop 6662 sibling threads from influencing the predictions of other 6663 sibling threads. For that reason, STIBP is used on pro- 6664 cessors that support it, and mitigate SMT on processors 6665 that don't. 6666 6667 off - no mitigation 6668 auto - automatically select a mitigation 6669 auto,nosmt - automatically select a mitigation, 6670 disabling SMT if necessary for 6671 the full mitigation (only on Zen1 6672 and older without STIBP). 6673 ibpb - On AMD, mitigate short speculation 6674 windows on basic block boundaries too. 6675 Safe, highest perf impact. It also 6676 enables STIBP if present. Not suitable 6677 on Intel. 6678 ibpb,nosmt - Like "ibpb" above but will disable SMT 6679 when STIBP is not available. This is 6680 the alternative for systems which do not 6681 have STIBP. 6682 unret - Force enable untrained return thunks, 6683 only effective on AMD f15h-f17h based 6684 systems. 6685 unret,nosmt - Like unret, but will disable SMT when STIBP 6686 is not available. This is the alternative for 6687 systems which do not have STIBP. 6688 6689 Selecting 'auto' will choose a mitigation method at run 6690 time according to the CPU. 6691 6692 Not specifying this option is equivalent to retbleed=auto. 6693 6694 rfkill.default_state= 6695 0 "airplane mode". All wifi, bluetooth, wimax, gps, fm, 6696 etc. communication is blocked by default. 6697 1 Unblocked. 6698 6699 rfkill.master_switch_mode= 6700 0 The "airplane mode" button does nothing. 6701 1 The "airplane mode" button toggles between everything 6702 blocked and the previous configuration. 6703 2 The "airplane mode" button toggles between everything 6704 blocked and everything unblocked. 6705 6706 ring3mwait=disable 6707 [KNL] Disable ring 3 MONITOR/MWAIT feature on supported 6708 CPUs. 6709 6710 riscv_isa_fallback [RISCV,EARLY] 6711 When CONFIG_RISCV_ISA_FALLBACK is not enabled, permit 6712 falling back to detecting extension support by parsing 6713 "riscv,isa" property on devicetree systems when the 6714 replacement properties are not found. See the Kconfig 6715 entry for RISCV_ISA_FALLBACK. 6716 6717 riscv_nousercfi= 6718 all Disable user CFI ABI to userspace even if cpu extension 6719 are available. 6720 bcfi Disable user backward CFI ABI to userspace even if 6721 the shadow stack extension is available. 6722 fcfi Disable user forward CFI ABI to userspace even if the 6723 landing pad extension is available. 6724 6725 ro [KNL] Mount root device read-only on boot 6726 6727 rodata= [KNL,EARLY] 6728 on Mark read-only kernel memory as read-only (default). 6729 off Leave read-only kernel memory writable for debugging. 6730 noalias Mark read-only kernel memory as read-only but retain 6731 writable aliases in the direct map for regions outside 6732 of the kernel image. [arm64] 6733 6734 rockchip.usb_uart 6735 [EARLY] 6736 Enable the uart passthrough on the designated usb port 6737 on Rockchip SoCs. When active, the signals of the 6738 debug-uart get routed to the D+ and D- pins of the usb 6739 port and the regular usb controller gets disabled. 6740 6741 root= [KNL] Root filesystem 6742 Usually this is a block device specifier of some kind, 6743 see the early_lookup_bdev comment in 6744 block/early-lookup.c for details. 6745 Alternatively this can be "ram" for the legacy initial 6746 ramdisk, "nfs" and "cifs" for root on a network file 6747 system, or "mtd" and "ubi" for mounting from raw flash. 6748 6749 rootdelay= [KNL] Delay (in seconds) to pause before attempting to 6750 mount the root filesystem 6751 6752 rootflags= [KNL] Set root filesystem mount option string 6753 6754 rseq_slice_ext= [KNL] RSEQ based time slice extension 6755 Format: boolean 6756 Control enablement of RSEQ based time slice extension. 6757 Default is 'on'. 6758 6759 initramfs_options= [KNL] 6760 Specify mount options for the initramfs mount. 6761 6762 rootfstype= [KNL] Set root filesystem type 6763 6764 rootwait [KNL] Wait (indefinitely) for root device to show up. 6765 Useful for devices that are detected asynchronously 6766 (e.g. USB and MMC devices). 6767 6768 rootwait= [KNL] Maximum time (in seconds) to wait for root device 6769 to show up before attempting to mount the root 6770 filesystem. 6771 6772 rproc_mem=nn[KMG][@address] 6773 [KNL,ARM,CMA] Remoteproc physical memory block. 6774 Memory area to be used by remote processor image, 6775 managed by CMA. 6776 6777 rseq_debug= [KNL] Enable or disable restartable sequence 6778 debug mode. Defaults to CONFIG_RSEQ_DEBUG_DEFAULT_ENABLE. 6779 Format: <bool> 6780 6781 rt_group_sched= [KNL] Enable or disable SCHED_RR/FIFO group scheduling 6782 when CONFIG_RT_GROUP_SCHED=y. Defaults to 6783 !CONFIG_RT_GROUP_SCHED_DEFAULT_DISABLED. 6784 Format: <bool> 6785 6786 rw [KNL] Mount root device read-write on boot 6787 6788 S [KNL] Run init in single mode 6789 6790 s390_iommu= [HW,S390] 6791 Set s390 IOTLB flushing mode 6792 strict 6793 With strict flushing every unmap operation will result 6794 in an IOTLB flush. Default is lazy flushing before 6795 reuse, which is faster. Deprecated, equivalent to 6796 iommu.strict=1. 6797 6798 s390_iommu_aperture= [KNL,S390] 6799 Specifies the size of the per device DMA address space 6800 accessible through the DMA and IOMMU APIs as a decimal 6801 factor of the size of main memory. 6802 The default is 1 meaning that one can concurrently use 6803 as many DMA addresses as physical memory is installed, 6804 if supported by hardware, and thus map all of memory 6805 once. With a value of 2 one can map all of memory twice 6806 and so on. As a special case a factor of 0 imposes no 6807 restrictions other than those given by hardware at the 6808 cost of significant additional memory use for tables. 6809 6810 sa1100ir [NET] 6811 See drivers/net/irda/sa1100_ir.c. 6812 6813 sched_proxy_exec= [KNL] 6814 Enables or disables "proxy execution" style 6815 solution to mutex-based priority inversion. 6816 Format: <bool> 6817 6818 sched_verbose [KNL,EARLY] Enables verbose scheduler debug messages. 6819 6820 schedstats= [KNL,X86] Enable or disable scheduled statistics. 6821 Allowed values are enable and disable. This feature 6822 incurs a small amount of overhead in the scheduler 6823 but is useful for debugging and performance tuning. 6824 6825 sched_thermal_decay_shift= 6826 [Deprecated] 6827 [KNL, SMP] Set a decay shift for scheduler thermal 6828 pressure signal. Thermal pressure signal follows the 6829 default decay period of other scheduler pelt 6830 signals(usually 32 ms but configurable). Setting 6831 sched_thermal_decay_shift will left shift the decay 6832 period for the thermal pressure signal by the shift 6833 value. 6834 i.e. with the default pelt decay period of 32 ms 6835 sched_thermal_decay_shift thermal pressure decay pr 6836 1 64 ms 6837 2 128 ms 6838 and so on. 6839 Format: integer between 0 and 10 6840 Default is 0. 6841 6842 scftorture.holdoff= [KNL] 6843 Number of seconds to hold off before starting 6844 test. Defaults to zero for module insertion and 6845 to 10 seconds for built-in smp_call_function() 6846 tests. 6847 6848 scftorture.longwait= [KNL] 6849 Request ridiculously long waits randomly selected 6850 up to the chosen limit in seconds. Zero (the 6851 default) disables this feature. Please note 6852 that requesting even small non-zero numbers of 6853 seconds can result in RCU CPU stall warnings, 6854 softlockup complaints, and so on. 6855 6856 scftorture.nthreads= [KNL] 6857 Number of kthreads to spawn to invoke the 6858 smp_call_function() family of functions. 6859 The default of -1 specifies a number of kthreads 6860 equal to the number of CPUs. 6861 6862 scftorture.onoff_holdoff= [KNL] 6863 Number seconds to wait after the start of the 6864 test before initiating CPU-hotplug operations. 6865 6866 scftorture.onoff_interval= [KNL] 6867 Number seconds to wait between successive 6868 CPU-hotplug operations. Specifying zero (which 6869 is the default) disables CPU-hotplug operations. 6870 6871 scftorture.shutdown_secs= [KNL] 6872 The number of seconds following the start of the 6873 test after which to shut down the system. The 6874 default of zero avoids shutting down the system. 6875 Non-zero values are useful for automated tests. 6876 6877 scftorture.stat_interval= [KNL] 6878 The number of seconds between outputting the 6879 current test statistics to the console. A value 6880 of zero disables statistics output. 6881 6882 scftorture.stutter_cpus= [KNL] 6883 The number of jiffies to wait between each change 6884 to the set of CPUs under test. 6885 6886 scftorture.use_cpus_read_lock= [KNL] 6887 Use use_cpus_read_lock() instead of the default 6888 preempt_disable() to disable CPU hotplug 6889 while invoking one of the smp_call_function*() 6890 functions. 6891 6892 scftorture.verbose= [KNL] 6893 Enable additional printk() statements. 6894 6895 scftorture.weight_single= [KNL] 6896 The probability weighting to use for the 6897 smp_call_function_single() function with a zero 6898 "wait" parameter. A value of -1 selects the 6899 default if all other weights are -1. However, 6900 if at least one weight has some other value, a 6901 value of -1 will instead select a weight of zero. 6902 6903 scftorture.weight_single_wait= [KNL] 6904 The probability weighting to use for the 6905 smp_call_function_single() function with a 6906 non-zero "wait" parameter. See weight_single. 6907 6908 scftorture.weight_many= [KNL] 6909 The probability weighting to use for the 6910 smp_call_function_many() function with a zero 6911 "wait" parameter. See weight_single. 6912 Note well that setting a high probability for 6913 this weighting can place serious IPI load 6914 on the system. 6915 6916 scftorture.weight_many_wait= [KNL] 6917 The probability weighting to use for the 6918 smp_call_function_many() function with a 6919 non-zero "wait" parameter. See weight_single 6920 and weight_many. 6921 6922 scftorture.weight_all= [KNL] 6923 The probability weighting to use for the 6924 smp_call_function_all() function with a zero 6925 "wait" parameter. See weight_single and 6926 weight_many. 6927 6928 scftorture.weight_all_wait= [KNL] 6929 The probability weighting to use for the 6930 smp_call_function_all() function with a 6931 non-zero "wait" parameter. See weight_single 6932 and weight_many. 6933 6934 sdw_mclk_divider=[SDW] 6935 Specify the MCLK divider for Intel SoundWire buses in 6936 case the BIOS does not provide the clock rate properly. 6937 6938 skew_tick= [KNL,EARLY] Offset the periodic timer tick per cpu to mitigate 6939 xtime_lock contention on larger systems, and/or RCU lock 6940 contention on all systems with CONFIG_MAXSMP set. 6941 Format: { "0" | "1" } 6942 0 -- disable. (may be 1 via CONFIG_CMDLINE="skew_tick=1" 6943 1 -- enable. 6944 Note: increases power consumption, thus should only be 6945 enabled if running jitter sensitive (HPC/RT) workloads. 6946 6947 security= [SECURITY] Choose a legacy "major" security module to 6948 enable at boot. This has been deprecated by the 6949 "lsm=" parameter. 6950 6951 selinux= [SELINUX] Disable or enable SELinux at boot time. 6952 Format: { "0" | "1" } 6953 See security/selinux/Kconfig help text. 6954 0 -- disable. 6955 1 -- enable. 6956 Default value is 1. 6957 6958 serialnumber [BUGS=X86-32] 6959 6960 sev=option[,option...] [X86-64] 6961 6962 debug 6963 Enable debug messages. 6964 6965 nosnp 6966 Do not enable SEV-SNP (applies to host/hypervisor 6967 only). Setting 'nosnp' avoids the RMP check overhead 6968 in memory accesses when users do not want to run 6969 SEV-SNP guests. 6970 6971 shapers= [NET] 6972 Maximal number of shapers. 6973 6974 show_lapic= [APIC,X86] Advanced Programmable Interrupt Controller 6975 Limit apic dumping. The parameter defines the maximal 6976 number of local apics being dumped. Also it is possible 6977 to set it to "all" by meaning -- no limit here. 6978 Format: { 1 (default) | 2 | ... | all }. 6979 The parameter valid if only apic=debug or 6980 apic=verbose is specified. 6981 Example: apic=debug show_lapic=all 6982 6983 slab_debug[=options[,slabs][;[options[,slabs]]...] [MM] 6984 Enabling slab_debug allows one to determine the 6985 culprit if slab objects become corrupted. Enabling 6986 slab_debug can create guard zones around objects and 6987 may poison objects when not in use. Also tracks the 6988 last alloc / free. For more information see 6989 Documentation/admin-guide/mm/slab.rst. 6990 (slub_debug legacy name also accepted for now) 6991 6992 Using this option implies the "no_hash_pointers" 6993 option which can be undone by adding the 6994 "hash_pointers=always" option. 6995 6996 slab_max_order= [MM] 6997 Determines the maximum allowed order for slabs. 6998 A high setting may cause OOMs due to memory 6999 fragmentation. For more information see 7000 Documentation/admin-guide/mm/slab.rst. 7001 (slub_max_order legacy name also accepted for now) 7002 7003 slab_merge [MM] 7004 Enable merging of slabs with similar size when the 7005 kernel is built without CONFIG_SLAB_MERGE_DEFAULT. 7006 (slub_merge legacy name also accepted for now) 7007 7008 slab_min_objects= [MM] 7009 The minimum number of objects per slab. SLUB will 7010 increase the slab order up to slab_max_order to 7011 generate a sufficiently large slab able to contain 7012 the number of objects indicated. The higher the number 7013 of objects the smaller the overhead of tracking slabs 7014 and the less frequently locks need to be acquired. 7015 For more information see 7016 Documentation/admin-guide/mm/slab.rst. 7017 (slub_min_objects legacy name also accepted for now) 7018 7019 slab_min_order= [MM] 7020 Determines the minimum page order for slabs. Must be 7021 lower or equal to slab_max_order. For more information see 7022 Documentation/admin-guide/mm/slab.rst. 7023 (slub_min_order legacy name also accepted for now) 7024 7025 slab_nomerge [MM] 7026 Disable merging of slabs with similar size. May be 7027 necessary if there is some reason to distinguish 7028 allocs to different slabs, especially in hardened 7029 environments where the risk of heap overflows and 7030 layout control by attackers can usually be 7031 frustrated by disabling merging. This will reduce 7032 most of the exposure of a heap attack to a single 7033 cache (risks via metadata attacks are mostly 7034 unchanged). Debug options disable merging on their 7035 own. 7036 For more information see 7037 Documentation/admin-guide/mm/slab.rst. 7038 (slub_nomerge legacy name also accepted for now) 7039 7040 slab_strict_numa [MM] 7041 Support memory policies on a per object level 7042 in the slab allocator. The default is for memory 7043 policies to be applied at the folio level when 7044 a new folio is needed or a partial folio is 7045 retrieved from the lists. Increases overhead 7046 in the slab fastpaths but gains more accurate 7047 NUMA kernel object placement which helps with slow 7048 interconnects in NUMA systems. 7049 7050 slram= [HW,MTD] 7051 7052 smart2= [HW] 7053 Format: <io1>[,<io2>[,...,<io8>]] 7054 7055 smp.csd_lock_timeout= [KNL] 7056 Specify the period of time in milliseconds 7057 that smp_call_function() and friends will wait 7058 for a CPU to release the CSD lock. This is 7059 useful when diagnosing bugs involving CPUs 7060 disabling interrupts for extended periods 7061 of time. Defaults to 5,000 milliseconds, and 7062 setting a value of zero disables this feature. 7063 This feature may be more efficiently disabled 7064 using the csdlock_debug- kernel parameter. 7065 7066 smp.panic_on_ipistall= [KNL] 7067 If a csd_lock_timeout extends for more than 7068 the specified number of milliseconds, panic the 7069 system. By default, let CSD-lock acquisition 7070 take as long as they take. Specifying 300,000 7071 for this value provides a 5-minute timeout. 7072 7073 smsc-ircc2.nopnp [HW] Don't use PNP to discover SMC devices 7074 smsc-ircc2.ircc_cfg= [HW] Device configuration I/O port 7075 smsc-ircc2.ircc_sir= [HW] SIR base I/O port 7076 smsc-ircc2.ircc_fir= [HW] FIR base I/O port 7077 smsc-ircc2.ircc_irq= [HW] IRQ line 7078 smsc-ircc2.ircc_dma= [HW] DMA channel 7079 smsc-ircc2.ircc_transceiver= [HW] Transceiver type: 7080 0: Toshiba Satellite 1800 (GP data pin select) 7081 1: Fast pin select (default) 7082 2: ATC IRMode 7083 7084 smt= [KNL,MIPS,S390,EARLY] Set the maximum number of threads 7085 (logical CPUs) to use per physical CPU on systems 7086 capable of symmetric multithreading (SMT). Will 7087 be capped to the actual hardware limit. 7088 Format: <integer> 7089 Default: -1 (no limit) 7090 7091 softlockup_panic= 7092 [KNL] Should the soft-lockup detector generate panics. 7093 Format: <int> 7094 7095 A value of non-zero instructs the soft-lockup detector 7096 to panic the machine when a soft-lockup duration exceeds 7097 N thresholds. It is also controlled by the kernel.softlockup_panic 7098 sysctl and CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC, which is the 7099 respective build-time switch to that functionality. 7100 7101 softlockup_all_cpu_backtrace= 7102 [KNL] Should the soft-lockup detector generate 7103 backtraces on all cpus. 7104 Format: 0 | 1 7105 7106 sonypi.*= [HW] Sony Programmable I/O Control Device driver 7107 See Documentation/admin-guide/laptops/sonypi.rst 7108 7109 spectre_bhi= [X86] Control mitigation of Branch History Injection 7110 (BHI) vulnerability. This setting affects the 7111 deployment of the HW BHI control and the SW BHB 7112 clearing sequence. 7113 7114 on - (default) Enable the HW or SW mitigation as 7115 needed. This protects the kernel from 7116 both syscalls and VMs. 7117 vmexit - On systems which don't have the HW mitigation 7118 available, enable the SW mitigation on vmexit 7119 ONLY. On such systems, the host kernel is 7120 protected from VM-originated BHI attacks, but 7121 may still be vulnerable to syscall attacks. 7122 off - Disable the mitigation. 7123 7124 spectre_v2= [X86,EARLY] Control mitigation of Spectre variant 2 7125 (indirect branch speculation) vulnerability. 7126 The default operation protects the kernel from 7127 user space attacks. 7128 7129 on - unconditionally enable, implies 7130 spectre_v2_user=on 7131 off - unconditionally disable, implies 7132 spectre_v2_user=off 7133 auto - kernel detects whether your CPU model is 7134 vulnerable 7135 7136 Selecting 'on' will, and 'auto' may, choose a 7137 mitigation method at run time according to the 7138 CPU, the available microcode, the setting of the 7139 CONFIG_MITIGATION_RETPOLINE configuration option, 7140 and the compiler with which the kernel was built. 7141 7142 Selecting 'on' will also enable the mitigation 7143 against user space to user space task attacks. 7144 Selecting specific mitigation does not force enable 7145 user mitigations. 7146 7147 Selecting 'off' will disable both the kernel and 7148 the user space protections. 7149 7150 Specific mitigations can also be selected manually: 7151 7152 retpoline - replace indirect branches 7153 retpoline,generic - Retpolines 7154 retpoline,lfence - LFENCE; indirect branch 7155 retpoline,amd - alias for retpoline,lfence 7156 eibrs - Enhanced/Auto IBRS 7157 eibrs,retpoline - Enhanced/Auto IBRS + Retpolines 7158 eibrs,lfence - Enhanced/Auto IBRS + LFENCE 7159 ibrs - use IBRS to protect kernel 7160 7161 Not specifying this option is equivalent to 7162 spectre_v2=auto. 7163 7164 spectre_v2_user= 7165 [X86] Control mitigation of Spectre variant 2 7166 (indirect branch speculation) vulnerability between 7167 user space tasks 7168 7169 on - Unconditionally enable mitigations. Is 7170 enforced by spectre_v2=on 7171 7172 off - Unconditionally disable mitigations. Is 7173 enforced by spectre_v2=off 7174 7175 prctl - Indirect branch speculation is enabled, 7176 but mitigation can be enabled via prctl 7177 per thread. The mitigation control state 7178 is inherited on fork. 7179 7180 prctl,ibpb 7181 - Like "prctl" above, but only STIBP is 7182 controlled per thread. IBPB is issued 7183 always when switching between different user 7184 space processes. 7185 7186 seccomp 7187 - Same as "prctl" above, but all seccomp 7188 threads will enable the mitigation unless 7189 they explicitly opt out. 7190 7191 seccomp,ibpb 7192 - Like "seccomp" above, but only STIBP is 7193 controlled per thread. IBPB is issued 7194 always when switching between different 7195 user space processes. 7196 7197 auto - Kernel selects the mitigation depending on 7198 the available CPU features and vulnerability. 7199 7200 Default mitigation: "prctl" 7201 7202 Not specifying this option is equivalent to 7203 spectre_v2_user=auto. 7204 7205 spec_rstack_overflow= 7206 [X86,EARLY] Control RAS overflow mitigation on AMD Zen CPUs 7207 7208 off - Disable mitigation 7209 microcode - Enable microcode mitigation only 7210 safe-ret - Enable sw-only safe RET mitigation (default) 7211 ibpb - Enable mitigation by issuing IBPB on 7212 kernel entry 7213 ibpb-vmexit - Issue IBPB only on VMEXIT 7214 (cloud-specific mitigation) 7215 7216 spec_store_bypass_disable= 7217 [HW,EARLY] Control Speculative Store Bypass (SSB) Disable mitigation 7218 (Speculative Store Bypass vulnerability) 7219 7220 Certain CPUs are vulnerable to an exploit against a 7221 a common industry wide performance optimization known 7222 as "Speculative Store Bypass" in which recent stores 7223 to the same memory location may not be observed by 7224 later loads during speculative execution. The idea 7225 is that such stores are unlikely and that they can 7226 be detected prior to instruction retirement at the 7227 end of a particular speculation execution window. 7228 7229 In vulnerable processors, the speculatively forwarded 7230 store can be used in a cache side channel attack, for 7231 example to read memory to which the attacker does not 7232 directly have access (e.g. inside sandboxed code). 7233 7234 This parameter controls whether the Speculative Store 7235 Bypass optimization is used. 7236 7237 On x86 the options are: 7238 7239 on - Unconditionally disable Speculative Store Bypass 7240 off - Unconditionally enable Speculative Store Bypass 7241 auto - Kernel detects whether the CPU model contains an 7242 implementation of Speculative Store Bypass and 7243 picks the most appropriate mitigation. If the 7244 CPU is not vulnerable, "off" is selected. If the 7245 CPU is vulnerable the default mitigation is 7246 architecture and Kconfig dependent. See below. 7247 prctl - Control Speculative Store Bypass per thread 7248 via prctl. Speculative Store Bypass is enabled 7249 for a process by default. The state of the control 7250 is inherited on fork. 7251 seccomp - Same as "prctl" above, but all seccomp threads 7252 will disable SSB unless they explicitly opt out. 7253 7254 Default mitigations: 7255 X86: "prctl" 7256 7257 On powerpc the options are: 7258 7259 on,auto - On Power8 and Power9 insert a store-forwarding 7260 barrier on kernel entry and exit. On Power7 7261 perform a software flush on kernel entry and 7262 exit. 7263 off - No action. 7264 7265 Not specifying this option is equivalent to 7266 spec_store_bypass_disable=auto. 7267 7268 split_lock_detect= 7269 [X86] Enable split lock detection or bus lock detection 7270 7271 When enabled (and if hardware support is present), atomic 7272 instructions that access data across cache line 7273 boundaries will result in an alignment check exception 7274 for split lock detection or a debug exception for 7275 bus lock detection. 7276 7277 off - not enabled 7278 7279 warn - the kernel will emit rate-limited warnings 7280 about applications triggering the #AC 7281 exception or the #DB exception. This mode is 7282 the default on CPUs that support split lock 7283 detection or bus lock detection. Default 7284 behavior is by #AC if both features are 7285 enabled in hardware. 7286 7287 fatal - the kernel will send SIGBUS to applications 7288 that trigger the #AC exception or the #DB 7289 exception. Default behavior is by #AC if 7290 both features are enabled in hardware. 7291 7292 ratelimit:N - 7293 Set system wide rate limit to N bus locks 7294 per second for bus lock detection. 7295 0 < N <= 1000. 7296 7297 N/A for split lock detection. 7298 7299 7300 If an #AC exception is hit in the kernel or in 7301 firmware (i.e. not while executing in user mode) 7302 the kernel will oops in either "warn" or "fatal" 7303 mode. 7304 7305 #DB exception for bus lock is triggered only when 7306 CPL > 0. 7307 7308 srbds= [X86,INTEL,EARLY] 7309 Control the Special Register Buffer Data Sampling 7310 (SRBDS) mitigation. 7311 7312 Certain CPUs are vulnerable to an MDS-like 7313 exploit which can leak bits from the random 7314 number generator. 7315 7316 By default, this issue is mitigated by 7317 microcode. However, the microcode fix can cause 7318 the RDRAND and RDSEED instructions to become 7319 much slower. Among other effects, this will 7320 result in reduced throughput from /dev/urandom. 7321 7322 The microcode mitigation can be disabled with 7323 the following option: 7324 7325 off: Disable mitigation and remove 7326 performance impact to RDRAND and RDSEED 7327 7328 srcutree.big_cpu_lim [KNL] 7329 Specifies the number of CPUs constituting a 7330 large system, such that srcu_struct structures 7331 should immediately allocate an srcu_node array. 7332 This kernel-boot parameter defaults to 128, 7333 but takes effect only when the low-order four 7334 bits of srcutree.convert_to_big is equal to 3 7335 (decide at boot). 7336 7337 srcutree.convert_to_big [KNL] 7338 Specifies under what conditions an SRCU tree 7339 srcu_struct structure will be converted to big 7340 form, that is, with an rcu_node tree: 7341 7342 0: Never. 7343 1: At init_srcu_struct() time. 7344 2: When rcutorture decides to. 7345 3: Decide at boot time (default). 7346 0x1X: Above plus if high contention. 7347 7348 Either way, the srcu_node tree will be sized based 7349 on the actual runtime number of CPUs (nr_cpu_ids) 7350 instead of the compile-time CONFIG_NR_CPUS. 7351 7352 srcutree.counter_wrap_check [KNL] 7353 Specifies how frequently to check for 7354 grace-period sequence counter wrap for the 7355 srcu_data structure's ->srcu_gp_seq_needed field. 7356 The greater the number of bits set in this kernel 7357 parameter, the less frequently counter wrap will 7358 be checked for. Note that the bottom two bits 7359 are ignored. 7360 7361 srcutree.exp_holdoff [KNL] 7362 Specifies how many nanoseconds must elapse 7363 since the end of the last SRCU grace period for 7364 a given srcu_struct until the next normal SRCU 7365 grace period will be considered for automatic 7366 expediting. Set to zero to disable automatic 7367 expediting. 7368 7369 srcutree.srcu_max_nodelay [KNL] 7370 Specifies the number of no-delay instances 7371 per jiffy for which the SRCU grace period 7372 worker thread will be rescheduled with zero 7373 delay. Beyond this limit, worker thread will 7374 be rescheduled with a sleep delay of one jiffy. 7375 7376 srcutree.srcu_max_nodelay_phase [KNL] 7377 Specifies the per-grace-period phase, number of 7378 non-sleeping polls of readers. Beyond this limit, 7379 grace period worker thread will be rescheduled 7380 with a sleep delay of one jiffy, between each 7381 rescan of the readers, for a grace period phase. 7382 7383 srcutree.srcu_retry_check_delay [KNL] 7384 Specifies number of microseconds of non-sleeping 7385 delay between each non-sleeping poll of readers. 7386 7387 srcutree.small_contention_lim [KNL] 7388 Specifies the number of update-side contention 7389 events per jiffy will be tolerated before 7390 initiating a conversion of an srcu_struct 7391 structure to big form. Note that the value of 7392 srcutree.convert_to_big must have the 0x10 bit 7393 set for contention-based conversions to occur. 7394 7395 ssbd= [ARM64,HW,EARLY] 7396 Speculative Store Bypass Disable control 7397 7398 On CPUs that are vulnerable to the Speculative 7399 Store Bypass vulnerability and offer a 7400 firmware based mitigation, this parameter 7401 indicates how the mitigation should be used: 7402 7403 force-on: Unconditionally enable mitigation for 7404 for both kernel and userspace 7405 force-off: Unconditionally disable mitigation for 7406 for both kernel and userspace 7407 kernel: Always enable mitigation in the 7408 kernel, and offer a prctl interface 7409 to allow userspace to register its 7410 interest in being mitigated too. 7411 7412 stack_guard_gap= [MM] 7413 override the default stack gap protection. The value 7414 is in page units and it defines how many pages prior 7415 to (for stacks growing down) resp. after (for stacks 7416 growing up) the main stack are reserved for no other 7417 mapping. Default value is 256 pages. 7418 7419 stack_depot_disable= [KNL,EARLY] 7420 Setting this to true through kernel command line will 7421 disable the stack depot thereby saving the static memory 7422 consumed by the stack hash table. By default this is set 7423 to false. 7424 7425 stack_depot_max_pools= [KNL,EARLY] 7426 Specify the maximum number of pools to use for storing 7427 stack traces. Pools are allocated on-demand up to this 7428 limit. Default value is 8191 pools. 7429 7430 stacktrace [FTRACE] 7431 Enable the stack tracer on boot up. 7432 7433 stacktrace_filter=[function-list] 7434 [FTRACE] Limit the functions that the stack tracer 7435 will trace at boot up. function-list is a comma-separated 7436 list of functions. This list can be changed at run 7437 time by the stack_trace_filter file in the debugfs 7438 tracing directory. Note, this enables stack tracing 7439 and the stacktrace above is not needed. 7440 7441 sti= [PARISC,HW] 7442 Format: <num> 7443 Set the STI (builtin display/keyboard on the HP-PARISC 7444 machines) console (graphic card) which should be used 7445 as the initial boot-console. 7446 See also comment in drivers/video/console/sticore.c. 7447 7448 sti_font= [HW] 7449 See comment in drivers/video/console/sticore.c. 7450 7451 stifb= [HW] 7452 Format: bpp:<bpp1>[:<bpp2>[:<bpp3>...]] 7453 7454 strict_sas_size= 7455 [X86] 7456 Format: <bool> 7457 Enable or disable strict sigaltstack size checks 7458 against the required signal frame size which 7459 depends on the supported FPU features. This can 7460 be used to filter out binaries which have 7461 not yet been made aware of AT_MINSIGSTKSZ. 7462 7463 stress_hpt [PPC,EARLY] 7464 Limits the number of kernel HPT entries in the hash 7465 page table to increase the rate of hash page table 7466 faults on kernel addresses. 7467 7468 stress_slb [PPC,EARLY] 7469 Limits the number of kernel SLB entries, and flushes 7470 them frequently to increase the rate of SLB faults 7471 on kernel addresses. 7472 7473 no_slb_preload [PPC,EARLY] 7474 Disables slb preloading for userspace. 7475 7476 sunrpc.min_resvport= 7477 sunrpc.max_resvport= 7478 [NFS,SUNRPC] 7479 SunRPC servers often require that client requests 7480 originate from a privileged port (i.e. a port in the 7481 range 0 < portnr < 1024). 7482 An administrator who wishes to reserve some of these 7483 ports for other uses may adjust the range that the 7484 kernel's sunrpc client considers to be privileged 7485 using these two parameters to set the minimum and 7486 maximum port values. 7487 7488 sunrpc.svc_rpc_per_connection_limit= 7489 [NFS,SUNRPC] 7490 Limit the number of requests that the server will 7491 process in parallel from a single connection. 7492 The default value is 0 (no limit). 7493 7494 sunrpc.pool_mode= 7495 [NFS] 7496 Control how the NFS server code allocates CPUs to 7497 service thread pools. Depending on how many NICs 7498 you have and where their interrupts are bound, this 7499 option will affect which CPUs will do NFS serving. 7500 Note: this parameter cannot be changed while the 7501 NFS server is running. 7502 7503 auto the server chooses an appropriate mode 7504 automatically using heuristics 7505 global a single global pool contains all CPUs 7506 percpu one pool for each CPU 7507 pernode one pool for each NUMA node (equivalent 7508 to global on non-NUMA machines) 7509 7510 sunrpc.tcp_slot_table_entries= 7511 sunrpc.udp_slot_table_entries= 7512 [NFS,SUNRPC] 7513 Sets the upper limit on the number of simultaneous 7514 RPC calls that can be sent from the client to a 7515 server. Increasing these values may allow you to 7516 improve throughput, but will also increase the 7517 amount of memory reserved for use by the client. 7518 7519 suspend.pm_test_delay= 7520 [SUSPEND] 7521 Sets the number of seconds to remain in a suspend test 7522 mode before resuming the system (see 7523 /sys/power/pm_test). Only available when CONFIG_PM_DEBUG 7524 is set. Default value is 5. 7525 7526 svm= [PPC] 7527 Format: { on | off | y | n | 1 | 0 } 7528 This parameter controls use of the Protected 7529 Execution Facility on pSeries. 7530 7531 swiotlb= [ARM,PPC,MIPS,X86,S390,EARLY] 7532 Format: { <int> [,<int>] | force | noforce } 7533 <int> -- Number of I/O TLB slabs 7534 <int> -- Second integer after comma. Number of swiotlb 7535 areas with their own lock. Will be rounded up 7536 to a power of 2. 7537 force -- force using of bounce buffers even if they 7538 wouldn't be automatically used by the kernel 7539 noforce -- Never use bounce buffers (for debugging) 7540 7541 switches= [HW,M68k,EARLY] 7542 7543 sysctl.*= [KNL] 7544 Set a sysctl parameter, right before loading the init 7545 process, as if the value was written to the respective 7546 /proc/sys/... file. Both '.' and '/' are recognized as 7547 separators. Unrecognized parameters and invalid values 7548 are reported in the kernel log. Sysctls registered 7549 later by a loaded module cannot be set this way. 7550 Example: sysctl.vm.swappiness=40 7551 7552 sysrq_always_enabled 7553 [KNL] 7554 Ignore sysrq setting - this boot parameter will 7555 neutralize any effect of /proc/sys/kernel/sysrq. 7556 Useful for debugging. 7557 7558 tcpmhash_entries= [KNL,NET] 7559 Set the number of tcp_metrics_hash slots. 7560 Default value is 8192 or 16384 depending on total 7561 ram pages. This is used to specify the TCP metrics 7562 cache size. See Documentation/networking/ip-sysctl.rst 7563 "tcp_no_metrics_save" section for more details. 7564 7565 tdfx= [HW,DRM] 7566 7567 test_suspend= [SUSPEND] 7568 Format: { "mem" | "standby" | "freeze" }[,N] 7569 Specify "mem" (for Suspend-to-RAM) or "standby" (for 7570 standby suspend) or "freeze" (for suspend type freeze) 7571 as the system sleep state during system startup with 7572 the optional capability to repeat N number of times. 7573 The system is woken from this state using a 7574 wakeup-capable RTC alarm. 7575 7576 thash_entries= [KNL,NET] 7577 Set number of hash buckets for TCP connection 7578 7579 thermal.act= [HW,ACPI] 7580 -1: disable all active trip points in all thermal zones 7581 <degrees C>: override all lowest active trip points 7582 7583 thermal.crt= [HW,ACPI] 7584 -1: disable all critical trip points in all thermal zones 7585 <degrees C>: override all critical trip points 7586 7587 thermal.off= [HW,ACPI] 7588 1: disable ACPI thermal control 7589 7590 thermal.psv= [HW,ACPI] 7591 -1: disable all passive trip points 7592 <degrees C>: override all passive trip points to this 7593 value 7594 7595 thermal.tzp= [HW,ACPI] 7596 Specify global default ACPI thermal zone polling rate 7597 <deci-seconds>: poll all this frequency 7598 0: no polling (default) 7599 7600 thp_anon= [KNL] 7601 Format: <size>[KMG],<size>[KMG]:<state>;<size>[KMG]-<size>[KMG]:<state> 7602 state is one of "always", "madvise", "never" or "inherit". 7603 Control the default behavior of the system with respect 7604 to anonymous transparent hugepages. 7605 Can be used multiple times for multiple anon THP sizes. 7606 See Documentation/admin-guide/mm/transhuge.rst for more 7607 details. 7608 7609 threadirqs [KNL,EARLY] 7610 Force threading of all interrupt handlers except those 7611 marked explicitly IRQF_NO_THREAD. 7612 7613 thp_shmem= [KNL] 7614 Format: <size>[KMG],<size>[KMG]:<policy>;<size>[KMG]-<size>[KMG]:<policy> 7615 Control the default policy of each hugepage size for the 7616 internal shmem mount. <policy> is one of policies available 7617 for the shmem mount ("always", "inherit", "never", "within_size", 7618 and "advise"). 7619 It can be used multiple times for multiple shmem THP sizes. 7620 See Documentation/admin-guide/mm/transhuge.rst for more 7621 details. 7622 7623 topology= [S390,EARLY] 7624 Format: {off | on} 7625 Specify if the kernel should make use of the cpu 7626 topology information if the hardware supports this. 7627 The scheduler will make use of this information and 7628 e.g. base its process migration decisions on it. 7629 Default is on. 7630 7631 torture.disable_onoff_at_boot= [KNL] 7632 Prevent the CPU-hotplug component of torturing 7633 until after init has spawned. 7634 7635 torture.ftrace_dump_at_shutdown= [KNL] 7636 Dump the ftrace buffer at torture-test shutdown, 7637 even if there were no errors. This can be a 7638 very costly operation when many torture tests 7639 are running concurrently, especially on systems 7640 with rotating-rust storage. 7641 7642 torture.verbose_sleep_frequency= [KNL] 7643 Specifies how many verbose printk()s should be 7644 emitted between each sleep. The default of zero 7645 disables verbose-printk() sleeping. 7646 7647 torture.verbose_sleep_duration= [KNL] 7648 Duration of each verbose-printk() sleep in jiffies. 7649 7650 tpm.disable_pcr_integrity= [HW,TPM] 7651 Do not protect PCR registers from unintended physical 7652 access, or interposers in the bus by the means of 7653 having an integrity protected session wrapped around 7654 TPM2_PCR_Extend command. Consider this in a situation 7655 where TPM is heavily utilized by IMA, thus protection 7656 causing a major performance hit, and the space where 7657 machines are deployed is by other means guarded. 7658 7659 tpm_crb_ffa.busy_timeout_ms= [ARM64,TPM] 7660 Maximum time in milliseconds to retry sending a message 7661 to the TPM service before giving up. This parameter controls 7662 how long the system will continue retrying when the TPM 7663 service is busy. 7664 Format: <unsigned int> 7665 Default: 2000 (2 seconds) 7666 7667 tpm_suspend_pcr=[HW,TPM] 7668 Format: integer pcr id 7669 Specify that at suspend time, the tpm driver 7670 should extend the specified pcr with zeros, 7671 as a workaround for some chips which fail to 7672 flush the last written pcr on TPM_SaveState. 7673 This will guarantee that all the other pcrs 7674 are saved. 7675 7676 tpm_tis.interrupts= [HW,TPM] 7677 Enable interrupts for the MMIO based physical layer 7678 for the FIFO interface. By default it is set to false 7679 (0). For more information about TPM hardware interfaces 7680 defined by Trusted Computing Group (TCG) see 7681 https://trustedcomputinggroup.org/resource/pc-client-platform-tpm-profile-ptp-specification/ 7682 7683 tp_printk [FTRACE] 7684 Have the tracepoints sent to printk as well as the 7685 tracing ring buffer. This is useful for early boot up 7686 where the system hangs or reboots and does not give the 7687 option for reading the tracing buffer or performing a 7688 ftrace_dump_on_oops. 7689 7690 To turn off having tracepoints sent to printk, 7691 echo 0 > /proc/sys/kernel/tracepoint_printk 7692 Note, echoing 1 into this file without the 7693 tp_printk kernel cmdline option has no effect. 7694 7695 The tp_printk_stop_on_boot (see below) can also be used 7696 to stop the printing of events to console at 7697 late_initcall_sync. 7698 7699 ** CAUTION ** 7700 7701 Having tracepoints sent to printk() and activating high 7702 frequency tracepoints such as irq or sched, can cause 7703 the system to live lock. 7704 7705 tp_printk_stop_on_boot [FTRACE] 7706 When tp_printk (above) is set, it can cause a lot of noise 7707 on the console. It may be useful to only include the 7708 printing of events during boot up, as user space may 7709 make the system inoperable. 7710 7711 This command line option will stop the printing of events 7712 to console at the late_initcall_sync() time frame. 7713 7714 trace_buf_size=nn[KMG] 7715 [FTRACE] will set tracing buffer size on each cpu. 7716 7717 trace_clock= [FTRACE] Set the clock used for tracing events 7718 at boot up. 7719 local - Use the per CPU time stamp counter 7720 (converted into nanoseconds). Fast, but 7721 depending on the architecture, may not be 7722 in sync between CPUs. 7723 global - Event time stamps are synchronized across 7724 CPUs. May be slower than the local clock, 7725 but better for some race conditions. 7726 counter - Simple counting of events (1, 2, ..) 7727 note, some counts may be skipped due to the 7728 infrastructure grabbing the clock more than 7729 once per event. 7730 uptime - Use jiffies as the time stamp. 7731 perf - Use the same clock that perf uses. 7732 mono - Use ktime_get_mono_fast_ns() for time stamps. 7733 mono_raw - Use ktime_get_raw_fast_ns() for time 7734 stamps. 7735 boot - Use ktime_get_boot_fast_ns() for time stamps. 7736 Architectures may add more clocks. See 7737 Documentation/trace/ftrace.rst for more details. 7738 7739 trace_event=[event-list] 7740 [FTRACE] Set and start specified trace events in order 7741 to facilitate early boot debugging. The event-list is a 7742 comma-separated list of trace events to enable. See 7743 also Documentation/trace/events.rst 7744 7745 To enable modules, use :mod: keyword: 7746 7747 trace_event=:mod:<module> 7748 7749 The value before :mod: will only enable specific events 7750 that are part of the module. See the above mentioned 7751 document for more information. 7752 7753 trace_instance=[instance-info] 7754 [FTRACE] Create a ring buffer instance early in boot up. 7755 This will be listed in: 7756 7757 /sys/kernel/tracing/instances 7758 7759 Events can be enabled at the time the instance is created 7760 via: 7761 7762 trace_instance=<name>,<system1>:<event1>,<system2>:<event2> 7763 7764 Note, the "<system*>:" portion is optional if the event is 7765 unique. 7766 7767 trace_instance=foo,sched:sched_switch,irq_handler_entry,initcall 7768 7769 will enable the "sched_switch" event (note, the "sched:" is optional, and 7770 the same thing would happen if it was left off). The irq_handler_entry 7771 event, and all events under the "initcall" system. 7772 7773 Flags can be added to the instance to modify its behavior when it is 7774 created. The flags are separated by '^'. 7775 7776 The available flags are: 7777 7778 traceoff - Have the tracing instance tracing disabled after it is created. 7779 traceprintk - Have trace_printk() write into this trace instance 7780 (note, "printk" and "trace_printk" can also be used) 7781 7782 trace_instance=foo^traceoff^traceprintk,sched,irq 7783 7784 The flags must come before the defined events. 7785 7786 If memory has been reserved (see memmap for x86), the instance 7787 can use that memory: 7788 7789 memmap=12M$0x284500000 trace_instance=boot_map@0x284500000:12M 7790 7791 The above will create a "boot_map" instance that uses the physical 7792 memory at 0x284500000 that is 12Megs. The per CPU buffers of that 7793 instance will be split up accordingly. 7794 7795 Alternatively, the memory can be reserved by the reserve_mem option: 7796 7797 reserve_mem=12M:4096:trace trace_instance=boot_map@trace 7798 7799 This will reserve 12 megabytes at boot up with a 4096 byte alignment 7800 and place the ring buffer in this memory. Note that due to KASLR, the 7801 memory may not be the same location each time, which will not preserve 7802 the buffer content. 7803 7804 Also note that the layout of the ring buffer data may change between 7805 kernel versions where the validator will fail and reset the ring buffer 7806 if the layout is not the same as the previous kernel. 7807 7808 If the ring buffer is used for persistent bootups and has events enabled, 7809 it is recommend to disable tracing so that events from a previous boot do not 7810 mix with events of the current boot (unless you are debugging a random crash 7811 at boot up). 7812 7813 reserve_mem=12M:4096:trace trace_instance=boot_map^traceoff^traceprintk@trace,sched,irq 7814 7815 Note, saving the trace buffer across reboots does require that the system 7816 is set up to not wipe memory. For instance, CONFIG_RESET_ATTACK_MITIGATION 7817 can force a memory reset on boot which will clear any trace that was stored. 7818 This is just one of many ways that can clear memory. Make sure your system 7819 keeps the content of memory across reboots before relying on this option. 7820 7821 NB: Both the mapped address and size must be page aligned for the architecture. 7822 7823 See also Documentation/trace/debugging.rst 7824 7825 7826 trace_options=[option-list] 7827 [FTRACE] Enable or disable tracer options at boot. 7828 The option-list is a comma delimited list of options 7829 that can be enabled or disabled just as if you were 7830 to echo the option name into 7831 7832 /sys/kernel/tracing/trace_options 7833 7834 For example, to enable stacktrace option (to dump the 7835 stack trace of each event), add to the command line: 7836 7837 trace_options=stacktrace 7838 7839 See also Documentation/trace/ftrace.rst "trace options" 7840 section. 7841 7842 trace_trigger=[trigger-list] 7843 [FTRACE] Add an event trigger on specific events. 7844 Set a trigger on top of a specific event, with an optional 7845 filter. 7846 7847 The format is "trace_trigger=<event>.<trigger>[ if <filter>],..." 7848 Where more than one trigger may be specified that are comma delimited. 7849 7850 For example: 7851 7852 trace_trigger="sched_switch.stacktrace if prev_state == 2" 7853 7854 The above will enable the "stacktrace" trigger on the "sched_switch" 7855 event but only trigger it if the "prev_state" of the "sched_switch" 7856 event is "2" (TASK_UNINTERRUPTIBLE). 7857 7858 See also "Event triggers" in Documentation/trace/events.rst 7859 7860 7861 traceoff_after_boot 7862 [FTRACE] Sometimes tracing is used to debug issues 7863 during the boot process. Since the trace buffer has a 7864 limited amount of storage, it may be prudent to 7865 disable tracing after the boot is finished, otherwise 7866 the critical information may be overwritten. With this 7867 option, the main tracing buffer will be turned off at 7868 the end of the boot process. 7869 7870 traceoff_on_warning 7871 [FTRACE] enable this option to disable tracing when a 7872 warning is hit. This turns off "tracing_on". Tracing can 7873 be enabled again by echoing '1' into the "tracing_on" 7874 file located in /sys/kernel/tracing/ 7875 7876 This option is useful, as it disables the trace before 7877 the WARNING dump is called, which prevents the trace to 7878 be filled with content caused by the warning output. 7879 7880 This option can also be set at run time via the sysctl 7881 option: kernel/traceoff_on_warning 7882 7883 transparent_hugepage= 7884 [KNL] 7885 Format: [always|madvise|never] 7886 Can be used to control the default behavior of the system 7887 with respect to transparent hugepages. 7888 See Documentation/admin-guide/mm/transhuge.rst 7889 for more details. 7890 7891 transparent_hugepage_shmem= [KNL] 7892 Format: [always|within_size|advise|never|deny|force] 7893 Can be used to control the hugepage allocation policy for 7894 the internal shmem mount. 7895 See Documentation/admin-guide/mm/transhuge.rst 7896 for more details. 7897 7898 transparent_hugepage_tmpfs= [KNL] 7899 Format: [always|within_size|advise|never] 7900 Can be used to control the default hugepage allocation policy 7901 for the tmpfs mount. 7902 See Documentation/admin-guide/mm/transhuge.rst 7903 for more details. 7904 7905 trusted.source= [KEYS] 7906 Format: <string> 7907 This parameter identifies the trust source as a backend 7908 for trusted keys implementation. Supported trust 7909 sources: 7910 - "tpm" 7911 - "tee" 7912 - "caam" 7913 - "dcp" 7914 - "pkwm" 7915 If not specified then it defaults to iterating through 7916 the trust source list starting with TPM and assigns the 7917 first trust source as a backend which is initialized 7918 successfully during iteration. 7919 7920 trusted.rng= [KEYS] 7921 Format: <string> 7922 The RNG used to generate key material for trusted keys. 7923 Can be one of: 7924 - "kernel" 7925 - the same value as trusted.source: "tpm" or "tee" 7926 - "default" 7927 If not specified, "default" is used. In this case, 7928 the RNG's choice is left to each individual trust source. 7929 7930 trusted.dcp_use_otp_key 7931 This is intended to be used in combination with 7932 trusted.source=dcp and will select the DCP OTP key 7933 instead of the DCP UNIQUE key blob encryption. 7934 7935 trusted.dcp_skip_zk_test 7936 This is intended to be used in combination with 7937 trusted.source=dcp and will disable the check if the 7938 blob key is all zeros. This is helpful for situations where 7939 having this key zero'ed is acceptable. E.g. in testing 7940 scenarios. 7941 7942 tsa= [X86] Control mitigation for Transient Scheduler 7943 Attacks on AMD CPUs. Search the following in your 7944 favourite search engine for more details: 7945 7946 "Technical guidance for mitigating transient scheduler 7947 attacks". 7948 7949 off - disable the mitigation 7950 on - enable the mitigation (default) 7951 user - mitigate only user/kernel transitions 7952 vm - mitigate only guest/host transitions 7953 7954 7955 tsc= Disable clocksource stability checks for TSC. 7956 Format: <string> 7957 [x86] reliable: mark tsc clocksource as reliable, this 7958 disables clocksource verification at runtime, as well 7959 as the stability checks done at bootup. Used to enable 7960 high-resolution timer mode on older hardware, and in 7961 virtualized environment. 7962 [x86] noirqtime: Do not use TSC to do irq accounting. 7963 Used to run time disable IRQ_TIME_ACCOUNTING on any 7964 platforms where RDTSC is slow and this accounting 7965 can add overhead. 7966 [x86] unstable: mark the TSC clocksource as unstable, this 7967 marks the TSC unconditionally unstable at bootup and 7968 avoids any further wobbles once the TSC watchdog notices. 7969 [x86] nowatchdog: disable clocksource watchdog. Used 7970 in situations with strict latency requirements (where 7971 interruptions from clocksource watchdog are not 7972 acceptable). 7973 [x86] recalibrate: force recalibration against a HW timer 7974 (HPET or PM timer) on systems whose TSC frequency was 7975 obtained from HW or FW using either an MSR or CPUID(0x15). 7976 Warn if the difference is more than 500 ppm. 7977 [x86] watchdog: Enforce the clocksource watchdog on TSC 7978 7979 tsc_early_khz= [X86,EARLY] Skip early TSC calibration and use the given 7980 value instead. Useful when the early TSC frequency discovery 7981 procedure is not reliable, such as on overclocked systems 7982 with CPUID.16h support and partial CPUID.15h support. 7983 Format: <unsigned int> 7984 7985 tsx= [X86] Control Transactional Synchronization 7986 Extensions (TSX) feature in Intel processors that 7987 support TSX control. 7988 7989 This parameter controls the TSX feature. The options are: 7990 7991 on - Enable TSX on the system. Although there are 7992 mitigations for all known security vulnerabilities, 7993 TSX has been known to be an accelerator for 7994 several previous speculation-related CVEs, and 7995 so there may be unknown security risks associated 7996 with leaving it enabled. 7997 7998 off - Disable TSX on the system. (Note that this 7999 option takes effect only on newer CPUs which are 8000 not vulnerable to MDS, i.e., have 8001 MSR_IA32_ARCH_CAPABILITIES.MDS_NO=1 and which get 8002 the new IA32_TSX_CTRL MSR through a microcode 8003 update. This new MSR allows for the reliable 8004 deactivation of the TSX functionality.) 8005 8006 auto - Disable TSX if X86_BUG_TAA is present, 8007 otherwise enable TSX on the system. 8008 8009 Not specifying this option is equivalent to tsx=off. 8010 8011 See Documentation/admin-guide/hw-vuln/tsx_async_abort.rst 8012 for more details. 8013 8014 tsx_async_abort= [X86,INTEL,EARLY] Control mitigation for the TSX Async 8015 Abort (TAA) vulnerability. 8016 8017 Similar to Micro-architectural Data Sampling (MDS) 8018 certain CPUs that support Transactional 8019 Synchronization Extensions (TSX) are vulnerable to an 8020 exploit against CPU internal buffers which can forward 8021 information to a disclosure gadget under certain 8022 conditions. 8023 8024 In vulnerable processors, the speculatively forwarded 8025 data can be used in a cache side channel attack, to 8026 access data to which the attacker does not have direct 8027 access. 8028 8029 This parameter controls the TAA mitigation. The 8030 options are: 8031 8032 full - Enable TAA mitigation on vulnerable CPUs 8033 if TSX is enabled. 8034 8035 full,nosmt - Enable TAA mitigation and disable SMT on 8036 vulnerable CPUs. If TSX is disabled, SMT 8037 is not disabled because CPU is not 8038 vulnerable to cross-thread TAA attacks. 8039 off - Unconditionally disable TAA mitigation 8040 8041 On MDS-affected machines, tsx_async_abort=off can be 8042 prevented by an active MDS mitigation as both vulnerabilities 8043 are mitigated with the same mechanism so in order to disable 8044 this mitigation, you need to specify mds=off too. 8045 8046 Not specifying this option is equivalent to 8047 tsx_async_abort=full. On CPUs which are MDS affected 8048 and deploy MDS mitigation, TAA mitigation is not 8049 required and doesn't provide any additional 8050 mitigation. 8051 8052 For details see: 8053 Documentation/admin-guide/hw-vuln/tsx_async_abort.rst 8054 8055 turbografx.map[2|3]= [HW,JOY] 8056 TurboGraFX parallel port interface 8057 Format: 8058 <port#>,<js1>,<js2>,<js3>,<js4>,<js5>,<js6>,<js7> 8059 See also Documentation/input/devices/joystick-parport.rst 8060 8061 udbg-immortal [PPC] When debugging early kernel crashes that 8062 happen after console_init() and before a proper 8063 console driver takes over, this boot options might 8064 help "seeing" what's going on. 8065 8066 uhash_entries= [KNL,NET] 8067 Set number of hash buckets for UDP/UDP-Lite connections 8068 8069 uhci-hcd.ignore_oc= 8070 [USB] Ignore overcurrent events (default N). 8071 Some badly-designed motherboards generate lots of 8072 bogus events, for ports that aren't wired to 8073 anything. Set this parameter to avoid log spamming. 8074 Note that genuine overcurrent events won't be 8075 reported either. 8076 8077 unaligned_scalar_speed= 8078 [RISCV] 8079 Format: {slow | fast | unsupported} 8080 Allow skipping scalar unaligned access speed tests. This 8081 is useful for testing alternative code paths and to skip 8082 the tests in environments where they run too slowly. All 8083 CPUs must have the same scalar unaligned access speed. 8084 8085 unaligned_vector_speed= 8086 [RISCV] 8087 Format: {slow | fast | unsupported} 8088 Allow skipping vector unaligned access speed tests. This 8089 is useful for testing alternative code paths and to skip 8090 the tests in environments where they run too slowly. All 8091 CPUs must have the same vector unaligned access speed. 8092 8093 unknown_nmi_panic 8094 [X86] Cause panic on unknown NMI. 8095 8096 unwind_debug [X86-64,EARLY] 8097 Enable unwinder debug output. This can be 8098 useful for debugging certain unwinder error 8099 conditions, including corrupt stacks and 8100 bad/missing unwinder metadata. 8101 8102 usbcore.authorized_default= 8103 [USB] Default USB device authorization: 8104 (default -1 = authorized (same as 1), 8105 0 = not authorized, 1 = authorized, 2 = authorized 8106 if device connected to internal port) 8107 8108 usbcore.autosuspend= 8109 [USB] The autosuspend time delay (in seconds) used 8110 for newly-detected USB devices (default 2). This 8111 is the time required before an idle device will be 8112 autosuspended. Devices for which the delay is set 8113 to a negative value won't be autosuspended at all. 8114 8115 usbcore.usbfs_snoop= 8116 [USB] Set to log all usbfs traffic (default 0 = off). 8117 8118 usbcore.usbfs_snoop_max= 8119 [USB] Maximum number of bytes to snoop in each URB 8120 (default = 65536). 8121 8122 usbcore.blinkenlights= 8123 [USB] Set to cycle leds on hubs (default 0 = off). 8124 8125 usbcore.old_scheme_first= 8126 [USB] Start with the old device initialization 8127 scheme (default 0 = off). 8128 8129 usbcore.usbfs_memory_mb= 8130 [USB] Memory limit (in MB) for buffers allocated by 8131 usbfs (default = 16, 0 = max = 2047). 8132 8133 usbcore.use_both_schemes= 8134 [USB] Try the other device initialization scheme 8135 if the first one fails (default 1 = enabled). 8136 8137 usbcore.initial_descriptor_timeout= 8138 [USB] Specifies timeout for the initial 64-byte 8139 USB_REQ_GET_DESCRIPTOR request in milliseconds 8140 (default 5000 = 5.0 seconds). 8141 8142 usbcore.nousb [USB] Disable the USB subsystem 8143 8144 usbcore.quirks= 8145 [USB] A list of quirk entries to augment the built-in 8146 usb core quirk list. List entries are separated by 8147 commas. Each entry has the form 8148 VendorID:ProductID:Flags. The IDs are 4-digit hex 8149 numbers and Flags is a set of letters. Each letter 8150 will change the built-in quirk; setting it if it is 8151 clear and clearing it if it is set. The letters have 8152 the following meanings: 8153 a = USB_QUIRK_STRING_FETCH_255 (string 8154 descriptors must not be fetched using 8155 a 255-byte read); 8156 b = USB_QUIRK_RESET_RESUME (device can't resume 8157 correctly so reset it instead); 8158 c = USB_QUIRK_NO_SET_INTF (device can't handle 8159 Set-Interface requests); 8160 d = USB_QUIRK_CONFIG_INTF_STRINGS (device can't 8161 handle its Configuration or Interface 8162 strings); 8163 e = USB_QUIRK_RESET (device can't be reset 8164 (e.g morph devices), don't use reset); 8165 f = USB_QUIRK_HONOR_BNUMINTERFACES (device has 8166 more interface descriptions than the 8167 bNumInterfaces count, and can't handle 8168 talking to these interfaces); 8169 g = USB_QUIRK_DELAY_INIT (device needs a pause 8170 during initialization, after we read 8171 the device descriptor); 8172 h = USB_QUIRK_LINEAR_UFRAME_INTR_BINTERVAL (For 8173 high speed and super speed interrupt 8174 endpoints, the USB 2.0 and USB 3.0 spec 8175 require the interval in microframes (1 8176 microframe = 125 microseconds) to be 8177 calculated as interval = 2 ^ 8178 (bInterval-1). 8179 Devices with this quirk report their 8180 bInterval as the result of this 8181 calculation instead of the exponent 8182 variable used in the calculation); 8183 i = USB_QUIRK_DEVICE_QUALIFIER (device can't 8184 handle device_qualifier descriptor 8185 requests); 8186 j = USB_QUIRK_IGNORE_REMOTE_WAKEUP (device 8187 generates spurious wakeup, ignore 8188 remote wakeup capability); 8189 k = USB_QUIRK_NO_LPM (device can't handle Link 8190 Power Management); 8191 l = USB_QUIRK_LINEAR_FRAME_INTR_BINTERVAL 8192 (Device reports its bInterval as linear 8193 frames instead of the USB 2.0 8194 calculation); 8195 m = USB_QUIRK_DISCONNECT_SUSPEND (Device needs 8196 to be disconnected before suspend to 8197 prevent spurious wakeup); 8198 n = USB_QUIRK_DELAY_CTRL_MSG (Device needs a 8199 pause after every control message); 8200 o = USB_QUIRK_HUB_SLOW_RESET (Hub needs extra 8201 delay after resetting its port); 8202 p = USB_QUIRK_SHORT_SET_ADDRESS_REQ_TIMEOUT 8203 (Reduce timeout of the SET_ADDRESS 8204 request from 5000 ms to 500 ms); 8205 q = USB_QUIRK_FORCE_ONE_CONFIG (Device 8206 claims zero configurations, 8207 forcing to 1); 8208 Example: quirks=0781:5580:bk,0a5c:5834:gij 8209 8210 usbhid.mousepoll= 8211 [USBHID] The interval which mice are to be polled at. 8212 8213 usbhid.jspoll= 8214 [USBHID] The interval which joysticks are to be polled at. 8215 8216 usbhid.kbpoll= 8217 [USBHID] The interval which keyboards are to be polled at. 8218 8219 usb-storage.delay_use= 8220 [UMS] The delay in seconds before a new device is 8221 scanned for Logical Units (default 1). 8222 Optionally the delay in milliseconds if the value has 8223 suffix with "ms". 8224 Example: delay_use=2567ms 8225 8226 usb-storage.quirks= 8227 [UMS] A list of quirks entries to supplement or 8228 override the built-in unusual_devs list. List 8229 entries are separated by commas. Each entry has 8230 the form VID:PID:Flags where VID and PID are Vendor 8231 and Product ID values (4-digit hex numbers) and 8232 Flags is a set of characters, each corresponding 8233 to a common usb-storage quirk flag as follows: 8234 a = SANE_SENSE (collect more than 18 bytes 8235 of sense data, not on uas); 8236 b = BAD_SENSE (don't collect more than 18 8237 bytes of sense data, not on uas); 8238 c = FIX_CAPACITY (decrease the reported 8239 device capacity by one sector); 8240 d = NO_READ_DISC_INFO (don't use 8241 READ_DISC_INFO command, not on uas); 8242 e = NO_READ_CAPACITY_16 (don't use 8243 READ_CAPACITY_16 command); 8244 f = NO_REPORT_OPCODES (don't use report opcodes 8245 command, uas only); 8246 g = MAX_SECTORS_240 (don't transfer more than 8247 240 sectors at a time, uas only); 8248 h = CAPACITY_HEURISTICS (decrease the 8249 reported device capacity by one 8250 sector if the number is odd); 8251 i = IGNORE_DEVICE (don't bind to this 8252 device); 8253 j = NO_REPORT_LUNS (don't use report luns 8254 command, uas only); 8255 k = NO_SAME (do not use WRITE_SAME, uas only) 8256 l = NOT_LOCKABLE (don't try to lock and 8257 unlock ejectable media, not on uas); 8258 m = MAX_SECTORS_64 (don't transfer more 8259 than 64 sectors = 32 KB at a time, 8260 not on uas); 8261 n = INITIAL_READ10 (force a retry of the 8262 initial READ(10) command, not on uas); 8263 o = CAPACITY_OK (accept the capacity 8264 reported by the device, not on uas); 8265 p = WRITE_CACHE (the device cache is ON 8266 by default, not on uas); 8267 r = IGNORE_RESIDUE (the device reports 8268 bogus residue values, not on uas); 8269 s = SINGLE_LUN (the device has only one 8270 Logical Unit); 8271 t = NO_ATA_1X (don't allow ATA(12) and ATA(16) 8272 commands, uas only); 8273 u = IGNORE_UAS (don't bind to the uas driver); 8274 w = NO_WP_DETECT (don't test whether the 8275 medium is write-protected). 8276 y = ALWAYS_SYNC (issue a SYNCHRONIZE_CACHE 8277 even if the device claims no cache, 8278 not on uas) 8279 Example: quirks=0419:aaf5:rl,0421:0433:rc 8280 8281 user_debug= [KNL,ARM] 8282 Format: <int> 8283 See arch/arm/Kconfig.debug help text. 8284 1 - undefined instruction events 8285 2 - system calls 8286 4 - invalid data aborts 8287 8 - SIGSEGV faults 8288 16 - SIGBUS faults 8289 Example: user_debug=31 8290 8291 vdso= [X86,SH,SPARC] 8292 On X86_32, this is an alias for vdso32=. Otherwise: 8293 8294 vdso=1: enable VDSO (the default) 8295 vdso=0: disable VDSO mapping 8296 8297 vdso32= [X86] Control the 32-bit vDSO 8298 vdso32=1: enable 32-bit VDSO 8299 vdso32=0 or vdso32=2: disable 32-bit VDSO 8300 8301 See the help text for CONFIG_COMPAT_VDSO for more 8302 details. If CONFIG_COMPAT_VDSO is set, the default is 8303 vdso32=0; otherwise, the default is vdso32=1. 8304 8305 For compatibility with older kernels, vdso32=2 is an 8306 alias for vdso32=0. 8307 8308 Try vdso32=0 if you encounter an error that says: 8309 dl_main: Assertion `(void *) ph->p_vaddr == _rtld_local._dl_sysinfo_dso' failed! 8310 8311 video= [FB,EARLY] Frame buffer configuration 8312 See Documentation/fb/modedb.rst. 8313 8314 video.brightness_switch_enabled= [ACPI] 8315 Format: [0|1] 8316 If set to 1, on receiving an ACPI notify event 8317 generated by hotkey, video driver will adjust brightness 8318 level and then send out the event to user space through 8319 the allocated input device. If set to 0, video driver 8320 will only send out the event without touching backlight 8321 brightness level. 8322 default: 1 8323 8324 virtio_mmio.device= 8325 [VMMIO] Memory mapped virtio (platform) device. 8326 8327 <size>@<baseaddr>:<irq>[:<id>] 8328 where: 8329 <size> := size (can use standard suffixes 8330 like K, M and G) 8331 <baseaddr> := physical base address 8332 <irq> := interrupt number (as passed to 8333 request_irq()) 8334 <id> := (optional) platform device id 8335 example: 8336 virtio_mmio.device=1K@0x100b0000:48:7 8337 8338 Can be used multiple times for multiple devices. 8339 8340 vga= [BOOT,X86-32] Select a particular video mode 8341 See Documentation/arch/x86/boot.rst and 8342 Documentation/admin-guide/svga.rst. 8343 Use vga=ask for menu. 8344 This is actually a boot loader parameter; the value is 8345 passed to the kernel using a special protocol. 8346 8347 vm_debug[=options] [KNL] Available with CONFIG_DEBUG_VM=y. 8348 May slow down system boot speed, especially when 8349 enabled on systems with a large amount of memory. 8350 All options are enabled by default, and this 8351 interface is meant to allow for selectively 8352 enabling or disabling specific virtual memory 8353 debugging features. 8354 8355 Available options are: 8356 P Enable page structure init time poisoning 8357 - Disable all of the above options 8358 8359 vmalloc=nn[KMG] [KNL,BOOT,EARLY] Forces the vmalloc area to have an 8360 exact size of <nn>. This can be used to increase 8361 the minimum size (128MB on x86, arm32 platforms). 8362 It can also be used to decrease the size and leave more room 8363 for directly mapped kernel RAM. Note that this parameter does 8364 not exist on many other platforms (including arm64, alpha, 8365 loongarch, arc, csky, hexagon, microblaze, mips, nios2, openrisc, 8366 parisc, m64k, powerpc, riscv, sh, um, xtensa, s390, sparc). 8367 8368 vmcp_cma=nn[MG] [KNL,S390,EARLY] 8369 Sets the memory size reserved for contiguous memory 8370 allocations for the vmcp device driver. 8371 8372 vmhalt= [KNL,S390] Perform z/VM CP command after system halt. 8373 Format: <command> 8374 8375 vmpanic= [KNL,S390] Perform z/VM CP command after kernel panic. 8376 Format: <command> 8377 8378 vmpoff= [KNL,S390] Perform z/VM CP command after power off. 8379 Format: <command> 8380 8381 vmscape= [X86] Controls mitigation for VMscape attacks. 8382 VMscape attacks can leak information from a userspace 8383 hypervisor to a guest via speculative side-channels. 8384 8385 off - disable the mitigation 8386 ibpb - use Indirect Branch Prediction Barrier 8387 (IBPB) mitigation (default) 8388 force - force vulnerability detection even on 8389 unaffected processors 8390 8391 vsyscall= [X86-64,EARLY] 8392 Controls the behavior of vsyscalls (i.e. calls to 8393 fixed addresses of 0xffffffffff600x00 from legacy 8394 code). Most statically-linked binaries and older 8395 versions of glibc use these calls. Because these 8396 functions are at fixed addresses, they make nice 8397 targets for exploits that can control RIP. 8398 8399 emulate Vsyscalls turn into traps and are emulated 8400 reasonably safely. The vsyscall page is 8401 readable. 8402 8403 xonly [default] Vsyscalls turn into traps and are 8404 emulated reasonably safely. The vsyscall 8405 page is not readable. 8406 8407 none Vsyscalls don't work at all. This makes 8408 them quite hard to use for exploits but 8409 might break your system. 8410 8411 vt.color= [VT] Default text color. 8412 Format: 0xYX, X = foreground, Y = background. 8413 Default: 0x07 = light gray on black. 8414 8415 vt.cur_default= [VT] Default cursor shape. 8416 Format: 0xCCBBAA, where AA, BB, and CC are the same as 8417 the parameters of the <Esc>[?A;B;Cc escape sequence; 8418 see vga-softcursor.rst. Default: 2 = underline. 8419 8420 vt.default_blu= [VT] 8421 Format: <blue0>,<blue1>,<blue2>,...,<blue15> 8422 Change the default blue palette of the console. 8423 This is a 16-member array composed of values 8424 ranging from 0-255. 8425 8426 vt.default_grn= [VT] 8427 Format: <green0>,<green1>,<green2>,...,<green15> 8428 Change the default green palette of the console. 8429 This is a 16-member array composed of values 8430 ranging from 0-255. 8431 8432 vt.default_red= [VT] 8433 Format: <red0>,<red1>,<red2>,...,<red15> 8434 Change the default red palette of the console. 8435 This is a 16-member array composed of values 8436 ranging from 0-255. 8437 8438 vt.default_utf8= 8439 [VT] 8440 Format=<0|1> 8441 Set system-wide default UTF-8 mode for all tty's. 8442 Default is 1, i.e. UTF-8 mode is enabled for all 8443 newly opened terminals. 8444 8445 vt.global_cursor_default= 8446 [VT] 8447 Format=<-1|0|1> 8448 Set system-wide default for whether a cursor 8449 is shown on new VTs. Default is -1, 8450 i.e. cursors will be created by default unless 8451 overridden by individual drivers. 0 will hide 8452 cursors, 1 will display them. 8453 8454 vt.italic= [VT] Default color for italic text; 0-15. 8455 Default: 2 = green. 8456 8457 vt.underline= [VT] Default color for underlined text; 0-15. 8458 Default: 3 = cyan. 8459 8460 watchdog timers [HW,WDT] For information on watchdog timers, 8461 see Documentation/watchdog/watchdog-parameters.rst 8462 or other driver-specific files in the 8463 Documentation/watchdog/ directory. 8464 8465 watchdog_thresh= 8466 [KNL] 8467 Set the hard lockup detector stall duration 8468 threshold in seconds. The soft lockup detector 8469 threshold is set to twice the value. A value of 0 8470 disables both lockup detectors. Default is 10 8471 seconds. 8472 8473 workqueue.unbound_cpus= 8474 [KNL,SMP] Specify to constrain one or some CPUs 8475 to use in unbound workqueues. 8476 Format: <cpu-list> 8477 By default, all online CPUs are available for 8478 unbound workqueues. 8479 8480 workqueue.watchdog_thresh= 8481 If CONFIG_WQ_WATCHDOG is configured, workqueue can 8482 warn stall conditions and dump internal state to 8483 help debugging. 0 disables workqueue stall 8484 detection; otherwise, it's the stall threshold 8485 duration in seconds. The default value is 30 and 8486 it can be updated at runtime by writing to the 8487 corresponding sysfs file. 8488 8489 workqueue.panic_on_stall=<uint> 8490 Panic when workqueue stall is detected by 8491 CONFIG_WQ_WATCHDOG. It sets the number times of the 8492 stall to trigger panic. 8493 8494 The default is set by CONFIG_BOOTPARAM_WQ_STALL_PANIC, 8495 which is 0 (disabled) if not configured. 8496 8497 workqueue.panic_on_stall_time=<uint> 8498 Panic when a workqueue stall has been continuous for 8499 the specified number of seconds. Unlike panic_on_stall 8500 which counts accumulated stall events, this triggers 8501 based on the duration of a single continuous stall. 8502 8503 The default is 0, which disables the time-based panic. 8504 8505 workqueue.cpu_intensive_thresh_us= 8506 Per-cpu work items which run for longer than this 8507 threshold are automatically considered CPU intensive 8508 and excluded from concurrency management to prevent 8509 them from noticeably delaying other per-cpu work 8510 items. Default is 10000 (10ms). 8511 8512 If CONFIG_WQ_CPU_INTENSIVE_REPORT is set, the kernel 8513 will report the work functions which violate this 8514 threshold repeatedly. They are likely good 8515 candidates for using WQ_UNBOUND workqueues instead. 8516 8517 workqueue.cpu_intensive_warning_thresh=<uint> 8518 If CONFIG_WQ_CPU_INTENSIVE_REPORT is set, the kernel 8519 will report the work functions which violate the 8520 intensive_threshold_us repeatedly. In order to prevent 8521 spurious warnings, start printing only after a work 8522 function has violated this threshold number of times. 8523 8524 The default is 4 times. 0 disables the warning. 8525 8526 workqueue.power_efficient 8527 Per-cpu workqueues are generally preferred because 8528 they show better performance thanks to cache 8529 locality; unfortunately, per-cpu workqueues tend to 8530 be more power hungry than unbound workqueues. 8531 8532 Enabling this makes the per-cpu workqueues which 8533 were observed to contribute significantly to power 8534 consumption unbound, leading to measurably lower 8535 power usage at the cost of small performance 8536 overhead. 8537 8538 The default value of this parameter is determined by 8539 the config option CONFIG_WQ_POWER_EFFICIENT_DEFAULT. 8540 8541 workqueue.default_affinity_scope= 8542 Select the default affinity scope to use for unbound 8543 workqueues. Can be one of "cpu", "smt", "cache", 8544 "numa" and "system". Default is "cache". For more 8545 information, see the Affinity Scopes section in 8546 Documentation/core-api/workqueue.rst. 8547 8548 This can be changed after boot by writing to the 8549 matching /sys/module/workqueue/parameters file. All 8550 workqueues with the "default" affinity scope will be 8551 updated accordingly. 8552 8553 workqueue.debug_force_rr_cpu 8554 Workqueue used to implicitly guarantee that work 8555 items queued without explicit CPU specified are put 8556 on the local CPU. This guarantee is no longer true 8557 and while local CPU is still preferred work items 8558 may be put on foreign CPUs. This debug option 8559 forces round-robin CPU selection to flush out 8560 usages which depend on the now broken guarantee. 8561 When enabled, memory and cache locality will be 8562 impacted. 8563 8564 writecombine= [LOONGARCH,EARLY] Control the MAT (Memory Access 8565 Type) of ioremap_wc(). 8566 8567 on - Enable writecombine, use WUC for ioremap_wc() 8568 off - Disable writecombine, use SUC for ioremap_wc() 8569 8570 x2apic_phys [X86-64,APIC,EARLY] Use x2apic physical mode instead of 8571 default x2apic cluster mode on platforms 8572 supporting x2apic. 8573 8574 xen_512gb_limit [KNL,X86-64,XEN] 8575 Restricts the kernel running paravirtualized under Xen 8576 to use only up to 512 GB of RAM. The reason to do so is 8577 crash analysis tools and Xen tools for doing domain 8578 save/restore/migration must be enabled to handle larger 8579 domains. 8580 8581 xen_console_io [XEN,EARLY] 8582 Boolean option to enable/disable the usage of the Xen 8583 console_io hypercalls to read and write to the console. 8584 Mostly useful for debugging and development. 8585 8586 xen_emul_unplug= [HW,X86,XEN,EARLY] 8587 Unplug Xen emulated devices 8588 Format: [unplug0,][unplug1] 8589 ide-disks -- unplug primary master IDE devices 8590 aux-ide-disks -- unplug non-primary-master IDE devices 8591 nics -- unplug network devices 8592 all -- unplug all emulated devices (NICs and IDE disks) 8593 unnecessary -- unplugging emulated devices is 8594 unnecessary even if the host did not respond to 8595 the unplug protocol 8596 never -- do not unplug even if version check succeeds 8597 8598 xen_legacy_crash [X86,XEN,EARLY] 8599 Crash from Xen panic notifier, without executing late 8600 panic() code such as dumping handler. 8601 8602 xen_mc_debug [X86,XEN,EARLY] 8603 Enable multicall debugging when running as a Xen PV guest. 8604 Enabling this feature will reduce performance a little 8605 bit, so it should only be enabled for obtaining extended 8606 debug data in case of multicall errors. 8607 8608 xen_msr_safe= [X86,XEN,EARLY] 8609 Format: <bool> 8610 Select whether to always use non-faulting (safe) MSR 8611 access functions when running as Xen PV guest. The 8612 default value is controlled by CONFIG_XEN_PV_MSR_SAFE. 8613 8614 xen_nopv [X86] 8615 Disables the PV optimizations forcing the HVM guest to 8616 run as generic HVM guest with no PV drivers. 8617 This option is obsoleted by the "nopv" option, which 8618 has equivalent effect for XEN platform. 8619 8620 xen_no_vector_callback 8621 [KNL,X86,XEN,EARLY] Disable the vector callback for Xen 8622 event channel interrupts. 8623 8624 xen_scrub_pages= [XEN] 8625 Boolean option to control scrubbing pages before giving them back 8626 to Xen, for use by other domains. Can be also changed at runtime 8627 with /sys/devices/system/xen_memory/xen_memory0/scrub_pages. 8628 Default value controlled with CONFIG_XEN_SCRUB_PAGES_DEFAULT. 8629 8630 xen_timer_slop= [X86-64,XEN,EARLY] 8631 Set the timer slop (in nanoseconds) for the virtual Xen 8632 timers (default is 100000). This adjusts the minimum 8633 delta of virtualized Xen timers, where lower values 8634 improve timer resolution at the expense of processing 8635 more timer interrupts. 8636 8637 xen.balloon_boot_timeout= [XEN] 8638 The time (in seconds) to wait before giving up to boot 8639 in case initial ballooning fails to free enough memory. 8640 Applies only when running as HVM or PVH guest and 8641 started with less memory configured than allowed at 8642 max. Default is 180. 8643 8644 xen.event_eoi_delay= [XEN] 8645 How long to delay EOI handling in case of event 8646 storms (jiffies). Default is 10. 8647 8648 xen.event_loop_timeout= [XEN] 8649 After which time (jiffies) the event handling loop 8650 should start to delay EOI handling. Default is 2. 8651 8652 xen.fifo_events= [XEN] 8653 Boolean parameter to disable using fifo event handling 8654 even if available. Normally fifo event handling is 8655 preferred over the 2-level event handling, as it is 8656 fairer and the number of possible event channels is 8657 much higher. Default is on (use fifo events). 8658 8659 xirc2ps_cs= [NET,PCMCIA] 8660 Format: 8661 <irq>,<irq_mask>,<io>,<full_duplex>,<do_sound>,<lockup_hack>[,<irq2>[,<irq3>[,<irq4>]]] 8662 8663 xive= [PPC] 8664 By default on POWER9 and above, the kernel will 8665 natively use the XIVE interrupt controller. This option 8666 allows the fallback firmware mode to be used: 8667 8668 off Fallback to firmware control of XIVE interrupt 8669 controller on both pseries and powernv 8670 platforms. Only useful on POWER9 and above. 8671 8672 xive.store-eoi=off [PPC] 8673 By default on POWER10 and above, the kernel will use 8674 stores for EOI handling when the XIVE interrupt mode 8675 is active. This option allows the XIVE driver to use 8676 loads instead, as on POWER9. 8677 8678 xhci-hcd.quirks [USB,KNL] 8679 A hex value specifying bitmask with supplemental xhci 8680 host controller quirks. Meaning of each bit can be 8681 consulted in header drivers/usb/host/xhci.h. 8682 8683 xmon [PPC,EARLY] 8684 Format: { early | on | rw | ro | off } 8685 Controls if xmon debugger is enabled. Default is off. 8686 Passing only "xmon" is equivalent to "xmon=early". 8687 early Call xmon as early as possible on boot; xmon 8688 debugger is called from setup_arch(). 8689 on xmon debugger hooks will be installed so xmon 8690 is only called on a kernel crash. Default mode, 8691 i.e. either "ro" or "rw" mode, is controlled 8692 with CONFIG_XMON_DEFAULT_RO_MODE. 8693 rw xmon debugger hooks will be installed so xmon 8694 is called only on a kernel crash, mode is write, 8695 meaning SPR registers, memory and, other data 8696 can be written using xmon commands. 8697 ro same as "rw" option above but SPR registers, 8698 memory, and other data can't be written using 8699 xmon commands. 8700 off xmon is disabled. 8701