1 ACPI ACPI support is enabled. 2 AGP AGP (Accelerated Graphics Port) is enabled. 3 ALSA ALSA sound support is enabled. 4 APIC APIC support is enabled. 5 APM Advanced Power Management support is enabled. 6 APPARMOR AppArmor support is enabled. 7 ARM ARM architecture is enabled. 8 ARM64 ARM64 architecture is enabled. 9 CLK Common clock infrastructure is enabled. 10 CMA Contiguous Memory Area support is enabled. 11 DRM Direct Rendering Management support is enabled. 12 DYNAMIC_DEBUG Build in debug messages and enable them at runtime 13 EARLY Parameter processed too early to be embedded in initrd. 14 EDD BIOS Enhanced Disk Drive Services (EDD) is enabled 15 EFI EFI Partitioning (GPT) is enabled 16 EVM Extended Verification Module 17 FB The frame buffer device is enabled. 18 FTRACE Function tracing enabled. 19 GCOV GCOV profiling is enabled. 20 HIBERNATION HIBERNATION is enabled. 21 HW Appropriate hardware is enabled. 22 HYPER_V HYPERV support is enabled. 23 IMA Integrity measurement architecture is enabled. 24 IP_PNP IP DHCP, BOOTP, or RARP is enabled. 25 IPV6 IPv6 support is enabled. 26 ISAPNP ISA PnP code is enabled. 27 ISOL CPU Isolation is enabled. 28 JOY Appropriate joystick support is enabled. 29 KGDB Kernel debugger support is enabled. 30 KVM Kernel Virtual Machine support is enabled. 31 LIBATA Libata driver is enabled 32 LOONGARCH LoongArch architecture is enabled. 33 LOOP Loopback device support is enabled. 34 LP Printer support is enabled. 35 M68k M68k architecture is enabled. 36 These options have more detailed description inside of 37 Documentation/arch/m68k/kernel-options.rst. 38 MIPS MIPS architecture is enabled. 39 MOUSE Appropriate mouse support is enabled. 40 MSI Message Signaled Interrupts (PCI). 41 MTD MTD (Memory Technology Device) support is enabled. 42 NET Appropriate network support is enabled. 43 NFS Appropriate NFS support is enabled. 44 NUMA NUMA support is enabled. 45 OF Devicetree is enabled. 46 PARISC The PA-RISC architecture is enabled. 47 PCI PCI bus support is enabled. 48 PCIE PCI Express support is enabled. 49 PCMCIA The PCMCIA subsystem is enabled. 50 PNP Plug & Play support is enabled. 51 PPC PowerPC architecture is enabled. 52 PPT Parallel port support is enabled. 53 PS2 Appropriate PS/2 support is enabled. 54 PV_OPS A paravirtualized kernel is enabled. 55 RAM RAM disk support is enabled. 56 RDT Intel Resource Director Technology. 57 RISCV RISCV architecture is enabled. 58 S390 S390 architecture is enabled. 59 SCSI Appropriate SCSI support is enabled. 60 A lot of drivers have their options described inside 61 the Documentation/scsi/ sub-directory. 62 SDW SoundWire support is enabled. 63 SECURITY Different security models are enabled. 64 SELINUX SELinux support is enabled. 65 SERIAL Serial support is enabled. 66 SH SuperH architecture is enabled. 67 SMP The kernel is an SMP kernel. 68 SPARC Sparc architecture is enabled. 69 SUSPEND System suspend states are enabled. 70 SWSUSP Software suspend (hibernation) is enabled. 71 TPM TPM drivers are enabled. 72 UMS USB Mass Storage support is enabled. 73 USB USB support is enabled. 74 NVME NVMe support is enabled 75 USBHID USB Human Interface Device support is enabled. 76 V4L Video For Linux support is enabled. 77 VGA The VGA console has been enabled. 78 VMMIO Driver for memory mapped virtio devices is enabled. 79 VT Virtual terminal support is enabled. 80 WDT Watchdog support is enabled. 81 X86-32 X86-32, aka i386 architecture is enabled. 82 X86-64 X86-64 architecture is enabled. 83 X86 Either 32-bit or 64-bit x86 (same as X86-32+X86-64) 84 X86_UV SGI UV support is enabled. 85 XEN Xen support is enabled 86 XTENSA xtensa architecture is enabled. 87 88In addition, the following text indicates that the option 89 90 BOOT Is a boot loader parameter. 91 BUGS= Relates to possible processor bugs on the said processor. 92 KNL Is a kernel start-up parameter. 93 94 95Kernel parameters 96 97 accept_memory= [MM] 98 Format: { eager | lazy } 99 default: lazy 100 By default, unaccepted memory is accepted lazily to 101 avoid prolonged boot times. The lazy option will add 102 some runtime overhead until all memory is eventually 103 accepted. In most cases the overhead is negligible. 104 For some workloads or for debugging purposes 105 accept_memory=eager can be used to accept all memory 106 at once during boot. 107 108 acpi= [HW,ACPI,X86,ARM64,RISCV64,EARLY] 109 Advanced Configuration and Power Interface 110 Format: { force | on | off | strict | noirq | rsdt | 111 copy_dsdt | nospcr } 112 force -- enable ACPI if default was off 113 on -- enable ACPI but allow fallback to DT [arm64,riscv64] 114 off -- disable ACPI if default was on 115 noirq -- do not use ACPI for IRQ routing 116 strict -- Be less tolerant of platforms that are not 117 strictly ACPI specification compliant. 118 rsdt -- prefer RSDT over (default) XSDT 119 copy_dsdt -- copy DSDT to memory 120 nocmcff -- Disable firmware first mode for corrected 121 errors. This disables parsing the HEST CMC error 122 source to check if firmware has set the FF flag. This 123 may result in duplicate corrected error reports. 124 nospcr -- disable console in ACPI SPCR table as 125 default _serial_ console on ARM64 126 spcr -- enable console in ACPI SPCR table as 127 default _serial_ console on x86 128 For ARM64, ONLY "acpi=off", "acpi=on", "acpi=force" or 129 "acpi=nospcr" are available 130 For RISCV64, ONLY "acpi=off", "acpi=on" or "acpi=force" 131 are available 132 133 See also Documentation/power/runtime_pm.rst, pci=noacpi 134 135 acpi_apic_instance= [ACPI,IOAPIC,EARLY] 136 Format: <int> 137 2: use 2nd APIC table, if available 138 1,0: use 1st APIC table 139 default: 0 140 141 acpi_backlight= [HW,ACPI] 142 { vendor | video | native | none } 143 If set to vendor, prefer vendor-specific driver 144 (e.g. thinkpad_acpi, sony_acpi, etc.) instead 145 of the ACPI video.ko driver. 146 If set to video, use the ACPI video.ko driver. 147 If set to native, use the device's native backlight mode. 148 If set to none, disable the ACPI backlight interface. 149 150 acpi_force_32bit_fadt_addr [ACPI,EARLY] 151 force FADT to use 32 bit addresses rather than the 152 64 bit X_* addresses. Some firmware have broken 64 153 bit addresses for force ACPI ignore these and use 154 the older legacy 32 bit addresses. 155 156 acpica_no_return_repair [HW, ACPI] 157 Disable AML predefined validation mechanism 158 This mechanism can repair the evaluation result to make 159 the return objects more ACPI specification compliant. 160 This option is useful for developers to identify the 161 root cause of an AML interpreter issue when the issue 162 has something to do with the repair mechanism. 163 164 acpi.debug_layer= [HW,ACPI,ACPI_DEBUG] 165 acpi.debug_level= [HW,ACPI,ACPI_DEBUG] 166 Format: <int> 167 CONFIG_ACPI_DEBUG must be enabled to produce any ACPI 168 debug output. Bits in debug_layer correspond to a 169 _COMPONENT in an ACPI source file, e.g., 170 #define _COMPONENT ACPI_EVENTS 171 Bits in debug_level correspond to a level in 172 ACPI_DEBUG_PRINT statements, e.g., 173 ACPI_DEBUG_PRINT((ACPI_DB_INFO, ... 174 The debug_level mask defaults to "info". See 175 Documentation/firmware-guide/acpi/debug.rst for more information about 176 debug layers and levels. 177 178 Enable processor driver info messages: 179 acpi.debug_layer=0x20000000 180 Enable AML "Debug" output, i.e., stores to the Debug 181 object while interpreting AML: 182 acpi.debug_layer=0xffffffff acpi.debug_level=0x2 183 Enable all messages related to ACPI hardware: 184 acpi.debug_layer=0x2 acpi.debug_level=0xffffffff 185 186 Some values produce so much output that the system is 187 unusable. The "log_buf_len" parameter may be useful 188 if you need to capture more output. 189 190 acpi.poweroff_on_fatal= [ACPI] 191 {0 | 1} 192 Causes the system to poweroff when the ACPI bytecode signals 193 a fatal error. The default value of this setting is 1. 194 Overriding this value should only be done for diagnosing 195 ACPI firmware problems, as the system might behave erratically 196 after having encountered a fatal ACPI error. 197 198 acpi_enforce_resources= [ACPI] 199 { strict | lax | no } 200 Check for resource conflicts between native drivers 201 and ACPI OperationRegions (SystemIO and SystemMemory 202 only). IO ports and memory declared in ACPI might be 203 used by the ACPI subsystem in arbitrary AML code and 204 can interfere with legacy drivers. 205 strict (default): access to resources claimed by ACPI 206 is denied; legacy drivers trying to access reserved 207 resources will fail to bind to device using them. 208 lax: access to resources claimed by ACPI is allowed; 209 legacy drivers trying to access reserved resources 210 will bind successfully but a warning message is logged. 211 no: ACPI OperationRegions are not marked as reserved, 212 no further checks are performed. 213 214 acpi_force_table_verification [HW,ACPI,EARLY] 215 Enable table checksum verification during early stage. 216 By default, this is disabled due to x86 early mapping 217 size limitation. 218 219 acpi_irq_balance [HW,ACPI] 220 ACPI will balance active IRQs 221 default in APIC mode 222 223 acpi_irq_nobalance [HW,ACPI] 224 ACPI will not move active IRQs (default) 225 default in PIC mode 226 227 acpi_irq_isa= [HW,ACPI] If irq_balance, mark listed IRQs used by ISA 228 Format: <irq>,<irq>... 229 230 acpi_irq_pci= [HW,ACPI] If irq_balance, clear listed IRQs for 231 use by PCI 232 Format: <irq>,<irq>... 233 234 acpi_mask_gpe= [HW,ACPI] 235 Due to the existence of _Lxx/_Exx, some GPEs triggered 236 by unsupported hardware/firmware features can result in 237 GPE floodings that cannot be automatically disabled by 238 the GPE dispatcher. 239 This facility can be used to prevent such uncontrolled 240 GPE floodings. 241 Format: <byte> or <bitmap-list> 242 243 acpi_no_auto_serialize [HW,ACPI] 244 Disable auto-serialization of AML methods 245 AML control methods that contain the opcodes to create 246 named objects will be marked as "Serialized" by the 247 auto-serialization feature. 248 This feature is enabled by default. 249 This option allows to turn off the feature. 250 251 acpi_no_memhotplug [ACPI] Disable memory hotplug. Useful for kdump 252 kernels. 253 254 acpi_no_static_ssdt [HW,ACPI,EARLY] 255 Disable installation of static SSDTs at early boot time 256 By default, SSDTs contained in the RSDT/XSDT will be 257 installed automatically and they will appear under 258 /sys/firmware/acpi/tables. 259 This option turns off this feature. 260 Note that specifying this option does not affect 261 dynamic table installation which will install SSDT 262 tables to /sys/firmware/acpi/tables/dynamic. 263 264 acpi_no_watchdog [HW,ACPI,WDT] 265 Ignore the ACPI-based watchdog interface (WDAT) and let 266 a native driver control the watchdog device instead. 267 268 acpi_rsdp= [ACPI,EFI,KEXEC,EARLY] 269 Pass the RSDP address to the kernel, mostly used 270 on machines running EFI runtime service to boot the 271 second kernel for kdump. 272 273 acpi_os_name= [HW,ACPI] Tell ACPI BIOS the name of the OS 274 Format: To spoof as Windows 98: ="Microsoft Windows" 275 276 acpi_rev_override [ACPI] Override the _REV object to return 5 (instead 277 of 2 which is mandated by ACPI 6) as the supported ACPI 278 specification revision (when using this switch, it may 279 be necessary to carry out a cold reboot _twice_ in a 280 row to make it take effect on the platform firmware). 281 282 acpi_osi= [HW,ACPI] Modify list of supported OS interface strings 283 acpi_osi="string1" # add string1 284 acpi_osi="!string2" # remove string2 285 acpi_osi=!* # remove all strings 286 acpi_osi=! # disable all built-in OS vendor 287 strings 288 acpi_osi=!! # enable all built-in OS vendor 289 strings 290 acpi_osi= # disable all strings 291 292 'acpi_osi=!' can be used in combination with single or 293 multiple 'acpi_osi="string1"' to support specific OS 294 vendor string(s). Note that such command can only 295 affect the default state of the OS vendor strings, thus 296 it cannot affect the default state of the feature group 297 strings and the current state of the OS vendor strings, 298 specifying it multiple times through kernel command line 299 is meaningless. This command is useful when one do not 300 care about the state of the feature group strings which 301 should be controlled by the OSPM. 302 Examples: 303 1. 'acpi_osi=! acpi_osi="Windows 2000"' is equivalent 304 to 'acpi_osi="Windows 2000" acpi_osi=!', they all 305 can make '_OSI("Windows 2000")' TRUE. 306 307 'acpi_osi=' cannot be used in combination with other 308 'acpi_osi=' command lines, the _OSI method will not 309 exist in the ACPI namespace. NOTE that such command can 310 only affect the _OSI support state, thus specifying it 311 multiple times through kernel command line is also 312 meaningless. 313 Examples: 314 1. 'acpi_osi=' can make 'CondRefOf(_OSI, Local1)' 315 FALSE. 316 317 'acpi_osi=!*' can be used in combination with single or 318 multiple 'acpi_osi="string1"' to support specific 319 string(s). Note that such command can affect the 320 current state of both the OS vendor strings and the 321 feature group strings, thus specifying it multiple times 322 through kernel command line is meaningful. But it may 323 still not able to affect the final state of a string if 324 there are quirks related to this string. This command 325 is useful when one want to control the state of the 326 feature group strings to debug BIOS issues related to 327 the OSPM features. 328 Examples: 329 1. 'acpi_osi="Module Device" acpi_osi=!*' can make 330 '_OSI("Module Device")' FALSE. 331 2. 'acpi_osi=!* acpi_osi="Module Device"' can make 332 '_OSI("Module Device")' TRUE. 333 3. 'acpi_osi=! acpi_osi=!* acpi_osi="Windows 2000"' is 334 equivalent to 335 'acpi_osi=!* acpi_osi=! acpi_osi="Windows 2000"' 336 and 337 'acpi_osi=!* acpi_osi="Windows 2000" acpi_osi=!', 338 they all will make '_OSI("Windows 2000")' TRUE. 339 340 acpi_pm_good [X86] 341 Override the pmtimer bug detection: force the kernel 342 to assume that this machine's pmtimer latches its value 343 and always returns good values. 344 345 acpi_sci= [HW,ACPI,EARLY] ACPI System Control Interrupt trigger mode 346 Format: { level | edge | high | low } 347 348 acpi_skip_timer_override [HW,ACPI,EARLY] 349 Recognize and ignore IRQ0/pin2 Interrupt Override. 350 For broken nForce2 BIOS resulting in XT-PIC timer. 351 352 acpi_sleep= [HW,ACPI] Sleep options 353 Format: { s3_bios, s3_mode, s3_beep, s4_hwsig, 354 s4_nohwsig, old_ordering, nonvs, 355 sci_force_enable, nobl } 356 See Documentation/power/video.rst for information on 357 s3_bios and s3_mode. 358 s3_beep is for debugging; it makes the PC's speaker beep 359 as soon as the kernel's real-mode entry point is called. 360 s4_hwsig causes the kernel to check the ACPI hardware 361 signature during resume from hibernation, and gracefully 362 refuse to resume if it has changed. This complies with 363 the ACPI specification but not with reality, since 364 Windows does not do this and many laptops do change it 365 on docking. So the default behaviour is to allow resume 366 and simply warn when the signature changes, unless the 367 s4_hwsig option is enabled. 368 s4_nohwsig prevents ACPI hardware signature from being 369 used (or even warned about) during resume. 370 old_ordering causes the ACPI 1.0 ordering of the _PTS 371 control method, with respect to putting devices into 372 low power states, to be enforced (the ACPI 2.0 ordering 373 of _PTS is used by default). 374 nonvs prevents the kernel from saving/restoring the 375 ACPI NVS memory during suspend/hibernation and resume. 376 sci_force_enable causes the kernel to set SCI_EN directly 377 on resume from S1/S3 (which is against the ACPI spec, 378 but some broken systems don't work without it). 379 nobl causes the internal blacklist of systems known to 380 behave incorrectly in some ways with respect to system 381 suspend and resume to be ignored (use wisely). 382 383 acpi_use_timer_override [HW,ACPI,EARLY] 384 Use timer override. For some broken Nvidia NF5 boards 385 that require a timer override, but don't have HPET 386 387 add_efi_memmap [EFI,X86,EARLY] Include EFI memory map in 388 kernel's map of available physical RAM. 389 390 agp= [AGP] 391 { off | try_unsupported } 392 off: disable AGP support 393 try_unsupported: try to drive unsupported chipsets 394 (may crash computer or cause data corruption) 395 396 ALSA [HW,ALSA] 397 See Documentation/sound/alsa-configuration.rst 398 399 alignment= [KNL,ARM] 400 Allow the default userspace alignment fault handler 401 behaviour to be specified. Bit 0 enables warnings, 402 bit 1 enables fixups, and bit 2 sends a segfault. 403 404 align_va_addr= [X86-64] 405 Align virtual addresses by clearing slice [14:12] when 406 allocating a VMA at process creation time. This option 407 gives you up to 3% performance improvement on AMD F15h 408 machines (where it is enabled by default) for a 409 CPU-intensive style benchmark, and it can vary highly in 410 a microbenchmark depending on workload and compiler. 411 412 32: only for 32-bit processes 413 64: only for 64-bit processes 414 on: enable for both 32- and 64-bit processes 415 off: disable for both 32- and 64-bit processes 416 417 alloc_snapshot [FTRACE] 418 Allocate the ftrace snapshot buffer on boot up when the 419 main buffer is allocated. This is handy if debugging 420 and you need to use tracing_snapshot() on boot up, and 421 do not want to use tracing_snapshot_alloc() as it needs 422 to be done where GFP_KERNEL allocations are allowed. 423 424 allow_mismatched_32bit_el0 [ARM64,EARLY] 425 Allow execve() of 32-bit applications and setting of the 426 PER_LINUX32 personality on systems where only a strict 427 subset of the CPUs support 32-bit EL0. When this 428 parameter is present, the set of CPUs supporting 32-bit 429 EL0 is indicated by /sys/devices/system/cpu/aarch32_el0 430 and hot-unplug operations may be restricted. 431 432 See Documentation/arch/arm64/asymmetric-32bit.rst for more 433 information. 434 435 amd_iommu= [HW,X86-64] 436 Pass parameters to the AMD IOMMU driver in the system. 437 Possible values are: 438 fullflush - Deprecated, equivalent to iommu.strict=1 439 off - do not initialize any AMD IOMMU found in 440 the system 441 force_isolation - Force device isolation for all 442 devices. The IOMMU driver is not 443 allowed anymore to lift isolation 444 requirements as needed. This option 445 does not override iommu=pt 446 force_enable - Force enable the IOMMU on platforms known 447 to be buggy with IOMMU enabled. Use this 448 option with care. 449 pgtbl_v1 - Use v1 page table for DMA-API (Default). 450 pgtbl_v2 - Use v2 page table for DMA-API. 451 irtcachedis - Disable Interrupt Remapping Table (IRT) caching. 452 nohugepages - Limit page-sizes used for v1 page-tables 453 to 4 KiB. 454 v2_pgsizes_only - Limit page-sizes used for v1 page-tables 455 to 4KiB/2Mib/1GiB. 456 457 458 amd_iommu_dump= [HW,X86-64] 459 Enable AMD IOMMU driver option to dump the ACPI table 460 for AMD IOMMU. With this option enabled, AMD IOMMU 461 driver will print ACPI tables for AMD IOMMU during 462 IOMMU initialization. 463 464 amd_iommu_intr= [HW,X86-64] 465 Specifies one of the following AMD IOMMU interrupt 466 remapping modes: 467 legacy - Use legacy interrupt remapping mode. 468 vapic - Use virtual APIC mode, which allows IOMMU 469 to inject interrupts directly into guest. 470 This mode requires kvm-amd.avic=1. 471 (Default when IOMMU HW support is present.) 472 473 amd_pstate= [X86,EARLY] 474 disable 475 Do not enable amd_pstate as the default 476 scaling driver for the supported processors 477 passive 478 Use amd_pstate with passive mode as a scaling driver. 479 In this mode autonomous selection is disabled. 480 Driver requests a desired performance level and platform 481 tries to match the same performance level if it is 482 satisfied by guaranteed performance level. 483 active 484 Use amd_pstate_epp driver instance as the scaling driver, 485 driver provides a hint to the hardware if software wants 486 to bias toward performance (0x0) or energy efficiency (0xff) 487 to the CPPC firmware. then CPPC power algorithm will 488 calculate the runtime workload and adjust the realtime cores 489 frequency. 490 guided 491 Activate guided autonomous mode. Driver requests minimum and 492 maximum performance level and the platform autonomously 493 selects a performance level in this range and appropriate 494 to the current workload. 495 496 amd_prefcore= 497 [X86] 498 disable 499 Disable amd-pstate preferred core. 500 501 amd_dynamic_epp= 502 [X86] 503 disable 504 Disable amd-pstate dynamic EPP. 505 enable 506 Enable amd-pstate dynamic EPP. 507 508 amijoy.map= [HW,JOY] Amiga joystick support 509 Map of devices attached to JOY0DAT and JOY1DAT 510 Format: <a>,<b> 511 See also Documentation/input/joydev/joystick.rst 512 513 analog.map= [HW,JOY] Analog joystick and gamepad support 514 Specifies type or capabilities of an analog joystick 515 connected to one of 16 gameports 516 Format: <type1>,<type2>,..<type16> 517 518 apc= [HW,SPARC] 519 Power management functions (SPARCstation-4/5 + deriv.) 520 Format: noidle 521 Disable APC CPU standby support. SPARCstation-Fox does 522 not play well with APC CPU idle - disable it if you have 523 APC and your system crashes randomly. 524 525 apic [APIC,X86-64] Use IO-APIC. Default. 526 527 apic= [APIC,X86,EARLY] Advanced Programmable Interrupt Controller 528 Change the output verbosity while booting 529 Format: { quiet (default) | verbose | debug } 530 Change the amount of debugging information output 531 when initialising the APIC and IO-APIC components. 532 533 apic_extnmi= [APIC,X86,EARLY] External NMI delivery setting 534 Format: { bsp (default) | all | none } 535 bsp: External NMI is delivered only to CPU 0 536 all: External NMIs are broadcast to all CPUs as a 537 backup of CPU 0 538 none: External NMI is masked for all CPUs. This is 539 useful so that a dump capture kernel won't be 540 shot down by NMI 541 542 apicpmtimer Do APIC timer calibration using the pmtimer. Implies 543 apicmaintimer. Useful when your PIT timer is totally 544 broken. 545 546 autoconf= [IPV6] 547 See Documentation/networking/ipv6.rst. 548 549 apm= [APM] Advanced Power Management 550 See header of arch/x86/kernel/apm_32.c. 551 552 apparmor= [APPARMOR] Disable or enable AppArmor at boot time 553 Format: { "0" | "1" } 554 See security/apparmor/Kconfig help text 555 0 -- disable. 556 1 -- enable. 557 Default value is set via kernel config option. 558 559 arm64.no32bit_el0 [ARM64] Unconditionally disable the execution of 560 32 bit applications. 561 562 arm64.nobti [ARM64] Unconditionally disable Branch Target 563 Identification support 564 565 arm64.nogcs [ARM64] Unconditionally disable Guarded Control Stack 566 support 567 568 arm64.nomops [ARM64] Unconditionally disable Memory Copy and Memory 569 Set instructions support 570 571 arm64.nompam [ARM64] Unconditionally disable Memory Partitioning And 572 Monitoring support 573 574 arm64.nomte [ARM64] Unconditionally disable Memory Tagging Extension 575 support 576 577 arm64.nopauth [ARM64] Unconditionally disable Pointer Authentication 578 support 579 580 arm64.nosme [ARM64] Unconditionally disable Scalable Matrix 581 Extension support 582 583 arm64.nosve [ARM64] Unconditionally disable Scalable Vector 584 Extension support 585 586 ataflop= [HW,M68k] 587 588 atarimouse= [HW,MOUSE] Atari Mouse 589 590 atkbd.extra= [HW] Enable extra LEDs and keys on IBM RapidAccess, 591 EzKey and similar keyboards 592 593 atkbd.reset= [HW] Reset keyboard during initialization 594 595 atkbd.set= [HW] Select keyboard code set 596 Format: <int> (2 = AT (default), 3 = PS/2) 597 598 atkbd.scroll= [HW] Enable scroll wheel on MS Office and similar 599 keyboards 600 601 atkbd.softraw= [HW] Choose between synthetic and real raw mode 602 Format: <bool> (0 = real, 1 = synthetic (default)) 603 604 atkbd.softrepeat= [HW] 605 Use software keyboard repeat 606 607 audit= [KNL] Enable the audit sub-system 608 Format: { "0" | "1" | "off" | "on" } 609 0 | off - kernel audit is disabled and can not be 610 enabled until the next reboot 611 unset - kernel audit is initialized but disabled and 612 will be fully enabled by the userspace auditd. 613 1 | on - kernel audit is initialized and partially 614 enabled, storing at most audit_backlog_limit 615 messages in RAM until it is fully enabled by the 616 userspace auditd. 617 Default: unset 618 619 audit_backlog_limit= [KNL] Set the audit queue size limit. 620 Format: <int> (must be >=0) 621 Default: 64 622 623 bau= [X86_UV] Enable the BAU on SGI UV. The default 624 behavior is to disable the BAU (i.e. bau=0). 625 Format: { "0" | "1" } 626 0 - Disable the BAU. 627 1 - Enable the BAU. 628 unset - Disable the BAU. 629 630 bdev_allow_write_mounted= 631 Format: <bool> 632 Control the ability to open a mounted block device 633 for writing, i.e., allow / disallow writes that bypass 634 the FS. This was implemented as a means to prevent 635 fuzzers from crashing the kernel by overwriting the 636 metadata underneath a mounted FS without its awareness. 637 This also prevents destructive formatting of mounted 638 filesystems by naive storage tooling that don't use 639 O_EXCL. Default is Y and can be changed through the 640 Kconfig option CONFIG_BLK_DEV_WRITE_MOUNTED. 641 642 bert_disable [ACPI] 643 Disable BERT OS support on buggy BIOSes. 644 645 bgrt_disable [ACPI,X86,EARLY] 646 Disable BGRT to avoid flickering OEM logo. 647 648 blkdevparts= Manual partition parsing of block device(s) for 649 embedded devices based on command line input. 650 See Documentation/block/cmdline-partition.rst 651 652 boot_delay= [KNL,EARLY] 653 Milliseconds to delay each printk during boot. 654 Only works if CONFIG_BOOT_PRINTK_DELAY is enabled, 655 and you may also have to specify "lpj=". Boot_delay 656 values larger than 10 seconds (10000) are assumed 657 erroneous and ignored. 658 Format: integer 659 660 bootconfig [KNL,EARLY] 661 Extended command line options can be added to an initrd 662 and this will cause the kernel to look for it. 663 664 See Documentation/admin-guide/bootconfig.rst 665 666 bttv.card= [HW,V4L] bttv (bt848 + bt878 based grabber cards) 667 bttv.radio= Most important insmod options are available as 668 kernel args too. 669 bttv.pll= See Documentation/admin-guide/media/bttv.rst 670 bttv.tuner= 671 672 bulk_remove=off [PPC] This parameter disables the use of the pSeries 673 firmware feature for flushing multiple hpte entries 674 at a time. 675 676 c101= [NET] Moxa C101 synchronous serial card 677 678 cachesize= [BUGS=X86-32] Override level 2 CPU cache size detection. 679 Sometimes CPU hardware bugs make them report the cache 680 size incorrectly. The kernel will attempt work arounds 681 to fix known problems, but for some CPUs it is not 682 possible to determine what the correct size should be. 683 This option provides an override for these situations. 684 685 carrier_timeout= 686 [NET] Specifies amount of time (in seconds) that 687 the kernel should wait for a network carrier. By default 688 it waits 120 seconds. 689 690 ca_keys= [KEYS] This parameter identifies a specific key(s) on 691 the system trusted keyring to be used for certificate 692 trust validation. 693 format: { id:<keyid> | builtin } 694 695 cca= [MIPS,EARLY] Override the kernel pages' cache coherency 696 algorithm. Accepted values range from 0 to 7 697 inclusive. See arch/mips/include/asm/pgtable-bits.h 698 for platform specific values (SB1, Loongson3 and 699 others). 700 701 ccw_timeout_log [S390] 702 See Documentation/arch/s390/common_io.rst for details. 703 704 cfi= [X86-64] Set Control Flow Integrity checking features 705 when CONFIG_FINEIBT is enabled. 706 Format: feature[,feature...] 707 Default: auto 708 709 auto: Use FineIBT if IBT available, otherwise kCFI. 710 Under FineIBT, enable "paranoid" mode when 711 FRED is not available. 712 off: Turn off CFI checking. 713 kcfi: Use kCFI (disable FineIBT). 714 fineibt: Use FineIBT (even if IBT not available). 715 norand: Do not re-randomize CFI hashes. 716 paranoid: Add caller hash checking under FineIBT. 717 bhi: Enable register poisoning to stop speculation 718 across FineIBT. (Disabled by default.) 719 warn: Do not enforce CFI checking: warn only. 720 debug: Report CFI initialization details. 721 722 cgroup_disable= [KNL] Disable a particular controller or optional feature 723 Format: {name of the controller(s) or feature(s) to disable} 724 The effects of cgroup_disable=foo are: 725 - foo isn't auto-mounted if you mount all cgroups in 726 a single hierarchy 727 - foo isn't visible as an individually mountable 728 subsystem 729 - if foo is an optional feature then the feature is 730 disabled and corresponding cgroup files are not 731 created 732 {Currently only "memory" controller deal with this and 733 cut the overhead, others just disable the usage. So 734 only cgroup_disable=memory is actually worthy} 735 Specifying "pressure" disables per-cgroup pressure 736 stall information accounting feature 737 738 cgroup_no_v1= [KNL] Disable cgroup controllers and named hierarchies in v1 739 Format: { { controller | "all" | "named" } 740 [,{ controller | "all" | "named" }...] } 741 Like cgroup_disable, but only applies to cgroup v1; 742 the blacklisted controllers remain available in cgroup2. 743 "all" blacklists all controllers and "named" disables 744 named mounts. Specifying both "all" and "named" disables 745 all v1 hierarchies. 746 747 cgroup_v1_proc= [KNL] Show also missing controllers in /proc/cgroups 748 Format: { "true" | "false" } 749 /proc/cgroups lists only v1 controllers by default. 750 This compatibility option enables listing also v2 751 controllers (whose v1 code is not compiled!), so that 752 semi-legacy software can check this file to decide 753 about usage of v2 (sic) controllers. 754 755 cgroup_favordynmods= [KNL] Enable or Disable favordynmods. 756 Format: { "true" | "false" } 757 Defaults to the value of CONFIG_CGROUP_FAVOR_DYNMODS. 758 759 cgroup.memory= [KNL] Pass options to the cgroup memory controller. 760 Format: <string> 761 nosocket -- Disable socket memory accounting. 762 nokmem -- Disable kernel memory accounting. 763 nobpf -- Disable BPF memory accounting. 764 765 check_pages= [MM,EARLY] Enable sanity checking of pages after 766 allocations / before freeing. This adds checks to catch 767 double-frees, use-after-frees, and other sources of 768 page corruption by inspecting page internals (flags, 769 mapcount/refcount, memcg_data, etc.). 770 Format: { "0" | "1" } 771 Default: 0 (1 if CONFIG_DEBUG_VM is set) 772 773 checkreqprot= [SELINUX] Set initial checkreqprot flag value. 774 Format: { "0" | "1" } 775 See security/selinux/Kconfig help text. 776 0 -- check protection applied by kernel (includes 777 any implied execute protection). 778 1 -- check protection requested by application. 779 Default value is set via a kernel config option. 780 Value can be changed at runtime via 781 /sys/fs/selinux/checkreqprot. 782 Setting checkreqprot to 1 is deprecated. 783 784 cio_ignore= [S390] 785 See Documentation/arch/s390/common_io.rst for details. 786 787 clk_ignore_unused 788 [CLK] 789 Prevents the clock framework from automatically gating 790 clocks that have not been explicitly enabled by a Linux 791 device driver but are enabled in hardware at reset or 792 by the bootloader/firmware. Note that this does not 793 force such clocks to be always-on nor does it reserve 794 those clocks in any way. This parameter is useful for 795 debug and development, but should not be needed on a 796 platform with proper driver support. For more 797 information, see Documentation/driver-api/clk.rst. 798 799 clock= [BUGS=X86-32, HW] gettimeofday clocksource override. 800 [Deprecated] 801 Forces specified clocksource (if available) to be used 802 when calculating gettimeofday(). If specified 803 clocksource is not available, it defaults to PIT. 804 Format: { pit | tsc | cyclone | pmtmr } 805 806 clocksource= Override the default clocksource 807 Format: <string> 808 Override the default clocksource and use the clocksource 809 with the name specified. 810 Some clocksource names to choose from, depending on 811 the platform: 812 [all] jiffies (this is the base, fallback clocksource) 813 [ACPI] acpi_pm 814 [ARM] imx_timer1,OSTS,netx_timer,mpu_timer2, 815 pxa_timer,timer3,32k_counter,timer0_1 816 [X86-32] pit,hpet,tsc; 817 scx200_hrt on Geode; cyclone on IBM x440 818 [MIPS] MIPS 819 [PARISC] cr16 820 [S390] tod 821 [SH] SuperH 822 [SPARC64] tick 823 [X86-64] hpet,tsc 824 825 clocksource.arm_arch_timer.evtstrm= 826 [ARM,ARM64,EARLY] 827 Format: <bool> 828 Enable/disable the eventstream feature of the ARM 829 architected timer so that code using WFE-based polling 830 loops can be debugged more effectively on production 831 systems. 832 833 clocksource.verify_n_cpus= [KNL] 834 Limit the number of CPUs checked for clocksources 835 marked with CLOCK_SOURCE_VERIFY_PERCPU that 836 are marked unstable due to excessive skew. 837 A negative value says to check all CPUs, while 838 zero says not to check any. Values larger than 839 nr_cpu_ids are silently truncated to nr_cpu_ids. 840 The actual CPUs are chosen randomly, with 841 no replacement if the same CPU is chosen twice. 842 843 clocksource-wdtest.holdoff= [KNL] 844 Set the time in seconds that the clocksource 845 watchdog test waits before commencing its tests. 846 Defaults to zero when built as a module and to 847 10 seconds when built into the kernel. 848 849 cma=nn[MG]@[start[MG][-end[MG]]] 850 [KNL,CMA,EARLY] 851 Sets the size of kernel global memory area for 852 contiguous memory allocations and optionally the 853 placement constraint by the physical address range of 854 memory allocations. A value of 0 disables CMA 855 altogether. For more information, see 856 kernel/dma/contiguous.c 857 858 cma_pernuma=nn[MG] 859 [KNL,CMA,EARLY] 860 Sets the size of kernel per-numa memory area for 861 contiguous memory allocations. A value of 0 disables 862 per-numa CMA altogether. And If this option is not 863 specified, the default value is 0. 864 With per-numa CMA enabled, DMA users on node nid will 865 first try to allocate buffer from the pernuma area 866 which is located in node nid, if the allocation fails, 867 they will fallback to the global default memory area. 868 869 numa_cma=<node>:nn[MG][,<node>:nn[MG]] 870 [KNL,CMA,EARLY] 871 Sets the size of kernel numa memory area for 872 contiguous memory allocations. It will reserve CMA 873 area for the specified node. 874 875 If it is setup together with upper 'cmd_pernuma=' 876 (unlikely), its size setting takes priority for the 877 specified numa nodes. 878 879 With numa CMA enabled, DMA users on node nid will 880 first try to allocate buffer from the numa area 881 which is located in node nid, if the allocation fails, 882 they will fallback to the global default memory area. 883 884 cmo_free_hint= [PPC] Format: { yes | no } 885 Specify whether pages are marked as being inactive 886 when they are freed. This is used in CMO environments 887 to determine OS memory pressure for page stealing by 888 a hypervisor. 889 Default: yes 890 891 coherent_pool=nn[KMG] [ARM,KNL,EARLY] 892 Sets the size of memory pool for coherent, atomic dma 893 allocations, by default set to 256K. 894 895 condev= [HW,S390] console device 896 conmode= 897 898 con3215_drop= [S390,EARLY] 3215 console drop mode. 899 Format: y|n|Y|N|1|0 900 When set to true, drop data on the 3215 console when 901 the console buffer is full. In this case the 902 operator using a 3270 terminal emulator (for example 903 x3270) does not have to enter the clear key for the 904 console output to advance and the kernel to continue. 905 This leads to a much faster boot time when a 3270 906 terminal emulator is active. If no 3270 terminal 907 emulator is used, this parameter has no effect. 908 909 console= [KNL] Output console device and options. 910 911 tty<n> Use the virtual console device <n>. 912 913 ttyS<n>[,options] 914 ttyUSB0[,options] 915 Use the specified serial port. The options are of 916 the form "bbbbpnf", where "bbbb" is the baud rate, 917 "p" is parity ("n", "o", or "e"), "n" is number of 918 bits, and "f" is flow control ("r" for RTS or 919 omit it). Default is "9600n8". 920 921 See Documentation/admin-guide/serial-console.rst for more 922 information. See 923 Documentation/networking/netconsole.rst for an 924 alternative. 925 926 <DEVNAME>:<n>.<n>[,options] 927 Use the specified serial port on the serial core bus. 928 The addressing uses DEVNAME of the physical serial port 929 device, followed by the serial core controller instance, 930 and the serial port instance. The options are the same 931 as documented for the ttyS addressing above. 932 933 The mapping of the serial ports to the tty instances 934 can be viewed with: 935 936 $ ls -d /sys/bus/serial-base/devices/*:*.*/tty/* 937 /sys/bus/serial-base/devices/00:04:0.0/tty/ttyS0 938 939 In the above example, the console can be addressed with 940 console=00:04:0.0. Note that a console addressed this 941 way will only get added when the related device driver 942 is ready. The use of an earlycon parameter in addition to 943 the console may be desired for console output early on. 944 945 uart[8250],io,<addr>[,options] 946 uart[8250],mmio,<addr>[,options] 947 uart[8250],mmio16,<addr>[,options] 948 uart[8250],mmio32,<addr>[,options] 949 uart[8250],0x<addr>[,options] 950 Start an early, polled-mode console on the 8250/16550 951 UART at the specified I/O port or MMIO address, 952 switching to the matching ttyS device later. 953 MMIO inter-register address stride is either 8-bit 954 (mmio), 16-bit (mmio16), or 32-bit (mmio32). 955 If none of [io|mmio|mmio16|mmio32], <addr> is assumed 956 to be equivalent to 'mmio'. 'options' are specified in 957 the same format described for ttyS above; if unspecified, 958 the h/w is not re-initialized. 959 960 hvc<n> Use the hypervisor console device <n>. This is for 961 both Xen and PowerPC hypervisors. 962 963 { null | "" } 964 Use to disable console output, i.e., to have kernel 965 console messages discarded. 966 This must be the only console= parameter used on the 967 kernel command line. 968 969 If the device connected to the port is not a TTY but a braille 970 device, prepend "brl," before the device type, for instance 971 console=brl,ttyS0 972 For now, only VisioBraille is supported. 973 974 console_msg_format= 975 [KNL] Change console messages format 976 default 977 By default we print messages on consoles in 978 "[time stamp] text\n" format (time stamp may not be 979 printed, depending on CONFIG_PRINTK_TIME or 980 `printk_time' param). 981 syslog 982 Switch to syslog format: "<%u>[time stamp] text\n" 983 IOW, each message will have a facility and loglevel 984 prefix. The format is similar to one used by syslog() 985 syscall, or to executing "dmesg -S --raw" or to reading 986 from /proc/kmsg. 987 988 consoleblank= [KNL] The console blank (screen saver) timeout in 989 seconds. A value of 0 disables the blank timer. 990 Defaults to 0. 991 992 coredump_filter= 993 [KNL] Change the default value for 994 /proc/<pid>/coredump_filter. 995 See also Documentation/filesystems/proc.rst. 996 997 coresight_cpu_debug.enable 998 [ARM,ARM64] 999 Format: <bool> 1000 Enable/disable the CPU sampling based debugging. 1001 0: default value, disable debugging 1002 1: enable debugging at boot time 1003 1004 cpcihp_generic= [HW,PCI] Generic port I/O CompactPCI driver 1005 Format: 1006 <first_slot>,<last_slot>,<port>,<enum_bit>[,<debug>] 1007 1008 cpuidle.off=1 [CPU_IDLE] 1009 disable the cpuidle sub-system 1010 1011 cpuidle.governor= 1012 [CPU_IDLE] Name of the cpuidle governor to use. 1013 1014 cpufreq.off=1 [CPU_FREQ] 1015 disable the cpufreq sub-system 1016 1017 cpufreq.default_governor= 1018 [CPU_FREQ] Name of the default cpufreq governor or 1019 policy to use. This governor must be registered in the 1020 kernel before the cpufreq driver probes. 1021 1022 cpu_init_udelay=N 1023 [X86,EARLY] Delay for N microsec between assert and de-assert 1024 of APIC INIT to start processors. This delay occurs 1025 on every CPU online, such as boot, and resume from suspend. 1026 Default: 10000 1027 1028 cpuhp.parallel= 1029 [SMP] Enable/disable parallel bringup of secondary CPUs 1030 Format: <bool> 1031 Default is enabled if CONFIG_HOTPLUG_PARALLEL=y. Otherwise 1032 the parameter has no effect. 1033 1034 crash_kexec_post_notifiers 1035 Only jump to kdump kernel after running the panic 1036 notifiers and dumping kmsg. This option increases 1037 the risks of a kdump failure, since some panic 1038 notifiers can make the crashed kernel more unstable. 1039 In configurations where kdump may not be reliable, 1040 running the panic notifiers could allow collecting 1041 more data on dmesg, like stack traces from other CPUS 1042 or extra data dumped by panic_print. Note that some 1043 configurations enable this option unconditionally, 1044 like Hyper-V, PowerPC (fadump) and AMD SEV-SNP. 1045 1046 crashkernel=size[KMG][@offset[KMG]] 1047 [KNL,EARLY] Using kexec, Linux can switch to a 'crash kernel' 1048 upon panic. This parameter reserves the physical 1049 memory region [offset, offset + size] for that kernel 1050 image. If '@offset' is omitted, then a suitable offset 1051 is selected automatically. 1052 [KNL, X86-64, ARM64, RISCV, LoongArch] Select a region 1053 under 4G first, and fall back to reserve region above 1054 4G when '@offset' hasn't been specified. 1055 See Documentation/admin-guide/kdump/kdump.rst for further details. 1056 1057 crashkernel=range1:size1[,range2:size2,...][@offset] 1058 [KNL] Same as above, but depends on the memory 1059 in the running system. The syntax of range is 1060 start-[end] where start and end are both 1061 a memory unit (amount[KMG]). See also 1062 Documentation/admin-guide/kdump/kdump.rst for an example. 1063 1064 crashkernel=size[KMG],high 1065 [KNL, X86-64, ARM64, RISCV, LoongArch] range could be 1066 above 4G. 1067 Allow kernel to allocate physical memory region from top, 1068 so could be above 4G if system have more than 4G ram 1069 installed. Otherwise memory region will be allocated 1070 below 4G, if available. 1071 It will be ignored if crashkernel=X is specified. 1072 crashkernel=size[KMG],low 1073 [KNL, X86-64, ARM64, RISCV, LoongArch] range under 4G. 1074 When crashkernel=X,high is passed, kernel could allocate 1075 physical memory region above 4G, that cause second kernel 1076 crash on system that require some amount of low memory, 1077 e.g. swiotlb requires at least 64M+32K low memory, also 1078 enough extra low memory is needed to make sure DMA buffers 1079 for 32-bit devices won't run out. Kernel would try to allocate 1080 default size of memory below 4G automatically. The default 1081 size is platform dependent. 1082 --> x86: max(swiotlb_size_or_default() + 8MiB, 256MiB) 1083 --> arm64: 128MiB 1084 --> riscv: 128MiB 1085 --> loongarch: 128MiB 1086 This one lets the user specify own low range under 4G 1087 for second kernel instead. 1088 0: to disable low allocation. 1089 It will be ignored when crashkernel=X,high is not used 1090 or memory reserved is below 4G. 1091 crashkernel=size[KMG],cma 1092 [KNL, X86, ppc] Reserve additional crash kernel memory from 1093 CMA. This reservation is usable by the first system's 1094 userspace memory and kernel movable allocations (memory 1095 balloon, zswap). Pages allocated from this memory range 1096 will not be included in the vmcore so this should not 1097 be used if dumping of userspace memory is intended and 1098 it has to be expected that some movable kernel pages 1099 may be missing from the dump. 1100 1101 A standard crashkernel reservation, as described above, 1102 is still needed to hold the crash kernel and initrd. 1103 1104 This option increases the risk of a kdump failure: DMA 1105 transfers configured by the first kernel may end up 1106 corrupting the second kernel's memory. 1107 1108 This reservation method is intended for systems that 1109 can't afford to sacrifice enough memory for standard 1110 crashkernel reservation and where less reliable and 1111 possibly incomplete kdump is preferable to no kdump at 1112 all. 1113 1114 cryptomgr.notests 1115 [KNL] Disable crypto self-tests 1116 1117 cs89x0_dma= [HW,NET] 1118 Format: <dma> 1119 1120 cs89x0_media= [HW,NET] 1121 Format: { rj45 | aui | bnc } 1122 1123 csdlock_debug= [KNL] Enable or disable debug add-ons of cross-CPU 1124 function call handling. When switched on, 1125 additional debug data is printed to the console 1126 in case a hanging CPU is detected, and that 1127 CPU is pinged again in order to try to resolve 1128 the hang situation. The default value of this 1129 option depends on the CSD_LOCK_WAIT_DEBUG_DEFAULT 1130 Kconfig option. 1131 1132 dasd= [HW,NET] 1133 See header of drivers/s390/block/dasd_devmap.c. 1134 1135 db9.dev[2|3]= [HW,JOY] Multisystem joystick support via parallel port 1136 (one device per port) 1137 Format: <port#>,<type> 1138 See also Documentation/input/devices/joystick-parport.rst 1139 1140 debug [KNL,EARLY] Enable kernel debugging (events log level). 1141 1142 debug_boot_weak_hash 1143 [KNL,EARLY] Enable printing [hashed] pointers early in the 1144 boot sequence. If enabled, we use a weak hash instead 1145 of siphash to hash pointers. Use this option if you are 1146 seeing instances of '(___ptrval___)') and need to see a 1147 value (hashed pointer) instead. Cryptographically 1148 insecure, please do not use on production kernels. 1149 1150 debug_locks_verbose= 1151 [KNL] verbose locking self-tests 1152 Format: <int> 1153 Print debugging info while doing the locking API 1154 self-tests. 1155 Bitmask for the various LOCKTYPE_ tests. Defaults to 0 1156 (no extra messages), setting it to -1 (all bits set) 1157 will print _a_lot_ more information - normally only 1158 useful to lockdep developers. 1159 1160 debug_objects [KNL,EARLY] Enable object debugging 1161 1162 debug_guardpage_minorder= 1163 [KNL,EARLY] When CONFIG_DEBUG_PAGEALLOC is set, this 1164 parameter allows control of the order of pages that will 1165 be intentionally kept free (and hence protected) by the 1166 buddy allocator. Bigger value increase the probability 1167 of catching random memory corruption, but reduce the 1168 amount of memory for normal system use. The maximum 1169 possible value is MAX_PAGE_ORDER/2. Setting this 1170 parameter to 1 or 2 should be enough to identify most 1171 random memory corruption problems caused by bugs in 1172 kernel or driver code when a CPU writes to (or reads 1173 from) a random memory location. Note that there exists 1174 a class of memory corruptions problems caused by buggy 1175 H/W or F/W or by drivers badly programming DMA 1176 (basically when memory is written at bus level and the 1177 CPU MMU is bypassed) which are not detectable by 1178 CONFIG_DEBUG_PAGEALLOC, hence this option will not 1179 help tracking down these problems. 1180 1181 debug_pagealloc= 1182 [KNL,EARLY] When CONFIG_DEBUG_PAGEALLOC is set, this parameter 1183 enables the feature at boot time. By default, it is 1184 disabled and the system will work mostly the same as a 1185 kernel built without CONFIG_DEBUG_PAGEALLOC. 1186 Note: to get most of debug_pagealloc error reports, it's 1187 useful to also enable the page_owner functionality. 1188 on: enable the feature 1189 1190 debugfs= [KNL,EARLY] This parameter enables what is exposed to 1191 userspace and debugfs internal clients. 1192 Format: { on, off } 1193 on: All functions are enabled. 1194 off: Filesystem is not registered and clients 1195 get a -EPERM as result when trying to register files 1196 or directories within debugfs. 1197 This is equivalent of the runtime functionality if 1198 debugfs was not enabled in the kernel at all. 1199 Default value is set in build-time with a kernel configuration. 1200 1201 debugpat [X86] Enable PAT debugging 1202 1203 default_hugepagesz= 1204 [HW] The size of the default HugeTLB page. This is 1205 the size represented by the legacy /proc/ hugepages 1206 APIs. In addition, this is the default hugetlb size 1207 used for shmget(), mmap() and mounting hugetlbfs 1208 filesystems. If not specified, defaults to the 1209 architecture's default huge page size. Huge page 1210 sizes are architecture dependent. See also 1211 Documentation/admin-guide/mm/hugetlbpage.rst. 1212 Format: size[KMG] 1213 1214 deferred_probe_timeout= 1215 [KNL] Debugging option to set a timeout in seconds for 1216 deferred probe to give up waiting on dependencies to 1217 probe. Only specific dependencies (subsystems or 1218 drivers) that have opted in will be ignored. A timeout 1219 of 0 will timeout at the end of initcalls; a negative 1220 value is treated as an infinite timeout value. If the 1221 timeout hasn't expired, it'll be restarted by each 1222 successful driver registration. This option will also 1223 dump out devices still on the deferred probe list after 1224 retrying. 1225 1226 delayacct [KNL] Enable per-task delay accounting 1227 1228 dell_smm_hwmon.ignore_dmi= 1229 [HW] Continue probing hardware even if DMI data 1230 indicates that the driver is running on unsupported 1231 hardware. 1232 1233 dell_smm_hwmon.force= 1234 [HW] Activate driver even if SMM BIOS signature does 1235 not match list of supported models and enable otherwise 1236 blacklisted features. 1237 1238 dell_smm_hwmon.power_status= 1239 [HW] Report power status in /proc/i8k 1240 (disabled by default). 1241 1242 dell_smm_hwmon.restricted= 1243 [HW] Allow controlling fans only if SYS_ADMIN 1244 capability is set. 1245 1246 dell_smm_hwmon.fan_mult= 1247 [HW] Factor to multiply fan speed with. 1248 1249 dell_smm_hwmon.fan_max= 1250 [HW] Maximum configurable fan speed. 1251 1252 dfltcc= [HW,S390] 1253 Format: { on | off | def_only | inf_only | always } 1254 on: s390 zlib hardware support for compression on 1255 level 1 and decompression (default) 1256 off: No s390 zlib hardware support 1257 def_only: s390 zlib hardware support for deflate 1258 only (compression on level 1) 1259 inf_only: s390 zlib hardware support for inflate 1260 only (decompression) 1261 always: Same as 'on' but ignores the selected compression 1262 level always using hardware support (used for debugging) 1263 1264 dhash_entries= [KNL] 1265 Set number of hash buckets for dentry cache. 1266 1267 disable_1tb_segments [PPC,EARLY] 1268 Disables the use of 1TB hash page table segments. This 1269 causes the kernel to fall back to 256MB segments which 1270 can be useful when debugging issues that require an SLB 1271 miss to occur. 1272 1273 disable= [IPV6] 1274 See Documentation/networking/ipv6.rst. 1275 1276 disable_radix [PPC,EARLY] 1277 Disable RADIX MMU mode on POWER9 1278 1279 disable_tlbie [PPC] 1280 Disable TLBIE instruction. Currently does not work 1281 with KVM, with HASH MMU, or with coherent accelerators. 1282 1283 disable_ddw [PPC/PSERIES,EARLY] 1284 Disable Dynamic DMA Window support. Use this 1285 to workaround buggy firmware. 1286 1287 disable_ipv6= [IPV6] 1288 See Documentation/networking/ipv6.rst. 1289 1290 disable_mtrr_cleanup [X86,EARLY] 1291 The kernel tries to adjust MTRR layout from continuous 1292 to discrete, to make X server driver able to add WB 1293 entry later. This parameter disables that. 1294 1295 disable_mtrr_trim [X86, Intel and AMD only,EARLY] 1296 By default the kernel will trim any uncacheable 1297 memory out of your available memory pool based on 1298 MTRR settings. This parameter disables that behavior, 1299 possibly causing your machine to run very slowly. 1300 1301 disable_timer_pin_1 [X86,EARLY] 1302 Disable PIN 1 of APIC timer 1303 Can be useful to work around chipset bugs. 1304 1305 dis_ucode_ldr [X86] Disable the microcode loader. 1306 1307 dma_debug=off If the kernel is compiled with DMA_API_DEBUG support, 1308 this option disables the debugging code at boot. 1309 1310 dma_debug_entries=<number> 1311 This option allows to tune the number of preallocated 1312 entries for DMA-API debugging code. One entry is 1313 required per DMA-API allocation. Use this if the 1314 DMA-API debugging code disables itself because the 1315 architectural default is too low. 1316 1317 dma_debug_driver=<driver_name> 1318 With this option the DMA-API debugging driver 1319 filter feature can be enabled at boot time. Just 1320 pass the driver to filter for as the parameter. 1321 The filter can be disabled or changed to another 1322 driver later using sysfs. 1323 1324 reg_file_data_sampling= 1325 [X86] Controls mitigation for Register File Data 1326 Sampling (RFDS) vulnerability. RFDS is a CPU 1327 vulnerability which may allow userspace to infer 1328 kernel data values previously stored in floating point 1329 registers, vector registers, or integer registers. 1330 RFDS only affects Intel Atom processors. 1331 1332 on: Turns ON the mitigation. 1333 off: Turns OFF the mitigation. 1334 1335 This parameter overrides the compile time default set 1336 by CONFIG_MITIGATION_RFDS. Mitigation cannot be 1337 disabled when other VERW based mitigations (like MDS) 1338 are enabled. In order to disable RFDS mitigation all 1339 VERW based mitigations need to be disabled. 1340 1341 For details see: 1342 Documentation/admin-guide/hw-vuln/reg-file-data-sampling.rst 1343 1344 dm_verity.keyring_unsealed= 1345 [KNL] When set to 1, leave the dm-verity keyring 1346 unsealed after initialization so userspace can 1347 provision keys. Once the keyring is restricted 1348 it becomes active and is searched during signature 1349 verification. 1350 1351 driver_async_probe= [KNL] 1352 List of driver names to be probed asynchronously. * 1353 matches with all driver names. If * is specified, the 1354 rest of the listed driver names are those that will NOT 1355 match the *. 1356 Format: <driver_name1>,<driver_name2>... 1357 1358 drm.edid_firmware=[<connector>:]<file>[,[<connector>:]<file>] 1359 Broken monitors, graphic adapters, KVMs and EDIDless 1360 panels may send no or incorrect EDID data sets. 1361 This parameter allows to specify an EDID data sets 1362 in the /lib/firmware directory that are used instead. 1363 An EDID data set will only be used for a particular 1364 connector, if its name and a colon are prepended to 1365 the EDID name. Each connector may use a unique EDID 1366 data set by separating the files with a comma. An EDID 1367 data set with no connector name will be used for 1368 any connectors not explicitly specified. 1369 1370 dscc4.setup= [NET] 1371 1372 dt_cpu_ftrs= [PPC,EARLY] 1373 Format: {"off" | "known"} 1374 Control how the dt_cpu_ftrs device-tree binding is 1375 used for CPU feature discovery and setup (if it 1376 exists). 1377 off: Do not use it, fall back to legacy cpu table. 1378 known: Do not pass through unknown features to guests 1379 or userspace, only those that the kernel is aware of. 1380 1381 dump_apple_properties [X86] 1382 Dump name and content of EFI device properties on 1383 x86 Macs. Useful for driver authors to determine 1384 what data is available or for reverse-engineering. 1385 1386 dyndbg[="val"] [KNL,DYNAMIC_DEBUG] 1387 <module>.dyndbg[="val"] 1388 Enable debug messages at boot time. See 1389 Documentation/admin-guide/dynamic-debug-howto.rst 1390 for details. 1391 1392 early_ioremap_debug [KNL,EARLY] 1393 Enable debug messages in early_ioremap support. This 1394 is useful for tracking down temporary early mappings 1395 which are not unmapped. 1396 1397 earlycon= [KNL,EARLY] Output early console device and options. 1398 1399 When used with no options, the early console is 1400 determined by stdout-path property in device tree's 1401 chosen node or the ACPI SPCR table if supported by 1402 the platform. 1403 1404 cdns,<addr>[,options] 1405 Start an early, polled-mode console on a Cadence 1406 (xuartps) serial port at the specified address. Only 1407 supported option is baud rate. If baud rate is not 1408 specified, the serial port must already be setup and 1409 configured. 1410 1411 uart[8250],io,<addr>[,options[,uartclk]] 1412 uart[8250],mmio,<addr>[,options[,uartclk]] 1413 uart[8250],mmio32,<addr>[,options[,uartclk]] 1414 uart[8250],mmio32be,<addr>[,options[,uartclk]] 1415 uart[8250],0x<addr>[,options] 1416 Start an early, polled-mode console on the 8250/16550 1417 UART at the specified I/O port or MMIO address. 1418 MMIO inter-register address stride is either 8-bit 1419 (mmio) or 32-bit (mmio32 or mmio32be). 1420 If none of [io|mmio|mmio32|mmio32be], <addr> is assumed 1421 to be equivalent to 'mmio'. 'options' are specified 1422 in the same format described for "console=ttyS<n>"; if 1423 unspecified, the h/w is not initialized. 'uartclk' is 1424 the uart clock frequency; if unspecified, it is set 1425 to 'BASE_BAUD' * 16. 1426 1427 pl011,<addr> 1428 pl011,mmio32,<addr> 1429 Start an early, polled-mode console on a pl011 serial 1430 port at the specified address. The pl011 serial port 1431 must already be setup and configured. Options are not 1432 yet supported. If 'mmio32' is specified, then only 1433 the driver will use only 32-bit accessors to read/write 1434 the device registers. 1435 1436 liteuart,<addr> 1437 Start an early console on a litex serial port at the 1438 specified address. The serial port must already be 1439 setup and configured. Options are not yet supported. 1440 1441 meson,<addr> 1442 Start an early, polled-mode console on a meson serial 1443 port at the specified address. The serial port must 1444 already be setup and configured. Options are not yet 1445 supported. 1446 1447 msm_serial,<addr> 1448 Start an early, polled-mode console on an msm serial 1449 port at the specified address. The serial port 1450 must already be setup and configured. Options are not 1451 yet supported. 1452 1453 msm_serial_dm,<addr> 1454 Start an early, polled-mode console on an msm serial 1455 dm port at the specified address. The serial port 1456 must already be setup and configured. Options are not 1457 yet supported. 1458 1459 owl,<addr> 1460 Start an early, polled-mode console on a serial port 1461 of an Actions Semi SoC, such as S500 or S900, at the 1462 specified address. The serial port must already be 1463 setup and configured. Options are not yet supported. 1464 1465 rda,<addr> 1466 Start an early, polled-mode console on a serial port 1467 of an RDA Micro SoC, such as RDA8810PL, at the 1468 specified address. The serial port must already be 1469 setup and configured. Options are not yet supported. 1470 1471 sbi 1472 Use RISC-V SBI (Supervisor Binary Interface) for early 1473 console. 1474 1475 smh Use ARM semihosting calls for early console. 1476 1477 s3c2410,<addr> 1478 s3c2412,<addr> 1479 s3c2440,<addr> 1480 s3c6400,<addr> 1481 s5pv210,<addr> 1482 exynos4210,<addr> 1483 Use early console provided by serial driver available 1484 on Samsung SoCs, requires selecting proper type and 1485 a correct base address of the selected UART port. The 1486 serial port must already be setup and configured. 1487 Options are not yet supported. 1488 1489 lantiq,<addr> 1490 Start an early, polled-mode console on a lantiq serial 1491 (lqasc) port at the specified address. The serial port 1492 must already be setup and configured. Options are not 1493 yet supported. 1494 1495 lpuart,<addr> 1496 lpuart32,<addr> 1497 Use early console provided by Freescale LP UART driver 1498 found on Freescale Vybrid and QorIQ LS1021A processors. 1499 A valid base address must be provided, and the serial 1500 port must already be setup and configured. 1501 1502 ec_imx21,<addr> 1503 ec_imx6q,<addr> 1504 Start an early, polled-mode, output-only console on the 1505 Freescale i.MX UART at the specified address. The UART 1506 must already be setup and configured. 1507 1508 ar3700_uart,<addr> 1509 Start an early, polled-mode console on the 1510 Armada 3700 serial port at the specified 1511 address. The serial port must already be setup 1512 and configured. Options are not yet supported. 1513 1514 qcom_geni,<addr> 1515 Start an early, polled-mode console on a Qualcomm 1516 Generic Interface (GENI) based serial port at the 1517 specified address. The serial port must already be 1518 setup and configured. Options are not yet supported. 1519 1520 efifb,[options] 1521 Start an early, unaccelerated console on the EFI 1522 memory mapped framebuffer (if available). On cache 1523 coherent non-x86 systems that use system memory for 1524 the framebuffer, pass the 'ram' option so that it is 1525 mapped with the correct attributes. 1526 1527 linflex,<addr> 1528 Use early console provided by Freescale LINFlexD UART 1529 serial driver for NXP S32V234 SoCs. A valid base 1530 address must be provided, and the serial port must 1531 already be setup and configured. 1532 1533 earlyprintk= [X86,SH,ARM,M68k,S390,UM,EARLY] 1534 earlyprintk=vga 1535 earlyprintk=sclp 1536 earlyprintk=xen 1537 earlyprintk=serial[,ttySn[,baudrate]] 1538 earlyprintk=serial[,0x...[,baudrate]] 1539 earlyprintk=ttySn[,baudrate] 1540 earlyprintk=dbgp[debugController#] 1541 earlyprintk=mmio32,membase[,{nocfg|baudrate}] 1542 earlyprintk=pciserial[,force],bus:device.function[,{nocfg|baudrate}] 1543 earlyprintk=xdbc[xhciController#] 1544 earlyprintk=bios 1545 1546 earlyprintk is useful when the kernel crashes before 1547 the normal console is initialized. It is not enabled by 1548 default because it has some cosmetic problems. 1549 1550 Use "nocfg" to skip UART configuration, assume 1551 BIOS/firmware has configured UART correctly. 1552 1553 Append ",keep" to not disable it when the real console 1554 takes over. 1555 1556 Only one of vga, serial, or usb debug port can 1557 be used at a time. 1558 1559 Currently only ttyS0 and ttyS1 may be specified by 1560 name. Other I/O ports may be explicitly specified 1561 on some architectures (x86 and arm at least) by 1562 replacing ttySn with an I/O port address, like this: 1563 earlyprintk=serial,0x1008,115200 1564 You can find the port for a given device in 1565 /proc/tty/driver/serial: 1566 2: uart:ST16650V2 port:00001008 irq:18 ... 1567 1568 Interaction with the standard serial driver is not 1569 very good. 1570 1571 The VGA output is eventually overwritten by 1572 the real console. 1573 1574 The xen option can only be used in Xen domains. 1575 1576 The sclp output can only be used on s390. 1577 1578 The bios output can only be used on SuperH. 1579 1580 The optional "force" to "pciserial" enables use of a 1581 PCI device even when its classcode is not of the 1582 UART class. 1583 1584 edac_report= [HW,EDAC] Control how to report EDAC event 1585 Format: {"on" | "off" | "force"} 1586 on: enable EDAC to report H/W event. May be overridden 1587 by other higher priority error reporting module. 1588 off: disable H/W event reporting through EDAC. 1589 force: enforce the use of EDAC to report H/W event. 1590 default: on. 1591 1592 edd= [EDD] 1593 Format: {"off" | "on" | "skip[mbr]"} 1594 1595 efi= [EFI,EARLY] 1596 Format: { "debug", "disable_early_pci_dma", 1597 "nochunk", "noruntime", "nosoftreserve", 1598 "novamap", "no_disable_early_pci_dma" } 1599 debug: enable misc debug output. 1600 disable_early_pci_dma: disable the busmaster bit on all 1601 PCI bridges while in the EFI boot stub. 1602 nochunk: disable reading files in "chunks" in the EFI 1603 boot stub, as chunking can cause problems with some 1604 firmware implementations. 1605 noruntime : disable EFI runtime services support 1606 nosoftreserve: The EFI_MEMORY_SP (Specific Purpose) 1607 attribute may cause the kernel to reserve the 1608 memory range for a memory mapping driver to 1609 claim. Specify efi=nosoftreserve to disable this 1610 reservation and treat the memory by its base type 1611 (i.e. EFI_CONVENTIONAL_MEMORY / "System RAM"). 1612 novamap: do not call SetVirtualAddressMap(). 1613 no_disable_early_pci_dma: Leave the busmaster bit set 1614 on all PCI bridges while in the EFI boot stub 1615 1616 efi_no_storage_paranoia [EFI,X86,EARLY] 1617 Using this parameter you can use more than 50% of 1618 your efi variable storage. Use this parameter only if 1619 you are really sure that your UEFI does sane gc and 1620 fulfills the spec otherwise your board may brick. 1621 1622 efivar_ssdt= [EFI; X86] Name of an EFI variable that contains an SSDT 1623 that is to be dynamically loaded by Linux. If there are 1624 multiple variables with the same name but with different 1625 vendor GUIDs, all of them will be loaded. See 1626 Documentation/admin-guide/acpi/ssdt-overlays.rst for details. 1627 1628 1629 eisa_irq_edge= [PARISC,HW] 1630 See header of drivers/parisc/eisa.c. 1631 1632 ekgdboc= [X86,KGDB,EARLY] Allow early kernel console debugging 1633 Format: ekgdboc=kbd 1634 1635 This is designed to be used in conjunction with 1636 the boot argument: earlyprintk=vga 1637 1638 This parameter works in place of the kgdboc parameter 1639 but can only be used if the backing tty is available 1640 very early in the boot process. For early debugging 1641 via a serial port see kgdboc_earlycon instead. 1642 1643 elfcorehdr=[size[KMG]@]offset[KMG] [PPC,SH,X86,S390,EARLY] 1644 Specifies physical address of start of kernel core 1645 image elf header and optionally the size. Generally 1646 kexec loader will pass this option to capture kernel. 1647 See Documentation/admin-guide/kdump/kdump.rst for details. 1648 1649 enable_mtrr_cleanup [X86,EARLY] 1650 The kernel tries to adjust MTRR layout from continuous 1651 to discrete, to make X server driver able to add WB 1652 entry later. This parameter enables that. 1653 1654 enable_timer_pin_1 [X86] 1655 Enable PIN 1 of APIC timer 1656 Can be useful to work around chipset bugs 1657 (in particular on some ATI chipsets). 1658 The kernel tries to set a reasonable default. 1659 1660 enforcing= [SELINUX] Set initial enforcing status. 1661 Format: {"0" | "1"} 1662 See security/selinux/Kconfig help text. 1663 0 -- permissive (log only, no denials). 1664 1 -- enforcing (deny and log). 1665 Default value is 0. 1666 Value can be changed at runtime via 1667 /sys/fs/selinux/enforce. 1668 1669 erst_disable [ACPI] 1670 Disable Error Record Serialization Table (ERST) 1671 support. 1672 1673 ether= [HW,NET] Ethernet cards parameters 1674 This option is obsoleted by the "netdev=" option, which 1675 has equivalent usage. See its documentation for details. 1676 1677 evm= [EVM] 1678 Format: { "fix" } 1679 Permit 'security.evm' to be updated regardless of 1680 current integrity status. 1681 1682 early_page_ext [KNL,EARLY] Enforces page_ext initialization to earlier 1683 stages so cover more early boot allocations. 1684 Please note that as side effect some optimizations 1685 might be disabled to achieve that (e.g. parallelized 1686 memory initialization is disabled) so the boot process 1687 might take longer, especially on systems with a lot of 1688 memory. Available with CONFIG_PAGE_EXTENSION=y. 1689 1690 failslab= 1691 fail_usercopy= 1692 fail_page_alloc= 1693 fail_skb_realloc= 1694 fail_make_request=[KNL] 1695 General fault injection mechanism. 1696 Format: <interval>,<probability>,<space>,<times> 1697 See also Documentation/fault-injection/. 1698 1699 fb_tunnels= [NET] 1700 Format: { initns | none } 1701 See Documentation/admin-guide/sysctl/net.rst for 1702 fb_tunnels_only_for_init_ns 1703 1704 floppy= [HW] 1705 See Documentation/admin-guide/blockdev/floppy.rst. 1706 1707 forcepae [X86-32] 1708 Forcefully enable Physical Address Extension (PAE). 1709 Many Pentium M systems disable PAE but may have a 1710 functionally usable PAE implementation. 1711 Warning: use of this parameter will taint the kernel 1712 and may cause unknown problems. 1713 1714 fred= [X86-64] 1715 Enable/disable Flexible Return and Event Delivery. 1716 Format: { on | off } 1717 on: enable FRED when it's present, the default setting. 1718 off: disable FRED. 1719 1720 ftrace=[tracer] 1721 [FTRACE] will set and start the specified tracer 1722 as early as possible in order to facilitate early 1723 boot debugging. 1724 1725 ftrace_boot_snapshot 1726 [FTRACE] On boot up, a snapshot will be taken of the 1727 ftrace ring buffer that can be read at: 1728 /sys/kernel/tracing/snapshot. 1729 This is useful if you need tracing information from kernel 1730 boot up that is likely to be overridden by user space 1731 start up functionality. 1732 1733 Optionally, the snapshot can also be defined for a tracing 1734 instance that was created by the trace_instance= command 1735 line parameter. 1736 1737 trace_instance=foo,sched_switch ftrace_boot_snapshot=foo 1738 1739 The above will cause the "foo" tracing instance to trigger 1740 a snapshot at the end of boot up. 1741 1742 ftrace_dump_on_oops[=2(orig_cpu) | =<instance>][,<instance> | 1743 ,<instance>=2(orig_cpu)] 1744 [FTRACE] will dump the trace buffers on oops. 1745 If no parameter is passed, ftrace will dump global 1746 buffers of all CPUs, if you pass 2 or orig_cpu, it 1747 will dump only the buffer of the CPU that triggered 1748 the oops, or the specific instance will be dumped if 1749 its name is passed. Multiple instance dump is also 1750 supported, and instances are separated by commas. Each 1751 instance supports only dump on CPU that triggered the 1752 oops by passing 2 or orig_cpu to it. 1753 1754 ftrace_dump_on_oops=foo=orig_cpu 1755 1756 The above will dump only the buffer of "foo" instance 1757 on CPU that triggered the oops. 1758 1759 ftrace_dump_on_oops,foo,bar=orig_cpu 1760 1761 The above will dump global buffer on all CPUs, the 1762 buffer of "foo" instance on all CPUs and the buffer 1763 of "bar" instance on CPU that triggered the oops. 1764 1765 ftrace_filter=[function-list] 1766 [FTRACE] Limit the functions traced by the function 1767 tracer at boot up. function-list is a comma-separated 1768 list of functions. This list can be changed at run 1769 time by the set_ftrace_filter file in the debugfs 1770 tracing directory. 1771 1772 ftrace_notrace=[function-list] 1773 [FTRACE] Do not trace the functions specified in 1774 function-list. This list can be changed at run time 1775 by the set_ftrace_notrace file in the debugfs 1776 tracing directory. 1777 1778 ftrace_graph_filter=[function-list] 1779 [FTRACE] Limit the top level callers functions traced 1780 by the function graph tracer at boot up. 1781 function-list is a comma-separated list of functions 1782 that can be changed at run time by the 1783 set_graph_function file in the debugfs tracing directory. 1784 1785 ftrace_graph_notrace=[function-list] 1786 [FTRACE] Do not trace from the functions specified in 1787 function-list. This list is a comma-separated list of 1788 functions that can be changed at run time by the 1789 set_graph_notrace file in the debugfs tracing directory. 1790 1791 ftrace_graph_max_depth=<uint> 1792 [FTRACE] Used with the function graph tracer. This is 1793 the max depth it will trace into a function. This value 1794 can be changed at run time by the max_graph_depth file 1795 in the tracefs tracing directory. default: 0 (no limit) 1796 1797 fw_devlink= [KNL,EARLY] Create device links between consumer and supplier 1798 devices by scanning the firmware to infer the 1799 consumer/supplier relationships. This feature is 1800 especially useful when drivers are loaded as modules as 1801 it ensures proper ordering of tasks like device probing 1802 (suppliers first, then consumers), supplier boot state 1803 clean up (only after all consumers have probed), 1804 suspend/resume & runtime PM (consumers first, then 1805 suppliers). 1806 Format: { off | permissive | on | rpm } 1807 off -- Don't create device links from firmware info. 1808 permissive -- Create device links from firmware info 1809 but use it only for ordering boot state clean 1810 up (sync_state() calls). 1811 on -- Create device links from firmware info and use it 1812 to enforce probe and suspend/resume ordering. 1813 rpm -- Like "on", but also use to order runtime PM. 1814 1815 fw_devlink.strict=<bool> 1816 [KNL,EARLY] Treat all inferred dependencies as mandatory 1817 dependencies. This only applies for fw_devlink=on|rpm. 1818 Format: <bool> 1819 1820 fw_devlink.sync_state = 1821 [KNL,EARLY] When all devices that could probe have finished 1822 probing, this parameter controls what to do with 1823 devices that haven't yet received their sync_state() 1824 calls. 1825 Format: { strict | timeout } 1826 strict -- Default. Continue waiting on consumers to 1827 probe successfully. 1828 timeout -- Give up waiting on consumers and call 1829 sync_state() on any devices that haven't yet 1830 received their sync_state() calls after 1831 deferred_probe_timeout has expired or by 1832 late_initcall() if !CONFIG_MODULES. 1833 1834 gamecon.map[2|3]= 1835 [HW,JOY] Multisystem joystick and NES/SNES/PSX pad 1836 support via parallel port (up to 5 devices per port) 1837 Format: <port#>,<pad1>,<pad2>,<pad3>,<pad4>,<pad5> 1838 See also Documentation/input/devices/joystick-parport.rst 1839 1840 gamma= [HW,DRM] 1841 1842 gart_fix_e820= [X86-64,EARLY] disable the fix e820 for K8 GART 1843 Format: off | on 1844 default: on 1845 1846 gather_data_sampling= 1847 [X86,INTEL,EARLY] Control the Gather Data Sampling (GDS) 1848 mitigation. 1849 1850 Gather Data Sampling is a hardware vulnerability which 1851 allows unprivileged speculative access to data which was 1852 previously stored in vector registers. 1853 1854 This issue is mitigated by default in updated microcode. 1855 The mitigation may have a performance impact but can be 1856 disabled. On systems without the microcode mitigation 1857 disabling AVX serves as a mitigation. 1858 1859 force: Disable AVX to mitigate systems without 1860 microcode mitigation. No effect if the microcode 1861 mitigation is present. Known to cause crashes in 1862 userspace with buggy AVX enumeration. 1863 1864 off: Disable GDS mitigation. 1865 1866 gbpages [X86] Use GB pages for kernel direct mappings. 1867 1868 gcov_persist= [GCOV] When non-zero (default), profiling data for 1869 kernel modules is saved and remains accessible via 1870 debugfs, even when the module is unloaded/reloaded. 1871 When zero, profiling data is discarded and associated 1872 debugfs files are removed at module unload time. 1873 1874 goldfish [X86] Enable the goldfish android emulator platform. 1875 Don't use this when you are not running on the 1876 android emulator 1877 1878 gpio-mockup.gpio_mockup_ranges 1879 [HW] Sets the ranges of gpiochip of for this device. 1880 Format: <start1>,<end1>,<start2>,<end2>... 1881 gpio-mockup.gpio_mockup_named_lines 1882 [HW] Let the driver know GPIO lines should be named. 1883 1884 gpt [EFI] Forces disk with valid GPT signature but 1885 invalid Protective MBR to be treated as GPT. If the 1886 primary GPT is corrupted, it enables the backup/alternate 1887 GPT to be used instead. 1888 1889 grcan.enable0= [HW] Configuration of physical interface 0. Determines 1890 the "Enable 0" bit of the configuration register. 1891 Format: 0 | 1 1892 Default: 0 1893 grcan.enable1= [HW] Configuration of physical interface 1. Determines 1894 the "Enable 0" bit of the configuration register. 1895 Format: 0 | 1 1896 Default: 0 1897 grcan.select= [HW] Select which physical interface to use. 1898 Format: 0 | 1 1899 Default: 0 1900 grcan.txsize= [HW] Sets the size of the tx buffer. 1901 Format: <unsigned int> such that (txsize & ~0x1fffc0) == 0. 1902 Default: 1024 1903 grcan.rxsize= [HW] Sets the size of the rx buffer. 1904 Format: <unsigned int> such that (rxsize & ~0x1fffc0) == 0. 1905 Default: 1024 1906 1907 hardened_usercopy= 1908 [KNL] Under CONFIG_HARDENED_USERCOPY, whether 1909 hardening is enabled for this boot. Hardened 1910 usercopy checking is used to protect the kernel 1911 from reading or writing beyond known memory 1912 allocation boundaries as a proactive defense 1913 against bounds-checking flaws in the kernel's 1914 copy_to_user()/copy_from_user() interface. 1915 The default is determined by 1916 CONFIG_HARDENED_USERCOPY_DEFAULT_ON. 1917 on Perform hardened usercopy checks. 1918 off Disable hardened usercopy checks. 1919 1920 hardlockup_all_cpu_backtrace= 1921 [KNL] Should the hard-lockup detector generate 1922 backtraces on all cpus. 1923 Format: 0 | 1 1924 1925 hash_pointers= 1926 [KNL,EARLY] 1927 By default, when pointers are printed to the console 1928 or buffers via the %p format string, that pointer is 1929 "hashed", i.e. obscured by hashing the pointer value. 1930 This is a security feature that hides actual kernel 1931 addresses from unprivileged users, but it also makes 1932 debugging the kernel more difficult since unequal 1933 pointers can no longer be compared. The choices are: 1934 Format: { auto | always | never } 1935 Default: auto 1936 1937 auto - Hash pointers unless slab_debug is enabled. 1938 always - Always hash pointers (even if slab_debug is 1939 enabled). 1940 never - Never hash pointers. This option should only 1941 be specified when debugging the kernel. Do 1942 not use on production kernels. The boot 1943 param "no_hash_pointers" is an alias for 1944 this mode. 1945 1946 For controlling hashing dynamically at runtime, 1947 use the "kernel.kptr_restrict" sysctl instead. 1948 1949 hashdist= [KNL,NUMA] Large hashes allocated during boot 1950 are distributed across NUMA nodes. Defaults on 1951 for 64-bit NUMA, off otherwise. 1952 Format: 0 | 1 (for off | on) 1953 1954 hd= [EIDE] (E)IDE hard drive subsystem geometry 1955 Format: <cyl>,<head>,<sect> 1956 1957 hest_disable [ACPI] 1958 Disable Hardware Error Source Table (HEST) support; 1959 corresponding firmware-first mode error processing 1960 logic will be disabled. 1961 1962 hibernate= [HIBERNATION] 1963 noresume Don't check if there's a hibernation image 1964 present during boot. 1965 nocompress Don't compress/decompress hibernation images. 1966 no Disable hibernation and resume. 1967 protect_image Turn on image protection during restoration 1968 (that will set all pages holding image data 1969 during restoration read-only). 1970 1971 hibernate.compressor= [HIBERNATION] Compression algorithm to be 1972 used with hibernation. 1973 Format: { lzo | lz4 } 1974 Default: lzo 1975 1976 lzo: Select LZO compression algorithm to 1977 compress/decompress hibernation image. 1978 1979 lz4: Select LZ4 compression algorithm to 1980 compress/decompress hibernation image. 1981 1982 hibernate.pm_test_delay= 1983 [HIBERNATION] 1984 Sets the number of seconds to remain in a hibernation test 1985 mode before resuming the system (see 1986 /sys/power/pm_test). Only available when CONFIG_PM_DEBUG 1987 is set. Default value is 5. 1988 1989 hibernate_compression_threads= 1990 [HIBERNATION] 1991 Set the number of threads used for compressing or decompressing 1992 hibernation images. 1993 1994 Format: <integer> 1995 Default: 3 1996 Minimum: 1 1997 Example: hibernate_compression_threads=4 1998 1999 highmem=nn[KMG] [KNL,BOOT,EARLY] forces the highmem zone to have an exact 2000 size of <nn>. This works even on boxes that have no 2001 highmem otherwise. This also works to reduce highmem 2002 size on bigger boxes. 2003 2004 highres= [KNL] Enable/disable high resolution timer mode. 2005 Valid parameters: "on", "off" 2006 Default: "on" 2007 2008 hlt [BUGS=ARM,SH] 2009 2010 hostname= [KNL,EARLY] Set the hostname (aka UTS nodename). 2011 Format: <string> 2012 This allows setting the system's hostname during early 2013 startup. This sets the name returned by gethostname. 2014 Using this parameter to set the hostname makes it 2015 possible to ensure the hostname is correctly set before 2016 any userspace processes run, avoiding the possibility 2017 that a process may call gethostname before the hostname 2018 has been explicitly set, resulting in the calling 2019 process getting an incorrect result. The string must 2020 not exceed the maximum allowed hostname length (usually 2021 64 characters) and will be truncated otherwise. 2022 2023 hpet= [X86-32,HPET] option to control HPET usage 2024 Format: { enable (default) | disable | force | 2025 verbose } 2026 disable: disable HPET and use PIT instead 2027 force: allow force enabled of undocumented chips (ICH4, 2028 VIA, nVidia) 2029 verbose: show contents of HPET registers during setup 2030 2031 hpet_mmap= [X86, HPET_MMAP] Allow userspace to mmap HPET 2032 registers. Default set by CONFIG_HPET_MMAP_DEFAULT. 2033 2034 hugepages= [HW,EARLY] Number of HugeTLB pages to allocate at boot. 2035 If this follows hugepagesz (below), it specifies 2036 the number of pages of hugepagesz to be allocated. 2037 If this is the first HugeTLB parameter on the command 2038 line, it specifies the number of pages to allocate for 2039 the default huge page size. If using node format, the 2040 number of pages to allocate per-node can be specified. 2041 See also Documentation/admin-guide/mm/hugetlbpage.rst. 2042 Format: <integer> or (node format) 2043 <node>:<integer>[,<node>:<integer>] 2044 2045 hugepagesz= 2046 [HW,EARLY] The size of the HugeTLB pages. This is 2047 used in conjunction with hugepages (above) to 2048 allocate huge pages of a specific size at boot. The 2049 pair hugepagesz=X hugepages=Y can be specified once 2050 for each supported huge page size. Huge page sizes 2051 are architecture dependent. See also 2052 Documentation/admin-guide/mm/hugetlbpage.rst. 2053 Format: size[KMG] 2054 2055 hugepage_alloc_threads= 2056 [HW] The number of threads that should be used to 2057 allocate hugepages during boot. This option can be 2058 used to improve system bootup time when allocating 2059 a large amount of huge pages. 2060 The default value is 25% of the available hardware threads. 2061 2062 Note that this parameter only applies to non-gigantic huge pages. 2063 2064 hugetlb_cma= [HW,CMA,EARLY] The size of a CMA area used for allocation 2065 of gigantic hugepages. Or using node format, the size 2066 of a CMA area per node can be specified. 2067 Format: nn[KMGTPE] or (node format) 2068 <node>:nn[KMGTPE][,<node>:nn[KMGTPE]] 2069 2070 The size must be a multiple of the gigantic page size. 2071 When using node format, this applies to each per-node size. 2072 Missaligned values are dropped with a warning. 2073 2074 Reserve a CMA area of given size and allocate gigantic 2075 hugepages using the CMA allocator. If enabled, the 2076 boot-time allocation of gigantic hugepages is skipped. 2077 2078 hugetlb_cma_only= 2079 [HW,CMA,EARLY] When allocating new HugeTLB pages, only 2080 try to allocate from the CMA areas. 2081 2082 This option does nothing if hugetlb_cma= is not also 2083 specified. 2084 2085 hugetlb_free_vmemmap= 2086 [KNL] Requires CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP 2087 enabled. 2088 Control if HugeTLB Vmemmap Optimization (HVO) is enabled. 2089 Allows heavy hugetlb users to free up some more 2090 memory (7 * PAGE_SIZE for each 2MB hugetlb page). 2091 Format: { on | off (default) } 2092 2093 on: enable HVO 2094 off: disable HVO 2095 2096 Built with CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP_DEFAULT_ON=y, 2097 the default is on. 2098 2099 Note that the vmemmap pages may be allocated from the added 2100 memory block itself when memory_hotplug.memmap_on_memory is 2101 enabled, those vmemmap pages cannot be optimized even if this 2102 feature is enabled. Other vmemmap pages not allocated from 2103 the added memory block itself do not be affected. 2104 2105 hung_task_panic= 2106 [KNL] Number of hung tasks to trigger kernel panic. 2107 Format: <int> 2108 2109 When set to a non-zero value, a kernel panic will be triggered if 2110 the number of detected hung tasks reaches this value. 2111 2112 0: don't panic 2113 1: panic immediately on first hung task 2114 N: panic after N hung tasks are detected in a single scan 2115 2116 The default value is controlled by the 2117 CONFIG_BOOTPARAM_HUNG_TASK_PANIC build-time option. The value 2118 selected by this boot parameter can be changed later by the 2119 kernel.hung_task_panic sysctl. 2120 2121 hvc_iucv= [S390] Number of z/VM IUCV hypervisor console (HVC) 2122 terminal devices. Valid values: 0..8 2123 hvc_iucv_allow= [S390] Comma-separated list of z/VM user IDs. 2124 If specified, z/VM IUCV HVC accepts connections 2125 from listed z/VM user IDs only. 2126 2127 hv_nopvspin [X86,HYPER_V,EARLY] 2128 Disables the paravirt spinlock optimizations 2129 which allow the hypervisor to 'idle' the guest 2130 on lock contention. 2131 2132 hw_protection= [HW] 2133 Format: reboot | shutdown 2134 2135 Hardware protection action taken on critical events like 2136 overtemperature or imminent voltage loss. 2137 2138 i2c_bus= [HW] Override the default board specific I2C bus speed 2139 or register an additional I2C bus that is not 2140 registered from board initialization code. 2141 Format: 2142 <bus_id>,<clkrate> 2143 2144 i2c_touchscreen_props= [HW,ACPI,X86] 2145 Set device-properties for ACPI-enumerated I2C-attached 2146 touchscreen, to e.g. fix coordinates of upside-down 2147 mounted touchscreens. If you need this option please 2148 submit a drivers/platform/x86/touchscreen_dmi.c patch 2149 adding a DMI quirk for this. 2150 2151 Format: 2152 <ACPI_HW_ID>:<prop_name>=<val>[:prop_name=val][:...] 2153 Where <val> is one of: 2154 Omit "=<val>" entirely Set a boolean device-property 2155 Unsigned number Set a u32 device-property 2156 Anything else Set a string device-property 2157 2158 Examples (split over multiple lines): 2159 i2c_touchscreen_props=GDIX1001:touchscreen-inverted-x: 2160 touchscreen-inverted-y 2161 2162 i2c_touchscreen_props=MSSL1680:touchscreen-size-x=1920: 2163 touchscreen-size-y=1080:touchscreen-inverted-y: 2164 firmware-name=gsl1680-vendor-model.fw:silead,home-button 2165 2166 i8042.debug [HW] Toggle i8042 debug mode 2167 i8042.unmask_kbd_data 2168 [HW] Enable printing of interrupt data from the KBD port 2169 (disabled by default, and as a pre-condition 2170 requires that i8042.debug=1 be enabled) 2171 i8042.direct [HW] Put keyboard port into non-translated mode 2172 i8042.dumbkbd [HW] Pretend that controller can only read data from 2173 keyboard and cannot control its state 2174 (Don't attempt to blink the leds) 2175 i8042.noaux [HW] Don't check for auxiliary (== mouse) port 2176 i8042.nokbd [HW] Don't check/create keyboard port 2177 i8042.noloop [HW] Disable the AUX Loopback command while probing 2178 for the AUX port 2179 i8042.nomux [HW] Don't check presence of an active multiplexing 2180 controller 2181 i8042.nopnp [HW] Don't use ACPIPnP / PnPBIOS to discover KBD/AUX 2182 controllers 2183 i8042.notimeout [HW] Ignore timeout condition signalled by controller 2184 i8042.reset [HW] Reset the controller during init, cleanup and 2185 suspend-to-ram transitions, only during s2r 2186 transitions, or never reset 2187 Format: { 1 | Y | y | 0 | N | n } 2188 1, Y, y: always reset controller 2189 0, N, n: don't ever reset controller 2190 Default: only on s2r transitions on x86; most other 2191 architectures force reset to be always executed 2192 i8042.unlock [HW] Unlock (ignore) the keylock 2193 i8042.kbdreset [HW] Reset device connected to KBD port 2194 i8042.probe_defer 2195 [HW] Allow deferred probing upon i8042 probe errors 2196 2197 i810= [HW,DRM] 2198 2199 i915.invert_brightness= 2200 [DRM] Invert the sense of the variable that is used to 2201 set the brightness of the panel backlight. Normally a 2202 brightness value of 0 indicates backlight switched off, 2203 and the maximum of the brightness value sets the backlight 2204 to maximum brightness. If this parameter is set to 0 2205 (default) and the machine requires it, or this parameter 2206 is set to 1, a brightness value of 0 sets the backlight 2207 to maximum brightness, and the maximum of the brightness 2208 value switches the backlight off. 2209 -1 -- never invert brightness 2210 0 -- machine default 2211 1 -- force brightness inversion 2212 2213 ia32_emulation= [X86-64] 2214 Format: <bool> 2215 When true, allows loading 32-bit programs and executing 32-bit 2216 syscalls, essentially overriding IA32_EMULATION_DEFAULT_DISABLED at 2217 boot time. When false, unconditionally disables IA32 emulation. 2218 2219 2220 idle= [X86,EARLY] 2221 Format: idle=poll, idle=halt, idle=nomwait 2222 2223 idle=poll: Don't do power saving in the idle loop 2224 using HLT, but poll for rescheduling event. This will 2225 make the CPUs eat a lot more power, but may be useful 2226 to get slightly better performance in multiprocessor 2227 benchmarks. It also makes some profiling using 2228 performance counters more accurate. Please note that 2229 on systems with MONITOR/MWAIT support (like Intel 2230 EM64T CPUs) this option has no performance advantage 2231 over the normal idle loop. It may also interact badly 2232 with hyperthreading. 2233 2234 idle=halt: Halt is forced to be used for CPU idle. 2235 In such case C2/C3 won't be used again. 2236 2237 idle=nomwait: Disable mwait for CPU C-states 2238 2239 idxd.sva= [HW] 2240 Format: <bool> 2241 Allow force disabling of Shared Virtual Memory (SVA) 2242 support for the idxd driver. By default it is set to 2243 true (1). 2244 2245 idxd.tc_override= [HW] 2246 Format: <bool> 2247 Allow override of default traffic class configuration 2248 for the device. By default it is set to false (0). 2249 2250 ieee754= [MIPS] Select IEEE Std 754 conformance mode 2251 Format: { strict | legacy | 2008 | relaxed | emulated } 2252 Default: strict 2253 2254 Choose which programs will be accepted for execution 2255 based on the IEEE 754 NaN encoding(s) supported by 2256 the FPU and the NaN encoding requested with the value 2257 of an ELF file header flag individually set by each 2258 binary. Hardware implementations are permitted to 2259 support either or both of the legacy and the 2008 NaN 2260 encoding mode. 2261 2262 Available settings are as follows: 2263 strict accept binaries that request a NaN encoding 2264 supported by the FPU 2265 legacy only accept legacy-NaN binaries, if supported 2266 by the FPU 2267 2008 only accept 2008-NaN binaries, if supported 2268 by the FPU 2269 relaxed accept any binaries regardless of whether 2270 supported by the FPU 2271 emulated accept any binaries but enable FPU emulator 2272 if binary mode is unsupported by the FPU. 2273 2274 The FPU emulator is always able to support both NaN 2275 encodings, so if no FPU hardware is present or it has 2276 been disabled with 'nofpu', then the settings of 2277 'legacy' and '2008' strap the emulator accordingly, 2278 'relaxed' straps the emulator for both legacy-NaN and 2279 2008-NaN, whereas 'strict' enables legacy-NaN only on 2280 legacy processors and both NaN encodings on MIPS32 or 2281 MIPS64 CPUs. 2282 2283 The setting for ABS.fmt/NEG.fmt instruction execution 2284 mode generally follows that for the NaN encoding, 2285 except where unsupported by hardware. 2286 2287 ignore_loglevel [KNL,EARLY] 2288 Ignore loglevel setting - this will print /all/ 2289 kernel messages to the console. Useful for debugging. 2290 We also add it as printk module parameter, so users 2291 could change it dynamically, usually by 2292 /sys/module/printk/parameters/ignore_loglevel. 2293 2294 ignore_rlimit_data 2295 Ignore RLIMIT_DATA setting for data mappings, 2296 print warning at first misuse. Can be changed via 2297 /sys/module/kernel/parameters/ignore_rlimit_data. 2298 2299 ihash_entries= [KNL] 2300 Set number of hash buckets for inode cache. 2301 2302 ima_appraise= [IMA] appraise integrity measurements 2303 Format: { "off" | "enforce" | "fix" | "log" } 2304 default: "enforce" 2305 2306 ima_appraise_tcb [IMA] Deprecated. Use ima_policy= instead. 2307 The builtin appraise policy appraises all files 2308 owned by uid=0. 2309 2310 ima_canonical_fmt [IMA] 2311 Use the canonical format for the binary runtime 2312 measurements, instead of host native format. 2313 2314 ima_flush_htable [IMA] 2315 Flush the IMA hash table when deleting all the 2316 staged measurement records, to achieve maximum 2317 memory saving at the cost of having duplicate 2318 records across the staged measurement lists. 2319 2320 ima_hash= [IMA] 2321 Format: { md5 | sha1 | rmd160 | sha256 | sha384 2322 | sha512 | ... } 2323 default: "sha1" 2324 2325 The list of supported hash algorithms is defined 2326 in crypto/hash_info.h. 2327 2328 ima_policy= [IMA] 2329 The builtin policies to load during IMA setup. 2330 Format: "tcb | appraise_tcb | secure_boot | 2331 fail_securely | critical_data" 2332 2333 The "tcb" policy measures all programs exec'd, files 2334 mmap'd for exec, and all files opened with the read 2335 mode bit set by either the effective uid (euid=0) or 2336 uid=0. 2337 2338 The "appraise_tcb" policy appraises the integrity of 2339 all files owned by root. 2340 2341 The "secure_boot" policy appraises the integrity 2342 of files (eg. kexec kernel image, kernel modules, 2343 firmware, policy, etc) based on file signatures. 2344 2345 The "fail_securely" policy forces file signature 2346 verification failure also on privileged mounted 2347 filesystems with the SB_I_UNVERIFIABLE_SIGNATURE 2348 flag. 2349 2350 The "critical_data" policy measures kernel integrity 2351 critical data. 2352 2353 ima_tcb [IMA] Deprecated. Use ima_policy= instead. 2354 Load a policy which meets the needs of the Trusted 2355 Computing Base. This means IMA will measure all 2356 programs exec'd, files mmap'd for exec, and all files 2357 opened for read by uid=0. 2358 2359 ima_template= [IMA] 2360 Select one of defined IMA measurements template formats. 2361 Formats: { "ima" | "ima-ng" | "ima-ngv2" | "ima-sig" | 2362 "ima-sigv2" } 2363 Default: "ima-ng" 2364 2365 ima_template_fmt= 2366 [IMA] Define a custom template format. 2367 Format: { "field1|...|fieldN" } 2368 2369 ima= [IMA] Enable or disable IMA 2370 Format: { "off" | "on" } 2371 Default: "on" 2372 Note that disabling IMA is limited to kdump kernel. 2373 2374 indirect_target_selection= [X86,Intel] Mitigation control for Indirect 2375 Target Selection(ITS) bug in Intel CPUs. Updated 2376 microcode is also required for a fix in IBPB. 2377 2378 on: Enable mitigation (default). 2379 off: Disable mitigation. 2380 force: Force the ITS bug and deploy default 2381 mitigation. 2382 vmexit: Only deploy mitigation if CPU is affected by 2383 guest/host isolation part of ITS. 2384 stuff: Deploy RSB-fill mitigation when retpoline is 2385 also deployed. Otherwise, deploy the default 2386 mitigation. 2387 2388 For details see: 2389 Documentation/admin-guide/hw-vuln/indirect-target-selection.rst 2390 2391 init= [KNL] 2392 Format: <full_path> 2393 Run specified binary instead of /sbin/init as init 2394 process. 2395 2396 initcall_debug [KNL] Trace initcalls as they are executed. Useful 2397 for working out where the kernel is dying during 2398 startup. 2399 2400 initcall_blacklist= [KNL] Do not execute a comma-separated list of 2401 initcall functions. Useful for debugging built-in 2402 modules and initcalls. 2403 2404 initramfs_async= [KNL] 2405 Format: <bool> 2406 Default: 1 2407 This parameter controls whether the initramfs 2408 image is unpacked asynchronously, concurrently 2409 with devices being probed and 2410 initialized. This should normally just work, 2411 but as a debugging aid, one can get the 2412 historical behaviour of the initramfs 2413 unpacking being completed before device_ and 2414 late_ initcalls. 2415 2416 initrd= [BOOT,EARLY] Specify the location of the initial ramdisk 2417 2418 initrdmem= [KNL,EARLY] Specify a physical address and size from which to 2419 load the initrd. If an initrd is compiled in or 2420 specified in the bootparams, it takes priority over this 2421 setting. 2422 Format: ss[KMG],nn[KMG] 2423 Default is 0, 0 2424 2425 init_on_alloc= [MM,EARLY] Fill newly allocated pages and heap objects with 2426 zeroes. 2427 Format: 0 | 1 2428 Default set by CONFIG_INIT_ON_ALLOC_DEFAULT_ON. 2429 2430 init_on_free= [MM,EARLY] Fill freed pages and heap objects with zeroes. 2431 Format: 0 | 1 2432 Default set by CONFIG_INIT_ON_FREE_DEFAULT_ON. 2433 2434 init_pkru= [X86] Specify the default memory protection keys rights 2435 register contents for all processes. 0x55555554 by 2436 default (disallow access to all but pkey 0). Can 2437 override in debugfs after boot. 2438 2439 inport.irq= [HW] Inport (ATI XL and Microsoft) busmouse driver 2440 Format: <irq> 2441 2442 int_pln_enable [X86] Enable power limit notification interrupt 2443 2444 integrity_audit=[IMA] 2445 Format: { "0" | "1" } 2446 0 -- basic integrity auditing messages. (Default) 2447 1 -- additional integrity auditing messages. 2448 2449 intel_iommu= [DMAR] Intel IOMMU driver (DMAR) option 2450 on 2451 Enable intel iommu driver. 2452 off 2453 Disable intel iommu driver. 2454 igfx_off [Default Off] 2455 By default, gfx is mapped as normal device. If a gfx 2456 device has a dedicated DMAR unit, the DMAR unit is 2457 bypassed by not enabling DMAR with this option. In 2458 this case, gfx device will use physical address for 2459 DMA. 2460 strict [Default Off] 2461 Deprecated, equivalent to iommu.strict=1. 2462 sp_off [Default Off] 2463 By default, super page will be supported if Intel IOMMU 2464 has the capability. With this option, super page will 2465 not be supported. 2466 sm_on 2467 Enable the Intel IOMMU scalable mode if the hardware 2468 advertises that it has support for the scalable mode 2469 translation. 2470 sm_off 2471 Disallow use of the Intel IOMMU scalable mode. 2472 tboot_noforce [Default Off] 2473 Do not force the Intel IOMMU enabled under tboot. 2474 By default, tboot will force Intel IOMMU on, which 2475 could harm performance of some high-throughput 2476 devices like 40GBit network cards, even if identity 2477 mapping is enabled. 2478 Note that using this option lowers the security 2479 provided by tboot because it makes the system 2480 vulnerable to DMA attacks. 2481 2482 intel_idle.max_cstate= [KNL,HW,ACPI,X86] 2483 0 disables intel_idle and fall back on acpi_idle. 2484 1 to 9 specify maximum depth of C-state. 2485 2486 intel_pstate= [X86,EARLY] 2487 disable 2488 Do not enable intel_pstate as the default 2489 scaling driver for the supported processors 2490 active 2491 Use intel_pstate driver to bypass the scaling 2492 governors layer of cpufreq and provides it own 2493 algorithms for p-state selection. There are two 2494 P-state selection algorithms provided by 2495 intel_pstate in the active mode: powersave and 2496 performance. The way they both operate depends 2497 on whether or not the hardware managed P-states 2498 (HWP) feature has been enabled in the processor 2499 and possibly on the processor model. 2500 passive 2501 Use intel_pstate as a scaling driver, but configure it 2502 to work with generic cpufreq governors (instead of 2503 enabling its internal governor). This mode cannot be 2504 used along with the hardware-managed P-states (HWP) 2505 feature. 2506 force 2507 Enable intel_pstate on systems that prohibit it by default 2508 in favor of acpi-cpufreq. Forcing the intel_pstate driver 2509 instead of acpi-cpufreq may disable platform features, such 2510 as thermal controls and power capping, that rely on ACPI 2511 P-States information being indicated to OSPM and therefore 2512 should be used with caution. This option does not work with 2513 processors that aren't supported by the intel_pstate driver 2514 or on platforms that use pcc-cpufreq instead of acpi-cpufreq. 2515 no_hwp 2516 Do not enable hardware P state control (HWP) 2517 if available. 2518 hwp_only 2519 Only load intel_pstate on systems which support 2520 hardware P state control (HWP) if available. 2521 support_acpi_ppc 2522 Enforce ACPI _PPC performance limits. If the Fixed ACPI 2523 Description Table, specifies preferred power management 2524 profile as "Enterprise Server" or "Performance Server", 2525 then this feature is turned on by default. 2526 per_cpu_perf_limits 2527 Allow per-logical-CPU P-State performance control limits using 2528 cpufreq sysfs interface 2529 no_cas 2530 Do not enable capacity-aware scheduling (CAS) on 2531 hybrid systems 2532 2533 intremap= [X86-64,Intel-IOMMU,EARLY] 2534 on enable Interrupt Remapping (default) 2535 off disable Interrupt Remapping 2536 nosid disable Source ID checking 2537 no_x2apic_optout 2538 BIOS x2APIC opt-out request will be ignored 2539 nopost disable Interrupt Posting 2540 posted_msi 2541 enable MSIs delivered as posted interrupts 2542 2543 iomem= Disable strict checking of access to MMIO memory 2544 strict regions from userspace. 2545 relaxed 2546 2547 iommu= [X86,EARLY] 2548 2549 off 2550 Don't initialize and use any kind of IOMMU. 2551 2552 force 2553 Force the use of the hardware IOMMU even when 2554 it is not actually needed (e.g. because < 3 GB 2555 memory). 2556 2557 noforce 2558 Don't force hardware IOMMU usage when it is not 2559 needed. (default). 2560 2561 merge 2562 Do scatter-gather (SG) merging. Implies "force" 2563 (experimental). 2564 2565 nomerge 2566 Don't do scatter-gather (SG) merging. 2567 2568 biomerge 2569 Do scatter-gather (SG) merging. Implies "force" 2570 (experimental). [same as "merge"] 2571 2572 panic 2573 Always panic when IOMMU overflows. 2574 2575 nopanic 2576 Don't panic on IOMMU overflows. 2577 2578 pt 2579 Use passththrough mode by default 2580 (Equivalent to iommu.passthrough=1) 2581 2582 nopt 2583 Use translated mode for DMA by default 2584 (Equivalent to iommu.passthrough=0) 2585 2586 soft 2587 Use software bounce buffering (SWIOTLB) (default for 2588 Intel machines). This can be used to prevent the usage 2589 of an available hardware IOMMU. 2590 2591 usedac 2592 Use the DAC on VIA PCI bridge 2593 (default: disable the VIA PCI bridge DAC) 2594 2595 AMD Gart HW IOMMU-specific options: (CONFIG_GART_IOMMU) 2596 2597 <size> 2598 Set the size of the remapping area in bytes. 2599 2600 allowed 2601 Overwrite iommu off workarounds for specific chipsets 2602 2603 force 2604 Overwrite iommu off workarounds for specific chipsets 2605 2606 fullflush 2607 Flush IOMMU on each allocation (default). 2608 2609 nofullflush 2610 Don't use IOMMU fullflush. 2611 2612 memaper[=<order>] 2613 Allocate an own aperture over RAM with size 2614 32MB<<order. (default: order=1, i.e. 64MB) 2615 2616 noaperture 2617 Ask the IOMMU not to touch the aperture for AGP. 2618 2619 noagp 2620 Don't initialize the AGP driver and use full aperture. 2621 2622 iommu= [PPC/POWERNV] 2623 2624 nobypass 2625 Disable IOMMU bypass, using IOMMU for PCI devices. 2626 2627 iommu.forcedac= [ARM64,X86,EARLY] Control IOVA allocation for PCI devices. 2628 Format: { "0" | "1" } 2629 0 - Try to allocate a 32-bit DMA address first, before 2630 falling back to the full range if needed. 2631 1 - Allocate directly from the full usable range, 2632 forcing Dual Address Cycle for PCI cards supporting 2633 greater than 32-bit addressing. 2634 2635 iommu.strict= [ARM64,X86,S390,EARLY] Configure TLB invalidation behaviour 2636 Format: { "0" | "1" } 2637 0 - Lazy mode. 2638 Request that DMA unmap operations use deferred 2639 invalidation of hardware TLBs, for increased 2640 throughput at the cost of reduced device isolation. 2641 Will fall back to strict mode if not supported by 2642 the relevant IOMMU driver. 2643 1 - Strict mode. 2644 DMA unmap operations invalidate IOMMU hardware TLBs 2645 synchronously. 2646 unset - Use value of CONFIG_IOMMU_DEFAULT_DMA_{LAZY,STRICT}. 2647 Note: on x86, strict mode specified via one of the 2648 legacy driver-specific options takes precedence. 2649 2650 iommu.passthrough= 2651 [ARM64,X86,EARLY] Configure DMA to bypass the IOMMU by default. 2652 Format: { "0" | "1" } 2653 0 - Use IOMMU translation for DMA. 2654 1 - Bypass the IOMMU for DMA. 2655 unset - Use value of CONFIG_IOMMU_DEFAULT_PASSTHROUGH. 2656 2657 iommu.debug_pagealloc= 2658 [KNL,EARLY] When CONFIG_IOMMU_DEBUG_PAGEALLOC is set, this 2659 parameter enables the feature at boot time. By default, it 2660 is disabled and the system behaves the same way as a kernel 2661 built without CONFIG_IOMMU_DEBUG_PAGEALLOC. 2662 Format: { "0" | "1" } 2663 0 - Sanitizer disabled. 2664 1 - Sanitizer enabled, expect runtime overhead. 2665 2666 io7= [HW] IO7 for Marvel-based Alpha systems 2667 See comment before marvel_specify_io7 in 2668 arch/alpha/kernel/core_marvel.c. 2669 2670 io_delay= [X86,EARLY] I/O delay method 2671 0x80 2672 Standard port 0x80 based delay 2673 0xed 2674 Alternate port 0xed based delay (needed on some systems) 2675 udelay 2676 Simple two microseconds delay 2677 none 2678 No delay 2679 2680 ip= [IP_PNP] 2681 See Documentation/admin-guide/nfs/nfsroot.rst. 2682 2683 ipcmni_extend [KNL,EARLY] Extend the maximum number of unique System V 2684 IPC identifiers from 32,768 to 16,777,216. 2685 2686 ipe.enforce= [IPE] 2687 Format: <bool> 2688 Determine whether IPE starts in permissive (0) or 2689 enforce (1) mode. The default is enforce. 2690 2691 ipe.success_audit= 2692 [IPE] 2693 Format: <bool> 2694 Start IPE with success auditing enabled, emitting 2695 an audit event when a binary is allowed. The default 2696 is 0. 2697 2698 irqaffinity= [SMP] Set the default irq affinity mask 2699 The argument is a cpu list, as described above. 2700 2701 irqchip.gicv2_force_probe= 2702 [ARM,ARM64,EARLY] 2703 Format: <bool> 2704 Force the kernel to look for the second 4kB page 2705 of a GICv2 controller even if the memory range 2706 exposed by the device tree is too small. 2707 2708 irqchip.gicv3_nolpi= 2709 [ARM,ARM64,EARLY] 2710 Force the kernel to ignore the availability of 2711 LPIs (and by consequence ITSs). Intended for system 2712 that use the kernel as a bootloader, and thus want 2713 to let secondary kernels in charge of setting up 2714 LPIs. 2715 2716 irqchip.gicv3_pseudo_nmi= [ARM64,EARLY] 2717 Enables support for pseudo-NMIs in the kernel. This 2718 requires the kernel to be built with 2719 CONFIG_ARM64_PSEUDO_NMI. 2720 2721 irqchip.riscv_imsic_noipi 2722 [RISC-V,EARLY] 2723 Force the kernel to not use IMSIC software injected MSIs 2724 as IPIs. Intended for system where IMSIC is trap-n-emulated, 2725 and thus want to reduce MMIO traps when triggering IPIs 2726 to multiple harts. 2727 2728 irqfixup [HW] 2729 When an interrupt is not handled search all handlers 2730 for it. Intended to get systems with badly broken 2731 firmware running. 2732 2733 irqhandler.duration_warn_us= [KNL] 2734 Warn if an IRQ handler exceeds the specified duration 2735 threshold in microseconds. Useful for identifying 2736 long-running IRQs in the system. 2737 2738 irqpoll [HW] 2739 When an interrupt is not handled search all handlers 2740 for it. Also check all handlers each timer 2741 interrupt. Intended to get systems with badly broken 2742 firmware running. 2743 2744 isapnp= [ISAPNP] 2745 Format: <RDP>,<reset>,<pci_scan>,<verbosity> 2746 2747 isolcpus= [KNL,SMP,ISOL] Isolate a given set of CPUs from disturbance. 2748 Format: [flag-list,]<cpu-list> 2749 2750 Specify one or more CPUs to isolate from disturbances 2751 specified in the flag list (default: domain): 2752 2753 nohz 2754 Disable the tick when a single task runs as well as 2755 disabling other kernel noises like having RCU callbacks 2756 offloaded. This is equivalent to the nohz_full parameter. 2757 2758 A residual 1Hz tick is offloaded to workqueues, which you 2759 need to affine to housekeeping through the global 2760 workqueue's affinity configured via the 2761 /sys/devices/virtual/workqueue/cpumask sysfs file, or 2762 by using the 'domain' flag described below. 2763 2764 NOTE: by default the global workqueue runs on all CPUs, 2765 so to protect individual CPUs the 'cpumask' file has to 2766 be configured manually after bootup. 2767 2768 domain 2769 Isolate from the general SMP balancing and scheduling 2770 algorithms. Note that performing domain isolation this way 2771 is irreversible: it's not possible to bring back a CPU to 2772 the domains once isolated through this boot time 2773 configuration. Use cpusets for a dynamic configuration 2774 which can be altered at runtime. For details see 2775 Documentation/admin-guide/cpu-isolation.rst. 2776 2777 You can move a process onto or off an "isolated" CPU via 2778 the CPU affinity syscalls or cpuset. 2779 <cpu number> begins at 0 and the maximum value is 2780 "number of CPUs in system - 1". 2781 2782 managed_irq 2783 2784 Isolate from being targeted by managed interrupts 2785 which have an interrupt mask containing isolated 2786 CPUs. The affinity of managed interrupts is 2787 handled by the kernel and cannot be changed via 2788 the /proc/irq/* interfaces. 2789 2790 This isolation is best effort and only effective 2791 if the automatically assigned interrupt mask of a 2792 device queue contains isolated and housekeeping 2793 CPUs. If housekeeping CPUs are online then such 2794 interrupts are directed to the housekeeping CPU 2795 so that IO submitted on the housekeeping CPU 2796 cannot disturb the isolated CPU. 2797 2798 If a queue's affinity mask contains only isolated 2799 CPUs then this parameter has no effect on the 2800 interrupt routing decision, though interrupts are 2801 only delivered when tasks running on those 2802 isolated CPUs submit IO. IO submitted on 2803 housekeeping CPUs has no influence on those 2804 queues. 2805 2806 The format of <cpu-list> is described above. 2807 2808 iucv= [HW,NET] 2809 2810 ivrs_ioapic [HW,X86-64] 2811 Provide an override to the IOAPIC-ID<->DEVICE-ID 2812 mapping provided in the IVRS ACPI table. 2813 By default, PCI segment is 0, and can be omitted. 2814 2815 For example, to map IOAPIC-ID decimal 10 to 2816 PCI segment 0x1 and PCI device 00:14.0, 2817 write the parameter as: 2818 ivrs_ioapic=10@0001:00:14.0 2819 2820 Deprecated formats: 2821 * To map IOAPIC-ID decimal 10 to PCI device 00:14.0 2822 write the parameter as: 2823 ivrs_ioapic[10]=00:14.0 2824 * To map IOAPIC-ID decimal 10 to PCI segment 0x1 and 2825 PCI device 00:14.0 write the parameter as: 2826 ivrs_ioapic[10]=0001:00:14.0 2827 2828 ivrs_hpet [HW,X86-64] 2829 Provide an override to the HPET-ID<->DEVICE-ID 2830 mapping provided in the IVRS ACPI table. 2831 By default, PCI segment is 0, and can be omitted. 2832 2833 For example, to map HPET-ID decimal 10 to 2834 PCI segment 0x1 and PCI device 00:14.0, 2835 write the parameter as: 2836 ivrs_hpet=10@0001:00:14.0 2837 2838 Deprecated formats: 2839 * To map HPET-ID decimal 0 to PCI device 00:14.0 2840 write the parameter as: 2841 ivrs_hpet[0]=00:14.0 2842 * To map HPET-ID decimal 10 to PCI segment 0x1 and 2843 PCI device 00:14.0 write the parameter as: 2844 ivrs_ioapic[10]=0001:00:14.0 2845 2846 ivrs_acpihid [HW,X86-64] 2847 Provide an override to the ACPI-HID:UID<->DEVICE-ID 2848 mapping provided in the IVRS ACPI table. 2849 By default, PCI segment is 0, and can be omitted. 2850 2851 For example, to map UART-HID:UID AMD0020:0 to 2852 PCI segment 0x1 and PCI device ID 00:14.5, 2853 write the parameter as: 2854 ivrs_acpihid=AMD0020:0@0001:00:14.5 2855 2856 Deprecated formats: 2857 * To map UART-HID:UID AMD0020:0 to PCI segment is 0, 2858 PCI device ID 00:14.5, write the parameter as: 2859 ivrs_acpihid[00:14.5]=AMD0020:0 2860 * To map UART-HID:UID AMD0020:0 to PCI segment 0x1 and 2861 PCI device ID 00:14.5, write the parameter as: 2862 ivrs_acpihid[0001:00:14.5]=AMD0020:0 2863 2864 js= [HW,JOY] Analog joystick 2865 See Documentation/input/joydev/joystick.rst. 2866 2867 kasan_multi_shot 2868 [KNL] Enforce KASAN (Kernel Address Sanitizer) to print 2869 report on every invalid memory access. Without this 2870 parameter KASAN will print report only for the first 2871 invalid access. 2872 2873 keep_bootcon [KNL,EARLY] 2874 Do not unregister boot console at start. This is only 2875 useful for debugging when something happens in the window 2876 between unregistering the boot console and initializing 2877 the real console. 2878 2879 keepinitrd [HW,ARM] See retain_initrd. 2880 2881 kernelcore= [KNL,X86,PPC,EARLY] 2882 Format: nn[KMGTPE] | nn% | "mirror" 2883 This parameter specifies the amount of memory usable by 2884 the kernel for non-movable allocations. The requested 2885 amount is spread evenly throughout all nodes in the 2886 system as ZONE_NORMAL. The remaining memory is used for 2887 movable memory in its own zone, ZONE_MOVABLE. In the 2888 event, a node is too small to have both ZONE_NORMAL and 2889 ZONE_MOVABLE, kernelcore memory will take priority and 2890 other nodes will have a larger ZONE_MOVABLE. 2891 2892 ZONE_MOVABLE is used for the allocation of pages that 2893 may be reclaimed or moved by the page migration 2894 subsystem. Note that allocations like PTEs-from-HighMem 2895 still use the HighMem zone if it exists, and the Normal 2896 zone if it does not. 2897 2898 It is possible to specify the exact amount of memory in 2899 the form of "nn[KMGTPE]", a percentage of total system 2900 memory in the form of "nn%", or "mirror". If "mirror" 2901 option is specified, mirrored (reliable) memory is used 2902 for non-movable allocations and remaining memory is used 2903 for Movable pages. "nn[KMGTPE]", "nn%", and "mirror" 2904 are exclusive, so you cannot specify multiple forms. 2905 2906 kfence.burst= [MM,KFENCE] The number of additional successive 2907 allocations to be attempted through KFENCE for each 2908 sample interval. 2909 Format: <unsigned integer> 2910 Default: 0 2911 2912 kfence.check_on_panic= 2913 [MM,KFENCE] Whether to check all KFENCE-managed objects' 2914 canaries on panic. 2915 Format: <bool> 2916 Default: false 2917 2918 kfence.deferrable= 2919 [MM,KFENCE] Whether to use a deferrable timer to trigger 2920 allocations. This avoids forcing CPU wake-ups if the 2921 system is idle, at the risk of a less predictable 2922 sample interval. 2923 Format: <bool> 2924 Default: CONFIG_KFENCE_DEFERRABLE 2925 2926 kfence.fault= [MM,KFENCE] Controls the behavior when a KFENCE 2927 error is detected. 2928 report - print the error report and continue (default). 2929 oops - print the error report and oops. 2930 panic - print the error report and panic. 2931 2932 kfence.sample_interval= 2933 [MM,KFENCE] KFENCE's sample interval in milliseconds. 2934 Format: <unsigned integer> 2935 0 - Disable KFENCE. 2936 >0 - Enabled KFENCE with given sample interval. 2937 Default: CONFIG_KFENCE_SAMPLE_INTERVAL 2938 2939 kfence.skip_covered_thresh= 2940 [MM,KFENCE] If pool utilization reaches this threshold 2941 (pool usage%), KFENCE limits currently covered 2942 allocations of the same source from further filling 2943 up the pool. 2944 Format: <unsigned integer> 2945 Default: 75 2946 2947 kgdbdbgp= [KGDB,HW,EARLY] kgdb over EHCI usb debug port. 2948 Format: <Controller#>[,poll interval] 2949 The controller # is the number of the ehci usb debug 2950 port as it is probed via PCI. The poll interval is 2951 optional and is the number seconds in between 2952 each poll cycle to the debug port in case you need 2953 the functionality for interrupting the kernel with 2954 gdb or control-c on the dbgp connection. When 2955 not using this parameter you use sysrq-g to break into 2956 the kernel debugger. 2957 2958 kgdboc= [KGDB,HW] kgdb over consoles. 2959 Requires a tty driver that supports console polling, 2960 or a supported polling keyboard driver (non-usb). 2961 Serial only format: <serial_device>[,baud] 2962 keyboard only format: kbd 2963 keyboard and serial format: kbd,<serial_device>[,baud] 2964 Optional Kernel mode setting: 2965 kms, kbd format: kms,kbd 2966 kms, kbd and serial format: kms,kbd,<ser_dev>[,baud] 2967 2968 kgdboc_earlycon= [KGDB,HW,EARLY] 2969 If the boot console provides the ability to read 2970 characters and can work in polling mode, you can use 2971 this parameter to tell kgdb to use it as a backend 2972 until the normal console is registered. Intended to 2973 be used together with the kgdboc parameter which 2974 specifies the normal console to transition to. 2975 2976 The name of the early console should be specified 2977 as the value of this parameter. Note that the name of 2978 the early console might be different than the tty 2979 name passed to kgdboc. It's OK to leave the value 2980 blank and the first boot console that implements 2981 read() will be picked. 2982 2983 kgdbwait [KGDB,EARLY] Stop kernel execution and enter the 2984 kernel debugger at the earliest opportunity. 2985 2986 kho= [KEXEC,EARLY] 2987 Format: { "0" | "1" | "off" | "on" | "y" | "n" } 2988 Enables or disables Kexec HandOver. 2989 "0" | "off" | "n" - kexec handover is disabled 2990 "1" | "on" | "y" - kexec handover is enabled 2991 2992 kho_scratch= [KEXEC,EARLY] 2993 Format: ll[KMG],mm[KMG],nn[KMG] | nn% 2994 Defines the size of the KHO scratch region. The KHO 2995 scratch regions are physically contiguous memory 2996 ranges that can only be used for non-kernel 2997 allocations. That way, even when memory is heavily 2998 fragmented with handed over memory, the kexeced 2999 kernel will always have enough contiguous ranges to 3000 bootstrap itself. 3001 3002 It is possible to specify the exact amount of 3003 memory in the form of "ll[KMG],mm[KMG],nn[KMG]" 3004 where the first parameter defines the size of a low 3005 memory scratch area, the second parameter defines 3006 the size of a global scratch area and the third 3007 parameter defines the size of additional per-node 3008 scratch areas. The form "nn%" defines scale factor 3009 (in percents) of memory that was used during boot. 3010 3011 kmac= [MIPS] Korina ethernet MAC address. 3012 Configure the RouterBoard 532 series on-chip 3013 Ethernet adapter MAC address. 3014 3015 kmemleak= [KNL,EARLY] Boot-time kmemleak enable/disable 3016 Valid arguments: on, off 3017 Default: on 3018 Built with CONFIG_DEBUG_KMEMLEAK_DEFAULT_OFF=y, 3019 the default is off. 3020 3021 kprobe_event=[probe-list] 3022 [FTRACE] Add kprobe events and enable at boot time. 3023 The probe-list is a semicolon delimited list of probe 3024 definitions. Each definition is same as kprobe_events 3025 interface, but the parameters are comma delimited. 3026 For example, to add a kprobe event on vfs_read with 3027 arg1 and arg2, add to the command line; 3028 3029 kprobe_event=p,vfs_read,$arg1,$arg2 3030 3031 See also Documentation/trace/kprobetrace.rst "Kernel 3032 Boot Parameter" section. 3033 3034 kpti= [ARM64,EARLY] Control page table isolation of 3035 user and kernel address spaces. 3036 Default: enabled on cores which need mitigation. 3037 0: force disabled 3038 1: force enabled 3039 3040 kunit.enable= [KUNIT] Enable executing KUnit tests. Requires 3041 CONFIG_KUNIT to be set to be fully enabled. The 3042 default value can be overridden via 3043 KUNIT_DEFAULT_ENABLED. 3044 Default is 1 (enabled) 3045 3046 kvm.ignore_msrs=[KVM] Ignore guest accesses to unhandled MSRs. 3047 Default is 0 (don't ignore, but inject #GP) 3048 3049 kvm.eager_page_split= 3050 [KVM,X86] Controls whether or not KVM will try to 3051 proactively split all huge pages during dirty logging. 3052 Eager page splitting reduces interruptions to vCPU 3053 execution by eliminating the write-protection faults 3054 and MMU lock contention that would otherwise be 3055 required to split huge pages lazily. 3056 3057 VM workloads that rarely perform writes or that write 3058 only to a small region of VM memory may benefit from 3059 disabling eager page splitting to allow huge pages to 3060 still be used for reads. 3061 3062 The behavior of eager page splitting depends on whether 3063 KVM_DIRTY_LOG_INITIALLY_SET is enabled or disabled. If 3064 disabled, all huge pages in a memslot will be eagerly 3065 split when dirty logging is enabled on that memslot. If 3066 enabled, eager page splitting will be performed during 3067 the KVM_CLEAR_DIRTY ioctl, and only for the pages being 3068 cleared. 3069 3070 Eager page splitting is only supported when kvm.tdp_mmu=Y. 3071 3072 Default is Y (on). 3073 3074 kvm.enable_pmu=[KVM,X86] 3075 If enabled, KVM will virtualize PMU functionality based 3076 on the virtual CPU model defined by userspace. This 3077 can be overridden on a per-VM basis via 3078 KVM_CAP_PMU_CAPABILITY. 3079 3080 If disabled, KVM will not virtualize PMU functionality, 3081 e.g. MSRs, PMCs, PMIs, etc., even if userspace defines 3082 a virtual CPU model that contains PMU assets. 3083 3084 Note, KVM's vPMU support implicitly requires running 3085 with an in-kernel local APIC, e.g. to deliver PMIs to 3086 the guest. Running without an in-kernel local APIC is 3087 not supported, though KVM will allow such a combination 3088 (with severely degraded functionality). 3089 3090 See also enable_mediated_pmu. 3091 3092 Default is Y (on). 3093 3094 kvm.enable_virt_at_load=[KVM,ARM64,LOONGARCH,MIPS,RISCV,X86] 3095 If enabled, KVM will enable virtualization in hardware 3096 when KVM is loaded, and disable virtualization when KVM 3097 is unloaded (if KVM is built as a module). 3098 3099 If disabled, KVM will dynamically enable and disable 3100 virtualization on-demand when creating and destroying 3101 VMs, i.e. on the 0=>1 and 1=>0 transitions of the 3102 number of VMs. 3103 3104 Enabling virtualization at module load avoids potential 3105 latency for creation of the 0=>1 VM, as KVM serializes 3106 virtualization enabling across all online CPUs. The 3107 "cost" of enabling virtualization when KVM is loaded, 3108 is that doing so may interfere with using out-of-tree 3109 hypervisors that want to "own" virtualization hardware. 3110 3111 kvm.enable_vmware_backdoor=[KVM] Support VMware backdoor PV interface. 3112 Default is false (don't support). 3113 3114 kvm.nx_huge_pages= 3115 [KVM] Controls the software workaround for the 3116 X86_BUG_ITLB_MULTIHIT bug. 3117 force : Always deploy workaround. 3118 off : Never deploy workaround. 3119 auto : Deploy workaround based on the presence of 3120 X86_BUG_ITLB_MULTIHIT. 3121 3122 Default is 'auto'. 3123 3124 If the software workaround is enabled for the host, 3125 guests do need not to enable it for nested guests. 3126 3127 kvm.nx_huge_pages_recovery_ratio= 3128 [KVM] Controls how many 4KiB pages are periodically zapped 3129 back to huge pages. 0 disables the recovery, otherwise if 3130 the value is N KVM will zap 1/Nth of the 4KiB pages every 3131 period (see below). The default is 60. 3132 3133 kvm.nx_huge_pages_recovery_period_ms= 3134 [KVM] Controls the time period at which KVM zaps 4KiB pages 3135 back to huge pages. If the value is a non-zero N, KVM will 3136 zap a portion (see ratio above) of the pages every N msecs. 3137 If the value is 0 (the default), KVM will pick a period based 3138 on the ratio, such that a page is zapped after 1 hour on average. 3139 3140 kvm-{amd,intel}.enable_mediated_pmu=[KVM,AMD,INTEL] 3141 If enabled, KVM will provide a mediated virtual PMU, 3142 instead of the default perf-based virtual PMU (if 3143 kvm.enable_pmu is true and PMU is enumerated via the 3144 virtual CPU model). 3145 3146 With a perf-based vPMU, KVM operates as a user of perf, 3147 i.e. emulates guest PMU counters using perf events. 3148 KVM-created perf events are managed by perf as regular 3149 (guest-only) events, e.g. are scheduled in/out, contend 3150 for hardware resources, etc. Using a perf-based vPMU 3151 allows guest and host usage of the PMU to co-exist, but 3152 incurs non-trivial overhead and can result in silently 3153 dropped guest events (due to resource contention). 3154 3155 With a mediated vPMU, hardware PMU state is context 3156 switched around the world switch to/from the guest. 3157 KVM mediates which events the guest can utilize, but 3158 gives the guest direct access to all other PMU assets 3159 when possible (KVM may intercept some accesses if the 3160 virtual CPU model provides a subset of hardware PMU 3161 functionality). Using a mediated vPMU significantly 3162 reduces PMU virtualization overhead and eliminates lost 3163 guest events, but is mutually exclusive with using perf 3164 to profile KVM guests and adds latency to most VM-Exits 3165 (to context switch PMU state). 3166 3167 Default is N (off). 3168 3169 kvm-amd.nested= [KVM,AMD] Control nested virtualization feature in 3170 KVM/SVM. Default is 1 (enabled). 3171 3172 kvm-amd.npt= [KVM,AMD] Control KVM's use of Nested Page Tables, 3173 a.k.a. Two-Dimensional Page Tables. Default is 1 3174 (enabled). Disable by KVM if hardware lacks support 3175 for NPT. 3176 3177 kvm-amd.ciphertext_hiding_asids= 3178 [KVM,AMD] Ciphertext hiding prevents disallowed accesses 3179 to SNP private memory from reading ciphertext. Instead, 3180 reads will see constant default values (0xff). 3181 3182 If ciphertext hiding is enabled, the joint SEV-ES and 3183 SEV-SNP ASID space is partitioned into separate SEV-ES 3184 and SEV-SNP ASID ranges, with the SEV-SNP range being 3185 [1..max_snp_asid] and the SEV-ES range being 3186 (max_snp_asid..min_sev_asid), where min_sev_asid is 3187 enumerated by CPUID.0x.8000_001F[EDX]. 3188 3189 A non-zero value enables SEV-SNP ciphertext hiding and 3190 adjusts the ASID ranges for SEV-ES and SEV-SNP guests. 3191 KVM caps the number of SEV-SNP ASIDs at the maximum 3192 possible value, e.g. specifying -1u will assign all 3193 joint SEV-ES and SEV-SNP ASIDs to SEV-SNP. Note, 3194 assigning all joint ASIDs to SEV-SNP, i.e. configuring 3195 max_snp_asid == min_sev_asid-1, will effectively make 3196 SEV-ES unusable. 3197 3198 kvm-arm.mode= 3199 [KVM,ARM,EARLY] Select one of KVM/arm64's modes of 3200 operation. 3201 3202 none: Forcefully disable KVM. 3203 3204 nvhe: Standard nVHE-based mode, without support for 3205 protected guests. 3206 3207 protected: Mode with support for guests whose state is 3208 kept private from the host, using VHE or 3209 nVHE depending on HW support. 3210 3211 nested: VHE-based mode with support for nested 3212 virtualization. Requires at least ARMv8.4 3213 hardware (with FEAT_NV2). 3214 3215 Defaults to VHE/nVHE based on hardware support. Setting 3216 mode to "protected" will disable kexec and hibernation 3217 for the host. To force nVHE on VHE hardware, add 3218 "arm64_sw.hvhe=0 id_aa64mmfr1.vh=0" to the 3219 command-line. 3220 "nested" and "protected" are experimental and should be 3221 used with extreme caution. 3222 3223 kvm-arm.vgic_v3_group0_trap= 3224 [KVM,ARM,EARLY] Trap guest accesses to GICv3 group-0 3225 system registers 3226 3227 kvm-arm.vgic_v3_group1_trap= 3228 [KVM,ARM,EARLY] Trap guest accesses to GICv3 group-1 3229 system registers 3230 3231 kvm-arm.vgic_v3_common_trap= 3232 [KVM,ARM,EARLY] Trap guest accesses to GICv3 common 3233 system registers 3234 3235 kvm-arm.vgic_v4_enable= 3236 [KVM,ARM,EARLY] Allow use of GICv4 for direct 3237 injection of LPIs. 3238 3239 kvm-arm.wfe_trap_policy= 3240 [KVM,ARM] Control when to set WFE instruction trap for 3241 KVM VMs. Traps are allowed but not guaranteed by the 3242 CPU architecture. 3243 3244 trap: set WFE instruction trap 3245 3246 notrap: clear WFE instruction trap 3247 3248 kvm-arm.wfi_trap_policy= 3249 [KVM,ARM] Control when to set WFI instruction trap for 3250 KVM VMs. Traps are allowed but not guaranteed by the 3251 CPU architecture. 3252 3253 trap: set WFI instruction trap 3254 3255 notrap: clear WFI instruction trap 3256 3257 kvm_cma_resv_ratio=n [PPC,EARLY] 3258 Reserves given percentage from system memory area for 3259 contiguous memory allocation for KVM hash pagetable 3260 allocation. 3261 By default it reserves 5% of total system memory. 3262 Format: <integer> 3263 Default: 5 3264 3265 kvm-intel.ept= [KVM,Intel] Control KVM's use of Extended Page Tables, 3266 a.k.a. Two-Dimensional Page Tables. Default is 1 3267 (enabled). Disable by KVM if hardware lacks support 3268 for EPT. 3269 3270 kvm-intel.emulate_invalid_guest_state= 3271 [KVM,Intel] Control whether to emulate invalid guest 3272 state. Ignored if kvm-intel.enable_unrestricted_guest=1, 3273 as guest state is never invalid for unrestricted 3274 guests. This param doesn't apply to nested guests (L2), 3275 as KVM never emulates invalid L2 guest state. 3276 Default is 1 (enabled). 3277 3278 kvm-intel.flexpriority= 3279 [KVM,Intel] Control KVM's use of FlexPriority feature 3280 (TPR shadow). Default is 1 (enabled). Disable by KVM if 3281 hardware lacks support for it. 3282 3283 kvm-intel.nested= 3284 [KVM,Intel] Control nested virtualization feature in 3285 KVM/VMX. Default is 1 (enabled). 3286 3287 kvm-intel.unrestricted_guest= 3288 [KVM,Intel] Control KVM's use of unrestricted guest 3289 feature (virtualized real and unpaged mode). Default 3290 is 1 (enabled). Disable by KVM if EPT is disabled or 3291 hardware lacks support for it. 3292 3293 kvm-intel.vmentry_l1d_flush=[KVM,Intel] Mitigation for L1 Terminal Fault 3294 CVE-2018-3620. 3295 3296 Valid arguments: never, cond, always 3297 3298 always: L1D cache flush on every VMENTER. 3299 cond: Flush L1D on VMENTER only when the code between 3300 VMEXIT and VMENTER can leak host memory. 3301 never: Disables the mitigation 3302 3303 Default is cond (do L1 cache flush in specific instances) 3304 3305 kvm-intel.vpid= [KVM,Intel] Control KVM's use of Virtual Processor 3306 Identification feature (tagged TLBs). Default is 1 3307 (enabled). Disable by KVM if hardware lacks support 3308 for it. 3309 3310 l1d_flush= [X86,INTEL,EARLY] 3311 Control mitigation for L1D based snooping vulnerability. 3312 3313 Certain CPUs are vulnerable to an exploit against CPU 3314 internal buffers which can forward information to a 3315 disclosure gadget under certain conditions. 3316 3317 In vulnerable processors, the speculatively 3318 forwarded data can be used in a cache side channel 3319 attack, to access data to which the attacker does 3320 not have direct access. 3321 3322 This parameter controls the mitigation. The 3323 options are: 3324 3325 on - enable the interface for the mitigation 3326 3327 l1tf= [X86,EARLY] Control mitigation of the L1TF vulnerability on 3328 affected CPUs 3329 3330 The kernel PTE inversion protection is unconditionally 3331 enabled and cannot be disabled. 3332 3333 full 3334 Provides all available mitigations for the 3335 L1TF vulnerability. Disables SMT and 3336 enables all mitigations in the 3337 hypervisors, i.e. unconditional L1D flush. 3338 3339 SMT control and L1D flush control via the 3340 sysfs interface is still possible after 3341 boot. Hypervisors will issue a warning 3342 when the first VM is started in a 3343 potentially insecure configuration, 3344 i.e. SMT enabled or L1D flush disabled. 3345 3346 full,force 3347 Same as 'full', but disables SMT and L1D 3348 flush runtime control. Implies the 3349 'nosmt=force' command line option. 3350 (i.e. sysfs control of SMT is disabled.) 3351 3352 flush 3353 Leaves SMT enabled and enables the default 3354 hypervisor mitigation, i.e. conditional 3355 L1D flush. 3356 3357 SMT control and L1D flush control via the 3358 sysfs interface is still possible after 3359 boot. Hypervisors will issue a warning 3360 when the first VM is started in a 3361 potentially insecure configuration, 3362 i.e. SMT enabled or L1D flush disabled. 3363 3364 flush,nosmt 3365 3366 Disables SMT and enables the default 3367 hypervisor mitigation. 3368 3369 SMT control and L1D flush control via the 3370 sysfs interface is still possible after 3371 boot. Hypervisors will issue a warning 3372 when the first VM is started in a 3373 potentially insecure configuration, 3374 i.e. SMT enabled or L1D flush disabled. 3375 3376 flush,nowarn 3377 Same as 'flush', but hypervisors will not 3378 warn when a VM is started in a potentially 3379 insecure configuration. 3380 3381 off 3382 Disables hypervisor mitigations and doesn't 3383 emit any warnings. 3384 It also drops the swap size and available 3385 RAM limit restriction on both hypervisor and 3386 bare metal. 3387 3388 Default is 'flush'. 3389 3390 For details see: Documentation/admin-guide/hw-vuln/l1tf.rst 3391 3392 l2cr= [PPC] 3393 3394 l3cr= [PPC] 3395 3396 lapic [X86-32,APIC,EARLY] Enable the local APIC even if BIOS 3397 disabled it. 3398 3399 lapic= [X86,APIC] Do not use TSC deadline 3400 value for LAPIC timer one-shot implementation. Default 3401 back to the programmable timer unit in the LAPIC. 3402 Format: notscdeadline 3403 3404 lapic_timer_c2_ok [X86,APIC,EARLY] trust the local apic timer 3405 in C2 power state. 3406 3407 libata.dma= [LIBATA] DMA control 3408 libata.dma=0 Disable all PATA and SATA DMA 3409 libata.dma=1 PATA and SATA Disk DMA only 3410 libata.dma=2 ATAPI (CDROM) DMA only 3411 libata.dma=4 Compact Flash DMA only 3412 Combinations also work, so libata.dma=3 enables DMA 3413 for disks and CDROMs, but not CFs. 3414 3415 libata.ignore_hpa= [LIBATA] Ignore HPA limit 3416 libata.ignore_hpa=0 keep BIOS limits (default) 3417 libata.ignore_hpa=1 ignore limits, using full disk 3418 3419 libata.noacpi [LIBATA] Disables use of ACPI in libata suspend/resume 3420 when set. 3421 Format: <int> 3422 3423 libata.force= [LIBATA] Force configurations. The format is a comma- 3424 separated list of "[ID:]VAL" where ID is PORT[.DEVICE]. 3425 PORT and DEVICE are decimal numbers matching port, link 3426 or device. Basically, it matches the ATA ID string 3427 printed on console by libata. If the whole ID part is 3428 omitted, the last PORT and DEVICE values are used. If 3429 ID hasn't been specified yet, the configuration applies 3430 to all ports, links and devices. 3431 3432 If only DEVICE is omitted, the parameter applies to 3433 the port and all links and devices behind it. DEVICE 3434 number of 0 either selects the first device or the 3435 first fan-out link behind PMP device. It does not 3436 select the host link. DEVICE number of 15 selects the 3437 host link and device attached to it. 3438 3439 The VAL specifies the configuration to force. As long 3440 as there is no ambiguity, shortcut notation is allowed. 3441 For example, both 1.5 and 1.5G would work for 1.5Gbps. 3442 The following configurations can be forced. 3443 3444 * Cable type: 40c, 80c, short40c, unk, ign or sata. 3445 Any ID with matching PORT is used. 3446 3447 * SATA link speed limit: 1.5Gbps or 3.0Gbps. 3448 3449 * Transfer mode: pio[0-7], mwdma[0-4] and udma[0-7]. 3450 udma[/][16,25,33,44,66,100,133] notation is also 3451 allowed. 3452 3453 * nohrst, nosrst, norst: suppress hard, soft and both 3454 resets. 3455 3456 * rstonce: only attempt one reset during hot-unplug 3457 link recovery. 3458 3459 * [no]dbdelay: Enable or disable the extra 200ms delay 3460 before debouncing a link PHY and device presence 3461 detection. 3462 3463 * [no]ncq: Turn on or off NCQ. 3464 3465 * [no]ncqtrim: Enable or disable queued DSM TRIM. 3466 3467 * [no]ncqati: Enable or disable NCQ trim on ATI chipset. 3468 3469 * [no]trim: Enable or disable (unqueued) TRIM. 3470 3471 * trim_zero: Indicate that TRIM command zeroes data. 3472 3473 * max_trim_128m: Set 128M maximum trim size limit. 3474 3475 * [no]dma: Turn on or off DMA transfers. 3476 3477 * atapi_dmadir: Enable ATAPI DMADIR bridge support. 3478 3479 * atapi_mod16_dma: Enable the use of ATAPI DMA for 3480 commands that are not a multiple of 16 bytes. 3481 3482 * [no]dmalog: Enable or disable the use of the 3483 READ LOG DMA EXT command to access logs. 3484 3485 * [no]iddevlog: Enable or disable access to the 3486 identify device data log. 3487 3488 * [no]logdir: Enable or disable access to the general 3489 purpose log directory. 3490 3491 * max_sec=<sectors>: Set the transfer size limit, in 3492 number of 512-byte sectors, to the value specified in 3493 <sectors>. The value specified in <sectors> has to be 3494 a non-zero positive integer. 3495 3496 * max_sec_128: Set transfer size limit to 128 sectors. 3497 3498 * max_sec_1024: Set or clear transfer size limit to 3499 1024 sectors. 3500 3501 * max_sec_lba48: Set or clear transfer size limit to 3502 65535 sectors. 3503 3504 * external: Mark port as external (hotplug-capable). 3505 3506 * [no]lpm: Enable or disable link power management. 3507 3508 * [no]setxfer: Indicate if transfer speed mode setting 3509 should be skipped. 3510 3511 * [no]fua: Disable or enable FUA (Force Unit Access) 3512 support for devices supporting this feature. 3513 3514 * dump_id: Dump IDENTIFY data. 3515 3516 * disable: Disable this device. 3517 3518 If there are multiple matching configurations changing 3519 the same attribute, the last one is used. 3520 3521 liveupdate= [KNL,EARLY] 3522 Format: <bool> 3523 Enable Live Update Orchestrator (LUO). 3524 Default: off. 3525 3526 lockd.nlm_grace_period=P [NFS] Assign grace period. 3527 Format: <integer> 3528 3529 lockd.nlm_tcpport=N [NFS] Assign TCP port. 3530 Format: <integer> 3531 3532 lockd.nlm_timeout=T [NFS] Assign timeout value. 3533 Format: <integer> 3534 3535 lockd.nlm_udpport=M [NFS] Assign UDP port. 3536 Format: <integer> 3537 3538 lockdown= [SECURITY,EARLY] 3539 { integrity | confidentiality } 3540 Enable the kernel lockdown feature. If set to 3541 integrity, kernel features that allow userland to 3542 modify the running kernel are disabled. If set to 3543 confidentiality, kernel features that allow userland 3544 to extract confidential information from the kernel 3545 are also disabled. 3546 3547 locktorture.acq_writer_lim= [KNL] 3548 Set the time limit in jiffies for a lock 3549 acquisition. Acquisitions exceeding this limit 3550 will result in a splat once they do complete. 3551 3552 locktorture.bind_readers= [KNL] 3553 Specify the list of CPUs to which the readers are 3554 to be bound. 3555 3556 locktorture.bind_writers= [KNL] 3557 Specify the list of CPUs to which the writers are 3558 to be bound. 3559 3560 locktorture.call_rcu_chains= [KNL] 3561 Specify the number of self-propagating call_rcu() 3562 chains to set up. These are used to ensure that 3563 there is a high probability of an RCU grace period 3564 in progress at any given time. Defaults to 0, 3565 which disables these call_rcu() chains. 3566 3567 locktorture.long_hold= [KNL] 3568 Specify the duration in milliseconds for the 3569 occasional long-duration lock hold time. Defaults 3570 to 100 milliseconds. Select 0 to disable. 3571 3572 locktorture.nested_locks= [KNL] 3573 Specify the maximum lock nesting depth that 3574 locktorture is to exercise, up to a limit of 8 3575 (MAX_NESTED_LOCKS). Specify zero to disable. 3576 Note that this parameter is ineffective on types 3577 of locks that do not support nested acquisition. 3578 3579 locktorture.nreaders_stress= [KNL] 3580 Set the number of locking read-acquisition kthreads. 3581 Defaults to being automatically set based on the 3582 number of online CPUs. 3583 3584 locktorture.nwriters_stress= [KNL] 3585 Set the number of locking write-acquisition kthreads. 3586 3587 locktorture.onoff_holdoff= [KNL] 3588 Set time (s) after boot for CPU-hotplug testing. 3589 3590 locktorture.onoff_interval= [KNL] 3591 Set time (s) between CPU-hotplug operations, or 3592 zero to disable CPU-hotplug testing. 3593 3594 locktorture.rt_boost= [KNL] 3595 Do periodic testing of real-time lock priority 3596 boosting. Select 0 to disable, 1 to boost 3597 only rt_mutex, and 2 to boost unconditionally. 3598 Defaults to 2, which might seem to be an 3599 odd choice, but which should be harmless for 3600 non-real-time spinlocks, due to their disabling 3601 of preemption. Note that non-realtime mutexes 3602 disable boosting. 3603 3604 locktorture.rt_boost_factor= [KNL] 3605 Number that determines how often and for how 3606 long priority boosting is exercised. This is 3607 scaled down by the number of writers, so that the 3608 number of boosts per unit time remains roughly 3609 constant as the number of writers increases. 3610 On the other hand, the duration of each boost 3611 increases with the number of writers. 3612 3613 locktorture.shuffle_interval= [KNL] 3614 Set task-shuffle interval (jiffies). Shuffling 3615 tasks allows some CPUs to go into dyntick-idle 3616 mode during the locktorture test. 3617 3618 locktorture.shutdown_secs= [KNL] 3619 Set time (s) after boot system shutdown. This 3620 is useful for hands-off automated testing. 3621 3622 locktorture.stat_interval= [KNL] 3623 Time (s) between statistics printk()s. 3624 3625 locktorture.stutter= [KNL] 3626 Time (s) to stutter testing, for example, 3627 specifying five seconds causes the test to run for 3628 five seconds, wait for five seconds, and so on. 3629 This tests the locking primitive's ability to 3630 transition abruptly to and from idle. 3631 3632 locktorture.torture_type= [KNL] 3633 Specify the locking implementation to test. 3634 3635 locktorture.verbose= [KNL] 3636 Enable additional printk() statements. 3637 3638 locktorture.writer_fifo= [KNL] 3639 Run the write-side locktorture kthreads at 3640 sched_set_fifo() real-time priority. 3641 3642 logibm.irq= [HW,MOUSE] Logitech Bus Mouse Driver 3643 Format: <irq> 3644 3645 loglevel= [KNL,EARLY] 3646 All Kernel Messages with a loglevel smaller than the 3647 console loglevel will be printed to the console. It can 3648 also be changed with klogd or other programs. The 3649 loglevels are defined as follows: 3650 3651 0 (KERN_EMERG) system is unusable 3652 1 (KERN_ALERT) action must be taken immediately 3653 2 (KERN_CRIT) critical conditions 3654 3 (KERN_ERR) error conditions 3655 4 (KERN_WARNING) warning conditions 3656 5 (KERN_NOTICE) normal but significant condition 3657 6 (KERN_INFO) informational 3658 7 (KERN_DEBUG) debug-level messages 3659 3660 log_buf_len=n[KMG] [KNL,EARLY] 3661 Sets the size of the printk ring buffer, in bytes. 3662 n must be a power of two and greater than the 3663 minimal size. The minimal size is defined by 3664 LOG_BUF_SHIFT kernel config parameter. There 3665 is also CONFIG_LOG_CPU_MAX_BUF_SHIFT config 3666 parameter that allows to increase the default size 3667 depending on the number of CPUs. See init/Kconfig 3668 for more details. 3669 3670 logo.nologo [FB] Disables display of the built-in Linux logo. 3671 This may be used to provide more screen space for 3672 kernel log messages and is useful when debugging 3673 kernel boot problems. 3674 3675 lp=0 [LP] Specify parallel ports to use, e.g, 3676 lp=port[,port...] lp=none,parport0 (lp0 not configured, lp1 uses 3677 lp=reset first parallel port). 'lp=0' disables the 3678 lp=auto printer driver. 'lp=reset' (which can be 3679 specified in addition to the ports) causes 3680 attached printers to be reset. Using 3681 lp=port1,port2,... specifies the parallel ports 3682 to associate lp devices with, starting with 3683 lp0. A port specification may be 'none' to skip 3684 that lp device, or a parport name such as 3685 'parport0'. Specifying 'lp=auto' instead of a 3686 port specification list means that device IDs 3687 from each port should be examined, to see if 3688 an IEEE 1284-compliant printer is attached; if 3689 so, the driver will manage that printer. 3690 See also header of drivers/char/lp.c. 3691 3692 lpj=n [KNL] 3693 Sets loops_per_jiffy to given constant, thus avoiding 3694 time-consuming boot-time autodetection (up to 250 ms per 3695 CPU). 0 enables autodetection (default). To determine 3696 the correct value for your kernel, boot with normal 3697 autodetection and see what value is printed. Note that 3698 on SMP systems the preset will be applied to all CPUs, 3699 which is likely to cause problems if your CPUs need 3700 significantly divergent settings. An incorrect value 3701 will cause delays in the kernel to be wrong, leading to 3702 unpredictable I/O errors and other breakage. Although 3703 unlikely, in the extreme case this might damage your 3704 hardware. 3705 3706 lsm.debug [SECURITY] Enable LSM initialization debugging output. 3707 3708 lsm=lsm1,...,lsmN 3709 [SECURITY] Choose order of LSM initialization. This 3710 overrides CONFIG_LSM, and the "security=" parameter. 3711 3712 machtype= [Loongson] Share the same kernel image file between 3713 different yeeloong laptops. 3714 Example: machtype=lemote-yeeloong-2f-7inch 3715 3716 maxcpus= [SMP,EARLY] Maximum number of processors that an SMP kernel 3717 will bring up during bootup. maxcpus=n : n >= 0 limits 3718 the kernel to bring up 'n' processors. Surely after 3719 bootup you can bring up the other plugged cpu by executing 3720 "echo 1 > /sys/devices/system/cpu/cpuX/online". So maxcpus 3721 only takes effect during system bootup. 3722 While n=0 is a special case, it is equivalent to "nosmp", 3723 which also disables the IO APIC. 3724 3725 max_loop= [LOOP] The number of loop block devices that get 3726 (loop.max_loop) unconditionally pre-created at init time. The default 3727 number is configured by BLK_DEV_LOOP_MIN_COUNT. Instead 3728 of statically allocating a predefined number, loop 3729 devices can be requested on-demand with the 3730 /dev/loop-control interface. 3731 3732 mce= [X86-{32,64}] 3733 3734 Please see Documentation/arch/x86/x86_64/machinecheck.rst for sysfs runtime tunables. 3735 3736 off 3737 disable machine check 3738 3739 no_cmci 3740 disable CMCI(Corrected Machine Check Interrupt) that 3741 Intel processor supports. Usually this disablement is 3742 not recommended, but it might be handy if your 3743 hardware is misbehaving. 3744 3745 Note that you'll get more problems without CMCI than 3746 with due to the shared banks, i.e. you might get 3747 duplicated error logs. 3748 3749 dont_log_ce 3750 don't make logs for corrected errors. All events 3751 reported as corrected are silently cleared by OS. This 3752 option will be useful if you have no interest in any 3753 of corrected errors. 3754 3755 ignore_ce 3756 disable features for corrected errors, e.g. 3757 polling timer and CMCI. All events reported as 3758 corrected are not cleared by OS and remained in its 3759 error banks. 3760 3761 Usually this disablement is not recommended, however 3762 if there is an agent checking/clearing corrected 3763 errors (e.g. BIOS or hardware monitoring 3764 applications), conflicting with OS's error handling, 3765 and you cannot deactivate the agent, then this option 3766 will be a help. 3767 3768 no_lmce 3769 do not opt-in to Local MCE delivery. Use legacy method 3770 to broadcast MCEs. 3771 3772 bootlog 3773 enable logging of machine checks left over from 3774 booting. Disabled by default on AMD Fam10h and older 3775 because some BIOS leave bogus ones. 3776 3777 If your BIOS doesn't do that it's a good idea to 3778 enable though to make sure you log even machine check 3779 events that result in a reboot. On Intel systems it is 3780 enabled by default. 3781 3782 nobootlog 3783 disable boot machine check logging. 3784 3785 monarchtimeout (number) 3786 sets the time in us to wait for other CPUs on machine 3787 checks. 0 to disable. 3788 3789 bios_cmci_threshold 3790 don't overwrite the bios-set CMCI threshold. This boot 3791 option prevents Linux from overwriting the CMCI 3792 threshold set by the bios. Without this option, Linux 3793 always sets the CMCI threshold to 1. Enabling this may 3794 make memory predictive failure analysis less effective 3795 if the bios sets thresholds for memory errors since we 3796 will not see details for all errors. 3797 3798 recovery 3799 force-enable recoverable machine check code paths 3800 3801 Everything else is in sysfs now. 3802 3803 3804 md= [HW] RAID subsystems devices and level 3805 See Documentation/admin-guide/md.rst. 3806 3807 mds= [X86,INTEL,EARLY] 3808 Control mitigation for the Micro-architectural Data 3809 Sampling (MDS) vulnerability. 3810 3811 Certain CPUs are vulnerable to an exploit against CPU 3812 internal buffers which can forward information to a 3813 disclosure gadget under certain conditions. 3814 3815 In vulnerable processors, the speculatively 3816 forwarded data can be used in a cache side channel 3817 attack, to access data to which the attacker does 3818 not have direct access. 3819 3820 This parameter controls the MDS mitigation. The 3821 options are: 3822 3823 full - Enable MDS mitigation on vulnerable CPUs 3824 full,nosmt - Enable MDS mitigation and disable 3825 SMT on vulnerable CPUs 3826 off - Unconditionally disable MDS mitigation 3827 3828 On TAA-affected machines, mds=off can be prevented by 3829 an active TAA mitigation as both vulnerabilities are 3830 mitigated with the same mechanism so in order to disable 3831 this mitigation, you need to specify tsx_async_abort=off 3832 too. 3833 3834 Not specifying this option is equivalent to 3835 mds=full. 3836 3837 For details see: Documentation/admin-guide/hw-vuln/mds.rst 3838 3839 mem=nn[KMG] [HEXAGON,EARLY] Set the memory size. 3840 Must be specified, otherwise memory size will be 0. 3841 3842 mem=nn[KMG] [KNL,BOOT,EARLY] Force usage of a specific amount 3843 of memory Amount of memory to be used in cases 3844 as follows: 3845 3846 1 for test; 3847 2 when the kernel is not able to see the whole system memory; 3848 3 memory that lies after 'mem=' boundary is excluded from 3849 the hypervisor, then assigned to KVM guests. 3850 4 to limit the memory available for kdump kernel. 3851 3852 [ARC,MICROBLAZE] - the limit applies only to low memory, 3853 high memory is not affected. 3854 3855 [ARM64] - only limits memory covered by the linear 3856 mapping. The NOMAP regions are not affected. 3857 3858 [X86] Work as limiting max address. Use together 3859 with memmap= to avoid physical address space collisions. 3860 Without memmap= PCI devices could be placed at addresses 3861 belonging to unused RAM. 3862 3863 Note that this only takes effects during boot time since 3864 in above case 3, memory may need be hot added after boot 3865 if system memory of hypervisor is not sufficient. 3866 3867 mem=nn[KMG]@ss[KMG] 3868 [ARM,MIPS,EARLY] - override the memory layout 3869 reported by firmware. 3870 Define a memory region of size nn[KMG] starting at 3871 ss[KMG]. 3872 Multiple different regions can be specified with 3873 multiple mem= parameters on the command line. 3874 3875 mem=nopentium [BUGS=X86-32] Disable usage of 4MB pages for kernel 3876 memory. 3877 3878 memblock=debug [KNL,EARLY] Enable memblock debug messages. 3879 3880 memchunk=nn[KMG] 3881 [KNL,SH] Allow user to override the default size for 3882 per-device physically contiguous DMA buffers. 3883 3884 memhp_default_state=online/offline/online_kernel/online_movable 3885 [KNL] Set the initial state for the memory hotplug 3886 onlining policy. If not specified, the default value is 3887 set according to the 3888 CONFIG_MHP_DEFAULT_ONLINE_TYPE kernel config 3889 options. 3890 See Documentation/admin-guide/mm/memory-hotplug.rst. 3891 3892 memmap=exactmap [KNL,X86,EARLY] Enable setting of an exact 3893 E820 memory map, as specified by the user. 3894 Such memmap=exactmap lines can be constructed based on 3895 BIOS output or other requirements. See the memmap=nn@ss 3896 option description. 3897 3898 memmap=nn[KMG]@ss[KMG] 3899 [KNL, X86,MIPS,XTENSA,EARLY] Force usage of a specific region of memory. 3900 Region of memory to be used is from ss to ss+nn. 3901 If @ss[KMG] is omitted, it is equivalent to mem=nn[KMG], 3902 which limits max address to nn[KMG]. 3903 Multiple different regions can be specified, 3904 comma delimited. 3905 Example: 3906 memmap=100M@2G,100M#3G,1G!1024G 3907 3908 memmap=nn[KMG]#ss[KMG] 3909 [KNL,ACPI,EARLY] Mark specific memory as ACPI data. 3910 Region of memory to be marked is from ss to ss+nn. 3911 3912 memmap=nn[KMG]$ss[KMG] 3913 [KNL,ACPI,EARLY] Mark specific memory as reserved. 3914 Region of memory to be reserved is from ss to ss+nn. 3915 Example: Exclude memory from 0x18690000-0x1869ffff 3916 memmap=64K$0x18690000 3917 or 3918 memmap=0x10000$0x18690000 3919 Some bootloaders may need an escape character before '$', 3920 like Grub2, otherwise '$' and the following number 3921 will be eaten. 3922 3923 memmap=nn[KMG]!ss[KMG,EARLY] 3924 [KNL,X86] Mark specific memory as protected. 3925 Region of memory to be used, from ss to ss+nn. 3926 The memory region may be marked as e820 type 12 (0xc) 3927 and is NVDIMM or ADR memory. 3928 3929 memmap=<size>%<offset>-<oldtype>+<newtype> 3930 [KNL,ACPI,EARLY] Convert memory within the specified region 3931 from <oldtype> to <newtype>. If "-<oldtype>" is left 3932 out, the whole region will be marked as <newtype>, 3933 even if previously unavailable. If "+<newtype>" is left 3934 out, matching memory will be removed. Types are 3935 specified as e820 types, e.g., 1 = RAM, 2 = reserved, 3936 3 = ACPI, 12 = PRAM. 3937 3938 memory_corruption_check=0/1 [X86,EARLY] 3939 Some BIOSes seem to corrupt the first 64k of 3940 memory when doing things like suspend/resume. 3941 Setting this option will scan the memory 3942 looking for corruption. Enabling this will 3943 both detect corruption and prevent the kernel 3944 from using the memory being corrupted. 3945 However, it's intended as a diagnostic tool; if 3946 repeatable BIOS-originated corruption always 3947 affects the same memory, you can use memmap= 3948 to prevent the kernel from using that memory. 3949 3950 memory_corruption_check_size=size [X86,EARLY] 3951 By default it checks for corruption in the low 3952 64k, making this memory unavailable for normal 3953 use. Use this parameter to scan for 3954 corruption in more or less memory. 3955 3956 memory_corruption_check_period=seconds [X86,EARLY] 3957 By default it checks for corruption every 60 3958 seconds. Use this parameter to check at some 3959 other rate. 0 disables periodic checking. 3960 3961 memory_hotplug.memmap_on_memory 3962 [KNL,X86,ARM] Boolean flag to enable this feature. 3963 Format: {on | off (default)} 3964 When enabled, runtime hotplugged memory will 3965 allocate its internal metadata (struct pages, 3966 those vmemmap pages cannot be optimized even 3967 if hugetlb_free_vmemmap is enabled) from the 3968 hotadded memory which will allow to hotadd a 3969 lot of memory without requiring additional 3970 memory to do so. 3971 This feature is disabled by default because it 3972 has some implication on large (e.g. GB) 3973 allocations in some configurations (e.g. small 3974 memory blocks). 3975 The state of the flag can be read in 3976 /sys/module/memory_hotplug/parameters/memmap_on_memory. 3977 Note that even when enabled, there are a few cases where 3978 the feature is not effective. 3979 3980 memtest= [KNL,X86,ARM,M68K,PPC,RISCV,EARLY] Enable memtest 3981 Format: <integer> 3982 default : 0 <disable> 3983 Specifies the number of memtest passes to be 3984 performed. Each pass selects another test 3985 pattern from a given set of patterns. Memtest 3986 fills the memory with this pattern, validates 3987 memory contents and reserves bad memory 3988 regions that are detected. 3989 3990 mem_encrypt= [X86-64] AMD Secure Memory Encryption (SME) control 3991 Valid arguments: on, off 3992 Default: off 3993 mem_encrypt=on: Activate SME 3994 mem_encrypt=off: Do not activate SME 3995 3996 Refer to Documentation/virt/kvm/x86/amd-memory-encryption.rst 3997 for details on when memory encryption can be activated. 3998 3999 mem_sleep_default= [SUSPEND] Default system suspend mode: 4000 s2idle - Suspend-To-Idle 4001 shallow - Power-On Suspend or equivalent (if supported) 4002 deep - Suspend-To-RAM or equivalent (if supported) 4003 See Documentation/admin-guide/pm/sleep-states.rst. 4004 4005 mfgptfix [X86-32] Fix MFGPT timers on AMD Geode platforms when 4006 the BIOS has incorrectly applied a workaround. TinyBIOS 4007 version 0.98 is known to be affected, 0.99 fixes the 4008 problem by letting the user disable the workaround. 4009 4010 mga= [HW,DRM] 4011 4012 microcode= [X86] Control the behavior of the microcode loader. 4013 Available options, comma separated: 4014 4015 base_rev=X - with <X> with format: <u32> 4016 Set the base microcode revision of each thread when in 4017 debug mode. 4018 4019 dis_ucode_ldr: disable the microcode loader 4020 4021 force_minrev: 4022 Enable or disable the microcode minimal revision 4023 enforcement for the runtime microcode loader. 4024 4025 mini2440= [ARM,HW,KNL] 4026 Format:[0..2][b][c][t] 4027 Default: "0tb" 4028 MINI2440 configuration specification: 4029 0 - The attached screen is the 3.5" TFT 4030 1 - The attached screen is the 7" TFT 4031 2 - The VGA Shield is attached (1024x768) 4032 Leaving out the screen size parameter will not load 4033 the TFT driver, and the framebuffer will be left 4034 unconfigured. 4035 b - Enable backlight. The TFT backlight pin will be 4036 linked to the kernel VESA blanking code and a GPIO 4037 LED. This parameter is not necessary when using the 4038 VGA shield. 4039 c - Enable the s3c camera interface. 4040 t - Reserved for enabling touchscreen support. The 4041 touchscreen support is not enabled in the mainstream 4042 kernel as of 2.6.30, a preliminary port can be found 4043 in the "bleeding edge" mini2440 support kernel at 4044 https://repo.or.cz/w/linux-2.6/mini2440.git 4045 4046 mitigations= 4047 [X86,PPC,S390,ARM64,EARLY] Control optional mitigations for 4048 CPU vulnerabilities. This is a set of curated, 4049 arch-independent options, each of which is an 4050 aggregation of existing arch-specific options. 4051 4052 Note, "mitigations" is supported if and only if the 4053 kernel was built with CPU_MITIGATIONS=y. 4054 4055 off 4056 Disable all optional CPU mitigations. This 4057 improves system performance, but it may also 4058 expose users to several CPU vulnerabilities. 4059 Equivalent to: if nokaslr then kpti=0 [ARM64] 4060 gather_data_sampling=off [X86] 4061 indirect_target_selection=off [X86] 4062 kvm.nx_huge_pages=off [X86] 4063 l1tf=off [X86] 4064 mds=off [X86] 4065 mmio_stale_data=off [X86] 4066 no_entry_flush [PPC] 4067 no_uaccess_flush [PPC] 4068 nobp=0 [S390] 4069 nopti [X86,PPC] 4070 nospectre_bhb [ARM64] 4071 nospectre_v1 [X86,PPC] 4072 nospectre_v2 [X86,PPC,S390,ARM64] 4073 reg_file_data_sampling=off [X86] 4074 retbleed=off [X86] 4075 spec_rstack_overflow=off [X86] 4076 spec_store_bypass_disable=off [X86,PPC] 4077 spectre_bhi=off [X86] 4078 spectre_v2_user=off [X86] 4079 srbds=off [X86,INTEL] 4080 ssbd=force-off [ARM64] 4081 tsa=off [X86,AMD] 4082 tsx_async_abort=off [X86] 4083 vmscape=off [X86] 4084 4085 Exceptions: 4086 This does not have any effect on 4087 kvm.nx_huge_pages when 4088 kvm.nx_huge_pages=force. 4089 4090 auto (default) 4091 Mitigate all CPU vulnerabilities, but leave SMT 4092 enabled, even if it's vulnerable. This is for 4093 users who don't want to be surprised by SMT 4094 getting disabled across kernel upgrades, or who 4095 have other ways of avoiding SMT-based attacks. 4096 Equivalent to: (default behavior) 4097 4098 auto,nosmt 4099 Mitigate all CPU vulnerabilities, disabling SMT 4100 if needed. This is for users who always want to 4101 be fully mitigated, even if it means losing SMT. 4102 Equivalent to: l1tf=flush,nosmt [X86] 4103 mds=full,nosmt [X86] 4104 tsx_async_abort=full,nosmt [X86] 4105 mmio_stale_data=full,nosmt [X86] 4106 retbleed=auto,nosmt [X86] 4107 4108 [X86] After one of the above options, additionally 4109 supports attack-vector based controls as documented in 4110 Documentation/admin-guide/hw-vuln/attack_vector_controls.rst 4111 4112 mminit_loglevel= 4113 [KNL,EARLY] When CONFIG_DEBUG_MEMORY_INIT is set, this 4114 parameter allows control of the logging verbosity for 4115 the additional memory initialisation checks. A value 4116 of 0 disables mminit logging and a level of 4 will 4117 log everything. Information is printed at KERN_DEBUG 4118 so loglevel=8 may also need to be specified. 4119 4120 mmio_stale_data= 4121 [X86,INTEL,EARLY] Control mitigation for the Processor 4122 MMIO Stale Data vulnerabilities. 4123 4124 Processor MMIO Stale Data is a class of 4125 vulnerabilities that may expose data after an MMIO 4126 operation. Exposed data could originate or end in 4127 the same CPU buffers as affected by MDS and TAA. 4128 Therefore, similar to MDS and TAA, the mitigation 4129 is to clear the affected CPU buffers. 4130 4131 This parameter controls the mitigation. The 4132 options are: 4133 4134 full - Enable mitigation on vulnerable CPUs 4135 4136 full,nosmt - Enable mitigation and disable SMT on 4137 vulnerable CPUs. 4138 4139 off - Unconditionally disable mitigation 4140 4141 On MDS or TAA affected machines, 4142 mmio_stale_data=off can be prevented by an active 4143 MDS or TAA mitigation as these vulnerabilities are 4144 mitigated with the same mechanism so in order to 4145 disable this mitigation, you need to specify 4146 mds=off and tsx_async_abort=off too. 4147 4148 Not specifying this option is equivalent to 4149 mmio_stale_data=full. 4150 4151 For details see: 4152 Documentation/admin-guide/hw-vuln/processor_mmio_stale_data.rst 4153 4154 <module>.async_probe[=<bool>] [KNL] 4155 If no <bool> value is specified or if the value 4156 specified is not a valid <bool>, enable asynchronous 4157 probe on this module. Otherwise, enable/disable 4158 asynchronous probe on this module as indicated by the 4159 <bool> value. See also: module.async_probe 4160 4161 module.async_probe=<bool> 4162 [KNL] When set to true, modules will use async probing 4163 by default. To enable/disable async probing for a 4164 specific module, use the module specific control that 4165 is documented under <module>.async_probe. When both 4166 module.async_probe and <module>.async_probe are 4167 specified, <module>.async_probe takes precedence for 4168 the specific module. 4169 4170 module.enable_dups_trace 4171 [KNL] When CONFIG_MODULE_DEBUG_AUTOLOAD_DUPS is set, 4172 this means that duplicate request_module() calls will 4173 trigger a WARN_ON() instead of a pr_warn(). Note that 4174 if MODULE_DEBUG_AUTOLOAD_DUPS_TRACE is set, WARN_ON()s 4175 will always be issued and this option does nothing. 4176 module.sig_enforce 4177 [KNL] When CONFIG_MODULE_SIG is set, this means that 4178 modules without (valid) signatures will fail to load. 4179 Note that if CONFIG_MODULE_SIG_FORCE is set, that 4180 is always true, so this option does nothing. 4181 4182 module_blacklist= [KNL] Do not load a comma-separated list of 4183 modules. Useful for debugging problem modules. 4184 4185 mousedev.tap_time= 4186 [MOUSE] Maximum time between finger touching and 4187 leaving touchpad surface for touch to be considered 4188 a tap and be reported as a left button click (for 4189 touchpads working in absolute mode only). 4190 Format: <msecs> 4191 mousedev.xres= [MOUSE] Horizontal screen resolution, used for devices 4192 reporting absolute coordinates, such as tablets 4193 mousedev.yres= [MOUSE] Vertical screen resolution, used for devices 4194 reporting absolute coordinates, such as tablets 4195 4196 movablecore= [KNL,X86,PPC,EARLY] 4197 Format: nn[KMGTPE] | nn% 4198 This parameter is the complement to kernelcore=, it 4199 specifies the amount of memory used for migratable 4200 allocations. If both kernelcore and movablecore is 4201 specified, then kernelcore will be at *least* the 4202 specified value but may be more. If movablecore on its 4203 own is specified, the administrator must be careful 4204 that the amount of memory usable for all allocations 4205 is not too small. 4206 4207 movable_node [KNL,EARLY] Boot-time switch to make hotplugable memory 4208 NUMA nodes to be movable. This means that the memory 4209 of such nodes will be usable only for movable 4210 allocations which rules out almost all kernel 4211 allocations. Use with caution! 4212 4213 MTD_Partition= [MTD] 4214 Format: <name>,<region-number>,<size>,<offset> 4215 4216 MTD_Region= [MTD] Format: 4217 <name>,<region-number>[,<base>,<size>,<buswidth>,<altbuswidth>] 4218 4219 mtdparts= [MTD] 4220 See drivers/mtd/parsers/cmdlinepart.c 4221 4222 mtouchusb.raw_coordinates= 4223 [HW] Make the MicroTouch USB driver use raw coordinates 4224 ('y', default) or cooked coordinates ('n') 4225 4226 mtrr=debug [X86,EARLY] 4227 Enable printing debug information related to MTRR 4228 registers at boot time. 4229 4230 mtrr_chunk_size=nn[KMG,X86,EARLY] 4231 used for mtrr cleanup. It is largest continuous chunk 4232 that could hold holes aka. UC entries. 4233 4234 mtrr_gran_size=nn[KMG,X86,EARLY] 4235 Used for mtrr cleanup. It is granularity of mtrr block. 4236 Default is 1. 4237 Large value could prevent small alignment from 4238 using up MTRRs. 4239 4240 mtrr_spare_reg_nr=n [X86,EARLY] 4241 Format: <integer> 4242 Range: 0,7 : spare reg number 4243 Default : 1 4244 Used for mtrr cleanup. It is spare mtrr entries number. 4245 Set to 2 or more if your graphical card needs more. 4246 4247 multitce=off [PPC] This parameter disables the use of the pSeries 4248 firmware feature for updating multiple TCE entries 4249 at a time. 4250 4251 n2= [NET] SDL Inc. RISCom/N2 synchronous serial card 4252 4253 netdev= [NET] NE2000 ISA network devices parameters 4254 Format: <irq>,<io>,<mem_start>,<mem_end>,<name> 4255 4256 netpoll.carrier_timeout= 4257 [NET] Specifies amount of time (in seconds) that 4258 netpoll should wait for a carrier. By default netpoll 4259 waits 4 seconds. 4260 4261 nf_conntrack.acct= 4262 [NETFILTER] Enable connection tracking flow accounting 4263 0 to disable accounting 4264 1 to enable accounting 4265 Default value is 0. 4266 4267 nfs.cache_getent= 4268 [NFS] sets the pathname to the program which is used 4269 to update the NFS client cache entries. 4270 4271 nfs.cache_getent_timeout= 4272 [NFS] sets the timeout after which an attempt to 4273 update a cache entry is deemed to have failed. 4274 4275 nfs.callback_nr_threads= 4276 [NFSv4] set the total number of threads that the 4277 NFS client will assign to service NFSv4 callback 4278 requests. 4279 4280 nfs.callback_tcpport= 4281 [NFS] set the TCP port on which the NFSv4 callback 4282 channel should listen. 4283 4284 nfs.delay_retrans= 4285 [NFS] specifies the number of times the NFSv4 client 4286 retries the request before returning an EAGAIN error, 4287 after a reply of NFS4ERR_DELAY from the server. 4288 Only applies if the softerr mount option is enabled, 4289 and the specified value is >= 0. 4290 4291 nfs.idmap_cache_timeout= 4292 [NFS] set the maximum lifetime for idmapper cache 4293 entries. 4294 4295 nfs.max_session_cb_slots= 4296 [NFSv4.1] Sets the maximum number of session 4297 slots the client will assign to the callback 4298 channel. This determines the maximum number of 4299 callbacks the client will process in parallel for 4300 a particular server. 4301 4302 nfs.max_session_slots= 4303 [NFSv4.1] Sets the maximum number of session slots 4304 the client will attempt to negotiate with the server. 4305 This limits the number of simultaneous RPC requests 4306 that the client can send to the NFSv4.1 server. 4307 Note that there is little point in setting this 4308 value higher than the max_tcp_slot_table_limit. 4309 4310 nfs.nfs4_disable_idmapping= 4311 [NFSv4] When set to the default of '1', this option 4312 ensures that both the RPC level authentication 4313 scheme and the NFS level operations agree to use 4314 numeric uids/gids if the mount is using the 4315 'sec=sys' security flavour. In effect it is 4316 disabling idmapping, which can make migration from 4317 legacy NFSv2/v3 systems to NFSv4 easier. 4318 Servers that do not support this mode of operation 4319 will be autodetected by the client, and it will fall 4320 back to using the idmapper. 4321 To turn off this behaviour, set the value to '0'. 4322 4323 nfs.nfs4_unique_id= 4324 [NFS4] Specify an additional fixed unique ident- 4325 ification string that NFSv4 clients can insert into 4326 their nfs_client_id4 string. This is typically a 4327 UUID that is generated at system install time. 4328 4329 nfs.recover_lost_locks= 4330 [NFSv4] Attempt to recover locks that were lost due 4331 to a lease timeout on the server. Please note that 4332 doing this risks data corruption, since there are 4333 no guarantees that the file will remain unchanged 4334 after the locks are lost. 4335 If you want to enable the kernel legacy behaviour of 4336 attempting to recover these locks, then set this 4337 parameter to '1'. 4338 The default parameter value of '0' causes the kernel 4339 not to attempt recovery of lost locks. 4340 4341 nfs.send_implementation_id= 4342 [NFSv4.1] Send client implementation identification 4343 information in exchange_id requests. 4344 If zero, no implementation identification information 4345 will be sent. 4346 The default is to send the implementation identification 4347 information. 4348 4349 nfs4.layoutstats_timer= 4350 [NFSv4.2] Change the rate at which the kernel sends 4351 layoutstats to the pNFS metadata server. 4352 4353 Setting this to value to 0 causes the kernel to use 4354 whatever value is the default set by the layout 4355 driver. A non-zero value sets the minimum interval 4356 in seconds between layoutstats transmissions. 4357 4358 nfsd.inter_copy_offload_enable= 4359 [NFSv4.2] When set to 1, the server will support 4360 server-to-server copies for which this server is 4361 the destination of the copy. 4362 4363 nfsd.nfs4_disable_idmapping= 4364 [NFSv4] When set to the default of '1', the NFSv4 4365 server will return only numeric uids and gids to 4366 clients using auth_sys, and will accept numeric uids 4367 and gids from such clients. This is intended to ease 4368 migration from NFSv2/v3. 4369 4370 nfsd.nfsd4_ssc_umount_timeout= 4371 [NFSv4.2] When used as the destination of a 4372 server-to-server copy, knfsd temporarily mounts 4373 the source server. It caches the mount in case 4374 it will be needed again, and discards it if not 4375 used for the number of milliseconds specified by 4376 this parameter. 4377 4378 nfsaddrs= [NFS] Deprecated. Use ip= instead. 4379 See Documentation/admin-guide/nfs/nfsroot.rst. 4380 4381 nfsroot= [NFS] nfs root filesystem for disk-less boxes. 4382 See Documentation/admin-guide/nfs/nfsroot.rst. 4383 4384 nfsrootdebug [NFS] enable nfsroot debugging messages. 4385 See Documentation/admin-guide/nfs/nfsroot.rst. 4386 4387 nmi_backtrace.backtrace_idle [KNL] 4388 Dump stacks even of idle CPUs in response to an 4389 NMI stack-backtrace request. 4390 4391 nmi_debug= [KNL,SH] Specify one or more actions to take 4392 when a NMI is triggered. 4393 Format: [state][,regs][,debounce][,die] 4394 4395 nmi_watchdog= [KNL,BUGS=X86] Debugging features for SMP kernels 4396 Format: [panic,][nopanic,][rNNN,][num] 4397 Valid num: 0 or 1 4398 0 - turn hardlockup detector in nmi_watchdog off 4399 1 - turn hardlockup detector in nmi_watchdog on 4400 rNNN - configure the watchdog with raw perf event 0xNNN 4401 4402 When panic is specified, panic when an NMI watchdog 4403 timeout occurs (or 'nopanic' to not panic on an NMI 4404 watchdog, if CONFIG_BOOTPARAM_HARDLOCKUP_PANIC is set) 4405 To disable both hard and soft lockup detectors, 4406 please see 'nowatchdog'. 4407 This is useful when you use a panic=... timeout and 4408 need the box quickly up again. 4409 4410 These settings can be accessed at runtime via 4411 the nmi_watchdog and hardlockup_panic sysctls. 4412 4413 no4lvl [RISCV,EARLY] Disable 4-level and 5-level paging modes. 4414 Forces kernel to use 3-level paging instead. 4415 4416 no5lvl [X86-64,RISCV,EARLY] Disable 5-level paging mode. Forces 4417 kernel to use 4-level paging instead. 4418 4419 noalign [KNL,ARM] 4420 4421 noapic [SMP,APIC,EARLY] Tells the kernel to not make use of any 4422 IOAPICs that may be present in the system. 4423 4424 noapictimer [APIC,X86] Don't set up the APIC timer 4425 4426 noautogroup Disable scheduler automatic task group creation. 4427 4428 nocache [ARM,EARLY] 4429 4430 no_console_suspend 4431 [HW] Never suspend the console 4432 Disable suspending of consoles during suspend and 4433 hibernate operations. Once disabled, debugging 4434 messages can reach various consoles while the rest 4435 of the system is being put to sleep (ie, while 4436 debugging driver suspend/resume hooks). This may 4437 not work reliably with all consoles, but is known 4438 to work with serial and VGA consoles. 4439 To facilitate more flexible debugging, we also add 4440 console_suspend, a printk module parameter to control 4441 it. Users could use console_suspend (usually 4442 /sys/module/printk/parameters/console_suspend) to 4443 turn on/off it dynamically. 4444 4445 no_debug_objects 4446 [KNL,EARLY] Disable object debugging 4447 4448 nodsp [SH] Disable hardware DSP at boot time. 4449 4450 noefi [EFI,EARLY] Disable EFI runtime services support. 4451 4452 no_entry_flush [PPC,EARLY] Don't flush the L1-D cache when entering the kernel. 4453 4454 noexec32 [X86-64] 4455 This affects only 32-bit executables. 4456 noexec32=on: enable non-executable mappings (default) 4457 read doesn't imply executable mappings 4458 noexec32=off: disable non-executable mappings 4459 read implies executable mappings 4460 4461 no_file_caps Tells the kernel not to honor file capabilities. The 4462 only way then for a file to be executed with privilege 4463 is to be setuid root or executed by root. 4464 4465 nofpu [MIPS,SH] Disable hardware FPU at boot time. 4466 4467 nofsgsbase [X86] Disables FSGSBASE instructions. 4468 4469 nofxsr [BUGS=X86-32] Disables x86 floating point extended 4470 register save and restore. The kernel will only save 4471 legacy floating-point registers on task switch. 4472 4473 nogbpages [X86] Do not use GB pages for kernel direct mappings. 4474 4475 no_hash_pointers 4476 [KNL,EARLY] 4477 Alias for "hash_pointers=never". 4478 4479 nohibernate [HIBERNATION] Disable hibernation and resume. 4480 4481 nohlt [ARM,ARM64,MICROBLAZE,MIPS,PPC,RISCV,SH] Forces the kernel to 4482 busy wait in do_idle() and not use the arch_cpu_idle() 4483 implementation; requires CONFIG_GENERIC_IDLE_POLL_SETUP 4484 to be effective. This is useful on platforms where the 4485 sleep(SH) or wfi(ARM,ARM64) instructions do not work 4486 correctly or when doing power measurements to evaluate 4487 the impact of the sleep instructions. This is also 4488 useful when using JTAG debugger. 4489 4490 nohpet [X86] Don't use the HPET timer. 4491 4492 nohugeiomap [KNL,X86,PPC,ARM64,EARLY] Disable kernel huge I/O mappings. 4493 4494 nohugevmalloc [KNL,X86,PPC,ARM64,EARLY] Disable kernel huge vmalloc mappings. 4495 4496 nohz= [KNL] Boottime enable/disable dynamic ticks 4497 Valid arguments: on, off 4498 Default: on 4499 4500 nohz_full= [KNL,BOOT,SMP,ISOL] 4501 The argument is a cpu list, as described above. 4502 In kernels built with CONFIG_NO_HZ_FULL=y, set 4503 the specified list of CPUs whose tick will be stopped 4504 whenever possible. The boot CPU will be forced outside 4505 the range to maintain the timekeeping. Any CPUs 4506 in this list will have their RCU callbacks offloaded, 4507 just as if they had also been called out in the 4508 rcu_nocbs= boot parameter. 4509 4510 Note that this argument takes precedence over 4511 the CONFIG_RCU_NOCB_CPU_DEFAULT_ALL option. 4512 4513 noinitrd [Deprecated,RAM] Tells the kernel not to load any configured 4514 initial RAM disk. Currently this parameter applies to 4515 initrd only, not to initramfs. But it applies to both 4516 in EFI mode. 4517 4518 nointremap [X86-64,Intel-IOMMU,EARLY] Do not enable interrupt 4519 remapping. 4520 [Deprecated - use intremap=off] 4521 4522 noinvpcid [X86,EARLY] Disable the INVPCID cpu feature. 4523 4524 noiotrap [SH] Disables trapped I/O port accesses. 4525 4526 noirqdebug [X86-32] Disables the code which attempts to detect and 4527 disable unhandled interrupt sources. 4528 4529 noisapnp [ISAPNP] Disables ISA PnP code. 4530 4531 nokaslr [KNL,EARLY] 4532 When CONFIG_RANDOMIZE_BASE is set, this disables 4533 kernel and module base offset ASLR (Address Space 4534 Layout Randomization). 4535 4536 no-kvmapf [X86,KVM,EARLY] Disable paravirtualized asynchronous page 4537 fault handling. 4538 4539 no-kvmclock [X86,KVM,EARLY] Disable paravirtualized KVM clock driver 4540 4541 nolapic [X86-32,APIC,EARLY] Do not enable or use the local APIC. 4542 4543 nolapic_timer [X86-32,APIC,EARLY] Do not use the local APIC timer. 4544 4545 nomce [X86-32] Disable Machine Check Exception 4546 4547 nomfgpt [X86-32] Disable Multi-Function General Purpose 4548 Timer usage (for AMD Geode machines). 4549 4550 nomodeset Disable kernel modesetting. Most systems' firmware 4551 sets up a display mode and provides framebuffer memory 4552 for output. With nomodeset, DRM and fbdev drivers will 4553 not load if they could possibly displace the pre- 4554 initialized output. Only the system framebuffer will 4555 be available for use. The respective drivers will not 4556 perform display-mode changes or accelerated rendering. 4557 4558 Useful as error fallback, or for testing and debugging. 4559 4560 nomodule Disable module load 4561 4562 nonmi_ipi [X86] Disable using NMI IPIs during panic/reboot to 4563 shutdown the other cpus. Instead use the REBOOT_VECTOR 4564 irq. 4565 4566 nopat [X86,EARLY] Disable PAT (page attribute table extension of 4567 pagetables) support. 4568 4569 nopcid [X86-64,EARLY] Disable the PCID cpu feature. 4570 4571 nopku [X86] Disable Memory Protection Keys CPU feature found 4572 in some Intel CPUs. 4573 4574 nopti [X86-64,EARLY] 4575 Equivalent to pti=off 4576 4577 nopv= [X86,XEN,KVM,HYPER_V,VMWARE,EARLY] 4578 Disables the PV optimizations forcing the guest to run 4579 as generic guest with no PV drivers. Currently support 4580 XEN HVM, KVM, HYPER_V and VMWARE guest. 4581 4582 nopvspin [X86,XEN,KVM,EARLY] 4583 Disables the qspinlock slow path using PV optimizations 4584 which allow the hypervisor to 'idle' the guest on lock 4585 contention. 4586 4587 norandmaps Don't use address space randomization. Equivalent to 4588 echo 0 > /proc/sys/kernel/randomize_va_space 4589 4590 noreplace-smp [X86-32,SMP] Don't replace SMP instructions 4591 with UP alternatives 4592 4593 noresume [SWSUSP] Disables resume and restores original swap 4594 space. 4595 4596 no-scroll [VGA] Disables scrollback. 4597 This is required for the Braillex ib80-piezo Braille 4598 reader made by F.H. Papenmeier (Germany). 4599 4600 nosgx [X86-64,SGX,EARLY] Disables Intel SGX kernel support. 4601 4602 nosmap [PPC,EARLY] 4603 Disable SMAP (Supervisor Mode Access Prevention) 4604 even if it is supported by processor. 4605 4606 nosmep [PPC64s,EARLY] 4607 Disable SMEP (Supervisor Mode Execution Prevention) 4608 even if it is supported by processor. 4609 4610 nosmp [SMP,EARLY] Tells an SMP kernel to act as a UP kernel, 4611 and disable the IO APIC. legacy for "maxcpus=0". 4612 4613 nosmt [KNL,MIPS,PPC,EARLY] Disable symmetric multithreading (SMT). 4614 Equivalent to smt=1. 4615 4616 [KNL,LOONGARCH,X86,ARM64,PPC,S390] Disable symmetric multithreading (SMT). 4617 nosmt=force: Force disable SMT, cannot be undone 4618 via the sysfs control file. 4619 4620 nosoftlockup [KNL] Disable the soft-lockup detector. 4621 4622 nospec_store_bypass_disable 4623 [HW,EARLY] Disable all mitigations for the Speculative 4624 Store Bypass vulnerability 4625 4626 nospectre_bhb [ARM64,EARLY] Disable all mitigations for Spectre-BHB (branch 4627 history injection) vulnerability. System may allow data leaks 4628 with this option. 4629 4630 nospectre_v1 [X86,PPC,EARLY] Disable mitigations for Spectre Variant 1 4631 (bounds check bypass). With this option data leaks are 4632 possible in the system. 4633 4634 nospectre_v2 [X86,PPC_E500,ARM64,EARLY] Disable all mitigations 4635 for the Spectre variant 2 (indirect branch 4636 prediction) vulnerability. System may allow data 4637 leaks with this option. 4638 4639 no-steal-acc [X86,PV_OPS,ARM64,PPC/PSERIES,RISCV,LOONGARCH,EARLY] 4640 Disable paravirtualized steal time accounting. steal time 4641 is computed, but won't influence scheduler behaviour 4642 4643 nosync [HW,M68K] Disables sync negotiation for all devices. 4644 4645 no_timer_check [X86,APIC] Disables the code which tests for broken 4646 timer IRQ sources, i.e., the IO-APIC timer. This can 4647 work around problems with incorrect timer 4648 initialization on some boards. 4649 4650 no_uaccess_flush 4651 [PPC,EARLY] Don't flush the L1-D cache after accessing user data. 4652 4653 novmcoredd [KNL,KDUMP] 4654 Disable device dump. Device dump allows drivers to 4655 append dump data to vmcore so you can collect driver 4656 specified debug info. Drivers can append the data 4657 without any limit and this data is stored in memory, 4658 so this may cause significant memory stress. Disabling 4659 device dump can help save memory but the driver debug 4660 data will be no longer available. This parameter 4661 is only available when CONFIG_PROC_VMCORE_DEVICE_DUMP 4662 is set. 4663 4664 no-vmw-sched-clock 4665 [X86,PV_OPS,EARLY] Disable paravirtualized VMware 4666 scheduler clock and use the default one. 4667 4668 nowatchdog [KNL] Disable both lockup detectors, i.e. 4669 soft-lockup and NMI watchdog (hard-lockup). 4670 4671 nowb [ARM,EARLY] 4672 4673 nox2apic [X86-64,APIC,EARLY] Do not enable x2APIC mode. 4674 4675 NOTE: this parameter will be ignored on systems with the 4676 LEGACY_XAPIC_DISABLED bit set in the 4677 IA32_XAPIC_DISABLE_STATUS MSR. 4678 4679 noxsave [BUGS=X86] Disables x86 extended register state save 4680 and restore using xsave. The kernel will fallback to 4681 enabling legacy floating-point and sse state. 4682 4683 noxsaveopt [X86] Disables xsaveopt used in saving x86 extended 4684 register states. The kernel will fall back to use 4685 xsave to save the states. By using this parameter, 4686 performance of saving the states is degraded because 4687 xsave doesn't support modified optimization while 4688 xsaveopt supports it on xsaveopt enabled systems. 4689 4690 noxsaves [X86] Disables xsaves and xrstors used in saving and 4691 restoring x86 extended register state in compacted 4692 form of xsave area. The kernel will fall back to use 4693 xsaveopt and xrstor to save and restore the states 4694 in standard form of xsave area. By using this 4695 parameter, xsave area per process might occupy more 4696 memory on xsaves enabled systems. 4697 4698 nr_cpus= [SMP,EARLY] Maximum number of processors that an SMP kernel 4699 could support. nr_cpus=n : n >= 1 limits the kernel to 4700 support 'n' processors. It could be larger than the 4701 number of already plugged CPU during bootup, later in 4702 runtime you can physically add extra cpu until it reaches 4703 n. So during boot up some boot time memory for per-cpu 4704 variables need be pre-allocated for later physical cpu 4705 hot plugging. 4706 4707 nr_uarts= [SERIAL] maximum number of UARTs to be registered. 4708 4709 numa=off [KNL, ARM64, PPC, RISCV, SPARC, X86, EARLY] 4710 Disable NUMA, Only set up a single NUMA node 4711 spanning all memory. 4712 4713 numa=fake=<size>[MG] 4714 [KNL, ARM64, RISCV, X86, EARLY] 4715 If given as a memory unit, fills all system RAM with 4716 nodes of size interleaved over physical nodes. 4717 4718 numa=fake=<N> 4719 [KNL, ARM64, RISCV, X86, EARLY] 4720 If given as an integer, fills all system RAM with N 4721 fake nodes interleaved over physical nodes. 4722 4723 numa=fake=<N>U 4724 [KNL, ARM64, RISCV, X86, EARLY] 4725 If given as an integer followed by 'U', it will 4726 divide each physical node into N emulated nodes. 4727 4728 numa=noacpi [X86] Don't parse the SRAT table for NUMA setup 4729 4730 numa=nohmat [X86] Don't parse the HMAT table for NUMA setup, or 4731 soft-reserved memory partitioning. 4732 4733 numa_balancing= [KNL,ARM64,PPC,RISCV,S390,X86] Enable or disable automatic 4734 NUMA balancing. 4735 Allowed values are enable and disable 4736 4737 numa_zonelist_order= [KNL, BOOT] Select zonelist order for NUMA. 4738 'node', 'default' can be specified 4739 This can be set from sysctl after boot. 4740 See Documentation/admin-guide/sysctl/vm.rst for details. 4741 4742 nvme.quirks= [NVME] A list of quirk entries to augment the built-in 4743 nvme quirk list. List entries are separated by a 4744 '-' character. 4745 Each entry has the form VendorID:ProductID:quirk_names. 4746 The IDs are 4-digits hex numbers and quirk_names is a 4747 list of quirk names separated by commas. A quirk name 4748 can be prefixed by '^', meaning that the specified 4749 quirk must be disabled. 4750 4751 Example: 4752 nvme.quirks=7710:2267:bogus_nid,^identify_cns-9900:7711:broken_msi 4753 4754 ohci1394_dma=early [HW,EARLY] enable debugging via the ohci1394 driver. 4755 See Documentation/core-api/debugging-via-ohci1394.rst for more 4756 info. 4757 4758 olpc_ec_timeout= [OLPC] ms delay when issuing EC commands 4759 Rather than timing out after 20 ms if an EC 4760 command is not properly ACKed, override the length 4761 of the timeout. We have interrupts disabled while 4762 waiting for the ACK, so if this is set too high 4763 interrupts *may* be lost! 4764 4765 omap_mux= [OMAP] Override bootloader pin multiplexing. 4766 Format: <mux_mode0.mode_name=value>... 4767 For example, to override I2C bus2: 4768 omap_mux=i2c2_scl.i2c2_scl=0x100,i2c2_sda.i2c2_sda=0x100 4769 4770 onenand.bdry= [HW,MTD] Flex-OneNAND Boundary Configuration 4771 4772 Format: [die0_boundary][,die0_lock][,die1_boundary][,die1_lock] 4773 4774 boundary - index of last SLC block on Flex-OneNAND. 4775 The remaining blocks are configured as MLC blocks. 4776 lock - Configure if Flex-OneNAND boundary should be locked. 4777 Once locked, the boundary cannot be changed. 4778 1 indicates lock status, 0 indicates unlock status. 4779 4780 oops=panic [KNL,EARLY] 4781 Always panic on oopses. Default is to just kill the 4782 process, but there is a small probability of 4783 deadlocking the machine. 4784 This will also cause panics on machine check exceptions. 4785 Useful together with panic=30 to trigger a reboot. 4786 4787 page_alloc.shuffle= 4788 [KNL] Boolean flag to control whether the page allocator 4789 should randomize its free lists. This parameter can be 4790 used to enable/disable page randomization. The state of 4791 the flag can be read from sysfs at: 4792 /sys/module/page_alloc/parameters/shuffle. 4793 This parameter is only available if CONFIG_SHUFFLE_PAGE_ALLOCATOR=y. 4794 4795 page_owner= [KNL,EARLY] Boot-time page_owner enabling option. 4796 Storage of the information about who allocated 4797 each page is disabled in default. With this switch, 4798 we can turn it on. 4799 on: enable the feature 4800 4801 page_poison= [KNL,EARLY] Boot-time parameter changing the state of 4802 poisoning on the buddy allocator, available with 4803 CONFIG_PAGE_POISONING=y. 4804 off: turn off poisoning (default) 4805 on: turn on poisoning 4806 4807 page_reporting.page_reporting_order= 4808 [KNL] Minimal page reporting order 4809 Format: <integer> 4810 Adjust the minimal page reporting order. The page 4811 reporting is disabled when it exceeds MAX_PAGE_ORDER. 4812 4813 panic= [KNL] Kernel behaviour on panic: delay <timeout> 4814 timeout > 0: seconds before rebooting 4815 timeout = 0: wait forever 4816 timeout < 0: reboot immediately 4817 Format: <timeout> 4818 4819 panic_on_taint= [KNL,EARLY] 4820 Bitmask for conditionally calling panic() in add_taint() 4821 Format: <hex>[,nousertaint] 4822 Hexadecimal bitmask representing the set of TAINT flags 4823 that will cause the kernel to panic when add_taint() is 4824 called with any of the flags in this set. 4825 The optional switch "nousertaint" can be utilized to 4826 prevent userspace forced crashes by writing to sysctl 4827 /proc/sys/kernel/tainted any flagset matching with the 4828 bitmask set on panic_on_taint. 4829 See Documentation/admin-guide/tainted-kernels.rst for 4830 extra details on the taint flags that users can pick 4831 to compose the bitmask to assign to panic_on_taint. 4832 4833 panic_on_warn=1 panic() instead of WARN(). Useful to cause kdump 4834 on a WARN(). 4835 4836 panic_force_cpu= 4837 [KNL,SMP] Force panic handling to execute on a specific CPU. 4838 Format: <cpu number> 4839 Some platforms require panic handling to occur on a 4840 specific CPU for the crash kernel to function correctly. 4841 This can be due to firmware limitations, interrupt routing 4842 constraints, or platform-specific requirements where only 4843 a particular CPU can safely enter the crash kernel. 4844 When set, panic() will redirect execution to the specified 4845 CPU before proceeding with the normal panic and kexec flow. 4846 If the target CPU is offline or unavailable, panic proceeds 4847 on the current CPU. 4848 This option should only be used for systems with the above 4849 constraints as it might cause the panic operation to be less reliable. 4850 4851 panic_print= Bitmask for printing system info when panic happens. 4852 User can chose combination of the following bits: 4853 bit 0: print all tasks info 4854 bit 1: print system memory info 4855 bit 2: print timer info 4856 bit 3: print locks info if CONFIG_LOCKDEP is on 4857 bit 4: print ftrace buffer 4858 bit 5: replay all kernel messages on consoles at the end of panic 4859 bit 6: print all CPUs backtrace (if available in the arch) 4860 bit 7: print only tasks in uninterruptible (blocked) state 4861 *Be aware* that this option may print a _lot_ of lines, 4862 so there are risks of losing older messages in the log. 4863 Use this option carefully, maybe worth to setup a 4864 bigger log buffer with "log_buf_len" along with this. 4865 4866 panic_sys_info= A comma separated list of extra information to be dumped 4867 on panic. 4868 Format: val[,val...] 4869 Where @val can be any of the following: 4870 4871 tasks: print all tasks info 4872 mem: print system memory info 4873 timers: print timers info 4874 locks: print locks info if CONFIG_LOCKDEP is on 4875 ftrace: print ftrace buffer 4876 all_bt: print all CPUs backtrace (if available in the arch) 4877 blocked_tasks: print only tasks in uninterruptible (blocked) state 4878 4879 This is a human readable alternative to the 'panic_print' option. 4880 4881 panic_console_replay 4882 When panic happens, replay all kernel messages on 4883 consoles at the end of panic. 4884 4885 parkbd.port= [HW] Parallel port number the keyboard adapter is 4886 connected to, default is 0. 4887 Format: <parport#> 4888 parkbd.mode= [HW] Parallel port keyboard adapter mode of operation, 4889 0 for XT, 1 for AT (default is AT). 4890 Format: <mode> 4891 4892 parport= [HW,PPT] Specify parallel ports. 0 disables. 4893 Format: { 0 | auto | 0xBBB[,IRQ[,DMA]] } 4894 Use 'auto' to force the driver to use any 4895 IRQ/DMA settings detected (the default is to 4896 ignore detected IRQ/DMA settings because of 4897 possible conflicts). You can specify the base 4898 address, IRQ, and DMA settings; IRQ and DMA 4899 should be numbers, or 'auto' (for using detected 4900 settings on that particular port), or 'nofifo' 4901 (to avoid using a FIFO even if it is detected). 4902 Parallel ports are assigned in the order they 4903 are specified on the command line, starting 4904 with parport0. 4905 4906 parport_init_mode= [HW,PPT] 4907 Configure VIA parallel port to operate in 4908 a specific mode. This is necessary on Pegasos 4909 computer where firmware has no options for setting 4910 up parallel port mode and sets it to spp. 4911 Currently this function knows 686a and 8231 chips. 4912 Format: [spp|ps2|epp|ecp|ecpepp] 4913 4914 pata_legacy.all= [HW,LIBATA] 4915 Format: <int> 4916 Set to non-zero to probe primary and secondary ISA 4917 port ranges on PCI systems where no PCI PATA device 4918 has been found at either range. Disabled by default. 4919 4920 pata_legacy.autospeed= [HW,LIBATA] 4921 Format: <int> 4922 Set to non-zero if a chip is present that snoops speed 4923 changes. Disabled by default. 4924 4925 pata_legacy.ht6560a= [HW,LIBATA] 4926 Format: <int> 4927 Set to 1, 2, or 3 for HT 6560A on the primary channel, 4928 the secondary channel, or both channels respectively. 4929 Disabled by default. 4930 4931 pata_legacy.ht6560b= [HW,LIBATA] 4932 Format: <int> 4933 Set to 1, 2, or 3 for HT 6560B on the primary channel, 4934 the secondary channel, or both channels respectively. 4935 Disabled by default. 4936 4937 pata_legacy.iordy_mask= [HW,LIBATA] 4938 Format: <int> 4939 IORDY enable mask. Set individual bits to allow IORDY 4940 for the respective channel. Bit 0 is for the first 4941 legacy channel handled by this driver, bit 1 is for 4942 the second channel, and so on. The sequence will often 4943 correspond to the primary legacy channel, the secondary 4944 legacy channel, and so on, but the handling of a PCI 4945 bus and the use of other driver options may interfere 4946 with the sequence. By default IORDY is allowed across 4947 all channels. 4948 4949 pata_legacy.opti82c46x= [HW,LIBATA] 4950 Format: <int> 4951 Set to 1, 2, or 3 for Opti 82c611A on the primary 4952 channel, the secondary channel, or both channels 4953 respectively. Disabled by default. 4954 4955 pata_legacy.opti82c611a= [HW,LIBATA] 4956 Format: <int> 4957 Set to 1, 2, or 3 for Opti 82c465MV on the primary 4958 channel, the secondary channel, or both channels 4959 respectively. Disabled by default. 4960 4961 pata_legacy.pio_mask= [HW,LIBATA] 4962 Format: <int> 4963 PIO mode mask for autospeed devices. Set individual 4964 bits to allow the use of the respective PIO modes. 4965 Bit 0 is for mode 0, bit 1 is for mode 1, and so on. 4966 All modes allowed by default. 4967 4968 pata_legacy.probe_all= [HW,LIBATA] 4969 Format: <int> 4970 Set to non-zero to probe tertiary and further ISA 4971 port ranges on PCI systems. Disabled by default. 4972 4973 pata_legacy.probe_mask= [HW,LIBATA] 4974 Format: <int> 4975 Probe mask for legacy ISA PATA ports. Depending on 4976 platform configuration and the use of other driver 4977 options up to 6 legacy ports are supported: 0x1f0, 4978 0x170, 0x1e8, 0x168, 0x1e0, 0x160, however probing 4979 of individual ports can be disabled by setting the 4980 corresponding bits in the mask to 1. Bit 0 is for 4981 the first port in the list above (0x1f0), and so on. 4982 By default all supported ports are probed. 4983 4984 pata_legacy.qdi= [HW,LIBATA] 4985 Format: <int> 4986 Set to non-zero to probe QDI controllers. By default 4987 set to 1 if CONFIG_PATA_QDI_MODULE, 0 otherwise. 4988 4989 pata_legacy.winbond= [HW,LIBATA] 4990 Format: <int> 4991 Set to non-zero to probe Winbond controllers. Use 4992 the standard I/O port (0x130) if 1, otherwise the 4993 value given is the I/O port to use (typically 0x1b0). 4994 By default set to 1 if CONFIG_PATA_WINBOND_VLB_MODULE, 4995 0 otherwise. 4996 4997 pata_platform.pio_mask= [HW,LIBATA] 4998 Format: <int> 4999 Supported PIO mode mask. Set individual bits to allow 5000 the use of the respective PIO modes. Bit 0 is for 5001 mode 0, bit 1 is for mode 1, and so on. Mode 0 only 5002 allowed by default. 5003 5004 pause_on_oops=<int> 5005 Halt all CPUs after the first oops has been printed for 5006 the specified number of seconds. This is to be used if 5007 your oopses keep scrolling off the screen. 5008 5009 pci=option[,option...] [PCI,EARLY] various PCI subsystem options. 5010 5011 Some options herein operate on a specific device 5012 or a set of devices (<pci_dev>). These are 5013 specified in one of the following formats: 5014 5015 [<domain>:]<bus>:<dev>.<func>[/<dev>.<func>]* 5016 pci:<vendor>:<device>[:<subvendor>:<subdevice>] 5017 5018 Note: the first format specifies a PCI 5019 bus/device/function address which may change 5020 if new hardware is inserted, if motherboard 5021 firmware changes, or due to changes caused 5022 by other kernel parameters. If the 5023 domain is left unspecified, it is 5024 taken to be zero. Optionally, a path 5025 to a device through multiple device/function 5026 addresses can be specified after the base 5027 address (this is more robust against 5028 renumbering issues). The second format 5029 selects devices using IDs from the 5030 configuration space which may match multiple 5031 devices in the system. 5032 5033 earlydump dump PCI config space before the kernel 5034 changes anything 5035 off [X86] don't probe for the PCI bus 5036 bios [X86-32] force use of PCI BIOS, don't access 5037 the hardware directly. Use this if your machine 5038 has a non-standard PCI host bridge. 5039 nobios [X86-32] disallow use of PCI BIOS, only direct 5040 hardware access methods are allowed. Use this 5041 if you experience crashes upon bootup and you 5042 suspect they are caused by the BIOS. 5043 conf1 [X86] Force use of PCI Configuration Access 5044 Mechanism 1 (config address in IO port 0xCF8, 5045 data in IO port 0xCFC, both 32-bit). 5046 conf2 [X86] Force use of PCI Configuration Access 5047 Mechanism 2 (IO port 0xCF8 is an 8-bit port for 5048 the function, IO port 0xCFA, also 8-bit, sets 5049 bus number. The config space is then accessed 5050 through ports 0xC000-0xCFFF). 5051 See http://wiki.osdev.org/PCI for more info 5052 on the configuration access mechanisms. 5053 noaer [PCIE] If the PCIEAER kernel config parameter is 5054 enabled, this kernel boot option can be used to 5055 disable the use of PCIE advanced error reporting. 5056 nodomains [PCI] Disable support for multiple PCI 5057 root domains (aka PCI segments, in ACPI-speak). 5058 nommconf [X86] Disable use of MMCONFIG for PCI 5059 Configuration 5060 check_enable_amd_mmconf [X86] check for and enable 5061 properly configured MMIO access to PCI 5062 config space on AMD family 10h CPU 5063 nomsi [MSI] If the PCI_MSI kernel config parameter is 5064 enabled, this kernel boot option can be used to 5065 disable the use of MSI interrupts system-wide. 5066 noioapicquirk [APIC] Disable all boot interrupt quirks. 5067 Safety option to keep boot IRQs enabled. This 5068 should never be necessary. 5069 ioapicreroute [APIC] Enable rerouting of boot IRQs to the 5070 primary IO-APIC for bridges that cannot disable 5071 boot IRQs. This fixes a source of spurious IRQs 5072 when the system masks IRQs. 5073 noioapicreroute [APIC] Disable workaround that uses the 5074 boot IRQ equivalent of an IRQ that connects to 5075 a chipset where boot IRQs cannot be disabled. 5076 The opposite of ioapicreroute. 5077 biosirq [X86-32] Use PCI BIOS calls to get the interrupt 5078 routing table. These calls are known to be buggy 5079 on several machines and they hang the machine 5080 when used, but on other computers it's the only 5081 way to get the interrupt routing table. Try 5082 this option if the kernel is unable to allocate 5083 IRQs or discover secondary PCI buses on your 5084 motherboard. 5085 rom [X86] Assign address space to expansion ROMs. 5086 Use with caution as certain devices share 5087 address decoders between ROMs and other 5088 resources. 5089 norom [X86] Do not assign address space to 5090 expansion ROMs that do not already have 5091 BIOS assigned address ranges. 5092 nobar [X86] Do not assign address space to the 5093 BARs that weren't assigned by the BIOS. 5094 irqmask=0xMMMM [X86] Set a bit mask of IRQs allowed to be 5095 assigned automatically to PCI devices. You can 5096 make the kernel exclude IRQs of your ISA cards 5097 this way. 5098 pirqaddr=0xAAAAA [X86] Specify the physical address 5099 of the PIRQ table (normally generated 5100 by the BIOS) if it is outside the 5101 F0000h-100000h range. 5102 lastbus=N [X86] Scan all buses thru bus #N. Can be 5103 useful if the kernel is unable to find your 5104 secondary buses and you want to tell it 5105 explicitly which ones they are. 5106 assign-busses [X86] Always assign all PCI bus 5107 numbers ourselves, overriding 5108 whatever the firmware may have done. 5109 usepirqmask [X86] Honor the possible IRQ mask stored 5110 in the BIOS $PIR table. This is needed on 5111 some systems with broken BIOSes, notably 5112 some HP Pavilion N5400 and Omnibook XE3 5113 notebooks. This will have no effect if ACPI 5114 IRQ routing is enabled. 5115 noacpi [X86] Do not use ACPI for IRQ routing 5116 or for PCI scanning. 5117 use_crs [X86] Use PCI host bridge window information 5118 from ACPI. On BIOSes from 2008 or later, this 5119 is enabled by default. If you need to use this, 5120 please report a bug. 5121 nocrs [X86] Ignore PCI host bridge windows from ACPI. 5122 If you need to use this, please report a bug. 5123 use_e820 [X86] Use E820 reservations to exclude parts of 5124 PCI host bridge windows. This is a workaround 5125 for BIOS defects in host bridge _CRS methods. 5126 If you need to use this, please report a bug to 5127 <linux-pci@vger.kernel.org>. 5128 no_e820 [X86] Ignore E820 reservations for PCI host 5129 bridge windows. This is the default on modern 5130 hardware. If you need to use this, please report 5131 a bug to <linux-pci@vger.kernel.org>. 5132 routeirq Do IRQ routing for all PCI devices. 5133 This is normally done in pci_enable_device(), 5134 so this option is a temporary workaround 5135 for broken drivers that don't call it. 5136 skip_isa_align [X86] do not align io start addr, so can 5137 handle more pci cards 5138 noearly [X86] Don't do any early type 1 scanning. 5139 This might help on some broken boards which 5140 machine check when some devices' config space 5141 is read. But various workarounds are disabled 5142 and some IOMMU drivers will not work. 5143 bfsort Sort PCI devices into breadth-first order. 5144 This sorting is done to get a device 5145 order compatible with older (<= 2.4) kernels. 5146 nobfsort Don't sort PCI devices into breadth-first order. 5147 pcie_bus_tune_off Disable PCIe MPS (Max Payload Size) 5148 tuning and use the BIOS-configured MPS defaults. 5149 pcie_bus_safe Set every device's MPS to the largest value 5150 supported by all devices below the root complex. 5151 pcie_bus_perf Set device MPS to the largest allowable MPS 5152 based on its parent bus. Also set MRRS (Max 5153 Read Request Size) to the largest supported 5154 value (no larger than the MPS that the device 5155 or bus can support) for best performance. 5156 pcie_bus_peer2peer Set every device's MPS to 128B, which 5157 every device is guaranteed to support. This 5158 configuration allows peer-to-peer DMA between 5159 any pair of devices, possibly at the cost of 5160 reduced performance. This also guarantees 5161 that hot-added devices will work. 5162 cbiosize=nn[KMG] The fixed amount of bus space which is 5163 reserved for the CardBus bridge's IO window. 5164 The default value is 256 bytes. 5165 cbmemsize=nn[KMG] The fixed amount of bus space which is 5166 reserved for the CardBus bridge's memory 5167 window. The default value is 64 megabytes. 5168 resource_alignment= 5169 Format: 5170 [<order of align>@]<pci_dev>[; ...] 5171 Specifies alignment and device to reassign 5172 aligned memory resources. How to 5173 specify the device is described above. 5174 If <order of align> is not specified, 5175 PAGE_SIZE is used as alignment. 5176 A PCI-PCI bridge can be specified if resource 5177 windows need to be expanded. 5178 To specify the alignment for several 5179 instances of a device, the PCI vendor, 5180 device, subvendor, and subdevice may be 5181 specified, e.g., 12@pci:8086:9c22:103c:198f 5182 for 4096-byte alignment. 5183 ecrc= Enable/disable PCIe ECRC (transaction layer 5184 end-to-end CRC checking). Only effective if 5185 OS has native AER control (either granted by 5186 ACPI _OSC or forced via "pcie_ports=native") 5187 bios: Use BIOS/firmware settings. This is the 5188 the default. 5189 off: Turn ECRC off 5190 on: Turn ECRC on. 5191 hpiosize=nn[KMG] The fixed amount of bus space which is 5192 reserved for hotplug bridge's IO window. 5193 Default size is 256 bytes. 5194 hpmmiosize=nn[KMG] The fixed amount of bus space which is 5195 reserved for hotplug bridge's MMIO window. 5196 Default size is 2 megabytes. 5197 hpmmioprefsize=nn[KMG] The fixed amount of bus space which is 5198 reserved for hotplug bridge's MMIO_PREF window. 5199 Default size is 2 megabytes. 5200 hpmemsize=nn[KMG] The fixed amount of bus space which is 5201 reserved for hotplug bridge's MMIO and 5202 MMIO_PREF window. 5203 Default size is 2 megabytes. 5204 hpbussize=nn The minimum amount of additional bus numbers 5205 reserved for buses below a hotplug bridge. 5206 Default is 1. 5207 realloc= Enable/disable reallocating PCI bridge resources 5208 if allocations done by BIOS are too small to 5209 accommodate resources required by all child 5210 devices. 5211 off: Turn realloc off 5212 on: Turn realloc on 5213 realloc same as realloc=on 5214 noari do not use PCIe ARI. 5215 noats [PCIE, Intel-IOMMU, AMD-IOMMU] 5216 do not use PCIe ATS (and IOMMU device IOTLB). 5217 pcie_scan_all Scan all possible PCIe devices. Otherwise we 5218 only look for one device below a PCIe downstream 5219 port. 5220 big_root_window Try to add a big 64bit memory window to the PCIe 5221 root complex on AMD CPUs. Some GFX hardware 5222 can resize a BAR to allow access to all VRAM. 5223 Adding the window is slightly risky (it may 5224 conflict with unreported devices), so this 5225 taints the kernel. 5226 disable_acs_redir=<pci_dev>[; ...] 5227 Specify one or more PCI devices (in the format 5228 specified above) separated by semicolons. 5229 Each device specified will have the PCI ACS 5230 redirect capabilities forced off which will 5231 allow P2P traffic between devices through 5232 bridges without forcing it upstream. Note: 5233 this removes isolation between devices and 5234 may put more devices in an IOMMU group. 5235 config_acs= 5236 Format: 5237 <ACS flags>@<pci_dev>[; ...] 5238 Specify one or more PCI devices (in the format 5239 specified above) optionally prepended with flags 5240 and separated by semicolons. The respective 5241 capabilities will be enabled, disabled or 5242 unchanged based on what is specified in 5243 flags. 5244 5245 ACS Flags is defined as follows: 5246 bit-0 : ACS Source Validation 5247 bit-1 : ACS Translation Blocking 5248 bit-2 : ACS P2P Request Redirect 5249 bit-3 : ACS P2P Completion Redirect 5250 bit-4 : ACS Upstream Forwarding 5251 bit-5 : ACS P2P Egress Control 5252 bit-6 : ACS Direct Translated P2P 5253 Each bit can be marked as: 5254 '0' – force disabled 5255 '1' – force enabled 5256 'x' – unchanged 5257 For example, 5258 pci=config_acs=10x@pci:0:0 5259 would configure all devices that support 5260 ACS to enable P2P Request Redirect, disable 5261 Translation Blocking, and leave Source 5262 Validation unchanged from whatever power-up 5263 or firmware set it to. 5264 5265 Note: this may remove isolation between devices 5266 and may put more devices in an IOMMU group. 5267 force_floating [S390] Force usage of floating interrupts. 5268 nomio [S390] Do not use MIO instructions. 5269 norid [S390] ignore the RID field and force use of 5270 one PCI domain per PCI function 5271 notph [PCIE] If the PCIE_TPH kernel config parameter 5272 is enabled, this kernel boot option can be used 5273 to disable PCIe TLP Processing Hints support 5274 system-wide. 5275 5276 pcie_aspm= [PCIE] Forcibly enable or ignore PCIe Active State Power 5277 Management. 5278 off Don't touch ASPM configuration at all. Leave any 5279 configuration done by firmware unchanged. 5280 force Enable ASPM even on devices that claim not to support it. 5281 WARNING: Forcing ASPM on may cause system lockups. 5282 5283 pcie_ports= [PCIE] PCIe port services handling: 5284 native Use native PCIe services (PME, AER, DPC, PCIe hotplug) 5285 even if the platform doesn't give the OS permission to 5286 use them. This may cause conflicts if the platform 5287 also tries to use these services. 5288 dpc-native Use native PCIe service for DPC only. May 5289 cause conflicts if firmware uses AER or DPC. 5290 compat Disable native PCIe services (PME, AER, DPC, PCIe 5291 hotplug). 5292 5293 pcie_port_pm= [PCIE] PCIe port power management handling: 5294 off Disable power management of all PCIe ports 5295 force Forcibly enable power management of all PCIe ports 5296 5297 pcie_pme= [PCIE,PM] Native PCIe PME signaling options: 5298 nomsi Do not use MSI for native PCIe PME signaling (this makes 5299 all PCIe root ports use INTx for all services). 5300 5301 pcmv= [HW,PCMCIA] BadgePAD 4 5302 5303 pd_ignore_unused 5304 [PM] 5305 Keep all power-domains already enabled by bootloader on, 5306 even if no driver has claimed them. This is useful 5307 for debug and development, but should not be 5308 needed on a platform with proper driver support. 5309 5310 pdcchassis= [PARISC,HW] Disable/Enable PDC Chassis Status codes at 5311 boot time. 5312 Format: { 0 | 1 } 5313 See arch/parisc/kernel/pdc_chassis.c 5314 5315 percpu_alloc= [MM,EARLY] 5316 Select which percpu first chunk allocator to use. 5317 Currently supported values are "embed" and "page". 5318 Archs may support subset or none of the selections. 5319 See comments in mm/percpu.c for details on each 5320 allocator. This parameter is primarily for debugging 5321 and performance comparison. 5322 5323 pirq= [SMP,APIC] Manual mp-table setup 5324 See Documentation/arch/x86/i386/IO-APIC.rst. 5325 5326 plip= [PPT,NET] Parallel port network link 5327 Format: { parport<nr> | timid | 0 } 5328 See also Documentation/admin-guide/parport.rst. 5329 5330 pmtmr= [X86] Manual setup of pmtmr I/O Port. 5331 Override pmtimer IOPort with a hex value. 5332 e.g. pmtmr=0x508 5333 5334 pmu_override= [PPC] Override the PMU. 5335 This option takes over the PMU facility, so it is no 5336 longer usable by perf. Setting this option starts the 5337 PMU counters by setting MMCR0 to 0 (the FC bit is 5338 cleared). If a number is given, then MMCR1 is set to 5339 that number, otherwise (e.g., 'pmu_override=on'), MMCR1 5340 remains 0. 5341 5342 pm_async= [PM] 5343 Format: off 5344 This parameter sets the initial value of the 5345 /sys/power/pm_async sysfs knob at boot time. 5346 If set to "off", disables asynchronous suspend and 5347 resume of devices during system-wide power transitions. 5348 This can be useful on platforms where device 5349 dependencies are not well-defined, or for debugging 5350 power management issues. Asynchronous operations are 5351 enabled by default. 5352 5353 5354 pm_debug_messages [SUSPEND,KNL] 5355 Enable suspend/resume debug messages during boot up. 5356 5357 pnp.debug=1 [PNP] 5358 Enable PNP debug messages (depends on the 5359 CONFIG_PNP_DEBUG_MESSAGES option). Change at run-time 5360 via /sys/module/pnp/parameters/debug. We always show 5361 current resource usage; turning this on also shows 5362 possible settings and some assignment information. 5363 5364 pnpacpi= [ACPI] 5365 { off } 5366 5367 pnpbios= [ISAPNP] 5368 { on | off | curr | res | no-curr | no-res } 5369 5370 pnp_reserve_irq= 5371 [ISAPNP] Exclude IRQs for the autoconfiguration 5372 5373 pnp_reserve_dma= 5374 [ISAPNP] Exclude DMAs for the autoconfiguration 5375 5376 pnp_reserve_io= [ISAPNP] Exclude I/O ports for the autoconfiguration 5377 Ranges are in pairs (I/O port base and size). 5378 5379 pnp_reserve_mem= 5380 [ISAPNP] Exclude memory regions for the 5381 autoconfiguration. 5382 Ranges are in pairs (memory base and size). 5383 5384 ports= [IP_VS_FTP] IPVS ftp helper module 5385 Default is 21. 5386 Up to 8 (IP_VS_APP_MAX_PORTS) ports 5387 may be specified. 5388 Format: <port>,<port>.... 5389 5390 possible_cpus= [SMP,S390,X86] 5391 Format: <unsigned int> 5392 Set the number of possible CPUs, overriding the 5393 regular discovery mechanisms (such as ACPI/FW, etc). 5394 5395 powersave=off [PPC] This option disables power saving features. 5396 It specifically disables cpuidle and sets the 5397 platform machine description specific power_save 5398 function to NULL. On Idle the CPU just reduces 5399 execution priority. 5400 5401 ppc_strict_facility_enable 5402 [PPC,ENABLE] This option catches any kernel floating point, 5403 Altivec, VSX and SPE outside of regions specifically 5404 allowed (eg kernel_enable_fpu()/kernel_disable_fpu()). 5405 There is some performance impact when enabling this. 5406 5407 ppc_tm= [PPC,EARLY] 5408 Format: {"off"} 5409 Disable Hardware Transactional Memory 5410 5411 preempt= [KNL] 5412 Select preemption mode if you have CONFIG_PREEMPT_DYNAMIC 5413 none - Limited to cond_resched() calls 5414 voluntary - Limited to cond_resched() and might_sleep() calls 5415 full - Any section that isn't explicitly preempt disabled 5416 can be preempted anytime. Tasks will also yield 5417 contended spinlocks (if the critical section isn't 5418 explicitly preempt disabled beyond the lock itself). 5419 lazy - Scheduler controlled. Similar to full but instead 5420 of preempting the task immediately, the task gets 5421 one HZ tick time to yield itself before the 5422 preemption will be forced. One preemption is when the 5423 task returns to user space. 5424 5425 print-fatal-signals= 5426 [KNL] debug: print fatal signals 5427 5428 If enabled, warn about various signal handling 5429 related application anomalies: too many signals, 5430 too many POSIX.1 timers, fatal signals causing a 5431 coredump - etc. 5432 5433 If you hit the warning due to signal overflow, 5434 you might want to try "ulimit -i unlimited". 5435 5436 default: off. 5437 5438 printk.always_kmsg_dump= 5439 Trigger kmsg_dump for cases other than kernel oops or 5440 panics 5441 Format: <bool> (1/Y/y=enable, 0/N/n=disable) 5442 default: disabled 5443 5444 printk.console_no_auto_verbose= 5445 Disable console loglevel raise on oops, panic 5446 or lockdep-detected issues (only if lock debug is on). 5447 With an exception to setups with low baudrate on 5448 serial console, keeping this 0 is a good choice 5449 in order to provide more debug information. 5450 Format: <bool> 5451 default: 0 (auto_verbose is enabled) 5452 5453 printk.debug_non_panic_cpus= 5454 Allows storing messages from non-panic CPUs into 5455 the printk log buffer during panic(). They are 5456 flushed to consoles by the panic-CPU on 5457 a best-effort basis. 5458 Format: <bool> (1/Y/y=enable, 0/N/n=disable) 5459 Default: disabled 5460 5461 printk.devkmsg={on,off,ratelimit} 5462 Control writing to /dev/kmsg. 5463 on - unlimited logging to /dev/kmsg from userspace 5464 off - logging to /dev/kmsg disabled 5465 ratelimit - ratelimit the logging 5466 Default: ratelimit 5467 5468 printk.time= Show timing data prefixed to each printk message line 5469 Format: <bool> (1/Y/y=enable, 0/N/n=disable) 5470 5471 proc_mem.force_override= [KNL] 5472 Format: {always | ptrace | never} 5473 Traditionally /proc/pid/mem allows memory permissions to be 5474 overridden without restrictions. This option may be set to 5475 restrict that. Can be one of: 5476 - 'always': traditional behavior always allows mem overrides. 5477 - 'ptrace': only allow mem overrides for active ptracers. 5478 - 'never': never allow mem overrides. 5479 If not specified, default is the CONFIG_PROC_MEM_* choice. 5480 5481 processor.max_cstate= [HW,ACPI] 5482 Limit processor to maximum C-state 5483 max_cstate=9 overrides any DMI blacklist limit. 5484 5485 processor.nocst [HW,ACPI] 5486 Ignore the _CST method to determine C-states, 5487 instead using the legacy FADT method 5488 5489 profile= [KNL] Enable kernel profiling via /proc/profile 5490 Format: [<profiletype>,]<number> 5491 Param: <profiletype>: "schedule" or "kvm" 5492 [defaults to kernel profiling] 5493 Param: "schedule" - profile schedule points. 5494 Param: "kvm" - profile VM exits. 5495 Param: <number> - step/bucket size as a power of 2 for 5496 statistical time based profiling. 5497 5498 prot_virt= [S390] enable hosting protected virtual machines 5499 isolated from the hypervisor (if hardware supports 5500 that). If enabled, the default kernel base address 5501 might be overridden even when Kernel Address Space 5502 Layout Randomization is disabled. 5503 Format: <bool> 5504 5505 psi= [KNL] Enable or disable pressure stall information 5506 tracking. 5507 Format: <bool> 5508 5509 psmouse.proto= [HW,MOUSE] Highest PS2 mouse protocol extension to 5510 probe for; one of (bare|imps|exps|lifebook|any). 5511 psmouse.rate= [HW,MOUSE] Set desired mouse report rate, in reports 5512 per second. 5513 psmouse.resetafter= [HW,MOUSE] 5514 Try to reset the device after so many bad packets 5515 (0 = never). 5516 psmouse.resolution= 5517 [HW,MOUSE] Set desired mouse resolution, in dpi. 5518 psmouse.smartscroll= 5519 [HW,MOUSE] Controls Logitech smartscroll autorepeat. 5520 0 = disabled, 1 = enabled (default). 5521 5522 pstore.backend= Specify the name of the pstore backend to use 5523 5524 pti= [X86-64] Control Page Table Isolation of user and 5525 kernel address spaces. Disabling this feature 5526 removes hardening, but improves performance of 5527 system calls and interrupts. 5528 5529 on - unconditionally enable 5530 off - unconditionally disable 5531 auto - kernel detects whether your CPU model is 5532 vulnerable to issues that PTI mitigates 5533 5534 Not specifying this option is equivalent to pti=auto. 5535 5536 pty.legacy_count= 5537 [KNL] Number of legacy pty's. Overwrites compiled-in 5538 default number. 5539 5540 quiet [KNL,EARLY] Disable most log messages 5541 5542 r128= [HW,DRM] 5543 5544 radix_hcall_invalidate=on [PPC/PSERIES] 5545 Disable RADIX GTSE feature and use hcall for TLB 5546 invalidate. 5547 5548 raid= [HW,RAID] 5549 See Documentation/admin-guide/md.rst. 5550 5551 ramdisk_size= [RAM] Sizes of RAM disks in kilobytes 5552 See Documentation/admin-guide/blockdev/ramdisk.rst. 5553 5554 ramdisk_start= [Deprecated,RAM] RAM disk image start address 5555 5556 random.trust_cpu=off 5557 [KNL,EARLY] Disable trusting the use of the CPU's 5558 random number generator (if available) to 5559 initialize the kernel's RNG. 5560 5561 random.trust_bootloader=off 5562 [KNL,EARLY] Disable trusting the use of the a seed 5563 passed by the bootloader (if available) to 5564 initialize the kernel's RNG. 5565 5566 randomize_kstack_offset= 5567 [KNL,EARLY] Enable or disable kernel stack offset 5568 randomization, which provides roughly 5 bits of 5569 entropy, frustrating memory corruption attacks 5570 that depend on stack address determinism or 5571 cross-syscall address exposures. This is only 5572 available on architectures that have defined 5573 CONFIG_HAVE_ARCH_RANDOMIZE_KSTACK_OFFSET. 5574 Format: <bool> (1/Y/y=enable, 0/N/n=disable) 5575 Default is CONFIG_RANDOMIZE_KSTACK_OFFSET_DEFAULT. 5576 5577 ras=option[,option,...] [KNL] RAS-specific options 5578 5579 cec_disable [X86] 5580 Disable the Correctable Errors Collector, 5581 see CONFIG_RAS_CEC help text. 5582 5583 rcu_nocbs[=cpu-list] 5584 [KNL] The optional argument is a cpu list, 5585 as described above. 5586 5587 In kernels built with CONFIG_RCU_NOCB_CPU=y, 5588 enable the no-callback CPU mode, which prevents 5589 such CPUs' callbacks from being invoked in 5590 softirq context. Invocation of such CPUs' RCU 5591 callbacks will instead be offloaded to "rcuox/N" 5592 kthreads created for that purpose, where "x" is 5593 "p" for RCU-preempt, "s" for RCU-sched, and "g" 5594 for the kthreads that mediate grace periods; and 5595 "N" is the CPU number. This reduces OS jitter on 5596 the offloaded CPUs, which can be useful for HPC 5597 and real-time workloads. It can also improve 5598 energy efficiency for asymmetric multiprocessors. 5599 5600 If a cpulist is passed as an argument, the specified 5601 list of CPUs is set to no-callback mode from boot. 5602 5603 Otherwise, if the '=' sign and the cpulist 5604 arguments are omitted, no CPU will be set to 5605 no-callback mode from boot but the mode may be 5606 toggled at runtime via cpusets. 5607 5608 Note that this argument takes precedence over 5609 the CONFIG_RCU_NOCB_CPU_DEFAULT_ALL option. 5610 5611 rcu_nocb_poll [KNL] 5612 Rather than requiring that offloaded CPUs 5613 (specified by rcu_nocbs= above) explicitly 5614 awaken the corresponding "rcuoN" kthreads, 5615 make these kthreads poll for callbacks. 5616 This improves the real-time response for the 5617 offloaded CPUs by relieving them of the need to 5618 wake up the corresponding kthread, but degrades 5619 energy efficiency by requiring that the kthreads 5620 periodically wake up to do the polling. 5621 5622 rcutree.blimit= [KNL] 5623 Set maximum number of finished RCU callbacks to 5624 process in one batch. 5625 5626 rcutree.csd_lock_suppress_rcu_stall= [KNL] 5627 Do only a one-line RCU CPU stall warning when 5628 there is an ongoing too-long CSD-lock wait. 5629 5630 rcutree.do_rcu_barrier= [KNL] 5631 Request a call to rcu_barrier(). This is 5632 throttled so that userspace tests can safely 5633 hammer on the sysfs variable if they so choose. 5634 If triggered before the RCU grace-period machinery 5635 is fully active, this will error out with EAGAIN. 5636 5637 rcutree.dump_tree= [KNL] 5638 Dump the structure of the rcu_node combining tree 5639 out at early boot. This is used for diagnostic 5640 purposes, to verify correct tree setup. 5641 5642 rcutree.gp_cleanup_delay= [KNL] 5643 Set the number of jiffies to delay each step of 5644 RCU grace-period cleanup. 5645 5646 rcutree.gp_init_delay= [KNL] 5647 Set the number of jiffies to delay each step of 5648 RCU grace-period initialization. 5649 5650 rcutree.gp_preinit_delay= [KNL] 5651 Set the number of jiffies to delay each step of 5652 RCU grace-period pre-initialization, that is, 5653 the propagation of recent CPU-hotplug changes up 5654 the rcu_node combining tree. 5655 5656 rcutree.jiffies_till_first_fqs= [KNL] 5657 Set delay from grace-period initialization to 5658 first attempt to force quiescent states. 5659 Units are jiffies, minimum value is zero, 5660 and maximum value is HZ. 5661 5662 rcutree.jiffies_till_next_fqs= [KNL] 5663 Set delay between subsequent attempts to force 5664 quiescent states. Units are jiffies, minimum 5665 value is one, and maximum value is HZ. 5666 5667 rcutree.jiffies_till_sched_qs= [KNL] 5668 Set required age in jiffies for a 5669 given grace period before RCU starts 5670 soliciting quiescent-state help from 5671 rcu_note_context_switch() and cond_resched(). 5672 If not specified, the kernel will calculate 5673 a value based on the most recent settings 5674 of rcutree.jiffies_till_first_fqs 5675 and rcutree.jiffies_till_next_fqs. 5676 This calculated value may be viewed in 5677 rcutree.jiffies_to_sched_qs. Any attempt to set 5678 rcutree.jiffies_to_sched_qs will be cheerfully 5679 overwritten. 5680 5681 rcutree.kthread_prio= [KNL,BOOT] 5682 Set the SCHED_FIFO priority of the RCU per-CPU 5683 kthreads (rcuc/N). This value is also used for 5684 the priority of the RCU boost threads (rcub/N) 5685 and for the RCU grace-period kthreads (rcu_bh, 5686 rcu_preempt, and rcu_sched). If RCU_BOOST is 5687 set, valid values are 1-99 and the default is 1 5688 (the least-favored priority). Otherwise, when 5689 RCU_BOOST is not set, valid values are 0-99 and 5690 the default is zero (non-realtime operation). 5691 When RCU_NOCB_CPU is set, also adjust the 5692 priority of NOCB callback kthreads. 5693 5694 rcutree.nocb_nobypass_lim_per_jiffy= [KNL] 5695 On callback-offloaded (rcu_nocbs) CPUs, 5696 RCU reduces the lock contention that would 5697 otherwise be caused by callback floods through 5698 use of the ->nocb_bypass list. However, in the 5699 common non-flooded case, RCU queues directly to 5700 the main ->cblist in order to avoid the extra 5701 overhead of the ->nocb_bypass list and its lock. 5702 But if there are too many callbacks queued during 5703 a single jiffy, RCU pre-queues the callbacks into 5704 the ->nocb_bypass queue. The definition of "too 5705 many" is supplied by this kernel boot parameter. 5706 5707 rcutree.nohz_full_patience_delay= [KNL] 5708 On callback-offloaded (rcu_nocbs) CPUs, avoid 5709 disturbing RCU unless the grace period has 5710 reached the specified age in milliseconds. 5711 Defaults to zero. Large values will be capped 5712 at five seconds. All values will be rounded down 5713 to the nearest value representable by jiffies. 5714 5715 rcutree.qhimark= [KNL] 5716 Set threshold of queued RCU callbacks beyond which 5717 batch limiting is disabled. 5718 5719 rcutree.qlowmark= [KNL] 5720 Set threshold of queued RCU callbacks below which 5721 batch limiting is re-enabled. 5722 5723 rcutree.qovld= [KNL] 5724 Set threshold of queued RCU callbacks beyond which 5725 RCU's force-quiescent-state scan will aggressively 5726 enlist help from cond_resched() and sched IPIs to 5727 help CPUs more quickly reach quiescent states. 5728 Set to less than zero to make this be set based 5729 on rcutree.qhimark at boot time and to zero to 5730 disable more aggressive help enlistment. 5731 5732 rcutree.rcu_delay_page_cache_fill_msec= [KNL] 5733 Set the page-cache refill delay (in milliseconds) 5734 in response to low-memory conditions. The range 5735 of permitted values is in the range 0:100000. 5736 5737 rcutree.rcu_divisor= [KNL] 5738 Set the shift-right count to use to compute 5739 the callback-invocation batch limit bl from 5740 the number of callbacks queued on this CPU. 5741 The result will be bounded below by the value of 5742 the rcutree.blimit kernel parameter. Every bl 5743 callbacks, the softirq handler will exit in 5744 order to allow the CPU to do other work. 5745 5746 Please note that this callback-invocation batch 5747 limit applies only to non-offloaded callback 5748 invocation. Offloaded callbacks are instead 5749 invoked in the context of an rcuoc kthread, which 5750 scheduler will preempt as it does any other task. 5751 5752 rcutree.rcu_fanout_exact= [KNL] 5753 Disable autobalancing of the rcu_node combining 5754 tree. This is used by rcutorture, and might 5755 possibly be useful for architectures having high 5756 cache-to-cache transfer latencies. 5757 5758 rcutree.rcu_fanout_leaf= [KNL] 5759 Change the number of CPUs assigned to each 5760 leaf rcu_node structure. Useful for very 5761 large systems, which will choose the value 64, 5762 and for NUMA systems with large remote-access 5763 latencies, which will choose a value aligned 5764 with the appropriate hardware boundaries. 5765 5766 rcutree.rcu_min_cached_objs= [KNL] 5767 Minimum number of objects which are cached and 5768 maintained per one CPU. Object size is equal 5769 to PAGE_SIZE. The cache allows to reduce the 5770 pressure to page allocator, also it makes the 5771 whole algorithm to behave better in low memory 5772 condition. 5773 5774 rcutree.rcu_nocb_gp_stride= [KNL] 5775 Set the number of NOCB callback kthreads in 5776 each group, which defaults to the square root 5777 of the number of CPUs. Larger numbers reduce 5778 the wakeup overhead on the global grace-period 5779 kthread, but increases that same overhead on 5780 each group's NOCB grace-period kthread. 5781 5782 rcutree.rcu_kick_kthreads= [KNL] 5783 Cause the grace-period kthread to get an extra 5784 wake_up() if it sleeps three times longer than 5785 it should at force-quiescent-state time. 5786 This wake_up() will be accompanied by a 5787 WARN_ONCE() splat and an ftrace_dump(). 5788 5789 rcutree.rcu_resched_ns= [KNL] 5790 Limit the time spend invoking a batch of RCU 5791 callbacks to the specified number of nanoseconds. 5792 By default, this limit is checked only once 5793 every 32 callbacks in order to limit the pain 5794 inflicted by local_clock() overhead. 5795 5796 rcutree.rcu_unlock_delay= [KNL] 5797 In CONFIG_RCU_STRICT_GRACE_PERIOD=y kernels, 5798 this specifies an rcu_read_unlock()-time delay 5799 in microseconds. This defaults to zero. 5800 Larger delays increase the probability of 5801 catching RCU pointer leaks, that is, buggy use 5802 of RCU-protected pointers after the relevant 5803 rcu_read_unlock() has completed. 5804 5805 rcutree.sysrq_rcu= [KNL] 5806 Commandeer a sysrq key to dump out Tree RCU's 5807 rcu_node tree with an eye towards determining 5808 why a new grace period has not yet started. 5809 5810 rcutree.use_softirq= [KNL] 5811 If set to zero, move all RCU_SOFTIRQ processing to 5812 per-CPU rcuc kthreads. Defaults to a non-zero 5813 value, meaning that RCU_SOFTIRQ is used by default. 5814 Specify rcutree.use_softirq=0 to use rcuc kthreads. 5815 5816 But note that CONFIG_PREEMPT_RT=y kernels disable 5817 this kernel boot parameter, forcibly setting it 5818 to zero. 5819 5820 rcutree.enable_rcu_lazy= [KNL] 5821 To save power, batch RCU callbacks and flush after 5822 delay, memory pressure or callback list growing too 5823 big. 5824 5825 rcutree.rcu_normal_wake_from_gp= [KNL] 5826 Reduces a latency of synchronize_rcu() call. This approach 5827 maintains its own track of synchronize_rcu() callers, so it 5828 does not interact with regular callbacks because it does not 5829 use a call_rcu[_hurry]() path. Please note, this is for a 5830 normal grace period. 5831 5832 How to disable it: 5833 5834 echo 0 > /sys/module/rcutree/parameters/rcu_normal_wake_from_gp 5835 or pass a boot parameter "rcutree.rcu_normal_wake_from_gp=0" 5836 5837 Default is 1 if it is not explicitly disabled by the boot parameter 5838 passing 0. 5839 5840 rcuscale.gp_async= [KNL] 5841 Measure performance of asynchronous 5842 grace-period primitives such as call_rcu(). 5843 5844 rcuscale.gp_async_max= [KNL] 5845 Specify the maximum number of outstanding 5846 callbacks per writer thread. When a writer 5847 thread exceeds this limit, it invokes the 5848 corresponding flavor of rcu_barrier() to allow 5849 previously posted callbacks to drain. 5850 5851 rcuscale.gp_exp= [KNL] 5852 Measure performance of expedited synchronous 5853 grace-period primitives. 5854 5855 rcuscale.holdoff= [KNL] 5856 Set test-start holdoff period. The purpose of 5857 this parameter is to delay the start of the 5858 test until boot completes in order to avoid 5859 interference. 5860 5861 rcuscale.kfree_by_call_rcu= [KNL] 5862 In kernels built with CONFIG_RCU_LAZY=y, test 5863 call_rcu() instead of kfree_rcu(). 5864 5865 rcuscale.kfree_mult= [KNL] 5866 Instead of allocating an object of size kfree_obj, 5867 allocate one of kfree_mult * sizeof(kfree_obj). 5868 Defaults to 1. 5869 5870 rcuscale.kfree_rcu_test= [KNL] 5871 Set to measure performance of kfree_rcu() flooding. 5872 5873 rcuscale.kfree_rcu_test_double= [KNL] 5874 Test the double-argument variant of kfree_rcu(). 5875 If this parameter has the same value as 5876 rcuscale.kfree_rcu_test_single, both the single- 5877 and double-argument variants are tested. 5878 5879 rcuscale.kfree_rcu_test_single= [KNL] 5880 Test the single-argument variant of kfree_rcu(). 5881 If this parameter has the same value as 5882 rcuscale.kfree_rcu_test_double, both the single- 5883 and double-argument variants are tested. 5884 5885 rcuscale.kfree_nthreads= [KNL] 5886 The number of threads running loops of kfree_rcu(). 5887 5888 rcuscale.kfree_alloc_num= [KNL] 5889 Number of allocations and frees done in an iteration. 5890 5891 rcuscale.kfree_loops= [KNL] 5892 Number of loops doing rcuscale.kfree_alloc_num number 5893 of allocations and frees. 5894 5895 rcuscale.minruntime= [KNL] 5896 Set the minimum test run time in seconds. This 5897 does not affect the data-collection interval, 5898 but instead allows better measurement of things 5899 like CPU consumption. 5900 5901 rcuscale.nreaders= [KNL] 5902 Set number of RCU readers. The value -1 selects 5903 N, where N is the number of CPUs. A value 5904 "n" less than -1 selects N-n+1, where N is again 5905 the number of CPUs. For example, -2 selects N 5906 (the number of CPUs), -3 selects N+1, and so on. 5907 A value of "n" less than or equal to -N selects 5908 a single reader. 5909 5910 rcuscale.nwriters= [KNL] 5911 Set number of RCU writers. The values operate 5912 the same as for rcuscale.nreaders. 5913 N, where N is the number of CPUs 5914 5915 rcuscale.scale_type= [KNL] 5916 Specify the RCU implementation to test. 5917 5918 rcuscale.shutdown= [KNL] 5919 Shut the system down after performance tests 5920 complete. This is useful for hands-off automated 5921 testing. 5922 5923 rcuscale.verbose= [KNL] 5924 Enable additional printk() statements. 5925 5926 rcuscale.writer_holdoff= [KNL] 5927 Write-side holdoff between grace periods, 5928 in microseconds. The default of zero says 5929 no holdoff. 5930 5931 rcuscale.writer_holdoff_jiffies= [KNL] 5932 Additional write-side holdoff between grace 5933 periods, but in jiffies. The default of zero 5934 says no holdoff. 5935 5936 rcutorture.fqs_duration= [KNL] 5937 Set duration of force_quiescent_state bursts 5938 in microseconds. 5939 5940 rcutorture.fqs_holdoff= [KNL] 5941 Set holdoff time within force_quiescent_state bursts 5942 in microseconds. 5943 5944 rcutorture.fqs_stutter= [KNL] 5945 Set wait time between force_quiescent_state bursts 5946 in seconds. 5947 5948 rcutorture.fwd_progress= [KNL] 5949 Specifies the number of kthreads to be used 5950 for RCU grace-period forward-progress testing 5951 for the types of RCU supporting this notion. 5952 Defaults to 1 kthread, values less than zero or 5953 greater than the number of CPUs cause the number 5954 of CPUs to be used. 5955 5956 rcutorture.fwd_progress_div= [KNL] 5957 Specify the fraction of a CPU-stall-warning 5958 period to do tight-loop forward-progress testing. 5959 5960 rcutorture.fwd_progress_holdoff= [KNL] 5961 Number of seconds to wait between successive 5962 forward-progress tests. 5963 5964 rcutorture.fwd_progress_need_resched= [KNL] 5965 Enclose cond_resched() calls within checks for 5966 need_resched() during tight-loop forward-progress 5967 testing. 5968 5969 rcutorture.gp_cond= [KNL] 5970 Use conditional/asynchronous update-side 5971 normal-grace-period primitives, if available. 5972 5973 rcutorture.gp_cond_exp= [KNL] 5974 Use conditional/asynchronous update-side 5975 expedited-grace-period primitives, if available. 5976 5977 rcutorture.gp_cond_full= [KNL] 5978 Use conditional/asynchronous update-side 5979 normal-grace-period primitives that also take 5980 concurrent expedited grace periods into account, 5981 if available. 5982 5983 rcutorture.gp_cond_exp_full= [KNL] 5984 Use conditional/asynchronous update-side 5985 expedited-grace-period primitives that also take 5986 concurrent normal grace periods into account, 5987 if available. 5988 5989 rcutorture.gp_cond_wi= [KNL] 5990 Nominal wait interval for normal conditional 5991 grace periods (specified by rcutorture's 5992 gp_cond and gp_cond_full module parameters), 5993 in microseconds. The actual wait interval will 5994 be randomly selected to nanosecond granularity up 5995 to this wait interval. Defaults to 16 jiffies, 5996 for example, 16,000 microseconds on a system 5997 with HZ=1000. 5998 5999 rcutorture.gp_cond_wi_exp= [KNL] 6000 Nominal wait interval for expedited conditional 6001 grace periods (specified by rcutorture's 6002 gp_cond_exp and gp_cond_exp_full module 6003 parameters), in microseconds. The actual wait 6004 interval will be randomly selected to nanosecond 6005 granularity up to this wait interval. Defaults to 6006 128 microseconds. 6007 6008 rcutorture.gp_exp= [KNL] 6009 Use expedited update-side primitives, if available. 6010 6011 rcutorture.gp_normal= [KNL] 6012 Use normal (non-expedited) asynchronous 6013 update-side primitives, if available. 6014 6015 rcutorture.gp_poll= [KNL] 6016 Use polled update-side normal-grace-period 6017 primitives, if available. 6018 6019 rcutorture.gp_poll_exp= [KNL] 6020 Use polled update-side expedited-grace-period 6021 primitives, if available. 6022 6023 rcutorture.gp_poll_full= [KNL] 6024 Use polled update-side normal-grace-period 6025 primitives that also take concurrent expedited 6026 grace periods into account, if available. 6027 6028 rcutorture.gp_poll_exp_full= [KNL] 6029 Use polled update-side expedited-grace-period 6030 primitives that also take concurrent normal 6031 grace periods into account, if available. 6032 6033 rcutorture.gp_poll_wi= [KNL] 6034 Nominal wait interval for normal conditional 6035 grace periods (specified by rcutorture's 6036 gp_poll and gp_poll_full module parameters), 6037 in microseconds. The actual wait interval will 6038 be randomly selected to nanosecond granularity up 6039 to this wait interval. Defaults to 16 jiffies, 6040 for example, 16,000 microseconds on a system 6041 with HZ=1000. 6042 6043 rcutorture.gp_poll_wi_exp= [KNL] 6044 Nominal wait interval for expedited conditional 6045 grace periods (specified by rcutorture's 6046 gp_poll_exp and gp_poll_exp_full module 6047 parameters), in microseconds. The actual wait 6048 interval will be randomly selected to nanosecond 6049 granularity up to this wait interval. Defaults to 6050 128 microseconds. 6051 6052 rcutorture.gp_sync= [KNL] 6053 Use normal (non-expedited) synchronous 6054 update-side primitives, if available. If all 6055 of rcutorture.gp_cond=, rcutorture.gp_exp=, 6056 rcutorture.gp_normal=, and rcutorture.gp_sync= 6057 are zero, rcutorture acts as if is interpreted 6058 they are all non-zero. 6059 6060 rcutorture.gpwrap_lag= [KNL] 6061 Enable grace-period wrap lag testing. Setting 6062 to false prevents the gpwrap lag test from 6063 running. Default is true. 6064 6065 rcutorture.gpwrap_lag_gps= [KNL] 6066 Set the value for grace-period wrap lag during 6067 active lag testing periods. This controls how many 6068 grace periods differences we tolerate between 6069 rdp and rnp's gp_seq before setting overflow flag. 6070 The default is always set to 8. 6071 6072 rcutorture.gpwrap_lag_cycle_mins= [KNL] 6073 Set the total cycle duration for gpwrap lag 6074 testing in minutes. This is the total time for 6075 one complete cycle of active and inactive 6076 testing periods. Default is 30 minutes. 6077 6078 rcutorture.gpwrap_lag_active_mins= [KNL] 6079 Set the duration for which gpwrap lag is active 6080 within each cycle, in minutes. During this time, 6081 the grace-period wrap lag will be set to the 6082 value specified by gpwrap_lag_gps. Default is 6083 5 minutes. 6084 6085 rcutorture.irqreader= [KNL] 6086 Run RCU readers from irq handlers, or, more 6087 accurately, from a timer handler. Not all RCU 6088 flavors take kindly to this sort of thing. 6089 6090 rcutorture.leakpointer= [KNL] 6091 Leak an RCU-protected pointer out of the reader. 6092 This can of course result in splats, and is 6093 intended to test the ability of things like 6094 CONFIG_RCU_STRICT_GRACE_PERIOD=y to detect 6095 such leaks. 6096 6097 rcutorture.n_barrier_cbs= [KNL] 6098 Set callbacks/threads for rcu_barrier() testing. 6099 6100 rcutorture.nfakewriters= [KNL] 6101 Set number of concurrent RCU writers. These just 6102 stress RCU, they don't participate in the actual 6103 test, hence the "fake". 6104 6105 rcutorture.nocbs_nthreads= [KNL] 6106 Set number of RCU callback-offload togglers. 6107 Zero (the default) disables toggling. 6108 6109 rcutorture.nocbs_toggle= [KNL] 6110 Set the delay in milliseconds between successive 6111 callback-offload toggling attempts. 6112 6113 rcutorture.nreaders= [KNL] 6114 Set number of RCU readers. The value -1 selects 6115 N-1, where N is the number of CPUs. A value 6116 "n" less than -1 selects N-n-2, where N is again 6117 the number of CPUs. For example, -2 selects N 6118 (the number of CPUs), -3 selects N+1, and so on. 6119 6120 rcutorture.object_debug= [KNL] 6121 Enable debug-object double-call_rcu() testing. 6122 6123 rcutorture.onoff_holdoff= [KNL] 6124 Set time (s) after boot for CPU-hotplug testing. 6125 6126 rcutorture.onoff_interval= [KNL] 6127 Set time (jiffies) between CPU-hotplug operations, 6128 or zero to disable CPU-hotplug testing. 6129 6130 rcutorture.preempt_duration= [KNL] 6131 Set duration (in milliseconds) of preemptions 6132 by a high-priority FIFO real-time task. Set to 6133 zero (the default) to disable. The CPUs to 6134 preempt are selected randomly from the set that 6135 are online at a given point in time. Races with 6136 CPUs going offline are ignored, with that attempt 6137 at preemption skipped. 6138 6139 rcutorture.preempt_interval= [KNL] 6140 Set interval (in milliseconds, defaulting to one 6141 second) between preemptions by a high-priority 6142 FIFO real-time task. This delay is mediated 6143 by an hrtimer and is further fuzzed to avoid 6144 inadvertent synchronizations. 6145 6146 rcutorture.read_exit_burst= [KNL] 6147 The number of times in a given read-then-exit 6148 episode that a set of read-then-exit kthreads 6149 is spawned. 6150 6151 rcutorture.read_exit_delay= [KNL] 6152 The delay, in seconds, between successive 6153 read-then-exit testing episodes. 6154 6155 rcutorture.reader_flavor= [KNL] 6156 A bit mask indicating which readers to use. 6157 If there is more than one bit set, the readers 6158 are entered from low-order bit up, and are 6159 exited in the opposite order. For SRCU, the 6160 0x1 bit is normal readers, 0x2 NMI-safe readers, 6161 and 0x4 light-weight readers. 6162 6163 rcutorture.shuffle_interval= [KNL] 6164 Set task-shuffle interval (s). Shuffling tasks 6165 allows some CPUs to go into dyntick-idle mode 6166 during the rcutorture test. 6167 6168 rcutorture.shutdown_secs= [KNL] 6169 Set time (s) after boot system shutdown. This 6170 is useful for hands-off automated testing. 6171 6172 rcutorture.stall_cpu= [KNL] 6173 Duration of CPU stall (s) to test RCU CPU stall 6174 warnings, zero to disable. 6175 6176 rcutorture.stall_cpu_block= [KNL] 6177 Sleep while stalling if set. This will result 6178 in warnings from preemptible RCU in addition to 6179 any other stall-related activity. Note that 6180 in kernels built with CONFIG_PREEMPTION=n and 6181 CONFIG_PREEMPT_COUNT=y, this parameter will 6182 cause the CPU to pass through a quiescent state. 6183 Given CONFIG_PREEMPTION=n, this will suppress 6184 RCU CPU stall warnings, but will instead result 6185 in scheduling-while-atomic splats. 6186 6187 Use of this module parameter results in splats. 6188 6189 6190 rcutorture.stall_cpu_holdoff= [KNL] 6191 Time to wait (s) after boot before inducing stall. 6192 6193 rcutorture.stall_cpu_irqsoff= [KNL] 6194 Disable interrupts while stalling if set, but only 6195 on the first stall in the set. 6196 6197 rcutorture.stall_cpu_repeat= [KNL] 6198 Number of times to repeat the stall sequence, 6199 so that rcutorture.stall_cpu_repeat=3 will result 6200 in four stall sequences. 6201 6202 rcutorture.stall_gp_kthread= [KNL] 6203 Duration (s) of forced sleep within RCU 6204 grace-period kthread to test RCU CPU stall 6205 warnings, zero to disable. If both stall_cpu 6206 and stall_gp_kthread are specified, the 6207 kthread is starved first, then the CPU. 6208 6209 rcutorture.stat_interval= [KNL] 6210 Time (s) between statistics printk()s. 6211 6212 rcutorture.stutter= [KNL] 6213 Time (s) to stutter testing, for example, specifying 6214 five seconds causes the test to run for five seconds, 6215 wait for five seconds, and so on. This tests RCU's 6216 ability to transition abruptly to and from idle. 6217 6218 rcutorture.test_boost= [KNL] 6219 Test RCU priority boosting? 0=no, 1=maybe, 2=yes. 6220 "Maybe" means test if the RCU implementation 6221 under test support RCU priority boosting. 6222 6223 rcutorture.test_boost_duration= [KNL] 6224 Duration (s) of each individual boost test. 6225 6226 rcutorture.test_boost_holdoff= [KNL] 6227 Holdoff time (s) from start of test to the start 6228 of RCU priority-boost testing. Defaults to zero, 6229 that is, no holdoff. 6230 6231 rcutorture.test_boost_interval= [KNL] 6232 Interval (s) between each boost test. 6233 6234 rcutorture.test_no_idle_hz= [KNL] 6235 Test RCU's dyntick-idle handling. See also the 6236 rcutorture.shuffle_interval parameter. 6237 6238 rcutorture.torture_type= [KNL] 6239 Specify the RCU implementation to test. 6240 6241 rcutorture.verbose= [KNL] 6242 Enable additional printk() statements. 6243 6244 rcupdate.rcu_cpu_stall_ftrace_dump= [KNL] 6245 Dump ftrace buffer after reporting RCU CPU 6246 stall warning. 6247 6248 rcupdate.rcu_cpu_stall_notifiers= [KNL] 6249 Provide RCU CPU stall notifiers, but see the 6250 warnings in the RCU_CPU_STALL_NOTIFIER Kconfig 6251 option's help text. TL;DR: You almost certainly 6252 do not want rcupdate.rcu_cpu_stall_notifiers. 6253 6254 rcupdate.rcu_cpu_stall_suppress= [KNL] 6255 Suppress RCU CPU stall warning messages. 6256 6257 rcupdate.rcu_cpu_stall_suppress_at_boot= [KNL] 6258 Suppress RCU CPU stall warning messages and 6259 rcutorture writer stall warnings that occur 6260 during early boot, that is, during the time 6261 before the init task is spawned. 6262 6263 rcupdate.rcu_cpu_stall_timeout= [KNL] 6264 Set timeout for RCU CPU stall warning messages. 6265 The value is in seconds and the maximum allowed 6266 value is 300 seconds. 6267 6268 rcupdate.rcu_exp_cpu_stall_timeout= [KNL] 6269 Set timeout for expedited RCU CPU stall warning 6270 messages. The value is in milliseconds 6271 and the maximum allowed value is 21000 6272 milliseconds. Please note that this value is 6273 adjusted to an arch timer tick resolution. 6274 Setting this to zero causes the value from 6275 rcupdate.rcu_cpu_stall_timeout to be used (after 6276 conversion from seconds to milliseconds). 6277 6278 rcupdate.rcu_cpu_stall_cputime= [KNL] 6279 Provide statistics on the cputime and count of 6280 interrupts and tasks during the sampling period. For 6281 multiple continuous RCU stalls, all sampling periods 6282 begin at half of the first RCU stall timeout. 6283 6284 rcupdate.rcu_exp_stall_task_details= [KNL] 6285 Print stack dumps of any tasks blocking the 6286 current expedited RCU grace period during an 6287 expedited RCU CPU stall warning. 6288 6289 rcupdate.rcu_expedited= [KNL] 6290 Use expedited grace-period primitives, for 6291 example, synchronize_rcu_expedited() instead 6292 of synchronize_rcu(). This reduces latency, 6293 but can increase CPU utilization, degrade 6294 real-time latency, and degrade energy efficiency. 6295 No effect on CONFIG_TINY_RCU kernels. 6296 6297 rcupdate.rcu_normal= [KNL] 6298 Use only normal grace-period primitives, 6299 for example, synchronize_rcu() instead of 6300 synchronize_rcu_expedited(). This improves 6301 real-time latency, CPU utilization, and 6302 energy efficiency, but can expose users to 6303 increased grace-period latency. This parameter 6304 overrides rcupdate.rcu_expedited. No effect on 6305 CONFIG_TINY_RCU kernels. 6306 6307 rcupdate.rcu_normal_after_boot= [KNL] 6308 Once boot has completed (that is, after 6309 rcu_end_inkernel_boot() has been invoked), use 6310 only normal grace-period primitives. No effect 6311 on CONFIG_TINY_RCU kernels. 6312 6313 But note that CONFIG_PREEMPT_RT=y kernels enables 6314 this kernel boot parameter, forcibly setting 6315 it to the value one, that is, converting any 6316 post-boot attempt at an expedited RCU grace 6317 period to instead use normal non-expedited 6318 grace-period processing. 6319 6320 rcupdate.rcu_task_collapse_lim= [KNL] 6321 Set the maximum number of callbacks present 6322 at the beginning of a grace period that allows 6323 the RCU Tasks flavors to collapse back to using 6324 a single callback queue. This switching only 6325 occurs when rcupdate.rcu_task_enqueue_lim is 6326 set to the default value of -1. 6327 6328 rcupdate.rcu_task_contend_lim= [KNL] 6329 Set the minimum number of callback-queuing-time 6330 lock-contention events per jiffy required to 6331 cause the RCU Tasks flavors to switch to per-CPU 6332 callback queuing. This switching only occurs 6333 when rcupdate.rcu_task_enqueue_lim is set to 6334 the default value of -1. 6335 6336 rcupdate.rcu_task_enqueue_lim= [KNL] 6337 Set the number of callback queues to use for the 6338 RCU Tasks family of RCU flavors. The default 6339 of -1 allows this to be automatically (and 6340 dynamically) adjusted. This parameter is intended 6341 for use in testing. 6342 6343 rcupdate.rcu_task_lazy_lim= [KNL] 6344 Number of callbacks on a given CPU that will 6345 cancel laziness on that CPU. Use -1 to disable 6346 cancellation of laziness, but be advised that 6347 doing so increases the danger of OOM due to 6348 callback flooding. 6349 6350 rcupdate.rcu_task_stall_info= [KNL] 6351 Set initial timeout in jiffies for RCU task stall 6352 informational messages, which give some indication 6353 of the problem for those not patient enough to 6354 wait for ten minutes. Informational messages are 6355 only printed prior to the stall-warning message 6356 for a given grace period. Disable with a value 6357 less than or equal to zero. Defaults to ten 6358 seconds. A change in value does not take effect 6359 until the beginning of the next grace period. 6360 6361 rcupdate.rcu_task_stall_info_mult= [KNL] 6362 Multiplier for time interval between successive 6363 RCU task stall informational messages for a given 6364 RCU tasks grace period. This value is clamped 6365 to one through ten, inclusive. It defaults to 6366 the value three, so that the first informational 6367 message is printed 10 seconds into the grace 6368 period, the second at 40 seconds, the third at 6369 160 seconds, and then the stall warning at 600 6370 seconds would prevent a fourth at 640 seconds. 6371 6372 rcupdate.rcu_task_stall_timeout= [KNL] 6373 Set timeout in jiffies for RCU task stall 6374 warning messages. Disable with a value less 6375 than or equal to zero. Defaults to ten minutes. 6376 A change in value does not take effect until 6377 the beginning of the next grace period. 6378 6379 rcupdate.rcu_tasks_lazy_ms= [KNL] 6380 Set timeout in milliseconds RCU Tasks asynchronous 6381 callback batching for call_rcu_tasks(). 6382 A negative value will take the default. A value 6383 of zero will disable batching. Batching is 6384 always disabled for synchronize_rcu_tasks(). 6385 6386 rcupdate.rcu_self_test= [KNL] 6387 Run the RCU early boot self tests 6388 6389 rdinit= [KNL] 6390 Format: <full_path> 6391 Run specified binary instead of /init from the ramdisk, 6392 used for early userspace startup. See initrd. 6393 6394 rdrand= [X86,EARLY] 6395 force - Override the decision by the kernel to hide the 6396 advertisement of RDRAND support (this affects 6397 certain AMD processors because of buggy BIOS 6398 support, specifically around the suspend/resume 6399 path). 6400 6401 rdt= [HW,X86,RDT] 6402 Turn on/off individual RDT features. List is: 6403 cmt, mbmtotal, mbmlocal, l3cat, l3cdp, l2cat, l2cdp, 6404 mba, smba, bmec, abmc, sdciae, energy[:guid], 6405 perf[:guid]. 6406 E.g. to turn on cmt and turn off mba use: 6407 rdt=cmt,!mba 6408 To turn off all energy telemetry monitoring and ensure that 6409 perf telemetry monitoring associated with guid 0x12345 6410 is enabled use: 6411 rdt=!energy,perf:0x12345 6412 6413 reboot= [KNL] 6414 Format (x86 or x86_64): 6415 [w[arm] | c[old] | h[ard] | s[oft] | g[pio]] | d[efault] \ 6416 [[,]s[mp]#### \ 6417 [[,]b[ios] | a[cpi] | k[bd] | t[riple] | e[fi] | p[ci]] \ 6418 [[,]f[orce] 6419 Where reboot_mode is one of warm (soft) or cold (hard) or gpio 6420 (prefix with 'panic_' to set mode for panic 6421 reboot only), 6422 reboot_type is one of bios, acpi, kbd, triple, efi, or pci, 6423 reboot_force is either force or not specified, 6424 reboot_cpu is s[mp]#### with #### being the processor 6425 to be used for rebooting. 6426 6427 acpi 6428 Use the ACPI RESET_REG in the FADT. If ACPI is not 6429 configured or the ACPI reset does not work, the reboot 6430 path attempts the reset using the keyboard controller. 6431 6432 bios 6433 Use the CPU reboot vector for warm reset 6434 6435 cold 6436 Set the cold reboot flag 6437 6438 default 6439 There are some built-in platform specific "quirks" 6440 - you may see: "reboot: <name> series board detected. 6441 Selecting <type> for reboots." In the case where you 6442 think the quirk is in error (e.g. you have newer BIOS, 6443 or newer board) using this option will ignore the 6444 built-in quirk table, and use the generic default 6445 reboot actions. 6446 6447 efi 6448 Use efi reset_system runtime service. If EFI is not 6449 configured or the EFI reset does not work, the reboot 6450 path attempts the reset using the keyboard controller. 6451 6452 force 6453 Don't stop other CPUs on reboot. This can make reboot 6454 more reliable in some cases. 6455 6456 kbd 6457 Use the keyboard controller. cold reset (default) 6458 6459 pci 6460 Use a write to the PCI config space register 0xcf9 to 6461 trigger reboot. 6462 6463 triple 6464 Force a triple fault (init) 6465 6466 warm 6467 Don't set the cold reboot flag 6468 6469 Using warm reset will be much faster especially on big 6470 memory systems because the BIOS will not go through 6471 the memory check. Disadvantage is that not all 6472 hardware will be completely reinitialized on reboot so 6473 there may be boot problems on some systems. 6474 6475 6476 refscale.holdoff= [KNL] 6477 Set test-start holdoff period. The purpose of 6478 this parameter is to delay the start of the 6479 test until boot completes in order to avoid 6480 interference. 6481 6482 refscale.lookup_instances= [KNL] 6483 Number of data elements to use for the forms of 6484 SLAB_TYPESAFE_BY_RCU testing. A negative number 6485 is negated and multiplied by nr_cpu_ids, while 6486 zero specifies nr_cpu_ids. 6487 6488 refscale.loops= [KNL] 6489 Set the number of loops over the synchronization 6490 primitive under test. Increasing this number 6491 reduces noise due to loop start/end overhead, 6492 but the default has already reduced the per-pass 6493 noise to a handful of picoseconds on ca. 2020 6494 x86 laptops. 6495 6496 refscale.nreaders= [KNL] 6497 Set number of readers. The default value of -1 6498 selects N, where N is roughly 75% of the number 6499 of CPUs. A value of zero is an interesting choice. 6500 6501 refscale.nruns= [KNL] 6502 Set number of runs, each of which is dumped onto 6503 the console log. 6504 6505 refscale.readdelay= [KNL] 6506 Set the read-side critical-section duration, 6507 measured in microseconds. 6508 6509 refscale.scale_type= [KNL] 6510 Specify the read-protection implementation to test. 6511 6512 refscale.shutdown= [KNL] 6513 Shut down the system at the end of the performance 6514 test. This defaults to 1 (shut it down) when 6515 refscale is built into the kernel and to 0 (leave 6516 it running) when refscale is built as a module. 6517 6518 refscale.verbose= [KNL] 6519 Enable additional printk() statements. 6520 6521 refscale.verbose_batched= [KNL] 6522 Batch the additional printk() statements. If zero 6523 (the default) or negative, print everything. Otherwise, 6524 print every Nth verbose statement, where N is the value 6525 specified. 6526 6527 regulator_ignore_unused 6528 [REGULATOR] 6529 Prevents regulator framework from disabling regulators 6530 that are unused, due no driver claiming them. This may 6531 be useful for debug and development, but should not be 6532 needed on a platform with proper driver support. 6533 6534 relax_domain_level= 6535 [KNL, SMP] Set scheduler's default relax_domain_level. 6536 See Documentation/admin-guide/cgroup-v1/cpusets.rst. 6537 6538 reserve= [KNL,BUGS] Force kernel to ignore I/O ports or memory 6539 Format: <base1>,<size1>[,<base2>,<size2>,...] 6540 Reserve I/O ports or memory so the kernel won't use 6541 them. If <base> is less than 0x10000, the region 6542 is assumed to be I/O ports; otherwise it is memory. 6543 6544 reserve_mem= [RAM] 6545 Format: nn[KMG]:<align>:<label> 6546 Reserve physical memory and label it with a name that 6547 other subsystems can use to access it. This is typically 6548 used for systems that do not wipe the RAM, and this command 6549 line will try to reserve the same physical memory on 6550 soft reboots. Note, it is not guaranteed to be the same 6551 location. For example, if anything about the system changes 6552 or if booting a different kernel. It can also fail if KASLR 6553 places the kernel at the location of where the RAM reservation 6554 was from a previous boot, the new reservation will be at a 6555 different location. 6556 Any subsystem using this feature must add a way to verify 6557 that the contents of the physical memory is from a previous 6558 boot, as there may be cases where the memory will not be 6559 located at the same location. 6560 6561 The format is size:align:label for example, to request 6562 12 megabytes of 4096 alignment for ramoops: 6563 6564 reserve_mem=12M:4096:oops ramoops.mem_name=oops 6565 6566 reservetop= [X86-32,EARLY] 6567 Format: nn[KMG] 6568 Reserves a hole at the top of the kernel virtual 6569 address space. 6570 6571 reset_devices [KNL] Force drivers to reset the underlying device 6572 during initialization. 6573 6574 resume= [SWSUSP] 6575 Specify the partition device for software suspend 6576 Format: 6577 {/dev/<dev> | PARTUUID=<uuid> | <int>:<int> | <hex>} 6578 6579 resume_offset= [SWSUSP] 6580 Specify the offset from the beginning of the partition 6581 given by "resume=" at which the swap header is located, 6582 in <PAGE_SIZE> units (needed only for swap files). 6583 See Documentation/power/swsusp-and-swap-files.rst 6584 6585 resumedelay= [HIBERNATION] Delay (in seconds) to pause before attempting to 6586 read the resume files 6587 6588 resumewait [HIBERNATION] Wait (indefinitely) for resume device to show up. 6589 Useful for devices that are detected asynchronously 6590 (e.g. USB and MMC devices). 6591 6592 retain_initrd [RAM] Keep initrd memory after extraction. After boot, it will 6593 be accessible via /sys/firmware/initrd. 6594 6595 retbleed= [X86] Control mitigation of RETBleed (Arbitrary 6596 Speculative Code Execution with Return Instructions) 6597 vulnerability. 6598 6599 AMD-based UNRET and IBPB mitigations alone do not stop 6600 sibling threads from influencing the predictions of other 6601 sibling threads. For that reason, STIBP is used on pro- 6602 cessors that support it, and mitigate SMT on processors 6603 that don't. 6604 6605 off - no mitigation 6606 auto - automatically select a mitigation 6607 auto,nosmt - automatically select a mitigation, 6608 disabling SMT if necessary for 6609 the full mitigation (only on Zen1 6610 and older without STIBP). 6611 ibpb - On AMD, mitigate short speculation 6612 windows on basic block boundaries too. 6613 Safe, highest perf impact. It also 6614 enables STIBP if present. Not suitable 6615 on Intel. 6616 ibpb,nosmt - Like "ibpb" above but will disable SMT 6617 when STIBP is not available. This is 6618 the alternative for systems which do not 6619 have STIBP. 6620 unret - Force enable untrained return thunks, 6621 only effective on AMD f15h-f17h based 6622 systems. 6623 unret,nosmt - Like unret, but will disable SMT when STIBP 6624 is not available. This is the alternative for 6625 systems which do not have STIBP. 6626 6627 Selecting 'auto' will choose a mitigation method at run 6628 time according to the CPU. 6629 6630 Not specifying this option is equivalent to retbleed=auto. 6631 6632 rfkill.default_state= 6633 0 "airplane mode". All wifi, bluetooth, wimax, gps, fm, 6634 etc. communication is blocked by default. 6635 1 Unblocked. 6636 6637 rfkill.master_switch_mode= 6638 0 The "airplane mode" button does nothing. 6639 1 The "airplane mode" button toggles between everything 6640 blocked and the previous configuration. 6641 2 The "airplane mode" button toggles between everything 6642 blocked and everything unblocked. 6643 6644 ring3mwait=disable 6645 [KNL] Disable ring 3 MONITOR/MWAIT feature on supported 6646 CPUs. 6647 6648 riscv_isa_fallback [RISCV,EARLY] 6649 When CONFIG_RISCV_ISA_FALLBACK is not enabled, permit 6650 falling back to detecting extension support by parsing 6651 "riscv,isa" property on devicetree systems when the 6652 replacement properties are not found. See the Kconfig 6653 entry for RISCV_ISA_FALLBACK. 6654 6655 riscv_nousercfi= 6656 all Disable user CFI ABI to userspace even if cpu extension 6657 are available. 6658 bcfi Disable user backward CFI ABI to userspace even if 6659 the shadow stack extension is available. 6660 fcfi Disable user forward CFI ABI to userspace even if the 6661 landing pad extension is available. 6662 6663 ro [KNL] Mount root device read-only on boot 6664 6665 rodata= [KNL,EARLY] 6666 on Mark read-only kernel memory as read-only (default). 6667 off Leave read-only kernel memory writable for debugging. 6668 noalias Mark read-only kernel memory as read-only but retain 6669 writable aliases in the direct map for regions outside 6670 of the kernel image. [arm64] 6671 6672 rockchip.usb_uart 6673 [EARLY] 6674 Enable the uart passthrough on the designated usb port 6675 on Rockchip SoCs. When active, the signals of the 6676 debug-uart get routed to the D+ and D- pins of the usb 6677 port and the regular usb controller gets disabled. 6678 6679 root= [KNL] Root filesystem 6680 Usually this is a block device specifier of some kind, 6681 see the early_lookup_bdev comment in 6682 block/early-lookup.c for details. 6683 Alternatively this can be "ram" for the legacy initial 6684 ramdisk, "nfs" and "cifs" for root on a network file 6685 system, or "mtd" and "ubi" for mounting from raw flash. 6686 6687 rootdelay= [KNL] Delay (in seconds) to pause before attempting to 6688 mount the root filesystem 6689 6690 rootflags= [KNL] Set root filesystem mount option string 6691 6692 rseq_slice_ext= [KNL] RSEQ based time slice extension 6693 Format: boolean 6694 Control enablement of RSEQ based time slice extension. 6695 Default is 'on'. 6696 6697 initramfs_options= [KNL] 6698 Specify mount options for the initramfs mount. 6699 6700 rootfstype= [KNL] Set root filesystem type 6701 6702 rootwait [KNL] Wait (indefinitely) for root device to show up. 6703 Useful for devices that are detected asynchronously 6704 (e.g. USB and MMC devices). 6705 6706 rootwait= [KNL] Maximum time (in seconds) to wait for root device 6707 to show up before attempting to mount the root 6708 filesystem. 6709 6710 rproc_mem=nn[KMG][@address] 6711 [KNL,ARM,CMA] Remoteproc physical memory block. 6712 Memory area to be used by remote processor image, 6713 managed by CMA. 6714 6715 rseq_debug= [KNL] Enable or disable restartable sequence 6716 debug mode. Defaults to CONFIG_RSEQ_DEBUG_DEFAULT_ENABLE. 6717 Format: <bool> 6718 6719 rt_group_sched= [KNL] Enable or disable SCHED_RR/FIFO group scheduling 6720 when CONFIG_RT_GROUP_SCHED=y. Defaults to 6721 !CONFIG_RT_GROUP_SCHED_DEFAULT_DISABLED. 6722 Format: <bool> 6723 6724 rw [KNL] Mount root device read-write on boot 6725 6726 S [KNL] Run init in single mode 6727 6728 s390_iommu= [HW,S390] 6729 Set s390 IOTLB flushing mode 6730 strict 6731 With strict flushing every unmap operation will result 6732 in an IOTLB flush. Default is lazy flushing before 6733 reuse, which is faster. Deprecated, equivalent to 6734 iommu.strict=1. 6735 6736 s390_iommu_aperture= [KNL,S390] 6737 Specifies the size of the per device DMA address space 6738 accessible through the DMA and IOMMU APIs as a decimal 6739 factor of the size of main memory. 6740 The default is 1 meaning that one can concurrently use 6741 as many DMA addresses as physical memory is installed, 6742 if supported by hardware, and thus map all of memory 6743 once. With a value of 2 one can map all of memory twice 6744 and so on. As a special case a factor of 0 imposes no 6745 restrictions other than those given by hardware at the 6746 cost of significant additional memory use for tables. 6747 6748 6749 sched_proxy_exec= [KNL] 6750 Enables or disables "proxy execution" style 6751 solution to mutex-based priority inversion. 6752 Format: <bool> 6753 6754 sched_verbose [KNL,EARLY] Enables verbose scheduler debug messages. 6755 6756 schedstats= [KNL,X86] Enable or disable scheduled statistics. 6757 Allowed values are enable and disable. This feature 6758 incurs a small amount of overhead in the scheduler 6759 but is useful for debugging and performance tuning. 6760 6761 sched_thermal_decay_shift= 6762 [Deprecated] 6763 [KNL, SMP] Set a decay shift for scheduler thermal 6764 pressure signal. Thermal pressure signal follows the 6765 default decay period of other scheduler pelt 6766 signals(usually 32 ms but configurable). Setting 6767 sched_thermal_decay_shift will left shift the decay 6768 period for the thermal pressure signal by the shift 6769 value. 6770 i.e. with the default pelt decay period of 32 ms 6771 sched_thermal_decay_shift thermal pressure decay pr 6772 1 64 ms 6773 2 128 ms 6774 and so on. 6775 Format: integer between 0 and 10 6776 Default is 0. 6777 6778 scftorture.holdoff= [KNL] 6779 Number of seconds to hold off before starting 6780 test. Defaults to zero for module insertion and 6781 to 10 seconds for built-in smp_call_function() 6782 tests. 6783 6784 scftorture.longwait= [KNL] 6785 Request ridiculously long waits randomly selected 6786 up to the chosen limit in seconds. Zero (the 6787 default) disables this feature. Please note 6788 that requesting even small non-zero numbers of 6789 seconds can result in RCU CPU stall warnings, 6790 softlockup complaints, and so on. 6791 6792 scftorture.nthreads= [KNL] 6793 Number of kthreads to spawn to invoke the 6794 smp_call_function() family of functions. 6795 The default of -1 specifies a number of kthreads 6796 equal to the number of CPUs. 6797 6798 scftorture.onoff_holdoff= [KNL] 6799 Number seconds to wait after the start of the 6800 test before initiating CPU-hotplug operations. 6801 6802 scftorture.onoff_interval= [KNL] 6803 Number seconds to wait between successive 6804 CPU-hotplug operations. Specifying zero (which 6805 is the default) disables CPU-hotplug operations. 6806 6807 scftorture.shutdown_secs= [KNL] 6808 The number of seconds following the start of the 6809 test after which to shut down the system. The 6810 default of zero avoids shutting down the system. 6811 Non-zero values are useful for automated tests. 6812 6813 scftorture.stat_interval= [KNL] 6814 The number of seconds between outputting the 6815 current test statistics to the console. A value 6816 of zero disables statistics output. 6817 6818 scftorture.stutter_cpus= [KNL] 6819 The number of jiffies to wait between each change 6820 to the set of CPUs under test. 6821 6822 scftorture.use_cpus_read_lock= [KNL] 6823 Use use_cpus_read_lock() instead of the default 6824 preempt_disable() to disable CPU hotplug 6825 while invoking one of the smp_call_function*() 6826 functions. 6827 6828 scftorture.verbose= [KNL] 6829 Enable additional printk() statements. 6830 6831 scftorture.weight_single= [KNL] 6832 The probability weighting to use for the 6833 smp_call_function_single() function with a zero 6834 "wait" parameter. A value of -1 selects the 6835 default if all other weights are -1. However, 6836 if at least one weight has some other value, a 6837 value of -1 will instead select a weight of zero. 6838 6839 scftorture.weight_single_wait= [KNL] 6840 The probability weighting to use for the 6841 smp_call_function_single() function with a 6842 non-zero "wait" parameter. See weight_single. 6843 6844 scftorture.weight_many= [KNL] 6845 The probability weighting to use for the 6846 smp_call_function_many() function with a zero 6847 "wait" parameter. See weight_single. 6848 Note well that setting a high probability for 6849 this weighting can place serious IPI load 6850 on the system. 6851 6852 scftorture.weight_many_wait= [KNL] 6853 The probability weighting to use for the 6854 smp_call_function_many() function with a 6855 non-zero "wait" parameter. See weight_single 6856 and weight_many. 6857 6858 scftorture.weight_all= [KNL] 6859 The probability weighting to use for the 6860 smp_call_function_all() function with a zero 6861 "wait" parameter. See weight_single and 6862 weight_many. 6863 6864 scftorture.weight_all_wait= [KNL] 6865 The probability weighting to use for the 6866 smp_call_function_all() function with a 6867 non-zero "wait" parameter. See weight_single 6868 and weight_many. 6869 6870 sdw_mclk_divider=[SDW] 6871 Specify the MCLK divider for Intel SoundWire buses in 6872 case the BIOS does not provide the clock rate properly. 6873 6874 skew_tick= [KNL,EARLY] Offset the periodic timer tick per cpu to mitigate 6875 xtime_lock contention on larger systems, and/or RCU lock 6876 contention on all systems with CONFIG_MAXSMP set. 6877 Format: { "0" | "1" } 6878 0 -- disable. (may be 1 via CONFIG_CMDLINE="skew_tick=1" 6879 1 -- enable. 6880 Note: increases power consumption, thus should only be 6881 enabled if running jitter sensitive (HPC/RT) workloads. 6882 6883 security= [SECURITY] Choose a legacy "major" security module to 6884 enable at boot. This has been deprecated by the 6885 "lsm=" parameter. 6886 6887 selinux= [SELINUX] Disable or enable SELinux at boot time. 6888 Format: { "0" | "1" } 6889 See security/selinux/Kconfig help text. 6890 0 -- disable. 6891 1 -- enable. 6892 Default value is 1. 6893 6894 serialnumber [BUGS=X86-32] 6895 6896 sev=option[,option...] [X86-64] 6897 6898 debug 6899 Enable debug messages. 6900 6901 nosnp 6902 Do not enable SEV-SNP (applies to host/hypervisor 6903 only). Setting 'nosnp' avoids the RMP check overhead 6904 in memory accesses when users do not want to run 6905 SEV-SNP guests. 6906 6907 shapers= [NET] 6908 Maximal number of shapers. 6909 6910 show_lapic= [APIC,X86] Advanced Programmable Interrupt Controller 6911 Limit apic dumping. The parameter defines the maximal 6912 number of local apics being dumped. Also it is possible 6913 to set it to "all" by meaning -- no limit here. 6914 Format: { 1 (default) | 2 | ... | all }. 6915 The parameter valid if only apic=debug or 6916 apic=verbose is specified. 6917 Example: apic=debug show_lapic=all 6918 6919 slab_debug[=options[,slabs][;[options[,slabs]]...] [MM] 6920 Enabling slab_debug allows one to determine the 6921 culprit if slab objects become corrupted. Enabling 6922 slab_debug can create guard zones around objects and 6923 may poison objects when not in use. Also tracks the 6924 last alloc / free. For more information see 6925 Documentation/admin-guide/mm/slab.rst. 6926 (slub_debug legacy name also accepted for now) 6927 6928 Using this option implies the "no_hash_pointers" 6929 option which can be undone by adding the 6930 "hash_pointers=always" option. 6931 6932 slab_max_order= [MM] 6933 Determines the maximum allowed order for slabs. 6934 A high setting may cause OOMs due to memory 6935 fragmentation. For more information see 6936 Documentation/admin-guide/mm/slab.rst. 6937 (slub_max_order legacy name also accepted for now) 6938 6939 slab_merge [MM] 6940 Enable merging of slabs with similar size when the 6941 kernel is built without CONFIG_SLAB_MERGE_DEFAULT. 6942 (slub_merge legacy name also accepted for now) 6943 6944 slab_min_objects= [MM] 6945 The minimum number of objects per slab. SLUB will 6946 increase the slab order up to slab_max_order to 6947 generate a sufficiently large slab able to contain 6948 the number of objects indicated. The higher the number 6949 of objects the smaller the overhead of tracking slabs 6950 and the less frequently locks need to be acquired. 6951 For more information see 6952 Documentation/admin-guide/mm/slab.rst. 6953 (slub_min_objects legacy name also accepted for now) 6954 6955 slab_min_order= [MM] 6956 Determines the minimum page order for slabs. Must be 6957 lower or equal to slab_max_order. For more information see 6958 Documentation/admin-guide/mm/slab.rst. 6959 (slub_min_order legacy name also accepted for now) 6960 6961 slab_nomerge [MM] 6962 Disable merging of slabs with similar size. May be 6963 necessary if there is some reason to distinguish 6964 allocs to different slabs, especially in hardened 6965 environments where the risk of heap overflows and 6966 layout control by attackers can usually be 6967 frustrated by disabling merging. This will reduce 6968 most of the exposure of a heap attack to a single 6969 cache (risks via metadata attacks are mostly 6970 unchanged). Debug options disable merging on their 6971 own. 6972 For more information see 6973 Documentation/admin-guide/mm/slab.rst. 6974 (slub_nomerge legacy name also accepted for now) 6975 6976 slab_strict_numa [MM] 6977 Support memory policies on a per object level 6978 in the slab allocator. The default is for memory 6979 policies to be applied at the folio level when 6980 a new folio is needed or a partial folio is 6981 retrieved from the lists. Increases overhead 6982 in the slab fastpaths but gains more accurate 6983 NUMA kernel object placement which helps with slow 6984 interconnects in NUMA systems. 6985 6986 slram= [HW,MTD] 6987 6988 smart2= [HW] 6989 Format: <io1>[,<io2>[,...,<io8>]] 6990 6991 smp.csd_lock_timeout= [KNL] 6992 Specify the period of time in milliseconds 6993 that smp_call_function() and friends will wait 6994 for a CPU to release the CSD lock. This is 6995 useful when diagnosing bugs involving CPUs 6996 disabling interrupts for extended periods 6997 of time. Defaults to 5,000 milliseconds, and 6998 setting a value of zero disables this feature. 6999 This feature may be more efficiently disabled 7000 using the csdlock_debug- kernel parameter. 7001 7002 smp.panic_on_ipistall= [KNL] 7003 If a csd_lock_timeout extends for more than 7004 the specified number of milliseconds, panic the 7005 system. By default, let CSD-lock acquisition 7006 take as long as they take. Specifying 300,000 7007 for this value provides a 5-minute timeout. 7008 7009 smsc-ircc2.nopnp [HW] Don't use PNP to discover SMC devices 7010 smsc-ircc2.ircc_cfg= [HW] Device configuration I/O port 7011 smsc-ircc2.ircc_sir= [HW] SIR base I/O port 7012 smsc-ircc2.ircc_fir= [HW] FIR base I/O port 7013 smsc-ircc2.ircc_irq= [HW] IRQ line 7014 smsc-ircc2.ircc_dma= [HW] DMA channel 7015 smsc-ircc2.ircc_transceiver= [HW] Transceiver type: 7016 0: Toshiba Satellite 1800 (GP data pin select) 7017 1: Fast pin select (default) 7018 2: ATC IRMode 7019 7020 smt= [KNL,MIPS,S390,EARLY] Set the maximum number of threads 7021 (logical CPUs) to use per physical CPU on systems 7022 capable of symmetric multithreading (SMT). Will 7023 be capped to the actual hardware limit. 7024 Format: <integer> 7025 Default: -1 (no limit) 7026 7027 softlockup_panic= 7028 [KNL] Should the soft-lockup detector generate panics. 7029 Format: <int> 7030 7031 A value of non-zero instructs the soft-lockup detector 7032 to panic the machine when a soft-lockup duration exceeds 7033 N thresholds. It is also controlled by the kernel.softlockup_panic 7034 sysctl and CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC, which is the 7035 respective build-time switch to that functionality. 7036 7037 softlockup_all_cpu_backtrace= 7038 [KNL] Should the soft-lockup detector generate 7039 backtraces on all cpus. 7040 Format: 0 | 1 7041 7042 sonypi.*= [HW] Sony Programmable I/O Control Device driver 7043 See Documentation/admin-guide/laptops/sonypi.rst 7044 7045 spectre_bhi= [X86] Control mitigation of Branch History Injection 7046 (BHI) vulnerability. This setting affects the 7047 deployment of the HW BHI control and the SW BHB 7048 clearing sequence. 7049 7050 on - (default) Enable the HW or SW mitigation as 7051 needed. This protects the kernel from 7052 both syscalls and VMs. 7053 vmexit - On systems which don't have the HW mitigation 7054 available, enable the SW mitigation on vmexit 7055 ONLY. On such systems, the host kernel is 7056 protected from VM-originated BHI attacks, but 7057 may still be vulnerable to syscall attacks. 7058 off - Disable the mitigation. 7059 7060 spectre_v2= [X86,EARLY] Control mitigation of Spectre variant 2 7061 (indirect branch speculation) vulnerability. 7062 The default operation protects the kernel from 7063 user space attacks. 7064 7065 on - unconditionally enable, implies 7066 spectre_v2_user=on 7067 off - unconditionally disable, implies 7068 spectre_v2_user=off 7069 auto - kernel detects whether your CPU model is 7070 vulnerable 7071 7072 Selecting 'on' will, and 'auto' may, choose a 7073 mitigation method at run time according to the 7074 CPU, the available microcode, the setting of the 7075 CONFIG_MITIGATION_RETPOLINE configuration option, 7076 and the compiler with which the kernel was built. 7077 7078 Selecting 'on' will also enable the mitigation 7079 against user space to user space task attacks. 7080 Selecting specific mitigation does not force enable 7081 user mitigations. 7082 7083 Selecting 'off' will disable both the kernel and 7084 the user space protections. 7085 7086 Specific mitigations can also be selected manually: 7087 7088 retpoline - replace indirect branches 7089 retpoline,generic - Retpolines 7090 retpoline,lfence - LFENCE; indirect branch 7091 retpoline,amd - alias for retpoline,lfence 7092 eibrs - Enhanced/Auto IBRS 7093 eibrs,retpoline - Enhanced/Auto IBRS + Retpolines 7094 eibrs,lfence - Enhanced/Auto IBRS + LFENCE 7095 ibrs - use IBRS to protect kernel 7096 7097 Not specifying this option is equivalent to 7098 spectre_v2=auto. 7099 7100 spectre_v2_user= 7101 [X86] Control mitigation of Spectre variant 2 7102 (indirect branch speculation) vulnerability between 7103 user space tasks 7104 7105 on - Unconditionally enable mitigations. Is 7106 enforced by spectre_v2=on 7107 7108 off - Unconditionally disable mitigations. Is 7109 enforced by spectre_v2=off 7110 7111 prctl - Indirect branch speculation is enabled, 7112 but mitigation can be enabled via prctl 7113 per thread. The mitigation control state 7114 is inherited on fork. 7115 7116 prctl,ibpb 7117 - Like "prctl" above, but only STIBP is 7118 controlled per thread. IBPB is issued 7119 always when switching between different user 7120 space processes. 7121 7122 seccomp 7123 - Same as "prctl" above, but all seccomp 7124 threads will enable the mitigation unless 7125 they explicitly opt out. 7126 7127 seccomp,ibpb 7128 - Like "seccomp" above, but only STIBP is 7129 controlled per thread. IBPB is issued 7130 always when switching between different 7131 user space processes. 7132 7133 auto - Kernel selects the mitigation depending on 7134 the available CPU features and vulnerability. 7135 7136 Default mitigation: "prctl" 7137 7138 Not specifying this option is equivalent to 7139 spectre_v2_user=auto. 7140 7141 spec_rstack_overflow= 7142 [X86,EARLY] Control RAS overflow mitigation on AMD Zen CPUs 7143 7144 off - Disable mitigation 7145 microcode - Enable microcode mitigation only 7146 safe-ret - Enable sw-only safe RET mitigation (default) 7147 ibpb - Enable mitigation by issuing IBPB on 7148 kernel entry 7149 ibpb-vmexit - Issue IBPB only on VMEXIT 7150 (cloud-specific mitigation) 7151 7152 spec_store_bypass_disable= 7153 [HW,EARLY] Control Speculative Store Bypass (SSB) Disable mitigation 7154 (Speculative Store Bypass vulnerability) 7155 7156 Certain CPUs are vulnerable to an exploit against a 7157 a common industry wide performance optimization known 7158 as "Speculative Store Bypass" in which recent stores 7159 to the same memory location may not be observed by 7160 later loads during speculative execution. The idea 7161 is that such stores are unlikely and that they can 7162 be detected prior to instruction retirement at the 7163 end of a particular speculation execution window. 7164 7165 In vulnerable processors, the speculatively forwarded 7166 store can be used in a cache side channel attack, for 7167 example to read memory to which the attacker does not 7168 directly have access (e.g. inside sandboxed code). 7169 7170 This parameter controls whether the Speculative Store 7171 Bypass optimization is used. 7172 7173 On x86 the options are: 7174 7175 on - Unconditionally disable Speculative Store Bypass 7176 off - Unconditionally enable Speculative Store Bypass 7177 auto - Kernel detects whether the CPU model contains an 7178 implementation of Speculative Store Bypass and 7179 picks the most appropriate mitigation. If the 7180 CPU is not vulnerable, "off" is selected. If the 7181 CPU is vulnerable the default mitigation is 7182 architecture and Kconfig dependent. See below. 7183 prctl - Control Speculative Store Bypass per thread 7184 via prctl. Speculative Store Bypass is enabled 7185 for a process by default. The state of the control 7186 is inherited on fork. 7187 seccomp - Same as "prctl" above, but all seccomp threads 7188 will disable SSB unless they explicitly opt out. 7189 7190 Default mitigations: 7191 X86: "prctl" 7192 7193 On powerpc the options are: 7194 7195 on,auto - On Power8 and Power9 insert a store-forwarding 7196 barrier on kernel entry and exit. On Power7 7197 perform a software flush on kernel entry and 7198 exit. 7199 off - No action. 7200 7201 Not specifying this option is equivalent to 7202 spec_store_bypass_disable=auto. 7203 7204 split_llc= 7205 [X86,EARLY] Split the LLC N-ways 7206 7207 When set, the LLC is split this many ways by matching 7208 'core_id % n'. This is setup before SMP bringup and 7209 used during SMP bringup before it knows the full 7210 topology. If your core count doesn't nicely divide by 7211 the number given, you get to keep the pieces. 7212 7213 This is mostly a debug feature to emulate multiple LLCs 7214 on hardware that only have a single LLC. 7215 7216 split_lock_detect= 7217 [X86] Enable split lock detection or bus lock detection 7218 7219 When enabled (and if hardware support is present), atomic 7220 instructions that access data across cache line 7221 boundaries will result in an alignment check exception 7222 for split lock detection or a debug exception for 7223 bus lock detection. 7224 7225 off - not enabled 7226 7227 warn - the kernel will emit rate-limited warnings 7228 about applications triggering the #AC 7229 exception or the #DB exception. This mode is 7230 the default on CPUs that support split lock 7231 detection or bus lock detection. Default 7232 behavior is by #AC if both features are 7233 enabled in hardware. 7234 7235 fatal - the kernel will send SIGBUS to applications 7236 that trigger the #AC exception or the #DB 7237 exception. Default behavior is by #AC if 7238 both features are enabled in hardware. 7239 7240 ratelimit:N - 7241 Set system wide rate limit to N bus locks 7242 per second for bus lock detection. 7243 0 < N <= 1000. 7244 7245 N/A for split lock detection. 7246 7247 7248 If an #AC exception is hit in the kernel or in 7249 firmware (i.e. not while executing in user mode) 7250 the kernel will oops in either "warn" or "fatal" 7251 mode. 7252 7253 #DB exception for bus lock is triggered only when 7254 CPL > 0. 7255 7256 srbds= [X86,INTEL,EARLY] 7257 Control the Special Register Buffer Data Sampling 7258 (SRBDS) mitigation. 7259 7260 Certain CPUs are vulnerable to an MDS-like 7261 exploit which can leak bits from the random 7262 number generator. 7263 7264 By default, this issue is mitigated by 7265 microcode. However, the microcode fix can cause 7266 the RDRAND and RDSEED instructions to become 7267 much slower. Among other effects, this will 7268 result in reduced throughput from /dev/urandom. 7269 7270 The microcode mitigation can be disabled with 7271 the following option: 7272 7273 off: Disable mitigation and remove 7274 performance impact to RDRAND and RDSEED 7275 7276 srcutree.big_cpu_lim [KNL] 7277 Specifies the number of CPUs constituting a 7278 large system, such that srcu_struct structures 7279 should immediately allocate an srcu_node array. 7280 This kernel-boot parameter defaults to 128, 7281 but takes effect only when the low-order four 7282 bits of srcutree.convert_to_big is equal to 3 7283 (decide at boot). 7284 7285 srcutree.convert_to_big [KNL] 7286 Specifies under what conditions an SRCU tree 7287 srcu_struct structure will be converted to big 7288 form, that is, with an rcu_node tree: 7289 7290 0: Never. 7291 1: At init_srcu_struct() time. 7292 2: When rcutorture decides to. 7293 3: Decide at boot time (default). 7294 0x1X: Above plus if high contention. 7295 7296 Either way, the srcu_node tree will be sized based 7297 on the actual runtime number of CPUs (nr_cpu_ids) 7298 instead of the compile-time CONFIG_NR_CPUS. 7299 7300 srcutree.counter_wrap_check [KNL] 7301 Specifies how frequently to check for 7302 grace-period sequence counter wrap for the 7303 srcu_data structure's ->srcu_gp_seq_needed field. 7304 The greater the number of bits set in this kernel 7305 parameter, the less frequently counter wrap will 7306 be checked for. Note that the bottom two bits 7307 are ignored. 7308 7309 srcutree.exp_holdoff [KNL] 7310 Specifies how many nanoseconds must elapse 7311 since the end of the last SRCU grace period for 7312 a given srcu_struct until the next normal SRCU 7313 grace period will be considered for automatic 7314 expediting. Set to zero to disable automatic 7315 expediting. 7316 7317 srcutree.srcu_max_nodelay [KNL] 7318 Specifies the number of no-delay instances 7319 per jiffy for which the SRCU grace period 7320 worker thread will be rescheduled with zero 7321 delay. Beyond this limit, worker thread will 7322 be rescheduled with a sleep delay of one jiffy. 7323 7324 srcutree.srcu_max_nodelay_phase [KNL] 7325 Specifies the per-grace-period phase, number of 7326 non-sleeping polls of readers. Beyond this limit, 7327 grace period worker thread will be rescheduled 7328 with a sleep delay of one jiffy, between each 7329 rescan of the readers, for a grace period phase. 7330 7331 srcutree.srcu_retry_check_delay [KNL] 7332 Specifies number of microseconds of non-sleeping 7333 delay between each non-sleeping poll of readers. 7334 7335 srcutree.small_contention_lim [KNL] 7336 Specifies the number of update-side contention 7337 events per jiffy will be tolerated before 7338 initiating a conversion of an srcu_struct 7339 structure to big form. Note that the value of 7340 srcutree.convert_to_big must have the 0x10 bit 7341 set for contention-based conversions to occur. 7342 7343 ssbd= [ARM64,HW,EARLY] 7344 Speculative Store Bypass Disable control 7345 7346 On CPUs that are vulnerable to the Speculative 7347 Store Bypass vulnerability and offer a 7348 firmware based mitigation, this parameter 7349 indicates how the mitigation should be used: 7350 7351 force-on: Unconditionally enable mitigation for 7352 for both kernel and userspace 7353 force-off: Unconditionally disable mitigation for 7354 for both kernel and userspace 7355 kernel: Always enable mitigation in the 7356 kernel, and offer a prctl interface 7357 to allow userspace to register its 7358 interest in being mitigated too. 7359 7360 stack_guard_gap= [MM] 7361 override the default stack gap protection. The value 7362 is in page units and it defines how many pages prior 7363 to (for stacks growing down) resp. after (for stacks 7364 growing up) the main stack are reserved for no other 7365 mapping. Default value is 256 pages. 7366 7367 stack_depot_disable= [KNL,EARLY] 7368 Setting this to true through kernel command line will 7369 disable the stack depot thereby saving the static memory 7370 consumed by the stack hash table. By default this is set 7371 to false. 7372 7373 stack_depot_max_pools= [KNL,EARLY] 7374 Specify the maximum number of pools to use for storing 7375 stack traces. Pools are allocated on-demand up to this 7376 limit. Default value is 8191 pools. 7377 7378 stacktrace [FTRACE] 7379 Enable the stack tracer on boot up. 7380 7381 stacktrace_filter=[function-list] 7382 [FTRACE] Limit the functions that the stack tracer 7383 will trace at boot up. function-list is a comma-separated 7384 list of functions. This list can be changed at run 7385 time by the stack_trace_filter file in the debugfs 7386 tracing directory. Note, this enables stack tracing 7387 and the stacktrace above is not needed. 7388 7389 sti= [PARISC,HW] 7390 Format: <num> 7391 Set the STI (builtin display/keyboard on the HP-PARISC 7392 machines) console (graphic card) which should be used 7393 as the initial boot-console. 7394 See also comment in drivers/video/sticore.c. 7395 7396 sti_font= [HW] 7397 See comment in drivers/video/sticore.c. 7398 7399 stifb= [HW] 7400 Format: bpp:<bpp1>[:<bpp2>[:<bpp3>...]] 7401 7402 strict_sas_size= 7403 [X86] 7404 Format: <bool> 7405 Enable or disable strict sigaltstack size checks 7406 against the required signal frame size which 7407 depends on the supported FPU features. This can 7408 be used to filter out binaries which have 7409 not yet been made aware of AT_MINSIGSTKSZ. 7410 7411 stress_hpt [PPC,EARLY] 7412 Limits the number of kernel HPT entries in the hash 7413 page table to increase the rate of hash page table 7414 faults on kernel addresses. 7415 7416 stress_slb [PPC,EARLY] 7417 Limits the number of kernel SLB entries, and flushes 7418 them frequently to increase the rate of SLB faults 7419 on kernel addresses. 7420 7421 no_slb_preload [PPC,EARLY] 7422 Disables slb preloading for userspace. 7423 7424 sunrpc.min_resvport= 7425 sunrpc.max_resvport= 7426 [NFS,SUNRPC] 7427 SunRPC servers often require that client requests 7428 originate from a privileged port (i.e. a port in the 7429 range 0 < portnr < 1024). 7430 An administrator who wishes to reserve some of these 7431 ports for other uses may adjust the range that the 7432 kernel's sunrpc client considers to be privileged 7433 using these two parameters to set the minimum and 7434 maximum port values. 7435 7436 sunrpc.svc_rpc_per_connection_limit= 7437 [NFS,SUNRPC] 7438 Limit the number of requests that the server will 7439 process in parallel from a single connection. 7440 The default value is 0 (no limit). 7441 7442 sunrpc.pool_mode= 7443 [NFS] 7444 Control how the NFS server code allocates CPUs to 7445 service thread pools. Depending on how many NICs 7446 you have and where their interrupts are bound, this 7447 option will affect which CPUs will do NFS serving. 7448 Note: this parameter cannot be changed while the 7449 NFS server is running. 7450 7451 auto the server chooses an appropriate mode 7452 automatically using heuristics 7453 global a single global pool contains all CPUs 7454 percpu one pool for each CPU 7455 pernode one pool for each NUMA node (equivalent 7456 to global on non-NUMA machines) 7457 7458 sunrpc.tcp_slot_table_entries= 7459 sunrpc.udp_slot_table_entries= 7460 [NFS,SUNRPC] 7461 Sets the upper limit on the number of simultaneous 7462 RPC calls that can be sent from the client to a 7463 server. Increasing these values may allow you to 7464 improve throughput, but will also increase the 7465 amount of memory reserved for use by the client. 7466 7467 suspend.pm_test_delay= 7468 [SUSPEND] 7469 Sets the number of seconds to remain in a suspend test 7470 mode before resuming the system (see 7471 /sys/power/pm_test). Only available when CONFIG_PM_DEBUG 7472 is set. Default value is 5. 7473 7474 svm= [PPC] 7475 Format: { on | off | y | n | 1 | 0 } 7476 This parameter controls use of the Protected 7477 Execution Facility on pSeries. 7478 7479 swiotlb= [ARM,PPC,MIPS,X86,S390,EARLY] 7480 Format: { <int> [,<int>] | force | noforce } 7481 <int> -- Number of I/O TLB slabs 7482 <int> -- Second integer after comma. Number of swiotlb 7483 areas with their own lock. Will be rounded up 7484 to a power of 2. 7485 force -- force using of bounce buffers even if they 7486 wouldn't be automatically used by the kernel 7487 noforce -- Never use bounce buffers (for debugging) 7488 7489 switches= [HW,M68k,EARLY] 7490 7491 sysctl.*= [KNL] 7492 Set a sysctl parameter, right before loading the init 7493 process, as if the value was written to the respective 7494 /proc/sys/... file. Both '.' and '/' are recognized as 7495 separators. Unrecognized parameters and invalid values 7496 are reported in the kernel log. Sysctls registered 7497 later by a loaded module cannot be set this way. 7498 Example: sysctl.vm.swappiness=40 7499 7500 sysrq_always_enabled 7501 [KNL] 7502 Ignore sysrq setting - this boot parameter will 7503 neutralize any effect of /proc/sys/kernel/sysrq. 7504 Useful for debugging. 7505 7506 tcpmhash_entries= [KNL,NET] 7507 Set the number of tcp_metrics_hash slots. 7508 Default value is 8192 or 16384 depending on total 7509 ram pages. This is used to specify the TCP metrics 7510 cache size. See Documentation/networking/ip-sysctl.rst 7511 "tcp_no_metrics_save" section for more details. 7512 7513 tdfx= [HW,DRM] 7514 7515 test_suspend= [SUSPEND] 7516 Format: { "mem" | "standby" | "freeze" }[,N] 7517 Specify "mem" (for Suspend-to-RAM) or "standby" (for 7518 standby suspend) or "freeze" (for suspend type freeze) 7519 as the system sleep state during system startup with 7520 the optional capability to repeat N number of times. 7521 The system is woken from this state using a 7522 wakeup-capable RTC alarm. 7523 7524 thash_entries= [KNL,NET] 7525 Set number of hash buckets for TCP connection 7526 7527 thermal.act= [HW,ACPI] 7528 -1: disable all active trip points in all thermal zones 7529 <degrees C>: override all lowest active trip points 7530 7531 thermal.crt= [HW,ACPI] 7532 -1: disable all critical trip points in all thermal zones 7533 <degrees C>: override all critical trip points 7534 7535 thermal.off= [HW,ACPI] 7536 1: disable ACPI thermal control 7537 7538 thermal.psv= [HW,ACPI] 7539 -1: disable all passive trip points 7540 <degrees C>: override all passive trip points to this 7541 value 7542 7543 thermal.tzp= [HW,ACPI] 7544 Specify global default ACPI thermal zone polling rate 7545 <deci-seconds>: poll all this frequency 7546 0: no polling (default) 7547 7548 thp_anon= [KNL] 7549 Format: <size>[KMG],<size>[KMG]:<state>;<size>[KMG]-<size>[KMG]:<state> 7550 state is one of "always", "madvise", "never" or "inherit". 7551 Control the default behavior of the system with respect 7552 to anonymous transparent hugepages. 7553 Can be used multiple times for multiple anon THP sizes. 7554 See Documentation/admin-guide/mm/transhuge.rst for more 7555 details. 7556 7557 threadirqs [KNL,EARLY] 7558 Force threading of all interrupt handlers except those 7559 marked explicitly IRQF_NO_THREAD. 7560 7561 thp_shmem= [KNL] 7562 Format: <size>[KMG],<size>[KMG]:<policy>;<size>[KMG]-<size>[KMG]:<policy> 7563 Control the default policy of each hugepage size for the 7564 internal shmem mount. <policy> is one of policies available 7565 for the shmem mount ("always", "inherit", "never", "within_size", 7566 and "advise"). 7567 It can be used multiple times for multiple shmem THP sizes. 7568 See Documentation/admin-guide/mm/transhuge.rst for more 7569 details. 7570 7571 topology= [S390,EARLY] 7572 Format: {off | on} 7573 Specify if the kernel should make use of the cpu 7574 topology information if the hardware supports this. 7575 The scheduler will make use of this information and 7576 e.g. base its process migration decisions on it. 7577 Default is on. 7578 7579 torture.disable_onoff_at_boot= [KNL] 7580 Prevent the CPU-hotplug component of torturing 7581 until after init has spawned. 7582 7583 torture.ftrace_dump_at_shutdown= [KNL] 7584 Dump the ftrace buffer at torture-test shutdown, 7585 even if there were no errors. This can be a 7586 very costly operation when many torture tests 7587 are running concurrently, especially on systems 7588 with rotating-rust storage. 7589 7590 torture.verbose_sleep_frequency= [KNL] 7591 Specifies how many verbose printk()s should be 7592 emitted between each sleep. The default of zero 7593 disables verbose-printk() sleeping. 7594 7595 torture.verbose_sleep_duration= [KNL] 7596 Duration of each verbose-printk() sleep in jiffies. 7597 7598 tpm.disable_pcr_integrity= [HW,TPM] 7599 Do not protect PCR registers from unintended physical 7600 access, or interposers in the bus by the means of 7601 having an integrity protected session wrapped around 7602 TPM2_PCR_Extend command. Consider this in a situation 7603 where TPM is heavily utilized by IMA, thus protection 7604 causing a major performance hit, and the space where 7605 machines are deployed is by other means guarded. 7606 7607 tpm_crb_ffa.busy_timeout_ms= [ARM64,TPM] 7608 Maximum time in milliseconds to retry sending a message 7609 to the TPM service before giving up. This parameter controls 7610 how long the system will continue retrying when the TPM 7611 service is busy. 7612 Format: <unsigned int> 7613 Default: 2000 (2 seconds) 7614 7615 tpm_suspend_pcr=[HW,TPM] 7616 Format: integer pcr id 7617 Specify that at suspend time, the tpm driver 7618 should extend the specified pcr with zeros, 7619 as a workaround for some chips which fail to 7620 flush the last written pcr on TPM_SaveState. 7621 This will guarantee that all the other pcrs 7622 are saved. 7623 7624 tpm_tis.interrupts= [HW,TPM] 7625 Enable interrupts for the MMIO based physical layer 7626 for the FIFO interface. By default it is set to false 7627 (0). For more information about TPM hardware interfaces 7628 defined by Trusted Computing Group (TCG) see 7629 https://trustedcomputinggroup.org/resource/pc-client-platform-tpm-profile-ptp-specification/ 7630 7631 tp_printk [FTRACE] 7632 Have the tracepoints sent to printk as well as the 7633 tracing ring buffer. This is useful for early boot up 7634 where the system hangs or reboots and does not give the 7635 option for reading the tracing buffer or performing a 7636 ftrace_dump_on_oops. 7637 7638 To turn off having tracepoints sent to printk, 7639 echo 0 > /proc/sys/kernel/tracepoint_printk 7640 Note, echoing 1 into this file without the 7641 tp_printk kernel cmdline option has no effect. 7642 7643 The tp_printk_stop_on_boot (see below) can also be used 7644 to stop the printing of events to console at 7645 late_initcall_sync. 7646 7647 ** CAUTION ** 7648 7649 Having tracepoints sent to printk() and activating high 7650 frequency tracepoints such as irq or sched, can cause 7651 the system to live lock. 7652 7653 tp_printk_stop_on_boot [FTRACE] 7654 When tp_printk (above) is set, it can cause a lot of noise 7655 on the console. It may be useful to only include the 7656 printing of events during boot up, as user space may 7657 make the system inoperable. 7658 7659 This command line option will stop the printing of events 7660 to console at the late_initcall_sync() time frame. 7661 7662 trace_buf_size=nn[KMG] 7663 [FTRACE] will set tracing buffer size on each cpu. 7664 7665 trace_clock= [FTRACE] Set the clock used for tracing events 7666 at boot up. 7667 local - Use the per CPU time stamp counter 7668 (converted into nanoseconds). Fast, but 7669 depending on the architecture, may not be 7670 in sync between CPUs. 7671 global - Event time stamps are synchronized across 7672 CPUs. May be slower than the local clock, 7673 but better for some race conditions. 7674 counter - Simple counting of events (1, 2, ..) 7675 note, some counts may be skipped due to the 7676 infrastructure grabbing the clock more than 7677 once per event. 7678 uptime - Use jiffies as the time stamp. 7679 perf - Use the same clock that perf uses. 7680 mono - Use ktime_get_mono_fast_ns() for time stamps. 7681 mono_raw - Use ktime_get_raw_fast_ns() for time 7682 stamps. 7683 boot - Use ktime_get_boot_fast_ns() for time stamps. 7684 Architectures may add more clocks. See 7685 Documentation/trace/ftrace.rst for more details. 7686 7687 trace_event=[event-list] 7688 [FTRACE] Set and start specified trace events in order 7689 to facilitate early boot debugging. The event-list is a 7690 comma-separated list of trace events to enable. See 7691 also Documentation/trace/events.rst 7692 7693 To enable modules, use :mod: keyword: 7694 7695 trace_event=:mod:<module> 7696 7697 The value before :mod: will only enable specific events 7698 that are part of the module. See the above mentioned 7699 document for more information. 7700 7701 trace_instance=[instance-info] 7702 [FTRACE] Create a ring buffer instance early in boot up. 7703 This will be listed in: 7704 7705 /sys/kernel/tracing/instances 7706 7707 Events can be enabled at the time the instance is created 7708 via: 7709 7710 trace_instance=<name>,<system1>:<event1>,<system2>:<event2> 7711 7712 Note, the "<system*>:" portion is optional if the event is 7713 unique. 7714 7715 trace_instance=foo,sched:sched_switch,irq_handler_entry,initcall 7716 7717 will enable the "sched_switch" event (note, the "sched:" is optional, and 7718 the same thing would happen if it was left off). The irq_handler_entry 7719 event, and all events under the "initcall" system. 7720 7721 Flags can be added to the instance to modify its behavior when it is 7722 created. The flags are separated by '^'. 7723 7724 The available flags are: 7725 7726 traceoff - Have the tracing instance tracing disabled after it is created. 7727 traceprintk - Have trace_printk() write into this trace instance 7728 (note, "printk" and "trace_printk" can also be used) 7729 7730 trace_instance=foo^traceoff^traceprintk,sched,irq 7731 7732 The flags must come before the defined events. 7733 7734 If memory has been reserved (see memmap for x86), the instance 7735 can use that memory: 7736 7737 memmap=12M$0x284500000 trace_instance=boot_map@0x284500000:12M 7738 7739 The above will create a "boot_map" instance that uses the physical 7740 memory at 0x284500000 that is 12Megs. The per CPU buffers of that 7741 instance will be split up accordingly. 7742 7743 Alternatively, the memory can be reserved by the reserve_mem option: 7744 7745 reserve_mem=12M:4096:trace trace_instance=boot_map@trace 7746 7747 This will reserve 12 megabytes at boot up with a 4096 byte alignment 7748 and place the ring buffer in this memory. Note that due to KASLR, the 7749 memory may not be the same location each time, which will not preserve 7750 the buffer content. 7751 7752 Also note that the layout of the ring buffer data may change between 7753 kernel versions where the validator will fail and reset the ring buffer 7754 if the layout is not the same as the previous kernel. 7755 7756 If the ring buffer is used for persistent bootups and has events enabled, 7757 it is recommend to disable tracing so that events from a previous boot do not 7758 mix with events of the current boot (unless you are debugging a random crash 7759 at boot up). 7760 7761 reserve_mem=12M:4096:trace trace_instance=boot_map^traceoff^traceprintk@trace,sched,irq 7762 7763 Note, saving the trace buffer across reboots does require that the system 7764 is set up to not wipe memory. For instance, CONFIG_RESET_ATTACK_MITIGATION 7765 can force a memory reset on boot which will clear any trace that was stored. 7766 This is just one of many ways that can clear memory. Make sure your system 7767 keeps the content of memory across reboots before relying on this option. 7768 7769 NB: Both the mapped address and size must be page aligned for the architecture. 7770 7771 See also Documentation/trace/debugging.rst 7772 7773 7774 trace_options=[option-list] 7775 [FTRACE] Enable or disable tracer options at boot. 7776 The option-list is a comma delimited list of options 7777 that can be enabled or disabled just as if you were 7778 to echo the option name into 7779 7780 /sys/kernel/tracing/trace_options 7781 7782 For example, to enable stacktrace option (to dump the 7783 stack trace of each event), add to the command line: 7784 7785 trace_options=stacktrace 7786 7787 See also Documentation/trace/ftrace.rst "trace options" 7788 section. 7789 7790 trace_trigger=[trigger-list] 7791 [FTRACE] Add an event trigger on specific events. 7792 Set a trigger on top of a specific event, with an optional 7793 filter. 7794 7795 The format is "trace_trigger=<event>.<trigger>[ if <filter>],..." 7796 Where more than one trigger may be specified that are comma delimited. 7797 7798 For example: 7799 7800 trace_trigger="sched_switch.stacktrace if prev_state == 2" 7801 7802 The above will enable the "stacktrace" trigger on the "sched_switch" 7803 event but only trigger it if the "prev_state" of the "sched_switch" 7804 event is "2" (TASK_UNINTERRUPTIBLE). 7805 7806 See also "Event triggers" in Documentation/trace/events.rst 7807 7808 7809 traceoff_after_boot 7810 [FTRACE] Sometimes tracing is used to debug issues 7811 during the boot process. Since the trace buffer has a 7812 limited amount of storage, it may be prudent to 7813 disable tracing after the boot is finished, otherwise 7814 the critical information may be overwritten. With this 7815 option, the main tracing buffer will be turned off at 7816 the end of the boot process. 7817 7818 traceoff_on_warning 7819 [FTRACE] enable this option to disable tracing when a 7820 warning is hit. This turns off "tracing_on". Tracing can 7821 be enabled again by echoing '1' into the "tracing_on" 7822 file located in /sys/kernel/tracing/ 7823 7824 This option is useful, as it disables the trace before 7825 the WARNING dump is called, which prevents the trace to 7826 be filled with content caused by the warning output. 7827 7828 This option can also be set at run time via the sysctl 7829 option: kernel/traceoff_on_warning 7830 7831 transparent_hugepage= 7832 [KNL] 7833 Format: [always|madvise|never] 7834 Can be used to control the default behavior of the system 7835 with respect to transparent hugepages. 7836 See Documentation/admin-guide/mm/transhuge.rst 7837 for more details. 7838 7839 transparent_hugepage_shmem= [KNL] 7840 Format: [always|within_size|advise|never|deny|force] 7841 Can be used to control the hugepage allocation policy for 7842 the internal shmem mount. 7843 See Documentation/admin-guide/mm/transhuge.rst 7844 for more details. 7845 7846 transparent_hugepage_tmpfs= [KNL] 7847 Format: [always|within_size|advise|never] 7848 Can be used to control the default hugepage allocation policy 7849 for the tmpfs mount. 7850 See Documentation/admin-guide/mm/transhuge.rst 7851 for more details. 7852 7853 trusted.source= [KEYS] 7854 Format: <string> 7855 This parameter identifies the trust source as a backend 7856 for trusted keys implementation. Supported trust 7857 sources: 7858 - "tpm" 7859 - "tee" 7860 - "caam" 7861 - "dcp" 7862 - "pkwm" 7863 If not specified then it defaults to iterating through 7864 the trust source list starting with TPM and assigns the 7865 first trust source as a backend which is initialized 7866 successfully during iteration. 7867 7868 trusted.debug= [KEYS] 7869 Format: <bool> 7870 Enable trusted keys debug traces at runtime when 7871 CONFIG_TRUSTED_KEYS_DEBUG=y. 7872 7873 To make the traces visible after enabling the option, 7874 use trusted.dyndbg='+p' as needed. By convention, 7875 the subsystem uses pr_debug() for these traces. 7876 7877 SAFETY: The traces can leak sensitive data, so be 7878 cautious before enabling this. They remain inactive 7879 unless this parameter is set this option to a true 7880 value. 7881 7882 Default: false 7883 7884 trusted.rng= [KEYS] 7885 Format: <string> 7886 The RNG used to generate key material for trusted keys. 7887 Can be one of: 7888 - "kernel" 7889 - the same value as trusted.source: "tpm" or "tee" 7890 - "default" 7891 If not specified, "default" is used. In this case, 7892 the RNG's choice is left to each individual trust source. 7893 7894 trusted.dcp_use_otp_key 7895 This is intended to be used in combination with 7896 trusted.source=dcp and will select the DCP OTP key 7897 instead of the DCP UNIQUE key blob encryption. 7898 7899 trusted.dcp_skip_zk_test 7900 This is intended to be used in combination with 7901 trusted.source=dcp and will disable the check if the 7902 blob key is all zeros. This is helpful for situations where 7903 having this key zero'ed is acceptable. E.g. in testing 7904 scenarios. 7905 7906 tsa= [X86] Control mitigation for Transient Scheduler 7907 Attacks on AMD CPUs. Search the following in your 7908 favourite search engine for more details: 7909 7910 "Technical guidance for mitigating transient scheduler 7911 attacks". 7912 7913 off - disable the mitigation 7914 on - enable the mitigation (default) 7915 user - mitigate only user/kernel transitions 7916 vm - mitigate only guest/host transitions 7917 7918 7919 tsc= Disable clocksource stability checks for TSC. 7920 Format: <string> 7921 [x86] reliable: mark tsc clocksource as reliable, this 7922 disables clocksource verification at runtime, as well 7923 as the stability checks done at bootup. Used to enable 7924 high-resolution timer mode on older hardware, and in 7925 virtualized environment. 7926 [x86] noirqtime: Do not use TSC to do irq accounting. 7927 Used to run time disable IRQ_TIME_ACCOUNTING on any 7928 platforms where RDTSC is slow and this accounting 7929 can add overhead. 7930 [x86] unstable: mark the TSC clocksource as unstable, this 7931 marks the TSC unconditionally unstable at bootup and 7932 avoids any further wobbles once the TSC watchdog notices. 7933 [x86] nowatchdog: disable clocksource watchdog. Used 7934 in situations with strict latency requirements (where 7935 interruptions from clocksource watchdog are not 7936 acceptable). 7937 [x86] recalibrate: force recalibration against a HW timer 7938 (HPET or PM timer) on systems whose TSC frequency was 7939 obtained from HW or FW using either an MSR or CPUID(0x15). 7940 Warn if the difference is more than 500 ppm. 7941 [x86] watchdog: Enforce the clocksource watchdog on TSC 7942 7943 tsc_early_khz= [X86,EARLY] Skip early TSC calibration and use the given 7944 value instead. Useful when the early TSC frequency discovery 7945 procedure is not reliable, such as on overclocked systems 7946 with CPUID.16h support and partial CPUID.15h support. 7947 Format: <unsigned int> 7948 7949 tsx= [X86] Control Transactional Synchronization 7950 Extensions (TSX) feature in Intel processors that 7951 support TSX control. 7952 7953 This parameter controls the TSX feature. The options are: 7954 7955 on - Enable TSX on the system. Although there are 7956 mitigations for all known security vulnerabilities, 7957 TSX has been known to be an accelerator for 7958 several previous speculation-related CVEs, and 7959 so there may be unknown security risks associated 7960 with leaving it enabled. 7961 7962 off - Disable TSX on the system. (Note that this 7963 option takes effect only on newer CPUs which are 7964 not vulnerable to MDS, i.e., have 7965 MSR_IA32_ARCH_CAPABILITIES.MDS_NO=1 and which get 7966 the new IA32_TSX_CTRL MSR through a microcode 7967 update. This new MSR allows for the reliable 7968 deactivation of the TSX functionality.) 7969 7970 auto - Disable TSX if X86_BUG_TAA is present, 7971 otherwise enable TSX on the system. 7972 7973 Not specifying this option is equivalent to tsx=off. 7974 7975 See Documentation/admin-guide/hw-vuln/tsx_async_abort.rst 7976 for more details. 7977 7978 tsx_async_abort= [X86,INTEL,EARLY] Control mitigation for the TSX Async 7979 Abort (TAA) vulnerability. 7980 7981 Similar to Micro-architectural Data Sampling (MDS) 7982 certain CPUs that support Transactional 7983 Synchronization Extensions (TSX) are vulnerable to an 7984 exploit against CPU internal buffers which can forward 7985 information to a disclosure gadget under certain 7986 conditions. 7987 7988 In vulnerable processors, the speculatively forwarded 7989 data can be used in a cache side channel attack, to 7990 access data to which the attacker does not have direct 7991 access. 7992 7993 This parameter controls the TAA mitigation. The 7994 options are: 7995 7996 full - Enable TAA mitigation on vulnerable CPUs 7997 if TSX is enabled. 7998 7999 full,nosmt - Enable TAA mitigation and disable SMT on 8000 vulnerable CPUs. If TSX is disabled, SMT 8001 is not disabled because CPU is not 8002 vulnerable to cross-thread TAA attacks. 8003 off - Unconditionally disable TAA mitigation 8004 8005 On MDS-affected machines, tsx_async_abort=off can be 8006 prevented by an active MDS mitigation as both vulnerabilities 8007 are mitigated with the same mechanism so in order to disable 8008 this mitigation, you need to specify mds=off too. 8009 8010 Not specifying this option is equivalent to 8011 tsx_async_abort=full. On CPUs which are MDS affected 8012 and deploy MDS mitigation, TAA mitigation is not 8013 required and doesn't provide any additional 8014 mitigation. 8015 8016 For details see: 8017 Documentation/admin-guide/hw-vuln/tsx_async_abort.rst 8018 8019 turbografx.map[2|3]= [HW,JOY] 8020 TurboGraFX parallel port interface 8021 Format: 8022 <port#>,<js1>,<js2>,<js3>,<js4>,<js5>,<js6>,<js7> 8023 See also Documentation/input/devices/joystick-parport.rst 8024 8025 udbg-immortal [PPC] When debugging early kernel crashes that 8026 happen after console_init() and before a proper 8027 console driver takes over, this boot options might 8028 help "seeing" what's going on. 8029 8030 uhash_entries= [KNL,NET] 8031 Set number of hash buckets for UDP/UDP-Lite connections 8032 8033 uhci-hcd.ignore_oc= 8034 [USB] Ignore overcurrent events (default N). 8035 Some badly-designed motherboards generate lots of 8036 bogus events, for ports that aren't wired to 8037 anything. Set this parameter to avoid log spamming. 8038 Note that genuine overcurrent events won't be 8039 reported either. 8040 8041 unaligned_scalar_speed= 8042 [RISCV] 8043 Format: {slow | fast | unsupported} 8044 Allow skipping scalar unaligned access speed tests. This 8045 is useful for testing alternative code paths and to skip 8046 the tests in environments where they run too slowly. All 8047 CPUs must have the same scalar unaligned access speed. 8048 8049 unaligned_vector_speed= 8050 [RISCV] 8051 Format: {slow | fast | unsupported} 8052 Allow skipping vector unaligned access speed tests. This 8053 is useful for testing alternative code paths and to skip 8054 the tests in environments where they run too slowly. All 8055 CPUs must have the same vector unaligned access speed. 8056 8057 unknown_nmi_panic 8058 [X86] Cause panic on unknown NMI. 8059 8060 unwind_debug [X86-64,EARLY] 8061 Enable unwinder debug output. This can be 8062 useful for debugging certain unwinder error 8063 conditions, including corrupt stacks and 8064 bad/missing unwinder metadata. 8065 8066 usbcore.authorized_default= 8067 [USB] Default USB device authorization: 8068 (default -1 = authorized (same as 1), 8069 0 = not authorized, 1 = authorized, 2 = authorized 8070 if device connected to internal port) 8071 8072 usbcore.autosuspend= 8073 [USB] The autosuspend time delay (in seconds) used 8074 for newly-detected USB devices (default 2). This 8075 is the time required before an idle device will be 8076 autosuspended. Devices for which the delay is set 8077 to a negative value won't be autosuspended at all. 8078 8079 usbcore.usbfs_snoop= 8080 [USB] Set to log all usbfs traffic (default 0 = off). 8081 8082 usbcore.usbfs_snoop_max= 8083 [USB] Maximum number of bytes to snoop in each URB 8084 (default = 65536). 8085 8086 usbcore.blinkenlights= 8087 [USB] Set to cycle leds on hubs (default 0 = off). 8088 8089 usbcore.old_scheme_first= 8090 [USB] Start with the old device initialization 8091 scheme (default 0 = off). 8092 8093 usbcore.usbfs_memory_mb= 8094 [USB] Memory limit (in MB) for buffers allocated by 8095 usbfs (default = 16, 0 = max = 2047). 8096 8097 usbcore.use_both_schemes= 8098 [USB] Try the other device initialization scheme 8099 if the first one fails (default 1 = enabled). 8100 8101 usbcore.initial_descriptor_timeout= 8102 [USB] Specifies timeout for the initial 64-byte 8103 USB_REQ_GET_DESCRIPTOR request in milliseconds 8104 (default 5000 = 5.0 seconds). 8105 8106 usbcore.nousb [USB] Disable the USB subsystem 8107 8108 usbcore.quirks= 8109 [USB] A list of quirk entries to augment the built-in 8110 usb core quirk list. List entries are separated by 8111 commas. Each entry has the form 8112 VendorID:ProductID:Flags. The IDs are 4-digit hex 8113 numbers and Flags is a set of letters. Each letter 8114 will change the built-in quirk; setting it if it is 8115 clear and clearing it if it is set. The letters have 8116 the following meanings: 8117 a = USB_QUIRK_STRING_FETCH_255 (string 8118 descriptors must not be fetched using 8119 a 255-byte read); 8120 b = USB_QUIRK_RESET_RESUME (device can't resume 8121 correctly so reset it instead); 8122 c = USB_QUIRK_NO_SET_INTF (device can't handle 8123 Set-Interface requests); 8124 d = USB_QUIRK_CONFIG_INTF_STRINGS (device can't 8125 handle its Configuration or Interface 8126 strings); 8127 e = USB_QUIRK_RESET (device can't be reset 8128 (e.g morph devices), don't use reset); 8129 f = USB_QUIRK_HONOR_BNUMINTERFACES (device has 8130 more interface descriptions than the 8131 bNumInterfaces count, and can't handle 8132 talking to these interfaces); 8133 g = USB_QUIRK_DELAY_INIT (device needs a pause 8134 during initialization, after we read 8135 the device descriptor); 8136 h = USB_QUIRK_LINEAR_UFRAME_INTR_BINTERVAL (For 8137 high speed and super speed interrupt 8138 endpoints, the USB 2.0 and USB 3.0 spec 8139 require the interval in microframes (1 8140 microframe = 125 microseconds) to be 8141 calculated as interval = 2 ^ 8142 (bInterval-1). 8143 Devices with this quirk report their 8144 bInterval as the result of this 8145 calculation instead of the exponent 8146 variable used in the calculation); 8147 i = USB_QUIRK_DEVICE_QUALIFIER (device can't 8148 handle device_qualifier descriptor 8149 requests); 8150 j = USB_QUIRK_IGNORE_REMOTE_WAKEUP (device 8151 generates spurious wakeup, ignore 8152 remote wakeup capability); 8153 k = USB_QUIRK_NO_LPM (device can't handle Link 8154 Power Management); 8155 l = USB_QUIRK_LINEAR_FRAME_INTR_BINTERVAL 8156 (Device reports its bInterval as linear 8157 frames instead of the USB 2.0 8158 calculation); 8159 m = USB_QUIRK_DISCONNECT_SUSPEND (Device needs 8160 to be disconnected before suspend to 8161 prevent spurious wakeup); 8162 n = USB_QUIRK_DELAY_CTRL_MSG (Device needs a 8163 pause after every control message); 8164 o = USB_QUIRK_HUB_SLOW_RESET (Hub needs extra 8165 delay after resetting its port); 8166 p = USB_QUIRK_SHORT_SET_ADDRESS_REQ_TIMEOUT 8167 (Reduce timeout of the SET_ADDRESS 8168 request from 5000 ms to 500 ms); 8169 q = USB_QUIRK_FORCE_ONE_CONFIG (Device 8170 claims zero configurations, 8171 forcing to 1); 8172 Example: quirks=0781:5580:bk,0a5c:5834:gij 8173 8174 usbhid.mousepoll= 8175 [USBHID] The interval which mice are to be polled at. 8176 8177 usbhid.jspoll= 8178 [USBHID] The interval which joysticks are to be polled at. 8179 8180 usbhid.kbpoll= 8181 [USBHID] The interval which keyboards are to be polled at. 8182 8183 usb-storage.delay_use= 8184 [UMS] The delay in seconds before a new device is 8185 scanned for Logical Units (default 1). 8186 Optionally the delay in milliseconds if the value has 8187 suffix with "ms". 8188 Example: delay_use=2567ms 8189 8190 usb-storage.quirks= 8191 [UMS] A list of quirks entries to supplement or 8192 override the built-in unusual_devs list. List 8193 entries are separated by commas. Each entry has 8194 the form VID:PID:Flags where VID and PID are Vendor 8195 and Product ID values (4-digit hex numbers) and 8196 Flags is a set of characters, each corresponding 8197 to a common usb-storage quirk flag as follows: 8198 a = SANE_SENSE (collect more than 18 bytes 8199 of sense data, not on uas); 8200 b = BAD_SENSE (don't collect more than 18 8201 bytes of sense data, not on uas); 8202 c = FIX_CAPACITY (decrease the reported 8203 device capacity by one sector); 8204 d = NO_READ_DISC_INFO (don't use 8205 READ_DISC_INFO command, not on uas); 8206 e = NO_READ_CAPACITY_16 (don't use 8207 READ_CAPACITY_16 command); 8208 f = NO_REPORT_OPCODES (don't use report opcodes 8209 command, uas only); 8210 g = MAX_SECTORS_240 (don't transfer more than 8211 240 sectors at a time, uas only); 8212 h = CAPACITY_HEURISTICS (decrease the 8213 reported device capacity by one 8214 sector if the number is odd); 8215 i = IGNORE_DEVICE (don't bind to this 8216 device); 8217 j = NO_REPORT_LUNS (don't use report luns 8218 command, uas only); 8219 k = NO_SAME (do not use WRITE_SAME, uas only) 8220 l = NOT_LOCKABLE (don't try to lock and 8221 unlock ejectable media, not on uas); 8222 m = MAX_SECTORS_64 (don't transfer more 8223 than 64 sectors = 32 KB at a time, 8224 not on uas); 8225 n = INITIAL_READ10 (force a retry of the 8226 initial READ(10) command, not on uas); 8227 o = CAPACITY_OK (accept the capacity 8228 reported by the device, not on uas); 8229 p = WRITE_CACHE (the device cache is ON 8230 by default, not on uas); 8231 r = IGNORE_RESIDUE (the device reports 8232 bogus residue values, not on uas); 8233 s = SINGLE_LUN (the device has only one 8234 Logical Unit); 8235 t = NO_ATA_1X (don't allow ATA(12) and ATA(16) 8236 commands, uas only); 8237 u = IGNORE_UAS (don't bind to the uas driver); 8238 w = NO_WP_DETECT (don't test whether the 8239 medium is write-protected). 8240 y = ALWAYS_SYNC (issue a SYNCHRONIZE_CACHE 8241 even if the device claims no cache, 8242 not on uas) 8243 Example: quirks=0419:aaf5:rl,0421:0433:rc 8244 8245 user_debug= [KNL,ARM] 8246 Format: <int> 8247 See arch/arm/Kconfig.debug help text. 8248 1 - undefined instruction events 8249 2 - system calls 8250 4 - invalid data aborts 8251 8 - SIGSEGV faults 8252 16 - SIGBUS faults 8253 Example: user_debug=31 8254 8255 vdso= [X86,SH,SPARC] 8256 On X86_32, this is an alias for vdso32=. Otherwise: 8257 8258 vdso=1: enable VDSO (the default) 8259 vdso=0: disable VDSO mapping 8260 8261 vdso32= [X86] Control the 32-bit vDSO 8262 vdso32=1: enable 32-bit VDSO 8263 vdso32=0 or vdso32=2: disable 32-bit VDSO 8264 8265 See the help text for CONFIG_COMPAT_VDSO for more 8266 details. If CONFIG_COMPAT_VDSO is set, the default is 8267 vdso32=0; otherwise, the default is vdso32=1. 8268 8269 For compatibility with older kernels, vdso32=2 is an 8270 alias for vdso32=0. 8271 8272 Try vdso32=0 if you encounter an error that says: 8273 dl_main: Assertion `(void *) ph->p_vaddr == _rtld_local._dl_sysinfo_dso' failed! 8274 8275 video= [FB,EARLY] Frame buffer configuration 8276 See Documentation/fb/modedb.rst. 8277 8278 video.brightness_switch_enabled= [ACPI] 8279 Format: [0|1] 8280 If set to 1, on receiving an ACPI notify event 8281 generated by hotkey, video driver will adjust brightness 8282 level and then send out the event to user space through 8283 the allocated input device. If set to 0, video driver 8284 will only send out the event without touching backlight 8285 brightness level. 8286 default: 1 8287 8288 virtio_mmio.device= 8289 [VMMIO] Memory mapped virtio (platform) device. 8290 8291 <size>@<baseaddr>:<irq>[:<id>] 8292 where: 8293 <size> := size (can use standard suffixes 8294 like K, M and G) 8295 <baseaddr> := physical base address 8296 <irq> := interrupt number (as passed to 8297 request_irq()) 8298 <id> := (optional) platform device id 8299 example: 8300 virtio_mmio.device=1K@0x100b0000:48:7 8301 8302 Can be used multiple times for multiple devices. 8303 8304 vga= [BOOT,X86-32] Select a particular video mode 8305 See Documentation/arch/x86/boot.rst and 8306 Documentation/admin-guide/svga.rst. 8307 Use vga=ask for menu. 8308 This is actually a boot loader parameter; the value is 8309 passed to the kernel using a special protocol. 8310 8311 vm_debug[=options] [KNL] Available with CONFIG_DEBUG_VM=y. 8312 May slow down system boot speed, especially when 8313 enabled on systems with a large amount of memory. 8314 All options are enabled by default, and this 8315 interface is meant to allow for selectively 8316 enabling or disabling specific virtual memory 8317 debugging features. 8318 8319 Available options are: 8320 P Enable page structure init time poisoning 8321 - Disable all of the above options 8322 8323 vmalloc=nn[KMG] [KNL,BOOT,EARLY] Forces the vmalloc area to have an 8324 exact size of <nn>. This can be used to increase 8325 the minimum size (128MB on x86, arm32 platforms). 8326 It can also be used to decrease the size and leave more room 8327 for directly mapped kernel RAM. Note that this parameter does 8328 not exist on many other platforms (including arm64, alpha, 8329 loongarch, arc, csky, hexagon, microblaze, mips, nios2, openrisc, 8330 parisc, m64k, powerpc, riscv, sh, um, xtensa, s390, sparc). 8331 8332 vmcp_cma=nn[MG] [KNL,S390,EARLY] 8333 Sets the memory size reserved for contiguous memory 8334 allocations for the vmcp device driver. 8335 8336 vmhalt= [KNL,S390] Perform z/VM CP command after system halt. 8337 Format: <command> 8338 8339 vmpanic= [KNL,S390] Perform z/VM CP command after kernel panic. 8340 Format: <command> 8341 8342 vmpoff= [KNL,S390] Perform z/VM CP command after power off. 8343 Format: <command> 8344 8345 vmscape= [X86] Controls mitigation for VMscape attacks. 8346 VMscape attacks can leak information from a userspace 8347 hypervisor to a guest via speculative side-channels. 8348 8349 off - disable the mitigation 8350 ibpb - use Indirect Branch Prediction Barrier 8351 (IBPB) mitigation (default) 8352 force - force vulnerability detection even on 8353 unaffected processors 8354 8355 vsyscall= [X86-64,EARLY] 8356 Controls the behavior of vsyscalls (i.e. calls to 8357 fixed addresses of 0xffffffffff600x00 from legacy 8358 code). Most statically-linked binaries and older 8359 versions of glibc use these calls. Because these 8360 functions are at fixed addresses, they make nice 8361 targets for exploits that can control RIP. 8362 8363 emulate Vsyscalls turn into traps and are emulated 8364 reasonably safely. The vsyscall page is 8365 readable. This disables the Linear 8366 Address Space Separation (LASS) security 8367 feature and makes the system less secure. 8368 8369 xonly [default] Vsyscalls turn into traps and are 8370 emulated reasonably safely. The vsyscall 8371 page is not readable. 8372 8373 none Vsyscalls don't work at all. This makes 8374 them quite hard to use for exploits but 8375 might break your system. 8376 8377 vt.color= [VT] Default text color. 8378 Format: 0xYX, X = foreground, Y = background. 8379 Default: 0x07 = light gray on black. 8380 8381 vt.cur_default= [VT] Default cursor shape. 8382 Format: 0xCCBBAA, where AA, BB, and CC are the same as 8383 the parameters of the <Esc>[?A;B;Cc escape sequence; 8384 see vga-softcursor.rst. Default: 2 = underline. 8385 8386 vt.default_blu= [VT] 8387 Format: <blue0>,<blue1>,<blue2>,...,<blue15> 8388 Change the default blue palette of the console. 8389 This is a 16-member array composed of values 8390 ranging from 0-255. 8391 8392 vt.default_grn= [VT] 8393 Format: <green0>,<green1>,<green2>,...,<green15> 8394 Change the default green palette of the console. 8395 This is a 16-member array composed of values 8396 ranging from 0-255. 8397 8398 vt.default_red= [VT] 8399 Format: <red0>,<red1>,<red2>,...,<red15> 8400 Change the default red palette of the console. 8401 This is a 16-member array composed of values 8402 ranging from 0-255. 8403 8404 vt.default_utf8= 8405 [VT] 8406 Format=<0|1> 8407 Set system-wide default UTF-8 mode for all tty's. 8408 Default is 1, i.e. UTF-8 mode is enabled for all 8409 newly opened terminals. 8410 8411 vt.global_cursor_default= 8412 [VT] 8413 Format=<-1|0|1> 8414 Set system-wide default for whether a cursor 8415 is shown on new VTs. Default is -1, 8416 i.e. cursors will be created by default unless 8417 overridden by individual drivers. 0 will hide 8418 cursors, 1 will display them. 8419 8420 vt.italic= [VT] Default color for italic text; 0-15. 8421 Default: 2 = green. 8422 8423 vt.underline= [VT] Default color for underlined text; 0-15. 8424 Default: 3 = cyan. 8425 8426 watchdog timers [HW,WDT] For information on watchdog timers, 8427 see Documentation/watchdog/watchdog-parameters.rst 8428 or other driver-specific files in the 8429 Documentation/watchdog/ directory. 8430 8431 watchdog_thresh= 8432 [KNL] 8433 Set the hard lockup detector stall duration 8434 threshold in seconds. The soft lockup detector 8435 threshold is set to twice the value. A value of 0 8436 disables both lockup detectors. Default is 10 8437 seconds. 8438 8439 workqueue.unbound_cpus= 8440 [KNL,SMP] Specify to constrain one or some CPUs 8441 to use in unbound workqueues. 8442 Format: <cpu-list> 8443 By default, all online CPUs are available for 8444 unbound workqueues. 8445 8446 workqueue.watchdog_thresh= 8447 If CONFIG_WQ_WATCHDOG is configured, workqueue can 8448 warn stall conditions and dump internal state to 8449 help debugging. 0 disables workqueue stall 8450 detection; otherwise, it's the stall threshold 8451 duration in seconds. The default value is 30 and 8452 it can be updated at runtime by writing to the 8453 corresponding sysfs file. 8454 8455 workqueue.panic_on_stall=<uint> 8456 Panic when workqueue stall is detected by 8457 CONFIG_WQ_WATCHDOG. It sets the number times of the 8458 stall to trigger panic. 8459 8460 The default is set by CONFIG_BOOTPARAM_WQ_STALL_PANIC, 8461 which is 0 (disabled) if not configured. 8462 8463 workqueue.panic_on_stall_time=<uint> 8464 Panic when a workqueue stall has been continuous for 8465 the specified number of seconds. Unlike panic_on_stall 8466 which counts accumulated stall events, this triggers 8467 based on the duration of a single continuous stall. 8468 8469 The default is 0, which disables the time-based panic. 8470 8471 workqueue.cpu_intensive_thresh_us= 8472 Per-cpu work items which run for longer than this 8473 threshold are automatically considered CPU intensive 8474 and excluded from concurrency management to prevent 8475 them from noticeably delaying other per-cpu work 8476 items. Default is 10000 (10ms). 8477 8478 If CONFIG_WQ_CPU_INTENSIVE_REPORT is set, the kernel 8479 will report the work functions which violate this 8480 threshold repeatedly. They are likely good 8481 candidates for using WQ_UNBOUND workqueues instead. 8482 8483 workqueue.cpu_intensive_warning_thresh=<uint> 8484 If CONFIG_WQ_CPU_INTENSIVE_REPORT is set, the kernel 8485 will report the work functions which violate the 8486 intensive_threshold_us repeatedly. In order to prevent 8487 spurious warnings, start printing only after a work 8488 function has violated this threshold number of times. 8489 8490 The default is 4 times. 0 disables the warning. 8491 8492 workqueue.power_efficient 8493 Per-cpu workqueues are generally preferred because 8494 they show better performance thanks to cache 8495 locality; unfortunately, per-cpu workqueues tend to 8496 be more power hungry than unbound workqueues. 8497 8498 Enabling this makes the per-cpu workqueues which 8499 were observed to contribute significantly to power 8500 consumption unbound, leading to measurably lower 8501 power usage at the cost of small performance 8502 overhead. 8503 8504 The default value of this parameter is determined by 8505 the config option CONFIG_WQ_POWER_EFFICIENT_DEFAULT. 8506 8507 workqueue.default_affinity_scope= 8508 Select the default affinity scope to use for unbound 8509 workqueues. Can be one of "cpu", "smt", "cache", 8510 "cache_shard", "numa" and "system". Default is 8511 "cache_shard". For more 8512 information, see the Affinity Scopes section in 8513 Documentation/core-api/workqueue.rst. 8514 8515 This can be changed after boot by writing to the 8516 matching /sys/module/workqueue/parameters file. All 8517 workqueues with the "default" affinity scope will be 8518 updated accordingly. 8519 8520 workqueue.debug_force_rr_cpu 8521 Workqueue used to implicitly guarantee that work 8522 items queued without explicit CPU specified are put 8523 on the local CPU. This guarantee is no longer true 8524 and while local CPU is still preferred work items 8525 may be put on foreign CPUs. This debug option 8526 forces round-robin CPU selection to flush out 8527 usages which depend on the now broken guarantee. 8528 When enabled, memory and cache locality will be 8529 impacted. 8530 8531 writecombine= [LOONGARCH,EARLY] Control the MAT (Memory Access 8532 Type) of ioremap_wc(). 8533 8534 on - Enable writecombine, use WUC for ioremap_wc() 8535 off - Disable writecombine, use SUC for ioremap_wc() 8536 8537 x2apic_phys [X86-64,APIC,EARLY] Use x2apic physical mode instead of 8538 default x2apic cluster mode on platforms 8539 supporting x2apic. 8540 8541 xen_512gb_limit [KNL,X86-64,XEN] 8542 Restricts the kernel running paravirtualized under Xen 8543 to use only up to 512 GB of RAM. The reason to do so is 8544 crash analysis tools and Xen tools for doing domain 8545 save/restore/migration must be enabled to handle larger 8546 domains. 8547 8548 xen_console_io [XEN,EARLY] 8549 Boolean option to enable/disable the usage of the Xen 8550 console_io hypercalls to read and write to the console. 8551 Mostly useful for debugging and development. 8552 8553 xen_emul_unplug= [HW,X86,XEN,EARLY] 8554 Unplug Xen emulated devices 8555 Format: [unplug0,][unplug1] 8556 ide-disks -- unplug primary master IDE devices 8557 aux-ide-disks -- unplug non-primary-master IDE devices 8558 nics -- unplug network devices 8559 all -- unplug all emulated devices (NICs and IDE disks) 8560 unnecessary -- unplugging emulated devices is 8561 unnecessary even if the host did not respond to 8562 the unplug protocol 8563 never -- do not unplug even if version check succeeds 8564 8565 xen_legacy_crash [X86,XEN,EARLY] 8566 Crash from Xen panic notifier, without executing late 8567 panic() code such as dumping handler. 8568 8569 xen_mc_debug [X86,XEN,EARLY] 8570 Enable multicall debugging when running as a Xen PV guest. 8571 Enabling this feature will reduce performance a little 8572 bit, so it should only be enabled for obtaining extended 8573 debug data in case of multicall errors. 8574 8575 xen_msr_safe= [X86,XEN,EARLY] 8576 Format: <bool> 8577 Select whether to always use non-faulting (safe) MSR 8578 access functions when running as Xen PV guest. The 8579 default value is controlled by CONFIG_XEN_PV_MSR_SAFE. 8580 8581 xen_nopv [X86] 8582 Disables the PV optimizations forcing the HVM guest to 8583 run as generic HVM guest with no PV drivers. 8584 This option is obsoleted by the "nopv" option, which 8585 has equivalent effect for XEN platform. 8586 8587 xen_no_vector_callback 8588 [KNL,X86,XEN,EARLY] Disable the vector callback for Xen 8589 event channel interrupts. 8590 8591 xen_scrub_pages= [XEN] 8592 Boolean option to control scrubbing pages before giving them back 8593 to Xen, for use by other domains. Can be also changed at runtime 8594 with /sys/devices/system/xen_memory/xen_memory0/scrub_pages. 8595 Default value controlled with CONFIG_XEN_SCRUB_PAGES_DEFAULT. 8596 8597 xen_timer_slop= [X86-64,XEN,EARLY] 8598 Set the timer slop (in nanoseconds) for the virtual Xen 8599 timers (default is 100000). This adjusts the minimum 8600 delta of virtualized Xen timers, where lower values 8601 improve timer resolution at the expense of processing 8602 more timer interrupts. 8603 8604 xen.balloon_boot_timeout= [XEN] 8605 The time (in seconds) to wait before giving up to boot 8606 in case initial ballooning fails to free enough memory. 8607 Applies only when running as HVM or PVH guest and 8608 started with less memory configured than allowed at 8609 max. Default is 180. 8610 8611 xen.event_eoi_delay= [XEN] 8612 How long to delay EOI handling in case of event 8613 storms (jiffies). Default is 10. 8614 8615 xen.event_loop_timeout= [XEN] 8616 After which time (jiffies) the event handling loop 8617 should start to delay EOI handling. Default is 2. 8618 8619 xen.fifo_events= [XEN] 8620 Boolean parameter to disable using fifo event handling 8621 even if available. Normally fifo event handling is 8622 preferred over the 2-level event handling, as it is 8623 fairer and the number of possible event channels is 8624 much higher. Default is on (use fifo events). 8625 8626 xirc2ps_cs= [NET,PCMCIA] 8627 Format: 8628 <irq>,<irq_mask>,<io>,<full_duplex>,<do_sound>,<lockup_hack>[,<irq2>[,<irq3>[,<irq4>]]] 8629 8630 xive= [PPC] 8631 By default on POWER9 and above, the kernel will 8632 natively use the XIVE interrupt controller. This option 8633 allows the fallback firmware mode to be used: 8634 8635 off Fallback to firmware control of XIVE interrupt 8636 controller on both pseries and powernv 8637 platforms. Only useful on POWER9 and above. 8638 8639 xive.store-eoi=off [PPC] 8640 By default on POWER10 and above, the kernel will use 8641 stores for EOI handling when the XIVE interrupt mode 8642 is active. This option allows the XIVE driver to use 8643 loads instead, as on POWER9. 8644 8645 xhci-hcd.quirks [USB,KNL] 8646 A hex value specifying bitmask with supplemental xhci 8647 host controller quirks. Meaning of each bit can be 8648 consulted in header drivers/usb/host/xhci.h. 8649 8650 xmon [PPC,EARLY] 8651 Format: { early | on | rw | ro | off } 8652 Controls if xmon debugger is enabled. Default is off. 8653 Passing only "xmon" is equivalent to "xmon=early". 8654 early Call xmon as early as possible on boot; xmon 8655 debugger is called from setup_arch(). 8656 on xmon debugger hooks will be installed so xmon 8657 is only called on a kernel crash. Default mode, 8658 i.e. either "ro" or "rw" mode, is controlled 8659 with CONFIG_XMON_DEFAULT_RO_MODE. 8660 rw xmon debugger hooks will be installed so xmon 8661 is called only on a kernel crash, mode is write, 8662 meaning SPR registers, memory and, other data 8663 can be written using xmon commands. 8664 ro same as "rw" option above but SPR registers, 8665 memory, and other data can't be written using 8666 xmon commands. 8667 off xmon is disabled. 8668