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