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