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