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