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