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