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