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