1 acpi= [HW,ACPI,X86,ARM64] 2 Advanced Configuration and Power Interface 3 Format: { force | on | off | strict | noirq | rsdt | 4 copy_dsdt } 5 force -- enable ACPI if default was off 6 on -- enable ACPI but allow fallback to DT [arm64] 7 off -- disable ACPI if default was on 8 noirq -- do not use ACPI for IRQ routing 9 strict -- Be less tolerant of platforms that are not 10 strictly ACPI specification compliant. 11 rsdt -- prefer RSDT over (default) XSDT 12 copy_dsdt -- copy DSDT to memory 13 For ARM64, ONLY "acpi=off", "acpi=on" or "acpi=force" 14 are available 15 16 See also Documentation/power/runtime_pm.rst, pci=noacpi 17 18 acpi_apic_instance= [ACPI, IOAPIC] 19 Format: <int> 20 2: use 2nd APIC table, if available 21 1,0: use 1st APIC table 22 default: 0 23 24 acpi_backlight= [HW,ACPI] 25 { vendor | video | native | none } 26 If set to vendor, prefer vendor-specific driver 27 (e.g. thinkpad_acpi, sony_acpi, etc.) instead 28 of the ACPI video.ko driver. 29 If set to video, use the ACPI video.ko driver. 30 If set to native, use the device's native backlight mode. 31 If set to none, disable the ACPI backlight interface. 32 33 acpi_force_32bit_fadt_addr 34 force FADT to use 32 bit addresses rather than the 35 64 bit X_* addresses. Some firmware have broken 64 36 bit addresses for force ACPI ignore these and use 37 the older legacy 32 bit addresses. 38 39 acpica_no_return_repair [HW, ACPI] 40 Disable AML predefined validation mechanism 41 This mechanism can repair the evaluation result to make 42 the return objects more ACPI specification compliant. 43 This option is useful for developers to identify the 44 root cause of an AML interpreter issue when the issue 45 has something to do with the repair mechanism. 46 47 acpi.debug_layer= [HW,ACPI,ACPI_DEBUG] 48 acpi.debug_level= [HW,ACPI,ACPI_DEBUG] 49 Format: <int> 50 CONFIG_ACPI_DEBUG must be enabled to produce any ACPI 51 debug output. Bits in debug_layer correspond to a 52 _COMPONENT in an ACPI source file, e.g., 53 #define _COMPONENT ACPI_PCI_COMPONENT 54 Bits in debug_level correspond to a level in 55 ACPI_DEBUG_PRINT statements, e.g., 56 ACPI_DEBUG_PRINT((ACPI_DB_INFO, ... 57 The debug_level mask defaults to "info". See 58 Documentation/firmware-guide/acpi/debug.rst for more information about 59 debug layers and levels. 60 61 Enable processor driver info messages: 62 acpi.debug_layer=0x20000000 63 Enable PCI/PCI interrupt routing info messages: 64 acpi.debug_layer=0x400000 65 Enable AML "Debug" output, i.e., stores to the Debug 66 object while interpreting AML: 67 acpi.debug_layer=0xffffffff acpi.debug_level=0x2 68 Enable all messages related to ACPI hardware: 69 acpi.debug_layer=0x2 acpi.debug_level=0xffffffff 70 71 Some values produce so much output that the system is 72 unusable. The "log_buf_len" parameter may be useful 73 if you need to capture more output. 74 75 acpi_enforce_resources= [ACPI] 76 { strict | lax | no } 77 Check for resource conflicts between native drivers 78 and ACPI OperationRegions (SystemIO and SystemMemory 79 only). IO ports and memory declared in ACPI might be 80 used by the ACPI subsystem in arbitrary AML code and 81 can interfere with legacy drivers. 82 strict (default): access to resources claimed by ACPI 83 is denied; legacy drivers trying to access reserved 84 resources will fail to bind to device using them. 85 lax: access to resources claimed by ACPI is allowed; 86 legacy drivers trying to access reserved resources 87 will bind successfully but a warning message is logged. 88 no: ACPI OperationRegions are not marked as reserved, 89 no further checks are performed. 90 91 acpi_force_table_verification [HW,ACPI] 92 Enable table checksum verification during early stage. 93 By default, this is disabled due to x86 early mapping 94 size limitation. 95 96 acpi_irq_balance [HW,ACPI] 97 ACPI will balance active IRQs 98 default in APIC mode 99 100 acpi_irq_nobalance [HW,ACPI] 101 ACPI will not move active IRQs (default) 102 default in PIC mode 103 104 acpi_irq_isa= [HW,ACPI] If irq_balance, mark listed IRQs used by ISA 105 Format: <irq>,<irq>... 106 107 acpi_irq_pci= [HW,ACPI] If irq_balance, clear listed IRQs for 108 use by PCI 109 Format: <irq>,<irq>... 110 111 acpi_mask_gpe= [HW,ACPI] 112 Due to the existence of _Lxx/_Exx, some GPEs triggered 113 by unsupported hardware/firmware features can result in 114 GPE floodings that cannot be automatically disabled by 115 the GPE dispatcher. 116 This facility can be used to prevent such uncontrolled 117 GPE floodings. 118 Format: <byte> 119 120 acpi_no_auto_serialize [HW,ACPI] 121 Disable auto-serialization of AML methods 122 AML control methods that contain the opcodes to create 123 named objects will be marked as "Serialized" by the 124 auto-serialization feature. 125 This feature is enabled by default. 126 This option allows to turn off the feature. 127 128 acpi_no_memhotplug [ACPI] Disable memory hotplug. Useful for kdump 129 kernels. 130 131 acpi_no_static_ssdt [HW,ACPI] 132 Disable installation of static SSDTs at early boot time 133 By default, SSDTs contained in the RSDT/XSDT will be 134 installed automatically and they will appear under 135 /sys/firmware/acpi/tables. 136 This option turns off this feature. 137 Note that specifying this option does not affect 138 dynamic table installation which will install SSDT 139 tables to /sys/firmware/acpi/tables/dynamic. 140 141 acpi_no_watchdog [HW,ACPI,WDT] 142 Ignore the ACPI-based watchdog interface (WDAT) and let 143 a native driver control the watchdog device instead. 144 145 acpi_rsdp= [ACPI,EFI,KEXEC] 146 Pass the RSDP address to the kernel, mostly used 147 on machines running EFI runtime service to boot the 148 second kernel for kdump. 149 150 acpi_os_name= [HW,ACPI] Tell ACPI BIOS the name of the OS 151 Format: To spoof as Windows 98: ="Microsoft Windows" 152 153 acpi_rev_override [ACPI] Override the _REV object to return 5 (instead 154 of 2 which is mandated by ACPI 6) as the supported ACPI 155 specification revision (when using this switch, it may 156 be necessary to carry out a cold reboot _twice_ in a 157 row to make it take effect on the platform firmware). 158 159 acpi_osi= [HW,ACPI] Modify list of supported OS interface strings 160 acpi_osi="string1" # add string1 161 acpi_osi="!string2" # remove string2 162 acpi_osi=!* # remove all strings 163 acpi_osi=! # disable all built-in OS vendor 164 strings 165 acpi_osi=!! # enable all built-in OS vendor 166 strings 167 acpi_osi= # disable all strings 168 169 'acpi_osi=!' can be used in combination with single or 170 multiple 'acpi_osi="string1"' to support specific OS 171 vendor string(s). Note that such command can only 172 affect the default state of the OS vendor strings, thus 173 it cannot affect the default state of the feature group 174 strings and the current state of the OS vendor strings, 175 specifying it multiple times through kernel command line 176 is meaningless. This command is useful when one do not 177 care about the state of the feature group strings which 178 should be controlled by the OSPM. 179 Examples: 180 1. 'acpi_osi=! acpi_osi="Windows 2000"' is equivalent 181 to 'acpi_osi="Windows 2000" acpi_osi=!', they all 182 can make '_OSI("Windows 2000")' TRUE. 183 184 'acpi_osi=' cannot be used in combination with other 185 'acpi_osi=' command lines, the _OSI method will not 186 exist in the ACPI namespace. NOTE that such command can 187 only affect the _OSI support state, thus specifying it 188 multiple times through kernel command line is also 189 meaningless. 190 Examples: 191 1. 'acpi_osi=' can make 'CondRefOf(_OSI, Local1)' 192 FALSE. 193 194 'acpi_osi=!*' can be used in combination with single or 195 multiple 'acpi_osi="string1"' to support specific 196 string(s). Note that such command can affect the 197 current state of both the OS vendor strings and the 198 feature group strings, thus specifying it multiple times 199 through kernel command line is meaningful. But it may 200 still not able to affect the final state of a string if 201 there are quirks related to this string. This command 202 is useful when one want to control the state of the 203 feature group strings to debug BIOS issues related to 204 the OSPM features. 205 Examples: 206 1. 'acpi_osi="Module Device" acpi_osi=!*' can make 207 '_OSI("Module Device")' FALSE. 208 2. 'acpi_osi=!* acpi_osi="Module Device"' can make 209 '_OSI("Module Device")' TRUE. 210 3. 'acpi_osi=! acpi_osi=!* acpi_osi="Windows 2000"' is 211 equivalent to 212 'acpi_osi=!* acpi_osi=! acpi_osi="Windows 2000"' 213 and 214 'acpi_osi=!* acpi_osi="Windows 2000" acpi_osi=!', 215 they all will make '_OSI("Windows 2000")' TRUE. 216 217 acpi_pm_good [X86] 218 Override the pmtimer bug detection: force the kernel 219 to assume that this machine's pmtimer latches its value 220 and always returns good values. 221 222 acpi_sci= [HW,ACPI] ACPI System Control Interrupt trigger mode 223 Format: { level | edge | high | low } 224 225 acpi_skip_timer_override [HW,ACPI] 226 Recognize and ignore IRQ0/pin2 Interrupt Override. 227 For broken nForce2 BIOS resulting in XT-PIC timer. 228 229 acpi_sleep= [HW,ACPI] Sleep options 230 Format: { s3_bios, s3_mode, s3_beep, s4_nohwsig, 231 old_ordering, nonvs, sci_force_enable, nobl } 232 See Documentation/power/video.rst for information on 233 s3_bios and s3_mode. 234 s3_beep is for debugging; it makes the PC's speaker beep 235 as soon as the kernel's real-mode entry point is called. 236 s4_nohwsig prevents ACPI hardware signature from being 237 used during resume from hibernation. 238 old_ordering causes the ACPI 1.0 ordering of the _PTS 239 control method, with respect to putting devices into 240 low power states, to be enforced (the ACPI 2.0 ordering 241 of _PTS is used by default). 242 nonvs prevents the kernel from saving/restoring the 243 ACPI NVS memory during suspend/hibernation and resume. 244 sci_force_enable causes the kernel to set SCI_EN directly 245 on resume from S1/S3 (which is against the ACPI spec, 246 but some broken systems don't work without it). 247 nobl causes the internal blacklist of systems known to 248 behave incorrectly in some ways with respect to system 249 suspend and resume to be ignored (use wisely). 250 251 acpi_use_timer_override [HW,ACPI] 252 Use timer override. For some broken Nvidia NF5 boards 253 that require a timer override, but don't have HPET 254 255 add_efi_memmap [EFI; X86] Include EFI memory map in 256 kernel's map of available physical RAM. 257 258 agp= [AGP] 259 { off | try_unsupported } 260 off: disable AGP support 261 try_unsupported: try to drive unsupported chipsets 262 (may crash computer or cause data corruption) 263 264 ALSA [HW,ALSA] 265 See Documentation/sound/alsa-configuration.rst 266 267 alignment= [KNL,ARM] 268 Allow the default userspace alignment fault handler 269 behaviour to be specified. Bit 0 enables warnings, 270 bit 1 enables fixups, and bit 2 sends a segfault. 271 272 align_va_addr= [X86-64] 273 Align virtual addresses by clearing slice [14:12] when 274 allocating a VMA at process creation time. This option 275 gives you up to 3% performance improvement on AMD F15h 276 machines (where it is enabled by default) for a 277 CPU-intensive style benchmark, and it can vary highly in 278 a microbenchmark depending on workload and compiler. 279 280 32: only for 32-bit processes 281 64: only for 64-bit processes 282 on: enable for both 32- and 64-bit processes 283 off: disable for both 32- and 64-bit processes 284 285 alloc_snapshot [FTRACE] 286 Allocate the ftrace snapshot buffer on boot up when the 287 main buffer is allocated. This is handy if debugging 288 and you need to use tracing_snapshot() on boot up, and 289 do not want to use tracing_snapshot_alloc() as it needs 290 to be done where GFP_KERNEL allocations are allowed. 291 292 amd_iommu= [HW,X86-64] 293 Pass parameters to the AMD IOMMU driver in the system. 294 Possible values are: 295 fullflush - enable flushing of IO/TLB entries when 296 they are unmapped. Otherwise they are 297 flushed before they will be reused, which 298 is a lot of faster 299 off - do not initialize any AMD IOMMU found in 300 the system 301 force_isolation - Force device isolation for all 302 devices. The IOMMU driver is not 303 allowed anymore to lift isolation 304 requirements as needed. This option 305 does not override iommu=pt 306 307 amd_iommu_dump= [HW,X86-64] 308 Enable AMD IOMMU driver option to dump the ACPI table 309 for AMD IOMMU. With this option enabled, AMD IOMMU 310 driver will print ACPI tables for AMD IOMMU during 311 IOMMU initialization. 312 313 amd_iommu_intr= [HW,X86-64] 314 Specifies one of the following AMD IOMMU interrupt 315 remapping modes: 316 legacy - Use legacy interrupt remapping mode. 317 vapic - Use virtual APIC mode, which allows IOMMU 318 to inject interrupts directly into guest. 319 This mode requires kvm-amd.avic=1. 320 (Default when IOMMU HW support is present.) 321 322 amijoy.map= [HW,JOY] Amiga joystick support 323 Map of devices attached to JOY0DAT and JOY1DAT 324 Format: <a>,<b> 325 See also Documentation/input/joydev/joystick.rst 326 327 analog.map= [HW,JOY] Analog joystick and gamepad support 328 Specifies type or capabilities of an analog joystick 329 connected to one of 16 gameports 330 Format: <type1>,<type2>,..<type16> 331 332 apc= [HW,SPARC] 333 Power management functions (SPARCstation-4/5 + deriv.) 334 Format: noidle 335 Disable APC CPU standby support. SPARCstation-Fox does 336 not play well with APC CPU idle - disable it if you have 337 APC and your system crashes randomly. 338 339 apic= [APIC,X86] Advanced Programmable Interrupt Controller 340 Change the output verbosity while booting 341 Format: { quiet (default) | verbose | debug } 342 Change the amount of debugging information output 343 when initialising the APIC and IO-APIC components. 344 For X86-32, this can also be used to specify an APIC 345 driver name. 346 Format: apic=driver_name 347 Examples: apic=bigsmp 348 349 apic_extnmi= [APIC,X86] External NMI delivery setting 350 Format: { bsp (default) | all | none } 351 bsp: External NMI is delivered only to CPU 0 352 all: External NMIs are broadcast to all CPUs as a 353 backup of CPU 0 354 none: External NMI is masked for all CPUs. This is 355 useful so that a dump capture kernel won't be 356 shot down by NMI 357 358 autoconf= [IPV6] 359 See Documentation/networking/ipv6.rst. 360 361 show_lapic= [APIC,X86] Advanced Programmable Interrupt Controller 362 Limit apic dumping. The parameter defines the maximal 363 number of local apics being dumped. Also it is possible 364 to set it to "all" by meaning -- no limit here. 365 Format: { 1 (default) | 2 | ... | all }. 366 The parameter valid if only apic=debug or 367 apic=verbose is specified. 368 Example: apic=debug show_lapic=all 369 370 apm= [APM] Advanced Power Management 371 See header of arch/x86/kernel/apm_32.c. 372 373 arcrimi= [HW,NET] ARCnet - "RIM I" (entirely mem-mapped) cards 374 Format: <io>,<irq>,<nodeID> 375 376 ataflop= [HW,M68k] 377 378 atarimouse= [HW,MOUSE] Atari Mouse 379 380 atkbd.extra= [HW] Enable extra LEDs and keys on IBM RapidAccess, 381 EzKey and similar keyboards 382 383 atkbd.reset= [HW] Reset keyboard during initialization 384 385 atkbd.set= [HW] Select keyboard code set 386 Format: <int> (2 = AT (default), 3 = PS/2) 387 388 atkbd.scroll= [HW] Enable scroll wheel on MS Office and similar 389 keyboards 390 391 atkbd.softraw= [HW] Choose between synthetic and real raw mode 392 Format: <bool> (0 = real, 1 = synthetic (default)) 393 394 atkbd.softrepeat= [HW] 395 Use software keyboard repeat 396 397 audit= [KNL] Enable the audit sub-system 398 Format: { "0" | "1" | "off" | "on" } 399 0 | off - kernel audit is disabled and can not be 400 enabled until the next reboot 401 unset - kernel audit is initialized but disabled and 402 will be fully enabled by the userspace auditd. 403 1 | on - kernel audit is initialized and partially 404 enabled, storing at most audit_backlog_limit 405 messages in RAM until it is fully enabled by the 406 userspace auditd. 407 Default: unset 408 409 audit_backlog_limit= [KNL] Set the audit queue size limit. 410 Format: <int> (must be >=0) 411 Default: 64 412 413 bau= [X86_UV] Enable the BAU on SGI UV. The default 414 behavior is to disable the BAU (i.e. bau=0). 415 Format: { "0" | "1" } 416 0 - Disable the BAU. 417 1 - Enable the BAU. 418 unset - Disable the BAU. 419 420 baycom_epp= [HW,AX25] 421 Format: <io>,<mode> 422 423 baycom_par= [HW,AX25] BayCom Parallel Port AX.25 Modem 424 Format: <io>,<mode> 425 See header of drivers/net/hamradio/baycom_par.c. 426 427 baycom_ser_fdx= [HW,AX25] 428 BayCom Serial Port AX.25 Modem (Full Duplex Mode) 429 Format: <io>,<irq>,<mode>[,<baud>] 430 See header of drivers/net/hamradio/baycom_ser_fdx.c. 431 432 baycom_ser_hdx= [HW,AX25] 433 BayCom Serial Port AX.25 Modem (Half Duplex Mode) 434 Format: <io>,<irq>,<mode> 435 See header of drivers/net/hamradio/baycom_ser_hdx.c. 436 437 blkdevparts= Manual partition parsing of block device(s) for 438 embedded devices based on command line input. 439 See Documentation/block/cmdline-partition.rst 440 441 boot_delay= Milliseconds to delay each printk during boot. 442 Values larger than 10 seconds (10000) are changed to 443 no delay (0). 444 Format: integer 445 446 bootconfig [KNL] 447 Extended command line options can be added to an initrd 448 and this will cause the kernel to look for it. 449 450 See Documentation/admin-guide/bootconfig.rst 451 452 bert_disable [ACPI] 453 Disable BERT OS support on buggy BIOSes. 454 455 bgrt_disable [ACPI][X86] 456 Disable BGRT to avoid flickering OEM logo. 457 458 bttv.card= [HW,V4L] bttv (bt848 + bt878 based grabber cards) 459 bttv.radio= Most important insmod options are available as 460 kernel args too. 461 bttv.pll= See Documentation/admin-guide/media/bttv.rst 462 bttv.tuner= 463 464 bulk_remove=off [PPC] This parameter disables the use of the pSeries 465 firmware feature for flushing multiple hpte entries 466 at a time. 467 468 c101= [NET] Moxa C101 synchronous serial card 469 470 cachesize= [BUGS=X86-32] Override level 2 CPU cache size detection. 471 Sometimes CPU hardware bugs make them report the cache 472 size incorrectly. The kernel will attempt work arounds 473 to fix known problems, but for some CPUs it is not 474 possible to determine what the correct size should be. 475 This option provides an override for these situations. 476 477 carrier_timeout= 478 [NET] Specifies amount of time (in seconds) that 479 the kernel should wait for a network carrier. By default 480 it waits 120 seconds. 481 482 ca_keys= [KEYS] This parameter identifies a specific key(s) on 483 the system trusted keyring to be used for certificate 484 trust validation. 485 format: { id:<keyid> | builtin } 486 487 cca= [MIPS] Override the kernel pages' cache coherency 488 algorithm. Accepted values range from 0 to 7 489 inclusive. See arch/mips/include/asm/pgtable-bits.h 490 for platform specific values (SB1, Loongson3 and 491 others). 492 493 ccw_timeout_log [S390] 494 See Documentation/s390/common_io.rst for details. 495 496 cgroup_disable= [KNL] Disable a particular controller 497 Format: {name of the controller(s) to disable} 498 The effects of cgroup_disable=foo are: 499 - foo isn't auto-mounted if you mount all cgroups in 500 a single hierarchy 501 - foo isn't visible as an individually mountable 502 subsystem 503 {Currently only "memory" controller deal with this and 504 cut the overhead, others just disable the usage. So 505 only cgroup_disable=memory is actually worthy} 506 507 cgroup_no_v1= [KNL] Disable cgroup controllers and named hierarchies in v1 508 Format: { { controller | "all" | "named" } 509 [,{ controller | "all" | "named" }...] } 510 Like cgroup_disable, but only applies to cgroup v1; 511 the blacklisted controllers remain available in cgroup2. 512 "all" blacklists all controllers and "named" disables 513 named mounts. Specifying both "all" and "named" disables 514 all v1 hierarchies. 515 516 cgroup.memory= [KNL] Pass options to the cgroup memory controller. 517 Format: <string> 518 nosocket -- Disable socket memory accounting. 519 nokmem -- Disable kernel memory accounting. 520 521 checkreqprot [SELINUX] Set initial checkreqprot flag value. 522 Format: { "0" | "1" } 523 See security/selinux/Kconfig help text. 524 0 -- check protection applied by kernel (includes 525 any implied execute protection). 526 1 -- check protection requested by application. 527 Default value is set via a kernel config option. 528 Value can be changed at runtime via 529 /sys/fs/selinux/checkreqprot. 530 Setting checkreqprot to 1 is deprecated. 531 532 cio_ignore= [S390] 533 See Documentation/s390/common_io.rst for details. 534 clk_ignore_unused 535 [CLK] 536 Prevents the clock framework from automatically gating 537 clocks that have not been explicitly enabled by a Linux 538 device driver but are enabled in hardware at reset or 539 by the bootloader/firmware. Note that this does not 540 force such clocks to be always-on nor does it reserve 541 those clocks in any way. This parameter is useful for 542 debug and development, but should not be needed on a 543 platform with proper driver support. For more 544 information, see Documentation/driver-api/clk.rst. 545 546 clock= [BUGS=X86-32, HW] gettimeofday clocksource override. 547 [Deprecated] 548 Forces specified clocksource (if available) to be used 549 when calculating gettimeofday(). If specified 550 clocksource is not available, it defaults to PIT. 551 Format: { pit | tsc | cyclone | pmtmr } 552 553 clocksource= Override the default clocksource 554 Format: <string> 555 Override the default clocksource and use the clocksource 556 with the name specified. 557 Some clocksource names to choose from, depending on 558 the platform: 559 [all] jiffies (this is the base, fallback clocksource) 560 [ACPI] acpi_pm 561 [ARM] imx_timer1,OSTS,netx_timer,mpu_timer2, 562 pxa_timer,timer3,32k_counter,timer0_1 563 [X86-32] pit,hpet,tsc; 564 scx200_hrt on Geode; cyclone on IBM x440 565 [MIPS] MIPS 566 [PARISC] cr16 567 [S390] tod 568 [SH] SuperH 569 [SPARC64] tick 570 [X86-64] hpet,tsc 571 572 clocksource.arm_arch_timer.evtstrm= 573 [ARM,ARM64] 574 Format: <bool> 575 Enable/disable the eventstream feature of the ARM 576 architected timer so that code using WFE-based polling 577 loops can be debugged more effectively on production 578 systems. 579 580 clearcpuid=BITNUM[,BITNUM...] [X86] 581 Disable CPUID feature X for the kernel. See 582 arch/x86/include/asm/cpufeatures.h for the valid bit 583 numbers. Note the Linux specific bits are not necessarily 584 stable over kernel options, but the vendor specific 585 ones should be. 586 Also note that user programs calling CPUID directly 587 or using the feature without checking anything 588 will still see it. This just prevents it from 589 being used by the kernel or shown in /proc/cpuinfo. 590 Also note the kernel might malfunction if you disable 591 some critical bits. 592 593 cma=nn[MG]@[start[MG][-end[MG]]] 594 [KNL,CMA] 595 Sets the size of kernel global memory area for 596 contiguous memory allocations and optionally the 597 placement constraint by the physical address range of 598 memory allocations. A value of 0 disables CMA 599 altogether. For more information, see 600 kernel/dma/contiguous.c 601 602 cma_pernuma=nn[MG] 603 [ARM64,KNL] 604 Sets the size of kernel per-numa memory area for 605 contiguous memory allocations. A value of 0 disables 606 per-numa CMA altogether. And If this option is not 607 specificed, the default value is 0. 608 With per-numa CMA enabled, DMA users on node nid will 609 first try to allocate buffer from the pernuma area 610 which is located in node nid, if the allocation fails, 611 they will fallback to the global default memory area. 612 613 cmo_free_hint= [PPC] Format: { yes | no } 614 Specify whether pages are marked as being inactive 615 when they are freed. This is used in CMO environments 616 to determine OS memory pressure for page stealing by 617 a hypervisor. 618 Default: yes 619 620 coherent_pool=nn[KMG] [ARM,KNL] 621 Sets the size of memory pool for coherent, atomic dma 622 allocations, by default set to 256K. 623 624 com20020= [HW,NET] ARCnet - COM20020 chipset 625 Format: 626 <io>[,<irq>[,<nodeID>[,<backplane>[,<ckp>[,<timeout>]]]]] 627 628 com90io= [HW,NET] ARCnet - COM90xx chipset (IO-mapped buffers) 629 Format: <io>[,<irq>] 630 631 com90xx= [HW,NET] 632 ARCnet - COM90xx chipset (memory-mapped buffers) 633 Format: <io>[,<irq>[,<memstart>]] 634 635 condev= [HW,S390] console device 636 conmode= 637 638 console= [KNL] Output console device and options. 639 640 tty<n> Use the virtual console device <n>. 641 642 ttyS<n>[,options] 643 ttyUSB0[,options] 644 Use the specified serial port. The options are of 645 the form "bbbbpnf", where "bbbb" is the baud rate, 646 "p" is parity ("n", "o", or "e"), "n" is number of 647 bits, and "f" is flow control ("r" for RTS or 648 omit it). Default is "9600n8". 649 650 See Documentation/admin-guide/serial-console.rst for more 651 information. See 652 Documentation/networking/netconsole.rst for an 653 alternative. 654 655 uart[8250],io,<addr>[,options] 656 uart[8250],mmio,<addr>[,options] 657 uart[8250],mmio16,<addr>[,options] 658 uart[8250],mmio32,<addr>[,options] 659 uart[8250],0x<addr>[,options] 660 Start an early, polled-mode console on the 8250/16550 661 UART at the specified I/O port or MMIO address, 662 switching to the matching ttyS device later. 663 MMIO inter-register address stride is either 8-bit 664 (mmio), 16-bit (mmio16), or 32-bit (mmio32). 665 If none of [io|mmio|mmio16|mmio32], <addr> is assumed 666 to be equivalent to 'mmio'. 'options' are specified in 667 the same format described for ttyS above; if unspecified, 668 the h/w is not re-initialized. 669 670 hvc<n> Use the hypervisor console device <n>. This is for 671 both Xen and PowerPC hypervisors. 672 673 If the device connected to the port is not a TTY but a braille 674 device, prepend "brl," before the device type, for instance 675 console=brl,ttyS0 676 For now, only VisioBraille is supported. 677 678 console_msg_format= 679 [KNL] Change console messages format 680 default 681 By default we print messages on consoles in 682 "[time stamp] text\n" format (time stamp may not be 683 printed, depending on CONFIG_PRINTK_TIME or 684 `printk_time' param). 685 syslog 686 Switch to syslog format: "<%u>[time stamp] text\n" 687 IOW, each message will have a facility and loglevel 688 prefix. The format is similar to one used by syslog() 689 syscall, or to executing "dmesg -S --raw" or to reading 690 from /proc/kmsg. 691 692 consoleblank= [KNL] The console blank (screen saver) timeout in 693 seconds. A value of 0 disables the blank timer. 694 Defaults to 0. 695 696 coredump_filter= 697 [KNL] Change the default value for 698 /proc/<pid>/coredump_filter. 699 See also Documentation/filesystems/proc.rst. 700 701 coresight_cpu_debug.enable 702 [ARM,ARM64] 703 Format: <bool> 704 Enable/disable the CPU sampling based debugging. 705 0: default value, disable debugging 706 1: enable debugging at boot time 707 708 cpuidle.off=1 [CPU_IDLE] 709 disable the cpuidle sub-system 710 711 cpuidle.governor= 712 [CPU_IDLE] Name of the cpuidle governor to use. 713 714 cpufreq.off=1 [CPU_FREQ] 715 disable the cpufreq sub-system 716 717 cpufreq.default_governor= 718 [CPU_FREQ] Name of the default cpufreq governor or 719 policy to use. This governor must be registered in the 720 kernel before the cpufreq driver probes. 721 722 cpu_init_udelay=N 723 [X86] Delay for N microsec between assert and de-assert 724 of APIC INIT to start processors. This delay occurs 725 on every CPU online, such as boot, and resume from suspend. 726 Default: 10000 727 728 cpcihp_generic= [HW,PCI] Generic port I/O CompactPCI driver 729 Format: 730 <first_slot>,<last_slot>,<port>,<enum_bit>[,<debug>] 731 732 crashkernel=size[KMG][@offset[KMG]] 733 [KNL] Using kexec, Linux can switch to a 'crash kernel' 734 upon panic. This parameter reserves the physical 735 memory region [offset, offset + size] for that kernel 736 image. If '@offset' is omitted, then a suitable offset 737 is selected automatically. 738 [KNL, X86-64] Select a region under 4G first, and 739 fall back to reserve region above 4G when '@offset' 740 hasn't been specified. 741 See Documentation/admin-guide/kdump/kdump.rst for further details. 742 743 crashkernel=range1:size1[,range2:size2,...][@offset] 744 [KNL] Same as above, but depends on the memory 745 in the running system. The syntax of range is 746 start-[end] where start and end are both 747 a memory unit (amount[KMG]). See also 748 Documentation/admin-guide/kdump/kdump.rst for an example. 749 750 crashkernel=size[KMG],high 751 [KNL, X86-64] range could be above 4G. Allow kernel 752 to allocate physical memory region from top, so could 753 be above 4G if system have more than 4G ram installed. 754 Otherwise memory region will be allocated below 4G, if 755 available. 756 It will be ignored if crashkernel=X is specified. 757 crashkernel=size[KMG],low 758 [KNL, X86-64] range under 4G. When crashkernel=X,high 759 is passed, kernel could allocate physical memory region 760 above 4G, that cause second kernel crash on system 761 that require some amount of low memory, e.g. swiotlb 762 requires at least 64M+32K low memory, also enough extra 763 low memory is needed to make sure DMA buffers for 32-bit 764 devices won't run out. Kernel would try to allocate at 765 at least 256M below 4G automatically. 766 This one let user to specify own low range under 4G 767 for second kernel instead. 768 0: to disable low allocation. 769 It will be ignored when crashkernel=X,high is not used 770 or memory reserved is below 4G. 771 772 cryptomgr.notests 773 [KNL] Disable crypto self-tests 774 775 cs89x0_dma= [HW,NET] 776 Format: <dma> 777 778 cs89x0_media= [HW,NET] 779 Format: { rj45 | aui | bnc } 780 781 dasd= [HW,NET] 782 See header of drivers/s390/block/dasd_devmap.c. 783 784 db9.dev[2|3]= [HW,JOY] Multisystem joystick support via parallel port 785 (one device per port) 786 Format: <port#>,<type> 787 See also Documentation/input/devices/joystick-parport.rst 788 789 ddebug_query= [KNL,DYNAMIC_DEBUG] Enable debug messages at early boot 790 time. See 791 Documentation/admin-guide/dynamic-debug-howto.rst for 792 details. Deprecated, see dyndbg. 793 794 debug [KNL] Enable kernel debugging (events log level). 795 796 debug_boot_weak_hash 797 [KNL] Enable printing [hashed] pointers early in the 798 boot sequence. If enabled, we use a weak hash instead 799 of siphash to hash pointers. Use this option if you are 800 seeing instances of '(___ptrval___)') and need to see a 801 value (hashed pointer) instead. Cryptographically 802 insecure, please do not use on production kernels. 803 804 debug_locks_verbose= 805 [KNL] verbose self-tests 806 Format=<0|1> 807 Print debugging info while doing the locking API 808 self-tests. 809 We default to 0 (no extra messages), setting it to 810 1 will print _a lot_ more information - normally 811 only useful to kernel developers. 812 813 debug_objects [KNL] Enable object debugging 814 815 no_debug_objects 816 [KNL] Disable object debugging 817 818 debug_guardpage_minorder= 819 [KNL] When CONFIG_DEBUG_PAGEALLOC is set, this 820 parameter allows control of the order of pages that will 821 be intentionally kept free (and hence protected) by the 822 buddy allocator. Bigger value increase the probability 823 of catching random memory corruption, but reduce the 824 amount of memory for normal system use. The maximum 825 possible value is MAX_ORDER/2. Setting this parameter 826 to 1 or 2 should be enough to identify most random 827 memory corruption problems caused by bugs in kernel or 828 driver code when a CPU writes to (or reads from) a 829 random memory location. Note that there exists a class 830 of memory corruptions problems caused by buggy H/W or 831 F/W or by drivers badly programing DMA (basically when 832 memory is written at bus level and the CPU MMU is 833 bypassed) which are not detectable by 834 CONFIG_DEBUG_PAGEALLOC, hence this option will not help 835 tracking down these problems. 836 837 debug_pagealloc= 838 [KNL] When CONFIG_DEBUG_PAGEALLOC is set, this parameter 839 enables the feature at boot time. By default, it is 840 disabled and the system will work mostly the same as a 841 kernel built without CONFIG_DEBUG_PAGEALLOC. 842 Note: to get most of debug_pagealloc error reports, it's 843 useful to also enable the page_owner functionality. 844 on: enable the feature 845 846 debugfs= [KNL] This parameter enables what is exposed to userspace 847 and debugfs internal clients. 848 Format: { on, no-mount, off } 849 on: All functions are enabled. 850 no-mount: 851 Filesystem is not registered but kernel clients can 852 access APIs and a crashkernel can be used to read 853 its content. There is nothing to mount. 854 off: Filesystem is not registered and clients 855 get a -EPERM as result when trying to register files 856 or directories within debugfs. 857 This is equivalent of the runtime functionality if 858 debugfs was not enabled in the kernel at all. 859 Default value is set in build-time with a kernel configuration. 860 861 debugpat [X86] Enable PAT debugging 862 863 decnet.addr= [HW,NET] 864 Format: <area>[,<node>] 865 See also Documentation/networking/decnet.rst. 866 867 default_hugepagesz= 868 [HW] The size of the default HugeTLB page. This is 869 the size represented by the legacy /proc/ hugepages 870 APIs. In addition, this is the default hugetlb size 871 used for shmget(), mmap() and mounting hugetlbfs 872 filesystems. If not specified, defaults to the 873 architecture's default huge page size. Huge page 874 sizes are architecture dependent. See also 875 Documentation/admin-guide/mm/hugetlbpage.rst. 876 Format: size[KMG] 877 878 deferred_probe_timeout= 879 [KNL] Debugging option to set a timeout in seconds for 880 deferred probe to give up waiting on dependencies to 881 probe. Only specific dependencies (subsystems or 882 drivers) that have opted in will be ignored. A timeout of 0 883 will timeout at the end of initcalls. This option will also 884 dump out devices still on the deferred probe list after 885 retrying. 886 887 dfltcc= [HW,S390] 888 Format: { on | off | def_only | inf_only | always } 889 on: s390 zlib hardware support for compression on 890 level 1 and decompression (default) 891 off: No s390 zlib hardware support 892 def_only: s390 zlib hardware support for deflate 893 only (compression on level 1) 894 inf_only: s390 zlib hardware support for inflate 895 only (decompression) 896 always: Same as 'on' but ignores the selected compression 897 level always using hardware support (used for debugging) 898 899 dhash_entries= [KNL] 900 Set number of hash buckets for dentry cache. 901 902 disable_1tb_segments [PPC] 903 Disables the use of 1TB hash page table segments. This 904 causes the kernel to fall back to 256MB segments which 905 can be useful when debugging issues that require an SLB 906 miss to occur. 907 908 stress_slb [PPC] 909 Limits the number of kernel SLB entries, and flushes 910 them frequently to increase the rate of SLB faults 911 on kernel addresses. 912 913 disable= [IPV6] 914 See Documentation/networking/ipv6.rst. 915 916 hardened_usercopy= 917 [KNL] Under CONFIG_HARDENED_USERCOPY, whether 918 hardening is enabled for this boot. Hardened 919 usercopy checking is used to protect the kernel 920 from reading or writing beyond known memory 921 allocation boundaries as a proactive defense 922 against bounds-checking flaws in the kernel's 923 copy_to_user()/copy_from_user() interface. 924 on Perform hardened usercopy checks (default). 925 off Disable hardened usercopy checks. 926 927 disable_radix [PPC] 928 Disable RADIX MMU mode on POWER9 929 930 radix_hcall_invalidate=on [PPC/PSERIES] 931 Disable RADIX GTSE feature and use hcall for TLB 932 invalidate. 933 934 disable_tlbie [PPC] 935 Disable TLBIE instruction. Currently does not work 936 with KVM, with HASH MMU, or with coherent accelerators. 937 938 disable_cpu_apicid= [X86,APIC,SMP] 939 Format: <int> 940 The number of initial APIC ID for the 941 corresponding CPU to be disabled at boot, 942 mostly used for the kdump 2nd kernel to 943 disable BSP to wake up multiple CPUs without 944 causing system reset or hang due to sending 945 INIT from AP to BSP. 946 947 perf_v4_pmi= [X86,INTEL] 948 Format: <bool> 949 Disable Intel PMU counter freezing feature. 950 The feature only exists starting from 951 Arch Perfmon v4 (Skylake and newer). 952 953 disable_ddw [PPC/PSERIES] 954 Disable Dynamic DMA Window support. Use this 955 to workaround buggy firmware. 956 957 disable_ipv6= [IPV6] 958 See Documentation/networking/ipv6.rst. 959 960 disable_mtrr_cleanup [X86] 961 The kernel tries to adjust MTRR layout from continuous 962 to discrete, to make X server driver able to add WB 963 entry later. This parameter disables that. 964 965 disable_mtrr_trim [X86, Intel and AMD only] 966 By default the kernel will trim any uncacheable 967 memory out of your available memory pool based on 968 MTRR settings. This parameter disables that behavior, 969 possibly causing your machine to run very slowly. 970 971 disable_timer_pin_1 [X86] 972 Disable PIN 1 of APIC timer 973 Can be useful to work around chipset bugs. 974 975 dis_ucode_ldr [X86] Disable the microcode loader. 976 977 dma_debug=off If the kernel is compiled with DMA_API_DEBUG support, 978 this option disables the debugging code at boot. 979 980 dma_debug_entries=<number> 981 This option allows to tune the number of preallocated 982 entries for DMA-API debugging code. One entry is 983 required per DMA-API allocation. Use this if the 984 DMA-API debugging code disables itself because the 985 architectural default is too low. 986 987 dma_debug_driver=<driver_name> 988 With this option the DMA-API debugging driver 989 filter feature can be enabled at boot time. Just 990 pass the driver to filter for as the parameter. 991 The filter can be disabled or changed to another 992 driver later using sysfs. 993 994 driver_async_probe= [KNL] 995 List of driver names to be probed asynchronously. 996 Format: <driver_name1>,<driver_name2>... 997 998 drm.edid_firmware=[<connector>:]<file>[,[<connector>:]<file>] 999 Broken monitors, graphic adapters, KVMs and EDIDless 1000 panels may send no or incorrect EDID data sets. 1001 This parameter allows to specify an EDID data sets 1002 in the /lib/firmware directory that are used instead. 1003 Generic built-in EDID data sets are used, if one of 1004 edid/1024x768.bin, edid/1280x1024.bin, 1005 edid/1680x1050.bin, or edid/1920x1080.bin is given 1006 and no file with the same name exists. Details and 1007 instructions how to build your own EDID data are 1008 available in Documentation/admin-guide/edid.rst. An EDID 1009 data set will only be used for a particular connector, 1010 if its name and a colon are prepended to the EDID 1011 name. Each connector may use a unique EDID data 1012 set by separating the files with a comma. An EDID 1013 data set with no connector name will be used for 1014 any connectors not explicitly specified. 1015 1016 dscc4.setup= [NET] 1017 1018 dt_cpu_ftrs= [PPC] 1019 Format: {"off" | "known"} 1020 Control how the dt_cpu_ftrs device-tree binding is 1021 used for CPU feature discovery and setup (if it 1022 exists). 1023 off: Do not use it, fall back to legacy cpu table. 1024 known: Do not pass through unknown features to guests 1025 or userspace, only those that the kernel is aware of. 1026 1027 dump_apple_properties [X86] 1028 Dump name and content of EFI device properties on 1029 x86 Macs. Useful for driver authors to determine 1030 what data is available or for reverse-engineering. 1031 1032 dyndbg[="val"] [KNL,DYNAMIC_DEBUG] 1033 <module>.dyndbg[="val"] 1034 Enable debug messages at boot time. See 1035 Documentation/admin-guide/dynamic-debug-howto.rst 1036 for details. 1037 1038 nopku [X86] Disable Memory Protection Keys CPU feature found 1039 in some Intel CPUs. 1040 1041 <module>.async_probe [KNL] 1042 Enable asynchronous probe on this module. 1043 1044 early_ioremap_debug [KNL] 1045 Enable debug messages in early_ioremap support. This 1046 is useful for tracking down temporary early mappings 1047 which are not unmapped. 1048 1049 earlycon= [KNL] Output early console device and options. 1050 1051 When used with no options, the early console is 1052 determined by stdout-path property in device tree's 1053 chosen node or the ACPI SPCR table if supported by 1054 the platform. 1055 1056 cdns,<addr>[,options] 1057 Start an early, polled-mode console on a Cadence 1058 (xuartps) serial port at the specified address. Only 1059 supported option is baud rate. If baud rate is not 1060 specified, the serial port must already be setup and 1061 configured. 1062 1063 uart[8250],io,<addr>[,options] 1064 uart[8250],mmio,<addr>[,options] 1065 uart[8250],mmio32,<addr>[,options] 1066 uart[8250],mmio32be,<addr>[,options] 1067 uart[8250],0x<addr>[,options] 1068 Start an early, polled-mode console on the 8250/16550 1069 UART at the specified I/O port or MMIO address. 1070 MMIO inter-register address stride is either 8-bit 1071 (mmio) or 32-bit (mmio32 or mmio32be). 1072 If none of [io|mmio|mmio32|mmio32be], <addr> is assumed 1073 to be equivalent to 'mmio'. 'options' are specified 1074 in the same format described for "console=ttyS<n>"; if 1075 unspecified, the h/w is not initialized. 1076 1077 pl011,<addr> 1078 pl011,mmio32,<addr> 1079 Start an early, polled-mode console on a pl011 serial 1080 port at the specified address. The pl011 serial port 1081 must already be setup and configured. Options are not 1082 yet supported. If 'mmio32' is specified, then only 1083 the driver will use only 32-bit accessors to read/write 1084 the device registers. 1085 1086 meson,<addr> 1087 Start an early, polled-mode console on a meson serial 1088 port at the specified address. The serial port must 1089 already be setup and configured. Options are not yet 1090 supported. 1091 1092 msm_serial,<addr> 1093 Start an early, polled-mode console on an msm serial 1094 port at the specified address. The serial port 1095 must already be setup and configured. Options are not 1096 yet supported. 1097 1098 msm_serial_dm,<addr> 1099 Start an early, polled-mode console on an msm serial 1100 dm port at the specified address. The serial port 1101 must already be setup and configured. Options are not 1102 yet supported. 1103 1104 owl,<addr> 1105 Start an early, polled-mode console on a serial port 1106 of an Actions Semi SoC, such as S500 or S900, at the 1107 specified address. The serial port must already be 1108 setup and configured. Options are not yet supported. 1109 1110 rda,<addr> 1111 Start an early, polled-mode console on a serial port 1112 of an RDA Micro SoC, such as RDA8810PL, at the 1113 specified address. The serial port must already be 1114 setup and configured. Options are not yet supported. 1115 1116 sbi 1117 Use RISC-V SBI (Supervisor Binary Interface) for early 1118 console. 1119 1120 smh Use ARM semihosting calls for early console. 1121 1122 s3c2410,<addr> 1123 s3c2412,<addr> 1124 s3c2440,<addr> 1125 s3c6400,<addr> 1126 s5pv210,<addr> 1127 exynos4210,<addr> 1128 Use early console provided by serial driver available 1129 on Samsung SoCs, requires selecting proper type and 1130 a correct base address of the selected UART port. The 1131 serial port must already be setup and configured. 1132 Options are not yet supported. 1133 1134 lantiq,<addr> 1135 Start an early, polled-mode console on a lantiq serial 1136 (lqasc) port at the specified address. The serial port 1137 must already be setup and configured. Options are not 1138 yet supported. 1139 1140 lpuart,<addr> 1141 lpuart32,<addr> 1142 Use early console provided by Freescale LP UART driver 1143 found on Freescale Vybrid and QorIQ LS1021A processors. 1144 A valid base address must be provided, and the serial 1145 port must already be setup and configured. 1146 1147 ec_imx21,<addr> 1148 ec_imx6q,<addr> 1149 Start an early, polled-mode, output-only console on the 1150 Freescale i.MX UART at the specified address. The UART 1151 must already be setup and configured. 1152 1153 ar3700_uart,<addr> 1154 Start an early, polled-mode console on the 1155 Armada 3700 serial port at the specified 1156 address. The serial port must already be setup 1157 and configured. Options are not yet supported. 1158 1159 qcom_geni,<addr> 1160 Start an early, polled-mode console on a Qualcomm 1161 Generic Interface (GENI) based serial port at the 1162 specified address. The serial port must already be 1163 setup and configured. Options are not yet supported. 1164 1165 efifb,[options] 1166 Start an early, unaccelerated console on the EFI 1167 memory mapped framebuffer (if available). On cache 1168 coherent non-x86 systems that use system memory for 1169 the framebuffer, pass the 'ram' option so that it is 1170 mapped with the correct attributes. 1171 1172 linflex,<addr> 1173 Use early console provided by Freescale LINFlexD UART 1174 serial driver for NXP S32V234 SoCs. A valid base 1175 address must be provided, and the serial port must 1176 already be setup and configured. 1177 1178 earlyprintk= [X86,SH,ARM,M68k,S390] 1179 earlyprintk=vga 1180 earlyprintk=sclp 1181 earlyprintk=xen 1182 earlyprintk=serial[,ttySn[,baudrate]] 1183 earlyprintk=serial[,0x...[,baudrate]] 1184 earlyprintk=ttySn[,baudrate] 1185 earlyprintk=dbgp[debugController#] 1186 earlyprintk=pciserial[,force],bus:device.function[,baudrate] 1187 earlyprintk=xdbc[xhciController#] 1188 1189 earlyprintk is useful when the kernel crashes before 1190 the normal console is initialized. It is not enabled by 1191 default because it has some cosmetic problems. 1192 1193 Append ",keep" to not disable it when the real console 1194 takes over. 1195 1196 Only one of vga, efi, serial, or usb debug port can 1197 be used at a time. 1198 1199 Currently only ttyS0 and ttyS1 may be specified by 1200 name. Other I/O ports may be explicitly specified 1201 on some architectures (x86 and arm at least) by 1202 replacing ttySn with an I/O port address, like this: 1203 earlyprintk=serial,0x1008,115200 1204 You can find the port for a given device in 1205 /proc/tty/driver/serial: 1206 2: uart:ST16650V2 port:00001008 irq:18 ... 1207 1208 Interaction with the standard serial driver is not 1209 very good. 1210 1211 The VGA and EFI output is eventually overwritten by 1212 the real console. 1213 1214 The xen output can only be used by Xen PV guests. 1215 1216 The sclp output can only be used on s390. 1217 1218 The optional "force" to "pciserial" enables use of a 1219 PCI device even when its classcode is not of the 1220 UART class. 1221 1222 edac_report= [HW,EDAC] Control how to report EDAC event 1223 Format: {"on" | "off" | "force"} 1224 on: enable EDAC to report H/W event. May be overridden 1225 by other higher priority error reporting module. 1226 off: disable H/W event reporting through EDAC. 1227 force: enforce the use of EDAC to report H/W event. 1228 default: on. 1229 1230 ekgdboc= [X86,KGDB] Allow early kernel console debugging 1231 ekgdboc=kbd 1232 1233 This is designed to be used in conjunction with 1234 the boot argument: earlyprintk=vga 1235 1236 This parameter works in place of the kgdboc parameter 1237 but can only be used if the backing tty is available 1238 very early in the boot process. For early debugging 1239 via a serial port see kgdboc_earlycon instead. 1240 1241 edd= [EDD] 1242 Format: {"off" | "on" | "skip[mbr]"} 1243 1244 efi= [EFI] 1245 Format: { "debug", "disable_early_pci_dma", 1246 "nochunk", "noruntime", "nosoftreserve", 1247 "novamap", "no_disable_early_pci_dma" } 1248 debug: enable misc debug output. 1249 disable_early_pci_dma: disable the busmaster bit on all 1250 PCI bridges while in the EFI boot stub. 1251 nochunk: disable reading files in "chunks" in the EFI 1252 boot stub, as chunking can cause problems with some 1253 firmware implementations. 1254 noruntime : disable EFI runtime services support 1255 nosoftreserve: The EFI_MEMORY_SP (Specific Purpose) 1256 attribute may cause the kernel to reserve the 1257 memory range for a memory mapping driver to 1258 claim. Specify efi=nosoftreserve to disable this 1259 reservation and treat the memory by its base type 1260 (i.e. EFI_CONVENTIONAL_MEMORY / "System RAM"). 1261 novamap: do not call SetVirtualAddressMap(). 1262 no_disable_early_pci_dma: Leave the busmaster bit set 1263 on all PCI bridges while in the EFI boot stub 1264 1265 efi_no_storage_paranoia [EFI; X86] 1266 Using this parameter you can use more than 50% of 1267 your efi variable storage. Use this parameter only if 1268 you are really sure that your UEFI does sane gc and 1269 fulfills the spec otherwise your board may brick. 1270 1271 efi_fake_mem= nn[KMG]@ss[KMG]:aa[,nn[KMG]@ss[KMG]:aa,..] [EFI; X86] 1272 Add arbitrary attribute to specific memory range by 1273 updating original EFI memory map. 1274 Region of memory which aa attribute is added to is 1275 from ss to ss+nn. 1276 1277 If efi_fake_mem=2G@4G:0x10000,2G@0x10a0000000:0x10000 1278 is specified, EFI_MEMORY_MORE_RELIABLE(0x10000) 1279 attribute is added to range 0x100000000-0x180000000 and 1280 0x10a0000000-0x1120000000. 1281 1282 If efi_fake_mem=8G@9G:0x40000 is specified, the 1283 EFI_MEMORY_SP(0x40000) attribute is added to 1284 range 0x240000000-0x43fffffff. 1285 1286 Using this parameter you can do debugging of EFI memmap 1287 related features. For example, you can do debugging of 1288 Address Range Mirroring feature even if your box 1289 doesn't support it, or mark specific memory as 1290 "soft reserved". 1291 1292 efivar_ssdt= [EFI; X86] Name of an EFI variable that contains an SSDT 1293 that is to be dynamically loaded by Linux. If there are 1294 multiple variables with the same name but with different 1295 vendor GUIDs, all of them will be loaded. See 1296 Documentation/admin-guide/acpi/ssdt-overlays.rst for details. 1297 1298 1299 eisa_irq_edge= [PARISC,HW] 1300 See header of drivers/parisc/eisa.c. 1301 1302 elanfreq= [X86-32] 1303 See comment before function elanfreq_setup() in 1304 arch/x86/kernel/cpu/cpufreq/elanfreq.c. 1305 1306 elfcorehdr=[size[KMG]@]offset[KMG] [IA64,PPC,SH,X86,S390] 1307 Specifies physical address of start of kernel core 1308 image elf header and optionally the size. Generally 1309 kexec loader will pass this option to capture kernel. 1310 See Documentation/admin-guide/kdump/kdump.rst for details. 1311 1312 enable_mtrr_cleanup [X86] 1313 The kernel tries to adjust MTRR layout from continuous 1314 to discrete, to make X server driver able to add WB 1315 entry later. This parameter enables that. 1316 1317 enable_timer_pin_1 [X86] 1318 Enable PIN 1 of APIC timer 1319 Can be useful to work around chipset bugs 1320 (in particular on some ATI chipsets). 1321 The kernel tries to set a reasonable default. 1322 1323 enforcing [SELINUX] Set initial enforcing status. 1324 Format: {"0" | "1"} 1325 See security/selinux/Kconfig help text. 1326 0 -- permissive (log only, no denials). 1327 1 -- enforcing (deny and log). 1328 Default value is 0. 1329 Value can be changed at runtime via 1330 /sys/fs/selinux/enforce. 1331 1332 erst_disable [ACPI] 1333 Disable Error Record Serialization Table (ERST) 1334 support. 1335 1336 ether= [HW,NET] Ethernet cards parameters 1337 This option is obsoleted by the "netdev=" option, which 1338 has equivalent usage. See its documentation for details. 1339 1340 evm= [EVM] 1341 Format: { "fix" } 1342 Permit 'security.evm' to be updated regardless of 1343 current integrity status. 1344 1345 failslab= 1346 fail_usercopy= 1347 fail_page_alloc= 1348 fail_make_request=[KNL] 1349 General fault injection mechanism. 1350 Format: <interval>,<probability>,<space>,<times> 1351 See also Documentation/fault-injection/. 1352 1353 fb_tunnels= [NET] 1354 Format: { initns | none } 1355 See Documentation/admin-guide/sysctl/net.rst for 1356 fb_tunnels_only_for_init_ns 1357 1358 floppy= [HW] 1359 See Documentation/admin-guide/blockdev/floppy.rst. 1360 1361 force_pal_cache_flush 1362 [IA-64] Avoid check_sal_cache_flush which may hang on 1363 buggy SAL_CACHE_FLUSH implementations. Using this 1364 parameter will force ia64_sal_cache_flush to call 1365 ia64_pal_cache_flush instead of SAL_CACHE_FLUSH. 1366 1367 forcepae [X86-32] 1368 Forcefully enable Physical Address Extension (PAE). 1369 Many Pentium M systems disable PAE but may have a 1370 functionally usable PAE implementation. 1371 Warning: use of this parameter will taint the kernel 1372 and may cause unknown problems. 1373 1374 ftrace=[tracer] 1375 [FTRACE] will set and start the specified tracer 1376 as early as possible in order to facilitate early 1377 boot debugging. 1378 1379 ftrace_dump_on_oops[=orig_cpu] 1380 [FTRACE] will dump the trace buffers on oops. 1381 If no parameter is passed, ftrace will dump 1382 buffers of all CPUs, but if you pass orig_cpu, it will 1383 dump only the buffer of the CPU that triggered the 1384 oops. 1385 1386 ftrace_filter=[function-list] 1387 [FTRACE] Limit the functions traced by the function 1388 tracer at boot up. function-list is a comma-separated 1389 list of functions. This list can be changed at run 1390 time by the set_ftrace_filter file in the debugfs 1391 tracing directory. 1392 1393 ftrace_notrace=[function-list] 1394 [FTRACE] Do not trace the functions specified in 1395 function-list. This list can be changed at run time 1396 by the set_ftrace_notrace file in the debugfs 1397 tracing directory. 1398 1399 ftrace_graph_filter=[function-list] 1400 [FTRACE] Limit the top level callers functions traced 1401 by the function graph tracer at boot up. 1402 function-list is a comma-separated list of functions 1403 that can be changed at run time by the 1404 set_graph_function file in the debugfs tracing directory. 1405 1406 ftrace_graph_notrace=[function-list] 1407 [FTRACE] Do not trace from the functions specified in 1408 function-list. This list is a comma-separated list of 1409 functions that can be changed at run time by the 1410 set_graph_notrace file in the debugfs tracing directory. 1411 1412 ftrace_graph_max_depth=<uint> 1413 [FTRACE] Used with the function graph tracer. This is 1414 the max depth it will trace into a function. This value 1415 can be changed at run time by the max_graph_depth file 1416 in the tracefs tracing directory. default: 0 (no limit) 1417 1418 fw_devlink= [KNL] Create device links between consumer and supplier 1419 devices by scanning the firmware to infer the 1420 consumer/supplier relationships. This feature is 1421 especially useful when drivers are loaded as modules as 1422 it ensures proper ordering of tasks like device probing 1423 (suppliers first, then consumers), supplier boot state 1424 clean up (only after all consumers have probed), 1425 suspend/resume & runtime PM (consumers first, then 1426 suppliers). 1427 Format: { off | permissive | on | rpm } 1428 off -- Don't create device links from firmware info. 1429 permissive -- Create device links from firmware info 1430 but use it only for ordering boot state clean 1431 up (sync_state() calls). 1432 on -- Create device links from firmware info and use it 1433 to enforce probe and suspend/resume ordering. 1434 rpm -- Like "on", but also use to order runtime PM. 1435 1436 gamecon.map[2|3]= 1437 [HW,JOY] Multisystem joystick and NES/SNES/PSX pad 1438 support via parallel port (up to 5 devices per port) 1439 Format: <port#>,<pad1>,<pad2>,<pad3>,<pad4>,<pad5> 1440 See also Documentation/input/devices/joystick-parport.rst 1441 1442 gamma= [HW,DRM] 1443 1444 gart_fix_e820= [X86-64] disable the fix e820 for K8 GART 1445 Format: off | on 1446 default: on 1447 1448 gcov_persist= [GCOV] When non-zero (default), profiling data for 1449 kernel modules is saved and remains accessible via 1450 debugfs, even when the module is unloaded/reloaded. 1451 When zero, profiling data is discarded and associated 1452 debugfs files are removed at module unload time. 1453 1454 goldfish [X86] Enable the goldfish android emulator platform. 1455 Don't use this when you are not running on the 1456 android emulator 1457 1458 gpt [EFI] Forces disk with valid GPT signature but 1459 invalid Protective MBR to be treated as GPT. If the 1460 primary GPT is corrupted, it enables the backup/alternate 1461 GPT to be used instead. 1462 1463 grcan.enable0= [HW] Configuration of physical interface 0. Determines 1464 the "Enable 0" bit of the configuration register. 1465 Format: 0 | 1 1466 Default: 0 1467 grcan.enable1= [HW] Configuration of physical interface 1. Determines 1468 the "Enable 0" bit of the configuration register. 1469 Format: 0 | 1 1470 Default: 0 1471 grcan.select= [HW] Select which physical interface to use. 1472 Format: 0 | 1 1473 Default: 0 1474 grcan.txsize= [HW] Sets the size of the tx buffer. 1475 Format: <unsigned int> such that (txsize & ~0x1fffc0) == 0. 1476 Default: 1024 1477 grcan.rxsize= [HW] Sets the size of the rx buffer. 1478 Format: <unsigned int> such that (rxsize & ~0x1fffc0) == 0. 1479 Default: 1024 1480 1481 gpio-mockup.gpio_mockup_ranges 1482 [HW] Sets the ranges of gpiochip of for this device. 1483 Format: <start1>,<end1>,<start2>,<end2>... 1484 1485 hardlockup_all_cpu_backtrace= 1486 [KNL] Should the hard-lockup detector generate 1487 backtraces on all cpus. 1488 Format: 0 | 1 1489 1490 hashdist= [KNL,NUMA] Large hashes allocated during boot 1491 are distributed across NUMA nodes. Defaults on 1492 for 64-bit NUMA, off otherwise. 1493 Format: 0 | 1 (for off | on) 1494 1495 hcl= [IA-64] SGI's Hardware Graph compatibility layer 1496 1497 hd= [EIDE] (E)IDE hard drive subsystem geometry 1498 Format: <cyl>,<head>,<sect> 1499 1500 hest_disable [ACPI] 1501 Disable Hardware Error Source Table (HEST) support; 1502 corresponding firmware-first mode error processing 1503 logic will be disabled. 1504 1505 highmem=nn[KMG] [KNL,BOOT] forces the highmem zone to have an exact 1506 size of <nn>. This works even on boxes that have no 1507 highmem otherwise. This also works to reduce highmem 1508 size on bigger boxes. 1509 1510 highres= [KNL] Enable/disable high resolution timer mode. 1511 Valid parameters: "on", "off" 1512 Default: "on" 1513 1514 hlt [BUGS=ARM,SH] 1515 1516 hpet= [X86-32,HPET] option to control HPET usage 1517 Format: { enable (default) | disable | force | 1518 verbose } 1519 disable: disable HPET and use PIT instead 1520 force: allow force enabled of undocumented chips (ICH4, 1521 VIA, nVidia) 1522 verbose: show contents of HPET registers during setup 1523 1524 hpet_mmap= [X86, HPET_MMAP] Allow userspace to mmap HPET 1525 registers. Default set by CONFIG_HPET_MMAP_DEFAULT. 1526 1527 hugetlb_cma= [HW] The size of a cma area used for allocation 1528 of gigantic hugepages. 1529 Format: nn[KMGTPE] 1530 1531 Reserve a cma area of given size and allocate gigantic 1532 hugepages using the cma allocator. If enabled, the 1533 boot-time allocation of gigantic hugepages is skipped. 1534 1535 hugepages= [HW] Number of HugeTLB pages to allocate at boot. 1536 If this follows hugepagesz (below), it specifies 1537 the number of pages of hugepagesz to be allocated. 1538 If this is the first HugeTLB parameter on the command 1539 line, it specifies the number of pages to allocate for 1540 the default huge page size. See also 1541 Documentation/admin-guide/mm/hugetlbpage.rst. 1542 Format: <integer> 1543 1544 hugepagesz= 1545 [HW] The size of the HugeTLB pages. This is used in 1546 conjunction with hugepages (above) to allocate huge 1547 pages of a specific size at boot. The pair 1548 hugepagesz=X hugepages=Y can be specified once for 1549 each supported huge page size. Huge page sizes are 1550 architecture dependent. See also 1551 Documentation/admin-guide/mm/hugetlbpage.rst. 1552 Format: size[KMG] 1553 1554 hung_task_panic= 1555 [KNL] Should the hung task detector generate panics. 1556 Format: 0 | 1 1557 1558 A value of 1 instructs the kernel to panic when a 1559 hung task is detected. The default value is controlled 1560 by the CONFIG_BOOTPARAM_HUNG_TASK_PANIC build-time 1561 option. The value selected by this boot parameter can 1562 be changed later by the kernel.hung_task_panic sysctl. 1563 1564 hvc_iucv= [S390] Number of z/VM IUCV hypervisor console (HVC) 1565 terminal devices. Valid values: 0..8 1566 hvc_iucv_allow= [S390] Comma-separated list of z/VM user IDs. 1567 If specified, z/VM IUCV HVC accepts connections 1568 from listed z/VM user IDs only. 1569 1570 hv_nopvspin [X86,HYPER_V] Disables the paravirt spinlock optimizations 1571 which allow the hypervisor to 'idle' the 1572 guest on lock contention. 1573 1574 keep_bootcon [KNL] 1575 Do not unregister boot console at start. This is only 1576 useful for debugging when something happens in the window 1577 between unregistering the boot console and initializing 1578 the real console. 1579 1580 i2c_bus= [HW] Override the default board specific I2C bus speed 1581 or register an additional I2C bus that is not 1582 registered from board initialization code. 1583 Format: 1584 <bus_id>,<clkrate> 1585 1586 i8042.debug [HW] Toggle i8042 debug mode 1587 i8042.unmask_kbd_data 1588 [HW] Enable printing of interrupt data from the KBD port 1589 (disabled by default, and as a pre-condition 1590 requires that i8042.debug=1 be enabled) 1591 i8042.direct [HW] Put keyboard port into non-translated mode 1592 i8042.dumbkbd [HW] Pretend that controller can only read data from 1593 keyboard and cannot control its state 1594 (Don't attempt to blink the leds) 1595 i8042.noaux [HW] Don't check for auxiliary (== mouse) port 1596 i8042.nokbd [HW] Don't check/create keyboard port 1597 i8042.noloop [HW] Disable the AUX Loopback command while probing 1598 for the AUX port 1599 i8042.nomux [HW] Don't check presence of an active multiplexing 1600 controller 1601 i8042.nopnp [HW] Don't use ACPIPnP / PnPBIOS to discover KBD/AUX 1602 controllers 1603 i8042.notimeout [HW] Ignore timeout condition signalled by controller 1604 i8042.reset [HW] Reset the controller during init, cleanup and 1605 suspend-to-ram transitions, only during s2r 1606 transitions, or never reset 1607 Format: { 1 | Y | y | 0 | N | n } 1608 1, Y, y: always reset controller 1609 0, N, n: don't ever reset controller 1610 Default: only on s2r transitions on x86; most other 1611 architectures force reset to be always executed 1612 i8042.unlock [HW] Unlock (ignore) the keylock 1613 i8042.kbdreset [HW] Reset device connected to KBD port 1614 1615 i810= [HW,DRM] 1616 1617 i8k.ignore_dmi [HW] Continue probing hardware even if DMI data 1618 indicates that the driver is running on unsupported 1619 hardware. 1620 i8k.force [HW] Activate i8k driver even if SMM BIOS signature 1621 does not match list of supported models. 1622 i8k.power_status 1623 [HW] Report power status in /proc/i8k 1624 (disabled by default) 1625 i8k.restricted [HW] Allow controlling fans only if SYS_ADMIN 1626 capability is set. 1627 1628 i915.invert_brightness= 1629 [DRM] Invert the sense of the variable that is used to 1630 set the brightness of the panel backlight. Normally a 1631 brightness value of 0 indicates backlight switched off, 1632 and the maximum of the brightness value sets the backlight 1633 to maximum brightness. If this parameter is set to 0 1634 (default) and the machine requires it, or this parameter 1635 is set to 1, a brightness value of 0 sets the backlight 1636 to maximum brightness, and the maximum of the brightness 1637 value switches the backlight off. 1638 -1 -- never invert brightness 1639 0 -- machine default 1640 1 -- force brightness inversion 1641 1642 icn= [HW,ISDN] 1643 Format: <io>[,<membase>[,<icn_id>[,<icn_id2>]]] 1644 1645 ide-core.nodma= [HW] (E)IDE subsystem 1646 Format: =0.0 to prevent dma on hda, =0.1 hdb =1.0 hdc 1647 .vlb_clock .pci_clock .noflush .nohpa .noprobe .nowerr 1648 .cdrom .chs .ignore_cable are additional options 1649 See Documentation/ide/ide.rst. 1650 1651 ide-generic.probe-mask= [HW] (E)IDE subsystem 1652 Format: <int> 1653 Probe mask for legacy ISA IDE ports. Depending on 1654 platform up to 6 ports are supported, enabled by 1655 setting corresponding bits in the mask to 1. The 1656 default value is 0x0, which has a special meaning. 1657 On systems that have PCI, it triggers scanning the 1658 PCI bus for the first and the second port, which 1659 are then probed. On systems without PCI the value 1660 of 0x0 enables probing the two first ports as if it 1661 was 0x3. 1662 1663 ide-pci-generic.all-generic-ide [HW] (E)IDE subsystem 1664 Claim all unknown PCI IDE storage controllers. 1665 1666 idle= [X86] 1667 Format: idle=poll, idle=halt, idle=nomwait 1668 Poll forces a polling idle loop that can slightly 1669 improve the performance of waking up a idle CPU, but 1670 will use a lot of power and make the system run hot. 1671 Not recommended. 1672 idle=halt: Halt is forced to be used for CPU idle. 1673 In such case C2/C3 won't be used again. 1674 idle=nomwait: Disable mwait for CPU C-states 1675 1676 ieee754= [MIPS] Select IEEE Std 754 conformance mode 1677 Format: { strict | legacy | 2008 | relaxed } 1678 Default: strict 1679 1680 Choose which programs will be accepted for execution 1681 based on the IEEE 754 NaN encoding(s) supported by 1682 the FPU and the NaN encoding requested with the value 1683 of an ELF file header flag individually set by each 1684 binary. Hardware implementations are permitted to 1685 support either or both of the legacy and the 2008 NaN 1686 encoding mode. 1687 1688 Available settings are as follows: 1689 strict accept binaries that request a NaN encoding 1690 supported by the FPU 1691 legacy only accept legacy-NaN binaries, if supported 1692 by the FPU 1693 2008 only accept 2008-NaN binaries, if supported 1694 by the FPU 1695 relaxed accept any binaries regardless of whether 1696 supported by the FPU 1697 1698 The FPU emulator is always able to support both NaN 1699 encodings, so if no FPU hardware is present or it has 1700 been disabled with 'nofpu', then the settings of 1701 'legacy' and '2008' strap the emulator accordingly, 1702 'relaxed' straps the emulator for both legacy-NaN and 1703 2008-NaN, whereas 'strict' enables legacy-NaN only on 1704 legacy processors and both NaN encodings on MIPS32 or 1705 MIPS64 CPUs. 1706 1707 The setting for ABS.fmt/NEG.fmt instruction execution 1708 mode generally follows that for the NaN encoding, 1709 except where unsupported by hardware. 1710 1711 ignore_loglevel [KNL] 1712 Ignore loglevel setting - this will print /all/ 1713 kernel messages to the console. Useful for debugging. 1714 We also add it as printk module parameter, so users 1715 could change it dynamically, usually by 1716 /sys/module/printk/parameters/ignore_loglevel. 1717 1718 ignore_rlimit_data 1719 Ignore RLIMIT_DATA setting for data mappings, 1720 print warning at first misuse. Can be changed via 1721 /sys/module/kernel/parameters/ignore_rlimit_data. 1722 1723 ihash_entries= [KNL] 1724 Set number of hash buckets for inode cache. 1725 1726 ima_appraise= [IMA] appraise integrity measurements 1727 Format: { "off" | "enforce" | "fix" | "log" } 1728 default: "enforce" 1729 1730 ima_appraise_tcb [IMA] Deprecated. Use ima_policy= instead. 1731 The builtin appraise policy appraises all files 1732 owned by uid=0. 1733 1734 ima_canonical_fmt [IMA] 1735 Use the canonical format for the binary runtime 1736 measurements, instead of host native format. 1737 1738 ima_hash= [IMA] 1739 Format: { md5 | sha1 | rmd160 | sha256 | sha384 1740 | sha512 | ... } 1741 default: "sha1" 1742 1743 The list of supported hash algorithms is defined 1744 in crypto/hash_info.h. 1745 1746 ima_policy= [IMA] 1747 The builtin policies to load during IMA setup. 1748 Format: "tcb | appraise_tcb | secure_boot | 1749 fail_securely" 1750 1751 The "tcb" policy measures all programs exec'd, files 1752 mmap'd for exec, and all files opened with the read 1753 mode bit set by either the effective uid (euid=0) or 1754 uid=0. 1755 1756 The "appraise_tcb" policy appraises the integrity of 1757 all files owned by root. 1758 1759 The "secure_boot" policy appraises the integrity 1760 of files (eg. kexec kernel image, kernel modules, 1761 firmware, policy, etc) based on file signatures. 1762 1763 The "fail_securely" policy forces file signature 1764 verification failure also on privileged mounted 1765 filesystems with the SB_I_UNVERIFIABLE_SIGNATURE 1766 flag. 1767 1768 ima_tcb [IMA] Deprecated. Use ima_policy= instead. 1769 Load a policy which meets the needs of the Trusted 1770 Computing Base. This means IMA will measure all 1771 programs exec'd, files mmap'd for exec, and all files 1772 opened for read by uid=0. 1773 1774 ima_template= [IMA] 1775 Select one of defined IMA measurements template formats. 1776 Formats: { "ima" | "ima-ng" | "ima-sig" } 1777 Default: "ima-ng" 1778 1779 ima_template_fmt= 1780 [IMA] Define a custom template format. 1781 Format: { "field1|...|fieldN" } 1782 1783 ima.ahash_minsize= [IMA] Minimum file size for asynchronous hash usage 1784 Format: <min_file_size> 1785 Set the minimal file size for using asynchronous hash. 1786 If left unspecified, ahash usage is disabled. 1787 1788 ahash performance varies for different data sizes on 1789 different crypto accelerators. This option can be used 1790 to achieve the best performance for a particular HW. 1791 1792 ima.ahash_bufsize= [IMA] Asynchronous hash buffer size 1793 Format: <bufsize> 1794 Set hashing buffer size. Default: 4k. 1795 1796 ahash performance varies for different chunk sizes on 1797 different crypto accelerators. This option can be used 1798 to achieve best performance for particular HW. 1799 1800 init= [KNL] 1801 Format: <full_path> 1802 Run specified binary instead of /sbin/init as init 1803 process. 1804 1805 initcall_debug [KNL] Trace initcalls as they are executed. Useful 1806 for working out where the kernel is dying during 1807 startup. 1808 1809 initcall_blacklist= [KNL] Do not execute a comma-separated list of 1810 initcall functions. Useful for debugging built-in 1811 modules and initcalls. 1812 1813 initrd= [BOOT] Specify the location of the initial ramdisk 1814 1815 initrdmem= [KNL] Specify a physical address and size from which to 1816 load the initrd. If an initrd is compiled in or 1817 specified in the bootparams, it takes priority over this 1818 setting. 1819 Format: ss[KMG],nn[KMG] 1820 Default is 0, 0 1821 1822 init_on_alloc= [MM] Fill newly allocated pages and heap objects with 1823 zeroes. 1824 Format: 0 | 1 1825 Default set by CONFIG_INIT_ON_ALLOC_DEFAULT_ON. 1826 1827 init_on_free= [MM] Fill freed pages and heap objects with zeroes. 1828 Format: 0 | 1 1829 Default set by CONFIG_INIT_ON_FREE_DEFAULT_ON. 1830 1831 init_pkru= [X86] Specify the default memory protection keys rights 1832 register contents for all processes. 0x55555554 by 1833 default (disallow access to all but pkey 0). Can 1834 override in debugfs after boot. 1835 1836 inport.irq= [HW] Inport (ATI XL and Microsoft) busmouse driver 1837 Format: <irq> 1838 1839 int_pln_enable [X86] Enable power limit notification interrupt 1840 1841 integrity_audit=[IMA] 1842 Format: { "0" | "1" } 1843 0 -- basic integrity auditing messages. (Default) 1844 1 -- additional integrity auditing messages. 1845 1846 intel_iommu= [DMAR] Intel IOMMU driver (DMAR) option 1847 on 1848 Enable intel iommu driver. 1849 off 1850 Disable intel iommu driver. 1851 igfx_off [Default Off] 1852 By default, gfx is mapped as normal device. If a gfx 1853 device has a dedicated DMAR unit, the DMAR unit is 1854 bypassed by not enabling DMAR with this option. In 1855 this case, gfx device will use physical address for 1856 DMA. 1857 forcedac [X86-64] 1858 With this option iommu will not optimize to look 1859 for io virtual address below 32-bit forcing dual 1860 address cycle on pci bus for cards supporting greater 1861 than 32-bit addressing. The default is to look 1862 for translation below 32-bit and if not available 1863 then look in the higher range. 1864 strict [Default Off] 1865 With this option on every unmap_single operation will 1866 result in a hardware IOTLB flush operation as opposed 1867 to batching them for performance. 1868 sp_off [Default Off] 1869 By default, super page will be supported if Intel IOMMU 1870 has the capability. With this option, super page will 1871 not be supported. 1872 sm_on [Default Off] 1873 By default, scalable mode will be disabled even if the 1874 hardware advertises that it has support for the scalable 1875 mode translation. With this option set, scalable mode 1876 will be used on hardware which claims to support it. 1877 tboot_noforce [Default Off] 1878 Do not force the Intel IOMMU enabled under tboot. 1879 By default, tboot will force Intel IOMMU on, which 1880 could harm performance of some high-throughput 1881 devices like 40GBit network cards, even if identity 1882 mapping is enabled. 1883 Note that using this option lowers the security 1884 provided by tboot because it makes the system 1885 vulnerable to DMA attacks. 1886 1887 intel_idle.max_cstate= [KNL,HW,ACPI,X86] 1888 0 disables intel_idle and fall back on acpi_idle. 1889 1 to 9 specify maximum depth of C-state. 1890 1891 intel_pstate= [X86] 1892 disable 1893 Do not enable intel_pstate as the default 1894 scaling driver for the supported processors 1895 passive 1896 Use intel_pstate as a scaling driver, but configure it 1897 to work with generic cpufreq governors (instead of 1898 enabling its internal governor). This mode cannot be 1899 used along with the hardware-managed P-states (HWP) 1900 feature. 1901 force 1902 Enable intel_pstate on systems that prohibit it by default 1903 in favor of acpi-cpufreq. Forcing the intel_pstate driver 1904 instead of acpi-cpufreq may disable platform features, such 1905 as thermal controls and power capping, that rely on ACPI 1906 P-States information being indicated to OSPM and therefore 1907 should be used with caution. This option does not work with 1908 processors that aren't supported by the intel_pstate driver 1909 or on platforms that use pcc-cpufreq instead of acpi-cpufreq. 1910 no_hwp 1911 Do not enable hardware P state control (HWP) 1912 if available. 1913 hwp_only 1914 Only load intel_pstate on systems which support 1915 hardware P state control (HWP) if available. 1916 support_acpi_ppc 1917 Enforce ACPI _PPC performance limits. If the Fixed ACPI 1918 Description Table, specifies preferred power management 1919 profile as "Enterprise Server" or "Performance Server", 1920 then this feature is turned on by default. 1921 per_cpu_perf_limits 1922 Allow per-logical-CPU P-State performance control limits using 1923 cpufreq sysfs interface 1924 1925 intremap= [X86-64, Intel-IOMMU] 1926 on enable Interrupt Remapping (default) 1927 off disable Interrupt Remapping 1928 nosid disable Source ID checking 1929 no_x2apic_optout 1930 BIOS x2APIC opt-out request will be ignored 1931 nopost disable Interrupt Posting 1932 1933 iomem= Disable strict checking of access to MMIO memory 1934 strict regions from userspace. 1935 relaxed 1936 1937 iommu= [X86] 1938 off 1939 force 1940 noforce 1941 biomerge 1942 panic 1943 nopanic 1944 merge 1945 nomerge 1946 soft 1947 pt [X86] 1948 nopt [X86] 1949 nobypass [PPC/POWERNV] 1950 Disable IOMMU bypass, using IOMMU for PCI devices. 1951 1952 iommu.strict= [ARM64] Configure TLB invalidation behaviour 1953 Format: { "0" | "1" } 1954 0 - Lazy mode. 1955 Request that DMA unmap operations use deferred 1956 invalidation of hardware TLBs, for increased 1957 throughput at the cost of reduced device isolation. 1958 Will fall back to strict mode if not supported by 1959 the relevant IOMMU driver. 1960 1 - Strict mode (default). 1961 DMA unmap operations invalidate IOMMU hardware TLBs 1962 synchronously. 1963 1964 iommu.passthrough= 1965 [ARM64, X86] Configure DMA to bypass the IOMMU by default. 1966 Format: { "0" | "1" } 1967 0 - Use IOMMU translation for DMA. 1968 1 - Bypass the IOMMU for DMA. 1969 unset - Use value of CONFIG_IOMMU_DEFAULT_PASSTHROUGH. 1970 1971 io7= [HW] IO7 for Marvel-based Alpha systems 1972 See comment before marvel_specify_io7 in 1973 arch/alpha/kernel/core_marvel.c. 1974 1975 io_delay= [X86] I/O delay method 1976 0x80 1977 Standard port 0x80 based delay 1978 0xed 1979 Alternate port 0xed based delay (needed on some systems) 1980 udelay 1981 Simple two microseconds delay 1982 none 1983 No delay 1984 1985 ip= [IP_PNP] 1986 See Documentation/admin-guide/nfs/nfsroot.rst. 1987 1988 ipcmni_extend [KNL] Extend the maximum number of unique System V 1989 IPC identifiers from 32,768 to 16,777,216. 1990 1991 irqaffinity= [SMP] Set the default irq affinity mask 1992 The argument is a cpu list, as described above. 1993 1994 irqchip.gicv2_force_probe= 1995 [ARM, ARM64] 1996 Format: <bool> 1997 Force the kernel to look for the second 4kB page 1998 of a GICv2 controller even if the memory range 1999 exposed by the device tree is too small. 2000 2001 irqchip.gicv3_nolpi= 2002 [ARM, ARM64] 2003 Force the kernel to ignore the availability of 2004 LPIs (and by consequence ITSs). Intended for system 2005 that use the kernel as a bootloader, and thus want 2006 to let secondary kernels in charge of setting up 2007 LPIs. 2008 2009 irqchip.gicv3_pseudo_nmi= [ARM64] 2010 Enables support for pseudo-NMIs in the kernel. This 2011 requires the kernel to be built with 2012 CONFIG_ARM64_PSEUDO_NMI. 2013 2014 irqfixup [HW] 2015 When an interrupt is not handled search all handlers 2016 for it. Intended to get systems with badly broken 2017 firmware running. 2018 2019 irqpoll [HW] 2020 When an interrupt is not handled search all handlers 2021 for it. Also check all handlers each timer 2022 interrupt. Intended to get systems with badly broken 2023 firmware running. 2024 2025 isapnp= [ISAPNP] 2026 Format: <RDP>,<reset>,<pci_scan>,<verbosity> 2027 2028 isolcpus= [KNL,SMP,ISOL] Isolate a given set of CPUs from disturbance. 2029 [Deprecated - use cpusets instead] 2030 Format: [flag-list,]<cpu-list> 2031 2032 Specify one or more CPUs to isolate from disturbances 2033 specified in the flag list (default: domain): 2034 2035 nohz 2036 Disable the tick when a single task runs. 2037 2038 A residual 1Hz tick is offloaded to workqueues, which you 2039 need to affine to housekeeping through the global 2040 workqueue's affinity configured via the 2041 /sys/devices/virtual/workqueue/cpumask sysfs file, or 2042 by using the 'domain' flag described below. 2043 2044 NOTE: by default the global workqueue runs on all CPUs, 2045 so to protect individual CPUs the 'cpumask' file has to 2046 be configured manually after bootup. 2047 2048 domain 2049 Isolate from the general SMP balancing and scheduling 2050 algorithms. Note that performing domain isolation this way 2051 is irreversible: it's not possible to bring back a CPU to 2052 the domains once isolated through isolcpus. It's strongly 2053 advised to use cpusets instead to disable scheduler load 2054 balancing through the "cpuset.sched_load_balance" file. 2055 It offers a much more flexible interface where CPUs can 2056 move in and out of an isolated set anytime. 2057 2058 You can move a process onto or off an "isolated" CPU via 2059 the CPU affinity syscalls or cpuset. 2060 <cpu number> begins at 0 and the maximum value is 2061 "number of CPUs in system - 1". 2062 2063 managed_irq 2064 2065 Isolate from being targeted by managed interrupts 2066 which have an interrupt mask containing isolated 2067 CPUs. The affinity of managed interrupts is 2068 handled by the kernel and cannot be changed via 2069 the /proc/irq/* interfaces. 2070 2071 This isolation is best effort and only effective 2072 if the automatically assigned interrupt mask of a 2073 device queue contains isolated and housekeeping 2074 CPUs. If housekeeping CPUs are online then such 2075 interrupts are directed to the housekeeping CPU 2076 so that IO submitted on the housekeeping CPU 2077 cannot disturb the isolated CPU. 2078 2079 If a queue's affinity mask contains only isolated 2080 CPUs then this parameter has no effect on the 2081 interrupt routing decision, though interrupts are 2082 only delivered when tasks running on those 2083 isolated CPUs submit IO. IO submitted on 2084 housekeeping CPUs has no influence on those 2085 queues. 2086 2087 The format of <cpu-list> is described above. 2088 2089 iucv= [HW,NET] 2090 2091 ivrs_ioapic [HW,X86-64] 2092 Provide an override to the IOAPIC-ID<->DEVICE-ID 2093 mapping provided in the IVRS ACPI table. For 2094 example, to map IOAPIC-ID decimal 10 to 2095 PCI device 00:14.0 write the parameter as: 2096 ivrs_ioapic[10]=00:14.0 2097 2098 ivrs_hpet [HW,X86-64] 2099 Provide an override to the HPET-ID<->DEVICE-ID 2100 mapping provided in the IVRS ACPI table. For 2101 example, to map HPET-ID decimal 0 to 2102 PCI device 00:14.0 write the parameter as: 2103 ivrs_hpet[0]=00:14.0 2104 2105 ivrs_acpihid [HW,X86-64] 2106 Provide an override to the ACPI-HID:UID<->DEVICE-ID 2107 mapping provided in the IVRS ACPI table. For 2108 example, to map UART-HID:UID AMD0020:0 to 2109 PCI device 00:14.5 write the parameter as: 2110 ivrs_acpihid[00:14.5]=AMD0020:0 2111 2112 js= [HW,JOY] Analog joystick 2113 See Documentation/input/joydev/joystick.rst. 2114 2115 nokaslr [KNL] 2116 When CONFIG_RANDOMIZE_BASE is set, this disables 2117 kernel and module base offset ASLR (Address Space 2118 Layout Randomization). 2119 2120 kasan_multi_shot 2121 [KNL] Enforce KASAN (Kernel Address Sanitizer) to print 2122 report on every invalid memory access. Without this 2123 parameter KASAN will print report only for the first 2124 invalid access. 2125 2126 keepinitrd [HW,ARM] 2127 2128 kernelcore= [KNL,X86,IA-64,PPC] 2129 Format: nn[KMGTPE] | nn% | "mirror" 2130 This parameter specifies the amount of memory usable by 2131 the kernel for non-movable allocations. The requested 2132 amount is spread evenly throughout all nodes in the 2133 system as ZONE_NORMAL. The remaining memory is used for 2134 movable memory in its own zone, ZONE_MOVABLE. In the 2135 event, a node is too small to have both ZONE_NORMAL and 2136 ZONE_MOVABLE, kernelcore memory will take priority and 2137 other nodes will have a larger ZONE_MOVABLE. 2138 2139 ZONE_MOVABLE is used for the allocation of pages that 2140 may be reclaimed or moved by the page migration 2141 subsystem. Note that allocations like PTEs-from-HighMem 2142 still use the HighMem zone if it exists, and the Normal 2143 zone if it does not. 2144 2145 It is possible to specify the exact amount of memory in 2146 the form of "nn[KMGTPE]", a percentage of total system 2147 memory in the form of "nn%", or "mirror". If "mirror" 2148 option is specified, mirrored (reliable) memory is used 2149 for non-movable allocations and remaining memory is used 2150 for Movable pages. "nn[KMGTPE]", "nn%", and "mirror" 2151 are exclusive, so you cannot specify multiple forms. 2152 2153 kgdbdbgp= [KGDB,HW] kgdb over EHCI usb debug port. 2154 Format: <Controller#>[,poll interval] 2155 The controller # is the number of the ehci usb debug 2156 port as it is probed via PCI. The poll interval is 2157 optional and is the number seconds in between 2158 each poll cycle to the debug port in case you need 2159 the functionality for interrupting the kernel with 2160 gdb or control-c on the dbgp connection. When 2161 not using this parameter you use sysrq-g to break into 2162 the kernel debugger. 2163 2164 kgdboc= [KGDB,HW] kgdb over consoles. 2165 Requires a tty driver that supports console polling, 2166 or a supported polling keyboard driver (non-usb). 2167 Serial only format: <serial_device>[,baud] 2168 keyboard only format: kbd 2169 keyboard and serial format: kbd,<serial_device>[,baud] 2170 Optional Kernel mode setting: 2171 kms, kbd format: kms,kbd 2172 kms, kbd and serial format: kms,kbd,<ser_dev>[,baud] 2173 2174 kgdboc_earlycon= [KGDB,HW] 2175 If the boot console provides the ability to read 2176 characters and can work in polling mode, you can use 2177 this parameter to tell kgdb to use it as a backend 2178 until the normal console is registered. Intended to 2179 be used together with the kgdboc parameter which 2180 specifies the normal console to transition to. 2181 2182 The name of the early console should be specified 2183 as the value of this parameter. Note that the name of 2184 the early console might be different than the tty 2185 name passed to kgdboc. It's OK to leave the value 2186 blank and the first boot console that implements 2187 read() will be picked. 2188 2189 kgdbwait [KGDB] Stop kernel execution and enter the 2190 kernel debugger at the earliest opportunity. 2191 2192 kmac= [MIPS] Korina ethernet MAC address. 2193 Configure the RouterBoard 532 series on-chip 2194 Ethernet adapter MAC address. 2195 2196 kmemleak= [KNL] Boot-time kmemleak enable/disable 2197 Valid arguments: on, off 2198 Default: on 2199 Built with CONFIG_DEBUG_KMEMLEAK_DEFAULT_OFF=y, 2200 the default is off. 2201 2202 kprobe_event=[probe-list] 2203 [FTRACE] Add kprobe events and enable at boot time. 2204 The probe-list is a semicolon delimited list of probe 2205 definitions. Each definition is same as kprobe_events 2206 interface, but the parameters are comma delimited. 2207 For example, to add a kprobe event on vfs_read with 2208 arg1 and arg2, add to the command line; 2209 2210 kprobe_event=p,vfs_read,$arg1,$arg2 2211 2212 See also Documentation/trace/kprobetrace.rst "Kernel 2213 Boot Parameter" section. 2214 2215 kpti= [ARM64] Control page table isolation of user 2216 and kernel address spaces. 2217 Default: enabled on cores which need mitigation. 2218 0: force disabled 2219 1: force enabled 2220 2221 kvm.ignore_msrs=[KVM] Ignore guest accesses to unhandled MSRs. 2222 Default is 0 (don't ignore, but inject #GP) 2223 2224 kvm.enable_vmware_backdoor=[KVM] Support VMware backdoor PV interface. 2225 Default is false (don't support). 2226 2227 kvm.mmu_audit= [KVM] This is a R/W parameter which allows audit 2228 KVM MMU at runtime. 2229 Default is 0 (off) 2230 2231 kvm.nx_huge_pages= 2232 [KVM] Controls the software workaround for the 2233 X86_BUG_ITLB_MULTIHIT bug. 2234 force : Always deploy workaround. 2235 off : Never deploy workaround. 2236 auto : Deploy workaround based on the presence of 2237 X86_BUG_ITLB_MULTIHIT. 2238 2239 Default is 'auto'. 2240 2241 If the software workaround is enabled for the host, 2242 guests do need not to enable it for nested guests. 2243 2244 kvm.nx_huge_pages_recovery_ratio= 2245 [KVM] Controls how many 4KiB pages are periodically zapped 2246 back to huge pages. 0 disables the recovery, otherwise if 2247 the value is N KVM will zap 1/Nth of the 4KiB pages every 2248 minute. The default is 60. 2249 2250 kvm-amd.nested= [KVM,AMD] Allow nested virtualization in KVM/SVM. 2251 Default is 1 (enabled) 2252 2253 kvm-amd.npt= [KVM,AMD] Disable nested paging (virtualized MMU) 2254 for all guests. 2255 Default is 1 (enabled) if in 64-bit or 32-bit PAE mode. 2256 2257 kvm-arm.mode= 2258 [KVM,ARM] Select one of KVM/arm64's modes of operation. 2259 2260 nvhe: Standard nVHE-based mode, without support for 2261 protected guests. 2262 2263 protected: nVHE-based mode with support for guests whose 2264 state is kept private from the host. 2265 Not valid if the kernel is running in EL2. 2266 2267 Defaults to VHE/nVHE based on hardware support and 2268 the value of CONFIG_ARM64_VHE. 2269 2270 kvm-arm.vgic_v3_group0_trap= 2271 [KVM,ARM] Trap guest accesses to GICv3 group-0 2272 system registers 2273 2274 kvm-arm.vgic_v3_group1_trap= 2275 [KVM,ARM] Trap guest accesses to GICv3 group-1 2276 system registers 2277 2278 kvm-arm.vgic_v3_common_trap= 2279 [KVM,ARM] Trap guest accesses to GICv3 common 2280 system registers 2281 2282 kvm-arm.vgic_v4_enable= 2283 [KVM,ARM] Allow use of GICv4 for direct injection of 2284 LPIs. 2285 2286 kvm_cma_resv_ratio=n [PPC] 2287 Reserves given percentage from system memory area for 2288 contiguous memory allocation for KVM hash pagetable 2289 allocation. 2290 By default it reserves 5% of total system memory. 2291 Format: <integer> 2292 Default: 5 2293 2294 kvm-intel.ept= [KVM,Intel] Disable extended page tables 2295 (virtualized MMU) support on capable Intel chips. 2296 Default is 1 (enabled) 2297 2298 kvm-intel.emulate_invalid_guest_state= 2299 [KVM,Intel] Enable emulation of invalid guest states 2300 Default is 0 (disabled) 2301 2302 kvm-intel.flexpriority= 2303 [KVM,Intel] Disable FlexPriority feature (TPR shadow). 2304 Default is 1 (enabled) 2305 2306 kvm-intel.nested= 2307 [KVM,Intel] Enable VMX nesting (nVMX). 2308 Default is 0 (disabled) 2309 2310 kvm-intel.unrestricted_guest= 2311 [KVM,Intel] Disable unrestricted guest feature 2312 (virtualized real and unpaged mode) on capable 2313 Intel chips. Default is 1 (enabled) 2314 2315 kvm-intel.vmentry_l1d_flush=[KVM,Intel] Mitigation for L1 Terminal Fault 2316 CVE-2018-3620. 2317 2318 Valid arguments: never, cond, always 2319 2320 always: L1D cache flush on every VMENTER. 2321 cond: Flush L1D on VMENTER only when the code between 2322 VMEXIT and VMENTER can leak host memory. 2323 never: Disables the mitigation 2324 2325 Default is cond (do L1 cache flush in specific instances) 2326 2327 kvm-intel.vpid= [KVM,Intel] Disable Virtual Processor Identification 2328 feature (tagged TLBs) on capable Intel chips. 2329 Default is 1 (enabled) 2330 2331 l1tf= [X86] Control mitigation of the L1TF vulnerability on 2332 affected CPUs 2333 2334 The kernel PTE inversion protection is unconditionally 2335 enabled and cannot be disabled. 2336 2337 full 2338 Provides all available mitigations for the 2339 L1TF vulnerability. Disables SMT and 2340 enables all mitigations in the 2341 hypervisors, i.e. unconditional L1D flush. 2342 2343 SMT control and L1D flush control via the 2344 sysfs interface is still possible after 2345 boot. Hypervisors will issue a warning 2346 when the first VM is started in a 2347 potentially insecure configuration, 2348 i.e. SMT enabled or L1D flush disabled. 2349 2350 full,force 2351 Same as 'full', but disables SMT and L1D 2352 flush runtime control. Implies the 2353 'nosmt=force' command line option. 2354 (i.e. sysfs control of SMT is disabled.) 2355 2356 flush 2357 Leaves SMT enabled and enables the default 2358 hypervisor mitigation, i.e. conditional 2359 L1D flush. 2360 2361 SMT control and L1D flush control via the 2362 sysfs interface is still possible after 2363 boot. Hypervisors will issue a warning 2364 when the first VM is started in a 2365 potentially insecure configuration, 2366 i.e. SMT enabled or L1D flush disabled. 2367 2368 flush,nosmt 2369 2370 Disables SMT and enables the default 2371 hypervisor mitigation. 2372 2373 SMT control and L1D flush control via the 2374 sysfs interface is still possible after 2375 boot. Hypervisors will issue a warning 2376 when the first VM is started in a 2377 potentially insecure configuration, 2378 i.e. SMT enabled or L1D flush disabled. 2379 2380 flush,nowarn 2381 Same as 'flush', but hypervisors will not 2382 warn when a VM is started in a potentially 2383 insecure configuration. 2384 2385 off 2386 Disables hypervisor mitigations and doesn't 2387 emit any warnings. 2388 It also drops the swap size and available 2389 RAM limit restriction on both hypervisor and 2390 bare metal. 2391 2392 Default is 'flush'. 2393 2394 For details see: Documentation/admin-guide/hw-vuln/l1tf.rst 2395 2396 l2cr= [PPC] 2397 2398 l3cr= [PPC] 2399 2400 lapic [X86-32,APIC] Enable the local APIC even if BIOS 2401 disabled it. 2402 2403 lapic= [X86,APIC] Do not use TSC deadline 2404 value for LAPIC timer one-shot implementation. Default 2405 back to the programmable timer unit in the LAPIC. 2406 Format: notscdeadline 2407 2408 lapic_timer_c2_ok [X86,APIC] trust the local apic timer 2409 in C2 power state. 2410 2411 libata.dma= [LIBATA] DMA control 2412 libata.dma=0 Disable all PATA and SATA DMA 2413 libata.dma=1 PATA and SATA Disk DMA only 2414 libata.dma=2 ATAPI (CDROM) DMA only 2415 libata.dma=4 Compact Flash DMA only 2416 Combinations also work, so libata.dma=3 enables DMA 2417 for disks and CDROMs, but not CFs. 2418 2419 libata.ignore_hpa= [LIBATA] Ignore HPA limit 2420 libata.ignore_hpa=0 keep BIOS limits (default) 2421 libata.ignore_hpa=1 ignore limits, using full disk 2422 2423 libata.noacpi [LIBATA] Disables use of ACPI in libata suspend/resume 2424 when set. 2425 Format: <int> 2426 2427 libata.force= [LIBATA] Force configurations. The format is comma- 2428 separated list of "[ID:]VAL" where ID is 2429 PORT[.DEVICE]. PORT and DEVICE are decimal numbers 2430 matching port, link or device. Basically, it matches 2431 the ATA ID string printed on console by libata. If 2432 the whole ID part is omitted, the last PORT and DEVICE 2433 values are used. If ID hasn't been specified yet, the 2434 configuration applies to all ports, links and devices. 2435 2436 If only DEVICE is omitted, the parameter applies to 2437 the port and all links and devices behind it. DEVICE 2438 number of 0 either selects the first device or the 2439 first fan-out link behind PMP device. It does not 2440 select the host link. DEVICE number of 15 selects the 2441 host link and device attached to it. 2442 2443 The VAL specifies the configuration to force. As long 2444 as there's no ambiguity shortcut notation is allowed. 2445 For example, both 1.5 and 1.5G would work for 1.5Gbps. 2446 The following configurations can be forced. 2447 2448 * Cable type: 40c, 80c, short40c, unk, ign or sata. 2449 Any ID with matching PORT is used. 2450 2451 * SATA link speed limit: 1.5Gbps or 3.0Gbps. 2452 2453 * Transfer mode: pio[0-7], mwdma[0-4] and udma[0-7]. 2454 udma[/][16,25,33,44,66,100,133] notation is also 2455 allowed. 2456 2457 * [no]ncq: Turn on or off NCQ. 2458 2459 * [no]ncqtrim: Turn off queued DSM TRIM. 2460 2461 * nohrst, nosrst, norst: suppress hard, soft 2462 and both resets. 2463 2464 * rstonce: only attempt one reset during 2465 hot-unplug link recovery 2466 2467 * dump_id: dump IDENTIFY data. 2468 2469 * atapi_dmadir: Enable ATAPI DMADIR bridge support 2470 2471 * disable: Disable this device. 2472 2473 If there are multiple matching configurations changing 2474 the same attribute, the last one is used. 2475 2476 memblock=debug [KNL] Enable memblock debug messages. 2477 2478 load_ramdisk= [RAM] [Deprecated] 2479 2480 lockd.nlm_grace_period=P [NFS] Assign grace period. 2481 Format: <integer> 2482 2483 lockd.nlm_tcpport=N [NFS] Assign TCP port. 2484 Format: <integer> 2485 2486 lockd.nlm_timeout=T [NFS] Assign timeout value. 2487 Format: <integer> 2488 2489 lockd.nlm_udpport=M [NFS] Assign UDP port. 2490 Format: <integer> 2491 2492 lockdown= [SECURITY] 2493 { integrity | confidentiality } 2494 Enable the kernel lockdown feature. If set to 2495 integrity, kernel features that allow userland to 2496 modify the running kernel are disabled. If set to 2497 confidentiality, kernel features that allow userland 2498 to extract confidential information from the kernel 2499 are also disabled. 2500 2501 locktorture.nreaders_stress= [KNL] 2502 Set the number of locking read-acquisition kthreads. 2503 Defaults to being automatically set based on the 2504 number of online CPUs. 2505 2506 locktorture.nwriters_stress= [KNL] 2507 Set the number of locking write-acquisition kthreads. 2508 2509 locktorture.onoff_holdoff= [KNL] 2510 Set time (s) after boot for CPU-hotplug testing. 2511 2512 locktorture.onoff_interval= [KNL] 2513 Set time (s) between CPU-hotplug operations, or 2514 zero to disable CPU-hotplug testing. 2515 2516 locktorture.shuffle_interval= [KNL] 2517 Set task-shuffle interval (jiffies). Shuffling 2518 tasks allows some CPUs to go into dyntick-idle 2519 mode during the locktorture test. 2520 2521 locktorture.shutdown_secs= [KNL] 2522 Set time (s) after boot system shutdown. This 2523 is useful for hands-off automated testing. 2524 2525 locktorture.stat_interval= [KNL] 2526 Time (s) between statistics printk()s. 2527 2528 locktorture.stutter= [KNL] 2529 Time (s) to stutter testing, for example, 2530 specifying five seconds causes the test to run for 2531 five seconds, wait for five seconds, and so on. 2532 This tests the locking primitive's ability to 2533 transition abruptly to and from idle. 2534 2535 locktorture.torture_type= [KNL] 2536 Specify the locking implementation to test. 2537 2538 locktorture.verbose= [KNL] 2539 Enable additional printk() statements. 2540 2541 logibm.irq= [HW,MOUSE] Logitech Bus Mouse Driver 2542 Format: <irq> 2543 2544 loglevel= All Kernel Messages with a loglevel smaller than the 2545 console loglevel will be printed to the console. It can 2546 also be changed with klogd or other programs. The 2547 loglevels are defined as follows: 2548 2549 0 (KERN_EMERG) system is unusable 2550 1 (KERN_ALERT) action must be taken immediately 2551 2 (KERN_CRIT) critical conditions 2552 3 (KERN_ERR) error conditions 2553 4 (KERN_WARNING) warning conditions 2554 5 (KERN_NOTICE) normal but significant condition 2555 6 (KERN_INFO) informational 2556 7 (KERN_DEBUG) debug-level messages 2557 2558 log_buf_len=n[KMG] Sets the size of the printk ring buffer, 2559 in bytes. n must be a power of two and greater 2560 than the minimal size. The minimal size is defined 2561 by LOG_BUF_SHIFT kernel config parameter. There is 2562 also CONFIG_LOG_CPU_MAX_BUF_SHIFT config parameter 2563 that allows to increase the default size depending on 2564 the number of CPUs. See init/Kconfig for more details. 2565 2566 logo.nologo [FB] Disables display of the built-in Linux logo. 2567 This may be used to provide more screen space for 2568 kernel log messages and is useful when debugging 2569 kernel boot problems. 2570 2571 lp=0 [LP] Specify parallel ports to use, e.g, 2572 lp=port[,port...] lp=none,parport0 (lp0 not configured, lp1 uses 2573 lp=reset first parallel port). 'lp=0' disables the 2574 lp=auto printer driver. 'lp=reset' (which can be 2575 specified in addition to the ports) causes 2576 attached printers to be reset. Using 2577 lp=port1,port2,... specifies the parallel ports 2578 to associate lp devices with, starting with 2579 lp0. A port specification may be 'none' to skip 2580 that lp device, or a parport name such as 2581 'parport0'. Specifying 'lp=auto' instead of a 2582 port specification list means that device IDs 2583 from each port should be examined, to see if 2584 an IEEE 1284-compliant printer is attached; if 2585 so, the driver will manage that printer. 2586 See also header of drivers/char/lp.c. 2587 2588 lpj=n [KNL] 2589 Sets loops_per_jiffy to given constant, thus avoiding 2590 time-consuming boot-time autodetection (up to 250 ms per 2591 CPU). 0 enables autodetection (default). To determine 2592 the correct value for your kernel, boot with normal 2593 autodetection and see what value is printed. Note that 2594 on SMP systems the preset will be applied to all CPUs, 2595 which is likely to cause problems if your CPUs need 2596 significantly divergent settings. An incorrect value 2597 will cause delays in the kernel to be wrong, leading to 2598 unpredictable I/O errors and other breakage. Although 2599 unlikely, in the extreme case this might damage your 2600 hardware. 2601 2602 ltpc= [NET] 2603 Format: <io>,<irq>,<dma> 2604 2605 lsm.debug [SECURITY] Enable LSM initialization debugging output. 2606 2607 lsm=lsm1,...,lsmN 2608 [SECURITY] Choose order of LSM initialization. This 2609 overrides CONFIG_LSM, and the "security=" parameter. 2610 2611 machvec= [IA-64] Force the use of a particular machine-vector 2612 (machvec) in a generic kernel. 2613 Example: machvec=hpzx1 2614 2615 machtype= [Loongson] Share the same kernel image file between 2616 different yeeloong laptops. 2617 Example: machtype=lemote-yeeloong-2f-7inch 2618 2619 max_addr=nn[KMG] [KNL,BOOT,ia64] All physical memory greater 2620 than or equal to this physical address is ignored. 2621 2622 maxcpus= [SMP] Maximum number of processors that an SMP kernel 2623 will bring up during bootup. maxcpus=n : n >= 0 limits 2624 the kernel to bring up 'n' processors. Surely after 2625 bootup you can bring up the other plugged cpu by executing 2626 "echo 1 > /sys/devices/system/cpu/cpuX/online". So maxcpus 2627 only takes effect during system bootup. 2628 While n=0 is a special case, it is equivalent to "nosmp", 2629 which also disables the IO APIC. 2630 2631 max_loop= [LOOP] The number of loop block devices that get 2632 (loop.max_loop) unconditionally pre-created at init time. The default 2633 number is configured by BLK_DEV_LOOP_MIN_COUNT. Instead 2634 of statically allocating a predefined number, loop 2635 devices can be requested on-demand with the 2636 /dev/loop-control interface. 2637 2638 mce [X86-32] Machine Check Exception 2639 2640 mce=option [X86-64] See Documentation/x86/x86_64/boot-options.rst 2641 2642 md= [HW] RAID subsystems devices and level 2643 See Documentation/admin-guide/md.rst. 2644 2645 mdacon= [MDA] 2646 Format: <first>,<last> 2647 Specifies range of consoles to be captured by the MDA. 2648 2649 mds= [X86,INTEL] 2650 Control mitigation for the Micro-architectural Data 2651 Sampling (MDS) vulnerability. 2652 2653 Certain CPUs are vulnerable to an exploit against CPU 2654 internal buffers which can forward information to a 2655 disclosure gadget under certain conditions. 2656 2657 In vulnerable processors, the speculatively 2658 forwarded data can be used in a cache side channel 2659 attack, to access data to which the attacker does 2660 not have direct access. 2661 2662 This parameter controls the MDS mitigation. The 2663 options are: 2664 2665 full - Enable MDS mitigation on vulnerable CPUs 2666 full,nosmt - Enable MDS mitigation and disable 2667 SMT on vulnerable CPUs 2668 off - Unconditionally disable MDS mitigation 2669 2670 On TAA-affected machines, mds=off can be prevented by 2671 an active TAA mitigation as both vulnerabilities are 2672 mitigated with the same mechanism so in order to disable 2673 this mitigation, you need to specify tsx_async_abort=off 2674 too. 2675 2676 Not specifying this option is equivalent to 2677 mds=full. 2678 2679 For details see: Documentation/admin-guide/hw-vuln/mds.rst 2680 2681 mem=nn[KMG] [KNL,BOOT] Force usage of a specific amount of memory 2682 Amount of memory to be used in cases as follows: 2683 2684 1 for test; 2685 2 when the kernel is not able to see the whole system memory; 2686 3 memory that lies after 'mem=' boundary is excluded from 2687 the hypervisor, then assigned to KVM guests. 2688 2689 [X86] Work as limiting max address. Use together 2690 with memmap= to avoid physical address space collisions. 2691 Without memmap= PCI devices could be placed at addresses 2692 belonging to unused RAM. 2693 2694 Note that this only takes effects during boot time since 2695 in above case 3, memory may need be hot added after boot 2696 if system memory of hypervisor is not sufficient. 2697 2698 mem=nopentium [BUGS=X86-32] Disable usage of 4MB pages for kernel 2699 memory. 2700 2701 memchunk=nn[KMG] 2702 [KNL,SH] Allow user to override the default size for 2703 per-device physically contiguous DMA buffers. 2704 2705 memhp_default_state=online/offline 2706 [KNL] Set the initial state for the memory hotplug 2707 onlining policy. If not specified, the default value is 2708 set according to the 2709 CONFIG_MEMORY_HOTPLUG_DEFAULT_ONLINE kernel config 2710 option. 2711 See Documentation/admin-guide/mm/memory-hotplug.rst. 2712 2713 memmap=exactmap [KNL,X86] Enable setting of an exact 2714 E820 memory map, as specified by the user. 2715 Such memmap=exactmap lines can be constructed based on 2716 BIOS output or other requirements. See the memmap=nn@ss 2717 option description. 2718 2719 memmap=nn[KMG]@ss[KMG] 2720 [KNL, X86, MIPS, XTENSA] Force usage of a specific region of memory. 2721 Region of memory to be used is from ss to ss+nn. 2722 If @ss[KMG] is omitted, it is equivalent to mem=nn[KMG], 2723 which limits max address to nn[KMG]. 2724 Multiple different regions can be specified, 2725 comma delimited. 2726 Example: 2727 memmap=100M@2G,100M#3G,1G!1024G 2728 2729 memmap=nn[KMG]#ss[KMG] 2730 [KNL,ACPI] Mark specific memory as ACPI data. 2731 Region of memory to be marked is from ss to ss+nn. 2732 2733 memmap=nn[KMG]$ss[KMG] 2734 [KNL,ACPI] Mark specific memory as reserved. 2735 Region of memory to be reserved is from ss to ss+nn. 2736 Example: Exclude memory from 0x18690000-0x1869ffff 2737 memmap=64K$0x18690000 2738 or 2739 memmap=0x10000$0x18690000 2740 Some bootloaders may need an escape character before '$', 2741 like Grub2, otherwise '$' and the following number 2742 will be eaten. 2743 2744 memmap=nn[KMG]!ss[KMG] 2745 [KNL,X86] Mark specific memory as protected. 2746 Region of memory to be used, from ss to ss+nn. 2747 The memory region may be marked as e820 type 12 (0xc) 2748 and is NVDIMM or ADR memory. 2749 2750 memmap=<size>%<offset>-<oldtype>+<newtype> 2751 [KNL,ACPI] Convert memory within the specified region 2752 from <oldtype> to <newtype>. If "-<oldtype>" is left 2753 out, the whole region will be marked as <newtype>, 2754 even if previously unavailable. If "+<newtype>" is left 2755 out, matching memory will be removed. Types are 2756 specified as e820 types, e.g., 1 = RAM, 2 = reserved, 2757 3 = ACPI, 12 = PRAM. 2758 2759 memory_corruption_check=0/1 [X86] 2760 Some BIOSes seem to corrupt the first 64k of 2761 memory when doing things like suspend/resume. 2762 Setting this option will scan the memory 2763 looking for corruption. Enabling this will 2764 both detect corruption and prevent the kernel 2765 from using the memory being corrupted. 2766 However, its intended as a diagnostic tool; if 2767 repeatable BIOS-originated corruption always 2768 affects the same memory, you can use memmap= 2769 to prevent the kernel from using that memory. 2770 2771 memory_corruption_check_size=size [X86] 2772 By default it checks for corruption in the low 2773 64k, making this memory unavailable for normal 2774 use. Use this parameter to scan for 2775 corruption in more or less memory. 2776 2777 memory_corruption_check_period=seconds [X86] 2778 By default it checks for corruption every 60 2779 seconds. Use this parameter to check at some 2780 other rate. 0 disables periodic checking. 2781 2782 memtest= [KNL,X86,ARM,PPC] Enable memtest 2783 Format: <integer> 2784 default : 0 <disable> 2785 Specifies the number of memtest passes to be 2786 performed. Each pass selects another test 2787 pattern from a given set of patterns. Memtest 2788 fills the memory with this pattern, validates 2789 memory contents and reserves bad memory 2790 regions that are detected. 2791 2792 mem_encrypt= [X86-64] AMD Secure Memory Encryption (SME) control 2793 Valid arguments: on, off 2794 Default (depends on kernel configuration option): 2795 on (CONFIG_AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT=y) 2796 off (CONFIG_AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT=n) 2797 mem_encrypt=on: Activate SME 2798 mem_encrypt=off: Do not activate SME 2799 2800 Refer to Documentation/virt/kvm/amd-memory-encryption.rst 2801 for details on when memory encryption can be activated. 2802 2803 mem_sleep_default= [SUSPEND] Default system suspend mode: 2804 s2idle - Suspend-To-Idle 2805 shallow - Power-On Suspend or equivalent (if supported) 2806 deep - Suspend-To-RAM or equivalent (if supported) 2807 See Documentation/admin-guide/pm/sleep-states.rst. 2808 2809 meye.*= [HW] Set MotionEye Camera parameters 2810 See Documentation/admin-guide/media/meye.rst. 2811 2812 mfgpt_irq= [IA-32] Specify the IRQ to use for the 2813 Multi-Function General Purpose Timers on AMD Geode 2814 platforms. 2815 2816 mfgptfix [X86-32] Fix MFGPT timers on AMD Geode platforms when 2817 the BIOS has incorrectly applied a workaround. TinyBIOS 2818 version 0.98 is known to be affected, 0.99 fixes the 2819 problem by letting the user disable the workaround. 2820 2821 mga= [HW,DRM] 2822 2823 min_addr=nn[KMG] [KNL,BOOT,ia64] All physical memory below this 2824 physical address is ignored. 2825 2826 mini2440= [ARM,HW,KNL] 2827 Format:[0..2][b][c][t] 2828 Default: "0tb" 2829 MINI2440 configuration specification: 2830 0 - The attached screen is the 3.5" TFT 2831 1 - The attached screen is the 7" TFT 2832 2 - The VGA Shield is attached (1024x768) 2833 Leaving out the screen size parameter will not load 2834 the TFT driver, and the framebuffer will be left 2835 unconfigured. 2836 b - Enable backlight. The TFT backlight pin will be 2837 linked to the kernel VESA blanking code and a GPIO 2838 LED. This parameter is not necessary when using the 2839 VGA shield. 2840 c - Enable the s3c camera interface. 2841 t - Reserved for enabling touchscreen support. The 2842 touchscreen support is not enabled in the mainstream 2843 kernel as of 2.6.30, a preliminary port can be found 2844 in the "bleeding edge" mini2440 support kernel at 2845 https://repo.or.cz/w/linux-2.6/mini2440.git 2846 2847 mitigations= 2848 [X86,PPC,S390,ARM64] Control optional mitigations for 2849 CPU vulnerabilities. This is a set of curated, 2850 arch-independent options, each of which is an 2851 aggregation of existing arch-specific options. 2852 2853 off 2854 Disable all optional CPU mitigations. This 2855 improves system performance, but it may also 2856 expose users to several CPU vulnerabilities. 2857 Equivalent to: nopti [X86,PPC] 2858 kpti=0 [ARM64] 2859 nospectre_v1 [X86,PPC] 2860 nobp=0 [S390] 2861 nospectre_v2 [X86,PPC,S390,ARM64] 2862 spectre_v2_user=off [X86] 2863 spec_store_bypass_disable=off [X86,PPC] 2864 ssbd=force-off [ARM64] 2865 l1tf=off [X86] 2866 mds=off [X86] 2867 tsx_async_abort=off [X86] 2868 kvm.nx_huge_pages=off [X86] 2869 no_entry_flush [PPC] 2870 no_uaccess_flush [PPC] 2871 2872 Exceptions: 2873 This does not have any effect on 2874 kvm.nx_huge_pages when 2875 kvm.nx_huge_pages=force. 2876 2877 auto (default) 2878 Mitigate all CPU vulnerabilities, but leave SMT 2879 enabled, even if it's vulnerable. This is for 2880 users who don't want to be surprised by SMT 2881 getting disabled across kernel upgrades, or who 2882 have other ways of avoiding SMT-based attacks. 2883 Equivalent to: (default behavior) 2884 2885 auto,nosmt 2886 Mitigate all CPU vulnerabilities, disabling SMT 2887 if needed. This is for users who always want to 2888 be fully mitigated, even if it means losing SMT. 2889 Equivalent to: l1tf=flush,nosmt [X86] 2890 mds=full,nosmt [X86] 2891 tsx_async_abort=full,nosmt [X86] 2892 2893 mminit_loglevel= 2894 [KNL] When CONFIG_DEBUG_MEMORY_INIT is set, this 2895 parameter allows control of the logging verbosity for 2896 the additional memory initialisation checks. A value 2897 of 0 disables mminit logging and a level of 4 will 2898 log everything. Information is printed at KERN_DEBUG 2899 so loglevel=8 may also need to be specified. 2900 2901 module.sig_enforce 2902 [KNL] When CONFIG_MODULE_SIG is set, this means that 2903 modules without (valid) signatures will fail to load. 2904 Note that if CONFIG_MODULE_SIG_FORCE is set, that 2905 is always true, so this option does nothing. 2906 2907 module_blacklist= [KNL] Do not load a comma-separated list of 2908 modules. Useful for debugging problem modules. 2909 2910 mousedev.tap_time= 2911 [MOUSE] Maximum time between finger touching and 2912 leaving touchpad surface for touch to be considered 2913 a tap and be reported as a left button click (for 2914 touchpads working in absolute mode only). 2915 Format: <msecs> 2916 mousedev.xres= [MOUSE] Horizontal screen resolution, used for devices 2917 reporting absolute coordinates, such as tablets 2918 mousedev.yres= [MOUSE] Vertical screen resolution, used for devices 2919 reporting absolute coordinates, such as tablets 2920 2921 movablecore= [KNL,X86,IA-64,PPC] 2922 Format: nn[KMGTPE] | nn% 2923 This parameter is the complement to kernelcore=, it 2924 specifies the amount of memory used for migratable 2925 allocations. If both kernelcore and movablecore is 2926 specified, then kernelcore will be at *least* the 2927 specified value but may be more. If movablecore on its 2928 own is specified, the administrator must be careful 2929 that the amount of memory usable for all allocations 2930 is not too small. 2931 2932 movable_node [KNL] Boot-time switch to make hotplugable memory 2933 NUMA nodes to be movable. This means that the memory 2934 of such nodes will be usable only for movable 2935 allocations which rules out almost all kernel 2936 allocations. Use with caution! 2937 2938 MTD_Partition= [MTD] 2939 Format: <name>,<region-number>,<size>,<offset> 2940 2941 MTD_Region= [MTD] Format: 2942 <name>,<region-number>[,<base>,<size>,<buswidth>,<altbuswidth>] 2943 2944 mtdparts= [MTD] 2945 See drivers/mtd/parsers/cmdlinepart.c 2946 2947 multitce=off [PPC] This parameter disables the use of the pSeries 2948 firmware feature for updating multiple TCE entries 2949 at a time. 2950 2951 onenand.bdry= [HW,MTD] Flex-OneNAND Boundary Configuration 2952 2953 Format: [die0_boundary][,die0_lock][,die1_boundary][,die1_lock] 2954 2955 boundary - index of last SLC block on Flex-OneNAND. 2956 The remaining blocks are configured as MLC blocks. 2957 lock - Configure if Flex-OneNAND boundary should be locked. 2958 Once locked, the boundary cannot be changed. 2959 1 indicates lock status, 0 indicates unlock status. 2960 2961 mtdset= [ARM] 2962 ARM/S3C2412 JIVE boot control 2963 2964 See arch/arm/mach-s3c/mach-jive.c 2965 2966 mtouchusb.raw_coordinates= 2967 [HW] Make the MicroTouch USB driver use raw coordinates 2968 ('y', default) or cooked coordinates ('n') 2969 2970 mtrr_chunk_size=nn[KMG] [X86] 2971 used for mtrr cleanup. It is largest continuous chunk 2972 that could hold holes aka. UC entries. 2973 2974 mtrr_gran_size=nn[KMG] [X86] 2975 Used for mtrr cleanup. It is granularity of mtrr block. 2976 Default is 1. 2977 Large value could prevent small alignment from 2978 using up MTRRs. 2979 2980 mtrr_spare_reg_nr=n [X86] 2981 Format: <integer> 2982 Range: 0,7 : spare reg number 2983 Default : 1 2984 Used for mtrr cleanup. It is spare mtrr entries number. 2985 Set to 2 or more if your graphical card needs more. 2986 2987 n2= [NET] SDL Inc. RISCom/N2 synchronous serial card 2988 2989 netdev= [NET] Network devices parameters 2990 Format: <irq>,<io>,<mem_start>,<mem_end>,<name> 2991 Note that mem_start is often overloaded to mean 2992 something different and driver-specific. 2993 This usage is only documented in each driver source 2994 file if at all. 2995 2996 nf_conntrack.acct= 2997 [NETFILTER] Enable connection tracking flow accounting 2998 0 to disable accounting 2999 1 to enable accounting 3000 Default value is 0. 3001 3002 nfsaddrs= [NFS] Deprecated. Use ip= instead. 3003 See Documentation/admin-guide/nfs/nfsroot.rst. 3004 3005 nfsroot= [NFS] nfs root filesystem for disk-less boxes. 3006 See Documentation/admin-guide/nfs/nfsroot.rst. 3007 3008 nfsrootdebug [NFS] enable nfsroot debugging messages. 3009 See Documentation/admin-guide/nfs/nfsroot.rst. 3010 3011 nfs.callback_nr_threads= 3012 [NFSv4] set the total number of threads that the 3013 NFS client will assign to service NFSv4 callback 3014 requests. 3015 3016 nfs.callback_tcpport= 3017 [NFS] set the TCP port on which the NFSv4 callback 3018 channel should listen. 3019 3020 nfs.cache_getent= 3021 [NFS] sets the pathname to the program which is used 3022 to update the NFS client cache entries. 3023 3024 nfs.cache_getent_timeout= 3025 [NFS] sets the timeout after which an attempt to 3026 update a cache entry is deemed to have failed. 3027 3028 nfs.idmap_cache_timeout= 3029 [NFS] set the maximum lifetime for idmapper cache 3030 entries. 3031 3032 nfs.enable_ino64= 3033 [NFS] enable 64-bit inode numbers. 3034 If zero, the NFS client will fake up a 32-bit inode 3035 number for the readdir() and stat() syscalls instead 3036 of returning the full 64-bit number. 3037 The default is to return 64-bit inode numbers. 3038 3039 nfs.max_session_cb_slots= 3040 [NFSv4.1] Sets the maximum number of session 3041 slots the client will assign to the callback 3042 channel. This determines the maximum number of 3043 callbacks the client will process in parallel for 3044 a particular server. 3045 3046 nfs.max_session_slots= 3047 [NFSv4.1] Sets the maximum number of session slots 3048 the client will attempt to negotiate with the server. 3049 This limits the number of simultaneous RPC requests 3050 that the client can send to the NFSv4.1 server. 3051 Note that there is little point in setting this 3052 value higher than the max_tcp_slot_table_limit. 3053 3054 nfs.nfs4_disable_idmapping= 3055 [NFSv4] When set to the default of '1', this option 3056 ensures that both the RPC level authentication 3057 scheme and the NFS level operations agree to use 3058 numeric uids/gids if the mount is using the 3059 'sec=sys' security flavour. In effect it is 3060 disabling idmapping, which can make migration from 3061 legacy NFSv2/v3 systems to NFSv4 easier. 3062 Servers that do not support this mode of operation 3063 will be autodetected by the client, and it will fall 3064 back to using the idmapper. 3065 To turn off this behaviour, set the value to '0'. 3066 nfs.nfs4_unique_id= 3067 [NFS4] Specify an additional fixed unique ident- 3068 ification string that NFSv4 clients can insert into 3069 their nfs_client_id4 string. This is typically a 3070 UUID that is generated at system install time. 3071 3072 nfs.send_implementation_id = 3073 [NFSv4.1] Send client implementation identification 3074 information in exchange_id requests. 3075 If zero, no implementation identification information 3076 will be sent. 3077 The default is to send the implementation identification 3078 information. 3079 3080 nfs.recover_lost_locks = 3081 [NFSv4] Attempt to recover locks that were lost due 3082 to a lease timeout on the server. Please note that 3083 doing this risks data corruption, since there are 3084 no guarantees that the file will remain unchanged 3085 after the locks are lost. 3086 If you want to enable the kernel legacy behaviour of 3087 attempting to recover these locks, then set this 3088 parameter to '1'. 3089 The default parameter value of '0' causes the kernel 3090 not to attempt recovery of lost locks. 3091 3092 nfs4.layoutstats_timer = 3093 [NFSv4.2] Change the rate at which the kernel sends 3094 layoutstats to the pNFS metadata server. 3095 3096 Setting this to value to 0 causes the kernel to use 3097 whatever value is the default set by the layout 3098 driver. A non-zero value sets the minimum interval 3099 in seconds between layoutstats transmissions. 3100 3101 nfsd.nfs4_disable_idmapping= 3102 [NFSv4] When set to the default of '1', the NFSv4 3103 server will return only numeric uids and gids to 3104 clients using auth_sys, and will accept numeric uids 3105 and gids from such clients. This is intended to ease 3106 migration from NFSv2/v3. 3107 3108 nmi_backtrace.backtrace_idle [KNL] 3109 Dump stacks even of idle CPUs in response to an 3110 NMI stack-backtrace request. 3111 3112 nmi_debug= [KNL,SH] Specify one or more actions to take 3113 when a NMI is triggered. 3114 Format: [state][,regs][,debounce][,die] 3115 3116 nmi_watchdog= [KNL,BUGS=X86] Debugging features for SMP kernels 3117 Format: [panic,][nopanic,][num] 3118 Valid num: 0 or 1 3119 0 - turn hardlockup detector in nmi_watchdog off 3120 1 - turn hardlockup detector in nmi_watchdog on 3121 When panic is specified, panic when an NMI watchdog 3122 timeout occurs (or 'nopanic' to not panic on an NMI 3123 watchdog, if CONFIG_BOOTPARAM_HARDLOCKUP_PANIC is set) 3124 To disable both hard and soft lockup detectors, 3125 please see 'nowatchdog'. 3126 This is useful when you use a panic=... timeout and 3127 need the box quickly up again. 3128 3129 These settings can be accessed at runtime via 3130 the nmi_watchdog and hardlockup_panic sysctls. 3131 3132 netpoll.carrier_timeout= 3133 [NET] Specifies amount of time (in seconds) that 3134 netpoll should wait for a carrier. By default netpoll 3135 waits 4 seconds. 3136 3137 no387 [BUGS=X86-32] Tells the kernel to use the 387 maths 3138 emulation library even if a 387 maths coprocessor 3139 is present. 3140 3141 no5lvl [X86-64] Disable 5-level paging mode. Forces 3142 kernel to use 4-level paging instead. 3143 3144 nofsgsbase [X86] Disables FSGSBASE instructions. 3145 3146 no_console_suspend 3147 [HW] Never suspend the console 3148 Disable suspending of consoles during suspend and 3149 hibernate operations. Once disabled, debugging 3150 messages can reach various consoles while the rest 3151 of the system is being put to sleep (ie, while 3152 debugging driver suspend/resume hooks). This may 3153 not work reliably with all consoles, but is known 3154 to work with serial and VGA consoles. 3155 To facilitate more flexible debugging, we also add 3156 console_suspend, a printk module parameter to control 3157 it. Users could use console_suspend (usually 3158 /sys/module/printk/parameters/console_suspend) to 3159 turn on/off it dynamically. 3160 3161 novmcoredd [KNL,KDUMP] 3162 Disable device dump. Device dump allows drivers to 3163 append dump data to vmcore so you can collect driver 3164 specified debug info. Drivers can append the data 3165 without any limit and this data is stored in memory, 3166 so this may cause significant memory stress. Disabling 3167 device dump can help save memory but the driver debug 3168 data will be no longer available. This parameter 3169 is only available when CONFIG_PROC_VMCORE_DEVICE_DUMP 3170 is set. 3171 3172 noaliencache [MM, NUMA, SLAB] Disables the allocation of alien 3173 caches in the slab allocator. Saves per-node memory, 3174 but will impact performance. 3175 3176 noalign [KNL,ARM] 3177 3178 noaltinstr [S390] Disables alternative instructions patching 3179 (CPU alternatives feature). 3180 3181 noapic [SMP,APIC] Tells the kernel to not make use of any 3182 IOAPICs that may be present in the system. 3183 3184 noautogroup Disable scheduler automatic task group creation. 3185 3186 nobats [PPC] Do not use BATs for mapping kernel lowmem 3187 on "Classic" PPC cores. 3188 3189 nocache [ARM] 3190 3191 noclflush [BUGS=X86] Don't use the CLFLUSH instruction 3192 3193 nodelayacct [KNL] Disable per-task delay accounting 3194 3195 nodsp [SH] Disable hardware DSP at boot time. 3196 3197 noefi Disable EFI runtime services support. 3198 3199 no_entry_flush [PPC] Don't flush the L1-D cache when entering the kernel. 3200 3201 noexec [IA-64] 3202 3203 noexec [X86] 3204 On X86-32 available only on PAE configured kernels. 3205 noexec=on: enable non-executable mappings (default) 3206 noexec=off: disable non-executable mappings 3207 3208 nosmap [X86,PPC] 3209 Disable SMAP (Supervisor Mode Access Prevention) 3210 even if it is supported by processor. 3211 3212 nosmep [X86,PPC] 3213 Disable SMEP (Supervisor Mode Execution Prevention) 3214 even if it is supported by processor. 3215 3216 noexec32 [X86-64] 3217 This affects only 32-bit executables. 3218 noexec32=on: enable non-executable mappings (default) 3219 read doesn't imply executable mappings 3220 noexec32=off: disable non-executable mappings 3221 read implies executable mappings 3222 3223 nofpu [MIPS,SH] Disable hardware FPU at boot time. 3224 3225 nofxsr [BUGS=X86-32] Disables x86 floating point extended 3226 register save and restore. The kernel will only save 3227 legacy floating-point registers on task switch. 3228 3229 nohugeiomap [KNL,X86,PPC,ARM64] Disable kernel huge I/O mappings. 3230 3231 nosmt [KNL,S390] Disable symmetric multithreading (SMT). 3232 Equivalent to smt=1. 3233 3234 [KNL,X86] Disable symmetric multithreading (SMT). 3235 nosmt=force: Force disable SMT, cannot be undone 3236 via the sysfs control file. 3237 3238 nospectre_v1 [X86,PPC] Disable mitigations for Spectre Variant 1 3239 (bounds check bypass). With this option data leaks are 3240 possible in the system. 3241 3242 nospectre_v2 [X86,PPC_FSL_BOOK3E,ARM64] Disable all mitigations for 3243 the Spectre variant 2 (indirect branch prediction) 3244 vulnerability. System may allow data leaks with this 3245 option. 3246 3247 nospec_store_bypass_disable 3248 [HW] Disable all mitigations for the Speculative Store Bypass vulnerability 3249 3250 no_uaccess_flush 3251 [PPC] Don't flush the L1-D cache after accessing user data. 3252 3253 noxsave [BUGS=X86] Disables x86 extended register state save 3254 and restore using xsave. The kernel will fallback to 3255 enabling legacy floating-point and sse state. 3256 3257 noxsaveopt [X86] Disables xsaveopt used in saving x86 extended 3258 register states. The kernel will fall back to use 3259 xsave to save the states. By using this parameter, 3260 performance of saving the states is degraded because 3261 xsave doesn't support modified optimization while 3262 xsaveopt supports it on xsaveopt enabled systems. 3263 3264 noxsaves [X86] Disables xsaves and xrstors used in saving and 3265 restoring x86 extended register state in compacted 3266 form of xsave area. The kernel will fall back to use 3267 xsaveopt and xrstor to save and restore the states 3268 in standard form of xsave area. By using this 3269 parameter, xsave area per process might occupy more 3270 memory on xsaves enabled systems. 3271 3272 nohlt [BUGS=ARM,SH] Tells the kernel that the sleep(SH) or 3273 wfi(ARM) instruction doesn't work correctly and not to 3274 use it. This is also useful when using JTAG debugger. 3275 3276 no_file_caps Tells the kernel not to honor file capabilities. The 3277 only way then for a file to be executed with privilege 3278 is to be setuid root or executed by root. 3279 3280 nohalt [IA-64] Tells the kernel not to use the power saving 3281 function PAL_HALT_LIGHT when idle. This increases 3282 power-consumption. On the positive side, it reduces 3283 interrupt wake-up latency, which may improve performance 3284 in certain environments such as networked servers or 3285 real-time systems. 3286 3287 nohibernate [HIBERNATION] Disable hibernation and resume. 3288 3289 nohz= [KNL] Boottime enable/disable dynamic ticks 3290 Valid arguments: on, off 3291 Default: on 3292 3293 nohz_full= [KNL,BOOT,SMP,ISOL] 3294 The argument is a cpu list, as described above. 3295 In kernels built with CONFIG_NO_HZ_FULL=y, set 3296 the specified list of CPUs whose tick will be stopped 3297 whenever possible. The boot CPU will be forced outside 3298 the range to maintain the timekeeping. Any CPUs 3299 in this list will have their RCU callbacks offloaded, 3300 just as if they had also been called out in the 3301 rcu_nocbs= boot parameter. 3302 3303 noiotrap [SH] Disables trapped I/O port accesses. 3304 3305 noirqdebug [X86-32] Disables the code which attempts to detect and 3306 disable unhandled interrupt sources. 3307 3308 no_timer_check [X86,APIC] Disables the code which tests for 3309 broken timer IRQ sources. 3310 3311 noisapnp [ISAPNP] Disables ISA PnP code. 3312 3313 noinitrd [RAM] Tells the kernel not to load any configured 3314 initial RAM disk. 3315 3316 nointremap [X86-64, Intel-IOMMU] Do not enable interrupt 3317 remapping. 3318 [Deprecated - use intremap=off] 3319 3320 nointroute [IA-64] 3321 3322 noinvpcid [X86] Disable the INVPCID cpu feature. 3323 3324 nojitter [IA-64] Disables jitter checking for ITC timers. 3325 3326 no-kvmclock [X86,KVM] Disable paravirtualized KVM clock driver 3327 3328 no-kvmapf [X86,KVM] Disable paravirtualized asynchronous page 3329 fault handling. 3330 3331 no-vmw-sched-clock 3332 [X86,PV_OPS] Disable paravirtualized VMware scheduler 3333 clock and use the default one. 3334 3335 no-steal-acc [X86,PV_OPS,ARM64] Disable paravirtualized steal time 3336 accounting. steal time is computed, but won't 3337 influence scheduler behaviour 3338 3339 nolapic [X86-32,APIC] Do not enable or use the local APIC. 3340 3341 nolapic_timer [X86-32,APIC] Do not use the local APIC timer. 3342 3343 noltlbs [PPC] Do not use large page/tlb entries for kernel 3344 lowmem mapping on PPC40x and PPC8xx 3345 3346 nomca [IA-64] Disable machine check abort handling 3347 3348 nomce [X86-32] Disable Machine Check Exception 3349 3350 nomfgpt [X86-32] Disable Multi-Function General Purpose 3351 Timer usage (for AMD Geode machines). 3352 3353 nonmi_ipi [X86] Disable using NMI IPIs during panic/reboot to 3354 shutdown the other cpus. Instead use the REBOOT_VECTOR 3355 irq. 3356 3357 nomodule Disable module load 3358 3359 nopat [X86] Disable PAT (page attribute table extension of 3360 pagetables) support. 3361 3362 nopcid [X86-64] Disable the PCID cpu feature. 3363 3364 norandmaps Don't use address space randomization. Equivalent to 3365 echo 0 > /proc/sys/kernel/randomize_va_space 3366 3367 noreplace-smp [X86-32,SMP] Don't replace SMP instructions 3368 with UP alternatives 3369 3370 nordrand [X86] Disable kernel use of the RDRAND and 3371 RDSEED instructions even if they are supported 3372 by the processor. RDRAND and RDSEED are still 3373 available to user space applications. 3374 3375 noresume [SWSUSP] Disables resume and restores original swap 3376 space. 3377 3378 no-scroll [VGA] Disables scrollback. 3379 This is required for the Braillex ib80-piezo Braille 3380 reader made by F.H. Papenmeier (Germany). 3381 3382 nosbagart [IA-64] 3383 3384 nosep [BUGS=X86-32] Disables x86 SYSENTER/SYSEXIT support. 3385 3386 nosgx [X86-64,SGX] Disables Intel SGX kernel support. 3387 3388 nosmp [SMP] Tells an SMP kernel to act as a UP kernel, 3389 and disable the IO APIC. legacy for "maxcpus=0". 3390 3391 nosoftlockup [KNL] Disable the soft-lockup detector. 3392 3393 nosync [HW,M68K] Disables sync negotiation for all devices. 3394 3395 nowatchdog [KNL] Disable both lockup detectors, i.e. 3396 soft-lockup and NMI watchdog (hard-lockup). 3397 3398 nowb [ARM] 3399 3400 nox2apic [X86-64,APIC] Do not enable x2APIC mode. 3401 3402 cpu0_hotplug [X86] Turn on CPU0 hotplug feature when 3403 CONFIG_BOOTPARAM_HOTPLUG_CPU0 is off. 3404 Some features depend on CPU0. Known dependencies are: 3405 1. Resume from suspend/hibernate depends on CPU0. 3406 Suspend/hibernate will fail if CPU0 is offline and you 3407 need to online CPU0 before suspend/hibernate. 3408 2. PIC interrupts also depend on CPU0. CPU0 can't be 3409 removed if a PIC interrupt is detected. 3410 It's said poweroff/reboot may depend on CPU0 on some 3411 machines although I haven't seen such issues so far 3412 after CPU0 is offline on a few tested machines. 3413 If the dependencies are under your control, you can 3414 turn on cpu0_hotplug. 3415 3416 nps_mtm_hs_ctr= [KNL,ARC] 3417 This parameter sets the maximum duration, in 3418 cycles, each HW thread of the CTOP can run 3419 without interruptions, before HW switches it. 3420 The actual maximum duration is 16 times this 3421 parameter's value. 3422 Format: integer between 1 and 255 3423 Default: 255 3424 3425 nptcg= [IA-64] Override max number of concurrent global TLB 3426 purges which is reported from either PAL_VM_SUMMARY or 3427 SAL PALO. 3428 3429 nr_cpus= [SMP] Maximum number of processors that an SMP kernel 3430 could support. nr_cpus=n : n >= 1 limits the kernel to 3431 support 'n' processors. It could be larger than the 3432 number of already plugged CPU during bootup, later in 3433 runtime you can physically add extra cpu until it reaches 3434 n. So during boot up some boot time memory for per-cpu 3435 variables need be pre-allocated for later physical cpu 3436 hot plugging. 3437 3438 nr_uarts= [SERIAL] maximum number of UARTs to be registered. 3439 3440 numa_balancing= [KNL,X86] Enable or disable automatic NUMA balancing. 3441 Allowed values are enable and disable 3442 3443 numa_zonelist_order= [KNL, BOOT] Select zonelist order for NUMA. 3444 'node', 'default' can be specified 3445 This can be set from sysctl after boot. 3446 See Documentation/admin-guide/sysctl/vm.rst for details. 3447 3448 ohci1394_dma=early [HW] enable debugging via the ohci1394 driver. 3449 See Documentation/core-api/debugging-via-ohci1394.rst for more 3450 info. 3451 3452 olpc_ec_timeout= [OLPC] ms delay when issuing EC commands 3453 Rather than timing out after 20 ms if an EC 3454 command is not properly ACKed, override the length 3455 of the timeout. We have interrupts disabled while 3456 waiting for the ACK, so if this is set too high 3457 interrupts *may* be lost! 3458 3459 omap_mux= [OMAP] Override bootloader pin multiplexing. 3460 Format: <mux_mode0.mode_name=value>... 3461 For example, to override I2C bus2: 3462 omap_mux=i2c2_scl.i2c2_scl=0x100,i2c2_sda.i2c2_sda=0x100 3463 3464 oprofile.timer= [HW] 3465 Use timer interrupt instead of performance counters 3466 3467 oprofile.cpu_type= Force an oprofile cpu type 3468 This might be useful if you have an older oprofile 3469 userland or if you want common events. 3470 Format: { arch_perfmon } 3471 arch_perfmon: [X86] Force use of architectural 3472 perfmon on Intel CPUs instead of the 3473 CPU specific event set. 3474 timer: [X86] Force use of architectural NMI 3475 timer mode (see also oprofile.timer 3476 for generic hr timer mode) 3477 3478 oops=panic Always panic on oopses. Default is to just kill the 3479 process, but there is a small probability of 3480 deadlocking the machine. 3481 This will also cause panics on machine check exceptions. 3482 Useful together with panic=30 to trigger a reboot. 3483 3484 page_alloc.shuffle= 3485 [KNL] Boolean flag to control whether the page allocator 3486 should randomize its free lists. The randomization may 3487 be automatically enabled if the kernel detects it is 3488 running on a platform with a direct-mapped memory-side 3489 cache, and this parameter can be used to 3490 override/disable that behavior. The state of the flag 3491 can be read from sysfs at: 3492 /sys/module/page_alloc/parameters/shuffle. 3493 3494 page_owner= [KNL] Boot-time page_owner enabling option. 3495 Storage of the information about who allocated 3496 each page is disabled in default. With this switch, 3497 we can turn it on. 3498 on: enable the feature 3499 3500 page_poison= [KNL] Boot-time parameter changing the state of 3501 poisoning on the buddy allocator, available with 3502 CONFIG_PAGE_POISONING=y. 3503 off: turn off poisoning (default) 3504 on: turn on poisoning 3505 3506 panic= [KNL] Kernel behaviour on panic: delay <timeout> 3507 timeout > 0: seconds before rebooting 3508 timeout = 0: wait forever 3509 timeout < 0: reboot immediately 3510 Format: <timeout> 3511 3512 panic_print= Bitmask for printing system info when panic happens. 3513 User can chose combination of the following bits: 3514 bit 0: print all tasks info 3515 bit 1: print system memory info 3516 bit 2: print timer info 3517 bit 3: print locks info if CONFIG_LOCKDEP is on 3518 bit 4: print ftrace buffer 3519 bit 5: print all printk messages in buffer 3520 3521 panic_on_taint= Bitmask for conditionally calling panic() in add_taint() 3522 Format: <hex>[,nousertaint] 3523 Hexadecimal bitmask representing the set of TAINT flags 3524 that will cause the kernel to panic when add_taint() is 3525 called with any of the flags in this set. 3526 The optional switch "nousertaint" can be utilized to 3527 prevent userspace forced crashes by writing to sysctl 3528 /proc/sys/kernel/tainted any flagset matching with the 3529 bitmask set on panic_on_taint. 3530 See Documentation/admin-guide/tainted-kernels.rst for 3531 extra details on the taint flags that users can pick 3532 to compose the bitmask to assign to panic_on_taint. 3533 3534 panic_on_warn panic() instead of WARN(). Useful to cause kdump 3535 on a WARN(). 3536 3537 crash_kexec_post_notifiers 3538 Run kdump after running panic-notifiers and dumping 3539 kmsg. This only for the users who doubt kdump always 3540 succeeds in any situation. 3541 Note that this also increases risks of kdump failure, 3542 because some panic notifiers can make the crashed 3543 kernel more unstable. 3544 3545 parkbd.port= [HW] Parallel port number the keyboard adapter is 3546 connected to, default is 0. 3547 Format: <parport#> 3548 parkbd.mode= [HW] Parallel port keyboard adapter mode of operation, 3549 0 for XT, 1 for AT (default is AT). 3550 Format: <mode> 3551 3552 parport= [HW,PPT] Specify parallel ports. 0 disables. 3553 Format: { 0 | auto | 0xBBB[,IRQ[,DMA]] } 3554 Use 'auto' to force the driver to use any 3555 IRQ/DMA settings detected (the default is to 3556 ignore detected IRQ/DMA settings because of 3557 possible conflicts). You can specify the base 3558 address, IRQ, and DMA settings; IRQ and DMA 3559 should be numbers, or 'auto' (for using detected 3560 settings on that particular port), or 'nofifo' 3561 (to avoid using a FIFO even if it is detected). 3562 Parallel ports are assigned in the order they 3563 are specified on the command line, starting 3564 with parport0. 3565 3566 parport_init_mode= [HW,PPT] 3567 Configure VIA parallel port to operate in 3568 a specific mode. This is necessary on Pegasos 3569 computer where firmware has no options for setting 3570 up parallel port mode and sets it to spp. 3571 Currently this function knows 686a and 8231 chips. 3572 Format: [spp|ps2|epp|ecp|ecpepp] 3573 3574 pause_on_oops= 3575 Halt all CPUs after the first oops has been printed for 3576 the specified number of seconds. This is to be used if 3577 your oopses keep scrolling off the screen. 3578 3579 pcbit= [HW,ISDN] 3580 3581 pcd. [PARIDE] 3582 See header of drivers/block/paride/pcd.c. 3583 See also Documentation/admin-guide/blockdev/paride.rst. 3584 3585 pci=option[,option...] [PCI] various PCI subsystem options. 3586 3587 Some options herein operate on a specific device 3588 or a set of devices (<pci_dev>). These are 3589 specified in one of the following formats: 3590 3591 [<domain>:]<bus>:<dev>.<func>[/<dev>.<func>]* 3592 pci:<vendor>:<device>[:<subvendor>:<subdevice>] 3593 3594 Note: the first format specifies a PCI 3595 bus/device/function address which may change 3596 if new hardware is inserted, if motherboard 3597 firmware changes, or due to changes caused 3598 by other kernel parameters. If the 3599 domain is left unspecified, it is 3600 taken to be zero. Optionally, a path 3601 to a device through multiple device/function 3602 addresses can be specified after the base 3603 address (this is more robust against 3604 renumbering issues). The second format 3605 selects devices using IDs from the 3606 configuration space which may match multiple 3607 devices in the system. 3608 3609 earlydump dump PCI config space before the kernel 3610 changes anything 3611 off [X86] don't probe for the PCI bus 3612 bios [X86-32] force use of PCI BIOS, don't access 3613 the hardware directly. Use this if your machine 3614 has a non-standard PCI host bridge. 3615 nobios [X86-32] disallow use of PCI BIOS, only direct 3616 hardware access methods are allowed. Use this 3617 if you experience crashes upon bootup and you 3618 suspect they are caused by the BIOS. 3619 conf1 [X86] Force use of PCI Configuration Access 3620 Mechanism 1 (config address in IO port 0xCF8, 3621 data in IO port 0xCFC, both 32-bit). 3622 conf2 [X86] Force use of PCI Configuration Access 3623 Mechanism 2 (IO port 0xCF8 is an 8-bit port for 3624 the function, IO port 0xCFA, also 8-bit, sets 3625 bus number. The config space is then accessed 3626 through ports 0xC000-0xCFFF). 3627 See http://wiki.osdev.org/PCI for more info 3628 on the configuration access mechanisms. 3629 noaer [PCIE] If the PCIEAER kernel config parameter is 3630 enabled, this kernel boot option can be used to 3631 disable the use of PCIE advanced error reporting. 3632 nodomains [PCI] Disable support for multiple PCI 3633 root domains (aka PCI segments, in ACPI-speak). 3634 nommconf [X86] Disable use of MMCONFIG for PCI 3635 Configuration 3636 check_enable_amd_mmconf [X86] check for and enable 3637 properly configured MMIO access to PCI 3638 config space on AMD family 10h CPU 3639 nomsi [MSI] If the PCI_MSI kernel config parameter is 3640 enabled, this kernel boot option can be used to 3641 disable the use of MSI interrupts system-wide. 3642 noioapicquirk [APIC] Disable all boot interrupt quirks. 3643 Safety option to keep boot IRQs enabled. This 3644 should never be necessary. 3645 ioapicreroute [APIC] Enable rerouting of boot IRQs to the 3646 primary IO-APIC for bridges that cannot disable 3647 boot IRQs. This fixes a source of spurious IRQs 3648 when the system masks IRQs. 3649 noioapicreroute [APIC] Disable workaround that uses the 3650 boot IRQ equivalent of an IRQ that connects to 3651 a chipset where boot IRQs cannot be disabled. 3652 The opposite of ioapicreroute. 3653 biosirq [X86-32] Use PCI BIOS calls to get the interrupt 3654 routing table. These calls are known to be buggy 3655 on several machines and they hang the machine 3656 when used, but on other computers it's the only 3657 way to get the interrupt routing table. Try 3658 this option if the kernel is unable to allocate 3659 IRQs or discover secondary PCI buses on your 3660 motherboard. 3661 rom [X86] Assign address space to expansion ROMs. 3662 Use with caution as certain devices share 3663 address decoders between ROMs and other 3664 resources. 3665 norom [X86] Do not assign address space to 3666 expansion ROMs that do not already have 3667 BIOS assigned address ranges. 3668 nobar [X86] Do not assign address space to the 3669 BARs that weren't assigned by the BIOS. 3670 irqmask=0xMMMM [X86] Set a bit mask of IRQs allowed to be 3671 assigned automatically to PCI devices. You can 3672 make the kernel exclude IRQs of your ISA cards 3673 this way. 3674 pirqaddr=0xAAAAA [X86] Specify the physical address 3675 of the PIRQ table (normally generated 3676 by the BIOS) if it is outside the 3677 F0000h-100000h range. 3678 lastbus=N [X86] Scan all buses thru bus #N. Can be 3679 useful if the kernel is unable to find your 3680 secondary buses and you want to tell it 3681 explicitly which ones they are. 3682 assign-busses [X86] Always assign all PCI bus 3683 numbers ourselves, overriding 3684 whatever the firmware may have done. 3685 usepirqmask [X86] Honor the possible IRQ mask stored 3686 in the BIOS $PIR table. This is needed on 3687 some systems with broken BIOSes, notably 3688 some HP Pavilion N5400 and Omnibook XE3 3689 notebooks. This will have no effect if ACPI 3690 IRQ routing is enabled. 3691 noacpi [X86] Do not use ACPI for IRQ routing 3692 or for PCI scanning. 3693 use_crs [X86] Use PCI host bridge window information 3694 from ACPI. On BIOSes from 2008 or later, this 3695 is enabled by default. If you need to use this, 3696 please report a bug. 3697 nocrs [X86] Ignore PCI host bridge windows from ACPI. 3698 If you need to use this, please report a bug. 3699 routeirq Do IRQ routing for all PCI devices. 3700 This is normally done in pci_enable_device(), 3701 so this option is a temporary workaround 3702 for broken drivers that don't call it. 3703 skip_isa_align [X86] do not align io start addr, so can 3704 handle more pci cards 3705 noearly [X86] Don't do any early type 1 scanning. 3706 This might help on some broken boards which 3707 machine check when some devices' config space 3708 is read. But various workarounds are disabled 3709 and some IOMMU drivers will not work. 3710 bfsort Sort PCI devices into breadth-first order. 3711 This sorting is done to get a device 3712 order compatible with older (<= 2.4) kernels. 3713 nobfsort Don't sort PCI devices into breadth-first order. 3714 pcie_bus_tune_off Disable PCIe MPS (Max Payload Size) 3715 tuning and use the BIOS-configured MPS defaults. 3716 pcie_bus_safe Set every device's MPS to the largest value 3717 supported by all devices below the root complex. 3718 pcie_bus_perf Set device MPS to the largest allowable MPS 3719 based on its parent bus. Also set MRRS (Max 3720 Read Request Size) to the largest supported 3721 value (no larger than the MPS that the device 3722 or bus can support) for best performance. 3723 pcie_bus_peer2peer Set every device's MPS to 128B, which 3724 every device is guaranteed to support. This 3725 configuration allows peer-to-peer DMA between 3726 any pair of devices, possibly at the cost of 3727 reduced performance. This also guarantees 3728 that hot-added devices will work. 3729 cbiosize=nn[KMG] The fixed amount of bus space which is 3730 reserved for the CardBus bridge's IO window. 3731 The default value is 256 bytes. 3732 cbmemsize=nn[KMG] The fixed amount of bus space which is 3733 reserved for the CardBus bridge's memory 3734 window. The default value is 64 megabytes. 3735 resource_alignment= 3736 Format: 3737 [<order of align>@]<pci_dev>[; ...] 3738 Specifies alignment and device to reassign 3739 aligned memory resources. How to 3740 specify the device is described above. 3741 If <order of align> is not specified, 3742 PAGE_SIZE is used as alignment. 3743 A PCI-PCI bridge can be specified if resource 3744 windows need to be expanded. 3745 To specify the alignment for several 3746 instances of a device, the PCI vendor, 3747 device, subvendor, and subdevice may be 3748 specified, e.g., 12@pci:8086:9c22:103c:198f 3749 for 4096-byte alignment. 3750 ecrc= Enable/disable PCIe ECRC (transaction layer 3751 end-to-end CRC checking). 3752 bios: Use BIOS/firmware settings. This is the 3753 the default. 3754 off: Turn ECRC off 3755 on: Turn ECRC on. 3756 hpiosize=nn[KMG] The fixed amount of bus space which is 3757 reserved for hotplug bridge's IO window. 3758 Default size is 256 bytes. 3759 hpmmiosize=nn[KMG] The fixed amount of bus space which is 3760 reserved for hotplug bridge's MMIO window. 3761 Default size is 2 megabytes. 3762 hpmmioprefsize=nn[KMG] The fixed amount of bus space which is 3763 reserved for hotplug bridge's MMIO_PREF window. 3764 Default size is 2 megabytes. 3765 hpmemsize=nn[KMG] The fixed amount of bus space which is 3766 reserved for hotplug bridge's MMIO and 3767 MMIO_PREF window. 3768 Default size is 2 megabytes. 3769 hpbussize=nn The minimum amount of additional bus numbers 3770 reserved for buses below a hotplug bridge. 3771 Default is 1. 3772 realloc= Enable/disable reallocating PCI bridge resources 3773 if allocations done by BIOS are too small to 3774 accommodate resources required by all child 3775 devices. 3776 off: Turn realloc off 3777 on: Turn realloc on 3778 realloc same as realloc=on 3779 noari do not use PCIe ARI. 3780 noats [PCIE, Intel-IOMMU, AMD-IOMMU] 3781 do not use PCIe ATS (and IOMMU device IOTLB). 3782 pcie_scan_all Scan all possible PCIe devices. Otherwise we 3783 only look for one device below a PCIe downstream 3784 port. 3785 big_root_window Try to add a big 64bit memory window to the PCIe 3786 root complex on AMD CPUs. Some GFX hardware 3787 can resize a BAR to allow access to all VRAM. 3788 Adding the window is slightly risky (it may 3789 conflict with unreported devices), so this 3790 taints the kernel. 3791 disable_acs_redir=<pci_dev>[; ...] 3792 Specify one or more PCI devices (in the format 3793 specified above) separated by semicolons. 3794 Each device specified will have the PCI ACS 3795 redirect capabilities forced off which will 3796 allow P2P traffic between devices through 3797 bridges without forcing it upstream. Note: 3798 this removes isolation between devices and 3799 may put more devices in an IOMMU group. 3800 force_floating [S390] Force usage of floating interrupts. 3801 nomio [S390] Do not use MIO instructions. 3802 norid [S390] ignore the RID field and force use of 3803 one PCI domain per PCI function 3804 3805 pcie_aspm= [PCIE] Forcibly enable or disable PCIe Active State Power 3806 Management. 3807 off Disable ASPM. 3808 force Enable ASPM even on devices that claim not to support it. 3809 WARNING: Forcing ASPM on may cause system lockups. 3810 3811 pcie_ports= [PCIE] PCIe port services handling: 3812 native Use native PCIe services (PME, AER, DPC, PCIe hotplug) 3813 even if the platform doesn't give the OS permission to 3814 use them. This may cause conflicts if the platform 3815 also tries to use these services. 3816 dpc-native Use native PCIe service for DPC only. May 3817 cause conflicts if firmware uses AER or DPC. 3818 compat Disable native PCIe services (PME, AER, DPC, PCIe 3819 hotplug). 3820 3821 pcie_port_pm= [PCIE] PCIe port power management handling: 3822 off Disable power management of all PCIe ports 3823 force Forcibly enable power management of all PCIe ports 3824 3825 pcie_pme= [PCIE,PM] Native PCIe PME signaling options: 3826 nomsi Do not use MSI for native PCIe PME signaling (this makes 3827 all PCIe root ports use INTx for all services). 3828 3829 pcmv= [HW,PCMCIA] BadgePAD 4 3830 3831 pd_ignore_unused 3832 [PM] 3833 Keep all power-domains already enabled by bootloader on, 3834 even if no driver has claimed them. This is useful 3835 for debug and development, but should not be 3836 needed on a platform with proper driver support. 3837 3838 pd. [PARIDE] 3839 See Documentation/admin-guide/blockdev/paride.rst. 3840 3841 pdcchassis= [PARISC,HW] Disable/Enable PDC Chassis Status codes at 3842 boot time. 3843 Format: { 0 | 1 } 3844 See arch/parisc/kernel/pdc_chassis.c 3845 3846 percpu_alloc= Select which percpu first chunk allocator to use. 3847 Currently supported values are "embed" and "page". 3848 Archs may support subset or none of the selections. 3849 See comments in mm/percpu.c for details on each 3850 allocator. This parameter is primarily for debugging 3851 and performance comparison. 3852 3853 pf. [PARIDE] 3854 See Documentation/admin-guide/blockdev/paride.rst. 3855 3856 pg. [PARIDE] 3857 See Documentation/admin-guide/blockdev/paride.rst. 3858 3859 pirq= [SMP,APIC] Manual mp-table setup 3860 See Documentation/x86/i386/IO-APIC.rst. 3861 3862 plip= [PPT,NET] Parallel port network link 3863 Format: { parport<nr> | timid | 0 } 3864 See also Documentation/admin-guide/parport.rst. 3865 3866 pmtmr= [X86] Manual setup of pmtmr I/O Port. 3867 Override pmtimer IOPort with a hex value. 3868 e.g. pmtmr=0x508 3869 3870 pm_debug_messages [SUSPEND,KNL] 3871 Enable suspend/resume debug messages during boot up. 3872 3873 pnp.debug=1 [PNP] 3874 Enable PNP debug messages (depends on the 3875 CONFIG_PNP_DEBUG_MESSAGES option). Change at run-time 3876 via /sys/module/pnp/parameters/debug. We always show 3877 current resource usage; turning this on also shows 3878 possible settings and some assignment information. 3879 3880 pnpacpi= [ACPI] 3881 { off } 3882 3883 pnpbios= [ISAPNP] 3884 { on | off | curr | res | no-curr | no-res } 3885 3886 pnp_reserve_irq= 3887 [ISAPNP] Exclude IRQs for the autoconfiguration 3888 3889 pnp_reserve_dma= 3890 [ISAPNP] Exclude DMAs for the autoconfiguration 3891 3892 pnp_reserve_io= [ISAPNP] Exclude I/O ports for the autoconfiguration 3893 Ranges are in pairs (I/O port base and size). 3894 3895 pnp_reserve_mem= 3896 [ISAPNP] Exclude memory regions for the 3897 autoconfiguration. 3898 Ranges are in pairs (memory base and size). 3899 3900 ports= [IP_VS_FTP] IPVS ftp helper module 3901 Default is 21. 3902 Up to 8 (IP_VS_APP_MAX_PORTS) ports 3903 may be specified. 3904 Format: <port>,<port>.... 3905 3906 powersave=off [PPC] This option disables power saving features. 3907 It specifically disables cpuidle and sets the 3908 platform machine description specific power_save 3909 function to NULL. On Idle the CPU just reduces 3910 execution priority. 3911 3912 ppc_strict_facility_enable 3913 [PPC] This option catches any kernel floating point, 3914 Altivec, VSX and SPE outside of regions specifically 3915 allowed (eg kernel_enable_fpu()/kernel_disable_fpu()). 3916 There is some performance impact when enabling this. 3917 3918 ppc_tm= [PPC] 3919 Format: {"off"} 3920 Disable Hardware Transactional Memory 3921 3922 print-fatal-signals= 3923 [KNL] debug: print fatal signals 3924 3925 If enabled, warn about various signal handling 3926 related application anomalies: too many signals, 3927 too many POSIX.1 timers, fatal signals causing a 3928 coredump - etc. 3929 3930 If you hit the warning due to signal overflow, 3931 you might want to try "ulimit -i unlimited". 3932 3933 default: off. 3934 3935 printk.always_kmsg_dump= 3936 Trigger kmsg_dump for cases other than kernel oops or 3937 panics 3938 Format: <bool> (1/Y/y=enable, 0/N/n=disable) 3939 default: disabled 3940 3941 printk.devkmsg={on,off,ratelimit} 3942 Control writing to /dev/kmsg. 3943 on - unlimited logging to /dev/kmsg from userspace 3944 off - logging to /dev/kmsg disabled 3945 ratelimit - ratelimit the logging 3946 Default: ratelimit 3947 3948 printk.time= Show timing data prefixed to each printk message line 3949 Format: <bool> (1/Y/y=enable, 0/N/n=disable) 3950 3951 processor.max_cstate= [HW,ACPI] 3952 Limit processor to maximum C-state 3953 max_cstate=9 overrides any DMI blacklist limit. 3954 3955 processor.nocst [HW,ACPI] 3956 Ignore the _CST method to determine C-states, 3957 instead using the legacy FADT method 3958 3959 profile= [KNL] Enable kernel profiling via /proc/profile 3960 Format: [<profiletype>,]<number> 3961 Param: <profiletype>: "schedule", "sleep", or "kvm" 3962 [defaults to kernel profiling] 3963 Param: "schedule" - profile schedule points. 3964 Param: "sleep" - profile D-state sleeping (millisecs). 3965 Requires CONFIG_SCHEDSTATS 3966 Param: "kvm" - profile VM exits. 3967 Param: <number> - step/bucket size as a power of 2 for 3968 statistical time based profiling. 3969 3970 prompt_ramdisk= [RAM] [Deprecated] 3971 3972 prot_virt= [S390] enable hosting protected virtual machines 3973 isolated from the hypervisor (if hardware supports 3974 that). 3975 Format: <bool> 3976 3977 psi= [KNL] Enable or disable pressure stall information 3978 tracking. 3979 Format: <bool> 3980 3981 psmouse.proto= [HW,MOUSE] Highest PS2 mouse protocol extension to 3982 probe for; one of (bare|imps|exps|lifebook|any). 3983 psmouse.rate= [HW,MOUSE] Set desired mouse report rate, in reports 3984 per second. 3985 psmouse.resetafter= [HW,MOUSE] 3986 Try to reset the device after so many bad packets 3987 (0 = never). 3988 psmouse.resolution= 3989 [HW,MOUSE] Set desired mouse resolution, in dpi. 3990 psmouse.smartscroll= 3991 [HW,MOUSE] Controls Logitech smartscroll autorepeat. 3992 0 = disabled, 1 = enabled (default). 3993 3994 pstore.backend= Specify the name of the pstore backend to use 3995 3996 pt. [PARIDE] 3997 See Documentation/admin-guide/blockdev/paride.rst. 3998 3999 pti= [X86-64] Control Page Table Isolation of user and 4000 kernel address spaces. Disabling this feature 4001 removes hardening, but improves performance of 4002 system calls and interrupts. 4003 4004 on - unconditionally enable 4005 off - unconditionally disable 4006 auto - kernel detects whether your CPU model is 4007 vulnerable to issues that PTI mitigates 4008 4009 Not specifying this option is equivalent to pti=auto. 4010 4011 nopti [X86-64] 4012 Equivalent to pti=off 4013 4014 pty.legacy_count= 4015 [KNL] Number of legacy pty's. Overwrites compiled-in 4016 default number. 4017 4018 quiet [KNL] Disable most log messages 4019 4020 r128= [HW,DRM] 4021 4022 raid= [HW,RAID] 4023 See Documentation/admin-guide/md.rst. 4024 4025 ramdisk_size= [RAM] Sizes of RAM disks in kilobytes 4026 See Documentation/admin-guide/blockdev/ramdisk.rst. 4027 4028 ramdisk_start= [RAM] RAM disk image start address 4029 4030 random.trust_cpu={on,off} 4031 [KNL] Enable or disable trusting the use of the 4032 CPU's random number generator (if available) to 4033 fully seed the kernel's CRNG. Default is controlled 4034 by CONFIG_RANDOM_TRUST_CPU. 4035 4036 ras=option[,option,...] [KNL] RAS-specific options 4037 4038 cec_disable [X86] 4039 Disable the Correctable Errors Collector, 4040 see CONFIG_RAS_CEC help text. 4041 4042 rcu_nocbs= [KNL] 4043 The argument is a cpu list, as described above, 4044 except that the string "all" can be used to 4045 specify every CPU on the system. 4046 4047 In kernels built with CONFIG_RCU_NOCB_CPU=y, set 4048 the specified list of CPUs to be no-callback CPUs. 4049 Invocation of these CPUs' RCU callbacks will be 4050 offloaded to "rcuox/N" kthreads created for that 4051 purpose, where "x" is "p" for RCU-preempt, and 4052 "s" for RCU-sched, and "N" is the CPU number. 4053 This reduces OS jitter on the offloaded CPUs, 4054 which can be useful for HPC and real-time 4055 workloads. It can also improve energy efficiency 4056 for asymmetric multiprocessors. 4057 4058 rcu_nocb_poll [KNL] 4059 Rather than requiring that offloaded CPUs 4060 (specified by rcu_nocbs= above) explicitly 4061 awaken the corresponding "rcuoN" kthreads, 4062 make these kthreads poll for callbacks. 4063 This improves the real-time response for the 4064 offloaded CPUs by relieving them of the need to 4065 wake up the corresponding kthread, but degrades 4066 energy efficiency by requiring that the kthreads 4067 periodically wake up to do the polling. 4068 4069 rcutree.blimit= [KNL] 4070 Set maximum number of finished RCU callbacks to 4071 process in one batch. 4072 4073 rcutree.dump_tree= [KNL] 4074 Dump the structure of the rcu_node combining tree 4075 out at early boot. This is used for diagnostic 4076 purposes, to verify correct tree setup. 4077 4078 rcutree.gp_cleanup_delay= [KNL] 4079 Set the number of jiffies to delay each step of 4080 RCU grace-period cleanup. 4081 4082 rcutree.gp_init_delay= [KNL] 4083 Set the number of jiffies to delay each step of 4084 RCU grace-period initialization. 4085 4086 rcutree.gp_preinit_delay= [KNL] 4087 Set the number of jiffies to delay each step of 4088 RCU grace-period pre-initialization, that is, 4089 the propagation of recent CPU-hotplug changes up 4090 the rcu_node combining tree. 4091 4092 rcutree.use_softirq= [KNL] 4093 If set to zero, move all RCU_SOFTIRQ processing to 4094 per-CPU rcuc kthreads. Defaults to a non-zero 4095 value, meaning that RCU_SOFTIRQ is used by default. 4096 Specify rcutree.use_softirq=0 to use rcuc kthreads. 4097 4098 rcutree.rcu_fanout_exact= [KNL] 4099 Disable autobalancing of the rcu_node combining 4100 tree. This is used by rcutorture, and might 4101 possibly be useful for architectures having high 4102 cache-to-cache transfer latencies. 4103 4104 rcutree.rcu_fanout_leaf= [KNL] 4105 Change the number of CPUs assigned to each 4106 leaf rcu_node structure. Useful for very 4107 large systems, which will choose the value 64, 4108 and for NUMA systems with large remote-access 4109 latencies, which will choose a value aligned 4110 with the appropriate hardware boundaries. 4111 4112 rcutree.rcu_min_cached_objs= [KNL] 4113 Minimum number of objects which are cached and 4114 maintained per one CPU. Object size is equal 4115 to PAGE_SIZE. The cache allows to reduce the 4116 pressure to page allocator, also it makes the 4117 whole algorithm to behave better in low memory 4118 condition. 4119 4120 rcutree.jiffies_till_first_fqs= [KNL] 4121 Set delay from grace-period initialization to 4122 first attempt to force quiescent states. 4123 Units are jiffies, minimum value is zero, 4124 and maximum value is HZ. 4125 4126 rcutree.jiffies_till_next_fqs= [KNL] 4127 Set delay between subsequent attempts to force 4128 quiescent states. Units are jiffies, minimum 4129 value is one, and maximum value is HZ. 4130 4131 rcutree.jiffies_till_sched_qs= [KNL] 4132 Set required age in jiffies for a 4133 given grace period before RCU starts 4134 soliciting quiescent-state help from 4135 rcu_note_context_switch() and cond_resched(). 4136 If not specified, the kernel will calculate 4137 a value based on the most recent settings 4138 of rcutree.jiffies_till_first_fqs 4139 and rcutree.jiffies_till_next_fqs. 4140 This calculated value may be viewed in 4141 rcutree.jiffies_to_sched_qs. Any attempt to set 4142 rcutree.jiffies_to_sched_qs will be cheerfully 4143 overwritten. 4144 4145 rcutree.kthread_prio= [KNL,BOOT] 4146 Set the SCHED_FIFO priority of the RCU per-CPU 4147 kthreads (rcuc/N). This value is also used for 4148 the priority of the RCU boost threads (rcub/N) 4149 and for the RCU grace-period kthreads (rcu_bh, 4150 rcu_preempt, and rcu_sched). If RCU_BOOST is 4151 set, valid values are 1-99 and the default is 1 4152 (the least-favored priority). Otherwise, when 4153 RCU_BOOST is not set, valid values are 0-99 and 4154 the default is zero (non-realtime operation). 4155 4156 rcutree.rcu_nocb_gp_stride= [KNL] 4157 Set the number of NOCB callback kthreads in 4158 each group, which defaults to the square root 4159 of the number of CPUs. Larger numbers reduce 4160 the wakeup overhead on the global grace-period 4161 kthread, but increases that same overhead on 4162 each group's NOCB grace-period kthread. 4163 4164 rcutree.qhimark= [KNL] 4165 Set threshold of queued RCU callbacks beyond which 4166 batch limiting is disabled. 4167 4168 rcutree.qlowmark= [KNL] 4169 Set threshold of queued RCU callbacks below which 4170 batch limiting is re-enabled. 4171 4172 rcutree.qovld= [KNL] 4173 Set threshold of queued RCU callbacks beyond which 4174 RCU's force-quiescent-state scan will aggressively 4175 enlist help from cond_resched() and sched IPIs to 4176 help CPUs more quickly reach quiescent states. 4177 Set to less than zero to make this be set based 4178 on rcutree.qhimark at boot time and to zero to 4179 disable more aggressive help enlistment. 4180 4181 rcutree.rcu_idle_gp_delay= [KNL] 4182 Set wakeup interval for idle CPUs that have 4183 RCU callbacks (RCU_FAST_NO_HZ=y). 4184 4185 rcutree.rcu_idle_lazy_gp_delay= [KNL] 4186 Set wakeup interval for idle CPUs that have 4187 only "lazy" RCU callbacks (RCU_FAST_NO_HZ=y). 4188 Lazy RCU callbacks are those which RCU can 4189 prove do nothing more than free memory. 4190 4191 rcutree.rcu_kick_kthreads= [KNL] 4192 Cause the grace-period kthread to get an extra 4193 wake_up() if it sleeps three times longer than 4194 it should at force-quiescent-state time. 4195 This wake_up() will be accompanied by a 4196 WARN_ONCE() splat and an ftrace_dump(). 4197 4198 rcutree.rcu_unlock_delay= [KNL] 4199 In CONFIG_RCU_STRICT_GRACE_PERIOD=y kernels, 4200 this specifies an rcu_read_unlock()-time delay 4201 in microseconds. This defaults to zero. 4202 Larger delays increase the probability of 4203 catching RCU pointer leaks, that is, buggy use 4204 of RCU-protected pointers after the relevant 4205 rcu_read_unlock() has completed. 4206 4207 rcutree.sysrq_rcu= [KNL] 4208 Commandeer a sysrq key to dump out Tree RCU's 4209 rcu_node tree with an eye towards determining 4210 why a new grace period has not yet started. 4211 4212 rcuscale.gp_async= [KNL] 4213 Measure performance of asynchronous 4214 grace-period primitives such as call_rcu(). 4215 4216 rcuscale.gp_async_max= [KNL] 4217 Specify the maximum number of outstanding 4218 callbacks per writer thread. When a writer 4219 thread exceeds this limit, it invokes the 4220 corresponding flavor of rcu_barrier() to allow 4221 previously posted callbacks to drain. 4222 4223 rcuscale.gp_exp= [KNL] 4224 Measure performance of expedited synchronous 4225 grace-period primitives. 4226 4227 rcuscale.holdoff= [KNL] 4228 Set test-start holdoff period. The purpose of 4229 this parameter is to delay the start of the 4230 test until boot completes in order to avoid 4231 interference. 4232 4233 rcuscale.kfree_rcu_test= [KNL] 4234 Set to measure performance of kfree_rcu() flooding. 4235 4236 rcuscale.kfree_nthreads= [KNL] 4237 The number of threads running loops of kfree_rcu(). 4238 4239 rcuscale.kfree_alloc_num= [KNL] 4240 Number of allocations and frees done in an iteration. 4241 4242 rcuscale.kfree_loops= [KNL] 4243 Number of loops doing rcuscale.kfree_alloc_num number 4244 of allocations and frees. 4245 4246 rcuscale.nreaders= [KNL] 4247 Set number of RCU readers. The value -1 selects 4248 N, where N is the number of CPUs. A value 4249 "n" less than -1 selects N-n+1, where N is again 4250 the number of CPUs. For example, -2 selects N 4251 (the number of CPUs), -3 selects N+1, and so on. 4252 A value of "n" less than or equal to -N selects 4253 a single reader. 4254 4255 rcuscale.nwriters= [KNL] 4256 Set number of RCU writers. The values operate 4257 the same as for rcuscale.nreaders. 4258 N, where N is the number of CPUs 4259 4260 rcuscale.perf_type= [KNL] 4261 Specify the RCU implementation to test. 4262 4263 rcuscale.shutdown= [KNL] 4264 Shut the system down after performance tests 4265 complete. This is useful for hands-off automated 4266 testing. 4267 4268 rcuscale.verbose= [KNL] 4269 Enable additional printk() statements. 4270 4271 rcuscale.writer_holdoff= [KNL] 4272 Write-side holdoff between grace periods, 4273 in microseconds. The default of zero says 4274 no holdoff. 4275 4276 rcutorture.fqs_duration= [KNL] 4277 Set duration of force_quiescent_state bursts 4278 in microseconds. 4279 4280 rcutorture.fqs_holdoff= [KNL] 4281 Set holdoff time within force_quiescent_state bursts 4282 in microseconds. 4283 4284 rcutorture.fqs_stutter= [KNL] 4285 Set wait time between force_quiescent_state bursts 4286 in seconds. 4287 4288 rcutorture.fwd_progress= [KNL] 4289 Enable RCU grace-period forward-progress testing 4290 for the types of RCU supporting this notion. 4291 4292 rcutorture.fwd_progress_div= [KNL] 4293 Specify the fraction of a CPU-stall-warning 4294 period to do tight-loop forward-progress testing. 4295 4296 rcutorture.fwd_progress_holdoff= [KNL] 4297 Number of seconds to wait between successive 4298 forward-progress tests. 4299 4300 rcutorture.fwd_progress_need_resched= [KNL] 4301 Enclose cond_resched() calls within checks for 4302 need_resched() during tight-loop forward-progress 4303 testing. 4304 4305 rcutorture.gp_cond= [KNL] 4306 Use conditional/asynchronous update-side 4307 primitives, if available. 4308 4309 rcutorture.gp_exp= [KNL] 4310 Use expedited update-side primitives, if available. 4311 4312 rcutorture.gp_normal= [KNL] 4313 Use normal (non-expedited) asynchronous 4314 update-side primitives, if available. 4315 4316 rcutorture.gp_sync= [KNL] 4317 Use normal (non-expedited) synchronous 4318 update-side primitives, if available. If all 4319 of rcutorture.gp_cond=, rcutorture.gp_exp=, 4320 rcutorture.gp_normal=, and rcutorture.gp_sync= 4321 are zero, rcutorture acts as if is interpreted 4322 they are all non-zero. 4323 4324 rcutorture.irqreader= [KNL] 4325 Run RCU readers from irq handlers, or, more 4326 accurately, from a timer handler. Not all RCU 4327 flavors take kindly to this sort of thing. 4328 4329 rcutorture.leakpointer= [KNL] 4330 Leak an RCU-protected pointer out of the reader. 4331 This can of course result in splats, and is 4332 intended to test the ability of things like 4333 CONFIG_RCU_STRICT_GRACE_PERIOD=y to detect 4334 such leaks. 4335 4336 rcutorture.n_barrier_cbs= [KNL] 4337 Set callbacks/threads for rcu_barrier() testing. 4338 4339 rcutorture.nfakewriters= [KNL] 4340 Set number of concurrent RCU writers. These just 4341 stress RCU, they don't participate in the actual 4342 test, hence the "fake". 4343 4344 rcutorture.nreaders= [KNL] 4345 Set number of RCU readers. The value -1 selects 4346 N-1, where N is the number of CPUs. A value 4347 "n" less than -1 selects N-n-2, where N is again 4348 the number of CPUs. For example, -2 selects N 4349 (the number of CPUs), -3 selects N+1, and so on. 4350 4351 rcutorture.object_debug= [KNL] 4352 Enable debug-object double-call_rcu() testing. 4353 4354 rcutorture.onoff_holdoff= [KNL] 4355 Set time (s) after boot for CPU-hotplug testing. 4356 4357 rcutorture.onoff_interval= [KNL] 4358 Set time (jiffies) between CPU-hotplug operations, 4359 or zero to disable CPU-hotplug testing. 4360 4361 rcutorture.read_exit= [KNL] 4362 Set the number of read-then-exit kthreads used 4363 to test the interaction of RCU updaters and 4364 task-exit processing. 4365 4366 rcutorture.read_exit_burst= [KNL] 4367 The number of times in a given read-then-exit 4368 episode that a set of read-then-exit kthreads 4369 is spawned. 4370 4371 rcutorture.read_exit_delay= [KNL] 4372 The delay, in seconds, between successive 4373 read-then-exit testing episodes. 4374 4375 rcutorture.shuffle_interval= [KNL] 4376 Set task-shuffle interval (s). Shuffling tasks 4377 allows some CPUs to go into dyntick-idle mode 4378 during the rcutorture test. 4379 4380 rcutorture.shutdown_secs= [KNL] 4381 Set time (s) after boot system shutdown. This 4382 is useful for hands-off automated testing. 4383 4384 rcutorture.stall_cpu= [KNL] 4385 Duration of CPU stall (s) to test RCU CPU stall 4386 warnings, zero to disable. 4387 4388 rcutorture.stall_cpu_block= [KNL] 4389 Sleep while stalling if set. This will result 4390 in warnings from preemptible RCU in addition 4391 to any other stall-related activity. 4392 4393 rcutorture.stall_cpu_holdoff= [KNL] 4394 Time to wait (s) after boot before inducing stall. 4395 4396 rcutorture.stall_cpu_irqsoff= [KNL] 4397 Disable interrupts while stalling if set. 4398 4399 rcutorture.stall_gp_kthread= [KNL] 4400 Duration (s) of forced sleep within RCU 4401 grace-period kthread to test RCU CPU stall 4402 warnings, zero to disable. If both stall_cpu 4403 and stall_gp_kthread are specified, the 4404 kthread is starved first, then the CPU. 4405 4406 rcutorture.stat_interval= [KNL] 4407 Time (s) between statistics printk()s. 4408 4409 rcutorture.stutter= [KNL] 4410 Time (s) to stutter testing, for example, specifying 4411 five seconds causes the test to run for five seconds, 4412 wait for five seconds, and so on. This tests RCU's 4413 ability to transition abruptly to and from idle. 4414 4415 rcutorture.test_boost= [KNL] 4416 Test RCU priority boosting? 0=no, 1=maybe, 2=yes. 4417 "Maybe" means test if the RCU implementation 4418 under test support RCU priority boosting. 4419 4420 rcutorture.test_boost_duration= [KNL] 4421 Duration (s) of each individual boost test. 4422 4423 rcutorture.test_boost_interval= [KNL] 4424 Interval (s) between each boost test. 4425 4426 rcutorture.test_no_idle_hz= [KNL] 4427 Test RCU's dyntick-idle handling. See also the 4428 rcutorture.shuffle_interval parameter. 4429 4430 rcutorture.torture_type= [KNL] 4431 Specify the RCU implementation to test. 4432 4433 rcutorture.verbose= [KNL] 4434 Enable additional printk() statements. 4435 4436 rcupdate.rcu_cpu_stall_ftrace_dump= [KNL] 4437 Dump ftrace buffer after reporting RCU CPU 4438 stall warning. 4439 4440 rcupdate.rcu_cpu_stall_suppress= [KNL] 4441 Suppress RCU CPU stall warning messages. 4442 4443 rcupdate.rcu_cpu_stall_suppress_at_boot= [KNL] 4444 Suppress RCU CPU stall warning messages and 4445 rcutorture writer stall warnings that occur 4446 during early boot, that is, during the time 4447 before the init task is spawned. 4448 4449 rcupdate.rcu_cpu_stall_timeout= [KNL] 4450 Set timeout for RCU CPU stall warning messages. 4451 4452 rcupdate.rcu_expedited= [KNL] 4453 Use expedited grace-period primitives, for 4454 example, synchronize_rcu_expedited() instead 4455 of synchronize_rcu(). This reduces latency, 4456 but can increase CPU utilization, degrade 4457 real-time latency, and degrade energy efficiency. 4458 No effect on CONFIG_TINY_RCU kernels. 4459 4460 rcupdate.rcu_normal= [KNL] 4461 Use only normal grace-period primitives, 4462 for example, synchronize_rcu() instead of 4463 synchronize_rcu_expedited(). This improves 4464 real-time latency, CPU utilization, and 4465 energy efficiency, but can expose users to 4466 increased grace-period latency. This parameter 4467 overrides rcupdate.rcu_expedited. No effect on 4468 CONFIG_TINY_RCU kernels. 4469 4470 rcupdate.rcu_normal_after_boot= [KNL] 4471 Once boot has completed (that is, after 4472 rcu_end_inkernel_boot() has been invoked), use 4473 only normal grace-period primitives. No effect 4474 on CONFIG_TINY_RCU kernels. 4475 4476 rcupdate.rcu_task_ipi_delay= [KNL] 4477 Set time in jiffies during which RCU tasks will 4478 avoid sending IPIs, starting with the beginning 4479 of a given grace period. Setting a large 4480 number avoids disturbing real-time workloads, 4481 but lengthens grace periods. 4482 4483 rcupdate.rcu_task_stall_timeout= [KNL] 4484 Set timeout in jiffies for RCU task stall warning 4485 messages. Disable with a value less than or equal 4486 to zero. 4487 4488 rcupdate.rcu_self_test= [KNL] 4489 Run the RCU early boot self tests 4490 4491 rdinit= [KNL] 4492 Format: <full_path> 4493 Run specified binary instead of /init from the ramdisk, 4494 used for early userspace startup. See initrd. 4495 4496 rdrand= [X86] 4497 force - Override the decision by the kernel to hide the 4498 advertisement of RDRAND support (this affects 4499 certain AMD processors because of buggy BIOS 4500 support, specifically around the suspend/resume 4501 path). 4502 4503 rdt= [HW,X86,RDT] 4504 Turn on/off individual RDT features. List is: 4505 cmt, mbmtotal, mbmlocal, l3cat, l3cdp, l2cat, l2cdp, 4506 mba. 4507 E.g. to turn on cmt and turn off mba use: 4508 rdt=cmt,!mba 4509 4510 reboot= [KNL] 4511 Format (x86 or x86_64): 4512 [w[arm] | c[old] | h[ard] | s[oft] | g[pio]] \ 4513 [[,]s[mp]#### \ 4514 [[,]b[ios] | a[cpi] | k[bd] | t[riple] | e[fi] | p[ci]] \ 4515 [[,]f[orce] 4516 Where reboot_mode is one of warm (soft) or cold (hard) or gpio 4517 (prefix with 'panic_' to set mode for panic 4518 reboot only), 4519 reboot_type is one of bios, acpi, kbd, triple, efi, or pci, 4520 reboot_force is either force or not specified, 4521 reboot_cpu is s[mp]#### with #### being the processor 4522 to be used for rebooting. 4523 4524 refscale.holdoff= [KNL] 4525 Set test-start holdoff period. The purpose of 4526 this parameter is to delay the start of the 4527 test until boot completes in order to avoid 4528 interference. 4529 4530 refscale.loops= [KNL] 4531 Set the number of loops over the synchronization 4532 primitive under test. Increasing this number 4533 reduces noise due to loop start/end overhead, 4534 but the default has already reduced the per-pass 4535 noise to a handful of picoseconds on ca. 2020 4536 x86 laptops. 4537 4538 refscale.nreaders= [KNL] 4539 Set number of readers. The default value of -1 4540 selects N, where N is roughly 75% of the number 4541 of CPUs. A value of zero is an interesting choice. 4542 4543 refscale.nruns= [KNL] 4544 Set number of runs, each of which is dumped onto 4545 the console log. 4546 4547 refscale.readdelay= [KNL] 4548 Set the read-side critical-section duration, 4549 measured in microseconds. 4550 4551 refscale.scale_type= [KNL] 4552 Specify the read-protection implementation to test. 4553 4554 refscale.shutdown= [KNL] 4555 Shut down the system at the end of the performance 4556 test. This defaults to 1 (shut it down) when 4557 refscale is built into the kernel and to 0 (leave 4558 it running) when refscale is built as a module. 4559 4560 refscale.verbose= [KNL] 4561 Enable additional printk() statements. 4562 4563 relax_domain_level= 4564 [KNL, SMP] Set scheduler's default relax_domain_level. 4565 See Documentation/admin-guide/cgroup-v1/cpusets.rst. 4566 4567 reserve= [KNL,BUGS] Force kernel to ignore I/O ports or memory 4568 Format: <base1>,<size1>[,<base2>,<size2>,...] 4569 Reserve I/O ports or memory so the kernel won't use 4570 them. If <base> is less than 0x10000, the region 4571 is assumed to be I/O ports; otherwise it is memory. 4572 4573 reservetop= [X86-32] 4574 Format: nn[KMG] 4575 Reserves a hole at the top of the kernel virtual 4576 address space. 4577 4578 reservelow= [X86] 4579 Format: nn[K] 4580 Set the amount of memory to reserve for BIOS at 4581 the bottom of the address space. 4582 4583 reset_devices [KNL] Force drivers to reset the underlying device 4584 during initialization. 4585 4586 resume= [SWSUSP] 4587 Specify the partition device for software suspend 4588 Format: 4589 {/dev/<dev> | PARTUUID=<uuid> | <int>:<int> | <hex>} 4590 4591 resume_offset= [SWSUSP] 4592 Specify the offset from the beginning of the partition 4593 given by "resume=" at which the swap header is located, 4594 in <PAGE_SIZE> units (needed only for swap files). 4595 See Documentation/power/swsusp-and-swap-files.rst 4596 4597 resumedelay= [HIBERNATION] Delay (in seconds) to pause before attempting to 4598 read the resume files 4599 4600 resumewait [HIBERNATION] Wait (indefinitely) for resume device to show up. 4601 Useful for devices that are detected asynchronously 4602 (e.g. USB and MMC devices). 4603 4604 hibernate= [HIBERNATION] 4605 noresume Don't check if there's a hibernation image 4606 present during boot. 4607 nocompress Don't compress/decompress hibernation images. 4608 no Disable hibernation and resume. 4609 protect_image Turn on image protection during restoration 4610 (that will set all pages holding image data 4611 during restoration read-only). 4612 4613 retain_initrd [RAM] Keep initrd memory after extraction 4614 4615 rfkill.default_state= 4616 0 "airplane mode". All wifi, bluetooth, wimax, gps, fm, 4617 etc. communication is blocked by default. 4618 1 Unblocked. 4619 4620 rfkill.master_switch_mode= 4621 0 The "airplane mode" button does nothing. 4622 1 The "airplane mode" button toggles between everything 4623 blocked and the previous configuration. 4624 2 The "airplane mode" button toggles between everything 4625 blocked and everything unblocked. 4626 4627 rhash_entries= [KNL,NET] 4628 Set number of hash buckets for route cache 4629 4630 ring3mwait=disable 4631 [KNL] Disable ring 3 MONITOR/MWAIT feature on supported 4632 CPUs. 4633 4634 ro [KNL] Mount root device read-only on boot 4635 4636 rodata= [KNL] 4637 on Mark read-only kernel memory as read-only (default). 4638 off Leave read-only kernel memory writable for debugging. 4639 4640 rockchip.usb_uart 4641 Enable the uart passthrough on the designated usb port 4642 on Rockchip SoCs. When active, the signals of the 4643 debug-uart get routed to the D+ and D- pins of the usb 4644 port and the regular usb controller gets disabled. 4645 4646 root= [KNL] Root filesystem 4647 See name_to_dev_t comment in init/do_mounts.c. 4648 4649 rootdelay= [KNL] Delay (in seconds) to pause before attempting to 4650 mount the root filesystem 4651 4652 rootflags= [KNL] Set root filesystem mount option string 4653 4654 rootfstype= [KNL] Set root filesystem type 4655 4656 rootwait [KNL] Wait (indefinitely) for root device to show up. 4657 Useful for devices that are detected asynchronously 4658 (e.g. USB and MMC devices). 4659 4660 rproc_mem=nn[KMG][@address] 4661 [KNL,ARM,CMA] Remoteproc physical memory block. 4662 Memory area to be used by remote processor image, 4663 managed by CMA. 4664 4665 rw [KNL] Mount root device read-write on boot 4666 4667 S [KNL] Run init in single mode 4668 4669 s390_iommu= [HW,S390] 4670 Set s390 IOTLB flushing mode 4671 strict 4672 With strict flushing every unmap operation will result in 4673 an IOTLB flush. Default is lazy flushing before reuse, 4674 which is faster. 4675 4676 sa1100ir [NET] 4677 See drivers/net/irda/sa1100_ir.c. 4678 4679 sbni= [NET] Granch SBNI12 leased line adapter 4680 4681 sched_debug [KNL] Enables verbose scheduler debug messages. 4682 4683 schedstats= [KNL,X86] Enable or disable scheduled statistics. 4684 Allowed values are enable and disable. This feature 4685 incurs a small amount of overhead in the scheduler 4686 but is useful for debugging and performance tuning. 4687 4688 sched_thermal_decay_shift= 4689 [KNL, SMP] Set a decay shift for scheduler thermal 4690 pressure signal. Thermal pressure signal follows the 4691 default decay period of other scheduler pelt 4692 signals(usually 32 ms but configurable). Setting 4693 sched_thermal_decay_shift will left shift the decay 4694 period for the thermal pressure signal by the shift 4695 value. 4696 i.e. with the default pelt decay period of 32 ms 4697 sched_thermal_decay_shift thermal pressure decay pr 4698 1 64 ms 4699 2 128 ms 4700 and so on. 4701 Format: integer between 0 and 10 4702 Default is 0. 4703 4704 scftorture.holdoff= [KNL] 4705 Number of seconds to hold off before starting 4706 test. Defaults to zero for module insertion and 4707 to 10 seconds for built-in smp_call_function() 4708 tests. 4709 4710 scftorture.longwait= [KNL] 4711 Request ridiculously long waits randomly selected 4712 up to the chosen limit in seconds. Zero (the 4713 default) disables this feature. Please note 4714 that requesting even small non-zero numbers of 4715 seconds can result in RCU CPU stall warnings, 4716 softlockup complaints, and so on. 4717 4718 scftorture.nthreads= [KNL] 4719 Number of kthreads to spawn to invoke the 4720 smp_call_function() family of functions. 4721 The default of -1 specifies a number of kthreads 4722 equal to the number of CPUs. 4723 4724 scftorture.onoff_holdoff= [KNL] 4725 Number seconds to wait after the start of the 4726 test before initiating CPU-hotplug operations. 4727 4728 scftorture.onoff_interval= [KNL] 4729 Number seconds to wait between successive 4730 CPU-hotplug operations. Specifying zero (which 4731 is the default) disables CPU-hotplug operations. 4732 4733 scftorture.shutdown_secs= [KNL] 4734 The number of seconds following the start of the 4735 test after which to shut down the system. The 4736 default of zero avoids shutting down the system. 4737 Non-zero values are useful for automated tests. 4738 4739 scftorture.stat_interval= [KNL] 4740 The number of seconds between outputting the 4741 current test statistics to the console. A value 4742 of zero disables statistics output. 4743 4744 scftorture.stutter_cpus= [KNL] 4745 The number of jiffies to wait between each change 4746 to the set of CPUs under test. 4747 4748 scftorture.use_cpus_read_lock= [KNL] 4749 Use use_cpus_read_lock() instead of the default 4750 preempt_disable() to disable CPU hotplug 4751 while invoking one of the smp_call_function*() 4752 functions. 4753 4754 scftorture.verbose= [KNL] 4755 Enable additional printk() statements. 4756 4757 scftorture.weight_single= [KNL] 4758 The probability weighting to use for the 4759 smp_call_function_single() function with a zero 4760 "wait" parameter. A value of -1 selects the 4761 default if all other weights are -1. However, 4762 if at least one weight has some other value, a 4763 value of -1 will instead select a weight of zero. 4764 4765 scftorture.weight_single_wait= [KNL] 4766 The probability weighting to use for the 4767 smp_call_function_single() function with a 4768 non-zero "wait" parameter. See weight_single. 4769 4770 scftorture.weight_many= [KNL] 4771 The probability weighting to use for the 4772 smp_call_function_many() function with a zero 4773 "wait" parameter. See weight_single. 4774 Note well that setting a high probability for 4775 this weighting can place serious IPI load 4776 on the system. 4777 4778 scftorture.weight_many_wait= [KNL] 4779 The probability weighting to use for the 4780 smp_call_function_many() function with a 4781 non-zero "wait" parameter. See weight_single 4782 and weight_many. 4783 4784 scftorture.weight_all= [KNL] 4785 The probability weighting to use for the 4786 smp_call_function_all() function with a zero 4787 "wait" parameter. See weight_single and 4788 weight_many. 4789 4790 scftorture.weight_all_wait= [KNL] 4791 The probability weighting to use for the 4792 smp_call_function_all() function with a 4793 non-zero "wait" parameter. See weight_single 4794 and weight_many. 4795 4796 skew_tick= [KNL] Offset the periodic timer tick per cpu to mitigate 4797 xtime_lock contention on larger systems, and/or RCU lock 4798 contention on all systems with CONFIG_MAXSMP set. 4799 Format: { "0" | "1" } 4800 0 -- disable. (may be 1 via CONFIG_CMDLINE="skew_tick=1" 4801 1 -- enable. 4802 Note: increases power consumption, thus should only be 4803 enabled if running jitter sensitive (HPC/RT) workloads. 4804 4805 security= [SECURITY] Choose a legacy "major" security module to 4806 enable at boot. This has been deprecated by the 4807 "lsm=" parameter. 4808 4809 selinux= [SELINUX] Disable or enable SELinux at boot time. 4810 Format: { "0" | "1" } 4811 See security/selinux/Kconfig help text. 4812 0 -- disable. 4813 1 -- enable. 4814 Default value is 1. 4815 4816 apparmor= [APPARMOR] Disable or enable AppArmor at boot time 4817 Format: { "0" | "1" } 4818 See security/apparmor/Kconfig help text 4819 0 -- disable. 4820 1 -- enable. 4821 Default value is set via kernel config option. 4822 4823 serialnumber [BUGS=X86-32] 4824 4825 shapers= [NET] 4826 Maximal number of shapers. 4827 4828 simeth= [IA-64] 4829 simscsi= 4830 4831 slram= [HW,MTD] 4832 4833 slab_nomerge [MM] 4834 Disable merging of slabs with similar size. May be 4835 necessary if there is some reason to distinguish 4836 allocs to different slabs, especially in hardened 4837 environments where the risk of heap overflows and 4838 layout control by attackers can usually be 4839 frustrated by disabling merging. This will reduce 4840 most of the exposure of a heap attack to a single 4841 cache (risks via metadata attacks are mostly 4842 unchanged). Debug options disable merging on their 4843 own. 4844 For more information see Documentation/vm/slub.rst. 4845 4846 slab_max_order= [MM, SLAB] 4847 Determines the maximum allowed order for slabs. 4848 A high setting may cause OOMs due to memory 4849 fragmentation. Defaults to 1 for systems with 4850 more than 32MB of RAM, 0 otherwise. 4851 4852 slub_debug[=options[,slabs][;[options[,slabs]]...] [MM, SLUB] 4853 Enabling slub_debug allows one to determine the 4854 culprit if slab objects become corrupted. Enabling 4855 slub_debug can create guard zones around objects and 4856 may poison objects when not in use. Also tracks the 4857 last alloc / free. For more information see 4858 Documentation/vm/slub.rst. 4859 4860 slub_memcg_sysfs= [MM, SLUB] 4861 Determines whether to enable sysfs directories for 4862 memory cgroup sub-caches. 1 to enable, 0 to disable. 4863 The default is determined by CONFIG_SLUB_MEMCG_SYSFS_ON. 4864 Enabling this can lead to a very high number of debug 4865 directories and files being created under 4866 /sys/kernel/slub. 4867 4868 slub_max_order= [MM, SLUB] 4869 Determines the maximum allowed order for slabs. 4870 A high setting may cause OOMs due to memory 4871 fragmentation. For more information see 4872 Documentation/vm/slub.rst. 4873 4874 slub_min_objects= [MM, SLUB] 4875 The minimum number of objects per slab. SLUB will 4876 increase the slab order up to slub_max_order to 4877 generate a sufficiently large slab able to contain 4878 the number of objects indicated. The higher the number 4879 of objects the smaller the overhead of tracking slabs 4880 and the less frequently locks need to be acquired. 4881 For more information see Documentation/vm/slub.rst. 4882 4883 slub_min_order= [MM, SLUB] 4884 Determines the minimum page order for slabs. Must be 4885 lower than slub_max_order. 4886 For more information see Documentation/vm/slub.rst. 4887 4888 slub_nomerge [MM, SLUB] 4889 Same with slab_nomerge. This is supported for legacy. 4890 See slab_nomerge for more information. 4891 4892 smart2= [HW] 4893 Format: <io1>[,<io2>[,...,<io8>]] 4894 4895 smsc-ircc2.nopnp [HW] Don't use PNP to discover SMC devices 4896 smsc-ircc2.ircc_cfg= [HW] Device configuration I/O port 4897 smsc-ircc2.ircc_sir= [HW] SIR base I/O port 4898 smsc-ircc2.ircc_fir= [HW] FIR base I/O port 4899 smsc-ircc2.ircc_irq= [HW] IRQ line 4900 smsc-ircc2.ircc_dma= [HW] DMA channel 4901 smsc-ircc2.ircc_transceiver= [HW] Transceiver type: 4902 0: Toshiba Satellite 1800 (GP data pin select) 4903 1: Fast pin select (default) 4904 2: ATC IRMode 4905 4906 smt [KNL,S390] Set the maximum number of threads (logical 4907 CPUs) to use per physical CPU on systems capable of 4908 symmetric multithreading (SMT). Will be capped to the 4909 actual hardware limit. 4910 Format: <integer> 4911 Default: -1 (no limit) 4912 4913 softlockup_panic= 4914 [KNL] Should the soft-lockup detector generate panics. 4915 Format: 0 | 1 4916 4917 A value of 1 instructs the soft-lockup detector 4918 to panic the machine when a soft-lockup occurs. It is 4919 also controlled by the kernel.softlockup_panic sysctl 4920 and CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC, which is the 4921 respective build-time switch to that functionality. 4922 4923 softlockup_all_cpu_backtrace= 4924 [KNL] Should the soft-lockup detector generate 4925 backtraces on all cpus. 4926 Format: 0 | 1 4927 4928 sonypi.*= [HW] Sony Programmable I/O Control Device driver 4929 See Documentation/admin-guide/laptops/sonypi.rst 4930 4931 spectre_v2= [X86] Control mitigation of Spectre variant 2 4932 (indirect branch speculation) vulnerability. 4933 The default operation protects the kernel from 4934 user space attacks. 4935 4936 on - unconditionally enable, implies 4937 spectre_v2_user=on 4938 off - unconditionally disable, implies 4939 spectre_v2_user=off 4940 auto - kernel detects whether your CPU model is 4941 vulnerable 4942 4943 Selecting 'on' will, and 'auto' may, choose a 4944 mitigation method at run time according to the 4945 CPU, the available microcode, the setting of the 4946 CONFIG_RETPOLINE configuration option, and the 4947 compiler with which the kernel was built. 4948 4949 Selecting 'on' will also enable the mitigation 4950 against user space to user space task attacks. 4951 4952 Selecting 'off' will disable both the kernel and 4953 the user space protections. 4954 4955 Specific mitigations can also be selected manually: 4956 4957 retpoline - replace indirect branches 4958 retpoline,generic - google's original retpoline 4959 retpoline,amd - AMD-specific minimal thunk 4960 4961 Not specifying this option is equivalent to 4962 spectre_v2=auto. 4963 4964 spectre_v2_user= 4965 [X86] Control mitigation of Spectre variant 2 4966 (indirect branch speculation) vulnerability between 4967 user space tasks 4968 4969 on - Unconditionally enable mitigations. Is 4970 enforced by spectre_v2=on 4971 4972 off - Unconditionally disable mitigations. Is 4973 enforced by spectre_v2=off 4974 4975 prctl - Indirect branch speculation is enabled, 4976 but mitigation can be enabled via prctl 4977 per thread. The mitigation control state 4978 is inherited on fork. 4979 4980 prctl,ibpb 4981 - Like "prctl" above, but only STIBP is 4982 controlled per thread. IBPB is issued 4983 always when switching between different user 4984 space processes. 4985 4986 seccomp 4987 - Same as "prctl" above, but all seccomp 4988 threads will enable the mitigation unless 4989 they explicitly opt out. 4990 4991 seccomp,ibpb 4992 - Like "seccomp" above, but only STIBP is 4993 controlled per thread. IBPB is issued 4994 always when switching between different 4995 user space processes. 4996 4997 auto - Kernel selects the mitigation depending on 4998 the available CPU features and vulnerability. 4999 5000 Default mitigation: 5001 If CONFIG_SECCOMP=y then "seccomp", otherwise "prctl" 5002 5003 Not specifying this option is equivalent to 5004 spectre_v2_user=auto. 5005 5006 spec_store_bypass_disable= 5007 [HW] Control Speculative Store Bypass (SSB) Disable mitigation 5008 (Speculative Store Bypass vulnerability) 5009 5010 Certain CPUs are vulnerable to an exploit against a 5011 a common industry wide performance optimization known 5012 as "Speculative Store Bypass" in which recent stores 5013 to the same memory location may not be observed by 5014 later loads during speculative execution. The idea 5015 is that such stores are unlikely and that they can 5016 be detected prior to instruction retirement at the 5017 end of a particular speculation execution window. 5018 5019 In vulnerable processors, the speculatively forwarded 5020 store can be used in a cache side channel attack, for 5021 example to read memory to which the attacker does not 5022 directly have access (e.g. inside sandboxed code). 5023 5024 This parameter controls whether the Speculative Store 5025 Bypass optimization is used. 5026 5027 On x86 the options are: 5028 5029 on - Unconditionally disable Speculative Store Bypass 5030 off - Unconditionally enable Speculative Store Bypass 5031 auto - Kernel detects whether the CPU model contains an 5032 implementation of Speculative Store Bypass and 5033 picks the most appropriate mitigation. If the 5034 CPU is not vulnerable, "off" is selected. If the 5035 CPU is vulnerable the default mitigation is 5036 architecture and Kconfig dependent. See below. 5037 prctl - Control Speculative Store Bypass per thread 5038 via prctl. Speculative Store Bypass is enabled 5039 for a process by default. The state of the control 5040 is inherited on fork. 5041 seccomp - Same as "prctl" above, but all seccomp threads 5042 will disable SSB unless they explicitly opt out. 5043 5044 Default mitigations: 5045 X86: If CONFIG_SECCOMP=y "seccomp", otherwise "prctl" 5046 5047 On powerpc the options are: 5048 5049 on,auto - On Power8 and Power9 insert a store-forwarding 5050 barrier on kernel entry and exit. On Power7 5051 perform a software flush on kernel entry and 5052 exit. 5053 off - No action. 5054 5055 Not specifying this option is equivalent to 5056 spec_store_bypass_disable=auto. 5057 5058 spia_io_base= [HW,MTD] 5059 spia_fio_base= 5060 spia_pedr= 5061 spia_peddr= 5062 5063 split_lock_detect= 5064 [X86] Enable split lock detection 5065 5066 When enabled (and if hardware support is present), atomic 5067 instructions that access data across cache line 5068 boundaries will result in an alignment check exception. 5069 5070 off - not enabled 5071 5072 warn - the kernel will emit rate limited warnings 5073 about applications triggering the #AC 5074 exception. This mode is the default on CPUs 5075 that supports split lock detection. 5076 5077 fatal - the kernel will send SIGBUS to applications 5078 that trigger the #AC exception. 5079 5080 If an #AC exception is hit in the kernel or in 5081 firmware (i.e. not while executing in user mode) 5082 the kernel will oops in either "warn" or "fatal" 5083 mode. 5084 5085 srbds= [X86,INTEL] 5086 Control the Special Register Buffer Data Sampling 5087 (SRBDS) mitigation. 5088 5089 Certain CPUs are vulnerable to an MDS-like 5090 exploit which can leak bits from the random 5091 number generator. 5092 5093 By default, this issue is mitigated by 5094 microcode. However, the microcode fix can cause 5095 the RDRAND and RDSEED instructions to become 5096 much slower. Among other effects, this will 5097 result in reduced throughput from /dev/urandom. 5098 5099 The microcode mitigation can be disabled with 5100 the following option: 5101 5102 off: Disable mitigation and remove 5103 performance impact to RDRAND and RDSEED 5104 5105 srcutree.counter_wrap_check [KNL] 5106 Specifies how frequently to check for 5107 grace-period sequence counter wrap for the 5108 srcu_data structure's ->srcu_gp_seq_needed field. 5109 The greater the number of bits set in this kernel 5110 parameter, the less frequently counter wrap will 5111 be checked for. Note that the bottom two bits 5112 are ignored. 5113 5114 srcutree.exp_holdoff [KNL] 5115 Specifies how many nanoseconds must elapse 5116 since the end of the last SRCU grace period for 5117 a given srcu_struct until the next normal SRCU 5118 grace period will be considered for automatic 5119 expediting. Set to zero to disable automatic 5120 expediting. 5121 5122 ssbd= [ARM64,HW] 5123 Speculative Store Bypass Disable control 5124 5125 On CPUs that are vulnerable to the Speculative 5126 Store Bypass vulnerability and offer a 5127 firmware based mitigation, this parameter 5128 indicates how the mitigation should be used: 5129 5130 force-on: Unconditionally enable mitigation for 5131 for both kernel and userspace 5132 force-off: Unconditionally disable mitigation for 5133 for both kernel and userspace 5134 kernel: Always enable mitigation in the 5135 kernel, and offer a prctl interface 5136 to allow userspace to register its 5137 interest in being mitigated too. 5138 5139 stack_guard_gap= [MM] 5140 override the default stack gap protection. The value 5141 is in page units and it defines how many pages prior 5142 to (for stacks growing down) resp. after (for stacks 5143 growing up) the main stack are reserved for no other 5144 mapping. Default value is 256 pages. 5145 5146 stacktrace [FTRACE] 5147 Enabled the stack tracer on boot up. 5148 5149 stacktrace_filter=[function-list] 5150 [FTRACE] Limit the functions that the stack tracer 5151 will trace at boot up. function-list is a comma-separated 5152 list of functions. This list can be changed at run 5153 time by the stack_trace_filter file in the debugfs 5154 tracing directory. Note, this enables stack tracing 5155 and the stacktrace above is not needed. 5156 5157 sti= [PARISC,HW] 5158 Format: <num> 5159 Set the STI (builtin display/keyboard on the HP-PARISC 5160 machines) console (graphic card) which should be used 5161 as the initial boot-console. 5162 See also comment in drivers/video/console/sticore.c. 5163 5164 sti_font= [HW] 5165 See comment in drivers/video/console/sticore.c. 5166 5167 stifb= [HW] 5168 Format: bpp:<bpp1>[:<bpp2>[:<bpp3>...]] 5169 5170 sunrpc.min_resvport= 5171 sunrpc.max_resvport= 5172 [NFS,SUNRPC] 5173 SunRPC servers often require that client requests 5174 originate from a privileged port (i.e. a port in the 5175 range 0 < portnr < 1024). 5176 An administrator who wishes to reserve some of these 5177 ports for other uses may adjust the range that the 5178 kernel's sunrpc client considers to be privileged 5179 using these two parameters to set the minimum and 5180 maximum port values. 5181 5182 sunrpc.svc_rpc_per_connection_limit= 5183 [NFS,SUNRPC] 5184 Limit the number of requests that the server will 5185 process in parallel from a single connection. 5186 The default value is 0 (no limit). 5187 5188 sunrpc.pool_mode= 5189 [NFS] 5190 Control how the NFS server code allocates CPUs to 5191 service thread pools. Depending on how many NICs 5192 you have and where their interrupts are bound, this 5193 option will affect which CPUs will do NFS serving. 5194 Note: this parameter cannot be changed while the 5195 NFS server is running. 5196 5197 auto the server chooses an appropriate mode 5198 automatically using heuristics 5199 global a single global pool contains all CPUs 5200 percpu one pool for each CPU 5201 pernode one pool for each NUMA node (equivalent 5202 to global on non-NUMA machines) 5203 5204 sunrpc.tcp_slot_table_entries= 5205 sunrpc.udp_slot_table_entries= 5206 [NFS,SUNRPC] 5207 Sets the upper limit on the number of simultaneous 5208 RPC calls that can be sent from the client to a 5209 server. Increasing these values may allow you to 5210 improve throughput, but will also increase the 5211 amount of memory reserved for use by the client. 5212 5213 suspend.pm_test_delay= 5214 [SUSPEND] 5215 Sets the number of seconds to remain in a suspend test 5216 mode before resuming the system (see 5217 /sys/power/pm_test). Only available when CONFIG_PM_DEBUG 5218 is set. Default value is 5. 5219 5220 svm= [PPC] 5221 Format: { on | off | y | n | 1 | 0 } 5222 This parameter controls use of the Protected 5223 Execution Facility on pSeries. 5224 5225 swapaccount=[0|1] 5226 [KNL] Enable accounting of swap in memory resource 5227 controller if no parameter or 1 is given or disable 5228 it if 0 is given (See Documentation/admin-guide/cgroup-v1/memory.rst) 5229 5230 swiotlb= [ARM,IA-64,PPC,MIPS,X86] 5231 Format: { <int> | force | noforce } 5232 <int> -- Number of I/O TLB slabs 5233 force -- force using of bounce buffers even if they 5234 wouldn't be automatically used by the kernel 5235 noforce -- Never use bounce buffers (for debugging) 5236 5237 switches= [HW,M68k] 5238 5239 sysctl.*= [KNL] 5240 Set a sysctl parameter, right before loading the init 5241 process, as if the value was written to the respective 5242 /proc/sys/... file. Both '.' and '/' are recognized as 5243 separators. Unrecognized parameters and invalid values 5244 are reported in the kernel log. Sysctls registered 5245 later by a loaded module cannot be set this way. 5246 Example: sysctl.vm.swappiness=40 5247 5248 sysfs.deprecated=0|1 [KNL] 5249 Enable/disable old style sysfs layout for old udev 5250 on older distributions. When this option is enabled 5251 very new udev will not work anymore. When this option 5252 is disabled (or CONFIG_SYSFS_DEPRECATED not compiled) 5253 in older udev will not work anymore. 5254 Default depends on CONFIG_SYSFS_DEPRECATED_V2 set in 5255 the kernel configuration. 5256 5257 sysrq_always_enabled 5258 [KNL] 5259 Ignore sysrq setting - this boot parameter will 5260 neutralize any effect of /proc/sys/kernel/sysrq. 5261 Useful for debugging. 5262 5263 tcpmhash_entries= [KNL,NET] 5264 Set the number of tcp_metrics_hash slots. 5265 Default value is 8192 or 16384 depending on total 5266 ram pages. This is used to specify the TCP metrics 5267 cache size. See Documentation/networking/ip-sysctl.rst 5268 "tcp_no_metrics_save" section for more details. 5269 5270 tdfx= [HW,DRM] 5271 5272 test_suspend= [SUSPEND][,N] 5273 Specify "mem" (for Suspend-to-RAM) or "standby" (for 5274 standby suspend) or "freeze" (for suspend type freeze) 5275 as the system sleep state during system startup with 5276 the optional capability to repeat N number of times. 5277 The system is woken from this state using a 5278 wakeup-capable RTC alarm. 5279 5280 thash_entries= [KNL,NET] 5281 Set number of hash buckets for TCP connection 5282 5283 thermal.act= [HW,ACPI] 5284 -1: disable all active trip points in all thermal zones 5285 <degrees C>: override all lowest active trip points 5286 5287 thermal.crt= [HW,ACPI] 5288 -1: disable all critical trip points in all thermal zones 5289 <degrees C>: override all critical trip points 5290 5291 thermal.nocrt= [HW,ACPI] 5292 Set to disable actions on ACPI thermal zone 5293 critical and hot trip points. 5294 5295 thermal.off= [HW,ACPI] 5296 1: disable ACPI thermal control 5297 5298 thermal.psv= [HW,ACPI] 5299 -1: disable all passive trip points 5300 <degrees C>: override all passive trip points to this 5301 value 5302 5303 thermal.tzp= [HW,ACPI] 5304 Specify global default ACPI thermal zone polling rate 5305 <deci-seconds>: poll all this frequency 5306 0: no polling (default) 5307 5308 threadirqs [KNL] 5309 Force threading of all interrupt handlers except those 5310 marked explicitly IRQF_NO_THREAD. 5311 5312 topology= [S390] 5313 Format: {off | on} 5314 Specify if the kernel should make use of the cpu 5315 topology information if the hardware supports this. 5316 The scheduler will make use of this information and 5317 e.g. base its process migration decisions on it. 5318 Default is on. 5319 5320 topology_updates= [KNL, PPC, NUMA] 5321 Format: {off} 5322 Specify if the kernel should ignore (off) 5323 topology updates sent by the hypervisor to this 5324 LPAR. 5325 5326 torture.disable_onoff_at_boot= [KNL] 5327 Prevent the CPU-hotplug component of torturing 5328 until after init has spawned. 5329 5330 torture.ftrace_dump_at_shutdown= [KNL] 5331 Dump the ftrace buffer at torture-test shutdown, 5332 even if there were no errors. This can be a 5333 very costly operation when many torture tests 5334 are running concurrently, especially on systems 5335 with rotating-rust storage. 5336 5337 tp720= [HW,PS2] 5338 5339 tpm_suspend_pcr=[HW,TPM] 5340 Format: integer pcr id 5341 Specify that at suspend time, the tpm driver 5342 should extend the specified pcr with zeros, 5343 as a workaround for some chips which fail to 5344 flush the last written pcr on TPM_SaveState. 5345 This will guarantee that all the other pcrs 5346 are saved. 5347 5348 trace_buf_size=nn[KMG] 5349 [FTRACE] will set tracing buffer size on each cpu. 5350 5351 trace_event=[event-list] 5352 [FTRACE] Set and start specified trace events in order 5353 to facilitate early boot debugging. The event-list is a 5354 comma-separated list of trace events to enable. See 5355 also Documentation/trace/events.rst 5356 5357 trace_options=[option-list] 5358 [FTRACE] Enable or disable tracer options at boot. 5359 The option-list is a comma delimited list of options 5360 that can be enabled or disabled just as if you were 5361 to echo the option name into 5362 5363 /sys/kernel/debug/tracing/trace_options 5364 5365 For example, to enable stacktrace option (to dump the 5366 stack trace of each event), add to the command line: 5367 5368 trace_options=stacktrace 5369 5370 See also Documentation/trace/ftrace.rst "trace options" 5371 section. 5372 5373 tp_printk[FTRACE] 5374 Have the tracepoints sent to printk as well as the 5375 tracing ring buffer. This is useful for early boot up 5376 where the system hangs or reboots and does not give the 5377 option for reading the tracing buffer or performing a 5378 ftrace_dump_on_oops. 5379 5380 To turn off having tracepoints sent to printk, 5381 echo 0 > /proc/sys/kernel/tracepoint_printk 5382 Note, echoing 1 into this file without the 5383 tracepoint_printk kernel cmdline option has no effect. 5384 5385 ** CAUTION ** 5386 5387 Having tracepoints sent to printk() and activating high 5388 frequency tracepoints such as irq or sched, can cause 5389 the system to live lock. 5390 5391 traceoff_on_warning 5392 [FTRACE] enable this option to disable tracing when a 5393 warning is hit. This turns off "tracing_on". Tracing can 5394 be enabled again by echoing '1' into the "tracing_on" 5395 file located in /sys/kernel/debug/tracing/ 5396 5397 This option is useful, as it disables the trace before 5398 the WARNING dump is called, which prevents the trace to 5399 be filled with content caused by the warning output. 5400 5401 This option can also be set at run time via the sysctl 5402 option: kernel/traceoff_on_warning 5403 5404 transparent_hugepage= 5405 [KNL] 5406 Format: [always|madvise|never] 5407 Can be used to control the default behavior of the system 5408 with respect to transparent hugepages. 5409 See Documentation/admin-guide/mm/transhuge.rst 5410 for more details. 5411 5412 tsc= Disable clocksource stability checks for TSC. 5413 Format: <string> 5414 [x86] reliable: mark tsc clocksource as reliable, this 5415 disables clocksource verification at runtime, as well 5416 as the stability checks done at bootup. Used to enable 5417 high-resolution timer mode on older hardware, and in 5418 virtualized environment. 5419 [x86] noirqtime: Do not use TSC to do irq accounting. 5420 Used to run time disable IRQ_TIME_ACCOUNTING on any 5421 platforms where RDTSC is slow and this accounting 5422 can add overhead. 5423 [x86] unstable: mark the TSC clocksource as unstable, this 5424 marks the TSC unconditionally unstable at bootup and 5425 avoids any further wobbles once the TSC watchdog notices. 5426 [x86] nowatchdog: disable clocksource watchdog. Used 5427 in situations with strict latency requirements (where 5428 interruptions from clocksource watchdog are not 5429 acceptable). 5430 5431 tsc_early_khz= [X86] Skip early TSC calibration and use the given 5432 value instead. Useful when the early TSC frequency discovery 5433 procedure is not reliable, such as on overclocked systems 5434 with CPUID.16h support and partial CPUID.15h support. 5435 Format: <unsigned int> 5436 5437 tsx= [X86] Control Transactional Synchronization 5438 Extensions (TSX) feature in Intel processors that 5439 support TSX control. 5440 5441 This parameter controls the TSX feature. The options are: 5442 5443 on - Enable TSX on the system. Although there are 5444 mitigations for all known security vulnerabilities, 5445 TSX has been known to be an accelerator for 5446 several previous speculation-related CVEs, and 5447 so there may be unknown security risks associated 5448 with leaving it enabled. 5449 5450 off - Disable TSX on the system. (Note that this 5451 option takes effect only on newer CPUs which are 5452 not vulnerable to MDS, i.e., have 5453 MSR_IA32_ARCH_CAPABILITIES.MDS_NO=1 and which get 5454 the new IA32_TSX_CTRL MSR through a microcode 5455 update. This new MSR allows for the reliable 5456 deactivation of the TSX functionality.) 5457 5458 auto - Disable TSX if X86_BUG_TAA is present, 5459 otherwise enable TSX on the system. 5460 5461 Not specifying this option is equivalent to tsx=off. 5462 5463 See Documentation/admin-guide/hw-vuln/tsx_async_abort.rst 5464 for more details. 5465 5466 tsx_async_abort= [X86,INTEL] Control mitigation for the TSX Async 5467 Abort (TAA) vulnerability. 5468 5469 Similar to Micro-architectural Data Sampling (MDS) 5470 certain CPUs that support Transactional 5471 Synchronization Extensions (TSX) are vulnerable to an 5472 exploit against CPU internal buffers which can forward 5473 information to a disclosure gadget under certain 5474 conditions. 5475 5476 In vulnerable processors, the speculatively forwarded 5477 data can be used in a cache side channel attack, to 5478 access data to which the attacker does not have direct 5479 access. 5480 5481 This parameter controls the TAA mitigation. The 5482 options are: 5483 5484 full - Enable TAA mitigation on vulnerable CPUs 5485 if TSX is enabled. 5486 5487 full,nosmt - Enable TAA mitigation and disable SMT on 5488 vulnerable CPUs. If TSX is disabled, SMT 5489 is not disabled because CPU is not 5490 vulnerable to cross-thread TAA attacks. 5491 off - Unconditionally disable TAA mitigation 5492 5493 On MDS-affected machines, tsx_async_abort=off can be 5494 prevented by an active MDS mitigation as both vulnerabilities 5495 are mitigated with the same mechanism so in order to disable 5496 this mitigation, you need to specify mds=off too. 5497 5498 Not specifying this option is equivalent to 5499 tsx_async_abort=full. On CPUs which are MDS affected 5500 and deploy MDS mitigation, TAA mitigation is not 5501 required and doesn't provide any additional 5502 mitigation. 5503 5504 For details see: 5505 Documentation/admin-guide/hw-vuln/tsx_async_abort.rst 5506 5507 turbografx.map[2|3]= [HW,JOY] 5508 TurboGraFX parallel port interface 5509 Format: 5510 <port#>,<js1>,<js2>,<js3>,<js4>,<js5>,<js6>,<js7> 5511 See also Documentation/input/devices/joystick-parport.rst 5512 5513 udbg-immortal [PPC] When debugging early kernel crashes that 5514 happen after console_init() and before a proper 5515 console driver takes over, this boot options might 5516 help "seeing" what's going on. 5517 5518 uhash_entries= [KNL,NET] 5519 Set number of hash buckets for UDP/UDP-Lite connections 5520 5521 uhci-hcd.ignore_oc= 5522 [USB] Ignore overcurrent events (default N). 5523 Some badly-designed motherboards generate lots of 5524 bogus events, for ports that aren't wired to 5525 anything. Set this parameter to avoid log spamming. 5526 Note that genuine overcurrent events won't be 5527 reported either. 5528 5529 unknown_nmi_panic 5530 [X86] Cause panic on unknown NMI. 5531 5532 usbcore.authorized_default= 5533 [USB] Default USB device authorization: 5534 (default -1 = authorized except for wireless USB, 5535 0 = not authorized, 1 = authorized, 2 = authorized 5536 if device connected to internal port) 5537 5538 usbcore.autosuspend= 5539 [USB] The autosuspend time delay (in seconds) used 5540 for newly-detected USB devices (default 2). This 5541 is the time required before an idle device will be 5542 autosuspended. Devices for which the delay is set 5543 to a negative value won't be autosuspended at all. 5544 5545 usbcore.usbfs_snoop= 5546 [USB] Set to log all usbfs traffic (default 0 = off). 5547 5548 usbcore.usbfs_snoop_max= 5549 [USB] Maximum number of bytes to snoop in each URB 5550 (default = 65536). 5551 5552 usbcore.blinkenlights= 5553 [USB] Set to cycle leds on hubs (default 0 = off). 5554 5555 usbcore.old_scheme_first= 5556 [USB] Start with the old device initialization 5557 scheme (default 0 = off). 5558 5559 usbcore.usbfs_memory_mb= 5560 [USB] Memory limit (in MB) for buffers allocated by 5561 usbfs (default = 16, 0 = max = 2047). 5562 5563 usbcore.use_both_schemes= 5564 [USB] Try the other device initialization scheme 5565 if the first one fails (default 1 = enabled). 5566 5567 usbcore.initial_descriptor_timeout= 5568 [USB] Specifies timeout for the initial 64-byte 5569 USB_REQ_GET_DESCRIPTOR request in milliseconds 5570 (default 5000 = 5.0 seconds). 5571 5572 usbcore.nousb [USB] Disable the USB subsystem 5573 5574 usbcore.quirks= 5575 [USB] A list of quirk entries to augment the built-in 5576 usb core quirk list. List entries are separated by 5577 commas. Each entry has the form 5578 VendorID:ProductID:Flags. The IDs are 4-digit hex 5579 numbers and Flags is a set of letters. Each letter 5580 will change the built-in quirk; setting it if it is 5581 clear and clearing it if it is set. The letters have 5582 the following meanings: 5583 a = USB_QUIRK_STRING_FETCH_255 (string 5584 descriptors must not be fetched using 5585 a 255-byte read); 5586 b = USB_QUIRK_RESET_RESUME (device can't resume 5587 correctly so reset it instead); 5588 c = USB_QUIRK_NO_SET_INTF (device can't handle 5589 Set-Interface requests); 5590 d = USB_QUIRK_CONFIG_INTF_STRINGS (device can't 5591 handle its Configuration or Interface 5592 strings); 5593 e = USB_QUIRK_RESET (device can't be reset 5594 (e.g morph devices), don't use reset); 5595 f = USB_QUIRK_HONOR_BNUMINTERFACES (device has 5596 more interface descriptions than the 5597 bNumInterfaces count, and can't handle 5598 talking to these interfaces); 5599 g = USB_QUIRK_DELAY_INIT (device needs a pause 5600 during initialization, after we read 5601 the device descriptor); 5602 h = USB_QUIRK_LINEAR_UFRAME_INTR_BINTERVAL (For 5603 high speed and super speed interrupt 5604 endpoints, the USB 2.0 and USB 3.0 spec 5605 require the interval in microframes (1 5606 microframe = 125 microseconds) to be 5607 calculated as interval = 2 ^ 5608 (bInterval-1). 5609 Devices with this quirk report their 5610 bInterval as the result of this 5611 calculation instead of the exponent 5612 variable used in the calculation); 5613 i = USB_QUIRK_DEVICE_QUALIFIER (device can't 5614 handle device_qualifier descriptor 5615 requests); 5616 j = USB_QUIRK_IGNORE_REMOTE_WAKEUP (device 5617 generates spurious wakeup, ignore 5618 remote wakeup capability); 5619 k = USB_QUIRK_NO_LPM (device can't handle Link 5620 Power Management); 5621 l = USB_QUIRK_LINEAR_FRAME_INTR_BINTERVAL 5622 (Device reports its bInterval as linear 5623 frames instead of the USB 2.0 5624 calculation); 5625 m = USB_QUIRK_DISCONNECT_SUSPEND (Device needs 5626 to be disconnected before suspend to 5627 prevent spurious wakeup); 5628 n = USB_QUIRK_DELAY_CTRL_MSG (Device needs a 5629 pause after every control message); 5630 o = USB_QUIRK_HUB_SLOW_RESET (Hub needs extra 5631 delay after resetting its port); 5632 Example: quirks=0781:5580:bk,0a5c:5834:gij 5633 5634 usbhid.mousepoll= 5635 [USBHID] The interval which mice are to be polled at. 5636 5637 usbhid.jspoll= 5638 [USBHID] The interval which joysticks are to be polled at. 5639 5640 usbhid.kbpoll= 5641 [USBHID] The interval which keyboards are to be polled at. 5642 5643 usb-storage.delay_use= 5644 [UMS] The delay in seconds before a new device is 5645 scanned for Logical Units (default 1). 5646 5647 usb-storage.quirks= 5648 [UMS] A list of quirks entries to supplement or 5649 override the built-in unusual_devs list. List 5650 entries are separated by commas. Each entry has 5651 the form VID:PID:Flags where VID and PID are Vendor 5652 and Product ID values (4-digit hex numbers) and 5653 Flags is a set of characters, each corresponding 5654 to a common usb-storage quirk flag as follows: 5655 a = SANE_SENSE (collect more than 18 bytes 5656 of sense data, not on uas); 5657 b = BAD_SENSE (don't collect more than 18 5658 bytes of sense data, not on uas); 5659 c = FIX_CAPACITY (decrease the reported 5660 device capacity by one sector); 5661 d = NO_READ_DISC_INFO (don't use 5662 READ_DISC_INFO command, not on uas); 5663 e = NO_READ_CAPACITY_16 (don't use 5664 READ_CAPACITY_16 command); 5665 f = NO_REPORT_OPCODES (don't use report opcodes 5666 command, uas only); 5667 g = MAX_SECTORS_240 (don't transfer more than 5668 240 sectors at a time, uas only); 5669 h = CAPACITY_HEURISTICS (decrease the 5670 reported device capacity by one 5671 sector if the number is odd); 5672 i = IGNORE_DEVICE (don't bind to this 5673 device); 5674 j = NO_REPORT_LUNS (don't use report luns 5675 command, uas only); 5676 k = NO_SAME (do not use WRITE_SAME, uas only) 5677 l = NOT_LOCKABLE (don't try to lock and 5678 unlock ejectable media, not on uas); 5679 m = MAX_SECTORS_64 (don't transfer more 5680 than 64 sectors = 32 KB at a time, 5681 not on uas); 5682 n = INITIAL_READ10 (force a retry of the 5683 initial READ(10) command, not on uas); 5684 o = CAPACITY_OK (accept the capacity 5685 reported by the device, not on uas); 5686 p = WRITE_CACHE (the device cache is ON 5687 by default, not on uas); 5688 r = IGNORE_RESIDUE (the device reports 5689 bogus residue values, not on uas); 5690 s = SINGLE_LUN (the device has only one 5691 Logical Unit); 5692 t = NO_ATA_1X (don't allow ATA(12) and ATA(16) 5693 commands, uas only); 5694 u = IGNORE_UAS (don't bind to the uas driver); 5695 w = NO_WP_DETECT (don't test whether the 5696 medium is write-protected). 5697 y = ALWAYS_SYNC (issue a SYNCHRONIZE_CACHE 5698 even if the device claims no cache, 5699 not on uas) 5700 Example: quirks=0419:aaf5:rl,0421:0433:rc 5701 5702 user_debug= [KNL,ARM] 5703 Format: <int> 5704 See arch/arm/Kconfig.debug help text. 5705 1 - undefined instruction events 5706 2 - system calls 5707 4 - invalid data aborts 5708 8 - SIGSEGV faults 5709 16 - SIGBUS faults 5710 Example: user_debug=31 5711 5712 userpte= 5713 [X86] Flags controlling user PTE allocations. 5714 5715 nohigh = do not allocate PTE pages in 5716 HIGHMEM regardless of setting 5717 of CONFIG_HIGHPTE. 5718 5719 vdso= [X86,SH] 5720 On X86_32, this is an alias for vdso32=. Otherwise: 5721 5722 vdso=1: enable VDSO (the default) 5723 vdso=0: disable VDSO mapping 5724 5725 vdso32= [X86] Control the 32-bit vDSO 5726 vdso32=1: enable 32-bit VDSO 5727 vdso32=0 or vdso32=2: disable 32-bit VDSO 5728 5729 See the help text for CONFIG_COMPAT_VDSO for more 5730 details. If CONFIG_COMPAT_VDSO is set, the default is 5731 vdso32=0; otherwise, the default is vdso32=1. 5732 5733 For compatibility with older kernels, vdso32=2 is an 5734 alias for vdso32=0. 5735 5736 Try vdso32=0 if you encounter an error that says: 5737 dl_main: Assertion `(void *) ph->p_vaddr == _rtld_local._dl_sysinfo_dso' failed! 5738 5739 vector= [IA-64,SMP] 5740 vector=percpu: enable percpu vector domain 5741 5742 video= [FB] Frame buffer configuration 5743 See Documentation/fb/modedb.rst. 5744 5745 video.brightness_switch_enabled= [0,1] 5746 If set to 1, on receiving an ACPI notify event 5747 generated by hotkey, video driver will adjust brightness 5748 level and then send out the event to user space through 5749 the allocated input device; If set to 0, video driver 5750 will only send out the event without touching backlight 5751 brightness level. 5752 default: 1 5753 5754 virtio_mmio.device= 5755 [VMMIO] Memory mapped virtio (platform) device. 5756 5757 <size>@<baseaddr>:<irq>[:<id>] 5758 where: 5759 <size> := size (can use standard suffixes 5760 like K, M and G) 5761 <baseaddr> := physical base address 5762 <irq> := interrupt number (as passed to 5763 request_irq()) 5764 <id> := (optional) platform device id 5765 example: 5766 virtio_mmio.device=1K@0x100b0000:48:7 5767 5768 Can be used multiple times for multiple devices. 5769 5770 vga= [BOOT,X86-32] Select a particular video mode 5771 See Documentation/x86/boot.rst and 5772 Documentation/admin-guide/svga.rst. 5773 Use vga=ask for menu. 5774 This is actually a boot loader parameter; the value is 5775 passed to the kernel using a special protocol. 5776 5777 vm_debug[=options] [KNL] Available with CONFIG_DEBUG_VM=y. 5778 May slow down system boot speed, especially when 5779 enabled on systems with a large amount of memory. 5780 All options are enabled by default, and this 5781 interface is meant to allow for selectively 5782 enabling or disabling specific virtual memory 5783 debugging features. 5784 5785 Available options are: 5786 P Enable page structure init time poisoning 5787 - Disable all of the above options 5788 5789 vmalloc=nn[KMG] [KNL,BOOT] Forces the vmalloc area to have an exact 5790 size of <nn>. This can be used to increase the 5791 minimum size (128MB on x86). It can also be used to 5792 decrease the size and leave more room for directly 5793 mapped kernel RAM. 5794 5795 vmcp_cma=nn[MG] [KNL,S390] 5796 Sets the memory size reserved for contiguous memory 5797 allocations for the vmcp device driver. 5798 5799 vmhalt= [KNL,S390] Perform z/VM CP command after system halt. 5800 Format: <command> 5801 5802 vmpanic= [KNL,S390] Perform z/VM CP command after kernel panic. 5803 Format: <command> 5804 5805 vmpoff= [KNL,S390] Perform z/VM CP command after power off. 5806 Format: <command> 5807 5808 vsyscall= [X86-64] 5809 Controls the behavior of vsyscalls (i.e. calls to 5810 fixed addresses of 0xffffffffff600x00 from legacy 5811 code). Most statically-linked binaries and older 5812 versions of glibc use these calls. Because these 5813 functions are at fixed addresses, they make nice 5814 targets for exploits that can control RIP. 5815 5816 emulate [default] Vsyscalls turn into traps and are 5817 emulated reasonably safely. The vsyscall 5818 page is readable. 5819 5820 xonly Vsyscalls turn into traps and are 5821 emulated reasonably safely. The vsyscall 5822 page is not readable. 5823 5824 none Vsyscalls don't work at all. This makes 5825 them quite hard to use for exploits but 5826 might break your system. 5827 5828 vt.color= [VT] Default text color. 5829 Format: 0xYX, X = foreground, Y = background. 5830 Default: 0x07 = light gray on black. 5831 5832 vt.cur_default= [VT] Default cursor shape. 5833 Format: 0xCCBBAA, where AA, BB, and CC are the same as 5834 the parameters of the <Esc>[?A;B;Cc escape sequence; 5835 see VGA-softcursor.txt. Default: 2 = underline. 5836 5837 vt.default_blu= [VT] 5838 Format: <blue0>,<blue1>,<blue2>,...,<blue15> 5839 Change the default blue palette of the console. 5840 This is a 16-member array composed of values 5841 ranging from 0-255. 5842 5843 vt.default_grn= [VT] 5844 Format: <green0>,<green1>,<green2>,...,<green15> 5845 Change the default green palette of the console. 5846 This is a 16-member array composed of values 5847 ranging from 0-255. 5848 5849 vt.default_red= [VT] 5850 Format: <red0>,<red1>,<red2>,...,<red15> 5851 Change the default red palette of the console. 5852 This is a 16-member array composed of values 5853 ranging from 0-255. 5854 5855 vt.default_utf8= 5856 [VT] 5857 Format=<0|1> 5858 Set system-wide default UTF-8 mode for all tty's. 5859 Default is 1, i.e. UTF-8 mode is enabled for all 5860 newly opened terminals. 5861 5862 vt.global_cursor_default= 5863 [VT] 5864 Format=<-1|0|1> 5865 Set system-wide default for whether a cursor 5866 is shown on new VTs. Default is -1, 5867 i.e. cursors will be created by default unless 5868 overridden by individual drivers. 0 will hide 5869 cursors, 1 will display them. 5870 5871 vt.italic= [VT] Default color for italic text; 0-15. 5872 Default: 2 = green. 5873 5874 vt.underline= [VT] Default color for underlined text; 0-15. 5875 Default: 3 = cyan. 5876 5877 watchdog timers [HW,WDT] For information on watchdog timers, 5878 see Documentation/watchdog/watchdog-parameters.rst 5879 or other driver-specific files in the 5880 Documentation/watchdog/ directory. 5881 5882 watchdog_thresh= 5883 [KNL] 5884 Set the hard lockup detector stall duration 5885 threshold in seconds. The soft lockup detector 5886 threshold is set to twice the value. A value of 0 5887 disables both lockup detectors. Default is 10 5888 seconds. 5889 5890 workqueue.watchdog_thresh= 5891 If CONFIG_WQ_WATCHDOG is configured, workqueue can 5892 warn stall conditions and dump internal state to 5893 help debugging. 0 disables workqueue stall 5894 detection; otherwise, it's the stall threshold 5895 duration in seconds. The default value is 30 and 5896 it can be updated at runtime by writing to the 5897 corresponding sysfs file. 5898 5899 workqueue.disable_numa 5900 By default, all work items queued to unbound 5901 workqueues are affine to the NUMA nodes they're 5902 issued on, which results in better behavior in 5903 general. If NUMA affinity needs to be disabled for 5904 whatever reason, this option can be used. Note 5905 that this also can be controlled per-workqueue for 5906 workqueues visible under /sys/bus/workqueue/. 5907 5908 workqueue.power_efficient 5909 Per-cpu workqueues are generally preferred because 5910 they show better performance thanks to cache 5911 locality; unfortunately, per-cpu workqueues tend to 5912 be more power hungry than unbound workqueues. 5913 5914 Enabling this makes the per-cpu workqueues which 5915 were observed to contribute significantly to power 5916 consumption unbound, leading to measurably lower 5917 power usage at the cost of small performance 5918 overhead. 5919 5920 The default value of this parameter is determined by 5921 the config option CONFIG_WQ_POWER_EFFICIENT_DEFAULT. 5922 5923 workqueue.debug_force_rr_cpu 5924 Workqueue used to implicitly guarantee that work 5925 items queued without explicit CPU specified are put 5926 on the local CPU. This guarantee is no longer true 5927 and while local CPU is still preferred work items 5928 may be put on foreign CPUs. This debug option 5929 forces round-robin CPU selection to flush out 5930 usages which depend on the now broken guarantee. 5931 When enabled, memory and cache locality will be 5932 impacted. 5933 5934 x2apic_phys [X86-64,APIC] Use x2apic physical mode instead of 5935 default x2apic cluster mode on platforms 5936 supporting x2apic. 5937 5938 x86_intel_mid_timer= [X86-32,APBT] 5939 Choose timer option for x86 Intel MID platform. 5940 Two valid options are apbt timer only and lapic timer 5941 plus one apbt timer for broadcast timer. 5942 x86_intel_mid_timer=apbt_only | lapic_and_apbt 5943 5944 xen_512gb_limit [KNL,X86-64,XEN] 5945 Restricts the kernel running paravirtualized under Xen 5946 to use only up to 512 GB of RAM. The reason to do so is 5947 crash analysis tools and Xen tools for doing domain 5948 save/restore/migration must be enabled to handle larger 5949 domains. 5950 5951 xen_emul_unplug= [HW,X86,XEN] 5952 Unplug Xen emulated devices 5953 Format: [unplug0,][unplug1] 5954 ide-disks -- unplug primary master IDE devices 5955 aux-ide-disks -- unplug non-primary-master IDE devices 5956 nics -- unplug network devices 5957 all -- unplug all emulated devices (NICs and IDE disks) 5958 unnecessary -- unplugging emulated devices is 5959 unnecessary even if the host did not respond to 5960 the unplug protocol 5961 never -- do not unplug even if version check succeeds 5962 5963 xen_legacy_crash [X86,XEN] 5964 Crash from Xen panic notifier, without executing late 5965 panic() code such as dumping handler. 5966 5967 xen_nopvspin [X86,XEN] 5968 Disables the qspinlock slowpath using Xen PV optimizations. 5969 This parameter is obsoleted by "nopvspin" parameter, which 5970 has equivalent effect for XEN platform. 5971 5972 xen_nopv [X86] 5973 Disables the PV optimizations forcing the HVM guest to 5974 run as generic HVM guest with no PV drivers. 5975 This option is obsoleted by the "nopv" option, which 5976 has equivalent effect for XEN platform. 5977 5978 xen_no_vector_callback 5979 [KNL,X86,XEN] Disable the vector callback for Xen 5980 event channel interrupts. 5981 5982 xen_scrub_pages= [XEN] 5983 Boolean option to control scrubbing pages before giving them back 5984 to Xen, for use by other domains. Can be also changed at runtime 5985 with /sys/devices/system/xen_memory/xen_memory0/scrub_pages. 5986 Default value controlled with CONFIG_XEN_SCRUB_PAGES_DEFAULT. 5987 5988 xen_timer_slop= [X86-64,XEN] 5989 Set the timer slop (in nanoseconds) for the virtual Xen 5990 timers (default is 100000). This adjusts the minimum 5991 delta of virtualized Xen timers, where lower values 5992 improve timer resolution at the expense of processing 5993 more timer interrupts. 5994 5995 xen.event_eoi_delay= [XEN] 5996 How long to delay EOI handling in case of event 5997 storms (jiffies). Default is 10. 5998 5999 xen.event_loop_timeout= [XEN] 6000 After which time (jiffies) the event handling loop 6001 should start to delay EOI handling. Default is 2. 6002 6003 xen.fifo_events= [XEN] 6004 Boolean parameter to disable using fifo event handling 6005 even if available. Normally fifo event handling is 6006 preferred over the 2-level event handling, as it is 6007 fairer and the number of possible event channels is 6008 much higher. Default is on (use fifo events). 6009 6010 nopv= [X86,XEN,KVM,HYPER_V,VMWARE] 6011 Disables the PV optimizations forcing the guest to run 6012 as generic guest with no PV drivers. Currently support 6013 XEN HVM, KVM, HYPER_V and VMWARE guest. 6014 6015 nopvspin [X86,XEN,KVM] 6016 Disables the qspinlock slow path using PV optimizations 6017 which allow the hypervisor to 'idle' the guest on lock 6018 contention. 6019 6020 xirc2ps_cs= [NET,PCMCIA] 6021 Format: 6022 <irq>,<irq_mask>,<io>,<full_duplex>,<do_sound>,<lockup_hack>[,<irq2>[,<irq3>[,<irq4>]]] 6023 6024 xive= [PPC] 6025 By default on POWER9 and above, the kernel will 6026 natively use the XIVE interrupt controller. This option 6027 allows the fallback firmware mode to be used: 6028 6029 off Fallback to firmware control of XIVE interrupt 6030 controller on both pseries and powernv 6031 platforms. Only useful on POWER9 and above. 6032 6033 xhci-hcd.quirks [USB,KNL] 6034 A hex value specifying bitmask with supplemental xhci 6035 host controller quirks. Meaning of each bit can be 6036 consulted in header drivers/usb/host/xhci.h. 6037 6038 xmon [PPC] 6039 Format: { early | on | rw | ro | off } 6040 Controls if xmon debugger is enabled. Default is off. 6041 Passing only "xmon" is equivalent to "xmon=early". 6042 early Call xmon as early as possible on boot; xmon 6043 debugger is called from setup_arch(). 6044 on xmon debugger hooks will be installed so xmon 6045 is only called on a kernel crash. Default mode, 6046 i.e. either "ro" or "rw" mode, is controlled 6047 with CONFIG_XMON_DEFAULT_RO_MODE. 6048 rw xmon debugger hooks will be installed so xmon 6049 is called only on a kernel crash, mode is write, 6050 meaning SPR registers, memory and, other data 6051 can be written using xmon commands. 6052 ro same as "rw" option above but SPR registers, 6053 memory, and other data can't be written using 6054 xmon commands. 6055 off xmon is disabled. 6056