4 The following is a consolidated list of the kernel parameters as
5 implemented by the __setup(), core_param() and module_param() macros
6 and sorted into English Dictionary order (defined as ignoring all
7 punctuation and sorting digits before letters in a case insensitive
8 manner), and with descriptions where known.
10 The kernel parses parameters from the kernel command line up to "--";
11 if it doesn't recognize a parameter and it doesn't contain a '.', the
12 parameter gets passed to init: parameters with '=' go into init's
13 environment, others are passed as command line arguments to init.
14 Everything after "--" is passed as an argument to init.
16 Module parameters can be specified in two ways: via the kernel command
17 line with a module name prefix, or via modprobe, e.g.:
19 (kernel command line) usbcore.blinkenlights=1
20 (modprobe command line) modprobe usbcore blinkenlights=1
22 Parameters for modules which are built into the kernel need to be
23 specified on the kernel command line. modprobe looks through the
24 kernel command line (/proc/cmdline) and collects module parameters
25 when it loads a module, so the kernel command line can be used for
28 Hyphens (dashes) and underscores are equivalent in parameter names, so
29 log_buf_len=1M print-fatal-signals=1
30 can also be entered as
31 log-buf-len=1M print_fatal_signals=1
33 Double-quotes can be used to protect spaces in values, e.g.:
34 param="spaces in here"
36 This document may not be entirely up to date and comprehensive. The command
37 "modinfo -p ${modulename}" shows a current list of all parameters of a loadable
38 module. Loadable modules, after being loaded into the running kernel, also
39 reveal their parameters in /sys/module/${modulename}/parameters/. Some of these
40 parameters may be changed at runtime by the command
41 "echo -n ${value} > /sys/module/${modulename}/parameters/${parm}".
43 The parameters listed below are only valid if certain kernel build options were
44 enabled and if respective hardware is present. The text in square brackets at
45 the beginning of each description states the restrictions within which a
46 parameter is applicable:
48 ACPI ACPI support is enabled.
49 AGP AGP (Accelerated Graphics Port) is enabled.
50 ALSA ALSA sound support is enabled.
51 APIC APIC support is enabled.
52 APM Advanced Power Management support is enabled.
53 ARM ARM architecture is enabled.
54 AVR32 AVR32 architecture is enabled.
55 AX25 Appropriate AX.25 support is enabled.
56 BLACKFIN Blackfin architecture is enabled.
57 CLK Common clock infrastructure is enabled.
58 CMA Contiguous Memory Area support is enabled.
59 DRM Direct Rendering Management support is enabled.
60 DYNAMIC_DEBUG Build in debug messages and enable them at runtime
61 EDD BIOS Enhanced Disk Drive Services (EDD) is enabled
62 EFI EFI Partitioning (GPT) is enabled
63 EIDE EIDE/ATAPI support is enabled.
64 EVM Extended Verification Module
65 FB The frame buffer device is enabled.
66 FTRACE Function tracing enabled.
67 GCOV GCOV profiling is enabled.
68 HW Appropriate hardware is enabled.
69 IA-64 IA-64 architecture is enabled.
70 IMA Integrity measurement architecture is enabled.
71 IOSCHED More than one I/O scheduler is enabled.
72 IP_PNP IP DHCP, BOOTP, or RARP is enabled.
73 IPV6 IPv6 support is enabled.
74 ISAPNP ISA PnP code is enabled.
75 ISDN Appropriate ISDN support is enabled.
76 JOY Appropriate joystick support is enabled.
77 KGDB Kernel debugger support is enabled.
78 KVM Kernel Virtual Machine support is enabled.
79 LIBATA Libata driver is enabled
80 LP Printer support is enabled.
81 LOOP Loopback device support is enabled.
82 M68k M68k architecture is enabled.
83 These options have more detailed description inside of
84 Documentation/m68k/kernel-options.txt.
85 MDA MDA console support is enabled.
86 MIPS MIPS architecture is enabled.
87 MOUSE Appropriate mouse support is enabled.
88 MSI Message Signaled Interrupts (PCI).
89 MTD MTD (Memory Technology Device) support is enabled.
90 NET Appropriate network support is enabled.
91 NUMA NUMA support is enabled.
92 NFS Appropriate NFS support is enabled.
93 OSS OSS sound support is enabled.
94 PV_OPS A paravirtualized kernel is enabled.
95 PARIDE The ParIDE (parallel port IDE) subsystem is enabled.
96 PARISC The PA-RISC architecture is enabled.
97 PCI PCI bus support is enabled.
98 PCIE PCI Express support is enabled.
99 PCMCIA The PCMCIA subsystem is enabled.
100 PNP Plug & Play support is enabled.
101 PPC PowerPC architecture is enabled.
102 PPT Parallel port support is enabled.
103 PS2 Appropriate PS/2 support is enabled.
104 RAM RAM disk support is enabled.
105 S390 S390 architecture is enabled.
106 SCSI Appropriate SCSI support is enabled.
107 A lot of drivers have their options described inside
108 the Documentation/scsi/ sub-directory.
109 SECURITY Different security models are enabled.
110 SELINUX SELinux support is enabled.
111 APPARMOR AppArmor support is enabled.
112 SERIAL Serial support is enabled.
113 SH SuperH architecture is enabled.
114 SMP The kernel is an SMP kernel.
115 SPARC Sparc architecture is enabled.
116 SWSUSP Software suspend (hibernation) is enabled.
117 SUSPEND System suspend states are enabled.
118 TPM TPM drivers are enabled.
119 TS Appropriate touchscreen support is enabled.
120 UMS USB Mass Storage support is enabled.
121 USB USB support is enabled.
122 USBHID USB Human Interface Device support is enabled.
123 V4L Video For Linux support is enabled.
124 VMMIO Driver for memory mapped virtio devices is enabled.
125 VGA The VGA console has been enabled.
126 VT Virtual terminal support is enabled.
127 WDT Watchdog support is enabled.
128 XT IBM PC/XT MFM hard disk support is enabled.
129 X86-32 X86-32, aka i386 architecture is enabled.
130 X86-64 X86-64 architecture is enabled.
131 More X86-64 boot options can be found in
132 Documentation/x86/x86_64/boot-options.txt .
133 X86 Either 32-bit or 64-bit x86 (same as X86-32+X86-64)
134 X86_UV SGI UV support is enabled.
135 XEN Xen support is enabled
137 In addition, the following text indicates that the option:
139 BUGS= Relates to possible processor bugs on the said processor.
140 KNL Is a kernel start-up parameter.
141 BOOT Is a boot loader parameter.
143 Parameters denoted with BOOT are actually interpreted by the boot
144 loader, and have no meaning to the kernel directly.
145 Do not modify the syntax of boot loader parameters without extreme
146 need or coordination with <Documentation/x86/boot.txt>.
148 There are also arch-specific kernel-parameters not documented here.
149 See for example <Documentation/x86/x86_64/boot-options.txt>.
151 Note that ALL kernel parameters listed below are CASE SENSITIVE, and that
152 a trailing = on the name of any parameter states that that parameter will
153 be entered as an environment variable, whereas its absence indicates that
154 it will appear as a kernel argument readable via /proc/cmdline by programs
155 running once the system is up.
157 The number of kernel parameters is not limited, but the length of the
158 complete command line (parameters including spaces etc.) is limited to
159 a fixed number of characters. This limit depends on the architecture
160 and is between 256 and 4096 characters. It is defined in the file
161 ./include/asm/setup.h as COMMAND_LINE_SIZE.
163 Finally, the [KMG] suffix is commonly described after a number of kernel
164 parameter values. These 'K', 'M', and 'G' letters represent the _binary_
165 multipliers 'Kilo', 'Mega', and 'Giga', equalling 2^10, 2^20, and 2^30
166 bytes respectively. Such letter suffixes can also be entirely omitted.
169 acpi= [HW,ACPI,X86,ARM64]
170 Advanced Configuration and Power Interface
171 Format: { force | on | off | strict | noirq | rsdt |
173 force -- enable ACPI if default was off
174 on -- enable ACPI but allow fallback to DT [arm64]
175 off -- disable ACPI if default was on
176 noirq -- do not use ACPI for IRQ routing
177 strict -- Be less tolerant of platforms that are not
178 strictly ACPI specification compliant.
179 rsdt -- prefer RSDT over (default) XSDT
180 copy_dsdt -- copy DSDT to memory
181 For ARM64, ONLY "acpi=off", "acpi=on" or "acpi=force"
184 See also Documentation/power/runtime_pm.txt, pci=noacpi
186 acpi_apic_instance= [ACPI, IOAPIC]
188 2: use 2nd APIC table, if available
189 1,0: use 1st APIC table
192 acpi_backlight= [HW,ACPI]
193 acpi_backlight=vendor
195 If set to vendor, prefer vendor specific driver
196 (e.g. thinkpad_acpi, sony_acpi, etc.) instead
197 of the ACPI video.ko driver.
199 acpi_force_32bit_fadt_addr
200 force FADT to use 32 bit addresses rather than the
201 64 bit X_* addresses. Some firmware have broken 64
202 bit addresses for force ACPI ignore these and use
203 the older legacy 32 bit addresses.
205 acpica_no_return_repair [HW, ACPI]
206 Disable AML predefined validation mechanism
207 This mechanism can repair the evaluation result to make
208 the return objects more ACPI specification compliant.
209 This option is useful for developers to identify the
210 root cause of an AML interpreter issue when the issue
211 has something to do with the repair mechanism.
213 acpi.debug_layer= [HW,ACPI,ACPI_DEBUG]
214 acpi.debug_level= [HW,ACPI,ACPI_DEBUG]
216 CONFIG_ACPI_DEBUG must be enabled to produce any ACPI
217 debug output. Bits in debug_layer correspond to a
218 _COMPONENT in an ACPI source file, e.g.,
219 #define _COMPONENT ACPI_PCI_COMPONENT
220 Bits in debug_level correspond to a level in
221 ACPI_DEBUG_PRINT statements, e.g.,
222 ACPI_DEBUG_PRINT((ACPI_DB_INFO, ...
223 The debug_level mask defaults to "info". See
224 Documentation/acpi/debug.txt for more information about
225 debug layers and levels.
227 Enable processor driver info messages:
228 acpi.debug_layer=0x20000000
229 Enable PCI/PCI interrupt routing info messages:
230 acpi.debug_layer=0x400000
231 Enable AML "Debug" output, i.e., stores to the Debug
232 object while interpreting AML:
233 acpi.debug_layer=0xffffffff acpi.debug_level=0x2
234 Enable all messages related to ACPI hardware:
235 acpi.debug_layer=0x2 acpi.debug_level=0xffffffff
237 Some values produce so much output that the system is
238 unusable. The "log_buf_len" parameter may be useful
239 if you need to capture more output.
241 acpi_enforce_resources= [ACPI]
242 { strict | lax | no }
243 Check for resource conflicts between native drivers
244 and ACPI OperationRegions (SystemIO and SystemMemory
245 only). IO ports and memory declared in ACPI might be
246 used by the ACPI subsystem in arbitrary AML code and
247 can interfere with legacy drivers.
248 strict (default): access to resources claimed by ACPI
249 is denied; legacy drivers trying to access reserved
250 resources will fail to bind to device using them.
251 lax: access to resources claimed by ACPI is allowed;
252 legacy drivers trying to access reserved resources
253 will bind successfully but a warning message is logged.
254 no: ACPI OperationRegions are not marked as reserved,
255 no further checks are performed.
257 acpi_force_table_verification [HW,ACPI]
258 Enable table checksum verification during early stage.
259 By default, this is disabled due to x86 early mapping
262 acpi_irq_balance [HW,ACPI]
263 ACPI will balance active IRQs
266 acpi_irq_nobalance [HW,ACPI]
267 ACPI will not move active IRQs (default)
270 acpi_irq_isa= [HW,ACPI] If irq_balance, mark listed IRQs used by ISA
271 Format: <irq>,<irq>...
273 acpi_irq_pci= [HW,ACPI] If irq_balance, clear listed IRQs for
275 Format: <irq>,<irq>...
277 acpi_no_auto_serialize [HW,ACPI]
278 Disable auto-serialization of AML methods
279 AML control methods that contain the opcodes to create
280 named objects will be marked as "Serialized" by the
281 auto-serialization feature.
282 This feature is enabled by default.
283 This option allows to turn off the feature.
285 acpi_no_memhotplug [ACPI] Disable memory hotplug. Useful for kdump
288 acpi_no_static_ssdt [HW,ACPI]
289 Disable installation of static SSDTs at early boot time
290 By default, SSDTs contained in the RSDT/XSDT will be
291 installed automatically and they will appear under
292 /sys/firmware/acpi/tables.
293 This option turns off this feature.
294 Note that specifying this option does not affect
295 dynamic table installation which will install SSDT
296 tables to /sys/firmware/acpi/tables/dynamic.
298 acpi_rsdp= [ACPI,EFI,KEXEC]
299 Pass the RSDP address to the kernel, mostly used
300 on machines running EFI runtime service to boot the
301 second kernel for kdump.
303 acpi_os_name= [HW,ACPI] Tell ACPI BIOS the name of the OS
304 Format: To spoof as Windows 98: ="Microsoft Windows"
306 acpi_rev_override [ACPI] Override the _REV object to return 5 (instead
307 of 2 which is mandated by ACPI 6) as the supported ACPI
308 specification revision (when using this switch, it may
309 be necessary to carry out a cold reboot _twice_ in a
310 row to make it take effect on the platform firmware).
312 acpi_osi= [HW,ACPI] Modify list of supported OS interface strings
313 acpi_osi="string1" # add string1
314 acpi_osi="!string2" # remove string2
315 acpi_osi=!* # remove all strings
316 acpi_osi=! # disable all built-in OS vendor
318 acpi_osi=!! # enable all built-in OS vendor
320 acpi_osi= # disable all strings
322 'acpi_osi=!' can be used in combination with single or
323 multiple 'acpi_osi="string1"' to support specific OS
324 vendor string(s). Note that such command can only
325 affect the default state of the OS vendor strings, thus
326 it cannot affect the default state of the feature group
327 strings and the current state of the OS vendor strings,
328 specifying it multiple times through kernel command line
329 is meaningless. This command is useful when one do not
330 care about the state of the feature group strings which
331 should be controlled by the OSPM.
333 1. 'acpi_osi=! acpi_osi="Windows 2000"' is equivalent
334 to 'acpi_osi="Windows 2000" acpi_osi=!', they all
335 can make '_OSI("Windows 2000")' TRUE.
337 'acpi_osi=' cannot be used in combination with other
338 'acpi_osi=' command lines, the _OSI method will not
339 exist in the ACPI namespace. NOTE that such command can
340 only affect the _OSI support state, thus specifying it
341 multiple times through kernel command line is also
344 1. 'acpi_osi=' can make 'CondRefOf(_OSI, Local1)'
347 'acpi_osi=!*' can be used in combination with single or
348 multiple 'acpi_osi="string1"' to support specific
349 string(s). Note that such command can affect the
350 current state of both the OS vendor strings and the
351 feature group strings, thus specifying it multiple times
352 through kernel command line is meaningful. But it may
353 still not able to affect the final state of a string if
354 there are quirks related to this string. This command
355 is useful when one want to control the state of the
356 feature group strings to debug BIOS issues related to
359 1. 'acpi_osi="Module Device" acpi_osi=!*' can make
360 '_OSI("Module Device")' FALSE.
361 2. 'acpi_osi=!* acpi_osi="Module Device"' can make
362 '_OSI("Module Device")' TRUE.
363 3. 'acpi_osi=! acpi_osi=!* acpi_osi="Windows 2000"' is
365 'acpi_osi=!* acpi_osi=! acpi_osi="Windows 2000"'
367 'acpi_osi=!* acpi_osi="Windows 2000" acpi_osi=!',
368 they all will make '_OSI("Windows 2000")' TRUE.
371 Override the pmtimer bug detection: force the kernel
372 to assume that this machine's pmtimer latches its value
373 and always returns good values.
375 acpi_sci= [HW,ACPI] ACPI System Control Interrupt trigger mode
376 Format: { level | edge | high | low }
378 acpi_skip_timer_override [HW,ACPI]
379 Recognize and ignore IRQ0/pin2 Interrupt Override.
380 For broken nForce2 BIOS resulting in XT-PIC timer.
382 acpi_sleep= [HW,ACPI] Sleep options
383 Format: { s3_bios, s3_mode, s3_beep, s4_nohwsig,
384 old_ordering, nonvs, sci_force_enable }
385 See Documentation/power/video.txt for information on
387 s3_beep is for debugging; it makes the PC's speaker beep
388 as soon as the kernel's real-mode entry point is called.
389 s4_nohwsig prevents ACPI hardware signature from being
390 used during resume from hibernation.
391 old_ordering causes the ACPI 1.0 ordering of the _PTS
392 control method, with respect to putting devices into
393 low power states, to be enforced (the ACPI 2.0 ordering
394 of _PTS is used by default).
395 nonvs prevents the kernel from saving/restoring the
396 ACPI NVS memory during suspend/hibernation and resume.
397 sci_force_enable causes the kernel to set SCI_EN directly
398 on resume from S1/S3 (which is against the ACPI spec,
399 but some broken systems don't work without it).
401 acpi_use_timer_override [HW,ACPI]
402 Use timer override. For some broken Nvidia NF5 boards
403 that require a timer override, but don't have HPET
405 add_efi_memmap [EFI; X86] Include EFI memory map in
406 kernel's map of available physical RAM.
409 { off | try_unsupported }
410 off: disable AGP support
411 try_unsupported: try to drive unsupported chipsets
412 (may crash computer or cause data corruption)
415 See Documentation/sound/alsa/alsa-parameters.txt
418 Allow the default userspace alignment fault handler
419 behaviour to be specified. Bit 0 enables warnings,
420 bit 1 enables fixups, and bit 2 sends a segfault.
422 align_va_addr= [X86-64]
423 Align virtual addresses by clearing slice [14:12] when
424 allocating a VMA at process creation time. This option
425 gives you up to 3% performance improvement on AMD F15h
426 machines (where it is enabled by default) for a
427 CPU-intensive style benchmark, and it can vary highly in
428 a microbenchmark depending on workload and compiler.
430 32: only for 32-bit processes
431 64: only for 64-bit processes
432 on: enable for both 32- and 64-bit processes
433 off: disable for both 32- and 64-bit processes
435 alloc_snapshot [FTRACE]
436 Allocate the ftrace snapshot buffer on boot up when the
437 main buffer is allocated. This is handy if debugging
438 and you need to use tracing_snapshot() on boot up, and
439 do not want to use tracing_snapshot_alloc() as it needs
440 to be done where GFP_KERNEL allocations are allowed.
442 amd_iommu= [HW,X86-64]
443 Pass parameters to the AMD IOMMU driver in the system.
445 fullflush - enable flushing of IO/TLB entries when
446 they are unmapped. Otherwise they are
447 flushed before they will be reused, which
449 off - do not initialize any AMD IOMMU found in
451 force_isolation - Force device isolation for all
452 devices. The IOMMU driver is not
453 allowed anymore to lift isolation
454 requirements as needed. This option
455 does not override iommu=pt
457 amd_iommu_dump= [HW,X86-64]
458 Enable AMD IOMMU driver option to dump the ACPI table
459 for AMD IOMMU. With this option enabled, AMD IOMMU
460 driver will print ACPI tables for AMD IOMMU during
461 IOMMU initialization.
463 amijoy.map= [HW,JOY] Amiga joystick support
464 Map of devices attached to JOY0DAT and JOY1DAT
466 See also Documentation/input/joystick.txt
468 analog.map= [HW,JOY] Analog joystick and gamepad support
469 Specifies type or capabilities of an analog joystick
470 connected to one of 16 gameports
471 Format: <type1>,<type2>,..<type16>
474 Power management functions (SPARCstation-4/5 + deriv.)
476 Disable APC CPU standby support. SPARCstation-Fox does
477 not play well with APC CPU idle - disable it if you have
478 APC and your system crashes randomly.
480 apic= [APIC,X86-32] Advanced Programmable Interrupt Controller
481 Change the output verbosity whilst booting
482 Format: { quiet (default) | verbose | debug }
483 Change the amount of debugging information output
484 when initialising the APIC and IO-APIC components.
486 apic_extnmi= [APIC,X86] External NMI delivery setting
487 Format: { bsp (default) | all | none }
488 bsp: External NMI is delivered only to CPU 0
489 all: External NMIs are broadcast to all CPUs as a
491 none: External NMI is masked for all CPUs. This is
492 useful so that a dump capture kernel won't be
496 See Documentation/networking/ipv6.txt.
498 show_lapic= [APIC,X86] Advanced Programmable Interrupt Controller
499 Limit apic dumping. The parameter defines the maximal
500 number of local apics being dumped. Also it is possible
501 to set it to "all" by meaning -- no limit here.
502 Format: { 1 (default) | 2 | ... | all }.
503 The parameter valid if only apic=debug or
504 apic=verbose is specified.
505 Example: apic=debug show_lapic=all
507 apm= [APM] Advanced Power Management
508 See header of arch/x86/kernel/apm_32.c.
510 arcrimi= [HW,NET] ARCnet - "RIM I" (entirely mem-mapped) cards
511 Format: <io>,<irq>,<nodeID>
515 atarimouse= [HW,MOUSE] Atari Mouse
517 atkbd.extra= [HW] Enable extra LEDs and keys on IBM RapidAccess,
518 EzKey and similar keyboards
520 atkbd.reset= [HW] Reset keyboard during initialization
522 atkbd.set= [HW] Select keyboard code set
523 Format: <int> (2 = AT (default), 3 = PS/2)
525 atkbd.scroll= [HW] Enable scroll wheel on MS Office and similar
528 atkbd.softraw= [HW] Choose between synthetic and real raw mode
529 Format: <bool> (0 = real, 1 = synthetic (default))
531 atkbd.softrepeat= [HW]
532 Use software keyboard repeat
534 audit= [KNL] Enable the audit sub-system
535 Format: { "0" | "1" } (0 = disabled, 1 = enabled)
536 0 - kernel audit is disabled and can not be enabled
537 until the next reboot
538 unset - kernel audit is initialized but disabled and
539 will be fully enabled by the userspace auditd.
540 1 - kernel audit is initialized and partially enabled,
541 storing at most audit_backlog_limit messages in
542 RAM until it is fully enabled by the userspace
546 audit_backlog_limit= [KNL] Set the audit queue size limit.
547 Format: <int> (must be >=0)
550 bau= [X86_UV] Enable the BAU on SGI UV. The default
551 behavior is to disable the BAU (i.e. bau=0).
552 Format: { "0" | "1" }
555 unset - Disable the BAU.
557 baycom_epp= [HW,AX25]
560 baycom_par= [HW,AX25] BayCom Parallel Port AX.25 Modem
562 See header of drivers/net/hamradio/baycom_par.c.
564 baycom_ser_fdx= [HW,AX25]
565 BayCom Serial Port AX.25 Modem (Full Duplex Mode)
566 Format: <io>,<irq>,<mode>[,<baud>]
567 See header of drivers/net/hamradio/baycom_ser_fdx.c.
569 baycom_ser_hdx= [HW,AX25]
570 BayCom Serial Port AX.25 Modem (Half Duplex Mode)
571 Format: <io>,<irq>,<mode>
572 See header of drivers/net/hamradio/baycom_ser_hdx.c.
574 blkdevparts= Manual partition parsing of block device(s) for
575 embedded devices based on command line input.
576 See Documentation/block/cmdline-partition.txt
578 boot_delay= Milliseconds to delay each printk during boot.
579 Values larger than 10 seconds (10000) are changed to
583 bootmem_debug [KNL] Enable bootmem allocator debug messages.
585 bttv.card= [HW,V4L] bttv (bt848 + bt878 based grabber cards)
586 bttv.radio= Most important insmod options are available as
588 bttv.pll= See Documentation/video4linux/bttv/Insmod-options
591 bulk_remove=off [PPC] This parameter disables the use of the pSeries
592 firmware feature for flushing multiple hpte entries
595 c101= [NET] Moxa C101 synchronous serial card
597 cachesize= [BUGS=X86-32] Override level 2 CPU cache size detection.
598 Sometimes CPU hardware bugs make them report the cache
599 size incorrectly. The kernel will attempt work arounds
600 to fix known problems, but for some CPUs it is not
601 possible to determine what the correct size should be.
602 This option provides an override for these situations.
604 ca_keys= [KEYS] This parameter identifies a specific key(s) on
605 the system trusted keyring to be used for certificate
607 format: { id:<keyid> | builtin }
609 cca= [MIPS] Override the kernel pages' cache coherency
610 algorithm. Accepted values range from 0 to 7
611 inclusive. See arch/mips/include/asm/pgtable-bits.h
612 for platform specific values (SB1, Loongson3 and
615 ccw_timeout_log [S390]
616 See Documentation/s390/CommonIO for details.
618 cgroup_disable= [KNL] Disable a particular controller
619 Format: {name of the controller(s) to disable}
620 The effects of cgroup_disable=foo are:
621 - foo isn't auto-mounted if you mount all cgroups in
623 - foo isn't visible as an individually mountable
625 {Currently only "memory" controller deal with this and
626 cut the overhead, others just disable the usage. So
627 only cgroup_disable=memory is actually worthy}
629 cgroup_no_v1= [KNL] Disable one, multiple, all cgroup controllers in v1
630 Format: { controller[,controller...] | "all" }
631 Like cgroup_disable, but only applies to cgroup v1;
632 the blacklisted controllers remain available in cgroup2.
634 cgroup.memory= [KNL] Pass options to the cgroup memory controller.
636 nosocket -- Disable socket memory accounting.
637 nokmem -- Disable kernel memory accounting.
639 checkreqprot [SELINUX] Set initial checkreqprot flag value.
640 Format: { "0" | "1" }
641 See security/selinux/Kconfig help text.
642 0 -- check protection applied by kernel (includes
643 any implied execute protection).
644 1 -- check protection requested by application.
645 Default value is set via a kernel config option.
646 Value can be changed at runtime via
647 /selinux/checkreqprot.
650 See Documentation/s390/CommonIO for details.
653 Prevents the clock framework from automatically gating
654 clocks that have not been explicitly enabled by a Linux
655 device driver but are enabled in hardware at reset or
656 by the bootloader/firmware. Note that this does not
657 force such clocks to be always-on nor does it reserve
658 those clocks in any way. This parameter is useful for
659 debug and development, but should not be needed on a
660 platform with proper driver support. For more
661 information, see Documentation/clk.txt.
663 clock= [BUGS=X86-32, HW] gettimeofday clocksource override.
665 Forces specified clocksource (if available) to be used
666 when calculating gettimeofday(). If specified
667 clocksource is not available, it defaults to PIT.
668 Format: { pit | tsc | cyclone | pmtmr }
670 clocksource= Override the default clocksource
672 Override the default clocksource and use the clocksource
673 with the name specified.
674 Some clocksource names to choose from, depending on
676 [all] jiffies (this is the base, fallback clocksource)
678 [ARM] imx_timer1,OSTS,netx_timer,mpu_timer2,
679 pxa_timer,timer3,32k_counter,timer0_1
681 [X86-32] pit,hpet,tsc;
682 scx200_hrt on Geode; cyclone on IBM x440
690 clearcpuid=BITNUM [X86]
691 Disable CPUID feature X for the kernel. See
692 arch/x86/include/asm/cpufeatures.h for the valid bit
693 numbers. Note the Linux specific bits are not necessarily
694 stable over kernel options, but the vendor specific
696 Also note that user programs calling CPUID directly
697 or using the feature without checking anything
698 will still see it. This just prevents it from
699 being used by the kernel or shown in /proc/cpuinfo.
700 Also note the kernel might malfunction if you disable
703 cma=nn[MG]@[start[MG][-end[MG]]]
705 Sets the size of kernel global memory area for
706 contiguous memory allocations and optionally the
707 placement constraint by the physical address range of
708 memory allocations. A value of 0 disables CMA
709 altogether. For more information, see
710 include/linux/dma-contiguous.h
712 cmo_free_hint= [PPC] Format: { yes | no }
713 Specify whether pages are marked as being inactive
714 when they are freed. This is used in CMO environments
715 to determine OS memory pressure for page stealing by
719 coherent_pool=nn[KMG] [ARM,KNL]
720 Sets the size of memory pool for coherent, atomic dma
721 allocations, by default set to 256K.
723 code_bytes [X86] How many bytes of object code to print
728 com20020= [HW,NET] ARCnet - COM20020 chipset
730 <io>[,<irq>[,<nodeID>[,<backplane>[,<ckp>[,<timeout>]]]]]
732 com90io= [HW,NET] ARCnet - COM90xx chipset (IO-mapped buffers)
736 ARCnet - COM90xx chipset (memory-mapped buffers)
737 Format: <io>[,<irq>[,<memstart>]]
739 condev= [HW,S390] console device
742 console= [KNL] Output console device and options.
744 tty<n> Use the virtual console device <n>.
748 Use the specified serial port. The options are of
749 the form "bbbbpnf", where "bbbb" is the baud rate,
750 "p" is parity ("n", "o", or "e"), "n" is number of
751 bits, and "f" is flow control ("r" for RTS or
752 omit it). Default is "9600n8".
754 See Documentation/serial-console.txt for more
756 Documentation/networking/netconsole.txt for an
759 uart[8250],io,<addr>[,options]
760 uart[8250],mmio,<addr>[,options]
761 uart[8250],mmio16,<addr>[,options]
762 uart[8250],mmio32,<addr>[,options]
763 uart[8250],0x<addr>[,options]
764 Start an early, polled-mode console on the 8250/16550
765 UART at the specified I/O port or MMIO address,
766 switching to the matching ttyS device later.
767 MMIO inter-register address stride is either 8-bit
768 (mmio), 16-bit (mmio16), or 32-bit (mmio32).
769 If none of [io|mmio|mmio16|mmio32], <addr> is assumed
770 to be equivalent to 'mmio'. 'options' are specified in
771 the same format described for ttyS above; if unspecified,
772 the h/w is not re-initialized.
774 hvc<n> Use the hypervisor console device <n>. This is for
775 both Xen and PowerPC hypervisors.
777 If the device connected to the port is not a TTY but a braille
778 device, prepend "brl," before the device type, for instance
780 For now, only VisioBraille is supported.
782 consoleblank= [KNL] The console blank (screen saver) timeout in
783 seconds. Defaults to 10*60 = 10mins. A value of 0
784 disables the blank timer.
787 [KNL] Change the default value for
788 /proc/<pid>/coredump_filter.
789 See also Documentation/filesystems/proc.txt.
791 cpuidle.off=1 [CPU_IDLE]
792 disable the cpuidle sub-system
795 [X86] Delay for N microsec between assert and de-assert
796 of APIC INIT to start processors. This delay occurs
797 on every CPU online, such as boot, and resume from suspend.
800 cpcihp_generic= [HW,PCI] Generic port I/O CompactPCI driver
802 <first_slot>,<last_slot>,<port>,<enum_bit>[,<debug>]
804 crashkernel=size[KMG][@offset[KMG]]
805 [KNL] Using kexec, Linux can switch to a 'crash kernel'
806 upon panic. This parameter reserves the physical
807 memory region [offset, offset + size] for that kernel
808 image. If '@offset' is omitted, then a suitable offset
809 is selected automatically. Check
810 Documentation/kdump/kdump.txt for further details.
812 crashkernel=range1:size1[,range2:size2,...][@offset]
813 [KNL] Same as above, but depends on the memory
814 in the running system. The syntax of range is
815 start-[end] where start and end are both
816 a memory unit (amount[KMG]). See also
817 Documentation/kdump/kdump.txt for an example.
819 crashkernel=size[KMG],high
820 [KNL, x86_64] range could be above 4G. Allow kernel
821 to allocate physical memory region from top, so could
822 be above 4G if system have more than 4G ram installed.
823 Otherwise memory region will be allocated below 4G, if
825 It will be ignored if crashkernel=X is specified.
826 crashkernel=size[KMG],low
827 [KNL, x86_64] range under 4G. When crashkernel=X,high
828 is passed, kernel could allocate physical memory region
829 above 4G, that cause second kernel crash on system
830 that require some amount of low memory, e.g. swiotlb
831 requires at least 64M+32K low memory, also enough extra
832 low memory is needed to make sure DMA buffers for 32-bit
833 devices won't run out. Kernel would try to allocate at
834 at least 256M below 4G automatically.
835 This one let user to specify own low range under 4G
836 for second kernel instead.
837 0: to disable low allocation.
838 It will be ignored when crashkernel=X,high is not used
839 or memory reserved is below 4G.
842 [KNL] Disable crypto self-tests
847 cs89x0_media= [HW,NET]
848 Format: { rj45 | aui | bnc }
851 See header of drivers/s390/block/dasd_devmap.c.
853 db9.dev[2|3]= [HW,JOY] Multisystem joystick support via parallel port
854 (one device per port)
855 Format: <port#>,<type>
856 See also Documentation/input/joystick-parport.txt
858 ddebug_query= [KNL,DYNAMIC_DEBUG] Enable debug messages at early boot
859 time. See Documentation/dynamic-debug-howto.txt for
860 details. Deprecated, see dyndbg.
862 debug [KNL] Enable kernel debugging (events log level).
865 [KNL] verbose self-tests
867 Print debugging info while doing the locking API
869 We default to 0 (no extra messages), setting it to
870 1 will print _a lot_ more information - normally
871 only useful to kernel developers.
873 debug_objects [KNL] Enable object debugging
876 [KNL] Disable object debugging
878 debug_guardpage_minorder=
879 [KNL] When CONFIG_DEBUG_PAGEALLOC is set, this
880 parameter allows control of the order of pages that will
881 be intentionally kept free (and hence protected) by the
882 buddy allocator. Bigger value increase the probability
883 of catching random memory corruption, but reduce the
884 amount of memory for normal system use. The maximum
885 possible value is MAX_ORDER/2. Setting this parameter
886 to 1 or 2 should be enough to identify most random
887 memory corruption problems caused by bugs in kernel or
888 driver code when a CPU writes to (or reads from) a
889 random memory location. Note that there exists a class
890 of memory corruptions problems caused by buggy H/W or
891 F/W or by drivers badly programing DMA (basically when
892 memory is written at bus level and the CPU MMU is
893 bypassed) which are not detectable by
894 CONFIG_DEBUG_PAGEALLOC, hence this option will not help
895 tracking down these problems.
898 [KNL] When CONFIG_DEBUG_PAGEALLOC is set, this
899 parameter enables the feature at boot time. In
900 default, it is disabled. We can avoid allocating huge
901 chunk of memory for debug pagealloc if we don't enable
902 it at boot time and the system will work mostly same
903 with the kernel built without CONFIG_DEBUG_PAGEALLOC.
904 on: enable the feature
906 debugpat [X86] Enable PAT debugging
908 decnet.addr= [HW,NET]
909 Format: <area>[,<node>]
910 See also Documentation/networking/decnet.txt.
913 [same as hugepagesz=] The size of the default
914 HugeTLB page size. This is the size represented by
915 the legacy /proc/ hugepages APIs, used for SHM, and
916 default size when mounting hugetlbfs filesystems.
917 Defaults to the default architecture's huge page size
921 Set number of hash buckets for dentry cache.
924 See Documentation/networking/ipv6.txt.
926 disable_cpu_apicid= [X86,APIC,SMP]
928 The number of initial APIC ID for the
929 corresponding CPU to be disabled at boot,
930 mostly used for the kdump 2nd kernel to
931 disable BSP to wake up multiple CPUs without
932 causing system reset or hang due to sending
935 disable_ddw [PPC/PSERIES]
936 Disable Dynamic DMA Window support. Use this if
937 to workaround buggy firmware.
940 See Documentation/networking/ipv6.txt.
942 disable_mtrr_cleanup [X86]
943 The kernel tries to adjust MTRR layout from continuous
944 to discrete, to make X server driver able to add WB
945 entry later. This parameter disables that.
947 disable_mtrr_trim [X86, Intel and AMD only]
948 By default the kernel will trim any uncacheable
949 memory out of your available memory pool based on
950 MTRR settings. This parameter disables that behavior,
951 possibly causing your machine to run very slowly.
953 disable_timer_pin_1 [X86]
954 Disable PIN 1 of APIC timer
955 Can be useful to work around chipset bugs.
957 dis_ucode_ldr [X86] Disable the microcode loader.
959 dma_debug=off If the kernel is compiled with DMA_API_DEBUG support,
960 this option disables the debugging code at boot.
962 dma_debug_entries=<number>
963 This option allows to tune the number of preallocated
964 entries for DMA-API debugging code. One entry is
965 required per DMA-API allocation. Use this if the
966 DMA-API debugging code disables itself because the
967 architectural default is too low.
969 dma_debug_driver=<driver_name>
970 With this option the DMA-API debugging driver
971 filter feature can be enabled at boot time. Just
972 pass the driver to filter for as the parameter.
973 The filter can be disabled or changed to another
974 driver later using sysfs.
976 drm_kms_helper.edid_firmware=[<connector>:]<file>[,[<connector>:]<file>]
977 Broken monitors, graphic adapters, KVMs and EDIDless
978 panels may send no or incorrect EDID data sets.
979 This parameter allows to specify an EDID data sets
980 in the /lib/firmware directory that are used instead.
981 Generic built-in EDID data sets are used, if one of
982 edid/1024x768.bin, edid/1280x1024.bin,
983 edid/1680x1050.bin, or edid/1920x1080.bin is given
984 and no file with the same name exists. Details and
985 instructions how to build your own EDID data are
986 available in Documentation/EDID/HOWTO.txt. An EDID
987 data set will only be used for a particular connector,
988 if its name and a colon are prepended to the EDID
989 name. Each connector may use a unique EDID data
990 set by separating the files with a comma. An EDID
991 data set with no connector name will be used for
992 any connectors not explicitly specified.
996 dyndbg[="val"] [KNL,DYNAMIC_DEBUG]
997 module.dyndbg[="val"]
998 Enable debug messages at boot time. See
999 Documentation/dynamic-debug-howto.txt for details.
1001 nompx [X86] Disables Intel Memory Protection Extensions.
1002 See Documentation/x86/intel_mpx.txt for more
1003 information about the feature.
1005 nopku [X86] Disable Memory Protection Keys CPU feature found
1009 on enable eager fpu restore
1010 off disable eager fpu restore
1011 auto selects the default scheme, which automatically
1012 enables eagerfpu restore for xsaveopt.
1014 module.async_probe [KNL]
1015 Enable asynchronous probe on this module.
1017 early_ioremap_debug [KNL]
1018 Enable debug messages in early_ioremap support. This
1019 is useful for tracking down temporary early mappings
1020 which are not unmapped.
1022 earlycon= [KNL] Output early console device and options.
1024 When used with no options, the early console is
1025 determined by the stdout-path property in device
1029 Start an early, polled-mode console on a cadence serial
1030 port at the specified address. The cadence serial port
1031 must already be setup and configured. Options are not
1034 uart[8250],io,<addr>[,options]
1035 uart[8250],mmio,<addr>[,options]
1036 uart[8250],mmio32,<addr>[,options]
1037 uart[8250],mmio32be,<addr>[,options]
1038 uart[8250],0x<addr>[,options]
1039 Start an early, polled-mode console on the 8250/16550
1040 UART at the specified I/O port or MMIO address.
1041 MMIO inter-register address stride is either 8-bit
1042 (mmio) or 32-bit (mmio32 or mmio32be).
1043 If none of [io|mmio|mmio32|mmio32be], <addr> is assumed
1044 to be equivalent to 'mmio'. 'options' are specified
1045 in the same format described for "console=ttyS<n>"; if
1046 unspecified, the h/w is not initialized.
1050 Start an early, polled-mode console on a pl011 serial
1051 port at the specified address. The pl011 serial port
1052 must already be setup and configured. Options are not
1053 yet supported. If 'mmio32' is specified, then only
1054 the driver will use only 32-bit accessors to read/write
1055 the device registers.
1058 Start an early, polled-mode console on a meson serial
1059 port at the specified address. The serial port must
1060 already be setup and configured. Options are not yet
1064 Start an early, polled-mode console on an msm serial
1065 port at the specified address. The serial port
1066 must already be setup and configured. Options are not
1069 msm_serial_dm,<addr>
1070 Start an early, polled-mode console on an msm serial
1071 dm port at the specified address. The serial port
1072 must already be setup and configured. Options are not
1075 smh Use ARM semihosting calls for early console.
1083 Use early console provided by serial driver available
1084 on Samsung SoCs, requires selecting proper type and
1085 a correct base address of the selected UART port. The
1086 serial port must already be setup and configured.
1087 Options are not yet supported.
1091 Use early console provided by Freescale LP UART driver
1092 found on Freescale Vybrid and QorIQ LS1021A processors.
1093 A valid base address must be provided, and the serial
1094 port must already be setup and configured.
1096 armada3700_uart,<addr>
1097 Start an early, polled-mode console on the
1098 Armada 3700 serial port at the specified
1099 address. The serial port must already be setup
1100 and configured. Options are not yet supported.
1102 earlyprintk= [X86,SH,BLACKFIN,ARM,M68k]
1106 earlyprintk=serial[,ttySn[,baudrate]]
1107 earlyprintk=serial[,0x...[,baudrate]]
1108 earlyprintk=ttySn[,baudrate]
1109 earlyprintk=dbgp[debugController#]
1110 earlyprintk=pciserial,bus:device.function[,baudrate]
1112 earlyprintk is useful when the kernel crashes before
1113 the normal console is initialized. It is not enabled by
1114 default because it has some cosmetic problems.
1116 Append ",keep" to not disable it when the real console
1119 Only one of vga, efi, serial, or usb debug port can
1122 Currently only ttyS0 and ttyS1 may be specified by
1123 name. Other I/O ports may be explicitly specified
1124 on some architectures (x86 and arm at least) by
1125 replacing ttySn with an I/O port address, like this:
1126 earlyprintk=serial,0x1008,115200
1127 You can find the port for a given device in
1128 /proc/tty/driver/serial:
1129 2: uart:ST16650V2 port:00001008 irq:18 ...
1131 Interaction with the standard serial driver is not
1134 The VGA and EFI output is eventually overwritten by
1137 The xen output can only be used by Xen PV guests.
1139 edac_report= [HW,EDAC] Control how to report EDAC event
1140 Format: {"on" | "off" | "force"}
1141 on: enable EDAC to report H/W event. May be overridden
1142 by other higher priority error reporting module.
1143 off: disable H/W event reporting through EDAC.
1144 force: enforce the use of EDAC to report H/W event.
1147 ekgdboc= [X86,KGDB] Allow early kernel console debugging
1150 This is designed to be used in conjunction with
1151 the boot argument: earlyprintk=vga
1154 Format: {"off" | "on" | "skip[mbr]"}
1157 Format: { "old_map", "nochunk", "noruntime", "debug" }
1158 old_map [X86-64]: switch to the old ioremap-based EFI
1159 runtime services mapping. 32-bit still uses this one by
1161 nochunk: disable reading files in "chunks" in the EFI
1162 boot stub, as chunking can cause problems with some
1163 firmware implementations.
1164 noruntime : disable EFI runtime services support
1165 debug: enable misc debug output
1167 efi_no_storage_paranoia [EFI; X86]
1168 Using this parameter you can use more than 50% of
1169 your efi variable storage. Use this parameter only if
1170 you are really sure that your UEFI does sane gc and
1171 fulfills the spec otherwise your board may brick.
1173 efi_fake_mem= nn[KMG]@ss[KMG]:aa[,nn[KMG]@ss[KMG]:aa,..] [EFI; X86]
1174 Add arbitrary attribute to specific memory range by
1175 updating original EFI memory map.
1176 Region of memory which aa attribute is added to is
1178 If efi_fake_mem=2G@4G:0x10000,2G@0x10a0000000:0x10000
1179 is specified, EFI_MEMORY_MORE_RELIABLE(0x10000)
1180 attribute is added to range 0x100000000-0x180000000 and
1181 0x10a0000000-0x1120000000.
1183 Using this parameter you can do debugging of EFI memmap
1184 related feature. For example, you can do debugging of
1185 Address Range Mirroring feature even if your box
1188 eisa_irq_edge= [PARISC,HW]
1189 See header of drivers/parisc/eisa.c.
1192 See comment before function elanfreq_setup() in
1193 arch/x86/kernel/cpu/cpufreq/elanfreq.c.
1196 Format: {"cfq" | "deadline" | "noop"}
1197 See Documentation/block/cfq-iosched.txt and
1198 Documentation/block/deadline-iosched.txt for details.
1200 elfcorehdr=[size[KMG]@]offset[KMG] [IA64,PPC,SH,X86,S390]
1201 Specifies physical address of start of kernel core
1202 image elf header and optionally the size. Generally
1203 kexec loader will pass this option to capture kernel.
1204 See Documentation/kdump/kdump.txt for details.
1206 enable_mtrr_cleanup [X86]
1207 The kernel tries to adjust MTRR layout from continuous
1208 to discrete, to make X server driver able to add WB
1209 entry later. This parameter enables that.
1211 enable_timer_pin_1 [X86]
1212 Enable PIN 1 of APIC timer
1213 Can be useful to work around chipset bugs
1214 (in particular on some ATI chipsets).
1215 The kernel tries to set a reasonable default.
1217 enforcing [SELINUX] Set initial enforcing status.
1219 See security/selinux/Kconfig help text.
1220 0 -- permissive (log only, no denials).
1221 1 -- enforcing (deny and log).
1223 Value can be changed at runtime via /selinux/enforce.
1226 Disable Error Record Serialization Table (ERST)
1229 ether= [HW,NET] Ethernet cards parameters
1230 This option is obsoleted by the "netdev=" option, which
1231 has equivalent usage. See its documentation for details.
1235 Permit 'security.evm' to be updated regardless of
1236 current integrity status.
1240 fail_make_request=[KNL]
1241 General fault injection mechanism.
1242 Format: <interval>,<probability>,<space>,<times>
1243 See also Documentation/fault-injection/.
1246 See Documentation/blockdev/floppy.txt.
1248 force_pal_cache_flush
1249 [IA-64] Avoid check_sal_cache_flush which may hang on
1250 buggy SAL_CACHE_FLUSH implementations. Using this
1251 parameter will force ia64_sal_cache_flush to call
1252 ia64_pal_cache_flush instead of SAL_CACHE_FLUSH.
1255 Forcefully enable Physical Address Extension (PAE).
1256 Many Pentium M systems disable PAE but may have a
1257 functionally usable PAE implementation.
1258 Warning: use of this parameter will taint the kernel
1259 and may cause unknown problems.
1262 [FTRACE] will set and start the specified tracer
1263 as early as possible in order to facilitate early
1266 ftrace_dump_on_oops[=orig_cpu]
1267 [FTRACE] will dump the trace buffers on oops.
1268 If no parameter is passed, ftrace will dump
1269 buffers of all CPUs, but if you pass orig_cpu, it will
1270 dump only the buffer of the CPU that triggered the
1273 ftrace_filter=[function-list]
1274 [FTRACE] Limit the functions traced by the function
1275 tracer at boot up. function-list is a comma separated
1276 list of functions. This list can be changed at run
1277 time by the set_ftrace_filter file in the debugfs
1280 ftrace_notrace=[function-list]
1281 [FTRACE] Do not trace the functions specified in
1282 function-list. This list can be changed at run time
1283 by the set_ftrace_notrace file in the debugfs
1286 ftrace_graph_filter=[function-list]
1287 [FTRACE] Limit the top level callers functions traced
1288 by the function graph tracer at boot up.
1289 function-list is a comma separated list of functions
1290 that can be changed at run time by the
1291 set_graph_function file in the debugfs tracing directory.
1293 ftrace_graph_notrace=[function-list]
1294 [FTRACE] Do not trace from the functions specified in
1295 function-list. This list is a comma separated list of
1296 functions that can be changed at run time by the
1297 set_graph_notrace file in the debugfs tracing directory.
1300 [HW,JOY] Multisystem joystick and NES/SNES/PSX pad
1301 support via parallel port (up to 5 devices per port)
1302 Format: <port#>,<pad1>,<pad2>,<pad3>,<pad4>,<pad5>
1303 See also Documentation/input/joystick-parport.txt
1307 gart_fix_e820= [X86_64] disable the fix e820 for K8 GART
1311 gcov_persist= [GCOV] When non-zero (default), profiling data for
1312 kernel modules is saved and remains accessible via
1313 debugfs, even when the module is unloaded/reloaded.
1314 When zero, profiling data is discarded and associated
1315 debugfs files are removed at module unload time.
1317 gpt [EFI] Forces disk with valid GPT signature but
1318 invalid Protective MBR to be treated as GPT. If the
1319 primary GPT is corrupted, it enables the backup/alternate
1320 GPT to be used instead.
1322 grcan.enable0= [HW] Configuration of physical interface 0. Determines
1323 the "Enable 0" bit of the configuration register.
1326 grcan.enable1= [HW] Configuration of physical interface 1. Determines
1327 the "Enable 0" bit of the configuration register.
1330 grcan.select= [HW] Select which physical interface to use.
1333 grcan.txsize= [HW] Sets the size of the tx buffer.
1334 Format: <unsigned int> such that (txsize & ~0x1fffc0) == 0.
1336 grcan.rxsize= [HW] Sets the size of the rx buffer.
1337 Format: <unsigned int> such that (rxsize & ~0x1fffc0) == 0.
1340 hardlockup_all_cpu_backtrace=
1341 [KNL] Should the hard-lockup detector generate
1342 backtraces on all cpus.
1345 hashdist= [KNL,NUMA] Large hashes allocated during boot
1346 are distributed across NUMA nodes. Defaults on
1347 for 64-bit NUMA, off otherwise.
1348 Format: 0 | 1 (for off | on)
1350 hcl= [IA-64] SGI's Hardware Graph compatibility layer
1352 hd= [EIDE] (E)IDE hard drive subsystem geometry
1353 Format: <cyl>,<head>,<sect>
1356 Disable Hardware Error Source Table (HEST) support;
1357 corresponding firmware-first mode error processing
1358 logic will be disabled.
1360 highmem=nn[KMG] [KNL,BOOT] forces the highmem zone to have an exact
1361 size of <nn>. This works even on boxes that have no
1362 highmem otherwise. This also works to reduce highmem
1363 size on bigger boxes.
1365 highres= [KNL] Enable/disable high resolution timer mode.
1366 Valid parameters: "on", "off"
1370 See Documentation/isdn/README.HiSax.
1374 hpet= [X86-32,HPET] option to control HPET usage
1375 Format: { enable (default) | disable | force |
1377 disable: disable HPET and use PIT instead
1378 force: allow force enabled of undocumented chips (ICH4,
1380 verbose: show contents of HPET registers during setup
1382 hpet_mmap= [X86, HPET_MMAP] Allow userspace to mmap HPET
1383 registers. Default set by CONFIG_HPET_MMAP_DEFAULT.
1385 hugepages= [HW,X86-32,IA-64] HugeTLB pages to allocate at boot.
1386 hugepagesz= [HW,IA-64,PPC,X86-64] The size of the HugeTLB pages.
1387 On x86-64 and powerpc, this option can be specified
1388 multiple times interleaved with hugepages= to reserve
1389 huge pages of different sizes. Valid pages sizes on
1390 x86-64 are 2M (when the CPU supports "pse") and 1G
1391 (when the CPU supports the "pdpe1gb" cpuinfo flag).
1393 hvc_iucv= [S390] Number of z/VM IUCV hypervisor console (HVC)
1394 terminal devices. Valid values: 0..8
1395 hvc_iucv_allow= [S390] Comma-separated list of z/VM user IDs.
1396 If specified, z/VM IUCV HVC accepts connections
1397 from listed z/VM user IDs only.
1399 hwthread_map= [METAG] Comma-separated list of Linux cpu id to
1400 hardware thread id mappings.
1401 Format: <cpu>:<hwthread>
1404 Do not unregister boot console at start. This is only
1405 useful for debugging when something happens in the window
1406 between unregistering the boot console and initializing
1409 i2c_bus= [HW] Override the default board specific I2C bus speed
1410 or register an additional I2C bus that is not
1411 registered from board initialization code.
1415 i8042.debug [HW] Toggle i8042 debug mode
1416 i8042.unmask_kbd_data
1417 [HW] Enable printing of interrupt data from the KBD port
1418 (disabled by default, and as a pre-condition
1419 requires that i8042.debug=1 be enabled)
1420 i8042.direct [HW] Put keyboard port into non-translated mode
1421 i8042.dumbkbd [HW] Pretend that controller can only read data from
1422 keyboard and cannot control its state
1423 (Don't attempt to blink the leds)
1424 i8042.noaux [HW] Don't check for auxiliary (== mouse) port
1425 i8042.nokbd [HW] Don't check/create keyboard port
1426 i8042.noloop [HW] Disable the AUX Loopback command while probing
1428 i8042.nomux [HW] Don't check presence of an active multiplexing
1430 i8042.nopnp [HW] Don't use ACPIPnP / PnPBIOS to discover KBD/AUX
1432 i8042.notimeout [HW] Ignore timeout condition signalled by controller
1433 i8042.reset [HW] Reset the controller during init and cleanup
1434 i8042.unlock [HW] Unlock (ignore) the keylock
1435 i8042.kbdreset [HW] Reset device connected to KBD port
1439 i8k.ignore_dmi [HW] Continue probing hardware even if DMI data
1440 indicates that the driver is running on unsupported
1442 i8k.force [HW] Activate i8k driver even if SMM BIOS signature
1443 does not match list of supported models.
1445 [HW] Report power status in /proc/i8k
1446 (disabled by default)
1447 i8k.restricted [HW] Allow controlling fans only if SYS_ADMIN
1450 i915.invert_brightness=
1451 [DRM] Invert the sense of the variable that is used to
1452 set the brightness of the panel backlight. Normally a
1453 brightness value of 0 indicates backlight switched off,
1454 and the maximum of the brightness value sets the backlight
1455 to maximum brightness. If this parameter is set to 0
1456 (default) and the machine requires it, or this parameter
1457 is set to 1, a brightness value of 0 sets the backlight
1458 to maximum brightness, and the maximum of the brightness
1459 value switches the backlight off.
1460 -1 -- never invert brightness
1461 0 -- machine default
1462 1 -- force brightness inversion
1465 Format: <io>[,<membase>[,<icn_id>[,<icn_id2>]]]
1467 ide-core.nodma= [HW] (E)IDE subsystem
1468 Format: =0.0 to prevent dma on hda, =0.1 hdb =1.0 hdc
1469 .vlb_clock .pci_clock .noflush .nohpa .noprobe .nowerr
1470 .cdrom .chs .ignore_cable are additional options
1471 See Documentation/ide/ide.txt.
1473 ide-generic.probe-mask= [HW] (E)IDE subsystem
1475 Probe mask for legacy ISA IDE ports. Depending on
1476 platform up to 6 ports are supported, enabled by
1477 setting corresponding bits in the mask to 1. The
1478 default value is 0x0, which has a special meaning.
1479 On systems that have PCI, it triggers scanning the
1480 PCI bus for the first and the second port, which
1481 are then probed. On systems without PCI the value
1482 of 0x0 enables probing the two first ports as if it
1485 ide-pci-generic.all-generic-ide [HW] (E)IDE subsystem
1486 Claim all unknown PCI IDE storage controllers.
1489 Format: idle=poll, idle=halt, idle=nomwait
1490 Poll forces a polling idle loop that can slightly
1491 improve the performance of waking up a idle CPU, but
1492 will use a lot of power and make the system run hot.
1494 idle=halt: Halt is forced to be used for CPU idle.
1495 In such case C2/C3 won't be used again.
1496 idle=nomwait: Disable mwait for CPU C-states
1498 ieee754= [MIPS] Select IEEE Std 754 conformance mode
1499 Format: { strict | legacy | 2008 | relaxed }
1502 Choose which programs will be accepted for execution
1503 based on the IEEE 754 NaN encoding(s) supported by
1504 the FPU and the NaN encoding requested with the value
1505 of an ELF file header flag individually set by each
1506 binary. Hardware implementations are permitted to
1507 support either or both of the legacy and the 2008 NaN
1510 Available settings are as follows:
1511 strict accept binaries that request a NaN encoding
1512 supported by the FPU
1513 legacy only accept legacy-NaN binaries, if supported
1515 2008 only accept 2008-NaN binaries, if supported
1517 relaxed accept any binaries regardless of whether
1518 supported by the FPU
1520 The FPU emulator is always able to support both NaN
1521 encodings, so if no FPU hardware is present or it has
1522 been disabled with 'nofpu', then the settings of
1523 'legacy' and '2008' strap the emulator accordingly,
1524 'relaxed' straps the emulator for both legacy-NaN and
1525 2008-NaN, whereas 'strict' enables legacy-NaN only on
1526 legacy processors and both NaN encodings on MIPS32 or
1529 The setting for ABS.fmt/NEG.fmt instruction execution
1530 mode generally follows that for the NaN encoding,
1531 except where unsupported by hardware.
1533 ignore_loglevel [KNL]
1534 Ignore loglevel setting - this will print /all/
1535 kernel messages to the console. Useful for debugging.
1536 We also add it as printk module parameter, so users
1537 could change it dynamically, usually by
1538 /sys/module/printk/parameters/ignore_loglevel.
1541 Ignore RLIMIT_DATA setting for data mappings,
1542 print warning at first misuse. Can be changed via
1543 /sys/module/kernel/parameters/ignore_rlimit_data.
1545 ihash_entries= [KNL]
1546 Set number of hash buckets for inode cache.
1548 ima_appraise= [IMA] appraise integrity measurements
1549 Format: { "off" | "enforce" | "fix" | "log" }
1552 ima_appraise_tcb [IMA]
1553 The builtin appraise policy appraises all files
1557 Format: { md5 | sha1 | rmd160 | sha256 | sha384
1561 The list of supported hash algorithms is defined
1562 in crypto/hash_info.h.
1565 The builtin measurement policy to load during IMA
1566 setup. Specyfing "tcb" as the value, measures all
1567 programs exec'd, files mmap'd for exec, and all files
1568 opened with the read mode bit set by either the
1569 effective uid (euid=0) or uid=0.
1572 ima_tcb [IMA] Deprecated. Use ima_policy= instead.
1573 Load a policy which meets the needs of the Trusted
1574 Computing Base. This means IMA will measure all
1575 programs exec'd, files mmap'd for exec, and all files
1576 opened for read by uid=0.
1579 Select one of defined IMA measurements template formats.
1580 Formats: { "ima" | "ima-ng" | "ima-sig" }
1584 [IMA] Define a custom template format.
1585 Format: { "field1|...|fieldN" }
1587 ima.ahash_minsize= [IMA] Minimum file size for asynchronous hash usage
1588 Format: <min_file_size>
1589 Set the minimal file size for using asynchronous hash.
1590 If left unspecified, ahash usage is disabled.
1592 ahash performance varies for different data sizes on
1593 different crypto accelerators. This option can be used
1594 to achieve the best performance for a particular HW.
1596 ima.ahash_bufsize= [IMA] Asynchronous hash buffer size
1598 Set hashing buffer size. Default: 4k.
1600 ahash performance varies for different chunk sizes on
1601 different crypto accelerators. This option can be used
1602 to achieve best performance for particular HW.
1606 Run specified binary instead of /sbin/init as init
1609 initcall_debug [KNL] Trace initcalls as they are executed. Useful
1610 for working out where the kernel is dying during
1613 initcall_blacklist= [KNL] Do not execute a comma-separated list of
1614 initcall functions. Useful for debugging built-in
1615 modules and initcalls.
1617 initrd= [BOOT] Specify the location of the initial ramdisk
1619 inport.irq= [HW] Inport (ATI XL and Microsoft) busmouse driver
1622 int_pln_enable [x86] Enable power limit notification interrupt
1624 integrity_audit=[IMA]
1625 Format: { "0" | "1" }
1626 0 -- basic integrity auditing messages. (Default)
1627 1 -- additional integrity auditing messages.
1629 intel_iommu= [DMAR] Intel IOMMU driver (DMAR) option
1631 Enable intel iommu driver.
1633 Disable intel iommu driver.
1634 igfx_off [Default Off]
1635 By default, gfx is mapped as normal device. If a gfx
1636 device has a dedicated DMAR unit, the DMAR unit is
1637 bypassed by not enabling DMAR with this option. In
1638 this case, gfx device will use physical address for
1641 With this option iommu will not optimize to look
1642 for io virtual address below 32-bit forcing dual
1643 address cycle on pci bus for cards supporting greater
1644 than 32-bit addressing. The default is to look
1645 for translation below 32-bit and if not available
1646 then look in the higher range.
1647 strict [Default Off]
1648 With this option on every unmap_single operation will
1649 result in a hardware IOTLB flush operation as opposed
1650 to batching them for performance.
1651 sp_off [Default Off]
1652 By default, super page will be supported if Intel IOMMU
1653 has the capability. With this option, super page will
1655 ecs_off [Default Off]
1656 By default, extended context tables will be supported if
1657 the hardware advertises that it has support both for the
1658 extended tables themselves, and also PASID support. With
1659 this option set, extended tables will not be used even
1660 on hardware which claims to support them.
1662 intel_idle.max_cstate= [KNL,HW,ACPI,X86]
1663 0 disables intel_idle and fall back on acpi_idle.
1664 1 to 6 specify maximum depth of C-state.
1668 Do not enable intel_pstate as the default
1669 scaling driver for the supported processors
1671 Enable intel_pstate on systems that prohibit it by default
1672 in favor of acpi-cpufreq. Forcing the intel_pstate driver
1673 instead of acpi-cpufreq may disable platform features, such
1674 as thermal controls and power capping, that rely on ACPI
1675 P-States information being indicated to OSPM and therefore
1676 should be used with caution. This option does not work with
1677 processors that aren't supported by the intel_pstate driver
1678 or on platforms that use pcc-cpufreq instead of acpi-cpufreq.
1680 Do not enable hardware P state control (HWP)
1683 Only load intel_pstate on systems which support
1684 hardware P state control (HWP) if available.
1686 Enforce ACPI _PPC performance limits. If the Fixed ACPI
1687 Description Table, specifies preferred power management
1688 profile as "Enterprise Server" or "Performance Server",
1689 then this feature is turned on by default.
1691 intremap= [X86-64, Intel-IOMMU]
1692 on enable Interrupt Remapping (default)
1693 off disable Interrupt Remapping
1694 nosid disable Source ID checking
1696 BIOS x2APIC opt-out request will be ignored
1697 nopost disable Interrupt Posting
1699 iomem= Disable strict checking of access to MMIO memory
1700 strict regions from userspace.
1715 nobypass [PPC/POWERNV]
1716 Disable IOMMU bypass, using IOMMU for PCI devices.
1719 io7= [HW] IO7 for Marvel based alpha systems
1720 See comment before marvel_specify_io7 in
1721 arch/alpha/kernel/core_marvel.c.
1723 io_delay= [X86] I/O delay method
1725 Standard port 0x80 based delay
1727 Alternate port 0xed based delay (needed on some systems)
1729 Simple two microseconds delay
1734 See Documentation/filesystems/nfs/nfsroot.txt.
1736 irqaffinity= [SMP] Set the default irq affinity mask
1738 <cpu number>,...,<cpu number>
1740 <cpu number>-<cpu number>
1741 (must be a positive range in ascending order)
1743 <cpu number>,...,<cpu number>-<cpu number>
1746 When an interrupt is not handled search all handlers
1747 for it. Intended to get systems with badly broken
1751 When an interrupt is not handled search all handlers
1752 for it. Also check all handlers each timer
1753 interrupt. Intended to get systems with badly broken
1757 Format: <RDP>,<reset>,<pci_scan>,<verbosity>
1759 isolcpus= [KNL,SMP] Isolate CPUs from the general scheduler.
1761 <cpu number>,...,<cpu number>
1763 <cpu number>-<cpu number>
1764 (must be a positive range in ascending order)
1766 <cpu number>,...,<cpu number>-<cpu number>
1768 This option can be used to specify one or more CPUs
1769 to isolate from the general SMP balancing and scheduling
1770 algorithms. You can move a process onto or off an
1771 "isolated" CPU via the CPU affinity syscalls or cpuset.
1772 <cpu number> begins at 0 and the maximum value is
1773 "number of CPUs in system - 1".
1775 This option is the preferred way to isolate CPUs. The
1776 alternative -- manually setting the CPU mask of all
1777 tasks in the system -- can cause problems and
1778 suboptimal load balancer performance.
1782 ivrs_ioapic [HW,X86_64]
1783 Provide an override to the IOAPIC-ID<->DEVICE-ID
1784 mapping provided in the IVRS ACPI table. For
1785 example, to map IOAPIC-ID decimal 10 to
1786 PCI device 00:14.0 write the parameter as:
1787 ivrs_ioapic[10]=00:14.0
1789 ivrs_hpet [HW,X86_64]
1790 Provide an override to the HPET-ID<->DEVICE-ID
1791 mapping provided in the IVRS ACPI table. For
1792 example, to map HPET-ID decimal 0 to
1793 PCI device 00:14.0 write the parameter as:
1794 ivrs_hpet[0]=00:14.0
1796 ivrs_acpihid [HW,X86_64]
1797 Provide an override to the ACPI-HID:UID<->DEVICE-ID
1798 mapping provided in the IVRS ACPI table. For
1799 example, to map UART-HID:UID AMD0020:0 to
1800 PCI device 00:14.5 write the parameter as:
1801 ivrs_acpihid[00:14.5]=AMD0020:0
1803 js= [HW,JOY] Analog joystick
1804 See Documentation/input/joystick.txt.
1807 When CONFIG_RANDOMIZE_BASE is set, this disables
1808 kernel and module base offset ASLR (Address Space
1809 Layout Randomization).
1813 kernelcore= [KNL,X86,IA-64,PPC]
1814 Format: nn[KMGTPE] | "mirror"
1816 specifies the amount of memory usable by the kernel
1817 for non-movable allocations. The requested amount is
1818 spread evenly throughout all nodes in the system. The
1819 remaining memory in each node is used for Movable
1820 pages. In the event, a node is too small to have both
1821 kernelcore and Movable pages, kernelcore pages will
1822 take priority and other nodes will have a larger number
1823 of Movable pages. The Movable zone is used for the
1824 allocation of pages that may be reclaimed or moved
1825 by the page migration subsystem. This means that
1826 HugeTLB pages may not be allocated from this zone.
1827 Note that allocations like PTEs-from-HighMem still
1828 use the HighMem zone if it exists, and the Normal
1829 zone if it does not.
1831 Instead of specifying the amount of memory (nn[KMGTPE]),
1832 you can specify "mirror" option. In case "mirror"
1833 option is specified, mirrored (reliable) memory is used
1834 for non-movable allocations and remaining memory is used
1835 for Movable pages. nn[KMGTPE] and "mirror" are exclusive,
1836 so you can NOT specify nn[KMGTPE] and "mirror" at the same
1839 kgdbdbgp= [KGDB,HW] kgdb over EHCI usb debug port.
1840 Format: <Controller#>[,poll interval]
1841 The controller # is the number of the ehci usb debug
1842 port as it is probed via PCI. The poll interval is
1843 optional and is the number seconds in between
1844 each poll cycle to the debug port in case you need
1845 the functionality for interrupting the kernel with
1846 gdb or control-c on the dbgp connection. When
1847 not using this parameter you use sysrq-g to break into
1848 the kernel debugger.
1850 kgdboc= [KGDB,HW] kgdb over consoles.
1851 Requires a tty driver that supports console polling,
1852 or a supported polling keyboard driver (non-usb).
1853 Serial only format: <serial_device>[,baud]
1854 keyboard only format: kbd
1855 keyboard and serial format: kbd,<serial_device>[,baud]
1856 Optional Kernel mode setting:
1857 kms, kbd format: kms,kbd
1858 kms, kbd and serial format: kms,kbd,<ser_dev>[,baud]
1860 kgdbwait [KGDB] Stop kernel execution and enter the
1861 kernel debugger at the earliest opportunity.
1863 kmac= [MIPS] korina ethernet MAC address.
1864 Configure the RouterBoard 532 series on-chip
1865 Ethernet adapter MAC address.
1867 kmemleak= [KNL] Boot-time kmemleak enable/disable
1868 Valid arguments: on, off
1870 Built with CONFIG_DEBUG_KMEMLEAK_DEFAULT_OFF=y,
1873 kmemcheck= [X86] Boot-time kmemcheck enable/disable/one-shot mode
1874 Valid arguments: 0, 1, 2
1875 kmemcheck=0 (disabled)
1876 kmemcheck=1 (enabled)
1877 kmemcheck=2 (one-shot mode)
1878 Default: 2 (one-shot mode)
1880 kstack=N [X86] Print N words from the kernel stack
1883 kvm.ignore_msrs=[KVM] Ignore guest accesses to unhandled MSRs.
1884 Default is 0 (don't ignore, but inject #GP)
1886 kvm.mmu_audit= [KVM] This is a R/W parameter which allows audit
1890 kvm-amd.nested= [KVM,AMD] Allow nested virtualization in KVM/SVM.
1891 Default is 1 (enabled)
1893 kvm-amd.npt= [KVM,AMD] Disable nested paging (virtualized MMU)
1895 Default is 1 (enabled) if in 64-bit or 32-bit PAE mode.
1897 kvm-intel.ept= [KVM,Intel] Disable extended page tables
1898 (virtualized MMU) support on capable Intel chips.
1899 Default is 1 (enabled)
1901 kvm-intel.emulate_invalid_guest_state=
1902 [KVM,Intel] Enable emulation of invalid guest states
1903 Default is 0 (disabled)
1905 kvm-intel.flexpriority=
1906 [KVM,Intel] Disable FlexPriority feature (TPR shadow).
1907 Default is 1 (enabled)
1910 [KVM,Intel] Enable VMX nesting (nVMX).
1911 Default is 0 (disabled)
1913 kvm-intel.unrestricted_guest=
1914 [KVM,Intel] Disable unrestricted guest feature
1915 (virtualized real and unpaged mode) on capable
1916 Intel chips. Default is 1 (enabled)
1918 kvm-intel.vpid= [KVM,Intel] Disable Virtual Processor Identification
1919 feature (tagged TLBs) on capable Intel chips.
1920 Default is 1 (enabled)
1926 lapic [X86-32,APIC] Enable the local APIC even if BIOS
1929 lapic= [x86,APIC] "notscdeadline" Do not use TSC deadline
1930 value for LAPIC timer one-shot implementation. Default
1931 back to the programmable timer unit in the LAPIC.
1933 lapic_timer_c2_ok [X86,APIC] trust the local apic timer
1936 libata.dma= [LIBATA] DMA control
1937 libata.dma=0 Disable all PATA and SATA DMA
1938 libata.dma=1 PATA and SATA Disk DMA only
1939 libata.dma=2 ATAPI (CDROM) DMA only
1940 libata.dma=4 Compact Flash DMA only
1941 Combinations also work, so libata.dma=3 enables DMA
1942 for disks and CDROMs, but not CFs.
1944 libata.ignore_hpa= [LIBATA] Ignore HPA limit
1945 libata.ignore_hpa=0 keep BIOS limits (default)
1946 libata.ignore_hpa=1 ignore limits, using full disk
1948 libata.noacpi [LIBATA] Disables use of ACPI in libata suspend/resume
1952 libata.force= [LIBATA] Force configurations. The format is comma
1953 separated list of "[ID:]VAL" where ID is
1954 PORT[.DEVICE]. PORT and DEVICE are decimal numbers
1955 matching port, link or device. Basically, it matches
1956 the ATA ID string printed on console by libata. If
1957 the whole ID part is omitted, the last PORT and DEVICE
1958 values are used. If ID hasn't been specified yet, the
1959 configuration applies to all ports, links and devices.
1961 If only DEVICE is omitted, the parameter applies to
1962 the port and all links and devices behind it. DEVICE
1963 number of 0 either selects the first device or the
1964 first fan-out link behind PMP device. It does not
1965 select the host link. DEVICE number of 15 selects the
1966 host link and device attached to it.
1968 The VAL specifies the configuration to force. As long
1969 as there's no ambiguity shortcut notation is allowed.
1970 For example, both 1.5 and 1.5G would work for 1.5Gbps.
1971 The following configurations can be forced.
1973 * Cable type: 40c, 80c, short40c, unk, ign or sata.
1974 Any ID with matching PORT is used.
1976 * SATA link speed limit: 1.5Gbps or 3.0Gbps.
1978 * Transfer mode: pio[0-7], mwdma[0-4] and udma[0-7].
1979 udma[/][16,25,33,44,66,100,133] notation is also
1982 * [no]ncq: Turn on or off NCQ.
1984 * [no]ncqtrim: Turn off queued DSM TRIM.
1986 * nohrst, nosrst, norst: suppress hard, soft
1989 * rstonce: only attempt one reset during
1990 hot-unplug link recovery
1992 * dump_id: dump IDENTIFY data.
1994 * atapi_dmadir: Enable ATAPI DMADIR bridge support
1996 * disable: Disable this device.
1998 If there are multiple matching configurations changing
1999 the same attribute, the last one is used.
2001 memblock=debug [KNL] Enable memblock debug messages.
2003 load_ramdisk= [RAM] List of ramdisks to load from floppy
2004 See Documentation/blockdev/ramdisk.txt.
2006 lockd.nlm_grace_period=P [NFS] Assign grace period.
2009 lockd.nlm_tcpport=N [NFS] Assign TCP port.
2012 lockd.nlm_timeout=T [NFS] Assign timeout value.
2015 lockd.nlm_udpport=M [NFS] Assign UDP port.
2018 locktorture.nreaders_stress= [KNL]
2019 Set the number of locking read-acquisition kthreads.
2020 Defaults to being automatically set based on the
2021 number of online CPUs.
2023 locktorture.nwriters_stress= [KNL]
2024 Set the number of locking write-acquisition kthreads.
2026 locktorture.onoff_holdoff= [KNL]
2027 Set time (s) after boot for CPU-hotplug testing.
2029 locktorture.onoff_interval= [KNL]
2030 Set time (s) between CPU-hotplug operations, or
2031 zero to disable CPU-hotplug testing.
2033 locktorture.shuffle_interval= [KNL]
2034 Set task-shuffle interval (jiffies). Shuffling
2035 tasks allows some CPUs to go into dyntick-idle
2036 mode during the locktorture test.
2038 locktorture.shutdown_secs= [KNL]
2039 Set time (s) after boot system shutdown. This
2040 is useful for hands-off automated testing.
2042 locktorture.stat_interval= [KNL]
2043 Time (s) between statistics printk()s.
2045 locktorture.stutter= [KNL]
2046 Time (s) to stutter testing, for example,
2047 specifying five seconds causes the test to run for
2048 five seconds, wait for five seconds, and so on.
2049 This tests the locking primitive's ability to
2050 transition abruptly to and from idle.
2052 locktorture.torture_runnable= [BOOT]
2053 Start locktorture running at boot time.
2055 locktorture.torture_type= [KNL]
2056 Specify the locking implementation to test.
2058 locktorture.verbose= [KNL]
2059 Enable additional printk() statements.
2061 logibm.irq= [HW,MOUSE] Logitech Bus Mouse Driver
2064 loglevel= All Kernel Messages with a loglevel smaller than the
2065 console loglevel will be printed to the console. It can
2066 also be changed with klogd or other programs. The
2067 loglevels are defined as follows:
2069 0 (KERN_EMERG) system is unusable
2070 1 (KERN_ALERT) action must be taken immediately
2071 2 (KERN_CRIT) critical conditions
2072 3 (KERN_ERR) error conditions
2073 4 (KERN_WARNING) warning conditions
2074 5 (KERN_NOTICE) normal but significant condition
2075 6 (KERN_INFO) informational
2076 7 (KERN_DEBUG) debug-level messages
2078 log_buf_len=n[KMG] Sets the size of the printk ring buffer,
2079 in bytes. n must be a power of two and greater
2080 than the minimal size. The minimal size is defined
2081 by LOG_BUF_SHIFT kernel config parameter. There is
2082 also CONFIG_LOG_CPU_MAX_BUF_SHIFT config parameter
2083 that allows to increase the default size depending on
2084 the number of CPUs. See init/Kconfig for more details.
2086 logo.nologo [FB] Disables display of the built-in Linux logo.
2087 This may be used to provide more screen space for
2088 kernel log messages and is useful when debugging
2089 kernel boot problems.
2091 lp=0 [LP] Specify parallel ports to use, e.g,
2092 lp=port[,port...] lp=none,parport0 (lp0 not configured, lp1 uses
2093 lp=reset first parallel port). 'lp=0' disables the
2094 lp=auto printer driver. 'lp=reset' (which can be
2095 specified in addition to the ports) causes
2096 attached printers to be reset. Using
2097 lp=port1,port2,... specifies the parallel ports
2098 to associate lp devices with, starting with
2099 lp0. A port specification may be 'none' to skip
2100 that lp device, or a parport name such as
2101 'parport0'. Specifying 'lp=auto' instead of a
2102 port specification list means that device IDs
2103 from each port should be examined, to see if
2104 an IEEE 1284-compliant printer is attached; if
2105 so, the driver will manage that printer.
2106 See also header of drivers/char/lp.c.
2109 Sets loops_per_jiffy to given constant, thus avoiding
2110 time-consuming boot-time autodetection (up to 250 ms per
2111 CPU). 0 enables autodetection (default). To determine
2112 the correct value for your kernel, boot with normal
2113 autodetection and see what value is printed. Note that
2114 on SMP systems the preset will be applied to all CPUs,
2115 which is likely to cause problems if your CPUs need
2116 significantly divergent settings. An incorrect value
2117 will cause delays in the kernel to be wrong, leading to
2118 unpredictable I/O errors and other breakage. Although
2119 unlikely, in the extreme case this might damage your
2123 Format: <io>,<irq>,<dma>
2125 machvec= [IA-64] Force the use of a particular machine-vector
2126 (machvec) in a generic kernel.
2127 Example: machvec=hpzx1_swiotlb
2129 machtype= [Loongson] Share the same kernel image file between different
2131 Example: machtype=lemote-yeeloong-2f-7inch
2133 max_addr=nn[KMG] [KNL,BOOT,ia64] All physical memory greater
2134 than or equal to this physical address is ignored.
2136 maxcpus= [SMP] Maximum number of processors that an SMP kernel
2137 should make use of. maxcpus=n : n >= 0 limits the
2138 kernel to using 'n' processors. n=0 is a special case,
2139 it is equivalent to "nosmp", which also disables
2142 max_loop= [LOOP] The number of loop block devices that get
2143 (loop.max_loop) unconditionally pre-created at init time. The default
2144 number is configured by BLK_DEV_LOOP_MIN_COUNT. Instead
2145 of statically allocating a predefined number, loop
2146 devices can be requested on-demand with the
2147 /dev/loop-control interface.
2149 mce [X86-32] Machine Check Exception
2151 mce=option [X86-64] See Documentation/x86/x86_64/boot-options.txt
2153 md= [HW] RAID subsystems devices and level
2154 See Documentation/md.txt.
2157 Format: <first>,<last>
2158 Specifies range of consoles to be captured by the MDA.
2160 mem=nn[KMG] [KNL,BOOT] Force usage of a specific amount of memory
2161 Amount of memory to be used when the kernel is not able
2162 to see the whole system memory or for test.
2163 [X86] Work as limiting max address. Use together
2164 with memmap= to avoid physical address space collisions.
2165 Without memmap= PCI devices could be placed at addresses
2166 belonging to unused RAM.
2168 mem=nopentium [BUGS=X86-32] Disable usage of 4MB pages for kernel
2172 [KNL,SH] Allow user to override the default size for
2173 per-device physically contiguous DMA buffers.
2175 memhp_default_state=online/offline
2176 [KNL] Set the initial state for the memory hotplug
2177 onlining policy. If not specified, the default value is
2178 set according to the
2179 CONFIG_MEMORY_HOTPLUG_DEFAULT_ONLINE kernel config
2181 See Documentation/memory-hotplug.txt.
2183 memmap=exactmap [KNL,X86] Enable setting of an exact
2184 E820 memory map, as specified by the user.
2185 Such memmap=exactmap lines can be constructed based on
2186 BIOS output or other requirements. See the memmap=nn@ss
2189 memmap=nn[KMG]@ss[KMG]
2190 [KNL] Force usage of a specific region of memory.
2191 Region of memory to be used is from ss to ss+nn.
2193 memmap=nn[KMG]#ss[KMG]
2194 [KNL,ACPI] Mark specific memory as ACPI data.
2195 Region of memory to be marked is from ss to ss+nn.
2197 memmap=nn[KMG]$ss[KMG]
2198 [KNL,ACPI] Mark specific memory as reserved.
2199 Region of memory to be reserved is from ss to ss+nn.
2200 Example: Exclude memory from 0x18690000-0x1869ffff
2201 memmap=64K$0x18690000
2203 memmap=0x10000$0x18690000
2205 memmap=nn[KMG]!ss[KMG]
2206 [KNL,X86] Mark specific memory as protected.
2207 Region of memory to be used, from ss to ss+nn.
2208 The memory region may be marked as e820 type 12 (0xc)
2209 and is NVDIMM or ADR memory.
2211 memory_corruption_check=0/1 [X86]
2212 Some BIOSes seem to corrupt the first 64k of
2213 memory when doing things like suspend/resume.
2214 Setting this option will scan the memory
2215 looking for corruption. Enabling this will
2216 both detect corruption and prevent the kernel
2217 from using the memory being corrupted.
2218 However, its intended as a diagnostic tool; if
2219 repeatable BIOS-originated corruption always
2220 affects the same memory, you can use memmap=
2221 to prevent the kernel from using that memory.
2223 memory_corruption_check_size=size [X86]
2224 By default it checks for corruption in the low
2225 64k, making this memory unavailable for normal
2226 use. Use this parameter to scan for
2227 corruption in more or less memory.
2229 memory_corruption_check_period=seconds [X86]
2230 By default it checks for corruption every 60
2231 seconds. Use this parameter to check at some
2232 other rate. 0 disables periodic checking.
2234 memtest= [KNL,X86,ARM] Enable memtest
2236 default : 0 <disable>
2237 Specifies the number of memtest passes to be
2238 performed. Each pass selects another test
2239 pattern from a given set of patterns. Memtest
2240 fills the memory with this pattern, validates
2241 memory contents and reserves bad memory
2242 regions that are detected.
2244 meye.*= [HW] Set MotionEye Camera parameters
2245 See Documentation/video4linux/meye.txt.
2247 mfgpt_irq= [IA-32] Specify the IRQ to use for the
2248 Multi-Function General Purpose Timers on AMD Geode
2251 mfgptfix [X86-32] Fix MFGPT timers on AMD Geode platforms when
2252 the BIOS has incorrectly applied a workaround. TinyBIOS
2253 version 0.98 is known to be affected, 0.99 fixes the
2254 problem by letting the user disable the workaround.
2258 min_addr=nn[KMG] [KNL,BOOT,ia64] All physical memory below this
2259 physical address is ignored.
2261 mini2440= [ARM,HW,KNL]
2262 Format:[0..2][b][c][t]
2264 MINI2440 configuration specification:
2265 0 - The attached screen is the 3.5" TFT
2266 1 - The attached screen is the 7" TFT
2267 2 - The VGA Shield is attached (1024x768)
2268 Leaving out the screen size parameter will not load
2269 the TFT driver, and the framebuffer will be left
2271 b - Enable backlight. The TFT backlight pin will be
2272 linked to the kernel VESA blanking code and a GPIO
2273 LED. This parameter is not necessary when using the
2275 c - Enable the s3c camera interface.
2276 t - Reserved for enabling touchscreen support. The
2277 touchscreen support is not enabled in the mainstream
2278 kernel as of 2.6.30, a preliminary port can be found
2279 in the "bleeding edge" mini2440 support kernel at
2280 http://repo.or.cz/w/linux-2.6/mini2440.git
2283 [KNL] When CONFIG_DEBUG_MEMORY_INIT is set, this
2284 parameter allows control of the logging verbosity for
2285 the additional memory initialisation checks. A value
2286 of 0 disables mminit logging and a level of 4 will
2287 log everything. Information is printed at KERN_DEBUG
2288 so loglevel=8 may also need to be specified.
2291 [KNL] When CONFIG_MODULE_SIG is set, this means that
2292 modules without (valid) signatures will fail to load.
2293 Note that if CONFIG_MODULE_SIG_FORCE is set, that
2294 is always true, so this option does nothing.
2297 [MOUSE] Maximum time between finger touching and
2298 leaving touchpad surface for touch to be considered
2299 a tap and be reported as a left button click (for
2300 touchpads working in absolute mode only).
2302 mousedev.xres= [MOUSE] Horizontal screen resolution, used for devices
2303 reporting absolute coordinates, such as tablets
2304 mousedev.yres= [MOUSE] Vertical screen resolution, used for devices
2305 reporting absolute coordinates, such as tablets
2307 movablecore=nn[KMG] [KNL,X86,IA-64,PPC] This parameter
2308 is similar to kernelcore except it specifies the
2309 amount of memory used for migratable allocations.
2310 If both kernelcore and movablecore is specified,
2311 then kernelcore will be at *least* the specified
2312 value but may be more. If movablecore on its own
2313 is specified, the administrator must be careful
2314 that the amount of memory usable for all allocations
2317 movable_node [KNL,X86] Boot-time switch to enable the effects
2318 of CONFIG_MOVABLE_NODE=y. See mm/Kconfig for details.
2320 MTD_Partition= [MTD]
2321 Format: <name>,<region-number>,<size>,<offset>
2323 MTD_Region= [MTD] Format:
2324 <name>,<region-number>[,<base>,<size>,<buswidth>,<altbuswidth>]
2327 See drivers/mtd/cmdlinepart.c.
2329 multitce=off [PPC] This parameter disables the use of the pSeries
2330 firmware feature for updating multiple TCE entries
2333 onenand.bdry= [HW,MTD] Flex-OneNAND Boundary Configuration
2335 Format: [die0_boundary][,die0_lock][,die1_boundary][,die1_lock]
2337 boundary - index of last SLC block on Flex-OneNAND.
2338 The remaining blocks are configured as MLC blocks.
2339 lock - Configure if Flex-OneNAND boundary should be locked.
2340 Once locked, the boundary cannot be changed.
2341 1 indicates lock status, 0 indicates unlock status.
2344 ARM/S3C2412 JIVE boot control
2346 See arch/arm/mach-s3c2412/mach-jive.c
2348 mtouchusb.raw_coordinates=
2349 [HW] Make the MicroTouch USB driver use raw coordinates
2350 ('y', default) or cooked coordinates ('n')
2352 mtrr_chunk_size=nn[KMG] [X86]
2353 used for mtrr cleanup. It is largest continuous chunk
2354 that could hold holes aka. UC entries.
2356 mtrr_gran_size=nn[KMG] [X86]
2357 Used for mtrr cleanup. It is granularity of mtrr block.
2359 Large value could prevent small alignment from
2362 mtrr_spare_reg_nr=n [X86]
2364 Range: 0,7 : spare reg number
2366 Used for mtrr cleanup. It is spare mtrr entries number.
2367 Set to 2 or more if your graphical card needs more.
2369 n2= [NET] SDL Inc. RISCom/N2 synchronous serial card
2371 netdev= [NET] Network devices parameters
2372 Format: <irq>,<io>,<mem_start>,<mem_end>,<name>
2373 Note that mem_start is often overloaded to mean
2374 something different and driver-specific.
2375 This usage is only documented in each driver source
2379 [NETFILTER] Enable connection tracking flow accounting
2380 0 to disable accounting
2381 1 to enable accounting
2384 nfsaddrs= [NFS] Deprecated. Use ip= instead.
2385 See Documentation/filesystems/nfs/nfsroot.txt.
2387 nfsroot= [NFS] nfs root filesystem for disk-less boxes.
2388 See Documentation/filesystems/nfs/nfsroot.txt.
2390 nfsrootdebug [NFS] enable nfsroot debugging messages.
2391 See Documentation/filesystems/nfs/nfsroot.txt.
2393 nfs.callback_tcpport=
2394 [NFS] set the TCP port on which the NFSv4 callback
2395 channel should listen.
2398 [NFS] sets the pathname to the program which is used
2399 to update the NFS client cache entries.
2401 nfs.cache_getent_timeout=
2402 [NFS] sets the timeout after which an attempt to
2403 update a cache entry is deemed to have failed.
2405 nfs.idmap_cache_timeout=
2406 [NFS] set the maximum lifetime for idmapper cache
2410 [NFS] enable 64-bit inode numbers.
2411 If zero, the NFS client will fake up a 32-bit inode
2412 number for the readdir() and stat() syscalls instead
2413 of returning the full 64-bit number.
2414 The default is to return 64-bit inode numbers.
2416 nfs.max_session_slots=
2417 [NFSv4.1] Sets the maximum number of session slots
2418 the client will attempt to negotiate with the server.
2419 This limits the number of simultaneous RPC requests
2420 that the client can send to the NFSv4.1 server.
2421 Note that there is little point in setting this
2422 value higher than the max_tcp_slot_table_limit.
2424 nfs.nfs4_disable_idmapping=
2425 [NFSv4] When set to the default of '1', this option
2426 ensures that both the RPC level authentication
2427 scheme and the NFS level operations agree to use
2428 numeric uids/gids if the mount is using the
2429 'sec=sys' security flavour. In effect it is
2430 disabling idmapping, which can make migration from
2431 legacy NFSv2/v3 systems to NFSv4 easier.
2432 Servers that do not support this mode of operation
2433 will be autodetected by the client, and it will fall
2434 back to using the idmapper.
2435 To turn off this behaviour, set the value to '0'.
2437 [NFS4] Specify an additional fixed unique ident-
2438 ification string that NFSv4 clients can insert into
2439 their nfs_client_id4 string. This is typically a
2440 UUID that is generated at system install time.
2442 nfs.send_implementation_id =
2443 [NFSv4.1] Send client implementation identification
2444 information in exchange_id requests.
2445 If zero, no implementation identification information
2447 The default is to send the implementation identification
2450 nfs.recover_lost_locks =
2451 [NFSv4] Attempt to recover locks that were lost due
2452 to a lease timeout on the server. Please note that
2453 doing this risks data corruption, since there are
2454 no guarantees that the file will remain unchanged
2455 after the locks are lost.
2456 If you want to enable the kernel legacy behaviour of
2457 attempting to recover these locks, then set this
2459 The default parameter value of '0' causes the kernel
2460 not to attempt recovery of lost locks.
2462 nfs4.layoutstats_timer =
2463 [NFSv4.2] Change the rate at which the kernel sends
2464 layoutstats to the pNFS metadata server.
2466 Setting this to value to 0 causes the kernel to use
2467 whatever value is the default set by the layout
2468 driver. A non-zero value sets the minimum interval
2469 in seconds between layoutstats transmissions.
2471 nfsd.nfs4_disable_idmapping=
2472 [NFSv4] When set to the default of '1', the NFSv4
2473 server will return only numeric uids and gids to
2474 clients using auth_sys, and will accept numeric uids
2475 and gids from such clients. This is intended to ease
2476 migration from NFSv2/v3.
2478 objlayoutdriver.osd_login_prog=
2479 [NFS] [OBJLAYOUT] sets the pathname to the program which
2480 is used to automatically discover and login into new
2481 osd-targets. Please see:
2482 Documentation/filesystems/pnfs.txt for more explanations
2484 nmi_debug= [KNL,AVR32,SH] Specify one or more actions to take
2485 when a NMI is triggered.
2486 Format: [state][,regs][,debounce][,die]
2488 nmi_watchdog= [KNL,BUGS=X86] Debugging features for SMP kernels
2489 Format: [panic,][nopanic,][num]
2491 0 - turn hardlockup detector in nmi_watchdog off
2492 1 - turn hardlockup detector in nmi_watchdog on
2493 When panic is specified, panic when an NMI watchdog
2494 timeout occurs (or 'nopanic' to override the opposite
2495 default). To disable both hard and soft lockup detectors,
2496 please see 'nowatchdog'.
2497 This is useful when you use a panic=... timeout and
2498 need the box quickly up again.
2500 netpoll.carrier_timeout=
2501 [NET] Specifies amount of time (in seconds) that
2502 netpoll should wait for a carrier. By default netpoll
2505 no387 [BUGS=X86-32] Tells the kernel to use the 387 maths
2506 emulation library even if a 387 maths coprocessor
2510 [HW] Never suspend the console
2511 Disable suspending of consoles during suspend and
2512 hibernate operations. Once disabled, debugging
2513 messages can reach various consoles while the rest
2514 of the system is being put to sleep (ie, while
2515 debugging driver suspend/resume hooks). This may
2516 not work reliably with all consoles, but is known
2517 to work with serial and VGA consoles.
2518 To facilitate more flexible debugging, we also add
2519 console_suspend, a printk module parameter to control
2520 it. Users could use console_suspend (usually
2521 /sys/module/printk/parameters/console_suspend) to
2522 turn on/off it dynamically.
2524 noaliencache [MM, NUMA, SLAB] Disables the allocation of alien
2525 caches in the slab allocator. Saves per-node memory,
2526 but will impact performance.
2530 noapic [SMP,APIC] Tells the kernel to not make use of any
2531 IOAPICs that may be present in the system.
2533 noautogroup Disable scheduler automatic task group creation.
2535 nobats [PPC] Do not use BATs for mapping kernel lowmem
2536 on "Classic" PPC cores.
2540 noclflush [BUGS=X86] Don't use the CLFLUSH instruction
2542 nodelayacct [KNL] Disable per-task delay accounting
2544 nodisconnect [HW,SCSI,M68K] Disables SCSI disconnects.
2546 nodsp [SH] Disable hardware DSP at boot time.
2548 noefi Disable EFI runtime services support.
2553 On X86-32 available only on PAE configured kernels.
2554 noexec=on: enable non-executable mappings (default)
2555 noexec=off: disable non-executable mappings
2558 Disable SMAP (Supervisor Mode Access Prevention)
2559 even if it is supported by processor.
2562 Disable SMEP (Supervisor Mode Execution Prevention)
2563 even if it is supported by processor.
2566 This affects only 32-bit executables.
2567 noexec32=on: enable non-executable mappings (default)
2568 read doesn't imply executable mappings
2569 noexec32=off: disable non-executable mappings
2570 read implies executable mappings
2572 nofpu [MIPS,SH] Disable hardware FPU at boot time.
2574 nofxsr [BUGS=X86-32] Disables x86 floating point extended
2575 register save and restore. The kernel will only save
2576 legacy floating-point registers on task switch.
2578 nohugeiomap [KNL,x86] Disable kernel huge I/O mappings.
2580 nosmt [KNL,S390] Disable symmetric multithreading (SMT).
2581 Equivalent to smt=1.
2583 noxsave [BUGS=X86] Disables x86 extended register state save
2584 and restore using xsave. The kernel will fallback to
2585 enabling legacy floating-point and sse state.
2587 noxsaveopt [X86] Disables xsaveopt used in saving x86 extended
2588 register states. The kernel will fall back to use
2589 xsave to save the states. By using this parameter,
2590 performance of saving the states is degraded because
2591 xsave doesn't support modified optimization while
2592 xsaveopt supports it on xsaveopt enabled systems.
2594 noxsaves [X86] Disables xsaves and xrstors used in saving and
2595 restoring x86 extended register state in compacted
2596 form of xsave area. The kernel will fall back to use
2597 xsaveopt and xrstor to save and restore the states
2598 in standard form of xsave area. By using this
2599 parameter, xsave area per process might occupy more
2600 memory on xsaves enabled systems.
2602 nohlt [BUGS=ARM,SH] Tells the kernel that the sleep(SH) or
2603 wfi(ARM) instruction doesn't work correctly and not to
2604 use it. This is also useful when using JTAG debugger.
2606 no_file_caps Tells the kernel not to honor file capabilities. The
2607 only way then for a file to be executed with privilege
2608 is to be setuid root or executed by root.
2610 nohalt [IA-64] Tells the kernel not to use the power saving
2611 function PAL_HALT_LIGHT when idle. This increases
2612 power-consumption. On the positive side, it reduces
2613 interrupt wake-up latency, which may improve performance
2614 in certain environments such as networked servers or
2617 nohibernate [HIBERNATION] Disable hibernation and resume.
2619 nohz= [KNL] Boottime enable/disable dynamic ticks
2620 Valid arguments: on, off
2623 nohz_full= [KNL,BOOT]
2624 In kernels built with CONFIG_NO_HZ_FULL=y, set
2625 the specified list of CPUs whose tick will be stopped
2626 whenever possible. The boot CPU will be forced outside
2627 the range to maintain the timekeeping.
2628 The CPUs in this range must also be included in the
2631 noiotrap [SH] Disables trapped I/O port accesses.
2633 noirqdebug [X86-32] Disables the code which attempts to detect and
2634 disable unhandled interrupt sources.
2636 no_timer_check [X86,APIC] Disables the code which tests for
2637 broken timer IRQ sources.
2639 noisapnp [ISAPNP] Disables ISA PnP code.
2641 noinitrd [RAM] Tells the kernel not to load any configured
2644 nointremap [X86-64, Intel-IOMMU] Do not enable interrupt
2646 [Deprecated - use intremap=off]
2650 noinvpcid [X86] Disable the INVPCID cpu feature.
2652 nojitter [IA-64] Disables jitter checking for ITC timers.
2654 no-kvmclock [X86,KVM] Disable paravirtualized KVM clock driver
2656 no-kvmapf [X86,KVM] Disable paravirtualized asynchronous page
2659 no-steal-acc [X86,KVM] Disable paravirtualized steal time accounting.
2660 steal time is computed, but won't influence scheduler
2663 nolapic [X86-32,APIC] Do not enable or use the local APIC.
2665 nolapic_timer [X86-32,APIC] Do not use the local APIC timer.
2667 noltlbs [PPC] Do not use large page/tlb entries for kernel
2668 lowmem mapping on PPC40x and PPC8xx
2670 nomca [IA-64] Disable machine check abort handling
2672 nomce [X86-32] Disable Machine Check Exception
2674 nomfgpt [X86-32] Disable Multi-Function General Purpose
2675 Timer usage (for AMD Geode machines).
2677 nonmi_ipi [X86] Disable using NMI IPIs during panic/reboot to
2678 shutdown the other cpus. Instead use the REBOOT_VECTOR
2681 nomodule Disable module load
2683 nopat [X86] Disable PAT (page attribute table extension of
2684 pagetables) support.
2686 norandmaps Don't use address space randomization. Equivalent to
2687 echo 0 > /proc/sys/kernel/randomize_va_space
2689 noreplace-paravirt [X86,IA-64,PV_OPS] Don't patch paravirt_ops
2691 noreplace-smp [X86-32,SMP] Don't replace SMP instructions
2692 with UP alternatives
2694 nordrand [X86] Disable kernel use of the RDRAND and
2695 RDSEED instructions even if they are supported
2696 by the processor. RDRAND and RDSEED are still
2697 available to user space applications.
2699 noresume [SWSUSP] Disables resume and restores original swap
2702 no-scroll [VGA] Disables scrollback.
2703 This is required for the Braillex ib80-piezo Braille
2704 reader made by F.H. Papenmeier (Germany).
2708 nosep [BUGS=X86-32] Disables x86 SYSENTER/SYSEXIT support.
2710 nosmp [SMP] Tells an SMP kernel to act as a UP kernel,
2711 and disable the IO APIC. legacy for "maxcpus=0".
2713 nosoftlockup [KNL] Disable the soft-lockup detector.
2715 nosync [HW,M68K] Disables sync negotiation for all devices.
2717 notsc [BUGS=X86-32] Disable Time Stamp Counter
2719 nowatchdog [KNL] Disable both lockup detectors, i.e.
2720 soft-lockup and NMI watchdog (hard-lockup).
2724 nox2apic [X86-64,APIC] Do not enable x2APIC mode.
2726 cpu0_hotplug [X86] Turn on CPU0 hotplug feature when
2727 CONFIG_BOOTPARAM_HOTPLUG_CPU0 is off.
2728 Some features depend on CPU0. Known dependencies are:
2729 1. Resume from suspend/hibernate depends on CPU0.
2730 Suspend/hibernate will fail if CPU0 is offline and you
2731 need to online CPU0 before suspend/hibernate.
2732 2. PIC interrupts also depend on CPU0. CPU0 can't be
2733 removed if a PIC interrupt is detected.
2734 It's said poweroff/reboot may depend on CPU0 on some
2735 machines although I haven't seen such issues so far
2736 after CPU0 is offline on a few tested machines.
2737 If the dependencies are under your control, you can
2738 turn on cpu0_hotplug.
2740 nptcg= [IA-64] Override max number of concurrent global TLB
2741 purges which is reported from either PAL_VM_SUMMARY or
2744 nr_cpus= [SMP] Maximum number of processors that an SMP kernel
2745 could support. nr_cpus=n : n >= 1 limits the kernel to
2746 supporting 'n' processors. Later in runtime you can not
2747 use hotplug cpu feature to put more cpu back to online.
2748 just like you compile the kernel NR_CPUS=n
2750 nr_uarts= [SERIAL] maximum number of UARTs to be registered.
2752 numa_balancing= [KNL,X86] Enable or disable automatic NUMA balancing.
2753 Allowed values are enable and disable
2755 numa_zonelist_order= [KNL, BOOT] Select zonelist order for NUMA.
2756 one of ['zone', 'node', 'default'] can be specified
2757 This can be set from sysctl after boot.
2758 See Documentation/sysctl/vm.txt for details.
2760 ohci1394_dma=early [HW] enable debugging via the ohci1394 driver.
2761 See Documentation/debugging-via-ohci1394.txt for more
2764 olpc_ec_timeout= [OLPC] ms delay when issuing EC commands
2765 Rather than timing out after 20 ms if an EC
2766 command is not properly ACKed, override the length
2767 of the timeout. We have interrupts disabled while
2768 waiting for the ACK, so if this is set too high
2769 interrupts *may* be lost!
2771 omap_mux= [OMAP] Override bootloader pin multiplexing.
2772 Format: <mux_mode0.mode_name=value>...
2773 For example, to override I2C bus2:
2774 omap_mux=i2c2_scl.i2c2_scl=0x100,i2c2_sda.i2c2_sda=0x100
2776 oprofile.timer= [HW]
2777 Use timer interrupt instead of performance counters
2779 oprofile.cpu_type= Force an oprofile cpu type
2780 This might be useful if you have an older oprofile
2781 userland or if you want common events.
2782 Format: { arch_perfmon }
2783 arch_perfmon: [X86] Force use of architectural
2784 perfmon on Intel CPUs instead of the
2785 CPU specific event set.
2786 timer: [X86] Force use of architectural NMI
2787 timer mode (see also oprofile.timer
2788 for generic hr timer mode)
2789 [s390] Force legacy basic mode sampling
2790 (report cpu_type "timer")
2792 oops=panic Always panic on oopses. Default is to just kill the
2793 process, but there is a small probability of
2794 deadlocking the machine.
2795 This will also cause panics on machine check exceptions.
2796 Useful together with panic=30 to trigger a reboot.
2799 See Documentation/sound/oss/oss-parameters.txt
2801 page_owner= [KNL] Boot-time page_owner enabling option.
2802 Storage of the information about who allocated
2803 each page is disabled in default. With this switch,
2805 on: enable the feature
2807 page_poison= [KNL] Boot-time parameter changing the state of
2808 poisoning on the buddy allocator.
2809 off: turn off poisoning
2810 on: turn on poisoning
2812 panic= [KNL] Kernel behaviour on panic: delay <timeout>
2813 timeout > 0: seconds before rebooting
2814 timeout = 0: wait forever
2815 timeout < 0: reboot immediately
2818 panic_on_warn panic() instead of WARN(). Useful to cause kdump
2821 crash_kexec_post_notifiers
2822 Run kdump after running panic-notifiers and dumping
2823 kmsg. This only for the users who doubt kdump always
2824 succeeds in any situation.
2825 Note that this also increases risks of kdump failure,
2826 because some panic notifiers can make the crashed
2827 kernel more unstable.
2829 parkbd.port= [HW] Parallel port number the keyboard adapter is
2830 connected to, default is 0.
2832 parkbd.mode= [HW] Parallel port keyboard adapter mode of operation,
2833 0 for XT, 1 for AT (default is AT).
2836 parport= [HW,PPT] Specify parallel ports. 0 disables.
2837 Format: { 0 | auto | 0xBBB[,IRQ[,DMA]] }
2838 Use 'auto' to force the driver to use any
2839 IRQ/DMA settings detected (the default is to
2840 ignore detected IRQ/DMA settings because of
2841 possible conflicts). You can specify the base
2842 address, IRQ, and DMA settings; IRQ and DMA
2843 should be numbers, or 'auto' (for using detected
2844 settings on that particular port), or 'nofifo'
2845 (to avoid using a FIFO even if it is detected).
2846 Parallel ports are assigned in the order they
2847 are specified on the command line, starting
2850 parport_init_mode= [HW,PPT]
2851 Configure VIA parallel port to operate in
2852 a specific mode. This is necessary on Pegasos
2853 computer where firmware has no options for setting
2854 up parallel port mode and sets it to spp.
2855 Currently this function knows 686a and 8231 chips.
2856 Format: [spp|ps2|epp|ecp|ecpepp]
2859 Halt all CPUs after the first oops has been printed for
2860 the specified number of seconds. This is to be used if
2861 your oopses keep scrolling off the screen.
2866 See header of drivers/block/paride/pcd.c.
2867 See also Documentation/blockdev/paride.txt.
2869 pci=option[,option...] [PCI] various PCI subsystem options:
2870 earlydump [X86] dump PCI config space before the kernel
2872 off [X86] don't probe for the PCI bus
2873 bios [X86-32] force use of PCI BIOS, don't access
2874 the hardware directly. Use this if your machine
2875 has a non-standard PCI host bridge.
2876 nobios [X86-32] disallow use of PCI BIOS, only direct
2877 hardware access methods are allowed. Use this
2878 if you experience crashes upon bootup and you
2879 suspect they are caused by the BIOS.
2880 conf1 [X86] Force use of PCI Configuration Access
2881 Mechanism 1 (config address in IO port 0xCF8,
2882 data in IO port 0xCFC, both 32-bit).
2883 conf2 [X86] Force use of PCI Configuration Access
2884 Mechanism 2 (IO port 0xCF8 is an 8-bit port for
2885 the function, IO port 0xCFA, also 8-bit, sets
2886 bus number. The config space is then accessed
2887 through ports 0xC000-0xCFFF).
2888 See http://wiki.osdev.org/PCI for more info
2889 on the configuration access mechanisms.
2890 noaer [PCIE] If the PCIEAER kernel config parameter is
2891 enabled, this kernel boot option can be used to
2892 disable the use of PCIE advanced error reporting.
2893 nodomains [PCI] Disable support for multiple PCI
2894 root domains (aka PCI segments, in ACPI-speak).
2895 nommconf [X86] Disable use of MMCONFIG for PCI
2897 check_enable_amd_mmconf [X86] check for and enable
2898 properly configured MMIO access to PCI
2899 config space on AMD family 10h CPU
2900 nomsi [MSI] If the PCI_MSI kernel config parameter is
2901 enabled, this kernel boot option can be used to
2902 disable the use of MSI interrupts system-wide.
2903 noioapicquirk [APIC] Disable all boot interrupt quirks.
2904 Safety option to keep boot IRQs enabled. This
2905 should never be necessary.
2906 ioapicreroute [APIC] Enable rerouting of boot IRQs to the
2907 primary IO-APIC for bridges that cannot disable
2908 boot IRQs. This fixes a source of spurious IRQs
2909 when the system masks IRQs.
2910 noioapicreroute [APIC] Disable workaround that uses the
2911 boot IRQ equivalent of an IRQ that connects to
2912 a chipset where boot IRQs cannot be disabled.
2913 The opposite of ioapicreroute.
2914 biosirq [X86-32] Use PCI BIOS calls to get the interrupt
2915 routing table. These calls are known to be buggy
2916 on several machines and they hang the machine
2917 when used, but on other computers it's the only
2918 way to get the interrupt routing table. Try
2919 this option if the kernel is unable to allocate
2920 IRQs or discover secondary PCI buses on your
2922 rom [X86] Assign address space to expansion ROMs.
2923 Use with caution as certain devices share
2924 address decoders between ROMs and other
2926 norom [X86] Do not assign address space to
2927 expansion ROMs that do not already have
2928 BIOS assigned address ranges.
2929 nobar [X86] Do not assign address space to the
2930 BARs that weren't assigned by the BIOS.
2931 irqmask=0xMMMM [X86] Set a bit mask of IRQs allowed to be
2932 assigned automatically to PCI devices. You can
2933 make the kernel exclude IRQs of your ISA cards
2935 pirqaddr=0xAAAAA [X86] Specify the physical address
2936 of the PIRQ table (normally generated
2937 by the BIOS) if it is outside the
2938 F0000h-100000h range.
2939 lastbus=N [X86] Scan all buses thru bus #N. Can be
2940 useful if the kernel is unable to find your
2941 secondary buses and you want to tell it
2942 explicitly which ones they are.
2943 assign-busses [X86] Always assign all PCI bus
2944 numbers ourselves, overriding
2945 whatever the firmware may have done.
2946 usepirqmask [X86] Honor the possible IRQ mask stored
2947 in the BIOS $PIR table. This is needed on
2948 some systems with broken BIOSes, notably
2949 some HP Pavilion N5400 and Omnibook XE3
2950 notebooks. This will have no effect if ACPI
2951 IRQ routing is enabled.
2952 noacpi [X86] Do not use ACPI for IRQ routing
2953 or for PCI scanning.
2954 use_crs [X86] Use PCI host bridge window information
2955 from ACPI. On BIOSes from 2008 or later, this
2956 is enabled by default. If you need to use this,
2957 please report a bug.
2958 nocrs [X86] Ignore PCI host bridge windows from ACPI.
2959 If you need to use this, please report a bug.
2960 routeirq Do IRQ routing for all PCI devices.
2961 This is normally done in pci_enable_device(),
2962 so this option is a temporary workaround
2963 for broken drivers that don't call it.
2964 skip_isa_align [X86] do not align io start addr, so can
2965 handle more pci cards
2966 noearly [X86] Don't do any early type 1 scanning.
2967 This might help on some broken boards which
2968 machine check when some devices' config space
2969 is read. But various workarounds are disabled
2970 and some IOMMU drivers will not work.
2971 bfsort Sort PCI devices into breadth-first order.
2972 This sorting is done to get a device
2973 order compatible with older (<= 2.4) kernels.
2974 nobfsort Don't sort PCI devices into breadth-first order.
2975 pcie_bus_tune_off Disable PCIe MPS (Max Payload Size)
2976 tuning and use the BIOS-configured MPS defaults.
2977 pcie_bus_safe Set every device's MPS to the largest value
2978 supported by all devices below the root complex.
2979 pcie_bus_perf Set device MPS to the largest allowable MPS
2980 based on its parent bus. Also set MRRS (Max
2981 Read Request Size) to the largest supported
2982 value (no larger than the MPS that the device
2983 or bus can support) for best performance.
2984 pcie_bus_peer2peer Set every device's MPS to 128B, which
2985 every device is guaranteed to support. This
2986 configuration allows peer-to-peer DMA between
2987 any pair of devices, possibly at the cost of
2988 reduced performance. This also guarantees
2989 that hot-added devices will work.
2990 cbiosize=nn[KMG] The fixed amount of bus space which is
2991 reserved for the CardBus bridge's IO window.
2992 The default value is 256 bytes.
2993 cbmemsize=nn[KMG] The fixed amount of bus space which is
2994 reserved for the CardBus bridge's memory
2995 window. The default value is 64 megabytes.
2998 [<order of align>@][<domain>:]<bus>:<slot>.<func>[; ...]
2999 Specifies alignment and device to reassign
3000 aligned memory resources.
3001 If <order of align> is not specified,
3002 PAGE_SIZE is used as alignment.
3003 PCI-PCI bridge can be specified, if resource
3004 windows need to be expanded.
3005 ecrc= Enable/disable PCIe ECRC (transaction layer
3006 end-to-end CRC checking).
3007 bios: Use BIOS/firmware settings. This is the
3011 hpiosize=nn[KMG] The fixed amount of bus space which is
3012 reserved for hotplug bridge's IO window.
3013 Default size is 256 bytes.
3014 hpmemsize=nn[KMG] The fixed amount of bus space which is
3015 reserved for hotplug bridge's memory window.
3016 Default size is 2 megabytes.
3017 realloc= Enable/disable reallocating PCI bridge resources
3018 if allocations done by BIOS are too small to
3019 accommodate resources required by all child
3021 off: Turn realloc off
3023 realloc same as realloc=on
3024 noari do not use PCIe ARI.
3025 pcie_scan_all Scan all possible PCIe devices. Otherwise we
3026 only look for one device below a PCIe downstream
3029 pcie_aspm= [PCIE] Forcibly enable or disable PCIe Active State Power
3032 force Enable ASPM even on devices that claim not to support it.
3033 WARNING: Forcing ASPM on may cause system lockups.
3035 pcie_hp= [PCIE] PCI Express Hotplug driver options:
3036 nomsi Do not use MSI for PCI Express Native Hotplug (this
3037 makes all PCIe ports use INTx for hotplug services).
3039 pcie_ports= [PCIE] PCIe ports handling:
3040 auto Ask the BIOS whether or not to use native PCIe services
3041 associated with PCIe ports (PME, hot-plug, AER). Use
3042 them only if that is allowed by the BIOS.
3043 native Use native PCIe services associated with PCIe ports
3045 compat Treat PCIe ports as PCI-to-PCI bridges, disable the PCIe
3048 pcie_pme= [PCIE,PM] Native PCIe PME signaling options:
3049 nomsi Do not use MSI for native PCIe PME signaling (this makes
3050 all PCIe root ports use INTx for all services).
3052 pcmv= [HW,PCMCIA] BadgePAD 4
3056 Keep all power-domains already enabled by bootloader on,
3057 even if no driver has claimed them. This is useful
3058 for debug and development, but should not be
3059 needed on a platform with proper driver support.
3062 See Documentation/blockdev/paride.txt.
3064 pdcchassis= [PARISC,HW] Disable/Enable PDC Chassis Status codes at
3067 See arch/parisc/kernel/pdc_chassis.c
3069 percpu_alloc= Select which percpu first chunk allocator to use.
3070 Currently supported values are "embed" and "page".
3071 Archs may support subset or none of the selections.
3072 See comments in mm/percpu.c for details on each
3073 allocator. This parameter is primarily for debugging
3074 and performance comparison.
3077 See Documentation/blockdev/paride.txt.
3080 See Documentation/blockdev/paride.txt.
3082 pirq= [SMP,APIC] Manual mp-table setup
3083 See Documentation/x86/i386/IO-APIC.txt.
3085 plip= [PPT,NET] Parallel port network link
3086 Format: { parport<nr> | timid | 0 }
3087 See also Documentation/parport.txt.
3089 pmtmr= [X86] Manual setup of pmtmr I/O Port.
3090 Override pmtimer IOPort with a hex value.
3094 Enable PNP debug messages (depends on the
3095 CONFIG_PNP_DEBUG_MESSAGES option). Change at run-time
3096 via /sys/module/pnp/parameters/debug. We always show
3097 current resource usage; turning this on also shows
3098 possible settings and some assignment information.
3104 { on | off | curr | res | no-curr | no-res }
3107 [ISAPNP] Exclude IRQs for the autoconfiguration
3110 [ISAPNP] Exclude DMAs for the autoconfiguration
3112 pnp_reserve_io= [ISAPNP] Exclude I/O ports for the autoconfiguration
3113 Ranges are in pairs (I/O port base and size).
3116 [ISAPNP] Exclude memory regions for the
3118 Ranges are in pairs (memory base and size).
3120 ports= [IP_VS_FTP] IPVS ftp helper module
3122 Up to 8 (IP_VS_APP_MAX_PORTS) ports
3124 Format: <port>,<port>....
3126 ppc_strict_facility_enable
3127 [PPC] This option catches any kernel floating point,
3128 Altivec, VSX and SPE outside of regions specifically
3129 allowed (eg kernel_enable_fpu()/kernel_disable_fpu()).
3130 There is some performance impact when enabling this.
3132 print-fatal-signals=
3133 [KNL] debug: print fatal signals
3135 If enabled, warn about various signal handling
3136 related application anomalies: too many signals,
3137 too many POSIX.1 timers, fatal signals causing a
3140 If you hit the warning due to signal overflow,
3141 you might want to try "ulimit -i unlimited".
3145 printk.always_kmsg_dump=
3146 Trigger kmsg_dump for cases other than kernel oops or
3148 Format: <bool> (1/Y/y=enable, 0/N/n=disable)
3151 printk.time= Show timing data prefixed to each printk message line
3152 Format: <bool> (1/Y/y=enable, 0/N/n=disable)
3154 processor.max_cstate= [HW,ACPI]
3155 Limit processor to maximum C-state
3156 max_cstate=9 overrides any DMI blacklist limit.
3158 processor.nocst [HW,ACPI]
3159 Ignore the _CST method to determine C-states,
3160 instead using the legacy FADT method
3162 profile= [KNL] Enable kernel profiling via /proc/profile
3163 Format: [schedule,]<number>
3164 Param: "schedule" - profile schedule points.
3165 Param: <number> - step/bucket size as a power of 2 for
3166 statistical time based profiling.
3167 Param: "sleep" - profile D-state sleeping (millisecs).
3168 Requires CONFIG_SCHEDSTATS
3169 Param: "kvm" - profile VM exits.
3171 prompt_ramdisk= [RAM] List of RAM disks to prompt for floppy disk
3173 See Documentation/blockdev/ramdisk.txt.
3175 psmouse.proto= [HW,MOUSE] Highest PS2 mouse protocol extension to
3176 probe for; one of (bare|imps|exps|lifebook|any).
3177 psmouse.rate= [HW,MOUSE] Set desired mouse report rate, in reports
3179 psmouse.resetafter= [HW,MOUSE]
3180 Try to reset the device after so many bad packets
3183 [HW,MOUSE] Set desired mouse resolution, in dpi.
3184 psmouse.smartscroll=
3185 [HW,MOUSE] Controls Logitech smartscroll autorepeat.
3186 0 = disabled, 1 = enabled (default).
3188 pstore.backend= Specify the name of the pstore backend to use
3191 See Documentation/blockdev/paride.txt.
3194 [KNL] Number of legacy pty's. Overwrites compiled-in
3197 quiet [KNL] Disable most log messages
3202 See Documentation/md.txt.
3204 ramdisk_size= [RAM] Sizes of RAM disks in kilobytes
3205 See Documentation/blockdev/ramdisk.txt.
3208 In kernels built with CONFIG_RCU_NOCB_CPU=y, set
3209 the specified list of CPUs to be no-callback CPUs.
3210 Invocation of these CPUs' RCU callbacks will
3211 be offloaded to "rcuox/N" kthreads created for
3212 that purpose, where "x" is "b" for RCU-bh, "p"
3213 for RCU-preempt, and "s" for RCU-sched, and "N"
3214 is the CPU number. This reduces OS jitter on the
3215 offloaded CPUs, which can be useful for HPC and
3216 real-time workloads. It can also improve energy
3217 efficiency for asymmetric multiprocessors.
3220 Rather than requiring that offloaded CPUs
3221 (specified by rcu_nocbs= above) explicitly
3222 awaken the corresponding "rcuoN" kthreads,
3223 make these kthreads poll for callbacks.
3224 This improves the real-time response for the
3225 offloaded CPUs by relieving them of the need to
3226 wake up the corresponding kthread, but degrades
3227 energy efficiency by requiring that the kthreads
3228 periodically wake up to do the polling.
3230 rcutree.blimit= [KNL]
3231 Set maximum number of finished RCU callbacks to
3232 process in one batch.
3234 rcutree.dump_tree= [KNL]
3235 Dump the structure of the rcu_node combining tree
3236 out at early boot. This is used for diagnostic
3237 purposes, to verify correct tree setup.
3239 rcutree.gp_cleanup_delay= [KNL]
3240 Set the number of jiffies to delay each step of
3241 RCU grace-period cleanup. This only has effect
3242 when CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP is set.
3244 rcutree.gp_init_delay= [KNL]
3245 Set the number of jiffies to delay each step of
3246 RCU grace-period initialization. This only has
3247 effect when CONFIG_RCU_TORTURE_TEST_SLOW_INIT
3250 rcutree.gp_preinit_delay= [KNL]
3251 Set the number of jiffies to delay each step of
3252 RCU grace-period pre-initialization, that is,
3253 the propagation of recent CPU-hotplug changes up
3254 the rcu_node combining tree. This only has effect
3255 when CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT is set.
3257 rcutree.rcu_fanout_exact= [KNL]
3258 Disable autobalancing of the rcu_node combining
3259 tree. This is used by rcutorture, and might
3260 possibly be useful for architectures having high
3261 cache-to-cache transfer latencies.
3263 rcutree.rcu_fanout_leaf= [KNL]
3264 Change the number of CPUs assigned to each
3265 leaf rcu_node structure. Useful for very
3266 large systems, which will choose the value 64,
3267 and for NUMA systems with large remote-access
3268 latencies, which will choose a value aligned
3269 with the appropriate hardware boundaries.
3271 rcutree.jiffies_till_sched_qs= [KNL]
3272 Set required age in jiffies for a
3273 given grace period before RCU starts
3274 soliciting quiescent-state help from
3275 rcu_note_context_switch().
3277 rcutree.jiffies_till_first_fqs= [KNL]
3278 Set delay from grace-period initialization to
3279 first attempt to force quiescent states.
3280 Units are jiffies, minimum value is zero,
3281 and maximum value is HZ.
3283 rcutree.jiffies_till_next_fqs= [KNL]
3284 Set delay between subsequent attempts to force
3285 quiescent states. Units are jiffies, minimum
3286 value is one, and maximum value is HZ.
3288 rcutree.kthread_prio= [KNL,BOOT]
3289 Set the SCHED_FIFO priority of the RCU per-CPU
3290 kthreads (rcuc/N). This value is also used for
3291 the priority of the RCU boost threads (rcub/N)
3292 and for the RCU grace-period kthreads (rcu_bh,
3293 rcu_preempt, and rcu_sched). If RCU_BOOST is
3294 set, valid values are 1-99 and the default is 1
3295 (the least-favored priority). Otherwise, when
3296 RCU_BOOST is not set, valid values are 0-99 and
3297 the default is zero (non-realtime operation).
3299 rcutree.rcu_nocb_leader_stride= [KNL]
3300 Set the number of NOCB kthread groups, which
3301 defaults to the square root of the number of
3302 CPUs. Larger numbers reduces the wakeup overhead
3303 on the per-CPU grace-period kthreads, but increases
3304 that same overhead on each group's leader.
3306 rcutree.qhimark= [KNL]
3307 Set threshold of queued RCU callbacks beyond which
3308 batch limiting is disabled.
3310 rcutree.qlowmark= [KNL]
3311 Set threshold of queued RCU callbacks below which
3312 batch limiting is re-enabled.
3314 rcutree.rcu_idle_gp_delay= [KNL]
3315 Set wakeup interval for idle CPUs that have
3316 RCU callbacks (RCU_FAST_NO_HZ=y).
3318 rcutree.rcu_idle_lazy_gp_delay= [KNL]
3319 Set wakeup interval for idle CPUs that have
3320 only "lazy" RCU callbacks (RCU_FAST_NO_HZ=y).
3321 Lazy RCU callbacks are those which RCU can
3322 prove do nothing more than free memory.
3324 rcuperf.gp_exp= [KNL]
3325 Measure performance of expedited synchronous
3326 grace-period primitives.
3328 rcuperf.holdoff= [KNL]
3329 Set test-start holdoff period. The purpose of
3330 this parameter is to delay the start of the
3331 test until boot completes in order to avoid
3334 rcuperf.nreaders= [KNL]
3335 Set number of RCU readers. The value -1 selects
3336 N, where N is the number of CPUs. A value
3337 "n" less than -1 selects N-n+1, where N is again
3338 the number of CPUs. For example, -2 selects N
3339 (the number of CPUs), -3 selects N+1, and so on.
3340 A value of "n" less than or equal to -N selects
3343 rcuperf.nwriters= [KNL]
3344 Set number of RCU writers. The values operate
3345 the same as for rcuperf.nreaders.
3346 N, where N is the number of CPUs
3348 rcuperf.perf_runnable= [BOOT]
3349 Start rcuperf running at boot time.
3351 rcuperf.shutdown= [KNL]
3352 Shut the system down after performance tests
3353 complete. This is useful for hands-off automated
3356 rcuperf.perf_type= [KNL]
3357 Specify the RCU implementation to test.
3359 rcuperf.verbose= [KNL]
3360 Enable additional printk() statements.
3362 rcutorture.cbflood_inter_holdoff= [KNL]
3363 Set holdoff time (jiffies) between successive
3364 callback-flood tests.
3366 rcutorture.cbflood_intra_holdoff= [KNL]
3367 Set holdoff time (jiffies) between successive
3368 bursts of callbacks within a given callback-flood
3371 rcutorture.cbflood_n_burst= [KNL]
3372 Set the number of bursts making up a given
3373 callback-flood test. Set this to zero to
3374 disable callback-flood testing.
3376 rcutorture.cbflood_n_per_burst= [KNL]
3377 Set the number of callbacks to be registered
3378 in a given burst of a callback-flood test.
3380 rcutorture.fqs_duration= [KNL]
3381 Set duration of force_quiescent_state bursts
3384 rcutorture.fqs_holdoff= [KNL]
3385 Set holdoff time within force_quiescent_state bursts
3388 rcutorture.fqs_stutter= [KNL]
3389 Set wait time between force_quiescent_state bursts
3392 rcutorture.gp_cond= [KNL]
3393 Use conditional/asynchronous update-side
3394 primitives, if available.
3396 rcutorture.gp_exp= [KNL]
3397 Use expedited update-side primitives, if available.
3399 rcutorture.gp_normal= [KNL]
3400 Use normal (non-expedited) asynchronous
3401 update-side primitives, if available.
3403 rcutorture.gp_sync= [KNL]
3404 Use normal (non-expedited) synchronous
3405 update-side primitives, if available. If all
3406 of rcutorture.gp_cond=, rcutorture.gp_exp=,
3407 rcutorture.gp_normal=, and rcutorture.gp_sync=
3408 are zero, rcutorture acts as if is interpreted
3409 they are all non-zero.
3411 rcutorture.n_barrier_cbs= [KNL]
3412 Set callbacks/threads for rcu_barrier() testing.
3414 rcutorture.nfakewriters= [KNL]
3415 Set number of concurrent RCU writers. These just
3416 stress RCU, they don't participate in the actual
3417 test, hence the "fake".
3419 rcutorture.nreaders= [KNL]
3420 Set number of RCU readers. The value -1 selects
3421 N-1, where N is the number of CPUs. A value
3422 "n" less than -1 selects N-n-2, where N is again
3423 the number of CPUs. For example, -2 selects N
3424 (the number of CPUs), -3 selects N+1, and so on.
3426 rcutorture.object_debug= [KNL]
3427 Enable debug-object double-call_rcu() testing.
3429 rcutorture.onoff_holdoff= [KNL]
3430 Set time (s) after boot for CPU-hotplug testing.
3432 rcutorture.onoff_interval= [KNL]
3433 Set time (s) between CPU-hotplug operations, or
3434 zero to disable CPU-hotplug testing.
3436 rcutorture.shuffle_interval= [KNL]
3437 Set task-shuffle interval (s). Shuffling tasks
3438 allows some CPUs to go into dyntick-idle mode
3439 during the rcutorture test.
3441 rcutorture.shutdown_secs= [KNL]
3442 Set time (s) after boot system shutdown. This
3443 is useful for hands-off automated testing.
3445 rcutorture.stall_cpu= [KNL]
3446 Duration of CPU stall (s) to test RCU CPU stall
3447 warnings, zero to disable.
3449 rcutorture.stall_cpu_holdoff= [KNL]
3450 Time to wait (s) after boot before inducing stall.
3452 rcutorture.stat_interval= [KNL]
3453 Time (s) between statistics printk()s.
3455 rcutorture.stutter= [KNL]
3456 Time (s) to stutter testing, for example, specifying
3457 five seconds causes the test to run for five seconds,
3458 wait for five seconds, and so on. This tests RCU's
3459 ability to transition abruptly to and from idle.
3461 rcutorture.test_boost= [KNL]
3462 Test RCU priority boosting? 0=no, 1=maybe, 2=yes.
3463 "Maybe" means test if the RCU implementation
3464 under test support RCU priority boosting.
3466 rcutorture.test_boost_duration= [KNL]
3467 Duration (s) of each individual boost test.
3469 rcutorture.test_boost_interval= [KNL]
3470 Interval (s) between each boost test.
3472 rcutorture.test_no_idle_hz= [KNL]
3473 Test RCU's dyntick-idle handling. See also the
3474 rcutorture.shuffle_interval parameter.
3476 rcutorture.torture_runnable= [BOOT]
3477 Start rcutorture running at boot time.
3479 rcutorture.torture_type= [KNL]
3480 Specify the RCU implementation to test.
3482 rcutorture.verbose= [KNL]
3483 Enable additional printk() statements.
3485 rcupdate.rcu_cpu_stall_suppress= [KNL]
3486 Suppress RCU CPU stall warning messages.
3488 rcupdate.rcu_cpu_stall_timeout= [KNL]
3489 Set timeout for RCU CPU stall warning messages.
3491 rcupdate.rcu_expedited= [KNL]
3492 Use expedited grace-period primitives, for
3493 example, synchronize_rcu_expedited() instead
3494 of synchronize_rcu(). This reduces latency,
3495 but can increase CPU utilization, degrade
3496 real-time latency, and degrade energy efficiency.
3497 No effect on CONFIG_TINY_RCU kernels.
3499 rcupdate.rcu_normal= [KNL]
3500 Use only normal grace-period primitives,
3501 for example, synchronize_rcu() instead of
3502 synchronize_rcu_expedited(). This improves
3503 real-time latency, CPU utilization, and
3504 energy efficiency, but can expose users to
3505 increased grace-period latency. This parameter
3506 overrides rcupdate.rcu_expedited. No effect on
3507 CONFIG_TINY_RCU kernels.
3509 rcupdate.rcu_normal_after_boot= [KNL]
3510 Once boot has completed (that is, after
3511 rcu_end_inkernel_boot() has been invoked), use
3512 only normal grace-period primitives. No effect
3513 on CONFIG_TINY_RCU kernels.
3515 rcupdate.rcu_task_stall_timeout= [KNL]
3516 Set timeout in jiffies for RCU task stall warning
3517 messages. Disable with a value less than or equal
3520 rcupdate.rcu_self_test= [KNL]
3521 Run the RCU early boot self tests
3523 rcupdate.rcu_self_test_bh= [KNL]
3524 Run the RCU bh early boot self tests
3526 rcupdate.rcu_self_test_sched= [KNL]
3527 Run the RCU sched early boot self tests
3531 Run specified binary instead of /init from the ramdisk,
3532 used for early userspace startup. See initrd.
3535 Format (x86 or x86_64):
3536 [w[arm] | c[old] | h[ard] | s[oft] | g[pio]] \
3538 [[,]b[ios] | a[cpi] | k[bd] | t[riple] | e[fi] | p[ci]] \
3540 Where reboot_mode is one of warm (soft) or cold (hard) or gpio,
3541 reboot_type is one of bios, acpi, kbd, triple, efi, or pci,
3542 reboot_force is either force or not specified,
3543 reboot_cpu is s[mp]#### with #### being the processor
3544 to be used for rebooting.
3547 [KNL, SMP] Set scheduler's default relax_domain_level.
3548 See Documentation/cgroups/cpusets.txt.
3550 relative_sleep_states=
3551 [SUSPEND] Use sleep state labeling where the deepest
3552 state available other than hibernation is always "mem".
3553 Format: { "0" | "1" }
3554 0 -- Traditional sleep state labels.
3555 1 -- Relative sleep state labels.
3557 reserve= [KNL,BUGS] Force the kernel to ignore some iomem area
3559 reservetop= [X86-32]
3561 Reserves a hole at the top of the kernel virtual
3566 Set the amount of memory to reserve for BIOS at
3567 the bottom of the address space.
3569 reset_devices [KNL] Force drivers to reset the underlying device
3570 during initialization.
3573 Specify the partition device for software suspend
3575 {/dev/<dev> | PARTUUID=<uuid> | <int>:<int> | <hex>}
3577 resume_offset= [SWSUSP]
3578 Specify the offset from the beginning of the partition
3579 given by "resume=" at which the swap header is located,
3580 in <PAGE_SIZE> units (needed only for swap files).
3581 See Documentation/power/swsusp-and-swap-files.txt
3583 resumedelay= [HIBERNATION] Delay (in seconds) to pause before attempting to
3584 read the resume files
3586 resumewait [HIBERNATION] Wait (indefinitely) for resume device to show up.
3587 Useful for devices that are detected asynchronously
3588 (e.g. USB and MMC devices).
3590 hibernate= [HIBERNATION]
3591 noresume Don't check if there's a hibernation image
3592 present during boot.
3593 nocompress Don't compress/decompress hibernation images.
3594 no Disable hibernation and resume.
3596 retain_initrd [RAM] Keep initrd memory after extraction
3598 rfkill.default_state=
3599 0 "airplane mode". All wifi, bluetooth, wimax, gps, fm,
3600 etc. communication is blocked by default.
3603 rfkill.master_switch_mode=
3604 0 The "airplane mode" button does nothing.
3605 1 The "airplane mode" button toggles between everything
3606 blocked and the previous configuration.
3607 2 The "airplane mode" button toggles between everything
3608 blocked and everything unblocked.
3610 rhash_entries= [KNL,NET]
3611 Set number of hash buckets for route cache
3613 ro [KNL] Mount root device read-only on boot
3616 on Mark read-only kernel memory as read-only (default).
3617 off Leave read-only kernel memory writable for debugging.
3620 Enable the uart passthrough on the designated usb port
3621 on Rockchip SoCs. When active, the signals of the
3622 debug-uart get routed to the D+ and D- pins of the usb
3623 port and the regular usb controller gets disabled.
3625 root= [KNL] Root filesystem
3626 See name_to_dev_t comment in init/do_mounts.c.
3628 rootdelay= [KNL] Delay (in seconds) to pause before attempting to
3629 mount the root filesystem
3631 rootflags= [KNL] Set root filesystem mount option string
3633 rootfstype= [KNL] Set root filesystem type
3635 rootwait [KNL] Wait (indefinitely) for root device to show up.
3636 Useful for devices that are detected asynchronously
3637 (e.g. USB and MMC devices).
3639 rproc_mem=nn[KMG][@address]
3640 [KNL,ARM,CMA] Remoteproc physical memory block.
3641 Memory area to be used by remote processor image,
3644 rw [KNL] Mount root device read-write on boot
3646 S [KNL] Run init in single mode
3648 s390_iommu= [HW,S390]
3649 Set s390 IOTLB flushing mode
3651 With strict flushing every unmap operation will result in
3652 an IOTLB flush. Default is lazy flushing before reuse,
3656 See drivers/net/irda/sa1100_ir.c.
3658 sbni= [NET] Granch SBNI12 leased line adapter
3660 sched_debug [KNL] Enables verbose scheduler debug messages.
3662 schedstats= [KNL,X86] Enable or disable scheduled statistics.
3663 Allowed values are enable and disable. This feature
3664 incurs a small amount of overhead in the scheduler
3665 but is useful for debugging and performance tuning.
3667 skew_tick= [KNL] Offset the periodic timer tick per cpu to mitigate
3668 xtime_lock contention on larger systems, and/or RCU lock
3669 contention on all systems with CONFIG_MAXSMP set.
3670 Format: { "0" | "1" }
3671 0 -- disable. (may be 1 via CONFIG_CMDLINE="skew_tick=1"
3673 Note: increases power consumption, thus should only be
3674 enabled if running jitter sensitive (HPC/RT) workloads.
3676 security= [SECURITY] Choose a security module to enable at boot.
3677 If this boot parameter is not specified, only the first
3678 security module asking for security registration will be
3679 loaded. An invalid security module name will be treated
3680 as if no module has been chosen.
3682 selinux= [SELINUX] Disable or enable SELinux at boot time.
3683 Format: { "0" | "1" }
3684 See security/selinux/Kconfig help text.
3687 Default value is set via kernel config option.
3688 If enabled at boot time, /selinux/disable can be used
3689 later to disable prior to initial policy load.
3691 apparmor= [APPARMOR] Disable or enable AppArmor at boot time
3692 Format: { "0" | "1" }
3693 See security/apparmor/Kconfig help text
3696 Default value is set via kernel config option.
3698 serialnumber [BUGS=X86-32]
3701 Maximal number of shapers.
3703 show_msr= [x86] show boot-time MSR settings
3704 Format: { <integer> }
3705 Show boot-time (BIOS-initialized) MSR settings.
3706 The parameter means the number of CPUs to show,
3707 for example 1 means boot CPU only.
3715 Disable merging of slabs with similar size. May be
3716 necessary if there is some reason to distinguish
3717 allocs to different slabs. Debug options disable
3718 merging on their own.
3719 For more information see Documentation/vm/slub.txt.
3721 slab_max_order= [MM, SLAB]
3722 Determines the maximum allowed order for slabs.
3723 A high setting may cause OOMs due to memory
3724 fragmentation. Defaults to 1 for systems with
3725 more than 32MB of RAM, 0 otherwise.
3727 slub_debug[=options[,slabs]] [MM, SLUB]
3728 Enabling slub_debug allows one to determine the
3729 culprit if slab objects become corrupted. Enabling
3730 slub_debug can create guard zones around objects and
3731 may poison objects when not in use. Also tracks the
3732 last alloc / free. For more information see
3733 Documentation/vm/slub.txt.
3735 slub_max_order= [MM, SLUB]
3736 Determines the maximum allowed order for slabs.
3737 A high setting may cause OOMs due to memory
3738 fragmentation. For more information see
3739 Documentation/vm/slub.txt.
3741 slub_min_objects= [MM, SLUB]
3742 The minimum number of objects per slab. SLUB will
3743 increase the slab order up to slub_max_order to
3744 generate a sufficiently large slab able to contain
3745 the number of objects indicated. The higher the number
3746 of objects the smaller the overhead of tracking slabs
3747 and the less frequently locks need to be acquired.
3748 For more information see Documentation/vm/slub.txt.
3750 slub_min_order= [MM, SLUB]
3751 Determines the minimum page order for slabs. Must be
3752 lower than slub_max_order.
3753 For more information see Documentation/vm/slub.txt.
3755 slub_nomerge [MM, SLUB]
3756 Same with slab_nomerge. This is supported for legacy.
3757 See slab_nomerge for more information.
3760 Format: <io1>[,<io2>[,...,<io8>]]
3762 smsc-ircc2.nopnp [HW] Don't use PNP to discover SMC devices
3763 smsc-ircc2.ircc_cfg= [HW] Device configuration I/O port
3764 smsc-ircc2.ircc_sir= [HW] SIR base I/O port
3765 smsc-ircc2.ircc_fir= [HW] FIR base I/O port
3766 smsc-ircc2.ircc_irq= [HW] IRQ line
3767 smsc-ircc2.ircc_dma= [HW] DMA channel
3768 smsc-ircc2.ircc_transceiver= [HW] Transceiver type:
3769 0: Toshiba Satellite 1800 (GP data pin select)
3770 1: Fast pin select (default)
3773 smt [KNL,S390] Set the maximum number of threads (logical
3774 CPUs) to use per physical CPU on systems capable of
3775 symmetric multithreading (SMT). Will be capped to the
3776 actual hardware limit.
3778 Default: -1 (no limit)
3781 [KNL] Should the soft-lockup detector generate panics.
3784 softlockup_all_cpu_backtrace=
3785 [KNL] Should the soft-lockup detector generate
3786 backtraces on all cpus.
3789 sonypi.*= [HW] Sony Programmable I/O Control Device driver
3790 See Documentation/laptops/sonypi.txt
3792 spia_io_base= [HW,MTD]
3798 Enabled the stack tracer on boot up.
3800 stacktrace_filter=[function-list]
3801 [FTRACE] Limit the functions that the stack tracer
3802 will trace at boot up. function-list is a comma separated
3803 list of functions. This list can be changed at run
3804 time by the stack_trace_filter file in the debugfs
3805 tracing directory. Note, this enables stack tracing
3806 and the stacktrace above is not needed.
3810 Set the STI (builtin display/keyboard on the HP-PARISC
3811 machines) console (graphic card) which should be used
3812 as the initial boot-console.
3813 See also comment in drivers/video/console/sticore.c.
3816 See comment in drivers/video/console/sticore.c.
3819 Format: bpp:<bpp1>[:<bpp2>[:<bpp3>...]]
3821 sunrpc.min_resvport=
3822 sunrpc.max_resvport=
3824 SunRPC servers often require that client requests
3825 originate from a privileged port (i.e. a port in the
3826 range 0 < portnr < 1024).
3827 An administrator who wishes to reserve some of these
3828 ports for other uses may adjust the range that the
3829 kernel's sunrpc client considers to be privileged
3830 using these two parameters to set the minimum and
3831 maximum port values.
3835 Control how the NFS server code allocates CPUs to
3836 service thread pools. Depending on how many NICs
3837 you have and where their interrupts are bound, this
3838 option will affect which CPUs will do NFS serving.
3839 Note: this parameter cannot be changed while the
3840 NFS server is running.
3842 auto the server chooses an appropriate mode
3843 automatically using heuristics
3844 global a single global pool contains all CPUs
3845 percpu one pool for each CPU
3846 pernode one pool for each NUMA node (equivalent
3847 to global on non-NUMA machines)
3849 sunrpc.tcp_slot_table_entries=
3850 sunrpc.udp_slot_table_entries=
3852 Sets the upper limit on the number of simultaneous
3853 RPC calls that can be sent from the client to a
3854 server. Increasing these values may allow you to
3855 improve throughput, but will also increase the
3856 amount of memory reserved for use by the client.
3858 suspend.pm_test_delay=
3860 Sets the number of seconds to remain in a suspend test
3861 mode before resuming the system (see
3862 /sys/power/pm_test). Only available when CONFIG_PM_DEBUG
3863 is set. Default value is 5.
3866 [KNL] Enable accounting of swap in memory resource
3867 controller if no parameter or 1 is given or disable
3868 it if 0 is given (See Documentation/cgroups/memory.txt)
3870 swiotlb= [ARM,IA-64,PPC,MIPS,X86]
3871 Format: { <int> | force }
3872 <int> -- Number of I/O TLB slabs
3873 force -- force using of bounce buffers even if they
3874 wouldn't be automatically used by the kernel
3878 sysfs.deprecated=0|1 [KNL]
3879 Enable/disable old style sysfs layout for old udev
3880 on older distributions. When this option is enabled
3881 very new udev will not work anymore. When this option
3882 is disabled (or CONFIG_SYSFS_DEPRECATED not compiled)
3883 in older udev will not work anymore.
3884 Default depends on CONFIG_SYSFS_DEPRECATED_V2 set in
3885 the kernel configuration.
3887 sysrq_always_enabled
3889 Ignore sysrq setting - this boot parameter will
3890 neutralize any effect of /proc/sys/kernel/sysrq.
3891 Useful for debugging.
3893 tcpmhash_entries= [KNL,NET]
3894 Set the number of tcp_metrics_hash slots.
3895 Default value is 8192 or 16384 depending on total
3896 ram pages. This is used to specify the TCP metrics
3897 cache size. See Documentation/networking/ip-sysctl.txt
3898 "tcp_no_metrics_save" section for more details.
3902 test_suspend= [SUSPEND][,N]
3903 Specify "mem" (for Suspend-to-RAM) or "standby" (for
3904 standby suspend) or "freeze" (for suspend type freeze)
3905 as the system sleep state during system startup with
3906 the optional capability to repeat N number of times.
3907 The system is woken from this state using a
3908 wakeup-capable RTC alarm.
3910 thash_entries= [KNL,NET]
3911 Set number of hash buckets for TCP connection
3913 thermal.act= [HW,ACPI]
3914 -1: disable all active trip points in all thermal zones
3915 <degrees C>: override all lowest active trip points
3917 thermal.crt= [HW,ACPI]
3918 -1: disable all critical trip points in all thermal zones
3919 <degrees C>: override all critical trip points
3921 thermal.nocrt= [HW,ACPI]
3922 Set to disable actions on ACPI thermal zone
3923 critical and hot trip points.
3925 thermal.off= [HW,ACPI]
3926 1: disable ACPI thermal control
3928 thermal.psv= [HW,ACPI]
3929 -1: disable all passive trip points
3930 <degrees C>: override all passive trip points to this
3933 thermal.tzp= [HW,ACPI]
3934 Specify global default ACPI thermal zone polling rate
3935 <deci-seconds>: poll all this frequency
3936 0: no polling (default)
3939 Force threading of all interrupt handlers except those
3940 marked explicitly IRQF_NO_THREAD.
3943 Enable the Transcendent memory driver if built-in.
3945 tmem.cleancache=0|1 [KNL, XEN]
3946 Default is on (1). Disable the usage of the cleancache
3947 API to send anonymous pages to the hypervisor.
3949 tmem.frontswap=0|1 [KNL, XEN]
3950 Default is on (1). Disable the usage of the frontswap
3951 API to send swap pages to the hypervisor. If disabled
3952 the selfballooning and selfshrinking are force disabled.
3954 tmem.selfballooning=0|1 [KNL, XEN]
3955 Default is on (1). Disable the driving of swap pages
3958 tmem.selfshrinking=0|1 [KNL, XEN]
3959 Default is on (1). Partial swapoff that immediately
3960 transfers pages from Xen hypervisor back to the
3961 kernel based on different criteria.
3965 Specify if the kernel should make use of the cpu
3966 topology information if the hardware supports this.
3967 The scheduler will make use of this information and
3968 e.g. base its process migration decisions on it.
3971 topology_updates= [KNL, PPC, NUMA]
3973 Specify if the kernel should ignore (off)
3974 topology updates sent by the hypervisor to this
3979 tpm_suspend_pcr=[HW,TPM]
3980 Format: integer pcr id
3981 Specify that at suspend time, the tpm driver
3982 should extend the specified pcr with zeros,
3983 as a workaround for some chips which fail to
3984 flush the last written pcr on TPM_SaveState.
3985 This will guarantee that all the other pcrs
3988 trace_buf_size=nn[KMG]
3989 [FTRACE] will set tracing buffer size on each cpu.
3991 trace_event=[event-list]
3992 [FTRACE] Set and start specified trace events in order
3993 to facilitate early boot debugging.
3994 See also Documentation/trace/events.txt
3996 trace_options=[option-list]
3997 [FTRACE] Enable or disable tracer options at boot.
3998 The option-list is a comma delimited list of options
3999 that can be enabled or disabled just as if you were
4000 to echo the option name into
4002 /sys/kernel/debug/tracing/trace_options
4004 For example, to enable stacktrace option (to dump the
4005 stack trace of each event), add to the command line:
4007 trace_options=stacktrace
4009 See also Documentation/trace/ftrace.txt "trace options"
4013 Have the tracepoints sent to printk as well as the
4014 tracing ring buffer. This is useful for early boot up
4015 where the system hangs or reboots and does not give the
4016 option for reading the tracing buffer or performing a
4017 ftrace_dump_on_oops.
4019 To turn off having tracepoints sent to printk,
4020 echo 0 > /proc/sys/kernel/tracepoint_printk
4021 Note, echoing 1 into this file without the
4022 tracepoint_printk kernel cmdline option has no effect.
4026 Having tracepoints sent to printk() and activating high
4027 frequency tracepoints such as irq or sched, can cause
4028 the system to live lock.
4031 [FTRACE] enable this option to disable tracing when a
4032 warning is hit. This turns off "tracing_on". Tracing can
4033 be enabled again by echoing '1' into the "tracing_on"
4034 file located in /sys/kernel/debug/tracing/
4036 This option is useful, as it disables the trace before
4037 the WARNING dump is called, which prevents the trace to
4038 be filled with content caused by the warning output.
4040 This option can also be set at run time via the sysctl
4041 option: kernel/traceoff_on_warning
4043 transparent_hugepage=
4045 Format: [always|madvise|never]
4046 Can be used to control the default behavior of the system
4047 with respect to transparent hugepages.
4048 See Documentation/vm/transhuge.txt for more details.
4050 tsc= Disable clocksource stability checks for TSC.
4052 [x86] reliable: mark tsc clocksource as reliable, this
4053 disables clocksource verification at runtime, as well
4054 as the stability checks done at bootup. Used to enable
4055 high-resolution timer mode on older hardware, and in
4056 virtualized environment.
4057 [x86] noirqtime: Do not use TSC to do irq accounting.
4058 Used to run time disable IRQ_TIME_ACCOUNTING on any
4059 platforms where RDTSC is slow and this accounting
4062 turbografx.map[2|3]= [HW,JOY]
4063 TurboGraFX parallel port interface
4065 <port#>,<js1>,<js2>,<js3>,<js4>,<js5>,<js6>,<js7>
4066 See also Documentation/input/joystick-parport.txt
4068 udbg-immortal [PPC] When debugging early kernel crashes that
4069 happen after console_init() and before a proper
4070 console driver takes over, this boot options might
4071 help "seeing" what's going on.
4073 uhash_entries= [KNL,NET]
4074 Set number of hash buckets for UDP/UDP-Lite connections
4077 [USB] Ignore overcurrent events (default N).
4078 Some badly-designed motherboards generate lots of
4079 bogus events, for ports that aren't wired to
4080 anything. Set this parameter to avoid log spamming.
4081 Note that genuine overcurrent events won't be
4085 [X86] Cause panic on unknown NMI.
4087 usbcore.authorized_default=
4088 [USB] Default USB device authorization:
4089 (default -1 = authorized except for wireless USB,
4090 0 = not authorized, 1 = authorized)
4092 usbcore.autosuspend=
4093 [USB] The autosuspend time delay (in seconds) used
4094 for newly-detected USB devices (default 2). This
4095 is the time required before an idle device will be
4096 autosuspended. Devices for which the delay is set
4097 to a negative value won't be autosuspended at all.
4099 usbcore.usbfs_snoop=
4100 [USB] Set to log all usbfs traffic (default 0 = off).
4102 usbcore.usbfs_snoop_max=
4103 [USB] Maximum number of bytes to snoop in each URB
4106 usbcore.blinkenlights=
4107 [USB] Set to cycle leds on hubs (default 0 = off).
4109 usbcore.old_scheme_first=
4110 [USB] Start with the old device initialization
4111 scheme (default 0 = off).
4113 usbcore.usbfs_memory_mb=
4114 [USB] Memory limit (in MB) for buffers allocated by
4115 usbfs (default = 16, 0 = max = 2047).
4117 usbcore.use_both_schemes=
4118 [USB] Try the other device initialization scheme
4119 if the first one fails (default 1 = enabled).
4121 usbcore.initial_descriptor_timeout=
4122 [USB] Specifies timeout for the initial 64-byte
4123 USB_REQ_GET_DESCRIPTOR request in milliseconds
4124 (default 5000 = 5.0 seconds).
4126 usbcore.nousb [USB] Disable the USB subsystem
4129 [USBHID] The interval which mice are to be polled at.
4131 usb-storage.delay_use=
4132 [UMS] The delay in seconds before a new device is
4133 scanned for Logical Units (default 1).
4136 [UMS] A list of quirks entries to supplement or
4137 override the built-in unusual_devs list. List
4138 entries are separated by commas. Each entry has
4139 the form VID:PID:Flags where VID and PID are Vendor
4140 and Product ID values (4-digit hex numbers) and
4141 Flags is a set of characters, each corresponding
4142 to a common usb-storage quirk flag as follows:
4143 a = SANE_SENSE (collect more than 18 bytes
4145 b = BAD_SENSE (don't collect more than 18
4146 bytes of sense data);
4147 c = FIX_CAPACITY (decrease the reported
4148 device capacity by one sector);
4149 d = NO_READ_DISC_INFO (don't use
4150 READ_DISC_INFO command);
4151 e = NO_READ_CAPACITY_16 (don't use
4152 READ_CAPACITY_16 command);
4153 f = NO_REPORT_OPCODES (don't use report opcodes
4155 g = MAX_SECTORS_240 (don't transfer more than
4156 240 sectors at a time, uas only);
4157 h = CAPACITY_HEURISTICS (decrease the
4158 reported device capacity by one
4159 sector if the number is odd);
4160 i = IGNORE_DEVICE (don't bind to this
4162 j = NO_REPORT_LUNS (don't use report luns
4164 l = NOT_LOCKABLE (don't try to lock and
4165 unlock ejectable media);
4166 m = MAX_SECTORS_64 (don't transfer more
4167 than 64 sectors = 32 KB at a time);
4168 n = INITIAL_READ10 (force a retry of the
4169 initial READ(10) command);
4170 o = CAPACITY_OK (accept the capacity
4171 reported by the device);
4172 p = WRITE_CACHE (the device cache is ON
4174 r = IGNORE_RESIDUE (the device reports
4175 bogus residue values);
4176 s = SINGLE_LUN (the device has only one
4178 t = NO_ATA_1X (don't allow ATA(12) and ATA(16)
4179 commands, uas only);
4180 u = IGNORE_UAS (don't bind to the uas driver);
4181 w = NO_WP_DETECT (don't test whether the
4182 medium is write-protected).
4183 Example: quirks=0419:aaf5:rl,0421:0433:rc
4185 user_debug= [KNL,ARM]
4187 See arch/arm/Kconfig.debug help text.
4188 1 - undefined instruction events
4190 4 - invalid data aborts
4193 Example: user_debug=31
4196 [X86] Flags controlling user PTE allocations.
4198 nohigh = do not allocate PTE pages in
4199 HIGHMEM regardless of setting
4203 On X86_32, this is an alias for vdso32=. Otherwise:
4205 vdso=1: enable VDSO (the default)
4206 vdso=0: disable VDSO mapping
4208 vdso32= [X86] Control the 32-bit vDSO
4209 vdso32=1: enable 32-bit VDSO
4210 vdso32=0 or vdso32=2: disable 32-bit VDSO
4212 See the help text for CONFIG_COMPAT_VDSO for more
4213 details. If CONFIG_COMPAT_VDSO is set, the default is
4214 vdso32=0; otherwise, the default is vdso32=1.
4216 For compatibility with older kernels, vdso32=2 is an
4219 Try vdso32=0 if you encounter an error that says:
4220 dl_main: Assertion `(void *) ph->p_vaddr == _rtld_local._dl_sysinfo_dso' failed!
4223 vector=percpu: enable percpu vector domain
4225 video= [FB] Frame buffer configuration
4226 See Documentation/fb/modedb.txt.
4228 video.brightness_switch_enabled= [0,1]
4229 If set to 1, on receiving an ACPI notify event
4230 generated by hotkey, video driver will adjust brightness
4231 level and then send out the event to user space through
4232 the allocated input device; If set to 0, video driver
4233 will only send out the event without touching backlight
4238 [VMMIO] Memory mapped virtio (platform) device.
4240 <size>@<baseaddr>:<irq>[:<id>]
4242 <size> := size (can use standard suffixes
4244 <baseaddr> := physical base address
4245 <irq> := interrupt number (as passed to
4247 <id> := (optional) platform device id
4249 virtio_mmio.device=1K@0x100b0000:48:7
4251 Can be used multiple times for multiple devices.
4253 vga= [BOOT,X86-32] Select a particular video mode
4254 See Documentation/x86/boot.txt and
4255 Documentation/svga.txt.
4256 Use vga=ask for menu.
4257 This is actually a boot loader parameter; the value is
4258 passed to the kernel using a special protocol.
4260 vmalloc=nn[KMG] [KNL,BOOT] Forces the vmalloc area to have an exact
4261 size of <nn>. This can be used to increase the
4262 minimum size (128MB on x86). It can also be used to
4263 decrease the size and leave more room for directly
4266 vmhalt= [KNL,S390] Perform z/VM CP command after system halt.
4269 vmpanic= [KNL,S390] Perform z/VM CP command after kernel panic.
4272 vmpoff= [KNL,S390] Perform z/VM CP command after power off.
4276 Controls the behavior of vsyscalls (i.e. calls to
4277 fixed addresses of 0xffffffffff600x00 from legacy
4278 code). Most statically-linked binaries and older
4279 versions of glibc use these calls. Because these
4280 functions are at fixed addresses, they make nice
4281 targets for exploits that can control RIP.
4283 emulate [default] Vsyscalls turn into traps and are
4284 emulated reasonably safely.
4286 native Vsyscalls are native syscall instructions.
4287 This is a little bit faster than trapping
4288 and makes a few dynamic recompilers work
4289 better than they would in emulation mode.
4290 It also makes exploits much easier to write.
4292 none Vsyscalls don't work at all. This makes
4293 them quite hard to use for exploits but
4294 might break your system.
4296 vt.color= [VT] Default text color.
4297 Format: 0xYX, X = foreground, Y = background.
4298 Default: 0x07 = light gray on black.
4300 vt.cur_default= [VT] Default cursor shape.
4301 Format: 0xCCBBAA, where AA, BB, and CC are the same as
4302 the parameters of the <Esc>[?A;B;Cc escape sequence;
4303 see VGA-softcursor.txt. Default: 2 = underline.
4305 vt.default_blu= [VT]
4306 Format: <blue0>,<blue1>,<blue2>,...,<blue15>
4307 Change the default blue palette of the console.
4308 This is a 16-member array composed of values
4311 vt.default_grn= [VT]
4312 Format: <green0>,<green1>,<green2>,...,<green15>
4313 Change the default green palette of the console.
4314 This is a 16-member array composed of values
4317 vt.default_red= [VT]
4318 Format: <red0>,<red1>,<red2>,...,<red15>
4319 Change the default red palette of the console.
4320 This is a 16-member array composed of values
4326 Set system-wide default UTF-8 mode for all tty's.
4327 Default is 1, i.e. UTF-8 mode is enabled for all
4328 newly opened terminals.
4330 vt.global_cursor_default=
4333 Set system-wide default for whether a cursor
4334 is shown on new VTs. Default is -1,
4335 i.e. cursors will be created by default unless
4336 overridden by individual drivers. 0 will hide
4337 cursors, 1 will display them.
4339 vt.italic= [VT] Default color for italic text; 0-15.
4342 vt.underline= [VT] Default color for underlined text; 0-15.
4345 watchdog timers [HW,WDT] For information on watchdog timers,
4346 see Documentation/watchdog/watchdog-parameters.txt
4347 or other driver-specific files in the
4348 Documentation/watchdog/ directory.
4350 workqueue.watchdog_thresh=
4351 If CONFIG_WQ_WATCHDOG is configured, workqueue can
4352 warn stall conditions and dump internal state to
4353 help debugging. 0 disables workqueue stall
4354 detection; otherwise, it's the stall threshold
4355 duration in seconds. The default value is 30 and
4356 it can be updated at runtime by writing to the
4357 corresponding sysfs file.
4359 workqueue.disable_numa
4360 By default, all work items queued to unbound
4361 workqueues are affine to the NUMA nodes they're
4362 issued on, which results in better behavior in
4363 general. If NUMA affinity needs to be disabled for
4364 whatever reason, this option can be used. Note
4365 that this also can be controlled per-workqueue for
4366 workqueues visible under /sys/bus/workqueue/.
4368 workqueue.power_efficient
4369 Per-cpu workqueues are generally preferred because
4370 they show better performance thanks to cache
4371 locality; unfortunately, per-cpu workqueues tend to
4372 be more power hungry than unbound workqueues.
4374 Enabling this makes the per-cpu workqueues which
4375 were observed to contribute significantly to power
4376 consumption unbound, leading to measurably lower
4377 power usage at the cost of small performance
4380 The default value of this parameter is determined by
4381 the config option CONFIG_WQ_POWER_EFFICIENT_DEFAULT.
4383 workqueue.debug_force_rr_cpu
4384 Workqueue used to implicitly guarantee that work
4385 items queued without explicit CPU specified are put
4386 on the local CPU. This guarantee is no longer true
4387 and while local CPU is still preferred work items
4388 may be put on foreign CPUs. This debug option
4389 forces round-robin CPU selection to flush out
4390 usages which depend on the now broken guarantee.
4391 When enabled, memory and cache locality will be
4394 x2apic_phys [X86-64,APIC] Use x2apic physical mode instead of
4395 default x2apic cluster mode on platforms
4398 x86_intel_mid_timer= [X86-32,APBT]
4399 Choose timer option for x86 Intel MID platform.
4400 Two valid options are apbt timer only and lapic timer
4401 plus one apbt timer for broadcast timer.
4402 x86_intel_mid_timer=apbt_only | lapic_and_apbt
4404 xen_512gb_limit [KNL,X86-64,XEN]
4405 Restricts the kernel running paravirtualized under Xen
4406 to use only up to 512 GB of RAM. The reason to do so is
4407 crash analysis tools and Xen tools for doing domain
4408 save/restore/migration must be enabled to handle larger
4411 xen_emul_unplug= [HW,X86,XEN]
4412 Unplug Xen emulated devices
4413 Format: [unplug0,][unplug1]
4414 ide-disks -- unplug primary master IDE devices
4415 aux-ide-disks -- unplug non-primary-master IDE devices
4416 nics -- unplug network devices
4417 all -- unplug all emulated devices (NICs and IDE disks)
4418 unnecessary -- unplugging emulated devices is
4419 unnecessary even if the host did not respond to
4421 never -- do not unplug even if version check succeeds
4423 xen_nopvspin [X86,XEN]
4424 Disables the ticketlock slowpath using Xen PV
4428 Disables the PV optimizations forcing the HVM guest to
4429 run as generic HVM guest with no PV drivers.
4431 xirc2ps_cs= [NET,PCMCIA]
4433 <irq>,<irq_mask>,<io>,<full_duplex>,<do_sound>,<lockup_hack>[,<irq2>[,<irq3>[,<irq4>]]]
4435 ______________________________________________________________________
4439 Add more DRM drivers.