1 acpi= [HW,ACPI,X86,ARM64]
2 Advanced Configuration and Power Interface
3 Format: { force | on | off | strict | noirq | rsdt |
5 force -- enable ACPI if default was off
6 on -- enable ACPI but allow fallback to DT [arm64]
7 off -- disable ACPI if default was on
8 noirq -- do not use ACPI for IRQ routing
9 strict -- Be less tolerant of platforms that are not
10 strictly ACPI specification compliant.
11 rsdt -- prefer RSDT over (default) XSDT
12 copy_dsdt -- copy DSDT to memory
13 For ARM64, ONLY "acpi=off", "acpi=on" or "acpi=force"
16 See also Documentation/power/runtime_pm.rst, pci=noacpi
18 acpi_apic_instance= [ACPI, IOAPIC]
20 2: use 2nd APIC table, if available
21 1,0: use 1st APIC table
24 acpi_backlight= [HW,ACPI]
25 { vendor | video | native | none }
26 If set to vendor, prefer vendor-specific driver
27 (e.g. thinkpad_acpi, sony_acpi, etc.) instead
28 of the ACPI video.ko driver.
29 If set to video, use the ACPI video.ko driver.
30 If set to native, use the device's native backlight mode.
31 If set to none, disable the ACPI backlight interface.
33 acpi_force_32bit_fadt_addr
34 force FADT to use 32 bit addresses rather than the
35 64 bit X_* addresses. Some firmware have broken 64
36 bit addresses for force ACPI ignore these and use
37 the older legacy 32 bit addresses.
39 acpica_no_return_repair [HW, ACPI]
40 Disable AML predefined validation mechanism
41 This mechanism can repair the evaluation result to make
42 the return objects more ACPI specification compliant.
43 This option is useful for developers to identify the
44 root cause of an AML interpreter issue when the issue
45 has something to do with the repair mechanism.
47 acpi.debug_layer= [HW,ACPI,ACPI_DEBUG]
48 acpi.debug_level= [HW,ACPI,ACPI_DEBUG]
50 CONFIG_ACPI_DEBUG must be enabled to produce any ACPI
51 debug output. Bits in debug_layer correspond to a
52 _COMPONENT in an ACPI source file, e.g.,
53 #define _COMPONENT ACPI_EVENTS
54 Bits in debug_level correspond to a level in
55 ACPI_DEBUG_PRINT statements, e.g.,
56 ACPI_DEBUG_PRINT((ACPI_DB_INFO, ...
57 The debug_level mask defaults to "info". See
58 Documentation/firmware-guide/acpi/debug.rst for more information about
59 debug layers and levels.
61 Enable processor driver info messages:
62 acpi.debug_layer=0x20000000
63 Enable AML "Debug" output, i.e., stores to the Debug
64 object while interpreting AML:
65 acpi.debug_layer=0xffffffff acpi.debug_level=0x2
66 Enable all messages related to ACPI hardware:
67 acpi.debug_layer=0x2 acpi.debug_level=0xffffffff
69 Some values produce so much output that the system is
70 unusable. The "log_buf_len" parameter may be useful
71 if you need to capture more output.
73 acpi_enforce_resources= [ACPI]
75 Check for resource conflicts between native drivers
76 and ACPI OperationRegions (SystemIO and SystemMemory
77 only). IO ports and memory declared in ACPI might be
78 used by the ACPI subsystem in arbitrary AML code and
79 can interfere with legacy drivers.
80 strict (default): access to resources claimed by ACPI
81 is denied; legacy drivers trying to access reserved
82 resources will fail to bind to device using them.
83 lax: access to resources claimed by ACPI is allowed;
84 legacy drivers trying to access reserved resources
85 will bind successfully but a warning message is logged.
86 no: ACPI OperationRegions are not marked as reserved,
87 no further checks are performed.
89 acpi_force_table_verification [HW,ACPI]
90 Enable table checksum verification during early stage.
91 By default, this is disabled due to x86 early mapping
94 acpi_irq_balance [HW,ACPI]
95 ACPI will balance active IRQs
98 acpi_irq_nobalance [HW,ACPI]
99 ACPI will not move active IRQs (default)
102 acpi_irq_isa= [HW,ACPI] If irq_balance, mark listed IRQs used by ISA
103 Format: <irq>,<irq>...
105 acpi_irq_pci= [HW,ACPI] If irq_balance, clear listed IRQs for
107 Format: <irq>,<irq>...
109 acpi_mask_gpe= [HW,ACPI]
110 Due to the existence of _Lxx/_Exx, some GPEs triggered
111 by unsupported hardware/firmware features can result in
112 GPE floodings that cannot be automatically disabled by
114 This facility can be used to prevent such uncontrolled
116 Format: <byte> or <bitmap-list>
118 acpi_no_auto_serialize [HW,ACPI]
119 Disable auto-serialization of AML methods
120 AML control methods that contain the opcodes to create
121 named objects will be marked as "Serialized" by the
122 auto-serialization feature.
123 This feature is enabled by default.
124 This option allows to turn off the feature.
126 acpi_no_memhotplug [ACPI] Disable memory hotplug. Useful for kdump
129 acpi_no_static_ssdt [HW,ACPI]
130 Disable installation of static SSDTs at early boot time
131 By default, SSDTs contained in the RSDT/XSDT will be
132 installed automatically and they will appear under
133 /sys/firmware/acpi/tables.
134 This option turns off this feature.
135 Note that specifying this option does not affect
136 dynamic table installation which will install SSDT
137 tables to /sys/firmware/acpi/tables/dynamic.
139 acpi_no_watchdog [HW,ACPI,WDT]
140 Ignore the ACPI-based watchdog interface (WDAT) and let
141 a native driver control the watchdog device instead.
143 acpi_rsdp= [ACPI,EFI,KEXEC]
144 Pass the RSDP address to the kernel, mostly used
145 on machines running EFI runtime service to boot the
146 second kernel for kdump.
148 acpi_os_name= [HW,ACPI] Tell ACPI BIOS the name of the OS
149 Format: To spoof as Windows 98: ="Microsoft Windows"
151 acpi_rev_override [ACPI] Override the _REV object to return 5 (instead
152 of 2 which is mandated by ACPI 6) as the supported ACPI
153 specification revision (when using this switch, it may
154 be necessary to carry out a cold reboot _twice_ in a
155 row to make it take effect on the platform firmware).
157 acpi_osi= [HW,ACPI] Modify list of supported OS interface strings
158 acpi_osi="string1" # add string1
159 acpi_osi="!string2" # remove string2
160 acpi_osi=!* # remove all strings
161 acpi_osi=! # disable all built-in OS vendor
163 acpi_osi=!! # enable all built-in OS vendor
165 acpi_osi= # disable all strings
167 'acpi_osi=!' can be used in combination with single or
168 multiple 'acpi_osi="string1"' to support specific OS
169 vendor string(s). Note that such command can only
170 affect the default state of the OS vendor strings, thus
171 it cannot affect the default state of the feature group
172 strings and the current state of the OS vendor strings,
173 specifying it multiple times through kernel command line
174 is meaningless. This command is useful when one do not
175 care about the state of the feature group strings which
176 should be controlled by the OSPM.
178 1. 'acpi_osi=! acpi_osi="Windows 2000"' is equivalent
179 to 'acpi_osi="Windows 2000" acpi_osi=!', they all
180 can make '_OSI("Windows 2000")' TRUE.
182 'acpi_osi=' cannot be used in combination with other
183 'acpi_osi=' command lines, the _OSI method will not
184 exist in the ACPI namespace. NOTE that such command can
185 only affect the _OSI support state, thus specifying it
186 multiple times through kernel command line is also
189 1. 'acpi_osi=' can make 'CondRefOf(_OSI, Local1)'
192 'acpi_osi=!*' can be used in combination with single or
193 multiple 'acpi_osi="string1"' to support specific
194 string(s). Note that such command can affect the
195 current state of both the OS vendor strings and the
196 feature group strings, thus specifying it multiple times
197 through kernel command line is meaningful. But it may
198 still not able to affect the final state of a string if
199 there are quirks related to this string. This command
200 is useful when one want to control the state of the
201 feature group strings to debug BIOS issues related to
204 1. 'acpi_osi="Module Device" acpi_osi=!*' can make
205 '_OSI("Module Device")' FALSE.
206 2. 'acpi_osi=!* acpi_osi="Module Device"' can make
207 '_OSI("Module Device")' TRUE.
208 3. 'acpi_osi=! acpi_osi=!* acpi_osi="Windows 2000"' is
210 'acpi_osi=!* acpi_osi=! acpi_osi="Windows 2000"'
212 'acpi_osi=!* acpi_osi="Windows 2000" acpi_osi=!',
213 they all will make '_OSI("Windows 2000")' TRUE.
216 Override the pmtimer bug detection: force the kernel
217 to assume that this machine's pmtimer latches its value
218 and always returns good values.
220 acpi_sci= [HW,ACPI] ACPI System Control Interrupt trigger mode
221 Format: { level | edge | high | low }
223 acpi_skip_timer_override [HW,ACPI]
224 Recognize and ignore IRQ0/pin2 Interrupt Override.
225 For broken nForce2 BIOS resulting in XT-PIC timer.
227 acpi_sleep= [HW,ACPI] Sleep options
228 Format: { s3_bios, s3_mode, s3_beep, s4_hwsig,
229 s4_nohwsig, old_ordering, nonvs,
230 sci_force_enable, nobl }
231 See Documentation/power/video.rst for information on
233 s3_beep is for debugging; it makes the PC's speaker beep
234 as soon as the kernel's real-mode entry point is called.
235 s4_hwsig causes the kernel to check the ACPI hardware
236 signature during resume from hibernation, and gracefully
237 refuse to resume if it has changed. This complies with
238 the ACPI specification but not with reality, since
239 Windows does not do this and many laptops do change it
240 on docking. So the default behaviour is to allow resume
241 and simply warn when the signature changes, unless the
242 s4_hwsig option is enabled.
243 s4_nohwsig prevents ACPI hardware signature from being
244 used (or even warned about) during resume.
245 old_ordering causes the ACPI 1.0 ordering of the _PTS
246 control method, with respect to putting devices into
247 low power states, to be enforced (the ACPI 2.0 ordering
248 of _PTS is used by default).
249 nonvs prevents the kernel from saving/restoring the
250 ACPI NVS memory during suspend/hibernation and resume.
251 sci_force_enable causes the kernel to set SCI_EN directly
252 on resume from S1/S3 (which is against the ACPI spec,
253 but some broken systems don't work without it).
254 nobl causes the internal blacklist of systems known to
255 behave incorrectly in some ways with respect to system
256 suspend and resume to be ignored (use wisely).
258 acpi_use_timer_override [HW,ACPI]
259 Use timer override. For some broken Nvidia NF5 boards
260 that require a timer override, but don't have HPET
262 add_efi_memmap [EFI; X86] Include EFI memory map in
263 kernel's map of available physical RAM.
266 { off | try_unsupported }
267 off: disable AGP support
268 try_unsupported: try to drive unsupported chipsets
269 (may crash computer or cause data corruption)
272 See Documentation/sound/alsa-configuration.rst
275 Allow the default userspace alignment fault handler
276 behaviour to be specified. Bit 0 enables warnings,
277 bit 1 enables fixups, and bit 2 sends a segfault.
279 align_va_addr= [X86-64]
280 Align virtual addresses by clearing slice [14:12] when
281 allocating a VMA at process creation time. This option
282 gives you up to 3% performance improvement on AMD F15h
283 machines (where it is enabled by default) for a
284 CPU-intensive style benchmark, and it can vary highly in
285 a microbenchmark depending on workload and compiler.
287 32: only for 32-bit processes
288 64: only for 64-bit processes
289 on: enable for both 32- and 64-bit processes
290 off: disable for both 32- and 64-bit processes
292 alloc_snapshot [FTRACE]
293 Allocate the ftrace snapshot buffer on boot up when the
294 main buffer is allocated. This is handy if debugging
295 and you need to use tracing_snapshot() on boot up, and
296 do not want to use tracing_snapshot_alloc() as it needs
297 to be done where GFP_KERNEL allocations are allowed.
299 allow_mismatched_32bit_el0 [ARM64]
300 Allow execve() of 32-bit applications and setting of the
301 PER_LINUX32 personality on systems where only a strict
302 subset of the CPUs support 32-bit EL0. When this
303 parameter is present, the set of CPUs supporting 32-bit
304 EL0 is indicated by /sys/devices/system/cpu/aarch32_el0
305 and hot-unplug operations may be restricted.
307 See Documentation/arm64/asymmetric-32bit.rst for more
310 amd_iommu= [HW,X86-64]
311 Pass parameters to the AMD IOMMU driver in the system.
313 fullflush - Deprecated, equivalent to iommu.strict=1
314 off - do not initialize any AMD IOMMU found in
316 force_isolation - Force device isolation for all
317 devices. The IOMMU driver is not
318 allowed anymore to lift isolation
319 requirements as needed. This option
320 does not override iommu=pt
321 force_enable - Force enable the IOMMU on platforms known
322 to be buggy with IOMMU enabled. Use this
325 amd_iommu_dump= [HW,X86-64]
326 Enable AMD IOMMU driver option to dump the ACPI table
327 for AMD IOMMU. With this option enabled, AMD IOMMU
328 driver will print ACPI tables for AMD IOMMU during
329 IOMMU initialization.
331 amd_iommu_intr= [HW,X86-64]
332 Specifies one of the following AMD IOMMU interrupt
334 legacy - Use legacy interrupt remapping mode.
335 vapic - Use virtual APIC mode, which allows IOMMU
336 to inject interrupts directly into guest.
337 This mode requires kvm-amd.avic=1.
338 (Default when IOMMU HW support is present.)
340 amijoy.map= [HW,JOY] Amiga joystick support
341 Map of devices attached to JOY0DAT and JOY1DAT
343 See also Documentation/input/joydev/joystick.rst
345 analog.map= [HW,JOY] Analog joystick and gamepad support
346 Specifies type or capabilities of an analog joystick
347 connected to one of 16 gameports
348 Format: <type1>,<type2>,..<type16>
351 Power management functions (SPARCstation-4/5 + deriv.)
353 Disable APC CPU standby support. SPARCstation-Fox does
354 not play well with APC CPU idle - disable it if you have
355 APC and your system crashes randomly.
357 apic= [APIC,X86] Advanced Programmable Interrupt Controller
358 Change the output verbosity while booting
359 Format: { quiet (default) | verbose | debug }
360 Change the amount of debugging information output
361 when initialising the APIC and IO-APIC components.
362 For X86-32, this can also be used to specify an APIC
364 Format: apic=driver_name
365 Examples: apic=bigsmp
367 apic_extnmi= [APIC,X86] External NMI delivery setting
368 Format: { bsp (default) | all | none }
369 bsp: External NMI is delivered only to CPU 0
370 all: External NMIs are broadcast to all CPUs as a
372 none: External NMI is masked for all CPUs. This is
373 useful so that a dump capture kernel won't be
377 See Documentation/networking/ipv6.rst.
379 show_lapic= [APIC,X86] Advanced Programmable Interrupt Controller
380 Limit apic dumping. The parameter defines the maximal
381 number of local apics being dumped. Also it is possible
382 to set it to "all" by meaning -- no limit here.
383 Format: { 1 (default) | 2 | ... | all }.
384 The parameter valid if only apic=debug or
385 apic=verbose is specified.
386 Example: apic=debug show_lapic=all
388 apm= [APM] Advanced Power Management
389 See header of arch/x86/kernel/apm_32.c.
391 arcrimi= [HW,NET] ARCnet - "RIM I" (entirely mem-mapped) cards
392 Format: <io>,<irq>,<nodeID>
394 arm64.nobti [ARM64] Unconditionally disable Branch Target
395 Identification support
397 arm64.nopauth [ARM64] Unconditionally disable Pointer Authentication
400 arm64.nomte [ARM64] Unconditionally disable Memory Tagging Extension
405 atarimouse= [HW,MOUSE] Atari Mouse
407 atkbd.extra= [HW] Enable extra LEDs and keys on IBM RapidAccess,
408 EzKey and similar keyboards
410 atkbd.reset= [HW] Reset keyboard during initialization
412 atkbd.set= [HW] Select keyboard code set
413 Format: <int> (2 = AT (default), 3 = PS/2)
415 atkbd.scroll= [HW] Enable scroll wheel on MS Office and similar
418 atkbd.softraw= [HW] Choose between synthetic and real raw mode
419 Format: <bool> (0 = real, 1 = synthetic (default))
421 atkbd.softrepeat= [HW]
422 Use software keyboard repeat
424 audit= [KNL] Enable the audit sub-system
425 Format: { "0" | "1" | "off" | "on" }
426 0 | off - kernel audit is disabled and can not be
427 enabled until the next reboot
428 unset - kernel audit is initialized but disabled and
429 will be fully enabled by the userspace auditd.
430 1 | on - kernel audit is initialized and partially
431 enabled, storing at most audit_backlog_limit
432 messages in RAM until it is fully enabled by the
436 audit_backlog_limit= [KNL] Set the audit queue size limit.
437 Format: <int> (must be >=0)
440 bau= [X86_UV] Enable the BAU on SGI UV. The default
441 behavior is to disable the BAU (i.e. bau=0).
442 Format: { "0" | "1" }
445 unset - Disable the BAU.
447 baycom_epp= [HW,AX25]
450 baycom_par= [HW,AX25] BayCom Parallel Port AX.25 Modem
452 See header of drivers/net/hamradio/baycom_par.c.
454 baycom_ser_fdx= [HW,AX25]
455 BayCom Serial Port AX.25 Modem (Full Duplex Mode)
456 Format: <io>,<irq>,<mode>[,<baud>]
457 See header of drivers/net/hamradio/baycom_ser_fdx.c.
459 baycom_ser_hdx= [HW,AX25]
460 BayCom Serial Port AX.25 Modem (Half Duplex Mode)
461 Format: <io>,<irq>,<mode>
462 See header of drivers/net/hamradio/baycom_ser_hdx.c.
464 blkdevparts= Manual partition parsing of block device(s) for
465 embedded devices based on command line input.
466 See Documentation/block/cmdline-partition.rst
468 boot_delay= Milliseconds to delay each printk during boot.
469 Values larger than 10 seconds (10000) are changed to
474 Extended command line options can be added to an initrd
475 and this will cause the kernel to look for it.
477 See Documentation/admin-guide/bootconfig.rst
480 Disable BERT OS support on buggy BIOSes.
482 bgrt_disable [ACPI][X86]
483 Disable BGRT to avoid flickering OEM logo.
485 bttv.card= [HW,V4L] bttv (bt848 + bt878 based grabber cards)
486 bttv.radio= Most important insmod options are available as
488 bttv.pll= See Documentation/admin-guide/media/bttv.rst
491 bulk_remove=off [PPC] This parameter disables the use of the pSeries
492 firmware feature for flushing multiple hpte entries
495 c101= [NET] Moxa C101 synchronous serial card
497 cachesize= [BUGS=X86-32] Override level 2 CPU cache size detection.
498 Sometimes CPU hardware bugs make them report the cache
499 size incorrectly. The kernel will attempt work arounds
500 to fix known problems, but for some CPUs it is not
501 possible to determine what the correct size should be.
502 This option provides an override for these situations.
505 [NET] Specifies amount of time (in seconds) that
506 the kernel should wait for a network carrier. By default
507 it waits 120 seconds.
509 ca_keys= [KEYS] This parameter identifies a specific key(s) on
510 the system trusted keyring to be used for certificate
512 format: { id:<keyid> | builtin }
514 cca= [MIPS] Override the kernel pages' cache coherency
515 algorithm. Accepted values range from 0 to 7
516 inclusive. See arch/mips/include/asm/pgtable-bits.h
517 for platform specific values (SB1, Loongson3 and
520 ccw_timeout_log [S390]
521 See Documentation/s390/common_io.rst for details.
523 cgroup_disable= [KNL] Disable a particular controller or optional feature
524 Format: {name of the controller(s) or feature(s) to disable}
525 The effects of cgroup_disable=foo are:
526 - foo isn't auto-mounted if you mount all cgroups in
528 - foo isn't visible as an individually mountable
530 - if foo is an optional feature then the feature is
531 disabled and corresponding cgroup files are not
533 {Currently only "memory" controller deal with this and
534 cut the overhead, others just disable the usage. So
535 only cgroup_disable=memory is actually worthy}
536 Specifying "pressure" disables per-cgroup pressure
537 stall information accounting feature
539 cgroup_no_v1= [KNL] Disable cgroup controllers and named hierarchies in v1
540 Format: { { controller | "all" | "named" }
541 [,{ controller | "all" | "named" }...] }
542 Like cgroup_disable, but only applies to cgroup v1;
543 the blacklisted controllers remain available in cgroup2.
544 "all" blacklists all controllers and "named" disables
545 named mounts. Specifying both "all" and "named" disables
548 cgroup.memory= [KNL] Pass options to the cgroup memory controller.
550 nosocket -- Disable socket memory accounting.
551 nokmem -- Disable kernel memory accounting.
553 checkreqprot [SELINUX] Set initial checkreqprot flag value.
554 Format: { "0" | "1" }
555 See security/selinux/Kconfig help text.
556 0 -- check protection applied by kernel (includes
557 any implied execute protection).
558 1 -- check protection requested by application.
559 Default value is set via a kernel config option.
560 Value can be changed at runtime via
561 /sys/fs/selinux/checkreqprot.
562 Setting checkreqprot to 1 is deprecated.
565 See Documentation/s390/common_io.rst for details.
568 Prevents the clock framework from automatically gating
569 clocks that have not been explicitly enabled by a Linux
570 device driver but are enabled in hardware at reset or
571 by the bootloader/firmware. Note that this does not
572 force such clocks to be always-on nor does it reserve
573 those clocks in any way. This parameter is useful for
574 debug and development, but should not be needed on a
575 platform with proper driver support. For more
576 information, see Documentation/driver-api/clk.rst.
578 clock= [BUGS=X86-32, HW] gettimeofday clocksource override.
580 Forces specified clocksource (if available) to be used
581 when calculating gettimeofday(). If specified
582 clocksource is not available, it defaults to PIT.
583 Format: { pit | tsc | cyclone | pmtmr }
585 clocksource= Override the default clocksource
587 Override the default clocksource and use the clocksource
588 with the name specified.
589 Some clocksource names to choose from, depending on
591 [all] jiffies (this is the base, fallback clocksource)
593 [ARM] imx_timer1,OSTS,netx_timer,mpu_timer2,
594 pxa_timer,timer3,32k_counter,timer0_1
595 [X86-32] pit,hpet,tsc;
596 scx200_hrt on Geode; cyclone on IBM x440
604 clocksource.arm_arch_timer.evtstrm=
607 Enable/disable the eventstream feature of the ARM
608 architected timer so that code using WFE-based polling
609 loops can be debugged more effectively on production
612 clocksource.max_cswd_read_retries= [KNL]
613 Number of clocksource_watchdog() retries due to
614 external delays before the clock will be marked
615 unstable. Defaults to two retries, that is,
616 three attempts to read the clock under test.
618 clocksource.verify_n_cpus= [KNL]
619 Limit the number of CPUs checked for clocksources
620 marked with CLOCK_SOURCE_VERIFY_PERCPU that
621 are marked unstable due to excessive skew.
622 A negative value says to check all CPUs, while
623 zero says not to check any. Values larger than
624 nr_cpu_ids are silently truncated to nr_cpu_ids.
625 The actual CPUs are chosen randomly, with
626 no replacement if the same CPU is chosen twice.
628 clocksource-wdtest.holdoff= [KNL]
629 Set the time in seconds that the clocksource
630 watchdog test waits before commencing its tests.
631 Defaults to zero when built as a module and to
632 10 seconds when built into the kernel.
634 clearcpuid=BITNUM[,BITNUM...] [X86]
635 Disable CPUID feature X for the kernel. See
636 arch/x86/include/asm/cpufeatures.h for the valid bit
637 numbers. Note the Linux specific bits are not necessarily
638 stable over kernel options, but the vendor specific
640 Also note that user programs calling CPUID directly
641 or using the feature without checking anything
642 will still see it. This just prevents it from
643 being used by the kernel or shown in /proc/cpuinfo.
644 Also note the kernel might malfunction if you disable
647 cma=nn[MG]@[start[MG][-end[MG]]]
649 Sets the size of kernel global memory area for
650 contiguous memory allocations and optionally the
651 placement constraint by the physical address range of
652 memory allocations. A value of 0 disables CMA
653 altogether. For more information, see
654 kernel/dma/contiguous.c
658 Sets the size of kernel per-numa memory area for
659 contiguous memory allocations. A value of 0 disables
660 per-numa CMA altogether. And If this option is not
661 specificed, the default value is 0.
662 With per-numa CMA enabled, DMA users on node nid will
663 first try to allocate buffer from the pernuma area
664 which is located in node nid, if the allocation fails,
665 they will fallback to the global default memory area.
667 cmo_free_hint= [PPC] Format: { yes | no }
668 Specify whether pages are marked as being inactive
669 when they are freed. This is used in CMO environments
670 to determine OS memory pressure for page stealing by
674 coherent_pool=nn[KMG] [ARM,KNL]
675 Sets the size of memory pool for coherent, atomic dma
676 allocations, by default set to 256K.
678 com20020= [HW,NET] ARCnet - COM20020 chipset
680 <io>[,<irq>[,<nodeID>[,<backplane>[,<ckp>[,<timeout>]]]]]
682 com90io= [HW,NET] ARCnet - COM90xx chipset (IO-mapped buffers)
686 ARCnet - COM90xx chipset (memory-mapped buffers)
687 Format: <io>[,<irq>[,<memstart>]]
689 condev= [HW,S390] console device
692 console= [KNL] Output console device and options.
694 tty<n> Use the virtual console device <n>.
698 Use the specified serial port. The options are of
699 the form "bbbbpnf", where "bbbb" is the baud rate,
700 "p" is parity ("n", "o", or "e"), "n" is number of
701 bits, and "f" is flow control ("r" for RTS or
702 omit it). Default is "9600n8".
704 See Documentation/admin-guide/serial-console.rst for more
706 Documentation/networking/netconsole.rst for an
709 uart[8250],io,<addr>[,options]
710 uart[8250],mmio,<addr>[,options]
711 uart[8250],mmio16,<addr>[,options]
712 uart[8250],mmio32,<addr>[,options]
713 uart[8250],0x<addr>[,options]
714 Start an early, polled-mode console on the 8250/16550
715 UART at the specified I/O port or MMIO address,
716 switching to the matching ttyS device later.
717 MMIO inter-register address stride is either 8-bit
718 (mmio), 16-bit (mmio16), or 32-bit (mmio32).
719 If none of [io|mmio|mmio16|mmio32], <addr> is assumed
720 to be equivalent to 'mmio'. 'options' are specified in
721 the same format described for ttyS above; if unspecified,
722 the h/w is not re-initialized.
724 hvc<n> Use the hypervisor console device <n>. This is for
725 both Xen and PowerPC hypervisors.
728 Use to disable console output, i.e., to have kernel
729 console messages discarded.
730 This must be the only console= parameter used on the
733 If the device connected to the port is not a TTY but a braille
734 device, prepend "brl," before the device type, for instance
736 For now, only VisioBraille is supported.
739 [KNL] Change console messages format
741 By default we print messages on consoles in
742 "[time stamp] text\n" format (time stamp may not be
743 printed, depending on CONFIG_PRINTK_TIME or
744 `printk_time' param).
746 Switch to syslog format: "<%u>[time stamp] text\n"
747 IOW, each message will have a facility and loglevel
748 prefix. The format is similar to one used by syslog()
749 syscall, or to executing "dmesg -S --raw" or to reading
752 consoleblank= [KNL] The console blank (screen saver) timeout in
753 seconds. A value of 0 disables the blank timer.
757 [KNL] Change the default value for
758 /proc/<pid>/coredump_filter.
759 See also Documentation/filesystems/proc.rst.
761 coresight_cpu_debug.enable
764 Enable/disable the CPU sampling based debugging.
765 0: default value, disable debugging
766 1: enable debugging at boot time
768 cpuidle.off=1 [CPU_IDLE]
769 disable the cpuidle sub-system
772 [CPU_IDLE] Name of the cpuidle governor to use.
774 cpufreq.off=1 [CPU_FREQ]
775 disable the cpufreq sub-system
777 cpufreq.default_governor=
778 [CPU_FREQ] Name of the default cpufreq governor or
779 policy to use. This governor must be registered in the
780 kernel before the cpufreq driver probes.
783 [X86] Delay for N microsec between assert and de-assert
784 of APIC INIT to start processors. This delay occurs
785 on every CPU online, such as boot, and resume from suspend.
788 cpcihp_generic= [HW,PCI] Generic port I/O CompactPCI driver
790 <first_slot>,<last_slot>,<port>,<enum_bit>[,<debug>]
792 crashkernel=size[KMG][@offset[KMG]]
793 [KNL] Using kexec, Linux can switch to a 'crash kernel'
794 upon panic. This parameter reserves the physical
795 memory region [offset, offset + size] for that kernel
796 image. If '@offset' is omitted, then a suitable offset
797 is selected automatically.
798 [KNL, X86-64] Select a region under 4G first, and
799 fall back to reserve region above 4G when '@offset'
800 hasn't been specified.
801 See Documentation/admin-guide/kdump/kdump.rst for further details.
803 crashkernel=range1:size1[,range2:size2,...][@offset]
804 [KNL] Same as above, but depends on the memory
805 in the running system. The syntax of range is
806 start-[end] where start and end are both
807 a memory unit (amount[KMG]). See also
808 Documentation/admin-guide/kdump/kdump.rst for an example.
810 crashkernel=size[KMG],high
811 [KNL, X86-64] range could be above 4G. Allow kernel
812 to allocate physical memory region from top, so could
813 be above 4G if system have more than 4G ram installed.
814 Otherwise memory region will be allocated below 4G, if
816 It will be ignored if crashkernel=X is specified.
817 crashkernel=size[KMG],low
818 [KNL, X86-64] range under 4G. When crashkernel=X,high
819 is passed, kernel could allocate physical memory region
820 above 4G, that cause second kernel crash on system
821 that require some amount of low memory, e.g. swiotlb
822 requires at least 64M+32K low memory, also enough extra
823 low memory is needed to make sure DMA buffers for 32-bit
824 devices won't run out. Kernel would try to allocate at
825 at least 256M below 4G automatically.
826 This one let user to specify own low range under 4G
827 for second kernel instead.
828 0: to disable low allocation.
829 It will be ignored when crashkernel=X,high is not used
830 or memory reserved is below 4G.
833 [KNL] Disable crypto self-tests
838 cs89x0_media= [HW,NET]
839 Format: { rj45 | aui | bnc }
841 csdlock_debug= [KNL] Enable debug add-ons of cross-CPU function call
842 handling. When switched on, additional debug data is
843 printed to the console in case a hanging CPU is
844 detected, and that CPU is pinged again in order to try
845 to resolve the hang situation.
846 0: disable csdlock debugging (default)
847 1: enable basic csdlock debugging (minor impact)
848 ext: enable extended csdlock debugging (more impact,
852 See header of drivers/s390/block/dasd_devmap.c.
854 db9.dev[2|3]= [HW,JOY] Multisystem joystick support via parallel port
855 (one device per port)
856 Format: <port#>,<type>
857 See also Documentation/input/devices/joystick-parport.rst
859 debug [KNL] Enable kernel debugging (events log level).
862 [KNL] Enable printing [hashed] pointers early in the
863 boot sequence. If enabled, we use a weak hash instead
864 of siphash to hash pointers. Use this option if you are
865 seeing instances of '(___ptrval___)') and need to see a
866 value (hashed pointer) instead. Cryptographically
867 insecure, please do not use on production kernels.
870 [KNL] verbose locking self-tests
872 Print debugging info while doing the locking API
874 Bitmask for the various LOCKTYPE_ tests. Defaults to 0
875 (no extra messages), setting it to -1 (all bits set)
876 will print _a_lot_ more information - normally only
877 useful to lockdep developers.
879 debug_objects [KNL] Enable object debugging
882 [KNL] Disable object debugging
884 debug_guardpage_minorder=
885 [KNL] When CONFIG_DEBUG_PAGEALLOC is set, this
886 parameter allows control of the order of pages that will
887 be intentionally kept free (and hence protected) by the
888 buddy allocator. Bigger value increase the probability
889 of catching random memory corruption, but reduce the
890 amount of memory for normal system use. The maximum
891 possible value is MAX_ORDER/2. Setting this parameter
892 to 1 or 2 should be enough to identify most random
893 memory corruption problems caused by bugs in kernel or
894 driver code when a CPU writes to (or reads from) a
895 random memory location. Note that there exists a class
896 of memory corruptions problems caused by buggy H/W or
897 F/W or by drivers badly programing DMA (basically when
898 memory is written at bus level and the CPU MMU is
899 bypassed) which are not detectable by
900 CONFIG_DEBUG_PAGEALLOC, hence this option will not help
901 tracking down these problems.
904 [KNL] When CONFIG_DEBUG_PAGEALLOC is set, this parameter
905 enables the feature at boot time. By default, it is
906 disabled and the system will work mostly the same as a
907 kernel built without CONFIG_DEBUG_PAGEALLOC.
908 Note: to get most of debug_pagealloc error reports, it's
909 useful to also enable the page_owner functionality.
910 on: enable the feature
912 debugfs= [KNL] This parameter enables what is exposed to userspace
913 and debugfs internal clients.
914 Format: { on, no-mount, off }
915 on: All functions are enabled.
917 Filesystem is not registered but kernel clients can
918 access APIs and a crashkernel can be used to read
919 its content. There is nothing to mount.
920 off: Filesystem is not registered and clients
921 get a -EPERM as result when trying to register files
922 or directories within debugfs.
923 This is equivalent of the runtime functionality if
924 debugfs was not enabled in the kernel at all.
925 Default value is set in build-time with a kernel configuration.
927 debugpat [X86] Enable PAT debugging
929 decnet.addr= [HW,NET]
930 Format: <area>[,<node>]
931 See also Documentation/networking/decnet.rst.
934 [HW] The size of the default HugeTLB page. This is
935 the size represented by the legacy /proc/ hugepages
936 APIs. In addition, this is the default hugetlb size
937 used for shmget(), mmap() and mounting hugetlbfs
938 filesystems. If not specified, defaults to the
939 architecture's default huge page size. Huge page
940 sizes are architecture dependent. See also
941 Documentation/admin-guide/mm/hugetlbpage.rst.
944 deferred_probe_timeout=
945 [KNL] Debugging option to set a timeout in seconds for
946 deferred probe to give up waiting on dependencies to
947 probe. Only specific dependencies (subsystems or
948 drivers) that have opted in will be ignored. A timeout of 0
949 will timeout at the end of initcalls. This option will also
950 dump out devices still on the deferred probe list after
953 dell_smm_hwmon.ignore_dmi=
954 [HW] Continue probing hardware even if DMI data
955 indicates that the driver is running on unsupported
958 dell_smm_hwmon.force=
959 [HW] Activate driver even if SMM BIOS signature does
960 not match list of supported models and enable otherwise
961 blacklisted features.
963 dell_smm_hwmon.power_status=
964 [HW] Report power status in /proc/i8k
965 (disabled by default).
967 dell_smm_hwmon.restricted=
968 [HW] Allow controlling fans only if SYS_ADMIN
971 dell_smm_hwmon.fan_mult=
972 [HW] Factor to multiply fan speed with.
974 dell_smm_hwmon.fan_max=
975 [HW] Maximum configurable fan speed.
978 Format: { on | off | def_only | inf_only | always }
979 on: s390 zlib hardware support for compression on
980 level 1 and decompression (default)
981 off: No s390 zlib hardware support
982 def_only: s390 zlib hardware support for deflate
983 only (compression on level 1)
984 inf_only: s390 zlib hardware support for inflate
986 always: Same as 'on' but ignores the selected compression
987 level always using hardware support (used for debugging)
990 Set number of hash buckets for dentry cache.
992 disable_1tb_segments [PPC]
993 Disables the use of 1TB hash page table segments. This
994 causes the kernel to fall back to 256MB segments which
995 can be useful when debugging issues that require an SLB
999 Limits the number of kernel SLB entries, and flushes
1000 them frequently to increase the rate of SLB faults
1001 on kernel addresses.
1004 See Documentation/networking/ipv6.rst.
1007 [KNL] Under CONFIG_HARDENED_USERCOPY, whether
1008 hardening is enabled for this boot. Hardened
1009 usercopy checking is used to protect the kernel
1010 from reading or writing beyond known memory
1011 allocation boundaries as a proactive defense
1012 against bounds-checking flaws in the kernel's
1013 copy_to_user()/copy_from_user() interface.
1014 on Perform hardened usercopy checks (default).
1015 off Disable hardened usercopy checks.
1018 Disable RADIX MMU mode on POWER9
1020 radix_hcall_invalidate=on [PPC/PSERIES]
1021 Disable RADIX GTSE feature and use hcall for TLB
1025 Disable TLBIE instruction. Currently does not work
1026 with KVM, with HASH MMU, or with coherent accelerators.
1028 disable_cpu_apicid= [X86,APIC,SMP]
1030 The number of initial APIC ID for the
1031 corresponding CPU to be disabled at boot,
1032 mostly used for the kdump 2nd kernel to
1033 disable BSP to wake up multiple CPUs without
1034 causing system reset or hang due to sending
1035 INIT from AP to BSP.
1037 disable_ddw [PPC/PSERIES]
1038 Disable Dynamic DMA Window support. Use this
1039 to workaround buggy firmware.
1041 disable_ipv6= [IPV6]
1042 See Documentation/networking/ipv6.rst.
1044 disable_mtrr_cleanup [X86]
1045 The kernel tries to adjust MTRR layout from continuous
1046 to discrete, to make X server driver able to add WB
1047 entry later. This parameter disables that.
1049 disable_mtrr_trim [X86, Intel and AMD only]
1050 By default the kernel will trim any uncacheable
1051 memory out of your available memory pool based on
1052 MTRR settings. This parameter disables that behavior,
1053 possibly causing your machine to run very slowly.
1055 disable_timer_pin_1 [X86]
1056 Disable PIN 1 of APIC timer
1057 Can be useful to work around chipset bugs.
1059 dis_ucode_ldr [X86] Disable the microcode loader.
1061 dma_debug=off If the kernel is compiled with DMA_API_DEBUG support,
1062 this option disables the debugging code at boot.
1064 dma_debug_entries=<number>
1065 This option allows to tune the number of preallocated
1066 entries for DMA-API debugging code. One entry is
1067 required per DMA-API allocation. Use this if the
1068 DMA-API debugging code disables itself because the
1069 architectural default is too low.
1071 dma_debug_driver=<driver_name>
1072 With this option the DMA-API debugging driver
1073 filter feature can be enabled at boot time. Just
1074 pass the driver to filter for as the parameter.
1075 The filter can be disabled or changed to another
1076 driver later using sysfs.
1078 driver_async_probe= [KNL]
1079 List of driver names to be probed asynchronously.
1080 Format: <driver_name1>,<driver_name2>...
1082 drm.edid_firmware=[<connector>:]<file>[,[<connector>:]<file>]
1083 Broken monitors, graphic adapters, KVMs and EDIDless
1084 panels may send no or incorrect EDID data sets.
1085 This parameter allows to specify an EDID data sets
1086 in the /lib/firmware directory that are used instead.
1087 Generic built-in EDID data sets are used, if one of
1088 edid/1024x768.bin, edid/1280x1024.bin,
1089 edid/1680x1050.bin, or edid/1920x1080.bin is given
1090 and no file with the same name exists. Details and
1091 instructions how to build your own EDID data are
1092 available in Documentation/admin-guide/edid.rst. An EDID
1093 data set will only be used for a particular connector,
1094 if its name and a colon are prepended to the EDID
1095 name. Each connector may use a unique EDID data
1096 set by separating the files with a comma. An EDID
1097 data set with no connector name will be used for
1098 any connectors not explicitly specified.
1103 Format: {"off" | "known"}
1104 Control how the dt_cpu_ftrs device-tree binding is
1105 used for CPU feature discovery and setup (if it
1107 off: Do not use it, fall back to legacy cpu table.
1108 known: Do not pass through unknown features to guests
1109 or userspace, only those that the kernel is aware of.
1111 dump_apple_properties [X86]
1112 Dump name and content of EFI device properties on
1113 x86 Macs. Useful for driver authors to determine
1114 what data is available or for reverse-engineering.
1116 dyndbg[="val"] [KNL,DYNAMIC_DEBUG]
1117 <module>.dyndbg[="val"]
1118 Enable debug messages at boot time. See
1119 Documentation/admin-guide/dynamic-debug-howto.rst
1122 nopku [X86] Disable Memory Protection Keys CPU feature found
1125 <module>.async_probe [KNL]
1126 Enable asynchronous probe on this module.
1128 early_ioremap_debug [KNL]
1129 Enable debug messages in early_ioremap support. This
1130 is useful for tracking down temporary early mappings
1131 which are not unmapped.
1133 earlycon= [KNL] Output early console device and options.
1135 When used with no options, the early console is
1136 determined by stdout-path property in device tree's
1137 chosen node or the ACPI SPCR table if supported by
1140 cdns,<addr>[,options]
1141 Start an early, polled-mode console on a Cadence
1142 (xuartps) serial port at the specified address. Only
1143 supported option is baud rate. If baud rate is not
1144 specified, the serial port must already be setup and
1147 uart[8250],io,<addr>[,options]
1148 uart[8250],mmio,<addr>[,options]
1149 uart[8250],mmio32,<addr>[,options]
1150 uart[8250],mmio32be,<addr>[,options]
1151 uart[8250],0x<addr>[,options]
1152 Start an early, polled-mode console on the 8250/16550
1153 UART at the specified I/O port or MMIO address.
1154 MMIO inter-register address stride is either 8-bit
1155 (mmio) or 32-bit (mmio32 or mmio32be).
1156 If none of [io|mmio|mmio32|mmio32be], <addr> is assumed
1157 to be equivalent to 'mmio'. 'options' are specified
1158 in the same format described for "console=ttyS<n>"; if
1159 unspecified, the h/w is not initialized.
1163 Start an early, polled-mode console on a pl011 serial
1164 port at the specified address. The pl011 serial port
1165 must already be setup and configured. Options are not
1166 yet supported. If 'mmio32' is specified, then only
1167 the driver will use only 32-bit accessors to read/write
1168 the device registers.
1171 Start an early console on a litex serial port at the
1172 specified address. The serial port must already be
1173 setup and configured. Options are not yet supported.
1176 Start an early, polled-mode console on a meson serial
1177 port at the specified address. The serial port must
1178 already be setup and configured. Options are not yet
1182 Start an early, polled-mode console on an msm serial
1183 port at the specified address. The serial port
1184 must already be setup and configured. Options are not
1187 msm_serial_dm,<addr>
1188 Start an early, polled-mode console on an msm serial
1189 dm port at the specified address. The serial port
1190 must already be setup and configured. Options are not
1194 Start an early, polled-mode console on a serial port
1195 of an Actions Semi SoC, such as S500 or S900, at the
1196 specified address. The serial port must already be
1197 setup and configured. Options are not yet supported.
1200 Start an early, polled-mode console on a serial port
1201 of an RDA Micro SoC, such as RDA8810PL, at the
1202 specified address. The serial port must already be
1203 setup and configured. Options are not yet supported.
1206 Use RISC-V SBI (Supervisor Binary Interface) for early
1209 smh Use ARM semihosting calls for early console.
1217 Use early console provided by serial driver available
1218 on Samsung SoCs, requires selecting proper type and
1219 a correct base address of the selected UART port. The
1220 serial port must already be setup and configured.
1221 Options are not yet supported.
1224 Start an early, polled-mode console on a lantiq serial
1225 (lqasc) port at the specified address. The serial port
1226 must already be setup and configured. Options are not
1231 Use early console provided by Freescale LP UART driver
1232 found on Freescale Vybrid and QorIQ LS1021A processors.
1233 A valid base address must be provided, and the serial
1234 port must already be setup and configured.
1238 Start an early, polled-mode, output-only console on the
1239 Freescale i.MX UART at the specified address. The UART
1240 must already be setup and configured.
1243 Start an early, polled-mode console on the
1244 Armada 3700 serial port at the specified
1245 address. The serial port must already be setup
1246 and configured. Options are not yet supported.
1249 Start an early, polled-mode console on a Qualcomm
1250 Generic Interface (GENI) based serial port at the
1251 specified address. The serial port must already be
1252 setup and configured. Options are not yet supported.
1255 Start an early, unaccelerated console on the EFI
1256 memory mapped framebuffer (if available). On cache
1257 coherent non-x86 systems that use system memory for
1258 the framebuffer, pass the 'ram' option so that it is
1259 mapped with the correct attributes.
1262 Use early console provided by Freescale LINFlexD UART
1263 serial driver for NXP S32V234 SoCs. A valid base
1264 address must be provided, and the serial port must
1265 already be setup and configured.
1267 earlyprintk= [X86,SH,ARM,M68k,S390]
1271 earlyprintk=serial[,ttySn[,baudrate]]
1272 earlyprintk=serial[,0x...[,baudrate]]
1273 earlyprintk=ttySn[,baudrate]
1274 earlyprintk=dbgp[debugController#]
1275 earlyprintk=pciserial[,force],bus:device.function[,baudrate]
1276 earlyprintk=xdbc[xhciController#]
1278 earlyprintk is useful when the kernel crashes before
1279 the normal console is initialized. It is not enabled by
1280 default because it has some cosmetic problems.
1282 Append ",keep" to not disable it when the real console
1285 Only one of vga, efi, serial, or usb debug port can
1288 Currently only ttyS0 and ttyS1 may be specified by
1289 name. Other I/O ports may be explicitly specified
1290 on some architectures (x86 and arm at least) by
1291 replacing ttySn with an I/O port address, like this:
1292 earlyprintk=serial,0x1008,115200
1293 You can find the port for a given device in
1294 /proc/tty/driver/serial:
1295 2: uart:ST16650V2 port:00001008 irq:18 ...
1297 Interaction with the standard serial driver is not
1300 The VGA and EFI output is eventually overwritten by
1303 The xen option can only be used in Xen domains.
1305 The sclp output can only be used on s390.
1307 The optional "force" to "pciserial" enables use of a
1308 PCI device even when its classcode is not of the
1311 edac_report= [HW,EDAC] Control how to report EDAC event
1312 Format: {"on" | "off" | "force"}
1313 on: enable EDAC to report H/W event. May be overridden
1314 by other higher priority error reporting module.
1315 off: disable H/W event reporting through EDAC.
1316 force: enforce the use of EDAC to report H/W event.
1319 ekgdboc= [X86,KGDB] Allow early kernel console debugging
1322 This is designed to be used in conjunction with
1323 the boot argument: earlyprintk=vga
1325 This parameter works in place of the kgdboc parameter
1326 but can only be used if the backing tty is available
1327 very early in the boot process. For early debugging
1328 via a serial port see kgdboc_earlycon instead.
1331 Format: {"off" | "on" | "skip[mbr]"}
1334 Format: { "debug", "disable_early_pci_dma",
1335 "nochunk", "noruntime", "nosoftreserve",
1336 "novamap", "no_disable_early_pci_dma" }
1337 debug: enable misc debug output.
1338 disable_early_pci_dma: disable the busmaster bit on all
1339 PCI bridges while in the EFI boot stub.
1340 nochunk: disable reading files in "chunks" in the EFI
1341 boot stub, as chunking can cause problems with some
1342 firmware implementations.
1343 noruntime : disable EFI runtime services support
1344 nosoftreserve: The EFI_MEMORY_SP (Specific Purpose)
1345 attribute may cause the kernel to reserve the
1346 memory range for a memory mapping driver to
1347 claim. Specify efi=nosoftreserve to disable this
1348 reservation and treat the memory by its base type
1349 (i.e. EFI_CONVENTIONAL_MEMORY / "System RAM").
1350 novamap: do not call SetVirtualAddressMap().
1351 no_disable_early_pci_dma: Leave the busmaster bit set
1352 on all PCI bridges while in the EFI boot stub
1354 efi_no_storage_paranoia [EFI; X86]
1355 Using this parameter you can use more than 50% of
1356 your efi variable storage. Use this parameter only if
1357 you are really sure that your UEFI does sane gc and
1358 fulfills the spec otherwise your board may brick.
1360 efi_fake_mem= nn[KMG]@ss[KMG]:aa[,nn[KMG]@ss[KMG]:aa,..] [EFI; X86]
1361 Add arbitrary attribute to specific memory range by
1362 updating original EFI memory map.
1363 Region of memory which aa attribute is added to is
1366 If efi_fake_mem=2G@4G:0x10000,2G@0x10a0000000:0x10000
1367 is specified, EFI_MEMORY_MORE_RELIABLE(0x10000)
1368 attribute is added to range 0x100000000-0x180000000 and
1369 0x10a0000000-0x1120000000.
1371 If efi_fake_mem=8G@9G:0x40000 is specified, the
1372 EFI_MEMORY_SP(0x40000) attribute is added to
1373 range 0x240000000-0x43fffffff.
1375 Using this parameter you can do debugging of EFI memmap
1376 related features. For example, you can do debugging of
1377 Address Range Mirroring feature even if your box
1378 doesn't support it, or mark specific memory as
1381 efivar_ssdt= [EFI; X86] Name of an EFI variable that contains an SSDT
1382 that is to be dynamically loaded by Linux. If there are
1383 multiple variables with the same name but with different
1384 vendor GUIDs, all of them will be loaded. See
1385 Documentation/admin-guide/acpi/ssdt-overlays.rst for details.
1388 eisa_irq_edge= [PARISC,HW]
1389 See header of drivers/parisc/eisa.c.
1392 See comment before function elanfreq_setup() in
1393 arch/x86/kernel/cpu/cpufreq/elanfreq.c.
1395 elfcorehdr=[size[KMG]@]offset[KMG] [IA64,PPC,SH,X86,S390]
1396 Specifies physical address of start of kernel core
1397 image elf header and optionally the size. Generally
1398 kexec loader will pass this option to capture kernel.
1399 See Documentation/admin-guide/kdump/kdump.rst for details.
1401 enable_mtrr_cleanup [X86]
1402 The kernel tries to adjust MTRR layout from continuous
1403 to discrete, to make X server driver able to add WB
1404 entry later. This parameter enables that.
1406 enable_timer_pin_1 [X86]
1407 Enable PIN 1 of APIC timer
1408 Can be useful to work around chipset bugs
1409 (in particular on some ATI chipsets).
1410 The kernel tries to set a reasonable default.
1412 enforcing [SELINUX] Set initial enforcing status.
1414 See security/selinux/Kconfig help text.
1415 0 -- permissive (log only, no denials).
1416 1 -- enforcing (deny and log).
1418 Value can be changed at runtime via
1419 /sys/fs/selinux/enforce.
1422 Disable Error Record Serialization Table (ERST)
1425 ether= [HW,NET] Ethernet cards parameters
1426 This option is obsoleted by the "netdev=" option, which
1427 has equivalent usage. See its documentation for details.
1431 Permit 'security.evm' to be updated regardless of
1432 current integrity status.
1437 fail_make_request=[KNL]
1438 General fault injection mechanism.
1439 Format: <interval>,<probability>,<space>,<times>
1440 See also Documentation/fault-injection/.
1443 Format: { initns | none }
1444 See Documentation/admin-guide/sysctl/net.rst for
1445 fb_tunnels_only_for_init_ns
1448 See Documentation/admin-guide/blockdev/floppy.rst.
1450 force_pal_cache_flush
1451 [IA-64] Avoid check_sal_cache_flush which may hang on
1452 buggy SAL_CACHE_FLUSH implementations. Using this
1453 parameter will force ia64_sal_cache_flush to call
1454 ia64_pal_cache_flush instead of SAL_CACHE_FLUSH.
1457 Forcefully enable Physical Address Extension (PAE).
1458 Many Pentium M systems disable PAE but may have a
1459 functionally usable PAE implementation.
1460 Warning: use of this parameter will taint the kernel
1461 and may cause unknown problems.
1464 [FTRACE] will set and start the specified tracer
1465 as early as possible in order to facilitate early
1468 ftrace_boot_snapshot
1469 [FTRACE] On boot up, a snapshot will be taken of the
1470 ftrace ring buffer that can be read at:
1471 /sys/kernel/tracing/snapshot.
1472 This is useful if you need tracing information from kernel
1473 boot up that is likely to be overridden by user space
1474 start up functionality.
1476 ftrace_dump_on_oops[=orig_cpu]
1477 [FTRACE] will dump the trace buffers on oops.
1478 If no parameter is passed, ftrace will dump
1479 buffers of all CPUs, but if you pass orig_cpu, it will
1480 dump only the buffer of the CPU that triggered the
1483 ftrace_filter=[function-list]
1484 [FTRACE] Limit the functions traced by the function
1485 tracer at boot up. function-list is a comma-separated
1486 list of functions. This list can be changed at run
1487 time by the set_ftrace_filter file in the debugfs
1490 ftrace_notrace=[function-list]
1491 [FTRACE] Do not trace the functions specified in
1492 function-list. This list can be changed at run time
1493 by the set_ftrace_notrace file in the debugfs
1496 ftrace_graph_filter=[function-list]
1497 [FTRACE] Limit the top level callers functions traced
1498 by the function graph tracer at boot up.
1499 function-list is a comma-separated list of functions
1500 that can be changed at run time by the
1501 set_graph_function file in the debugfs tracing directory.
1503 ftrace_graph_notrace=[function-list]
1504 [FTRACE] Do not trace from the functions specified in
1505 function-list. This list is a comma-separated list of
1506 functions that can be changed at run time by the
1507 set_graph_notrace file in the debugfs tracing directory.
1509 ftrace_graph_max_depth=<uint>
1510 [FTRACE] Used with the function graph tracer. This is
1511 the max depth it will trace into a function. This value
1512 can be changed at run time by the max_graph_depth file
1513 in the tracefs tracing directory. default: 0 (no limit)
1515 fw_devlink= [KNL] Create device links between consumer and supplier
1516 devices by scanning the firmware to infer the
1517 consumer/supplier relationships. This feature is
1518 especially useful when drivers are loaded as modules as
1519 it ensures proper ordering of tasks like device probing
1520 (suppliers first, then consumers), supplier boot state
1521 clean up (only after all consumers have probed),
1522 suspend/resume & runtime PM (consumers first, then
1524 Format: { off | permissive | on | rpm }
1525 off -- Don't create device links from firmware info.
1526 permissive -- Create device links from firmware info
1527 but use it only for ordering boot state clean
1528 up (sync_state() calls).
1529 on -- Create device links from firmware info and use it
1530 to enforce probe and suspend/resume ordering.
1531 rpm -- Like "on", but also use to order runtime PM.
1533 fw_devlink.strict=<bool>
1534 [KNL] Treat all inferred dependencies as mandatory
1535 dependencies. This only applies for fw_devlink=on|rpm.
1539 [HW,JOY] Multisystem joystick and NES/SNES/PSX pad
1540 support via parallel port (up to 5 devices per port)
1541 Format: <port#>,<pad1>,<pad2>,<pad3>,<pad4>,<pad5>
1542 See also Documentation/input/devices/joystick-parport.rst
1546 gart_fix_e820= [X86-64] disable the fix e820 for K8 GART
1550 gcov_persist= [GCOV] When non-zero (default), profiling data for
1551 kernel modules is saved and remains accessible via
1552 debugfs, even when the module is unloaded/reloaded.
1553 When zero, profiling data is discarded and associated
1554 debugfs files are removed at module unload time.
1556 goldfish [X86] Enable the goldfish android emulator platform.
1557 Don't use this when you are not running on the
1560 gpio-mockup.gpio_mockup_ranges
1561 [HW] Sets the ranges of gpiochip of for this device.
1562 Format: <start1>,<end1>,<start2>,<end2>...
1563 gpio-mockup.gpio_mockup_named_lines
1564 [HW] Let the driver know GPIO lines should be named.
1566 gpt [EFI] Forces disk with valid GPT signature but
1567 invalid Protective MBR to be treated as GPT. If the
1568 primary GPT is corrupted, it enables the backup/alternate
1569 GPT to be used instead.
1571 grcan.enable0= [HW] Configuration of physical interface 0. Determines
1572 the "Enable 0" bit of the configuration register.
1575 grcan.enable1= [HW] Configuration of physical interface 1. Determines
1576 the "Enable 0" bit of the configuration register.
1579 grcan.select= [HW] Select which physical interface to use.
1582 grcan.txsize= [HW] Sets the size of the tx buffer.
1583 Format: <unsigned int> such that (txsize & ~0x1fffc0) == 0.
1585 grcan.rxsize= [HW] Sets the size of the rx buffer.
1586 Format: <unsigned int> such that (rxsize & ~0x1fffc0) == 0.
1589 hardlockup_all_cpu_backtrace=
1590 [KNL] Should the hard-lockup detector generate
1591 backtraces on all cpus.
1594 hashdist= [KNL,NUMA] Large hashes allocated during boot
1595 are distributed across NUMA nodes. Defaults on
1596 for 64-bit NUMA, off otherwise.
1597 Format: 0 | 1 (for off | on)
1599 hcl= [IA-64] SGI's Hardware Graph compatibility layer
1601 hd= [EIDE] (E)IDE hard drive subsystem geometry
1602 Format: <cyl>,<head>,<sect>
1605 Disable Hardware Error Source Table (HEST) support;
1606 corresponding firmware-first mode error processing
1607 logic will be disabled.
1609 highmem=nn[KMG] [KNL,BOOT] forces the highmem zone to have an exact
1610 size of <nn>. This works even on boxes that have no
1611 highmem otherwise. This also works to reduce highmem
1612 size on bigger boxes.
1614 highres= [KNL] Enable/disable high resolution timer mode.
1615 Valid parameters: "on", "off"
1620 hpet= [X86-32,HPET] option to control HPET usage
1621 Format: { enable (default) | disable | force |
1623 disable: disable HPET and use PIT instead
1624 force: allow force enabled of undocumented chips (ICH4,
1626 verbose: show contents of HPET registers during setup
1628 hpet_mmap= [X86, HPET_MMAP] Allow userspace to mmap HPET
1629 registers. Default set by CONFIG_HPET_MMAP_DEFAULT.
1631 hugetlb_cma= [HW,CMA] The size of a CMA area used for allocation
1632 of gigantic hugepages. Or using node format, the size
1633 of a CMA area per node can be specified.
1634 Format: nn[KMGTPE] or (node format)
1635 <node>:nn[KMGTPE][,<node>:nn[KMGTPE]]
1637 Reserve a CMA area of given size and allocate gigantic
1638 hugepages using the CMA allocator. If enabled, the
1639 boot-time allocation of gigantic hugepages is skipped.
1641 hugepages= [HW] Number of HugeTLB pages to allocate at boot.
1642 If this follows hugepagesz (below), it specifies
1643 the number of pages of hugepagesz to be allocated.
1644 If this is the first HugeTLB parameter on the command
1645 line, it specifies the number of pages to allocate for
1646 the default huge page size. If using node format, the
1647 number of pages to allocate per-node can be specified.
1648 See also Documentation/admin-guide/mm/hugetlbpage.rst.
1649 Format: <integer> or (node format)
1650 <node>:<integer>[,<node>:<integer>]
1653 [HW] The size of the HugeTLB pages. This is used in
1654 conjunction with hugepages (above) to allocate huge
1655 pages of a specific size at boot. The pair
1656 hugepagesz=X hugepages=Y can be specified once for
1657 each supported huge page size. Huge page sizes are
1658 architecture dependent. See also
1659 Documentation/admin-guide/mm/hugetlbpage.rst.
1662 hugetlb_free_vmemmap=
1663 [KNL] Reguires CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
1665 Allows heavy hugetlb users to free up some more
1666 memory (7 * PAGE_SIZE for each 2MB hugetlb page).
1667 Format: { on | off (default) }
1669 on: enable the feature
1670 off: disable the feature
1672 Built with CONFIG_HUGETLB_PAGE_FREE_VMEMMAP_DEFAULT_ON=y,
1675 This is not compatible with memory_hotplug.memmap_on_memory.
1676 If both parameters are enabled, hugetlb_free_vmemmap takes
1677 precedence over memory_hotplug.memmap_on_memory.
1680 [KNL] Should the hung task detector generate panics.
1683 A value of 1 instructs the kernel to panic when a
1684 hung task is detected. The default value is controlled
1685 by the CONFIG_BOOTPARAM_HUNG_TASK_PANIC build-time
1686 option. The value selected by this boot parameter can
1687 be changed later by the kernel.hung_task_panic sysctl.
1689 hvc_iucv= [S390] Number of z/VM IUCV hypervisor console (HVC)
1690 terminal devices. Valid values: 0..8
1691 hvc_iucv_allow= [S390] Comma-separated list of z/VM user IDs.
1692 If specified, z/VM IUCV HVC accepts connections
1693 from listed z/VM user IDs only.
1695 hv_nopvspin [X86,HYPER_V] Disables the paravirt spinlock optimizations
1696 which allow the hypervisor to 'idle' the
1697 guest on lock contention.
1700 Do not unregister boot console at start. This is only
1701 useful for debugging when something happens in the window
1702 between unregistering the boot console and initializing
1705 i2c_bus= [HW] Override the default board specific I2C bus speed
1706 or register an additional I2C bus that is not
1707 registered from board initialization code.
1711 i8042.debug [HW] Toggle i8042 debug mode
1712 i8042.unmask_kbd_data
1713 [HW] Enable printing of interrupt data from the KBD port
1714 (disabled by default, and as a pre-condition
1715 requires that i8042.debug=1 be enabled)
1716 i8042.direct [HW] Put keyboard port into non-translated mode
1717 i8042.dumbkbd [HW] Pretend that controller can only read data from
1718 keyboard and cannot control its state
1719 (Don't attempt to blink the leds)
1720 i8042.noaux [HW] Don't check for auxiliary (== mouse) port
1721 i8042.nokbd [HW] Don't check/create keyboard port
1722 i8042.noloop [HW] Disable the AUX Loopback command while probing
1724 i8042.nomux [HW] Don't check presence of an active multiplexing
1726 i8042.nopnp [HW] Don't use ACPIPnP / PnPBIOS to discover KBD/AUX
1728 i8042.notimeout [HW] Ignore timeout condition signalled by controller
1729 i8042.reset [HW] Reset the controller during init, cleanup and
1730 suspend-to-ram transitions, only during s2r
1731 transitions, or never reset
1732 Format: { 1 | Y | y | 0 | N | n }
1733 1, Y, y: always reset controller
1734 0, N, n: don't ever reset controller
1735 Default: only on s2r transitions on x86; most other
1736 architectures force reset to be always executed
1737 i8042.unlock [HW] Unlock (ignore) the keylock
1738 i8042.kbdreset [HW] Reset device connected to KBD port
1740 [HW] Allow deferred probing upon i8042 probe errors
1744 i915.invert_brightness=
1745 [DRM] Invert the sense of the variable that is used to
1746 set the brightness of the panel backlight. Normally a
1747 brightness value of 0 indicates backlight switched off,
1748 and the maximum of the brightness value sets the backlight
1749 to maximum brightness. If this parameter is set to 0
1750 (default) and the machine requires it, or this parameter
1751 is set to 1, a brightness value of 0 sets the backlight
1752 to maximum brightness, and the maximum of the brightness
1753 value switches the backlight off.
1754 -1 -- never invert brightness
1755 0 -- machine default
1756 1 -- force brightness inversion
1759 Format: <io>[,<membase>[,<icn_id>[,<icn_id2>]]]
1761 ide-core.nodma= [HW] (E)IDE subsystem
1762 Format: =0.0 to prevent dma on hda, =0.1 hdb =1.0 hdc
1763 .vlb_clock .pci_clock .noflush .nohpa .noprobe .nowerr
1764 .cdrom .chs .ignore_cable are additional options
1765 See Documentation/ide/ide.rst.
1767 ide-generic.probe-mask= [HW] (E)IDE subsystem
1769 Probe mask for legacy ISA IDE ports. Depending on
1770 platform up to 6 ports are supported, enabled by
1771 setting corresponding bits in the mask to 1. The
1772 default value is 0x0, which has a special meaning.
1773 On systems that have PCI, it triggers scanning the
1774 PCI bus for the first and the second port, which
1775 are then probed. On systems without PCI the value
1776 of 0x0 enables probing the two first ports as if it
1779 ide-pci-generic.all-generic-ide [HW] (E)IDE subsystem
1780 Claim all unknown PCI IDE storage controllers.
1783 Format: idle=poll, idle=halt, idle=nomwait
1784 Poll forces a polling idle loop that can slightly
1785 improve the performance of waking up a idle CPU, but
1786 will use a lot of power and make the system run hot.
1788 idle=halt: Halt is forced to be used for CPU idle.
1789 In such case C2/C3 won't be used again.
1790 idle=nomwait: Disable mwait for CPU C-states
1794 Allow force disabling of Shared Virtual Memory (SVA)
1795 support for the idxd driver. By default it is set to
1798 idxd.tc_override= [HW]
1800 Allow override of default traffic class configuration
1801 for the device. By default it is set to false (0).
1803 ieee754= [MIPS] Select IEEE Std 754 conformance mode
1804 Format: { strict | legacy | 2008 | relaxed }
1807 Choose which programs will be accepted for execution
1808 based on the IEEE 754 NaN encoding(s) supported by
1809 the FPU and the NaN encoding requested with the value
1810 of an ELF file header flag individually set by each
1811 binary. Hardware implementations are permitted to
1812 support either or both of the legacy and the 2008 NaN
1815 Available settings are as follows:
1816 strict accept binaries that request a NaN encoding
1817 supported by the FPU
1818 legacy only accept legacy-NaN binaries, if supported
1820 2008 only accept 2008-NaN binaries, if supported
1822 relaxed accept any binaries regardless of whether
1823 supported by the FPU
1825 The FPU emulator is always able to support both NaN
1826 encodings, so if no FPU hardware is present or it has
1827 been disabled with 'nofpu', then the settings of
1828 'legacy' and '2008' strap the emulator accordingly,
1829 'relaxed' straps the emulator for both legacy-NaN and
1830 2008-NaN, whereas 'strict' enables legacy-NaN only on
1831 legacy processors and both NaN encodings on MIPS32 or
1834 The setting for ABS.fmt/NEG.fmt instruction execution
1835 mode generally follows that for the NaN encoding,
1836 except where unsupported by hardware.
1838 ignore_loglevel [KNL]
1839 Ignore loglevel setting - this will print /all/
1840 kernel messages to the console. Useful for debugging.
1841 We also add it as printk module parameter, so users
1842 could change it dynamically, usually by
1843 /sys/module/printk/parameters/ignore_loglevel.
1846 Ignore RLIMIT_DATA setting for data mappings,
1847 print warning at first misuse. Can be changed via
1848 /sys/module/kernel/parameters/ignore_rlimit_data.
1850 ihash_entries= [KNL]
1851 Set number of hash buckets for inode cache.
1853 ima_appraise= [IMA] appraise integrity measurements
1854 Format: { "off" | "enforce" | "fix" | "log" }
1857 ima_appraise_tcb [IMA] Deprecated. Use ima_policy= instead.
1858 The builtin appraise policy appraises all files
1861 ima_canonical_fmt [IMA]
1862 Use the canonical format for the binary runtime
1863 measurements, instead of host native format.
1866 Format: { md5 | sha1 | rmd160 | sha256 | sha384
1870 The list of supported hash algorithms is defined
1871 in crypto/hash_info.h.
1874 The builtin policies to load during IMA setup.
1875 Format: "tcb | appraise_tcb | secure_boot |
1876 fail_securely | critical_data"
1878 The "tcb" policy measures all programs exec'd, files
1879 mmap'd for exec, and all files opened with the read
1880 mode bit set by either the effective uid (euid=0) or
1883 The "appraise_tcb" policy appraises the integrity of
1884 all files owned by root.
1886 The "secure_boot" policy appraises the integrity
1887 of files (eg. kexec kernel image, kernel modules,
1888 firmware, policy, etc) based on file signatures.
1890 The "fail_securely" policy forces file signature
1891 verification failure also on privileged mounted
1892 filesystems with the SB_I_UNVERIFIABLE_SIGNATURE
1895 The "critical_data" policy measures kernel integrity
1898 ima_tcb [IMA] Deprecated. Use ima_policy= instead.
1899 Load a policy which meets the needs of the Trusted
1900 Computing Base. This means IMA will measure all
1901 programs exec'd, files mmap'd for exec, and all files
1902 opened for read by uid=0.
1905 Select one of defined IMA measurements template formats.
1906 Formats: { "ima" | "ima-ng" | "ima-sig" }
1910 [IMA] Define a custom template format.
1911 Format: { "field1|...|fieldN" }
1913 ima.ahash_minsize= [IMA] Minimum file size for asynchronous hash usage
1914 Format: <min_file_size>
1915 Set the minimal file size for using asynchronous hash.
1916 If left unspecified, ahash usage is disabled.
1918 ahash performance varies for different data sizes on
1919 different crypto accelerators. This option can be used
1920 to achieve the best performance for a particular HW.
1922 ima.ahash_bufsize= [IMA] Asynchronous hash buffer size
1924 Set hashing buffer size. Default: 4k.
1926 ahash performance varies for different chunk sizes on
1927 different crypto accelerators. This option can be used
1928 to achieve best performance for particular HW.
1932 Run specified binary instead of /sbin/init as init
1935 initcall_debug [KNL] Trace initcalls as they are executed. Useful
1936 for working out where the kernel is dying during
1939 initcall_blacklist= [KNL] Do not execute a comma-separated list of
1940 initcall functions. Useful for debugging built-in
1941 modules and initcalls.
1943 initramfs_async= [KNL]
1946 This parameter controls whether the initramfs
1947 image is unpacked asynchronously, concurrently
1948 with devices being probed and
1949 initialized. This should normally just work,
1950 but as a debugging aid, one can get the
1951 historical behaviour of the initramfs
1952 unpacking being completed before device_ and
1955 initrd= [BOOT] Specify the location of the initial ramdisk
1957 initrdmem= [KNL] Specify a physical address and size from which to
1958 load the initrd. If an initrd is compiled in or
1959 specified in the bootparams, it takes priority over this
1961 Format: ss[KMG],nn[KMG]
1964 init_on_alloc= [MM] Fill newly allocated pages and heap objects with
1967 Default set by CONFIG_INIT_ON_ALLOC_DEFAULT_ON.
1969 init_on_free= [MM] Fill freed pages and heap objects with zeroes.
1971 Default set by CONFIG_INIT_ON_FREE_DEFAULT_ON.
1973 init_pkru= [X86] Specify the default memory protection keys rights
1974 register contents for all processes. 0x55555554 by
1975 default (disallow access to all but pkey 0). Can
1976 override in debugfs after boot.
1978 inport.irq= [HW] Inport (ATI XL and Microsoft) busmouse driver
1981 int_pln_enable [X86] Enable power limit notification interrupt
1983 integrity_audit=[IMA]
1984 Format: { "0" | "1" }
1985 0 -- basic integrity auditing messages. (Default)
1986 1 -- additional integrity auditing messages.
1988 intel_iommu= [DMAR] Intel IOMMU driver (DMAR) option
1990 Enable intel iommu driver.
1992 Disable intel iommu driver.
1993 igfx_off [Default Off]
1994 By default, gfx is mapped as normal device. If a gfx
1995 device has a dedicated DMAR unit, the DMAR unit is
1996 bypassed by not enabling DMAR with this option. In
1997 this case, gfx device will use physical address for
1999 strict [Default Off]
2000 Deprecated, equivalent to iommu.strict=1.
2001 sp_off [Default Off]
2002 By default, super page will be supported if Intel IOMMU
2003 has the capability. With this option, super page will
2006 Enable the Intel IOMMU scalable mode if the hardware
2007 advertises that it has support for the scalable mode
2010 Disallow use of the Intel IOMMU scalable mode.
2011 tboot_noforce [Default Off]
2012 Do not force the Intel IOMMU enabled under tboot.
2013 By default, tboot will force Intel IOMMU on, which
2014 could harm performance of some high-throughput
2015 devices like 40GBit network cards, even if identity
2017 Note that using this option lowers the security
2018 provided by tboot because it makes the system
2019 vulnerable to DMA attacks.
2021 intel_idle.max_cstate= [KNL,HW,ACPI,X86]
2022 0 disables intel_idle and fall back on acpi_idle.
2023 1 to 9 specify maximum depth of C-state.
2027 Do not enable intel_pstate as the default
2028 scaling driver for the supported processors
2030 Use intel_pstate as a scaling driver, but configure it
2031 to work with generic cpufreq governors (instead of
2032 enabling its internal governor). This mode cannot be
2033 used along with the hardware-managed P-states (HWP)
2036 Enable intel_pstate on systems that prohibit it by default
2037 in favor of acpi-cpufreq. Forcing the intel_pstate driver
2038 instead of acpi-cpufreq may disable platform features, such
2039 as thermal controls and power capping, that rely on ACPI
2040 P-States information being indicated to OSPM and therefore
2041 should be used with caution. This option does not work with
2042 processors that aren't supported by the intel_pstate driver
2043 or on platforms that use pcc-cpufreq instead of acpi-cpufreq.
2045 Do not enable hardware P state control (HWP)
2048 Only load intel_pstate on systems which support
2049 hardware P state control (HWP) if available.
2051 Enforce ACPI _PPC performance limits. If the Fixed ACPI
2052 Description Table, specifies preferred power management
2053 profile as "Enterprise Server" or "Performance Server",
2054 then this feature is turned on by default.
2056 Allow per-logical-CPU P-State performance control limits using
2057 cpufreq sysfs interface
2059 intremap= [X86-64, Intel-IOMMU]
2060 on enable Interrupt Remapping (default)
2061 off disable Interrupt Remapping
2062 nosid disable Source ID checking
2064 BIOS x2APIC opt-out request will be ignored
2065 nopost disable Interrupt Posting
2067 iomem= Disable strict checking of access to MMIO memory
2068 strict regions from userspace.
2083 nobypass [PPC/POWERNV]
2084 Disable IOMMU bypass, using IOMMU for PCI devices.
2086 iommu.forcedac= [ARM64, X86] Control IOVA allocation for PCI devices.
2087 Format: { "0" | "1" }
2088 0 - Try to allocate a 32-bit DMA address first, before
2089 falling back to the full range if needed.
2090 1 - Allocate directly from the full usable range,
2091 forcing Dual Address Cycle for PCI cards supporting
2092 greater than 32-bit addressing.
2094 iommu.strict= [ARM64, X86] Configure TLB invalidation behaviour
2095 Format: { "0" | "1" }
2097 Request that DMA unmap operations use deferred
2098 invalidation of hardware TLBs, for increased
2099 throughput at the cost of reduced device isolation.
2100 Will fall back to strict mode if not supported by
2101 the relevant IOMMU driver.
2103 DMA unmap operations invalidate IOMMU hardware TLBs
2105 unset - Use value of CONFIG_IOMMU_DEFAULT_DMA_{LAZY,STRICT}.
2106 Note: on x86, strict mode specified via one of the
2107 legacy driver-specific options takes precedence.
2110 [ARM64, X86] Configure DMA to bypass the IOMMU by default.
2111 Format: { "0" | "1" }
2112 0 - Use IOMMU translation for DMA.
2113 1 - Bypass the IOMMU for DMA.
2114 unset - Use value of CONFIG_IOMMU_DEFAULT_PASSTHROUGH.
2116 io7= [HW] IO7 for Marvel-based Alpha systems
2117 See comment before marvel_specify_io7 in
2118 arch/alpha/kernel/core_marvel.c.
2120 io_delay= [X86] I/O delay method
2122 Standard port 0x80 based delay
2124 Alternate port 0xed based delay (needed on some systems)
2126 Simple two microseconds delay
2131 See Documentation/admin-guide/nfs/nfsroot.rst.
2133 ipcmni_extend [KNL] Extend the maximum number of unique System V
2134 IPC identifiers from 32,768 to 16,777,216.
2136 irqaffinity= [SMP] Set the default irq affinity mask
2137 The argument is a cpu list, as described above.
2139 irqchip.gicv2_force_probe=
2142 Force the kernel to look for the second 4kB page
2143 of a GICv2 controller even if the memory range
2144 exposed by the device tree is too small.
2146 irqchip.gicv3_nolpi=
2148 Force the kernel to ignore the availability of
2149 LPIs (and by consequence ITSs). Intended for system
2150 that use the kernel as a bootloader, and thus want
2151 to let secondary kernels in charge of setting up
2154 irqchip.gicv3_pseudo_nmi= [ARM64]
2155 Enables support for pseudo-NMIs in the kernel. This
2156 requires the kernel to be built with
2157 CONFIG_ARM64_PSEUDO_NMI.
2160 When an interrupt is not handled search all handlers
2161 for it. Intended to get systems with badly broken
2165 When an interrupt is not handled search all handlers
2166 for it. Also check all handlers each timer
2167 interrupt. Intended to get systems with badly broken
2171 Format: <RDP>,<reset>,<pci_scan>,<verbosity>
2173 isolcpus= [KNL,SMP,ISOL] Isolate a given set of CPUs from disturbance.
2174 [Deprecated - use cpusets instead]
2175 Format: [flag-list,]<cpu-list>
2177 Specify one or more CPUs to isolate from disturbances
2178 specified in the flag list (default: domain):
2181 Disable the tick when a single task runs.
2183 A residual 1Hz tick is offloaded to workqueues, which you
2184 need to affine to housekeeping through the global
2185 workqueue's affinity configured via the
2186 /sys/devices/virtual/workqueue/cpumask sysfs file, or
2187 by using the 'domain' flag described below.
2189 NOTE: by default the global workqueue runs on all CPUs,
2190 so to protect individual CPUs the 'cpumask' file has to
2191 be configured manually after bootup.
2194 Isolate from the general SMP balancing and scheduling
2195 algorithms. Note that performing domain isolation this way
2196 is irreversible: it's not possible to bring back a CPU to
2197 the domains once isolated through isolcpus. It's strongly
2198 advised to use cpusets instead to disable scheduler load
2199 balancing through the "cpuset.sched_load_balance" file.
2200 It offers a much more flexible interface where CPUs can
2201 move in and out of an isolated set anytime.
2203 You can move a process onto or off an "isolated" CPU via
2204 the CPU affinity syscalls or cpuset.
2205 <cpu number> begins at 0 and the maximum value is
2206 "number of CPUs in system - 1".
2210 Isolate from being targeted by managed interrupts
2211 which have an interrupt mask containing isolated
2212 CPUs. The affinity of managed interrupts is
2213 handled by the kernel and cannot be changed via
2214 the /proc/irq/* interfaces.
2216 This isolation is best effort and only effective
2217 if the automatically assigned interrupt mask of a
2218 device queue contains isolated and housekeeping
2219 CPUs. If housekeeping CPUs are online then such
2220 interrupts are directed to the housekeeping CPU
2221 so that IO submitted on the housekeeping CPU
2222 cannot disturb the isolated CPU.
2224 If a queue's affinity mask contains only isolated
2225 CPUs then this parameter has no effect on the
2226 interrupt routing decision, though interrupts are
2227 only delivered when tasks running on those
2228 isolated CPUs submit IO. IO submitted on
2229 housekeeping CPUs has no influence on those
2232 The format of <cpu-list> is described above.
2236 ivrs_ioapic [HW,X86-64]
2237 Provide an override to the IOAPIC-ID<->DEVICE-ID
2238 mapping provided in the IVRS ACPI table. For
2239 example, to map IOAPIC-ID decimal 10 to
2240 PCI device 00:14.0 write the parameter as:
2241 ivrs_ioapic[10]=00:14.0
2243 ivrs_hpet [HW,X86-64]
2244 Provide an override to the HPET-ID<->DEVICE-ID
2245 mapping provided in the IVRS ACPI table. For
2246 example, to map HPET-ID decimal 0 to
2247 PCI device 00:14.0 write the parameter as:
2248 ivrs_hpet[0]=00:14.0
2250 ivrs_acpihid [HW,X86-64]
2251 Provide an override to the ACPI-HID:UID<->DEVICE-ID
2252 mapping provided in the IVRS ACPI table. For
2253 example, to map UART-HID:UID AMD0020:0 to
2254 PCI device 00:14.5 write the parameter as:
2255 ivrs_acpihid[00:14.5]=AMD0020:0
2257 js= [HW,JOY] Analog joystick
2258 See Documentation/input/joydev/joystick.rst.
2261 When CONFIG_RANDOMIZE_BASE is set, this disables
2262 kernel and module base offset ASLR (Address Space
2263 Layout Randomization).
2266 [KNL] Enforce KASAN (Kernel Address Sanitizer) to print
2267 report on every invalid memory access. Without this
2268 parameter KASAN will print report only for the first
2273 kernelcore= [KNL,X86,IA-64,PPC]
2274 Format: nn[KMGTPE] | nn% | "mirror"
2275 This parameter specifies the amount of memory usable by
2276 the kernel for non-movable allocations. The requested
2277 amount is spread evenly throughout all nodes in the
2278 system as ZONE_NORMAL. The remaining memory is used for
2279 movable memory in its own zone, ZONE_MOVABLE. In the
2280 event, a node is too small to have both ZONE_NORMAL and
2281 ZONE_MOVABLE, kernelcore memory will take priority and
2282 other nodes will have a larger ZONE_MOVABLE.
2284 ZONE_MOVABLE is used for the allocation of pages that
2285 may be reclaimed or moved by the page migration
2286 subsystem. Note that allocations like PTEs-from-HighMem
2287 still use the HighMem zone if it exists, and the Normal
2288 zone if it does not.
2290 It is possible to specify the exact amount of memory in
2291 the form of "nn[KMGTPE]", a percentage of total system
2292 memory in the form of "nn%", or "mirror". If "mirror"
2293 option is specified, mirrored (reliable) memory is used
2294 for non-movable allocations and remaining memory is used
2295 for Movable pages. "nn[KMGTPE]", "nn%", and "mirror"
2296 are exclusive, so you cannot specify multiple forms.
2298 kgdbdbgp= [KGDB,HW] kgdb over EHCI usb debug port.
2299 Format: <Controller#>[,poll interval]
2300 The controller # is the number of the ehci usb debug
2301 port as it is probed via PCI. The poll interval is
2302 optional and is the number seconds in between
2303 each poll cycle to the debug port in case you need
2304 the functionality for interrupting the kernel with
2305 gdb or control-c on the dbgp connection. When
2306 not using this parameter you use sysrq-g to break into
2307 the kernel debugger.
2309 kgdboc= [KGDB,HW] kgdb over consoles.
2310 Requires a tty driver that supports console polling,
2311 or a supported polling keyboard driver (non-usb).
2312 Serial only format: <serial_device>[,baud]
2313 keyboard only format: kbd
2314 keyboard and serial format: kbd,<serial_device>[,baud]
2315 Optional Kernel mode setting:
2316 kms, kbd format: kms,kbd
2317 kms, kbd and serial format: kms,kbd,<ser_dev>[,baud]
2319 kgdboc_earlycon= [KGDB,HW]
2320 If the boot console provides the ability to read
2321 characters and can work in polling mode, you can use
2322 this parameter to tell kgdb to use it as a backend
2323 until the normal console is registered. Intended to
2324 be used together with the kgdboc parameter which
2325 specifies the normal console to transition to.
2327 The name of the early console should be specified
2328 as the value of this parameter. Note that the name of
2329 the early console might be different than the tty
2330 name passed to kgdboc. It's OK to leave the value
2331 blank and the first boot console that implements
2332 read() will be picked.
2334 kgdbwait [KGDB] Stop kernel execution and enter the
2335 kernel debugger at the earliest opportunity.
2337 kmac= [MIPS] Korina ethernet MAC address.
2338 Configure the RouterBoard 532 series on-chip
2339 Ethernet adapter MAC address.
2341 kmemleak= [KNL] Boot-time kmemleak enable/disable
2342 Valid arguments: on, off
2344 Built with CONFIG_DEBUG_KMEMLEAK_DEFAULT_OFF=y,
2347 kprobe_event=[probe-list]
2348 [FTRACE] Add kprobe events and enable at boot time.
2349 The probe-list is a semicolon delimited list of probe
2350 definitions. Each definition is same as kprobe_events
2351 interface, but the parameters are comma delimited.
2352 For example, to add a kprobe event on vfs_read with
2353 arg1 and arg2, add to the command line;
2355 kprobe_event=p,vfs_read,$arg1,$arg2
2357 See also Documentation/trace/kprobetrace.rst "Kernel
2358 Boot Parameter" section.
2360 kpti= [ARM64] Control page table isolation of user
2361 and kernel address spaces.
2362 Default: enabled on cores which need mitigation.
2366 kvm.ignore_msrs=[KVM] Ignore guest accesses to unhandled MSRs.
2367 Default is 0 (don't ignore, but inject #GP)
2369 kvm.enable_vmware_backdoor=[KVM] Support VMware backdoor PV interface.
2370 Default is false (don't support).
2372 kvm.mmu_audit= [KVM] This is a R/W parameter which allows audit
2377 [KVM] Controls the software workaround for the
2378 X86_BUG_ITLB_MULTIHIT bug.
2379 force : Always deploy workaround.
2380 off : Never deploy workaround.
2381 auto : Deploy workaround based on the presence of
2382 X86_BUG_ITLB_MULTIHIT.
2386 If the software workaround is enabled for the host,
2387 guests do need not to enable it for nested guests.
2389 kvm.nx_huge_pages_recovery_ratio=
2390 [KVM] Controls how many 4KiB pages are periodically zapped
2391 back to huge pages. 0 disables the recovery, otherwise if
2392 the value is N KVM will zap 1/Nth of the 4KiB pages every
2393 period (see below). The default is 60.
2395 kvm.nx_huge_pages_recovery_period_ms=
2396 [KVM] Controls the time period at which KVM zaps 4KiB pages
2397 back to huge pages. If the value is a non-zero N, KVM will
2398 zap a portion (see ratio above) of the pages every N msecs.
2399 If the value is 0 (the default), KVM will pick a period based
2400 on the ratio, such that a page is zapped after 1 hour on average.
2402 kvm-amd.nested= [KVM,AMD] Allow nested virtualization in KVM/SVM.
2403 Default is 1 (enabled)
2405 kvm-amd.npt= [KVM,AMD] Disable nested paging (virtualized MMU)
2407 Default is 1 (enabled) if in 64-bit or 32-bit PAE mode.
2410 [KVM,ARM] Select one of KVM/arm64's modes of operation.
2412 none: Forcefully disable KVM.
2414 nvhe: Standard nVHE-based mode, without support for
2417 protected: nVHE-based mode with support for guests whose
2418 state is kept private from the host.
2419 Not valid if the kernel is running in EL2.
2421 Defaults to VHE/nVHE based on hardware support. Setting
2422 mode to "protected" will disable kexec and hibernation
2425 kvm-arm.vgic_v3_group0_trap=
2426 [KVM,ARM] Trap guest accesses to GICv3 group-0
2429 kvm-arm.vgic_v3_group1_trap=
2430 [KVM,ARM] Trap guest accesses to GICv3 group-1
2433 kvm-arm.vgic_v3_common_trap=
2434 [KVM,ARM] Trap guest accesses to GICv3 common
2437 kvm-arm.vgic_v4_enable=
2438 [KVM,ARM] Allow use of GICv4 for direct injection of
2441 kvm_cma_resv_ratio=n [PPC]
2442 Reserves given percentage from system memory area for
2443 contiguous memory allocation for KVM hash pagetable
2445 By default it reserves 5% of total system memory.
2449 kvm-intel.ept= [KVM,Intel] Disable extended page tables
2450 (virtualized MMU) support on capable Intel chips.
2451 Default is 1 (enabled)
2453 kvm-intel.emulate_invalid_guest_state=
2454 [KVM,Intel] Disable emulation of invalid guest state.
2455 Ignored if kvm-intel.enable_unrestricted_guest=1, as
2456 guest state is never invalid for unrestricted guests.
2457 This param doesn't apply to nested guests (L2), as KVM
2458 never emulates invalid L2 guest state.
2459 Default is 1 (enabled)
2461 kvm-intel.flexpriority=
2462 [KVM,Intel] Disable FlexPriority feature (TPR shadow).
2463 Default is 1 (enabled)
2466 [KVM,Intel] Enable VMX nesting (nVMX).
2467 Default is 0 (disabled)
2469 kvm-intel.unrestricted_guest=
2470 [KVM,Intel] Disable unrestricted guest feature
2471 (virtualized real and unpaged mode) on capable
2472 Intel chips. Default is 1 (enabled)
2474 kvm-intel.vmentry_l1d_flush=[KVM,Intel] Mitigation for L1 Terminal Fault
2477 Valid arguments: never, cond, always
2479 always: L1D cache flush on every VMENTER.
2480 cond: Flush L1D on VMENTER only when the code between
2481 VMEXIT and VMENTER can leak host memory.
2482 never: Disables the mitigation
2484 Default is cond (do L1 cache flush in specific instances)
2486 kvm-intel.vpid= [KVM,Intel] Disable Virtual Processor Identification
2487 feature (tagged TLBs) on capable Intel chips.
2488 Default is 1 (enabled)
2490 l1d_flush= [X86,INTEL]
2491 Control mitigation for L1D based snooping vulnerability.
2493 Certain CPUs are vulnerable to an exploit against CPU
2494 internal buffers which can forward information to a
2495 disclosure gadget under certain conditions.
2497 In vulnerable processors, the speculatively
2498 forwarded data can be used in a cache side channel
2499 attack, to access data to which the attacker does
2500 not have direct access.
2502 This parameter controls the mitigation. The
2505 on - enable the interface for the mitigation
2507 l1tf= [X86] Control mitigation of the L1TF vulnerability on
2510 The kernel PTE inversion protection is unconditionally
2511 enabled and cannot be disabled.
2514 Provides all available mitigations for the
2515 L1TF vulnerability. Disables SMT and
2516 enables all mitigations in the
2517 hypervisors, i.e. unconditional L1D flush.
2519 SMT control and L1D flush control via the
2520 sysfs interface is still possible after
2521 boot. Hypervisors will issue a warning
2522 when the first VM is started in a
2523 potentially insecure configuration,
2524 i.e. SMT enabled or L1D flush disabled.
2527 Same as 'full', but disables SMT and L1D
2528 flush runtime control. Implies the
2529 'nosmt=force' command line option.
2530 (i.e. sysfs control of SMT is disabled.)
2533 Leaves SMT enabled and enables the default
2534 hypervisor mitigation, i.e. conditional
2537 SMT control and L1D flush control via the
2538 sysfs interface is still possible after
2539 boot. Hypervisors will issue a warning
2540 when the first VM is started in a
2541 potentially insecure configuration,
2542 i.e. SMT enabled or L1D flush disabled.
2546 Disables SMT and enables the default
2547 hypervisor mitigation.
2549 SMT control and L1D flush control via the
2550 sysfs interface is still possible after
2551 boot. Hypervisors will issue a warning
2552 when the first VM is started in a
2553 potentially insecure configuration,
2554 i.e. SMT enabled or L1D flush disabled.
2557 Same as 'flush', but hypervisors will not
2558 warn when a VM is started in a potentially
2559 insecure configuration.
2562 Disables hypervisor mitigations and doesn't
2564 It also drops the swap size and available
2565 RAM limit restriction on both hypervisor and
2570 For details see: Documentation/admin-guide/hw-vuln/l1tf.rst
2576 lapic [X86-32,APIC] Enable the local APIC even if BIOS
2579 lapic= [X86,APIC] Do not use TSC deadline
2580 value for LAPIC timer one-shot implementation. Default
2581 back to the programmable timer unit in the LAPIC.
2582 Format: notscdeadline
2584 lapic_timer_c2_ok [X86,APIC] trust the local apic timer
2587 libata.dma= [LIBATA] DMA control
2588 libata.dma=0 Disable all PATA and SATA DMA
2589 libata.dma=1 PATA and SATA Disk DMA only
2590 libata.dma=2 ATAPI (CDROM) DMA only
2591 libata.dma=4 Compact Flash DMA only
2592 Combinations also work, so libata.dma=3 enables DMA
2593 for disks and CDROMs, but not CFs.
2595 libata.ignore_hpa= [LIBATA] Ignore HPA limit
2596 libata.ignore_hpa=0 keep BIOS limits (default)
2597 libata.ignore_hpa=1 ignore limits, using full disk
2599 libata.noacpi [LIBATA] Disables use of ACPI in libata suspend/resume
2603 libata.force= [LIBATA] Force configurations. The format is comma-
2604 separated list of "[ID:]VAL" where ID is
2605 PORT[.DEVICE]. PORT and DEVICE are decimal numbers
2606 matching port, link or device. Basically, it matches
2607 the ATA ID string printed on console by libata. If
2608 the whole ID part is omitted, the last PORT and DEVICE
2609 values are used. If ID hasn't been specified yet, the
2610 configuration applies to all ports, links and devices.
2612 If only DEVICE is omitted, the parameter applies to
2613 the port and all links and devices behind it. DEVICE
2614 number of 0 either selects the first device or the
2615 first fan-out link behind PMP device. It does not
2616 select the host link. DEVICE number of 15 selects the
2617 host link and device attached to it.
2619 The VAL specifies the configuration to force. As long
2620 as there's no ambiguity shortcut notation is allowed.
2621 For example, both 1.5 and 1.5G would work for 1.5Gbps.
2622 The following configurations can be forced.
2624 * Cable type: 40c, 80c, short40c, unk, ign or sata.
2625 Any ID with matching PORT is used.
2627 * SATA link speed limit: 1.5Gbps or 3.0Gbps.
2629 * Transfer mode: pio[0-7], mwdma[0-4] and udma[0-7].
2630 udma[/][16,25,33,44,66,100,133] notation is also
2633 * [no]ncq: Turn on or off NCQ.
2635 * [no]ncqtrim: Turn off queued DSM TRIM.
2637 * nohrst, nosrst, norst: suppress hard, soft
2640 * rstonce: only attempt one reset during
2641 hot-unplug link recovery
2643 * dump_id: dump IDENTIFY data.
2645 * atapi_dmadir: Enable ATAPI DMADIR bridge support
2647 * disable: Disable this device.
2649 If there are multiple matching configurations changing
2650 the same attribute, the last one is used.
2652 memblock=debug [KNL] Enable memblock debug messages.
2654 load_ramdisk= [RAM] [Deprecated]
2656 lockd.nlm_grace_period=P [NFS] Assign grace period.
2659 lockd.nlm_tcpport=N [NFS] Assign TCP port.
2662 lockd.nlm_timeout=T [NFS] Assign timeout value.
2665 lockd.nlm_udpport=M [NFS] Assign UDP port.
2668 lockdown= [SECURITY]
2669 { integrity | confidentiality }
2670 Enable the kernel lockdown feature. If set to
2671 integrity, kernel features that allow userland to
2672 modify the running kernel are disabled. If set to
2673 confidentiality, kernel features that allow userland
2674 to extract confidential information from the kernel
2677 locktorture.nreaders_stress= [KNL]
2678 Set the number of locking read-acquisition kthreads.
2679 Defaults to being automatically set based on the
2680 number of online CPUs.
2682 locktorture.nwriters_stress= [KNL]
2683 Set the number of locking write-acquisition kthreads.
2685 locktorture.onoff_holdoff= [KNL]
2686 Set time (s) after boot for CPU-hotplug testing.
2688 locktorture.onoff_interval= [KNL]
2689 Set time (s) between CPU-hotplug operations, or
2690 zero to disable CPU-hotplug testing.
2692 locktorture.shuffle_interval= [KNL]
2693 Set task-shuffle interval (jiffies). Shuffling
2694 tasks allows some CPUs to go into dyntick-idle
2695 mode during the locktorture test.
2697 locktorture.shutdown_secs= [KNL]
2698 Set time (s) after boot system shutdown. This
2699 is useful for hands-off automated testing.
2701 locktorture.stat_interval= [KNL]
2702 Time (s) between statistics printk()s.
2704 locktorture.stutter= [KNL]
2705 Time (s) to stutter testing, for example,
2706 specifying five seconds causes the test to run for
2707 five seconds, wait for five seconds, and so on.
2708 This tests the locking primitive's ability to
2709 transition abruptly to and from idle.
2711 locktorture.torture_type= [KNL]
2712 Specify the locking implementation to test.
2714 locktorture.verbose= [KNL]
2715 Enable additional printk() statements.
2717 logibm.irq= [HW,MOUSE] Logitech Bus Mouse Driver
2720 loglevel= All Kernel Messages with a loglevel smaller than the
2721 console loglevel will be printed to the console. It can
2722 also be changed with klogd or other programs. The
2723 loglevels are defined as follows:
2725 0 (KERN_EMERG) system is unusable
2726 1 (KERN_ALERT) action must be taken immediately
2727 2 (KERN_CRIT) critical conditions
2728 3 (KERN_ERR) error conditions
2729 4 (KERN_WARNING) warning conditions
2730 5 (KERN_NOTICE) normal but significant condition
2731 6 (KERN_INFO) informational
2732 7 (KERN_DEBUG) debug-level messages
2734 log_buf_len=n[KMG] Sets the size of the printk ring buffer,
2735 in bytes. n must be a power of two and greater
2736 than the minimal size. The minimal size is defined
2737 by LOG_BUF_SHIFT kernel config parameter. There is
2738 also CONFIG_LOG_CPU_MAX_BUF_SHIFT config parameter
2739 that allows to increase the default size depending on
2740 the number of CPUs. See init/Kconfig for more details.
2742 logo.nologo [FB] Disables display of the built-in Linux logo.
2743 This may be used to provide more screen space for
2744 kernel log messages and is useful when debugging
2745 kernel boot problems.
2747 lp=0 [LP] Specify parallel ports to use, e.g,
2748 lp=port[,port...] lp=none,parport0 (lp0 not configured, lp1 uses
2749 lp=reset first parallel port). 'lp=0' disables the
2750 lp=auto printer driver. 'lp=reset' (which can be
2751 specified in addition to the ports) causes
2752 attached printers to be reset. Using
2753 lp=port1,port2,... specifies the parallel ports
2754 to associate lp devices with, starting with
2755 lp0. A port specification may be 'none' to skip
2756 that lp device, or a parport name such as
2757 'parport0'. Specifying 'lp=auto' instead of a
2758 port specification list means that device IDs
2759 from each port should be examined, to see if
2760 an IEEE 1284-compliant printer is attached; if
2761 so, the driver will manage that printer.
2762 See also header of drivers/char/lp.c.
2765 Sets loops_per_jiffy to given constant, thus avoiding
2766 time-consuming boot-time autodetection (up to 250 ms per
2767 CPU). 0 enables autodetection (default). To determine
2768 the correct value for your kernel, boot with normal
2769 autodetection and see what value is printed. Note that
2770 on SMP systems the preset will be applied to all CPUs,
2771 which is likely to cause problems if your CPUs need
2772 significantly divergent settings. An incorrect value
2773 will cause delays in the kernel to be wrong, leading to
2774 unpredictable I/O errors and other breakage. Although
2775 unlikely, in the extreme case this might damage your
2779 Format: <io>,<irq>,<dma>
2781 lsm.debug [SECURITY] Enable LSM initialization debugging output.
2784 [SECURITY] Choose order of LSM initialization. This
2785 overrides CONFIG_LSM, and the "security=" parameter.
2787 machvec= [IA-64] Force the use of a particular machine-vector
2788 (machvec) in a generic kernel.
2789 Example: machvec=hpzx1
2791 machtype= [Loongson] Share the same kernel image file between
2792 different yeeloong laptops.
2793 Example: machtype=lemote-yeeloong-2f-7inch
2795 max_addr=nn[KMG] [KNL,BOOT,ia64] All physical memory greater
2796 than or equal to this physical address is ignored.
2798 maxcpus= [SMP] Maximum number of processors that an SMP kernel
2799 will bring up during bootup. maxcpus=n : n >= 0 limits
2800 the kernel to bring up 'n' processors. Surely after
2801 bootup you can bring up the other plugged cpu by executing
2802 "echo 1 > /sys/devices/system/cpu/cpuX/online". So maxcpus
2803 only takes effect during system bootup.
2804 While n=0 is a special case, it is equivalent to "nosmp",
2805 which also disables the IO APIC.
2807 max_loop= [LOOP] The number of loop block devices that get
2808 (loop.max_loop) unconditionally pre-created at init time. The default
2809 number is configured by BLK_DEV_LOOP_MIN_COUNT. Instead
2810 of statically allocating a predefined number, loop
2811 devices can be requested on-demand with the
2812 /dev/loop-control interface.
2814 mce [X86-32] Machine Check Exception
2816 mce=option [X86-64] See Documentation/x86/x86_64/boot-options.rst
2818 md= [HW] RAID subsystems devices and level
2819 See Documentation/admin-guide/md.rst.
2822 Format: <first>,<last>
2823 Specifies range of consoles to be captured by the MDA.
2826 Control mitigation for the Micro-architectural Data
2827 Sampling (MDS) vulnerability.
2829 Certain CPUs are vulnerable to an exploit against CPU
2830 internal buffers which can forward information to a
2831 disclosure gadget under certain conditions.
2833 In vulnerable processors, the speculatively
2834 forwarded data can be used in a cache side channel
2835 attack, to access data to which the attacker does
2836 not have direct access.
2838 This parameter controls the MDS mitigation. The
2841 full - Enable MDS mitigation on vulnerable CPUs
2842 full,nosmt - Enable MDS mitigation and disable
2843 SMT on vulnerable CPUs
2844 off - Unconditionally disable MDS mitigation
2846 On TAA-affected machines, mds=off can be prevented by
2847 an active TAA mitigation as both vulnerabilities are
2848 mitigated with the same mechanism so in order to disable
2849 this mitigation, you need to specify tsx_async_abort=off
2852 Not specifying this option is equivalent to
2855 For details see: Documentation/admin-guide/hw-vuln/mds.rst
2857 mem=nn[KMG] [HEXAGON] Set the memory size.
2858 Must be specified, otherwise memory size will be 0.
2860 mem=nn[KMG] [KNL,BOOT] Force usage of a specific amount of memory
2861 Amount of memory to be used in cases as follows:
2864 2 when the kernel is not able to see the whole system memory;
2865 3 memory that lies after 'mem=' boundary is excluded from
2866 the hypervisor, then assigned to KVM guests.
2867 4 to limit the memory available for kdump kernel.
2869 [ARC,MICROBLAZE] - the limit applies only to low memory,
2870 high memory is not affected.
2872 [ARM64] - only limits memory covered by the linear
2873 mapping. The NOMAP regions are not affected.
2875 [X86] Work as limiting max address. Use together
2876 with memmap= to avoid physical address space collisions.
2877 Without memmap= PCI devices could be placed at addresses
2878 belonging to unused RAM.
2880 Note that this only takes effects during boot time since
2881 in above case 3, memory may need be hot added after boot
2882 if system memory of hypervisor is not sufficient.
2885 [ARM,MIPS] - override the memory layout reported by
2887 Define a memory region of size nn[KMG] starting at
2889 Multiple different regions can be specified with
2890 multiple mem= parameters on the command line.
2892 mem=nopentium [BUGS=X86-32] Disable usage of 4MB pages for kernel
2896 [KNL,SH] Allow user to override the default size for
2897 per-device physically contiguous DMA buffers.
2899 memhp_default_state=online/offline
2900 [KNL] Set the initial state for the memory hotplug
2901 onlining policy. If not specified, the default value is
2902 set according to the
2903 CONFIG_MEMORY_HOTPLUG_DEFAULT_ONLINE kernel config
2905 See Documentation/admin-guide/mm/memory-hotplug.rst.
2907 memmap=exactmap [KNL,X86] Enable setting of an exact
2908 E820 memory map, as specified by the user.
2909 Such memmap=exactmap lines can be constructed based on
2910 BIOS output or other requirements. See the memmap=nn@ss
2913 memmap=nn[KMG]@ss[KMG]
2914 [KNL, X86, MIPS, XTENSA] Force usage of a specific region of memory.
2915 Region of memory to be used is from ss to ss+nn.
2916 If @ss[KMG] is omitted, it is equivalent to mem=nn[KMG],
2917 which limits max address to nn[KMG].
2918 Multiple different regions can be specified,
2921 memmap=100M@2G,100M#3G,1G!1024G
2923 memmap=nn[KMG]#ss[KMG]
2924 [KNL,ACPI] Mark specific memory as ACPI data.
2925 Region of memory to be marked is from ss to ss+nn.
2927 memmap=nn[KMG]$ss[KMG]
2928 [KNL,ACPI] Mark specific memory as reserved.
2929 Region of memory to be reserved is from ss to ss+nn.
2930 Example: Exclude memory from 0x18690000-0x1869ffff
2931 memmap=64K$0x18690000
2933 memmap=0x10000$0x18690000
2934 Some bootloaders may need an escape character before '$',
2935 like Grub2, otherwise '$' and the following number
2938 memmap=nn[KMG]!ss[KMG]
2939 [KNL,X86] Mark specific memory as protected.
2940 Region of memory to be used, from ss to ss+nn.
2941 The memory region may be marked as e820 type 12 (0xc)
2942 and is NVDIMM or ADR memory.
2944 memmap=<size>%<offset>-<oldtype>+<newtype>
2945 [KNL,ACPI] Convert memory within the specified region
2946 from <oldtype> to <newtype>. If "-<oldtype>" is left
2947 out, the whole region will be marked as <newtype>,
2948 even if previously unavailable. If "+<newtype>" is left
2949 out, matching memory will be removed. Types are
2950 specified as e820 types, e.g., 1 = RAM, 2 = reserved,
2951 3 = ACPI, 12 = PRAM.
2953 memory_corruption_check=0/1 [X86]
2954 Some BIOSes seem to corrupt the first 64k of
2955 memory when doing things like suspend/resume.
2956 Setting this option will scan the memory
2957 looking for corruption. Enabling this will
2958 both detect corruption and prevent the kernel
2959 from using the memory being corrupted.
2960 However, its intended as a diagnostic tool; if
2961 repeatable BIOS-originated corruption always
2962 affects the same memory, you can use memmap=
2963 to prevent the kernel from using that memory.
2965 memory_corruption_check_size=size [X86]
2966 By default it checks for corruption in the low
2967 64k, making this memory unavailable for normal
2968 use. Use this parameter to scan for
2969 corruption in more or less memory.
2971 memory_corruption_check_period=seconds [X86]
2972 By default it checks for corruption every 60
2973 seconds. Use this parameter to check at some
2974 other rate. 0 disables periodic checking.
2976 memory_hotplug.memmap_on_memory
2977 [KNL,X86,ARM] Boolean flag to enable this feature.
2978 Format: {on | off (default)}
2979 When enabled, runtime hotplugged memory will
2980 allocate its internal metadata (struct pages)
2981 from the hotadded memory which will allow to
2982 hotadd a lot of memory without requiring
2983 additional memory to do so.
2984 This feature is disabled by default because it
2985 has some implication on large (e.g. GB)
2986 allocations in some configurations (e.g. small
2988 The state of the flag can be read in
2989 /sys/module/memory_hotplug/parameters/memmap_on_memory.
2990 Note that even when enabled, there are a few cases where
2991 the feature is not effective.
2993 This is not compatible with hugetlb_free_vmemmap. If
2994 both parameters are enabled, hugetlb_free_vmemmap takes
2995 precedence over memory_hotplug.memmap_on_memory.
2997 memtest= [KNL,X86,ARM,M68K,PPC,RISCV] Enable memtest
2999 default : 0 <disable>
3000 Specifies the number of memtest passes to be
3001 performed. Each pass selects another test
3002 pattern from a given set of patterns. Memtest
3003 fills the memory with this pattern, validates
3004 memory contents and reserves bad memory
3005 regions that are detected.
3007 mem_encrypt= [X86-64] AMD Secure Memory Encryption (SME) control
3008 Valid arguments: on, off
3009 Default (depends on kernel configuration option):
3010 on (CONFIG_AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT=y)
3011 off (CONFIG_AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT=n)
3012 mem_encrypt=on: Activate SME
3013 mem_encrypt=off: Do not activate SME
3015 Refer to Documentation/virt/kvm/amd-memory-encryption.rst
3016 for details on when memory encryption can be activated.
3018 mem_sleep_default= [SUSPEND] Default system suspend mode:
3019 s2idle - Suspend-To-Idle
3020 shallow - Power-On Suspend or equivalent (if supported)
3021 deep - Suspend-To-RAM or equivalent (if supported)
3022 See Documentation/admin-guide/pm/sleep-states.rst.
3024 meye.*= [HW] Set MotionEye Camera parameters
3025 See Documentation/admin-guide/media/meye.rst.
3027 mfgpt_irq= [IA-32] Specify the IRQ to use for the
3028 Multi-Function General Purpose Timers on AMD Geode
3031 mfgptfix [X86-32] Fix MFGPT timers on AMD Geode platforms when
3032 the BIOS has incorrectly applied a workaround. TinyBIOS
3033 version 0.98 is known to be affected, 0.99 fixes the
3034 problem by letting the user disable the workaround.
3038 min_addr=nn[KMG] [KNL,BOOT,ia64] All physical memory below this
3039 physical address is ignored.
3041 mini2440= [ARM,HW,KNL]
3042 Format:[0..2][b][c][t]
3044 MINI2440 configuration specification:
3045 0 - The attached screen is the 3.5" TFT
3046 1 - The attached screen is the 7" TFT
3047 2 - The VGA Shield is attached (1024x768)
3048 Leaving out the screen size parameter will not load
3049 the TFT driver, and the framebuffer will be left
3051 b - Enable backlight. The TFT backlight pin will be
3052 linked to the kernel VESA blanking code and a GPIO
3053 LED. This parameter is not necessary when using the
3055 c - Enable the s3c camera interface.
3056 t - Reserved for enabling touchscreen support. The
3057 touchscreen support is not enabled in the mainstream
3058 kernel as of 2.6.30, a preliminary port can be found
3059 in the "bleeding edge" mini2440 support kernel at
3060 https://repo.or.cz/w/linux-2.6/mini2440.git
3063 [X86,PPC,S390,ARM64] Control optional mitigations for
3064 CPU vulnerabilities. This is a set of curated,
3065 arch-independent options, each of which is an
3066 aggregation of existing arch-specific options.
3069 Disable all optional CPU mitigations. This
3070 improves system performance, but it may also
3071 expose users to several CPU vulnerabilities.
3072 Equivalent to: nopti [X86,PPC]
3074 nospectre_v1 [X86,PPC]
3076 nospectre_v2 [X86,PPC,S390,ARM64]
3077 spectre_v2_user=off [X86]
3078 spec_store_bypass_disable=off [X86,PPC]
3079 ssbd=force-off [ARM64]
3082 tsx_async_abort=off [X86]
3083 kvm.nx_huge_pages=off [X86]
3084 no_entry_flush [PPC]
3085 no_uaccess_flush [PPC]
3088 This does not have any effect on
3089 kvm.nx_huge_pages when
3090 kvm.nx_huge_pages=force.
3093 Mitigate all CPU vulnerabilities, but leave SMT
3094 enabled, even if it's vulnerable. This is for
3095 users who don't want to be surprised by SMT
3096 getting disabled across kernel upgrades, or who
3097 have other ways of avoiding SMT-based attacks.
3098 Equivalent to: (default behavior)
3101 Mitigate all CPU vulnerabilities, disabling SMT
3102 if needed. This is for users who always want to
3103 be fully mitigated, even if it means losing SMT.
3104 Equivalent to: l1tf=flush,nosmt [X86]
3105 mds=full,nosmt [X86]
3106 tsx_async_abort=full,nosmt [X86]
3109 [KNL] When CONFIG_DEBUG_MEMORY_INIT is set, this
3110 parameter allows control of the logging verbosity for
3111 the additional memory initialisation checks. A value
3112 of 0 disables mminit logging and a level of 4 will
3113 log everything. Information is printed at KERN_DEBUG
3114 so loglevel=8 may also need to be specified.
3117 [KNL] When CONFIG_MODULE_SIG is set, this means that
3118 modules without (valid) signatures will fail to load.
3119 Note that if CONFIG_MODULE_SIG_FORCE is set, that
3120 is always true, so this option does nothing.
3122 module_blacklist= [KNL] Do not load a comma-separated list of
3123 modules. Useful for debugging problem modules.
3126 [MOUSE] Maximum time between finger touching and
3127 leaving touchpad surface for touch to be considered
3128 a tap and be reported as a left button click (for
3129 touchpads working in absolute mode only).
3131 mousedev.xres= [MOUSE] Horizontal screen resolution, used for devices
3132 reporting absolute coordinates, such as tablets
3133 mousedev.yres= [MOUSE] Vertical screen resolution, used for devices
3134 reporting absolute coordinates, such as tablets
3136 movablecore= [KNL,X86,IA-64,PPC]
3137 Format: nn[KMGTPE] | nn%
3138 This parameter is the complement to kernelcore=, it
3139 specifies the amount of memory used for migratable
3140 allocations. If both kernelcore and movablecore is
3141 specified, then kernelcore will be at *least* the
3142 specified value but may be more. If movablecore on its
3143 own is specified, the administrator must be careful
3144 that the amount of memory usable for all allocations
3147 movable_node [KNL] Boot-time switch to make hotplugable memory
3148 NUMA nodes to be movable. This means that the memory
3149 of such nodes will be usable only for movable
3150 allocations which rules out almost all kernel
3151 allocations. Use with caution!
3153 MTD_Partition= [MTD]
3154 Format: <name>,<region-number>,<size>,<offset>
3156 MTD_Region= [MTD] Format:
3157 <name>,<region-number>[,<base>,<size>,<buswidth>,<altbuswidth>]
3160 See drivers/mtd/parsers/cmdlinepart.c
3162 multitce=off [PPC] This parameter disables the use of the pSeries
3163 firmware feature for updating multiple TCE entries
3166 onenand.bdry= [HW,MTD] Flex-OneNAND Boundary Configuration
3168 Format: [die0_boundary][,die0_lock][,die1_boundary][,die1_lock]
3170 boundary - index of last SLC block on Flex-OneNAND.
3171 The remaining blocks are configured as MLC blocks.
3172 lock - Configure if Flex-OneNAND boundary should be locked.
3173 Once locked, the boundary cannot be changed.
3174 1 indicates lock status, 0 indicates unlock status.
3177 ARM/S3C2412 JIVE boot control
3179 See arch/arm/mach-s3c/mach-jive.c
3181 mtouchusb.raw_coordinates=
3182 [HW] Make the MicroTouch USB driver use raw coordinates
3183 ('y', default) or cooked coordinates ('n')
3185 mtrr_chunk_size=nn[KMG] [X86]
3186 used for mtrr cleanup. It is largest continuous chunk
3187 that could hold holes aka. UC entries.
3189 mtrr_gran_size=nn[KMG] [X86]
3190 Used for mtrr cleanup. It is granularity of mtrr block.
3192 Large value could prevent small alignment from
3195 mtrr_spare_reg_nr=n [X86]
3197 Range: 0,7 : spare reg number
3199 Used for mtrr cleanup. It is spare mtrr entries number.
3200 Set to 2 or more if your graphical card needs more.
3202 n2= [NET] SDL Inc. RISCom/N2 synchronous serial card
3204 netdev= [NET] Network devices parameters
3205 Format: <irq>,<io>,<mem_start>,<mem_end>,<name>
3206 Note that mem_start is often overloaded to mean
3207 something different and driver-specific.
3208 This usage is only documented in each driver source
3212 [NETFILTER] Enable connection tracking flow accounting
3213 0 to disable accounting
3214 1 to enable accounting
3217 nfsaddrs= [NFS] Deprecated. Use ip= instead.
3218 See Documentation/admin-guide/nfs/nfsroot.rst.
3220 nfsroot= [NFS] nfs root filesystem for disk-less boxes.
3221 See Documentation/admin-guide/nfs/nfsroot.rst.
3223 nfsrootdebug [NFS] enable nfsroot debugging messages.
3224 See Documentation/admin-guide/nfs/nfsroot.rst.
3226 nfs.callback_nr_threads=
3227 [NFSv4] set the total number of threads that the
3228 NFS client will assign to service NFSv4 callback
3231 nfs.callback_tcpport=
3232 [NFS] set the TCP port on which the NFSv4 callback
3233 channel should listen.
3236 [NFS] sets the pathname to the program which is used
3237 to update the NFS client cache entries.
3239 nfs.cache_getent_timeout=
3240 [NFS] sets the timeout after which an attempt to
3241 update a cache entry is deemed to have failed.
3243 nfs.idmap_cache_timeout=
3244 [NFS] set the maximum lifetime for idmapper cache
3248 [NFS] enable 64-bit inode numbers.
3249 If zero, the NFS client will fake up a 32-bit inode
3250 number for the readdir() and stat() syscalls instead
3251 of returning the full 64-bit number.
3252 The default is to return 64-bit inode numbers.
3254 nfs.max_session_cb_slots=
3255 [NFSv4.1] Sets the maximum number of session
3256 slots the client will assign to the callback
3257 channel. This determines the maximum number of
3258 callbacks the client will process in parallel for
3259 a particular server.
3261 nfs.max_session_slots=
3262 [NFSv4.1] Sets the maximum number of session slots
3263 the client will attempt to negotiate with the server.
3264 This limits the number of simultaneous RPC requests
3265 that the client can send to the NFSv4.1 server.
3266 Note that there is little point in setting this
3267 value higher than the max_tcp_slot_table_limit.
3269 nfs.nfs4_disable_idmapping=
3270 [NFSv4] When set to the default of '1', this option
3271 ensures that both the RPC level authentication
3272 scheme and the NFS level operations agree to use
3273 numeric uids/gids if the mount is using the
3274 'sec=sys' security flavour. In effect it is
3275 disabling idmapping, which can make migration from
3276 legacy NFSv2/v3 systems to NFSv4 easier.
3277 Servers that do not support this mode of operation
3278 will be autodetected by the client, and it will fall
3279 back to using the idmapper.
3280 To turn off this behaviour, set the value to '0'.
3282 [NFS4] Specify an additional fixed unique ident-
3283 ification string that NFSv4 clients can insert into
3284 their nfs_client_id4 string. This is typically a
3285 UUID that is generated at system install time.
3287 nfs.send_implementation_id =
3288 [NFSv4.1] Send client implementation identification
3289 information in exchange_id requests.
3290 If zero, no implementation identification information
3292 The default is to send the implementation identification
3295 nfs.recover_lost_locks =
3296 [NFSv4] Attempt to recover locks that were lost due
3297 to a lease timeout on the server. Please note that
3298 doing this risks data corruption, since there are
3299 no guarantees that the file will remain unchanged
3300 after the locks are lost.
3301 If you want to enable the kernel legacy behaviour of
3302 attempting to recover these locks, then set this
3304 The default parameter value of '0' causes the kernel
3305 not to attempt recovery of lost locks.
3307 nfs4.layoutstats_timer =
3308 [NFSv4.2] Change the rate at which the kernel sends
3309 layoutstats to the pNFS metadata server.
3311 Setting this to value to 0 causes the kernel to use
3312 whatever value is the default set by the layout
3313 driver. A non-zero value sets the minimum interval
3314 in seconds between layoutstats transmissions.
3316 nfsd.inter_copy_offload_enable =
3317 [NFSv4.2] When set to 1, the server will support
3318 server-to-server copies for which this server is
3319 the destination of the copy.
3321 nfsd.nfsd4_ssc_umount_timeout =
3322 [NFSv4.2] When used as the destination of a
3323 server-to-server copy, knfsd temporarily mounts
3324 the source server. It caches the mount in case
3325 it will be needed again, and discards it if not
3326 used for the number of milliseconds specified by
3329 nfsd.nfs4_disable_idmapping=
3330 [NFSv4] When set to the default of '1', the NFSv4
3331 server will return only numeric uids and gids to
3332 clients using auth_sys, and will accept numeric uids
3333 and gids from such clients. This is intended to ease
3334 migration from NFSv2/v3.
3337 nmi_backtrace.backtrace_idle [KNL]
3338 Dump stacks even of idle CPUs in response to an
3339 NMI stack-backtrace request.
3341 nmi_debug= [KNL,SH] Specify one or more actions to take
3342 when a NMI is triggered.
3343 Format: [state][,regs][,debounce][,die]
3345 nmi_watchdog= [KNL,BUGS=X86] Debugging features for SMP kernels
3346 Format: [panic,][nopanic,][num]
3348 0 - turn hardlockup detector in nmi_watchdog off
3349 1 - turn hardlockup detector in nmi_watchdog on
3350 When panic is specified, panic when an NMI watchdog
3351 timeout occurs (or 'nopanic' to not panic on an NMI
3352 watchdog, if CONFIG_BOOTPARAM_HARDLOCKUP_PANIC is set)
3353 To disable both hard and soft lockup detectors,
3354 please see 'nowatchdog'.
3355 This is useful when you use a panic=... timeout and
3356 need the box quickly up again.
3358 These settings can be accessed at runtime via
3359 the nmi_watchdog and hardlockup_panic sysctls.
3361 netpoll.carrier_timeout=
3362 [NET] Specifies amount of time (in seconds) that
3363 netpoll should wait for a carrier. By default netpoll
3366 no387 [BUGS=X86-32] Tells the kernel to use the 387 maths
3367 emulation library even if a 387 maths coprocessor
3370 no5lvl [X86-64] Disable 5-level paging mode. Forces
3371 kernel to use 4-level paging instead.
3373 nofsgsbase [X86] Disables FSGSBASE instructions.
3376 [HW] Never suspend the console
3377 Disable suspending of consoles during suspend and
3378 hibernate operations. Once disabled, debugging
3379 messages can reach various consoles while the rest
3380 of the system is being put to sleep (ie, while
3381 debugging driver suspend/resume hooks). This may
3382 not work reliably with all consoles, but is known
3383 to work with serial and VGA consoles.
3384 To facilitate more flexible debugging, we also add
3385 console_suspend, a printk module parameter to control
3386 it. Users could use console_suspend (usually
3387 /sys/module/printk/parameters/console_suspend) to
3388 turn on/off it dynamically.
3390 novmcoredd [KNL,KDUMP]
3391 Disable device dump. Device dump allows drivers to
3392 append dump data to vmcore so you can collect driver
3393 specified debug info. Drivers can append the data
3394 without any limit and this data is stored in memory,
3395 so this may cause significant memory stress. Disabling
3396 device dump can help save memory but the driver debug
3397 data will be no longer available. This parameter
3398 is only available when CONFIG_PROC_VMCORE_DEVICE_DUMP
3401 noaliencache [MM, NUMA, SLAB] Disables the allocation of alien
3402 caches in the slab allocator. Saves per-node memory,
3403 but will impact performance.
3407 noaltinstr [S390] Disables alternative instructions patching
3408 (CPU alternatives feature).
3410 noapic [SMP,APIC] Tells the kernel to not make use of any
3411 IOAPICs that may be present in the system.
3413 noautogroup Disable scheduler automatic task group creation.
3415 nobats [PPC] Do not use BATs for mapping kernel lowmem
3416 on "Classic" PPC cores.
3420 noclflush [BUGS=X86] Don't use the CLFLUSH instruction
3422 delayacct [KNL] Enable per-task delay accounting
3424 nodsp [SH] Disable hardware DSP at boot time.
3426 noefi Disable EFI runtime services support.
3428 no_entry_flush [PPC] Don't flush the L1-D cache when entering the kernel.
3433 On X86-32 available only on PAE configured kernels.
3434 noexec=on: enable non-executable mappings (default)
3435 noexec=off: disable non-executable mappings
3438 Disable SMAP (Supervisor Mode Access Prevention)
3439 even if it is supported by processor.
3442 Disable SMEP (Supervisor Mode Execution Prevention)
3443 even if it is supported by processor.
3446 This affects only 32-bit executables.
3447 noexec32=on: enable non-executable mappings (default)
3448 read doesn't imply executable mappings
3449 noexec32=off: disable non-executable mappings
3450 read implies executable mappings
3452 nofpu [MIPS,SH] Disable hardware FPU at boot time.
3454 nofxsr [BUGS=X86-32] Disables x86 floating point extended
3455 register save and restore. The kernel will only save
3456 legacy floating-point registers on task switch.
3458 nohugeiomap [KNL,X86,PPC,ARM64] Disable kernel huge I/O mappings.
3460 nohugevmalloc [PPC] Disable kernel huge vmalloc mappings.
3462 nosmt [KNL,S390] Disable symmetric multithreading (SMT).
3463 Equivalent to smt=1.
3465 [KNL,X86] Disable symmetric multithreading (SMT).
3466 nosmt=force: Force disable SMT, cannot be undone
3467 via the sysfs control file.
3469 nospectre_v1 [X86,PPC] Disable mitigations for Spectre Variant 1
3470 (bounds check bypass). With this option data leaks are
3471 possible in the system.
3473 nospectre_v2 [X86,PPC_FSL_BOOK3E,ARM64] Disable all mitigations for
3474 the Spectre variant 2 (indirect branch prediction)
3475 vulnerability. System may allow data leaks with this
3478 nospec_store_bypass_disable
3479 [HW] Disable all mitigations for the Speculative Store Bypass vulnerability
3482 [PPC] Don't flush the L1-D cache after accessing user data.
3484 noxsave [BUGS=X86] Disables x86 extended register state save
3485 and restore using xsave. The kernel will fallback to
3486 enabling legacy floating-point and sse state.
3488 noxsaveopt [X86] Disables xsaveopt used in saving x86 extended
3489 register states. The kernel will fall back to use
3490 xsave to save the states. By using this parameter,
3491 performance of saving the states is degraded because
3492 xsave doesn't support modified optimization while
3493 xsaveopt supports it on xsaveopt enabled systems.
3495 noxsaves [X86] Disables xsaves and xrstors used in saving and
3496 restoring x86 extended register state in compacted
3497 form of xsave area. The kernel will fall back to use
3498 xsaveopt and xrstor to save and restore the states
3499 in standard form of xsave area. By using this
3500 parameter, xsave area per process might occupy more
3501 memory on xsaves enabled systems.
3503 nohlt [ARM,ARM64,MICROBLAZE,SH] Forces the kernel to busy wait
3504 in do_idle() and not use the arch_cpu_idle()
3505 implementation; requires CONFIG_GENERIC_IDLE_POLL_SETUP
3506 to be effective. This is useful on platforms where the
3507 sleep(SH) or wfi(ARM,ARM64) instructions do not work
3508 correctly or when doing power measurements to evalute
3509 the impact of the sleep instructions. This is also
3510 useful when using JTAG debugger.
3512 no_file_caps Tells the kernel not to honor file capabilities. The
3513 only way then for a file to be executed with privilege
3514 is to be setuid root or executed by root.
3516 nohalt [IA-64] Tells the kernel not to use the power saving
3517 function PAL_HALT_LIGHT when idle. This increases
3518 power-consumption. On the positive side, it reduces
3519 interrupt wake-up latency, which may improve performance
3520 in certain environments such as networked servers or
3524 Force pointers printed to the console or buffers to be
3525 unhashed. By default, when a pointer is printed via %p
3526 format string, that pointer is "hashed", i.e. obscured
3527 by hashing the pointer value. This is a security feature
3528 that hides actual kernel addresses from unprivileged
3529 users, but it also makes debugging the kernel more
3530 difficult since unequal pointers can no longer be
3531 compared. However, if this command-line option is
3532 specified, then all normal pointers will have their true
3533 value printed. This option should only be specified when
3534 debugging the kernel. Please do not use on production
3537 nohibernate [HIBERNATION] Disable hibernation and resume.
3539 nohz= [KNL] Boottime enable/disable dynamic ticks
3540 Valid arguments: on, off
3543 nohz_full= [KNL,BOOT,SMP,ISOL]
3544 The argument is a cpu list, as described above.
3545 In kernels built with CONFIG_NO_HZ_FULL=y, set
3546 the specified list of CPUs whose tick will be stopped
3547 whenever possible. The boot CPU will be forced outside
3548 the range to maintain the timekeeping. Any CPUs
3549 in this list will have their RCU callbacks offloaded,
3550 just as if they had also been called out in the
3551 rcu_nocbs= boot parameter.
3553 noiotrap [SH] Disables trapped I/O port accesses.
3555 noirqdebug [X86-32] Disables the code which attempts to detect and
3556 disable unhandled interrupt sources.
3558 no_timer_check [X86,APIC] Disables the code which tests for
3559 broken timer IRQ sources.
3561 noisapnp [ISAPNP] Disables ISA PnP code.
3563 noinitrd [RAM] Tells the kernel not to load any configured
3566 nointremap [X86-64, Intel-IOMMU] Do not enable interrupt
3568 [Deprecated - use intremap=off]
3572 noinvpcid [X86] Disable the INVPCID cpu feature.
3574 nojitter [IA-64] Disables jitter checking for ITC timers.
3576 no-kvmclock [X86,KVM] Disable paravirtualized KVM clock driver
3578 no-kvmapf [X86,KVM] Disable paravirtualized asynchronous page
3582 [X86,PV_OPS] Disable paravirtualized VMware scheduler
3583 clock and use the default one.
3585 no-steal-acc [X86,PV_OPS,ARM64] Disable paravirtualized steal time
3586 accounting. steal time is computed, but won't
3587 influence scheduler behaviour
3589 nolapic [X86-32,APIC] Do not enable or use the local APIC.
3591 nolapic_timer [X86-32,APIC] Do not use the local APIC timer.
3593 noltlbs [PPC] Do not use large page/tlb entries for kernel
3594 lowmem mapping on PPC40x and PPC8xx
3596 nomca [IA-64] Disable machine check abort handling
3598 nomce [X86-32] Disable Machine Check Exception
3600 nomfgpt [X86-32] Disable Multi-Function General Purpose
3601 Timer usage (for AMD Geode machines).
3603 nonmi_ipi [X86] Disable using NMI IPIs during panic/reboot to
3604 shutdown the other cpus. Instead use the REBOOT_VECTOR
3607 nomodeset Disable kernel modesetting. DRM drivers will not perform
3608 display-mode changes or accelerated rendering. Only the
3609 system framebuffer will be available for use if this was
3610 set-up by the firmware or boot loader.
3612 Useful as fallback, or for testing and debugging.
3614 nomodule Disable module load
3616 nopat [X86] Disable PAT (page attribute table extension of
3617 pagetables) support.
3619 nopcid [X86-64] Disable the PCID cpu feature.
3621 norandmaps Don't use address space randomization. Equivalent to
3622 echo 0 > /proc/sys/kernel/randomize_va_space
3624 noreplace-smp [X86-32,SMP] Don't replace SMP instructions
3625 with UP alternatives
3627 nordrand [X86] Disable kernel use of the RDRAND and
3628 RDSEED instructions even if they are supported
3629 by the processor. RDRAND and RDSEED are still
3630 available to user space applications.
3632 noresume [SWSUSP] Disables resume and restores original swap
3635 no-scroll [VGA] Disables scrollback.
3636 This is required for the Braillex ib80-piezo Braille
3637 reader made by F.H. Papenmeier (Germany).
3641 nosep [BUGS=X86-32] Disables x86 SYSENTER/SYSEXIT support.
3643 nosgx [X86-64,SGX] Disables Intel SGX kernel support.
3645 nosmp [SMP] Tells an SMP kernel to act as a UP kernel,
3646 and disable the IO APIC. legacy for "maxcpus=0".
3648 nosoftlockup [KNL] Disable the soft-lockup detector.
3650 nosync [HW,M68K] Disables sync negotiation for all devices.
3652 nowatchdog [KNL] Disable both lockup detectors, i.e.
3653 soft-lockup and NMI watchdog (hard-lockup).
3657 nox2apic [X86-64,APIC] Do not enable x2APIC mode.
3659 cpu0_hotplug [X86] Turn on CPU0 hotplug feature when
3660 CONFIG_BOOTPARAM_HOTPLUG_CPU0 is off.
3661 Some features depend on CPU0. Known dependencies are:
3662 1. Resume from suspend/hibernate depends on CPU0.
3663 Suspend/hibernate will fail if CPU0 is offline and you
3664 need to online CPU0 before suspend/hibernate.
3665 2. PIC interrupts also depend on CPU0. CPU0 can't be
3666 removed if a PIC interrupt is detected.
3667 It's said poweroff/reboot may depend on CPU0 on some
3668 machines although I haven't seen such issues so far
3669 after CPU0 is offline on a few tested machines.
3670 If the dependencies are under your control, you can
3671 turn on cpu0_hotplug.
3673 nps_mtm_hs_ctr= [KNL,ARC]
3674 This parameter sets the maximum duration, in
3675 cycles, each HW thread of the CTOP can run
3676 without interruptions, before HW switches it.
3677 The actual maximum duration is 16 times this
3679 Format: integer between 1 and 255
3682 nptcg= [IA-64] Override max number of concurrent global TLB
3683 purges which is reported from either PAL_VM_SUMMARY or
3686 nr_cpus= [SMP] Maximum number of processors that an SMP kernel
3687 could support. nr_cpus=n : n >= 1 limits the kernel to
3688 support 'n' processors. It could be larger than the
3689 number of already plugged CPU during bootup, later in
3690 runtime you can physically add extra cpu until it reaches
3691 n. So during boot up some boot time memory for per-cpu
3692 variables need be pre-allocated for later physical cpu
3695 nr_uarts= [SERIAL] maximum number of UARTs to be registered.
3697 numa=off [KNL, ARM64, PPC, RISCV, SPARC, X86] Disable NUMA, Only
3698 set up a single NUMA node spanning all memory.
3700 numa_balancing= [KNL,ARM64,PPC,RISCV,S390,X86] Enable or disable automatic
3702 Allowed values are enable and disable
3704 numa_zonelist_order= [KNL, BOOT] Select zonelist order for NUMA.
3705 'node', 'default' can be specified
3706 This can be set from sysctl after boot.
3707 See Documentation/admin-guide/sysctl/vm.rst for details.
3709 ohci1394_dma=early [HW] enable debugging via the ohci1394 driver.
3710 See Documentation/core-api/debugging-via-ohci1394.rst for more
3713 olpc_ec_timeout= [OLPC] ms delay when issuing EC commands
3714 Rather than timing out after 20 ms if an EC
3715 command is not properly ACKed, override the length
3716 of the timeout. We have interrupts disabled while
3717 waiting for the ACK, so if this is set too high
3718 interrupts *may* be lost!
3720 omap_mux= [OMAP] Override bootloader pin multiplexing.
3721 Format: <mux_mode0.mode_name=value>...
3722 For example, to override I2C bus2:
3723 omap_mux=i2c2_scl.i2c2_scl=0x100,i2c2_sda.i2c2_sda=0x100
3725 oops=panic Always panic on oopses. Default is to just kill the
3726 process, but there is a small probability of
3727 deadlocking the machine.
3728 This will also cause panics on machine check exceptions.
3729 Useful together with panic=30 to trigger a reboot.
3732 [KNL] Boolean flag to control whether the page allocator
3733 should randomize its free lists. The randomization may
3734 be automatically enabled if the kernel detects it is
3735 running on a platform with a direct-mapped memory-side
3736 cache, and this parameter can be used to
3737 override/disable that behavior. The state of the flag
3738 can be read from sysfs at:
3739 /sys/module/page_alloc/parameters/shuffle.
3741 page_owner= [KNL] Boot-time page_owner enabling option.
3742 Storage of the information about who allocated
3743 each page is disabled in default. With this switch,
3745 on: enable the feature
3747 page_poison= [KNL] Boot-time parameter changing the state of
3748 poisoning on the buddy allocator, available with
3749 CONFIG_PAGE_POISONING=y.
3750 off: turn off poisoning (default)
3751 on: turn on poisoning
3753 page_reporting.page_reporting_order=
3754 [KNL] Minimal page reporting order
3756 Adjust the minimal page reporting order. The page
3757 reporting is disabled when it exceeds (MAX_ORDER-1).
3759 panic= [KNL] Kernel behaviour on panic: delay <timeout>
3760 timeout > 0: seconds before rebooting
3761 timeout = 0: wait forever
3762 timeout < 0: reboot immediately
3765 panic_print= Bitmask for printing system info when panic happens.
3766 User can chose combination of the following bits:
3767 bit 0: print all tasks info
3768 bit 1: print system memory info
3769 bit 2: print timer info
3770 bit 3: print locks info if CONFIG_LOCKDEP is on
3771 bit 4: print ftrace buffer
3772 bit 5: print all printk messages in buffer
3774 panic_on_taint= Bitmask for conditionally calling panic() in add_taint()
3775 Format: <hex>[,nousertaint]
3776 Hexadecimal bitmask representing the set of TAINT flags
3777 that will cause the kernel to panic when add_taint() is
3778 called with any of the flags in this set.
3779 The optional switch "nousertaint" can be utilized to
3780 prevent userspace forced crashes by writing to sysctl
3781 /proc/sys/kernel/tainted any flagset matching with the
3782 bitmask set on panic_on_taint.
3783 See Documentation/admin-guide/tainted-kernels.rst for
3784 extra details on the taint flags that users can pick
3785 to compose the bitmask to assign to panic_on_taint.
3787 panic_on_warn panic() instead of WARN(). Useful to cause kdump
3790 crash_kexec_post_notifiers
3791 Run kdump after running panic-notifiers and dumping
3792 kmsg. This only for the users who doubt kdump always
3793 succeeds in any situation.
3794 Note that this also increases risks of kdump failure,
3795 because some panic notifiers can make the crashed
3796 kernel more unstable.
3798 parkbd.port= [HW] Parallel port number the keyboard adapter is
3799 connected to, default is 0.
3801 parkbd.mode= [HW] Parallel port keyboard adapter mode of operation,
3802 0 for XT, 1 for AT (default is AT).
3805 parport= [HW,PPT] Specify parallel ports. 0 disables.
3806 Format: { 0 | auto | 0xBBB[,IRQ[,DMA]] }
3807 Use 'auto' to force the driver to use any
3808 IRQ/DMA settings detected (the default is to
3809 ignore detected IRQ/DMA settings because of
3810 possible conflicts). You can specify the base
3811 address, IRQ, and DMA settings; IRQ and DMA
3812 should be numbers, or 'auto' (for using detected
3813 settings on that particular port), or 'nofifo'
3814 (to avoid using a FIFO even if it is detected).
3815 Parallel ports are assigned in the order they
3816 are specified on the command line, starting
3819 parport_init_mode= [HW,PPT]
3820 Configure VIA parallel port to operate in
3821 a specific mode. This is necessary on Pegasos
3822 computer where firmware has no options for setting
3823 up parallel port mode and sets it to spp.
3824 Currently this function knows 686a and 8231 chips.
3825 Format: [spp|ps2|epp|ecp|ecpepp]
3827 pata_legacy.all= [HW,LIBATA]
3829 Set to non-zero to probe primary and secondary ISA
3830 port ranges on PCI systems where no PCI PATA device
3831 has been found at either range. Disabled by default.
3833 pata_legacy.autospeed= [HW,LIBATA]
3835 Set to non-zero if a chip is present that snoops speed
3836 changes. Disabled by default.
3838 pata_legacy.ht6560a= [HW,LIBATA]
3840 Set to 1, 2, or 3 for HT 6560A on the primary channel,
3841 the secondary channel, or both channels respectively.
3842 Disabled by default.
3844 pata_legacy.ht6560b= [HW,LIBATA]
3846 Set to 1, 2, or 3 for HT 6560B on the primary channel,
3847 the secondary channel, or both channels respectively.
3848 Disabled by default.
3850 pata_legacy.iordy_mask= [HW,LIBATA]
3852 IORDY enable mask. Set individual bits to allow IORDY
3853 for the respective channel. Bit 0 is for the first
3854 legacy channel handled by this driver, bit 1 is for
3855 the second channel, and so on. The sequence will often
3856 correspond to the primary legacy channel, the secondary
3857 legacy channel, and so on, but the handling of a PCI
3858 bus and the use of other driver options may interfere
3859 with the sequence. By default IORDY is allowed across
3862 pata_legacy.opti82c46x= [HW,LIBATA]
3864 Set to 1, 2, or 3 for Opti 82c611A on the primary
3865 channel, the secondary channel, or both channels
3866 respectively. Disabled by default.
3868 pata_legacy.opti82c611a= [HW,LIBATA]
3870 Set to 1, 2, or 3 for Opti 82c465MV on the primary
3871 channel, the secondary channel, or both channels
3872 respectively. Disabled by default.
3874 pata_legacy.pio_mask= [HW,LIBATA]
3876 PIO mode mask for autospeed devices. Set individual
3877 bits to allow the use of the respective PIO modes.
3878 Bit 0 is for mode 0, bit 1 is for mode 1, and so on.
3879 All modes allowed by default.
3881 pata_legacy.probe_all= [HW,LIBATA]
3883 Set to non-zero to probe tertiary and further ISA
3884 port ranges on PCI systems. Disabled by default.
3886 pata_legacy.probe_mask= [HW,LIBATA]
3888 Probe mask for legacy ISA PATA ports. Depending on
3889 platform configuration and the use of other driver
3890 options up to 6 legacy ports are supported: 0x1f0,
3891 0x170, 0x1e8, 0x168, 0x1e0, 0x160, however probing
3892 of individual ports can be disabled by setting the
3893 corresponding bits in the mask to 1. Bit 0 is for
3894 the first port in the list above (0x1f0), and so on.
3895 By default all supported ports are probed.
3897 pata_legacy.qdi= [HW,LIBATA]
3899 Set to non-zero to probe QDI controllers. By default
3900 set to 1 if CONFIG_PATA_QDI_MODULE, 0 otherwise.
3902 pata_legacy.winbond= [HW,LIBATA]
3904 Set to non-zero to probe Winbond controllers. Use
3905 the standard I/O port (0x130) if 1, otherwise the
3906 value given is the I/O port to use (typically 0x1b0).
3907 By default set to 1 if CONFIG_PATA_WINBOND_VLB_MODULE,
3910 pata_platform.pio_mask= [HW,LIBATA]
3912 Supported PIO mode mask. Set individual bits to allow
3913 the use of the respective PIO modes. Bit 0 is for
3914 mode 0, bit 1 is for mode 1, and so on. Mode 0 only
3918 Halt all CPUs after the first oops has been printed for
3919 the specified number of seconds. This is to be used if
3920 your oopses keep scrolling off the screen.
3925 See header of drivers/block/paride/pcd.c.
3926 See also Documentation/admin-guide/blockdev/paride.rst.
3928 pci=option[,option...] [PCI] various PCI subsystem options.
3930 Some options herein operate on a specific device
3931 or a set of devices (<pci_dev>). These are
3932 specified in one of the following formats:
3934 [<domain>:]<bus>:<dev>.<func>[/<dev>.<func>]*
3935 pci:<vendor>:<device>[:<subvendor>:<subdevice>]
3937 Note: the first format specifies a PCI
3938 bus/device/function address which may change
3939 if new hardware is inserted, if motherboard
3940 firmware changes, or due to changes caused
3941 by other kernel parameters. If the
3942 domain is left unspecified, it is
3943 taken to be zero. Optionally, a path
3944 to a device through multiple device/function
3945 addresses can be specified after the base
3946 address (this is more robust against
3947 renumbering issues). The second format
3948 selects devices using IDs from the
3949 configuration space which may match multiple
3950 devices in the system.
3952 earlydump dump PCI config space before the kernel
3954 off [X86] don't probe for the PCI bus
3955 bios [X86-32] force use of PCI BIOS, don't access
3956 the hardware directly. Use this if your machine
3957 has a non-standard PCI host bridge.
3958 nobios [X86-32] disallow use of PCI BIOS, only direct
3959 hardware access methods are allowed. Use this
3960 if you experience crashes upon bootup and you
3961 suspect they are caused by the BIOS.
3962 conf1 [X86] Force use of PCI Configuration Access
3963 Mechanism 1 (config address in IO port 0xCF8,
3964 data in IO port 0xCFC, both 32-bit).
3965 conf2 [X86] Force use of PCI Configuration Access
3966 Mechanism 2 (IO port 0xCF8 is an 8-bit port for
3967 the function, IO port 0xCFA, also 8-bit, sets
3968 bus number. The config space is then accessed
3969 through ports 0xC000-0xCFFF).
3970 See http://wiki.osdev.org/PCI for more info
3971 on the configuration access mechanisms.
3972 noaer [PCIE] If the PCIEAER kernel config parameter is
3973 enabled, this kernel boot option can be used to
3974 disable the use of PCIE advanced error reporting.
3975 nodomains [PCI] Disable support for multiple PCI
3976 root domains (aka PCI segments, in ACPI-speak).
3977 nommconf [X86] Disable use of MMCONFIG for PCI
3979 check_enable_amd_mmconf [X86] check for and enable
3980 properly configured MMIO access to PCI
3981 config space on AMD family 10h CPU
3982 nomsi [MSI] If the PCI_MSI kernel config parameter is
3983 enabled, this kernel boot option can be used to
3984 disable the use of MSI interrupts system-wide.
3985 noioapicquirk [APIC] Disable all boot interrupt quirks.
3986 Safety option to keep boot IRQs enabled. This
3987 should never be necessary.
3988 ioapicreroute [APIC] Enable rerouting of boot IRQs to the
3989 primary IO-APIC for bridges that cannot disable
3990 boot IRQs. This fixes a source of spurious IRQs
3991 when the system masks IRQs.
3992 noioapicreroute [APIC] Disable workaround that uses the
3993 boot IRQ equivalent of an IRQ that connects to
3994 a chipset where boot IRQs cannot be disabled.
3995 The opposite of ioapicreroute.
3996 biosirq [X86-32] Use PCI BIOS calls to get the interrupt
3997 routing table. These calls are known to be buggy
3998 on several machines and they hang the machine
3999 when used, but on other computers it's the only
4000 way to get the interrupt routing table. Try
4001 this option if the kernel is unable to allocate
4002 IRQs or discover secondary PCI buses on your
4004 rom [X86] Assign address space to expansion ROMs.
4005 Use with caution as certain devices share
4006 address decoders between ROMs and other
4008 norom [X86] Do not assign address space to
4009 expansion ROMs that do not already have
4010 BIOS assigned address ranges.
4011 nobar [X86] Do not assign address space to the
4012 BARs that weren't assigned by the BIOS.
4013 irqmask=0xMMMM [X86] Set a bit mask of IRQs allowed to be
4014 assigned automatically to PCI devices. You can
4015 make the kernel exclude IRQs of your ISA cards
4017 pirqaddr=0xAAAAA [X86] Specify the physical address
4018 of the PIRQ table (normally generated
4019 by the BIOS) if it is outside the
4020 F0000h-100000h range.
4021 lastbus=N [X86] Scan all buses thru bus #N. Can be
4022 useful if the kernel is unable to find your
4023 secondary buses and you want to tell it
4024 explicitly which ones they are.
4025 assign-busses [X86] Always assign all PCI bus
4026 numbers ourselves, overriding
4027 whatever the firmware may have done.
4028 usepirqmask [X86] Honor the possible IRQ mask stored
4029 in the BIOS $PIR table. This is needed on
4030 some systems with broken BIOSes, notably
4031 some HP Pavilion N5400 and Omnibook XE3
4032 notebooks. This will have no effect if ACPI
4033 IRQ routing is enabled.
4034 noacpi [X86] Do not use ACPI for IRQ routing
4035 or for PCI scanning.
4036 use_crs [X86] Use PCI host bridge window information
4037 from ACPI. On BIOSes from 2008 or later, this
4038 is enabled by default. If you need to use this,
4039 please report a bug.
4040 nocrs [X86] Ignore PCI host bridge windows from ACPI.
4041 If you need to use this, please report a bug.
4042 routeirq Do IRQ routing for all PCI devices.
4043 This is normally done in pci_enable_device(),
4044 so this option is a temporary workaround
4045 for broken drivers that don't call it.
4046 skip_isa_align [X86] do not align io start addr, so can
4047 handle more pci cards
4048 noearly [X86] Don't do any early type 1 scanning.
4049 This might help on some broken boards which
4050 machine check when some devices' config space
4051 is read. But various workarounds are disabled
4052 and some IOMMU drivers will not work.
4053 bfsort Sort PCI devices into breadth-first order.
4054 This sorting is done to get a device
4055 order compatible with older (<= 2.4) kernels.
4056 nobfsort Don't sort PCI devices into breadth-first order.
4057 pcie_bus_tune_off Disable PCIe MPS (Max Payload Size)
4058 tuning and use the BIOS-configured MPS defaults.
4059 pcie_bus_safe Set every device's MPS to the largest value
4060 supported by all devices below the root complex.
4061 pcie_bus_perf Set device MPS to the largest allowable MPS
4062 based on its parent bus. Also set MRRS (Max
4063 Read Request Size) to the largest supported
4064 value (no larger than the MPS that the device
4065 or bus can support) for best performance.
4066 pcie_bus_peer2peer Set every device's MPS to 128B, which
4067 every device is guaranteed to support. This
4068 configuration allows peer-to-peer DMA between
4069 any pair of devices, possibly at the cost of
4070 reduced performance. This also guarantees
4071 that hot-added devices will work.
4072 cbiosize=nn[KMG] The fixed amount of bus space which is
4073 reserved for the CardBus bridge's IO window.
4074 The default value is 256 bytes.
4075 cbmemsize=nn[KMG] The fixed amount of bus space which is
4076 reserved for the CardBus bridge's memory
4077 window. The default value is 64 megabytes.
4080 [<order of align>@]<pci_dev>[; ...]
4081 Specifies alignment and device to reassign
4082 aligned memory resources. How to
4083 specify the device is described above.
4084 If <order of align> is not specified,
4085 PAGE_SIZE is used as alignment.
4086 A PCI-PCI bridge can be specified if resource
4087 windows need to be expanded.
4088 To specify the alignment for several
4089 instances of a device, the PCI vendor,
4090 device, subvendor, and subdevice may be
4091 specified, e.g., 12@pci:8086:9c22:103c:198f
4092 for 4096-byte alignment.
4093 ecrc= Enable/disable PCIe ECRC (transaction layer
4094 end-to-end CRC checking).
4095 bios: Use BIOS/firmware settings. This is the
4099 hpiosize=nn[KMG] The fixed amount of bus space which is
4100 reserved for hotplug bridge's IO window.
4101 Default size is 256 bytes.
4102 hpmmiosize=nn[KMG] The fixed amount of bus space which is
4103 reserved for hotplug bridge's MMIO window.
4104 Default size is 2 megabytes.
4105 hpmmioprefsize=nn[KMG] The fixed amount of bus space which is
4106 reserved for hotplug bridge's MMIO_PREF window.
4107 Default size is 2 megabytes.
4108 hpmemsize=nn[KMG] The fixed amount of bus space which is
4109 reserved for hotplug bridge's MMIO and
4111 Default size is 2 megabytes.
4112 hpbussize=nn The minimum amount of additional bus numbers
4113 reserved for buses below a hotplug bridge.
4115 realloc= Enable/disable reallocating PCI bridge resources
4116 if allocations done by BIOS are too small to
4117 accommodate resources required by all child
4119 off: Turn realloc off
4121 realloc same as realloc=on
4122 noari do not use PCIe ARI.
4123 noats [PCIE, Intel-IOMMU, AMD-IOMMU]
4124 do not use PCIe ATS (and IOMMU device IOTLB).
4125 pcie_scan_all Scan all possible PCIe devices. Otherwise we
4126 only look for one device below a PCIe downstream
4128 big_root_window Try to add a big 64bit memory window to the PCIe
4129 root complex on AMD CPUs. Some GFX hardware
4130 can resize a BAR to allow access to all VRAM.
4131 Adding the window is slightly risky (it may
4132 conflict with unreported devices), so this
4134 disable_acs_redir=<pci_dev>[; ...]
4135 Specify one or more PCI devices (in the format
4136 specified above) separated by semicolons.
4137 Each device specified will have the PCI ACS
4138 redirect capabilities forced off which will
4139 allow P2P traffic between devices through
4140 bridges without forcing it upstream. Note:
4141 this removes isolation between devices and
4142 may put more devices in an IOMMU group.
4143 force_floating [S390] Force usage of floating interrupts.
4144 nomio [S390] Do not use MIO instructions.
4145 norid [S390] ignore the RID field and force use of
4146 one PCI domain per PCI function
4148 pcie_aspm= [PCIE] Forcibly enable or disable PCIe Active State Power
4151 force Enable ASPM even on devices that claim not to support it.
4152 WARNING: Forcing ASPM on may cause system lockups.
4154 pcie_ports= [PCIE] PCIe port services handling:
4155 native Use native PCIe services (PME, AER, DPC, PCIe hotplug)
4156 even if the platform doesn't give the OS permission to
4157 use them. This may cause conflicts if the platform
4158 also tries to use these services.
4159 dpc-native Use native PCIe service for DPC only. May
4160 cause conflicts if firmware uses AER or DPC.
4161 compat Disable native PCIe services (PME, AER, DPC, PCIe
4164 pcie_port_pm= [PCIE] PCIe port power management handling:
4165 off Disable power management of all PCIe ports
4166 force Forcibly enable power management of all PCIe ports
4168 pcie_pme= [PCIE,PM] Native PCIe PME signaling options:
4169 nomsi Do not use MSI for native PCIe PME signaling (this makes
4170 all PCIe root ports use INTx for all services).
4172 pcmv= [HW,PCMCIA] BadgePAD 4
4176 Keep all power-domains already enabled by bootloader on,
4177 even if no driver has claimed them. This is useful
4178 for debug and development, but should not be
4179 needed on a platform with proper driver support.
4182 See Documentation/admin-guide/blockdev/paride.rst.
4184 pdcchassis= [PARISC,HW] Disable/Enable PDC Chassis Status codes at
4187 See arch/parisc/kernel/pdc_chassis.c
4189 percpu_alloc= Select which percpu first chunk allocator to use.
4190 Currently supported values are "embed" and "page".
4191 Archs may support subset or none of the selections.
4192 See comments in mm/percpu.c for details on each
4193 allocator. This parameter is primarily for debugging
4194 and performance comparison.
4197 See Documentation/admin-guide/blockdev/paride.rst.
4200 See Documentation/admin-guide/blockdev/paride.rst.
4202 pirq= [SMP,APIC] Manual mp-table setup
4203 See Documentation/x86/i386/IO-APIC.rst.
4205 plip= [PPT,NET] Parallel port network link
4206 Format: { parport<nr> | timid | 0 }
4207 See also Documentation/admin-guide/parport.rst.
4209 pmtmr= [X86] Manual setup of pmtmr I/O Port.
4210 Override pmtimer IOPort with a hex value.
4213 pmu_override= [PPC] Override the PMU.
4214 This option takes over the PMU facility, so it is no
4215 longer usable by perf. Setting this option starts the
4216 PMU counters by setting MMCR0 to 0 (the FC bit is
4217 cleared). If a number is given, then MMCR1 is set to
4218 that number, otherwise (e.g., 'pmu_override=on'), MMCR1
4221 pm_debug_messages [SUSPEND,KNL]
4222 Enable suspend/resume debug messages during boot up.
4225 Enable PNP debug messages (depends on the
4226 CONFIG_PNP_DEBUG_MESSAGES option). Change at run-time
4227 via /sys/module/pnp/parameters/debug. We always show
4228 current resource usage; turning this on also shows
4229 possible settings and some assignment information.
4235 { on | off | curr | res | no-curr | no-res }
4238 [ISAPNP] Exclude IRQs for the autoconfiguration
4241 [ISAPNP] Exclude DMAs for the autoconfiguration
4243 pnp_reserve_io= [ISAPNP] Exclude I/O ports for the autoconfiguration
4244 Ranges are in pairs (I/O port base and size).
4247 [ISAPNP] Exclude memory regions for the
4249 Ranges are in pairs (memory base and size).
4251 ports= [IP_VS_FTP] IPVS ftp helper module
4253 Up to 8 (IP_VS_APP_MAX_PORTS) ports
4255 Format: <port>,<port>....
4257 powersave=off [PPC] This option disables power saving features.
4258 It specifically disables cpuidle and sets the
4259 platform machine description specific power_save
4260 function to NULL. On Idle the CPU just reduces
4263 ppc_strict_facility_enable
4264 [PPC] This option catches any kernel floating point,
4265 Altivec, VSX and SPE outside of regions specifically
4266 allowed (eg kernel_enable_fpu()/kernel_disable_fpu()).
4267 There is some performance impact when enabling this.
4271 Disable Hardware Transactional Memory
4274 Select preemption mode if you have CONFIG_PREEMPT_DYNAMIC
4275 none - Limited to cond_resched() calls
4276 voluntary - Limited to cond_resched() and might_sleep() calls
4277 full - Any section that isn't explicitly preempt disabled
4278 can be preempted anytime.
4280 print-fatal-signals=
4281 [KNL] debug: print fatal signals
4283 If enabled, warn about various signal handling
4284 related application anomalies: too many signals,
4285 too many POSIX.1 timers, fatal signals causing a
4288 If you hit the warning due to signal overflow,
4289 you might want to try "ulimit -i unlimited".
4293 printk.always_kmsg_dump=
4294 Trigger kmsg_dump for cases other than kernel oops or
4296 Format: <bool> (1/Y/y=enable, 0/N/n=disable)
4299 printk.console_no_auto_verbose=
4300 Disable console loglevel raise on oops, panic
4301 or lockdep-detected issues (only if lock debug is on).
4302 With an exception to setups with low baudrate on
4303 serial console, keeping this 0 is a good choice
4304 in order to provide more debug information.
4306 default: 0 (auto_verbose is enabled)
4308 printk.devkmsg={on,off,ratelimit}
4309 Control writing to /dev/kmsg.
4310 on - unlimited logging to /dev/kmsg from userspace
4311 off - logging to /dev/kmsg disabled
4312 ratelimit - ratelimit the logging
4315 printk.time= Show timing data prefixed to each printk message line
4316 Format: <bool> (1/Y/y=enable, 0/N/n=disable)
4318 processor.max_cstate= [HW,ACPI]
4319 Limit processor to maximum C-state
4320 max_cstate=9 overrides any DMI blacklist limit.
4322 processor.nocst [HW,ACPI]
4323 Ignore the _CST method to determine C-states,
4324 instead using the legacy FADT method
4326 profile= [KNL] Enable kernel profiling via /proc/profile
4327 Format: [<profiletype>,]<number>
4328 Param: <profiletype>: "schedule", "sleep", or "kvm"
4329 [defaults to kernel profiling]
4330 Param: "schedule" - profile schedule points.
4331 Param: "sleep" - profile D-state sleeping (millisecs).
4332 Requires CONFIG_SCHEDSTATS
4333 Param: "kvm" - profile VM exits.
4334 Param: <number> - step/bucket size as a power of 2 for
4335 statistical time based profiling.
4337 prompt_ramdisk= [RAM] [Deprecated]
4339 prot_virt= [S390] enable hosting protected virtual machines
4340 isolated from the hypervisor (if hardware supports
4344 psi= [KNL] Enable or disable pressure stall information
4348 psmouse.proto= [HW,MOUSE] Highest PS2 mouse protocol extension to
4349 probe for; one of (bare|imps|exps|lifebook|any).
4350 psmouse.rate= [HW,MOUSE] Set desired mouse report rate, in reports
4352 psmouse.resetafter= [HW,MOUSE]
4353 Try to reset the device after so many bad packets
4356 [HW,MOUSE] Set desired mouse resolution, in dpi.
4357 psmouse.smartscroll=
4358 [HW,MOUSE] Controls Logitech smartscroll autorepeat.
4359 0 = disabled, 1 = enabled (default).
4361 pstore.backend= Specify the name of the pstore backend to use
4364 See Documentation/admin-guide/blockdev/paride.rst.
4366 pti= [X86-64] Control Page Table Isolation of user and
4367 kernel address spaces. Disabling this feature
4368 removes hardening, but improves performance of
4369 system calls and interrupts.
4371 on - unconditionally enable
4372 off - unconditionally disable
4373 auto - kernel detects whether your CPU model is
4374 vulnerable to issues that PTI mitigates
4376 Not specifying this option is equivalent to pti=auto.
4379 Equivalent to pti=off
4382 [KNL] Number of legacy pty's. Overwrites compiled-in
4385 quiet [KNL] Disable most log messages
4390 See Documentation/admin-guide/md.rst.
4392 ramdisk_size= [RAM] Sizes of RAM disks in kilobytes
4393 See Documentation/admin-guide/blockdev/ramdisk.rst.
4395 ramdisk_start= [RAM] RAM disk image start address
4397 random.trust_cpu={on,off}
4398 [KNL] Enable or disable trusting the use of the
4399 CPU's random number generator (if available) to
4400 fully seed the kernel's CRNG. Default is controlled
4401 by CONFIG_RANDOM_TRUST_CPU.
4403 randomize_kstack_offset=
4404 [KNL] Enable or disable kernel stack offset
4405 randomization, which provides roughly 5 bits of
4406 entropy, frustrating memory corruption attacks
4407 that depend on stack address determinism or
4408 cross-syscall address exposures. This is only
4409 available on architectures that have defined
4410 CONFIG_HAVE_ARCH_RANDOMIZE_KSTACK_OFFSET.
4411 Format: <bool> (1/Y/y=enable, 0/N/n=disable)
4412 Default is CONFIG_RANDOMIZE_KSTACK_OFFSET_DEFAULT.
4414 ras=option[,option,...] [KNL] RAS-specific options
4417 Disable the Correctable Errors Collector,
4418 see CONFIG_RAS_CEC help text.
4420 rcu_nocbs[=cpu-list]
4421 [KNL] The optional argument is a cpu list,
4424 In kernels built with CONFIG_RCU_NOCB_CPU=y,
4425 enable the no-callback CPU mode, which prevents
4426 such CPUs' callbacks from being invoked in
4427 softirq context. Invocation of such CPUs' RCU
4428 callbacks will instead be offloaded to "rcuox/N"
4429 kthreads created for that purpose, where "x" is
4430 "p" for RCU-preempt, "s" for RCU-sched, and "g"
4431 for the kthreads that mediate grace periods; and
4432 "N" is the CPU number. This reduces OS jitter on
4433 the offloaded CPUs, which can be useful for HPC
4434 and real-time workloads. It can also improve
4435 energy efficiency for asymmetric multiprocessors.
4437 If a cpulist is passed as an argument, the specified
4438 list of CPUs is set to no-callback mode from boot.
4440 Otherwise, if the '=' sign and the cpulist
4441 arguments are omitted, no CPU will be set to
4442 no-callback mode from boot but the mode may be
4443 toggled at runtime via cpusets.
4446 Rather than requiring that offloaded CPUs
4447 (specified by rcu_nocbs= above) explicitly
4448 awaken the corresponding "rcuoN" kthreads,
4449 make these kthreads poll for callbacks.
4450 This improves the real-time response for the
4451 offloaded CPUs by relieving them of the need to
4452 wake up the corresponding kthread, but degrades
4453 energy efficiency by requiring that the kthreads
4454 periodically wake up to do the polling.
4456 rcutree.blimit= [KNL]
4457 Set maximum number of finished RCU callbacks to
4458 process in one batch.
4460 rcutree.dump_tree= [KNL]
4461 Dump the structure of the rcu_node combining tree
4462 out at early boot. This is used for diagnostic
4463 purposes, to verify correct tree setup.
4465 rcutree.gp_cleanup_delay= [KNL]
4466 Set the number of jiffies to delay each step of
4467 RCU grace-period cleanup.
4469 rcutree.gp_init_delay= [KNL]
4470 Set the number of jiffies to delay each step of
4471 RCU grace-period initialization.
4473 rcutree.gp_preinit_delay= [KNL]
4474 Set the number of jiffies to delay each step of
4475 RCU grace-period pre-initialization, that is,
4476 the propagation of recent CPU-hotplug changes up
4477 the rcu_node combining tree.
4479 rcutree.use_softirq= [KNL]
4480 If set to zero, move all RCU_SOFTIRQ processing to
4481 per-CPU rcuc kthreads. Defaults to a non-zero
4482 value, meaning that RCU_SOFTIRQ is used by default.
4483 Specify rcutree.use_softirq=0 to use rcuc kthreads.
4485 But note that CONFIG_PREEMPT_RT=y kernels disable
4486 this kernel boot parameter, forcibly setting it
4489 rcutree.rcu_fanout_exact= [KNL]
4490 Disable autobalancing of the rcu_node combining
4491 tree. This is used by rcutorture, and might
4492 possibly be useful for architectures having high
4493 cache-to-cache transfer latencies.
4495 rcutree.rcu_fanout_leaf= [KNL]
4496 Change the number of CPUs assigned to each
4497 leaf rcu_node structure. Useful for very
4498 large systems, which will choose the value 64,
4499 and for NUMA systems with large remote-access
4500 latencies, which will choose a value aligned
4501 with the appropriate hardware boundaries.
4503 rcutree.rcu_min_cached_objs= [KNL]
4504 Minimum number of objects which are cached and
4505 maintained per one CPU. Object size is equal
4506 to PAGE_SIZE. The cache allows to reduce the
4507 pressure to page allocator, also it makes the
4508 whole algorithm to behave better in low memory
4511 rcutree.rcu_delay_page_cache_fill_msec= [KNL]
4512 Set the page-cache refill delay (in milliseconds)
4513 in response to low-memory conditions. The range
4514 of permitted values is in the range 0:100000.
4516 rcutree.jiffies_till_first_fqs= [KNL]
4517 Set delay from grace-period initialization to
4518 first attempt to force quiescent states.
4519 Units are jiffies, minimum value is zero,
4520 and maximum value is HZ.
4522 rcutree.jiffies_till_next_fqs= [KNL]
4523 Set delay between subsequent attempts to force
4524 quiescent states. Units are jiffies, minimum
4525 value is one, and maximum value is HZ.
4527 rcutree.jiffies_till_sched_qs= [KNL]
4528 Set required age in jiffies for a
4529 given grace period before RCU starts
4530 soliciting quiescent-state help from
4531 rcu_note_context_switch() and cond_resched().
4532 If not specified, the kernel will calculate
4533 a value based on the most recent settings
4534 of rcutree.jiffies_till_first_fqs
4535 and rcutree.jiffies_till_next_fqs.
4536 This calculated value may be viewed in
4537 rcutree.jiffies_to_sched_qs. Any attempt to set
4538 rcutree.jiffies_to_sched_qs will be cheerfully
4541 rcutree.kthread_prio= [KNL,BOOT]
4542 Set the SCHED_FIFO priority of the RCU per-CPU
4543 kthreads (rcuc/N). This value is also used for
4544 the priority of the RCU boost threads (rcub/N)
4545 and for the RCU grace-period kthreads (rcu_bh,
4546 rcu_preempt, and rcu_sched). If RCU_BOOST is
4547 set, valid values are 1-99 and the default is 1
4548 (the least-favored priority). Otherwise, when
4549 RCU_BOOST is not set, valid values are 0-99 and
4550 the default is zero (non-realtime operation).
4551 When RCU_NOCB_CPU is set, also adjust the
4552 priority of NOCB callback kthreads.
4554 rcutree.rcu_nocb_gp_stride= [KNL]
4555 Set the number of NOCB callback kthreads in
4556 each group, which defaults to the square root
4557 of the number of CPUs. Larger numbers reduce
4558 the wakeup overhead on the global grace-period
4559 kthread, but increases that same overhead on
4560 each group's NOCB grace-period kthread.
4562 rcutree.qhimark= [KNL]
4563 Set threshold of queued RCU callbacks beyond which
4564 batch limiting is disabled.
4566 rcutree.qlowmark= [KNL]
4567 Set threshold of queued RCU callbacks below which
4568 batch limiting is re-enabled.
4570 rcutree.qovld= [KNL]
4571 Set threshold of queued RCU callbacks beyond which
4572 RCU's force-quiescent-state scan will aggressively
4573 enlist help from cond_resched() and sched IPIs to
4574 help CPUs more quickly reach quiescent states.
4575 Set to less than zero to make this be set based
4576 on rcutree.qhimark at boot time and to zero to
4577 disable more aggressive help enlistment.
4579 rcutree.rcu_kick_kthreads= [KNL]
4580 Cause the grace-period kthread to get an extra
4581 wake_up() if it sleeps three times longer than
4582 it should at force-quiescent-state time.
4583 This wake_up() will be accompanied by a
4584 WARN_ONCE() splat and an ftrace_dump().
4586 rcutree.rcu_unlock_delay= [KNL]
4587 In CONFIG_RCU_STRICT_GRACE_PERIOD=y kernels,
4588 this specifies an rcu_read_unlock()-time delay
4589 in microseconds. This defaults to zero.
4590 Larger delays increase the probability of
4591 catching RCU pointer leaks, that is, buggy use
4592 of RCU-protected pointers after the relevant
4593 rcu_read_unlock() has completed.
4595 rcutree.sysrq_rcu= [KNL]
4596 Commandeer a sysrq key to dump out Tree RCU's
4597 rcu_node tree with an eye towards determining
4598 why a new grace period has not yet started.
4600 rcuscale.gp_async= [KNL]
4601 Measure performance of asynchronous
4602 grace-period primitives such as call_rcu().
4604 rcuscale.gp_async_max= [KNL]
4605 Specify the maximum number of outstanding
4606 callbacks per writer thread. When a writer
4607 thread exceeds this limit, it invokes the
4608 corresponding flavor of rcu_barrier() to allow
4609 previously posted callbacks to drain.
4611 rcuscale.gp_exp= [KNL]
4612 Measure performance of expedited synchronous
4613 grace-period primitives.
4615 rcuscale.holdoff= [KNL]
4616 Set test-start holdoff period. The purpose of
4617 this parameter is to delay the start of the
4618 test until boot completes in order to avoid
4621 rcuscale.kfree_rcu_test= [KNL]
4622 Set to measure performance of kfree_rcu() flooding.
4624 rcuscale.kfree_rcu_test_double= [KNL]
4625 Test the double-argument variant of kfree_rcu().
4626 If this parameter has the same value as
4627 rcuscale.kfree_rcu_test_single, both the single-
4628 and double-argument variants are tested.
4630 rcuscale.kfree_rcu_test_single= [KNL]
4631 Test the single-argument variant of kfree_rcu().
4632 If this parameter has the same value as
4633 rcuscale.kfree_rcu_test_double, both the single-
4634 and double-argument variants are tested.
4636 rcuscale.kfree_nthreads= [KNL]
4637 The number of threads running loops of kfree_rcu().
4639 rcuscale.kfree_alloc_num= [KNL]
4640 Number of allocations and frees done in an iteration.
4642 rcuscale.kfree_loops= [KNL]
4643 Number of loops doing rcuscale.kfree_alloc_num number
4644 of allocations and frees.
4646 rcuscale.nreaders= [KNL]
4647 Set number of RCU readers. The value -1 selects
4648 N, where N is the number of CPUs. A value
4649 "n" less than -1 selects N-n+1, where N is again
4650 the number of CPUs. For example, -2 selects N
4651 (the number of CPUs), -3 selects N+1, and so on.
4652 A value of "n" less than or equal to -N selects
4655 rcuscale.nwriters= [KNL]
4656 Set number of RCU writers. The values operate
4657 the same as for rcuscale.nreaders.
4658 N, where N is the number of CPUs
4660 rcuscale.perf_type= [KNL]
4661 Specify the RCU implementation to test.
4663 rcuscale.shutdown= [KNL]
4664 Shut the system down after performance tests
4665 complete. This is useful for hands-off automated
4668 rcuscale.verbose= [KNL]
4669 Enable additional printk() statements.
4671 rcuscale.writer_holdoff= [KNL]
4672 Write-side holdoff between grace periods,
4673 in microseconds. The default of zero says
4676 rcutorture.fqs_duration= [KNL]
4677 Set duration of force_quiescent_state bursts
4680 rcutorture.fqs_holdoff= [KNL]
4681 Set holdoff time within force_quiescent_state bursts
4684 rcutorture.fqs_stutter= [KNL]
4685 Set wait time between force_quiescent_state bursts
4688 rcutorture.fwd_progress= [KNL]
4689 Specifies the number of kthreads to be used
4690 for RCU grace-period forward-progress testing
4691 for the types of RCU supporting this notion.
4692 Defaults to 1 kthread, values less than zero or
4693 greater than the number of CPUs cause the number
4696 rcutorture.fwd_progress_div= [KNL]
4697 Specify the fraction of a CPU-stall-warning
4698 period to do tight-loop forward-progress testing.
4700 rcutorture.fwd_progress_holdoff= [KNL]
4701 Number of seconds to wait between successive
4702 forward-progress tests.
4704 rcutorture.fwd_progress_need_resched= [KNL]
4705 Enclose cond_resched() calls within checks for
4706 need_resched() during tight-loop forward-progress
4709 rcutorture.gp_cond= [KNL]
4710 Use conditional/asynchronous update-side
4711 primitives, if available.
4713 rcutorture.gp_exp= [KNL]
4714 Use expedited update-side primitives, if available.
4716 rcutorture.gp_normal= [KNL]
4717 Use normal (non-expedited) asynchronous
4718 update-side primitives, if available.
4720 rcutorture.gp_sync= [KNL]
4721 Use normal (non-expedited) synchronous
4722 update-side primitives, if available. If all
4723 of rcutorture.gp_cond=, rcutorture.gp_exp=,
4724 rcutorture.gp_normal=, and rcutorture.gp_sync=
4725 are zero, rcutorture acts as if is interpreted
4726 they are all non-zero.
4728 rcutorture.irqreader= [KNL]
4729 Run RCU readers from irq handlers, or, more
4730 accurately, from a timer handler. Not all RCU
4731 flavors take kindly to this sort of thing.
4733 rcutorture.leakpointer= [KNL]
4734 Leak an RCU-protected pointer out of the reader.
4735 This can of course result in splats, and is
4736 intended to test the ability of things like
4737 CONFIG_RCU_STRICT_GRACE_PERIOD=y to detect
4740 rcutorture.n_barrier_cbs= [KNL]
4741 Set callbacks/threads for rcu_barrier() testing.
4743 rcutorture.nfakewriters= [KNL]
4744 Set number of concurrent RCU writers. These just
4745 stress RCU, they don't participate in the actual
4746 test, hence the "fake".
4748 rcutorture.nocbs_nthreads= [KNL]
4749 Set number of RCU callback-offload togglers.
4750 Zero (the default) disables toggling.
4752 rcutorture.nocbs_toggle= [KNL]
4753 Set the delay in milliseconds between successive
4754 callback-offload toggling attempts.
4756 rcutorture.nreaders= [KNL]
4757 Set number of RCU readers. The value -1 selects
4758 N-1, where N is the number of CPUs. A value
4759 "n" less than -1 selects N-n-2, where N is again
4760 the number of CPUs. For example, -2 selects N
4761 (the number of CPUs), -3 selects N+1, and so on.
4763 rcutorture.object_debug= [KNL]
4764 Enable debug-object double-call_rcu() testing.
4766 rcutorture.onoff_holdoff= [KNL]
4767 Set time (s) after boot for CPU-hotplug testing.
4769 rcutorture.onoff_interval= [KNL]
4770 Set time (jiffies) between CPU-hotplug operations,
4771 or zero to disable CPU-hotplug testing.
4773 rcutorture.read_exit= [KNL]
4774 Set the number of read-then-exit kthreads used
4775 to test the interaction of RCU updaters and
4776 task-exit processing.
4778 rcutorture.read_exit_burst= [KNL]
4779 The number of times in a given read-then-exit
4780 episode that a set of read-then-exit kthreads
4783 rcutorture.read_exit_delay= [KNL]
4784 The delay, in seconds, between successive
4785 read-then-exit testing episodes.
4787 rcutorture.shuffle_interval= [KNL]
4788 Set task-shuffle interval (s). Shuffling tasks
4789 allows some CPUs to go into dyntick-idle mode
4790 during the rcutorture test.
4792 rcutorture.shutdown_secs= [KNL]
4793 Set time (s) after boot system shutdown. This
4794 is useful for hands-off automated testing.
4796 rcutorture.stall_cpu= [KNL]
4797 Duration of CPU stall (s) to test RCU CPU stall
4798 warnings, zero to disable.
4800 rcutorture.stall_cpu_block= [KNL]
4801 Sleep while stalling if set. This will result
4802 in warnings from preemptible RCU in addition
4803 to any other stall-related activity.
4805 rcutorture.stall_cpu_holdoff= [KNL]
4806 Time to wait (s) after boot before inducing stall.
4808 rcutorture.stall_cpu_irqsoff= [KNL]
4809 Disable interrupts while stalling if set.
4811 rcutorture.stall_gp_kthread= [KNL]
4812 Duration (s) of forced sleep within RCU
4813 grace-period kthread to test RCU CPU stall
4814 warnings, zero to disable. If both stall_cpu
4815 and stall_gp_kthread are specified, the
4816 kthread is starved first, then the CPU.
4818 rcutorture.stat_interval= [KNL]
4819 Time (s) between statistics printk()s.
4821 rcutorture.stutter= [KNL]
4822 Time (s) to stutter testing, for example, specifying
4823 five seconds causes the test to run for five seconds,
4824 wait for five seconds, and so on. This tests RCU's
4825 ability to transition abruptly to and from idle.
4827 rcutorture.test_boost= [KNL]
4828 Test RCU priority boosting? 0=no, 1=maybe, 2=yes.
4829 "Maybe" means test if the RCU implementation
4830 under test support RCU priority boosting.
4832 rcutorture.test_boost_duration= [KNL]
4833 Duration (s) of each individual boost test.
4835 rcutorture.test_boost_interval= [KNL]
4836 Interval (s) between each boost test.
4838 rcutorture.test_no_idle_hz= [KNL]
4839 Test RCU's dyntick-idle handling. See also the
4840 rcutorture.shuffle_interval parameter.
4842 rcutorture.torture_type= [KNL]
4843 Specify the RCU implementation to test.
4845 rcutorture.verbose= [KNL]
4846 Enable additional printk() statements.
4848 rcupdate.rcu_cpu_stall_ftrace_dump= [KNL]
4849 Dump ftrace buffer after reporting RCU CPU
4852 rcupdate.rcu_cpu_stall_suppress= [KNL]
4853 Suppress RCU CPU stall warning messages.
4855 rcupdate.rcu_cpu_stall_suppress_at_boot= [KNL]
4856 Suppress RCU CPU stall warning messages and
4857 rcutorture writer stall warnings that occur
4858 during early boot, that is, during the time
4859 before the init task is spawned.
4861 rcupdate.rcu_cpu_stall_timeout= [KNL]
4862 Set timeout for RCU CPU stall warning messages.
4864 rcupdate.rcu_expedited= [KNL]
4865 Use expedited grace-period primitives, for
4866 example, synchronize_rcu_expedited() instead
4867 of synchronize_rcu(). This reduces latency,
4868 but can increase CPU utilization, degrade
4869 real-time latency, and degrade energy efficiency.
4870 No effect on CONFIG_TINY_RCU kernels.
4872 rcupdate.rcu_normal= [KNL]
4873 Use only normal grace-period primitives,
4874 for example, synchronize_rcu() instead of
4875 synchronize_rcu_expedited(). This improves
4876 real-time latency, CPU utilization, and
4877 energy efficiency, but can expose users to
4878 increased grace-period latency. This parameter
4879 overrides rcupdate.rcu_expedited. No effect on
4880 CONFIG_TINY_RCU kernels.
4882 rcupdate.rcu_normal_after_boot= [KNL]
4883 Once boot has completed (that is, after
4884 rcu_end_inkernel_boot() has been invoked), use
4885 only normal grace-period primitives. No effect
4886 on CONFIG_TINY_RCU kernels.
4888 But note that CONFIG_PREEMPT_RT=y kernels enables
4889 this kernel boot parameter, forcibly setting
4890 it to the value one, that is, converting any
4891 post-boot attempt at an expedited RCU grace
4892 period to instead use normal non-expedited
4893 grace-period processing.
4895 rcupdate.rcu_task_collapse_lim= [KNL]
4896 Set the maximum number of callbacks present
4897 at the beginning of a grace period that allows
4898 the RCU Tasks flavors to collapse back to using
4899 a single callback queue. This switching only
4900 occurs when rcupdate.rcu_task_enqueue_lim is
4901 set to the default value of -1.
4903 rcupdate.rcu_task_contend_lim= [KNL]
4904 Set the minimum number of callback-queuing-time
4905 lock-contention events per jiffy required to
4906 cause the RCU Tasks flavors to switch to per-CPU
4907 callback queuing. This switching only occurs
4908 when rcupdate.rcu_task_enqueue_lim is set to
4909 the default value of -1.
4911 rcupdate.rcu_task_enqueue_lim= [KNL]
4912 Set the number of callback queues to use for the
4913 RCU Tasks family of RCU flavors. The default
4914 of -1 allows this to be automatically (and
4915 dynamically) adjusted. This parameter is intended
4918 rcupdate.rcu_task_ipi_delay= [KNL]
4919 Set time in jiffies during which RCU tasks will
4920 avoid sending IPIs, starting with the beginning
4921 of a given grace period. Setting a large
4922 number avoids disturbing real-time workloads,
4923 but lengthens grace periods.
4925 rcupdate.rcu_task_stall_timeout= [KNL]
4926 Set timeout in jiffies for RCU task stall warning
4927 messages. Disable with a value less than or equal
4930 rcupdate.rcu_self_test= [KNL]
4931 Run the RCU early boot self tests
4935 Run specified binary instead of /init from the ramdisk,
4936 used for early userspace startup. See initrd.
4939 force - Override the decision by the kernel to hide the
4940 advertisement of RDRAND support (this affects
4941 certain AMD processors because of buggy BIOS
4942 support, specifically around the suspend/resume
4946 Turn on/off individual RDT features. List is:
4947 cmt, mbmtotal, mbmlocal, l3cat, l3cdp, l2cat, l2cdp,
4949 E.g. to turn on cmt and turn off mba use:
4953 Format (x86 or x86_64):
4954 [w[arm] | c[old] | h[ard] | s[oft] | g[pio]] | d[efault] \
4956 [[,]b[ios] | a[cpi] | k[bd] | t[riple] | e[fi] | p[ci]] \
4958 Where reboot_mode is one of warm (soft) or cold (hard) or gpio
4959 (prefix with 'panic_' to set mode for panic
4961 reboot_type is one of bios, acpi, kbd, triple, efi, or pci,
4962 reboot_force is either force or not specified,
4963 reboot_cpu is s[mp]#### with #### being the processor
4964 to be used for rebooting.
4966 refscale.holdoff= [KNL]
4967 Set test-start holdoff period. The purpose of
4968 this parameter is to delay the start of the
4969 test until boot completes in order to avoid
4972 refscale.loops= [KNL]
4973 Set the number of loops over the synchronization
4974 primitive under test. Increasing this number
4975 reduces noise due to loop start/end overhead,
4976 but the default has already reduced the per-pass
4977 noise to a handful of picoseconds on ca. 2020
4980 refscale.nreaders= [KNL]
4981 Set number of readers. The default value of -1
4982 selects N, where N is roughly 75% of the number
4983 of CPUs. A value of zero is an interesting choice.
4985 refscale.nruns= [KNL]
4986 Set number of runs, each of which is dumped onto
4989 refscale.readdelay= [KNL]
4990 Set the read-side critical-section duration,
4991 measured in microseconds.
4993 refscale.scale_type= [KNL]
4994 Specify the read-protection implementation to test.
4996 refscale.shutdown= [KNL]
4997 Shut down the system at the end of the performance
4998 test. This defaults to 1 (shut it down) when
4999 refscale is built into the kernel and to 0 (leave
5000 it running) when refscale is built as a module.
5002 refscale.verbose= [KNL]
5003 Enable additional printk() statements.
5005 refscale.verbose_batched= [KNL]
5006 Batch the additional printk() statements. If zero
5007 (the default) or negative, print everything. Otherwise,
5008 print every Nth verbose statement, where N is the value
5012 [KNL, SMP] Set scheduler's default relax_domain_level.
5013 See Documentation/admin-guide/cgroup-v1/cpusets.rst.
5015 reserve= [KNL,BUGS] Force kernel to ignore I/O ports or memory
5016 Format: <base1>,<size1>[,<base2>,<size2>,...]
5017 Reserve I/O ports or memory so the kernel won't use
5018 them. If <base> is less than 0x10000, the region
5019 is assumed to be I/O ports; otherwise it is memory.
5021 reservetop= [X86-32]
5023 Reserves a hole at the top of the kernel virtual
5026 reset_devices [KNL] Force drivers to reset the underlying device
5027 during initialization.
5030 Specify the partition device for software suspend
5032 {/dev/<dev> | PARTUUID=<uuid> | <int>:<int> | <hex>}
5034 resume_offset= [SWSUSP]
5035 Specify the offset from the beginning of the partition
5036 given by "resume=" at which the swap header is located,
5037 in <PAGE_SIZE> units (needed only for swap files).
5038 See Documentation/power/swsusp-and-swap-files.rst
5040 resumedelay= [HIBERNATION] Delay (in seconds) to pause before attempting to
5041 read the resume files
5043 resumewait [HIBERNATION] Wait (indefinitely) for resume device to show up.
5044 Useful for devices that are detected asynchronously
5045 (e.g. USB and MMC devices).
5047 hibernate= [HIBERNATION]
5048 noresume Don't check if there's a hibernation image
5049 present during boot.
5050 nocompress Don't compress/decompress hibernation images.
5051 no Disable hibernation and resume.
5052 protect_image Turn on image protection during restoration
5053 (that will set all pages holding image data
5054 during restoration read-only).
5056 retain_initrd [RAM] Keep initrd memory after extraction
5058 rfkill.default_state=
5059 0 "airplane mode". All wifi, bluetooth, wimax, gps, fm,
5060 etc. communication is blocked by default.
5063 rfkill.master_switch_mode=
5064 0 The "airplane mode" button does nothing.
5065 1 The "airplane mode" button toggles between everything
5066 blocked and the previous configuration.
5067 2 The "airplane mode" button toggles between everything
5068 blocked and everything unblocked.
5070 rhash_entries= [KNL,NET]
5071 Set number of hash buckets for route cache
5074 [KNL] Disable ring 3 MONITOR/MWAIT feature on supported
5077 ro [KNL] Mount root device read-only on boot
5080 on Mark read-only kernel memory as read-only (default).
5081 off Leave read-only kernel memory writable for debugging.
5084 Enable the uart passthrough on the designated usb port
5085 on Rockchip SoCs. When active, the signals of the
5086 debug-uart get routed to the D+ and D- pins of the usb
5087 port and the regular usb controller gets disabled.
5089 root= [KNL] Root filesystem
5090 See name_to_dev_t comment in init/do_mounts.c.
5092 rootdelay= [KNL] Delay (in seconds) to pause before attempting to
5093 mount the root filesystem
5095 rootflags= [KNL] Set root filesystem mount option string
5097 rootfstype= [KNL] Set root filesystem type
5099 rootwait [KNL] Wait (indefinitely) for root device to show up.
5100 Useful for devices that are detected asynchronously
5101 (e.g. USB and MMC devices).
5103 rproc_mem=nn[KMG][@address]
5104 [KNL,ARM,CMA] Remoteproc physical memory block.
5105 Memory area to be used by remote processor image,
5108 rw [KNL] Mount root device read-write on boot
5110 S [KNL] Run init in single mode
5112 s390_iommu= [HW,S390]
5113 Set s390 IOTLB flushing mode
5115 With strict flushing every unmap operation will result in
5116 an IOTLB flush. Default is lazy flushing before reuse,
5119 s390_iommu_aperture= [KNL,S390]
5120 Specifies the size of the per device DMA address space
5121 accessible through the DMA and IOMMU APIs as a decimal
5122 factor of the size of main memory.
5123 The default is 1 meaning that one can concurrently use
5124 as many DMA addresses as physical memory is installed,
5125 if supported by hardware, and thus map all of memory
5126 once. With a value of 2 one can map all of memory twice
5127 and so on. As a special case a factor of 0 imposes no
5128 restrictions other than those given by hardware at the
5129 cost of significant additional memory use for tables.
5132 See drivers/net/irda/sa1100_ir.c.
5134 sched_verbose [KNL] Enables verbose scheduler debug messages.
5136 schedstats= [KNL,X86] Enable or disable scheduled statistics.
5137 Allowed values are enable and disable. This feature
5138 incurs a small amount of overhead in the scheduler
5139 but is useful for debugging and performance tuning.
5141 sched_thermal_decay_shift=
5142 [KNL, SMP] Set a decay shift for scheduler thermal
5143 pressure signal. Thermal pressure signal follows the
5144 default decay period of other scheduler pelt
5145 signals(usually 32 ms but configurable). Setting
5146 sched_thermal_decay_shift will left shift the decay
5147 period for the thermal pressure signal by the shift
5149 i.e. with the default pelt decay period of 32 ms
5150 sched_thermal_decay_shift thermal pressure decay pr
5154 Format: integer between 0 and 10
5157 scftorture.holdoff= [KNL]
5158 Number of seconds to hold off before starting
5159 test. Defaults to zero for module insertion and
5160 to 10 seconds for built-in smp_call_function()
5163 scftorture.longwait= [KNL]
5164 Request ridiculously long waits randomly selected
5165 up to the chosen limit in seconds. Zero (the
5166 default) disables this feature. Please note
5167 that requesting even small non-zero numbers of
5168 seconds can result in RCU CPU stall warnings,
5169 softlockup complaints, and so on.
5171 scftorture.nthreads= [KNL]
5172 Number of kthreads to spawn to invoke the
5173 smp_call_function() family of functions.
5174 The default of -1 specifies a number of kthreads
5175 equal to the number of CPUs.
5177 scftorture.onoff_holdoff= [KNL]
5178 Number seconds to wait after the start of the
5179 test before initiating CPU-hotplug operations.
5181 scftorture.onoff_interval= [KNL]
5182 Number seconds to wait between successive
5183 CPU-hotplug operations. Specifying zero (which
5184 is the default) disables CPU-hotplug operations.
5186 scftorture.shutdown_secs= [KNL]
5187 The number of seconds following the start of the
5188 test after which to shut down the system. The
5189 default of zero avoids shutting down the system.
5190 Non-zero values are useful for automated tests.
5192 scftorture.stat_interval= [KNL]
5193 The number of seconds between outputting the
5194 current test statistics to the console. A value
5195 of zero disables statistics output.
5197 scftorture.stutter_cpus= [KNL]
5198 The number of jiffies to wait between each change
5199 to the set of CPUs under test.
5201 scftorture.use_cpus_read_lock= [KNL]
5202 Use use_cpus_read_lock() instead of the default
5203 preempt_disable() to disable CPU hotplug
5204 while invoking one of the smp_call_function*()
5207 scftorture.verbose= [KNL]
5208 Enable additional printk() statements.
5210 scftorture.weight_single= [KNL]
5211 The probability weighting to use for the
5212 smp_call_function_single() function with a zero
5213 "wait" parameter. A value of -1 selects the
5214 default if all other weights are -1. However,
5215 if at least one weight has some other value, a
5216 value of -1 will instead select a weight of zero.
5218 scftorture.weight_single_wait= [KNL]
5219 The probability weighting to use for the
5220 smp_call_function_single() function with a
5221 non-zero "wait" parameter. See weight_single.
5223 scftorture.weight_many= [KNL]
5224 The probability weighting to use for the
5225 smp_call_function_many() function with a zero
5226 "wait" parameter. See weight_single.
5227 Note well that setting a high probability for
5228 this weighting can place serious IPI load
5231 scftorture.weight_many_wait= [KNL]
5232 The probability weighting to use for the
5233 smp_call_function_many() function with a
5234 non-zero "wait" parameter. See weight_single
5237 scftorture.weight_all= [KNL]
5238 The probability weighting to use for the
5239 smp_call_function_all() function with a zero
5240 "wait" parameter. See weight_single and
5243 scftorture.weight_all_wait= [KNL]
5244 The probability weighting to use for the
5245 smp_call_function_all() function with a
5246 non-zero "wait" parameter. See weight_single
5249 skew_tick= [KNL] Offset the periodic timer tick per cpu to mitigate
5250 xtime_lock contention on larger systems, and/or RCU lock
5251 contention on all systems with CONFIG_MAXSMP set.
5252 Format: { "0" | "1" }
5253 0 -- disable. (may be 1 via CONFIG_CMDLINE="skew_tick=1"
5255 Note: increases power consumption, thus should only be
5256 enabled if running jitter sensitive (HPC/RT) workloads.
5258 security= [SECURITY] Choose a legacy "major" security module to
5259 enable at boot. This has been deprecated by the
5262 selinux= [SELINUX] Disable or enable SELinux at boot time.
5263 Format: { "0" | "1" }
5264 See security/selinux/Kconfig help text.
5269 apparmor= [APPARMOR] Disable or enable AppArmor at boot time
5270 Format: { "0" | "1" }
5271 See security/apparmor/Kconfig help text
5274 Default value is set via kernel config option.
5276 serialnumber [BUGS=X86-32]
5279 Maximal number of shapers.
5287 Enable merging of slabs with similar size when the
5288 kernel is built without CONFIG_SLAB_MERGE_DEFAULT.
5291 Disable merging of slabs with similar size. May be
5292 necessary if there is some reason to distinguish
5293 allocs to different slabs, especially in hardened
5294 environments where the risk of heap overflows and
5295 layout control by attackers can usually be
5296 frustrated by disabling merging. This will reduce
5297 most of the exposure of a heap attack to a single
5298 cache (risks via metadata attacks are mostly
5299 unchanged). Debug options disable merging on their
5301 For more information see Documentation/vm/slub.rst.
5303 slab_max_order= [MM, SLAB]
5304 Determines the maximum allowed order for slabs.
5305 A high setting may cause OOMs due to memory
5306 fragmentation. Defaults to 1 for systems with
5307 more than 32MB of RAM, 0 otherwise.
5309 slub_debug[=options[,slabs][;[options[,slabs]]...] [MM, SLUB]
5310 Enabling slub_debug allows one to determine the
5311 culprit if slab objects become corrupted. Enabling
5312 slub_debug can create guard zones around objects and
5313 may poison objects when not in use. Also tracks the
5314 last alloc / free. For more information see
5315 Documentation/vm/slub.rst.
5317 slub_max_order= [MM, SLUB]
5318 Determines the maximum allowed order for slabs.
5319 A high setting may cause OOMs due to memory
5320 fragmentation. For more information see
5321 Documentation/vm/slub.rst.
5323 slub_min_objects= [MM, SLUB]
5324 The minimum number of objects per slab. SLUB will
5325 increase the slab order up to slub_max_order to
5326 generate a sufficiently large slab able to contain
5327 the number of objects indicated. The higher the number
5328 of objects the smaller the overhead of tracking slabs
5329 and the less frequently locks need to be acquired.
5330 For more information see Documentation/vm/slub.rst.
5332 slub_min_order= [MM, SLUB]
5333 Determines the minimum page order for slabs. Must be
5334 lower than slub_max_order.
5335 For more information see Documentation/vm/slub.rst.
5337 slub_merge [MM, SLUB]
5338 Same with slab_merge.
5340 slub_nomerge [MM, SLUB]
5341 Same with slab_nomerge. This is supported for legacy.
5342 See slab_nomerge for more information.
5345 Format: <io1>[,<io2>[,...,<io8>]]
5347 smsc-ircc2.nopnp [HW] Don't use PNP to discover SMC devices
5348 smsc-ircc2.ircc_cfg= [HW] Device configuration I/O port
5349 smsc-ircc2.ircc_sir= [HW] SIR base I/O port
5350 smsc-ircc2.ircc_fir= [HW] FIR base I/O port
5351 smsc-ircc2.ircc_irq= [HW] IRQ line
5352 smsc-ircc2.ircc_dma= [HW] DMA channel
5353 smsc-ircc2.ircc_transceiver= [HW] Transceiver type:
5354 0: Toshiba Satellite 1800 (GP data pin select)
5355 1: Fast pin select (default)
5358 smt [KNL,S390] Set the maximum number of threads (logical
5359 CPUs) to use per physical CPU on systems capable of
5360 symmetric multithreading (SMT). Will be capped to the
5361 actual hardware limit.
5363 Default: -1 (no limit)
5366 [KNL] Should the soft-lockup detector generate panics.
5369 A value of 1 instructs the soft-lockup detector
5370 to panic the machine when a soft-lockup occurs. It is
5371 also controlled by the kernel.softlockup_panic sysctl
5372 and CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC, which is the
5373 respective build-time switch to that functionality.
5375 softlockup_all_cpu_backtrace=
5376 [KNL] Should the soft-lockup detector generate
5377 backtraces on all cpus.
5380 sonypi.*= [HW] Sony Programmable I/O Control Device driver
5381 See Documentation/admin-guide/laptops/sonypi.rst
5383 spectre_v2= [X86] Control mitigation of Spectre variant 2
5384 (indirect branch speculation) vulnerability.
5385 The default operation protects the kernel from
5388 on - unconditionally enable, implies
5390 off - unconditionally disable, implies
5392 auto - kernel detects whether your CPU model is
5395 Selecting 'on' will, and 'auto' may, choose a
5396 mitigation method at run time according to the
5397 CPU, the available microcode, the setting of the
5398 CONFIG_RETPOLINE configuration option, and the
5399 compiler with which the kernel was built.
5401 Selecting 'on' will also enable the mitigation
5402 against user space to user space task attacks.
5404 Selecting 'off' will disable both the kernel and
5405 the user space protections.
5407 Specific mitigations can also be selected manually:
5409 retpoline - replace indirect branches
5410 retpoline,generic - Retpolines
5411 retpoline,lfence - LFENCE; indirect branch
5412 retpoline,amd - alias for retpoline,lfence
5413 eibrs - enhanced IBRS
5414 eibrs,retpoline - enhanced IBRS + Retpolines
5415 eibrs,lfence - enhanced IBRS + LFENCE
5417 Not specifying this option is equivalent to
5421 [X86] Control mitigation of Spectre variant 2
5422 (indirect branch speculation) vulnerability between
5425 on - Unconditionally enable mitigations. Is
5426 enforced by spectre_v2=on
5428 off - Unconditionally disable mitigations. Is
5429 enforced by spectre_v2=off
5431 prctl - Indirect branch speculation is enabled,
5432 but mitigation can be enabled via prctl
5433 per thread. The mitigation control state
5434 is inherited on fork.
5437 - Like "prctl" above, but only STIBP is
5438 controlled per thread. IBPB is issued
5439 always when switching between different user
5443 - Same as "prctl" above, but all seccomp
5444 threads will enable the mitigation unless
5445 they explicitly opt out.
5448 - Like "seccomp" above, but only STIBP is
5449 controlled per thread. IBPB is issued
5450 always when switching between different
5451 user space processes.
5453 auto - Kernel selects the mitigation depending on
5454 the available CPU features and vulnerability.
5456 Default mitigation: "prctl"
5458 Not specifying this option is equivalent to
5459 spectre_v2_user=auto.
5461 spec_store_bypass_disable=
5462 [HW] Control Speculative Store Bypass (SSB) Disable mitigation
5463 (Speculative Store Bypass vulnerability)
5465 Certain CPUs are vulnerable to an exploit against a
5466 a common industry wide performance optimization known
5467 as "Speculative Store Bypass" in which recent stores
5468 to the same memory location may not be observed by
5469 later loads during speculative execution. The idea
5470 is that such stores are unlikely and that they can
5471 be detected prior to instruction retirement at the
5472 end of a particular speculation execution window.
5474 In vulnerable processors, the speculatively forwarded
5475 store can be used in a cache side channel attack, for
5476 example to read memory to which the attacker does not
5477 directly have access (e.g. inside sandboxed code).
5479 This parameter controls whether the Speculative Store
5480 Bypass optimization is used.
5482 On x86 the options are:
5484 on - Unconditionally disable Speculative Store Bypass
5485 off - Unconditionally enable Speculative Store Bypass
5486 auto - Kernel detects whether the CPU model contains an
5487 implementation of Speculative Store Bypass and
5488 picks the most appropriate mitigation. If the
5489 CPU is not vulnerable, "off" is selected. If the
5490 CPU is vulnerable the default mitigation is
5491 architecture and Kconfig dependent. See below.
5492 prctl - Control Speculative Store Bypass per thread
5493 via prctl. Speculative Store Bypass is enabled
5494 for a process by default. The state of the control
5495 is inherited on fork.
5496 seccomp - Same as "prctl" above, but all seccomp threads
5497 will disable SSB unless they explicitly opt out.
5499 Default mitigations:
5502 On powerpc the options are:
5504 on,auto - On Power8 and Power9 insert a store-forwarding
5505 barrier on kernel entry and exit. On Power7
5506 perform a software flush on kernel entry and
5510 Not specifying this option is equivalent to
5511 spec_store_bypass_disable=auto.
5513 spia_io_base= [HW,MTD]
5519 [X86] Enable split lock detection or bus lock detection
5521 When enabled (and if hardware support is present), atomic
5522 instructions that access data across cache line
5523 boundaries will result in an alignment check exception
5524 for split lock detection or a debug exception for
5529 warn - the kernel will emit rate-limited warnings
5530 about applications triggering the #AC
5531 exception or the #DB exception. This mode is
5532 the default on CPUs that support split lock
5533 detection or bus lock detection. Default
5534 behavior is by #AC if both features are
5535 enabled in hardware.
5537 fatal - the kernel will send SIGBUS to applications
5538 that trigger the #AC exception or the #DB
5539 exception. Default behavior is by #AC if
5540 both features are enabled in hardware.
5543 Set system wide rate limit to N bus locks
5544 per second for bus lock detection.
5547 N/A for split lock detection.
5550 If an #AC exception is hit in the kernel or in
5551 firmware (i.e. not while executing in user mode)
5552 the kernel will oops in either "warn" or "fatal"
5555 #DB exception for bus lock is triggered only when
5559 Control the Special Register Buffer Data Sampling
5562 Certain CPUs are vulnerable to an MDS-like
5563 exploit which can leak bits from the random
5566 By default, this issue is mitigated by
5567 microcode. However, the microcode fix can cause
5568 the RDRAND and RDSEED instructions to become
5569 much slower. Among other effects, this will
5570 result in reduced throughput from /dev/urandom.
5572 The microcode mitigation can be disabled with
5573 the following option:
5575 off: Disable mitigation and remove
5576 performance impact to RDRAND and RDSEED
5578 srcutree.counter_wrap_check [KNL]
5579 Specifies how frequently to check for
5580 grace-period sequence counter wrap for the
5581 srcu_data structure's ->srcu_gp_seq_needed field.
5582 The greater the number of bits set in this kernel
5583 parameter, the less frequently counter wrap will
5584 be checked for. Note that the bottom two bits
5587 srcutree.exp_holdoff [KNL]
5588 Specifies how many nanoseconds must elapse
5589 since the end of the last SRCU grace period for
5590 a given srcu_struct until the next normal SRCU
5591 grace period will be considered for automatic
5592 expediting. Set to zero to disable automatic
5596 Speculative Store Bypass Disable control
5598 On CPUs that are vulnerable to the Speculative
5599 Store Bypass vulnerability and offer a
5600 firmware based mitigation, this parameter
5601 indicates how the mitigation should be used:
5603 force-on: Unconditionally enable mitigation for
5604 for both kernel and userspace
5605 force-off: Unconditionally disable mitigation for
5606 for both kernel and userspace
5607 kernel: Always enable mitigation in the
5608 kernel, and offer a prctl interface
5609 to allow userspace to register its
5610 interest in being mitigated too.
5612 stack_guard_gap= [MM]
5613 override the default stack gap protection. The value
5614 is in page units and it defines how many pages prior
5615 to (for stacks growing down) resp. after (for stacks
5616 growing up) the main stack are reserved for no other
5617 mapping. Default value is 256 pages.
5619 stack_depot_disable= [KNL]
5620 Setting this to true through kernel command line will
5621 disable the stack depot thereby saving the static memory
5622 consumed by the stack hash table. By default this is set
5626 Enabled the stack tracer on boot up.
5628 stacktrace_filter=[function-list]
5629 [FTRACE] Limit the functions that the stack tracer
5630 will trace at boot up. function-list is a comma-separated
5631 list of functions. This list can be changed at run
5632 time by the stack_trace_filter file in the debugfs
5633 tracing directory. Note, this enables stack tracing
5634 and the stacktrace above is not needed.
5638 Set the STI (builtin display/keyboard on the HP-PARISC
5639 machines) console (graphic card) which should be used
5640 as the initial boot-console.
5641 See also comment in drivers/video/console/sticore.c.
5644 See comment in drivers/video/console/sticore.c.
5647 Format: bpp:<bpp1>[:<bpp2>[:<bpp3>...]]
5652 Enable or disable strict sigaltstack size checks
5653 against the required signal frame size which
5654 depends on the supported FPU features. This can
5655 be used to filter out binaries which have
5656 not yet been made aware of AT_MINSIGSTKSZ.
5658 sunrpc.min_resvport=
5659 sunrpc.max_resvport=
5661 SunRPC servers often require that client requests
5662 originate from a privileged port (i.e. a port in the
5663 range 0 < portnr < 1024).
5664 An administrator who wishes to reserve some of these
5665 ports for other uses may adjust the range that the
5666 kernel's sunrpc client considers to be privileged
5667 using these two parameters to set the minimum and
5668 maximum port values.
5670 sunrpc.svc_rpc_per_connection_limit=
5672 Limit the number of requests that the server will
5673 process in parallel from a single connection.
5674 The default value is 0 (no limit).
5678 Control how the NFS server code allocates CPUs to
5679 service thread pools. Depending on how many NICs
5680 you have and where their interrupts are bound, this
5681 option will affect which CPUs will do NFS serving.
5682 Note: this parameter cannot be changed while the
5683 NFS server is running.
5685 auto the server chooses an appropriate mode
5686 automatically using heuristics
5687 global a single global pool contains all CPUs
5688 percpu one pool for each CPU
5689 pernode one pool for each NUMA node (equivalent
5690 to global on non-NUMA machines)
5692 sunrpc.tcp_slot_table_entries=
5693 sunrpc.udp_slot_table_entries=
5695 Sets the upper limit on the number of simultaneous
5696 RPC calls that can be sent from the client to a
5697 server. Increasing these values may allow you to
5698 improve throughput, but will also increase the
5699 amount of memory reserved for use by the client.
5701 suspend.pm_test_delay=
5703 Sets the number of seconds to remain in a suspend test
5704 mode before resuming the system (see
5705 /sys/power/pm_test). Only available when CONFIG_PM_DEBUG
5706 is set. Default value is 5.
5709 Format: { on | off | y | n | 1 | 0 }
5710 This parameter controls use of the Protected
5711 Execution Facility on pSeries.
5714 [KNL] Enable accounting of swap in memory resource
5715 controller if no parameter or 1 is given or disable
5716 it if 0 is given (See Documentation/admin-guide/cgroup-v1/memory.rst)
5718 swiotlb= [ARM,IA-64,PPC,MIPS,X86]
5719 Format: { <int> | force | noforce }
5720 <int> -- Number of I/O TLB slabs
5721 force -- force using of bounce buffers even if they
5722 wouldn't be automatically used by the kernel
5723 noforce -- Never use bounce buffers (for debugging)
5728 Set a sysctl parameter, right before loading the init
5729 process, as if the value was written to the respective
5730 /proc/sys/... file. Both '.' and '/' are recognized as
5731 separators. Unrecognized parameters and invalid values
5732 are reported in the kernel log. Sysctls registered
5733 later by a loaded module cannot be set this way.
5734 Example: sysctl.vm.swappiness=40
5736 sysfs.deprecated=0|1 [KNL]
5737 Enable/disable old style sysfs layout for old udev
5738 on older distributions. When this option is enabled
5739 very new udev will not work anymore. When this option
5740 is disabled (or CONFIG_SYSFS_DEPRECATED not compiled)
5741 in older udev will not work anymore.
5742 Default depends on CONFIG_SYSFS_DEPRECATED_V2 set in
5743 the kernel configuration.
5745 sysrq_always_enabled
5747 Ignore sysrq setting - this boot parameter will
5748 neutralize any effect of /proc/sys/kernel/sysrq.
5749 Useful for debugging.
5751 tcpmhash_entries= [KNL,NET]
5752 Set the number of tcp_metrics_hash slots.
5753 Default value is 8192 or 16384 depending on total
5754 ram pages. This is used to specify the TCP metrics
5755 cache size. See Documentation/networking/ip-sysctl.rst
5756 "tcp_no_metrics_save" section for more details.
5760 test_suspend= [SUSPEND][,N]
5761 Specify "mem" (for Suspend-to-RAM) or "standby" (for
5762 standby suspend) or "freeze" (for suspend type freeze)
5763 as the system sleep state during system startup with
5764 the optional capability to repeat N number of times.
5765 The system is woken from this state using a
5766 wakeup-capable RTC alarm.
5768 thash_entries= [KNL,NET]
5769 Set number of hash buckets for TCP connection
5771 thermal.act= [HW,ACPI]
5772 -1: disable all active trip points in all thermal zones
5773 <degrees C>: override all lowest active trip points
5775 thermal.crt= [HW,ACPI]
5776 -1: disable all critical trip points in all thermal zones
5777 <degrees C>: override all critical trip points
5779 thermal.nocrt= [HW,ACPI]
5780 Set to disable actions on ACPI thermal zone
5781 critical and hot trip points.
5783 thermal.off= [HW,ACPI]
5784 1: disable ACPI thermal control
5786 thermal.psv= [HW,ACPI]
5787 -1: disable all passive trip points
5788 <degrees C>: override all passive trip points to this
5791 thermal.tzp= [HW,ACPI]
5792 Specify global default ACPI thermal zone polling rate
5793 <deci-seconds>: poll all this frequency
5794 0: no polling (default)
5797 Force threading of all interrupt handlers except those
5798 marked explicitly IRQF_NO_THREAD.
5802 Specify if the kernel should make use of the cpu
5803 topology information if the hardware supports this.
5804 The scheduler will make use of this information and
5805 e.g. base its process migration decisions on it.
5808 topology_updates= [KNL, PPC, NUMA]
5810 Specify if the kernel should ignore (off)
5811 topology updates sent by the hypervisor to this
5814 torture.disable_onoff_at_boot= [KNL]
5815 Prevent the CPU-hotplug component of torturing
5816 until after init has spawned.
5818 torture.ftrace_dump_at_shutdown= [KNL]
5819 Dump the ftrace buffer at torture-test shutdown,
5820 even if there were no errors. This can be a
5821 very costly operation when many torture tests
5822 are running concurrently, especially on systems
5823 with rotating-rust storage.
5825 torture.verbose_sleep_frequency= [KNL]
5826 Specifies how many verbose printk()s should be
5827 emitted between each sleep. The default of zero
5828 disables verbose-printk() sleeping.
5830 torture.verbose_sleep_duration= [KNL]
5831 Duration of each verbose-printk() sleep in jiffies.
5835 tpm_suspend_pcr=[HW,TPM]
5836 Format: integer pcr id
5837 Specify that at suspend time, the tpm driver
5838 should extend the specified pcr with zeros,
5839 as a workaround for some chips which fail to
5840 flush the last written pcr on TPM_SaveState.
5841 This will guarantee that all the other pcrs
5844 trace_buf_size=nn[KMG]
5845 [FTRACE] will set tracing buffer size on each cpu.
5847 trace_event=[event-list]
5848 [FTRACE] Set and start specified trace events in order
5849 to facilitate early boot debugging. The event-list is a
5850 comma-separated list of trace events to enable. See
5851 also Documentation/trace/events.rst
5853 trace_options=[option-list]
5854 [FTRACE] Enable or disable tracer options at boot.
5855 The option-list is a comma delimited list of options
5856 that can be enabled or disabled just as if you were
5857 to echo the option name into
5859 /sys/kernel/debug/tracing/trace_options
5861 For example, to enable stacktrace option (to dump the
5862 stack trace of each event), add to the command line:
5864 trace_options=stacktrace
5866 See also Documentation/trace/ftrace.rst "trace options"
5870 Have the tracepoints sent to printk as well as the
5871 tracing ring buffer. This is useful for early boot up
5872 where the system hangs or reboots and does not give the
5873 option for reading the tracing buffer or performing a
5874 ftrace_dump_on_oops.
5876 To turn off having tracepoints sent to printk,
5877 echo 0 > /proc/sys/kernel/tracepoint_printk
5878 Note, echoing 1 into this file without the
5879 tracepoint_printk kernel cmdline option has no effect.
5881 The tp_printk_stop_on_boot (see below) can also be used
5882 to stop the printing of events to console at
5887 Having tracepoints sent to printk() and activating high
5888 frequency tracepoints such as irq or sched, can cause
5889 the system to live lock.
5891 tp_printk_stop_on_boot[FTRACE]
5892 When tp_printk (above) is set, it can cause a lot of noise
5893 on the console. It may be useful to only include the
5894 printing of events during boot up, as user space may
5895 make the system inoperable.
5897 This command line option will stop the printing of events
5898 to console at the late_initcall_sync() time frame.
5901 [FTRACE] enable this option to disable tracing when a
5902 warning is hit. This turns off "tracing_on". Tracing can
5903 be enabled again by echoing '1' into the "tracing_on"
5904 file located in /sys/kernel/debug/tracing/
5906 This option is useful, as it disables the trace before
5907 the WARNING dump is called, which prevents the trace to
5908 be filled with content caused by the warning output.
5910 This option can also be set at run time via the sysctl
5911 option: kernel/traceoff_on_warning
5913 transparent_hugepage=
5915 Format: [always|madvise|never]
5916 Can be used to control the default behavior of the system
5917 with respect to transparent hugepages.
5918 See Documentation/admin-guide/mm/transhuge.rst
5921 trusted.source= [KEYS]
5923 This parameter identifies the trust source as a backend
5924 for trusted keys implementation. Supported trust
5928 If not specified then it defaults to iterating through
5929 the trust source list starting with TPM and assigns the
5930 first trust source as a backend which is initialized
5931 successfully during iteration.
5933 tsc= Disable clocksource stability checks for TSC.
5935 [x86] reliable: mark tsc clocksource as reliable, this
5936 disables clocksource verification at runtime, as well
5937 as the stability checks done at bootup. Used to enable
5938 high-resolution timer mode on older hardware, and in
5939 virtualized environment.
5940 [x86] noirqtime: Do not use TSC to do irq accounting.
5941 Used to run time disable IRQ_TIME_ACCOUNTING on any
5942 platforms where RDTSC is slow and this accounting
5944 [x86] unstable: mark the TSC clocksource as unstable, this
5945 marks the TSC unconditionally unstable at bootup and
5946 avoids any further wobbles once the TSC watchdog notices.
5947 [x86] nowatchdog: disable clocksource watchdog. Used
5948 in situations with strict latency requirements (where
5949 interruptions from clocksource watchdog are not
5952 tsc_early_khz= [X86] Skip early TSC calibration and use the given
5953 value instead. Useful when the early TSC frequency discovery
5954 procedure is not reliable, such as on overclocked systems
5955 with CPUID.16h support and partial CPUID.15h support.
5956 Format: <unsigned int>
5958 tsx= [X86] Control Transactional Synchronization
5959 Extensions (TSX) feature in Intel processors that
5960 support TSX control.
5962 This parameter controls the TSX feature. The options are:
5964 on - Enable TSX on the system. Although there are
5965 mitigations for all known security vulnerabilities,
5966 TSX has been known to be an accelerator for
5967 several previous speculation-related CVEs, and
5968 so there may be unknown security risks associated
5969 with leaving it enabled.
5971 off - Disable TSX on the system. (Note that this
5972 option takes effect only on newer CPUs which are
5973 not vulnerable to MDS, i.e., have
5974 MSR_IA32_ARCH_CAPABILITIES.MDS_NO=1 and which get
5975 the new IA32_TSX_CTRL MSR through a microcode
5976 update. This new MSR allows for the reliable
5977 deactivation of the TSX functionality.)
5979 auto - Disable TSX if X86_BUG_TAA is present,
5980 otherwise enable TSX on the system.
5982 Not specifying this option is equivalent to tsx=off.
5984 See Documentation/admin-guide/hw-vuln/tsx_async_abort.rst
5987 tsx_async_abort= [X86,INTEL] Control mitigation for the TSX Async
5988 Abort (TAA) vulnerability.
5990 Similar to Micro-architectural Data Sampling (MDS)
5991 certain CPUs that support Transactional
5992 Synchronization Extensions (TSX) are vulnerable to an
5993 exploit against CPU internal buffers which can forward
5994 information to a disclosure gadget under certain
5997 In vulnerable processors, the speculatively forwarded
5998 data can be used in a cache side channel attack, to
5999 access data to which the attacker does not have direct
6002 This parameter controls the TAA mitigation. The
6005 full - Enable TAA mitigation on vulnerable CPUs
6008 full,nosmt - Enable TAA mitigation and disable SMT on
6009 vulnerable CPUs. If TSX is disabled, SMT
6010 is not disabled because CPU is not
6011 vulnerable to cross-thread TAA attacks.
6012 off - Unconditionally disable TAA mitigation
6014 On MDS-affected machines, tsx_async_abort=off can be
6015 prevented by an active MDS mitigation as both vulnerabilities
6016 are mitigated with the same mechanism so in order to disable
6017 this mitigation, you need to specify mds=off too.
6019 Not specifying this option is equivalent to
6020 tsx_async_abort=full. On CPUs which are MDS affected
6021 and deploy MDS mitigation, TAA mitigation is not
6022 required and doesn't provide any additional
6026 Documentation/admin-guide/hw-vuln/tsx_async_abort.rst
6028 turbografx.map[2|3]= [HW,JOY]
6029 TurboGraFX parallel port interface
6031 <port#>,<js1>,<js2>,<js3>,<js4>,<js5>,<js6>,<js7>
6032 See also Documentation/input/devices/joystick-parport.rst
6034 udbg-immortal [PPC] When debugging early kernel crashes that
6035 happen after console_init() and before a proper
6036 console driver takes over, this boot options might
6037 help "seeing" what's going on.
6039 uhash_entries= [KNL,NET]
6040 Set number of hash buckets for UDP/UDP-Lite connections
6043 [USB] Ignore overcurrent events (default N).
6044 Some badly-designed motherboards generate lots of
6045 bogus events, for ports that aren't wired to
6046 anything. Set this parameter to avoid log spamming.
6047 Note that genuine overcurrent events won't be
6051 [X86] Cause panic on unknown NMI.
6053 usbcore.authorized_default=
6054 [USB] Default USB device authorization:
6055 (default -1 = authorized except for wireless USB,
6056 0 = not authorized, 1 = authorized, 2 = authorized
6057 if device connected to internal port)
6059 usbcore.autosuspend=
6060 [USB] The autosuspend time delay (in seconds) used
6061 for newly-detected USB devices (default 2). This
6062 is the time required before an idle device will be
6063 autosuspended. Devices for which the delay is set
6064 to a negative value won't be autosuspended at all.
6066 usbcore.usbfs_snoop=
6067 [USB] Set to log all usbfs traffic (default 0 = off).
6069 usbcore.usbfs_snoop_max=
6070 [USB] Maximum number of bytes to snoop in each URB
6073 usbcore.blinkenlights=
6074 [USB] Set to cycle leds on hubs (default 0 = off).
6076 usbcore.old_scheme_first=
6077 [USB] Start with the old device initialization
6078 scheme (default 0 = off).
6080 usbcore.usbfs_memory_mb=
6081 [USB] Memory limit (in MB) for buffers allocated by
6082 usbfs (default = 16, 0 = max = 2047).
6084 usbcore.use_both_schemes=
6085 [USB] Try the other device initialization scheme
6086 if the first one fails (default 1 = enabled).
6088 usbcore.initial_descriptor_timeout=
6089 [USB] Specifies timeout for the initial 64-byte
6090 USB_REQ_GET_DESCRIPTOR request in milliseconds
6091 (default 5000 = 5.0 seconds).
6093 usbcore.nousb [USB] Disable the USB subsystem
6096 [USB] A list of quirk entries to augment the built-in
6097 usb core quirk list. List entries are separated by
6098 commas. Each entry has the form
6099 VendorID:ProductID:Flags. The IDs are 4-digit hex
6100 numbers and Flags is a set of letters. Each letter
6101 will change the built-in quirk; setting it if it is
6102 clear and clearing it if it is set. The letters have
6103 the following meanings:
6104 a = USB_QUIRK_STRING_FETCH_255 (string
6105 descriptors must not be fetched using
6107 b = USB_QUIRK_RESET_RESUME (device can't resume
6108 correctly so reset it instead);
6109 c = USB_QUIRK_NO_SET_INTF (device can't handle
6110 Set-Interface requests);
6111 d = USB_QUIRK_CONFIG_INTF_STRINGS (device can't
6112 handle its Configuration or Interface
6114 e = USB_QUIRK_RESET (device can't be reset
6115 (e.g morph devices), don't use reset);
6116 f = USB_QUIRK_HONOR_BNUMINTERFACES (device has
6117 more interface descriptions than the
6118 bNumInterfaces count, and can't handle
6119 talking to these interfaces);
6120 g = USB_QUIRK_DELAY_INIT (device needs a pause
6121 during initialization, after we read
6122 the device descriptor);
6123 h = USB_QUIRK_LINEAR_UFRAME_INTR_BINTERVAL (For
6124 high speed and super speed interrupt
6125 endpoints, the USB 2.0 and USB 3.0 spec
6126 require the interval in microframes (1
6127 microframe = 125 microseconds) to be
6128 calculated as interval = 2 ^
6130 Devices with this quirk report their
6131 bInterval as the result of this
6132 calculation instead of the exponent
6133 variable used in the calculation);
6134 i = USB_QUIRK_DEVICE_QUALIFIER (device can't
6135 handle device_qualifier descriptor
6137 j = USB_QUIRK_IGNORE_REMOTE_WAKEUP (device
6138 generates spurious wakeup, ignore
6139 remote wakeup capability);
6140 k = USB_QUIRK_NO_LPM (device can't handle Link
6142 l = USB_QUIRK_LINEAR_FRAME_INTR_BINTERVAL
6143 (Device reports its bInterval as linear
6144 frames instead of the USB 2.0
6146 m = USB_QUIRK_DISCONNECT_SUSPEND (Device needs
6147 to be disconnected before suspend to
6148 prevent spurious wakeup);
6149 n = USB_QUIRK_DELAY_CTRL_MSG (Device needs a
6150 pause after every control message);
6151 o = USB_QUIRK_HUB_SLOW_RESET (Hub needs extra
6152 delay after resetting its port);
6153 Example: quirks=0781:5580:bk,0a5c:5834:gij
6156 [USBHID] The interval which mice are to be polled at.
6159 [USBHID] The interval which joysticks are to be polled at.
6162 [USBHID] The interval which keyboards are to be polled at.
6164 usb-storage.delay_use=
6165 [UMS] The delay in seconds before a new device is
6166 scanned for Logical Units (default 1).
6169 [UMS] A list of quirks entries to supplement or
6170 override the built-in unusual_devs list. List
6171 entries are separated by commas. Each entry has
6172 the form VID:PID:Flags where VID and PID are Vendor
6173 and Product ID values (4-digit hex numbers) and
6174 Flags is a set of characters, each corresponding
6175 to a common usb-storage quirk flag as follows:
6176 a = SANE_SENSE (collect more than 18 bytes
6177 of sense data, not on uas);
6178 b = BAD_SENSE (don't collect more than 18
6179 bytes of sense data, not on uas);
6180 c = FIX_CAPACITY (decrease the reported
6181 device capacity by one sector);
6182 d = NO_READ_DISC_INFO (don't use
6183 READ_DISC_INFO command, not on uas);
6184 e = NO_READ_CAPACITY_16 (don't use
6185 READ_CAPACITY_16 command);
6186 f = NO_REPORT_OPCODES (don't use report opcodes
6188 g = MAX_SECTORS_240 (don't transfer more than
6189 240 sectors at a time, uas only);
6190 h = CAPACITY_HEURISTICS (decrease the
6191 reported device capacity by one
6192 sector if the number is odd);
6193 i = IGNORE_DEVICE (don't bind to this
6195 j = NO_REPORT_LUNS (don't use report luns
6197 k = NO_SAME (do not use WRITE_SAME, uas only)
6198 l = NOT_LOCKABLE (don't try to lock and
6199 unlock ejectable media, not on uas);
6200 m = MAX_SECTORS_64 (don't transfer more
6201 than 64 sectors = 32 KB at a time,
6203 n = INITIAL_READ10 (force a retry of the
6204 initial READ(10) command, not on uas);
6205 o = CAPACITY_OK (accept the capacity
6206 reported by the device, not on uas);
6207 p = WRITE_CACHE (the device cache is ON
6208 by default, not on uas);
6209 r = IGNORE_RESIDUE (the device reports
6210 bogus residue values, not on uas);
6211 s = SINGLE_LUN (the device has only one
6213 t = NO_ATA_1X (don't allow ATA(12) and ATA(16)
6214 commands, uas only);
6215 u = IGNORE_UAS (don't bind to the uas driver);
6216 w = NO_WP_DETECT (don't test whether the
6217 medium is write-protected).
6218 y = ALWAYS_SYNC (issue a SYNCHRONIZE_CACHE
6219 even if the device claims no cache,
6221 Example: quirks=0419:aaf5:rl,0421:0433:rc
6223 user_debug= [KNL,ARM]
6225 See arch/arm/Kconfig.debug help text.
6226 1 - undefined instruction events
6228 4 - invalid data aborts
6231 Example: user_debug=31
6234 [X86] Flags controlling user PTE allocations.
6236 nohigh = do not allocate PTE pages in
6237 HIGHMEM regardless of setting
6241 On X86_32, this is an alias for vdso32=. Otherwise:
6243 vdso=1: enable VDSO (the default)
6244 vdso=0: disable VDSO mapping
6246 vdso32= [X86] Control the 32-bit vDSO
6247 vdso32=1: enable 32-bit VDSO
6248 vdso32=0 or vdso32=2: disable 32-bit VDSO
6250 See the help text for CONFIG_COMPAT_VDSO for more
6251 details. If CONFIG_COMPAT_VDSO is set, the default is
6252 vdso32=0; otherwise, the default is vdso32=1.
6254 For compatibility with older kernels, vdso32=2 is an
6257 Try vdso32=0 if you encounter an error that says:
6258 dl_main: Assertion `(void *) ph->p_vaddr == _rtld_local._dl_sysinfo_dso' failed!
6261 vector=percpu: enable percpu vector domain
6263 video= [FB] Frame buffer configuration
6264 See Documentation/fb/modedb.rst.
6266 video.brightness_switch_enabled= [0,1]
6267 If set to 1, on receiving an ACPI notify event
6268 generated by hotkey, video driver will adjust brightness
6269 level and then send out the event to user space through
6270 the allocated input device; If set to 0, video driver
6271 will only send out the event without touching backlight
6276 [VMMIO] Memory mapped virtio (platform) device.
6278 <size>@<baseaddr>:<irq>[:<id>]
6280 <size> := size (can use standard suffixes
6282 <baseaddr> := physical base address
6283 <irq> := interrupt number (as passed to
6285 <id> := (optional) platform device id
6287 virtio_mmio.device=1K@0x100b0000:48:7
6289 Can be used multiple times for multiple devices.
6291 vga= [BOOT,X86-32] Select a particular video mode
6292 See Documentation/x86/boot.rst and
6293 Documentation/admin-guide/svga.rst.
6294 Use vga=ask for menu.
6295 This is actually a boot loader parameter; the value is
6296 passed to the kernel using a special protocol.
6298 vm_debug[=options] [KNL] Available with CONFIG_DEBUG_VM=y.
6299 May slow down system boot speed, especially when
6300 enabled on systems with a large amount of memory.
6301 All options are enabled by default, and this
6302 interface is meant to allow for selectively
6303 enabling or disabling specific virtual memory
6306 Available options are:
6307 P Enable page structure init time poisoning
6308 - Disable all of the above options
6310 vmalloc=nn[KMG] [KNL,BOOT] Forces the vmalloc area to have an exact
6311 size of <nn>. This can be used to increase the
6312 minimum size (128MB on x86). It can also be used to
6313 decrease the size and leave more room for directly
6316 vmcp_cma=nn[MG] [KNL,S390]
6317 Sets the memory size reserved for contiguous memory
6318 allocations for the vmcp device driver.
6320 vmhalt= [KNL,S390] Perform z/VM CP command after system halt.
6323 vmpanic= [KNL,S390] Perform z/VM CP command after kernel panic.
6326 vmpoff= [KNL,S390] Perform z/VM CP command after power off.
6330 Controls the behavior of vsyscalls (i.e. calls to
6331 fixed addresses of 0xffffffffff600x00 from legacy
6332 code). Most statically-linked binaries and older
6333 versions of glibc use these calls. Because these
6334 functions are at fixed addresses, they make nice
6335 targets for exploits that can control RIP.
6337 emulate [default] Vsyscalls turn into traps and are
6338 emulated reasonably safely. The vsyscall
6341 xonly Vsyscalls turn into traps and are
6342 emulated reasonably safely. The vsyscall
6343 page is not readable.
6345 none Vsyscalls don't work at all. This makes
6346 them quite hard to use for exploits but
6347 might break your system.
6349 vt.color= [VT] Default text color.
6350 Format: 0xYX, X = foreground, Y = background.
6351 Default: 0x07 = light gray on black.
6353 vt.cur_default= [VT] Default cursor shape.
6354 Format: 0xCCBBAA, where AA, BB, and CC are the same as
6355 the parameters of the <Esc>[?A;B;Cc escape sequence;
6356 see VGA-softcursor.txt. Default: 2 = underline.
6358 vt.default_blu= [VT]
6359 Format: <blue0>,<blue1>,<blue2>,...,<blue15>
6360 Change the default blue palette of the console.
6361 This is a 16-member array composed of values
6364 vt.default_grn= [VT]
6365 Format: <green0>,<green1>,<green2>,...,<green15>
6366 Change the default green palette of the console.
6367 This is a 16-member array composed of values
6370 vt.default_red= [VT]
6371 Format: <red0>,<red1>,<red2>,...,<red15>
6372 Change the default red palette of the console.
6373 This is a 16-member array composed of values
6379 Set system-wide default UTF-8 mode for all tty's.
6380 Default is 1, i.e. UTF-8 mode is enabled for all
6381 newly opened terminals.
6383 vt.global_cursor_default=
6386 Set system-wide default for whether a cursor
6387 is shown on new VTs. Default is -1,
6388 i.e. cursors will be created by default unless
6389 overridden by individual drivers. 0 will hide
6390 cursors, 1 will display them.
6392 vt.italic= [VT] Default color for italic text; 0-15.
6395 vt.underline= [VT] Default color for underlined text; 0-15.
6398 watchdog timers [HW,WDT] For information on watchdog timers,
6399 see Documentation/watchdog/watchdog-parameters.rst
6400 or other driver-specific files in the
6401 Documentation/watchdog/ directory.
6405 Set the hard lockup detector stall duration
6406 threshold in seconds. The soft lockup detector
6407 threshold is set to twice the value. A value of 0
6408 disables both lockup detectors. Default is 10
6411 workqueue.watchdog_thresh=
6412 If CONFIG_WQ_WATCHDOG is configured, workqueue can
6413 warn stall conditions and dump internal state to
6414 help debugging. 0 disables workqueue stall
6415 detection; otherwise, it's the stall threshold
6416 duration in seconds. The default value is 30 and
6417 it can be updated at runtime by writing to the
6418 corresponding sysfs file.
6420 workqueue.disable_numa
6421 By default, all work items queued to unbound
6422 workqueues are affine to the NUMA nodes they're
6423 issued on, which results in better behavior in
6424 general. If NUMA affinity needs to be disabled for
6425 whatever reason, this option can be used. Note
6426 that this also can be controlled per-workqueue for
6427 workqueues visible under /sys/bus/workqueue/.
6429 workqueue.power_efficient
6430 Per-cpu workqueues are generally preferred because
6431 they show better performance thanks to cache
6432 locality; unfortunately, per-cpu workqueues tend to
6433 be more power hungry than unbound workqueues.
6435 Enabling this makes the per-cpu workqueues which
6436 were observed to contribute significantly to power
6437 consumption unbound, leading to measurably lower
6438 power usage at the cost of small performance
6441 The default value of this parameter is determined by
6442 the config option CONFIG_WQ_POWER_EFFICIENT_DEFAULT.
6444 workqueue.debug_force_rr_cpu
6445 Workqueue used to implicitly guarantee that work
6446 items queued without explicit CPU specified are put
6447 on the local CPU. This guarantee is no longer true
6448 and while local CPU is still preferred work items
6449 may be put on foreign CPUs. This debug option
6450 forces round-robin CPU selection to flush out
6451 usages which depend on the now broken guarantee.
6452 When enabled, memory and cache locality will be
6455 x2apic_phys [X86-64,APIC] Use x2apic physical mode instead of
6456 default x2apic cluster mode on platforms
6459 xen_512gb_limit [KNL,X86-64,XEN]
6460 Restricts the kernel running paravirtualized under Xen
6461 to use only up to 512 GB of RAM. The reason to do so is
6462 crash analysis tools and Xen tools for doing domain
6463 save/restore/migration must be enabled to handle larger
6466 xen_emul_unplug= [HW,X86,XEN]
6467 Unplug Xen emulated devices
6468 Format: [unplug0,][unplug1]
6469 ide-disks -- unplug primary master IDE devices
6470 aux-ide-disks -- unplug non-primary-master IDE devices
6471 nics -- unplug network devices
6472 all -- unplug all emulated devices (NICs and IDE disks)
6473 unnecessary -- unplugging emulated devices is
6474 unnecessary even if the host did not respond to
6476 never -- do not unplug even if version check succeeds
6478 xen_legacy_crash [X86,XEN]
6479 Crash from Xen panic notifier, without executing late
6480 panic() code such as dumping handler.
6482 xen_nopvspin [X86,XEN]
6483 Disables the qspinlock slowpath using Xen PV optimizations.
6484 This parameter is obsoleted by "nopvspin" parameter, which
6485 has equivalent effect for XEN platform.
6488 Disables the PV optimizations forcing the HVM guest to
6489 run as generic HVM guest with no PV drivers.
6490 This option is obsoleted by the "nopv" option, which
6491 has equivalent effect for XEN platform.
6493 xen_no_vector_callback
6494 [KNL,X86,XEN] Disable the vector callback for Xen
6495 event channel interrupts.
6497 xen_scrub_pages= [XEN]
6498 Boolean option to control scrubbing pages before giving them back
6499 to Xen, for use by other domains. Can be also changed at runtime
6500 with /sys/devices/system/xen_memory/xen_memory0/scrub_pages.
6501 Default value controlled with CONFIG_XEN_SCRUB_PAGES_DEFAULT.
6503 xen_timer_slop= [X86-64,XEN]
6504 Set the timer slop (in nanoseconds) for the virtual Xen
6505 timers (default is 100000). This adjusts the minimum
6506 delta of virtualized Xen timers, where lower values
6507 improve timer resolution at the expense of processing
6508 more timer interrupts.
6510 xen.balloon_boot_timeout= [XEN]
6511 The time (in seconds) to wait before giving up to boot
6512 in case initial ballooning fails to free enough memory.
6513 Applies only when running as HVM or PVH guest and
6514 started with less memory configured than allowed at
6515 max. Default is 180.
6517 xen.event_eoi_delay= [XEN]
6518 How long to delay EOI handling in case of event
6519 storms (jiffies). Default is 10.
6521 xen.event_loop_timeout= [XEN]
6522 After which time (jiffies) the event handling loop
6523 should start to delay EOI handling. Default is 2.
6525 xen.fifo_events= [XEN]
6526 Boolean parameter to disable using fifo event handling
6527 even if available. Normally fifo event handling is
6528 preferred over the 2-level event handling, as it is
6529 fairer and the number of possible event channels is
6530 much higher. Default is on (use fifo events).
6532 nopv= [X86,XEN,KVM,HYPER_V,VMWARE]
6533 Disables the PV optimizations forcing the guest to run
6534 as generic guest with no PV drivers. Currently support
6535 XEN HVM, KVM, HYPER_V and VMWARE guest.
6537 nopvspin [X86,XEN,KVM]
6538 Disables the qspinlock slow path using PV optimizations
6539 which allow the hypervisor to 'idle' the guest on lock
6542 xirc2ps_cs= [NET,PCMCIA]
6544 <irq>,<irq_mask>,<io>,<full_duplex>,<do_sound>,<lockup_hack>[,<irq2>[,<irq3>[,<irq4>]]]
6547 By default on POWER9 and above, the kernel will
6548 natively use the XIVE interrupt controller. This option
6549 allows the fallback firmware mode to be used:
6551 off Fallback to firmware control of XIVE interrupt
6552 controller on both pseries and powernv
6553 platforms. Only useful on POWER9 and above.
6555 xive.store-eoi=off [PPC]
6556 By default on POWER10 and above, the kernel will use
6557 stores for EOI handling when the XIVE interrupt mode
6558 is active. This option allows the XIVE driver to use
6559 loads instead, as on POWER9.
6561 xhci-hcd.quirks [USB,KNL]
6562 A hex value specifying bitmask with supplemental xhci
6563 host controller quirks. Meaning of each bit can be
6564 consulted in header drivers/usb/host/xhci.h.
6567 Format: { early | on | rw | ro | off }
6568 Controls if xmon debugger is enabled. Default is off.
6569 Passing only "xmon" is equivalent to "xmon=early".
6570 early Call xmon as early as possible on boot; xmon
6571 debugger is called from setup_arch().
6572 on xmon debugger hooks will be installed so xmon
6573 is only called on a kernel crash. Default mode,
6574 i.e. either "ro" or "rw" mode, is controlled
6575 with CONFIG_XMON_DEFAULT_RO_MODE.
6576 rw xmon debugger hooks will be installed so xmon
6577 is called only on a kernel crash, mode is write,
6578 meaning SPR registers, memory and, other data
6579 can be written using xmon commands.
6580 ro same as "rw" option above but SPR registers,
6581 memory, and other data can't be written using
6583 off xmon is disabled.
projects / platform / kernel / linux-rpi.git / blob