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
403 arm64.nosve [ARM64] Unconditionally disable Scalable Vector
406 arm64.nosme [ARM64] Unconditionally disable Scalable Matrix
411 atarimouse= [HW,MOUSE] Atari Mouse
413 atkbd.extra= [HW] Enable extra LEDs and keys on IBM RapidAccess,
414 EzKey and similar keyboards
416 atkbd.reset= [HW] Reset keyboard during initialization
418 atkbd.set= [HW] Select keyboard code set
419 Format: <int> (2 = AT (default), 3 = PS/2)
421 atkbd.scroll= [HW] Enable scroll wheel on MS Office and similar
424 atkbd.softraw= [HW] Choose between synthetic and real raw mode
425 Format: <bool> (0 = real, 1 = synthetic (default))
427 atkbd.softrepeat= [HW]
428 Use software keyboard repeat
430 audit= [KNL] Enable the audit sub-system
431 Format: { "0" | "1" | "off" | "on" }
432 0 | off - kernel audit is disabled and can not be
433 enabled until the next reboot
434 unset - kernel audit is initialized but disabled and
435 will be fully enabled by the userspace auditd.
436 1 | on - kernel audit is initialized and partially
437 enabled, storing at most audit_backlog_limit
438 messages in RAM until it is fully enabled by the
442 audit_backlog_limit= [KNL] Set the audit queue size limit.
443 Format: <int> (must be >=0)
446 bau= [X86_UV] Enable the BAU on SGI UV. The default
447 behavior is to disable the BAU (i.e. bau=0).
448 Format: { "0" | "1" }
451 unset - Disable the BAU.
453 baycom_epp= [HW,AX25]
456 baycom_par= [HW,AX25] BayCom Parallel Port AX.25 Modem
458 See header of drivers/net/hamradio/baycom_par.c.
460 baycom_ser_fdx= [HW,AX25]
461 BayCom Serial Port AX.25 Modem (Full Duplex Mode)
462 Format: <io>,<irq>,<mode>[,<baud>]
463 See header of drivers/net/hamradio/baycom_ser_fdx.c.
465 baycom_ser_hdx= [HW,AX25]
466 BayCom Serial Port AX.25 Modem (Half Duplex Mode)
467 Format: <io>,<irq>,<mode>
468 See header of drivers/net/hamradio/baycom_ser_hdx.c.
471 Disable BERT OS support on buggy BIOSes.
473 bgrt_disable [ACPI][X86]
474 Disable BGRT to avoid flickering OEM logo.
476 blkdevparts= Manual partition parsing of block device(s) for
477 embedded devices based on command line input.
478 See Documentation/block/cmdline-partition.rst
480 boot_delay= Milliseconds to delay each printk during boot.
481 Values larger than 10 seconds (10000) are changed to
486 Extended command line options can be added to an initrd
487 and this will cause the kernel to look for it.
489 See Documentation/admin-guide/bootconfig.rst
491 bttv.card= [HW,V4L] bttv (bt848 + bt878 based grabber cards)
492 bttv.radio= Most important insmod options are available as
494 bttv.pll= See Documentation/admin-guide/media/bttv.rst
497 bulk_remove=off [PPC] This parameter disables the use of the pSeries
498 firmware feature for flushing multiple hpte entries
501 c101= [NET] Moxa C101 synchronous serial card
503 cachesize= [BUGS=X86-32] Override level 2 CPU cache size detection.
504 Sometimes CPU hardware bugs make them report the cache
505 size incorrectly. The kernel will attempt work arounds
506 to fix known problems, but for some CPUs it is not
507 possible to determine what the correct size should be.
508 This option provides an override for these situations.
511 [NET] Specifies amount of time (in seconds) that
512 the kernel should wait for a network carrier. By default
513 it waits 120 seconds.
515 ca_keys= [KEYS] This parameter identifies a specific key(s) on
516 the system trusted keyring to be used for certificate
518 format: { id:<keyid> | builtin }
520 cca= [MIPS] Override the kernel pages' cache coherency
521 algorithm. Accepted values range from 0 to 7
522 inclusive. See arch/mips/include/asm/pgtable-bits.h
523 for platform specific values (SB1, Loongson3 and
526 ccw_timeout_log [S390]
527 See Documentation/s390/common_io.rst for details.
529 cgroup_disable= [KNL] Disable a particular controller or optional feature
530 Format: {name of the controller(s) or feature(s) to disable}
531 The effects of cgroup_disable=foo are:
532 - foo isn't auto-mounted if you mount all cgroups in
534 - foo isn't visible as an individually mountable
536 - if foo is an optional feature then the feature is
537 disabled and corresponding cgroup files are not
539 {Currently only "memory" controller deal with this and
540 cut the overhead, others just disable the usage. So
541 only cgroup_disable=memory is actually worthy}
542 Specifying "pressure" disables per-cgroup pressure
543 stall information accounting feature
545 cgroup_no_v1= [KNL] Disable cgroup controllers and named hierarchies in v1
546 Format: { { controller | "all" | "named" }
547 [,{ controller | "all" | "named" }...] }
548 Like cgroup_disable, but only applies to cgroup v1;
549 the blacklisted controllers remain available in cgroup2.
550 "all" blacklists all controllers and "named" disables
551 named mounts. Specifying both "all" and "named" disables
554 cgroup.memory= [KNL] Pass options to the cgroup memory controller.
556 nosocket -- Disable socket memory accounting.
557 nokmem -- Disable kernel memory accounting.
559 checkreqprot= [SELINUX] Set initial checkreqprot flag value.
560 Format: { "0" | "1" }
561 See security/selinux/Kconfig help text.
562 0 -- check protection applied by kernel (includes
563 any implied execute protection).
564 1 -- check protection requested by application.
565 Default value is set via a kernel config option.
566 Value can be changed at runtime via
567 /sys/fs/selinux/checkreqprot.
568 Setting checkreqprot to 1 is deprecated.
571 See Documentation/s390/common_io.rst for details.
573 clearcpuid=X[,X...] [X86]
574 Disable CPUID feature X for the kernel. See
575 arch/x86/include/asm/cpufeatures.h for the valid bit
576 numbers X. Note the Linux-specific bits are not necessarily
577 stable over kernel options, but the vendor-specific
579 X can also be a string as appearing in the flags: line
580 in /proc/cpuinfo which does not have the above
581 instability issue. However, not all features have names
583 Note that using this option will taint your kernel.
584 Also note that user programs calling CPUID directly
585 or using the feature without checking anything
586 will still see it. This just prevents it from
587 being used by the kernel or shown in /proc/cpuinfo.
588 Also note the kernel might malfunction if you disable
593 Prevents the clock framework from automatically gating
594 clocks that have not been explicitly enabled by a Linux
595 device driver but are enabled in hardware at reset or
596 by the bootloader/firmware. Note that this does not
597 force such clocks to be always-on nor does it reserve
598 those clocks in any way. This parameter is useful for
599 debug and development, but should not be needed on a
600 platform with proper driver support. For more
601 information, see Documentation/driver-api/clk.rst.
603 clock= [BUGS=X86-32, HW] gettimeofday clocksource override.
605 Forces specified clocksource (if available) to be used
606 when calculating gettimeofday(). If specified
607 clocksource is not available, it defaults to PIT.
608 Format: { pit | tsc | cyclone | pmtmr }
610 clocksource= Override the default clocksource
612 Override the default clocksource and use the clocksource
613 with the name specified.
614 Some clocksource names to choose from, depending on
616 [all] jiffies (this is the base, fallback clocksource)
618 [ARM] imx_timer1,OSTS,netx_timer,mpu_timer2,
619 pxa_timer,timer3,32k_counter,timer0_1
620 [X86-32] pit,hpet,tsc;
621 scx200_hrt on Geode; cyclone on IBM x440
629 clocksource.arm_arch_timer.evtstrm=
632 Enable/disable the eventstream feature of the ARM
633 architected timer so that code using WFE-based polling
634 loops can be debugged more effectively on production
637 clocksource.max_cswd_read_retries= [KNL]
638 Number of clocksource_watchdog() retries due to
639 external delays before the clock will be marked
640 unstable. Defaults to two retries, that is,
641 three attempts to read the clock under test.
643 clocksource.verify_n_cpus= [KNL]
644 Limit the number of CPUs checked for clocksources
645 marked with CLOCK_SOURCE_VERIFY_PERCPU that
646 are marked unstable due to excessive skew.
647 A negative value says to check all CPUs, while
648 zero says not to check any. Values larger than
649 nr_cpu_ids are silently truncated to nr_cpu_ids.
650 The actual CPUs are chosen randomly, with
651 no replacement if the same CPU is chosen twice.
653 clocksource-wdtest.holdoff= [KNL]
654 Set the time in seconds that the clocksource
655 watchdog test waits before commencing its tests.
656 Defaults to zero when built as a module and to
657 10 seconds when built into the kernel.
659 cma=nn[MG]@[start[MG][-end[MG]]]
661 Sets the size of kernel global memory area for
662 contiguous memory allocations and optionally the
663 placement constraint by the physical address range of
664 memory allocations. A value of 0 disables CMA
665 altogether. For more information, see
666 kernel/dma/contiguous.c
670 Sets the size of kernel per-numa memory area for
671 contiguous memory allocations. A value of 0 disables
672 per-numa CMA altogether. And If this option is not
673 specificed, the default value is 0.
674 With per-numa CMA enabled, DMA users on node nid will
675 first try to allocate buffer from the pernuma area
676 which is located in node nid, if the allocation fails,
677 they will fallback to the global default memory area.
679 cmo_free_hint= [PPC] Format: { yes | no }
680 Specify whether pages are marked as being inactive
681 when they are freed. This is used in CMO environments
682 to determine OS memory pressure for page stealing by
686 coherent_pool=nn[KMG] [ARM,KNL]
687 Sets the size of memory pool for coherent, atomic dma
688 allocations, by default set to 256K.
690 com20020= [HW,NET] ARCnet - COM20020 chipset
692 <io>[,<irq>[,<nodeID>[,<backplane>[,<ckp>[,<timeout>]]]]]
694 com90io= [HW,NET] ARCnet - COM90xx chipset (IO-mapped buffers)
698 ARCnet - COM90xx chipset (memory-mapped buffers)
699 Format: <io>[,<irq>[,<memstart>]]
701 condev= [HW,S390] console device
704 console= [KNL] Output console device and options.
706 tty<n> Use the virtual console device <n>.
710 Use the specified serial port. The options are of
711 the form "bbbbpnf", where "bbbb" is the baud rate,
712 "p" is parity ("n", "o", or "e"), "n" is number of
713 bits, and "f" is flow control ("r" for RTS or
714 omit it). Default is "9600n8".
716 See Documentation/admin-guide/serial-console.rst for more
718 Documentation/networking/netconsole.rst for an
721 uart[8250],io,<addr>[,options]
722 uart[8250],mmio,<addr>[,options]
723 uart[8250],mmio16,<addr>[,options]
724 uart[8250],mmio32,<addr>[,options]
725 uart[8250],0x<addr>[,options]
726 Start an early, polled-mode console on the 8250/16550
727 UART at the specified I/O port or MMIO address,
728 switching to the matching ttyS device later.
729 MMIO inter-register address stride is either 8-bit
730 (mmio), 16-bit (mmio16), or 32-bit (mmio32).
731 If none of [io|mmio|mmio16|mmio32], <addr> is assumed
732 to be equivalent to 'mmio'. 'options' are specified in
733 the same format described for ttyS above; if unspecified,
734 the h/w is not re-initialized.
736 hvc<n> Use the hypervisor console device <n>. This is for
737 both Xen and PowerPC hypervisors.
740 Use to disable console output, i.e., to have kernel
741 console messages discarded.
742 This must be the only console= parameter used on the
745 If the device connected to the port is not a TTY but a braille
746 device, prepend "brl," before the device type, for instance
748 For now, only VisioBraille is supported.
751 [KNL] Change console messages format
753 By default we print messages on consoles in
754 "[time stamp] text\n" format (time stamp may not be
755 printed, depending on CONFIG_PRINTK_TIME or
756 `printk_time' param).
758 Switch to syslog format: "<%u>[time stamp] text\n"
759 IOW, each message will have a facility and loglevel
760 prefix. The format is similar to one used by syslog()
761 syscall, or to executing "dmesg -S --raw" or to reading
764 consoleblank= [KNL] The console blank (screen saver) timeout in
765 seconds. A value of 0 disables the blank timer.
769 [KNL] Change the default value for
770 /proc/<pid>/coredump_filter.
771 See also Documentation/filesystems/proc.rst.
773 coresight_cpu_debug.enable
776 Enable/disable the CPU sampling based debugging.
777 0: default value, disable debugging
778 1: enable debugging at boot time
780 cpcihp_generic= [HW,PCI] Generic port I/O CompactPCI driver
782 <first_slot>,<last_slot>,<port>,<enum_bit>[,<debug>]
784 cpu0_hotplug [X86] Turn on CPU0 hotplug feature when
785 CONFIG_BOOTPARAM_HOTPLUG_CPU0 is off.
786 Some features depend on CPU0. Known dependencies are:
787 1. Resume from suspend/hibernate depends on CPU0.
788 Suspend/hibernate will fail if CPU0 is offline and you
789 need to online CPU0 before suspend/hibernate.
790 2. PIC interrupts also depend on CPU0. CPU0 can't be
791 removed if a PIC interrupt is detected.
792 It's said poweroff/reboot may depend on CPU0 on some
793 machines although I haven't seen such issues so far
794 after CPU0 is offline on a few tested machines.
795 If the dependencies are under your control, you can
796 turn on cpu0_hotplug.
798 cpuidle.off=1 [CPU_IDLE]
799 disable the cpuidle sub-system
802 [CPU_IDLE] Name of the cpuidle governor to use.
804 cpufreq.off=1 [CPU_FREQ]
805 disable the cpufreq sub-system
807 cpufreq.default_governor=
808 [CPU_FREQ] Name of the default cpufreq governor or
809 policy to use. This governor must be registered in the
810 kernel before the cpufreq driver probes.
813 [X86] Delay for N microsec between assert and de-assert
814 of APIC INIT to start processors. This delay occurs
815 on every CPU online, such as boot, and resume from suspend.
818 crash_kexec_post_notifiers
819 Run kdump after running panic-notifiers and dumping
820 kmsg. This only for the users who doubt kdump always
821 succeeds in any situation.
822 Note that this also increases risks of kdump failure,
823 because some panic notifiers can make the crashed
824 kernel more unstable.
826 crashkernel=size[KMG][@offset[KMG]]
827 [KNL] Using kexec, Linux can switch to a 'crash kernel'
828 upon panic. This parameter reserves the physical
829 memory region [offset, offset + size] for that kernel
830 image. If '@offset' is omitted, then a suitable offset
831 is selected automatically.
832 [KNL, X86-64] Select a region under 4G first, and
833 fall back to reserve region above 4G when '@offset'
834 hasn't been specified.
835 See Documentation/admin-guide/kdump/kdump.rst for further details.
837 crashkernel=range1:size1[,range2:size2,...][@offset]
838 [KNL] Same as above, but depends on the memory
839 in the running system. The syntax of range is
840 start-[end] where start and end are both
841 a memory unit (amount[KMG]). See also
842 Documentation/admin-guide/kdump/kdump.rst for an example.
844 crashkernel=size[KMG],high
845 [KNL, X86-64, ARM64] range could be above 4G. Allow kernel
846 to allocate physical memory region from top, so could
847 be above 4G if system have more than 4G ram installed.
848 Otherwise memory region will be allocated below 4G, if
850 It will be ignored if crashkernel=X is specified.
851 crashkernel=size[KMG],low
852 [KNL, X86-64] range under 4G. When crashkernel=X,high
853 is passed, kernel could allocate physical memory region
854 above 4G, that cause second kernel crash on system
855 that require some amount of low memory, e.g. swiotlb
856 requires at least 64M+32K low memory, also enough extra
857 low memory is needed to make sure DMA buffers for 32-bit
858 devices won't run out. Kernel would try to allocate
859 at least 256M below 4G automatically.
860 This one lets the user specify own low range under 4G
861 for second kernel instead.
862 0: to disable low allocation.
863 It will be ignored when crashkernel=X,high is not used
864 or memory reserved is below 4G.
866 [KNL, ARM64] range in low memory.
867 This one lets the user specify a low range in the
868 DMA zone for the crash dump kernel.
869 It will be ignored when crashkernel=X,high is not used
870 or memory reserved is located in the DMA zones.
873 [KNL] Disable crypto self-tests
878 cs89x0_media= [HW,NET]
879 Format: { rj45 | aui | bnc }
881 csdlock_debug= [KNL] Enable debug add-ons of cross-CPU function call
882 handling. When switched on, additional debug data is
883 printed to the console in case a hanging CPU is
884 detected, and that CPU is pinged again in order to try
885 to resolve the hang situation.
886 0: disable csdlock debugging (default)
887 1: enable basic csdlock debugging (minor impact)
888 ext: enable extended csdlock debugging (more impact,
892 See header of drivers/s390/block/dasd_devmap.c.
894 db9.dev[2|3]= [HW,JOY] Multisystem joystick support via parallel port
895 (one device per port)
896 Format: <port#>,<type>
897 See also Documentation/input/devices/joystick-parport.rst
899 debug [KNL] Enable kernel debugging (events log level).
902 [KNL] Enable printing [hashed] pointers early in the
903 boot sequence. If enabled, we use a weak hash instead
904 of siphash to hash pointers. Use this option if you are
905 seeing instances of '(___ptrval___)') and need to see a
906 value (hashed pointer) instead. Cryptographically
907 insecure, please do not use on production kernels.
910 [KNL] verbose locking self-tests
912 Print debugging info while doing the locking API
914 Bitmask for the various LOCKTYPE_ tests. Defaults to 0
915 (no extra messages), setting it to -1 (all bits set)
916 will print _a_lot_ more information - normally only
917 useful to lockdep developers.
919 debug_objects [KNL] Enable object debugging
922 [KNL] Disable object debugging
924 debug_guardpage_minorder=
925 [KNL] When CONFIG_DEBUG_PAGEALLOC is set, this
926 parameter allows control of the order of pages that will
927 be intentionally kept free (and hence protected) by the
928 buddy allocator. Bigger value increase the probability
929 of catching random memory corruption, but reduce the
930 amount of memory for normal system use. The maximum
931 possible value is MAX_ORDER/2. Setting this parameter
932 to 1 or 2 should be enough to identify most random
933 memory corruption problems caused by bugs in kernel or
934 driver code when a CPU writes to (or reads from) a
935 random memory location. Note that there exists a class
936 of memory corruptions problems caused by buggy H/W or
937 F/W or by drivers badly programing DMA (basically when
938 memory is written at bus level and the CPU MMU is
939 bypassed) which are not detectable by
940 CONFIG_DEBUG_PAGEALLOC, hence this option will not help
941 tracking down these problems.
944 [KNL] When CONFIG_DEBUG_PAGEALLOC is set, this parameter
945 enables the feature at boot time. By default, it is
946 disabled and the system will work mostly the same as a
947 kernel built without CONFIG_DEBUG_PAGEALLOC.
948 Note: to get most of debug_pagealloc error reports, it's
949 useful to also enable the page_owner functionality.
950 on: enable the feature
952 debugfs= [KNL] This parameter enables what is exposed to userspace
953 and debugfs internal clients.
954 Format: { on, no-mount, off }
955 on: All functions are enabled.
957 Filesystem is not registered but kernel clients can
958 access APIs and a crashkernel can be used to read
959 its content. There is nothing to mount.
960 off: Filesystem is not registered and clients
961 get a -EPERM as result when trying to register files
962 or directories within debugfs.
963 This is equivalent of the runtime functionality if
964 debugfs was not enabled in the kernel at all.
965 Default value is set in build-time with a kernel configuration.
967 debugpat [X86] Enable PAT debugging
969 decnet.addr= [HW,NET]
970 Format: <area>[,<node>]
971 See also Documentation/networking/decnet.rst.
974 [HW] The size of the default HugeTLB page. This is
975 the size represented by the legacy /proc/ hugepages
976 APIs. In addition, this is the default hugetlb size
977 used for shmget(), mmap() and mounting hugetlbfs
978 filesystems. If not specified, defaults to the
979 architecture's default huge page size. Huge page
980 sizes are architecture dependent. See also
981 Documentation/admin-guide/mm/hugetlbpage.rst.
984 deferred_probe_timeout=
985 [KNL] Debugging option to set a timeout in seconds for
986 deferred probe to give up waiting on dependencies to
987 probe. Only specific dependencies (subsystems or
988 drivers) that have opted in will be ignored. A timeout
989 of 0 will timeout at the end of initcalls. If the time
990 out hasn't expired, it'll be restarted by each
991 successful driver registration. This option will also
992 dump out devices still on the deferred probe list after
995 delayacct [KNL] Enable per-task delay accounting
997 dell_smm_hwmon.ignore_dmi=
998 [HW] Continue probing hardware even if DMI data
999 indicates that the driver is running on unsupported
1002 dell_smm_hwmon.force=
1003 [HW] Activate driver even if SMM BIOS signature does
1004 not match list of supported models and enable otherwise
1005 blacklisted features.
1007 dell_smm_hwmon.power_status=
1008 [HW] Report power status in /proc/i8k
1009 (disabled by default).
1011 dell_smm_hwmon.restricted=
1012 [HW] Allow controlling fans only if SYS_ADMIN
1015 dell_smm_hwmon.fan_mult=
1016 [HW] Factor to multiply fan speed with.
1018 dell_smm_hwmon.fan_max=
1019 [HW] Maximum configurable fan speed.
1022 Format: { on | off | def_only | inf_only | always }
1023 on: s390 zlib hardware support for compression on
1024 level 1 and decompression (default)
1025 off: No s390 zlib hardware support
1026 def_only: s390 zlib hardware support for deflate
1027 only (compression on level 1)
1028 inf_only: s390 zlib hardware support for inflate
1029 only (decompression)
1030 always: Same as 'on' but ignores the selected compression
1031 level always using hardware support (used for debugging)
1033 dhash_entries= [KNL]
1034 Set number of hash buckets for dentry cache.
1036 disable_1tb_segments [PPC]
1037 Disables the use of 1TB hash page table segments. This
1038 causes the kernel to fall back to 256MB segments which
1039 can be useful when debugging issues that require an SLB
1043 Limits the number of kernel SLB entries, and flushes
1044 them frequently to increase the rate of SLB faults
1045 on kernel addresses.
1048 See Documentation/networking/ipv6.rst.
1051 Disable RADIX MMU mode on POWER9
1053 radix_hcall_invalidate=on [PPC/PSERIES]
1054 Disable RADIX GTSE feature and use hcall for TLB
1058 Disable TLBIE instruction. Currently does not work
1059 with KVM, with HASH MMU, or with coherent accelerators.
1061 disable_cpu_apicid= [X86,APIC,SMP]
1063 The number of initial APIC ID for the
1064 corresponding CPU to be disabled at boot,
1065 mostly used for the kdump 2nd kernel to
1066 disable BSP to wake up multiple CPUs without
1067 causing system reset or hang due to sending
1068 INIT from AP to BSP.
1070 disable_ddw [PPC/PSERIES]
1071 Disable Dynamic DMA Window support. Use this
1072 to workaround buggy firmware.
1074 disable_ipv6= [IPV6]
1075 See Documentation/networking/ipv6.rst.
1077 disable_mtrr_cleanup [X86]
1078 The kernel tries to adjust MTRR layout from continuous
1079 to discrete, to make X server driver able to add WB
1080 entry later. This parameter disables that.
1082 disable_mtrr_trim [X86, Intel and AMD only]
1083 By default the kernel will trim any uncacheable
1084 memory out of your available memory pool based on
1085 MTRR settings. This parameter disables that behavior,
1086 possibly causing your machine to run very slowly.
1088 disable_timer_pin_1 [X86]
1089 Disable PIN 1 of APIC timer
1090 Can be useful to work around chipset bugs.
1092 dis_ucode_ldr [X86] Disable the microcode loader.
1094 dma_debug=off If the kernel is compiled with DMA_API_DEBUG support,
1095 this option disables the debugging code at boot.
1097 dma_debug_entries=<number>
1098 This option allows to tune the number of preallocated
1099 entries for DMA-API debugging code. One entry is
1100 required per DMA-API allocation. Use this if the
1101 DMA-API debugging code disables itself because the
1102 architectural default is too low.
1104 dma_debug_driver=<driver_name>
1105 With this option the DMA-API debugging driver
1106 filter feature can be enabled at boot time. Just
1107 pass the driver to filter for as the parameter.
1108 The filter can be disabled or changed to another
1109 driver later using sysfs.
1111 driver_async_probe= [KNL]
1112 List of driver names to be probed asynchronously. *
1113 matches with all driver names. If * is specified, the
1114 rest of the listed driver names are those that will NOT
1116 Format: <driver_name1>,<driver_name2>...
1118 drm.edid_firmware=[<connector>:]<file>[,[<connector>:]<file>]
1119 Broken monitors, graphic adapters, KVMs and EDIDless
1120 panels may send no or incorrect EDID data sets.
1121 This parameter allows to specify an EDID data sets
1122 in the /lib/firmware directory that are used instead.
1123 Generic built-in EDID data sets are used, if one of
1124 edid/1024x768.bin, edid/1280x1024.bin,
1125 edid/1680x1050.bin, or edid/1920x1080.bin is given
1126 and no file with the same name exists. Details and
1127 instructions how to build your own EDID data are
1128 available in Documentation/admin-guide/edid.rst. An EDID
1129 data set will only be used for a particular connector,
1130 if its name and a colon are prepended to the EDID
1131 name. Each connector may use a unique EDID data
1132 set by separating the files with a comma. An EDID
1133 data set with no connector name will be used for
1134 any connectors not explicitly specified.
1139 Format: {"off" | "known"}
1140 Control how the dt_cpu_ftrs device-tree binding is
1141 used for CPU feature discovery and setup (if it
1143 off: Do not use it, fall back to legacy cpu table.
1144 known: Do not pass through unknown features to guests
1145 or userspace, only those that the kernel is aware of.
1147 dump_apple_properties [X86]
1148 Dump name and content of EFI device properties on
1149 x86 Macs. Useful for driver authors to determine
1150 what data is available or for reverse-engineering.
1152 dyndbg[="val"] [KNL,DYNAMIC_DEBUG]
1153 <module>.dyndbg[="val"]
1154 Enable debug messages at boot time. See
1155 Documentation/admin-guide/dynamic-debug-howto.rst
1158 nopku [X86] Disable Memory Protection Keys CPU feature found
1161 <module>.async_probe [KNL]
1162 Enable asynchronous probe on this module.
1164 early_ioremap_debug [KNL]
1165 Enable debug messages in early_ioremap support. This
1166 is useful for tracking down temporary early mappings
1167 which are not unmapped.
1169 earlycon= [KNL] Output early console device and options.
1171 When used with no options, the early console is
1172 determined by stdout-path property in device tree's
1173 chosen node or the ACPI SPCR table if supported by
1176 cdns,<addr>[,options]
1177 Start an early, polled-mode console on a Cadence
1178 (xuartps) serial port at the specified address. Only
1179 supported option is baud rate. If baud rate is not
1180 specified, the serial port must already be setup and
1183 uart[8250],io,<addr>[,options]
1184 uart[8250],mmio,<addr>[,options]
1185 uart[8250],mmio32,<addr>[,options]
1186 uart[8250],mmio32be,<addr>[,options]
1187 uart[8250],0x<addr>[,options]
1188 Start an early, polled-mode console on the 8250/16550
1189 UART at the specified I/O port or MMIO address.
1190 MMIO inter-register address stride is either 8-bit
1191 (mmio) or 32-bit (mmio32 or mmio32be).
1192 If none of [io|mmio|mmio32|mmio32be], <addr> is assumed
1193 to be equivalent to 'mmio'. 'options' are specified
1194 in the same format described for "console=ttyS<n>"; if
1195 unspecified, the h/w is not initialized.
1199 Start an early, polled-mode console on a pl011 serial
1200 port at the specified address. The pl011 serial port
1201 must already be setup and configured. Options are not
1202 yet supported. If 'mmio32' is specified, then only
1203 the driver will use only 32-bit accessors to read/write
1204 the device registers.
1207 Start an early console on a litex serial port at the
1208 specified address. The serial port must already be
1209 setup and configured. Options are not yet supported.
1212 Start an early, polled-mode console on a meson serial
1213 port at the specified address. The serial port must
1214 already be setup and configured. Options are not yet
1218 Start an early, polled-mode console on an msm serial
1219 port at the specified address. The serial port
1220 must already be setup and configured. Options are not
1223 msm_serial_dm,<addr>
1224 Start an early, polled-mode console on an msm serial
1225 dm port at the specified address. The serial port
1226 must already be setup and configured. Options are not
1230 Start an early, polled-mode console on a serial port
1231 of an Actions Semi SoC, such as S500 or S900, at the
1232 specified address. The serial port must already be
1233 setup and configured. Options are not yet supported.
1236 Start an early, polled-mode console on a serial port
1237 of an RDA Micro SoC, such as RDA8810PL, at the
1238 specified address. The serial port must already be
1239 setup and configured. Options are not yet supported.
1242 Use RISC-V SBI (Supervisor Binary Interface) for early
1245 smh Use ARM semihosting calls for early console.
1253 Use early console provided by serial driver available
1254 on Samsung SoCs, requires selecting proper type and
1255 a correct base address of the selected UART port. The
1256 serial port must already be setup and configured.
1257 Options are not yet supported.
1260 Start an early, polled-mode console on a lantiq serial
1261 (lqasc) port at the specified address. The serial port
1262 must already be setup and configured. Options are not
1267 Use early console provided by Freescale LP UART driver
1268 found on Freescale Vybrid and QorIQ LS1021A processors.
1269 A valid base address must be provided, and the serial
1270 port must already be setup and configured.
1274 Start an early, polled-mode, output-only console on the
1275 Freescale i.MX UART at the specified address. The UART
1276 must already be setup and configured.
1279 Start an early, polled-mode console on the
1280 Armada 3700 serial port at the specified
1281 address. The serial port must already be setup
1282 and configured. Options are not yet supported.
1285 Start an early, polled-mode console on a Qualcomm
1286 Generic Interface (GENI) based serial port at the
1287 specified address. The serial port must already be
1288 setup and configured. Options are not yet supported.
1291 Start an early, unaccelerated console on the EFI
1292 memory mapped framebuffer (if available). On cache
1293 coherent non-x86 systems that use system memory for
1294 the framebuffer, pass the 'ram' option so that it is
1295 mapped with the correct attributes.
1298 Use early console provided by Freescale LINFlexD UART
1299 serial driver for NXP S32V234 SoCs. A valid base
1300 address must be provided, and the serial port must
1301 already be setup and configured.
1303 earlyprintk= [X86,SH,ARM,M68k,S390]
1307 earlyprintk=serial[,ttySn[,baudrate]]
1308 earlyprintk=serial[,0x...[,baudrate]]
1309 earlyprintk=ttySn[,baudrate]
1310 earlyprintk=dbgp[debugController#]
1311 earlyprintk=pciserial[,force],bus:device.function[,baudrate]
1312 earlyprintk=xdbc[xhciController#]
1314 earlyprintk is useful when the kernel crashes before
1315 the normal console is initialized. It is not enabled by
1316 default because it has some cosmetic problems.
1318 Append ",keep" to not disable it when the real console
1321 Only one of vga, serial, or usb debug port can
1324 Currently only ttyS0 and ttyS1 may be specified by
1325 name. Other I/O ports may be explicitly specified
1326 on some architectures (x86 and arm at least) by
1327 replacing ttySn with an I/O port address, like this:
1328 earlyprintk=serial,0x1008,115200
1329 You can find the port for a given device in
1330 /proc/tty/driver/serial:
1331 2: uart:ST16650V2 port:00001008 irq:18 ...
1333 Interaction with the standard serial driver is not
1336 The VGA output is eventually overwritten by
1339 The xen option can only be used in Xen domains.
1341 The sclp output can only be used on s390.
1343 The optional "force" to "pciserial" enables use of a
1344 PCI device even when its classcode is not of the
1347 edac_report= [HW,EDAC] Control how to report EDAC event
1348 Format: {"on" | "off" | "force"}
1349 on: enable EDAC to report H/W event. May be overridden
1350 by other higher priority error reporting module.
1351 off: disable H/W event reporting through EDAC.
1352 force: enforce the use of EDAC to report H/W event.
1356 Format: {"off" | "on" | "skip[mbr]"}
1359 Format: { "debug", "disable_early_pci_dma",
1360 "nochunk", "noruntime", "nosoftreserve",
1361 "novamap", "no_disable_early_pci_dma" }
1362 debug: enable misc debug output.
1363 disable_early_pci_dma: disable the busmaster bit on all
1364 PCI bridges while in the EFI boot stub.
1365 nochunk: disable reading files in "chunks" in the EFI
1366 boot stub, as chunking can cause problems with some
1367 firmware implementations.
1368 noruntime : disable EFI runtime services support
1369 nosoftreserve: The EFI_MEMORY_SP (Specific Purpose)
1370 attribute may cause the kernel to reserve the
1371 memory range for a memory mapping driver to
1372 claim. Specify efi=nosoftreserve to disable this
1373 reservation and treat the memory by its base type
1374 (i.e. EFI_CONVENTIONAL_MEMORY / "System RAM").
1375 novamap: do not call SetVirtualAddressMap().
1376 no_disable_early_pci_dma: Leave the busmaster bit set
1377 on all PCI bridges while in the EFI boot stub
1379 efi_no_storage_paranoia [EFI; X86]
1380 Using this parameter you can use more than 50% of
1381 your efi variable storage. Use this parameter only if
1382 you are really sure that your UEFI does sane gc and
1383 fulfills the spec otherwise your board may brick.
1385 efi_fake_mem= nn[KMG]@ss[KMG]:aa[,nn[KMG]@ss[KMG]:aa,..] [EFI; X86]
1386 Add arbitrary attribute to specific memory range by
1387 updating original EFI memory map.
1388 Region of memory which aa attribute is added to is
1391 If efi_fake_mem=2G@4G:0x10000,2G@0x10a0000000:0x10000
1392 is specified, EFI_MEMORY_MORE_RELIABLE(0x10000)
1393 attribute is added to range 0x100000000-0x180000000 and
1394 0x10a0000000-0x1120000000.
1396 If efi_fake_mem=8G@9G:0x40000 is specified, the
1397 EFI_MEMORY_SP(0x40000) attribute is added to
1398 range 0x240000000-0x43fffffff.
1400 Using this parameter you can do debugging of EFI memmap
1401 related features. For example, you can do debugging of
1402 Address Range Mirroring feature even if your box
1403 doesn't support it, or mark specific memory as
1406 efivar_ssdt= [EFI; X86] Name of an EFI variable that contains an SSDT
1407 that is to be dynamically loaded by Linux. If there are
1408 multiple variables with the same name but with different
1409 vendor GUIDs, all of them will be loaded. See
1410 Documentation/admin-guide/acpi/ssdt-overlays.rst for details.
1413 eisa_irq_edge= [PARISC,HW]
1414 See header of drivers/parisc/eisa.c.
1416 ekgdboc= [X86,KGDB] Allow early kernel console debugging
1419 This is designed to be used in conjunction with
1420 the boot argument: earlyprintk=vga
1422 This parameter works in place of the kgdboc parameter
1423 but can only be used if the backing tty is available
1424 very early in the boot process. For early debugging
1425 via a serial port see kgdboc_earlycon instead.
1428 See comment before function elanfreq_setup() in
1429 arch/x86/kernel/cpu/cpufreq/elanfreq.c.
1431 elfcorehdr=[size[KMG]@]offset[KMG] [IA64,PPC,SH,X86,S390]
1432 Specifies physical address of start of kernel core
1433 image elf header and optionally the size. Generally
1434 kexec loader will pass this option to capture kernel.
1435 See Documentation/admin-guide/kdump/kdump.rst for details.
1437 enable_mtrr_cleanup [X86]
1438 The kernel tries to adjust MTRR layout from continuous
1439 to discrete, to make X server driver able to add WB
1440 entry later. This parameter enables that.
1442 enable_timer_pin_1 [X86]
1443 Enable PIN 1 of APIC timer
1444 Can be useful to work around chipset bugs
1445 (in particular on some ATI chipsets).
1446 The kernel tries to set a reasonable default.
1448 enforcing= [SELINUX] Set initial enforcing status.
1450 See security/selinux/Kconfig help text.
1451 0 -- permissive (log only, no denials).
1452 1 -- enforcing (deny and log).
1454 Value can be changed at runtime via
1455 /sys/fs/selinux/enforce.
1458 Disable Error Record Serialization Table (ERST)
1461 ether= [HW,NET] Ethernet cards parameters
1462 This option is obsoleted by the "netdev=" option, which
1463 has equivalent usage. See its documentation for details.
1467 Permit 'security.evm' to be updated regardless of
1468 current integrity status.
1473 fail_make_request=[KNL]
1474 General fault injection mechanism.
1475 Format: <interval>,<probability>,<space>,<times>
1476 See also Documentation/fault-injection/.
1479 Format: { initns | none }
1480 See Documentation/admin-guide/sysctl/net.rst for
1481 fb_tunnels_only_for_init_ns
1484 See Documentation/admin-guide/blockdev/floppy.rst.
1486 force_pal_cache_flush
1487 [IA-64] Avoid check_sal_cache_flush which may hang on
1488 buggy SAL_CACHE_FLUSH implementations. Using this
1489 parameter will force ia64_sal_cache_flush to call
1490 ia64_pal_cache_flush instead of SAL_CACHE_FLUSH.
1493 Forcefully enable Physical Address Extension (PAE).
1494 Many Pentium M systems disable PAE but may have a
1495 functionally usable PAE implementation.
1496 Warning: use of this parameter will taint the kernel
1497 and may cause unknown problems.
1500 [FTRACE] will set and start the specified tracer
1501 as early as possible in order to facilitate early
1504 ftrace_boot_snapshot
1505 [FTRACE] On boot up, a snapshot will be taken of the
1506 ftrace ring buffer that can be read at:
1507 /sys/kernel/tracing/snapshot.
1508 This is useful if you need tracing information from kernel
1509 boot up that is likely to be overridden by user space
1510 start up functionality.
1512 ftrace_dump_on_oops[=orig_cpu]
1513 [FTRACE] will dump the trace buffers on oops.
1514 If no parameter is passed, ftrace will dump
1515 buffers of all CPUs, but if you pass orig_cpu, it will
1516 dump only the buffer of the CPU that triggered the
1519 ftrace_filter=[function-list]
1520 [FTRACE] Limit the functions traced by the function
1521 tracer at boot up. function-list is a comma-separated
1522 list of functions. This list can be changed at run
1523 time by the set_ftrace_filter file in the debugfs
1526 ftrace_notrace=[function-list]
1527 [FTRACE] Do not trace the functions specified in
1528 function-list. This list can be changed at run time
1529 by the set_ftrace_notrace file in the debugfs
1532 ftrace_graph_filter=[function-list]
1533 [FTRACE] Limit the top level callers functions traced
1534 by the function graph tracer at boot up.
1535 function-list is a comma-separated list of functions
1536 that can be changed at run time by the
1537 set_graph_function file in the debugfs tracing directory.
1539 ftrace_graph_notrace=[function-list]
1540 [FTRACE] Do not trace from the functions specified in
1541 function-list. This list is a comma-separated list of
1542 functions that can be changed at run time by the
1543 set_graph_notrace file in the debugfs tracing directory.
1545 ftrace_graph_max_depth=<uint>
1546 [FTRACE] Used with the function graph tracer. This is
1547 the max depth it will trace into a function. This value
1548 can be changed at run time by the max_graph_depth file
1549 in the tracefs tracing directory. default: 0 (no limit)
1551 fw_devlink= [KNL] Create device links between consumer and supplier
1552 devices by scanning the firmware to infer the
1553 consumer/supplier relationships. This feature is
1554 especially useful when drivers are loaded as modules as
1555 it ensures proper ordering of tasks like device probing
1556 (suppliers first, then consumers), supplier boot state
1557 clean up (only after all consumers have probed),
1558 suspend/resume & runtime PM (consumers first, then
1560 Format: { off | permissive | on | rpm }
1561 off -- Don't create device links from firmware info.
1562 permissive -- Create device links from firmware info
1563 but use it only for ordering boot state clean
1564 up (sync_state() calls).
1565 on -- Create device links from firmware info and use it
1566 to enforce probe and suspend/resume ordering.
1567 rpm -- Like "on", but also use to order runtime PM.
1569 fw_devlink.strict=<bool>
1570 [KNL] Treat all inferred dependencies as mandatory
1571 dependencies. This only applies for fw_devlink=on|rpm.
1575 [HW,JOY] Multisystem joystick and NES/SNES/PSX pad
1576 support via parallel port (up to 5 devices per port)
1577 Format: <port#>,<pad1>,<pad2>,<pad3>,<pad4>,<pad5>
1578 See also Documentation/input/devices/joystick-parport.rst
1582 gart_fix_e820= [X86-64] disable the fix e820 for K8 GART
1586 gcov_persist= [GCOV] When non-zero (default), profiling data for
1587 kernel modules is saved and remains accessible via
1588 debugfs, even when the module is unloaded/reloaded.
1589 When zero, profiling data is discarded and associated
1590 debugfs files are removed at module unload time.
1592 goldfish [X86] Enable the goldfish android emulator platform.
1593 Don't use this when you are not running on the
1596 gpio-mockup.gpio_mockup_ranges
1597 [HW] Sets the ranges of gpiochip of for this device.
1598 Format: <start1>,<end1>,<start2>,<end2>...
1599 gpio-mockup.gpio_mockup_named_lines
1600 [HW] Let the driver know GPIO lines should be named.
1602 gpt [EFI] Forces disk with valid GPT signature but
1603 invalid Protective MBR to be treated as GPT. If the
1604 primary GPT is corrupted, it enables the backup/alternate
1605 GPT to be used instead.
1607 grcan.enable0= [HW] Configuration of physical interface 0. Determines
1608 the "Enable 0" bit of the configuration register.
1611 grcan.enable1= [HW] Configuration of physical interface 1. Determines
1612 the "Enable 0" bit of the configuration register.
1615 grcan.select= [HW] Select which physical interface to use.
1618 grcan.txsize= [HW] Sets the size of the tx buffer.
1619 Format: <unsigned int> such that (txsize & ~0x1fffc0) == 0.
1621 grcan.rxsize= [HW] Sets the size of the rx buffer.
1622 Format: <unsigned int> such that (rxsize & ~0x1fffc0) == 0.
1626 [KNL] Under CONFIG_HARDENED_USERCOPY, whether
1627 hardening is enabled for this boot. Hardened
1628 usercopy checking is used to protect the kernel
1629 from reading or writing beyond known memory
1630 allocation boundaries as a proactive defense
1631 against bounds-checking flaws in the kernel's
1632 copy_to_user()/copy_from_user() interface.
1633 on Perform hardened usercopy checks (default).
1634 off Disable hardened usercopy checks.
1636 hardlockup_all_cpu_backtrace=
1637 [KNL] Should the hard-lockup detector generate
1638 backtraces on all cpus.
1641 hashdist= [KNL,NUMA] Large hashes allocated during boot
1642 are distributed across NUMA nodes. Defaults on
1643 for 64-bit NUMA, off otherwise.
1644 Format: 0 | 1 (for off | on)
1646 hcl= [IA-64] SGI's Hardware Graph compatibility layer
1648 hd= [EIDE] (E)IDE hard drive subsystem geometry
1649 Format: <cyl>,<head>,<sect>
1652 Disable Hardware Error Source Table (HEST) support;
1653 corresponding firmware-first mode error processing
1654 logic will be disabled.
1656 hibernate= [HIBERNATION]
1657 noresume Don't check if there's a hibernation image
1658 present during boot.
1659 nocompress Don't compress/decompress hibernation images.
1660 no Disable hibernation and resume.
1661 protect_image Turn on image protection during restoration
1662 (that will set all pages holding image data
1663 during restoration read-only).
1665 highmem=nn[KMG] [KNL,BOOT] forces the highmem zone to have an exact
1666 size of <nn>. This works even on boxes that have no
1667 highmem otherwise. This also works to reduce highmem
1668 size on bigger boxes.
1670 highres= [KNL] Enable/disable high resolution timer mode.
1671 Valid parameters: "on", "off"
1676 hpet= [X86-32,HPET] option to control HPET usage
1677 Format: { enable (default) | disable | force |
1679 disable: disable HPET and use PIT instead
1680 force: allow force enabled of undocumented chips (ICH4,
1682 verbose: show contents of HPET registers during setup
1684 hpet_mmap= [X86, HPET_MMAP] Allow userspace to mmap HPET
1685 registers. Default set by CONFIG_HPET_MMAP_DEFAULT.
1687 hugepages= [HW] Number of HugeTLB pages to allocate at boot.
1688 If this follows hugepagesz (below), it specifies
1689 the number of pages of hugepagesz to be allocated.
1690 If this is the first HugeTLB parameter on the command
1691 line, it specifies the number of pages to allocate for
1692 the default huge page size. If using node format, the
1693 number of pages to allocate per-node can be specified.
1694 See also Documentation/admin-guide/mm/hugetlbpage.rst.
1695 Format: <integer> or (node format)
1696 <node>:<integer>[,<node>:<integer>]
1699 [HW] The size of the HugeTLB pages. This is used in
1700 conjunction with hugepages (above) to allocate huge
1701 pages of a specific size at boot. The pair
1702 hugepagesz=X hugepages=Y can be specified once for
1703 each supported huge page size. Huge page sizes are
1704 architecture dependent. See also
1705 Documentation/admin-guide/mm/hugetlbpage.rst.
1708 hugetlb_cma= [HW,CMA] The size of a CMA area used for allocation
1709 of gigantic hugepages. Or using node format, the size
1710 of a CMA area per node can be specified.
1711 Format: nn[KMGTPE] or (node format)
1712 <node>:nn[KMGTPE][,<node>:nn[KMGTPE]]
1714 Reserve a CMA area of given size and allocate gigantic
1715 hugepages using the CMA allocator. If enabled, the
1716 boot-time allocation of gigantic hugepages is skipped.
1718 hugetlb_free_vmemmap=
1719 [KNL] Reguires CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP
1721 Allows heavy hugetlb users to free up some more
1722 memory (7 * PAGE_SIZE for each 2MB hugetlb page).
1723 Format: { [oO][Nn]/Y/y/1 | [oO][Ff]/N/n/0 (default) }
1725 [oO][Nn]/Y/y/1: enable the feature
1726 [oO][Ff]/N/n/0: disable the feature
1728 Built with CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP_DEFAULT_ON=y,
1731 This is not compatible with memory_hotplug.memmap_on_memory.
1732 If both parameters are enabled, hugetlb_free_vmemmap takes
1733 precedence over memory_hotplug.memmap_on_memory.
1736 [KNL] Should the hung task detector generate panics.
1739 A value of 1 instructs the kernel to panic when a
1740 hung task is detected. The default value is controlled
1741 by the CONFIG_BOOTPARAM_HUNG_TASK_PANIC build-time
1742 option. The value selected by this boot parameter can
1743 be changed later by the kernel.hung_task_panic sysctl.
1745 hvc_iucv= [S390] Number of z/VM IUCV hypervisor console (HVC)
1746 terminal devices. Valid values: 0..8
1747 hvc_iucv_allow= [S390] Comma-separated list of z/VM user IDs.
1748 If specified, z/VM IUCV HVC accepts connections
1749 from listed z/VM user IDs only.
1751 hv_nopvspin [X86,HYPER_V] Disables the paravirt spinlock optimizations
1752 which allow the hypervisor to 'idle' the
1753 guest on lock contention.
1756 Do not unregister boot console at start. This is only
1757 useful for debugging when something happens in the window
1758 between unregistering the boot console and initializing
1761 i2c_bus= [HW] Override the default board specific I2C bus speed
1762 or register an additional I2C bus that is not
1763 registered from board initialization code.
1767 i8042.debug [HW] Toggle i8042 debug mode
1768 i8042.unmask_kbd_data
1769 [HW] Enable printing of interrupt data from the KBD port
1770 (disabled by default, and as a pre-condition
1771 requires that i8042.debug=1 be enabled)
1772 i8042.direct [HW] Put keyboard port into non-translated mode
1773 i8042.dumbkbd [HW] Pretend that controller can only read data from
1774 keyboard and cannot control its state
1775 (Don't attempt to blink the leds)
1776 i8042.noaux [HW] Don't check for auxiliary (== mouse) port
1777 i8042.nokbd [HW] Don't check/create keyboard port
1778 i8042.noloop [HW] Disable the AUX Loopback command while probing
1780 i8042.nomux [HW] Don't check presence of an active multiplexing
1782 i8042.nopnp [HW] Don't use ACPIPnP / PnPBIOS to discover KBD/AUX
1784 i8042.notimeout [HW] Ignore timeout condition signalled by controller
1785 i8042.reset [HW] Reset the controller during init, cleanup and
1786 suspend-to-ram transitions, only during s2r
1787 transitions, or never reset
1788 Format: { 1 | Y | y | 0 | N | n }
1789 1, Y, y: always reset controller
1790 0, N, n: don't ever reset controller
1791 Default: only on s2r transitions on x86; most other
1792 architectures force reset to be always executed
1793 i8042.unlock [HW] Unlock (ignore) the keylock
1794 i8042.kbdreset [HW] Reset device connected to KBD port
1796 [HW] Allow deferred probing upon i8042 probe errors
1800 i915.invert_brightness=
1801 [DRM] Invert the sense of the variable that is used to
1802 set the brightness of the panel backlight. Normally a
1803 brightness value of 0 indicates backlight switched off,
1804 and the maximum of the brightness value sets the backlight
1805 to maximum brightness. If this parameter is set to 0
1806 (default) and the machine requires it, or this parameter
1807 is set to 1, a brightness value of 0 sets the backlight
1808 to maximum brightness, and the maximum of the brightness
1809 value switches the backlight off.
1810 -1 -- never invert brightness
1811 0 -- machine default
1812 1 -- force brightness inversion
1815 Format: <io>[,<membase>[,<icn_id>[,<icn_id2>]]]
1819 Format: idle=poll, idle=halt, idle=nomwait
1820 Poll forces a polling idle loop that can slightly
1821 improve the performance of waking up a idle CPU, but
1822 will use a lot of power and make the system run hot.
1824 idle=halt: Halt is forced to be used for CPU idle.
1825 In such case C2/C3 won't be used again.
1826 idle=nomwait: Disable mwait for CPU C-states
1830 Allow force disabling of Shared Virtual Memory (SVA)
1831 support for the idxd driver. By default it is set to
1834 idxd.tc_override= [HW]
1836 Allow override of default traffic class configuration
1837 for the device. By default it is set to false (0).
1839 ieee754= [MIPS] Select IEEE Std 754 conformance mode
1840 Format: { strict | legacy | 2008 | relaxed }
1843 Choose which programs will be accepted for execution
1844 based on the IEEE 754 NaN encoding(s) supported by
1845 the FPU and the NaN encoding requested with the value
1846 of an ELF file header flag individually set by each
1847 binary. Hardware implementations are permitted to
1848 support either or both of the legacy and the 2008 NaN
1851 Available settings are as follows:
1852 strict accept binaries that request a NaN encoding
1853 supported by the FPU
1854 legacy only accept legacy-NaN binaries, if supported
1856 2008 only accept 2008-NaN binaries, if supported
1858 relaxed accept any binaries regardless of whether
1859 supported by the FPU
1861 The FPU emulator is always able to support both NaN
1862 encodings, so if no FPU hardware is present or it has
1863 been disabled with 'nofpu', then the settings of
1864 'legacy' and '2008' strap the emulator accordingly,
1865 'relaxed' straps the emulator for both legacy-NaN and
1866 2008-NaN, whereas 'strict' enables legacy-NaN only on
1867 legacy processors and both NaN encodings on MIPS32 or
1870 The setting for ABS.fmt/NEG.fmt instruction execution
1871 mode generally follows that for the NaN encoding,
1872 except where unsupported by hardware.
1874 ignore_loglevel [KNL]
1875 Ignore loglevel setting - this will print /all/
1876 kernel messages to the console. Useful for debugging.
1877 We also add it as printk module parameter, so users
1878 could change it dynamically, usually by
1879 /sys/module/printk/parameters/ignore_loglevel.
1882 Ignore RLIMIT_DATA setting for data mappings,
1883 print warning at first misuse. Can be changed via
1884 /sys/module/kernel/parameters/ignore_rlimit_data.
1886 ihash_entries= [KNL]
1887 Set number of hash buckets for inode cache.
1889 ima_appraise= [IMA] appraise integrity measurements
1890 Format: { "off" | "enforce" | "fix" | "log" }
1893 ima_appraise_tcb [IMA] Deprecated. Use ima_policy= instead.
1894 The builtin appraise policy appraises all files
1897 ima_canonical_fmt [IMA]
1898 Use the canonical format for the binary runtime
1899 measurements, instead of host native format.
1902 Format: { md5 | sha1 | rmd160 | sha256 | sha384
1906 The list of supported hash algorithms is defined
1907 in crypto/hash_info.h.
1910 The builtin policies to load during IMA setup.
1911 Format: "tcb | appraise_tcb | secure_boot |
1912 fail_securely | critical_data"
1914 The "tcb" policy measures all programs exec'd, files
1915 mmap'd for exec, and all files opened with the read
1916 mode bit set by either the effective uid (euid=0) or
1919 The "appraise_tcb" policy appraises the integrity of
1920 all files owned by root.
1922 The "secure_boot" policy appraises the integrity
1923 of files (eg. kexec kernel image, kernel modules,
1924 firmware, policy, etc) based on file signatures.
1926 The "fail_securely" policy forces file signature
1927 verification failure also on privileged mounted
1928 filesystems with the SB_I_UNVERIFIABLE_SIGNATURE
1931 The "critical_data" policy measures kernel integrity
1934 ima_tcb [IMA] Deprecated. Use ima_policy= instead.
1935 Load a policy which meets the needs of the Trusted
1936 Computing Base. This means IMA will measure all
1937 programs exec'd, files mmap'd for exec, and all files
1938 opened for read by uid=0.
1941 Select one of defined IMA measurements template formats.
1942 Formats: { "ima" | "ima-ng" | "ima-ngv2" | "ima-sig" |
1947 [IMA] Define a custom template format.
1948 Format: { "field1|...|fieldN" }
1950 ima.ahash_minsize= [IMA] Minimum file size for asynchronous hash usage
1951 Format: <min_file_size>
1952 Set the minimal file size for using asynchronous hash.
1953 If left unspecified, ahash usage is disabled.
1955 ahash performance varies for different data sizes on
1956 different crypto accelerators. This option can be used
1957 to achieve the best performance for a particular HW.
1959 ima.ahash_bufsize= [IMA] Asynchronous hash buffer size
1961 Set hashing buffer size. Default: 4k.
1963 ahash performance varies for different chunk sizes on
1964 different crypto accelerators. This option can be used
1965 to achieve best performance for particular HW.
1969 Run specified binary instead of /sbin/init as init
1972 initcall_debug [KNL] Trace initcalls as they are executed. Useful
1973 for working out where the kernel is dying during
1976 initcall_blacklist= [KNL] Do not execute a comma-separated list of
1977 initcall functions. Useful for debugging built-in
1978 modules and initcalls.
1980 initramfs_async= [KNL]
1983 This parameter controls whether the initramfs
1984 image is unpacked asynchronously, concurrently
1985 with devices being probed and
1986 initialized. This should normally just work,
1987 but as a debugging aid, one can get the
1988 historical behaviour of the initramfs
1989 unpacking being completed before device_ and
1992 initrd= [BOOT] Specify the location of the initial ramdisk
1994 initrdmem= [KNL] Specify a physical address and size from which to
1995 load the initrd. If an initrd is compiled in or
1996 specified in the bootparams, it takes priority over this
1998 Format: ss[KMG],nn[KMG]
2001 init_on_alloc= [MM] Fill newly allocated pages and heap objects with
2004 Default set by CONFIG_INIT_ON_ALLOC_DEFAULT_ON.
2006 init_on_free= [MM] Fill freed pages and heap objects with zeroes.
2008 Default set by CONFIG_INIT_ON_FREE_DEFAULT_ON.
2010 init_pkru= [X86] Specify the default memory protection keys rights
2011 register contents for all processes. 0x55555554 by
2012 default (disallow access to all but pkey 0). Can
2013 override in debugfs after boot.
2015 inport.irq= [HW] Inport (ATI XL and Microsoft) busmouse driver
2018 int_pln_enable [X86] Enable power limit notification interrupt
2020 integrity_audit=[IMA]
2021 Format: { "0" | "1" }
2022 0 -- basic integrity auditing messages. (Default)
2023 1 -- additional integrity auditing messages.
2025 intel_iommu= [DMAR] Intel IOMMU driver (DMAR) option
2027 Enable intel iommu driver.
2029 Disable intel iommu driver.
2030 igfx_off [Default Off]
2031 By default, gfx is mapped as normal device. If a gfx
2032 device has a dedicated DMAR unit, the DMAR unit is
2033 bypassed by not enabling DMAR with this option. In
2034 this case, gfx device will use physical address for
2036 strict [Default Off]
2037 Deprecated, equivalent to iommu.strict=1.
2038 sp_off [Default Off]
2039 By default, super page will be supported if Intel IOMMU
2040 has the capability. With this option, super page will
2043 Enable the Intel IOMMU scalable mode if the hardware
2044 advertises that it has support for the scalable mode
2047 Disallow use of the Intel IOMMU scalable mode.
2048 tboot_noforce [Default Off]
2049 Do not force the Intel IOMMU enabled under tboot.
2050 By default, tboot will force Intel IOMMU on, which
2051 could harm performance of some high-throughput
2052 devices like 40GBit network cards, even if identity
2054 Note that using this option lowers the security
2055 provided by tboot because it makes the system
2056 vulnerable to DMA attacks.
2058 intel_idle.max_cstate= [KNL,HW,ACPI,X86]
2059 0 disables intel_idle and fall back on acpi_idle.
2060 1 to 9 specify maximum depth of C-state.
2064 Do not enable intel_pstate as the default
2065 scaling driver for the supported processors
2067 Use intel_pstate as a scaling driver, but configure it
2068 to work with generic cpufreq governors (instead of
2069 enabling its internal governor). This mode cannot be
2070 used along with the hardware-managed P-states (HWP)
2073 Enable intel_pstate on systems that prohibit it by default
2074 in favor of acpi-cpufreq. Forcing the intel_pstate driver
2075 instead of acpi-cpufreq may disable platform features, such
2076 as thermal controls and power capping, that rely on ACPI
2077 P-States information being indicated to OSPM and therefore
2078 should be used with caution. This option does not work with
2079 processors that aren't supported by the intel_pstate driver
2080 or on platforms that use pcc-cpufreq instead of acpi-cpufreq.
2082 Do not enable hardware P state control (HWP)
2085 Only load intel_pstate on systems which support
2086 hardware P state control (HWP) if available.
2088 Enforce ACPI _PPC performance limits. If the Fixed ACPI
2089 Description Table, specifies preferred power management
2090 profile as "Enterprise Server" or "Performance Server",
2091 then this feature is turned on by default.
2093 Allow per-logical-CPU P-State performance control limits using
2094 cpufreq sysfs interface
2096 intremap= [X86-64, Intel-IOMMU]
2097 on enable Interrupt Remapping (default)
2098 off disable Interrupt Remapping
2099 nosid disable Source ID checking
2101 BIOS x2APIC opt-out request will be ignored
2102 nopost disable Interrupt Posting
2104 iomem= Disable strict checking of access to MMIO memory
2105 strict regions from userspace.
2120 nobypass [PPC/POWERNV]
2121 Disable IOMMU bypass, using IOMMU for PCI devices.
2123 iommu.forcedac= [ARM64, X86] Control IOVA allocation for PCI devices.
2124 Format: { "0" | "1" }
2125 0 - Try to allocate a 32-bit DMA address first, before
2126 falling back to the full range if needed.
2127 1 - Allocate directly from the full usable range,
2128 forcing Dual Address Cycle for PCI cards supporting
2129 greater than 32-bit addressing.
2131 iommu.strict= [ARM64, X86] Configure TLB invalidation behaviour
2132 Format: { "0" | "1" }
2134 Request that DMA unmap operations use deferred
2135 invalidation of hardware TLBs, for increased
2136 throughput at the cost of reduced device isolation.
2137 Will fall back to strict mode if not supported by
2138 the relevant IOMMU driver.
2140 DMA unmap operations invalidate IOMMU hardware TLBs
2142 unset - Use value of CONFIG_IOMMU_DEFAULT_DMA_{LAZY,STRICT}.
2143 Note: on x86, strict mode specified via one of the
2144 legacy driver-specific options takes precedence.
2147 [ARM64, X86] Configure DMA to bypass the IOMMU by default.
2148 Format: { "0" | "1" }
2149 0 - Use IOMMU translation for DMA.
2150 1 - Bypass the IOMMU for DMA.
2151 unset - Use value of CONFIG_IOMMU_DEFAULT_PASSTHROUGH.
2153 io7= [HW] IO7 for Marvel-based Alpha systems
2154 See comment before marvel_specify_io7 in
2155 arch/alpha/kernel/core_marvel.c.
2157 io_delay= [X86] I/O delay method
2159 Standard port 0x80 based delay
2161 Alternate port 0xed based delay (needed on some systems)
2163 Simple two microseconds delay
2168 See Documentation/admin-guide/nfs/nfsroot.rst.
2170 ipcmni_extend [KNL] Extend the maximum number of unique System V
2171 IPC identifiers from 32,768 to 16,777,216.
2173 irqaffinity= [SMP] Set the default irq affinity mask
2174 The argument is a cpu list, as described above.
2176 irqchip.gicv2_force_probe=
2179 Force the kernel to look for the second 4kB page
2180 of a GICv2 controller even if the memory range
2181 exposed by the device tree is too small.
2183 irqchip.gicv3_nolpi=
2185 Force the kernel to ignore the availability of
2186 LPIs (and by consequence ITSs). Intended for system
2187 that use the kernel as a bootloader, and thus want
2188 to let secondary kernels in charge of setting up
2191 irqchip.gicv3_pseudo_nmi= [ARM64]
2192 Enables support for pseudo-NMIs in the kernel. This
2193 requires the kernel to be built with
2194 CONFIG_ARM64_PSEUDO_NMI.
2197 When an interrupt is not handled search all handlers
2198 for it. Intended to get systems with badly broken
2202 When an interrupt is not handled search all handlers
2203 for it. Also check all handlers each timer
2204 interrupt. Intended to get systems with badly broken
2208 Format: <RDP>,<reset>,<pci_scan>,<verbosity>
2210 isolcpus= [KNL,SMP,ISOL] Isolate a given set of CPUs from disturbance.
2211 [Deprecated - use cpusets instead]
2212 Format: [flag-list,]<cpu-list>
2214 Specify one or more CPUs to isolate from disturbances
2215 specified in the flag list (default: domain):
2218 Disable the tick when a single task runs.
2220 A residual 1Hz tick is offloaded to workqueues, which you
2221 need to affine to housekeeping through the global
2222 workqueue's affinity configured via the
2223 /sys/devices/virtual/workqueue/cpumask sysfs file, or
2224 by using the 'domain' flag described below.
2226 NOTE: by default the global workqueue runs on all CPUs,
2227 so to protect individual CPUs the 'cpumask' file has to
2228 be configured manually after bootup.
2231 Isolate from the general SMP balancing and scheduling
2232 algorithms. Note that performing domain isolation this way
2233 is irreversible: it's not possible to bring back a CPU to
2234 the domains once isolated through isolcpus. It's strongly
2235 advised to use cpusets instead to disable scheduler load
2236 balancing through the "cpuset.sched_load_balance" file.
2237 It offers a much more flexible interface where CPUs can
2238 move in and out of an isolated set anytime.
2240 You can move a process onto or off an "isolated" CPU via
2241 the CPU affinity syscalls or cpuset.
2242 <cpu number> begins at 0 and the maximum value is
2243 "number of CPUs in system - 1".
2247 Isolate from being targeted by managed interrupts
2248 which have an interrupt mask containing isolated
2249 CPUs. The affinity of managed interrupts is
2250 handled by the kernel and cannot be changed via
2251 the /proc/irq/* interfaces.
2253 This isolation is best effort and only effective
2254 if the automatically assigned interrupt mask of a
2255 device queue contains isolated and housekeeping
2256 CPUs. If housekeeping CPUs are online then such
2257 interrupts are directed to the housekeeping CPU
2258 so that IO submitted on the housekeeping CPU
2259 cannot disturb the isolated CPU.
2261 If a queue's affinity mask contains only isolated
2262 CPUs then this parameter has no effect on the
2263 interrupt routing decision, though interrupts are
2264 only delivered when tasks running on those
2265 isolated CPUs submit IO. IO submitted on
2266 housekeeping CPUs has no influence on those
2269 The format of <cpu-list> is described above.
2273 ivrs_ioapic [HW,X86-64]
2274 Provide an override to the IOAPIC-ID<->DEVICE-ID
2275 mapping provided in the IVRS ACPI table. For
2276 example, to map IOAPIC-ID decimal 10 to
2277 PCI device 00:14.0 write the parameter as:
2278 ivrs_ioapic[10]=00:14.0
2280 ivrs_hpet [HW,X86-64]
2281 Provide an override to the HPET-ID<->DEVICE-ID
2282 mapping provided in the IVRS ACPI table. For
2283 example, to map HPET-ID decimal 0 to
2284 PCI device 00:14.0 write the parameter as:
2285 ivrs_hpet[0]=00:14.0
2287 ivrs_acpihid [HW,X86-64]
2288 Provide an override to the ACPI-HID:UID<->DEVICE-ID
2289 mapping provided in the IVRS ACPI table. For
2290 example, to map UART-HID:UID AMD0020:0 to
2291 PCI device 00:14.5 write the parameter as:
2292 ivrs_acpihid[00:14.5]=AMD0020:0
2294 js= [HW,JOY] Analog joystick
2295 See Documentation/input/joydev/joystick.rst.
2298 When CONFIG_RANDOMIZE_BASE is set, this disables
2299 kernel and module base offset ASLR (Address Space
2300 Layout Randomization).
2303 [KNL] Enforce KASAN (Kernel Address Sanitizer) to print
2304 report on every invalid memory access. Without this
2305 parameter KASAN will print report only for the first
2310 kernelcore= [KNL,X86,IA-64,PPC]
2311 Format: nn[KMGTPE] | nn% | "mirror"
2312 This parameter specifies the amount of memory usable by
2313 the kernel for non-movable allocations. The requested
2314 amount is spread evenly throughout all nodes in the
2315 system as ZONE_NORMAL. The remaining memory is used for
2316 movable memory in its own zone, ZONE_MOVABLE. In the
2317 event, a node is too small to have both ZONE_NORMAL and
2318 ZONE_MOVABLE, kernelcore memory will take priority and
2319 other nodes will have a larger ZONE_MOVABLE.
2321 ZONE_MOVABLE is used for the allocation of pages that
2322 may be reclaimed or moved by the page migration
2323 subsystem. Note that allocations like PTEs-from-HighMem
2324 still use the HighMem zone if it exists, and the Normal
2325 zone if it does not.
2327 It is possible to specify the exact amount of memory in
2328 the form of "nn[KMGTPE]", a percentage of total system
2329 memory in the form of "nn%", or "mirror". If "mirror"
2330 option is specified, mirrored (reliable) memory is used
2331 for non-movable allocations and remaining memory is used
2332 for Movable pages. "nn[KMGTPE]", "nn%", and "mirror"
2333 are exclusive, so you cannot specify multiple forms.
2335 kgdbdbgp= [KGDB,HW] kgdb over EHCI usb debug port.
2336 Format: <Controller#>[,poll interval]
2337 The controller # is the number of the ehci usb debug
2338 port as it is probed via PCI. The poll interval is
2339 optional and is the number seconds in between
2340 each poll cycle to the debug port in case you need
2341 the functionality for interrupting the kernel with
2342 gdb or control-c on the dbgp connection. When
2343 not using this parameter you use sysrq-g to break into
2344 the kernel debugger.
2346 kgdboc= [KGDB,HW] kgdb over consoles.
2347 Requires a tty driver that supports console polling,
2348 or a supported polling keyboard driver (non-usb).
2349 Serial only format: <serial_device>[,baud]
2350 keyboard only format: kbd
2351 keyboard and serial format: kbd,<serial_device>[,baud]
2352 Optional Kernel mode setting:
2353 kms, kbd format: kms,kbd
2354 kms, kbd and serial format: kms,kbd,<ser_dev>[,baud]
2356 kgdboc_earlycon= [KGDB,HW]
2357 If the boot console provides the ability to read
2358 characters and can work in polling mode, you can use
2359 this parameter to tell kgdb to use it as a backend
2360 until the normal console is registered. Intended to
2361 be used together with the kgdboc parameter which
2362 specifies the normal console to transition to.
2364 The name of the early console should be specified
2365 as the value of this parameter. Note that the name of
2366 the early console might be different than the tty
2367 name passed to kgdboc. It's OK to leave the value
2368 blank and the first boot console that implements
2369 read() will be picked.
2371 kgdbwait [KGDB] Stop kernel execution and enter the
2372 kernel debugger at the earliest opportunity.
2374 kmac= [MIPS] Korina ethernet MAC address.
2375 Configure the RouterBoard 532 series on-chip
2376 Ethernet adapter MAC address.
2378 kmemleak= [KNL] Boot-time kmemleak enable/disable
2379 Valid arguments: on, off
2381 Built with CONFIG_DEBUG_KMEMLEAK_DEFAULT_OFF=y,
2384 kprobe_event=[probe-list]
2385 [FTRACE] Add kprobe events and enable at boot time.
2386 The probe-list is a semicolon delimited list of probe
2387 definitions. Each definition is same as kprobe_events
2388 interface, but the parameters are comma delimited.
2389 For example, to add a kprobe event on vfs_read with
2390 arg1 and arg2, add to the command line;
2392 kprobe_event=p,vfs_read,$arg1,$arg2
2394 See also Documentation/trace/kprobetrace.rst "Kernel
2395 Boot Parameter" section.
2397 kpti= [ARM64] Control page table isolation of user
2398 and kernel address spaces.
2399 Default: enabled on cores which need mitigation.
2403 kvm.ignore_msrs=[KVM] Ignore guest accesses to unhandled MSRs.
2404 Default is 0 (don't ignore, but inject #GP)
2406 kvm.eager_page_split=
2407 [KVM,X86] Controls whether or not KVM will try to
2408 proactively split all huge pages during dirty logging.
2409 Eager page splitting reduces interruptions to vCPU
2410 execution by eliminating the write-protection faults
2411 and MMU lock contention that would otherwise be
2412 required to split huge pages lazily.
2414 VM workloads that rarely perform writes or that write
2415 only to a small region of VM memory may benefit from
2416 disabling eager page splitting to allow huge pages to
2417 still be used for reads.
2419 The behavior of eager page splitting depends on whether
2420 KVM_DIRTY_LOG_INITIALLY_SET is enabled or disabled. If
2421 disabled, all huge pages in a memslot will be eagerly
2422 split when dirty logging is enabled on that memslot. If
2423 enabled, eager page splitting will be performed during
2424 the KVM_CLEAR_DIRTY ioctl, and only for the pages being
2427 Eager page splitting is only supported when kvm.tdp_mmu=Y.
2431 kvm.enable_vmware_backdoor=[KVM] Support VMware backdoor PV interface.
2432 Default is false (don't support).
2435 [KVM] Controls the software workaround for the
2436 X86_BUG_ITLB_MULTIHIT bug.
2437 force : Always deploy workaround.
2438 off : Never deploy workaround.
2439 auto : Deploy workaround based on the presence of
2440 X86_BUG_ITLB_MULTIHIT.
2444 If the software workaround is enabled for the host,
2445 guests do need not to enable it for nested guests.
2447 kvm.nx_huge_pages_recovery_ratio=
2448 [KVM] Controls how many 4KiB pages are periodically zapped
2449 back to huge pages. 0 disables the recovery, otherwise if
2450 the value is N KVM will zap 1/Nth of the 4KiB pages every
2451 period (see below). The default is 60.
2453 kvm.nx_huge_pages_recovery_period_ms=
2454 [KVM] Controls the time period at which KVM zaps 4KiB pages
2455 back to huge pages. If the value is a non-zero N, KVM will
2456 zap a portion (see ratio above) of the pages every N msecs.
2457 If the value is 0 (the default), KVM will pick a period based
2458 on the ratio, such that a page is zapped after 1 hour on average.
2460 kvm-amd.nested= [KVM,AMD] Allow nested virtualization in KVM/SVM.
2461 Default is 1 (enabled)
2463 kvm-amd.npt= [KVM,AMD] Disable nested paging (virtualized MMU)
2465 Default is 1 (enabled) if in 64-bit or 32-bit PAE mode.
2468 [KVM,ARM] Select one of KVM/arm64's modes of operation.
2470 none: Forcefully disable KVM.
2472 nvhe: Standard nVHE-based mode, without support for
2475 protected: nVHE-based mode with support for guests whose
2476 state is kept private from the host.
2478 Defaults to VHE/nVHE based on hardware support. Setting
2479 mode to "protected" will disable kexec and hibernation
2482 kvm-arm.vgic_v3_group0_trap=
2483 [KVM,ARM] Trap guest accesses to GICv3 group-0
2486 kvm-arm.vgic_v3_group1_trap=
2487 [KVM,ARM] Trap guest accesses to GICv3 group-1
2490 kvm-arm.vgic_v3_common_trap=
2491 [KVM,ARM] Trap guest accesses to GICv3 common
2494 kvm-arm.vgic_v4_enable=
2495 [KVM,ARM] Allow use of GICv4 for direct injection of
2498 kvm_cma_resv_ratio=n [PPC]
2499 Reserves given percentage from system memory area for
2500 contiguous memory allocation for KVM hash pagetable
2502 By default it reserves 5% of total system memory.
2506 kvm-intel.ept= [KVM,Intel] Disable extended page tables
2507 (virtualized MMU) support on capable Intel chips.
2508 Default is 1 (enabled)
2510 kvm-intel.emulate_invalid_guest_state=
2511 [KVM,Intel] Disable emulation of invalid guest state.
2512 Ignored if kvm-intel.enable_unrestricted_guest=1, as
2513 guest state is never invalid for unrestricted guests.
2514 This param doesn't apply to nested guests (L2), as KVM
2515 never emulates invalid L2 guest state.
2516 Default is 1 (enabled)
2518 kvm-intel.flexpriority=
2519 [KVM,Intel] Disable FlexPriority feature (TPR shadow).
2520 Default is 1 (enabled)
2523 [KVM,Intel] Enable VMX nesting (nVMX).
2524 Default is 0 (disabled)
2526 kvm-intel.unrestricted_guest=
2527 [KVM,Intel] Disable unrestricted guest feature
2528 (virtualized real and unpaged mode) on capable
2529 Intel chips. Default is 1 (enabled)
2531 kvm-intel.vmentry_l1d_flush=[KVM,Intel] Mitigation for L1 Terminal Fault
2534 Valid arguments: never, cond, always
2536 always: L1D cache flush on every VMENTER.
2537 cond: Flush L1D on VMENTER only when the code between
2538 VMEXIT and VMENTER can leak host memory.
2539 never: Disables the mitigation
2541 Default is cond (do L1 cache flush in specific instances)
2543 kvm-intel.vpid= [KVM,Intel] Disable Virtual Processor Identification
2544 feature (tagged TLBs) on capable Intel chips.
2545 Default is 1 (enabled)
2547 l1d_flush= [X86,INTEL]
2548 Control mitigation for L1D based snooping vulnerability.
2550 Certain CPUs are vulnerable to an exploit against CPU
2551 internal buffers which can forward information to a
2552 disclosure gadget under certain conditions.
2554 In vulnerable processors, the speculatively
2555 forwarded data can be used in a cache side channel
2556 attack, to access data to which the attacker does
2557 not have direct access.
2559 This parameter controls the mitigation. The
2562 on - enable the interface for the mitigation
2564 l1tf= [X86] Control mitigation of the L1TF vulnerability on
2567 The kernel PTE inversion protection is unconditionally
2568 enabled and cannot be disabled.
2571 Provides all available mitigations for the
2572 L1TF vulnerability. Disables SMT and
2573 enables all mitigations in the
2574 hypervisors, i.e. unconditional L1D flush.
2576 SMT control and L1D flush control via the
2577 sysfs interface is still possible after
2578 boot. Hypervisors will issue a warning
2579 when the first VM is started in a
2580 potentially insecure configuration,
2581 i.e. SMT enabled or L1D flush disabled.
2584 Same as 'full', but disables SMT and L1D
2585 flush runtime control. Implies the
2586 'nosmt=force' command line option.
2587 (i.e. sysfs control of SMT is disabled.)
2590 Leaves SMT enabled and enables the default
2591 hypervisor mitigation, i.e. conditional
2594 SMT control and L1D flush control via the
2595 sysfs interface is still possible after
2596 boot. Hypervisors will issue a warning
2597 when the first VM is started in a
2598 potentially insecure configuration,
2599 i.e. SMT enabled or L1D flush disabled.
2603 Disables SMT and enables the default
2604 hypervisor mitigation.
2606 SMT control and L1D flush control via the
2607 sysfs interface is still possible after
2608 boot. Hypervisors will issue a warning
2609 when the first VM is started in a
2610 potentially insecure configuration,
2611 i.e. SMT enabled or L1D flush disabled.
2614 Same as 'flush', but hypervisors will not
2615 warn when a VM is started in a potentially
2616 insecure configuration.
2619 Disables hypervisor mitigations and doesn't
2621 It also drops the swap size and available
2622 RAM limit restriction on both hypervisor and
2627 For details see: Documentation/admin-guide/hw-vuln/l1tf.rst
2633 lapic [X86-32,APIC] Enable the local APIC even if BIOS
2636 lapic= [X86,APIC] Do not use TSC deadline
2637 value for LAPIC timer one-shot implementation. Default
2638 back to the programmable timer unit in the LAPIC.
2639 Format: notscdeadline
2641 lapic_timer_c2_ok [X86,APIC] trust the local apic timer
2644 libata.dma= [LIBATA] DMA control
2645 libata.dma=0 Disable all PATA and SATA DMA
2646 libata.dma=1 PATA and SATA Disk DMA only
2647 libata.dma=2 ATAPI (CDROM) DMA only
2648 libata.dma=4 Compact Flash DMA only
2649 Combinations also work, so libata.dma=3 enables DMA
2650 for disks and CDROMs, but not CFs.
2652 libata.ignore_hpa= [LIBATA] Ignore HPA limit
2653 libata.ignore_hpa=0 keep BIOS limits (default)
2654 libata.ignore_hpa=1 ignore limits, using full disk
2656 libata.noacpi [LIBATA] Disables use of ACPI in libata suspend/resume
2660 libata.force= [LIBATA] Force configurations. The format is a comma-
2661 separated list of "[ID:]VAL" where ID is PORT[.DEVICE].
2662 PORT and DEVICE are decimal numbers matching port, link
2663 or device. Basically, it matches the ATA ID string
2664 printed on console by libata. If the whole ID part is
2665 omitted, the last PORT and DEVICE values are used. If
2666 ID hasn't been specified yet, the configuration applies
2667 to all ports, links and devices.
2669 If only DEVICE is omitted, the parameter applies to
2670 the port and all links and devices behind it. DEVICE
2671 number of 0 either selects the first device or the
2672 first fan-out link behind PMP device. It does not
2673 select the host link. DEVICE number of 15 selects the
2674 host link and device attached to it.
2676 The VAL specifies the configuration to force. As long
2677 as there is no ambiguity, shortcut notation is allowed.
2678 For example, both 1.5 and 1.5G would work for 1.5Gbps.
2679 The following configurations can be forced.
2681 * Cable type: 40c, 80c, short40c, unk, ign or sata.
2682 Any ID with matching PORT is used.
2684 * SATA link speed limit: 1.5Gbps or 3.0Gbps.
2686 * Transfer mode: pio[0-7], mwdma[0-4] and udma[0-7].
2687 udma[/][16,25,33,44,66,100,133] notation is also
2690 * nohrst, nosrst, norst: suppress hard, soft and both
2693 * rstonce: only attempt one reset during hot-unplug
2696 * [no]dbdelay: Enable or disable the extra 200ms delay
2697 before debouncing a link PHY and device presence
2700 * [no]ncq: Turn on or off NCQ.
2702 * [no]ncqtrim: Enable or disable queued DSM TRIM.
2704 * [no]ncqati: Enable or disable NCQ trim on ATI chipset.
2706 * [no]trim: Enable or disable (unqueued) TRIM.
2708 * trim_zero: Indicate that TRIM command zeroes data.
2710 * max_trim_128m: Set 128M maximum trim size limit.
2712 * [no]dma: Turn on or off DMA transfers.
2714 * atapi_dmadir: Enable ATAPI DMADIR bridge support.
2716 * atapi_mod16_dma: Enable the use of ATAPI DMA for
2717 commands that are not a multiple of 16 bytes.
2719 * [no]dmalog: Enable or disable the use of the
2720 READ LOG DMA EXT command to access logs.
2722 * [no]iddevlog: Enable or disable access to the
2723 identify device data log.
2725 * [no]logdir: Enable or disable access to the general
2726 purpose log directory.
2728 * max_sec_128: Set transfer size limit to 128 sectors.
2730 * max_sec_1024: Set or clear transfer size limit to
2733 * max_sec_lba48: Set or clear transfer size limit to
2736 * [no]lpm: Enable or disable link power management.
2738 * [no]setxfer: Indicate if transfer speed mode setting
2741 * dump_id: Dump IDENTIFY data.
2743 * disable: Disable this device.
2745 If there are multiple matching configurations changing
2746 the same attribute, the last one is used.
2748 load_ramdisk= [RAM] [Deprecated]
2750 lockd.nlm_grace_period=P [NFS] Assign grace period.
2753 lockd.nlm_tcpport=N [NFS] Assign TCP port.
2756 lockd.nlm_timeout=T [NFS] Assign timeout value.
2759 lockd.nlm_udpport=M [NFS] Assign UDP port.
2762 lockdown= [SECURITY]
2763 { integrity | confidentiality }
2764 Enable the kernel lockdown feature. If set to
2765 integrity, kernel features that allow userland to
2766 modify the running kernel are disabled. If set to
2767 confidentiality, kernel features that allow userland
2768 to extract confidential information from the kernel
2771 locktorture.nreaders_stress= [KNL]
2772 Set the number of locking read-acquisition kthreads.
2773 Defaults to being automatically set based on the
2774 number of online CPUs.
2776 locktorture.nwriters_stress= [KNL]
2777 Set the number of locking write-acquisition kthreads.
2779 locktorture.onoff_holdoff= [KNL]
2780 Set time (s) after boot for CPU-hotplug testing.
2782 locktorture.onoff_interval= [KNL]
2783 Set time (s) between CPU-hotplug operations, or
2784 zero to disable CPU-hotplug testing.
2786 locktorture.shuffle_interval= [KNL]
2787 Set task-shuffle interval (jiffies). Shuffling
2788 tasks allows some CPUs to go into dyntick-idle
2789 mode during the locktorture test.
2791 locktorture.shutdown_secs= [KNL]
2792 Set time (s) after boot system shutdown. This
2793 is useful for hands-off automated testing.
2795 locktorture.stat_interval= [KNL]
2796 Time (s) between statistics printk()s.
2798 locktorture.stutter= [KNL]
2799 Time (s) to stutter testing, for example,
2800 specifying five seconds causes the test to run for
2801 five seconds, wait for five seconds, and so on.
2802 This tests the locking primitive's ability to
2803 transition abruptly to and from idle.
2805 locktorture.torture_type= [KNL]
2806 Specify the locking implementation to test.
2808 locktorture.verbose= [KNL]
2809 Enable additional printk() statements.
2811 logibm.irq= [HW,MOUSE] Logitech Bus Mouse Driver
2814 loglevel= All Kernel Messages with a loglevel smaller than the
2815 console loglevel will be printed to the console. It can
2816 also be changed with klogd or other programs. The
2817 loglevels are defined as follows:
2819 0 (KERN_EMERG) system is unusable
2820 1 (KERN_ALERT) action must be taken immediately
2821 2 (KERN_CRIT) critical conditions
2822 3 (KERN_ERR) error conditions
2823 4 (KERN_WARNING) warning conditions
2824 5 (KERN_NOTICE) normal but significant condition
2825 6 (KERN_INFO) informational
2826 7 (KERN_DEBUG) debug-level messages
2828 log_buf_len=n[KMG] Sets the size of the printk ring buffer,
2829 in bytes. n must be a power of two and greater
2830 than the minimal size. The minimal size is defined
2831 by LOG_BUF_SHIFT kernel config parameter. There is
2832 also CONFIG_LOG_CPU_MAX_BUF_SHIFT config parameter
2833 that allows to increase the default size depending on
2834 the number of CPUs. See init/Kconfig for more details.
2836 logo.nologo [FB] Disables display of the built-in Linux logo.
2837 This may be used to provide more screen space for
2838 kernel log messages and is useful when debugging
2839 kernel boot problems.
2841 lp=0 [LP] Specify parallel ports to use, e.g,
2842 lp=port[,port...] lp=none,parport0 (lp0 not configured, lp1 uses
2843 lp=reset first parallel port). 'lp=0' disables the
2844 lp=auto printer driver. 'lp=reset' (which can be
2845 specified in addition to the ports) causes
2846 attached printers to be reset. Using
2847 lp=port1,port2,... specifies the parallel ports
2848 to associate lp devices with, starting with
2849 lp0. A port specification may be 'none' to skip
2850 that lp device, or a parport name such as
2851 'parport0'. Specifying 'lp=auto' instead of a
2852 port specification list means that device IDs
2853 from each port should be examined, to see if
2854 an IEEE 1284-compliant printer is attached; if
2855 so, the driver will manage that printer.
2856 See also header of drivers/char/lp.c.
2859 Sets loops_per_jiffy to given constant, thus avoiding
2860 time-consuming boot-time autodetection (up to 250 ms per
2861 CPU). 0 enables autodetection (default). To determine
2862 the correct value for your kernel, boot with normal
2863 autodetection and see what value is printed. Note that
2864 on SMP systems the preset will be applied to all CPUs,
2865 which is likely to cause problems if your CPUs need
2866 significantly divergent settings. An incorrect value
2867 will cause delays in the kernel to be wrong, leading to
2868 unpredictable I/O errors and other breakage. Although
2869 unlikely, in the extreme case this might damage your
2873 Format: <io>,<irq>,<dma>
2875 lsm.debug [SECURITY] Enable LSM initialization debugging output.
2878 [SECURITY] Choose order of LSM initialization. This
2879 overrides CONFIG_LSM, and the "security=" parameter.
2881 machvec= [IA-64] Force the use of a particular machine-vector
2882 (machvec) in a generic kernel.
2883 Example: machvec=hpzx1
2885 machtype= [Loongson] Share the same kernel image file between
2886 different yeeloong laptops.
2887 Example: machtype=lemote-yeeloong-2f-7inch
2889 max_addr=nn[KMG] [KNL,BOOT,IA-64] All physical memory greater
2890 than or equal to this physical address is ignored.
2892 maxcpus= [SMP] Maximum number of processors that an SMP kernel
2893 will bring up during bootup. maxcpus=n : n >= 0 limits
2894 the kernel to bring up 'n' processors. Surely after
2895 bootup you can bring up the other plugged cpu by executing
2896 "echo 1 > /sys/devices/system/cpu/cpuX/online". So maxcpus
2897 only takes effect during system bootup.
2898 While n=0 is a special case, it is equivalent to "nosmp",
2899 which also disables the IO APIC.
2901 max_loop= [LOOP] The number of loop block devices that get
2902 (loop.max_loop) unconditionally pre-created at init time. The default
2903 number is configured by BLK_DEV_LOOP_MIN_COUNT. Instead
2904 of statically allocating a predefined number, loop
2905 devices can be requested on-demand with the
2906 /dev/loop-control interface.
2908 mce [X86-32] Machine Check Exception
2910 mce=option [X86-64] See Documentation/x86/x86_64/boot-options.rst
2912 md= [HW] RAID subsystems devices and level
2913 See Documentation/admin-guide/md.rst.
2916 Format: <first>,<last>
2917 Specifies range of consoles to be captured by the MDA.
2920 Control mitigation for the Micro-architectural Data
2921 Sampling (MDS) vulnerability.
2923 Certain CPUs are vulnerable to an exploit against CPU
2924 internal buffers which can forward information to a
2925 disclosure gadget under certain conditions.
2927 In vulnerable processors, the speculatively
2928 forwarded data can be used in a cache side channel
2929 attack, to access data to which the attacker does
2930 not have direct access.
2932 This parameter controls the MDS mitigation. The
2935 full - Enable MDS mitigation on vulnerable CPUs
2936 full,nosmt - Enable MDS mitigation and disable
2937 SMT on vulnerable CPUs
2938 off - Unconditionally disable MDS mitigation
2940 On TAA-affected machines, mds=off can be prevented by
2941 an active TAA mitigation as both vulnerabilities are
2942 mitigated with the same mechanism so in order to disable
2943 this mitigation, you need to specify tsx_async_abort=off
2946 Not specifying this option is equivalent to
2949 For details see: Documentation/admin-guide/hw-vuln/mds.rst
2951 mem=nn[KMG] [HEXAGON] Set the memory size.
2952 Must be specified, otherwise memory size will be 0.
2954 mem=nn[KMG] [KNL,BOOT] Force usage of a specific amount of memory
2955 Amount of memory to be used in cases as follows:
2958 2 when the kernel is not able to see the whole system memory;
2959 3 memory that lies after 'mem=' boundary is excluded from
2960 the hypervisor, then assigned to KVM guests.
2961 4 to limit the memory available for kdump kernel.
2963 [ARC,MICROBLAZE] - the limit applies only to low memory,
2964 high memory is not affected.
2966 [ARM64] - only limits memory covered by the linear
2967 mapping. The NOMAP regions are not affected.
2969 [X86] Work as limiting max address. Use together
2970 with memmap= to avoid physical address space collisions.
2971 Without memmap= PCI devices could be placed at addresses
2972 belonging to unused RAM.
2974 Note that this only takes effects during boot time since
2975 in above case 3, memory may need be hot added after boot
2976 if system memory of hypervisor is not sufficient.
2979 [ARM,MIPS] - override the memory layout reported by
2981 Define a memory region of size nn[KMG] starting at
2983 Multiple different regions can be specified with
2984 multiple mem= parameters on the command line.
2986 mem=nopentium [BUGS=X86-32] Disable usage of 4MB pages for kernel
2989 memblock=debug [KNL] Enable memblock debug messages.
2992 [KNL,SH] Allow user to override the default size for
2993 per-device physically contiguous DMA buffers.
2995 memhp_default_state=online/offline
2996 [KNL] Set the initial state for the memory hotplug
2997 onlining policy. If not specified, the default value is
2998 set according to the
2999 CONFIG_MEMORY_HOTPLUG_DEFAULT_ONLINE kernel config
3001 See Documentation/admin-guide/mm/memory-hotplug.rst.
3003 memmap=exactmap [KNL,X86] Enable setting of an exact
3004 E820 memory map, as specified by the user.
3005 Such memmap=exactmap lines can be constructed based on
3006 BIOS output or other requirements. See the memmap=nn@ss
3009 memmap=nn[KMG]@ss[KMG]
3010 [KNL, X86, MIPS, XTENSA] Force usage of a specific region of memory.
3011 Region of memory to be used is from ss to ss+nn.
3012 If @ss[KMG] is omitted, it is equivalent to mem=nn[KMG],
3013 which limits max address to nn[KMG].
3014 Multiple different regions can be specified,
3017 memmap=100M@2G,100M#3G,1G!1024G
3019 memmap=nn[KMG]#ss[KMG]
3020 [KNL,ACPI] Mark specific memory as ACPI data.
3021 Region of memory to be marked is from ss to ss+nn.
3023 memmap=nn[KMG]$ss[KMG]
3024 [KNL,ACPI] Mark specific memory as reserved.
3025 Region of memory to be reserved is from ss to ss+nn.
3026 Example: Exclude memory from 0x18690000-0x1869ffff
3027 memmap=64K$0x18690000
3029 memmap=0x10000$0x18690000
3030 Some bootloaders may need an escape character before '$',
3031 like Grub2, otherwise '$' and the following number
3034 memmap=nn[KMG]!ss[KMG]
3035 [KNL,X86] Mark specific memory as protected.
3036 Region of memory to be used, from ss to ss+nn.
3037 The memory region may be marked as e820 type 12 (0xc)
3038 and is NVDIMM or ADR memory.
3040 memmap=<size>%<offset>-<oldtype>+<newtype>
3041 [KNL,ACPI] Convert memory within the specified region
3042 from <oldtype> to <newtype>. If "-<oldtype>" is left
3043 out, the whole region will be marked as <newtype>,
3044 even if previously unavailable. If "+<newtype>" is left
3045 out, matching memory will be removed. Types are
3046 specified as e820 types, e.g., 1 = RAM, 2 = reserved,
3047 3 = ACPI, 12 = PRAM.
3049 memory_corruption_check=0/1 [X86]
3050 Some BIOSes seem to corrupt the first 64k of
3051 memory when doing things like suspend/resume.
3052 Setting this option will scan the memory
3053 looking for corruption. Enabling this will
3054 both detect corruption and prevent the kernel
3055 from using the memory being corrupted.
3056 However, its intended as a diagnostic tool; if
3057 repeatable BIOS-originated corruption always
3058 affects the same memory, you can use memmap=
3059 to prevent the kernel from using that memory.
3061 memory_corruption_check_size=size [X86]
3062 By default it checks for corruption in the low
3063 64k, making this memory unavailable for normal
3064 use. Use this parameter to scan for
3065 corruption in more or less memory.
3067 memory_corruption_check_period=seconds [X86]
3068 By default it checks for corruption every 60
3069 seconds. Use this parameter to check at some
3070 other rate. 0 disables periodic checking.
3072 memory_hotplug.memmap_on_memory
3073 [KNL,X86,ARM] Boolean flag to enable this feature.
3074 Format: {on | off (default)}
3075 When enabled, runtime hotplugged memory will
3076 allocate its internal metadata (struct pages)
3077 from the hotadded memory which will allow to
3078 hotadd a lot of memory without requiring
3079 additional memory to do so.
3080 This feature is disabled by default because it
3081 has some implication on large (e.g. GB)
3082 allocations in some configurations (e.g. small
3084 The state of the flag can be read in
3085 /sys/module/memory_hotplug/parameters/memmap_on_memory.
3086 Note that even when enabled, there are a few cases where
3087 the feature is not effective.
3089 This is not compatible with hugetlb_free_vmemmap. If
3090 both parameters are enabled, hugetlb_free_vmemmap takes
3091 precedence over memory_hotplug.memmap_on_memory.
3093 memtest= [KNL,X86,ARM,M68K,PPC,RISCV] Enable memtest
3095 default : 0 <disable>
3096 Specifies the number of memtest passes to be
3097 performed. Each pass selects another test
3098 pattern from a given set of patterns. Memtest
3099 fills the memory with this pattern, validates
3100 memory contents and reserves bad memory
3101 regions that are detected.
3103 mem_encrypt= [X86-64] AMD Secure Memory Encryption (SME) control
3104 Valid arguments: on, off
3105 Default (depends on kernel configuration option):
3106 on (CONFIG_AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT=y)
3107 off (CONFIG_AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT=n)
3108 mem_encrypt=on: Activate SME
3109 mem_encrypt=off: Do not activate SME
3111 Refer to Documentation/virt/kvm/x86/amd-memory-encryption.rst
3112 for details on when memory encryption can be activated.
3114 mem_sleep_default= [SUSPEND] Default system suspend mode:
3115 s2idle - Suspend-To-Idle
3116 shallow - Power-On Suspend or equivalent (if supported)
3117 deep - Suspend-To-RAM or equivalent (if supported)
3118 See Documentation/admin-guide/pm/sleep-states.rst.
3120 meye.*= [HW] Set MotionEye Camera parameters
3121 See Documentation/admin-guide/media/meye.rst.
3123 mfgpt_irq= [IA-32] Specify the IRQ to use for the
3124 Multi-Function General Purpose Timers on AMD Geode
3127 mfgptfix [X86-32] Fix MFGPT timers on AMD Geode platforms when
3128 the BIOS has incorrectly applied a workaround. TinyBIOS
3129 version 0.98 is known to be affected, 0.99 fixes the
3130 problem by letting the user disable the workaround.
3134 min_addr=nn[KMG] [KNL,BOOT,IA-64] All physical memory below this
3135 physical address is ignored.
3137 mini2440= [ARM,HW,KNL]
3138 Format:[0..2][b][c][t]
3140 MINI2440 configuration specification:
3141 0 - The attached screen is the 3.5" TFT
3142 1 - The attached screen is the 7" TFT
3143 2 - The VGA Shield is attached (1024x768)
3144 Leaving out the screen size parameter will not load
3145 the TFT driver, and the framebuffer will be left
3147 b - Enable backlight. The TFT backlight pin will be
3148 linked to the kernel VESA blanking code and a GPIO
3149 LED. This parameter is not necessary when using the
3151 c - Enable the s3c camera interface.
3152 t - Reserved for enabling touchscreen support. The
3153 touchscreen support is not enabled in the mainstream
3154 kernel as of 2.6.30, a preliminary port can be found
3155 in the "bleeding edge" mini2440 support kernel at
3156 https://repo.or.cz/w/linux-2.6/mini2440.git
3159 [X86,PPC,S390,ARM64] Control optional mitigations for
3160 CPU vulnerabilities. This is a set of curated,
3161 arch-independent options, each of which is an
3162 aggregation of existing arch-specific options.
3165 Disable all optional CPU mitigations. This
3166 improves system performance, but it may also
3167 expose users to several CPU vulnerabilities.
3168 Equivalent to: nopti [X86,PPC]
3169 if nokaslr then kpti=0 [ARM64]
3170 nospectre_v1 [X86,PPC]
3172 nospectre_v2 [X86,PPC,S390,ARM64]
3173 spectre_v2_user=off [X86]
3174 spec_store_bypass_disable=off [X86,PPC]
3175 ssbd=force-off [ARM64]
3178 tsx_async_abort=off [X86]
3179 kvm.nx_huge_pages=off [X86]
3180 srbds=off [X86,INTEL]
3181 no_entry_flush [PPC]
3182 no_uaccess_flush [PPC]
3183 mmio_stale_data=off [X86]
3187 This does not have any effect on
3188 kvm.nx_huge_pages when
3189 kvm.nx_huge_pages=force.
3192 Mitigate all CPU vulnerabilities, but leave SMT
3193 enabled, even if it's vulnerable. This is for
3194 users who don't want to be surprised by SMT
3195 getting disabled across kernel upgrades, or who
3196 have other ways of avoiding SMT-based attacks.
3197 Equivalent to: (default behavior)
3200 Mitigate all CPU vulnerabilities, disabling SMT
3201 if needed. This is for users who always want to
3202 be fully mitigated, even if it means losing SMT.
3203 Equivalent to: l1tf=flush,nosmt [X86]
3204 mds=full,nosmt [X86]
3205 tsx_async_abort=full,nosmt [X86]
3206 mmio_stale_data=full,nosmt [X86]
3207 retbleed=auto,nosmt [X86]
3210 [KNL] When CONFIG_DEBUG_MEMORY_INIT is set, this
3211 parameter allows control of the logging verbosity for
3212 the additional memory initialisation checks. A value
3213 of 0 disables mminit logging and a level of 4 will
3214 log everything. Information is printed at KERN_DEBUG
3215 so loglevel=8 may also need to be specified.
3218 [X86,INTEL] Control mitigation for the Processor
3219 MMIO Stale Data vulnerabilities.
3221 Processor MMIO Stale Data is a class of
3222 vulnerabilities that may expose data after an MMIO
3223 operation. Exposed data could originate or end in
3224 the same CPU buffers as affected by MDS and TAA.
3225 Therefore, similar to MDS and TAA, the mitigation
3226 is to clear the affected CPU buffers.
3228 This parameter controls the mitigation. The
3231 full - Enable mitigation on vulnerable CPUs
3233 full,nosmt - Enable mitigation and disable SMT on
3236 off - Unconditionally disable mitigation
3238 On MDS or TAA affected machines,
3239 mmio_stale_data=off can be prevented by an active
3240 MDS or TAA mitigation as these vulnerabilities are
3241 mitigated with the same mechanism so in order to
3242 disable this mitigation, you need to specify
3243 mds=off and tsx_async_abort=off too.
3245 Not specifying this option is equivalent to
3246 mmio_stale_data=full.
3249 Documentation/admin-guide/hw-vuln/processor_mmio_stale_data.rst
3252 [KNL] When CONFIG_MODULE_SIG is set, this means that
3253 modules without (valid) signatures will fail to load.
3254 Note that if CONFIG_MODULE_SIG_FORCE is set, that
3255 is always true, so this option does nothing.
3257 module_blacklist= [KNL] Do not load a comma-separated list of
3258 modules. Useful for debugging problem modules.
3261 [MOUSE] Maximum time between finger touching and
3262 leaving touchpad surface for touch to be considered
3263 a tap and be reported as a left button click (for
3264 touchpads working in absolute mode only).
3266 mousedev.xres= [MOUSE] Horizontal screen resolution, used for devices
3267 reporting absolute coordinates, such as tablets
3268 mousedev.yres= [MOUSE] Vertical screen resolution, used for devices
3269 reporting absolute coordinates, such as tablets
3271 movablecore= [KNL,X86,IA-64,PPC]
3272 Format: nn[KMGTPE] | nn%
3273 This parameter is the complement to kernelcore=, it
3274 specifies the amount of memory used for migratable
3275 allocations. If both kernelcore and movablecore is
3276 specified, then kernelcore will be at *least* the
3277 specified value but may be more. If movablecore on its
3278 own is specified, the administrator must be careful
3279 that the amount of memory usable for all allocations
3282 movable_node [KNL] Boot-time switch to make hotplugable memory
3283 NUMA nodes to be movable. This means that the memory
3284 of such nodes will be usable only for movable
3285 allocations which rules out almost all kernel
3286 allocations. Use with caution!
3288 MTD_Partition= [MTD]
3289 Format: <name>,<region-number>,<size>,<offset>
3291 MTD_Region= [MTD] Format:
3292 <name>,<region-number>[,<base>,<size>,<buswidth>,<altbuswidth>]
3295 See drivers/mtd/parsers/cmdlinepart.c
3298 ARM/S3C2412 JIVE boot control
3300 See arch/arm/mach-s3c/mach-jive.c
3302 mtouchusb.raw_coordinates=
3303 [HW] Make the MicroTouch USB driver use raw coordinates
3304 ('y', default) or cooked coordinates ('n')
3306 mtrr_chunk_size=nn[KMG] [X86]
3307 used for mtrr cleanup. It is largest continuous chunk
3308 that could hold holes aka. UC entries.
3310 mtrr_gran_size=nn[KMG] [X86]
3311 Used for mtrr cleanup. It is granularity of mtrr block.
3313 Large value could prevent small alignment from
3316 mtrr_spare_reg_nr=n [X86]
3318 Range: 0,7 : spare reg number
3320 Used for mtrr cleanup. It is spare mtrr entries number.
3321 Set to 2 or more if your graphical card needs more.
3323 multitce=off [PPC] This parameter disables the use of the pSeries
3324 firmware feature for updating multiple TCE entries
3327 n2= [NET] SDL Inc. RISCom/N2 synchronous serial card
3329 netdev= [NET] Network devices parameters
3330 Format: <irq>,<io>,<mem_start>,<mem_end>,<name>
3331 Note that mem_start is often overloaded to mean
3332 something different and driver-specific.
3333 This usage is only documented in each driver source
3336 netpoll.carrier_timeout=
3337 [NET] Specifies amount of time (in seconds) that
3338 netpoll should wait for a carrier. By default netpoll
3342 [NETFILTER] Enable connection tracking flow accounting
3343 0 to disable accounting
3344 1 to enable accounting
3347 nfsaddrs= [NFS] Deprecated. Use ip= instead.
3348 See Documentation/admin-guide/nfs/nfsroot.rst.
3350 nfsroot= [NFS] nfs root filesystem for disk-less boxes.
3351 See Documentation/admin-guide/nfs/nfsroot.rst.
3353 nfsrootdebug [NFS] enable nfsroot debugging messages.
3354 See Documentation/admin-guide/nfs/nfsroot.rst.
3356 nfs.callback_nr_threads=
3357 [NFSv4] set the total number of threads that the
3358 NFS client will assign to service NFSv4 callback
3361 nfs.callback_tcpport=
3362 [NFS] set the TCP port on which the NFSv4 callback
3363 channel should listen.
3366 [NFS] sets the pathname to the program which is used
3367 to update the NFS client cache entries.
3369 nfs.cache_getent_timeout=
3370 [NFS] sets the timeout after which an attempt to
3371 update a cache entry is deemed to have failed.
3373 nfs.idmap_cache_timeout=
3374 [NFS] set the maximum lifetime for idmapper cache
3378 [NFS] enable 64-bit inode numbers.
3379 If zero, the NFS client will fake up a 32-bit inode
3380 number for the readdir() and stat() syscalls instead
3381 of returning the full 64-bit number.
3382 The default is to return 64-bit inode numbers.
3384 nfs.max_session_cb_slots=
3385 [NFSv4.1] Sets the maximum number of session
3386 slots the client will assign to the callback
3387 channel. This determines the maximum number of
3388 callbacks the client will process in parallel for
3389 a particular server.
3391 nfs.max_session_slots=
3392 [NFSv4.1] Sets the maximum number of session slots
3393 the client will attempt to negotiate with the server.
3394 This limits the number of simultaneous RPC requests
3395 that the client can send to the NFSv4.1 server.
3396 Note that there is little point in setting this
3397 value higher than the max_tcp_slot_table_limit.
3399 nfs.nfs4_disable_idmapping=
3400 [NFSv4] When set to the default of '1', this option
3401 ensures that both the RPC level authentication
3402 scheme and the NFS level operations agree to use
3403 numeric uids/gids if the mount is using the
3404 'sec=sys' security flavour. In effect it is
3405 disabling idmapping, which can make migration from
3406 legacy NFSv2/v3 systems to NFSv4 easier.
3407 Servers that do not support this mode of operation
3408 will be autodetected by the client, and it will fall
3409 back to using the idmapper.
3410 To turn off this behaviour, set the value to '0'.
3412 [NFS4] Specify an additional fixed unique ident-
3413 ification string that NFSv4 clients can insert into
3414 their nfs_client_id4 string. This is typically a
3415 UUID that is generated at system install time.
3417 nfs.send_implementation_id =
3418 [NFSv4.1] Send client implementation identification
3419 information in exchange_id requests.
3420 If zero, no implementation identification information
3422 The default is to send the implementation identification
3425 nfs.recover_lost_locks =
3426 [NFSv4] Attempt to recover locks that were lost due
3427 to a lease timeout on the server. Please note that
3428 doing this risks data corruption, since there are
3429 no guarantees that the file will remain unchanged
3430 after the locks are lost.
3431 If you want to enable the kernel legacy behaviour of
3432 attempting to recover these locks, then set this
3434 The default parameter value of '0' causes the kernel
3435 not to attempt recovery of lost locks.
3437 nfs4.layoutstats_timer =
3438 [NFSv4.2] Change the rate at which the kernel sends
3439 layoutstats to the pNFS metadata server.
3441 Setting this to value to 0 causes the kernel to use
3442 whatever value is the default set by the layout
3443 driver. A non-zero value sets the minimum interval
3444 in seconds between layoutstats transmissions.
3446 nfsd.inter_copy_offload_enable =
3447 [NFSv4.2] When set to 1, the server will support
3448 server-to-server copies for which this server is
3449 the destination of the copy.
3451 nfsd.nfsd4_ssc_umount_timeout =
3452 [NFSv4.2] When used as the destination of a
3453 server-to-server copy, knfsd temporarily mounts
3454 the source server. It caches the mount in case
3455 it will be needed again, and discards it if not
3456 used for the number of milliseconds specified by
3459 nfsd.nfs4_disable_idmapping=
3460 [NFSv4] When set to the default of '1', the NFSv4
3461 server will return only numeric uids and gids to
3462 clients using auth_sys, and will accept numeric uids
3463 and gids from such clients. This is intended to ease
3464 migration from NFSv2/v3.
3467 nmi_backtrace.backtrace_idle [KNL]
3468 Dump stacks even of idle CPUs in response to an
3469 NMI stack-backtrace request.
3471 nmi_debug= [KNL,SH] Specify one or more actions to take
3472 when a NMI is triggered.
3473 Format: [state][,regs][,debounce][,die]
3475 nmi_watchdog= [KNL,BUGS=X86] Debugging features for SMP kernels
3476 Format: [panic,][nopanic,][num]
3478 0 - turn hardlockup detector in nmi_watchdog off
3479 1 - turn hardlockup detector in nmi_watchdog on
3480 When panic is specified, panic when an NMI watchdog
3481 timeout occurs (or 'nopanic' to not panic on an NMI
3482 watchdog, if CONFIG_BOOTPARAM_HARDLOCKUP_PANIC is set)
3483 To disable both hard and soft lockup detectors,
3484 please see 'nowatchdog'.
3485 This is useful when you use a panic=... timeout and
3486 need the box quickly up again.
3488 These settings can be accessed at runtime via
3489 the nmi_watchdog and hardlockup_panic sysctls.
3491 no387 [BUGS=X86-32] Tells the kernel to use the 387 maths
3492 emulation library even if a 387 maths coprocessor
3495 no5lvl [X86-64] Disable 5-level paging mode. Forces
3496 kernel to use 4-level paging instead.
3498 nofsgsbase [X86] Disables FSGSBASE instructions.
3501 [HW] Never suspend the console
3502 Disable suspending of consoles during suspend and
3503 hibernate operations. Once disabled, debugging
3504 messages can reach various consoles while the rest
3505 of the system is being put to sleep (ie, while
3506 debugging driver suspend/resume hooks). This may
3507 not work reliably with all consoles, but is known
3508 to work with serial and VGA consoles.
3509 To facilitate more flexible debugging, we also add
3510 console_suspend, a printk module parameter to control
3511 it. Users could use console_suspend (usually
3512 /sys/module/printk/parameters/console_suspend) to
3513 turn on/off it dynamically.
3515 novmcoredd [KNL,KDUMP]
3516 Disable device dump. Device dump allows drivers to
3517 append dump data to vmcore so you can collect driver
3518 specified debug info. Drivers can append the data
3519 without any limit and this data is stored in memory,
3520 so this may cause significant memory stress. Disabling
3521 device dump can help save memory but the driver debug
3522 data will be no longer available. This parameter
3523 is only available when CONFIG_PROC_VMCORE_DEVICE_DUMP
3526 noaliencache [MM, NUMA, SLAB] Disables the allocation of alien
3527 caches in the slab allocator. Saves per-node memory,
3528 but will impact performance.
3532 noaltinstr [S390] Disables alternative instructions patching
3533 (CPU alternatives feature).
3535 noapic [SMP,APIC] Tells the kernel to not make use of any
3536 IOAPICs that may be present in the system.
3538 noautogroup Disable scheduler automatic task group creation.
3540 nobats [PPC] Do not use BATs for mapping kernel lowmem
3541 on "Classic" PPC cores.
3545 nodsp [SH] Disable hardware DSP at boot time.
3547 noefi Disable EFI runtime services support.
3549 no_entry_flush [PPC] Don't flush the L1-D cache when entering the kernel.
3554 Disable SMAP (Supervisor Mode Access Prevention)
3555 even if it is supported by processor.
3558 Disable SMEP (Supervisor Mode Execution Prevention)
3559 even if it is supported by processor.
3562 This affects only 32-bit executables.
3563 noexec32=on: enable non-executable mappings (default)
3564 read doesn't imply executable mappings
3565 noexec32=off: disable non-executable mappings
3566 read implies executable mappings
3568 nofpu [MIPS,SH] Disable hardware FPU at boot time.
3570 nofxsr [BUGS=X86-32] Disables x86 floating point extended
3571 register save and restore. The kernel will only save
3572 legacy floating-point registers on task switch.
3574 nohugeiomap [KNL,X86,PPC,ARM64] Disable kernel huge I/O mappings.
3576 nohugevmalloc [PPC] Disable kernel huge vmalloc mappings.
3578 nosmt [KNL,S390] Disable symmetric multithreading (SMT).
3579 Equivalent to smt=1.
3581 [KNL,X86] Disable symmetric multithreading (SMT).
3582 nosmt=force: Force disable SMT, cannot be undone
3583 via the sysfs control file.
3585 nospectre_v1 [X86,PPC] Disable mitigations for Spectre Variant 1
3586 (bounds check bypass). With this option data leaks are
3587 possible in the system.
3589 nospectre_v2 [X86,PPC_FSL_BOOK3E,ARM64] Disable all mitigations for
3590 the Spectre variant 2 (indirect branch prediction)
3591 vulnerability. System may allow data leaks with this
3594 nospec_store_bypass_disable
3595 [HW] Disable all mitigations for the Speculative Store Bypass vulnerability
3598 [PPC] Don't flush the L1-D cache after accessing user data.
3600 noxsave [BUGS=X86] Disables x86 extended register state save
3601 and restore using xsave. The kernel will fallback to
3602 enabling legacy floating-point and sse state.
3604 noxsaveopt [X86] Disables xsaveopt used in saving x86 extended
3605 register states. The kernel will fall back to use
3606 xsave to save the states. By using this parameter,
3607 performance of saving the states is degraded because
3608 xsave doesn't support modified optimization while
3609 xsaveopt supports it on xsaveopt enabled systems.
3611 noxsaves [X86] Disables xsaves and xrstors used in saving and
3612 restoring x86 extended register state in compacted
3613 form of xsave area. The kernel will fall back to use
3614 xsaveopt and xrstor to save and restore the states
3615 in standard form of xsave area. By using this
3616 parameter, xsave area per process might occupy more
3617 memory on xsaves enabled systems.
3619 nohlt [ARM,ARM64,MICROBLAZE,SH] Forces the kernel to busy wait
3620 in do_idle() and not use the arch_cpu_idle()
3621 implementation; requires CONFIG_GENERIC_IDLE_POLL_SETUP
3622 to be effective. This is useful on platforms where the
3623 sleep(SH) or wfi(ARM,ARM64) instructions do not work
3624 correctly or when doing power measurements to evalute
3625 the impact of the sleep instructions. This is also
3626 useful when using JTAG debugger.
3628 no_file_caps Tells the kernel not to honor file capabilities. The
3629 only way then for a file to be executed with privilege
3630 is to be setuid root or executed by root.
3632 nohalt [IA-64] Tells the kernel not to use the power saving
3633 function PAL_HALT_LIGHT when idle. This increases
3634 power-consumption. On the positive side, it reduces
3635 interrupt wake-up latency, which may improve performance
3636 in certain environments such as networked servers or
3640 Force pointers printed to the console or buffers to be
3641 unhashed. By default, when a pointer is printed via %p
3642 format string, that pointer is "hashed", i.e. obscured
3643 by hashing the pointer value. This is a security feature
3644 that hides actual kernel addresses from unprivileged
3645 users, but it also makes debugging the kernel more
3646 difficult since unequal pointers can no longer be
3647 compared. However, if this command-line option is
3648 specified, then all normal pointers will have their true
3649 value printed. This option should only be specified when
3650 debugging the kernel. Please do not use on production
3653 nohibernate [HIBERNATION] Disable hibernation and resume.
3655 nohz= [KNL] Boottime enable/disable dynamic ticks
3656 Valid arguments: on, off
3659 nohz_full= [KNL,BOOT,SMP,ISOL]
3660 The argument is a cpu list, as described above.
3661 In kernels built with CONFIG_NO_HZ_FULL=y, set
3662 the specified list of CPUs whose tick will be stopped
3663 whenever possible. The boot CPU will be forced outside
3664 the range to maintain the timekeeping. Any CPUs
3665 in this list will have their RCU callbacks offloaded,
3666 just as if they had also been called out in the
3667 rcu_nocbs= boot parameter.
3669 Note that this argument takes precedence over
3670 the CONFIG_RCU_NOCB_CPU_DEFAULT_ALL option.
3672 noiotrap [SH] Disables trapped I/O port accesses.
3674 noirqdebug [X86-32] Disables the code which attempts to detect and
3675 disable unhandled interrupt sources.
3677 no_timer_check [X86,APIC] Disables the code which tests for
3678 broken timer IRQ sources.
3680 noisapnp [ISAPNP] Disables ISA PnP code.
3682 noinitrd [RAM] Tells the kernel not to load any configured
3685 nointremap [X86-64, Intel-IOMMU] Do not enable interrupt
3687 [Deprecated - use intremap=off]
3691 noinvpcid [X86] Disable the INVPCID cpu feature.
3693 nojitter [IA-64] Disables jitter checking for ITC timers.
3695 no-kvmclock [X86,KVM] Disable paravirtualized KVM clock driver
3697 no-kvmapf [X86,KVM] Disable paravirtualized asynchronous page
3701 [X86,PV_OPS] Disable paravirtualized VMware scheduler
3702 clock and use the default one.
3704 no-steal-acc [X86,PV_OPS,ARM64] Disable paravirtualized steal time
3705 accounting. steal time is computed, but won't
3706 influence scheduler behaviour
3708 nolapic [X86-32,APIC] Do not enable or use the local APIC.
3710 nolapic_timer [X86-32,APIC] Do not use the local APIC timer.
3712 noltlbs [PPC] Do not use large page/tlb entries for kernel
3713 lowmem mapping on PPC40x and PPC8xx
3715 nomca [IA-64] Disable machine check abort handling
3717 nomce [X86-32] Disable Machine Check Exception
3719 nomfgpt [X86-32] Disable Multi-Function General Purpose
3720 Timer usage (for AMD Geode machines).
3722 nonmi_ipi [X86] Disable using NMI IPIs during panic/reboot to
3723 shutdown the other cpus. Instead use the REBOOT_VECTOR
3726 nomodeset Disable kernel modesetting. DRM drivers will not perform
3727 display-mode changes or accelerated rendering. Only the
3728 system framebuffer will be available for use if this was
3729 set-up by the firmware or boot loader.
3731 Useful as fallback, or for testing and debugging.
3733 nomodule Disable module load
3735 nopat [X86] Disable PAT (page attribute table extension of
3736 pagetables) support.
3738 nopcid [X86-64] Disable the PCID cpu feature.
3740 norandmaps Don't use address space randomization. Equivalent to
3741 echo 0 > /proc/sys/kernel/randomize_va_space
3743 noreplace-smp [X86-32,SMP] Don't replace SMP instructions
3744 with UP alternatives
3746 noresume [SWSUSP] Disables resume and restores original swap
3749 no-scroll [VGA] Disables scrollback.
3750 This is required for the Braillex ib80-piezo Braille
3751 reader made by F.H. Papenmeier (Germany).
3755 nosgx [X86-64,SGX] Disables Intel SGX kernel support.
3757 nosmp [SMP] Tells an SMP kernel to act as a UP kernel,
3758 and disable the IO APIC. legacy for "maxcpus=0".
3760 nosoftlockup [KNL] Disable the soft-lockup detector.
3762 nosync [HW,M68K] Disables sync negotiation for all devices.
3764 nowatchdog [KNL] Disable both lockup detectors, i.e.
3765 soft-lockup and NMI watchdog (hard-lockup).
3769 nox2apic [X86-64,APIC] Do not enable x2APIC mode.
3771 nps_mtm_hs_ctr= [KNL,ARC]
3772 This parameter sets the maximum duration, in
3773 cycles, each HW thread of the CTOP can run
3774 without interruptions, before HW switches it.
3775 The actual maximum duration is 16 times this
3777 Format: integer between 1 and 255
3780 nptcg= [IA-64] Override max number of concurrent global TLB
3781 purges which is reported from either PAL_VM_SUMMARY or
3784 nr_cpus= [SMP] Maximum number of processors that an SMP kernel
3785 could support. nr_cpus=n : n >= 1 limits the kernel to
3786 support 'n' processors. It could be larger than the
3787 number of already plugged CPU during bootup, later in
3788 runtime you can physically add extra cpu until it reaches
3789 n. So during boot up some boot time memory for per-cpu
3790 variables need be pre-allocated for later physical cpu
3793 nr_uarts= [SERIAL] maximum number of UARTs to be registered.
3795 numa=off [KNL, ARM64, PPC, RISCV, SPARC, X86] Disable NUMA, Only
3796 set up a single NUMA node spanning all memory.
3798 numa_balancing= [KNL,ARM64,PPC,RISCV,S390,X86] Enable or disable automatic
3800 Allowed values are enable and disable
3802 numa_zonelist_order= [KNL, BOOT] Select zonelist order for NUMA.
3803 'node', 'default' can be specified
3804 This can be set from sysctl after boot.
3805 See Documentation/admin-guide/sysctl/vm.rst for details.
3807 ohci1394_dma=early [HW] enable debugging via the ohci1394 driver.
3808 See Documentation/core-api/debugging-via-ohci1394.rst for more
3811 olpc_ec_timeout= [OLPC] ms delay when issuing EC commands
3812 Rather than timing out after 20 ms if an EC
3813 command is not properly ACKed, override the length
3814 of the timeout. We have interrupts disabled while
3815 waiting for the ACK, so if this is set too high
3816 interrupts *may* be lost!
3818 omap_mux= [OMAP] Override bootloader pin multiplexing.
3819 Format: <mux_mode0.mode_name=value>...
3820 For example, to override I2C bus2:
3821 omap_mux=i2c2_scl.i2c2_scl=0x100,i2c2_sda.i2c2_sda=0x100
3823 onenand.bdry= [HW,MTD] Flex-OneNAND Boundary Configuration
3825 Format: [die0_boundary][,die0_lock][,die1_boundary][,die1_lock]
3827 boundary - index of last SLC block on Flex-OneNAND.
3828 The remaining blocks are configured as MLC blocks.
3829 lock - Configure if Flex-OneNAND boundary should be locked.
3830 Once locked, the boundary cannot be changed.
3831 1 indicates lock status, 0 indicates unlock status.
3833 oops=panic Always panic on oopses. Default is to just kill the
3834 process, but there is a small probability of
3835 deadlocking the machine.
3836 This will also cause panics on machine check exceptions.
3837 Useful together with panic=30 to trigger a reboot.
3840 [KNL] Boolean flag to control whether the page allocator
3841 should randomize its free lists. The randomization may
3842 be automatically enabled if the kernel detects it is
3843 running on a platform with a direct-mapped memory-side
3844 cache, and this parameter can be used to
3845 override/disable that behavior. The state of the flag
3846 can be read from sysfs at:
3847 /sys/module/page_alloc/parameters/shuffle.
3849 page_owner= [KNL] Boot-time page_owner enabling option.
3850 Storage of the information about who allocated
3851 each page is disabled in default. With this switch,
3853 on: enable the feature
3855 page_poison= [KNL] Boot-time parameter changing the state of
3856 poisoning on the buddy allocator, available with
3857 CONFIG_PAGE_POISONING=y.
3858 off: turn off poisoning (default)
3859 on: turn on poisoning
3861 page_reporting.page_reporting_order=
3862 [KNL] Minimal page reporting order
3864 Adjust the minimal page reporting order. The page
3865 reporting is disabled when it exceeds (MAX_ORDER-1).
3867 panic= [KNL] Kernel behaviour on panic: delay <timeout>
3868 timeout > 0: seconds before rebooting
3869 timeout = 0: wait forever
3870 timeout < 0: reboot immediately
3873 panic_print= Bitmask for printing system info when panic happens.
3874 User can chose combination of the following bits:
3875 bit 0: print all tasks info
3876 bit 1: print system memory info
3877 bit 2: print timer info
3878 bit 3: print locks info if CONFIG_LOCKDEP is on
3879 bit 4: print ftrace buffer
3880 bit 5: print all printk messages in buffer
3881 bit 6: print all CPUs backtrace (if available in the arch)
3882 *Be aware* that this option may print a _lot_ of lines,
3883 so there are risks of losing older messages in the log.
3884 Use this option carefully, maybe worth to setup a
3885 bigger log buffer with "log_buf_len" along with this.
3887 panic_on_taint= Bitmask for conditionally calling panic() in add_taint()
3888 Format: <hex>[,nousertaint]
3889 Hexadecimal bitmask representing the set of TAINT flags
3890 that will cause the kernel to panic when add_taint() is
3891 called with any of the flags in this set.
3892 The optional switch "nousertaint" can be utilized to
3893 prevent userspace forced crashes by writing to sysctl
3894 /proc/sys/kernel/tainted any flagset matching with the
3895 bitmask set on panic_on_taint.
3896 See Documentation/admin-guide/tainted-kernels.rst for
3897 extra details on the taint flags that users can pick
3898 to compose the bitmask to assign to panic_on_taint.
3900 panic_on_warn panic() instead of WARN(). Useful to cause kdump
3903 parkbd.port= [HW] Parallel port number the keyboard adapter is
3904 connected to, default is 0.
3906 parkbd.mode= [HW] Parallel port keyboard adapter mode of operation,
3907 0 for XT, 1 for AT (default is AT).
3910 parport= [HW,PPT] Specify parallel ports. 0 disables.
3911 Format: { 0 | auto | 0xBBB[,IRQ[,DMA]] }
3912 Use 'auto' to force the driver to use any
3913 IRQ/DMA settings detected (the default is to
3914 ignore detected IRQ/DMA settings because of
3915 possible conflicts). You can specify the base
3916 address, IRQ, and DMA settings; IRQ and DMA
3917 should be numbers, or 'auto' (for using detected
3918 settings on that particular port), or 'nofifo'
3919 (to avoid using a FIFO even if it is detected).
3920 Parallel ports are assigned in the order they
3921 are specified on the command line, starting
3924 parport_init_mode= [HW,PPT]
3925 Configure VIA parallel port to operate in
3926 a specific mode. This is necessary on Pegasos
3927 computer where firmware has no options for setting
3928 up parallel port mode and sets it to spp.
3929 Currently this function knows 686a and 8231 chips.
3930 Format: [spp|ps2|epp|ecp|ecpepp]
3932 pata_legacy.all= [HW,LIBATA]
3934 Set to non-zero to probe primary and secondary ISA
3935 port ranges on PCI systems where no PCI PATA device
3936 has been found at either range. Disabled by default.
3938 pata_legacy.autospeed= [HW,LIBATA]
3940 Set to non-zero if a chip is present that snoops speed
3941 changes. Disabled by default.
3943 pata_legacy.ht6560a= [HW,LIBATA]
3945 Set to 1, 2, or 3 for HT 6560A on the primary channel,
3946 the secondary channel, or both channels respectively.
3947 Disabled by default.
3949 pata_legacy.ht6560b= [HW,LIBATA]
3951 Set to 1, 2, or 3 for HT 6560B on the primary channel,
3952 the secondary channel, or both channels respectively.
3953 Disabled by default.
3955 pata_legacy.iordy_mask= [HW,LIBATA]
3957 IORDY enable mask. Set individual bits to allow IORDY
3958 for the respective channel. Bit 0 is for the first
3959 legacy channel handled by this driver, bit 1 is for
3960 the second channel, and so on. The sequence will often
3961 correspond to the primary legacy channel, the secondary
3962 legacy channel, and so on, but the handling of a PCI
3963 bus and the use of other driver options may interfere
3964 with the sequence. By default IORDY is allowed across
3967 pata_legacy.opti82c46x= [HW,LIBATA]
3969 Set to 1, 2, or 3 for Opti 82c611A on the primary
3970 channel, the secondary channel, or both channels
3971 respectively. Disabled by default.
3973 pata_legacy.opti82c611a= [HW,LIBATA]
3975 Set to 1, 2, or 3 for Opti 82c465MV on the primary
3976 channel, the secondary channel, or both channels
3977 respectively. Disabled by default.
3979 pata_legacy.pio_mask= [HW,LIBATA]
3981 PIO mode mask for autospeed devices. Set individual
3982 bits to allow the use of the respective PIO modes.
3983 Bit 0 is for mode 0, bit 1 is for mode 1, and so on.
3984 All modes allowed by default.
3986 pata_legacy.probe_all= [HW,LIBATA]
3988 Set to non-zero to probe tertiary and further ISA
3989 port ranges on PCI systems. Disabled by default.
3991 pata_legacy.probe_mask= [HW,LIBATA]
3993 Probe mask for legacy ISA PATA ports. Depending on
3994 platform configuration and the use of other driver
3995 options up to 6 legacy ports are supported: 0x1f0,
3996 0x170, 0x1e8, 0x168, 0x1e0, 0x160, however probing
3997 of individual ports can be disabled by setting the
3998 corresponding bits in the mask to 1. Bit 0 is for
3999 the first port in the list above (0x1f0), and so on.
4000 By default all supported ports are probed.
4002 pata_legacy.qdi= [HW,LIBATA]
4004 Set to non-zero to probe QDI controllers. By default
4005 set to 1 if CONFIG_PATA_QDI_MODULE, 0 otherwise.
4007 pata_legacy.winbond= [HW,LIBATA]
4009 Set to non-zero to probe Winbond controllers. Use
4010 the standard I/O port (0x130) if 1, otherwise the
4011 value given is the I/O port to use (typically 0x1b0).
4012 By default set to 1 if CONFIG_PATA_WINBOND_VLB_MODULE,
4015 pata_platform.pio_mask= [HW,LIBATA]
4017 Supported PIO mode mask. Set individual bits to allow
4018 the use of the respective PIO modes. Bit 0 is for
4019 mode 0, bit 1 is for mode 1, and so on. Mode 0 only
4023 Halt all CPUs after the first oops has been printed for
4024 the specified number of seconds. This is to be used if
4025 your oopses keep scrolling off the screen.
4030 See header of drivers/block/paride/pcd.c.
4031 See also Documentation/admin-guide/blockdev/paride.rst.
4033 pci=option[,option...] [PCI] various PCI subsystem options.
4035 Some options herein operate on a specific device
4036 or a set of devices (<pci_dev>). These are
4037 specified in one of the following formats:
4039 [<domain>:]<bus>:<dev>.<func>[/<dev>.<func>]*
4040 pci:<vendor>:<device>[:<subvendor>:<subdevice>]
4042 Note: the first format specifies a PCI
4043 bus/device/function address which may change
4044 if new hardware is inserted, if motherboard
4045 firmware changes, or due to changes caused
4046 by other kernel parameters. If the
4047 domain is left unspecified, it is
4048 taken to be zero. Optionally, a path
4049 to a device through multiple device/function
4050 addresses can be specified after the base
4051 address (this is more robust against
4052 renumbering issues). The second format
4053 selects devices using IDs from the
4054 configuration space which may match multiple
4055 devices in the system.
4057 earlydump dump PCI config space before the kernel
4059 off [X86] don't probe for the PCI bus
4060 bios [X86-32] force use of PCI BIOS, don't access
4061 the hardware directly. Use this if your machine
4062 has a non-standard PCI host bridge.
4063 nobios [X86-32] disallow use of PCI BIOS, only direct
4064 hardware access methods are allowed. Use this
4065 if you experience crashes upon bootup and you
4066 suspect they are caused by the BIOS.
4067 conf1 [X86] Force use of PCI Configuration Access
4068 Mechanism 1 (config address in IO port 0xCF8,
4069 data in IO port 0xCFC, both 32-bit).
4070 conf2 [X86] Force use of PCI Configuration Access
4071 Mechanism 2 (IO port 0xCF8 is an 8-bit port for
4072 the function, IO port 0xCFA, also 8-bit, sets
4073 bus number. The config space is then accessed
4074 through ports 0xC000-0xCFFF).
4075 See http://wiki.osdev.org/PCI for more info
4076 on the configuration access mechanisms.
4077 noaer [PCIE] If the PCIEAER kernel config parameter is
4078 enabled, this kernel boot option can be used to
4079 disable the use of PCIE advanced error reporting.
4080 nodomains [PCI] Disable support for multiple PCI
4081 root domains (aka PCI segments, in ACPI-speak).
4082 nommconf [X86] Disable use of MMCONFIG for PCI
4084 check_enable_amd_mmconf [X86] check for and enable
4085 properly configured MMIO access to PCI
4086 config space on AMD family 10h CPU
4087 nomsi [MSI] If the PCI_MSI kernel config parameter is
4088 enabled, this kernel boot option can be used to
4089 disable the use of MSI interrupts system-wide.
4090 noioapicquirk [APIC] Disable all boot interrupt quirks.
4091 Safety option to keep boot IRQs enabled. This
4092 should never be necessary.
4093 ioapicreroute [APIC] Enable rerouting of boot IRQs to the
4094 primary IO-APIC for bridges that cannot disable
4095 boot IRQs. This fixes a source of spurious IRQs
4096 when the system masks IRQs.
4097 noioapicreroute [APIC] Disable workaround that uses the
4098 boot IRQ equivalent of an IRQ that connects to
4099 a chipset where boot IRQs cannot be disabled.
4100 The opposite of ioapicreroute.
4101 biosirq [X86-32] Use PCI BIOS calls to get the interrupt
4102 routing table. These calls are known to be buggy
4103 on several machines and they hang the machine
4104 when used, but on other computers it's the only
4105 way to get the interrupt routing table. Try
4106 this option if the kernel is unable to allocate
4107 IRQs or discover secondary PCI buses on your
4109 rom [X86] Assign address space to expansion ROMs.
4110 Use with caution as certain devices share
4111 address decoders between ROMs and other
4113 norom [X86] Do not assign address space to
4114 expansion ROMs that do not already have
4115 BIOS assigned address ranges.
4116 nobar [X86] Do not assign address space to the
4117 BARs that weren't assigned by the BIOS.
4118 irqmask=0xMMMM [X86] Set a bit mask of IRQs allowed to be
4119 assigned automatically to PCI devices. You can
4120 make the kernel exclude IRQs of your ISA cards
4122 pirqaddr=0xAAAAA [X86] Specify the physical address
4123 of the PIRQ table (normally generated
4124 by the BIOS) if it is outside the
4125 F0000h-100000h range.
4126 lastbus=N [X86] Scan all buses thru bus #N. Can be
4127 useful if the kernel is unable to find your
4128 secondary buses and you want to tell it
4129 explicitly which ones they are.
4130 assign-busses [X86] Always assign all PCI bus
4131 numbers ourselves, overriding
4132 whatever the firmware may have done.
4133 usepirqmask [X86] Honor the possible IRQ mask stored
4134 in the BIOS $PIR table. This is needed on
4135 some systems with broken BIOSes, notably
4136 some HP Pavilion N5400 and Omnibook XE3
4137 notebooks. This will have no effect if ACPI
4138 IRQ routing is enabled.
4139 noacpi [X86] Do not use ACPI for IRQ routing
4140 or for PCI scanning.
4141 use_crs [X86] Use PCI host bridge window information
4142 from ACPI. On BIOSes from 2008 or later, this
4143 is enabled by default. If you need to use this,
4144 please report a bug.
4145 nocrs [X86] Ignore PCI host bridge windows from ACPI.
4146 If you need to use this, please report a bug.
4147 use_e820 [X86] Use E820 reservations to exclude parts of
4148 PCI host bridge windows. This is a workaround
4149 for BIOS defects in host bridge _CRS methods.
4150 If you need to use this, please report a bug to
4151 <linux-pci@vger.kernel.org>.
4152 no_e820 [X86] Ignore E820 reservations for PCI host
4153 bridge windows. This is the default on modern
4154 hardware. If you need to use this, please report
4155 a bug to <linux-pci@vger.kernel.org>.
4156 routeirq Do IRQ routing for all PCI devices.
4157 This is normally done in pci_enable_device(),
4158 so this option is a temporary workaround
4159 for broken drivers that don't call it.
4160 skip_isa_align [X86] do not align io start addr, so can
4161 handle more pci cards
4162 noearly [X86] Don't do any early type 1 scanning.
4163 This might help on some broken boards which
4164 machine check when some devices' config space
4165 is read. But various workarounds are disabled
4166 and some IOMMU drivers will not work.
4167 bfsort Sort PCI devices into breadth-first order.
4168 This sorting is done to get a device
4169 order compatible with older (<= 2.4) kernels.
4170 nobfsort Don't sort PCI devices into breadth-first order.
4171 pcie_bus_tune_off Disable PCIe MPS (Max Payload Size)
4172 tuning and use the BIOS-configured MPS defaults.
4173 pcie_bus_safe Set every device's MPS to the largest value
4174 supported by all devices below the root complex.
4175 pcie_bus_perf Set device MPS to the largest allowable MPS
4176 based on its parent bus. Also set MRRS (Max
4177 Read Request Size) to the largest supported
4178 value (no larger than the MPS that the device
4179 or bus can support) for best performance.
4180 pcie_bus_peer2peer Set every device's MPS to 128B, which
4181 every device is guaranteed to support. This
4182 configuration allows peer-to-peer DMA between
4183 any pair of devices, possibly at the cost of
4184 reduced performance. This also guarantees
4185 that hot-added devices will work.
4186 cbiosize=nn[KMG] The fixed amount of bus space which is
4187 reserved for the CardBus bridge's IO window.
4188 The default value is 256 bytes.
4189 cbmemsize=nn[KMG] The fixed amount of bus space which is
4190 reserved for the CardBus bridge's memory
4191 window. The default value is 64 megabytes.
4194 [<order of align>@]<pci_dev>[; ...]
4195 Specifies alignment and device to reassign
4196 aligned memory resources. How to
4197 specify the device is described above.
4198 If <order of align> is not specified,
4199 PAGE_SIZE is used as alignment.
4200 A PCI-PCI bridge can be specified if resource
4201 windows need to be expanded.
4202 To specify the alignment for several
4203 instances of a device, the PCI vendor,
4204 device, subvendor, and subdevice may be
4205 specified, e.g., 12@pci:8086:9c22:103c:198f
4206 for 4096-byte alignment.
4207 ecrc= Enable/disable PCIe ECRC (transaction layer
4208 end-to-end CRC checking).
4209 bios: Use BIOS/firmware settings. This is the
4213 hpiosize=nn[KMG] The fixed amount of bus space which is
4214 reserved for hotplug bridge's IO window.
4215 Default size is 256 bytes.
4216 hpmmiosize=nn[KMG] The fixed amount of bus space which is
4217 reserved for hotplug bridge's MMIO window.
4218 Default size is 2 megabytes.
4219 hpmmioprefsize=nn[KMG] The fixed amount of bus space which is
4220 reserved for hotplug bridge's MMIO_PREF window.
4221 Default size is 2 megabytes.
4222 hpmemsize=nn[KMG] The fixed amount of bus space which is
4223 reserved for hotplug bridge's MMIO and
4225 Default size is 2 megabytes.
4226 hpbussize=nn The minimum amount of additional bus numbers
4227 reserved for buses below a hotplug bridge.
4229 realloc= Enable/disable reallocating PCI bridge resources
4230 if allocations done by BIOS are too small to
4231 accommodate resources required by all child
4233 off: Turn realloc off
4235 realloc same as realloc=on
4236 noari do not use PCIe ARI.
4237 noats [PCIE, Intel-IOMMU, AMD-IOMMU]
4238 do not use PCIe ATS (and IOMMU device IOTLB).
4239 pcie_scan_all Scan all possible PCIe devices. Otherwise we
4240 only look for one device below a PCIe downstream
4242 big_root_window Try to add a big 64bit memory window to the PCIe
4243 root complex on AMD CPUs. Some GFX hardware
4244 can resize a BAR to allow access to all VRAM.
4245 Adding the window is slightly risky (it may
4246 conflict with unreported devices), so this
4248 disable_acs_redir=<pci_dev>[; ...]
4249 Specify one or more PCI devices (in the format
4250 specified above) separated by semicolons.
4251 Each device specified will have the PCI ACS
4252 redirect capabilities forced off which will
4253 allow P2P traffic between devices through
4254 bridges without forcing it upstream. Note:
4255 this removes isolation between devices and
4256 may put more devices in an IOMMU group.
4257 force_floating [S390] Force usage of floating interrupts.
4258 nomio [S390] Do not use MIO instructions.
4259 norid [S390] ignore the RID field and force use of
4260 one PCI domain per PCI function
4262 pcie_aspm= [PCIE] Forcibly enable or disable PCIe Active State Power
4265 force Enable ASPM even on devices that claim not to support it.
4266 WARNING: Forcing ASPM on may cause system lockups.
4268 pcie_ports= [PCIE] PCIe port services handling:
4269 native Use native PCIe services (PME, AER, DPC, PCIe hotplug)
4270 even if the platform doesn't give the OS permission to
4271 use them. This may cause conflicts if the platform
4272 also tries to use these services.
4273 dpc-native Use native PCIe service for DPC only. May
4274 cause conflicts if firmware uses AER or DPC.
4275 compat Disable native PCIe services (PME, AER, DPC, PCIe
4278 pcie_port_pm= [PCIE] PCIe port power management handling:
4279 off Disable power management of all PCIe ports
4280 force Forcibly enable power management of all PCIe ports
4282 pcie_pme= [PCIE,PM] Native PCIe PME signaling options:
4283 nomsi Do not use MSI for native PCIe PME signaling (this makes
4284 all PCIe root ports use INTx for all services).
4286 pcmv= [HW,PCMCIA] BadgePAD 4
4290 Keep all power-domains already enabled by bootloader on,
4291 even if no driver has claimed them. This is useful
4292 for debug and development, but should not be
4293 needed on a platform with proper driver support.
4296 See Documentation/admin-guide/blockdev/paride.rst.
4298 pdcchassis= [PARISC,HW] Disable/Enable PDC Chassis Status codes at
4301 See arch/parisc/kernel/pdc_chassis.c
4303 percpu_alloc= Select which percpu first chunk allocator to use.
4304 Currently supported values are "embed" and "page".
4305 Archs may support subset or none of the selections.
4306 See comments in mm/percpu.c for details on each
4307 allocator. This parameter is primarily for debugging
4308 and performance comparison.
4311 See Documentation/admin-guide/blockdev/paride.rst.
4314 See Documentation/admin-guide/blockdev/paride.rst.
4316 pirq= [SMP,APIC] Manual mp-table setup
4317 See Documentation/x86/i386/IO-APIC.rst.
4319 plip= [PPT,NET] Parallel port network link
4320 Format: { parport<nr> | timid | 0 }
4321 See also Documentation/admin-guide/parport.rst.
4323 pmtmr= [X86] Manual setup of pmtmr I/O Port.
4324 Override pmtimer IOPort with a hex value.
4327 pmu_override= [PPC] Override the PMU.
4328 This option takes over the PMU facility, so it is no
4329 longer usable by perf. Setting this option starts the
4330 PMU counters by setting MMCR0 to 0 (the FC bit is
4331 cleared). If a number is given, then MMCR1 is set to
4332 that number, otherwise (e.g., 'pmu_override=on'), MMCR1
4335 pm_debug_messages [SUSPEND,KNL]
4336 Enable suspend/resume debug messages during boot up.
4339 Enable PNP debug messages (depends on the
4340 CONFIG_PNP_DEBUG_MESSAGES option). Change at run-time
4341 via /sys/module/pnp/parameters/debug. We always show
4342 current resource usage; turning this on also shows
4343 possible settings and some assignment information.
4349 { on | off | curr | res | no-curr | no-res }
4352 [ISAPNP] Exclude IRQs for the autoconfiguration
4355 [ISAPNP] Exclude DMAs for the autoconfiguration
4357 pnp_reserve_io= [ISAPNP] Exclude I/O ports for the autoconfiguration
4358 Ranges are in pairs (I/O port base and size).
4361 [ISAPNP] Exclude memory regions for the
4363 Ranges are in pairs (memory base and size).
4365 ports= [IP_VS_FTP] IPVS ftp helper module
4367 Up to 8 (IP_VS_APP_MAX_PORTS) ports
4369 Format: <port>,<port>....
4371 powersave=off [PPC] This option disables power saving features.
4372 It specifically disables cpuidle and sets the
4373 platform machine description specific power_save
4374 function to NULL. On Idle the CPU just reduces
4377 ppc_strict_facility_enable
4378 [PPC] This option catches any kernel floating point,
4379 Altivec, VSX and SPE outside of regions specifically
4380 allowed (eg kernel_enable_fpu()/kernel_disable_fpu()).
4381 There is some performance impact when enabling this.
4385 Disable Hardware Transactional Memory
4388 Select preemption mode if you have CONFIG_PREEMPT_DYNAMIC
4389 none - Limited to cond_resched() calls
4390 voluntary - Limited to cond_resched() and might_sleep() calls
4391 full - Any section that isn't explicitly preempt disabled
4392 can be preempted anytime.
4394 print-fatal-signals=
4395 [KNL] debug: print fatal signals
4397 If enabled, warn about various signal handling
4398 related application anomalies: too many signals,
4399 too many POSIX.1 timers, fatal signals causing a
4402 If you hit the warning due to signal overflow,
4403 you might want to try "ulimit -i unlimited".
4407 printk.always_kmsg_dump=
4408 Trigger kmsg_dump for cases other than kernel oops or
4410 Format: <bool> (1/Y/y=enable, 0/N/n=disable)
4413 printk.console_no_auto_verbose=
4414 Disable console loglevel raise on oops, panic
4415 or lockdep-detected issues (only if lock debug is on).
4416 With an exception to setups with low baudrate on
4417 serial console, keeping this 0 is a good choice
4418 in order to provide more debug information.
4420 default: 0 (auto_verbose is enabled)
4422 printk.devkmsg={on,off,ratelimit}
4423 Control writing to /dev/kmsg.
4424 on - unlimited logging to /dev/kmsg from userspace
4425 off - logging to /dev/kmsg disabled
4426 ratelimit - ratelimit the logging
4429 printk.time= Show timing data prefixed to each printk message line
4430 Format: <bool> (1/Y/y=enable, 0/N/n=disable)
4432 processor.max_cstate= [HW,ACPI]
4433 Limit processor to maximum C-state
4434 max_cstate=9 overrides any DMI blacklist limit.
4436 processor.nocst [HW,ACPI]
4437 Ignore the _CST method to determine C-states,
4438 instead using the legacy FADT method
4440 profile= [KNL] Enable kernel profiling via /proc/profile
4441 Format: [<profiletype>,]<number>
4442 Param: <profiletype>: "schedule", "sleep", or "kvm"
4443 [defaults to kernel profiling]
4444 Param: "schedule" - profile schedule points.
4445 Param: "sleep" - profile D-state sleeping (millisecs).
4446 Requires CONFIG_SCHEDSTATS
4447 Param: "kvm" - profile VM exits.
4448 Param: <number> - step/bucket size as a power of 2 for
4449 statistical time based profiling.
4451 prompt_ramdisk= [RAM] [Deprecated]
4453 prot_virt= [S390] enable hosting protected virtual machines
4454 isolated from the hypervisor (if hardware supports
4458 psi= [KNL] Enable or disable pressure stall information
4462 psmouse.proto= [HW,MOUSE] Highest PS2 mouse protocol extension to
4463 probe for; one of (bare|imps|exps|lifebook|any).
4464 psmouse.rate= [HW,MOUSE] Set desired mouse report rate, in reports
4466 psmouse.resetafter= [HW,MOUSE]
4467 Try to reset the device after so many bad packets
4470 [HW,MOUSE] Set desired mouse resolution, in dpi.
4471 psmouse.smartscroll=
4472 [HW,MOUSE] Controls Logitech smartscroll autorepeat.
4473 0 = disabled, 1 = enabled (default).
4475 pstore.backend= Specify the name of the pstore backend to use
4478 See Documentation/admin-guide/blockdev/paride.rst.
4480 pti= [X86-64] Control Page Table Isolation of user and
4481 kernel address spaces. Disabling this feature
4482 removes hardening, but improves performance of
4483 system calls and interrupts.
4485 on - unconditionally enable
4486 off - unconditionally disable
4487 auto - kernel detects whether your CPU model is
4488 vulnerable to issues that PTI mitigates
4490 Not specifying this option is equivalent to pti=auto.
4493 Equivalent to pti=off
4496 [KNL] Number of legacy pty's. Overwrites compiled-in
4499 quiet [KNL] Disable most log messages
4504 See Documentation/admin-guide/md.rst.
4506 ramdisk_size= [RAM] Sizes of RAM disks in kilobytes
4507 See Documentation/admin-guide/blockdev/ramdisk.rst.
4509 ramdisk_start= [RAM] RAM disk image start address
4511 random.trust_cpu={on,off}
4512 [KNL] Enable or disable trusting the use of the
4513 CPU's random number generator (if available) to
4514 fully seed the kernel's CRNG. Default is controlled
4515 by CONFIG_RANDOM_TRUST_CPU.
4517 random.trust_bootloader={on,off}
4518 [KNL] Enable or disable trusting the use of a
4519 seed passed by the bootloader (if available) to
4520 fully seed the kernel's CRNG. Default is controlled
4521 by CONFIG_RANDOM_TRUST_BOOTLOADER.
4523 randomize_kstack_offset=
4524 [KNL] Enable or disable kernel stack offset
4525 randomization, which provides roughly 5 bits of
4526 entropy, frustrating memory corruption attacks
4527 that depend on stack address determinism or
4528 cross-syscall address exposures. This is only
4529 available on architectures that have defined
4530 CONFIG_HAVE_ARCH_RANDOMIZE_KSTACK_OFFSET.
4531 Format: <bool> (1/Y/y=enable, 0/N/n=disable)
4532 Default is CONFIG_RANDOMIZE_KSTACK_OFFSET_DEFAULT.
4534 ras=option[,option,...] [KNL] RAS-specific options
4537 Disable the Correctable Errors Collector,
4538 see CONFIG_RAS_CEC help text.
4540 rcu_nocbs[=cpu-list]
4541 [KNL] The optional argument is a cpu list,
4544 In kernels built with CONFIG_RCU_NOCB_CPU=y,
4545 enable the no-callback CPU mode, which prevents
4546 such CPUs' callbacks from being invoked in
4547 softirq context. Invocation of such CPUs' RCU
4548 callbacks will instead be offloaded to "rcuox/N"
4549 kthreads created for that purpose, where "x" is
4550 "p" for RCU-preempt, "s" for RCU-sched, and "g"
4551 for the kthreads that mediate grace periods; and
4552 "N" is the CPU number. This reduces OS jitter on
4553 the offloaded CPUs, which can be useful for HPC
4554 and real-time workloads. It can also improve
4555 energy efficiency for asymmetric multiprocessors.
4557 If a cpulist is passed as an argument, the specified
4558 list of CPUs is set to no-callback mode from boot.
4560 Otherwise, if the '=' sign and the cpulist
4561 arguments are omitted, no CPU will be set to
4562 no-callback mode from boot but the mode may be
4563 toggled at runtime via cpusets.
4565 Note that this argument takes precedence over
4566 the CONFIG_RCU_NOCB_CPU_DEFAULT_ALL option.
4569 Rather than requiring that offloaded CPUs
4570 (specified by rcu_nocbs= above) explicitly
4571 awaken the corresponding "rcuoN" kthreads,
4572 make these kthreads poll for callbacks.
4573 This improves the real-time response for the
4574 offloaded CPUs by relieving them of the need to
4575 wake up the corresponding kthread, but degrades
4576 energy efficiency by requiring that the kthreads
4577 periodically wake up to do the polling.
4579 rcutree.blimit= [KNL]
4580 Set maximum number of finished RCU callbacks to
4581 process in one batch.
4583 rcutree.dump_tree= [KNL]
4584 Dump the structure of the rcu_node combining tree
4585 out at early boot. This is used for diagnostic
4586 purposes, to verify correct tree setup.
4588 rcutree.gp_cleanup_delay= [KNL]
4589 Set the number of jiffies to delay each step of
4590 RCU grace-period cleanup.
4592 rcutree.gp_init_delay= [KNL]
4593 Set the number of jiffies to delay each step of
4594 RCU grace-period initialization.
4596 rcutree.gp_preinit_delay= [KNL]
4597 Set the number of jiffies to delay each step of
4598 RCU grace-period pre-initialization, that is,
4599 the propagation of recent CPU-hotplug changes up
4600 the rcu_node combining tree.
4602 rcutree.use_softirq= [KNL]
4603 If set to zero, move all RCU_SOFTIRQ processing to
4604 per-CPU rcuc kthreads. Defaults to a non-zero
4605 value, meaning that RCU_SOFTIRQ is used by default.
4606 Specify rcutree.use_softirq=0 to use rcuc kthreads.
4608 But note that CONFIG_PREEMPT_RT=y kernels disable
4609 this kernel boot parameter, forcibly setting it
4612 rcutree.rcu_fanout_exact= [KNL]
4613 Disable autobalancing of the rcu_node combining
4614 tree. This is used by rcutorture, and might
4615 possibly be useful for architectures having high
4616 cache-to-cache transfer latencies.
4618 rcutree.rcu_fanout_leaf= [KNL]
4619 Change the number of CPUs assigned to each
4620 leaf rcu_node structure. Useful for very
4621 large systems, which will choose the value 64,
4622 and for NUMA systems with large remote-access
4623 latencies, which will choose a value aligned
4624 with the appropriate hardware boundaries.
4626 rcutree.rcu_min_cached_objs= [KNL]
4627 Minimum number of objects which are cached and
4628 maintained per one CPU. Object size is equal
4629 to PAGE_SIZE. The cache allows to reduce the
4630 pressure to page allocator, also it makes the
4631 whole algorithm to behave better in low memory
4634 rcutree.rcu_delay_page_cache_fill_msec= [KNL]
4635 Set the page-cache refill delay (in milliseconds)
4636 in response to low-memory conditions. The range
4637 of permitted values is in the range 0:100000.
4639 rcutree.jiffies_till_first_fqs= [KNL]
4640 Set delay from grace-period initialization to
4641 first attempt to force quiescent states.
4642 Units are jiffies, minimum value is zero,
4643 and maximum value is HZ.
4645 rcutree.jiffies_till_next_fqs= [KNL]
4646 Set delay between subsequent attempts to force
4647 quiescent states. Units are jiffies, minimum
4648 value is one, and maximum value is HZ.
4650 rcutree.jiffies_till_sched_qs= [KNL]
4651 Set required age in jiffies for a
4652 given grace period before RCU starts
4653 soliciting quiescent-state help from
4654 rcu_note_context_switch() and cond_resched().
4655 If not specified, the kernel will calculate
4656 a value based on the most recent settings
4657 of rcutree.jiffies_till_first_fqs
4658 and rcutree.jiffies_till_next_fqs.
4659 This calculated value may be viewed in
4660 rcutree.jiffies_to_sched_qs. Any attempt to set
4661 rcutree.jiffies_to_sched_qs will be cheerfully
4664 rcutree.kthread_prio= [KNL,BOOT]
4665 Set the SCHED_FIFO priority of the RCU per-CPU
4666 kthreads (rcuc/N). This value is also used for
4667 the priority of the RCU boost threads (rcub/N)
4668 and for the RCU grace-period kthreads (rcu_bh,
4669 rcu_preempt, and rcu_sched). If RCU_BOOST is
4670 set, valid values are 1-99 and the default is 1
4671 (the least-favored priority). Otherwise, when
4672 RCU_BOOST is not set, valid values are 0-99 and
4673 the default is zero (non-realtime operation).
4674 When RCU_NOCB_CPU is set, also adjust the
4675 priority of NOCB callback kthreads.
4677 rcutree.rcu_divisor= [KNL]
4678 Set the shift-right count to use to compute
4679 the callback-invocation batch limit bl from
4680 the number of callbacks queued on this CPU.
4681 The result will be bounded below by the value of
4682 the rcutree.blimit kernel parameter. Every bl
4683 callbacks, the softirq handler will exit in
4684 order to allow the CPU to do other work.
4686 Please note that this callback-invocation batch
4687 limit applies only to non-offloaded callback
4688 invocation. Offloaded callbacks are instead
4689 invoked in the context of an rcuoc kthread, which
4690 scheduler will preempt as it does any other task.
4692 rcutree.nocb_nobypass_lim_per_jiffy= [KNL]
4693 On callback-offloaded (rcu_nocbs) CPUs,
4694 RCU reduces the lock contention that would
4695 otherwise be caused by callback floods through
4696 use of the ->nocb_bypass list. However, in the
4697 common non-flooded case, RCU queues directly to
4698 the main ->cblist in order to avoid the extra
4699 overhead of the ->nocb_bypass list and its lock.
4700 But if there are too many callbacks queued during
4701 a single jiffy, RCU pre-queues the callbacks into
4702 the ->nocb_bypass queue. The definition of "too
4703 many" is supplied by this kernel boot parameter.
4705 rcutree.rcu_nocb_gp_stride= [KNL]
4706 Set the number of NOCB callback kthreads in
4707 each group, which defaults to the square root
4708 of the number of CPUs. Larger numbers reduce
4709 the wakeup overhead on the global grace-period
4710 kthread, but increases that same overhead on
4711 each group's NOCB grace-period kthread.
4713 rcutree.qhimark= [KNL]
4714 Set threshold of queued RCU callbacks beyond which
4715 batch limiting is disabled.
4717 rcutree.qlowmark= [KNL]
4718 Set threshold of queued RCU callbacks below which
4719 batch limiting is re-enabled.
4721 rcutree.qovld= [KNL]
4722 Set threshold of queued RCU callbacks beyond which
4723 RCU's force-quiescent-state scan will aggressively
4724 enlist help from cond_resched() and sched IPIs to
4725 help CPUs more quickly reach quiescent states.
4726 Set to less than zero to make this be set based
4727 on rcutree.qhimark at boot time and to zero to
4728 disable more aggressive help enlistment.
4730 rcutree.rcu_kick_kthreads= [KNL]
4731 Cause the grace-period kthread to get an extra
4732 wake_up() if it sleeps three times longer than
4733 it should at force-quiescent-state time.
4734 This wake_up() will be accompanied by a
4735 WARN_ONCE() splat and an ftrace_dump().
4737 rcutree.rcu_unlock_delay= [KNL]
4738 In CONFIG_RCU_STRICT_GRACE_PERIOD=y kernels,
4739 this specifies an rcu_read_unlock()-time delay
4740 in microseconds. This defaults to zero.
4741 Larger delays increase the probability of
4742 catching RCU pointer leaks, that is, buggy use
4743 of RCU-protected pointers after the relevant
4744 rcu_read_unlock() has completed.
4746 rcutree.sysrq_rcu= [KNL]
4747 Commandeer a sysrq key to dump out Tree RCU's
4748 rcu_node tree with an eye towards determining
4749 why a new grace period has not yet started.
4751 rcuscale.gp_async= [KNL]
4752 Measure performance of asynchronous
4753 grace-period primitives such as call_rcu().
4755 rcuscale.gp_async_max= [KNL]
4756 Specify the maximum number of outstanding
4757 callbacks per writer thread. When a writer
4758 thread exceeds this limit, it invokes the
4759 corresponding flavor of rcu_barrier() to allow
4760 previously posted callbacks to drain.
4762 rcuscale.gp_exp= [KNL]
4763 Measure performance of expedited synchronous
4764 grace-period primitives.
4766 rcuscale.holdoff= [KNL]
4767 Set test-start holdoff period. The purpose of
4768 this parameter is to delay the start of the
4769 test until boot completes in order to avoid
4772 rcuscale.kfree_rcu_test= [KNL]
4773 Set to measure performance of kfree_rcu() flooding.
4775 rcuscale.kfree_rcu_test_double= [KNL]
4776 Test the double-argument variant of kfree_rcu().
4777 If this parameter has the same value as
4778 rcuscale.kfree_rcu_test_single, both the single-
4779 and double-argument variants are tested.
4781 rcuscale.kfree_rcu_test_single= [KNL]
4782 Test the single-argument variant of kfree_rcu().
4783 If this parameter has the same value as
4784 rcuscale.kfree_rcu_test_double, both the single-
4785 and double-argument variants are tested.
4787 rcuscale.kfree_nthreads= [KNL]
4788 The number of threads running loops of kfree_rcu().
4790 rcuscale.kfree_alloc_num= [KNL]
4791 Number of allocations and frees done in an iteration.
4793 rcuscale.kfree_loops= [KNL]
4794 Number of loops doing rcuscale.kfree_alloc_num number
4795 of allocations and frees.
4797 rcuscale.nreaders= [KNL]
4798 Set number of RCU readers. The value -1 selects
4799 N, where N is the number of CPUs. A value
4800 "n" less than -1 selects N-n+1, where N is again
4801 the number of CPUs. For example, -2 selects N
4802 (the number of CPUs), -3 selects N+1, and so on.
4803 A value of "n" less than or equal to -N selects
4806 rcuscale.nwriters= [KNL]
4807 Set number of RCU writers. The values operate
4808 the same as for rcuscale.nreaders.
4809 N, where N is the number of CPUs
4811 rcuscale.perf_type= [KNL]
4812 Specify the RCU implementation to test.
4814 rcuscale.shutdown= [KNL]
4815 Shut the system down after performance tests
4816 complete. This is useful for hands-off automated
4819 rcuscale.verbose= [KNL]
4820 Enable additional printk() statements.
4822 rcuscale.writer_holdoff= [KNL]
4823 Write-side holdoff between grace periods,
4824 in microseconds. The default of zero says
4827 rcutorture.fqs_duration= [KNL]
4828 Set duration of force_quiescent_state bursts
4831 rcutorture.fqs_holdoff= [KNL]
4832 Set holdoff time within force_quiescent_state bursts
4835 rcutorture.fqs_stutter= [KNL]
4836 Set wait time between force_quiescent_state bursts
4839 rcutorture.fwd_progress= [KNL]
4840 Specifies the number of kthreads to be used
4841 for RCU grace-period forward-progress testing
4842 for the types of RCU supporting this notion.
4843 Defaults to 1 kthread, values less than zero or
4844 greater than the number of CPUs cause the number
4847 rcutorture.fwd_progress_div= [KNL]
4848 Specify the fraction of a CPU-stall-warning
4849 period to do tight-loop forward-progress testing.
4851 rcutorture.fwd_progress_holdoff= [KNL]
4852 Number of seconds to wait between successive
4853 forward-progress tests.
4855 rcutorture.fwd_progress_need_resched= [KNL]
4856 Enclose cond_resched() calls within checks for
4857 need_resched() during tight-loop forward-progress
4860 rcutorture.gp_cond= [KNL]
4861 Use conditional/asynchronous update-side
4862 primitives, if available.
4864 rcutorture.gp_exp= [KNL]
4865 Use expedited update-side primitives, if available.
4867 rcutorture.gp_normal= [KNL]
4868 Use normal (non-expedited) asynchronous
4869 update-side primitives, if available.
4871 rcutorture.gp_sync= [KNL]
4872 Use normal (non-expedited) synchronous
4873 update-side primitives, if available. If all
4874 of rcutorture.gp_cond=, rcutorture.gp_exp=,
4875 rcutorture.gp_normal=, and rcutorture.gp_sync=
4876 are zero, rcutorture acts as if is interpreted
4877 they are all non-zero.
4879 rcutorture.irqreader= [KNL]
4880 Run RCU readers from irq handlers, or, more
4881 accurately, from a timer handler. Not all RCU
4882 flavors take kindly to this sort of thing.
4884 rcutorture.leakpointer= [KNL]
4885 Leak an RCU-protected pointer out of the reader.
4886 This can of course result in splats, and is
4887 intended to test the ability of things like
4888 CONFIG_RCU_STRICT_GRACE_PERIOD=y to detect
4891 rcutorture.n_barrier_cbs= [KNL]
4892 Set callbacks/threads for rcu_barrier() testing.
4894 rcutorture.nfakewriters= [KNL]
4895 Set number of concurrent RCU writers. These just
4896 stress RCU, they don't participate in the actual
4897 test, hence the "fake".
4899 rcutorture.nocbs_nthreads= [KNL]
4900 Set number of RCU callback-offload togglers.
4901 Zero (the default) disables toggling.
4903 rcutorture.nocbs_toggle= [KNL]
4904 Set the delay in milliseconds between successive
4905 callback-offload toggling attempts.
4907 rcutorture.nreaders= [KNL]
4908 Set number of RCU readers. The value -1 selects
4909 N-1, where N is the number of CPUs. A value
4910 "n" less than -1 selects N-n-2, where N is again
4911 the number of CPUs. For example, -2 selects N
4912 (the number of CPUs), -3 selects N+1, and so on.
4914 rcutorture.object_debug= [KNL]
4915 Enable debug-object double-call_rcu() testing.
4917 rcutorture.onoff_holdoff= [KNL]
4918 Set time (s) after boot for CPU-hotplug testing.
4920 rcutorture.onoff_interval= [KNL]
4921 Set time (jiffies) between CPU-hotplug operations,
4922 or zero to disable CPU-hotplug testing.
4924 rcutorture.read_exit= [KNL]
4925 Set the number of read-then-exit kthreads used
4926 to test the interaction of RCU updaters and
4927 task-exit processing.
4929 rcutorture.read_exit_burst= [KNL]
4930 The number of times in a given read-then-exit
4931 episode that a set of read-then-exit kthreads
4934 rcutorture.read_exit_delay= [KNL]
4935 The delay, in seconds, between successive
4936 read-then-exit testing episodes.
4938 rcutorture.shuffle_interval= [KNL]
4939 Set task-shuffle interval (s). Shuffling tasks
4940 allows some CPUs to go into dyntick-idle mode
4941 during the rcutorture test.
4943 rcutorture.shutdown_secs= [KNL]
4944 Set time (s) after boot system shutdown. This
4945 is useful for hands-off automated testing.
4947 rcutorture.stall_cpu= [KNL]
4948 Duration of CPU stall (s) to test RCU CPU stall
4949 warnings, zero to disable.
4951 rcutorture.stall_cpu_block= [KNL]
4952 Sleep while stalling if set. This will result
4953 in warnings from preemptible RCU in addition
4954 to any other stall-related activity.
4956 rcutorture.stall_cpu_holdoff= [KNL]
4957 Time to wait (s) after boot before inducing stall.
4959 rcutorture.stall_cpu_irqsoff= [KNL]
4960 Disable interrupts while stalling if set.
4962 rcutorture.stall_gp_kthread= [KNL]
4963 Duration (s) of forced sleep within RCU
4964 grace-period kthread to test RCU CPU stall
4965 warnings, zero to disable. If both stall_cpu
4966 and stall_gp_kthread are specified, the
4967 kthread is starved first, then the CPU.
4969 rcutorture.stat_interval= [KNL]
4970 Time (s) between statistics printk()s.
4972 rcutorture.stutter= [KNL]
4973 Time (s) to stutter testing, for example, specifying
4974 five seconds causes the test to run for five seconds,
4975 wait for five seconds, and so on. This tests RCU's
4976 ability to transition abruptly to and from idle.
4978 rcutorture.test_boost= [KNL]
4979 Test RCU priority boosting? 0=no, 1=maybe, 2=yes.
4980 "Maybe" means test if the RCU implementation
4981 under test support RCU priority boosting.
4983 rcutorture.test_boost_duration= [KNL]
4984 Duration (s) of each individual boost test.
4986 rcutorture.test_boost_interval= [KNL]
4987 Interval (s) between each boost test.
4989 rcutorture.test_no_idle_hz= [KNL]
4990 Test RCU's dyntick-idle handling. See also the
4991 rcutorture.shuffle_interval parameter.
4993 rcutorture.torture_type= [KNL]
4994 Specify the RCU implementation to test.
4996 rcutorture.verbose= [KNL]
4997 Enable additional printk() statements.
4999 rcupdate.rcu_cpu_stall_ftrace_dump= [KNL]
5000 Dump ftrace buffer after reporting RCU CPU
5003 rcupdate.rcu_cpu_stall_suppress= [KNL]
5004 Suppress RCU CPU stall warning messages.
5006 rcupdate.rcu_cpu_stall_suppress_at_boot= [KNL]
5007 Suppress RCU CPU stall warning messages and
5008 rcutorture writer stall warnings that occur
5009 during early boot, that is, during the time
5010 before the init task is spawned.
5012 rcupdate.rcu_cpu_stall_timeout= [KNL]
5013 Set timeout for RCU CPU stall warning messages.
5014 The value is in seconds and the maximum allowed
5015 value is 300 seconds.
5017 rcupdate.rcu_exp_cpu_stall_timeout= [KNL]
5018 Set timeout for expedited RCU CPU stall warning
5019 messages. The value is in milliseconds
5020 and the maximum allowed value is 21000
5021 milliseconds. Please note that this value is
5022 adjusted to an arch timer tick resolution.
5023 Setting this to zero causes the value from
5024 rcupdate.rcu_cpu_stall_timeout to be used (after
5025 conversion from seconds to milliseconds).
5027 rcupdate.rcu_expedited= [KNL]
5028 Use expedited grace-period primitives, for
5029 example, synchronize_rcu_expedited() instead
5030 of synchronize_rcu(). This reduces latency,
5031 but can increase CPU utilization, degrade
5032 real-time latency, and degrade energy efficiency.
5033 No effect on CONFIG_TINY_RCU kernels.
5035 rcupdate.rcu_normal= [KNL]
5036 Use only normal grace-period primitives,
5037 for example, synchronize_rcu() instead of
5038 synchronize_rcu_expedited(). This improves
5039 real-time latency, CPU utilization, and
5040 energy efficiency, but can expose users to
5041 increased grace-period latency. This parameter
5042 overrides rcupdate.rcu_expedited. No effect on
5043 CONFIG_TINY_RCU kernels.
5045 rcupdate.rcu_normal_after_boot= [KNL]
5046 Once boot has completed (that is, after
5047 rcu_end_inkernel_boot() has been invoked), use
5048 only normal grace-period primitives. No effect
5049 on CONFIG_TINY_RCU kernels.
5051 But note that CONFIG_PREEMPT_RT=y kernels enables
5052 this kernel boot parameter, forcibly setting
5053 it to the value one, that is, converting any
5054 post-boot attempt at an expedited RCU grace
5055 period to instead use normal non-expedited
5056 grace-period processing.
5058 rcupdate.rcu_task_collapse_lim= [KNL]
5059 Set the maximum number of callbacks present
5060 at the beginning of a grace period that allows
5061 the RCU Tasks flavors to collapse back to using
5062 a single callback queue. This switching only
5063 occurs when rcupdate.rcu_task_enqueue_lim is
5064 set to the default value of -1.
5066 rcupdate.rcu_task_contend_lim= [KNL]
5067 Set the minimum number of callback-queuing-time
5068 lock-contention events per jiffy required to
5069 cause the RCU Tasks flavors to switch to per-CPU
5070 callback queuing. This switching only occurs
5071 when rcupdate.rcu_task_enqueue_lim is set to
5072 the default value of -1.
5074 rcupdate.rcu_task_enqueue_lim= [KNL]
5075 Set the number of callback queues to use for the
5076 RCU Tasks family of RCU flavors. The default
5077 of -1 allows this to be automatically (and
5078 dynamically) adjusted. This parameter is intended
5081 rcupdate.rcu_task_ipi_delay= [KNL]
5082 Set time in jiffies during which RCU tasks will
5083 avoid sending IPIs, starting with the beginning
5084 of a given grace period. Setting a large
5085 number avoids disturbing real-time workloads,
5086 but lengthens grace periods.
5088 rcupdate.rcu_task_stall_info= [KNL]
5089 Set initial timeout in jiffies for RCU task stall
5090 informational messages, which give some indication
5091 of the problem for those not patient enough to
5092 wait for ten minutes. Informational messages are
5093 only printed prior to the stall-warning message
5094 for a given grace period. Disable with a value
5095 less than or equal to zero. Defaults to ten
5096 seconds. A change in value does not take effect
5097 until the beginning of the next grace period.
5099 rcupdate.rcu_task_stall_info_mult= [KNL]
5100 Multiplier for time interval between successive
5101 RCU task stall informational messages for a given
5102 RCU tasks grace period. This value is clamped
5103 to one through ten, inclusive. It defaults to
5104 the value three, so that the first informational
5105 message is printed 10 seconds into the grace
5106 period, the second at 40 seconds, the third at
5107 160 seconds, and then the stall warning at 600
5108 seconds would prevent a fourth at 640 seconds.
5110 rcupdate.rcu_task_stall_timeout= [KNL]
5111 Set timeout in jiffies for RCU task stall
5112 warning messages. Disable with a value less
5113 than or equal to zero. Defaults to ten minutes.
5114 A change in value does not take effect until
5115 the beginning of the next grace period.
5117 rcupdate.rcu_self_test= [KNL]
5118 Run the RCU early boot self tests
5122 Run specified binary instead of /init from the ramdisk,
5123 used for early userspace startup. See initrd.
5126 force - Override the decision by the kernel to hide the
5127 advertisement of RDRAND support (this affects
5128 certain AMD processors because of buggy BIOS
5129 support, specifically around the suspend/resume
5133 Turn on/off individual RDT features. List is:
5134 cmt, mbmtotal, mbmlocal, l3cat, l3cdp, l2cat, l2cdp,
5136 E.g. to turn on cmt and turn off mba use:
5140 Format (x86 or x86_64):
5141 [w[arm] | c[old] | h[ard] | s[oft] | g[pio]] | d[efault] \
5143 [[,]b[ios] | a[cpi] | k[bd] | t[riple] | e[fi] | p[ci]] \
5145 Where reboot_mode is one of warm (soft) or cold (hard) or gpio
5146 (prefix with 'panic_' to set mode for panic
5148 reboot_type is one of bios, acpi, kbd, triple, efi, or pci,
5149 reboot_force is either force or not specified,
5150 reboot_cpu is s[mp]#### with #### being the processor
5151 to be used for rebooting.
5153 refscale.holdoff= [KNL]
5154 Set test-start holdoff period. The purpose of
5155 this parameter is to delay the start of the
5156 test until boot completes in order to avoid
5159 refscale.loops= [KNL]
5160 Set the number of loops over the synchronization
5161 primitive under test. Increasing this number
5162 reduces noise due to loop start/end overhead,
5163 but the default has already reduced the per-pass
5164 noise to a handful of picoseconds on ca. 2020
5167 refscale.nreaders= [KNL]
5168 Set number of readers. The default value of -1
5169 selects N, where N is roughly 75% of the number
5170 of CPUs. A value of zero is an interesting choice.
5172 refscale.nruns= [KNL]
5173 Set number of runs, each of which is dumped onto
5176 refscale.readdelay= [KNL]
5177 Set the read-side critical-section duration,
5178 measured in microseconds.
5180 refscale.scale_type= [KNL]
5181 Specify the read-protection implementation to test.
5183 refscale.shutdown= [KNL]
5184 Shut down the system at the end of the performance
5185 test. This defaults to 1 (shut it down) when
5186 refscale is built into the kernel and to 0 (leave
5187 it running) when refscale is built as a module.
5189 refscale.verbose= [KNL]
5190 Enable additional printk() statements.
5192 refscale.verbose_batched= [KNL]
5193 Batch the additional printk() statements. If zero
5194 (the default) or negative, print everything. Otherwise,
5195 print every Nth verbose statement, where N is the value
5199 [KNL, SMP] Set scheduler's default relax_domain_level.
5200 See Documentation/admin-guide/cgroup-v1/cpusets.rst.
5202 reserve= [KNL,BUGS] Force kernel to ignore I/O ports or memory
5203 Format: <base1>,<size1>[,<base2>,<size2>,...]
5204 Reserve I/O ports or memory so the kernel won't use
5205 them. If <base> is less than 0x10000, the region
5206 is assumed to be I/O ports; otherwise it is memory.
5208 reservetop= [X86-32]
5210 Reserves a hole at the top of the kernel virtual
5213 reset_devices [KNL] Force drivers to reset the underlying device
5214 during initialization.
5217 Specify the partition device for software suspend
5219 {/dev/<dev> | PARTUUID=<uuid> | <int>:<int> | <hex>}
5221 resume_offset= [SWSUSP]
5222 Specify the offset from the beginning of the partition
5223 given by "resume=" at which the swap header is located,
5224 in <PAGE_SIZE> units (needed only for swap files).
5225 See Documentation/power/swsusp-and-swap-files.rst
5227 resumedelay= [HIBERNATION] Delay (in seconds) to pause before attempting to
5228 read the resume files
5230 resumewait [HIBERNATION] Wait (indefinitely) for resume device to show up.
5231 Useful for devices that are detected asynchronously
5232 (e.g. USB and MMC devices).
5234 retain_initrd [RAM] Keep initrd memory after extraction
5236 retbleed= [X86] Control mitigation of RETBleed (Arbitrary
5237 Speculative Code Execution with Return Instructions)
5241 auto - automatically select a migitation
5242 auto,nosmt - automatically select a mitigation,
5243 disabling SMT if necessary for
5244 the full mitigation (only on Zen1
5245 and older without STIBP).
5246 ibpb - mitigate short speculation windows on
5247 basic block boundaries too. Safe, highest
5249 unret - force enable untrained return thunks,
5250 only effective on AMD f15h-f17h
5252 unret,nosmt - like unret, will disable SMT when STIBP
5255 Selecting 'auto' will choose a mitigation method at run
5256 time according to the CPU.
5258 Not specifying this option is equivalent to retbleed=auto.
5260 rfkill.default_state=
5261 0 "airplane mode". All wifi, bluetooth, wimax, gps, fm,
5262 etc. communication is blocked by default.
5265 rfkill.master_switch_mode=
5266 0 The "airplane mode" button does nothing.
5267 1 The "airplane mode" button toggles between everything
5268 blocked and the previous configuration.
5269 2 The "airplane mode" button toggles between everything
5270 blocked and everything unblocked.
5272 rhash_entries= [KNL,NET]
5273 Set number of hash buckets for route cache
5276 [KNL] Disable ring 3 MONITOR/MWAIT feature on supported
5279 ro [KNL] Mount root device read-only on boot
5282 on Mark read-only kernel memory as read-only (default).
5283 off Leave read-only kernel memory writable for debugging.
5286 Enable the uart passthrough on the designated usb port
5287 on Rockchip SoCs. When active, the signals of the
5288 debug-uart get routed to the D+ and D- pins of the usb
5289 port and the regular usb controller gets disabled.
5291 root= [KNL] Root filesystem
5292 See name_to_dev_t comment in init/do_mounts.c.
5294 rootdelay= [KNL] Delay (in seconds) to pause before attempting to
5295 mount the root filesystem
5297 rootflags= [KNL] Set root filesystem mount option string
5299 rootfstype= [KNL] Set root filesystem type
5301 rootwait [KNL] Wait (indefinitely) for root device to show up.
5302 Useful for devices that are detected asynchronously
5303 (e.g. USB and MMC devices).
5305 rproc_mem=nn[KMG][@address]
5306 [KNL,ARM,CMA] Remoteproc physical memory block.
5307 Memory area to be used by remote processor image,
5310 rw [KNL] Mount root device read-write on boot
5312 S [KNL] Run init in single mode
5314 s390_iommu= [HW,S390]
5315 Set s390 IOTLB flushing mode
5317 With strict flushing every unmap operation will result in
5318 an IOTLB flush. Default is lazy flushing before reuse,
5321 s390_iommu_aperture= [KNL,S390]
5322 Specifies the size of the per device DMA address space
5323 accessible through the DMA and IOMMU APIs as a decimal
5324 factor of the size of main memory.
5325 The default is 1 meaning that one can concurrently use
5326 as many DMA addresses as physical memory is installed,
5327 if supported by hardware, and thus map all of memory
5328 once. With a value of 2 one can map all of memory twice
5329 and so on. As a special case a factor of 0 imposes no
5330 restrictions other than those given by hardware at the
5331 cost of significant additional memory use for tables.
5334 See drivers/net/irda/sa1100_ir.c.
5336 sched_verbose [KNL] Enables verbose scheduler debug messages.
5338 schedstats= [KNL,X86] Enable or disable scheduled statistics.
5339 Allowed values are enable and disable. This feature
5340 incurs a small amount of overhead in the scheduler
5341 but is useful for debugging and performance tuning.
5343 sched_thermal_decay_shift=
5344 [KNL, SMP] Set a decay shift for scheduler thermal
5345 pressure signal. Thermal pressure signal follows the
5346 default decay period of other scheduler pelt
5347 signals(usually 32 ms but configurable). Setting
5348 sched_thermal_decay_shift will left shift the decay
5349 period for the thermal pressure signal by the shift
5351 i.e. with the default pelt decay period of 32 ms
5352 sched_thermal_decay_shift thermal pressure decay pr
5356 Format: integer between 0 and 10
5359 scftorture.holdoff= [KNL]
5360 Number of seconds to hold off before starting
5361 test. Defaults to zero for module insertion and
5362 to 10 seconds for built-in smp_call_function()
5365 scftorture.longwait= [KNL]
5366 Request ridiculously long waits randomly selected
5367 up to the chosen limit in seconds. Zero (the
5368 default) disables this feature. Please note
5369 that requesting even small non-zero numbers of
5370 seconds can result in RCU CPU stall warnings,
5371 softlockup complaints, and so on.
5373 scftorture.nthreads= [KNL]
5374 Number of kthreads to spawn to invoke the
5375 smp_call_function() family of functions.
5376 The default of -1 specifies a number of kthreads
5377 equal to the number of CPUs.
5379 scftorture.onoff_holdoff= [KNL]
5380 Number seconds to wait after the start of the
5381 test before initiating CPU-hotplug operations.
5383 scftorture.onoff_interval= [KNL]
5384 Number seconds to wait between successive
5385 CPU-hotplug operations. Specifying zero (which
5386 is the default) disables CPU-hotplug operations.
5388 scftorture.shutdown_secs= [KNL]
5389 The number of seconds following the start of the
5390 test after which to shut down the system. The
5391 default of zero avoids shutting down the system.
5392 Non-zero values are useful for automated tests.
5394 scftorture.stat_interval= [KNL]
5395 The number of seconds between outputting the
5396 current test statistics to the console. A value
5397 of zero disables statistics output.
5399 scftorture.stutter_cpus= [KNL]
5400 The number of jiffies to wait between each change
5401 to the set of CPUs under test.
5403 scftorture.use_cpus_read_lock= [KNL]
5404 Use use_cpus_read_lock() instead of the default
5405 preempt_disable() to disable CPU hotplug
5406 while invoking one of the smp_call_function*()
5409 scftorture.verbose= [KNL]
5410 Enable additional printk() statements.
5412 scftorture.weight_single= [KNL]
5413 The probability weighting to use for the
5414 smp_call_function_single() function with a zero
5415 "wait" parameter. A value of -1 selects the
5416 default if all other weights are -1. However,
5417 if at least one weight has some other value, a
5418 value of -1 will instead select a weight of zero.
5420 scftorture.weight_single_wait= [KNL]
5421 The probability weighting to use for the
5422 smp_call_function_single() function with a
5423 non-zero "wait" parameter. See weight_single.
5425 scftorture.weight_many= [KNL]
5426 The probability weighting to use for the
5427 smp_call_function_many() function with a zero
5428 "wait" parameter. See weight_single.
5429 Note well that setting a high probability for
5430 this weighting can place serious IPI load
5433 scftorture.weight_many_wait= [KNL]
5434 The probability weighting to use for the
5435 smp_call_function_many() function with a
5436 non-zero "wait" parameter. See weight_single
5439 scftorture.weight_all= [KNL]
5440 The probability weighting to use for the
5441 smp_call_function_all() function with a zero
5442 "wait" parameter. See weight_single and
5445 scftorture.weight_all_wait= [KNL]
5446 The probability weighting to use for the
5447 smp_call_function_all() function with a
5448 non-zero "wait" parameter. See weight_single
5451 skew_tick= [KNL] Offset the periodic timer tick per cpu to mitigate
5452 xtime_lock contention on larger systems, and/or RCU lock
5453 contention on all systems with CONFIG_MAXSMP set.
5454 Format: { "0" | "1" }
5455 0 -- disable. (may be 1 via CONFIG_CMDLINE="skew_tick=1"
5457 Note: increases power consumption, thus should only be
5458 enabled if running jitter sensitive (HPC/RT) workloads.
5460 security= [SECURITY] Choose a legacy "major" security module to
5461 enable at boot. This has been deprecated by the
5464 selinux= [SELINUX] Disable or enable SELinux at boot time.
5465 Format: { "0" | "1" }
5466 See security/selinux/Kconfig help text.
5471 apparmor= [APPARMOR] Disable or enable AppArmor at boot time
5472 Format: { "0" | "1" }
5473 See security/apparmor/Kconfig help text
5476 Default value is set via kernel config option.
5478 serialnumber [BUGS=X86-32]
5480 sev=option[,option...] [X86-64] See Documentation/x86/x86_64/boot-options.rst
5483 Maximal number of shapers.
5491 Enable merging of slabs with similar size when the
5492 kernel is built without CONFIG_SLAB_MERGE_DEFAULT.
5495 Disable merging of slabs with similar size. May be
5496 necessary if there is some reason to distinguish
5497 allocs to different slabs, especially in hardened
5498 environments where the risk of heap overflows and
5499 layout control by attackers can usually be
5500 frustrated by disabling merging. This will reduce
5501 most of the exposure of a heap attack to a single
5502 cache (risks via metadata attacks are mostly
5503 unchanged). Debug options disable merging on their
5505 For more information see Documentation/vm/slub.rst.
5507 slab_max_order= [MM, SLAB]
5508 Determines the maximum allowed order for slabs.
5509 A high setting may cause OOMs due to memory
5510 fragmentation. Defaults to 1 for systems with
5511 more than 32MB of RAM, 0 otherwise.
5513 slub_debug[=options[,slabs][;[options[,slabs]]...] [MM, SLUB]
5514 Enabling slub_debug allows one to determine the
5515 culprit if slab objects become corrupted. Enabling
5516 slub_debug can create guard zones around objects and
5517 may poison objects when not in use. Also tracks the
5518 last alloc / free. For more information see
5519 Documentation/vm/slub.rst.
5521 slub_max_order= [MM, SLUB]
5522 Determines the maximum allowed order for slabs.
5523 A high setting may cause OOMs due to memory
5524 fragmentation. For more information see
5525 Documentation/vm/slub.rst.
5527 slub_min_objects= [MM, SLUB]
5528 The minimum number of objects per slab. SLUB will
5529 increase the slab order up to slub_max_order to
5530 generate a sufficiently large slab able to contain
5531 the number of objects indicated. The higher the number
5532 of objects the smaller the overhead of tracking slabs
5533 and the less frequently locks need to be acquired.
5534 For more information see Documentation/vm/slub.rst.
5536 slub_min_order= [MM, SLUB]
5537 Determines the minimum page order for slabs. Must be
5538 lower than slub_max_order.
5539 For more information see Documentation/vm/slub.rst.
5541 slub_merge [MM, SLUB]
5542 Same with slab_merge.
5544 slub_nomerge [MM, SLUB]
5545 Same with slab_nomerge. This is supported for legacy.
5546 See slab_nomerge for more information.
5549 Format: <io1>[,<io2>[,...,<io8>]]
5551 smp.csd_lock_timeout= [KNL]
5552 Specify the period of time in milliseconds
5553 that smp_call_function() and friends will wait
5554 for a CPU to release the CSD lock. This is
5555 useful when diagnosing bugs involving CPUs
5556 disabling interrupts for extended periods
5557 of time. Defaults to 5,000 milliseconds, and
5558 setting a value of zero disables this feature.
5559 This feature may be more efficiently disabled
5560 using the csdlock_debug- kernel parameter.
5562 smsc-ircc2.nopnp [HW] Don't use PNP to discover SMC devices
5563 smsc-ircc2.ircc_cfg= [HW] Device configuration I/O port
5564 smsc-ircc2.ircc_sir= [HW] SIR base I/O port
5565 smsc-ircc2.ircc_fir= [HW] FIR base I/O port
5566 smsc-ircc2.ircc_irq= [HW] IRQ line
5567 smsc-ircc2.ircc_dma= [HW] DMA channel
5568 smsc-ircc2.ircc_transceiver= [HW] Transceiver type:
5569 0: Toshiba Satellite 1800 (GP data pin select)
5570 1: Fast pin select (default)
5573 smt= [KNL,S390] Set the maximum number of threads (logical
5574 CPUs) to use per physical CPU on systems capable of
5575 symmetric multithreading (SMT). Will be capped to the
5576 actual hardware limit.
5578 Default: -1 (no limit)
5581 [KNL] Should the soft-lockup detector generate panics.
5584 A value of 1 instructs the soft-lockup detector
5585 to panic the machine when a soft-lockup occurs. It is
5586 also controlled by the kernel.softlockup_panic sysctl
5587 and CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC, which is the
5588 respective build-time switch to that functionality.
5590 softlockup_all_cpu_backtrace=
5591 [KNL] Should the soft-lockup detector generate
5592 backtraces on all cpus.
5595 sonypi.*= [HW] Sony Programmable I/O Control Device driver
5596 See Documentation/admin-guide/laptops/sonypi.rst
5598 spectre_v2= [X86] Control mitigation of Spectre variant 2
5599 (indirect branch speculation) vulnerability.
5600 The default operation protects the kernel from
5603 on - unconditionally enable, implies
5605 off - unconditionally disable, implies
5607 auto - kernel detects whether your CPU model is
5610 Selecting 'on' will, and 'auto' may, choose a
5611 mitigation method at run time according to the
5612 CPU, the available microcode, the setting of the
5613 CONFIG_RETPOLINE configuration option, and the
5614 compiler with which the kernel was built.
5616 Selecting 'on' will also enable the mitigation
5617 against user space to user space task attacks.
5619 Selecting 'off' will disable both the kernel and
5620 the user space protections.
5622 Specific mitigations can also be selected manually:
5624 retpoline - replace indirect branches
5625 retpoline,generic - Retpolines
5626 retpoline,lfence - LFENCE; indirect branch
5627 retpoline,amd - alias for retpoline,lfence
5628 eibrs - enhanced IBRS
5629 eibrs,retpoline - enhanced IBRS + Retpolines
5630 eibrs,lfence - enhanced IBRS + LFENCE
5631 ibrs - use IBRS to protect kernel
5633 Not specifying this option is equivalent to
5637 [X86] Control mitigation of Spectre variant 2
5638 (indirect branch speculation) vulnerability between
5641 on - Unconditionally enable mitigations. Is
5642 enforced by spectre_v2=on
5644 off - Unconditionally disable mitigations. Is
5645 enforced by spectre_v2=off
5647 prctl - Indirect branch speculation is enabled,
5648 but mitigation can be enabled via prctl
5649 per thread. The mitigation control state
5650 is inherited on fork.
5653 - Like "prctl" above, but only STIBP is
5654 controlled per thread. IBPB is issued
5655 always when switching between different user
5659 - Same as "prctl" above, but all seccomp
5660 threads will enable the mitigation unless
5661 they explicitly opt out.
5664 - Like "seccomp" above, but only STIBP is
5665 controlled per thread. IBPB is issued
5666 always when switching between different
5667 user space processes.
5669 auto - Kernel selects the mitigation depending on
5670 the available CPU features and vulnerability.
5672 Default mitigation: "prctl"
5674 Not specifying this option is equivalent to
5675 spectre_v2_user=auto.
5677 spec_store_bypass_disable=
5678 [HW] Control Speculative Store Bypass (SSB) Disable mitigation
5679 (Speculative Store Bypass vulnerability)
5681 Certain CPUs are vulnerable to an exploit against a
5682 a common industry wide performance optimization known
5683 as "Speculative Store Bypass" in which recent stores
5684 to the same memory location may not be observed by
5685 later loads during speculative execution. The idea
5686 is that such stores are unlikely and that they can
5687 be detected prior to instruction retirement at the
5688 end of a particular speculation execution window.
5690 In vulnerable processors, the speculatively forwarded
5691 store can be used in a cache side channel attack, for
5692 example to read memory to which the attacker does not
5693 directly have access (e.g. inside sandboxed code).
5695 This parameter controls whether the Speculative Store
5696 Bypass optimization is used.
5698 On x86 the options are:
5700 on - Unconditionally disable Speculative Store Bypass
5701 off - Unconditionally enable Speculative Store Bypass
5702 auto - Kernel detects whether the CPU model contains an
5703 implementation of Speculative Store Bypass and
5704 picks the most appropriate mitigation. If the
5705 CPU is not vulnerable, "off" is selected. If the
5706 CPU is vulnerable the default mitigation is
5707 architecture and Kconfig dependent. See below.
5708 prctl - Control Speculative Store Bypass per thread
5709 via prctl. Speculative Store Bypass is enabled
5710 for a process by default. The state of the control
5711 is inherited on fork.
5712 seccomp - Same as "prctl" above, but all seccomp threads
5713 will disable SSB unless they explicitly opt out.
5715 Default mitigations:
5718 On powerpc the options are:
5720 on,auto - On Power8 and Power9 insert a store-forwarding
5721 barrier on kernel entry and exit. On Power7
5722 perform a software flush on kernel entry and
5726 Not specifying this option is equivalent to
5727 spec_store_bypass_disable=auto.
5729 spia_io_base= [HW,MTD]
5735 [X86] Enable split lock detection or bus lock detection
5737 When enabled (and if hardware support is present), atomic
5738 instructions that access data across cache line
5739 boundaries will result in an alignment check exception
5740 for split lock detection or a debug exception for
5745 warn - the kernel will emit rate-limited warnings
5746 about applications triggering the #AC
5747 exception or the #DB exception. This mode is
5748 the default on CPUs that support split lock
5749 detection or bus lock detection. Default
5750 behavior is by #AC if both features are
5751 enabled in hardware.
5753 fatal - the kernel will send SIGBUS to applications
5754 that trigger the #AC exception or the #DB
5755 exception. Default behavior is by #AC if
5756 both features are enabled in hardware.
5759 Set system wide rate limit to N bus locks
5760 per second for bus lock detection.
5763 N/A for split lock detection.
5766 If an #AC exception is hit in the kernel or in
5767 firmware (i.e. not while executing in user mode)
5768 the kernel will oops in either "warn" or "fatal"
5771 #DB exception for bus lock is triggered only when
5775 Control the Special Register Buffer Data Sampling
5778 Certain CPUs are vulnerable to an MDS-like
5779 exploit which can leak bits from the random
5782 By default, this issue is mitigated by
5783 microcode. However, the microcode fix can cause
5784 the RDRAND and RDSEED instructions to become
5785 much slower. Among other effects, this will
5786 result in reduced throughput from /dev/urandom.
5788 The microcode mitigation can be disabled with
5789 the following option:
5791 off: Disable mitigation and remove
5792 performance impact to RDRAND and RDSEED
5794 srcutree.big_cpu_lim [KNL]
5795 Specifies the number of CPUs constituting a
5796 large system, such that srcu_struct structures
5797 should immediately allocate an srcu_node array.
5798 This kernel-boot parameter defaults to 128,
5799 but takes effect only when the low-order four
5800 bits of srcutree.convert_to_big is equal to 3
5803 srcutree.convert_to_big [KNL]
5804 Specifies under what conditions an SRCU tree
5805 srcu_struct structure will be converted to big
5806 form, that is, with an rcu_node tree:
5809 1: At init_srcu_struct() time.
5810 2: When rcutorture decides to.
5811 3: Decide at boot time (default).
5812 0x1X: Above plus if high contention.
5814 Either way, the srcu_node tree will be sized based
5815 on the actual runtime number of CPUs (nr_cpu_ids)
5816 instead of the compile-time CONFIG_NR_CPUS.
5818 srcutree.counter_wrap_check [KNL]
5819 Specifies how frequently to check for
5820 grace-period sequence counter wrap for the
5821 srcu_data structure's ->srcu_gp_seq_needed field.
5822 The greater the number of bits set in this kernel
5823 parameter, the less frequently counter wrap will
5824 be checked for. Note that the bottom two bits
5827 srcutree.exp_holdoff [KNL]
5828 Specifies how many nanoseconds must elapse
5829 since the end of the last SRCU grace period for
5830 a given srcu_struct until the next normal SRCU
5831 grace period will be considered for automatic
5832 expediting. Set to zero to disable automatic
5835 srcutree.srcu_max_nodelay [KNL]
5836 Specifies the number of no-delay instances
5837 per jiffy for which the SRCU grace period
5838 worker thread will be rescheduled with zero
5839 delay. Beyond this limit, worker thread will
5840 be rescheduled with a sleep delay of one jiffy.
5842 srcutree.srcu_max_nodelay_phase [KNL]
5843 Specifies the per-grace-period phase, number of
5844 non-sleeping polls of readers. Beyond this limit,
5845 grace period worker thread will be rescheduled
5846 with a sleep delay of one jiffy, between each
5847 rescan of the readers, for a grace period phase.
5849 srcutree.srcu_retry_check_delay [KNL]
5850 Specifies number of microseconds of non-sleeping
5851 delay between each non-sleeping poll of readers.
5853 srcutree.small_contention_lim [KNL]
5854 Specifies the number of update-side contention
5855 events per jiffy will be tolerated before
5856 initiating a conversion of an srcu_struct
5857 structure to big form. Note that the value of
5858 srcutree.convert_to_big must have the 0x10 bit
5859 set for contention-based conversions to occur.
5862 Speculative Store Bypass Disable control
5864 On CPUs that are vulnerable to the Speculative
5865 Store Bypass vulnerability and offer a
5866 firmware based mitigation, this parameter
5867 indicates how the mitigation should be used:
5869 force-on: Unconditionally enable mitigation for
5870 for both kernel and userspace
5871 force-off: Unconditionally disable mitigation for
5872 for both kernel and userspace
5873 kernel: Always enable mitigation in the
5874 kernel, and offer a prctl interface
5875 to allow userspace to register its
5876 interest in being mitigated too.
5878 stack_guard_gap= [MM]
5879 override the default stack gap protection. The value
5880 is in page units and it defines how many pages prior
5881 to (for stacks growing down) resp. after (for stacks
5882 growing up) the main stack are reserved for no other
5883 mapping. Default value is 256 pages.
5885 stack_depot_disable= [KNL]
5886 Setting this to true through kernel command line will
5887 disable the stack depot thereby saving the static memory
5888 consumed by the stack hash table. By default this is set
5892 Enabled the stack tracer on boot up.
5894 stacktrace_filter=[function-list]
5895 [FTRACE] Limit the functions that the stack tracer
5896 will trace at boot up. function-list is a comma-separated
5897 list of functions. This list can be changed at run
5898 time by the stack_trace_filter file in the debugfs
5899 tracing directory. Note, this enables stack tracing
5900 and the stacktrace above is not needed.
5904 Set the STI (builtin display/keyboard on the HP-PARISC
5905 machines) console (graphic card) which should be used
5906 as the initial boot-console.
5907 See also comment in drivers/video/console/sticore.c.
5910 See comment in drivers/video/console/sticore.c.
5913 Format: bpp:<bpp1>[:<bpp2>[:<bpp3>...]]
5918 Enable or disable strict sigaltstack size checks
5919 against the required signal frame size which
5920 depends on the supported FPU features. This can
5921 be used to filter out binaries which have
5922 not yet been made aware of AT_MINSIGSTKSZ.
5924 sunrpc.min_resvport=
5925 sunrpc.max_resvport=
5927 SunRPC servers often require that client requests
5928 originate from a privileged port (i.e. a port in the
5929 range 0 < portnr < 1024).
5930 An administrator who wishes to reserve some of these
5931 ports for other uses may adjust the range that the
5932 kernel's sunrpc client considers to be privileged
5933 using these two parameters to set the minimum and
5934 maximum port values.
5936 sunrpc.svc_rpc_per_connection_limit=
5938 Limit the number of requests that the server will
5939 process in parallel from a single connection.
5940 The default value is 0 (no limit).
5944 Control how the NFS server code allocates CPUs to
5945 service thread pools. Depending on how many NICs
5946 you have and where their interrupts are bound, this
5947 option will affect which CPUs will do NFS serving.
5948 Note: this parameter cannot be changed while the
5949 NFS server is running.
5951 auto the server chooses an appropriate mode
5952 automatically using heuristics
5953 global a single global pool contains all CPUs
5954 percpu one pool for each CPU
5955 pernode one pool for each NUMA node (equivalent
5956 to global on non-NUMA machines)
5958 sunrpc.tcp_slot_table_entries=
5959 sunrpc.udp_slot_table_entries=
5961 Sets the upper limit on the number of simultaneous
5962 RPC calls that can be sent from the client to a
5963 server. Increasing these values may allow you to
5964 improve throughput, but will also increase the
5965 amount of memory reserved for use by the client.
5967 suspend.pm_test_delay=
5969 Sets the number of seconds to remain in a suspend test
5970 mode before resuming the system (see
5971 /sys/power/pm_test). Only available when CONFIG_PM_DEBUG
5972 is set. Default value is 5.
5975 Format: { on | off | y | n | 1 | 0 }
5976 This parameter controls use of the Protected
5977 Execution Facility on pSeries.
5981 Enable accounting of swap in memory resource
5982 controller if no parameter or 1 is given or disable
5983 it if 0 is given (See Documentation/admin-guide/cgroup-v1/memory.rst)
5985 swiotlb= [ARM,IA-64,PPC,MIPS,X86]
5986 Format: { <int> | force | noforce }
5987 <int> -- Number of I/O TLB slabs
5988 force -- force using of bounce buffers even if they
5989 wouldn't be automatically used by the kernel
5990 noforce -- Never use bounce buffers (for debugging)
5995 Set a sysctl parameter, right before loading the init
5996 process, as if the value was written to the respective
5997 /proc/sys/... file. Both '.' and '/' are recognized as
5998 separators. Unrecognized parameters and invalid values
5999 are reported in the kernel log. Sysctls registered
6000 later by a loaded module cannot be set this way.
6001 Example: sysctl.vm.swappiness=40
6003 sysfs.deprecated=0|1 [KNL]
6004 Enable/disable old style sysfs layout for old udev
6005 on older distributions. When this option is enabled
6006 very new udev will not work anymore. When this option
6007 is disabled (or CONFIG_SYSFS_DEPRECATED not compiled)
6008 in older udev will not work anymore.
6009 Default depends on CONFIG_SYSFS_DEPRECATED_V2 set in
6010 the kernel configuration.
6012 sysrq_always_enabled
6014 Ignore sysrq setting - this boot parameter will
6015 neutralize any effect of /proc/sys/kernel/sysrq.
6016 Useful for debugging.
6018 tcpmhash_entries= [KNL,NET]
6019 Set the number of tcp_metrics_hash slots.
6020 Default value is 8192 or 16384 depending on total
6021 ram pages. This is used to specify the TCP metrics
6022 cache size. See Documentation/networking/ip-sysctl.rst
6023 "tcp_no_metrics_save" section for more details.
6027 test_suspend= [SUSPEND]
6028 Format: { "mem" | "standby" | "freeze" }[,N]
6029 Specify "mem" (for Suspend-to-RAM) or "standby" (for
6030 standby suspend) or "freeze" (for suspend type freeze)
6031 as the system sleep state during system startup with
6032 the optional capability to repeat N number of times.
6033 The system is woken from this state using a
6034 wakeup-capable RTC alarm.
6036 thash_entries= [KNL,NET]
6037 Set number of hash buckets for TCP connection
6039 thermal.act= [HW,ACPI]
6040 -1: disable all active trip points in all thermal zones
6041 <degrees C>: override all lowest active trip points
6043 thermal.crt= [HW,ACPI]
6044 -1: disable all critical trip points in all thermal zones
6045 <degrees C>: override all critical trip points
6047 thermal.nocrt= [HW,ACPI]
6048 Set to disable actions on ACPI thermal zone
6049 critical and hot trip points.
6051 thermal.off= [HW,ACPI]
6052 1: disable ACPI thermal control
6054 thermal.psv= [HW,ACPI]
6055 -1: disable all passive trip points
6056 <degrees C>: override all passive trip points to this
6059 thermal.tzp= [HW,ACPI]
6060 Specify global default ACPI thermal zone polling rate
6061 <deci-seconds>: poll all this frequency
6062 0: no polling (default)
6065 Force threading of all interrupt handlers except those
6066 marked explicitly IRQF_NO_THREAD.
6070 Specify if the kernel should make use of the cpu
6071 topology information if the hardware supports this.
6072 The scheduler will make use of this information and
6073 e.g. base its process migration decisions on it.
6076 topology_updates= [KNL, PPC, NUMA]
6078 Specify if the kernel should ignore (off)
6079 topology updates sent by the hypervisor to this
6082 torture.disable_onoff_at_boot= [KNL]
6083 Prevent the CPU-hotplug component of torturing
6084 until after init has spawned.
6086 torture.ftrace_dump_at_shutdown= [KNL]
6087 Dump the ftrace buffer at torture-test shutdown,
6088 even if there were no errors. This can be a
6089 very costly operation when many torture tests
6090 are running concurrently, especially on systems
6091 with rotating-rust storage.
6093 torture.verbose_sleep_frequency= [KNL]
6094 Specifies how many verbose printk()s should be
6095 emitted between each sleep. The default of zero
6096 disables verbose-printk() sleeping.
6098 torture.verbose_sleep_duration= [KNL]
6099 Duration of each verbose-printk() sleep in jiffies.
6103 tpm_suspend_pcr=[HW,TPM]
6104 Format: integer pcr id
6105 Specify that at suspend time, the tpm driver
6106 should extend the specified pcr with zeros,
6107 as a workaround for some chips which fail to
6108 flush the last written pcr on TPM_SaveState.
6109 This will guarantee that all the other pcrs
6113 Have the tracepoints sent to printk as well as the
6114 tracing ring buffer. This is useful for early boot up
6115 where the system hangs or reboots and does not give the
6116 option for reading the tracing buffer or performing a
6117 ftrace_dump_on_oops.
6119 To turn off having tracepoints sent to printk,
6120 echo 0 > /proc/sys/kernel/tracepoint_printk
6121 Note, echoing 1 into this file without the
6122 tracepoint_printk kernel cmdline option has no effect.
6124 The tp_printk_stop_on_boot (see below) can also be used
6125 to stop the printing of events to console at
6130 Having tracepoints sent to printk() and activating high
6131 frequency tracepoints such as irq or sched, can cause
6132 the system to live lock.
6134 tp_printk_stop_on_boot [FTRACE]
6135 When tp_printk (above) is set, it can cause a lot of noise
6136 on the console. It may be useful to only include the
6137 printing of events during boot up, as user space may
6138 make the system inoperable.
6140 This command line option will stop the printing of events
6141 to console at the late_initcall_sync() time frame.
6143 trace_buf_size=nn[KMG]
6144 [FTRACE] will set tracing buffer size on each cpu.
6146 trace_clock= [FTRACE] Set the clock used for tracing events
6148 local - Use the per CPU time stamp counter
6149 (converted into nanoseconds). Fast, but
6150 depending on the architecture, may not be
6151 in sync between CPUs.
6152 global - Event time stamps are synchronize across
6153 CPUs. May be slower than the local clock,
6154 but better for some race conditions.
6155 counter - Simple counting of events (1, 2, ..)
6156 note, some counts may be skipped due to the
6157 infrastructure grabbing the clock more than
6159 uptime - Use jiffies as the time stamp.
6160 perf - Use the same clock that perf uses.
6161 mono - Use ktime_get_mono_fast_ns() for time stamps.
6162 mono_raw - Use ktime_get_raw_fast_ns() for time
6164 boot - Use ktime_get_boot_fast_ns() for time stamps.
6165 Architectures may add more clocks. See
6166 Documentation/trace/ftrace.rst for more details.
6168 trace_event=[event-list]
6169 [FTRACE] Set and start specified trace events in order
6170 to facilitate early boot debugging. The event-list is a
6171 comma-separated list of trace events to enable. See
6172 also Documentation/trace/events.rst
6174 trace_options=[option-list]
6175 [FTRACE] Enable or disable tracer options at boot.
6176 The option-list is a comma delimited list of options
6177 that can be enabled or disabled just as if you were
6178 to echo the option name into
6180 /sys/kernel/debug/tracing/trace_options
6182 For example, to enable stacktrace option (to dump the
6183 stack trace of each event), add to the command line:
6185 trace_options=stacktrace
6187 See also Documentation/trace/ftrace.rst "trace options"
6191 [FTRACE] enable this option to disable tracing when a
6192 warning is hit. This turns off "tracing_on". Tracing can
6193 be enabled again by echoing '1' into the "tracing_on"
6194 file located in /sys/kernel/debug/tracing/
6196 This option is useful, as it disables the trace before
6197 the WARNING dump is called, which prevents the trace to
6198 be filled with content caused by the warning output.
6200 This option can also be set at run time via the sysctl
6201 option: kernel/traceoff_on_warning
6203 transparent_hugepage=
6205 Format: [always|madvise|never]
6206 Can be used to control the default behavior of the system
6207 with respect to transparent hugepages.
6208 See Documentation/admin-guide/mm/transhuge.rst
6211 trusted.source= [KEYS]
6213 This parameter identifies the trust source as a backend
6214 for trusted keys implementation. Supported trust
6219 If not specified then it defaults to iterating through
6220 the trust source list starting with TPM and assigns the
6221 first trust source as a backend which is initialized
6222 successfully during iteration.
6226 The RNG used to generate key material for trusted keys.
6229 - the same value as trusted.source: "tpm" or "tee"
6231 If not specified, "default" is used. In this case,
6232 the RNG's choice is left to each individual trust source.
6234 tsc= Disable clocksource stability checks for TSC.
6236 [x86] reliable: mark tsc clocksource as reliable, this
6237 disables clocksource verification at runtime, as well
6238 as the stability checks done at bootup. Used to enable
6239 high-resolution timer mode on older hardware, and in
6240 virtualized environment.
6241 [x86] noirqtime: Do not use TSC to do irq accounting.
6242 Used to run time disable IRQ_TIME_ACCOUNTING on any
6243 platforms where RDTSC is slow and this accounting
6245 [x86] unstable: mark the TSC clocksource as unstable, this
6246 marks the TSC unconditionally unstable at bootup and
6247 avoids any further wobbles once the TSC watchdog notices.
6248 [x86] nowatchdog: disable clocksource watchdog. Used
6249 in situations with strict latency requirements (where
6250 interruptions from clocksource watchdog are not
6253 tsc_early_khz= [X86] Skip early TSC calibration and use the given
6254 value instead. Useful when the early TSC frequency discovery
6255 procedure is not reliable, such as on overclocked systems
6256 with CPUID.16h support and partial CPUID.15h support.
6257 Format: <unsigned int>
6259 tsx= [X86] Control Transactional Synchronization
6260 Extensions (TSX) feature in Intel processors that
6261 support TSX control.
6263 This parameter controls the TSX feature. The options are:
6265 on - Enable TSX on the system. Although there are
6266 mitigations for all known security vulnerabilities,
6267 TSX has been known to be an accelerator for
6268 several previous speculation-related CVEs, and
6269 so there may be unknown security risks associated
6270 with leaving it enabled.
6272 off - Disable TSX on the system. (Note that this
6273 option takes effect only on newer CPUs which are
6274 not vulnerable to MDS, i.e., have
6275 MSR_IA32_ARCH_CAPABILITIES.MDS_NO=1 and which get
6276 the new IA32_TSX_CTRL MSR through a microcode
6277 update. This new MSR allows for the reliable
6278 deactivation of the TSX functionality.)
6280 auto - Disable TSX if X86_BUG_TAA is present,
6281 otherwise enable TSX on the system.
6283 Not specifying this option is equivalent to tsx=off.
6285 See Documentation/admin-guide/hw-vuln/tsx_async_abort.rst
6288 tsx_async_abort= [X86,INTEL] Control mitigation for the TSX Async
6289 Abort (TAA) vulnerability.
6291 Similar to Micro-architectural Data Sampling (MDS)
6292 certain CPUs that support Transactional
6293 Synchronization Extensions (TSX) are vulnerable to an
6294 exploit against CPU internal buffers which can forward
6295 information to a disclosure gadget under certain
6298 In vulnerable processors, the speculatively forwarded
6299 data can be used in a cache side channel attack, to
6300 access data to which the attacker does not have direct
6303 This parameter controls the TAA mitigation. The
6306 full - Enable TAA mitigation on vulnerable CPUs
6309 full,nosmt - Enable TAA mitigation and disable SMT on
6310 vulnerable CPUs. If TSX is disabled, SMT
6311 is not disabled because CPU is not
6312 vulnerable to cross-thread TAA attacks.
6313 off - Unconditionally disable TAA mitigation
6315 On MDS-affected machines, tsx_async_abort=off can be
6316 prevented by an active MDS mitigation as both vulnerabilities
6317 are mitigated with the same mechanism so in order to disable
6318 this mitigation, you need to specify mds=off too.
6320 Not specifying this option is equivalent to
6321 tsx_async_abort=full. On CPUs which are MDS affected
6322 and deploy MDS mitigation, TAA mitigation is not
6323 required and doesn't provide any additional
6327 Documentation/admin-guide/hw-vuln/tsx_async_abort.rst
6329 turbografx.map[2|3]= [HW,JOY]
6330 TurboGraFX parallel port interface
6332 <port#>,<js1>,<js2>,<js3>,<js4>,<js5>,<js6>,<js7>
6333 See also Documentation/input/devices/joystick-parport.rst
6335 udbg-immortal [PPC] When debugging early kernel crashes that
6336 happen after console_init() and before a proper
6337 console driver takes over, this boot options might
6338 help "seeing" what's going on.
6340 uhash_entries= [KNL,NET]
6341 Set number of hash buckets for UDP/UDP-Lite connections
6344 [USB] Ignore overcurrent events (default N).
6345 Some badly-designed motherboards generate lots of
6346 bogus events, for ports that aren't wired to
6347 anything. Set this parameter to avoid log spamming.
6348 Note that genuine overcurrent events won't be
6352 [X86] Cause panic on unknown NMI.
6354 usbcore.authorized_default=
6355 [USB] Default USB device authorization:
6356 (default -1 = authorized except for wireless USB,
6357 0 = not authorized, 1 = authorized, 2 = authorized
6358 if device connected to internal port)
6360 usbcore.autosuspend=
6361 [USB] The autosuspend time delay (in seconds) used
6362 for newly-detected USB devices (default 2). This
6363 is the time required before an idle device will be
6364 autosuspended. Devices for which the delay is set
6365 to a negative value won't be autosuspended at all.
6367 usbcore.usbfs_snoop=
6368 [USB] Set to log all usbfs traffic (default 0 = off).
6370 usbcore.usbfs_snoop_max=
6371 [USB] Maximum number of bytes to snoop in each URB
6374 usbcore.blinkenlights=
6375 [USB] Set to cycle leds on hubs (default 0 = off).
6377 usbcore.old_scheme_first=
6378 [USB] Start with the old device initialization
6379 scheme (default 0 = off).
6381 usbcore.usbfs_memory_mb=
6382 [USB] Memory limit (in MB) for buffers allocated by
6383 usbfs (default = 16, 0 = max = 2047).
6385 usbcore.use_both_schemes=
6386 [USB] Try the other device initialization scheme
6387 if the first one fails (default 1 = enabled).
6389 usbcore.initial_descriptor_timeout=
6390 [USB] Specifies timeout for the initial 64-byte
6391 USB_REQ_GET_DESCRIPTOR request in milliseconds
6392 (default 5000 = 5.0 seconds).
6394 usbcore.nousb [USB] Disable the USB subsystem
6397 [USB] A list of quirk entries to augment the built-in
6398 usb core quirk list. List entries are separated by
6399 commas. Each entry has the form
6400 VendorID:ProductID:Flags. The IDs are 4-digit hex
6401 numbers and Flags is a set of letters. Each letter
6402 will change the built-in quirk; setting it if it is
6403 clear and clearing it if it is set. The letters have
6404 the following meanings:
6405 a = USB_QUIRK_STRING_FETCH_255 (string
6406 descriptors must not be fetched using
6408 b = USB_QUIRK_RESET_RESUME (device can't resume
6409 correctly so reset it instead);
6410 c = USB_QUIRK_NO_SET_INTF (device can't handle
6411 Set-Interface requests);
6412 d = USB_QUIRK_CONFIG_INTF_STRINGS (device can't
6413 handle its Configuration or Interface
6415 e = USB_QUIRK_RESET (device can't be reset
6416 (e.g morph devices), don't use reset);
6417 f = USB_QUIRK_HONOR_BNUMINTERFACES (device has
6418 more interface descriptions than the
6419 bNumInterfaces count, and can't handle
6420 talking to these interfaces);
6421 g = USB_QUIRK_DELAY_INIT (device needs a pause
6422 during initialization, after we read
6423 the device descriptor);
6424 h = USB_QUIRK_LINEAR_UFRAME_INTR_BINTERVAL (For
6425 high speed and super speed interrupt
6426 endpoints, the USB 2.0 and USB 3.0 spec
6427 require the interval in microframes (1
6428 microframe = 125 microseconds) to be
6429 calculated as interval = 2 ^
6431 Devices with this quirk report their
6432 bInterval as the result of this
6433 calculation instead of the exponent
6434 variable used in the calculation);
6435 i = USB_QUIRK_DEVICE_QUALIFIER (device can't
6436 handle device_qualifier descriptor
6438 j = USB_QUIRK_IGNORE_REMOTE_WAKEUP (device
6439 generates spurious wakeup, ignore
6440 remote wakeup capability);
6441 k = USB_QUIRK_NO_LPM (device can't handle Link
6443 l = USB_QUIRK_LINEAR_FRAME_INTR_BINTERVAL
6444 (Device reports its bInterval as linear
6445 frames instead of the USB 2.0
6447 m = USB_QUIRK_DISCONNECT_SUSPEND (Device needs
6448 to be disconnected before suspend to
6449 prevent spurious wakeup);
6450 n = USB_QUIRK_DELAY_CTRL_MSG (Device needs a
6451 pause after every control message);
6452 o = USB_QUIRK_HUB_SLOW_RESET (Hub needs extra
6453 delay after resetting its port);
6454 Example: quirks=0781:5580:bk,0a5c:5834:gij
6457 [USBHID] The interval which mice are to be polled at.
6460 [USBHID] The interval which joysticks are to be polled at.
6463 [USBHID] The interval which keyboards are to be polled at.
6465 usb-storage.delay_use=
6466 [UMS] The delay in seconds before a new device is
6467 scanned for Logical Units (default 1).
6470 [UMS] A list of quirks entries to supplement or
6471 override the built-in unusual_devs list. List
6472 entries are separated by commas. Each entry has
6473 the form VID:PID:Flags where VID and PID are Vendor
6474 and Product ID values (4-digit hex numbers) and
6475 Flags is a set of characters, each corresponding
6476 to a common usb-storage quirk flag as follows:
6477 a = SANE_SENSE (collect more than 18 bytes
6478 of sense data, not on uas);
6479 b = BAD_SENSE (don't collect more than 18
6480 bytes of sense data, not on uas);
6481 c = FIX_CAPACITY (decrease the reported
6482 device capacity by one sector);
6483 d = NO_READ_DISC_INFO (don't use
6484 READ_DISC_INFO command, not on uas);
6485 e = NO_READ_CAPACITY_16 (don't use
6486 READ_CAPACITY_16 command);
6487 f = NO_REPORT_OPCODES (don't use report opcodes
6489 g = MAX_SECTORS_240 (don't transfer more than
6490 240 sectors at a time, uas only);
6491 h = CAPACITY_HEURISTICS (decrease the
6492 reported device capacity by one
6493 sector if the number is odd);
6494 i = IGNORE_DEVICE (don't bind to this
6496 j = NO_REPORT_LUNS (don't use report luns
6498 k = NO_SAME (do not use WRITE_SAME, uas only)
6499 l = NOT_LOCKABLE (don't try to lock and
6500 unlock ejectable media, not on uas);
6501 m = MAX_SECTORS_64 (don't transfer more
6502 than 64 sectors = 32 KB at a time,
6504 n = INITIAL_READ10 (force a retry of the
6505 initial READ(10) command, not on uas);
6506 o = CAPACITY_OK (accept the capacity
6507 reported by the device, not on uas);
6508 p = WRITE_CACHE (the device cache is ON
6509 by default, not on uas);
6510 r = IGNORE_RESIDUE (the device reports
6511 bogus residue values, not on uas);
6512 s = SINGLE_LUN (the device has only one
6514 t = NO_ATA_1X (don't allow ATA(12) and ATA(16)
6515 commands, uas only);
6516 u = IGNORE_UAS (don't bind to the uas driver);
6517 w = NO_WP_DETECT (don't test whether the
6518 medium is write-protected).
6519 y = ALWAYS_SYNC (issue a SYNCHRONIZE_CACHE
6520 even if the device claims no cache,
6522 Example: quirks=0419:aaf5:rl,0421:0433:rc
6524 user_debug= [KNL,ARM]
6526 See arch/arm/Kconfig.debug help text.
6527 1 - undefined instruction events
6529 4 - invalid data aborts
6532 Example: user_debug=31
6535 [X86] Flags controlling user PTE allocations.
6537 nohigh = do not allocate PTE pages in
6538 HIGHMEM regardless of setting
6541 vdso= [X86,SH,SPARC]
6542 On X86_32, this is an alias for vdso32=. Otherwise:
6544 vdso=1: enable VDSO (the default)
6545 vdso=0: disable VDSO mapping
6547 vdso32= [X86] Control the 32-bit vDSO
6548 vdso32=1: enable 32-bit VDSO
6549 vdso32=0 or vdso32=2: disable 32-bit VDSO
6551 See the help text for CONFIG_COMPAT_VDSO for more
6552 details. If CONFIG_COMPAT_VDSO is set, the default is
6553 vdso32=0; otherwise, the default is vdso32=1.
6555 For compatibility with older kernels, vdso32=2 is an
6558 Try vdso32=0 if you encounter an error that says:
6559 dl_main: Assertion `(void *) ph->p_vaddr == _rtld_local._dl_sysinfo_dso' failed!
6562 vector=percpu: enable percpu vector domain
6564 video= [FB] Frame buffer configuration
6565 See Documentation/fb/modedb.rst.
6567 video.brightness_switch_enabled= [ACPI]
6569 If set to 1, on receiving an ACPI notify event
6570 generated by hotkey, video driver will adjust brightness
6571 level and then send out the event to user space through
6572 the allocated input device. If set to 0, video driver
6573 will only send out the event without touching backlight
6578 [VMMIO] Memory mapped virtio (platform) device.
6580 <size>@<baseaddr>:<irq>[:<id>]
6582 <size> := size (can use standard suffixes
6584 <baseaddr> := physical base address
6585 <irq> := interrupt number (as passed to
6587 <id> := (optional) platform device id
6589 virtio_mmio.device=1K@0x100b0000:48:7
6591 Can be used multiple times for multiple devices.
6593 vga= [BOOT,X86-32] Select a particular video mode
6594 See Documentation/x86/boot.rst and
6595 Documentation/admin-guide/svga.rst.
6596 Use vga=ask for menu.
6597 This is actually a boot loader parameter; the value is
6598 passed to the kernel using a special protocol.
6600 vm_debug[=options] [KNL] Available with CONFIG_DEBUG_VM=y.
6601 May slow down system boot speed, especially when
6602 enabled on systems with a large amount of memory.
6603 All options are enabled by default, and this
6604 interface is meant to allow for selectively
6605 enabling or disabling specific virtual memory
6608 Available options are:
6609 P Enable page structure init time poisoning
6610 - Disable all of the above options
6612 vmalloc=nn[KMG] [KNL,BOOT] Forces the vmalloc area to have an exact
6613 size of <nn>. This can be used to increase the
6614 minimum size (128MB on x86). It can also be used to
6615 decrease the size and leave more room for directly
6618 vmcp_cma=nn[MG] [KNL,S390]
6619 Sets the memory size reserved for contiguous memory
6620 allocations for the vmcp device driver.
6622 vmhalt= [KNL,S390] Perform z/VM CP command after system halt.
6625 vmpanic= [KNL,S390] Perform z/VM CP command after kernel panic.
6628 vmpoff= [KNL,S390] Perform z/VM CP command after power off.
6632 Controls the behavior of vsyscalls (i.e. calls to
6633 fixed addresses of 0xffffffffff600x00 from legacy
6634 code). Most statically-linked binaries and older
6635 versions of glibc use these calls. Because these
6636 functions are at fixed addresses, they make nice
6637 targets for exploits that can control RIP.
6639 emulate [default] Vsyscalls turn into traps and are
6640 emulated reasonably safely. The vsyscall
6643 xonly Vsyscalls turn into traps and are
6644 emulated reasonably safely. The vsyscall
6645 page is not readable.
6647 none Vsyscalls don't work at all. This makes
6648 them quite hard to use for exploits but
6649 might break your system.
6651 vt.color= [VT] Default text color.
6652 Format: 0xYX, X = foreground, Y = background.
6653 Default: 0x07 = light gray on black.
6655 vt.cur_default= [VT] Default cursor shape.
6656 Format: 0xCCBBAA, where AA, BB, and CC are the same as
6657 the parameters of the <Esc>[?A;B;Cc escape sequence;
6658 see VGA-softcursor.txt. Default: 2 = underline.
6660 vt.default_blu= [VT]
6661 Format: <blue0>,<blue1>,<blue2>,...,<blue15>
6662 Change the default blue palette of the console.
6663 This is a 16-member array composed of values
6666 vt.default_grn= [VT]
6667 Format: <green0>,<green1>,<green2>,...,<green15>
6668 Change the default green palette of the console.
6669 This is a 16-member array composed of values
6672 vt.default_red= [VT]
6673 Format: <red0>,<red1>,<red2>,...,<red15>
6674 Change the default red palette of the console.
6675 This is a 16-member array composed of values
6681 Set system-wide default UTF-8 mode for all tty's.
6682 Default is 1, i.e. UTF-8 mode is enabled for all
6683 newly opened terminals.
6685 vt.global_cursor_default=
6688 Set system-wide default for whether a cursor
6689 is shown on new VTs. Default is -1,
6690 i.e. cursors will be created by default unless
6691 overridden by individual drivers. 0 will hide
6692 cursors, 1 will display them.
6694 vt.italic= [VT] Default color for italic text; 0-15.
6697 vt.underline= [VT] Default color for underlined text; 0-15.
6700 watchdog timers [HW,WDT] For information on watchdog timers,
6701 see Documentation/watchdog/watchdog-parameters.rst
6702 or other driver-specific files in the
6703 Documentation/watchdog/ directory.
6707 Set the hard lockup detector stall duration
6708 threshold in seconds. The soft lockup detector
6709 threshold is set to twice the value. A value of 0
6710 disables both lockup detectors. Default is 10
6713 workqueue.watchdog_thresh=
6714 If CONFIG_WQ_WATCHDOG is configured, workqueue can
6715 warn stall conditions and dump internal state to
6716 help debugging. 0 disables workqueue stall
6717 detection; otherwise, it's the stall threshold
6718 duration in seconds. The default value is 30 and
6719 it can be updated at runtime by writing to the
6720 corresponding sysfs file.
6722 workqueue.disable_numa
6723 By default, all work items queued to unbound
6724 workqueues are affine to the NUMA nodes they're
6725 issued on, which results in better behavior in
6726 general. If NUMA affinity needs to be disabled for
6727 whatever reason, this option can be used. Note
6728 that this also can be controlled per-workqueue for
6729 workqueues visible under /sys/bus/workqueue/.
6731 workqueue.power_efficient
6732 Per-cpu workqueues are generally preferred because
6733 they show better performance thanks to cache
6734 locality; unfortunately, per-cpu workqueues tend to
6735 be more power hungry than unbound workqueues.
6737 Enabling this makes the per-cpu workqueues which
6738 were observed to contribute significantly to power
6739 consumption unbound, leading to measurably lower
6740 power usage at the cost of small performance
6743 The default value of this parameter is determined by
6744 the config option CONFIG_WQ_POWER_EFFICIENT_DEFAULT.
6746 workqueue.debug_force_rr_cpu
6747 Workqueue used to implicitly guarantee that work
6748 items queued without explicit CPU specified are put
6749 on the local CPU. This guarantee is no longer true
6750 and while local CPU is still preferred work items
6751 may be put on foreign CPUs. This debug option
6752 forces round-robin CPU selection to flush out
6753 usages which depend on the now broken guarantee.
6754 When enabled, memory and cache locality will be
6757 x2apic_phys [X86-64,APIC] Use x2apic physical mode instead of
6758 default x2apic cluster mode on platforms
6761 xen_512gb_limit [KNL,X86-64,XEN]
6762 Restricts the kernel running paravirtualized under Xen
6763 to use only up to 512 GB of RAM. The reason to do so is
6764 crash analysis tools and Xen tools for doing domain
6765 save/restore/migration must be enabled to handle larger
6768 xen_emul_unplug= [HW,X86,XEN]
6769 Unplug Xen emulated devices
6770 Format: [unplug0,][unplug1]
6771 ide-disks -- unplug primary master IDE devices
6772 aux-ide-disks -- unplug non-primary-master IDE devices
6773 nics -- unplug network devices
6774 all -- unplug all emulated devices (NICs and IDE disks)
6775 unnecessary -- unplugging emulated devices is
6776 unnecessary even if the host did not respond to
6778 never -- do not unplug even if version check succeeds
6780 xen_legacy_crash [X86,XEN]
6781 Crash from Xen panic notifier, without executing late
6782 panic() code such as dumping handler.
6784 xen_nopvspin [X86,XEN]
6785 Disables the qspinlock slowpath using Xen PV optimizations.
6786 This parameter is obsoleted by "nopvspin" parameter, which
6787 has equivalent effect for XEN platform.
6790 Disables the PV optimizations forcing the HVM guest to
6791 run as generic HVM guest with no PV drivers.
6792 This option is obsoleted by the "nopv" option, which
6793 has equivalent effect for XEN platform.
6795 xen_no_vector_callback
6796 [KNL,X86,XEN] Disable the vector callback for Xen
6797 event channel interrupts.
6799 xen_scrub_pages= [XEN]
6800 Boolean option to control scrubbing pages before giving them back
6801 to Xen, for use by other domains. Can be also changed at runtime
6802 with /sys/devices/system/xen_memory/xen_memory0/scrub_pages.
6803 Default value controlled with CONFIG_XEN_SCRUB_PAGES_DEFAULT.
6805 xen_timer_slop= [X86-64,XEN]
6806 Set the timer slop (in nanoseconds) for the virtual Xen
6807 timers (default is 100000). This adjusts the minimum
6808 delta of virtualized Xen timers, where lower values
6809 improve timer resolution at the expense of processing
6810 more timer interrupts.
6812 xen.balloon_boot_timeout= [XEN]
6813 The time (in seconds) to wait before giving up to boot
6814 in case initial ballooning fails to free enough memory.
6815 Applies only when running as HVM or PVH guest and
6816 started with less memory configured than allowed at
6817 max. Default is 180.
6819 xen.event_eoi_delay= [XEN]
6820 How long to delay EOI handling in case of event
6821 storms (jiffies). Default is 10.
6823 xen.event_loop_timeout= [XEN]
6824 After which time (jiffies) the event handling loop
6825 should start to delay EOI handling. Default is 2.
6827 xen.fifo_events= [XEN]
6828 Boolean parameter to disable using fifo event handling
6829 even if available. Normally fifo event handling is
6830 preferred over the 2-level event handling, as it is
6831 fairer and the number of possible event channels is
6832 much higher. Default is on (use fifo events).
6834 nopv= [X86,XEN,KVM,HYPER_V,VMWARE]
6835 Disables the PV optimizations forcing the guest to run
6836 as generic guest with no PV drivers. Currently support
6837 XEN HVM, KVM, HYPER_V and VMWARE guest.
6839 nopvspin [X86,XEN,KVM]
6840 Disables the qspinlock slow path using PV optimizations
6841 which allow the hypervisor to 'idle' the guest on lock
6844 xirc2ps_cs= [NET,PCMCIA]
6846 <irq>,<irq_mask>,<io>,<full_duplex>,<do_sound>,<lockup_hack>[,<irq2>[,<irq3>[,<irq4>]]]
6849 By default on POWER9 and above, the kernel will
6850 natively use the XIVE interrupt controller. This option
6851 allows the fallback firmware mode to be used:
6853 off Fallback to firmware control of XIVE interrupt
6854 controller on both pseries and powernv
6855 platforms. Only useful on POWER9 and above.
6857 xive.store-eoi=off [PPC]
6858 By default on POWER10 and above, the kernel will use
6859 stores for EOI handling when the XIVE interrupt mode
6860 is active. This option allows the XIVE driver to use
6861 loads instead, as on POWER9.
6863 xhci-hcd.quirks [USB,KNL]
6864 A hex value specifying bitmask with supplemental xhci
6865 host controller quirks. Meaning of each bit can be
6866 consulted in header drivers/usb/host/xhci.h.
6869 Format: { early | on | rw | ro | off }
6870 Controls if xmon debugger is enabled. Default is off.
6871 Passing only "xmon" is equivalent to "xmon=early".
6872 early Call xmon as early as possible on boot; xmon
6873 debugger is called from setup_arch().
6874 on xmon debugger hooks will be installed so xmon
6875 is only called on a kernel crash. Default mode,
6876 i.e. either "ro" or "rw" mode, is controlled
6877 with CONFIG_XMON_DEFAULT_RO_MODE.
6878 rw xmon debugger hooks will be installed so xmon
6879 is called only on a kernel crash, mode is write,
6880 meaning SPR registers, memory and, other data
6881 can be written using xmon commands.
6882 ro same as "rw" option above but SPR registers,
6883 memory, and other data can't be written using
6885 off xmon is disabled.
projects / linux-2.6-microblaze.git / blob