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]
27 If set to vendor, prefer vendor specific driver
28 (e.g. thinkpad_acpi, sony_acpi, etc.) instead
29 of the ACPI video.ko driver.
31 acpi_force_32bit_fadt_addr
32 force FADT to use 32 bit addresses rather than the
33 64 bit X_* addresses. Some firmware have broken 64
34 bit addresses for force ACPI ignore these and use
35 the older legacy 32 bit addresses.
37 acpica_no_return_repair [HW, ACPI]
38 Disable AML predefined validation mechanism
39 This mechanism can repair the evaluation result to make
40 the return objects more ACPI specification compliant.
41 This option is useful for developers to identify the
42 root cause of an AML interpreter issue when the issue
43 has something to do with the repair mechanism.
45 acpi.debug_layer= [HW,ACPI,ACPI_DEBUG]
46 acpi.debug_level= [HW,ACPI,ACPI_DEBUG]
48 CONFIG_ACPI_DEBUG must be enabled to produce any ACPI
49 debug output. Bits in debug_layer correspond to a
50 _COMPONENT in an ACPI source file, e.g.,
51 #define _COMPONENT ACPI_PCI_COMPONENT
52 Bits in debug_level correspond to a level in
53 ACPI_DEBUG_PRINT statements, e.g.,
54 ACPI_DEBUG_PRINT((ACPI_DB_INFO, ...
55 The debug_level mask defaults to "info". See
56 Documentation/firmware-guide/acpi/debug.rst for more information about
57 debug layers and levels.
59 Enable processor driver info messages:
60 acpi.debug_layer=0x20000000
61 Enable PCI/PCI interrupt routing info messages:
62 acpi.debug_layer=0x400000
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
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_nohwsig,
229 old_ordering, nonvs, sci_force_enable, nobl }
230 See Documentation/power/video.rst for information on
232 s3_beep is for debugging; it makes the PC's speaker beep
233 as soon as the kernel's real-mode entry point is called.
234 s4_nohwsig prevents ACPI hardware signature from being
235 used during resume from hibernation.
236 old_ordering causes the ACPI 1.0 ordering of the _PTS
237 control method, with respect to putting devices into
238 low power states, to be enforced (the ACPI 2.0 ordering
239 of _PTS is used by default).
240 nonvs prevents the kernel from saving/restoring the
241 ACPI NVS memory during suspend/hibernation and resume.
242 sci_force_enable causes the kernel to set SCI_EN directly
243 on resume from S1/S3 (which is against the ACPI spec,
244 but some broken systems don't work without it).
245 nobl causes the internal blacklist of systems known to
246 behave incorrectly in some ways with respect to system
247 suspend and resume to be ignored (use wisely).
249 acpi_use_timer_override [HW,ACPI]
250 Use timer override. For some broken Nvidia NF5 boards
251 that require a timer override, but don't have HPET
253 add_efi_memmap [EFI; X86] Include EFI memory map in
254 kernel's map of available physical RAM.
257 { off | try_unsupported }
258 off: disable AGP support
259 try_unsupported: try to drive unsupported chipsets
260 (may crash computer or cause data corruption)
263 See Documentation/sound/alsa-configuration.rst
266 Allow the default userspace alignment fault handler
267 behaviour to be specified. Bit 0 enables warnings,
268 bit 1 enables fixups, and bit 2 sends a segfault.
270 align_va_addr= [X86-64]
271 Align virtual addresses by clearing slice [14:12] when
272 allocating a VMA at process creation time. This option
273 gives you up to 3% performance improvement on AMD F15h
274 machines (where it is enabled by default) for a
275 CPU-intensive style benchmark, and it can vary highly in
276 a microbenchmark depending on workload and compiler.
278 32: only for 32-bit processes
279 64: only for 64-bit processes
280 on: enable for both 32- and 64-bit processes
281 off: disable for both 32- and 64-bit processes
283 alloc_snapshot [FTRACE]
284 Allocate the ftrace snapshot buffer on boot up when the
285 main buffer is allocated. This is handy if debugging
286 and you need to use tracing_snapshot() on boot up, and
287 do not want to use tracing_snapshot_alloc() as it needs
288 to be done where GFP_KERNEL allocations are allowed.
290 amd_iommu= [HW,X86-64]
291 Pass parameters to the AMD IOMMU driver in the system.
293 fullflush - enable flushing of IO/TLB entries when
294 they are unmapped. Otherwise they are
295 flushed before they will be reused, which
297 off - do not initialize any AMD IOMMU found in
299 force_isolation - Force device isolation for all
300 devices. The IOMMU driver is not
301 allowed anymore to lift isolation
302 requirements as needed. This option
303 does not override iommu=pt
305 amd_iommu_dump= [HW,X86-64]
306 Enable AMD IOMMU driver option to dump the ACPI table
307 for AMD IOMMU. With this option enabled, AMD IOMMU
308 driver will print ACPI tables for AMD IOMMU during
309 IOMMU initialization.
311 amd_iommu_intr= [HW,X86-64]
312 Specifies one of the following AMD IOMMU interrupt
314 legacy - Use legacy interrupt remapping mode.
315 vapic - Use virtual APIC mode, which allows IOMMU
316 to inject interrupts directly into guest.
317 This mode requires kvm-amd.avic=1.
318 (Default when IOMMU HW support is present.)
320 amijoy.map= [HW,JOY] Amiga joystick support
321 Map of devices attached to JOY0DAT and JOY1DAT
323 See also Documentation/input/joydev/joystick.rst
325 analog.map= [HW,JOY] Analog joystick and gamepad support
326 Specifies type or capabilities of an analog joystick
327 connected to one of 16 gameports
328 Format: <type1>,<type2>,..<type16>
331 Power management functions (SPARCstation-4/5 + deriv.)
333 Disable APC CPU standby support. SPARCstation-Fox does
334 not play well with APC CPU idle - disable it if you have
335 APC and your system crashes randomly.
337 apic= [APIC,X86] Advanced Programmable Interrupt Controller
338 Change the output verbosity while booting
339 Format: { quiet (default) | verbose | debug }
340 Change the amount of debugging information output
341 when initialising the APIC and IO-APIC components.
342 For X86-32, this can also be used to specify an APIC
344 Format: apic=driver_name
345 Examples: apic=bigsmp
347 apic_extnmi= [APIC,X86] External NMI delivery setting
348 Format: { bsp (default) | all | none }
349 bsp: External NMI is delivered only to CPU 0
350 all: External NMIs are broadcast to all CPUs as a
352 none: External NMI is masked for all CPUs. This is
353 useful so that a dump capture kernel won't be
357 See Documentation/networking/ipv6.txt.
359 show_lapic= [APIC,X86] Advanced Programmable Interrupt Controller
360 Limit apic dumping. The parameter defines the maximal
361 number of local apics being dumped. Also it is possible
362 to set it to "all" by meaning -- no limit here.
363 Format: { 1 (default) | 2 | ... | all }.
364 The parameter valid if only apic=debug or
365 apic=verbose is specified.
366 Example: apic=debug show_lapic=all
368 apm= [APM] Advanced Power Management
369 See header of arch/x86/kernel/apm_32.c.
371 arcrimi= [HW,NET] ARCnet - "RIM I" (entirely mem-mapped) cards
372 Format: <io>,<irq>,<nodeID>
376 atarimouse= [HW,MOUSE] Atari Mouse
378 atkbd.extra= [HW] Enable extra LEDs and keys on IBM RapidAccess,
379 EzKey and similar keyboards
381 atkbd.reset= [HW] Reset keyboard during initialization
383 atkbd.set= [HW] Select keyboard code set
384 Format: <int> (2 = AT (default), 3 = PS/2)
386 atkbd.scroll= [HW] Enable scroll wheel on MS Office and similar
389 atkbd.softraw= [HW] Choose between synthetic and real raw mode
390 Format: <bool> (0 = real, 1 = synthetic (default))
392 atkbd.softrepeat= [HW]
393 Use software keyboard repeat
395 audit= [KNL] Enable the audit sub-system
396 Format: { "0" | "1" | "off" | "on" }
397 0 | off - kernel audit is disabled and can not be
398 enabled until the next reboot
399 unset - kernel audit is initialized but disabled and
400 will be fully enabled by the userspace auditd.
401 1 | on - kernel audit is initialized and partially
402 enabled, storing at most audit_backlog_limit
403 messages in RAM until it is fully enabled by the
407 audit_backlog_limit= [KNL] Set the audit queue size limit.
408 Format: <int> (must be >=0)
411 bau= [X86_UV] Enable the BAU on SGI UV. The default
412 behavior is to disable the BAU (i.e. bau=0).
413 Format: { "0" | "1" }
416 unset - Disable the BAU.
418 baycom_epp= [HW,AX25]
421 baycom_par= [HW,AX25] BayCom Parallel Port AX.25 Modem
423 See header of drivers/net/hamradio/baycom_par.c.
425 baycom_ser_fdx= [HW,AX25]
426 BayCom Serial Port AX.25 Modem (Full Duplex Mode)
427 Format: <io>,<irq>,<mode>[,<baud>]
428 See header of drivers/net/hamradio/baycom_ser_fdx.c.
430 baycom_ser_hdx= [HW,AX25]
431 BayCom Serial Port AX.25 Modem (Half Duplex Mode)
432 Format: <io>,<irq>,<mode>
433 See header of drivers/net/hamradio/baycom_ser_hdx.c.
435 blkdevparts= Manual partition parsing of block device(s) for
436 embedded devices based on command line input.
437 See Documentation/block/cmdline-partition.rst
439 boot_delay= Milliseconds to delay each printk during boot.
440 Values larger than 10 seconds (10000) are changed to
444 bootmem_debug [KNL] Enable bootmem allocator debug messages.
447 Disable BERT OS support on buggy BIOSes.
449 bttv.card= [HW,V4L] bttv (bt848 + bt878 based grabber cards)
450 bttv.radio= Most important insmod options are available as
452 bttv.pll= See Documentation/media/v4l-drivers/bttv.rst
455 bulk_remove=off [PPC] This parameter disables the use of the pSeries
456 firmware feature for flushing multiple hpte entries
459 c101= [NET] Moxa C101 synchronous serial card
461 cachesize= [BUGS=X86-32] Override level 2 CPU cache size detection.
462 Sometimes CPU hardware bugs make them report the cache
463 size incorrectly. The kernel will attempt work arounds
464 to fix known problems, but for some CPUs it is not
465 possible to determine what the correct size should be.
466 This option provides an override for these situations.
469 [NET] Specifies amount of time (in seconds) that
470 the kernel should wait for a network carrier. By default
471 it waits 120 seconds.
473 ca_keys= [KEYS] This parameter identifies a specific key(s) on
474 the system trusted keyring to be used for certificate
476 format: { id:<keyid> | builtin }
478 cca= [MIPS] Override the kernel pages' cache coherency
479 algorithm. Accepted values range from 0 to 7
480 inclusive. See arch/mips/include/asm/pgtable-bits.h
481 for platform specific values (SB1, Loongson3 and
484 ccw_timeout_log [S390]
485 See Documentation/s390/common_io.rst for details.
487 cgroup_disable= [KNL] Disable a particular controller
488 Format: {name of the controller(s) to disable}
489 The effects of cgroup_disable=foo are:
490 - foo isn't auto-mounted if you mount all cgroups in
492 - foo isn't visible as an individually mountable
494 {Currently only "memory" controller deal with this and
495 cut the overhead, others just disable the usage. So
496 only cgroup_disable=memory is actually worthy}
498 cgroup_no_v1= [KNL] Disable cgroup controllers and named hierarchies in v1
499 Format: { { controller | "all" | "named" }
500 [,{ controller | "all" | "named" }...] }
501 Like cgroup_disable, but only applies to cgroup v1;
502 the blacklisted controllers remain available in cgroup2.
503 "all" blacklists all controllers and "named" disables
504 named mounts. Specifying both "all" and "named" disables
507 cgroup.memory= [KNL] Pass options to the cgroup memory controller.
509 nosocket -- Disable socket memory accounting.
510 nokmem -- Disable kernel memory accounting.
512 checkreqprot [SELINUX] Set initial checkreqprot flag value.
513 Format: { "0" | "1" }
514 See security/selinux/Kconfig help text.
515 0 -- check protection applied by kernel (includes
516 any implied execute protection).
517 1 -- check protection requested by application.
518 Default value is set via a kernel config option.
519 Value can be changed at runtime via
520 /selinux/checkreqprot.
523 See Documentation/s390/common_io.rst for details.
526 Prevents the clock framework from automatically gating
527 clocks that have not been explicitly enabled by a Linux
528 device driver but are enabled in hardware at reset or
529 by the bootloader/firmware. Note that this does not
530 force such clocks to be always-on nor does it reserve
531 those clocks in any way. This parameter is useful for
532 debug and development, but should not be needed on a
533 platform with proper driver support. For more
534 information, see Documentation/driver-api/clk.rst.
536 clock= [BUGS=X86-32, HW] gettimeofday clocksource override.
538 Forces specified clocksource (if available) to be used
539 when calculating gettimeofday(). If specified
540 clocksource is not available, it defaults to PIT.
541 Format: { pit | tsc | cyclone | pmtmr }
543 clocksource= Override the default clocksource
545 Override the default clocksource and use the clocksource
546 with the name specified.
547 Some clocksource names to choose from, depending on
549 [all] jiffies (this is the base, fallback clocksource)
551 [ARM] imx_timer1,OSTS,netx_timer,mpu_timer2,
552 pxa_timer,timer3,32k_counter,timer0_1
553 [X86-32] pit,hpet,tsc;
554 scx200_hrt on Geode; cyclone on IBM x440
562 clocksource.arm_arch_timer.evtstrm=
565 Enable/disable the eventstream feature of the ARM
566 architected timer so that code using WFE-based polling
567 loops can be debugged more effectively on production
570 clocksource.max_cswd_read_retries= [KNL]
571 Number of clocksource_watchdog() retries due to
572 external delays before the clock will be marked
573 unstable. Defaults to three retries, that is,
574 four attempts to read the clock under test.
576 clearcpuid=BITNUM[,BITNUM...] [X86]
577 Disable CPUID feature X for the kernel. See
578 arch/x86/include/asm/cpufeatures.h for the valid bit
579 numbers. Note the Linux specific bits are not necessarily
580 stable over kernel options, but the vendor specific
582 Also note that user programs calling CPUID directly
583 or using the feature without checking anything
584 will still see it. This just prevents it from
585 being used by the kernel or shown in /proc/cpuinfo.
586 Also note the kernel might malfunction if you disable
589 cma=nn[MG]@[start[MG][-end[MG]]]
591 Sets the size of kernel global memory area for
592 contiguous memory allocations and optionally the
593 placement constraint by the physical address range of
594 memory allocations. A value of 0 disables CMA
595 altogether. For more information, see
596 include/linux/dma-contiguous.h
598 cmo_free_hint= [PPC] Format: { yes | no }
599 Specify whether pages are marked as being inactive
600 when they are freed. This is used in CMO environments
601 to determine OS memory pressure for page stealing by
605 coherent_pool=nn[KMG] [ARM,KNL]
606 Sets the size of memory pool for coherent, atomic dma
607 allocations, by default set to 256K.
609 com20020= [HW,NET] ARCnet - COM20020 chipset
611 <io>[,<irq>[,<nodeID>[,<backplane>[,<ckp>[,<timeout>]]]]]
613 com90io= [HW,NET] ARCnet - COM90xx chipset (IO-mapped buffers)
617 ARCnet - COM90xx chipset (memory-mapped buffers)
618 Format: <io>[,<irq>[,<memstart>]]
620 condev= [HW,S390] console device
623 console= [KNL] Output console device and options.
625 tty<n> Use the virtual console device <n>.
629 Use the specified serial port. The options are of
630 the form "bbbbpnf", where "bbbb" is the baud rate,
631 "p" is parity ("n", "o", or "e"), "n" is number of
632 bits, and "f" is flow control ("r" for RTS or
633 omit it). Default is "9600n8".
635 See Documentation/admin-guide/serial-console.rst for more
637 Documentation/networking/netconsole.txt for an
640 uart[8250],io,<addr>[,options]
641 uart[8250],mmio,<addr>[,options]
642 uart[8250],mmio16,<addr>[,options]
643 uart[8250],mmio32,<addr>[,options]
644 uart[8250],0x<addr>[,options]
645 Start an early, polled-mode console on the 8250/16550
646 UART at the specified I/O port or MMIO address,
647 switching to the matching ttyS device later.
648 MMIO inter-register address stride is either 8-bit
649 (mmio), 16-bit (mmio16), or 32-bit (mmio32).
650 If none of [io|mmio|mmio16|mmio32], <addr> is assumed
651 to be equivalent to 'mmio'. 'options' are specified in
652 the same format described for ttyS above; if unspecified,
653 the h/w is not re-initialized.
655 hvc<n> Use the hypervisor console device <n>. This is for
656 both Xen and PowerPC hypervisors.
658 If the device connected to the port is not a TTY but a braille
659 device, prepend "brl," before the device type, for instance
661 For now, only VisioBraille is supported.
664 [KNL] Change console messages format
666 By default we print messages on consoles in
667 "[time stamp] text\n" format (time stamp may not be
668 printed, depending on CONFIG_PRINTK_TIME or
669 `printk_time' param).
671 Switch to syslog format: "<%u>[time stamp] text\n"
672 IOW, each message will have a facility and loglevel
673 prefix. The format is similar to one used by syslog()
674 syscall, or to executing "dmesg -S --raw" or to reading
677 consoleblank= [KNL] The console blank (screen saver) timeout in
678 seconds. A value of 0 disables the blank timer.
682 [KNL] Change the default value for
683 /proc/<pid>/coredump_filter.
684 See also Documentation/filesystems/proc.txt.
686 coresight_cpu_debug.enable
689 Enable/disable the CPU sampling based debugging.
690 0: default value, disable debugging
691 1: enable debugging at boot time
693 cpuidle.off=1 [CPU_IDLE]
694 disable the cpuidle sub-system
697 [CPU_IDLE] Name of the cpuidle governor to use.
699 cpufreq.off=1 [CPU_FREQ]
700 disable the cpufreq sub-system
703 [X86] Delay for N microsec between assert and de-assert
704 of APIC INIT to start processors. This delay occurs
705 on every CPU online, such as boot, and resume from suspend.
708 cpcihp_generic= [HW,PCI] Generic port I/O CompactPCI driver
710 <first_slot>,<last_slot>,<port>,<enum_bit>[,<debug>]
712 crashkernel=size[KMG][@offset[KMG]]
713 [KNL] Using kexec, Linux can switch to a 'crash kernel'
714 upon panic. This parameter reserves the physical
715 memory region [offset, offset + size] for that kernel
716 image. If '@offset' is omitted, then a suitable offset
717 is selected automatically.
718 [KNL, x86_64] select a region under 4G first, and
719 fall back to reserve region above 4G when '@offset'
720 hasn't been specified.
721 See Documentation/admin-guide/kdump/kdump.rst for further details.
723 crashkernel=range1:size1[,range2:size2,...][@offset]
724 [KNL] Same as above, but depends on the memory
725 in the running system. The syntax of range is
726 start-[end] where start and end are both
727 a memory unit (amount[KMG]). See also
728 Documentation/admin-guide/kdump/kdump.rst for an example.
730 crashkernel=size[KMG],high
731 [KNL, x86_64] range could be above 4G. Allow kernel
732 to allocate physical memory region from top, so could
733 be above 4G if system have more than 4G ram installed.
734 Otherwise memory region will be allocated below 4G, if
736 It will be ignored if crashkernel=X is specified.
737 crashkernel=size[KMG],low
738 [KNL, x86_64] range under 4G. When crashkernel=X,high
739 is passed, kernel could allocate physical memory region
740 above 4G, that cause second kernel crash on system
741 that require some amount of low memory, e.g. swiotlb
742 requires at least 64M+32K low memory, also enough extra
743 low memory is needed to make sure DMA buffers for 32-bit
744 devices won't run out. Kernel would try to allocate at
745 at least 256M below 4G automatically.
746 This one let user to specify own low range under 4G
747 for second kernel instead.
748 0: to disable low allocation.
749 It will be ignored when crashkernel=X,high is not used
750 or memory reserved is below 4G.
753 [KNL] Disable crypto self-tests
758 cs89x0_media= [HW,NET]
759 Format: { rj45 | aui | bnc }
762 See header of drivers/s390/block/dasd_devmap.c.
764 db9.dev[2|3]= [HW,JOY] Multisystem joystick support via parallel port
765 (one device per port)
766 Format: <port#>,<type>
767 See also Documentation/input/devices/joystick-parport.rst
769 ddebug_query= [KNL,DYNAMIC_DEBUG] Enable debug messages at early boot
771 Documentation/admin-guide/dynamic-debug-howto.rst for
772 details. Deprecated, see dyndbg.
774 debug [KNL] Enable kernel debugging (events log level).
777 [KNL] Enable printing [hashed] pointers early in the
778 boot sequence. If enabled, we use a weak hash instead
779 of siphash to hash pointers. Use this option if you are
780 seeing instances of '(___ptrval___)') and need to see a
781 value (hashed pointer) instead. Cryptographically
782 insecure, please do not use on production kernels.
785 [KNL] verbose self-tests
787 Print debugging info while doing the locking API
789 We default to 0 (no extra messages), setting it to
790 1 will print _a lot_ more information - normally
791 only useful to kernel developers.
793 debug_objects [KNL] Enable object debugging
796 [KNL] Disable object debugging
798 debug_guardpage_minorder=
799 [KNL] When CONFIG_DEBUG_PAGEALLOC is set, this
800 parameter allows control of the order of pages that will
801 be intentionally kept free (and hence protected) by the
802 buddy allocator. Bigger value increase the probability
803 of catching random memory corruption, but reduce the
804 amount of memory for normal system use. The maximum
805 possible value is MAX_ORDER/2. Setting this parameter
806 to 1 or 2 should be enough to identify most random
807 memory corruption problems caused by bugs in kernel or
808 driver code when a CPU writes to (or reads from) a
809 random memory location. Note that there exists a class
810 of memory corruptions problems caused by buggy H/W or
811 F/W or by drivers badly programing DMA (basically when
812 memory is written at bus level and the CPU MMU is
813 bypassed) which are not detectable by
814 CONFIG_DEBUG_PAGEALLOC, hence this option will not help
815 tracking down these problems.
818 [KNL] When CONFIG_DEBUG_PAGEALLOC is set, this parameter
819 enables the feature at boot time. By default, it is
820 disabled and the system will work mostly the same as a
821 kernel built without CONFIG_DEBUG_PAGEALLOC.
822 Note: to get most of debug_pagealloc error reports, it's
823 useful to also enable the page_owner functionality.
824 on: enable the feature
826 debugpat [X86] Enable PAT debugging
828 decnet.addr= [HW,NET]
829 Format: <area>[,<node>]
830 See also Documentation/networking/decnet.txt.
833 [same as hugepagesz=] The size of the default
834 HugeTLB page size. This is the size represented by
835 the legacy /proc/ hugepages APIs, used for SHM, and
836 default size when mounting hugetlbfs filesystems.
837 Defaults to the default architecture's huge page size
840 deferred_probe_timeout=
841 [KNL] Debugging option to set a timeout in seconds for
842 deferred probe to give up waiting on dependencies to
843 probe. Only specific dependencies (subsystems or
844 drivers) that have opted in will be ignored. A timeout of 0
845 will timeout at the end of initcalls. This option will also
846 dump out devices still on the deferred probe list after
850 Set number of hash buckets for dentry cache.
852 disable_1tb_segments [PPC]
853 Disables the use of 1TB hash page table segments. This
854 causes the kernel to fall back to 256MB segments which
855 can be useful when debugging issues that require an SLB
859 See Documentation/networking/ipv6.txt.
862 [KNL] Under CONFIG_HARDENED_USERCOPY, whether
863 hardening is enabled for this boot. Hardened
864 usercopy checking is used to protect the kernel
865 from reading or writing beyond known memory
866 allocation boundaries as a proactive defense
867 against bounds-checking flaws in the kernel's
868 copy_to_user()/copy_from_user() interface.
869 on Perform hardened usercopy checks (default).
870 off Disable hardened usercopy checks.
873 Disable RADIX MMU mode on POWER9
876 Disable TLBIE instruction. Currently does not work
877 with KVM, with HASH MMU, or with coherent accelerators.
879 disable_cpu_apicid= [X86,APIC,SMP]
881 The number of initial APIC ID for the
882 corresponding CPU to be disabled at boot,
883 mostly used for the kdump 2nd kernel to
884 disable BSP to wake up multiple CPUs without
885 causing system reset or hang due to sending
888 perf_v4_pmi= [X86,INTEL]
890 Disable Intel PMU counter freezing feature.
891 The feature only exists starting from
892 Arch Perfmon v4 (Skylake and newer).
894 disable_ddw [PPC/PSERIES]
895 Disable Dynamic DMA Window support. Use this if
896 to workaround buggy firmware.
899 See Documentation/networking/ipv6.txt.
901 disable_mtrr_cleanup [X86]
902 The kernel tries to adjust MTRR layout from continuous
903 to discrete, to make X server driver able to add WB
904 entry later. This parameter disables that.
906 disable_mtrr_trim [X86, Intel and AMD only]
907 By default the kernel will trim any uncacheable
908 memory out of your available memory pool based on
909 MTRR settings. This parameter disables that behavior,
910 possibly causing your machine to run very slowly.
912 disable_timer_pin_1 [X86]
913 Disable PIN 1 of APIC timer
914 Can be useful to work around chipset bugs.
916 dis_ucode_ldr [X86] Disable the microcode loader.
918 dma_debug=off If the kernel is compiled with DMA_API_DEBUG support,
919 this option disables the debugging code at boot.
921 dma_debug_entries=<number>
922 This option allows to tune the number of preallocated
923 entries for DMA-API debugging code. One entry is
924 required per DMA-API allocation. Use this if the
925 DMA-API debugging code disables itself because the
926 architectural default is too low.
928 dma_debug_driver=<driver_name>
929 With this option the DMA-API debugging driver
930 filter feature can be enabled at boot time. Just
931 pass the driver to filter for as the parameter.
932 The filter can be disabled or changed to another
933 driver later using sysfs.
935 driver_async_probe= [KNL]
936 List of driver names to be probed asynchronously.
937 Format: <driver_name1>,<driver_name2>...
939 drm.edid_firmware=[<connector>:]<file>[,[<connector>:]<file>]
940 Broken monitors, graphic adapters, KVMs and EDIDless
941 panels may send no or incorrect EDID data sets.
942 This parameter allows to specify an EDID data sets
943 in the /lib/firmware directory that are used instead.
944 Generic built-in EDID data sets are used, if one of
945 edid/1024x768.bin, edid/1280x1024.bin,
946 edid/1680x1050.bin, or edid/1920x1080.bin is given
947 and no file with the same name exists. Details and
948 instructions how to build your own EDID data are
949 available in Documentation/driver-api/edid.rst. An EDID
950 data set will only be used for a particular connector,
951 if its name and a colon are prepended to the EDID
952 name. Each connector may use a unique EDID data
953 set by separating the files with a comma. An EDID
954 data set with no connector name will be used for
955 any connectors not explicitly specified.
960 Format: {"off" | "known"}
961 Control how the dt_cpu_ftrs device-tree binding is
962 used for CPU feature discovery and setup (if it
964 off: Do not use it, fall back to legacy cpu table.
965 known: Do not pass through unknown features to guests
966 or userspace, only those that the kernel is aware of.
968 dump_apple_properties [X86]
969 Dump name and content of EFI device properties on
970 x86 Macs. Useful for driver authors to determine
971 what data is available or for reverse-engineering.
973 dyndbg[="val"] [KNL,DYNAMIC_DEBUG]
974 module.dyndbg[="val"]
975 Enable debug messages at boot time. See
976 Documentation/admin-guide/dynamic-debug-howto.rst
979 nompx [X86] Disables Intel Memory Protection Extensions.
980 See Documentation/x86/intel_mpx.rst for more
981 information about the feature.
983 nopku [X86] Disable Memory Protection Keys CPU feature found
986 module.async_probe [KNL]
987 Enable asynchronous probe on this module.
989 early_ioremap_debug [KNL]
990 Enable debug messages in early_ioremap support. This
991 is useful for tracking down temporary early mappings
992 which are not unmapped.
994 earlycon= [KNL] Output early console device and options.
996 [ARM64] The early console is determined by the
997 stdout-path property in device tree's chosen node,
998 or determined by the ACPI SPCR table.
1000 [X86] When used with no options the early console is
1001 determined by the ACPI SPCR table.
1003 cdns,<addr>[,options]
1004 Start an early, polled-mode console on a Cadence
1005 (xuartps) serial port at the specified address. Only
1006 supported option is baud rate. If baud rate is not
1007 specified, the serial port must already be setup and
1010 uart[8250],io,<addr>[,options]
1011 uart[8250],mmio,<addr>[,options]
1012 uart[8250],mmio32,<addr>[,options]
1013 uart[8250],mmio32be,<addr>[,options]
1014 uart[8250],0x<addr>[,options]
1015 Start an early, polled-mode console on the 8250/16550
1016 UART at the specified I/O port or MMIO address.
1017 MMIO inter-register address stride is either 8-bit
1018 (mmio) or 32-bit (mmio32 or mmio32be).
1019 If none of [io|mmio|mmio32|mmio32be], <addr> is assumed
1020 to be equivalent to 'mmio'. 'options' are specified
1021 in the same format described for "console=ttyS<n>"; if
1022 unspecified, the h/w is not initialized.
1026 Start an early, polled-mode console on a pl011 serial
1027 port at the specified address. The pl011 serial port
1028 must already be setup and configured. Options are not
1029 yet supported. If 'mmio32' is specified, then only
1030 the driver will use only 32-bit accessors to read/write
1031 the device registers.
1034 Start an early, polled-mode console on a meson serial
1035 port at the specified address. The serial port must
1036 already be setup and configured. Options are not yet
1040 Start an early, polled-mode console on an msm serial
1041 port at the specified address. The serial port
1042 must already be setup and configured. Options are not
1045 msm_serial_dm,<addr>
1046 Start an early, polled-mode console on an msm serial
1047 dm port at the specified address. The serial port
1048 must already be setup and configured. Options are not
1052 Start an early, polled-mode console on a serial port
1053 of an Actions Semi SoC, such as S500 or S900, at the
1054 specified address. The serial port must already be
1055 setup and configured. Options are not yet supported.
1058 Start an early, polled-mode console on a serial port
1059 of an RDA Micro SoC, such as RDA8810PL, at the
1060 specified address. The serial port must already be
1061 setup and configured. Options are not yet supported.
1064 Use RISC-V SBI (Supervisor Binary Interface) for early
1067 smh Use ARM semihosting calls for early console.
1075 Use early console provided by serial driver available
1076 on Samsung SoCs, requires selecting proper type and
1077 a correct base address of the selected UART port. The
1078 serial port must already be setup and configured.
1079 Options are not yet supported.
1082 Start an early, polled-mode console on a lantiq serial
1083 (lqasc) port at the specified address. The serial port
1084 must already be setup and configured. Options are not
1089 Use early console provided by Freescale LP UART driver
1090 found on Freescale Vybrid and QorIQ LS1021A processors.
1091 A valid base address must be provided, and the serial
1092 port must already be setup and configured.
1095 Start an early, polled-mode console on the
1096 Armada 3700 serial port at the specified
1097 address. The serial port must already be setup
1098 and configured. Options are not yet supported.
1101 Start an early, polled-mode console on a Qualcomm
1102 Generic Interface (GENI) based serial port at the
1103 specified address. The serial port must already be
1104 setup and configured. Options are not yet supported.
1107 Start an early, unaccelerated console on the EFI
1108 memory mapped framebuffer (if available). On cache
1109 coherent non-x86 systems that use system memory for
1110 the framebuffer, pass the 'ram' option so that it is
1111 mapped with the correct attributes.
1114 Use early console provided by Freescale LinFlex UART
1115 serial driver for NXP S32V234 SoCs. A valid base
1116 address must be provided, and the serial port must
1117 already be setup and configured.
1119 earlyprintk= [X86,SH,ARM,M68k,S390]
1123 earlyprintk=serial[,ttySn[,baudrate]]
1124 earlyprintk=serial[,0x...[,baudrate]]
1125 earlyprintk=ttySn[,baudrate]
1126 earlyprintk=dbgp[debugController#]
1127 earlyprintk=pciserial[,force],bus:device.function[,baudrate]
1128 earlyprintk=xdbc[xhciController#]
1130 earlyprintk is useful when the kernel crashes before
1131 the normal console is initialized. It is not enabled by
1132 default because it has some cosmetic problems.
1134 Append ",keep" to not disable it when the real console
1137 Only one of vga, efi, serial, or usb debug port can
1140 Currently only ttyS0 and ttyS1 may be specified by
1141 name. Other I/O ports may be explicitly specified
1142 on some architectures (x86 and arm at least) by
1143 replacing ttySn with an I/O port address, like this:
1144 earlyprintk=serial,0x1008,115200
1145 You can find the port for a given device in
1146 /proc/tty/driver/serial:
1147 2: uart:ST16650V2 port:00001008 irq:18 ...
1149 Interaction with the standard serial driver is not
1152 The VGA and EFI output is eventually overwritten by
1155 The xen output can only be used by Xen PV guests.
1157 The sclp output can only be used on s390.
1159 The optional "force" to "pciserial" enables use of a
1160 PCI device even when its classcode is not of the
1163 edac_report= [HW,EDAC] Control how to report EDAC event
1164 Format: {"on" | "off" | "force"}
1165 on: enable EDAC to report H/W event. May be overridden
1166 by other higher priority error reporting module.
1167 off: disable H/W event reporting through EDAC.
1168 force: enforce the use of EDAC to report H/W event.
1171 ekgdboc= [X86,KGDB] Allow early kernel console debugging
1174 This is designed to be used in conjunction with
1175 the boot argument: earlyprintk=vga
1178 Format: {"off" | "on" | "skip[mbr]"}
1181 Format: { "old_map", "nochunk", "noruntime", "debug" }
1182 old_map [X86-64]: switch to the old ioremap-based EFI
1183 runtime services mapping. 32-bit still uses this one by
1185 nochunk: disable reading files in "chunks" in the EFI
1186 boot stub, as chunking can cause problems with some
1187 firmware implementations.
1188 noruntime : disable EFI runtime services support
1189 debug: enable misc debug output
1191 efi_no_storage_paranoia [EFI; X86]
1192 Using this parameter you can use more than 50% of
1193 your efi variable storage. Use this parameter only if
1194 you are really sure that your UEFI does sane gc and
1195 fulfills the spec otherwise your board may brick.
1197 efi_fake_mem= nn[KMG]@ss[KMG]:aa[,nn[KMG]@ss[KMG]:aa,..] [EFI; X86]
1198 Add arbitrary attribute to specific memory range by
1199 updating original EFI memory map.
1200 Region of memory which aa attribute is added to is
1202 If efi_fake_mem=2G@4G:0x10000,2G@0x10a0000000:0x10000
1203 is specified, EFI_MEMORY_MORE_RELIABLE(0x10000)
1204 attribute is added to range 0x100000000-0x180000000 and
1205 0x10a0000000-0x1120000000.
1207 Using this parameter you can do debugging of EFI memmap
1208 related feature. For example, you can do debugging of
1209 Address Range Mirroring feature even if your box
1212 efivar_ssdt= [EFI; X86] Name of an EFI variable that contains an SSDT
1213 that is to be dynamically loaded by Linux. If there are
1214 multiple variables with the same name but with different
1215 vendor GUIDs, all of them will be loaded. See
1216 Documentation/admin-guide/acpi/ssdt-overlays.rst for details.
1219 eisa_irq_edge= [PARISC,HW]
1220 See header of drivers/parisc/eisa.c.
1223 See comment before function elanfreq_setup() in
1224 arch/x86/kernel/cpu/cpufreq/elanfreq.c.
1226 elfcorehdr=[size[KMG]@]offset[KMG] [IA64,PPC,SH,X86,S390]
1227 Specifies physical address of start of kernel core
1228 image elf header and optionally the size. Generally
1229 kexec loader will pass this option to capture kernel.
1230 See Documentation/admin-guide/kdump/kdump.rst for details.
1232 enable_mtrr_cleanup [X86]
1233 The kernel tries to adjust MTRR layout from continuous
1234 to discrete, to make X server driver able to add WB
1235 entry later. This parameter enables that.
1237 enable_timer_pin_1 [X86]
1238 Enable PIN 1 of APIC timer
1239 Can be useful to work around chipset bugs
1240 (in particular on some ATI chipsets).
1241 The kernel tries to set a reasonable default.
1243 enforcing [SELINUX] Set initial enforcing status.
1245 See security/selinux/Kconfig help text.
1246 0 -- permissive (log only, no denials).
1247 1 -- enforcing (deny and log).
1249 Value can be changed at runtime via /selinux/enforce.
1252 Disable Error Record Serialization Table (ERST)
1255 ether= [HW,NET] Ethernet cards parameters
1256 This option is obsoleted by the "netdev=" option, which
1257 has equivalent usage. See its documentation for details.
1261 Permit 'security.evm' to be updated regardless of
1262 current integrity status.
1266 fail_make_request=[KNL]
1267 General fault injection mechanism.
1268 Format: <interval>,<probability>,<space>,<times>
1269 See also Documentation/fault-injection/.
1272 See Documentation/admin-guide/blockdev/floppy.rst.
1274 force_pal_cache_flush
1275 [IA-64] Avoid check_sal_cache_flush which may hang on
1276 buggy SAL_CACHE_FLUSH implementations. Using this
1277 parameter will force ia64_sal_cache_flush to call
1278 ia64_pal_cache_flush instead of SAL_CACHE_FLUSH.
1281 Forcefully enable Physical Address Extension (PAE).
1282 Many Pentium M systems disable PAE but may have a
1283 functionally usable PAE implementation.
1284 Warning: use of this parameter will taint the kernel
1285 and may cause unknown problems.
1288 [FTRACE] will set and start the specified tracer
1289 as early as possible in order to facilitate early
1292 ftrace_dump_on_oops[=orig_cpu]
1293 [FTRACE] will dump the trace buffers on oops.
1294 If no parameter is passed, ftrace will dump
1295 buffers of all CPUs, but if you pass orig_cpu, it will
1296 dump only the buffer of the CPU that triggered the
1299 ftrace_filter=[function-list]
1300 [FTRACE] Limit the functions traced by the function
1301 tracer at boot up. function-list is a comma separated
1302 list of functions. This list can be changed at run
1303 time by the set_ftrace_filter file in the debugfs
1306 ftrace_notrace=[function-list]
1307 [FTRACE] Do not trace the functions specified in
1308 function-list. This list can be changed at run time
1309 by the set_ftrace_notrace file in the debugfs
1312 ftrace_graph_filter=[function-list]
1313 [FTRACE] Limit the top level callers functions traced
1314 by the function graph tracer at boot up.
1315 function-list is a comma separated list of functions
1316 that can be changed at run time by the
1317 set_graph_function file in the debugfs tracing directory.
1319 ftrace_graph_notrace=[function-list]
1320 [FTRACE] Do not trace from the functions specified in
1321 function-list. This list is a comma separated list of
1322 functions that can be changed at run time by the
1323 set_graph_notrace file in the debugfs tracing directory.
1325 ftrace_graph_max_depth=<uint>
1326 [FTRACE] Used with the function graph tracer. This is
1327 the max depth it will trace into a function. This value
1328 can be changed at run time by the max_graph_depth file
1329 in the tracefs tracing directory. default: 0 (no limit)
1332 [HW,JOY] Multisystem joystick and NES/SNES/PSX pad
1333 support via parallel port (up to 5 devices per port)
1334 Format: <port#>,<pad1>,<pad2>,<pad3>,<pad4>,<pad5>
1335 See also Documentation/input/devices/joystick-parport.rst
1339 gart_fix_e820= [X86_64] disable the fix e820 for K8 GART
1343 gcov_persist= [GCOV] When non-zero (default), profiling data for
1344 kernel modules is saved and remains accessible via
1345 debugfs, even when the module is unloaded/reloaded.
1346 When zero, profiling data is discarded and associated
1347 debugfs files are removed at module unload time.
1349 goldfish [X86] Enable the goldfish android emulator platform.
1350 Don't use this when you are not running on the
1353 gpt [EFI] Forces disk with valid GPT signature but
1354 invalid Protective MBR to be treated as GPT. If the
1355 primary GPT is corrupted, it enables the backup/alternate
1356 GPT to be used instead.
1358 grcan.enable0= [HW] Configuration of physical interface 0. Determines
1359 the "Enable 0" bit of the configuration register.
1362 grcan.enable1= [HW] Configuration of physical interface 1. Determines
1363 the "Enable 0" bit of the configuration register.
1366 grcan.select= [HW] Select which physical interface to use.
1369 grcan.txsize= [HW] Sets the size of the tx buffer.
1370 Format: <unsigned int> such that (txsize & ~0x1fffc0) == 0.
1372 grcan.rxsize= [HW] Sets the size of the rx buffer.
1373 Format: <unsigned int> such that (rxsize & ~0x1fffc0) == 0.
1376 gpio-mockup.gpio_mockup_ranges
1377 [HW] Sets the ranges of gpiochip of for this device.
1378 Format: <start1>,<end1>,<start2>,<end2>...
1380 hardlockup_all_cpu_backtrace=
1381 [KNL] Should the hard-lockup detector generate
1382 backtraces on all cpus.
1385 hashdist= [KNL,NUMA] Large hashes allocated during boot
1386 are distributed across NUMA nodes. Defaults on
1387 for 64-bit NUMA, off otherwise.
1388 Format: 0 | 1 (for off | on)
1390 hcl= [IA-64] SGI's Hardware Graph compatibility layer
1392 hd= [EIDE] (E)IDE hard drive subsystem geometry
1393 Format: <cyl>,<head>,<sect>
1396 Disable Hardware Error Source Table (HEST) support;
1397 corresponding firmware-first mode error processing
1398 logic will be disabled.
1400 highmem=nn[KMG] [KNL,BOOT] forces the highmem zone to have an exact
1401 size of <nn>. This works even on boxes that have no
1402 highmem otherwise. This also works to reduce highmem
1403 size on bigger boxes.
1405 highres= [KNL] Enable/disable high resolution timer mode.
1406 Valid parameters: "on", "off"
1411 hpet= [X86-32,HPET] option to control HPET usage
1412 Format: { enable (default) | disable | force |
1414 disable: disable HPET and use PIT instead
1415 force: allow force enabled of undocumented chips (ICH4,
1417 verbose: show contents of HPET registers during setup
1419 hpet_mmap= [X86, HPET_MMAP] Allow userspace to mmap HPET
1420 registers. Default set by CONFIG_HPET_MMAP_DEFAULT.
1422 hugepages= [HW,X86-32,IA-64] HugeTLB pages to allocate at boot.
1423 hugepagesz= [HW,IA-64,PPC,X86-64] The size of the HugeTLB pages.
1424 On x86-64 and powerpc, this option can be specified
1425 multiple times interleaved with hugepages= to reserve
1426 huge pages of different sizes. Valid pages sizes on
1427 x86-64 are 2M (when the CPU supports "pse") and 1G
1428 (when the CPU supports the "pdpe1gb" cpuinfo flag).
1431 [KNL] Should the hung task detector generate panics.
1434 A nonzero value instructs the kernel to panic when a
1435 hung task is detected. The default value is controlled
1436 by the CONFIG_BOOTPARAM_HUNG_TASK_PANIC build-time
1437 option. The value selected by this boot parameter can
1438 be changed later by the kernel.hung_task_panic sysctl.
1440 hvc_iucv= [S390] Number of z/VM IUCV hypervisor console (HVC)
1441 terminal devices. Valid values: 0..8
1442 hvc_iucv_allow= [S390] Comma-separated list of z/VM user IDs.
1443 If specified, z/VM IUCV HVC accepts connections
1444 from listed z/VM user IDs only.
1446 hv_nopvspin [X86,HYPER_V] Disables the paravirt spinlock optimizations
1447 which allow the hypervisor to 'idle' the
1448 guest on lock contention.
1451 Do not unregister boot console at start. This is only
1452 useful for debugging when something happens in the window
1453 between unregistering the boot console and initializing
1456 i2c_bus= [HW] Override the default board specific I2C bus speed
1457 or register an additional I2C bus that is not
1458 registered from board initialization code.
1462 i8042.debug [HW] Toggle i8042 debug mode
1463 i8042.unmask_kbd_data
1464 [HW] Enable printing of interrupt data from the KBD port
1465 (disabled by default, and as a pre-condition
1466 requires that i8042.debug=1 be enabled)
1467 i8042.direct [HW] Put keyboard port into non-translated mode
1468 i8042.dumbkbd [HW] Pretend that controller can only read data from
1469 keyboard and cannot control its state
1470 (Don't attempt to blink the leds)
1471 i8042.noaux [HW] Don't check for auxiliary (== mouse) port
1472 i8042.nokbd [HW] Don't check/create keyboard port
1473 i8042.noloop [HW] Disable the AUX Loopback command while probing
1475 i8042.nomux [HW] Don't check presence of an active multiplexing
1477 i8042.nopnp [HW] Don't use ACPIPnP / PnPBIOS to discover KBD/AUX
1479 i8042.notimeout [HW] Ignore timeout condition signalled by controller
1480 i8042.reset [HW] Reset the controller during init, cleanup and
1481 suspend-to-ram transitions, only during s2r
1482 transitions, or never reset
1483 Format: { 1 | Y | y | 0 | N | n }
1484 1, Y, y: always reset controller
1485 0, N, n: don't ever reset controller
1486 Default: only on s2r transitions on x86; most other
1487 architectures force reset to be always executed
1488 i8042.unlock [HW] Unlock (ignore) the keylock
1489 i8042.kbdreset [HW] Reset device connected to KBD port
1491 [HW] Allow deferred probing upon i8042 probe errors
1495 i8k.ignore_dmi [HW] Continue probing hardware even if DMI data
1496 indicates that the driver is running on unsupported
1498 i8k.force [HW] Activate i8k driver even if SMM BIOS signature
1499 does not match list of supported models.
1501 [HW] Report power status in /proc/i8k
1502 (disabled by default)
1503 i8k.restricted [HW] Allow controlling fans only if SYS_ADMIN
1506 i915.invert_brightness=
1507 [DRM] Invert the sense of the variable that is used to
1508 set the brightness of the panel backlight. Normally a
1509 brightness value of 0 indicates backlight switched off,
1510 and the maximum of the brightness value sets the backlight
1511 to maximum brightness. If this parameter is set to 0
1512 (default) and the machine requires it, or this parameter
1513 is set to 1, a brightness value of 0 sets the backlight
1514 to maximum brightness, and the maximum of the brightness
1515 value switches the backlight off.
1516 -1 -- never invert brightness
1517 0 -- machine default
1518 1 -- force brightness inversion
1521 Format: <io>[,<membase>[,<icn_id>[,<icn_id2>]]]
1523 ide-core.nodma= [HW] (E)IDE subsystem
1524 Format: =0.0 to prevent dma on hda, =0.1 hdb =1.0 hdc
1525 .vlb_clock .pci_clock .noflush .nohpa .noprobe .nowerr
1526 .cdrom .chs .ignore_cable are additional options
1527 See Documentation/ide/ide.rst.
1529 ide-generic.probe-mask= [HW] (E)IDE subsystem
1531 Probe mask for legacy ISA IDE ports. Depending on
1532 platform up to 6 ports are supported, enabled by
1533 setting corresponding bits in the mask to 1. The
1534 default value is 0x0, which has a special meaning.
1535 On systems that have PCI, it triggers scanning the
1536 PCI bus for the first and the second port, which
1537 are then probed. On systems without PCI the value
1538 of 0x0 enables probing the two first ports as if it
1541 ide-pci-generic.all-generic-ide [HW] (E)IDE subsystem
1542 Claim all unknown PCI IDE storage controllers.
1545 Format: idle=poll, idle=halt, idle=nomwait
1546 Poll forces a polling idle loop that can slightly
1547 improve the performance of waking up a idle CPU, but
1548 will use a lot of power and make the system run hot.
1550 idle=halt: Halt is forced to be used for CPU idle.
1551 In such case C2/C3 won't be used again.
1552 idle=nomwait: Disable mwait for CPU C-states
1554 ieee754= [MIPS] Select IEEE Std 754 conformance mode
1555 Format: { strict | legacy | 2008 | relaxed }
1558 Choose which programs will be accepted for execution
1559 based on the IEEE 754 NaN encoding(s) supported by
1560 the FPU and the NaN encoding requested with the value
1561 of an ELF file header flag individually set by each
1562 binary. Hardware implementations are permitted to
1563 support either or both of the legacy and the 2008 NaN
1566 Available settings are as follows:
1567 strict accept binaries that request a NaN encoding
1568 supported by the FPU
1569 legacy only accept legacy-NaN binaries, if supported
1571 2008 only accept 2008-NaN binaries, if supported
1573 relaxed accept any binaries regardless of whether
1574 supported by the FPU
1576 The FPU emulator is always able to support both NaN
1577 encodings, so if no FPU hardware is present or it has
1578 been disabled with 'nofpu', then the settings of
1579 'legacy' and '2008' strap the emulator accordingly,
1580 'relaxed' straps the emulator for both legacy-NaN and
1581 2008-NaN, whereas 'strict' enables legacy-NaN only on
1582 legacy processors and both NaN encodings on MIPS32 or
1585 The setting for ABS.fmt/NEG.fmt instruction execution
1586 mode generally follows that for the NaN encoding,
1587 except where unsupported by hardware.
1589 ignore_loglevel [KNL]
1590 Ignore loglevel setting - this will print /all/
1591 kernel messages to the console. Useful for debugging.
1592 We also add it as printk module parameter, so users
1593 could change it dynamically, usually by
1594 /sys/module/printk/parameters/ignore_loglevel.
1597 Ignore RLIMIT_DATA setting for data mappings,
1598 print warning at first misuse. Can be changed via
1599 /sys/module/kernel/parameters/ignore_rlimit_data.
1601 ihash_entries= [KNL]
1602 Set number of hash buckets for inode cache.
1604 ima_appraise= [IMA] appraise integrity measurements
1605 Format: { "off" | "enforce" | "fix" | "log" }
1608 ima_appraise_tcb [IMA] Deprecated. Use ima_policy= instead.
1609 The builtin appraise policy appraises all files
1612 ima_canonical_fmt [IMA]
1613 Use the canonical format for the binary runtime
1614 measurements, instead of host native format.
1617 Format: { md5 | sha1 | rmd160 | sha256 | sha384
1621 The list of supported hash algorithms is defined
1622 in crypto/hash_info.h.
1625 The builtin policies to load during IMA setup.
1626 Format: "tcb | appraise_tcb | secure_boot |
1629 The "tcb" policy measures all programs exec'd, files
1630 mmap'd for exec, and all files opened with the read
1631 mode bit set by either the effective uid (euid=0) or
1634 The "appraise_tcb" policy appraises the integrity of
1635 all files owned by root.
1637 The "secure_boot" policy appraises the integrity
1638 of files (eg. kexec kernel image, kernel modules,
1639 firmware, policy, etc) based on file signatures.
1641 The "fail_securely" policy forces file signature
1642 verification failure also on privileged mounted
1643 filesystems with the SB_I_UNVERIFIABLE_SIGNATURE
1646 ima_tcb [IMA] Deprecated. Use ima_policy= instead.
1647 Load a policy which meets the needs of the Trusted
1648 Computing Base. This means IMA will measure all
1649 programs exec'd, files mmap'd for exec, and all files
1650 opened for read by uid=0.
1653 Select one of defined IMA measurements template formats.
1654 Formats: { "ima" | "ima-ng" | "ima-sig" }
1658 [IMA] Define a custom template format.
1659 Format: { "field1|...|fieldN" }
1661 ima.ahash_minsize= [IMA] Minimum file size for asynchronous hash usage
1662 Format: <min_file_size>
1663 Set the minimal file size for using asynchronous hash.
1664 If left unspecified, ahash usage is disabled.
1666 ahash performance varies for different data sizes on
1667 different crypto accelerators. This option can be used
1668 to achieve the best performance for a particular HW.
1670 ima.ahash_bufsize= [IMA] Asynchronous hash buffer size
1672 Set hashing buffer size. Default: 4k.
1674 ahash performance varies for different chunk sizes on
1675 different crypto accelerators. This option can be used
1676 to achieve best performance for particular HW.
1680 Run specified binary instead of /sbin/init as init
1683 initcall_debug [KNL] Trace initcalls as they are executed. Useful
1684 for working out where the kernel is dying during
1687 initcall_blacklist= [KNL] Do not execute a comma-separated list of
1688 initcall functions. Useful for debugging built-in
1689 modules and initcalls.
1691 initrd= [BOOT] Specify the location of the initial ramdisk
1693 init_on_alloc= [MM] Fill newly allocated pages and heap objects with
1696 Default set by CONFIG_INIT_ON_ALLOC_DEFAULT_ON.
1698 init_on_free= [MM] Fill freed pages and heap objects with zeroes.
1700 Default set by CONFIG_INIT_ON_FREE_DEFAULT_ON.
1702 init_pkru= [x86] Specify the default memory protection keys rights
1703 register contents for all processes. 0x55555554 by
1704 default (disallow access to all but pkey 0). Can
1705 override in debugfs after boot.
1707 inport.irq= [HW] Inport (ATI XL and Microsoft) busmouse driver
1710 int_pln_enable [x86] Enable power limit notification interrupt
1712 integrity_audit=[IMA]
1713 Format: { "0" | "1" }
1714 0 -- basic integrity auditing messages. (Default)
1715 1 -- additional integrity auditing messages.
1717 intel_iommu= [DMAR] Intel IOMMU driver (DMAR) option
1719 Enable intel iommu driver.
1721 Disable intel iommu driver.
1722 igfx_off [Default Off]
1723 By default, gfx is mapped as normal device. If a gfx
1724 device has a dedicated DMAR unit, the DMAR unit is
1725 bypassed by not enabling DMAR with this option. In
1726 this case, gfx device will use physical address for
1729 With this option iommu will not optimize to look
1730 for io virtual address below 32-bit forcing dual
1731 address cycle on pci bus for cards supporting greater
1732 than 32-bit addressing. The default is to look
1733 for translation below 32-bit and if not available
1734 then look in the higher range.
1735 strict [Default Off]
1736 With this option on every unmap_single operation will
1737 result in a hardware IOTLB flush operation as opposed
1738 to batching them for performance.
1739 sp_off [Default Off]
1740 By default, super page will be supported if Intel IOMMU
1741 has the capability. With this option, super page will
1744 By default, scalable mode will be disabled even if the
1745 hardware advertises that it has support for the scalable
1746 mode translation. With this option set, scalable mode
1747 will be used on hardware which claims to support it.
1748 tboot_noforce [Default Off]
1749 Do not force the Intel IOMMU enabled under tboot.
1750 By default, tboot will force Intel IOMMU on, which
1751 could harm performance of some high-throughput
1752 devices like 40GBit network cards, even if identity
1754 Note that using this option lowers the security
1755 provided by tboot because it makes the system
1756 vulnerable to DMA attacks.
1757 nobounce [Default off]
1758 Disable bounce buffer for unstrusted devices such as
1759 the Thunderbolt devices. This will treat the untrusted
1760 devices as the trusted ones, hence might expose security
1761 risks of DMA attacks.
1763 intel_idle.max_cstate= [KNL,HW,ACPI,X86]
1764 0 disables intel_idle and fall back on acpi_idle.
1765 1 to 9 specify maximum depth of C-state.
1769 Do not enable intel_pstate as the default
1770 scaling driver for the supported processors
1772 Use intel_pstate as a scaling driver, but configure it
1773 to work with generic cpufreq governors (instead of
1774 enabling its internal governor). This mode cannot be
1775 used along with the hardware-managed P-states (HWP)
1778 Enable intel_pstate on systems that prohibit it by default
1779 in favor of acpi-cpufreq. Forcing the intel_pstate driver
1780 instead of acpi-cpufreq may disable platform features, such
1781 as thermal controls and power capping, that rely on ACPI
1782 P-States information being indicated to OSPM and therefore
1783 should be used with caution. This option does not work with
1784 processors that aren't supported by the intel_pstate driver
1785 or on platforms that use pcc-cpufreq instead of acpi-cpufreq.
1787 Do not enable hardware P state control (HWP)
1790 Only load intel_pstate on systems which support
1791 hardware P state control (HWP) if available.
1793 Enforce ACPI _PPC performance limits. If the Fixed ACPI
1794 Description Table, specifies preferred power management
1795 profile as "Enterprise Server" or "Performance Server",
1796 then this feature is turned on by default.
1798 Allow per-logical-CPU P-State performance control limits using
1799 cpufreq sysfs interface
1801 intremap= [X86-64, Intel-IOMMU]
1802 on enable Interrupt Remapping (default)
1803 off disable Interrupt Remapping
1804 nosid disable Source ID checking
1806 BIOS x2APIC opt-out request will be ignored
1807 nopost disable Interrupt Posting
1809 iomem= Disable strict checking of access to MMIO memory
1810 strict regions from userspace.
1825 nobypass [PPC/POWERNV]
1826 Disable IOMMU bypass, using IOMMU for PCI devices.
1828 iommu.strict= [ARM64] Configure TLB invalidation behaviour
1829 Format: { "0" | "1" }
1831 Request that DMA unmap operations use deferred
1832 invalidation of hardware TLBs, for increased
1833 throughput at the cost of reduced device isolation.
1834 Will fall back to strict mode if not supported by
1835 the relevant IOMMU driver.
1836 1 - Strict mode (default).
1837 DMA unmap operations invalidate IOMMU hardware TLBs
1841 [ARM64, X86] Configure DMA to bypass the IOMMU by default.
1842 Format: { "0" | "1" }
1843 0 - Use IOMMU translation for DMA.
1844 1 - Bypass the IOMMU for DMA.
1845 unset - Use value of CONFIG_IOMMU_DEFAULT_PASSTHROUGH.
1847 io7= [HW] IO7 for Marvel based alpha systems
1848 See comment before marvel_specify_io7 in
1849 arch/alpha/kernel/core_marvel.c.
1851 io_delay= [X86] I/O delay method
1853 Standard port 0x80 based delay
1855 Alternate port 0xed based delay (needed on some systems)
1857 Simple two microseconds delay
1862 See Documentation/filesystems/nfs/nfsroot.txt.
1864 ipcmni_extend [KNL] Extend the maximum number of unique System V
1865 IPC identifiers from 32,768 to 16,777,216.
1867 irqaffinity= [SMP] Set the default irq affinity mask
1868 The argument is a cpu list, as described above.
1870 irqchip.gicv2_force_probe=
1873 Force the kernel to look for the second 4kB page
1874 of a GICv2 controller even if the memory range
1875 exposed by the device tree is too small.
1877 irqchip.gicv3_nolpi=
1879 Force the kernel to ignore the availability of
1880 LPIs (and by consequence ITSs). Intended for system
1881 that use the kernel as a bootloader, and thus want
1882 to let secondary kernels in charge of setting up
1885 irqchip.gicv3_pseudo_nmi= [ARM64]
1886 Enables support for pseudo-NMIs in the kernel. This
1887 requires the kernel to be built with
1888 CONFIG_ARM64_PSEUDO_NMI.
1891 When an interrupt is not handled search all handlers
1892 for it. Intended to get systems with badly broken
1896 When an interrupt is not handled search all handlers
1897 for it. Also check all handlers each timer
1898 interrupt. Intended to get systems with badly broken
1902 Format: <RDP>,<reset>,<pci_scan>,<verbosity>
1904 isolcpus= [KNL,SMP,ISOL] Isolate a given set of CPUs from disturbance.
1905 [Deprecated - use cpusets instead]
1906 Format: [flag-list,]<cpu-list>
1908 Specify one or more CPUs to isolate from disturbances
1909 specified in the flag list (default: domain):
1912 Disable the tick when a single task runs.
1914 A residual 1Hz tick is offloaded to workqueues, which you
1915 need to affine to housekeeping through the global
1916 workqueue's affinity configured via the
1917 /sys/devices/virtual/workqueue/cpumask sysfs file, or
1918 by using the 'domain' flag described below.
1920 NOTE: by default the global workqueue runs on all CPUs,
1921 so to protect individual CPUs the 'cpumask' file has to
1922 be configured manually after bootup.
1925 Isolate from the general SMP balancing and scheduling
1926 algorithms. Note that performing domain isolation this way
1927 is irreversible: it's not possible to bring back a CPU to
1928 the domains once isolated through isolcpus. It's strongly
1929 advised to use cpusets instead to disable scheduler load
1930 balancing through the "cpuset.sched_load_balance" file.
1931 It offers a much more flexible interface where CPUs can
1932 move in and out of an isolated set anytime.
1934 You can move a process onto or off an "isolated" CPU via
1935 the CPU affinity syscalls or cpuset.
1936 <cpu number> begins at 0 and the maximum value is
1937 "number of CPUs in system - 1".
1939 The format of <cpu-list> is described above.
1945 ivrs_ioapic [HW,X86_64]
1946 Provide an override to the IOAPIC-ID<->DEVICE-ID
1947 mapping provided in the IVRS ACPI table. For
1948 example, to map IOAPIC-ID decimal 10 to
1949 PCI device 00:14.0 write the parameter as:
1950 ivrs_ioapic[10]=00:14.0
1952 ivrs_hpet [HW,X86_64]
1953 Provide an override to the HPET-ID<->DEVICE-ID
1954 mapping provided in the IVRS ACPI table. For
1955 example, to map HPET-ID decimal 0 to
1956 PCI device 00:14.0 write the parameter as:
1957 ivrs_hpet[0]=00:14.0
1959 ivrs_acpihid [HW,X86_64]
1960 Provide an override to the ACPI-HID:UID<->DEVICE-ID
1961 mapping provided in the IVRS ACPI table. For
1962 example, to map UART-HID:UID AMD0020:0 to
1963 PCI device 00:14.5 write the parameter as:
1964 ivrs_acpihid[00:14.5]=AMD0020:0
1966 js= [HW,JOY] Analog joystick
1967 See Documentation/input/joydev/joystick.rst.
1970 When CONFIG_RANDOMIZE_BASE is set, this disables
1971 kernel and module base offset ASLR (Address Space
1972 Layout Randomization).
1975 [KNL] Enforce KASAN (Kernel Address Sanitizer) to print
1976 report on every invalid memory access. Without this
1977 parameter KASAN will print report only for the first
1982 kernelcore= [KNL,X86,IA-64,PPC]
1983 Format: nn[KMGTPE] | nn% | "mirror"
1984 This parameter specifies the amount of memory usable by
1985 the kernel for non-movable allocations. The requested
1986 amount is spread evenly throughout all nodes in the
1987 system as ZONE_NORMAL. The remaining memory is used for
1988 movable memory in its own zone, ZONE_MOVABLE. In the
1989 event, a node is too small to have both ZONE_NORMAL and
1990 ZONE_MOVABLE, kernelcore memory will take priority and
1991 other nodes will have a larger ZONE_MOVABLE.
1993 ZONE_MOVABLE is used for the allocation of pages that
1994 may be reclaimed or moved by the page migration
1995 subsystem. Note that allocations like PTEs-from-HighMem
1996 still use the HighMem zone if it exists, and the Normal
1997 zone if it does not.
1999 It is possible to specify the exact amount of memory in
2000 the form of "nn[KMGTPE]", a percentage of total system
2001 memory in the form of "nn%", or "mirror". If "mirror"
2002 option is specified, mirrored (reliable) memory is used
2003 for non-movable allocations and remaining memory is used
2004 for Movable pages. "nn[KMGTPE]", "nn%", and "mirror"
2005 are exclusive, so you cannot specify multiple forms.
2007 kgdbdbgp= [KGDB,HW] kgdb over EHCI usb debug port.
2008 Format: <Controller#>[,poll interval]
2009 The controller # is the number of the ehci usb debug
2010 port as it is probed via PCI. The poll interval is
2011 optional and is the number seconds in between
2012 each poll cycle to the debug port in case you need
2013 the functionality for interrupting the kernel with
2014 gdb or control-c on the dbgp connection. When
2015 not using this parameter you use sysrq-g to break into
2016 the kernel debugger.
2018 kgdboc= [KGDB,HW] kgdb over consoles.
2019 Requires a tty driver that supports console polling,
2020 or a supported polling keyboard driver (non-usb).
2021 Serial only format: <serial_device>[,baud]
2022 keyboard only format: kbd
2023 keyboard and serial format: kbd,<serial_device>[,baud]
2024 Optional Kernel mode setting:
2025 kms, kbd format: kms,kbd
2026 kms, kbd and serial format: kms,kbd,<ser_dev>[,baud]
2028 kgdbwait [KGDB] Stop kernel execution and enter the
2029 kernel debugger at the earliest opportunity.
2031 kmac= [MIPS] korina ethernet MAC address.
2032 Configure the RouterBoard 532 series on-chip
2033 Ethernet adapter MAC address.
2035 kmemleak= [KNL] Boot-time kmemleak enable/disable
2036 Valid arguments: on, off
2038 Built with CONFIG_DEBUG_KMEMLEAK_DEFAULT_OFF=y,
2041 kprobe_event=[probe-list]
2042 [FTRACE] Add kprobe events and enable at boot time.
2043 The probe-list is a semicolon delimited list of probe
2044 definitions. Each definition is same as kprobe_events
2045 interface, but the parameters are comma delimited.
2046 For example, to add a kprobe event on vfs_read with
2047 arg1 and arg2, add to the command line;
2049 kprobe_event=p,vfs_read,$arg1,$arg2
2051 See also Documentation/trace/kprobetrace.rst "Kernel
2052 Boot Parameter" section.
2054 kpti= [ARM64] Control page table isolation of user
2055 and kernel address spaces.
2056 Default: enabled on cores which need mitigation.
2060 kvm.ignore_msrs=[KVM] Ignore guest accesses to unhandled MSRs.
2061 Default is 0 (don't ignore, but inject #GP)
2063 kvm.enable_vmware_backdoor=[KVM] Support VMware backdoor PV interface.
2064 Default is false (don't support).
2066 kvm.mmu_audit= [KVM] This is a R/W parameter which allows audit
2071 [KVM] Controls the software workaround for the
2072 X86_BUG_ITLB_MULTIHIT bug.
2073 force : Always deploy workaround.
2074 off : Never deploy workaround.
2075 auto : Deploy workaround based on the presence of
2076 X86_BUG_ITLB_MULTIHIT.
2080 If the software workaround is enabled for the host,
2081 guests do need not to enable it for nested guests.
2083 kvm.nx_huge_pages_recovery_ratio=
2084 [KVM] Controls how many 4KiB pages are periodically zapped
2085 back to huge pages. 0 disables the recovery, otherwise if
2086 the value is N KVM will zap 1/Nth of the 4KiB pages every
2087 minute. The default is 60.
2089 kvm-amd.nested= [KVM,AMD] Allow nested virtualization in KVM/SVM.
2090 Default is 1 (enabled)
2092 kvm-amd.npt= [KVM,AMD] Disable nested paging (virtualized MMU)
2094 Default is 1 (enabled) if in 64-bit or 32-bit PAE mode.
2096 kvm-arm.vgic_v3_group0_trap=
2097 [KVM,ARM] Trap guest accesses to GICv3 group-0
2100 kvm-arm.vgic_v3_group1_trap=
2101 [KVM,ARM] Trap guest accesses to GICv3 group-1
2104 kvm-arm.vgic_v3_common_trap=
2105 [KVM,ARM] Trap guest accesses to GICv3 common
2108 kvm-arm.vgic_v4_enable=
2109 [KVM,ARM] Allow use of GICv4 for direct injection of
2112 kvm-intel.ept= [KVM,Intel] Disable extended page tables
2113 (virtualized MMU) support on capable Intel chips.
2114 Default is 1 (enabled)
2116 kvm-intel.emulate_invalid_guest_state=
2117 [KVM,Intel] Disable emulation of invalid guest state.
2118 Ignored if kvm-intel.enable_unrestricted_guest=1, as
2119 guest state is never invalid for unrestricted guests.
2120 This param doesn't apply to nested guests (L2), as KVM
2121 never emulates invalid L2 guest state.
2122 Default is 1 (enabled)
2124 kvm-intel.flexpriority=
2125 [KVM,Intel] Disable FlexPriority feature (TPR shadow).
2126 Default is 1 (enabled)
2129 [KVM,Intel] Enable VMX nesting (nVMX).
2130 Default is 0 (disabled)
2132 kvm-intel.unrestricted_guest=
2133 [KVM,Intel] Disable unrestricted guest feature
2134 (virtualized real and unpaged mode) on capable
2135 Intel chips. Default is 1 (enabled)
2137 kvm-intel.vmentry_l1d_flush=[KVM,Intel] Mitigation for L1 Terminal Fault
2140 Valid arguments: never, cond, always
2142 always: L1D cache flush on every VMENTER.
2143 cond: Flush L1D on VMENTER only when the code between
2144 VMEXIT and VMENTER can leak host memory.
2145 never: Disables the mitigation
2147 Default is cond (do L1 cache flush in specific instances)
2149 kvm-intel.vpid= [KVM,Intel] Disable Virtual Processor Identification
2150 feature (tagged TLBs) on capable Intel chips.
2151 Default is 1 (enabled)
2153 l1tf= [X86] Control mitigation of the L1TF vulnerability on
2156 The kernel PTE inversion protection is unconditionally
2157 enabled and cannot be disabled.
2160 Provides all available mitigations for the
2161 L1TF vulnerability. Disables SMT and
2162 enables all mitigations in the
2163 hypervisors, i.e. unconditional L1D flush.
2165 SMT control and L1D flush control via the
2166 sysfs interface is still possible after
2167 boot. Hypervisors will issue a warning
2168 when the first VM is started in a
2169 potentially insecure configuration,
2170 i.e. SMT enabled or L1D flush disabled.
2173 Same as 'full', but disables SMT and L1D
2174 flush runtime control. Implies the
2175 'nosmt=force' command line option.
2176 (i.e. sysfs control of SMT is disabled.)
2179 Leaves SMT enabled and enables the default
2180 hypervisor mitigation, i.e. conditional
2183 SMT control and L1D flush control via the
2184 sysfs interface is still possible after
2185 boot. Hypervisors will issue a warning
2186 when the first VM is started in a
2187 potentially insecure configuration,
2188 i.e. SMT enabled or L1D flush disabled.
2192 Disables SMT and enables the default
2193 hypervisor mitigation.
2195 SMT control and L1D flush control via the
2196 sysfs interface is still possible after
2197 boot. Hypervisors will issue a warning
2198 when the first VM is started in a
2199 potentially insecure configuration,
2200 i.e. SMT enabled or L1D flush disabled.
2203 Same as 'flush', but hypervisors will not
2204 warn when a VM is started in a potentially
2205 insecure configuration.
2208 Disables hypervisor mitigations and doesn't
2210 It also drops the swap size and available
2211 RAM limit restriction on both hypervisor and
2216 For details see: Documentation/admin-guide/hw-vuln/l1tf.rst
2222 lapic [X86-32,APIC] Enable the local APIC even if BIOS
2225 lapic= [x86,APIC] "notscdeadline" Do not use TSC deadline
2226 value for LAPIC timer one-shot implementation. Default
2227 back to the programmable timer unit in the LAPIC.
2229 lapic_timer_c2_ok [X86,APIC] trust the local apic timer
2232 libata.dma= [LIBATA] DMA control
2233 libata.dma=0 Disable all PATA and SATA DMA
2234 libata.dma=1 PATA and SATA Disk DMA only
2235 libata.dma=2 ATAPI (CDROM) DMA only
2236 libata.dma=4 Compact Flash DMA only
2237 Combinations also work, so libata.dma=3 enables DMA
2238 for disks and CDROMs, but not CFs.
2240 libata.ignore_hpa= [LIBATA] Ignore HPA limit
2241 libata.ignore_hpa=0 keep BIOS limits (default)
2242 libata.ignore_hpa=1 ignore limits, using full disk
2244 libata.noacpi [LIBATA] Disables use of ACPI in libata suspend/resume
2248 libata.force= [LIBATA] Force configurations. The format is comma
2249 separated list of "[ID:]VAL" where ID is
2250 PORT[.DEVICE]. PORT and DEVICE are decimal numbers
2251 matching port, link or device. Basically, it matches
2252 the ATA ID string printed on console by libata. If
2253 the whole ID part is omitted, the last PORT and DEVICE
2254 values are used. If ID hasn't been specified yet, the
2255 configuration applies to all ports, links and devices.
2257 If only DEVICE is omitted, the parameter applies to
2258 the port and all links and devices behind it. DEVICE
2259 number of 0 either selects the first device or the
2260 first fan-out link behind PMP device. It does not
2261 select the host link. DEVICE number of 15 selects the
2262 host link and device attached to it.
2264 The VAL specifies the configuration to force. As long
2265 as there's no ambiguity shortcut notation is allowed.
2266 For example, both 1.5 and 1.5G would work for 1.5Gbps.
2267 The following configurations can be forced.
2269 * Cable type: 40c, 80c, short40c, unk, ign or sata.
2270 Any ID with matching PORT is used.
2272 * SATA link speed limit: 1.5Gbps or 3.0Gbps.
2274 * Transfer mode: pio[0-7], mwdma[0-4] and udma[0-7].
2275 udma[/][16,25,33,44,66,100,133] notation is also
2278 * [no]ncq: Turn on or off NCQ.
2280 * [no]ncqtrim: Turn off queued DSM TRIM.
2282 * nohrst, nosrst, norst: suppress hard, soft
2285 * rstonce: only attempt one reset during
2286 hot-unplug link recovery
2288 * dump_id: dump IDENTIFY data.
2290 * atapi_dmadir: Enable ATAPI DMADIR bridge support
2292 * disable: Disable this device.
2294 If there are multiple matching configurations changing
2295 the same attribute, the last one is used.
2297 memblock=debug [KNL] Enable memblock debug messages.
2299 load_ramdisk= [RAM] List of ramdisks to load from floppy
2300 See Documentation/admin-guide/blockdev/ramdisk.rst.
2302 lockd.nlm_grace_period=P [NFS] Assign grace period.
2305 lockd.nlm_tcpport=N [NFS] Assign TCP port.
2308 lockd.nlm_timeout=T [NFS] Assign timeout value.
2311 lockd.nlm_udpport=M [NFS] Assign UDP port.
2314 lockdown= [SECURITY]
2315 { integrity | confidentiality }
2316 Enable the kernel lockdown feature. If set to
2317 integrity, kernel features that allow userland to
2318 modify the running kernel are disabled. If set to
2319 confidentiality, kernel features that allow userland
2320 to extract confidential information from the kernel
2323 locktorture.nreaders_stress= [KNL]
2324 Set the number of locking read-acquisition kthreads.
2325 Defaults to being automatically set based on the
2326 number of online CPUs.
2328 locktorture.nwriters_stress= [KNL]
2329 Set the number of locking write-acquisition kthreads.
2331 locktorture.onoff_holdoff= [KNL]
2332 Set time (s) after boot for CPU-hotplug testing.
2334 locktorture.onoff_interval= [KNL]
2335 Set time (s) between CPU-hotplug operations, or
2336 zero to disable CPU-hotplug testing.
2338 locktorture.shuffle_interval= [KNL]
2339 Set task-shuffle interval (jiffies). Shuffling
2340 tasks allows some CPUs to go into dyntick-idle
2341 mode during the locktorture test.
2343 locktorture.shutdown_secs= [KNL]
2344 Set time (s) after boot system shutdown. This
2345 is useful for hands-off automated testing.
2347 locktorture.stat_interval= [KNL]
2348 Time (s) between statistics printk()s.
2350 locktorture.stutter= [KNL]
2351 Time (s) to stutter testing, for example,
2352 specifying five seconds causes the test to run for
2353 five seconds, wait for five seconds, and so on.
2354 This tests the locking primitive's ability to
2355 transition abruptly to and from idle.
2357 locktorture.torture_type= [KNL]
2358 Specify the locking implementation to test.
2360 locktorture.verbose= [KNL]
2361 Enable additional printk() statements.
2363 logibm.irq= [HW,MOUSE] Logitech Bus Mouse Driver
2366 loglevel= All Kernel Messages with a loglevel smaller than the
2367 console loglevel will be printed to the console. It can
2368 also be changed with klogd or other programs. The
2369 loglevels are defined as follows:
2371 0 (KERN_EMERG) system is unusable
2372 1 (KERN_ALERT) action must be taken immediately
2373 2 (KERN_CRIT) critical conditions
2374 3 (KERN_ERR) error conditions
2375 4 (KERN_WARNING) warning conditions
2376 5 (KERN_NOTICE) normal but significant condition
2377 6 (KERN_INFO) informational
2378 7 (KERN_DEBUG) debug-level messages
2380 log_buf_len=n[KMG] Sets the size of the printk ring buffer,
2381 in bytes. n must be a power of two and greater
2382 than the minimal size. The minimal size is defined
2383 by LOG_BUF_SHIFT kernel config parameter. There is
2384 also CONFIG_LOG_CPU_MAX_BUF_SHIFT config parameter
2385 that allows to increase the default size depending on
2386 the number of CPUs. See init/Kconfig for more details.
2388 logo.nologo [FB] Disables display of the built-in Linux logo.
2389 This may be used to provide more screen space for
2390 kernel log messages and is useful when debugging
2391 kernel boot problems.
2393 lp=0 [LP] Specify parallel ports to use, e.g,
2394 lp=port[,port...] lp=none,parport0 (lp0 not configured, lp1 uses
2395 lp=reset first parallel port). 'lp=0' disables the
2396 lp=auto printer driver. 'lp=reset' (which can be
2397 specified in addition to the ports) causes
2398 attached printers to be reset. Using
2399 lp=port1,port2,... specifies the parallel ports
2400 to associate lp devices with, starting with
2401 lp0. A port specification may be 'none' to skip
2402 that lp device, or a parport name such as
2403 'parport0'. Specifying 'lp=auto' instead of a
2404 port specification list means that device IDs
2405 from each port should be examined, to see if
2406 an IEEE 1284-compliant printer is attached; if
2407 so, the driver will manage that printer.
2408 See also header of drivers/char/lp.c.
2411 Sets loops_per_jiffy to given constant, thus avoiding
2412 time-consuming boot-time autodetection (up to 250 ms per
2413 CPU). 0 enables autodetection (default). To determine
2414 the correct value for your kernel, boot with normal
2415 autodetection and see what value is printed. Note that
2416 on SMP systems the preset will be applied to all CPUs,
2417 which is likely to cause problems if your CPUs need
2418 significantly divergent settings. An incorrect value
2419 will cause delays in the kernel to be wrong, leading to
2420 unpredictable I/O errors and other breakage. Although
2421 unlikely, in the extreme case this might damage your
2425 Format: <io>,<irq>,<dma>
2427 lsm.debug [SECURITY] Enable LSM initialization debugging output.
2430 [SECURITY] Choose order of LSM initialization. This
2431 overrides CONFIG_LSM, and the "security=" parameter.
2433 machvec= [IA-64] Force the use of a particular machine-vector
2434 (machvec) in a generic kernel.
2435 Example: machvec=hpzx1
2437 machtype= [Loongson] Share the same kernel image file between different
2439 Example: machtype=lemote-yeeloong-2f-7inch
2441 max_addr=nn[KMG] [KNL,BOOT,ia64] All physical memory greater
2442 than or equal to this physical address is ignored.
2444 maxcpus= [SMP] Maximum number of processors that an SMP kernel
2445 will bring up during bootup. maxcpus=n : n >= 0 limits
2446 the kernel to bring up 'n' processors. Surely after
2447 bootup you can bring up the other plugged cpu by executing
2448 "echo 1 > /sys/devices/system/cpu/cpuX/online". So maxcpus
2449 only takes effect during system bootup.
2450 While n=0 is a special case, it is equivalent to "nosmp",
2451 which also disables the IO APIC.
2453 max_loop= [LOOP] The number of loop block devices that get
2454 (loop.max_loop) unconditionally pre-created at init time. The default
2455 number is configured by BLK_DEV_LOOP_MIN_COUNT. Instead
2456 of statically allocating a predefined number, loop
2457 devices can be requested on-demand with the
2458 /dev/loop-control interface.
2460 mce [X86-32] Machine Check Exception
2462 mce=option [X86-64] See Documentation/x86/x86_64/boot-options.rst
2464 md= [HW] RAID subsystems devices and level
2465 See Documentation/admin-guide/md.rst.
2468 Format: <first>,<last>
2469 Specifies range of consoles to be captured by the MDA.
2472 Control mitigation for the Micro-architectural Data
2473 Sampling (MDS) vulnerability.
2475 Certain CPUs are vulnerable to an exploit against CPU
2476 internal buffers which can forward information to a
2477 disclosure gadget under certain conditions.
2479 In vulnerable processors, the speculatively
2480 forwarded data can be used in a cache side channel
2481 attack, to access data to which the attacker does
2482 not have direct access.
2484 This parameter controls the MDS mitigation. The
2487 full - Enable MDS mitigation on vulnerable CPUs
2488 full,nosmt - Enable MDS mitigation and disable
2489 SMT on vulnerable CPUs
2490 off - Unconditionally disable MDS mitigation
2492 On TAA-affected machines, mds=off can be prevented by
2493 an active TAA mitigation as both vulnerabilities are
2494 mitigated with the same mechanism so in order to disable
2495 this mitigation, you need to specify tsx_async_abort=off
2498 Not specifying this option is equivalent to
2501 For details see: Documentation/admin-guide/hw-vuln/mds.rst
2503 mem=nn[KMG] [KNL,BOOT] Force usage of a specific amount of memory
2504 Amount of memory to be used when the kernel is not able
2505 to see the whole system memory or for test.
2506 [X86] Work as limiting max address. Use together
2507 with memmap= to avoid physical address space collisions.
2508 Without memmap= PCI devices could be placed at addresses
2509 belonging to unused RAM.
2511 mem=nopentium [BUGS=X86-32] Disable usage of 4MB pages for kernel
2515 [KNL,SH] Allow user to override the default size for
2516 per-device physically contiguous DMA buffers.
2518 memhp_default_state=online/offline
2519 [KNL] Set the initial state for the memory hotplug
2520 onlining policy. If not specified, the default value is
2521 set according to the
2522 CONFIG_MEMORY_HOTPLUG_DEFAULT_ONLINE kernel config
2524 See Documentation/admin-guide/mm/memory-hotplug.rst.
2526 memmap=exactmap [KNL,X86] Enable setting of an exact
2527 E820 memory map, as specified by the user.
2528 Such memmap=exactmap lines can be constructed based on
2529 BIOS output or other requirements. See the memmap=nn@ss
2532 memmap=nn[KMG]@ss[KMG]
2533 [KNL] Force usage of a specific region of memory.
2534 Region of memory to be used is from ss to ss+nn.
2535 If @ss[KMG] is omitted, it is equivalent to mem=nn[KMG],
2536 which limits max address to nn[KMG].
2537 Multiple different regions can be specified,
2540 memmap=100M@2G,100M#3G,1G!1024G
2542 memmap=nn[KMG]#ss[KMG]
2543 [KNL,ACPI] Mark specific memory as ACPI data.
2544 Region of memory to be marked is from ss to ss+nn.
2546 memmap=nn[KMG]$ss[KMG]
2547 [KNL,ACPI] Mark specific memory as reserved.
2548 Region of memory to be reserved is from ss to ss+nn.
2549 Example: Exclude memory from 0x18690000-0x1869ffff
2550 memmap=64K$0x18690000
2552 memmap=0x10000$0x18690000
2553 Some bootloaders may need an escape character before '$',
2554 like Grub2, otherwise '$' and the following number
2557 memmap=nn[KMG]!ss[KMG]
2558 [KNL,X86] Mark specific memory as protected.
2559 Region of memory to be used, from ss to ss+nn.
2560 The memory region may be marked as e820 type 12 (0xc)
2561 and is NVDIMM or ADR memory.
2563 memmap=<size>%<offset>-<oldtype>+<newtype>
2564 [KNL,ACPI] Convert memory within the specified region
2565 from <oldtype> to <newtype>. If "-<oldtype>" is left
2566 out, the whole region will be marked as <newtype>,
2567 even if previously unavailable. If "+<newtype>" is left
2568 out, matching memory will be removed. Types are
2569 specified as e820 types, e.g., 1 = RAM, 2 = reserved,
2570 3 = ACPI, 12 = PRAM.
2572 memory_corruption_check=0/1 [X86]
2573 Some BIOSes seem to corrupt the first 64k of
2574 memory when doing things like suspend/resume.
2575 Setting this option will scan the memory
2576 looking for corruption. Enabling this will
2577 both detect corruption and prevent the kernel
2578 from using the memory being corrupted.
2579 However, its intended as a diagnostic tool; if
2580 repeatable BIOS-originated corruption always
2581 affects the same memory, you can use memmap=
2582 to prevent the kernel from using that memory.
2584 memory_corruption_check_size=size [X86]
2585 By default it checks for corruption in the low
2586 64k, making this memory unavailable for normal
2587 use. Use this parameter to scan for
2588 corruption in more or less memory.
2590 memory_corruption_check_period=seconds [X86]
2591 By default it checks for corruption every 60
2592 seconds. Use this parameter to check at some
2593 other rate. 0 disables periodic checking.
2595 memtest= [KNL,X86,ARM,PPC] Enable memtest
2597 default : 0 <disable>
2598 Specifies the number of memtest passes to be
2599 performed. Each pass selects another test
2600 pattern from a given set of patterns. Memtest
2601 fills the memory with this pattern, validates
2602 memory contents and reserves bad memory
2603 regions that are detected.
2605 mem_encrypt= [X86-64] AMD Secure Memory Encryption (SME) control
2606 Valid arguments: on, off
2607 Default (depends on kernel configuration option):
2608 on (CONFIG_AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT=y)
2609 off (CONFIG_AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT=n)
2610 mem_encrypt=on: Activate SME
2611 mem_encrypt=off: Do not activate SME
2613 Refer to Documentation/virt/kvm/amd-memory-encryption.rst
2614 for details on when memory encryption can be activated.
2616 mem_sleep_default= [SUSPEND] Default system suspend mode:
2617 s2idle - Suspend-To-Idle
2618 shallow - Power-On Suspend or equivalent (if supported)
2619 deep - Suspend-To-RAM or equivalent (if supported)
2620 See Documentation/admin-guide/pm/sleep-states.rst.
2622 meye.*= [HW] Set MotionEye Camera parameters
2623 See Documentation/media/v4l-drivers/meye.rst.
2625 mfgpt_irq= [IA-32] Specify the IRQ to use for the
2626 Multi-Function General Purpose Timers on AMD Geode
2629 mfgptfix [X86-32] Fix MFGPT timers on AMD Geode platforms when
2630 the BIOS has incorrectly applied a workaround. TinyBIOS
2631 version 0.98 is known to be affected, 0.99 fixes the
2632 problem by letting the user disable the workaround.
2636 min_addr=nn[KMG] [KNL,BOOT,ia64] All physical memory below this
2637 physical address is ignored.
2639 mini2440= [ARM,HW,KNL]
2640 Format:[0..2][b][c][t]
2642 MINI2440 configuration specification:
2643 0 - The attached screen is the 3.5" TFT
2644 1 - The attached screen is the 7" TFT
2645 2 - The VGA Shield is attached (1024x768)
2646 Leaving out the screen size parameter will not load
2647 the TFT driver, and the framebuffer will be left
2649 b - Enable backlight. The TFT backlight pin will be
2650 linked to the kernel VESA blanking code and a GPIO
2651 LED. This parameter is not necessary when using the
2653 c - Enable the s3c camera interface.
2654 t - Reserved for enabling touchscreen support. The
2655 touchscreen support is not enabled in the mainstream
2656 kernel as of 2.6.30, a preliminary port can be found
2657 in the "bleeding edge" mini2440 support kernel at
2658 http://repo.or.cz/w/linux-2.6/mini2440.git
2661 [X86,PPC,S390,ARM64] Control optional mitigations for
2662 CPU vulnerabilities. This is a set of curated,
2663 arch-independent options, each of which is an
2664 aggregation of existing arch-specific options.
2667 Disable all optional CPU mitigations. This
2668 improves system performance, but it may also
2669 expose users to several CPU vulnerabilities.
2670 Equivalent to: nopti [X86,PPC]
2672 nospectre_v1 [X86,PPC]
2674 nospectre_v2 [X86,PPC,S390,ARM64]
2675 spectre_v2_user=off [X86]
2676 spec_store_bypass_disable=off [X86,PPC]
2677 ssbd=force-off [ARM64]
2680 tsx_async_abort=off [X86]
2681 kvm.nx_huge_pages=off [X86]
2682 no_entry_flush [PPC]
2683 no_uaccess_flush [PPC]
2684 mmio_stale_data=off [X86]
2687 This does not have any effect on
2688 kvm.nx_huge_pages when
2689 kvm.nx_huge_pages=force.
2692 Mitigate all CPU vulnerabilities, but leave SMT
2693 enabled, even if it's vulnerable. This is for
2694 users who don't want to be surprised by SMT
2695 getting disabled across kernel upgrades, or who
2696 have other ways of avoiding SMT-based attacks.
2697 Equivalent to: (default behavior)
2700 Mitigate all CPU vulnerabilities, disabling SMT
2701 if needed. This is for users who always want to
2702 be fully mitigated, even if it means losing SMT.
2703 Equivalent to: l1tf=flush,nosmt [X86]
2704 mds=full,nosmt [X86]
2705 tsx_async_abort=full,nosmt [X86]
2706 mmio_stale_data=full,nosmt [X86]
2709 [KNL] When CONFIG_DEBUG_MEMORY_INIT is set, this
2710 parameter allows control of the logging verbosity for
2711 the additional memory initialisation checks. A value
2712 of 0 disables mminit logging and a level of 4 will
2713 log everything. Information is printed at KERN_DEBUG
2714 so loglevel=8 may also need to be specified.
2717 [X86,INTEL] Control mitigation for the Processor
2718 MMIO Stale Data vulnerabilities.
2720 Processor MMIO Stale Data is a class of
2721 vulnerabilities that may expose data after an MMIO
2722 operation. Exposed data could originate or end in
2723 the same CPU buffers as affected by MDS and TAA.
2724 Therefore, similar to MDS and TAA, the mitigation
2725 is to clear the affected CPU buffers.
2727 This parameter controls the mitigation. The
2730 full - Enable mitigation on vulnerable CPUs
2732 full,nosmt - Enable mitigation and disable SMT on
2735 off - Unconditionally disable mitigation
2737 On MDS or TAA affected machines,
2738 mmio_stale_data=off can be prevented by an active
2739 MDS or TAA mitigation as these vulnerabilities are
2740 mitigated with the same mechanism so in order to
2741 disable this mitigation, you need to specify
2742 mds=off and tsx_async_abort=off too.
2744 Not specifying this option is equivalent to
2745 mmio_stale_data=full.
2748 Documentation/admin-guide/hw-vuln/processor_mmio_stale_data.rst
2751 [KNL] When CONFIG_MODULE_SIG is set, this means that
2752 modules without (valid) signatures will fail to load.
2753 Note that if CONFIG_MODULE_SIG_FORCE is set, that
2754 is always true, so this option does nothing.
2756 module_blacklist= [KNL] Do not load a comma-separated list of
2757 modules. Useful for debugging problem modules.
2760 [MOUSE] Maximum time between finger touching and
2761 leaving touchpad surface for touch to be considered
2762 a tap and be reported as a left button click (for
2763 touchpads working in absolute mode only).
2765 mousedev.xres= [MOUSE] Horizontal screen resolution, used for devices
2766 reporting absolute coordinates, such as tablets
2767 mousedev.yres= [MOUSE] Vertical screen resolution, used for devices
2768 reporting absolute coordinates, such as tablets
2770 movablecore= [KNL,X86,IA-64,PPC]
2771 Format: nn[KMGTPE] | nn%
2772 This parameter is the complement to kernelcore=, it
2773 specifies the amount of memory used for migratable
2774 allocations. If both kernelcore and movablecore is
2775 specified, then kernelcore will be at *least* the
2776 specified value but may be more. If movablecore on its
2777 own is specified, the administrator must be careful
2778 that the amount of memory usable for all allocations
2781 movable_node [KNL] Boot-time switch to make hotplugable memory
2782 NUMA nodes to be movable. This means that the memory
2783 of such nodes will be usable only for movable
2784 allocations which rules out almost all kernel
2785 allocations. Use with caution!
2787 MTD_Partition= [MTD]
2788 Format: <name>,<region-number>,<size>,<offset>
2790 MTD_Region= [MTD] Format:
2791 <name>,<region-number>[,<base>,<size>,<buswidth>,<altbuswidth>]
2794 See drivers/mtd/parsers/cmdlinepart.c
2796 multitce=off [PPC] This parameter disables the use of the pSeries
2797 firmware feature for updating multiple TCE entries
2800 onenand.bdry= [HW,MTD] Flex-OneNAND Boundary Configuration
2802 Format: [die0_boundary][,die0_lock][,die1_boundary][,die1_lock]
2804 boundary - index of last SLC block on Flex-OneNAND.
2805 The remaining blocks are configured as MLC blocks.
2806 lock - Configure if Flex-OneNAND boundary should be locked.
2807 Once locked, the boundary cannot be changed.
2808 1 indicates lock status, 0 indicates unlock status.
2811 ARM/S3C2412 JIVE boot control
2813 See arch/arm/mach-s3c2412/mach-jive.c
2815 mtouchusb.raw_coordinates=
2816 [HW] Make the MicroTouch USB driver use raw coordinates
2817 ('y', default) or cooked coordinates ('n')
2819 mtrr_chunk_size=nn[KMG] [X86]
2820 used for mtrr cleanup. It is largest continuous chunk
2821 that could hold holes aka. UC entries.
2823 mtrr_gran_size=nn[KMG] [X86]
2824 Used for mtrr cleanup. It is granularity of mtrr block.
2826 Large value could prevent small alignment from
2829 mtrr_spare_reg_nr=n [X86]
2831 Range: 0,7 : spare reg number
2833 Used for mtrr cleanup. It is spare mtrr entries number.
2834 Set to 2 or more if your graphical card needs more.
2836 n2= [NET] SDL Inc. RISCom/N2 synchronous serial card
2838 netdev= [NET] Network devices parameters
2839 Format: <irq>,<io>,<mem_start>,<mem_end>,<name>
2840 Note that mem_start is often overloaded to mean
2841 something different and driver-specific.
2842 This usage is only documented in each driver source
2846 [NETFILTER] Enable connection tracking flow accounting
2847 0 to disable accounting
2848 1 to enable accounting
2851 nfsaddrs= [NFS] Deprecated. Use ip= instead.
2852 See Documentation/filesystems/nfs/nfsroot.txt.
2854 nfsroot= [NFS] nfs root filesystem for disk-less boxes.
2855 See Documentation/filesystems/nfs/nfsroot.txt.
2857 nfsrootdebug [NFS] enable nfsroot debugging messages.
2858 See Documentation/filesystems/nfs/nfsroot.txt.
2860 nfs.callback_nr_threads=
2861 [NFSv4] set the total number of threads that the
2862 NFS client will assign to service NFSv4 callback
2865 nfs.callback_tcpport=
2866 [NFS] set the TCP port on which the NFSv4 callback
2867 channel should listen.
2870 [NFS] sets the pathname to the program which is used
2871 to update the NFS client cache entries.
2873 nfs.cache_getent_timeout=
2874 [NFS] sets the timeout after which an attempt to
2875 update a cache entry is deemed to have failed.
2877 nfs.idmap_cache_timeout=
2878 [NFS] set the maximum lifetime for idmapper cache
2882 [NFS] enable 64-bit inode numbers.
2883 If zero, the NFS client will fake up a 32-bit inode
2884 number for the readdir() and stat() syscalls instead
2885 of returning the full 64-bit number.
2886 The default is to return 64-bit inode numbers.
2888 nfs.max_session_cb_slots=
2889 [NFSv4.1] Sets the maximum number of session
2890 slots the client will assign to the callback
2891 channel. This determines the maximum number of
2892 callbacks the client will process in parallel for
2893 a particular server.
2895 nfs.max_session_slots=
2896 [NFSv4.1] Sets the maximum number of session slots
2897 the client will attempt to negotiate with the server.
2898 This limits the number of simultaneous RPC requests
2899 that the client can send to the NFSv4.1 server.
2900 Note that there is little point in setting this
2901 value higher than the max_tcp_slot_table_limit.
2903 nfs.nfs4_disable_idmapping=
2904 [NFSv4] When set to the default of '1', this option
2905 ensures that both the RPC level authentication
2906 scheme and the NFS level operations agree to use
2907 numeric uids/gids if the mount is using the
2908 'sec=sys' security flavour. In effect it is
2909 disabling idmapping, which can make migration from
2910 legacy NFSv2/v3 systems to NFSv4 easier.
2911 Servers that do not support this mode of operation
2912 will be autodetected by the client, and it will fall
2913 back to using the idmapper.
2914 To turn off this behaviour, set the value to '0'.
2916 [NFS4] Specify an additional fixed unique ident-
2917 ification string that NFSv4 clients can insert into
2918 their nfs_client_id4 string. This is typically a
2919 UUID that is generated at system install time.
2921 nfs.send_implementation_id =
2922 [NFSv4.1] Send client implementation identification
2923 information in exchange_id requests.
2924 If zero, no implementation identification information
2926 The default is to send the implementation identification
2929 nfs.recover_lost_locks =
2930 [NFSv4] Attempt to recover locks that were lost due
2931 to a lease timeout on the server. Please note that
2932 doing this risks data corruption, since there are
2933 no guarantees that the file will remain unchanged
2934 after the locks are lost.
2935 If you want to enable the kernel legacy behaviour of
2936 attempting to recover these locks, then set this
2938 The default parameter value of '0' causes the kernel
2939 not to attempt recovery of lost locks.
2941 nfs4.layoutstats_timer =
2942 [NFSv4.2] Change the rate at which the kernel sends
2943 layoutstats to the pNFS metadata server.
2945 Setting this to value to 0 causes the kernel to use
2946 whatever value is the default set by the layout
2947 driver. A non-zero value sets the minimum interval
2948 in seconds between layoutstats transmissions.
2950 nfsd.nfs4_disable_idmapping=
2951 [NFSv4] When set to the default of '1', the NFSv4
2952 server will return only numeric uids and gids to
2953 clients using auth_sys, and will accept numeric uids
2954 and gids from such clients. This is intended to ease
2955 migration from NFSv2/v3.
2957 nmi_debug= [KNL,SH] Specify one or more actions to take
2958 when a NMI is triggered.
2959 Format: [state][,regs][,debounce][,die]
2961 nmi_watchdog= [KNL,BUGS=X86] Debugging features for SMP kernels
2962 Format: [panic,][nopanic,][num]
2964 0 - turn hardlockup detector in nmi_watchdog off
2965 1 - turn hardlockup detector in nmi_watchdog on
2966 When panic is specified, panic when an NMI watchdog
2967 timeout occurs (or 'nopanic' to not panic on an NMI
2968 watchdog, if CONFIG_BOOTPARAM_HARDLOCKUP_PANIC is set)
2969 To disable both hard and soft lockup detectors,
2970 please see 'nowatchdog'.
2971 This is useful when you use a panic=... timeout and
2972 need the box quickly up again.
2974 These settings can be accessed at runtime via
2975 the nmi_watchdog and hardlockup_panic sysctls.
2977 netpoll.carrier_timeout=
2978 [NET] Specifies amount of time (in seconds) that
2979 netpoll should wait for a carrier. By default netpoll
2982 no387 [BUGS=X86-32] Tells the kernel to use the 387 maths
2983 emulation library even if a 387 maths coprocessor
2986 no5lvl [X86-64] Disable 5-level paging mode. Forces
2987 kernel to use 4-level paging instead.
2990 [HW] Never suspend the console
2991 Disable suspending of consoles during suspend and
2992 hibernate operations. Once disabled, debugging
2993 messages can reach various consoles while the rest
2994 of the system is being put to sleep (ie, while
2995 debugging driver suspend/resume hooks). This may
2996 not work reliably with all consoles, but is known
2997 to work with serial and VGA consoles.
2998 To facilitate more flexible debugging, we also add
2999 console_suspend, a printk module parameter to control
3000 it. Users could use console_suspend (usually
3001 /sys/module/printk/parameters/console_suspend) to
3002 turn on/off it dynamically.
3004 novmcoredd [KNL,KDUMP]
3005 Disable device dump. Device dump allows drivers to
3006 append dump data to vmcore so you can collect driver
3007 specified debug info. Drivers can append the data
3008 without any limit and this data is stored in memory,
3009 so this may cause significant memory stress. Disabling
3010 device dump can help save memory but the driver debug
3011 data will be no longer available. This parameter
3012 is only available when CONFIG_PROC_VMCORE_DEVICE_DUMP
3015 noaliencache [MM, NUMA, SLAB] Disables the allocation of alien
3016 caches in the slab allocator. Saves per-node memory,
3017 but will impact performance.
3021 noaltinstr [S390] Disables alternative instructions patching
3022 (CPU alternatives feature).
3024 noapic [SMP,APIC] Tells the kernel to not make use of any
3025 IOAPICs that may be present in the system.
3027 noautogroup Disable scheduler automatic task group creation.
3029 nobats [PPC] Do not use BATs for mapping kernel lowmem
3030 on "Classic" PPC cores.
3034 noclflush [BUGS=X86] Don't use the CLFLUSH instruction
3036 nodelayacct [KNL] Disable per-task delay accounting
3038 nodsp [SH] Disable hardware DSP at boot time.
3040 noefi Disable EFI runtime services support.
3042 no_entry_flush [PPC] Don't flush the L1-D cache when entering the kernel.
3047 On X86-32 available only on PAE configured kernels.
3048 noexec=on: enable non-executable mappings (default)
3049 noexec=off: disable non-executable mappings
3052 Disable SMAP (Supervisor Mode Access Prevention)
3053 even if it is supported by processor.
3056 Disable SMEP (Supervisor Mode Execution Prevention)
3057 even if it is supported by processor.
3060 This affects only 32-bit executables.
3061 noexec32=on: enable non-executable mappings (default)
3062 read doesn't imply executable mappings
3063 noexec32=off: disable non-executable mappings
3064 read implies executable mappings
3066 nofpu [MIPS,SH] Disable hardware FPU at boot time.
3068 nofxsr [BUGS=X86-32] Disables x86 floating point extended
3069 register save and restore. The kernel will only save
3070 legacy floating-point registers on task switch.
3072 nohugeiomap [KNL,x86,PPC] Disable kernel huge I/O mappings.
3074 nosmt [KNL,S390] Disable symmetric multithreading (SMT).
3075 Equivalent to smt=1.
3077 [KNL,x86] Disable symmetric multithreading (SMT).
3078 nosmt=force: Force disable SMT, cannot be undone
3079 via the sysfs control file.
3081 nospectre_v1 [X86,PPC] Disable mitigations for Spectre Variant 1
3082 (bounds check bypass). With this option data leaks are
3083 possible in the system.
3085 nospectre_v2 [X86,PPC_FSL_BOOK3E,ARM64] Disable all mitigations for
3086 the Spectre variant 2 (indirect branch prediction)
3087 vulnerability. System may allow data leaks with this
3090 nospec_store_bypass_disable
3091 [HW] Disable all mitigations for the Speculative Store Bypass vulnerability
3094 [PPC] Don't flush the L1-D cache after accessing user data.
3096 noxsave [BUGS=X86] Disables x86 extended register state save
3097 and restore using xsave. The kernel will fallback to
3098 enabling legacy floating-point and sse state.
3100 noxsaveopt [X86] Disables xsaveopt used in saving x86 extended
3101 register states. The kernel will fall back to use
3102 xsave to save the states. By using this parameter,
3103 performance of saving the states is degraded because
3104 xsave doesn't support modified optimization while
3105 xsaveopt supports it on xsaveopt enabled systems.
3107 noxsaves [X86] Disables xsaves and xrstors used in saving and
3108 restoring x86 extended register state in compacted
3109 form of xsave area. The kernel will fall back to use
3110 xsaveopt and xrstor to save and restore the states
3111 in standard form of xsave area. By using this
3112 parameter, xsave area per process might occupy more
3113 memory on xsaves enabled systems.
3115 nohlt [BUGS=ARM,SH] Tells the kernel that the sleep(SH) or
3116 wfi(ARM) instruction doesn't work correctly and not to
3117 use it. This is also useful when using JTAG debugger.
3119 no_file_caps Tells the kernel not to honor file capabilities. The
3120 only way then for a file to be executed with privilege
3121 is to be setuid root or executed by root.
3123 nohalt [IA-64] Tells the kernel not to use the power saving
3124 function PAL_HALT_LIGHT when idle. This increases
3125 power-consumption. On the positive side, it reduces
3126 interrupt wake-up latency, which may improve performance
3127 in certain environments such as networked servers or
3130 nohibernate [HIBERNATION] Disable hibernation and resume.
3132 nohz= [KNL] Boottime enable/disable dynamic ticks
3133 Valid arguments: on, off
3136 nohz_full= [KNL,BOOT,SMP,ISOL]
3137 The argument is a cpu list, as described above.
3138 In kernels built with CONFIG_NO_HZ_FULL=y, set
3139 the specified list of CPUs whose tick will be stopped
3140 whenever possible. The boot CPU will be forced outside
3141 the range to maintain the timekeeping. Any CPUs
3142 in this list will have their RCU callbacks offloaded,
3143 just as if they had also been called out in the
3144 rcu_nocbs= boot parameter.
3146 noiotrap [SH] Disables trapped I/O port accesses.
3148 noirqdebug [X86-32] Disables the code which attempts to detect and
3149 disable unhandled interrupt sources.
3151 no_timer_check [X86,APIC] Disables the code which tests for
3152 broken timer IRQ sources.
3154 noisapnp [ISAPNP] Disables ISA PnP code.
3156 noinitrd [RAM] Tells the kernel not to load any configured
3159 nointremap [X86-64, Intel-IOMMU] Do not enable interrupt
3161 [Deprecated - use intremap=off]
3165 noinvpcid [X86] Disable the INVPCID cpu feature.
3167 nojitter [IA-64] Disables jitter checking for ITC timers.
3169 no-kvmclock [X86,KVM] Disable paravirtualized KVM clock driver
3171 no-kvmapf [X86,KVM] Disable paravirtualized asynchronous page
3175 [X86,PV_OPS] Disable paravirtualized VMware scheduler
3176 clock and use the default one.
3178 no-steal-acc [X86,KVM] Disable paravirtualized steal time accounting.
3179 steal time is computed, but won't influence scheduler
3182 nolapic [X86-32,APIC] Do not enable or use the local APIC.
3184 nolapic_timer [X86-32,APIC] Do not use the local APIC timer.
3186 noltlbs [PPC] Do not use large page/tlb entries for kernel
3187 lowmem mapping on PPC40x and PPC8xx
3189 nomca [IA-64] Disable machine check abort handling
3191 nomce [X86-32] Disable Machine Check Exception
3193 nomfgpt [X86-32] Disable Multi-Function General Purpose
3194 Timer usage (for AMD Geode machines).
3196 nonmi_ipi [X86] Disable using NMI IPIs during panic/reboot to
3197 shutdown the other cpus. Instead use the REBOOT_VECTOR
3200 nomodule Disable module load
3202 nopat [X86] Disable PAT (page attribute table extension of
3203 pagetables) support.
3205 nopcid [X86-64] Disable the PCID cpu feature.
3207 norandmaps Don't use address space randomization. Equivalent to
3208 echo 0 > /proc/sys/kernel/randomize_va_space
3210 noreplace-smp [X86-32,SMP] Don't replace SMP instructions
3211 with UP alternatives
3213 nordrand [X86] Disable kernel use of the RDRAND and
3214 RDSEED instructions even if they are supported
3215 by the processor. RDRAND and RDSEED are still
3216 available to user space applications.
3218 noresume [SWSUSP] Disables resume and restores original swap
3221 no-scroll [VGA] Disables scrollback.
3222 This is required for the Braillex ib80-piezo Braille
3223 reader made by F.H. Papenmeier (Germany).
3227 nosep [BUGS=X86-32] Disables x86 SYSENTER/SYSEXIT support.
3229 nosmp [SMP] Tells an SMP kernel to act as a UP kernel,
3230 and disable the IO APIC. legacy for "maxcpus=0".
3232 nosoftlockup [KNL] Disable the soft-lockup detector.
3234 nosync [HW,M68K] Disables sync negotiation for all devices.
3236 nowatchdog [KNL] Disable both lockup detectors, i.e.
3237 soft-lockup and NMI watchdog (hard-lockup).
3241 nox2apic [X86-64,APIC] Do not enable x2APIC mode.
3243 cpu0_hotplug [X86] Turn on CPU0 hotplug feature when
3244 CONFIG_BOOTPARAM_HOTPLUG_CPU0 is off.
3245 Some features depend on CPU0. Known dependencies are:
3246 1. Resume from suspend/hibernate depends on CPU0.
3247 Suspend/hibernate will fail if CPU0 is offline and you
3248 need to online CPU0 before suspend/hibernate.
3249 2. PIC interrupts also depend on CPU0. CPU0 can't be
3250 removed if a PIC interrupt is detected.
3251 It's said poweroff/reboot may depend on CPU0 on some
3252 machines although I haven't seen such issues so far
3253 after CPU0 is offline on a few tested machines.
3254 If the dependencies are under your control, you can
3255 turn on cpu0_hotplug.
3257 nps_mtm_hs_ctr= [KNL,ARC]
3258 This parameter sets the maximum duration, in
3259 cycles, each HW thread of the CTOP can run
3260 without interruptions, before HW switches it.
3261 The actual maximum duration is 16 times this
3263 Format: integer between 1 and 255
3266 nptcg= [IA-64] Override max number of concurrent global TLB
3267 purges which is reported from either PAL_VM_SUMMARY or
3270 nr_cpus= [SMP] Maximum number of processors that an SMP kernel
3271 could support. nr_cpus=n : n >= 1 limits the kernel to
3272 support 'n' processors. It could be larger than the
3273 number of already plugged CPU during bootup, later in
3274 runtime you can physically add extra cpu until it reaches
3275 n. So during boot up some boot time memory for per-cpu
3276 variables need be pre-allocated for later physical cpu
3279 nr_uarts= [SERIAL] maximum number of UARTs to be registered.
3281 numa_balancing= [KNL,X86] Enable or disable automatic NUMA balancing.
3282 Allowed values are enable and disable
3284 numa_zonelist_order= [KNL, BOOT] Select zonelist order for NUMA.
3285 'node', 'default' can be specified
3286 This can be set from sysctl after boot.
3287 See Documentation/admin-guide/sysctl/vm.rst for details.
3289 ohci1394_dma=early [HW] enable debugging via the ohci1394 driver.
3290 See Documentation/debugging-via-ohci1394.txt for more
3293 olpc_ec_timeout= [OLPC] ms delay when issuing EC commands
3294 Rather than timing out after 20 ms if an EC
3295 command is not properly ACKed, override the length
3296 of the timeout. We have interrupts disabled while
3297 waiting for the ACK, so if this is set too high
3298 interrupts *may* be lost!
3300 omap_mux= [OMAP] Override bootloader pin multiplexing.
3301 Format: <mux_mode0.mode_name=value>...
3302 For example, to override I2C bus2:
3303 omap_mux=i2c2_scl.i2c2_scl=0x100,i2c2_sda.i2c2_sda=0x100
3305 oprofile.timer= [HW]
3306 Use timer interrupt instead of performance counters
3308 oprofile.cpu_type= Force an oprofile cpu type
3309 This might be useful if you have an older oprofile
3310 userland or if you want common events.
3311 Format: { arch_perfmon }
3312 arch_perfmon: [X86] Force use of architectural
3313 perfmon on Intel CPUs instead of the
3314 CPU specific event set.
3315 timer: [X86] Force use of architectural NMI
3316 timer mode (see also oprofile.timer
3317 for generic hr timer mode)
3319 oops=panic Always panic on oopses. Default is to just kill the
3320 process, but there is a small probability of
3321 deadlocking the machine.
3322 This will also cause panics on machine check exceptions.
3323 Useful together with panic=30 to trigger a reboot.
3326 [KNL] Boolean flag to control whether the page allocator
3327 should randomize its free lists. The randomization may
3328 be automatically enabled if the kernel detects it is
3329 running on a platform with a direct-mapped memory-side
3330 cache, and this parameter can be used to
3331 override/disable that behavior. The state of the flag
3332 can be read from sysfs at:
3333 /sys/module/page_alloc/parameters/shuffle.
3335 page_owner= [KNL] Boot-time page_owner enabling option.
3336 Storage of the information about who allocated
3337 each page is disabled in default. With this switch,
3339 on: enable the feature
3341 page_poison= [KNL] Boot-time parameter changing the state of
3342 poisoning on the buddy allocator, available with
3343 CONFIG_PAGE_POISONING=y.
3344 off: turn off poisoning (default)
3345 on: turn on poisoning
3347 panic= [KNL] Kernel behaviour on panic: delay <timeout>
3348 timeout > 0: seconds before rebooting
3349 timeout = 0: wait forever
3350 timeout < 0: reboot immediately
3353 panic_print= Bitmask for printing system info when panic happens.
3354 User can chose combination of the following bits:
3355 bit 0: print all tasks info
3356 bit 1: print system memory info
3357 bit 2: print timer info
3358 bit 3: print locks info if CONFIG_LOCKDEP is on
3359 bit 4: print ftrace buffer
3360 bit 5: print all printk messages in buffer
3362 panic_on_warn panic() instead of WARN(). Useful to cause kdump
3365 crash_kexec_post_notifiers
3366 Run kdump after running panic-notifiers and dumping
3367 kmsg. This only for the users who doubt kdump always
3368 succeeds in any situation.
3369 Note that this also increases risks of kdump failure,
3370 because some panic notifiers can make the crashed
3371 kernel more unstable.
3373 parkbd.port= [HW] Parallel port number the keyboard adapter is
3374 connected to, default is 0.
3376 parkbd.mode= [HW] Parallel port keyboard adapter mode of operation,
3377 0 for XT, 1 for AT (default is AT).
3380 parport= [HW,PPT] Specify parallel ports. 0 disables.
3381 Format: { 0 | auto | 0xBBB[,IRQ[,DMA]] }
3382 Use 'auto' to force the driver to use any
3383 IRQ/DMA settings detected (the default is to
3384 ignore detected IRQ/DMA settings because of
3385 possible conflicts). You can specify the base
3386 address, IRQ, and DMA settings; IRQ and DMA
3387 should be numbers, or 'auto' (for using detected
3388 settings on that particular port), or 'nofifo'
3389 (to avoid using a FIFO even if it is detected).
3390 Parallel ports are assigned in the order they
3391 are specified on the command line, starting
3394 parport_init_mode= [HW,PPT]
3395 Configure VIA parallel port to operate in
3396 a specific mode. This is necessary on Pegasos
3397 computer where firmware has no options for setting
3398 up parallel port mode and sets it to spp.
3399 Currently this function knows 686a and 8231 chips.
3400 Format: [spp|ps2|epp|ecp|ecpepp]
3403 Halt all CPUs after the first oops has been printed for
3404 the specified number of seconds. This is to be used if
3405 your oopses keep scrolling off the screen.
3410 See header of drivers/block/paride/pcd.c.
3411 See also Documentation/admin-guide/blockdev/paride.rst.
3413 pci=option[,option...] [PCI] various PCI subsystem options.
3415 Some options herein operate on a specific device
3416 or a set of devices (<pci_dev>). These are
3417 specified in one of the following formats:
3419 [<domain>:]<bus>:<dev>.<func>[/<dev>.<func>]*
3420 pci:<vendor>:<device>[:<subvendor>:<subdevice>]
3422 Note: the first format specifies a PCI
3423 bus/device/function address which may change
3424 if new hardware is inserted, if motherboard
3425 firmware changes, or due to changes caused
3426 by other kernel parameters. If the
3427 domain is left unspecified, it is
3428 taken to be zero. Optionally, a path
3429 to a device through multiple device/function
3430 addresses can be specified after the base
3431 address (this is more robust against
3432 renumbering issues). The second format
3433 selects devices using IDs from the
3434 configuration space which may match multiple
3435 devices in the system.
3437 earlydump dump PCI config space before the kernel
3439 off [X86] don't probe for the PCI bus
3440 bios [X86-32] force use of PCI BIOS, don't access
3441 the hardware directly. Use this if your machine
3442 has a non-standard PCI host bridge.
3443 nobios [X86-32] disallow use of PCI BIOS, only direct
3444 hardware access methods are allowed. Use this
3445 if you experience crashes upon bootup and you
3446 suspect they are caused by the BIOS.
3447 conf1 [X86] Force use of PCI Configuration Access
3448 Mechanism 1 (config address in IO port 0xCF8,
3449 data in IO port 0xCFC, both 32-bit).
3450 conf2 [X86] Force use of PCI Configuration Access
3451 Mechanism 2 (IO port 0xCF8 is an 8-bit port for
3452 the function, IO port 0xCFA, also 8-bit, sets
3453 bus number. The config space is then accessed
3454 through ports 0xC000-0xCFFF).
3455 See http://wiki.osdev.org/PCI for more info
3456 on the configuration access mechanisms.
3457 noaer [PCIE] If the PCIEAER kernel config parameter is
3458 enabled, this kernel boot option can be used to
3459 disable the use of PCIE advanced error reporting.
3460 nodomains [PCI] Disable support for multiple PCI
3461 root domains (aka PCI segments, in ACPI-speak).
3462 nommconf [X86] Disable use of MMCONFIG for PCI
3464 check_enable_amd_mmconf [X86] check for and enable
3465 properly configured MMIO access to PCI
3466 config space on AMD family 10h CPU
3467 nomsi [MSI] If the PCI_MSI kernel config parameter is
3468 enabled, this kernel boot option can be used to
3469 disable the use of MSI interrupts system-wide.
3470 noioapicquirk [APIC] Disable all boot interrupt quirks.
3471 Safety option to keep boot IRQs enabled. This
3472 should never be necessary.
3473 ioapicreroute [APIC] Enable rerouting of boot IRQs to the
3474 primary IO-APIC for bridges that cannot disable
3475 boot IRQs. This fixes a source of spurious IRQs
3476 when the system masks IRQs.
3477 noioapicreroute [APIC] Disable workaround that uses the
3478 boot IRQ equivalent of an IRQ that connects to
3479 a chipset where boot IRQs cannot be disabled.
3480 The opposite of ioapicreroute.
3481 biosirq [X86-32] Use PCI BIOS calls to get the interrupt
3482 routing table. These calls are known to be buggy
3483 on several machines and they hang the machine
3484 when used, but on other computers it's the only
3485 way to get the interrupt routing table. Try
3486 this option if the kernel is unable to allocate
3487 IRQs or discover secondary PCI buses on your
3489 rom [X86] Assign address space to expansion ROMs.
3490 Use with caution as certain devices share
3491 address decoders between ROMs and other
3493 norom [X86] Do not assign address space to
3494 expansion ROMs that do not already have
3495 BIOS assigned address ranges.
3496 nobar [X86] Do not assign address space to the
3497 BARs that weren't assigned by the BIOS.
3498 irqmask=0xMMMM [X86] Set a bit mask of IRQs allowed to be
3499 assigned automatically to PCI devices. You can
3500 make the kernel exclude IRQs of your ISA cards
3502 pirqaddr=0xAAAAA [X86] Specify the physical address
3503 of the PIRQ table (normally generated
3504 by the BIOS) if it is outside the
3505 F0000h-100000h range.
3506 lastbus=N [X86] Scan all buses thru bus #N. Can be
3507 useful if the kernel is unable to find your
3508 secondary buses and you want to tell it
3509 explicitly which ones they are.
3510 assign-busses [X86] Always assign all PCI bus
3511 numbers ourselves, overriding
3512 whatever the firmware may have done.
3513 usepirqmask [X86] Honor the possible IRQ mask stored
3514 in the BIOS $PIR table. This is needed on
3515 some systems with broken BIOSes, notably
3516 some HP Pavilion N5400 and Omnibook XE3
3517 notebooks. This will have no effect if ACPI
3518 IRQ routing is enabled.
3519 noacpi [X86] Do not use ACPI for IRQ routing
3520 or for PCI scanning.
3521 use_crs [X86] Use PCI host bridge window information
3522 from ACPI. On BIOSes from 2008 or later, this
3523 is enabled by default. If you need to use this,
3524 please report a bug.
3525 nocrs [X86] Ignore PCI host bridge windows from ACPI.
3526 If you need to use this, please report a bug.
3527 routeirq Do IRQ routing for all PCI devices.
3528 This is normally done in pci_enable_device(),
3529 so this option is a temporary workaround
3530 for broken drivers that don't call it.
3531 skip_isa_align [X86] do not align io start addr, so can
3532 handle more pci cards
3533 noearly [X86] Don't do any early type 1 scanning.
3534 This might help on some broken boards which
3535 machine check when some devices' config space
3536 is read. But various workarounds are disabled
3537 and some IOMMU drivers will not work.
3538 bfsort Sort PCI devices into breadth-first order.
3539 This sorting is done to get a device
3540 order compatible with older (<= 2.4) kernels.
3541 nobfsort Don't sort PCI devices into breadth-first order.
3542 pcie_bus_tune_off Disable PCIe MPS (Max Payload Size)
3543 tuning and use the BIOS-configured MPS defaults.
3544 pcie_bus_safe Set every device's MPS to the largest value
3545 supported by all devices below the root complex.
3546 pcie_bus_perf Set device MPS to the largest allowable MPS
3547 based on its parent bus. Also set MRRS (Max
3548 Read Request Size) to the largest supported
3549 value (no larger than the MPS that the device
3550 or bus can support) for best performance.
3551 pcie_bus_peer2peer Set every device's MPS to 128B, which
3552 every device is guaranteed to support. This
3553 configuration allows peer-to-peer DMA between
3554 any pair of devices, possibly at the cost of
3555 reduced performance. This also guarantees
3556 that hot-added devices will work.
3557 cbiosize=nn[KMG] The fixed amount of bus space which is
3558 reserved for the CardBus bridge's IO window.
3559 The default value is 256 bytes.
3560 cbmemsize=nn[KMG] The fixed amount of bus space which is
3561 reserved for the CardBus bridge's memory
3562 window. The default value is 64 megabytes.
3565 [<order of align>@]<pci_dev>[; ...]
3566 Specifies alignment and device to reassign
3567 aligned memory resources. How to
3568 specify the device is described above.
3569 If <order of align> is not specified,
3570 PAGE_SIZE is used as alignment.
3571 A PCI-PCI bridge can be specified if resource
3572 windows need to be expanded.
3573 To specify the alignment for several
3574 instances of a device, the PCI vendor,
3575 device, subvendor, and subdevice may be
3576 specified, e.g., 12@pci:8086:9c22:103c:198f
3577 for 4096-byte alignment.
3578 ecrc= Enable/disable PCIe ECRC (transaction layer
3579 end-to-end CRC checking).
3580 bios: Use BIOS/firmware settings. This is the
3584 hpiosize=nn[KMG] The fixed amount of bus space which is
3585 reserved for hotplug bridge's IO window.
3586 Default size is 256 bytes.
3587 hpmemsize=nn[KMG] The fixed amount of bus space which is
3588 reserved for hotplug bridge's memory window.
3589 Default size is 2 megabytes.
3590 hpbussize=nn The minimum amount of additional bus numbers
3591 reserved for buses below a hotplug bridge.
3593 realloc= Enable/disable reallocating PCI bridge resources
3594 if allocations done by BIOS are too small to
3595 accommodate resources required by all child
3597 off: Turn realloc off
3599 realloc same as realloc=on
3600 noari do not use PCIe ARI.
3601 noats [PCIE, Intel-IOMMU, AMD-IOMMU]
3602 do not use PCIe ATS (and IOMMU device IOTLB).
3603 pcie_scan_all Scan all possible PCIe devices. Otherwise we
3604 only look for one device below a PCIe downstream
3606 big_root_window Try to add a big 64bit memory window to the PCIe
3607 root complex on AMD CPUs. Some GFX hardware
3608 can resize a BAR to allow access to all VRAM.
3609 Adding the window is slightly risky (it may
3610 conflict with unreported devices), so this
3612 disable_acs_redir=<pci_dev>[; ...]
3613 Specify one or more PCI devices (in the format
3614 specified above) separated by semicolons.
3615 Each device specified will have the PCI ACS
3616 redirect capabilities forced off which will
3617 allow P2P traffic between devices through
3618 bridges without forcing it upstream. Note:
3619 this removes isolation between devices and
3620 may put more devices in an IOMMU group.
3621 force_floating [S390] Force usage of floating interrupts.
3622 nomio [S390] Do not use MIO instructions.
3624 pcie_aspm= [PCIE] Forcibly enable or disable PCIe Active State Power
3627 force Enable ASPM even on devices that claim not to support it.
3628 WARNING: Forcing ASPM on may cause system lockups.
3630 pcie_ports= [PCIE] PCIe port services handling:
3631 native Use native PCIe services (PME, AER, DPC, PCIe hotplug)
3632 even if the platform doesn't give the OS permission to
3633 use them. This may cause conflicts if the platform
3634 also tries to use these services.
3635 compat Disable native PCIe services (PME, AER, DPC, PCIe
3638 pcie_port_pm= [PCIE] PCIe port power management handling:
3639 off Disable power management of all PCIe ports
3640 force Forcibly enable power management of all PCIe ports
3642 pcie_pme= [PCIE,PM] Native PCIe PME signaling options:
3643 nomsi Do not use MSI for native PCIe PME signaling (this makes
3644 all PCIe root ports use INTx for all services).
3646 pcmv= [HW,PCMCIA] BadgePAD 4
3650 Keep all power-domains already enabled by bootloader on,
3651 even if no driver has claimed them. This is useful
3652 for debug and development, but should not be
3653 needed on a platform with proper driver support.
3656 See Documentation/admin-guide/blockdev/paride.rst.
3658 pdcchassis= [PARISC,HW] Disable/Enable PDC Chassis Status codes at
3661 See arch/parisc/kernel/pdc_chassis.c
3663 percpu_alloc= Select which percpu first chunk allocator to use.
3664 Currently supported values are "embed" and "page".
3665 Archs may support subset or none of the selections.
3666 See comments in mm/percpu.c for details on each
3667 allocator. This parameter is primarily for debugging
3668 and performance comparison.
3671 See Documentation/admin-guide/blockdev/paride.rst.
3674 See Documentation/admin-guide/blockdev/paride.rst.
3676 pirq= [SMP,APIC] Manual mp-table setup
3677 See Documentation/x86/i386/IO-APIC.rst.
3679 plip= [PPT,NET] Parallel port network link
3680 Format: { parport<nr> | timid | 0 }
3681 See also Documentation/admin-guide/parport.rst.
3683 pmtmr= [X86] Manual setup of pmtmr I/O Port.
3684 Override pmtimer IOPort with a hex value.
3688 Enable PNP debug messages (depends on the
3689 CONFIG_PNP_DEBUG_MESSAGES option). Change at run-time
3690 via /sys/module/pnp/parameters/debug. We always show
3691 current resource usage; turning this on also shows
3692 possible settings and some assignment information.
3698 { on | off | curr | res | no-curr | no-res }
3701 [ISAPNP] Exclude IRQs for the autoconfiguration
3704 [ISAPNP] Exclude DMAs for the autoconfiguration
3706 pnp_reserve_io= [ISAPNP] Exclude I/O ports for the autoconfiguration
3707 Ranges are in pairs (I/O port base and size).
3710 [ISAPNP] Exclude memory regions for the
3712 Ranges are in pairs (memory base and size).
3714 ports= [IP_VS_FTP] IPVS ftp helper module
3716 Up to 8 (IP_VS_APP_MAX_PORTS) ports
3718 Format: <port>,<port>....
3720 powersave=off [PPC] This option disables power saving features.
3721 It specifically disables cpuidle and sets the
3722 platform machine description specific power_save
3723 function to NULL. On Idle the CPU just reduces
3726 ppc_strict_facility_enable
3727 [PPC] This option catches any kernel floating point,
3728 Altivec, VSX and SPE outside of regions specifically
3729 allowed (eg kernel_enable_fpu()/kernel_disable_fpu()).
3730 There is some performance impact when enabling this.
3734 Disable Hardware Transactional Memory
3736 print-fatal-signals=
3737 [KNL] debug: print fatal signals
3739 If enabled, warn about various signal handling
3740 related application anomalies: too many signals,
3741 too many POSIX.1 timers, fatal signals causing a
3744 If you hit the warning due to signal overflow,
3745 you might want to try "ulimit -i unlimited".
3749 printk.always_kmsg_dump=
3750 Trigger kmsg_dump for cases other than kernel oops or
3752 Format: <bool> (1/Y/y=enable, 0/N/n=disable)
3755 printk.devkmsg={on,off,ratelimit}
3756 Control writing to /dev/kmsg.
3757 on - unlimited logging to /dev/kmsg from userspace
3758 off - logging to /dev/kmsg disabled
3759 ratelimit - ratelimit the logging
3762 printk.time= Show timing data prefixed to each printk message line
3763 Format: <bool> (1/Y/y=enable, 0/N/n=disable)
3765 processor.max_cstate= [HW,ACPI]
3766 Limit processor to maximum C-state
3767 max_cstate=9 overrides any DMI blacklist limit.
3769 processor.nocst [HW,ACPI]
3770 Ignore the _CST method to determine C-states,
3771 instead using the legacy FADT method
3773 profile= [KNL] Enable kernel profiling via /proc/profile
3774 Format: [<profiletype>,]<number>
3775 Param: <profiletype>: "schedule", "sleep", or "kvm"
3776 [defaults to kernel profiling]
3777 Param: "schedule" - profile schedule points.
3778 Param: "sleep" - profile D-state sleeping (millisecs).
3779 Requires CONFIG_SCHEDSTATS
3780 Param: "kvm" - profile VM exits.
3781 Param: <number> - step/bucket size as a power of 2 for
3782 statistical time based profiling.
3784 prompt_ramdisk= [RAM] List of RAM disks to prompt for floppy disk
3786 See Documentation/admin-guide/blockdev/ramdisk.rst.
3788 psi= [KNL] Enable or disable pressure stall information
3792 psmouse.proto= [HW,MOUSE] Highest PS2 mouse protocol extension to
3793 probe for; one of (bare|imps|exps|lifebook|any).
3794 psmouse.rate= [HW,MOUSE] Set desired mouse report rate, in reports
3796 psmouse.resetafter= [HW,MOUSE]
3797 Try to reset the device after so many bad packets
3800 [HW,MOUSE] Set desired mouse resolution, in dpi.
3801 psmouse.smartscroll=
3802 [HW,MOUSE] Controls Logitech smartscroll autorepeat.
3803 0 = disabled, 1 = enabled (default).
3805 pstore.backend= Specify the name of the pstore backend to use
3808 See Documentation/admin-guide/blockdev/paride.rst.
3810 pti= [X86_64] Control Page Table Isolation of user and
3811 kernel address spaces. Disabling this feature
3812 removes hardening, but improves performance of
3813 system calls and interrupts.
3815 on - unconditionally enable
3816 off - unconditionally disable
3817 auto - kernel detects whether your CPU model is
3818 vulnerable to issues that PTI mitigates
3820 Not specifying this option is equivalent to pti=auto.
3823 Equivalent to pti=off
3826 [KNL] Number of legacy pty's. Overwrites compiled-in
3829 quiet [KNL] Disable most log messages
3834 See Documentation/admin-guide/md.rst.
3836 ramdisk_size= [RAM] Sizes of RAM disks in kilobytes
3837 See Documentation/admin-guide/blockdev/ramdisk.rst.
3839 random.trust_cpu={on,off}
3840 [KNL] Enable or disable trusting the use of the
3841 CPU's random number generator (if available) to
3842 fully seed the kernel's CRNG. Default is controlled
3843 by CONFIG_RANDOM_TRUST_CPU.
3845 random.trust_bootloader={on,off}
3846 [KNL] Enable or disable trusting the use of a
3847 seed passed by the bootloader (if available) to
3848 fully seed the kernel's CRNG. Default is controlled
3849 by CONFIG_RANDOM_TRUST_BOOTLOADER.
3851 ras=option[,option,...] [KNL] RAS-specific options
3854 Disable the Correctable Errors Collector,
3855 see CONFIG_RAS_CEC help text.
3858 The argument is a cpu list, as described above,
3859 except that the string "all" can be used to
3860 specify every CPU on the system.
3862 In kernels built with CONFIG_RCU_NOCB_CPU=y, set
3863 the specified list of CPUs to be no-callback CPUs.
3864 Invocation of these CPUs' RCU callbacks will be
3865 offloaded to "rcuox/N" kthreads created for that
3866 purpose, where "x" is "p" for RCU-preempt, and
3867 "s" for RCU-sched, and "N" is the CPU number.
3868 This reduces OS jitter on the offloaded CPUs,
3869 which can be useful for HPC and real-time
3870 workloads. It can also improve energy efficiency
3871 for asymmetric multiprocessors.
3874 Rather than requiring that offloaded CPUs
3875 (specified by rcu_nocbs= above) explicitly
3876 awaken the corresponding "rcuoN" kthreads,
3877 make these kthreads poll for callbacks.
3878 This improves the real-time response for the
3879 offloaded CPUs by relieving them of the need to
3880 wake up the corresponding kthread, but degrades
3881 energy efficiency by requiring that the kthreads
3882 periodically wake up to do the polling.
3884 rcutree.blimit= [KNL]
3885 Set maximum number of finished RCU callbacks to
3886 process in one batch.
3888 rcutree.dump_tree= [KNL]
3889 Dump the structure of the rcu_node combining tree
3890 out at early boot. This is used for diagnostic
3891 purposes, to verify correct tree setup.
3893 rcutree.gp_cleanup_delay= [KNL]
3894 Set the number of jiffies to delay each step of
3895 RCU grace-period cleanup.
3897 rcutree.gp_init_delay= [KNL]
3898 Set the number of jiffies to delay each step of
3899 RCU grace-period initialization.
3901 rcutree.gp_preinit_delay= [KNL]
3902 Set the number of jiffies to delay each step of
3903 RCU grace-period pre-initialization, that is,
3904 the propagation of recent CPU-hotplug changes up
3905 the rcu_node combining tree.
3907 rcutree.use_softirq= [KNL]
3908 If set to zero, move all RCU_SOFTIRQ processing to
3909 per-CPU rcuc kthreads. Defaults to a non-zero
3910 value, meaning that RCU_SOFTIRQ is used by default.
3911 Specify rcutree.use_softirq=0 to use rcuc kthreads.
3913 rcutree.rcu_fanout_exact= [KNL]
3914 Disable autobalancing of the rcu_node combining
3915 tree. This is used by rcutorture, and might
3916 possibly be useful for architectures having high
3917 cache-to-cache transfer latencies.
3919 rcutree.rcu_fanout_leaf= [KNL]
3920 Change the number of CPUs assigned to each
3921 leaf rcu_node structure. Useful for very
3922 large systems, which will choose the value 64,
3923 and for NUMA systems with large remote-access
3924 latencies, which will choose a value aligned
3925 with the appropriate hardware boundaries.
3927 rcutree.jiffies_till_first_fqs= [KNL]
3928 Set delay from grace-period initialization to
3929 first attempt to force quiescent states.
3930 Units are jiffies, minimum value is zero,
3931 and maximum value is HZ.
3933 rcutree.jiffies_till_next_fqs= [KNL]
3934 Set delay between subsequent attempts to force
3935 quiescent states. Units are jiffies, minimum
3936 value is one, and maximum value is HZ.
3938 rcutree.jiffies_till_sched_qs= [KNL]
3939 Set required age in jiffies for a
3940 given grace period before RCU starts
3941 soliciting quiescent-state help from
3942 rcu_note_context_switch() and cond_resched().
3943 If not specified, the kernel will calculate
3944 a value based on the most recent settings
3945 of rcutree.jiffies_till_first_fqs
3946 and rcutree.jiffies_till_next_fqs.
3947 This calculated value may be viewed in
3948 rcutree.jiffies_to_sched_qs. Any attempt to set
3949 rcutree.jiffies_to_sched_qs will be cheerfully
3952 rcutree.kthread_prio= [KNL,BOOT]
3953 Set the SCHED_FIFO priority of the RCU per-CPU
3954 kthreads (rcuc/N). This value is also used for
3955 the priority of the RCU boost threads (rcub/N)
3956 and for the RCU grace-period kthreads (rcu_bh,
3957 rcu_preempt, and rcu_sched). If RCU_BOOST is
3958 set, valid values are 1-99 and the default is 1
3959 (the least-favored priority). Otherwise, when
3960 RCU_BOOST is not set, valid values are 0-99 and
3961 the default is zero (non-realtime operation).
3963 rcutree.rcu_nocb_gp_stride= [KNL]
3964 Set the number of NOCB callback kthreads in
3965 each group, which defaults to the square root
3966 of the number of CPUs. Larger numbers reduce
3967 the wakeup overhead on the global grace-period
3968 kthread, but increases that same overhead on
3969 each group's NOCB grace-period kthread.
3971 rcutree.qhimark= [KNL]
3972 Set threshold of queued RCU callbacks beyond which
3973 batch limiting is disabled.
3975 rcutree.qlowmark= [KNL]
3976 Set threshold of queued RCU callbacks below which
3977 batch limiting is re-enabled.
3979 rcutree.rcu_idle_gp_delay= [KNL]
3980 Set wakeup interval for idle CPUs that have
3981 RCU callbacks (RCU_FAST_NO_HZ=y).
3983 rcutree.rcu_idle_lazy_gp_delay= [KNL]
3984 Set wakeup interval for idle CPUs that have
3985 only "lazy" RCU callbacks (RCU_FAST_NO_HZ=y).
3986 Lazy RCU callbacks are those which RCU can
3987 prove do nothing more than free memory.
3989 rcutree.rcu_kick_kthreads= [KNL]
3990 Cause the grace-period kthread to get an extra
3991 wake_up() if it sleeps three times longer than
3992 it should at force-quiescent-state time.
3993 This wake_up() will be accompanied by a
3994 WARN_ONCE() splat and an ftrace_dump().
3996 rcutree.sysrq_rcu= [KNL]
3997 Commandeer a sysrq key to dump out Tree RCU's
3998 rcu_node tree with an eye towards determining
3999 why a new grace period has not yet started.
4001 rcuperf.gp_async= [KNL]
4002 Measure performance of asynchronous
4003 grace-period primitives such as call_rcu().
4005 rcuperf.gp_async_max= [KNL]
4006 Specify the maximum number of outstanding
4007 callbacks per writer thread. When a writer
4008 thread exceeds this limit, it invokes the
4009 corresponding flavor of rcu_barrier() to allow
4010 previously posted callbacks to drain.
4012 rcuperf.gp_exp= [KNL]
4013 Measure performance of expedited synchronous
4014 grace-period primitives.
4016 rcuperf.holdoff= [KNL]
4017 Set test-start holdoff period. The purpose of
4018 this parameter is to delay the start of the
4019 test until boot completes in order to avoid
4022 rcuperf.nreaders= [KNL]
4023 Set number of RCU readers. The value -1 selects
4024 N, where N is the number of CPUs. A value
4025 "n" less than -1 selects N-n+1, where N is again
4026 the number of CPUs. For example, -2 selects N
4027 (the number of CPUs), -3 selects N+1, and so on.
4028 A value of "n" less than or equal to -N selects
4031 rcuperf.nwriters= [KNL]
4032 Set number of RCU writers. The values operate
4033 the same as for rcuperf.nreaders.
4034 N, where N is the number of CPUs
4036 rcuperf.perf_type= [KNL]
4037 Specify the RCU implementation to test.
4039 rcuperf.shutdown= [KNL]
4040 Shut the system down after performance tests
4041 complete. This is useful for hands-off automated
4044 rcuperf.verbose= [KNL]
4045 Enable additional printk() statements.
4047 rcuperf.writer_holdoff= [KNL]
4048 Write-side holdoff between grace periods,
4049 in microseconds. The default of zero says
4052 rcutorture.fqs_duration= [KNL]
4053 Set duration of force_quiescent_state bursts
4056 rcutorture.fqs_holdoff= [KNL]
4057 Set holdoff time within force_quiescent_state bursts
4060 rcutorture.fqs_stutter= [KNL]
4061 Set wait time between force_quiescent_state bursts
4064 rcutorture.fwd_progress= [KNL]
4065 Enable RCU grace-period forward-progress testing
4066 for the types of RCU supporting this notion.
4068 rcutorture.fwd_progress_div= [KNL]
4069 Specify the fraction of a CPU-stall-warning
4070 period to do tight-loop forward-progress testing.
4072 rcutorture.fwd_progress_holdoff= [KNL]
4073 Number of seconds to wait between successive
4074 forward-progress tests.
4076 rcutorture.fwd_progress_need_resched= [KNL]
4077 Enclose cond_resched() calls within checks for
4078 need_resched() during tight-loop forward-progress
4081 rcutorture.gp_cond= [KNL]
4082 Use conditional/asynchronous update-side
4083 primitives, if available.
4085 rcutorture.gp_exp= [KNL]
4086 Use expedited update-side primitives, if available.
4088 rcutorture.gp_normal= [KNL]
4089 Use normal (non-expedited) asynchronous
4090 update-side primitives, if available.
4092 rcutorture.gp_sync= [KNL]
4093 Use normal (non-expedited) synchronous
4094 update-side primitives, if available. If all
4095 of rcutorture.gp_cond=, rcutorture.gp_exp=,
4096 rcutorture.gp_normal=, and rcutorture.gp_sync=
4097 are zero, rcutorture acts as if is interpreted
4098 they are all non-zero.
4100 rcutorture.n_barrier_cbs= [KNL]
4101 Set callbacks/threads for rcu_barrier() testing.
4103 rcutorture.nfakewriters= [KNL]
4104 Set number of concurrent RCU writers. These just
4105 stress RCU, they don't participate in the actual
4106 test, hence the "fake".
4108 rcutorture.nreaders= [KNL]
4109 Set number of RCU readers. The value -1 selects
4110 N-1, where N is the number of CPUs. A value
4111 "n" less than -1 selects N-n-2, where N is again
4112 the number of CPUs. For example, -2 selects N
4113 (the number of CPUs), -3 selects N+1, and so on.
4115 rcutorture.object_debug= [KNL]
4116 Enable debug-object double-call_rcu() testing.
4118 rcutorture.onoff_holdoff= [KNL]
4119 Set time (s) after boot for CPU-hotplug testing.
4121 rcutorture.onoff_interval= [KNL]
4122 Set time (jiffies) between CPU-hotplug operations,
4123 or zero to disable CPU-hotplug testing.
4125 rcutorture.shuffle_interval= [KNL]
4126 Set task-shuffle interval (s). Shuffling tasks
4127 allows some CPUs to go into dyntick-idle mode
4128 during the rcutorture test.
4130 rcutorture.shutdown_secs= [KNL]
4131 Set time (s) after boot system shutdown. This
4132 is useful for hands-off automated testing.
4134 rcutorture.stall_cpu= [KNL]
4135 Duration of CPU stall (s) to test RCU CPU stall
4136 warnings, zero to disable.
4138 rcutorture.stall_cpu_holdoff= [KNL]
4139 Time to wait (s) after boot before inducing stall.
4141 rcutorture.stall_cpu_irqsoff= [KNL]
4142 Disable interrupts while stalling if set.
4144 rcutorture.stat_interval= [KNL]
4145 Time (s) between statistics printk()s.
4147 rcutorture.stutter= [KNL]
4148 Time (s) to stutter testing, for example, specifying
4149 five seconds causes the test to run for five seconds,
4150 wait for five seconds, and so on. This tests RCU's
4151 ability to transition abruptly to and from idle.
4153 rcutorture.test_boost= [KNL]
4154 Test RCU priority boosting? 0=no, 1=maybe, 2=yes.
4155 "Maybe" means test if the RCU implementation
4156 under test support RCU priority boosting.
4158 rcutorture.test_boost_duration= [KNL]
4159 Duration (s) of each individual boost test.
4161 rcutorture.test_boost_interval= [KNL]
4162 Interval (s) between each boost test.
4164 rcutorture.test_no_idle_hz= [KNL]
4165 Test RCU's dyntick-idle handling. See also the
4166 rcutorture.shuffle_interval parameter.
4168 rcutorture.torture_type= [KNL]
4169 Specify the RCU implementation to test.
4171 rcutorture.verbose= [KNL]
4172 Enable additional printk() statements.
4174 rcupdate.rcu_cpu_stall_ftrace_dump= [KNL]
4175 Dump ftrace buffer after reporting RCU CPU
4178 rcupdate.rcu_cpu_stall_suppress= [KNL]
4179 Suppress RCU CPU stall warning messages.
4181 rcupdate.rcu_cpu_stall_timeout= [KNL]
4182 Set timeout for RCU CPU stall warning messages.
4184 rcupdate.rcu_expedited= [KNL]
4185 Use expedited grace-period primitives, for
4186 example, synchronize_rcu_expedited() instead
4187 of synchronize_rcu(). This reduces latency,
4188 but can increase CPU utilization, degrade
4189 real-time latency, and degrade energy efficiency.
4190 No effect on CONFIG_TINY_RCU kernels.
4192 rcupdate.rcu_normal= [KNL]
4193 Use only normal grace-period primitives,
4194 for example, synchronize_rcu() instead of
4195 synchronize_rcu_expedited(). This improves
4196 real-time latency, CPU utilization, and
4197 energy efficiency, but can expose users to
4198 increased grace-period latency. This parameter
4199 overrides rcupdate.rcu_expedited. No effect on
4200 CONFIG_TINY_RCU kernels.
4202 rcupdate.rcu_normal_after_boot= [KNL]
4203 Once boot has completed (that is, after
4204 rcu_end_inkernel_boot() has been invoked), use
4205 only normal grace-period primitives. No effect
4206 on CONFIG_TINY_RCU kernels.
4208 rcupdate.rcu_task_stall_timeout= [KNL]
4209 Set timeout in jiffies for RCU task stall warning
4210 messages. Disable with a value less than or equal
4213 rcupdate.rcu_self_test= [KNL]
4214 Run the RCU early boot self tests
4218 Run specified binary instead of /init from the ramdisk,
4219 used for early userspace startup. See initrd.
4222 force - Override the decision by the kernel to hide the
4223 advertisement of RDRAND support (this affects
4224 certain AMD processors because of buggy BIOS
4225 support, specifically around the suspend/resume
4229 Turn on/off individual RDT features. List is:
4230 cmt, mbmtotal, mbmlocal, l3cat, l3cdp, l2cat, l2cdp,
4232 E.g. to turn on cmt and turn off mba use:
4236 Format (x86 or x86_64):
4237 [w[arm] | c[old] | h[ard] | s[oft] | g[pio]] \
4239 [[,]b[ios] | a[cpi] | k[bd] | t[riple] | e[fi] | p[ci]] \
4241 Where reboot_mode is one of warm (soft) or cold (hard) or gpio
4242 (prefix with 'panic_' to set mode for panic
4244 reboot_type is one of bios, acpi, kbd, triple, efi, or pci,
4245 reboot_force is either force or not specified,
4246 reboot_cpu is s[mp]#### with #### being the processor
4247 to be used for rebooting.
4250 [KNL, SMP] Set scheduler's default relax_domain_level.
4251 See Documentation/admin-guide/cgroup-v1/cpusets.rst.
4253 reserve= [KNL,BUGS] Force kernel to ignore I/O ports or memory
4254 Format: <base1>,<size1>[,<base2>,<size2>,...]
4255 Reserve I/O ports or memory so the kernel won't use
4256 them. If <base> is less than 0x10000, the region
4257 is assumed to be I/O ports; otherwise it is memory.
4259 reservetop= [X86-32]
4261 Reserves a hole at the top of the kernel virtual
4266 Set the amount of memory to reserve for BIOS at
4267 the bottom of the address space.
4269 reset_devices [KNL] Force drivers to reset the underlying device
4270 during initialization.
4273 Specify the partition device for software suspend
4275 {/dev/<dev> | PARTUUID=<uuid> | <int>:<int> | <hex>}
4277 resume_offset= [SWSUSP]
4278 Specify the offset from the beginning of the partition
4279 given by "resume=" at which the swap header is located,
4280 in <PAGE_SIZE> units (needed only for swap files).
4281 See Documentation/power/swsusp-and-swap-files.rst
4283 resumedelay= [HIBERNATION] Delay (in seconds) to pause before attempting to
4284 read the resume files
4286 resumewait [HIBERNATION] Wait (indefinitely) for resume device to show up.
4287 Useful for devices that are detected asynchronously
4288 (e.g. USB and MMC devices).
4290 hibernate= [HIBERNATION]
4291 noresume Don't check if there's a hibernation image
4292 present during boot.
4293 nocompress Don't compress/decompress hibernation images.
4294 no Disable hibernation and resume.
4295 protect_image Turn on image protection during restoration
4296 (that will set all pages holding image data
4297 during restoration read-only).
4299 retain_initrd [RAM] Keep initrd memory after extraction
4301 retbleed= [X86] Control mitigation of RETBleed (Arbitrary
4302 Speculative Code Execution with Return Instructions)
4305 off - unconditionally disable
4306 auto - automatically select a migitation
4308 Selecting 'auto' will choose a mitigation method at run
4309 time according to the CPU.
4311 Not specifying this option is equivalent to retbleed=auto.
4313 rfkill.default_state=
4314 0 "airplane mode". All wifi, bluetooth, wimax, gps, fm,
4315 etc. communication is blocked by default.
4318 rfkill.master_switch_mode=
4319 0 The "airplane mode" button does nothing.
4320 1 The "airplane mode" button toggles between everything
4321 blocked and the previous configuration.
4322 2 The "airplane mode" button toggles between everything
4323 blocked and everything unblocked.
4325 rhash_entries= [KNL,NET]
4326 Set number of hash buckets for route cache
4329 [KNL] Disable ring 3 MONITOR/MWAIT feature on supported
4332 ro [KNL] Mount root device read-only on boot
4335 on Mark read-only kernel memory as read-only (default).
4336 off Leave read-only kernel memory writable for debugging.
4339 Enable the uart passthrough on the designated usb port
4340 on Rockchip SoCs. When active, the signals of the
4341 debug-uart get routed to the D+ and D- pins of the usb
4342 port and the regular usb controller gets disabled.
4344 root= [KNL] Root filesystem
4345 See name_to_dev_t comment in init/do_mounts.c.
4347 rootdelay= [KNL] Delay (in seconds) to pause before attempting to
4348 mount the root filesystem
4350 rootflags= [KNL] Set root filesystem mount option string
4352 rootfstype= [KNL] Set root filesystem type
4354 rootwait [KNL] Wait (indefinitely) for root device to show up.
4355 Useful for devices that are detected asynchronously
4356 (e.g. USB and MMC devices).
4358 rproc_mem=nn[KMG][@address]
4359 [KNL,ARM,CMA] Remoteproc physical memory block.
4360 Memory area to be used by remote processor image,
4363 rw [KNL] Mount root device read-write on boot
4365 S [KNL] Run init in single mode
4367 s390_iommu= [HW,S390]
4368 Set s390 IOTLB flushing mode
4370 With strict flushing every unmap operation will result in
4371 an IOTLB flush. Default is lazy flushing before reuse,
4375 See drivers/net/irda/sa1100_ir.c.
4377 sbni= [NET] Granch SBNI12 leased line adapter
4379 sched_debug [KNL] Enables verbose scheduler debug messages.
4381 schedstats= [KNL,X86] Enable or disable scheduled statistics.
4382 Allowed values are enable and disable. This feature
4383 incurs a small amount of overhead in the scheduler
4384 but is useful for debugging and performance tuning.
4386 skew_tick= [KNL] Offset the periodic timer tick per cpu to mitigate
4387 xtime_lock contention on larger systems, and/or RCU lock
4388 contention on all systems with CONFIG_MAXSMP set.
4389 Format: { "0" | "1" }
4390 0 -- disable. (may be 1 via CONFIG_CMDLINE="skew_tick=1"
4392 Note: increases power consumption, thus should only be
4393 enabled if running jitter sensitive (HPC/RT) workloads.
4395 security= [SECURITY] Choose a legacy "major" security module to
4396 enable at boot. This has been deprecated by the
4399 selinux= [SELINUX] Disable or enable SELinux at boot time.
4400 Format: { "0" | "1" }
4401 See security/selinux/Kconfig help text.
4404 Default value is set via kernel config option.
4405 If enabled at boot time, /selinux/disable can be used
4406 later to disable prior to initial policy load.
4408 apparmor= [APPARMOR] Disable or enable AppArmor at boot time
4409 Format: { "0" | "1" }
4410 See security/apparmor/Kconfig help text
4413 Default value is set via kernel config option.
4415 serialnumber [BUGS=X86-32]
4418 Maximal number of shapers.
4426 Disable merging of slabs with similar size. May be
4427 necessary if there is some reason to distinguish
4428 allocs to different slabs, especially in hardened
4429 environments where the risk of heap overflows and
4430 layout control by attackers can usually be
4431 frustrated by disabling merging. This will reduce
4432 most of the exposure of a heap attack to a single
4433 cache (risks via metadata attacks are mostly
4434 unchanged). Debug options disable merging on their
4436 For more information see Documentation/vm/slub.rst.
4438 slab_max_order= [MM, SLAB]
4439 Determines the maximum allowed order for slabs.
4440 A high setting may cause OOMs due to memory
4441 fragmentation. Defaults to 1 for systems with
4442 more than 32MB of RAM, 0 otherwise.
4444 slub_debug[=options[,slabs]] [MM, SLUB]
4445 Enabling slub_debug allows one to determine the
4446 culprit if slab objects become corrupted. Enabling
4447 slub_debug can create guard zones around objects and
4448 may poison objects when not in use. Also tracks the
4449 last alloc / free. For more information see
4450 Documentation/vm/slub.rst.
4452 slub_memcg_sysfs= [MM, SLUB]
4453 Determines whether to enable sysfs directories for
4454 memory cgroup sub-caches. 1 to enable, 0 to disable.
4455 The default is determined by CONFIG_SLUB_MEMCG_SYSFS_ON.
4456 Enabling this can lead to a very high number of debug
4457 directories and files being created under
4460 slub_max_order= [MM, SLUB]
4461 Determines the maximum allowed order for slabs.
4462 A high setting may cause OOMs due to memory
4463 fragmentation. For more information see
4464 Documentation/vm/slub.rst.
4466 slub_min_objects= [MM, SLUB]
4467 The minimum number of objects per slab. SLUB will
4468 increase the slab order up to slub_max_order to
4469 generate a sufficiently large slab able to contain
4470 the number of objects indicated. The higher the number
4471 of objects the smaller the overhead of tracking slabs
4472 and the less frequently locks need to be acquired.
4473 For more information see Documentation/vm/slub.rst.
4475 slub_min_order= [MM, SLUB]
4476 Determines the minimum page order for slabs. Must be
4477 lower than slub_max_order.
4478 For more information see Documentation/vm/slub.rst.
4480 slub_nomerge [MM, SLUB]
4481 Same with slab_nomerge. This is supported for legacy.
4482 See slab_nomerge for more information.
4485 Format: <io1>[,<io2>[,...,<io8>]]
4487 smsc-ircc2.nopnp [HW] Don't use PNP to discover SMC devices
4488 smsc-ircc2.ircc_cfg= [HW] Device configuration I/O port
4489 smsc-ircc2.ircc_sir= [HW] SIR base I/O port
4490 smsc-ircc2.ircc_fir= [HW] FIR base I/O port
4491 smsc-ircc2.ircc_irq= [HW] IRQ line
4492 smsc-ircc2.ircc_dma= [HW] DMA channel
4493 smsc-ircc2.ircc_transceiver= [HW] Transceiver type:
4494 0: Toshiba Satellite 1800 (GP data pin select)
4495 1: Fast pin select (default)
4498 smt [KNL,S390] Set the maximum number of threads (logical
4499 CPUs) to use per physical CPU on systems capable of
4500 symmetric multithreading (SMT). Will be capped to the
4501 actual hardware limit.
4503 Default: -1 (no limit)
4506 [KNL] Should the soft-lockup detector generate panics.
4509 A nonzero value instructs the soft-lockup detector
4510 to panic the machine when a soft-lockup occurs. This
4511 is also controlled by CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC
4512 which is the respective build-time switch to that
4515 softlockup_all_cpu_backtrace=
4516 [KNL] Should the soft-lockup detector generate
4517 backtraces on all cpus.
4520 sonypi.*= [HW] Sony Programmable I/O Control Device driver
4521 See Documentation/admin-guide/laptops/sonypi.rst
4523 spectre_v2= [X86] Control mitigation of Spectre variant 2
4524 (indirect branch speculation) vulnerability.
4525 The default operation protects the kernel from
4528 on - unconditionally enable, implies
4530 off - unconditionally disable, implies
4532 auto - kernel detects whether your CPU model is
4535 Selecting 'on' will, and 'auto' may, choose a
4536 mitigation method at run time according to the
4537 CPU, the available microcode, the setting of the
4538 CONFIG_RETPOLINE configuration option, and the
4539 compiler with which the kernel was built.
4541 Selecting 'on' will also enable the mitigation
4542 against user space to user space task attacks.
4544 Selecting 'off' will disable both the kernel and
4545 the user space protections.
4547 Specific mitigations can also be selected manually:
4549 retpoline - replace indirect branches
4550 retpoline,generic - Retpolines
4551 retpoline,lfence - LFENCE; indirect branch
4552 retpoline,amd - alias for retpoline,lfence
4553 eibrs - enhanced IBRS
4554 eibrs,retpoline - enhanced IBRS + Retpolines
4555 eibrs,lfence - enhanced IBRS + LFENCE
4556 ibrs - use IBRS to protect kernel
4558 Not specifying this option is equivalent to
4562 [X86] Control mitigation of Spectre variant 2
4563 (indirect branch speculation) vulnerability between
4566 on - Unconditionally enable mitigations. Is
4567 enforced by spectre_v2=on
4569 off - Unconditionally disable mitigations. Is
4570 enforced by spectre_v2=off
4572 prctl - Indirect branch speculation is enabled,
4573 but mitigation can be enabled via prctl
4574 per thread. The mitigation control state
4575 is inherited on fork.
4578 - Like "prctl" above, but only STIBP is
4579 controlled per thread. IBPB is issued
4580 always when switching between different user
4584 - Same as "prctl" above, but all seccomp
4585 threads will enable the mitigation unless
4586 they explicitly opt out.
4589 - Like "seccomp" above, but only STIBP is
4590 controlled per thread. IBPB is issued
4591 always when switching between different
4592 user space processes.
4594 auto - Kernel selects the mitigation depending on
4595 the available CPU features and vulnerability.
4598 If CONFIG_SECCOMP=y then "seccomp", otherwise "prctl"
4600 Not specifying this option is equivalent to
4601 spectre_v2_user=auto.
4603 spec_store_bypass_disable=
4604 [HW] Control Speculative Store Bypass (SSB) Disable mitigation
4605 (Speculative Store Bypass vulnerability)
4607 Certain CPUs are vulnerable to an exploit against a
4608 a common industry wide performance optimization known
4609 as "Speculative Store Bypass" in which recent stores
4610 to the same memory location may not be observed by
4611 later loads during speculative execution. The idea
4612 is that such stores are unlikely and that they can
4613 be detected prior to instruction retirement at the
4614 end of a particular speculation execution window.
4616 In vulnerable processors, the speculatively forwarded
4617 store can be used in a cache side channel attack, for
4618 example to read memory to which the attacker does not
4619 directly have access (e.g. inside sandboxed code).
4621 This parameter controls whether the Speculative Store
4622 Bypass optimization is used.
4624 On x86 the options are:
4626 on - Unconditionally disable Speculative Store Bypass
4627 off - Unconditionally enable Speculative Store Bypass
4628 auto - Kernel detects whether the CPU model contains an
4629 implementation of Speculative Store Bypass and
4630 picks the most appropriate mitigation. If the
4631 CPU is not vulnerable, "off" is selected. If the
4632 CPU is vulnerable the default mitigation is
4633 architecture and Kconfig dependent. See below.
4634 prctl - Control Speculative Store Bypass per thread
4635 via prctl. Speculative Store Bypass is enabled
4636 for a process by default. The state of the control
4637 is inherited on fork.
4638 seccomp - Same as "prctl" above, but all seccomp threads
4639 will disable SSB unless they explicitly opt out.
4641 Default mitigations:
4642 X86: If CONFIG_SECCOMP=y "seccomp", otherwise "prctl"
4644 On powerpc the options are:
4646 on,auto - On Power8 and Power9 insert a store-forwarding
4647 barrier on kernel entry and exit. On Power7
4648 perform a software flush on kernel entry and
4652 Not specifying this option is equivalent to
4653 spec_store_bypass_disable=auto.
4655 spia_io_base= [HW,MTD]
4661 Control the Special Register Buffer Data Sampling
4664 Certain CPUs are vulnerable to an MDS-like
4665 exploit which can leak bits from the random
4668 By default, this issue is mitigated by
4669 microcode. However, the microcode fix can cause
4670 the RDRAND and RDSEED instructions to become
4671 much slower. Among other effects, this will
4672 result in reduced throughput from /dev/urandom.
4674 The microcode mitigation can be disabled with
4675 the following option:
4677 off: Disable mitigation and remove
4678 performance impact to RDRAND and RDSEED
4680 srcutree.counter_wrap_check [KNL]
4681 Specifies how frequently to check for
4682 grace-period sequence counter wrap for the
4683 srcu_data structure's ->srcu_gp_seq_needed field.
4684 The greater the number of bits set in this kernel
4685 parameter, the less frequently counter wrap will
4686 be checked for. Note that the bottom two bits
4689 srcutree.exp_holdoff [KNL]
4690 Specifies how many nanoseconds must elapse
4691 since the end of the last SRCU grace period for
4692 a given srcu_struct until the next normal SRCU
4693 grace period will be considered for automatic
4694 expediting. Set to zero to disable automatic
4698 Speculative Store Bypass Disable control
4700 On CPUs that are vulnerable to the Speculative
4701 Store Bypass vulnerability and offer a
4702 firmware based mitigation, this parameter
4703 indicates how the mitigation should be used:
4705 force-on: Unconditionally enable mitigation for
4706 for both kernel and userspace
4707 force-off: Unconditionally disable mitigation for
4708 for both kernel and userspace
4709 kernel: Always enable mitigation in the
4710 kernel, and offer a prctl interface
4711 to allow userspace to register its
4712 interest in being mitigated too.
4714 stack_guard_gap= [MM]
4715 override the default stack gap protection. The value
4716 is in page units and it defines how many pages prior
4717 to (for stacks growing down) resp. after (for stacks
4718 growing up) the main stack are reserved for no other
4719 mapping. Default value is 256 pages.
4722 Enabled the stack tracer on boot up.
4724 stacktrace_filter=[function-list]
4725 [FTRACE] Limit the functions that the stack tracer
4726 will trace at boot up. function-list is a comma separated
4727 list of functions. This list can be changed at run
4728 time by the stack_trace_filter file in the debugfs
4729 tracing directory. Note, this enables stack tracing
4730 and the stacktrace above is not needed.
4734 Set the STI (builtin display/keyboard on the HP-PARISC
4735 machines) console (graphic card) which should be used
4736 as the initial boot-console.
4737 See also comment in drivers/video/console/sticore.c.
4740 See comment in drivers/video/console/sticore.c.
4743 Format: bpp:<bpp1>[:<bpp2>[:<bpp3>...]]
4745 sunrpc.min_resvport=
4746 sunrpc.max_resvport=
4748 SunRPC servers often require that client requests
4749 originate from a privileged port (i.e. a port in the
4750 range 0 < portnr < 1024).
4751 An administrator who wishes to reserve some of these
4752 ports for other uses may adjust the range that the
4753 kernel's sunrpc client considers to be privileged
4754 using these two parameters to set the minimum and
4755 maximum port values.
4757 sunrpc.svc_rpc_per_connection_limit=
4759 Limit the number of requests that the server will
4760 process in parallel from a single connection.
4761 The default value is 0 (no limit).
4765 Control how the NFS server code allocates CPUs to
4766 service thread pools. Depending on how many NICs
4767 you have and where their interrupts are bound, this
4768 option will affect which CPUs will do NFS serving.
4769 Note: this parameter cannot be changed while the
4770 NFS server is running.
4772 auto the server chooses an appropriate mode
4773 automatically using heuristics
4774 global a single global pool contains all CPUs
4775 percpu one pool for each CPU
4776 pernode one pool for each NUMA node (equivalent
4777 to global on non-NUMA machines)
4779 sunrpc.tcp_slot_table_entries=
4780 sunrpc.udp_slot_table_entries=
4782 Sets the upper limit on the number of simultaneous
4783 RPC calls that can be sent from the client to a
4784 server. Increasing these values may allow you to
4785 improve throughput, but will also increase the
4786 amount of memory reserved for use by the client.
4788 suspend.pm_test_delay=
4790 Sets the number of seconds to remain in a suspend test
4791 mode before resuming the system (see
4792 /sys/power/pm_test). Only available when CONFIG_PM_DEBUG
4793 is set. Default value is 5.
4796 Format: { on | off | y | n | 1 | 0 }
4797 This parameter controls use of the Protected
4798 Execution Facility on pSeries.
4801 [KNL] Enable accounting of swap in memory resource
4802 controller if no parameter or 1 is given or disable
4803 it if 0 is given (See Documentation/admin-guide/cgroup-v1/memory.rst)
4805 swiotlb= [ARM,IA-64,PPC,MIPS,X86]
4806 Format: { <int> | force | noforce }
4807 <int> -- Number of I/O TLB slabs
4808 force -- force using of bounce buffers even if they
4809 wouldn't be automatically used by the kernel
4810 noforce -- Never use bounce buffers (for debugging)
4814 sysfs.deprecated=0|1 [KNL]
4815 Enable/disable old style sysfs layout for old udev
4816 on older distributions. When this option is enabled
4817 very new udev will not work anymore. When this option
4818 is disabled (or CONFIG_SYSFS_DEPRECATED not compiled)
4819 in older udev will not work anymore.
4820 Default depends on CONFIG_SYSFS_DEPRECATED_V2 set in
4821 the kernel configuration.
4823 sysrq_always_enabled
4825 Ignore sysrq setting - this boot parameter will
4826 neutralize any effect of /proc/sys/kernel/sysrq.
4827 Useful for debugging.
4829 tcpmhash_entries= [KNL,NET]
4830 Set the number of tcp_metrics_hash slots.
4831 Default value is 8192 or 16384 depending on total
4832 ram pages. This is used to specify the TCP metrics
4833 cache size. See Documentation/networking/ip-sysctl.txt
4834 "tcp_no_metrics_save" section for more details.
4838 test_suspend= [SUSPEND][,N]
4839 Specify "mem" (for Suspend-to-RAM) or "standby" (for
4840 standby suspend) or "freeze" (for suspend type freeze)
4841 as the system sleep state during system startup with
4842 the optional capability to repeat N number of times.
4843 The system is woken from this state using a
4844 wakeup-capable RTC alarm.
4846 thash_entries= [KNL,NET]
4847 Set number of hash buckets for TCP connection
4849 thermal.act= [HW,ACPI]
4850 -1: disable all active trip points in all thermal zones
4851 <degrees C>: override all lowest active trip points
4853 thermal.crt= [HW,ACPI]
4854 -1: disable all critical trip points in all thermal zones
4855 <degrees C>: override all critical trip points
4857 thermal.nocrt= [HW,ACPI]
4858 Set to disable actions on ACPI thermal zone
4859 critical and hot trip points.
4861 thermal.off= [HW,ACPI]
4862 1: disable ACPI thermal control
4864 thermal.psv= [HW,ACPI]
4865 -1: disable all passive trip points
4866 <degrees C>: override all passive trip points to this
4869 thermal.tzp= [HW,ACPI]
4870 Specify global default ACPI thermal zone polling rate
4871 <deci-seconds>: poll all this frequency
4872 0: no polling (default)
4875 Force threading of all interrupt handlers except those
4876 marked explicitly IRQF_NO_THREAD.
4880 Specify if the kernel should make use of the cpu
4881 topology information if the hardware supports this.
4882 The scheduler will make use of this information and
4883 e.g. base its process migration decisions on it.
4886 topology_updates= [KNL, PPC, NUMA]
4888 Specify if the kernel should ignore (off)
4889 topology updates sent by the hypervisor to this
4894 tpm_suspend_pcr=[HW,TPM]
4895 Format: integer pcr id
4896 Specify that at suspend time, the tpm driver
4897 should extend the specified pcr with zeros,
4898 as a workaround for some chips which fail to
4899 flush the last written pcr on TPM_SaveState.
4900 This will guarantee that all the other pcrs
4903 trace_buf_size=nn[KMG]
4904 [FTRACE] will set tracing buffer size on each cpu.
4906 trace_event=[event-list]
4907 [FTRACE] Set and start specified trace events in order
4908 to facilitate early boot debugging. The event-list is a
4909 comma separated list of trace events to enable. See
4910 also Documentation/trace/events.rst
4912 trace_options=[option-list]
4913 [FTRACE] Enable or disable tracer options at boot.
4914 The option-list is a comma delimited list of options
4915 that can be enabled or disabled just as if you were
4916 to echo the option name into
4918 /sys/kernel/debug/tracing/trace_options
4920 For example, to enable stacktrace option (to dump the
4921 stack trace of each event), add to the command line:
4923 trace_options=stacktrace
4925 See also Documentation/trace/ftrace.rst "trace options"
4929 Have the tracepoints sent to printk as well as the
4930 tracing ring buffer. This is useful for early boot up
4931 where the system hangs or reboots and does not give the
4932 option for reading the tracing buffer or performing a
4933 ftrace_dump_on_oops.
4935 To turn off having tracepoints sent to printk,
4936 echo 0 > /proc/sys/kernel/tracepoint_printk
4937 Note, echoing 1 into this file without the
4938 tracepoint_printk kernel cmdline option has no effect.
4942 Having tracepoints sent to printk() and activating high
4943 frequency tracepoints such as irq or sched, can cause
4944 the system to live lock.
4947 [FTRACE] enable this option to disable tracing when a
4948 warning is hit. This turns off "tracing_on". Tracing can
4949 be enabled again by echoing '1' into the "tracing_on"
4950 file located in /sys/kernel/debug/tracing/
4952 This option is useful, as it disables the trace before
4953 the WARNING dump is called, which prevents the trace to
4954 be filled with content caused by the warning output.
4956 This option can also be set at run time via the sysctl
4957 option: kernel/traceoff_on_warning
4959 transparent_hugepage=
4961 Format: [always|madvise|never]
4962 Can be used to control the default behavior of the system
4963 with respect to transparent hugepages.
4964 See Documentation/admin-guide/mm/transhuge.rst
4967 tsc= Disable clocksource stability checks for TSC.
4969 [x86] reliable: mark tsc clocksource as reliable, this
4970 disables clocksource verification at runtime, as well
4971 as the stability checks done at bootup. Used to enable
4972 high-resolution timer mode on older hardware, and in
4973 virtualized environment.
4974 [x86] noirqtime: Do not use TSC to do irq accounting.
4975 Used to run time disable IRQ_TIME_ACCOUNTING on any
4976 platforms where RDTSC is slow and this accounting
4978 [x86] unstable: mark the TSC clocksource as unstable, this
4979 marks the TSC unconditionally unstable at bootup and
4980 avoids any further wobbles once the TSC watchdog notices.
4981 [x86] nowatchdog: disable clocksource watchdog. Used
4982 in situations with strict latency requirements (where
4983 interruptions from clocksource watchdog are not
4986 tsx= [X86] Control Transactional Synchronization
4987 Extensions (TSX) feature in Intel processors that
4988 support TSX control.
4990 This parameter controls the TSX feature. The options are:
4992 on - Enable TSX on the system. Although there are
4993 mitigations for all known security vulnerabilities,
4994 TSX has been known to be an accelerator for
4995 several previous speculation-related CVEs, and
4996 so there may be unknown security risks associated
4997 with leaving it enabled.
4999 off - Disable TSX on the system. (Note that this
5000 option takes effect only on newer CPUs which are
5001 not vulnerable to MDS, i.e., have
5002 MSR_IA32_ARCH_CAPABILITIES.MDS_NO=1 and which get
5003 the new IA32_TSX_CTRL MSR through a microcode
5004 update. This new MSR allows for the reliable
5005 deactivation of the TSX functionality.)
5007 auto - Disable TSX if X86_BUG_TAA is present,
5008 otherwise enable TSX on the system.
5010 Not specifying this option is equivalent to tsx=off.
5012 See Documentation/admin-guide/hw-vuln/tsx_async_abort.rst
5015 tsx_async_abort= [X86,INTEL] Control mitigation for the TSX Async
5016 Abort (TAA) vulnerability.
5018 Similar to Micro-architectural Data Sampling (MDS)
5019 certain CPUs that support Transactional
5020 Synchronization Extensions (TSX) are vulnerable to an
5021 exploit against CPU internal buffers which can forward
5022 information to a disclosure gadget under certain
5025 In vulnerable processors, the speculatively forwarded
5026 data can be used in a cache side channel attack, to
5027 access data to which the attacker does not have direct
5030 This parameter controls the TAA mitigation. The
5033 full - Enable TAA mitigation on vulnerable CPUs
5036 full,nosmt - Enable TAA mitigation and disable SMT on
5037 vulnerable CPUs. If TSX is disabled, SMT
5038 is not disabled because CPU is not
5039 vulnerable to cross-thread TAA attacks.
5040 off - Unconditionally disable TAA mitigation
5042 On MDS-affected machines, tsx_async_abort=off can be
5043 prevented by an active MDS mitigation as both vulnerabilities
5044 are mitigated with the same mechanism so in order to disable
5045 this mitigation, you need to specify mds=off too.
5047 Not specifying this option is equivalent to
5048 tsx_async_abort=full. On CPUs which are MDS affected
5049 and deploy MDS mitigation, TAA mitigation is not
5050 required and doesn't provide any additional
5054 Documentation/admin-guide/hw-vuln/tsx_async_abort.rst
5056 turbografx.map[2|3]= [HW,JOY]
5057 TurboGraFX parallel port interface
5059 <port#>,<js1>,<js2>,<js3>,<js4>,<js5>,<js6>,<js7>
5060 See also Documentation/input/devices/joystick-parport.rst
5062 udbg-immortal [PPC] When debugging early kernel crashes that
5063 happen after console_init() and before a proper
5064 console driver takes over, this boot options might
5065 help "seeing" what's going on.
5067 uhash_entries= [KNL,NET]
5068 Set number of hash buckets for UDP/UDP-Lite connections
5071 [USB] Ignore overcurrent events (default N).
5072 Some badly-designed motherboards generate lots of
5073 bogus events, for ports that aren't wired to
5074 anything. Set this parameter to avoid log spamming.
5075 Note that genuine overcurrent events won't be
5079 [X86] Cause panic on unknown NMI.
5081 usbcore.authorized_default=
5082 [USB] Default USB device authorization:
5083 (default -1 = authorized except for wireless USB,
5084 0 = not authorized, 1 = authorized, 2 = authorized
5085 if device connected to internal port)
5087 usbcore.autosuspend=
5088 [USB] The autosuspend time delay (in seconds) used
5089 for newly-detected USB devices (default 2). This
5090 is the time required before an idle device will be
5091 autosuspended. Devices for which the delay is set
5092 to a negative value won't be autosuspended at all.
5094 usbcore.usbfs_snoop=
5095 [USB] Set to log all usbfs traffic (default 0 = off).
5097 usbcore.usbfs_snoop_max=
5098 [USB] Maximum number of bytes to snoop in each URB
5101 usbcore.blinkenlights=
5102 [USB] Set to cycle leds on hubs (default 0 = off).
5104 usbcore.old_scheme_first=
5105 [USB] Start with the old device initialization
5106 scheme (default 0 = off).
5108 usbcore.usbfs_memory_mb=
5109 [USB] Memory limit (in MB) for buffers allocated by
5110 usbfs (default = 16, 0 = max = 2047).
5112 usbcore.use_both_schemes=
5113 [USB] Try the other device initialization scheme
5114 if the first one fails (default 1 = enabled).
5116 usbcore.initial_descriptor_timeout=
5117 [USB] Specifies timeout for the initial 64-byte
5118 USB_REQ_GET_DESCRIPTOR request in milliseconds
5119 (default 5000 = 5.0 seconds).
5121 usbcore.nousb [USB] Disable the USB subsystem
5124 [USB] A list of quirk entries to augment the built-in
5125 usb core quirk list. List entries are separated by
5126 commas. Each entry has the form
5127 VendorID:ProductID:Flags. The IDs are 4-digit hex
5128 numbers and Flags is a set of letters. Each letter
5129 will change the built-in quirk; setting it if it is
5130 clear and clearing it if it is set. The letters have
5131 the following meanings:
5132 a = USB_QUIRK_STRING_FETCH_255 (string
5133 descriptors must not be fetched using
5135 b = USB_QUIRK_RESET_RESUME (device can't resume
5136 correctly so reset it instead);
5137 c = USB_QUIRK_NO_SET_INTF (device can't handle
5138 Set-Interface requests);
5139 d = USB_QUIRK_CONFIG_INTF_STRINGS (device can't
5140 handle its Configuration or Interface
5142 e = USB_QUIRK_RESET (device can't be reset
5143 (e.g morph devices), don't use reset);
5144 f = USB_QUIRK_HONOR_BNUMINTERFACES (device has
5145 more interface descriptions than the
5146 bNumInterfaces count, and can't handle
5147 talking to these interfaces);
5148 g = USB_QUIRK_DELAY_INIT (device needs a pause
5149 during initialization, after we read
5150 the device descriptor);
5151 h = USB_QUIRK_LINEAR_UFRAME_INTR_BINTERVAL (For
5152 high speed and super speed interrupt
5153 endpoints, the USB 2.0 and USB 3.0 spec
5154 require the interval in microframes (1
5155 microframe = 125 microseconds) to be
5156 calculated as interval = 2 ^
5158 Devices with this quirk report their
5159 bInterval as the result of this
5160 calculation instead of the exponent
5161 variable used in the calculation);
5162 i = USB_QUIRK_DEVICE_QUALIFIER (device can't
5163 handle device_qualifier descriptor
5165 j = USB_QUIRK_IGNORE_REMOTE_WAKEUP (device
5166 generates spurious wakeup, ignore
5167 remote wakeup capability);
5168 k = USB_QUIRK_NO_LPM (device can't handle Link
5170 l = USB_QUIRK_LINEAR_FRAME_INTR_BINTERVAL
5171 (Device reports its bInterval as linear
5172 frames instead of the USB 2.0
5174 m = USB_QUIRK_DISCONNECT_SUSPEND (Device needs
5175 to be disconnected before suspend to
5176 prevent spurious wakeup);
5177 n = USB_QUIRK_DELAY_CTRL_MSG (Device needs a
5178 pause after every control message);
5179 o = USB_QUIRK_HUB_SLOW_RESET (Hub needs extra
5180 delay after resetting its port);
5181 Example: quirks=0781:5580:bk,0a5c:5834:gij
5184 [USBHID] The interval which mice are to be polled at.
5187 [USBHID] The interval which joysticks are to be polled at.
5190 [USBHID] The interval which keyboards are to be polled at.
5192 usb-storage.delay_use=
5193 [UMS] The delay in seconds before a new device is
5194 scanned for Logical Units (default 1).
5197 [UMS] A list of quirks entries to supplement or
5198 override the built-in unusual_devs list. List
5199 entries are separated by commas. Each entry has
5200 the form VID:PID:Flags where VID and PID are Vendor
5201 and Product ID values (4-digit hex numbers) and
5202 Flags is a set of characters, each corresponding
5203 to a common usb-storage quirk flag as follows:
5204 a = SANE_SENSE (collect more than 18 bytes
5205 of sense data, not on uas);
5206 b = BAD_SENSE (don't collect more than 18
5207 bytes of sense data, not on uas);
5208 c = FIX_CAPACITY (decrease the reported
5209 device capacity by one sector);
5210 d = NO_READ_DISC_INFO (don't use
5211 READ_DISC_INFO command, not on uas);
5212 e = NO_READ_CAPACITY_16 (don't use
5213 READ_CAPACITY_16 command);
5214 f = NO_REPORT_OPCODES (don't use report opcodes
5216 g = MAX_SECTORS_240 (don't transfer more than
5217 240 sectors at a time, uas only);
5218 h = CAPACITY_HEURISTICS (decrease the
5219 reported device capacity by one
5220 sector if the number is odd);
5221 i = IGNORE_DEVICE (don't bind to this
5223 j = NO_REPORT_LUNS (don't use report luns
5225 k = NO_SAME (do not use WRITE_SAME, uas only)
5226 l = NOT_LOCKABLE (don't try to lock and
5227 unlock ejectable media, not on uas);
5228 m = MAX_SECTORS_64 (don't transfer more
5229 than 64 sectors = 32 KB at a time,
5231 n = INITIAL_READ10 (force a retry of the
5232 initial READ(10) command, not on uas);
5233 o = CAPACITY_OK (accept the capacity
5234 reported by the device, not on uas);
5235 p = WRITE_CACHE (the device cache is ON
5236 by default, not on uas);
5237 r = IGNORE_RESIDUE (the device reports
5238 bogus residue values, not on uas);
5239 s = SINGLE_LUN (the device has only one
5241 t = NO_ATA_1X (don't allow ATA(12) and ATA(16)
5242 commands, uas only);
5243 u = IGNORE_UAS (don't bind to the uas driver);
5244 w = NO_WP_DETECT (don't test whether the
5245 medium is write-protected).
5246 y = ALWAYS_SYNC (issue a SYNCHRONIZE_CACHE
5247 even if the device claims no cache,
5249 Example: quirks=0419:aaf5:rl,0421:0433:rc
5251 user_debug= [KNL,ARM]
5253 See arch/arm/Kconfig.debug help text.
5254 1 - undefined instruction events
5256 4 - invalid data aborts
5259 Example: user_debug=31
5262 [X86] Flags controlling user PTE allocations.
5264 nohigh = do not allocate PTE pages in
5265 HIGHMEM regardless of setting
5269 On X86_32, this is an alias for vdso32=. Otherwise:
5271 vdso=1: enable VDSO (the default)
5272 vdso=0: disable VDSO mapping
5274 vdso32= [X86] Control the 32-bit vDSO
5275 vdso32=1: enable 32-bit VDSO
5276 vdso32=0 or vdso32=2: disable 32-bit VDSO
5278 See the help text for CONFIG_COMPAT_VDSO for more
5279 details. If CONFIG_COMPAT_VDSO is set, the default is
5280 vdso32=0; otherwise, the default is vdso32=1.
5282 For compatibility with older kernels, vdso32=2 is an
5285 Try vdso32=0 if you encounter an error that says:
5286 dl_main: Assertion `(void *) ph->p_vaddr == _rtld_local._dl_sysinfo_dso' failed!
5289 vector=percpu: enable percpu vector domain
5291 video= [FB] Frame buffer configuration
5292 See Documentation/fb/modedb.rst.
5294 video.brightness_switch_enabled= [0,1]
5295 If set to 1, on receiving an ACPI notify event
5296 generated by hotkey, video driver will adjust brightness
5297 level and then send out the event to user space through
5298 the allocated input device; If set to 0, video driver
5299 will only send out the event without touching backlight
5304 [VMMIO] Memory mapped virtio (platform) device.
5306 <size>@<baseaddr>:<irq>[:<id>]
5308 <size> := size (can use standard suffixes
5310 <baseaddr> := physical base address
5311 <irq> := interrupt number (as passed to
5313 <id> := (optional) platform device id
5315 virtio_mmio.device=1K@0x100b0000:48:7
5317 Can be used multiple times for multiple devices.
5319 vga= [BOOT,X86-32] Select a particular video mode
5320 See Documentation/x86/boot.rst and
5321 Documentation/admin-guide/svga.rst.
5322 Use vga=ask for menu.
5323 This is actually a boot loader parameter; the value is
5324 passed to the kernel using a special protocol.
5326 vm_debug[=options] [KNL] Available with CONFIG_DEBUG_VM=y.
5327 May slow down system boot speed, especially when
5328 enabled on systems with a large amount of memory.
5329 All options are enabled by default, and this
5330 interface is meant to allow for selectively
5331 enabling or disabling specific virtual memory
5334 Available options are:
5335 P Enable page structure init time poisoning
5336 - Disable all of the above options
5338 vmalloc=nn[KMG] [KNL,BOOT] Forces the vmalloc area to have an exact
5339 size of <nn>. This can be used to increase the
5340 minimum size (128MB on x86). It can also be used to
5341 decrease the size and leave more room for directly
5344 vmcp_cma=nn[MG] [KNL,S390]
5345 Sets the memory size reserved for contiguous memory
5346 allocations for the vmcp device driver.
5348 vmhalt= [KNL,S390] Perform z/VM CP command after system halt.
5351 vmpanic= [KNL,S390] Perform z/VM CP command after kernel panic.
5354 vmpoff= [KNL,S390] Perform z/VM CP command after power off.
5358 Controls the behavior of vsyscalls (i.e. calls to
5359 fixed addresses of 0xffffffffff600x00 from legacy
5360 code). Most statically-linked binaries and older
5361 versions of glibc use these calls. Because these
5362 functions are at fixed addresses, they make nice
5363 targets for exploits that can control RIP.
5365 emulate [default] Vsyscalls turn into traps and are
5366 emulated reasonably safely. The vsyscall
5369 xonly Vsyscalls turn into traps and are
5370 emulated reasonably safely. The vsyscall
5371 page is not readable.
5373 none Vsyscalls don't work at all. This makes
5374 them quite hard to use for exploits but
5375 might break your system.
5377 vt.color= [VT] Default text color.
5378 Format: 0xYX, X = foreground, Y = background.
5379 Default: 0x07 = light gray on black.
5381 vt.cur_default= [VT] Default cursor shape.
5382 Format: 0xCCBBAA, where AA, BB, and CC are the same as
5383 the parameters of the <Esc>[?A;B;Cc escape sequence;
5384 see VGA-softcursor.txt. Default: 2 = underline.
5386 vt.default_blu= [VT]
5387 Format: <blue0>,<blue1>,<blue2>,...,<blue15>
5388 Change the default blue palette of the console.
5389 This is a 16-member array composed of values
5392 vt.default_grn= [VT]
5393 Format: <green0>,<green1>,<green2>,...,<green15>
5394 Change the default green palette of the console.
5395 This is a 16-member array composed of values
5398 vt.default_red= [VT]
5399 Format: <red0>,<red1>,<red2>,...,<red15>
5400 Change the default red palette of the console.
5401 This is a 16-member array composed of values
5407 Set system-wide default UTF-8 mode for all tty's.
5408 Default is 1, i.e. UTF-8 mode is enabled for all
5409 newly opened terminals.
5411 vt.global_cursor_default=
5414 Set system-wide default for whether a cursor
5415 is shown on new VTs. Default is -1,
5416 i.e. cursors will be created by default unless
5417 overridden by individual drivers. 0 will hide
5418 cursors, 1 will display them.
5420 vt.italic= [VT] Default color for italic text; 0-15.
5423 vt.underline= [VT] Default color for underlined text; 0-15.
5426 watchdog timers [HW,WDT] For information on watchdog timers,
5427 see Documentation/watchdog/watchdog-parameters.rst
5428 or other driver-specific files in the
5429 Documentation/watchdog/ directory.
5433 Set the hard lockup detector stall duration
5434 threshold in seconds. The soft lockup detector
5435 threshold is set to twice the value. A value of 0
5436 disables both lockup detectors. Default is 10
5439 workqueue.watchdog_thresh=
5440 If CONFIG_WQ_WATCHDOG is configured, workqueue can
5441 warn stall conditions and dump internal state to
5442 help debugging. 0 disables workqueue stall
5443 detection; otherwise, it's the stall threshold
5444 duration in seconds. The default value is 30 and
5445 it can be updated at runtime by writing to the
5446 corresponding sysfs file.
5448 workqueue.disable_numa
5449 By default, all work items queued to unbound
5450 workqueues are affine to the NUMA nodes they're
5451 issued on, which results in better behavior in
5452 general. If NUMA affinity needs to be disabled for
5453 whatever reason, this option can be used. Note
5454 that this also can be controlled per-workqueue for
5455 workqueues visible under /sys/bus/workqueue/.
5457 workqueue.power_efficient
5458 Per-cpu workqueues are generally preferred because
5459 they show better performance thanks to cache
5460 locality; unfortunately, per-cpu workqueues tend to
5461 be more power hungry than unbound workqueues.
5463 Enabling this makes the per-cpu workqueues which
5464 were observed to contribute significantly to power
5465 consumption unbound, leading to measurably lower
5466 power usage at the cost of small performance
5469 The default value of this parameter is determined by
5470 the config option CONFIG_WQ_POWER_EFFICIENT_DEFAULT.
5472 workqueue.debug_force_rr_cpu
5473 Workqueue used to implicitly guarantee that work
5474 items queued without explicit CPU specified are put
5475 on the local CPU. This guarantee is no longer true
5476 and while local CPU is still preferred work items
5477 may be put on foreign CPUs. This debug option
5478 forces round-robin CPU selection to flush out
5479 usages which depend on the now broken guarantee.
5480 When enabled, memory and cache locality will be
5483 x2apic_phys [X86-64,APIC] Use x2apic physical mode instead of
5484 default x2apic cluster mode on platforms
5487 x86_intel_mid_timer= [X86-32,APBT]
5488 Choose timer option for x86 Intel MID platform.
5489 Two valid options are apbt timer only and lapic timer
5490 plus one apbt timer for broadcast timer.
5491 x86_intel_mid_timer=apbt_only | lapic_and_apbt
5493 xen_512gb_limit [KNL,X86-64,XEN]
5494 Restricts the kernel running paravirtualized under Xen
5495 to use only up to 512 GB of RAM. The reason to do so is
5496 crash analysis tools and Xen tools for doing domain
5497 save/restore/migration must be enabled to handle larger
5500 xen_emul_unplug= [HW,X86,XEN]
5501 Unplug Xen emulated devices
5502 Format: [unplug0,][unplug1]
5503 ide-disks -- unplug primary master IDE devices
5504 aux-ide-disks -- unplug non-primary-master IDE devices
5505 nics -- unplug network devices
5506 all -- unplug all emulated devices (NICs and IDE disks)
5507 unnecessary -- unplugging emulated devices is
5508 unnecessary even if the host did not respond to
5510 never -- do not unplug even if version check succeeds
5512 xen_legacy_crash [X86,XEN]
5513 Crash from Xen panic notifier, without executing late
5514 panic() code such as dumping handler.
5516 xen_nopvspin [X86,XEN]
5517 Disables the ticketlock slowpath using Xen PV
5521 Disables the PV optimizations forcing the HVM guest to
5522 run as generic HVM guest with no PV drivers.
5523 This option is obsoleted by the "nopv" option, which
5524 has equivalent effect for XEN platform.
5526 xen_no_vector_callback
5527 [KNL,X86,XEN] Disable the vector callback for Xen
5528 event channel interrupts.
5530 xen_scrub_pages= [XEN]
5531 Boolean option to control scrubbing pages before giving them back
5532 to Xen, for use by other domains. Can be also changed at runtime
5533 with /sys/devices/system/xen_memory/xen_memory0/scrub_pages.
5534 Default value controlled with CONFIG_XEN_SCRUB_PAGES_DEFAULT.
5536 xen_timer_slop= [X86-64,XEN]
5537 Set the timer slop (in nanoseconds) for the virtual Xen
5538 timers (default is 100000). This adjusts the minimum
5539 delta of virtualized Xen timers, where lower values
5540 improve timer resolution at the expense of processing
5541 more timer interrupts.
5543 nopv= [X86,XEN,KVM,HYPER_V,VMWARE]
5544 Disables the PV optimizations forcing the guest to run
5545 as generic guest with no PV drivers. Currently support
5546 XEN HVM, KVM, HYPER_V and VMWARE guest.
5548 xen.balloon_boot_timeout= [XEN]
5549 The time (in seconds) to wait before giving up to boot
5550 in case initial ballooning fails to free enough memory.
5551 Applies only when running as HVM or PVH guest and
5552 started with less memory configured than allowed at
5553 max. Default is 180.
5555 xen.event_eoi_delay= [XEN]
5556 How long to delay EOI handling in case of event
5557 storms (jiffies). Default is 10.
5559 xen.event_loop_timeout= [XEN]
5560 After which time (jiffies) the event handling loop
5561 should start to delay EOI handling. Default is 2.
5563 xirc2ps_cs= [NET,PCMCIA]
5565 <irq>,<irq_mask>,<io>,<full_duplex>,<do_sound>,<lockup_hack>[,<irq2>[,<irq3>[,<irq4>]]]
5568 By default on POWER9 and above, the kernel will
5569 natively use the XIVE interrupt controller. This option
5570 allows the fallback firmware mode to be used:
5572 off Fallback to firmware control of XIVE interrupt
5573 controller on both pseries and powernv
5574 platforms. Only useful on POWER9 and above.
5576 xhci-hcd.quirks [USB,KNL]
5577 A hex value specifying bitmask with supplemental xhci
5578 host controller quirks. Meaning of each bit can be
5579 consulted in header drivers/usb/host/xhci.h.
5582 Format: { early | on | rw | ro | off }
5583 Controls if xmon debugger is enabled. Default is off.
5584 Passing only "xmon" is equivalent to "xmon=early".
5585 early Call xmon as early as possible on boot; xmon
5586 debugger is called from setup_arch().
5587 on xmon debugger hooks will be installed so xmon
5588 is only called on a kernel crash. Default mode,
5589 i.e. either "ro" or "rw" mode, is controlled
5590 with CONFIG_XMON_DEFAULT_RO_MODE.
5591 rw xmon debugger hooks will be installed so xmon
5592 is called only on a kernel crash, mode is write,
5593 meaning SPR registers, memory and, other data
5594 can be written using xmon commands.
5595 ro same as "rw" option above but SPR registers,
5596 memory, and other data can't be written using
5598 off xmon is disabled.