Lines Matching +full:processor +full:- +full:intensive
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
11 rsdt -- prefer RSDT over (default) XSDT
12 copy_dsdt -- copy DSDT to memory
26 If set to vendor, prefer vendor-specific driver
58 Documentation/firmware-guide/acpi/debug.rst for more information about
61 Enable processor driver info messages:
116 Format: <byte> or <bitmap-list>
119 Disable auto-serialization of AML methods
122 auto-serialization feature.
140 Ignore the ACPI-based watchdog interface (WDAT) and let
161 acpi_osi=! # disable all built-in OS vendor
163 acpi_osi=!! # enable all built-in OS vendor
225 For broken nForce2 BIOS resulting in XT-PIC timer.
234 as soon as the kernel's real-mode entry point is called.
272 See Documentation/sound/alsa-configuration.rst
279 align_va_addr= [X86-64]
284 CPU-intensive style benchmark, and it can vary highly in
287 32: only for 32-bit processes
288 64: only for 64-bit processes
289 on: enable for both 32- and 64-bit processes
290 off: disable for both 32- and 64-bit processes
300 Allow execve() of 32-bit applications and setting of the
302 subset of the CPUs support 32-bit EL0. When this
303 parameter is present, the set of CPUs supporting 32-bit
305 and hot-unplug operations may be restricted.
307 See Documentation/arm64/asymmetric-32bit.rst for more
310 amd_iommu= [HW,X86-64]
313 fullflush - Deprecated, equivalent to iommu.strict=1
314 off - do not initialize any AMD IOMMU found in
316 force_isolation - Force device isolation for all
321 force_enable - Force enable the IOMMU on platforms known
324 pgtbl_v1 - Use v1 page table for DMA-API (Default).
325 pgtbl_v2 - Use v2 page table for DMA-API.
327 amd_iommu_dump= [HW,X86-64]
333 amd_iommu_intr= [HW,X86-64]
336 legacy - Use legacy interrupt remapping mode.
337 vapic - Use virtual APIC mode, which allows IOMMU
339 This mode requires kvm-amd.avic=1.
353 Power management functions (SPARCstation-4/5 + deriv.)
355 Disable APC CPU standby support. SPARCstation-Fox does
356 not play well with APC CPU idle - disable it if you have
363 when initialising the APIC and IO-APIC components.
364 For X86-32, this can also be used to specify an APIC
384 to set it to "all" by meaning -- no limit here.
393 arcrimi= [HW,NET] ARCnet - "RIM I" (entirely mem-mapped) cards
432 audit= [KNL] Enable the audit sub-system
434 0 | off - kernel audit is disabled and can not be
436 unset - kernel audit is initialized but disabled and
438 1 | on - kernel audit is initialized and partially
451 0 - Disable the BAU.
452 1 - Enable the BAU.
453 unset - Disable the BAU.
480 See Documentation/block/cmdline-partition.rst
491 See Documentation/admin-guide/bootconfig.rst
496 bttv.pll= See Documentation/admin-guide/media/bttv.rst
505 cachesize= [BUGS=X86-32] Override level 2 CPU cache size detection.
524 inclusive. See arch/mips/include/asm/pgtable-bits.h
534 - foo isn't auto-mounted if you mount all cgroups in
536 - foo isn't visible as an individually mountable
538 - if foo is an optional feature then the feature is
544 Specifying "pressure" disables per-cgroup pressure
558 nosocket -- Disable socket memory accounting.
559 nokmem -- Disable kernel memory accounting.
564 0 -- check protection applied by kernel (includes
566 1 -- check protection requested by application.
578 numbers X. Note the Linux-specific bits are not necessarily
579 stable over kernel options, but the vendor-specific
599 force such clocks to be always-on nor does it reserve
603 information, see Documentation/driver-api/clk.rst.
605 clock= [BUGS=X86-32, HW] gettimeofday clocksource override.
622 [X86-32] pit,hpet,tsc;
629 [X86-64] hpet,tsc
635 architected timer so that code using WFE-based polling
655 clocksource-wdtest.holdoff= [KNL]
661 cma=nn[MG]@[start[MG][-end[MG]]]
672 Sets the size of kernel per-numa memory area for
674 per-numa CMA altogether. And If this option is not
676 With per-numa CMA enabled, DMA users on node nid will
692 com20020= [HW,NET] ARCnet - COM20020 chipset
696 com90io= [HW,NET] ARCnet - COM90xx chipset (IO-mapped buffers)
700 ARCnet - COM90xx chipset (memory-mapped buffers)
718 See Documentation/admin-guide/serial-console.rst for more
728 Start an early, polled-mode console on the 8250/16550
731 MMIO inter-register address stride is either 8-bit
732 (mmio), 16-bit (mmio16), or 32-bit (mmio32).
736 the h/w is not re-initialized.
763 syscall, or to executing "dmesg -S --raw" or to reading
801 disable the cpuidle sub-system
807 disable the cpufreq sub-system
815 [X86] Delay for N microsec between assert and de-assert
821 Run kdump after running panic-notifiers and dumping
834 [KNL, X86-64] Select a region under 4G first, and
837 See Documentation/admin-guide/kdump/kdump.rst for further details.
842 start-[end] where start and end are both
844 Documentation/admin-guide/kdump/kdump.rst for an example.
847 [KNL, X86-64, ARM64] range could be above 4G. Allow kernel
854 [KNL, X86-64] range under 4G. When crashkernel=X,high
859 low memory is needed to make sure DMA buffers for 32-bit
875 [KNL] Disable crypto self-tests
883 csdlock_debug= [KNL] Enable debug add-ons of cross-CPU function call
899 See also Documentation/input/devices/joystick-parport.rst
912 [KNL] verbose locking self-tests
915 self-tests.
917 (no extra messages), setting it to -1 (all bits set)
918 will print _a_lot_ more information - normally only
956 Format: { on, no-mount, off }
958 no-mount:
963 get a -EPERM as result when trying to register files
967 Default value is set in build-time with a kernel configuration.
979 Documentation/admin-guide/mm/hugetlbpage.rst.
993 delayacct [KNL] Enable per-task delay accounting
1097 entries for DMA-API debugging code. One entry is
1098 required per DMA-API allocation. Use this if the
1099 DMA-API debugging code disables itself because the
1103 With this option the DMA-API debugging driver
1121 Generic built-in EDID data sets are used, if one of
1126 available in Documentation/admin-guide/edid.rst. An EDID
1138 Control how the dt_cpu_ftrs device-tree binding is
1148 what data is available or for reverse-engineering.
1153 Documentation/admin-guide/dynamic-debug-howto.rst
1174 determined by stdout-path property in device tree's
1179 Start an early, polled-mode console on a Cadence
1190 Start an early, polled-mode console on the 8250/16550
1192 MMIO inter-register address stride is either 8-bit
1193 (mmio) or 32-bit (mmio32 or mmio32be).
1201 Start an early, polled-mode console on a pl011 serial
1205 the driver will use only 32-bit accessors to read/write
1214 Start an early, polled-mode console on a meson serial
1220 Start an early, polled-mode console on an msm serial
1226 Start an early, polled-mode console on an msm serial
1232 Start an early, polled-mode console on a serial port
1238 Start an early, polled-mode console on a serial port
1244 Use RISC-V SBI (Supervisor Binary Interface) for early
1262 Start an early, polled-mode console on a lantiq serial
1276 Start an early, polled-mode, output-only console on the
1281 Start an early, polled-mode console on the
1287 Start an early, polled-mode console on a Qualcomm
1295 coherent non-x86 systems that use system memory for
1395 attribute is added to range 0x100000000-0x180000000 and
1396 0x10a0000000-0x1120000000.
1400 range 0x240000000-0x43fffffff.
1412 Documentation/admin-guide/acpi/ssdt-overlays.rst for details.
1429 elanfreq= [X86-32]
1437 See Documentation/admin-guide/kdump/kdump.rst for details.
1453 0 -- permissive (log only, no denials).
1454 1 -- enforcing (deny and log).
1486 See also Documentation/fault-injection/.
1490 See Documentation/admin-guide/sysctl/net.rst for
1494 See Documentation/admin-guide/blockdev/floppy.rst.
1497 [IA-64] Avoid check_sal_cache_flush which may hang on
1502 forcepae [X86-32]
1529 ftrace_filter=[function-list]
1531 tracer at boot up. function-list is a comma-separated
1536 ftrace_notrace=[function-list]
1538 function-list. This list can be changed at run time
1542 ftrace_graph_filter=[function-list]
1545 function-list is a comma-separated list of functions
1549 ftrace_graph_notrace=[function-list]
1551 function-list. This list is a comma-separated list of
1571 off -- Don't create device links from firmware info.
1572 permissive -- Create device links from firmware info
1575 on -- Create device links from firmware info and use it
1577 rpm -- Like "on", but also use to order runtime PM.
1588 See also Documentation/input/devices/joystick-parport.rst
1592 gart_fix_e820= [X86-64] disable the fix e820 for K8 GART
1596 gcov_persist= [GCOV] When non-zero (default), profiling data for
1606 gpio-mockup.gpio_mockup_ranges
1609 gpio-mockup.gpio_mockup_named_lines
1641 against bounds-checking flaws in the kernel's
1647 [KNL] Should the hard-lockup detector generate
1653 for 64-bit NUMA, off otherwise.
1656 hcl= [IA-64] SGI's Hardware Graph compatibility layer
1663 corresponding firmware-first mode error processing
1673 during restoration read-only).
1699 hpet= [X86-32,HPET] option to control HPET usage
1716 number of pages to allocate per-node can be specified.
1717 See also Documentation/admin-guide/mm/hugetlbpage.rst.
1728 Documentation/admin-guide/mm/hugetlbpage.rst.
1739 boot-time allocation of gigantic hugepages is skipped.
1767 by the CONFIG_BOOTPARAM_HUNG_TASK_PANIC build-time
1773 hvc_iucv_allow= [S390] Comma-separated list of z/VM user IDs.
1796 (disabled by default, and as a pre-condition
1798 i8042.direct [HW] Put keyboard port into non-translated mode
1812 suspend-to-ram transitions, only during s2r
1836 -1 -- never invert brightness
1837 0 -- machine default
1838 1 -- force brightness inversion
1852 idle=nomwait: Disable mwait for CPU C-states
1880 legacy only accept legacy-NaN binaries, if supported
1882 2008 only accept 2008-NaN binaries, if supported
1891 'relaxed' straps the emulator for both legacy-NaN and
1892 2008-NaN, whereas 'strict' enables legacy-NaN only on
1901 Ignore loglevel setting - this will print /all/
1968 Formats: { "ima" | "ima-ng" | "ima-ngv2" | "ima-sig" |
1969 "ima-sigv2" }
1970 Default: "ima-ng"
2002 initcall_blacklist= [KNL] Do not execute a comma-separated list of
2003 initcall functions. Useful for debugging built-in
2048 0 -- basic integrity auditing messages. (Default)
2049 1 -- additional integrity auditing messages.
2077 could harm performance of some high-throughput
2086 1 to 9 specify maximum depth of C-state.
2096 used along with the hardware-managed P-states (HWP)
2100 in favor of acpi-cpufreq. Forcing the intel_pstate driver
2101 instead of acpi-cpufreq may disable platform features, such
2103 P-States information being indicated to OSPM and therefore
2106 or on platforms that use pcc-cpufreq instead of acpi-cpufreq.
2119 Allow per-logical-CPU P-State performance control limits using
2122 intremap= [X86-64, Intel-IOMMU]
2127 BIOS x2APIC opt-out request will be ignored
2151 0 - Try to allocate a 32-bit DMA address first, before
2153 1 - Allocate directly from the full usable range,
2155 greater than 32-bit addressing.
2159 0 - Lazy mode.
2165 1 - Strict mode.
2168 unset - Use value of CONFIG_IOMMU_DEFAULT_DMA_{LAZY,STRICT}.
2170 legacy driver-specific options takes precedence.
2175 0 - Use IOMMU translation for DMA.
2176 1 - Bypass the IOMMU for DMA.
2177 unset - Use value of CONFIG_IOMMU_DEFAULT_PASSTHROUGH.
2179 io7= [HW] IO7 for Marvel-based Alpha systems
2194 See Documentation/admin-guide/nfs/nfsroot.rst.
2218 Enables support for pseudo-NMIs in the kernel. This
2237 [Deprecated - use cpusets instead]
2238 Format: [flag-list,]<cpu-list>
2269 "number of CPUs in system - 1".
2295 The format of <cpu-list> is described above.
2299 ivrs_ioapic [HW,X86-64]
2300 Provide an override to the IOAPIC-ID<->DEVICE-ID
2304 * To map IOAPIC-ID decimal 10 to PCI device 00:14.0
2307 * To map IOAPIC-ID decimal 10 to PCI segment 0x1 and
2311 ivrs_hpet [HW,X86-64]
2312 Provide an override to the HPET-ID<->DEVICE-ID
2316 * To map HPET-ID decimal 0 to PCI device 00:14.0
2319 * To map HPET-ID decimal 10 to PCI segment 0x1 and
2323 ivrs_acpihid [HW,X86-64]
2324 Provide an override to the ACPI-HID:UID<->DEVICE-ID
2327 For example, to map UART-HID:UID AMD0020:0 to
2352 kernelcore= [KNL,X86,IA-64,PPC]
2355 the kernel for non-movable allocations. The requested
2365 subsystem. Note that allocations like PTEs-from-HighMem
2373 for non-movable allocations and remaining memory is used
2384 gdb or control-c on the dbgp connection. When
2385 not using this parameter you use sysrq-g to break into
2390 or a supported polling keyboard driver (non-usb).
2417 Configure the RouterBoard 532 series on-chip
2420 kmemleak= [KNL] Boot-time kmemleak enable/disable
2426 kprobe_event=[probe-list]
2428 The probe-list is a semicolon delimited list of probe
2458 execution by eliminating the write-protection faults
2503 back to huge pages. If the value is a non-zero N, KVM will
2508 kvm-amd.nested= [KVM,AMD] Allow nested virtualization in KVM/SVM.
2511 kvm-amd.npt= [KVM,AMD] Disable nested paging (virtualized MMU)
2513 Default is 1 (enabled) if in 64-bit or 32-bit PAE mode.
2515 kvm-arm.mode=
2520 nvhe: Standard nVHE-based mode, without support for
2523 protected: nVHE-based mode with support for guests whose
2530 kvm-arm.vgic_v3_group0_trap=
2531 [KVM,ARM] Trap guest accesses to GICv3 group-0
2534 kvm-arm.vgic_v3_group1_trap=
2535 [KVM,ARM] Trap guest accesses to GICv3 group-1
2538 kvm-arm.vgic_v3_common_trap=
2542 kvm-arm.vgic_v4_enable=
2554 kvm-intel.ept= [KVM,Intel] Disable extended page tables
2558 kvm-intel.emulate_invalid_guest_state=
2560 Ignored if kvm-intel.enable_unrestricted_guest=1, as
2566 kvm-intel.flexpriority=
2570 kvm-intel.nested=
2574 kvm-intel.unrestricted_guest=
2579 kvm-intel.vmentry_l1d_flush=[KVM,Intel] Mitigation for L1 Terminal Fault
2580 CVE-2018-3620.
2591 kvm-intel.vpid= [KVM,Intel] Disable Virtual Processor Identification
2610 on - enable the interface for the mitigation
2675 For details see: Documentation/admin-guide/hw-vuln/l1tf.rst
2681 lapic [X86-32,APIC] Enable the local APIC even if BIOS
2685 value for LAPIC timer one-shot implementation. Default
2708 libata.force= [LIBATA] Force configurations. The format is a comma-
2720 first fan-out link behind PMP device. It does not
2734 * Transfer mode: pio[0-7], mwdma[0-4] and udma[0-7].
2741 * rstonce: only attempt one reset during hot-unplug
2820 Set the number of locking read-acquisition kthreads.
2825 Set the number of locking write-acquisition kthreads.
2828 Set time (s) after boot for CPU-hotplug testing.
2831 Set time (s) between CPU-hotplug operations, or
2832 zero to disable CPU-hotplug testing.
2835 Set task-shuffle interval (jiffies). Shuffling
2836 tasks allows some CPUs to go into dyntick-idle
2841 is useful for hands-off automated testing.
2874 7 (KERN_DEBUG) debug-level messages
2884 logo.nologo [FB] Disables display of the built-in Linux logo.
2902 an IEEE 1284-compliant printer is attached; if
2908 time-consuming boot-time autodetection (up to 250 ms per
2929 machvec= [IA-64] Force the use of a particular machine-vector
2935 Example: machtype=lemote-yeeloong-2f-7inch
2937 max_addr=nn[KMG] [KNL,BOOT,IA-64] All physical memory greater
2950 (loop.max_loop) unconditionally pre-created at init time. The default
2953 devices can be requested on-demand with the
2954 /dev/loop-control interface.
2956 mce [X86-32] Machine Check Exception
2958 mce=option [X86-64] See Documentation/x86/x86_64/boot-options.rst
2961 See Documentation/admin-guide/md.rst.
2968 Control mitigation for the Micro-architectural Data
2983 full - Enable MDS mitigation on vulnerable CPUs
2984 full,nosmt - Enable MDS mitigation and disable
2986 off - Unconditionally disable MDS mitigation
2988 On TAA-affected machines, mds=off can be prevented by
2997 For details see: Documentation/admin-guide/hw-vuln/mds.rst
3011 [ARC,MICROBLAZE] - the limit applies only to low memory,
3014 [ARM64] - only limits memory covered by the linear
3027 [ARM,MIPS] - override the memory layout reported by
3034 mem=nopentium [BUGS=X86-32] Disable usage of 4MB pages for kernel
3041 per-device physically contiguous DMA buffers.
3049 See Documentation/admin-guide/mm/memory-hotplug.rst.
3074 Example: Exclude memory from 0x18690000-0x1869ffff
3088 memmap=<size>%<offset>-<oldtype>+<newtype>
3090 from <oldtype> to <newtype>. If "-<oldtype>" is left
3105 repeatable BIOS-originated corruption always
3149 mem_encrypt= [X86-64] AMD Secure Memory Encryption (SME) control
3157 Refer to Documentation/virt/kvm/x86/amd-memory-encryption.rst
3161 s2idle - Suspend-To-Idle
3162 shallow - Power-On Suspend or equivalent (if supported)
3163 deep - Suspend-To-RAM or equivalent (if supported)
3164 See Documentation/admin-guide/pm/sleep-states.rst.
3167 See Documentation/admin-guide/media/meye.rst.
3169 mfgpt_irq= [IA-32] Specify the IRQ to use for the
3170 Multi-Function General Purpose Timers on AMD Geode
3173 mfgptfix [X86-32] Fix MFGPT timers on AMD Geode platforms when
3180 min_addr=nn[KMG] [KNL,BOOT,IA-64] All physical memory below this
3187 0 - The attached screen is the 3.5" TFT
3188 1 - The attached screen is the 7" TFT
3189 2 - The VGA Shield is attached (1024x768)
3193 b - Enable backlight. The TFT backlight pin will be
3197 c - Enable the s3c camera interface.
3198 t - Reserved for enabling touchscreen support. The
3202 https://repo.or.cz/w/linux-2.6/mini2440.git
3207 arch-independent options, each of which is an
3208 aggregation of existing arch-specific options.
3221 ssbd=force-off [ARM64]
3243 have other ways of avoiding SMT-based attacks.
3265 [X86,INTEL] Control mitigation for the Processor
3268 Processor MMIO Stale Data is a class of
3278 full - Enable mitigation on vulnerable CPUs
3280 full,nosmt - Enable mitigation and disable SMT on
3283 off - Unconditionally disable mitigation
3296 Documentation/admin-guide/hw-vuln/processor_mmio_stale_data.rst
3313 module_blacklist= [KNL] Do not load a comma-separated list of
3327 movablecore= [KNL,X86,IA-64,PPC]
3338 movable_node [KNL] Boot-time switch to make hotplugable memory
3345 Format: <name>,<region-number>,<size>,<offset>
3348 <name>,<region-number>[,<base>,<size>,<buswidth>,<altbuswidth>]
3356 See arch/arm/mach-s3c/mach-jive.c
3388 something different and driver-specific.
3404 See Documentation/admin-guide/nfs/nfsroot.rst.
3406 nfsroot= [NFS] nfs root filesystem for disk-less boxes.
3407 See Documentation/admin-guide/nfs/nfsroot.rst.
3410 See Documentation/admin-guide/nfs/nfsroot.rst.
3434 [NFS] enable 64-bit inode numbers.
3435 If zero, the NFS client will fake up a 32-bit inode
3437 of returning the full 64-bit number.
3438 The default is to return 64-bit inode numbers.
3468 [NFS4] Specify an additional fixed unique ident-
3499 driver. A non-zero value sets the minimum interval
3504 server-to-server copies for which this server is
3509 server-to-server copy, knfsd temporarily mounts
3525 NMI stack-backtrace request.
3534 0 - turn hardlockup detector in nmi_watchdog off
3535 1 - turn hardlockup detector in nmi_watchdog on
3547 no387 [BUGS=X86-32] Tells the kernel to use the 387 maths
3551 no5lvl [X86-64] Disable 5-level paging mode. Forces
3552 kernel to use 4-level paging instead.
3583 caches in the slab allocator. Saves per-node memory,
3602 no_entry_flush [PPC] Don't flush the L1-D cache when entering the kernel.
3604 noexec [IA-64]
3608 even if it is supported by processor.
3612 even if it is supported by processor.
3614 noexec32 [X86-64]
3615 This affects only 32-bit executables.
3616 noexec32=on: enable non-executable mappings (default)
3618 noexec32=off: disable non-executable mappings
3623 nofxsr [BUGS=X86-32] Disables x86 floating point extended
3625 legacy floating-point registers on task switch.
3647 nospectre_bhb [ARM64] Disable all mitigations for Spectre-BHB (branch
3655 [PPC] Don't flush the L1-D cache after accessing user data.
3659 enabling legacy floating-point and sse state.
3689 nohalt [IA-64] Tells the kernel not to use the power saving
3691 power-consumption. On the positive side, it reduces
3692 interrupt wake-up latency, which may improve performance
3694 real-time systems.
3704 compared. However, if this command-line option is
3731 noirqdebug [X86-32] Disables the code which attempts to detect and
3742 nointremap [X86-64, Intel-IOMMU] Do not enable interrupt
3744 [Deprecated - use intremap=off]
3746 nointroute [IA-64]
3750 nojitter [IA-64] Disables jitter checking for ITC timers.
3752 no-kvmclock [X86,KVM] Disable paravirtualized KVM clock driver
3754 no-kvmapf [X86,KVM] Disable paravirtualized asynchronous page
3757 no-vmw-sched-clock
3761 no-steal-acc [X86,PV_OPS,ARM64,PPC/PSERIES] Disable paravirtualized
3765 nolapic [X86-32,APIC] Do not enable or use the local APIC.
3767 nolapic_timer [X86-32,APIC] Do not use the local APIC timer.
3769 nomca [IA-64] Disable machine check abort handling
3771 nomce [X86-32] Disable Machine Check Exception
3773 nomfgpt [X86-32] Disable Multi-Function General Purpose
3781 display-mode changes or accelerated rendering. Only the
3783 set-up by the firmware or boot loader.
3792 nopcid [X86-64] Disable the PCID cpu feature.
3797 noreplace-smp [X86-32,SMP] Don't replace SMP instructions
3803 no-scroll [VGA] Disables scrollback.
3804 This is required for the Braillex ib80-piezo Braille
3807 nosbagart [IA-64]
3809 nosgx [X86-64,SGX] Disables Intel SGX kernel support.
3814 nosoftlockup [KNL] Disable the soft-lockup detector.
3819 soft-lockup and NMI watchdog (hard-lockup).
3823 nox2apic [X86-64,APIC] Do not enable x2APIC mode.
3838 nptcg= [IA-64] Override max number of concurrent global TLB
3847 n. So during boot up some boot time memory for per-cpu
3848 variables need be pre-allocated for later physical cpu
3863 See Documentation/admin-guide/sysctl/vm.rst for details.
3866 See Documentation/core-api/debugging-via-ohci1394.rst for more
3881 onenand.bdry= [HW,MTD] Flex-OneNAND Boundary Configuration
3885 boundary - index of last SLC block on Flex-OneNAND.
3887 lock - Configure if Flex-OneNAND boundary should be locked.
3901 running on a platform with a direct-mapped memory-side
3907 page_owner= [KNL] Boot-time page_owner enabling option.
3913 page_poison= [KNL] Boot-time parameter changing the state of
3923 reporting is disabled when it exceeds (MAX_ORDER-1).
3954 See Documentation/admin-guide/tainted-kernels.rst for
3992 Set to non-zero to probe primary and secondary ISA
3998 Set to non-zero if a chip is present that snoops speed
4046 Set to non-zero to probe tertiary and further ISA
4062 Set to non-zero to probe QDI controllers. By default
4067 Set to non-zero to probe Winbond controllers. Use
4089 See also Documentation/admin-guide/blockdev/paride.rst.
4118 bios [X86-32] force use of PCI BIOS, don't access
4120 has a non-standard PCI host bridge.
4121 nobios [X86-32] disallow use of PCI BIOS, only direct
4127 data in IO port 0xCFC, both 32-bit).
4129 Mechanism 2 (IO port 0xCF8 is an 8-bit port for
4130 the function, IO port 0xCFA, also 8-bit, sets
4132 through ports 0xC000-0xCFFF).
4139 root domains (aka PCI segments, in ACPI-speak).
4147 disable the use of MSI interrupts system-wide.
4152 primary IO-APIC for bridges that cannot disable
4159 biosirq [X86-32] Use PCI BIOS calls to get the interrupt
4183 F0000h-100000h range.
4188 assign-busses [X86] Always assign all PCI bus
4209 <linux-pci@vger.kernel.org>.
4213 a bug to <linux-pci@vger.kernel.org>.
4225 bfsort Sort PCI devices into breadth-first order.
4228 nobfsort Don't sort PCI devices into breadth-first order.
4230 tuning and use the BIOS-configured MPS defaults.
4240 configuration allows peer-to-peer DMA between
4243 that hot-added devices will work.
4258 A PCI-PCI bridge can be specified if resource
4264 for 4096-byte alignment.
4266 end-to-end CRC checking).
4295 noats [PCIE, Intel-IOMMU, AMD-IOMMU]
4331 dpc-native Use native PCIe service for DPC only. May
4348 Keep all power-domains already enabled by bootloader on,
4354 See Documentation/admin-guide/blockdev/paride.rst.
4369 See Documentation/admin-guide/blockdev/paride.rst.
4372 See Documentation/admin-guide/blockdev/paride.rst.
4374 pirq= [SMP,APIC] Manual mp-table setup
4375 See Documentation/x86/i386/IO-APIC.rst.
4379 See also Documentation/admin-guide/parport.rst.
4398 CONFIG_PNP_DEBUG_MESSAGES option). Change at run-time
4407 { on | off | curr | res | no-curr | no-res }
4447 none - Limited to cond_resched() calls
4448 voluntary - Limited to cond_resched() and might_sleep() calls
4449 full - Any section that isn't explicitly preempt disabled
4452 print-fatal-signals=
4458 coredump - etc.
4461 you might want to try "ulimit -i unlimited".
4473 or lockdep-detected issues (only if lock debug is on).
4482 on - unlimited logging to /dev/kmsg from userspace
4483 off - logging to /dev/kmsg disabled
4484 ratelimit - ratelimit the logging
4490 processor.max_cstate= [HW,ACPI]
4491 Limit processor to maximum C-state
4494 processor.nocst [HW,ACPI]
4495 Ignore the _CST method to determine C-states,
4502 Param: "schedule" - profile schedule points.
4503 Param: "sleep" - profile D-state sleeping (millisecs).
4505 Param: "kvm" - profile VM exits.
4506 Param: <number> - step/bucket size as a power of 2 for
4536 See Documentation/admin-guide/blockdev/paride.rst.
4538 pti= [X86-64] Control Page Table Isolation of user and
4543 on - unconditionally enable
4544 off - unconditionally disable
4545 auto - kernel detects whether your CPU model is
4550 nopti [X86-64]
4554 [KNL] Number of legacy pty's. Overwrites compiled-in
4562 See Documentation/admin-guide/md.rst.
4565 See Documentation/admin-guide/blockdev/ramdisk.rst.
4586 cross-syscall address exposures. This is only
4592 ras=option[,option,...] [KNL] RAS-specific options
4598 rcu_nocbs[=cpu-list]
4603 enable the no-callback CPU mode, which prevents
4608 "p" for RCU-preempt, "s" for RCU-sched, and "g"
4612 and real-time workloads. It can also improve
4616 list of CPUs is set to no-callback mode from boot.
4620 no-callback mode from boot but the mode may be
4631 This improves the real-time response for the
4648 RCU grace-period cleanup.
4652 RCU grace-period initialization.
4656 RCU grace-period pre-initialization, that is,
4657 the propagation of recent CPU-hotplug changes up
4662 per-CPU rcuc kthreads. Defaults to a non-zero
4674 cache-to-cache transfer latencies.
4680 and for NUMA systems with large remote-access
4693 Set the page-cache refill delay (in milliseconds)
4694 in response to low-memory conditions. The range
4698 Set delay from grace-period initialization to
4711 soliciting quiescent-state help from
4723 Set the SCHED_FIFO priority of the RCU per-CPU
4726 and for the RCU grace-period kthreads (rcu_bh,
4728 set, valid values are 1-99 and the default is 1
4729 (the least-favored priority). Otherwise, when
4730 RCU_BOOST is not set, valid values are 0-99 and
4731 the default is zero (non-realtime operation).
4736 Set the shift-right count to use to compute
4737 the callback-invocation batch limit bl from
4744 Please note that this callback-invocation batch
4745 limit applies only to non-offloaded callback
4751 On callback-offloaded (rcu_nocbs) CPUs,
4754 use of the ->nocb_bypass list. However, in the
4755 common non-flooded case, RCU queues directly to
4756 the main ->cblist in order to avoid the extra
4757 overhead of the ->nocb_bypass list and its lock.
4759 a single jiffy, RCU pre-queues the callbacks into
4760 the ->nocb_bypass queue. The definition of "too
4767 the wakeup overhead on the global grace-period
4769 each group's NOCB grace-period kthread.
4777 batch limiting is re-enabled.
4781 RCU's force-quiescent-state scan will aggressively
4789 Cause the grace-period kthread to get an extra
4791 it should at force-quiescent-state time.
4797 this specifies an rcu_read_unlock()-time delay
4801 of RCU-protected pointers after the relevant
4811 grace-period primitives such as call_rcu().
4822 grace-period primitives.
4825 Set test-start holdoff period. The purpose of
4834 Test the double-argument variant of kfree_rcu().
4836 rcuscale.kfree_rcu_test_single, both the single-
4837 and double-argument variants are tested.
4840 Test the single-argument variant of kfree_rcu().
4842 rcuscale.kfree_rcu_test_double, both the single-
4843 and double-argument variants are tested.
4856 Set number of RCU readers. The value -1 selects
4858 "n" less than -1 selects N-n+1, where N is again
4859 the number of CPUs. For example, -2 selects N
4860 (the number of CPUs), -3 selects N+1, and so on.
4861 A value of "n" less than or equal to -N selects
4874 complete. This is useful for hands-off automated
4881 Write-side holdoff between grace periods,
4899 for RCU grace-period forward-progress testing
4906 Specify the fraction of a CPU-stall-warning
4907 period to do tight-loop forward-progress testing.
4911 forward-progress tests.
4915 need_resched() during tight-loop forward-progress
4919 Use conditional/asynchronous update-side
4923 Use expedited update-side primitives, if available.
4926 Use normal (non-expedited) asynchronous
4927 update-side primitives, if available.
4930 Use normal (non-expedited) synchronous
4931 update-side primitives, if available. If all
4935 they are all non-zero.
4943 Leak an RCU-protected pointer out of the reader.
4958 Set number of RCU callback-offload togglers.
4963 callback-offload toggling attempts.
4966 Set number of RCU readers. The value -1 selects
4967 N-1, where N is the number of CPUs. A value
4968 "n" less than -1 selects N-n-2, where N is again
4969 the number of CPUs. For example, -2 selects N
4970 (the number of CPUs), -3 selects N+1, and so on.
4973 Enable debug-object double-call_rcu() testing.
4976 Set time (s) after boot for CPU-hotplug testing.
4979 Set time (jiffies) between CPU-hotplug operations,
4980 or zero to disable CPU-hotplug testing.
4983 Set the number of read-then-exit kthreads used
4985 task-exit processing.
4988 The number of times in a given read-then-exit
4989 episode that a set of read-then-exit kthreads
4994 read-then-exit testing episodes.
4997 Set task-shuffle interval (s). Shuffling tasks
4998 allows some CPUs to go into dyntick-idle mode
5003 is useful for hands-off automated testing.
5012 to any other stall-related activity.
5022 grace-period kthread to test RCU CPU stall
5048 Test RCU's dyntick-idle handling. See also the
5086 Use expedited grace-period primitives, for
5090 real-time latency, and degrade energy efficiency.
5094 Use only normal grace-period primitives,
5097 real-time latency, CPU utilization, and
5099 increased grace-period latency. This parameter
5106 only normal grace-period primitives. No effect
5112 post-boot attempt at an expedited RCU grace
5113 period to instead use normal non-expedited
5114 grace-period processing.
5122 set to the default value of -1.
5125 Set the minimum number of callback-queuing-time
5126 lock-contention events per jiffy required to
5127 cause the RCU Tasks flavors to switch to per-CPU
5130 the default value of -1.
5135 of -1 allows this to be automatically (and
5143 number avoids disturbing real-time workloads,
5151 only printed prior to the stall-warning message
5184 force - Override the decision by the kernel to hide the
5208 reboot_cpu is s[mp]#### with #### being the processor
5212 Set test-start holdoff period. The purpose of
5221 but the default has already reduced the per-pass
5226 Set number of readers. The default value of -1
5235 Set the read-side critical-section duration,
5239 Specify the read-protection implementation to test.
5258 See Documentation/admin-guide/cgroup-v1/cpusets.rst.
5266 reservetop= [X86-32]
5283 See Documentation/power/swsusp-and-swap-files.rst
5298 AMD-based UNRET and IBPB mitigations alone do not stop
5300 sibling threads. For that reason, STIBP is used on pro-
5304 off - no mitigation
5305 auto - automatically select a migitation
5306 auto,nosmt - automatically select a mitigation,
5310 ibpb - On AMD, mitigate short speculation
5315 ibpb,nosmt - Like "ibpb" above but will disable SMT
5319 unret - Force enable untrained return thunks,
5320 only effective on AMD f15h-f17h based
5322 unret,nosmt - Like unret, but will disable SMT when STIBP
5350 ro [KNL] Mount root device read-only on boot
5353 on Mark read-only kernel memory as read-only (default).
5354 off Leave read-only kernel memory writable for debugging.
5355 full Mark read-only kernel memory and aliases as read-only
5361 debug-uart get routed to the D+ and D- pins of the usb
5380 Memory area to be used by remote processor image,
5383 rw [KNL] Mount root device read-write on boot
5435 to 10 seconds for built-in smp_call_function()
5442 that requesting even small non-zero numbers of
5449 The default of -1 specifies a number of kthreads
5454 test before initiating CPU-hotplug operations.
5458 CPU-hotplug operations. Specifying zero (which
5459 is the default) disables CPU-hotplug operations.
5465 Non-zero values are useful for automated tests.
5488 "wait" parameter. A value of -1 selects the
5489 default if all other weights are -1. However,
5491 value of -1 will instead select a weight of zero.
5496 non-zero "wait" parameter. See weight_single.
5509 non-zero "wait" parameter. See weight_single
5521 non-zero "wait" parameter. See weight_single
5528 0 -- disable. (may be 1 via CONFIG_CMDLINE="skew_tick=1"
5529 1 -- enable.
5540 0 -- disable.
5541 1 -- enable.
5547 0 -- disable.
5548 1 -- enable.
5551 serialnumber [BUGS=X86-32]
5553 sev=option[,option...] [X86-64] See Documentation/x86/x86_64/boot-options.rst
5558 simeth= [IA-64]
5633 using the csdlock_debug- kernel parameter.
5635 smsc-ircc2.nopnp [HW] Don't use PNP to discover SMC devices
5636 smsc-ircc2.ircc_cfg= [HW] Device configuration I/O port
5637 smsc-ircc2.ircc_sir= [HW] SIR base I/O port
5638 smsc-ircc2.ircc_fir= [HW] FIR base I/O port
5639 smsc-ircc2.ircc_irq= [HW] IRQ line
5640 smsc-ircc2.ircc_dma= [HW] DMA channel
5641 smsc-ircc2.ircc_transceiver= [HW] Transceiver type:
5651 Default: -1 (no limit)
5654 [KNL] Should the soft-lockup detector generate panics.
5657 A value of 1 instructs the soft-lockup detector
5658 to panic the machine when a soft-lockup occurs. It is
5661 respective build-time switch to that functionality.
5664 [KNL] Should the soft-lockup detector generate
5669 See Documentation/admin-guide/laptops/sonypi.rst
5676 on - unconditionally enable, implies
5678 off - unconditionally disable, implies
5680 auto - kernel detects whether your CPU model is
5697 retpoline - replace indirect branches
5698 retpoline,generic - Retpolines
5699 retpoline,lfence - LFENCE; indirect branch
5700 retpoline,amd - alias for retpoline,lfence
5701 eibrs - enhanced IBRS
5702 eibrs,retpoline - enhanced IBRS + Retpolines
5703 eibrs,lfence - enhanced IBRS + LFENCE
5704 ibrs - use IBRS to protect kernel
5714 on - Unconditionally enable mitigations. Is
5717 off - Unconditionally disable mitigations. Is
5720 prctl - Indirect branch speculation is enabled,
5726 - Like "prctl" above, but only STIBP is
5732 - Same as "prctl" above, but all seccomp
5737 - Like "seccomp" above, but only STIBP is
5742 auto - Kernel selects the mitigation depending on
5773 on - Unconditionally disable Speculative Store Bypass
5774 off - Unconditionally enable Speculative Store Bypass
5775 auto - Kernel detects whether the CPU model contains an
5781 prctl - Control Speculative Store Bypass per thread
5785 seccomp - Same as "prctl" above, but all seccomp threads
5793 on,auto - On Power8 and Power9 insert a store-forwarding
5797 off - No action.
5816 off - not enabled
5818 warn - the kernel will emit rate-limited warnings
5826 fatal - the kernel will send SIGBUS to applications
5831 ratelimit:N -
5851 Certain CPUs are vulnerable to an MDS-like
5871 This kernel-boot parameter defaults to 128,
5872 but takes effect only when the low-order four
5889 instead of the compile-time CONFIG_NR_CPUS.
5893 grace-period sequence counter wrap for the
5894 srcu_data structure's ->srcu_gp_seq_needed field.
5909 Specifies the number of no-delay instances
5916 Specifies the per-grace-period phase, number of
5917 non-sleeping polls of readers. Beyond this limit,
5923 Specifies number of microseconds of non-sleeping
5924 delay between each non-sleeping poll of readers.
5927 Specifies the number of update-side contention
5932 set for contention-based conversions to occur.
5942 force-on: Unconditionally enable mitigation for
5944 force-off: Unconditionally disable mitigation for
5967 stacktrace_filter=[function-list]
5969 will trace at boot up. function-list is a comma-separated
5977 Set the STI (builtin display/keyboard on the HP-PARISC
5979 as the initial boot-console.
6029 to global on non-NUMA machines)
6052 swiotlb= [ARM,IA-64,PPC,MIPS,X86]
6054 <int> -- Number of I/O TLB slabs
6055 <int> -- Second integer after comma. Number of swiotlb
6058 force -- force using of bounce buffers even if they
6060 noforce -- Never use bounce buffers (for debugging)
6084 Ignore sysrq setting - this boot parameter will
6092 cache size. See Documentation/networking/ip-sysctl.rst
6099 Specify "mem" (for Suspend-to-RAM) or "standby" (for
6104 wakeup-capable RTC alarm.
6110 -1: disable all active trip points in all thermal zones
6114 -1: disable all critical trip points in all thermal zones
6125 -1: disable all passive trip points
6131 <deci-seconds>: poll all this frequency
6153 Prevent the CPU-hotplug component of torturing
6157 Dump the ftrace buffer at torture-test shutdown,
6161 with rotating-rust storage.
6166 disables verbose-printk() sleeping.
6169 Duration of each verbose-printk() sleep in jiffies.
6218 local - Use the per CPU time stamp counter
6222 global - Event time stamps are synchronize across
6225 counter - Simple counting of events (1, 2, ..)
6229 uptime - Use jiffies as the time stamp.
6230 perf - Use the same clock that perf uses.
6231 mono - Use ktime_get_mono_fast_ns() for time stamps.
6232 mono_raw - Use ktime_get_raw_fast_ns() for time
6234 boot - Use ktime_get_boot_fast_ns() for time stamps.
6238 trace_event=[event-list]
6240 to facilitate early boot debugging. The event-list is a
6241 comma-separated list of trace events to enable. See
6244 trace_options=[option-list]
6246 The option-list is a comma delimited list of options
6278 See Documentation/admin-guide/mm/transhuge.rst
6286 - "tpm"
6287 - "tee"
6288 - "caam"
6298 - "kernel"
6299 - the same value as trusted.source: "tpm" or "tee"
6300 - "default"
6309 high-resolution timer mode on older hardware, and in
6335 on - Enable TSX on the system. Although there are
6338 several previous speculation-related CVEs, and
6342 off - Disable TSX on the system. (Note that this
6350 auto - Disable TSX if X86_BUG_TAA is present,
6355 See Documentation/admin-guide/hw-vuln/tsx_async_abort.rst
6361 Similar to Micro-architectural Data Sampling (MDS)
6376 full - Enable TAA mitigation on vulnerable CPUs
6379 full,nosmt - Enable TAA mitigation and disable SMT on
6382 vulnerable to cross-thread TAA attacks.
6383 off - Unconditionally disable TAA mitigation
6385 On MDS-affected machines, tsx_async_abort=off can be
6397 Documentation/admin-guide/hw-vuln/tsx_async_abort.rst
6403 See also Documentation/input/devices/joystick-parport.rst
6405 udbg-immortal [PPC] When debugging early kernel crashes that
6411 Set number of hash buckets for UDP/UDP-Lite connections
6413 uhci-hcd.ignore_oc=
6415 Some badly-designed motherboards generate lots of
6426 (default -1 = authorized except for wireless USB,
6432 for newly-detected USB devices (default 2). This
6460 [USB] Specifies timeout for the initial 64-byte
6467 [USB] A list of quirk entries to augment the built-in
6470 VendorID:ProductID:Flags. The IDs are 4-digit hex
6472 will change the built-in quirk; setting it if it is
6477 a 255-byte read);
6481 Set-Interface requests);
6500 (bInterval-1).
6535 usb-storage.delay_use=
6539 usb-storage.quirks=
6541 override the built-in unusual_devs list. List
6544 and Product ID values (4-digit hex numbers) and
6546 to a common usb-storage quirk flag as follows:
6588 medium is write-protected).
6597 1 - undefined instruction events
6598 2 - system calls
6599 4 - invalid data aborts
6600 8 - SIGSEGV faults
6601 16 - SIGBUS faults
6617 vdso32= [X86] Control the 32-bit vDSO
6618 vdso32=1: enable 32-bit VDSO
6619 vdso32=0 or vdso32=2: disable 32-bit VDSO
6629 dl_main: Assertion `(void *) ph->p_vaddr == _rtld_local._dl_sysinfo_dso' failed!
6631 vector= [IA-64,SMP]
6663 vga= [BOOT,X86-32] Select a particular video mode
6665 Documentation/admin-guide/svga.rst.
6680 - Disable all of the above options
6701 vsyscall= [X86-64]
6704 code). Most statically-linked binaries and older
6728 see VGA-softcursor.txt. Default: 2 = underline.
6733 This is a 16-member array composed of values
6734 ranging from 0-255.
6739 This is a 16-member array composed of values
6740 ranging from 0-255.
6745 This is a 16-member array composed of values
6746 ranging from 0-255.
6751 Set system-wide default UTF-8 mode for all tty's.
6752 Default is 1, i.e. UTF-8 mode is enabled for all
6757 Format=<-1|0|1>
6758 Set system-wide default for whether a cursor
6759 is shown on new VTs. Default is -1,
6764 vt.italic= [VT] Default color for italic text; 0-15.
6767 vt.underline= [VT] Default color for underlined text; 0-15.
6771 see Documentation/watchdog/watchdog-parameters.rst
6772 or other driver-specific files in the
6798 that this also can be controlled per-workqueue for
6802 Per-cpu workqueues are generally preferred because
6804 locality; unfortunately, per-cpu workqueues tend to
6807 Enabling this makes the per-cpu workqueues which
6822 forces round-robin CPU selection to flush out
6827 x2apic_phys [X86-64,APIC] Use x2apic physical mode instead of
6831 xen_512gb_limit [KNL,X86-64,XEN]
6841 ide-disks -- unplug primary master IDE devices
6842 aux-ide-disks -- unplug non-primary-master IDE devices
6843 nics -- unplug network devices
6844 all -- unplug all emulated devices (NICs and IDE disks)
6845 unnecessary -- unplugging emulated devices is
6848 never -- do not unplug even if version check succeeds
6856 Select whether to always use non-faulting (safe) MSR
6881 xen_timer_slop= [X86-64,XEN]
6906 preferred over the 2-level event handling, as it is
6933 xive.store-eoi=off [PPC]
6939 xhci-hcd.quirks [USB,KNL]