Lines Matching +full:sata +full:- +full:cold
16 force -- enable ACPI if default was off
17 on -- enable ACPI but allow fallback to DT [arm64,riscv64]
18 off -- disable ACPI if default was on
19 noirq -- do not use ACPI for IRQ routing
20 strict -- Be less tolerant of platforms that are not
22 rsdt -- prefer RSDT over (default) XSDT
23 copy_dsdt -- copy DSDT to memory
24 nospcr -- disable console in ACPI SPCR table as
41 If set to vendor, prefer vendor-specific driver
73 Documentation/firmware-guide/acpi/debug.rst for more information about
131 Format: <byte> or <bitmap-list>
134 Disable auto-serialization of AML methods
137 auto-serialization feature.
155 Ignore the ACPI-based watchdog interface (WDAT) and let
169 be necessary to carry out a cold reboot _twice_ in a
176 acpi_osi=! # disable all built-in OS vendor
178 acpi_osi=!! # enable all built-in OS vendor
240 For broken nForce2 BIOS resulting in XT-PIC timer.
249 as soon as the kernel's real-mode entry point is called.
287 See Documentation/sound/alsa-configuration.rst
294 align_va_addr= [X86-64]
299 CPU-intensive style benchmark, and it can vary highly in
302 32: only for 32-bit processes
303 64: only for 64-bit processes
304 on: enable for both 32- and 64-bit processes
305 off: disable for both 32- and 64-bit processes
315 Allow execve() of 32-bit applications and setting of the
317 subset of the CPUs support 32-bit EL0. When this
318 parameter is present, the set of CPUs supporting 32-bit
320 and hot-unplug operations may be restricted.
322 See Documentation/arch/arm64/asymmetric-32bit.rst for more
325 amd_iommu= [HW,X86-64]
328 fullflush - Deprecated, equivalent to iommu.strict=1
329 off - do not initialize any AMD IOMMU found in
331 force_isolation - Force device isolation for all
336 force_enable - Force enable the IOMMU on platforms known
339 pgtbl_v1 - Use v1 page table for DMA-API (Default).
340 pgtbl_v2 - Use v2 page table for DMA-API.
341 irtcachedis - Disable Interrupt Remapping Table (IRT) caching.
342 nohugepages - Limit page-sizes used for v1 page-tables
344 v2_pgsizes_only - Limit page-sizes used for v1 page-tables
348 amd_iommu_dump= [HW,X86-64]
354 amd_iommu_intr= [HW,X86-64]
357 legacy - Use legacy interrupt remapping mode.
358 vapic - Use virtual APIC mode, which allows IOMMU
360 This mode requires kvm-amd.avic=1.
389 Disable amd-pstate preferred core.
402 Power management functions (SPARCstation-4/5 + deriv.)
404 Disable APC CPU standby support. SPARCstation-Fox does
405 not play well with APC CPU idle - disable it if you have
412 when initialising the APIC and IO-APIC components.
413 For X86-32, this can also be used to specify an APIC
436 0 -- disable.
437 1 -- enable.
440 arcrimi= [HW,NET] ARCnet - "RIM I" (entirely mem-mapped) cards
488 audit= [KNL] Enable the audit sub-system
490 0 | off - kernel audit is disabled and can not be
492 unset - kernel audit is initialized but disabled and
494 1 | on - kernel audit is initialized and partially
507 0 - Disable the BAU.
508 1 - Enable the BAU.
509 unset - Disable the BAU.
548 See Documentation/block/cmdline-partition.rst
562 See Documentation/admin-guide/bootconfig.rst
567 bttv.pll= See Documentation/admin-guide/media/bttv.rst
576 cachesize= [BUGS=X86-32] Override level 2 CPU cache size detection.
595 inclusive. See arch/mips/include/asm/pgtable-bits.h
605 - foo isn't auto-mounted if you mount all cgroups in
607 - foo isn't visible as an individually mountable
609 - if foo is an optional feature then the feature is
615 Specifying "pressure" disables per-cgroup pressure
633 nosocket -- Disable socket memory accounting.
634 nokmem -- Disable kernel memory accounting.
635 nobpf -- Disable BPF memory accounting.
640 0 -- check protection applied by kernel (includes
642 1 -- check protection requested by application.
654 numbers X. Note the Linux-specific bits are not necessarily
655 stable over kernel options, but the vendor-specific
675 force such clocks to be always-on nor does it reserve
679 information, see Documentation/driver-api/clk.rst.
681 clock= [BUGS=X86-32, HW] gettimeofday clocksource override.
698 [X86-32] pit,hpet,tsc;
705 [X86-64] hpet,tsc
711 architected timer so that code using WFE-based polling
725 clocksource-wdtest.holdoff= [KNL]
731 cma=nn[MG]@[start[MG][-end[MG]]]
742 Sets the size of kernel per-numa memory area for
744 per-numa CMA altogether. And If this option is not
746 With per-numa CMA enabled, DMA users on node nid will
773 com20020= [HW,NET] ARCnet - COM20020 chipset
777 com90io= [HW,NET] ARCnet - COM90xx chipset (IO-mapped buffers)
781 ARCnet - COM90xx chipset (memory-mapped buffers)
810 See Documentation/admin-guide/serial-console.rst for more
825 $ ls -d /sys/bus/serial-base/devices/*:*.*/tty/*
826 /sys/bus/serial-base/devices/00:04:0.0/tty/ttyS0
839 Start an early, polled-mode console on the 8250/16550
842 MMIO inter-register address stride is either 8-bit
843 (mmio), 16-bit (mmio16), or 32-bit (mmio32).
847 the h/w is not re-initialized.
874 syscall, or to executing "dmesg -S --raw" or to reading
898 disable the cpuidle sub-system
904 disable the cpufreq sub-system
912 [X86,EARLY] Delay for N microsec between assert and de-assert
933 like Hyper-V, PowerPC (fadump) and AMD SEV-SNP.
941 [KNL, X86-64, ARM64, RISCV, LoongArch] Select a region
944 See Documentation/admin-guide/kdump/kdump.rst for further details.
949 start-[end] where start and end are both
951 Documentation/admin-guide/kdump/kdump.rst for an example.
954 [KNL, X86-64, ARM64, RISCV, LoongArch] range could be
962 [KNL, X86-64, ARM64, RISCV, LoongArch] range under 4G.
968 for 32-bit devices won't run out. Kernel would try to allocate
971 --> x86: max(swiotlb_size_or_default() + 8MiB, 256MiB)
972 --> arm64: 128MiB
973 --> riscv: 128MiB
974 --> loongarch: 128MiB
982 [KNL] Disable crypto self-tests
990 csdlock_debug= [KNL] Enable or disable debug add-ons of cross-CPU
1005 See also Documentation/input/devices/joystick-parport.rst
1018 [KNL] verbose locking self-tests
1021 self-tests.
1023 (no extra messages), setting it to -1 (all bits set)
1024 will print _a_lot_ more information - normally only
1059 Format: { on, no-mount, off }
1061 no-mount:
1066 get a -EPERM as result when trying to register files
1070 Default value is set in build-time with a kernel configuration.
1082 Documentation/admin-guide/mm/hugetlbpage.rst.
1096 delayacct [KNL] Enable per-task delay accounting
1182 entries for DMA-API debugging code. One entry is
1183 required per DMA-API allocation. Use this if the
1184 DMA-API debugging code disables itself because the
1188 With this option the DMA-API debugging driver
1212 Documentation/admin-guide/hw-vuln/reg-file-data-sampling.rst
1237 Control how the dt_cpu_ftrs device-tree binding is
1247 what data is available or for reverse-engineering.
1252 Documentation/admin-guide/dynamic-debug-howto.rst
1263 determined by stdout-path property in device tree's
1268 Start an early, polled-mode console on a Cadence
1279 Start an early, polled-mode console on the 8250/16550
1281 MMIO inter-register address stride is either 8-bit
1282 (mmio) or 32-bit (mmio32 or mmio32be).
1292 Start an early, polled-mode console on a pl011 serial
1296 the driver will use only 32-bit accessors to read/write
1305 Start an early, polled-mode console on a meson serial
1311 Start an early, polled-mode console on an msm serial
1317 Start an early, polled-mode console on an msm serial
1323 Start an early, polled-mode console on a serial port
1329 Start an early, polled-mode console on a serial port
1335 Use RISC-V SBI (Supervisor Binary Interface) for early
1353 Start an early, polled-mode console on a lantiq serial
1367 Start an early, polled-mode, output-only console on the
1372 Start an early, polled-mode console on the
1378 Start an early, polled-mode console on a Qualcomm
1386 coherent non-x86 systems that use system memory for
1485 Documentation/admin-guide/acpi/ssdt-overlays.rst for details.
1502 elanfreq= [X86-32]
1510 See Documentation/admin-guide/kdump/kdump.rst for details.
1526 0 -- permissive (log only, no denials).
1527 1 -- enforcing (deny and log).
1560 See also Documentation/fault-injection/.
1564 See Documentation/admin-guide/sysctl/net.rst for
1568 See Documentation/admin-guide/blockdev/floppy.rst.
1570 forcepae [X86-32]
1577 fred= [X86-64]
1628 ftrace_filter=[function-list]
1630 tracer at boot up. function-list is a comma-separated
1635 ftrace_notrace=[function-list]
1637 function-list. This list can be changed at run time
1641 ftrace_graph_filter=[function-list]
1644 function-list is a comma-separated list of functions
1648 ftrace_graph_notrace=[function-list]
1650 function-list. This list is a comma-separated list of
1670 off -- Don't create device links from firmware info.
1671 permissive -- Create device links from firmware info
1674 on -- Create device links from firmware info and use it
1676 rpm -- Like "on", but also use to order runtime PM.
1689 strict -- Default. Continue waiting on consumers to
1691 timeout -- Give up waiting on consumers and call
1701 See also Documentation/input/devices/joystick-parport.rst
1705 gart_fix_e820= [X86-64,EARLY] disable the fix e820 for K8 GART
1729 gcov_persist= [GCOV] When non-zero (default), profiling data for
1739 gpio-mockup.gpio_mockup_ranges
1742 gpio-mockup.gpio_mockup_named_lines
1774 against bounds-checking flaws in the kernel's
1780 [KNL] Should the hard-lockup detector generate
1786 for 64-bit NUMA, off otherwise.
1794 corresponding firmware-first mode error processing
1804 during restoration read-only).
1841 hpet= [X86-32,HPET] option to control HPET usage
1858 number of pages to allocate per-node can be specified.
1859 See also Documentation/admin-guide/mm/hugetlbpage.rst.
1870 Documentation/admin-guide/mm/hugetlbpage.rst.
1881 boot-time allocation of gigantic hugepages is skipped.
1909 by the CONFIG_BOOTPARAM_HUNG_TASK_PANIC build-time
1915 hvc_iucv_allow= [S390] Comma-separated list of z/VM user IDs.
1931 Set device-properties for ACPI-enumerated I2C-attached
1932 touchscreen, to e.g. fix coordinates of upside-down
1940 Omit "=<val>" entirely Set a boolean device-property
1941 Unsigned number Set a u32 device-property
1942 Anything else Set a string device-property
1945 i2c_touchscreen_props=GDIX1001:touchscreen-inverted-x:
1946 touchscreen-inverted-y
1948 i2c_touchscreen_props=MSSL1680:touchscreen-size-x=1920:
1949 touchscreen-size-y=1080:touchscreen-inverted-y:
1950 firmware-name=gsl1680-vendor-model.fw:silead,home-button
1955 (disabled by default, and as a pre-condition
1957 i8042.direct [HW] Put keyboard port into non-translated mode
1971 suspend-to-ram transitions, only during s2r
1995 -1 -- never invert brightness
1996 0 -- machine default
1997 1 -- force brightness inversion
1999 ia32_emulation= [X86-64]
2001 When true, allows loading 32-bit programs and executing 32-bit
2017 idle=nomwait: Disable mwait for CPU C-states
2045 legacy only accept legacy-NaN binaries, if supported
2047 2008 only accept 2008-NaN binaries, if supported
2058 'relaxed' straps the emulator for both legacy-NaN and
2059 2008-NaN, whereas 'strict' enables legacy-NaN only on
2068 Ignore loglevel setting - this will print /all/
2135 Formats: { "ima" | "ima-ng" | "ima-ngv2" | "ima-sig" |
2136 "ima-sigv2" }
2137 Default: "ima-ng"
2169 initcall_blacklist= [KNL] Do not execute a comma-separated list of
2170 initcall functions. Useful for debugging built-in
2215 0 -- basic integrity auditing messages. (Default)
2216 1 -- additional integrity auditing messages.
2244 could harm performance of some high-throughput
2253 1 to 9 specify maximum depth of C-state.
2262 algorithms for p-state selection. There are two
2263 P-state selection algorithms provided by
2266 on whether or not the hardware managed P-states
2273 used along with the hardware-managed P-states (HWP)
2277 in favor of acpi-cpufreq. Forcing the intel_pstate driver
2278 instead of acpi-cpufreq may disable platform features, such
2280 P-States information being indicated to OSPM and therefore
2283 or on platforms that use pcc-cpufreq instead of acpi-cpufreq.
2296 Allow per-logical-CPU P-State performance control limits using
2299 intremap= [X86-64,Intel-IOMMU,EARLY]
2304 BIOS x2APIC opt-out request will be ignored
2330 0 - Try to allocate a 32-bit DMA address first, before
2332 1 - Allocate directly from the full usable range,
2334 greater than 32-bit addressing.
2338 0 - Lazy mode.
2344 1 - Strict mode.
2347 unset - Use value of CONFIG_IOMMU_DEFAULT_DMA_{LAZY,STRICT}.
2349 legacy driver-specific options takes precedence.
2354 0 - Use IOMMU translation for DMA.
2355 1 - Bypass the IOMMU for DMA.
2356 unset - Use value of CONFIG_IOMMU_DEFAULT_PASSTHROUGH.
2358 io7= [HW] IO7 for Marvel-based Alpha systems
2373 See Documentation/admin-guide/nfs/nfsroot.rst.
2409 Enables support for pseudo-NMIs in the kernel. This
2428 [Deprecated - use cpusets instead]
2429 Format: [flag-list,]<cpu-list>
2460 "number of CPUs in system - 1".
2486 The format of <cpu-list> is described above.
2490 ivrs_ioapic [HW,X86-64]
2491 Provide an override to the IOAPIC-ID<->DEVICE-ID
2495 For example, to map IOAPIC-ID decimal 10 to
2501 * To map IOAPIC-ID decimal 10 to PCI device 00:14.0
2504 * To map IOAPIC-ID decimal 10 to PCI segment 0x1 and
2508 ivrs_hpet [HW,X86-64]
2509 Provide an override to the HPET-ID<->DEVICE-ID
2513 For example, to map HPET-ID decimal 10 to
2519 * To map HPET-ID decimal 0 to PCI device 00:14.0
2522 * To map HPET-ID decimal 10 to PCI segment 0x1 and
2526 ivrs_acpihid [HW,X86-64]
2527 Provide an override to the ACPI-HID:UID<->DEVICE-ID
2531 For example, to map UART-HID:UID AMD0020:0 to
2537 * To map UART-HID:UID AMD0020:0 to PCI segment is 0,
2540 * To map UART-HID:UID AMD0020:0 to PCI segment 0x1 and
2564 the kernel for non-movable allocations. The requested
2574 subsystem. Note that allocations like PTEs-from-HighMem
2582 for non-movable allocations and remaining memory is used
2593 gdb or control-c on the dbgp connection. When
2594 not using this parameter you use sysrq-g to break into
2599 or a supported polling keyboard driver (non-usb).
2626 Configure the RouterBoard 532 series on-chip
2629 kmemleak= [KNL,EARLY] Boot-time kmemleak enable/disable
2635 kprobe_event=[probe-list]
2637 The probe-list is a semicolon delimited list of probe
2667 execution by eliminating the write-protection faults
2694 virtualization on-demand when creating and destroying
2702 is that doing so may interfere with using out-of-tree
2729 back to huge pages. If the value is a non-zero N, KVM will
2734 kvm-amd.nested= [KVM,AMD] Control nested virtualization feature in
2737 kvm-amd.npt= [KVM,AMD] Control KVM's use of Nested Page Tables,
2738 a.k.a. Two-Dimensional Page Tables. Default is 1
2742 kvm-arm.mode=
2748 nvhe: Standard nVHE-based mode, without support for
2751 protected: nVHE-based mode with support for guests whose
2754 nested: VHE-based mode with support for nested
2763 kvm-arm.vgic_v3_group0_trap=
2764 [KVM,ARM,EARLY] Trap guest accesses to GICv3 group-0
2767 kvm-arm.vgic_v3_group1_trap=
2768 [KVM,ARM,EARLY] Trap guest accesses to GICv3 group-1
2771 kvm-arm.vgic_v3_common_trap=
2775 kvm-arm.vgic_v4_enable=
2779 kvm-arm.wfe_trap_policy=
2788 kvm-arm.wfi_trap_policy=
2805 kvm-intel.ept= [KVM,Intel] Control KVM's use of Extended Page Tables,
2806 a.k.a. Two-Dimensional Page Tables. Default is 1
2810 kvm-intel.emulate_invalid_guest_state=
2812 state. Ignored if kvm-intel.enable_unrestricted_guest=1,
2818 kvm-intel.flexpriority=
2823 kvm-intel.nested=
2827 kvm-intel.unrestricted_guest=
2833 kvm-intel.vmentry_l1d_flush=[KVM,Intel] Mitigation for L1 Terminal Fault
2834 CVE-2018-3620.
2845 kvm-intel.vpid= [KVM,Intel] Control KVM's use of Virtual Processor
2865 on - enable the interface for the mitigation
2930 For details see: Documentation/admin-guide/hw-vuln/l1tf.rst
2936 lapic [X86-32,APIC,EARLY] Enable the local APIC even if BIOS
2940 value for LAPIC timer one-shot implementation. Default
2948 libata.dma=0 Disable all PATA and SATA DMA
2949 libata.dma=1 PATA and SATA Disk DMA only
2963 libata.force= [LIBATA] Force configurations. The format is a comma-
2975 first fan-out link behind PMP device. It does not
2984 * Cable type: 40c, 80c, short40c, unk, ign or sata.
2987 * SATA link speed limit: 1.5Gbps or 3.0Gbps.
2989 * Transfer mode: pio[0-7], mwdma[0-4] and udma[0-7].
2996 * rstonce: only attempt one reset during hot-unplug
3091 Specify the number of self-propagating call_rcu()
3099 occasional long-duration lock hold time. Defaults
3110 Set the number of locking read-acquisition kthreads.
3115 Set the number of locking write-acquisition kthreads.
3118 Set time (s) after boot for CPU-hotplug testing.
3121 Set time (s) between CPU-hotplug operations, or
3122 zero to disable CPU-hotplug testing.
3125 Do periodic testing of real-time lock priority
3130 non-real-time spinlocks, due to their disabling
3131 of preemption. Note that non-realtime mutexes
3144 Set task-shuffle interval (jiffies). Shuffling
3145 tasks allows some CPUs to go into dyntick-idle
3150 is useful for hands-off automated testing.
3169 Run the write-side locktorture kthreads at
3170 sched_set_fifo() real-time priority.
3188 7 (KERN_DEBUG) debug-level messages
3200 logo.nologo [FB] Disables display of the built-in Linux logo.
3218 an IEEE 1284-compliant printer is attached; if
3224 time-consuming boot-time autodetection (up to 250 ms per
3244 Example: machtype=lemote-yeeloong-2f-7inch
3256 (loop.max_loop) unconditionally pre-created at init time. The default
3259 devices can be requested on-demand with the
3260 /dev/loop-control interface.
3262 mce [X86-32] Machine Check Exception
3264 mce=option [X86-64] See Documentation/arch/x86/x86_64/boot-options.rst
3267 See Documentation/admin-guide/md.rst.
3274 Control mitigation for the Micro-architectural Data
3289 full - Enable MDS mitigation on vulnerable CPUs
3290 full,nosmt - Enable MDS mitigation and disable
3292 off - Unconditionally disable MDS mitigation
3294 On TAA-affected machines, mds=off can be prevented by
3303 For details see: Documentation/admin-guide/hw-vuln/mds.rst
3318 [ARC,MICROBLAZE] - the limit applies only to low memory,
3321 [ARM64] - only limits memory covered by the linear
3334 [ARM,MIPS,EARLY] - override the memory layout
3341 mem=nopentium [BUGS=X86-32] Disable usage of 4MB pages for kernel
3348 per-device physically contiguous DMA buffers.
3356 See Documentation/admin-guide/mm/memory-hotplug.rst.
3381 Example: Exclude memory from 0x18690000-0x1869ffff
3395 memmap=<size>%<offset>-<oldtype>+<newtype>
3397 from <oldtype> to <newtype>. If "-<oldtype>" is left
3412 repeatable BIOS-originated corruption always
3456 mem_encrypt= [X86-64] AMD Secure Memory Encryption (SME) control
3462 Refer to Documentation/virt/kvm/x86/amd-memory-encryption.rst
3466 s2idle - Suspend-To-Idle
3467 shallow - Power-On Suspend or equivalent (if supported)
3468 deep - Suspend-To-RAM or equivalent (if supported)
3469 See Documentation/admin-guide/pm/sleep-states.rst.
3471 mfgptfix [X86-32] Fix MFGPT timers on AMD Geode platforms when
3487 0 - The attached screen is the 3.5" TFT
3488 1 - The attached screen is the 7" TFT
3489 2 - The VGA Shield is attached (1024x768)
3493 b - Enable backlight. The TFT backlight pin will be
3497 c - Enable the s3c camera interface.
3498 t - Reserved for enabling touchscreen support. The
3502 https://repo.or.cz/w/linux-2.6/mini2440.git
3507 arch-independent options, each of which is an
3508 aggregation of existing arch-specific options.
3537 ssbd=force-off [ARM64]
3550 have other ways of avoiding SMT-based attacks.
3585 full - Enable mitigation on vulnerable CPUs
3587 full,nosmt - Enable mitigation and disable SMT on
3590 off - Unconditionally disable mitigation
3603 Documentation/admin-guide/hw-vuln/processor_mmio_stale_data.rst
3633 module_blacklist= [KNL] Do not load a comma-separated list of
3658 movable_node [KNL,EARLY] Boot-time switch to make hotplugable memory
3665 Format: <name>,<region-number>,<size>,<offset>
3668 <name>,<region-number>[,<base>,<size>,<buswidth>,<altbuswidth>]
3707 something different and driver-specific.
3747 [NFS] enable 64-bit inode numbers.
3748 If zero, the NFS client will fake up a 32-bit inode
3750 of returning the full 64-bit number.
3751 The default is to return 64-bit inode numbers.
3786 [NFS4] Specify an additional fixed unique ident-
3817 driver. A non-zero value sets the minimum interval
3822 server-to-server copies for which this server is
3834 server-to-server copy, knfsd temporarily mounts
3841 See Documentation/admin-guide/nfs/nfsroot.rst.
3843 nfsroot= [NFS] nfs root filesystem for disk-less boxes.
3844 See Documentation/admin-guide/nfs/nfsroot.rst.
3847 See Documentation/admin-guide/nfs/nfsroot.rst.
3851 NMI stack-backtrace request.
3860 0 - turn hardlockup detector in nmi_watchdog off
3861 1 - turn hardlockup detector in nmi_watchdog on
3862 rNNN - configure the watchdog with raw perf event 0xNNN
3875 no387 [BUGS=X86-32] Tells the kernel to use the 387 maths
3879 no4lvl [RISCV,EARLY] Disable 4-level and 5-level paging modes.
3880 Forces kernel to use 3-level paging instead.
3882 no5lvl [X86-64,RISCV,EARLY] Disable 5-level paging mode. Forces
3883 kernel to use 4-level paging instead.
3916 no_entry_flush [PPC,EARLY] Don't flush the L1-D cache when entering the kernel.
3918 noexec32 [X86-64]
3919 This affects only 32-bit executables.
3920 noexec32=on: enable non-executable mappings (default)
3922 noexec32=off: disable non-executable mappings
3933 nofxsr [BUGS=X86-32] Disables x86 floating point extended
3935 legacy floating-point registers on task switch.
3946 compared. However, if this command-line option is
3987 nointremap [X86-64,Intel-IOMMU,EARLY] Do not enable interrupt
3989 [Deprecated - use intremap=off]
3995 noirqdebug [X86-32] Disables the code which attempts to detect and
4005 no-kvmapf [X86,KVM,EARLY] Disable paravirtualized asynchronous page
4008 no-kvmclock [X86,KVM,EARLY] Disable paravirtualized KVM clock driver
4010 nolapic [X86-32,APIC,EARLY] Do not enable or use the local APIC.
4012 nolapic_timer [X86-32,APIC,EARLY] Do not use the local APIC timer.
4014 nomce [X86-32] Disable Machine Check Exception
4016 nomfgpt [X86-32] Disable Multi-Function General Purpose
4022 not load if they could possibly displace the pre-
4025 perform display-mode changes or accelerated rendering.
4038 nopcid [X86-64,EARLY] Disable the PCID cpu feature.
4043 nopti [X86-64,EARLY]
4059 noreplace-smp [X86-32,SMP] Don't replace SMP instructions
4065 no-scroll [VGA] Disables scrollback.
4066 This is required for the Braillex ib80-piezo Braille
4069 nosgx [X86-64,SGX,EARLY] Disables Intel SGX kernel support.
4089 nosoftlockup [KNL] Disable the soft-lockup detector.
4095 nospectre_bhb [ARM64,EARLY] Disable all mitigations for Spectre-BHB (branch
4108 no-steal-acc [X86,PV_OPS,ARM64,PPC/PSERIES,RISCV,LOONGARCH,EARLY]
4118 [PPC,EARLY] Don't flush the L1-D cache after accessing user data.
4131 no-vmw-sched-clock
4136 soft-lockup and NMI watchdog (hard-lockup).
4140 nox2apic [X86-64,APIC,EARLY] Do not enable x2APIC mode.
4148 enabling legacy floating-point and sse state.
4170 n. So during boot up some boot time memory for per-cpu
4171 variables need be pre-allocated for later physical cpu
4202 See Documentation/admin-guide/sysctl/vm.rst for details.
4205 See Documentation/core-api/debugging-via-ohci1394.rst for more
4220 onenand.bdry= [HW,MTD] Flex-OneNAND Boundary Configuration
4224 boundary - index of last SLC block on Flex-OneNAND.
4226 lock - Configure if Flex-OneNAND boundary should be locked.
4245 page_owner= [KNL,EARLY] Boot-time page_owner enabling option.
4251 page_poison= [KNL,EARLY] Boot-time parameter changing the state of
4279 See Documentation/admin-guide/tainted-kernels.rst for
4332 Set to non-zero to probe primary and secondary ISA
4338 Set to non-zero if a chip is present that snoops speed
4386 Set to non-zero to probe tertiary and further ISA
4402 Set to non-zero to probe QDI controllers. By default
4407 Set to non-zero to probe Winbond controllers. Use
4454 bios [X86-32] force use of PCI BIOS, don't access
4456 has a non-standard PCI host bridge.
4457 nobios [X86-32] disallow use of PCI BIOS, only direct
4463 data in IO port 0xCFC, both 32-bit).
4465 Mechanism 2 (IO port 0xCF8 is an 8-bit port for
4466 the function, IO port 0xCFA, also 8-bit, sets
4468 through ports 0xC000-0xCFFF).
4475 root domains (aka PCI segments, in ACPI-speak).
4483 disable the use of MSI interrupts system-wide.
4488 primary IO-APIC for bridges that cannot disable
4495 biosirq [X86-32] Use PCI BIOS calls to get the interrupt
4519 F0000h-100000h range.
4524 assign-busses [X86] Always assign all PCI bus
4545 <linux-pci@vger.kernel.org>.
4549 a bug to <linux-pci@vger.kernel.org>.
4561 bfsort Sort PCI devices into breadth-first order.
4564 nobfsort Don't sort PCI devices into breadth-first order.
4566 tuning and use the BIOS-configured MPS defaults.
4576 configuration allows peer-to-peer DMA between
4579 that hot-added devices will work.
4594 A PCI-PCI bridge can be specified if resource
4600 for 4096-byte alignment.
4602 end-to-end CRC checking). Only effective if
4633 noats [PCIE, Intel-IOMMU, AMD-IOMMU]
4664 bit-0 : ACS Source Validation
4665 bit-1 : ACS Translation Blocking
4666 bit-2 : ACS P2P Request Redirect
4667 bit-3 : ACS P2P Completion Redirect
4668 bit-4 : ACS Upstream Forwarding
4669 bit-5 : ACS P2P Egress Control
4670 bit-6 : ACS Direct Translated P2P
4680 Validation unchanged from whatever power-up
4692 system-wide.
4706 dpc-native Use native PCIe service for DPC only. May
4723 Keep all power-domains already enabled by bootloader on,
4741 pirq= [SMP,APIC] Manual mp-table setup
4742 See Documentation/arch/x86/i386/IO-APIC.rst.
4746 See also Documentation/admin-guide/parport.rst.
4765 CONFIG_PNP_DEBUG_MESSAGES option). Change at run-time
4774 { on | off | curr | res | no-curr | no-res }
4819 none - Limited to cond_resched() calls
4820 voluntary - Limited to cond_resched() and might_sleep() calls
4821 full - Any section that isn't explicitly preempt disabled
4825 lazy - Scheduler controlled. Similar to full but instead
4831 print-fatal-signals=
4837 coredump - etc.
4840 you might want to try "ulimit -i unlimited".
4852 or lockdep-detected issues (only if lock debug is on).
4861 on - unlimited logging to /dev/kmsg from userspace
4862 off - logging to /dev/kmsg disabled
4863 ratelimit - ratelimit the logging
4874 - 'always': traditional behavior always allows mem overrides.
4875 - 'ptrace': only allow mem overrides for active ptracers.
4876 - 'never': never allow mem overrides.
4880 Limit processor to maximum C-state
4884 Ignore the _CST method to determine C-states,
4891 Param: "schedule" - profile schedule points.
4892 Param: "kvm" - profile VM exits.
4893 Param: <number> - step/bucket size as a power of 2 for
4924 pti= [X86-64] Control Page Table Isolation of user and
4929 on - unconditionally enable
4930 off - unconditionally disable
4931 auto - kernel detects whether your CPU model is
4937 [KNL] Number of legacy pty's. Overwrites compiled-in
4949 See Documentation/admin-guide/md.rst.
4952 See Documentation/admin-guide/blockdev/ramdisk.rst.
4971 cross-syscall address exposures. This is only
4977 ras=option[,option,...] [KNL] RAS-specific options
4983 rcu_nocbs[=cpu-list]
4988 enable the no-callback CPU mode, which prevents
4993 "p" for RCU-preempt, "s" for RCU-sched, and "g"
4997 and real-time workloads. It can also improve
5001 list of CPUs is set to no-callback mode from boot.
5005 no-callback mode from boot but the mode may be
5016 This improves the real-time response for the
5027 Do only a one-line RCU CPU stall warning when
5028 there is an ongoing too-long CSD-lock wait.
5034 If triggered before the RCU grace-period machinery
5044 RCU grace-period cleanup.
5048 RCU grace-period initialization.
5052 RCU grace-period pre-initialization, that is,
5053 the propagation of recent CPU-hotplug changes up
5057 Set delay from grace-period initialization to
5070 soliciting quiescent-state help from
5082 Set the SCHED_FIFO priority of the RCU per-CPU
5085 and for the RCU grace-period kthreads (rcu_bh,
5087 set, valid values are 1-99 and the default is 1
5088 (the least-favored priority). Otherwise, when
5089 RCU_BOOST is not set, valid values are 0-99 and
5090 the default is zero (non-realtime operation).
5095 On callback-offloaded (rcu_nocbs) CPUs,
5098 use of the ->nocb_bypass list. However, in the
5099 common non-flooded case, RCU queues directly to
5100 the main ->cblist in order to avoid the extra
5101 overhead of the ->nocb_bypass list and its lock.
5103 a single jiffy, RCU pre-queues the callbacks into
5104 the ->nocb_bypass queue. The definition of "too
5108 On callback-offloaded (rcu_nocbs) CPUs, avoid
5121 batch limiting is re-enabled.
5125 RCU's force-quiescent-state scan will aggressively
5133 Set the page-cache refill delay (in milliseconds)
5134 in response to low-memory conditions. The range
5138 Set the shift-right count to use to compute
5139 the callback-invocation batch limit bl from
5146 Please note that this callback-invocation batch
5147 limit applies only to non-offloaded callback
5156 cache-to-cache transfer latencies.
5162 and for NUMA systems with large remote-access
5178 the wakeup overhead on the global grace-period
5180 each group's NOCB grace-period kthread.
5183 Cause the grace-period kthread to get an extra
5185 it should at force-quiescent-state time.
5198 this specifies an rcu_read_unlock()-time delay
5202 of RCU-protected pointers after the relevant
5212 per-CPU rcuc kthreads. Defaults to a non-zero
5241 grace-period primitives such as call_rcu().
5252 grace-period primitives.
5255 Set test-start holdoff period. The purpose of
5273 Test the double-argument variant of kfree_rcu().
5275 rcuscale.kfree_rcu_test_single, both the single-
5276 and double-argument variants are tested.
5279 Test the single-argument variant of kfree_rcu().
5281 rcuscale.kfree_rcu_test_double, both the single-
5282 and double-argument variants are tested.
5296 does not affect the data-collection interval,
5301 Set number of RCU readers. The value -1 selects
5303 "n" less than -1 selects N-n+1, where N is again
5304 the number of CPUs. For example, -2 selects N
5305 (the number of CPUs), -3 selects N+1, and so on.
5306 A value of "n" less than or equal to -N selects
5319 complete. This is useful for hands-off automated
5326 Write-side holdoff between grace periods,
5331 Additional write-side holdoff between grace
5349 for RCU grace-period forward-progress testing
5356 Specify the fraction of a CPU-stall-warning
5357 period to do tight-loop forward-progress testing.
5361 forward-progress tests.
5365 need_resched() during tight-loop forward-progress
5369 Use conditional/asynchronous update-side
5373 Use expedited update-side primitives, if available.
5376 Use normal (non-expedited) asynchronous
5377 update-side primitives, if available.
5380 Use normal (non-expedited) synchronous
5381 update-side primitives, if available. If all
5385 they are all non-zero.
5393 Leak an RCU-protected pointer out of the reader.
5408 Set number of RCU callback-offload togglers.
5413 callback-offload toggling attempts.
5416 Set number of RCU readers. The value -1 selects
5417 N-1, where N is the number of CPUs. A value
5418 "n" less than -1 selects N-n-2, where N is again
5419 the number of CPUs. For example, -2 selects N
5420 (the number of CPUs), -3 selects N+1, and so on.
5423 Enable debug-object double-call_rcu() testing.
5426 Set time (s) after boot for CPU-hotplug testing.
5429 Set time (jiffies) between CPU-hotplug operations,
5430 or zero to disable CPU-hotplug testing.
5433 The number of times in a given read-then-exit
5434 episode that a set of read-then-exit kthreads
5439 read-then-exit testing episodes.
5444 are entered from low-order bit up, and are
5446 0x1 bit is normal readers, 0x2 NMI-safe readers,
5447 and 0x4 light-weight readers.
5450 Set task-shuffle interval (s). Shuffling tasks
5451 allows some CPUs to go into dyntick-idle mode
5456 is useful for hands-off automated testing.
5465 any other stall-related activity. Note that
5471 in scheduling-while-atomic splats.
5490 grace-period kthread to test RCU CPU stall
5516 Test RCU's dyntick-idle handling. See also the
5571 Use expedited grace-period primitives, for
5575 real-time latency, and degrade energy efficiency.
5579 Use only normal grace-period primitives,
5582 real-time latency, CPU utilization, and
5584 increased grace-period latency. This parameter
5591 only normal grace-period primitives. No effect
5597 post-boot attempt at an expedited RCU grace
5598 period to instead use normal non-expedited
5599 grace-period processing.
5607 set to the default value of -1.
5610 Set the minimum number of callback-queuing-time
5611 lock-contention events per jiffy required to
5612 cause the RCU Tasks flavors to switch to per-CPU
5615 the default value of -1.
5620 of -1 allows this to be automatically (and
5628 number avoids disturbing real-time workloads,
5633 cancel laziness on that CPU. Use -1 to disable
5643 only printed prior to the stall-warning message
5691 force - Override the decision by the kernel to hide the
5710 Where reboot_mode is one of warm (soft) or cold (hard) or gpio
5719 Set test-start holdoff period. The purpose of
5734 but the default has already reduced the per-pass
5739 Set number of readers. The default value of -1
5748 Set the read-side critical-section duration,
5752 Specify the read-protection implementation to test.
5778 See Documentation/admin-guide/cgroup-v1/cpusets.rst.
5808 reservetop= [X86-32,EARLY]
5825 See Documentation/power/swsusp-and-swap-files.rst
5841 AMD-based UNRET and IBPB mitigations alone do not stop
5843 sibling threads. For that reason, STIBP is used on pro-
5847 off - no mitigation
5848 auto - automatically select a migitation
5849 auto,nosmt - automatically select a mitigation,
5853 ibpb - On AMD, mitigate short speculation
5858 ibpb,nosmt - Like "ibpb" above but will disable SMT
5862 unret - Force enable untrained return thunks,
5863 only effective on AMD f15h-f17h based
5865 unret,nosmt - Like unret, but will disable SMT when STIBP
5897 ro [KNL] Mount root device read-only on boot
5900 on Mark read-only kernel memory as read-only (default).
5901 off Leave read-only kernel memory writable for debugging.
5902 full Mark read-only kernel memory and aliases as read-only
5909 debug-uart get routed to the D+ and D- pins of the usb
5915 block/early-lookup.c for details.
5940 rw [KNL] Mount root device read-write on boot
5994 to 10 seconds for built-in smp_call_function()
6001 that requesting even small non-zero numbers of
6008 The default of -1 specifies a number of kthreads
6013 test before initiating CPU-hotplug operations.
6017 CPU-hotplug operations. Specifying zero (which
6018 is the default) disables CPU-hotplug operations.
6024 Non-zero values are useful for automated tests.
6047 "wait" parameter. A value of -1 selects the
6048 default if all other weights are -1. However,
6050 value of -1 will instead select a weight of zero.
6055 non-zero "wait" parameter. See weight_single.
6068 non-zero "wait" parameter. See weight_single
6080 non-zero "wait" parameter. See weight_single
6091 0 -- disable. (may be 1 via CONFIG_CMDLINE="skew_tick=1"
6092 1 -- enable.
6103 0 -- disable.
6104 1 -- enable.
6107 serialnumber [BUGS=X86-32]
6109 sev=option[,option...] [X86-64] See Documentation/arch/x86/x86_64/boot-options.rst
6117 to set it to "all" by meaning -- no limit here.
6198 using the csdlock_debug- kernel parameter.
6203 system. By default, let CSD-lock acquisition
6205 for this value provides a 5-minute timeout.
6207 smsc-ircc2.nopnp [HW] Don't use PNP to discover SMC devices
6208 smsc-ircc2.ircc_cfg= [HW] Device configuration I/O port
6209 smsc-ircc2.ircc_sir= [HW] SIR base I/O port
6210 smsc-ircc2.ircc_fir= [HW] FIR base I/O port
6211 smsc-ircc2.ircc_irq= [HW] IRQ line
6212 smsc-ircc2.ircc_dma= [HW] DMA channel
6213 smsc-ircc2.ircc_transceiver= [HW] Transceiver type:
6223 Default: -1 (no limit)
6226 [KNL] Should the soft-lockup detector generate panics.
6229 A value of 1 instructs the soft-lockup detector
6230 to panic the machine when a soft-lockup occurs. It is
6233 respective build-time switch to that functionality.
6236 [KNL] Should the soft-lockup detector generate
6241 See Documentation/admin-guide/laptops/sonypi.rst
6248 on - (default) Enable the HW or SW mitigation as
6251 vmexit - On systems which don't have the HW mitigation
6254 protected from VM-originated BHI attacks, but
6256 off - Disable the mitigation.
6263 on - unconditionally enable, implies
6265 off - unconditionally disable, implies
6267 auto - kernel detects whether your CPU model is
6284 retpoline - replace indirect branches
6285 retpoline,generic - Retpolines
6286 retpoline,lfence - LFENCE; indirect branch
6287 retpoline,amd - alias for retpoline,lfence
6288 eibrs - Enhanced/Auto IBRS
6289 eibrs,retpoline - Enhanced/Auto IBRS + Retpolines
6290 eibrs,lfence - Enhanced/Auto IBRS + LFENCE
6291 ibrs - use IBRS to protect kernel
6301 on - Unconditionally enable mitigations. Is
6304 off - Unconditionally disable mitigations. Is
6307 prctl - Indirect branch speculation is enabled,
6313 - Like "prctl" above, but only STIBP is
6319 - Same as "prctl" above, but all seccomp
6324 - Like "seccomp" above, but only STIBP is
6329 auto - Kernel selects the mitigation depending on
6340 off - Disable mitigation
6341 microcode - Enable microcode mitigation only
6342 safe-ret - Enable sw-only safe RET mitigation (default)
6343 ibpb - Enable mitigation by issuing IBPB on
6345 ibpb-vmexit - Issue IBPB only on VMEXIT
6346 (cloud-specific mitigation)
6371 on - Unconditionally disable Speculative Store Bypass
6372 off - Unconditionally enable Speculative Store Bypass
6373 auto - Kernel detects whether the CPU model contains an
6379 prctl - Control Speculative Store Bypass per thread
6383 seccomp - Same as "prctl" above, but all seccomp threads
6391 on,auto - On Power8 and Power9 insert a store-forwarding
6395 off - No action.
6409 off - not enabled
6411 warn - the kernel will emit rate-limited warnings
6419 fatal - the kernel will send SIGBUS to applications
6424 ratelimit:N -
6444 Certain CPUs are vulnerable to an MDS-like
6464 This kernel-boot parameter defaults to 128,
6465 but takes effect only when the low-order four
6482 instead of the compile-time CONFIG_NR_CPUS.
6486 grace-period sequence counter wrap for the
6487 srcu_data structure's ->srcu_gp_seq_needed field.
6502 Specifies the number of no-delay instances
6509 Specifies the per-grace-period phase, number of
6510 non-sleeping polls of readers. Beyond this limit,
6516 Specifies number of microseconds of non-sleeping
6517 delay between each non-sleeping poll of readers.
6520 Specifies the number of update-side contention
6525 set for contention-based conversions to occur.
6535 force-on: Unconditionally enable mitigation for
6537 force-off: Unconditionally disable mitigation for
6560 stacktrace_filter=[function-list]
6562 will trace at boot up. function-list is a comma-separated
6570 Set the STI (builtin display/keyboard on the HP-PARISC
6572 as the initial boot-console.
6632 to global on non-NUMA machines)
6657 <int> -- Number of I/O TLB slabs
6658 <int> -- Second integer after comma. Number of swiotlb
6661 force -- force using of bounce buffers even if they
6663 noforce -- Never use bounce buffers (for debugging)
6678 Ignore sysrq setting - this boot parameter will
6686 cache size. See Documentation/networking/ip-sysctl.rst
6693 Specify "mem" (for Suspend-to-RAM) or "standby" (for
6698 wakeup-capable RTC alarm.
6704 -1: disable all active trip points in all thermal zones
6708 -1: disable all critical trip points in all thermal zones
6715 -1: disable all passive trip points
6721 <deci-seconds>: poll all this frequency
6725 Format: <size>[KMG],<size>[KMG]:<state>;<size>[KMG]-<size>[KMG]:<state>
6730 See Documentation/admin-guide/mm/transhuge.rst for more
6738 Format: <size>[KMG],<size>[KMG]:<policy>;<size>[KMG]-<size>[KMG]:<policy>
6744 See Documentation/admin-guide/mm/transhuge.rst for more
6756 Prevent the CPU-hotplug component of torturing
6760 Dump the ftrace buffer at torture-test shutdown,
6764 with rotating-rust storage.
6769 disables verbose-printk() sleeping.
6772 Duration of each verbose-printk() sleep in jiffies.
6797 https://trustedcomputinggroup.org/resource/pc-client-platform-tpm-profile-ptp-specification/
6835 local - Use the per CPU time stamp counter
6839 global - Event time stamps are synchronize across
6842 counter - Simple counting of events (1, 2, ..)
6846 uptime - Use jiffies as the time stamp.
6847 perf - Use the same clock that perf uses.
6848 mono - Use ktime_get_mono_fast_ns() for time stamps.
6849 mono_raw - Use ktime_get_raw_fast_ns() for time
6851 boot - Use ktime_get_boot_fast_ns() for time stamps.
6855 trace_event=[event-list]
6857 to facilitate early boot debugging. The event-list is a
6858 comma-separated list of trace events to enable. See
6861 trace_instance=[instance-info]
6886 traceoff - Have the tracing instance tracing disabled after it is created.
6887 traceprintk - Have trace_printk() write into this trace instance
6932 trace_options=[option-list]
6934 The option-list is a comma delimited list of options
6948 trace_trigger=[trigger-list]
6985 See Documentation/admin-guide/mm/transhuge.rst
6992 See Documentation/admin-guide/mm/transhuge.rst
7000 - "tpm"
7001 - "tee"
7002 - "caam"
7003 - "dcp"
7013 - "kernel"
7014 - the same value as trusted.source: "tpm" or "tee"
7015 - "default"
7036 high-resolution timer mode on older hardware, and in
7072 on - Enable TSX on the system. Although there are
7075 several previous speculation-related CVEs, and
7079 off - Disable TSX on the system. (Note that this
7087 auto - Disable TSX if X86_BUG_TAA is present,
7092 See Documentation/admin-guide/hw-vuln/tsx_async_abort.rst
7098 Similar to Micro-architectural Data Sampling (MDS)
7113 full - Enable TAA mitigation on vulnerable CPUs
7116 full,nosmt - Enable TAA mitigation and disable SMT on
7119 vulnerable to cross-thread TAA attacks.
7120 off - Unconditionally disable TAA mitigation
7122 On MDS-affected machines, tsx_async_abort=off can be
7134 Documentation/admin-guide/hw-vuln/tsx_async_abort.rst
7140 See also Documentation/input/devices/joystick-parport.rst
7142 udbg-immortal [PPC] When debugging early kernel crashes that
7148 Set number of hash buckets for UDP/UDP-Lite connections
7150 uhci-hcd.ignore_oc=
7152 Some badly-designed motherboards generate lots of
7161 unwind_debug [X86-64,EARLY]
7169 (default -1 = authorized (same as 1),
7175 for newly-detected USB devices (default 2). This
7203 [USB] Specifies timeout for the initial 64-byte
7210 [USB] A list of quirk entries to augment the built-in
7213 VendorID:ProductID:Flags. The IDs are 4-digit hex
7215 will change the built-in quirk; setting it if it is
7220 a 255-byte read);
7224 Set-Interface requests);
7243 (bInterval-1).
7281 usb-storage.delay_use=
7288 usb-storage.quirks=
7290 override the built-in unusual_devs list. List
7293 and Product ID values (4-digit hex numbers) and
7295 to a common usb-storage quirk flag as follows:
7337 medium is write-protected).
7346 1 - undefined instruction events
7347 2 - system calls
7348 4 - invalid data aborts
7349 8 - SIGSEGV faults
7350 16 - SIGBUS faults
7366 vdso32= [X86] Control the 32-bit vDSO
7367 vdso32=1: enable 32-bit VDSO
7368 vdso32=0 or vdso32=2: disable 32-bit VDSO
7378 dl_main: Assertion `(void *) ph->p_vaddr == _rtld_local._dl_sysinfo_dso' failed!
7409 vga= [BOOT,X86-32] Select a particular video mode
7411 Documentation/admin-guide/svga.rst.
7426 - Disable all of the above options
7450 vsyscall= [X86-64,EARLY]
7453 code). Most statically-linked binaries and older
7477 see VGA-softcursor.txt. Default: 2 = underline.
7482 This is a 16-member array composed of values
7483 ranging from 0-255.
7488 This is a 16-member array composed of values
7489 ranging from 0-255.
7494 This is a 16-member array composed of values
7495 ranging from 0-255.
7500 Set system-wide default UTF-8 mode for all tty's.
7501 Default is 1, i.e. UTF-8 mode is enabled for all
7506 Format=<-1|0|1>
7507 Set system-wide default for whether a cursor
7508 is shown on new VTs. Default is -1,
7513 vt.italic= [VT] Default color for italic text; 0-15.
7516 vt.underline= [VT] Default color for underlined text; 0-15.
7520 see Documentation/watchdog/watchdog-parameters.rst
7521 or other driver-specific files in the
7535 Format: <cpu-list>
7556 Per-cpu work items which run for longer than this
7559 them from noticeably delaying other per-cpu work
7577 Per-cpu workqueues are generally preferred because
7579 locality; unfortunately, per-cpu workqueues tend to
7582 Enabling this makes the per-cpu workqueues which
7596 Documentation/core-api/workqueue.rst.
7609 forces round-robin CPU selection to flush out
7617 on - Enable writecombine, use WUC for ioremap_wc()
7618 off - Disable writecombine, use SUC for ioremap_wc()
7620 x2apic_phys [X86-64,APIC,EARLY] Use x2apic physical mode instead of
7624 xen_512gb_limit [KNL,X86-64,XEN]
7634 ide-disks -- unplug primary master IDE devices
7635 aux-ide-disks -- unplug non-primary-master IDE devices
7636 nics -- unplug network devices
7637 all -- unplug all emulated devices (NICs and IDE disks)
7638 unnecessary -- unplugging emulated devices is
7641 never -- do not unplug even if version check succeeds
7655 Select whether to always use non-faulting (safe) MSR
7675 xen_timer_slop= [X86-64,XEN,EARLY]
7700 preferred over the 2-level event handling, as it is
7717 xive.store-eoi=off [PPC]
7723 xhci-hcd.quirks [USB,KNL]