Lines Matching +full:allow +full:- +full:set +full:- +full:time
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 nocmcff -- Disable firmware first mode for corrected
26 source to check if firmware has set the FF flag. This
28 nospcr -- disable console in ACPI SPCR table as
45 If set to vendor, prefer vendor-specific driver
48 If set to video, use the ACPI video.ko driver.
49 If set to native, use the device's native backlight mode.
50 If set to none, disable the ACPI backlight interface.
77 Documentation/firmware-guide/acpi/debug.rst for more information about
135 Format: <byte> or <bitmap-list>
138 Disable auto-serialization of AML methods
141 auto-serialization feature.
149 Disable installation of static SSDTs at early boot time
159 Ignore the ACPI-based watchdog interface (WDAT) and let
180 acpi_osi=! # disable all built-in OS vendor
182 acpi_osi=!! # enable all built-in OS vendor
244 For broken nForce2 BIOS resulting in XT-PIC timer.
253 as soon as the kernel's real-mode entry point is called.
259 on docking. So the default behaviour is to allow resume
270 sci_force_enable causes the kernel to set SCI_EN directly
291 See Documentation/sound/alsa-configuration.rst
294 Allow the default userspace alignment fault handler
298 align_va_addr= [X86-64]
300 allocating a VMA at process creation time. This option
303 CPU-intensive style benchmark, and it can vary highly in
306 32: only for 32-bit processes
307 64: only for 64-bit processes
308 on: enable for both 32- and 64-bit processes
309 off: disable for both 32- and 64-bit processes
319 Allow execve() of 32-bit applications and setting of the
321 subset of the CPUs support 32-bit EL0. When this
322 parameter is present, the set of CPUs supporting 32-bit
324 and hot-unplug operations may be restricted.
326 See Documentation/arch/arm64/asymmetric-32bit.rst for more
329 amd_iommu= [HW,X86-64]
332 fullflush - Deprecated, equivalent to iommu.strict=1
333 off - do not initialize any AMD IOMMU found in
335 force_isolation - Force device isolation for all
340 force_enable - Force enable the IOMMU on platforms known
343 pgtbl_v1 - Use v1 page table for DMA-API (Default).
344 pgtbl_v2 - Use v2 page table for DMA-API.
345 irtcachedis - Disable Interrupt Remapping Table (IRT) caching.
346 nohugepages - Limit page-sizes used for v1 page-tables
348 v2_pgsizes_only - Limit page-sizes used for v1 page-tables
352 amd_iommu_dump= [HW,X86-64]
358 amd_iommu_intr= [HW,X86-64]
361 legacy - Use legacy interrupt remapping mode.
362 vapic - Use virtual APIC mode, which allows IOMMU
364 This mode requires kvm-amd.avic=1.
393 Disable amd-pstate preferred core.
406 Power management functions (SPARCstation-4/5 + deriv.)
408 Disable APC CPU standby support. SPARCstation-Fox does
409 not play well with APC CPU idle - disable it if you have
412 apic [APIC,X86-64] Use IO-APIC. Default.
418 when initialising the APIC and IO-APIC components.
439 apparmor= [APPARMOR] Disable or enable AppArmor at boot time
442 0 -- disable.
443 1 -- enable.
444 Default value is set via kernel config option.
446 arcrimi= [HW,NET] ARCnet - "RIM I" (entirely mem-mapped) cards
459 Set instructions support
485 atkbd.set= [HW] Select keyboard code set
497 audit= [KNL] Enable the audit sub-system
499 0 | off - kernel audit is disabled and can not be
501 unset - kernel audit is initialized but disabled and
503 1 | on - kernel audit is initialized and partially
509 audit_backlog_limit= [KNL] Set the audit queue size limit.
516 0 - Disable the BAU.
517 1 - Enable the BAU.
518 unset - Disable the BAU.
540 for writing, i.e., allow / disallow writes that bypass
557 See Documentation/block/cmdline-partition.rst
571 See Documentation/admin-guide/bootconfig.rst
576 bttv.pll= See Documentation/admin-guide/media/bttv.rst
581 at a time.
585 cachesize= [BUGS=X86-32] Override level 2 CPU cache size detection.
593 [NET] Specifies amount of time (in seconds) that
604 inclusive. See arch/mips/include/asm/pgtable-bits.h
614 - foo isn't auto-mounted if you mount all cgroups in
616 - foo isn't visible as an individually mountable
618 - if foo is an optional feature then the feature is
624 Specifying "pressure" disables per-cgroup pressure
642 nosocket -- Disable socket memory accounting.
643 nokmem -- Disable kernel memory accounting.
644 nobpf -- Disable BPF memory accounting.
646 checkreqprot= [SELINUX] Set initial checkreqprot flag value.
649 0 -- check protection applied by kernel (includes
651 1 -- check protection requested by application.
652 Default value is set via a kernel config option.
663 numbers X. Note the Linux-specific bits are not necessarily
664 stable over kernel options, but the vendor-specific
684 force such clocks to be always-on nor does it reserve
688 information, see Documentation/driver-api/clk.rst.
690 clock= [BUGS=X86-32, HW] gettimeofday clocksource override.
707 [X86-32] pit,hpet,tsc;
714 [X86-64] hpet,tsc
720 architected timer so that code using WFE-based polling
734 clocksource-wdtest.holdoff= [KNL]
735 Set the time in seconds that the clocksource
740 cma=nn[MG]@[start[MG][-end[MG]]]
751 Sets the size of kernel per-numa memory area for
753 per-numa CMA altogether. And If this option is not
755 With per-numa CMA enabled, DMA users on node nid will
780 allocations, by default set to 256K.
782 com20020= [HW,NET] ARCnet - COM20020 chipset
786 com90io= [HW,NET] ARCnet - COM90xx chipset (IO-mapped buffers)
790 ARCnet - COM90xx chipset (memory-mapped buffers)
798 When set to true, drop data on the 3215 console when
803 This leads to a much faster boot time when a 3270
819 See Documentation/admin-guide/serial-console.rst for more
834 $ ls -d /sys/bus/serial-base/devices/*:*.*/tty/*
835 /sys/bus/serial-base/devices/00:04:0.0/tty/ttyS0
848 Start an early, polled-mode console on the 8250/16550
851 MMIO inter-register address stride is either 8-bit
852 (mmio), 16-bit (mmio16), or 32-bit (mmio32).
856 the h/w is not re-initialized.
876 "[time stamp] text\n" format (time stamp may not be
880 Switch to syslog format: "<%u>[time stamp] text\n"
883 syscall, or to executing "dmesg -S --raw" or to reading
900 1: enable debugging at boot time
907 disable the cpuidle sub-system
913 disable the cpufreq sub-system
921 [X86,EARLY] Delay for N microsec between assert and de-assert
938 running the panic notifiers could allow collecting
942 like Hyper-V, PowerPC (fadump) and AMD SEV-SNP.
950 [KNL, X86-64, ARM64, RISCV, LoongArch] Select a region
953 See Documentation/admin-guide/kdump/kdump.rst for further details.
958 start-[end] where start and end are both
960 Documentation/admin-guide/kdump/kdump.rst for an example.
963 [KNL, X86-64, ARM64, RISCV, LoongArch] range could be
965 Allow kernel to allocate physical memory region from top,
971 [KNL, X86-64, ARM64, RISCV, LoongArch] range under 4G.
977 for 32-bit devices won't run out. Kernel would try to allocate
980 --> x86: max(swiotlb_size_or_default() + 8MiB, 256MiB)
981 --> arm64: 128MiB
982 --> riscv: 128MiB
983 --> loongarch: 128MiB
991 [KNL] Disable crypto self-tests
999 csdlock_debug= [KNL] Enable or disable debug add-ons of cross-CPU
1014 See also Documentation/input/devices/joystick-parport.rst
1027 [KNL] verbose locking self-tests
1030 self-tests.
1032 (no extra messages), setting it to -1 (all bits set)
1033 will print _a_lot_ more information - normally only
1039 [KNL,EARLY] When CONFIG_DEBUG_PAGEALLOC is set, this
1058 [KNL,EARLY] When CONFIG_DEBUG_PAGEALLOC is set, this parameter
1059 enables the feature at boot time. By default, it is
1068 Format: { on, no-mount, off }
1070 no-mount:
1075 get a -EPERM as result when trying to register files
1079 Default value is set in build-time with a kernel configuration.
1091 Documentation/admin-guide/mm/hugetlbpage.rst.
1095 [KNL] Debugging option to set a timeout in seconds for
1099 of 0 will timeout at the end of initcalls. If the time
1105 delayacct [KNL] Enable per-task delay accounting
1122 [HW] Allow controlling fans only if SYS_ADMIN
1123 capability is set.
1144 Set number of hash buckets for dentry cache.
1191 entries for DMA-API debugging code. One entry is
1192 required per DMA-API allocation. Use this if the
1193 DMA-API debugging code disables itself because the
1197 With this option the DMA-API debugging driver
1198 filter feature can be enabled at boot time. Just
1206 vulnerability which may allow userspace to infer
1214 This parameter overrides the compile time default set
1221 Documentation/admin-guide/hw-vuln/reg-file-data-sampling.rst
1235 An EDID data set will only be used for a particular
1238 data set by separating the files with a comma. An EDID
1239 data set with no connector name will be used for
1246 Control how the dt_cpu_ftrs device-tree binding is
1256 what data is available or for reverse-engineering.
1260 Enable debug messages at boot time. See
1261 Documentation/admin-guide/dynamic-debug-howto.rst
1272 determined by stdout-path property in device tree's
1277 Start an early, polled-mode console on a Cadence
1288 Start an early, polled-mode console on the 8250/16550
1290 MMIO inter-register address stride is either 8-bit
1291 (mmio) or 32-bit (mmio32 or mmio32be).
1296 the uart clock frequency; if unspecified, it is set
1301 Start an early, polled-mode console on a pl011 serial
1305 the driver will use only 32-bit accessors to read/write
1314 Start an early, polled-mode console on a meson serial
1320 Start an early, polled-mode console on an msm serial
1326 Start an early, polled-mode console on an msm serial
1332 Start an early, polled-mode console on a serial port
1338 Start an early, polled-mode console on a serial port
1344 Use RISC-V SBI (Supervisor Binary Interface) for early
1362 Start an early, polled-mode console on a lantiq serial
1376 Start an early, polled-mode, output-only console on the
1381 Start an early, polled-mode console on the
1387 Start an early, polled-mode console on a Qualcomm
1395 coherent non-x86 systems that use system memory for
1429 be used at a time.
1485 no_disable_early_pci_dma: Leave the busmaster bit set
1498 Documentation/admin-guide/acpi/ssdt-overlays.rst for details.
1504 ekgdboc= [X86,KGDB,EARLY] Allow early kernel console debugging
1515 elanfreq= [X86-32]
1523 See Documentation/admin-guide/kdump/kdump.rst for details.
1534 The kernel tries to set a reasonable default.
1536 enforcing= [SELINUX] Set initial enforcing status.
1539 0 -- permissive (log only, no denials).
1540 1 -- enforcing (deny and log).
1573 See also Documentation/fault-injection/.
1577 See Documentation/admin-guide/sysctl/net.rst for
1581 See Documentation/admin-guide/blockdev/floppy.rst.
1583 forcepae [X86-32]
1590 fred= [X86-64]
1597 [FTRACE] will set and start the specified tracer
1641 ftrace_filter=[function-list]
1643 tracer at boot up. function-list is a comma-separated
1645 time by the set_ftrace_filter file in the debugfs
1648 ftrace_notrace=[function-list]
1650 function-list. This list can be changed at run time
1654 ftrace_graph_filter=[function-list]
1657 function-list is a comma-separated list of functions
1658 that can be changed at run time by the
1661 ftrace_graph_notrace=[function-list]
1663 function-list. This list is a comma-separated list of
1664 functions that can be changed at run time by the
1670 can be changed at run time by the max_graph_depth file
1683 off -- Don't create device links from firmware info.
1684 permissive -- Create device links from firmware info
1687 on -- Create device links from firmware info and use it
1689 rpm -- Like "on", but also use to order runtime PM.
1702 strict -- Default. Continue waiting on consumers to
1704 timeout -- Give up waiting on consumers and call
1714 See also Documentation/input/devices/joystick-parport.rst
1718 gart_fix_e820= [X86-64,EARLY] disable the fix e820 for K8 GART
1744 gcov_persist= [GCOV] When non-zero (default), profiling data for
1748 debugfs files are removed at module unload time.
1754 gpio-mockup.gpio_mockup_ranges
1757 gpio-mockup.gpio_mockup_named_lines
1789 against bounds-checking flaws in the kernel's
1797 [KNL] Should the hard-lockup detector generate
1803 for 64-bit NUMA, off otherwise.
1811 corresponding firmware-first mode error processing
1820 (that will set all pages holding image data
1821 during restoration read-only).
1839 is set. Default value is 5.
1852 hostname= [KNL,EARLY] Set the hostname (aka UTS nodename).
1856 Using this parameter to set the hostname makes it
1857 possible to ensure the hostname is correctly set before
1860 has been explicitly set, resulting in the calling
1865 hpet= [X86-32,HPET] option to control HPET usage
1869 force: allow force enabled of undocumented chips (ICH4,
1873 hpet_mmap= [X86, HPET_MMAP] Allow userspace to mmap HPET
1874 registers. Default set by CONFIG_HPET_MMAP_DEFAULT.
1882 number of pages to allocate per-node can be specified.
1883 See also Documentation/admin-guide/mm/hugetlbpage.rst.
1894 Documentation/admin-guide/mm/hugetlbpage.rst.
1900 used to improve system bootup time when allocating
1904 Note that this parameter only applies to non-gigantic huge pages.
1914 boot-time allocation of gigantic hugepages is skipped.
1949 by the CONFIG_BOOTPARAM_HUNG_TASK_PANIC build-time
1955 hvc_iucv_allow= [S390] Comma-separated list of z/VM user IDs.
1961 which allow the hypervisor to 'idle' the guest
1977 Set device-properties for ACPI-enumerated I2C-attached
1978 touchscreen, to e.g. fix coordinates of upside-down
1986 Omit "=<val>" entirely Set a boolean device-property
1987 Unsigned number Set a u32 device-property
1988 Anything else Set a string device-property
1991 i2c_touchscreen_props=GDIX1001:touchscreen-inverted-x:
1992 touchscreen-inverted-y
1994 i2c_touchscreen_props=MSSL1680:touchscreen-size-x=1920:
1995 touchscreen-size-y=1080:touchscreen-inverted-y:
1996 firmware-name=gsl1680-vendor-model.fw:silead,home-button
2001 (disabled by default, and as a pre-condition
2003 i8042.direct [HW] Put keyboard port into non-translated mode
2017 suspend-to-ram transitions, only during s2r
2027 [HW] Allow deferred probing upon i8042 probe errors
2033 set the brightness of the panel backlight. Normally a
2036 to maximum brightness. If this parameter is set to 0
2038 is set to 1, a brightness value of 0 sets the backlight
2041 -1 -- never invert brightness
2042 0 -- machine default
2043 1 -- force brightness inversion
2045 ia32_emulation= [X86-64]
2047 When true, allows loading 32-bit programs and executing 32-bit
2049 boot time. When false, unconditionally disables IA32 emulation.
2072 idle=nomwait: Disable mwait for CPU C-states
2076 Allow force disabling of Shared Virtual Memory (SVA)
2077 support for the idxd driver. By default it is set to
2082 Allow override of default traffic class configuration
2083 for the device. By default it is set to false (0).
2092 of an ELF file header flag individually set by each
2100 legacy only accept legacy-NaN binaries, if supported
2102 2008 only accept 2008-NaN binaries, if supported
2113 'relaxed' straps the emulator for both legacy-NaN and
2114 2008-NaN, whereas 'strict' enables legacy-NaN only on
2123 Ignore loglevel setting - this will print /all/
2135 Set number of hash buckets for inode cache.
2164 mode bit set by either the effective uid (euid=0) or
2190 Formats: { "ima" | "ima-ng" | "ima-ngv2" | "ima-sig" |
2191 "ima-sigv2" }
2192 Default: "ima-ng"
2200 Set the minimal file size for using asynchronous hash.
2209 Set hashing buffer size. Default: 4k.
2225 stuff: Deploy RSB-fill mitigation when retpoline is
2230 Documentation/admin-guide/hw-vuln/indirect-target-selection.rst
2241 initcall_blacklist= [KNL] Do not execute a comma-separated list of
2242 initcall functions. Useful for debugging built-in
2269 Default set by CONFIG_INIT_ON_ALLOC_DEFAULT_ON.
2273 Default set by CONFIG_INIT_ON_FREE_DEFAULT_ON.
2287 0 -- basic integrity auditing messages. (Default)
2288 1 -- additional integrity auditing messages.
2316 could harm performance of some high-throughput
2325 1 to 9 specify maximum depth of C-state.
2334 algorithms for p-state selection. There are two
2335 P-state selection algorithms provided by
2338 on whether or not the hardware managed P-states
2345 used along with the hardware-managed P-states (HWP)
2349 in favor of acpi-cpufreq. Forcing the intel_pstate driver
2350 instead of acpi-cpufreq may disable platform features, such
2352 P-States information being indicated to OSPM and therefore
2355 or on platforms that use pcc-cpufreq instead of acpi-cpufreq.
2368 Allow per-logical-CPU P-State performance control limits using
2371 Do not enable capacity-aware scheduling (CAS) on
2374 intremap= [X86-64,Intel-IOMMU,EARLY]
2379 BIOS x2APIC opt-out request will be ignored
2422 AMD Gart HW IOMMU-specific options:
2425 Set the size of the remapping area in bytes.
2441 Do scatter-gather (SG) merging. Implies "force"
2445 Don't do scatter-gather (SG) merging.
2458 0 - Try to allocate a 32-bit DMA address first, before
2460 1 - Allocate directly from the full usable range,
2462 greater than 32-bit addressing.
2466 0 - Lazy mode.
2472 1 - Strict mode.
2475 unset - Use value of CONFIG_IOMMU_DEFAULT_DMA_{LAZY,STRICT}.
2477 legacy driver-specific options takes precedence.
2482 0 - Use IOMMU translation for DMA.
2483 1 - Bypass the IOMMU for DMA.
2484 unset - Use value of CONFIG_IOMMU_DEFAULT_PASSTHROUGH.
2486 io7= [HW] IO7 for Marvel-based Alpha systems
2501 See Documentation/admin-guide/nfs/nfsroot.rst.
2518 irqaffinity= [SMP] Set the default irq affinity mask
2537 Enables support for pseudo-NMIs in the kernel. This
2542 [RISC-V,EARLY]
2544 as IPIs. Intended for system where IMSIC is trap-n-emulated,
2562 isolcpus= [KNL,SMP,ISOL] Isolate a given set of CPUs from disturbance.
2563 [Deprecated - use cpusets instead]
2564 Format: [flag-list,]<cpu-list>
2592 move in and out of an isolated set anytime.
2597 "number of CPUs in system - 1".
2623 The format of <cpu-list> is described above.
2627 ivrs_ioapic [HW,X86-64]
2628 Provide an override to the IOAPIC-ID<->DEVICE-ID
2632 For example, to map IOAPIC-ID decimal 10 to
2638 * To map IOAPIC-ID decimal 10 to PCI device 00:14.0
2641 * To map IOAPIC-ID decimal 10 to PCI segment 0x1 and
2645 ivrs_hpet [HW,X86-64]
2646 Provide an override to the HPET-ID<->DEVICE-ID
2650 For example, to map HPET-ID decimal 10 to
2656 * To map HPET-ID decimal 0 to PCI device 00:14.0
2659 * To map HPET-ID decimal 10 to PCI segment 0x1 and
2663 ivrs_acpihid [HW,X86-64]
2664 Provide an override to the ACPI-HID:UID<->DEVICE-ID
2668 For example, to map UART-HID:UID AMD0020:0 to
2674 * To map UART-HID:UID AMD0020:0 to PCI segment is 0,
2677 * To map UART-HID:UID AMD0020:0 to PCI segment 0x1 and
2701 the kernel for non-movable allocations. The requested
2711 subsystem. Note that allocations like PTEs-from-HighMem
2719 for non-movable allocations and remaining memory is used
2730 gdb or control-c on the dbgp connection. When
2731 not using this parameter you use sysrq-g to break into
2736 or a supported polling keyboard driver (non-usb).
2765 "0" | "off" | "n" - kexec handover is disabled
2766 "1" | "on" | "y" - kexec handover is enabled
2772 ranges that can only be used for non-kernel
2783 parameter defines the size of additional per-node
2788 Configure the RouterBoard 532 series on-chip
2791 kmemleak= [KNL,EARLY] Boot-time kmemleak enable/disable
2797 kprobe_event=[probe-list]
2798 [FTRACE] Add kprobe events and enable at boot time.
2799 The probe-list is a semicolon delimited list of probe
2817 CONFIG_KUNIT to be set to be fully enabled. The
2829 execution by eliminating the write-protection faults
2835 disabling eager page splitting to allow huge pages to
2856 virtualization on-demand when creating and destroying
2864 is that doing so may interfere with using out-of-tree
2890 [KVM] Controls the time period at which KVM zaps 4KiB pages
2891 back to huge pages. If the value is a non-zero N, KVM will
2896 kvm-amd.nested= [KVM,AMD] Control nested virtualization feature in
2899 kvm-amd.npt= [KVM,AMD] Control KVM's use of Nested Page Tables,
2900 a.k.a. Two-Dimensional Page Tables. Default is 1
2904 kvm-arm.mode=
2910 nvhe: Standard nVHE-based mode, without support for
2917 nested: VHE-based mode with support for nested
2925 command-line.
2929 kvm-arm.vgic_v3_group0_trap=
2930 [KVM,ARM,EARLY] Trap guest accesses to GICv3 group-0
2933 kvm-arm.vgic_v3_group1_trap=
2934 [KVM,ARM,EARLY] Trap guest accesses to GICv3 group-1
2937 kvm-arm.vgic_v3_common_trap=
2941 kvm-arm.vgic_v4_enable=
2942 [KVM,ARM,EARLY] Allow use of GICv4 for direct
2945 kvm-arm.wfe_trap_policy=
2946 [KVM,ARM] Control when to set WFE instruction trap for
2950 trap: set WFE instruction trap
2954 kvm-arm.wfi_trap_policy=
2955 [KVM,ARM] Control when to set WFI instruction trap for
2959 trap: set WFI instruction trap
2971 kvm-intel.ept= [KVM,Intel] Control KVM's use of Extended Page Tables,
2972 a.k.a. Two-Dimensional Page Tables. Default is 1
2976 kvm-intel.emulate_invalid_guest_state=
2978 state. Ignored if kvm-intel.enable_unrestricted_guest=1,
2984 kvm-intel.flexpriority=
2989 kvm-intel.nested=
2993 kvm-intel.unrestricted_guest=
2999 kvm-intel.vmentry_l1d_flush=[KVM,Intel] Mitigation for L1 Terminal Fault
3000 CVE-2018-3620.
3011 kvm-intel.vpid= [KVM,Intel] Control KVM's use of Virtual Processor
3031 on - enable the interface for the mitigation
3096 For details see: Documentation/admin-guide/hw-vuln/l1tf.rst
3102 lapic [X86-32,APIC,EARLY] Enable the local APIC even if BIOS
3106 value for LAPIC timer one-shot implementation. Default
3126 when set.
3129 libata.force= [LIBATA] Force configurations. The format is a comma-
3141 first fan-out link behind PMP device. It does not
3155 * Transfer mode: pio[0-7], mwdma[0-4] and udma[0-7].
3162 * rstonce: only attempt one reset during hot-unplug
3179 * max_trim_128m: Set 128M maximum trim size limit.
3197 * max_sec_128: Set transfer size limit to 128 sectors.
3199 * max_sec_1024: Set or clear transfer size limit to
3202 * max_sec_lba48: Set or clear transfer size limit to
3205 * external: Mark port as external (hotplug-capable).
3238 Enable the kernel lockdown feature. If set to
3239 integrity, kernel features that allow userland to
3240 modify the running kernel are disabled. If set to
3241 confidentiality, kernel features that allow userland
3246 Set the time limit in jiffies for a lock
3259 Specify the number of self-propagating call_rcu()
3260 chains to set up. These are used to ensure that
3262 in progress at any given time. Defaults to 0,
3267 occasional long-duration lock hold time. Defaults
3278 Set the number of locking read-acquisition kthreads.
3279 Defaults to being automatically set based on the
3283 Set the number of locking write-acquisition kthreads.
3286 Set time (s) after boot for CPU-hotplug testing.
3289 Set time (s) between CPU-hotplug operations, or
3290 zero to disable CPU-hotplug testing.
3293 Do periodic testing of real-time lock priority
3298 non-real-time spinlocks, due to their disabling
3299 of preemption. Note that non-realtime mutexes
3306 number of boosts per unit time remains roughly
3312 Set task-shuffle interval (jiffies). Shuffling
3313 tasks allows some CPUs to go into dyntick-idle
3317 Set time (s) after boot system shutdown. This
3318 is useful for hands-off automated testing.
3321 Time (s) between statistics printk()s.
3324 Time (s) to stutter testing, for example,
3337 Run the write-side locktorture kthreads at
3338 sched_set_fifo() real-time priority.
3356 7 (KERN_DEBUG) debug-level messages
3368 logo.nologo [FB] Disables display of the built-in Linux logo.
3386 an IEEE 1284-compliant printer is attached; if
3392 time-consuming boot-time autodetection (up to 250 ms per
3412 Example: machtype=lemote-yeeloong-2f-7inch
3424 (loop.max_loop) unconditionally pre-created at init time. The default
3427 devices can be requested on-demand with the
3428 /dev/loop-control interface.
3430 mce= [X86-{32,64}]
3467 do not opt-in to Local MCE delivery. Use legacy method
3484 sets the time in us to wait for other CPUs on machine
3488 don't overwrite the bios-set CMCI threshold. This boot
3490 threshold set by the bios. Without this option, Linux
3497 force-enable recoverable machine check code paths
3503 See Documentation/admin-guide/md.rst.
3510 Control mitigation for the Micro-architectural Data
3525 full - Enable MDS mitigation on vulnerable CPUs
3526 full,nosmt - Enable MDS mitigation and disable
3528 off - Unconditionally disable MDS mitigation
3530 On TAA-affected machines, mds=off can be prevented by
3539 For details see: Documentation/admin-guide/hw-vuln/mds.rst
3541 mem=nn[KMG] [HEXAGON,EARLY] Set the memory size.
3554 [ARC,MICROBLAZE] - the limit applies only to low memory,
3557 [ARM64] - only limits memory covered by the linear
3565 Note that this only takes effects during boot time since
3570 [ARM,MIPS,EARLY] - override the memory layout
3577 mem=nopentium [BUGS=X86-32] Disable usage of 4MB pages for kernel
3583 [KNL,SH] Allow user to override the default size for
3584 per-device physically contiguous DMA buffers.
3587 [KNL] Set the initial state for the memory hotplug
3589 set according to the
3592 See Documentation/admin-guide/mm/memory-hotplug.rst.
3617 Example: Exclude memory from 0x18690000-0x1869ffff
3631 memmap=<size>%<offset>-<oldtype>+<newtype>
3633 from <oldtype> to <newtype>. If "-<oldtype>" is left
3648 repeatable BIOS-originated corruption always
3670 hotadded memory which will allow to hotadd a
3687 pattern from a given set of patterns. Memtest
3692 mem_encrypt= [X86-64] AMD Secure Memory Encryption (SME) control
3698 Refer to Documentation/virt/kvm/x86/amd-memory-encryption.rst
3702 s2idle - Suspend-To-Idle
3703 shallow - Power-On Suspend or equivalent (if supported)
3704 deep - Suspend-To-RAM or equivalent (if supported)
3705 See Documentation/admin-guide/pm/sleep-states.rst.
3707 mfgptfix [X86-32] Fix MFGPT timers on AMD Geode platforms when
3723 0 - The attached screen is the 3.5" TFT
3724 1 - The attached screen is the 7" TFT
3725 2 - The VGA Shield is attached (1024x768)
3729 b - Enable backlight. The TFT backlight pin will be
3733 c - Enable the s3c camera interface.
3734 t - Reserved for enabling touchscreen support. The
3738 https://repo.or.cz/w/linux-2.6/mini2440.git
3742 CPU vulnerabilities. This is a set of curated,
3743 arch-independent options, each of which is an
3744 aggregation of existing arch-specific options.
3774 ssbd=force-off [ARM64]
3787 have other ways of avoiding SMT-based attacks.
3801 supports attack-vector based controls as documented in
3802 Documentation/admin-guide/hw-vuln/attack_vector_controls.rst
3805 [KNL,EARLY] When CONFIG_DEBUG_MEMORY_INIT is set, this
3826 full - Enable mitigation on vulnerable CPUs
3828 full,nosmt - Enable mitigation and disable SMT on
3831 off - Unconditionally disable mitigation
3844 Documentation/admin-guide/hw-vuln/processor_mmio_stale_data.rst
3854 [KNL] When set to true, modules will use async probing
3863 [KNL] When CONFIG_MODULE_DEBUG_AUTOLOAD_DUPS is set,
3866 if MODULE_DEBUG_AUTOLOAD_DUPS_TRACE is set, WARN_ON()s
3869 [KNL] When CONFIG_MODULE_SIG is set, this means that
3871 Note that if CONFIG_MODULE_SIG_FORCE is set, that
3874 module_blacklist= [KNL] Do not load a comma-separated list of
3878 [MOUSE] Maximum time between finger touching and
3899 movable_node [KNL,EARLY] Boot-time switch to make hotplugable memory
3906 Format: <name>,<region-number>,<size>,<offset>
3909 <name>,<region-number>[,<base>,<size>,<buswidth>,<altbuswidth>]
3920 registers at boot time.
3937 Set to 2 or more if your graphical card needs more.
3941 at a time.
3948 something different and driver-specific.
3953 [NET] Specifies amount of time (in seconds) that
3972 [NFSv4] set the total number of threads that the
3977 [NFS] set the TCP port on which the NFSv4 callback
3988 [NFS] enable 64-bit inode numbers.
3989 If zero, the NFS client will fake up a 32-bit inode
3991 of returning the full 64-bit number.
3992 The default is to return 64-bit inode numbers.
3995 [NFS] set the maximum lifetime for idmapper cache
4014 [NFSv4] When set to the default of '1', this option
4024 To turn off this behaviour, set the value to '0'.
4027 [NFS4] Specify an additional fixed unique ident-
4030 UUID that is generated at system install time.
4039 attempting to recover these locks, then set this
4057 whatever value is the default set by the layout
4058 driver. A non-zero value sets the minimum interval
4062 [NFSv4.2] When set to 1, the server will support
4063 server-to-server copies for which this server is
4067 [NFSv4] When set to the default of '1', the NFSv4
4075 server-to-server copy, knfsd temporarily mounts
4082 See Documentation/admin-guide/nfs/nfsroot.rst.
4084 nfsroot= [NFS] nfs root filesystem for disk-less boxes.
4085 See Documentation/admin-guide/nfs/nfsroot.rst.
4088 See Documentation/admin-guide/nfs/nfsroot.rst.
4092 NMI stack-backtrace request.
4101 0 - turn hardlockup detector in nmi_watchdog off
4102 1 - turn hardlockup detector in nmi_watchdog on
4103 rNNN - configure the watchdog with raw perf event 0xNNN
4107 watchdog, if CONFIG_BOOTPARAM_HARDLOCKUP_PANIC is set)
4116 no387 [BUGS=X86-32] Tells the kernel to use the 387 maths
4120 no4lvl [RISCV,EARLY] Disable 4-level and 5-level paging modes.
4121 Forces kernel to use 3-level paging instead.
4123 no5lvl [X86-64,RISCV,EARLY] Disable 5-level paging mode. Forces
4124 kernel to use 4-level paging instead.
4131 noapictimer [APIC,X86] Don't set up the APIC timer
4155 nodsp [SH] Disable hardware DSP at boot time.
4159 no_entry_flush [PPC,EARLY] Don't flush the L1-D cache when entering the kernel.
4161 noexec32 [X86-64]
4162 This affects only 32-bit executables.
4163 noexec32=on: enable non-executable mappings (default)
4165 noexec32=off: disable non-executable mappings
4172 nofpu [MIPS,SH] Disable hardware FPU at boot time.
4176 nofxsr [BUGS=X86-32] Disables x86 floating point extended
4178 legacy floating-point registers on task switch.
4191 compared. However, if this command-line option is
4220 In kernels built with CONFIG_NO_HZ_FULL=y, set
4234 nointremap [X86-64,Intel-IOMMU,EARLY] Do not enable interrupt
4236 [Deprecated - use intremap=off]
4242 noirqdebug [X86-32] Disables the code which attempts to detect and
4248 When CONFIG_RANDOMIZE_BASE is set, this disables
4252 no-kvmapf [X86,KVM,EARLY] Disable paravirtualized asynchronous page
4255 no-kvmclock [X86,KVM,EARLY] Disable paravirtualized KVM clock driver
4257 nolapic [X86-32,APIC,EARLY] Do not enable or use the local APIC.
4259 nolapic_timer [X86-32,APIC,EARLY] Do not use the local APIC timer.
4261 nomce [X86-32] Disable Machine Check Exception
4263 nomfgpt [X86-32] Disable Multi-Function General Purpose
4269 not load if they could possibly displace the pre-
4272 perform display-mode changes or accelerated rendering.
4285 nopcid [X86-64,EARLY] Disable the PCID cpu feature.
4290 nopti [X86-64,EARLY]
4300 which allow the hypervisor to 'idle' the guest on lock
4306 noreplace-smp [X86-32,SMP] Don't replace SMP instructions
4312 no-scroll [VGA] Disables scrollback.
4313 This is required for the Braillex ib80-piezo Braille
4316 nosgx [X86-64,SGX,EARLY] Disables Intel SGX kernel support.
4336 nosoftlockup [KNL] Disable the soft-lockup detector.
4342 nospectre_bhb [ARM64,EARLY] Disable all mitigations for Spectre-BHB (branch
4343 history injection) vulnerability. System may allow data leaks
4352 prediction) vulnerability. System may allow data
4355 no-steal-acc [X86,PV_OPS,ARM64,PPC/PSERIES,RISCV,LOONGARCH,EARLY]
4356 Disable paravirtualized steal time accounting. steal time
4362 timer IRQ sources, i.e., the IO-APIC timer. This can
4367 [PPC,EARLY] Don't flush the L1-D cache after accessing user data.
4378 is set.
4380 no-vmw-sched-clock
4385 soft-lockup and NMI watchdog (hard-lockup).
4389 nox2apic [X86-64,APIC,EARLY] Do not enable x2APIC mode.
4392 LEGACY_XAPIC_DISABLED bit set in the
4397 enabling legacy floating-point and sse state.
4419 n. So during boot up some boot time memory for per-cpu
4420 variables need be pre-allocated for later physical cpu
4426 Disable NUMA, Only set up a single NUMA node
4447 soft-reserved memory partitioning.
4455 This can be set from sysctl after boot.
4456 See Documentation/admin-guide/sysctl/vm.rst for details.
4459 See Documentation/core-api/debugging-via-ohci1394.rst for more
4466 waiting for the ACK, so if this is set too high
4474 onenand.bdry= [HW,MTD] Flex-OneNAND Boundary Configuration
4478 boundary - index of last SLC block on Flex-OneNAND.
4480 lock - Configure if Flex-OneNAND boundary should be locked.
4499 page_owner= [KNL,EARLY] Boot-time page_owner enabling option.
4505 page_poison= [KNL,EARLY] Boot-time parameter changing the state of
4526 Hexadecimal bitmask representing the set of TAINT flags
4528 called with any of the flags in this set.
4532 bitmask set on panic_on_taint.
4533 See Documentation/admin-guide/tainted-kernels.rst for
4586 Set to non-zero to probe primary and secondary ISA
4592 Set to non-zero if a chip is present that snoops speed
4597 Set to 1, 2, or 3 for HT 6560A on the primary channel,
4603 Set to 1, 2, or 3 for HT 6560B on the primary channel,
4609 IORDY enable mask. Set individual bits to allow IORDY
4621 Set to 1, 2, or 3 for Opti 82c611A on the primary
4627 Set to 1, 2, or 3 for Opti 82c465MV on the primary
4633 PIO mode mask for autospeed devices. Set individual
4634 bits to allow the use of the respective PIO modes.
4640 Set to non-zero to probe tertiary and further ISA
4656 Set to non-zero to probe QDI controllers. By default
4657 set to 1 if CONFIG_PATA_QDI_MODULE, 0 otherwise.
4661 Set to non-zero to probe Winbond controllers. Use
4664 By default set to 1 if CONFIG_PATA_WINBOND_VLB_MODULE,
4669 Supported PIO mode mask. Set individual bits to allow
4684 or a set of devices (<pci_dev>). These are
4708 bios [X86-32] force use of PCI BIOS, don't access
4710 has a non-standard PCI host bridge.
4711 nobios [X86-32] disallow use of PCI BIOS, only direct
4717 data in IO port 0xCFC, both 32-bit).
4719 Mechanism 2 (IO port 0xCF8 is an 8-bit port for
4720 the function, IO port 0xCFA, also 8-bit, sets
4722 through ports 0xC000-0xCFFF).
4729 root domains (aka PCI segments, in ACPI-speak).
4737 disable the use of MSI interrupts system-wide.
4742 primary IO-APIC for bridges that cannot disable
4749 biosirq [X86-32] Use PCI BIOS calls to get the interrupt
4766 irqmask=0xMMMM [X86] Set a bit mask of IRQs allowed to be
4773 F0000h-100000h range.
4778 assign-busses [X86] Always assign all PCI bus
4799 <linux-pci@vger.kernel.org>.
4803 a bug to <linux-pci@vger.kernel.org>.
4815 bfsort Sort PCI devices into breadth-first order.
4818 nobfsort Don't sort PCI devices into breadth-first order.
4820 tuning and use the BIOS-configured MPS defaults.
4821 pcie_bus_safe Set every device's MPS to the largest value
4823 pcie_bus_perf Set device MPS to the largest allowable MPS
4824 based on its parent bus. Also set MRRS (Max
4828 pcie_bus_peer2peer Set every device's MPS to 128B, which
4830 configuration allows peer-to-peer DMA between
4833 that hot-added devices will work.
4848 A PCI-PCI bridge can be specified if resource
4854 for 4096-byte alignment.
4856 end-to-end CRC checking). Only effective if
4887 noats [PCIE, Intel-IOMMU, AMD-IOMMU]
4894 can resize a BAR to allow access to all VRAM.
4903 allow P2P traffic between devices through
4918 bit-0 : ACS Source Validation
4919 bit-1 : ACS Translation Blocking
4920 bit-2 : ACS P2P Request Redirect
4921 bit-3 : ACS P2P Completion Redirect
4922 bit-4 : ACS Upstream Forwarding
4923 bit-5 : ACS P2P Egress Control
4924 bit-6 : ACS Direct Translated P2P
4934 Validation unchanged from whatever power-up
4935 or firmware set it to.
4946 system-wide.
4960 dpc-native Use native PCIe service for DPC only. May
4977 Keep all power-domains already enabled by bootloader on,
4983 boot time.
4995 pirq= [SMP,APIC] Manual mp-table setup
4996 See Documentation/arch/x86/i386/IO-APIC.rst.
5000 See also Documentation/admin-guide/parport.rst.
5010 cleared). If a number is given, then MMCR1 is set to
5017 /sys/power/pm_async sysfs knob at boot time.
5018 If set to "off", disables asynchronous suspend and
5019 resume of devices during system-wide power transitions.
5021 dependencies are not well-defined, or for debugging
5031 CONFIG_PNP_DEBUG_MESSAGES option). Change at run-time
5040 { on | off | curr | res | no-curr | no-res }
5064 Set the number of possible CPUs, overriding the
5085 none - Limited to cond_resched() calls
5086 voluntary - Limited to cond_resched() and might_sleep() calls
5087 full - Any section that isn't explicitly preempt disabled
5091 lazy - Scheduler controlled. Similar to full but instead
5093 one HZ tick time to yield itself before the
5097 print-fatal-signals=
5103 coredump - etc.
5106 you might want to try "ulimit -i unlimited".
5118 or lockdep-detected issues (only if lock debug is on).
5126 Allows storing messages from non-panic CPUs into
5128 flushed to consoles by the panic-CPU on
5129 a best-effort basis.
5135 on - unlimited logging to /dev/kmsg from userspace
5136 off - logging to /dev/kmsg disabled
5137 ratelimit - ratelimit the logging
5140 printk.time= Show timing data prefixed to each printk message line
5146 overridden without restrictions. This option may be set to
5148 - 'always': traditional behavior always allows mem overrides.
5149 - 'ptrace': only allow mem overrides for active ptracers.
5150 - 'never': never allow mem overrides.
5154 Limit processor to maximum C-state
5158 Ignore the _CST method to determine C-states,
5165 Param: "schedule" - profile schedule points.
5166 Param: "kvm" - profile VM exits.
5167 Param: <number> - step/bucket size as a power of 2 for
5168 statistical time based profiling.
5185 psmouse.rate= [HW,MOUSE] Set desired mouse report rate, in reports
5191 [HW,MOUSE] Set desired mouse resolution, in dpi.
5198 pti= [X86-64] Control Page Table Isolation of user and
5203 on - unconditionally enable
5204 off - unconditionally disable
5205 auto - kernel detects whether your CPU model is
5211 [KNL] Number of legacy pty's. Overwrites compiled-in
5223 See Documentation/admin-guide/md.rst.
5226 See Documentation/admin-guide/blockdev/ramdisk.rst.
5245 cross-syscall address exposures. This is only
5251 ras=option[,option,...] [KNL] RAS-specific options
5257 rcu_nocbs[=cpu-list]
5262 enable the no-callback CPU mode, which prevents
5267 "p" for RCU-preempt, "s" for RCU-sched, and "g"
5271 and real-time workloads. It can also improve
5275 list of CPUs is set to no-callback mode from boot.
5278 arguments are omitted, no CPU will be set to
5279 no-callback mode from boot but the mode may be
5290 This improves the real-time response for the
5297 Set maximum number of finished RCU callbacks to
5301 Do only a one-line RCU CPU stall warning when
5302 there is an ongoing too-long CSD-lock wait.
5308 If triggered before the RCU grace-period machinery
5317 Set the number of jiffies to delay each step of
5318 RCU grace-period cleanup.
5321 Set the number of jiffies to delay each step of
5322 RCU grace-period initialization.
5325 Set the number of jiffies to delay each step of
5326 RCU grace-period pre-initialization, that is,
5327 the propagation of recent CPU-hotplug changes up
5331 Set delay from grace-period initialization to
5337 Set delay between subsequent attempts to force
5342 Set required age in jiffies for a
5344 soliciting quiescent-state help from
5351 rcutree.jiffies_to_sched_qs. Any attempt to set
5356 Set the SCHED_FIFO priority of the RCU per-CPU
5359 and for the RCU grace-period kthreads (rcu_bh,
5361 set, valid values are 1-99 and the default is 1
5362 (the least-favored priority). Otherwise, when
5363 RCU_BOOST is not set, valid values are 0-99 and
5364 the default is zero (non-realtime operation).
5365 When RCU_NOCB_CPU is set, also adjust the
5369 On callback-offloaded (rcu_nocbs) CPUs,
5372 use of the ->nocb_bypass list. However, in the
5373 common non-flooded case, RCU queues directly to
5374 the main ->cblist in order to avoid the extra
5375 overhead of the ->nocb_bypass list and its lock.
5377 a single jiffy, RCU pre-queues the callbacks into
5378 the ->nocb_bypass queue. The definition of "too
5382 On callback-offloaded (rcu_nocbs) CPUs, avoid
5390 Set threshold of queued RCU callbacks beyond which
5394 Set threshold of queued RCU callbacks below which
5395 batch limiting is re-enabled.
5398 Set threshold of queued RCU callbacks beyond which
5399 RCU's force-quiescent-state scan will aggressively
5402 Set to less than zero to make this be set based
5403 on rcutree.qhimark at boot time and to zero to
5407 Set the page-cache refill delay (in milliseconds)
5408 in response to low-memory conditions. The range
5412 Set the shift-right count to use to compute
5413 the callback-invocation batch limit bl from
5418 order to allow the CPU to do other work.
5420 Please note that this callback-invocation batch
5421 limit applies only to non-offloaded callback
5430 cache-to-cache transfer latencies.
5436 and for NUMA systems with large remote-access
5449 Set the number of NOCB callback kthreads in
5452 the wakeup overhead on the global grace-period
5454 each group's NOCB grace-period kthread.
5457 Cause the grace-period kthread to get an extra
5459 it should at force-quiescent-state time.
5464 Limit the time spend invoking a batch of RCU
5472 this specifies an rcu_read_unlock()-time delay
5476 of RCU-protected pointers after the relevant
5485 If set to zero, move all RCU_SOFTIRQ processing to
5486 per-CPU rcuc kthreads. Defaults to a non-zero
5516 grace-period primitives such as call_rcu().
5522 corresponding flavor of rcu_barrier() to allow
5527 grace-period primitives.
5530 Set test-start holdoff period. The purpose of
5545 Set to measure performance of kfree_rcu() flooding.
5548 Test the double-argument variant of kfree_rcu().
5550 rcuscale.kfree_rcu_test_single, both the single-
5551 and double-argument variants are tested.
5554 Test the single-argument variant of kfree_rcu().
5556 rcuscale.kfree_rcu_test_double, both the single-
5557 and double-argument variants are tested.
5570 Set the minimum test run time in seconds. This
5571 does not affect the data-collection interval,
5576 Set number of RCU readers. The value -1 selects
5578 "n" less than -1 selects N-n+1, where N is again
5579 the number of CPUs. For example, -2 selects N
5580 (the number of CPUs), -3 selects N+1, and so on.
5581 A value of "n" less than or equal to -N selects
5585 Set number of RCU writers. The values operate
5594 complete. This is useful for hands-off automated
5601 Write-side holdoff between grace periods,
5606 Additional write-side holdoff between grace
5611 Set duration of force_quiescent_state bursts
5615 Set holdoff time within force_quiescent_state bursts
5619 Set wait time between force_quiescent_state bursts
5624 for RCU grace-period forward-progress testing
5631 Specify the fraction of a CPU-stall-warning
5632 period to do tight-loop forward-progress testing.
5636 forward-progress tests.
5640 need_resched() during tight-loop forward-progress
5644 Use conditional/asynchronous update-side
5645 normal-grace-period primitives, if available.
5648 Use conditional/asynchronous update-side
5649 expedited-grace-period primitives, if available.
5652 Use conditional/asynchronous update-side
5653 normal-grace-period primitives that also take
5658 Use conditional/asynchronous update-side
5659 expedited-grace-period primitives that also take
5683 Use expedited update-side primitives, if available.
5686 Use normal (non-expedited) asynchronous
5687 update-side primitives, if available.
5690 Use polled update-side normal-grace-period
5694 Use polled update-side expedited-grace-period
5698 Use polled update-side normal-grace-period
5703 Use polled update-side expedited-grace-period
5727 Use normal (non-expedited) synchronous
5728 update-side primitives, if available. If all
5732 they are all non-zero.
5735 Enable grace-period wrap lag testing. Setting
5740 Set the value for grace-period wrap lag during
5744 The default is always set to 8.
5747 Set the total cycle duration for gpwrap lag
5748 testing in minutes. This is the total time for
5753 Set the duration for which gpwrap lag is active
5754 within each cycle, in minutes. During this time,
5755 the grace-period wrap lag will be set to the
5765 Leak an RCU-protected pointer out of the reader.
5772 Set callbacks/threads for rcu_barrier() testing.
5775 Set number of concurrent RCU writers. These just
5780 Set number of RCU callback-offload togglers.
5784 Set the delay in milliseconds between successive
5785 callback-offload toggling attempts.
5788 Set number of RCU readers. The value -1 selects
5789 N-1, where N is the number of CPUs. A value
5790 "n" less than -1 selects N-n-2, where N is again
5791 the number of CPUs. For example, -2 selects N
5792 (the number of CPUs), -3 selects N+1, and so on.
5795 Enable debug-object double-call_rcu() testing.
5798 Set time (s) after boot for CPU-hotplug testing.
5801 Set time (jiffies) between CPU-hotplug operations,
5802 or zero to disable CPU-hotplug testing.
5805 Set duration (in milliseconds) of preemptions
5806 by a high-priority FIFO real-time task. Set to
5808 preempt are selected randomly from the set that
5809 are online at a given point in time. Races with
5814 Set interval (in milliseconds, defaulting to one
5815 second) between preemptions by a high-priority
5816 FIFO real-time task. This delay is mediated
5821 The number of times in a given read-then-exit
5822 episode that a set of read-then-exit kthreads
5827 read-then-exit testing episodes.
5831 If there is more than one bit set, the readers
5832 are entered from low-order bit up, and are
5834 0x1 bit is normal readers, 0x2 NMI-safe readers,
5835 and 0x4 light-weight readers.
5838 Set task-shuffle interval (s). Shuffling tasks
5839 allows some CPUs to go into dyntick-idle mode
5843 Set time (s) after boot system shutdown. This
5844 is useful for hands-off automated testing.
5851 Sleep while stalling if set. This will result
5853 any other stall-related activity. Note that
5859 in scheduling-while-atomic splats.
5865 Time to wait (s) after boot before inducing stall.
5868 Disable interrupts while stalling if set, but only
5869 on the first stall in the set.
5878 grace-period kthread to test RCU CPU stall
5884 Time (s) between statistics printk()s.
5887 Time (s) to stutter testing, for example, specifying
5901 Holdoff time (s) from start of test to the start
5902 of RCU priority-boost testing. Defaults to zero,
5909 Test RCU's dyntick-idle handling. See also the
5934 during early boot, that is, during the time
5938 Set timeout for RCU CPU stall warning messages.
5943 Set timeout for expedited RCU CPU stall warning
5964 Use expedited grace-period primitives, for
5968 real-time latency, and degrade energy efficiency.
5972 Use only normal grace-period primitives,
5975 real-time latency, CPU utilization, and
5977 increased grace-period latency. This parameter
5984 only normal grace-period primitives. No effect
5990 post-boot attempt at an expedited RCU grace
5991 period to instead use normal non-expedited
5992 grace-period processing.
5995 Set the maximum number of callbacks present
6000 set to the default value of -1.
6003 Set the minimum number of callback-queuing-time
6004 lock-contention events per jiffy required to
6005 cause the RCU Tasks flavors to switch to per-CPU
6007 when rcupdate.rcu_task_enqueue_lim is set to
6008 the default value of -1.
6011 Set the number of callback queues to use for the
6013 of -1 allows this to be automatically (and
6018 Set time in jiffies during which RCU tasks will
6021 number avoids disturbing real-time workloads,
6026 cancel laziness on that CPU. Use -1 to disable
6032 Set initial timeout in jiffies for RCU task stall
6036 only printed prior to the stall-warning message
6043 Multiplier for time interval between successive
6054 Set timeout in jiffies for RCU task stall
6061 Set timeout in milliseconds RCU Tasks asynchronous
6068 Set timeout in milliseconds RCU Tasks
6084 force - Override the decision by the kernel to hide the
6104 (prefix with 'panic_' to set mode for panic
6120 Set the cold reboot flag
6123 There are some built-in platform specific "quirks"
6124 - you may see: "reboot: <name> series board detected.
6128 built-in quirk table, and use the generic default
6151 Don't set the cold reboot flag
6161 Set test-start holdoff period. The purpose of
6173 Set the number of loops over the synchronization
6176 but the default has already reduced the per-pass
6181 Set number of readers. The default value of -1
6186 Set number of runs, each of which is dumped onto
6190 Set the read-side critical-section duration,
6194 Specify the read-protection implementation to test.
6219 [KNL, SMP] Set scheduler's default relax_domain_level.
6220 See Documentation/admin-guide/cgroup-v1/cpusets.rst.
6250 reservetop= [X86-32,EARLY]
6267 See Documentation/power/swsusp-and-swap-files.rst
6283 AMD-based UNRET and IBPB mitigations alone do not stop
6285 sibling threads. For that reason, STIBP is used on pro-
6289 off - no mitigation
6290 auto - automatically select a migitation
6291 auto,nosmt - automatically select a mitigation,
6295 ibpb - On AMD, mitigate short speculation
6300 ibpb,nosmt - Like "ibpb" above but will disable SMT
6304 unret - Force enable untrained return thunks,
6305 only effective on AMD f15h-f17h based
6307 unret,nosmt - Like unret, but will disable SMT when STIBP
6312 time according to the CPU.
6339 ro [KNL] Mount root device read-only on boot
6342 on Mark read-only kernel memory as read-only (default).
6343 off Leave read-only kernel memory writable for debugging.
6344 full Mark read-only kernel memory and aliases as read-only
6351 debug-uart get routed to the D+ and D- pins of the usb
6357 block/early-lookup.c for details.
6365 rootflags= [KNL] Set root filesystem mount option string
6367 rootfstype= [KNL] Set root filesystem type
6373 rootwait= [KNL] Maximum time (in seconds) to wait for root device
6387 rw [KNL] Mount root device read-write on boot
6392 Set s390 IOTLB flushing mode
6416 solution to mutex-based priority inversion.
6428 [KNL, SMP] Set a decay shift for scheduler thermal
6446 to 10 seconds for built-in smp_call_function()
6453 that requesting even small non-zero numbers of
6460 The default of -1 specifies a number of kthreads
6465 test before initiating CPU-hotplug operations.
6469 CPU-hotplug operations. Specifying zero (which
6470 is the default) disables CPU-hotplug operations.
6476 Non-zero values are useful for automated tests.
6485 to the set of CPUs under test.
6499 "wait" parameter. A value of -1 selects the
6500 default if all other weights are -1. However,
6502 value of -1 will instead select a weight of zero.
6507 non-zero "wait" parameter. See weight_single.
6520 non-zero "wait" parameter. See weight_single
6532 non-zero "wait" parameter. See weight_single
6541 contention on all systems with CONFIG_MAXSMP set.
6543 0 -- disable. (may be 1 via CONFIG_CMDLINE="skew_tick=1"
6544 1 -- enable.
6552 selinux= [SELINUX] Disable or enable SELinux at boot time.
6555 0 -- disable.
6556 1 -- enable.
6559 serialnumber [BUGS=X86-32]
6561 sev=option[,option...] [X86-64]
6567 Do not enable SEV-SNP (applies to host/hypervisor
6570 SEV-SNP guests.
6578 to set it to "all" by meaning -- no limit here.
6590 Documentation/admin-guide/mm/slab.rst.
6597 Documentation/admin-guide/mm/slab.rst.
6613 Documentation/admin-guide/mm/slab.rst.
6619 Documentation/admin-guide/mm/slab.rst.
6634 Documentation/admin-guide/mm/slab.rst.
6653 Specify the period of time in milliseconds
6658 of time. Defaults to 5,000 milliseconds, and
6661 using the csdlock_debug- kernel parameter.
6666 system. By default, let CSD-lock acquisition
6668 for this value provides a 5-minute timeout.
6670 smsc-ircc2.nopnp [HW] Don't use PNP to discover SMC devices
6671 smsc-ircc2.ircc_cfg= [HW] Device configuration I/O port
6672 smsc-ircc2.ircc_sir= [HW] SIR base I/O port
6673 smsc-ircc2.ircc_fir= [HW] FIR base I/O port
6674 smsc-ircc2.ircc_irq= [HW] IRQ line
6675 smsc-ircc2.ircc_dma= [HW] DMA channel
6676 smsc-ircc2.ircc_transceiver= [HW] Transceiver type:
6681 smt= [KNL,MIPS,S390,EARLY] Set the maximum number of threads
6686 Default: -1 (no limit)
6689 [KNL] Should the soft-lockup detector generate panics.
6692 A value of 1 instructs the soft-lockup detector
6693 to panic the machine when a soft-lockup occurs. It is
6696 respective build-time switch to that functionality.
6699 [KNL] Should the soft-lockup detector generate
6704 See Documentation/admin-guide/laptops/sonypi.rst
6711 on - (default) Enable the HW or SW mitigation as
6714 vmexit - On systems which don't have the HW mitigation
6717 protected from VM-originated BHI attacks, but
6719 off - Disable the mitigation.
6726 on - unconditionally enable, implies
6728 off - unconditionally disable, implies
6730 auto - kernel detects whether your CPU model is
6734 mitigation method at run time according to the
6749 retpoline - replace indirect branches
6750 retpoline,generic - Retpolines
6751 retpoline,lfence - LFENCE; indirect branch
6752 retpoline,amd - alias for retpoline,lfence
6753 eibrs - Enhanced/Auto IBRS
6754 eibrs,retpoline - Enhanced/Auto IBRS + Retpolines
6755 eibrs,lfence - Enhanced/Auto IBRS + LFENCE
6756 ibrs - use IBRS to protect kernel
6766 on - Unconditionally enable mitigations. Is
6769 off - Unconditionally disable mitigations. Is
6772 prctl - Indirect branch speculation is enabled,
6778 - Like "prctl" above, but only STIBP is
6784 - Same as "prctl" above, but all seccomp
6789 - Like "seccomp" above, but only STIBP is
6794 auto - Kernel selects the mitigation depending on
6805 off - Disable mitigation
6806 microcode - Enable microcode mitigation only
6807 safe-ret - Enable sw-only safe RET mitigation (default)
6808 ibpb - Enable mitigation by issuing IBPB on
6810 ibpb-vmexit - Issue IBPB only on VMEXIT
6811 (cloud-specific mitigation)
6836 on - Unconditionally disable Speculative Store Bypass
6837 off - Unconditionally enable Speculative Store Bypass
6838 auto - Kernel detects whether the CPU model contains an
6844 prctl - Control Speculative Store Bypass per thread
6848 seccomp - Same as "prctl" above, but all seccomp threads
6856 on,auto - On Power8 and Power9 insert a store-forwarding
6860 off - No action.
6874 off - not enabled
6876 warn - the kernel will emit rate-limited warnings
6884 fatal - the kernel will send SIGBUS to applications
6889 ratelimit:N -
6890 Set system wide rate limit to N bus locks
6909 Certain CPUs are vulnerable to an MDS-like
6929 This kernel-boot parameter defaults to 128,
6930 but takes effect only when the low-order four
6940 1: At init_srcu_struct() time.
6942 3: Decide at boot time (default).
6947 instead of the compile-time CONFIG_NR_CPUS.
6951 grace-period sequence counter wrap for the
6952 srcu_data structure's ->srcu_gp_seq_needed field.
6953 The greater the number of bits set in this kernel
6963 expediting. Set to zero to disable automatic
6967 Specifies the number of no-delay instances
6974 Specifies the per-grace-period phase, number of
6975 non-sleeping polls of readers. Beyond this limit,
6981 Specifies number of microseconds of non-sleeping
6982 delay between each non-sleeping poll of readers.
6985 Specifies the number of update-side contention
6990 set for contention-based conversions to occur.
7000 force-on: Unconditionally enable mitigation for
7002 force-off: Unconditionally disable mitigation for
7006 to allow userspace to register its
7019 consumed by the stack hash table. By default this is set
7025 stacktrace_filter=[function-list]
7027 will trace at boot up. function-list is a comma-separated
7029 time by the stack_trace_filter file in the debugfs
7035 Set the STI (builtin display/keyboard on the HP-PARISC
7037 as the initial boot-console.
7074 using these two parameters to set the minimum and
7097 to global on non-NUMA machines)
7104 server. Increasing these values may allow you to
7113 is set. Default value is 5.
7122 <int> -- Number of I/O TLB slabs
7123 <int> -- Second integer after comma. Number of swiotlb
7126 force -- force using of bounce buffers even if they
7128 noforce -- Never use bounce buffers (for debugging)
7133 Set a sysctl parameter, right before loading the init
7138 later by a loaded module cannot be set this way.
7143 Ignore sysrq setting - this boot parameter will
7148 Set the number of tcp_metrics_hash slots.
7151 cache size. See Documentation/networking/ip-sysctl.rst
7158 Specify "mem" (for Suspend-to-RAM) or "standby" (for
7163 wakeup-capable RTC alarm.
7166 Set number of hash buckets for TCP connection
7169 -1: disable all active trip points in all thermal zones
7173 -1: disable all critical trip points in all thermal zones
7180 -1: disable all passive trip points
7186 <deci-seconds>: poll all this frequency
7190 Format: <size>[KMG],<size>[KMG]:<state>;<size>[KMG]-<size>[KMG]:<state>
7195 See Documentation/admin-guide/mm/transhuge.rst for more
7203 Format: <size>[KMG],<size>[KMG]:<policy>;<size>[KMG]-<size>[KMG]:<policy>
7209 See Documentation/admin-guide/mm/transhuge.rst for more
7221 Prevent the CPU-hotplug component of torturing
7225 Dump the ftrace buffer at torture-test shutdown,
7229 with rotating-rust storage.
7234 disables verbose-printk() sleeping.
7237 Duration of each verbose-printk() sleep in jiffies.
7249 Maximum time in milliseconds to retry sending a message
7258 Specify that at suspend time, the tpm driver
7267 for the FIFO interface. By default it is set to false
7270 https://trustedcomputinggroup.org/resource/pc-client-platform-tpm-profile-ptp-specification/
7295 When tp_printk (above) is set, it can cause a lot of noise
7301 to console at the late_initcall_sync() time frame.
7304 [FTRACE] will set tracing buffer size on each cpu.
7306 trace_clock= [FTRACE] Set the clock used for tracing events
7308 local - Use the per CPU time stamp counter
7312 global - Event time stamps are synchronize across
7315 counter - Simple counting of events (1, 2, ..)
7319 uptime - Use jiffies as the time stamp.
7320 perf - Use the same clock that perf uses.
7321 mono - Use ktime_get_mono_fast_ns() for time stamps.
7322 mono_raw - Use ktime_get_raw_fast_ns() for time
7324 boot - Use ktime_get_boot_fast_ns() for time stamps.
7328 trace_event=[event-list]
7329 [FTRACE] Set and start specified trace events in order
7330 to facilitate early boot debugging. The event-list is a
7331 comma-separated list of trace events to enable. See
7342 trace_instance=[instance-info]
7348 Events can be enabled at the time the instance is created
7367 traceoff - Have the tracing instance tracing disabled after it is created.
7368 traceprintk - Have trace_printk() write into this trace instance
7390 memory may not be the same location each time, which will not preserve
7405 is set up to not wipe memory. For instance, CONFIG_RESET_ATTACK_MITIGATION
7415 trace_options=[option-list]
7417 The option-list is a comma delimited list of options
7431 trace_trigger=[trigger-list]
7433 Set a trigger on top of a specific event, with an optional
7469 This option can also be set at run time via the sysctl
7477 See Documentation/admin-guide/mm/transhuge.rst
7484 See Documentation/admin-guide/mm/transhuge.rst
7491 See Documentation/admin-guide/mm/transhuge.rst
7499 - "tpm"
7500 - "tee"
7501 - "caam"
7502 - "dcp"
7512 - "kernel"
7513 - the same value as trusted.source: "tpm" or "tee"
7514 - "default"
7537 off - disable the mitigation
7538 on - enable the mitigation (default)
7539 user - mitigate only user/kernel transitions
7540 vm - mitigate only guest/host transitions
7548 high-resolution timer mode on older hardware, and in
7551 Used to run time disable IRQ_TIME_ACCOUNTING on any
7584 on - Enable TSX on the system. Although there are
7587 several previous speculation-related CVEs, and
7591 off - Disable TSX on the system. (Note that this
7599 auto - Disable TSX if X86_BUG_TAA is present,
7604 See Documentation/admin-guide/hw-vuln/tsx_async_abort.rst
7610 Similar to Micro-architectural Data Sampling (MDS)
7625 full - Enable TAA mitigation on vulnerable CPUs
7628 full,nosmt - Enable TAA mitigation and disable SMT on
7631 vulnerable to cross-thread TAA attacks.
7632 off - Unconditionally disable TAA mitigation
7634 On MDS-affected machines, tsx_async_abort=off can be
7646 Documentation/admin-guide/hw-vuln/tsx_async_abort.rst
7652 See also Documentation/input/devices/joystick-parport.rst
7654 udbg-immortal [PPC] When debugging early kernel crashes that
7660 Set number of hash buckets for UDP/UDP-Lite connections
7662 uhci-hcd.ignore_oc=
7664 Some badly-designed motherboards generate lots of
7666 anything. Set this parameter to avoid log spamming.
7673 Allow skipping scalar unaligned access speed tests. This
7681 Allow skipping vector unaligned access speed tests. This
7689 unwind_debug [X86-64,EARLY]
7697 (default -1 = authorized (same as 1),
7702 [USB] The autosuspend time delay (in seconds) used
7703 for newly-detected USB devices (default 2). This
7704 is the time required before an idle device will be
7705 autosuspended. Devices for which the delay is set
7709 [USB] Set to log all usbfs traffic (default 0 = off).
7716 [USB] Set to cycle leds on hubs (default 0 = off).
7731 [USB] Specifies timeout for the initial 64-byte
7738 [USB] A list of quirk entries to augment the built-in
7741 VendorID:ProductID:Flags. The IDs are 4-digit hex
7742 numbers and Flags is a set of letters. Each letter
7743 will change the built-in quirk; setting it if it is
7744 clear and clearing it if it is set. The letters have
7748 a 255-byte read);
7752 Set-Interface requests);
7771 (bInterval-1).
7809 usb-storage.delay_use=
7816 usb-storage.quirks=
7818 override the built-in unusual_devs list. List
7821 and Product ID values (4-digit hex numbers) and
7822 Flags is a set of characters, each corresponding
7823 to a common usb-storage quirk flag as follows:
7837 240 sectors at a time, uas only);
7849 than 64 sectors = 32 KB at a time,
7861 t = NO_ATA_1X (don't allow ATA(12) and ATA(16)
7865 medium is write-protected).
7874 1 - undefined instruction events
7875 2 - system calls
7876 4 - invalid data aborts
7877 8 - SIGSEGV faults
7878 16 - SIGBUS faults
7887 vdso32= [X86] Control the 32-bit vDSO
7888 vdso32=1: enable 32-bit VDSO
7889 vdso32=0 or vdso32=2: disable 32-bit VDSO
7892 details. If CONFIG_COMPAT_VDSO is set, the default is
7899 dl_main: Assertion `(void *) ph->p_vaddr == _rtld_local._dl_sysinfo_dso' failed!
7906 If set to 1, on receiving an ACPI notify event
7909 the allocated input device. If set to 0, video driver
7930 vga= [BOOT,X86-32] Select a particular video mode
7932 Documentation/admin-guide/svga.rst.
7941 interface is meant to allow for selectively
7946 P Enable page structure init time poisoning
7947 - Disable all of the above options
7971 vsyscall= [X86-64,EARLY]
7974 code). Most statically-linked binaries and older
7998 see vga-softcursor.rst. Default: 2 = underline.
8003 This is a 16-member array composed of values
8004 ranging from 0-255.
8009 This is a 16-member array composed of values
8010 ranging from 0-255.
8015 This is a 16-member array composed of values
8016 ranging from 0-255.
8021 Set system-wide default UTF-8 mode for all tty's.
8022 Default is 1, i.e. UTF-8 mode is enabled for all
8027 Format=<-1|0|1>
8028 Set system-wide default for whether a cursor
8029 is shown on new VTs. Default is -1,
8034 vt.italic= [VT] Default color for italic text; 0-15.
8037 vt.underline= [VT] Default color for underlined text; 0-15.
8041 see Documentation/watchdog/watchdog-parameters.rst
8042 or other driver-specific files in the
8047 Set the hard lockup detector stall duration
8049 threshold is set to twice the value. A value of 0
8056 Format: <cpu-list>
8077 Per-cpu work items which run for longer than this
8080 them from noticeably delaying other per-cpu work
8083 If CONFIG_WQ_CPU_INTENSIVE_REPORT is set, the kernel
8089 If CONFIG_WQ_CPU_INTENSIVE_REPORT is set, the kernel
8098 Per-cpu workqueues are generally preferred because
8100 locality; unfortunately, per-cpu workqueues tend to
8103 Enabling this makes the per-cpu workqueues which
8117 Documentation/core-api/workqueue.rst.
8130 forces round-robin CPU selection to flush out
8138 on - Enable writecombine, use WUC for ioremap_wc()
8139 off - Disable writecombine, use SUC for ioremap_wc()
8141 x2apic_phys [X86-64,APIC,EARLY] Use x2apic physical mode instead of
8145 xen_512gb_limit [KNL,X86-64,XEN]
8155 ide-disks -- unplug primary master IDE devices
8156 aux-ide-disks -- unplug non-primary-master IDE devices
8157 nics -- unplug network devices
8158 all -- unplug all emulated devices (NICs and IDE disks)
8159 unnecessary -- unplugging emulated devices is
8162 never -- do not unplug even if version check succeeds
8176 Select whether to always use non-faulting (safe) MSR
8196 xen_timer_slop= [X86-64,XEN,EARLY]
8197 Set the timer slop (in nanoseconds) for the virtual Xen
8204 The time (in seconds) to wait before giving up to boot
8215 After which time (jiffies) the event handling loop
8221 preferred over the 2-level event handling, as it is
8238 xive.store-eoi=off [PPC]
8244 xhci-hcd.quirks [USB,KNL]