Lines Matching +refs:is +refs:pre +refs:merge
4 By default, unaccepted memory is accepted lazily to
6 some runtime overhead until all memory is eventually
7 accepted. In most cases the overhead is negligible.
62 This option is useful for developers to identify the
88 Some values produce so much output that the system is
100 is denied; legacy drivers trying to access reserved
102 lax: access to resources claimed by ACPI is allowed;
104 will bind successfully but a warning message is logged.
110 By default, this is disabled due to x86 early mapping
142 This feature is enabled by default.
171 of 2 which is mandated by ACPI 6) as the supported ACPI
193 is meaningless. This command is useful when one do not
197 1. 'acpi_osi=! acpi_osi="Windows 2000"' is equivalent
205 multiple times through kernel command line is also
216 through kernel command line is meaningful. But it may
219 is useful when one want to control the state of the
227 3. 'acpi_osi=! acpi_osi=!* acpi_osi="Windows 2000"' is
252 s3_beep is for debugging; it makes the PC's speaker beep
253 as soon as the kernel's real-mode entry point is called.
259 on docking. So the default behaviour is to allow resume
261 s4_hwsig option is enabled.
267 of _PTS is used by default).
271 on resume from S1/S3 (which is against the ACPI spec,
302 machines (where it is enabled by default) for a
313 main buffer is allocated. This is handy if debugging
322 parameter is present, the set of CPUs supporting 32-bit
323 EL0 is indicated by /sys/devices/system/cpu/aarch32_el0
336 devices. The IOMMU driver is not
365 (Default when IOMMU HW support is present.)
373 In this mode autonomous selection is disabled.
375 tries to match the same performance level if it is
422 bsp: External NMI is delivered only to CPU 0
425 none: External NMI is masked for all CPUs. This is
430 apicmaintimer. Useful when your PIT timer is totally
444 Default value is set via kernel config option.
496 0 | off - kernel audit is disabled and can not be
498 unset - kernel audit is initialized but disabled and
500 1 | on - kernel audit is initialized and partially
502 messages in RAM until it is fully enabled by the
511 behavior is to disable the BAU (i.e. bau=0).
543 O_EXCL. Default is Y and can be changed through the
558 Only works if CONFIG_BOOT_PRINTK_DELAY is enabled,
585 to fix known problems, but for some CPUs it is not
615 - if foo is an optional feature then the feature is
620 only cgroup_disable=memory is actually worthy}
649 Default value is set via a kernel config option.
652 Setting checkreqprot to 1 is deprecated.
682 those clocks in any way. This parameter is useful for
691 clocksource is not available, it defaults to PIT.
700 [all] jiffies (this is the base, fallback clocksource)
729 no replacement if the same CPU is chosen twice.
750 per-numa CMA altogether. And If this option is not
751 specified, the default value is 0.
754 which is located in node nid, if the allocation fails,
765 which is located in node nid, if the allocation fails,
770 when they are freed. This is used in CMO environments
796 the console buffer is full. In this case the
801 terminal emulator is active. If no 3270 terminal
802 emulator is used, this parameter has no effect.
811 the form "bbbbpnf", where "bbbb" is the baud rate,
812 "p" is parity ("n", "o", or "e"), "n" is number of
813 bits, and "f" is flow control ("r" for RTS or
814 omit it). Default is "9600n8".
837 is ready. The use of an earlycon parameter in addition to
848 MMIO inter-register address stride is either 8-bit
850 If none of [io|mmio|mmio16|mmio32], <addr> is assumed
853 the h/w is not re-initialized.
855 hvc<n> Use the hypervisor console device <n>. This is for
864 If the device connected to the port is not a TTY but a braille
867 For now, only VisioBraille is supported.
879 prefix. The format is similar to one used by syslog()
926 Default is enabled if CONFIG_HOTPLUG_PARALLEL=y. Otherwise
945 image. If '@offset' is omitted, then a suitable offset
946 is selected automatically.
954 in the running system. The syntax of range is
966 It will be ignored if crashkernel=X is specified.
969 When crashkernel=X,high is passed, kernel could allocate
973 enough extra low memory is needed to make sure DMA buffers
976 size is platform dependent.
984 It will be ignored when crashkernel=X,high is not used
985 or memory reserved is below 4G.
998 additional debug data is printed to the console
999 in case a hanging CPU is detected, and that
1000 CPU is pinged again in order to try to resolve
1036 [KNL,EARLY] When CONFIG_DEBUG_PAGEALLOC is set, this
1042 possible value is MAX_PAGE_ORDER/2. Setting this
1049 (basically when memory is written at bus level and the
1050 CPU MMU is bypassed) which are not detectable by
1055 [KNL,EARLY] When CONFIG_DEBUG_PAGEALLOC is set, this parameter
1056 enables the feature at boot time. By default, it is
1063 debugfs= [KNL,EARLY] This parameter enables what is exposed to
1068 Filesystem is not registered but kernel clients can
1070 its content. There is nothing to mount.
1071 off: Filesystem is not registered and clients
1074 This is equivalent of the runtime functionality if
1076 Default value is set in build-time with a kernel configuration.
1081 [HW] The size of the default HugeTLB page. This is
1083 APIs. In addition, this is the default hugetlb size
1106 indicates that the driver is running on unsupported
1120 capability is set.
1183 dma_debug=off If the kernel is compiled with DMA_API_DEBUG support,
1188 entries for DMA-API debugging code. One entry is
1191 architectural default is too low.
1202 Sampling (RFDS) vulnerability. RFDS is a CPU
1222 matches with all driver names. If * is specified, the
1243 Control how the dt_cpu_ftrs device-tree binding is
1248 or userspace, only those that the kernel is aware of.
1253 what data is available or for reverse-engineering.
1263 is useful for tracking down temporary early mappings
1268 When used with no options, the early console is
1276 supported option is baud rate. If baud rate is not
1287 MMIO inter-register address stride is either 8-bit
1289 If none of [io|mmio|mmio32|mmio32be], <addr> is assumed
1292 unspecified, the h/w is not initialized. 'uartclk' is
1293 the uart clock frequency; if unspecified, it is set
1301 yet supported. If 'mmio32' is specified, then only
1393 the framebuffer, pass the 'ram' option so that it is
1415 earlyprintk is useful when the kernel crashes before
1416 the normal console is initialized. It is not enabled by
1437 Interaction with the standard serial driver is not
1440 The VGA output is eventually overwritten by
1450 PCI device even when its classcode is not of the
1492 that is to be dynamically loaded by Linux. If there are
1504 This is designed to be used in conjunction with
1508 but can only be used if the backing tty is available
1538 Default value is 0.
1547 This option is obsoleted by the "netdev=" option, which
1559 memory initialization is disabled) so the boot process
1602 This is useful if you need tracing information from kernel
1603 boot up that is likely to be overridden by user space
1618 If no parameter is passed, ftrace will dump global
1622 its name is passed. Multiple instance dump is also
1640 tracer at boot up. function-list is a comma-separated
1654 function-list is a comma-separated list of functions
1660 function-list. This list is a comma-separated list of
1665 [FTRACE] Used with the function graph tracer. This is
1672 consumer/supplier relationships. This feature is
1723 Gather Data Sampling is a hardware vulnerability which
1727 This issue is mitigated by default in updated microcode.
1734 mitigation is present. Known to cause crashes in
1742 kernel modules is saved and remains accessible via
1743 debugfs, even when the module is unloaded/reloaded.
1744 When zero, profiling data is discarded and associated
1759 primary GPT is corrupted, it enables the backup/alternate
1782 hardening is enabled for this boot. Hardened
1783 usercopy checking is used to protect the kernel
1788 The default is determined by
1847 possible to ensure the hostname is correctly set before
1869 If this is the first HugeTLB parameter on the command
1878 [HW,EARLY] The size of the HugeTLB pages. This is
1892 The default value is 25% of the available hardware threads.
1904 boot-time allocation of gigantic hugepages is skipped.
1910 This option does nothing if hugetlb_cma= is not also
1916 Control if HugeTLB Vmemmap Optimization (HVO) is enabled.
1925 the default is on.
1928 memory block itself when memory_hotplug.memmap_on_memory is
1930 feature is enabled. Other vmemmap pages not allocated from
1938 hung task is detected. The default value is controlled
1961 or register an additional I2C bus that is not
1975 Where <val> is one of:
1991 (disabled by default, and as a pre-condition
2022 [DRM] Invert the sense of the variable that is used to
2026 to maximum brightness. If this parameter is set to 0
2028 is set to 1, a brightness value of 0 sets the backlight
2059 idle=halt: Halt is forced to be used for CPU idle.
2067 support for the idxd driver. By default it is set to
2073 for the device. By default it is set to false (0).
2097 if binary mode is unsupported by the FPU.
2099 The FPU emulator is always able to support both NaN
2100 encodings, so if no FPU hardware is present or it has
2144 The list of supported hash algorithms is defined
2191 If left unspecified, ahash usage is disabled.
2207 microcode is also required for a fix in IBPB.
2213 vmexit: Only deploy mitigation if CPU is affected by
2215 stuff: Deploy RSB-fill mitigation when retpoline is
2228 for working out where the kernel is dying during
2239 image is unpacked asynchronously, concurrently
2250 load the initrd. If an initrd is compiled in or
2254 Default is 0, 0
2286 By default, gfx is mapped as normal device. If a gfx
2287 device has a dedicated DMAR unit, the DMAR unit is
2308 mapping is enabled.
2356 then this feature is turned on by default.
2385 it is not actually needed (e.g. because < 3 GB
2389 Don't force hardware IOMMU usage when it is not
2395 merge
2430 merge
2499 enforce (1) mode. The default is enforce.
2505 an audit event when a binary is allowed. The default
2506 is 0.
2509 The argument is a cpu list, as described above.
2516 exposed by the device tree is too small.
2532 When an interrupt is not handled search all handlers
2537 When an interrupt is not handled search all handlers
2555 offloaded. This is equivalent to the nohz_full parameter.
2557 A residual 1Hz tick is offloaded to workqueues, which you
2570 is irreversible: it's not possible to bring back a CPU to
2579 <cpu number> begins at 0 and the maximum value is
2586 CPUs. The affinity of managed interrupts is
2590 This isolation is best effort and only effective
2606 The format of <cpu-list> is described above.
2613 By default, PCI segment is 0, and can be omitted.
2631 By default, PCI segment is 0, and can be omitted.
2649 By default, PCI segment is 0, and can be omitted.
2657 * To map UART-HID:UID AMD0020:0 to PCI segment is 0,
2674 Do not unregister boot console at start. This is only
2685 amount is spread evenly throughout all nodes in the
2686 system as ZONE_NORMAL. The remaining memory is used for
2688 event, a node is too small to have both ZONE_NORMAL and
2692 ZONE_MOVABLE is used for the allocation of pages that
2698 It is possible to specify the exact amount of memory in
2701 option is specified, mirrored (reliable) memory is used
2702 for non-movable allocations and remaining memory is used
2708 The controller # is the number of the ehci usb debug
2709 port as it is probed via PCI. The poll interval is
2710 optional and is the number seconds in between
2731 until the normal console is registered. Intended to
2753 the default is off.
2757 The probe-list is a semicolon delimited list of probe
2758 definitions. Each definition is same as kprobe_events
2778 Default is 1 (enabled)
2781 Default is 0 (don't ignore, but inject #GP)
2797 KVM_DIRTY_LOG_INITIALLY_SET is enabled or disabled. If
2799 split when dirty logging is enabled on that memslot. If
2804 Eager page splitting is only supported when kvm.tdp_mmu=Y.
2806 Default is Y (on).
2810 when KVM is loaded, and disable virtualization when KVM
2811 is unloaded (if KVM is built as a module).
2821 "cost" of enabling virtualization when KVM is loaded,
2822 is that doing so may interfere with using out-of-tree
2826 Default is false (don't support).
2836 Default is 'auto'.
2838 If the software workaround is enabled for the host,
2844 the value is N KVM will zap 1/Nth of the 4KiB pages every
2845 period (see below). The default is 60.
2849 back to huge pages. If the value is a non-zero N, KVM will
2851 If the value is 0 (the default), KVM will pick a period based
2852 on the ratio, such that a page is zapped after 1 hour on average.
2855 KVM/SVM. Default is 1 (enabled).
2858 a.k.a. Two-Dimensional Page Tables. Default is 1
2871 protected: Mode with support for guests whose state is
2884 "nested" is experimental and should be used with
2930 a.k.a. Two-Dimensional Page Tables. Default is 1
2937 as guest state is never invalid for unrestricted
2940 Default is 1 (enabled).
2944 (TPR shadow). Default is 1 (enabled). Disable by KVM if
2949 KVM/VMX. Default is 1 (enabled).
2954 is 1 (enabled). Disable by KVM if EPT is disabled or
2967 Default is cond (do L1 cache flush in specific instances)
2970 Identification feature (tagged TLBs). Default is 1
2994 The kernel PTE inversion protection is unconditionally
3004 sysfs interface is still possible after
3006 when the first VM is started in a
3014 (i.e. sysfs control of SMT is disabled.)
3022 sysfs interface is still possible after
3024 when the first VM is started in a
3034 sysfs interface is still possible after
3036 when the first VM is started in a
3042 warn when a VM is started in a potentially
3052 Default is 'flush'.
3087 libata.force= [LIBATA] Force configurations. The format is a comma-
3088 separated list of "[ID:]VAL" where ID is PORT[.DEVICE].
3091 printed on console by libata. If the whole ID part is
3096 If only DEVICE is omitted, the parameter applies to
3104 as there is no ambiguity, shortcut notation is allowed.
3109 Any ID with matching PORT is used.
3114 udma[/][16,25,33,44,66,100,133] notation is also
3178 the same attribute, the last one is used.
3219 there is a high probability of an RCU grace period
3230 locktorture is to exercise, up to a limit of 8
3232 Note that this parameter is ineffective on types
3262 long priority boosting is exercised. This is
3276 is useful for hands-off automated testing.
3307 0 (KERN_EMERG) system is unusable
3319 minimal size. The minimal size is defined by
3321 is also CONFIG_LOG_CPU_MAX_BUF_SHIFT config
3328 kernel log messages and is useful when debugging
3344 an IEEE 1284-compliant printer is attached; if
3353 autodetection and see what value is printed. Note that
3355 which is likely to cause problems if your CPUs need
3378 While n=0 is a special case, it is equivalent to "nosmp",
3382 (loop.max_loop) unconditionally pre-created at init time. The default
3383 number is configured by BLK_DEV_LOOP_MIN_COUNT. Instead
3397 Intel processor supports. Usually this disablement is
3399 hardware is misbehaving.
3417 Usually this disablement is not recommended, however
3418 if there is an agent checking/clearing corrected
3435 events that result in a reboot. On Intel systems it is
3457 Everything else is in sysfs now.
3494 Not specifying this option is equivalent to
3507 2 when the kernel is not able to see the whole system memory;
3508 3 memory that lies after 'mem=' boundary is excluded from
3513 high memory is not affected.
3525 if system memory of hypervisor is not sufficient.
3546 onlining policy. If not specified, the default value is
3560 Region of memory to be used is from ss to ss+nn.
3561 If @ss[KMG] is omitted, it is equivalent to mem=nn[KMG],
3570 Region of memory to be marked is from ss to ss+nn.
3574 Region of memory to be reserved is from ss to ss+nn.
3587 and is NVDIMM or ADR memory.
3591 from <oldtype> to <newtype>. If "-<oldtype>" is left
3593 even if previously unavailable. If "+<newtype>" is left
3627 if hugetlb_free_vmemmap is enabled) from the
3631 This feature is disabled by default because it
3638 the feature is not effective.
3667 version 0.98 is known to be affected, 0.99 fixes the
3681 0 - The attached screen is the 3.5" TFT
3682 1 - The attached screen is the 7" TFT
3683 2 - The VGA Shield is attached (1024x768)
3689 LED. This parameter is not necessary when using the
3693 touchscreen support is not enabled in the mainstream
3700 CPU vulnerabilities. This is a set of curated,
3701 arch-independent options, each of which is an
3704 Note, "mitigations" is supported if and only if the
3742 enabled, even if it's vulnerable. This is for
3750 if needed. This is for users who always want to
3759 [KNL,EARLY] When CONFIG_DEBUG_MEMORY_INIT is set, this
3763 log everything. Information is printed at KERN_DEBUG
3770 Processor MMIO Stale Data is a class of
3775 is to clear the affected CPU buffers.
3794 Not specifying this option is equivalent to
3801 If no <bool> value is specified or if the value
3802 specified is not a valid <bool>, enable asynchronous
3811 is documented under <module>.async_probe. When both
3817 [KNL] When CONFIG_MODULE_DEBUG_AUTOLOAD_DUPS is set,
3820 if MODULE_DEBUG_AUTOLOAD_DUPS_TRACE is set, WARN_ON()s
3823 [KNL] When CONFIG_MODULE_SIG is set, this means that
3825 Note that if CONFIG_MODULE_SIG_FORCE is set, that
3826 is always true, so this option does nothing.
3844 This parameter is the complement to kernelcore=, it
3846 allocations. If both kernelcore and movablecore is
3849 own is specified, the administrator must be careful
3851 is not too small.
3877 used for mtrr cleanup. It is largest continuous chunk
3881 Used for mtrr cleanup. It is granularity of mtrr block.
3882 Default is 1.
3890 Used for mtrr cleanup. It is spare mtrr entries number.
3901 Note that mem_start is often overloaded to mean
3903 This usage is only documented in each driver source
3915 Default value is 0.
3918 [NFS] sets the pathname to the program which is used
3923 update a cache entry is deemed to have failed.
3938 Only applies if the softerr mount option is enabled,
3939 and the specified value is >= 0.
3946 The default is to return 64-bit inode numbers.
3964 Note that there is little point in setting this
3971 numeric uids/gids if the mount is using the
3972 'sec=sys' security flavour. In effect it is
3983 their nfs_client_id4 string. This is typically a
3984 UUID that is generated at system install time.
4003 The default is to send the implementation identification
4011 whatever value is the default set by the layout
4017 server-to-server copies for which this server is
4024 and gids from such clients. This is intended to ease
4049 when a NMI is triggered.
4059 When panic is specified, panic when an NMI watchdog
4061 watchdog, if CONFIG_BOOTPARAM_HARDLOCKUP_PANIC is set)
4064 This is useful when you use a panic=... timeout and
4072 is present.
4096 of the system is being put to sleep (ie, while
4098 not work reliably with all consoles, but is known
4124 is to be setuid root or executed by root.
4139 unhashed. By default, when a pointer is printed via %p
4140 format string, that pointer is "hashed", i.e. obscured
4141 by hashing the pointer value. This is a security feature
4145 compared. However, if this command-line option is
4156 to be effective. This is useful on platforms where the
4159 the impact of the sleep instructions. This is also
4173 The argument is a cpu list, as described above.
4202 When CONFIG_RANDOMIZE_BASE is set, this disables
4223 not load if they could possibly displace the pre-
4267 This is required for the Braillex ib80-piezo Braille
4274 even if it is supported by processor.
4278 even if it is supported by processor.
4311 is computed, but won't influence scheduler behaviour
4327 without any limit and this data is stored in memory,
4331 is only available when CONFIG_PROC_VMCORE_DEVICE_DUMP
4332 is set.
4356 performance of saving the states is degraded because
4374 variables need be pre-allocated for later physical cpu
4418 command is not properly ACKed, override the length
4420 waiting for the ACK, so if this is set too high
4439 Always panic on oopses. Default is to just kill the
4440 process, but there is a small probability of
4451 This parameter is only available if CONFIG_SHUFFLE_PAGE_ALLOCATOR=y.
4455 each page is disabled in default. With this switch,
4469 reporting is disabled when it exceeds MAX_PAGE_ORDER.
4481 that will cause the kernel to panic when add_taint() is
4499 bit 3: print locks info if CONFIG_LOCKDEP is on
4509 parkbd.port= [HW] Parallel port number the keyboard adapter is
4510 connected to, default is 0.
4513 0 for XT, 1 for AT (default is AT).
4519 IRQ/DMA settings detected (the default is to
4525 (to avoid using a FIFO even if it is detected).
4532 a specific mode. This is necessary on Pegasos
4546 Set to non-zero if a chip is present that snoops speed
4564 for the respective channel. Bit 0 is for the first
4565 legacy channel handled by this driver, bit 1 is for
4570 with the sequence. By default IORDY is allowed across
4589 Bit 0 is for mode 0, bit 1 is for mode 1, and so on.
4604 corresponding bits in the mask to 1. Bit 0 is for
4617 value given is the I/O port to use (typically 0x1b0).
4624 the use of the respective PIO modes. Bit 0 is for
4625 mode 0, bit 1 is for mode 1, and so on. Mode 0 only
4630 the specified number of seconds. This is to be used if
4646 if new hardware is inserted, if motherboard
4649 domain is left unspecified, it is
4653 address (this is more robust against
4673 Mechanism 2 (IO port 0xCF8 is an 8-bit port for
4675 bus number. The config space is then accessed
4679 noaer [PCIE] If the PCIEAER kernel config parameter is
4689 nomsi [MSI] If the PCI_MSI kernel config parameter is
4708 this option if the kernel is unable to allocate
4726 by the BIOS) if it is outside the
4729 useful if the kernel is unable to find your
4736 in the BIOS $PIR table. This is needed on
4740 IRQ routing is enabled.
4745 is enabled by default. If you need to use this,
4750 PCI host bridge windows. This is a workaround
4755 bridge windows. This is the default on modern
4759 This is normally done in pci_enable_device(),
4760 so this option is a temporary workaround
4767 is read. But various workarounds are disabled
4770 This sorting is done to get a device
4783 every device is guaranteed to support. This
4788 cbiosize=nn[KMG] The fixed amount of bus space which is
4790 The default value is 256 bytes.
4791 cbmemsize=nn[KMG] The fixed amount of bus space which is
4793 window. The default value is 64 megabytes.
4799 specify the device is described above.
4800 If <order of align> is not specified,
4801 PAGE_SIZE is used as alignment.
4813 bios: Use BIOS/firmware settings. This is the
4817 hpiosize=nn[KMG] The fixed amount of bus space which is
4819 Default size is 256 bytes.
4820 hpmmiosize=nn[KMG] The fixed amount of bus space which is
4822 Default size is 2 megabytes.
4823 hpmmioprefsize=nn[KMG] The fixed amount of bus space which is
4825 Default size is 2 megabytes.
4826 hpmemsize=nn[KMG] The fixed amount of bus space which is
4829 Default size is 2 megabytes.
4832 Default is 1.
4849 Adding the window is slightly risky (it may
4868 unchanged based on what is specified in
4871 ACS Flags is defined as follows:
4898 is enabled, this kernel boot option can be used
4932 even if no driver has claimed them. This is useful
4946 allocator. This parameter is primarily for debugging
4961 This option takes over the PMU facility, so it is no
4963 PMU counters by setting MMCR0 to 0 (the FC bit is
4964 cleared). If a number is given, then MMCR1 is set to
4999 Default is 21.
5019 There is some performance impact when enabling this.
5036 preemption will be forced. One preemption is when the
5060 or lockdep-detected issues (only if lock debug is on).
5062 serial console, keeping this 0 is a good choice
5065 default: 0 (auto_verbose is enabled)
5093 If not specified, default is the CONFIG_PROC_MEM_* choice.
5118 Layout Randomization is disabled.
5147 auto - kernel detects whether your CPU model is
5150 Not specifying this option is equivalent to pti=auto.
5187 cross-syscall address exposures. This is only
5191 Default is CONFIG_RANDOMIZE_KSTACK_OFFSET_DEFAULT.
5200 [KNL] The optional argument is a cpu list,
5208 kthreads created for that purpose, where "x" is
5211 "N" is the CPU number. This reduces OS jitter on
5216 If a cpulist is passed as an argument, the specified
5217 list of CPUs is set to no-callback mode from boot.
5244 there is an ongoing too-long CSD-lock wait.
5247 Request a call to rcu_barrier(). This is
5251 is fully active, this will error out with EAGAIN.
5255 out at early boot. This is used for diagnostic
5268 RCU grace-period pre-initialization, that is,
5275 Units are jiffies, minimum value is zero,
5276 and maximum value is HZ.
5281 value is one, and maximum value is HZ.
5299 kthreads (rcuc/N). This value is also used for
5302 rcu_preempt, and rcu_sched). If RCU_BOOST is
5303 set, valid values are 1-99 and the default is 1
5305 RCU_BOOST is not set, valid values are 0-99 and
5306 the default is zero (non-realtime operation).
5307 When RCU_NOCB_CPU is set, also adjust the
5319 a single jiffy, RCU pre-queues the callbacks into
5321 many" is supplied by this kernel boot parameter.
5333 batch limiting is disabled.
5337 batch limiting is re-enabled.
5351 of permitted values is in the range 0:100000.
5370 tree. This is used by rcutorture, and might
5384 maintained per one CPU. Object size is equal
5408 By default, this limit is checked only once
5417 catching RCU pointer leaks, that is, buggy use
5429 value, meaning that RCU_SOFTIRQ is used by default.
5445 use a call_rcu[_hurry]() path. Please note, this is for a
5453 Default is 0.
5472 this parameter is to delay the start of the
5518 N, where N is the number of CPUs. A value
5519 "n" less than -1 selects N-n+1, where N is again
5528 N, where N is the number of CPUs
5535 complete. This is useful for hands-off automated
5672 are zero, rcutorture acts as if is interpreted
5682 This can of course result in splats, and is
5705 N-1, where N is the number of CPUs. A value
5706 "n" less than -1 selects N-n-2, where N is again
5732 FIFO real-time task. This delay is mediated
5733 by an hrtimer and is further fuzzed to avoid
5739 is spawned.
5747 If there is more than one bit set, the readers
5750 0x1 bit is normal readers, 0x2 NMI-safe readers,
5760 is useful for hands-off automated testing.
5797 kthread is starved first, then the CPU.
5819 that is, no holdoff.
5850 during early boot, that is, during the time
5851 before the init task is spawned.
5855 The value is in seconds and the maximum allowed
5856 value is 300 seconds.
5860 messages. The value is in milliseconds
5861 and the maximum allowed value is 21000
5862 milliseconds. Please note that this value is
5898 Once boot has completed (that is, after
5905 it to the value one, that is, converting any
5915 occurs when rcupdate.rcu_task_enqueue_lim is
5923 when rcupdate.rcu_task_enqueue_lim is set to
5930 dynamically) adjusted. This parameter is intended
5961 RCU tasks grace period. This value is clamped
5964 message is printed 10 seconds into the grace
5980 of zero will disable batching. Batching is
5988 disable batching. Batching is always disabled
6007 Turn on/off individual RDT features. List is:
6019 Where reboot_mode is one of warm (soft) or cold (hard) or gpio
6022 reboot_type is one of bios, acpi, kbd, triple, efi, or pci,
6023 reboot_force is either force or not specified,
6024 reboot_cpu is s[mp]#### with #### being the processor
6028 Use the ACPI RESET_REG in the FADT. If ACPI is not
6042 think the quirk is in error (e.g. you have newer BIOS,
6048 Use efi reset_system runtime service. If EFI is not
6071 the memory check. Disadvantage is that not all
6078 this parameter is to delay the start of the
6085 is negated and multiplied by nr_cpu_ids, while
6098 selects N, where N is roughly 75% of the number
6099 of CPUs. A value of zero is an interesting choice.
6102 Set number of runs, each of which is dumped onto
6115 refscale is built into the kernel and to 0 (leave
6116 it running) when refscale is built as a module.
6124 print every Nth verbose statement, where N is the value
6141 them. If <base> is less than 0x10000, the region
6142 is assumed to be I/O ports; otherwise it is memory.
6147 other subsystems can use to access it. This is typically
6150 soft reboots. Note, it is not guaranteed to be the same
6157 that the contents of the physical memory is from a previous
6161 The format is size:align:label for example, to request
6181 given by "resume=" at which the swap header is located,
6201 sibling threads. For that reason, STIBP is used on pro-
6217 when STIBP is not available. This is
6224 is not available. This is the alternative for
6230 Not specifying this option is equivalent to retbleed=auto.
6234 etc. communication is blocked by default.
6249 When CONFIG_RISCV_ISA_FALLBACK is not enabled, permit
6306 in an IOTLB flush. Default is lazy flushing before
6307 reuse, which is faster. Deprecated, equivalent to
6314 The default is 1 meaning that one can concurrently use
6315 as many DMA addresses as physical memory is installed,
6330 but is useful for debugging and performance tuning.
6347 Default is 0.
6376 is the default) disables CPU-hotplug operations.
6463 Default value is 1.
6483 number of local apics being dumped. Also it is possible
6487 apic=verbose is specified.
6508 kernel is built without CONFIG_SLAB_MERGE_DEFAULT.
6529 necessary if there is some reason to distinguish
6543 in the slab allocator. The default is for memory
6545 a new folio is needed or a partial folio is
6559 for a CPU to release the CSD lock. This is
6597 to panic the machine when a soft-lockup occurs. It is
6599 and CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC, which is the
6620 ONLY. On such systems, the host kernel is
6634 auto - kernel detects whether your CPU model is
6662 Not specifying this option is equivalent to
6676 prctl - Indirect branch speculation is enabled,
6679 is inherited on fork.
6682 - Like "prctl" above, but only STIBP is
6683 controlled per thread. IBPB is issued
6693 - Like "seccomp" above, but only STIBP is
6694 controlled per thread. IBPB is issued
6703 Not specifying this option is equivalent to
6726 is that such stores are unlikely and that they can
6736 Bypass optimization is used.
6745 CPU is not vulnerable, "off" is selected. If the
6746 CPU is vulnerable the default mitigation is
6749 via prctl. Speculative Store Bypass is enabled
6751 is inherited on fork.
6766 Not specifying this option is equivalent to
6772 When enabled (and if hardware support is present), atomic
6782 exception or the #DB exception. This mode is
6785 behavior is by #AC if both features are
6790 exception. Default behavior is by #AC if
6801 If an #AC exception is hit in the kernel or in
6806 #DB exception for bus lock is triggered only when
6817 By default, this issue is mitigated by
6835 bits of srcutree.convert_to_big is equal to 3
6841 form, that is, with an rcu_node tree:
6915 is in page units and it defines how many pages prior
6918 mapping. Default value is 256 pages.
6923 consumed by the stack hash table. By default this is set
6931 will trace at boot up. function-list is a comma-separated
6935 and the stacktrace above is not needed.
6985 The default value is 0 (no limit).
6994 NFS server is running.
7017 is set. Default value is 5.
7053 Default value is 8192 or 16384 depending on total
7054 ram pages. This is used to specify the TCP metrics
7066 The system is woken from this state using a
7095 state is one of "always", "madvise", "never" or "inherit".
7109 internal shmem mount. <policy> is one of policies available
7122 Default is on.
7148 where TPM is heavily utilized by IMA, thus protection
7150 machines are deployed is by other means guarded.
7163 for the FIFO interface. By default it is set to false
7170 tracing ring buffer. This is useful for early boot up
7191 When tp_printk (above) is set, it can cause a lot of noise
7226 to facilitate early boot debugging. The event-list is a
7244 Events can be enabled at the time the instance is created
7249 Note, the "<system*>:" portion is optional if the event is
7254 will enable the "sched_switch" event (note, the "sched:" is optional, and
7258 Flags can be added to the instance to modify its behavior when it is
7263 traceoff - Have the tracing instance tracing disabled after it is created.
7277 memory at 0x284500000 that is 12Megs. The per CPU buffers of that
7291 if the layout is not the same as the previous kernel.
7293 If the ring buffer is used for persistent bootups and has events enabled,
7294 it is recommend to disable tracing so that events from a previous boot do not
7301 is set up to not wipe memory. For instance, CONFIG_RESET_ATTACK_MITIGATION
7303 This is just one of many ways that can clear memory. Make sure your system
7313 The option-list is a comma delimited list of options
7332 The format is is "trace_trigger=<event>.<trigger>[ if <filter>],..."
7341 event is "2" (TASK_UNINTERUPTIBLE).
7347 [FTRACE] Sometimes tracing is used to debug issues
7350 disable tracing after the boot is finished, otherwise
7357 warning is hit. This turns off "tracing_on". Tracing can
7361 This option is useful, as it disables the trace before
7362 the WARNING dump is called, which prevents the trace to
7401 first trust source as a backend which is initialized
7411 If not specified, "default" is used. In this case,
7412 the RNG's choice is left to each individual trust source.
7415 This is intended to be used in combination with
7420 This is intended to be used in combination with
7422 blob key is all zeros. This is helpful for situations where
7423 having this key zero'ed is acceptable. E.g. in testing
7435 platforms where RDTSC is slow and this accounting
7447 Warn if the difference is more than 500 ppm.
7457 procedure is not reliable, such as on overclocked systems
7482 auto - Disable TSX if X86_BUG_TAA is present,
7485 Not specifying this option is equivalent to tsx=off.
7509 if TSX is enabled.
7512 vulnerable CPUs. If TSX is disabled, SMT
7513 is not disabled because CPU is not
7522 Not specifying this option is equivalent to
7524 and deploy MDS mitigation, TAA mitigation is not
7557 is useful for testing alternative code paths and to skip
7565 is useful for testing alternative code paths and to skip
7587 is the time required before an idle device will be
7588 autosuspended. Devices for which the delay is set
7625 numbers and Flags is a set of letters. Each letter
7626 will change the built-in quirk; setting it if it is
7627 clear and clearing it if it is set. The letters have
7693 [UMS] The delay in seconds before a new device is
7705 Flags is a set of characters, each corresponding
7723 sector if the number is odd);
7738 p = WRITE_CACHE (the device cache is ON
7748 medium is write-protected).
7765 On X86_32, this is an alias for vdso32=. Otherwise:
7775 details. If CONFIG_COMPAT_VDSO is set, the default is
7776 vdso32=0; otherwise, the default is vdso32=1.
7778 For compatibility with older kernels, vdso32=2 is an
7817 This is actually a boot loader parameter; the value is
7824 interface is meant to allow for selectively
7863 reasonably safely. The vsyscall page is
7868 page is not readable.
7886 This is a 16-member array composed of values
7892 This is a 16-member array composed of values
7898 This is a 16-member array composed of values
7905 Default is 1, i.e. UTF-8 mode is enabled for all
7912 is shown on new VTs. Default is -1,
7932 threshold is set to twice the value. A value of 0
7933 disables both lockup detectors. Default is 10
7944 If CONFIG_WQ_WATCHDOG is configured, workqueue can
7948 duration in seconds. The default value is 30 and
7953 Panic when workqueue stall is detected by
7957 The default is 0, which disables the panic on stall.
7964 items. Default is 10000 (10ms).
7966 If CONFIG_WQ_CPU_INTENSIVE_REPORT is set, the kernel
7972 If CONFIG_WQ_CPU_INTENSIVE_REPORT is set, the kernel
7978 The default is 4 times. 0 disables the warning.
7992 The default value of this parameter is determined by
7998 "numa" and "system". Default is "cache". For more
8010 on the local CPU. This guarantee is no longer true
8011 and while local CPU is still preferred work items
8030 to use only up to 512 GB of RAM. The reason to do so is
8042 unnecessary -- unplugging emulated devices is
8061 default value is controlled by CONFIG_XEN_PV_MSR_SAFE.
8066 This option is obsoleted by the "nopv" option, which
8081 timers (default is 100000). This adjusts the minimum
8091 max. Default is 180.
8095 storms (jiffies). Default is 10.
8099 should start to delay EOI handling. Default is 2.
8103 even if available. Normally fifo event handling is
8104 preferred over the 2-level event handling, as it is
8105 fairer and the number of possible event channels is
8106 much higher. Default is on (use fifo events).
8124 is active. This option allows the XIVE driver to use
8134 Controls if xmon debugger is enabled. Default is off.
8135 Passing only "xmon" is equivalent to "xmon=early".
8137 debugger is called from setup_arch().
8139 is only called on a kernel crash. Default mode,
8140 i.e. either "ro" or "rw" mode, is controlled
8143 is called only on a kernel crash, mode is write,
8149 off xmon is disabled.