Commit | Line | Data |
---|---|---|
b10d79f7 | 1 | acpi= [HW,ACPI,X86,ARM64] |
03d926f8 | 2 | Advanced Configuration and Power Interface |
6a1f5471 | 3 | Format: { force | on | off | strict | noirq | rsdt | |
e58d154b | 4 | copy_dsdt } |
1da177e4 | 5 | force -- enable ACPI if default was off |
6a1f5471 | 6 | on -- enable ACPI but allow fallback to DT [arm64] |
1da177e4 LT |
7 | off -- disable ACPI if default was on |
8 | noirq -- do not use ACPI for IRQ routing | |
a9913044 | 9 | strict -- Be less tolerant of platforms that are not |
1da177e4 | 10 | strictly ACPI specification compliant. |
237889bf | 11 | rsdt -- prefer RSDT over (default) XSDT |
aa2110cb | 12 | copy_dsdt -- copy DSDT to memory |
6a1f5471 AB |
13 | For ARM64, ONLY "acpi=off", "acpi=on" or "acpi=force" |
14 | are available | |
1da177e4 | 15 | |
151f4e2b | 16 | See also Documentation/power/runtime_pm.rst, pci=noacpi |
1da177e4 | 17 | |
a1fdcc0d LB |
18 | acpi_apic_instance= [ACPI, IOAPIC] |
19 | Format: <int> | |
20 | 2: use 2nd APIC table, if available | |
21 | 1,0: use 1st APIC table | |
4e381a4f | 22 | default: 0 |
a1fdcc0d | 23 | |
c3d6de69 | 24 | acpi_backlight= [HW,ACPI] |
5fd769c2 RD |
25 | { vendor | video | native | none } |
26 | If set to vendor, prefer vendor-specific driver | |
c3d6de69 TR |
27 | (e.g. thinkpad_acpi, sony_acpi, etc.) instead |
28 | of the ACPI video.ko driver. | |
5fd769c2 RD |
29 | If set to video, use the ACPI video.ko driver. |
30 | If set to native, use the device's native backlight mode. | |
31 | If set to none, disable the ACPI backlight interface. | |
c3d6de69 | 32 | |
b2ca5dae CIK |
33 | acpi_force_32bit_fadt_addr |
34 | force FADT to use 32 bit addresses rather than the | |
35 | 64 bit X_* addresses. Some firmware have broken 64 | |
36 | bit addresses for force ACPI ignore these and use | |
37 | the older legacy 32 bit addresses. | |
38 | ||
ef69449b DB |
39 | acpica_no_return_repair [HW, ACPI] |
40 | Disable AML predefined validation mechanism | |
41 | This mechanism can repair the evaluation result to make | |
42 | the return objects more ACPI specification compliant. | |
43 | This option is useful for developers to identify the | |
44 | root cause of an AML interpreter issue when the issue | |
45 | has something to do with the repair mechanism. | |
46 | ||
a0d84a92 BH |
47 | acpi.debug_layer= [HW,ACPI,ACPI_DEBUG] |
48 | acpi.debug_level= [HW,ACPI,ACPI_DEBUG] | |
1da177e4 | 49 | Format: <int> |
a0d84a92 BH |
50 | CONFIG_ACPI_DEBUG must be enabled to produce any ACPI |
51 | debug output. Bits in debug_layer correspond to a | |
52 | _COMPONENT in an ACPI source file, e.g., | |
53 | #define _COMPONENT ACPI_PCI_COMPONENT | |
54 | Bits in debug_level correspond to a level in | |
55 | ACPI_DEBUG_PRINT statements, e.g., | |
56 | ACPI_DEBUG_PRINT((ACPI_DB_INFO, ... | |
e76f4276 | 57 | The debug_level mask defaults to "info". See |
cb1aaebe | 58 | Documentation/firmware-guide/acpi/debug.rst for more information about |
e76f4276 | 59 | debug layers and levels. |
a0d84a92 | 60 | |
e76f4276 BH |
61 | Enable processor driver info messages: |
62 | acpi.debug_layer=0x20000000 | |
63 | Enable PCI/PCI interrupt routing info messages: | |
64 | acpi.debug_layer=0x400000 | |
a0d84a92 BH |
65 | Enable AML "Debug" output, i.e., stores to the Debug |
66 | object while interpreting AML: | |
67 | acpi.debug_layer=0xffffffff acpi.debug_level=0x2 | |
a0d84a92 BH |
68 | Enable all messages related to ACPI hardware: |
69 | acpi.debug_layer=0x2 acpi.debug_level=0xffffffff | |
70 | ||
71 | Some values produce so much output that the system is | |
72 | unusable. The "log_buf_len" parameter may be useful | |
73 | if you need to capture more output. | |
f989106c | 74 | |
ef69449b DB |
75 | acpi_enforce_resources= [ACPI] |
76 | { strict | lax | no } | |
77 | Check for resource conflicts between native drivers | |
78 | and ACPI OperationRegions (SystemIO and SystemMemory | |
79 | only). IO ports and memory declared in ACPI might be | |
80 | used by the ACPI subsystem in arbitrary AML code and | |
81 | can interfere with legacy drivers. | |
82 | strict (default): access to resources claimed by ACPI | |
83 | is denied; legacy drivers trying to access reserved | |
84 | resources will fail to bind to device using them. | |
85 | lax: access to resources claimed by ACPI is allowed; | |
86 | legacy drivers trying to access reserved resources | |
87 | will bind successfully but a warning message is logged. | |
88 | no: ACPI OperationRegions are not marked as reserved, | |
89 | no further checks are performed. | |
90 | ||
4fc0a7e8 LZ |
91 | acpi_force_table_verification [HW,ACPI] |
92 | Enable table checksum verification during early stage. | |
93 | By default, this is disabled due to x86 early mapping | |
94 | size limitation. | |
95 | ||
0cb55ad2 RD |
96 | acpi_irq_balance [HW,ACPI] |
97 | ACPI will balance active IRQs | |
98 | default in APIC mode | |
99 | ||
100 | acpi_irq_nobalance [HW,ACPI] | |
101 | ACPI will not move active IRQs (default) | |
102 | default in PIC mode | |
103 | ||
104 | acpi_irq_isa= [HW,ACPI] If irq_balance, mark listed IRQs used by ISA | |
105 | Format: <irq>,<irq>... | |
106 | ||
107 | acpi_irq_pci= [HW,ACPI] If irq_balance, clear listed IRQs for | |
108 | use by PCI | |
109 | Format: <irq>,<irq>... | |
110 | ||
6dddd7a7 | 111 | acpi_mask_gpe= [HW,ACPI] |
9c4aa1ee LZ |
112 | Due to the existence of _Lxx/_Exx, some GPEs triggered |
113 | by unsupported hardware/firmware features can result in | |
6dddd7a7 TB |
114 | GPE floodings that cannot be automatically disabled by |
115 | the GPE dispatcher. | |
9c4aa1ee LZ |
116 | This facility can be used to prevent such uncontrolled |
117 | GPE floodings. | |
a7583e72 | 118 | Format: <byte> |
9c4aa1ee | 119 | |
08e1d7c0 LZ |
120 | acpi_no_auto_serialize [HW,ACPI] |
121 | Disable auto-serialization of AML methods | |
22b5afce BM |
122 | AML control methods that contain the opcodes to create |
123 | named objects will be marked as "Serialized" by the | |
124 | auto-serialization feature. | |
08e1d7c0 LZ |
125 | This feature is enabled by default. |
126 | This option allows to turn off the feature. | |
22b5afce | 127 | |
ef69449b DB |
128 | acpi_no_memhotplug [ACPI] Disable memory hotplug. Useful for kdump |
129 | kernels. | |
130 | ||
a94e88cd LZ |
131 | acpi_no_static_ssdt [HW,ACPI] |
132 | Disable installation of static SSDTs at early boot time | |
133 | By default, SSDTs contained in the RSDT/XSDT will be | |
134 | installed automatically and they will appear under | |
135 | /sys/firmware/acpi/tables. | |
136 | This option turns off this feature. | |
137 | Note that specifying this option does not affect | |
138 | dynamic table installation which will install SSDT | |
139 | tables to /sys/firmware/acpi/tables/dynamic. | |
0cb55ad2 | 140 | |
3f9e12e0 JD |
141 | acpi_no_watchdog [HW,ACPI,WDT] |
142 | Ignore the ACPI-based watchdog interface (WDAT) and let | |
143 | a native driver control the watchdog device instead. | |
144 | ||
ef69449b DB |
145 | acpi_rsdp= [ACPI,EFI,KEXEC] |
146 | Pass the RSDP address to the kernel, mostly used | |
147 | on machines running EFI runtime service to boot the | |
148 | second kernel for kdump. | |
4dde507f | 149 | |
0cb55ad2 RD |
150 | acpi_os_name= [HW,ACPI] Tell ACPI BIOS the name of the OS |
151 | Format: To spoof as Windows 98: ="Microsoft Windows" | |
152 | ||
18d78b64 RW |
153 | acpi_rev_override [ACPI] Override the _REV object to return 5 (instead |
154 | of 2 which is mandated by ACPI 6) as the supported ACPI | |
155 | specification revision (when using this switch, it may | |
156 | be necessary to carry out a cold reboot _twice_ in a | |
157 | row to make it take effect on the platform firmware). | |
158 | ||
0cb55ad2 | 159 | acpi_osi= [HW,ACPI] Modify list of supported OS interface strings |
5dc17986 LZ |
160 | acpi_osi="string1" # add string1 |
161 | acpi_osi="!string2" # remove string2 | |
741d8128 | 162 | acpi_osi=!* # remove all strings |
5dc17986 LZ |
163 | acpi_osi=! # disable all built-in OS vendor |
164 | strings | |
a707edeb LZ |
165 | acpi_osi=!! # enable all built-in OS vendor |
166 | strings | |
0cb55ad2 RD |
167 | acpi_osi= # disable all strings |
168 | ||
5dc17986 LZ |
169 | 'acpi_osi=!' can be used in combination with single or |
170 | multiple 'acpi_osi="string1"' to support specific OS | |
171 | vendor string(s). Note that such command can only | |
172 | affect the default state of the OS vendor strings, thus | |
173 | it cannot affect the default state of the feature group | |
174 | strings and the current state of the OS vendor strings, | |
175 | specifying it multiple times through kernel command line | |
741d8128 LZ |
176 | is meaningless. This command is useful when one do not |
177 | care about the state of the feature group strings which | |
178 | should be controlled by the OSPM. | |
5dc17986 LZ |
179 | Examples: |
180 | 1. 'acpi_osi=! acpi_osi="Windows 2000"' is equivalent | |
181 | to 'acpi_osi="Windows 2000" acpi_osi=!', they all | |
182 | can make '_OSI("Windows 2000")' TRUE. | |
183 | ||
184 | 'acpi_osi=' cannot be used in combination with other | |
185 | 'acpi_osi=' command lines, the _OSI method will not | |
186 | exist in the ACPI namespace. NOTE that such command can | |
187 | only affect the _OSI support state, thus specifying it | |
188 | multiple times through kernel command line is also | |
189 | meaningless. | |
190 | Examples: | |
191 | 1. 'acpi_osi=' can make 'CondRefOf(_OSI, Local1)' | |
192 | FALSE. | |
193 | ||
741d8128 LZ |
194 | 'acpi_osi=!*' can be used in combination with single or |
195 | multiple 'acpi_osi="string1"' to support specific | |
196 | string(s). Note that such command can affect the | |
197 | current state of both the OS vendor strings and the | |
198 | feature group strings, thus specifying it multiple times | |
199 | through kernel command line is meaningful. But it may | |
200 | still not able to affect the final state of a string if | |
201 | there are quirks related to this string. This command | |
202 | is useful when one want to control the state of the | |
203 | feature group strings to debug BIOS issues related to | |
204 | the OSPM features. | |
205 | Examples: | |
206 | 1. 'acpi_osi="Module Device" acpi_osi=!*' can make | |
207 | '_OSI("Module Device")' FALSE. | |
208 | 2. 'acpi_osi=!* acpi_osi="Module Device"' can make | |
209 | '_OSI("Module Device")' TRUE. | |
210 | 3. 'acpi_osi=! acpi_osi=!* acpi_osi="Windows 2000"' is | |
211 | equivalent to | |
212 | 'acpi_osi=!* acpi_osi=! acpi_osi="Windows 2000"' | |
213 | and | |
214 | 'acpi_osi=!* acpi_osi="Windows 2000" acpi_osi=!', | |
215 | they all will make '_OSI("Windows 2000")' TRUE. | |
216 | ||
6cececfc | 217 | acpi_pm_good [X86] |
0cb55ad2 RD |
218 | Override the pmtimer bug detection: force the kernel |
219 | to assume that this machine's pmtimer latches its value | |
220 | and always returns good values. | |
221 | ||
4af94f39 RD |
222 | acpi_sci= [HW,ACPI] ACPI System Control Interrupt trigger mode |
223 | Format: { level | edge | high | low } | |
224 | ||
4af94f39 RD |
225 | acpi_skip_timer_override [HW,ACPI] |
226 | Recognize and ignore IRQ0/pin2 Interrupt Override. | |
227 | For broken nForce2 BIOS resulting in XT-PIC timer. | |
228 | ||
229 | acpi_sleep= [HW,ACPI] Sleep options | |
230 | Format: { s3_bios, s3_mode, s3_beep, s4_nohwsig, | |
57044031 | 231 | old_ordering, nonvs, sci_force_enable, nobl } |
151f4e2b | 232 | See Documentation/power/video.rst for information on |
4af94f39 RD |
233 | s3_bios and s3_mode. |
234 | s3_beep is for debugging; it makes the PC's speaker beep | |
235 | as soon as the kernel's real-mode entry point is called. | |
236 | s4_nohwsig prevents ACPI hardware signature from being | |
237 | used during resume from hibernation. | |
238 | old_ordering causes the ACPI 1.0 ordering of the _PTS | |
239 | control method, with respect to putting devices into | |
240 | low power states, to be enforced (the ACPI 2.0 ordering | |
241 | of _PTS is used by default). | |
72ad5d77 RW |
242 | nonvs prevents the kernel from saving/restoring the |
243 | ACPI NVS memory during suspend/hibernation and resume. | |
d7f0eea9 ZR |
244 | sci_force_enable causes the kernel to set SCI_EN directly |
245 | on resume from S1/S3 (which is against the ACPI spec, | |
246 | but some broken systems don't work without it). | |
57044031 RW |
247 | nobl causes the internal blacklist of systems known to |
248 | behave incorrectly in some ways with respect to system | |
249 | suspend and resume to be ignored (use wisely). | |
4af94f39 RD |
250 | |
251 | acpi_use_timer_override [HW,ACPI] | |
252 | Use timer override. For some broken Nvidia NF5 boards | |
253 | that require a timer override, but don't have HPET | |
254 | ||
4af94f39 RD |
255 | add_efi_memmap [EFI; X86] Include EFI memory map in |
256 | kernel's map of available physical RAM. | |
257 | ||
0cb55ad2 RD |
258 | agp= [AGP] |
259 | { off | try_unsupported } | |
260 | off: disable AGP support | |
261 | try_unsupported: try to drive unsupported chipsets | |
262 | (may crash computer or cause data corruption) | |
263 | ||
bcfde334 | 264 | ALSA [HW,ALSA] |
1ca2c806 | 265 | See Documentation/sound/alsa-configuration.rst |
bcfde334 | 266 | |
d944d549 RK |
267 | alignment= [KNL,ARM] |
268 | Allow the default userspace alignment fault handler | |
269 | behaviour to be specified. Bit 0 enables warnings, | |
270 | bit 1 enables fixups, and bit 2 sends a segfault. | |
271 | ||
dfb09f9b BP |
272 | align_va_addr= [X86-64] |
273 | Align virtual addresses by clearing slice [14:12] when | |
274 | allocating a VMA at process creation time. This option | |
275 | gives you up to 3% performance improvement on AMD F15h | |
276 | machines (where it is enabled by default) for a | |
277 | CPU-intensive style benchmark, and it can vary highly in | |
278 | a microbenchmark depending on workload and compiler. | |
279 | ||
8360ee2f BP |
280 | 32: only for 32-bit processes |
281 | 64: only for 64-bit processes | |
dfb09f9b BP |
282 | on: enable for both 32- and 64-bit processes |
283 | off: disable for both 32- and 64-bit processes | |
284 | ||
55034cd6 SRRH |
285 | alloc_snapshot [FTRACE] |
286 | Allocate the ftrace snapshot buffer on boot up when the | |
287 | main buffer is allocated. This is handy if debugging | |
288 | and you need to use tracing_snapshot() on boot up, and | |
289 | do not want to use tracing_snapshot_alloc() as it needs | |
290 | to be done where GFP_KERNEL allocations are allowed. | |
291 | ||
89e0b9a3 | 292 | amd_iommu= [HW,X86-64] |
54b4cbd2 JR |
293 | Pass parameters to the AMD IOMMU driver in the system. |
294 | Possible values are: | |
afa9fdc2 FT |
295 | fullflush - enable flushing of IO/TLB entries when |
296 | they are unmapped. Otherwise they are | |
297 | flushed before they will be reused, which | |
298 | is a lot of faster | |
a5235725 JR |
299 | off - do not initialize any AMD IOMMU found in |
300 | the system | |
5abcdba4 JR |
301 | force_isolation - Force device isolation for all |
302 | devices. The IOMMU driver is not | |
303 | allowed anymore to lift isolation | |
304 | requirements as needed. This option | |
305 | does not override iommu=pt | |
afa9fdc2 | 306 | |
c099cf17 SK |
307 | amd_iommu_dump= [HW,X86-64] |
308 | Enable AMD IOMMU driver option to dump the ACPI table | |
309 | for AMD IOMMU. With this option enabled, AMD IOMMU | |
310 | driver will print ACPI tables for AMD IOMMU during | |
311 | IOMMU initialization. | |
312 | ||
3928aa3f SS |
313 | amd_iommu_intr= [HW,X86-64] |
314 | Specifies one of the following AMD IOMMU interrupt | |
315 | remapping modes: | |
316 | legacy - Use legacy interrupt remapping mode. | |
317 | vapic - Use virtual APIC mode, which allows IOMMU | |
318 | to inject interrupts directly into guest. | |
319 | This mode requires kvm-amd.avic=1. | |
320 | (Default when IOMMU HW support is present.) | |
321 | ||
1da177e4 LT |
322 | amijoy.map= [HW,JOY] Amiga joystick support |
323 | Map of devices attached to JOY0DAT and JOY1DAT | |
324 | Format: <a>,<b> | |
1752118d | 325 | See also Documentation/input/joydev/joystick.rst |
1da177e4 LT |
326 | |
327 | analog.map= [HW,JOY] Analog joystick and gamepad support | |
328 | Specifies type or capabilities of an analog joystick | |
329 | connected to one of 16 gameports | |
330 | Format: <type1>,<type2>,..<type16> | |
331 | ||
a9913044 RD |
332 | apc= [HW,SPARC] |
333 | Power management functions (SPARCstation-4/5 + deriv.) | |
1da177e4 LT |
334 | Format: noidle |
335 | Disable APC CPU standby support. SPARCstation-Fox does | |
336 | not play well with APC CPU idle - disable it if you have | |
337 | APC and your system crashes randomly. | |
338 | ||
64e05d11 | 339 | apic= [APIC,X86] Advanced Programmable Interrupt Controller |
806654a9 | 340 | Change the output verbosity while booting |
1da177e4 LT |
341 | Format: { quiet (default) | verbose | debug } |
342 | Change the amount of debugging information output | |
343 | when initialising the APIC and IO-APIC components. | |
64e05d11 DL |
344 | For X86-32, this can also be used to specify an APIC |
345 | driver name. | |
346 | Format: apic=driver_name | |
347 | Examples: apic=bigsmp | |
a9913044 | 348 | |
b7c4948e HK |
349 | apic_extnmi= [APIC,X86] External NMI delivery setting |
350 | Format: { bsp (default) | all | none } | |
351 | bsp: External NMI is delivered only to CPU 0 | |
352 | all: External NMIs are broadcast to all CPUs as a | |
353 | backup of CPU 0 | |
354 | none: External NMI is masked for all CPUs. This is | |
355 | useful so that a dump capture kernel won't be | |
356 | shot down by NMI | |
357 | ||
b0f83b28 BH |
358 | autoconf= [IPV6] |
359 | See Documentation/networking/ipv6.txt. | |
360 | ||
9636bc05 CG |
361 | show_lapic= [APIC,X86] Advanced Programmable Interrupt Controller |
362 | Limit apic dumping. The parameter defines the maximal | |
363 | number of local apics being dumped. Also it is possible | |
364 | to set it to "all" by meaning -- no limit here. | |
365 | Format: { 1 (default) | 2 | ... | all }. | |
366 | The parameter valid if only apic=debug or | |
367 | apic=verbose is specified. | |
368 | Example: apic=debug show_lapic=all | |
369 | ||
1da177e4 | 370 | apm= [APM] Advanced Power Management |
71f77055 | 371 | See header of arch/x86/kernel/apm_32.c. |
1da177e4 | 372 | |
1da177e4 LT |
373 | arcrimi= [HW,NET] ARCnet - "RIM I" (entirely mem-mapped) cards |
374 | Format: <io>,<irq>,<nodeID> | |
375 | ||
376 | ataflop= [HW,M68k] | |
377 | ||
378 | atarimouse= [HW,MOUSE] Atari Mouse | |
379 | ||
1da177e4 LT |
380 | atkbd.extra= [HW] Enable extra LEDs and keys on IBM RapidAccess, |
381 | EzKey and similar keyboards | |
382 | ||
383 | atkbd.reset= [HW] Reset keyboard during initialization | |
384 | ||
a9913044 RD |
385 | atkbd.set= [HW] Select keyboard code set |
386 | Format: <int> (2 = AT (default), 3 = PS/2) | |
1da177e4 LT |
387 | |
388 | atkbd.scroll= [HW] Enable scroll wheel on MS Office and similar | |
389 | keyboards | |
390 | ||
391 | atkbd.softraw= [HW] Choose between synthetic and real raw mode | |
392 | Format: <bool> (0 = real, 1 = synthetic (default)) | |
a9913044 RD |
393 | |
394 | atkbd.softrepeat= [HW] | |
395 | Use software keyboard repeat | |
1da177e4 | 396 | |
a106fb0c | 397 | audit= [KNL] Enable the audit sub-system |
11dd2666 GE |
398 | Format: { "0" | "1" | "off" | "on" } |
399 | 0 | off - kernel audit is disabled and can not be | |
400 | enabled until the next reboot | |
d7961148 EP |
401 | unset - kernel audit is initialized but disabled and |
402 | will be fully enabled by the userspace auditd. | |
11dd2666 GE |
403 | 1 | on - kernel audit is initialized and partially |
404 | enabled, storing at most audit_backlog_limit | |
405 | messages in RAM until it is fully enabled by the | |
406 | userspace auditd. | |
a106fb0c | 407 | Default: unset |
f3411cb2 | 408 | |
f910fde7 RGB |
409 | audit_backlog_limit= [KNL] Set the audit queue size limit. |
410 | Format: <int> (must be >=0) | |
411 | Default: 64 | |
412 | ||
1c532e00 AT |
413 | bau= [X86_UV] Enable the BAU on SGI UV. The default |
414 | behavior is to disable the BAU (i.e. bau=0). | |
415 | Format: { "0" | "1" } | |
416 | 0 - Disable the BAU. | |
417 | 1 - Enable the BAU. | |
418 | unset - Disable the BAU. | |
419 | ||
1da177e4 LT |
420 | baycom_epp= [HW,AX25] |
421 | Format: <io>,<mode> | |
a9913044 | 422 | |
1da177e4 LT |
423 | baycom_par= [HW,AX25] BayCom Parallel Port AX.25 Modem |
424 | Format: <io>,<mode> | |
425 | See header of drivers/net/hamradio/baycom_par.c. | |
426 | ||
a9913044 RD |
427 | baycom_ser_fdx= [HW,AX25] |
428 | BayCom Serial Port AX.25 Modem (Full Duplex Mode) | |
1da177e4 LT |
429 | Format: <io>,<irq>,<mode>[,<baud>] |
430 | See header of drivers/net/hamradio/baycom_ser_fdx.c. | |
431 | ||
a9913044 RD |
432 | baycom_ser_hdx= [HW,AX25] |
433 | BayCom Serial Port AX.25 Modem (Half Duplex Mode) | |
1da177e4 LT |
434 | Format: <io>,<irq>,<mode> |
435 | See header of drivers/net/hamradio/baycom_ser_hdx.c. | |
436 | ||
080506ad PG |
437 | blkdevparts= Manual partition parsing of block device(s) for |
438 | embedded devices based on command line input. | |
898bd37a | 439 | See Documentation/block/cmdline-partition.rst |
080506ad | 440 | |
bfe8df3d RD |
441 | boot_delay= Milliseconds to delay each printk during boot. |
442 | Values larger than 10 seconds (10000) are changed to | |
443 | no delay (0). | |
444 | Format: integer | |
445 | ||
7495e092 SRV |
446 | bootconfig [KNL] |
447 | Extended command line options can be added to an initrd | |
448 | and this will cause the kernel to look for it. | |
449 | ||
450 | See Documentation/admin-guide/bootconfig.rst | |
451 | ||
a3e2acc5 HY |
452 | bert_disable [ACPI] |
453 | Disable BERT OS support on buggy BIOSes. | |
454 | ||
1ffb8d03 AH |
455 | bgrt_disable [ACPI][X86] |
456 | Disable BGRT to avoid flickering OEM logo. | |
457 | ||
1da177e4 | 458 | bttv.card= [HW,V4L] bttv (bt848 + bt878 based grabber cards) |
a9913044 RD |
459 | bttv.radio= Most important insmod options are available as |
460 | kernel args too. | |
a405ed85 | 461 | bttv.pll= See Documentation/media/v4l-drivers/bttv.rst |
395cf969 | 462 | bttv.tuner= |
1da177e4 | 463 | |
4e89a2d8 WS |
464 | bulk_remove=off [PPC] This parameter disables the use of the pSeries |
465 | firmware feature for flushing multiple hpte entries | |
466 | at a time. | |
467 | ||
1da177e4 LT |
468 | c101= [NET] Moxa C101 synchronous serial card |
469 | ||
cd4f0ef7 | 470 | cachesize= [BUGS=X86-32] Override level 2 CPU cache size detection. |
1da177e4 LT |
471 | Sometimes CPU hardware bugs make them report the cache |
472 | size incorrectly. The kernel will attempt work arounds | |
473 | to fix known problems, but for some CPUs it is not | |
474 | possible to determine what the correct size should be. | |
475 | This option provides an override for these situations. | |
476 | ||
3fc46fc9 MK |
477 | carrier_timeout= |
478 | [NET] Specifies amount of time (in seconds) that | |
479 | the kernel should wait for a network carrier. By default | |
480 | it waits 120 seconds. | |
481 | ||
ffb70f61 DK |
482 | ca_keys= [KEYS] This parameter identifies a specific key(s) on |
483 | the system trusted keyring to be used for certificate | |
484 | trust validation. | |
32c4741c | 485 | format: { id:<keyid> | builtin } |
ffb70f61 | 486 | |
fd1bb4c9 FF |
487 | cca= [MIPS] Override the kernel pages' cache coherency |
488 | algorithm. Accepted values range from 0 to 7 | |
489 | inclusive. See arch/mips/include/asm/pgtable-bits.h | |
490 | for platform specific values (SB1, Loongson3 and | |
491 | others). | |
492 | ||
6dddd7a7 | 493 | ccw_timeout_log [S390] |
8b4a503d | 494 | See Documentation/s390/common_io.rst for details. |
1da177e4 | 495 | |
6dddd7a7 | 496 | cgroup_disable= [KNL] Disable a particular controller |
8bab8dde | 497 | Format: {name of the controller(s) to disable} |
ca0bdbb5 QH |
498 | The effects of cgroup_disable=foo are: |
499 | - foo isn't auto-mounted if you mount all cgroups in | |
500 | a single hierarchy | |
501 | - foo isn't visible as an individually mountable | |
502 | subsystem | |
503 | {Currently only "memory" controller deal with this and | |
504 | cut the overhead, others just disable the usage. So | |
505 | only cgroup_disable=memory is actually worthy} | |
8bab8dde | 506 | |
3fc9c12d TH |
507 | cgroup_no_v1= [KNL] Disable cgroup controllers and named hierarchies in v1 |
508 | Format: { { controller | "all" | "named" } | |
509 | [,{ controller | "all" | "named" }...] } | |
1619b6d4 JW |
510 | Like cgroup_disable, but only applies to cgroup v1; |
511 | the blacklisted controllers remain available in cgroup2. | |
3fc9c12d TH |
512 | "all" blacklists all controllers and "named" disables |
513 | named mounts. Specifying both "all" and "named" disables | |
514 | all v1 hierarchies. | |
1619b6d4 | 515 | |
f7e1cb6e JW |
516 | cgroup.memory= [KNL] Pass options to the cgroup memory controller. |
517 | Format: <string> | |
518 | nosocket -- Disable socket memory accounting. | |
04823c83 | 519 | nokmem -- Disable kernel memory accounting. |
f7e1cb6e | 520 | |
1da177e4 LT |
521 | checkreqprot [SELINUX] Set initial checkreqprot flag value. |
522 | Format: { "0" | "1" } | |
523 | See security/selinux/Kconfig help text. | |
a9913044 RD |
524 | 0 -- check protection applied by kernel (includes |
525 | any implied execute protection). | |
1da177e4 LT |
526 | 1 -- check protection requested by application. |
527 | Default value is set via a kernel config option. | |
a9913044 | 528 | Value can be changed at runtime via |
d41415eb | 529 | /sys/fs/selinux/checkreqprot. |
e9c38f9f | 530 | Setting checkreqprot to 1 is deprecated. |
a9913044 | 531 | |
661ca0da | 532 | cio_ignore= [S390] |
8b4a503d | 533 | See Documentation/s390/common_io.rst for details. |
1e435256 OJ |
534 | clk_ignore_unused |
535 | [CLK] | |
e156ee56 MT |
536 | Prevents the clock framework from automatically gating |
537 | clocks that have not been explicitly enabled by a Linux | |
538 | device driver but are enabled in hardware at reset or | |
539 | by the bootloader/firmware. Note that this does not | |
540 | force such clocks to be always-on nor does it reserve | |
541 | those clocks in any way. This parameter is useful for | |
542 | debug and development, but should not be needed on a | |
543 | platform with proper driver support. For more | |
18bcaa4e | 544 | information, see Documentation/driver-api/clk.rst. |
661ca0da | 545 | |
cd4f0ef7 | 546 | clock= [BUGS=X86-32, HW] gettimeofday clocksource override. |
734efb46 | 547 | [Deprecated] |
3f6dee9b | 548 | Forces specified clocksource (if available) to be used |
734efb46 | 549 | when calculating gettimeofday(). If specified |
3f6dee9b | 550 | clocksource is not available, it defaults to PIT. |
1da177e4 LT |
551 | Format: { pit | tsc | cyclone | pmtmr } |
552 | ||
592913ec | 553 | clocksource= Override the default clocksource |
3d6ac984 RD |
554 | Format: <string> |
555 | Override the default clocksource and use the clocksource | |
556 | with the name specified. | |
557 | Some clocksource names to choose from, depending on | |
558 | the platform: | |
559 | [all] jiffies (this is the base, fallback clocksource) | |
560 | [ACPI] acpi_pm | |
561 | [ARM] imx_timer1,OSTS,netx_timer,mpu_timer2, | |
562 | pxa_timer,timer3,32k_counter,timer0_1 | |
9863c90f | 563 | [X86-32] pit,hpet,tsc; |
3d6ac984 RD |
564 | scx200_hrt on Geode; cyclone on IBM x440 |
565 | [MIPS] MIPS | |
566 | [PARISC] cr16 | |
567 | [S390] tod | |
568 | [SH] SuperH | |
569 | [SPARC64] tick | |
570 | [X86-64] hpet,tsc | |
571 | ||
46fd5c6b WD |
572 | clocksource.arm_arch_timer.evtstrm= |
573 | [ARM,ARM64] | |
574 | Format: <bool> | |
575 | Enable/disable the eventstream feature of the ARM | |
576 | architected timer so that code using WFE-based polling | |
577 | loops can be debugged more effectively on production | |
578 | systems. | |
579 | ||
ac72e788 AK |
580 | clearcpuid=BITNUM [X86] |
581 | Disable CPUID feature X for the kernel. See | |
cd4d09ec | 582 | arch/x86/include/asm/cpufeatures.h for the valid bit |
07983f0e | 583 | numbers. Note the Linux specific bits are not necessarily |
ac72e788 AK |
584 | stable over kernel options, but the vendor specific |
585 | ones should be. | |
586 | Also note that user programs calling CPUID directly | |
587 | or using the feature without checking anything | |
588 | will still see it. This just prevents it from | |
589 | being used by the kernel or shown in /proc/cpuinfo. | |
590 | Also note the kernel might malfunction if you disable | |
591 | some critical bits. | |
592 | ||
5ea3b1b2 AM |
593 | cma=nn[MG]@[start[MG][-end[MG]]] |
594 | [ARM,X86,KNL] | |
595 | Sets the size of kernel global memory area for | |
596 | contiguous memory allocations and optionally the | |
597 | placement constraint by the physical address range of | |
f0d6d1f6 JD |
598 | memory allocations. A value of 0 disables CMA |
599 | altogether. For more information, see | |
c64be2bb MS |
600 | include/linux/dma-contiguous.h |
601 | ||
14f966e7 RJ |
602 | cmo_free_hint= [PPC] Format: { yes | no } |
603 | Specify whether pages are marked as being inactive | |
604 | when they are freed. This is used in CMO environments | |
605 | to determine OS memory pressure for page stealing by | |
606 | a hypervisor. | |
607 | Default: yes | |
608 | ||
c7909509 MS |
609 | coherent_pool=nn[KMG] [ARM,KNL] |
610 | Sets the size of memory pool for coherent, atomic dma | |
e9da6e99 | 611 | allocations, by default set to 256K. |
c7909509 | 612 | |
1da177e4 | 613 | com20020= [HW,NET] ARCnet - COM20020 chipset |
a9913044 RD |
614 | Format: |
615 | <io>[,<irq>[,<nodeID>[,<backplane>[,<ckp>[,<timeout>]]]]] | |
1da177e4 LT |
616 | |
617 | com90io= [HW,NET] ARCnet - COM90xx chipset (IO-mapped buffers) | |
618 | Format: <io>[,<irq>] | |
619 | ||
a9913044 RD |
620 | com90xx= [HW,NET] |
621 | ARCnet - COM90xx chipset (memory-mapped buffers) | |
1da177e4 LT |
622 | Format: <io>[,<irq>[,<memstart>]] |
623 | ||
624 | condev= [HW,S390] console device | |
625 | conmode= | |
a9913044 | 626 | |
1da177e4 LT |
627 | console= [KNL] Output console device and options. |
628 | ||
629 | tty<n> Use the virtual console device <n>. | |
630 | ||
631 | ttyS<n>[,options] | |
f1a1c2dc | 632 | ttyUSB0[,options] |
1da177e4 | 633 | Use the specified serial port. The options are of |
f1a1c2dc RD |
634 | the form "bbbbpnf", where "bbbb" is the baud rate, |
635 | "p" is parity ("n", "o", or "e"), "n" is number of | |
636 | bits, and "f" is flow control ("r" for RTS or | |
637 | omit it). Default is "9600n8". | |
638 | ||
e52347bd | 639 | See Documentation/admin-guide/serial-console.rst for more |
f1a1c2dc RD |
640 | information. See |
641 | Documentation/networking/netconsole.txt for an | |
642 | alternative. | |
1da177e4 | 643 | |
18a8bd94 YL |
644 | uart[8250],io,<addr>[,options] |
645 | uart[8250],mmio,<addr>[,options] | |
bd94c407 | 646 | uart[8250],mmio16,<addr>[,options] |
ca782f16 PH |
647 | uart[8250],mmio32,<addr>[,options] |
648 | uart[8250],0x<addr>[,options] | |
1da177e4 LT |
649 | Start an early, polled-mode console on the 8250/16550 |
650 | UART at the specified I/O port or MMIO address, | |
ca782f16 PH |
651 | switching to the matching ttyS device later. |
652 | MMIO inter-register address stride is either 8-bit | |
bd94c407 MY |
653 | (mmio), 16-bit (mmio16), or 32-bit (mmio32). |
654 | If none of [io|mmio|mmio16|mmio32], <addr> is assumed | |
655 | to be equivalent to 'mmio'. 'options' are specified in | |
656 | the same format described for ttyS above; if unspecified, | |
ca782f16 PH |
657 | the h/w is not re-initialized. |
658 | ||
a2fd6419 KRW |
659 | hvc<n> Use the hypervisor console device <n>. This is for |
660 | both Xen and PowerPC hypervisors. | |
1da177e4 | 661 | |
6dddd7a7 TB |
662 | If the device connected to the port is not a TTY but a braille |
663 | device, prepend "brl," before the device type, for instance | |
f7511d5f ST |
664 | console=brl,ttyS0 |
665 | For now, only VisioBraille is supported. | |
666 | ||
cca10d58 SS |
667 | console_msg_format= |
668 | [KNL] Change console messages format | |
669 | default | |
670 | By default we print messages on consoles in | |
671 | "[time stamp] text\n" format (time stamp may not be | |
672 | printed, depending on CONFIG_PRINTK_TIME or | |
673 | `printk_time' param). | |
674 | syslog | |
675 | Switch to syslog format: "<%u>[time stamp] text\n" | |
676 | IOW, each message will have a facility and loglevel | |
677 | prefix. The format is similar to one used by syslog() | |
678 | syscall, or to executing "dmesg -S --raw" or to reading | |
679 | from /proc/kmsg. | |
680 | ||
f324edc8 | 681 | consoleblank= [KNL] The console blank (screen saver) timeout in |
ac0a314c | 682 | seconds. A value of 0 disables the blank timer. |
6dddd7a7 | 683 | Defaults to 0. |
f324edc8 | 684 | |
4cb0e11b HK |
685 | coredump_filter= |
686 | [KNL] Change the default value for | |
687 | /proc/<pid>/coredump_filter. | |
cd4ca341 | 688 | See also Documentation/filesystems/proc.rst. |
4cb0e11b | 689 | |
62a31ce1 LY |
690 | coresight_cpu_debug.enable |
691 | [ARM,ARM64] | |
692 | Format: <bool> | |
693 | Enable/disable the CPU sampling based debugging. | |
694 | 0: default value, disable debugging | |
695 | 1: enable debugging at boot time | |
696 | ||
62027aea LB |
697 | cpuidle.off=1 [CPU_IDLE] |
698 | disable the cpuidle sub-system | |
699 | ||
61cb5758 RW |
700 | cpuidle.governor= |
701 | [CPU_IDLE] Name of the cpuidle governor to use. | |
702 | ||
d82f2692 LB |
703 | cpufreq.off=1 [CPU_FREQ] |
704 | disable the cpufreq sub-system | |
705 | ||
d68921f9 LB |
706 | cpu_init_udelay=N |
707 | [X86] Delay for N microsec between assert and de-assert | |
708 | of APIC INIT to start processors. This delay occurs | |
709 | on every CPU online, such as boot, and resume from suspend. | |
710 | Default: 10000 | |
711 | ||
1da177e4 | 712 | cpcihp_generic= [HW,PCI] Generic port I/O CompactPCI driver |
a9913044 RD |
713 | Format: |
714 | <first_slot>,<last_slot>,<port>,<enum_bit>[,<debug>] | |
1da177e4 | 715 | |
6f21e646 AD |
716 | crashkernel=size[KMG][@offset[KMG]] |
717 | [KNL] Using kexec, Linux can switch to a 'crash kernel' | |
718 | upon panic. This parameter reserves the physical | |
719 | memory region [offset, offset + size] for that kernel | |
720 | image. If '@offset' is omitted, then a suitable offset | |
b9ac3849 DY |
721 | is selected automatically. |
722 | [KNL, x86_64] select a region under 4G first, and | |
723 | fall back to reserve region above 4G when '@offset' | |
724 | hasn't been specified. | |
330d4810 | 725 | See Documentation/admin-guide/kdump/kdump.rst for further details. |
dc009d92 | 726 | |
fb391599 BW |
727 | crashkernel=range1:size1[,range2:size2,...][@offset] |
728 | [KNL] Same as above, but depends on the memory | |
729 | in the running system. The syntax of range is | |
730 | start-[end] where start and end are both | |
731 | a memory unit (amount[KMG]). See also | |
330d4810 | 732 | Documentation/admin-guide/kdump/kdump.rst for an example. |
fb391599 | 733 | |
adbc742b | 734 | crashkernel=size[KMG],high |
55a20ee7 YL |
735 | [KNL, x86_64] range could be above 4G. Allow kernel |
736 | to allocate physical memory region from top, so could | |
737 | be above 4G if system have more than 4G ram installed. | |
738 | Otherwise memory region will be allocated below 4G, if | |
739 | available. | |
740 | It will be ignored if crashkernel=X is specified. | |
adbc742b YL |
741 | crashkernel=size[KMG],low |
742 | [KNL, x86_64] range under 4G. When crashkernel=X,high | |
743 | is passed, kernel could allocate physical memory region | |
c729de8f YL |
744 | above 4G, that cause second kernel crash on system |
745 | that require some amount of low memory, e.g. swiotlb | |
c6045031 BH |
746 | requires at least 64M+32K low memory, also enough extra |
747 | low memory is needed to make sure DMA buffers for 32-bit | |
748 | devices won't run out. Kernel would try to allocate at | |
749 | at least 256M below 4G automatically. | |
c729de8f YL |
750 | This one let user to specify own low range under 4G |
751 | for second kernel instead. | |
752 | 0: to disable low allocation. | |
adbc742b | 753 | It will be ignored when crashkernel=X,high is not used |
55a20ee7 | 754 | or memory reserved is below 4G. |
c729de8f | 755 | |
9e5c9fe4 | 756 | cryptomgr.notests |
6dddd7a7 | 757 | [KNL] Disable crypto self-tests |
9e5c9fe4 | 758 | |
1da177e4 LT |
759 | cs89x0_dma= [HW,NET] |
760 | Format: <dma> | |
761 | ||
762 | cs89x0_media= [HW,NET] | |
763 | Format: { rj45 | aui | bnc } | |
a9913044 | 764 | |
a9913044 | 765 | dasd= [HW,NET] |
1da177e4 LT |
766 | See header of drivers/s390/block/dasd_devmap.c. |
767 | ||
768 | db9.dev[2|3]= [HW,JOY] Multisystem joystick support via parallel port | |
769 | (one device per port) | |
770 | Format: <port#>,<type> | |
1752118d | 771 | See also Documentation/input/devices/joystick-parport.rst |
1da177e4 | 772 | |
6dddd7a7 | 773 | ddebug_query= [KNL,DYNAMIC_DEBUG] Enable debug messages at early boot |
787e3075 SM |
774 | time. See |
775 | Documentation/admin-guide/dynamic-debug-howto.rst for | |
29e36c9f | 776 | details. Deprecated, see dyndbg. |
a648ec05 | 777 | |
1da177e4 LT |
778 | debug [KNL] Enable kernel debugging (events log level). |
779 | ||
3672476e TH |
780 | debug_boot_weak_hash |
781 | [KNL] Enable printing [hashed] pointers early in the | |
782 | boot sequence. If enabled, we use a weak hash instead | |
783 | of siphash to hash pointers. Use this option if you are | |
784 | seeing instances of '(___ptrval___)') and need to see a | |
785 | value (hashed pointer) instead. Cryptographically | |
786 | insecure, please do not use on production kernels. | |
787 | ||
cae2ed9a IM |
788 | debug_locks_verbose= |
789 | [KNL] verbose self-tests | |
790 | Format=<0|1> | |
791 | Print debugging info while doing the locking API | |
792 | self-tests. | |
793 | We default to 0 (no extra messages), setting it to | |
794 | 1 will print _a lot_ more information - normally | |
795 | only useful to kernel developers. | |
796 | ||
3ac7fe5a TG |
797 | debug_objects [KNL] Enable object debugging |
798 | ||
3e8ebb5c KM |
799 | no_debug_objects |
800 | [KNL] Disable object debugging | |
801 | ||
c0a32fc5 SG |
802 | debug_guardpage_minorder= |
803 | [KNL] When CONFIG_DEBUG_PAGEALLOC is set, this | |
804 | parameter allows control of the order of pages that will | |
805 | be intentionally kept free (and hence protected) by the | |
806 | buddy allocator. Bigger value increase the probability | |
807 | of catching random memory corruption, but reduce the | |
808 | amount of memory for normal system use. The maximum | |
809 | possible value is MAX_ORDER/2. Setting this parameter | |
810 | to 1 or 2 should be enough to identify most random | |
811 | memory corruption problems caused by bugs in kernel or | |
812 | driver code when a CPU writes to (or reads from) a | |
813 | random memory location. Note that there exists a class | |
814 | of memory corruptions problems caused by buggy H/W or | |
815 | F/W or by drivers badly programing DMA (basically when | |
816 | memory is written at bus level and the CPU MMU is | |
817 | bypassed) which are not detectable by | |
818 | CONFIG_DEBUG_PAGEALLOC, hence this option will not help | |
819 | tracking down these problems. | |
820 | ||
031bc574 | 821 | debug_pagealloc= |
3972f6bb VB |
822 | [KNL] When CONFIG_DEBUG_PAGEALLOC is set, this parameter |
823 | enables the feature at boot time. By default, it is | |
824 | disabled and the system will work mostly the same as a | |
825 | kernel built without CONFIG_DEBUG_PAGEALLOC. | |
8974558f VB |
826 | Note: to get most of debug_pagealloc error reports, it's |
827 | useful to also enable the page_owner functionality. | |
031bc574 JK |
828 | on: enable the feature |
829 | ||
d3af01f1 TG |
830 | debugpat [X86] Enable PAT debugging |
831 | ||
2d27a966 | 832 | decnet.addr= [HW,NET] |
1da177e4 LT |
833 | Format: <area>[,<node>] |
834 | See also Documentation/networking/decnet.txt. | |
835 | ||
0cb55ad2 RD |
836 | default_hugepagesz= |
837 | [same as hugepagesz=] The size of the default | |
838 | HugeTLB page size. This is the size represented by | |
839 | the legacy /proc/ hugepages APIs, used for SHM, and | |
840 | default size when mounting hugetlbfs filesystems. | |
841 | Defaults to the default architecture's huge page size | |
842 | if not specified. | |
55ff9780 | 843 | |
25b4e70d RH |
844 | deferred_probe_timeout= |
845 | [KNL] Debugging option to set a timeout in seconds for | |
846 | deferred probe to give up waiting on dependencies to | |
847 | probe. Only specific dependencies (subsystems or | |
848 | drivers) that have opted in will be ignored. A timeout of 0 | |
849 | will timeout at the end of initcalls. This option will also | |
850 | dump out devices still on the deferred probe list after | |
851 | retrying. | |
852 | ||
c65e6815 MZ |
853 | dfltcc= [HW,S390] |
854 | Format: { on | off | def_only | inf_only | always } | |
855 | on: s390 zlib hardware support for compression on | |
856 | level 1 and decompression (default) | |
857 | off: No s390 zlib hardware support | |
858 | def_only: s390 zlib hardware support for deflate | |
859 | only (compression on level 1) | |
860 | inf_only: s390 zlib hardware support for inflate | |
861 | only (decompression) | |
862 | always: Same as 'on' but ignores the selected compression | |
863 | level always using hardware support (used for debugging) | |
864 | ||
1da177e4 LT |
865 | dhash_entries= [KNL] |
866 | Set number of hash buckets for dentry cache. | |
a9913044 | 867 | |
faf78829 OH |
868 | disable_1tb_segments [PPC] |
869 | Disables the use of 1TB hash page table segments. This | |
870 | causes the kernel to fall back to 256MB segments which | |
871 | can be useful when debugging issues that require an SLB | |
872 | miss to occur. | |
873 | ||
b0f83b28 BH |
874 | disable= [IPV6] |
875 | See Documentation/networking/ipv6.txt. | |
876 | ||
b5cb15d9 CR |
877 | hardened_usercopy= |
878 | [KNL] Under CONFIG_HARDENED_USERCOPY, whether | |
879 | hardening is enabled for this boot. Hardened | |
880 | usercopy checking is used to protect the kernel | |
881 | from reading or writing beyond known memory | |
882 | allocation boundaries as a proactive defense | |
883 | against bounds-checking flaws in the kernel's | |
884 | copy_to_user()/copy_from_user() interface. | |
885 | on Perform hardened usercopy checks (default). | |
886 | off Disable hardened usercopy checks. | |
887 | ||
b275bfb2 AK |
888 | disable_radix [PPC] |
889 | Disable RADIX MMU mode on POWER9 | |
890 | ||
2275d7b5 NP |
891 | disable_tlbie [PPC] |
892 | Disable TLBIE instruction. Currently does not work | |
893 | with KVM, with HASH MMU, or with coherent accelerators. | |
894 | ||
151e0c7d HD |
895 | disable_cpu_apicid= [X86,APIC,SMP] |
896 | Format: <int> | |
897 | The number of initial APIC ID for the | |
898 | corresponding CPU to be disabled at boot, | |
899 | mostly used for the kdump 2nd kernel to | |
900 | disable BSP to wake up multiple CPUs without | |
901 | causing system reset or hang due to sending | |
902 | INIT from AP to BSP. | |
903 | ||
2a5bf23d PZ |
904 | perf_v4_pmi= [X86,INTEL] |
905 | Format: <bool> | |
af3bdb99 AK |
906 | Disable Intel PMU counter freezing feature. |
907 | The feature only exists starting from | |
908 | Arch Perfmon v4 (Skylake and newer). | |
909 | ||
6dddd7a7 | 910 | disable_ddw [PPC/PSERIES] |
4e8b0cf4 NA |
911 | Disable Dynamic DMA Window support. Use this if |
912 | to workaround buggy firmware. | |
913 | ||
b0f83b28 BH |
914 | disable_ipv6= [IPV6] |
915 | See Documentation/networking/ipv6.txt. | |
916 | ||
95ffa243 | 917 | disable_mtrr_cleanup [X86] |
95ffa243 YL |
918 | The kernel tries to adjust MTRR layout from continuous |
919 | to discrete, to make X server driver able to add WB | |
0cb55ad2 | 920 | entry later. This parameter disables that. |
95ffa243 | 921 | |
093af8d7 | 922 | disable_mtrr_trim [X86, Intel and AMD only] |
99fc8d42 JB |
923 | By default the kernel will trim any uncacheable |
924 | memory out of your available memory pool based on | |
925 | MTRR settings. This parameter disables that behavior, | |
926 | possibly causing your machine to run very slowly. | |
927 | ||
6cececfc | 928 | disable_timer_pin_1 [X86] |
0cb55ad2 RD |
929 | Disable PIN 1 of APIC timer |
930 | Can be useful to work around chipset bugs. | |
931 | ||
ce14c583 PB |
932 | dis_ucode_ldr [X86] Disable the microcode loader. |
933 | ||
0cb55ad2 RD |
934 | dma_debug=off If the kernel is compiled with DMA_API_DEBUG support, |
935 | this option disables the debugging code at boot. | |
936 | ||
937 | dma_debug_entries=<number> | |
938 | This option allows to tune the number of preallocated | |
939 | entries for DMA-API debugging code. One entry is | |
940 | required per DMA-API allocation. Use this if the | |
941 | DMA-API debugging code disables itself because the | |
942 | architectural default is too low. | |
943 | ||
1745de5e JR |
944 | dma_debug_driver=<driver_name> |
945 | With this option the DMA-API debugging driver | |
946 | filter feature can be enabled at boot time. Just | |
947 | pass the driver to filter for as the parameter. | |
948 | The filter can be disabled or changed to another | |
949 | driver later using sysfs. | |
950 | ||
1ea61b68 FT |
951 | driver_async_probe= [KNL] |
952 | List of driver names to be probed asynchronously. | |
953 | Format: <driver_name1>,<driver_name2>... | |
954 | ||
53fd40a9 | 955 | drm.edid_firmware=[<connector>:]<file>[,[<connector>:]<file>] |
96206e29 BP |
956 | Broken monitors, graphic adapters, KVMs and EDIDless |
957 | panels may send no or incorrect EDID data sets. | |
958 | This parameter allows to specify an EDID data sets | |
959 | in the /lib/firmware directory that are used instead. | |
da0df92b CE |
960 | Generic built-in EDID data sets are used, if one of |
961 | edid/1024x768.bin, edid/1280x1024.bin, | |
962 | edid/1680x1050.bin, or edid/1920x1080.bin is given | |
963 | and no file with the same name exists. Details and | |
964 | instructions how to build your own EDID data are | |
cd4ca341 | 965 | available in Documentation/admin-guide/edid.rst. An EDID |
da0df92b CE |
966 | data set will only be used for a particular connector, |
967 | if its name and a colon are prepended to the EDID | |
96206e29 BP |
968 | name. Each connector may use a unique EDID data |
969 | set by separating the files with a comma. An EDID | |
970 | data set with no connector name will be used for | |
971 | any connectors not explicitly specified. | |
da0df92b | 972 | |
1da177e4 LT |
973 | dscc4.setup= [NET] |
974 | ||
a2b05b7a NP |
975 | dt_cpu_ftrs= [PPC] |
976 | Format: {"off" | "known"} | |
977 | Control how the dt_cpu_ftrs device-tree binding is | |
978 | used for CPU feature discovery and setup (if it | |
979 | exists). | |
980 | off: Do not use it, fall back to legacy cpu table. | |
981 | known: Do not pass through unknown features to guests | |
982 | or userspace, only those that the kernel is aware of. | |
983 | ||
58c5475a LW |
984 | dump_apple_properties [X86] |
985 | Dump name and content of EFI device properties on | |
986 | x86 Macs. Useful for driver authors to determine | |
987 | what data is available or for reverse-engineering. | |
988 | ||
29e36c9f JC |
989 | dyndbg[="val"] [KNL,DYNAMIC_DEBUG] |
990 | module.dyndbg[="val"] | |
991 | Enable debug messages at boot time. See | |
787e3075 SM |
992 | Documentation/admin-guide/dynamic-debug-howto.rst |
993 | for details. | |
29e36c9f | 994 | |
06976945 DH |
995 | nopku [X86] Disable Memory Protection Keys CPU feature found |
996 | in some Intel CPUs. | |
997 | ||
f2411da7 LR |
998 | module.async_probe [KNL] |
999 | Enable asynchronous probe on this module. | |
1000 | ||
56aeeba8 MS |
1001 | early_ioremap_debug [KNL] |
1002 | Enable debug messages in early_ioremap support. This | |
1003 | is useful for tracking down temporary early mappings | |
1004 | which are not unmapped. | |
1005 | ||
0cb55ad2 | 1006 | earlycon= [KNL] Output early console device and options. |
0d3c673e | 1007 | |
e18409c0 CH |
1008 | When used with no options, the early console is |
1009 | determined by stdout-path property in device tree's | |
1010 | chosen node or the ACPI SPCR table if supported by | |
1011 | the platform. | |
5664f764 | 1012 | |
c41251b1 ST |
1013 | cdns,<addr>[,options] |
1014 | Start an early, polled-mode console on a Cadence | |
1015 | (xuartps) serial port at the specified address. Only | |
1016 | supported option is baud rate. If baud rate is not | |
1017 | specified, the serial port must already be setup and | |
1018 | configured. | |
6fa62fc4 | 1019 | |
0cb55ad2 RD |
1020 | uart[8250],io,<addr>[,options] |
1021 | uart[8250],mmio,<addr>[,options] | |
1917ac76 | 1022 | uart[8250],mmio32,<addr>[,options] |
6e63be3f | 1023 | uart[8250],mmio32be,<addr>[,options] |
ca782f16 | 1024 | uart[8250],0x<addr>[,options] |
0cb55ad2 RD |
1025 | Start an early, polled-mode console on the 8250/16550 |
1026 | UART at the specified I/O port or MMIO address. | |
16290246 | 1027 | MMIO inter-register address stride is either 8-bit |
6e63be3f NC |
1028 | (mmio) or 32-bit (mmio32 or mmio32be). |
1029 | If none of [io|mmio|mmio32|mmio32be], <addr> is assumed | |
1030 | to be equivalent to 'mmio'. 'options' are specified | |
1031 | in the same format described for "console=ttyS<n>"; if | |
ca782f16 | 1032 | unspecified, the h/w is not initialized. |
0cb55ad2 | 1033 | |
0d3c673e | 1034 | pl011,<addr> |
3b78fae7 | 1035 | pl011,mmio32,<addr> |
0d3c673e RH |
1036 | Start an early, polled-mode console on a pl011 serial |
1037 | port at the specified address. The pl011 serial port | |
1038 | must already be setup and configured. Options are not | |
3b78fae7 TT |
1039 | yet supported. If 'mmio32' is specified, then only |
1040 | the driver will use only 32-bit accessors to read/write | |
1041 | the device registers. | |
0d3c673e | 1042 | |
736d5538 AF |
1043 | meson,<addr> |
1044 | Start an early, polled-mode console on a meson serial | |
1045 | port at the specified address. The serial port must | |
1046 | already be setup and configured. Options are not yet | |
1047 | supported. | |
1048 | ||
0efe7296 SB |
1049 | msm_serial,<addr> |
1050 | Start an early, polled-mode console on an msm serial | |
1051 | port at the specified address. The serial port | |
1052 | must already be setup and configured. Options are not | |
1053 | yet supported. | |
1054 | ||
1055 | msm_serial_dm,<addr> | |
1056 | Start an early, polled-mode console on an msm serial | |
1057 | dm port at the specified address. The serial port | |
1058 | must already be setup and configured. Options are not | |
1059 | yet supported. | |
1060 | ||
e36361d7 AF |
1061 | owl,<addr> |
1062 | Start an early, polled-mode console on a serial port | |
1063 | of an Actions Semi SoC, such as S500 or S900, at the | |
1064 | specified address. The serial port must already be | |
1065 | setup and configured. Options are not yet supported. | |
1066 | ||
c10b1332 MS |
1067 | rda,<addr> |
1068 | Start an early, polled-mode console on a serial port | |
1069 | of an RDA Micro SoC, such as RDA8810PL, at the | |
1070 | specified address. The serial port must already be | |
e36361d7 AF |
1071 | setup and configured. Options are not yet supported. |
1072 | ||
82f12ab3 PD |
1073 | sbi |
1074 | Use RISC-V SBI (Supervisor Binary Interface) for early | |
1075 | console. | |
1076 | ||
d50d7269 RH |
1077 | smh Use ARM semihosting calls for early console. |
1078 | ||
b94ba032 TF |
1079 | s3c2410,<addr> |
1080 | s3c2412,<addr> | |
1081 | s3c2440,<addr> | |
1082 | s3c6400,<addr> | |
1083 | s5pv210,<addr> | |
1084 | exynos4210,<addr> | |
1085 | Use early console provided by serial driver available | |
1086 | on Samsung SoCs, requires selecting proper type and | |
1087 | a correct base address of the selected UART port. The | |
1088 | serial port must already be setup and configured. | |
1089 | Options are not yet supported. | |
1090 | ||
ec84aa0a MB |
1091 | lantiq,<addr> |
1092 | Start an early, polled-mode console on a lantiq serial | |
1093 | (lqasc) port at the specified address. The serial port | |
1094 | must already be setup and configured. Options are not | |
1095 | yet supported. | |
1096 | ||
1d59b382 SA |
1097 | lpuart,<addr> |
1098 | lpuart32,<addr> | |
1099 | Use early console provided by Freescale LP UART driver | |
1100 | found on Freescale Vybrid and QorIQ LS1021A processors. | |
1101 | A valid base address must be provided, and the serial | |
1102 | port must already be setup and configured. | |
1103 | ||
7fe068db JN |
1104 | ec_imx21,<addr> |
1105 | ec_imx6q,<addr> | |
1106 | Start an early, polled-mode, output-only console on the | |
1107 | Freescale i.MX UART at the specified address. The UART | |
1108 | must already be setup and configured. | |
1109 | ||
f7c864e7 | 1110 | ar3700_uart,<addr> |
30530791 WD |
1111 | Start an early, polled-mode console on the |
1112 | Armada 3700 serial port at the specified | |
1113 | address. The serial port must already be setup | |
1114 | and configured. Options are not yet supported. | |
1115 | ||
43f1831b KR |
1116 | qcom_geni,<addr> |
1117 | Start an early, polled-mode console on a Qualcomm | |
1118 | Generic Interface (GENI) based serial port at the | |
1119 | specified address. The serial port must already be | |
1120 | setup and configured. Options are not yet supported. | |
1121 | ||
69c1f396 AB |
1122 | efifb,[options] |
1123 | Start an early, unaccelerated console on the EFI | |
1124 | memory mapped framebuffer (if available). On cache | |
1125 | coherent non-x86 systems that use system memory for | |
1126 | the framebuffer, pass the 'ram' option so that it is | |
1127 | mapped with the correct attributes. | |
1128 | ||
09864c1c | 1129 | linflex,<addr> |
9905f32a | 1130 | Use early console provided by Freescale LINFlexD UART |
09864c1c SM |
1131 | serial driver for NXP S32V234 SoCs. A valid base |
1132 | address must be provided, and the serial port must | |
1133 | already be setup and configured. | |
1134 | ||
4ba66a97 | 1135 | earlyprintk= [X86,SH,ARM,M68k,S390] |
1da177e4 | 1136 | earlyprintk=vga |
89175cf7 | 1137 | earlyprintk=sclp |
2482a92e | 1138 | earlyprintk=xen |
1da177e4 | 1139 | earlyprintk=serial[,ttySn[,baudrate]] |
147ea091 | 1140 | earlyprintk=serial[,0x...[,baudrate]] |
ea3acb19 | 1141 | earlyprintk=ttySn[,baudrate] |
9780bc41 | 1142 | earlyprintk=dbgp[debugController#] |
d2266bbf | 1143 | earlyprintk=pciserial[,force],bus:device.function[,baudrate] |
1b5aeebf | 1144 | earlyprintk=xdbc[xhciController#] |
1da177e4 | 1145 | |
147ea091 DH |
1146 | earlyprintk is useful when the kernel crashes before |
1147 | the normal console is initialized. It is not enabled by | |
1148 | default because it has some cosmetic problems. | |
1149 | ||
a9913044 | 1150 | Append ",keep" to not disable it when the real console |
1da177e4 LT |
1151 | takes over. |
1152 | ||
72548e83 MF |
1153 | Only one of vga, efi, serial, or usb debug port can |
1154 | be used at a time. | |
1da177e4 | 1155 | |
147ea091 DH |
1156 | Currently only ttyS0 and ttyS1 may be specified by |
1157 | name. Other I/O ports may be explicitly specified | |
1158 | on some architectures (x86 and arm at least) by | |
1159 | replacing ttySn with an I/O port address, like this: | |
1160 | earlyprintk=serial,0x1008,115200 | |
1161 | You can find the port for a given device in | |
1162 | /proc/tty/driver/serial: | |
1163 | 2: uart:ST16650V2 port:00001008 irq:18 ... | |
1da177e4 LT |
1164 | |
1165 | Interaction with the standard serial driver is not | |
1166 | very good. | |
1167 | ||
72548e83 MF |
1168 | The VGA and EFI output is eventually overwritten by |
1169 | the real console. | |
1da177e4 | 1170 | |
2482a92e KRW |
1171 | The xen output can only be used by Xen PV guests. |
1172 | ||
89175cf7 HC |
1173 | The sclp output can only be used on s390. |
1174 | ||
d2266bbf FT |
1175 | The optional "force" to "pciserial" enables use of a |
1176 | PCI device even when its classcode is not of the | |
1177 | UART class. | |
1178 | ||
c700f013 CG |
1179 | edac_report= [HW,EDAC] Control how to report EDAC event |
1180 | Format: {"on" | "off" | "force"} | |
1181 | on: enable EDAC to report H/W event. May be overridden | |
1182 | by other higher priority error reporting module. | |
1183 | off: disable H/W event reporting through EDAC. | |
1184 | force: enforce the use of EDAC to report H/W event. | |
1185 | default: on. | |
1186 | ||
9731191f JW |
1187 | ekgdboc= [X86,KGDB] Allow early kernel console debugging |
1188 | ekgdboc=kbd | |
1189 | ||
25985edc | 1190 | This is designed to be used in conjunction with |
9731191f JW |
1191 | the boot argument: earlyprintk=vga |
1192 | ||
1da177e4 | 1193 | edd= [EDD] |
8c4dd606 | 1194 | Format: {"off" | "on" | "skip[mbr]"} |
1da177e4 | 1195 | |
d2f7cbe7 | 1196 | efi= [EFI] |
b617c526 | 1197 | Format: { "old_map", "nochunk", "noruntime", "debug", |
4444f854 MG |
1198 | "nosoftreserve", "disable_early_pci_dma", |
1199 | "no_disable_early_pci_dma" } | |
d2f7cbe7 | 1200 | old_map [X86-64]: switch to the old ioremap-based EFI |
1f299fad | 1201 | runtime services mapping. [Needs CONFIG_X86_UV=y] |
5a17dae4 MF |
1202 | nochunk: disable reading files in "chunks" in the EFI |
1203 | boot stub, as chunking can cause problems with some | |
1204 | firmware implementations. | |
5ae3683c | 1205 | noruntime : disable EFI runtime services support |
fed6cefe | 1206 | debug: enable misc debug output |
b617c526 DW |
1207 | nosoftreserve: The EFI_MEMORY_SP (Specific Purpose) |
1208 | attribute may cause the kernel to reserve the | |
1209 | memory range for a memory mapping driver to | |
1210 | claim. Specify efi=nosoftreserve to disable this | |
1211 | reservation and treat the memory by its base type | |
1212 | (i.e. EFI_CONVENTIONAL_MEMORY / "System RAM"). | |
4444f854 MG |
1213 | disable_early_pci_dma: Disable the busmaster bit on all |
1214 | PCI bridges while in the EFI boot stub | |
1215 | no_disable_early_pci_dma: Leave the busmaster bit set | |
1216 | on all PCI bridges while in the EFI boot stub | |
d2f7cbe7 | 1217 | |
8c58bf3e RW |
1218 | efi_no_storage_paranoia [EFI; X86] |
1219 | Using this parameter you can use more than 50% of | |
1220 | your efi variable storage. Use this parameter only if | |
1221 | you are really sure that your UEFI does sane gc and | |
1222 | fulfills the spec otherwise your board may brick. | |
1223 | ||
0f96a99d TI |
1224 | efi_fake_mem= nn[KMG]@ss[KMG]:aa[,nn[KMG]@ss[KMG]:aa,..] [EFI; X86] |
1225 | Add arbitrary attribute to specific memory range by | |
1226 | updating original EFI memory map. | |
1227 | Region of memory which aa attribute is added to is | |
1228 | from ss to ss+nn. | |
199c8471 | 1229 | |
0f96a99d TI |
1230 | If efi_fake_mem=2G@4G:0x10000,2G@0x10a0000000:0x10000 |
1231 | is specified, EFI_MEMORY_MORE_RELIABLE(0x10000) | |
1232 | attribute is added to range 0x100000000-0x180000000 and | |
1233 | 0x10a0000000-0x1120000000. | |
1234 | ||
199c8471 DW |
1235 | If efi_fake_mem=8G@9G:0x40000 is specified, the |
1236 | EFI_MEMORY_SP(0x40000) attribute is added to | |
1237 | range 0x240000000-0x43fffffff. | |
1238 | ||
0f96a99d | 1239 | Using this parameter you can do debugging of EFI memmap |
199c8471 | 1240 | related features. For example, you can do debugging of |
0f96a99d | 1241 | Address Range Mirroring feature even if your box |
199c8471 DW |
1242 | doesn't support it, or mark specific memory as |
1243 | "soft reserved". | |
0f96a99d | 1244 | |
475fb4e8 OP |
1245 | efivar_ssdt= [EFI; X86] Name of an EFI variable that contains an SSDT |
1246 | that is to be dynamically loaded by Linux. If there are | |
1247 | multiple variables with the same name but with different | |
1248 | vendor GUIDs, all of them will be loaded. See | |
cb1aaebe | 1249 | Documentation/admin-guide/acpi/ssdt-overlays.rst for details. |
475fb4e8 OP |
1250 | |
1251 | ||
1da177e4 LT |
1252 | eisa_irq_edge= [PARISC,HW] |
1253 | See header of drivers/parisc/eisa.c. | |
1254 | ||
cd4f0ef7 | 1255 | elanfreq= [X86-32] |
1da177e4 | 1256 | See comment before function elanfreq_setup() in |
71f77055 | 1257 | arch/x86/kernel/cpu/cpufreq/elanfreq.c. |
1da177e4 | 1258 | |
d3bf3795 | 1259 | elfcorehdr=[size[KMG]@]offset[KMG] [IA64,PPC,SH,X86,S390] |
a9913044 | 1260 | Specifies physical address of start of kernel core |
d3bf3795 MH |
1261 | image elf header and optionally the size. Generally |
1262 | kexec loader will pass this option to capture kernel. | |
330d4810 | 1263 | See Documentation/admin-guide/kdump/kdump.rst for details. |
1da177e4 | 1264 | |
0cb55ad2 RD |
1265 | enable_mtrr_cleanup [X86] |
1266 | The kernel tries to adjust MTRR layout from continuous | |
1267 | to discrete, to make X server driver able to add WB | |
1268 | entry later. This parameter enables that. | |
1269 | ||
ca1eda2d | 1270 | enable_timer_pin_1 [X86] |
0cb55ad2 RD |
1271 | Enable PIN 1 of APIC timer |
1272 | Can be useful to work around chipset bugs | |
1273 | (in particular on some ATI chipsets). | |
1274 | The kernel tries to set a reasonable default. | |
1275 | ||
1da177e4 LT |
1276 | enforcing [SELINUX] Set initial enforcing status. |
1277 | Format: {"0" | "1"} | |
1278 | See security/selinux/Kconfig help text. | |
1279 | 0 -- permissive (log only, no denials). | |
1280 | 1 -- enforcing (deny and log). | |
1281 | Default value is 0. | |
d41415eb SS |
1282 | Value can be changed at runtime via |
1283 | /sys/fs/selinux/enforce. | |
1da177e4 | 1284 | |
a08f82d0 HY |
1285 | erst_disable [ACPI] |
1286 | Disable Error Record Serialization Table (ERST) | |
1287 | support. | |
1288 | ||
1da177e4 LT |
1289 | ether= [HW,NET] Ethernet cards parameters |
1290 | This option is obsoleted by the "netdev=" option, which | |
1291 | has equivalent usage. See its documentation for details. | |
1292 | ||
7102ebcd MZ |
1293 | evm= [EVM] |
1294 | Format: { "fix" } | |
1295 | Permit 'security.evm' to be updated regardless of | |
1296 | current integrity status. | |
1297 | ||
de1ba09b AM |
1298 | failslab= |
1299 | fail_page_alloc= | |
1300 | fail_make_request=[KNL] | |
1301 | General fault injection mechanism. | |
1302 | Format: <interval>,<probability>,<space>,<times> | |
395cf969 | 1303 | See also Documentation/fault-injection/. |
de1ba09b | 1304 | |
1da177e4 | 1305 | floppy= [HW] |
e7751617 | 1306 | See Documentation/admin-guide/blockdev/floppy.rst. |
1da177e4 | 1307 | |
f13ae30e AC |
1308 | force_pal_cache_flush |
1309 | [IA-64] Avoid check_sal_cache_flush which may hang on | |
1310 | buggy SAL_CACHE_FLUSH implementations. Using this | |
1311 | parameter will force ia64_sal_cache_flush to call | |
1312 | ia64_pal_cache_flush instead of SAL_CACHE_FLUSH. | |
1313 | ||
6dddd7a7 | 1314 | forcepae [X86-32] |
69f2366c CB |
1315 | Forcefully enable Physical Address Extension (PAE). |
1316 | Many Pentium M systems disable PAE but may have a | |
1317 | functionally usable PAE implementation. | |
1318 | Warning: use of this parameter will taint the kernel | |
1319 | and may cause unknown problems. | |
1320 | ||
d9e54076 | 1321 | ftrace=[tracer] |
2af15d6a | 1322 | [FTRACE] will set and start the specified tracer |
d9e54076 PZ |
1323 | as early as possible in order to facilitate early |
1324 | boot debugging. | |
1325 | ||
cecbca96 | 1326 | ftrace_dump_on_oops[=orig_cpu] |
2af15d6a | 1327 | [FTRACE] will dump the trace buffers on oops. |
cecbca96 FW |
1328 | If no parameter is passed, ftrace will dump |
1329 | buffers of all CPUs, but if you pass orig_cpu, it will | |
1330 | dump only the buffer of the CPU that triggered the | |
1331 | oops. | |
2af15d6a SR |
1332 | |
1333 | ftrace_filter=[function-list] | |
1334 | [FTRACE] Limit the functions traced by the function | |
1335 | tracer at boot up. function-list is a comma separated | |
1336 | list of functions. This list can be changed at run | |
1337 | time by the set_ftrace_filter file in the debugfs | |
16290246 | 1338 | tracing directory. |
2af15d6a SR |
1339 | |
1340 | ftrace_notrace=[function-list] | |
1341 | [FTRACE] Do not trace the functions specified in | |
1342 | function-list. This list can be changed at run time | |
1343 | by the set_ftrace_notrace file in the debugfs | |
1344 | tracing directory. | |
d9e54076 | 1345 | |
369bc18f SA |
1346 | ftrace_graph_filter=[function-list] |
1347 | [FTRACE] Limit the top level callers functions traced | |
1348 | by the function graph tracer at boot up. | |
1349 | function-list is a comma separated list of functions | |
1350 | that can be changed at run time by the | |
1351 | set_graph_function file in the debugfs tracing directory. | |
1352 | ||
0d7d9a16 NK |
1353 | ftrace_graph_notrace=[function-list] |
1354 | [FTRACE] Do not trace from the functions specified in | |
1355 | function-list. This list is a comma separated list of | |
1356 | functions that can be changed at run time by the | |
1357 | set_graph_notrace file in the debugfs tracing directory. | |
1358 | ||
65a50c65 TB |
1359 | ftrace_graph_max_depth=<uint> |
1360 | [FTRACE] Used with the function graph tracer. This is | |
1361 | the max depth it will trace into a function. This value | |
1362 | can be changed at run time by the max_graph_depth file | |
1363 | in the tracefs tracing directory. default: 0 (no limit) | |
1364 | ||
8375e74f SK |
1365 | fw_devlink= [KNL] Create device links between consumer and supplier |
1366 | devices by scanning the firmware to infer the | |
1367 | consumer/supplier relationships. This feature is | |
1368 | especially useful when drivers are loaded as modules as | |
1369 | it ensures proper ordering of tasks like device probing | |
1370 | (suppliers first, then consumers), supplier boot state | |
1371 | clean up (only after all consumers have probed), | |
1372 | suspend/resume & runtime PM (consumers first, then | |
1373 | suppliers). | |
1374 | Format: { off | permissive | on | rpm } | |
1375 | off -- Don't create device links from firmware info. | |
1376 | permissive -- Create device links from firmware info | |
1377 | but use it only for ordering boot state clean | |
1378 | up (sync_state() calls). | |
1379 | on -- Create device links from firmware info and use it | |
1380 | to enforce probe and suspend/resume ordering. | |
1381 | rpm -- Like "on", but also use to order runtime PM. | |
1382 | ||
1da177e4 LT |
1383 | gamecon.map[2|3]= |
1384 | [HW,JOY] Multisystem joystick and NES/SNES/PSX pad | |
1385 | support via parallel port (up to 5 devices per port) | |
1386 | Format: <port#>,<pad1>,<pad2>,<pad3>,<pad4>,<pad5> | |
1752118d | 1387 | See also Documentation/input/devices/joystick-parport.rst |
1da177e4 LT |
1388 | |
1389 | gamma= [HW,DRM] | |
1390 | ||
6dddd7a7 | 1391 | gart_fix_e820= [X86_64] disable the fix e820 for K8 GART |
aaf23042 YL |
1392 | Format: off | on |
1393 | default: on | |
1394 | ||
2521f2c2 PO |
1395 | gcov_persist= [GCOV] When non-zero (default), profiling data for |
1396 | kernel modules is saved and remains accessible via | |
1397 | debugfs, even when the module is unloaded/reloaded. | |
1398 | When zero, profiling data is discarded and associated | |
1399 | debugfs files are removed at module unload time. | |
1400 | ||
47512cfd TG |
1401 | goldfish [X86] Enable the goldfish android emulator platform. |
1402 | Don't use this when you are not running on the | |
1403 | android emulator | |
1404 | ||
1da177e4 | 1405 | gpt [EFI] Forces disk with valid GPT signature but |
6c5de79b DB |
1406 | invalid Protective MBR to be treated as GPT. If the |
1407 | primary GPT is corrupted, it enables the backup/alternate | |
1408 | GPT to be used instead. | |
1da177e4 | 1409 | |
6cec9b07 AL |
1410 | grcan.enable0= [HW] Configuration of physical interface 0. Determines |
1411 | the "Enable 0" bit of the configuration register. | |
1412 | Format: 0 | 1 | |
1413 | Default: 0 | |
1414 | grcan.enable1= [HW] Configuration of physical interface 1. Determines | |
1415 | the "Enable 0" bit of the configuration register. | |
1416 | Format: 0 | 1 | |
1417 | Default: 0 | |
1418 | grcan.select= [HW] Select which physical interface to use. | |
1419 | Format: 0 | 1 | |
1420 | Default: 0 | |
1421 | grcan.txsize= [HW] Sets the size of the tx buffer. | |
1422 | Format: <unsigned int> such that (txsize & ~0x1fffc0) == 0. | |
1423 | Default: 1024 | |
1424 | grcan.rxsize= [HW] Sets the size of the rx buffer. | |
1425 | Format: <unsigned int> such that (rxsize & ~0x1fffc0) == 0. | |
1426 | Default: 1024 | |
1427 | ||
0f98dd1b BJZ |
1428 | gpio-mockup.gpio_mockup_ranges |
1429 | [HW] Sets the ranges of gpiochip of for this device. | |
1430 | Format: <start1>,<end1>,<start2>,<end2>... | |
1431 | ||
55537871 JK |
1432 | hardlockup_all_cpu_backtrace= |
1433 | [KNL] Should the hard-lockup detector generate | |
1434 | backtraces on all cpus. | |
1435 | Format: <integer> | |
1436 | ||
1da177e4 LT |
1437 | hashdist= [KNL,NUMA] Large hashes allocated during boot |
1438 | are distributed across NUMA nodes. Defaults on | |
16290246 | 1439 | for 64-bit NUMA, off otherwise. |
a9913044 | 1440 | Format: 0 | 1 (for off | on) |
1da177e4 LT |
1441 | |
1442 | hcl= [IA-64] SGI's Hardware Graph compatibility layer | |
1443 | ||
1444 | hd= [EIDE] (E)IDE hard drive subsystem geometry | |
1445 | Format: <cyl>,<head>,<sect> | |
1446 | ||
ea8c071c HY |
1447 | hest_disable [ACPI] |
1448 | Disable Hardware Error Source Table (HEST) support; | |
1449 | corresponding firmware-first mode error processing | |
1450 | logic will be disabled. | |
1451 | ||
1da177e4 LT |
1452 | highmem=nn[KMG] [KNL,BOOT] forces the highmem zone to have an exact |
1453 | size of <nn>. This works even on boxes that have no | |
1454 | highmem otherwise. This also works to reduce highmem | |
1455 | size on bigger boxes. | |
1456 | ||
54cdfdb4 TG |
1457 | highres= [KNL] Enable/disable high resolution timer mode. |
1458 | Valid parameters: "on", "off" | |
1459 | Default: "on" | |
1460 | ||
0cb55ad2 RD |
1461 | hlt [BUGS=ARM,SH] |
1462 | ||
1463 | hpet= [X86-32,HPET] option to control HPET usage | |
1464 | Format: { enable (default) | disable | force | | |
1465 | verbose } | |
1466 | disable: disable HPET and use PIT instead | |
1467 | force: allow force enabled of undocumented chips (ICH4, | |
1468 | VIA, nVidia) | |
1469 | verbose: show contents of HPET registers during setup | |
1470 | ||
3d035f58 PB |
1471 | hpet_mmap= [X86, HPET_MMAP] Allow userspace to mmap HPET |
1472 | registers. Default set by CONFIG_HPET_MMAP_DEFAULT. | |
1473 | ||
cf11e85f RG |
1474 | hugetlb_cma= [HW] The size of a cma area used for allocation |
1475 | of gigantic hugepages. | |
1476 | Format: nn[KMGTPE] | |
1477 | ||
1478 | Reserve a cma area of given size and allocate gigantic | |
1479 | hugepages using the cma allocator. If enabled, the | |
1480 | boot-time allocation of gigantic hugepages is skipped. | |
1481 | ||
b4718e62 AK |
1482 | hugepages= [HW,X86-32,IA-64] HugeTLB pages to allocate at boot. |
1483 | hugepagesz= [HW,IA-64,PPC,X86-64] The size of the HugeTLB pages. | |
0d9ea754 JT |
1484 | On x86-64 and powerpc, this option can be specified |
1485 | multiple times interleaved with hugepages= to reserve | |
1486 | huge pages of different sizes. Valid pages sizes on | |
1487 | x86-64 are 2M (when the CPU supports "pse") and 1G | |
27ec26ec | 1488 | (when the CPU supports the "pdpe1gb" cpuinfo flag). |
6902aa84 | 1489 | |
a49d9c0a OS |
1490 | hung_task_panic= |
1491 | [KNL] Should the hung task detector generate panics. | |
1492 | Format: <integer> | |
cef7125d | 1493 | |
a49d9c0a OS |
1494 | A nonzero value instructs the kernel to panic when a |
1495 | hung task is detected. The default value is controlled | |
1496 | by the CONFIG_BOOTPARAM_HUNG_TASK_PANIC build-time | |
1497 | option. The value selected by this boot parameter can | |
1498 | be changed later by the kernel.hung_task_panic sysctl. | |
1499 | ||
6dddd7a7 TB |
1500 | hvc_iucv= [S390] Number of z/VM IUCV hypervisor console (HVC) |
1501 | terminal devices. Valid values: 0..8 | |
1502 | hvc_iucv_allow= [S390] Comma-separated list of z/VM user IDs. | |
1503 | If specified, z/VM IUCV HVC accepts connections | |
1504 | from listed z/VM user IDs only. | |
3a025de6 YS |
1505 | |
1506 | hv_nopvspin [X86,HYPER_V] Disables the paravirt spinlock optimizations | |
1507 | which allow the hypervisor to 'idle' the | |
1508 | guest on lock contention. | |
1509 | ||
7bf69395 FDN |
1510 | keep_bootcon [KNL] |
1511 | Do not unregister boot console at start. This is only | |
1512 | useful for debugging when something happens in the window | |
1513 | between unregistering the boot console and initializing | |
1514 | the real console. | |
1515 | ||
6dddd7a7 TB |
1516 | i2c_bus= [HW] Override the default board specific I2C bus speed |
1517 | or register an additional I2C bus that is not | |
1518 | registered from board initialization code. | |
1519 | Format: | |
1520 | <bus_id>,<clkrate> | |
3a853fb9 | 1521 | |
36d95739 | 1522 | i8042.debug [HW] Toggle i8042 debug mode |
e1443d28 SCP |
1523 | i8042.unmask_kbd_data |
1524 | [HW] Enable printing of interrupt data from the KBD port | |
1525 | (disabled by default, and as a pre-condition | |
1526 | requires that i8042.debug=1 be enabled) | |
1da177e4 | 1527 | i8042.direct [HW] Put keyboard port into non-translated mode |
84eb8d06 ML |
1528 | i8042.dumbkbd [HW] Pretend that controller can only read data from |
1529 | keyboard and cannot control its state | |
1da177e4 LT |
1530 | (Don't attempt to blink the leds) |
1531 | i8042.noaux [HW] Don't check for auxiliary (== mouse) port | |
945ef0d4 | 1532 | i8042.nokbd [HW] Don't check/create keyboard port |
75d08c78 JK |
1533 | i8042.noloop [HW] Disable the AUX Loopback command while probing |
1534 | for the AUX port | |
1da177e4 | 1535 | i8042.nomux [HW] Don't check presence of an active multiplexing |
e55a3366 | 1536 | controller |
1da177e4 LT |
1537 | i8042.nopnp [HW] Don't use ACPIPnP / PnPBIOS to discover KBD/AUX |
1538 | controllers | |
24775d65 | 1539 | i8042.notimeout [HW] Ignore timeout condition signalled by controller |
930e1924 MPS |
1540 | i8042.reset [HW] Reset the controller during init, cleanup and |
1541 | suspend-to-ram transitions, only during s2r | |
1542 | transitions, or never reset | |
1543 | Format: { 1 | Y | y | 0 | N | n } | |
1544 | 1, Y, y: always reset controller | |
1545 | 0, N, n: don't ever reset controller | |
1546 | Default: only on s2r transitions on x86; most other | |
1547 | architectures force reset to be always executed | |
1da177e4 | 1548 | i8042.unlock [HW] Unlock (ignore) the keylock |
6dddd7a7 | 1549 | i8042.kbdreset [HW] Reset device connected to KBD port |
1da177e4 LT |
1550 | |
1551 | i810= [HW,DRM] | |
1552 | ||
e70c9d5e DT |
1553 | i8k.ignore_dmi [HW] Continue probing hardware even if DMI data |
1554 | indicates that the driver is running on unsupported | |
1555 | hardware. | |
1da177e4 LT |
1556 | i8k.force [HW] Activate i8k driver even if SMM BIOS signature |
1557 | does not match list of supported models. | |
1558 | i8k.power_status | |
1559 | [HW] Report power status in /proc/i8k | |
1560 | (disabled by default) | |
1561 | i8k.restricted [HW] Allow controlling fans only if SYS_ADMIN | |
1562 | capability is set. | |
1563 | ||
4dca20ef | 1564 | i915.invert_brightness= |
7bd90909 CE |
1565 | [DRM] Invert the sense of the variable that is used to |
1566 | set the brightness of the panel backlight. Normally a | |
4dca20ef CE |
1567 | brightness value of 0 indicates backlight switched off, |
1568 | and the maximum of the brightness value sets the backlight | |
1569 | to maximum brightness. If this parameter is set to 0 | |
1570 | (default) and the machine requires it, or this parameter | |
1571 | is set to 1, a brightness value of 0 sets the backlight | |
1572 | to maximum brightness, and the maximum of the brightness | |
1573 | value switches the backlight off. | |
1574 | -1 -- never invert brightness | |
1575 | 0 -- machine default | |
1576 | 1 -- force brightness inversion | |
7bd90909 | 1577 | |
1da177e4 LT |
1578 | icn= [HW,ISDN] |
1579 | Format: <io>[,<membase>[,<icn_id>[,<icn_id2>]]] | |
1580 | ||
0af80c04 DF |
1581 | ide-core.nodma= [HW] (E)IDE subsystem |
1582 | Format: =0.0 to prevent dma on hda, =0.1 hdb =1.0 hdc | |
075affcb BZ |
1583 | .vlb_clock .pci_clock .noflush .nohpa .noprobe .nowerr |
1584 | .cdrom .chs .ignore_cable are additional options | |
d7b461c5 | 1585 | See Documentation/ide/ide.rst. |
1da177e4 | 1586 | |
0f8b7f5d MR |
1587 | ide-generic.probe-mask= [HW] (E)IDE subsystem |
1588 | Format: <int> | |
1589 | Probe mask for legacy ISA IDE ports. Depending on | |
1590 | platform up to 6 ports are supported, enabled by | |
1591 | setting corresponding bits in the mask to 1. The | |
1592 | default value is 0x0, which has a special meaning. | |
1593 | On systems that have PCI, it triggers scanning the | |
1594 | PCI bus for the first and the second port, which | |
1595 | are then probed. On systems without PCI the value | |
1596 | of 0x0 enables probing the two first ports as if it | |
1597 | was 0x3. | |
1598 | ||
0cb55ad2 RD |
1599 | ide-pci-generic.all-generic-ide [HW] (E)IDE subsystem |
1600 | Claim all unknown PCI IDE storage controllers. | |
1601 | ||
f039b754 | 1602 | idle= [X86] |
69fb3676 | 1603 | Format: idle=poll, idle=halt, idle=nomwait |
ada9cfdd RD |
1604 | Poll forces a polling idle loop that can slightly |
1605 | improve the performance of waking up a idle CPU, but | |
1606 | will use a lot of power and make the system run hot. | |
1607 | Not recommended. | |
ada9cfdd | 1608 | idle=halt: Halt is forced to be used for CPU idle. |
c1e3b377 | 1609 | In such case C2/C3 won't be used again. |
ada9cfdd | 1610 | idle=nomwait: Disable mwait for CPU C-states |
a9913044 | 1611 | |
503943e0 MR |
1612 | ieee754= [MIPS] Select IEEE Std 754 conformance mode |
1613 | Format: { strict | legacy | 2008 | relaxed } | |
1614 | Default: strict | |
1615 | ||
1616 | Choose which programs will be accepted for execution | |
1617 | based on the IEEE 754 NaN encoding(s) supported by | |
1618 | the FPU and the NaN encoding requested with the value | |
1619 | of an ELF file header flag individually set by each | |
1620 | binary. Hardware implementations are permitted to | |
1621 | support either or both of the legacy and the 2008 NaN | |
1622 | encoding mode. | |
1623 | ||
1624 | Available settings are as follows: | |
1625 | strict accept binaries that request a NaN encoding | |
1626 | supported by the FPU | |
1627 | legacy only accept legacy-NaN binaries, if supported | |
1628 | by the FPU | |
1629 | 2008 only accept 2008-NaN binaries, if supported | |
1630 | by the FPU | |
1631 | relaxed accept any binaries regardless of whether | |
1632 | supported by the FPU | |
1633 | ||
1634 | The FPU emulator is always able to support both NaN | |
1635 | encodings, so if no FPU hardware is present or it has | |
1636 | been disabled with 'nofpu', then the settings of | |
1637 | 'legacy' and '2008' strap the emulator accordingly, | |
1638 | 'relaxed' straps the emulator for both legacy-NaN and | |
1639 | 2008-NaN, whereas 'strict' enables legacy-NaN only on | |
1640 | legacy processors and both NaN encodings on MIPS32 or | |
1641 | MIPS64 CPUs. | |
1642 | ||
1643 | The setting for ABS.fmt/NEG.fmt instruction execution | |
1644 | mode generally follows that for the NaN encoding, | |
1645 | except where unsupported by hardware. | |
1646 | ||
79290822 IM |
1647 | ignore_loglevel [KNL] |
1648 | Ignore loglevel setting - this will print /all/ | |
1649 | kernel messages to the console. Useful for debugging. | |
0eca6b7c YZ |
1650 | We also add it as printk module parameter, so users |
1651 | could change it dynamically, usually by | |
1652 | /sys/module/printk/parameters/ignore_loglevel. | |
79290822 | 1653 | |
d977d56c KK |
1654 | ignore_rlimit_data |
1655 | Ignore RLIMIT_DATA setting for data mappings, | |
1656 | print warning at first misuse. Can be changed via | |
1657 | /sys/module/kernel/parameters/ignore_rlimit_data. | |
1658 | ||
1da177e4 LT |
1659 | ihash_entries= [KNL] |
1660 | Set number of hash buckets for inode cache. | |
1661 | ||
2fe5d6de | 1662 | ima_appraise= [IMA] appraise integrity measurements |
2faa6ef3 | 1663 | Format: { "off" | "enforce" | "fix" | "log" } |
2fe5d6de MZ |
1664 | default: "enforce" |
1665 | ||
41475a3e | 1666 | ima_appraise_tcb [IMA] Deprecated. Use ima_policy= instead. |
07f6a794 MZ |
1667 | The builtin appraise policy appraises all files |
1668 | owned by uid=0. | |
1669 | ||
d68a6fe9 MZ |
1670 | ima_canonical_fmt [IMA] |
1671 | Use the canonical format for the binary runtime | |
1672 | measurements, instead of host native format. | |
1673 | ||
3323eec9 | 1674 | ima_hash= [IMA] |
e7a2ad7e MZ |
1675 | Format: { md5 | sha1 | rmd160 | sha256 | sha384 |
1676 | | sha512 | ... } | |
3323eec9 MZ |
1677 | default: "sha1" |
1678 | ||
e7a2ad7e MZ |
1679 | The list of supported hash algorithms is defined |
1680 | in crypto/hash_info.h. | |
1681 | ||
24fd03c8 | 1682 | ima_policy= [IMA] |
33ce9549 | 1683 | The builtin policies to load during IMA setup. |
9e67028e MZ |
1684 | Format: "tcb | appraise_tcb | secure_boot | |
1685 | fail_securely" | |
33ce9549 MZ |
1686 | |
1687 | The "tcb" policy measures all programs exec'd, files | |
1688 | mmap'd for exec, and all files opened with the read | |
1689 | mode bit set by either the effective uid (euid=0) or | |
1690 | uid=0. | |
1691 | ||
1692 | The "appraise_tcb" policy appraises the integrity of | |
41475a3e | 1693 | all files owned by root. |
24fd03c8 | 1694 | |
503ceaef MZ |
1695 | The "secure_boot" policy appraises the integrity |
1696 | of files (eg. kexec kernel image, kernel modules, | |
1697 | firmware, policy, etc) based on file signatures. | |
24fd03c8 | 1698 | |
9e67028e MZ |
1699 | The "fail_securely" policy forces file signature |
1700 | verification failure also on privileged mounted | |
1701 | filesystems with the SB_I_UNVERIFIABLE_SIGNATURE | |
1702 | flag. | |
1703 | ||
24fd03c8 | 1704 | ima_tcb [IMA] Deprecated. Use ima_policy= instead. |
5789ba3b EP |
1705 | Load a policy which meets the needs of the Trusted |
1706 | Computing Base. This means IMA will measure all | |
1707 | programs exec'd, files mmap'd for exec, and all files | |
1708 | opened for read by uid=0. | |
1709 | ||
6dddd7a7 | 1710 | ima_template= [IMA] |
9b9d4ce5 | 1711 | Select one of defined IMA measurements template formats. |
8265a2f8 | 1712 | Formats: { "ima" | "ima-ng" | "ima-sig" } |
9b9d4ce5 RS |
1713 | Default: "ima-ng" |
1714 | ||
c2426d2a | 1715 | ima_template_fmt= |
6dddd7a7 | 1716 | [IMA] Define a custom template format. |
c2426d2a RS |
1717 | Format: { "field1|...|fieldN" } |
1718 | ||
3bcced39 DK |
1719 | ima.ahash_minsize= [IMA] Minimum file size for asynchronous hash usage |
1720 | Format: <min_file_size> | |
1721 | Set the minimal file size for using asynchronous hash. | |
1722 | If left unspecified, ahash usage is disabled. | |
1723 | ||
1724 | ahash performance varies for different data sizes on | |
1725 | different crypto accelerators. This option can be used | |
1726 | to achieve the best performance for a particular HW. | |
1727 | ||
6edf7a89 DK |
1728 | ima.ahash_bufsize= [IMA] Asynchronous hash buffer size |
1729 | Format: <bufsize> | |
1730 | Set hashing buffer size. Default: 4k. | |
1731 | ||
1732 | ahash performance varies for different chunk sizes on | |
1733 | different crypto accelerators. This option can be used | |
1734 | to achieve best performance for particular HW. | |
1735 | ||
1da177e4 LT |
1736 | init= [KNL] |
1737 | Format: <full_path> | |
1738 | Run specified binary instead of /sbin/init as init | |
1739 | process. | |
1740 | ||
1741 | initcall_debug [KNL] Trace initcalls as they are executed. Useful | |
1742 | for working out where the kernel is dying during | |
1743 | startup. | |
1744 | ||
7b0b73d7 PB |
1745 | initcall_blacklist= [KNL] Do not execute a comma-separated list of |
1746 | initcall functions. Useful for debugging built-in | |
1747 | modules and initcalls. | |
1748 | ||
1da177e4 LT |
1749 | initrd= [BOOT] Specify the location of the initial ramdisk |
1750 | ||
6471384a AP |
1751 | init_on_alloc= [MM] Fill newly allocated pages and heap objects with |
1752 | zeroes. | |
1753 | Format: 0 | 1 | |
1754 | Default set by CONFIG_INIT_ON_ALLOC_DEFAULT_ON. | |
1755 | ||
1756 | init_on_free= [MM] Fill freed pages and heap objects with zeroes. | |
1757 | Format: 0 | 1 | |
1758 | Default set by CONFIG_INIT_ON_FREE_DEFAULT_ON. | |
1759 | ||
acd547b2 DH |
1760 | init_pkru= [x86] Specify the default memory protection keys rights |
1761 | register contents for all processes. 0x55555554 by | |
1762 | default (disallow access to all but pkey 0). Can | |
1763 | override in debugfs after boot. | |
1764 | ||
1da177e4 LT |
1765 | inport.irq= [HW] Inport (ATI XL and Microsoft) busmouse driver |
1766 | Format: <irq> | |
1767 | ||
6dddd7a7 | 1768 | int_pln_enable [x86] Enable power limit notification interrupt |
6bb2ff84 | 1769 | |
d726d8d7 MZ |
1770 | integrity_audit=[IMA] |
1771 | Format: { "0" | "1" } | |
1772 | 0 -- basic integrity auditing messages. (Default) | |
1773 | 1 -- additional integrity auditing messages. | |
1774 | ||
ba395927 | 1775 | intel_iommu= [DMAR] Intel IOMMU driver (DMAR) option |
0cd5c3c8 KM |
1776 | on |
1777 | Enable intel iommu driver. | |
ba395927 KA |
1778 | off |
1779 | Disable intel iommu driver. | |
1780 | igfx_off [Default Off] | |
1781 | By default, gfx is mapped as normal device. If a gfx | |
1782 | device has a dedicated DMAR unit, the DMAR unit is | |
1783 | bypassed by not enabling DMAR with this option. In | |
1784 | this case, gfx device will use physical address for | |
1785 | DMA. | |
7d3b03ce KA |
1786 | forcedac [x86_64] |
1787 | With this option iommu will not optimize to look | |
16290246 | 1788 | for io virtual address below 32-bit forcing dual |
7d3b03ce | 1789 | address cycle on pci bus for cards supporting greater |
16290246 RD |
1790 | than 32-bit addressing. The default is to look |
1791 | for translation below 32-bit and if not available | |
7d3b03ce | 1792 | then look in the higher range. |
5e0d2a6f | 1793 | strict [Default Off] |
1794 | With this option on every unmap_single operation will | |
1795 | result in a hardware IOTLB flush operation as opposed | |
1796 | to batching them for performance. | |
6dd9a7c7 YS |
1797 | sp_off [Default Off] |
1798 | By default, super page will be supported if Intel IOMMU | |
1799 | has the capability. With this option, super page will | |
1800 | not be supported. | |
8950dcd8 LB |
1801 | sm_on [Default Off] |
1802 | By default, scalable mode will be disabled even if the | |
765b6a98 LB |
1803 | hardware advertises that it has support for the scalable |
1804 | mode translation. With this option set, scalable mode | |
8950dcd8 | 1805 | will be used on hardware which claims to support it. |
bfd20f1c SL |
1806 | tboot_noforce [Default Off] |
1807 | Do not force the Intel IOMMU enabled under tboot. | |
1808 | By default, tboot will force Intel IOMMU on, which | |
1809 | could harm performance of some high-throughput | |
1810 | devices like 40GBit network cards, even if identity | |
1811 | mapping is enabled. | |
1812 | Note that using this option lowers the security | |
1813 | provided by tboot because it makes the system | |
1814 | vulnerable to DMA attacks. | |
e5e04d05 | 1815 | nobounce [Default off] |
bf347b9d | 1816 | Disable bounce buffer for untrusted devices such as |
e5e04d05 LB |
1817 | the Thunderbolt devices. This will treat the untrusted |
1818 | devices as the trusted ones, hence might expose security | |
1819 | risks of DMA attacks. | |
2e92c7ad MI |
1820 | |
1821 | intel_idle.max_cstate= [KNL,HW,ACPI,X86] | |
1822 | 0 disables intel_idle and fall back on acpi_idle. | |
22c6bbe4 | 1823 | 1 to 9 specify maximum depth of C-state. |
2e92c7ad | 1824 | |
6dddd7a7 TB |
1825 | intel_pstate= [X86] |
1826 | disable | |
1827 | Do not enable intel_pstate as the default | |
1828 | scaling driver for the supported processors | |
1829 | passive | |
1830 | Use intel_pstate as a scaling driver, but configure it | |
1831 | to work with generic cpufreq governors (instead of | |
1832 | enabling its internal governor). This mode cannot be | |
1833 | used along with the hardware-managed P-states (HWP) | |
1834 | feature. | |
1835 | force | |
1836 | Enable intel_pstate on systems that prohibit it by default | |
1837 | in favor of acpi-cpufreq. Forcing the intel_pstate driver | |
1838 | instead of acpi-cpufreq may disable platform features, such | |
1839 | as thermal controls and power capping, that rely on ACPI | |
1840 | P-States information being indicated to OSPM and therefore | |
1841 | should be used with caution. This option does not work with | |
1842 | processors that aren't supported by the intel_pstate driver | |
1843 | or on platforms that use pcc-cpufreq instead of acpi-cpufreq. | |
1844 | no_hwp | |
1845 | Do not enable hardware P state control (HWP) | |
1846 | if available. | |
1847 | hwp_only | |
1848 | Only load intel_pstate on systems which support | |
1849 | hardware P state control (HWP) if available. | |
1850 | support_acpi_ppc | |
1851 | Enforce ACPI _PPC performance limits. If the Fixed ACPI | |
1852 | Description Table, specifies preferred power management | |
1853 | profile as "Enterprise Server" or "Performance Server", | |
1854 | then this feature is turned on by default. | |
1855 | per_cpu_perf_limits | |
1856 | Allow per-logical-CPU P-State performance control limits using | |
1857 | cpufreq sysfs interface | |
6be26498 | 1858 | |
d1423d56 | 1859 | intremap= [X86-64, Intel-IOMMU] |
d1423d56 CW |
1860 | on enable Interrupt Remapping (default) |
1861 | off disable Interrupt Remapping | |
1862 | nosid disable Source ID checking | |
41750d31 SS |
1863 | no_x2apic_optout |
1864 | BIOS x2APIC opt-out request will be ignored | |
b7d20631 | 1865 | nopost disable Interrupt Posting |
d1423d56 | 1866 | |
0cb55ad2 RD |
1867 | iomem= Disable strict checking of access to MMIO memory |
1868 | strict regions from userspace. | |
1869 | relaxed | |
1870 | ||
1871 | iommu= [x86] | |
1872 | off | |
1873 | force | |
1874 | noforce | |
1875 | biomerge | |
1876 | panic | |
1877 | nopanic | |
1878 | merge | |
1879 | nomerge | |
0cb55ad2 | 1880 | soft |
58d11317 OJ |
1881 | pt [x86] |
1882 | nopt [x86] | |
4e287840 TLSC |
1883 | nobypass [PPC/POWERNV] |
1884 | Disable IOMMU bypass, using IOMMU for PCI devices. | |
bcb71abe | 1885 | |
68a6efe8 ZL |
1886 | iommu.strict= [ARM64] Configure TLB invalidation behaviour |
1887 | Format: { "0" | "1" } | |
1888 | 0 - Lazy mode. | |
1889 | Request that DMA unmap operations use deferred | |
1890 | invalidation of hardware TLBs, for increased | |
1891 | throughput at the cost of reduced device isolation. | |
1892 | Will fall back to strict mode if not supported by | |
1893 | the relevant IOMMU driver. | |
1894 | 1 - Strict mode (default). | |
1895 | DMA unmap operations invalidate IOMMU hardware TLBs | |
1896 | synchronously. | |
1897 | ||
fccb4e3b | 1898 | iommu.passthrough= |
c8fb436b | 1899 | [ARM64, X86] Configure DMA to bypass the IOMMU by default. |
fccb4e3b WD |
1900 | Format: { "0" | "1" } |
1901 | 0 - Use IOMMU translation for DMA. | |
1902 | 1 - Bypass the IOMMU for DMA. | |
9d723b4c | 1903 | unset - Use value of CONFIG_IOMMU_DEFAULT_PASSTHROUGH. |
0cb55ad2 RD |
1904 | |
1905 | io7= [HW] IO7 for Marvel based alpha systems | |
1906 | See comment before marvel_specify_io7 in | |
1907 | arch/alpha/kernel/core_marvel.c. | |
1908 | ||
6cececfc | 1909 | io_delay= [X86] I/O delay method |
6e7c4025 IM |
1910 | 0x80 |
1911 | Standard port 0x80 based delay | |
1912 | 0xed | |
1913 | Alternate port 0xed based delay (needed on some systems) | |
b02aae9c | 1914 | udelay |
6e7c4025 IM |
1915 | Simple two microseconds delay |
1916 | none | |
1917 | No delay | |
b02aae9c | 1918 | |
1da177e4 | 1919 | ip= [IP_PNP] |
3eb30c51 | 1920 | See Documentation/admin-guide/nfs/nfsroot.rst. |
1da177e4 | 1921 | |
5ac893b8 WL |
1922 | ipcmni_extend [KNL] Extend the maximum number of unique System V |
1923 | IPC identifiers from 32,768 to 16,777,216. | |
1924 | ||
fbf19803 | 1925 | irqaffinity= [SMP] Set the default irq affinity mask |
2d13e6ca | 1926 | The argument is a cpu list, as described above. |
fbf19803 | 1927 | |
0962289b MZ |
1928 | irqchip.gicv2_force_probe= |
1929 | [ARM, ARM64] | |
1930 | Format: <bool> | |
1931 | Force the kernel to look for the second 4kB page | |
1932 | of a GICv2 controller even if the memory range | |
1933 | exposed by the device tree is too small. | |
1934 | ||
f736d65d MZ |
1935 | irqchip.gicv3_nolpi= |
1936 | [ARM, ARM64] | |
1937 | Force the kernel to ignore the availability of | |
1938 | LPIs (and by consequence ITSs). Intended for system | |
1939 | that use the kernel as a bootloader, and thus want | |
1940 | to let secondary kernels in charge of setting up | |
1941 | LPIs. | |
1942 | ||
bc3c03cc JT |
1943 | irqchip.gicv3_pseudo_nmi= [ARM64] |
1944 | Enables support for pseudo-NMIs in the kernel. This | |
1945 | requires the kernel to be built with | |
1946 | CONFIG_ARM64_PSEUDO_NMI. | |
1947 | ||
200803df AC |
1948 | irqfixup [HW] |
1949 | When an interrupt is not handled search all handlers | |
1950 | for it. Intended to get systems with badly broken | |
1951 | firmware running. | |
1952 | ||
1953 | irqpoll [HW] | |
1954 | When an interrupt is not handled search all handlers | |
1955 | for it. Also check all handlers each timer | |
1956 | interrupt. Intended to get systems with badly broken | |
1957 | firmware running. | |
1958 | ||
1da177e4 | 1959 | isapnp= [ISAPNP] |
a9913044 | 1960 | Format: <RDP>,<reset>,<pci_scan>,<verbosity> |
1da177e4 | 1961 | |
d94d1053 | 1962 | isolcpus= [KNL,SMP,ISOL] Isolate a given set of CPUs from disturbance. |
b0d40d2b FW |
1963 | [Deprecated - use cpusets instead] |
1964 | Format: [flag-list,]<cpu-list> | |
1965 | ||
1966 | Specify one or more CPUs to isolate from disturbances | |
1967 | specified in the flag list (default: domain): | |
1968 | ||
1969 | nohz | |
1970 | Disable the tick when a single task runs. | |
083c6eea FW |
1971 | |
1972 | A residual 1Hz tick is offloaded to workqueues, which you | |
1973 | need to affine to housekeeping through the global | |
1974 | workqueue's affinity configured via the | |
1975 | /sys/devices/virtual/workqueue/cpumask sysfs file, or | |
1976 | by using the 'domain' flag described below. | |
1977 | ||
1978 | NOTE: by default the global workqueue runs on all CPUs, | |
1979 | so to protect individual CPUs the 'cpumask' file has to | |
1980 | be configured manually after bootup. | |
1981 | ||
b0d40d2b FW |
1982 | domain |
1983 | Isolate from the general SMP balancing and scheduling | |
1984 | algorithms. Note that performing domain isolation this way | |
1985 | is irreversible: it's not possible to bring back a CPU to | |
1986 | the domains once isolated through isolcpus. It's strongly | |
1987 | advised to use cpusets instead to disable scheduler load | |
1988 | balancing through the "cpuset.sched_load_balance" file. | |
1989 | It offers a much more flexible interface where CPUs can | |
1990 | move in and out of an isolated set anytime. | |
1991 | ||
1992 | You can move a process onto or off an "isolated" CPU via | |
1993 | the CPU affinity syscalls or cpuset. | |
1994 | <cpu number> begins at 0 and the maximum value is | |
1995 | "number of CPUs in system - 1". | |
1996 | ||
11ea68f5 ML |
1997 | managed_irq |
1998 | ||
1999 | Isolate from being targeted by managed interrupts | |
2000 | which have an interrupt mask containing isolated | |
2001 | CPUs. The affinity of managed interrupts is | |
2002 | handled by the kernel and cannot be changed via | |
2003 | the /proc/irq/* interfaces. | |
2004 | ||
2005 | This isolation is best effort and only effective | |
2006 | if the automatically assigned interrupt mask of a | |
2007 | device queue contains isolated and housekeeping | |
2008 | CPUs. If housekeeping CPUs are online then such | |
2009 | interrupts are directed to the housekeeping CPU | |
2010 | so that IO submitted on the housekeeping CPU | |
2011 | cannot disturb the isolated CPU. | |
2012 | ||
2013 | If a queue's affinity mask contains only isolated | |
2014 | CPUs then this parameter has no effect on the | |
2015 | interrupt routing decision, though interrupts are | |
2016 | only delivered when tasks running on those | |
2017 | isolated CPUs submit IO. IO submitted on | |
2018 | housekeeping CPUs has no influence on those | |
2019 | queues. | |
1da177e4 | 2020 | |
11ea68f5 | 2021 | The format of <cpu-list> is described above. |
1da177e4 | 2022 | |
a9913044 | 2023 | iucv= [HW,NET] |
1da177e4 | 2024 | |
7d8bfa26 JR |
2025 | ivrs_ioapic [HW,X86_64] |
2026 | Provide an override to the IOAPIC-ID<->DEVICE-ID | |
2027 | mapping provided in the IVRS ACPI table. For | |
2028 | example, to map IOAPIC-ID decimal 10 to | |
2029 | PCI device 00:14.0 write the parameter as: | |
2030 | ivrs_ioapic[10]=00:14.0 | |
2031 | ||
2032 | ivrs_hpet [HW,X86_64] | |
2033 | Provide an override to the HPET-ID<->DEVICE-ID | |
2034 | mapping provided in the IVRS ACPI table. For | |
2035 | example, to map HPET-ID decimal 0 to | |
2036 | PCI device 00:14.0 write the parameter as: | |
2037 | ivrs_hpet[0]=00:14.0 | |
2038 | ||
ca3bf5d4 SS |
2039 | ivrs_acpihid [HW,X86_64] |
2040 | Provide an override to the ACPI-HID:UID<->DEVICE-ID | |
2041 | mapping provided in the IVRS ACPI table. For | |
2042 | example, to map UART-HID:UID AMD0020:0 to | |
2043 | PCI device 00:14.5 write the parameter as: | |
2044 | ivrs_acpihid[00:14.5]=AMD0020:0 | |
2045 | ||
1da177e4 | 2046 | js= [HW,JOY] Analog joystick |
1752118d | 2047 | See Documentation/input/joydev/joystick.rst. |
1da177e4 | 2048 | |
65fe935d KC |
2049 | nokaslr [KNL] |
2050 | When CONFIG_RANDOMIZE_BASE is set, this disables | |
2051 | kernel and module base offset ASLR (Address Space | |
2052 | Layout Randomization). | |
24f2e027 | 2053 | |
b0845ce5 MR |
2054 | kasan_multi_shot |
2055 | [KNL] Enforce KASAN (Kernel Address Sanitizer) to print | |
2056 | report on every invalid memory access. Without this | |
2057 | parameter KASAN will print report only for the first | |
2058 | invalid access. | |
2059 | ||
0cb55ad2 RD |
2060 | keepinitrd [HW,ARM] |
2061 | ||
342332e6 | 2062 | kernelcore= [KNL,X86,IA-64,PPC] |
a5c6d650 DR |
2063 | Format: nn[KMGTPE] | nn% | "mirror" |
2064 | This parameter specifies the amount of memory usable by | |
2065 | the kernel for non-movable allocations. The requested | |
2066 | amount is spread evenly throughout all nodes in the | |
2067 | system as ZONE_NORMAL. The remaining memory is used for | |
2068 | movable memory in its own zone, ZONE_MOVABLE. In the | |
2069 | event, a node is too small to have both ZONE_NORMAL and | |
2070 | ZONE_MOVABLE, kernelcore memory will take priority and | |
2071 | other nodes will have a larger ZONE_MOVABLE. | |
2072 | ||
2073 | ZONE_MOVABLE is used for the allocation of pages that | |
2074 | may be reclaimed or moved by the page migration | |
2075 | subsystem. Note that allocations like PTEs-from-HighMem | |
2076 | still use the HighMem zone if it exists, and the Normal | |
ed7ed365 MG |
2077 | zone if it does not. |
2078 | ||
a5c6d650 DR |
2079 | It is possible to specify the exact amount of memory in |
2080 | the form of "nn[KMGTPE]", a percentage of total system | |
2081 | memory in the form of "nn%", or "mirror". If "mirror" | |
342332e6 TI |
2082 | option is specified, mirrored (reliable) memory is used |
2083 | for non-movable allocations and remaining memory is used | |
a5c6d650 DR |
2084 | for Movable pages. "nn[KMGTPE]", "nn%", and "mirror" |
2085 | are exclusive, so you cannot specify multiple forms. | |
ed7ed365 | 2086 | |
4fe1da4e JW |
2087 | kgdbdbgp= [KGDB,HW] kgdb over EHCI usb debug port. |
2088 | Format: <Controller#>[,poll interval] | |
2089 | The controller # is the number of the ehci usb debug | |
2090 | port as it is probed via PCI. The poll interval is | |
2091 | optional and is the number seconds in between | |
2092 | each poll cycle to the debug port in case you need | |
2093 | the functionality for interrupting the kernel with | |
2094 | gdb or control-c on the dbgp connection. When | |
2095 | not using this parameter you use sysrq-g to break into | |
2096 | the kernel debugger. | |
2097 | ||
84c08fd6 | 2098 | kgdboc= [KGDB,HW] kgdb over consoles. |
ada64e4c JW |
2099 | Requires a tty driver that supports console polling, |
2100 | or a supported polling keyboard driver (non-usb). | |
65b5ac14 JW |
2101 | Serial only format: <serial_device>[,baud] |
2102 | keyboard only format: kbd | |
2103 | keyboard and serial format: kbd,<serial_device>[,baud] | |
2104 | Optional Kernel mode setting: | |
2105 | kms, kbd format: kms,kbd | |
2106 | kms, kbd and serial format: kms,kbd,<ser_dev>[,baud] | |
6cdf6e06 | 2107 | |
84c08fd6 JW |
2108 | kgdbwait [KGDB] Stop kernel execution and enter the |
2109 | kernel debugger at the earliest opportunity. | |
2110 | ||
9bed90c6 FF |
2111 | kmac= [MIPS] korina ethernet MAC address. |
2112 | Configure the RouterBoard 532 series on-chip | |
2113 | Ethernet adapter MAC address. | |
2114 | ||
04f70336 CM |
2115 | kmemleak= [KNL] Boot-time kmemleak enable/disable |
2116 | Valid arguments: on, off | |
2117 | Default: on | |
47aeeddc MI |
2118 | Built with CONFIG_DEBUG_KMEMLEAK_DEFAULT_OFF=y, |
2119 | the default is off. | |
04f70336 | 2120 | |
970988e1 MH |
2121 | kprobe_event=[probe-list] |
2122 | [FTRACE] Add kprobe events and enable at boot time. | |
2123 | The probe-list is a semicolon delimited list of probe | |
2124 | definitions. Each definition is same as kprobe_events | |
2125 | interface, but the parameters are comma delimited. | |
2126 | For example, to add a kprobe event on vfs_read with | |
2127 | arg1 and arg2, add to the command line; | |
2128 | ||
2129 | kprobe_event=p,vfs_read,$arg1,$arg2 | |
2130 | ||
2131 | See also Documentation/trace/kprobetrace.rst "Kernel | |
2132 | Boot Parameter" section. | |
2133 | ||
de190555 JL |
2134 | kpti= [ARM64] Control page table isolation of user |
2135 | and kernel address spaces. | |
2136 | Default: enabled on cores which need mitigation. | |
2137 | 0: force disabled | |
2138 | 1: force enabled | |
2139 | ||
fef07aae AP |
2140 | kvm.ignore_msrs=[KVM] Ignore guest accesses to unhandled MSRs. |
2141 | Default is 0 (don't ignore, but inject #GP) | |
2142 | ||
c4ae60e4 LA |
2143 | kvm.enable_vmware_backdoor=[KVM] Support VMware backdoor PV interface. |
2144 | Default is false (don't support). | |
2145 | ||
a182d873 XG |
2146 | kvm.mmu_audit= [KVM] This is a R/W parameter which allows audit |
2147 | KVM MMU at runtime. | |
fef07aae AP |
2148 | Default is 0 (off) |
2149 | ||
b8e8c830 PB |
2150 | kvm.nx_huge_pages= |
2151 | [KVM] Controls the software workaround for the | |
2152 | X86_BUG_ITLB_MULTIHIT bug. | |
2153 | force : Always deploy workaround. | |
2154 | off : Never deploy workaround. | |
2155 | auto : Deploy workaround based on the presence of | |
2156 | X86_BUG_ITLB_MULTIHIT. | |
2157 | ||
2158 | Default is 'auto'. | |
2159 | ||
2160 | If the software workaround is enabled for the host, | |
2161 | guests do need not to enable it for nested guests. | |
2162 | ||
1aa9b957 JS |
2163 | kvm.nx_huge_pages_recovery_ratio= |
2164 | [KVM] Controls how many 4KiB pages are periodically zapped | |
2165 | back to huge pages. 0 disables the recovery, otherwise if | |
2166 | the value is N KVM will zap 1/Nth of the 4KiB pages every | |
2167 | minute. The default is 60. | |
2168 | ||
fef07aae | 2169 | kvm-amd.nested= [KVM,AMD] Allow nested virtualization in KVM/SVM. |
8475f94a | 2170 | Default is 1 (enabled) |
fef07aae AP |
2171 | |
2172 | kvm-amd.npt= [KVM,AMD] Disable nested paging (virtualized MMU) | |
2173 | for all guests. | |
16290246 | 2174 | Default is 1 (enabled) if in 64-bit or 32-bit PAE mode. |
fef07aae | 2175 | |
e23f62f7 MZ |
2176 | kvm-arm.vgic_v3_group0_trap= |
2177 | [KVM,ARM] Trap guest accesses to GICv3 group-0 | |
2178 | system registers | |
2179 | ||
182936ee MZ |
2180 | kvm-arm.vgic_v3_group1_trap= |
2181 | [KVM,ARM] Trap guest accesses to GICv3 group-1 | |
2182 | system registers | |
2183 | ||
ff89511e MZ |
2184 | kvm-arm.vgic_v3_common_trap= |
2185 | [KVM,ARM] Trap guest accesses to GICv3 common | |
2186 | system registers | |
2187 | ||
a7546054 MZ |
2188 | kvm-arm.vgic_v4_enable= |
2189 | [KVM,ARM] Allow use of GICv4 for direct injection of | |
2190 | LPIs. | |
2191 | ||
fef07aae AP |
2192 | kvm-intel.ept= [KVM,Intel] Disable extended page tables |
2193 | (virtualized MMU) support on capable Intel chips. | |
2194 | Default is 1 (enabled) | |
2195 | ||
2196 | kvm-intel.emulate_invalid_guest_state= | |
2197 | [KVM,Intel] Enable emulation of invalid guest states | |
2198 | Default is 0 (disabled) | |
2199 | ||
2200 | kvm-intel.flexpriority= | |
2201 | [KVM,Intel] Disable FlexPriority feature (TPR shadow). | |
2202 | Default is 1 (enabled) | |
2203 | ||
e1a72ae2 SL |
2204 | kvm-intel.nested= |
2205 | [KVM,Intel] Enable VMX nesting (nVMX). | |
2206 | Default is 0 (disabled) | |
2207 | ||
fef07aae AP |
2208 | kvm-intel.unrestricted_guest= |
2209 | [KVM,Intel] Disable unrestricted guest feature | |
2210 | (virtualized real and unpaged mode) on capable | |
2211 | Intel chips. Default is 1 (enabled) | |
2212 | ||
a399477e KRW |
2213 | kvm-intel.vmentry_l1d_flush=[KVM,Intel] Mitigation for L1 Terminal Fault |
2214 | CVE-2018-3620. | |
2215 | ||
2216 | Valid arguments: never, cond, always | |
2217 | ||
2218 | always: L1D cache flush on every VMENTER. | |
2219 | cond: Flush L1D on VMENTER only when the code between | |
2220 | VMEXIT and VMENTER can leak host memory. | |
2221 | never: Disables the mitigation | |
2222 | ||
2223 | Default is cond (do L1 cache flush in specific instances) | |
2224 | ||
fef07aae AP |
2225 | kvm-intel.vpid= [KVM,Intel] Disable Virtual Processor Identification |
2226 | feature (tagged TLBs) on capable Intel chips. | |
2227 | Default is 1 (enabled) | |
2228 | ||
d90a7a0e JK |
2229 | l1tf= [X86] Control mitigation of the L1TF vulnerability on |
2230 | affected CPUs | |
2231 | ||
2232 | The kernel PTE inversion protection is unconditionally | |
2233 | enabled and cannot be disabled. | |
2234 | ||
2235 | full | |
2236 | Provides all available mitigations for the | |
2237 | L1TF vulnerability. Disables SMT and | |
2238 | enables all mitigations in the | |
2239 | hypervisors, i.e. unconditional L1D flush. | |
2240 | ||
2241 | SMT control and L1D flush control via the | |
2242 | sysfs interface is still possible after | |
2243 | boot. Hypervisors will issue a warning | |
2244 | when the first VM is started in a | |
2245 | potentially insecure configuration, | |
2246 | i.e. SMT enabled or L1D flush disabled. | |
2247 | ||
2248 | full,force | |
2249 | Same as 'full', but disables SMT and L1D | |
2250 | flush runtime control. Implies the | |
2251 | 'nosmt=force' command line option. | |
2252 | (i.e. sysfs control of SMT is disabled.) | |
2253 | ||
2254 | flush | |
2255 | Leaves SMT enabled and enables the default | |
2256 | hypervisor mitigation, i.e. conditional | |
2257 | L1D flush. | |
2258 | ||
2259 | SMT control and L1D flush control via the | |
2260 | sysfs interface is still possible after | |
2261 | boot. Hypervisors will issue a warning | |
2262 | when the first VM is started in a | |
2263 | potentially insecure configuration, | |
2264 | i.e. SMT enabled or L1D flush disabled. | |
2265 | ||
2266 | flush,nosmt | |
2267 | ||
2268 | Disables SMT and enables the default | |
2269 | hypervisor mitigation. | |
2270 | ||
2271 | SMT control and L1D flush control via the | |
2272 | sysfs interface is still possible after | |
2273 | boot. Hypervisors will issue a warning | |
2274 | when the first VM is started in a | |
2275 | potentially insecure configuration, | |
2276 | i.e. SMT enabled or L1D flush disabled. | |
2277 | ||
2278 | flush,nowarn | |
2279 | Same as 'flush', but hypervisors will not | |
2280 | warn when a VM is started in a potentially | |
2281 | insecure configuration. | |
2282 | ||
2283 | off | |
2284 | Disables hypervisor mitigations and doesn't | |
2285 | emit any warnings. | |
5b5e4d62 MH |
2286 | It also drops the swap size and available |
2287 | RAM limit restriction on both hypervisor and | |
2288 | bare metal. | |
d90a7a0e JK |
2289 | |
2290 | Default is 'flush'. | |
2291 | ||
65fd4cb6 | 2292 | For details see: Documentation/admin-guide/hw-vuln/l1tf.rst |
d90a7a0e | 2293 | |
1da177e4 LT |
2294 | l2cr= [PPC] |
2295 | ||
a78bfbfc RB |
2296 | l3cr= [PPC] |
2297 | ||
cd4f0ef7 | 2298 | lapic [X86-32,APIC] Enable the local APIC even if BIOS |
a9913044 | 2299 | disabled it. |
1da177e4 | 2300 | |
279f1461 SS |
2301 | lapic= [x86,APIC] "notscdeadline" Do not use TSC deadline |
2302 | value for LAPIC timer one-shot implementation. Default | |
2303 | back to the programmable timer unit in the LAPIC. | |
2304 | ||
6cececfc | 2305 | lapic_timer_c2_ok [X86,APIC] trust the local apic timer |
ada9cfdd | 2306 | in C2 power state. |
e585bef8 | 2307 | |
fcb71f6f FC |
2308 | libata.dma= [LIBATA] DMA control |
2309 | libata.dma=0 Disable all PATA and SATA DMA | |
2310 | libata.dma=1 PATA and SATA Disk DMA only | |
2311 | libata.dma=2 ATAPI (CDROM) DMA only | |
16290246 | 2312 | libata.dma=4 Compact Flash DMA only |
fcb71f6f FC |
2313 | Combinations also work, so libata.dma=3 enables DMA |
2314 | for disks and CDROMs, but not CFs. | |
16290246 | 2315 | |
20308871 MP |
2316 | libata.ignore_hpa= [LIBATA] Ignore HPA limit |
2317 | libata.ignore_hpa=0 keep BIOS limits (default) | |
2318 | libata.ignore_hpa=1 ignore limits, using full disk | |
fcb71f6f | 2319 | |
78e70c23 DJ |
2320 | libata.noacpi [LIBATA] Disables use of ACPI in libata suspend/resume |
2321 | when set. | |
2322 | Format: <int> | |
2323 | ||
33267325 TH |
2324 | libata.force= [LIBATA] Force configurations. The format is comma |
2325 | separated list of "[ID:]VAL" where ID is | |
4c44f309 | 2326 | PORT[.DEVICE]. PORT and DEVICE are decimal numbers |
33267325 TH |
2327 | matching port, link or device. Basically, it matches |
2328 | the ATA ID string printed on console by libata. If | |
2329 | the whole ID part is omitted, the last PORT and DEVICE | |
2330 | values are used. If ID hasn't been specified yet, the | |
2331 | configuration applies to all ports, links and devices. | |
2332 | ||
2333 | If only DEVICE is omitted, the parameter applies to | |
2334 | the port and all links and devices behind it. DEVICE | |
2335 | number of 0 either selects the first device or the | |
2336 | first fan-out link behind PMP device. It does not | |
2337 | select the host link. DEVICE number of 15 selects the | |
2338 | host link and device attached to it. | |
2339 | ||
2340 | The VAL specifies the configuration to force. As long | |
2341 | as there's no ambiguity shortcut notation is allowed. | |
2342 | For example, both 1.5 and 1.5G would work for 1.5Gbps. | |
2343 | The following configurations can be forced. | |
2344 | ||
2345 | * Cable type: 40c, 80c, short40c, unk, ign or sata. | |
2346 | Any ID with matching PORT is used. | |
2347 | ||
2348 | * SATA link speed limit: 1.5Gbps or 3.0Gbps. | |
2349 | ||
2350 | * Transfer mode: pio[0-7], mwdma[0-4] and udma[0-7]. | |
2351 | udma[/][16,25,33,44,66,100,133] notation is also | |
2352 | allowed. | |
2353 | ||
2354 | * [no]ncq: Turn on or off NCQ. | |
2355 | ||
d7b16e4f MP |
2356 | * [no]ncqtrim: Turn off queued DSM TRIM. |
2357 | ||
05944bdf | 2358 | * nohrst, nosrst, norst: suppress hard, soft |
6dddd7a7 | 2359 | and both resets. |
05944bdf | 2360 | |
ca6d43b0 DW |
2361 | * rstonce: only attempt one reset during |
2362 | hot-unplug link recovery | |
2363 | ||
43c9c591 TH |
2364 | * dump_id: dump IDENTIFY data. |
2365 | ||
966fbe19 VP |
2366 | * atapi_dmadir: Enable ATAPI DMADIR bridge support |
2367 | ||
b8bd6dc3 RJ |
2368 | * disable: Disable this device. |
2369 | ||
33267325 TH |
2370 | If there are multiple matching configurations changing |
2371 | the same attribute, the last one is used. | |
2372 | ||
95f72d1e | 2373 | memblock=debug [KNL] Enable memblock debug messages. |
7c4be253 | 2374 | |
1da177e4 | 2375 | load_ramdisk= [RAM] List of ramdisks to load from floppy |
e7751617 | 2376 | See Documentation/admin-guide/blockdev/ramdisk.rst. |
1da177e4 | 2377 | |
a6b25b67 RD |
2378 | lockd.nlm_grace_period=P [NFS] Assign grace period. |
2379 | Format: <integer> | |
1da177e4 | 2380 | |
a6b25b67 RD |
2381 | lockd.nlm_tcpport=N [NFS] Assign TCP port. |
2382 | Format: <integer> | |
2383 | ||
2384 | lockd.nlm_timeout=T [NFS] Assign timeout value. | |
2385 | Format: <integer> | |
2386 | ||
2387 | lockd.nlm_udpport=M [NFS] Assign UDP port. | |
2388 | Format: <integer> | |
1da177e4 | 2389 | |
000d388e MG |
2390 | lockdown= [SECURITY] |
2391 | { integrity | confidentiality } | |
2392 | Enable the kernel lockdown feature. If set to | |
2393 | integrity, kernel features that allow userland to | |
2394 | modify the running kernel are disabled. If set to | |
2395 | confidentiality, kernel features that allow userland | |
2396 | to extract confidential information from the kernel | |
2397 | are also disabled. | |
2398 | ||
ec4518aa PM |
2399 | locktorture.nreaders_stress= [KNL] |
2400 | Set the number of locking read-acquisition kthreads. | |
2401 | Defaults to being automatically set based on the | |
2402 | number of online CPUs. | |
2403 | ||
2404 | locktorture.nwriters_stress= [KNL] | |
2405 | Set the number of locking write-acquisition kthreads. | |
2406 | ||
2407 | locktorture.onoff_holdoff= [KNL] | |
2408 | Set time (s) after boot for CPU-hotplug testing. | |
2409 | ||
2410 | locktorture.onoff_interval= [KNL] | |
2411 | Set time (s) between CPU-hotplug operations, or | |
2412 | zero to disable CPU-hotplug testing. | |
2413 | ||
2414 | locktorture.shuffle_interval= [KNL] | |
2415 | Set task-shuffle interval (jiffies). Shuffling | |
2416 | tasks allows some CPUs to go into dyntick-idle | |
2417 | mode during the locktorture test. | |
2418 | ||
2419 | locktorture.shutdown_secs= [KNL] | |
2420 | Set time (s) after boot system shutdown. This | |
2421 | is useful for hands-off automated testing. | |
2422 | ||
2423 | locktorture.stat_interval= [KNL] | |
2424 | Time (s) between statistics printk()s. | |
2425 | ||
2426 | locktorture.stutter= [KNL] | |
2427 | Time (s) to stutter testing, for example, | |
2428 | specifying five seconds causes the test to run for | |
2429 | five seconds, wait for five seconds, and so on. | |
2430 | This tests the locking primitive's ability to | |
2431 | transition abruptly to and from idle. | |
2432 | ||
ec4518aa PM |
2433 | locktorture.torture_type= [KNL] |
2434 | Specify the locking implementation to test. | |
2435 | ||
2436 | locktorture.verbose= [KNL] | |
2437 | Enable additional printk() statements. | |
2438 | ||
1da177e4 LT |
2439 | logibm.irq= [HW,MOUSE] Logitech Bus Mouse Driver |
2440 | Format: <irq> | |
2441 | ||
2442 | loglevel= All Kernel Messages with a loglevel smaller than the | |
2443 | console loglevel will be printed to the console. It can | |
2444 | also be changed with klogd or other programs. The | |
2445 | loglevels are defined as follows: | |
2446 | ||
2447 | 0 (KERN_EMERG) system is unusable | |
2448 | 1 (KERN_ALERT) action must be taken immediately | |
2449 | 2 (KERN_CRIT) critical conditions | |
2450 | 3 (KERN_ERR) error conditions | |
2451 | 4 (KERN_WARNING) warning conditions | |
2452 | 5 (KERN_NOTICE) normal but significant condition | |
2453 | 6 (KERN_INFO) informational | |
2454 | 7 (KERN_DEBUG) debug-level messages | |
2455 | ||
c756d08a | 2456 | log_buf_len=n[KMG] Sets the size of the printk ring buffer, |
23b2899f LR |
2457 | in bytes. n must be a power of two and greater |
2458 | than the minimal size. The minimal size is defined | |
2459 | by LOG_BUF_SHIFT kernel config parameter. There is | |
2460 | also CONFIG_LOG_CPU_MAX_BUF_SHIFT config parameter | |
2461 | that allows to increase the default size depending on | |
2462 | the number of CPUs. See init/Kconfig for more details. | |
1da177e4 | 2463 | |
accaa24c RD |
2464 | logo.nologo [FB] Disables display of the built-in Linux logo. |
2465 | This may be used to provide more screen space for | |
2466 | kernel log messages and is useful when debugging | |
2467 | kernel boot problems. | |
2468 | ||
1da177e4 LT |
2469 | lp=0 [LP] Specify parallel ports to use, e.g, |
2470 | lp=port[,port...] lp=none,parport0 (lp0 not configured, lp1 uses | |
2471 | lp=reset first parallel port). 'lp=0' disables the | |
2472 | lp=auto printer driver. 'lp=reset' (which can be | |
2473 | specified in addition to the ports) causes | |
2474 | attached printers to be reset. Using | |
2475 | lp=port1,port2,... specifies the parallel ports | |
2476 | to associate lp devices with, starting with | |
2477 | lp0. A port specification may be 'none' to skip | |
2478 | that lp device, or a parport name such as | |
2479 | 'parport0'. Specifying 'lp=auto' instead of a | |
2480 | port specification list means that device IDs | |
2481 | from each port should be examined, to see if | |
2482 | an IEEE 1284-compliant printer is attached; if | |
2483 | so, the driver will manage that printer. | |
2484 | See also header of drivers/char/lp.c. | |
2485 | ||
2486 | lpj=n [KNL] | |
2487 | Sets loops_per_jiffy to given constant, thus avoiding | |
2488 | time-consuming boot-time autodetection (up to 250 ms per | |
2489 | CPU). 0 enables autodetection (default). To determine | |
2490 | the correct value for your kernel, boot with normal | |
2491 | autodetection and see what value is printed. Note that | |
2492 | on SMP systems the preset will be applied to all CPUs, | |
2493 | which is likely to cause problems if your CPUs need | |
2494 | significantly divergent settings. An incorrect value | |
2495 | will cause delays in the kernel to be wrong, leading to | |
2496 | unpredictable I/O errors and other breakage. Although | |
2497 | unlikely, in the extreme case this might damage your | |
2498 | hardware. | |
2499 | ||
2500 | ltpc= [NET] | |
2501 | Format: <io>,<irq>,<dma> | |
2502 | ||
9b8c7c14 KC |
2503 | lsm.debug [SECURITY] Enable LSM initialization debugging output. |
2504 | ||
79f7865d KC |
2505 | lsm=lsm1,...,lsmN |
2506 | [SECURITY] Choose order of LSM initialization. This | |
89a9684e | 2507 | overrides CONFIG_LSM, and the "security=" parameter. |
79f7865d | 2508 | |
16290246 | 2509 | machvec= [IA-64] Force the use of a particular machine-vector |
a9913044 | 2510 | (machvec) in a generic kernel. |
df43acac | 2511 | Example: machvec=hpzx1 |
1da177e4 | 2512 | |
3209e70e WZ |
2513 | machtype= [Loongson] Share the same kernel image file between different |
2514 | yeeloong laptop. | |
2515 | Example: machtype=lemote-yeeloong-2f-7inch | |
2516 | ||
0cb55ad2 RD |
2517 | max_addr=nn[KMG] [KNL,BOOT,ia64] All physical memory greater |
2518 | than or equal to this physical address is ignored. | |
1da177e4 LT |
2519 | |
2520 | maxcpus= [SMP] Maximum number of processors that an SMP kernel | |
7c142bfe BH |
2521 | will bring up during bootup. maxcpus=n : n >= 0 limits |
2522 | the kernel to bring up 'n' processors. Surely after | |
2523 | bootup you can bring up the other plugged cpu by executing | |
2524 | "echo 1 > /sys/devices/system/cpu/cpuX/online". So maxcpus | |
2525 | only takes effect during system bootup. | |
2526 | While n=0 is a special case, it is equivalent to "nosmp", | |
2527 | which also disables the IO APIC. | |
1da177e4 | 2528 | |
d134b00b KS |
2529 | max_loop= [LOOP] The number of loop block devices that get |
2530 | (loop.max_loop) unconditionally pre-created at init time. The default | |
2531 | number is configured by BLK_DEV_LOOP_MIN_COUNT. Instead | |
2532 | of statically allocating a predefined number, loop | |
2533 | devices can be requested on-demand with the | |
2534 | /dev/loop-control interface. | |
2b2c3750 | 2535 | |
cd4f0ef7 | 2536 | mce [X86-32] Machine Check Exception |
1da177e4 | 2537 | |
cb1aaebe | 2538 | mce=option [X86-64] See Documentation/x86/x86_64/boot-options.rst |
909dd324 | 2539 | |
1da177e4 | 2540 | md= [HW] RAID subsystems devices and level |
e52347bd | 2541 | See Documentation/admin-guide/md.rst. |
a9913044 | 2542 | |
1da177e4 LT |
2543 | mdacon= [MDA] |
2544 | Format: <first>,<last> | |
2545 | Specifies range of consoles to be captured by the MDA. | |
a9913044 | 2546 | |
bc124170 TG |
2547 | mds= [X86,INTEL] |
2548 | Control mitigation for the Micro-architectural Data | |
2549 | Sampling (MDS) vulnerability. | |
2550 | ||
2551 | Certain CPUs are vulnerable to an exploit against CPU | |
2552 | internal buffers which can forward information to a | |
2553 | disclosure gadget under certain conditions. | |
2554 | ||
2555 | In vulnerable processors, the speculatively | |
2556 | forwarded data can be used in a cache side channel | |
2557 | attack, to access data to which the attacker does | |
2558 | not have direct access. | |
2559 | ||
2560 | This parameter controls the MDS mitigation. The | |
2561 | options are: | |
2562 | ||
d71eb0ce JP |
2563 | full - Enable MDS mitigation on vulnerable CPUs |
2564 | full,nosmt - Enable MDS mitigation and disable | |
2565 | SMT on vulnerable CPUs | |
2566 | off - Unconditionally disable MDS mitigation | |
bc124170 | 2567 | |
64870ed1 WL |
2568 | On TAA-affected machines, mds=off can be prevented by |
2569 | an active TAA mitigation as both vulnerabilities are | |
2570 | mitigated with the same mechanism so in order to disable | |
2571 | this mitigation, you need to specify tsx_async_abort=off | |
2572 | too. | |
2573 | ||
bc124170 TG |
2574 | Not specifying this option is equivalent to |
2575 | mds=full. | |
2576 | ||
5999bbe7 TG |
2577 | For details see: Documentation/admin-guide/hw-vuln/mds.rst |
2578 | ||
1da177e4 | 2579 | mem=nn[KMG] [KNL,BOOT] Force usage of a specific amount of memory |
f3cd4c86 BH |
2580 | Amount of memory to be used in cases as follows: |
2581 | ||
2582 | 1 for test; | |
2583 | 2 when the kernel is not able to see the whole system memory; | |
2584 | 3 memory that lies after 'mem=' boundary is excluded from | |
2585 | the hypervisor, then assigned to KVM guests. | |
2586 | ||
fbb97d87 WC |
2587 | [X86] Work as limiting max address. Use together |
2588 | with memmap= to avoid physical address space collisions. | |
2589 | Without memmap= PCI devices could be placed at addresses | |
2590 | belonging to unused RAM. | |
1da177e4 | 2591 | |
f3cd4c86 BH |
2592 | Note that this only takes effects during boot time since |
2593 | in above case 3, memory may need be hot added after boot | |
2594 | if system memory of hypervisor is not sufficient. | |
2595 | ||
cd4f0ef7 | 2596 | mem=nopentium [BUGS=X86-32] Disable usage of 4MB pages for kernel |
1da177e4 LT |
2597 | memory. |
2598 | ||
6902aa84 PM |
2599 | memchunk=nn[KMG] |
2600 | [KNL,SH] Allow user to override the default size for | |
2601 | per-device physically contiguous DMA buffers. | |
2602 | ||
6dddd7a7 | 2603 | memhp_default_state=online/offline |
86dd995d VK |
2604 | [KNL] Set the initial state for the memory hotplug |
2605 | onlining policy. If not specified, the default value is | |
2606 | set according to the | |
2607 | CONFIG_MEMORY_HOTPLUG_DEFAULT_ONLINE kernel config | |
2608 | option. | |
cb1aaebe | 2609 | See Documentation/admin-guide/mm/memory-hotplug.rst. |
86dd995d | 2610 | |
6cececfc | 2611 | memmap=exactmap [KNL,X86] Enable setting of an exact |
1da177e4 LT |
2612 | E820 memory map, as specified by the user. |
2613 | Such memmap=exactmap lines can be constructed based on | |
2614 | BIOS output or other requirements. See the memmap=nn@ss | |
2615 | option description. | |
2616 | ||
2617 | memmap=nn[KMG]@ss[KMG] | |
277cba1d RD |
2618 | [KNL] Force usage of a specific region of memory. |
2619 | Region of memory to be used is from ss to ss+nn. | |
8fcc9bc3 BH |
2620 | If @ss[KMG] is omitted, it is equivalent to mem=nn[KMG], |
2621 | which limits max address to nn[KMG]. | |
2622 | Multiple different regions can be specified, | |
2623 | comma delimited. | |
2624 | Example: | |
2625 | memmap=100M@2G,100M#3G,1G!1024G | |
1da177e4 LT |
2626 | |
2627 | memmap=nn[KMG]#ss[KMG] | |
2628 | [KNL,ACPI] Mark specific memory as ACPI data. | |
277cba1d | 2629 | Region of memory to be marked is from ss to ss+nn. |
1da177e4 LT |
2630 | |
2631 | memmap=nn[KMG]$ss[KMG] | |
2632 | [KNL,ACPI] Mark specific memory as reserved. | |
277cba1d | 2633 | Region of memory to be reserved is from ss to ss+nn. |
1312848e PM |
2634 | Example: Exclude memory from 0x18690000-0x1869ffff |
2635 | memmap=64K$0x18690000 | |
2636 | or | |
2637 | memmap=0x10000$0x18690000 | |
8fcc9bc3 BH |
2638 | Some bootloaders may need an escape character before '$', |
2639 | like Grub2, otherwise '$' and the following number | |
2640 | will be eaten. | |
1da177e4 | 2641 | |
ec776ef6 CH |
2642 | memmap=nn[KMG]!ss[KMG] |
2643 | [KNL,X86] Mark specific memory as protected. | |
2644 | Region of memory to be used, from ss to ss+nn. | |
2645 | The memory region may be marked as e820 type 12 (0xc) | |
2646 | and is NVDIMM or ADR memory. | |
2647 | ||
ef61f8a3 JS |
2648 | memmap=<size>%<offset>-<oldtype>+<newtype> |
2649 | [KNL,ACPI] Convert memory within the specified region | |
2650 | from <oldtype> to <newtype>. If "-<oldtype>" is left | |
2651 | out, the whole region will be marked as <newtype>, | |
2652 | even if previously unavailable. If "+<newtype>" is left | |
2653 | out, matching memory will be removed. Types are | |
2654 | specified as e820 types, e.g., 1 = RAM, 2 = reserved, | |
2655 | 3 = ACPI, 12 = PRAM. | |
2656 | ||
9f077871 JF |
2657 | memory_corruption_check=0/1 [X86] |
2658 | Some BIOSes seem to corrupt the first 64k of | |
2659 | memory when doing things like suspend/resume. | |
2660 | Setting this option will scan the memory | |
2661 | looking for corruption. Enabling this will | |
2662 | both detect corruption and prevent the kernel | |
2663 | from using the memory being corrupted. | |
2664 | However, its intended as a diagnostic tool; if | |
2665 | repeatable BIOS-originated corruption always | |
2666 | affects the same memory, you can use memmap= | |
2667 | to prevent the kernel from using that memory. | |
2668 | ||
2669 | memory_corruption_check_size=size [X86] | |
2670 | By default it checks for corruption in the low | |
2671 | 64k, making this memory unavailable for normal | |
2672 | use. Use this parameter to scan for | |
2673 | corruption in more or less memory. | |
2674 | ||
2675 | memory_corruption_check_period=seconds [X86] | |
2676 | By default it checks for corruption every 60 | |
2677 | seconds. Use this parameter to check at some | |
2678 | other rate. 0 disables periodic checking. | |
2679 | ||
d90fe2ac | 2680 | memtest= [KNL,X86,ARM,PPC] Enable memtest |
c64df707 | 2681 | Format: <integer> |
c64df707 | 2682 | default : 0 <disable> |
9e5f6cf5 AH |
2683 | Specifies the number of memtest passes to be |
2684 | performed. Each pass selects another test | |
2685 | pattern from a given set of patterns. Memtest | |
2686 | fills the memory with this pattern, validates | |
2687 | memory contents and reserves bad memory | |
2688 | regions that are detected. | |
c64df707 | 2689 | |
c262f3b9 TL |
2690 | mem_encrypt= [X86-64] AMD Secure Memory Encryption (SME) control |
2691 | Valid arguments: on, off | |
2692 | Default (depends on kernel configuration option): | |
2693 | on (CONFIG_AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT=y) | |
2694 | off (CONFIG_AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT=n) | |
2695 | mem_encrypt=on: Activate SME | |
2696 | mem_encrypt=off: Do not activate SME | |
2697 | ||
2f5947df | 2698 | Refer to Documentation/virt/kvm/amd-memory-encryption.rst |
c262f3b9 TL |
2699 | for details on when memory encryption can be activated. |
2700 | ||
406e7938 RW |
2701 | mem_sleep_default= [SUSPEND] Default system suspend mode: |
2702 | s2idle - Suspend-To-Idle | |
2703 | shallow - Power-On Suspend or equivalent (if supported) | |
2704 | deep - Suspend-To-RAM or equivalent (if supported) | |
58e7cb9e | 2705 | See Documentation/admin-guide/pm/sleep-states.rst. |
406e7938 | 2706 | |
1da177e4 | 2707 | meye.*= [HW] Set MotionEye Camera parameters |
a405ed85 | 2708 | See Documentation/media/v4l-drivers/meye.rst. |
1da177e4 | 2709 | |
8f36881b AS |
2710 | mfgpt_irq= [IA-32] Specify the IRQ to use for the |
2711 | Multi-Function General Purpose Timers on AMD Geode | |
2712 | platforms. | |
2713 | ||
e6c4dc6c WT |
2714 | mfgptfix [X86-32] Fix MFGPT timers on AMD Geode platforms when |
2715 | the BIOS has incorrectly applied a workaround. TinyBIOS | |
2716 | version 0.98 is known to be affected, 0.99 fixes the | |
2717 | problem by letting the user disable the workaround. | |
2718 | ||
1da177e4 LT |
2719 | mga= [HW,DRM] |
2720 | ||
1c207f95 RD |
2721 | min_addr=nn[KMG] [KNL,BOOT,ia64] All physical memory below this |
2722 | physical address is ignored. | |
2723 | ||
39f45d7b MP |
2724 | mini2440= [ARM,HW,KNL] |
2725 | Format:[0..2][b][c][t] | |
2726 | Default: "0tb" | |
2727 | MINI2440 configuration specification: | |
2728 | 0 - The attached screen is the 3.5" TFT | |
2729 | 1 - The attached screen is the 7" TFT | |
2730 | 2 - The VGA Shield is attached (1024x768) | |
2731 | Leaving out the screen size parameter will not load | |
2732 | the TFT driver, and the framebuffer will be left | |
2733 | unconfigured. | |
2734 | b - Enable backlight. The TFT backlight pin will be | |
2735 | linked to the kernel VESA blanking code and a GPIO | |
2736 | LED. This parameter is not necessary when using the | |
2737 | VGA shield. | |
2738 | c - Enable the s3c camera interface. | |
2739 | t - Reserved for enabling touchscreen support. The | |
2740 | touchscreen support is not enabled in the mainstream | |
2741 | kernel as of 2.6.30, a preliminary port can be found | |
2742 | in the "bleeding edge" mini2440 support kernel at | |
2743 | http://repo.or.cz/w/linux-2.6/mini2440.git | |
2744 | ||
98af8452 | 2745 | mitigations= |
a111b7c0 JP |
2746 | [X86,PPC,S390,ARM64] Control optional mitigations for |
2747 | CPU vulnerabilities. This is a set of curated, | |
d68be4c4 JP |
2748 | arch-independent options, each of which is an |
2749 | aggregation of existing arch-specific options. | |
98af8452 JP |
2750 | |
2751 | off | |
2752 | Disable all optional CPU mitigations. This | |
2753 | improves system performance, but it may also | |
2754 | expose users to several CPU vulnerabilities. | |
782e69ef | 2755 | Equivalent to: nopti [X86,PPC] |
a111b7c0 | 2756 | kpti=0 [ARM64] |
a2059825 | 2757 | nospectre_v1 [X86,PPC] |
0336e04a | 2758 | nobp=0 [S390] |
a111b7c0 | 2759 | nospectre_v2 [X86,PPC,S390,ARM64] |
d68be4c4 | 2760 | spectre_v2_user=off [X86] |
782e69ef | 2761 | spec_store_bypass_disable=off [X86,PPC] |
a111b7c0 | 2762 | ssbd=force-off [ARM64] |
d68be4c4 | 2763 | l1tf=off [X86] |
5c14068f | 2764 | mds=off [X86] |
a7a248c5 | 2765 | tsx_async_abort=off [X86] |
b8e8c830 PB |
2766 | kvm.nx_huge_pages=off [X86] |
2767 | ||
2768 | Exceptions: | |
2769 | This does not have any effect on | |
2770 | kvm.nx_huge_pages when | |
2771 | kvm.nx_huge_pages=force. | |
98af8452 JP |
2772 | |
2773 | auto (default) | |
2774 | Mitigate all CPU vulnerabilities, but leave SMT | |
2775 | enabled, even if it's vulnerable. This is for | |
2776 | users who don't want to be surprised by SMT | |
2777 | getting disabled across kernel upgrades, or who | |
2778 | have other ways of avoiding SMT-based attacks. | |
d68be4c4 | 2779 | Equivalent to: (default behavior) |
98af8452 JP |
2780 | |
2781 | auto,nosmt | |
2782 | Mitigate all CPU vulnerabilities, disabling SMT | |
2783 | if needed. This is for users who always want to | |
2784 | be fully mitigated, even if it means losing SMT. | |
d68be4c4 | 2785 | Equivalent to: l1tf=flush,nosmt [X86] |
5c14068f | 2786 | mds=full,nosmt [X86] |
a7a248c5 | 2787 | tsx_async_abort=full,nosmt [X86] |
98af8452 | 2788 | |
6b74ab97 MG |
2789 | mminit_loglevel= |
2790 | [KNL] When CONFIG_DEBUG_MEMORY_INIT is set, this | |
2791 | parameter allows control of the logging verbosity for | |
2792 | the additional memory initialisation checks. A value | |
2793 | of 0 disables mminit logging and a level of 4 will | |
2794 | log everything. Information is printed at KERN_DEBUG | |
2795 | so loglevel=8 may also need to be specified. | |
2796 | ||
106a4ee2 RR |
2797 | module.sig_enforce |
2798 | [KNL] When CONFIG_MODULE_SIG is set, this means that | |
2799 | modules without (valid) signatures will fail to load. | |
2a039be7 | 2800 | Note that if CONFIG_MODULE_SIG_FORCE is set, that |
106a4ee2 RR |
2801 | is always true, so this option does nothing. |
2802 | ||
be7de5f9 PB |
2803 | module_blacklist= [KNL] Do not load a comma-separated list of |
2804 | modules. Useful for debugging problem modules. | |
2805 | ||
1da177e4 LT |
2806 | mousedev.tap_time= |
2807 | [MOUSE] Maximum time between finger touching and | |
2808 | leaving touchpad surface for touch to be considered | |
2809 | a tap and be reported as a left button click (for | |
2810 | touchpads working in absolute mode only). | |
2811 | Format: <msecs> | |
2812 | mousedev.xres= [MOUSE] Horizontal screen resolution, used for devices | |
2813 | reporting absolute coordinates, such as tablets | |
2814 | mousedev.yres= [MOUSE] Vertical screen resolution, used for devices | |
2815 | reporting absolute coordinates, such as tablets | |
2816 | ||
a5c6d650 DR |
2817 | movablecore= [KNL,X86,IA-64,PPC] |
2818 | Format: nn[KMGTPE] | nn% | |
2819 | This parameter is the complement to kernelcore=, it | |
2820 | specifies the amount of memory used for migratable | |
2821 | allocations. If both kernelcore and movablecore is | |
2822 | specified, then kernelcore will be at *least* the | |
2823 | specified value but may be more. If movablecore on its | |
2824 | own is specified, the administrator must be careful | |
0cb55ad2 RD |
2825 | that the amount of memory usable for all allocations |
2826 | is not too small. | |
2827 | ||
f70029bb MH |
2828 | movable_node [KNL] Boot-time switch to make hotplugable memory |
2829 | NUMA nodes to be movable. This means that the memory | |
2830 | of such nodes will be usable only for movable | |
2831 | allocations which rules out almost all kernel | |
2832 | allocations. Use with caution! | |
c5320926 | 2833 | |
1da177e4 LT |
2834 | MTD_Partition= [MTD] |
2835 | Format: <name>,<region-number>,<size>,<offset> | |
2836 | ||
a9913044 RD |
2837 | MTD_Region= [MTD] Format: |
2838 | <name>,<region-number>[,<base>,<size>,<buswidth>,<altbuswidth>] | |
1da177e4 LT |
2839 | |
2840 | mtdparts= [MTD] | |
fb251124 | 2841 | See drivers/mtd/parsers/cmdlinepart.c |
1da177e4 | 2842 | |
4e89a2d8 WS |
2843 | multitce=off [PPC] This parameter disables the use of the pSeries |
2844 | firmware feature for updating multiple TCE entries | |
2845 | at a time. | |
2846 | ||
5988af23 RH |
2847 | onenand.bdry= [HW,MTD] Flex-OneNAND Boundary Configuration |
2848 | ||
2849 | Format: [die0_boundary][,die0_lock][,die1_boundary][,die1_lock] | |
2850 | ||
2851 | boundary - index of last SLC block on Flex-OneNAND. | |
2852 | The remaining blocks are configured as MLC blocks. | |
2853 | lock - Configure if Flex-OneNAND boundary should be locked. | |
2854 | Once locked, the boundary cannot be changed. | |
2855 | 1 indicates lock status, 0 indicates unlock status. | |
2856 | ||
9db829f4 BD |
2857 | mtdset= [ARM] |
2858 | ARM/S3C2412 JIVE boot control | |
2859 | ||
2860 | See arch/arm/mach-s3c2412/mach-jive.c | |
2861 | ||
1da177e4 | 2862 | mtouchusb.raw_coordinates= |
a9913044 RD |
2863 | [HW] Make the MicroTouch USB driver use raw coordinates |
2864 | ('y', default) or cooked coordinates ('n') | |
1da177e4 | 2865 | |
0cb55ad2 | 2866 | mtrr_chunk_size=nn[KMG] [X86] |
19f59460 | 2867 | used for mtrr cleanup. It is largest continuous chunk |
0cb55ad2 RD |
2868 | that could hold holes aka. UC entries. |
2869 | ||
2870 | mtrr_gran_size=nn[KMG] [X86] | |
2871 | Used for mtrr cleanup. It is granularity of mtrr block. | |
2872 | Default is 1. | |
2873 | Large value could prevent small alignment from | |
2874 | using up MTRRs. | |
2875 | ||
2876 | mtrr_spare_reg_nr=n [X86] | |
2877 | Format: <integer> | |
2878 | Range: 0,7 : spare reg number | |
2879 | Default : 1 | |
2880 | Used for mtrr cleanup. It is spare mtrr entries number. | |
2881 | Set to 2 or more if your graphical card needs more. | |
2882 | ||
1da177e4 LT |
2883 | n2= [NET] SDL Inc. RISCom/N2 synchronous serial card |
2884 | ||
1da177e4 LT |
2885 | netdev= [NET] Network devices parameters |
2886 | Format: <irq>,<io>,<mem_start>,<mem_end>,<name> | |
2887 | Note that mem_start is often overloaded to mean | |
2888 | something different and driver-specific. | |
a9913044 RD |
2889 | This usage is only documented in each driver source |
2890 | file if at all. | |
2891 | ||
58401572 KPO |
2892 | nf_conntrack.acct= |
2893 | [NETFILTER] Enable connection tracking flow accounting | |
2894 | 0 to disable accounting | |
2895 | 1 to enable accounting | |
d70a011d | 2896 | Default value is 0. |
58401572 | 2897 | |
306a0753 | 2898 | nfsaddrs= [NFS] Deprecated. Use ip= instead. |
3eb30c51 | 2899 | See Documentation/admin-guide/nfs/nfsroot.rst. |
1da177e4 LT |
2900 | |
2901 | nfsroot= [NFS] nfs root filesystem for disk-less boxes. | |
3eb30c51 | 2902 | See Documentation/admin-guide/nfs/nfsroot.rst. |
1da177e4 | 2903 | |
306a0753 | 2904 | nfsrootdebug [NFS] enable nfsroot debugging messages. |
3eb30c51 | 2905 | See Documentation/admin-guide/nfs/nfsroot.rst. |
306a0753 | 2906 | |
5405fc44 TM |
2907 | nfs.callback_nr_threads= |
2908 | [NFSv4] set the total number of threads that the | |
2909 | NFS client will assign to service NFSv4 callback | |
2910 | requests. | |
2911 | ||
a72b4422 TM |
2912 | nfs.callback_tcpport= |
2913 | [NFS] set the TCP port on which the NFSv4 callback | |
2914 | channel should listen. | |
2915 | ||
e571cbf1 TM |
2916 | nfs.cache_getent= |
2917 | [NFS] sets the pathname to the program which is used | |
2918 | to update the NFS client cache entries. | |
2919 | ||
2920 | nfs.cache_getent_timeout= | |
2921 | [NFS] sets the timeout after which an attempt to | |
2922 | update a cache entry is deemed to have failed. | |
2923 | ||
58df095b TM |
2924 | nfs.idmap_cache_timeout= |
2925 | [NFS] set the maximum lifetime for idmapper cache | |
2926 | entries. | |
2927 | ||
f43bf0be TM |
2928 | nfs.enable_ino64= |
2929 | [NFS] enable 64-bit inode numbers. | |
2930 | If zero, the NFS client will fake up a 32-bit inode | |
2931 | number for the readdir() and stat() syscalls instead | |
2932 | of returning the full 64-bit number. | |
2933 | The default is to return 64-bit inode numbers. | |
2934 | ||
5405fc44 TM |
2935 | nfs.max_session_cb_slots= |
2936 | [NFSv4.1] Sets the maximum number of session | |
2937 | slots the client will assign to the callback | |
2938 | channel. This determines the maximum number of | |
2939 | callbacks the client will process in parallel for | |
2940 | a particular server. | |
2941 | ||
ef159e91 TM |
2942 | nfs.max_session_slots= |
2943 | [NFSv4.1] Sets the maximum number of session slots | |
2944 | the client will attempt to negotiate with the server. | |
2945 | This limits the number of simultaneous RPC requests | |
2946 | that the client can send to the NFSv4.1 server. | |
2947 | Note that there is little point in setting this | |
2948 | value higher than the max_tcp_slot_table_limit. | |
2949 | ||
b064eca2 | 2950 | nfs.nfs4_disable_idmapping= |
074b1d12 TM |
2951 | [NFSv4] When set to the default of '1', this option |
2952 | ensures that both the RPC level authentication | |
2953 | scheme and the NFS level operations agree to use | |
2954 | numeric uids/gids if the mount is using the | |
2955 | 'sec=sys' security flavour. In effect it is | |
2956 | disabling idmapping, which can make migration from | |
2957 | legacy NFSv2/v3 systems to NFSv4 easier. | |
2958 | Servers that do not support this mode of operation | |
2959 | will be autodetected by the client, and it will fall | |
2960 | back to using the idmapper. | |
2961 | To turn off this behaviour, set the value to '0'. | |
6f2ea7f2 CL |
2962 | nfs.nfs4_unique_id= |
2963 | [NFS4] Specify an additional fixed unique ident- | |
2964 | ification string that NFSv4 clients can insert into | |
2965 | their nfs_client_id4 string. This is typically a | |
2966 | UUID that is generated at system install time. | |
b064eca2 | 2967 | |
db8ac8ba WAA |
2968 | nfs.send_implementation_id = |
2969 | [NFSv4.1] Send client implementation identification | |
2970 | information in exchange_id requests. | |
2971 | If zero, no implementation identification information | |
2972 | will be sent. | |
2973 | The default is to send the implementation identification | |
2974 | information. | |
e52347bd | 2975 | |
f6de7a39 TM |
2976 | nfs.recover_lost_locks = |
2977 | [NFSv4] Attempt to recover locks that were lost due | |
2978 | to a lease timeout on the server. Please note that | |
2979 | doing this risks data corruption, since there are | |
2980 | no guarantees that the file will remain unchanged | |
2981 | after the locks are lost. | |
2982 | If you want to enable the kernel legacy behaviour of | |
2983 | attempting to recover these locks, then set this | |
2984 | parameter to '1'. | |
2985 | The default parameter value of '0' causes the kernel | |
2986 | not to attempt recovery of lost locks. | |
db8ac8ba | 2987 | |
bbf58bf3 TM |
2988 | nfs4.layoutstats_timer = |
2989 | [NFSv4.2] Change the rate at which the kernel sends | |
2990 | layoutstats to the pNFS metadata server. | |
2991 | ||
2992 | Setting this to value to 0 causes the kernel to use | |
2993 | whatever value is the default set by the layout | |
2994 | driver. A non-zero value sets the minimum interval | |
2995 | in seconds between layoutstats transmissions. | |
2996 | ||
e9541ce8 BF |
2997 | nfsd.nfs4_disable_idmapping= |
2998 | [NFSv4] When set to the default of '1', the NFSv4 | |
2999 | server will return only numeric uids and gids to | |
3000 | clients using auth_sys, and will accept numeric uids | |
3001 | and gids from such clients. This is intended to ease | |
3002 | migration from NFSv2/v3. | |
db8ac8ba | 3003 | |
c0c74acb | 3004 | nmi_debug= [KNL,SH] Specify one or more actions to take |
e7ba176b HS |
3005 | when a NMI is triggered. |
3006 | Format: [state][,regs][,debounce][,die] | |
3007 | ||
6cececfc | 3008 | nmi_watchdog= [KNL,BUGS=X86] Debugging features for SMP kernels |
fef2c9bc | 3009 | Format: [panic,][nopanic,][num] |
195daf66 | 3010 | Valid num: 0 or 1 |
334bb79c PK |
3011 | 0 - turn hardlockup detector in nmi_watchdog off |
3012 | 1 - turn hardlockup detector in nmi_watchdog on | |
0cb55ad2 | 3013 | When panic is specified, panic when an NMI watchdog |
93285c01 ZD |
3014 | timeout occurs (or 'nopanic' to not panic on an NMI |
3015 | watchdog, if CONFIG_BOOTPARAM_HARDLOCKUP_PANIC is set) | |
3016 | To disable both hard and soft lockup detectors, | |
334bb79c | 3017 | please see 'nowatchdog'. |
0cb55ad2 RD |
3018 | This is useful when you use a panic=... timeout and |
3019 | need the box quickly up again. | |
1da177e4 | 3020 | |
d22881dc SW |
3021 | These settings can be accessed at runtime via |
3022 | the nmi_watchdog and hardlockup_panic sysctls. | |
3023 | ||
bff38771 AV |
3024 | netpoll.carrier_timeout= |
3025 | [NET] Specifies amount of time (in seconds) that | |
3026 | netpoll should wait for a carrier. By default netpoll | |
3027 | waits 4 seconds. | |
3028 | ||
cd4f0ef7 | 3029 | no387 [BUGS=X86-32] Tells the kernel to use the 387 maths |
1da177e4 LT |
3030 | emulation library even if a 387 maths coprocessor |
3031 | is present. | |
3032 | ||
372fddf7 KS |
3033 | no5lvl [X86-64] Disable 5-level paging mode. Forces |
3034 | kernel to use 4-level paging instead. | |
3035 | ||
0cb55ad2 RD |
3036 | no_console_suspend |
3037 | [HW] Never suspend the console | |
3038 | Disable suspending of consoles during suspend and | |
3039 | hibernate operations. Once disabled, debugging | |
3040 | messages can reach various consoles while the rest | |
3041 | of the system is being put to sleep (ie, while | |
3042 | debugging driver suspend/resume hooks). This may | |
3043 | not work reliably with all consoles, but is known | |
3044 | to work with serial and VGA consoles. | |
134620f7 YZ |
3045 | To facilitate more flexible debugging, we also add |
3046 | console_suspend, a printk module parameter to control | |
3047 | it. Users could use console_suspend (usually | |
3048 | /sys/module/printk/parameters/console_suspend) to | |
3049 | turn on/off it dynamically. | |
0cb55ad2 | 3050 | |
c6c40533 KS |
3051 | novmcoredd [KNL,KDUMP] |
3052 | Disable device dump. Device dump allows drivers to | |
3053 | append dump data to vmcore so you can collect driver | |
3054 | specified debug info. Drivers can append the data | |
3055 | without any limit and this data is stored in memory, | |
3056 | so this may cause significant memory stress. Disabling | |
3057 | device dump can help save memory but the driver debug | |
3058 | data will be no longer available. This parameter | |
3059 | is only available when CONFIG_PROC_VMCORE_DEVICE_DUMP | |
3060 | is set. | |
3061 | ||
c1aee215 CL |
3062 | noaliencache [MM, NUMA, SLAB] Disables the allocation of alien |
3063 | caches in the slab allocator. Saves per-node memory, | |
3064 | but will impact performance. | |
3395ee05 | 3065 | |
a9913044 RD |
3066 | noalign [KNL,ARM] |
3067 | ||
686140a1 VG |
3068 | noaltinstr [S390] Disables alternative instructions patching |
3069 | (CPU alternatives feature). | |
3070 | ||
1da177e4 LT |
3071 | noapic [SMP,APIC] Tells the kernel to not make use of any |
3072 | IOAPICs that may be present in the system. | |
3073 | ||
5091faa4 MG |
3074 | noautogroup Disable scheduler automatic task group creation. |
3075 | ||
1da177e4 LT |
3076 | nobats [PPC] Do not use BATs for mapping kernel lowmem |
3077 | on "Classic" PPC cores. | |
3078 | ||
3079 | nocache [ARM] | |
a9913044 | 3080 | |
0cb55ad2 RD |
3081 | noclflush [BUGS=X86] Don't use the CLFLUSH instruction |
3082 | ||
163ecdff SN |
3083 | nodelayacct [KNL] Disable per-task delay accounting |
3084 | ||
6902aa84 PM |
3085 | nodsp [SH] Disable hardware DSP at boot time. |
3086 | ||
b2e0a54a | 3087 | noefi Disable EFI runtime services support. |
8b2cb7a8 | 3088 | |
1da177e4 LT |
3089 | noexec [IA-64] |
3090 | ||
6cececfc | 3091 | noexec [X86] |
f5a1b191 | 3092 | On X86-32 available only on PAE configured kernels. |
1da177e4 | 3093 | noexec=on: enable non-executable mappings (default) |
f5a1b191 JS |
3094 | noexec=off: disable non-executable mappings |
3095 | ||
de78a9c4 | 3096 | nosmap [X86,PPC] |
52b6179a PA |
3097 | Disable SMAP (Supervisor Mode Access Prevention) |
3098 | even if it is supported by processor. | |
3099 | ||
0fb1c25a | 3100 | nosmep [X86,PPC] |
52b6179a | 3101 | Disable SMEP (Supervisor Mode Execution Prevention) |
de5397ad FY |
3102 | even if it is supported by processor. |
3103 | ||
f5a1b191 JS |
3104 | noexec32 [X86-64] |
3105 | This affects only 32-bit executables. | |
3106 | noexec32=on: enable non-executable mappings (default) | |
3107 | read doesn't imply executable mappings | |
3108 | noexec32=off: disable non-executable mappings | |
3109 | read implies executable mappings | |
1da177e4 | 3110 | |
fab43ef4 | 3111 | nofpu [MIPS,SH] Disable hardware FPU at boot time. |
6902aa84 | 3112 | |
cd4f0ef7 | 3113 | nofxsr [BUGS=X86-32] Disables x86 floating point extended |
4f886511 CE |
3114 | register save and restore. The kernel will only save |
3115 | legacy floating-point registers on task switch. | |
1da177e4 | 3116 | |
d909f910 | 3117 | nohugeiomap [KNL,x86,PPC] Disable kernel huge I/O mappings. |
0ddab1d2 | 3118 | |
52c48c51 SS |
3119 | nosmt [KNL,S390] Disable symmetric multithreading (SMT). |
3120 | Equivalent to smt=1. | |
3121 | ||
05736e4a | 3122 | [KNL,x86] Disable symmetric multithreading (SMT). |
506a66f3 TG |
3123 | nosmt=force: Force disable SMT, cannot be undone |
3124 | via the sysfs control file. | |
5e2d059b | 3125 | |
a2059825 JP |
3126 | nospectre_v1 [X86,PPC] Disable mitigations for Spectre Variant 1 |
3127 | (bounds check bypass). With this option data leaks are | |
3128 | possible in the system. | |
05736e4a | 3129 | |
e5ce5e72 JL |
3130 | nospectre_v2 [X86,PPC_FSL_BOOK3E,ARM64] Disable all mitigations for |
3131 | the Spectre variant 2 (indirect branch prediction) | |
3132 | vulnerability. System may allow data leaks with this | |
3133 | option. | |
da285121 | 3134 | |
24f7fc83 KRW |
3135 | nospec_store_bypass_disable |
3136 | [HW] Disable all mitigations for the Speculative Store Bypass vulnerability | |
3137 | ||
0c752a93 SS |
3138 | noxsave [BUGS=X86] Disables x86 extended register state save |
3139 | and restore using xsave. The kernel will fallback to | |
3140 | enabling legacy floating-point and sse state. | |
3141 | ||
b6f42a4a FY |
3142 | noxsaveopt [X86] Disables xsaveopt used in saving x86 extended |
3143 | register states. The kernel will fall back to use | |
3144 | xsave to save the states. By using this parameter, | |
3145 | performance of saving the states is degraded because | |
3146 | xsave doesn't support modified optimization while | |
3147 | xsaveopt supports it on xsaveopt enabled systems. | |
3148 | ||
3149 | noxsaves [X86] Disables xsaves and xrstors used in saving and | |
3150 | restoring x86 extended register state in compacted | |
3151 | form of xsave area. The kernel will fall back to use | |
3152 | xsaveopt and xrstor to save and restore the states | |
3153 | in standard form of xsave area. By using this | |
3154 | parameter, xsave area per process might occupy more | |
3155 | memory on xsaves enabled systems. | |
3156 | ||
01a24d2b PZ |
3157 | nohlt [BUGS=ARM,SH] Tells the kernel that the sleep(SH) or |
3158 | wfi(ARM) instruction doesn't work correctly and not to | |
3159 | use it. This is also useful when using JTAG debugger. | |
a9913044 | 3160 | |
1f29fae2 SH |
3161 | no_file_caps Tells the kernel not to honor file capabilities. The |
3162 | only way then for a file to be executed with privilege | |
3163 | is to be setuid root or executed by root. | |
3164 | ||
1da177e4 LT |
3165 | nohalt [IA-64] Tells the kernel not to use the power saving |
3166 | function PAL_HALT_LIGHT when idle. This increases | |
3167 | power-consumption. On the positive side, it reduces | |
3168 | interrupt wake-up latency, which may improve performance | |
3169 | in certain environments such as networked servers or | |
3170 | real-time systems. | |
3171 | ||
a6e15a39 KC |
3172 | nohibernate [HIBERNATION] Disable hibernation and resume. |
3173 | ||
79bf2bb3 TG |
3174 | nohz= [KNL] Boottime enable/disable dynamic ticks |
3175 | Valid arguments: on, off | |
3176 | Default: on | |
3177 | ||
d94d1053 | 3178 | nohz_full= [KNL,BOOT,SMP,ISOL] |
2d13e6ca | 3179 | The argument is a cpu list, as described above. |
c5bfece2 | 3180 | In kernels built with CONFIG_NO_HZ_FULL=y, set |
a831881b | 3181 | the specified list of CPUs whose tick will be stopped |
0453b435 | 3182 | whenever possible. The boot CPU will be forced outside |
f99bcb2c PM |
3183 | the range to maintain the timekeeping. Any CPUs |
3184 | in this list will have their RCU callbacks offloaded, | |
3185 | just as if they had also been called out in the | |
3186 | rcu_nocbs= boot parameter. | |
a831881b | 3187 | |
eeee7853 PM |
3188 | noiotrap [SH] Disables trapped I/O port accesses. |
3189 | ||
cd4f0ef7 | 3190 | noirqdebug [X86-32] Disables the code which attempts to detect and |
1da177e4 LT |
3191 | disable unhandled interrupt sources. |
3192 | ||
6cececfc | 3193 | no_timer_check [X86,APIC] Disables the code which tests for |
8542b200 ZA |
3194 | broken timer IRQ sources. |
3195 | ||
1da177e4 LT |
3196 | noisapnp [ISAPNP] Disables ISA PnP code. |
3197 | ||
3198 | noinitrd [RAM] Tells the kernel not to load any configured | |
3199 | initial RAM disk. | |
3200 | ||
03ea8155 WH |
3201 | nointremap [X86-64, Intel-IOMMU] Do not enable interrupt |
3202 | remapping. | |
d1423d56 | 3203 | [Deprecated - use intremap=off] |
03ea8155 | 3204 | |
1da177e4 LT |
3205 | nointroute [IA-64] |
3206 | ||
d12a72b8 AL |
3207 | noinvpcid [X86] Disable the INVPCID cpu feature. |
3208 | ||
16290246 | 3209 | nojitter [IA-64] Disables jitter checking for ITC timers. |
0aa366f3 | 3210 | |
9cf4c4fc JK |
3211 | no-kvmclock [X86,KVM] Disable paravirtualized KVM clock driver |
3212 | ||
fd10cde9 GN |
3213 | no-kvmapf [X86,KVM] Disable paravirtualized asynchronous page |
3214 | fault handling. | |
3215 | ||
80e9a4f2 AM |
3216 | no-vmw-sched-clock |
3217 | [X86,PV_OPS] Disable paravirtualized VMware scheduler | |
3218 | clock and use the default one. | |
3219 | ||
e73a8f38 | 3220 | no-steal-acc [X86,PV_OPS,ARM64] Disable paravirtualized steal time |
e0685fa2 SP |
3221 | accounting. steal time is computed, but won't |
3222 | influence scheduler behaviour | |
d910f5c1 | 3223 | |
cd4f0ef7 | 3224 | nolapic [X86-32,APIC] Do not enable or use the local APIC. |
1da177e4 | 3225 | |
cd4f0ef7 | 3226 | nolapic_timer [X86-32,APIC] Do not use the local APIC timer. |
ad62ca2b | 3227 | |
1da177e4 | 3228 | noltlbs [PPC] Do not use large page/tlb entries for kernel |
f15eea66 | 3229 | lowmem mapping on PPC40x and PPC8xx |
1da177e4 | 3230 | |
312f1f01 H |
3231 | nomca [IA-64] Disable machine check abort handling |
3232 | ||
13696e0a | 3233 | nomce [X86-32] Disable Machine Check Exception |
abe37e5a | 3234 | |
83d7384f AS |
3235 | nomfgpt [X86-32] Disable Multi-Function General Purpose |
3236 | Timer usage (for AMD Geode machines). | |
3237 | ||
bda62633 DZ |
3238 | nonmi_ipi [X86] Disable using NMI IPIs during panic/reboot to |
3239 | shutdown the other cpus. Instead use the REBOOT_VECTOR | |
3240 | irq. | |
3241 | ||
02608bef DY |
3242 | nomodule Disable module load |
3243 | ||
016ddd9b JK |
3244 | nopat [X86] Disable PAT (page attribute table extension of |
3245 | pagetables) support. | |
3246 | ||
0790c9aa AL |
3247 | nopcid [X86-64] Disable the PCID cpu feature. |
3248 | ||
0cb55ad2 RD |
3249 | norandmaps Don't use address space randomization. Equivalent to |
3250 | echo 0 > /proc/sys/kernel/randomize_va_space | |
3251 | ||
cd4f0ef7 | 3252 | noreplace-smp [X86-32,SMP] Don't replace SMP instructions |
b7fb4af0 JF |
3253 | with UP alternatives |
3254 | ||
7a5091d5 PA |
3255 | nordrand [X86] Disable kernel use of the RDRAND and |
3256 | RDSEED instructions even if they are supported | |
3257 | by the processor. RDRAND and RDSEED are still | |
3258 | available to user space applications. | |
49d859d7 | 3259 | |
a9913044 RD |
3260 | noresume [SWSUSP] Disables resume and restores original swap |
3261 | space. | |
3262 | ||
1da177e4 LT |
3263 | no-scroll [VGA] Disables scrollback. |
3264 | This is required for the Braillex ib80-piezo Braille | |
3265 | reader made by F.H. Papenmeier (Germany). | |
3266 | ||
3267 | nosbagart [IA-64] | |
3268 | ||
cd4f0ef7 | 3269 | nosep [BUGS=X86-32] Disables x86 SYSENTER/SYSEXIT support. |
4f886511 | 3270 | |
61ec7567 LB |
3271 | nosmp [SMP] Tells an SMP kernel to act as a UP kernel, |
3272 | and disable the IO APIC. legacy for "maxcpus=0". | |
1da177e4 | 3273 | |
97842216 DJ |
3274 | nosoftlockup [KNL] Disable the soft-lockup detector. |
3275 | ||
1da177e4 LT |
3276 | nosync [HW,M68K] Disables sync negotiation for all devices. |
3277 | ||
195daf66 | 3278 | nowatchdog [KNL] Disable both lockup detectors, i.e. |
6dddd7a7 | 3279 | soft-lockup and NMI watchdog (hard-lockup). |
58687acb | 3280 | |
1da177e4 | 3281 | nowb [ARM] |
a9913044 | 3282 | |
2b2fd87a WH |
3283 | nox2apic [X86-64,APIC] Do not enable x2APIC mode. |
3284 | ||
f78cff48 FY |
3285 | cpu0_hotplug [X86] Turn on CPU0 hotplug feature when |
3286 | CONFIG_BOOTPARAM_HOTPLUG_CPU0 is off. | |
3287 | Some features depend on CPU0. Known dependencies are: | |
3288 | 1. Resume from suspend/hibernate depends on CPU0. | |
3289 | Suspend/hibernate will fail if CPU0 is offline and you | |
3290 | need to online CPU0 before suspend/hibernate. | |
3291 | 2. PIC interrupts also depend on CPU0. CPU0 can't be | |
3292 | removed if a PIC interrupt is detected. | |
3293 | It's said poweroff/reboot may depend on CPU0 on some | |
3294 | machines although I haven't seen such issues so far | |
3295 | after CPU0 is offline on a few tested machines. | |
3296 | If the dependencies are under your control, you can | |
3297 | turn on cpu0_hotplug. | |
3298 | ||
6dddd7a7 | 3299 | nps_mtm_hs_ctr= [KNL,ARC] |
35b55ef2 NC |
3300 | This parameter sets the maximum duration, in |
3301 | cycles, each HW thread of the CTOP can run | |
3302 | without interruptions, before HW switches it. | |
3303 | The actual maximum duration is 16 times this | |
3304 | parameter's value. | |
3305 | Format: integer between 1 and 255 | |
3306 | Default: 255 | |
3307 | ||
16290246 | 3308 | nptcg= [IA-64] Override max number of concurrent global TLB |
a6c75b86 FY |
3309 | purges which is reported from either PAL_VM_SUMMARY or |
3310 | SAL PALO. | |
3311 | ||
2b633e3f YL |
3312 | nr_cpus= [SMP] Maximum number of processors that an SMP kernel |
3313 | could support. nr_cpus=n : n >= 1 limits the kernel to | |
7c142bfe BH |
3314 | support 'n' processors. It could be larger than the |
3315 | number of already plugged CPU during bootup, later in | |
3316 | runtime you can physically add extra cpu until it reaches | |
3317 | n. So during boot up some boot time memory for per-cpu | |
3318 | variables need be pre-allocated for later physical cpu | |
3319 | hot plugging. | |
2b633e3f | 3320 | |
0cb55ad2 RD |
3321 | nr_uarts= [SERIAL] maximum number of UARTs to be registered. |
3322 | ||
1a687c2e MG |
3323 | numa_balancing= [KNL,X86] Enable or disable automatic NUMA balancing. |
3324 | Allowed values are enable and disable | |
3325 | ||
f0c0b2b8 | 3326 | numa_zonelist_order= [KNL, BOOT] Select zonelist order for NUMA. |
c9bff3ee | 3327 | 'node', 'default' can be specified |
f0c0b2b8 | 3328 | This can be set from sysctl after boot. |
57043247 | 3329 | See Documentation/admin-guide/sysctl/vm.rst for details. |
f0c0b2b8 | 3330 | |
7c4be253 RD |
3331 | ohci1394_dma=early [HW] enable debugging via the ohci1394 driver. |
3332 | See Documentation/debugging-via-ohci1394.txt for more | |
3333 | info. | |
3334 | ||
3ef0e1f8 AS |
3335 | olpc_ec_timeout= [OLPC] ms delay when issuing EC commands |
3336 | Rather than timing out after 20 ms if an EC | |
3337 | command is not properly ACKed, override the length | |
3338 | of the timeout. We have interrupts disabled while | |
3339 | waiting for the ACK, so if this is set too high | |
3340 | interrupts *may* be lost! | |
3341 | ||
15ac7afe TL |
3342 | omap_mux= [OMAP] Override bootloader pin multiplexing. |
3343 | Format: <mux_mode0.mode_name=value>... | |
3344 | For example, to override I2C bus2: | |
3345 | omap_mux=i2c2_scl.i2c2_scl=0x100,i2c2_sda.i2c2_sda=0x100 | |
3346 | ||
1da177e4 LT |
3347 | oprofile.timer= [HW] |
3348 | Use timer interrupt instead of performance counters | |
3349 | ||
7e4e0bd5 RR |
3350 | oprofile.cpu_type= Force an oprofile cpu type |
3351 | This might be useful if you have an older oprofile | |
3352 | userland or if you want common events. | |
8d7ff4f2 RR |
3353 | Format: { arch_perfmon } |
3354 | arch_perfmon: [X86] Force use of architectural | |
7e4e0bd5 RR |
3355 | perfmon on Intel CPUs instead of the |
3356 | CPU specific event set. | |
159a80b2 RR |
3357 | timer: [X86] Force use of architectural NMI |
3358 | timer mode (see also oprofile.timer | |
3359 | for generic hr timer mode) | |
1dcdb5a9 | 3360 | |
44a4dcf7 RD |
3361 | oops=panic Always panic on oopses. Default is to just kill the |
3362 | process, but there is a small probability of | |
3363 | deadlocking the machine. | |
d404ab0a OH |
3364 | This will also cause panics on machine check exceptions. |
3365 | Useful together with panic=30 to trigger a reboot. | |
3366 | ||
e900a918 DW |
3367 | page_alloc.shuffle= |
3368 | [KNL] Boolean flag to control whether the page allocator | |
3369 | should randomize its free lists. The randomization may | |
3370 | be automatically enabled if the kernel detects it is | |
3371 | running on a platform with a direct-mapped memory-side | |
3372 | cache, and this parameter can be used to | |
3373 | override/disable that behavior. The state of the flag | |
3374 | can be read from sysfs at: | |
3375 | /sys/module/page_alloc/parameters/shuffle. | |
3376 | ||
48c96a36 JK |
3377 | page_owner= [KNL] Boot-time page_owner enabling option. |
3378 | Storage of the information about who allocated | |
3379 | each page is disabled in default. With this switch, | |
3380 | we can turn it on. | |
3381 | on: enable the feature | |
3382 | ||
8823b1db | 3383 | page_poison= [KNL] Boot-time parameter changing the state of |
8c9a134c KC |
3384 | poisoning on the buddy allocator, available with |
3385 | CONFIG_PAGE_POISONING=y. | |
3386 | off: turn off poisoning (default) | |
8823b1db LA |
3387 | on: turn on poisoning |
3388 | ||
44a4dcf7 | 3389 | panic= [KNL] Kernel behaviour on panic: delay <timeout> |
4302fbc8 HD |
3390 | timeout > 0: seconds before rebooting |
3391 | timeout = 0: wait forever | |
3392 | timeout < 0: reboot immediately | |
1da177e4 LT |
3393 | Format: <timeout> |
3394 | ||
d999bd93 FT |
3395 | panic_print= Bitmask for printing system info when panic happens. |
3396 | User can chose combination of the following bits: | |
3397 | bit 0: print all tasks info | |
3398 | bit 1: print system memory info | |
3399 | bit 2: print timer info | |
3400 | bit 3: print locks info if CONFIG_LOCKDEP is on | |
3401 | bit 4: print ftrace buffer | |
de6da1e8 | 3402 | bit 5: print all printk messages in buffer |
d999bd93 | 3403 | |
9e3961a0 PB |
3404 | panic_on_warn panic() instead of WARN(). Useful to cause kdump |
3405 | on a WARN(). | |
3406 | ||
f06e5153 MH |
3407 | crash_kexec_post_notifiers |
3408 | Run kdump after running panic-notifiers and dumping | |
3409 | kmsg. This only for the users who doubt kdump always | |
3410 | succeeds in any situation. | |
3411 | Note that this also increases risks of kdump failure, | |
3412 | because some panic notifiers can make the crashed | |
3413 | kernel more unstable. | |
3414 | ||
1da177e4 LT |
3415 | parkbd.port= [HW] Parallel port number the keyboard adapter is |
3416 | connected to, default is 0. | |
3417 | Format: <parport#> | |
3418 | parkbd.mode= [HW] Parallel port keyboard adapter mode of operation, | |
3419 | 0 for XT, 1 for AT (default is AT). | |
a9913044 RD |
3420 | Format: <mode> |
3421 | ||
3422 | parport= [HW,PPT] Specify parallel ports. 0 disables. | |
3423 | Format: { 0 | auto | 0xBBB[,IRQ[,DMA]] } | |
3424 | Use 'auto' to force the driver to use any | |
3425 | IRQ/DMA settings detected (the default is to | |
3426 | ignore detected IRQ/DMA settings because of | |
3427 | possible conflicts). You can specify the base | |
3428 | address, IRQ, and DMA settings; IRQ and DMA | |
3429 | should be numbers, or 'auto' (for using detected | |
3430 | settings on that particular port), or 'nofifo' | |
3431 | (to avoid using a FIFO even if it is detected). | |
3432 | Parallel ports are assigned in the order they | |
3433 | are specified on the command line, starting | |
3434 | with parport0. | |
3435 | ||
3436 | parport_init_mode= [HW,PPT] | |
3437 | Configure VIA parallel port to operate in | |
3438 | a specific mode. This is necessary on Pegasos | |
3439 | computer where firmware has no options for setting | |
3440 | up parallel port mode and sets it to spp. | |
3441 | Currently this function knows 686a and 8231 chips. | |
1da177e4 LT |
3442 | Format: [spp|ps2|epp|ecp|ecpepp] |
3443 | ||
dd287796 AM |
3444 | pause_on_oops= |
3445 | Halt all CPUs after the first oops has been printed for | |
3446 | the specified number of seconds. This is to be used if | |
3447 | your oopses keep scrolling off the screen. | |
3448 | ||
1da177e4 LT |
3449 | pcbit= [HW,ISDN] |
3450 | ||
3451 | pcd. [PARIDE] | |
3452 | See header of drivers/block/paride/pcd.c. | |
e7751617 | 3453 | See also Documentation/admin-guide/blockdev/paride.rst. |
1da177e4 | 3454 | |
07d8d7e5 LG |
3455 | pci=option[,option...] [PCI] various PCI subsystem options. |
3456 | ||
3457 | Some options herein operate on a specific device | |
3458 | or a set of devices (<pci_dev>). These are | |
3459 | specified in one of the following formats: | |
3460 | ||
45db3370 | 3461 | [<domain>:]<bus>:<dev>.<func>[/<dev>.<func>]* |
07d8d7e5 LG |
3462 | pci:<vendor>:<device>[:<subvendor>:<subdevice>] |
3463 | ||
3464 | Note: the first format specifies a PCI | |
3465 | bus/device/function address which may change | |
3466 | if new hardware is inserted, if motherboard | |
3467 | firmware changes, or due to changes caused | |
3468 | by other kernel parameters. If the | |
3469 | domain is left unspecified, it is | |
45db3370 LG |
3470 | taken to be zero. Optionally, a path |
3471 | to a device through multiple device/function | |
3472 | addresses can be specified after the base | |
3473 | address (this is more robust against | |
3474 | renumbering issues). The second format | |
07d8d7e5 LG |
3475 | selects devices using IDs from the |
3476 | configuration space which may match multiple | |
3477 | devices in the system. | |
3478 | ||
11eb0e0e | 3479 | earlydump dump PCI config space before the kernel |
6dddd7a7 | 3480 | changes anything |
c0115606 | 3481 | off [X86] don't probe for the PCI bus |
cd4f0ef7 | 3482 | bios [X86-32] force use of PCI BIOS, don't access |
a9913044 RD |
3483 | the hardware directly. Use this if your machine |
3484 | has a non-standard PCI host bridge. | |
cd4f0ef7 | 3485 | nobios [X86-32] disallow use of PCI BIOS, only direct |
a9913044 RD |
3486 | hardware access methods are allowed. Use this |
3487 | if you experience crashes upon bootup and you | |
3488 | suspect they are caused by the BIOS. | |
afd8c084 BP |
3489 | conf1 [X86] Force use of PCI Configuration Access |
3490 | Mechanism 1 (config address in IO port 0xCF8, | |
3491 | data in IO port 0xCFC, both 32-bit). | |
3492 | conf2 [X86] Force use of PCI Configuration Access | |
3493 | Mechanism 2 (IO port 0xCF8 is an 8-bit port for | |
3494 | the function, IO port 0xCFA, also 8-bit, sets | |
3495 | bus number. The config space is then accessed | |
3496 | through ports 0xC000-0xCFFF). | |
3497 | See http://wiki.osdev.org/PCI for more info | |
3498 | on the configuration access mechanisms. | |
7f785763 RD |
3499 | noaer [PCIE] If the PCIEAER kernel config parameter is |
3500 | enabled, this kernel boot option can be used to | |
3501 | disable the use of PCIE advanced error reporting. | |
32a2eea7 JG |
3502 | nodomains [PCI] Disable support for multiple PCI |
3503 | root domains (aka PCI segments, in ACPI-speak). | |
6cececfc | 3504 | nommconf [X86] Disable use of MMCONFIG for PCI |
61be6d66 | 3505 | Configuration |
12983077 AH |
3506 | check_enable_amd_mmconf [X86] check for and enable |
3507 | properly configured MMIO access to PCI | |
3508 | config space on AMD family 10h CPU | |
309e57df MW |
3509 | nomsi [MSI] If the PCI_MSI kernel config parameter is |
3510 | enabled, this kernel boot option can be used to | |
3511 | disable the use of MSI interrupts system-wide. | |
a9322f64 SA |
3512 | noioapicquirk [APIC] Disable all boot interrupt quirks. |
3513 | Safety option to keep boot IRQs enabled. This | |
3514 | should never be necessary. | |
9197979b SA |
3515 | ioapicreroute [APIC] Enable rerouting of boot IRQs to the |
3516 | primary IO-APIC for bridges that cannot disable | |
3517 | boot IRQs. This fixes a source of spurious IRQs | |
3518 | when the system masks IRQs. | |
41b9eb26 SA |
3519 | noioapicreroute [APIC] Disable workaround that uses the |
3520 | boot IRQ equivalent of an IRQ that connects to | |
3521 | a chipset where boot IRQs cannot be disabled. | |
3522 | The opposite of ioapicreroute. | |
cd4f0ef7 | 3523 | biosirq [X86-32] Use PCI BIOS calls to get the interrupt |
a9913044 RD |
3524 | routing table. These calls are known to be buggy |
3525 | on several machines and they hang the machine | |
3526 | when used, but on other computers it's the only | |
3527 | way to get the interrupt routing table. Try | |
3528 | this option if the kernel is unable to allocate | |
3529 | IRQs or discover secondary PCI buses on your | |
3530 | motherboard. | |
c0115606 | 3531 | rom [X86] Assign address space to expansion ROMs. |
a9913044 RD |
3532 | Use with caution as certain devices share |
3533 | address decoders between ROMs and other | |
3534 | resources. | |
c0115606 | 3535 | norom [X86] Do not assign address space to |
bb71ad88 GH |
3536 | expansion ROMs that do not already have |
3537 | BIOS assigned address ranges. | |
7bd1c365 MH |
3538 | nobar [X86] Do not assign address space to the |
3539 | BARs that weren't assigned by the BIOS. | |
c0115606 | 3540 | irqmask=0xMMMM [X86] Set a bit mask of IRQs allowed to be |
a9913044 RD |
3541 | assigned automatically to PCI devices. You can |
3542 | make the kernel exclude IRQs of your ISA cards | |
3543 | this way. | |
c0115606 | 3544 | pirqaddr=0xAAAAA [X86] Specify the physical address |
a9913044 RD |
3545 | of the PIRQ table (normally generated |
3546 | by the BIOS) if it is outside the | |
3547 | F0000h-100000h range. | |
c0115606 | 3548 | lastbus=N [X86] Scan all buses thru bus #N. Can be |
a9913044 RD |
3549 | useful if the kernel is unable to find your |
3550 | secondary buses and you want to tell it | |
3551 | explicitly which ones they are. | |
c0115606 | 3552 | assign-busses [X86] Always assign all PCI bus |
a9913044 RD |
3553 | numbers ourselves, overriding |
3554 | whatever the firmware may have done. | |
c0115606 | 3555 | usepirqmask [X86] Honor the possible IRQ mask stored |
a9913044 RD |
3556 | in the BIOS $PIR table. This is needed on |
3557 | some systems with broken BIOSes, notably | |
3558 | some HP Pavilion N5400 and Omnibook XE3 | |
3559 | notebooks. This will have no effect if ACPI | |
3560 | IRQ routing is enabled. | |
c0115606 | 3561 | noacpi [X86] Do not use ACPI for IRQ routing |
a9913044 | 3562 | or for PCI scanning. |
7bc5e3f2 BH |
3563 | use_crs [X86] Use PCI host bridge window information |
3564 | from ACPI. On BIOSes from 2008 or later, this | |
3565 | is enabled by default. If you need to use this, | |
3566 | please report a bug. | |
3567 | nocrs [X86] Ignore PCI host bridge windows from ACPI. | |
6dddd7a7 | 3568 | If you need to use this, please report a bug. |
a9913044 RD |
3569 | routeirq Do IRQ routing for all PCI devices. |
3570 | This is normally done in pci_enable_device(), | |
3571 | so this option is a temporary workaround | |
3572 | for broken drivers that don't call it. | |
13a6ddb0 YL |
3573 | skip_isa_align [X86] do not align io start addr, so can |
3574 | handle more pci cards | |
0637a70a AK |
3575 | noearly [X86] Don't do any early type 1 scanning. |
3576 | This might help on some broken boards which | |
3577 | machine check when some devices' config space | |
3578 | is read. But various workarounds are disabled | |
3579 | and some IOMMU drivers will not work. | |
6b4b78fe MD |
3580 | bfsort Sort PCI devices into breadth-first order. |
3581 | This sorting is done to get a device | |
3582 | order compatible with older (<= 2.4) kernels. | |
3583 | nobfsort Don't sort PCI devices into breadth-first order. | |
fa238712 YW |
3584 | pcie_bus_tune_off Disable PCIe MPS (Max Payload Size) |
3585 | tuning and use the BIOS-configured MPS defaults. | |
3586 | pcie_bus_safe Set every device's MPS to the largest value | |
3587 | supported by all devices below the root complex. | |
3588 | pcie_bus_perf Set device MPS to the largest allowable MPS | |
3589 | based on its parent bus. Also set MRRS (Max | |
3590 | Read Request Size) to the largest supported | |
3591 | value (no larger than the MPS that the device | |
3592 | or bus can support) for best performance. | |
3593 | pcie_bus_peer2peer Set every device's MPS to 128B, which | |
3594 | every device is guaranteed to support. This | |
3595 | configuration allows peer-to-peer DMA between | |
3596 | any pair of devices, possibly at the cost of | |
3597 | reduced performance. This also guarantees | |
3598 | that hot-added devices will work. | |
4516a618 AN |
3599 | cbiosize=nn[KMG] The fixed amount of bus space which is |
3600 | reserved for the CardBus bridge's IO window. | |
3601 | The default value is 256 bytes. | |
3602 | cbmemsize=nn[KMG] The fixed amount of bus space which is | |
3603 | reserved for the CardBus bridge's memory | |
3604 | window. The default value is 64 megabytes. | |
32a9a682 YS |
3605 | resource_alignment= |
3606 | Format: | |
07d8d7e5 | 3607 | [<order of align>@]<pci_dev>[; ...] |
32a9a682 | 3608 | Specifies alignment and device to reassign |
07d8d7e5 LG |
3609 | aligned memory resources. How to |
3610 | specify the device is described above. | |
32a9a682 YS |
3611 | If <order of align> is not specified, |
3612 | PAGE_SIZE is used as alignment. | |
3b1b1ce3 | 3613 | A PCI-PCI bridge can be specified if resource |
32a9a682 | 3614 | windows need to be expanded. |
8b078c60 MK |
3615 | To specify the alignment for several |
3616 | instances of a device, the PCI vendor, | |
3617 | device, subvendor, and subdevice may be | |
3b1b1ce3 AK |
3618 | specified, e.g., 12@pci:8086:9c22:103c:198f |
3619 | for 4096-byte alignment. | |
43c16408 AP |
3620 | ecrc= Enable/disable PCIe ECRC (transaction layer |
3621 | end-to-end CRC checking). | |
3622 | bios: Use BIOS/firmware settings. This is the | |
3623 | the default. | |
3624 | off: Turn ECRC off | |
3625 | on: Turn ECRC on. | |
8c8803c5 YW |
3626 | hpiosize=nn[KMG] The fixed amount of bus space which is |
3627 | reserved for hotplug bridge's IO window. | |
3628 | Default size is 256 bytes. | |
d7b8a217 NJ |
3629 | hpmmiosize=nn[KMG] The fixed amount of bus space which is |
3630 | reserved for hotplug bridge's MMIO window. | |
3631 | Default size is 2 megabytes. | |
3632 | hpmmioprefsize=nn[KMG] The fixed amount of bus space which is | |
3633 | reserved for hotplug bridge's MMIO_PREF window. | |
3634 | Default size is 2 megabytes. | |
8c8803c5 | 3635 | hpmemsize=nn[KMG] The fixed amount of bus space which is |
d7b8a217 NJ |
3636 | reserved for hotplug bridge's MMIO and |
3637 | MMIO_PREF window. | |
8c8803c5 | 3638 | Default size is 2 megabytes. |
e16b4660 KB |
3639 | hpbussize=nn The minimum amount of additional bus numbers |
3640 | reserved for buses below a hotplug bridge. | |
3641 | Default is 1. | |
b55438fd YL |
3642 | realloc= Enable/disable reallocating PCI bridge resources |
3643 | if allocations done by BIOS are too small to | |
3644 | accommodate resources required by all child | |
3645 | devices. | |
3646 | off: Turn realloc off | |
3647 | on: Turn realloc on | |
3648 | realloc same as realloc=on | |
6748dcc2 | 3649 | noari do not use PCIe ARI. |
cef74409 GK |
3650 | noats [PCIE, Intel-IOMMU, AMD-IOMMU] |
3651 | do not use PCIe ATS (and IOMMU device IOTLB). | |
284f5f9d BH |
3652 | pcie_scan_all Scan all possible PCIe devices. Otherwise we |
3653 | only look for one device below a PCIe downstream | |
3654 | port. | |
f32ab754 UCCB |
3655 | big_root_window Try to add a big 64bit memory window to the PCIe |
3656 | root complex on AMD CPUs. Some GFX hardware | |
3657 | can resize a BAR to allow access to all VRAM. | |
3658 | Adding the window is slightly risky (it may | |
3659 | conflict with unreported devices), so this | |
3660 | taints the kernel. | |
aaca43fd LG |
3661 | disable_acs_redir=<pci_dev>[; ...] |
3662 | Specify one or more PCI devices (in the format | |
3663 | specified above) separated by semicolons. | |
3664 | Each device specified will have the PCI ACS | |
3665 | redirect capabilities forced off which will | |
3666 | allow P2P traffic between devices through | |
3667 | bridges without forcing it upstream. Note: | |
3668 | this removes isolation between devices and | |
3669 | may put more devices in an IOMMU group. | |
fbfe07d4 | 3670 | force_floating [S390] Force usage of floating interrupts. |
56271303 | 3671 | nomio [S390] Do not use MIO instructions. |
6b4b78fe | 3672 | |
e5665a45 CE |
3673 | pcie_aspm= [PCIE] Forcibly enable or disable PCIe Active State Power |
3674 | Management. | |
3675 | off Disable ASPM. | |
3676 | force Enable ASPM even on devices that claim not to support it. | |
3677 | WARNING: Forcing ASPM on may cause system lockups. | |
3678 | ||
4c0fd764 BH |
3679 | pcie_ports= [PCIE] PCIe port services handling: |
3680 | native Use native PCIe services (PME, AER, DPC, PCIe hotplug) | |
3681 | even if the platform doesn't give the OS permission to | |
3682 | use them. This may cause conflicts if the platform | |
3683 | also tries to use these services. | |
35a0b237 OJ |
3684 | dpc-native Use native PCIe service for DPC only. May |
3685 | cause conflicts if firmware uses AER or DPC. | |
4c0fd764 BH |
3686 | compat Disable native PCIe services (PME, AER, DPC, PCIe |
3687 | hotplug). | |
79dd9182 | 3688 | |
9d26d3a8 MW |
3689 | pcie_port_pm= [PCIE] PCIe port power management handling: |
3690 | off Disable power management of all PCIe ports | |
3691 | force Forcibly enable power management of all PCIe ports | |
3692 | ||
c7f48656 | 3693 | pcie_pme= [PCIE,PM] Native PCIe PME signaling options: |
c39fae14 | 3694 | nomsi Do not use MSI for native PCIe PME signaling (this makes |
28eb5f27 | 3695 | all PCIe root ports use INTx for all services). |
c7f48656 | 3696 | |
1da177e4 LT |
3697 | pcmv= [HW,PCMCIA] BadgePAD 4 |
3698 | ||
39ac5ba5 TB |
3699 | pd_ignore_unused |
3700 | [PM] | |
3701 | Keep all power-domains already enabled by bootloader on, | |
3702 | even if no driver has claimed them. This is useful | |
3703 | for debug and development, but should not be | |
3704 | needed on a platform with proper driver support. | |
3705 | ||
1da177e4 | 3706 | pd. [PARIDE] |
e7751617 | 3707 | See Documentation/admin-guide/blockdev/paride.rst. |
1da177e4 LT |
3708 | |
3709 | pdcchassis= [PARISC,HW] Disable/Enable PDC Chassis Status codes at | |
3710 | boot time. | |
3711 | Format: { 0 | 1 } | |
3712 | See arch/parisc/kernel/pdc_chassis.c | |
3713 | ||
f58dc01b | 3714 | percpu_alloc= Select which percpu first chunk allocator to use. |
e933a73f TH |
3715 | Currently supported values are "embed" and "page". |
3716 | Archs may support subset or none of the selections. | |
3717 | See comments in mm/percpu.c for details on each | |
3718 | allocator. This parameter is primarily for debugging | |
3719 | and performance comparison. | |
fa8a7094 | 3720 | |
1da177e4 | 3721 | pf. [PARIDE] |
e7751617 | 3722 | See Documentation/admin-guide/blockdev/paride.rst. |
1da177e4 LT |
3723 | |
3724 | pg. [PARIDE] | |
e7751617 | 3725 | See Documentation/admin-guide/blockdev/paride.rst. |
1da177e4 LT |
3726 | |
3727 | pirq= [SMP,APIC] Manual mp-table setup | |
cb1aaebe | 3728 | See Documentation/x86/i386/IO-APIC.rst. |
1da177e4 LT |
3729 | |
3730 | plip= [PPT,NET] Parallel port network link | |
3731 | Format: { parport<nr> | timid | 0 } | |
3ba9b1b8 | 3732 | See also Documentation/admin-guide/parport.rst. |
1da177e4 | 3733 | |
16290246 | 3734 | pmtmr= [X86] Manual setup of pmtmr I/O Port. |
de32a243 TG |
3735 | Override pmtimer IOPort with a hex value. |
3736 | e.g. pmtmr=0x508 | |
3737 | ||
db96a759 CY |
3738 | pm_debug_messages [SUSPEND,KNL] |
3739 | Enable suspend/resume debug messages during boot up. | |
3740 | ||
96242116 BH |
3741 | pnp.debug=1 [PNP] |
3742 | Enable PNP debug messages (depends on the | |
3743 | CONFIG_PNP_DEBUG_MESSAGES option). Change at run-time | |
3744 | via /sys/module/pnp/parameters/debug. We always show | |
3745 | current resource usage; turning this on also shows | |
3746 | possible settings and some assignment information. | |
97ef062b | 3747 | |
1da177e4 LT |
3748 | pnpacpi= [ACPI] |
3749 | { off } | |
3750 | ||
3751 | pnpbios= [ISAPNP] | |
3752 | { on | off | curr | res | no-curr | no-res } | |
3753 | ||
3754 | pnp_reserve_irq= | |
3755 | [ISAPNP] Exclude IRQs for the autoconfiguration | |
3756 | ||
3757 | pnp_reserve_dma= | |
3758 | [ISAPNP] Exclude DMAs for the autoconfiguration | |
3759 | ||
3760 | pnp_reserve_io= [ISAPNP] Exclude I/O ports for the autoconfiguration | |
a9913044 | 3761 | Ranges are in pairs (I/O port base and size). |
1da177e4 LT |
3762 | |
3763 | pnp_reserve_mem= | |
a9913044 RD |
3764 | [ISAPNP] Exclude memory regions for the |
3765 | autoconfiguration. | |
1da177e4 LT |
3766 | Ranges are in pairs (memory base and size). |
3767 | ||
4af94f39 RD |
3768 | ports= [IP_VS_FTP] IPVS ftp helper module |
3769 | Default is 21. | |
3770 | Up to 8 (IP_VS_APP_MAX_PORTS) ports | |
3771 | may be specified. | |
3772 | Format: <port>,<port>.... | |
3773 | ||
c3cbd075 BS |
3774 | powersave=off [PPC] This option disables power saving features. |
3775 | It specifically disables cpuidle and sets the | |
3776 | platform machine description specific power_save | |
3777 | function to NULL. On Idle the CPU just reduces | |
3778 | execution priority. | |
3779 | ||
3eb5d588 AB |
3780 | ppc_strict_facility_enable |
3781 | [PPC] This option catches any kernel floating point, | |
3782 | Altivec, VSX and SPE outside of regions specifically | |
3783 | allowed (eg kernel_enable_fpu()/kernel_disable_fpu()). | |
3784 | There is some performance impact when enabling this. | |
3785 | ||
07fd1761 CB |
3786 | ppc_tm= [PPC] |
3787 | Format: {"off"} | |
3788 | Disable Hardware Transactional Memory | |
3789 | ||
45807a1d IM |
3790 | print-fatal-signals= |
3791 | [KNL] debug: print fatal signals | |
f84d49b2 NO |
3792 | |
3793 | If enabled, warn about various signal handling | |
3794 | related application anomalies: too many signals, | |
3795 | too many POSIX.1 timers, fatal signals causing a | |
3796 | coredump - etc. | |
3797 | ||
3798 | If you hit the warning due to signal overflow, | |
3799 | you might want to try "ulimit -i unlimited". | |
3800 | ||
45807a1d IM |
3801 | default: off. |
3802 | ||
c22ab332 MG |
3803 | printk.always_kmsg_dump= |
3804 | Trigger kmsg_dump for cases other than kernel oops or | |
3805 | panics | |
3806 | Format: <bool> (1/Y/y=enable, 0/N/n=disable) | |
3807 | default: disabled | |
3808 | ||
750afe7b BP |
3809 | printk.devkmsg={on,off,ratelimit} |
3810 | Control writing to /dev/kmsg. | |
3811 | on - unlimited logging to /dev/kmsg from userspace | |
3812 | off - logging to /dev/kmsg disabled | |
3813 | ratelimit - ratelimit the logging | |
3814 | Default: ratelimit | |
3815 | ||
e84845c4 RD |
3816 | printk.time= Show timing data prefixed to each printk message line |
3817 | Format: <bool> (1/Y/y=enable, 0/N/n=disable) | |
3818 | ||
0cb55ad2 RD |
3819 | processor.max_cstate= [HW,ACPI] |
3820 | Limit processor to maximum C-state | |
3821 | max_cstate=9 overrides any DMI blacklist limit. | |
3822 | ||
3823 | processor.nocst [HW,ACPI] | |
3824 | Ignore the _CST method to determine C-states, | |
3825 | instead using the legacy FADT method | |
3826 | ||
1da177e4 | 3827 | profile= [KNL] Enable kernel profiling via /proc/profile |
e7e61fc0 RD |
3828 | Format: [<profiletype>,]<number> |
3829 | Param: <profiletype>: "schedule", "sleep", or "kvm" | |
3830 | [defaults to kernel profiling] | |
a9913044 | 3831 | Param: "schedule" - profile schedule points. |
b3da2a73 MG |
3832 | Param: "sleep" - profile D-state sleeping (millisecs). |
3833 | Requires CONFIG_SCHEDSTATS | |
c0fe2e69 | 3834 | Param: "kvm" - profile VM exits. |
e7e61fc0 RD |
3835 | Param: <number> - step/bucket size as a power of 2 for |
3836 | statistical time based profiling. | |
1da177e4 | 3837 | |
1da177e4 LT |
3838 | prompt_ramdisk= [RAM] List of RAM disks to prompt for floppy disk |
3839 | before loading. | |
e7751617 | 3840 | See Documentation/admin-guide/blockdev/ramdisk.rst. |
1da177e4 | 3841 | |
ecdc5d84 VG |
3842 | prot_virt= [S390] enable hosting protected virtual machines |
3843 | isolated from the hypervisor (if hardware supports | |
3844 | that). | |
3845 | Format: <bool> | |
3846 | ||
e0c27447 JW |
3847 | psi= [KNL] Enable or disable pressure stall information |
3848 | tracking. | |
3849 | Format: <bool> | |
3850 | ||
a9913044 RD |
3851 | psmouse.proto= [HW,MOUSE] Highest PS2 mouse protocol extension to |
3852 | probe for; one of (bare|imps|exps|lifebook|any). | |
1da177e4 LT |
3853 | psmouse.rate= [HW,MOUSE] Set desired mouse report rate, in reports |
3854 | per second. | |
a9913044 RD |
3855 | psmouse.resetafter= [HW,MOUSE] |
3856 | Try to reset the device after so many bad packets | |
1da177e4 LT |
3857 | (0 = never). |
3858 | psmouse.resolution= | |
3859 | [HW,MOUSE] Set desired mouse resolution, in dpi. | |
3860 | psmouse.smartscroll= | |
a9913044 | 3861 | [HW,MOUSE] Controls Logitech smartscroll autorepeat. |
1da177e4 LT |
3862 | 0 = disabled, 1 = enabled (default). |
3863 | ||
dee28e72 MG |
3864 | pstore.backend= Specify the name of the pstore backend to use |
3865 | ||
1da177e4 | 3866 | pt. [PARIDE] |
e7751617 | 3867 | See Documentation/admin-guide/blockdev/paride.rst. |
1da177e4 | 3868 | |
01c9b17b DH |
3869 | pti= [X86_64] Control Page Table Isolation of user and |
3870 | kernel address spaces. Disabling this feature | |
3871 | removes hardening, but improves performance of | |
3872 | system calls and interrupts. | |
3873 | ||
3874 | on - unconditionally enable | |
3875 | off - unconditionally disable | |
3876 | auto - kernel detects whether your CPU model is | |
3877 | vulnerable to issues that PTI mitigates | |
3878 | ||
3879 | Not specifying this option is equivalent to pti=auto. | |
3880 | ||
3881 | nopti [X86_64] | |
3882 | Equivalent to pti=off | |
41f4c20b | 3883 | |
dc8c8587 KS |
3884 | pty.legacy_count= |
3885 | [KNL] Number of legacy pty's. Overwrites compiled-in | |
3886 | default number. | |
3887 | ||
7d2c502f | 3888 | quiet [KNL] Disable most log messages |
a9913044 | 3889 | |
1da177e4 LT |
3890 | r128= [HW,DRM] |
3891 | ||
3892 | raid= [HW,RAID] | |
e52347bd | 3893 | See Documentation/admin-guide/md.rst. |
1da177e4 | 3894 | |
1da177e4 | 3895 | ramdisk_size= [RAM] Sizes of RAM disks in kilobytes |
e7751617 | 3896 | See Documentation/admin-guide/blockdev/ramdisk.rst. |
1da177e4 | 3897 | |
9b254366 KC |
3898 | random.trust_cpu={on,off} |
3899 | [KNL] Enable or disable trusting the use of the | |
3900 | CPU's random number generator (if available) to | |
3901 | fully seed the kernel's CRNG. Default is controlled | |
3902 | by CONFIG_RANDOM_TRUST_CPU. | |
3903 | ||
011d8261 BP |
3904 | ras=option[,option,...] [KNL] RAS-specific options |
3905 | ||
3906 | cec_disable [X86] | |
3907 | Disable the Correctable Errors Collector, | |
3908 | see CONFIG_RAS_CEC help text. | |
3909 | ||
4102adab | 3910 | rcu_nocbs= [KNL] |
da8739f2 PM |
3911 | The argument is a cpu list, as described above, |
3912 | except that the string "all" can be used to | |
3913 | specify every CPU on the system. | |
2d13e6ca | 3914 | |
3fbfbf7a PM |
3915 | In kernels built with CONFIG_RCU_NOCB_CPU=y, set |
3916 | the specified list of CPUs to be no-callback CPUs. | |
77095901 PM |
3917 | Invocation of these CPUs' RCU callbacks will be |
3918 | offloaded to "rcuox/N" kthreads created for that | |
3919 | purpose, where "x" is "p" for RCU-preempt, and | |
3920 | "s" for RCU-sched, and "N" is the CPU number. | |
3921 | This reduces OS jitter on the offloaded CPUs, | |
3922 | which can be useful for HPC and real-time | |
3923 | workloads. It can also improve energy efficiency | |
3924 | for asymmetric multiprocessors. | |
3fbfbf7a | 3925 | |
4102adab | 3926 | rcu_nocb_poll [KNL] |
3fbfbf7a PM |
3927 | Rather than requiring that offloaded CPUs |
3928 | (specified by rcu_nocbs= above) explicitly | |
3929 | awaken the corresponding "rcuoN" kthreads, | |
3930 | make these kthreads poll for callbacks. | |
3931 | This improves the real-time response for the | |
3932 | offloaded CPUs by relieving them of the need to | |
3933 | wake up the corresponding kthread, but degrades | |
3934 | energy efficiency by requiring that the kthreads | |
3935 | periodically wake up to do the polling. | |
3936 | ||
4102adab | 3937 | rcutree.blimit= [KNL] |
97e63f0c PM |
3938 | Set maximum number of finished RCU callbacks to |
3939 | process in one batch. | |
21a1ea9e | 3940 | |
a3dc2948 PM |
3941 | rcutree.dump_tree= [KNL] |
3942 | Dump the structure of the rcu_node combining tree | |
3943 | out at early boot. This is used for diagnostic | |
3944 | purposes, to verify correct tree setup. | |
3945 | ||
0f41c0dd PM |
3946 | rcutree.gp_cleanup_delay= [KNL] |
3947 | Set the number of jiffies to delay each step of | |
90040c9e | 3948 | RCU grace-period cleanup. |
0f41c0dd | 3949 | |
37745d28 PM |
3950 | rcutree.gp_init_delay= [KNL] |
3951 | Set the number of jiffies to delay each step of | |
90040c9e | 3952 | RCU grace-period initialization. |
0f41c0dd PM |
3953 | |
3954 | rcutree.gp_preinit_delay= [KNL] | |
3955 | Set the number of jiffies to delay each step of | |
3956 | RCU grace-period pre-initialization, that is, | |
3957 | the propagation of recent CPU-hotplug changes up | |
90040c9e | 3958 | the rcu_node combining tree. |
37745d28 | 3959 | |
48d07c04 SAS |
3960 | rcutree.use_softirq= [KNL] |
3961 | If set to zero, move all RCU_SOFTIRQ processing to | |
3962 | per-CPU rcuc kthreads. Defaults to a non-zero | |
3963 | value, meaning that RCU_SOFTIRQ is used by default. | |
3964 | Specify rcutree.use_softirq=0 to use rcuc kthreads. | |
3965 | ||
7fa27001 PM |
3966 | rcutree.rcu_fanout_exact= [KNL] |
3967 | Disable autobalancing of the rcu_node combining | |
3968 | tree. This is used by rcutorture, and might | |
3969 | possibly be useful for architectures having high | |
3970 | cache-to-cache transfer latencies. | |
37745d28 | 3971 | |
4102adab | 3972 | rcutree.rcu_fanout_leaf= [KNL] |
ee968ac6 PM |
3973 | Change the number of CPUs assigned to each |
3974 | leaf rcu_node structure. Useful for very | |
3975 | large systems, which will choose the value 64, | |
3976 | and for NUMA systems with large remote-access | |
3977 | latencies, which will choose a value aligned | |
3978 | with the appropriate hardware boundaries. | |
f885b7f2 | 3979 | |
4102adab | 3980 | rcutree.jiffies_till_first_fqs= [KNL] |
c0f4dfd4 PM |
3981 | Set delay from grace-period initialization to |
3982 | first attempt to force quiescent states. | |
3983 | Units are jiffies, minimum value is zero, | |
3984 | and maximum value is HZ. | |
3985 | ||
4102adab | 3986 | rcutree.jiffies_till_next_fqs= [KNL] |
c0f4dfd4 PM |
3987 | Set delay between subsequent attempts to force |
3988 | quiescent states. Units are jiffies, minimum | |
3989 | value is one, and maximum value is HZ. | |
3990 | ||
1a4762b9 PM |
3991 | rcutree.jiffies_till_sched_qs= [KNL] |
3992 | Set required age in jiffies for a | |
3993 | given grace period before RCU starts | |
3994 | soliciting quiescent-state help from | |
3995 | rcu_note_context_switch() and cond_resched(). | |
3996 | If not specified, the kernel will calculate | |
3997 | a value based on the most recent settings | |
3998 | of rcutree.jiffies_till_first_fqs | |
3999 | and rcutree.jiffies_till_next_fqs. | |
4000 | This calculated value may be viewed in | |
4001 | rcutree.jiffies_to_sched_qs. Any attempt to set | |
4002 | rcutree.jiffies_to_sched_qs will be cheerfully | |
4003 | overwritten. | |
4004 | ||
21871d7e | 4005 | rcutree.kthread_prio= [KNL,BOOT] |
d2af1ad7 PM |
4006 | Set the SCHED_FIFO priority of the RCU per-CPU |
4007 | kthreads (rcuc/N). This value is also used for | |
4008 | the priority of the RCU boost threads (rcub/N) | |
4009 | and for the RCU grace-period kthreads (rcu_bh, | |
4010 | rcu_preempt, and rcu_sched). If RCU_BOOST is | |
4011 | set, valid values are 1-99 and the default is 1 | |
4012 | (the least-favored priority). Otherwise, when | |
4013 | RCU_BOOST is not set, valid values are 0-99 and | |
4014 | the default is zero (non-realtime operation). | |
21871d7e | 4015 | |
f7c612b0 PM |
4016 | rcutree.rcu_nocb_gp_stride= [KNL] |
4017 | Set the number of NOCB callback kthreads in | |
4018 | each group, which defaults to the square root | |
4019 | of the number of CPUs. Larger numbers reduce | |
4020 | the wakeup overhead on the global grace-period | |
4021 | kthread, but increases that same overhead on | |
4022 | each group's NOCB grace-period kthread. | |
fbce7497 | 4023 | |
4102adab | 4024 | rcutree.qhimark= [KNL] |
97e63f0c PM |
4025 | Set threshold of queued RCU callbacks beyond which |
4026 | batch limiting is disabled. | |
21a1ea9e | 4027 | |
4102adab | 4028 | rcutree.qlowmark= [KNL] |
24aaef8d RD |
4029 | Set threshold of queued RCU callbacks below which |
4030 | batch limiting is re-enabled. | |
21a1ea9e | 4031 | |
b2b00ddf PM |
4032 | rcutree.qovld= [KNL] |
4033 | Set threshold of queued RCU callbacks beyond which | |
4034 | RCU's force-quiescent-state scan will aggressively | |
4035 | enlist help from cond_resched() and sched IPIs to | |
4036 | help CPUs more quickly reach quiescent states. | |
4037 | Set to less than zero to make this be set based | |
4038 | on rcutree.qhimark at boot time and to zero to | |
4039 | disable more aggressive help enlistment. | |
4040 | ||
4102adab | 4041 | rcutree.rcu_idle_gp_delay= [KNL] |
c0f4dfd4 PM |
4042 | Set wakeup interval for idle CPUs that have |
4043 | RCU callbacks (RCU_FAST_NO_HZ=y). | |
d40011f6 | 4044 | |
4102adab | 4045 | rcutree.rcu_idle_lazy_gp_delay= [KNL] |
c0f4dfd4 PM |
4046 | Set wakeup interval for idle CPUs that have |
4047 | only "lazy" RCU callbacks (RCU_FAST_NO_HZ=y). | |
4048 | Lazy RCU callbacks are those which RCU can | |
4049 | prove do nothing more than free memory. | |
d40011f6 | 4050 | |
e3c50dfb PM |
4051 | rcutree.rcu_kick_kthreads= [KNL] |
4052 | Cause the grace-period kthread to get an extra | |
4053 | wake_up() if it sleeps three times longer than | |
4054 | it should at force-quiescent-state time. | |
4055 | This wake_up() will be accompanied by a | |
4056 | WARN_ONCE() splat and an ftrace_dump(). | |
4057 | ||
2ccaff10 PM |
4058 | rcutree.sysrq_rcu= [KNL] |
4059 | Commandeer a sysrq key to dump out Tree RCU's | |
4060 | rcu_node tree with an eye towards determining | |
4061 | why a new grace period has not yet started. | |
4062 | ||
881ed593 PM |
4063 | rcuperf.gp_async= [KNL] |
4064 | Measure performance of asynchronous | |
4065 | grace-period primitives such as call_rcu(). | |
4066 | ||
4067 | rcuperf.gp_async_max= [KNL] | |
4068 | Specify the maximum number of outstanding | |
4069 | callbacks per writer thread. When a writer | |
4070 | thread exceeds this limit, it invokes the | |
4071 | corresponding flavor of rcu_barrier() to allow | |
4072 | previously posted callbacks to drain. | |
4073 | ||
bdea9e34 PM |
4074 | rcuperf.gp_exp= [KNL] |
4075 | Measure performance of expedited synchronous | |
4076 | grace-period primitives. | |
4077 | ||
df37e66b PM |
4078 | rcuperf.holdoff= [KNL] |
4079 | Set test-start holdoff period. The purpose of | |
4080 | this parameter is to delay the start of the | |
4081 | test until boot completes in order to avoid | |
4082 | interference. | |
4083 | ||
e6e78b00 JFG |
4084 | rcuperf.kfree_rcu_test= [KNL] |
4085 | Set to measure performance of kfree_rcu() flooding. | |
4086 | ||
4087 | rcuperf.kfree_nthreads= [KNL] | |
4088 | The number of threads running loops of kfree_rcu(). | |
4089 | ||
4090 | rcuperf.kfree_alloc_num= [KNL] | |
4091 | Number of allocations and frees done in an iteration. | |
4092 | ||
4093 | rcuperf.kfree_loops= [KNL] | |
4094 | Number of loops doing rcuperf.kfree_alloc_num number | |
4095 | of allocations and frees. | |
4096 | ||
bdea9e34 PM |
4097 | rcuperf.nreaders= [KNL] |
4098 | Set number of RCU readers. The value -1 selects | |
4099 | N, where N is the number of CPUs. A value | |
4100 | "n" less than -1 selects N-n+1, where N is again | |
4101 | the number of CPUs. For example, -2 selects N | |
4102 | (the number of CPUs), -3 selects N+1, and so on. | |
4103 | A value of "n" less than or equal to -N selects | |
4104 | a single reader. | |
4105 | ||
4106 | rcuperf.nwriters= [KNL] | |
4107 | Set number of RCU writers. The values operate | |
4108 | the same as for rcuperf.nreaders. | |
4109 | N, where N is the number of CPUs | |
4110 | ||
820687a7 PM |
4111 | rcuperf.perf_type= [KNL] |
4112 | Specify the RCU implementation to test. | |
4113 | ||
bdea9e34 PM |
4114 | rcuperf.shutdown= [KNL] |
4115 | Shut the system down after performance tests | |
4116 | complete. This is useful for hands-off automated | |
4117 | testing. | |
4118 | ||
bdea9e34 PM |
4119 | rcuperf.verbose= [KNL] |
4120 | Enable additional printk() statements. | |
4121 | ||
820687a7 PM |
4122 | rcuperf.writer_holdoff= [KNL] |
4123 | Write-side holdoff between grace periods, | |
4124 | in microseconds. The default of zero says | |
4125 | no holdoff. | |
4126 | ||
4102adab | 4127 | rcutorture.fqs_duration= [KNL] |
21b05de4 PM |
4128 | Set duration of force_quiescent_state bursts |
4129 | in microseconds. | |
dabb8aa9 | 4130 | |
4102adab | 4131 | rcutorture.fqs_holdoff= [KNL] |
21b05de4 PM |
4132 | Set holdoff time within force_quiescent_state bursts |
4133 | in microseconds. | |
dabb8aa9 | 4134 | |
4102adab | 4135 | rcutorture.fqs_stutter= [KNL] |
21b05de4 PM |
4136 | Set wait time between force_quiescent_state bursts |
4137 | in seconds. | |
4138 | ||
ed8f6fb2 PM |
4139 | rcutorture.fwd_progress= [KNL] |
4140 | Enable RCU grace-period forward-progress testing | |
4141 | for the types of RCU supporting this notion. | |
4142 | ||
4143 | rcutorture.fwd_progress_div= [KNL] | |
4144 | Specify the fraction of a CPU-stall-warning | |
4145 | period to do tight-loop forward-progress testing. | |
4146 | ||
4147 | rcutorture.fwd_progress_holdoff= [KNL] | |
4148 | Number of seconds to wait between successive | |
4149 | forward-progress tests. | |
4150 | ||
4151 | rcutorture.fwd_progress_need_resched= [KNL] | |
4152 | Enclose cond_resched() calls within checks for | |
4153 | need_resched() during tight-loop forward-progress | |
4154 | testing. | |
4155 | ||
21b05de4 PM |
4156 | rcutorture.gp_cond= [KNL] |
4157 | Use conditional/asynchronous update-side | |
4158 | primitives, if available. | |
dabb8aa9 | 4159 | |
4102adab | 4160 | rcutorture.gp_exp= [KNL] |
21b05de4 | 4161 | Use expedited update-side primitives, if available. |
4102adab PM |
4162 | |
4163 | rcutorture.gp_normal= [KNL] | |
21b05de4 PM |
4164 | Use normal (non-expedited) asynchronous |
4165 | update-side primitives, if available. | |
4166 | ||
4167 | rcutorture.gp_sync= [KNL] | |
4168 | Use normal (non-expedited) synchronous | |
4169 | update-side primitives, if available. If all | |
4170 | of rcutorture.gp_cond=, rcutorture.gp_exp=, | |
4171 | rcutorture.gp_normal=, and rcutorture.gp_sync= | |
4172 | are zero, rcutorture acts as if is interpreted | |
4173 | they are all non-zero. | |
dabb8aa9 | 4174 | |
4102adab | 4175 | rcutorture.n_barrier_cbs= [KNL] |
dabb8aa9 PM |
4176 | Set callbacks/threads for rcu_barrier() testing. |
4177 | ||
4102adab | 4178 | rcutorture.nfakewriters= [KNL] |
dabb8aa9 PM |
4179 | Set number of concurrent RCU writers. These just |
4180 | stress RCU, they don't participate in the actual | |
4181 | test, hence the "fake". | |
4182 | ||
4102adab | 4183 | rcutorture.nreaders= [KNL] |
3838cc18 PM |
4184 | Set number of RCU readers. The value -1 selects |
4185 | N-1, where N is the number of CPUs. A value | |
4186 | "n" less than -1 selects N-n-2, where N is again | |
4187 | the number of CPUs. For example, -2 selects N | |
4188 | (the number of CPUs), -3 selects N+1, and so on. | |
dabb8aa9 | 4189 | |
4102adab PM |
4190 | rcutorture.object_debug= [KNL] |
4191 | Enable debug-object double-call_rcu() testing. | |
4192 | ||
4193 | rcutorture.onoff_holdoff= [KNL] | |
dabb8aa9 PM |
4194 | Set time (s) after boot for CPU-hotplug testing. |
4195 | ||
4102adab | 4196 | rcutorture.onoff_interval= [KNL] |
028be12b PM |
4197 | Set time (jiffies) between CPU-hotplug operations, |
4198 | or zero to disable CPU-hotplug testing. | |
dabb8aa9 | 4199 | |
4102adab | 4200 | rcutorture.shuffle_interval= [KNL] |
dabb8aa9 PM |
4201 | Set task-shuffle interval (s). Shuffling tasks |
4202 | allows some CPUs to go into dyntick-idle mode | |
4203 | during the rcutorture test. | |
4204 | ||
4102adab | 4205 | rcutorture.shutdown_secs= [KNL] |
dabb8aa9 PM |
4206 | Set time (s) after boot system shutdown. This |
4207 | is useful for hands-off automated testing. | |
4208 | ||
4102adab | 4209 | rcutorture.stall_cpu= [KNL] |
dabb8aa9 PM |
4210 | Duration of CPU stall (s) to test RCU CPU stall |
4211 | warnings, zero to disable. | |
4212 | ||
4102adab | 4213 | rcutorture.stall_cpu_holdoff= [KNL] |
dabb8aa9 PM |
4214 | Time to wait (s) after boot before inducing stall. |
4215 | ||
2b1516e5 PM |
4216 | rcutorture.stall_cpu_irqsoff= [KNL] |
4217 | Disable interrupts while stalling if set. | |
4218 | ||
4102adab | 4219 | rcutorture.stat_interval= [KNL] |
dabb8aa9 PM |
4220 | Time (s) between statistics printk()s. |
4221 | ||
4102adab | 4222 | rcutorture.stutter= [KNL] |
dabb8aa9 PM |
4223 | Time (s) to stutter testing, for example, specifying |
4224 | five seconds causes the test to run for five seconds, | |
4225 | wait for five seconds, and so on. This tests RCU's | |
4226 | ability to transition abruptly to and from idle. | |
4227 | ||
4102adab | 4228 | rcutorture.test_boost= [KNL] |
dabb8aa9 PM |
4229 | Test RCU priority boosting? 0=no, 1=maybe, 2=yes. |
4230 | "Maybe" means test if the RCU implementation | |
4231 | under test support RCU priority boosting. | |
4232 | ||
4102adab | 4233 | rcutorture.test_boost_duration= [KNL] |
dabb8aa9 PM |
4234 | Duration (s) of each individual boost test. |
4235 | ||
4102adab | 4236 | rcutorture.test_boost_interval= [KNL] |
dabb8aa9 PM |
4237 | Interval (s) between each boost test. |
4238 | ||
4102adab | 4239 | rcutorture.test_no_idle_hz= [KNL] |
dabb8aa9 PM |
4240 | Test RCU's dyntick-idle handling. See also the |
4241 | rcutorture.shuffle_interval parameter. | |
4242 | ||
4102adab | 4243 | rcutorture.torture_type= [KNL] |
dabb8aa9 PM |
4244 | Specify the RCU implementation to test. |
4245 | ||
4102adab | 4246 | rcutorture.verbose= [KNL] |
dabb8aa9 PM |
4247 | Enable additional printk() statements. |
4248 | ||
cdc694b2 PM |
4249 | rcupdate.rcu_cpu_stall_ftrace_dump= [KNL] |
4250 | Dump ftrace buffer after reporting RCU CPU | |
4251 | stall warning. | |
4252 | ||
5a9be7c6 PM |
4253 | rcupdate.rcu_cpu_stall_suppress= [KNL] |
4254 | Suppress RCU CPU stall warning messages. | |
4255 | ||
58c53360 PM |
4256 | rcupdate.rcu_cpu_stall_suppress_at_boot= [KNL] |
4257 | Suppress RCU CPU stall warning messages and | |
4258 | rcutorture writer stall warnings that occur | |
4259 | during early boot, that is, during the time | |
4260 | before the init task is spawned. | |
4261 | ||
5a9be7c6 PM |
4262 | rcupdate.rcu_cpu_stall_timeout= [KNL] |
4263 | Set timeout for RCU CPU stall warning messages. | |
4264 | ||
4102adab PM |
4265 | rcupdate.rcu_expedited= [KNL] |
4266 | Use expedited grace-period primitives, for | |
4267 | example, synchronize_rcu_expedited() instead | |
4268 | of synchronize_rcu(). This reduces latency, | |
4269 | but can increase CPU utilization, degrade | |
4270 | real-time latency, and degrade energy efficiency. | |
79cfea02 | 4271 | No effect on CONFIG_TINY_RCU kernels. |
4102adab | 4272 | |
5a9be7c6 PM |
4273 | rcupdate.rcu_normal= [KNL] |
4274 | Use only normal grace-period primitives, | |
4275 | for example, synchronize_rcu() instead of | |
4276 | synchronize_rcu_expedited(). This improves | |
79cfea02 PM |
4277 | real-time latency, CPU utilization, and |
4278 | energy efficiency, but can expose users to | |
4279 | increased grace-period latency. This parameter | |
4280 | overrides rcupdate.rcu_expedited. No effect on | |
4281 | CONFIG_TINY_RCU kernels. | |
4102adab | 4282 | |
3e42ec1a PM |
4283 | rcupdate.rcu_normal_after_boot= [KNL] |
4284 | Once boot has completed (that is, after | |
4285 | rcu_end_inkernel_boot() has been invoked), use | |
79cfea02 PM |
4286 | only normal grace-period primitives. No effect |
4287 | on CONFIG_TINY_RCU kernels. | |
3e42ec1a | 4288 | |
52db30ab PM |
4289 | rcupdate.rcu_task_stall_timeout= [KNL] |
4290 | Set timeout in jiffies for RCU task stall warning | |
4291 | messages. Disable with a value less than or equal | |
4292 | to zero. | |
4293 | ||
74860fee PK |
4294 | rcupdate.rcu_self_test= [KNL] |
4295 | Run the RCU early boot self tests | |
4296 | ||
ffdfc409 OJ |
4297 | rdinit= [KNL] |
4298 | Format: <full_path> | |
4299 | Run specified binary instead of /init from the ramdisk, | |
4300 | used for early userspace startup. See initrd. | |
4301 | ||
c49a0a80 TL |
4302 | rdrand= [X86] |
4303 | force - Override the decision by the kernel to hide the | |
4304 | advertisement of RDRAND support (this affects | |
4305 | certain AMD processors because of buggy BIOS | |
4306 | support, specifically around the suspend/resume | |
4307 | path). | |
4308 | ||
1d9807fc TL |
4309 | rdt= [HW,X86,RDT] |
4310 | Turn on/off individual RDT features. List is: | |
31516de3 FY |
4311 | cmt, mbmtotal, mbmlocal, l3cat, l3cdp, l2cat, l2cdp, |
4312 | mba. | |
1d9807fc TL |
4313 | E.g. to turn on cmt and turn off mba use: |
4314 | rdt=cmt,!mba | |
4315 | ||
1b3a5d02 RH |
4316 | reboot= [KNL] |
4317 | Format (x86 or x86_64): | |
4318 | [w[arm] | c[old] | h[ard] | s[oft] | g[pio]] \ | |
4319 | [[,]s[mp]#### \ | |
4320 | [[,]b[ios] | a[cpi] | k[bd] | t[riple] | e[fi] | p[ci]] \ | |
4321 | [[,]f[orce] | |
b287a25a AK |
4322 | Where reboot_mode is one of warm (soft) or cold (hard) or gpio |
4323 | (prefix with 'panic_' to set mode for panic | |
4324 | reboot only), | |
1b3a5d02 RH |
4325 | reboot_type is one of bios, acpi, kbd, triple, efi, or pci, |
4326 | reboot_force is either force or not specified, | |
4327 | reboot_cpu is s[mp]#### with #### being the processor | |
4328 | to be used for rebooting. | |
1da177e4 | 4329 | |
46b6d94e PJ |
4330 | relax_domain_level= |
4331 | [KNL, SMP] Set scheduler's default relax_domain_level. | |
da82c92f | 4332 | See Documentation/admin-guide/cgroup-v1/cpusets.rst. |
46b6d94e | 4333 | |
ffd2e8df BH |
4334 | reserve= [KNL,BUGS] Force kernel to ignore I/O ports or memory |
4335 | Format: <base1>,<size1>[,<base2>,<size2>,...] | |
4336 | Reserve I/O ports or memory so the kernel won't use | |
4337 | them. If <base> is less than 0x10000, the region | |
4338 | is assumed to be I/O ports; otherwise it is memory. | |
1da177e4 | 4339 | |
cd4f0ef7 | 4340 | reservetop= [X86-32] |
461a9aff ZA |
4341 | Format: nn[KMG] |
4342 | Reserves a hole at the top of the kernel virtual | |
4343 | address space. | |
4344 | ||
9ea77bdb PA |
4345 | reservelow= [X86] |
4346 | Format: nn[K] | |
4347 | Set the amount of memory to reserve for BIOS at | |
4348 | the bottom of the address space. | |
4349 | ||
7e96287d VG |
4350 | reset_devices [KNL] Force drivers to reset the underlying device |
4351 | during initialization. | |
4352 | ||
a9913044 RD |
4353 | resume= [SWSUSP] |
4354 | Specify the partition device for software suspend | |
2df83fa4 MB |
4355 | Format: |
4356 | {/dev/<dev> | PARTUUID=<uuid> | <int>:<int> | <hex>} | |
1da177e4 | 4357 | |
ecbd0da1 RW |
4358 | resume_offset= [SWSUSP] |
4359 | Specify the offset from the beginning of the partition | |
4360 | given by "resume=" at which the swap header is located, | |
4361 | in <PAGE_SIZE> units (needed only for swap files). | |
151f4e2b | 4362 | See Documentation/power/swsusp-and-swap-files.rst |
ecbd0da1 | 4363 | |
f126f733 BS |
4364 | resumedelay= [HIBERNATION] Delay (in seconds) to pause before attempting to |
4365 | read the resume files | |
4366 | ||
6f8d7022 BS |
4367 | resumewait [HIBERNATION] Wait (indefinitely) for resume device to show up. |
4368 | Useful for devices that are detected asynchronously | |
4369 | (e.g. USB and MMC devices). | |
4370 | ||
f996fc96 BS |
4371 | hibernate= [HIBERNATION] |
4372 | noresume Don't check if there's a hibernation image | |
4373 | present during boot. | |
4374 | nocompress Don't compress/decompress hibernation images. | |
a6e15a39 | 4375 | no Disable hibernation and resume. |
4c0b6c10 RW |
4376 | protect_image Turn on image protection during restoration |
4377 | (that will set all pages holding image data | |
4378 | during restoration read-only). | |
f996fc96 | 4379 | |
0a7b35cb MN |
4380 | retain_initrd [RAM] Keep initrd memory after extraction |
4381 | ||
0efbb786 AC |
4382 | rfkill.default_state= |
4383 | 0 "airplane mode". All wifi, bluetooth, wimax, gps, fm, | |
4384 | etc. communication is blocked by default. | |
4385 | 1 Unblocked. | |
4386 | ||
4387 | rfkill.master_switch_mode= | |
4388 | 0 The "airplane mode" button does nothing. | |
4389 | 1 The "airplane mode" button toggles between everything | |
4390 | blocked and the previous configuration. | |
4391 | 2 The "airplane mode" button toggles between everything | |
4392 | blocked and everything unblocked. | |
4393 | ||
1da177e4 LT |
4394 | rhash_entries= [KNL,NET] |
4395 | Set number of hash buckets for route cache | |
4396 | ||
e16fd002 GA |
4397 | ring3mwait=disable |
4398 | [KNL] Disable ring 3 MONITOR/MWAIT feature on supported | |
4399 | CPUs. | |
4400 | ||
1da177e4 LT |
4401 | ro [KNL] Mount root device read-only on boot |
4402 | ||
d2aa1aca KC |
4403 | rodata= [KNL] |
4404 | on Mark read-only kernel memory as read-only (default). | |
4405 | off Leave read-only kernel memory writable for debugging. | |
4406 | ||
605df8af HS |
4407 | rockchip.usb_uart |
4408 | Enable the uart passthrough on the designated usb port | |
4409 | on Rockchip SoCs. When active, the signals of the | |
4410 | debug-uart get routed to the D+ and D- pins of the usb | |
4411 | port and the regular usb controller gets disabled. | |
4412 | ||
1da177e4 | 4413 | root= [KNL] Root filesystem |
f2d34fd9 | 4414 | See name_to_dev_t comment in init/do_mounts.c. |
1da177e4 LT |
4415 | |
4416 | rootdelay= [KNL] Delay (in seconds) to pause before attempting to | |
4417 | mount the root filesystem | |
4418 | ||
4419 | rootflags= [KNL] Set root filesystem mount option string | |
4420 | ||
4421 | rootfstype= [KNL] Set root filesystem type | |
4422 | ||
cc1ed754 PO |
4423 | rootwait [KNL] Wait (indefinitely) for root device to show up. |
4424 | Useful for devices that are detected asynchronously | |
4425 | (e.g. USB and MMC devices). | |
4426 | ||
5c71d618 RT |
4427 | rproc_mem=nn[KMG][@address] |
4428 | [KNL,ARM,CMA] Remoteproc physical memory block. | |
4429 | Memory area to be used by remote processor image, | |
4430 | managed by CMA. | |
4431 | ||
1da177e4 LT |
4432 | rw [KNL] Mount root device read-write on boot |
4433 | ||
4434 | S [KNL] Run init in single mode | |
4435 | ||
c60d1ae4 GS |
4436 | s390_iommu= [HW,S390] |
4437 | Set s390 IOTLB flushing mode | |
4438 | strict | |
4439 | With strict flushing every unmap operation will result in | |
4440 | an IOTLB flush. Default is lazy flushing before reuse, | |
4441 | which is faster. | |
4442 | ||
1da177e4 LT |
4443 | sa1100ir [NET] |
4444 | See drivers/net/irda/sa1100_ir.c. | |
4445 | ||
1da177e4 | 4446 | sbni= [NET] Granch SBNI12 leased line adapter |
a9913044 | 4447 | |
f6630114 MT |
4448 | sched_debug [KNL] Enables verbose scheduler debug messages. |
4449 | ||
cb251765 MG |
4450 | schedstats= [KNL,X86] Enable or disable scheduled statistics. |
4451 | Allowed values are enable and disable. This feature | |
4452 | incurs a small amount of overhead in the scheduler | |
4453 | but is useful for debugging and performance tuning. | |
f6630114 | 4454 | |
05289b90 TG |
4455 | sched_thermal_decay_shift= |
4456 | [KNL, SMP] Set a decay shift for scheduler thermal | |
4457 | pressure signal. Thermal pressure signal follows the | |
4458 | default decay period of other scheduler pelt | |
4459 | signals(usually 32 ms but configurable). Setting | |
4460 | sched_thermal_decay_shift will left shift the decay | |
4461 | period for the thermal pressure signal by the shift | |
4462 | value. | |
4463 | i.e. with the default pelt decay period of 32 ms | |
4464 | sched_thermal_decay_shift thermal pressure decay pr | |
4465 | 1 64 ms | |
4466 | 2 128 ms | |
4467 | and so on. | |
4468 | Format: integer between 0 and 10 | |
4469 | Default is 0. | |
4470 | ||
5307c955 MG |
4471 | skew_tick= [KNL] Offset the periodic timer tick per cpu to mitigate |
4472 | xtime_lock contention on larger systems, and/or RCU lock | |
4473 | contention on all systems with CONFIG_MAXSMP set. | |
4474 | Format: { "0" | "1" } | |
4475 | 0 -- disable. (may be 1 via CONFIG_CMDLINE="skew_tick=1" | |
4476 | 1 -- enable. | |
4477 | Note: increases power consumption, thus should only be | |
4478 | enabled if running jitter sensitive (HPC/RT) workloads. | |
4479 | ||
89a9684e KC |
4480 | security= [SECURITY] Choose a legacy "major" security module to |
4481 | enable at boot. This has been deprecated by the | |
4482 | "lsm=" parameter. | |
0cb55ad2 RD |
4483 | |
4484 | selinux= [SELINUX] Disable or enable SELinux at boot time. | |
1da177e4 LT |
4485 | Format: { "0" | "1" } |
4486 | See security/selinux/Kconfig help text. | |
4487 | 0 -- disable. | |
4488 | 1 -- enable. | |
d41415eb | 4489 | Default value is 1. |
1da177e4 | 4490 | |
c1c124e9 JJ |
4491 | apparmor= [APPARMOR] Disable or enable AppArmor at boot time |
4492 | Format: { "0" | "1" } | |
4493 | See security/apparmor/Kconfig help text | |
4494 | 0 -- disable. | |
4495 | 1 -- enable. | |
4496 | Default value is set via kernel config option. | |
4497 | ||
cd4f0ef7 | 4498 | serialnumber [BUGS=X86-32] |
1da177e4 | 4499 | |
1da177e4 LT |
4500 | shapers= [NET] |
4501 | Maximal number of shapers. | |
a9913044 | 4502 | |
1da177e4 LT |
4503 | simeth= [IA-64] |
4504 | simscsi= | |
a9913044 | 4505 | |
1da177e4 LT |
4506 | slram= [HW,MTD] |
4507 | ||
423c929c JK |
4508 | slab_nomerge [MM] |
4509 | Disable merging of slabs with similar size. May be | |
4510 | necessary if there is some reason to distinguish | |
7660a6fd KC |
4511 | allocs to different slabs, especially in hardened |
4512 | environments where the risk of heap overflows and | |
4513 | layout control by attackers can usually be | |
4514 | frustrated by disabling merging. This will reduce | |
4515 | most of the exposure of a heap attack to a single | |
4516 | cache (risks via metadata attacks are mostly | |
4517 | unchanged). Debug options disable merging on their | |
4518 | own. | |
ad56b738 | 4519 | For more information see Documentation/vm/slub.rst. |
423c929c | 4520 | |
3df1cccd DR |
4521 | slab_max_order= [MM, SLAB] |
4522 | Determines the maximum allowed order for slabs. | |
4523 | A high setting may cause OOMs due to memory | |
4524 | fragmentation. Defaults to 1 for systems with | |
4525 | more than 32MB of RAM, 0 otherwise. | |
4526 | ||
f0630fff CL |
4527 | slub_debug[=options[,slabs]] [MM, SLUB] |
4528 | Enabling slub_debug allows one to determine the | |
4529 | culprit if slab objects become corrupted. Enabling | |
4530 | slub_debug can create guard zones around objects and | |
4531 | may poison objects when not in use. Also tracks the | |
4532 | last alloc / free. For more information see | |
ad56b738 | 4533 | Documentation/vm/slub.rst. |
c1aee215 | 4534 | |
1663f26d TH |
4535 | slub_memcg_sysfs= [MM, SLUB] |
4536 | Determines whether to enable sysfs directories for | |
4537 | memory cgroup sub-caches. 1 to enable, 0 to disable. | |
4538 | The default is determined by CONFIG_SLUB_MEMCG_SYSFS_ON. | |
4539 | Enabling this can lead to a very high number of debug | |
4540 | directories and files being created under | |
4541 | /sys/kernel/slub. | |
4542 | ||
c1aee215 | 4543 | slub_max_order= [MM, SLUB] |
f0630fff CL |
4544 | Determines the maximum allowed order for slabs. |
4545 | A high setting may cause OOMs due to memory | |
4546 | fragmentation. For more information see | |
ad56b738 | 4547 | Documentation/vm/slub.rst. |
c1aee215 CL |
4548 | |
4549 | slub_min_objects= [MM, SLUB] | |
f0630fff CL |
4550 | The minimum number of objects per slab. SLUB will |
4551 | increase the slab order up to slub_max_order to | |
4552 | generate a sufficiently large slab able to contain | |
4553 | the number of objects indicated. The higher the number | |
4554 | of objects the smaller the overhead of tracking slabs | |
4555 | and the less frequently locks need to be acquired. | |
ad56b738 | 4556 | For more information see Documentation/vm/slub.rst. |
c1aee215 CL |
4557 | |
4558 | slub_min_order= [MM, SLUB] | |
24775d65 | 4559 | Determines the minimum page order for slabs. Must be |
f0630fff | 4560 | lower than slub_max_order. |
ad56b738 | 4561 | For more information see Documentation/vm/slub.rst. |
c1aee215 CL |
4562 | |
4563 | slub_nomerge [MM, SLUB] | |
423c929c JK |
4564 | Same with slab_nomerge. This is supported for legacy. |
4565 | See slab_nomerge for more information. | |
c1aee215 | 4566 | |
1da177e4 LT |
4567 | smart2= [HW] |
4568 | Format: <io1>[,<io2>[,...,<io8>]] | |
4569 | ||
d0d4f69b BH |
4570 | smsc-ircc2.nopnp [HW] Don't use PNP to discover SMC devices |
4571 | smsc-ircc2.ircc_cfg= [HW] Device configuration I/O port | |
4572 | smsc-ircc2.ircc_sir= [HW] SIR base I/O port | |
4573 | smsc-ircc2.ircc_fir= [HW] FIR base I/O port | |
4574 | smsc-ircc2.ircc_irq= [HW] IRQ line | |
4575 | smsc-ircc2.ircc_dma= [HW] DMA channel | |
4576 | smsc-ircc2.ircc_transceiver= [HW] Transceiver type: | |
4577 | 0: Toshiba Satellite 1800 (GP data pin select) | |
4578 | 1: Fast pin select (default) | |
4579 | 2: ATC IRMode | |
4580 | ||
52c48c51 SS |
4581 | smt [KNL,S390] Set the maximum number of threads (logical |
4582 | CPUs) to use per physical CPU on systems capable of | |
4583 | symmetric multithreading (SMT). Will be capped to the | |
4584 | actual hardware limit. | |
4585 | Format: <integer> | |
4586 | Default: -1 (no limit) | |
4587 | ||
9c44bc03 IM |
4588 | softlockup_panic= |
4589 | [KNL] Should the soft-lockup detector generate panics. | |
44a4dcf7 | 4590 | Format: <integer> |
9c44bc03 | 4591 | |
3ce62385 | 4592 | A nonzero value instructs the soft-lockup detector |
0a07bef6 GP |
4593 | to panic the machine when a soft-lockup occurs. It is |
4594 | also controlled by the kernel.softlockup_panic sysctl | |
4595 | and CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC, which is the | |
4596 | respective build-time switch to that functionality. | |
3ce62385 | 4597 | |
ed235875 AT |
4598 | softlockup_all_cpu_backtrace= |
4599 | [KNL] Should the soft-lockup detector generate | |
4600 | backtraces on all cpus. | |
4601 | Format: <integer> | |
4602 | ||
1da177e4 | 4603 | sonypi.*= [HW] Sony Programmable I/O Control Device driver |
9e1cbede | 4604 | See Documentation/admin-guide/laptops/sonypi.rst |
1da177e4 | 4605 | |
da285121 DW |
4606 | spectre_v2= [X86] Control mitigation of Spectre variant 2 |
4607 | (indirect branch speculation) vulnerability. | |
fa1202ef TG |
4608 | The default operation protects the kernel from |
4609 | user space attacks. | |
da285121 | 4610 | |
fa1202ef TG |
4611 | on - unconditionally enable, implies |
4612 | spectre_v2_user=on | |
4613 | off - unconditionally disable, implies | |
4614 | spectre_v2_user=off | |
da285121 DW |
4615 | auto - kernel detects whether your CPU model is |
4616 | vulnerable | |
4617 | ||
4618 | Selecting 'on' will, and 'auto' may, choose a | |
4619 | mitigation method at run time according to the | |
4620 | CPU, the available microcode, the setting of the | |
4621 | CONFIG_RETPOLINE configuration option, and the | |
4622 | compiler with which the kernel was built. | |
4623 | ||
fa1202ef TG |
4624 | Selecting 'on' will also enable the mitigation |
4625 | against user space to user space task attacks. | |
4626 | ||
4627 | Selecting 'off' will disable both the kernel and | |
4628 | the user space protections. | |
4629 | ||
da285121 DW |
4630 | Specific mitigations can also be selected manually: |
4631 | ||
4632 | retpoline - replace indirect branches | |
4633 | retpoline,generic - google's original retpoline | |
4634 | retpoline,amd - AMD-specific minimal thunk | |
4635 | ||
4636 | Not specifying this option is equivalent to | |
4637 | spectre_v2=auto. | |
4638 | ||
fa1202ef TG |
4639 | spectre_v2_user= |
4640 | [X86] Control mitigation of Spectre variant 2 | |
4641 | (indirect branch speculation) vulnerability between | |
4642 | user space tasks | |
4643 | ||
4644 | on - Unconditionally enable mitigations. Is | |
4645 | enforced by spectre_v2=on | |
4646 | ||
4647 | off - Unconditionally disable mitigations. Is | |
4648 | enforced by spectre_v2=off | |
4649 | ||
7cc765a6 TG |
4650 | prctl - Indirect branch speculation is enabled, |
4651 | but mitigation can be enabled via prctl | |
4652 | per thread. The mitigation control state | |
4653 | is inherited on fork. | |
4654 | ||
55a97402 TG |
4655 | prctl,ibpb |
4656 | - Like "prctl" above, but only STIBP is | |
4657 | controlled per thread. IBPB is issued | |
4658 | always when switching between different user | |
4659 | space processes. | |
4660 | ||
6b3e64c2 TG |
4661 | seccomp |
4662 | - Same as "prctl" above, but all seccomp | |
4663 | threads will enable the mitigation unless | |
4664 | they explicitly opt out. | |
4665 | ||
55a97402 TG |
4666 | seccomp,ibpb |
4667 | - Like "seccomp" above, but only STIBP is | |
4668 | controlled per thread. IBPB is issued | |
4669 | always when switching between different | |
4670 | user space processes. | |
4671 | ||
fa1202ef TG |
4672 | auto - Kernel selects the mitigation depending on |
4673 | the available CPU features and vulnerability. | |
6b3e64c2 TG |
4674 | |
4675 | Default mitigation: | |
4676 | If CONFIG_SECCOMP=y then "seccomp", otherwise "prctl" | |
fa1202ef TG |
4677 | |
4678 | Not specifying this option is equivalent to | |
4679 | spectre_v2_user=auto. | |
4680 | ||
24f7fc83 KRW |
4681 | spec_store_bypass_disable= |
4682 | [HW] Control Speculative Store Bypass (SSB) Disable mitigation | |
4683 | (Speculative Store Bypass vulnerability) | |
4684 | ||
4685 | Certain CPUs are vulnerable to an exploit against a | |
4686 | a common industry wide performance optimization known | |
4687 | as "Speculative Store Bypass" in which recent stores | |
4688 | to the same memory location may not be observed by | |
4689 | later loads during speculative execution. The idea | |
4690 | is that such stores are unlikely and that they can | |
4691 | be detected prior to instruction retirement at the | |
4692 | end of a particular speculation execution window. | |
4693 | ||
4694 | In vulnerable processors, the speculatively forwarded | |
4695 | store can be used in a cache side channel attack, for | |
4696 | example to read memory to which the attacker does not | |
4697 | directly have access (e.g. inside sandboxed code). | |
4698 | ||
4699 | This parameter controls whether the Speculative Store | |
4700 | Bypass optimization is used. | |
4701 | ||
6b4c1360 ME |
4702 | On x86 the options are: |
4703 | ||
f21b53b2 KC |
4704 | on - Unconditionally disable Speculative Store Bypass |
4705 | off - Unconditionally enable Speculative Store Bypass | |
4706 | auto - Kernel detects whether the CPU model contains an | |
4707 | implementation of Speculative Store Bypass and | |
4708 | picks the most appropriate mitigation. If the | |
4709 | CPU is not vulnerable, "off" is selected. If the | |
4710 | CPU is vulnerable the default mitigation is | |
4711 | architecture and Kconfig dependent. See below. | |
4712 | prctl - Control Speculative Store Bypass per thread | |
4713 | via prctl. Speculative Store Bypass is enabled | |
4714 | for a process by default. The state of the control | |
4715 | is inherited on fork. | |
4716 | seccomp - Same as "prctl" above, but all seccomp threads | |
4717 | will disable SSB unless they explicitly opt out. | |
24f7fc83 | 4718 | |
f21b53b2 KC |
4719 | Default mitigations: |
4720 | X86: If CONFIG_SECCOMP=y "seccomp", otherwise "prctl" | |
4721 | ||
6b4c1360 ME |
4722 | On powerpc the options are: |
4723 | ||
4724 | on,auto - On Power8 and Power9 insert a store-forwarding | |
4725 | barrier on kernel entry and exit. On Power7 | |
4726 | perform a software flush on kernel entry and | |
4727 | exit. | |
4728 | off - No action. | |
4729 | ||
4730 | Not specifying this option is equivalent to | |
4731 | spec_store_bypass_disable=auto. | |
4732 | ||
1da177e4 LT |
4733 | spia_io_base= [HW,MTD] |
4734 | spia_fio_base= | |
4735 | spia_pedr= | |
4736 | spia_peddr= | |
4737 | ||
6650cdd9 PZI |
4738 | split_lock_detect= |
4739 | [X86] Enable split lock detection | |
4740 | ||
4741 | When enabled (and if hardware support is present), atomic | |
4742 | instructions that access data across cache line | |
4743 | boundaries will result in an alignment check exception. | |
4744 | ||
4745 | off - not enabled | |
4746 | ||
4747 | warn - the kernel will emit rate limited warnings | |
4748 | about applications triggering the #AC | |
4749 | exception. This mode is the default on CPUs | |
4750 | that supports split lock detection. | |
4751 | ||
4752 | fatal - the kernel will send SIGBUS to applications | |
4753 | that trigger the #AC exception. | |
4754 | ||
4755 | If an #AC exception is hit in the kernel or in | |
4756 | firmware (i.e. not while executing in user mode) | |
4757 | the kernel will oops in either "warn" or "fatal" | |
4758 | mode. | |
4759 | ||
c350c008 PM |
4760 | srcutree.counter_wrap_check [KNL] |
4761 | Specifies how frequently to check for | |
4762 | grace-period sequence counter wrap for the | |
4763 | srcu_data structure's ->srcu_gp_seq_needed field. | |
4764 | The greater the number of bits set in this kernel | |
4765 | parameter, the less frequently counter wrap will | |
4766 | be checked for. Note that the bottom two bits | |
4767 | are ignored. | |
4768 | ||
22607d66 PM |
4769 | srcutree.exp_holdoff [KNL] |
4770 | Specifies how many nanoseconds must elapse | |
4771 | since the end of the last SRCU grace period for | |
4772 | a given srcu_struct until the next normal SRCU | |
4773 | grace period will be considered for automatic | |
4774 | expediting. Set to zero to disable automatic | |
4775 | expediting. | |
4776 | ||
a43ae4df MZ |
4777 | ssbd= [ARM64,HW] |
4778 | Speculative Store Bypass Disable control | |
4779 | ||
4780 | On CPUs that are vulnerable to the Speculative | |
4781 | Store Bypass vulnerability and offer a | |
4782 | firmware based mitigation, this parameter | |
4783 | indicates how the mitigation should be used: | |
4784 | ||
4785 | force-on: Unconditionally enable mitigation for | |
4786 | for both kernel and userspace | |
4787 | force-off: Unconditionally disable mitigation for | |
4788 | for both kernel and userspace | |
4789 | kernel: Always enable mitigation in the | |
4790 | kernel, and offer a prctl interface | |
4791 | to allow userspace to register its | |
4792 | interest in being mitigated too. | |
4793 | ||
1be7107f HD |
4794 | stack_guard_gap= [MM] |
4795 | override the default stack gap protection. The value | |
4796 | is in page units and it defines how many pages prior | |
4797 | to (for stacks growing down) resp. after (for stacks | |
4798 | growing up) the main stack are reserved for no other | |
4799 | mapping. Default value is 256 pages. | |
4800 | ||
f38f1d2a SR |
4801 | stacktrace [FTRACE] |
4802 | Enabled the stack tracer on boot up. | |
4803 | ||
762e1207 SR |
4804 | stacktrace_filter=[function-list] |
4805 | [FTRACE] Limit the functions that the stack tracer | |
4806 | will trace at boot up. function-list is a comma separated | |
4807 | list of functions. This list can be changed at run | |
4808 | time by the stack_trace_filter file in the debugfs | |
4809 | tracing directory. Note, this enables stack tracing | |
4810 | and the stacktrace above is not needed. | |
4811 | ||
1da177e4 LT |
4812 | sti= [PARISC,HW] |
4813 | Format: <num> | |
4814 | Set the STI (builtin display/keyboard on the HP-PARISC | |
4815 | machines) console (graphic card) which should be used | |
4816 | as the initial boot-console. | |
4817 | See also comment in drivers/video/console/sticore.c. | |
4818 | ||
4819 | sti_font= [HW] | |
4820 | See comment in drivers/video/console/sticore.c. | |
4821 | ||
4822 | stifb= [HW] | |
4823 | Format: bpp:<bpp1>[:<bpp2>[:<bpp3>...]] | |
4824 | ||
cbf11071 TM |
4825 | sunrpc.min_resvport= |
4826 | sunrpc.max_resvport= | |
4827 | [NFS,SUNRPC] | |
4828 | SunRPC servers often require that client requests | |
4829 | originate from a privileged port (i.e. a port in the | |
4830 | range 0 < portnr < 1024). | |
4831 | An administrator who wishes to reserve some of these | |
4832 | ports for other uses may adjust the range that the | |
4833 | kernel's sunrpc client considers to be privileged | |
4834 | using these two parameters to set the minimum and | |
4835 | maximum port values. | |
4836 | ||
ff3ac5c3 TM |
4837 | sunrpc.svc_rpc_per_connection_limit= |
4838 | [NFS,SUNRPC] | |
4839 | Limit the number of requests that the server will | |
4840 | process in parallel from a single connection. | |
4841 | The default value is 0 (no limit). | |
4842 | ||
42a7fc4a GB |
4843 | sunrpc.pool_mode= |
4844 | [NFS] | |
4845 | Control how the NFS server code allocates CPUs to | |
4846 | service thread pools. Depending on how many NICs | |
4847 | you have and where their interrupts are bound, this | |
4848 | option will affect which CPUs will do NFS serving. | |
4849 | Note: this parameter cannot be changed while the | |
4850 | NFS server is running. | |
4851 | ||
4852 | auto the server chooses an appropriate mode | |
4853 | automatically using heuristics | |
4854 | global a single global pool contains all CPUs | |
4855 | percpu one pool for each CPU | |
4856 | pernode one pool for each NUMA node (equivalent | |
4857 | to global on non-NUMA machines) | |
4858 | ||
cbf11071 TM |
4859 | sunrpc.tcp_slot_table_entries= |
4860 | sunrpc.udp_slot_table_entries= | |
4861 | [NFS,SUNRPC] | |
4862 | Sets the upper limit on the number of simultaneous | |
4863 | RPC calls that can be sent from the client to a | |
4864 | server. Increasing these values may allow you to | |
4865 | improve throughput, but will also increase the | |
4866 | amount of memory reserved for use by the client. | |
4867 | ||
1d4a9c17 BN |
4868 | suspend.pm_test_delay= |
4869 | [SUSPEND] | |
4870 | Sets the number of seconds to remain in a suspend test | |
4871 | mode before resuming the system (see | |
4872 | /sys/power/pm_test). Only available when CONFIG_PM_DEBUG | |
4873 | is set. Default value is 5. | |
4874 | ||
6a9c930b RP |
4875 | svm= [PPC] |
4876 | Format: { on | off | y | n | 1 | 0 } | |
4877 | This parameter controls use of the Protected | |
4878 | Execution Facility on pSeries. | |
4879 | ||
07555ac1 | 4880 | swapaccount=[0|1] |
a42c390c MH |
4881 | [KNL] Enable accounting of swap in memory resource |
4882 | controller if no parameter or 1 is given or disable | |
da82c92f | 4883 | it if 0 is given (See Documentation/admin-guide/cgroup-v1/memory.rst) |
a42c390c | 4884 | |
91fec0f5 | 4885 | swiotlb= [ARM,IA-64,PPC,MIPS,X86] |
fff5d992 | 4886 | Format: { <int> | force | noforce } |
91fec0f5 JK |
4887 | <int> -- Number of I/O TLB slabs |
4888 | force -- force using of bounce buffers even if they | |
4889 | wouldn't be automatically used by the kernel | |
fff5d992 | 4890 | noforce -- Never use bounce buffers (for debugging) |
a9913044 | 4891 | |
1da177e4 LT |
4892 | switches= [HW,M68k] |
4893 | ||
e52eec13 AK |
4894 | sysfs.deprecated=0|1 [KNL] |
4895 | Enable/disable old style sysfs layout for old udev | |
4896 | on older distributions. When this option is enabled | |
4897 | very new udev will not work anymore. When this option | |
4898 | is disabled (or CONFIG_SYSFS_DEPRECATED not compiled) | |
4899 | in older udev will not work anymore. | |
4900 | Default depends on CONFIG_SYSFS_DEPRECATED_V2 set in | |
4901 | the kernel configuration. | |
4902 | ||
5d6f647f IM |
4903 | sysrq_always_enabled |
4904 | [KNL] | |
4905 | Ignore sysrq setting - this boot parameter will | |
4906 | neutralize any effect of /proc/sys/kernel/sysrq. | |
4907 | Useful for debugging. | |
4908 | ||
747029a5 FF |
4909 | tcpmhash_entries= [KNL,NET] |
4910 | Set the number of tcp_metrics_hash slots. | |
4911 | Default value is 8192 or 16384 depending on total | |
4912 | ram pages. This is used to specify the TCP metrics | |
4913 | cache size. See Documentation/networking/ip-sysctl.txt | |
4914 | "tcp_no_metrics_save" section for more details. | |
4915 | ||
1da177e4 LT |
4916 | tdfx= [HW,DRM] |
4917 | ||
acc82342 | 4918 | test_suspend= [SUSPEND][,N] |
77437fd4 | 4919 | Specify "mem" (for Suspend-to-RAM) or "standby" (for |
acc82342 SP |
4920 | standby suspend) or "freeze" (for suspend type freeze) |
4921 | as the system sleep state during system startup with | |
4922 | the optional capability to repeat N number of times. | |
4923 | The system is woken from this state using a | |
4924 | wakeup-capable RTC alarm. | |
77437fd4 | 4925 | |
1da177e4 LT |
4926 | thash_entries= [KNL,NET] |
4927 | Set number of hash buckets for TCP connection | |
4928 | ||
f8707ec9 LB |
4929 | thermal.act= [HW,ACPI] |
4930 | -1: disable all active trip points in all thermal zones | |
4931 | <degrees C>: override all lowest active trip points | |
4932 | ||
c52a7419 LB |
4933 | thermal.crt= [HW,ACPI] |
4934 | -1: disable all critical trip points in all thermal zones | |
22a94d79 | 4935 | <degrees C>: override all critical trip points |
c52a7419 | 4936 | |
f5487145 LB |
4937 | thermal.nocrt= [HW,ACPI] |
4938 | Set to disable actions on ACPI thermal zone | |
4939 | critical and hot trip points. | |
4940 | ||
72b33ef8 LB |
4941 | thermal.off= [HW,ACPI] |
4942 | 1: disable ACPI thermal control | |
4943 | ||
a70cdc52 LB |
4944 | thermal.psv= [HW,ACPI] |
4945 | -1: disable all passive trip points | |
ada9cfdd RD |
4946 | <degrees C>: override all passive trip points to this |
4947 | value | |
a70cdc52 | 4948 | |
730ff34d LB |
4949 | thermal.tzp= [HW,ACPI] |
4950 | Specify global default ACPI thermal zone polling rate | |
4951 | <deci-seconds>: poll all this frequency | |
4952 | 0: no polling (default) | |
4953 | ||
8d32a307 TG |
4954 | threadirqs [KNL] |
4955 | Force threading of all interrupt handlers except those | |
24775d65 | 4956 | marked explicitly IRQF_NO_THREAD. |
8d32a307 | 4957 | |
2b1a61f0 HC |
4958 | topology= [S390] |
4959 | Format: {off | on} | |
4960 | Specify if the kernel should make use of the cpu | |
f65e51d7 SL |
4961 | topology information if the hardware supports this. |
4962 | The scheduler will make use of this information and | |
2b1a61f0 | 4963 | e.g. base its process migration decisions on it. |
c9af3fa9 | 4964 | Default is on. |
2b1a61f0 | 4965 | |
2d73bae1 NA |
4966 | topology_updates= [KNL, PPC, NUMA] |
4967 | Format: {off} | |
4968 | Specify if the kernel should ignore (off) | |
4969 | topology updates sent by the hypervisor to this | |
4970 | LPAR. | |
4971 | ||
8171d3e0 PM |
4972 | torture.disable_onoff_at_boot= [KNL] |
4973 | Prevent the CPU-hotplug component of torturing | |
4974 | until after init has spawned. | |
4975 | ||
1da177e4 LT |
4976 | tp720= [HW,PS2] |
4977 | ||
225a9be2 RA |
4978 | tpm_suspend_pcr=[HW,TPM] |
4979 | Format: integer pcr id | |
4980 | Specify that at suspend time, the tpm driver | |
4981 | should extend the specified pcr with zeros, | |
4982 | as a workaround for some chips which fail to | |
4983 | flush the last written pcr on TPM_SaveState. | |
4984 | This will guarantee that all the other pcrs | |
4985 | are saved. | |
4986 | ||
9d612bef | 4987 | trace_buf_size=nn[KMG] |
3e6fb8e9 | 4988 | [FTRACE] will set tracing buffer size on each cpu. |
631595fb | 4989 | |
020e5f85 LZ |
4990 | trace_event=[event-list] |
4991 | [FTRACE] Set and start specified trace events in order | |
d81749ea BN |
4992 | to facilitate early boot debugging. The event-list is a |
4993 | comma separated list of trace events to enable. See | |
5fb94e9c | 4994 | also Documentation/trace/events.rst |
020e5f85 | 4995 | |
7bcfaf54 SR |
4996 | trace_options=[option-list] |
4997 | [FTRACE] Enable or disable tracer options at boot. | |
4998 | The option-list is a comma delimited list of options | |
4999 | that can be enabled or disabled just as if you were | |
5000 | to echo the option name into | |
5001 | ||
5002 | /sys/kernel/debug/tracing/trace_options | |
5003 | ||
5004 | For example, to enable stacktrace option (to dump the | |
5005 | stack trace of each event), add to the command line: | |
5006 | ||
5007 | trace_options=stacktrace | |
5008 | ||
5fb94e9c | 5009 | See also Documentation/trace/ftrace.rst "trace options" |
7bcfaf54 SR |
5010 | section. |
5011 | ||
0daa2302 SRRH |
5012 | tp_printk[FTRACE] |
5013 | Have the tracepoints sent to printk as well as the | |
5014 | tracing ring buffer. This is useful for early boot up | |
5015 | where the system hangs or reboots and does not give the | |
5016 | option for reading the tracing buffer or performing a | |
5017 | ftrace_dump_on_oops. | |
5018 | ||
5019 | To turn off having tracepoints sent to printk, | |
5020 | echo 0 > /proc/sys/kernel/tracepoint_printk | |
5021 | Note, echoing 1 into this file without the | |
5022 | tracepoint_printk kernel cmdline option has no effect. | |
5023 | ||
5024 | ** CAUTION ** | |
5025 | ||
5026 | Having tracepoints sent to printk() and activating high | |
5027 | frequency tracepoints such as irq or sched, can cause | |
5028 | the system to live lock. | |
5029 | ||
de7edd31 SRRH |
5030 | traceoff_on_warning |
5031 | [FTRACE] enable this option to disable tracing when a | |
5032 | warning is hit. This turns off "tracing_on". Tracing can | |
5033 | be enabled again by echoing '1' into the "tracing_on" | |
5034 | file located in /sys/kernel/debug/tracing/ | |
5035 | ||
5036 | This option is useful, as it disables the trace before | |
5037 | the WARNING dump is called, which prevents the trace to | |
5038 | be filled with content caused by the warning output. | |
5039 | ||
5040 | This option can also be set at run time via the sysctl | |
5041 | option: kernel/traceoff_on_warning | |
5042 | ||
fcf4d821 JK |
5043 | transparent_hugepage= |
5044 | [KNL] | |
5045 | Format: [always|madvise|never] | |
5046 | Can be used to control the default behavior of the system | |
5047 | with respect to transparent hugepages. | |
45c9a74f MR |
5048 | See Documentation/admin-guide/mm/transhuge.rst |
5049 | for more details. | |
fcf4d821 | 5050 | |
d3b8f889 | 5051 | tsc= Disable clocksource stability checks for TSC. |
395628ef AK |
5052 | Format: <string> |
5053 | [x86] reliable: mark tsc clocksource as reliable, this | |
d3b8f889 | 5054 | disables clocksource verification at runtime, as well |
5055 | as the stability checks done at bootup. Used to enable | |
5056 | high-resolution timer mode on older hardware, and in | |
5057 | virtualized environment. | |
e82b8e4e VP |
5058 | [x86] noirqtime: Do not use TSC to do irq accounting. |
5059 | Used to run time disable IRQ_TIME_ACCOUNTING on any | |
5060 | platforms where RDTSC is slow and this accounting | |
5061 | can add overhead. | |
6be53520 DL |
5062 | [x86] unstable: mark the TSC clocksource as unstable, this |
5063 | marks the TSC unconditionally unstable at bootup and | |
5064 | avoids any further wobbles once the TSC watchdog notices. | |
0f0b7e1c JL |
5065 | [x86] nowatchdog: disable clocksource watchdog. Used |
5066 | in situations with strict latency requirements (where | |
5067 | interruptions from clocksource watchdog are not | |
5068 | acceptable). | |
395628ef | 5069 | |
95c5824f PG |
5070 | tsx= [X86] Control Transactional Synchronization |
5071 | Extensions (TSX) feature in Intel processors that | |
5072 | support TSX control. | |
5073 | ||
5074 | This parameter controls the TSX feature. The options are: | |
5075 | ||
5076 | on - Enable TSX on the system. Although there are | |
5077 | mitigations for all known security vulnerabilities, | |
5078 | TSX has been known to be an accelerator for | |
5079 | several previous speculation-related CVEs, and | |
5080 | so there may be unknown security risks associated | |
5081 | with leaving it enabled. | |
5082 | ||
5083 | off - Disable TSX on the system. (Note that this | |
5084 | option takes effect only on newer CPUs which are | |
5085 | not vulnerable to MDS, i.e., have | |
5086 | MSR_IA32_ARCH_CAPABILITIES.MDS_NO=1 and which get | |
5087 | the new IA32_TSX_CTRL MSR through a microcode | |
5088 | update. This new MSR allows for the reliable | |
5089 | deactivation of the TSX functionality.) | |
5090 | ||
7531a359 PG |
5091 | auto - Disable TSX if X86_BUG_TAA is present, |
5092 | otherwise enable TSX on the system. | |
5093 | ||
95c5824f PG |
5094 | Not specifying this option is equivalent to tsx=off. |
5095 | ||
5096 | See Documentation/admin-guide/hw-vuln/tsx_async_abort.rst | |
5097 | for more details. | |
5098 | ||
a7a248c5 PG |
5099 | tsx_async_abort= [X86,INTEL] Control mitigation for the TSX Async |
5100 | Abort (TAA) vulnerability. | |
5101 | ||
5102 | Similar to Micro-architectural Data Sampling (MDS) | |
5103 | certain CPUs that support Transactional | |
5104 | Synchronization Extensions (TSX) are vulnerable to an | |
5105 | exploit against CPU internal buffers which can forward | |
5106 | information to a disclosure gadget under certain | |
5107 | conditions. | |
5108 | ||
5109 | In vulnerable processors, the speculatively forwarded | |
5110 | data can be used in a cache side channel attack, to | |
5111 | access data to which the attacker does not have direct | |
5112 | access. | |
5113 | ||
5114 | This parameter controls the TAA mitigation. The | |
5115 | options are: | |
5116 | ||
5117 | full - Enable TAA mitigation on vulnerable CPUs | |
5118 | if TSX is enabled. | |
5119 | ||
5120 | full,nosmt - Enable TAA mitigation and disable SMT on | |
5121 | vulnerable CPUs. If TSX is disabled, SMT | |
5122 | is not disabled because CPU is not | |
5123 | vulnerable to cross-thread TAA attacks. | |
5124 | off - Unconditionally disable TAA mitigation | |
5125 | ||
64870ed1 WL |
5126 | On MDS-affected machines, tsx_async_abort=off can be |
5127 | prevented by an active MDS mitigation as both vulnerabilities | |
5128 | are mitigated with the same mechanism so in order to disable | |
5129 | this mitigation, you need to specify mds=off too. | |
5130 | ||
a7a248c5 PG |
5131 | Not specifying this option is equivalent to |
5132 | tsx_async_abort=full. On CPUs which are MDS affected | |
5133 | and deploy MDS mitigation, TAA mitigation is not | |
5134 | required and doesn't provide any additional | |
5135 | mitigation. | |
5136 | ||
5137 | For details see: | |
5138 | Documentation/admin-guide/hw-vuln/tsx_async_abort.rst | |
5139 | ||
a9913044 RD |
5140 | turbografx.map[2|3]= [HW,JOY] |
5141 | TurboGraFX parallel port interface | |
5142 | Format: | |
5143 | <port#>,<js1>,<js2>,<js3>,<js4>,<js5>,<js6>,<js7> | |
1752118d | 5144 | See also Documentation/input/devices/joystick-parport.rst |
1da177e4 | 5145 | |
b6935f8c | 5146 | udbg-immortal [PPC] When debugging early kernel crashes that |
e52347bd | 5147 | happen after console_init() and before a proper |
b6935f8c CK |
5148 | console driver takes over, this boot options might |
5149 | help "seeing" what's going on. | |
5150 | ||
f86dcc5a ED |
5151 | uhash_entries= [KNL,NET] |
5152 | Set number of hash buckets for UDP/UDP-Lite connections | |
5153 | ||
5f8364b7 AS |
5154 | uhci-hcd.ignore_oc= |
5155 | [USB] Ignore overcurrent events (default N). | |
5156 | Some badly-designed motherboards generate lots of | |
5157 | bogus events, for ports that aren't wired to | |
5158 | anything. Set this parameter to avoid log spamming. | |
5159 | Note that genuine overcurrent events won't be | |
5160 | reported either. | |
5161 | ||
e3a61b0a | 5162 | unknown_nmi_panic |
44a4dcf7 | 5163 | [X86] Cause panic on unknown NMI. |
e3a61b0a | 5164 | |
c4fc2342 CDH |
5165 | usbcore.authorized_default= |
5166 | [USB] Default USB device authorization: | |
5167 | (default -1 = authorized except for wireless USB, | |
7bae0432 DT |
5168 | 0 = not authorized, 1 = authorized, 2 = authorized |
5169 | if device connected to internal port) | |
c4fc2342 | 5170 | |
b5e795f8 AS |
5171 | usbcore.autosuspend= |
5172 | [USB] The autosuspend time delay (in seconds) used | |
5173 | for newly-detected USB devices (default 2). This | |
5174 | is the time required before an idle device will be | |
5175 | autosuspended. Devices for which the delay is set | |
eaafbc3a | 5176 | to a negative value won't be autosuspended at all. |
b5e795f8 | 5177 | |
fd7c519d JK |
5178 | usbcore.usbfs_snoop= |
5179 | [USB] Set to log all usbfs traffic (default 0 = off). | |
5180 | ||
0290cc9f AS |
5181 | usbcore.usbfs_snoop_max= |
5182 | [USB] Maximum number of bytes to snoop in each URB | |
5183 | (default = 65536). | |
5184 | ||
fd7c519d JK |
5185 | usbcore.blinkenlights= |
5186 | [USB] Set to cycle leds on hubs (default 0 = off). | |
5187 | ||
5188 | usbcore.old_scheme_first= | |
5189 | [USB] Start with the old device initialization | |
bd0e6c96 ZT |
5190 | scheme, applies only to low and full-speed devices |
5191 | (default 0 = off). | |
fd7c519d | 5192 | |
3f5eb8d5 AS |
5193 | usbcore.usbfs_memory_mb= |
5194 | [USB] Memory limit (in MB) for buffers allocated by | |
5195 | usbfs (default = 16, 0 = max = 2047). | |
5196 | ||
fd7c519d JK |
5197 | usbcore.use_both_schemes= |
5198 | [USB] Try the other device initialization scheme | |
5199 | if the first one fails (default 1 = enabled). | |
5200 | ||
5201 | usbcore.initial_descriptor_timeout= | |
5202 | [USB] Specifies timeout for the initial 64-byte | |
6dddd7a7 | 5203 | USB_REQ_GET_DESCRIPTOR request in milliseconds |
fd7c519d JK |
5204 | (default 5000 = 5.0 seconds). |
5205 | ||
40d58148 ON |
5206 | usbcore.nousb [USB] Disable the USB subsystem |
5207 | ||
027bd6ca KHF |
5208 | usbcore.quirks= |
5209 | [USB] A list of quirk entries to augment the built-in | |
5210 | usb core quirk list. List entries are separated by | |
5211 | commas. Each entry has the form | |
5212 | VendorID:ProductID:Flags. The IDs are 4-digit hex | |
5213 | numbers and Flags is a set of letters. Each letter | |
5214 | will change the built-in quirk; setting it if it is | |
5215 | clear and clearing it if it is set. The letters have | |
5216 | the following meanings: | |
5217 | a = USB_QUIRK_STRING_FETCH_255 (string | |
5218 | descriptors must not be fetched using | |
5219 | a 255-byte read); | |
5220 | b = USB_QUIRK_RESET_RESUME (device can't resume | |
5221 | correctly so reset it instead); | |
5222 | c = USB_QUIRK_NO_SET_INTF (device can't handle | |
5223 | Set-Interface requests); | |
5224 | d = USB_QUIRK_CONFIG_INTF_STRINGS (device can't | |
5225 | handle its Configuration or Interface | |
5226 | strings); | |
5227 | e = USB_QUIRK_RESET (device can't be reset | |
5228 | (e.g morph devices), don't use reset); | |
5229 | f = USB_QUIRK_HONOR_BNUMINTERFACES (device has | |
5230 | more interface descriptions than the | |
5231 | bNumInterfaces count, and can't handle | |
5232 | talking to these interfaces); | |
5233 | g = USB_QUIRK_DELAY_INIT (device needs a pause | |
5234 | during initialization, after we read | |
5235 | the device descriptor); | |
5236 | h = USB_QUIRK_LINEAR_UFRAME_INTR_BINTERVAL (For | |
5237 | high speed and super speed interrupt | |
5238 | endpoints, the USB 2.0 and USB 3.0 spec | |
5239 | require the interval in microframes (1 | |
5240 | microframe = 125 microseconds) to be | |
5241 | calculated as interval = 2 ^ | |
5242 | (bInterval-1). | |
5243 | Devices with this quirk report their | |
5244 | bInterval as the result of this | |
5245 | calculation instead of the exponent | |
5246 | variable used in the calculation); | |
5247 | i = USB_QUIRK_DEVICE_QUALIFIER (device can't | |
5248 | handle device_qualifier descriptor | |
5249 | requests); | |
5250 | j = USB_QUIRK_IGNORE_REMOTE_WAKEUP (device | |
5251 | generates spurious wakeup, ignore | |
5252 | remote wakeup capability); | |
5253 | k = USB_QUIRK_NO_LPM (device can't handle Link | |
5254 | Power Management); | |
5255 | l = USB_QUIRK_LINEAR_FRAME_INTR_BINTERVAL | |
5256 | (Device reports its bInterval as linear | |
5257 | frames instead of the USB 2.0 | |
5258 | calculation); | |
5259 | m = USB_QUIRK_DISCONNECT_SUSPEND (Device needs | |
5260 | to be disconnected before suspend to | |
4d8d5a39 KHF |
5261 | prevent spurious wakeup); |
5262 | n = USB_QUIRK_DELAY_CTRL_MSG (Device needs a | |
5263 | pause after every control message); | |
781f0766 KHF |
5264 | o = USB_QUIRK_HUB_SLOW_RESET (Hub needs extra |
5265 | delay after resetting its port); | |
027bd6ca KHF |
5266 | Example: quirks=0781:5580:bk,0a5c:5834:gij |
5267 | ||
1da177e4 LT |
5268 | usbhid.mousepoll= |
5269 | [USBHID] The interval which mice are to be polled at. | |
a9913044 | 5270 | |
933bfe4d TJ |
5271 | usbhid.jspoll= |
5272 | [USBHID] The interval which joysticks are to be polled at. | |
5273 | ||
2ddc8e2d FA |
5274 | usbhid.kbpoll= |
5275 | [USBHID] The interval which keyboards are to be polled at. | |
5276 | ||
d4f373e5 AS |
5277 | usb-storage.delay_use= |
5278 | [UMS] The delay in seconds before a new device is | |
19101954 | 5279 | scanned for Logical Units (default 1). |
d4f373e5 AS |
5280 | |
5281 | usb-storage.quirks= | |
5282 | [UMS] A list of quirks entries to supplement or | |
5283 | override the built-in unusual_devs list. List | |
5284 | entries are separated by commas. Each entry has | |
5285 | the form VID:PID:Flags where VID and PID are Vendor | |
5286 | and Product ID values (4-digit hex numbers) and | |
5287 | Flags is a set of characters, each corresponding | |
5288 | to a common usb-storage quirk flag as follows: | |
c838ea46 | 5289 | a = SANE_SENSE (collect more than 18 bytes |
65cc8bf9 | 5290 | of sense data, not on uas); |
a0bb1081 | 5291 | b = BAD_SENSE (don't collect more than 18 |
65cc8bf9 | 5292 | bytes of sense data, not on uas); |
d4f373e5 AS |
5293 | c = FIX_CAPACITY (decrease the reported |
5294 | device capacity by one sector); | |
5116901d | 5295 | d = NO_READ_DISC_INFO (don't use |
65cc8bf9 | 5296 | READ_DISC_INFO command, not on uas); |
5116901d KR |
5297 | e = NO_READ_CAPACITY_16 (don't use |
5298 | READ_CAPACITY_16 command); | |
734016b0 HG |
5299 | f = NO_REPORT_OPCODES (don't use report opcodes |
5300 | command, uas only); | |
ee136af4 HG |
5301 | g = MAX_SECTORS_240 (don't transfer more than |
5302 | 240 sectors at a time, uas only); | |
c838ea46 AS |
5303 | h = CAPACITY_HEURISTICS (decrease the |
5304 | reported device capacity by one | |
5305 | sector if the number is odd); | |
d4f373e5 AS |
5306 | i = IGNORE_DEVICE (don't bind to this |
5307 | device); | |
13630746 HG |
5308 | j = NO_REPORT_LUNS (don't use report luns |
5309 | command, uas only); | |
d4f373e5 | 5310 | l = NOT_LOCKABLE (don't try to lock and |
65cc8bf9 | 5311 | unlock ejectable media, not on uas); |
d4f373e5 | 5312 | m = MAX_SECTORS_64 (don't transfer more |
65cc8bf9 ON |
5313 | than 64 sectors = 32 KB at a time, |
5314 | not on uas); | |
21c13a4f | 5315 | n = INITIAL_READ10 (force a retry of the |
65cc8bf9 | 5316 | initial READ(10) command, not on uas); |
c838ea46 | 5317 | o = CAPACITY_OK (accept the capacity |
65cc8bf9 | 5318 | reported by the device, not on uas); |
eaa05dfc | 5319 | p = WRITE_CACHE (the device cache is ON |
65cc8bf9 | 5320 | by default, not on uas); |
d4f373e5 | 5321 | r = IGNORE_RESIDUE (the device reports |
65cc8bf9 | 5322 | bogus residue values, not on uas); |
d4f373e5 AS |
5323 | s = SINGLE_LUN (the device has only one |
5324 | Logical Unit); | |
59307852 HG |
5325 | t = NO_ATA_1X (don't allow ATA(12) and ATA(16) |
5326 | commands, uas only); | |
b6089f19 | 5327 | u = IGNORE_UAS (don't bind to the uas driver); |
d4f373e5 AS |
5328 | w = NO_WP_DETECT (don't test whether the |
5329 | medium is write-protected). | |
050bc4e8 | 5330 | y = ALWAYS_SYNC (issue a SYNCHRONIZE_CACHE |
65cc8bf9 ON |
5331 | even if the device claims no cache, |
5332 | not on uas) | |
d4f373e5 AS |
5333 | Example: quirks=0419:aaf5:rl,0421:0433:rc |
5334 | ||
ac1667db SB |
5335 | user_debug= [KNL,ARM] |
5336 | Format: <int> | |
5337 | See arch/arm/Kconfig.debug help text. | |
5338 | 1 - undefined instruction events | |
5339 | 2 - system calls | |
5340 | 4 - invalid data aborts | |
5341 | 8 - SIGSEGV faults | |
5342 | 16 - SIGBUS faults | |
5343 | Example: user_debug=31 | |
5344 | ||
14315592 IC |
5345 | userpte= |
5346 | [X86] Flags controlling user PTE allocations. | |
5347 | ||
5348 | nohigh = do not allocate PTE pages in | |
5349 | HIGHMEM regardless of setting | |
5350 | of CONFIG_HIGHPTE. | |
5351 | ||
6cececfc | 5352 | vdso= [X86,SH] |
b0b49f26 AL |
5353 | On X86_32, this is an alias for vdso32=. Otherwise: |
5354 | ||
5355 | vdso=1: enable VDSO (the default) | |
e6e5494c IM |
5356 | vdso=0: disable VDSO mapping |
5357 | ||
b0b49f26 AL |
5358 | vdso32= [X86] Control the 32-bit vDSO |
5359 | vdso32=1: enable 32-bit VDSO | |
5360 | vdso32=0 or vdso32=2: disable 32-bit VDSO | |
5361 | ||
5362 | See the help text for CONFIG_COMPAT_VDSO for more | |
5363 | details. If CONFIG_COMPAT_VDSO is set, the default is | |
5364 | vdso32=0; otherwise, the default is vdso32=1. | |
5365 | ||
5366 | For compatibility with older kernels, vdso32=2 is an | |
5367 | alias for vdso32=0. | |
5368 | ||
5369 | Try vdso32=0 if you encounter an error that says: | |
5370 | dl_main: Assertion `(void *) ph->p_vaddr == _rtld_local._dl_sysinfo_dso' failed! | |
af65d648 | 5371 | |
d080d397 YI |
5372 | vector= [IA-64,SMP] |
5373 | vector=percpu: enable percpu vector domain | |
5374 | ||
1da177e4 | 5375 | video= [FB] Frame buffer configuration |
ab42b818 | 5376 | See Documentation/fb/modedb.rst. |
1da177e4 | 5377 | |
3afe6dab AL |
5378 | video.brightness_switch_enabled= [0,1] |
5379 | If set to 1, on receiving an ACPI notify event | |
5380 | generated by hotkey, video driver will adjust brightness | |
5381 | level and then send out the event to user space through | |
5382 | the allocated input device; If set to 0, video driver | |
5383 | will only send out the event without touching backlight | |
5384 | brightness level. | |
2843768b | 5385 | default: 1 |
3afe6dab | 5386 | |
81a054ce PM |
5387 | virtio_mmio.device= |
5388 | [VMMIO] Memory mapped virtio (platform) device. | |
5389 | ||
5390 | <size>@<baseaddr>:<irq>[:<id>] | |
5391 | where: | |
5392 | <size> := size (can use standard suffixes | |
5393 | like K, M and G) | |
5394 | <baseaddr> := physical base address | |
5395 | <irq> := interrupt number (as passed to | |
5396 | request_irq()) | |
5397 | <id> := (optional) platform device id | |
5398 | example: | |
5399 | virtio_mmio.device=1K@0x100b0000:48:7 | |
5400 | ||
5401 | Can be used multiple times for multiple devices. | |
5402 | ||
cd4f0ef7 | 5403 | vga= [BOOT,X86-32] Select a particular video mode |
cb1aaebe | 5404 | See Documentation/x86/boot.rst and |
4f4cfa6c | 5405 | Documentation/admin-guide/svga.rst. |
1da177e4 LT |
5406 | Use vga=ask for menu. |
5407 | This is actually a boot loader parameter; the value is | |
5408 | passed to the kernel using a special protocol. | |
5409 | ||
f682a97a AD |
5410 | vm_debug[=options] [KNL] Available with CONFIG_DEBUG_VM=y. |
5411 | May slow down system boot speed, especially when | |
5412 | enabled on systems with a large amount of memory. | |
5413 | All options are enabled by default, and this | |
5414 | interface is meant to allow for selectively | |
5415 | enabling or disabling specific virtual memory | |
5416 | debugging features. | |
5417 | ||
5418 | Available options are: | |
5419 | P Enable page structure init time poisoning | |
5420 | - Disable all of the above options | |
5421 | ||
a9913044 | 5422 | vmalloc=nn[KMG] [KNL,BOOT] Forces the vmalloc area to have an exact |
1da177e4 LT |
5423 | size of <nn>. This can be used to increase the |
5424 | minimum size (128MB on x86). It can also be used to | |
5425 | decrease the size and leave more room for directly | |
5426 | mapped kernel RAM. | |
5427 | ||
3f429842 HC |
5428 | vmcp_cma=nn[MG] [KNL,S390] |
5429 | Sets the memory size reserved for contiguous memory | |
5430 | allocations for the vmcp device driver. | |
5431 | ||
585c3047 PO |
5432 | vmhalt= [KNL,S390] Perform z/VM CP command after system halt. |
5433 | Format: <command> | |
1da177e4 | 5434 | |
585c3047 PO |
5435 | vmpanic= [KNL,S390] Perform z/VM CP command after kernel panic. |
5436 | Format: <command> | |
5437 | ||
5438 | vmpoff= [KNL,S390] Perform z/VM CP command after power off. | |
5439 | Format: <command> | |
a9913044 | 5440 | |
3ae36655 AL |
5441 | vsyscall= [X86-64] |
5442 | Controls the behavior of vsyscalls (i.e. calls to | |
5443 | fixed addresses of 0xffffffffff600x00 from legacy | |
5444 | code). Most statically-linked binaries and older | |
5445 | versions of glibc use these calls. Because these | |
5446 | functions are at fixed addresses, they make nice | |
5447 | targets for exploits that can control RIP. | |
5448 | ||
2e57ae05 | 5449 | emulate [default] Vsyscalls turn into traps and are |
bd49e16e AL |
5450 | emulated reasonably safely. The vsyscall |
5451 | page is readable. | |
3ae36655 | 5452 | |
bd49e16e AL |
5453 | xonly Vsyscalls turn into traps and are |
5454 | emulated reasonably safely. The vsyscall | |
5455 | page is not readable. | |
3ae36655 AL |
5456 | |
5457 | none Vsyscalls don't work at all. This makes | |
5458 | them quite hard to use for exploits but | |
5459 | might break your system. | |
5460 | ||
3855ae1c CL |
5461 | vt.color= [VT] Default text color. |
5462 | Format: 0xYX, X = foreground, Y = background. | |
5463 | Default: 0x07 = light gray on black. | |
5464 | ||
9ea9a886 CL |
5465 | vt.cur_default= [VT] Default cursor shape. |
5466 | Format: 0xCCBBAA, where AA, BB, and CC are the same as | |
5467 | the parameters of the <Esc>[?A;B;Cc escape sequence; | |
5468 | see VGA-softcursor.txt. Default: 2 = underline. | |
5469 | ||
0cb55ad2 RD |
5470 | vt.default_blu= [VT] |
5471 | Format: <blue0>,<blue1>,<blue2>,...,<blue15> | |
5472 | Change the default blue palette of the console. | |
5473 | This is a 16-member array composed of values | |
5474 | ranging from 0-255. | |
5475 | ||
5476 | vt.default_grn= [VT] | |
5477 | Format: <green0>,<green1>,<green2>,...,<green15> | |
5478 | Change the default green palette of the console. | |
5479 | This is a 16-member array composed of values | |
5480 | ranging from 0-255. | |
5481 | ||
5482 | vt.default_red= [VT] | |
5483 | Format: <red0>,<red1>,<red2>,...,<red15> | |
5484 | Change the default red palette of the console. | |
5485 | This is a 16-member array composed of values | |
5486 | ranging from 0-255. | |
5487 | ||
5488 | vt.default_utf8= | |
5489 | [VT] | |
5490 | Format=<0|1> | |
5491 | Set system-wide default UTF-8 mode for all tty's. | |
5492 | Default is 1, i.e. UTF-8 mode is enabled for all | |
5493 | newly opened terminals. | |
5494 | ||
f6c06b68 MG |
5495 | vt.global_cursor_default= |
5496 | [VT] | |
5497 | Format=<-1|0|1> | |
5498 | Set system-wide default for whether a cursor | |
5499 | is shown on new VTs. Default is -1, | |
5500 | i.e. cursors will be created by default unless | |
5501 | overridden by individual drivers. 0 will hide | |
5502 | cursors, 1 will display them. | |
5503 | ||
3855ae1c CL |
5504 | vt.italic= [VT] Default color for italic text; 0-15. |
5505 | Default: 2 = green. | |
5506 | ||
5507 | vt.underline= [VT] Default color for underlined text; 0-15. | |
5508 | Default: 3 = cyan. | |
5509 | ||
4724ba57 | 5510 | watchdog timers [HW,WDT] For information on watchdog timers, |
cc2a2d19 | 5511 | see Documentation/watchdog/watchdog-parameters.rst |
4724ba57 RD |
5512 | or other driver-specific files in the |
5513 | Documentation/watchdog/ directory. | |
1da177e4 | 5514 | |
11295055 LO |
5515 | watchdog_thresh= |
5516 | [KNL] | |
5517 | Set the hard lockup detector stall duration | |
5518 | threshold in seconds. The soft lockup detector | |
5519 | threshold is set to twice the value. A value of 0 | |
5520 | disables both lockup detectors. Default is 10 | |
5521 | seconds. | |
5522 | ||
82607adc TH |
5523 | workqueue.watchdog_thresh= |
5524 | If CONFIG_WQ_WATCHDOG is configured, workqueue can | |
5525 | warn stall conditions and dump internal state to | |
5526 | help debugging. 0 disables workqueue stall | |
5527 | detection; otherwise, it's the stall threshold | |
5528 | duration in seconds. The default value is 30 and | |
5529 | it can be updated at runtime by writing to the | |
5530 | corresponding sysfs file. | |
5531 | ||
d55262c4 TH |
5532 | workqueue.disable_numa |
5533 | By default, all work items queued to unbound | |
5534 | workqueues are affine to the NUMA nodes they're | |
5535 | issued on, which results in better behavior in | |
5536 | general. If NUMA affinity needs to be disabled for | |
5537 | whatever reason, this option can be used. Note | |
5538 | that this also can be controlled per-workqueue for | |
5539 | workqueues visible under /sys/bus/workqueue/. | |
5540 | ||
cee22a15 VK |
5541 | workqueue.power_efficient |
5542 | Per-cpu workqueues are generally preferred because | |
5543 | they show better performance thanks to cache | |
5544 | locality; unfortunately, per-cpu workqueues tend to | |
5545 | be more power hungry than unbound workqueues. | |
5546 | ||
5547 | Enabling this makes the per-cpu workqueues which | |
5548 | were observed to contribute significantly to power | |
5549 | consumption unbound, leading to measurably lower | |
5550 | power usage at the cost of small performance | |
5551 | overhead. | |
5552 | ||
5553 | The default value of this parameter is determined by | |
5554 | the config option CONFIG_WQ_POWER_EFFICIENT_DEFAULT. | |
5555 | ||
f303fccb TH |
5556 | workqueue.debug_force_rr_cpu |
5557 | Workqueue used to implicitly guarantee that work | |
5558 | items queued without explicit CPU specified are put | |
5559 | on the local CPU. This guarantee is no longer true | |
5560 | and while local CPU is still preferred work items | |
5561 | may be put on foreign CPUs. This debug option | |
5562 | forces round-robin CPU selection to flush out | |
5563 | usages which depend on the now broken guarantee. | |
5564 | When enabled, memory and cache locality will be | |
5565 | impacted. | |
5566 | ||
0cb55ad2 RD |
5567 | x2apic_phys [X86-64,APIC] Use x2apic physical mode instead of |
5568 | default x2apic cluster mode on platforms | |
5569 | supporting x2apic. | |
5570 | ||
712b6aa8 KS |
5571 | x86_intel_mid_timer= [X86-32,APBT] |
5572 | Choose timer option for x86 Intel MID platform. | |
bb24c471 JP |
5573 | Two valid options are apbt timer only and lapic timer |
5574 | plus one apbt timer for broadcast timer. | |
712b6aa8 | 5575 | x86_intel_mid_timer=apbt_only | lapic_and_apbt |
bb24c471 | 5576 | |
c70727a5 JG |
5577 | xen_512gb_limit [KNL,X86-64,XEN] |
5578 | Restricts the kernel running paravirtualized under Xen | |
5579 | to use only up to 512 GB of RAM. The reason to do so is | |
5580 | crash analysis tools and Xen tools for doing domain | |
5581 | save/restore/migration must be enabled to handle larger | |
5582 | domains. | |
5583 | ||
c1c5413a SS |
5584 | xen_emul_unplug= [HW,X86,XEN] |
5585 | Unplug Xen emulated devices | |
5586 | Format: [unplug0,][unplug1] | |
5587 | ide-disks -- unplug primary master IDE devices | |
5588 | aux-ide-disks -- unplug non-primary-master IDE devices | |
5589 | nics -- unplug network devices | |
5590 | all -- unplug all emulated devices (NICs and IDE disks) | |
1dc7ce99 IC |
5591 | unnecessary -- unplugging emulated devices is |
5592 | unnecessary even if the host did not respond to | |
5593 | the unplug protocol | |
c93a4dfb | 5594 | never -- do not unplug even if version check succeeds |
c1c5413a | 5595 | |
c6875f3a BO |
5596 | xen_legacy_crash [X86,XEN] |
5597 | Crash from Xen panic notifier, without executing late | |
5598 | panic() code such as dumping handler. | |
5599 | ||
15a3eac0 KRW |
5600 | xen_nopvspin [X86,XEN] |
5601 | Disables the ticketlock slowpath using Xen PV | |
5602 | optimizations. | |
5603 | ||
8d693b91 KRW |
5604 | xen_nopv [X86] |
5605 | Disables the PV optimizations forcing the HVM guest to | |
5606 | run as generic HVM guest with no PV drivers. | |
b39b0497 ZD |
5607 | This option is obsoleted by the "nopv" option, which |
5608 | has equivalent effect for XEN platform. | |
8d693b91 | 5609 | |
197ecb38 MMG |
5610 | xen_scrub_pages= [XEN] |
5611 | Boolean option to control scrubbing pages before giving them back | |
5612 | to Xen, for use by other domains. Can be also changed at runtime | |
5613 | with /sys/devices/system/xen_memory/xen_memory0/scrub_pages. | |
5614 | Default value controlled with CONFIG_XEN_SCRUB_PAGES_DEFAULT. | |
5615 | ||
2ec16bc0 RT |
5616 | xen_timer_slop= [X86-64,XEN] |
5617 | Set the timer slop (in nanoseconds) for the virtual Xen | |
5618 | timers (default is 100000). This adjusts the minimum | |
5619 | delta of virtualized Xen timers, where lower values | |
5620 | improve timer resolution at the expense of processing | |
5621 | more timer interrupts. | |
5622 | ||
30978346 ZD |
5623 | nopv= [X86,XEN,KVM,HYPER_V,VMWARE] |
5624 | Disables the PV optimizations forcing the guest to run | |
5625 | as generic guest with no PV drivers. Currently support | |
5626 | XEN HVM, KVM, HYPER_V and VMWARE guest. | |
5627 | ||
1da177e4 | 5628 | xirc2ps_cs= [NET,PCMCIA] |
a9913044 RD |
5629 | Format: |
5630 | <irq>,<irq_mask>,<io>,<full_duplex>,<do_sound>,<lockup_hack>[,<irq2>[,<irq3>[,<irq4>]]] | |
c0addc9a | 5631 | |
ba45cff6 MN |
5632 | xive= [PPC] |
5633 | By default on POWER9 and above, the kernel will | |
5634 | natively use the XIVE interrupt controller. This option | |
5635 | allows the fallback firmware mode to be used: | |
5636 | ||
5637 | off Fallback to firmware control of XIVE interrupt | |
5638 | controller on both pseries and powernv | |
5639 | platforms. Only useful on POWER9 and above. | |
5640 | ||
c0addc9a LT |
5641 | xhci-hcd.quirks [USB,KNL] |
5642 | A hex value specifying bitmask with supplemental xhci | |
5643 | host controller quirks. Meaning of each bit can be | |
5644 | consulted in header drivers/usb/host/xhci.h. | |
6278f55b GR |
5645 | |
5646 | xmon [PPC] | |
5647 | Format: { early | on | rw | ro | off } | |
5648 | Controls if xmon debugger is enabled. Default is off. | |
5649 | Passing only "xmon" is equivalent to "xmon=early". | |
5650 | early Call xmon as early as possible on boot; xmon | |
5651 | debugger is called from setup_arch(). | |
5652 | on xmon debugger hooks will be installed so xmon | |
5653 | is only called on a kernel crash. Default mode, | |
5654 | i.e. either "ro" or "rw" mode, is controlled | |
5655 | with CONFIG_XMON_DEFAULT_RO_MODE. | |
5656 | rw xmon debugger hooks will be installed so xmon | |
5657 | is called only on a kernel crash, mode is write, | |
5658 | meaning SPR registers, memory and, other data | |
5659 | can be written using xmon commands. | |
5660 | ro same as "rw" option above but SPR registers, | |
5661 | memory, and other data can't be written using | |
5662 | xmon commands. | |
5663 | off xmon is disabled. |