Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 1 | AMD64 specific boot options |
| 2 | |
| 3 | There are many others (usually documented in driver documentation), but |
| 4 | only the AMD64 specific ones are listed here. |
| 5 | |
| 6 | Machine check |
| 7 | |
Andi Kleen | 8780e8e | 2009-05-27 21:56:56 +0200 | [diff] [blame] | 8 | Please see Documentation/x86/x86_64/machinecheck for sysfs runtime tunables. |
| 9 | |
Hidetoshi Seto | 62fdac5 | 2009-06-11 16:06:07 +0900 | [diff] [blame] | 10 | mce=off |
| 11 | Disable machine check |
| 12 | mce=no_cmci |
| 13 | Disable CMCI(Corrected Machine Check Interrupt) that |
| 14 | Intel processor supports. Usually this disablement is |
| 15 | not recommended, but it might be handy if your hardware |
| 16 | is misbehaving. |
| 17 | Note that you'll get more problems without CMCI than with |
| 18 | due to the shared banks, i.e. you might get duplicated |
| 19 | error logs. |
| 20 | mce=dont_log_ce |
| 21 | Don't make logs for corrected errors. All events reported |
| 22 | as corrected are silently cleared by OS. |
| 23 | This option will be useful if you have no interest in any |
| 24 | of corrected errors. |
| 25 | mce=ignore_ce |
| 26 | Disable features for corrected errors, e.g. polling timer |
| 27 | and CMCI. All events reported as corrected are not cleared |
| 28 | by OS and remained in its error banks. |
| 29 | Usually this disablement is not recommended, however if |
| 30 | there is an agent checking/clearing corrected errors |
| 31 | (e.g. BIOS or hardware monitoring applications), conflicting |
| 32 | with OS's error handling, and you cannot deactivate the agent, |
| 33 | then this option will be a help. |
| 34 | mce=bootlog |
| 35 | Enable logging of machine checks left over from booting. |
| 36 | Disabled by default on AMD because some BIOS leave bogus ones. |
| 37 | If your BIOS doesn't do that it's a good idea to enable though |
| 38 | to make sure you log even machine check events that result |
| 39 | in a reboot. On Intel systems it is enabled by default. |
Andi Kleen | e583538 | 2005-11-05 17:25:54 +0100 | [diff] [blame] | 40 | mce=nobootlog |
| 41 | Disable boot machine check logging. |
Andi Kleen | 3c07979 | 2009-05-27 21:56:55 +0200 | [diff] [blame] | 42 | mce=tolerancelevel[,monarchtimeout] (number,number) |
| 43 | tolerance levels: |
Tim Hockin | bd78432 | 2007-07-21 17:10:37 +0200 | [diff] [blame] | 44 | 0: always panic on uncorrected errors, log corrected errors |
| 45 | 1: panic or SIGBUS on uncorrected errors, log corrected errors |
| 46 | 2: SIGBUS or log uncorrected errors, log corrected errors |
| 47 | 3: never panic or SIGBUS, log all errors (for testing only) |
| 48 | Default is 1 |
Andi Kleen | 8c566ef | 2005-09-12 18:49:24 +0200 | [diff] [blame] | 49 | Can be also set using sysfs which is preferable. |
Andi Kleen | 3c07979 | 2009-05-27 21:56:55 +0200 | [diff] [blame] | 50 | monarchtimeout: |
| 51 | Sets the time in us to wait for other CPUs on machine checks. 0 |
| 52 | to disable. |
Naveen N. Rao | 450cc20 | 2012-09-27 10:08:00 -0700 | [diff] [blame] | 53 | mce=bios_cmci_threshold |
| 54 | Don't overwrite the bios-set CMCI threshold. This boot option |
| 55 | prevents Linux from overwriting the CMCI threshold set by the |
| 56 | bios. Without this option, Linux always sets the CMCI |
| 57 | threshold to 1. Enabling this may make memory predictive failure |
| 58 | analysis less effective if the bios sets thresholds for memory |
| 59 | errors since we will not see details for all errors. |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 60 | |
| 61 | nomce (for compatibility with i386): same as mce=off |
| 62 | |
| 63 | Everything else is in sysfs now. |
| 64 | |
| 65 | APICs |
| 66 | |
| 67 | apic Use IO-APIC. Default |
| 68 | |
| 69 | noapic Don't use the IO-APIC. |
| 70 | |
| 71 | disableapic Don't use the local APIC |
| 72 | |
| 73 | nolapic Don't use the local APIC (alias for i386 compatibility) |
| 74 | |
Uwe Hermann | 71cced6 | 2008-10-20 09:32:21 -0700 | [diff] [blame] | 75 | pirq=... See Documentation/x86/i386/IO-APIC.txt |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 76 | |
| 77 | noapictimer Don't set up the APIC timer |
| 78 | |
Andi Kleen | 14d98ca | 2005-05-20 14:27:59 -0700 | [diff] [blame] | 79 | no_timer_check Don't check the IO-APIC timer. This can work around |
| 80 | problems with incorrect timer initialization on some boards. |
Andi Kleen | 0c3749c | 2006-02-03 21:51:41 +0100 | [diff] [blame] | 81 | apicpmtimer |
| 82 | Do APIC timer calibration using the pmtimer. Implies |
| 83 | apicmaintimer. Useful when your PIT timer is totally |
| 84 | broken. |
| 85 | |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 86 | Timing |
| 87 | |
| 88 | notsc |
| 89 | Don't use the CPU time stamp counter to read the wall time. |
| 90 | This can be used to work around timing problems on multiprocessor systems |
Andi Kleen | ef4d7cb | 2005-07-28 21:15:34 -0700 | [diff] [blame] | 91 | with not properly synchronized CPUs. |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 92 | |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 93 | nohpet |
| 94 | Don't use the HPET timer. |
| 95 | |
| 96 | Idle loop |
| 97 | |
| 98 | idle=poll |
| 99 | Don't do power saving in the idle loop using HLT, but poll for rescheduling |
| 100 | event. This will make the CPUs eat a lot more power, but may be useful |
| 101 | to get slightly better performance in multiprocessor benchmarks. It also |
| 102 | makes some profiling using performance counters more accurate. |
Andi Kleen | ef4d7cb | 2005-07-28 21:15:34 -0700 | [diff] [blame] | 103 | Please note that on systems with MONITOR/MWAIT support (like Intel EM64T |
| 104 | CPUs) this option has no performance advantage over the normal idle loop. |
| 105 | It may also interact badly with hyperthreading. |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 106 | |
| 107 | Rebooting |
| 108 | |
Huang, Ying | 9ad65e4 | 2008-01-30 13:31:19 +0100 | [diff] [blame] | 109 | reboot=b[ios] | t[riple] | k[bd] | a[cpi] | e[fi] [, [w]arm | [c]old] |
Matt LaPlante | d6bc8ac | 2006-10-03 22:54:15 +0200 | [diff] [blame] | 110 | bios Use the CPU reboot vector for warm reset |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 111 | warm Don't set the cold reboot flag |
| 112 | cold Set the cold reboot flag |
| 113 | triple Force a triple fault (init) |
| 114 | kbd Use the keyboard controller. cold reset (default) |
Aaron Durbin | fa20efd | 2008-01-30 13:31:17 +0100 | [diff] [blame] | 115 | acpi Use the ACPI RESET_REG in the FADT. If ACPI is not configured or the |
| 116 | ACPI reset does not work, the reboot path attempts the reset using |
| 117 | the keyboard controller. |
Huang, Ying | 9ad65e4 | 2008-01-30 13:31:19 +0100 | [diff] [blame] | 118 | efi Use efi reset_system runtime service. If EFI is not configured or the |
| 119 | EFI reset does not work, the reboot path attempts the reset using |
| 120 | the keyboard controller. |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 121 | |
| 122 | Using warm reset will be much faster especially on big memory |
| 123 | systems because the BIOS will not go through the memory check. |
| 124 | Disadvantage is that not all hardware will be completely reinitialized |
| 125 | on reboot so there may be boot problems on some systems. |
| 126 | |
| 127 | reboot=force |
| 128 | |
| 129 | Don't stop other CPUs on reboot. This can make reboot more reliable |
| 130 | in some cases. |
| 131 | |
| 132 | Non Executable Mappings |
| 133 | |
| 134 | noexec=on|off |
| 135 | |
| 136 | on Enable(default) |
| 137 | off Disable |
| 138 | |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 139 | NUMA |
| 140 | |
| 141 | numa=off Only set up a single NUMA node spanning all memory. |
| 142 | |
| 143 | numa=noacpi Don't parse the SRAT table for NUMA setup |
| 144 | |
David Rientjes | 8df5bb34 | 2010-02-15 13:43:30 -0800 | [diff] [blame] | 145 | numa=fake=<size>[MG] |
| 146 | If given as a memory unit, fills all system RAM with nodes of |
| 147 | size interleaved over physical nodes. |
| 148 | |
David Rientjes | ca2107c | 2010-02-15 13:43:33 -0800 | [diff] [blame] | 149 | numa=fake=<N> |
| 150 | If given as an integer, fills all system RAM with N fake nodes |
| 151 | interleaved over physical nodes. |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 152 | |
| 153 | ACPI |
| 154 | |
| 155 | acpi=off Don't enable ACPI |
| 156 | acpi=ht Use ACPI boot table parsing, but don't enable ACPI |
| 157 | interpreter |
| 158 | acpi=force Force ACPI on (currently not needed) |
| 159 | |
| 160 | acpi=strict Disable out of spec ACPI workarounds. |
| 161 | |
| 162 | acpi_sci={edge,level,high,low} Set up ACPI SCI interrupt. |
| 163 | |
| 164 | acpi=noirq Don't route interrupts |
| 165 | |
Naveen N. Rao | 9ad9587 | 2013-07-01 21:08:54 +0530 | [diff] [blame] | 166 | acpi=nocmcff Disable firmware first mode for corrected errors. This |
| 167 | disables parsing the HEST CMC error source to check if |
| 168 | firmware has set the FF flag. This may result in |
| 169 | duplicate corrected error reports. |
| 170 | |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 171 | PCI |
| 172 | |
Lucas De Marchi | a6c3270 | 2011-03-17 16:24:15 -0300 | [diff] [blame] | 173 | pci=off Don't use PCI |
| 174 | pci=conf1 Use conf1 access. |
| 175 | pci=conf2 Use conf2 access. |
| 176 | pci=rom Assign ROMs. |
| 177 | pci=assign-busses Assign busses |
| 178 | pci=irqmask=MASK Set PCI interrupt mask to MASK |
| 179 | pci=lastbus=NUMBER Scan up to NUMBER busses, no matter what the mptable says. |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 180 | pci=noacpi Don't use ACPI to set up PCI interrupt routing. |
| 181 | |
Karsten Weiss | 5558870 | 2007-02-13 13:26:21 +0100 | [diff] [blame] | 182 | IOMMU (input/output memory management unit) |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 183 | |
Karsten Weiss | 5558870 | 2007-02-13 13:26:21 +0100 | [diff] [blame] | 184 | Currently four x86-64 PCI-DMA mapping implementations exist: |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 185 | |
Karsten Weiss | 5558870 | 2007-02-13 13:26:21 +0100 | [diff] [blame] | 186 | 1. <arch/x86_64/kernel/pci-nommu.c>: use no hardware/software IOMMU at all |
| 187 | (e.g. because you have < 3 GB memory). |
| 188 | Kernel boot message: "PCI-DMA: Disabling IOMMU" |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 189 | |
Joerg Roedel | fffcda1 | 2011-05-10 17:22:06 +0200 | [diff] [blame] | 190 | 2. <arch/x86/kernel/amd_gart_64.c>: AMD GART based hardware IOMMU. |
Karsten Weiss | 5558870 | 2007-02-13 13:26:21 +0100 | [diff] [blame] | 191 | Kernel boot message: "PCI-DMA: using GART IOMMU" |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 192 | |
Karsten Weiss | 5558870 | 2007-02-13 13:26:21 +0100 | [diff] [blame] | 193 | 3. <arch/x86_64/kernel/pci-swiotlb.c> : Software IOMMU implementation. Used |
| 194 | e.g. if there is no hardware IOMMU in the system and it is need because |
| 195 | you have >3GB memory or told the kernel to us it (iommu=soft)) |
| 196 | Kernel boot message: "PCI-DMA: Using software bounce buffering |
| 197 | for IO (SWIOTLB)" |
| 198 | |
| 199 | 4. <arch/x86_64/pci-calgary.c> : IBM Calgary hardware IOMMU. Used in IBM |
| 200 | pSeries and xSeries servers. This hardware IOMMU supports DMA address |
| 201 | mapping with memory protection, etc. |
| 202 | Kernel boot message: "PCI-DMA: Using Calgary IOMMU" |
| 203 | |
| 204 | iommu=[<size>][,noagp][,off][,force][,noforce][,leak[=<nr_of_leak_pages>] |
| 205 | [,memaper[=<order>]][,merge][,forcesac][,fullflush][,nomerge] |
| 206 | [,noaperture][,calgary] |
| 207 | |
| 208 | General iommu options: |
| 209 | off Don't initialize and use any kind of IOMMU. |
| 210 | noforce Don't force hardware IOMMU usage when it is not needed. |
| 211 | (default). |
| 212 | force Force the use of the hardware IOMMU even when it is |
| 213 | not actually needed (e.g. because < 3 GB memory). |
| 214 | soft Use software bounce buffering (SWIOTLB) (default for |
| 215 | Intel machines). This can be used to prevent the usage |
| 216 | of an available hardware IOMMU. |
| 217 | |
| 218 | iommu options only relevant to the AMD GART hardware IOMMU: |
| 219 | <size> Set the size of the remapping area in bytes. |
| 220 | allowed Overwrite iommu off workarounds for specific chipsets. |
| 221 | fullflush Flush IOMMU on each allocation (default). |
| 222 | nofullflush Don't use IOMMU fullflush. |
| 223 | leak Turn on simple iommu leak tracing (only when |
| 224 | CONFIG_IOMMU_LEAK is on). Default number of leak pages |
| 225 | is 20. |
| 226 | memaper[=<order>] Allocate an own aperture over RAM with size 32MB<<order. |
| 227 | (default: order=1, i.e. 64MB) |
Randy Dunlap | 57d3077 | 2007-02-13 13:26:23 +0100 | [diff] [blame] | 228 | merge Do scatter-gather (SG) merging. Implies "force" |
Karsten Weiss | 5558870 | 2007-02-13 13:26:21 +0100 | [diff] [blame] | 229 | (experimental). |
Randy Dunlap | 57d3077 | 2007-02-13 13:26:23 +0100 | [diff] [blame] | 230 | nomerge Don't do scatter-gather (SG) merging. |
Karsten Weiss | 5558870 | 2007-02-13 13:26:21 +0100 | [diff] [blame] | 231 | noaperture Ask the IOMMU not to touch the aperture for AGP. |
| 232 | forcesac Force single-address cycle (SAC) mode for masks <40bits |
| 233 | (experimental). |
| 234 | noagp Don't initialize the AGP driver and use full aperture. |
| 235 | allowdac Allow double-address cycle (DAC) mode, i.e. DMA >4GB. |
| 236 | DAC is used with 32-bit PCI to push a 64-bit address in |
| 237 | two cycles. When off all DMA over >4GB is forced through |
| 238 | an IOMMU or software bounce buffering. |
| 239 | nodac Forbid DAC mode, i.e. DMA >4GB. |
| 240 | panic Always panic when IOMMU overflows. |
| 241 | calgary Use the Calgary IOMMU if it is available |
| 242 | |
| 243 | iommu options only relevant to the software bounce buffering (SWIOTLB) IOMMU |
| 244 | implementation: |
| 245 | swiotlb=<pages>[,force] |
| 246 | <pages> Prereserve that many 128K pages for the software IO |
| 247 | bounce buffering. |
| 248 | force Force all IO through the software TLB. |
| 249 | |
| 250 | Settings for the IBM Calgary hardware IOMMU currently found in IBM |
| 251 | pSeries and xSeries machines: |
| 252 | |
| 253 | calgary=[64k,128k,256k,512k,1M,2M,4M,8M] |
| 254 | calgary=[translate_empty_slots] |
| 255 | calgary=[disable=<PCI bus number>] |
| 256 | panic Always panic when IOMMU overflows |
Jon Mason | e465058 | 2006-06-26 13:58:14 +0200 | [diff] [blame] | 257 | |
| 258 | 64k,...,8M - Set the size of each PCI slot's translation table |
| 259 | when using the Calgary IOMMU. This is the size of the translation |
| 260 | table itself in main memory. The smallest table, 64k, covers an IO |
| 261 | space of 32MB; the largest, 8MB table, can cover an IO space of |
| 262 | 4GB. Normally the kernel will make the right choice by itself. |
| 263 | |
| 264 | translate_empty_slots - Enable translation even on slots that have |
| 265 | no devices attached to them, in case a device will be hotplugged |
| 266 | in the future. |
| 267 | |
| 268 | disable=<PCI bus number> - Disable translation on a given PHB. For |
| 269 | example, the built-in graphics adapter resides on the first bridge |
| 270 | (PCI bus number 0); if translation (isolation) is enabled on this |
| 271 | bridge, X servers that access the hardware directly from user |
| 272 | space might stop working. Use this option if you have devices that |
| 273 | are accessed from userspace directly on some PCI host bridge. |
| 274 | |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 275 | Debugging |
| 276 | |
Randy Dunlap | 57d3077 | 2007-02-13 13:26:23 +0100 | [diff] [blame] | 277 | kstack=N Print N words from the kernel stack in oops dumps. |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 278 | |
Randy Dunlap | 57d3077 | 2007-02-13 13:26:23 +0100 | [diff] [blame] | 279 | Miscellaneous |
Ingo Molnar | 00d1c5e | 2008-04-17 17:40:45 +0200 | [diff] [blame] | 280 | |
| 281 | nogbpages |
| 282 | Do not use GB pages for kernel direct mappings. |
| 283 | gbpages |
| 284 | Use GB pages for kernel direct mappings. |