spelling: s/appropiate/appropriate/
[deliverable/linux.git] / Documentation / x86_64 / boot-options.txt
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
8 mce=off disable machine check
9 mce=bootlog Enable logging of machine checks left over from booting.
10 Disabled by default on AMD because some BIOS leave bogus ones.
11 If your BIOS doesn't do that it's a good idea to enable though
12 to make sure you log even machine check events that result
13 in a reboot. On Intel systems it is enabled by default.
14 mce=nobootlog
15 Disable boot machine check logging.
16 mce=tolerancelevel (number)
17 0: always panic, 1: panic if deadlock possible,
18 2: try to avoid panic, 3: never panic or exit (for testing)
19 default is 1
20 Can be also set using sysfs which is preferable.
21
22 nomce (for compatibility with i386): same as mce=off
23
24 Everything else is in sysfs now.
25
26 APICs
27
28 apic Use IO-APIC. Default
29
30 noapic Don't use the IO-APIC.
31
32 disableapic Don't use the local APIC
33
34 nolapic Don't use the local APIC (alias for i386 compatibility)
35
36 pirq=... See Documentation/i386/IO-APIC.txt
37
38 noapictimer Don't set up the APIC timer
39
40 no_timer_check Don't check the IO-APIC timer. This can work around
41 problems with incorrect timer initialization on some boards.
42
43 Early Console
44
45 syntax: earlyprintk=vga
46 earlyprintk=serial[,ttySn[,baudrate]]
47
48 The early console is useful when the kernel crashes before the
49 normal console is initialized. It is not enabled by
50 default because it has some cosmetic problems.
51 Append ,keep to not disable it when the real console takes over.
52 Only vga or serial at a time, not both.
53 Currently only ttyS0 and ttyS1 are supported.
54 Interaction with the standard serial driver is not very good.
55 The VGA output is eventually overwritten by the real console.
56
57 Timing
58
59 notsc
60 Don't use the CPU time stamp counter to read the wall time.
61 This can be used to work around timing problems on multiprocessor systems
62 with not properly synchronized CPUs.
63
64 report_lost_ticks
65 Report when timer interrupts are lost because some code turned off
66 interrupts for too long.
67
68 nmi_watchdog=NUMBER[,panic]
69 NUMBER can be:
70 0 don't use an NMI watchdog
71 1 use the IO-APIC timer for the NMI watchdog
72 2 use the local APIC for the NMI watchdog using a performance counter. Note
73 This will use one performance counter and the local APIC's performance
74 vector.
75 When panic is specified panic when an NMI watchdog timeout occurs.
76 This is useful when you use a panic=... timeout and need the box
77 quickly up again.
78
79 nohpet
80 Don't use the HPET timer.
81
82 Idle loop
83
84 idle=poll
85 Don't do power saving in the idle loop using HLT, but poll for rescheduling
86 event. This will make the CPUs eat a lot more power, but may be useful
87 to get slightly better performance in multiprocessor benchmarks. It also
88 makes some profiling using performance counters more accurate.
89 Please note that on systems with MONITOR/MWAIT support (like Intel EM64T
90 CPUs) this option has no performance advantage over the normal idle loop.
91 It may also interact badly with hyperthreading.
92
93 Rebooting
94
95 reboot=b[ios] | t[riple] | k[bd] [, [w]arm | [c]old]
96 bios Use the CPU reboto vector for warm reset
97 warm Don't set the cold reboot flag
98 cold Set the cold reboot flag
99 triple Force a triple fault (init)
100 kbd Use the keyboard controller. cold reset (default)
101
102 Using warm reset will be much faster especially on big memory
103 systems because the BIOS will not go through the memory check.
104 Disadvantage is that not all hardware will be completely reinitialized
105 on reboot so there may be boot problems on some systems.
106
107 reboot=force
108
109 Don't stop other CPUs on reboot. This can make reboot more reliable
110 in some cases.
111
112 Non Executable Mappings
113
114 noexec=on|off
115
116 on Enable(default)
117 off Disable
118
119 SMP
120
121 nosmp Only use a single CPU
122
123 maxcpus=NUMBER only use upto NUMBER CPUs
124
125 cpumask=MASK only use cpus with bits set in mask
126
127 additional_cpus=NUM Allow NUM more CPUs for hotplug
128 (defaults are specified by the BIOS, see Documentation/x86_64/cpu-hotplug-spec)
129
130 NUMA
131
132 numa=off Only set up a single NUMA node spanning all memory.
133
134 numa=noacpi Don't parse the SRAT table for NUMA setup
135
136 numa=fake=X Fake X nodes and ignore NUMA setup of the actual machine.
137
138 ACPI
139
140 acpi=off Don't enable ACPI
141 acpi=ht Use ACPI boot table parsing, but don't enable ACPI
142 interpreter
143 acpi=force Force ACPI on (currently not needed)
144
145 acpi=strict Disable out of spec ACPI workarounds.
146
147 acpi_sci={edge,level,high,low} Set up ACPI SCI interrupt.
148
149 acpi=noirq Don't route interrupts
150
151 PCI
152
153 pci=off Don't use PCI
154 pci=conf1 Use conf1 access.
155 pci=conf2 Use conf2 access.
156 pci=rom Assign ROMs.
157 pci=assign-busses Assign busses
158 pci=irqmask=MASK Set PCI interrupt mask to MASK
159 pci=lastbus=NUMBER Scan upto NUMBER busses, no matter what the mptable says.
160 pci=noacpi Don't use ACPI to set up PCI interrupt routing.
161
162 IOMMU
163
164 iommu=[size][,noagp][,off][,force][,noforce][,leak][,memaper[=order]][,merge]
165 [,forcesac][,fullflush][,nomerge][,noaperture]
166 size set size of iommu (in bytes)
167 noagp don't initialize the AGP driver and use full aperture.
168 off don't use the IOMMU
169 leak turn on simple iommu leak tracing (only when CONFIG_IOMMU_LEAK is on)
170 memaper[=order] allocate an own aperture over RAM with size 32MB^order.
171 noforce don't force IOMMU usage. Default.
172 force Force IOMMU.
173 merge Do SG merging. Implies force (experimental)
174 nomerge Don't do SG merging.
175 forcesac For SAC mode for masks <40bits (experimental)
176 fullflush Flush IOMMU on each allocation (default)
177 nofullflush Don't use IOMMU fullflush
178 allowed overwrite iommu off workarounds for specific chipsets.
179 soft Use software bounce buffering (default for Intel machines)
180 noaperture Don't touch the aperture for AGP.
181
182 swiotlb=pages[,force]
183
184 pages Prereserve that many 128K pages for the software IO bounce buffering.
185 force Force all IO through the software TLB.
186
187 Debugging
188
189 oops=panic Always panic on oopses. Default is to just kill the process,
190 but there is a small probability of deadlocking the machine.
191 This will also cause panics on machine check exceptions.
192 Useful together with panic=30 to trigger a reboot.
193
194 kstack=N Print that many words from the kernel stack in oops dumps.
195
196 pagefaulttrace Dump all page faults. Only useful for extreme debugging
197 and will create a lot of output.
198
199 Misc
200
201 noreplacement Don't replace instructions with more appropriate ones
202 for the CPU. This may be useful on asymmetric MP systems
203 where some CPU have less capabilities than the others.
This page took 0.034962 seconds and 5 git commands to generate.