diff options
author | Linus Torvalds <torvalds@ppc970.osdl.org> | 2005-04-16 18:20:36 -0400 |
---|---|---|
committer | Linus Torvalds <torvalds@ppc970.osdl.org> | 2005-04-16 18:20:36 -0400 |
commit | 1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 (patch) | |
tree | 0bba044c4ce775e45a88a51686b5d9f90697ea9d /Documentation/x86_64/boot-options.txt |
Linux-2.6.12-rc2v2.6.12-rc2
Initial git repository build. I'm not bothering with the full history,
even though we have it. We can create a separate "historical" git
archive of that later if we want to, and in the meantime it's about
3.2GB when imported into git - space that would just make the early
git days unnecessarily complicated, when we don't have a lot of good
infrastructure for it.
Let it rip!
Diffstat (limited to 'Documentation/x86_64/boot-options.txt')
-rw-r--r-- | Documentation/x86_64/boot-options.txt | 180 |
1 files changed, 180 insertions, 0 deletions
diff --git a/Documentation/x86_64/boot-options.txt b/Documentation/x86_64/boot-options.txt new file mode 100644 index 000000000000..44b6eea60ece --- /dev/null +++ b/Documentation/x86_64/boot-options.txt | |||
@@ -0,0 +1,180 @@ | |||
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 | |||
10 | nomce (for compatibility with i386): same as mce=off | ||
11 | |||
12 | Everything else is in sysfs now. | ||
13 | |||
14 | APICs | ||
15 | |||
16 | apic Use IO-APIC. Default | ||
17 | |||
18 | noapic Don't use the IO-APIC. | ||
19 | |||
20 | disableapic Don't use the local APIC | ||
21 | |||
22 | nolapic Don't use the local APIC (alias for i386 compatibility) | ||
23 | |||
24 | pirq=... See Documentation/i386/IO-APIC.txt | ||
25 | |||
26 | noapictimer Don't set up the APIC timer | ||
27 | |||
28 | Early Console | ||
29 | |||
30 | syntax: earlyprintk=vga | ||
31 | earlyprintk=serial[,ttySn[,baudrate]] | ||
32 | |||
33 | The early console is useful when the kernel crashes before the | ||
34 | normal console is initialized. It is not enabled by | ||
35 | default because it has some cosmetic problems. | ||
36 | Append ,keep to not disable it when the real console takes over. | ||
37 | Only vga or serial at a time, not both. | ||
38 | Currently only ttyS0 and ttyS1 are supported. | ||
39 | Interaction with the standard serial driver is not very good. | ||
40 | The VGA output is eventually overwritten by the real console. | ||
41 | |||
42 | Timing | ||
43 | |||
44 | notsc | ||
45 | Don't use the CPU time stamp counter to read the wall time. | ||
46 | This can be used to work around timing problems on multiprocessor systems | ||
47 | with not properly synchronized CPUs. Only useful with a SMP kernel | ||
48 | |||
49 | report_lost_ticks | ||
50 | Report when timer interrupts are lost because some code turned off | ||
51 | interrupts for too long. | ||
52 | |||
53 | nmi_watchdog=NUMBER[,panic] | ||
54 | NUMBER can be: | ||
55 | 0 don't use an NMI watchdog | ||
56 | 1 use the IO-APIC timer for the NMI watchdog | ||
57 | 2 use the local APIC for the NMI watchdog using a performance counter. Note | ||
58 | This will use one performance counter and the local APIC's performance | ||
59 | vector. | ||
60 | When panic is specified panic when an NMI watchdog timeout occurs. | ||
61 | This is useful when you use a panic=... timeout and need the box | ||
62 | quickly up again. | ||
63 | |||
64 | nohpet | ||
65 | Don't use the HPET timer. | ||
66 | |||
67 | Idle loop | ||
68 | |||
69 | idle=poll | ||
70 | Don't do power saving in the idle loop using HLT, but poll for rescheduling | ||
71 | event. This will make the CPUs eat a lot more power, but may be useful | ||
72 | to get slightly better performance in multiprocessor benchmarks. It also | ||
73 | makes some profiling using performance counters more accurate. | ||
74 | |||
75 | Rebooting | ||
76 | |||
77 | reboot=b[ios] | t[riple] | k[bd] [, [w]arm | [c]old] | ||
78 | bios Use the CPU reboto vector for warm reset | ||
79 | warm Don't set the cold reboot flag | ||
80 | cold Set the cold reboot flag | ||
81 | triple Force a triple fault (init) | ||
82 | kbd Use the keyboard controller. cold reset (default) | ||
83 | |||
84 | Using warm reset will be much faster especially on big memory | ||
85 | systems because the BIOS will not go through the memory check. | ||
86 | Disadvantage is that not all hardware will be completely reinitialized | ||
87 | on reboot so there may be boot problems on some systems. | ||
88 | |||
89 | reboot=force | ||
90 | |||
91 | Don't stop other CPUs on reboot. This can make reboot more reliable | ||
92 | in some cases. | ||
93 | |||
94 | Non Executable Mappings | ||
95 | |||
96 | noexec=on|off | ||
97 | |||
98 | on Enable(default) | ||
99 | off Disable | ||
100 | |||
101 | SMP | ||
102 | |||
103 | nosmp Only use a single CPU | ||
104 | |||
105 | maxcpus=NUMBER only use upto NUMBER CPUs | ||
106 | |||
107 | cpumask=MASK only use cpus with bits set in mask | ||
108 | |||
109 | NUMA | ||
110 | |||
111 | numa=off Only set up a single NUMA node spanning all memory. | ||
112 | |||
113 | numa=noacpi Don't parse the SRAT table for NUMA setup | ||
114 | |||
115 | numa=fake=X Fake X nodes and ignore NUMA setup of the actual machine. | ||
116 | |||
117 | ACPI | ||
118 | |||
119 | acpi=off Don't enable ACPI | ||
120 | acpi=ht Use ACPI boot table parsing, but don't enable ACPI | ||
121 | interpreter | ||
122 | acpi=force Force ACPI on (currently not needed) | ||
123 | |||
124 | acpi=strict Disable out of spec ACPI workarounds. | ||
125 | |||
126 | acpi_sci={edge,level,high,low} Set up ACPI SCI interrupt. | ||
127 | |||
128 | acpi=noirq Don't route interrupts | ||
129 | |||
130 | PCI | ||
131 | |||
132 | pci=off Don't use PCI | ||
133 | pci=conf1 Use conf1 access. | ||
134 | pci=conf2 Use conf2 access. | ||
135 | pci=rom Assign ROMs. | ||
136 | pci=assign-busses Assign busses | ||
137 | pci=irqmask=MASK Set PCI interrupt mask to MASK | ||
138 | pci=lastbus=NUMBER Scan upto NUMBER busses, no matter what the mptable says. | ||
139 | pci=noacpi Don't use ACPI to set up PCI interrupt routing. | ||
140 | |||
141 | IOMMU | ||
142 | |||
143 | iommu=[size][,noagp][,off][,force][,noforce][,leak][,memaper[=order]][,merge] | ||
144 | [,forcesac][,fullflush][,nomerge][,noaperture] | ||
145 | size set size of iommu (in bytes) | ||
146 | noagp don't initialize the AGP driver and use full aperture. | ||
147 | off don't use the IOMMU | ||
148 | leak turn on simple iommu leak tracing (only when CONFIG_IOMMU_LEAK is on) | ||
149 | memaper[=order] allocate an own aperture over RAM with size 32MB^order. | ||
150 | noforce don't force IOMMU usage. Default. | ||
151 | force Force IOMMU. | ||
152 | merge Do SG merging. Implies force (experimental) | ||
153 | nomerge Don't do SG merging. | ||
154 | forcesac For SAC mode for masks <40bits (experimental) | ||
155 | fullflush Flush IOMMU on each allocation (default) | ||
156 | nofullflush Don't use IOMMU fullflush | ||
157 | allowed overwrite iommu off workarounds for specific chipsets. | ||
158 | soft Use software bounce buffering (default for Intel machines) | ||
159 | noaperture Don't touch the aperture for AGP. | ||
160 | |||
161 | swiotlb=pages[,force] | ||
162 | |||
163 | pages Prereserve that many 128K pages for the software IO bounce buffering. | ||
164 | force Force all IO through the software TLB. | ||
165 | |||
166 | Debugging | ||
167 | |||
168 | oops=panic Always panic on oopses. Default is to just kill the process, | ||
169 | but there is a small probability of deadlocking the machine. | ||
170 | This will also cause panics on machine check exceptions. | ||
171 | Useful together with panic=30 to trigger a reboot. | ||
172 | |||
173 | kstack=N Print that many words from the kernel stack in oops dumps. | ||
174 | |||
175 | Misc | ||
176 | |||
177 | noreplacement Don't replace instructions with more appropiate ones | ||
178 | for the CPU. This may be useful on asymmetric MP systems | ||
179 | where some CPU have less capabilities than the others. | ||
180 | |||