1 |
3 |
xianfeng |
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 on uncorrected errors, log corrected errors
|
18 |
|
|
1: panic or SIGBUS on uncorrected errors, log corrected errors
|
19 |
|
|
2: SIGBUS or log uncorrected errors, log corrected errors
|
20 |
|
|
3: never panic or SIGBUS, log all errors (for testing only)
|
21 |
|
|
Default is 1
|
22 |
|
|
Can be also set using sysfs which is preferable.
|
23 |
|
|
|
24 |
|
|
nomce (for compatibility with i386): same as mce=off
|
25 |
|
|
|
26 |
|
|
Everything else is in sysfs now.
|
27 |
|
|
|
28 |
|
|
APICs
|
29 |
|
|
|
30 |
|
|
apic Use IO-APIC. Default
|
31 |
|
|
|
32 |
|
|
noapic Don't use the IO-APIC.
|
33 |
|
|
|
34 |
|
|
disableapic Don't use the local APIC
|
35 |
|
|
|
36 |
|
|
nolapic Don't use the local APIC (alias for i386 compatibility)
|
37 |
|
|
|
38 |
|
|
pirq=... See Documentation/i386/IO-APIC.txt
|
39 |
|
|
|
40 |
|
|
noapictimer Don't set up the APIC timer
|
41 |
|
|
|
42 |
|
|
no_timer_check Don't check the IO-APIC timer. This can work around
|
43 |
|
|
problems with incorrect timer initialization on some boards.
|
44 |
|
|
|
45 |
|
|
apicmaintimer Run time keeping from the local APIC timer instead
|
46 |
|
|
of using the PIT/HPET interrupt for this. This is useful
|
47 |
|
|
when the PIT/HPET interrupts are unreliable.
|
48 |
|
|
|
49 |
|
|
noapicmaintimer Don't do time keeping using the APIC timer.
|
50 |
|
|
Useful when this option was auto selected, but doesn't work.
|
51 |
|
|
|
52 |
|
|
apicpmtimer
|
53 |
|
|
Do APIC timer calibration using the pmtimer. Implies
|
54 |
|
|
apicmaintimer. Useful when your PIT timer is totally
|
55 |
|
|
broken.
|
56 |
|
|
|
57 |
|
|
disable_8254_timer / enable_8254_timer
|
58 |
|
|
Enable interrupt 0 timer routing over the 8254 in addition to over
|
59 |
|
|
the IO-APIC. The kernel tries to set a sensible default.
|
60 |
|
|
|
61 |
|
|
Early Console
|
62 |
|
|
|
63 |
|
|
syntax: earlyprintk=vga
|
64 |
|
|
earlyprintk=serial[,ttySn[,baudrate]]
|
65 |
|
|
|
66 |
|
|
The early console is useful when the kernel crashes before the
|
67 |
|
|
normal console is initialized. It is not enabled by
|
68 |
|
|
default because it has some cosmetic problems.
|
69 |
|
|
Append ,keep to not disable it when the real console takes over.
|
70 |
|
|
Only vga or serial at a time, not both.
|
71 |
|
|
Currently only ttyS0 and ttyS1 are supported.
|
72 |
|
|
Interaction with the standard serial driver is not very good.
|
73 |
|
|
The VGA output is eventually overwritten by the real console.
|
74 |
|
|
|
75 |
|
|
Timing
|
76 |
|
|
|
77 |
|
|
notsc
|
78 |
|
|
Don't use the CPU time stamp counter to read the wall time.
|
79 |
|
|
This can be used to work around timing problems on multiprocessor systems
|
80 |
|
|
with not properly synchronized CPUs.
|
81 |
|
|
|
82 |
|
|
report_lost_ticks
|
83 |
|
|
Report when timer interrupts are lost because some code turned off
|
84 |
|
|
interrupts for too long.
|
85 |
|
|
|
86 |
|
|
nmi_watchdog=NUMBER[,panic]
|
87 |
|
|
NUMBER can be:
|
88 |
|
|
|
89 |
|
|
1 use the IO-APIC timer for the NMI watchdog
|
90 |
|
|
2 use the local APIC for the NMI watchdog using a performance counter. Note
|
91 |
|
|
This will use one performance counter and the local APIC's performance
|
92 |
|
|
vector.
|
93 |
|
|
When panic is specified panic when an NMI watchdog timeout occurs.
|
94 |
|
|
This is useful when you use a panic=... timeout and need the box
|
95 |
|
|
quickly up again.
|
96 |
|
|
|
97 |
|
|
nohpet
|
98 |
|
|
Don't use the HPET timer.
|
99 |
|
|
|
100 |
|
|
Idle loop
|
101 |
|
|
|
102 |
|
|
idle=poll
|
103 |
|
|
Don't do power saving in the idle loop using HLT, but poll for rescheduling
|
104 |
|
|
event. This will make the CPUs eat a lot more power, but may be useful
|
105 |
|
|
to get slightly better performance in multiprocessor benchmarks. It also
|
106 |
|
|
makes some profiling using performance counters more accurate.
|
107 |
|
|
Please note that on systems with MONITOR/MWAIT support (like Intel EM64T
|
108 |
|
|
CPUs) this option has no performance advantage over the normal idle loop.
|
109 |
|
|
It may also interact badly with hyperthreading.
|
110 |
|
|
|
111 |
|
|
Rebooting
|
112 |
|
|
|
113 |
|
|
reboot=b[ios] | t[riple] | k[bd] [, [w]arm | [c]old]
|
114 |
|
|
bios Use the CPU reboot vector for warm reset
|
115 |
|
|
warm Don't set the cold reboot flag
|
116 |
|
|
cold Set the cold reboot flag
|
117 |
|
|
triple Force a triple fault (init)
|
118 |
|
|
kbd Use the keyboard controller. cold reset (default)
|
119 |
|
|
|
120 |
|
|
Using warm reset will be much faster especially on big memory
|
121 |
|
|
systems because the BIOS will not go through the memory check.
|
122 |
|
|
Disadvantage is that not all hardware will be completely reinitialized
|
123 |
|
|
on reboot so there may be boot problems on some systems.
|
124 |
|
|
|
125 |
|
|
reboot=force
|
126 |
|
|
|
127 |
|
|
Don't stop other CPUs on reboot. This can make reboot more reliable
|
128 |
|
|
in some cases.
|
129 |
|
|
|
130 |
|
|
Non Executable Mappings
|
131 |
|
|
|
132 |
|
|
noexec=on|off
|
133 |
|
|
|
134 |
|
|
on Enable(default)
|
135 |
|
|
off Disable
|
136 |
|
|
|
137 |
|
|
SMP
|
138 |
|
|
|
139 |
|
|
additional_cpus=NUM Allow NUM more CPUs for hotplug
|
140 |
|
|
(defaults are specified by the BIOS, see Documentation/x86_64/cpu-hotplug-spec)
|
141 |
|
|
|
142 |
|
|
NUMA
|
143 |
|
|
|
144 |
|
|
numa=off Only set up a single NUMA node spanning all memory.
|
145 |
|
|
|
146 |
|
|
numa=noacpi Don't parse the SRAT table for NUMA setup
|
147 |
|
|
|
148 |
|
|
numa=fake=CMDLINE
|
149 |
|
|
If a number, fakes CMDLINE nodes and ignores NUMA setup of the
|
150 |
|
|
actual machine. Otherwise, system memory is configured
|
151 |
|
|
depending on the sizes and coefficients listed. For example:
|
152 |
|
|
numa=fake=2*512,1024,4*256,*128
|
153 |
|
|
gives two 512M nodes, a 1024M node, four 256M nodes, and the
|
154 |
|
|
rest split into 128M chunks. If the last character of CMDLINE
|
155 |
|
|
is a *, the remaining memory is divided up equally among its
|
156 |
|
|
coefficient:
|
157 |
|
|
numa=fake=2*512,2*
|
158 |
|
|
gives two 512M nodes and the rest split into two nodes.
|
159 |
|
|
Otherwise, the remaining system RAM is allocated to an
|
160 |
|
|
additional node.
|
161 |
|
|
|
162 |
|
|
numa=hotadd=percent
|
163 |
|
|
Only allow hotadd memory to preallocate page structures upto
|
164 |
|
|
percent of already available memory.
|
165 |
|
|
numa=hotadd=0 will disable hotadd memory.
|
166 |
|
|
|
167 |
|
|
ACPI
|
168 |
|
|
|
169 |
|
|
acpi=off Don't enable ACPI
|
170 |
|
|
acpi=ht Use ACPI boot table parsing, but don't enable ACPI
|
171 |
|
|
interpreter
|
172 |
|
|
acpi=force Force ACPI on (currently not needed)
|
173 |
|
|
|
174 |
|
|
acpi=strict Disable out of spec ACPI workarounds.
|
175 |
|
|
|
176 |
|
|
acpi_sci={edge,level,high,low} Set up ACPI SCI interrupt.
|
177 |
|
|
|
178 |
|
|
acpi=noirq Don't route interrupts
|
179 |
|
|
|
180 |
|
|
PCI
|
181 |
|
|
|
182 |
|
|
pci=off Don't use PCI
|
183 |
|
|
pci=conf1 Use conf1 access.
|
184 |
|
|
pci=conf2 Use conf2 access.
|
185 |
|
|
pci=rom Assign ROMs.
|
186 |
|
|
pci=assign-busses Assign busses
|
187 |
|
|
pci=irqmask=MASK Set PCI interrupt mask to MASK
|
188 |
|
|
pci=lastbus=NUMBER Scan upto NUMBER busses, no matter what the mptable says.
|
189 |
|
|
pci=noacpi Don't use ACPI to set up PCI interrupt routing.
|
190 |
|
|
|
191 |
|
|
IOMMU (input/output memory management unit)
|
192 |
|
|
|
193 |
|
|
Currently four x86-64 PCI-DMA mapping implementations exist:
|
194 |
|
|
|
195 |
|
|
1. : use no hardware/software IOMMU at all
|
196 |
|
|
(e.g. because you have < 3 GB memory).
|
197 |
|
|
Kernel boot message: "PCI-DMA: Disabling IOMMU"
|
198 |
|
|
|
199 |
|
|
2. : AMD GART based hardware IOMMU.
|
200 |
|
|
Kernel boot message: "PCI-DMA: using GART IOMMU"
|
201 |
|
|
|
202 |
|
|
3. : Software IOMMU implementation. Used
|
203 |
|
|
e.g. if there is no hardware IOMMU in the system and it is need because
|
204 |
|
|
you have >3GB memory or told the kernel to us it (iommu=soft))
|
205 |
|
|
Kernel boot message: "PCI-DMA: Using software bounce buffering
|
206 |
|
|
for IO (SWIOTLB)"
|
207 |
|
|
|
208 |
|
|
4. : IBM Calgary hardware IOMMU. Used in IBM
|
209 |
|
|
pSeries and xSeries servers. This hardware IOMMU supports DMA address
|
210 |
|
|
mapping with memory protection, etc.
|
211 |
|
|
Kernel boot message: "PCI-DMA: Using Calgary IOMMU"
|
212 |
|
|
|
213 |
|
|
iommu=[][,noagp][,off][,force][,noforce][,leak[=]
|
214 |
|
|
[,memaper[=]][,merge][,forcesac][,fullflush][,nomerge]
|
215 |
|
|
[,noaperture][,calgary]
|
216 |
|
|
|
217 |
|
|
General iommu options:
|
218 |
|
|
off Don't initialize and use any kind of IOMMU.
|
219 |
|
|
noforce Don't force hardware IOMMU usage when it is not needed.
|
220 |
|
|
(default).
|
221 |
|
|
force Force the use of the hardware IOMMU even when it is
|
222 |
|
|
not actually needed (e.g. because < 3 GB memory).
|
223 |
|
|
soft Use software bounce buffering (SWIOTLB) (default for
|
224 |
|
|
Intel machines). This can be used to prevent the usage
|
225 |
|
|
of an available hardware IOMMU.
|
226 |
|
|
|
227 |
|
|
iommu options only relevant to the AMD GART hardware IOMMU:
|
228 |
|
|
Set the size of the remapping area in bytes.
|
229 |
|
|
allowed Overwrite iommu off workarounds for specific chipsets.
|
230 |
|
|
fullflush Flush IOMMU on each allocation (default).
|
231 |
|
|
nofullflush Don't use IOMMU fullflush.
|
232 |
|
|
leak Turn on simple iommu leak tracing (only when
|
233 |
|
|
CONFIG_IOMMU_LEAK is on). Default number of leak pages
|
234 |
|
|
is 20.
|
235 |
|
|
memaper[=] Allocate an own aperture over RAM with size 32MB<
|
236 |
|
|
(default: order=1, i.e. 64MB)
|
237 |
|
|
merge Do scatter-gather (SG) merging. Implies "force"
|
238 |
|
|
(experimental).
|
239 |
|
|
nomerge Don't do scatter-gather (SG) merging.
|
240 |
|
|
noaperture Ask the IOMMU not to touch the aperture for AGP.
|
241 |
|
|
forcesac Force single-address cycle (SAC) mode for masks <40bits
|
242 |
|
|
(experimental).
|
243 |
|
|
noagp Don't initialize the AGP driver and use full aperture.
|
244 |
|
|
allowdac Allow double-address cycle (DAC) mode, i.e. DMA >4GB.
|
245 |
|
|
DAC is used with 32-bit PCI to push a 64-bit address in
|
246 |
|
|
two cycles. When off all DMA over >4GB is forced through
|
247 |
|
|
an IOMMU or software bounce buffering.
|
248 |
|
|
nodac Forbid DAC mode, i.e. DMA >4GB.
|
249 |
|
|
panic Always panic when IOMMU overflows.
|
250 |
|
|
calgary Use the Calgary IOMMU if it is available
|
251 |
|
|
|
252 |
|
|
iommu options only relevant to the software bounce buffering (SWIOTLB) IOMMU
|
253 |
|
|
implementation:
|
254 |
|
|
swiotlb=[,force]
|
255 |
|
|
Prereserve that many 128K pages for the software IO
|
256 |
|
|
bounce buffering.
|
257 |
|
|
force Force all IO through the software TLB.
|
258 |
|
|
|
259 |
|
|
Settings for the IBM Calgary hardware IOMMU currently found in IBM
|
260 |
|
|
pSeries and xSeries machines:
|
261 |
|
|
|
262 |
|
|
calgary=[64k,128k,256k,512k,1M,2M,4M,8M]
|
263 |
|
|
calgary=[translate_empty_slots]
|
264 |
|
|
calgary=[disable=]
|
265 |
|
|
panic Always panic when IOMMU overflows
|
266 |
|
|
|
267 |
|
|
64k,...,8M - Set the size of each PCI slot's translation table
|
268 |
|
|
when using the Calgary IOMMU. This is the size of the translation
|
269 |
|
|
table itself in main memory. The smallest table, 64k, covers an IO
|
270 |
|
|
space of 32MB; the largest, 8MB table, can cover an IO space of
|
271 |
|
|
4GB. Normally the kernel will make the right choice by itself.
|
272 |
|
|
|
273 |
|
|
translate_empty_slots - Enable translation even on slots that have
|
274 |
|
|
no devices attached to them, in case a device will be hotplugged
|
275 |
|
|
in the future.
|
276 |
|
|
|
277 |
|
|
disable= - Disable translation on a given PHB. For
|
278 |
|
|
example, the built-in graphics adapter resides on the first bridge
|
279 |
|
|
(PCI bus number 0); if translation (isolation) is enabled on this
|
280 |
|
|
bridge, X servers that access the hardware directly from user
|
281 |
|
|
space might stop working. Use this option if you have devices that
|
282 |
|
|
are accessed from userspace directly on some PCI host bridge.
|
283 |
|
|
|
284 |
|
|
Debugging
|
285 |
|
|
|
286 |
|
|
oops=panic Always panic on oopses. Default is to just kill the process,
|
287 |
|
|
but there is a small probability of deadlocking the machine.
|
288 |
|
|
This will also cause panics on machine check exceptions.
|
289 |
|
|
Useful together with panic=30 to trigger a reboot.
|
290 |
|
|
|
291 |
|
|
kstack=N Print N words from the kernel stack in oops dumps.
|
292 |
|
|
|
293 |
|
|
pagefaulttrace Dump all page faults. Only useful for extreme debugging
|
294 |
|
|
and will create a lot of output.
|
295 |
|
|
|
296 |
|
|
call_trace=[old|both|newfallback|new]
|
297 |
|
|
old: use old inexact backtracer
|
298 |
|
|
new: use new exact dwarf2 unwinder
|
299 |
|
|
both: print entries from both
|
300 |
|
|
newfallback: use new unwinder but fall back to old if it gets
|
301 |
|
|
stuck (default)
|
302 |
|
|
|
303 |
|
|
Miscellaneous
|