1 .TH lspci 8 "@TODAY@" "@VERSION@" "The PCI Utilities"
4 lspci \- list all PCI devices
10 is a utility for displaying information about PCI buses in the system and
11 devices connected to them.
13 By default, it shows a brief list of devices. Use the options described
14 below to request either a more verbose output or output intended for
15 parsing by other programs.
17 If you are going to report bugs in PCI device drivers or in
19 itself, please include output of "lspci -vvx" or even better "lspci -vvxxx"
20 (however, see below for possible caveats).
22 Some parts of the output, especially in the highly verbose modes, are probably
23 intelligible only to experienced PCI hackers. For exact definitions of
24 the fields, please consult either the PCI specifications or the
27 .B /usr/include/linux/pci.h
30 Access to some parts of the PCI configuration space is restricted to root
31 on many operating systems, so the features of
33 available to normal users are limited. However,
35 tries its best to display as much as available and mark all other
42 .SS Basic display modes
45 Dump PCI device data in a backward-compatible machine readable form.
46 See below for details.
49 Dump PCI device data in a machine readable form for easy parsing by scripts.
50 See below for details.
53 Show a tree-like diagram containing all buses, bridges, devices and connections
59 Be verbose and display detailed information about all devices.
62 Be very verbose and display more details. This level includes everything deemed
66 Be even more verbose and display everything we are able to parse,
67 even if it doesn't look interesting at all (e.g., undefined memory regions).
70 Show kernel drivers handling each device and also kernel modules capable of handling it.
71 Turned on by default when
73 is given in the normal mode of output.
74 (Currently works only on Linux with kernel 2.6 or newer.)
77 Show hexadecimal dump of the standard part of the configuration space (the first
78 64 bytes or 128 bytes for CardBus bridges).
81 Show hexadecimal dump of the whole PCI configuration space. It is available only to root
82 as several PCI devices
84 when you try to read some parts of the config space (this behavior probably
85 doesn't violate the PCI standard, but it's at least very stupid). However, such
86 devices are rare, so you needn't worry much.
89 Show hexadecimal dump of the extended (4096-byte) PCI configuration space available
90 on PCI-X 2.0 and PCI Express buses.
93 Bus-centric view. Show all IRQ numbers and addresses as seen by the cards on the
94 PCI bus instead of as seen by the kernel.
97 Always show PCI domain numbers. By default, lspci suppresses them on machines which
100 .SS Options to control resolving ID's to names
103 Show PCI vendor and device codes as numbers instead of looking them up in the
107 Show PCI vendor and device codes as both numbers and names.
110 Use DNS to query the central PCI ID database if a device is not found in the local
112 file. If the DNS query succeeds, the result is cached in
114 and it is recognized in subsequent runs even if
116 is not given any more. Please use this switch inside automated scripts only
117 with caution to avoid overloading the database servers.
122 but the local cache is reset.
125 Query the central database even for entries which are recognized locally.
126 Use this if you suspect that the displayed entry is wrong.
128 .SS Options for selection of devices
130 .B -s [[[[<domain>]:]<bus>]:][<slot>][.[<func>]]
131 Show only devices in the specified domain (in case your machine has several host bridges,
132 they can either share a common bus number space or each of them can address a PCI domain
133 of its own; domains are numbered from 0 to ffff), bus (0 to ff), slot (0 to 1f) and function (0 to 7).
134 Each component of the device address can be omitted or set to "*", both meaning "any value". All numbers are
135 hexadecimal. E.g., "0:" means all devices on bus 0, "0" means all functions of device 0
136 on any bus, "0.3" selects third function of device 0 on all buses and ".4" shows only
137 the fourth function of each device.
139 .B -d [<vendor>]:[<device>]
140 Show only devices with specified vendor and device ID. Both ID's are given in
141 hexadecimal and may be omitted or given as "*", both meaning "any value".
149 as the PCI ID list instead of @IDSDIR@/pci.ids.
155 as the map of PCI ID's handled by kernel modules. By default, lspci uses
156 .RI /lib/modules/ kernel_version /modules.pcimap.
157 Applies only to Linux systems with recent enough module tools.
160 Invoke bus mapping mode which performs a thorough scan of all PCI devices, including
161 those behind misconfigured bridges etc. This option is available only to root and it
162 gives meaningful results only if combined with direct hardware access mode (otherwise
163 the results are identical to normal listing modes, modulo bugs in lspci). Please note
164 that the bus mapper doesn't support PCI domains and scans only domain 0.
169 version. This option should be used stand-alone.
171 .SS PCI access options
173 The PCI utilities use the PCI library to talk to PCI devices (see
174 \fBpcilib\fP(7) for details). You can use the following options to
175 influence its behavior:
178 The library supports a variety of methods to access the PCI hardware.
179 By default, it uses the first access method available, but you can use
180 this option to override this decision. See \fB-A help\fP for a list of
181 available methods and their descriptions.
183 .B -O <param>=<value>
184 The behavior of the library is controlled by several named parameters.
185 This option allows to set the value of any of the parameters. Use \fB-O help\fP
186 for a list of known parameters and their default values.
189 Use direct hardware access via Intel configuration mechanism 1.
190 (This is a shorthand for \fB-A intel-conf1\fP.)
193 Use direct hardware access via Intel configuration mechanism 2.
194 (This is a shorthand for \fB-A intel-conf2\fP.)
197 Instead of accessing real hardware, read the list of devices and values of their
198 configuration registers from the given file produced by an earlier run of lspci -x.
199 This is very useful for analysis of user-supplied bug reports, because you can display
200 the hardware configuration in any way you want without disturbing the user with
201 requests for more dumps.
204 Increase debug level of the library.
206 .SH MACHINE READABLE OUTPUT
207 If you intend to process the output of lspci automatically, please use one of the
208 machine-readable output formats
212 described in this section. All other formats are likely to change
213 between versions of lspci.
216 All numbers are always printed in hexadecimal. If you want to process numeric ID's instead of
217 names, please add the
221 .SS Simple format (-m)
223 In the simple format, each device is described on a single line, which is
224 formatted as parameters suitable for passing to a shell script, i.e., values
225 separated by whitespaces, quoted and escaped if necessary.
226 Some of the arguments are positional: slot, class, vendor name, device name,
227 subsystem vendor name and subsystem name (the last two are empty if
228 the device has no subsystem); the remaining arguments are option-like:
236 Programming interface.
239 The relative order of positional arguments and options is undefined.
240 New options can be added in future versions, but they will always
241 have a single argument not separated from the option by any spaces,
242 so they can be easily ignored if not recognized.
244 .SS Verbose format (-vmm)
246 The verbose output is a sequence of records separated by blank lines.
247 Each record describes a single device by a sequence of lines, each line
255 are separated by a single tab character.
256 Neither the records nor the lines within a record are in any particular order.
257 Tags are case-sensitive.
260 The following tags are defined:
264 The name of the slot where the device resides
265 .RI ([ domain :] bus : device . function ).
266 This tag is always the first in a record.
282 Name of the subsystem vendor (optional).
286 Name of the subsystem (optional).
290 The physical slot where the device resides (optional, Linux only).
294 Revision number (optional).
298 Programming interface (optional).
302 Kernel driver currently handling the device (optional, Linux only).
306 Kernel module reporting that it is capable of handling the device
307 (optional, Linux only).
310 New tags can be added in future versions, so you should silently ignore any tags you don't recognize.
312 .SS Backward-compatible verbose format (-vm)
314 In this mode, lspci tries to be perfectly compatible with its old versions.
315 It's almost the same as the regular verbose format, but the
318 tag is used for both the slot and the device name, so it occurs twice
319 in a single record. Please avoid using this format in any new code.
324 A list of all known PCI ID's (vendors, devices, classes and subclasses). Maintained
325 at http://pciids.sourceforge.net/, use the
327 utility to download the most recent version.
329 .B @IDSDIR@/pci.ids.gz
330 If lspci is compiled with support for compression, this file is tried before pci.ids.
333 All ID's found in the DNS query mode are cached in this file.
337 Sometimes, lspci is not able to decode the configuration registers completely.
338 This usually happens when not enough documentation was available to the authors.
339 In such cases, it at least prints the
341 mark to signal that there is potentially something more to say. If you know
342 the details, patches will be of course welcome.
344 Access to the extended configuration space is currently supported only by the
350 .BR update-pciids (8),
354 The PCI Utilities are maintained by Martin Mares <mj@ucw.cz>.