1 What: /sys/bus/pci/drivers/.../bind 1 What: /sys/bus/pci/drivers/.../bind
2 What: /sys/devices/pciX/.../bind <<
3 Date: December 2003 2 Date: December 2003
4 Contact: linux-pci@vger.kernel.org 3 Contact: linux-pci@vger.kernel.org
5 Description: 4 Description:
6 Writing a device location to t 5 Writing a device location to this file will cause
7 the driver to attempt to bind 6 the driver to attempt to bind to the device found at
8 this location. This is useful 7 this location. This is useful for overriding default
9 bindings. The format for the 8 bindings. The format for the location is: DDDD:BB:DD.F.
10 That is Domain:Bus:Device.Func 9 That is Domain:Bus:Device.Function and is the same as
11 found in /sys/bus/pci/devices/ 10 found in /sys/bus/pci/devices/. For example::
12 11
13 # echo 0000:00:19.0 > /sys/b 12 # echo 0000:00:19.0 > /sys/bus/pci/drivers/foo/bind
14 13
15 (Note: kernels before 2.6.28 m 14 (Note: kernels before 2.6.28 may require echo -n).
16 15
17 What: /sys/bus/pci/drivers/.../unbin 16 What: /sys/bus/pci/drivers/.../unbind
18 What: /sys/devices/pciX/.../unbind <<
19 Date: December 2003 17 Date: December 2003
20 Contact: linux-pci@vger.kernel.org 18 Contact: linux-pci@vger.kernel.org
21 Description: 19 Description:
22 Writing a device location to t 20 Writing a device location to this file will cause the
23 driver to attempt to unbind fr 21 driver to attempt to unbind from the device found at
24 this location. This may be us 22 this location. This may be useful when overriding default
25 bindings. The format for the 23 bindings. The format for the location is: DDDD:BB:DD.F.
26 That is Domain:Bus:Device.Func 24 That is Domain:Bus:Device.Function and is the same as
27 found in /sys/bus/pci/devices/ 25 found in /sys/bus/pci/devices/. For example::
28 26
29 # echo 0000:00:19.0 > /sys/b 27 # echo 0000:00:19.0 > /sys/bus/pci/drivers/foo/unbind
30 28
31 (Note: kernels before 2.6.28 m 29 (Note: kernels before 2.6.28 may require echo -n).
32 30
33 What: /sys/bus/pci/drivers/.../new_i 31 What: /sys/bus/pci/drivers/.../new_id
34 What: /sys/devices/pciX/.../new_id <<
35 Date: December 2003 32 Date: December 2003
36 Contact: linux-pci@vger.kernel.org 33 Contact: linux-pci@vger.kernel.org
37 Description: 34 Description:
38 Writing a device ID to this fi 35 Writing a device ID to this file will attempt to
39 dynamically add a new device I 36 dynamically add a new device ID to a PCI device driver.
40 This may allow the driver to s 37 This may allow the driver to support more hardware than
41 was included in the driver's s 38 was included in the driver's static device ID support
42 table at compile time. The fo 39 table at compile time. The format for the device ID is:
43 VVVV DDDD SVVV SDDD CCCC MMMM 40 VVVV DDDD SVVV SDDD CCCC MMMM PPPP. That is Vendor ID,
44 Device ID, Subsystem Vendor ID 41 Device ID, Subsystem Vendor ID, Subsystem Device ID,
45 Class, Class Mask, and Private 42 Class, Class Mask, and Private Driver Data. The Vendor ID
46 and Device ID fields are requi 43 and Device ID fields are required, the rest are optional.
47 Upon successfully adding an ID 44 Upon successfully adding an ID, the driver will probe
48 for the device and attempt to 45 for the device and attempt to bind to it. For example::
49 46
50 # echo "8086 10f5" > /sys/bu 47 # echo "8086 10f5" > /sys/bus/pci/drivers/foo/new_id
51 48
52 What: /sys/bus/pci/drivers/.../remov 49 What: /sys/bus/pci/drivers/.../remove_id
53 What: /sys/devices/pciX/.../remove_i <<
54 Date: February 2009 50 Date: February 2009
55 Contact: Chris Wright <chrisw@sous-sol.o 51 Contact: Chris Wright <chrisw@sous-sol.org>
56 Description: 52 Description:
57 Writing a device ID to this fi 53 Writing a device ID to this file will remove an ID
58 that was dynamically added via 54 that was dynamically added via the new_id sysfs entry.
59 The format for the device ID i 55 The format for the device ID is:
60 VVVV DDDD SVVV SDDD CCCC MMMM. 56 VVVV DDDD SVVV SDDD CCCC MMMM. That is Vendor ID, Device
61 ID, Subsystem Vendor ID, Subsy 57 ID, Subsystem Vendor ID, Subsystem Device ID, Class,
62 and Class Mask. The Vendor ID 58 and Class Mask. The Vendor ID and Device ID fields are
63 required, the rest are optiona 59 required, the rest are optional. After successfully
64 removing an ID, the driver wil 60 removing an ID, the driver will no longer support the
65 device. This is useful to ens 61 device. This is useful to ensure auto probing won't
66 match the driver to the device 62 match the driver to the device. For example::
67 63
68 # echo "8086 10f5" > /sys/bu 64 # echo "8086 10f5" > /sys/bus/pci/drivers/foo/remove_id
69 65
70 What: /sys/bus/pci/rescan 66 What: /sys/bus/pci/rescan
71 Date: January 2009 67 Date: January 2009
72 Contact: Linux PCI developers <linux-pci 68 Contact: Linux PCI developers <linux-pci@vger.kernel.org>
73 Description: 69 Description:
74 Writing a non-zero value to th 70 Writing a non-zero value to this attribute will
75 force a rescan of all PCI buse 71 force a rescan of all PCI buses in the system, and
76 re-discover previously removed 72 re-discover previously removed devices.
77 73
78 What: /sys/bus/pci/devices/.../msi_b 74 What: /sys/bus/pci/devices/.../msi_bus
79 Date: September 2014 75 Date: September 2014
80 Contact: Linux PCI developers <linux-pci 76 Contact: Linux PCI developers <linux-pci@vger.kernel.org>
81 Description: 77 Description:
82 Writing a zero value to this a 78 Writing a zero value to this attribute disallows MSI and
83 MSI-X for any future drivers o 79 MSI-X for any future drivers of the device. If the device
84 is a bridge, MSI and MSI-X wil 80 is a bridge, MSI and MSI-X will be disallowed for future
85 drivers of all child devices u 81 drivers of all child devices under the bridge. Drivers
86 must be reloaded for the new s 82 must be reloaded for the new setting to take effect.
87 83
88 What: /sys/bus/pci/devices/.../msi_i 84 What: /sys/bus/pci/devices/.../msi_irqs/
89 Date: September, 2011 85 Date: September, 2011
90 Contact: Neil Horman <nhorman@tuxdriver. 86 Contact: Neil Horman <nhorman@tuxdriver.com>
91 Description: 87 Description:
92 The /sys/devices/.../msi_irqs 88 The /sys/devices/.../msi_irqs directory contains a variable set
93 of files, with each file being 89 of files, with each file being named after a corresponding msi
94 irq vector allocated to that d 90 irq vector allocated to that device.
95 91
96 What: /sys/bus/pci/devices/.../msi_i 92 What: /sys/bus/pci/devices/.../msi_irqs/<N>
97 Date: September 2011 93 Date: September 2011
98 Contact: Neil Horman <nhorman@tuxdriver. 94 Contact: Neil Horman <nhorman@tuxdriver.com>
99 Description: 95 Description:
100 This attribute indicates the m 96 This attribute indicates the mode that the irq vector named by
101 the file is in (msi vs. msix) 97 the file is in (msi vs. msix)
102 98
103 What: /sys/bus/pci/devices/.../irq <<
104 Date: August 2021 <<
105 Contact: Linux PCI developers <linux-pci <<
106 Description: <<
107 If a driver has enabled MSI (n <<
108 IRQ of the first MSI vector. O <<
109 IRQ of the legacy INTx interru <<
110 <<
111 "irq" being set to 0 indicates <<
112 capable of generating legacy I <<
113 <<
114 What: /sys/bus/pci/devices/.../remov 99 What: /sys/bus/pci/devices/.../remove
115 Date: January 2009 100 Date: January 2009
116 Contact: Linux PCI developers <linux-pci 101 Contact: Linux PCI developers <linux-pci@vger.kernel.org>
117 Description: 102 Description:
118 Writing a non-zero value to th 103 Writing a non-zero value to this attribute will
119 hot-remove the PCI device and 104 hot-remove the PCI device and any of its children.
120 105
121 What: /sys/bus/pci/devices/.../pci_b 106 What: /sys/bus/pci/devices/.../pci_bus/.../rescan
122 Date: May 2011 107 Date: May 2011
123 Contact: Linux PCI developers <linux-pci 108 Contact: Linux PCI developers <linux-pci@vger.kernel.org>
124 Description: 109 Description:
125 Writing a non-zero value to th 110 Writing a non-zero value to this attribute will
126 force a rescan of the bus and 111 force a rescan of the bus and all child buses,
127 and re-discover devices remove 112 and re-discover devices removed earlier from this
128 part of the device tree. 113 part of the device tree.
129 114
130 What: /sys/bus/pci/devices/.../resca 115 What: /sys/bus/pci/devices/.../rescan
131 Date: January 2009 116 Date: January 2009
132 Contact: Linux PCI developers <linux-pci 117 Contact: Linux PCI developers <linux-pci@vger.kernel.org>
133 Description: 118 Description:
134 Writing a non-zero value to th 119 Writing a non-zero value to this attribute will
135 force a rescan of the device's 120 force a rescan of the device's parent bus and all
136 child buses, and re-discover d 121 child buses, and re-discover devices removed earlier
137 from this part of the device t 122 from this part of the device tree.
138 123
139 What: /sys/bus/pci/devices/.../reset 124 What: /sys/bus/pci/devices/.../reset_method
140 Date: August 2021 125 Date: August 2021
141 Contact: Amey Narkhede <ameynarkhede03@g 126 Contact: Amey Narkhede <ameynarkhede03@gmail.com>
142 Description: 127 Description:
143 Some devices allow an individu 128 Some devices allow an individual function to be reset
144 without affecting other functi 129 without affecting other functions in the same slot.
145 130
146 For devices that have this sup 131 For devices that have this support, a file named
147 reset_method is present in sys 132 reset_method is present in sysfs. Reading this file
148 gives names of the supported a 133 gives names of the supported and enabled reset methods and
149 their ordering. Writing a spa 134 their ordering. Writing a space-separated list of names of
150 reset methods sets the reset m 135 reset methods sets the reset methods and ordering to be
151 used when resetting the device 136 used when resetting the device. Writing an empty string
152 disables the ability to reset 137 disables the ability to reset the device. Writing
153 "default" enables all supporte 138 "default" enables all supported reset methods in the
154 default ordering. 139 default ordering.
155 140
156 What: /sys/bus/pci/devices/.../reset 141 What: /sys/bus/pci/devices/.../reset
157 Date: July 2009 142 Date: July 2009
158 Contact: Michael S. Tsirkin <mst@redhat. 143 Contact: Michael S. Tsirkin <mst@redhat.com>
159 Description: 144 Description:
160 Some devices allow an individu 145 Some devices allow an individual function to be reset
161 without affecting other functi 146 without affecting other functions in the same device.
162 For devices that have this sup 147 For devices that have this support, a file named reset
163 will be present in sysfs. Wri 148 will be present in sysfs. Writing 1 to this file
164 will perform reset. 149 will perform reset.
165 150
166 What: /sys/bus/pci/devices/.../vpd 151 What: /sys/bus/pci/devices/.../vpd
167 Date: February 2008 152 Date: February 2008
168 Contact: Ben Hutchings <bwh@kernel.org> 153 Contact: Ben Hutchings <bwh@kernel.org>
169 Description: 154 Description:
170 A file named vpd in a device d 155 A file named vpd in a device directory will be a
171 binary file containing the Vit 156 binary file containing the Vital Product Data for the
172 device. It should follow the 157 device. It should follow the VPD format defined in
173 PCI Specification 2.1 or 2.2, 158 PCI Specification 2.1 or 2.2, but users should consider
174 that some devices may have inc 159 that some devices may have incorrectly formatted data.
175 If the underlying VPD has a wr 160 If the underlying VPD has a writable section then the
176 corresponding section of this 161 corresponding section of this file will be writable.
177 162
178 What: /sys/bus/pci/devices/.../virtf !! 163 What: /sys/bus/pci/devices/.../virtfnN
179 Date: March 2009 164 Date: March 2009
180 Contact: Yu Zhao <yu.zhao@intel.com> 165 Contact: Yu Zhao <yu.zhao@intel.com>
181 Description: 166 Description:
182 This symbolic link appears whe 167 This symbolic link appears when hardware supports the SR-IOV
183 capability and the Physical Fu 168 capability and the Physical Function driver has enabled it.
184 The symbolic link points to th 169 The symbolic link points to the PCI device sysfs entry of the
185 Virtual Function whose index i 170 Virtual Function whose index is N (0...MaxVFs-1).
186 171
187 What: /sys/bus/pci/devices/.../dep_l 172 What: /sys/bus/pci/devices/.../dep_link
188 Date: March 2009 173 Date: March 2009
189 Contact: Yu Zhao <yu.zhao@intel.com> 174 Contact: Yu Zhao <yu.zhao@intel.com>
190 Description: 175 Description:
191 This symbolic link appears whe 176 This symbolic link appears when hardware supports the SR-IOV
192 capability and the Physical Fu 177 capability and the Physical Function driver has enabled it,
193 and this device has vendor spe 178 and this device has vendor specific dependencies with others.
194 The symbolic link points to th 179 The symbolic link points to the PCI device sysfs entry of
195 Physical Function this device 180 Physical Function this device depends on.
196 181
197 What: /sys/bus/pci/devices/.../physf 182 What: /sys/bus/pci/devices/.../physfn
198 Date: March 2009 183 Date: March 2009
199 Contact: Yu Zhao <yu.zhao@intel.com> 184 Contact: Yu Zhao <yu.zhao@intel.com>
200 Description: 185 Description:
201 This symbolic link appears whe 186 This symbolic link appears when a device is a Virtual Function.
202 The symbolic link points to th 187 The symbolic link points to the PCI device sysfs entry of the
203 Physical Function this device 188 Physical Function this device associates with.
204 189
205 What: /sys/bus/pci/devices/.../modal <<
206 Date: May 2005 <<
207 Contact: Greg Kroah-Hartman <gregkh@linu <<
208 Description: <<
209 This attribute indicates the P <<
210 <<
211 That is in the format: <<
212 pci:vXXXXXXXXdXXXXXXXXsvXXXXXX <<
213 where: <<
214 <<
215 - vXXXXXXXX contains the v <<
216 - dXXXXXXXX contains the d <<
217 - svXXXXXXXX contains the <<
218 - sdXXXXXXXX contains the <<
219 - bcXX contains the device <<
220 - scXX contains the device <<
221 - iXX contains the device <<
222 <<
223 What: /sys/bus/pci/slots/.../module 190 What: /sys/bus/pci/slots/.../module
224 Date: June 2009 191 Date: June 2009
225 Contact: linux-pci@vger.kernel.org 192 Contact: linux-pci@vger.kernel.org
226 Description: 193 Description:
227 This symbolic link points to t 194 This symbolic link points to the PCI hotplug controller driver
228 module that manages the hotplu 195 module that manages the hotplug slot.
229 196
230 What: /sys/bus/pci/devices/.../label 197 What: /sys/bus/pci/devices/.../label
231 Date: July 2010 198 Date: July 2010
232 Contact: Narendra K <narendra_k@dell.com 199 Contact: Narendra K <narendra_k@dell.com>, linux-bugs@dell.com
233 Description: 200 Description:
234 Reading this attribute will pr 201 Reading this attribute will provide the firmware
235 given name (SMBIOS type 41 str 202 given name (SMBIOS type 41 string or ACPI _DSM string) of
236 the PCI device. The attribute 203 the PCI device. The attribute will be created only
237 if the firmware has given a na 204 if the firmware has given a name to the PCI device.
238 ACPI _DSM string name will be 205 ACPI _DSM string name will be given priority if the
239 system firmware provides SMBIO 206 system firmware provides SMBIOS type 41 string also.
240 Users: 207 Users:
241 Userspace applications interes 208 Userspace applications interested in knowing the
242 firmware assigned name of the 209 firmware assigned name of the PCI device.
243 210
244 What: /sys/bus/pci/devices/.../index 211 What: /sys/bus/pci/devices/.../index
245 Date: July 2010 212 Date: July 2010
246 Contact: Narendra K <narendra_k@dell.com 213 Contact: Narendra K <narendra_k@dell.com>, linux-bugs@dell.com
247 Description: 214 Description:
248 Reading this attribute will pr 215 Reading this attribute will provide the firmware given instance
249 number of the PCI device. Dep 216 number of the PCI device. Depending on the platform this can
250 be for example the SMBIOS type 217 be for example the SMBIOS type 41 device type instance or the
251 user-defined ID (UID) on s390. 218 user-defined ID (UID) on s390. The attribute will be created
252 only if the firmware has given 219 only if the firmware has given an instance number to the PCI
253 device and that number is guar 220 device and that number is guaranteed to uniquely identify the
254 device in the system. 221 device in the system.
255 Users: 222 Users:
256 Userspace applications interes 223 Userspace applications interested in knowing the
257 firmware assigned device type 224 firmware assigned device type instance of the PCI
258 device that can help in unders 225 device that can help in understanding the firmware
259 intended order of the PCI devi 226 intended order of the PCI device.
260 227
261 What: /sys/bus/pci/devices/.../acpi_ 228 What: /sys/bus/pci/devices/.../acpi_index
262 Date: July 2010 229 Date: July 2010
263 Contact: Narendra K <narendra_k@dell.com 230 Contact: Narendra K <narendra_k@dell.com>, linux-bugs@dell.com
264 Description: 231 Description:
265 Reading this attribute will pr 232 Reading this attribute will provide the firmware
266 given instance (ACPI _DSM inst 233 given instance (ACPI _DSM instance number) of the PCI device.
267 The attribute will be created 234 The attribute will be created only if the firmware has given
268 an instance number to the PCI 235 an instance number to the PCI device. ACPI _DSM instance number
269 will be given priority if the 236 will be given priority if the system firmware provides SMBIOS
270 type 41 device type instance a 237 type 41 device type instance also.
271 Users: 238 Users:
272 Userspace applications interes 239 Userspace applications interested in knowing the
273 firmware assigned instance num 240 firmware assigned instance number of the PCI
274 device that can help in unders 241 device that can help in understanding the firmware
275 intended order of the PCI devi 242 intended order of the PCI device.
276 243
277 What: /sys/bus/pci/devices/.../d3col 244 What: /sys/bus/pci/devices/.../d3cold_allowed
278 Date: July 2012 245 Date: July 2012
279 Contact: Huang Ying <ying.huang@intel.co 246 Contact: Huang Ying <ying.huang@intel.com>
280 Description: 247 Description:
281 d3cold_allowed is bit to contr 248 d3cold_allowed is bit to control whether the corresponding PCI
282 device can be put into D3Cold 249 device can be put into D3Cold state. If it is cleared, the
283 device will never be put into 250 device will never be put into D3Cold state. If it is set, the
284 device may be put into D3Cold 251 device may be put into D3Cold state if other requirements are
285 satisfied too. Reading this a 252 satisfied too. Reading this attribute will show the current
286 value of d3cold_allowed bit. 253 value of d3cold_allowed bit. Writing this attribute will set
287 the value of d3cold_allowed bi 254 the value of d3cold_allowed bit.
288 255
289 What: /sys/bus/pci/devices/.../sriov 256 What: /sys/bus/pci/devices/.../sriov_totalvfs
290 Date: November 2012 257 Date: November 2012
291 Contact: Donald Dutile <ddutile@redhat.c 258 Contact: Donald Dutile <ddutile@redhat.com>
292 Description: 259 Description:
293 This file appears when a physi 260 This file appears when a physical PCIe device supports SR-IOV.
294 Userspace applications can rea 261 Userspace applications can read this file to determine the
295 maximum number of Virtual Func 262 maximum number of Virtual Functions (VFs) a PCIe physical
296 function (PF) can support. Typ 263 function (PF) can support. Typically, this is the value reported
297 in the PF's SR-IOV extended ca 264 in the PF's SR-IOV extended capability structure's TotalVFs
298 element. Drivers have the abi 265 element. Drivers have the ability at probe time to reduce the
299 value read from this file via 266 value read from this file via the pci_sriov_set_totalvfs()
300 function. 267 function.
301 268
302 What: /sys/bus/pci/devices/.../sriov 269 What: /sys/bus/pci/devices/.../sriov_numvfs
303 Date: November 2012 270 Date: November 2012
304 Contact: Donald Dutile <ddutile@redhat.c 271 Contact: Donald Dutile <ddutile@redhat.com>
305 Description: 272 Description:
306 This file appears when a physi 273 This file appears when a physical PCIe device supports SR-IOV.
307 Userspace applications can rea 274 Userspace applications can read and write to this file to
308 determine and control the enab 275 determine and control the enablement or disablement of Virtual
309 Functions (VFs) on the physica 276 Functions (VFs) on the physical function (PF). A read of this
310 file will return the number of 277 file will return the number of VFs that are enabled on this PF.
311 A number written to this file 278 A number written to this file will enable the specified
312 number of VFs. A userspace app 279 number of VFs. A userspace application would typically read the
313 file and check that the value 280 file and check that the value is zero, and then write the number
314 of VFs that should be enabled 281 of VFs that should be enabled on the PF; the value written
315 should be less than or equal t 282 should be less than or equal to the value in the sriov_totalvfs
316 file. A userspace application 283 file. A userspace application wanting to disable the VFs would
317 write a zero to this file. The 284 write a zero to this file. The core ensures that valid values
318 are written to this file, and 285 are written to this file, and returns errors when values are not
319 valid. For example, writing a 286 valid. For example, writing a 2 to this file when sriov_numvfs
320 is not 0 and not 2 already wil 287 is not 0 and not 2 already will return an error. Writing a 10
321 when the value of sriov_totalv 288 when the value of sriov_totalvfs is 8 will return an error.
322 289
323 What: /sys/bus/pci/devices/.../drive 290 What: /sys/bus/pci/devices/.../driver_override
324 Date: April 2014 291 Date: April 2014
325 Contact: Alex Williamson <alex.williamso 292 Contact: Alex Williamson <alex.williamson@redhat.com>
326 Description: 293 Description:
327 This file allows the driver fo 294 This file allows the driver for a device to be specified which
328 will override standard static 295 will override standard static and dynamic ID matching. When
329 specified, only a driver with 296 specified, only a driver with a name matching the value written
330 to driver_override will have a 297 to driver_override will have an opportunity to bind to the
331 device. The override is speci 298 device. The override is specified by writing a string to the
332 driver_override file (echo pci 299 driver_override file (echo pci-stub > driver_override) and
333 may be cleared with an empty s 300 may be cleared with an empty string (echo > driver_override).
334 This returns the device to sta 301 This returns the device to standard matching rules binding.
335 Writing to driver_override doe 302 Writing to driver_override does not automatically unbind the
336 device from its current driver 303 device from its current driver or make any attempt to
337 automatically load the specifi 304 automatically load the specified driver. If no driver with a
338 matching name is currently loa 305 matching name is currently loaded in the kernel, the device
339 will not bind to any driver. 306 will not bind to any driver. This also allows devices to
340 opt-out of driver binding usin 307 opt-out of driver binding using a driver_override name such as
341 "none". Only a single driver 308 "none". Only a single driver may be specified in the override,
342 there is no support for parsin 309 there is no support for parsing delimiters.
343 310
344 What: /sys/bus/pci/devices/.../numa_ 311 What: /sys/bus/pci/devices/.../numa_node
345 Date: Oct 2014 312 Date: Oct 2014
346 Contact: Prarit Bhargava <prarit@redhat. 313 Contact: Prarit Bhargava <prarit@redhat.com>
347 Description: 314 Description:
348 This file contains the NUMA no 315 This file contains the NUMA node to which the PCI device is
349 attached, or -1 if the node is 316 attached, or -1 if the node is unknown. The initial value
350 comes from an ACPI _PXM method 317 comes from an ACPI _PXM method or a similar firmware
351 source. If that is missing or 318 source. If that is missing or incorrect, this file can be
352 written to override the node. 319 written to override the node. In that case, please report
353 a firmware bug to the system v 320 a firmware bug to the system vendor. Writing to this file
354 taints the kernel with TAINT_F 321 taints the kernel with TAINT_FIRMWARE_WORKAROUND, which
355 reduces the supportability of 322 reduces the supportability of your system.
356 323
357 What: /sys/bus/pci/devices/.../revis 324 What: /sys/bus/pci/devices/.../revision
358 Date: November 2016 325 Date: November 2016
359 Contact: Emil Velikov <emil.l.velikov@gm 326 Contact: Emil Velikov <emil.l.velikov@gmail.com>
360 Description: 327 Description:
361 This file contains the revisio 328 This file contains the revision field of the PCI device.
362 The value comes from device co 329 The value comes from device config space. The file is read only.
363 330
364 What: /sys/bus/pci/devices/.../sriov 331 What: /sys/bus/pci/devices/.../sriov_drivers_autoprobe
365 Date: April 2017 332 Date: April 2017
366 Contact: Bodong Wang<bodong@mellanox.com 333 Contact: Bodong Wang<bodong@mellanox.com>
367 Description: 334 Description:
368 This file is associated with t 335 This file is associated with the PF of a device that
369 supports SR-IOV. It determine 336 supports SR-IOV. It determines whether newly-enabled VFs
370 are immediately bound to a dri 337 are immediately bound to a driver. It initially contains
371 1, which means the kernel auto 338 1, which means the kernel automatically binds VFs to a
372 compatible driver immediately 339 compatible driver immediately after they are enabled. If
373 an application writes 0 to the 340 an application writes 0 to the file before enabling VFs,
374 the kernel will not bind VFs t 341 the kernel will not bind VFs to a driver.
375 342
376 A typical use case is to write 343 A typical use case is to write 0 to this file, then enable
377 VFs, then assign the newly-cre 344 VFs, then assign the newly-created VFs to virtual machines.
378 Note that changing this file d 345 Note that changing this file does not affect already-
379 enabled VFs. In this scenario 346 enabled VFs. In this scenario, the user must first disable
380 the VFs, write 0 to sriov_driv 347 the VFs, write 0 to sriov_drivers_autoprobe, then re-enable
381 the VFs. 348 the VFs.
382 349
383 This is similar to /sys/bus/pc 350 This is similar to /sys/bus/pci/drivers_autoprobe, but
384 affects only the VFs associate 351 affects only the VFs associated with a specific PF.
385 352
386 What: /sys/bus/pci/devices/.../p2pme 353 What: /sys/bus/pci/devices/.../p2pmem/size
387 Date: November 2017 354 Date: November 2017
388 Contact: Logan Gunthorpe <logang@deltate 355 Contact: Logan Gunthorpe <logang@deltatee.com>
389 Description: 356 Description:
390 If the device has any Peer-to- 357 If the device has any Peer-to-Peer memory registered, this
391 file contains the total amount 358 file contains the total amount of memory that the device
392 provides (in decimal). 359 provides (in decimal).
393 360
394 What: /sys/bus/pci/devices/.../p2pme 361 What: /sys/bus/pci/devices/.../p2pmem/available
395 Date: November 2017 362 Date: November 2017
396 Contact: Logan Gunthorpe <logang@deltate 363 Contact: Logan Gunthorpe <logang@deltatee.com>
397 Description: 364 Description:
398 If the device has any Peer-to- 365 If the device has any Peer-to-Peer memory registered, this
399 file contains the amount of me 366 file contains the amount of memory that has not been
400 allocated (in decimal). 367 allocated (in decimal).
401 368
402 What: /sys/bus/pci/devices/.../p2pme 369 What: /sys/bus/pci/devices/.../p2pmem/published
403 Date: November 2017 370 Date: November 2017
404 Contact: Logan Gunthorpe <logang@deltate 371 Contact: Logan Gunthorpe <logang@deltatee.com>
405 Description: 372 Description:
406 If the device has any Peer-to- 373 If the device has any Peer-to-Peer memory registered, this
407 file contains a '1' if the mem 374 file contains a '1' if the memory has been published for
408 use outside the driver that ow 375 use outside the driver that owns the device.
409 376
410 What: /sys/bus/pci/devices/.../p2pme <<
411 Date: August 2022 <<
412 Contact: Logan Gunthorpe <logang@deltate <<
413 Description: <<
414 This file allows mapping p2pme <<
415 mmap() call on this file, the <<
416 of Peer-to-Peer memory for use <<
417 This memory can be used in O_D <<
418 files for Peer-to-Peer copies. <<
419 <<
420 What: /sys/bus/pci/devices/.../link/ 377 What: /sys/bus/pci/devices/.../link/clkpm
421 /sys/bus/pci/devices/.../link/ 378 /sys/bus/pci/devices/.../link/l0s_aspm
422 /sys/bus/pci/devices/.../link/ 379 /sys/bus/pci/devices/.../link/l1_aspm
423 /sys/bus/pci/devices/.../link/ 380 /sys/bus/pci/devices/.../link/l1_1_aspm
424 /sys/bus/pci/devices/.../link/ 381 /sys/bus/pci/devices/.../link/l1_2_aspm
425 /sys/bus/pci/devices/.../link/ 382 /sys/bus/pci/devices/.../link/l1_1_pcipm
426 /sys/bus/pci/devices/.../link/ 383 /sys/bus/pci/devices/.../link/l1_2_pcipm
427 Date: October 2019 384 Date: October 2019
428 Contact: Heiner Kallweit <hkallweit1@gma 385 Contact: Heiner Kallweit <hkallweit1@gmail.com>
429 Description: If ASPM is supported for an en 386 Description: If ASPM is supported for an endpoint, these files can be
430 used to disable or enable the 387 used to disable or enable the individual power management
431 states. Write y/1/on to enable 388 states. Write y/1/on to enable, n/0/off to disable.
432 389
433 What: /sys/bus/pci/devices/.../power 390 What: /sys/bus/pci/devices/.../power_state
434 Date: November 2020 391 Date: November 2020
435 Contact: Linux PCI developers <linux-pci 392 Contact: Linux PCI developers <linux-pci@vger.kernel.org>
436 Description: 393 Description:
437 This file contains the current 394 This file contains the current PCI power state of the device.
438 The value comes from the PCI k 395 The value comes from the PCI kernel device state and can be one
439 of: "unknown", "error", "D0", 396 of: "unknown", "error", "D0", D1", "D2", "D3hot", "D3cold".
440 The file is read only. 397 The file is read only.
441 398
442 What: /sys/bus/pci/devices/.../sriov 399 What: /sys/bus/pci/devices/.../sriov_vf_total_msix
443 Date: January 2021 400 Date: January 2021
444 Contact: Leon Romanovsky <leonro@nvidia. 401 Contact: Leon Romanovsky <leonro@nvidia.com>
445 Description: 402 Description:
446 This file is associated with a 403 This file is associated with a SR-IOV physical function (PF).
447 It contains the total number o 404 It contains the total number of MSI-X vectors available for
448 assignment to all virtual func 405 assignment to all virtual functions (VFs) associated with PF.
449 The value will be zero if the 406 The value will be zero if the device doesn't support this
450 functionality. For supported d 407 functionality. For supported devices, the value will be
451 constant and won't be changed 408 constant and won't be changed after MSI-X vectors assignment.
452 409
453 What: /sys/bus/pci/devices/.../sriov 410 What: /sys/bus/pci/devices/.../sriov_vf_msix_count
454 Date: January 2021 411 Date: January 2021
455 Contact: Leon Romanovsky <leonro@nvidia. 412 Contact: Leon Romanovsky <leonro@nvidia.com>
456 Description: 413 Description:
457 This file is associated with a 414 This file is associated with a SR-IOV virtual function (VF).
458 It allows configuration of the 415 It allows configuration of the number of MSI-X vectors for
459 the VF. This allows devices th 416 the VF. This allows devices that have a global pool of MSI-X
460 vectors to optimally divide th 417 vectors to optimally divide them between VFs based on VF usage.
461 418
462 The values accepted are: 419 The values accepted are:
463 * > 0 - this number will be r 420 * > 0 - this number will be reported as the Table Size in the
464 VF's MSI-X capability 421 VF's MSI-X capability
465 * < 0 - not valid 422 * < 0 - not valid
466 * = 0 - will reset to the dev 423 * = 0 - will reset to the device default value
467 424
468 The file is writable if the PF 425 The file is writable if the PF is bound to a driver that
469 implements ->sriov_set_msix_ve 426 implements ->sriov_set_msix_vec_count().
470 <<
471 What: /sys/bus/pci/devices/.../resou <<
472 Date: September 2022 <<
473 Contact: Alex Williamson <alex.williamso <<
474 Description: <<
475 These files provide an interfa <<
476 A file is created for each BAR <<
477 PCIe Resizable BAR extended ca <<
478 each file exposes the bitmap o <<
479 <<
480 # cat resource1_resize <<
481 00000000000001c0 <<
482 <<
483 The bitmap represents supporte <<
484 where bit0 = 1MB, bit1 = 2MB, <<
485 example the device supports 64 <<
486 <<
487 When writing the file, the use <<
488 the desired resource size, for <<
489 <<
490 # echo 7 > resource1_resize <<
491 <<
492 This indicates to set the size <<
493 128MB. The resulting size is <<
494 matches the PCIe specification <<
495 <<
496 In order to make use of resour <<
497 be unbound from the device and <<
498 parent bridge may need to be s <<
499 VGA devices, writing a resize <<
500 console drivers from the devic <<
501 resourceN attributes must be t <<
502 Success of the resizing operat <<
503 <<
504 What: /sys/bus/pci/devices/.../leds/ <<
505 What: /sys/class/leds/*:enclosure:*/ <<
506 Date: August 2024 <<
507 KernelVersion: 6.12 <<
508 Description: <<
509 LED indications on PCIe storag <<
510 through the NPEM interface (Na <<
511 PCIe r6.1 sec 6.28) are access <<
512 below /sys/class/leds and belo <<
513 <<
514 Although these led class devic <<
515 in practice they are typically <<
516 application such as ledmon(8). <<
517 <<
518 The name of a led class device <<
519 <bdf>:enclosure:<indication> <<
520 where: <<
521 <<
522 - <bdf> is the domain, bus, de <<
523 (e.g. 10000:02:05.0) <<
524 - <indication> is a short desc <<
525 <<
526 Valid indications per PCIe r6. <<
527 <<
528 - ok (drive is functioning nor <<
529 - locate (drive is being ident <<
530 - fail (drive is not functioni <<
531 - rebuild (drive is part of an <<
532 - pfa (drive is predicted to f <<
533 - hotspare (drive is marked to <<
534 - ica (drive is part of an arr <<
535 - ifa (drive is part of an arr <<
536 - idt (drive is not the right <<
537 - disabled (drive is disabled, <<
538 - specific0 to specific7 (encl <<
539 <<
540 Broadly, the indications fall <<
541 <<
542 - to signify drive state (ok, <<
543 - to signify drive role or sta <<
544 (rebuild, pfa, hotspare, ica <<
545 - to signify any other role or <<
546 <<
547 Mandatory indications per PCIe <<
548 ok, locate, fail, rebuild. All <<
549 A led class device is only vis <<
550 indication is supported by the <<
551 <<
552 To manipulate the indications, <<
553 to the "brightness" file. Note <<
554 may implicitly manipulate othe <<
555 discretion. E.g. when the user <<
556 the vendor may choose to autom <<
557 indication. The current state <<
558 retrieved by reading its "brig <<
559 <<
560 The PCIe Base Specification al <<
561 different colors or blinking p <<
562 but they typically follow the <<
563 indication is usually presente <<
564 4 Hz frequency: <<
565 https://en.wikipedia.org/wiki/ <<
566 <<
567 PCI Firmware Specification r3. <<
568 to facilitate shared access by <<
569 firmware to a device's NPEM re <<
570 this DSM interface where avail <<
571 registers directly. The DSM in <<
572 enclosure-specific indications <<
573 hence the corresponding led cl <<
574 the DSM interface is used. <<
Linux® is a registered trademark of Linus Torvalds in the United States and other countries.
TOMOYO® is a registered trademark of NTT DATA CORPORATION.