Loading...
1What: /sys/bus/pci/drivers/.../bind
2What: /sys/devices/pciX/.../bind
3Date: December 2003
4Contact: linux-pci@vger.kernel.org
5Description:
6 Writing a device location to this file will cause
7 the driver to attempt to bind to the device found at
8 this location. This is useful for overriding default
9 bindings. The format for the location is: DDDD:BB:DD.F.
10 That is Domain:Bus:Device.Function and is the same as
11 found in /sys/bus/pci/devices/. For example::
12
13 # echo 0000:00:19.0 > /sys/bus/pci/drivers/foo/bind
14
15 (Note: kernels before 2.6.28 may require echo -n).
16
17What: /sys/bus/pci/drivers/.../unbind
18What: /sys/devices/pciX/.../unbind
19Date: December 2003
20Contact: linux-pci@vger.kernel.org
21Description:
22 Writing a device location to this file will cause the
23 driver to attempt to unbind from the device found at
24 this location. This may be useful when overriding default
25 bindings. The format for the location is: DDDD:BB:DD.F.
26 That is Domain:Bus:Device.Function and is the same as
27 found in /sys/bus/pci/devices/. For example::
28
29 # echo 0000:00:19.0 > /sys/bus/pci/drivers/foo/unbind
30
31 (Note: kernels before 2.6.28 may require echo -n).
32
33What: /sys/bus/pci/drivers/.../new_id
34What: /sys/devices/pciX/.../new_id
35Date: December 2003
36Contact: linux-pci@vger.kernel.org
37Description:
38 Writing a device ID to this file will attempt to
39 dynamically add a new device ID to a PCI device driver.
40 This may allow the driver to support more hardware than
41 was included in the driver's static device ID support
42 table at compile time. The format for the device ID is:
43 VVVV DDDD SVVV SDDD CCCC MMMM PPPP. That is Vendor ID,
44 Device ID, Subsystem Vendor ID, Subsystem Device ID,
45 Class, Class Mask, and Private Driver Data. The Vendor ID
46 and Device ID fields are required, the rest are optional.
47 Upon successfully adding an ID, the driver will probe
48 for the device and attempt to bind to it. For example::
49
50 # echo "8086 10f5" > /sys/bus/pci/drivers/foo/new_id
51
52What: /sys/bus/pci/drivers/.../remove_id
53What: /sys/devices/pciX/.../remove_id
54Date: February 2009
55Contact: Chris Wright <chrisw@sous-sol.org>
56Description:
57 Writing a device ID to this file will remove an ID
58 that was dynamically added via the new_id sysfs entry.
59 The format for the device ID is:
60 VVVV DDDD SVVV SDDD CCCC MMMM. That is Vendor ID, Device
61 ID, Subsystem Vendor ID, Subsystem Device ID, Class,
62 and Class Mask. The Vendor ID and Device ID fields are
63 required, the rest are optional. After successfully
64 removing an ID, the driver will no longer support the
65 device. This is useful to ensure auto probing won't
66 match the driver to the device. For example::
67
68 # echo "8086 10f5" > /sys/bus/pci/drivers/foo/remove_id
69
70What: /sys/bus/pci/rescan
71Date: January 2009
72Contact: Linux PCI developers <linux-pci@vger.kernel.org>
73Description:
74 Writing a non-zero value to this attribute will
75 force a rescan of all PCI buses in the system, and
76 re-discover previously removed devices.
77
78What: /sys/bus/pci/devices/.../msi_bus
79Date: September 2014
80Contact: Linux PCI developers <linux-pci@vger.kernel.org>
81Description:
82 Writing a zero value to this attribute disallows MSI and
83 MSI-X for any future drivers of the device. If the device
84 is a bridge, MSI and MSI-X will be disallowed for future
85 drivers of all child devices under the bridge. Drivers
86 must be reloaded for the new setting to take effect.
87
88What: /sys/bus/pci/devices/.../msi_irqs/
89Date: September, 2011
90Contact: Neil Horman <nhorman@tuxdriver.com>
91Description:
92 The /sys/devices/.../msi_irqs directory contains a variable set
93 of files, with each file being named after a corresponding msi
94 irq vector allocated to that device.
95
96What: /sys/bus/pci/devices/.../msi_irqs/<N>
97Date: September 2011
98Contact: Neil Horman <nhorman@tuxdriver.com>
99Description:
100 This attribute indicates the mode that the irq vector named by
101 the file is in (msi vs. msix)
102
103What: /sys/bus/pci/devices/.../irq
104Date: August 2021
105Contact: Linux PCI developers <linux-pci@vger.kernel.org>
106Description:
107 If a driver has enabled MSI (not MSI-X), "irq" contains the
108 IRQ of the first MSI vector. Otherwise "irq" contains the
109 IRQ of the legacy INTx interrupt.
110
111 "irq" being set to 0 indicates that the device isn't
112 capable of generating legacy INTx interrupts.
113
114What: /sys/bus/pci/devices/.../remove
115Date: January 2009
116Contact: Linux PCI developers <linux-pci@vger.kernel.org>
117Description:
118 Writing a non-zero value to this attribute will
119 hot-remove the PCI device and any of its children.
120
121What: /sys/bus/pci/devices/.../pci_bus/.../rescan
122Date: May 2011
123Contact: Linux PCI developers <linux-pci@vger.kernel.org>
124Description:
125 Writing a non-zero value to this attribute will
126 force a rescan of the bus and all child buses,
127 and re-discover devices removed earlier from this
128 part of the device tree.
129
130What: /sys/bus/pci/devices/.../rescan
131Date: January 2009
132Contact: Linux PCI developers <linux-pci@vger.kernel.org>
133Description:
134 Writing a non-zero value to this attribute will
135 force a rescan of the device's parent bus and all
136 child buses, and re-discover devices removed earlier
137 from this part of the device tree.
138
139What: /sys/bus/pci/devices/.../reset_method
140Date: August 2021
141Contact: Amey Narkhede <ameynarkhede03@gmail.com>
142Description:
143 Some devices allow an individual function to be reset
144 without affecting other functions in the same slot.
145
146 For devices that have this support, a file named
147 reset_method is present in sysfs. Reading this file
148 gives names of the supported and enabled reset methods and
149 their ordering. Writing a space-separated list of names of
150 reset methods sets the reset methods and ordering to be
151 used when resetting the device. Writing an empty string
152 disables the ability to reset the device. Writing
153 "default" enables all supported reset methods in the
154 default ordering.
155
156What: /sys/bus/pci/devices/.../reset
157Date: July 2009
158Contact: Michael S. Tsirkin <mst@redhat.com>
159Description:
160 Some devices allow an individual function to be reset
161 without affecting other functions in the same device.
162 For devices that have this support, a file named reset
163 will be present in sysfs. Writing 1 to this file
164 will perform reset.
165
166What: /sys/bus/pci/devices/.../vpd
167Date: February 2008
168Contact: Ben Hutchings <bwh@kernel.org>
169Description:
170 A file named vpd in a device directory will be a
171 binary file containing the Vital Product Data for the
172 device. It should follow the VPD format defined in
173 PCI Specification 2.1 or 2.2, but users should consider
174 that some devices may have incorrectly formatted data.
175 If the underlying VPD has a writable section then the
176 corresponding section of this file will be writable.
177
178What: /sys/bus/pci/devices/.../virtfn<N>
179Date: March 2009
180Contact: Yu Zhao <yu.zhao@intel.com>
181Description:
182 This symbolic link appears when hardware supports the SR-IOV
183 capability and the Physical Function driver has enabled it.
184 The symbolic link points to the PCI device sysfs entry of the
185 Virtual Function whose index is N (0...MaxVFs-1).
186
187What: /sys/bus/pci/devices/.../dep_link
188Date: March 2009
189Contact: Yu Zhao <yu.zhao@intel.com>
190Description:
191 This symbolic link appears when hardware supports the SR-IOV
192 capability and the Physical Function driver has enabled it,
193 and this device has vendor specific dependencies with others.
194 The symbolic link points to the PCI device sysfs entry of
195 Physical Function this device depends on.
196
197What: /sys/bus/pci/devices/.../physfn
198Date: March 2009
199Contact: Yu Zhao <yu.zhao@intel.com>
200Description:
201 This symbolic link appears when a device is a Virtual Function.
202 The symbolic link points to the PCI device sysfs entry of the
203 Physical Function this device associates with.
204
205What: /sys/bus/pci/devices/.../modalias
206Date: May 2005
207Contact: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
208Description:
209 This attribute indicates the PCI ID of the device object.
210
211 That is in the format:
212 pci:vXXXXXXXXdXXXXXXXXsvXXXXXXXXsdXXXXXXXXbcXXscXXiXX,
213 where:
214
215 - vXXXXXXXX contains the vendor ID;
216 - dXXXXXXXX contains the device ID;
217 - svXXXXXXXX contains the sub-vendor ID;
218 - sdXXXXXXXX contains the subsystem device ID;
219 - bcXX contains the device class;
220 - scXX contains the device subclass;
221 - iXX contains the device class programming interface.
222
223What: /sys/bus/pci/slots/.../module
224Date: June 2009
225Contact: linux-pci@vger.kernel.org
226Description:
227 This symbolic link points to the PCI hotplug controller driver
228 module that manages the hotplug slot.
229
230What: /sys/bus/pci/devices/.../label
231Date: July 2010
232Contact: Narendra K <narendra_k@dell.com>, linux-bugs@dell.com
233Description:
234 Reading this attribute will provide the firmware
235 given name (SMBIOS type 41 string or ACPI _DSM string) of
236 the PCI device. The attribute will be created only
237 if the firmware has given a name to the PCI device.
238 ACPI _DSM string name will be given priority if the
239 system firmware provides SMBIOS type 41 string also.
240Users:
241 Userspace applications interested in knowing the
242 firmware assigned name of the PCI device.
243
244What: /sys/bus/pci/devices/.../index
245Date: July 2010
246Contact: Narendra K <narendra_k@dell.com>, linux-bugs@dell.com
247Description:
248 Reading this attribute will provide the firmware given instance
249 number of the PCI device. Depending on the platform this can
250 be for example the SMBIOS type 41 device type instance or the
251 user-defined ID (UID) on s390. The attribute will be created
252 only if the firmware has given an instance number to the PCI
253 device and that number is guaranteed to uniquely identify the
254 device in the system.
255Users:
256 Userspace applications interested in knowing the
257 firmware assigned device type instance of the PCI
258 device that can help in understanding the firmware
259 intended order of the PCI device.
260
261What: /sys/bus/pci/devices/.../acpi_index
262Date: July 2010
263Contact: Narendra K <narendra_k@dell.com>, linux-bugs@dell.com
264Description:
265 Reading this attribute will provide the firmware
266 given instance (ACPI _DSM instance number) of the PCI device.
267 The attribute will be created only if the firmware has given
268 an instance number to the PCI device. ACPI _DSM instance number
269 will be given priority if the system firmware provides SMBIOS
270 type 41 device type instance also.
271Users:
272 Userspace applications interested in knowing the
273 firmware assigned instance number of the PCI
274 device that can help in understanding the firmware
275 intended order of the PCI device.
276
277What: /sys/bus/pci/devices/.../d3cold_allowed
278Date: July 2012
279Contact: Huang Ying <ying.huang@intel.com>
280Description:
281 d3cold_allowed is bit to control whether the corresponding PCI
282 device can be put into D3Cold state. If it is cleared, the
283 device will never be put into D3Cold state. If it is set, the
284 device may be put into D3Cold state if other requirements are
285 satisfied too. Reading this attribute will show the current
286 value of d3cold_allowed bit. Writing this attribute will set
287 the value of d3cold_allowed bit.
288
289What: /sys/bus/pci/devices/.../sriov_totalvfs
290Date: November 2012
291Contact: Donald Dutile <ddutile@redhat.com>
292Description:
293 This file appears when a physical PCIe device supports SR-IOV.
294 Userspace applications can read this file to determine the
295 maximum number of Virtual Functions (VFs) a PCIe physical
296 function (PF) can support. Typically, this is the value reported
297 in the PF's SR-IOV extended capability structure's TotalVFs
298 element. Drivers have the ability at probe time to reduce the
299 value read from this file via the pci_sriov_set_totalvfs()
300 function.
301
302What: /sys/bus/pci/devices/.../sriov_numvfs
303Date: November 2012
304Contact: Donald Dutile <ddutile@redhat.com>
305Description:
306 This file appears when a physical PCIe device supports SR-IOV.
307 Userspace applications can read and write to this file to
308 determine and control the enablement or disablement of Virtual
309 Functions (VFs) on the physical function (PF). A read of this
310 file will return the number of VFs that are enabled on this PF.
311 A number written to this file will enable the specified
312 number of VFs. A userspace application would typically read the
313 file and check that the value is zero, and then write the number
314 of VFs that should be enabled on the PF; the value written
315 should be less than or equal to the value in the sriov_totalvfs
316 file. A userspace application wanting to disable the VFs would
317 write a zero to this file. The core ensures that valid values
318 are written to this file, and returns errors when values are not
319 valid. For example, writing a 2 to this file when sriov_numvfs
320 is not 0 and not 2 already will return an error. Writing a 10
321 when the value of sriov_totalvfs is 8 will return an error.
322
323What: /sys/bus/pci/devices/.../driver_override
324Date: April 2014
325Contact: Alex Williamson <alex.williamson@redhat.com>
326Description:
327 This file allows the driver for a device to be specified which
328 will override standard static and dynamic ID matching. When
329 specified, only a driver with a name matching the value written
330 to driver_override will have an opportunity to bind to the
331 device. The override is specified by writing a string to the
332 driver_override file (echo pci-stub > driver_override) and
333 may be cleared with an empty string (echo > driver_override).
334 This returns the device to standard matching rules binding.
335 Writing to driver_override does not automatically unbind the
336 device from its current driver or make any attempt to
337 automatically load the specified driver. If no driver with a
338 matching name is currently loaded in the kernel, the device
339 will not bind to any driver. This also allows devices to
340 opt-out of driver binding using a driver_override name such as
341 "none". Only a single driver may be specified in the override,
342 there is no support for parsing delimiters.
343
344What: /sys/bus/pci/devices/.../numa_node
345Date: Oct 2014
346Contact: Prarit Bhargava <prarit@redhat.com>
347Description:
348 This file contains the NUMA node to which the PCI device is
349 attached, or -1 if the node is unknown. The initial value
350 comes from an ACPI _PXM method or a similar firmware
351 source. If that is missing or incorrect, this file can be
352 written to override the node. In that case, please report
353 a firmware bug to the system vendor. Writing to this file
354 taints the kernel with TAINT_FIRMWARE_WORKAROUND, which
355 reduces the supportability of your system.
356
357What: /sys/bus/pci/devices/.../revision
358Date: November 2016
359Contact: Emil Velikov <emil.l.velikov@gmail.com>
360Description:
361 This file contains the revision field of the PCI device.
362 The value comes from device config space. The file is read only.
363
364What: /sys/bus/pci/devices/.../sriov_drivers_autoprobe
365Date: April 2017
366Contact: Bodong Wang<bodong@mellanox.com>
367Description:
368 This file is associated with the PF of a device that
369 supports SR-IOV. It determines whether newly-enabled VFs
370 are immediately bound to a driver. It initially contains
371 1, which means the kernel automatically binds VFs to a
372 compatible driver immediately after they are enabled. If
373 an application writes 0 to the file before enabling VFs,
374 the kernel will not bind VFs to a driver.
375
376 A typical use case is to write 0 to this file, then enable
377 VFs, then assign the newly-created VFs to virtual machines.
378 Note that changing this file does not affect already-
379 enabled VFs. In this scenario, the user must first disable
380 the VFs, write 0 to sriov_drivers_autoprobe, then re-enable
381 the VFs.
382
383 This is similar to /sys/bus/pci/drivers_autoprobe, but
384 affects only the VFs associated with a specific PF.
385
386What: /sys/bus/pci/devices/.../p2pmem/size
387Date: November 2017
388Contact: Logan Gunthorpe <logang@deltatee.com>
389Description:
390 If the device has any Peer-to-Peer memory registered, this
391 file contains the total amount of memory that the device
392 provides (in decimal).
393
394What: /sys/bus/pci/devices/.../p2pmem/available
395Date: November 2017
396Contact: Logan Gunthorpe <logang@deltatee.com>
397Description:
398 If the device has any Peer-to-Peer memory registered, this
399 file contains the amount of memory that has not been
400 allocated (in decimal).
401
402What: /sys/bus/pci/devices/.../p2pmem/published
403Date: November 2017
404Contact: Logan Gunthorpe <logang@deltatee.com>
405Description:
406 If the device has any Peer-to-Peer memory registered, this
407 file contains a '1' if the memory has been published for
408 use outside the driver that owns the device.
409
410What: /sys/bus/pci/devices/.../p2pmem/allocate
411Date: August 2022
412Contact: Logan Gunthorpe <logang@deltatee.com>
413Description:
414 This file allows mapping p2pmem into userspace. For each
415 mmap() call on this file, the kernel will allocate a chunk
416 of Peer-to-Peer memory for use in Peer-to-Peer transactions.
417 This memory can be used in O_DIRECT calls to NVMe backed
418 files for Peer-to-Peer copies.
419
420What: /sys/bus/pci/devices/.../link/clkpm
421 /sys/bus/pci/devices/.../link/l0s_aspm
422 /sys/bus/pci/devices/.../link/l1_aspm
423 /sys/bus/pci/devices/.../link/l1_1_aspm
424 /sys/bus/pci/devices/.../link/l1_2_aspm
425 /sys/bus/pci/devices/.../link/l1_1_pcipm
426 /sys/bus/pci/devices/.../link/l1_2_pcipm
427Date: October 2019
428Contact: Heiner Kallweit <hkallweit1@gmail.com>
429Description: If ASPM is supported for an endpoint, these files can be
430 used to disable or enable the individual power management
431 states. Write y/1/on to enable, n/0/off to disable.
432
433What: /sys/bus/pci/devices/.../power_state
434Date: November 2020
435Contact: Linux PCI developers <linux-pci@vger.kernel.org>
436Description:
437 This file contains the current PCI power state of the device.
438 The value comes from the PCI kernel device state and can be one
439 of: "unknown", "error", "D0", D1", "D2", "D3hot", "D3cold".
440 The file is read only.
441
442What: /sys/bus/pci/devices/.../sriov_vf_total_msix
443Date: January 2021
444Contact: Leon Romanovsky <leonro@nvidia.com>
445Description:
446 This file is associated with a SR-IOV physical function (PF).
447 It contains the total number of MSI-X vectors available for
448 assignment to all virtual functions (VFs) associated with PF.
449 The value will be zero if the device doesn't support this
450 functionality. For supported devices, the value will be
451 constant and won't be changed after MSI-X vectors assignment.
452
453What: /sys/bus/pci/devices/.../sriov_vf_msix_count
454Date: January 2021
455Contact: Leon Romanovsky <leonro@nvidia.com>
456Description:
457 This file is associated with a SR-IOV virtual function (VF).
458 It allows configuration of the number of MSI-X vectors for
459 the VF. This allows devices that have a global pool of MSI-X
460 vectors to optimally divide them between VFs based on VF usage.
461
462 The values accepted are:
463 * > 0 - this number will be reported as the Table Size in the
464 VF's MSI-X capability
465 * < 0 - not valid
466 * = 0 - will reset to the device default value
467
468 The file is writable if the PF is bound to a driver that
469 implements ->sriov_set_msix_vec_count().
470
471What: /sys/bus/pci/devices/.../resourceN_resize
472Date: September 2022
473Contact: Alex Williamson <alex.williamson@redhat.com>
474Description:
475 These files provide an interface to PCIe Resizable BAR support.
476 A file is created for each BAR resource (N) supported by the
477 PCIe Resizable BAR extended capability of the device. Reading
478 each file exposes the bitmap of available resource sizes:
479
480 # cat resource1_resize
481 00000000000001c0
482
483 The bitmap represents supported resource sizes for the BAR,
484 where bit0 = 1MB, bit1 = 2MB, bit2 = 4MB, etc. In the above
485 example the device supports 64MB, 128MB, and 256MB BAR sizes.
486
487 When writing the file, the user provides the bit position of
488 the desired resource size, for example:
489
490 # echo 7 > resource1_resize
491
492 This indicates to set the size value corresponding to bit 7,
493 128MB. The resulting size is 2 ^ (bit# + 20). This definition
494 matches the PCIe specification of this capability.
495
496 In order to make use of resource resizing, all PCI drivers must
497 be unbound from the device and peer devices under the same
498 parent bridge may need to be soft removed. In the case of
499 VGA devices, writing a resize value will remove low level
500 console drivers from the device. Raw users of pci-sysfs
501 resourceN attributes must be terminated prior to resizing.
502 Success of the resizing operation is not guaranteed.
1What: /sys/bus/pci/drivers/.../bind
2What: /sys/devices/pciX/.../bind
3Date: December 2003
4Contact: linux-pci@vger.kernel.org
5Description:
6 Writing a device location to this file will cause
7 the driver to attempt to bind to the device found at
8 this location. This is useful for overriding default
9 bindings. The format for the location is: DDDD:BB:DD.F.
10 That is Domain:Bus:Device.Function and is the same as
11 found in /sys/bus/pci/devices/. For example::
12
13 # echo 0000:00:19.0 > /sys/bus/pci/drivers/foo/bind
14
15 (Note: kernels before 2.6.28 may require echo -n).
16
17What: /sys/bus/pci/drivers/.../unbind
18What: /sys/devices/pciX/.../unbind
19Date: December 2003
20Contact: linux-pci@vger.kernel.org
21Description:
22 Writing a device location to this file will cause the
23 driver to attempt to unbind from the device found at
24 this location. This may be useful when overriding default
25 bindings. The format for the location is: DDDD:BB:DD.F.
26 That is Domain:Bus:Device.Function and is the same as
27 found in /sys/bus/pci/devices/. For example::
28
29 # echo 0000:00:19.0 > /sys/bus/pci/drivers/foo/unbind
30
31 (Note: kernels before 2.6.28 may require echo -n).
32
33What: /sys/bus/pci/drivers/.../new_id
34What: /sys/devices/pciX/.../new_id
35Date: December 2003
36Contact: linux-pci@vger.kernel.org
37Description:
38 Writing a device ID to this file will attempt to
39 dynamically add a new device ID to a PCI device driver.
40 This may allow the driver to support more hardware than
41 was included in the driver's static device ID support
42 table at compile time. The format for the device ID is:
43 VVVV DDDD SVVV SDDD CCCC MMMM PPPP. That is Vendor ID,
44 Device ID, Subsystem Vendor ID, Subsystem Device ID,
45 Class, Class Mask, and Private Driver Data. The Vendor ID
46 and Device ID fields are required, the rest are optional.
47 Upon successfully adding an ID, the driver will probe
48 for the device and attempt to bind to it. For example::
49
50 # echo "8086 10f5" > /sys/bus/pci/drivers/foo/new_id
51
52What: /sys/bus/pci/drivers/.../remove_id
53What: /sys/devices/pciX/.../remove_id
54Date: February 2009
55Contact: Chris Wright <chrisw@sous-sol.org>
56Description:
57 Writing a device ID to this file will remove an ID
58 that was dynamically added via the new_id sysfs entry.
59 The format for the device ID is:
60 VVVV DDDD SVVV SDDD CCCC MMMM. That is Vendor ID, Device
61 ID, Subsystem Vendor ID, Subsystem Device ID, Class,
62 and Class Mask. The Vendor ID and Device ID fields are
63 required, the rest are optional. After successfully
64 removing an ID, the driver will no longer support the
65 device. This is useful to ensure auto probing won't
66 match the driver to the device. For example::
67
68 # echo "8086 10f5" > /sys/bus/pci/drivers/foo/remove_id
69
70What: /sys/bus/pci/rescan
71Date: January 2009
72Contact: Linux PCI developers <linux-pci@vger.kernel.org>
73Description:
74 Writing a non-zero value to this attribute will
75 force a rescan of all PCI buses in the system, and
76 re-discover previously removed devices.
77
78What: /sys/bus/pci/devices/.../msi_bus
79Date: September 2014
80Contact: Linux PCI developers <linux-pci@vger.kernel.org>
81Description:
82 Writing a zero value to this attribute disallows MSI and
83 MSI-X for any future drivers of the device. If the device
84 is a bridge, MSI and MSI-X will be disallowed for future
85 drivers of all child devices under the bridge. Drivers
86 must be reloaded for the new setting to take effect.
87
88What: /sys/bus/pci/devices/.../msi_irqs/
89Date: September, 2011
90Contact: Neil Horman <nhorman@tuxdriver.com>
91Description:
92 The /sys/devices/.../msi_irqs directory contains a variable set
93 of files, with each file being named after a corresponding msi
94 irq vector allocated to that device.
95
96What: /sys/bus/pci/devices/.../msi_irqs/<N>
97Date: September 2011
98Contact: Neil Horman <nhorman@tuxdriver.com>
99Description:
100 This attribute indicates the mode that the irq vector named by
101 the file is in (msi vs. msix)
102
103What: /sys/bus/pci/devices/.../irq
104Date: August 2021
105Contact: Linux PCI developers <linux-pci@vger.kernel.org>
106Description:
107 If a driver has enabled MSI (not MSI-X), "irq" contains the
108 IRQ of the first MSI vector. Otherwise "irq" contains the
109 IRQ of the legacy INTx interrupt.
110
111 "irq" being set to 0 indicates that the device isn't
112 capable of generating legacy INTx interrupts.
113
114What: /sys/bus/pci/devices/.../remove
115Date: January 2009
116Contact: Linux PCI developers <linux-pci@vger.kernel.org>
117Description:
118 Writing a non-zero value to this attribute will
119 hot-remove the PCI device and any of its children.
120
121What: /sys/bus/pci/devices/.../pci_bus/.../rescan
122Date: May 2011
123Contact: Linux PCI developers <linux-pci@vger.kernel.org>
124Description:
125 Writing a non-zero value to this attribute will
126 force a rescan of the bus and all child buses,
127 and re-discover devices removed earlier from this
128 part of the device tree.
129
130What: /sys/bus/pci/devices/.../rescan
131Date: January 2009
132Contact: Linux PCI developers <linux-pci@vger.kernel.org>
133Description:
134 Writing a non-zero value to this attribute will
135 force a rescan of the device's parent bus and all
136 child buses, and re-discover devices removed earlier
137 from this part of the device tree.
138
139What: /sys/bus/pci/devices/.../reset_method
140Date: August 2021
141Contact: Amey Narkhede <ameynarkhede03@gmail.com>
142Description:
143 Some devices allow an individual function to be reset
144 without affecting other functions in the same slot.
145
146 For devices that have this support, a file named
147 reset_method is present in sysfs. Reading this file
148 gives names of the supported and enabled reset methods and
149 their ordering. Writing a space-separated list of names of
150 reset methods sets the reset methods and ordering to be
151 used when resetting the device. Writing an empty string
152 disables the ability to reset the device. Writing
153 "default" enables all supported reset methods in the
154 default ordering.
155
156What: /sys/bus/pci/devices/.../reset
157Date: July 2009
158Contact: Michael S. Tsirkin <mst@redhat.com>
159Description:
160 Some devices allow an individual function to be reset
161 without affecting other functions in the same device.
162 For devices that have this support, a file named reset
163 will be present in sysfs. Writing 1 to this file
164 will perform reset.
165
166What: /sys/bus/pci/devices/.../reset_subordinate
167Date: October 2024
168Contact: linux-pci@vger.kernel.org
169Description:
170 This is visible only for bridge devices. If you want to reset
171 all devices attached through the subordinate bus of a specific
172 bridge device, writing 1 to this will try to do it. This will
173 affect all devices attached to the system through this bridge
174 similiar to writing 1 to their individual "reset" file, so use
175 with caution.
176
177What: /sys/bus/pci/devices/.../vpd
178Date: February 2008
179Contact: Ben Hutchings <bwh@kernel.org>
180Description:
181 A file named vpd in a device directory will be a
182 binary file containing the Vital Product Data for the
183 device. It should follow the VPD format defined in
184 PCI Specification 2.1 or 2.2, but users should consider
185 that some devices may have incorrectly formatted data.
186 If the underlying VPD has a writable section then the
187 corresponding section of this file will be writable.
188
189What: /sys/bus/pci/devices/.../virtfn<N>
190Date: March 2009
191Contact: Yu Zhao <yu.zhao@intel.com>
192Description:
193 This symbolic link appears when hardware supports the SR-IOV
194 capability and the Physical Function driver has enabled it.
195 The symbolic link points to the PCI device sysfs entry of the
196 Virtual Function whose index is N (0...MaxVFs-1).
197
198What: /sys/bus/pci/devices/.../dep_link
199Date: March 2009
200Contact: Yu Zhao <yu.zhao@intel.com>
201Description:
202 This symbolic link appears when hardware supports the SR-IOV
203 capability and the Physical Function driver has enabled it,
204 and this device has vendor specific dependencies with others.
205 The symbolic link points to the PCI device sysfs entry of
206 Physical Function this device depends on.
207
208What: /sys/bus/pci/devices/.../physfn
209Date: March 2009
210Contact: Yu Zhao <yu.zhao@intel.com>
211Description:
212 This symbolic link appears when a device is a Virtual Function.
213 The symbolic link points to the PCI device sysfs entry of the
214 Physical Function this device associates with.
215
216What: /sys/bus/pci/devices/.../modalias
217Date: May 2005
218Contact: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
219Description:
220 This attribute indicates the PCI ID of the device object.
221
222 That is in the format:
223 pci:vXXXXXXXXdXXXXXXXXsvXXXXXXXXsdXXXXXXXXbcXXscXXiXX,
224 where:
225
226 - vXXXXXXXX contains the vendor ID;
227 - dXXXXXXXX contains the device ID;
228 - svXXXXXXXX contains the sub-vendor ID;
229 - sdXXXXXXXX contains the subsystem device ID;
230 - bcXX contains the device class;
231 - scXX contains the device subclass;
232 - iXX contains the device class programming interface.
233
234What: /sys/bus/pci/slots/.../module
235Date: June 2009
236Contact: linux-pci@vger.kernel.org
237Description:
238 This symbolic link points to the PCI hotplug controller driver
239 module that manages the hotplug slot.
240
241What: /sys/bus/pci/devices/.../label
242Date: July 2010
243Contact: Narendra K <narendra_k@dell.com>, linux-bugs@dell.com
244Description:
245 Reading this attribute will provide the firmware
246 given name (SMBIOS type 41 string or ACPI _DSM string) of
247 the PCI device. The attribute will be created only
248 if the firmware has given a name to the PCI device.
249 ACPI _DSM string name will be given priority if the
250 system firmware provides SMBIOS type 41 string also.
251Users:
252 Userspace applications interested in knowing the
253 firmware assigned name of the PCI device.
254
255What: /sys/bus/pci/devices/.../index
256Date: July 2010
257Contact: Narendra K <narendra_k@dell.com>, linux-bugs@dell.com
258Description:
259 Reading this attribute will provide the firmware given instance
260 number of the PCI device. Depending on the platform this can
261 be for example the SMBIOS type 41 device type instance or the
262 user-defined ID (UID) on s390. The attribute will be created
263 only if the firmware has given an instance number to the PCI
264 device and that number is guaranteed to uniquely identify the
265 device in the system.
266Users:
267 Userspace applications interested in knowing the
268 firmware assigned device type instance of the PCI
269 device that can help in understanding the firmware
270 intended order of the PCI device.
271
272What: /sys/bus/pci/devices/.../acpi_index
273Date: July 2010
274Contact: Narendra K <narendra_k@dell.com>, linux-bugs@dell.com
275Description:
276 Reading this attribute will provide the firmware
277 given instance (ACPI _DSM instance number) of the PCI device.
278 The attribute will be created only if the firmware has given
279 an instance number to the PCI device. ACPI _DSM instance number
280 will be given priority if the system firmware provides SMBIOS
281 type 41 device type instance also.
282Users:
283 Userspace applications interested in knowing the
284 firmware assigned instance number of the PCI
285 device that can help in understanding the firmware
286 intended order of the PCI device.
287
288What: /sys/bus/pci/devices/.../d3cold_allowed
289Date: July 2012
290Contact: Huang Ying <ying.huang@intel.com>
291Description:
292 d3cold_allowed is bit to control whether the corresponding PCI
293 device can be put into D3Cold state. If it is cleared, the
294 device will never be put into D3Cold state. If it is set, the
295 device may be put into D3Cold state if other requirements are
296 satisfied too. Reading this attribute will show the current
297 value of d3cold_allowed bit. Writing this attribute will set
298 the value of d3cold_allowed bit.
299
300What: /sys/bus/pci/devices/.../sriov_totalvfs
301Date: November 2012
302Contact: Donald Dutile <ddutile@redhat.com>
303Description:
304 This file appears when a physical PCIe device supports SR-IOV.
305 Userspace applications can read this file to determine the
306 maximum number of Virtual Functions (VFs) a PCIe physical
307 function (PF) can support. Typically, this is the value reported
308 in the PF's SR-IOV extended capability structure's TotalVFs
309 element. Drivers have the ability at probe time to reduce the
310 value read from this file via the pci_sriov_set_totalvfs()
311 function.
312
313What: /sys/bus/pci/devices/.../sriov_numvfs
314Date: November 2012
315Contact: Donald Dutile <ddutile@redhat.com>
316Description:
317 This file appears when a physical PCIe device supports SR-IOV.
318 Userspace applications can read and write to this file to
319 determine and control the enablement or disablement of Virtual
320 Functions (VFs) on the physical function (PF). A read of this
321 file will return the number of VFs that are enabled on this PF.
322 A number written to this file will enable the specified
323 number of VFs. A userspace application would typically read the
324 file and check that the value is zero, and then write the number
325 of VFs that should be enabled on the PF; the value written
326 should be less than or equal to the value in the sriov_totalvfs
327 file. A userspace application wanting to disable the VFs would
328 write a zero to this file. The core ensures that valid values
329 are written to this file, and returns errors when values are not
330 valid. For example, writing a 2 to this file when sriov_numvfs
331 is not 0 and not 2 already will return an error. Writing a 10
332 when the value of sriov_totalvfs is 8 will return an error.
333
334What: /sys/bus/pci/devices/.../driver_override
335Date: April 2014
336Contact: Alex Williamson <alex.williamson@redhat.com>
337Description:
338 This file allows the driver for a device to be specified which
339 will override standard static and dynamic ID matching. When
340 specified, only a driver with a name matching the value written
341 to driver_override will have an opportunity to bind to the
342 device. The override is specified by writing a string to the
343 driver_override file (echo pci-stub > driver_override) and
344 may be cleared with an empty string (echo > driver_override).
345 This returns the device to standard matching rules binding.
346 Writing to driver_override does not automatically unbind the
347 device from its current driver or make any attempt to
348 automatically load the specified driver. If no driver with a
349 matching name is currently loaded in the kernel, the device
350 will not bind to any driver. This also allows devices to
351 opt-out of driver binding using a driver_override name such as
352 "none". Only a single driver may be specified in the override,
353 there is no support for parsing delimiters.
354
355What: /sys/bus/pci/devices/.../numa_node
356Date: Oct 2014
357Contact: Prarit Bhargava <prarit@redhat.com>
358Description:
359 This file contains the NUMA node to which the PCI device is
360 attached, or -1 if the node is unknown. The initial value
361 comes from an ACPI _PXM method or a similar firmware
362 source. If that is missing or incorrect, this file can be
363 written to override the node. In that case, please report
364 a firmware bug to the system vendor. Writing to this file
365 taints the kernel with TAINT_FIRMWARE_WORKAROUND, which
366 reduces the supportability of your system.
367
368What: /sys/bus/pci/devices/.../revision
369Date: November 2016
370Contact: Emil Velikov <emil.l.velikov@gmail.com>
371Description:
372 This file contains the revision field of the PCI device.
373 The value comes from device config space. The file is read only.
374
375What: /sys/bus/pci/devices/.../sriov_drivers_autoprobe
376Date: April 2017
377Contact: Bodong Wang<bodong@mellanox.com>
378Description:
379 This file is associated with the PF of a device that
380 supports SR-IOV. It determines whether newly-enabled VFs
381 are immediately bound to a driver. It initially contains
382 1, which means the kernel automatically binds VFs to a
383 compatible driver immediately after they are enabled. If
384 an application writes 0 to the file before enabling VFs,
385 the kernel will not bind VFs to a driver.
386
387 A typical use case is to write 0 to this file, then enable
388 VFs, then assign the newly-created VFs to virtual machines.
389 Note that changing this file does not affect already-
390 enabled VFs. In this scenario, the user must first disable
391 the VFs, write 0 to sriov_drivers_autoprobe, then re-enable
392 the VFs.
393
394 This is similar to /sys/bus/pci/drivers_autoprobe, but
395 affects only the VFs associated with a specific PF.
396
397What: /sys/bus/pci/devices/.../p2pmem/size
398Date: November 2017
399Contact: Logan Gunthorpe <logang@deltatee.com>
400Description:
401 If the device has any Peer-to-Peer memory registered, this
402 file contains the total amount of memory that the device
403 provides (in decimal).
404
405What: /sys/bus/pci/devices/.../p2pmem/available
406Date: November 2017
407Contact: Logan Gunthorpe <logang@deltatee.com>
408Description:
409 If the device has any Peer-to-Peer memory registered, this
410 file contains the amount of memory that has not been
411 allocated (in decimal).
412
413What: /sys/bus/pci/devices/.../p2pmem/published
414Date: November 2017
415Contact: Logan Gunthorpe <logang@deltatee.com>
416Description:
417 If the device has any Peer-to-Peer memory registered, this
418 file contains a '1' if the memory has been published for
419 use outside the driver that owns the device.
420
421What: /sys/bus/pci/devices/.../p2pmem/allocate
422Date: August 2022
423Contact: Logan Gunthorpe <logang@deltatee.com>
424Description:
425 This file allows mapping p2pmem into userspace. For each
426 mmap() call on this file, the kernel will allocate a chunk
427 of Peer-to-Peer memory for use in Peer-to-Peer transactions.
428 This memory can be used in O_DIRECT calls to NVMe backed
429 files for Peer-to-Peer copies.
430
431What: /sys/bus/pci/devices/.../link/clkpm
432 /sys/bus/pci/devices/.../link/l0s_aspm
433 /sys/bus/pci/devices/.../link/l1_aspm
434 /sys/bus/pci/devices/.../link/l1_1_aspm
435 /sys/bus/pci/devices/.../link/l1_2_aspm
436 /sys/bus/pci/devices/.../link/l1_1_pcipm
437 /sys/bus/pci/devices/.../link/l1_2_pcipm
438Date: October 2019
439Contact: Heiner Kallweit <hkallweit1@gmail.com>
440Description: If ASPM is supported for an endpoint, these files can be
441 used to disable or enable the individual power management
442 states. Write y/1/on to enable, n/0/off to disable.
443
444What: /sys/bus/pci/devices/.../power_state
445Date: November 2020
446Contact: Linux PCI developers <linux-pci@vger.kernel.org>
447Description:
448 This file contains the current PCI power state of the device.
449 The value comes from the PCI kernel device state and can be one
450 of: "unknown", "error", "D0", D1", "D2", "D3hot", "D3cold".
451 The file is read only.
452
453What: /sys/bus/pci/devices/.../sriov_vf_total_msix
454Date: January 2021
455Contact: Leon Romanovsky <leonro@nvidia.com>
456Description:
457 This file is associated with a SR-IOV physical function (PF).
458 It contains the total number of MSI-X vectors available for
459 assignment to all virtual functions (VFs) associated with PF.
460 The value will be zero if the device doesn't support this
461 functionality. For supported devices, the value will be
462 constant and won't be changed after MSI-X vectors assignment.
463
464What: /sys/bus/pci/devices/.../sriov_vf_msix_count
465Date: January 2021
466Contact: Leon Romanovsky <leonro@nvidia.com>
467Description:
468 This file is associated with a SR-IOV virtual function (VF).
469 It allows configuration of the number of MSI-X vectors for
470 the VF. This allows devices that have a global pool of MSI-X
471 vectors to optimally divide them between VFs based on VF usage.
472
473 The values accepted are:
474 * > 0 - this number will be reported as the Table Size in the
475 VF's MSI-X capability
476 * < 0 - not valid
477 * = 0 - will reset to the device default value
478
479 The file is writable if the PF is bound to a driver that
480 implements ->sriov_set_msix_vec_count().
481
482What: /sys/bus/pci/devices/.../resourceN_resize
483Date: September 2022
484Contact: Alex Williamson <alex.williamson@redhat.com>
485Description:
486 These files provide an interface to PCIe Resizable BAR support.
487 A file is created for each BAR resource (N) supported by the
488 PCIe Resizable BAR extended capability of the device. Reading
489 each file exposes the bitmap of available resource sizes:
490
491 # cat resource1_resize
492 00000000000001c0
493
494 The bitmap represents supported resource sizes for the BAR,
495 where bit0 = 1MB, bit1 = 2MB, bit2 = 4MB, etc. In the above
496 example the device supports 64MB, 128MB, and 256MB BAR sizes.
497
498 When writing the file, the user provides the bit position of
499 the desired resource size, for example:
500
501 # echo 7 > resource1_resize
502
503 This indicates to set the size value corresponding to bit 7,
504 128MB. The resulting size is 2 ^ (bit# + 20). This definition
505 matches the PCIe specification of this capability.
506
507 In order to make use of resource resizing, all PCI drivers must
508 be unbound from the device and peer devices under the same
509 parent bridge may need to be soft removed. In the case of
510 VGA devices, writing a resize value will remove low level
511 console drivers from the device. Raw users of pci-sysfs
512 resourceN attributes must be terminated prior to resizing.
513 Success of the resizing operation is not guaranteed.
514
515What: /sys/bus/pci/devices/.../leds/*:enclosure:*/brightness
516What: /sys/class/leds/*:enclosure:*/brightness
517Date: August 2024
518KernelVersion: 6.12
519Description:
520 LED indications on PCIe storage enclosures which are controlled
521 through the NPEM interface (Native PCIe Enclosure Management,
522 PCIe r6.1 sec 6.28) are accessible as led class devices, both
523 below /sys/class/leds and below NPEM-capable PCI devices.
524
525 Although these led class devices could be manipulated manually,
526 in practice they are typically manipulated automatically by an
527 application such as ledmon(8).
528
529 The name of a led class device is as follows:
530 <bdf>:enclosure:<indication>
531 where:
532
533 - <bdf> is the domain, bus, device and function number
534 (e.g. 10000:02:05.0)
535 - <indication> is a short description of the LED indication
536
537 Valid indications per PCIe r6.1 table 6-27 are:
538
539 - ok (drive is functioning normally)
540 - locate (drive is being identified by an admin)
541 - fail (drive is not functioning properly)
542 - rebuild (drive is part of an array that is rebuilding)
543 - pfa (drive is predicted to fail soon)
544 - hotspare (drive is marked to be used as a replacement)
545 - ica (drive is part of an array that is degraded)
546 - ifa (drive is part of an array that is failed)
547 - idt (drive is not the right type for the connector)
548 - disabled (drive is disabled, removal is safe)
549 - specific0 to specific7 (enclosure-specific indications)
550
551 Broadly, the indications fall into one of these categories:
552
553 - to signify drive state (ok, locate, fail, idt, disabled)
554 - to signify drive role or state in a software RAID array
555 (rebuild, pfa, hotspare, ica, ifa)
556 - to signify any other role or state (specific0 to specific7)
557
558 Mandatory indications per PCIe r6.1 sec 7.9.19.2 comprise:
559 ok, locate, fail, rebuild. All others are optional.
560 A led class device is only visible if the corresponding
561 indication is supported by the device.
562
563 To manipulate the indications, write 0 (LED_OFF) or 1 (LED_ON)
564 to the "brightness" file. Note that manipulating an indication
565 may implicitly manipulate other indications at the vendor's
566 discretion. E.g. when the user lights up the "ok" indication,
567 the vendor may choose to automatically turn off the "fail"
568 indication. The current state of an indication can be
569 retrieved by reading its "brightness" file.
570
571 The PCIe Base Specification allows vendors leeway to choose
572 different colors or blinking patterns for the indications,
573 but they typically follow the IBPI standard. E.g. the "locate"
574 indication is usually presented as one or two LEDs blinking at
575 4 Hz frequency:
576 https://en.wikipedia.org/wiki/International_Blinking_Pattern_Interpretation
577
578 PCI Firmware Specification r3.3 sec 4.7 defines a DSM interface
579 to facilitate shared access by operating system and platform
580 firmware to a device's NPEM registers. The kernel will use
581 this DSM interface where available, instead of accessing NPEM
582 registers directly. The DSM interface does not support the
583 enclosure-specific indications "specific0" to "specific7",
584 hence the corresponding led class devices are unavailable if
585 the DSM interface is used.