1For all of the nmem device attributes under ``nfit/*``, see the 'NVDIMM Firmware
2Interface Table (NFIT)' section in the ACPI specification
3(http://www.uefi.org/specifications) for more details.
4
5What:		/sys/bus/nd/devices/nmemX/nfit/serial
6Date:		Jun, 2015
7KernelVersion:	v4.2
8Contact:	nvdimm@lists.linux.dev
9Description:
10		(RO) Serial number of the NVDIMM (non-volatile dual in-line
11		memory module), assigned by the module vendor.
12
13
14What:		/sys/bus/nd/devices/nmemX/nfit/handle
15Date:		Apr, 2015
16KernelVersion:	v4.2
17Contact:	nvdimm@lists.linux.dev
18Description:
19		(RO) The address (given by the _ADR object) of the device on its
20		parent bus of the NVDIMM device containing the NVDIMM region.
21
22
23What:		/sys/bus/nd/devices/nmemX/nfit/device
24Date:		Apr, 2015
25KernelVersion:	v4.1
26Contact:	nvdimm@lists.linux.dev
27Description:
28		(RO) Device id for the NVDIMM, assigned by the module vendor.
29
30
31What:		/sys/bus/nd/devices/nmemX/nfit/rev_id
32Date:		Jun, 2015
33KernelVersion:	v4.2
34Contact:	nvdimm@lists.linux.dev
35Description:
36		(RO) Revision of the NVDIMM, assigned by the module vendor.
37
38
39What:		/sys/bus/nd/devices/nmemX/nfit/phys_id
40Date:		Apr, 2015
41KernelVersion:	v4.2
42Contact:	nvdimm@lists.linux.dev
43Description:
44		(RO) Handle (i.e., instance number) for the SMBIOS (system
45		management BIOS) Memory Device structure describing the NVDIMM
46		containing the NVDIMM region.
47
48
49What:		/sys/bus/nd/devices/nmemX/nfit/flags
50Date:		Jun, 2015
51KernelVersion:	v4.2
52Contact:	nvdimm@lists.linux.dev
53Description:
54		(RO) The flags in the NFIT memory device sub-structure indicate
55		the state of the data on the nvdimm relative to its energy
56		source or last "flush to persistence".
57
58		The attribute is a translation of the 'NVDIMM State Flags' field
59		in section 5.2.25.3 'NVDIMM Region Mapping' Structure of the
60		ACPI specification 6.2.
61
62		The health states are "save_fail", "restore_fail", "flush_fail",
63		"not_armed", "smart_event", "map_fail" and "smart_notify".
64
65
66What:		/sys/bus/nd/devices/nmemX/nfit/format
67What:		/sys/bus/nd/devices/nmemX/nfit/format1
68What:		/sys/bus/nd/devices/nmemX/nfit/formats
69Date:		Apr, 2016
70KernelVersion:	v4.7
71Contact:	nvdimm@lists.linux.dev
72Description:
73		(RO) The interface codes indicate support for persistent memory
74		mapped directly into system physical address space and / or a
75		block aperture access mechanism to the NVDIMM media.
76		The 'formats' attribute displays the number of supported
77		interfaces.
78
79		This layout is compatible with existing libndctl binaries that
80		only expect one code per-dimm as they will ignore
81		nmemX/nfit/formats and nmemX/nfit/formatN.
82
83
84What:		/sys/bus/nd/devices/nmemX/nfit/vendor
85Date:		Apr, 2016
86KernelVersion:	v4.7
87Contact:	nvdimm@lists.linux.dev
88Description:
89		(RO) Vendor id of the NVDIMM.
90
91
92What:		/sys/bus/nd/devices/nmemX/nfit/dsm_mask
93Date:		May, 2016
94KernelVersion:	v4.7
95Contact:	nvdimm@lists.linux.dev
96Description:
97		(RO) The bitmask indicates the supported device specific control
98		functions relative to the NVDIMM command family supported by the
99		device
100
101
102What:		/sys/bus/nd/devices/nmemX/nfit/family
103Date:		Apr, 2016
104KernelVersion:	v4.7
105Contact:	nvdimm@lists.linux.dev
106Description:
107		(RO) Displays the NVDIMM family command sets. Values
108		0, 1, 2 and 3 correspond to NVDIMM_FAMILY_INTEL,
109		NVDIMM_FAMILY_HPE1, NVDIMM_FAMILY_HPE2 and NVDIMM_FAMILY_MSFT
110		respectively.
111
112		See the specifications for these command families here:
113		http://pmem.io/documents/NVDIMM_DSM_Interface-V1.6.pdf
114		https://github.com/HewlettPackard/hpe-nvm/blob/master/Documentation/
115		https://msdn.microsoft.com/library/windows/hardware/mt604741"
116
117
118What:		/sys/bus/nd/devices/nmemX/nfit/id
119Date:		Apr, 2016
120KernelVersion:	v4.7
121Contact:	nvdimm@lists.linux.dev
122Description:
123		(RO) ACPI specification 6.2 section 5.2.25.9, defines an
124		identifier for an NVDIMM, which reflects the id attribute.
125
126
127What:		/sys/bus/nd/devices/nmemX/nfit/subsystem_vendor
128Date:		Apr, 2016
129KernelVersion:	v4.7
130Contact:	nvdimm@lists.linux.dev
131Description:
132		(RO) Sub-system vendor id of the NVDIMM non-volatile memory
133		subsystem controller.
134
135
136What:		/sys/bus/nd/devices/nmemX/nfit/subsystem_rev_id
137Date:		Apr, 2016
138KernelVersion:	v4.7
139Contact:	nvdimm@lists.linux.dev
140Description:
141		(RO) Sub-system revision id of the NVDIMM non-volatile memory subsystem
142		controller, assigned by the non-volatile memory subsystem
143		controller vendor.
144
145
146What:		/sys/bus/nd/devices/nmemX/nfit/subsystem_device
147Date:		Apr, 2016
148KernelVersion:	v4.7
149Contact:	nvdimm@lists.linux.dev
150Description:
151		(RO) Sub-system device id for the NVDIMM non-volatile memory
152		subsystem controller, assigned by the non-volatile memory
153		subsystem controller vendor.
154
155
156What:		/sys/bus/nd/devices/ndbusX/nfit/revision
157Date:		Jun, 2015
158KernelVersion:	v4.2
159Contact:	nvdimm@lists.linux.dev
160Description:
161		(RO) ACPI NFIT table revision number.
162
163
164What:		/sys/bus/nd/devices/ndbusX/nfit/scrub
165Date:		Sep, 2016
166KernelVersion:	v4.9
167Contact:	nvdimm@lists.linux.dev
168Description:
169		(RW) This shows the number of full Address Range Scrubs (ARS)
170		that have been completed since driver load time. Userspace can
171		wait on this using select/poll etc. A '+' at the end indicates
172		an ARS is in progress
173
174		Writing a value of 1 triggers an ARS scan.
175
176
177What:		/sys/bus/nd/devices/ndbusX/nfit/hw_error_scrub
178Date:		Sep, 2016
179KernelVersion:	v4.9
180Contact:	nvdimm@lists.linux.dev
181Description:
182		(RW) Provides a way to toggle the behavior between just adding
183		the address (cache line) where the MCE happened to the poison
184		list and doing a full scrub. The former (selective insertion of
185		the address) is done unconditionally.
186
187		This attribute can have the following values written to it:
188
189		'0': Switch to the default mode where an exception will only
190		insert the address of the memory error into the poison and
191		badblocks lists.
192		'1': Enable a full scrub to happen if an exception for a memory
193		error is received.
194
195
196What:		/sys/bus/nd/devices/ndbusX/nfit/dsm_mask
197Date:		Jun, 2017
198KernelVersion:	v4.13
199Contact:	nvdimm@lists.linux.dev
200Description:
201		(RO) The bitmask indicates the supported bus specific control
202		functions. See the section named 'NVDIMM Root Device _DSMs' in
203		the ACPI specification.
204
205What:		/sys/bus/nd/devices/ndbusX/nfit/firmware_activate_noidle
206Date:		Apr, 2020
207KernelVersion:	v5.8
208Contact:	nvdimm@lists.linux.dev
209Description:
210		(RW) The Intel platform implementation of firmware activate
211		support exposes an option let the platform force idle devices in
212		the system over the activation event, or trust that the OS will
213		do it. The safe default is to let the platform force idle
214		devices since the kernel is already in a suspend state, and on
215		the chance that a driver does not properly quiesce bus-mastering
216		after a suspend callback the platform will handle it.  However,
217		the activation might abort if, for example, platform firmware
218		determines that the activation time exceeds the max PCI-E
219		completion timeout. Since the platform does not know whether the
220		OS is running the activation from a suspend context it aborts,
221		but if the system owner trusts driver suspend callback to be
222		sufficient then 'firmware_activation_noidle' can be
223		enabled to bypass the activation abort.
224
225What:		/sys/bus/nd/devices/regionX/nfit/range_index
226Date:		Jun, 2015
227KernelVersion:	v4.2
228Contact:	nvdimm@lists.linux.dev
229Description:
230		(RO) A unique number provided by the BIOS to identify an address
231		range. Used by NVDIMM Region Mapping Structure to uniquely refer
232		to this structure. Value of 0 is reserved and not used as an
233		index.
234