xref: /openbmc/linux/drivers/nvdimm/Kconfig (revision bb970707)
1menuconfig LIBNVDIMM
2	tristate "NVDIMM (Non-Volatile Memory Device) Support"
3	depends on PHYS_ADDR_T_64BIT
4	depends on BLK_DEV
5	help
6	  Generic support for non-volatile memory devices including
7	  ACPI-6-NFIT defined resources.  On platforms that define an
8	  NFIT, or otherwise can discover NVDIMM resources, a libnvdimm
9	  bus is registered to advertise PMEM (persistent memory)
10	  namespaces (/dev/pmemX) and BLK (sliding mmio window(s))
11	  namespaces (/dev/ndblkX.Y). A PMEM namespace refers to a
12	  memory resource that may span multiple DIMMs and support DAX
13	  (see CONFIG_DAX).  A BLK namespace refers to an NVDIMM control
14	  region which exposes an mmio register set for windowed access
15	  mode to non-volatile memory.
16
17if LIBNVDIMM
18
19config BLK_DEV_PMEM
20	tristate "PMEM: Persistent memory block device support"
21	default LIBNVDIMM
22	depends on HAS_IOMEM
23	select ND_BTT if BTT
24	select ND_PFN if NVDIMM_PFN
25	help
26	  Memory ranges for PMEM are described by either an NFIT
27	  (NVDIMM Firmware Interface Table, see CONFIG_NFIT_ACPI), a
28	  non-standard OEM-specific E820 memory type (type-12, see
29	  CONFIG_X86_PMEM_LEGACY), or it is manually specified by the
30	  'memmap=nn[KMG]!ss[KMG]' kernel command line (see
31	  Documentation/kernel-parameters.txt).  This driver converts
32	  these persistent memory ranges into block devices that are
33	  capable of DAX (direct-access) file system mappings.  See
34	  Documentation/nvdimm/nvdimm.txt for more details.
35
36	  Say Y if you want to use an NVDIMM
37
38config ND_BLK
39	tristate "BLK: Block data window (aperture) device support"
40	default LIBNVDIMM
41	select ND_BTT if BTT
42	help
43	  Support NVDIMMs, or other devices, that implement a BLK-mode
44	  access capability.  BLK-mode access uses memory-mapped-i/o
45	  apertures to access persistent media.
46
47	  Say Y if your platform firmware emits an ACPI.NFIT table
48	  (CONFIG_ACPI_NFIT), or otherwise exposes BLK-mode
49	  capabilities.
50
51config ND_CLAIM
52	bool
53
54config ND_BTT
55	tristate
56
57config BTT
58	bool "BTT: Block Translation Table (atomic sector updates)"
59	default y if LIBNVDIMM
60	select ND_CLAIM
61	help
62	  The Block Translation Table (BTT) provides atomic sector
63	  update semantics for persistent memory devices, so that
64	  applications that rely on sector writes not being torn (a
65	  guarantee that typical disks provide) can continue to do so.
66	  The BTT manifests itself as an alternate personality for an
67	  NVDIMM namespace, i.e. a namespace can be in raw mode (pmemX,
68	  ndblkX.Y, etc...), or 'sectored' mode, (pmemXs, ndblkX.Ys,
69	  etc...).
70
71	  Select Y if unsure
72
73config ND_PFN
74	tristate
75
76config NVDIMM_PFN
77	bool "PFN: Map persistent (device) memory"
78	default LIBNVDIMM
79	depends on ZONE_DEVICE
80	select ND_CLAIM
81	help
82	  Map persistent memory, i.e. advertise it to the memory
83	  management sub-system.  By default persistent memory does
84	  not support direct I/O, RDMA, or any other usage that
85	  requires a 'struct page' to mediate an I/O request.  This
86	  driver allocates and initializes the infrastructure needed
87	  to support those use cases.
88
89	  Select Y if unsure
90
91config NVDIMM_DAX
92	bool "NVDIMM DAX: Raw access to persistent memory"
93	default LIBNVDIMM
94	depends on NVDIMM_PFN
95	help
96	  Support raw device dax access to a persistent memory
97	  namespace.  For environments that want to hard partition
98	  peristent memory, this capability provides a mechanism to
99	  sub-divide a namespace into character devices that can only be
100	  accessed via DAX (mmap(2)).
101
102	  Select Y if unsure
103
104endif
105