Documentation/filesystems/dax.rst

6 ----------
12 For block devices that are memory-like, the page cache pages would be
19 -----
30 ------------------------------
32 When mounting the filesystem, use the ``-o dax`` option on the command line or
34 within the filesystem.  It is equivalent to the ``-o dax=always`` behavior below.
38 ----------------------------
41 -------
43  1. There exists an in-kernel file access mode flag `S_DAX` that corresponds to
61     ``-o dax=inode``  means "follow `FS_XFLAG_DAX`" and is the default.
63     ``-o dax=never``  means "never set `S_DAX`, ignore `FS_XFLAG_DAX`."
65     ``-o dax=always`` means "always set `S_DAX` ignore `FS_XFLAG_DAX`."
67     ``-o dax``      is a legacy option which is an alias for ``dax=always``.
71       The option ``-o dax`` may be removed in the future so ``-o dax=always`` is
78       in-core inode state (`S_DAX`) will be overridden until the filesystem is
98 -------
100 There are 2 per-file dax flags.  One is a persistent inode setting (`FS_XFLAG_DAX`)
111 sub-tree.
117 .. code-block:: shell
119   mkdir -p a/b/c
120   xfs_io -c 'chattr +x' a
122   mkdir a/e
124   ------[outcome]------
126   dax: a,e
131 .. code-block:: shell
134   xfs_io -c 'chattr +x' a
135   mkdir -p a/b/c/d
137   ------[outcome]------
144 .. code-block:: shell
146   mkdir -p a/b/c
147   xfs_io -c 'chattr +x' c
150   ------[outcome]------
172 ----------------------------
174 except that when '-o dax=inode' is specified, virtiofs client derives the hint
175 whether DAX shall be enabled or not from virtiofs server through FUSE protocol,
178 server itself may deploy various algorithm making this decision, e.g. depending
188 --------------------------------------------
192 (expressed in units of 512-byte sectors) to a page frame number (pfn)
201 In order to support this method, the storage must be byte-accessible by
209 - brd: RAM backed block device driver
210 - dcssblk: s390 dcss block device driver
211 - pmem: NVDIMM persistent memory driver
215 ------------------------------------------
221 * Implementing ->read_iter and ->write_iter operations which use
245   xfs:  see Documentation/admin-guide/xfs.rst
253 ---------------------
256 each pmem block device (in gendisk->badblocks). If we fault at such location,
271 2. Truncate or hole-punch the part of the file that has a bad-block (at least
272    an entire aligned sector has to be hole-punched, but not necessarily an
285 ------------
299 those memory ranges from a non-`DAX` file will fail