The ACPI NFIT specification defines a set of "NVDIMM State Flags". These
flags are already reported by `acpidump -t', but this change makes them
available on a per-device basis, in a format that is more easily parsed.

To simplify this, introduce acpi_nfit_get_memory_maps_by_dimm(), which
locates the (ACPI_NFIT_MEMORY_MAP)s associated with a given
(nfit_handle_t).

Reviewed by:	mav, cem
Tested by:	mav, rpokala (version for stable/12)
MFC after:	3 days
Sponsored by:	Panasas
Differential Revision:	https://reviews.freebsd.org/D28700

(cherry picked from commit bdde49b7c7232c6936525f84ffb90856a7cd8e74)

(diff applied manually due to refactoring)

Regression introduced in r343629 when malloc result was renamed from spa to
spa_mapping and the 'spa' name was instead used to iterate a table, but the
free() target was not updated.

Reviewed by:	kib, scottph
Sponsored by:	Dell EMC Isilon
Differential Revision:	https://reviews.freebsd.org/D21871

(cherry picked from commit 31f1c8fc84c850d73e74781126e12efceb50032b)

__builtin_unreachable doesn't raise any compile-time warnings/errors on its
own, so problems with its usage can't be easily detected. While it would be
nice for this situation to change and compilers to at least add a warning
for trivial cases where local state means the instruction can't be reached,
this isn't the case at the moment and likely will not happen.

This commit adds an __assert_unreachable, whose intent is incredibly clear:
it asserts that this instruction is unreachable. On INVARIANTS builds, it's
a panic(), and on non-INVARIANTS it expands to  __unreachable().

Existing users of __unreachable() are converted to __assert_unreachable,
to improve debuggability if this assumption is violated.

348757:
nvdimm: Provide nvdimm location information

Provide the acpi handle path as the location string for the nvdimm
children of the nvdimm_root device.

351225:
Don't set the string "unknown" as a device's location_str

Return an empty string when the location is unknown instead of the
string "unknown". This ensures that all location entries are of
the form key=val.

Approved by:	scottl (mentor)
Sponsored by:	Intel Corporation
Differential Revision:	https://reviews.freebsd.org/D20644

r344474:
nvdimm: split spa dev into a separate entity

Separate code for exposing a device backed by a system physical
address range away from the NVDIMM spa code. This will allow a
future patch to add support for NVDIMM namespaces while using the
same device code.

Submitted by:	D Scott Phillips <d.scott.phillips@intel.com>
Reviewed by:	bwidawsk
Sponsored by:	Intel Corporation
Differential Revision:	https://reviews.freebsd.org/D18736

r344475:
nvdimm: Read NVDIMM namespace labels

When attaching to NVDIMM devices, read and verify the namespace
labels from the special namespace label storage area. A later
change will expose NVDIMM namespaces derived from this label data.

Submitted by:	D Scott Phillips <d.scott.phillips@intel.com>
Discussed with:	kib
Sponsored by:	Intel Corporation
Differential Revision:	https://reviews.freebsd.org/D18735

r344476:
nvdimm: Simple namespace support

Add support for simple NVDIMM v1.2 namespaces from the UEFI
version 2.7 specification. The combination of NVDIMM regions and
labels can lead to a wide variety of namespace layouts. Here we
support a simple subset of namespaces where each NVDIMM SPA range
is composed of a single region per member dimm.

Submitted by:	D Scott Phillips <d.scott.phillips@intel.com>
Discussed with:	kib
Sponsored by:	Intel Corporation
Differential Revision:	https://reviews.freebsd.org/D18736

nvdimm: only enumerate present nvdimm devices

nvdimm: enumerate NVDIMM SPA ranges from the root device

nvdimm: initialize SPA uuids statically.

nvdimm: add a driver for the NVDIMM root device

nvdimm(4): Fix GCC 6.4.0 build