The ndctl unit tests discovered that the dax enabling omitted updates to
nd_detach_and_reset().  This routine clears device the configuration
when the namespace is detached.  Without this clearing userspace may
assume that the device is in the process of being configured by another
agent in the system.
Signed-off-by: Dan Williams <dan.j.williams@intel.com>

Testing the dax-device autodetect support revealed a probe failure with
the following result:

    dax0.1: bad offset: 0x8200000 dax disabled

The original pfn-device implementation inferred the alignment from
ilog2(offset), now that the alignment is explicit the is_power_of_2()
needs replacing with a real sanity check against the recorded alignment.
Otherwise the alignment check is useless in the implicit case and only
the minimum size of the offset matters.

This self-consistency check is further validated by the probe path that
will re-check that the offset is large enough to contain all the
metadata required to enable the device.

Cc: <stable@vger.kernel.org>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>

For autodetecting a previously established dax configuration we need the
info block to indicate block-device vs device-dax mode, and we need to
have the default namespace probe hand-off the configuration to the
dax_pmem driver.
Signed-off-by: Dan Williams <dan.j.williams@intel.com>

ida instances allocate some internal memory for ->free_bitmap in
addition to the base 'struct ida'.  Use ida_destroy() to release that
memory at module_exit().
Reported-by: Johannes Thumshirn <jthumshirn@suse.de>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>

This reverts commit 5a023cdb.

The functionality is superseded by the new "Device DAX" facility.

Cc: Jeff Moyer <jmoyer@redhat.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Ross Zwisler <ross.zwisler@linux.intel.com>
Cc: Jan Kara <jack@suse.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>

The "Device DAX" core enables dax mappings of performance / feature
differentiated memory.  An open mapping or file handle keeps the backing
struct device live, but new mappings are only possible while the device
is enabled.   Faults are handled under rcu_read_lock to synchronize
with the enabled state of the device.

Similar to the filesystem-dax case the backing memory may optionally
have struct page entries.  However, unlike fs-dax there is no support
for private mappings, or mappings that are not backed by media (see
use of zero-page in fs-dax).

Mappings are always guaranteed to match the alignment of the dax_region.
If the dax_region is configured to have a 2MB alignment, all mappings
are guaranteed to be backed by a pmd entry.  Contrast this determinism
with the fs-dax case where pmd mappings are opportunistic.  If userspace
attempts to force a misaligned mapping, the driver will fail the mmap
attempt.  See dax_dev_check_vma() for other scenarios that are rejected,
like MAP_PRIVATE mappings.

Cc: Hannes Reinecke <hare@suse.de>
Cc: Jeff Moyer <jmoyer@redhat.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Ross Zwisler <ross.zwisler@linux.intel.com>
Acked-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>

Device DAX is the device-centric analogue of Filesystem DAX
(CONFIG_FS_DAX).  It allows memory ranges to be allocated and mapped
without need of an intervening file system.  Device DAX is strict,
precise and predictable.  Specifically this interface:

1/ Guarantees fault granularity with respect to a given page size (pte,
pmd, or pud) set at configuration time.

2/ Enforces deterministic behavior by being strict about what fault
scenarios are supported.

For example, by forcing MADV_DONTFORK semantics and omitting MAP_PRIVATE
support device-dax guarantees that a mapping always behaves/performs the
same once established.  It is the "what you see is what you get" access
mechanism to differentiated memory vs filesystem DAX which has
filesystem specific implementation semantics.

Persistent memory is the first target, but the mechanism is also
targeted for exclusive allocations of performance differentiated memory
ranges.

This commit is limited to the base device driver infrastructure to
associate a dax device with pmem range.

Cc: Jeff Moyer <jmoyer@redhat.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Ross Zwisler <ross.zwisler@linux.intel.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>

The dax_pmem driver was implementing an empty ->remove() method to
satisfy the nvdimm bus driver that unconditionally calls ->remove().
Teach the core bus driver to check if ->remove() is NULL to remove that
requirement.
Reported-by: Johannes Thumshirn <jthumshirn@suse.de>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>

We want to use the alignment as the allocation and mapping unit.
Previously this information was only useful for establishing the data
offset, but now it is important to remember the granularity for the
later use.
Signed-off-by: Dan Williams <dan.j.williams@intel.com>

We may want to subdivide a device-dax range into multiple devices so
that each can have separate permissions or naming.  Reserve 128K of
label space by default so we have the capability of making allocation
decisions persistent.  This reservation is not something we can add
later since it would result in the default size of a device-dax range
changing between kernel versions.
Signed-off-by: Dan Williams <dan.j.williams@intel.com>

Device DAX is the device-centric analogue of Filesystem DAX
(CONFIG_FS_DAX).  It allows persistent memory ranges to be allocated and
mapped without need of an intervening file system.  This initial
infrastructure arranges for a libnvdimm pfn-device to be represented as
a different device-type so that it can be attached to a driver other
than the pmem driver.
Signed-off-by: Dan Williams <dan.j.williams@intel.com>

I had relied on the kbuild robot for cross build coverage, however it
only builds alpha_defconfig.  Switch from HPAGE_SIZE to PMD_SIZE, which
is more widely defined.

Fixes: 658922e5 ("libnvdimm, pfn: fix memmap reservation sizing")
Cc: <stable@vger.kernel.org>
Reported-by: Guenter Roeck <guenter@roeck-us.net>
Tested-by: Guenter Roeck <guenter@roeck-us.net>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>

Communicate the command format and supported functions to userspace
tooling.
Signed-off-by: Dan Williams <dan.j.williams@intel.com>

Enable nfit_test to use nd_cmd_pkg marshaling.
Signed-off-by: Dan Williams <dan.j.williams@intel.com>

Module option to limit userspace to the publicly defined command set.
For cases where private DIMM commands may be interfering with the
kernel's handling of DIMM state this option can be set to block vendor
specific commands.

Cc: Jerry Hoemann <jerry.hoemann@hpe.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>

When transportation of the command completes successfully, it indicates
that the 'status' result is valid.  Fix the missed checking and
translation of the status field at the end of acpi_nfit_ctl().
Otherwise, we fail to handle reported errors and assume commands
complete successfully.
Reported-by: Linda Knippers <linda.knippers@hpe.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>

When configuring a pfn-device instance to allocate the memmap array it
needs to account for the fact that vmemmap_populate_hugepages()
allocates struct page blocks in HPAGE_SIZE chunks.  We need to align the
reserved area size to 2MB otherwise arch_add_memory() runs out of memory
while establishing the memmap:

 WARNING: CPU: 0 PID: 496 at arch/x86/mm/init_64.c:704 arch_add_memory+0xe7/0xf0
 [..]
 Call Trace:
  [<ffffffff8148bdb3>] dump_stack+0x85/0xc2
  [<ffffffff810a749b>] __warn+0xcb/0xf0
  [<ffffffff810a75cd>] warn_slowpath_null+0x1d/0x20
  [<ffffffff8106a497>] arch_add_memory+0xe7/0xf0
  [<ffffffff811d2097>] devm_memremap_pages+0x287/0x450
  [<ffffffff811d1ffa>] ? devm_memremap_pages+0x1ea/0x450
  [<ffffffffa0000298>] __wrap_devm_memremap_pages+0x58/0x70 [nfit_test_iomap]
  [<ffffffffa0047a58>] pmem_attach_disk+0x318/0x420 [nd_pmem]
  [<ffffffffa0047bcf>] nd_pmem_probe+0x6f/0x90 [nd_pmem]
  [<ffffffffa0009469>] nvdimm_bus_probe+0x69/0x110 [libnvdimm]
 [..]
  ndbus0: nd_pmem.probe(pfn3.0) = -12
 nd_pmem: probe of pfn3.0 failed with error -12
libndctl: ndctl_pfn_enable: pfn3.0: failed to enable
Reported-by: Namratha Kothapalli <namratha.n.kothapalli@intel.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>

Similar to pci-sysfs export the subsystem information available in the
NFIT.  ACPI 6.1 clarifies that this data is copied as an array of bytes
from the DIMM SPD data.
Reported-by: Ryon Jensen <ryon.jensen@intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>

ACPI6.1 clarifies that DCR fields are stored as an array of bytes,
update the format interface code constants to match.
Reviewed-by: Toshi Kani <toshi.kani@hpe.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>

There are currently 4 known similar but incompatible definitions of the
command sets that can be sent to an NVDIMM through ACPI.  It is also
clear that future platform generations (ACPI or not) will continue to
revise and extend the DIMM command set as new devices and use cases
arrive.

It is obviously untenable to continue to proliferate divergence
of these command definitions, and to that end a standardization process
has begun to provide for a unified specification.  However, that leaves a
problem about what to do with this first generation where vendors are
already shipping divergence.

The Linux kernel can support these initial diverged platforms without
giving platform-firmware free reign to continue to diverge and compound
kernel maintenance overhead.  The kernel implementation can encourage
standardization in two ways:

1/ Require that any function code that userspace wants to send be
   explicitly white-listed in the implementation.  For ACPI this means
   function codes marked as supported by acpi_check_dsm() may
   only be invoked if they appear in the white-list.  A function must be
   publicly documented before it is added to the white-list.

2/ The above restrictions can be trivially bypassed by using the
   "vendor-specific" payload command.  However, since vendor-specific
   commands are by definition not publicly documented and have the
   potential to corrupt the kernel's view of the dimm state, we provide a
   toggle to disable vendor-specific operations.  Enabling undefined
   behavior is a policy decision that can be made by the platform owner
   and encourages firmware implementations to choose public over
   private command implementations.

Based on an initial patch from Jerry Hoemann
Cc: Jerry Hoemann <jerry.hoemann@hpe.com>
Cc: Christoph Hellwig <hch@infradead.org>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>

Clarify the distinction between "commands", the ioctls userspace calls
to request the kernel take some action on a given dimm device, and
"_DSMs", the actual function numbers used in the firmware interface to
the DIMM.  _DSMs are ACPI specific whereas commands are Linux kernel
generic.

This is in preparation for breaking the 1:1 implicit relationship
between the kernel ioctl number space and the firmware specific function
numbers.

Cc: Jerry Hoemann <jerry.hoemann@hpe.com>
Cc: Christoph Hellwig <hch@infradead.org>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>

nd_ioctl() must first read in the fixed sized portion of an ioctl so
that it can then determine the size of the variable part.

Prepare for ND_CMD_CALL calls which have larger fixed portion
envelope.
Signed-off-by: Jerry Hoemann <jerry.hoemann@hpe.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>

ACPI 6.1, section 5.2.25.9, defines an identifier for an NVDIMM.

Change the NFIT driver to add a new sysfs file "id" under nfit
directory.
Signed-off-by: Toshi Kani <toshi.kani@hpe.com>
Cc: Rafael J. Wysocki <rjw@rjwysocki.net>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Robert Moore <robert.moore@intel.com>
Cc: Robert Elliott <elliott@hpe.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>

ACPI 6.1, Table 5-133, updates NVDIMM Control Region Structure
as follows.
 - Valid Fields, Manufacturing Location, and Manufacturing Date
   are added from reserved range.  No change in the structure size.
 - IDs (SPD values) are stored as arrays of bytes (i.e. big-endian
   format).  The spec clarifies that they need to be represented
   as arrays of bytes as well.

This patch makes the following changes to support this update.
 - Change the NFIT driver to show SPD ID values in big-endian
   format.
 - Change sprintf format to use "0x" instead of "#" since "%#02x"
   does not prepend '0'.

link: http://www.uefi.org/sites/default/files/resources/ACPI_6_1.pdfSigned-off-by: Toshi Kani <toshi.kani@hpe.com>
Cc: Rafael J. Wysocki <rjw@rjwysocki.net>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Robert Moore <robert.moore@intel.com>
Cc: Robert Elliott <elliott@hpe.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>

Pull thermal fixes from Eduardo Valentin:
 "Specifics in this pull request:

   - Fixes in mediatek and OF thermal drivers

   - Fixes in power_allocator governor

   - More fixes of unsigned to int type change in thermal_core.c.

  These change have been CI tested using KernelCI bot. \o/"

* 'fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/evalenti/linux-soc-thermal:
  thermal: fix Mediatek thermal controller build
  thermal: consistently use int for trip temp
  thermal: fix mtk_thermal build dependency
  thermal: minor mtk_thermal.c cleanups
  thermal: power_allocator: req_range multiplication should be a 64 bit type
  thermal: of: add __init attribute

Pull asm-generic update from Arnd Bergmann:
 "Here is one patch to wire up the preadv/pwritev system calls in the
  generic system call table, which is required for all architectures
  that were merged in the last few years, including arm64.

  Usually these get merged along with the syscall implementation or one
  of the architecture trees, but this time that did not happen.

  Andre and Christoph both sent a version of this patch, I picked the
  one I got first"

* tag 'asm-generic-4.6' of git://git.kernel.org/pub/scm/linux/kernel/git/arnd/asm-generic:
  generic syscalls: wire up preadv2 and pwritev2 syscalls

These new syscalls are implemented as generic code, so enable them for
architectures like arm64 which use the generic syscall table.
Signed-off-by: Andre Przywara <andre.przywara@arm.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>

Pull x86 fixes from Ingo Molnar:
 "Misc fixes: two EDAC driver fixes, a Xen crash fix, a HyperV log spam
  fix and a documentation fix"

* 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86 EDAC, sb_edac.c: Take account of channel hashing when needed
  x86 EDAC, sb_edac.c: Repair damage introduced when "fixing" channel address
  x86/mm/xen: Suppress hugetlbfs in PV guests
  x86/doc: Correct limits in Documentation/x86/x86_64/mm.txt
  x86/hyperv: Avoid reporting bogus NMI status for Gen2 instances

Merge branches 'perf-urgent-for-linus', 'smp-urgent-for-linus' and 'timers-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf, cpu hotplug and timer fixes from Ingo Molnar:
 "perf:
   - A single tooling fix for a user-triggerable segfault.

  CPU hotplug:
   - Fix a CPU hotplug corner case regression, introduced by the recent
     hotplug rework

  timers:
   - Fix a boot hang in the ARM based Tango SoC clocksource driver"

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  perf intel-pt: Fix segfault tracing transactions

* 'smp-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  cpu/hotplug: Fix rollback during error-out in __cpu_disable()

* 'timers-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  clocksource/drivers/tango-xtal: Fix boot hang due to incorrect test

Pull locking fixes from Ingo Molnar:
 "Misc fixes:

  pvqspinlocks:
   - an instrumentation fix

  futexes:
   - preempt-count vs pagefault_disable decouple corner case fix
   - futex requeue plist race window fix
   - futex UNLOCK_PI transaction fix for a corner case"

* 'locking-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  asm-generic/futex: Re-enable preemption in futex_atomic_cmpxchg_inatomic()
  futex: Acknowledge a new waiter in counter before plist
  futex: Handle unlock_pi race gracefully
  locking/pvqspinlock: Fix division by zero in qstat_read()

Pull irq fixes from Ingo Molnar:
 "A core irq affinity masks related fix and a MIPS irqchip driver fix"

* 'irq-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  irqchip/mips-gic: Don't overrun pcpu_masks array
  genirq: Dont allow affinity mask to be updated on IPIs

Pull objtool fixes from Ingo Molnar:
 "A handful of objtool fixes: two improvements to how warnings are
  printed plus a false positive warning fix, and build environment fix"

* 'core-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  objtool: Fix Makefile to properly see if libelf is supported
  objtool: Detect falling through to the next function
  objtool: Add workaround for GCC switch jump table bug

Pull USB / PHY driver fixes from Greg KH:
 "Here are two small sets of patches, both from subsystem trees, USB
  gadget and PHY drivers.

  Full details are in the shortlog, and they have all been in linux-next
  for a while (before I merged them to the USB tree)"

* tag 'usb-4.6-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/usb:
  usb: gadget: f_fs: Fix use-after-free
  usb: dwc3: gadget: Fix suspend/resume during device mode
  usb: dwc3: fix memory leak of dwc->regset
  usb: dwc3: core: fix PHY handling during suspend
  usb: dwc3: omap: fix up error path on probe()
  usb: gadget: composite: Clear reserved fields of SSP Dev Cap
  phy: rockchip-emmc: adapt binding to specifiy register offset and length
  phy: rockchip-emmc: should be a child device of the GRF
  phy: rockchip-dp: should be a child device of the GRF

Pull serial fixes from Greg KH:
 "Here are 3 serial driver fixes for issues that have been reported.

  Two are reverts, fixing problems that were in the big TTY/Serial
  driver merge in 4.6-rc1, and the last one is a simple bugfix for a
  regression that showed up in 4.6-rc1 as well.

  All have been in linux-next with no reported issues"

* tag 'tty-4.6-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/tty:
  Revert "serial: 8250: Add hardware dependency to RT288X option"
  tty/serial/8250: fix RS485 half-duplex RX
  Revert "serial-uartlite: Constify uartlite_be/uartlite_le"