* acpi-numa:
docs: mm: numaperf.rst Add brief description for access class 1.
node: Add access1 class to represent CPU to memory characteristics
ACPI: HMAT: Fix handling of changes from ACPI 6.2 to ACPI 6.3
ACPI: Let ACPI know we support Generic Initiator Affinity Structures
x86: Support Generic Initiator only proximity domains
ACPI: Support Generic Initiator only domains
ACPI / NUMA: Add stub function for pxm_to_node()
irq-chip/gic-v3-its: Fix crash if ITS is in a proximity domain without processor or memory
ACPI: Remove side effect of partly creating a node in acpi_get_node()
ACPI: Rename acpi_map_pxm_to_online_node() to pxm_to_online_node()
ACPI: Remove side effect of partly creating a node in acpi_map_pxm_to_online_node()
ACPI: Do not create new NUMA domains from ACPI static tables that are not SRAT
ACPI: Add out of bounds and numa_off protections to pxm_to_node()
As this function is no longer allowed to create new mappings
let us rename it to reflect this.
Note all nodes should already exist before any of the users
of this function are called.
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Hanjun Guo <guohanjun@huawei.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Several ACPI static tables contain references to proximity domains.
ACPI 6.3 has clarified that only entries in SRAT may define a new
domain (sec 5.2.16).
Those tables described in the ACPI spec have additional clarifying text.
NFIT: Table 5-132,
"Integer that represents the proximity domain to which the memory
belongs. This number must match with corresponding entry in the
SRAT table."
HMAT: Table 5-145,
"... This number must match with the corresponding entry in the SRAT
table's processor affinity structure ... if the initiator is a processor,
or the Generic Initiator Affinity Structure if the initiator is a generic
initiator".
IORT and DMAR are defined by external specifications.
Intel Virtualization Technology for Directed I/O Rev 3.1 does not make any
explicit statements, but the general SRAT statement above will still apply.
https://software.intel.com/sites/default/files/managed/c5/15/vt-directed-io-spec.pdf
IO Remapping Table, Platform Design Document rev D, also makes not explicit
statement, but refers to ACPI SRAT table for more information and again the
generic SRAT statement above applies.
https://developer.arm.com/documentation/den0049/d/
In conclusion, any proximity domain specified in these tables, should be a
reference to a proximity domain also found in SRAT, and they should not be
able to instantiate a new domain. Hence we switch to pxm_to_node() which
will only return existing nodes.
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Barry Song <song.bao.hua@hisilicon.com>
Reviewed-by: Hanjun Guo <guohanjun@huawei.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Use kobj_to_dev() instead of container_of()
Signed-off-by: Wang Qing <wangqing@vivo.com>
Acked-by: Vishal Verma <vishal.l.verma@intel.com>
[ rjw: Subject edits ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Pending commit in -next "devres: handle zero size in devm_kmalloc()"
triggers a boot regression due to the ARS implementation expecting NULL
from a zero-sized allocation. Avoid the zero-sized allocation by
skipping ARS, otherwise crashes with the following signature when
de-referencing ZERO_SIZE_PTR.
BUG: kernel NULL pointer dereference, address: 0000000000000018
#PF: supervisor read access in kernel mode
#PF: error_code(0x0000) - not-present page
RIP: 0010:__acpi_nfit_scrub+0x28a/0x350 [nfit]
[..]
Call Trace:
? acpi_nfit_query_poison+0x6a/0x180 [nfit]
acpi_nfit_scrub+0x36/0xb0 [nfit]
process_one_work+0x23c/0x580
worker_thread+0x50/0x3b0
Otherwise the implementation correctly aborts when NULL is returned from
devm_kzalloc() in ars_status_alloc().
Link: https://lore.kernel.org/r/159624590643.3037264.14157533719042907758.stgit@dwillia2-desk3.amr.corp.intel.com
Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: Ira Weiny <ira.weiny@intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Vishal Verma <vishal.l.verma@intel.com>
Plumb the platform specific backend for the generic libnvdimm firmware
activate interface. Register dimm level operations to arm/disarm
activation, and register bus level operations to report the dynamic
platform-quiesce time relative to the number of dimms armed for firmware
activation.
A new nfit-specific bus attribute "firmware_activate_noidle" is added to
allow the activation to switch between platform enforced, and OS
opportunistic device quiesce. In other words, let the hibernate cycle
handle in-flight device-dma rather than the platform attempting to
increase PCI-E timeouts and the like.
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: Ira Weiny <ira.weiny@intel.com>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Vishal Verma <vishal.l.verma@intel.com>
Platform reboots are expensive. Towards reducing downtime to apply
firmware updates the Intel NVDIMM command definition is growing support
for applying live firmware updates that only require temporarily
suspending memory traffic instead of a full reboot.
Follow-on commits add support for triggering firmware activation, this
patch only defines the commands, adds probe support, and validates that
they are blocked via the ioctl path. The ioctl-path block ensures that
the OS is in charge since these commands have side effects only the OS
can handle. Specifically firmware activation may cause the memory
controller to be quiesced on the order of 100s of milliseconds. In that
case Linux ensure the activation only takes place while the OS is in a
suspend state.
Link: https://pmem.io/documents/IntelOptanePMem_DSM_Interface-V2.0.pdf
Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: Ira Weiny <ira.weiny@intel.com>
Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Cc: Len Brown <lenb@kernel.org>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Vishal Verma <vishal.l.verma@intel.com>
DSMs are strictly an ACPI mechanism, evict the bus_dsm_mask concept from
the generic 'struct nvdimm_bus_descriptor' object.
As a side effect the test facility ->bus_nfit_cmd_force_en is no longer
necessary. The test infrastructure can communicate that information
directly in ->bus_dsm_mask.
Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: Ira Weiny <ira.weiny@intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Vishal Verma <vishal.l.verma@intel.com>
The ND_CMD_CALL format allows for a general passthrough of passlisted
commands targeting a given command set. However there is no validation
of the family index relative to what the bus supports.
- Update the NFIT bus implementation (the only one that supports
ND_CMD_CALL passthrough) to also passlist the valid set of command
family indices.
- Update the generic __nd_ioctl() path to validate that field on behalf
of all implementations.
Fixes: 31eca76ba2 ("nfit, libnvdimm: limited/whitelisted dimm command marshaling mechanism")
Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: Ira Weiny <ira.weiny@intel.com>
Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Cc: Len Brown <lenb@kernel.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Vishal Verma <vishal.l.verma@intel.com>
There is a specific API to treat raw data as GUID, i.e. import_guid().
Use it instead of guid_copy() with explicit casting.
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Link: https://lore.kernel.org/r/20200422130539.45636-1-andriy.shevchenko@linux.intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Pick up some miscellaneous minor fixes, that missed v5.6-final,
including a some smatch reports in the ioctl path and some unit test
compilation fixups.
The NDD_ALIASING flag is used to indicate where pmem capacity might
alias with blk capacity and require labeling. It is also used to
indicate whether the DIMM supports labeling. Separate this latter
capability into its own flag so that the NDD_ALIASING flag is scoped to
true aliased configurations.
To my knowledge aliased configurations only exist in the ACPI spec,
there are no known platforms that ship this support in production.
This clarity allows namespace-capacity alignment constraints around
interleave-ways to be relaxed.
Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: Oliver O'Halloran <oohall@gmail.com>
Reviewed-by: Jeff Moyer <jmoyer@redhat.com>
Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Link: https://lore.kernel.org/r/158041477856.3889308.4212605617834097674.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
The 'func' variable can come from the user in the __nd_ioctl(). If it's
too high then the (1 << func) shift in acpi_nfit_clear_to_send() is
undefined. In acpi_nfit_ctl() we pass 'func' to test_bit(func, &dsm_mask)
which could result in an out of bounds access.
To fix these issues, I introduced the NVDIMM_CMD_MAX (31) define and
updated nfit_dsm_revid() to use that define as well instead of magic
numbers.
Fixes: 11189c1089 ("acpi/nfit: Fix command-supported detection")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Link: https://lore.kernel.org/r/20200225161927.hvftuq7kjn547fyj@kili.mountain
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
A 'struct device_type' instance can carry default attributes for the
device. Use this facility to remove the export of
nvdimm_bus_attribute_group and put the responsibility on the core rather
than leaf implementations to define this attribute.
Cc: Ira Weiny <ira.weiny@intel.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: "Oliver O'Halloran" <oohall@gmail.com>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Link: https://lore.kernel.org/r/157309903815.1582359.6418211876315050283.stgit@dwillia2-desk3.amr.corp.intel.com
A 'struct device_type' instance can carry default attributes for the
device. Use this facility to remove the export of
nvdimm_attribute_group and put the responsibility on the core rather
than leaf implementations to define this attribute.
Cc: Ira Weiny <ira.weiny@intel.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: "Oliver O'Halloran" <oohall@gmail.com>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Link: https://lore.kernel.org/r/157309903201.1582359.10966209746585062329.stgit@dwillia2-desk3.amr.corp.intel.com
A 'struct device_type' instance can carry default attributes for the
device. Use this facility to remove the export of
nd_mapping_attribute_group and put the responsibility on the core rather
than leaf implementations to define this attribute.
Cc: Ira Weiny <ira.weiny@intel.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: "Oliver O'Halloran" <oohall@gmail.com>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Link: https://lore.kernel.org/r/157309902686.1582359.6749533709859492704.stgit@dwillia2-desk3.amr.corp.intel.com
A 'struct device_type' instance can carry default attributes for the
device. Use this facility to remove the export of
nd_region_attribute_group and put the responsibility on the core rather
than leaf implementations to define this attribute.
Cc: Ira Weiny <ira.weiny@intel.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: "Oliver O'Halloran" <oohall@gmail.com>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Link: https://lore.kernel.org/r/157309902169.1582359.16828508538444551337.stgit@dwillia2-desk3.amr.corp.intel.com
A 'struct device_type' instance can carry default attributes for the
device. Use this facility to remove the export of
nd_numa_attribute_group and put the responsibility on the core rather
than leaf implementations to define this attribute.
Cc: Ira Weiny <ira.weiny@intel.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: "Oliver O'Halloran" <oohall@gmail.com>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Link: https://lore.kernel.org/r/157401269537.43284.14411189404186877352.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
A 'struct device_type' instance can carry default attributes for the
device. Use this facility to remove the export of
nd_device_attribute_group and put the responsibility on the core rather
than leaf implementations to define this attribute.
For regions this creates a new nd_region_attribute_groups[] added to the
per-region device-type instances.
Cc: Ira Weiny <ira.weiny@intel.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: "Oliver O'Halloran" <oohall@gmail.com>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Link: https://lore.kernel.org/r/157309901138.1582359.12909354140826530394.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
We change the locking in this function and forgot to update this error
path so we are accidentally still holding the "dev->lockdep_mutex".
Fixes: 87a30e1f05 ("driver-core, libnvdimm: Let device subsystems add local lockdep coverage")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Acked-by: Dan Williams <dan.j.williams@intel.com>
Cc: 5.3+ <stable@vger.kernel.org> # 5.3+
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
- Fix duplicate device_unregister() calls (multiple threads competing to
do unregister work when scheduling device removal from a sysfs attribute
of the self-same device).
- Fix badblocks registration order bug. Ensure region badblocks are
initialized in advance of namespace registration.
- Fix a deadlock between the bus lock and probe operations.
- Export device-core infrastructure to coordinate async operations via
the device ->dead state.
- Add device-core infrastructure to validate device_lock() usage with
lockdep.
-----BEGIN PGP SIGNATURE-----
iQIcBAABAgAGBQJdO39XAAoJEB7SkWpmfYgCzbEQAJigRJecrz+OyICGmIAeNSy5
hF6Cv+TPuccpnINNaULS7aJStv4Zl/3SxG5GkivKDk11Xs02VrLzv1m3nDxEOVwc
6LwRwcM7U3UtROzI5gjfT5StgBU4xvlQYKiYV5oxAXoQ5amApqbl3NgfH3qmCaXR
QqWhd7v7TiNZ1QWlnmRBw+j0YLbS1dHyaSAf4KZwnL6fVKmqxtfDxny5tG6jdDuq
olPue6nFAA+ebxyAsKR9VQVmcxDwuG0bJ/GUD6IeOQp/Eh6hcv2AfcVjp4Iwn/aM
n1dIXASFwKr6DoOXZgnUbfXMVGzq1qKHPNgzUvtK6SApZlcm+TnyIOfj0/6BNp9q
Bae1RMRwo5Wa5oAQed3CutvUUQAPa5WrW95E0/4T+dkcutkRnxL6akn/c87qQ4nL
F30zpL8U4UdeaJ5maEIqJ/mtAc9deHiFnO/k216+xvDcY3NGqvzY4PsUBAMep8i2
FgoaBr0hmTkb0KTMI858ChQrT+sjqwJIa854g7b4VxrQz93WYPABRK9ZhMSBEJ8b
rGCeNqvvq0G6dSN6e8bS6P/4EEk76nZAJUYKoMYmj3WuwYuY4Sxb86eFIudNeSEe
EqRGaefaZrqEL6LJTHScCk+55BgYSEOrDdip1lSWGdNHjvgZeIOZrgCrqrm/H72c
mkoCAzdA4drQ0D4ZbKrC
=mhIp
-----END PGP SIGNATURE-----
Merge tag 'libnvdimm-fixes-5.3-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm
Pull libnvdimm fixes from Dan Williams:
"A collection of locking and async operations fixes for v5.3-rc2. These
had been soaking in a branch targeting the merge window, but missed
due to a regression hunt. This fixed up version has otherwise been in
-next this past week with no reported issues.
In order to gain confidence in the locking changes the pull also
includes a debug / instrumentation patch to enable lockdep coverage
for libnvdimm subsystem operations that depend on the device_lock for
exclusion. As mentioned in the changelog it is a hack, but it works
and documents the locking expectations of the sub-system in a way that
others can use lockdep to verify. The driver core touches got an ack
from Greg.
Summary:
- Fix duplicate device_unregister() calls (multiple threads competing
to do unregister work when scheduling device removal from a sysfs
attribute of the self-same device).
- Fix badblocks registration order bug. Ensure region badblocks are
initialized in advance of namespace registration.
- Fix a deadlock between the bus lock and probe operations.
- Export device-core infrastructure to coordinate async operations
via the device ->dead state.
- Add device-core infrastructure to validate device_lock() usage with
lockdep"
* tag 'libnvdimm-fixes-5.3-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm:
driver-core, libnvdimm: Let device subsystems add local lockdep coverage
libnvdimm/bus: Fix wait_nvdimm_bus_probe_idle() ABBA deadlock
libnvdimm/bus: Stop holding nvdimm_bus_list_mutex over __nd_ioctl()
libnvdimm/bus: Prepare the nd_ioctl() path to be re-entrant
libnvdimm/region: Register badblocks before namespaces
libnvdimm/bus: Prevent duplicate device_unregister() calls
drivers/base: Introduce kill_device()
For good reason, the standard device_lock() is marked
lockdep_set_novalidate_class() because there is simply no sane way to
describe the myriad ways the device_lock() ordered with other locks.
However, that leaves subsystems that know their own local device_lock()
ordering rules to find lock ordering mistakes manually. Instead,
introduce an optional / additional lockdep-enabled lock that a subsystem
can acquire in all the same paths that the device_lock() is acquired.
A conversion of the NFIT driver and NVDIMM subsystem to a
lockdep-validate device_lock() scheme is included. The
debug_nvdimm_lock() implementation implements the correct lock-class and
stacking order for the libnvdimm device topology hierarchy.
Yes, this is a hack, but hopefully it is a useful hack for other
subsystems device_lock() debug sessions. Quoting Greg:
"Yeah, it feels a bit hacky but it's really up to a subsystem to mess up
using it as much as anything else, so user beware :)
I don't object to it if it makes things easier for you to debug."
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Ira Weiny <ira.weiny@intel.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: Keith Busch <keith.busch@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Link: https://lore.kernel.org/r/156341210661.292348.7014034644265455704.stgit@dwillia2-desk3.amr.corp.intel.com
This patch adds functionality to perform flush from guest
to host over VIRTIO. We are registering a callback based
on 'nd_region' type. virtio_pmem driver requires this special
flush function. For rest of the region types we are registering
existing flush function. Report error returned by host fsync
failure to userspace.
Signed-off-by: Pankaj Gupta <pagupta@redhat.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Based on 1 normalized pattern(s):
this program is free software you can redistribute it and or modify
it under the terms of version 2 of the gnu general public license as
published by the free software foundation this program is
distributed in the hope that it will be useful but without any
warranty without even the implied warranty of merchantability or
fitness for a particular purpose see the gnu general public license
for more details
extracted by the scancode license scanner the SPDX license identifier
GPL-2.0-only
has been chosen to replace the boilerplate/reference in 64 file(s).
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Alexios Zavras <alexios.zavras@intel.com>
Reviewed-by: Allison Randal <allison@lohutok.net>
Cc: linux-spdx@vger.kernel.org
Link: https://lkml.kernel.org/r/20190529141901.894819585@linutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
The dynamic-debug statements for command payload output only get emitted
when the command is not ND_CMD_CALL. Move the output payload dumping
ahead of the early return path for ND_CMD_CALL.
Fixes: 31eca76ba2 ("...whitelisted dimm command marshaling mechanism")
Reported-by: Vishal Verma <vishal.l.verma@intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
* Replace the /sys/class/dax device model with /sys/bus/dax, and include
a compat driver so distributions can opt-in to the new ABI.
* Allow for an alternative driver for the device-dax address-range
* Introduce the 'kmem' driver to hotplug / assign a device-dax
address-range to the core-mm.
* Arrange for the device-dax target-node to be onlined so that the newly
added memory range can be uniquely referenced by numa apis.
-----BEGIN PGP SIGNATURE-----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=hfa3
-----END PGP SIGNATURE-----
Merge tag 'devdax-for-5.1' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm
Pull device-dax updates from Dan Williams:
"New device-dax infrastructure to allow persistent memory and other
"reserved" / performance differentiated memories, to be assigned to
the core-mm as "System RAM".
Some users want to use persistent memory as additional volatile
memory. They are willing to cope with potential performance
differences, for example between DRAM and 3D Xpoint, and want to use
typical Linux memory management apis rather than a userspace memory
allocator layered over an mmap() of a dax file. The administration
model is to decide how much Persistent Memory (pmem) to use as System
RAM, create a device-dax-mode namespace of that size, and then assign
it to the core-mm. The rationale for device-dax is that it is a
generic memory-mapping driver that can be layered over any "special
purpose" memory, not just pmem. On subsequent boots udev rules can be
used to restore the memory assignment.
One implication of using pmem as RAM is that mlock() no longer keeps
data off persistent media. For this reason it is recommended to enable
NVDIMM Security (previously merged for 5.0) to encrypt pmem contents
at rest. We considered making this recommendation an actively enforced
requirement, but in the end decided to leave it as a distribution /
administrator policy to allow for emulation and test environments that
lack security capable NVDIMMs.
Summary:
- Replace the /sys/class/dax device model with /sys/bus/dax, and
include a compat driver so distributions can opt-in to the new ABI.
- Allow for an alternative driver for the device-dax address-range
- Introduce the 'kmem' driver to hotplug / assign a device-dax
address-range to the core-mm.
- Arrange for the device-dax target-node to be onlined so that the
newly added memory range can be uniquely referenced by numa apis"
NOTE! I'm not entirely happy with the whole "PMEM as RAM" model because
we currently have special - and very annoying rules in the kernel about
accessing PMEM only with the "MC safe" accessors, because machine checks
inside the regular repeat string copy functions can be fatal in some
(not described) circumstances.
And apparently the PMEM modules can cause that a lot more than regular
RAM. The argument is that this happens because PMEM doesn't necessarily
get scrubbed at boot like RAM does, but that is planned to be added for
the user space tooling.
Quoting Dan from another email:
"The exposure can be reduced in the volatile-RAM case by scanning for
and clearing errors before it is onlined as RAM. The userspace tooling
for that can be in place before v5.1-final. There's also runtime
notifications of errors via acpi_nfit_uc_error_notify() from
background scrubbers on the DIMM devices. With that mechanism the
kernel could proactively clear newly discovered poison in the volatile
case, but that would be additional development more suitable for v5.2.
I understand the concern, and the need to highlight this issue by
tapping the brakes on feature development, but I don't see PMEM as RAM
making the situation worse when the exposure is also there via DAX in
the PMEM case. Volatile-RAM is arguably a safer use case since it's
possible to repair pages where the persistent case needs active
application coordination"
* tag 'devdax-for-5.1' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm:
device-dax: "Hotplug" persistent memory for use like normal RAM
mm/resource: Let walk_system_ram_range() search child resources
mm/memory-hotplug: Allow memory resources to be children
mm/resource: Move HMM pr_debug() deeper into resource code
mm/resource: Return real error codes from walk failures
device-dax: Add a 'modalias' attribute to DAX 'bus' devices
device-dax: Add a 'target_node' attribute
device-dax: Auto-bind device after successful new_id
acpi/nfit, device-dax: Identify differentiated memory with a unique numa-node
device-dax: Add /sys/class/dax backwards compatibility
device-dax: Add support for a dax override driver
device-dax: Move resource pinning+mapping into the common driver
device-dax: Introduce bus + driver model
device-dax: Start defining a dax bus model
device-dax: Remove multi-resource infrastructure
device-dax: Kill dax_region base
device-dax: Kill dax_region ida
Merge several updates to the ARS implementation. Highlights include:
* Support retrieval of short-ARS results if the ARS state is "requires
continuation", and even if the "no_init_ars" module parameter is
specified.
* Allow busy-polling of the kernel ARS state by allowing root to reset
the exponential back-off timer.
* Filter potentially stale ARS results by tracking query-ARS relative to
the previous start-ARS.
Merge miscellaneous libnvdimm sub-system updates for v5.1. Highlights
include:
* Support for the Hyper-V family of device-specific-methods (DSMs)
* Several fixes and workarounds for Hyper-V compatibility.
* Fix for the support to cache the dirty-shutdown-count at init.
ACPI NFIT flags field reports major errors on NVDIMM, which need
user's attention.
Update the current log to a proper error message with dev_err().
The current message string is kept for grep-compatibility.
Signed-off-by: Toshi Kani <toshi.kani@hpe.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Cc: Robert Elliott <elliott@hpe.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Gate ARS result consumption on whether the OS issued start-ARS since the
previous consumption. The BIOS may only clear its result buffers after a
successful start-ARS.
Fixes: 0caeef63e6 ("libnvdimm: Add a poison list and export badblocks")
Cc: <stable@vger.kernel.org>
Reported-by: Krzysztof Rusocki <krzysztof.rusocki@intel.com>
Reported-by: Vishal Verma <vishal.l.verma@intel.com>
Reviewed-by: Toshi Kani <toshi.kani@hpe.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
The ARS implementation implements exponential back-off on the poll
interval to prevent high-frequency access to the DIMM / platform
interface. Depending on when the ARS completes the poll interval may
exceed the completion event by minutes. Allow root to reset the timeout
each time it probes the status. A one-second timeout is still enforced,
but root can otherwise can control the poll interval.
Fixes: bc6ba80858 ("nfit, address-range-scrub: rework and simplify ARS...")
Cc: <stable@vger.kernel.org>
Reported-by: Erwin Tsaur <erwin.tsaur@oracle.com>
Reviewed-by: Toshi Kani <toshi.kani@hpe.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
In preparation for introducing new flags to gate whether ARS results are
stale, or poll the completion state, convert the existing flags to an
unsigned long with enumerated values. This conversion allows the flags
to be atomically updated outside of ->init_mutex.
Reviewed-by: Toshi Kani <toshi.kani@hpe.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
The ars_start_flags property of 'struct acpi_nfit_desc' is no longer
used since ARS_REQ_SHORT and ARS_REQ_LONG were added.
Reviewed-by: Toshi Kani <toshi.kani@hpe.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
The no_init_ars option is meant to prevent long-ARS, but short-ARS
should be allowed to grab any immediate results.
Fixes: bc6ba80858 ("nfit, address-range-scrub: rework and simplify ARS...")
Cc: <stable@vger.kernel.org>
Reported-by: Erwin Tsaur <erwin.tsaur@oracle.com>
Reviewed-by: Toshi Kani <toshi.kani@hpe.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
If query-ARS reports that ARS has stopped and requires continuation
attempt to retrieve short-ARS results before continuing the long
operation.
Fixes: bc6ba80858 ("nfit, address-range-scrub: rework and simplify ARS...")
Cc: <stable@vger.kernel.org>
Reported-by: Krzysztof Rusocki <krzysztof.rusocki@intel.com>
Reviewed-by: Toshi Kani <toshi.kani@hpe.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Recent fixes to command handling enabled Linux to read label
configurations that it could not before. Unfortunately that means that
configurations that were operating in label-less mode will be broken as
the kernel ignores the existing namespace configuration and tries to
honor the new found labels.
Fortunately this seems limited to a case where Linux can quirk the
behavior and maintain the existing label-less semantics by default.
When the platform does not emit an _LSW method, disable all label access
methods. Provide a 'force_labels' module parameter to allow read-only
label operation.
Fixes: 11189c1089 ("acpi/nfit: Fix command-supported detection")
Reported-by: Dexuan Cui <decui@microsoft.com>
Reviewed-by: Dexuan Cui <decui@microsoft.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Commit 11189c1089 "acpi/nfit: Fix command-supported detection" broke
ND_CMD_CALL for bus-level commands. The "func = cmd" assumption is only
valid for:
ND_CMD_ARS_CAP
ND_CMD_ARS_START
ND_CMD_ARS_STATUS
ND_CMD_CLEAR_ERROR
The function number otherwise needs to be pulled from the command
payload for:
NFIT_CMD_TRANSLATE_SPA
NFIT_CMD_ARS_INJECT_SET
NFIT_CMD_ARS_INJECT_CLEAR
NFIT_CMD_ARS_INJECT_GET
Update cmd_to_func() for the bus case and call it in the common path.
Fixes: 11189c1089 ("acpi/nfit: Fix command-supported detection")
Cc: <stable@vger.kernel.org>
Reviewed-by: Vishal Verma <vishal.l.verma@intel.com>
Reported-by: Grzegorz Burzynski <grzegorz.burzynski@intel.com>
Tested-by: Jeff Moyer <jmoyer@redhat.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
As Dexuan reports the NVDIMM_FAMILY_HYPERV platform is incompatible with
the existing Linux namespace implementation because it uses
NSLABEL_FLAG_LOCAL for x1-width PMEM interleave sets. Quirk it as an
platform / DIMM that does not provide BLK-aperture access. Allow the
libnvdimm core to assume no potential for aliasing. In case other
implementations make the same mistake, provide a "noblk" module
parameter to force-enable the quirk.
Link: https://lkml.kernel.org/r/PU1P153MB0169977604493B82B662A01CBF920@PU1P153MB0169.APCP153.PROD.OUTLOOK.COM
Reported-by: Dexuan Cui <decui@microsoft.com>
Tested-by: Dexuan Cui <decui@microsoft.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Add the Hyper-V _DSM command set to the white list of NVDIMM command
sets.
This command set is documented at http://www.uefi.org/RFIC_LIST
(see "Virtual NVDIMM 0x1901").
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
In the case of ND_CMD_CALL, we should also check out_obj->type.
The patch uses out_obj->type, which is a short alias to
out_obj->package.type.
Fixes: 31eca76ba2 ("nfit, libnvdimm: limited/whitelisted dimm command marshaling mechanism")
Cc: <stable@vger.kernel.org>
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
The implementation is broken in all the ways the unit test did not touch:
1/ The local definition of in_buf and in_obj violated C99 initializer
expectations for zeroing. By only initializing 2 out of the three
struct members the compiler was free to zero-initialize the remaining
entry even though the aliased location in the union was initialized.
2/ The implementation made assumptions about the state of the 'smart'
payload after command execution that are satisfied by
acpi_nfit_ctl(), but not acpi_evaluate_dsm().
3/ populate_shutdown_status() is skipped on Intel NVDIMMs due to the early
return for skipping the common _LS{I,R,W} enabling.
4/ The input length should be zero.
This breakage was missed due to the unit test implementation only
testing the case where nfit_intel_shutdown_status() returns a valid
payload.
Much of this complexity would be saved if acpi_nfit_ctl() could be used, but
that currently requires a 'struct nvdimm *' argument and one is not created
until later in the init process. The health result is needed before the device
is created because the payload gates whether the nmemX/nfit/dirty_shutdown
property is visible in sysfs.
Cc: <stable@vger.kernel.org>
Fixes: 0ead11181f ("acpi, nfit: Collect shutdown status")
Reported-by: Dexuan Cui <decui@microsoft.com>
Reviewed-by: Dexuan Cui <decui@microsoft.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
The _DSM function number validation only happens to succeed when the
generic Linux command number translation corresponds with a
DSM-family-specific function number. This breaks NVDIMM-N
implementations that correctly implement _LSR, _LSW, and _LSI, but do
not happen to publish support for DSM function numbers 4, 5, and 6.
Recall that the support for _LS{I,R,W} family of methods results in the
DIMM being marked as supporting those command numbers at
acpi_nfit_register_dimms() time. The DSM function mask is only used for
ND_CMD_CALL support of non-NVDIMM_FAMILY_INTEL devices.
Fixes: 31eca76ba2 ("nfit, libnvdimm: limited/whitelisted dimm command...")
Cc: <stable@vger.kernel.org>
Link: https://github.com/pmem/ndctl/issues/78
Reported-by: Sujith Pandel <sujith_pandel@dell.com>
Tested-by: Sujith Pandel <sujith_pandel@dell.com>
Reviewed-by: Vishal Verma <vishal.l.verma@intel.com>
Reviewed-by: Jeff Moyer <jmoyer@redhat.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
In preparation for using function number 0 as an error value, prevent it
from being considered a valid function value by acpi_nfit_ctl().
Cc: <stable@vger.kernel.org>
Cc: stuart hayes <stuart.w.hayes@gmail.com>
Fixes: e02fb7264d ("nfit: add Microsoft NVDIMM DSM command set...")
Reported-by: Jeff Moyer <jmoyer@redhat.com>
Reviewed-by: Jeff Moyer <jmoyer@redhat.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
The following warning:
ACPI0012:00: security event setup failed: -19
...is meant to capture exceptional failures of sysfs_get_dirent(),
however it will also fail in the common case when security support is
disabled. A few issues:
1/ A dev_warn() report for a common case is too chatty
2/ The setup of this notifier is generic, no need for it to be driven
from the nfit driver, it can exist completely in the core.
3/ If it fails for any reason besides security support being disabled,
that's fatal and should abort DIMM activation. Userspace may hang if
it never gets overwrite notifications.
4/ The dirent needs to be released.
Move the call to the core 'dimm' driver, make it conditional on security
support being active, make it fatal for the exceptional case, add the
missing sysfs_put() at device disable time.
Fixes: 7d988097c5 ("...Add security DSM overwrite support")
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
We allocate nd_set in acpi_nfit_init_interleave_set() and assignn it to
ndr_desc, while the assignment is done twice in this function.
This patch removes the first assignment. No functional change.
Signed-off-by: Wei Yang <richardw.yang@linux.intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Possible race accessing memdev structures after dropping the
mutex. Dan Williams says this could race against another thread
that is doing:
# echo "ACPI0012:00" > /sys/bus/acpi/drivers/nfit/unbind
Reported-by: Jane Chu <jane.chu@oracle.com>
Fixes: 23222f8f8d ("acpi, nfit: Add function to look up nvdimm...")
Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
The function to_acpi_nfit_desc and function to_acpi_desc
do the same things,delete the function to_acpi_nfit_desc,
and keep the inline function to_acpi_desc.
Signed-off-by: Xiaochun Lee <lixc17@lenovo.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
The header file "intel.h" is repeated here, So delete one.
Signed-off-by: Xiaochun Lee <lixc17@lenovo.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Persistent memory, as described by the ACPI NFIT (NVDIMM Firmware
Interface Table), is the first known instance of a memory range
described by a unique "target" proximity domain. Where "initiator" and
"target" proximity domains is an approach that the ACPI HMAT
(Heterogeneous Memory Attributes Table) uses to described the unique
performance properties of a memory range relative to a given initiator
(e.g. CPU or DMA device).
Currently the numa-node for a /dev/pmemX block-device or /dev/daxX.Y
char-device follows the traditional notion of 'numa-node' where the
attribute conveys the closest online numa-node. That numa-node attribute
is useful for cpu-binding and memory-binding processes *near* the
device. However, when the memory range backing a 'pmem', or 'dax' device
is onlined (memory hot-add) the memory-only-numa-node representing that
address needs to be differentiated from the set of online nodes. In
other words, the numa-node association of the device depends on whether
you can bind processes *near* the cpu-numa-node in the offline
device-case, or bind process *on* the memory-range directly after the
backing address range is onlined.
Allow for the case that platform firmware describes persistent memory
with a unique proximity domain, i.e. when it is distinct from the
proximity of DRAM and CPUs that are on the same socket. Plumb the Linux
numa-node translation of that proximity through the libnvdimm region
device to namespaces that are in device-dax mode. With this in place the
proposed kmem driver [1] can optionally discover a unique numa-node
number for the address range as it transitions the memory from an
offline state managed by a device-driver to an online memory range
managed by the core-mm.
[1]: https://lore.kernel.org/lkml/20181022201317.8558C1D8@viggo.jf.intel.com
Reported-by: Fan Du <fan.du@intel.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: "Oliver O'Halloran" <oohall@gmail.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Jérôme Glisse <jglisse@redhat.com>
Reviewed-by: Yang Shi <yang.shi@linux.alibaba.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
* Use common helpers, bitmap_zalloc() and kstrndup(), to replace open
coded versions.
* Clarify the comments around hotplug vs initial init case for the nfit
driver.
* Cleanup the libnvdimm init path.
