mirror of
https://mirrors.bfsu.edu.cn/git/linux.git
synced 2024-12-11 13:04:03 +08:00
5ccac54f3e
The hmem enabling in commit cf8741ac57
("ACPI: NUMA: HMAT: Register
"soft reserved" memory as an "hmem" device") only registered ranges to the
hmem driver for each soft-reservation that also appeared in the HMAT.
While this is meant to encourage platform firmware to "do the right thing"
and publish an HMAT, the corollary is that platforms that fail to publish
an accurate HMAT will strand memory from Linux usage. Additionally, the
"efi_fake_mem" kernel command line option enabling will strand memory by
default without an HMAT.
Arrange for "soft reserved" memory that goes unclaimed by HMAT entries to
be published as raw resource ranges for the hmem driver to consume.
Include a module parameter to disable either this fallback behavior, or
the hmat enabling from creating hmem devices. The module parameter
requires the hmem device enabling to have unique name in the module
namespace: "device_hmem".
The driver depends on the architecture providing phys_to_target_node()
which is only x86 via numa_meminfo() and arm64 via a generic memblock
implementation.
[joao.m.martins@oracle.com: require NUMA_KEEP_MEMINFO for phys_to_target_node()]
Link: https://lkml.kernel.org/r/aaae71a7-4846-f5cc-5acf-cf05fdb1f2dc@oracle.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Joao Martins <joao.m.martins@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Joao Martins <joao.m.martins@oracle.com>
Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Cc: Brice Goglin <Brice.Goglin@inria.fr>
Cc: Jeff Moyer <jmoyer@redhat.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Ben Skeggs <bskeggs@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: David Airlie <airlied@linux.ie>
Cc: David Hildenbrand <david@redhat.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Ira Weiny <ira.weiny@intel.com>
Cc: Jason Gunthorpe <jgg@mellanox.com>
Cc: Jia He <justin.he@arm.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Mike Rapoport <rppt@linux.ibm.com>
Cc: Paul Mackerras <paulus@ozlabs.org>
Cc: Pavel Tatashin <pasha.tatashin@soleen.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tom Lendacky <thomas.lendacky@amd.com>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: Wei Yang <richard.weiyang@linux.alibaba.com>
Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Hulk Robot <hulkci@huawei.com>
Cc: Jason Yan <yanaijie@huawei.com>
Cc: "Jérôme Glisse" <jglisse@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: kernel test robot <lkp@intel.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Stefano Stabellini <sstabellini@kernel.org>
Cc: Vivek Goyal <vgoyal@redhat.com>
Link: https://lkml.kernel.org/r/159643098298.4062302.17587338161136144730.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
84 lines
2.7 KiB
Plaintext
84 lines
2.7 KiB
Plaintext
# SPDX-License-Identifier: GPL-2.0-only
|
|
config DAX_DRIVER
|
|
select DAX
|
|
bool
|
|
|
|
menuconfig DAX
|
|
tristate "DAX: direct access to differentiated memory"
|
|
select SRCU
|
|
default m if NVDIMM_DAX
|
|
|
|
if DAX
|
|
|
|
config DEV_DAX
|
|
tristate "Device DAX: direct access mapping device"
|
|
depends on TRANSPARENT_HUGEPAGE
|
|
help
|
|
Support raw access to differentiated (persistence, bandwidth,
|
|
latency...) memory via an mmap(2) capable character
|
|
device. Platform firmware or a device driver may identify a
|
|
platform memory resource that is differentiated from the
|
|
baseline memory pool. Mappings of a /dev/daxX.Y device impose
|
|
restrictions that make the mapping behavior deterministic.
|
|
|
|
config DEV_DAX_PMEM
|
|
tristate "PMEM DAX: direct access to persistent memory"
|
|
depends on LIBNVDIMM && NVDIMM_DAX && DEV_DAX
|
|
default DEV_DAX
|
|
help
|
|
Support raw access to persistent memory. Note that this
|
|
driver consumes memory ranges allocated and exported by the
|
|
libnvdimm sub-system.
|
|
|
|
Say M if unsure
|
|
|
|
config DEV_DAX_HMEM
|
|
tristate "HMEM DAX: direct access to 'specific purpose' memory"
|
|
depends on EFI_SOFT_RESERVE
|
|
select NUMA_KEEP_MEMINFO if (NUMA && X86)
|
|
default DEV_DAX
|
|
help
|
|
EFI 2.8 platforms, and others, may advertise 'specific purpose'
|
|
memory. For example, a high bandwidth memory pool. The
|
|
indication from platform firmware is meant to reserve the
|
|
memory from typical usage by default. This driver creates
|
|
device-dax instances for these memory ranges, and that also
|
|
enables the possibility to assign them to the DEV_DAX_KMEM
|
|
driver to override the reservation and add them to kernel
|
|
"System RAM" pool.
|
|
|
|
Say M if unsure.
|
|
|
|
config DEV_DAX_HMEM_DEVICES
|
|
depends on NUMA_KEEP_MEMINFO # for phys_to_target_node()
|
|
depends on DEV_DAX_HMEM && DAX=y
|
|
def_bool y
|
|
|
|
config DEV_DAX_KMEM
|
|
tristate "KMEM DAX: volatile-use of persistent memory"
|
|
default DEV_DAX
|
|
depends on DEV_DAX
|
|
depends on MEMORY_HOTPLUG # for add_memory() and friends
|
|
help
|
|
Support access to persistent, or other performance
|
|
differentiated memory as if it were System RAM. This allows
|
|
easier use of persistent memory by unmodified applications, or
|
|
adds core kernel memory services to heterogeneous memory types
|
|
(HMEM) marked "reserved" by platform firmware.
|
|
|
|
To use this feature, a DAX device must be unbound from the
|
|
device_dax driver and bound to this kmem driver on each boot.
|
|
|
|
Say N if unsure.
|
|
|
|
config DEV_DAX_PMEM_COMPAT
|
|
tristate "PMEM DAX: support the deprecated /sys/class/dax interface"
|
|
depends on m && DEV_DAX_PMEM=m
|
|
default DEV_DAX_PMEM
|
|
help
|
|
Older versions of the libdaxctl library expect to find all
|
|
device-dax instances under /sys/class/dax. If libdaxctl in
|
|
your distribution is older than v58 say M, otherwise say N.
|
|
|
|
endif
|