linux-toradex.git/include/linux/memremap.h, branch v5.12-rc5

mm: fix memory_failure() handling of dax-namespace metadata

2021-02-26T17:41:00+00:00

Given 'struct dev_pagemap' spans both data pages and metadata pages be
careful to consult the altmap if present to delineate metadata.  In fact
the pfn_first() helper already identifies the first valid data pfn, so
export that helper for other code paths via pgmap_pfn_valid().

Other usage of get_dev_pagemap() are not a concern because those are
operating on known data pfns having been looked up by get_user_pages().
I.e.  metadata pfns are never user mapped.

Link: https://lkml.kernel.org/r/161058501758.1840162.4239831989762604527.stgit@dwillia2-desk3.amr.corp.intel.com
Fixes: 6100e34b2526 ("mm, memory_failure: Teach memory_failure() about dev_pagemap pages")
Signed-off-by: Dan Williams 
Reported-by: David Hildenbrand 
Reviewed-by: David Hildenbrand 
Reviewed-by: Naoya Horiguchi 
Cc: Michal Hocko 
Cc: Oscar Salvador 
Cc: Qian Cai 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

mm/memremap_pages: support multiple ranges per invocation

2020-10-14T01:38:28+00:00

In support of device-dax growing the ability to front physically
dis-contiguous ranges of memory, update devm_memremap_pages() to track
multiple ranges with a single reference counter and devm instance.

Convert all [devm_]memremap_pages() users to specify the number of ranges
they are mapping in their 'struct dev_pagemap' instance.

Signed-off-by: Dan Williams 
Signed-off-by: Andrew Morton 
Cc: Paul Mackerras 
Cc: Michael Ellerman 
Cc: Benjamin Herrenschmidt 
Cc: Vishal Verma 
Cc: Vivek Goyal 
Cc: Dave Jiang 
Cc: Ben Skeggs 
Cc: David Airlie 
Cc: Daniel Vetter 
Cc: Ira Weiny 
Cc: Bjorn Helgaas 
Cc: Boris Ostrovsky 
Cc: Juergen Gross 
Cc: Stefano Stabellini 
Cc: "Jérôme Glisse" 
Cc: Ard Biesheuvel 
Cc: Ard Biesheuvel 
Cc: Borislav Petkov 
Cc: Brice Goglin 
Cc: Catalin Marinas 
Cc: Dave Hansen 
Cc: David Hildenbrand 
Cc: Greg Kroah-Hartman 
Cc: "H. Peter Anvin" 
Cc: Hulk Robot 
Cc: Ingo Molnar 
Cc: Jason Gunthorpe 
Cc: Jason Yan 
Cc: Jeff Moyer 
Cc: "Jérôme Glisse" 
Cc: Jia He 
Cc: Joao Martins 
Cc: Jonathan Cameron 
Cc: kernel test robot 
Cc: Mike Rapoport 
Cc: Pavel Tatashin 
Cc: Peter Zijlstra 
Cc: "Rafael J. Wysocki" 
Cc: Randy Dunlap 
Cc: Thomas Gleixner 
Cc: Tom Lendacky 
Cc: Wei Yang 
Cc: Will Deacon 
Link: https://lkml.kernel.org/r/159643103789.4062302.18426128170217903785.stgit@dwillia2-desk3.amr.corp.intel.com
Link: https://lkml.kernel.org/r/160106116293.30709.13350662794915396198.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Linus Torvalds

mm/memremap_pages: convert to 'struct range'

2020-10-14T01:38:28+00:00

The 'struct resource' in 'struct dev_pagemap' is only used for holding
resource span information.  The other fields, 'name', 'flags', 'desc',
'parent', 'sibling', and 'child' are all unused wasted space.

This is in preparation for introducing a multi-range extension of
devm_memremap_pages().

The bulk of this change is unwinding all the places internal to libnvdimm
that used 'struct resource' unnecessarily, and replacing instances of
'struct dev_pagemap'.res with 'struct dev_pagemap'.range.

P2PDMA had a minor usage of the resource flags field, but only to report
failures with "%pR".  That is replaced with an open coded print of the
range.

[dan.carpenter@oracle.com: mm/hmm/test: use after free in dmirror_allocate_chunk()]
  Link: https://lkml.kernel.org/r/20200926121402.GA7467@kadam

Signed-off-by: Dan Williams 
Signed-off-by: Dan Carpenter 
Signed-off-by: Andrew Morton 
Reviewed-by: Boris Ostrovsky 	[xen]
Cc: Paul Mackerras 
Cc: Michael Ellerman 
Cc: Benjamin Herrenschmidt 
Cc: Vishal Verma 
Cc: Vivek Goyal 
Cc: Dave Jiang 
Cc: Ben Skeggs 
Cc: David Airlie 
Cc: Daniel Vetter 
Cc: Ira Weiny 
Cc: Bjorn Helgaas 
Cc: Juergen Gross 
Cc: Stefano Stabellini 
Cc: "Jérôme Glisse" 
Cc: Andy Lutomirski 
Cc: Ard Biesheuvel 
Cc: Ard Biesheuvel 
Cc: Borislav Petkov 
Cc: Brice Goglin 
Cc: Catalin Marinas 
Cc: Dave Hansen 
Cc: David Hildenbrand 
Cc: Greg Kroah-Hartman 
Cc: "H. Peter Anvin" 
Cc: Hulk Robot 
Cc: Ingo Molnar 
Cc: Jason Gunthorpe 
Cc: Jason Yan 
Cc: Jeff Moyer 
Cc: Jia He 
Cc: Joao Martins 
Cc: Jonathan Cameron 
Cc: kernel test robot 
Cc: Mike Rapoport 
Cc: Pavel Tatashin 
Cc: Peter Zijlstra 
Cc: "Rafael J. Wysocki" 
Cc: Randy Dunlap 
Cc: Thomas Gleixner 
Cc: Tom Lendacky 
Cc: Wei Yang 
Cc: Will Deacon 
Link: https://lkml.kernel.org/r/159643103173.4062302.768998885691711532.stgit@dwillia2-desk3.amr.corp.intel.com
Link: https://lkml.kernel.org/r/160106115761.30709.13539840236873663620.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Linus Torvalds

memremap: rename MEMORY_DEVICE_DEVDAX to MEMORY_DEVICE_GENERIC

2020-09-04T07:59:59+00:00

This is in preparation for the logic behind MEMORY_DEVICE_DEVDAX also
being used by non DAX devices.

No functional change intended.

Signed-off-by: Roger Pau Monné 
Reviewed-by: Ira Weiny 
Acked-by: Andrew Morton 
Reviewed-by: Pankaj Gupta 
Link: https://lore.kernel.org/r/20200901083326.21264-3-roger.pau@citrix.com
Signed-off-by: Juergen Gross

Merge tag 'libnvdimm-for-5.7' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm

2020-04-09T04:03:40+00:00

Pull libnvdimm and dax updates from Dan Williams:
 "There were multiple touches outside of drivers/nvdimm/ this round to
  add cross arch compatibility to the devm_memremap_pages() interface,
  enhance numa information for persistent memory ranges, and add a
  zero_page_range() dax operation.

  This cycle I switched from the patchwork api to Konstantin's b4 script
  for collecting tags (from x86, PowerPC, filesystem, and device-mapper
  folks), and everything looks to have gone ok there. This has all
  appeared in -next with no reported issues.

  Summary:

   - Add support for region alignment configuration and enforcement to
     fix compatibility across architectures and PowerPC page size
     configurations.

   - Introduce 'zero_page_range' as a dax operation. This facilitates
     filesystem-dax operation without a block-device.

   - Introduce phys_to_target_node() to facilitate drivers that want to
     know resulting numa node if a given reserved address range was
     onlined.

   - Advertise a persistence-domain for of_pmem and papr_scm. The
     persistence domain indicates where cpu-store cycles need to reach
     in the platform-memory subsystem before the platform will consider
     them power-fail protected.

   - Promote numa_map_to_online_node() to a cross-kernel generic
     facility.

   - Save x86 numa information to allow for node-id lookups for reserved
     memory ranges, deploy that capability for the e820-pmem driver.

   - 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.

   - Fixup some flexible-array declarations"

* tag 'libnvdimm-for-5.7' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm: (29 commits)
  dax: Move mandatory ->zero_page_range() check in alloc_dax()
  dax,iomap: Add helper dax_iomap_zero() to zero a range
  dax: Use new dax zero page method for zeroing a page
  dm,dax: Add dax zero_page_range operation
  s390,dcssblk,dax: Add dax zero_page_range operation to dcssblk driver
  dax, pmem: Add a dax operation zero_page_range
  pmem: Add functions for reading/writing page to/from pmem
  libnvdimm: Update persistence domain value for of_pmem and papr_scm device
  tools/test/nvdimm: Fix out of tree build
  libnvdimm/region: Fix build error
  libnvdimm/region: Replace zero-length array with flexible-array member
  libnvdimm/label: Replace zero-length array with flexible-array member
  ACPI: NFIT: Replace zero-length array with flexible-array member
  libnvdimm/region: Introduce an 'align' attribute
  libnvdimm/region: Introduce NDD_LABELING
  libnvdimm/namespace: Enforce memremap_compat_align()
  libnvdimm/pfn: Prevent raw mode fallback if pfn-infoblock valid
  libnvdimm: Out of bounds read in __nd_ioctl()
  acpi/nfit: improve bounds checking for 'func'
  mm/memremap_pages: Introduce memremap_compat_align()
  ...

include/linux/memremap.h: remove stale comments

2020-04-07T17:43:41+00:00

Fixes: 80a72d0af05a ("memremap: remove the data field in struct dev_pagemap")
Fixes: fdc029b19dfd ("memremap: remove the dev field in struct dev_pagemap")
Signed-off-by: Ira Weiny 
Signed-off-by: Andrew Morton 
Reviewed-by: Christoph Hellwig 
Cc: Jason Gunthorpe 
Cc: Dan Williams 
Link: http://lkml.kernel.org/r/20200316213205.145333-1-ira.weiny@intel.com
Signed-off-by: Linus Torvalds

memremap: add an owner field to struct dev_pagemap

2020-03-26T17:33:37+00:00

Add a new opaque owner field to struct dev_pagemap, which will allow the
hmm and migrate_vma code to identify who owns ZONE_DEVICE memory, and
refuse to work on mappings not owned by the calling entity.

Link: https://lore.kernel.org/r/20200316193216.920734-2-hch@lst.de
Signed-off-by: Christoph Hellwig 
Reviewed-by: Ralph Campbell 
Tested-by: Bharata B Rao 
Signed-off-by: Jason Gunthorpe

mm/memremap_pages: Introduce memremap_compat_align()

2020-02-21T00:58:55+00:00

The "sub-section memory hotplug" facility allows memremap_pages() users
like libnvdimm to compensate for hardware platforms like x86 that have a
section size larger than their hardware memory mapping granularity.  The
compensation that sub-section support affords is being tolerant of
physical memory resources shifting by units smaller (64MiB on x86) than
the memory-hotplug section size (128 MiB). Where the platform
physical-memory mapping granularity is limited by the number and
capability of address-decode-registers in the memory controller.

While the sub-section support allows memremap_pages() to operate on
sub-section (2MiB) granularity, the Power architecture may still
require 16MiB alignment on "!radix_enabled()" platforms.

In order for libnvdimm to be able to detect and manage this per-arch
limitation, introduce memremap_compat_align() as a common minimum
alignment across all driver-facing memory-mapping interfaces, and let
Power override it to 16MiB in the "!radix_enabled()" case.

The assumption / requirement for 16MiB to be a viable
memremap_compat_align() value is that Power does not have platforms
where its equivalent of address-decode-registers never hardware remaps a
persistent memory resource on smaller than 16MiB boundaries. Note that I
tried my best to not add a new Kconfig symbol, but header include
entanglements defeated the #ifndef memremap_compat_align design pattern
and the need to export it defeats the __weak design pattern for arch
overrides.

Based on an initial patch by Aneesh.

Link: http://lore.kernel.org/r/CAPcyv4gBGNP95APYaBcsocEa50tQj9b5h__83vgngjq3ouGX_Q@mail.gmail.com
Reported-by: Aneesh Kumar K.V 
Reported-by: Jeff Moyer 
Cc: Benjamin Herrenschmidt 
Cc: Paul Mackerras 
Reviewed-by: Aneesh Kumar K.V 
Acked-by: Michael Ellerman  (powerpc)
Signed-off-by: Dan Williams

Merge tag 'libnvdimm-fixes-5.4-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm

2019-09-29T17:33:41+00:00

More libnvdimm updates from Dan Williams:

 - Complete the reworks to interoperate with powerpc dynamic huge page
   sizes

 - Fix a crash due to missed accounting for the powerpc 'struct
   page'-memmap mapping granularity

 - Fix badblock initialization for volatile (DRAM emulated) pmem ranges

 - Stop triggering request_key() notifications to userspace when
   NVDIMM-security is disabled / not present

 - Miscellaneous small fixups

* tag 'libnvdimm-fixes-5.4-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm:
  libnvdimm/region: Enable MAP_SYNC for volatile regions
  libnvdimm: prevent nvdimm from requesting key when security is disabled
  libnvdimm/region: Initialize bad block for volatile namespaces
  libnvdimm/nfit_test: Fix acpi_handle redefinition
  libnvdimm/altmap: Track namespace boundaries in altmap
  libnvdimm: Fix endian conversion issues 
  libnvdimm/dax: Pick the right alignment default when creating dax devices
  powerpc/book3s64: Export has_transparent_hugepage() related functions.

libnvdimm/altmap: Track namespace boundaries in altmap

2019-09-24T17:24:12+00:00

With PFN_MODE_PMEM namespace, the memmap area is allocated from the device
area. Some architectures map the memmap area with large page size. On
architectures like ppc64, 16MB page for memap mapping can map 262144 pfns.
This maps a namespace size of 16G.

When populating memmap region with 16MB page from the device area,
make sure the allocated space is not used to map resources outside this
namespace. Such usage of device area will prevent a namespace destroy.

Add resource end pnf in altmap and use that to check if the memmap area
allocation can map pfn outside the namespace. On ppc64 in such case we fallback
to allocation from memory.

This fix kernel crash reported below:

[  132.034989] WARNING: CPU: 13 PID: 13719 at mm/memremap.c:133 devm_memremap_pages_release+0x2d8/0x2e0
[  133.464754] BUG: Unable to handle kernel data access at 0xc00c00010b204000
[  133.464760] Faulting instruction address: 0xc00000000007580c
[  133.464766] Oops: Kernel access of bad area, sig: 11 [#1]
[  133.464771] LE PAGE_SIZE=64K MMU=Hash SMP NR_CPUS=2048 NUMA pSeries
.....
[  133.464901] NIP [c00000000007580c] vmemmap_free+0x2ac/0x3d0
[  133.464906] LR [c0000000000757f8] vmemmap_free+0x298/0x3d0
[  133.464910] Call Trace:
[  133.464914] [c000007cbfd0f7b0] [c0000000000757f8] vmemmap_free+0x298/0x3d0 (unreliable)
[  133.464921] [c000007cbfd0f8d0] [c000000000370a44] section_deactivate+0x1a4/0x240
[  133.464928] [c000007cbfd0f980] [c000000000386270] __remove_pages+0x3a0/0x590
[  133.464935] [c000007cbfd0fa50] [c000000000074158] arch_remove_memory+0x88/0x160
[  133.464942] [c000007cbfd0fae0] [c0000000003be8c0] devm_memremap_pages_release+0x150/0x2e0
[  133.464949] [c000007cbfd0fb70] [c000000000738ea0] devm_action_release+0x30/0x50
[  133.464955] [c000007cbfd0fb90] [c00000000073a5a4] release_nodes+0x344/0x400
[  133.464961] [c000007cbfd0fc40] [c00000000073378c] device_release_driver_internal+0x15c/0x250
[  133.464968] [c000007cbfd0fc80] [c00000000072fd14] unbind_store+0x104/0x110
[  133.464973] [c000007cbfd0fcd0] [c00000000072ee24] drv_attr_store+0x44/0x70
[  133.464981] [c000007cbfd0fcf0] [c0000000004a32bc] sysfs_kf_write+0x6c/0xa0
[  133.464987] [c000007cbfd0fd10] [c0000000004a1dfc] kernfs_fop_write+0x17c/0x250
[  133.464993] [c000007cbfd0fd60] [c0000000003c348c] __vfs_write+0x3c/0x70
[  133.464999] [c000007cbfd0fd80] [c0000000003c75d0] vfs_write+0xd0/0x250

djbw: Aneesh notes that this crash can likely be triggered in any kernel that
supports 'papr_scm', so flagging that commit for -stable consideration.

Fixes: b5beae5e224f ("powerpc/pseries: Add driver for PAPR SCM regions")
Cc: 
Reported-by: Sachin Sant 
Signed-off-by: Aneesh Kumar K.V 
Reviewed-by: Pankaj Gupta 
Tested-by: Santosh Sivaraj 
Reviewed-by: Johannes Thumshirn 
Link: https://lore.kernel.org/r/20190910062826.10041-1-aneesh.kumar@linux.ibm.com
Signed-off-by: Dan Williams