Merge tag 'mm-stable-2026-04-13-21-45' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull MM updates from Andrew Morton:

 - "maple_tree: Replace big node with maple copy" (Liam Howlett)

   Mainly prepararatory work for ongoing development but it does reduce
   stack usage and is an improvement.

 - "mm, swap: swap table phase III: remove swap_map" (Kairui Song)

   Offers memory savings by removing the static swap_map. It also yields
   some CPU savings and implements several cleanups.

 - "mm: memfd_luo: preserve file seals" (Pratyush Yadav)

   File seal preservation to LUO's memfd code

 - "mm: zswap: add per-memcg stat for incompressible pages" (Jiayuan
   Chen)

   Additional userspace stats reportng to zswap

 - "arch, mm: consolidate empty_zero_page" (Mike Rapoport)

   Some cleanups for our handling of ZERO_PAGE() and zero_pfn

 - "mm/kmemleak: Improve scan_should_stop() implementation" (Zhongqiu
   Han)

   A robustness improvement and some cleanups in the kmemleak code

 - "Improve khugepaged scan logic" (Vernon Yang)

   Improve khugepaged scan logic and reduce CPU consumption by
   prioritizing scanning tasks that access memory frequently

 - "Make KHO Stateless" (Jason Miu)

   Simplify Kexec Handover by transitioning KHO from an xarray-based
   metadata tracking system with serialization to a radix tree data
   structure that can be passed directly to the next kernel

 - "mm: vmscan: add PID and cgroup ID to vmscan tracepoints" (Thomas
   Ballasi and Steven Rostedt)

   Enhance vmscan's tracepointing

 - "mm: arch/shstk: Common shadow stack mapping helper and
   VM_NOHUGEPAGE" (Catalin Marinas)

   Cleanup for the shadow stack code: remove per-arch code in favour of
   a generic implementation

 - "Fix KASAN support for KHO restored vmalloc regions" (Pasha Tatashin)

   Fix a WARN() which can be emitted the KHO restores a vmalloc area

 - "mm: Remove stray references to pagevec" (Tal Zussman)

   Several cleanups, mainly udpating references to "struct pagevec",
   which became folio_batch three years ago

 - "mm: Eliminate fake head pages from vmemmap optimization" (Kiryl
   Shutsemau)

   Simplify the HugeTLB vmemmap optimization (HVO) by changing how tail
   pages encode their relationship to the head page

 - "mm/damon/core: improve DAMOS quota efficiency for core layer
   filters" (SeongJae Park)

   Improve two problematic behaviors of DAMOS that makes it less
   efficient when core layer filters are used

 - "mm/damon: strictly respect min_nr_regions" (SeongJae Park)

   Improve DAMON usability by extending the treatment of the
   min_nr_regions user-settable parameter

 - "mm/page_alloc: pcp locking cleanup" (Vlastimil Babka)

   The proper fix for a previously hotfixed SMP=n issue. Code
   simplifications and cleanups ensued

 - "mm: cleanups around unmapping / zapping" (David Hildenbrand)

   A bunch of cleanups around unmapping and zapping. Mostly
   simplifications, code movements, documentation and renaming of
   zapping functions

 - "support batched checking of the young flag for MGLRU" (Baolin Wang)

   Batched checking of the young flag for MGLRU. It's part cleanups; one
   benchmark shows large performance benefits for arm64

 - "memcg: obj stock and slab stat caching cleanups" (Johannes Weiner)

   memcg cleanup and robustness improvements

 - "Allow order zero pages in page reporting" (Yuvraj Sakshith)

   Enhance free page reporting - it is presently and undesirably order-0
   pages when reporting free memory.

 - "mm: vma flag tweaks" (Lorenzo Stoakes)

   Cleanup work following from the recent conversion of the VMA flags to
   a bitmap

 - "mm/damon: add optional debugging-purpose sanity checks" (SeongJae
   Park)

   Add some more developer-facing debug checks into DAMON core

 - "mm/damon: test and document power-of-2 min_region_sz requirement"
   (SeongJae Park)

   An additional DAMON kunit test and makes some adjustments to the
   addr_unit parameter handling

 - "mm/damon/core: make passed_sample_intervals comparisons
   overflow-safe" (SeongJae Park)

   Fix a hard-to-hit time overflow issue in DAMON core

 - "mm/damon: improve/fixup/update ratio calculation, test and
   documentation" (SeongJae Park)

   A batch of misc/minor improvements and fixups for DAMON

 - "mm: move vma_(kernel|mmu)_pagesize() out of hugetlb.c" (David
   Hildenbrand)

   Fix a possible issue with dax-device when CONFIG_HUGETLB=n. Some code
   movement was required.

 - "zram: recompression cleanups and tweaks" (Sergey Senozhatsky)

   A somewhat random mix of fixups, recompression cleanups and
   improvements in the zram code

 - "mm/damon: support multiple goal-based quota tuning algorithms"
   (SeongJae Park)

   Extend DAMOS quotas goal auto-tuning to support multiple tuning
   algorithms that users can select

 - "mm: thp: reduce unnecessary start_stop_khugepaged()" (Breno Leitao)

   Fix the khugpaged sysfs handling so we no longer spam the logs with
   reams of junk when starting/stopping khugepaged

 - "mm: improve map count checks" (Lorenzo Stoakes)

   Provide some cleanups and slight fixes in the mremap, mmap and vma
   code

 - "mm/damon: support addr_unit on default monitoring targets for
   modules" (SeongJae Park)

   Extend the use of DAMON core's addr_unit tunable

 - "mm: khugepaged cleanups and mTHP prerequisites" (Nico Pache)

   Cleanups to khugepaged and is a base for Nico's planned khugepaged
   mTHP support

 - "mm: memory hot(un)plug and SPARSEMEM cleanups" (David Hildenbrand)

   Code movement and cleanups in the memhotplug and sparsemem code

 - "mm: remove CONFIG_ARCH_ENABLE_MEMORY_HOTREMOVE and cleanup
   CONFIG_MIGRATION" (David Hildenbrand)

   Rationalize some memhotplug Kconfig support

 - "change young flag check functions to return bool" (Baolin Wang)

   Cleanups to change all young flag check functions to return bool

 - "mm/damon/sysfs: fix memory leak and NULL dereference issues" (Josh
   Law and SeongJae Park)

   Fix a few potential DAMON bugs

 - "mm/vma: convert vm_flags_t to vma_flags_t in vma code" (Lorenzo
   Stoakes)

   Convert a lot of the existing use of the legacy vm_flags_t data type
   to the new vma_flags_t type which replaces it. Mainly in the vma
   code.

 - "mm: expand mmap_prepare functionality and usage" (Lorenzo Stoakes)

   Expand the mmap_prepare functionality, which is intended to replace
   the deprecated f_op->mmap hook which has been the source of bugs and
   security issues for some time. Cleanups, documentation, extension of
   mmap_prepare into filesystem drivers

 - "mm/huge_memory: refactor zap_huge_pmd()" (Lorenzo Stoakes)

   Simplify and clean up zap_huge_pmd(). Additional cleanups around
   vm_normal_folio_pmd() and the softleaf functionality are performed.

* tag 'mm-stable-2026-04-13-21-45' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (369 commits)
  mm: fix deferred split queue races during migration
  mm/khugepaged: fix issue with tracking lock
  mm/huge_memory: add and use has_deposited_pgtable()
  mm/huge_memory: add and use normal_or_softleaf_folio_pmd()
  mm: add softleaf_is_valid_pmd_entry(), pmd_to_softleaf_folio()
  mm/huge_memory: separate out the folio part of zap_huge_pmd()
  mm/huge_memory: use mm instead of tlb->mm
  mm/huge_memory: remove unnecessary sanity checks
  mm/huge_memory: deduplicate zap deposited table call
  mm/huge_memory: remove unnecessary VM_BUG_ON_PAGE()
  mm/huge_memory: add a common exit path to zap_huge_pmd()
  mm/huge_memory: handle buggy PMD entry in zap_huge_pmd()
  mm/huge_memory: have zap_huge_pmd return a boolean, add kdoc
  mm/huge: avoid big else branch in zap_huge_pmd()
  mm/huge_memory: simplify vma_is_specal_huge()
  mm: on remap assert that input range within the proposed VMA
  mm: add mmap_action_map_kernel_pages[_full]()
  uio: replace deprecated mmap hook with mmap_prepare in uio_info
  drivers: hv: vmbus: replace deprecated mmap hook with mmap_prepare
  mm: allow handling of stacked mmap_prepare hooks in more drivers
  ...

Documentation/ABI/testing/sysfs-kernel-mm-damon

@@ -316,6 +316,12 @@ Contact:	SeongJae Park <sj@kernel.org>
 Description:	Writing to and reading from this file sets and gets the path
 		parameter of the goal.
 
+What:		/sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/quotas/goal_tuner
+Date:		Mar 2026
+Contact:	SeongJae Park <sj@kernel.org>
+Description:	Writing to and reading from this file sets and gets the
+		goal-based effective quota auto-tuning algorithm to use.
+
 What:		/sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/quotas/weights/sz_permil
 Date:		Mar 2022
 Contact:	SeongJae Park <sj@kernel.org>

Documentation/admin-guide/blockdev/zram.rst

@@ -462,7 +462,7 @@ know it via /sys/block/zram0/bd_stat's 3rd column.
 recompression
 -------------
 
-With CONFIG_ZRAM_MULTI_COMP, zram can recompress pages using alternative
+With `CONFIG_ZRAM_MULTI_COMP`, zram can recompress pages using alternative
 (secondary) compression algorithms. The basic idea is that alternative
 compression algorithm can provide better compression ratio at a price of
 (potentially) slower compression/decompression speeds. Alternative compression
@@ -471,7 +471,7 @@ that default algorithm failed to compress). Another application is idle pages
 recompression - pages that are cold and sit in the memory can be recompressed
 using more effective algorithm and, hence, reduce zsmalloc memory usage.
 
-With CONFIG_ZRAM_MULTI_COMP, zram supports up to 4 compression algorithms:
+With `CONFIG_ZRAM_MULTI_COMP`, zram supports up to 4 compression algorithms:
 one primary and up to 3 secondary ones. Primary zram compressor is explained
 in "3) Select compression algorithm", secondary algorithms are configured
 using recomp_algorithm device attribute.
@@ -495,56 +495,43 @@ configuration:::
 	#select deflate recompression algorithm, priority 2
 	echo "algo=deflate priority=2" > /sys/block/zramX/recomp_algorithm
 
-Another device attribute that CONFIG_ZRAM_MULTI_COMP enables is recompress,
+Another device attribute that `CONFIG_ZRAM_MULTI_COMP` enables is `recompress`,
 which controls recompression.
 
 Examples:::
 
 	#IDLE pages recompression is activated by `idle` mode
-	echo "type=idle" > /sys/block/zramX/recompress
+	echo "type=idle priority=1" > /sys/block/zramX/recompress
 
 	#HUGE pages recompression is activated by `huge` mode
-	echo "type=huge" > /sys/block/zram0/recompress
+	echo "type=huge priority=2" > /sys/block/zram0/recompress
 
 	#HUGE_IDLE pages recompression is activated by `huge_idle` mode
-	echo "type=huge_idle" > /sys/block/zramX/recompress
+	echo "type=huge_idle priority=1" > /sys/block/zramX/recompress
 
 The number of idle pages can be significant, so user-space can pass a size
 threshold (in bytes) to the recompress knob: zram will recompress only pages
 of equal or greater size:::
 
 	#recompress all pages larger than 3000 bytes
-	echo "threshold=3000" > /sys/block/zramX/recompress
+	echo "threshold=3000 priority=1" > /sys/block/zramX/recompress
 
 	#recompress idle pages larger than 2000 bytes
-	echo "type=idle threshold=2000" > /sys/block/zramX/recompress
+	echo "type=idle threshold=2000 priority=1" > \
+		/sys/block/zramX/recompress
 
 It is also possible to limit the number of pages zram re-compression will
 attempt to recompress:::
 
-	echo "type=huge_idle max_pages=42" > /sys/block/zramX/recompress
+	echo "type=huge_idle priority=1 max_pages=42" > \
+		/sys/block/zramX/recompress
 
-During re-compression for every page, that matches re-compression criteria,
+It is advised to always specify `priority` parameter.  While it is also
-ZRAM iterates the list of registered alternative compression algorithms in
+possible to specify `algo` parameter, so that `zram` will use algorithm's
-order of their priorities. ZRAM stops either when re-compression was
+name to determine the priority, it is not recommended, since it can lead to
-successful (re-compressed object is smaller in size than the original one)
+unexpected results when the same algorithm is configured with different
-and matches re-compression criteria (e.g. size threshold) or when there are
+priorities (e.g. different parameters).  `priority` is the only way to
-no secondary algorithms left to try. If none of the secondary algorithms can
+guarantee that the expected algorithm will be used.
-successfully re-compressed the page such a page is marked as incompressible,
-so ZRAM will not attempt to re-compress it in the future.
-
-This re-compression behaviour, when it iterates through the list of
-registered compression algorithms, increases our chances of finding the
-algorithm that successfully compresses a particular page. Sometimes, however,
-it is convenient (and sometimes even necessary) to limit recompression to
-only one particular algorithm so that it will not try any other algorithms.
-This can be achieved by providing a `algo` or `priority` parameter:::
-
-	#use zstd algorithm only (if registered)
-	echo "type=huge algo=zstd" > /sys/block/zramX/recompress
-
-	#use zstd algorithm only (if zstd was registered under priority 1)
-	echo "type=huge priority=1" > /sys/block/zramX/recompress
 
 memory tracking
 ===============

Documentation/admin-guide/cgroup-v2.rst

@@ -1734,6 +1734,11 @@ The following nested keys are defined.
 	  zswpwb
 		Number of pages written from zswap to swap.
 
+	  zswap_incomp
+		Number of incompressible pages currently stored in zswap
+		without compression. These pages could not be compressed to
+		a size smaller than PAGE_SIZE, so they are stored as-is.
+
 	  thp_fault_alloc (npn)
 		Number of transparent hugepages which were allocated to satisfy
 		a page fault. This counter is not present when CONFIG_TRANSPARENT_HUGEPAGE

Documentation/admin-guide/kdump/vmcoreinfo.rst

@@ -141,7 +141,7 @@ nodemask_t
 The size of a nodemask_t type. Used to compute the number of online
 nodes.
 
-(page, flags|_refcount|mapping|lru|_mapcount|private|compound_order|compound_head)
+(page, flags|_refcount|mapping|lru|_mapcount|private|compound_order|compound_info)
 ----------------------------------------------------------------------------------
 
 User-space tools compute their values based on the offset of these

Documentation/admin-guide/kernel-parameters.txt

@@ -2970,6 +2970,12 @@ Kernel parameters
 			Format: <bool>
 			Default: CONFIG_KFENCE_DEFERRABLE
 
+	kfence.fault=	[MM,KFENCE] Controls the behavior when a KFENCE
+			error is detected.
+			report - print the error report and continue (default).
+			oops   - print the error report and oops.
+			panic  - print the error report and panic.
+
 	kfence.sample_interval=
 			[MM,KFENCE] KFENCE's sample interval in milliseconds.
 			Format: <unsigned integer>

Documentation/admin-guide/mm/damon/lru_sort.rst

@@ -91,8 +91,8 @@ increases and decreases the effective level of the quota aiming the LRU
 
 Disabled by default.
 
-Auto-tune monitoring intervals
+autotune_monitoring_intervals
-------------------------------
+-----------------------------
 
 If this parameter is set as ``Y``, DAMON_LRU_SORT automatically tunes DAMON's
 sampling and aggregation intervals.  The auto-tuning aims to capture meaningful
@@ -221,6 +221,10 @@ But, setting this too high could result in increased monitoring overhead.
 Please refer to the DAMON documentation (:doc:`usage`) for more detail.  10 by
 default.
 
+Note that this must be 3 or higher. Please refer to the :ref:`Monitoring
+<damon_design_monitoring>` section of the design document for the rationale
+behind this lower bound.
+
 max_nr_regions
 --------------
 
@@ -351,3 +355,8 @@ the LRU-list based page granularity reclamation. ::
     # echo 400 > wmarks_mid
     # echo 200 > wmarks_low
     # echo Y > enabled
+
+Note that this module (damon_lru_sort) cannot run simultaneously with other
+DAMON-based special-purpose modules.  Refer to :ref:`DAMON design special
+purpose modules exclusivity <damon_design_special_purpose_modules_exclusivity>`
+for more details.

Documentation/admin-guide/mm/damon/reclaim.rst

@@ -204,6 +204,10 @@ monitoring.  This can be used to set lower-bound of the monitoring quality.
 But, setting this too high could result in increased monitoring overhead.
 Please refer to the DAMON documentation (:doc:`usage`) for more detail.
 
+Note that this must be 3 or higher. Please refer to the :ref:`Monitoring
+<damon_design_monitoring>` section of the design document for the rationale
+behind this lower bound.
+
 max_nr_regions
 --------------
 
@@ -318,6 +322,11 @@ granularity reclamation. ::
     # echo 200 > wmarks_low
     # echo Y > enabled
 
+Note that this module (damon_reclaim) cannot run simultaneously with other
+DAMON-based special-purpose modules.  Refer to :ref:`DAMON design special
+purpose modules exclusivity <damon_design_special_purpose_modules_exclusivity>`
+for more details.
+
 .. [1] https://research.google/pubs/pub48551/
 .. [2] https://lwn.net/Articles/787611/
 .. [3] https://www.kernel.org/doc/html/latest/mm/free_page_reporting.html

Documentation/admin-guide/mm/damon/stat.rst

@@ -45,6 +45,11 @@ You can enable DAMON_STAT by setting the value of this parameter as ``Y``.
 Setting it as ``N`` disables DAMON_STAT.  The default value is set by
 ``CONFIG_DAMON_STAT_ENABLED_DEFAULT`` build config option.
 
+Note that this module (damon_stat) cannot run simultaneously with other
+DAMON-based special-purpose modules.  Refer to :ref:`DAMON design special
+purpose modules exclusivity <damon_design_special_purpose_modules_exclusivity>`
+for more details.
+
 .. _damon_stat_aggr_interval_us:
 
 aggr_interval_us

Documentation/admin-guide/mm/damon/usage.rst

@@ -83,7 +83,7 @@ comma (",").
     │ │ │ │ │ │ │ │ sz/min,max
     │ │ │ │ │ │ │ │ nr_accesses/min,max
     │ │ │ │ │ │ │ │ age/min,max
-    │ │ │ │ │ │ │ :ref:`quotas <sysfs_quotas>`/ms,bytes,reset_interval_ms,effective_bytes
+    │ │ │ │ │ │ │ :ref:`quotas <sysfs_quotas>`/ms,bytes,reset_interval_ms,effective_bytes,goal_tuner
     │ │ │ │ │ │ │ │ weights/sz_permil,nr_accesses_permil,age_permil
     │ │ │ │ │ │ │ │ :ref:`goals <sysfs_schemes_quota_goals>`/nr_goals
     │ │ │ │ │ │ │ │ │ 0/target_metric,target_value,current_value,nid,path
@@ -377,9 +377,9 @@ schemes/<N>/quotas/
 The directory for the :ref:`quotas <damon_design_damos_quotas>` of the given
 DAMON-based operation scheme.
 
-Under ``quotas`` directory, four files (``ms``, ``bytes``,
+Under ``quotas`` directory, five files (``ms``, ``bytes``,
-``reset_interval_ms``, ``effective_bytes``) and two directories (``weights`` and
+``reset_interval_ms``, ``effective_bytes`` and ``goal_tuner``) and two
-``goals``) exist.
+directories (``weights`` and ``goals``) exist.
 
 You can set the ``time quota`` in milliseconds, ``size quota`` in bytes, and
 ``reset interval`` in milliseconds by writing the values to the three files,
@@ -390,6 +390,14 @@ apply the action to only up to ``bytes`` bytes of memory regions within the
 quota limits unless at least one :ref:`goal <sysfs_schemes_quota_goals>` is
 set.
 
+You can set the goal-based effective quota auto-tuning algorithm to use, by
+writing the algorithm name to ``goal_tuner`` file.  Reading the file returns
+the currently selected tuner algorithm.  Refer to the design documentation of
+:ref:`automatic quota tuning goals <damon_design_damos_quotas_auto_tuning>` for
+the background design of the feature and the name of the selectable algorithms.
+Refer to :ref:`goals directory <sysfs_schemes_quota_goals>` for the goals
+setup.
+
 The time quota is internally transformed to a size quota.  Between the
 transformed size quota and user-specified size quota, smaller one is applied.
 Based on the user-specified :ref:`goal <sysfs_schemes_quota_goals>`, the

Documentation/admin-guide/mm/kho.rst

@@ -28,20 +28,10 @@ per NUMA node scratch regions on boot.
 Perform a KHO kexec
 ===================
 
-First, before you perform a KHO kexec, you need to move the system into
+To perform a KHO kexec, load the target payload and kexec into it. It
-the :ref:`KHO finalization phase <kho-finalization-phase>` ::
+is important that you use the ``-s`` parameter to use the in-kernel
-
+kexec file loader, as user space kexec tooling currently has no
-  $ echo 1 > /sys/kernel/debug/kho/out/finalize
+support for KHO with the user space based file loader ::
-
-After this command, the KHO FDT is available in
-``/sys/kernel/debug/kho/out/fdt``. Other subsystems may also register
-their own preserved sub FDTs under
-``/sys/kernel/debug/kho/out/sub_fdts/``.
-
-Next, load the target payload and kexec into it. It is important that you
-use the ``-s`` parameter to use the in-kernel kexec file loader, as user
-space kexec tooling currently has no support for KHO with the user space
-based file loader ::
 
   # kexec -l /path/to/bzImage --initrd /path/to/initrd -s
   # kexec -e
@@ -52,40 +42,19 @@ For example, if you used ``reserve_mem`` command line parameter to create
 an early memory reservation, the new kernel will have that memory at the
 same physical address as the old kernel.
 
-Abort a KHO exec
-================
-
-You can move the system out of KHO finalization phase again by calling ::
-
-  $ echo 0 > /sys/kernel/debug/kho/out/active
-
-After this command, the KHO FDT is no longer available in
-``/sys/kernel/debug/kho/out/fdt``.
-
 debugfs Interfaces
 ==================
 
+These debugfs interfaces are available when the kernel is compiled with
+``CONFIG_KEXEC_HANDOVER_DEBUGFS`` enabled.
+
 Currently KHO creates the following debugfs interfaces. Notice that these
 interfaces may change in the future. They will be moved to sysfs once KHO is
 stabilized.
 
-``/sys/kernel/debug/kho/out/finalize``
-    Kexec HandOver (KHO) allows Linux to transition the state of
-    compatible drivers into the next kexec'ed kernel. To do so,
-    device drivers will instruct KHO to preserve memory regions,
-    which could contain serialized kernel state.
-    While the state is serialized, they are unable to perform
-    any modifications to state that was serialized, such as
-    handed over memory allocations.
-
-    When this file contains "1", the system is in the transition
-    state. When contains "0", it is not. To switch between the
-    two states, echo the respective number into this file.
-
 ``/sys/kernel/debug/kho/out/fdt``
-    When KHO state tree is finalized, the kernel exposes the
+    The kernel exposes the flattened device tree blob that carries its
-    flattened device tree blob that carries its current KHO
+    current KHO state in this file. Kexec user space tooling can use this
-    state in this file. Kexec user space tooling can use this
     as input file for the KHO payload image.
 
 ``/sys/kernel/debug/kho/out/scratch_len``
@@ -100,8 +69,8 @@ stabilized.
     it should place its payload images.
 
 ``/sys/kernel/debug/kho/out/sub_fdts/``
-    In the KHO finalization phase, KHO producers register their own
+    KHO producers can register their own FDT or another binary blob under
-    FDT blob under this directory.
+    this directory.
 
 ``/sys/kernel/debug/kho/in/fdt``
     When the kernel was booted with Kexec HandOver (KHO),

Documentation/admin-guide/mm/numa_memory_policy.rst

@@ -217,7 +217,7 @@ MPOL_PREFERRED
 	the MPOL_F_STATIC_NODES or MPOL_F_RELATIVE_NODES flags
 	described below.
 
-MPOL_INTERLEAVED
+MPOL_INTERLEAVE
 	This mode specifies that page allocations be interleaved, on a
 	page granularity, across the nodes specified in the policy.
 	This mode also behaves slightly differently, based on the

Documentation/core-api/kho/abi.rst

@@ -22,6 +22,12 @@ memblock preservation ABI
 .. kernel-doc:: include/linux/kho/abi/memblock.h
    :doc: memblock kexec handover ABI
 
+KHO persistent memory tracker ABI
+=================================
+
+.. kernel-doc:: include/linux/kho/abi/kexec_handover.h
+  :doc: KHO persistent memory tracker
+
 See Also
 ========
 

Documentation/core-api/kho/index.rst

@@ -71,17 +71,17 @@ for boot memory allocations and as target memory for kexec blobs, some parts
 of that memory region may be reserved. These reservations are irrelevant for
 the next KHO, because kexec can overwrite even the original kernel.
 
-.. _kho-finalization-phase:
+Kexec Handover Radix Tree
+=========================
 
-KHO finalization phase
+.. kernel-doc:: include/linux/kho_radix_tree.h
-======================
+  :doc: Kexec Handover Radix Tree
 
-To enable user space based kexec file loader, the kernel needs to be able to
+Public API
-provide the FDT that describes the current kernel's state before
+==========
-performing the actual kexec. The process of generating that FDT is
+
-called serialization. When the FDT is generated, some properties
+.. kernel-doc:: kernel/liveupdate/kexec_handover.c
-of the system may become immutable because they are already written down
+  :export:
-in the FDT. That state is called the KHO finalization phase.
 
 See Also
 ========

Documentation/dev-tools/kasan.rst

@@ -75,9 +75,6 @@ Software Tag-Based KASAN supports slab, page_alloc, vmalloc, and stack memory.
 Hardware Tag-Based KASAN supports slab, page_alloc, and non-executable vmalloc
 memory.
 
-For slab, both software KASAN modes support SLUB and SLAB allocators, while
-Hardware Tag-Based KASAN only supports SLUB.
-
 Usage
 -----
 

Documentation/dev-tools/kfence.rst

@@ -81,6 +81,13 @@ tables being allocated.
 Error reports
 ~~~~~~~~~~~~~
 
+The boot parameter ``kfence.fault`` can be used to control the behavior when a
+KFENCE error is detected:
+
+- ``kfence.fault=report``: Print the error report and continue (default).
+- ``kfence.fault=oops``: Print the error report and oops.
+- ``kfence.fault=panic``: Print the error report and panic.
+
 A typical out-of-bounds access looks like this::
 
     ==================================================================

Documentation/driver-api/vme.rst

@@ -107,7 +107,7 @@ The function :c:func:`vme_master_read` can be used to read from and
 
 In addition to simple reads and writes, :c:func:`vme_master_rmw` is provided to
 do a read-modify-write transaction. Parts of a VME window can also be mapped
-into user space memory using :c:func:`vme_master_mmap`.
+into user space memory using :c:func:`vme_master_mmap_prepare`.
 
 
 Slave windows

Documentation/filesystems/index.rst

@@ -29,6 +29,7 @@ algorithms work.
    fiemap
    files
    locks
+   mmap_prepare
    multigrain-ts
    mount_api
    quota

Documentation/filesystems/mmap_prepare.rst

@@ -0,0 +1,168 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+===========================
+mmap_prepare callback HOWTO
+===========================
+
+Introduction
+============
+
+The ``struct file->f_op->mmap()`` callback has been deprecated as it is both a
+stability and security risk, and doesn't always permit the merging of adjacent
+mappings resulting in unnecessary memory fragmentation.
+
+It has been replaced with the ``file->f_op->mmap_prepare()`` callback which
+solves these problems.
+
+This hook is called right at the beginning of setting up the mapping, and
+importantly it is invoked *before* any merging of adjacent mappings has taken
+place.
+
+If an error arises upon mapping, it might arise after this callback has been
+invoked, therefore it should be treated as effectively stateless.
+
+That is - no resources should be allocated nor state updated to reflect that a
+mapping has been established, as the mapping may either be merged, or fail to be
+mapped after the callback is complete.
+
+Mapped callback
+---------------
+
+If resources need to be allocated per-mapping, or state such as a reference
+count needs to be manipulated, this should be done using the ``vm_ops->mapped``
+hook, which itself should be set by the >mmap_prepare hook.
+
+This callback is only invoked if a new mapping has been established and was not
+merged with any other, and is invoked at a point where no error may occur before
+the mapping is established.
+
+You may return an error to the callback itself, which will cause the mapping to
+become unmapped and an error returned to the mmap() caller. This is useful if
+resources need to be allocated, and that allocation might fail.
+
+How To Use
+==========
+
+In your driver's struct file_operations struct, specify an ``mmap_prepare``
+callback rather than an ``mmap`` one, e.g. for ext4:
+
+.. code-block:: C
+
+    const struct file_operations ext4_file_operations = {
+        ...
+        .mmap_prepare    = ext4_file_mmap_prepare,
+    };
+
+This has a signature of ``int (*mmap_prepare)(struct vm_area_desc *)``.
+
+Examining the struct vm_area_desc type:
+
+.. code-block:: C
+
+    struct vm_area_desc {
+        /* Immutable state. */
+        const struct mm_struct *const mm;
+        struct file *const file; /* May vary from vm_file in stacked callers. */
+        unsigned long start;
+        unsigned long end;
+
+        /* Mutable fields. Populated with initial state. */
+        pgoff_t pgoff;
+        struct file *vm_file;
+        vma_flags_t vma_flags;
+        pgprot_t page_prot;
+
+        /* Write-only fields. */
+        const struct vm_operations_struct *vm_ops;
+        void *private_data;
+
+        /* Take further action? */
+        struct mmap_action action;
+    };
+
+This is straightforward - you have all the fields you need to set up the
+mapping, and you can update the mutable and writable fields, for instance:
+
+.. code-block:: C
+
+    static int ext4_file_mmap_prepare(struct vm_area_desc *desc)
+    {
+        int ret;
+        struct file *file = desc->file;
+        struct inode *inode = file->f_mapping->host;
+
+        ...
+
+        file_accessed(file);
+        if (IS_DAX(file_inode(file))) {
+            desc->vm_ops = &ext4_dax_vm_ops;
+            vma_desc_set_flags(desc, VMA_HUGEPAGE_BIT);
+        } else {
+            desc->vm_ops = &ext4_file_vm_ops;
+        }
+        return 0;
+    }
+
+Importantly, you no longer have to dance around with reference counts or locks
+when updating these fields - **you can simply go ahead and change them**.
+
+Everything is taken care of by the mapping code.
+
+VMA Flags
+---------
+
+Along with ``mmap_prepare``, VMA flags have undergone an overhaul. Where before
+you would invoke one of vm_flags_init(), vm_flags_reset(), vm_flags_set(),
+vm_flags_clear(), and vm_flags_mod() to modify flags (and to have the
+locking done correctly for you, this is no longer necessary.
+
+Also, the legacy approach of specifying VMA flags via ``VM_READ``, ``VM_WRITE``,
+etc. - i.e. using a ``-VM_xxx``- macro has changed too.
+
+When implementing mmap_prepare(), reference flags by their bit number, defined
+as a ``VMA_xxx_BIT`` macro, e.g. ``VMA_READ_BIT``, ``VMA_WRITE_BIT`` etc.,
+and use one of (where ``desc`` is a pointer to struct vm_area_desc):
+
+* ``vma_desc_test_any(desc, ...)`` - Specify a comma-separated list of flags
+  you wish to test for (whether _any_ are set), e.g. - ``vma_desc_test_any(
+  desc, VMA_WRITE_BIT, VMA_MAYWRITE_BIT)`` - returns ``true`` if either are set,
+  otherwise ``false``.
+* ``vma_desc_set_flags(desc, ...)`` - Update the VMA descriptor flags to set
+  additional flags specified by a comma-separated list,
+  e.g. - ``vma_desc_set_flags(desc, VMA_PFNMAP_BIT, VMA_IO_BIT)``.
+* ``vma_desc_clear_flags(desc, ...)`` - Update the VMA descriptor flags to clear
+  flags specified by a comma-separated list, e.g. - ``vma_desc_clear_flags(
+  desc, VMA_WRITE_BIT, VMA_MAYWRITE_BIT)``.
+
+Actions
+=======
+
+You can now very easily have actions be performed upon a mapping once set up by
+utilising simple helper functions invoked upon the struct vm_area_desc
+pointer. These are:
+
+* mmap_action_remap() - Remaps a range consisting only of PFNs for a specific
+  range starting a virtual address and PFN number of a set size.
+
+* mmap_action_remap_full() - Same as mmap_action_remap(), only remaps the
+  entire mapping from ``start_pfn`` onward.
+
+* mmap_action_ioremap() - Same as mmap_action_remap(), only performs an I/O
+  remap.
+
+* mmap_action_ioremap_full() - Same as mmap_action_ioremap(), only remaps
+  the entire mapping from ``start_pfn`` onward.
+
+* mmap_action_simple_ioremap() - Sets up an I/O remap from a specified
+  physical address and over a specified length.
+
+* mmap_action_map_kernel_pages() - Maps a specified array of `struct page`
+  pointers in the VMA from a specific offset.
+
+* mmap_action_map_kernel_pages_full() - Maps a specified array of `struct
+  page` pointers over the entire VMA. The caller must ensure there are
+  sufficient entries in the page array to cover the entire range of the
+  described VMA.
+
+**NOTE:** The ``action`` field should never normally be manipulated directly,
+rather you ought to use one of these helpers.

Documentation/mm/damon/design.rst

@@ -150,6 +150,8 @@ address on the given address space.  Support of ``address unit`` parameter is
 up to each operations set implementation.  ``paddr`` is the only operations set
 implementation that supports the parameter.
 
+If the value is smaller than ``PAGE_SIZE``, only a power of two should be used.
+
 .. _damon_core_logic:
 
 Core Logics
@@ -165,6 +167,13 @@ monitoring attributes, ``sampling interval``, ``aggregation interval``,
 ``update interval``, ``minimum number of regions``, and ``maximum number of
 regions``.
 
+Note that ``minimum number of regions`` must be 3 or higher. This is because the
+virtual address space monitoring is designed to handle at least three regions to
+accommodate two large unmapped areas commonly found in normal virtual address
+spaces. While this restriction might not be strictly necessary for other
+operation sets like ``paddr``, it is currently enforced across all DAMON
+operations for consistency.
+
 To know how user-space can set the attributes via :ref:`DAMON sysfs interface
 <sysfs_interface>`, refer to :ref:`monitoring_attrs <sysfs_monitoring_attrs>`
 part of the documentation.
@@ -458,9 +467,13 @@ that supports each action are as below.
  - ``pageout``: Reclaim the region.
    Supported by ``vaddr``, ``fvaddr`` and ``paddr`` operations set.
  - ``hugepage``: Call ``madvise()`` for the region with ``MADV_HUGEPAGE``.
-   Supported by ``vaddr`` and ``fvaddr`` operations set.
+   Supported by ``vaddr`` and ``fvaddr`` operations set. When
+   TRANSPARENT_HUGEPAGE is disabled, the application of the action will just
+   fail.
  - ``nohugepage``: Call ``madvise()`` for the region with ``MADV_NOHUGEPAGE``.
-   Supported by ``vaddr`` and ``fvaddr`` operations set.
+   Supported by ``vaddr`` and ``fvaddr`` operations set. When
+   TRANSPARENT_HUGEPAGE is disabled, the application of the action will just
+   fail.
  - ``lru_prio``: Prioritize the region on its LRU lists.
    Supported by ``paddr`` operations set.
  - ``lru_deprio``: Deprioritize the region on its LRU lists.
@@ -564,6 +577,18 @@ aggressiveness (the quota) of the corresponding scheme.  For example, if DAMOS
 is under achieving the goal, DAMOS automatically increases the quota.  If DAMOS
 is over achieving the goal, it decreases the quota.
 
+There are two such tuning algorithms that users can select as they need.
+
+- ``consist``: A proportional feedback loop based algorithm.  Tries to find an
+  optimum quota that should be consistently kept, to keep achieving the goal.
+  Useful for kernel-only operation on dynamic and long-running environments.
+  This is the default selection.  If unsure, use this.
+- ``temporal``: More straightforward algorithm.  Tries to achieve the goal as
+  fast as possible, using maximum allowed quota, but only for a temporal short
+  time.  When the quota is under-achieved, this algorithm keeps tuning quota to
+  a maximum allowed one.  Once the quota is [over]-achieved, this sets the
+  quota zero.  Useful for deterministic control required environments.
+
 The goal can be specified with five parameters, namely ``target_metric``,
 ``target_value``, ``current_value``, ``nid`` and ``path``.  The auto-tuning
 mechanism tries to make ``current_value`` of ``target_metric`` be same to
@@ -839,6 +864,10 @@ more detail, please read the usage documents for those
 (:doc:`/admin-guide/mm/damon/stat`, :doc:`/admin-guide/mm/damon/reclaim` and
 :doc:`/admin-guide/mm/damon/lru_sort`).
 
+.. _damon_design_special_purpose_modules_exclusivity:
+
+Note that these modules currently run in an exclusive manner.  If one of those
+is already running, others will return ``-EBUSY`` upon start requests.
 
 Sample DAMON Modules
 --------------------

Documentation/mm/damon/index.rst

@@ -12,7 +12,7 @@ DAMON is a Linux kernel subsystem for efficient :ref:`data access monitoring
  - *light-weight* (for production online usages),
  - *scalable* (in terms of memory size),
  - *tunable* (for flexible usages), and
- - *autoamted* (for production operation without manual tunings).
+ - *automated* (for production operation without manual tunings).
 
 .. toctree::
    :maxdepth: 2

Documentation/mm/damon/maintainer-profile.rst

@@ -63,10 +63,10 @@ management subsystem maintainer.
 Review cadence
 --------------
 
-The DAMON maintainer does the work on the usual work hour (09:00 to 17:00,
+The DAMON maintainer usually work in a flexible way, except early morning in PT
-Mon-Fri) in PT (Pacific Time).  The response to patches will occasionally be
+(Pacific Time).  The response to patches will occasionally be slow.  Do not
-slow.  Do not hesitate to send a ping if you have not heard back within a week
+hesitate to send a ping if you have not heard back within a week of sending a
-of sending a patch.
+patch.
 
 Mailing tool
 ------------

Documentation/mm/hugetlbfs_reserv.rst

@@ -155,7 +155,7 @@ are enough free huge pages to accommodate the reservation.  If there are,
 the global reservation count resv_huge_pages is adjusted something like the
 following::
 
-	if (resv_needed <= (resv_huge_pages - free_huge_pages))
+	if (resv_needed <= (free_huge_pages - resv_huge_pages)
 		resv_huge_pages += resv_needed;
 
 Note that the global lock hugetlb_lock is held when checking and adjusting

Documentation/mm/vmemmap_dedup.rst

@@ -24,7 +24,7 @@ For each base page, there is a corresponding ``struct page``.
 Within the HugeTLB subsystem, only the first 4 ``struct page`` are used to
 contain unique information about a HugeTLB page. ``__NR_USED_SUBPAGE`` provides
 this upper limit. The only 'useful' information in the remaining ``struct page``
-is the compound_head field, and this field is the same for all tail pages.
+is the compound_info field, and this field is the same for all tail pages.
 
 By removing redundant ``struct page`` for HugeTLB pages, memory can be returned
 to the buddy allocator for other uses.
@@ -124,33 +124,35 @@ Here is how things look before optimization::
  |           |
  +-----------+
 
-The value of page->compound_head is the same for all tail pages. The first
+The first page of ``struct page`` (page 0) associated with the HugeTLB page
-page of ``struct page`` (page 0) associated with the HugeTLB page contains the 4
+contains the 4 ``struct page`` necessary to describe the HugeTLB. The remaining
-``struct page`` necessary to describe the HugeTLB. The only use of the remaining
+pages of ``struct page`` (page 1 to page 7) are tail pages.
-pages of ``struct page`` (page 1 to page 7) is to point to page->compound_head.
+
-Therefore, we can remap pages 1 to 7 to page 0. Only 1 page of ``struct page``
+The optimization is only applied when the size of the struct page is a power
-will be used for each HugeTLB page. This will allow us to free the remaining
+of 2. In this case, all tail pages of the same order are identical. See
-7 pages to the buddy allocator.
+compound_head(). This allows us to remap the tail pages of the vmemmap to a
+shared, read-only page. The head page is also remapped to a new page. This
+allows the original vmemmap pages to be freed.
 
 Here is how things look after remapping::
 
-    HugeTLB                  struct pages(8 pages)         page frame(8 pages)
+    HugeTLB                  struct pages(8 pages)                 page frame (new)
- +-----------+ ---virt_to_page---> +-----------+   mapping to   +-----------+
+ +-----------+ ---virt_to_page---> +-----------+   mapping to   +----------------+
- |           |                     |     0     | -------------> |     0     |
+ |           |                     |     0     | -------------> |       0        |
- |           |                     +-----------+                +-----------+
+ |           |                     +-----------+                +----------------+
- |           |                     |     1     | ---------------^ ^ ^ ^ ^ ^ ^
+ |           |                     |     1     | ------┐
- |           |                     +-----------+                  | | | | | |
+ |           |                     +-----------+       |
- |           |                     |     2     | -----------------+ | | | | |
+ |           |                     |     2     | ------┼        +----------------------------+
- |           |                     +-----------+                    | | | | |
+ |           |                     +-----------+       |        | A single, per-zone page    |
- |           |                     |     3     | -------------------+ | | | |
+ |           |                     |     3     | ------┼------> | frame shared among all     |
- |           |                     +-----------+                      | | | |
+ |           |                     +-----------+       |        | hugepages of the same size |
- |           |                     |     4     | ---------------------+ | | |
+ |           |                     |     4     | ------┼        +----------------------------+
- |    PMD    |                     +-----------+                        | | |
+ |           |                     +-----------+       |
- |   level   |                     |     5     | -----------------------+ | |
+ |           |                     |     5     | ------┼
- |  mapping  |                     +-----------+                          | |
+ |    PMD    |                     +-----------+       |
- |           |                     |     6     | -------------------------+ |
+ |   level   |                     |     6     | ------┼
- |           |                     +-----------+                            |
+ |  mapping  |                     +-----------+       |
- |           |                     |     7     | ---------------------------+
+ |           |                     |     7     | ------┘
  |           |                     +-----------+
  |           |
  |           |
@@ -172,16 +174,6 @@ The contiguous bit is used to increase the mapping size at the pmd and pte
 (last) level. So this type of HugeTLB page can be optimized only when its
 size of the ``struct page`` structs is greater than **1** page.
 
-Notice: The head vmemmap page is not freed to the buddy allocator and all
-tail vmemmap pages are mapped to the head vmemmap page frame. So we can see
-more than one ``struct page`` struct with ``PG_head`` (e.g. 8 per 2 MB HugeTLB
-page) associated with each HugeTLB page. The ``compound_head()`` can handle
-this correctly. There is only **one** head ``struct page``, the tail
-``struct page`` with ``PG_head`` are fake head ``struct page``.  We need an
-approach to distinguish between those two different types of ``struct page`` so
-that ``compound_head()`` can return the real head ``struct page`` when the
-parameter is the tail ``struct page`` but with ``PG_head``.
-
 Device DAX
 ==========
 

MAINTAINERS

@@ -16738,6 +16738,7 @@ L:	linux-mm@kvack.org
 S:	Maintained
 W:	http://www.linux-mm.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
+F:	include/linux/folio_batch.h
 F:	include/linux/gfp.h
 F:	include/linux/gfp_types.h
 F:	include/linux/highmem.h
@@ -16754,6 +16755,7 @@ F:	include/linux/pgtable.h
 F:	include/linux/ptdump.h
 F:	include/linux/vmpressure.h
 F:	include/linux/vmstat.h
+F:	fs/proc/meminfo.c
 F:	kernel/fork.c
 F:	mm/Kconfig
 F:	mm/debug.c
@@ -16987,6 +16989,7 @@ R:	Kemeng Shi <shikemeng@huaweicloud.com>
 R:	Nhat Pham <nphamcs@gmail.com>
 R:	Baoquan He <bhe@redhat.com>
 R:	Barry Song <baohua@kernel.org>
+R:	Youngjun Park <youngjun.park@lge.com>
 L:	linux-mm@kvack.org
 S:	Maintained
 F:	Documentation/mm/swap-table.rst
@@ -17068,6 +17071,8 @@ S:	Maintained
 W:	http://www.linux-mm.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
 F:	include/trace/events/mmap.h
+F:	fs/proc/task_mmu.c
+F:	fs/proc/task_nommu.c
 F:	mm/interval_tree.c
 F:	mm/mincore.c
 F:	mm/mlock.c

arch/alpha/include/asm/pgtable.h

@@ -126,12 +126,6 @@ struct vm_area_struct;
  */
 #define pgprot_noncached(prot)	(prot)
 
-/*
- * ZERO_PAGE is a global shared page that is always zero:  used
- * for zero-mapped memory areas etc..
- */
-#define ZERO_PAGE(vaddr)	(virt_to_page(ZERO_PGE))
-
 /*
  * On certain platforms whose physical address space can overlap KSEG,
  * namely EV6 and above, we must re-twiddle the physaddr to restore the

arch/arc/include/asm/page.h

@@ -131,7 +131,7 @@ static inline unsigned long virt_to_pfn(const void *kaddr)
 #define virt_addr_valid(kaddr)  pfn_valid(virt_to_pfn(kaddr))
 
 /* Default Permissions for stack/heaps pages (Non Executable) */
-#define VM_DATA_DEFAULT_FLAGS	VM_DATA_FLAGS_NON_EXEC
+#define VMA_DATA_DEFAULT_FLAGS	VMA_DATA_FLAGS_NON_EXEC
 
 #define WANT_PAGE_VIRTUAL   1
 

arch/arc/include/asm/pgtable.h

@@ -21,9 +21,6 @@
 
 #ifndef __ASSEMBLER__
 
-extern char empty_zero_page[PAGE_SIZE];
-#define ZERO_PAGE(vaddr)	(virt_to_page(empty_zero_page))
-
 extern pgd_t swapper_pg_dir[] __aligned(PAGE_SIZE);
 
 /* to cope with aliasing VIPT cache */

arch/arc/mm/init.c

@@ -19,8 +19,6 @@
 #include <asm/arcregs.h>
 
 pgd_t swapper_pg_dir[PTRS_PER_PGD] __aligned(PAGE_SIZE);
-char empty_zero_page[PAGE_SIZE] __aligned(PAGE_SIZE);
-EXPORT_SYMBOL(empty_zero_page);
 
 static const unsigned long low_mem_start = CONFIG_LINUX_RAM_BASE;
 static unsigned long low_mem_sz;

arch/arm/include/asm/page.h

@@ -184,7 +184,7 @@ extern int pfn_valid(unsigned long);
 
 #include <asm/memory.h>
 
-#define VM_DATA_DEFAULT_FLAGS	VM_DATA_FLAGS_TSK_EXEC
+#define VMA_DATA_DEFAULT_FLAGS	VMA_DATA_FLAGS_TSK_EXEC
 
 #include <asm-generic/getorder.h>
 #include <asm-generic/memory_model.h>

arch/arm/include/asm/pgtable.h

@@ -10,15 +10,6 @@
 #include <linux/const.h>
 #include <asm/proc-fns.h>
 
-#ifndef __ASSEMBLY__
-/*
- * ZERO_PAGE is a global shared page that is always zero: used
- * for zero-mapped memory areas etc..
- */
-extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
-#define ZERO_PAGE(vaddr)	(virt_to_page(empty_zero_page))
-#endif
-
 #include <asm-generic/pgtable-nopud.h>
 
 #ifndef CONFIG_MMU

arch/arm/mm/mmu.c

@@ -41,13 +41,6 @@
 
 extern unsigned long __atags_pointer;
 
-/*
- * empty_zero_page is a special page that is used for
- * zero-initialized data and COW.
- */
-unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)] __page_aligned_bss;
-EXPORT_SYMBOL(empty_zero_page);
-
 /*
  * The pmd table for the upper-most set of pages.
  */

arch/arm/mm/nommu.c

@@ -27,13 +27,6 @@
 
 unsigned long vectors_base;
 
-/*
- * empty_zero_page is a special page that is used for
- * zero-initialized data and COW.
- */
-unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)] __page_aligned_bss;
-EXPORT_SYMBOL(empty_zero_page);
-
 #ifdef CONFIG_ARM_MPU
 struct mpu_rgn_info mpu_rgn_info;
 #endif

arch/arm64/Kconfig

@@ -16,7 +16,6 @@ config ARM64
 	select ARCH_BINFMT_ELF_STATE
 	select ARCH_ENABLE_HUGEPAGE_MIGRATION if HUGETLB_PAGE && MIGRATION
 	select ARCH_ENABLE_MEMORY_HOTPLUG
-	select ARCH_ENABLE_MEMORY_HOTREMOVE
 	select ARCH_ENABLE_SPLIT_PMD_PTLOCK if PGTABLE_LEVELS > 2
 	select ARCH_ENABLE_THP_MIGRATION if TRANSPARENT_HUGEPAGE
 	select ARCH_HAS_CACHE_LINE_SIZE

arch/arm64/include/asm/page.h

@@ -46,7 +46,12 @@ int pfn_is_map_memory(unsigned long pfn);
 
 #endif /* !__ASSEMBLER__ */
 
-#define VM_DATA_DEFAULT_FLAGS	(VM_DATA_FLAGS_TSK_EXEC | VM_MTE_ALLOWED)
+#ifdef CONFIG_ARM64_MTE
+#define VMA_DATA_DEFAULT_FLAGS	append_vma_flags(VMA_DATA_FLAGS_TSK_EXEC, \
+						 VMA_MTE_ALLOWED_BIT)
+#else
+#define VMA_DATA_DEFAULT_FLAGS	VMA_DATA_FLAGS_TSK_EXEC
+#endif
 
 #include <asm-generic/getorder.h>
 

arch/arm64/include/asm/pgtable.h

@@ -107,13 +107,6 @@ static inline void arch_leave_lazy_mmu_mode(void)
 	__flush_tlb_range(vma, address, address + PMD_SIZE, PMD_SIZE, 2,	\
 			  TLBF_NOBROADCAST | TLBF_NONOTIFY | TLBF_NOWALKCACHE)
 
-/*
- * ZERO_PAGE is a global shared page that is always zero: used
- * for zero-mapped memory areas etc..
- */
-extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
-#define ZERO_PAGE(vaddr)	phys_to_page(__pa_symbol(empty_zero_page))
-
 #define pte_ERROR(e)	\
 	pr_err("%s:%d: bad pte %016llx.\n", __FILE__, __LINE__, pte_val(e))
 
@@ -1309,9 +1302,8 @@ static inline void __pte_clear(struct mm_struct *mm,
 	__set_pte(ptep, __pte(0));
 }
 
-static inline int __ptep_test_and_clear_young(struct vm_area_struct *vma,
+static inline bool __ptep_test_and_clear_young(struct vm_area_struct *vma,
-					      unsigned long address,
+		unsigned long address, pte_t *ptep)
-					      pte_t *ptep)
 {
 	pte_t old_pte, pte;
 
@@ -1326,10 +1318,10 @@ static inline int __ptep_test_and_clear_young(struct vm_area_struct *vma,
 	return pte_young(pte);
 }
 
-static inline int __ptep_clear_flush_young(struct vm_area_struct *vma,
+static inline bool __ptep_clear_flush_young(struct vm_area_struct *vma,
-					 unsigned long address, pte_t *ptep)
+		unsigned long address, pte_t *ptep)
 {
-	int young = __ptep_test_and_clear_young(vma, address, ptep);
+	bool young = __ptep_test_and_clear_young(vma, address, ptep);
 
 	if (young) {
 		/*
@@ -1348,9 +1340,8 @@ static inline int __ptep_clear_flush_young(struct vm_area_struct *vma,
 
 #if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG)
 #define __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG
-static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma,
+static inline bool pmdp_test_and_clear_young(struct vm_area_struct *vma,
-					    unsigned long address,
+		unsigned long address, pmd_t *pmdp)
-					    pmd_t *pmdp)
 {
 	/* Operation applies to PMD table entry only if FEAT_HAFT is enabled */
 	VM_WARN_ON(pmd_table(READ_ONCE(*pmdp)) && !system_supports_haft());
@@ -1673,9 +1664,9 @@ extern void contpte_clear_full_ptes(struct mm_struct *mm, unsigned long addr,
 extern pte_t contpte_get_and_clear_full_ptes(struct mm_struct *mm,
 				unsigned long addr, pte_t *ptep,
 				unsigned int nr, int full);
-int contpte_test_and_clear_young_ptes(struct vm_area_struct *vma,
+bool contpte_test_and_clear_young_ptes(struct vm_area_struct *vma,
 				unsigned long addr, pte_t *ptep, unsigned int nr);
-int contpte_clear_flush_young_ptes(struct vm_area_struct *vma,
+bool contpte_clear_flush_young_ptes(struct vm_area_struct *vma,
 				unsigned long addr, pte_t *ptep, unsigned int nr);
 extern void contpte_wrprotect_ptes(struct mm_struct *mm, unsigned long addr,
 				pte_t *ptep, unsigned int nr);
@@ -1839,21 +1830,26 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
 	return __ptep_get_and_clear(mm, addr, ptep);
 }
 
-#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
+#define test_and_clear_young_ptes test_and_clear_young_ptes
-static inline int ptep_test_and_clear_young(struct vm_area_struct *vma,
+static inline bool test_and_clear_young_ptes(struct vm_area_struct *vma,
-				unsigned long addr, pte_t *ptep)
+		unsigned long addr, pte_t *ptep, unsigned int nr)
 {
-	pte_t orig_pte = __ptep_get(ptep);
+	if (likely(nr == 1 && !pte_cont(__ptep_get(ptep))))
-
-	if (likely(!pte_valid_cont(orig_pte)))
 		return __ptep_test_and_clear_young(vma, addr, ptep);
 
-	return contpte_test_and_clear_young_ptes(vma, addr, ptep, 1);
+	return contpte_test_and_clear_young_ptes(vma, addr, ptep, nr);
+}
+
+#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
+static inline bool ptep_test_and_clear_young(struct vm_area_struct *vma,
+		unsigned long addr, pte_t *ptep)
+{
+	return test_and_clear_young_ptes(vma, addr, ptep, 1);
 }
 
 #define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH
-static inline int ptep_clear_flush_young(struct vm_area_struct *vma,
+static inline bool ptep_clear_flush_young(struct vm_area_struct *vma,
-				unsigned long addr, pte_t *ptep)
+		unsigned long addr, pte_t *ptep)
 {
 	pte_t orig_pte = __ptep_get(ptep);
 
@@ -1864,9 +1860,8 @@ static inline int ptep_clear_flush_young(struct vm_area_struct *vma,
 }
 
 #define clear_flush_young_ptes clear_flush_young_ptes
-static inline int clear_flush_young_ptes(struct vm_area_struct *vma,
+static inline bool clear_flush_young_ptes(struct vm_area_struct *vma,
-					 unsigned long addr, pte_t *ptep,
+		unsigned long addr, pte_t *ptep, unsigned int nr)
-					 unsigned int nr)
 {
 	if (likely(nr == 1 && !pte_cont(__ptep_get(ptep))))
 		return __ptep_clear_flush_young(vma, addr, ptep);

arch/arm64/include/asm/pkeys.h

@@ -12,8 +12,7 @@
 
 #define arch_max_pkey() 8
 
-int arch_set_user_pkey_access(struct task_struct *tsk, int pkey,
+int arch_set_user_pkey_access(int pkey, unsigned long init_val);
-		unsigned long init_val);
 
 static inline bool arch_pkeys_enabled(void)
 {

arch/arm64/mm/contpte.c

@@ -509,9 +509,8 @@ pte_t contpte_get_and_clear_full_ptes(struct mm_struct *mm,
 }
 EXPORT_SYMBOL_GPL(contpte_get_and_clear_full_ptes);
 
-int contpte_test_and_clear_young_ptes(struct vm_area_struct *vma,
+bool contpte_test_and_clear_young_ptes(struct vm_area_struct *vma,
-					unsigned long addr, pte_t *ptep,
+		unsigned long addr, pte_t *ptep, unsigned int nr)
-					unsigned int nr)
 {
 	/*
 	 * ptep_clear_flush_young() technically requires us to clear the access
@@ -526,7 +525,7 @@ int contpte_test_and_clear_young_ptes(struct vm_area_struct *vma,
 	 */
 
 	unsigned long end = addr + nr * PAGE_SIZE;
-	int young = 0;
+	bool young = false;
 
 	ptep = contpte_align_addr_ptep(&addr, &end, ptep, nr);
 	for (; addr != end; ptep++, addr += PAGE_SIZE)
@@ -536,11 +535,10 @@ int contpte_test_and_clear_young_ptes(struct vm_area_struct *vma,
 }
 EXPORT_SYMBOL_GPL(contpte_test_and_clear_young_ptes);
 
-int contpte_clear_flush_young_ptes(struct vm_area_struct *vma,
+bool contpte_clear_flush_young_ptes(struct vm_area_struct *vma,
-				unsigned long addr, pte_t *ptep,
+		unsigned long addr, pte_t *ptep, unsigned int nr)
-				unsigned int nr)
 {
-	int young;
+	bool young;
 
 	young = contpte_test_and_clear_young_ptes(vma, addr, ptep, nr);
 

arch/arm64/mm/gcs.c

@@ -12,19 +12,7 @@
 
 static unsigned long alloc_gcs(unsigned long addr, unsigned long size)
 {
-	int flags = MAP_ANONYMOUS | MAP_PRIVATE;
+	return vm_mmap_shadow_stack(addr, size, 0);
-	struct mm_struct *mm = current->mm;
-	unsigned long mapped_addr, unused;
-
-	if (addr)
-		flags |= MAP_FIXED_NOREPLACE;
-
-	mmap_write_lock(mm);
-	mapped_addr = do_mmap(NULL, addr, size, PROT_READ, flags,
-			      VM_SHADOW_STACK | VM_WRITE, 0, &unused, NULL);
-	mmap_write_unlock(mm);
-
-	return mapped_addr;
 }
 
 static unsigned long gcs_size(unsigned long size)

arch/arm64/mm/init.c

@@ -328,6 +328,11 @@ void __init bootmem_init(void)
 	memblock_dump_all();
 }
 
+void __init arch_setup_zero_pages(void)
+{
+	__zero_page = phys_to_page(__pa_symbol(empty_zero_page));
+}
+
 void __init arch_mm_preinit(void)
 {
 	unsigned int flags = SWIOTLB_VERBOSE;

arch/arm64/mm/mmu.c

@@ -64,13 +64,6 @@ static bool rodata_is_rw __ro_after_init = true;
  */
 long __section(".mmuoff.data.write") __early_cpu_boot_status;
 
-/*
- * Empty_zero_page is a special page that is used for zero-initialized data
- * and COW.
- */
-unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)] __page_aligned_bss;
-EXPORT_SYMBOL(empty_zero_page);
-
 static DEFINE_SPINLOCK(swapper_pgdir_lock);
 static DEFINE_MUTEX(fixmap_lock);
 
@@ -2344,7 +2337,7 @@ void __cpu_replace_ttbr1(pgd_t *pgdp, bool cnp)
 }
 
 #ifdef CONFIG_ARCH_HAS_PKEYS
-int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, unsigned long init_val)
+int arch_set_user_pkey_access(int pkey, unsigned long init_val)
 {
 	u64 new_por;
 	u64 old_por;

arch/csky/include/asm/pgtable.h

@@ -76,9 +76,6 @@
 #define MAX_SWAPFILES_CHECK() \
 		BUILD_BUG_ON(MAX_SWAPFILES_SHIFT != 5)
 
-extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
-#define ZERO_PAGE(vaddr)	(virt_to_page(empty_zero_page))
-
 extern void load_pgd(unsigned long pg_dir);
 extern pte_t invalid_pte_table[PTRS_PER_PTE];
 

arch/csky/mm/init.c

@@ -38,9 +38,6 @@ pte_t invalid_pte_table[PTRS_PER_PTE] __page_aligned_bss;
 pte_t kernel_pte_tables[PTRS_KERN_TABLE] __page_aligned_bss;
 
 EXPORT_SYMBOL(invalid_pte_table);
-unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]
-						__page_aligned_bss;
-EXPORT_SYMBOL(empty_zero_page);
 
 void free_initmem(void)
 {

arch/hexagon/include/asm/page.h

@@ -90,7 +90,7 @@ struct page;
 #define virt_to_page(kaddr) pfn_to_page(PFN_DOWN(__pa(kaddr)))
 
 /* Default vm area behavior is non-executable.  */
-#define VM_DATA_DEFAULT_FLAGS	VM_DATA_FLAGS_NON_EXEC
+#define VMA_DATA_DEFAULT_FLAGS	VMA_DATA_FLAGS_NON_EXEC
 
 #define virt_addr_valid(kaddr) pfn_valid(__pa(kaddr) >> PAGE_SHIFT)
 

arch/hexagon/include/asm/pgtable.h

@@ -14,9 +14,6 @@
 #include <asm/page.h>
 #include <asm-generic/pgtable-nopmd.h>
 
-/* A handy thing to have if one has the RAM. Declared in head.S */
-extern unsigned long empty_zero_page;
-
 /*
  * The PTE model described here is that of the Hexagon Virtual Machine,
  * which autonomously walks 2-level page tables.  At a lower level, we
@@ -348,9 +345,6 @@ static inline unsigned long pmd_page_vaddr(pmd_t pmd)
 	return (unsigned long)__va(pmd_val(pmd) & PAGE_MASK);
 }
 
-/* ZERO_PAGE - returns the globally shared zero page */
-#define ZERO_PAGE(vaddr) (virt_to_page(&empty_zero_page))
-
 /*
  * Encode/decode swap entries and swap PTEs. Swap PTEs are all PTEs that
  * are !pte_none() && !pte_present().

arch/hexagon/kernel/head.S

@@ -216,8 +216,3 @@ __head_s_vaddr_target:
 .p2align PAGE_SHIFT
 ENTRY(external_cmdline_buffer)
         .fill _PAGE_SIZE,1,0
-
-.data
-.p2align PAGE_SHIFT
-ENTRY(empty_zero_page)
-        .fill _PAGE_SIZE,1,0

arch/hexagon/kernel/hexagon_ksyms.c

@@ -17,7 +17,6 @@ EXPORT_SYMBOL(raw_copy_to_user);
 EXPORT_SYMBOL(__vmgetie);
 EXPORT_SYMBOL(__vmsetie);
 EXPORT_SYMBOL(__vmyield);
-EXPORT_SYMBOL(empty_zero_page);
 EXPORT_SYMBOL(memcpy);
 EXPORT_SYMBOL(memset);
 

arch/loongarch/Kconfig

@@ -12,7 +12,6 @@ config LOONGARCH
 	select ARCH_NEEDS_DEFER_KASAN
 	select ARCH_DISABLE_KASAN_INLINE
 	select ARCH_ENABLE_MEMORY_HOTPLUG
-	select ARCH_ENABLE_MEMORY_HOTREMOVE
 	select ARCH_ENABLE_THP_MIGRATION if TRANSPARENT_HUGEPAGE
 	select ARCH_HAS_ACPI_TABLE_UPGRADE	if ACPI
 	select ARCH_HAS_CPU_FINALIZE_INIT

arch/loongarch/include/asm/page.h

@@ -104,7 +104,7 @@ struct page *tlb_virt_to_page(unsigned long kaddr);
 extern int __virt_addr_valid(volatile void *kaddr);
 #define virt_addr_valid(kaddr)	__virt_addr_valid((volatile void *)(kaddr))
 
-#define VM_DATA_DEFAULT_FLAGS	VM_DATA_FLAGS_TSK_EXEC
+#define VMA_DATA_DEFAULT_FLAGS	VMA_DATA_FLAGS_TSK_EXEC
 
 #include <asm-generic/memory_model.h>
 #include <asm-generic/getorder.h>

arch/loongarch/include/asm/pgtable.h

@@ -74,15 +74,6 @@
 struct mm_struct;
 struct vm_area_struct;
 
-/*
- * ZERO_PAGE is a global shared page that is always zero; used
- * for zero-mapped memory areas etc..
- */
-
-extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
-
-#define ZERO_PAGE(vaddr)	virt_to_page(empty_zero_page)
-
 #ifdef CONFIG_32BIT
 
 #define VMALLOC_START	(vm_map_base + PCI_IOSIZE + (2 * PAGE_SIZE))
@@ -113,7 +104,8 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
 	 min(PTRS_PER_PGD * PTRS_PER_PUD * PTRS_PER_PMD * PTRS_PER_PTE * PAGE_SIZE, (1UL << cpu_vabits) / 2) - PMD_SIZE - VMEMMAP_SIZE - KFENCE_AREA_SIZE)
 #endif
 
-#define vmemmap		((struct page *)((VMALLOC_END + PMD_SIZE) & PMD_MASK))
+#define VMEMMAP_ALIGN	max(PMD_SIZE, MAX_FOLIO_VMEMMAP_ALIGN)
+#define vmemmap		((struct page *)(ALIGN(VMALLOC_END, VMEMMAP_ALIGN)))
 #define VMEMMAP_END	((unsigned long)vmemmap + VMEMMAP_SIZE - 1)
 
 #define KFENCE_AREA_START	(VMEMMAP_END + 1)

arch/loongarch/mm/init.c

@@ -36,9 +36,6 @@
 #include <asm/pgalloc.h>
 #include <asm/tlb.h>
 
-unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)] __page_aligned_bss;
-EXPORT_SYMBOL(empty_zero_page);
-
 void copy_user_highpage(struct page *to, struct page *from,
 	unsigned long vaddr, struct vm_area_struct *vma)
 {

arch/m68k/include/asm/pgtable_mm.h

@@ -110,15 +110,6 @@ extern unsigned long m68k_vmalloc_end;
 #define VMALLOC_END KMAP_START
 #endif
 
-/* zero page used for uninitialized stuff */
-extern void *empty_zero_page;
-
-/*
- * ZERO_PAGE is a global shared page that is always zero: used
- * for zero-mapped memory areas etc..
- */
-#define ZERO_PAGE(vaddr)	(virt_to_page(empty_zero_page))
-
 extern void kernel_set_cachemode(void *addr, unsigned long size, int cmode);
 
 /*

arch/m68k/include/asm/pgtable_no.h

@@ -30,13 +30,6 @@
 
 #define swapper_pg_dir ((pgd_t *) 0)
 
-/*
- * ZERO_PAGE is a global shared page that is always zero: used
- * for zero-mapped memory areas etc..
- */
-extern void *empty_zero_page;
-#define ZERO_PAGE(vaddr)	(virt_to_page(empty_zero_page))
-
 /*
  * All 32bit addresses are effectively valid for vmalloc...
  * Sort of meaningless for non-VM targets.

arch/m68k/mm/init.c

@@ -33,13 +33,6 @@
 #include <asm/sections.h>
 #include <asm/tlb.h>
 
-/*
- * ZERO_PAGE is a special page that is used for zero-initialized
- * data and COW.
- */
-void *empty_zero_page;
-EXPORT_SYMBOL(empty_zero_page);
-
 void __init arch_zone_limits_init(unsigned long *max_zone_pfns)
 {
 	max_zone_pfns[ZONE_DMA] = PFN_DOWN(memblock_end_of_DRAM());
@@ -71,8 +64,6 @@ void __init paging_init(void)
 	unsigned long end_mem = memory_end & PAGE_MASK;
 
 	high_memory = (void *) end_mem;
-
-	empty_zero_page = memblock_alloc_or_panic(PAGE_SIZE, PAGE_SIZE);
 }
 
 #endif /* CONFIG_MMU */

arch/m68k/mm/mcfmmu.c

@@ -41,8 +41,6 @@ void __init paging_init(void)
 	unsigned long next_pgtable;
 	int i;
 
-	empty_zero_page = memblock_alloc_or_panic(PAGE_SIZE, PAGE_SIZE);
-
 	pg_dir = swapper_pg_dir;
 	memset(swapper_pg_dir, 0, sizeof(swapper_pg_dir));
 

arch/m68k/mm/motorola.c

@@ -498,12 +498,6 @@ void __init paging_init(void)
 
 	early_memtest(min_addr, max_addr);
 
-	/*
-	 * initialize the bad page table and bad page to point
-	 * to a couple of allocated pages
-	 */
-	empty_zero_page = memblock_alloc_or_panic(PAGE_SIZE, PAGE_SIZE);
-
 	/*
 	 * Set up SFC/DFC registers
 	 */

arch/m68k/mm/sun3mmu.c

@@ -43,8 +43,6 @@ void __init paging_init(void)
 	unsigned long bootmem_end;
 	unsigned long size;
 
-	empty_zero_page = memblock_alloc_or_panic(PAGE_SIZE, PAGE_SIZE);
-
 	address = PAGE_OFFSET;
 	pg_dir = swapper_pg_dir;
 	memset (swapper_pg_dir, 0, sizeof (swapper_pg_dir));

arch/microblaze/include/asm/pgtable.h

@@ -207,16 +207,6 @@ extern pte_t *va_to_pte(unsigned long address);
  * Also, write permissions imply read permissions.
  */
 
-#ifndef __ASSEMBLER__
-/*
- * ZERO_PAGE is a global shared page that is always zero: used
- * for zero-mapped memory areas etc..
- */
-extern unsigned long empty_zero_page[1024];
-#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page))
-
-#endif /* __ASSEMBLER__ */
-
 #define pte_none(pte)		((pte_val(pte) & ~_PTE_NONE_MASK) == 0)
 #define pte_present(pte)	(pte_val(pte) & _PAGE_PRESENT)
 #define pte_clear(mm, addr, ptep) \
@@ -328,7 +318,7 @@ static inline void set_pte(pte_t *ptep, pte_t pte)
 
 #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
 struct vm_area_struct;
-static inline int ptep_test_and_clear_young(struct vm_area_struct *vma,
+static inline bool ptep_test_and_clear_young(struct vm_area_struct *vma,
 		unsigned long address, pte_t *ptep)
 {
 	return (pte_update(ptep, _PAGE_ACCESSED, 0) & _PAGE_ACCESSED) != 0;

arch/microblaze/kernel/head.S

@@ -39,10 +39,6 @@
 #include <asm/processor.h>
 
 .section .data
-.global empty_zero_page
-.align 12
-empty_zero_page:
-	.space	PAGE_SIZE
 .global swapper_pg_dir
 swapper_pg_dir:
 	.space	PAGE_SIZE

arch/microblaze/kernel/microblaze_ksyms.c

@@ -33,8 +33,6 @@ EXPORT_SYMBOL(memcpy);
 EXPORT_SYMBOL(memmove);
 #endif
 
-EXPORT_SYMBOL(empty_zero_page);
-
 EXPORT_SYMBOL(mbc);
 
 extern void __divsi3(void);

arch/mips/include/asm/page.h

@@ -213,7 +213,7 @@ extern bool __virt_addr_valid(const volatile void *kaddr);
 #define virt_addr_valid(kaddr)						\
 	__virt_addr_valid((const volatile void *) (kaddr))
 
-#define VM_DATA_DEFAULT_FLAGS	VM_DATA_FLAGS_TSK_EXEC
+#define VMA_DATA_DEFAULT_FLAGS	VMA_DATA_FLAGS_TSK_EXEC
 
 extern unsigned long __kaslr_offset;
 static inline unsigned long kaslr_offset(void)

arch/mips/mm/init.c

@@ -56,10 +56,7 @@ unsigned long empty_zero_page, zero_page_mask;
 EXPORT_SYMBOL_GPL(empty_zero_page);
 EXPORT_SYMBOL(zero_page_mask);
 
-/*
+void __init arch_setup_zero_pages(void)
- * Not static inline because used by IP27 special magic initialization code
- */
-static void __init setup_zero_pages(void)
 {
 	unsigned int order;
 
@@ -450,7 +447,6 @@ void __init arch_mm_preinit(void)
 	BUILD_BUG_ON(IS_ENABLED(CONFIG_32BIT) && (PFN_PTE_SHIFT > PAGE_SHIFT));
 
 	maar_init();
-	setup_zero_pages();	/* Setup zeroed pages.  */
 	highmem_init();
 
 #ifdef CONFIG_64BIT
@@ -461,11 +457,6 @@ void __init arch_mm_preinit(void)
 				0x80000000 - 4, KCORE_TEXT);
 #endif
 }
-#else  /* CONFIG_NUMA */
-void __init arch_mm_preinit(void)
-{
-	setup_zero_pages();	/* This comes from node 0 */
-}
 #endif /* !CONFIG_NUMA */
 
 void free_init_pages(const char *what, unsigned long begin, unsigned long end)

arch/nios2/include/asm/page.h

@@ -85,7 +85,7 @@ extern struct page *mem_map;
 # define virt_to_page(vaddr)	pfn_to_page(PFN_DOWN(virt_to_phys(vaddr)))
 # define virt_addr_valid(vaddr)	pfn_valid(PFN_DOWN(virt_to_phys(vaddr)))
 
-# define VM_DATA_DEFAULT_FLAGS	VM_DATA_FLAGS_NON_EXEC
+# define VMA_DATA_DEFAULT_FLAGS	VMA_DATA_FLAGS_NON_EXEC
 
 #include <asm-generic/memory_model.h>
 

arch/nios2/include/asm/pgtable.h

@@ -65,13 +65,6 @@ struct mm_struct;
 #define PGDIR_SIZE	(1UL << PGDIR_SHIFT)
 #define PGDIR_MASK	(~(PGDIR_SIZE-1))
 
-/*
- * ZERO_PAGE is a global shared page that is always zero: used
- * for zero-mapped memory areas etc..
- */
-extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
-#define ZERO_PAGE(vaddr)	(virt_to_page(empty_zero_page))
-
 extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
 extern pte_t invalid_pte_table[PAGE_SIZE/sizeof(pte_t)];
 

arch/nios2/kernel/head.S

@@ -23,16 +23,6 @@
 #include <asm/asm-offsets.h>
 #include <asm/asm-macros.h>
 
-/*
- * ZERO_PAGE is a special page that is used for zero-initialized
- * data and COW.
- */
-.data
-.global empty_zero_page
-.align 12
-empty_zero_page:
-	.space	PAGE_SIZE
-
 /*
  * This global variable is used as an extension to the nios'
  * STATUS register to emulate a user/supervisor mode.

arch/nios2/kernel/nios2_ksyms.c

@@ -20,7 +20,6 @@ EXPORT_SYMBOL(memmove);
 
 /* memory management */
 
-EXPORT_SYMBOL(empty_zero_page);
 EXPORT_SYMBOL(flush_icache_range);
 
 /*

arch/openrisc/include/asm/pgtable.h

@@ -179,10 +179,6 @@ extern void paging_init(void);
 	__pgprot(_PAGE_ALL | _PAGE_SRE | _PAGE_SWE \
 		 | _PAGE_SHARED | _PAGE_DIRTY | _PAGE_EXEC | _PAGE_CI)
 
-/* zero page used for uninitialized stuff */
-extern unsigned long empty_zero_page[2048];
-#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page))
-
 #define pte_none(x)	(!pte_val(x))
 #define pte_present(x)	(pte_val(x) & _PAGE_PRESENT)
 #define pte_clear(mm, addr, xp)	do { pte_val(*(xp)) = 0; } while (0)

arch/openrisc/kernel/head.S

@@ -1563,9 +1563,6 @@ _string_nl:
  */
 	.section .data,"aw"
 	.align	8192
-	.global  empty_zero_page
-empty_zero_page:
-	.space  8192
 
 	.global  swapper_pg_dir
 swapper_pg_dir:

arch/openrisc/kernel/or32_ksyms.c

@@ -40,7 +40,6 @@ DECLARE_EXPORT(__ashldi3);
 DECLARE_EXPORT(__lshrdi3);
 DECLARE_EXPORT(__ucmpdi2);
 
-EXPORT_SYMBOL(empty_zero_page);
 EXPORT_SYMBOL(__copy_tofrom_user);
 EXPORT_SYMBOL(__clear_user);
 EXPORT_SYMBOL(memset);

arch/openrisc/mm/init.c

@@ -188,9 +188,6 @@ void __init mem_init(void)
 {
 	BUG_ON(!mem_map);
 
-	/* clear the zero-page */
-	memset((void *)empty_zero_page, 0, PAGE_SIZE);
-
 	printk("mem_init_done ...........................................\n");
 	mem_init_done = 1;
 	return;

arch/parisc/include/asm/pgtable.h

@@ -262,17 +262,6 @@ extern pgd_t swapper_pg_dir[]; /* declared in init_task.c */
 
 extern pte_t pg0[];
 
-/* zero page used for uninitialized stuff */
-
-extern unsigned long *empty_zero_page;
-
-/*
- * ZERO_PAGE is a global shared page that is always zero: used
- * for zero-mapped memory areas etc..
- */
-
-#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page))
-
 #define pte_none(x)     (pte_val(x) == 0)
 #define pte_present(x)	(pte_val(x) & _PAGE_PRESENT)
 #define pte_user(x)	(pte_val(x) & _PAGE_USER)
@@ -449,19 +438,20 @@ static inline pte_t ptep_get(pte_t *ptep)
 }
 #define ptep_get ptep_get
 
-static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep)
+static inline bool ptep_test_and_clear_young(struct vm_area_struct *vma,
+		unsigned long addr, pte_t *ptep)
 {
 	pte_t pte;
 
 	pte = ptep_get(ptep);
 	if (!pte_young(pte)) {
-		return 0;
+		return false;
 	}
 	set_pte_at(vma->vm_mm, addr, ptep, pte_mkold(pte));
-	return 1;
+	return true;
 }
 
-int ptep_clear_flush_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep);
+bool ptep_clear_flush_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep);
 pte_t ptep_clear_flush(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep);
 
 struct mm_struct;

arch/parisc/kernel/cache.c

@@ -781,18 +781,18 @@ void flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned lon
 	__flush_cache_page(vma, vmaddr, PFN_PHYS(page_to_pfn(page)));
 }
 
-int ptep_clear_flush_young(struct vm_area_struct *vma, unsigned long addr,
+bool ptep_clear_flush_young(struct vm_area_struct *vma,
-			   pte_t *ptep)
+		unsigned long addr, pte_t *ptep)
 {
 	pte_t pte = ptep_get(ptep);
 
 	if (!pte_young(pte))
-		return 0;
+		return false;
 	set_pte(ptep, pte_mkold(pte));
 #if CONFIG_FLUSH_PAGE_ACCESSED
 	__flush_cache_page(vma, addr, PFN_PHYS(pte_pfn(pte)));
 #endif
-	return 1;
+	return true;
 }
 
 /*

arch/parisc/mm/init.c

@@ -604,9 +604,6 @@ void __init mem_init(void)
 #endif
 }
 
-unsigned long *empty_zero_page __ro_after_init;
-EXPORT_SYMBOL(empty_zero_page);
-
 /*
  * pagetable_init() sets up the page tables
  *
@@ -639,9 +636,6 @@ static void __init pagetable_init(void)
 			  initrd_end - initrd_start, PAGE_KERNEL, 0);
 	}
 #endif
-
-	empty_zero_page = memblock_alloc_or_panic(PAGE_SIZE, PAGE_SIZE);
-
 }
 
 static void __init gateway_init(void)

arch/powerpc/Kconfig

@@ -126,7 +126,6 @@ config PPC
 	select ARCH_DISABLE_KASAN_INLINE	if PPC_RADIX_MMU
 	select ARCH_DMA_DEFAULT_COHERENT	if !NOT_COHERENT_CACHE
 	select ARCH_ENABLE_MEMORY_HOTPLUG
-	select ARCH_ENABLE_MEMORY_HOTREMOVE
 	select ARCH_HAS_COPY_MC			if PPC64
 	select ARCH_HAS_CURRENT_STACK_POINTER
 	select ARCH_HAS_DEBUG_VIRTUAL

arch/powerpc/include/asm/book3s/32/pgtable.h

@@ -295,8 +295,8 @@ static inline pte_basic_t pte_update(struct mm_struct *mm, unsigned long addr, p
  * for our hash-based implementation, we fix that up here.
  */
 #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
-static inline int __ptep_test_and_clear_young(struct mm_struct *mm,
+static inline bool __ptep_test_and_clear_young(struct mm_struct *mm,
-					      unsigned long addr, pte_t *ptep)
+		unsigned long addr, pte_t *ptep)
 {
 	unsigned long old;
 	old = pte_update(mm, addr, ptep, _PAGE_ACCESSED, 0, 0);

arch/powerpc/include/asm/book3s/64/pgtable.h

@@ -349,13 +349,13 @@ static inline unsigned long pte_update(struct mm_struct *mm, unsigned long addr,
  * For radix: H_PAGE_HASHPTE should be zero. Hence we can use the same
  * function for both hash and radix.
  */
-static inline int __ptep_test_and_clear_young(struct mm_struct *mm,
+static inline bool __ptep_test_and_clear_young(struct mm_struct *mm,
-					      unsigned long addr, pte_t *ptep)
+		unsigned long addr, pte_t *ptep)
 {
 	unsigned long old;
 
 	if ((pte_raw(*ptep) & cpu_to_be64(_PAGE_ACCESSED | H_PAGE_HASHPTE)) == 0)
-		return 0;
+		return false;
 	old = pte_update(mm, addr, ptep, _PAGE_ACCESSED, 0, 0);
 	return (old & _PAGE_ACCESSED) != 0;
 }
@@ -1161,24 +1161,24 @@ pud_hugepage_update(struct mm_struct *mm, unsigned long addr, pud_t *pudp,
  * For radix we should always find H_PAGE_HASHPTE zero. Hence
  * the below will work for radix too
  */
-static inline int __pmdp_test_and_clear_young(struct mm_struct *mm,
+static inline bool __pmdp_test_and_clear_young(struct mm_struct *mm,
-					      unsigned long addr, pmd_t *pmdp)
+		unsigned long addr, pmd_t *pmdp)
 {
 	unsigned long old;
 
 	if ((pmd_raw(*pmdp) & cpu_to_be64(_PAGE_ACCESSED | H_PAGE_HASHPTE)) == 0)
-		return 0;
+		return false;
 	old = pmd_hugepage_update(mm, addr, pmdp, _PAGE_ACCESSED, 0);
 	return ((old & _PAGE_ACCESSED) != 0);
 }
 
-static inline int __pudp_test_and_clear_young(struct mm_struct *mm,
+static inline bool __pudp_test_and_clear_young(struct mm_struct *mm,
-					      unsigned long addr, pud_t *pudp)
+		unsigned long addr, pud_t *pudp)
 {
 	unsigned long old;
 
 	if ((pud_raw(*pudp) & cpu_to_be64(_PAGE_ACCESSED | H_PAGE_HASHPTE)) == 0)
-		return 0;
+		return false;
 	old = pud_hugepage_update(mm, addr, pudp, _PAGE_ACCESSED, 0);
 	return ((old & _PAGE_ACCESSED) != 0);
 }
@@ -1323,11 +1323,11 @@ extern int pudp_set_access_flags(struct vm_area_struct *vma,
 				 pud_t entry, int dirty);
 
 #define __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG
-extern int pmdp_test_and_clear_young(struct vm_area_struct *vma,
+bool pmdp_test_and_clear_young(struct vm_area_struct *vma,
-				     unsigned long address, pmd_t *pmdp);
+		unsigned long address, pmd_t *pmdp);
 #define __HAVE_ARCH_PUDP_TEST_AND_CLEAR_YOUNG
-extern int pudp_test_and_clear_young(struct vm_area_struct *vma,
+bool pudp_test_and_clear_young(struct vm_area_struct *vma,
-				     unsigned long address, pud_t *pudp);
+		unsigned long address, pud_t *pudp);
 
 
 #define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR

arch/powerpc/include/asm/nohash/64/pgtable.h

@@ -155,7 +155,7 @@ static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
 #define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH
 #define ptep_clear_flush_young(__vma, __address, __ptep)		\
 ({									\
-	int __young = ptep_test_and_clear_young(__vma, __address, __ptep);\
+	bool __young = ptep_test_and_clear_young(__vma, __address, __ptep);\
 	__young;							\
 })
 

arch/powerpc/include/asm/nohash/pgtable.h

@@ -101,8 +101,8 @@ static inline pte_basic_t pte_update(struct mm_struct *mm, unsigned long addr, p
 }
 #endif
 
-static inline int ptep_test_and_clear_young(struct vm_area_struct *vma,
+static inline bool ptep_test_and_clear_young(struct vm_area_struct *vma,
-					    unsigned long addr, pte_t *ptep)
+		unsigned long addr, pte_t *ptep)
 {
 	unsigned long old;
 

arch/powerpc/include/asm/page.h

@@ -240,8 +240,8 @@ static inline const void *pfn_to_kaddr(unsigned long pfn)
  * and needs to be executable.  This means the whole heap ends
  * up being executable.
  */
-#define VM_DATA_DEFAULT_FLAGS32	VM_DATA_FLAGS_TSK_EXEC
+#define VMA_DATA_DEFAULT_FLAGS32	VMA_DATA_FLAGS_TSK_EXEC
-#define VM_DATA_DEFAULT_FLAGS64	VM_DATA_FLAGS_NON_EXEC
+#define VMA_DATA_DEFAULT_FLAGS64	VMA_DATA_FLAGS_NON_EXEC
 
 #ifdef __powerpc64__
 #include <asm/page_64.h>

arch/powerpc/include/asm/page_32.h

@@ -10,7 +10,7 @@
 #endif
 #endif
 
-#define VM_DATA_DEFAULT_FLAGS	VM_DATA_DEFAULT_FLAGS32
+#define VMA_DATA_DEFAULT_FLAGS	VMA_DATA_DEFAULT_FLAGS32
 
 #if defined(CONFIG_PPC_256K_PAGES) || \
     (defined(CONFIG_PPC_8xx) && defined(CONFIG_PPC_16K_PAGES))

arch/powerpc/include/asm/page_64.h

@@ -84,9 +84,9 @@ extern u64 ppc64_pft_size;
 
 #endif /* __ASSEMBLER__ */
 
-#define VM_DATA_DEFAULT_FLAGS \
+#define VMA_DATA_DEFAULT_FLAGS \
 	(is_32bit_task() ? \
-	 VM_DATA_DEFAULT_FLAGS32 : VM_DATA_DEFAULT_FLAGS64)
+	 VMA_DATA_DEFAULT_FLAGS32 : VMA_DATA_DEFAULT_FLAGS64)
 
 /*
  * This is the default if a program doesn't have a PT_GNU_STACK
@@ -94,12 +94,12 @@ extern u64 ppc64_pft_size;
  * stack by default, so in the absence of a PT_GNU_STACK program header
  * we turn execute permission off.
  */
-#define VM_STACK_DEFAULT_FLAGS32	VM_DATA_FLAGS_EXEC
+#define VMA_STACK_DEFAULT_FLAGS32	VMA_DATA_FLAGS_EXEC
-#define VM_STACK_DEFAULT_FLAGS64	VM_DATA_FLAGS_NON_EXEC
+#define VMA_STACK_DEFAULT_FLAGS64	VMA_DATA_FLAGS_NON_EXEC
 
-#define VM_STACK_DEFAULT_FLAGS \
+#define VMA_STACK_DEFAULT_FLAGS \
 	(is_32bit_task() ? \
-	 VM_STACK_DEFAULT_FLAGS32 : VM_STACK_DEFAULT_FLAGS64)
+	 VMA_STACK_DEFAULT_FLAGS32 : VMA_STACK_DEFAULT_FLAGS64)
 
 #include <asm-generic/getorder.h>
 

arch/powerpc/include/asm/pgtable.h

@@ -90,12 +90,6 @@ static inline const void *pmd_page_vaddr(pmd_t pmd)
 }
 #define pmd_page_vaddr pmd_page_vaddr
 #endif
-/*
- * ZERO_PAGE is a global shared page that is always zero: used
- * for zero-mapped memory areas etc..
- */
-extern unsigned long empty_zero_page[];
-#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page))
 
 extern pgd_t swapper_pg_dir[];
 

arch/powerpc/include/asm/pkeys.h

@@ -143,10 +143,8 @@ static inline int arch_override_mprotect_pkey(struct vm_area_struct *vma,
 	return __arch_override_mprotect_pkey(vma, prot, pkey);
 }
 
-extern int __arch_set_user_pkey_access(struct task_struct *tsk, int pkey,
+extern int __arch_set_user_pkey_access(int pkey, unsigned long init_val);
-				       unsigned long init_val);
+static inline int arch_set_user_pkey_access(int pkey, unsigned long init_val)
-static inline int arch_set_user_pkey_access(struct task_struct *tsk, int pkey,
-					    unsigned long init_val)
 {
 	if (!mmu_has_feature(MMU_FTR_PKEY))
 		return -EINVAL;
@@ -160,7 +158,7 @@ static inline int arch_set_user_pkey_access(struct task_struct *tsk, int pkey,
 	if (pkey == 0)
 		return init_val ? -EINVAL : 0;
 
-	return __arch_set_user_pkey_access(tsk, pkey, init_val);
+	return __arch_set_user_pkey_access(pkey, init_val);
 }
 
 static inline bool arch_pkeys_enabled(void)

arch/powerpc/kvm/book3s_hv.c

@@ -36,7 +36,6 @@
 #include <linux/gfp.h>
 #include <linux/vmalloc.h>
 #include <linux/highmem.h>
-#include <linux/hugetlb.h>
 #include <linux/kvm_irqfd.h>
 #include <linux/irqbypass.h>
 #include <linux/module.h>

arch/powerpc/mm/book3s64/pgtable.c

@@ -96,14 +96,14 @@ int pudp_set_access_flags(struct vm_area_struct *vma, unsigned long address,
 }
 
 
-int pmdp_test_and_clear_young(struct vm_area_struct *vma,
+bool pmdp_test_and_clear_young(struct vm_area_struct *vma,
-			      unsigned long address, pmd_t *pmdp)
+		unsigned long address, pmd_t *pmdp)
 {
 	return __pmdp_test_and_clear_young(vma->vm_mm, address, pmdp);
 }
 
-int pudp_test_and_clear_young(struct vm_area_struct *vma,
+bool pudp_test_and_clear_young(struct vm_area_struct *vma,
-			      unsigned long address, pud_t *pudp)
+		unsigned long address, pud_t *pudp)
 {
 	return __pudp_test_and_clear_young(vma->vm_mm, address, pudp);
 }

arch/powerpc/mm/book3s64/pkeys.c

@@ -335,8 +335,7 @@ static inline void init_iamr(int pkey, u8 init_bits)
  * Set the access rights in AMR IAMR and UAMOR registers for @pkey to that
  * specified in @init_val.
  */
-int __arch_set_user_pkey_access(struct task_struct *tsk, int pkey,
+int __arch_set_user_pkey_access(int pkey, unsigned long init_val)
-				unsigned long init_val)
 {
 	u64 new_amr_bits = 0x0ul;
 	u64 new_iamr_bits = 0x0ul;

arch/powerpc/mm/mem.c

@@ -38,9 +38,6 @@
 
 unsigned long long memory_limit __initdata;
 
-unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)] __page_aligned_bss;
-EXPORT_SYMBOL(empty_zero_page);
-
 pgprot_t __phys_mem_access_prot(unsigned long pfn, unsigned long size,
 				pgprot_t vma_prot)
 {

arch/powerpc/platforms/book3s/vas-api.c

@@ -414,7 +414,7 @@ static vm_fault_t vas_mmap_fault(struct vm_fault *vmf)
 	/*
 	 * When the LPAR lost credits due to core removal or during
 	 * migration, invalidate the existing mapping for the current
-	 * paste addresses and set windows in-active (zap_vma_pages in
+	 * paste addresses and set windows in-active (zap_vma() in
 	 * reconfig_close_windows()).
 	 * New mapping will be done later after migration or new credits
 	 * available. So continue to receive faults if the user space

arch/powerpc/platforms/pseries/vas.c

@@ -807,7 +807,7 @@ static int reconfig_close_windows(struct vas_caps *vcap, int excess_creds,
 		 * is done before the original mmap() and after the ioctl.
 		 */
 		if (vma)
-			zap_vma_pages(vma);
+			zap_vma(vma);
 
 		mutex_unlock(&task_ref->mmap_mutex);
 		mmap_write_unlock(task_ref->mm);

arch/riscv/Kconfig

@@ -21,7 +21,6 @@ config RISCV
 	select ARCH_DMA_DEFAULT_COHERENT
 	select ARCH_ENABLE_HUGEPAGE_MIGRATION if HUGETLB_PAGE && MIGRATION
 	select ARCH_ENABLE_MEMORY_HOTPLUG if SPARSEMEM_VMEMMAP
-	select ARCH_ENABLE_MEMORY_HOTREMOVE if MEMORY_HOTPLUG
 	select ARCH_ENABLE_SPLIT_PMD_PTLOCK if PGTABLE_LEVELS > 2
 	select ARCH_ENABLE_THP_MIGRATION if TRANSPARENT_HUGEPAGE
 	select ARCH_HAS_BINFMT_FLAT

arch/riscv/include/asm/page.h

@@ -204,7 +204,7 @@ static __always_inline void *pfn_to_kaddr(unsigned long pfn)
 	(unsigned long)(_addr) >= PAGE_OFFSET && pfn_valid(virt_to_pfn(_addr));	\
 })
 
-#define VM_DATA_DEFAULT_FLAGS	VM_DATA_FLAGS_NON_EXEC
+#define VMA_DATA_DEFAULT_FLAGS	VMA_DATA_FLAGS_NON_EXEC
 
 #include <asm-generic/memory_model.h>
 #include <asm-generic/getorder.h>

arch/riscv/include/asm/pgtable.h

@@ -659,8 +659,8 @@ static inline void pte_clear(struct mm_struct *mm,
 extern int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address,
 				 pte_t *ptep, pte_t entry, int dirty);
 #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG	/* defined in mm/pgtable.c */
-extern int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long address,
+bool ptep_test_and_clear_young(struct vm_area_struct *vma,
-				     pte_t *ptep);
+		unsigned long address, pte_t *ptep);
 
 #define __HAVE_ARCH_PTEP_GET_AND_CLEAR
 static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
@@ -695,8 +695,8 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm,
 }
 
 #define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH
-static inline int ptep_clear_flush_young(struct vm_area_struct *vma,
+static inline bool ptep_clear_flush_young(struct vm_area_struct *vma,
-					 unsigned long address, pte_t *ptep)
+		unsigned long address, pte_t *ptep)
 {
 	/*
 	 * This comment is borrowed from x86, but applies equally to RISC-V:
@@ -1015,8 +1015,8 @@ static inline int pmdp_set_access_flags(struct vm_area_struct *vma,
 }
 
 #define __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG
-static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma,
+static inline bool pmdp_test_and_clear_young(struct vm_area_struct *vma,
-					unsigned long address, pmd_t *pmdp)
+		unsigned long address, pmd_t *pmdp)
 {
 	return ptep_test_and_clear_young(vma, address, (pte_t *)pmdp);
 }
@@ -1109,8 +1109,8 @@ static inline int pudp_set_access_flags(struct vm_area_struct *vma,
 	return ptep_set_access_flags(vma, address, (pte_t *)pudp, pud_pte(entry), dirty);
 }
 
-static inline int pudp_test_and_clear_young(struct vm_area_struct *vma,
+static inline bool pudp_test_and_clear_young(struct vm_area_struct *vma,
-					    unsigned long address, pud_t *pudp)
+		unsigned long address, pud_t *pudp)
 {
 	return ptep_test_and_clear_young(vma, address, (pte_t *)pudp);
 }
@@ -1284,13 +1284,6 @@ extern u64 satp_mode;
 void paging_init(void);
 void misc_mem_init(void);
 
-/*
- * ZERO_PAGE is a global shared page that is always zero,
- * used for zero-mapped memory areas, etc.
- */
-extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
-#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page))
-
 /*
  * Use set_p*_safe(), and elide TLB flushing, when confident that *no*
  * TLB flush will be required as a result of the "set". For example, use

arch/riscv/kernel/usercfi.c

@@ -230,17 +230,7 @@ int restore_user_shstk(struct task_struct *tsk, unsigned long shstk_ptr)
 static unsigned long allocate_shadow_stack(unsigned long addr, unsigned long size,
 					   unsigned long token_offset, bool set_tok)
 {
-	int flags = MAP_ANONYMOUS | MAP_PRIVATE;
+	addr = vm_mmap_shadow_stack(addr, size, 0);
-	struct mm_struct *mm = current->mm;
-	unsigned long populate;
-
-	if (addr)
-		flags |= MAP_FIXED_NOREPLACE;
-
-	mmap_write_lock(mm);
-	addr = do_mmap(NULL, addr, size, PROT_READ, flags,
-		       VM_SHADOW_STACK | VM_WRITE, 0, &populate, NULL);
-	mmap_write_unlock(mm);
 
 	if (!set_tok || IS_ERR_VALUE(addr))
 		goto out;

arch/riscv/mm/init.c

@@ -63,16 +63,13 @@ phys_addr_t phys_ram_base __ro_after_init;
 EXPORT_SYMBOL(phys_ram_base);
 
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
-#define VMEMMAP_ADDR_ALIGN	(1ULL << SECTION_SIZE_BITS)
+#define VMEMMAP_ADDR_ALIGN	max(1ULL << SECTION_SIZE_BITS, \
+				    MAX_FOLIO_VMEMMAP_ALIGN)
 
 unsigned long vmemmap_start_pfn __ro_after_init;
 EXPORT_SYMBOL(vmemmap_start_pfn);
 #endif
 
-unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]
-							__page_aligned_bss;
-EXPORT_SYMBOL(empty_zero_page);
-
 extern char _start[];
 void *_dtb_early_va __initdata;
 uintptr_t _dtb_early_pa __initdata;

arch/riscv/mm/pgtable.c

@@ -29,12 +29,11 @@ int ptep_set_access_flags(struct vm_area_struct *vma,
 	return true;
 }
 
-int ptep_test_and_clear_young(struct vm_area_struct *vma,
+bool ptep_test_and_clear_young(struct vm_area_struct *vma,
-			      unsigned long address,
+		unsigned long address, pte_t *ptep)
-			      pte_t *ptep)
 {
 	if (!pte_young(ptep_get(ptep)))
-		return 0;
+		return false;
 	return test_and_clear_bit(_PAGE_ACCESSED_OFFSET, &pte_val(*ptep));
 }
 EXPORT_SYMBOL_GPL(ptep_test_and_clear_young);

arch/s390/Kconfig

@@ -85,7 +85,6 @@ config S390
 	select ARCH_32BIT_USTAT_F_TINODE
 	select ARCH_CORRECT_STACKTRACE_ON_KRETPROBE
 	select ARCH_ENABLE_MEMORY_HOTPLUG if SPARSEMEM
-	select ARCH_ENABLE_MEMORY_HOTREMOVE
 	select ARCH_ENABLE_SPLIT_PMD_PTLOCK if PGTABLE_LEVELS > 2
 	select ARCH_ENABLE_THP_MIGRATION if TRANSPARENT_HUGEPAGE
 	select ARCH_HAS_CC_CAN_LINK

arch/s390/include/asm/page.h

@@ -277,7 +277,7 @@ static inline unsigned long virt_to_pfn(const void *kaddr)
 
 #define virt_addr_valid(kaddr)	pfn_valid(phys_to_pfn(__pa_nodebug((unsigned long)(kaddr))))
 
-#define VM_DATA_DEFAULT_FLAGS	VM_DATA_FLAGS_NON_EXEC
+#define VMA_DATA_DEFAULT_FLAGS	VMA_DATA_FLAGS_NON_EXEC
 
 #endif /* !__ASSEMBLER__ */
 

arch/s390/include/asm/pgtable.h

@@ -1164,8 +1164,8 @@ pte_t ptep_xchg_direct(struct mm_struct *, unsigned long, pte_t *, pte_t);
 pte_t ptep_xchg_lazy(struct mm_struct *, unsigned long, pte_t *, pte_t);
 
 #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
-static inline int ptep_test_and_clear_young(struct vm_area_struct *vma,
+static inline bool ptep_test_and_clear_young(struct vm_area_struct *vma,
-					    unsigned long addr, pte_t *ptep)
+		unsigned long addr, pte_t *ptep)
 {
 	pte_t pte = *ptep;
 
@@ -1174,8 +1174,8 @@ static inline int ptep_test_and_clear_young(struct vm_area_struct *vma,
 }
 
 #define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH
-static inline int ptep_clear_flush_young(struct vm_area_struct *vma,
+static inline bool ptep_clear_flush_young(struct vm_area_struct *vma,
-					 unsigned long address, pte_t *ptep)
+		unsigned long address, pte_t *ptep)
 {
 	return ptep_test_and_clear_young(vma, address, ptep);
 }
@@ -1683,8 +1683,8 @@ static inline int pmdp_set_access_flags(struct vm_area_struct *vma,
 }
 
 #define __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG
-static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma,
+static inline bool pmdp_test_and_clear_young(struct vm_area_struct *vma,
-					    unsigned long addr, pmd_t *pmdp)
+		unsigned long addr, pmd_t *pmdp)
 {
 	pmd_t pmd = *pmdp;
 
@@ -1693,8 +1693,8 @@ static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma,
 }
 
 #define __HAVE_ARCH_PMDP_CLEAR_YOUNG_FLUSH
-static inline int pmdp_clear_flush_young(struct vm_area_struct *vma,
+static inline bool pmdp_clear_flush_young(struct vm_area_struct *vma,
-					 unsigned long addr, pmd_t *pmdp)
+		unsigned long addr, pmd_t *pmdp)
 {
 	VM_BUG_ON(addr & ~HPAGE_MASK);
 	return pmdp_test_and_clear_young(vma, addr, pmdp);

arch/s390/mm/gmap_helpers.c

@@ -89,7 +89,7 @@ void gmap_helper_discard(struct mm_struct *mm, unsigned long vmaddr, unsigned lo
 		if (!vma)
 			return;
 		if (!is_vm_hugetlb_page(vma))
-			zap_page_range_single(vma, vmaddr, min(end, vma->vm_end) - vmaddr, NULL);
+			zap_vma_range(vma, vmaddr, min(end, vma->vm_end) - vmaddr);
 		vmaddr = vma->vm_end;
 	}
 }

arch/s390/mm/init.c

@@ -69,7 +69,7 @@ unsigned long empty_zero_page, zero_page_mask;
 EXPORT_SYMBOL(empty_zero_page);
 EXPORT_SYMBOL(zero_page_mask);
 
-static void __init setup_zero_pages(void)
+void __init arch_setup_zero_pages(void)
 {
 	unsigned long total_pages = memblock_estimated_nr_free_pages();
 	unsigned int order;
@@ -159,8 +159,6 @@ void __init arch_mm_preinit(void)
 	cpumask_set_cpu(0, mm_cpumask(&init_mm));
 
 	pv_init();
-
-	setup_zero_pages();	/* Setup zeroed pages. */
 }
 
 unsigned long memory_block_size_bytes(void)

arch/sh/include/asm/pgtable.h

@@ -20,14 +20,6 @@
 #ifndef __ASSEMBLER__
 #include <asm/addrspace.h>
 #include <asm/fixmap.h>
-
-/*
- * ZERO_PAGE is a global shared page that is always zero: used
- * for zero-mapped memory areas etc..
- */
-extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
-#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page))
-
 #endif /* !__ASSEMBLER__ */
 
 /*