25 hotfixes. 16 are cc:stable. 19 are MM and 6 are non-MM.

The usual bunch of singletons and doubletons - please see the relevant
 changelogs for details.
 -----BEGIN PGP SIGNATURE-----
 
 iHUEABYKAB0WIQTTMBEPP41GrTpTJgfdBJ7gKXxAjgUCZ2cghQAKCRDdBJ7gKXxA
 jgrsAQCvlSmHYYLXBE1A6cram4qWgEP/2vD94d6sVv9UipO/FAEA8y1K7dbT2AGX
 A5ESuRndu5Iy76mb6Tiarqa/yt56QgU=
 =ZYVx
 -----END PGP SIGNATURE-----

Merge tag 'mm-hotfixes-stable-2024-12-21-12-09' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull misc fixes from Andrew Morton:
 "25 hotfixes.  16 are cc:stable.  19 are MM and 6 are non-MM.

  The usual bunch of singletons and doubletons - please see the relevant
  changelogs for details"

* tag 'mm-hotfixes-stable-2024-12-21-12-09' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (25 commits)
  mm: huge_memory: handle strsep not finding delimiter
  alloc_tag: fix set_codetag_empty() when !CONFIG_MEM_ALLOC_PROFILING_DEBUG
  alloc_tag: fix module allocation tags populated area calculation
  mm/codetag: clear tags before swap
  mm/vmstat: fix a W=1 clang compiler warning
  mm: convert partially_mapped set/clear operations to be atomic
  nilfs2: fix buffer head leaks in calls to truncate_inode_pages()
  vmalloc: fix accounting with i915
  mm/page_alloc: don't call pfn_to_page() on possibly non-existent PFN in split_large_buddy()
  fork: avoid inappropriate uprobe access to invalid mm
  nilfs2: prevent use of deleted inode
  zram: fix uninitialized ZRAM not releasing backing device
  zram: refuse to use zero sized block device as backing device
  mm: use clear_user_(high)page() for arch with special user folio handling
  mm: introduce cpu_icache_is_aliasing() across all architectures
  mm: add RCU annotation to pte_offset_map(_lock)
  mm: correctly reference merged VMA
  mm: use aligned address in copy_user_gigantic_page()
  mm: use aligned address in clear_gigantic_page()
  mm: shmem: fix ShmemHugePages at swapout
  ...

.mailmap

@@ -735,6 +735,7 @@ Wolfram Sang <wsa@kernel.org> <w.sang@pengutronix.de>
 Wolfram Sang <wsa@kernel.org> <wsa@the-dreams.de>
 Yakir Yang <kuankuan.y@gmail.com> <ykk@rock-chips.com>
 Yanteng Si <si.yanteng@linux.dev> <siyanteng@loongson.cn>
+Ying Huang <huang.ying.caritas@gmail.com> <ying.huang@intel.com>
 Yusuke Goda <goda.yusuke@renesas.com>
 Zack Rusin <zack.rusin@broadcom.com> <zackr@vmware.com>
 Zhu Yanjun <zyjzyj2000@gmail.com> <yanjunz@nvidia.com>

Documentation/mm/process_addrs.rst

@@ -3,3 +3,853 @@
 =================
 Process Addresses
 =================
+
+.. toctree::
+   :maxdepth: 3
+
+
+Userland memory ranges are tracked by the kernel via Virtual Memory Areas or
+'VMA's of type :c:struct:`!struct vm_area_struct`.
+
+Each VMA describes a virtually contiguous memory range with identical
+attributes, each described by a :c:struct:`!struct vm_area_struct`
+object. Userland access outside of VMAs is invalid except in the case where an
+adjacent stack VMA could be extended to contain the accessed address.
+
+All VMAs are contained within one and only one virtual address space, described
+by a :c:struct:`!struct mm_struct` object which is referenced by all tasks (that is,
+threads) which share the virtual address space. We refer to this as the
+:c:struct:`!mm`.
+
+Each mm object contains a maple tree data structure which describes all VMAs
+within the virtual address space.
+
+.. note:: An exception to this is the 'gate' VMA which is provided by
+          architectures which use :c:struct:`!vsyscall` and is a global static
+          object which does not belong to any specific mm.
+
+-------
+Locking
+-------
+
+The kernel is designed to be highly scalable against concurrent read operations
+on VMA **metadata** so a complicated set of locks are required to ensure memory
+corruption does not occur.
+
+.. note:: Locking VMAs for their metadata does not have any impact on the memory
+          they describe nor the page tables that map them.
+
+Terminology
+-----------
+
+* **mmap locks** - Each MM has a read/write semaphore :c:member:`!mmap_lock`
+  which locks at a process address space granularity which can be acquired via
+  :c:func:`!mmap_read_lock`, :c:func:`!mmap_write_lock` and variants.
+* **VMA locks** - The VMA lock is at VMA granularity (of course) which behaves
+  as a read/write semaphore in practice. A VMA read lock is obtained via
+  :c:func:`!lock_vma_under_rcu` (and unlocked via :c:func:`!vma_end_read`) and a
+  write lock via :c:func:`!vma_start_write` (all VMA write locks are unlocked
+  automatically when the mmap write lock is released). To take a VMA write lock
+  you **must** have already acquired an :c:func:`!mmap_write_lock`.
+* **rmap locks** - When trying to access VMAs through the reverse mapping via a
+  :c:struct:`!struct address_space` or :c:struct:`!struct anon_vma` object
+  (reachable from a folio via :c:member:`!folio->mapping`). VMAs must be stabilised via
+  :c:func:`!anon_vma_[try]lock_read` or :c:func:`!anon_vma_[try]lock_write` for
+  anonymous memory and :c:func:`!i_mmap_[try]lock_read` or
+  :c:func:`!i_mmap_[try]lock_write` for file-backed memory. We refer to these
+  locks as the reverse mapping locks, or 'rmap locks' for brevity.
+
+We discuss page table locks separately in the dedicated section below.
+
+The first thing **any** of these locks achieve is to **stabilise** the VMA
+within the MM tree. That is, guaranteeing that the VMA object will not be
+deleted from under you nor modified (except for some specific fields
+described below).
+
+Stabilising a VMA also keeps the address space described by it around.
+
+Lock usage
+----------
+
+If you want to **read** VMA metadata fields or just keep the VMA stable, you
+must do one of the following:
+
+* Obtain an mmap read lock at the MM granularity via :c:func:`!mmap_read_lock` (or a
+  suitable variant), unlocking it with a matching :c:func:`!mmap_read_unlock` when
+  you're done with the VMA, *or*
+* Try to obtain a VMA read lock via :c:func:`!lock_vma_under_rcu`. This tries to
+  acquire the lock atomically so might fail, in which case fall-back logic is
+  required to instead obtain an mmap read lock if this returns :c:macro:`!NULL`,
+  *or*
+* Acquire an rmap lock before traversing the locked interval tree (whether
+  anonymous or file-backed) to obtain the required VMA.
+
+If you want to **write** VMA metadata fields, then things vary depending on the
+field (we explore each VMA field in detail below). For the majority you must:
+
+* Obtain an mmap write lock at the MM granularity via :c:func:`!mmap_write_lock` (or a
+  suitable variant), unlocking it with a matching :c:func:`!mmap_write_unlock` when
+  you're done with the VMA, *and*
+* Obtain a VMA write lock via :c:func:`!vma_start_write` for each VMA you wish to
+  modify, which will be released automatically when :c:func:`!mmap_write_unlock` is
+  called.
+* If you want to be able to write to **any** field, you must also hide the VMA
+  from the reverse mapping by obtaining an **rmap write lock**.
+
+VMA locks are special in that you must obtain an mmap **write** lock **first**
+in order to obtain a VMA **write** lock. A VMA **read** lock however can be
+obtained without any other lock (:c:func:`!lock_vma_under_rcu` will acquire then
+release an RCU lock to lookup the VMA for you).
+
+This constrains the impact of writers on readers, as a writer can interact with
+one VMA while a reader interacts with another simultaneously.
+
+.. note:: The primary users of VMA read locks are page fault handlers, which
+          means that without a VMA write lock, page faults will run concurrent with
+          whatever you are doing.
+
+Examining all valid lock states:
+
+.. table::
+
+   ========= ======== ========= ======= ===== =========== ==========
+   mmap lock VMA lock rmap lock Stable? Read? Write most? Write all?
+   ========= ======== ========= ======= ===== =========== ==========
+   \-        \-       \-        N       N     N           N
+   \-        R        \-        Y       Y     N           N
+   \-        \-       R/W       Y       Y     N           N
+   R/W       \-/R     \-/R/W    Y       Y     N           N
+   W         W        \-/R      Y       Y     Y           N
+   W         W        W         Y       Y     Y           Y
+   ========= ======== ========= ======= ===== =========== ==========
+
+.. warning:: While it's possible to obtain a VMA lock while holding an mmap read lock,
+             attempting to do the reverse is invalid as it can result in deadlock - if
+             another task already holds an mmap write lock and attempts to acquire a VMA
+             write lock that will deadlock on the VMA read lock.
+
+All of these locks behave as read/write semaphores in practice, so you can
+obtain either a read or a write lock for each of these.
+
+.. note:: Generally speaking, a read/write semaphore is a class of lock which
+          permits concurrent readers. However a write lock can only be obtained
+          once all readers have left the critical region (and pending readers
+          made to wait).
+
+          This renders read locks on a read/write semaphore concurrent with other
+          readers and write locks exclusive against all others holding the semaphore.
+
+VMA fields
+^^^^^^^^^^
+
+We can subdivide :c:struct:`!struct vm_area_struct` fields by their purpose, which makes it
+easier to explore their locking characteristics:
+
+.. note:: We exclude VMA lock-specific fields here to avoid confusion, as these
+          are in effect an internal implementation detail.
+
+.. table:: Virtual layout fields
+
+   ===================== ======================================== ===========
+   Field                 Description                              Write lock
+   ===================== ======================================== ===========
+   :c:member:`!vm_start` Inclusive start virtual address of range mmap write,
+                         VMA describes.                           VMA write,
+                                                                  rmap write.
+   :c:member:`!vm_end`   Exclusive end virtual address of range   mmap write,
+                         VMA describes.                           VMA write,
+                                                                  rmap write.
+   :c:member:`!vm_pgoff` Describes the page offset into the file, mmap write,
+                         the original page offset within the      VMA write,
+                         virtual address space (prior to any      rmap write.
+                         :c:func:`!mremap`), or PFN if a PFN map
+                         and the architecture does not support
+                         :c:macro:`!CONFIG_ARCH_HAS_PTE_SPECIAL`.
+   ===================== ======================================== ===========
+
+These fields describes the size, start and end of the VMA, and as such cannot be
+modified without first being hidden from the reverse mapping since these fields
+are used to locate VMAs within the reverse mapping interval trees.
+
+.. table:: Core fields
+
+   ============================ ======================================== =========================
+   Field                        Description                              Write lock
+   ============================ ======================================== =========================
+   :c:member:`!vm_mm`           Containing mm_struct.                    None - written once on
+                                                                         initial map.
+   :c:member:`!vm_page_prot`    Architecture-specific page table         mmap write, VMA write.
+                                protection bits determined from VMA
+                                flags.
+   :c:member:`!vm_flags`        Read-only access to VMA flags describing N/A
+                                attributes of the VMA, in union with
+                                private writable
+                                :c:member:`!__vm_flags`.
+   :c:member:`!__vm_flags`      Private, writable access to VMA flags    mmap write, VMA write.
+                                field, updated by
+                                :c:func:`!vm_flags_*` functions.
+   :c:member:`!vm_file`         If the VMA is file-backed, points to a   None - written once on
+                                struct file object describing the        initial map.
+                                underlying file, if anonymous then
+                                :c:macro:`!NULL`.
+   :c:member:`!vm_ops`          If the VMA is file-backed, then either   None - Written once on
+                                the driver or file-system provides a     initial map by
+                                :c:struct:`!struct vm_operations_struct` :c:func:`!f_ops->mmap()`.
+                                object describing callbacks to be
+                                invoked on VMA lifetime events.
+   :c:member:`!vm_private_data` A :c:member:`!void *` field for          Handled by driver.
+                                driver-specific metadata.
+   ============================ ======================================== =========================
+
+These are the core fields which describe the MM the VMA belongs to and its attributes.
+
+.. table:: Config-specific fields
+
+   ================================= ===================== ======================================== ===============
+   Field                             Configuration option  Description                              Write lock
+   ================================= ===================== ======================================== ===============
+   :c:member:`!anon_name`            CONFIG_ANON_VMA_NAME  A field for storing a                    mmap write,
+                                                           :c:struct:`!struct anon_vma_name`        VMA write.
+                                                           object providing a name for anonymous
+                                                           mappings, or :c:macro:`!NULL` if none
+                                                           is set or the VMA is file-backed. The
+							   underlying object is reference counted
+							   and can be shared across multiple VMAs
+							   for scalability.
+   :c:member:`!swap_readahead_info`  CONFIG_SWAP           Metadata used by the swap mechanism      mmap read,
+                                                           to perform readahead. This field is      swap-specific
+                                                           accessed atomically.                     lock.
+   :c:member:`!vm_policy`            CONFIG_NUMA           :c:type:`!mempolicy` object which        mmap write,
+                                                           describes the NUMA behaviour of the      VMA write.
+                                                           VMA. The underlying object is reference
+							   counted.
+   :c:member:`!numab_state`          CONFIG_NUMA_BALANCING :c:type:`!vma_numab_state` object which  mmap read,
+                                                           describes the current state of           numab-specific
+                                                           NUMA balancing in relation to this VMA.  lock.
+                                                           Updated under mmap read lock by
+                                                           :c:func:`!task_numa_work`.
+   :c:member:`!vm_userfaultfd_ctx`   CONFIG_USERFAULTFD    Userfaultfd context wrapper object of    mmap write,
+                                                           type :c:type:`!vm_userfaultfd_ctx`,      VMA write.
+                                                           either of zero size if userfaultfd is
+                                                           disabled, or containing a pointer
+                                                           to an underlying
+                                                           :c:type:`!userfaultfd_ctx` object which
+                                                           describes userfaultfd metadata.
+   ================================= ===================== ======================================== ===============
+
+These fields are present or not depending on whether the relevant kernel
+configuration option is set.
+
+.. table:: Reverse mapping fields
+
+   =================================== ========================================= ============================
+   Field                               Description                               Write lock
+   =================================== ========================================= ============================
+   :c:member:`!shared.rb`              A red/black tree node used, if the        mmap write, VMA write,
+                                       mapping is file-backed, to place the VMA  i_mmap write.
+                                       in the
+                                       :c:member:`!struct address_space->i_mmap`
+                                       red/black interval tree.
+   :c:member:`!shared.rb_subtree_last` Metadata used for management of the       mmap write, VMA write,
+                                       interval tree if the VMA is file-backed.  i_mmap write.
+   :c:member:`!anon_vma_chain`         List of pointers to both forked/CoW’d     mmap read, anon_vma write.
+                                       :c:type:`!anon_vma` objects and
+                                       :c:member:`!vma->anon_vma` if it is
+                                       non-:c:macro:`!NULL`.
+   :c:member:`!anon_vma`               :c:type:`!anon_vma` object used by        When :c:macro:`NULL` and
+                                       anonymous folios mapped exclusively to    setting non-:c:macro:`NULL`:
+                                       this VMA. Initially set by                mmap read, page_table_lock.
+                                       :c:func:`!anon_vma_prepare` serialised
+                                       by the :c:macro:`!page_table_lock`. This  When non-:c:macro:`NULL` and
+                                       is set as soon as any page is faulted in. setting :c:macro:`NULL`:
+                                                                                 mmap write, VMA write,
+                                                                                 anon_vma write.
+   =================================== ========================================= ============================
+
+These fields are used to both place the VMA within the reverse mapping, and for
+anonymous mappings, to be able to access both related :c:struct:`!struct anon_vma` objects
+and the :c:struct:`!struct anon_vma` in which folios mapped exclusively to this VMA should
+reside.
+
+.. note:: If a file-backed mapping is mapped with :c:macro:`!MAP_PRIVATE` set
+          then it can be in both the :c:type:`!anon_vma` and :c:type:`!i_mmap`
+          trees at the same time, so all of these fields might be utilised at
+          once.
+
+Page tables
+-----------
+
+We won't speak exhaustively on the subject but broadly speaking, page tables map
+virtual addresses to physical ones through a series of page tables, each of
+which contain entries with physical addresses for the next page table level
+(along with flags), and at the leaf level the physical addresses of the
+underlying physical data pages or a special entry such as a swap entry,
+migration entry or other special marker. Offsets into these pages are provided
+by the virtual address itself.
+
+In Linux these are divided into five levels - PGD, P4D, PUD, PMD and PTE. Huge
+pages might eliminate one or two of these levels, but when this is the case we
+typically refer to the leaf level as the PTE level regardless.
+
+.. note:: In instances where the architecture supports fewer page tables than
+	  five the kernel cleverly 'folds' page table levels, that is stubbing
+	  out functions related to the skipped levels. This allows us to
+	  conceptually act as if there were always five levels, even if the
+	  compiler might, in practice, eliminate any code relating to missing
+	  ones.
+
+There are four key operations typically performed on page tables:
+
+1. **Traversing** page tables - Simply reading page tables in order to traverse
+   them. This only requires that the VMA is kept stable, so a lock which
+   establishes this suffices for traversal (there are also lockless variants
+   which eliminate even this requirement, such as :c:func:`!gup_fast`).
+2. **Installing** page table mappings - Whether creating a new mapping or
+   modifying an existing one in such a way as to change its identity. This
+   requires that the VMA is kept stable via an mmap or VMA lock (explicitly not
+   rmap locks).
+3. **Zapping/unmapping** page table entries - This is what the kernel calls
+   clearing page table mappings at the leaf level only, whilst leaving all page
+   tables in place. This is a very common operation in the kernel performed on
+   file truncation, the :c:macro:`!MADV_DONTNEED` operation via
+   :c:func:`!madvise`, and others. This is performed by a number of functions
+   including :c:func:`!unmap_mapping_range` and :c:func:`!unmap_mapping_pages`.
+   The VMA need only be kept stable for this operation.
+4. **Freeing** page tables - When finally the kernel removes page tables from a
+   userland process (typically via :c:func:`!free_pgtables`) extreme care must
+   be taken to ensure this is done safely, as this logic finally frees all page
+   tables in the specified range, ignoring existing leaf entries (it assumes the
+   caller has both zapped the range and prevented any further faults or
+   modifications within it).
+
+.. note:: Modifying mappings for reclaim or migration is performed under rmap
+          lock as it, like zapping, does not fundamentally modify the identity
+          of what is being mapped.
+
+**Traversing** and **zapping** ranges can be performed holding any one of the
+locks described in the terminology section above - that is the mmap lock, the
+VMA lock or either of the reverse mapping locks.
+
+That is - as long as you keep the relevant VMA **stable** - you are good to go
+ahead and perform these operations on page tables (though internally, kernel
+operations that perform writes also acquire internal page table locks to
+serialise - see the page table implementation detail section for more details).
+
+When **installing** page table entries, the mmap or VMA lock must be held to
+keep the VMA stable. We explore why this is in the page table locking details
+section below.
+
+.. warning:: Page tables are normally only traversed in regions covered by VMAs.
+             If you want to traverse page tables in areas that might not be
+             covered by VMAs, heavier locking is required.
+             See :c:func:`!walk_page_range_novma` for details.
+
+**Freeing** page tables is an entirely internal memory management operation and
+has special requirements (see the page freeing section below for more details).
+
+.. warning:: When **freeing** page tables, it must not be possible for VMAs
+             containing the ranges those page tables map to be accessible via
+             the reverse mapping.
+
+             The :c:func:`!free_pgtables` function removes the relevant VMAs
+             from the reverse mappings, but no other VMAs can be permitted to be
+             accessible and span the specified range.
+
+Lock ordering
+-------------
+
+As we have multiple locks across the kernel which may or may not be taken at the
+same time as explicit mm or VMA locks, we have to be wary of lock inversion, and
+the **order** in which locks are acquired and released becomes very important.
+
+.. note:: Lock inversion occurs when two threads need to acquire multiple locks,
+   but in doing so inadvertently cause a mutual deadlock.
+
+   For example, consider thread 1 which holds lock A and tries to acquire lock B,
+   while thread 2 holds lock B and tries to acquire lock A.
+
+   Both threads are now deadlocked on each other. However, had they attempted to
+   acquire locks in the same order, one would have waited for the other to
+   complete its work and no deadlock would have occurred.
+
+The opening comment in :c:macro:`!mm/rmap.c` describes in detail the required
+ordering of locks within memory management code:
+
+.. code-block::
+
+  inode->i_rwsem        (while writing or truncating, not reading or faulting)
+    mm->mmap_lock
+      mapping->invalidate_lock (in filemap_fault)
+        folio_lock
+          hugetlbfs_i_mmap_rwsem_key (in huge_pmd_share, see hugetlbfs below)
+            vma_start_write
+              mapping->i_mmap_rwsem
+                anon_vma->rwsem
+                  mm->page_table_lock or pte_lock
+                    swap_lock (in swap_duplicate, swap_info_get)
+                      mmlist_lock (in mmput, drain_mmlist and others)
+                      mapping->private_lock (in block_dirty_folio)
+                          i_pages lock (widely used)
+                            lruvec->lru_lock (in folio_lruvec_lock_irq)
+                      inode->i_lock (in set_page_dirty's __mark_inode_dirty)
+                      bdi.wb->list_lock (in set_page_dirty's __mark_inode_dirty)
+                        sb_lock (within inode_lock in fs/fs-writeback.c)
+                        i_pages lock (widely used, in set_page_dirty,
+                                  in arch-dependent flush_dcache_mmap_lock,
+                                  within bdi.wb->list_lock in __sync_single_inode)
+
+There is also a file-system specific lock ordering comment located at the top of
+:c:macro:`!mm/filemap.c`:
+
+.. code-block::
+
+  ->i_mmap_rwsem                        (truncate_pagecache)
+    ->private_lock                      (__free_pte->block_dirty_folio)
+      ->swap_lock                       (exclusive_swap_page, others)
+        ->i_pages lock
+
+  ->i_rwsem
+    ->invalidate_lock                   (acquired by fs in truncate path)
+      ->i_mmap_rwsem                    (truncate->unmap_mapping_range)
+
+  ->mmap_lock
+    ->i_mmap_rwsem
+      ->page_table_lock or pte_lock     (various, mainly in memory.c)
+        ->i_pages lock                  (arch-dependent flush_dcache_mmap_lock)
+
+  ->mmap_lock
+    ->invalidate_lock                   (filemap_fault)
+      ->lock_page                       (filemap_fault, access_process_vm)
+
+  ->i_rwsem                             (generic_perform_write)
+    ->mmap_lock                         (fault_in_readable->do_page_fault)
+
+  bdi->wb.list_lock
+    sb_lock                             (fs/fs-writeback.c)
+    ->i_pages lock                      (__sync_single_inode)
+
+  ->i_mmap_rwsem
+    ->anon_vma.lock                     (vma_merge)
+
+  ->anon_vma.lock
+    ->page_table_lock or pte_lock       (anon_vma_prepare and various)
+
+  ->page_table_lock or pte_lock
+    ->swap_lock                         (try_to_unmap_one)
+    ->private_lock                      (try_to_unmap_one)
+    ->i_pages lock                      (try_to_unmap_one)
+    ->lruvec->lru_lock                  (follow_page_mask->mark_page_accessed)
+    ->lruvec->lru_lock                  (check_pte_range->folio_isolate_lru)
+    ->private_lock                      (folio_remove_rmap_pte->set_page_dirty)
+    ->i_pages lock                      (folio_remove_rmap_pte->set_page_dirty)
+    bdi.wb->list_lock                   (folio_remove_rmap_pte->set_page_dirty)
+    ->inode->i_lock                     (folio_remove_rmap_pte->set_page_dirty)
+    bdi.wb->list_lock                   (zap_pte_range->set_page_dirty)
+    ->inode->i_lock                     (zap_pte_range->set_page_dirty)
+    ->private_lock                      (zap_pte_range->block_dirty_folio)
+
+Please check the current state of these comments which may have changed since
+the time of writing of this document.
+
+------------------------------
+Locking Implementation Details
+------------------------------
+
+.. warning:: Locking rules for PTE-level page tables are very different from
+             locking rules for page tables at other levels.
+
+Page table locking details
+--------------------------
+
+In addition to the locks described in the terminology section above, we have
+additional locks dedicated to page tables:
+
+* **Higher level page table locks** - Higher level page tables, that is PGD, P4D
+  and PUD each make use of the process address space granularity
+  :c:member:`!mm->page_table_lock` lock when modified.
+
+* **Fine-grained page table locks** - PMDs and PTEs each have fine-grained locks
+  either kept within the folios describing the page tables or allocated
+  separated and pointed at by the folios if :c:macro:`!ALLOC_SPLIT_PTLOCKS` is
+  set. The PMD spin lock is obtained via :c:func:`!pmd_lock`, however PTEs are
+  mapped into higher memory (if a 32-bit system) and carefully locked via
+  :c:func:`!pte_offset_map_lock`.
+
+These locks represent the minimum required to interact with each page table
+level, but there are further requirements.
+
+Importantly, note that on a **traversal** of page tables, sometimes no such
+locks are taken. However, at the PTE level, at least concurrent page table
+deletion must be prevented (using RCU) and the page table must be mapped into
+high memory, see below.
+
+Whether care is taken on reading the page table entries depends on the
+architecture, see the section on atomicity below.
+
+Locking rules
+^^^^^^^^^^^^^
+
+We establish basic locking rules when interacting with page tables:
+
+* When changing a page table entry the page table lock for that page table
+  **must** be held, except if you can safely assume nobody can access the page
+  tables concurrently (such as on invocation of :c:func:`!free_pgtables`).
+* Reads from and writes to page table entries must be *appropriately*
+  atomic. See the section on atomicity below for details.
+* Populating previously empty entries requires that the mmap or VMA locks are
+  held (read or write), doing so with only rmap locks would be dangerous (see
+  the warning below).
+* As mentioned previously, zapping can be performed while simply keeping the VMA
+  stable, that is holding any one of the mmap, VMA or rmap locks.
+
+.. warning:: Populating previously empty entries is dangerous as, when unmapping
+             VMAs, :c:func:`!vms_clear_ptes` has a window of time between
+             zapping (via :c:func:`!unmap_vmas`) and freeing page tables (via
+             :c:func:`!free_pgtables`), where the VMA is still visible in the
+             rmap tree. :c:func:`!free_pgtables` assumes that the zap has
+             already been performed and removes PTEs unconditionally (along with
+             all other page tables in the freed range), so installing new PTE
+             entries could leak memory and also cause other unexpected and
+             dangerous behaviour.
+
+There are additional rules applicable when moving page tables, which we discuss
+in the section on this topic below.
+
+PTE-level page tables are different from page tables at other levels, and there
+are extra requirements for accessing them:
+
+* On 32-bit architectures, they may be in high memory (meaning they need to be
+  mapped into kernel memory to be accessible).
+* When empty, they can be unlinked and RCU-freed while holding an mmap lock or
+  rmap lock for reading in combination with the PTE and PMD page table locks.
+  In particular, this happens in :c:func:`!retract_page_tables` when handling
+  :c:macro:`!MADV_COLLAPSE`.
+  So accessing PTE-level page tables requires at least holding an RCU read lock;
+  but that only suffices for readers that can tolerate racing with concurrent
+  page table updates such that an empty PTE is observed (in a page table that
+  has actually already been detached and marked for RCU freeing) while another
+  new page table has been installed in the same location and filled with
+  entries. Writers normally need to take the PTE lock and revalidate that the
+  PMD entry still refers to the same PTE-level page table.
+
+To access PTE-level page tables, a helper like :c:func:`!pte_offset_map_lock` or
+:c:func:`!pte_offset_map` can be used depending on stability requirements.
+These map the page table into kernel memory if required, take the RCU lock, and
+depending on variant, may also look up or acquire the PTE lock.
+See the comment on :c:func:`!__pte_offset_map_lock`.
+
+Atomicity
+^^^^^^^^^
+
+Regardless of page table locks, the MMU hardware concurrently updates accessed
+and dirty bits (perhaps more, depending on architecture). Additionally, page
+table traversal operations in parallel (though holding the VMA stable) and
+functionality like GUP-fast locklessly traverses (that is reads) page tables,
+without even keeping the VMA stable at all.
+
+When performing a page table traversal and keeping the VMA stable, whether a
+read must be performed once and only once or not depends on the architecture
+(for instance x86-64 does not require any special precautions).
+
+If a write is being performed, or if a read informs whether a write takes place
+(on an installation of a page table entry say, for instance in
+:c:func:`!__pud_install`), special care must always be taken. In these cases we
+can never assume that page table locks give us entirely exclusive access, and
+must retrieve page table entries once and only once.
+
+If we are reading page table entries, then we need only ensure that the compiler
+does not rearrange our loads. This is achieved via :c:func:`!pXXp_get`
+functions - :c:func:`!pgdp_get`, :c:func:`!p4dp_get`, :c:func:`!pudp_get`,
+:c:func:`!pmdp_get`, and :c:func:`!ptep_get`.
+
+Each of these uses :c:func:`!READ_ONCE` to guarantee that the compiler reads
+the page table entry only once.
+
+However, if we wish to manipulate an existing page table entry and care about
+the previously stored data, we must go further and use an hardware atomic
+operation as, for example, in :c:func:`!ptep_get_and_clear`.
+
+Equally, operations that do not rely on the VMA being held stable, such as
+GUP-fast (see :c:func:`!gup_fast` and its various page table level handlers like
+:c:func:`!gup_fast_pte_range`), must very carefully interact with page table
+entries, using functions such as :c:func:`!ptep_get_lockless` and equivalent for
+higher level page table levels.
+
+Writes to page table entries must also be appropriately atomic, as established
+by :c:func:`!set_pXX` functions - :c:func:`!set_pgd`, :c:func:`!set_p4d`,
+:c:func:`!set_pud`, :c:func:`!set_pmd`, and :c:func:`!set_pte`.
+
+Equally functions which clear page table entries must be appropriately atomic,
+as in :c:func:`!pXX_clear` functions - :c:func:`!pgd_clear`,
+:c:func:`!p4d_clear`, :c:func:`!pud_clear`, :c:func:`!pmd_clear`, and
+:c:func:`!pte_clear`.
+
+Page table installation
+^^^^^^^^^^^^^^^^^^^^^^^
+
+Page table installation is performed with the VMA held stable explicitly by an
+mmap or VMA lock in read or write mode (see the warning in the locking rules
+section for details as to why).
+
+When allocating a P4D, PUD or PMD and setting the relevant entry in the above
+PGD, P4D or PUD, the :c:member:`!mm->page_table_lock` must be held. This is
+acquired in :c:func:`!__p4d_alloc`, :c:func:`!__pud_alloc` and
+:c:func:`!__pmd_alloc` respectively.
+
+.. note:: :c:func:`!__pmd_alloc` actually invokes :c:func:`!pud_lock` and
+   :c:func:`!pud_lockptr` in turn, however at the time of writing it ultimately
+   references the :c:member:`!mm->page_table_lock`.
+
+Allocating a PTE will either use the :c:member:`!mm->page_table_lock` or, if
+:c:macro:`!USE_SPLIT_PMD_PTLOCKS` is defined, a lock embedded in the PMD
+physical page metadata in the form of a :c:struct:`!struct ptdesc`, acquired by
+:c:func:`!pmd_ptdesc` called from :c:func:`!pmd_lock` and ultimately
+:c:func:`!__pte_alloc`.
+
+Finally, modifying the contents of the PTE requires special treatment, as the
+PTE page table lock must be acquired whenever we want stable and exclusive
+access to entries contained within a PTE, especially when we wish to modify
+them.
+
+This is performed via :c:func:`!pte_offset_map_lock` which carefully checks to
+ensure that the PTE hasn't changed from under us, ultimately invoking
+:c:func:`!pte_lockptr` to obtain a spin lock at PTE granularity contained within
+the :c:struct:`!struct ptdesc` associated with the physical PTE page. The lock
+must be released via :c:func:`!pte_unmap_unlock`.
+
+.. note:: There are some variants on this, such as
+   :c:func:`!pte_offset_map_rw_nolock` when we know we hold the PTE stable but
+   for brevity we do not explore this.  See the comment for
+   :c:func:`!__pte_offset_map_lock` for more details.
+
+When modifying data in ranges we typically only wish to allocate higher page
+tables as necessary, using these locks to avoid races or overwriting anything,
+and set/clear data at the PTE level as required (for instance when page faulting
+or zapping).
+
+A typical pattern taken when traversing page table entries to install a new
+mapping is to optimistically determine whether the page table entry in the table
+above is empty, if so, only then acquiring the page table lock and checking
+again to see if it was allocated underneath us.
+
+This allows for a traversal with page table locks only being taken when
+required. An example of this is :c:func:`!__pud_alloc`.
+
+At the leaf page table, that is the PTE, we can't entirely rely on this pattern
+as we have separate PMD and PTE locks and a THP collapse for instance might have
+eliminated the PMD entry as well as the PTE from under us.
+
+This is why :c:func:`!__pte_offset_map_lock` locklessly retrieves the PMD entry
+for the PTE, carefully checking it is as expected, before acquiring the
+PTE-specific lock, and then *again* checking that the PMD entry is as expected.
+
+If a THP collapse (or similar) were to occur then the lock on both pages would
+be acquired, so we can ensure this is prevented while the PTE lock is held.
+
+Installing entries this way ensures mutual exclusion on write.
+
+Page table freeing
+^^^^^^^^^^^^^^^^^^
+
+Tearing down page tables themselves is something that requires significant
+care. There must be no way that page tables designated for removal can be
+traversed or referenced by concurrent tasks.
+
+It is insufficient to simply hold an mmap write lock and VMA lock (which will
+prevent racing faults, and rmap operations), as a file-backed mapping can be
+truncated under the :c:struct:`!struct address_space->i_mmap_rwsem` alone.
+
+As a result, no VMA which can be accessed via the reverse mapping (either
+through the :c:struct:`!struct anon_vma->rb_root` or the :c:member:`!struct
+address_space->i_mmap` interval trees) can have its page tables torn down.
+
+The operation is typically performed via :c:func:`!free_pgtables`, which assumes
+either the mmap write lock has been taken (as specified by its
+:c:member:`!mm_wr_locked` parameter), or that the VMA is already unreachable.
+
+It carefully removes the VMA from all reverse mappings, however it's important
+that no new ones overlap these or any route remain to permit access to addresses
+within the range whose page tables are being torn down.
+
+Additionally, it assumes that a zap has already been performed and steps have
+been taken to ensure that no further page table entries can be installed between
+the zap and the invocation of :c:func:`!free_pgtables`.
+
+Since it is assumed that all such steps have been taken, page table entries are
+cleared without page table locks (in the :c:func:`!pgd_clear`, :c:func:`!p4d_clear`,
+:c:func:`!pud_clear`, and :c:func:`!pmd_clear` functions.
+
+.. note:: It is possible for leaf page tables to be torn down independent of
+          the page tables above it as is done by
+          :c:func:`!retract_page_tables`, which is performed under the i_mmap
+          read lock, PMD, and PTE page table locks, without this level of care.
+
+Page table moving
+^^^^^^^^^^^^^^^^^
+
+Some functions manipulate page table levels above PMD (that is PUD, P4D and PGD
+page tables). Most notable of these is :c:func:`!mremap`, which is capable of
+moving higher level page tables.
+
+In these instances, it is required that **all** locks are taken, that is
+the mmap lock, the VMA lock and the relevant rmap locks.
+
+You can observe this in the :c:func:`!mremap` implementation in the functions
+:c:func:`!take_rmap_locks` and :c:func:`!drop_rmap_locks` which perform the rmap
+side of lock acquisition, invoked ultimately by :c:func:`!move_page_tables`.
+
+VMA lock internals
+------------------
+
+Overview
+^^^^^^^^
+
+VMA read locking is entirely optimistic - if the lock is contended or a competing
+write has started, then we do not obtain a read lock.
+
+A VMA **read** lock is obtained by :c:func:`!lock_vma_under_rcu`, which first
+calls :c:func:`!rcu_read_lock` to ensure that the VMA is looked up in an RCU
+critical section, then attempts to VMA lock it via :c:func:`!vma_start_read`,
+before releasing the RCU lock via :c:func:`!rcu_read_unlock`.
+
+VMA read locks hold the read lock on the :c:member:`!vma->vm_lock` semaphore for
+their duration and the caller of :c:func:`!lock_vma_under_rcu` must release it
+via :c:func:`!vma_end_read`.
+
+VMA **write** locks are acquired via :c:func:`!vma_start_write` in instances where a
+VMA is about to be modified, unlike :c:func:`!vma_start_read` the lock is always
+acquired. An mmap write lock **must** be held for the duration of the VMA write
+lock, releasing or downgrading the mmap write lock also releases the VMA write
+lock so there is no :c:func:`!vma_end_write` function.
+
+Note that a semaphore write lock is not held across a VMA lock. Rather, a
+sequence number is used for serialisation, and the write semaphore is only
+acquired at the point of write lock to update this.
+
+This ensures the semantics we require - VMA write locks provide exclusive write
+access to the VMA.
+
+Implementation details
+^^^^^^^^^^^^^^^^^^^^^^
+
+The VMA lock mechanism is designed to be a lightweight means of avoiding the use
+of the heavily contended mmap lock. It is implemented using a combination of a
+read/write semaphore and sequence numbers belonging to the containing
+:c:struct:`!struct mm_struct` and the VMA.
+
+Read locks are acquired via :c:func:`!vma_start_read`, which is an optimistic
+operation, i.e. it tries to acquire a read lock but returns false if it is
+unable to do so. At the end of the read operation, :c:func:`!vma_end_read` is
+called to release the VMA read lock.
+
+Invoking :c:func:`!vma_start_read` requires that :c:func:`!rcu_read_lock` has
+been called first, establishing that we are in an RCU critical section upon VMA
+read lock acquisition. Once acquired, the RCU lock can be released as it is only
+required for lookup. This is abstracted by :c:func:`!lock_vma_under_rcu` which
+is the interface a user should use.
+
+Writing requires the mmap to be write-locked and the VMA lock to be acquired via
+:c:func:`!vma_start_write`, however the write lock is released by the termination or
+downgrade of the mmap write lock so no :c:func:`!vma_end_write` is required.
+
+All this is achieved by the use of per-mm and per-VMA sequence counts, which are
+used in order to reduce complexity, especially for operations which write-lock
+multiple VMAs at once.
+
+If the mm sequence count, :c:member:`!mm->mm_lock_seq` is equal to the VMA
+sequence count :c:member:`!vma->vm_lock_seq` then the VMA is write-locked. If
+they differ, then it is not.
+
+Each time the mmap write lock is released in :c:func:`!mmap_write_unlock` or
+:c:func:`!mmap_write_downgrade`, :c:func:`!vma_end_write_all` is invoked which
+also increments :c:member:`!mm->mm_lock_seq` via
+:c:func:`!mm_lock_seqcount_end`.
+
+This way, we ensure that, regardless of the VMA's sequence number, a write lock
+is never incorrectly indicated and that when we release an mmap write lock we
+efficiently release **all** VMA write locks contained within the mmap at the
+same time.
+
+Since the mmap write lock is exclusive against others who hold it, the automatic
+release of any VMA locks on its release makes sense, as you would never want to
+keep VMAs locked across entirely separate write operations. It also maintains
+correct lock ordering.
+
+Each time a VMA read lock is acquired, we acquire a read lock on the
+:c:member:`!vma->vm_lock` read/write semaphore and hold it, while checking that
+the sequence count of the VMA does not match that of the mm.
+
+If it does, the read lock fails. If it does not, we hold the lock, excluding
+writers, but permitting other readers, who will also obtain this lock under RCU.
+
+Importantly, maple tree operations performed in :c:func:`!lock_vma_under_rcu`
+are also RCU safe, so the whole read lock operation is guaranteed to function
+correctly.
+
+On the write side, we acquire a write lock on the :c:member:`!vma->vm_lock`
+read/write semaphore, before setting the VMA's sequence number under this lock,
+also simultaneously holding the mmap write lock.
+
+This way, if any read locks are in effect, :c:func:`!vma_start_write` will sleep
+until these are finished and mutual exclusion is achieved.
+
+After setting the VMA's sequence number, the lock is released, avoiding
+complexity with a long-term held write lock.
+
+This clever combination of a read/write semaphore and sequence count allows for
+fast RCU-based per-VMA lock acquisition (especially on page fault, though
+utilised elsewhere) with minimal complexity around lock ordering.
+
+mmap write lock downgrading
+---------------------------
+
+When an mmap write lock is held one has exclusive access to resources within the
+mmap (with the usual caveats about requiring VMA write locks to avoid races with
+tasks holding VMA read locks).
+
+It is then possible to **downgrade** from a write lock to a read lock via
+:c:func:`!mmap_write_downgrade` which, similar to :c:func:`!mmap_write_unlock`,
+implicitly terminates all VMA write locks via :c:func:`!vma_end_write_all`, but
+importantly does not relinquish the mmap lock while downgrading, therefore
+keeping the locked virtual address space stable.
+
+An interesting consequence of this is that downgraded locks are exclusive
+against any other task possessing a downgraded lock (since a racing task would
+have to acquire a write lock first to downgrade it, and the downgraded lock
+prevents a new write lock from being obtained until the original lock is
+released).
+
+For clarity, we map read (R)/downgraded write (D)/write (W) locks against one
+another showing which locks exclude the others:
+
+.. list-table:: Lock exclusivity
+   :widths: 5 5 5 5
+   :header-rows: 1
+   :stub-columns: 1
+
+   * -
+     - R
+     - D
+     - W
+   * - R
+     - N
+     - N
+     - Y
+   * - D
+     - N
+     - Y
+     - Y
+   * - W
+     - Y
+     - Y
+     - Y
+
+Here a Y indicates the locks in the matching row/column are mutually exclusive,
+and N indicates that they are not.
+
+Stack expansion
+---------------
+
+Stack expansion throws up additional complexities in that we cannot permit there
+to be racing page faults, as a result we invoke :c:func:`!vma_start_write` to
+prevent this in :c:func:`!expand_downwards` or :c:func:`!expand_upwards`.

arch/arc/Kconfig

@@ -6,6 +6,7 @@
 config ARC
 	def_bool y
 	select ARC_TIMERS
+	select ARCH_HAS_CPU_CACHE_ALIASING
 	select ARCH_HAS_CACHE_LINE_SIZE
 	select ARCH_HAS_DEBUG_VM_PGTABLE
 	select ARCH_HAS_DMA_PREP_COHERENT

arch/arc/include/asm/cachetype.h

@@ -0,0 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_ARC_CACHETYPE_H
+#define __ASM_ARC_CACHETYPE_H
+
+#define cpu_dcache_is_aliasing()	false
+#define cpu_icache_is_aliasing()	true
+
+#endif

drivers/block/zram/zram_drv.c

@@ -614,6 +614,12 @@ static ssize_t backing_dev_store(struct device *dev,
 	}
 
 	nr_pages = i_size_read(inode) >> PAGE_SHIFT;
+	/* Refuse to use zero sized device (also prevents self reference) */
+	if (!nr_pages) {
+		err = -EINVAL;
+		goto out;
+	}
+
 	bitmap_sz = BITS_TO_LONGS(nr_pages) * sizeof(long);
 	bitmap = kvzalloc(bitmap_sz, GFP_KERNEL);
 	if (!bitmap) {
@@ -1438,12 +1444,16 @@ static void zram_meta_free(struct zram *zram, u64 disksize)
 	size_t num_pages = disksize >> PAGE_SHIFT;
 	size_t index;
 
+	if (!zram->table)
+		return;
+
 	/* Free all pages that are still in this zram device */
 	for (index = 0; index < num_pages; index++)
 		zram_free_page(zram, index);
 
 	zs_destroy_pool(zram->mem_pool);
 	vfree(zram->table);
+	zram->table = NULL;
 }
 
 static bool zram_meta_alloc(struct zram *zram, u64 disksize)
@@ -2320,11 +2330,6 @@ static void zram_reset_device(struct zram *zram)
 
 	zram->limit_pages = 0;
 
-	if (!init_done(zram)) {
-		up_write(&zram->init_lock);
-		return;
-	}
-
 	set_capacity_and_notify(zram->disk, 0);
 	part_stat_set_all(zram->disk->part0, 0);
 

fs/hugetlbfs/inode.c

@@ -825,7 +825,7 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset,
 			error = PTR_ERR(folio);
 			goto out;
 		}
-		folio_zero_user(folio, ALIGN_DOWN(addr, hpage_size));
+		folio_zero_user(folio, addr);
 		__folio_mark_uptodate(folio);
 		error = hugetlb_add_to_page_cache(folio, mapping, index);
 		if (unlikely(error)) {

fs/nilfs2/btnode.c

@@ -35,6 +35,7 @@ void nilfs_init_btnc_inode(struct inode *btnc_inode)
 	ii->i_flags = 0;
 	memset(&ii->i_bmap_data, 0, sizeof(struct nilfs_bmap));
 	mapping_set_gfp_mask(btnc_inode->i_mapping, GFP_NOFS);
+	btnc_inode->i_mapping->a_ops = &nilfs_buffer_cache_aops;
 }
 
 void nilfs_btnode_cache_clear(struct address_space *btnc)

fs/nilfs2/gcinode.c

@@ -163,7 +163,7 @@ int nilfs_init_gcinode(struct inode *inode)
 
 	inode->i_mode = S_IFREG;
 	mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS);
-	inode->i_mapping->a_ops = &empty_aops;
+	inode->i_mapping->a_ops = &nilfs_buffer_cache_aops;
 
 	ii->i_flags = 0;
 	nilfs_bmap_init_gc(ii->i_bmap);

fs/nilfs2/inode.c

@@ -276,6 +276,10 @@ const struct address_space_operations nilfs_aops = {
 	.is_partially_uptodate  = block_is_partially_uptodate,
 };
 
+const struct address_space_operations nilfs_buffer_cache_aops = {
+	.invalidate_folio	= block_invalidate_folio,
+};
+
 static int nilfs_insert_inode_locked(struct inode *inode,
 				     struct nilfs_root *root,
 				     unsigned long ino)
@@ -544,8 +548,14 @@ struct inode *nilfs_iget(struct super_block *sb, struct nilfs_root *root,
 	inode = nilfs_iget_locked(sb, root, ino);
 	if (unlikely(!inode))
 		return ERR_PTR(-ENOMEM);
-	if (!(inode->i_state & I_NEW))
+
+	if (!(inode->i_state & I_NEW)) {
+		if (!inode->i_nlink) {
+			iput(inode);
+			return ERR_PTR(-ESTALE);
+		}
 		return inode;
+	}
 
 	err = __nilfs_read_inode(sb, root, ino, inode);
 	if (unlikely(err)) {
@@ -675,6 +685,7 @@ struct inode *nilfs_iget_for_shadow(struct inode *inode)
 	NILFS_I(s_inode)->i_flags = 0;
 	memset(NILFS_I(s_inode)->i_bmap, 0, sizeof(struct nilfs_bmap));
 	mapping_set_gfp_mask(s_inode->i_mapping, GFP_NOFS);
+	s_inode->i_mapping->a_ops = &nilfs_buffer_cache_aops;
 
 	err = nilfs_attach_btree_node_cache(s_inode);
 	if (unlikely(err)) {

fs/nilfs2/namei.c

@@ -67,6 +67,11 @@ nilfs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
 		inode = NULL;
 	} else {
 		inode = nilfs_iget(dir->i_sb, NILFS_I(dir)->i_root, ino);
+		if (inode == ERR_PTR(-ESTALE)) {
+			nilfs_error(dir->i_sb,
+					"deleted inode referenced: %lu", ino);
+			return ERR_PTR(-EIO);
+		}
 	}
 
 	return d_splice_alias(inode, dentry);

fs/nilfs2/nilfs.h

@@ -401,6 +401,7 @@ extern const struct file_operations nilfs_dir_operations;
 extern const struct inode_operations nilfs_file_inode_operations;
 extern const struct file_operations nilfs_file_operations;
 extern const struct address_space_operations nilfs_aops;
+extern const struct address_space_operations nilfs_buffer_cache_aops;
 extern const struct inode_operations nilfs_dir_inode_operations;
 extern const struct inode_operations nilfs_special_inode_operations;
 extern const struct inode_operations nilfs_symlink_inode_operations;

fs/ocfs2/localalloc.c

@@ -971,9 +971,9 @@ static int ocfs2_sync_local_to_main(struct ocfs2_super *osb,
 	start = count = 0;
 	left = le32_to_cpu(alloc->id1.bitmap1.i_total);
 
-	while ((bit_off = ocfs2_find_next_zero_bit(bitmap, left, start)) <
+	while (1) {
-	       left) {
+		bit_off = ocfs2_find_next_zero_bit(bitmap, left, start);
-		if (bit_off == start) {
+		if ((bit_off < left) && (bit_off == start)) {
 			count++;
 			start++;
 			continue;
@@ -998,29 +998,12 @@ static int ocfs2_sync_local_to_main(struct ocfs2_super *osb,
 			}
 		}
 
+		if (bit_off >= left)
+			break;
 		count = 1;
 		start = bit_off + 1;
 	}
 
-	/* clear the contiguous bits until the end boundary */
-	if (count) {
-		blkno = la_start_blk +
-			ocfs2_clusters_to_blocks(osb->sb,
-					start - count);
-
-		trace_ocfs2_sync_local_to_main_free(
-				count, start - count,
-				(unsigned long long)la_start_blk,
-				(unsigned long long)blkno);
-
-		status = ocfs2_release_clusters(handle,
-				main_bm_inode,
-				main_bm_bh, blkno,
-				count);
-		if (status < 0)
-			mlog_errno(status);
-	}
-
 bail:
 	if (status)
 		mlog_errno(status);

include/linux/alloc_tag.h

@@ -63,7 +63,12 @@ static inline void set_codetag_empty(union codetag_ref *ref)
 #else /* CONFIG_MEM_ALLOC_PROFILING_DEBUG */
 
 static inline bool is_codetag_empty(union codetag_ref *ref) { return false; }
-static inline void set_codetag_empty(union codetag_ref *ref) {}
+
+static inline void set_codetag_empty(union codetag_ref *ref)
+{
+	if (ref)
+		ref->ct = NULL;
+}
 
 #endif /* CONFIG_MEM_ALLOC_PROFILING_DEBUG */
 
@@ -135,7 +140,7 @@ static inline struct alloc_tag_counters alloc_tag_read(struct alloc_tag *tag)
 #ifdef CONFIG_MEM_ALLOC_PROFILING_DEBUG
 static inline void alloc_tag_add_check(union codetag_ref *ref, struct alloc_tag *tag)
 {
-	WARN_ONCE(ref && ref->ct,
+	WARN_ONCE(ref && ref->ct && !is_codetag_empty(ref),
 		  "alloc_tag was not cleared (got tag for %s:%u)\n",
 		  ref->ct->filename, ref->ct->lineno);
 

include/linux/cacheinfo.h

@@ -155,8 +155,14 @@ static inline int get_cpu_cacheinfo_id(int cpu, int level)
 
 #ifndef CONFIG_ARCH_HAS_CPU_CACHE_ALIASING
 #define cpu_dcache_is_aliasing()	false
+#define cpu_icache_is_aliasing()	cpu_dcache_is_aliasing()
 #else
 #include <asm/cachetype.h>
+
+#ifndef cpu_icache_is_aliasing
+#define cpu_icache_is_aliasing()	cpu_dcache_is_aliasing()
+#endif
+
 #endif
 
 #endif /* _LINUX_CACHEINFO_H */

include/linux/highmem.h

@@ -224,7 +224,13 @@ static inline
 struct folio *vma_alloc_zeroed_movable_folio(struct vm_area_struct *vma,
 				   unsigned long vaddr)
 {
-	return vma_alloc_folio(GFP_HIGHUSER_MOVABLE | __GFP_ZERO, 0, vma, vaddr);
+	struct folio *folio;
+
+	folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma, vaddr);
+	if (folio && user_alloc_needs_zeroing())
+		clear_user_highpage(&folio->page, vaddr);
+
+	return folio;
 }
 #endif
 

include/linux/mm.h

@@ -31,6 +31,7 @@
 #include <linux/kasan.h>
 #include <linux/memremap.h>
 #include <linux/slab.h>
+#include <linux/cacheinfo.h>
 
 struct mempolicy;
 struct anon_vma;
@@ -3010,7 +3011,15 @@ static inline void pagetable_pte_dtor(struct ptdesc *ptdesc)
 	lruvec_stat_sub_folio(folio, NR_PAGETABLE);
 }
 
-pte_t *__pte_offset_map(pmd_t *pmd, unsigned long addr, pmd_t *pmdvalp);
+pte_t *___pte_offset_map(pmd_t *pmd, unsigned long addr, pmd_t *pmdvalp);
+static inline pte_t *__pte_offset_map(pmd_t *pmd, unsigned long addr,
+			pmd_t *pmdvalp)
+{
+	pte_t *pte;
+
+	__cond_lock(RCU, pte = ___pte_offset_map(pmd, addr, pmdvalp));
+	return pte;
+}
 static inline pte_t *pte_offset_map(pmd_t *pmd, unsigned long addr)
 {
 	return __pte_offset_map(pmd, addr, NULL);
@@ -3023,7 +3032,8 @@ static inline pte_t *pte_offset_map_lock(struct mm_struct *mm, pmd_t *pmd,
 {
 	pte_t *pte;
 
-	__cond_lock(*ptlp, pte = __pte_offset_map_lock(mm, pmd, addr, ptlp));
+	__cond_lock(RCU, __cond_lock(*ptlp,
+			pte = __pte_offset_map_lock(mm, pmd, addr, ptlp)));
 	return pte;
 }
 
@@ -4175,6 +4185,23 @@ static inline int do_mseal(unsigned long start, size_t len_in, unsigned long fla
 }
 #endif
 
+/*
+ * user_alloc_needs_zeroing checks if a user folio from page allocator needs to
+ * be zeroed or not.
+ */
+static inline bool user_alloc_needs_zeroing(void)
+{
+	/*
+	 * for user folios, arch with cache aliasing requires cache flush and
+	 * arc changes folio->flags to make icache coherent with dcache, so
+	 * always return false to make caller use
+	 * clear_user_page()/clear_user_highpage().
+	 */
+	return cpu_dcache_is_aliasing() || cpu_icache_is_aliasing() ||
+	       !static_branch_maybe(CONFIG_INIT_ON_ALLOC_DEFAULT_ON,
+				   &init_on_alloc);
+}
+
 int arch_get_shadow_stack_status(struct task_struct *t, unsigned long __user *status);
 int arch_set_shadow_stack_status(struct task_struct *t, unsigned long status);
 int arch_lock_shadow_stack_status(struct task_struct *t, unsigned long status);

include/linux/page-flags.h

@@ -862,18 +862,10 @@ static inline void ClearPageCompound(struct page *page)
 	ClearPageHead(page);
 }
 FOLIO_FLAG(large_rmappable, FOLIO_SECOND_PAGE)
-FOLIO_TEST_FLAG(partially_mapped, FOLIO_SECOND_PAGE)
+FOLIO_FLAG(partially_mapped, FOLIO_SECOND_PAGE)
-/*
- * PG_partially_mapped is protected by deferred_split split_queue_lock,
- * so its safe to use non-atomic set/clear.
- */
-__FOLIO_SET_FLAG(partially_mapped, FOLIO_SECOND_PAGE)
-__FOLIO_CLEAR_FLAG(partially_mapped, FOLIO_SECOND_PAGE)
 #else
 FOLIO_FLAG_FALSE(large_rmappable)
-FOLIO_TEST_FLAG_FALSE(partially_mapped)
+FOLIO_FLAG_FALSE(partially_mapped)
-__FOLIO_SET_FLAG_NOOP(partially_mapped)
-__FOLIO_CLEAR_FLAG_NOOP(partially_mapped)
 #endif
 
 #define PG_head_mask ((1UL << PG_head))

include/linux/vmstat.h

@@ -515,7 +515,7 @@ static inline const char *node_stat_name(enum node_stat_item item)
 
 static inline const char *lru_list_name(enum lru_list lru)
 {
-	return node_stat_name(NR_LRU_BASE + lru) + 3; // skip "nr_"
+	return node_stat_name(NR_LRU_BASE + (enum node_stat_item)lru) + 3; // skip "nr_"
 }
 
 #if defined(CONFIG_VM_EVENT_COUNTERS) || defined(CONFIG_MEMCG)

kernel/fork.c

@@ -639,11 +639,8 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
 	LIST_HEAD(uf);
 	VMA_ITERATOR(vmi, mm, 0);
 
-	uprobe_start_dup_mmap();
+	if (mmap_write_lock_killable(oldmm))
-	if (mmap_write_lock_killable(oldmm)) {
+		return -EINTR;
-		retval = -EINTR;
-		goto fail_uprobe_end;
-	}
 	flush_cache_dup_mm(oldmm);
 	uprobe_dup_mmap(oldmm, mm);
 	/*
@@ -782,8 +779,6 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
 		dup_userfaultfd_complete(&uf);
 	else
 		dup_userfaultfd_fail(&uf);
-fail_uprobe_end:
-	uprobe_end_dup_mmap();
 	return retval;
 
 fail_nomem_anon_vma_fork:
@@ -1692,9 +1687,11 @@ static struct mm_struct *dup_mm(struct task_struct *tsk,
 	if (!mm_init(mm, tsk, mm->user_ns))
 		goto fail_nomem;
 
+	uprobe_start_dup_mmap();
 	err = dup_mmap(mm, oldmm);
 	if (err)
 		goto free_pt;
+	uprobe_end_dup_mmap();
 
 	mm->hiwater_rss = get_mm_rss(mm);
 	mm->hiwater_vm = mm->total_vm;
@@ -1709,6 +1706,8 @@ static struct mm_struct *dup_mm(struct task_struct *tsk,
 	mm->binfmt = NULL;
 	mm_init_owner(mm, NULL);
 	mmput(mm);
+	if (err)
+		uprobe_end_dup_mmap();
 
 fail_nomem:
 	return NULL;

lib/alloc_tag.c

@@ -209,6 +209,13 @@ void pgalloc_tag_swap(struct folio *new, struct folio *old)
 		return;
 	}
 
+	/*
+	 * Clear tag references to avoid debug warning when using
+	 * __alloc_tag_ref_set() with non-empty reference.
+	 */
+	set_codetag_empty(&ref_old);
+	set_codetag_empty(&ref_new);
+
 	/* swap tags */
 	__alloc_tag_ref_set(&ref_old, tag_new);
 	update_page_tag_ref(handle_old, &ref_old);
@@ -401,28 +408,52 @@ static bool find_aligned_area(struct ma_state *mas, unsigned long section_size,
 
 static int vm_module_tags_populate(void)
 {
-	unsigned long phys_size = vm_module_tags->nr_pages << PAGE_SHIFT;
+	unsigned long phys_end = ALIGN_DOWN(module_tags.start_addr, PAGE_SIZE) +
+				 (vm_module_tags->nr_pages << PAGE_SHIFT);
+	unsigned long new_end = module_tags.start_addr + module_tags.size;
 
-	if (phys_size < module_tags.size) {
+	if (phys_end < new_end) {
 		struct page **next_page = vm_module_tags->pages + vm_module_tags->nr_pages;
-		unsigned long addr = module_tags.start_addr + phys_size;
+		unsigned long old_shadow_end = ALIGN(phys_end, MODULE_ALIGN);
+		unsigned long new_shadow_end = ALIGN(new_end, MODULE_ALIGN);
 		unsigned long more_pages;
 		unsigned long nr;
 
-		more_pages = ALIGN(module_tags.size - phys_size, PAGE_SIZE) >> PAGE_SHIFT;
+		more_pages = ALIGN(new_end - phys_end, PAGE_SIZE) >> PAGE_SHIFT;
 		nr = alloc_pages_bulk_array_node(GFP_KERNEL | __GFP_NOWARN,
 						 NUMA_NO_NODE, more_pages, next_page);
 		if (nr < more_pages ||
-		    vmap_pages_range(addr, addr + (nr << PAGE_SHIFT), PAGE_KERNEL,
+		    vmap_pages_range(phys_end, phys_end + (nr << PAGE_SHIFT), PAGE_KERNEL,
 				     next_page, PAGE_SHIFT) < 0) {
 			/* Clean up and error out */
 			for (int i = 0; i < nr; i++)
 				__free_page(next_page[i]);
 			return -ENOMEM;
 		}
+
 		vm_module_tags->nr_pages += nr;
+
+		/*
+		 * Kasan allocates 1 byte of shadow for every 8 bytes of data.
+		 * When kasan_alloc_module_shadow allocates shadow memory,
+		 * its unit of allocation is a page.
+		 * Therefore, here we need to align to MODULE_ALIGN.
+		 */
+		if (old_shadow_end < new_shadow_end)
+			kasan_alloc_module_shadow((void *)old_shadow_end,
+						  new_shadow_end - old_shadow_end,
+						  GFP_KERNEL);
 	}
 
+	/*
+	 * Mark the pages as accessible, now that they are mapped.
+	 * With hardware tag-based KASAN, marking is skipped for
+	 * non-VM_ALLOC mappings, see __kasan_unpoison_vmalloc().
+	 */
+	kasan_unpoison_vmalloc((void *)module_tags.start_addr,
+				new_end - module_tags.start_addr,
+				KASAN_VMALLOC_PROT_NORMAL);
+
 	return 0;
 }
 

mm/huge_memory.c

@@ -1176,11 +1176,12 @@ static struct folio *vma_alloc_anon_folio_pmd(struct vm_area_struct *vma,
 	folio_throttle_swaprate(folio, gfp);
 
        /*
-	* When a folio is not zeroed during allocation (__GFP_ZERO not used),
+	* When a folio is not zeroed during allocation (__GFP_ZERO not used)
-	* folio_zero_user() is used to make sure that the page corresponding
+	* or user folios require special handling, folio_zero_user() is used to
-	* to the faulting address will be hot in the cache after zeroing.
+	* make sure that the page corresponding to the faulting address will be
+	* hot in the cache after zeroing.
 	*/
-	if (!alloc_zeroed())
+	if (user_alloc_needs_zeroing())
 		folio_zero_user(folio, addr);
 	/*
 	 * The memory barrier inside __folio_mark_uptodate makes sure that
@@ -3576,7 +3577,7 @@ int split_huge_page_to_list_to_order(struct page *page, struct list_head *list,
 		    !list_empty(&folio->_deferred_list)) {
 			ds_queue->split_queue_len--;
 			if (folio_test_partially_mapped(folio)) {
-				__folio_clear_partially_mapped(folio);
+				folio_clear_partially_mapped(folio);
 				mod_mthp_stat(folio_order(folio),
 					      MTHP_STAT_NR_ANON_PARTIALLY_MAPPED, -1);
 			}
@@ -3688,7 +3689,7 @@ bool __folio_unqueue_deferred_split(struct folio *folio)
 	if (!list_empty(&folio->_deferred_list)) {
 		ds_queue->split_queue_len--;
 		if (folio_test_partially_mapped(folio)) {
-			__folio_clear_partially_mapped(folio);
+			folio_clear_partially_mapped(folio);
 			mod_mthp_stat(folio_order(folio),
 				      MTHP_STAT_NR_ANON_PARTIALLY_MAPPED, -1);
 		}
@@ -3732,7 +3733,7 @@ void deferred_split_folio(struct folio *folio, bool partially_mapped)
 	spin_lock_irqsave(&ds_queue->split_queue_lock, flags);
 	if (partially_mapped) {
 		if (!folio_test_partially_mapped(folio)) {
-			__folio_set_partially_mapped(folio);
+			folio_set_partially_mapped(folio);
 			if (folio_test_pmd_mappable(folio))
 				count_vm_event(THP_DEFERRED_SPLIT_PAGE);
 			count_mthp_stat(folio_order(folio), MTHP_STAT_SPLIT_DEFERRED);
@@ -3825,7 +3826,7 @@ static unsigned long deferred_split_scan(struct shrinker *shrink,
 		} else {
 			/* We lost race with folio_put() */
 			if (folio_test_partially_mapped(folio)) {
-				__folio_clear_partially_mapped(folio);
+				folio_clear_partially_mapped(folio);
 				mod_mthp_stat(folio_order(folio),
 					      MTHP_STAT_NR_ANON_PARTIALLY_MAPPED, -1);
 			}
@@ -4168,7 +4169,7 @@ static ssize_t split_huge_pages_write(struct file *file, const char __user *buf,
 		size_t input_len = strlen(input_buf);
 
 		tok = strsep(&buf, ",");
-		if (tok) {
+		if (tok && buf) {
 			strscpy(file_path, tok);
 		} else {
 			ret = -EINVAL;

mm/hugetlb.c

@@ -5340,7 +5340,7 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 					break;
 				}
 				ret = copy_user_large_folio(new_folio, pte_folio,
-						ALIGN_DOWN(addr, sz), dst_vma);
+							    addr, dst_vma);
 				folio_put(pte_folio);
 				if (ret) {
 					folio_put(new_folio);
@@ -6643,8 +6643,7 @@ int hugetlb_mfill_atomic_pte(pte_t *dst_pte,
 			*foliop = NULL;
 			goto out;
 		}
-		ret = copy_user_large_folio(folio, *foliop,
+		ret = copy_user_large_folio(folio, *foliop, dst_addr, dst_vma);
-					    ALIGN_DOWN(dst_addr, size), dst_vma);
 		folio_put(*foliop);
 		*foliop = NULL;
 		if (ret) {

mm/internal.h

@@ -1285,12 +1285,6 @@ void touch_pud(struct vm_area_struct *vma, unsigned long addr,
 void touch_pmd(struct vm_area_struct *vma, unsigned long addr,
 	       pmd_t *pmd, bool write);
 
-static inline bool alloc_zeroed(void)
-{
-	return static_branch_maybe(CONFIG_INIT_ON_ALLOC_DEFAULT_ON,
-			&init_on_alloc);
-}
-
 /*
  * Parses a string with mem suffixes into its order. Useful to parse kernel
  * parameters.

mm/memory.c

@@ -4733,12 +4733,12 @@ static struct folio *alloc_anon_folio(struct vm_fault *vmf)
 			folio_throttle_swaprate(folio, gfp);
 			/*
 			 * When a folio is not zeroed during allocation
-			 * (__GFP_ZERO not used), folio_zero_user() is used
+			 * (__GFP_ZERO not used) or user folios require special
-			 * to make sure that the page corresponding to the
+			 * handling, folio_zero_user() is used to make sure
-			 * faulting address will be hot in the cache after
+			 * that the page corresponding to the faulting address
-			 * zeroing.
+			 * will be hot in the cache after zeroing.
 			 */
-			if (!alloc_zeroed())
+			if (user_alloc_needs_zeroing())
 				folio_zero_user(folio, vmf->address);
 			return folio;
 		}
@@ -6815,9 +6815,10 @@ static inline int process_huge_page(
 	return 0;
 }
 
-static void clear_gigantic_page(struct folio *folio, unsigned long addr,
+static void clear_gigantic_page(struct folio *folio, unsigned long addr_hint,
 				unsigned int nr_pages)
 {
+	unsigned long addr = ALIGN_DOWN(addr_hint, folio_size(folio));
 	int i;
 
 	might_sleep();
@@ -6851,13 +6852,14 @@ void folio_zero_user(struct folio *folio, unsigned long addr_hint)
 }
 
 static int copy_user_gigantic_page(struct folio *dst, struct folio *src,
-				   unsigned long addr,
+				   unsigned long addr_hint,
 				   struct vm_area_struct *vma,
 				   unsigned int nr_pages)
 {
-	int i;
+	unsigned long addr = ALIGN_DOWN(addr_hint, folio_size(dst));
 	struct page *dst_page;
 	struct page *src_page;
+	int i;
 
 	for (i = 0; i < nr_pages; i++) {
 		dst_page = folio_page(dst, i);

mm/page_alloc.c

@@ -1238,13 +1238,15 @@ static void split_large_buddy(struct zone *zone, struct page *page,
 	if (order > pageblock_order)
 		order = pageblock_order;
 
-	while (pfn != end) {
+	do {
 		int mt = get_pfnblock_migratetype(page, pfn);
 
 		__free_one_page(page, pfn, zone, order, mt, fpi);
 		pfn += 1 << order;
+		if (pfn == end)
+			break;
 		page = pfn_to_page(pfn);
-	}
+	} while (1);
 }
 
 static void free_one_page(struct zone *zone, struct page *page,

mm/pgtable-generic.c

@@ -279,7 +279,7 @@ static unsigned long pmdp_get_lockless_start(void) { return 0; }
 static void pmdp_get_lockless_end(unsigned long irqflags) { }
 #endif
 
-pte_t *__pte_offset_map(pmd_t *pmd, unsigned long addr, pmd_t *pmdvalp)
+pte_t *___pte_offset_map(pmd_t *pmd, unsigned long addr, pmd_t *pmdvalp)
 {
 	unsigned long irqflags;
 	pmd_t pmdval;

mm/shmem.c

@@ -787,6 +787,14 @@ static bool shmem_huge_global_enabled(struct inode *inode, pgoff_t index,
 }
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
+static void shmem_update_stats(struct folio *folio, int nr_pages)
+{
+	if (folio_test_pmd_mappable(folio))
+		__lruvec_stat_mod_folio(folio, NR_SHMEM_THPS, nr_pages);
+	__lruvec_stat_mod_folio(folio, NR_FILE_PAGES, nr_pages);
+	__lruvec_stat_mod_folio(folio, NR_SHMEM, nr_pages);
+}
+
 /*
  * Somewhat like filemap_add_folio, but error if expected item has gone.
  */
@@ -821,10 +829,7 @@ static int shmem_add_to_page_cache(struct folio *folio,
 		xas_store(&xas, folio);
 		if (xas_error(&xas))
 			goto unlock;
-		if (folio_test_pmd_mappable(folio))
+		shmem_update_stats(folio, nr);
-			__lruvec_stat_mod_folio(folio, NR_SHMEM_THPS, nr);
-		__lruvec_stat_mod_folio(folio, NR_FILE_PAGES, nr);
-		__lruvec_stat_mod_folio(folio, NR_SHMEM, nr);
 		mapping->nrpages += nr;
 unlock:
 		xas_unlock_irq(&xas);
@@ -852,8 +857,7 @@ static void shmem_delete_from_page_cache(struct folio *folio, void *radswap)
 	error = shmem_replace_entry(mapping, folio->index, folio, radswap);
 	folio->mapping = NULL;
 	mapping->nrpages -= nr;
-	__lruvec_stat_mod_folio(folio, NR_FILE_PAGES, -nr);
+	shmem_update_stats(folio, -nr);
-	__lruvec_stat_mod_folio(folio, NR_SHMEM, -nr);
 	xa_unlock_irq(&mapping->i_pages);
 	folio_put_refs(folio, nr);
 	BUG_ON(error);
@@ -1969,10 +1973,8 @@ static int shmem_replace_folio(struct folio **foliop, gfp_t gfp,
 	}
 	if (!error) {
 		mem_cgroup_replace_folio(old, new);
-		__lruvec_stat_mod_folio(new, NR_FILE_PAGES, nr_pages);
+		shmem_update_stats(new, nr_pages);
-		__lruvec_stat_mod_folio(new, NR_SHMEM, nr_pages);
+		shmem_update_stats(old, -nr_pages);
-		__lruvec_stat_mod_folio(old, NR_FILE_PAGES, -nr_pages);
-		__lruvec_stat_mod_folio(old, NR_SHMEM, -nr_pages);
 	}
 	xa_unlock_irq(&swap_mapping->i_pages);
 

mm/vma.c

@@ -2460,10 +2460,13 @@ unsigned long __mmap_region(struct file *file, unsigned long addr,
 
 	/* If flags changed, we might be able to merge, so try again. */
 	if (map.retry_merge) {
+		struct vm_area_struct *merged;
 		VMG_MMAP_STATE(vmg, &map, vma);
 
 		vma_iter_config(map.vmi, map.addr, map.end);
-		vma_merge_existing_range(&vmg);
+		merged = vma_merge_existing_range(&vmg);
+		if (merged)
+			vma = merged;
 	}
 
 	__mmap_complete(&map, vma);

mm/vmalloc.c

@@ -3374,7 +3374,8 @@ void vfree(const void *addr)
 		struct page *page = vm->pages[i];
 
 		BUG_ON(!page);
-		mod_memcg_page_state(page, MEMCG_VMALLOC, -1);
+		if (!(vm->flags & VM_MAP_PUT_PAGES))
+			mod_memcg_page_state(page, MEMCG_VMALLOC, -1);
 		/*
 		 * High-order allocs for huge vmallocs are split, so
 		 * can be freed as an array of order-0 allocations
@@ -3382,7 +3383,8 @@ void vfree(const void *addr)
 		__free_page(page);
 		cond_resched();
 	}
-	atomic_long_sub(vm->nr_pages, &nr_vmalloc_pages);
+	if (!(vm->flags & VM_MAP_PUT_PAGES))
+		atomic_long_sub(vm->nr_pages, &nr_vmalloc_pages);
 	kvfree(vm->pages);
 	kfree(vm);
 }

tools/testing/selftests/memfd/memfd_test.c

@@ -9,6 +9,7 @@
 #include <fcntl.h>
 #include <linux/memfd.h>
 #include <sched.h>
+#include <stdbool.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <signal.h>
@@ -1557,6 +1558,11 @@ static void test_share_fork(char *banner, char *b_suffix)
 	close(fd);
 }
 
+static bool pid_ns_supported(void)
+{
+	return access("/proc/self/ns/pid", F_OK) == 0;
+}
+
 int main(int argc, char **argv)
 {
 	pid_t pid;
@@ -1591,8 +1597,12 @@ int main(int argc, char **argv)
 	test_seal_grow();
 	test_seal_resize();
 
-	test_sysctl_simple();
+	if (pid_ns_supported()) {
-	test_sysctl_nested();
+		test_sysctl_simple();
+		test_sysctl_nested();
+	} else {
+		printf("PID namespaces are not supported; skipping sysctl tests\n");
+	}
 
 	test_share_dup("SHARE-DUP", "");
 	test_share_mmap("SHARE-MMAP", "");