Merge tag 'mm-hotfixes-stable-2025-01-04-18-02' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull hotfixes from Andrew Morton:
 "25 hotfixes.  16 are cc:stable.  18 are MM and 7 are non-MM.

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

* tag 'mm-hotfixes-stable-2025-01-04-18-02' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (25 commits)
  MAINTAINERS: change Arınç _NAL's name and email address
  scripts/sorttable: fix orc_sort_cmp() to maintain symmetry and transitivity
  mm/util: make memdup_user_nul() similar to memdup_user()
  mm, madvise: fix potential workingset node list_lru leaks
  mm/damon/core: fix ignored quota goals and filters of newly committed schemes
  mm/damon/core: fix new damon_target objects leaks on damon_commit_targets()
  mm/list_lru: fix false warning of negative counter
  vmstat: disable vmstat_work on vmstat_cpu_down_prep()
  mm: shmem: fix the update of 'shmem_falloc->nr_unswapped'
  mm: shmem: fix incorrect index alignment for within_size policy
  percpu: remove intermediate variable in PERCPU_PTR()
  mm: zswap: fix race between [de]compression and CPU hotunplug
  ocfs2: fix slab-use-after-free due to dangling pointer dqi_priv
  fs/proc/task_mmu: fix pagemap flags with PMD THP entries on 32bit
  kcov: mark in_softirq_really() as __always_inline
  docs: mm: fix the incorrect 'FileHugeMapped' field
  mailmap: modify the entry for Mathieu Othacehe
  mm/kmemleak: fix sleeping function called from invalid context at print message
  mm: hugetlb: independent PMD page table shared count
  maple_tree: reload mas before the second call for mas_empty_area
  ...

4 files changed, 86 insertions, 22 deletions

diff --git a/include/linux/memfd.h b/include/linux/memfd.h
index 3f2cf339ceaf..d437e3070850 100644
--- a/include/linux/memfd.h
+++ b/include/linux/memfd.h
@@ -7,6 +7,7 @@
 #ifdef CONFIG_MEMFD_CREATE
 extern long memfd_fcntl(struct file *file, unsigned int cmd, unsigned int arg);
 struct folio *memfd_alloc_folio(struct file *memfd, pgoff_t idx);
+unsigned int *memfd_file_seals_ptr(struct file *file);
 #else
 static inline long memfd_fcntl(struct file *f, unsigned int c, unsigned int a)
 {
@@ -16,6 +17,19 @@ static inline struct folio *memfd_alloc_folio(struct file *memfd, pgoff_t idx)
 {
 	return ERR_PTR(-EINVAL);
 }
+
+static inline unsigned int *memfd_file_seals_ptr(struct file *file)
+{
+	return NULL;
+}
 #endif
 
+/* Retrieve memfd seals associated with the file, if any. */
+static inline unsigned int memfd_file_seals(struct file *file)
+{
+	unsigned int *sealsp = memfd_file_seals_ptr(file);
+
+	return sealsp ? *sealsp : 0;
+}
+
 #endif /* __LINUX_MEMFD_H */
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 338a76ce9083..b1c3db9cf355 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -3125,6 +3125,7 @@ static inline bool pagetable_pmd_ctor(struct ptdesc *ptdesc)
 	if (!pmd_ptlock_init(ptdesc))
 		return false;
 	__folio_set_pgtable(folio);
+	ptdesc_pmd_pts_init(ptdesc);
 	lruvec_stat_add_folio(folio, NR_PAGETABLE);
 	return true;
 }
@@ -4101,6 +4102,37 @@ void mem_dump_obj(void *object);
 static inline void mem_dump_obj(void *object) {}
 #endif
 
+static inline bool is_write_sealed(int seals)
+{
+	return seals & (F_SEAL_WRITE | F_SEAL_FUTURE_WRITE);
+}
+
+/**
+ * is_readonly_sealed - Checks whether write-sealed but mapped read-only,
+ *                      in which case writes should be disallowing moving
+ *                      forwards.
+ * @seals: the seals to check
+ * @vm_flags: the VMA flags to check
+ *
+ * Returns whether readonly sealed, in which case writess should be disallowed
+ * going forward.
+ */
+static inline bool is_readonly_sealed(int seals, vm_flags_t vm_flags)
+{
+	/*
+	 * Since an F_SEAL_[FUTURE_]WRITE sealed memfd can be mapped as
+	 * MAP_SHARED and read-only, take care to not allow mprotect to
+	 * revert protections on such mappings. Do this only for shared
+	 * mappings. For private mappings, don't need to mask
+	 * VM_MAYWRITE as we still want them to be COW-writable.
+	 */
+	if (is_write_sealed(seals) &&
+	    ((vm_flags & (VM_SHARED | VM_WRITE)) == VM_SHARED))
+		return true;
+
+	return false;
+}
+
 /**
  * seal_check_write - Check for F_SEAL_WRITE or F_SEAL_FUTURE_WRITE flags and
  *                    handle them.
@@ -4112,24 +4144,15 @@ static inline void mem_dump_obj(void *object) {}
  */
 static inline int seal_check_write(int seals, struct vm_area_struct *vma)
 {
-	if (seals & (F_SEAL_WRITE | F_SEAL_FUTURE_WRITE)) {
-		/*
-		 * New PROT_WRITE and MAP_SHARED mmaps are not allowed when
-		 * write seals are active.
-		 */
-		if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_WRITE))
-			return -EPERM;
-
-		/*
-		 * Since an F_SEAL_[FUTURE_]WRITE sealed memfd can be mapped as
-		 * MAP_SHARED and read-only, take care to not allow mprotect to
-		 * revert protections on such mappings. Do this only for shared
-		 * mappings. For private mappings, don't need to mask
-		 * VM_MAYWRITE as we still want them to be COW-writable.
-		 */
-		if (vma->vm_flags & VM_SHARED)
-			vm_flags_clear(vma, VM_MAYWRITE);
-	}
+	if (!is_write_sealed(seals))
+		return 0;
+
+	/*
+	 * New PROT_WRITE and MAP_SHARED mmaps are not allowed when
+	 * write seals are active.
+	 */
+	if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_WRITE))
+		return -EPERM;
 
 	return 0;
 }
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 7361a8f3ab68..332cee285662 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -445,6 +445,7 @@ FOLIO_MATCH(compound_head, _head_2a);
  * @pt_index:         Used for s390 gmap.
  * @pt_mm:            Used for x86 pgds.
  * @pt_frag_refcount: For fragmented page table tracking. Powerpc only.
+ * @pt_share_count:   Used for HugeTLB PMD page table share count.
  * @_pt_pad_2:        Padding to ensure proper alignment.
  * @ptl:              Lock for the page table.
  * @__page_type:      Same as page->page_type. Unused for page tables.
@@ -471,6 +472,9 @@ struct ptdesc {
 		pgoff_t pt_index;
 		struct mm_struct *pt_mm;
 		atomic_t pt_frag_refcount;
+#ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING
+		atomic_t pt_share_count;
+#endif
 	};
 
 	union {
@@ -516,6 +520,32 @@ static_assert(sizeof(struct ptdesc) <= sizeof(struct page));
 	const struct page *:		(const struct ptdesc *)(p),	\
 	struct page *:			(struct ptdesc *)(p)))
 
+#ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING
+static inline void ptdesc_pmd_pts_init(struct ptdesc *ptdesc)
+{
+	atomic_set(&ptdesc->pt_share_count, 0);
+}
+
+static inline void ptdesc_pmd_pts_inc(struct ptdesc *ptdesc)
+{
+	atomic_inc(&ptdesc->pt_share_count);
+}
+
+static inline void ptdesc_pmd_pts_dec(struct ptdesc *ptdesc)
+{
+	atomic_dec(&ptdesc->pt_share_count);
+}
+
+static inline int ptdesc_pmd_pts_count(struct ptdesc *ptdesc)
+{
+	return atomic_read(&ptdesc->pt_share_count);
+}
+#else
+static inline void ptdesc_pmd_pts_init(struct ptdesc *ptdesc)
+{
+}
+#endif
+
 /*
  * Used for sizing the vmemmap region on some architectures
  */
diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h
index 35842d1e3879..5b520fe86b60 100644
--- a/include/linux/percpu-defs.h
+++ b/include/linux/percpu-defs.h
@@ -221,10 +221,7 @@ do {									\
 } while (0)
 
 #define PERCPU_PTR(__p)							\
-({									\
-	unsigned long __pcpu_ptr = (__force unsigned long)(__p);	\
-	(typeof(*(__p)) __force __kernel *)(__pcpu_ptr);		\
-})
+	(typeof(*(__p)) __force __kernel *)((__force unsigned long)(__p))
 
 #ifdef CONFIG_SMP