Merge tag 'mm-hotfixes-stable-2023-10-01-08-34' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull misc fixes from Andrew Morton:
"Fourteen hotfixes, eleven of which are cc:stable. The remainder
pertain to issues which were introduced after 6.5"

* tag 'mm-hotfixes-stable-2023-10-01-08-34' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm:
Crash: add lock to serialize crash hotplug handling
selftests/mm: fix awk usage in charge_reserved_hugetlb.sh and hugetlb_reparenting_test.sh that may cause error
mm: mempolicy: keep VMA walk if both MPOL_MF_STRICT and MPOL_MF_MOVE are specified
mm/damon/vaddr-test: fix memory leak in damon_do_test_apply_three_regions()
mm, memcg: reconsider kmem.limit_in_bytes deprecation
mm: zswap: fix potential memory corruption on duplicate store
arm64: hugetlb: fix set_huge_pte_at() to work with all swap entries
mm: hugetlb: add huge page size param to set_huge_pte_at()
maple_tree: add MAS_UNDERFLOW and MAS_OVERFLOW states
maple_tree: add mas_is_active() to detect in-tree walks
nilfs2: fix potential use after free in nilfs_gccache_submit_read_data()
mm: abstract moving to the next PFN
mm: report success more often from filemap_map_folio_range()
fs: binfmt_elf_efpic: fix personality for ELF-FDPIC

Documentation/admin-guide/cgroup-v1/memory.rst

···
  memory.oom_control		     set/show oom controls.
  memory.numa_stat		     show the number of memory usage per numa
 				     node
+ memory.kmem.limit_in_bytes          Deprecated knob to set and read the kernel
+                                     memory hard limit. Kernel hard limit is not
+                                     supported since 5.16. Writing any value to
+                                     do file will not have any effect same as if
+                                     nokmem kernel parameter was specified.
+                                     Kernel memory is still charged and reported
+                                     by memory.kmem.usage_in_bytes.
  memory.kmem.usage_in_bytes          show current kernel memory allocation
  memory.kmem.failcnt                 show the number of kernel memory usage
 				     hits limits

arch/arm64/include/asm/hugetlb.h

···
 #define arch_make_huge_pte arch_make_huge_pte
 #define __HAVE_ARCH_HUGE_SET_HUGE_PTE_AT
 extern void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
-			    pte_t *ptep, pte_t pte);
+			    pte_t *ptep, pte_t pte, unsigned long sz);
 #define __HAVE_ARCH_HUGE_PTEP_SET_ACCESS_FLAGS
 extern int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 				      unsigned long addr, pte_t *ptep,

arch/arm64/mm/hugetlbpage.c

···
 	flush_tlb_range(&vma, saddr, addr);
 }
 
-static inline struct folio *hugetlb_swap_entry_to_folio(swp_entry_t entry)
-{
-	VM_BUG_ON(!is_migration_entry(entry) && !is_hwpoison_entry(entry));
-
-	return page_folio(pfn_to_page(swp_offset_pfn(entry)));
-}
-
 void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
-			    pte_t *ptep, pte_t pte)
+			    pte_t *ptep, pte_t pte, unsigned long sz)
 {
 	size_t pgsize;
 	int i;
···
 	unsigned long pfn, dpfn;
 	pgprot_t hugeprot;
 
+	ncontig = num_contig_ptes(sz, &pgsize);
+
 	if (!pte_present(pte)) {
-		struct folio *folio;
-
-		folio = hugetlb_swap_entry_to_folio(pte_to_swp_entry(pte));
-		ncontig = num_contig_ptes(folio_size(folio), &pgsize);
-
-		for (i = 0; i < ncontig; i++, ptep++)
+		for (i = 0; i < ncontig; i++, ptep++, addr += pgsize)
 			set_pte_at(mm, addr, ptep, pte);
 		return;
 	}
···
 		return;
 	}
 
-	ncontig = find_num_contig(mm, addr, ptep, &pgsize);
 	pfn = pte_pfn(pte);
 	dpfn = pgsize >> PAGE_SHIFT;
 	hugeprot = pte_pgprot(pte);
···
 void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep,
 				  pte_t old_pte, pte_t pte)
 {
-	set_huge_pte_at(vma->vm_mm, addr, ptep, pte);
+	unsigned long psize = huge_page_size(hstate_vma(vma));
+
+	set_huge_pte_at(vma->vm_mm, addr, ptep, pte, psize);
 }

arch/parisc/include/asm/hugetlb.h

···
 
 #define __HAVE_ARCH_HUGE_SET_HUGE_PTE_AT
 void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
-		     pte_t *ptep, pte_t pte);
+		     pte_t *ptep, pte_t pte, unsigned long sz);
 
 #define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
 pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,

arch/parisc/mm/hugetlbpage.c

···
 }
 
 void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
-		     pte_t *ptep, pte_t entry)
+		     pte_t *ptep, pte_t entry, unsigned long sz)
 {
 	__set_huge_pte_at(mm, addr, ptep, entry);
 }

arch/powerpc/include/asm/nohash/32/hugetlb-8xx.h

···
 }
 
 #define __HAVE_ARCH_HUGE_SET_HUGE_PTE_AT
-void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte);
+void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
+		     pte_t pte, unsigned long sz);
 
 #define __HAVE_ARCH_HUGE_PTE_CLEAR
 static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr,

arch/powerpc/mm/book3s64/hugetlbpage.c

···
 void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr,
 				  pte_t *ptep, pte_t old_pte, pte_t pte)
 {
+	unsigned long psize;
 
 	if (radix_enabled())
 		return radix__huge_ptep_modify_prot_commit(vma, addr, ptep,
 							   old_pte, pte);
-	set_huge_pte_at(vma->vm_mm, addr, ptep, pte);
+
+	psize = huge_page_size(hstate_vma(vma));
+	set_huge_pte_at(vma->vm_mm, addr, ptep, pte, psize);
 }
 
 void __init hugetlbpage_init_defaultsize(void)

arch/powerpc/mm/book3s64/radix_hugetlbpage.c

···
 					 pte_t old_pte, pte_t pte)
 {
 	struct mm_struct *mm = vma->vm_mm;
+	unsigned long psize = huge_page_size(hstate_vma(vma));
 
 	/*
 	 * POWER9 NMMU must flush the TLB after clearing the PTE before
···
 	    atomic_read(&mm->context.copros) > 0)
 		radix__flush_hugetlb_page(vma, addr);
 
-	set_huge_pte_at(vma->vm_mm, addr, ptep, pte);
+	set_huge_pte_at(vma->vm_mm, addr, ptep, pte, psize);
 }

arch/powerpc/mm/nohash/8xx.c

···
 	if (new && WARN_ON(pte_present(*ptep) && pgprot_val(prot)))
 		return -EINVAL;
 
-	set_huge_pte_at(&init_mm, va, ptep, pte_mkhuge(pfn_pte(pa >> PAGE_SHIFT, prot)));
+	set_huge_pte_at(&init_mm, va, ptep,
+			pte_mkhuge(pfn_pte(pa >> PAGE_SHIFT, prot)), psize);
 
 	return 0;
 }

arch/powerpc/mm/pgtable.c

···
 }
 
 #if defined(CONFIG_PPC_8xx)
-void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte)
+void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
+		     pte_t pte, unsigned long sz)
 {
 	pmd_t *pmd = pmd_off(mm, addr);
 	pte_basic_t val;

arch/riscv/include/asm/hugetlb.h

···
 
 #define __HAVE_ARCH_HUGE_SET_HUGE_PTE_AT
 void set_huge_pte_at(struct mm_struct *mm,
-		     unsigned long addr, pte_t *ptep, pte_t pte);
+		     unsigned long addr, pte_t *ptep, pte_t pte,
+		     unsigned long sz);
 
 #define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
 pte_t huge_ptep_get_and_clear(struct mm_struct *mm,

arch/riscv/mm/hugetlbpage.c

···
 void set_huge_pte_at(struct mm_struct *mm,
 		     unsigned long addr,
 		     pte_t *ptep,
-		     pte_t pte)
+		     pte_t pte,
+		     unsigned long sz)
 {
 	int i, pte_num;
 

arch/s390/include/asm/hugetlb.h

···
 #define hugepages_supported()			(MACHINE_HAS_EDAT1)
 
 void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
+		     pte_t *ptep, pte_t pte, unsigned long sz);
+void __set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 		     pte_t *ptep, pte_t pte);
 pte_t huge_ptep_get(pte_t *ptep);
 pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
···
 	int changed = !pte_same(huge_ptep_get(ptep), pte);
 	if (changed) {
 		huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
-		set_huge_pte_at(vma->vm_mm, addr, ptep, pte);
+		__set_huge_pte_at(vma->vm_mm, addr, ptep, pte);
 	}
 	return changed;
 }
···
 					   unsigned long addr, pte_t *ptep)
 {
 	pte_t pte = huge_ptep_get_and_clear(mm, addr, ptep);
-	set_huge_pte_at(mm, addr, ptep, pte_wrprotect(pte));
+	__set_huge_pte_at(mm, addr, ptep, pte_wrprotect(pte));
 }
 
 static inline pte_t mk_huge_pte(struct page *page, pgprot_t pgprot)

arch/s390/mm/hugetlbpage.c

···
 		__storage_key_init_range(paddr, paddr + size - 1);
 }
 
-void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
+void __set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 		     pte_t *ptep, pte_t pte)
 {
 	unsigned long rste;
···
 
 	clear_huge_pte_skeys(mm, rste);
 	set_pte(ptep, __pte(rste));
+}
+
+void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
+		     pte_t *ptep, pte_t pte, unsigned long sz)
+{
+	__set_huge_pte_at(mm, addr, ptep, pte);
 }
 
 pte_t huge_ptep_get(pte_t *ptep)

arch/sparc/include/asm/hugetlb.h

···
 
 #define __HAVE_ARCH_HUGE_SET_HUGE_PTE_AT
 void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
+		     pte_t *ptep, pte_t pte, unsigned long sz);
+void __set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 		     pte_t *ptep, pte_t pte);
 
 #define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
···
 					   unsigned long addr, pte_t *ptep)
 {
 	pte_t old_pte = *ptep;
-	set_huge_pte_at(mm, addr, ptep, pte_wrprotect(old_pte));
+	__set_huge_pte_at(mm, addr, ptep, pte_wrprotect(old_pte));
 }
 
 #define __HAVE_ARCH_HUGE_PTEP_SET_ACCESS_FLAGS
···
 {
 	int changed = !pte_same(*ptep, pte);
 	if (changed) {
-		set_huge_pte_at(vma->vm_mm, addr, ptep, pte);
+		__set_huge_pte_at(vma->vm_mm, addr, ptep, pte);
 		flush_tlb_page(vma, addr);
 	}
 	return changed;

arch/sparc/mm/hugetlbpage.c

···
 	return pte_offset_huge(pmd, addr);
 }
 
-void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
+void __set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 		     pte_t *ptep, pte_t entry)
 {
 	unsigned int nptes, orig_shift, shift;
···
 	if (size == HPAGE_SIZE)
 		maybe_tlb_batch_add(mm, addr + REAL_HPAGE_SIZE, ptep, orig, 0,
 				    orig_shift);
+}
+
+void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
+		     pte_t *ptep, pte_t entry, unsigned long sz)
+{
+	__set_huge_pte_at(mm, addr, ptep, entry);
 }
 
 pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,

arch/x86/include/asm/pgtable.h

···
 	return a.pte == b.pte;
 }
 
+static inline pte_t pte_next_pfn(pte_t pte)
+{
+	if (__pte_needs_invert(pte_val(pte)))
+		return __pte(pte_val(pte) - (1UL << PFN_PTE_SHIFT));
+	return __pte(pte_val(pte) + (1UL << PFN_PTE_SHIFT));
+}
+#define pte_next_pfn	pte_next_pfn
+
 static inline int pte_present(pte_t a)
 {
 	return pte_flags(a) & (_PAGE_PRESENT | _PAGE_PROTNONE);

fs/binfmt_elf_fdpic.c

···
 	/* there's now no turning back... the old userspace image is dead,
 	 * defunct, deceased, etc.
 	 */
+	SET_PERSONALITY(exec_params.hdr);
 	if (elf_check_fdpic(&exec_params.hdr))
-		set_personality(PER_LINUX_FDPIC);
-	else
-		set_personality(PER_LINUX);
+		current->personality |= PER_LINUX_FDPIC;
 	if (elf_read_implies_exec(&exec_params.hdr, executable_stack))
 		current->personality |= READ_IMPLIES_EXEC;
 

fs/nilfs2/gcinode.c

···
 		struct the_nilfs *nilfs = inode->i_sb->s_fs_info;
 
 		err = nilfs_dat_translate(nilfs->ns_dat, vbn, &pbn);
-		if (unlikely(err)) { /* -EIO, -ENOMEM, -ENOENT */
-			brelse(bh);
+		if (unlikely(err)) /* -EIO, -ENOMEM, -ENOENT */
 			goto failed;
-		}
 	}
 
 	lock_buffer(bh);
···
  failed:
 	unlock_page(bh->b_page);
 	put_page(bh->b_page);
+	if (unlikely(err))
+		brelse(bh);
 	return err;
 }
 

include/asm-generic/hugetlb.h

···
 
 #ifndef __HAVE_ARCH_HUGE_SET_HUGE_PTE_AT
 static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
-		pte_t *ptep, pte_t pte)
+		pte_t *ptep, pte_t pte, unsigned long sz)
 {
 	set_pte_at(mm, addr, ptep, pte);
 }

include/linux/hugetlb.h

···
 						unsigned long addr, pte_t *ptep,
 						pte_t old_pte, pte_t pte)
 {
-	set_huge_pte_at(vma->vm_mm, addr, ptep, pte);
+	unsigned long psize = huge_page_size(hstate_vma(vma));
+
+	set_huge_pte_at(vma->vm_mm, addr, ptep, pte, psize);
 }
 #endif
 
···
 }
 
 static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
-				   pte_t *ptep, pte_t pte)
+				   pte_t *ptep, pte_t pte, unsigned long sz)
 {
 }
 

include/linux/maple_tree.h

···
 #define MAS_ROOT	((struct maple_enode *)5UL)
 #define MAS_NONE	((struct maple_enode *)9UL)
 #define MAS_PAUSE	((struct maple_enode *)17UL)
+#define MAS_OVERFLOW	((struct maple_enode *)33UL)
+#define MAS_UNDERFLOW	((struct maple_enode *)65UL)
 #define MA_ERROR(err) \
 		((struct maple_enode *)(((unsigned long)err << 2) | 2UL))
 
···
 static inline bool mas_is_paused(const struct ma_state *mas)
 {
 	return mas->node == MAS_PAUSE;
+}
+
+/* Check if the mas is pointing to a node or not */
+static inline bool mas_is_active(struct ma_state *mas)
+{
+	if ((unsigned long)mas->node >= MAPLE_RESERVED_RANGE)
+		return true;
+
+	return false;
 }
 
 /**

include/linux/pgtable.h

···
 #endif
 
 #ifndef set_ptes
+
+#ifndef pte_next_pfn
+static inline pte_t pte_next_pfn(pte_t pte)
+{
+	return __pte(pte_val(pte) + (1UL << PFN_PTE_SHIFT));
+}
+#endif
+
 /**
  * set_ptes - Map consecutive pages to a contiguous range of addresses.
  * @mm: Address space to map the pages into.
···
 		if (--nr == 0)
 			break;
 		ptep++;
-		pte = __pte(pte_val(pte) + (1UL << PFN_PTE_SHIFT));
+		pte = pte_next_pfn(pte);
 	}
 	arch_leave_lazy_mmu_mode();
 }

kernel/crash_core.c

···
 #define pr_fmt(fmt) "crash hp: " fmt
 
 /*
+ * Different than kexec/kdump loading/unloading/jumping/shrinking which
+ * usually rarely happen, there will be many crash hotplug events notified
+ * during one short period, e.g one memory board is hot added and memory
+ * regions are online. So mutex lock  __crash_hotplug_lock is used to
+ * serialize the crash hotplug handling specifically.
+ */
+DEFINE_MUTEX(__crash_hotplug_lock);
+#define crash_hotplug_lock() mutex_lock(&__crash_hotplug_lock)
+#define crash_hotplug_unlock() mutex_unlock(&__crash_hotplug_lock)
+
+/*
  * This routine utilized when the crash_hotplug sysfs node is read.
  * It reflects the kernel's ability/permission to update the crash
  * elfcorehdr directly.
···
 {
 	int rc = 0;
 
+	crash_hotplug_lock();
 	/* Obtain lock while reading crash information */
 	if (!kexec_trylock()) {
 		pr_info("kexec_trylock() failed, elfcorehdr may be inaccurate\n");
+		crash_hotplug_unlock();
 		return 0;
 	}
 	if (kexec_crash_image) {
···
 	}
 	/* Release lock now that update complete */
 	kexec_unlock();
+	crash_hotplug_unlock();
 
 	return rc;
 }
···
 {
 	struct kimage *image;
 
+	crash_hotplug_lock();
 	/* Obtain lock while changing crash information */
 	if (!kexec_trylock()) {
 		pr_info("kexec_trylock() failed, elfcorehdr may be inaccurate\n");
+		crash_hotplug_unlock();
 		return;
 	}
 
···
 out:
 	/* Release lock now that update complete */
 	kexec_unlock();
+	crash_hotplug_unlock();
 }
 
 static int crash_memhp_notifier(struct notifier_block *nb, unsigned long val, void *v)

lib/maple_tree.c

···
 	return xa_is_err(mas->node);
 }
 
+static __always_inline bool mas_is_overflow(struct ma_state *mas)
+{
+	if (unlikely(mas->node == MAS_OVERFLOW))
+		return true;
+
+	return false;
+}
+
+static __always_inline bool mas_is_underflow(struct ma_state *mas)
+{
+	if (unlikely(mas->node == MAS_UNDERFLOW))
+		return true;
+
+	return false;
+}
+
 static inline bool mas_searchable(struct ma_state *mas)
 {
 	if (mas_is_none(mas))
···
  *
  * @mas: The maple state
  * @max: The minimum starting range
+ * @empty: Can be empty
+ * @set_underflow: Set the @mas->node to underflow state on limit.
  *
  * Return: The entry in the previous slot which is possibly NULL
  */
-static void *mas_prev_slot(struct ma_state *mas, unsigned long min, bool empty)
+static void *mas_prev_slot(struct ma_state *mas, unsigned long min, bool empty,
+			   bool set_underflow)
 {
 	void *entry;
 	void __rcu **slots;
···
 	if (unlikely(mas_rewalk_if_dead(mas, node, save_point)))
 		goto retry;
 
-again:
 	if (mas->min <= min) {
 		pivot = mas_safe_min(mas, pivots, mas->offset);
 
···
 			goto retry;
 
 		if (pivot <= min)
-			return NULL;
+			goto underflow;
 	}
 
+again:
 	if (likely(mas->offset)) {
 		mas->offset--;
 		mas->last = mas->index - 1;
···
 		}
 
 		if (mas_is_none(mas))
-			return NULL;
+			goto underflow;
 
 		mas->last = mas->max;
 		node = mas_mn(mas);
···
 	if (likely(entry))
 		return entry;
 
-	if (!empty)
+	if (!empty) {
+		if (mas->index <= min)
+			goto underflow;
+
 		goto again;
+	}
 
 	return entry;
+
+underflow:
+	if (set_underflow)
+		mas->node = MAS_UNDERFLOW;
+	return NULL;
 }
 
 /*
···
  * @mas: The maple state
  * @max: The maximum starting range
  * @empty: Can be empty
+ * @set_overflow: Should @mas->node be set to overflow when the limit is
+ * reached.
  *
  * Return: The entry in the next slot which is possibly NULL
  */
-static void *mas_next_slot(struct ma_state *mas, unsigned long max, bool empty)
+static void *mas_next_slot(struct ma_state *mas, unsigned long max, bool empty,
+			   bool set_overflow)
 {
 	void __rcu **slots;
 	unsigned long *pivots;
···
 	if (unlikely(mas_rewalk_if_dead(mas, node, save_point)))
 		goto retry;
 
-again:
 	if (mas->max >= max) {
 		if (likely(mas->offset < data_end))
 			pivot = pivots[mas->offset];
 		else
-			return NULL; /* must be mas->max */
+			goto overflow;
 
 		if (unlikely(mas_rewalk_if_dead(mas, node, save_point)))
 			goto retry;
 
 		if (pivot >= max)
-			return NULL;
+			goto overflow;
 	}
 
 	if (likely(mas->offset < data_end)) {
 		mas->index = pivots[mas->offset] + 1;
+again:
 		mas->offset++;
 		if (likely(mas->offset < data_end))
 			mas->last = pivots[mas->offset];
···
 			goto retry;
 		}
 
-		if (mas_is_none(mas))
+		if (WARN_ON_ONCE(mas_is_none(mas))) {
+			mas->node = MAS_OVERFLOW;
 			return NULL;
+			goto overflow;
+		}
 
 		mas->offset = 0;
 		mas->index = mas->min;
···
 		return entry;
 
 	if (!empty) {
-		if (!mas->offset)
-			data_end = 2;
+		if (mas->last >= max)
+			goto overflow;
+
+		mas->index = mas->last + 1;
+		/* Node cannot end on NULL, so it's safe to short-cut here */
 		goto again;
 	}
 
 	return entry;
+
+overflow:
+	if (set_overflow)
+		mas->node = MAS_OVERFLOW;
+	return NULL;
 }
 
 /*
···
  *
  * Set the @mas->node to the next entry and the range_start to
  * the beginning value for the entry.  Does not check beyond @limit.
- * Sets @mas->index and @mas->last to the limit if it is hit.
+ * Sets @mas->index and @mas->last to the range, Does not update @mas->index and
+ * @mas->last on overflow.
  * Restarts on dead nodes.
  *
  * Return: the next entry or %NULL.
  */
 static inline void *mas_next_entry(struct ma_state *mas, unsigned long limit)
 {
-	if (mas->last >= limit)
+	if (mas->last >= limit) {
+		mas->node = MAS_OVERFLOW;
 		return NULL;
+	}
 
-	return mas_next_slot(mas, limit, false);
+	return mas_next_slot(mas, limit, false, true);
 }
 
 /*
···
 {
 	void *entry;
 
-	if (mas_is_none(mas) || mas_is_paused(mas) || mas_is_ptr(mas))
+	if (!mas_is_active(mas) || !mas_is_start(mas))
 		mas->node = MAS_START;
 retry:
 	entry = mas_state_walk(mas);
···
 
 static void mas_wr_store_setup(struct ma_wr_state *wr_mas)
 {
-	if (mas_is_start(wr_mas->mas))
-		return;
+	if (!mas_is_active(wr_mas->mas)) {
+		if (mas_is_start(wr_mas->mas))
+			return;
 
-	if (unlikely(mas_is_paused(wr_mas->mas)))
-		goto reset;
+		if (unlikely(mas_is_paused(wr_mas->mas)))
+			goto reset;
 
-	if (unlikely(mas_is_none(wr_mas->mas)))
-		goto reset;
+		if (unlikely(mas_is_none(wr_mas->mas)))
+			goto reset;
+
+		if (unlikely(mas_is_overflow(wr_mas->mas)))
+			goto reset;
+
+		if (unlikely(mas_is_underflow(wr_mas->mas)))
+			goto reset;
+	}
 
 	/*
 	 * A less strict version of mas_is_span_wr() where we allow spanning
···
 {
 	bool was_none = mas_is_none(mas);
 
-	if (mas_is_none(mas) || mas_is_paused(mas))
+	if (unlikely(mas->last >= max)) {
+		mas->node = MAS_OVERFLOW;
+		return true;
+	}
+
+	if (mas_is_active(mas))
+		return false;
+
+	if (mas_is_none(mas) || mas_is_paused(mas)) {
 		mas->node = MAS_START;
+	} else if (mas_is_overflow(mas)) {
+		/* Overflowed before, but the max changed */
+		mas->node = MAS_START;
+	} else if (mas_is_underflow(mas)) {
+		mas->node = MAS_START;
+		*entry = mas_walk(mas);
+		if (*entry)
+			return true;
+	}
 
 	if (mas_is_start(mas))
 		*entry = mas_walk(mas); /* Retries on dead nodes handled by mas_walk */
···
 
 	if (mas_is_none(mas))
 		return true;
+
 	return false;
 }
 
···
 		return entry;
 
 	/* Retries on dead nodes handled by mas_next_slot */
-	return mas_next_slot(mas, max, false);
+	return mas_next_slot(mas, max, false, true);
 }
 EXPORT_SYMBOL_GPL(mas_next);
 
···
 		return entry;
 
 	/* Retries on dead nodes handled by mas_next_slot */
-	return mas_next_slot(mas, max, true);
+	return mas_next_slot(mas, max, true, true);
 }
 EXPORT_SYMBOL_GPL(mas_next_range);
 
···
 static inline bool mas_prev_setup(struct ma_state *mas, unsigned long min,
 		void **entry)
 {
-	if (mas->index <= min)
-		goto none;
-
-	if (mas_is_none(mas) || mas_is_paused(mas))
-		mas->node = MAS_START;
-
-	if (mas_is_start(mas)) {
-		mas_walk(mas);
-		if (!mas->index)
-			goto none;
+	if (unlikely(mas->index <= min)) {
+		mas->node = MAS_UNDERFLOW;
+		return true;
 	}
+
+	if (mas_is_active(mas))
+		return false;
+
+	if (mas_is_overflow(mas)) {
+		mas->node = MAS_START;
+		*entry = mas_walk(mas);
+		if (*entry)
+			return true;
+	}
+
+	if (mas_is_none(mas) || mas_is_paused(mas)) {
+		mas->node = MAS_START;
+	} else if (mas_is_underflow(mas)) {
+		/* underflowed before but the min changed */
+		mas->node = MAS_START;
+	}
+
+	if (mas_is_start(mas))
+		mas_walk(mas);
 
 	if (unlikely(mas_is_ptr(mas))) {
 		if (!mas->index)
···
 	if (mas_prev_setup(mas, min, &entry))
 		return entry;
 
-	return mas_prev_slot(mas, min, false);
+	return mas_prev_slot(mas, min, false, true);
 }
 EXPORT_SYMBOL_GPL(mas_prev);
 
···
 	if (mas_prev_setup(mas, min, &entry))
 		return entry;
 
-	return mas_prev_slot(mas, min, true);
+	return mas_prev_slot(mas, min, true, true);
 }
 EXPORT_SYMBOL_GPL(mas_prev_range);
 
···
 static inline bool mas_find_setup(struct ma_state *mas, unsigned long max,
 		void **entry)
 {
-	*entry = NULL;
+	if (mas_is_active(mas)) {
+		if (mas->last < max)
+			return false;
 
-	if (unlikely(mas_is_none(mas))) {
+		return true;
+	}
+
+	if (mas_is_paused(mas)) {
+		if (unlikely(mas->last >= max))
+			return true;
+
+		mas->index = ++mas->last;
+		mas->node = MAS_START;
+	} else if (mas_is_none(mas)) {
 		if (unlikely(mas->last >= max))
 			return true;
 
 		mas->index = mas->last;
 		mas->node = MAS_START;
-	} else if (unlikely(mas_is_paused(mas))) {
-		if (unlikely(mas->last >= max))
+	} else if (mas_is_overflow(mas) || mas_is_underflow(mas)) {
+		if (mas->index > max) {
+			mas->node = MAS_OVERFLOW;
 			return true;
+		}
 
 		mas->node = MAS_START;
-		mas->index = ++mas->last;
-	} else if (unlikely(mas_is_ptr(mas)))
-		goto ptr_out_of_range;
+	}
 
-	if (unlikely(mas_is_start(mas))) {
+	if (mas_is_start(mas)) {
 		/* First run or continue */
 		if (mas->index > max)
 			return true;
···
 		return entry;
 
 	/* Retries on dead nodes handled by mas_next_slot */
-	return mas_next_slot(mas, max, false);
+	return mas_next_slot(mas, max, false, false);
 }
 EXPORT_SYMBOL_GPL(mas_find);
 
···
  */
 void *mas_find_range(struct ma_state *mas, unsigned long max)
 {
-	void *entry;
+	void *entry = NULL;
 
 	if (mas_find_setup(mas, max, &entry))
 		return entry;
 
 	/* Retries on dead nodes handled by mas_next_slot */
-	return mas_next_slot(mas, max, true);
+	return mas_next_slot(mas, max, true, false);
 }
 EXPORT_SYMBOL_GPL(mas_find_range);
 
···
 static inline bool mas_find_rev_setup(struct ma_state *mas, unsigned long min,
 		void **entry)
 {
-	*entry = NULL;
+	if (mas_is_active(mas)) {
+		if (mas->index > min)
+			return false;
 
-	if (unlikely(mas_is_none(mas))) {
-		if (mas->index <= min)
-			goto none;
-
-		mas->last = mas->index;
-		mas->node = MAS_START;
+		return true;
 	}
 
-	if (unlikely(mas_is_paused(mas))) {
+	if (mas_is_paused(mas)) {
 		if (unlikely(mas->index <= min)) {
 			mas->node = MAS_NONE;
 			return true;
 		}
 		mas->node = MAS_START;
 		mas->last = --mas->index;
+	} else if (mas_is_none(mas)) {
+		if (mas->index <= min)
+			goto none;
+
+		mas->last = mas->index;
+		mas->node = MAS_START;
+	} else if (mas_is_underflow(mas) || mas_is_overflow(mas)) {
+		if (mas->last <= min) {
+			mas->node = MAS_UNDERFLOW;
+			return true;
+		}
+
+		mas->node = MAS_START;
 	}
 
-	if (unlikely(mas_is_start(mas))) {
+	if (mas_is_start(mas)) {
 		/* First run or continue */
 		if (mas->index < min)
 			return true;
···
  */
 void *mas_find_rev(struct ma_state *mas, unsigned long min)
 {
-	void *entry;
+	void *entry = NULL;
 
 	if (mas_find_rev_setup(mas, min, &entry))
 		return entry;
 
 	/* Retries on dead nodes handled by mas_prev_slot */
-	return mas_prev_slot(mas, min, false);
+	return mas_prev_slot(mas, min, false, false);
 
 }
 EXPORT_SYMBOL_GPL(mas_find_rev);
···
  */
 void *mas_find_range_rev(struct ma_state *mas, unsigned long min)
 {
-	void *entry;
+	void *entry = NULL;
 
 	if (mas_find_rev_setup(mas, min, &entry))
 		return entry;
 
 	/* Retries on dead nodes handled by mas_prev_slot */
-	return mas_prev_slot(mas, min, true);
+	return mas_prev_slot(mas, min, true, false);
 }
 EXPORT_SYMBOL_GPL(mas_find_range_rev);
 

lib/test_maple_tree.c

···
 	MT_BUG_ON(mt, val != NULL);
 	MT_BUG_ON(mt, mas.index != 0);
 	MT_BUG_ON(mt, mas.last != 5);
-	MT_BUG_ON(mt, mas.node != MAS_NONE);
+	MT_BUG_ON(mt, mas.node != MAS_UNDERFLOW);
 
 	mas.index = 0;
 	mas.last = 5;
···
  *		exists	MAS_NONE	active		range
  *		exists	active		active		range
  *		DNE	active		active		set to last range
+ *		ERANGE	active		MAS_OVERFLOW	last range
  *
  * Function	ENTRY	Start		Result		index & last
  * mas_prev()
···
  *		any	MAS_ROOT	MAS_NONE	0
  *		exists	active		active		range
  *		DNE	active		active		last range
+ *		ERANGE	active		MAS_UNDERFLOW	last range
  *
  * Function	ENTRY	Start		Result		index & last
  * mas_find()
···
  *		DNE	MAS_START	MAS_NONE	0
  *		DNE	MAS_PAUSE	MAS_NONE	0
  *		DNE	MAS_ROOT	MAS_NONE	0
- *		DNE	MAS_NONE	MAS_NONE	0
+ *		DNE	MAS_NONE	MAS_NONE	1
  *				if index ==  0
  *		exists	MAS_START	MAS_ROOT	0
  *		exists	MAS_PAUSE	MAS_ROOT	0
···
  *		DNE	MAS_START	active		set to max
  *		exists	MAS_PAUSE	active		range
  *		DNE	MAS_PAUSE	active		set to max
- *		exists	MAS_NONE	active		range
+ *		exists	MAS_NONE	active		range (start at last)
  *		exists	active		active		range
  *		DNE	active		active		last range (max < last)
  *
···
  *		DNE	MAS_START	active		set to min
  *		exists	MAS_PAUSE	active		range
  *		DNE	MAS_PAUSE	active		set to min
- *		exists	MAS_NONE	active		range
+ *		exists	MAS_NONE	active		range (start at index)
  *		exists	active		active		range
  *		DNE	active		active		last range (min > index)
  *
···
 	mtree_store_range(mt, 0, 0, ptr, GFP_KERNEL);
 
 	mas_lock(&mas);
-	/* prev: Start -> none */
+	/* prev: Start -> underflow*/
 	entry = mas_prev(&mas, 0);
 	MT_BUG_ON(mt, entry != NULL);
-	MT_BUG_ON(mt, mas.node != MAS_NONE);
+	MT_BUG_ON(mt, mas.node != MAS_UNDERFLOW);
 
 	/* prev: Start -> root */
 	mas_set(&mas, 10);
···
 	MT_BUG_ON(mt, entry != NULL);
 	MT_BUG_ON(mt, mas.node != MAS_NONE);
 
-	/* next: start -> none */
+	/* next: start -> none*/
 	mas_set(&mas, 10);
 	entry = mas_next(&mas, ULONG_MAX);
 	MT_BUG_ON(mt, mas.index != 1);
···
 	MT_BUG_ON(mt, mas.last != 0x2500);
 	MT_BUG_ON(mt, !mas_active(mas));
 
-	/* next:active -> active out of range*/
+	/* next:active -> active beyond data */
 	entry = mas_next(&mas, 0x2999);
 	MT_BUG_ON(mt, entry != NULL);
 	MT_BUG_ON(mt, mas.index != 0x2501);
 	MT_BUG_ON(mt, mas.last != 0x2fff);
 	MT_BUG_ON(mt, !mas_active(mas));
 
-	/* Continue after out of range*/
+	/* Continue after last range ends after max */
 	entry = mas_next(&mas, ULONG_MAX);
 	MT_BUG_ON(mt, entry != ptr3);
 	MT_BUG_ON(mt, mas.index != 0x3000);
 	MT_BUG_ON(mt, mas.last != 0x3500);
 	MT_BUG_ON(mt, !mas_active(mas));
 
-	/* next:active -> active out of range*/
+	/* next:active -> active continued */
 	entry = mas_next(&mas, ULONG_MAX);
 	MT_BUG_ON(mt, entry != NULL);
 	MT_BUG_ON(mt, mas.index != 0x3501);
 	MT_BUG_ON(mt, mas.last != ULONG_MAX);
+	MT_BUG_ON(mt, !mas_active(mas));
+
+	/* next:active -> overflow  */
+	entry = mas_next(&mas, ULONG_MAX);
+	MT_BUG_ON(mt, entry != NULL);
+	MT_BUG_ON(mt, mas.index != 0x3501);
+	MT_BUG_ON(mt, mas.last != ULONG_MAX);
+	MT_BUG_ON(mt, mas.node != MAS_OVERFLOW);
+
+	/* next:overflow -> overflow  */
+	entry = mas_next(&mas, ULONG_MAX);
+	MT_BUG_ON(mt, entry != NULL);
+	MT_BUG_ON(mt, mas.index != 0x3501);
+	MT_BUG_ON(mt, mas.last != ULONG_MAX);
+	MT_BUG_ON(mt, mas.node != MAS_OVERFLOW);
+
+	/* prev:overflow -> active  */
+	entry = mas_prev(&mas, 0);
+	MT_BUG_ON(mt, entry != ptr3);
+	MT_BUG_ON(mt, mas.index != 0x3000);
+	MT_BUG_ON(mt, mas.last != 0x3500);
 	MT_BUG_ON(mt, !mas_active(mas));
 
 	/* next: none -> active, skip value at location */
···
 	MT_BUG_ON(mt, mas.last != 0x1500);
 	MT_BUG_ON(mt, !mas_active(mas));
 
-	/* prev:active -> active out of range*/
+	/* prev:active -> active spanning end range */
+	entry = mas_prev(&mas, 0x0100);
+	MT_BUG_ON(mt, entry != NULL);
+	MT_BUG_ON(mt, mas.index != 0);
+	MT_BUG_ON(mt, mas.last != 0x0FFF);
+	MT_BUG_ON(mt, !mas_active(mas));
+
+	/* prev:active -> underflow */
 	entry = mas_prev(&mas, 0);
 	MT_BUG_ON(mt, entry != NULL);
 	MT_BUG_ON(mt, mas.index != 0);
 	MT_BUG_ON(mt, mas.last != 0x0FFF);
+	MT_BUG_ON(mt, mas.node != MAS_UNDERFLOW);
+
+	/* prev:underflow -> underflow */
+	entry = mas_prev(&mas, 0);
+	MT_BUG_ON(mt, entry != NULL);
+	MT_BUG_ON(mt, mas.index != 0);
+	MT_BUG_ON(mt, mas.last != 0x0FFF);
+	MT_BUG_ON(mt, mas.node != MAS_UNDERFLOW);
+
+	/* next:underflow -> active */
+	entry = mas_next(&mas, ULONG_MAX);
+	MT_BUG_ON(mt, entry != ptr);
+	MT_BUG_ON(mt, mas.index != 0x1000);
+	MT_BUG_ON(mt, mas.last != 0x1500);
+	MT_BUG_ON(mt, !mas_active(mas));
+
+	/* prev:first value -> underflow */
+	entry = mas_prev(&mas, 0x1000);
+	MT_BUG_ON(mt, entry != NULL);
+	MT_BUG_ON(mt, mas.index != 0x1000);
+	MT_BUG_ON(mt, mas.last != 0x1500);
+	MT_BUG_ON(mt, mas.node != MAS_UNDERFLOW);
+
+	/* find:underflow -> first value */
+	entry = mas_find(&mas, ULONG_MAX);
+	MT_BUG_ON(mt, entry != ptr);
+	MT_BUG_ON(mt, mas.index != 0x1000);
+	MT_BUG_ON(mt, mas.last != 0x1500);
 	MT_BUG_ON(mt, !mas_active(mas));
 
 	/* prev: pause ->active */
···
 	MT_BUG_ON(mt, mas.last != 0x2500);
 	MT_BUG_ON(mt, !mas_active(mas));
 
-	/* prev:active -> active out of range*/
+	/* prev:active -> active spanning min */
 	entry = mas_prev(&mas, 0x1600);
 	MT_BUG_ON(mt, entry != NULL);
 	MT_BUG_ON(mt, mas.index != 0x1501);
 	MT_BUG_ON(mt, mas.last != 0x1FFF);
 	MT_BUG_ON(mt, !mas_active(mas));
 
-	/* prev: active ->active, continue*/
+	/* prev: active ->active, continue */
 	entry = mas_prev(&mas, 0);
 	MT_BUG_ON(mt, entry != ptr);
 	MT_BUG_ON(mt, mas.index != 0x1000);
···
 	MT_BUG_ON(mt, mas.last != 0x2FFF);
 	MT_BUG_ON(mt, !mas_active(mas));
 
-	/* find: none ->active */
+	/* find: overflow ->active */
 	entry = mas_find(&mas, 0x5000);
 	MT_BUG_ON(mt, entry != ptr3);
 	MT_BUG_ON(mt, mas.index != 0x3000);
···
 	mt_init_flags(&tree, MT_FLAGS_ALLOC_RANGE);
 	check_empty_area_fill(&tree);
 	mtree_destroy(&tree);
-
 
 	mt_init_flags(&tree, MT_FLAGS_ALLOC_RANGE);
 	check_state_handling(&tree);

mm/damon/vaddr-test.h

···
 		KUNIT_EXPECT_EQ(test, r->ar.start, expected[i * 2]);
 		KUNIT_EXPECT_EQ(test, r->ar.end, expected[i * 2 + 1]);
 	}
+
+	damon_destroy_target(t);
 }
 
 /*

mm/damon/vaddr.c

···
 	bool referenced = false;
 	pte_t entry = huge_ptep_get(pte);
 	struct folio *folio = pfn_folio(pte_pfn(entry));
+	unsigned long psize = huge_page_size(hstate_vma(vma));
 
 	folio_get(folio);
 
 	if (pte_young(entry)) {
 		referenced = true;
 		entry = pte_mkold(entry);
-		set_huge_pte_at(mm, addr, pte, entry);
+		set_huge_pte_at(mm, addr, pte, entry, psize);
 	}
 
 #ifdef CONFIG_MMU_NOTIFIER

mm/filemap.c

···
 		if (count) {
 			set_pte_range(vmf, folio, page, count, addr);
 			folio_ref_add(folio, count);
-			if (in_range(vmf->address, addr, count))
+			if (in_range(vmf->address, addr, count * PAGE_SIZE))
 				ret = VM_FAULT_NOPAGE;
 		}
 
···
 	if (count) {
 		set_pte_range(vmf, folio, page, count, addr);
 		folio_ref_add(folio, count);
-		if (in_range(vmf->address, addr, count))
+		if (in_range(vmf->address, addr, count * PAGE_SIZE))
 			ret = VM_FAULT_NOPAGE;
 	}
 

mm/hugetlb.c

···
 
 static void
 hugetlb_install_folio(struct vm_area_struct *vma, pte_t *ptep, unsigned long addr,
-		      struct folio *new_folio, pte_t old)
+		      struct folio *new_folio, pte_t old, unsigned long sz)
 {
 	pte_t newpte = make_huge_pte(vma, &new_folio->page, 1);
 
···
 	hugepage_add_new_anon_rmap(new_folio, vma, addr);
 	if (userfaultfd_wp(vma) && huge_pte_uffd_wp(old))
 		newpte = huge_pte_mkuffd_wp(newpte);
-	set_huge_pte_at(vma->vm_mm, addr, ptep, newpte);
+	set_huge_pte_at(vma->vm_mm, addr, ptep, newpte, sz);
 	hugetlb_count_add(pages_per_huge_page(hstate_vma(vma)), vma->vm_mm);
 	folio_set_hugetlb_migratable(new_folio);
 }
···
 		} else if (unlikely(is_hugetlb_entry_hwpoisoned(entry))) {
 			if (!userfaultfd_wp(dst_vma))
 				entry = huge_pte_clear_uffd_wp(entry);
-			set_huge_pte_at(dst, addr, dst_pte, entry);
+			set_huge_pte_at(dst, addr, dst_pte, entry, sz);
 		} else if (unlikely(is_hugetlb_entry_migration(entry))) {
 			swp_entry_t swp_entry = pte_to_swp_entry(entry);
 			bool uffd_wp = pte_swp_uffd_wp(entry);
···
 				entry = swp_entry_to_pte(swp_entry);
 				if (userfaultfd_wp(src_vma) && uffd_wp)
 					entry = pte_swp_mkuffd_wp(entry);
-				set_huge_pte_at(src, addr, src_pte, entry);
+				set_huge_pte_at(src, addr, src_pte, entry, sz);
 			}
 			if (!userfaultfd_wp(dst_vma))
 				entry = huge_pte_clear_uffd_wp(entry);
-			set_huge_pte_at(dst, addr, dst_pte, entry);
+			set_huge_pte_at(dst, addr, dst_pte, entry, sz);
 		} else if (unlikely(is_pte_marker(entry))) {
 			pte_marker marker = copy_pte_marker(
 				pte_to_swp_entry(entry), dst_vma);
 
 			if (marker)
 				set_huge_pte_at(dst, addr, dst_pte,
-						make_pte_marker(marker));
+						make_pte_marker(marker), sz);
 		} else {
 			entry = huge_ptep_get(src_pte);
 			pte_folio = page_folio(pte_page(entry));
···
 					goto again;
 				}
 				hugetlb_install_folio(dst_vma, dst_pte, addr,
-						      new_folio, src_pte_old);
+						      new_folio, src_pte_old, sz);
 				spin_unlock(src_ptl);
 				spin_unlock(dst_ptl);
 				continue;
···
 			if (!userfaultfd_wp(dst_vma))
 				entry = huge_pte_clear_uffd_wp(entry);
 
-			set_huge_pte_at(dst, addr, dst_pte, entry);
+			set_huge_pte_at(dst, addr, dst_pte, entry, sz);
 			hugetlb_count_add(npages, dst);
 		}
 		spin_unlock(src_ptl);
···
 }
 
 static void move_huge_pte(struct vm_area_struct *vma, unsigned long old_addr,
-			  unsigned long new_addr, pte_t *src_pte, pte_t *dst_pte)
+			  unsigned long new_addr, pte_t *src_pte, pte_t *dst_pte,
+			  unsigned long sz)
 {
 	struct hstate *h = hstate_vma(vma);
 	struct mm_struct *mm = vma->vm_mm;
···
 		spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
 
 	pte = huge_ptep_get_and_clear(mm, old_addr, src_pte);
-	set_huge_pte_at(mm, new_addr, dst_pte, pte);
+	set_huge_pte_at(mm, new_addr, dst_pte, pte, sz);
 
 	if (src_ptl != dst_ptl)
 		spin_unlock(src_ptl);
···
 		if (!dst_pte)
 			break;
 
-		move_huge_pte(vma, old_addr, new_addr, src_pte, dst_pte);
+		move_huge_pte(vma, old_addr, new_addr, src_pte, dst_pte, sz);
 	}
 
 	if (shared_pmd)
···
 			if (pte_swp_uffd_wp_any(pte) &&
 			    !(zap_flags & ZAP_FLAG_DROP_MARKER))
 				set_huge_pte_at(mm, address, ptep,
-						make_pte_marker(PTE_MARKER_UFFD_WP));
+						make_pte_marker(PTE_MARKER_UFFD_WP),
+						sz);
 			else
 				huge_pte_clear(mm, address, ptep, sz);
 			spin_unlock(ptl);
···
 		if (huge_pte_uffd_wp(pte) &&
 		    !(zap_flags & ZAP_FLAG_DROP_MARKER))
 			set_huge_pte_at(mm, address, ptep,
-					make_pte_marker(PTE_MARKER_UFFD_WP));
+					make_pte_marker(PTE_MARKER_UFFD_WP),
+					sz);
 		hugetlb_count_sub(pages_per_huge_page(h), mm);
 		page_remove_rmap(page, vma, true);
 
···
 		hugepage_add_new_anon_rmap(new_folio, vma, haddr);
 		if (huge_pte_uffd_wp(pte))
 			newpte = huge_pte_mkuffd_wp(newpte);
-		set_huge_pte_at(mm, haddr, ptep, newpte);
+		set_huge_pte_at(mm, haddr, ptep, newpte, huge_page_size(h));
 		folio_set_hugetlb_migratable(new_folio);
 		/* Make the old page be freed below */
 		new_folio = old_folio;
···
 	 */
 	if (unlikely(pte_marker_uffd_wp(old_pte)))
 		new_pte = huge_pte_mkuffd_wp(new_pte);
-	set_huge_pte_at(mm, haddr, ptep, new_pte);
+	set_huge_pte_at(mm, haddr, ptep, new_pte, huge_page_size(h));
 
 	hugetlb_count_add(pages_per_huge_page(h), mm);
 	if ((flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED)) {
···
 		}
 
 		_dst_pte = make_pte_marker(PTE_MARKER_POISONED);
-		set_huge_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte);
+		set_huge_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte,
+				huge_page_size(h));
 
 		/* No need to invalidate - it was non-present before */
 		update_mmu_cache(dst_vma, dst_addr, dst_pte);
···
 	if (wp_enabled)
 		_dst_pte = huge_pte_mkuffd_wp(_dst_pte);
 
-	set_huge_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte);
+	set_huge_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte, huge_page_size(h));
 
 	hugetlb_count_add(pages_per_huge_page(h), dst_mm);
 
···
 			else if (uffd_wp_resolve)
 				newpte = pte_swp_clear_uffd_wp(newpte);
 			if (!pte_same(pte, newpte))
-				set_huge_pte_at(mm, address, ptep, newpte);
+				set_huge_pte_at(mm, address, ptep, newpte, psize);
 		} else if (unlikely(is_pte_marker(pte))) {
 			/* No other markers apply for now. */
 			WARN_ON_ONCE(!pte_marker_uffd_wp(pte));
···
 			if (unlikely(uffd_wp))
 				/* Safe to modify directly (none->non-present). */
 				set_huge_pte_at(mm, address, ptep,
-						make_pte_marker(PTE_MARKER_UFFD_WP));
+						make_pte_marker(PTE_MARKER_UFFD_WP),
+						psize);
 		}
 		spin_unlock(ptl);
 	}

mm/memcontrol.c

···
 		case _MEMSWAP:
 			ret = mem_cgroup_resize_max(memcg, nr_pages, true);
 			break;
+		case _KMEM:
+			pr_warn_once("kmem.limit_in_bytes is deprecated and will be removed. "
+				     "Writing any value to this file has no effect. "
+				     "Please report your usecase to [e-mail] if you "
+				     "depend on this functionality.\n");
+			ret = 0;
+			break;
 		case _TCP:
 			ret = memcg_update_tcp_max(memcg, nr_pages);
 			break;
···
 		.seq_show = memcg_numa_stat_show,
 	},
 #endif
+	{
+		.name = "kmem.limit_in_bytes",
+		.private = MEMFILE_PRIVATE(_KMEM, RES_LIMIT),
+		.write = mem_cgroup_write,
+		.read_u64 = mem_cgroup_read_u64,
+	},
 	{
 		.name = "kmem.usage_in_bytes",
 		.private = MEMFILE_PRIVATE(_KMEM, RES_USAGE),

mm/mempolicy.c

···
 	unsigned long start;
 	unsigned long end;
 	struct vm_area_struct *first;
+	bool has_unmovable;
 };
 
 /*
···
 /*
  * queue_folios_pmd() has three possible return values:
  * 0 - folios are placed on the right node or queued successfully, or
- *     special page is met, i.e. huge zero page.
- * 1 - there is unmovable folio, and MPOL_MF_MOVE* & MPOL_MF_STRICT were
- *     specified.
+ *     special page is met, i.e. zero page, or unmovable page is found
+ *     but continue walking (indicated by queue_pages.has_unmovable).
  * -EIO - is migration entry or only MPOL_MF_STRICT was specified and an
  *        existing folio was already on a node that does not follow the
  *        policy.
···
 	if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) {
 		if (!vma_migratable(walk->vma) ||
 		    migrate_folio_add(folio, qp->pagelist, flags)) {
-			ret = 1;
+			qp->has_unmovable = true;
 			goto unlock;
 		}
 	} else
···
  *
  * queue_folios_pte_range() has three possible return values:
  * 0 - folios are placed on the right node or queued successfully, or
- *     special page is met, i.e. zero page.
- * 1 - there is unmovable folio, and MPOL_MF_MOVE* & MPOL_MF_STRICT were
- *     specified.
+ *     special page is met, i.e. zero page, or unmovable page is found
+ *     but continue walking (indicated by queue_pages.has_unmovable).
  * -EIO - only MPOL_MF_STRICT was specified and an existing folio was already
  *        on a node that does not follow the policy.
  */
···
 	struct folio *folio;
 	struct queue_pages *qp = walk->private;
 	unsigned long flags = qp->flags;
-	bool has_unmovable = false;
 	pte_t *pte, *mapped_pte;
 	pte_t ptent;
 	spinlock_t *ptl;
···
 		if (!queue_folio_required(folio, qp))
 			continue;
 		if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) {
-			/* MPOL_MF_STRICT must be specified if we get here */
-			if (!vma_migratable(vma)) {
-				has_unmovable = true;
-				break;
-			}
+			/*
+			 * MPOL_MF_STRICT must be specified if we get here.
+			 * Continue walking vmas due to MPOL_MF_MOVE* flags.
+			 */
+			if (!vma_migratable(vma))
+				qp->has_unmovable = true;
 
 			/*
 			 * Do not abort immediately since there may be
···
 			 * need migrate other LRU pages.
 			 */
 			if (migrate_folio_add(folio, qp->pagelist, flags))
-				has_unmovable = true;
+				qp->has_unmovable = true;
 		} else
 			break;
 	}
 	pte_unmap_unlock(mapped_pte, ptl);
 	cond_resched();
-
-	if (has_unmovable)
-		return 1;
 
 	return addr != end ? -EIO : 0;
 }
···
 		 * Detecting misplaced folio but allow migrating folios which
 		 * have been queued.
 		 */
-		ret = 1;
+		qp->has_unmovable = true;
 		goto unlock;
 	}
 
···
 			 * Failed to isolate folio but allow migrating pages
 			 * which have been queued.
 			 */
-			ret = 1;
+			qp->has_unmovable = true;
 	}
 unlock:
 	spin_unlock(ptl);
···
 		.start = start,
 		.end = end,
 		.first = NULL,
+		.has_unmovable = false,
 	};
 	const struct mm_walk_ops *ops = lock_vma ?
 			&queue_pages_lock_vma_walk_ops : &queue_pages_walk_ops;
 
 	err = walk_page_range(mm, start, end, ops, &qp);
 
+	if (qp.has_unmovable)
+		err = 1;
 	if (!qp.first)
 		/* whole range in hole */
 		err = -EFAULT;
···
 				putback_movable_pages(&pagelist);
 		}
 
-		if ((ret > 0) || (nr_failed && (flags & MPOL_MF_STRICT)))
+		if (((ret > 0) || nr_failed) && (flags & MPOL_MF_STRICT))
 			err = -EIO;
 	} else {
 up_out:

mm/migrate.c

···
 
 #ifdef CONFIG_HUGETLB_PAGE
 		if (folio_test_hugetlb(folio)) {
-			unsigned int shift = huge_page_shift(hstate_vma(vma));
+			struct hstate *h = hstate_vma(vma);
+			unsigned int shift = huge_page_shift(h);
+			unsigned long psize = huge_page_size(h);
 
 			pte = arch_make_huge_pte(pte, shift, vma->vm_flags);
 			if (folio_test_anon(folio))
···
 						       rmap_flags);
 			else
 				page_dup_file_rmap(new, true);
-			set_huge_pte_at(vma->vm_mm, pvmw.address, pvmw.pte, pte);
+			set_huge_pte_at(vma->vm_mm, pvmw.address, pvmw.pte, pte,
+					psize);
 		} else
 #endif
 		{

mm/rmap.c

···
 	struct mmu_notifier_range range;
 	enum ttu_flags flags = (enum ttu_flags)(long)arg;
 	unsigned long pfn;
+	unsigned long hsz = 0;
 
 	/*
 	 * When racing against e.g. zap_pte_range() on another cpu,
···
 		 */
 		adjust_range_if_pmd_sharing_possible(vma, &range.start,
 						     &range.end);
+
+		/* We need the huge page size for set_huge_pte_at() */
+		hsz = huge_page_size(hstate_vma(vma));
 	}
 	mmu_notifier_invalidate_range_start(&range);
 
···
 			pteval = swp_entry_to_pte(make_hwpoison_entry(subpage));
 			if (folio_test_hugetlb(folio)) {
 				hugetlb_count_sub(folio_nr_pages(folio), mm);
-				set_huge_pte_at(mm, address, pvmw.pte, pteval);
+				set_huge_pte_at(mm, address, pvmw.pte, pteval,
+						hsz);
 			} else {
 				dec_mm_counter(mm, mm_counter(&folio->page));
 				set_pte_at(mm, address, pvmw.pte, pteval);
···
 	struct mmu_notifier_range range;
 	enum ttu_flags flags = (enum ttu_flags)(long)arg;
 	unsigned long pfn;
+	unsigned long hsz = 0;
 
 	/*
 	 * When racing against e.g. zap_pte_range() on another cpu,
···
 		 */
 		adjust_range_if_pmd_sharing_possible(vma, &range.start,
 						     &range.end);
+
+		/* We need the huge page size for set_huge_pte_at() */
+		hsz = huge_page_size(hstate_vma(vma));
 	}
 	mmu_notifier_invalidate_range_start(&range);
 
···
 			pteval = swp_entry_to_pte(make_hwpoison_entry(subpage));
 			if (folio_test_hugetlb(folio)) {
 				hugetlb_count_sub(folio_nr_pages(folio), mm);
-				set_huge_pte_at(mm, address, pvmw.pte, pteval);
+				set_huge_pte_at(mm, address, pvmw.pte, pteval,
+						hsz);
 			} else {
 				dec_mm_counter(mm, mm_counter(&folio->page));
 				set_pte_at(mm, address, pvmw.pte, pteval);
···
 
 			if (arch_unmap_one(mm, vma, address, pteval) < 0) {
 				if (folio_test_hugetlb(folio))
-					set_huge_pte_at(mm, address, pvmw.pte, pteval);
+					set_huge_pte_at(mm, address, pvmw.pte,
+							pteval, hsz);
 				else
 					set_pte_at(mm, address, pvmw.pte, pteval);
 				ret = false;
···
 			if (anon_exclusive &&
 			    page_try_share_anon_rmap(subpage)) {
 				if (folio_test_hugetlb(folio))
-					set_huge_pte_at(mm, address, pvmw.pte, pteval);
+					set_huge_pte_at(mm, address, pvmw.pte,
+							pteval, hsz);
 				else
 					set_pte_at(mm, address, pvmw.pte, pteval);
 				ret = false;
···
 			if (pte_uffd_wp(pteval))
 				swp_pte = pte_swp_mkuffd_wp(swp_pte);
 			if (folio_test_hugetlb(folio))
-				set_huge_pte_at(mm, address, pvmw.pte, swp_pte);
+				set_huge_pte_at(mm, address, pvmw.pte, swp_pte,
+						hsz);
 			else
 				set_pte_at(mm, address, pvmw.pte, swp_pte);
 			trace_set_migration_pte(address, pte_val(swp_pte),

mm/vmalloc.c

···
 			pte_t entry = pfn_pte(pfn, prot);
 
 			entry = arch_make_huge_pte(entry, ilog2(size), 0);
-			set_huge_pte_at(&init_mm, addr, pte, entry);
+			set_huge_pte_at(&init_mm, addr, pte, entry, size);
 			pfn += PFN_DOWN(size);
 			continue;
 		}

mm/zswap.c

···
 		return false;
 
 	/*
+	 * If this is a duplicate, it must be removed before attempting to store
+	 * it, otherwise, if the store fails the old page won't be removed from
+	 * the tree, and it might be written back overriding the new data.
+	 */
+	spin_lock(&tree->lock);
+	dupentry = zswap_rb_search(&tree->rbroot, offset);
+	if (dupentry) {
+		zswap_duplicate_entry++;
+		zswap_invalidate_entry(tree, dupentry);
+	}
+	spin_unlock(&tree->lock);
+
+	/*
 	 * XXX: zswap reclaim does not work with cgroups yet. Without a
 	 * cgroup-aware entry LRU, we will push out entries system-wide based on
 	 * local cgroup limits.
···
 
 	/* map */
 	spin_lock(&tree->lock);
+	/*
+	 * A duplicate entry should have been removed at the beginning of this
+	 * function. Since the swap entry should be pinned, if a duplicate is
+	 * found again here it means that something went wrong in the swap
+	 * cache.
+	 */
 	while (zswap_rb_insert(&tree->rbroot, entry, &dupentry) == -EEXIST) {
+		WARN_ON(1);
 		zswap_duplicate_entry++;
 		zswap_invalidate_entry(tree, dupentry);
 	}

tools/testing/selftests/mm/charge_reserved_hugetlb.sh

···
 fi
 
 if [[ $cgroup2 ]]; then
-  cgroup_path=$(mount -t cgroup2 | head -1 | awk -e '{print $3}')
+  cgroup_path=$(mount -t cgroup2 | head -1 | awk '{print $3}')
   if [[ -z "$cgroup_path" ]]; then
     cgroup_path=/dev/cgroup/memory
     mount -t cgroup2 none $cgroup_path
···
   fi
   echo "+hugetlb" >$cgroup_path/cgroup.subtree_control
 else
-  cgroup_path=$(mount -t cgroup | grep ",hugetlb" | awk -e '{print $3}')
+  cgroup_path=$(mount -t cgroup | grep ",hugetlb" | awk '{print $3}')
   if [[ -z "$cgroup_path" ]]; then
     cgroup_path=/dev/cgroup/memory
     mount -t cgroup memory,hugetlb $cgroup_path

tools/testing/selftests/mm/hugetlb_reparenting_test.sh

···
 
 
 if [[ $cgroup2 ]]; then
-  CGROUP_ROOT=$(mount -t cgroup2 | head -1 | awk -e '{print $3}')
+  CGROUP_ROOT=$(mount -t cgroup2 | head -1 | awk '{print $3}')
   if [[ -z "$CGROUP_ROOT" ]]; then
     CGROUP_ROOT=/dev/cgroup/memory
     mount -t cgroup2 none $CGROUP_ROOT
···
   fi
   echo "+hugetlb +memory" >$CGROUP_ROOT/cgroup.subtree_control
 else
-  CGROUP_ROOT=$(mount -t cgroup | grep ",hugetlb" | awk -e '{print $3}')
+  CGROUP_ROOT=$(mount -t cgroup | grep ",hugetlb" | awk '{print $3}')
   if [[ -z "$CGROUP_ROOT" ]]; then
     CGROUP_ROOT=/dev/cgroup/memory
     mount -t cgroup memory,hugetlb $CGROUP_ROOT