merge mm-hotfixes-stable into mm-stable to pick up depended-upon changes

MAINTAINERS

···
 
 MAPLE TREE
 M:	Liam R. Howlett <[e-mail]>
+L:	[e-mail]
 L:	[e-mail]
 S:	Supported
 F:	Documentation/core-api/maple_tree.rst

arch/powerpc/mm/book3s64/subpage_prot.c

···
 
 static const struct mm_walk_ops subpage_walk_ops = {
 	.pmd_entry	= subpage_walk_pmd_entry,
+	.walk_lock	= PGWALK_WRLOCK_VERIFY,
 };
 
 static void subpage_mark_vma_nohuge(struct mm_struct *mm, unsigned long addr,

arch/riscv/mm/pageattr.c

···
 	.pmd_entry = pageattr_pmd_entry,
 	.pte_entry = pageattr_pte_entry,
 	.pte_hole = pageattr_pte_hole,
+	.walk_lock = PGWALK_RDLOCK,
 };
 
 static int __set_memory(unsigned long addr, int numpages, pgprot_t set_mask,

arch/s390/mm/gmap.c

···
 
 static const struct mm_walk_ops thp_split_walk_ops = {
 	.pmd_entry	= thp_split_walk_pmd_entry,
+	.walk_lock	= PGWALK_WRLOCK_VERIFY,
 };
 
 static inline void thp_split_mm(struct mm_struct *mm)
···
 
 static const struct mm_walk_ops zap_zero_walk_ops = {
 	.pmd_entry	= __zap_zero_pages,
+	.walk_lock	= PGWALK_WRLOCK,
 };
 
 /*
···
 	.hugetlb_entry		= __s390_enable_skey_hugetlb,
 	.pte_entry		= __s390_enable_skey_pte,
 	.pmd_entry		= __s390_enable_skey_pmd,
+	.walk_lock		= PGWALK_WRLOCK,
 };
 
 int s390_enable_skey(void)
···
 
 static const struct mm_walk_ops reset_cmma_walk_ops = {
 	.pte_entry		= __s390_reset_cmma,
+	.walk_lock		= PGWALK_WRLOCK,
 };
 
 void s390_reset_cmma(struct mm_struct *mm)
···
 
 static const struct mm_walk_ops gather_pages_ops = {
 	.pte_entry = s390_gather_pages,
+	.walk_lock = PGWALK_RDLOCK,
 };
 
 /*

fs/nilfs2/inode.c

···
 
 int __nilfs_mark_inode_dirty(struct inode *inode, int flags)
 {
+	struct the_nilfs *nilfs = inode->i_sb->s_fs_info;
 	struct buffer_head *ibh;
 	int err;
+
+	/*
+	 * Do not dirty inodes after the log writer has been detached
+	 * and its nilfs_root struct has been freed.
+	 */
+	if (unlikely(nilfs_purging(nilfs)))
+		return 0;
 
 	err = nilfs_load_inode_block(inode, &ibh);
 	if (unlikely(err)) {

fs/nilfs2/segment.c

···
 		struct folio *folio = fbatch.folios[i];
 
 		folio_lock(folio);
+		if (unlikely(folio->mapping != mapping)) {
+			/* Exclude folios removed from the address space */
+			folio_unlock(folio);
+			continue;
+		}
 		head = folio_buffers(folio);
 		if (!head) {
 			create_empty_buffers(&folio->page, i_blocksize(inode), 0);
···
 		nilfs_segctor_destroy(nilfs->ns_writer);
 		nilfs->ns_writer = NULL;
 	}
+	set_nilfs_purging(nilfs);
 
 	/* Force to free the list of dirty files */
 	spin_lock(&nilfs->ns_inode_lock);
···
 	up_write(&nilfs->ns_segctor_sem);
 
 	nilfs_dispose_list(nilfs, &garbage_list, 1);
+	clear_nilfs_purging(nilfs);
 }

fs/nilfs2/the_nilfs.h

···
 	THE_NILFS_DISCONTINUED,	/* 'next' pointer chain has broken */
 	THE_NILFS_GC_RUNNING,	/* gc process is running */
 	THE_NILFS_SB_DIRTY,	/* super block is dirty */
+	THE_NILFS_PURGING,	/* disposing dirty files for cleanup */
 };
 
 /**
···
 THE_NILFS_FNS(DISCONTINUED, discontinued)
 THE_NILFS_FNS(GC_RUNNING, gc_running)
 THE_NILFS_FNS(SB_DIRTY, sb_dirty)
+THE_NILFS_FNS(PURGING, purging)
 
 /*
  * Mount option operations

fs/proc/kcore.c

···
 
 static ssize_t read_kcore_iter(struct kiocb *iocb, struct iov_iter *iter)
 {
+	struct file *file = iocb->ki_filp;
+	char *buf = file->private_data;
 	loff_t *fpos = &iocb->ki_pos;
 	size_t phdrs_offset, notes_offset, data_offset;
 	size_t page_offline_frozen = 1;
···
 		case KCORE_VMEMMAP:
 		case KCORE_TEXT:
 			/*
-			 * We use _copy_to_iter() to bypass usermode hardening
-			 * which would otherwise prevent this operation.
+			 * Sadly we must use a bounce buffer here to be able to
+			 * make use of copy_from_kernel_nofault(), as these
+			 * memory regions might not always be mapped on all
+			 * architectures.
 			 */
-			if (_copy_to_iter((char *)start, tsz, iter) != tsz) {
+			if (copy_from_kernel_nofault(buf, (void *)start, tsz)) {
+				if (iov_iter_zero(tsz, iter) != tsz) {
+					ret = -EFAULT;
+					goto out;
+				}
+			/*
+			 * We know the bounce buffer is safe to copy from, so
+			 * use _copy_to_iter() directly.
+			 */
+			} else if (_copy_to_iter(buf, tsz, iter) != tsz) {
 				ret = -EFAULT;
 				goto out;
 			}
···
 	if (ret)
 		return ret;
 
+	filp->private_data = kmalloc(PAGE_SIZE, GFP_KERNEL);
+	if (!filp->private_data)
+		return -ENOMEM;
+
 	if (kcore_need_update)
 		kcore_update_ram();
 	if (i_size_read(inode) != proc_root_kcore->size) {
···
 	return 0;
 }
 
+static int release_kcore(struct inode *inode, struct file *file)
+{
+	kfree(file->private_data);
+	return 0;
+}
+
 static const struct proc_ops kcore_proc_ops = {
 	.proc_read_iter	= read_kcore_iter,
 	.proc_open	= open_kcore,
+	.proc_release	= release_kcore,
 	.proc_lseek	= default_llseek,
 };
 

fs/proc/task_mmu.c

···
 	bool migration = false;
 
 	if (pmd_present(*pmd)) {
-		/* FOLL_DUMP will return -EFAULT on huge zero page */
-		page = follow_trans_huge_pmd(vma, addr, pmd, FOLL_DUMP);
+		page = vm_normal_page_pmd(vma, addr, *pmd);
 	} else if (unlikely(thp_migration_supported() && is_swap_pmd(*pmd))) {
 		swp_entry_t entry = pmd_to_swp_entry(*pmd);
 
···
 static const struct mm_walk_ops smaps_walk_ops = {
 	.pmd_entry		= smaps_pte_range,
 	.hugetlb_entry		= smaps_hugetlb_range,
+	.walk_lock		= PGWALK_RDLOCK,
 };
 
 static const struct mm_walk_ops smaps_shmem_walk_ops = {
 	.pmd_entry		= smaps_pte_range,
 	.hugetlb_entry		= smaps_hugetlb_range,
 	.pte_hole		= smaps_pte_hole,
+	.walk_lock		= PGWALK_RDLOCK,
 };
 
 /*
···
 static const struct mm_walk_ops clear_refs_walk_ops = {
 	.pmd_entry		= clear_refs_pte_range,
 	.test_walk		= clear_refs_test_walk,
+	.walk_lock		= PGWALK_WRLOCK,
 };
 
 static ssize_t clear_refs_write(struct file *file, const char __user *buf,
···
 	.pmd_entry	= pagemap_pmd_range,
 	.pte_hole	= pagemap_pte_hole,
 	.hugetlb_entry	= pagemap_hugetlb_range,
+	.walk_lock	= PGWALK_RDLOCK,
 };
 
 /*
···
 static const struct mm_walk_ops show_numa_ops = {
 	.hugetlb_entry = gather_hugetlb_stats,
 	.pmd_entry = gather_pte_stats,
+	.walk_lock = PGWALK_RDLOCK,
 };
 
 /*

include/linux/huge_mm.h

···
 #endif
 
 vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf);
-struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
-				   unsigned long addr, pmd_t *pmd,
-				   unsigned int flags);
 bool madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 			   pmd_t *pmd, unsigned long addr, unsigned long next);
 int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t *pmd,

include/linux/mm.h

···
  * Indicates whether GUP can follow a PROT_NONE mapped page, or whether
  * a (NUMA hinting) fault is required.
  */
-static inline bool gup_can_follow_protnone(unsigned int flags)
+static inline bool gup_can_follow_protnone(struct vm_area_struct *vma,
+					   unsigned int flags)
 {
 	/*
-	 * FOLL_FORCE has to be able to make progress even if the VMA is
-	 * inaccessible. Further, FOLL_FORCE access usually does not represent
-	 * application behaviour and we should avoid triggering NUMA hinting
-	 * faults.
+	 * If callers don't want to honor NUMA hinting faults, no need to
+	 * determine if we would actually have to trigger a NUMA hinting fault.
 	 */
-	return flags & FOLL_FORCE;
+	if (!(flags & FOLL_HONOR_NUMA_FAULT))
+		return true;
+
+	/*
+	 * NUMA hinting faults don't apply in inaccessible (PROT_NONE) VMAs.
+	 *
+	 * Requiring a fault here even for inaccessible VMAs would mean that
+	 * FOLL_FORCE cannot make any progress, because handle_mm_fault()
+	 * refuses to process NUMA hinting faults in inaccessible VMAs.
+	 */
+	return !vma_is_accessible(vma);
 }
 
 typedef int (*pte_fn_t)(pte_t *pte, unsigned long addr, void *data);

include/linux/mm_types.h

···
 	FOLL_PCI_P2PDMA = 1 << 10,
 	/* allow interrupts from generic signals */
 	FOLL_INTERRUPTIBLE = 1 << 11,
+	/*
+	 * Always honor (trigger) NUMA hinting faults.
+	 *
+	 * FOLL_WRITE implicitly honors NUMA hinting faults because a
+	 * PROT_NONE-mapped page is not writable (exceptions with FOLL_FORCE
+	 * apply). get_user_pages_fast_only() always implicitly honors NUMA
+	 * hinting faults.
+	 */
+	FOLL_HONOR_NUMA_FAULT = 1 << 12,
 
 	/* See also internal only FOLL flags in mm/internal.h */
 };

include/linux/pagewalk.h

···
 
 struct mm_walk;
 
+/* Locking requirement during a page walk. */
+enum page_walk_lock {
+	/* mmap_lock should be locked for read to stabilize the vma tree */
+	PGWALK_RDLOCK = 0,
+	/* vma will be write-locked during the walk */
+	PGWALK_WRLOCK = 1,
+	/* vma is expected to be already write-locked during the walk */
+	PGWALK_WRLOCK_VERIFY = 2,
+};
+
 /**
  * struct mm_walk_ops - callbacks for walk_page_range
  * @pgd_entry:		if set, called for each non-empty PGD (top-level) entry
···
 	int (*pre_vma)(unsigned long start, unsigned long end,
 		       struct mm_walk *walk);
 	void (*post_vma)(struct mm_walk *walk);
+	enum page_walk_lock walk_lock;
 };
 
 /*

lib/radix-tree.c

···
 void __rcu **radix_tree_iter_resume(void __rcu **slot,
 					struct radix_tree_iter *iter)
 {
-	slot++;
 	iter->index = __radix_tree_iter_add(iter, 1);
 	iter->next_index = iter->index;
 	iter->tags = 0;

lib/scatterlist.c

···
 
 failed:
 	while (sgtable->nents > sgtable->orig_nents)
-		put_page(sg_page(&sgtable->sgl[--sgtable->nents]));
+		unpin_user_page(sg_page(&sgtable->sgl[--sgtable->nents]));
 	return res;
 }
 

mm/compaction.c

···
 
 		/*
 		 * Check if the pageblock has already been marked skipped.
-		 * Only the aligned PFN is checked as the caller isolates
+		 * Only the first PFN is checked as the caller isolates
 		 * COMPACT_CLUSTER_MAX at a time so the second call must
 		 * not falsely conclude that the block should be skipped.
 		 */
-		if (!valid_page && pageblock_aligned(low_pfn)) {
+		if (!valid_page && (pageblock_aligned(low_pfn) ||
+				    low_pfn == cc->zone->zone_start_pfn)) {
 			if (!isolation_suitable(cc, page)) {
 				low_pfn = end_pfn;
 				folio = NULL;
···
 		 * before making it "skip" so other compaction instances do
 		 * not scan the same block.
 		 */
-		if (pageblock_aligned(low_pfn) &&
+		if ((pageblock_aligned(low_pfn) ||
+		     low_pfn == cc->zone->zone_start_pfn) &&
 		    !fast_find_block && !isolation_suitable(cc, page))
 			continue;
 

mm/damon/core.c

···
 		return NULL;
 	filter->type = type;
 	filter->matching = matching;
+	INIT_LIST_HEAD(&filter->list);
 	return filter;
 }
 

mm/damon/vaddr.c

···
 static const struct mm_walk_ops damon_mkold_ops = {
 	.pmd_entry = damon_mkold_pmd_entry,
 	.hugetlb_entry = damon_mkold_hugetlb_entry,
+	.walk_lock = PGWALK_RDLOCK,
 };
 
 static void damon_va_mkold(struct mm_struct *mm, unsigned long addr)
···
 static const struct mm_walk_ops damon_young_ops = {
 	.pmd_entry = damon_young_pmd_entry,
 	.hugetlb_entry = damon_young_hugetlb_entry,
+	.walk_lock = PGWALK_RDLOCK,
 };
 
 static bool damon_va_young(struct mm_struct *mm, unsigned long addr,

mm/gup.c

···
 	pte = ptep_get(ptep);
 	if (!pte_present(pte))
 		goto no_page;
-	if (pte_protnone(pte) && !gup_can_follow_protnone(flags))
+	if (pte_protnone(pte) && !gup_can_follow_protnone(vma, flags))
 		goto no_page;
 
 	page = vm_normal_page(vma, address, pte);
···
 	if (likely(!pmd_trans_huge(pmdval)))
 		return follow_page_pte(vma, address, pmd, flags, &ctx->pgmap);
 
-	if (pmd_protnone(pmdval) && !gup_can_follow_protnone(flags))
+	if (pmd_protnone(pmdval) && !gup_can_follow_protnone(vma, flags))
 		return no_page_table(vma, flags);
 
 	ptl = pmd_lock(mm, pmd);
···
 	if (WARN_ON_ONCE(foll_flags & FOLL_PIN))
 		return NULL;
 
+	/*
+	 * We never set FOLL_HONOR_NUMA_FAULT because callers don't expect
+	 * to fail on PROT_NONE-mapped pages.
+	 */
 	page = follow_page_mask(vma, address, foll_flags, &ctx);
 	if (ctx.pgmap)
 		put_dev_pagemap(ctx.pgmap);
···
 		gup_flags |= FOLL_UNLOCKABLE;
 	}
 
+	/*
+	 * For now, always trigger NUMA hinting faults. Some GUP users like
+	 * KVM require the hint to be as the calling context of GUP is
+	 * functionally similar to a memory reference from task context.
+	 */
+	gup_flags |= FOLL_HONOR_NUMA_FAULT;
+
 	/* FOLL_GET and FOLL_PIN are mutually exclusive. */
 	if (WARN_ON_ONCE((gup_flags & (FOLL_PIN | FOLL_GET)) ==
 			 (FOLL_PIN | FOLL_GET)))
···
 		struct page *page;
 		struct folio *folio;
 
-		if (pte_protnone(pte) && !gup_can_follow_protnone(flags))
+		/*
+		 * Always fallback to ordinary GUP on PROT_NONE-mapped pages:
+		 * pte_access_permitted() better should reject these pages
+		 * either way: otherwise, GUP-fast might succeed in
+		 * cases where ordinary GUP would fail due to VMA access
+		 * permissions.
+		 */
+		if (pte_protnone(pte))
 			goto pte_unmap;
 
 		if (!pte_access_permitted(pte, flags & FOLL_WRITE))
···
 
 		if (unlikely(pmd_trans_huge(pmd) || pmd_huge(pmd) ||
 			     pmd_devmap(pmd))) {
-			if (pmd_protnone(pmd) &&
-			    !gup_can_follow_protnone(flags))
+			/* See gup_pte_range() */
+			if (pmd_protnone(pmd))
 				return 0;
 
 			if (!gup_huge_pmd(pmd, pmdp, addr, next, flags,
···
 	if (WARN_ON_ONCE(gup_flags & ~(FOLL_WRITE | FOLL_LONGTERM |
 				       FOLL_FORCE | FOLL_PIN | FOLL_GET |
 				       FOLL_FAST_ONLY | FOLL_NOFAULT |
-				       FOLL_PCI_P2PDMA)))
+				       FOLL_PCI_P2PDMA | FOLL_HONOR_NUMA_FAULT)))
 		return -EINVAL;
 
 	if (gup_flags & FOLL_PIN)

mm/hmm.c

···
 	.pte_hole	= hmm_vma_walk_hole,
 	.hugetlb_entry	= hmm_vma_walk_hugetlb_entry,
 	.test_walk	= hmm_vma_walk_test,
+	.walk_lock	= PGWALK_RDLOCK,
 };
 
 /**

mm/huge_memory.c

···
 	if ((flags & FOLL_DUMP) && is_huge_zero_pmd(*pmd))
 		return ERR_PTR(-EFAULT);
 
-	/* Full NUMA hinting faults to serialise migration in fault paths */
-	if (pmd_protnone(*pmd) && !gup_can_follow_protnone(flags))
+	if (pmd_protnone(*pmd) && !gup_can_follow_protnone(vma, flags))
 		return NULL;
 
 	if (!pmd_write(*pmd) && gup_must_unshare(vma, flags, page))

mm/hugetlb.c

···
 						unsigned int order) { }
 #endif
 
+static inline void __clear_hugetlb_destructor(struct hstate *h,
+						struct folio *folio)
+{
+	lockdep_assert_held(&hugetlb_lock);
+
+	/*
+	 * Very subtle
+	 *
+	 * For non-gigantic pages set the destructor to the normal compound
+	 * page dtor.  This is needed in case someone takes an additional
+	 * temporary ref to the page, and freeing is delayed until they drop
+	 * their reference.
+	 *
+	 * For gigantic pages set the destructor to the null dtor.  This
+	 * destructor will never be called.  Before freeing the gigantic
+	 * page destroy_compound_gigantic_folio will turn the folio into a
+	 * simple group of pages.  After this the destructor does not
+	 * apply.
+	 *
+	 */
+	if (hstate_is_gigantic(h))
+		folio_set_compound_dtor(folio, NULL_COMPOUND_DTOR);
+	else
+		folio_set_compound_dtor(folio, COMPOUND_PAGE_DTOR);
+}
+
 /*
- * Remove hugetlb folio from lists, and update dtor so that the folio appears
- * as just a compound page.
+ * Remove hugetlb folio from lists.
+ * If vmemmap exists for the folio, update dtor so that the folio appears
+ * as just a compound page.  Otherwise, wait until after allocating vmemmap
+ * to update dtor.
  *
  * A reference is held on the folio, except in the case of demote.
  *
···
 	}
 
 	/*
-	 * Very subtle
-	 *
-	 * For non-gigantic pages set the destructor to the normal compound
-	 * page dtor.  This is needed in case someone takes an additional
-	 * temporary ref to the page, and freeing is delayed until they drop
-	 * their reference.
-	 *
-	 * For gigantic pages set the destructor to the null dtor.  This
-	 * destructor will never be called.  Before freeing the gigantic
-	 * page destroy_compound_gigantic_folio will turn the folio into a
-	 * simple group of pages.  After this the destructor does not
-	 * apply.
-	 *
-	 * This handles the case where more than one ref is held when and
-	 * after update_and_free_hugetlb_folio is called.
-	 *
-	 * In the case of demote we do not ref count the page as it will soon
-	 * be turned into a page of smaller size.
+	 * We can only clear the hugetlb destructor after allocating vmemmap
+	 * pages.  Otherwise, someone (memory error handling) may try to write
+	 * to tail struct pages.
+	 */
+	if (!folio_test_hugetlb_vmemmap_optimized(folio))
+		__clear_hugetlb_destructor(h, folio);
+
+	 /*
+	  * In the case of demote we do not ref count the page as it will soon
+	  * be turned into a page of smaller size.
 	 */
 	if (!demote)
 		folio_ref_unfreeze(folio, 1);
-	if (hstate_is_gigantic(h))
-		folio_set_compound_dtor(folio, NULL_COMPOUND_DTOR);
-	else
-		folio_set_compound_dtor(folio, COMPOUND_PAGE_DTOR);
 
 	h->nr_huge_pages--;
 	h->nr_huge_pages_node[nid]--;
···
 {
 	int i;
 	struct page *subpage;
+	bool clear_dtor = folio_test_hugetlb_vmemmap_optimized(folio);
 
 	if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported())
 		return;
···
 	 */
 	if (unlikely(folio_test_hwpoison(folio)))
 		folio_clear_hugetlb_hwpoison(folio);
+
+	/*
+	 * If vmemmap pages were allocated above, then we need to clear the
+	 * hugetlb destructor under the hugetlb lock.
+	 */
+	if (clear_dtor) {
+		spin_lock_irq(&hugetlb_lock);
+		__clear_hugetlb_destructor(h, folio);
+		spin_unlock_irq(&hugetlb_lock);
+	}
 
 	for (i = 0; i < pages_per_huge_page(h); i++) {
 		subpage = folio_page(folio, i);

mm/internal.h

···
 struct folio *try_grab_folio(struct page *page, int refs, unsigned int flags);
 int __must_check try_grab_page(struct page *page, unsigned int flags);
 
+/*
+ * mm/huge_memory.c
+ */
+struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
+				   unsigned long addr, pmd_t *pmd,
+				   unsigned int flags);
+
 enum {
 	/* mark page accessed */
 	FOLL_TOUCH = 1 << 16,
···
 	/* Paired with a memory barrier in page_try_share_anon_rmap(). */
 	if (IS_ENABLED(CONFIG_HAVE_FAST_GUP))
 		smp_rmb();
+
+	/*
+	 * During GUP-fast we might not get called on the head page for a
+	 * hugetlb page that is mapped using cont-PTE, because GUP-fast does
+	 * not work with the abstracted hugetlb PTEs that always point at the
+	 * head page. For hugetlb, PageAnonExclusive only applies on the head
+	 * page (as it cannot be partially COW-shared), so lookup the head page.
+	 */
+	if (unlikely(!PageHead(page) && PageHuge(page)))
+		page = compound_head(page);
 
 	/*
 	 * Note that PageKsm() pages cannot be exclusive, and consequently,

mm/ksm.c

···
 
 static const struct mm_walk_ops break_ksm_ops = {
 	.pmd_entry = break_ksm_pmd_entry,
+	.walk_lock = PGWALK_RDLOCK,
+};
+
+static const struct mm_walk_ops break_ksm_lock_vma_ops = {
+	.pmd_entry = break_ksm_pmd_entry,
+	.walk_lock = PGWALK_WRLOCK,
 };
 
 /*
···
  * of the process that owns 'vma'.  We also do not want to enforce
  * protection keys here anyway.
  */
-static int break_ksm(struct vm_area_struct *vma, unsigned long addr)
+static int break_ksm(struct vm_area_struct *vma, unsigned long addr, bool lock_vma)
 {
 	vm_fault_t ret = 0;
+	const struct mm_walk_ops *ops = lock_vma ?
+				&break_ksm_lock_vma_ops : &break_ksm_ops;
 
 	do {
 		int ksm_page;
 
 		cond_resched();
-		ksm_page = walk_page_range_vma(vma, addr, addr + 1,
-					       &break_ksm_ops, NULL);
+		ksm_page = walk_page_range_vma(vma, addr, addr + 1, ops, NULL);
 		if (WARN_ON_ONCE(ksm_page < 0))
 			return ksm_page;
 		if (!ksm_page)
···
 	mmap_read_lock(mm);
 	vma = find_mergeable_vma(mm, addr);
 	if (vma)
-		break_ksm(vma, addr);
+		break_ksm(vma, addr, false);
 	mmap_read_unlock(mm);
 }
 
···
  * in cmp_and_merge_page on one of the rmap_items we would be removing.
  */
 static int unmerge_ksm_pages(struct vm_area_struct *vma,
-			     unsigned long start, unsigned long end)
+			     unsigned long start, unsigned long end, bool lock_vma)
 {
 	unsigned long addr;
 	int err = 0;
···
 		if (signal_pending(current))
 			err = -ERESTARTSYS;
 		else
-			err = break_ksm(vma, addr);
+			err = break_ksm(vma, addr, lock_vma);
 	}
 	return err;
 }
···
 			if (!(vma->vm_flags & VM_MERGEABLE) || !vma->anon_vma)
 				continue;
 			err = unmerge_ksm_pages(vma,
-						vma->vm_start, vma->vm_end);
+						vma->vm_start, vma->vm_end, false);
 			if (err)
 				goto error;
 		}
···
 		return 0;
 
 	if (vma->anon_vma) {
-		err = unmerge_ksm_pages(vma, vma->vm_start, vma->vm_end);
+		err = unmerge_ksm_pages(vma, vma->vm_start, vma->vm_end, true);
 		if (err)
 			return err;
 	}
···
 			return 0;		/* just ignore the advice */
 
 		if (vma->anon_vma) {
-			err = unmerge_ksm_pages(vma, start, end);
+			err = unmerge_ksm_pages(vma, start, end, true);
 			if (err)
 				return err;
 		}
···
 			anon_vma->root == vma->anon_vma->root) {
 		return page;		/* still no need to copy it */
 	}
+	if (PageHWPoison(page))
+		return ERR_PTR(-EHWPOISON);
 	if (!PageUptodate(page))
 		return page;		/* let do_swap_page report the error */
 

mm/madvise.c

···
 
 static const struct mm_walk_ops swapin_walk_ops = {
 	.pmd_entry		= swapin_walk_pmd_entry,
+	.walk_lock		= PGWALK_RDLOCK,
 };
 
 static void shmem_swapin_range(struct vm_area_struct *vma,
···
 
 static const struct mm_walk_ops cold_walk_ops = {
 	.pmd_entry = madvise_cold_or_pageout_pte_range,
+	.walk_lock = PGWALK_RDLOCK,
 };
 
 static void madvise_cold_page_range(struct mmu_gather *tlb,
···
 
 static const struct mm_walk_ops madvise_free_walk_ops = {
 	.pmd_entry		= madvise_free_pte_range,
+	.walk_lock		= PGWALK_RDLOCK,
 };
 
 static int madvise_free_single_vma(struct vm_area_struct *vma,

mm/memcontrol.c

···
 
 static const struct mm_walk_ops precharge_walk_ops = {
 	.pmd_entry	= mem_cgroup_count_precharge_pte_range,
+	.walk_lock	= PGWALK_RDLOCK,
 };
 
 static unsigned long mem_cgroup_count_precharge(struct mm_struct *mm)
···
 
 static const struct mm_walk_ops charge_walk_ops = {
 	.pmd_entry	= mem_cgroup_move_charge_pte_range,
+	.walk_lock	= PGWALK_RDLOCK,
 };
 
 static void mem_cgroup_move_charge(void)

mm/memory-failure.c

···
 static const struct mm_walk_ops hwp_walk_ops = {
 	.pmd_entry = hwpoison_pte_range,
 	.hugetlb_entry = hwpoison_hugetlb_range,
+	.walk_lock = PGWALK_RDLOCK,
 };
 
 /*
···
 {
 	struct folio *folio;
 	struct page *p;
-	int ret = -EBUSY;
+	int ret = -EBUSY, ghp;
 	unsigned long count = 1;
 	bool huge = false;
 	static DEFINE_RATELIMIT_STATE(unpoison_rs, DEFAULT_RATELIMIT_INTERVAL,
···
 		goto unlock_mutex;
 	}
 
+	if (folio_test_slab(folio) || PageTable(&folio->page) || folio_test_reserved(folio))
+		goto unlock_mutex;
+
+	/*
+	 * Note that folio->_mapcount is overloaded in SLAB, so the simple test
+	 * in folio_mapped() has to be done after folio_test_slab() is checked.
+	 */
 	if (folio_mapped(folio)) {
 		unpoison_pr_info("Unpoison: Someone maps the hwpoison page %#lx\n",
 				 pfn, &unpoison_rs);
···
 		goto unlock_mutex;
 	}
 
-	if (folio_test_slab(folio) || PageTable(&folio->page) || folio_test_reserved(folio))
-		goto unlock_mutex;
-
-	ret = get_hwpoison_page(p, MF_UNPOISON);
-	if (!ret) {
+	ghp = get_hwpoison_page(p, MF_UNPOISON);
+	if (!ghp) {
 		if (PageHuge(p)) {
 			huge = true;
 			count = folio_free_raw_hwp(folio, false);
-			if (count == 0) {
-				ret = -EBUSY;
+			if (count == 0)
 				goto unlock_mutex;
-			}
 		}
 		ret = folio_test_clear_hwpoison(folio) ? 0 : -EBUSY;
-	} else if (ret < 0) {
-		if (ret == -EHWPOISON) {
+	} else if (ghp < 0) {
+		if (ghp == -EHWPOISON) {
 			ret = put_page_back_buddy(p) ? 0 : -EBUSY;
-		} else
+		} else {
+			ret = ghp;
 			unpoison_pr_info("Unpoison: failed to grab page %#lx\n",
 					 pfn, &unpoison_rs);
+		}
 	} else {
 		if (PageHuge(p)) {
 			huge = true;
 			count = folio_free_raw_hwp(folio, false);
 			if (count == 0) {
-				ret = -EBUSY;
 				folio_put(folio);
 				goto unlock_mutex;
 			}
···
 	if (ret > 0) {
 		ret = soft_offline_in_use_page(page);
 	} else if (ret == 0) {
-		if (!page_handle_poison(page, true, false) && try_again) {
-			try_again = false;
-			flags &= ~MF_COUNT_INCREASED;
-			goto retry;
+		if (!page_handle_poison(page, true, false)) {
+			if (try_again) {
+				try_again = false;
+				flags &= ~MF_COUNT_INCREASED;
+				goto retry;
+			}
+			ret = -EBUSY;
 		}
 	}
 

mm/mempolicy.c

···
 	.hugetlb_entry		= queue_folios_hugetlb,
 	.pmd_entry		= queue_folios_pte_range,
 	.test_walk		= queue_pages_test_walk,
+	.walk_lock		= PGWALK_RDLOCK,
+};
+
+static const struct mm_walk_ops queue_pages_lock_vma_walk_ops = {
+	.hugetlb_entry		= queue_folios_hugetlb,
+	.pmd_entry		= queue_folios_pte_range,
+	.test_walk		= queue_pages_test_walk,
+	.walk_lock		= PGWALK_WRLOCK,
 };
 
 /*
···
 static int
 queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end,
 		nodemask_t *nodes, unsigned long flags,
-		struct list_head *pagelist)
+		struct list_head *pagelist, bool lock_vma)
 {
 	int err;
 	struct queue_pages qp = {
···
 		.end = end,
 		.first = NULL,
 	};
+	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, &queue_pages_walk_ops, &qp);
+	err = walk_page_range(mm, start, end, ops, &qp);
 
 	if (!qp.first)
 		/* whole range in hole */
···
 	vma = find_vma(mm, 0);
 	VM_BUG_ON(!(flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)));
 	queue_pages_range(mm, vma->vm_start, mm->task_size, &nmask,
-			flags | MPOL_MF_DISCONTIG_OK, &pagelist);
+			flags | MPOL_MF_DISCONTIG_OK, &pagelist, false);
 
 	if (!list_empty(&pagelist)) {
 		err = migrate_pages(&pagelist, alloc_migration_target, NULL,
···
 	 * Lock the VMAs before scanning for pages to migrate, to ensure we don't
 	 * miss a concurrently inserted page.
 	 */
-	vma_iter_init(&vmi, mm, start);
-	for_each_vma_range(vmi, vma, end)
-		vma_start_write(vma);
-
 	ret = queue_pages_range(mm, start, end, nmask,
-			  flags | MPOL_MF_INVERT, &pagelist);
+			  flags | MPOL_MF_INVERT, &pagelist, true);
 
 	if (ret < 0) {
 		err = ret;

mm/migrate_device.c

···
 static const struct mm_walk_ops migrate_vma_walk_ops = {
 	.pmd_entry		= migrate_vma_collect_pmd,
 	.pte_hole		= migrate_vma_collect_hole,
+	.walk_lock		= PGWALK_RDLOCK,
 };
 
 /*

mm/mincore.c

···
 	.pmd_entry		= mincore_pte_range,
 	.pte_hole		= mincore_unmapped_range,
 	.hugetlb_entry		= mincore_hugetlb,
+	.walk_lock		= PGWALK_RDLOCK,
 };
 
 /*

mm/mlock.c

···
 {
 	static const struct mm_walk_ops mlock_walk_ops = {
 		.pmd_entry = mlock_pte_range,
+		.walk_lock = PGWALK_WRLOCK_VERIFY,
 	};
 
 	/*

mm/mprotect.c

···
 	.pte_entry		= prot_none_pte_entry,
 	.hugetlb_entry		= prot_none_hugetlb_entry,
 	.test_walk		= prot_none_test,
+	.walk_lock		= PGWALK_WRLOCK,
 };
 
 int

mm/pagewalk.c

···
 	return err;
 }
 
+static inline void process_mm_walk_lock(struct mm_struct *mm,
+					enum page_walk_lock walk_lock)
+{
+	if (walk_lock == PGWALK_RDLOCK)
+		mmap_assert_locked(mm);
+	else
+		mmap_assert_write_locked(mm);
+}
+
+static inline void process_vma_walk_lock(struct vm_area_struct *vma,
+					 enum page_walk_lock walk_lock)
+{
+#ifdef CONFIG_PER_VMA_LOCK
+	switch (walk_lock) {
+	case PGWALK_WRLOCK:
+		vma_start_write(vma);
+		break;
+	case PGWALK_WRLOCK_VERIFY:
+		vma_assert_write_locked(vma);
+		break;
+	case PGWALK_RDLOCK:
+		/* PGWALK_RDLOCK is handled by process_mm_walk_lock */
+		break;
+	}
+#endif
+}
+
 /**
  * walk_page_range - walk page table with caller specific callbacks
  * @mm:		mm_struct representing the target process of page table walk
···
 	if (!walk.mm)
 		return -EINVAL;
 
-	mmap_assert_locked(walk.mm);
+	process_mm_walk_lock(walk.mm, ops->walk_lock);
 
 	vma = find_vma(walk.mm, start);
 	do {
···
 			if (ops->pte_hole)
 				err = ops->pte_hole(start, next, -1, &walk);
 		} else { /* inside vma */
+			process_vma_walk_lock(vma, ops->walk_lock);
 			walk.vma = vma;
 			next = min(end, vma->vm_end);
 			vma = find_vma(mm, vma->vm_end);
···
 	if (start < vma->vm_start || end > vma->vm_end)
 		return -EINVAL;
 
-	mmap_assert_locked(walk.mm);
+	process_mm_walk_lock(walk.mm, ops->walk_lock);
+	process_vma_walk_lock(vma, ops->walk_lock);
 	return __walk_page_range(start, end, &walk);
 }
 
···
 	if (!walk.mm)
 		return -EINVAL;
 
-	mmap_assert_locked(walk.mm);
+	process_mm_walk_lock(walk.mm, ops->walk_lock);
+	process_vma_walk_lock(vma, ops->walk_lock);
 	return __walk_page_range(vma->vm_start, vma->vm_end, &walk);
 }
 

mm/swapfile.c

···
 	struct page *swapcache;
 	spinlock_t *ptl;
 	pte_t *pte, new_pte, old_pte;
-	bool hwposioned = false;
+	bool hwpoisoned = PageHWPoison(page);
 	int ret = 1;
 
 	swapcache = page;
···
 	if (unlikely(!page))
 		return -ENOMEM;
 	else if (unlikely(PTR_ERR(page) == -EHWPOISON))
-		hwposioned = true;
+		hwpoisoned = true;
 
 	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
 	if (unlikely(!pte || !pte_same_as_swp(ptep_get(pte),
···
 
 	old_pte = ptep_get(pte);
 
-	if (unlikely(hwposioned || !PageUptodate(page))) {
+	if (unlikely(hwpoisoned || !PageUptodate(page))) {
 		swp_entry_t swp_entry;
 
 		dec_mm_counter(vma->vm_mm, MM_SWAPENTS);
-		if (hwposioned) {
+		if (hwpoisoned) {
 			swp_entry = make_hwpoison_entry(swapcache);
 			page = swapcache;
 		} else {

mm/vmalloc.c

···
 		free_vm_area(area);
 		return NULL;
 	}
+
+	flush_cache_vmap((unsigned long)area->addr,
+			 (unsigned long)area->addr + count * PAGE_SIZE);
+
 	return area->addr;
 }
 EXPORT_SYMBOL_GPL(vmap_pfn);

mm/vmscan.c

···
 	static const struct mm_walk_ops mm_walk_ops = {
 		.test_walk = should_skip_vma,
 		.p4d_entry = walk_pud_range,
+		.walk_lock = PGWALK_RDLOCK,
 	};
 
 	int err;
···
 
 		spin_lock_irq(&pgdat->memcg_lru.lock);
 
-		VM_WARN_ON_ONCE(hlist_nulls_unhashed(&lruvec->lrugen.list));
+		if (hlist_nulls_unhashed(&lruvec->lrugen.list))
+			goto unlock;
 
 		gen = lruvec->lrugen.gen;
 
-		hlist_nulls_del_rcu(&lruvec->lrugen.list);
+		hlist_nulls_del_init_rcu(&lruvec->lrugen.list);
 		pgdat->memcg_lru.nr_memcgs[gen]--;
 
 		if (!pgdat->memcg_lru.nr_memcgs[gen] && gen == get_memcg_gen(pgdat->memcg_lru.seq))
 			WRITE_ONCE(pgdat->memcg_lru.seq, pgdat->memcg_lru.seq + 1);
-
+unlock:
 		spin_unlock_irq(&pgdat->memcg_lru.lock);
 	}
 }
···
 	rcu_read_lock();
 
 	hlist_nulls_for_each_entry_rcu(lrugen, pos, &pgdat->memcg_lru.fifo[gen][bin], list) {
-		if (op)
+		if (op) {
 			lru_gen_rotate_memcg(lruvec, op);
+			op = 0;
+		}
 
 		mem_cgroup_put(memcg);
 
···
 		memcg = lruvec_memcg(lruvec);
 
 		if (!mem_cgroup_tryget(memcg)) {
-			op = 0;
+			lru_gen_release_memcg(memcg);
 			memcg = NULL;
 			continue;
 		}

mm/zsmalloc.c

···
 
 static bool zs_page_isolate(struct page *page, isolate_mode_t mode)
 {
+	struct zs_pool *pool;
 	struct zspage *zspage;
 
 	/*
···
 	VM_BUG_ON_PAGE(PageIsolated(page), page);
 
 	zspage = get_zspage(page);
-	migrate_write_lock(zspage);
+	pool = zspage->pool;
+	spin_lock(&pool->lock);
 	inc_zspage_isolation(zspage);
-	migrate_write_unlock(zspage);
+	spin_unlock(&pool->lock);
 
 	return true;
 }
···
 	kunmap_atomic(s_addr);
 
 	replace_sub_page(class, zspage, newpage, page);
+	dec_zspage_isolation(zspage);
 	/*
 	 * Since we complete the data copy and set up new zspage structure,
 	 * it's okay to release the pool's lock.
 	 */
 	spin_unlock(&pool->lock);
-	dec_zspage_isolation(zspage);
 	migrate_write_unlock(zspage);
 
 	get_page(newpage);
···
 
 static void zs_page_putback(struct page *page)
 {
+	struct zs_pool *pool;
 	struct zspage *zspage;
 
 	VM_BUG_ON_PAGE(!PageIsolated(page), page);
 
 	zspage = get_zspage(page);
-	migrate_write_lock(zspage);
+	pool = zspage->pool;
+	spin_lock(&pool->lock);
 	dec_zspage_isolation(zspage);
-	migrate_write_unlock(zspage);
+	spin_unlock(&pool->lock);
 }
 
 static const struct movable_operations zsmalloc_mops = {

tools/testing/radix-tree/regression1.c

···
 	nr_threads = 2;
 	pthread_barrier_init(&worker_barrier, NULL, nr_threads);
 
-	threads = malloc(nr_threads * sizeof(pthread_t *));
+	threads = malloc(nr_threads * sizeof(*threads));
 
 	for (i = 0; i < nr_threads; i++) {
 		arg = i;

tools/testing/selftests/cgroup/test_kmem.c

···
 		goto cleanup;
 
 	cg_write(cg, "memory.high", "1M");
+
+	/* wait for RCU freeing */
+	sleep(1);
+
 	slab1 = cg_read_key_long(cg, "memory.stat", "slab ");
-	if (slab1 <= 0)
+	if (slab1 < 0)
 		goto cleanup;
 
 	current = cg_read_long(cg, "memory.current");
-	if (current <= 0)
+	if (current < 0)
 		goto cleanup;
 
 	if (slab1 < slab0 / 2 && current < slab0 / 2)

tools/testing/selftests/mm/hmm-tests.c

···
 
 #define ALIGN(x, a) (((x) + (a - 1)) & (~((a) - 1)))
 /* Just the flags we need, copied from mm.h: */
-#define FOLL_WRITE	0x01	/* check pte is writable */
-#define FOLL_LONGTERM   0x10000 /* mapping lifetime is indefinite */
 
+#ifndef FOLL_WRITE
+#define FOLL_WRITE	0x01	/* check pte is writable */
+#endif
+
+#ifndef FOLL_LONGTERM
+#define FOLL_LONGTERM   0x100 /* mapping lifetime is indefinite */
+#endif
 FIXTURE(hmm)
 {
 	int		fd;

tools/testing/selftests/mm/ksm_tests.c

···
 				printf("Size must be greater than 0\n");
 				return KSFT_FAIL;
 			}
+			break;
 		case 't':
 			{
 				int tmp = atoi(optarg);