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

22 files changed, 226 insertions, 86 deletions

diff --git a/mm/compaction.c b/mm/compaction.c
index 216081ab325a..38c8d216c6a3 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -933,11 +933,12 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 
 		/*
 		 * 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;
@@ -2030,7 +2031,8 @@ static isolate_migrate_t isolate_migratepages(struct compact_control *cc)
 		 * 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;
 
diff --git a/mm/damon/core.c b/mm/damon/core.c
index c1f1483c5082..bcd2bd9d6c10 100644
--- a/mm/damon/core.c
+++ b/mm/damon/core.c
@@ -273,6 +273,7 @@ struct damos_filter *damos_new_filter(enum damos_filter_type type,
 		return NULL;
 	filter->type = type;
 	filter->matching = matching;
+	INIT_LIST_HEAD(&filter->list);
 	return filter;
 }
 
diff --git a/mm/damon/vaddr.c b/mm/damon/vaddr.c
index d01cc46f4bf4..4c81a9dbd044 100644
--- a/mm/damon/vaddr.c
+++ b/mm/damon/vaddr.c
@@ -389,6 +389,7 @@ out:
 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)
@@ -532,6 +533,7 @@ out:
 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,
diff --git a/mm/gup.c b/mm/gup.c
index 2493ffa10f4b..3bbfae411880 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -597,7 +597,7 @@ static struct page *follow_page_pte(struct vm_area_struct *vma,
 	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);
@@ -714,7 +714,7 @@ static struct page *follow_pmd_mask(struct vm_area_struct *vma,
 	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);
@@ -844,6 +844,10 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
 	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);
@@ -2240,6 +2244,13 @@ static bool is_valid_gup_args(struct page **pages, int *locked,
 		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)))
@@ -2564,7 +2575,14 @@ static int gup_pte_range(pmd_t pmd, pmd_t *pmdp, unsigned long addr,
 		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))
@@ -2983,8 +3001,8 @@ static int gup_pmd_range(pud_t *pudp, pud_t pud, unsigned long addr, unsigned lo
 
 		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,
@@ -3164,7 +3182,7 @@ static int internal_get_user_pages_fast(unsigned long start,
 	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)
diff --git a/mm/hmm.c b/mm/hmm.c
index 855e25e59d8f..277ddcab4947 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -562,6 +562,7 @@ static const struct mm_walk_ops hmm_walk_ops = {
 	.pte_hole	= hmm_vma_walk_hole,
 	.hugetlb_entry	= hmm_vma_walk_hugetlb_entry,
 	.test_walk	= hmm_vma_walk_test,
+	.walk_lock	= PGWALK_RDLOCK,
 };
 
 /**
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index e371503f7746..154c210892a1 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1467,8 +1467,7 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
 	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))
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index abfdcaf114f1..5f498e8025cc 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1580,9 +1580,37 @@ static inline void destroy_compound_gigantic_folio(struct folio *folio,
 						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.
  *
@@ -1613,31 +1641,19 @@ static void __remove_hugetlb_folio(struct hstate *h, struct folio *folio,
 	}
 
 	/*
-	 * 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]--;
@@ -1706,6 +1722,7 @@ static void __update_and_free_hugetlb_folio(struct hstate *h,
 {
 	int i;
 	struct page *subpage;
+	bool clear_dtor = folio_test_hugetlb_vmemmap_optimized(folio);
 
 	if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported())
 		return;
@@ -1736,6 +1753,16 @@ static void __update_and_free_hugetlb_folio(struct hstate *h,
 	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);
 		subpage->flags &= ~(1 << PG_locked | 1 << PG_error |
diff --git a/mm/internal.h b/mm/internal.h
index c6ed10f0a5ad..d99ffb473f90 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -941,6 +941,13 @@ int migrate_device_coherent_page(struct page *page);
 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,
@@ -1015,6 +1022,16 @@ static inline bool gup_must_unshare(struct vm_area_struct *vma,
 		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,
 	 * cannot get pinned.
 	 */
diff --git a/mm/ksm.c b/mm/ksm.c
index 2653099539f2..8d6aee05421d 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -462,6 +462,12 @@ static int break_ksm_pmd_entry(pmd_t *pmd, unsigned long addr, unsigned long nex
 
 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,
 };
 
 /*
@@ -477,16 +483,17 @@ static const struct mm_walk_ops break_ksm_ops = {
  * 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)
@@ -572,7 +579,7 @@ static void break_cow(struct ksm_rmap_item *rmap_item)
 	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);
 }
 
@@ -878,7 +885,7 @@ static void remove_trailing_rmap_items(struct ksm_rmap_item **rmap_list)
  * 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;
@@ -889,7 +896,7 @@ static int unmerge_ksm_pages(struct vm_area_struct *vma,
 		if (signal_pending(current))
 			err = -ERESTARTSYS;
 		else
-			err = break_ksm(vma, addr);
+			err = break_ksm(vma, addr, lock_vma);
 	}
 	return err;
 }
@@ -1036,7 +1043,7 @@ static int unmerge_and_remove_all_rmap_items(void)
 			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;
 		}
@@ -2546,7 +2553,7 @@ static int __ksm_del_vma(struct vm_area_struct *vma)
 		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;
 	}
@@ -2684,7 +2691,7 @@ int ksm_madvise(struct vm_area_struct *vma, unsigned long start,
 			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;
 		}
@@ -2800,6 +2807,8 @@ struct page *ksm_might_need_to_copy(struct page *page,
 			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 */
 
diff --git a/mm/madvise.c b/mm/madvise.c
index 8498f700c284..1fb2a11d77d9 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -232,6 +232,7 @@ static int swapin_walk_pmd_entry(pmd_t *pmd, unsigned long start,
 
 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,
@@ -537,6 +538,7 @@ regular_folio:
 
 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,
@@ -760,6 +762,7 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr,
 
 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,
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index d83f99580900..8e125aa5a18d 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -6013,6 +6013,7 @@ static int mem_cgroup_count_precharge_pte_range(pmd_t *pmd,
 
 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)
@@ -6292,6 +6293,7 @@ put:			/* get_mctgt_type() gets & locks the page */
 
 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)
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 976747d28ce7..55dfe8a7bf4b 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -827,6 +827,7 @@ static int hwpoison_hugetlb_range(pte_t *ptep, unsigned long hmask,
 static const struct mm_walk_ops hwp_walk_ops = {
 	.pmd_entry = hwpoison_pte_range,
 	.hugetlb_entry = hwpoison_hugetlb_range,
+	.walk_lock = PGWALK_RDLOCK,
 };
 
 /*
@@ -2500,7 +2501,7 @@ int unpoison_memory(unsigned long pfn)
 {
 	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,
@@ -2533,6 +2534,13 @@ int unpoison_memory(unsigned long pfn)
 		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);
@@ -2545,32 +2553,28 @@ int unpoison_memory(unsigned long pfn)
 		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;
 			}
@@ -2771,10 +2775,13 @@ retry:
 	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;
 		}
 	}
 
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index c53f8beeb507..ec2eaceffd74 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -718,6 +718,14 @@ static const struct mm_walk_ops queue_pages_walk_ops = {
 	.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,
 };
 
 /*
@@ -738,7 +746,7 @@ static const struct mm_walk_ops queue_pages_walk_ops = {
 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 = {
@@ -749,8 +757,10 @@ queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end,
 		.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 */
@@ -1078,7 +1088,7 @@ static int migrate_to_node(struct mm_struct *mm, int source, int dest,
 	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,
@@ -1321,12 +1331,8 @@ static long do_mbind(unsigned long start, unsigned long len,
 	 * 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;
diff --git a/mm/migrate_device.c b/mm/migrate_device.c
index 6c556b5876c6..d69131adc51c 100644
--- a/mm/migrate_device.c
+++ b/mm/migrate_device.c
@@ -279,6 +279,7 @@ next:
 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,
 };
 
 /*
diff --git a/mm/mincore.c b/mm/mincore.c
index b7f7a516b26c..dad3622cc963 100644
--- a/mm/mincore.c
+++ b/mm/mincore.c
@@ -176,6 +176,7 @@ static const struct mm_walk_ops mincore_walk_ops = {
 	.pmd_entry		= mincore_pte_range,
 	.pte_hole		= mincore_unmapped_range,
 	.hugetlb_entry		= mincore_hugetlb,
+	.walk_lock		= PGWALK_RDLOCK,
 };
 
 /*
diff --git a/mm/mlock.c b/mm/mlock.c
index 1746600a2e14..06bdfab83b58 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -371,6 +371,7 @@ static void mlock_vma_pages_range(struct vm_area_struct *vma,
 {
 	static const struct mm_walk_ops mlock_walk_ops = {
 		.pmd_entry = mlock_pte_range,
+		.walk_lock = PGWALK_WRLOCK_VERIFY,
 	};
 
 	/*
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 7cd7f644da80..130db91d3a8c 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -568,6 +568,7 @@ static const struct mm_walk_ops prot_none_walk_ops = {
 	.pte_entry		= prot_none_pte_entry,
 	.hugetlb_entry		= prot_none_hugetlb_entry,
 	.test_walk		= prot_none_test,
+	.walk_lock		= PGWALK_WRLOCK,
 };
 
 int
diff --git a/mm/pagewalk.c b/mm/pagewalk.c
index 2022333805d3..9b2d23fbf4d3 100644
--- a/mm/pagewalk.c
+++ b/mm/pagewalk.c
@@ -400,6 +400,33 @@ static int __walk_page_range(unsigned long start, unsigned long end,
 	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
@@ -459,7 +486,7 @@ int walk_page_range(struct mm_struct *mm, unsigned long start,
 	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 {
@@ -474,6 +501,7 @@ int walk_page_range(struct mm_struct *mm, unsigned long start,
 			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);
@@ -549,7 +577,8 @@ int walk_page_range_vma(struct vm_area_struct *vma, unsigned long start,
 	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);
 }
 
@@ -566,7 +595,8 @@ int walk_page_vma(struct vm_area_struct *vma, const struct mm_walk_ops *ops,
 	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);
 }
 
diff --git a/mm/swapfile.c b/mm/swapfile.c
index b52145c6bac2..d46933adf789 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -1745,7 +1745,7 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd,
 	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;
@@ -1753,7 +1753,7 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd,
 	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),
@@ -1764,11 +1764,11 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd,
 
 	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 {
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 93cf99aba335..228a4a5312f2 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -2979,6 +2979,10 @@ void *vmap_pfn(unsigned long *pfns, unsigned int count, pgprot_t prot)
 		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);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 6cbe921ef662..c7c149cb8d66 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -4284,6 +4284,7 @@ static void walk_mm(struct lruvec *lruvec, struct mm_struct *mm, struct lru_gen_
 	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;
@@ -4855,16 +4856,17 @@ void lru_gen_release_memcg(struct mem_cgroup *memcg)
 
 		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);
 	}
 }
@@ -5446,8 +5448,10 @@ restart:
 	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);
 
@@ -5455,7 +5459,7 @@ restart:
 		memcg = lruvec_memcg(lruvec);
 
 		if (!mem_cgroup_tryget(memcg)) {
-			op = 0;
+			lru_gen_release_memcg(memcg);
 			memcg = NULL;
 			continue;
 		}
diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
index 32f5bc4074df..b58f957429f0 100644
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -1777,6 +1777,7 @@ static void replace_sub_page(struct size_class *class, struct zspage *zspage,
 
 static bool zs_page_isolate(struct page *page, isolate_mode_t mode)
 {
+	struct zs_pool *pool;
 	struct zspage *zspage;
 
 	/*
@@ -1786,9 +1787,10 @@ static bool zs_page_isolate(struct page *page, isolate_mode_t mode)
 	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;
 }
@@ -1854,12 +1856,12 @@ static int zs_page_migrate(struct page *newpage, struct page *page,
 	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);
@@ -1876,14 +1878,16 @@ static int zs_page_migrate(struct page *newpage, struct page *page,
 
 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 = {