Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

8 files changed, 65 insertions, 86 deletions

diff --git a/mm/highmem.c b/mm/highmem.c
index 0cc0c4da7ed9..1a692997fac4 100644
--- a/mm/highmem.c
+++ b/mm/highmem.c
@@ -624,7 +624,7 @@ void __kmap_local_sched_out(void)
 
 		/* With debug all even slots are unmapped and act as guard */
 		if (IS_ENABLED(CONFIG_DEBUG_KMAP_LOCAL) && !(i & 0x01)) {
-			WARN_ON_ONCE(!pte_none(pteval));
+			WARN_ON_ONCE(pte_val(pteval) != 0);
 			continue;
 		}
 		if (WARN_ON_ONCE(pte_none(pteval)))
@@ -661,7 +661,7 @@ void __kmap_local_sched_in(void)
 
 		/* With debug all even slots are unmapped and act as guard */
 		if (IS_ENABLED(CONFIG_DEBUG_KMAP_LOCAL) && !(i & 0x01)) {
-			WARN_ON_ONCE(!pte_none(pteval));
+			WARN_ON_ONCE(pte_val(pteval) != 0);
 			continue;
 		}
 		if (WARN_ON_ONCE(pte_none(pteval)))
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 2fe38212e07c..c468fee595ff 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2145,15 +2145,14 @@ void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 	 * pmd against. Otherwise we can end up replacing wrong folio.
 	 */
 	VM_BUG_ON(freeze && !folio);
-	if (folio) {
-		VM_WARN_ON_ONCE(!folio_test_locked(folio));
-		if (folio != page_folio(pmd_page(*pmd)))
-			goto out;
-	}
+	VM_WARN_ON_ONCE(folio && !folio_test_locked(folio));
 
 	if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd) ||
-	    is_pmd_migration_entry(*pmd))
+	    is_pmd_migration_entry(*pmd)) {
+		if (folio && folio != page_folio(pmd_page(*pmd)))
+			goto out;
 		__split_huge_pmd_locked(vma, pmd, range.start, freeze);
+	}
 
 out:
 	spin_unlock(ptl);
diff --git a/mm/list_lru.c b/mm/list_lru.c
index c669d87001a6..ba76428ceece 100644
--- a/mm/list_lru.c
+++ b/mm/list_lru.c
@@ -395,12 +395,6 @@ static void memcg_reparent_list_lru_node(struct list_lru *lru, int nid,
 	struct list_lru_one *src, *dst;
 
 	/*
-	 * If there is no lru entry in this nlru, we can skip it immediately.
-	 */
-	if (!READ_ONCE(nlru->nr_items))
-		return;
-
-	/*
 	 * Since list_lru_{add,del} may be called under an IRQ-safe lock,
 	 * we have to use IRQ-safe primitives here to avoid deadlock.
 	 */
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index a2516d31db6c..8c74107a2b15 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1191,8 +1191,10 @@ int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from,
  */
 static struct page *new_page(struct page *page, unsigned long start)
 {
+	struct folio *dst, *src = page_folio(page);
 	struct vm_area_struct *vma;
 	unsigned long address;
+	gfp_t gfp = GFP_HIGHUSER_MOVABLE | __GFP_RETRY_MAYFAIL;
 
 	vma = find_vma(current->mm, start);
 	while (vma) {
@@ -1202,24 +1204,19 @@ static struct page *new_page(struct page *page, unsigned long start)
 		vma = vma->vm_next;
 	}
 
-	if (PageHuge(page)) {
-		return alloc_huge_page_vma(page_hstate(compound_head(page)),
+	if (folio_test_hugetlb(src))
+		return alloc_huge_page_vma(page_hstate(&src->page),
 				vma, address);
-	} else if (PageTransHuge(page)) {
-		struct page *thp;
 
-		thp = alloc_hugepage_vma(GFP_TRANSHUGE, vma, address,
-					 HPAGE_PMD_ORDER);
-		if (!thp)
-			return NULL;
-		prep_transhuge_page(thp);
-		return thp;
-	}
+	if (folio_test_large(src))
+		gfp = GFP_TRANSHUGE;
+
 	/*
-	 * if !vma, alloc_page_vma() will use task or system default policy
+	 * if !vma, vma_alloc_folio() will use task or system default policy
 	 */
-	return alloc_page_vma(GFP_HIGHUSER_MOVABLE | __GFP_RETRY_MAYFAIL,
-			vma, address);
+	dst = vma_alloc_folio(gfp, folio_order(src), vma, address,
+			folio_test_large(src));
+	return &dst->page;
 }
 #else
 
@@ -2227,6 +2224,19 @@ out:
 }
 EXPORT_SYMBOL(alloc_pages_vma);
 
+struct folio *vma_alloc_folio(gfp_t gfp, int order, struct vm_area_struct *vma,
+		unsigned long addr, bool hugepage)
+{
+	struct folio *folio;
+
+	folio = (struct folio *)alloc_pages_vma(gfp, order, vma, addr,
+			hugepage);
+	if (folio && order > 1)
+		prep_transhuge_page(&folio->page);
+
+	return folio;
+}
+
 /**
  * alloc_pages - Allocate pages.
  * @gfp: GFP flags.
@@ -2733,6 +2743,7 @@ alloc_new:
 	mpol_new = kmem_cache_alloc(policy_cache, GFP_KERNEL);
 	if (!mpol_new)
 		goto err_out;
+	atomic_set(&mpol_new->refcnt, 1);
 	goto restart;
 }
 
diff --git a/mm/migrate.c b/mm/migrate.c
index de175e2fdba5..6c31ee1e1c9b 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1520,10 +1520,11 @@ out:
 
 struct page *alloc_migration_target(struct page *page, unsigned long private)
 {
+	struct folio *folio = page_folio(page);
 	struct migration_target_control *mtc;
 	gfp_t gfp_mask;
 	unsigned int order = 0;
-	struct page *new_page = NULL;
+	struct folio *new_folio = NULL;
 	int nid;
 	int zidx;
 
@@ -1531,34 +1532,31 @@ struct page *alloc_migration_target(struct page *page, unsigned long private)
 	gfp_mask = mtc->gfp_mask;
 	nid = mtc->nid;
 	if (nid == NUMA_NO_NODE)
-		nid = page_to_nid(page);
+		nid = folio_nid(folio);
 
-	if (PageHuge(page)) {
-		struct hstate *h = page_hstate(compound_head(page));
+	if (folio_test_hugetlb(folio)) {
+		struct hstate *h = page_hstate(&folio->page);
 
 		gfp_mask = htlb_modify_alloc_mask(h, gfp_mask);
 		return alloc_huge_page_nodemask(h, nid, mtc->nmask, gfp_mask);
 	}
 
-	if (PageTransHuge(page)) {
+	if (folio_test_large(folio)) {
 		/*
 		 * clear __GFP_RECLAIM to make the migration callback
 		 * consistent with regular THP allocations.
 		 */
 		gfp_mask &= ~__GFP_RECLAIM;
 		gfp_mask |= GFP_TRANSHUGE;
-		order = HPAGE_PMD_ORDER;
+		order = folio_order(folio);
 	}
-	zidx = zone_idx(page_zone(page));
+	zidx = zone_idx(folio_zone(folio));
 	if (is_highmem_idx(zidx) || zidx == ZONE_MOVABLE)
 		gfp_mask |= __GFP_HIGHMEM;
 
-	new_page = __alloc_pages(gfp_mask, order, nid, mtc->nmask);
-
-	if (new_page && PageTransHuge(new_page))
-		prep_transhuge_page(new_page);
+	new_folio = __folio_alloc(gfp_mask, order, nid, mtc->nmask);
 
-	return new_page;
+	return &new_folio->page;
 }
 
 #ifdef CONFIG_NUMA
@@ -1999,32 +1997,20 @@ static struct page *alloc_misplaced_dst_page(struct page *page,
 					   unsigned long data)
 {
 	int nid = (int) data;
-	struct page *newpage;
-
-	newpage = __alloc_pages_node(nid,
-					 (GFP_HIGHUSER_MOVABLE |
-					  __GFP_THISNODE | __GFP_NOMEMALLOC |
-					  __GFP_NORETRY | __GFP_NOWARN) &
-					 ~__GFP_RECLAIM, 0);
-
-	return newpage;
-}
-
-static struct page *alloc_misplaced_dst_page_thp(struct page *page,
-						 unsigned long data)
-{
-	int nid = (int) data;
-	struct page *newpage;
-
-	newpage = alloc_pages_node(nid, (GFP_TRANSHUGE_LIGHT | __GFP_THISNODE),
-				   HPAGE_PMD_ORDER);
-	if (!newpage)
-		goto out;
-
-	prep_transhuge_page(newpage);
+	int order = compound_order(page);
+	gfp_t gfp = __GFP_THISNODE;
+	struct folio *new;
+
+	if (order > 0)
+		gfp |= GFP_TRANSHUGE_LIGHT;
+	else {
+		gfp |= GFP_HIGHUSER_MOVABLE | __GFP_NOMEMALLOC | __GFP_NORETRY |
+			__GFP_NOWARN;
+		gfp &= ~__GFP_RECLAIM;
+	}
+	new = __folio_alloc_node(gfp, order, nid);
 
-out:
-	return newpage;
+	return &new->page;
 }
 
 static int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page)
@@ -2082,23 +2068,9 @@ int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma,
 	int nr_remaining;
 	unsigned int nr_succeeded;
 	LIST_HEAD(migratepages);
-	new_page_t *new;
-	bool compound;
 	int nr_pages = thp_nr_pages(page);
 
 	/*
-	 * PTE mapped THP or HugeTLB page can't reach here so the page could
-	 * be either base page or THP.  And it must be head page if it is
-	 * THP.
-	 */
-	compound = PageTransHuge(page);
-
-	if (compound)
-		new = alloc_misplaced_dst_page_thp;
-	else
-		new = alloc_misplaced_dst_page;
-
-	/*
 	 * Don't migrate file pages that are mapped in multiple processes
 	 * with execute permissions as they are probably shared libraries.
 	 */
@@ -2118,9 +2090,9 @@ int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma,
 		goto out;
 
 	list_add(&page->lru, &migratepages);
-	nr_remaining = migrate_pages(&migratepages, *new, NULL, node,
-				     MIGRATE_ASYNC, MR_NUMA_MISPLACED,
-				     &nr_succeeded);
+	nr_remaining = migrate_pages(&migratepages, alloc_misplaced_dst_page,
+				     NULL, node, MIGRATE_ASYNC,
+				     MR_NUMA_MISPLACED, &nr_succeeded);
 	if (nr_remaining) {
 		if (!list_empty(&migratepages)) {
 			list_del(&page->lru);
diff --git a/mm/mremap.c b/mm/mremap.c
index 9d76da79594d..303d3290b938 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -486,6 +486,9 @@ unsigned long move_page_tables(struct vm_area_struct *vma,
 	pmd_t *old_pmd, *new_pmd;
 	pud_t *old_pud, *new_pud;
 
+	if (!len)
+		return 0;
+
 	old_end = old_addr + len;
 	flush_cache_range(vma, old_addr, old_end);
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 2db95780e003..6e5b4488a0c5 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -128,7 +128,7 @@ static DEFINE_MUTEX(pcp_batch_high_lock);
 struct pagesets {
 	local_lock_t lock;
 };
-static DEFINE_PER_CPU(struct pagesets, pagesets) __maybe_unused = {
+static DEFINE_PER_CPU(struct pagesets, pagesets) = {
 	.lock = INIT_LOCAL_LOCK(lock),
 };
 
diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c
index 1187f9c1ec5b..14a5cda73dee 100644
--- a/mm/page_vma_mapped.c
+++ b/mm/page_vma_mapped.c
@@ -163,7 +163,8 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw)
 		return not_found(pvmw);
 
 	if (unlikely(is_vm_hugetlb_page(vma))) {
-		unsigned long size = pvmw->nr_pages * PAGE_SIZE;
+		struct hstate *hstate = hstate_vma(vma);
+		unsigned long size = huge_page_size(hstate);
 		/* The only possible mapping was handled on last iteration */
 		if (pvmw->pte)
 			return not_found(pvmw);
@@ -173,8 +174,7 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw)
 		if (!pvmw->pte)
 			return false;
 
-		pvmw->ptl = huge_pte_lockptr(size_to_hstate(size), mm,
-						pvmw->pte);
+		pvmw->ptl = huge_pte_lockptr(hstate, mm, pvmw->pte);
 		spin_lock(pvmw->ptl);
 		if (!check_pte(pvmw))
 			return not_found(pvmw);