Merging upstream version 6.7.7.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

1 files changed, 457 insertions, 166 deletions

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 5e6c4d367d..6feb3e0630 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -984,7 +984,7 @@ static long region_count(struct resv_map *resv, long f, long t)
 
 /*
  * Convert the address within this vma to the page offset within
- * the mapping, in pagecache page units; huge pages here.
+ * the mapping, huge page units here.
  */
 static pgoff_t vma_hugecache_offset(struct hstate *h,
 			struct vm_area_struct *vma, unsigned long address)
@@ -993,13 +993,6 @@ static pgoff_t vma_hugecache_offset(struct hstate *h,
 			(vma->vm_pgoff >> huge_page_order(h));
 }
 
-pgoff_t linear_hugepage_index(struct vm_area_struct *vma,
-				     unsigned long address)
-{
-	return vma_hugecache_offset(hstate_vma(vma), vma, address);
-}
-EXPORT_SYMBOL_GPL(linear_hugepage_index);
-
 /**
  * vma_kernel_pagesize - Page size granularity for this VMA.
  * @vma: The user mapping.
@@ -1485,7 +1478,7 @@ static int hstate_next_node_to_alloc(struct hstate *h,
 }
 
 /*
- * helper for remove_pool_huge_page() - return the previously saved
+ * helper for remove_pool_hugetlb_folio() - return the previously saved
  * node ["this node"] from which to free a huge page.  Advance the
  * next node id whether or not we find a free huge page to free so
  * that the next attempt to free addresses the next node.
@@ -1759,7 +1752,12 @@ static void __update_and_free_hugetlb_folio(struct hstate *h,
 	if (folio_test_hugetlb_raw_hwp_unreliable(folio))
 		return;
 
-	if (hugetlb_vmemmap_restore(h, &folio->page)) {
+	/*
+	 * If folio is not vmemmap optimized (!clear_dtor), then the folio
+	 * is no longer identified as a hugetlb page.  hugetlb_vmemmap_restore_folio
+	 * can only be passed hugetlb pages and will BUG otherwise.
+	 */
+	if (clear_dtor && hugetlb_vmemmap_restore_folio(h, folio)) {
 		spin_lock_irq(&hugetlb_lock);
 		/*
 		 * If we cannot allocate vmemmap pages, just refuse to free the
@@ -1821,22 +1819,22 @@ static void free_hpage_workfn(struct work_struct *work)
 	node = llist_del_all(&hpage_freelist);
 
 	while (node) {
-		struct page *page;
+		struct folio *folio;
 		struct hstate *h;
 
-		page = container_of((struct address_space **)node,
-				     struct page, mapping);
+		folio = container_of((struct address_space **)node,
+				     struct folio, mapping);
 		node = node->next;
-		page->mapping = NULL;
+		folio->mapping = NULL;
 		/*
 		 * The VM_BUG_ON_FOLIO(!folio_test_hugetlb(folio), folio) in
 		 * folio_hstate() is going to trigger because a previous call to
 		 * remove_hugetlb_folio() will clear the hugetlb bit, so do
 		 * not use folio_hstate() directly.
 		 */
-		h = size_to_hstate(page_size(page));
+		h = size_to_hstate(folio_size(folio));
 
-		__update_and_free_hugetlb_folio(h, page_folio(page));
+		__update_and_free_hugetlb_folio(h, folio);
 
 		cond_resched();
 	}
@@ -1868,13 +1866,93 @@ static void update_and_free_hugetlb_folio(struct hstate *h, struct folio *folio,
 		schedule_work(&free_hpage_work);
 }
 
-static void update_and_free_pages_bulk(struct hstate *h, struct list_head *list)
+static void bulk_vmemmap_restore_error(struct hstate *h,
+					struct list_head *folio_list,
+					struct list_head *non_hvo_folios)
 {
-	struct page *page, *t_page;
-	struct folio *folio;
+	struct folio *folio, *t_folio;
+
+	if (!list_empty(non_hvo_folios)) {
+		/*
+		 * Free any restored hugetlb pages so that restore of the
+		 * entire list can be retried.
+		 * The idea is that in the common case of ENOMEM errors freeing
+		 * hugetlb pages with vmemmap we will free up memory so that we
+		 * can allocate vmemmap for more hugetlb pages.
+		 */
+		list_for_each_entry_safe(folio, t_folio, non_hvo_folios, lru) {
+			list_del(&folio->lru);
+			spin_lock_irq(&hugetlb_lock);
+			__clear_hugetlb_destructor(h, folio);
+			spin_unlock_irq(&hugetlb_lock);
+			update_and_free_hugetlb_folio(h, folio, false);
+			cond_resched();
+		}
+	} else {
+		/*
+		 * In the case where there are no folios which can be
+		 * immediately freed, we loop through the list trying to restore
+		 * vmemmap individually in the hope that someone elsewhere may
+		 * have done something to cause success (such as freeing some
+		 * memory).  If unable to restore a hugetlb page, the hugetlb
+		 * page is made a surplus page and removed from the list.
+		 * If are able to restore vmemmap and free one hugetlb page, we
+		 * quit processing the list to retry the bulk operation.
+		 */
+		list_for_each_entry_safe(folio, t_folio, folio_list, lru)
+			if (hugetlb_vmemmap_restore_folio(h, folio)) {
+				list_del(&folio->lru);
+				spin_lock_irq(&hugetlb_lock);
+				add_hugetlb_folio(h, folio, true);
+				spin_unlock_irq(&hugetlb_lock);
+			} else {
+				list_del(&folio->lru);
+				spin_lock_irq(&hugetlb_lock);
+				__clear_hugetlb_destructor(h, folio);
+				spin_unlock_irq(&hugetlb_lock);
+				update_and_free_hugetlb_folio(h, folio, false);
+				cond_resched();
+				break;
+			}
+	}
+}
+
+static void update_and_free_pages_bulk(struct hstate *h,
+						struct list_head *folio_list)
+{
+	long ret;
+	struct folio *folio, *t_folio;
+	LIST_HEAD(non_hvo_folios);
+
+	/*
+	 * First allocate required vmemmmap (if necessary) for all folios.
+	 * Carefully handle errors and free up any available hugetlb pages
+	 * in an effort to make forward progress.
+	 */
+retry:
+	ret = hugetlb_vmemmap_restore_folios(h, folio_list, &non_hvo_folios);
+	if (ret < 0) {
+		bulk_vmemmap_restore_error(h, folio_list, &non_hvo_folios);
+		goto retry;
+	}
+
+	/*
+	 * At this point, list should be empty, ret should be >= 0 and there
+	 * should only be pages on the non_hvo_folios list.
+	 * Do note that the non_hvo_folios list could be empty.
+	 * Without HVO enabled, ret will be 0 and there is no need to call
+	 * __clear_hugetlb_destructor as this was done previously.
+	 */
+	VM_WARN_ON(!list_empty(folio_list));
+	VM_WARN_ON(ret < 0);
+	if (!list_empty(&non_hvo_folios) && ret) {
+		spin_lock_irq(&hugetlb_lock);
+		list_for_each_entry(folio, &non_hvo_folios, lru)
+			__clear_hugetlb_destructor(h, folio);
+		spin_unlock_irq(&hugetlb_lock);
+	}
 
-	list_for_each_entry_safe(page, t_page, list, lru) {
-		folio = page_folio(page);
+	list_for_each_entry_safe(folio, t_folio, &non_hvo_folios, lru) {
 		update_and_free_hugetlb_folio(h, folio, false);
 		cond_resched();
 	}
@@ -1938,6 +2016,7 @@ void free_huge_folio(struct folio *folio)
 				     pages_per_huge_page(h), folio);
 	hugetlb_cgroup_uncharge_folio_rsvd(hstate_index(h),
 					  pages_per_huge_page(h), folio);
+	mem_cgroup_uncharge(folio);
 	if (restore_reserve)
 		h->resv_huge_pages++;
 
@@ -1967,16 +2046,21 @@ static void __prep_account_new_huge_page(struct hstate *h, int nid)
 	h->nr_huge_pages_node[nid]++;
 }
 
-static void __prep_new_hugetlb_folio(struct hstate *h, struct folio *folio)
+static void init_new_hugetlb_folio(struct hstate *h, struct folio *folio)
 {
-	hugetlb_vmemmap_optimize(h, &folio->page);
-	INIT_LIST_HEAD(&folio->lru);
 	folio_set_hugetlb(folio);
+	INIT_LIST_HEAD(&folio->lru);
 	hugetlb_set_folio_subpool(folio, NULL);
 	set_hugetlb_cgroup(folio, NULL);
 	set_hugetlb_cgroup_rsvd(folio, NULL);
 }
 
+static void __prep_new_hugetlb_folio(struct hstate *h, struct folio *folio)
+{
+	init_new_hugetlb_folio(h, folio);
+	hugetlb_vmemmap_optimize_folio(h, folio);
+}
+
 static void prep_new_hugetlb_folio(struct hstate *h, struct folio *folio, int nid)
 {
 	__prep_new_hugetlb_folio(h, folio);
@@ -2110,20 +2194,6 @@ struct address_space *hugetlb_page_mapping_lock_write(struct page *hpage)
 	return NULL;
 }
 
-pgoff_t hugetlb_basepage_index(struct page *page)
-{
-	struct page *page_head = compound_head(page);
-	pgoff_t index = page_index(page_head);
-	unsigned long compound_idx;
-
-	if (compound_order(page_head) > MAX_ORDER)
-		compound_idx = page_to_pfn(page) - page_to_pfn(page_head);
-	else
-		compound_idx = page - page_head;
-
-	return (index << compound_order(page_head)) + compound_idx;
-}
-
 static struct folio *alloc_buddy_hugetlb_folio(struct hstate *h,
 		gfp_t gfp_mask, int nid, nodemask_t *nmask,
 		nodemask_t *node_alloc_noretry)
@@ -2187,16 +2257,9 @@ retry:
 	return page_folio(page);
 }
 
-/*
- * Common helper to allocate a fresh hugetlb page. All specific allocators
- * should use this function to get new hugetlb pages
- *
- * Note that returned page is 'frozen':  ref count of head page and all tail
- * pages is zero.
- */
-static struct folio *alloc_fresh_hugetlb_folio(struct hstate *h,
-		gfp_t gfp_mask, int nid, nodemask_t *nmask,
-		nodemask_t *node_alloc_noretry)
+static struct folio *__alloc_fresh_hugetlb_folio(struct hstate *h,
+				gfp_t gfp_mask, int nid, nodemask_t *nmask,
+				nodemask_t *node_alloc_noretry)
 {
 	struct folio *folio;
 	bool retry = false;
@@ -2209,6 +2272,7 @@ retry:
 				nid, nmask, node_alloc_noretry);
 	if (!folio)
 		return NULL;
+
 	if (hstate_is_gigantic(h)) {
 		if (!prep_compound_gigantic_folio(folio, huge_page_order(h))) {
 			/*
@@ -2223,32 +2287,84 @@ retry:
 			return NULL;
 		}
 	}
-	prep_new_hugetlb_folio(h, folio, folio_nid(folio));
 
 	return folio;
 }
 
+static struct folio *only_alloc_fresh_hugetlb_folio(struct hstate *h,
+		gfp_t gfp_mask, int nid, nodemask_t *nmask,
+		nodemask_t *node_alloc_noretry)
+{
+	struct folio *folio;
+
+	folio = __alloc_fresh_hugetlb_folio(h, gfp_mask, nid, nmask,
+						node_alloc_noretry);
+	if (folio)
+		init_new_hugetlb_folio(h, folio);
+	return folio;
+}
+
 /*
- * Allocates a fresh page to the hugetlb allocator pool in the node interleaved
- * manner.
+ * Common helper to allocate a fresh hugetlb page. All specific allocators
+ * should use this function to get new hugetlb pages
+ *
+ * Note that returned page is 'frozen':  ref count of head page and all tail
+ * pages is zero.
  */
-static int alloc_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed,
-				nodemask_t *node_alloc_noretry)
+static struct folio *alloc_fresh_hugetlb_folio(struct hstate *h,
+		gfp_t gfp_mask, int nid, nodemask_t *nmask,
+		nodemask_t *node_alloc_noretry)
 {
 	struct folio *folio;
-	int nr_nodes, node;
+
+	folio = __alloc_fresh_hugetlb_folio(h, gfp_mask, nid, nmask,
+						node_alloc_noretry);
+	if (!folio)
+		return NULL;
+
+	prep_new_hugetlb_folio(h, folio, folio_nid(folio));
+	return folio;
+}
+
+static void prep_and_add_allocated_folios(struct hstate *h,
+					struct list_head *folio_list)
+{
+	unsigned long flags;
+	struct folio *folio, *tmp_f;
+
+	/* Send list for bulk vmemmap optimization processing */
+	hugetlb_vmemmap_optimize_folios(h, folio_list);
+
+	/* Add all new pool pages to free lists in one lock cycle */
+	spin_lock_irqsave(&hugetlb_lock, flags);
+	list_for_each_entry_safe(folio, tmp_f, folio_list, lru) {
+		__prep_account_new_huge_page(h, folio_nid(folio));
+		enqueue_hugetlb_folio(h, folio);
+	}
+	spin_unlock_irqrestore(&hugetlb_lock, flags);
+}
+
+/*
+ * Allocates a fresh hugetlb page in a node interleaved manner.  The page
+ * will later be added to the appropriate hugetlb pool.
+ */
+static struct folio *alloc_pool_huge_folio(struct hstate *h,
+					nodemask_t *nodes_allowed,
+					nodemask_t *node_alloc_noretry)
+{
 	gfp_t gfp_mask = htlb_alloc_mask(h) | __GFP_THISNODE;
+	int nr_nodes, node;
 
 	for_each_node_mask_to_alloc(h, nr_nodes, node, nodes_allowed) {
-		folio = alloc_fresh_hugetlb_folio(h, gfp_mask, node,
+		struct folio *folio;
+
+		folio = only_alloc_fresh_hugetlb_folio(h, gfp_mask, node,
 					nodes_allowed, node_alloc_noretry);
-		if (folio) {
-			free_huge_folio(folio); /* free it into the hugepage allocator */
-			return 1;
-		}
+		if (folio)
+			return folio;
 	}
 
-	return 0;
+	return NULL;
 }
 
 /*
@@ -2258,13 +2374,11 @@ static int alloc_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed,
  * an additional call to free the page to low level allocators.
  * Called with hugetlb_lock locked.
  */
-static struct page *remove_pool_huge_page(struct hstate *h,
-						nodemask_t *nodes_allowed,
-						 bool acct_surplus)
+static struct folio *remove_pool_hugetlb_folio(struct hstate *h,
+		nodemask_t *nodes_allowed, bool acct_surplus)
 {
 	int nr_nodes, node;
-	struct page *page = NULL;
-	struct folio *folio;
+	struct folio *folio = NULL;
 
 	lockdep_assert_held(&hugetlb_lock);
 	for_each_node_mask_to_free(h, nr_nodes, node, nodes_allowed) {
@@ -2274,15 +2388,14 @@ static struct page *remove_pool_huge_page(struct hstate *h,
 		 */
 		if ((!acct_surplus || h->surplus_huge_pages_node[node]) &&
 		    !list_empty(&h->hugepage_freelists[node])) {
-			page = list_entry(h->hugepage_freelists[node].next,
-					  struct page, lru);
-			folio = page_folio(page);
+			folio = list_entry(h->hugepage_freelists[node].next,
+					  struct folio, lru);
 			remove_hugetlb_folio(h, folio, acct_surplus);
 			break;
 		}
 	}
 
-	return page;
+	return folio;
 }
 
 /*
@@ -2350,17 +2463,23 @@ retry:
 		 * need to adjust max_huge_pages if the page is not freed.
 		 * Attempt to allocate vmemmmap here so that we can take
 		 * appropriate action on failure.
+		 *
+		 * The folio_test_hugetlb check here is because
+		 * remove_hugetlb_folio will clear hugetlb folio flag for
+		 * non-vmemmap optimized hugetlb folios.
 		 */
-		rc = hugetlb_vmemmap_restore(h, &folio->page);
-		if (!rc) {
-			update_and_free_hugetlb_folio(h, folio, false);
-		} else {
-			spin_lock_irq(&hugetlb_lock);
-			add_hugetlb_folio(h, folio, false);
-			h->max_huge_pages++;
-			spin_unlock_irq(&hugetlb_lock);
-		}
+		if (folio_test_hugetlb(folio)) {
+			rc = hugetlb_vmemmap_restore_folio(h, folio);
+			if (rc) {
+				spin_lock_irq(&hugetlb_lock);
+				add_hugetlb_folio(h, folio, false);
+				h->max_huge_pages++;
+				goto out;
+			}
+		} else
+			rc = 0;
 
+		update_and_free_hugetlb_folio(h, folio, false);
 		return rc;
 	}
 out:
@@ -2518,24 +2637,6 @@ struct folio *alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid,
 	return alloc_migrate_hugetlb_folio(h, gfp_mask, preferred_nid, nmask);
 }
 
-/* mempolicy aware migration callback */
-struct folio *alloc_hugetlb_folio_vma(struct hstate *h, struct vm_area_struct *vma,
-		unsigned long address)
-{
-	struct mempolicy *mpol;
-	nodemask_t *nodemask;
-	struct folio *folio;
-	gfp_t gfp_mask;
-	int node;
-
-	gfp_mask = htlb_alloc_mask(h);
-	node = huge_node(vma, address, gfp_mask, &mpol, &nodemask);
-	folio = alloc_hugetlb_folio_nodemask(h, node, nodemask, gfp_mask);
-	mpol_cond_put(mpol);
-
-	return folio;
-}
-
 /*
  * Increase the hugetlb pool such that it can accommodate a reservation
  * of size 'delta'.
@@ -2636,7 +2737,6 @@ static void return_unused_surplus_pages(struct hstate *h,
 					unsigned long unused_resv_pages)
 {
 	unsigned long nr_pages;
-	struct page *page;
 	LIST_HEAD(page_list);
 
 	lockdep_assert_held(&hugetlb_lock);
@@ -2657,15 +2757,17 @@ static void return_unused_surplus_pages(struct hstate *h,
 	 * evenly across all nodes with memory. Iterate across these nodes
 	 * until we can no longer free unreserved surplus pages. This occurs
 	 * when the nodes with surplus pages have no free pages.
-	 * remove_pool_huge_page() will balance the freed pages across the
+	 * remove_pool_hugetlb_folio() will balance the freed pages across the
 	 * on-line nodes with memory and will handle the hstate accounting.
 	 */
 	while (nr_pages--) {
-		page = remove_pool_huge_page(h, &node_states[N_MEMORY], 1);
-		if (!page)
+		struct folio *folio;
+
+		folio = remove_pool_hugetlb_folio(h, &node_states[N_MEMORY], 1);
+		if (!folio)
 			goto out;
 
-		list_add(&page->lru, &page_list);
+		list_add(&folio->lru, &page_list);
 	}
 
 out:
@@ -3047,11 +3149,20 @@ struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma,
 	struct hugepage_subpool *spool = subpool_vma(vma);
 	struct hstate *h = hstate_vma(vma);
 	struct folio *folio;
-	long map_chg, map_commit;
+	long map_chg, map_commit, nr_pages = pages_per_huge_page(h);
 	long gbl_chg;
-	int ret, idx;
+	int memcg_charge_ret, ret, idx;
 	struct hugetlb_cgroup *h_cg = NULL;
+	struct mem_cgroup *memcg;
 	bool deferred_reserve;
+	gfp_t gfp = htlb_alloc_mask(h) | __GFP_RETRY_MAYFAIL;
+
+	memcg = get_mem_cgroup_from_current();
+	memcg_charge_ret = mem_cgroup_hugetlb_try_charge(memcg, gfp, nr_pages);
+	if (memcg_charge_ret == -ENOMEM) {
+		mem_cgroup_put(memcg);
+		return ERR_PTR(-ENOMEM);
+	}
 
 	idx = hstate_index(h);
 	/*
@@ -3060,8 +3171,12 @@ struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma,
 	 * code of zero indicates a reservation exists (no change).
 	 */
 	map_chg = gbl_chg = vma_needs_reservation(h, vma, addr);
-	if (map_chg < 0)
+	if (map_chg < 0) {
+		if (!memcg_charge_ret)
+			mem_cgroup_cancel_charge(memcg, nr_pages);
+		mem_cgroup_put(memcg);
 		return ERR_PTR(-ENOMEM);
+	}
 
 	/*
 	 * Processes that did not create the mapping will have no
@@ -3072,10 +3187,8 @@ struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma,
 	 */
 	if (map_chg || avoid_reserve) {
 		gbl_chg = hugepage_subpool_get_pages(spool, 1);
-		if (gbl_chg < 0) {
-			vma_end_reservation(h, vma, addr);
-			return ERR_PTR(-ENOSPC);
-		}
+		if (gbl_chg < 0)
+			goto out_end_reservation;
 
 		/*
 		 * Even though there was no reservation in the region/reserve
@@ -3157,6 +3270,11 @@ struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma,
 			hugetlb_cgroup_uncharge_folio_rsvd(hstate_index(h),
 					pages_per_huge_page(h), folio);
 	}
+
+	if (!memcg_charge_ret)
+		mem_cgroup_commit_charge(folio, memcg);
+	mem_cgroup_put(memcg);
+
 	return folio;
 
 out_uncharge_cgroup:
@@ -3168,7 +3286,11 @@ out_uncharge_cgroup_reservation:
 out_subpool_put:
 	if (map_chg || avoid_reserve)
 		hugepage_subpool_put_pages(spool, 1);
+out_end_reservation:
 	vma_end_reservation(h, vma, addr);
+	if (!memcg_charge_ret)
+		mem_cgroup_cancel_charge(memcg, nr_pages);
+	mem_cgroup_put(memcg);
 	return ERR_PTR(-ENOSPC);
 }
 
@@ -3203,6 +3325,16 @@ int __alloc_bootmem_huge_page(struct hstate *h, int nid)
 	}
 
 found:
+
+	/*
+	 * Only initialize the head struct page in memmap_init_reserved_pages,
+	 * rest of the struct pages will be initialized by the HugeTLB
+	 * subsystem itself.
+	 * The head struct page is used to get folio information by the HugeTLB
+	 * subsystem like zone id and node id.
+	 */
+	memblock_reserved_mark_noinit(virt_to_phys((void *)m + PAGE_SIZE),
+		huge_page_size(h) - PAGE_SIZE);
 	/* Put them into a private list first because mem_map is not up yet */
 	INIT_LIST_HEAD(&m->list);
 	list_add(&m->list, &huge_boot_pages);
@@ -3210,29 +3342,102 @@ found:
 	return 1;
 }
 
+/* Initialize [start_page:end_page_number] tail struct pages of a hugepage */
+static void __init hugetlb_folio_init_tail_vmemmap(struct folio *folio,
+					unsigned long start_page_number,
+					unsigned long end_page_number)
+{
+	enum zone_type zone = zone_idx(folio_zone(folio));
+	int nid = folio_nid(folio);
+	unsigned long head_pfn = folio_pfn(folio);
+	unsigned long pfn, end_pfn = head_pfn + end_page_number;
+	int ret;
+
+	for (pfn = head_pfn + start_page_number; pfn < end_pfn; pfn++) {
+		struct page *page = pfn_to_page(pfn);
+
+		__init_single_page(page, pfn, zone, nid);
+		prep_compound_tail((struct page *)folio, pfn - head_pfn);
+		ret = page_ref_freeze(page, 1);
+		VM_BUG_ON(!ret);
+	}
+}
+
+static void __init hugetlb_folio_init_vmemmap(struct folio *folio,
+					      struct hstate *h,
+					      unsigned long nr_pages)
+{
+	int ret;
+
+	/* Prepare folio head */
+	__folio_clear_reserved(folio);
+	__folio_set_head(folio);
+	ret = folio_ref_freeze(folio, 1);
+	VM_BUG_ON(!ret);
+	/* Initialize the necessary tail struct pages */
+	hugetlb_folio_init_tail_vmemmap(folio, 1, nr_pages);
+	prep_compound_head((struct page *)folio, huge_page_order(h));
+}
+
+static void __init prep_and_add_bootmem_folios(struct hstate *h,
+					struct list_head *folio_list)
+{
+	unsigned long flags;
+	struct folio *folio, *tmp_f;
+
+	/* Send list for bulk vmemmap optimization processing */
+	hugetlb_vmemmap_optimize_folios(h, folio_list);
+
+	/* Add all new pool pages to free lists in one lock cycle */
+	spin_lock_irqsave(&hugetlb_lock, flags);
+	list_for_each_entry_safe(folio, tmp_f, folio_list, lru) {
+		if (!folio_test_hugetlb_vmemmap_optimized(folio)) {
+			/*
+			 * If HVO fails, initialize all tail struct pages
+			 * We do not worry about potential long lock hold
+			 * time as this is early in boot and there should
+			 * be no contention.
+			 */
+			hugetlb_folio_init_tail_vmemmap(folio,
+					HUGETLB_VMEMMAP_RESERVE_PAGES,
+					pages_per_huge_page(h));
+		}
+		__prep_account_new_huge_page(h, folio_nid(folio));
+		enqueue_hugetlb_folio(h, folio);
+	}
+	spin_unlock_irqrestore(&hugetlb_lock, flags);
+}
+
 /*
  * Put bootmem huge pages into the standard lists after mem_map is up.
  * Note: This only applies to gigantic (order > MAX_ORDER) pages.
  */
 static void __init gather_bootmem_prealloc(void)
 {
+	LIST_HEAD(folio_list);
 	struct huge_bootmem_page *m;
+	struct hstate *h = NULL, *prev_h = NULL;
 
 	list_for_each_entry(m, &huge_boot_pages, list) {
 		struct page *page = virt_to_page(m);
-		struct folio *folio = page_folio(page);
-		struct hstate *h = m->hstate;
+		struct folio *folio = (void *)page;
+
+		h = m->hstate;
+		/*
+		 * It is possible to have multiple huge page sizes (hstates)
+		 * in this list.  If so, process each size separately.
+		 */
+		if (h != prev_h && prev_h != NULL)
+			prep_and_add_bootmem_folios(prev_h, &folio_list);
+		prev_h = h;
 
 		VM_BUG_ON(!hstate_is_gigantic(h));
 		WARN_ON(folio_ref_count(folio) != 1);
-		if (prep_compound_gigantic_folio(folio, huge_page_order(h))) {
-			WARN_ON(folio_test_reserved(folio));
-			prep_new_hugetlb_folio(h, folio, folio_nid(folio));
-			free_huge_folio(folio); /* add to the hugepage allocator */
-		} else {
-			/* VERY unlikely inflated ref count on a tail page */
-			free_gigantic_folio(folio, huge_page_order(h));
-		}
+
+		hugetlb_folio_init_vmemmap(folio, h,
+					   HUGETLB_VMEMMAP_RESERVE_PAGES);
+		init_new_hugetlb_folio(h, folio);
+		list_add(&folio->lru, &folio_list);
 
 		/*
 		 * We need to restore the 'stolen' pages to totalram_pages
@@ -3242,7 +3447,10 @@ static void __init gather_bootmem_prealloc(void)
 		adjust_managed_page_count(page, pages_per_huge_page(h));
 		cond_resched();
 	}
+
+	prep_and_add_bootmem_folios(h, &folio_list);
 }
+
 static void __init hugetlb_hstate_alloc_pages_onenode(struct hstate *h, int nid)
 {
 	unsigned long i;
@@ -3274,9 +3482,22 @@ static void __init hugetlb_hstate_alloc_pages_onenode(struct hstate *h, int nid)
 	h->max_huge_pages_node[nid] = i;
 }
 
+/*
+ * NOTE: this routine is called in different contexts for gigantic and
+ * non-gigantic pages.
+ * - For gigantic pages, this is called early in the boot process and
+ *   pages are allocated from memblock allocated or something similar.
+ *   Gigantic pages are actually added to pools later with the routine
+ *   gather_bootmem_prealloc.
+ * - For non-gigantic pages, this is called later in the boot process after
+ *   all of mm is up and functional.  Pages are allocated from buddy and
+ *   then added to hugetlb pools.
+ */
 static void __init hugetlb_hstate_alloc_pages(struct hstate *h)
 {
 	unsigned long i;
+	struct folio *folio;
+	LIST_HEAD(folio_list);
 	nodemask_t *node_alloc_noretry;
 	bool node_specific_alloc = false;
 
@@ -3318,14 +3539,25 @@ static void __init hugetlb_hstate_alloc_pages(struct hstate *h)
 
 	for (i = 0; i < h->max_huge_pages; ++i) {
 		if (hstate_is_gigantic(h)) {
+			/*
+			 * gigantic pages not added to list as they are not
+			 * added to pools now.
+			 */
 			if (!alloc_bootmem_huge_page(h, NUMA_NO_NODE))
 				break;
-		} else if (!alloc_pool_huge_page(h,
-					 &node_states[N_MEMORY],
-					 node_alloc_noretry))
-			break;
+		} else {
+			folio = alloc_pool_huge_folio(h, &node_states[N_MEMORY],
+							node_alloc_noretry);
+			if (!folio)
+				break;
+			list_add(&folio->lru, &folio_list);
+		}
 		cond_resched();
 	}
+
+	/* list will be empty if hstate_is_gigantic */
+	prep_and_add_allocated_folios(h, &folio_list);
+
 	if (i < h->max_huge_pages) {
 		char buf[32];
 
@@ -3398,15 +3630,15 @@ static void try_to_free_low(struct hstate *h, unsigned long count,
 	 * Collect pages to be freed on a list, and free after dropping lock
 	 */
 	for_each_node_mask(i, *nodes_allowed) {
-		struct page *page, *next;
+		struct folio *folio, *next;
 		struct list_head *freel = &h->hugepage_freelists[i];
-		list_for_each_entry_safe(page, next, freel, lru) {
+		list_for_each_entry_safe(folio, next, freel, lru) {
 			if (count >= h->nr_huge_pages)
 				goto out;
-			if (PageHighMem(page))
+			if (folio_test_highmem(folio))
 				continue;
-			remove_hugetlb_folio(h, page_folio(page), false);
-			list_add(&page->lru, &page_list);
+			remove_hugetlb_folio(h, folio, false);
+			list_add(&folio->lru, &page_list);
 		}
 	}
 
@@ -3459,8 +3691,9 @@ found:
 static int set_max_huge_pages(struct hstate *h, unsigned long count, int nid,
 			      nodemask_t *nodes_allowed)
 {
-	unsigned long min_count, ret;
-	struct page *page;
+	unsigned long min_count;
+	unsigned long allocated;
+	struct folio *folio;
 	LIST_HEAD(page_list);
 	NODEMASK_ALLOC(nodemask_t, node_alloc_noretry, GFP_KERNEL);
 
@@ -3491,7 +3724,9 @@ static int set_max_huge_pages(struct hstate *h, unsigned long count, int nid,
 	if (nid != NUMA_NO_NODE) {
 		unsigned long old_count = count;
 
-		count += h->nr_huge_pages - h->nr_huge_pages_node[nid];
+		count += persistent_huge_pages(h) -
+			 (h->nr_huge_pages_node[nid] -
+			  h->surplus_huge_pages_node[nid]);
 		/*
 		 * User may have specified a large count value which caused the
 		 * above calculation to overflow.  In this case, they wanted
@@ -3535,7 +3770,8 @@ static int set_max_huge_pages(struct hstate *h, unsigned long count, int nid,
 			break;
 	}
 
-	while (count > persistent_huge_pages(h)) {
+	allocated = 0;
+	while (count > (persistent_huge_pages(h) + allocated)) {
 		/*
 		 * If this allocation races such that we no longer need the
 		 * page, free_huge_folio will handle it by freeing the page
@@ -3546,15 +3782,32 @@ static int set_max_huge_pages(struct hstate *h, unsigned long count, int nid,
 		/* yield cpu to avoid soft lockup */
 		cond_resched();
 
-		ret = alloc_pool_huge_page(h, nodes_allowed,
+		folio = alloc_pool_huge_folio(h, nodes_allowed,
 						node_alloc_noretry);
-		spin_lock_irq(&hugetlb_lock);
-		if (!ret)
+		if (!folio) {
+			prep_and_add_allocated_folios(h, &page_list);
+			spin_lock_irq(&hugetlb_lock);
 			goto out;
+		}
+
+		list_add(&folio->lru, &page_list);
+		allocated++;
 
 		/* Bail for signals. Probably ctrl-c from user */
-		if (signal_pending(current))
+		if (signal_pending(current)) {
+			prep_and_add_allocated_folios(h, &page_list);
+			spin_lock_irq(&hugetlb_lock);
 			goto out;
+		}
+
+		spin_lock_irq(&hugetlb_lock);
+	}
+
+	/* Add allocated pages to the pool */
+	if (!list_empty(&page_list)) {
+		spin_unlock_irq(&hugetlb_lock);
+		prep_and_add_allocated_folios(h, &page_list);
+		spin_lock_irq(&hugetlb_lock);
 	}
 
 	/*
@@ -3580,11 +3833,11 @@ static int set_max_huge_pages(struct hstate *h, unsigned long count, int nid,
 	 * Collect pages to be removed on list without dropping lock
 	 */
 	while (min_count < persistent_huge_pages(h)) {
-		page = remove_pool_huge_page(h, nodes_allowed, 0);
-		if (!page)
+		folio = remove_pool_hugetlb_folio(h, nodes_allowed, 0);
+		if (!folio)
 			break;
 
-		list_add(&page->lru, &page_list);
+		list_add(&folio->lru, &page_list);
 	}
 	/* free the pages after dropping lock */
 	spin_unlock_irq(&hugetlb_lock);
@@ -3619,13 +3872,21 @@ static int demote_free_hugetlb_folio(struct hstate *h, struct folio *folio)
 	remove_hugetlb_folio_for_demote(h, folio, false);
 	spin_unlock_irq(&hugetlb_lock);
 
-	rc = hugetlb_vmemmap_restore(h, &folio->page);
-	if (rc) {
-		/* Allocation of vmemmmap failed, we can not demote folio */
-		spin_lock_irq(&hugetlb_lock);
-		folio_ref_unfreeze(folio, 1);
-		add_hugetlb_folio(h, folio, false);
-		return rc;
+	/*
+	 * If vmemmap already existed for folio, the remove routine above would
+	 * have cleared the hugetlb folio flag.  Hence the folio is technically
+	 * no longer a hugetlb folio.  hugetlb_vmemmap_restore_folio can only be
+	 * passed hugetlb folios and will BUG otherwise.
+	 */
+	if (folio_test_hugetlb(folio)) {
+		rc = hugetlb_vmemmap_restore_folio(h, folio);
+		if (rc) {
+			/* Allocation of vmemmmap failed, we can not demote folio */
+			spin_lock_irq(&hugetlb_lock);
+			folio_ref_unfreeze(folio, 1);
+			add_hugetlb_folio(h, folio, false);
+			return rc;
+		}
 	}
 
 	/*
@@ -4321,7 +4582,7 @@ void __init hugetlb_add_hstate(unsigned int order)
 		return;
 	}
 	BUG_ON(hugetlb_max_hstate >= HUGE_MAX_HSTATE);
-	BUG_ON(order == 0);
+	BUG_ON(order < order_base_2(__NR_USED_SUBPAGE));
 	h = &hstates[hugetlb_max_hstate++];
 	mutex_init(&h->resize_lock);
 	h->order = order;
@@ -5004,7 +5265,7 @@ bool is_hugetlb_entry_migration(pte_t pte)
 		return false;
 }
 
-static bool is_hugetlb_entry_hwpoisoned(pte_t pte)
+bool is_hugetlb_entry_hwpoisoned(pte_t pte)
 {
 	swp_entry_t swp;
 
@@ -5612,8 +5873,10 @@ retry_avoidcopy:
 	 * owner and can reuse this page.
 	 */
 	if (folio_mapcount(old_folio) == 1 && folio_test_anon(old_folio)) {
-		if (!PageAnonExclusive(&old_folio->page))
-			page_move_anon_rmap(&old_folio->page, vma);
+		if (!PageAnonExclusive(&old_folio->page)) {
+			folio_move_anon_rmap(old_folio, vma);
+			SetPageAnonExclusive(&old_folio->page);
+		}
 		if (likely(!unshare))
 			set_huge_ptep_writable(vma, haddr, ptep);
 
@@ -5759,7 +6022,7 @@ static bool hugetlbfs_pagecache_present(struct hstate *h,
 			struct vm_area_struct *vma, unsigned long address)
 {
 	struct address_space *mapping = vma->vm_file->f_mapping;
-	pgoff_t idx = vma_hugecache_offset(h, vma, address);
+	pgoff_t idx = linear_page_index(vma, address);
 	struct folio *folio;
 
 	folio = filemap_get_folio(mapping, idx);
@@ -5776,6 +6039,7 @@ int hugetlb_add_to_page_cache(struct folio *folio, struct address_space *mapping
 	struct hstate *h = hstate_inode(inode);
 	int err;
 
+	idx <<= huge_page_order(h);
 	__folio_set_locked(folio);
 	err = __filemap_add_folio(mapping, folio, idx, GFP_KERNEL, NULL);
 
@@ -5883,7 +6147,7 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm,
 	 * before we get page_table_lock.
 	 */
 	new_folio = false;
-	folio = filemap_lock_folio(mapping, idx);
+	folio = filemap_lock_hugetlb_folio(h, mapping, idx);
 	if (IS_ERR(folio)) {
 		size = i_size_read(mapping->host) >> huge_page_shift(h);
 		if (idx >= size)
@@ -6192,7 +6456,7 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 		/* Just decrements count, does not deallocate */
 		vma_end_reservation(h, vma, haddr);
 
-		pagecache_folio = filemap_lock_folio(mapping, idx);
+		pagecache_folio = filemap_lock_hugetlb_folio(h, mapping, idx);
 		if (IS_ERR(pagecache_folio))
 			pagecache_folio = NULL;
 	}
@@ -6206,21 +6470,28 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	/* Handle userfault-wp first, before trying to lock more pages */
 	if (userfaultfd_wp(vma) && huge_pte_uffd_wp(huge_ptep_get(ptep)) &&
 	    (flags & FAULT_FLAG_WRITE) && !huge_pte_write(entry)) {
-		struct vm_fault vmf = {
-			.vma = vma,
-			.address = haddr,
-			.real_address = address,
-			.flags = flags,
-		};
+		if (!userfaultfd_wp_async(vma)) {
+			struct vm_fault vmf = {
+				.vma = vma,
+				.address = haddr,
+				.real_address = address,
+				.flags = flags,
+			};
 
-		spin_unlock(ptl);
-		if (pagecache_folio) {
-			folio_unlock(pagecache_folio);
-			folio_put(pagecache_folio);
+			spin_unlock(ptl);
+			if (pagecache_folio) {
+				folio_unlock(pagecache_folio);
+				folio_put(pagecache_folio);
+			}
+			hugetlb_vma_unlock_read(vma);
+			mutex_unlock(&hugetlb_fault_mutex_table[hash]);
+			return handle_userfault(&vmf, VM_UFFD_WP);
 		}
-		hugetlb_vma_unlock_read(vma);
-		mutex_unlock(&hugetlb_fault_mutex_table[hash]);
-		return handle_userfault(&vmf, VM_UFFD_WP);
+
+		entry = huge_pte_clear_uffd_wp(entry);
+		set_huge_pte_at(mm, haddr, ptep, entry,
+				huge_page_size(hstate_vma(vma)));
+		/* Fallthrough to CoW */
 	}
 
 	/*
@@ -6278,6 +6549,26 @@ out_mutex:
 
 #ifdef CONFIG_USERFAULTFD
 /*
+ * Can probably be eliminated, but still used by hugetlb_mfill_atomic_pte().
+ */
+static struct folio *alloc_hugetlb_folio_vma(struct hstate *h,
+		struct vm_area_struct *vma, unsigned long address)
+{
+	struct mempolicy *mpol;
+	nodemask_t *nodemask;
+	struct folio *folio;
+	gfp_t gfp_mask;
+	int node;
+
+	gfp_mask = htlb_alloc_mask(h);
+	node = huge_node(vma, address, gfp_mask, &mpol, &nodemask);
+	folio = alloc_hugetlb_folio_nodemask(h, node, nodemask, gfp_mask);
+	mpol_cond_put(mpol);
+
+	return folio;
+}
+
+/*
  * Used by userfaultfd UFFDIO_* ioctls. Based on userfaultfd's mfill_atomic_pte
  * with modifications for hugetlb pages.
  */
@@ -6325,7 +6616,7 @@ int hugetlb_mfill_atomic_pte(pte_t *dst_pte,
 
 	if (is_continue) {
 		ret = -EFAULT;
-		folio = filemap_lock_folio(mapping, idx);
+		folio = filemap_lock_hugetlb_folio(h, mapping, idx);
 		if (IS_ERR(folio))
 			goto out;
 		folio_in_pagecache = true;