1 files changed, 170 insertions, 100 deletions

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index aa39534898e0..e070b8593b37 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -66,12 +66,6 @@ static bool hugetlb_cma_page(struct page *page, unsigned int order)
 #endif
 static unsigned long hugetlb_cma_size __initdata;
 
-/*
- * Minimum page order among possible hugepage sizes, set to a proper value
- * at boot time.
- */
-static unsigned int minimum_order __read_mostly = UINT_MAX;
-
 __initdata LIST_HEAD(huge_boot_pages);
 
 /* for command line parsing */
@@ -1135,7 +1129,7 @@ static struct page *dequeue_huge_page_node_exact(struct hstate *h, int nid)
 
 	lockdep_assert_held(&hugetlb_lock);
 	list_for_each_entry(page, &h->hugepage_freelists[nid], lru) {
-		if (pin && !is_pinnable_page(page))
+		if (pin && !is_longterm_pinnable_page(page))
 			continue;
 
 		if (PageHWPoison(page))
@@ -1541,7 +1535,14 @@ static void __update_and_free_page(struct hstate *h, struct page *page)
 	if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported())
 		return;
 
-	if (hugetlb_vmemmap_alloc(h, page)) {
+	/*
+	 * If we don't know which subpages are hwpoisoned, we can't free
+	 * the hugepage, so it's leaked intentionally.
+	 */
+	if (HPageRawHwpUnreliable(page))
+		return;
+
+	if (hugetlb_vmemmap_restore(h, page)) {
 		spin_lock_irq(&hugetlb_lock);
 		/*
 		 * If we cannot allocate vmemmap pages, just refuse to free the
@@ -1553,6 +1554,13 @@ static void __update_and_free_page(struct hstate *h, struct page *page)
 		return;
 	}
 
+	/*
+	 * Move PageHWPoison flag from head page to the raw error pages,
+	 * which makes any healthy subpages reusable.
+	 */
+	if (unlikely(PageHWPoison(page)))
+		hugetlb_clear_page_hwpoison(page);
+
 	for (i = 0; i < pages_per_huge_page(h);
 	     i++, subpage = mem_map_next(subpage, page, i)) {
 		subpage->flags &= ~(1 << PG_locked | 1 << PG_error |
@@ -1618,7 +1626,7 @@ static DECLARE_WORK(free_hpage_work, free_hpage_workfn);
 
 static inline void flush_free_hpage_work(struct hstate *h)
 {
-	if (hugetlb_optimize_vmemmap_pages(h))
+	if (hugetlb_vmemmap_optimizable(h))
 		flush_work(&free_hpage_work);
 }
 
@@ -1740,7 +1748,7 @@ static void __prep_account_new_huge_page(struct hstate *h, int nid)
 
 static void __prep_new_huge_page(struct hstate *h, struct page *page)
 {
-	hugetlb_vmemmap_free(h, page);
+	hugetlb_vmemmap_optimize(h, page);
 	INIT_LIST_HEAD(&page->lru);
 	set_compound_page_dtor(page, HUGETLB_PAGE_DTOR);
 	hugetlb_set_page_subpool(page, NULL);
@@ -2113,17 +2121,8 @@ retry:
 		 * Attempt to allocate vmemmmap here so that we can take
 		 * appropriate action on failure.
 		 */
-		rc = hugetlb_vmemmap_alloc(h, head);
+		rc = hugetlb_vmemmap_restore(h, head);
 		if (!rc) {
-			/*
-			 * Move PageHWPoison flag from head page to the raw
-			 * error page, which makes any subpages rather than
-			 * the error page reusable.
-			 */
-			if (PageHWPoison(head) && page != head) {
-				SetPageHWPoison(page);
-				ClearPageHWPoison(head);
-			}
 			update_and_free_page(h, head, false);
 		} else {
 			spin_lock_irq(&hugetlb_lock);
@@ -2152,11 +2151,17 @@ int dissolve_free_huge_pages(unsigned long start_pfn, unsigned long end_pfn)
 	unsigned long pfn;
 	struct page *page;
 	int rc = 0;
+	unsigned int order;
+	struct hstate *h;
 
 	if (!hugepages_supported())
 		return rc;
 
-	for (pfn = start_pfn; pfn < end_pfn; pfn += 1 << minimum_order) {
+	order = huge_page_order(&default_hstate);
+	for_each_hstate(h)
+		order = min(order, huge_page_order(h));
+
+	for (pfn = start_pfn; pfn < end_pfn; pfn += 1 << order) {
 		page = pfn_to_page(pfn);
 		rc = dissolve_free_huge_page(page);
 		if (rc)
@@ -2432,8 +2437,7 @@ static void return_unused_surplus_pages(struct hstate *h,
 	/* Uncommit the reservation */
 	h->resv_huge_pages -= unused_resv_pages;
 
-	/* Cannot return gigantic pages currently */
-	if (hstate_is_gigantic(h))
+	if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported())
 		goto out;
 
 	/*
@@ -2766,8 +2770,7 @@ retry:
 		 * Fail with -EBUSY if not possible.
 		 */
 		spin_unlock_irq(&hugetlb_lock);
-		if (!isolate_huge_page(old_page, list))
-			ret = -EBUSY;
+		ret = isolate_hugetlb(old_page, list);
 		spin_lock_irq(&hugetlb_lock);
 		goto free_new;
 	} else if (!HPageFreed(old_page)) {
@@ -2843,7 +2846,7 @@ int isolate_or_dissolve_huge_page(struct page *page, struct list_head *list)
 	if (hstate_is_gigantic(h))
 		return -ENOMEM;
 
-	if (page_count(head) && isolate_huge_page(head, list))
+	if (page_count(head) && !isolate_hugetlb(head, list))
 		ret = 0;
 	else if (!page_count(head))
 		ret = alloc_and_dissolve_huge_page(h, head, list);
@@ -3149,9 +3152,6 @@ static void __init hugetlb_init_hstates(void)
 	struct hstate *h, *h2;
 
 	for_each_hstate(h) {
-		if (minimum_order > huge_page_order(h))
-			minimum_order = huge_page_order(h);
-
 		/* oversize hugepages were init'ed in early boot */
 		if (!hstate_is_gigantic(h))
 			hugetlb_hstate_alloc_pages(h);
@@ -3176,7 +3176,6 @@ static void __init hugetlb_init_hstates(void)
 				h->demote_order = h2->order;
 		}
 	}
-	VM_BUG_ON(minimum_order == UINT_MAX);
 }
 
 static void __init report_hugepages(void)
@@ -3187,8 +3186,10 @@ static void __init report_hugepages(void)
 		char buf[32];
 
 		string_get_size(huge_page_size(h), 1, STRING_UNITS_2, buf, 32);
-		pr_info("HugeTLB registered %s page size, pre-allocated %ld pages\n",
+		pr_info("HugeTLB: registered %s page size, pre-allocated %ld pages\n",
 			buf, h->free_huge_pages);
+		pr_info("HugeTLB: %d KiB vmemmap can be freed for a %s page\n",
+			hugetlb_vmemmap_optimizable_size(h) / SZ_1K, buf);
 	}
 }
 
@@ -3426,7 +3427,7 @@ static int demote_free_huge_page(struct hstate *h, struct page *page)
 	remove_hugetlb_page_for_demote(h, page, false);
 	spin_unlock_irq(&hugetlb_lock);
 
-	rc = hugetlb_vmemmap_alloc(h, page);
+	rc = hugetlb_vmemmap_restore(h, page);
 	if (rc) {
 		/* Allocation of vmemmmap failed, we can not demote page */
 		spin_lock_irq(&hugetlb_lock);
@@ -4116,7 +4117,6 @@ void __init hugetlb_add_hstate(unsigned int order)
 	h->next_nid_to_free = first_memory_node;
 	snprintf(h->name, HSTATE_NAME_LEN, "hugepages-%lukB",
 					huge_page_size(h)/1024);
-	hugetlb_vmemmap_init(h);
 
 	parsed_hstate = h;
 }
@@ -4482,22 +4482,20 @@ int hugetlb_report_node_meminfo(char *buf, int len, int nid)
 			     nid, h->surplus_huge_pages_node[nid]);
 }
 
-void hugetlb_show_meminfo(void)
+void hugetlb_show_meminfo_node(int nid)
 {
 	struct hstate *h;
-	int nid;
 
 	if (!hugepages_supported())
 		return;
 
-	for_each_node_state(nid, N_MEMORY)
-		for_each_hstate(h)
-			pr_info("Node %d hugepages_total=%u hugepages_free=%u hugepages_surp=%u hugepages_size=%lukB\n",
-				nid,
-				h->nr_huge_pages_node[nid],
-				h->free_huge_pages_node[nid],
-				h->surplus_huge_pages_node[nid],
-				huge_page_size(h) / SZ_1K);
+	for_each_hstate(h)
+		printk("Node %d hugepages_total=%u hugepages_free=%u hugepages_surp=%u hugepages_size=%lukB\n",
+			nid,
+			h->nr_huge_pages_node[nid],
+			h->free_huge_pages_node[nid],
+			h->surplus_huge_pages_node[nid],
+			huge_page_size(h) / SZ_1K);
 }
 
 void hugetlb_report_usage(struct seq_file *m, struct mm_struct *mm)
@@ -4732,6 +4730,7 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 	unsigned long npages = pages_per_huge_page(h);
 	struct address_space *mapping = src_vma->vm_file->f_mapping;
 	struct mmu_notifier_range range;
+	unsigned long last_addr_mask;
 	int ret = 0;
 
 	if (cow) {
@@ -4751,11 +4750,14 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 		i_mmap_lock_read(mapping);
 	}
 
+	last_addr_mask = hugetlb_mask_last_page(h);
 	for (addr = src_vma->vm_start; addr < src_vma->vm_end; addr += sz) {
 		spinlock_t *src_ptl, *dst_ptl;
 		src_pte = huge_pte_offset(src, addr, sz);
-		if (!src_pte)
+		if (!src_pte) {
+			addr |= last_addr_mask;
 			continue;
+		}
 		dst_pte = huge_pte_alloc(dst, dst_vma, addr, sz);
 		if (!dst_pte) {
 			ret = -ENOMEM;
@@ -4772,8 +4774,10 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 		 * after taking the lock below.
 		 */
 		dst_entry = huge_ptep_get(dst_pte);
-		if ((dst_pte == src_pte) || !huge_pte_none(dst_entry))
+		if ((dst_pte == src_pte) || !huge_pte_none(dst_entry)) {
+			addr |= last_addr_mask;
 			continue;
+		}
 
 		dst_ptl = huge_pte_lock(h, dst, dst_pte);
 		src_ptl = huge_pte_lockptr(h, src, src_pte);
@@ -4808,12 +4812,11 @@ again:
 				entry = swp_entry_to_pte(swp_entry);
 				if (userfaultfd_wp(src_vma) && uffd_wp)
 					entry = huge_pte_mkuffd_wp(entry);
-				set_huge_swap_pte_at(src, addr, src_pte,
-						     entry, sz);
+				set_huge_pte_at(src, addr, src_pte, entry);
 			}
 			if (!userfaultfd_wp(dst_vma) && uffd_wp)
 				entry = huge_pte_clear_uffd_wp(entry);
-			set_huge_swap_pte_at(dst, addr, dst_pte, entry, sz);
+			set_huge_pte_at(dst, addr, dst_pte, entry);
 		} else if (unlikely(is_pte_marker(entry))) {
 			/*
 			 * We copy the pte marker only if the dst vma has
@@ -4880,7 +4883,7 @@ again:
 				 * table protection not changing it to point
 				 * to a new page.
 				 *
-				 * See Documentation/vm/mmu_notifier.rst
+				 * See Documentation/mm/mmu_notifier.rst
 				 */
 				huge_ptep_set_wrprotect(src, addr, src_pte);
 				entry = huge_pte_wrprotect(entry);
@@ -4939,7 +4942,7 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma,
 	unsigned long sz = huge_page_size(h);
 	struct mm_struct *mm = vma->vm_mm;
 	unsigned long old_end = old_addr + len;
-	unsigned long old_addr_copy;
+	unsigned long last_addr_mask;
 	pte_t *src_pte, *dst_pte;
 	struct mmu_notifier_range range;
 	bool shared_pmd = false;
@@ -4954,23 +4957,23 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma,
 	flush_cache_range(vma, range.start, range.end);
 
 	mmu_notifier_invalidate_range_start(&range);
+	last_addr_mask = hugetlb_mask_last_page(h);
 	/* Prevent race with file truncation */
 	i_mmap_lock_write(mapping);
 	for (; old_addr < old_end; old_addr += sz, new_addr += sz) {
 		src_pte = huge_pte_offset(mm, old_addr, sz);
-		if (!src_pte)
+		if (!src_pte) {
+			old_addr |= last_addr_mask;
+			new_addr |= last_addr_mask;
 			continue;
+		}
 		if (huge_pte_none(huge_ptep_get(src_pte)))
 			continue;
 
-		/* old_addr arg to huge_pmd_unshare() is a pointer and so the
-		 * arg may be modified. Pass a copy instead to preserve the
-		 * value in old_addr.
-		 */
-		old_addr_copy = old_addr;
-
-		if (huge_pmd_unshare(mm, vma, &old_addr_copy, src_pte)) {
+		if (huge_pmd_unshare(mm, vma, old_addr, src_pte)) {
 			shared_pmd = true;
+			old_addr |= last_addr_mask;
+			new_addr |= last_addr_mask;
 			continue;
 		}
 
@@ -5004,6 +5007,7 @@ static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct
 	struct hstate *h = hstate_vma(vma);
 	unsigned long sz = huge_page_size(h);
 	struct mmu_notifier_range range;
+	unsigned long last_addr_mask;
 	bool force_flush = false;
 
 	WARN_ON(!is_vm_hugetlb_page(vma));
@@ -5024,17 +5028,21 @@ static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct
 				end);
 	adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end);
 	mmu_notifier_invalidate_range_start(&range);
+	last_addr_mask = hugetlb_mask_last_page(h);
 	address = start;
 	for (; address < end; address += sz) {
 		ptep = huge_pte_offset(mm, address, sz);
-		if (!ptep)
+		if (!ptep) {
+			address |= last_addr_mask;
 			continue;
+		}
 
 		ptl = huge_pte_lock(h, mm, ptep);
-		if (huge_pmd_unshare(mm, vma, &address, ptep)) {
+		if (huge_pmd_unshare(mm, vma, address, ptep)) {
 			spin_unlock(ptl);
 			tlb_flush_pmd_range(tlb, address & PUD_MASK, PUD_SIZE);
 			force_flush = true;
+			address |= last_addr_mask;
 			continue;
 		}
 
@@ -5233,6 +5241,21 @@ static vm_fault_t hugetlb_wp(struct mm_struct *mm, struct vm_area_struct *vma,
 	VM_BUG_ON(unshare && (flags & FOLL_WRITE));
 	VM_BUG_ON(!unshare && !(flags & FOLL_WRITE));
 
+	/*
+	 * hugetlb does not support FOLL_FORCE-style write faults that keep the
+	 * PTE mapped R/O such as maybe_mkwrite() would do.
+	 */
+	if (WARN_ON_ONCE(!unshare && !(vma->vm_flags & VM_WRITE)))
+		return VM_FAULT_SIGSEGV;
+
+	/* Let's take out MAP_SHARED mappings first. */
+	if (vma->vm_flags & VM_MAYSHARE) {
+		if (unlikely(unshare))
+			return 0;
+		set_huge_ptep_writable(vma, haddr, ptep);
+		return 0;
+	}
+
 	pte = huge_ptep_get(ptep);
 	old_page = pte_page(pte);
 
@@ -5714,7 +5737,7 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 		 */
 		entry = huge_ptep_get(ptep);
 		if (unlikely(is_hugetlb_entry_migration(entry))) {
-			migration_entry_wait_huge(vma, mm, ptep);
+			migration_entry_wait_huge(vma, ptep);
 			return 0;
 		} else if (unlikely(is_hugetlb_entry_hwpoisoned(entry)))
 			return VM_FAULT_HWPOISON_LARGE |
@@ -5773,12 +5796,11 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	 * If we are going to COW/unshare the mapping later, we examine the
 	 * pending reservations for this page now. This will ensure that any
 	 * allocations necessary to record that reservation occur outside the
-	 * spinlock. For private mappings, we also lookup the pagecache
-	 * page now as it is used to determine if a reservation has been
-	 * consumed.
+	 * spinlock. Also lookup the pagecache page now as it is used to
+	 * determine if a reservation has been consumed.
 	 */
 	if ((flags & (FAULT_FLAG_WRITE|FAULT_FLAG_UNSHARE)) &&
-	    !huge_pte_write(entry)) {
+	    !(vma->vm_flags & VM_MAYSHARE) && !huge_pte_write(entry)) {
 		if (vma_needs_reservation(h, vma, haddr) < 0) {
 			ret = VM_FAULT_OOM;
 			goto out_mutex;
@@ -5786,9 +5808,7 @@ 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);
 
-		if (!(vma->vm_flags & VM_MAYSHARE))
-			pagecache_page = hugetlbfs_pagecache_page(h,
-								vma, haddr);
+		pagecache_page = hugetlbfs_pagecache_page(h, vma, haddr);
 	}
 
 	ptl = huge_pte_lock(h, mm, ptep);
@@ -6021,7 +6041,7 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm,
 	if (!huge_pte_none_mostly(huge_ptep_get(dst_pte)))
 		goto out_release_unlock;
 
-	if (vm_shared) {
+	if (page_in_pagecache) {
 		page_dup_file_rmap(page, true);
 	} else {
 		ClearHPageRestoreReserve(page);
@@ -6052,8 +6072,6 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm,
 
 	set_huge_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte);
 
-	(void)huge_ptep_set_access_flags(dst_vma, dst_addr, dst_pte, _dst_pte,
-					dst_vma->vm_flags & VM_WRITE);
 	hugetlb_count_add(pages_per_huge_page(h), dst_mm);
 
 	/* No need to invalidate - it was non-present before */
@@ -6305,6 +6323,7 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 	unsigned long pages = 0, psize = huge_page_size(h);
 	bool shared_pmd = false;
 	struct mmu_notifier_range range;
+	unsigned long last_addr_mask;
 	bool uffd_wp = cp_flags & MM_CP_UFFD_WP;
 	bool uffd_wp_resolve = cp_flags & MM_CP_UFFD_WP_RESOLVE;
 
@@ -6321,14 +6340,17 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 	flush_cache_range(vma, range.start, range.end);
 
 	mmu_notifier_invalidate_range_start(&range);
+	last_addr_mask = hugetlb_mask_last_page(h);
 	i_mmap_lock_write(vma->vm_file->f_mapping);
 	for (; address < end; address += psize) {
 		spinlock_t *ptl;
 		ptep = huge_pte_offset(mm, address, psize);
-		if (!ptep)
+		if (!ptep) {
+			address |= last_addr_mask;
 			continue;
+		}
 		ptl = huge_pte_lock(h, mm, ptep);
-		if (huge_pmd_unshare(mm, vma, &address, ptep)) {
+		if (huge_pmd_unshare(mm, vma, address, ptep)) {
 			/*
 			 * When uffd-wp is enabled on the vma, unshare
 			 * shouldn't happen at all.  Warn about it if it
@@ -6338,6 +6360,7 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 			pages++;
 			spin_unlock(ptl);
 			shared_pmd = true;
+			address |= last_addr_mask;
 			continue;
 		}
 		pte = huge_ptep_get(ptep);
@@ -6363,8 +6386,7 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 					newpte = pte_swp_mkuffd_wp(newpte);
 				else if (uffd_wp_resolve)
 					newpte = pte_swp_clear_uffd_wp(newpte);
-				set_huge_swap_pte_at(mm, address, ptep,
-						     newpte, psize);
+				set_huge_pte_at(mm, address, ptep, newpte);
 				pages++;
 			}
 			spin_unlock(ptl);
@@ -6415,7 +6437,7 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 	 * No need to call mmu_notifier_invalidate_range() we are downgrading
 	 * page table protection not changing it to point to a new page.
 	 *
-	 * See Documentation/vm/mmu_notifier.rst
+	 * See Documentation/mm/mmu_notifier.rst
 	 */
 	i_mmap_unlock_write(vma->vm_file->f_mapping);
 	mmu_notifier_invalidate_range_end(&range);
@@ -6761,11 +6783,11 @@ out:
  *	    0 the underlying pte page is not shared, or it is the last user
  */
 int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma,
-					unsigned long *addr, pte_t *ptep)
+					unsigned long addr, pte_t *ptep)
 {
-	pgd_t *pgd = pgd_offset(mm, *addr);
-	p4d_t *p4d = p4d_offset(pgd, *addr);
-	pud_t *pud = pud_offset(p4d, *addr);
+	pgd_t *pgd = pgd_offset(mm, addr);
+	p4d_t *p4d = p4d_offset(pgd, addr);
+	pud_t *pud = pud_offset(p4d, addr);
 
 	i_mmap_assert_write_locked(vma->vm_file->f_mapping);
 	BUG_ON(page_count(virt_to_page(ptep)) == 0);
@@ -6775,14 +6797,6 @@ int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma,
 	pud_clear(pud);
 	put_page(virt_to_page(ptep));
 	mm_dec_nr_pmds(mm);
-	/*
-	 * This update of passed address optimizes loops sequentially
-	 * processing addresses in increments of huge page size (PMD_SIZE
-	 * in this case).  By clearing the pud, a PUD_SIZE area is unmapped.
-	 * Update address to the 'last page' in the cleared area so that
-	 * calling loop can move to first page past this area.
-	 */
-	*addr |= PUD_SIZE - PMD_SIZE;
 	return 1;
 }
 
@@ -6794,7 +6808,7 @@ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma,
 }
 
 int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma,
-				unsigned long *addr, pte_t *ptep)
+				unsigned long addr, pte_t *ptep)
 {
 	return 0;
 }
@@ -6877,6 +6891,37 @@ pte_t *huge_pte_offset(struct mm_struct *mm,
 	return (pte_t *)pmd;
 }
 
+/*
+ * Return a mask that can be used to update an address to the last huge
+ * page in a page table page mapping size.  Used to skip non-present
+ * page table entries when linearly scanning address ranges.  Architectures
+ * with unique huge page to page table relationships can define their own
+ * version of this routine.
+ */
+unsigned long hugetlb_mask_last_page(struct hstate *h)
+{
+	unsigned long hp_size = huge_page_size(h);
+
+	if (hp_size == PUD_SIZE)
+		return P4D_SIZE - PUD_SIZE;
+	else if (hp_size == PMD_SIZE)
+		return PUD_SIZE - PMD_SIZE;
+	else
+		return 0UL;
+}
+
+#else
+
+/* See description above.  Architectures can provide their own version. */
+__weak unsigned long hugetlb_mask_last_page(struct hstate *h)
+{
+#ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE
+	if (huge_page_size(h) == PMD_SIZE)
+		return PUD_SIZE - PMD_SIZE;
+#endif
+	return 0UL;
+}
+
 #endif /* CONFIG_ARCH_WANT_GENERAL_HUGETLB */
 
 /*
@@ -6940,7 +6985,7 @@ retry:
 	} else {
 		if (is_hugetlb_entry_migration(pte)) {
 			spin_unlock(ptl);
-			__migration_entry_wait(mm, (pte_t *)pmd, ptl);
+			__migration_entry_wait_huge((pte_t *)pmd, ptl);
 			goto retry;
 		}
 		/*
@@ -6957,10 +7002,38 @@ struct page * __weak
 follow_huge_pud(struct mm_struct *mm, unsigned long address,
 		pud_t *pud, int flags)
 {
-	if (flags & (FOLL_GET | FOLL_PIN))
+	struct page *page = NULL;
+	spinlock_t *ptl;
+	pte_t pte;
+
+	if (WARN_ON_ONCE(flags & FOLL_PIN))
 		return NULL;
 
-	return pte_page(*(pte_t *)pud) + ((address & ~PUD_MASK) >> PAGE_SHIFT);
+retry:
+	ptl = huge_pte_lock(hstate_sizelog(PUD_SHIFT), mm, (pte_t *)pud);
+	if (!pud_huge(*pud))
+		goto out;
+	pte = huge_ptep_get((pte_t *)pud);
+	if (pte_present(pte)) {
+		page = pud_page(*pud) + ((address & ~PUD_MASK) >> PAGE_SHIFT);
+		if (WARN_ON_ONCE(!try_grab_page(page, flags))) {
+			page = NULL;
+			goto out;
+		}
+	} else {
+		if (is_hugetlb_entry_migration(pte)) {
+			spin_unlock(ptl);
+			__migration_entry_wait(mm, (pte_t *)pud, ptl);
+			goto retry;
+		}
+		/*
+		 * hwpoisoned entry is treated as no_page_table in
+		 * follow_page_mask().
+		 */
+	}
+out:
+	spin_unlock(ptl);
+	return page;
 }
 
 struct page * __weak
@@ -6972,15 +7045,15 @@ follow_huge_pgd(struct mm_struct *mm, unsigned long address, pgd_t *pgd, int fla
 	return pte_page(*(pte_t *)pgd) + ((address & ~PGDIR_MASK) >> PAGE_SHIFT);
 }
 
-bool isolate_huge_page(struct page *page, struct list_head *list)
+int isolate_hugetlb(struct page *page, struct list_head *list)
 {
-	bool ret = true;
+	int ret = 0;
 
 	spin_lock_irq(&hugetlb_lock);
 	if (!PageHeadHuge(page) ||
 	    !HPageMigratable(page) ||
 	    !get_page_unless_zero(page)) {
-		ret = false;
+		ret = -EBUSY;
 		goto unlock;
 	}
 	ClearHPageMigratable(page);
@@ -7100,21 +7173,18 @@ void hugetlb_unshare_all_pmds(struct vm_area_struct *vma)
 	mmu_notifier_invalidate_range_start(&range);
 	i_mmap_lock_write(vma->vm_file->f_mapping);
 	for (address = start; address < end; address += PUD_SIZE) {
-		unsigned long tmp = address;
-
 		ptep = huge_pte_offset(mm, address, sz);
 		if (!ptep)
 			continue;
 		ptl = huge_pte_lock(h, mm, ptep);
-		/* We don't want 'address' to be changed */
-		huge_pmd_unshare(mm, vma, &tmp, ptep);
+		huge_pmd_unshare(mm, vma, address, ptep);
 		spin_unlock(ptl);
 	}
 	flush_hugetlb_tlb_range(vma, start, end);
 	i_mmap_unlock_write(vma->vm_file->f_mapping);
 	/*
 	 * No need to call mmu_notifier_invalidate_range(), see
-	 * Documentation/vm/mmu_notifier.rst.
+	 * Documentation/mm/mmu_notifier.rst.
 	 */
 	mmu_notifier_invalidate_range_end(&range);
 }