1 files changed, 37 insertions, 7 deletions

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 90731e3b7e58..0b51e70e0a8b 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -328,7 +328,7 @@ static struct attribute *hugepage_attr[] = {
 	NULL,
 };
 
-static struct attribute_group hugepage_attr_group = {
+static const struct attribute_group hugepage_attr_group = {
 	.attrs = hugepage_attr,
 };
 
@@ -567,7 +567,7 @@ static int __do_huge_pmd_anonymous_page(struct vm_fault *vmf, struct page *page,
 		goto release;
 	}
 
-	clear_huge_page(page, haddr, HPAGE_PMD_NR);
+	clear_huge_page(page, vmf->address, HPAGE_PMD_NR);
 	/*
 	 * The memory barrier inside __SetPageUptodate makes sure that
 	 * clear_huge_page writes become visible before the set_pmd_at()
@@ -1240,15 +1240,29 @@ int do_huge_pmd_wp_page(struct vm_fault *vmf, pmd_t orig_pmd)
 	 * We can only reuse the page if nobody else maps the huge page or it's
 	 * part.
 	 */
-	if (page_trans_huge_mapcount(page, NULL) == 1) {
+	if (!trylock_page(page)) {
+		get_page(page);
+		spin_unlock(vmf->ptl);
+		lock_page(page);
+		spin_lock(vmf->ptl);
+		if (unlikely(!pmd_same(*vmf->pmd, orig_pmd))) {
+			unlock_page(page);
+			put_page(page);
+			goto out_unlock;
+		}
+		put_page(page);
+	}
+	if (reuse_swap_page(page, NULL)) {
 		pmd_t entry;
 		entry = pmd_mkyoung(orig_pmd);
 		entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
 		if (pmdp_set_access_flags(vma, haddr, vmf->pmd, entry,  1))
 			update_mmu_cache_pmd(vma, vmf->address, vmf->pmd);
 		ret |= VM_FAULT_WRITE;
+		unlock_page(page);
 		goto out_unlock;
 	}
+	unlock_page(page);
 	get_page(page);
 	spin_unlock(vmf->ptl);
 alloc:
@@ -1291,7 +1305,7 @@ alloc:
 	count_vm_event(THP_FAULT_ALLOC);
 
 	if (!page)
-		clear_huge_page(new_page, haddr, HPAGE_PMD_NR);
+		clear_huge_page(new_page, vmf->address, HPAGE_PMD_NR);
 	else
 		copy_user_huge_page(new_page, page, haddr, vma, HPAGE_PMD_NR);
 	__SetPageUptodate(new_page);
@@ -1510,8 +1524,15 @@ int do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t pmd)
 	}
 
 	/*
-	 * The page_table_lock above provides a memory barrier
-	 * with change_protection_range.
+	 * Since we took the NUMA fault, we must have observed the !accessible
+	 * bit. Make sure all other CPUs agree with that, to avoid them
+	 * modifying the page we're about to migrate.
+	 *
+	 * Must be done under PTL such that we'll observe the relevant
+	 * inc_tlb_flush_pending().
+	 *
+	 * We are not sure a pending tlb flush here is for a huge page
+	 * mapping or not. Hence use the tlb range variant
 	 */
 	if (mm_tlb_flush_pending(vma->vm_mm))
 		flush_tlb_range(vma, haddr, haddr + HPAGE_PMD_SIZE);
@@ -1521,6 +1542,7 @@ int do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t pmd)
 	 * and access rights restored.
 	 */
 	spin_unlock(vmf->ptl);
+
 	migrated = migrate_misplaced_transhuge_page(vma->vm_mm, vma,
 				vmf->pmd, pmd, vmf->address, page, target_nid);
 	if (migrated) {
@@ -2459,6 +2481,9 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 	VM_BUG_ON_PAGE(!PageLocked(page), page);
 	VM_BUG_ON_PAGE(!PageCompound(page), page);
 
+	if (PageWriteback(page))
+		return -EBUSY;
+
 	if (PageAnon(head)) {
 		/*
 		 * The caller does not necessarily hold an mmap_sem that would
@@ -2536,7 +2561,12 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 			__dec_node_page_state(page, NR_SHMEM_THPS);
 		spin_unlock(&pgdata->split_queue_lock);
 		__split_huge_page(page, list, flags);
-		ret = 0;
+		if (PageSwapCache(head)) {
+			swp_entry_t entry = { .val = page_private(head) };
+
+			ret = split_swap_cluster(entry);
+		} else
+			ret = 0;
 	} else {
 		if (IS_ENABLED(CONFIG_DEBUG_VM) && mapcount) {
 			pr_alert("total_mapcount: %u, page_count(): %u\n",