1 files changed, 82 insertions, 55 deletions

diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 62408047e8d7..20336cb3c040 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -108,16 +108,6 @@ static inline void hugetlb_drop_vma_policy(struct vm_area_struct *vma)
 }
 #endif
 
-static void huge_pagevec_release(struct pagevec *pvec)
-{
-	int i;
-
-	for (i = 0; i < pagevec_count(pvec); ++i)
-		put_page(pvec->pages[i]);
-
-	pagevec_reinit(pvec);
-}
-
 /*
  * Mask used when checking the page offset value passed in via system
  * calls.  This value will be converted to a loff_t which is signed.
@@ -480,25 +470,19 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart,
 	struct address_space *mapping = &inode->i_data;
 	const pgoff_t start = lstart >> huge_page_shift(h);
 	const pgoff_t end = lend >> huge_page_shift(h);
-	struct pagevec pvec;
+	struct folio_batch fbatch;
 	pgoff_t next, index;
 	int i, freed = 0;
 	bool truncate_op = (lend == LLONG_MAX);
 
-	pagevec_init(&pvec);
+	folio_batch_init(&fbatch);
 	next = start;
-	while (next < end) {
-		/*
-		 * When no more pages are found, we are done.
-		 */
-		if (!pagevec_lookup_range(&pvec, mapping, &next, end - 1))
-			break;
-
-		for (i = 0; i < pagevec_count(&pvec); ++i) {
-			struct page *page = pvec.pages[i];
+	while (filemap_get_folios(mapping, &next, end - 1, &fbatch)) {
+		for (i = 0; i < folio_batch_count(&fbatch); ++i) {
+			struct folio *folio = fbatch.folios[i];
 			u32 hash = 0;
 
-			index = page->index;
+			index = folio->index;
 			if (!truncate_op) {
 				/*
 				 * Only need to hold the fault mutex in the
@@ -511,15 +495,15 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart,
 			}
 
 			/*
-			 * If page is mapped, it was faulted in after being
+			 * If folio is mapped, it was faulted in after being
 			 * unmapped in caller.  Unmap (again) now after taking
 			 * the fault mutex.  The mutex will prevent faults
-			 * until we finish removing the page.
+			 * until we finish removing the folio.
 			 *
 			 * This race can only happen in the hole punch case.
 			 * Getting here in a truncate operation is a bug.
 			 */
-			if (unlikely(page_mapped(page))) {
+			if (unlikely(folio_mapped(folio))) {
 				BUG_ON(truncate_op);
 
 				mutex_unlock(&hugetlb_fault_mutex_table[hash]);
@@ -532,7 +516,7 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart,
 				i_mmap_unlock_write(mapping);
 			}
 
-			lock_page(page);
+			folio_lock(folio);
 			/*
 			 * We must free the huge page and remove from page
 			 * cache (remove_huge_page) BEFORE removing the
@@ -542,8 +526,8 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart,
 			 * the subpool and global reserve usage count can need
 			 * to be adjusted.
 			 */
-			VM_BUG_ON(HPageRestoreReserve(page));
-			remove_huge_page(page);
+			VM_BUG_ON(HPageRestoreReserve(&folio->page));
+			remove_huge_page(&folio->page);
 			freed++;
 			if (!truncate_op) {
 				if (unlikely(hugetlb_unreserve_pages(inode,
@@ -551,11 +535,11 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart,
 					hugetlb_fix_reserve_counts(inode);
 			}
 
-			unlock_page(page);
+			folio_unlock(folio);
 			if (!truncate_op)
 				mutex_unlock(&hugetlb_fault_mutex_table[hash]);
 		}
-		huge_pagevec_release(&pvec);
+		folio_batch_release(&fbatch);
 		cond_resched();
 	}
 
@@ -600,41 +584,79 @@ static void hugetlb_vmtruncate(struct inode *inode, loff_t offset)
 	remove_inode_hugepages(inode, offset, LLONG_MAX);
 }
 
+static void hugetlbfs_zero_partial_page(struct hstate *h,
+					struct address_space *mapping,
+					loff_t start,
+					loff_t end)
+{
+	pgoff_t idx = start >> huge_page_shift(h);
+	struct folio *folio;
+
+	folio = filemap_lock_folio(mapping, idx);
+	if (!folio)
+		return;
+
+	start = start & ~huge_page_mask(h);
+	end = end & ~huge_page_mask(h);
+	if (!end)
+		end = huge_page_size(h);
+
+	folio_zero_segment(folio, (size_t)start, (size_t)end);
+
+	folio_unlock(folio);
+	folio_put(folio);
+}
+
 static long hugetlbfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
 {
+	struct hugetlbfs_inode_info *info = HUGETLBFS_I(inode);
+	struct address_space *mapping = inode->i_mapping;
 	struct hstate *h = hstate_inode(inode);
 	loff_t hpage_size = huge_page_size(h);
 	loff_t hole_start, hole_end;
 
 	/*
-	 * For hole punch round up the beginning offset of the hole and
-	 * round down the end.
+	 * hole_start and hole_end indicate the full pages within the hole.
 	 */
 	hole_start = round_up(offset, hpage_size);
 	hole_end = round_down(offset + len, hpage_size);
 
-	if (hole_end > hole_start) {
-		struct address_space *mapping = inode->i_mapping;
-		struct hugetlbfs_inode_info *info = HUGETLBFS_I(inode);
+	inode_lock(inode);
 
-		inode_lock(inode);
+	/* protected by i_rwsem */
+	if (info->seals & (F_SEAL_WRITE | F_SEAL_FUTURE_WRITE)) {
+		inode_unlock(inode);
+		return -EPERM;
+	}
 
-		/* protected by i_rwsem */
-		if (info->seals & (F_SEAL_WRITE | F_SEAL_FUTURE_WRITE)) {
-			inode_unlock(inode);
-			return -EPERM;
-		}
+	i_mmap_lock_write(mapping);
+
+	/* If range starts before first full page, zero partial page. */
+	if (offset < hole_start)
+		hugetlbfs_zero_partial_page(h, mapping,
+				offset, min(offset + len, hole_start));
 
-		i_mmap_lock_write(mapping);
+	/* Unmap users of full pages in the hole. */
+	if (hole_end > hole_start) {
 		if (!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root))
 			hugetlb_vmdelete_list(&mapping->i_mmap,
 					      hole_start >> PAGE_SHIFT,
 					      hole_end >> PAGE_SHIFT, 0);
-		i_mmap_unlock_write(mapping);
-		remove_inode_hugepages(inode, hole_start, hole_end);
-		inode_unlock(inode);
 	}
 
+	/* If range extends beyond last full page, zero partial page. */
+	if ((offset + len) > hole_end && (offset + len) > hole_start)
+		hugetlbfs_zero_partial_page(h, mapping,
+				hole_end, offset + len);
+
+	i_mmap_unlock_write(mapping);
+
+	/* Remove full pages from the file. */
+	if (hole_end > hole_start)
+		remove_inode_hugepages(inode, hole_start, hole_end);
+
+	inode_unlock(inode);
+
 	return 0;
 }
 
@@ -759,7 +781,7 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset,
 
 		SetHPageMigratable(page);
 		/*
-		 * unlock_page because locked by add_to_page_cache()
+		 * unlock_page because locked by huge_add_to_page_cache()
 		 * put_page() due to reference from alloc_huge_page()
 		 */
 		unlock_page(page);
@@ -970,28 +992,33 @@ static int hugetlbfs_symlink(struct user_namespace *mnt_userns,
 	return error;
 }
 
-static int hugetlbfs_migrate_page(struct address_space *mapping,
-				struct page *newpage, struct page *page,
+#ifdef CONFIG_MIGRATION
+static int hugetlbfs_migrate_folio(struct address_space *mapping,
+				struct folio *dst, struct folio *src,
 				enum migrate_mode mode)
 {
 	int rc;
 
-	rc = migrate_huge_page_move_mapping(mapping, newpage, page);
+	rc = migrate_huge_page_move_mapping(mapping, dst, src);
 	if (rc != MIGRATEPAGE_SUCCESS)
 		return rc;
 
-	if (hugetlb_page_subpool(page)) {
-		hugetlb_set_page_subpool(newpage, hugetlb_page_subpool(page));
-		hugetlb_set_page_subpool(page, NULL);
+	if (hugetlb_page_subpool(&src->page)) {
+		hugetlb_set_page_subpool(&dst->page,
+					hugetlb_page_subpool(&src->page));
+		hugetlb_set_page_subpool(&src->page, NULL);
 	}
 
 	if (mode != MIGRATE_SYNC_NO_COPY)
-		migrate_page_copy(newpage, page);
+		folio_migrate_copy(dst, src);
 	else
-		migrate_page_states(newpage, page);
+		folio_migrate_flags(dst, src);
 
 	return MIGRATEPAGE_SUCCESS;
 }
+#else
+#define hugetlbfs_migrate_folio NULL
+#endif
 
 static int hugetlbfs_error_remove_page(struct address_space *mapping,
 				struct page *page)
@@ -1158,7 +1185,7 @@ static const struct address_space_operations hugetlbfs_aops = {
 	.write_begin	= hugetlbfs_write_begin,
 	.write_end	= hugetlbfs_write_end,
 	.dirty_folio	= noop_dirty_folio,
-	.migratepage    = hugetlbfs_migrate_page,
+	.migrate_folio  = hugetlbfs_migrate_folio,
 	.error_remove_page	= hugetlbfs_error_remove_page,
 };