Merge tag 'f2fs-for-6.10.rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs

Pull f2fs updates from Jaegeuk Kim:
 "In this round, we've tried to address some performance issues on zoned
  storage such as direct IO and write_hints. In addition, we've migrated
  some IO paths using folio. Meanwhile, there are multiple bug fixes in
  the compression paths, sanity check conditions, and error handlers.

  Enhancements:
   - allow direct io of pinned files for zoned storage
   - assign the write hint per stream by default
   - convert read paths and test_writeback to folio
   - avoid allocating WARM_DATA segment for direct IO

  Bug fixes:
   - fix false alarm on invalid block address
   - fix to add missing iput() in gc_data_segment()
   - fix to release node block count in error path of
     f2fs_new_node_page()
   - compress:
       - don't allow unaligned truncation on released compress inode
       - cover {reserve,release}_compress_blocks() w/ cp_rwsem lock
       - fix error path of inc_valid_block_count()
       - fix to update i_compr_blocks correctly
   - fix block migration when section is not aligned to pow2
   - don't trigger OPU on pinfile for direct IO
   - fix to do sanity check on i_xattr_nid in sanity_check_inode()
   - write missing last sum blk of file pinning section
   - clear writeback when compression failed
   - fix to adjust appropirate defragment pg_end

  As usual, there are several minor code clean-ups, and fixes to manage
  missing corner cases in the error paths"

* tag 'f2fs-for-6.10.rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (50 commits)
  f2fs: initialize last_block_in_bio variable
  f2fs: Add inline to f2fs_build_fault_attr() stub
  f2fs: fix some ambiguous comments
  f2fs: fix to add missing iput() in gc_data_segment()
  f2fs: allow dirty sections with zero valid block for checkpoint disabled
  f2fs: compress: don't allow unaligned truncation on released compress inode
  f2fs: fix to release node block count in error path of f2fs_new_node_page()
  f2fs: compress: fix to cover {reserve,release}_compress_blocks() w/ cp_rwsem lock
  f2fs: compress: fix error path of inc_valid_block_count()
  f2fs: compress: fix typo in f2fs_reserve_compress_blocks()
  f2fs: compress: fix to update i_compr_blocks correctly
  f2fs: check validation of fault attrs in f2fs_build_fault_attr()
  f2fs: fix to limit gc_pin_file_threshold
  f2fs: remove unused GC_FAILURE_PIN
  f2fs: use f2fs_{err,info}_ratelimited() for cleanup
  f2fs: fix block migration when section is not aligned to pow2
  f2fs: zone: fix to don't trigger OPU on pinfile for direct IO
  f2fs: fix to do sanity check on i_xattr_nid in sanity_check_inode()
  f2fs: fix to avoid allocating WARM_DATA segment for direct IO
  f2fs: remove redundant parameter in is_next_segment_free()
  ...

1 files changed, 132 insertions, 99 deletions

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 961e6ff77c72..b9b0debc6b3d 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -465,6 +465,8 @@ static struct bio *__bio_alloc(struct f2fs_io_info *fio, int npages)
 	} else {
 		bio->bi_end_io = f2fs_write_end_io;
 		bio->bi_private = sbi;
+		bio->bi_write_hint = f2fs_io_type_to_rw_hint(sbi,
+						fio->type, fio->temp);
 	}
 	iostat_alloc_and_bind_ctx(sbi, bio, NULL);
 
@@ -593,17 +595,20 @@ int f2fs_init_write_merge_io(struct f2fs_sb_info *sbi)
 			return -ENOMEM;
 
 		for (j = HOT; j < n; j++) {
-			init_f2fs_rwsem(&sbi->write_io[i][j].io_rwsem);
-			sbi->write_io[i][j].sbi = sbi;
-			sbi->write_io[i][j].bio = NULL;
-			spin_lock_init(&sbi->write_io[i][j].io_lock);
-			INIT_LIST_HEAD(&sbi->write_io[i][j].io_list);
-			INIT_LIST_HEAD(&sbi->write_io[i][j].bio_list);
-			init_f2fs_rwsem(&sbi->write_io[i][j].bio_list_lock);
+			struct f2fs_bio_info *io = &sbi->write_io[i][j];
+
+			init_f2fs_rwsem(&io->io_rwsem);
+			io->sbi = sbi;
+			io->bio = NULL;
+			io->last_block_in_bio = 0;
+			spin_lock_init(&io->io_lock);
+			INIT_LIST_HEAD(&io->io_list);
+			INIT_LIST_HEAD(&io->bio_list);
+			init_f2fs_rwsem(&io->bio_list_lock);
 #ifdef CONFIG_BLK_DEV_ZONED
-			init_completion(&sbi->write_io[i][j].zone_wait);
-			sbi->write_io[i][j].zone_pending_bio = NULL;
-			sbi->write_io[i][j].bi_private = NULL;
+			init_completion(&io->zone_wait);
+			io->zone_pending_bio = NULL;
+			io->bi_private = NULL;
 #endif
 		}
 	}
@@ -1507,6 +1512,25 @@ static bool f2fs_map_blocks_cached(struct inode *inode,
 	return true;
 }
 
+static bool map_is_mergeable(struct f2fs_sb_info *sbi,
+				struct f2fs_map_blocks *map,
+				block_t blkaddr, int flag, int bidx,
+				int ofs)
+{
+	if (map->m_multidev_dio && map->m_bdev != FDEV(bidx).bdev)
+		return false;
+	if (map->m_pblk != NEW_ADDR && blkaddr == (map->m_pblk + ofs))
+		return true;
+	if (map->m_pblk == NEW_ADDR && blkaddr == NEW_ADDR)
+		return true;
+	if (flag == F2FS_GET_BLOCK_PRE_DIO)
+		return true;
+	if (flag == F2FS_GET_BLOCK_DIO &&
+		map->m_pblk == NULL_ADDR && blkaddr == NULL_ADDR)
+		return true;
+	return false;
+}
+
 /*
  * f2fs_map_blocks() tries to find or build mapping relationship which
  * maps continuous logical blocks to physical blocks, and return such
@@ -1574,8 +1598,9 @@ next_block:
 	}
 
 	/* use out-place-update for direct IO under LFS mode */
-	if (map->m_may_create &&
-	    (is_hole || (f2fs_lfs_mode(sbi) && flag == F2FS_GET_BLOCK_DIO))) {
+	if (map->m_may_create && (is_hole ||
+		(flag == F2FS_GET_BLOCK_DIO && f2fs_lfs_mode(sbi) &&
+		!f2fs_is_pinned_file(inode)))) {
 		if (unlikely(f2fs_cp_error(sbi))) {
 			err = -EIO;
 			goto sync_out;
@@ -1628,6 +1653,10 @@ next_block:
 				goto sync_out;
 			}
 			break;
+		case F2FS_GET_BLOCK_DIO:
+			if (map->m_next_pgofs)
+				*map->m_next_pgofs = pgofs + 1;
+			break;
 		default:
 			/* for defragment case */
 			if (map->m_next_pgofs)
@@ -1646,19 +1675,15 @@ next_block:
 		/* reserved delalloc block should be mapped for fiemap. */
 		if (blkaddr == NEW_ADDR)
 			map->m_flags |= F2FS_MAP_DELALLOC;
-		map->m_flags |= F2FS_MAP_MAPPED;
+		if (flag != F2FS_GET_BLOCK_DIO || !is_hole)
+			map->m_flags |= F2FS_MAP_MAPPED;
 
 		map->m_pblk = blkaddr;
 		map->m_len = 1;
 
 		if (map->m_multidev_dio)
 			map->m_bdev = FDEV(bidx).bdev;
-	} else if ((map->m_pblk != NEW_ADDR &&
-			blkaddr == (map->m_pblk + ofs)) ||
-			(map->m_pblk == NEW_ADDR && blkaddr == NEW_ADDR) ||
-			flag == F2FS_GET_BLOCK_PRE_DIO) {
-		if (map->m_multidev_dio && map->m_bdev != FDEV(bidx).bdev)
-			goto sync_out;
+	} else if (map_is_mergeable(sbi, map, blkaddr, flag, bidx, ofs)) {
 		ofs++;
 		map->m_len++;
 	} else {
@@ -2042,7 +2067,7 @@ static inline loff_t f2fs_readpage_limit(struct inode *inode)
 	return i_size_read(inode);
 }
 
-static int f2fs_read_single_page(struct inode *inode, struct page *page,
+static int f2fs_read_single_page(struct inode *inode, struct folio *folio,
 					unsigned nr_pages,
 					struct f2fs_map_blocks *map,
 					struct bio **bio_ret,
@@ -2055,9 +2080,10 @@ static int f2fs_read_single_page(struct inode *inode, struct page *page,
 	sector_t last_block;
 	sector_t last_block_in_file;
 	sector_t block_nr;
+	pgoff_t index = folio_index(folio);
 	int ret = 0;
 
-	block_in_file = (sector_t)page_index(page);
+	block_in_file = (sector_t)index;
 	last_block = block_in_file + nr_pages;
 	last_block_in_file = bytes_to_blks(inode,
 			f2fs_readpage_limit(inode) + blocksize - 1);
@@ -2088,7 +2114,7 @@ static int f2fs_read_single_page(struct inode *inode, struct page *page,
 got_it:
 	if ((map->m_flags & F2FS_MAP_MAPPED)) {
 		block_nr = map->m_pblk + block_in_file - map->m_lblk;
-		SetPageMappedToDisk(page);
+		folio_set_mappedtodisk(folio);
 
 		if (!f2fs_is_valid_blkaddr(F2FS_I_SB(inode), block_nr,
 						DATA_GENERIC_ENHANCE_READ)) {
@@ -2097,15 +2123,15 @@ got_it:
 		}
 	} else {
 zero_out:
-		zero_user_segment(page, 0, PAGE_SIZE);
-		if (f2fs_need_verity(inode, page->index) &&
-		    !fsverity_verify_page(page)) {
+		folio_zero_segment(folio, 0, folio_size(folio));
+		if (f2fs_need_verity(inode, index) &&
+		    !fsverity_verify_folio(folio)) {
 			ret = -EIO;
 			goto out;
 		}
-		if (!PageUptodate(page))
-			SetPageUptodate(page);
-		unlock_page(page);
+		if (!folio_test_uptodate(folio))
+			folio_mark_uptodate(folio);
+		folio_unlock(folio);
 		goto out;
 	}
 
@@ -2115,14 +2141,14 @@ zero_out:
 	 */
 	if (bio && (!page_is_mergeable(F2FS_I_SB(inode), bio,
 				       *last_block_in_bio, block_nr) ||
-		    !f2fs_crypt_mergeable_bio(bio, inode, page->index, NULL))) {
+		    !f2fs_crypt_mergeable_bio(bio, inode, index, NULL))) {
 submit_and_realloc:
 		f2fs_submit_read_bio(F2FS_I_SB(inode), bio, DATA);
 		bio = NULL;
 	}
 	if (bio == NULL) {
 		bio = f2fs_grab_read_bio(inode, block_nr, nr_pages,
-				is_readahead ? REQ_RAHEAD : 0, page->index,
+				is_readahead ? REQ_RAHEAD : 0, index,
 				false);
 		if (IS_ERR(bio)) {
 			ret = PTR_ERR(bio);
@@ -2137,7 +2163,7 @@ submit_and_realloc:
 	 */
 	f2fs_wait_on_block_writeback(inode, block_nr);
 
-	if (bio_add_page(bio, page, blocksize, 0) < blocksize)
+	if (!bio_add_folio(bio, folio, blocksize, 0))
 		goto submit_and_realloc;
 
 	inc_page_count(F2FS_I_SB(inode), F2FS_RD_DATA);
@@ -2324,7 +2350,7 @@ out:
  * Major change was from block_size == page_size in f2fs by default.
  */
 static int f2fs_mpage_readpages(struct inode *inode,
-		struct readahead_control *rac, struct page *page)
+		struct readahead_control *rac, struct folio *folio)
 {
 	struct bio *bio = NULL;
 	sector_t last_block_in_bio = 0;
@@ -2344,6 +2370,7 @@ static int f2fs_mpage_readpages(struct inode *inode,
 #endif
 	unsigned nr_pages = rac ? readahead_count(rac) : 1;
 	unsigned max_nr_pages = nr_pages;
+	pgoff_t index;
 	int ret = 0;
 
 	map.m_pblk = 0;
@@ -2357,64 +2384,63 @@ static int f2fs_mpage_readpages(struct inode *inode,
 
 	for (; nr_pages; nr_pages--) {
 		if (rac) {
-			page = readahead_page(rac);
-			prefetchw(&page->flags);
+			folio = readahead_folio(rac);
+			prefetchw(&folio->flags);
 		}
 
-#ifdef CONFIG_F2FS_FS_COMPRESSION
-		if (f2fs_compressed_file(inode)) {
-			/* there are remained compressed pages, submit them */
-			if (!f2fs_cluster_can_merge_page(&cc, page->index)) {
-				ret = f2fs_read_multi_pages(&cc, &bio,
-							max_nr_pages,
-							&last_block_in_bio,
-							rac != NULL, false);
-				f2fs_destroy_compress_ctx(&cc, false);
-				if (ret)
-					goto set_error_page;
-			}
-			if (cc.cluster_idx == NULL_CLUSTER) {
-				if (nc_cluster_idx ==
-					page->index >> cc.log_cluster_size) {
-					goto read_single_page;
-				}
-
-				ret = f2fs_is_compressed_cluster(inode, page->index);
-				if (ret < 0)
-					goto set_error_page;
-				else if (!ret) {
-					nc_cluster_idx =
-						page->index >> cc.log_cluster_size;
-					goto read_single_page;
-				}
+		index = folio_index(folio);
 
-				nc_cluster_idx = NULL_CLUSTER;
-			}
-			ret = f2fs_init_compress_ctx(&cc);
+#ifdef CONFIG_F2FS_FS_COMPRESSION
+		if (!f2fs_compressed_file(inode))
+			goto read_single_page;
+
+		/* there are remained compressed pages, submit them */
+		if (!f2fs_cluster_can_merge_page(&cc, index)) {
+			ret = f2fs_read_multi_pages(&cc, &bio,
+						max_nr_pages,
+						&last_block_in_bio,
+						rac != NULL, false);
+			f2fs_destroy_compress_ctx(&cc, false);
 			if (ret)
 				goto set_error_page;
+		}
+		if (cc.cluster_idx == NULL_CLUSTER) {
+			if (nc_cluster_idx == index >> cc.log_cluster_size)
+				goto read_single_page;
 
-			f2fs_compress_ctx_add_page(&cc, page);
+			ret = f2fs_is_compressed_cluster(inode, index);
+			if (ret < 0)
+				goto set_error_page;
+			else if (!ret) {
+				nc_cluster_idx =
+					index >> cc.log_cluster_size;
+				goto read_single_page;
+			}
 
-			goto next_page;
+			nc_cluster_idx = NULL_CLUSTER;
 		}
+		ret = f2fs_init_compress_ctx(&cc);
+		if (ret)
+			goto set_error_page;
+
+		f2fs_compress_ctx_add_page(&cc, &folio->page);
+
+		goto next_page;
 read_single_page:
 #endif
 
-		ret = f2fs_read_single_page(inode, page, max_nr_pages, &map,
+		ret = f2fs_read_single_page(inode, folio, max_nr_pages, &map,
 					&bio, &last_block_in_bio, rac);
 		if (ret) {
 #ifdef CONFIG_F2FS_FS_COMPRESSION
 set_error_page:
 #endif
-			zero_user_segment(page, 0, PAGE_SIZE);
-			unlock_page(page);
+			folio_zero_segment(folio, 0, folio_size(folio));
+			folio_unlock(folio);
 		}
 #ifdef CONFIG_F2FS_FS_COMPRESSION
 next_page:
 #endif
-		if (rac)
-			put_page(page);
 
 #ifdef CONFIG_F2FS_FS_COMPRESSION
 		if (f2fs_compressed_file(inode)) {
@@ -2436,22 +2462,21 @@ next_page:
 
 static int f2fs_read_data_folio(struct file *file, struct folio *folio)
 {
-	struct page *page = &folio->page;
-	struct inode *inode = page_file_mapping(page)->host;
+	struct inode *inode = folio_file_mapping(folio)->host;
 	int ret = -EAGAIN;
 
-	trace_f2fs_readpage(page, DATA);
+	trace_f2fs_readpage(folio, DATA);
 
 	if (!f2fs_is_compress_backend_ready(inode)) {
-		unlock_page(page);
+		folio_unlock(folio);
 		return -EOPNOTSUPP;
 	}
 
 	/* If the file has inline data, try to read it directly */
 	if (f2fs_has_inline_data(inode))
-		ret = f2fs_read_inline_data(inode, page);
+		ret = f2fs_read_inline_data(inode, folio);
 	if (ret == -EAGAIN)
-		ret = f2fs_mpage_readpages(inode, NULL, page);
+		ret = f2fs_mpage_readpages(inode, NULL, folio);
 	return ret;
 }
 
@@ -2685,12 +2710,11 @@ got_it:
 		if (err) {
 			if (fscrypt_inode_uses_fs_layer_crypto(inode))
 				fscrypt_finalize_bounce_page(&fio->encrypted_page);
-			if (PageWriteback(page))
-				end_page_writeback(page);
+			end_page_writeback(page);
 		} else {
 			set_inode_flag(inode, FI_UPDATE_WRITE);
 		}
-		trace_f2fs_do_write_data_page(fio->page, IPU);
+		trace_f2fs_do_write_data_page(page_folio(page), IPU);
 		return err;
 	}
 
@@ -2719,7 +2743,7 @@ got_it:
 
 	/* LFS mode write path */
 	f2fs_outplace_write_data(&dn, fio);
-	trace_f2fs_do_write_data_page(page, OPU);
+	trace_f2fs_do_write_data_page(page_folio(page), OPU);
 	set_inode_flag(inode, FI_APPEND_WRITE);
 out_writepage:
 	f2fs_put_dnode(&dn);
@@ -2766,7 +2790,7 @@ int f2fs_write_single_data_page(struct page *page, int *submitted,
 		.last_block = last_block,
 	};
 
-	trace_f2fs_writepage(page, DATA);
+	trace_f2fs_writepage(page_folio(page), DATA);
 
 	/* we should bypass data pages to proceed the kworker jobs */
 	if (unlikely(f2fs_cp_error(sbi))) {
@@ -3379,7 +3403,7 @@ restart:
 
 	if (f2fs_has_inline_data(inode)) {
 		if (pos + len <= MAX_INLINE_DATA(inode)) {
-			f2fs_do_read_inline_data(page, ipage);
+			f2fs_do_read_inline_data(page_folio(page), ipage);
 			set_inode_flag(inode, FI_DATA_EXIST);
 			if (inode->i_nlink)
 				set_page_private_inline(ipage);
@@ -3740,7 +3764,7 @@ static bool f2fs_dirty_data_folio(struct address_space *mapping,
 {
 	struct inode *inode = mapping->host;
 
-	trace_f2fs_set_page_dirty(&folio->page, DATA);
+	trace_f2fs_set_page_dirty(folio, DATA);
 
 	if (!folio_test_uptodate(folio))
 		folio_mark_uptodate(folio);
@@ -3896,15 +3920,14 @@ static int check_swap_activate(struct swap_info_struct *sis,
 	struct address_space *mapping = swap_file->f_mapping;
 	struct inode *inode = mapping->host;
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
-	sector_t cur_lblock;
-	sector_t last_lblock;
-	sector_t pblock;
-	sector_t lowest_pblock = -1;
-	sector_t highest_pblock = 0;
+	block_t cur_lblock;
+	block_t last_lblock;
+	block_t pblock;
+	block_t lowest_pblock = -1;
+	block_t highest_pblock = 0;
 	int nr_extents = 0;
-	unsigned long nr_pblocks;
+	unsigned int nr_pblocks;
 	unsigned int blks_per_sec = BLKS_PER_SEC(sbi);
-	unsigned int sec_blks_mask = BLKS_PER_SEC(sbi) - 1;
 	unsigned int not_aligned = 0;
 	int ret = 0;
 
@@ -3942,8 +3965,8 @@ retry:
 		pblock = map.m_pblk;
 		nr_pblocks = map.m_len;
 
-		if ((pblock - SM_I(sbi)->main_blkaddr) & sec_blks_mask ||
-				nr_pblocks & sec_blks_mask ||
+		if ((pblock - SM_I(sbi)->main_blkaddr) % blks_per_sec ||
+				nr_pblocks % blks_per_sec ||
 				!f2fs_valid_pinned_area(sbi, pblock)) {
 			bool last_extent = false;
 
@@ -4160,7 +4183,8 @@ static int f2fs_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
 	map.m_lblk = bytes_to_blks(inode, offset);
 	map.m_len = bytes_to_blks(inode, offset + length - 1) - map.m_lblk + 1;
 	map.m_next_pgofs = &next_pgofs;
-	map.m_seg_type = f2fs_rw_hint_to_seg_type(inode->i_write_hint);
+	map.m_seg_type = f2fs_rw_hint_to_seg_type(F2FS_I_SB(inode),
+						inode->i_write_hint);
 	if (flags & IOMAP_WRITE)
 		map.m_may_create = true;
 
@@ -4181,12 +4205,13 @@ static int f2fs_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
 	 * We should never see delalloc or compressed extents here based on
 	 * prior flushing and checks.
 	 */
-	if (WARN_ON_ONCE(map.m_pblk == NEW_ADDR))
-		return -EINVAL;
 	if (WARN_ON_ONCE(map.m_pblk == COMPRESS_ADDR))
 		return -EINVAL;
 
-	if (map.m_pblk != NULL_ADDR) {
+	if (map.m_flags & F2FS_MAP_MAPPED) {
+		if (WARN_ON_ONCE(map.m_pblk == NEW_ADDR))
+			return -EINVAL;
+
 		iomap->length = blks_to_bytes(inode, map.m_len);
 		iomap->type = IOMAP_MAPPED;
 		iomap->flags |= IOMAP_F_MERGED;
@@ -4195,9 +4220,17 @@ static int f2fs_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
 	} else {
 		if (flags & IOMAP_WRITE)
 			return -ENOTBLK;
-		iomap->length = blks_to_bytes(inode, next_pgofs) -
-				iomap->offset;
-		iomap->type = IOMAP_HOLE;
+
+		if (map.m_pblk == NULL_ADDR) {
+			iomap->length = blks_to_bytes(inode, next_pgofs) -
+								iomap->offset;
+			iomap->type = IOMAP_HOLE;
+		} else if (map.m_pblk == NEW_ADDR) {
+			iomap->length = blks_to_bytes(inode, map.m_len);
+			iomap->type = IOMAP_UNWRITTEN;
+		} else {
+			f2fs_bug_on(F2FS_I_SB(inode), 1);
+		}
 		iomap->addr = IOMAP_NULL_ADDR;
 	}