for-f2fs-4.10

This patch series contains several performance tuning patches regarding to the
 IO submission flow, in addition to supporting new features such as a ZBC-base
 drive and multiple devices.
 
 It also includes some major bug fixes such as:
  - checkpoint version control
  - fdatasync-related roll-forward recovery routine
  - memory boundary or null-pointer access in corner cases
  - missing error cases
 
 It has various minor clean-up patches as well.
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v2
 
 iQIcBAABCAAGBQJYTx44AAoJEEAUqH6CSFDSnAQP/jeYJq5Zd0bweEF5g00Ec1Qg
 qNKQ57e9EHDRaDLBUmHHEaCEPRL0bw6SOUUWWqzGA07KcsIK+Yb/dGAyIcuV7WMl
 PjntVbYm4yARDYBHGupdOCzFSkzr8gDalb+98jJnoGUonsftljhES9jedQ1NjAms
 GFPHDNtirZM/r0bjKkYKjpqJ6FCxFxcGPfb/GtohDajIpohWfKZiemaXGTgtYR4d
 iBVek16h+Hprz90ycZBY69uz0TdAwu/gb+htMVBrAdExHWvlFzgp35OIywiAB/YX
 3QD/x4t2HqOBaNYiiOAY4ukVW/Yyqa/ZAzbm+m5B5CAcFYiWXMy+cMXUY9HJJ/K0
 wdvi//Avtvgpp2PVZFn2pASx14vgMFylBzuNgKpP6MPdtWTEL33jT7VYs9Nuz45E
 dgZ9IpiDt4DeTRuZ4mPO5iH7bVHPvAVV80bpXzirCCzDeNZ1EFFIQzXh/2UAmCxI
 twPXGBIYul0aIl9JkWAyhCZSd3XDSqedpfPudknjhzM9Xb1H5X0QJco7f/UwsWXH
 WxV6lHr1Q7UH96wJ7x/GAqj8ArOAASRV18+K51dqU+DWHnFPpBArJe39FVf8NGWs
 Fz1ZmlWBQ0ZgzvLkGa80llhjalXIEy/JabMrpy6VrzQGxHdmW4cVxe4dJ3710WxX
 VysJUcNMRKxMUTWOKsxp
 =Boum
 -----END PGP SIGNATURE-----

Merge tag 'for-f2fs-4.10' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs

Pull f2fs updates from Jaegeuk Kim:
 "This patch series contains several performance tuning patches
  regarding to the IO submission flow, in addition to supporting new
  features such as a ZBC-base drive and multiple devices.

  It also includes some major bug fixes such as:
   - checkpoint version control
   - fdatasync-related roll-forward recovery routine
   - memory boundary or null-pointer access in corner cases
   - missing error cases

  It has various minor clean-up patches as well"

* tag 'for-f2fs-4.10' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (66 commits)
  f2fs: fix a missing size change in f2fs_setattr
  f2fs: fix to access nullified flush_cmd_control pointer
  f2fs: free meta pages if sanity check for ckpt is failed
  f2fs: detect wrong layout
  f2fs: call sync_fs when f2fs is idle
  Revert "f2fs: use percpu_counter for # of dirty pages in inode"
  f2fs: return AOP_WRITEPAGE_ACTIVATE for writepage
  f2fs: do not activate auto_recovery for fallocated i_size
  f2fs: fix to determine start_cp_addr by sbi->cur_cp_pack
  f2fs: fix 32-bit build
  f2fs: set ->owner for debugfs status file's file_operations
  f2fs: fix incorrect free inode count in ->statfs
  f2fs: drop duplicate header timer.h
  f2fs: fix wrong AUTO_RECOVER condition
  f2fs: do not recover i_size if it's valid
  f2fs: fix fdatasync
  f2fs: fix to account total free nid correctly
  f2fs: fix an infinite loop when flush nodes in cp
  f2fs: don't wait writeback for datas during checkpoint
  f2fs: fix wrong written_valid_blocks counting
  ...

fs/f2fs/acl.c

@@ -384,7 +384,7 @@ int f2fs_init_acl(struct inode *inode, struct inode *dir, struct page *ipage,
 	if (error)
 		return error;
 
-	f2fs_mark_inode_dirty_sync(inode);
+	f2fs_mark_inode_dirty_sync(inode, true);
 
 	if (default_acl) {
 		error = __f2fs_set_acl(inode, ACL_TYPE_DEFAULT, default_acl,

fs/f2fs/checkpoint.c

@@ -228,7 +228,7 @@ void ra_meta_pages_cond(struct f2fs_sb_info *sbi, pgoff_t index)
 	f2fs_put_page(page, 0);
 
 	if (readahead)
-		ra_meta_pages(sbi, index, MAX_BIO_BLOCKS(sbi), META_POR, true);
+		ra_meta_pages(sbi, index, BIO_MAX_PAGES, META_POR, true);
 }
 
 static int f2fs_write_meta_page(struct page *page,
@@ -770,7 +770,12 @@ int get_valid_checkpoint(struct f2fs_sb_info *sbi)
 
 	/* Sanity checking of checkpoint */
 	if (sanity_check_ckpt(sbi))
-		goto fail_no_cp;
+		goto free_fail_no_cp;
+
+	if (cur_page == cp1)
+		sbi->cur_cp_pack = 1;
+	else
+		sbi->cur_cp_pack = 2;
 
 	if (cp_blks <= 1)
 		goto done;
@@ -793,6 +798,9 @@ done:
 	f2fs_put_page(cp2, 1);
 	return 0;
 
+free_fail_no_cp:
+	f2fs_put_page(cp1, 1);
+	f2fs_put_page(cp2, 1);
 fail_no_cp:
 	kfree(sbi->ckpt);
 	return -EINVAL;
@@ -921,7 +929,11 @@ int f2fs_sync_inode_meta(struct f2fs_sb_info *sbi)
 		inode = igrab(&fi->vfs_inode);
 		spin_unlock(&sbi->inode_lock[DIRTY_META]);
 		if (inode) {
-			update_inode_page(inode);
+			sync_inode_metadata(inode, 0);
+
+			/* it's on eviction */
+			if (is_inode_flag_set(inode, FI_DIRTY_INODE))
+				update_inode_page(inode);
 			iput(inode);
 		}
 	};
@@ -987,7 +999,7 @@ static void unblock_operations(struct f2fs_sb_info *sbi)
 {
 	up_write(&sbi->node_write);
 
-	build_free_nids(sbi);
+	build_free_nids(sbi, false);
 	f2fs_unlock_all(sbi);
 }
 
@@ -998,7 +1010,7 @@ static void wait_on_all_pages_writeback(struct f2fs_sb_info *sbi)
 	for (;;) {
 		prepare_to_wait(&sbi->cp_wait, &wait, TASK_UNINTERRUPTIBLE);
 
-		if (!atomic_read(&sbi->nr_wb_bios))
+		if (!get_pages(sbi, F2FS_WB_CP_DATA))
 			break;
 
 		io_schedule_timeout(5*HZ);
@@ -1123,7 +1135,7 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 				le32_to_cpu(ckpt->checksum_offset)))
 				= cpu_to_le32(crc32);
 
-	start_blk = __start_cp_addr(sbi);
+	start_blk = __start_cp_next_addr(sbi);
 
 	/* need to wait for end_io results */
 	wait_on_all_pages_writeback(sbi);
@@ -1184,9 +1196,9 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	if (unlikely(f2fs_cp_error(sbi)))
 		return -EIO;
 
-	clear_prefree_segments(sbi, cpc);
 	clear_sbi_flag(sbi, SBI_IS_DIRTY);
 	clear_sbi_flag(sbi, SBI_NEED_CP);
+	__set_cp_next_pack(sbi);
 
 	/*
 	 * redirty superblock if metadata like node page or inode cache is
@@ -1261,8 +1273,12 @@ int write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 
 	/* unlock all the fs_lock[] in do_checkpoint() */
 	err = do_checkpoint(sbi, cpc);
-
+	if (err) {
-	f2fs_wait_all_discard_bio(sbi);
+		release_discard_addrs(sbi);
+	} else {
+		clear_prefree_segments(sbi, cpc);
+		f2fs_wait_all_discard_bio(sbi);
+	}
 
 	unblock_operations(sbi);
 	stat_inc_cp_count(sbi->stat_info);

fs/f2fs/data.c

@@ -29,6 +29,26 @@
 #include "trace.h"
 #include <trace/events/f2fs.h>
 
+static bool __is_cp_guaranteed(struct page *page)
+{
+	struct address_space *mapping = page->mapping;
+	struct inode *inode;
+	struct f2fs_sb_info *sbi;
+
+	if (!mapping)
+		return false;
+
+	inode = mapping->host;
+	sbi = F2FS_I_SB(inode);
+
+	if (inode->i_ino == F2FS_META_INO(sbi) ||
+			inode->i_ino ==  F2FS_NODE_INO(sbi) ||
+			S_ISDIR(inode->i_mode) ||
+			is_cold_data(page))
+		return true;
+	return false;
+}
+
 static void f2fs_read_end_io(struct bio *bio)
 {
 	struct bio_vec *bvec;
@@ -71,6 +91,7 @@ static void f2fs_write_end_io(struct bio *bio)
 
 	bio_for_each_segment_all(bvec, bio, i) {
 		struct page *page = bvec->bv_page;
+		enum count_type type = WB_DATA_TYPE(page);
 
 		fscrypt_pullback_bio_page(&page, true);
 
@@ -78,15 +99,57 @@ static void f2fs_write_end_io(struct bio *bio)
 			mapping_set_error(page->mapping, -EIO);
 			f2fs_stop_checkpoint(sbi, true);
 		}
+		dec_page_count(sbi, type);
+		clear_cold_data(page);
 		end_page_writeback(page);
 	}
-	if (atomic_dec_and_test(&sbi->nr_wb_bios) &&
+	if (!get_pages(sbi, F2FS_WB_CP_DATA) &&
 				wq_has_sleeper(&sbi->cp_wait))
 		wake_up(&sbi->cp_wait);
 
 	bio_put(bio);
 }
 
+/*
+ * Return true, if pre_bio's bdev is same as its target device.
+ */
+struct block_device *f2fs_target_device(struct f2fs_sb_info *sbi,
+				block_t blk_addr, struct bio *bio)
+{
+	struct block_device *bdev = sbi->sb->s_bdev;
+	int i;
+
+	for (i = 0; i < sbi->s_ndevs; i++) {
+		if (FDEV(i).start_blk <= blk_addr &&
+					FDEV(i).end_blk >= blk_addr) {
+			blk_addr -= FDEV(i).start_blk;
+			bdev = FDEV(i).bdev;
+			break;
+		}
+	}
+	if (bio) {
+		bio->bi_bdev = bdev;
+		bio->bi_iter.bi_sector = SECTOR_FROM_BLOCK(blk_addr);
+	}
+	return bdev;
+}
+
+int f2fs_target_device_index(struct f2fs_sb_info *sbi, block_t blkaddr)
+{
+	int i;
+
+	for (i = 0; i < sbi->s_ndevs; i++)
+		if (FDEV(i).start_blk <= blkaddr && FDEV(i).end_blk >= blkaddr)
+			return i;
+	return 0;
+}
+
+static bool __same_bdev(struct f2fs_sb_info *sbi,
+				block_t blk_addr, struct bio *bio)
+{
+	return f2fs_target_device(sbi, blk_addr, NULL) == bio->bi_bdev;
+}
+
 /*
  * Low-level block read/write IO operations.
  */
@@ -97,8 +160,7 @@ static struct bio *__bio_alloc(struct f2fs_sb_info *sbi, block_t blk_addr,
 
 	bio = f2fs_bio_alloc(npages);
 
-	bio->bi_bdev = sbi->sb->s_bdev;
+	f2fs_target_device(sbi, blk_addr, bio);
-	bio->bi_iter.bi_sector = SECTOR_FROM_BLOCK(blk_addr);
 	bio->bi_end_io = is_read ? f2fs_read_end_io : f2fs_write_end_io;
 	bio->bi_private = is_read ? NULL : sbi;
 
@@ -109,8 +171,7 @@ static inline void __submit_bio(struct f2fs_sb_info *sbi,
 				struct bio *bio, enum page_type type)
 {
 	if (!is_read_io(bio_op(bio))) {
-		atomic_inc(&sbi->nr_wb_bios);
+		if (f2fs_sb_mounted_blkzoned(sbi->sb) &&
-		if (f2fs_sb_mounted_hmsmr(sbi->sb) &&
 			current->plug && (type == DATA || type == NODE))
 			blk_finish_plug(current->plug);
 	}
@@ -268,22 +329,24 @@ void f2fs_submit_page_mbio(struct f2fs_io_info *fio)
 		verify_block_addr(sbi, fio->old_blkaddr);
 	verify_block_addr(sbi, fio->new_blkaddr);
 
+	bio_page = fio->encrypted_page ? fio->encrypted_page : fio->page;
+
+	if (!is_read)
+		inc_page_count(sbi, WB_DATA_TYPE(bio_page));
+
 	down_write(&io->io_rwsem);
 
 	if (io->bio && (io->last_block_in_bio != fio->new_blkaddr - 1 ||
-	    (io->fio.op != fio->op || io->fio.op_flags != fio->op_flags)))
+	    (io->fio.op != fio->op || io->fio.op_flags != fio->op_flags) ||
+			!__same_bdev(sbi, fio->new_blkaddr, io->bio)))
 		__submit_merged_bio(io);
 alloc_new:
 	if (io->bio == NULL) {
-		int bio_blocks = MAX_BIO_BLOCKS(sbi);
-
 		io->bio = __bio_alloc(sbi, fio->new_blkaddr,
-						bio_blocks, is_read);
+						BIO_MAX_PAGES, is_read);
 		io->fio = *fio;
 	}
 
-	bio_page = fio->encrypted_page ? fio->encrypted_page : fio->page;
-
 	if (bio_add_page(io->bio, bio_page, PAGE_SIZE, 0) <
 							PAGE_SIZE) {
 		__submit_merged_bio(io);
@@ -588,7 +651,6 @@ static int __allocate_data_block(struct dnode_of_data *dn)
 	struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
 	struct f2fs_summary sum;
 	struct node_info ni;
-	int seg = CURSEG_WARM_DATA;
 	pgoff_t fofs;
 	blkcnt_t count = 1;
 
@@ -606,11 +668,8 @@ alloc:
 	get_node_info(sbi, dn->nid, &ni);
 	set_summary(&sum, dn->nid, dn->ofs_in_node, ni.version);
 
-	if (dn->ofs_in_node == 0 && dn->inode_page == dn->node_page)
-		seg = CURSEG_DIRECT_IO;
-
 	allocate_data_block(sbi, NULL, dn->data_blkaddr, &dn->data_blkaddr,
-								&sum, seg);
+						&sum, CURSEG_WARM_DATA);
 	set_data_blkaddr(dn);
 
 	/* update i_size */
@@ -622,11 +681,18 @@ alloc:
 	return 0;
 }
 
-ssize_t f2fs_preallocate_blocks(struct kiocb *iocb, struct iov_iter *from)
+static inline bool __force_buffered_io(struct inode *inode, int rw)
+{
+	return ((f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode)) ||
+			(rw == WRITE && test_opt(F2FS_I_SB(inode), LFS)) ||
+			F2FS_I_SB(inode)->s_ndevs);
+}
+
+int f2fs_preallocate_blocks(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct inode *inode = file_inode(iocb->ki_filp);
 	struct f2fs_map_blocks map;
-	ssize_t ret = 0;
+	int err = 0;
 
 	map.m_lblk = F2FS_BLK_ALIGN(iocb->ki_pos);
 	map.m_len = F2FS_BYTES_TO_BLK(iocb->ki_pos + iov_iter_count(from));
@@ -638,19 +704,22 @@ ssize_t f2fs_preallocate_blocks(struct kiocb *iocb, struct iov_iter *from)
 	map.m_next_pgofs = NULL;
 
 	if (iocb->ki_flags & IOCB_DIRECT) {
-		ret = f2fs_convert_inline_inode(inode);
+		err = f2fs_convert_inline_inode(inode);
-		if (ret)
+		if (err)
-			return ret;
+			return err;
-		return f2fs_map_blocks(inode, &map, 1, F2FS_GET_BLOCK_PRE_DIO);
+		return f2fs_map_blocks(inode, &map, 1,
+			__force_buffered_io(inode, WRITE) ?
+				F2FS_GET_BLOCK_PRE_AIO :
+				F2FS_GET_BLOCK_PRE_DIO);
 	}
 	if (iocb->ki_pos + iov_iter_count(from) > MAX_INLINE_DATA) {
-		ret = f2fs_convert_inline_inode(inode);
+		err = f2fs_convert_inline_inode(inode);
-		if (ret)
+		if (err)
-			return ret;
+			return err;
 	}
 	if (!f2fs_has_inline_data(inode))
 		return f2fs_map_blocks(inode, &map, 1, F2FS_GET_BLOCK_PRE_AIO);
-	return ret;
+	return err;
 }
 
 /*
@@ -674,7 +743,6 @@ int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
 	unsigned int ofs_in_node, last_ofs_in_node;
 	blkcnt_t prealloc;
 	struct extent_info ei;
-	bool allocated = false;
 	block_t blkaddr;
 
 	if (!maxblocks)
@@ -714,7 +782,7 @@ next_dnode:
 	}
 
 	prealloc = 0;
-	ofs_in_node = dn.ofs_in_node;
+	last_ofs_in_node = ofs_in_node = dn.ofs_in_node;
 	end_offset = ADDRS_PER_PAGE(dn.node_page, inode);
 
 next_block:
@@ -733,10 +801,8 @@ next_block:
 				}
 			} else {
 				err = __allocate_data_block(&dn);
-				if (!err) {
+				if (!err)
 					set_inode_flag(inode, FI_APPEND_WRITE);
-					allocated = true;
-				}
 			}
 			if (err)
 				goto sync_out;
@@ -791,7 +857,6 @@ skip:
 		err = reserve_new_blocks(&dn, prealloc);
 		if (err)
 			goto sync_out;
-		allocated = dn.node_changed;
 
 		map->m_len += dn.ofs_in_node - ofs_in_node;
 		if (prealloc && dn.ofs_in_node != last_ofs_in_node + 1) {
@@ -810,9 +875,8 @@ skip:
 
 	if (create) {
 		f2fs_unlock_op(sbi);
-		f2fs_balance_fs(sbi, allocated);
+		f2fs_balance_fs(sbi, dn.node_changed);
 	}
-	allocated = false;
 	goto next_dnode;
 
 sync_out:
@@ -820,7 +884,7 @@ sync_out:
 unlock_out:
 	if (create) {
 		f2fs_unlock_op(sbi);
-		f2fs_balance_fs(sbi, allocated);
+		f2fs_balance_fs(sbi, dn.node_changed);
 	}
 out:
 	trace_f2fs_map_blocks(inode, map, err);
@@ -832,19 +896,19 @@ static int __get_data_block(struct inode *inode, sector_t iblock,
 			pgoff_t *next_pgofs)
 {
 	struct f2fs_map_blocks map;
-	int ret;
+	int err;
 
 	map.m_lblk = iblock;
 	map.m_len = bh->b_size >> inode->i_blkbits;
 	map.m_next_pgofs = next_pgofs;
 
-	ret = f2fs_map_blocks(inode, &map, create, flag);
+	err = f2fs_map_blocks(inode, &map, create, flag);
-	if (!ret) {
+	if (!err) {
 		map_bh(bh, inode->i_sb, map.m_pblk);
 		bh->b_state = (bh->b_state & ~F2FS_MAP_FLAGS) | map.m_flags;
 		bh->b_size = map.m_len << inode->i_blkbits;
 	}
-	return ret;
+	return err;
 }
 
 static int get_data_block(struct inode *inode, sector_t iblock,
@@ -889,7 +953,6 @@ int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 	struct buffer_head map_bh;
 	sector_t start_blk, last_blk;
 	pgoff_t next_pgofs;
-	loff_t isize;
 	u64 logical = 0, phys = 0, size = 0;
 	u32 flags = 0;
 	int ret = 0;
@@ -906,13 +969,6 @@ int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 
 	inode_lock(inode);
 
-	isize = i_size_read(inode);
-	if (start >= isize)
-		goto out;
-
-	if (start + len > isize)
-		len = isize - start;
-
 	if (logical_to_blk(inode, len) == 0)
 		len = blk_to_logical(inode, 1);
 
@@ -931,13 +987,11 @@ next:
 	/* HOLE */
 	if (!buffer_mapped(&map_bh)) {
 		start_blk = next_pgofs;
-		/* Go through holes util pass the EOF */
+
-		if (blk_to_logical(inode, start_blk) < isize)
+		if (blk_to_logical(inode, start_blk) < blk_to_logical(inode,
+					F2FS_I_SB(inode)->max_file_blocks))
 			goto prep_next;
-		/* Found a hole beyond isize means no more extents.
+
-		 * Note that the premise is that filesystems don't
-		 * punch holes beyond isize and keep size unchanged.
-		 */
 		flags |= FIEMAP_EXTENT_LAST;
 	}
 
@@ -980,7 +1034,6 @@ static struct bio *f2fs_grab_bio(struct inode *inode, block_t blkaddr,
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	struct fscrypt_ctx *ctx = NULL;
-	struct block_device *bdev = sbi->sb->s_bdev;
 	struct bio *bio;
 
 	if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode)) {
@@ -998,8 +1051,7 @@ static struct bio *f2fs_grab_bio(struct inode *inode, block_t blkaddr,
 			fscrypt_release_ctx(ctx);
 		return ERR_PTR(-ENOMEM);
 	}
-	bio->bi_bdev = bdev;
+	f2fs_target_device(sbi, blkaddr, bio);
-	bio->bi_iter.bi_sector = SECTOR_FROM_BLOCK(blkaddr);
 	bio->bi_end_io = f2fs_read_end_io;
 	bio->bi_private = ctx;
 
@@ -1094,7 +1146,8 @@ got_it:
 		 * This page will go to BIO.  Do we need to send this
 		 * BIO off first?
 		 */
-		if (bio && (last_block_in_bio != block_nr - 1)) {
+		if (bio && (last_block_in_bio != block_nr - 1 ||
+			!__same_bdev(F2FS_I_SB(inode), block_nr, bio))) {
 submit_and_realloc:
 			__submit_bio(F2FS_I_SB(inode), bio, DATA);
 			bio = NULL;
@@ -1309,7 +1362,6 @@ done:
 	if (err && err != -ENOENT)
 		goto redirty_out;
 
-	clear_cold_data(page);
 out:
 	inode_dec_dirty_pages(inode);
 	if (err)
@@ -1330,6 +1382,8 @@ out:
 
 redirty_out:
 	redirty_page_for_writepage(wbc, page);
+	if (!err)
+		return AOP_WRITEPAGE_ACTIVATE;
 	unlock_page(page);
 	return err;
 }
@@ -1425,6 +1479,15 @@ continue_unlock:
 
 			ret = mapping->a_ops->writepage(page, wbc);
 			if (unlikely(ret)) {
+				/*
+				 * keep nr_to_write, since vfs uses this to
+				 * get # of written pages.
+				 */
+				if (ret == AOP_WRITEPAGE_ACTIVATE) {
+					unlock_page(page);
+					ret = 0;
+					continue;
+				}
 				done_index = page->index + 1;
 				done = 1;
 				break;
@@ -1712,7 +1775,6 @@ static int f2fs_write_end(struct file *file,
 		goto unlock_out;
 
 	set_page_dirty(page);
-	clear_cold_data(page);
 
 	if (pos + copied > i_size_read(inode))
 		f2fs_i_size_write(inode, pos + copied);
@@ -1749,9 +1811,7 @@ static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 	if (err)
 		return err;
 
-	if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode))
+	if (__force_buffered_io(inode, rw))
-		return 0;
-	if (test_opt(F2FS_I_SB(inode), LFS))
 		return 0;
 
 	trace_f2fs_direct_IO_enter(inode, offset, count, rw);
@@ -1783,12 +1843,14 @@ void f2fs_invalidate_page(struct page *page, unsigned int offset,
 		return;
 
 	if (PageDirty(page)) {
-		if (inode->i_ino == F2FS_META_INO(sbi))
+		if (inode->i_ino == F2FS_META_INO(sbi)) {
 			dec_page_count(sbi, F2FS_DIRTY_META);
-		else if (inode->i_ino == F2FS_NODE_INO(sbi))
+		} else if (inode->i_ino == F2FS_NODE_INO(sbi)) {
 			dec_page_count(sbi, F2FS_DIRTY_NODES);
-		else
+		} else {
 			inode_dec_dirty_pages(inode);
+			remove_dirty_inode(inode);
+		}
 	}
 
 	/* This is atomic written page, keep Private */

fs/f2fs/debug.c

@@ -50,7 +50,8 @@ static void update_general_status(struct f2fs_sb_info *sbi)
 	si->ndirty_files = sbi->ndirty_inode[FILE_INODE];
 	si->ndirty_all = sbi->ndirty_inode[DIRTY_META];
 	si->inmem_pages = get_pages(sbi, F2FS_INMEM_PAGES);
-	si->wb_bios = atomic_read(&sbi->nr_wb_bios);
+	si->nr_wb_cp_data = get_pages(sbi, F2FS_WB_CP_DATA);
+	si->nr_wb_data = get_pages(sbi, F2FS_WB_DATA);
 	si->total_count = (int)sbi->user_block_count / sbi->blocks_per_seg;
 	si->rsvd_segs = reserved_segments(sbi);
 	si->overp_segs = overprovision_segments(sbi);
@@ -74,7 +75,8 @@ static void update_general_status(struct f2fs_sb_info *sbi)
 	si->dirty_nats = NM_I(sbi)->dirty_nat_cnt;
 	si->sits = MAIN_SEGS(sbi);
 	si->dirty_sits = SIT_I(sbi)->dirty_sentries;
-	si->fnids = NM_I(sbi)->fcnt;
+	si->free_nids = NM_I(sbi)->nid_cnt[FREE_NID_LIST];
+	si->alloc_nids = NM_I(sbi)->nid_cnt[ALLOC_NID_LIST];
 	si->bg_gc = sbi->bg_gc;
 	si->util_free = (int)(free_user_blocks(sbi) >> sbi->log_blocks_per_seg)
 		* 100 / (int)(sbi->user_block_count >> sbi->log_blocks_per_seg)
@@ -194,7 +196,9 @@ get_cache:
 		si->cache_mem += sizeof(struct flush_cmd_control);
 
 	/* free nids */
-	si->cache_mem += NM_I(sbi)->fcnt * sizeof(struct free_nid);
+	si->cache_mem += (NM_I(sbi)->nid_cnt[FREE_NID_LIST] +
+				NM_I(sbi)->nid_cnt[ALLOC_NID_LIST]) *
+				sizeof(struct free_nid);
 	si->cache_mem += NM_I(sbi)->nat_cnt * sizeof(struct nat_entry);
 	si->cache_mem += NM_I(sbi)->dirty_nat_cnt *
 					sizeof(struct nat_entry_set);
@@ -310,22 +314,22 @@ static int stat_show(struct seq_file *s, void *v)
 		seq_printf(s, "  - Inner Struct Count: tree: %d(%d), node: %d\n",
 				si->ext_tree, si->zombie_tree, si->ext_node);
 		seq_puts(s, "\nBalancing F2FS Async:\n");
-		seq_printf(s, "  - inmem: %4lld, wb_bios: %4d\n",
+		seq_printf(s, "  - inmem: %4d, wb_cp_data: %4d, wb_data: %4d\n",
-			   si->inmem_pages, si->wb_bios);
+			   si->inmem_pages, si->nr_wb_cp_data, si->nr_wb_data);
-		seq_printf(s, "  - nodes: %4lld in %4d\n",
+		seq_printf(s, "  - nodes: %4d in %4d\n",
 			   si->ndirty_node, si->node_pages);
-		seq_printf(s, "  - dents: %4lld in dirs:%4d (%4d)\n",
+		seq_printf(s, "  - dents: %4d in dirs:%4d (%4d)\n",
 			   si->ndirty_dent, si->ndirty_dirs, si->ndirty_all);
-		seq_printf(s, "  - datas: %4lld in files:%4d\n",
+		seq_printf(s, "  - datas: %4d in files:%4d\n",
 			   si->ndirty_data, si->ndirty_files);
-		seq_printf(s, "  - meta: %4lld in %4d\n",
+		seq_printf(s, "  - meta: %4d in %4d\n",
 			   si->ndirty_meta, si->meta_pages);
-		seq_printf(s, "  - imeta: %4lld\n",
+		seq_printf(s, "  - imeta: %4d\n",
 			   si->ndirty_imeta);
 		seq_printf(s, "  - NATs: %9d/%9d\n  - SITs: %9d/%9d\n",
 			   si->dirty_nats, si->nats, si->dirty_sits, si->sits);
-		seq_printf(s, "  - free_nids: %9d\n",
+		seq_printf(s, "  - free_nids: %9d, alloc_nids: %9d\n",
-			   si->fnids);
+			   si->free_nids, si->alloc_nids);
 		seq_puts(s, "\nDistribution of User Blocks:");
 		seq_puts(s, " [ valid | invalid | free ]\n");
 		seq_puts(s, "  [");
@@ -373,6 +377,7 @@ static int stat_open(struct inode *inode, struct file *file)
 }
 
 static const struct file_operations stat_fops = {
+	.owner = THIS_MODULE,
 	.open = stat_open,
 	.read = seq_read,
 	.llseek = seq_lseek,

fs/f2fs/dir.c

@@ -136,7 +136,7 @@ struct f2fs_dir_entry *find_target_dentry(struct fscrypt_name *fname,
 
 		/* show encrypted name */
 		if (fname->hash) {
-			if (de->hash_code == fname->hash)
+			if (de->hash_code == cpu_to_le32(fname->hash))
 				goto found;
 		} else if (de_name.len == name->len &&
 			de->hash_code == namehash &&
@@ -313,7 +313,7 @@ void f2fs_set_link(struct inode *dir, struct f2fs_dir_entry *de,
 	set_page_dirty(page);
 
 	dir->i_mtime = dir->i_ctime = current_time(dir);
-	f2fs_mark_inode_dirty_sync(dir);
+	f2fs_mark_inode_dirty_sync(dir, false);
 	f2fs_put_page(page, 1);
 }
 
@@ -466,7 +466,7 @@ void update_parent_metadata(struct inode *dir, struct inode *inode,
 		clear_inode_flag(inode, FI_NEW_INODE);
 	}
 	dir->i_mtime = dir->i_ctime = current_time(dir);
-	f2fs_mark_inode_dirty_sync(dir);
+	f2fs_mark_inode_dirty_sync(dir, false);
 
 	if (F2FS_I(dir)->i_current_depth != current_depth)
 		f2fs_i_depth_write(dir, current_depth);
@@ -731,7 +731,7 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page,
 	set_page_dirty(page);
 
 	dir->i_ctime = dir->i_mtime = current_time(dir);
-	f2fs_mark_inode_dirty_sync(dir);
+	f2fs_mark_inode_dirty_sync(dir, false);
 
 	if (inode)
 		f2fs_drop_nlink(dir, inode);
@@ -742,6 +742,7 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page,
 		ClearPagePrivate(page);
 		ClearPageUptodate(page);
 		inode_dec_dirty_pages(dir);
+		remove_dirty_inode(dir);
 	}
 	f2fs_put_page(page, 1);
 }
@@ -784,7 +785,7 @@ bool f2fs_empty_dir(struct inode *dir)
 	return true;
 }
 
-bool f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d,
+int f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d,
 			unsigned int start_pos, struct fscrypt_str *fstr)
 {
 	unsigned char d_type = DT_UNKNOWN;
@@ -819,7 +820,7 @@ bool f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d,
 						(u32)de->hash_code, 0,
 						&de_name, fstr);
 			if (err)
-				return true;
+				return err;
 
 			de_name = *fstr;
 			fstr->len = save_len;
@@ -827,12 +828,12 @@ bool f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d,
 
 		if (!dir_emit(ctx, de_name.name, de_name.len,
 					le32_to_cpu(de->ino), d_type))
-			return true;
+			return 1;
 
 		bit_pos += GET_DENTRY_SLOTS(le16_to_cpu(de->name_len));
 		ctx->pos = start_pos + bit_pos;
 	}
-	return false;
+	return 0;
 }
 
 static int f2fs_readdir(struct file *file, struct dir_context *ctx)
@@ -871,17 +872,21 @@ static int f2fs_readdir(struct file *file, struct dir_context *ctx)
 		dentry_page = get_lock_data_page(inode, n, false);
 		if (IS_ERR(dentry_page)) {
 			err = PTR_ERR(dentry_page);
-			if (err == -ENOENT)
+			if (err == -ENOENT) {
+				err = 0;
 				continue;
-			else
+			} else {
 				goto out;
+			}
 		}
 
 		dentry_blk = kmap(dentry_page);
 
 		make_dentry_ptr(inode, &d, (void *)dentry_blk, 1);
 
-		if (f2fs_fill_dentries(ctx, &d, n * NR_DENTRY_IN_BLOCK, &fstr)) {
+		err = f2fs_fill_dentries(ctx, &d,
+				n * NR_DENTRY_IN_BLOCK, &fstr);
+		if (err) {
 			kunmap(dentry_page);
 			f2fs_put_page(dentry_page, 1);
 			break;
@@ -891,10 +896,9 @@ static int f2fs_readdir(struct file *file, struct dir_context *ctx)
 		kunmap(dentry_page);
 		f2fs_put_page(dentry_page, 1);
 	}
-	err = 0;
 out:
 	fscrypt_fname_free_buffer(&fstr);
-	return err;
+	return err < 0 ? err : 0;
 }
 
 static int f2fs_dir_open(struct inode *inode, struct file *filp)

fs/f2fs/extent_cache.c

@@ -172,7 +172,7 @@ static void __drop_largest_extent(struct inode *inode,
 
 	if (fofs < largest->fofs + largest->len && fofs + len > largest->fofs) {
 		largest->len = 0;
-		f2fs_mark_inode_dirty_sync(inode);
+		f2fs_mark_inode_dirty_sync(inode, true);
 	}
 }
 

fs/f2fs/f2fs.h

@@ -103,7 +103,7 @@ struct f2fs_mount_info {
 };
 
 #define F2FS_FEATURE_ENCRYPT	0x0001
-#define F2FS_FEATURE_HMSMR	0x0002
+#define F2FS_FEATURE_BLKZONED	0x0002
 
 #define F2FS_HAS_FEATURE(sb, mask)					\
 	((F2FS_SB(sb)->raw_super->feature & cpu_to_le32(mask)) != 0)
@@ -401,6 +401,7 @@ struct f2fs_map_blocks {
 #define FADVISE_LOST_PINO_BIT	0x02
 #define FADVISE_ENCRYPT_BIT	0x04
 #define FADVISE_ENC_NAME_BIT	0x08
+#define FADVISE_KEEP_SIZE_BIT	0x10
 
 #define file_is_cold(inode)	is_file(inode, FADVISE_COLD_BIT)
 #define file_wrong_pino(inode)	is_file(inode, FADVISE_LOST_PINO_BIT)
@@ -413,6 +414,8 @@ struct f2fs_map_blocks {
 #define file_clear_encrypt(inode) clear_file(inode, FADVISE_ENCRYPT_BIT)
 #define file_enc_name(inode)	is_file(inode, FADVISE_ENC_NAME_BIT)
 #define file_set_enc_name(inode) set_file(inode, FADVISE_ENC_NAME_BIT)
+#define file_keep_isize(inode)	is_file(inode, FADVISE_KEEP_SIZE_BIT)
+#define file_set_keep_isize(inode) set_file(inode, FADVISE_KEEP_SIZE_BIT)
 
 #define DEF_DIR_LEVEL		0
 
@@ -428,7 +431,7 @@ struct f2fs_inode_info {
 	/* Use below internally in f2fs*/
 	unsigned long flags;		/* use to pass per-file flags */
 	struct rw_semaphore i_sem;	/* protect fi info */
-	struct percpu_counter dirty_pages;	/* # of dirty pages */
+	atomic_t dirty_pages;		/* # of dirty pages */
 	f2fs_hash_t chash;		/* hash value of given file name */
 	unsigned int clevel;		/* maximum level of given file name */
 	nid_t i_xattr_nid;		/* node id that contains xattrs */
@@ -493,20 +496,26 @@ static inline bool __is_front_mergeable(struct extent_info *cur,
 	return __is_extent_mergeable(cur, front);
 }
 
-extern void f2fs_mark_inode_dirty_sync(struct inode *);
+extern void f2fs_mark_inode_dirty_sync(struct inode *, bool);
 static inline void __try_update_largest_extent(struct inode *inode,
 			struct extent_tree *et, struct extent_node *en)
 {
 	if (en->ei.len > et->largest.len) {
 		et->largest = en->ei;
-		f2fs_mark_inode_dirty_sync(inode);
+		f2fs_mark_inode_dirty_sync(inode, true);
 	}
 }
 
+enum nid_list {
+	FREE_NID_LIST,
+	ALLOC_NID_LIST,
+	MAX_NID_LIST,
+};
+
 struct f2fs_nm_info {
 	block_t nat_blkaddr;		/* base disk address of NAT */
 	nid_t max_nid;			/* maximum possible node ids */
-	nid_t available_nids;		/* maximum available node ids */
+	nid_t available_nids;		/* # of available node ids */
 	nid_t next_scan_nid;		/* the next nid to be scanned */
 	unsigned int ram_thresh;	/* control the memory footprint */
 	unsigned int ra_nid_pages;	/* # of nid pages to be readaheaded */
@@ -522,9 +531,9 @@ struct f2fs_nm_info {
 
 	/* free node ids management */
 	struct radix_tree_root free_nid_root;/* root of the free_nid cache */
-	struct list_head free_nid_list;	/* a list for free nids */
+	struct list_head nid_list[MAX_NID_LIST];/* lists for free nids */
-	spinlock_t free_nid_list_lock;	/* protect free nid list */
+	unsigned int nid_cnt[MAX_NID_LIST];	/* the number of free node id */
-	unsigned int fcnt;		/* the number of free node id */
+	spinlock_t nid_list_lock;	/* protect nid lists ops */
 	struct mutex build_lock;	/* lock for build free nids */
 
 	/* for checkpoint */
@@ -585,7 +594,6 @@ enum {
 	CURSEG_WARM_NODE,	/* direct node blocks of normal files */
 	CURSEG_COLD_NODE,	/* indirect node blocks */
 	NO_CHECK_TYPE,
-	CURSEG_DIRECT_IO,	/* to use for the direct IO path */
 };
 
 struct flush_cmd {
@@ -649,6 +657,7 @@ struct f2fs_sm_info {
  * f2fs monitors the number of several block types such as on-writeback,
  * dirty dentry blocks, dirty node blocks, and dirty meta blocks.
  */
+#define WB_DATA_TYPE(p)	(__is_cp_guaranteed(p) ? F2FS_WB_CP_DATA : F2FS_WB_DATA)
 enum count_type {
 	F2FS_DIRTY_DENTS,
 	F2FS_DIRTY_DATA,
@@ -656,6 +665,8 @@ enum count_type {
 	F2FS_DIRTY_META,
 	F2FS_INMEM_PAGES,
 	F2FS_DIRTY_IMETA,
+	F2FS_WB_CP_DATA,
+	F2FS_WB_DATA,
 	NR_COUNT_TYPE,
 };
 
@@ -704,6 +715,20 @@ struct f2fs_bio_info {
 	struct rw_semaphore io_rwsem;	/* blocking op for bio */
 };
 
+#define FDEV(i)				(sbi->devs[i])
+#define RDEV(i)				(raw_super->devs[i])
+struct f2fs_dev_info {
+	struct block_device *bdev;
+	char path[MAX_PATH_LEN];
+	unsigned int total_segments;
+	block_t start_blk;
+	block_t end_blk;
+#ifdef CONFIG_BLK_DEV_ZONED
+	unsigned int nr_blkz;			/* Total number of zones */
+	u8 *blkz_type;				/* Array of zones type */
+#endif
+};
+
 enum inode_type {
 	DIR_INODE,			/* for dirty dir inode */
 	FILE_INODE,			/* for dirty regular/symlink inode */
@@ -750,6 +775,12 @@ struct f2fs_sb_info {
 	u8 key_prefix[F2FS_KEY_DESC_PREFIX_SIZE];
 	u8 key_prefix_size;
 #endif
+
+#ifdef CONFIG_BLK_DEV_ZONED
+	unsigned int blocks_per_blkz;		/* F2FS blocks per zone */
+	unsigned int log_blocks_per_blkz;	/* log2 F2FS blocks per zone */
+#endif
+
 	/* for node-related operations */
 	struct f2fs_nm_info *nm_info;		/* node manager */
 	struct inode *node_inode;		/* cache node blocks */
@@ -764,6 +795,7 @@ struct f2fs_sb_info {
 
 	/* for checkpoint */
 	struct f2fs_checkpoint *ckpt;		/* raw checkpoint pointer */
+	int cur_cp_pack;			/* remain current cp pack */
 	spinlock_t cp_lock;			/* for flag in ckpt */
 	struct inode *meta_inode;		/* cache meta blocks */
 	struct mutex cp_mutex;			/* checkpoint procedure lock */
@@ -815,10 +847,9 @@ struct f2fs_sb_info {
 	block_t discard_blks;			/* discard command candidats */
 	block_t last_valid_block_count;		/* for recovery */
 	u32 s_next_generation;			/* for NFS support */
-	atomic_t nr_wb_bios;			/* # of writeback bios */
 
 	/* # of pages, see count_type */
-	struct percpu_counter nr_pages[NR_COUNT_TYPE];
+	atomic_t nr_pages[NR_COUNT_TYPE];
 	/* # of allocated blocks */
 	struct percpu_counter alloc_valid_block_count;
 
@@ -863,6 +894,8 @@ struct f2fs_sb_info {
 
 	/* For shrinker support */
 	struct list_head s_list;
+	int s_ndevs;				/* number of devices */
+	struct f2fs_dev_info *devs;		/* for device list */
 	struct mutex umount_mutex;
 	unsigned int shrinker_run_no;
 
@@ -1105,13 +1138,6 @@ static inline void clear_ckpt_flags(struct f2fs_sb_info *sbi, unsigned int f)
 	spin_unlock(&sbi->cp_lock);
 }
 
-static inline bool f2fs_discard_en(struct f2fs_sb_info *sbi)
-{
-	struct request_queue *q = bdev_get_queue(sbi->sb->s_bdev);
-
-	return blk_queue_discard(q);
-}
-
 static inline void f2fs_lock_op(struct f2fs_sb_info *sbi)
 {
 	down_read(&sbi->cp_rwsem);
@@ -1232,9 +1258,10 @@ static inline void dec_valid_block_count(struct f2fs_sb_info *sbi,
 
 static inline void inc_page_count(struct f2fs_sb_info *sbi, int count_type)
 {
-	percpu_counter_inc(&sbi->nr_pages[count_type]);
+	atomic_inc(&sbi->nr_pages[count_type]);
 
-	if (count_type == F2FS_DIRTY_DATA || count_type == F2FS_INMEM_PAGES)
+	if (count_type == F2FS_DIRTY_DATA || count_type == F2FS_INMEM_PAGES ||
+		count_type == F2FS_WB_CP_DATA || count_type == F2FS_WB_DATA)
 		return;
 
 	set_sbi_flag(sbi, SBI_IS_DIRTY);
@@ -1242,14 +1269,14 @@ static inline void inc_page_count(struct f2fs_sb_info *sbi, int count_type)
 
 static inline void inode_inc_dirty_pages(struct inode *inode)
 {
-	percpu_counter_inc(&F2FS_I(inode)->dirty_pages);
+	atomic_inc(&F2FS_I(inode)->dirty_pages);
 	inc_page_count(F2FS_I_SB(inode), S_ISDIR(inode->i_mode) ?
 				F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA);
 }
 
 static inline void dec_page_count(struct f2fs_sb_info *sbi, int count_type)
 {
-	percpu_counter_dec(&sbi->nr_pages[count_type]);
+	atomic_dec(&sbi->nr_pages[count_type]);
 }
 
 static inline void inode_dec_dirty_pages(struct inode *inode)
@@ -1258,19 +1285,19 @@ static inline void inode_dec_dirty_pages(struct inode *inode)
 			!S_ISLNK(inode->i_mode))
 		return;
 
-	percpu_counter_dec(&F2FS_I(inode)->dirty_pages);
+	atomic_dec(&F2FS_I(inode)->dirty_pages);
 	dec_page_count(F2FS_I_SB(inode), S_ISDIR(inode->i_mode) ?
 				F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA);
 }
 
 static inline s64 get_pages(struct f2fs_sb_info *sbi, int count_type)
 {
-	return percpu_counter_sum_positive(&sbi->nr_pages[count_type]);
+	return atomic_read(&sbi->nr_pages[count_type]);
 }
 
-static inline s64 get_dirty_pages(struct inode *inode)
+static inline int get_dirty_pages(struct inode *inode)
 {
-	return percpu_counter_sum_positive(&F2FS_I(inode)->dirty_pages);
+	return atomic_read(&F2FS_I(inode)->dirty_pages);
 }
 
 static inline int get_blocktype_secs(struct f2fs_sb_info *sbi, int block_type)
@@ -1329,22 +1356,27 @@ static inline void *__bitmap_ptr(struct f2fs_sb_info *sbi, int flag)
 
 static inline block_t __start_cp_addr(struct f2fs_sb_info *sbi)
 {
-	block_t start_addr;
+	block_t start_addr = le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_blkaddr);
-	struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
-	unsigned long long ckpt_version = cur_cp_version(ckpt);
 
-	start_addr = le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_blkaddr);
+	if (sbi->cur_cp_pack == 2)
-
-	/*
-	 * odd numbered checkpoint should at cp segment 0
-	 * and even segment must be at cp segment 1
-	 */
-	if (!(ckpt_version & 1))
 		start_addr += sbi->blocks_per_seg;
-
 	return start_addr;
 }
 
+static inline block_t __start_cp_next_addr(struct f2fs_sb_info *sbi)
+{
+	block_t start_addr = le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_blkaddr);
+
+	if (sbi->cur_cp_pack == 1)
+		start_addr += sbi->blocks_per_seg;
+	return start_addr;
+}
+
+static inline void __set_cp_next_pack(struct f2fs_sb_info *sbi)
+{
+	sbi->cur_cp_pack = (sbi->cur_cp_pack == 1) ? 2 : 1;
+}
+
 static inline block_t __start_sum_addr(struct f2fs_sb_info *sbi)
 {
 	return le32_to_cpu(F2FS_CKPT(sbi)->cp_pack_start_sum);
@@ -1621,7 +1653,7 @@ static inline void __mark_inode_dirty_flag(struct inode *inode,
 			return;
 	case FI_DATA_EXIST:
 	case FI_INLINE_DOTS:
-		f2fs_mark_inode_dirty_sync(inode);
+		f2fs_mark_inode_dirty_sync(inode, true);
 	}
 }
 
@@ -1648,7 +1680,7 @@ static inline void set_acl_inode(struct inode *inode, umode_t mode)
 {
 	F2FS_I(inode)->i_acl_mode = mode;
 	set_inode_flag(inode, FI_ACL_MODE);
-	f2fs_mark_inode_dirty_sync(inode);
+	f2fs_mark_inode_dirty_sync(inode, false);
 }
 
 static inline void f2fs_i_links_write(struct inode *inode, bool inc)
@@ -1657,7 +1689,7 @@ static inline void f2fs_i_links_write(struct inode *inode, bool inc)
 		inc_nlink(inode);
 	else
 		drop_nlink(inode);
-	f2fs_mark_inode_dirty_sync(inode);
+	f2fs_mark_inode_dirty_sync(inode, true);
 }
 
 static inline void f2fs_i_blocks_write(struct inode *inode,
@@ -1668,7 +1700,7 @@ static inline void f2fs_i_blocks_write(struct inode *inode,
 
 	inode->i_blocks = add ? inode->i_blocks + diff :
 				inode->i_blocks - diff;
-	f2fs_mark_inode_dirty_sync(inode);
+	f2fs_mark_inode_dirty_sync(inode, true);
 	if (clean || recover)
 		set_inode_flag(inode, FI_AUTO_RECOVER);
 }
@@ -1682,34 +1714,27 @@ static inline void f2fs_i_size_write(struct inode *inode, loff_t i_size)
 		return;
 
 	i_size_write(inode, i_size);
-	f2fs_mark_inode_dirty_sync(inode);
+	f2fs_mark_inode_dirty_sync(inode, true);
 	if (clean || recover)
 		set_inode_flag(inode, FI_AUTO_RECOVER);
 }
 
-static inline bool f2fs_skip_inode_update(struct inode *inode)
-{
-	if (!is_inode_flag_set(inode, FI_AUTO_RECOVER))
-		return false;
-	return F2FS_I(inode)->last_disk_size == i_size_read(inode);
-}
-
 static inline void f2fs_i_depth_write(struct inode *inode, unsigned int depth)
 {
 	F2FS_I(inode)->i_current_depth = depth;
-	f2fs_mark_inode_dirty_sync(inode);
+	f2fs_mark_inode_dirty_sync(inode, true);
 }
 
 static inline void f2fs_i_xnid_write(struct inode *inode, nid_t xnid)
 {
 	F2FS_I(inode)->i_xattr_nid = xnid;
-	f2fs_mark_inode_dirty_sync(inode);
+	f2fs_mark_inode_dirty_sync(inode, true);
 }
 
 static inline void f2fs_i_pino_write(struct inode *inode, nid_t pino)
 {
 	F2FS_I(inode)->i_pino = pino;
-	f2fs_mark_inode_dirty_sync(inode);
+	f2fs_mark_inode_dirty_sync(inode, true);
 }
 
 static inline void get_inline_info(struct inode *inode, struct f2fs_inode *ri)
@@ -1837,13 +1862,31 @@ static inline int is_file(struct inode *inode, int type)
 static inline void set_file(struct inode *inode, int type)
 {
 	F2FS_I(inode)->i_advise |= type;
-	f2fs_mark_inode_dirty_sync(inode);
+	f2fs_mark_inode_dirty_sync(inode, true);
 }
 
 static inline void clear_file(struct inode *inode, int type)
 {
 	F2FS_I(inode)->i_advise &= ~type;
-	f2fs_mark_inode_dirty_sync(inode);
+	f2fs_mark_inode_dirty_sync(inode, true);
+}
+
+static inline bool f2fs_skip_inode_update(struct inode *inode, int dsync)
+{
+	if (dsync) {
+		struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+		bool ret;
+
+		spin_lock(&sbi->inode_lock[DIRTY_META]);
+		ret = list_empty(&F2FS_I(inode)->gdirty_list);
+		spin_unlock(&sbi->inode_lock[DIRTY_META]);
+		return ret;
+	}
+	if (!is_inode_flag_set(inode, FI_AUTO_RECOVER) ||
+			file_keep_isize(inode) ||
+			i_size_read(inode) & PAGE_MASK)
+		return false;
+	return F2FS_I(inode)->last_disk_size == i_size_read(inode);
 }
 
 static inline int f2fs_readonly(struct super_block *sb)
@@ -1955,7 +1998,7 @@ void set_de_type(struct f2fs_dir_entry *, umode_t);
 unsigned char get_de_type(struct f2fs_dir_entry *);
 struct f2fs_dir_entry *find_target_dentry(struct fscrypt_name *,
 			f2fs_hash_t, int *, struct f2fs_dentry_ptr *);
-bool f2fs_fill_dentries(struct dir_context *, struct f2fs_dentry_ptr *,
+int f2fs_fill_dentries(struct dir_context *, struct f2fs_dentry_ptr *,
 			unsigned int, struct fscrypt_str *);
 void do_make_empty_dir(struct inode *, struct inode *,
 			struct f2fs_dentry_ptr *);
@@ -1995,7 +2038,7 @@ static inline int f2fs_add_link(struct dentry *dentry, struct inode *inode)
 /*
  * super.c
  */
-int f2fs_inode_dirtied(struct inode *);
+int f2fs_inode_dirtied(struct inode *, bool);
 void f2fs_inode_synced(struct inode *);
 int f2fs_commit_super(struct f2fs_sb_info *, bool);
 int f2fs_sync_fs(struct super_block *, int);
@@ -2034,7 +2077,7 @@ void move_node_page(struct page *, int);
 int fsync_node_pages(struct f2fs_sb_info *, struct inode *,
 			struct writeback_control *, bool);
 int sync_node_pages(struct f2fs_sb_info *, struct writeback_control *);
-void build_free_nids(struct f2fs_sb_info *);
+void build_free_nids(struct f2fs_sb_info *, bool);
 bool alloc_nid(struct f2fs_sb_info *, nid_t *);
 void alloc_nid_done(struct f2fs_sb_info *, nid_t);
 void alloc_nid_failed(struct f2fs_sb_info *, nid_t);
@@ -2060,7 +2103,7 @@ void f2fs_balance_fs(struct f2fs_sb_info *, bool);
 void f2fs_balance_fs_bg(struct f2fs_sb_info *);
 int f2fs_issue_flush(struct f2fs_sb_info *);
 int create_flush_cmd_control(struct f2fs_sb_info *);
-void destroy_flush_cmd_control(struct f2fs_sb_info *);
+void destroy_flush_cmd_control(struct f2fs_sb_info *, bool);
 void invalidate_blocks(struct f2fs_sb_info *, block_t);
 bool is_checkpointed_data(struct f2fs_sb_info *, block_t);
 void refresh_sit_entry(struct f2fs_sb_info *, block_t, block_t);
@@ -2132,12 +2175,15 @@ void f2fs_submit_merged_bio_cond(struct f2fs_sb_info *, struct inode *,
 void f2fs_flush_merged_bios(struct f2fs_sb_info *);
 int f2fs_submit_page_bio(struct f2fs_io_info *);
 void f2fs_submit_page_mbio(struct f2fs_io_info *);
+struct block_device *f2fs_target_device(struct f2fs_sb_info *,
+				block_t, struct bio *);
+int f2fs_target_device_index(struct f2fs_sb_info *, block_t);
 void set_data_blkaddr(struct dnode_of_data *);
 void f2fs_update_data_blkaddr(struct dnode_of_data *, block_t);
 int reserve_new_blocks(struct dnode_of_data *, blkcnt_t);
 int reserve_new_block(struct dnode_of_data *);
 int f2fs_get_block(struct dnode_of_data *, pgoff_t);
-ssize_t f2fs_preallocate_blocks(struct kiocb *, struct iov_iter *);
+int f2fs_preallocate_blocks(struct kiocb *, struct iov_iter *);
 int f2fs_reserve_block(struct dnode_of_data *, pgoff_t);
 struct page *get_read_data_page(struct inode *, pgoff_t, int, bool);
 struct page *find_data_page(struct inode *, pgoff_t);
@@ -2160,7 +2206,7 @@ int f2fs_migrate_page(struct address_space *, struct page *, struct page *,
 int start_gc_thread(struct f2fs_sb_info *);
 void stop_gc_thread(struct f2fs_sb_info *);
 block_t start_bidx_of_node(unsigned int, struct inode *);
-int f2fs_gc(struct f2fs_sb_info *, bool);
+int f2fs_gc(struct f2fs_sb_info *, bool, bool);
 void build_gc_manager(struct f2fs_sb_info *);
 
 /*
@@ -2181,12 +2227,12 @@ struct f2fs_stat_info {
 	unsigned long long hit_largest, hit_cached, hit_rbtree;
 	unsigned long long hit_total, total_ext;
 	int ext_tree, zombie_tree, ext_node;
-	s64 ndirty_node, ndirty_dent, ndirty_meta, ndirty_data, ndirty_imeta;
+	int ndirty_node, ndirty_dent, ndirty_meta, ndirty_data, ndirty_imeta;
-	s64 inmem_pages;
+	int inmem_pages;
 	unsigned int ndirty_dirs, ndirty_files, ndirty_all;
-	int nats, dirty_nats, sits, dirty_sits, fnids;
+	int nats, dirty_nats, sits, dirty_sits, free_nids, alloc_nids;
 	int total_count, utilization;
-	int bg_gc, wb_bios;
+	int bg_gc, nr_wb_cp_data, nr_wb_data;
 	int inline_xattr, inline_inode, inline_dir, orphans;
 	unsigned int valid_count, valid_node_count, valid_inode_count, discard_blks;
 	unsigned int bimodal, avg_vblocks;
@@ -2412,9 +2458,30 @@ static inline int f2fs_sb_has_crypto(struct super_block *sb)
 	return F2FS_HAS_FEATURE(sb, F2FS_FEATURE_ENCRYPT);
 }
 
-static inline int f2fs_sb_mounted_hmsmr(struct super_block *sb)
+static inline int f2fs_sb_mounted_blkzoned(struct super_block *sb)
 {
-	return F2FS_HAS_FEATURE(sb, F2FS_FEATURE_HMSMR);
+	return F2FS_HAS_FEATURE(sb, F2FS_FEATURE_BLKZONED);
+}
+
+#ifdef CONFIG_BLK_DEV_ZONED
+static inline int get_blkz_type(struct f2fs_sb_info *sbi,
+			struct block_device *bdev, block_t blkaddr)
+{
+	unsigned int zno = blkaddr >> sbi->log_blocks_per_blkz;
+	int i;
+
+	for (i = 0; i < sbi->s_ndevs; i++)
+		if (FDEV(i).bdev == bdev)
+			return FDEV(i).blkz_type[zno];
+	return -EINVAL;
+}
+#endif
+
+static inline bool f2fs_discard_en(struct f2fs_sb_info *sbi)
+{
+	struct request_queue *q = bdev_get_queue(sbi->sb->s_bdev);
+
+	return blk_queue_discard(q) || f2fs_sb_mounted_blkzoned(sbi->sb);
 }
 
 static inline void set_opt_mode(struct f2fs_sb_info *sbi, unsigned int mt)

fs/f2fs/file.c

@@ -94,8 +94,6 @@ mapped:
 	if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode))
 		f2fs_wait_on_encrypted_page_writeback(sbi, dn.data_blkaddr);
 
-	/* if gced page is attached, don't write to cold segment */
-	clear_cold_data(page);
 out:
 	sb_end_pagefault(inode->i_sb);
 	f2fs_update_time(sbi, REQ_TIME);
@@ -210,7 +208,7 @@ static int f2fs_do_sync_file(struct file *file, loff_t start, loff_t end,
 	}
 
 	/* if the inode is dirty, let's recover all the time */
-	if (!datasync && !f2fs_skip_inode_update(inode)) {
+	if (!f2fs_skip_inode_update(inode, datasync)) {
 		f2fs_write_inode(inode, NULL);
 		goto go_write;
 	}
@@ -264,7 +262,7 @@ sync_nodes:
 	}
 
 	if (need_inode_block_update(sbi, ino)) {
-		f2fs_mark_inode_dirty_sync(inode);
+		f2fs_mark_inode_dirty_sync(inode, true);
 		f2fs_write_inode(inode, NULL);
 		goto sync_nodes;
 	}
@@ -632,7 +630,7 @@ int f2fs_truncate(struct inode *inode)
 		return err;
 
 	inode->i_mtime = inode->i_ctime = current_time(inode);
-	f2fs_mark_inode_dirty_sync(inode);
+	f2fs_mark_inode_dirty_sync(inode, false);
 	return 0;
 }
 
@@ -679,6 +677,7 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr)
 {
 	struct inode *inode = d_inode(dentry);
 	int err;
+	bool size_changed = false;
 
 	err = setattr_prepare(dentry, attr);
 	if (err)
@@ -694,7 +693,6 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr)
 			err = f2fs_truncate(inode);
 			if (err)
 				return err;
-			f2fs_balance_fs(F2FS_I_SB(inode), true);
 		} else {
 			/*
 			 * do not trim all blocks after i_size if target size is
@@ -710,6 +708,8 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr)
 			}
 			inode->i_mtime = inode->i_ctime = current_time(inode);
 		}
+
+		size_changed = true;
 	}
 
 	__setattr_copy(inode, attr);
@@ -722,7 +722,12 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr)
 		}
 	}
 
-	f2fs_mark_inode_dirty_sync(inode);
+	/* file size may changed here */
+	f2fs_mark_inode_dirty_sync(inode, size_changed);
+
+	/* inode change will produce dirty node pages flushed by checkpoint */
+	f2fs_balance_fs(F2FS_I_SB(inode), true);
+
 	return err;
 }
 
@@ -967,7 +972,7 @@ static int __clone_blkaddrs(struct inode *src_inode, struct inode *dst_inode,
 				new_size = (dst + i) << PAGE_SHIFT;
 				if (dst_inode->i_size < new_size)
 					f2fs_i_size_write(dst_inode, new_size);
-			} while ((do_replace[i] || blkaddr[i] == NULL_ADDR) && --ilen);
+			} while (--ilen && (do_replace[i] || blkaddr[i] == NULL_ADDR));
 
 			f2fs_put_dnode(&dn);
 		} else {
@@ -1218,6 +1223,9 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len,
 			ret = f2fs_do_zero_range(&dn, index, end);
 			f2fs_put_dnode(&dn);
 			f2fs_unlock_op(sbi);
+
+			f2fs_balance_fs(sbi, dn.node_changed);
+
 			if (ret)
 				goto out;
 
@@ -1313,15 +1321,15 @@ static int expand_inode_data(struct inode *inode, loff_t offset,
 	pgoff_t pg_end;
 	loff_t new_size = i_size_read(inode);
 	loff_t off_end;
-	int ret;
+	int err;
 
-	ret = inode_newsize_ok(inode, (len + offset));
+	err = inode_newsize_ok(inode, (len + offset));
-	if (ret)
+	if (err)
-		return ret;
+		return err;
 
-	ret = f2fs_convert_inline_inode(inode);
+	err = f2fs_convert_inline_inode(inode);
-	if (ret)
+	if (err)
-		return ret;
+		return err;
 
 	f2fs_balance_fs(sbi, true);
 
@@ -1333,12 +1341,12 @@ static int expand_inode_data(struct inode *inode, loff_t offset,
 	if (off_end)
 		map.m_len++;
 
-	ret = f2fs_map_blocks(inode, &map, 1, F2FS_GET_BLOCK_PRE_AIO);
+	err = f2fs_map_blocks(inode, &map, 1, F2FS_GET_BLOCK_PRE_AIO);
-	if (ret) {
+	if (err) {
 		pgoff_t last_off;
 
 		if (!map.m_len)
-			return ret;
+			return err;
 
 		last_off = map.m_lblk + map.m_len - 1;
 
@@ -1352,7 +1360,7 @@ static int expand_inode_data(struct inode *inode, loff_t offset,
 	if (!(mode & FALLOC_FL_KEEP_SIZE) && i_size_read(inode) < new_size)
 		f2fs_i_size_write(inode, new_size);
 
-	return ret;
+	return err;
 }
 
 static long f2fs_fallocate(struct file *file, int mode,
@@ -1393,7 +1401,9 @@ static long f2fs_fallocate(struct file *file, int mode,
 
 	if (!ret) {
 		inode->i_mtime = inode->i_ctime = current_time(inode);
-		f2fs_mark_inode_dirty_sync(inode);
+		f2fs_mark_inode_dirty_sync(inode, false);
+		if (mode & FALLOC_FL_KEEP_SIZE)
+			file_set_keep_isize(inode);
 		f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
 	}
 
@@ -1526,7 +1536,7 @@ static int f2fs_ioc_start_atomic_write(struct file *filp)
 		goto out;
 
 	f2fs_msg(F2FS_I_SB(inode)->sb, KERN_WARNING,
-		"Unexpected flush for atomic writes: ino=%lu, npages=%lld",
+		"Unexpected flush for atomic writes: ino=%lu, npages=%u",
 					inode->i_ino, get_dirty_pages(inode));
 	ret = filemap_write_and_wait_range(inode->i_mapping, 0, LLONG_MAX);
 	if (ret)
@@ -1842,7 +1852,7 @@ static int f2fs_ioc_gc(struct file *filp, unsigned long arg)
 		mutex_lock(&sbi->gc_mutex);
 	}
 
-	ret = f2fs_gc(sbi, sync);
+	ret = f2fs_gc(sbi, sync, true);
 out:
 	mnt_drop_write_file(filp);
 	return ret;
@@ -2256,12 +2266,15 @@ static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	inode_lock(inode);
 	ret = generic_write_checks(iocb, from);
 	if (ret > 0) {
-		ret = f2fs_preallocate_blocks(iocb, from);
+		int err = f2fs_preallocate_blocks(iocb, from);
-		if (!ret) {
+
-			blk_start_plug(&plug);
+		if (err) {
-			ret = __generic_file_write_iter(iocb, from);
+			inode_unlock(inode);
-			blk_finish_plug(&plug);
+			return err;
 		}
+		blk_start_plug(&plug);
+		ret = __generic_file_write_iter(iocb, from);
+		blk_finish_plug(&plug);
 	}
 	inode_unlock(inode);
 

fs/f2fs/gc.c

@@ -82,7 +82,7 @@ static int gc_thread_func(void *data)
 		stat_inc_bggc_count(sbi);
 
 		/* if return value is not zero, no victim was selected */
-		if (f2fs_gc(sbi, test_opt(sbi, FORCE_FG_GC)))
+		if (f2fs_gc(sbi, test_opt(sbi, FORCE_FG_GC), true))
 			wait_ms = gc_th->no_gc_sleep_time;
 
 		trace_f2fs_background_gc(sbi->sb, wait_ms,
@@ -544,7 +544,8 @@ static bool is_alive(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
 	return true;
 }
 
-static void move_encrypted_block(struct inode *inode, block_t bidx)
+static void move_encrypted_block(struct inode *inode, block_t bidx,
+							unsigned int segno, int off)
 {
 	struct f2fs_io_info fio = {
 		.sbi = F2FS_I_SB(inode),
@@ -565,6 +566,9 @@ static void move_encrypted_block(struct inode *inode, block_t bidx)
 	if (!page)
 		return;
 
+	if (!check_valid_map(F2FS_I_SB(inode), segno, off))
+		goto out;
+
 	set_new_dnode(&dn, inode, NULL, NULL, 0);
 	err = get_dnode_of_data(&dn, bidx, LOOKUP_NODE);
 	if (err)
@@ -645,7 +649,8 @@ out:
 	f2fs_put_page(page, 1);
 }
 
-static void move_data_page(struct inode *inode, block_t bidx, int gc_type)
+static void move_data_page(struct inode *inode, block_t bidx, int gc_type,
+							unsigned int segno, int off)
 {
 	struct page *page;
 
@@ -653,6 +658,9 @@ static void move_data_page(struct inode *inode, block_t bidx, int gc_type)
 	if (IS_ERR(page))
 		return;
 
+	if (!check_valid_map(F2FS_I_SB(inode), segno, off))
+		goto out;
+
 	if (gc_type == BG_GC) {
 		if (PageWriteback(page))
 			goto out;
@@ -673,8 +681,10 @@ static void move_data_page(struct inode *inode, block_t bidx, int gc_type)
 retry:
 		set_page_dirty(page);
 		f2fs_wait_on_page_writeback(page, DATA, true);
-		if (clear_page_dirty_for_io(page))
+		if (clear_page_dirty_for_io(page)) {
 			inode_dec_dirty_pages(inode);
+			remove_dirty_inode(inode);
+		}
 
 		set_cold_data(page);
 
@@ -683,8 +693,6 @@ retry:
 			congestion_wait(BLK_RW_ASYNC, HZ/50);
 			goto retry;
 		}
-
-		clear_cold_data(page);
 	}
 out:
 	f2fs_put_page(page, 1);
@@ -794,9 +802,9 @@ next_step:
 			start_bidx = start_bidx_of_node(nofs, inode)
 								+ ofs_in_node;
 			if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode))
-				move_encrypted_block(inode, start_bidx);
+				move_encrypted_block(inode, start_bidx, segno, off);
 			else
-				move_data_page(inode, start_bidx, gc_type);
+				move_data_page(inode, start_bidx, gc_type, segno, off);
 
 			if (locked) {
 				up_write(&fi->dio_rwsem[WRITE]);
@@ -899,7 +907,7 @@ next:
 	return sec_freed;
 }
 
-int f2fs_gc(struct f2fs_sb_info *sbi, bool sync)
+int f2fs_gc(struct f2fs_sb_info *sbi, bool sync, bool background)
 {
 	unsigned int segno;
 	int gc_type = sync ? FG_GC : BG_GC;
@@ -940,6 +948,9 @@ gc_more:
 			if (ret)
 				goto stop;
 		}
+	} else if (gc_type == BG_GC && !background) {
+		/* f2fs_balance_fs doesn't need to do BG_GC in critical path. */
+		goto stop;
 	}
 
 	if (segno == NULL_SEGNO && !__get_victim(sbi, &segno, gc_type))

fs/f2fs/inline.c

@@ -137,8 +137,10 @@ int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page)
 	fio.old_blkaddr = dn->data_blkaddr;
 	write_data_page(dn, &fio);
 	f2fs_wait_on_page_writeback(page, DATA, true);
-	if (dirty)
+	if (dirty) {
 		inode_dec_dirty_pages(dn->inode);
+		remove_dirty_inode(dn->inode);
+	}
 
 	/* this converted inline_data should be recovered. */
 	set_inode_flag(dn->inode, FI_APPEND_WRITE);
@@ -419,7 +421,7 @@ static int f2fs_add_inline_entries(struct inode *dir,
 		}
 
 		new_name.name = d.filename[bit_pos];
-		new_name.len = de->name_len;
+		new_name.len = le16_to_cpu(de->name_len);
 
 		ino = le32_to_cpu(de->ino);
 		fake_mode = get_de_type(de) << S_SHIFT;
@@ -573,7 +575,7 @@ void f2fs_delete_inline_entry(struct f2fs_dir_entry *dentry, struct page *page,
 	f2fs_put_page(page, 1);
 
 	dir->i_ctime = dir->i_mtime = current_time(dir);
-	f2fs_mark_inode_dirty_sync(dir);
+	f2fs_mark_inode_dirty_sync(dir, false);
 
 	if (inode)
 		f2fs_drop_nlink(dir, inode);
@@ -610,6 +612,7 @@ int f2fs_read_inline_dir(struct file *file, struct dir_context *ctx,
 	struct f2fs_inline_dentry *inline_dentry = NULL;
 	struct page *ipage = NULL;
 	struct f2fs_dentry_ptr d;
+	int err;
 
 	if (ctx->pos == NR_INLINE_DENTRY)
 		return 0;
@@ -622,11 +625,12 @@ int f2fs_read_inline_dir(struct file *file, struct dir_context *ctx,
 
 	make_dentry_ptr(inode, &d, (void *)inline_dentry, 2);
 
-	if (!f2fs_fill_dentries(ctx, &d, 0, fstr))
+	err = f2fs_fill_dentries(ctx, &d, 0, fstr);
+	if (!err)
 		ctx->pos = NR_INLINE_DENTRY;
 
 	f2fs_put_page(ipage, 1);
-	return 0;
+	return err < 0 ? err : 0;
 }
 
 int f2fs_inline_data_fiemap(struct inode *inode,

fs/f2fs/inode.c

@@ -19,10 +19,11 @@
 
 #include <trace/events/f2fs.h>
 
-void f2fs_mark_inode_dirty_sync(struct inode *inode)
+void f2fs_mark_inode_dirty_sync(struct inode *inode, bool sync)
 {
-	if (f2fs_inode_dirtied(inode))
+	if (f2fs_inode_dirtied(inode, sync))
 		return;
+
 	mark_inode_dirty_sync(inode);
 }
 
@@ -43,7 +44,7 @@ void f2fs_set_inode_flags(struct inode *inode)
 		new_fl |= S_DIRSYNC;
 	inode_set_flags(inode, new_fl,
 			S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC);
-	f2fs_mark_inode_dirty_sync(inode);
+	f2fs_mark_inode_dirty_sync(inode, false);
 }
 
 static void __get_inode_rdev(struct inode *inode, struct f2fs_inode *ri)
@@ -252,6 +253,7 @@ retry:
 int update_inode(struct inode *inode, struct page *node_page)
 {
 	struct f2fs_inode *ri;
+	struct extent_tree *et = F2FS_I(inode)->extent_tree;
 
 	f2fs_inode_synced(inode);
 
@@ -267,11 +269,13 @@ int update_inode(struct inode *inode, struct page *node_page)
 	ri->i_size = cpu_to_le64(i_size_read(inode));
 	ri->i_blocks = cpu_to_le64(inode->i_blocks);
 
-	if (F2FS_I(inode)->extent_tree)
+	if (et) {
-		set_raw_extent(&F2FS_I(inode)->extent_tree->largest,
+		read_lock(&et->lock);
-							&ri->i_ext);
+		set_raw_extent(&et->largest, &ri->i_ext);
-	else
+		read_unlock(&et->lock);
+	} else {
 		memset(&ri->i_ext, 0, sizeof(ri->i_ext));
+	}
 	set_raw_inline(inode, ri);
 
 	ri->i_atime = cpu_to_le64(inode->i_atime.tv_sec);
@@ -335,7 +339,7 @@ int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc)
 	 * We need to balance fs here to prevent from producing dirty node pages
 	 * during the urgent cleaning time when runing out of free sections.
 	 */
-	if (update_inode_page(inode))
+	if (update_inode_page(inode) && wbc && wbc->nr_to_write)
 		f2fs_balance_fs(sbi, true);
 	return 0;
 }
@@ -373,6 +377,9 @@ void f2fs_evict_inode(struct inode *inode)
 		goto no_delete;
 #endif
 
+	remove_ino_entry(sbi, inode->i_ino, APPEND_INO);
+	remove_ino_entry(sbi, inode->i_ino, UPDATE_INO);
+
 	sb_start_intwrite(inode->i_sb);
 	set_inode_flag(inode, FI_NO_ALLOC);
 	i_size_write(inode, 0);
@@ -384,6 +391,8 @@ retry:
 		f2fs_lock_op(sbi);
 		err = remove_inode_page(inode);
 		f2fs_unlock_op(sbi);
+		if (err == -ENOENT)
+			err = 0;
 	}
 
 	/* give more chances, if ENOMEM case */
@@ -403,10 +412,12 @@ no_delete:
 	invalidate_mapping_pages(NODE_MAPPING(sbi), inode->i_ino, inode->i_ino);
 	if (xnid)
 		invalidate_mapping_pages(NODE_MAPPING(sbi), xnid, xnid);
-	if (is_inode_flag_set(inode, FI_APPEND_WRITE))
+	if (inode->i_nlink) {
-		add_ino_entry(sbi, inode->i_ino, APPEND_INO);
+		if (is_inode_flag_set(inode, FI_APPEND_WRITE))
-	if (is_inode_flag_set(inode, FI_UPDATE_WRITE))
+			add_ino_entry(sbi, inode->i_ino, APPEND_INO);
-		add_ino_entry(sbi, inode->i_ino, UPDATE_INO);
+		if (is_inode_flag_set(inode, FI_UPDATE_WRITE))
+			add_ino_entry(sbi, inode->i_ino, UPDATE_INO);
+	}
 	if (is_inode_flag_set(inode, FI_FREE_NID)) {
 		alloc_nid_failed(sbi, inode->i_ino);
 		clear_inode_flag(inode, FI_FREE_NID);
@@ -424,6 +435,18 @@ void handle_failed_inode(struct inode *inode)
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	struct node_info ni;
 
+	/*
+	 * clear nlink of inode in order to release resource of inode
+	 * immediately.
+	 */
+	clear_nlink(inode);
+
+	/*
+	 * we must call this to avoid inode being remained as dirty, resulting
+	 * in a panic when flushing dirty inodes in gdirty_list.
+	 */
+	update_inode_page(inode);
+
 	/* don't make bad inode, since it becomes a regular file. */
 	unlock_new_inode(inode);
 

fs/f2fs/namei.c

@@ -778,7 +778,7 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	up_write(&F2FS_I(old_inode)->i_sem);
 
 	old_inode->i_ctime = current_time(old_inode);
-	f2fs_mark_inode_dirty_sync(old_inode);
+	f2fs_mark_inode_dirty_sync(old_inode, false);
 
 	f2fs_delete_entry(old_entry, old_page, old_dir, NULL);
 
@@ -938,7 +938,7 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry,
 		f2fs_i_links_write(old_dir, old_nlink > 0);
 		up_write(&F2FS_I(old_dir)->i_sem);
 	}
-	f2fs_mark_inode_dirty_sync(old_dir);
+	f2fs_mark_inode_dirty_sync(old_dir, false);
 
 	/* update directory entry info of new dir inode */
 	f2fs_set_link(new_dir, new_entry, new_page, old_inode);
@@ -953,7 +953,7 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry,
 		f2fs_i_links_write(new_dir, new_nlink > 0);
 		up_write(&F2FS_I(new_dir)->i_sem);
 	}
-	f2fs_mark_inode_dirty_sync(new_dir);
+	f2fs_mark_inode_dirty_sync(new_dir, false);
 
 	f2fs_unlock_op(sbi);
 

fs/f2fs/node.c

@@ -45,8 +45,8 @@ bool available_free_memory(struct f2fs_sb_info *sbi, int type)
 	 * give 25%, 25%, 50%, 50%, 50% memory for each components respectively
 	 */
 	if (type == FREE_NIDS) {
-		mem_size = (nm_i->fcnt * sizeof(struct free_nid)) >>
+		mem_size = (nm_i->nid_cnt[FREE_NID_LIST] *
-							PAGE_SHIFT;
+				sizeof(struct free_nid)) >> PAGE_SHIFT;
 		res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 2);
 	} else if (type == NAT_ENTRIES) {
 		mem_size = (nm_i->nat_cnt * sizeof(struct nat_entry)) >>
@@ -270,8 +270,9 @@ static void cache_nat_entry(struct f2fs_sb_info *sbi, nid_t nid,
 		e = grab_nat_entry(nm_i, nid);
 		node_info_from_raw_nat(&e->ni, ne);
 	} else {
-		f2fs_bug_on(sbi, nat_get_ino(e) != ne->ino ||
+		f2fs_bug_on(sbi, nat_get_ino(e) != le32_to_cpu(ne->ino) ||
-				nat_get_blkaddr(e) != ne->block_addr ||
+				nat_get_blkaddr(e) !=
+					le32_to_cpu(ne->block_addr) ||
 				nat_get_version(e) != ne->version);
 	}
 }
@@ -1204,6 +1205,7 @@ static void flush_inline_data(struct f2fs_sb_info *sbi, nid_t ino)
 
 	ret = f2fs_write_inline_data(inode, page);
 	inode_dec_dirty_pages(inode);
+	remove_dirty_inode(inode);
 	if (ret)
 		set_page_dirty(page);
 page_out:
@@ -1338,7 +1340,8 @@ retry:
 			if (unlikely(f2fs_cp_error(sbi))) {
 				f2fs_put_page(last_page, 0);
 				pagevec_release(&pvec);
-				return -EIO;
+				ret = -EIO;
+				goto out;
 			}
 
 			if (!IS_DNODE(page) || !is_cold_node(page))
@@ -1407,11 +1410,12 @@ continue_unlock:
 			"Retry to write fsync mark: ino=%u, idx=%lx",
 					ino, last_page->index);
 		lock_page(last_page);
+		f2fs_wait_on_page_writeback(last_page, NODE, true);
 		set_page_dirty(last_page);
 		unlock_page(last_page);
 		goto retry;
 	}
-
+out:
 	if (nwritten)
 		f2fs_submit_merged_bio_cond(sbi, NULL, NULL, ino, NODE, WRITE);
 	return ret ? -EIO: 0;
@@ -1692,11 +1696,35 @@ static struct free_nid *__lookup_free_nid_list(struct f2fs_nm_info *nm_i,
 	return radix_tree_lookup(&nm_i->free_nid_root, n);
 }
 
-static void __del_from_free_nid_list(struct f2fs_nm_info *nm_i,
+static int __insert_nid_to_list(struct f2fs_sb_info *sbi,
-						struct free_nid *i)
+			struct free_nid *i, enum nid_list list, bool new)
 {
+	struct f2fs_nm_info *nm_i = NM_I(sbi);
+
+	if (new) {
+		int err = radix_tree_insert(&nm_i->free_nid_root, i->nid, i);
+		if (err)
+			return err;
+	}
+
+	f2fs_bug_on(sbi, list == FREE_NID_LIST ? i->state != NID_NEW :
+						i->state != NID_ALLOC);
+	nm_i->nid_cnt[list]++;
+	list_add_tail(&i->list, &nm_i->nid_list[list]);
+	return 0;
+}
+
+static void __remove_nid_from_list(struct f2fs_sb_info *sbi,
+			struct free_nid *i, enum nid_list list, bool reuse)
+{
+	struct f2fs_nm_info *nm_i = NM_I(sbi);
+
+	f2fs_bug_on(sbi, list == FREE_NID_LIST ? i->state != NID_NEW :
+						i->state != NID_ALLOC);
+	nm_i->nid_cnt[list]--;
 	list_del(&i->list);
-	radix_tree_delete(&nm_i->free_nid_root, i->nid);
+	if (!reuse)
+		radix_tree_delete(&nm_i->free_nid_root, i->nid);
 }
 
 static int add_free_nid(struct f2fs_sb_info *sbi, nid_t nid, bool build)
@@ -1704,9 +1732,7 @@ static int add_free_nid(struct f2fs_sb_info *sbi, nid_t nid, bool build)
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
 	struct free_nid *i;
 	struct nat_entry *ne;
-
+	int err;
-	if (!available_free_memory(sbi, FREE_NIDS))
-		return -1;
 
 	/* 0 nid should not be used */
 	if (unlikely(nid == 0))
@@ -1729,33 +1755,30 @@ static int add_free_nid(struct f2fs_sb_info *sbi, nid_t nid, bool build)
 		return 0;
 	}
 
-	spin_lock(&nm_i->free_nid_list_lock);
+	spin_lock(&nm_i->nid_list_lock);
-	if (radix_tree_insert(&nm_i->free_nid_root, i->nid, i)) {
+	err = __insert_nid_to_list(sbi, i, FREE_NID_LIST, true);
-		spin_unlock(&nm_i->free_nid_list_lock);
+	spin_unlock(&nm_i->nid_list_lock);
-		radix_tree_preload_end();
+	radix_tree_preload_end();
+	if (err) {
 		kmem_cache_free(free_nid_slab, i);
 		return 0;
 	}
-	list_add_tail(&i->list, &nm_i->free_nid_list);
-	nm_i->fcnt++;
-	spin_unlock(&nm_i->free_nid_list_lock);
-	radix_tree_preload_end();
 	return 1;
 }
 
-static void remove_free_nid(struct f2fs_nm_info *nm_i, nid_t nid)
+static void remove_free_nid(struct f2fs_sb_info *sbi, nid_t nid)
 {
+	struct f2fs_nm_info *nm_i = NM_I(sbi);
 	struct free_nid *i;
 	bool need_free = false;
 
-	spin_lock(&nm_i->free_nid_list_lock);
+	spin_lock(&nm_i->nid_list_lock);
 	i = __lookup_free_nid_list(nm_i, nid);
 	if (i && i->state == NID_NEW) {
-		__del_from_free_nid_list(nm_i, i);
+		__remove_nid_from_list(sbi, i, FREE_NID_LIST, false);
-		nm_i->fcnt--;
 		need_free = true;
 	}
-	spin_unlock(&nm_i->free_nid_list_lock);
+	spin_unlock(&nm_i->nid_list_lock);
 
 	if (need_free)
 		kmem_cache_free(free_nid_slab, i);
@@ -1778,14 +1801,12 @@ static void scan_nat_page(struct f2fs_sb_info *sbi,
 
 		blk_addr = le32_to_cpu(nat_blk->entries[i].block_addr);
 		f2fs_bug_on(sbi, blk_addr == NEW_ADDR);
-		if (blk_addr == NULL_ADDR) {
+		if (blk_addr == NULL_ADDR)
-			if (add_free_nid(sbi, start_nid, true) < 0)
+			add_free_nid(sbi, start_nid, true);
-				break;
-		}
 	}
 }
 
-void build_free_nids(struct f2fs_sb_info *sbi)
+static void __build_free_nids(struct f2fs_sb_info *sbi, bool sync)
 {
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
 	struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA);
@@ -1794,7 +1815,10 @@ void build_free_nids(struct f2fs_sb_info *sbi)
 	nid_t nid = nm_i->next_scan_nid;
 
 	/* Enough entries */
-	if (nm_i->fcnt >= NAT_ENTRY_PER_BLOCK)
+	if (nm_i->nid_cnt[FREE_NID_LIST] >= NAT_ENTRY_PER_BLOCK)
+		return;
+
+	if (!sync && !available_free_memory(sbi, FREE_NIDS))
 		return;
 
 	/* readahead nat pages to be scanned */
@@ -1830,7 +1854,7 @@ void build_free_nids(struct f2fs_sb_info *sbi)
 		if (addr == NULL_ADDR)
 			add_free_nid(sbi, nid, true);
 		else
-			remove_free_nid(nm_i, nid);
+			remove_free_nid(sbi, nid);
 	}
 	up_read(&curseg->journal_rwsem);
 	up_read(&nm_i->nat_tree_lock);
@@ -1839,6 +1863,13 @@ void build_free_nids(struct f2fs_sb_info *sbi)
 					nm_i->ra_nid_pages, META_NAT, false);
 }
 
+void build_free_nids(struct f2fs_sb_info *sbi, bool sync)
+{
+	mutex_lock(&NM_I(sbi)->build_lock);
+	__build_free_nids(sbi, sync);
+	mutex_unlock(&NM_I(sbi)->build_lock);
+}
+
 /*
  * If this function returns success, caller can obtain a new nid
  * from second parameter of this function.
@@ -1853,31 +1884,31 @@ retry:
 	if (time_to_inject(sbi, FAULT_ALLOC_NID))
 		return false;
 #endif
-	if (unlikely(sbi->total_valid_node_count + 1 > nm_i->available_nids))
+	spin_lock(&nm_i->nid_list_lock);
-		return false;
 
-	spin_lock(&nm_i->free_nid_list_lock);
+	if (unlikely(nm_i->available_nids == 0)) {
+		spin_unlock(&nm_i->nid_list_lock);
+		return false;
+	}
 
 	/* We should not use stale free nids created by build_free_nids */
-	if (nm_i->fcnt && !on_build_free_nids(nm_i)) {
+	if (nm_i->nid_cnt[FREE_NID_LIST] && !on_build_free_nids(nm_i)) {
-		f2fs_bug_on(sbi, list_empty(&nm_i->free_nid_list));
+		f2fs_bug_on(sbi, list_empty(&nm_i->nid_list[FREE_NID_LIST]));
-		list_for_each_entry(i, &nm_i->free_nid_list, list)
+		i = list_first_entry(&nm_i->nid_list[FREE_NID_LIST],
-			if (i->state == NID_NEW)
+					struct free_nid, list);
-				break;
-
-		f2fs_bug_on(sbi, i->state != NID_NEW);
 		*nid = i->nid;
+
+		__remove_nid_from_list(sbi, i, FREE_NID_LIST, true);
 		i->state = NID_ALLOC;
-		nm_i->fcnt--;
+		__insert_nid_to_list(sbi, i, ALLOC_NID_LIST, false);
-		spin_unlock(&nm_i->free_nid_list_lock);
+		nm_i->available_nids--;
+		spin_unlock(&nm_i->nid_list_lock);
 		return true;
 	}
-	spin_unlock(&nm_i->free_nid_list_lock);
+	spin_unlock(&nm_i->nid_list_lock);
 
 	/* Let's scan nat pages and its caches to get free nids */
-	mutex_lock(&nm_i->build_lock);
+	build_free_nids(sbi, true);
-	build_free_nids(sbi);
-	mutex_unlock(&nm_i->build_lock);
 	goto retry;
 }
 
@@ -1889,11 +1920,11 @@ void alloc_nid_done(struct f2fs_sb_info *sbi, nid_t nid)
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
 	struct free_nid *i;
 
-	spin_lock(&nm_i->free_nid_list_lock);
+	spin_lock(&nm_i->nid_list_lock);
 	i = __lookup_free_nid_list(nm_i, nid);
-	f2fs_bug_on(sbi, !i || i->state != NID_ALLOC);
+	f2fs_bug_on(sbi, !i);
-	__del_from_free_nid_list(nm_i, i);
+	__remove_nid_from_list(sbi, i, ALLOC_NID_LIST, false);
-	spin_unlock(&nm_i->free_nid_list_lock);
+	spin_unlock(&nm_i->nid_list_lock);
 
 	kmem_cache_free(free_nid_slab, i);
 }
@@ -1910,17 +1941,22 @@ void alloc_nid_failed(struct f2fs_sb_info *sbi, nid_t nid)
 	if (!nid)
 		return;
 
-	spin_lock(&nm_i->free_nid_list_lock);
+	spin_lock(&nm_i->nid_list_lock);
 	i = __lookup_free_nid_list(nm_i, nid);
-	f2fs_bug_on(sbi, !i || i->state != NID_ALLOC);
+	f2fs_bug_on(sbi, !i);
+
 	if (!available_free_memory(sbi, FREE_NIDS)) {
-		__del_from_free_nid_list(nm_i, i);
+		__remove_nid_from_list(sbi, i, ALLOC_NID_LIST, false);
 		need_free = true;
 	} else {
+		__remove_nid_from_list(sbi, i, ALLOC_NID_LIST, true);
 		i->state = NID_NEW;
-		nm_i->fcnt++;
+		__insert_nid_to_list(sbi, i, FREE_NID_LIST, false);
 	}
-	spin_unlock(&nm_i->free_nid_list_lock);
+
+	nm_i->available_nids++;
+
+	spin_unlock(&nm_i->nid_list_lock);
 
 	if (need_free)
 		kmem_cache_free(free_nid_slab, i);
@@ -1932,24 +1968,24 @@ int try_to_free_nids(struct f2fs_sb_info *sbi, int nr_shrink)
 	struct free_nid *i, *next;
 	int nr = nr_shrink;
 
-	if (nm_i->fcnt <= MAX_FREE_NIDS)
+	if (nm_i->nid_cnt[FREE_NID_LIST] <= MAX_FREE_NIDS)
 		return 0;
 
 	if (!mutex_trylock(&nm_i->build_lock))
 		return 0;
 
-	spin_lock(&nm_i->free_nid_list_lock);
+	spin_lock(&nm_i->nid_list_lock);
-	list_for_each_entry_safe(i, next, &nm_i->free_nid_list, list) {
+	list_for_each_entry_safe(i, next, &nm_i->nid_list[FREE_NID_LIST],
-		if (nr_shrink <= 0 || nm_i->fcnt <= MAX_FREE_NIDS)
+									list) {
+		if (nr_shrink <= 0 ||
+				nm_i->nid_cnt[FREE_NID_LIST] <= MAX_FREE_NIDS)
 			break;
-		if (i->state == NID_ALLOC)
+
-			continue;
+		__remove_nid_from_list(sbi, i, FREE_NID_LIST, false);
-		__del_from_free_nid_list(nm_i, i);
 		kmem_cache_free(free_nid_slab, i);
-		nm_i->fcnt--;
 		nr_shrink--;
 	}
-	spin_unlock(&nm_i->free_nid_list_lock);
+	spin_unlock(&nm_i->nid_list_lock);
 	mutex_unlock(&nm_i->build_lock);
 
 	return nr - nr_shrink;
@@ -2005,7 +2041,7 @@ recover_xnid:
 	if (unlikely(!inc_valid_node_count(sbi, inode)))
 		f2fs_bug_on(sbi, 1);
 
-	remove_free_nid(NM_I(sbi), new_xnid);
+	remove_free_nid(sbi, new_xnid);
 	get_node_info(sbi, new_xnid, &ni);
 	ni.ino = inode->i_ino;
 	set_node_addr(sbi, &ni, NEW_ADDR, false);
@@ -2035,7 +2071,7 @@ retry:
 	}
 
 	/* Should not use this inode from free nid list */
-	remove_free_nid(NM_I(sbi), ino);
+	remove_free_nid(sbi, ino);
 
 	if (!PageUptodate(ipage))
 		SetPageUptodate(ipage);
@@ -2069,7 +2105,6 @@ int restore_node_summary(struct f2fs_sb_info *sbi,
 	struct f2fs_node *rn;
 	struct f2fs_summary *sum_entry;
 	block_t addr;
-	int bio_blocks = MAX_BIO_BLOCKS(sbi);
 	int i, idx, last_offset, nrpages;
 
 	/* scan the node segment */
@@ -2078,7 +2113,7 @@ int restore_node_summary(struct f2fs_sb_info *sbi,
 	sum_entry = &sum->entries[0];
 
 	for (i = 0; i < last_offset; i += nrpages, addr += nrpages) {
-		nrpages = min(last_offset - i, bio_blocks);
+		nrpages = min(last_offset - i, BIO_MAX_PAGES);
 
 		/* readahead node pages */
 		ra_meta_pages(sbi, addr, nrpages, META_POR, true);
@@ -2120,6 +2155,19 @@ static void remove_nats_in_journal(struct f2fs_sb_info *sbi)
 			ne = grab_nat_entry(nm_i, nid);
 			node_info_from_raw_nat(&ne->ni, &raw_ne);
 		}
+
+		/*
+		 * if a free nat in journal has not been used after last
+		 * checkpoint, we should remove it from available nids,
+		 * since later we will add it again.
+		 */
+		if (!get_nat_flag(ne, IS_DIRTY) &&
+				le32_to_cpu(raw_ne.block_addr) == NULL_ADDR) {
+			spin_lock(&nm_i->nid_list_lock);
+			nm_i->available_nids--;
+			spin_unlock(&nm_i->nid_list_lock);
+		}
+
 		__set_nat_cache_dirty(nm_i, ne);
 	}
 	update_nats_in_cursum(journal, -i);
@@ -2192,8 +2240,12 @@ static void __flush_nat_entry_set(struct f2fs_sb_info *sbi,
 		raw_nat_from_node_info(raw_ne, &ne->ni);
 		nat_reset_flag(ne);
 		__clear_nat_cache_dirty(NM_I(sbi), ne);
-		if (nat_get_blkaddr(ne) == NULL_ADDR)
+		if (nat_get_blkaddr(ne) == NULL_ADDR) {
 			add_free_nid(sbi, nid, false);
+			spin_lock(&NM_I(sbi)->nid_list_lock);
+			NM_I(sbi)->available_nids++;
+			spin_unlock(&NM_I(sbi)->nid_list_lock);
+		}
 	}
 
 	if (to_journal)
@@ -2268,21 +2320,24 @@ static int init_node_manager(struct f2fs_sb_info *sbi)
 	nm_i->max_nid = NAT_ENTRY_PER_BLOCK * nat_blocks;
 
 	/* not used nids: 0, node, meta, (and root counted as valid node) */
-	nm_i->available_nids = nm_i->max_nid - F2FS_RESERVED_NODE_NUM;
+	nm_i->available_nids = nm_i->max_nid - sbi->total_valid_node_count -
-	nm_i->fcnt = 0;
+							F2FS_RESERVED_NODE_NUM;
+	nm_i->nid_cnt[FREE_NID_LIST] = 0;
+	nm_i->nid_cnt[ALLOC_NID_LIST] = 0;
 	nm_i->nat_cnt = 0;
 	nm_i->ram_thresh = DEF_RAM_THRESHOLD;
 	nm_i->ra_nid_pages = DEF_RA_NID_PAGES;
 	nm_i->dirty_nats_ratio = DEF_DIRTY_NAT_RATIO_THRESHOLD;
 
 	INIT_RADIX_TREE(&nm_i->free_nid_root, GFP_ATOMIC);
-	INIT_LIST_HEAD(&nm_i->free_nid_list);
+	INIT_LIST_HEAD(&nm_i->nid_list[FREE_NID_LIST]);
+	INIT_LIST_HEAD(&nm_i->nid_list[ALLOC_NID_LIST]);
 	INIT_RADIX_TREE(&nm_i->nat_root, GFP_NOIO);
 	INIT_RADIX_TREE(&nm_i->nat_set_root, GFP_NOIO);
 	INIT_LIST_HEAD(&nm_i->nat_entries);
 
 	mutex_init(&nm_i->build_lock);
-	spin_lock_init(&nm_i->free_nid_list_lock);
+	spin_lock_init(&nm_i->nid_list_lock);
 	init_rwsem(&nm_i->nat_tree_lock);
 
 	nm_i->next_scan_nid = le32_to_cpu(sbi->ckpt->next_free_nid);
@@ -2310,7 +2365,7 @@ int build_node_manager(struct f2fs_sb_info *sbi)
 	if (err)
 		return err;
 
-	build_free_nids(sbi);
+	build_free_nids(sbi, true);
 	return 0;
 }
 
@@ -2327,17 +2382,18 @@ void destroy_node_manager(struct f2fs_sb_info *sbi)
 		return;
 
 	/* destroy free nid list */
-	spin_lock(&nm_i->free_nid_list_lock);
+	spin_lock(&nm_i->nid_list_lock);
-	list_for_each_entry_safe(i, next_i, &nm_i->free_nid_list, list) {
+	list_for_each_entry_safe(i, next_i, &nm_i->nid_list[FREE_NID_LIST],
-		f2fs_bug_on(sbi, i->state == NID_ALLOC);
+									list) {
-		__del_from_free_nid_list(nm_i, i);
+		__remove_nid_from_list(sbi, i, FREE_NID_LIST, false);
-		nm_i->fcnt--;
+		spin_unlock(&nm_i->nid_list_lock);
-		spin_unlock(&nm_i->free_nid_list_lock);
 		kmem_cache_free(free_nid_slab, i);
-		spin_lock(&nm_i->free_nid_list_lock);
+		spin_lock(&nm_i->nid_list_lock);
 	}
-	f2fs_bug_on(sbi, nm_i->fcnt);
+	f2fs_bug_on(sbi, nm_i->nid_cnt[FREE_NID_LIST]);
-	spin_unlock(&nm_i->free_nid_list_lock);
+	f2fs_bug_on(sbi, nm_i->nid_cnt[ALLOC_NID_LIST]);
+	f2fs_bug_on(sbi, !list_empty(&nm_i->nid_list[ALLOC_NID_LIST]));
+	spin_unlock(&nm_i->nid_list_lock);
 
 	/* destroy nat cache */
 	down_write(&nm_i->nat_tree_lock);

fs/f2fs/node.h

@@ -169,14 +169,15 @@ static inline void next_free_nid(struct f2fs_sb_info *sbi, nid_t *nid)
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
 	struct free_nid *fnid;
 
-	spin_lock(&nm_i->free_nid_list_lock);
+	spin_lock(&nm_i->nid_list_lock);
-	if (nm_i->fcnt <= 0) {
+	if (nm_i->nid_cnt[FREE_NID_LIST] <= 0) {
-		spin_unlock(&nm_i->free_nid_list_lock);
+		spin_unlock(&nm_i->nid_list_lock);
 		return;
 	}
-	fnid = list_entry(nm_i->free_nid_list.next, struct free_nid, list);
+	fnid = list_entry(nm_i->nid_list[FREE_NID_LIST].next,
+						struct free_nid, list);
 	*nid = fnid->nid;
-	spin_unlock(&nm_i->free_nid_list_lock);
+	spin_unlock(&nm_i->nid_list_lock);
 }
 
 /*
@@ -313,7 +314,7 @@ static inline bool is_recoverable_dnode(struct page *page)
 				((unsigned char *)ckpt + crc_offset)));
 		cp_ver |= (crc << 32);
 	}
-	return cpu_to_le64(cp_ver) == cpver_of_node(page);
+	return cp_ver == cpver_of_node(page);
 }
 
 /*

fs/f2fs/recovery.c

@@ -180,13 +180,15 @@ static void recover_inode(struct inode *inode, struct page *page)
 
 	inode->i_mode = le16_to_cpu(raw->i_mode);
 	f2fs_i_size_write(inode, le64_to_cpu(raw->i_size));
-	inode->i_atime.tv_sec = le64_to_cpu(raw->i_mtime);
+	inode->i_atime.tv_sec = le64_to_cpu(raw->i_atime);
 	inode->i_ctime.tv_sec = le64_to_cpu(raw->i_ctime);
 	inode->i_mtime.tv_sec = le64_to_cpu(raw->i_mtime);
-	inode->i_atime.tv_nsec = le32_to_cpu(raw->i_mtime_nsec);
+	inode->i_atime.tv_nsec = le32_to_cpu(raw->i_atime_nsec);
 	inode->i_ctime.tv_nsec = le32_to_cpu(raw->i_ctime_nsec);
 	inode->i_mtime.tv_nsec = le32_to_cpu(raw->i_mtime_nsec);
 
+	F2FS_I(inode)->i_advise = raw->i_advise;
+
 	if (file_enc_name(inode))
 		name = "<encrypted>";
 	else
@@ -196,32 +198,6 @@ static void recover_inode(struct inode *inode, struct page *page)
 			ino_of_node(page), name);
 }
 
-static bool is_same_inode(struct inode *inode, struct page *ipage)
-{
-	struct f2fs_inode *ri = F2FS_INODE(ipage);
-	struct timespec disk;
-
-	if (!IS_INODE(ipage))
-		return true;
-
-	disk.tv_sec = le64_to_cpu(ri->i_ctime);
-	disk.tv_nsec = le32_to_cpu(ri->i_ctime_nsec);
-	if (timespec_compare(&inode->i_ctime, &disk) > 0)
-		return false;
-
-	disk.tv_sec = le64_to_cpu(ri->i_atime);
-	disk.tv_nsec = le32_to_cpu(ri->i_atime_nsec);
-	if (timespec_compare(&inode->i_atime, &disk) > 0)
-		return false;
-
-	disk.tv_sec = le64_to_cpu(ri->i_mtime);
-	disk.tv_nsec = le32_to_cpu(ri->i_mtime_nsec);
-	if (timespec_compare(&inode->i_mtime, &disk) > 0)
-		return false;
-
-	return true;
-}
-
 static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head)
 {
 	struct curseg_info *curseg;
@@ -248,10 +224,7 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head)
 			goto next;
 
 		entry = get_fsync_inode(head, ino_of_node(page));
-		if (entry) {
+		if (!entry) {
-			if (!is_same_inode(entry->inode, page))
-				goto next;
-		} else {
 			if (IS_INODE(page) && is_dent_dnode(page)) {
 				err = recover_inode_page(sbi, page);
 				if (err)
@@ -454,7 +427,8 @@ retry_dn:
 			continue;
 		}
 
-		if ((start + 1) << PAGE_SHIFT > i_size_read(inode))
+		if (!file_keep_isize(inode) &&
+				(i_size_read(inode) <= (start << PAGE_SHIFT)))
 			f2fs_i_size_write(inode, (start + 1) << PAGE_SHIFT);
 
 		/*
@@ -507,8 +481,10 @@ err:
 	f2fs_put_dnode(&dn);
 out:
 	f2fs_msg(sbi->sb, KERN_NOTICE,
-		"recover_data: ino = %lx, recovered = %d blocks, err = %d",
+		"recover_data: ino = %lx (i_size: %s) recovered = %d, err = %d",
-		inode->i_ino, recovered, err);
+		inode->i_ino,
+		file_keep_isize(inode) ? "keep" : "recover",
+		recovered, err);
 	return err;
 }
 

fs/f2fs/segment.c

@@ -274,8 +274,10 @@ static int __commit_inmem_pages(struct inode *inode,
 
 			set_page_dirty(page);
 			f2fs_wait_on_page_writeback(page, DATA, true);
-			if (clear_page_dirty_for_io(page))
+			if (clear_page_dirty_for_io(page)) {
 				inode_dec_dirty_pages(inode);
+				remove_dirty_inode(inode);
+			}
 
 			fio.page = page;
 			err = do_write_data_page(&fio);
@@ -287,7 +289,6 @@ static int __commit_inmem_pages(struct inode *inode,
 			/* record old blkaddr for revoking */
 			cur->old_addr = fio.old_blkaddr;
 
-			clear_cold_data(page);
 			submit_bio = true;
 		}
 		unlock_page(page);
@@ -363,7 +364,7 @@ void f2fs_balance_fs(struct f2fs_sb_info *sbi, bool need)
 	 */
 	if (has_not_enough_free_secs(sbi, 0, 0)) {
 		mutex_lock(&sbi->gc_mutex);
-		f2fs_gc(sbi, false);
+		f2fs_gc(sbi, false, false);
 	}
 }
 
@@ -380,14 +381,17 @@ void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi)
 	if (!available_free_memory(sbi, FREE_NIDS))
 		try_to_free_nids(sbi, MAX_FREE_NIDS);
 	else
-		build_free_nids(sbi);
+		build_free_nids(sbi, false);
+
+	if (!is_idle(sbi))
+		return;
 
 	/* checkpoint is the only way to shrink partial cached entries */
 	if (!available_free_memory(sbi, NAT_ENTRIES) ||
 			!available_free_memory(sbi, INO_ENTRIES) ||
 			excess_prefree_segs(sbi) ||
 			excess_dirty_nats(sbi) ||
-			(is_idle(sbi) && f2fs_time_over(sbi, CP_TIME))) {
+			f2fs_time_over(sbi, CP_TIME)) {
 		if (test_opt(sbi, DATA_FLUSH)) {
 			struct blk_plug plug;
 
@@ -400,6 +404,33 @@ void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi)
 	}
 }
 
+static int __submit_flush_wait(struct block_device *bdev)
+{
+	struct bio *bio = f2fs_bio_alloc(0);
+	int ret;
+
+	bio->bi_opf = REQ_OP_WRITE | REQ_PREFLUSH;
+	bio->bi_bdev = bdev;
+	ret = submit_bio_wait(bio);
+	bio_put(bio);
+	return ret;
+}
+
+static int submit_flush_wait(struct f2fs_sb_info *sbi)
+{
+	int ret = __submit_flush_wait(sbi->sb->s_bdev);
+	int i;
+
+	if (sbi->s_ndevs && !ret) {
+		for (i = 1; i < sbi->s_ndevs; i++) {
+			ret = __submit_flush_wait(FDEV(i).bdev);
+			if (ret)
+				break;
+		}
+	}
+	return ret;
+}
+
 static int issue_flush_thread(void *data)
 {
 	struct f2fs_sb_info *sbi = data;
@@ -410,25 +441,18 @@ repeat:
 		return 0;
 
 	if (!llist_empty(&fcc->issue_list)) {
-		struct bio *bio;
 		struct flush_cmd *cmd, *next;
 		int ret;
 
-		bio = f2fs_bio_alloc(0);
-
 		fcc->dispatch_list = llist_del_all(&fcc->issue_list);
 		fcc->dispatch_list = llist_reverse_order(fcc->dispatch_list);
 
-		bio->bi_bdev = sbi->sb->s_bdev;
+		ret = submit_flush_wait(sbi);
-		bio->bi_opf = REQ_OP_WRITE | REQ_PREFLUSH;
-		ret = submit_bio_wait(bio);
-
 		llist_for_each_entry_safe(cmd, next,
 					  fcc->dispatch_list, llnode) {
 			cmd->ret = ret;
 			complete(&cmd->wait);
 		}
-		bio_put(bio);
 		fcc->dispatch_list = NULL;
 	}
 
@@ -449,15 +473,11 @@ int f2fs_issue_flush(struct f2fs_sb_info *sbi)
 		return 0;
 
 	if (!test_opt(sbi, FLUSH_MERGE) || !atomic_read(&fcc->submit_flush)) {
-		struct bio *bio = f2fs_bio_alloc(0);
 		int ret;
 
 		atomic_inc(&fcc->submit_flush);
-		bio->bi_bdev = sbi->sb->s_bdev;
+		ret = submit_flush_wait(sbi);
-		bio->bi_opf = REQ_OP_WRITE | REQ_PREFLUSH;
-		ret = submit_bio_wait(bio);
 		atomic_dec(&fcc->submit_flush);
-		bio_put(bio);
 		return ret;
 	}
 
@@ -469,8 +489,13 @@ int f2fs_issue_flush(struct f2fs_sb_info *sbi)
 	if (!fcc->dispatch_list)
 		wake_up(&fcc->flush_wait_queue);
 
-	wait_for_completion(&cmd.wait);
+	if (fcc->f2fs_issue_flush) {
-	atomic_dec(&fcc->submit_flush);
+		wait_for_completion(&cmd.wait);
+		atomic_dec(&fcc->submit_flush);
+	} else {
+		llist_del_all(&fcc->issue_list);
+		atomic_set(&fcc->submit_flush, 0);
+	}
 
 	return cmd.ret;
 }
@@ -481,6 +506,11 @@ int create_flush_cmd_control(struct f2fs_sb_info *sbi)
 	struct flush_cmd_control *fcc;
 	int err = 0;
 
+	if (SM_I(sbi)->cmd_control_info) {
+		fcc = SM_I(sbi)->cmd_control_info;
+		goto init_thread;
+	}
+
 	fcc = kzalloc(sizeof(struct flush_cmd_control), GFP_KERNEL);
 	if (!fcc)
 		return -ENOMEM;
@@ -488,6 +518,7 @@ int create_flush_cmd_control(struct f2fs_sb_info *sbi)
 	init_waitqueue_head(&fcc->flush_wait_queue);
 	init_llist_head(&fcc->issue_list);
 	SM_I(sbi)->cmd_control_info = fcc;
+init_thread:
 	fcc->f2fs_issue_flush = kthread_run(issue_flush_thread, sbi,
 				"f2fs_flush-%u:%u", MAJOR(dev), MINOR(dev));
 	if (IS_ERR(fcc->f2fs_issue_flush)) {
@@ -500,14 +531,20 @@ int create_flush_cmd_control(struct f2fs_sb_info *sbi)
 	return err;
 }
 
-void destroy_flush_cmd_control(struct f2fs_sb_info *sbi)
+void destroy_flush_cmd_control(struct f2fs_sb_info *sbi, bool free)
 {
 	struct flush_cmd_control *fcc = SM_I(sbi)->cmd_control_info;
 
-	if (fcc && fcc->f2fs_issue_flush)
+	if (fcc && fcc->f2fs_issue_flush) {
-		kthread_stop(fcc->f2fs_issue_flush);
+		struct task_struct *flush_thread = fcc->f2fs_issue_flush;
-	kfree(fcc);
+
-	SM_I(sbi)->cmd_control_info = NULL;
+		fcc->f2fs_issue_flush = NULL;
+		kthread_stop(flush_thread);
+	}
+	if (free) {
+		kfree(fcc);
+		SM_I(sbi)->cmd_control_info = NULL;
+	}
 }
 
 static void __locate_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno,
@@ -633,15 +670,23 @@ static void f2fs_submit_bio_wait_endio(struct bio *bio)
 }
 
 /* this function is copied from blkdev_issue_discard from block/blk-lib.c */
-int __f2fs_issue_discard_async(struct f2fs_sb_info *sbi, sector_t sector,
+static int __f2fs_issue_discard_async(struct f2fs_sb_info *sbi,
-		sector_t nr_sects, gfp_t gfp_mask, unsigned long flags)
+		struct block_device *bdev, block_t blkstart, block_t blklen)
 {
-	struct block_device *bdev = sbi->sb->s_bdev;
 	struct bio *bio = NULL;
 	int err;
 
-	err = __blkdev_issue_discard(bdev, sector, nr_sects, gfp_mask, flags,
+	trace_f2fs_issue_discard(sbi->sb, blkstart, blklen);
-			&bio);
+
+	if (sbi->s_ndevs) {
+		int devi = f2fs_target_device_index(sbi, blkstart);
+
+		blkstart -= FDEV(devi).start_blk;
+	}
+	err = __blkdev_issue_discard(bdev,
+				SECTOR_FROM_BLOCK(blkstart),
+				SECTOR_FROM_BLOCK(blklen),
+				GFP_NOFS, 0, &bio);
 	if (!err && bio) {
 		struct bio_entry *be = __add_bio_entry(sbi, bio);
 
@@ -654,24 +699,101 @@ int __f2fs_issue_discard_async(struct f2fs_sb_info *sbi, sector_t sector,
 	return err;
 }
 
+#ifdef CONFIG_BLK_DEV_ZONED
+static int __f2fs_issue_discard_zone(struct f2fs_sb_info *sbi,
+		struct block_device *bdev, block_t blkstart, block_t blklen)
+{
+	sector_t nr_sects = SECTOR_FROM_BLOCK(blklen);
+	sector_t sector;
+	int devi = 0;
+
+	if (sbi->s_ndevs) {
+		devi = f2fs_target_device_index(sbi, blkstart);
+		blkstart -= FDEV(devi).start_blk;
+	}
+	sector = SECTOR_FROM_BLOCK(blkstart);
+
+	if (sector & (bdev_zone_size(bdev) - 1) ||
+				nr_sects != bdev_zone_size(bdev)) {
+		f2fs_msg(sbi->sb, KERN_INFO,
+			"(%d) %s: Unaligned discard attempted (block %x + %x)",
+			devi, sbi->s_ndevs ? FDEV(devi).path: "",
+			blkstart, blklen);
+		return -EIO;
+	}
+
+	/*
+	 * We need to know the type of the zone: for conventional zones,
+	 * use regular discard if the drive supports it. For sequential
+	 * zones, reset the zone write pointer.
+	 */
+	switch (get_blkz_type(sbi, bdev, blkstart)) {
+
+	case BLK_ZONE_TYPE_CONVENTIONAL:
+		if (!blk_queue_discard(bdev_get_queue(bdev)))
+			return 0;
+		return __f2fs_issue_discard_async(sbi, bdev, blkstart, blklen);
+	case BLK_ZONE_TYPE_SEQWRITE_REQ:
+	case BLK_ZONE_TYPE_SEQWRITE_PREF:
+		trace_f2fs_issue_reset_zone(sbi->sb, blkstart);
+		return blkdev_reset_zones(bdev, sector,
+					  nr_sects, GFP_NOFS);
+	default:
+		/* Unknown zone type: broken device ? */
+		return -EIO;
+	}
+}
+#endif
+
+static int __issue_discard_async(struct f2fs_sb_info *sbi,
+		struct block_device *bdev, block_t blkstart, block_t blklen)
+{
+#ifdef CONFIG_BLK_DEV_ZONED
+	if (f2fs_sb_mounted_blkzoned(sbi->sb) &&
+				bdev_zoned_model(bdev) != BLK_ZONED_NONE)
+		return __f2fs_issue_discard_zone(sbi, bdev, blkstart, blklen);
+#endif
+	return __f2fs_issue_discard_async(sbi, bdev, blkstart, blklen);
+}
+
 static int f2fs_issue_discard(struct f2fs_sb_info *sbi,
 				block_t blkstart, block_t blklen)
 {
-	sector_t start = SECTOR_FROM_BLOCK(blkstart);
+	sector_t start = blkstart, len = 0;
-	sector_t len = SECTOR_FROM_BLOCK(blklen);
+	struct block_device *bdev;
 	struct seg_entry *se;
 	unsigned int offset;
 	block_t i;
+	int err = 0;
+
+	bdev = f2fs_target_device(sbi, blkstart, NULL);
+
+	for (i = blkstart; i < blkstart + blklen; i++, len++) {
+		if (i != start) {
+			struct block_device *bdev2 =
+				f2fs_target_device(sbi, i, NULL);
+
+			if (bdev2 != bdev) {
+				err = __issue_discard_async(sbi, bdev,
+						start, len);
+				if (err)
+					return err;
+				bdev = bdev2;
+				start = i;
+				len = 0;
+			}
+		}
 
-	for (i = blkstart; i < blkstart + blklen; i++) {
 		se = get_seg_entry(sbi, GET_SEGNO(sbi, i));
 		offset = GET_BLKOFF_FROM_SEG0(sbi, i);
 
 		if (!f2fs_test_and_set_bit(offset, se->discard_map))
 			sbi->discard_blks--;
 	}
-	trace_f2fs_issue_discard(sbi->sb, blkstart, blklen);
+
-	return __f2fs_issue_discard_async(sbi, start, len, GFP_NOFS, 0);
+	if (len)
+		err = __issue_discard_async(sbi, bdev, start, len);
+	return err;
 }
 
 static void __add_discard_entry(struct f2fs_sb_info *sbi,
@@ -1296,25 +1418,21 @@ static void allocate_segment_by_default(struct f2fs_sb_info *sbi,
 	stat_inc_seg_type(sbi, curseg);
 }
 
-static void __allocate_new_segments(struct f2fs_sb_info *sbi, int type)
-{
-	struct curseg_info *curseg = CURSEG_I(sbi, type);
-	unsigned int old_segno;
-
-	old_segno = curseg->segno;
-	SIT_I(sbi)->s_ops->allocate_segment(sbi, type, true);
-	locate_dirty_segment(sbi, old_segno);
-}
-
 void allocate_new_segments(struct f2fs_sb_info *sbi)
 {
+	struct curseg_info *curseg;
+	unsigned int old_segno;
 	int i;
 
 	if (test_opt(sbi, LFS))
 		return;
 
-	for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++)
+	for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++) {
-		__allocate_new_segments(sbi, i);
+		curseg = CURSEG_I(sbi, i);
+		old_segno = curseg->segno;
+		SIT_I(sbi)->s_ops->allocate_segment(sbi, i, true);
+		locate_dirty_segment(sbi, old_segno);
+	}
 }
 
 static const struct segment_allocation default_salloc_ops = {
@@ -1448,21 +1566,11 @@ void allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
 		struct f2fs_summary *sum, int type)
 {
 	struct sit_info *sit_i = SIT_I(sbi);
-	struct curseg_info *curseg;
+	struct curseg_info *curseg = CURSEG_I(sbi, type);
-	bool direct_io = (type == CURSEG_DIRECT_IO);
-
-	type = direct_io ? CURSEG_WARM_DATA : type;
-
-	curseg = CURSEG_I(sbi, type);
 
 	mutex_lock(&curseg->curseg_mutex);
 	mutex_lock(&sit_i->sentry_lock);
 
-	/* direct_io'ed data is aligned to the segment for better performance */
-	if (direct_io && curseg->next_blkoff &&
-				!has_not_enough_free_secs(sbi, 0, 0))
-		__allocate_new_segments(sbi, type);
-
 	*new_blkaddr = NEXT_FREE_BLKADDR(sbi, curseg);
 
 	/*
@@ -2166,7 +2274,6 @@ out:
 static int build_sit_info(struct f2fs_sb_info *sbi)
 {
 	struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi);
-	struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
 	struct sit_info *sit_i;
 	unsigned int sit_segs, start;
 	char *src_bitmap, *dst_bitmap;
@@ -2233,7 +2340,7 @@ static int build_sit_info(struct f2fs_sb_info *sbi)
 
 	sit_i->sit_base_addr = le32_to_cpu(raw_super->sit_blkaddr);
 	sit_i->sit_blocks = sit_segs << sbi->log_blocks_per_seg;
-	sit_i->written_valid_blocks = le64_to_cpu(ckpt->valid_block_count);
+	sit_i->written_valid_blocks = 0;
 	sit_i->sit_bitmap = dst_bitmap;
 	sit_i->bitmap_size = bitmap_size;
 	sit_i->dirty_sentries = 0;
@@ -2315,10 +2422,10 @@ static void build_sit_entries(struct f2fs_sb_info *sbi)
 	int sit_blk_cnt = SIT_BLK_CNT(sbi);
 	unsigned int i, start, end;
 	unsigned int readed, start_blk = 0;
-	int nrpages = MAX_BIO_BLOCKS(sbi) * 8;
 
 	do {
-		readed = ra_meta_pages(sbi, start_blk, nrpages, META_SIT, true);
+		readed = ra_meta_pages(sbi, start_blk, BIO_MAX_PAGES,
+							META_SIT, true);
 
 		start = start_blk * sit_i->sents_per_block;
 		end = (start_blk + readed) * sit_i->sents_per_block;
@@ -2387,6 +2494,9 @@ static void init_free_segmap(struct f2fs_sb_info *sbi)
 		struct seg_entry *sentry = get_seg_entry(sbi, start);
 		if (!sentry->valid_blocks)
 			__set_free(sbi, start);
+		else
+			SIT_I(sbi)->written_valid_blocks +=
+						sentry->valid_blocks;
 	}
 
 	/* set use the current segments */
@@ -2645,7 +2755,7 @@ void destroy_segment_manager(struct f2fs_sb_info *sbi)
 
 	if (!sm_info)
 		return;
-	destroy_flush_cmd_control(sbi);
+	destroy_flush_cmd_control(sbi, true);
 	destroy_dirty_segmap(sbi);
 	destroy_curseg(sbi);
 	destroy_free_segmap(sbi);

fs/f2fs/segment.h

@@ -18,6 +18,8 @@
 #define DEF_RECLAIM_PREFREE_SEGMENTS	5	/* 5% over total segments */
 #define DEF_MAX_RECLAIM_PREFREE_SEGMENTS	4096	/* 8GB in maximum */
 
+#define F2FS_MIN_SEGMENTS	9 /* SB + 2 (CP + SIT + NAT) + SSA + MAIN */
+
 /* L: Logical segment # in volume, R: Relative segment # in main area */
 #define GET_L2R_SEGNO(free_i, segno)	(segno - free_i->start_segno)
 #define GET_R2L_SEGNO(free_i, segno)	(segno + free_i->start_segno)
@@ -102,8 +104,6 @@
 	(((sector_t)blk_addr) << F2FS_LOG_SECTORS_PER_BLOCK)
 #define SECTOR_TO_BLOCK(sectors)					\
 	(sectors >> F2FS_LOG_SECTORS_PER_BLOCK)
-#define MAX_BIO_BLOCKS(sbi)						\
-	((int)min((int)max_hw_blocks(sbi), BIO_MAX_PAGES))
 
 /*
  * indicate a block allocation direction: RIGHT and LEFT.
@@ -471,11 +471,12 @@ static inline bool need_SSR(struct f2fs_sb_info *sbi)
 {
 	int node_secs = get_blocktype_secs(sbi, F2FS_DIRTY_NODES);
 	int dent_secs = get_blocktype_secs(sbi, F2FS_DIRTY_DENTS);
+	int imeta_secs = get_blocktype_secs(sbi, F2FS_DIRTY_IMETA);
 
 	if (test_opt(sbi, LFS))
 		return false;
 
-	return free_sections(sbi) <= (node_secs + 2 * dent_secs +
+	return free_sections(sbi) <= (node_secs + 2 * dent_secs + imeta_secs +
 						reserved_sections(sbi) + 1);
 }
 
@@ -484,14 +485,14 @@ static inline bool has_not_enough_free_secs(struct f2fs_sb_info *sbi,
 {
 	int node_secs = get_blocktype_secs(sbi, F2FS_DIRTY_NODES);
 	int dent_secs = get_blocktype_secs(sbi, F2FS_DIRTY_DENTS);
-
+	int imeta_secs = get_blocktype_secs(sbi, F2FS_DIRTY_IMETA);
-	node_secs += get_blocktype_secs(sbi, F2FS_DIRTY_IMETA);
 
 	if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
 		return false;
 
 	return (free_sections(sbi) + freed) <=
-		(node_secs + 2 * dent_secs + reserved_sections(sbi) + needed);
+		(node_secs + 2 * dent_secs + imeta_secs +
+		reserved_sections(sbi) + needed);
 }
 
 static inline bool excess_prefree_segs(struct f2fs_sb_info *sbi)
@@ -695,13 +696,6 @@ static inline bool sec_usage_check(struct f2fs_sb_info *sbi, unsigned int secno)
 	return false;
 }
 
-static inline unsigned int max_hw_blocks(struct f2fs_sb_info *sbi)
-{
-	struct block_device *bdev = sbi->sb->s_bdev;
-	struct request_queue *q = bdev_get_queue(bdev);
-	return SECTOR_TO_BLOCK(queue_max_sectors(q));
-}
-
 /*
  * It is very important to gather dirty pages and write at once, so that we can
  * submit a big bio without interfering other data writes.
@@ -719,7 +713,7 @@ static inline int nr_pages_to_skip(struct f2fs_sb_info *sbi, int type)
 	else if (type == NODE)
 		return 8 * sbi->blocks_per_seg;
 	else if (type == META)
-		return 8 * MAX_BIO_BLOCKS(sbi);
+		return 8 * BIO_MAX_PAGES;
 	else
 		return 0;
 }
@@ -736,11 +730,9 @@ static inline long nr_pages_to_write(struct f2fs_sb_info *sbi, int type,
 		return 0;
 
 	nr_to_write = wbc->nr_to_write;
-
+	desired = BIO_MAX_PAGES;
 	if (type == NODE)
-		desired = 2 * max_hw_blocks(sbi);
+		desired <<= 1;
-	else
-		desired = MAX_BIO_BLOCKS(sbi);
 
 	wbc->nr_to_write = desired;
 	return desired - nr_to_write;

fs/f2fs/shrinker.c

@@ -21,14 +21,16 @@ static unsigned int shrinker_run_no;
 
 static unsigned long __count_nat_entries(struct f2fs_sb_info *sbi)
 {
-	return NM_I(sbi)->nat_cnt - NM_I(sbi)->dirty_nat_cnt;
+	long count = NM_I(sbi)->nat_cnt - NM_I(sbi)->dirty_nat_cnt;
+
+	return count > 0 ? count : 0;
 }
 
 static unsigned long __count_free_nids(struct f2fs_sb_info *sbi)
 {
-	if (NM_I(sbi)->fcnt > MAX_FREE_NIDS)
+	long count = NM_I(sbi)->nid_cnt[FREE_NID_LIST] - MAX_FREE_NIDS;
-		return NM_I(sbi)->fcnt - MAX_FREE_NIDS;
+
-	return 0;
+	return count > 0 ? count : 0;
 }
 
 static unsigned long __count_extent_cache(struct f2fs_sb_info *sbi)

fs/f2fs/super.c

@@ -412,14 +412,20 @@ static int parse_options(struct super_block *sb, char *options)
 			q = bdev_get_queue(sb->s_bdev);
 			if (blk_queue_discard(q)) {
 				set_opt(sbi, DISCARD);
-			} else {
+			} else if (!f2fs_sb_mounted_blkzoned(sb)) {
 				f2fs_msg(sb, KERN_WARNING,
 					"mounting with \"discard\" option, but "
 					"the device does not support discard");
 			}
 			break;
 		case Opt_nodiscard:
+			if (f2fs_sb_mounted_blkzoned(sb)) {
+				f2fs_msg(sb, KERN_WARNING,
+					"discard is required for zoned block devices");
+				return -EINVAL;
+			}
 			clear_opt(sbi, DISCARD);
+			break;
 		case Opt_noheap:
 			set_opt(sbi, NOHEAP);
 			break;
@@ -512,6 +518,13 @@ static int parse_options(struct super_block *sb, char *options)
 				return -ENOMEM;
 			if (strlen(name) == 8 &&
 					!strncmp(name, "adaptive", 8)) {
+				if (f2fs_sb_mounted_blkzoned(sb)) {
+					f2fs_msg(sb, KERN_WARNING,
+						 "adaptive mode is not allowed with "
+						 "zoned block device feature");
+					kfree(name);
+					return -EINVAL;
+				}
 				set_opt_mode(sbi, F2FS_MOUNT_ADAPTIVE);
 			} else if (strlen(name) == 3 &&
 					!strncmp(name, "lfs", 3)) {
@@ -558,13 +571,9 @@ static struct inode *f2fs_alloc_inode(struct super_block *sb)
 
 	init_once((void *) fi);
 
-	if (percpu_counter_init(&fi->dirty_pages, 0, GFP_NOFS)) {
-		kmem_cache_free(f2fs_inode_cachep, fi);
-		return NULL;
-	}
-
 	/* Initialize f2fs-specific inode info */
 	fi->vfs_inode.i_version = 1;
+	atomic_set(&fi->dirty_pages, 0);
 	fi->i_current_depth = 1;
 	fi->i_advise = 0;
 	init_rwsem(&fi->i_sem);
@@ -620,24 +629,25 @@ static int f2fs_drop_inode(struct inode *inode)
 	return generic_drop_inode(inode);
 }
 
-int f2fs_inode_dirtied(struct inode *inode)
+int f2fs_inode_dirtied(struct inode *inode, bool sync)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	int ret = 0;
 
 	spin_lock(&sbi->inode_lock[DIRTY_META]);
 	if (is_inode_flag_set(inode, FI_DIRTY_INODE)) {
-		spin_unlock(&sbi->inode_lock[DIRTY_META]);
+		ret = 1;
-		return 1;
+	} else {
+		set_inode_flag(inode, FI_DIRTY_INODE);
+		stat_inc_dirty_inode(sbi, DIRTY_META);
 	}
-
+	if (sync && list_empty(&F2FS_I(inode)->gdirty_list)) {
-	set_inode_flag(inode, FI_DIRTY_INODE);
+		list_add_tail(&F2FS_I(inode)->gdirty_list,
-	list_add_tail(&F2FS_I(inode)->gdirty_list,
 				&sbi->inode_list[DIRTY_META]);
-	inc_page_count(sbi, F2FS_DIRTY_IMETA);
+		inc_page_count(sbi, F2FS_DIRTY_IMETA);
-	stat_inc_dirty_inode(sbi, DIRTY_META);
+	}
 	spin_unlock(&sbi->inode_lock[DIRTY_META]);
-
+	return ret;
-	return 0;
 }
 
 void f2fs_inode_synced(struct inode *inode)
@@ -649,10 +659,12 @@ void f2fs_inode_synced(struct inode *inode)
 		spin_unlock(&sbi->inode_lock[DIRTY_META]);
 		return;
 	}
-	list_del_init(&F2FS_I(inode)->gdirty_list);
+	if (!list_empty(&F2FS_I(inode)->gdirty_list)) {
+		list_del_init(&F2FS_I(inode)->gdirty_list);
+		dec_page_count(sbi, F2FS_DIRTY_IMETA);
+	}
 	clear_inode_flag(inode, FI_DIRTY_INODE);
 	clear_inode_flag(inode, FI_AUTO_RECOVER);
-	dec_page_count(sbi, F2FS_DIRTY_IMETA);
 	stat_dec_dirty_inode(F2FS_I_SB(inode), DIRTY_META);
 	spin_unlock(&sbi->inode_lock[DIRTY_META]);
 }
@@ -676,7 +688,7 @@ static void f2fs_dirty_inode(struct inode *inode, int flags)
 	if (is_inode_flag_set(inode, FI_AUTO_RECOVER))
 		clear_inode_flag(inode, FI_AUTO_RECOVER);
 
-	f2fs_inode_dirtied(inode);
+	f2fs_inode_dirtied(inode, false);
 }
 
 static void f2fs_i_callback(struct rcu_head *head)
@@ -687,20 +699,28 @@ static void f2fs_i_callback(struct rcu_head *head)
 
 static void f2fs_destroy_inode(struct inode *inode)
 {
-	percpu_counter_destroy(&F2FS_I(inode)->dirty_pages);
 	call_rcu(&inode->i_rcu, f2fs_i_callback);
 }
 
 static void destroy_percpu_info(struct f2fs_sb_info *sbi)
 {
-	int i;
-
-	for (i = 0; i < NR_COUNT_TYPE; i++)
-		percpu_counter_destroy(&sbi->nr_pages[i]);
 	percpu_counter_destroy(&sbi->alloc_valid_block_count);
 	percpu_counter_destroy(&sbi->total_valid_inode_count);
 }
 
+static void destroy_device_list(struct f2fs_sb_info *sbi)
+{
+	int i;
+
+	for (i = 0; i < sbi->s_ndevs; i++) {
+		blkdev_put(FDEV(i).bdev, FMODE_EXCL);
+#ifdef CONFIG_BLK_DEV_ZONED
+		kfree(FDEV(i).blkz_type);
+#endif
+	}
+	kfree(sbi->devs);
+}
+
 static void f2fs_put_super(struct super_block *sb)
 {
 	struct f2fs_sb_info *sbi = F2FS_SB(sb);
@@ -738,7 +758,6 @@ static void f2fs_put_super(struct super_block *sb)
 	 * In addition, EIO will skip do checkpoint, we need this as well.
 	 */
 	release_ino_entry(sbi, true);
-	release_discard_addrs(sbi);
 
 	f2fs_leave_shrinker(sbi);
 	mutex_unlock(&sbi->umount_mutex);
@@ -762,6 +781,8 @@ static void f2fs_put_super(struct super_block *sb)
 		crypto_free_shash(sbi->s_chksum_driver);
 	kfree(sbi->raw_super);
 
+	destroy_device_list(sbi);
+
 	destroy_percpu_info(sbi);
 	kfree(sbi);
 }
@@ -789,13 +810,17 @@ int f2fs_sync_fs(struct super_block *sb, int sync)
 
 static int f2fs_freeze(struct super_block *sb)
 {
-	int err;
-
 	if (f2fs_readonly(sb))
 		return 0;
 
-	err = f2fs_sync_fs(sb, 1);
+	/* IO error happened before */
-	return err;
+	if (unlikely(f2fs_cp_error(F2FS_SB(sb))))
+		return -EIO;
+
+	/* must be clean, since sync_filesystem() was already called */
+	if (is_sbi_flag_set(F2FS_SB(sb), SBI_IS_DIRTY))
+		return -EINVAL;
+	return 0;
 }
 
 static int f2fs_unfreeze(struct super_block *sb)
@@ -822,7 +847,8 @@ static int f2fs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_bavail = user_block_count - valid_user_blocks(sbi);
 
 	buf->f_files = sbi->total_node_count - F2FS_RESERVED_NODE_NUM;
-	buf->f_ffree = buf->f_files - valid_inode_count(sbi);
+	buf->f_ffree = min(buf->f_files - valid_node_count(sbi),
+							buf->f_bavail);
 
 	buf->f_namelen = F2FS_NAME_LEN;
 	buf->f_fsid.val[0] = (u32)id;
@@ -974,7 +1000,7 @@ static void default_options(struct f2fs_sb_info *sbi)
 	set_opt(sbi, EXTENT_CACHE);
 	sbi->sb->s_flags |= MS_LAZYTIME;
 	set_opt(sbi, FLUSH_MERGE);
-	if (f2fs_sb_mounted_hmsmr(sbi->sb)) {
+	if (f2fs_sb_mounted_blkzoned(sbi->sb)) {
 		set_opt_mode(sbi, F2FS_MOUNT_LFS);
 		set_opt(sbi, DISCARD);
 	} else {
@@ -1076,8 +1102,9 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
 	 * or if flush_merge is not passed in mount option.
 	 */
 	if ((*flags & MS_RDONLY) || !test_opt(sbi, FLUSH_MERGE)) {
-		destroy_flush_cmd_control(sbi);
+		clear_opt(sbi, FLUSH_MERGE);
-	} else if (!SM_I(sbi)->cmd_control_info) {
+		destroy_flush_cmd_control(sbi, false);
+	} else {
 		err = create_flush_cmd_control(sbi);
 		if (err)
 			goto restore_gc;
@@ -1426,6 +1453,7 @@ int sanity_check_ckpt(struct f2fs_sb_info *sbi)
 	unsigned int total, fsmeta;
 	struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi);
 	struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
+	unsigned int ovp_segments, reserved_segments;
 
 	total = le32_to_cpu(raw_super->segment_count);
 	fsmeta = le32_to_cpu(raw_super->segment_count_ckpt);
@@ -1437,6 +1465,16 @@ int sanity_check_ckpt(struct f2fs_sb_info *sbi)
 	if (unlikely(fsmeta >= total))
 		return 1;
 
+	ovp_segments = le32_to_cpu(ckpt->overprov_segment_count);
+	reserved_segments = le32_to_cpu(ckpt->rsvd_segment_count);
+
+	if (unlikely(fsmeta < F2FS_MIN_SEGMENTS ||
+			ovp_segments == 0 || reserved_segments == 0)) {
+		f2fs_msg(sbi->sb, KERN_ERR,
+			"Wrong layout: check mkfs.f2fs version");
+		return 1;
+	}
+
 	if (unlikely(f2fs_cp_error(sbi))) {
 		f2fs_msg(sbi->sb, KERN_ERR, "A bug case: need to run fsck");
 		return 1;
@@ -1447,6 +1485,7 @@ int sanity_check_ckpt(struct f2fs_sb_info *sbi)
 static void init_sb_info(struct f2fs_sb_info *sbi)
 {
 	struct f2fs_super_block *raw_super = sbi->raw_super;
+	int i;
 
 	sbi->log_sectors_per_block =
 		le32_to_cpu(raw_super->log_sectors_per_block);
@@ -1471,6 +1510,9 @@ static void init_sb_info(struct f2fs_sb_info *sbi)
 	sbi->interval_time[REQ_TIME] = DEF_IDLE_INTERVAL;
 	clear_sbi_flag(sbi, SBI_NEED_FSCK);
 
+	for (i = 0; i < NR_COUNT_TYPE; i++)
+		atomic_set(&sbi->nr_pages[i], 0);
+
 	INIT_LIST_HEAD(&sbi->s_list);
 	mutex_init(&sbi->umount_mutex);
 	mutex_init(&sbi->wio_mutex[NODE]);
@@ -1486,13 +1528,7 @@ static void init_sb_info(struct f2fs_sb_info *sbi)
 
 static int init_percpu_info(struct f2fs_sb_info *sbi)
 {
-	int i, err;
+	int err;
-
-	for (i = 0; i < NR_COUNT_TYPE; i++) {
-		err = percpu_counter_init(&sbi->nr_pages[i], 0, GFP_KERNEL);
-		if (err)
-			return err;
-	}
 
 	err = percpu_counter_init(&sbi->alloc_valid_block_count, 0, GFP_KERNEL);
 	if (err)
@@ -1502,6 +1538,71 @@ static int init_percpu_info(struct f2fs_sb_info *sbi)
 								GFP_KERNEL);
 }
 
+#ifdef CONFIG_BLK_DEV_ZONED
+static int init_blkz_info(struct f2fs_sb_info *sbi, int devi)
+{
+	struct block_device *bdev = FDEV(devi).bdev;
+	sector_t nr_sectors = bdev->bd_part->nr_sects;
+	sector_t sector = 0;
+	struct blk_zone *zones;
+	unsigned int i, nr_zones;
+	unsigned int n = 0;
+	int err = -EIO;
+
+	if (!f2fs_sb_mounted_blkzoned(sbi->sb))
+		return 0;
+
+	if (sbi->blocks_per_blkz && sbi->blocks_per_blkz !=
+				SECTOR_TO_BLOCK(bdev_zone_size(bdev)))
+		return -EINVAL;
+	sbi->blocks_per_blkz = SECTOR_TO_BLOCK(bdev_zone_size(bdev));
+	if (sbi->log_blocks_per_blkz && sbi->log_blocks_per_blkz !=
+				__ilog2_u32(sbi->blocks_per_blkz))
+		return -EINVAL;
+	sbi->log_blocks_per_blkz = __ilog2_u32(sbi->blocks_per_blkz);
+	FDEV(devi).nr_blkz = SECTOR_TO_BLOCK(nr_sectors) >>
+					sbi->log_blocks_per_blkz;
+	if (nr_sectors & (bdev_zone_size(bdev) - 1))
+		FDEV(devi).nr_blkz++;
+
+	FDEV(devi).blkz_type = kmalloc(FDEV(devi).nr_blkz, GFP_KERNEL);
+	if (!FDEV(devi).blkz_type)
+		return -ENOMEM;
+
+#define F2FS_REPORT_NR_ZONES   4096
+
+	zones = kcalloc(F2FS_REPORT_NR_ZONES, sizeof(struct blk_zone),
+			GFP_KERNEL);
+	if (!zones)
+		return -ENOMEM;
+
+	/* Get block zones type */
+	while (zones && sector < nr_sectors) {
+
+		nr_zones = F2FS_REPORT_NR_ZONES;
+		err = blkdev_report_zones(bdev, sector,
+					  zones, &nr_zones,
+					  GFP_KERNEL);
+		if (err)
+			break;
+		if (!nr_zones) {
+			err = -EIO;
+			break;
+		}
+
+		for (i = 0; i < nr_zones; i++) {
+			FDEV(devi).blkz_type[n] = zones[i].type;
+			sector += zones[i].len;
+			n++;
+		}
+	}
+
+	kfree(zones);
+
+	return err;
+}
+#endif
+
 /*
  * Read f2fs raw super block.
  * Because we have two copies of super block, so read both of them
@@ -1594,6 +1695,77 @@ int f2fs_commit_super(struct f2fs_sb_info *sbi, bool recover)
 	return err;
 }
 
+static int f2fs_scan_devices(struct f2fs_sb_info *sbi)
+{
+	struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi);
+	int i;
+
+	for (i = 0; i < MAX_DEVICES; i++) {
+		if (!RDEV(i).path[0])
+			return 0;
+
+		if (i == 0) {
+			sbi->devs = kzalloc(sizeof(struct f2fs_dev_info) *
+						MAX_DEVICES, GFP_KERNEL);
+			if (!sbi->devs)
+				return -ENOMEM;
+		}
+
+		memcpy(FDEV(i).path, RDEV(i).path, MAX_PATH_LEN);
+		FDEV(i).total_segments = le32_to_cpu(RDEV(i).total_segments);
+		if (i == 0) {
+			FDEV(i).start_blk = 0;
+			FDEV(i).end_blk = FDEV(i).start_blk +
+				(FDEV(i).total_segments <<
+				sbi->log_blocks_per_seg) - 1 +
+				le32_to_cpu(raw_super->segment0_blkaddr);
+		} else {
+			FDEV(i).start_blk = FDEV(i - 1).end_blk + 1;
+			FDEV(i).end_blk = FDEV(i).start_blk +
+				(FDEV(i).total_segments <<
+				sbi->log_blocks_per_seg) - 1;
+		}
+
+		FDEV(i).bdev = blkdev_get_by_path(FDEV(i).path,
+					sbi->sb->s_mode, sbi->sb->s_type);
+		if (IS_ERR(FDEV(i).bdev))
+			return PTR_ERR(FDEV(i).bdev);
+
+		/* to release errored devices */
+		sbi->s_ndevs = i + 1;
+
+#ifdef CONFIG_BLK_DEV_ZONED
+		if (bdev_zoned_model(FDEV(i).bdev) == BLK_ZONED_HM &&
+				!f2fs_sb_mounted_blkzoned(sbi->sb)) {
+			f2fs_msg(sbi->sb, KERN_ERR,
+				"Zoned block device feature not enabled\n");
+			return -EINVAL;
+		}
+		if (bdev_zoned_model(FDEV(i).bdev) != BLK_ZONED_NONE) {
+			if (init_blkz_info(sbi, i)) {
+				f2fs_msg(sbi->sb, KERN_ERR,
+					"Failed to initialize F2FS blkzone information");
+				return -EINVAL;
+			}
+			f2fs_msg(sbi->sb, KERN_INFO,
+				"Mount Device [%2d]: %20s, %8u, %8x - %8x (zone: %s)",
+				i, FDEV(i).path,
+				FDEV(i).total_segments,
+				FDEV(i).start_blk, FDEV(i).end_blk,
+				bdev_zoned_model(FDEV(i).bdev) == BLK_ZONED_HA ?
+				"Host-aware" : "Host-managed");
+			continue;
+		}
+#endif
+		f2fs_msg(sbi->sb, KERN_INFO,
+			"Mount Device [%2d]: %20s, %8u, %8x - %8x",
+				i, FDEV(i).path,
+				FDEV(i).total_segments,
+				FDEV(i).start_blk, FDEV(i).end_blk);
+	}
+	return 0;
+}
+
 static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 {
 	struct f2fs_sb_info *sbi;
@@ -1641,6 +1813,18 @@ try_onemore:
 	sb->s_fs_info = sbi;
 	sbi->raw_super = raw_super;
 
+	/*
+	 * The BLKZONED feature indicates that the drive was formatted with
+	 * zone alignment optimization. This is optional for host-aware
+	 * devices, but mandatory for host-managed zoned block devices.
+	 */
+#ifndef CONFIG_BLK_DEV_ZONED
+	if (f2fs_sb_mounted_blkzoned(sb)) {
+		f2fs_msg(sb, KERN_ERR,
+			 "Zoned block device support is not enabled\n");
+		goto free_sb_buf;
+	}
+#endif
 	default_options(sbi);
 	/* parse mount options */
 	options = kstrdup((const char *)data, GFP_KERNEL);
@@ -1710,6 +1894,13 @@ try_onemore:
 		goto free_meta_inode;
 	}
 
+	/* Initialize device list */
+	err = f2fs_scan_devices(sbi);
+	if (err) {
+		f2fs_msg(sb, KERN_ERR, "Failed to find devices");
+		goto free_devices;
+	}
+
 	sbi->total_valid_node_count =
 				le32_to_cpu(sbi->ckpt->valid_node_count);
 	percpu_counter_set(&sbi->total_valid_inode_count,
@@ -1893,12 +2084,21 @@ free_node_inode:
 	mutex_lock(&sbi->umount_mutex);
 	release_ino_entry(sbi, true);
 	f2fs_leave_shrinker(sbi);
+	/*
+	 * Some dirty meta pages can be produced by recover_orphan_inodes()
+	 * failed by EIO. Then, iput(node_inode) can trigger balance_fs_bg()
+	 * followed by write_checkpoint() through f2fs_write_node_pages(), which
+	 * falls into an infinite loop in sync_meta_pages().
+	 */
+	truncate_inode_pages_final(META_MAPPING(sbi));
 	iput(sbi->node_inode);
 	mutex_unlock(&sbi->umount_mutex);
 free_nm:
 	destroy_node_manager(sbi);
 free_sm:
 	destroy_segment_manager(sbi);
+free_devices:
+	destroy_device_list(sbi);
 	kfree(sbi->ckpt);
 free_meta_inode:
 	make_bad_inode(sbi->meta_inode);
@@ -2044,3 +2244,4 @@ module_exit(exit_f2fs_fs)
 MODULE_AUTHOR("Samsung Electronics's Praesto Team");
 MODULE_DESCRIPTION("Flash Friendly File System");
 MODULE_LICENSE("GPL");
+

fs/f2fs/xattr.c

@@ -106,7 +106,7 @@ static int f2fs_xattr_advise_set(const struct xattr_handler *handler,
 		return -EINVAL;
 
 	F2FS_I(inode)->i_advise |= *(char *)value;
-	f2fs_mark_inode_dirty_sync(inode);
+	f2fs_mark_inode_dirty_sync(inode, true);
 	return 0;
 }
 
@@ -554,7 +554,7 @@ static int __f2fs_setxattr(struct inode *inode, int index,
 	if (index == F2FS_XATTR_INDEX_ENCRYPTION &&
 			!strcmp(name, F2FS_XATTR_NAME_ENCRYPTION_CONTEXT))
 		f2fs_set_encrypted_inode(inode);
-	f2fs_mark_inode_dirty_sync(inode);
+	f2fs_mark_inode_dirty_sync(inode, true);
 	if (!error && S_ISDIR(inode->i_mode))
 		set_sbi_flag(F2FS_I_SB(inode), SBI_NEED_CP);
 exit:

include/linux/f2fs_fs.h

@@ -52,10 +52,17 @@
 
 #define VERSION_LEN	256
 #define MAX_VOLUME_NAME		512
+#define MAX_PATH_LEN		64
+#define MAX_DEVICES		8
 
 /*
  * For superblock
  */
+struct f2fs_device {
+	__u8 path[MAX_PATH_LEN];
+	__le32 total_segments;
+} __packed;
+
 struct f2fs_super_block {
 	__le32 magic;			/* Magic Number */
 	__le16 major_ver;		/* Major Version */
@@ -94,7 +101,8 @@ struct f2fs_super_block {
 	__le32 feature;			/* defined features */
 	__u8 encryption_level;		/* versioning level for encryption */
 	__u8 encrypt_pw_salt[16];	/* Salt used for string2key algorithm */
-	__u8 reserved[871];		/* valid reserved region */
+	struct f2fs_device devs[MAX_DEVICES];	/* device list */
+	__u8 reserved[327];		/* valid reserved region */
 } __packed;
 
 /*

include/trace/events/f2fs.h

@@ -1111,6 +1111,27 @@ TRACE_EVENT(f2fs_issue_discard,
 		(unsigned long long)__entry->blklen)
 );
 
+TRACE_EVENT(f2fs_issue_reset_zone,
+
+	TP_PROTO(struct super_block *sb, block_t blkstart),
+
+	TP_ARGS(sb, blkstart),
+
+	TP_STRUCT__entry(
+		__field(dev_t,	dev)
+		__field(block_t, blkstart)
+	),
+
+	TP_fast_assign(
+		__entry->dev	= sb->s_dev;
+		__entry->blkstart = blkstart;
+	),
+
+	TP_printk("dev = (%d,%d), reset zone at block = 0x%llx",
+		show_dev(__entry),
+		(unsigned long long)__entry->blkstart)
+);
+
 TRACE_EVENT(f2fs_issue_flush,
 
 	TP_PROTO(struct super_block *sb, unsigned int nobarrier,