Merge tag 'for-f2fs-4.7' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs

Pull f2fs updates from Jaegeuk Kim:
 "In this round, as Ted pointed out, fscrypto allows one more key prefix
  given by filesystem to resolve backward compatibility issues.  Other
  than that, we've fixed several error handling cases by introducing
  a fault injection facility.  We've also achieved performance
  improvement in some workloads as well as a bunch of bug fixes.

  Summary:

  Enhancements:
   - fs-specific prefix for fscrypto
   - fault injection facility
   - expose validity bitmaps for user to be aware of fragmentation
   - fallocate/rm/preallocation speed up
   - use percpu counters

  Bug fixes:
   - some inline_dentry/inline_data bugs
   - error handling for atomic/volatile/orphan inodes
   - recover broken superblock"

* tag 'for-f2fs-4.7' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (73 commits)
  f2fs: fix to update dirty page count correctly
  f2fs: flush pending bios right away when error occurs
  f2fs: avoid ENOSPC fault in the recovery process
  f2fs: make exit_f2fs_fs more clear
  f2fs: use percpu_counter for total_valid_inode_count
  f2fs: use percpu_counter for alloc_valid_block_count
  f2fs: use percpu_counter for # of dirty pages in inode
  f2fs: use percpu_counter for page counters
  f2fs: use bio count instead of F2FS_WRITEBACK page count
  f2fs: manipulate dirty file inodes when DATA_FLUSH is set
  f2fs: add fault injection to sysfs
  f2fs: no need inc dirty pages under inode lock
  f2fs: fix incorrect error path handling in f2fs_move_rehashed_dirents
  f2fs: fix i_current_depth during inline dentry conversion
  f2fs: correct return value type of f2fs_fill_super
  f2fs: fix deadlock when flush inline data
  f2fs: avoid f2fs_bug_on during recovery
  f2fs: show # of orphan inodes
  f2fs: support in batch fzero in dnode page
  f2fs: support in batch multi blocks preallocation
  ...

1 files changed, 137 insertions, 60 deletions

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index bb376c3bca62..9a8bbc1fb1fa 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -68,13 +68,12 @@ static void f2fs_write_end_io(struct bio *bio)
 
 		if (unlikely(bio->bi_error)) {
 			set_bit(AS_EIO, &page->mapping->flags);
-			f2fs_stop_checkpoint(sbi);
+			f2fs_stop_checkpoint(sbi, true);
 		}
 		end_page_writeback(page);
-		dec_page_count(sbi, F2FS_WRITEBACK);
 	}
-
-	if (!get_pages(sbi, F2FS_WRITEBACK) && wq_has_sleeper(&sbi->cp_wait))
+	if (atomic_dec_and_test(&sbi->nr_wb_bios) &&
+				wq_has_sleeper(&sbi->cp_wait))
 		wake_up(&sbi->cp_wait);
 
 	bio_put(bio);
@@ -98,6 +97,14 @@ static struct bio *__bio_alloc(struct f2fs_sb_info *sbi, block_t blk_addr,
 	return bio;
 }
 
+static inline void __submit_bio(struct f2fs_sb_info *sbi, int rw,
+						struct bio *bio)
+{
+	if (!is_read_io(rw))
+		atomic_inc(&sbi->nr_wb_bios);
+	submit_bio(rw, bio);
+}
+
 static void __submit_merged_bio(struct f2fs_bio_info *io)
 {
 	struct f2fs_io_info *fio = &io->fio;
@@ -110,7 +117,7 @@ static void __submit_merged_bio(struct f2fs_bio_info *io)
 	else
 		trace_f2fs_submit_write_bio(io->sbi->sb, fio, io->bio);
 
-	submit_bio(fio->rw, io->bio);
+	__submit_bio(io->sbi, fio->rw, io->bio);
 	io->bio = NULL;
 }
 
@@ -228,7 +235,7 @@ int f2fs_submit_page_bio(struct f2fs_io_info *fio)
 		return -EFAULT;
 	}
 
-	submit_bio(fio->rw, bio);
+	__submit_bio(fio->sbi, fio->rw, bio);
 	return 0;
 }
 
@@ -248,9 +255,6 @@ void f2fs_submit_page_mbio(struct f2fs_io_info *fio)
 
 	down_write(&io->io_rwsem);
 
-	if (!is_read)
-		inc_page_count(sbi, F2FS_WRITEBACK);
-
 	if (io->bio && (io->last_block_in_bio != fio->new_blkaddr - 1 ||
 						io->fio.rw != fio->rw))
 		__submit_merged_bio(io);
@@ -278,6 +282,16 @@ alloc_new:
 	trace_f2fs_submit_page_mbio(fio->page, fio);
 }
 
+static void __set_data_blkaddr(struct dnode_of_data *dn)
+{
+	struct f2fs_node *rn = F2FS_NODE(dn->node_page);
+	__le32 *addr_array;
+
+	/* Get physical address of data block */
+	addr_array = blkaddr_in_node(rn);
+	addr_array[dn->ofs_in_node] = cpu_to_le32(dn->data_blkaddr);
+}
+
 /*
  * Lock ordering for the change of data block address:
  * ->data_page
@@ -286,19 +300,9 @@ alloc_new:
  */
 void set_data_blkaddr(struct dnode_of_data *dn)
 {
-	struct f2fs_node *rn;
-	__le32 *addr_array;
-	struct page *node_page = dn->node_page;
-	unsigned int ofs_in_node = dn->ofs_in_node;
-
-	f2fs_wait_on_page_writeback(node_page, NODE, true);
-
-	rn = F2FS_NODE(node_page);
-
-	/* Get physical address of data block */
-	addr_array = blkaddr_in_node(rn);
-	addr_array[ofs_in_node] = cpu_to_le32(dn->data_blkaddr);
-	if (set_page_dirty(node_page))
+	f2fs_wait_on_page_writeback(dn->node_page, NODE, true);
+	__set_data_blkaddr(dn);
+	if (set_page_dirty(dn->node_page))
 		dn->node_changed = true;
 }
 
@@ -309,24 +313,53 @@ void f2fs_update_data_blkaddr(struct dnode_of_data *dn, block_t blkaddr)
 	f2fs_update_extent_cache(dn);
 }
 
-int reserve_new_block(struct dnode_of_data *dn)
+/* dn->ofs_in_node will be returned with up-to-date last block pointer */
+int reserve_new_blocks(struct dnode_of_data *dn, blkcnt_t count)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
 
+	if (!count)
+		return 0;
+
 	if (unlikely(is_inode_flag_set(F2FS_I(dn->inode), FI_NO_ALLOC)))
 		return -EPERM;
-	if (unlikely(!inc_valid_block_count(sbi, dn->inode, 1)))
+	if (unlikely(!inc_valid_block_count(sbi, dn->inode, &count)))
 		return -ENOSPC;
 
-	trace_f2fs_reserve_new_block(dn->inode, dn->nid, dn->ofs_in_node);
+	trace_f2fs_reserve_new_blocks(dn->inode, dn->nid,
+						dn->ofs_in_node, count);
+
+	f2fs_wait_on_page_writeback(dn->node_page, NODE, true);
+
+	for (; count > 0; dn->ofs_in_node++) {
+		block_t blkaddr =
+			datablock_addr(dn->node_page, dn->ofs_in_node);
+		if (blkaddr == NULL_ADDR) {
+			dn->data_blkaddr = NEW_ADDR;
+			__set_data_blkaddr(dn);
+			count--;
+		}
+	}
+
+	if (set_page_dirty(dn->node_page))
+		dn->node_changed = true;
 
-	dn->data_blkaddr = NEW_ADDR;
-	set_data_blkaddr(dn);
 	mark_inode_dirty(dn->inode);
 	sync_inode_page(dn);
 	return 0;
 }
 
+/* Should keep dn->ofs_in_node unchanged */
+int reserve_new_block(struct dnode_of_data *dn)
+{
+	unsigned int ofs_in_node = dn->ofs_in_node;
+	int ret;
+
+	ret = reserve_new_blocks(dn, 1);
+	dn->ofs_in_node = ofs_in_node;
+	return ret;
+}
+
 int f2fs_reserve_block(struct dnode_of_data *dn, pgoff_t index)
 {
 	bool need_put = dn->inode_page ? false : true;
@@ -545,6 +578,7 @@ static int __allocate_data_block(struct dnode_of_data *dn)
 	struct node_info ni;
 	int seg = CURSEG_WARM_DATA;
 	pgoff_t fofs;
+	blkcnt_t count = 1;
 
 	if (unlikely(is_inode_flag_set(F2FS_I(dn->inode), FI_NO_ALLOC)))
 		return -EPERM;
@@ -553,7 +587,7 @@ static int __allocate_data_block(struct dnode_of_data *dn)
 	if (dn->data_blkaddr == NEW_ADDR)
 		goto alloc;
 
-	if (unlikely(!inc_valid_block_count(sbi, dn->inode, 1)))
+	if (unlikely(!inc_valid_block_count(sbi, dn->inode, &count)))
 		return -ENOSPC;
 
 alloc:
@@ -582,8 +616,8 @@ ssize_t f2fs_preallocate_blocks(struct kiocb *iocb, struct iov_iter *from)
 	struct f2fs_map_blocks map;
 	ssize_t ret = 0;
 
-	map.m_lblk = F2FS_BYTES_TO_BLK(iocb->ki_pos);
-	map.m_len = F2FS_BLK_ALIGN(iov_iter_count(from));
+	map.m_lblk = F2FS_BLK_ALIGN(iocb->ki_pos);
+	map.m_len = F2FS_BYTES_TO_BLK(iov_iter_count(from));
 	map.m_next_pgofs = NULL;
 
 	if (f2fs_encrypted_inode(inode))
@@ -621,8 +655,10 @@ int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
 	struct dnode_of_data dn;
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	int mode = create ? ALLOC_NODE : LOOKUP_NODE_RA;
-	pgoff_t pgofs, end_offset;
+	pgoff_t pgofs, end_offset, end;
 	int err = 0, ofs = 1;
+	unsigned int ofs_in_node, last_ofs_in_node;
+	blkcnt_t prealloc;
 	struct extent_info ei;
 	bool allocated = false;
 	block_t blkaddr;
@@ -632,6 +668,7 @@ int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
 
 	/* it only supports block size == page size */
 	pgofs =	(pgoff_t)map->m_lblk;
+	end = pgofs + maxblocks;
 
 	if (!create && f2fs_lookup_extent_cache(inode, pgofs, &ei)) {
 		map->m_pblk = ei.blk + pgofs - ei.fofs;
@@ -648,6 +685,8 @@ next_dnode:
 	set_new_dnode(&dn, inode, NULL, NULL, 0);
 	err = get_dnode_of_data(&dn, pgofs, mode);
 	if (err) {
+		if (flag == F2FS_GET_BLOCK_BMAP)
+			map->m_pblk = 0;
 		if (err == -ENOENT) {
 			err = 0;
 			if (map->m_next_pgofs)
@@ -657,6 +696,8 @@ next_dnode:
 		goto unlock_out;
 	}
 
+	prealloc = 0;
+	ofs_in_node = dn.ofs_in_node;
 	end_offset = ADDRS_PER_PAGE(dn.node_page, inode);
 
 next_block:
@@ -669,31 +710,41 @@ next_block:
 				goto sync_out;
 			}
 			if (flag == F2FS_GET_BLOCK_PRE_AIO) {
-				if (blkaddr == NULL_ADDR)
-					err = reserve_new_block(&dn);
+				if (blkaddr == NULL_ADDR) {
+					prealloc++;
+					last_ofs_in_node = dn.ofs_in_node;
+				}
 			} else {
 				err = __allocate_data_block(&dn);
+				if (!err) {
+					set_inode_flag(F2FS_I(inode),
+							FI_APPEND_WRITE);
+					allocated = true;
+				}
 			}
 			if (err)
 				goto sync_out;
-			allocated = true;
 			map->m_flags = F2FS_MAP_NEW;
 			blkaddr = dn.data_blkaddr;
 		} else {
+			if (flag == F2FS_GET_BLOCK_BMAP) {
+				map->m_pblk = 0;
+				goto sync_out;
+			}
 			if (flag == F2FS_GET_BLOCK_FIEMAP &&
 						blkaddr == NULL_ADDR) {
 				if (map->m_next_pgofs)
 					*map->m_next_pgofs = pgofs + 1;
 			}
 			if (flag != F2FS_GET_BLOCK_FIEMAP ||
-						blkaddr != NEW_ADDR) {
-				if (flag == F2FS_GET_BLOCK_BMAP)
-					err = -ENOENT;
+						blkaddr != NEW_ADDR)
 				goto sync_out;
-			}
 		}
 	}
 
+	if (flag == F2FS_GET_BLOCK_PRE_AIO)
+		goto skip;
+
 	if (map->m_len == 0) {
 		/* preallocated unwritten block should be mapped for fiemap. */
 		if (blkaddr == NEW_ADDR)
@@ -705,32 +756,49 @@ next_block:
 	} else if ((map->m_pblk != NEW_ADDR &&
 			blkaddr == (map->m_pblk + ofs)) ||
 			(map->m_pblk == NEW_ADDR && blkaddr == NEW_ADDR) ||
-			flag == F2FS_GET_BLOCK_PRE_DIO ||
-			flag == F2FS_GET_BLOCK_PRE_AIO) {
+			flag == F2FS_GET_BLOCK_PRE_DIO) {
 		ofs++;
 		map->m_len++;
 	} else {
 		goto sync_out;
 	}
 
+skip:
 	dn.ofs_in_node++;
 	pgofs++;
 
-	if (map->m_len < maxblocks) {
-		if (dn.ofs_in_node < end_offset)
-			goto next_block;
+	/* preallocate blocks in batch for one dnode page */
+	if (flag == F2FS_GET_BLOCK_PRE_AIO &&
+			(pgofs == end || dn.ofs_in_node == end_offset)) {
 
-		if (allocated)
-			sync_inode_page(&dn);
-		f2fs_put_dnode(&dn);
+		dn.ofs_in_node = ofs_in_node;
+		err = reserve_new_blocks(&dn, prealloc);
+		if (err)
+			goto sync_out;
 
-		if (create) {
-			f2fs_unlock_op(sbi);
-			f2fs_balance_fs(sbi, allocated);
+		map->m_len += dn.ofs_in_node - ofs_in_node;
+		if (prealloc && dn.ofs_in_node != last_ofs_in_node + 1) {
+			err = -ENOSPC;
+			goto sync_out;
 		}
-		allocated = false;
-		goto next_dnode;
+		dn.ofs_in_node = end_offset;
+	}
+
+	if (pgofs >= end)
+		goto sync_out;
+	else if (dn.ofs_in_node < end_offset)
+		goto next_block;
+
+	if (allocated)
+		sync_inode_page(&dn);
+	f2fs_put_dnode(&dn);
+
+	if (create) {
+		f2fs_unlock_op(sbi);
+		f2fs_balance_fs(sbi, allocated);
 	}
+	allocated = false;
+	goto next_dnode;
 
 sync_out:
 	if (allocated)
@@ -983,7 +1051,7 @@ got_it:
 		 */
 		if (bio && (last_block_in_bio != block_nr - 1)) {
 submit_and_realloc:
-			submit_bio(READ, bio);
+			__submit_bio(F2FS_I_SB(inode), READ, bio);
 			bio = NULL;
 		}
 		if (bio == NULL) {
@@ -1026,7 +1094,7 @@ set_error_page:
 		goto next_page;
 confused:
 		if (bio) {
-			submit_bio(READ, bio);
+			__submit_bio(F2FS_I_SB(inode), READ, bio);
 			bio = NULL;
 		}
 		unlock_page(page);
@@ -1036,7 +1104,7 @@ next_page:
 	}
 	BUG_ON(pages && !list_empty(pages));
 	if (bio)
-		submit_bio(READ, bio);
+		__submit_bio(F2FS_I_SB(inode), READ, bio);
 	return 0;
 }
 
@@ -1177,8 +1245,10 @@ write:
 		goto redirty_out;
 	if (f2fs_is_drop_cache(inode))
 		goto out;
-	if (f2fs_is_volatile_file(inode) && !wbc->for_reclaim &&
-			available_free_memory(sbi, BASE_CHECK))
+	/* we should not write 0'th page having journal header */
+	if (f2fs_is_volatile_file(inode) && (!page->index ||
+			(!wbc->for_reclaim &&
+			available_free_memory(sbi, BASE_CHECK))))
 		goto redirty_out;
 
 	/* Dentry blocks are controlled by checkpoint */
@@ -1480,7 +1550,8 @@ restart:
 		if (pos + len <= MAX_INLINE_DATA) {
 			read_inline_data(page, ipage);
 			set_inode_flag(F2FS_I(inode), FI_DATA_EXIST);
-			set_inline_node(ipage);
+			if (inode->i_nlink)
+				set_inline_node(ipage);
 		} else {
 			err = f2fs_convert_inline_page(&dn, page);
 			if (err)
@@ -1496,7 +1567,7 @@ restart:
 		} else {
 			/* hole case */
 			err = get_dnode_of_data(&dn, index, LOOKUP_NODE);
-			if (err || (!err && dn.data_blkaddr == NULL_ADDR)) {
+			if (err || dn.data_blkaddr == NULL_ADDR) {
 				f2fs_put_dnode(&dn);
 				f2fs_lock_op(sbi);
 				locked = true;
@@ -1683,8 +1754,12 @@ static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 	trace_f2fs_direct_IO_enter(inode, offset, count, iov_iter_rw(iter));
 
 	err = blockdev_direct_IO(iocb, inode, iter, get_data_block_dio);
-	if (err < 0 && iov_iter_rw(iter) == WRITE)
-		f2fs_write_failed(mapping, offset + count);
+	if (iov_iter_rw(iter) == WRITE) {
+		if (err > 0)
+			set_inode_flag(F2FS_I(inode), FI_UPDATE_WRITE);
+		else if (err < 0)
+			f2fs_write_failed(mapping, offset + count);
+	}
 
 	trace_f2fs_direct_IO_exit(inode, offset, count, iov_iter_rw(iter), err);
 
@@ -1714,6 +1789,7 @@ void f2fs_invalidate_page(struct page *page, unsigned int offset,
 	if (IS_ATOMIC_WRITTEN_PAGE(page))
 		return;
 
+	set_page_private(page, 0);
 	ClearPagePrivate(page);
 }
 
@@ -1727,6 +1803,7 @@ int f2fs_release_page(struct page *page, gfp_t wait)
 	if (IS_ATOMIC_WRITTEN_PAGE(page))
 		return 0;
 
+	set_page_private(page, 0);
 	ClearPagePrivate(page);
 	return 1;
 }