Merge tag 'for-f2fs-4.9' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs

Pull f2fs updates from Jaegeuk Kim:
 "In this round, we've investigated how f2fs deals with errors given by
  our fault injection facility. With this, we could fix several corner
  cases. And, in order to improve the performance, we set inline_dentry
  by default and enhance the exisiting discard issue flow. In addition,
  we added f2fs_migrate_page for better memory management.

  Enhancements:
   - set inline_dentry by default
   - improve discard issue flow
   - add more fault injection cases in f2fs
   - allow block preallocation for encrypted files
   - introduce migrate_page callback function
   - avoid truncating the next direct node block at every checkpoint

  Bug fixes:
   - set page flag correctly between write_begin and write_end
   - missing error handling cases detected by fault injection
   - preallocate blocks regarding to 4KB alignement correctly
   - dentry and filename handling of encryption
   - lost xattrs of directories"

* tag 'for-f2fs-4.9' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (69 commits)
  f2fs: introduce update_ckpt_flags to clean up
  f2fs: don't submit irrelevant page
  f2fs: fix to commit bio cache after flushing node pages
  f2fs: introduce get_checkpoint_version for cleanup
  f2fs: remove dead variable
  f2fs: remove redundant io plug
  f2fs: support checkpoint error injection
  f2fs: fix to recover old fault injection config in ->remount_fs
  f2fs: do fault injection initialization in default_options
  f2fs: remove redundant value definition
  f2fs: support configuring fault injection per superblock
  f2fs: adjust display format of segment bit
  f2fs: remove dirty inode pages in error path
  f2fs: do not unnecessarily null-terminate encrypted symlink data
  f2fs: handle errors during recover_orphan_inodes
  f2fs: avoid gc in cp_error case
  f2fs: should put_page for summary page
  f2fs: assign return value in f2fs_gc
  f2fs: add customized migrate_page callback
  f2fs: introduce cp_lock to protect updating of ckpt_flags
  ...

1 files changed, 101 insertions, 30 deletions

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index ccb401eebc11..0d0177c9149c 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -34,6 +34,11 @@ static void f2fs_read_end_io(struct bio *bio)
 	struct bio_vec *bvec;
 	int i;
 
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+	if (time_to_inject(F2FS_P_SB(bio->bi_io_vec->bv_page), FAULT_IO))
+		bio->bi_error = -EIO;
+#endif
+
 	if (f2fs_bio_encrypted(bio)) {
 		if (bio->bi_error) {
 			fscrypt_release_ctx(bio->bi_private);
@@ -626,11 +631,13 @@ ssize_t f2fs_preallocate_blocks(struct kiocb *iocb, struct iov_iter *from)
 	ssize_t ret = 0;
 
 	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;
+	map.m_len = F2FS_BYTES_TO_BLK(iocb->ki_pos + iov_iter_count(from));
+	if (map.m_len > map.m_lblk)
+		map.m_len -= map.m_lblk;
+	else
+		map.m_len = 0;
 
-	if (f2fs_encrypted_inode(inode))
-		return 0;
+	map.m_next_pgofs = NULL;
 
 	if (iocb->ki_flags & IOCB_DIRECT) {
 		ret = f2fs_convert_inline_inode(inode);
@@ -672,6 +679,9 @@ int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
 	bool allocated = false;
 	block_t blkaddr;
 
+	if (!maxblocks)
+		return 0;
+
 	map->m_len = 0;
 	map->m_flags = 0;
 
@@ -783,6 +793,7 @@ 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) {
@@ -966,8 +977,8 @@ out:
 	return ret;
 }
 
-struct bio *f2fs_grab_bio(struct inode *inode, block_t blkaddr,
-							unsigned nr_pages)
+static struct bio *f2fs_grab_bio(struct inode *inode, block_t blkaddr,
+				 unsigned nr_pages)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	struct fscrypt_ctx *ctx = NULL;
@@ -1284,7 +1295,7 @@ write:
 
 	if (!wbc->for_reclaim)
 		need_balance_fs = true;
-	else if (has_not_enough_free_secs(sbi, 0))
+	else if (has_not_enough_free_secs(sbi, 0, 0))
 		goto redirty_out;
 
 	err = -EAGAIN;
@@ -1344,6 +1355,7 @@ static int f2fs_write_cache_pages(struct address_space *mapping,
 	int cycled;
 	int range_whole = 0;
 	int tag;
+	int nwritten = 0;
 
 	pagevec_init(&pvec, 0);
 
@@ -1418,6 +1430,8 @@ continue_unlock:
 				done_index = page->index + 1;
 				done = 1;
 				break;
+			} else {
+				nwritten++;
 			}
 
 			if (--wbc->nr_to_write <= 0 &&
@@ -1439,6 +1453,10 @@ continue_unlock:
 	if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
 		mapping->writeback_index = done_index;
 
+	if (nwritten)
+		f2fs_submit_merged_bio_cond(F2FS_M_SB(mapping), mapping->host,
+							NULL, 0, DATA, WRITE);
+
 	return ret;
 }
 
@@ -1480,7 +1498,6 @@ static int f2fs_write_data_pages(struct address_space *mapping,
 	 * if some pages were truncated, we cannot guarantee its mapping->host
 	 * to detect pending bios.
 	 */
-	f2fs_submit_merged_bio(sbi, DATA, WRITE);
 
 	remove_dirty_inode(inode);
 	return ret;
@@ -1518,8 +1535,7 @@ static int prepare_write_begin(struct f2fs_sb_info *sbi,
 	 * we already allocated all the blocks, so we don't need to get
 	 * the block addresses when there is no need to fill the page.
 	 */
-	if (!f2fs_has_inline_data(inode) && !f2fs_encrypted_inode(inode) &&
-					len == PAGE_SIZE)
+	if (!f2fs_has_inline_data(inode) && len == PAGE_SIZE)
 		return 0;
 
 	if (f2fs_has_inline_data(inode) ||
@@ -1616,7 +1632,7 @@ repeat:
 	if (err)
 		goto fail;
 
-	if (need_balance && has_not_enough_free_secs(sbi, 0)) {
+	if (need_balance && has_not_enough_free_secs(sbi, 0, 0)) {
 		unlock_page(page);
 		f2fs_balance_fs(sbi, true);
 		lock_page(page);
@@ -1633,22 +1649,12 @@ repeat:
 	if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode))
 		f2fs_wait_on_encrypted_page_writeback(sbi, blkaddr);
 
-	if (len == PAGE_SIZE)
-		goto out_update;
-	if (PageUptodate(page))
-		goto out_clear;
-
-	if ((pos & PAGE_MASK) >= i_size_read(inode)) {
-		unsigned start = pos & (PAGE_SIZE - 1);
-		unsigned end = start + len;
-
-		/* Reading beyond i_size is simple: memset to zero */
-		zero_user_segments(page, 0, start, end, PAGE_SIZE);
-		goto out_update;
-	}
+	if (len == PAGE_SIZE || PageUptodate(page))
+		return 0;
 
 	if (blkaddr == NEW_ADDR) {
 		zero_user_segment(page, 0, PAGE_SIZE);
+		SetPageUptodate(page);
 	} else {
 		struct bio *bio;
 
@@ -1676,11 +1682,6 @@ repeat:
 			goto fail;
 		}
 	}
-out_update:
-	if (!PageUptodate(page))
-		SetPageUptodate(page);
-out_clear:
-	clear_cold_data(page);
 	return 0;
 
 fail:
@@ -1698,11 +1699,26 @@ static int f2fs_write_end(struct file *file,
 
 	trace_f2fs_write_end(inode, pos, len, copied);
 
+	/*
+	 * This should be come from len == PAGE_SIZE, and we expect copied
+	 * should be PAGE_SIZE. Otherwise, we treat it with zero copied and
+	 * let generic_perform_write() try to copy data again through copied=0.
+	 */
+	if (!PageUptodate(page)) {
+		if (unlikely(copied != PAGE_SIZE))
+			copied = 0;
+		else
+			SetPageUptodate(page);
+	}
+	if (!copied)
+		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);
-
+unlock_out:
 	f2fs_put_page(page, 1);
 	f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
 	return copied;
@@ -1873,6 +1889,58 @@ static sector_t f2fs_bmap(struct address_space *mapping, sector_t block)
 	return generic_block_bmap(mapping, block, get_data_block_bmap);
 }
 
+#ifdef CONFIG_MIGRATION
+#include <linux/migrate.h>
+
+int f2fs_migrate_page(struct address_space *mapping,
+		struct page *newpage, struct page *page, enum migrate_mode mode)
+{
+	int rc, extra_count;
+	struct f2fs_inode_info *fi = F2FS_I(mapping->host);
+	bool atomic_written = IS_ATOMIC_WRITTEN_PAGE(page);
+
+	BUG_ON(PageWriteback(page));
+
+	/* migrating an atomic written page is safe with the inmem_lock hold */
+	if (atomic_written && !mutex_trylock(&fi->inmem_lock))
+		return -EAGAIN;
+
+	/*
+	 * A reference is expected if PagePrivate set when move mapping,
+	 * however F2FS breaks this for maintaining dirty page counts when
+	 * truncating pages. So here adjusting the 'extra_count' make it work.
+	 */
+	extra_count = (atomic_written ? 1 : 0) - page_has_private(page);
+	rc = migrate_page_move_mapping(mapping, newpage,
+				page, NULL, mode, extra_count);
+	if (rc != MIGRATEPAGE_SUCCESS) {
+		if (atomic_written)
+			mutex_unlock(&fi->inmem_lock);
+		return rc;
+	}
+
+	if (atomic_written) {
+		struct inmem_pages *cur;
+		list_for_each_entry(cur, &fi->inmem_pages, list)
+			if (cur->page == page) {
+				cur->page = newpage;
+				break;
+			}
+		mutex_unlock(&fi->inmem_lock);
+		put_page(page);
+		get_page(newpage);
+	}
+
+	if (PagePrivate(page))
+		SetPagePrivate(newpage);
+	set_page_private(newpage, page_private(page));
+
+	migrate_page_copy(newpage, page);
+
+	return MIGRATEPAGE_SUCCESS;
+}
+#endif
+
 const struct address_space_operations f2fs_dblock_aops = {
 	.readpage	= f2fs_read_data_page,
 	.readpages	= f2fs_read_data_pages,
@@ -1885,4 +1953,7 @@ const struct address_space_operations f2fs_dblock_aops = {
 	.releasepage	= f2fs_release_page,
 	.direct_IO	= f2fs_direct_IO,
 	.bmap		= f2fs_bmap,
+#ifdef CONFIG_MIGRATION
+	.migratepage    = f2fs_migrate_page,
+#endif
 };