f2fs: fix performance issue observed with multi-thread sequential read

This reverts the commit - "b93f771 - f2fs: remove writepages lock"
to fix the drop in sequential read throughput.

Test: ./tiotest -t 32 -d /data/tio_tmp -f 32 -b 524288 -k 1 -k 3 -L
device: UFS

Before -
read throughput: 185 MB/s
total read requests: 85177 (of these ~80000 are 4KB size requests).
total write requests: 2546 (of these ~2208 requests are written in 512KB).

After -
read throughput: 758 MB/s
total read requests: 2417 (of these ~2042 are 512KB reads).
total write requests: 2701 (of these ~2034 requests are written in 512KB).

Signed-off-by: Sahitya Tummala <stummala@codeaurora.org>
Reviewed-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>

fs/f2fs/data.c

@@ -2122,6 +2122,18 @@ continue_unlock:
 	return ret;
 }
 
+static inline bool __should_serialize_io(struct inode *inode,
+					struct writeback_control *wbc)
+{
+	if (!S_ISREG(inode->i_mode))
+		return false;
+	if (wbc->sync_mode != WB_SYNC_ALL)
+		return true;
+	if (get_dirty_pages(inode) >= SM_I(F2FS_I_SB(inode))->min_seq_blocks)
+		return true;
+	return false;
+}
+
 static int __f2fs_write_data_pages(struct address_space *mapping,
 						struct writeback_control *wbc,
 						enum iostat_type io_type)
@@ -2130,6 +2142,7 @@ static int __f2fs_write_data_pages(struct address_space *mapping,
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	struct blk_plug plug;
 	int ret;
+	bool locked = false;
 
 	/* deal with chardevs and other special file */
 	if (!mapping->a_ops->writepage)
@@ -2160,10 +2173,18 @@ static int __f2fs_write_data_pages(struct address_space *mapping,
 	else if (atomic_read(&sbi->wb_sync_req[DATA]))
 		goto skip_write;
 
+	if (__should_serialize_io(inode, wbc)) {
+		mutex_lock(&sbi->writepages);
+		locked = true;
+	}
+
 	blk_start_plug(&plug);
 	ret = f2fs_write_cache_pages(mapping, wbc, io_type);
 	blk_finish_plug(&plug);
 
+	if (locked)
+		mutex_unlock(&sbi->writepages);
+
 	if (wbc->sync_mode == WB_SYNC_ALL)
 		atomic_dec(&sbi->wb_sync_req[DATA]);
 	/*