When new_curseg() is allocating a new segment, if mode=fragment:xxx is
switched on in large section scenario, __get_next_segno() will select
the next segno randomly in the range of [0, maxsegno] in order to
fragment segments.

If the candidate segno is free, get_new_segment() will use it directly
as the new segment.

However, if the section of the candidate is not empty, and some other
segments have already been used, and have a different type (e.g NODE)
with the candidate (e.g DATA), GC will complain inconsistent segment
type later.

This could be reproduced by the following steps:

  dd if=/dev/zero of=test.img bs=1M count=10240
  mkfs.f2fs -s 128 test.img
  mount -t f2fs test.img /mnt -o mode=fragment:block
  echo 1 > /sys/fs/f2fs/loop0/max_fragment_chunk
  echo 512 > /sys/fs/f2fs/loop0/max_fragment_hole
  dd if=/dev/zero of=/mnt/testfile bs=4K count=100
  umount /mnt

  F2FS-fs (loop0): Inconsistent segment (4377) type [0, 1] in SSA and SIT

In order to allow simulating segment fragmentation in large section
scenario, this patch reduces the candidate range:
 * if curseg is the last segment in the section, return curseg->segno
   to make get_new_segment() itself find the next free segment.
 * if curseg is in the middle of the section, select candicate randomly
   in the range of [curseg + 1, last_seg_in_the_same_section] to keep
   type consistent.
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Sheng Yong <shengyong@oppo.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>