f2fs: fix to reserve space for IO align feature

https://bugzilla.kernel.org/show_bug.cgi?id=204137

With below script, we will hit panic during new segment allocation:

DISK=bingo.img
MOUNT_DIR=/mnt/f2fs

dd if=/dev/zero of=$DISK bs=1M count=105
mkfs.f2fe -a 1 -o 19 -t 1 -z 1 -f -q $DISK

mount -t f2fs $DISK $MOUNT_DIR -o "noinline_dentry,flush_merge,noextent_cache,mode=lfs,io_bits=7,fsync_mode=strict"

for (( i = 0; i < 4096; i++ )); do
	name=`head /dev/urandom | tr -dc A-Za-z0-9 | head -c 10`
	mkdir $MOUNT_DIR/$name
done

umount $MOUNT_DIR
rm $DISK

--- Core dump ---
Call Trace:
 allocate_segment_by_default+0x9d/0x100 [f2fs]
 f2fs_allocate_data_block+0x3c0/0x5c0 [f2fs]
 do_write_page+0x62/0x110 [f2fs]
 f2fs_outplace_write_data+0x43/0xc0 [f2fs]
 f2fs_do_write_data_page+0x386/0x560 [f2fs]
 __write_data_page+0x706/0x850 [f2fs]
 f2fs_write_cache_pages+0x267/0x6a0 [f2fs]
 f2fs_write_data_pages+0x19c/0x2e0 [f2fs]
 do_writepages+0x1c/0x70
 __filemap_fdatawrite_range+0xaa/0xe0
 filemap_fdatawrite+0x1f/0x30
 f2fs_sync_dirty_inodes+0x74/0x1f0 [f2fs]
 block_operations+0xdc/0x350 [f2fs]
 f2fs_write_checkpoint+0x104/0x1150 [f2fs]
 f2fs_sync_fs+0xa2/0x120 [f2fs]
 f2fs_balance_fs_bg+0x33c/0x390 [f2fs]
 f2fs_write_node_pages+0x4c/0x1f0 [f2fs]
 do_writepages+0x1c/0x70
 __writeback_single_inode+0x45/0x320
 writeback_sb_inodes+0x273/0x5c0
 wb_writeback+0xff/0x2e0
 wb_workfn+0xa1/0x370
 process_one_work+0x138/0x350
 worker_thread+0x4d/0x3d0
 kthread+0x109/0x140
 ret_from_fork+0x25/0x30

The root cause here is, with IO alignment feature enables, in worst
case, we need F2FS_IO_SIZE() free blocks space for single one 4k write
due to IO alignment feature will fill dummy pages to make IO being
aligned.

So we will easily run out of free segments during non-inline directory's
data writeback, even in process of foreground GC.

In order to fix this issue, I just propose to reserve additional free
space for IO alignment feature to handle worst case of free space usage
ratio during FGGC.

Fixes: 0a595ebaaa6b ("f2fs: support IO alignment for DATA and NODE writes")
Signed-off-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>

1 files changed, 44 insertions, 0 deletions

diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index ca5783fa56d5..053b508d1e4f 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -329,6 +329,46 @@ static inline void limit_reserve_root(struct f2fs_sb_info *sbi)
 					   F2FS_OPTION(sbi).s_resgid));
 }
 
+static inline int adjust_reserved_segment(struct f2fs_sb_info *sbi)
+{
+	unsigned int sec_blks = sbi->blocks_per_seg * sbi->segs_per_sec;
+	unsigned int avg_vblocks;
+	unsigned int wanted_reserved_segments;
+	block_t avail_user_block_count;
+
+	if (!F2FS_IO_ALIGNED(sbi))
+		return 0;
+
+	/* average valid block count in section in worst case */
+	avg_vblocks = sec_blks / F2FS_IO_SIZE(sbi);
+
+	/*
+	 * we need enough free space when migrating one section in worst case
+	 */
+	wanted_reserved_segments = (F2FS_IO_SIZE(sbi) / avg_vblocks) *
+						reserved_segments(sbi);
+	wanted_reserved_segments -= reserved_segments(sbi);
+
+	avail_user_block_count = sbi->user_block_count -
+				sbi->current_reserved_blocks -
+				F2FS_OPTION(sbi).root_reserved_blocks;
+
+	if (wanted_reserved_segments * sbi->blocks_per_seg >
+					avail_user_block_count) {
+		f2fs_err(sbi, "IO align feature can't grab additional reserved segment: %u, available segments: %u",
+			wanted_reserved_segments,
+			avail_user_block_count >> sbi->log_blocks_per_seg);
+		return -ENOSPC;
+	}
+
+	SM_I(sbi)->additional_reserved_segments = wanted_reserved_segments;
+
+	f2fs_info(sbi, "IO align feature needs additional reserved segment: %u",
+			 wanted_reserved_segments);
+
+	return 0;
+}
+
 static inline void adjust_unusable_cap_perc(struct f2fs_sb_info *sbi)
 {
 	if (!F2FS_OPTION(sbi).unusable_cap_perc)
@@ -4182,6 +4222,10 @@ try_onemore:
 		goto free_nm;
 	}
 
+	err = adjust_reserved_segment(sbi);
+	if (err)
+		goto free_nm;
+
 	/* For write statistics */
 	sbi->sectors_written_start = f2fs_get_sectors_written(sbi);