For non-migration IO, we will keep order of data/node blocks' submitting
as allocation sequence by sorting IOs in per log io_list list, but for
migration IO, it could be out-of-order.
In LFS mode, we should keep all IOs including migration IO be ordered,
so that this patch fixes to add an additional lock to keep submitting
order.
Signed-off-by: Chao Yu <yuch...@huawei.com>
Signed-off-by: Yunlong Song <yunlong.s...@huawei.com>
---
fs/f2fs/f2fs.h | 2 ++
fs/f2fs/gc.c | 5 +++++
fs/f2fs/segment.c | 5 +++++
fs/f2fs/super.c | 1 +
4 files changed, 13 insertions(+)
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index e06b622ba661..233e00068472 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -1127,6 +1127,8 @@ struct f2fs_sb_info {
struct f2fs_bio_info *write_io[NR_PAGE_TYPE]; /* for write bios */
struct mutex wio_mutex[NR_PAGE_TYPE - 1][NR_TEMP_TYPE];
/* bio ordering for NODE/DATA */
+ /* keep migration IO order for LFS mode */
+ struct rw_semaphore io_order_lock;
mempool_t *write_io_dummy; /* Dummy pages */
/* for checkpoint */
diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
index 5ef3233c38d2..fca1d3745535 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -653,6 +653,9 @@ static void move_data_block(struct inode *inode, block_t
bidx,
fio.page = page;
fio.new_blkaddr = fio.old_blkaddr = dn.data_blkaddr;
+ if (test_opt(fio.sbi, LFS))
+ down_write(&fio.sbi->io_order_lock);
+
allocate_data_block(fio.sbi, NULL, fio.old_blkaddr, &newaddr,
&sum, CURSEG_COLD_DATA, NULL, false);
@@ -709,6 +712,8 @@ static void move_data_block(struct inode *inode, block_t
bidx,
put_page_out:
f2fs_put_page(fio.encrypted_page, 1);
recover_block:
+ if (test_opt(fio.sbi, LFS))
+ up_write(&fio.sbi->io_order_lock);
if (err)
__f2fs_replace_block(fio.sbi, &sum, newaddr, fio.old_blkaddr,
true, true);
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 697e7f8464b4..6b688e2d0b5d 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -2749,7 +2749,10 @@ static void do_write_page(struct f2fs_summary *sum,
struct f2fs_io_info *fio)
{
int type = __get_segment_type(fio);
int err;
+ bool keep_order = (test_opt(fio->sbi, LFS) && type == CURSEG_COLD_DATA);
+ if (keep_order)
+ down_read(&fio->sbi->io_order_lock);
reallocate:
allocate_data_block(fio->sbi, fio->page, fio->old_blkaddr,
&fio->new_blkaddr, sum, type, fio, true);
@@ -2762,6 +2765,8 @@ static void do_write_page(struct f2fs_summary *sum,
struct f2fs_io_info *fio)
} else if (!err) {
update_device_state(fio);
}
+ if (keep_order)
+ up_read(&fio->sbi->io_order_lock);
}
void write_meta_page(struct f2fs_sb_info *sbi, struct page *page,
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 8e5f0a178f5d..1b42fc7e4b29 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -2365,6 +2365,7 @@ static void init_sb_info(struct f2fs_sb_info *sbi)
for (i = 0; i < NR_PAGE_TYPE - 1; i++)
for (j = HOT; j < NR_TEMP_TYPE; j++)
mutex_init(&sbi->wio_mutex[i][j]);
+ init_rwsem(&sbi->io_order_lock);
spin_lock_init(&sbi->cp_lock);
sbi->dirty_device = 0;
--
2.17.0.391.g1f1cddd558b5
