[PATCH v3] f2fs: fix to avoid data update racing between GC and DIO

From: Chao Yu
Date: Thu Jul 07 2016 - 00:52:58 EST


From: Chao Yu <yuchao0@xxxxxxxxxx>

Datas in file can be operated by GC and DIO simultaneously, so we will
face race case as below:

For write case:
Thread A Thread B
- generic_file_direct_write
- invalidate_inode_pages2_range
- f2fs_direct_IO
- do_blockdev_direct_IO
- do_direct_IO
- get_more_blocks
- f2fs_gc
- do_garbage_collect
- gc_data_segment
- move_data_page
- do_write_data_page
migrate data block to new block address
- dio_bio_submit
update user data to old block address

For read case:
Thread A Thread B
- generic_file_direct_write
- invalidate_inode_pages2_range
- f2fs_direct_IO
- do_blockdev_direct_IO
- do_direct_IO
- get_more_blocks
- f2fs_balance_fs
- f2fs_gc
- do_garbage_collect
- gc_data_segment
- move_data_page
- do_write_data_page
migrate data block to new block address
- write_checkpoint
- do_checkpoint
- clear_prefree_segments
- f2fs_issue_discard
discard old block adress
- dio_bio_submit
update user buffer from obsolete block address

In order to fix this, for one file, we should let DIO and GC getting exclusion
against with each other.

Signed-off-by: Chao Yu <yuchao0@xxxxxxxxxx>
---
v3: use semaphore to avoid racing in between read dio and write dio.
fs/f2fs/data.c | 4 ++++
fs/f2fs/f2fs.h | 1 +
fs/f2fs/gc.c | 13 +++++++++++++
fs/f2fs/super.c | 1 +
4 files changed, 19 insertions(+)

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index b6fd5bd..19197bb 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -1712,6 +1712,7 @@ static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
{
struct address_space *mapping = iocb->ki_filp->f_mapping;
struct inode *inode = mapping->host;
+ struct f2fs_inode_info *fi = F2FS_I(inode);
size_t count = iov_iter_count(iter);
loff_t offset = iocb->ki_pos;
int err;
@@ -1727,7 +1728,10 @@ static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)

trace_f2fs_direct_IO_enter(inode, offset, count, iov_iter_rw(iter));

+ down_read(&fi->dio_rwsem);
err = blockdev_direct_IO(iocb, inode, iter, get_data_block_dio);
+ up_read(&fi->dio_rwsem);
+
if (iov_iter_rw(iter) == WRITE) {
if (err > 0)
set_inode_flag(inode, FI_UPDATE_WRITE);
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index bf9a13a..2e439ec 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -474,6 +474,7 @@ struct f2fs_inode_info {
struct list_head inmem_pages; /* inmemory pages managed by f2fs */
struct mutex inmem_lock; /* lock for inmemory pages */
struct extent_tree *extent_tree; /* cached extent_tree entry */
+ struct rw_semaphore dio_rwsem; /* avoid racing between dio and gc */
};

static inline void get_extent_info(struct extent_info *ext,
diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
index c612137..a9bfb8d 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -755,12 +755,25 @@ next_step:
/* phase 3 */
inode = find_gc_inode(gc_list, dni.ino);
if (inode) {
+ struct f2fs_inode_info *fi = F2FS_I(inode);
+ bool locked = false;
+
+ if (S_ISREG(inode->i_mode)) {
+ if (!down_write_trylock(&fi->dio_rwsem))
+ continue;
+ locked = true;
+ }
+
start_bidx = start_bidx_of_node(nofs, inode)
+ ofs_in_node;
if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode))
move_encrypted_block(inode, start_bidx);
else
move_data_page(inode, start_bidx, gc_type);
+
+ if (locked)
+ up_write(&fi->dio_rwsem);
+
stat_inc_data_blk_count(sbi, 1, gc_type);
}
}
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index edd1b35..dde57fb 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -579,6 +579,7 @@ static struct inode *f2fs_alloc_inode(struct super_block *sb)
INIT_LIST_HEAD(&fi->gdirty_list);
INIT_LIST_HEAD(&fi->inmem_pages);
mutex_init(&fi->inmem_lock);
+ init_rwsem(&fi->dio_rwsem);

/* Will be used by directory only */
fi->i_dir_level = F2FS_SB(sb)->dir_level;
--
2.7.2