f2fs: introduce F2FS_IOC_START_ATOMIC_REPLACE

introduce a new ioctl to replace the whole content of a file atomically,
which means it induces truncate and content update at the same time.
We can start it with F2FS_IOC_START_ATOMIC_REPLACE and complete it with
F2FS_IOC_COMMIT_ATOMIC_WRITE. Or abort it with
F2FS_IOC_ABORT_ATOMIC_WRITE.
Signed-off-by: Daeho Jeong <daehojeong@google.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>

fs/f2fs/data.c

@@ -3466,6 +3466,9 @@ static int prepare_atomic_write_begin(struct f2fs_sb_info *sbi,
 	else if (*blk_addr != NULL_ADDR)
 		return 0;
 
+	if (is_inode_flag_set(inode, FI_ATOMIC_REPLACE))
+		goto reserve_block;
+
 	/* Look for the block in the original inode */
 	err = __find_data_block(inode, index, &ori_blk_addr);
 	if (err)

fs/f2fs/f2fs.h

@@ -769,6 +769,7 @@ enum {
 	FI_ALIGNED_WRITE,	/* enable aligned write */
 	FI_COW_FILE,		/* indicate COW file */
 	FI_ATOMIC_COMMITTED,	/* indicate atomic commit completed except disk sync */
+	FI_ATOMIC_REPLACE,	/* indicate atomic replace */
 	FI_MAX,			/* max flag, never be used */
 };
 

fs/f2fs/file.c

@@ -2034,7 +2034,7 @@ static int f2fs_ioc_getversion(struct file *filp, unsigned long arg)
 	return put_user(inode->i_generation, (int __user *)arg);
 }
 
-static int f2fs_ioc_start_atomic_write(struct file *filp)
+static int f2fs_ioc_start_atomic_write(struct file *filp, bool truncate)
 {
 	struct inode *inode = file_inode(filp);
 	struct user_namespace *mnt_userns = file_mnt_user_ns(filp);
@@ -2103,15 +2103,22 @@ static int f2fs_ioc_start_atomic_write(struct file *filp)
 
 	f2fs_write_inode(inode, NULL);
 
-	isize = i_size_read(inode);
-	fi->original_i_size = isize;
-	f2fs_i_size_write(fi->cow_inode, isize);
-
 	stat_inc_atomic_inode(inode);
 
 	set_inode_flag(inode, FI_ATOMIC_FILE);
 	set_inode_flag(fi->cow_inode, FI_COW_FILE);
 	clear_inode_flag(fi->cow_inode, FI_INLINE_DATA);
+
+	isize = i_size_read(inode);
+	fi->original_i_size = isize;
+	if (truncate) {
+		set_inode_flag(inode, FI_ATOMIC_REPLACE);
+		truncate_inode_pages_final(inode->i_mapping);
+		f2fs_i_size_write(inode, 0);
+		isize = 0;
+	}
+	f2fs_i_size_write(fi->cow_inode, isize);
+
 	f2fs_up_write(&fi->i_gc_rwsem[WRITE]);
 
 	f2fs_update_time(sbi, REQ_TIME);
@@ -4139,7 +4146,9 @@ static long __f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 	case FS_IOC_GETVERSION:
 		return f2fs_ioc_getversion(filp, arg);
 	case F2FS_IOC_START_ATOMIC_WRITE:
-		return f2fs_ioc_start_atomic_write(filp);
+		return f2fs_ioc_start_atomic_write(filp, false);
+	case F2FS_IOC_START_ATOMIC_REPLACE:
+		return f2fs_ioc_start_atomic_write(filp, true);
 	case F2FS_IOC_COMMIT_ATOMIC_WRITE:
 		return f2fs_ioc_commit_atomic_write(filp);
 	case F2FS_IOC_ABORT_ATOMIC_WRITE:

fs/f2fs/segment.c

@@ -197,6 +197,7 @@ void f2fs_abort_atomic_write(struct inode *inode, bool clean)
 	fi->cow_inode = NULL;
 	release_atomic_write_cnt(inode);
 	clear_inode_flag(inode, FI_ATOMIC_COMMITTED);
+	clear_inode_flag(inode, FI_ATOMIC_REPLACE);
 	clear_inode_flag(inode, FI_ATOMIC_FILE);
 	stat_dec_atomic_inode(inode);
 
@@ -261,14 +262,24 @@ static void __complete_revoke_list(struct inode *inode, struct list_head *head,
 					bool revoke)
 {
 	struct revoke_entry *cur, *tmp;
+	pgoff_t start_index = 0;
+	bool truncate = is_inode_flag_set(inode, FI_ATOMIC_REPLACE);
 
 	list_for_each_entry_safe(cur, tmp, head, list) {
-		if (revoke)
+		if (revoke) {
 			__replace_atomic_write_block(inode, cur->index,
 						cur->old_addr, NULL, true);
+		} else if (truncate) {
+			f2fs_truncate_hole(inode, start_index, cur->index);
+			start_index = cur->index + 1;
+		}
+
 		list_del(&cur->list);
 		kmem_cache_free(revoke_entry_slab, cur);
 	}
+
+	if (!revoke && truncate)
+		f2fs_do_truncate_blocks(inode, start_index * PAGE_SIZE, false);
 }
 
 static int __f2fs_commit_atomic_write(struct inode *inode)

include/uapi/linux/f2fs.h

@@ -42,6 +42,7 @@
 						struct f2fs_comp_option)
 #define F2FS_IOC_DECOMPRESS_FILE	_IO(F2FS_IOCTL_MAGIC, 23)
 #define F2FS_IOC_COMPRESS_FILE		_IO(F2FS_IOCTL_MAGIC, 24)
+#define F2FS_IOC_START_ATOMIC_REPLACE	_IO(F2FS_IOCTL_MAGIC, 25)
 
 /*
  * should be same as XFS_IOC_GOINGDOWN.