f2fs: add F2FS_IOC_SEC_TRIM_FILE ioctl

Added a new ioctl to send discard commands or/and zero out
to selected data area of a regular file for security reason.

The way of handling range.len of F2FS_IOC_SEC_TRIM_FILE:
1. Added -1 value support for range.len to secure trim the whole blocks
   starting from range.start regardless of i_size.
2. If the end of the range passes over the end of file, it means until
   the end of file (i_size).
3. ignored the case of that range.len is zero to prevent the function
   from making end_addr zero and triggering different behaviour of
   the function.

Signed-off-by: Daeho Jeong <daehojeong@google.com>
Reviewed-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>

1 files changed, 191 insertions, 0 deletions

diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 521987cd8772..cc7f5670390f 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -21,6 +21,7 @@
 #include <linux/uuid.h>
 #include <linux/file.h>
 #include <linux/nls.h>
+#include <linux/sched/signal.h>
 
 #include "f2fs.h"
 #include "node.h"
@@ -3759,6 +3760,193 @@ out:
 	return ret;
 }
 
+static int f2fs_secure_erase(struct block_device *bdev, struct inode *inode,
+		pgoff_t off, block_t block, block_t len, u32 flags)
+{
+	struct request_queue *q = bdev_get_queue(bdev);
+	sector_t sector = SECTOR_FROM_BLOCK(block);
+	sector_t nr_sects = SECTOR_FROM_BLOCK(len);
+	int ret = 0;
+
+	if (!q)
+		return -ENXIO;
+
+	if (flags & F2FS_TRIM_FILE_DISCARD)
+		ret = blkdev_issue_discard(bdev, sector, nr_sects, GFP_NOFS,
+						blk_queue_secure_erase(q) ?
+						BLKDEV_DISCARD_SECURE : 0);
+
+	if (!ret && (flags & F2FS_TRIM_FILE_ZEROOUT)) {
+		if (IS_ENCRYPTED(inode))
+			ret = fscrypt_zeroout_range(inode, off, block, len);
+		else
+			ret = blkdev_issue_zeroout(bdev, sector, nr_sects,
+					GFP_NOFS, 0);
+	}
+
+	return ret;
+}
+
+static int f2fs_sec_trim_file(struct file *filp, unsigned long arg)
+{
+	struct inode *inode = file_inode(filp);
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	struct address_space *mapping = inode->i_mapping;
+	struct block_device *prev_bdev = NULL;
+	struct f2fs_sectrim_range range;
+	pgoff_t index, pg_end, prev_index = 0;
+	block_t prev_block = 0, len = 0;
+	loff_t end_addr;
+	bool to_end = false;
+	int ret = 0;
+
+	if (!(filp->f_mode & FMODE_WRITE))
+		return -EBADF;
+
+	if (copy_from_user(&range, (struct f2fs_sectrim_range __user *)arg,
+				sizeof(range)))
+		return -EFAULT;
+
+	if (range.flags == 0 || (range.flags & ~F2FS_TRIM_FILE_MASK) ||
+			!S_ISREG(inode->i_mode))
+		return -EINVAL;
+
+	if (((range.flags & F2FS_TRIM_FILE_DISCARD) &&
+			!f2fs_hw_support_discard(sbi)) ||
+			((range.flags & F2FS_TRIM_FILE_ZEROOUT) &&
+			 IS_ENCRYPTED(inode) && f2fs_is_multi_device(sbi)))
+		return -EOPNOTSUPP;
+
+	file_start_write(filp);
+	inode_lock(inode);
+
+	if (f2fs_is_atomic_file(inode) || f2fs_compressed_file(inode) ||
+			range.start >= inode->i_size) {
+		ret = -EINVAL;
+		goto err;
+	}
+
+	if (range.len == 0)
+		goto err;
+
+	if (inode->i_size - range.start > range.len) {
+		end_addr = range.start + range.len;
+	} else {
+		end_addr = range.len == (u64)-1 ?
+			sbi->sb->s_maxbytes : inode->i_size;
+		to_end = true;
+	}
+
+	if (!IS_ALIGNED(range.start, F2FS_BLKSIZE) ||
+			(!to_end && !IS_ALIGNED(end_addr, F2FS_BLKSIZE))) {
+		ret = -EINVAL;
+		goto err;
+	}
+
+	index = F2FS_BYTES_TO_BLK(range.start);
+	pg_end = DIV_ROUND_UP(end_addr, F2FS_BLKSIZE);
+
+	ret = f2fs_convert_inline_inode(inode);
+	if (ret)
+		goto err;
+
+	down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
+	down_write(&F2FS_I(inode)->i_mmap_sem);
+
+	ret = filemap_write_and_wait_range(mapping, range.start,
+			to_end ? LLONG_MAX : end_addr - 1);
+	if (ret)
+		goto out;
+
+	truncate_inode_pages_range(mapping, range.start,
+			to_end ? -1 : end_addr - 1);
+
+	while (index < pg_end) {
+		struct dnode_of_data dn;
+		pgoff_t end_offset, count;
+		int i;
+
+		set_new_dnode(&dn, inode, NULL, NULL, 0);
+		ret = f2fs_get_dnode_of_data(&dn, index, LOOKUP_NODE);
+		if (ret) {
+			if (ret == -ENOENT) {
+				index = f2fs_get_next_page_offset(&dn, index);
+				continue;
+			}
+			goto out;
+		}
+
+		end_offset = ADDRS_PER_PAGE(dn.node_page, inode);
+		count = min(end_offset - dn.ofs_in_node, pg_end - index);
+		for (i = 0; i < count; i++, index++, dn.ofs_in_node++) {
+			struct block_device *cur_bdev;
+			block_t blkaddr = f2fs_data_blkaddr(&dn);
+
+			if (!__is_valid_data_blkaddr(blkaddr))
+				continue;
+
+			if (!f2fs_is_valid_blkaddr(sbi, blkaddr,
+						DATA_GENERIC_ENHANCE)) {
+				ret = -EFSCORRUPTED;
+				f2fs_put_dnode(&dn);
+				goto out;
+			}
+
+			cur_bdev = f2fs_target_device(sbi, blkaddr, NULL);
+			if (f2fs_is_multi_device(sbi)) {
+				int di = f2fs_target_device_index(sbi, blkaddr);
+
+				blkaddr -= FDEV(di).start_blk;
+			}
+
+			if (len) {
+				if (prev_bdev == cur_bdev &&
+						index == prev_index + len &&
+						blkaddr == prev_block + len) {
+					len++;
+				} else {
+					ret = f2fs_secure_erase(prev_bdev,
+						inode, prev_index, prev_block,
+						len, range.flags);
+					if (ret) {
+						f2fs_put_dnode(&dn);
+						goto out;
+					}
+
+					len = 0;
+				}
+			}
+
+			if (!len) {
+				prev_bdev = cur_bdev;
+				prev_index = index;
+				prev_block = blkaddr;
+				len = 1;
+			}
+		}
+
+		f2fs_put_dnode(&dn);
+
+		if (fatal_signal_pending(current)) {
+			ret = -EINTR;
+			goto out;
+		}
+		cond_resched();
+	}
+
+	if (len)
+		ret = f2fs_secure_erase(prev_bdev, inode, prev_index,
+				prev_block, len, range.flags);
+out:
+	up_write(&F2FS_I(inode)->i_mmap_sem);
+	up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
+err:
+	inode_unlock(inode);
+	file_end_write(filp);
+
+	return ret;
+}
+
 long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 {
 	if (unlikely(f2fs_cp_error(F2FS_I_SB(file_inode(filp)))))
@@ -3845,6 +4033,8 @@ long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 		return f2fs_release_compress_blocks(filp, arg);
 	case F2FS_IOC_RESERVE_COMPRESS_BLOCKS:
 		return f2fs_reserve_compress_blocks(filp, arg);
+	case F2FS_IOC_SEC_TRIM_FILE:
+		return f2fs_sec_trim_file(filp, arg);
 	default:
 		return -ENOTTY;
 	}
@@ -4014,6 +4204,7 @@ long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	case F2FS_IOC_GET_COMPRESS_BLOCKS:
 	case F2FS_IOC_RELEASE_COMPRESS_BLOCKS:
 	case F2FS_IOC_RESERVE_COMPRESS_BLOCKS:
+	case F2FS_IOC_SEC_TRIM_FILE:
 		break;
 	default:
 		return -ENOIOCTLCMD;