Add a mount option which allows root to be able to access the
ciphertext of a file by reading it using O_DIRECT.
Signed-off-by: Theodore Ts'o <tytso@xxxxxxx>
---
fs/ext4/ext4.h | 3 +++
fs/ext4/file.c | 5 ++++-
fs/ext4/indirect.c | 24 +++++++++++++++++++-----
fs/ext4/inode.c | 17 ++++++++++-------
fs/ext4/super.c | 48 ++++++++++++++++++++++++++++++++++++++++++++++++
5 files changed, 84 insertions(+), 13 deletions(-)
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 1e20fa9..cf7a885 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1052,6 +1052,7 @@ struct ext4_inode_info {
#define EXT4_MOUNT_DIOREAD_NOLOCK 0x400000 /* Enable support for dio read nolocking */
#define EXT4_MOUNT_JOURNAL_CHECKSUM 0x800000 /* Journal checksums */
#define EXT4_MOUNT_JOURNAL_ASYNC_COMMIT 0x1000000 /* Journal Async Commit */
+#define EXT4_MOUNT_CIPHERTEXT_ACCESS 0x2000000 /* Direct I/O to ciphertext */
#define EXT4_MOUNT_DELALLOC 0x8000000 /* Delalloc support */
#define EXT4_MOUNT_DATA_ERR_ABORT 0x10000000 /* Abort on file data write */
#define EXT4_MOUNT_BLOCK_VALIDITY 0x20000000 /* Block validity checking */
@@ -2564,6 +2565,8 @@ extern int ext4_alloc_flex_bg_array(struct super_block *sb,
ext4_group_t ngroup);
extern const char *ext4_decode_error(struct super_block *sb, int errno,
char nbuf[16]);
+extern struct inode *ext4_alloc_shadow_inode(struct inode *inode);
+extern void ext4_free_shadow_inode(struct inode *shadow);
extern __printf(4, 5)
void __ext4_error(struct super_block *, const char *, unsigned int,
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 749b222..60683ab 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -388,7 +388,10 @@ static int ext4_file_open(struct inode * inode, struct file * filp)
ret = ext4_get_encryption_info(inode);
if (ret)
return -EACCES;
- if (ext4_encryption_info(inode) == NULL)
+ if ((ext4_encryption_info(inode) == NULL) &&
+ !(test_opt(inode->i_sb, CIPHERTEXT_ACCESS) &&
+ ((filp->f_flags & O_ACCMODE) == O_RDONLY) &&
+ capable(CAP_SYS_ADMIN)))
return -ENOKEY;
}
/*
diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c
index 355ef9c..e685736 100644
--- a/fs/ext4/indirect.c
+++ b/fs/ext4/indirect.c
@@ -649,17 +649,17 @@ ssize_t ext4_ind_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
+ struct inode *shadow = inode;
struct ext4_inode_info *ei = EXT4_I(inode);
handle_t *handle;
ssize_t ret;
int orphan = 0;
size_t count = iov_iter_count(iter);
int retries = 0;
+ loff_t final_size = offset + count;
if (iov_iter_rw(iter) == WRITE) {
- loff_t final_size = offset + count;
-
- if (final_size > inode->i_size) {
+ if (final_size > i_size_read(inode)) {
/* Credits for sb + inode write */
handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);
if (IS_ERR(handle)) {
@@ -676,6 +676,18 @@ ssize_t ext4_ind_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
ext4_journal_stop(handle);
}
}
+ if (iov_iter_rw(iter) == READ &&
+ ext4_encrypted_inode(inode) &&
+ is_sync_kiocb(iocb) &&
+ final_size > i_size_read(inode)) {
+ shadow = ext4_alloc_shadow_inode(inode);
+ if (shadow)
+ i_size_write(shadow,
+ round_up(i_size_read(inode),
+ inode->i_sb->s_blocksize));
+ else
+ shadow = inode;
+ }
retry:
if (iov_iter_rw(iter) == READ && ext4_should_dioread_nolock(inode)) {
@@ -695,7 +707,7 @@ retry:
ret = dax_do_io(iocb, inode, iter, offset,
ext4_get_block, NULL, 0);
else
- ret = __blockdev_direct_IO(iocb, inode,
+ ret = __blockdev_direct_IO(iocb, shadow,
inode->i_sb->s_bdev, iter,
offset, ext4_get_block, NULL,
NULL, 0);
@@ -706,7 +718,7 @@ locked:
ret = dax_do_io(iocb, inode, iter, offset,
ext4_get_block, NULL, DIO_LOCKING);
else
- ret = blockdev_direct_IO(iocb, inode, iter, offset,
+ ret = blockdev_direct_IO(iocb, shadow, iter, offset,
ext4_get_block);
if (unlikely(iov_iter_rw(iter) == WRITE && ret < 0)) {
@@ -757,6 +769,8 @@ locked:
ret = err;
}
out:
+ if (shadow != inode)
+ ext4_free_shadow_inode(shadow);
return ret;
}
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index ff2f3cd..16f6537 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -3279,9 +3279,6 @@ static ssize_t ext4_ext_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
get_block_func = ext4_get_block_write;
dio_flags = DIO_LOCKING;
}
-#ifdef CONFIG_EXT4_FS_ENCRYPTION
- BUG_ON(ext4_encrypted_inode(inode) && S_ISREG(inode->i_mode));
-#endif
if (IS_DAX(inode))
ret = dax_do_io(iocb, inode, iter, offset, get_block_func,
ext4_end_io_dio, dio_flags);
@@ -3344,10 +3341,16 @@ static ssize_t ext4_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
size_t count = iov_iter_count(iter);
ssize_t ret;
-#ifdef CONFIG_EXT4_FS_ENCRYPTION
- if (ext4_encrypted_inode(inode) && S_ISREG(inode->i_mode))
- return 0;
-#endif
+ if (ext4_encrypted_inode(inode) && S_ISREG(inode->i_mode)) {
+ if (iov_iter_rw(iter) == WRITE)
+ return 0;
+ if (test_opt(inode->i_sb, CIPHERTEXT_ACCESS) &&
+ capable(CAP_SYS_ADMIN)) {
+ if (iov_iter_rw(iter) == WRITE)
+ return -EPERM;
+ } else
+ return 0;
+ }
/*
* If we are doing data journalling we don't support O_DIRECT
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 486e869..6173b46 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1033,6 +1033,49 @@ void ext4_clear_inode(struct inode *inode)
#endif
}
+/*
+ * Create a copy of the inode structure so when we are reading the
+ * last block of an encrypted inode using direct I/O to get the
+ * ciphertext, we can futz with the i_size in the shadow inode. This
+ * is necessary so that we can make a copy of the full AES block when
+ * i_size is not a multiple of the AES block size.
+ */
+struct inode *ext4_alloc_shadow_inode(struct inode *inode)
+{
+ struct ext4_inode_info *shadow_ei, *ei = EXT4_I(inode);
+ struct inode *shadow;
+
+ shadow_ei = kmem_cache_alloc(ext4_inode_cachep, GFP_NOFS);
+ if (!shadow_ei)
+ return NULL;
+
+ memcpy(shadow_ei, ei, sizeof(struct ext4_inode_info));
+ shadow = &shadow_ei->vfs_inode;
+
+ init_rwsem(&shadow_ei->xattr_sem);
+ init_rwsem(&shadow_ei->i_data_sem);
+ init_rwsem(&shadow_ei->i_mmap_sem);
+ i_size_ordered_init(shadow);
+ mutex_init(&shadow->i_mutex);
+ spin_lock_init(&shadow_ei->i_raw_lock);
+ spin_lock_init(&shadow_ei->i_prealloc_lock);
+ spin_lock_init(&(shadow_ei->i_block_reservation_lock));
+ spin_lock_init(&shadow_ei->i_completed_io_lock);
+ rwlock_init(&shadow_ei->i_es_lock);
+ ext4_es_init_tree(&shadow_ei->i_es_tree);
+ INIT_LIST_HEAD(&shadow_ei->i_es_list);
+ shadow_ei->i_es_all_nr = 0;
+ shadow_ei->i_es_shk_nr = 0;
+
+ return shadow;
+}
+
+void ext4_free_shadow_inode(struct inode *shadow)
+{
+ ext4_es_remove_extent(shadow, 0, EXT_MAX_BLOCKS);
+ kmem_cache_free(ext4_inode_cachep, EXT4_I(shadow));
+}
+
static struct inode *ext4_nfs_get_inode(struct super_block *sb,
u64 ino, u32 generation)
{
@@ -1182,6 +1225,7 @@ enum {
Opt_journal_path, Opt_journal_checksum, Opt_journal_async_commit,
Opt_abort, Opt_data_journal, Opt_data_ordered, Opt_data_writeback,
Opt_data_err_abort, Opt_data_err_ignore, Opt_test_dummy_encryption,
+ Opt_ciphertext_access, Opt_nociphertext_access,
Opt_usrjquota, Opt_grpjquota, Opt_offusrjquota, Opt_offgrpjquota,
Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_jqfmt_vfsv1, Opt_quota,
Opt_noquota, Opt_barrier, Opt_nobarrier, Opt_err,
@@ -1273,6 +1317,8 @@ static const match_table_t tokens = {
{Opt_noinit_itable, "noinit_itable"},
{Opt_max_dir_size_kb, "max_dir_size_kb=%u"},
{Opt_test_dummy_encryption, "test_dummy_encryption"},
+ {Opt_ciphertext_access, "ciphertext_access"},
+ {Opt_nociphertext_access, "nociphertext_access"},
{Opt_removed, "check=none"}, /* mount option from ext2/3 */
{Opt_removed, "nocheck"}, /* mount option from ext2/3 */
{Opt_removed, "reservation"}, /* mount option from ext2/3 */
@@ -1475,6 +1521,8 @@ static const struct mount_opts {
{Opt_jqfmt_vfsv1, QFMT_VFS_V1, MOPT_QFMT},
{Opt_max_dir_size_kb, 0, MOPT_GTE0},
{Opt_test_dummy_encryption, 0, MOPT_GTE0},
+ {Opt_ciphertext_access, EXT4_MOUNT_CIPHERTEXT_ACCESS, MOPT_SET},
+ {Opt_nociphertext_access, EXT4_MOUNT_CIPHERTEXT_ACCESS, MOPT_CLEAR},
{Opt_err, 0, 0}
};
--
2.5.0
--
To unsubscribe from this list: send the line "unsubscribe linux-ext4" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
