io_uring: add IOURING_REGISTER_RESTRICTIONS opcode

The new io_uring_register(2) IOURING_REGISTER_RESTRICTIONS opcode
permanently installs a feature allowlist on an io_ring_ctx.
The io_ring_ctx can then be passed to untrusted code with the
knowledge that only operations present in the allowlist can be
executed.

The allowlist approach ensures that new features added to io_uring
do not accidentally become available when an existing application
is launched on a newer kernel version.

Currently is it possible to restrict sqe opcodes, sqe flags, and
register opcodes.

IOURING_REGISTER_RESTRICTIONS can only be made once. Afterwards
it is not possible to change restrictions anymore.
This prevents untrusted code from removing restrictions.

Suggested-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This commit is contained in:
Stefano Garzarella
2020-08-27 16:58:30 +02:00
committed by Jens Axboe
parent 9d4a75efa2
commit 21b55dbc06
2 changed files with 154 additions and 1 deletions

View File

@@ -267,6 +267,7 @@ enum {
IORING_REGISTER_PROBE = 8,
IORING_REGISTER_PERSONALITY = 9,
IORING_UNREGISTER_PERSONALITY = 10,
IORING_REGISTER_RESTRICTIONS = 11,
/* this goes last */
IORING_REGISTER_LAST
@@ -295,4 +296,34 @@ struct io_uring_probe {
struct io_uring_probe_op ops[0];
};
struct io_uring_restriction {
__u16 opcode;
union {
__u8 register_op; /* IORING_RESTRICTION_REGISTER_OP */
__u8 sqe_op; /* IORING_RESTRICTION_SQE_OP */
__u8 sqe_flags; /* IORING_RESTRICTION_SQE_FLAGS_* */
};
__u8 resv;
__u32 resv2[3];
};
/*
* io_uring_restriction->opcode values
*/
enum {
/* Allow an io_uring_register(2) opcode */
IORING_RESTRICTION_REGISTER_OP = 0,
/* Allow an sqe opcode */
IORING_RESTRICTION_SQE_OP = 1,
/* Allow sqe flags */
IORING_RESTRICTION_SQE_FLAGS_ALLOWED = 2,
/* Require sqe flags (these flags must be set on each submission) */
IORING_RESTRICTION_SQE_FLAGS_REQUIRED = 3,
IORING_RESTRICTION_LAST
};
#endif