Add BPF hook support for getsockopts io_uring command. So, BPF cgroups
programs can run when SOCKET_URING_OP_GETSOCKOPT command is executed
through io_uring.
This implementation follows a similar approach to what
__sys_getsockopt() does, but, using USER_SOCKPTR() for optval instead of
kernel pointer.
Signed-off-by: Breno Leitao <[email protected]>
---
io_uring/uring_cmd.c | 18 +++++++++++++-----
1 file changed, 13 insertions(+), 5 deletions(-)
diff --git a/io_uring/uring_cmd.c b/io_uring/uring_cmd.c
index a567dd32df00..9e08a14760c3 100644
--- a/io_uring/uring_cmd.c
+++ b/io_uring/uring_cmd.c
@@ -5,6 +5,8 @@
#include <linux/io_uring.h>
#include <linux/security.h>
#include <linux/nospec.h>
+#include <linux/compat.h>
+#include <linux/bpf-cgroup.h>
#include <uapi/linux/io_uring.h>
#include <uapi/asm-generic/ioctls.h>
@@ -184,17 +186,23 @@ static inline int io_uring_cmd_getsockopt(struct socket *sock,
if (err)
return err;
- if (level == SOL_SOCKET) {
+ err = -EOPNOTSUPP;
+ if (level == SOL_SOCKET)
err = sk_getsockopt(sock->sk, level, optname,
USER_SOCKPTR(optval),
KERNEL_SOCKPTR(&optlen));
- if (err)
- return err;
+ if (!(issue_flags & IO_URING_F_COMPAT))
+ err = BPF_CGROUP_RUN_PROG_GETSOCKOPT(sock->sk, level,
+ optname,
+ USER_SOCKPTR(optval),
+ KERNEL_SOCKPTR(&optlen),
+ optlen, err);
+
+ if (!err)
return optlen;
- }
- return -EOPNOTSUPP;
+ return err;
}
static inline int io_uring_cmd_setsockopt(struct socket *sock,
--
2.34.1
On Thu, Aug 17, 2023 at 03:08:47PM -0400, Gabriel Krisman Bertazi wrote:
> Breno Leitao <[email protected]> writes:
>
> > Add BPF hook support for getsockopts io_uring command. So, BPF cgroups
> > programs can run when SOCKET_URING_OP_GETSOCKOPT command is executed
> > through io_uring.
> >
> > This implementation follows a similar approach to what
> > __sys_getsockopt() does, but, using USER_SOCKPTR() for optval instead of
> > kernel pointer.
> >
> > Signed-off-by: Breno Leitao <[email protected]>
> > ---
> > io_uring/uring_cmd.c | 18 +++++++++++++-----
> > 1 file changed, 13 insertions(+), 5 deletions(-)
> >
> > diff --git a/io_uring/uring_cmd.c b/io_uring/uring_cmd.c
> > index a567dd32df00..9e08a14760c3 100644
> > --- a/io_uring/uring_cmd.c
> > +++ b/io_uring/uring_cmd.c
> > @@ -5,6 +5,8 @@
> > #include <linux/io_uring.h>
> > #include <linux/security.h>
> > #include <linux/nospec.h>
> > +#include <linux/compat.h>
> > +#include <linux/bpf-cgroup.h>
> >
> > #include <uapi/linux/io_uring.h>
> > #include <uapi/asm-generic/ioctls.h>
> > @@ -184,17 +186,23 @@ static inline int io_uring_cmd_getsockopt(struct socket *sock,
> > if (err)
> > return err;
> >
> > - if (level == SOL_SOCKET) {
> > + err = -EOPNOTSUPP;
> > + if (level == SOL_SOCKET)
> > err = sk_getsockopt(sock->sk, level, optname,
> > USER_SOCKPTR(optval),
> > KERNEL_SOCKPTR(&optlen));
> > - if (err)
> > - return err;
> >
> > + if (!(issue_flags & IO_URING_F_COMPAT))
> > + err = BPF_CGROUP_RUN_PROG_GETSOCKOPT(sock->sk, level,
> > + optname,
> > + USER_SOCKPTR(optval),
> > + KERNEL_SOCKPTR(&optlen),
> > + optlen, err);
> > +
> > + if (!err)
> > return optlen;
> > - }
>
> Shouldn't you call sock->ops->getsockopt for level!=SOL_SOCKET prior to
> running the hook?
> Before this patch, it would bail out with EOPNOTSUPP,
> but now the bpf hook gets called even for level!=SOL_SOCKET, which
> doesn't fit __sys_getsockopt. Am I misreading the code?
Not really, sock->ops->getsockopt() does not suport sockptr_t, but
__user addresses, differently from setsockopt()
int (*setsockopt)(struct socket *sock, int level,
int optname, sockptr_t optval,
unsigned int optlen);
int (*getsockopt)(struct socket *sock, int level,
int optname, char __user *optval, int __user *optlen);
In order to be able to call sock->ops->getsockopt(), the callback
function will need to accepted sockptr.
On Mon, Aug 21, 2023 at 01:03:08PM -0400, Gabriel Krisman Bertazi wrote:
> Breno Leitao <[email protected]> writes:
>
> > On Thu, Aug 17, 2023 at 03:08:47PM -0400, Gabriel Krisman Bertazi wrote:
> >> Breno Leitao <[email protected]> writes:
> >>
> >> > Add BPF hook support for getsockopts io_uring command. So, BPF cgroups
> >> > programs can run when SOCKET_URING_OP_GETSOCKOPT command is executed
> >> > through io_uring.
> >> >
> >> > This implementation follows a similar approach to what
> >> > __sys_getsockopt() does, but, using USER_SOCKPTR() for optval instead of
> >> > kernel pointer.
> >> >
> >> > Signed-off-by: Breno Leitao <[email protected]>
> >> > ---
> >> > io_uring/uring_cmd.c | 18 +++++++++++++-----
> >> > 1 file changed, 13 insertions(+), 5 deletions(-)
> >> >
> >> > diff --git a/io_uring/uring_cmd.c b/io_uring/uring_cmd.c
> >> > index a567dd32df00..9e08a14760c3 100644
> >> > --- a/io_uring/uring_cmd.c
> >> > +++ b/io_uring/uring_cmd.c
> >> > @@ -5,6 +5,8 @@
> >> > #include <linux/io_uring.h>
> >> > #include <linux/security.h>
> >> > #include <linux/nospec.h>
> >> > +#include <linux/compat.h>
> >> > +#include <linux/bpf-cgroup.h>
> >> >
> >> > #include <uapi/linux/io_uring.h>
> >> > #include <uapi/asm-generic/ioctls.h>
> >> > @@ -184,17 +186,23 @@ static inline int io_uring_cmd_getsockopt(struct socket *sock,
> >> > if (err)
> >> > return err;
> >> >
> >> > - if (level == SOL_SOCKET) {
> >> > + err = -EOPNOTSUPP;
> >> > + if (level == SOL_SOCKET)
> >> > err = sk_getsockopt(sock->sk, level, optname,
> >> > USER_SOCKPTR(optval),
> >> > KERNEL_SOCKPTR(&optlen));
> >> > - if (err)
> >> > - return err;
> >> >
> >> > + if (!(issue_flags & IO_URING_F_COMPAT))
> >> > + err = BPF_CGROUP_RUN_PROG_GETSOCKOPT(sock->sk, level,
> >> > + optname,
> >> > + USER_SOCKPTR(optval),
> >> > + KERNEL_SOCKPTR(&optlen),
> >> > + optlen, err);
> >> > +
> >> > + if (!err)
> >> > return optlen;
> >> > - }
> >>
> >> Shouldn't you call sock->ops->getsockopt for level!=SOL_SOCKET prior to
> >> running the hook?
> >> Before this patch, it would bail out with EOPNOTSUPP,
> >> but now the bpf hook gets called even for level!=SOL_SOCKET, which
> >> doesn't fit __sys_getsockopt. Am I misreading the code?
> >
> > Not really, sock->ops->getsockopt() does not suport sockptr_t, but
> > __user addresses, differently from setsockopt()
> >
> > int (*setsockopt)(struct socket *sock, int level,
> > int optname, sockptr_t optval,
> > unsigned int optlen);
> > int (*getsockopt)(struct socket *sock, int level,
> > int optname, char __user *optval, int __user *optlen);
> >
> > In order to be able to call sock->ops->getsockopt(), the callback
> > function will need to accepted sockptr.
>
> So, it seems you won't support !SOL_SOCKETs here. Then, I think you
> shouldn't call the hook for those sockets. My main concern is that we
> remain compatible to __sys_getsockopt when invoking the hook.
>
> I think you should just have the following as the very first thing in
> the function (but after the security_ check).
>
> if (level != SOL_SOCKET)
> return -EOPNOTSUPP;
Gotcha. I will update. Thanks!