net: add skeleton of bpfilter kernel module

bpfilter.ko consists of bpfilter_kern.c (normal kernel module code)
and user mode helper code that is embedded into bpfilter.ko

The steps to build bpfilter.ko are the following:
- main.c is compiled by HOSTCC into the bpfilter_umh elf executable file
- with quite a bit of objcopy and Makefile magic the bpfilter_umh elf file
  is converted into bpfilter_umh.o object file
  with _binary_net_bpfilter_bpfilter_umh_start and _end symbols
  Example:
  $ nm ./bld_x64/net/bpfilter/bpfilter_umh.o
  0000000000004cf8 T _binary_net_bpfilter_bpfilter_umh_end
  0000000000004cf8 A _binary_net_bpfilter_bpfilter_umh_size
  0000000000000000 T _binary_net_bpfilter_bpfilter_umh_start
- bpfilter_umh.o and bpfilter_kern.o are linked together into bpfilter.ko

bpfilter_kern.c is a normal kernel module code that calls
the fork_usermode_blob() helper to execute part of its own data
as a user mode process.

Notice that _binary_net_bpfilter_bpfilter_umh_start - end
is placed into .init.rodata section, so it's freed as soon as __init
function of bpfilter.ko is finished.
As part of __init the bpfilter.ko does first request/reply action
via two unix pipe provided by fork_usermode_blob() helper to
make sure that umh is healthy. If not it will kill it via pid.

Later bpfilter_process_sockopt() will be called from bpfilter hooks
in get/setsockopt() to pass iptable commands into umh via bpfilter.ko

If admin does 'rmmod bpfilter' the __exit code bpfilter.ko will
kill umh as well.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

4 files changed, 63 insertions, 0 deletions

diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile
index b379520f9133..7018f91c5a39 100644
--- a/net/ipv4/Makefile
+++ b/net/ipv4/Makefile
@@ -16,6 +16,8 @@ obj-y     := route.o inetpeer.o protocol.o \
 	     inet_fragment.o ping.o ip_tunnel_core.o gre_offload.o \
 	     metrics.o
 
+obj-$(CONFIG_BPFILTER) += bpfilter/
+
 obj-$(CONFIG_NET_IP_TUNNEL) += ip_tunnel.o
 obj-$(CONFIG_SYSCTL) += sysctl_net_ipv4.o
 obj-$(CONFIG_PROC_FS) += proc.o
diff --git a/net/ipv4/bpfilter/Makefile b/net/ipv4/bpfilter/Makefile
new file mode 100644
index 000000000000..ce262d76cc48
--- /dev/null
+++ b/net/ipv4/bpfilter/Makefile
@@ -0,0 +1,2 @@
+obj-$(CONFIG_BPFILTER) += sockopt.o
+
diff --git a/net/ipv4/bpfilter/sockopt.c b/net/ipv4/bpfilter/sockopt.c
new file mode 100644
index 000000000000..42a96d2d8d05
--- /dev/null
+++ b/net/ipv4/bpfilter/sockopt.c
@@ -0,0 +1,42 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/uaccess.h>
+#include <linux/bpfilter.h>
+#include <uapi/linux/bpf.h>
+#include <linux/wait.h>
+#include <linux/kmod.h>
+
+int (*bpfilter_process_sockopt)(struct sock *sk, int optname,
+				char __user *optval,
+				unsigned int optlen, bool is_set);
+EXPORT_SYMBOL_GPL(bpfilter_process_sockopt);
+
+int bpfilter_mbox_request(struct sock *sk, int optname, char __user *optval,
+			  unsigned int optlen, bool is_set)
+{
+	if (!bpfilter_process_sockopt) {
+		int err = request_module("bpfilter");
+
+		if (err)
+			return err;
+		if (!bpfilter_process_sockopt)
+			return -ECHILD;
+	}
+	return bpfilter_process_sockopt(sk, optname, optval, optlen, is_set);
+}
+
+int bpfilter_ip_set_sockopt(struct sock *sk, int optname, char __user *optval,
+			    unsigned int optlen)
+{
+	return bpfilter_mbox_request(sk, optname, optval, optlen, true);
+}
+
+int bpfilter_ip_get_sockopt(struct sock *sk, int optname, char __user *optval,
+			    int __user *optlen)
+{
+	int len;
+
+	if (get_user(len, optlen))
+		return -EFAULT;
+
+	return bpfilter_mbox_request(sk, optname, optval, len, false);
+}
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 5ad2d8ed3a3f..e0791faacb24 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -47,6 +47,8 @@
 #include <linux/errqueue.h>
 #include <linux/uaccess.h>
 
+#include <linux/bpfilter.h>
+
 /*
  *	SOL_IP control messages.
  */
@@ -1244,6 +1246,11 @@ int ip_setsockopt(struct sock *sk, int level,
 		return -ENOPROTOOPT;
 
 	err = do_ip_setsockopt(sk, level, optname, optval, optlen);
+#ifdef CONFIG_BPFILTER
+	if (optname >= BPFILTER_IPT_SO_SET_REPLACE &&
+	    optname < BPFILTER_IPT_SET_MAX)
+		err = bpfilter_ip_set_sockopt(sk, optname, optval, optlen);
+#endif
 #ifdef CONFIG_NETFILTER
 	/* we need to exclude all possible ENOPROTOOPTs except default case */
 	if (err == -ENOPROTOOPT && optname != IP_HDRINCL &&
@@ -1552,6 +1559,11 @@ int ip_getsockopt(struct sock *sk, int level,
 	int err;
 
 	err = do_ip_getsockopt(sk, level, optname, optval, optlen, 0);
+#ifdef CONFIG_BPFILTER
+	if (optname >= BPFILTER_IPT_SO_GET_INFO &&
+	    optname < BPFILTER_IPT_GET_MAX)
+		err = bpfilter_ip_get_sockopt(sk, optname, optval, optlen);
+#endif
 #ifdef CONFIG_NETFILTER
 	/* we need to exclude all possible ENOPROTOOPTs except default case */
 	if (err == -ENOPROTOOPT && optname != IP_PKTOPTIONS &&
@@ -1584,6 +1596,11 @@ int compat_ip_getsockopt(struct sock *sk, int level, int optname,
 	err = do_ip_getsockopt(sk, level, optname, optval, optlen,
 		MSG_CMSG_COMPAT);
 
+#ifdef CONFIG_BPFILTER
+	if (optname >= BPFILTER_IPT_SO_GET_INFO &&
+	    optname < BPFILTER_IPT_GET_MAX)
+		err = bpfilter_ip_get_sockopt(sk, optname, optval, optlen);
+#endif
 #ifdef CONFIG_NETFILTER
 	/* we need to exclude all possible ENOPROTOOPTs except default case */
 	if (err == -ENOPROTOOPT && optname != IP_PKTOPTIONS &&