Merge branch 'bpfilter'

Alexei Starovoitov says:

====================
bpfilter

v2->v3:
- followed Luis's suggestion and significantly simplied first patch
  with shmem_kernel_file_setup+kernel_write. Added kdoc for new helper
- fixed typos and race to access pipes with mutex
- tested with bpfilter being 'builtin'. CONFIG_BPFILTER_UMH=y|m both work.
  Interesting to see a usermode executable being embedded inside vmlinux.
- it doesn't hurt to enable bpfilter in .config.
  ip_setsockopt commands sent to usermode via pipes and -ENOPROTOOPT is
  returned from userspace, so kernel falls back to original iptables code

v1->v2:
this patch set is almost a full rewrite of the earlier umh modules approach
The v1 of patches and follow up discussion was covered by LWN:
https://lwn.net/Articles/749108/

I believe the v2 addresses all issues brought up by Andy and others.
Mainly there are zero changes to kernel/module.c
Instead of teaching module loading logic to recognize special
umh module, let normal kernel modules execute part of its own
.init.rodata as a new user space process (Andy's idea)
Patch 1 introduces this new helper:
int fork_usermode_blob(void *data, size_t len, struct umh_info *info);
Input:
  data + len == executable file
Output:
  struct umh_info {
       struct file *pipe_to_umh;
       struct file *pipe_from_umh;
       pid_t pid;
  };

Advantages vs v1:
- the embedded user mode executable is stored as .init.rodata inside
  normal kernel module. These pages are freed when .ko finishes loading
- the elf file is copied into tmpfs file. The user mode process is swappable.
- the communication between user mode process and 'parent' kernel module
  is done via two unix pipes, hence protocol is not exposed to
  user space
- impossible to launch umh on its own (that was the main issue of v1)
  and impossible to be man-in-the-middle due to pipes
- bpfilter.ko consists of tiny kernel part that passes the data
  between kernel and umh via pipes and much bigger umh part that
  doing all the work
- 'lsmod' shows bpfilter.ko as usual.
  'rmmod bpfilter' removes kernel module and kills corresponding umh
- signed bpfilter.ko covers the whole image including umh code

Few issues:
- the user can still attach to the process and debug it with
  'gdb /proc/pid/exe pid', but 'gdb -p pid' doesn't work.
  (a bit worse comparing to v1)
- tinyconfig will notice a small increase in .text
  +766 | TEXT | 7c8b94806bec umh: introduce fork_usermode_blob() helper
====================

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 &&