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>

5 files changed, 237 insertions, 0 deletions

diff --git a/net/bpfilter/Kconfig b/net/bpfilter/Kconfig
new file mode 100644
index 000000000000..60725c5f79db
--- /dev/null
+++ b/net/bpfilter/Kconfig
@@ -0,0 +1,16 @@
+menuconfig BPFILTER
+	bool "BPF based packet filtering framework (BPFILTER)"
+	default n
+	depends on NET && BPF
+	help
+	  This builds experimental bpfilter framework that is aiming to
+	  provide netfilter compatible functionality via BPF
+
+if BPFILTER
+config BPFILTER_UMH
+	tristate "bpfilter kernel module with user mode helper"
+	default m
+	help
+	  This builds bpfilter kernel module with embedded user mode helper
+endif
+
diff --git a/net/bpfilter/Makefile b/net/bpfilter/Makefile
new file mode 100644
index 000000000000..2af752c8ef5e
--- /dev/null
+++ b/net/bpfilter/Makefile
@@ -0,0 +1,30 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Makefile for the Linux BPFILTER layer.
+#
+
+hostprogs-y := bpfilter_umh
+bpfilter_umh-objs := main.o
+HOSTCFLAGS += -I. -Itools/include/
+ifeq ($(CONFIG_BPFILTER_UMH), y)
+# builtin bpfilter_umh should be compiled with -static
+# since rootfs isn't mounted at the time of __init
+# function is called and do_execv won't find elf interpreter
+HOSTLDFLAGS += -static
+endif
+
+# a bit of elf magic to convert bpfilter_umh binary into a binary blob
+# inside bpfilter_umh.o elf file referenced by
+# _binary_net_bpfilter_bpfilter_umh_start symbol
+# which bpfilter_kern.c passes further into umh blob loader at run-time
+quiet_cmd_copy_umh = GEN $@
+      cmd_copy_umh = echo ':' > $(obj)/.bpfilter_umh.o.cmd; \
+      $(OBJCOPY) -I binary -O $(CONFIG_OUTPUT_FORMAT) \
+      -B `$(OBJDUMP) -f $<|grep architecture|cut -d, -f1|cut -d' ' -f2` \
+      --rename-section .data=.init.rodata $< $@
+
+$(obj)/bpfilter_umh.o: $(obj)/bpfilter_umh
+	$(call cmd,copy_umh)
+
+obj-$(CONFIG_BPFILTER_UMH) += bpfilter.o
+bpfilter-objs += bpfilter_kern.o bpfilter_umh.o
diff --git a/net/bpfilter/bpfilter_kern.c b/net/bpfilter/bpfilter_kern.c
new file mode 100644
index 000000000000..7596314b61c7
--- /dev/null
+++ b/net/bpfilter/bpfilter_kern.c
@@ -0,0 +1,111 @@
+// SPDX-License-Identifier: GPL-2.0
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/umh.h>
+#include <linux/bpfilter.h>
+#include <linux/sched.h>
+#include <linux/sched/signal.h>
+#include <linux/fs.h>
+#include <linux/file.h>
+#include "msgfmt.h"
+
+#define UMH_start _binary_net_bpfilter_bpfilter_umh_start
+#define UMH_end _binary_net_bpfilter_bpfilter_umh_end
+
+extern char UMH_start;
+extern char UMH_end;
+
+static struct umh_info info;
+/* since ip_getsockopt() can run in parallel, serialize access to umh */
+static DEFINE_MUTEX(bpfilter_lock);
+
+static void shutdown_umh(struct umh_info *info)
+{
+	struct task_struct *tsk;
+
+	tsk = pid_task(find_vpid(info->pid), PIDTYPE_PID);
+	if (tsk)
+		force_sig(SIGKILL, tsk);
+	fput(info->pipe_to_umh);
+	fput(info->pipe_from_umh);
+}
+
+static void __stop_umh(void)
+{
+	if (bpfilter_process_sockopt) {
+		bpfilter_process_sockopt = NULL;
+		shutdown_umh(&info);
+	}
+}
+
+static void stop_umh(void)
+{
+	mutex_lock(&bpfilter_lock);
+	__stop_umh();
+	mutex_unlock(&bpfilter_lock);
+}
+
+static int __bpfilter_process_sockopt(struct sock *sk, int optname,
+				      char __user *optval,
+				      unsigned int optlen, bool is_set)
+{
+	struct mbox_request req;
+	struct mbox_reply reply;
+	loff_t pos;
+	ssize_t n;
+	int ret;
+
+	req.is_set = is_set;
+	req.pid = current->pid;
+	req.cmd = optname;
+	req.addr = (long)optval;
+	req.len = optlen;
+	mutex_lock(&bpfilter_lock);
+	n = __kernel_write(info.pipe_to_umh, &req, sizeof(req), &pos);
+	if (n != sizeof(req)) {
+		pr_err("write fail %zd\n", n);
+		__stop_umh();
+		ret = -EFAULT;
+		goto out;
+	}
+	pos = 0;
+	n = kernel_read(info.pipe_from_umh, &reply, sizeof(reply), &pos);
+	if (n != sizeof(reply)) {
+		pr_err("read fail %zd\n", n);
+		__stop_umh();
+		ret = -EFAULT;
+		goto out;
+	}
+	ret = reply.status;
+out:
+	mutex_unlock(&bpfilter_lock);
+	return ret;
+}
+
+static int __init load_umh(void)
+{
+	int err;
+
+	/* fork usermode process */
+	err = fork_usermode_blob(&UMH_start, &UMH_end - &UMH_start, &info);
+	if (err)
+		return err;
+	pr_info("Loaded bpfilter_umh pid %d\n", info.pid);
+
+	/* health check that usermode process started correctly */
+	if (__bpfilter_process_sockopt(NULL, 0, 0, 0, 0) != 0) {
+		stop_umh();
+		return -EFAULT;
+	}
+	bpfilter_process_sockopt = &__bpfilter_process_sockopt;
+	return 0;
+}
+
+static void __exit fini_umh(void)
+{
+	stop_umh();
+}
+module_init(load_umh);
+module_exit(fini_umh);
+MODULE_LICENSE("GPL");
diff --git a/net/bpfilter/main.c b/net/bpfilter/main.c
new file mode 100644
index 000000000000..81bbc1684896
--- /dev/null
+++ b/net/bpfilter/main.c
@@ -0,0 +1,63 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+#include <sys/uio.h>
+#include <errno.h>
+#include <stdio.h>
+#include <sys/socket.h>
+#include <fcntl.h>
+#include <unistd.h>
+#include "include/uapi/linux/bpf.h"
+#include <asm/unistd.h>
+#include "msgfmt.h"
+
+int debug_fd;
+
+static int handle_get_cmd(struct mbox_request *cmd)
+{
+	switch (cmd->cmd) {
+	case 0:
+		return 0;
+	default:
+		break;
+	}
+	return -ENOPROTOOPT;
+}
+
+static int handle_set_cmd(struct mbox_request *cmd)
+{
+	return -ENOPROTOOPT;
+}
+
+static void loop(void)
+{
+	while (1) {
+		struct mbox_request req;
+		struct mbox_reply reply;
+		int n;
+
+		n = read(0, &req, sizeof(req));
+		if (n != sizeof(req)) {
+			dprintf(debug_fd, "invalid request %d\n", n);
+			return;
+		}
+
+		reply.status = req.is_set ?
+			handle_set_cmd(&req) :
+			handle_get_cmd(&req);
+
+		n = write(1, &reply, sizeof(reply));
+		if (n != sizeof(reply)) {
+			dprintf(debug_fd, "reply failed %d\n", n);
+			return;
+		}
+	}
+}
+
+int main(void)
+{
+	debug_fd = open("/dev/console", 00000002 | 00000100);
+	dprintf(debug_fd, "Started bpfilter\n");
+	loop();
+	close(debug_fd);
+	return 0;
+}
diff --git a/net/bpfilter/msgfmt.h b/net/bpfilter/msgfmt.h
new file mode 100644
index 000000000000..98d121c62945
--- /dev/null
+++ b/net/bpfilter/msgfmt.h
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _NET_BPFILTER_MSGFMT_H
+#define _NET_BPFILTER_MSGFMT_H
+
+struct mbox_request {
+	__u64 addr;
+	__u32 len;
+	__u32 is_set;
+	__u32 cmd;
+	__u32 pid;
+};
+
+struct mbox_reply {
+	__u32 status;
+};
+
+#endif