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>
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_BPFILTER_H
+#define _LINUX_BPFILTER_H
+
+#include <uapi/linux/bpfilter.h>
+
+struct sock;
+int bpfilter_ip_set_sockopt(struct sock *sk, int optname, char *optval,
+ unsigned int optlen);
+int bpfilter_ip_get_sockopt(struct sock *sk, int optname, char *optval,
+ int *optlen);
+extern int (*bpfilter_process_sockopt)(struct sock *sk, int optname,
+ char __user *optval,
+ unsigned int optlen, bool is_set);
+#endif
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _UAPI_LINUX_BPFILTER_H
+#define _UAPI_LINUX_BPFILTER_H
+
+#include <linux/if.h>
+
+enum {
+ BPFILTER_IPT_SO_SET_REPLACE = 64,
+ BPFILTER_IPT_SO_SET_ADD_COUNTERS = 65,
+ BPFILTER_IPT_SET_MAX,
+};
+
+enum {
+ BPFILTER_IPT_SO_GET_INFO = 64,
+ BPFILTER_IPT_SO_GET_ENTRIES = 65,
+ BPFILTER_IPT_SO_GET_REVISION_MATCH = 66,
+ BPFILTER_IPT_SO_GET_REVISION_TARGET = 67,
+ BPFILTER_IPT_GET_MAX,
+};
+
+#endif /* _UAPI_LINUX_BPFILTER_H */
endif
+source "net/bpfilter/Kconfig"
+
source "net/dccp/Kconfig"
source "net/sctp/Kconfig"
source "net/rds/Kconfig"
obj-$(CONFIG_XFRM) += xfrm/
obj-$(CONFIG_UNIX) += unix/
obj-$(CONFIG_NET) += ipv6/
+obj-$(CONFIG_BPFILTER) += bpfilter/
obj-$(CONFIG_PACKET) += packet/
obj-$(CONFIG_NET_KEY) += key/
obj-$(CONFIG_BRIDGE) += bridge/
--- /dev/null
+menuconfig BPFILTER
+ bool "BPF based packet filtering framework (BPFILTER)"
+ default n
+ depends on NET && BPF
+ help
+ This builds experimental bpfilter framework that is aiming to
+ provide netfilter compatible functionality via BPF
+
+if BPFILTER
+config BPFILTER_UMH
+ tristate "bpfilter kernel module with user mode helper"
+ default m
+ help
+ This builds bpfilter kernel module with embedded user mode helper
+endif
+
--- /dev/null
+# SPDX-License-Identifier: GPL-2.0
+#
+# Makefile for the Linux BPFILTER layer.
+#
+
+hostprogs-y := bpfilter_umh
+bpfilter_umh-objs := main.o
+HOSTCFLAGS += -I. -Itools/include/
+ifeq ($(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
--- /dev/null
+// 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");
--- /dev/null
+// 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;
+}
--- /dev/null
+/* 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
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
--- /dev/null
+obj-$(CONFIG_BPFILTER) += sockopt.o
+
--- /dev/null
+// 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);
+}
#include <linux/errqueue.h>
#include <linux/uaccess.h>
+#include <linux/bpfilter.h>
+
/*
* SOL_IP control messages.
*/
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 &&
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 &&
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 &&
OSDN Git Service
