Merge branch 'bpf-socket-cookie-uid'

Chenbo Feng says:

====================
net: core: Two Helper function about socket information

Introduce two eBpf helper function to get the socket cookie and
socket uid for each packet. The helper function is useful when
the *sk field inside sk_buff is not empty. These helper functions
can be used on socket and uid based traffic monitoring programs.

Change since V7:
* change the user namespace of uid helper function to sock_net(sk)->user_ns

Change since V6:
* change the user namespace of uid helper function back to init_user_ns
  since in some situation, for example, pinned bpf object, the current
  user namespace is not always applicable.

Change since V5:
* Delete unnecessary blank lines in sample program.
* Refine the variable orders in get_uid helper function.

Change since V4:
* Using current user namespace to get uid instead of using init_ns.
* Add compiling setup of example program in to Makefile.
* Change the name style of the example program binaries.

Change since V3:
* Fixed some typos and incorrect comments in sample program
* replaced raw insns with BPF_STX_XADD and add it to libbpf.h
* Use a temp dir as mount point instead and added a check for
  the user input string.
* Make the get uid helper function returns the user namespace uid
  instead of kuid.
* Return a overflowuid instead of 0 when no uid information is found.

Change since V2:
* Add a sample program to demostrate the usage of the helper function.
* Moved the helper function proto invoking place.
* Add function header into tools/include
* Apply sk_to_full_sk() before getting uid.

Change since V1:
* Removed the unnecessary declarations and export command
* resolved conflict with master branch.
* Examine if the socket is a full socket before getting the uid.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

include/linux/sock_diag.h

@@ -24,6 +24,7 @@ void sock_diag_unregister(const struct sock_diag_handler *h);
 void sock_diag_register_inet_compat(int (*fn)(struct sk_buff *skb, struct nlmsghdr *nlh));
 void sock_diag_unregister_inet_compat(int (*fn)(struct sk_buff *skb, struct nlmsghdr *nlh));
 
+u64 sock_gen_cookie(struct sock *sk);
 int sock_diag_check_cookie(struct sock *sk, const __u32 *cookie);
 void sock_diag_save_cookie(struct sock *sk, __u32 *cookie);
 

include/uapi/linux/bpf.h

@@ -459,6 +459,18 @@ union bpf_attr {
  *     Return:
  *       > 0 length of the string including the trailing NUL on success
  *       < 0 error
+ *
+ * u64 bpf_bpf_get_socket_cookie(skb)
+ *     Get the cookie for the socket stored inside sk_buff.
+ *     @skb: pointer to skb
+ *     Return: 8 Bytes non-decreasing number on success or 0 if the socket
+ *     field is missing inside sk_buff
+ *
+ * u32 bpf_get_socket_uid(skb)
+ *     Get the owner uid of the socket stored inside sk_buff.
+ *     @skb: pointer to skb
+ *     Return: uid of the socket owner on success or 0 if the socket pointer
+ *     inside sk_buff is NULL
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -506,7 +518,9 @@ union bpf_attr {
 	FN(get_numa_node_id),		\
 	FN(skb_change_head),		\
 	FN(xdp_adjust_head),		\
-	FN(probe_read_str),
+	FN(probe_read_str),		\
+	FN(get_socket_cookie),		\
+	FN(get_socket_uid),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call

net/core/filter.c

@@ -26,6 +26,7 @@
 #include <linux/mm.h>
 #include <linux/fcntl.h>
 #include <linux/socket.h>
+#include <linux/sock_diag.h>
 #include <linux/in.h>
 #include <linux/inet.h>
 #include <linux/netdevice.h>
@@ -2606,6 +2607,36 @@ static const struct bpf_func_proto bpf_xdp_event_output_proto = {
 	.arg5_type	= ARG_CONST_SIZE,
 };
 
+BPF_CALL_1(bpf_get_socket_cookie, struct sk_buff *, skb)
+{
+	return skb->sk ? sock_gen_cookie(skb->sk) : 0;
+}
+
+static const struct bpf_func_proto bpf_get_socket_cookie_proto = {
+	.func           = bpf_get_socket_cookie,
+	.gpl_only       = false,
+	.ret_type       = RET_INTEGER,
+	.arg1_type      = ARG_PTR_TO_CTX,
+};
+
+BPF_CALL_1(bpf_get_socket_uid, struct sk_buff *, skb)
+{
+	struct sock *sk = sk_to_full_sk(skb->sk);
+	kuid_t kuid;
+
+	if (!sk || !sk_fullsock(sk))
+		return overflowuid;
+	kuid = sock_net_uid(sock_net(sk), sk);
+	return from_kuid_munged(sock_net(sk)->user_ns, kuid);
+}
+
+static const struct bpf_func_proto bpf_get_socket_uid_proto = {
+	.func           = bpf_get_socket_uid,
+	.gpl_only       = false,
+	.ret_type       = RET_INTEGER,
+	.arg1_type      = ARG_PTR_TO_CTX,
+};
+
 static const struct bpf_func_proto *
 bpf_base_func_proto(enum bpf_func_id func_id)
 {
@@ -2640,6 +2671,10 @@ sk_filter_func_proto(enum bpf_func_id func_id)
 	switch (func_id) {
 	case BPF_FUNC_skb_load_bytes:
 		return &bpf_skb_load_bytes_proto;
+	case BPF_FUNC_get_socket_cookie:
+		return &bpf_get_socket_cookie_proto;
+	case BPF_FUNC_get_socket_uid:
+		return &bpf_get_socket_uid_proto;
 	default:
 		return bpf_base_func_proto(func_id);
 	}
@@ -2699,6 +2734,10 @@ tc_cls_act_func_proto(enum bpf_func_id func_id)
 		return &bpf_get_smp_processor_id_proto;
 	case BPF_FUNC_skb_under_cgroup:
 		return &bpf_skb_under_cgroup_proto;
+	case BPF_FUNC_get_socket_cookie:
+		return &bpf_get_socket_cookie_proto;
+	case BPF_FUNC_get_socket_uid:
+		return &bpf_get_socket_uid_proto;
 	default:
 		return bpf_base_func_proto(func_id);
 	}

net/core/sock_diag.c

@@ -19,7 +19,7 @@ static int (*inet_rcv_compat)(struct sk_buff *skb, struct nlmsghdr *nlh);
 static DEFINE_MUTEX(sock_diag_table_mutex);
 static struct workqueue_struct *broadcast_wq;
 
-static u64 sock_gen_cookie(struct sock *sk)
+u64 sock_gen_cookie(struct sock *sk)
 {
 	while (1) {
 		u64 res = atomic64_read(&sk->sk_cookie);

samples/bpf/Makefile

@@ -35,6 +35,7 @@ hostprogs-y += tc_l2_redirect
 hostprogs-y += lwt_len_hist
 hostprogs-y += xdp_tx_iptunnel
 hostprogs-y += test_map_in_map
+hostprogs-y += per_socket_stats_example
 
 # Libbpf dependencies
 LIBBPF := ../../tools/lib/bpf/bpf.o
@@ -74,6 +75,7 @@ tc_l2_redirect-objs := bpf_load.o $(LIBBPF) tc_l2_redirect_user.o
 lwt_len_hist-objs := bpf_load.o $(LIBBPF) lwt_len_hist_user.o
 xdp_tx_iptunnel-objs := bpf_load.o $(LIBBPF) xdp_tx_iptunnel_user.o
 test_map_in_map-objs := bpf_load.o $(LIBBPF) test_map_in_map_user.o
+per_socket_stats_example-objs := $(LIBBPF) cookie_uid_helper_example.o
 
 # Tell kbuild to always build the programs
 always := $(hostprogs-y)
@@ -108,6 +110,7 @@ always += sampleip_kern.o
 always += lwt_len_hist_kern.o
 always += xdp_tx_iptunnel_kern.o
 always += test_map_in_map_kern.o
+always += cookie_uid_helper_example.o
 
 HOSTCFLAGS += -I$(objtree)/usr/include
 HOSTCFLAGS += -I$(srctree)/tools/lib/

samples/bpf/cookie_uid_helper_example.c

@@ -0,0 +1,217 @@
+/* This test is a demo of using get_socket_uid and get_socket_cookie
+ * helper function to do per socket based network traffic monitoring.
+ * It requires iptables version higher then 1.6.1. to load pinned eBPF
+ * program into the xt_bpf match.
+ *
+ * TEST:
+ * ./run_cookie_uid_helper_example.sh
+ * Then generate some traffic in variate ways. ping 0 -c 10 would work
+ * but the cookie and uid in this case could both be 0. A sample output
+ * with some traffic generated by web browser is shown below:
+ *
+ * cookie: 877, uid: 0x3e8, Pakcet Count: 20, Bytes Count: 11058
+ * cookie: 132, uid: 0x0, Pakcet Count: 2, Bytes Count: 286
+ * cookie: 812, uid: 0x3e8, Pakcet Count: 3, Bytes Count: 1726
+ * cookie: 802, uid: 0x3e8, Pakcet Count: 2, Bytes Count: 104
+ * cookie: 877, uid: 0x3e8, Pakcet Count: 20, Bytes Count: 11058
+ * cookie: 831, uid: 0x3e8, Pakcet Count: 2, Bytes Count: 104
+ * cookie: 0, uid: 0x0, Pakcet Count: 6, Bytes Count: 712
+ * cookie: 880, uid: 0xfffe, Pakcet Count: 1, Bytes Count: 70
+ *
+ * Clean up: if using shell script, the script file will delete the iptables
+ * rule and unmount the bpf program when exit. Else the iptables rule need
+ * to be deleted by hand, see run_cookie_uid_helper_example.sh for detail.
+ */
+
+#define _GNU_SOURCE
+
+#define offsetof(type, member)	__builtin_offsetof(type, member)
+#define ARRAY_SIZE(x) (sizeof(x) / sizeof(*(x)))
+
+#include <arpa/inet.h>
+#include <errno.h>
+#include <error.h>
+#include <limits.h>
+#include <linux/bpf.h>
+#include <linux/if_ether.h>
+#include <stdbool.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/socket.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <unistd.h>
+#include <bpf/bpf.h>
+#include "libbpf.h"
+
+struct stats {
+	uint32_t uid;
+	uint64_t packets;
+	uint64_t bytes;
+};
+
+static int map_fd, prog_fd;
+
+static void maps_create(void)
+{
+	map_fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(uint32_t),
+				sizeof(struct stats), 100, 0);
+	if (map_fd < 0)
+		error(1, errno, "map create failed!\n");
+}
+
+static void prog_load(void)
+{
+	static char log_buf[1 << 16];
+
+	struct bpf_insn prog[] = {
+		/*
+		 * Save sk_buff for future usage. value stored in R6 to R10 will
+		 * not be reset after a bpf helper function call.
+		 */
+		BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+		/*
+		 * pc1: BPF_FUNC_get_socket_cookie takes one parameter,
+		 * R1: sk_buff
+		 */
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				BPF_FUNC_get_socket_cookie),
+		/* pc2-4: save &socketCookie to r7 for future usage*/
+		BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8),
+		BPF_MOV64_REG(BPF_REG_7, BPF_REG_10),
+		BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8),
+		/*
+		 * pc5-8: set up the registers for BPF_FUNC_map_lookup_elem,
+		 * it takes two parameters (R1: map_fd,  R2: &socket_cookie)
+		 */
+		BPF_LD_MAP_FD(BPF_REG_1, map_fd),
+		BPF_MOV64_REG(BPF_REG_2, BPF_REG_7),
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				BPF_FUNC_map_lookup_elem),
+		/*
+		 * pc9. if r0 != 0x0, go to pc+14, since we have the cookie
+		 * stored already
+		 * Otherwise do pc10-22 to setup a new data entry.
+		 */
+		BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 14),
+		BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				BPF_FUNC_get_socket_uid),
+		/*
+		 * Place a struct stats in the R10 stack and sequentially
+		 * place the member value into the memory. Packets value
+		 * is set by directly place a IMM value 1 into the stack.
+		 */
+		BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0,
+				-32 + offsetof(struct stats, uid)),
+		BPF_ST_MEM(BPF_DW, BPF_REG_10,
+				-32 + offsetof(struct stats, packets), 1),
+		/*
+		 * __sk_buff is a special struct used for eBPF program to
+		 * directly access some sk_buff field.
+		 */
+		BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_6,
+				offsetof(struct __sk_buff, len)),
+		BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_1,
+				-32 + offsetof(struct stats, bytes)),
+		/*
+		 * add new map entry using BPF_FUNC_map_update_elem, it takes
+		 * 4 parameters (R1: map_fd, R2: &socket_cookie, R3: &stats,
+		 * R4: flags)
+		 */
+		BPF_LD_MAP_FD(BPF_REG_1, map_fd),
+		BPF_MOV64_REG(BPF_REG_2, BPF_REG_7),
+		BPF_MOV64_REG(BPF_REG_3, BPF_REG_10),
+		BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, -32),
+		BPF_MOV64_IMM(BPF_REG_4, 0),
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				BPF_FUNC_map_update_elem),
+		BPF_JMP_IMM(BPF_JA, 0, 0, 5),
+		/*
+		 * pc24-30 update the packet info to a exist data entry, it can
+		 * be done by directly write to pointers instead of using
+		 * BPF_FUNC_map_update_elem helper function
+		 */
+		BPF_MOV64_REG(BPF_REG_9, BPF_REG_0),
+		BPF_MOV64_IMM(BPF_REG_1, 1),
+		BPF_STX_XADD(BPF_DW, BPF_REG_9, BPF_REG_1,
+				offsetof(struct stats, packets)),
+		BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_6,
+				offsetof(struct __sk_buff, len)),
+		BPF_STX_XADD(BPF_DW, BPF_REG_9, BPF_REG_1,
+				offsetof(struct stats, bytes)),
+		BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_6,
+				offsetof(struct __sk_buff, len)),
+		BPF_EXIT_INSN(),
+	};
+	prog_fd = bpf_load_program(BPF_PROG_TYPE_SOCKET_FILTER, prog,
+					ARRAY_SIZE(prog), "GPL", 0,
+					log_buf, sizeof(log_buf));
+	if (prog_fd < 0)
+		error(1, errno, "failed to load prog\n%s\n", log_buf);
+}
+
+static void prog_attach_iptables(char *file)
+{
+	int ret;
+	char rules[100];
+
+	if (bpf_obj_pin(prog_fd, file))
+		error(1, errno, "bpf_obj_pin");
+	if (strlen(file) > 50) {
+		printf("file path too long: %s\n", file);
+		exit(1);
+	}
+	sprintf(rules, "iptables -A INPUT -m bpf --object-pinned %s -j ACCEPT",
+		file);
+	ret = system(rules);
+	if (ret < 0) {
+		printf("iptables rule update failed: %d/n", WEXITSTATUS(ret));
+		exit(1);
+	}
+}
+
+static void print_table(void)
+{
+	struct stats curEntry;
+	uint32_t curN = UINT32_MAX;
+	uint32_t nextN, res;
+
+	while (bpf_map_get_next_key(map_fd, &curN, &nextN) > -1) {
+		curN = nextN;
+		res = bpf_map_lookup_elem(map_fd, &curN, &curEntry);
+		if (res < 0) {
+			error(1, errno, "fail to get entry value of Key: %u\n",
+				curN);
+		} else {
+			printf("cookie: %u, uid: 0x%x, Packet Count: %lu,"
+				" Bytes Count: %lu\n", curN, curEntry.uid,
+				curEntry.packets, curEntry.bytes);
+		}
+	}
+}
+
+int main(int argc, char *argv[])
+{
+	if (argc > 2) {
+		printf("Too many argument provided\n");
+		return 1;
+	} else if (argc < 2) {
+		printf("Usage: %s bpfObjName\n", argv[0]);
+		return 1;
+	}
+
+	maps_create();
+	prog_load();
+	prog_attach_iptables(argv[1]);
+
+	while (true) {
+		print_table();
+		printf("\n");
+		sleep(1);
+	};
+
+	return 0;
+}

samples/bpf/libbpf.h

@@ -135,6 +135,16 @@ struct bpf_insn;
 		.off   = OFF,					\
 		.imm   = 0 })
 
+/* Atomic memory add, *(uint *)(dst_reg + off16) += src_reg */
+
+#define BPF_STX_XADD(SIZE, DST, SRC, OFF)			\
+	((struct bpf_insn) {					\
+		.code  = BPF_STX | BPF_SIZE(SIZE) | BPF_XADD,	\
+		.dst_reg = DST,					\
+		.src_reg = SRC,					\
+		.off   = OFF,					\
+		.imm   = 0 })
+
 /* Memory store, *(uint *) (dst_reg + off16) = imm32 */
 
 #define BPF_ST_MEM(SIZE, DST, OFF, IMM)				\

samples/bpf/run_cookie_uid_helper_example.sh

@@ -0,0 +1,14 @@
+#!/bin/bash
+local_dir="$(pwd)"
+root_dir=$local_dir/../..
+mnt_dir=$(mktemp -d --tmp)
+
+on_exit() {
+	iptables -D INPUT -m bpf --object-pinned ${mnt_dir}/bpf_prog -j ACCEPT
+	umount ${mnt_dir}
+	rm -r ${mnt_dir}
+}
+
+trap on_exit EXIT
+mount -t bpf bpf ${mnt_dir}
+./per_socket_stats_example ${mnt_dir}/bpf_prog

tools/include/uapi/linux/bpf.h

@@ -506,7 +506,9 @@ union bpf_attr {
 	FN(get_numa_node_id),		\
 	FN(skb_change_head),		\
 	FN(xdp_adjust_head),		\
-	FN(probe_read_str),
+	FN(probe_read_str),		\
+	FN(get_socket_cookie),		\
+	FN(get_socket_uid),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call