summaryrefslogtreecommitdiff
path: root/samples
diff options
context:
space:
mode:
Diffstat (limited to 'samples')
-rw-r--r--samples/bpf/Makefile7
-rw-r--r--samples/bpf/bpf_helpers.h1
-rw-r--r--samples/bpf/bpf_load.c22
-rw-r--r--samples/bpf/cookie_uid_helper_example.c321
-rw-r--r--samples/bpf/libbpf.h10
-rw-r--r--samples/bpf/map_perf_test_kern.c33
-rw-r--r--samples/bpf/map_perf_test_user.c32
-rwxr-xr-xsamples/bpf/run_cookie_uid_helper_example.sh14
-rw-r--r--samples/bpf/test_map_in_map_kern.c173
-rw-r--r--samples/bpf/test_map_in_map_user.c116
10 files changed, 724 insertions, 5 deletions
diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 09e9d535bd74..d42b495b0992 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -34,6 +34,8 @@ hostprogs-y += sampleip
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
@@ -72,6 +74,8 @@ sampleip-objs := bpf_load.o $(LIBBPF) sampleip_user.o
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 := $(hostprogs-y)
@@ -105,6 +109,8 @@ always += trace_event_kern.o
always += sampleip_kern.o
always += lwt_len_hist_kern.o
always += xdp_tx_iptunnel_kern.o
+always += test_map_in_map_kern.o
+always += cookie_uid_helper_example.o
HOSTCFLAGS += -I$(objtree)/usr/include
HOSTCFLAGS += -I$(srctree)/tools/lib/
@@ -139,6 +145,7 @@ HOSTLOADLIBES_sampleip += -lelf
HOSTLOADLIBES_tc_l2_redirect += -l elf
HOSTLOADLIBES_lwt_len_hist += -l elf
HOSTLOADLIBES_xdp_tx_iptunnel += -lelf
+HOSTLOADLIBES_test_map_in_map += -lelf
# Allows pointing LLC/CLANG to a LLVM backend with bpf support, redefine on cmdline:
# make samples/bpf/ LLC=~/git/llvm/build/bin/llc CLANG=~/git/llvm/build/bin/clang
diff --git a/samples/bpf/bpf_helpers.h b/samples/bpf/bpf_helpers.h
index faaffe2e139a..52de9d88c021 100644
--- a/samples/bpf/bpf_helpers.h
+++ b/samples/bpf/bpf_helpers.h
@@ -80,6 +80,7 @@ struct bpf_map_def {
unsigned int value_size;
unsigned int max_entries;
unsigned int map_flags;
+ unsigned int inner_map_idx;
};
static int (*bpf_skb_load_bytes)(void *ctx, int off, void *to, int len) =
diff --git a/samples/bpf/bpf_load.c b/samples/bpf/bpf_load.c
index b86ee54da2d1..dcdce1270d38 100644
--- a/samples/bpf/bpf_load.c
+++ b/samples/bpf/bpf_load.c
@@ -43,6 +43,7 @@ struct bpf_map_def {
unsigned int value_size;
unsigned int max_entries;
unsigned int map_flags;
+ unsigned int inner_map_idx;
};
static int populate_prog_array(const char *event, int prog_fd)
@@ -198,11 +199,22 @@ static int load_maps(struct bpf_map_def *maps, int len)
for (i = 0; i < len / sizeof(struct bpf_map_def); i++) {
- map_fd[i] = bpf_create_map(maps[i].type,
- maps[i].key_size,
- maps[i].value_size,
- maps[i].max_entries,
- maps[i].map_flags);
+ if (maps[i].type == BPF_MAP_TYPE_ARRAY_OF_MAPS ||
+ maps[i].type == BPF_MAP_TYPE_HASH_OF_MAPS) {
+ int inner_map_fd = map_fd[maps[i].inner_map_idx];
+
+ map_fd[i] = bpf_create_map_in_map(maps[i].type,
+ maps[i].key_size,
+ inner_map_fd,
+ maps[i].max_entries,
+ maps[i].map_flags);
+ } else {
+ map_fd[i] = bpf_create_map(maps[i].type,
+ maps[i].key_size,
+ maps[i].value_size,
+ maps[i].max_entries,
+ maps[i].map_flags);
+ }
if (map_fd[i] < 0) {
printf("failed to create a map: %d %s\n",
errno, strerror(errno));
diff --git a/samples/bpf/cookie_uid_helper_example.c b/samples/bpf/cookie_uid_helper_example.c
new file mode 100644
index 000000000000..ad5afedf2e70
--- /dev/null
+++ b/samples/bpf/cookie_uid_helper_example.c
@@ -0,0 +1,321 @@
+/* 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 -option
+ * option:
+ * -t: do traffic monitoring test, the program will continuously
+ * print out network traffic happens after program started A sample
+ * output 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
+ *
+ * -s: do getsockopt SO_COOKIE test, the program will set up a pair of
+ * UDP sockets and send packets between them. And read out the traffic data
+ * directly from the ebpf map based on the socket cookie.
+ *
+ * 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 <net/if.h>
+#include <signal.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"
+
+#define PORT 8888
+
+struct stats {
+ uint32_t uid;
+ uint64_t packets;
+ uint64_t bytes;
+};
+
+static int map_fd, prog_fd;
+
+static bool test_finish;
+
+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 OUTPUT -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;
+ int 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);
+ }
+ }
+}
+
+static void udp_client(void)
+{
+ struct sockaddr_in si_other = {0};
+ struct sockaddr_in si_me = {0};
+ struct stats dataEntry;
+ int s_rcv, s_send, i, recv_len;
+ char message = 'a';
+ char buf;
+ uint64_t cookie;
+ int res;
+ socklen_t cookie_len = sizeof(cookie);
+ socklen_t slen = sizeof(si_other);
+
+ s_rcv = socket(PF_INET, SOCK_DGRAM, 0);
+ if (s_rcv < 0)
+ error(1, errno, "rcv socket creat failed!\n");
+ si_other.sin_family = AF_INET;
+ si_other.sin_port = htons(PORT);
+ if (inet_aton("127.0.0.1", &si_other.sin_addr) == 0)
+ error(1, errno, "inet_aton\n");
+ if (bind(s_rcv, (struct sockaddr *)&si_other, sizeof(si_other)) == -1)
+ error(1, errno, "bind\n");
+ s_send = socket(PF_INET, SOCK_DGRAM, 0);
+ if (s_send < 0)
+ error(1, errno, "send socket creat failed!\n");
+ res = getsockopt(s_send, SOL_SOCKET, SO_COOKIE, &cookie, &cookie_len);
+ if (res < 0)
+ printf("get cookie failed: %s\n", strerror(errno));
+ res = bpf_map_lookup_elem(map_fd, &cookie, &dataEntry);
+ if (res != -1)
+ error(1, errno, "socket stat found while flow not active\n");
+ for (i = 0; i < 10; i++) {
+ res = sendto(s_send, &message, sizeof(message), 0,
+ (struct sockaddr *)&si_other, slen);
+ if (res == -1)
+ error(1, errno, "send\n");
+ if (res != sizeof(message))
+ error(1, 0, "%uB != %luB\n", res, sizeof(message));
+ recv_len = recvfrom(s_rcv, &buf, sizeof(buf), 0,
+ (struct sockaddr *)&si_me, &slen);
+ if (recv_len < 0)
+ error(1, errno, "revieve\n");
+ res = memcmp(&(si_other.sin_addr), &(si_me.sin_addr),
+ sizeof(si_me.sin_addr));
+ if (res != 0)
+ error(1, EFAULT, "sender addr error: %d\n", res);
+ printf("Message received: %c\n", buf);
+ res = bpf_map_lookup_elem(map_fd, &cookie, &dataEntry);
+ if (res < 0)
+ error(1, errno, "lookup sk stat failed, cookie: %lu\n",
+ cookie);
+ printf("cookie: %lu, uid: 0x%x, Packet Count: %lu,"
+ " Bytes Count: %lu\n\n", cookie, dataEntry.uid,
+ dataEntry.packets, dataEntry.bytes);
+ }
+ close(s_send);
+ close(s_rcv);
+}
+
+static int usage(void)
+{
+ printf("Usage: ./run_cookie_uid_helper_example.sh"
+ " bpfObjName -option\n"
+ " -t traffic monitor test\n"
+ " -s getsockopt cookie test\n");
+ return 1;
+}
+
+void finish(int ret)
+{
+ test_finish = true;
+}
+
+int main(int argc, char *argv[])
+{
+ int opt;
+ bool cfg_test_traffic = false;
+ bool cfg_test_cookie = false;
+
+ if (argc != 3)
+ return usage();
+ while ((opt = getopt(argc, argv, "ts")) != -1) {
+ switch (opt) {
+ case 't':
+ cfg_test_traffic = true;
+ break;
+ case 's':
+ cfg_test_cookie = true;
+ break;
+
+ default:
+ printf("unknown option %c\n", opt);
+ usage();
+ return -1;
+ }
+ }
+ maps_create();
+ prog_load();
+ prog_attach_iptables(argv[2]);
+ if (cfg_test_traffic) {
+ if (signal(SIGINT, finish) == SIG_ERR)
+ error(1, errno, "register handler failed");
+ while (!test_finish) {
+ print_table();
+ printf("\n");
+ sleep(1);
+ };
+ } else if (cfg_test_cookie) {
+ udp_client();
+ }
+ close(prog_fd);
+ close(map_fd);
+ return 0;
+}
diff --git a/samples/bpf/libbpf.h b/samples/bpf/libbpf.h
index 3705fba453a0..8ab36a04c174 100644
--- a/samples/bpf/libbpf.h
+++ b/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) \
diff --git a/samples/bpf/map_perf_test_kern.c b/samples/bpf/map_perf_test_kern.c
index a91872a97742..9da2a3441b0a 100644
--- a/samples/bpf/map_perf_test_kern.c
+++ b/samples/bpf/map_perf_test_kern.c
@@ -65,6 +65,13 @@ struct bpf_map_def SEC("maps") lpm_trie_map_alloc = {
.map_flags = BPF_F_NO_PREALLOC,
};
+struct bpf_map_def SEC("maps") array_map = {
+ .type = BPF_MAP_TYPE_ARRAY,
+ .key_size = sizeof(u32),
+ .value_size = sizeof(long),
+ .max_entries = MAX_ENTRIES,
+};
+
SEC("kprobe/sys_getuid")
int stress_hmap(struct pt_regs *ctx)
{
@@ -165,5 +172,31 @@ int stress_lpm_trie_map_alloc(struct pt_regs *ctx)
return 0;
}
+SEC("kprobe/sys_getpgid")
+int stress_hash_map_lookup(struct pt_regs *ctx)
+{
+ u32 key = 1, i;
+ long *value;
+
+#pragma clang loop unroll(full)
+ for (i = 0; i < 64; ++i)
+ value = bpf_map_lookup_elem(&hash_map, &key);
+
+ return 0;
+}
+
+SEC("kprobe/sys_getpgrp")
+int stress_array_map_lookup(struct pt_regs *ctx)
+{
+ u32 key = 1, i;
+ long *value;
+
+#pragma clang loop unroll(full)
+ for (i = 0; i < 64; ++i)
+ value = bpf_map_lookup_elem(&array_map, &key);
+
+ return 0;
+}
+
char _license[] SEC("license") = "GPL";
u32 _version SEC("version") = LINUX_VERSION_CODE;
diff --git a/samples/bpf/map_perf_test_user.c b/samples/bpf/map_perf_test_user.c
index 680260a91f50..e29ff318a793 100644
--- a/samples/bpf/map_perf_test_user.c
+++ b/samples/bpf/map_perf_test_user.c
@@ -38,6 +38,8 @@ static __u64 time_get_ns(void)
#define LRU_HASH_PREALLOC (1 << 4)
#define PERCPU_LRU_HASH_PREALLOC (1 << 5)
#define LPM_KMALLOC (1 << 6)
+#define HASH_LOOKUP (1 << 7)
+#define ARRAY_LOOKUP (1 << 8)
static int test_flags = ~0;
@@ -125,6 +127,30 @@ static void test_lpm_kmalloc(int cpu)
cpu, MAX_CNT * 1000000000ll / (time_get_ns() - start_time));
}
+static void test_hash_lookup(int cpu)
+{
+ __u64 start_time;
+ int i;
+
+ start_time = time_get_ns();
+ for (i = 0; i < MAX_CNT; i++)
+ syscall(__NR_getpgid, 0);
+ printf("%d:hash_lookup %lld lookups per sec\n",
+ cpu, MAX_CNT * 1000000000ll * 64 / (time_get_ns() - start_time));
+}
+
+static void test_array_lookup(int cpu)
+{
+ __u64 start_time;
+ int i;
+
+ start_time = time_get_ns();
+ for (i = 0; i < MAX_CNT; i++)
+ syscall(__NR_getpgrp, 0);
+ printf("%d:array_lookup %lld lookups per sec\n",
+ cpu, MAX_CNT * 1000000000ll * 64 / (time_get_ns() - start_time));
+}
+
static void loop(int cpu)
{
cpu_set_t cpuset;
@@ -153,6 +179,12 @@ static void loop(int cpu)
if (test_flags & LPM_KMALLOC)
test_lpm_kmalloc(cpu);
+
+ if (test_flags & HASH_LOOKUP)
+ test_hash_lookup(cpu);
+
+ if (test_flags & ARRAY_LOOKUP)
+ test_array_lookup(cpu);
}
static void run_perf_test(int tasks)
diff --git a/samples/bpf/run_cookie_uid_helper_example.sh b/samples/bpf/run_cookie_uid_helper_example.sh
new file mode 100755
index 000000000000..f898cfa2b1aa
--- /dev/null
+++ b/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 OUTPUT -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 $1
diff --git a/samples/bpf/test_map_in_map_kern.c b/samples/bpf/test_map_in_map_kern.c
new file mode 100644
index 000000000000..42c44d091dd1
--- /dev/null
+++ b/samples/bpf/test_map_in_map_kern.c
@@ -0,0 +1,173 @@
+/*
+ * Copyright (c) 2017 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#define KBUILD_MODNAME "foo"
+#include <linux/ptrace.h>
+#include <linux/version.h>
+#include <uapi/linux/bpf.h>
+#include <uapi/linux/in6.h>
+#include "bpf_helpers.h"
+
+#define MAX_NR_PORTS 65536
+
+/* map #0 */
+struct bpf_map_def SEC("maps") port_a = {
+ .type = BPF_MAP_TYPE_ARRAY,
+ .key_size = sizeof(u32),
+ .value_size = sizeof(int),
+ .max_entries = MAX_NR_PORTS,
+};
+
+/* map #1 */
+struct bpf_map_def SEC("maps") port_h = {
+ .type = BPF_MAP_TYPE_HASH,
+ .key_size = sizeof(u32),
+ .value_size = sizeof(int),
+ .max_entries = 1,
+};
+
+/* map #2 */
+struct bpf_map_def SEC("maps") reg_result_h = {
+ .type = BPF_MAP_TYPE_HASH,
+ .key_size = sizeof(u32),
+ .value_size = sizeof(int),
+ .max_entries = 1,
+};
+
+/* map #3 */
+struct bpf_map_def SEC("maps") inline_result_h = {
+ .type = BPF_MAP_TYPE_HASH,
+ .key_size = sizeof(u32),
+ .value_size = sizeof(int),
+ .max_entries = 1,
+};
+
+/* map #4 */ /* Test case #0 */
+struct bpf_map_def SEC("maps") a_of_port_a = {
+ .type = BPF_MAP_TYPE_ARRAY_OF_MAPS,
+ .key_size = sizeof(u32),
+ .inner_map_idx = 0, /* map_fd[0] is port_a */
+ .max_entries = MAX_NR_PORTS,
+};
+
+/* map #5 */ /* Test case #1 */
+struct bpf_map_def SEC("maps") h_of_port_a = {
+ .type = BPF_MAP_TYPE_HASH_OF_MAPS,
+ .key_size = sizeof(u32),
+ .inner_map_idx = 0, /* map_fd[0] is port_a */
+ .max_entries = 1,
+};
+
+/* map #6 */ /* Test case #2 */
+struct bpf_map_def SEC("maps") h_of_port_h = {
+ .type = BPF_MAP_TYPE_HASH_OF_MAPS,
+ .key_size = sizeof(u32),
+ .inner_map_idx = 1, /* map_fd[1] is port_h */
+ .max_entries = 1,
+};
+
+static __always_inline int do_reg_lookup(void *inner_map, u32 port)
+{
+ int *result;
+
+ result = bpf_map_lookup_elem(inner_map, &port);
+ return result ? *result : -ENOENT;
+}
+
+static __always_inline int do_inline_array_lookup(void *inner_map, u32 port)
+{
+ int *result;
+
+ if (inner_map != &port_a)
+ return -EINVAL;
+
+ result = bpf_map_lookup_elem(&port_a, &port);
+ return result ? *result : -ENOENT;
+}
+
+static __always_inline int do_inline_hash_lookup(void *inner_map, u32 port)
+{
+ int *result;
+
+ if (inner_map != &port_h)
+ return -EINVAL;
+
+ result = bpf_map_lookup_elem(&port_h, &port);
+ return result ? *result : -ENOENT;
+}
+
+SEC("kprobe/sys_connect")
+int trace_sys_connect(struct pt_regs *ctx)
+{
+ struct sockaddr_in6 *in6;
+ u16 test_case, port, dst6[8];
+ int addrlen, ret, inline_ret, ret_key = 0;
+ u32 port_key;
+ void *outer_map, *inner_map;
+ bool inline_hash = false;
+
+ in6 = (struct sockaddr_in6 *)PT_REGS_PARM2(ctx);
+ addrlen = (int)PT_REGS_PARM3(ctx);
+
+ if (addrlen != sizeof(*in6))
+ return 0;
+
+ ret = bpf_probe_read(dst6, sizeof(dst6), &in6->sin6_addr);
+ if (ret) {
+ inline_ret = ret;
+ goto done;
+ }
+
+ if (dst6[0] != 0xdead || dst6[1] != 0xbeef)
+ return 0;
+
+ test_case = dst6[7];
+
+ ret = bpf_probe_read(&port, sizeof(port), &in6->sin6_port);
+ if (ret) {
+ inline_ret = ret;
+ goto done;
+ }
+
+ port_key = port;
+
+ ret = -ENOENT;
+ if (test_case == 0) {
+ outer_map = &a_of_port_a;
+ } else if (test_case == 1) {
+ outer_map = &h_of_port_a;
+ } else if (test_case == 2) {
+ outer_map = &h_of_port_h;
+ } else {
+ ret = __LINE__;
+ inline_ret = ret;
+ goto done;
+ }
+
+ inner_map = bpf_map_lookup_elem(outer_map, &port_key);
+ if (!inner_map) {
+ ret = __LINE__;
+ inline_ret = ret;
+ goto done;
+ }
+
+ ret = do_reg_lookup(inner_map, port_key);
+
+ if (test_case == 0 || test_case == 1)
+ inline_ret = do_inline_array_lookup(inner_map, port_key);
+ else
+ inline_ret = do_inline_hash_lookup(inner_map, port_key);
+
+done:
+ bpf_map_update_elem(&reg_result_h, &ret_key, &ret, BPF_ANY);
+ bpf_map_update_elem(&inline_result_h, &ret_key, &inline_ret, BPF_ANY);
+
+ return 0;
+}
+
+char _license[] SEC("license") = "GPL";
+u32 _version SEC("version") = LINUX_VERSION_CODE;
diff --git a/samples/bpf/test_map_in_map_user.c b/samples/bpf/test_map_in_map_user.c
new file mode 100644
index 000000000000..f62fdc2bd428
--- /dev/null
+++ b/samples/bpf/test_map_in_map_user.c
@@ -0,0 +1,116 @@
+/*
+ * Copyright (c) 2017 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#include <sys/resource.h>
+#include <sys/socket.h>
+#include <arpa/inet.h>
+#include <stdint.h>
+#include <assert.h>
+#include <errno.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include "libbpf.h"
+#include "bpf_load.h"
+
+#define PORT_A (map_fd[0])
+#define PORT_H (map_fd[1])
+#define REG_RESULT_H (map_fd[2])
+#define INLINE_RESULT_H (map_fd[3])
+#define A_OF_PORT_A (map_fd[4]) /* Test case #0 */
+#define H_OF_PORT_A (map_fd[5]) /* Test case #1 */
+#define H_OF_PORT_H (map_fd[6]) /* Test case #2 */
+
+static const char * const test_names[] = {
+ "Array of Array",
+ "Hash of Array",
+ "Hash of Hash",
+};
+
+#define NR_TESTS (sizeof(test_names) / sizeof(*test_names))
+
+static void populate_map(uint32_t port_key, int magic_result)
+{
+ int ret;
+
+ ret = bpf_map_update_elem(PORT_A, &port_key, &magic_result, BPF_ANY);
+ assert(!ret);
+
+ ret = bpf_map_update_elem(PORT_H, &port_key, &magic_result,
+ BPF_NOEXIST);
+ assert(!ret);
+
+ ret = bpf_map_update_elem(A_OF_PORT_A, &port_key, &PORT_A, BPF_ANY);
+ assert(!ret);
+
+ ret = bpf_map_update_elem(H_OF_PORT_A, &port_key, &PORT_A, BPF_NOEXIST);
+ assert(!ret);
+
+ ret = bpf_map_update_elem(H_OF_PORT_H, &port_key, &PORT_H, BPF_NOEXIST);
+ assert(!ret);
+}
+
+static void test_map_in_map(void)
+{
+ struct sockaddr_in6 in6 = { .sin6_family = AF_INET6 };
+ uint32_t result_key = 0, port_key;
+ int result, inline_result;
+ int magic_result = 0xfaceb00c;
+ int ret;
+ int i;
+
+ port_key = rand() & 0x00FF;
+ populate_map(port_key, magic_result);
+
+ in6.sin6_addr.s6_addr16[0] = 0xdead;
+ in6.sin6_addr.s6_addr16[1] = 0xbeef;
+ in6.sin6_port = port_key;
+
+ for (i = 0; i < NR_TESTS; i++) {
+ printf("%s: ", test_names[i]);
+
+ in6.sin6_addr.s6_addr16[7] = i;
+ ret = connect(-1, (struct sockaddr *)&in6, sizeof(in6));
+ assert(ret == -1 && errno == EBADF);
+
+ ret = bpf_map_lookup_elem(REG_RESULT_H, &result_key, &result);
+ assert(!ret);
+
+ ret = bpf_map_lookup_elem(INLINE_RESULT_H, &result_key,
+ &inline_result);
+ assert(!ret);
+
+ if (result != magic_result || inline_result != magic_result) {
+ printf("Error. result:%d inline_result:%d\n",
+ result, inline_result);
+ exit(1);
+ }
+
+ bpf_map_delete_elem(REG_RESULT_H, &result_key);
+ bpf_map_delete_elem(INLINE_RESULT_H, &result_key);
+
+ printf("Pass\n");
+ }
+}
+
+int main(int argc, char **argv)
+{
+ struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
+ char filename[256];
+
+ assert(!setrlimit(RLIMIT_MEMLOCK, &r));
+
+ snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+
+ if (load_bpf_file(filename)) {
+ printf("%s", bpf_log_buf);
+ return 1;
+ }
+
+ test_map_in_map();
+
+ return 0;
+}