/* Test deletion */
static void test_lru_sanity4(int map_type, int map_flags, unsigned int tgt_free)
{
int lru_map_fd, expected_map_fd;
unsigned long long key, value[nr_cpus];
unsigned long long end_key;
int next_cpu = 0;
printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type,
map_flags);
assert(sched_next_online(0, &next_cpu) != -1);
if (map_flags & BPF_F_NO_COMMON_LRU)
lru_map_fd = create_map(map_type, map_flags,
3 * tgt_free * nr_cpus);
else
lru_map_fd = create_map(map_type, map_flags, 3 * tgt_free);
assert(lru_map_fd != -1);
expected_map_fd = create_map(BPF_MAP_TYPE_HASH, 0,
3 * tgt_free);
assert(expected_map_fd != -1);
value[0] = 1234;
for (key = 1; key <= 2 * tgt_free; key++)
assert(!bpf_map_update_elem(lru_map_fd, &key, value,
BPF_NOEXIST));
key = 1;
assert(bpf_map_update_elem(lru_map_fd, &key, value, BPF_NOEXIST));
for (key = 1; key <= tgt_free; key++) {
assert(!bpf_map_lookup_elem(lru_map_fd, &key, value));
assert(!bpf_map_update_elem(expected_map_fd, &key, value,
BPF_NOEXIST));
}
for (; key <= 2 * tgt_free; key++) {
assert(!bpf_map_delete_elem(lru_map_fd, &key));
assert(bpf_map_delete_elem(lru_map_fd, &key));
}
end_key = key + 2 * tgt_free;
for (; key < end_key; key++) {
assert(!bpf_map_update_elem(lru_map_fd, &key, value,
BPF_NOEXIST));
assert(!bpf_map_update_elem(expected_map_fd, &key, value,
BPF_NOEXIST));
}
assert(map_equal(lru_map_fd, expected_map_fd));
close(expected_map_fd);
close(lru_map_fd);
printf("Pass\n");
}
static int bpf_do_map(const char *file, uint32_t flags, uint32_t key,
uint32_t value)
{
int fd, ret;
if (flags & BPF_F_PIN) {
fd = bpf_map_create();
printf("bpf: map fd:%d (%s)\n", fd, strerror(errno));
assert(fd > 0);
ret = bpf_obj_pin(fd, file);
printf("bpf: pin ret:(%d,%s)\n", ret, strerror(errno));
assert(ret == 0);
} else {
fd = bpf_obj_get(file);
printf("bpf: get fd:%d (%s)\n", fd, strerror(errno));
assert(fd > 0);
}
if ((flags & BPF_F_KEY_VAL) == BPF_F_KEY_VAL) {
ret = bpf_map_update_elem(fd, &key, &value, 0);
printf("bpf: fd:%d u->(%u:%u) ret:(%d,%s)\n", fd, key, value,
ret, strerror(errno));
assert(ret == 0);
} else if (flags & BPF_F_KEY) {
ret = bpf_map_lookup_elem(fd, &key, &value);
printf("bpf: fd:%d l->(%u):%u ret:(%d,%s)\n", fd, key, value,
ret, strerror(errno));
assert(ret == 0);
}
return 0;
}
int bpf_prog1(struct pt_regs *ctx)
{
long rq = ctx->di;
u64 val = bpf_ktime_get_ns();
bpf_map_update_elem(&start_ts, &rq, &val, BPF_ANY);
return 0;
}
int bpf_prog1(struct pt_regs *ctx)
{
long rq = PT_REGS_PARM1(ctx);
u64 val = bpf_ktime_get_ns();
bpf_map_update_elem(&my_map, &rq, &val, BPF_ANY);
return 0;
}
void test_xdp(void)
{
struct vip key4 = {.protocol = 6, .family = AF_INET};
struct vip key6 = {.protocol = 6, .family = AF_INET6};
struct iptnl_info value4 = {.family = AF_INET};
struct iptnl_info value6 = {.family = AF_INET6};
const char *file = "./test_xdp.o";
struct bpf_object *obj;
char buf[128];
struct ipv6hdr *iph6 = (void *)buf + sizeof(struct ethhdr);
struct iphdr *iph = (void *)buf + sizeof(struct ethhdr);
__u32 duration, retval, size;
int err, prog_fd, map_fd;
err = bpf_prog_load(file, BPF_PROG_TYPE_XDP, &obj, &prog_fd);
if (err) {
error_cnt++;
return;
}
map_fd = bpf_find_map(__func__, obj, "vip2tnl");
if (map_fd < 0)
goto out;
bpf_map_update_elem(map_fd, &key4, &value4, 0);
bpf_map_update_elem(map_fd, &key6, &value6, 0);
err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4),
buf, &size, &retval, &duration);
CHECK(err || retval != XDP_TX || size != 74 ||
iph->protocol != IPPROTO_IPIP, "ipv4",
"err %d errno %d retval %d size %d\n",
err, errno, retval, size);
err = bpf_prog_test_run(prog_fd, 1, &pkt_v6, sizeof(pkt_v6),
buf, &size, &retval, &duration);
CHECK(err || retval != XDP_TX || size != 114 ||
iph6->nexthdr != IPPROTO_IPV6, "ipv6",
"err %d errno %d retval %d size %d\n",
err, errno, retval, size);
out:
bpf_object__close(obj);
}
static void clear_stats(int fd)
{
unsigned int nr_cpus = bpf_num_possible_cpus();
__u64 values[nr_cpus];
__u32 key;
memset(values, 0, sizeof(values));
for (key = 0; key < SLOTS; key++)
bpf_map_update_elem(fd, &key, values, BPF_ANY);
}
static int populate_prog_array(const char *event, int prog_fd)
{
int ind = atoi(event), err;
err = bpf_map_update_elem(prog_array_fd, &ind, &prog_fd, BPF_ANY);
if (err < 0) {
printf("failed to store prog_fd in prog_array\n");
return -1;
}
return 0;
}
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);
check_map_id(PORT_A, A_OF_PORT_A, port_key);
ret = bpf_map_update_elem(H_OF_PORT_A, &port_key, &PORT_A, BPF_NOEXIST);
assert(!ret);
check_map_id(PORT_A, H_OF_PORT_A, port_key);
ret = bpf_map_update_elem(H_OF_PORT_H, &port_key, &PORT_H, BPF_NOEXIST);
assert(!ret);
check_map_id(PORT_H, H_OF_PORT_H, port_key);
}
int main(int argc, char **argv)
{
const char *pinned_file = NULL;
int ifindex = -1;
int array_key = 0;
int array_fd = -1;
int ret = -1;
int opt;
while ((opt = getopt(argc, argv, "F:U:i:")) != -1) {
switch (opt) {
/* General args */
case 'U':
pinned_file = optarg;
break;
case 'i':
ifindex = atoi(optarg);
break;
default:
usage();
goto out;
}
}
if (ifindex < 0 || !pinned_file) {
usage();
goto out;
}
array_fd = bpf_obj_get(pinned_file);
if (array_fd < 0) {
fprintf(stderr, "bpf_obj_get(%s): %s(%d)\n",
pinned_file, strerror(errno), errno);
goto out;
}
/* bpf_tunnel_key.remote_ipv4 expects host byte orders */
ret = bpf_map_update_elem(array_fd, &array_key, &ifindex, 0);
if (ret) {
perror("bpf_map_update_elem");
goto out;
}
out:
if (array_fd != -1)
close(array_fd);
return ret;
}
static void do_test_lru_sanity5(unsigned long long last_key, int map_fd)
{
unsigned long long key, value[nr_cpus];
/* Ensure the last key inserted by previous CPU can be found */
assert(!bpf_map_lookup_elem(map_fd, &last_key, value));
value[0] = 1234;
key = last_key + 1;
assert(!bpf_map_update_elem(map_fd, &key, value, BPF_NOEXIST));
assert(!bpf_map_lookup_elem(map_fd, &key, value));
/* Cannot find the last key because it was removed by LRU */
assert(bpf_map_lookup_elem(map_fd, &last_key, value));
}
/* Test map with only one element */
static void test_lru_sanity5(int map_type, int map_flags)
{
unsigned long long key, value[nr_cpus];
int next_cpu = 0;
int map_fd;
if (map_flags & BPF_F_NO_COMMON_LRU)
return;
printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type,
map_flags);
map_fd = create_map(map_type, map_flags, 1);
assert(map_fd != -1);
value[0] = 1234;
key = 0;
assert(!bpf_map_update_elem(map_fd, &key, value, BPF_NOEXIST));
while (sched_next_online(0, &next_cpu) != -1) {
pid_t pid;
pid = fork();
if (pid == 0) {
do_test_lru_sanity5(key, map_fd);
exit(0);
} else if (pid == -1) {
printf("couldn't spawn process to test key:%llu\n",
key);
exit(1);
} else {
int status;
assert(waitpid(pid, &status, 0) == pid);
assert(status == 0);
key++;
}
}
close(map_fd);
/* At least one key should be tested */
assert(key > 0);
printf("Pass\n");
}
static int setup_bpf_perf_event(int mapfd)
{
struct perf_event_attr attr = {
.sample_type = PERF_SAMPLE_RAW,
.type = PERF_TYPE_SOFTWARE,
.config = PERF_COUNT_SW_BPF_OUTPUT,
};
int key = 0;
int pmu_fd;
pmu_fd = syscall(__NR_perf_event_open, &attr, -1, 0, -1, 0);
if (pmu_fd < 0)
return pmu_fd;
bpf_map_update_elem(mapfd, &key, &pmu_fd, BPF_ANY);
ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0);
return pmu_fd;
}
int bpf_prog2(struct pt_regs *ctx)
{
long loc = 0;
long init_val = 1;
long *value;
/* read ip of kfree_skb caller.
* non-portable version of __builtin_return_address(0)
*/
BPF_KPROBE_READ_RET_IP(loc, ctx);
value = bpf_map_lookup_elem(&my_map, &loc);
if (value)
*value += 1;
else
bpf_map_update_elem(&my_map, &loc, &init_val, BPF_ANY);
return 0;
}
static void verify_map(int map_id)
{
__u32 key = 0;
__u32 val;
if (bpf_map_lookup_elem(map_id, &key, &val) != 0) {
fprintf(stderr, "map_lookup failed: %s\n", strerror(errno));
return;
}
if (val == 0) {
fprintf(stderr, "failed: map #%d returns value 0\n", map_id);
return;
}
val = 0;
if (bpf_map_update_elem(map_id, &key, &val, BPF_ANY) != 0) {
fprintf(stderr, "map_update failed: %s\n", strerror(errno));
return;
}
}
static int run_test(int server_fd, int results_fd)
{
int client = -1, srv_client = -1;
int ret = 0;
__u32 key = 0;
__u64 value = 0;
if (bpf_map_update_elem(results_fd, &key, &value, 0) < 0) {
log_err("Can't clear results");
goto err;
}
client = connect_to_server(server_fd);
if (client == -1)
goto err;
srv_client = accept(server_fd, NULL, 0);
if (srv_client == -1) {
log_err("Can't accept connection");
goto err;
}
if (bpf_map_lookup_elem(results_fd, &key, &value) < 0) {
log_err("Can't lookup result");
goto err;
}
if (value != 1) {
log_err("Didn't match syncookie: %llu", value);
goto err;
}
goto out;
err:
ret = 1;
out:
close(client);
close(srv_client);
return ret;
}
/* Size of the LRU map is 1.5*tgt_free
* Insert 1 to tgt_free (+tgt_free keys)
* Lookup 1 to tgt_free/2
* Insert 1+tgt_free to 2*tgt_free (+tgt_free keys)
* => 1+tgt_free/2 to LOCALFREE_TARGET will be removed by LRU
*/
static void test_lru_sanity1(int map_type, int map_flags, unsigned int tgt_free)
{
unsigned long long key, end_key, value[nr_cpus];
int lru_map_fd, expected_map_fd;
unsigned int batch_size;
unsigned int map_size;
int next_cpu = 0;
if (map_flags & BPF_F_NO_COMMON_LRU)
/* Ther percpu lru list (i.e each cpu has its own LRU
* list) does not have a local free list. Hence,
* it will only free old nodes till there is no free
* from the LRU list. Hence, this test does not apply
* to BPF_F_NO_COMMON_LRU
*/
return;
printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type,
map_flags);
assert(sched_next_online(0, &next_cpu) != -1);
batch_size = tgt_free / 2;
assert(batch_size * 2 == tgt_free);
map_size = tgt_free + batch_size;
lru_map_fd = create_map(map_type, map_flags, map_size);
assert(lru_map_fd != -1);
expected_map_fd = create_map(BPF_MAP_TYPE_HASH, 0, map_size);
assert(expected_map_fd != -1);
value[0] = 1234;
/* Insert 1 to tgt_free (+tgt_free keys) */
end_key = 1 + tgt_free;
for (key = 1; key < end_key; key++)
assert(!bpf_map_update_elem(lru_map_fd, &key, value,
BPF_NOEXIST));
/* Lookup 1 to tgt_free/2 */
end_key = 1 + batch_size;
for (key = 1; key < end_key; key++) {
assert(!bpf_map_lookup_elem(lru_map_fd, &key, value));
assert(!bpf_map_update_elem(expected_map_fd, &key, value,
BPF_NOEXIST));
}
/* Insert 1+tgt_free to 2*tgt_free
* => 1+tgt_free/2 to LOCALFREE_TARGET will be
* removed by LRU
*/
key = 1 + tgt_free;
end_key = key + tgt_free;
for (; key < end_key; key++) {
assert(!bpf_map_update_elem(lru_map_fd, &key, value,
BPF_NOEXIST));
assert(!bpf_map_update_elem(expected_map_fd, &key, value,
BPF_NOEXIST));
}
assert(map_equal(lru_map_fd, expected_map_fd));
close(expected_map_fd);
close(lru_map_fd);
printf("Pass\n");
}
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(®_result_h, &ret_key, &ret, BPF_ANY);
bpf_map_update_elem(&inline_result_h, &ret_key, &inline_ret, BPF_ANY);
return 0;
}
static void test_bpf_obj_id(void)
{
const __u64 array_magic_value = 0xfaceb00c;
const __u32 array_key = 0;
const int nr_iters = 2;
const char *file = "./test_obj_id.o";
const char *jit_sysctl = "/proc/sys/net/core/bpf_jit_enable";
const char *expected_prog_name = "test_obj_id";
const char *expected_map_name = "test_map_id";
const __u64 nsec_per_sec = 1000000000;
struct bpf_object *objs[nr_iters];
int prog_fds[nr_iters], map_fds[nr_iters];
/* +1 to test for the info_len returned by kernel */
struct bpf_prog_info prog_infos[nr_iters + 1];
struct bpf_map_info map_infos[nr_iters + 1];
/* Each prog only uses one map. +1 to test nr_map_ids
* returned by kernel.
*/
__u32 map_ids[nr_iters + 1];
char jited_insns[128], xlated_insns[128], zeros[128];
__u32 i, next_id, info_len, nr_id_found, duration = 0;
struct timespec real_time_ts, boot_time_ts;
int sysctl_fd, jit_enabled = 0, err = 0;
__u64 array_value;
uid_t my_uid = getuid();
time_t now, load_time;
sysctl_fd = open(jit_sysctl, 0, O_RDONLY);
if (sysctl_fd != -1) {
char tmpc;
if (read(sysctl_fd, &tmpc, sizeof(tmpc)) == 1)
jit_enabled = (tmpc != '0');
close(sysctl_fd);
}
err = bpf_prog_get_fd_by_id(0);
CHECK(err >= 0 || errno != ENOENT,
"get-fd-by-notexist-prog-id", "err %d errno %d\n", err, errno);
err = bpf_map_get_fd_by_id(0);
CHECK(err >= 0 || errno != ENOENT,
"get-fd-by-notexist-map-id", "err %d errno %d\n", err, errno);
for (i = 0; i < nr_iters; i++)
objs[i] = NULL;
/* Check bpf_obj_get_info_by_fd() */
bzero(zeros, sizeof(zeros));
for (i = 0; i < nr_iters; i++) {
now = time(NULL);
err = bpf_prog_load(file, BPF_PROG_TYPE_SOCKET_FILTER,
&objs[i], &prog_fds[i]);
/* test_obj_id.o is a dumb prog. It should never fail
* to load.
*/
if (err)
error_cnt++;
assert(!err);
/* Insert a magic value to the map */
map_fds[i] = bpf_find_map(__func__, objs[i], "test_map_id");
assert(map_fds[i] >= 0);
err = bpf_map_update_elem(map_fds[i], &array_key,
&array_magic_value, 0);
assert(!err);
/* Check getting map info */
info_len = sizeof(struct bpf_map_info) * 2;
bzero(&map_infos[i], info_len);
err = bpf_obj_get_info_by_fd(map_fds[i], &map_infos[i],
&info_len);
if (CHECK(err ||
map_infos[i].type != BPF_MAP_TYPE_ARRAY ||
map_infos[i].key_size != sizeof(__u32) ||
map_infos[i].value_size != sizeof(__u64) ||
map_infos[i].max_entries != 1 ||
map_infos[i].map_flags != 0 ||
info_len != sizeof(struct bpf_map_info) ||
strcmp((char *)map_infos[i].name, expected_map_name),
"get-map-info(fd)",
"err %d errno %d type %d(%d) info_len %u(%lu) key_size %u value_size %u max_entries %u map_flags %X name %s(%s)\n",
err, errno,
map_infos[i].type, BPF_MAP_TYPE_ARRAY,
info_len, sizeof(struct bpf_map_info),
map_infos[i].key_size,
map_infos[i].value_size,
map_infos[i].max_entries,
map_infos[i].map_flags,
map_infos[i].name, expected_map_name))
goto done;
/* Check getting prog info */
info_len = sizeof(struct bpf_prog_info) * 2;
bzero(&prog_infos[i], info_len);
bzero(jited_insns, sizeof(jited_insns));
bzero(xlated_insns, sizeof(xlated_insns));
prog_infos[i].jited_prog_insns = ptr_to_u64(jited_insns);
prog_infos[i].jited_prog_len = sizeof(jited_insns);
prog_infos[i].xlated_prog_insns = ptr_to_u64(xlated_insns);
prog_infos[i].xlated_prog_len = sizeof(xlated_insns);
prog_infos[i].map_ids = ptr_to_u64(map_ids + i);
prog_infos[i].nr_map_ids = 2;
err = clock_gettime(CLOCK_REALTIME, &real_time_ts);
assert(!err);
err = clock_gettime(CLOCK_BOOTTIME, &boot_time_ts);
assert(!err);
err = bpf_obj_get_info_by_fd(prog_fds[i], &prog_infos[i],
&info_len);
load_time = (real_time_ts.tv_sec - boot_time_ts.tv_sec)
+ (prog_infos[i].load_time / nsec_per_sec);
if (CHECK(err ||
prog_infos[i].type != BPF_PROG_TYPE_SOCKET_FILTER ||
info_len != sizeof(struct bpf_prog_info) ||
(jit_enabled && !prog_infos[i].jited_prog_len) ||
(jit_enabled &&
!memcmp(jited_insns, zeros, sizeof(zeros))) ||
!prog_infos[i].xlated_prog_len ||
!memcmp(xlated_insns, zeros, sizeof(zeros)) ||
load_time < now - 60 || load_time > now + 60 ||
prog_infos[i].created_by_uid != my_uid ||
prog_infos[i].nr_map_ids != 1 ||
*(int *)prog_infos[i].map_ids != map_infos[i].id ||
strcmp((char *)prog_infos[i].name, expected_prog_name),
"get-prog-info(fd)",
"err %d errno %d i %d type %d(%d) info_len %u(%lu) jit_enabled %d jited_prog_len %u xlated_prog_len %u jited_prog %d xlated_prog %d load_time %lu(%lu) uid %u(%u) nr_map_ids %u(%u) map_id %u(%u) name %s(%s)\n",
err, errno, i,
prog_infos[i].type, BPF_PROG_TYPE_SOCKET_FILTER,
info_len, sizeof(struct bpf_prog_info),
jit_enabled,
prog_infos[i].jited_prog_len,
prog_infos[i].xlated_prog_len,
!!memcmp(jited_insns, zeros, sizeof(zeros)),
!!memcmp(xlated_insns, zeros, sizeof(zeros)),
load_time, now,
prog_infos[i].created_by_uid, my_uid,
prog_infos[i].nr_map_ids, 1,
*(int *)prog_infos[i].map_ids, map_infos[i].id,
prog_infos[i].name, expected_prog_name))
goto done;
}
/* Check bpf_prog_get_next_id() */
nr_id_found = 0;
next_id = 0;
while (!bpf_prog_get_next_id(next_id, &next_id)) {
struct bpf_prog_info prog_info = {};
__u32 saved_map_id;
int prog_fd;
info_len = sizeof(prog_info);
prog_fd = bpf_prog_get_fd_by_id(next_id);
if (prog_fd < 0 && errno == ENOENT)
/* The bpf_prog is in the dead row */
continue;
if (CHECK(prog_fd < 0, "get-prog-fd(next_id)",
"prog_fd %d next_id %d errno %d\n",
prog_fd, next_id, errno))
break;
for (i = 0; i < nr_iters; i++)
if (prog_infos[i].id == next_id)
break;
if (i == nr_iters)
continue;
nr_id_found++;
/* Negative test:
* prog_info.nr_map_ids = 1
* prog_info.map_ids = NULL
*/
prog_info.nr_map_ids = 1;
err = bpf_obj_get_info_by_fd(prog_fd, &prog_info, &info_len);
if (CHECK(!err || errno != EFAULT,
"get-prog-fd-bad-nr-map-ids", "err %d errno %d(%d)",
err, errno, EFAULT))
break;
bzero(&prog_info, sizeof(prog_info));
info_len = sizeof(prog_info);
saved_map_id = *(int *)(prog_infos[i].map_ids);
prog_info.map_ids = prog_infos[i].map_ids;
prog_info.nr_map_ids = 2;
err = bpf_obj_get_info_by_fd(prog_fd, &prog_info, &info_len);
prog_infos[i].jited_prog_insns = 0;
prog_infos[i].xlated_prog_insns = 0;
CHECK(err || info_len != sizeof(struct bpf_prog_info) ||
memcmp(&prog_info, &prog_infos[i], info_len) ||
*(int *)prog_info.map_ids != saved_map_id,
"get-prog-info(next_id->fd)",
"err %d errno %d info_len %u(%lu) memcmp %d map_id %u(%u)\n",
err, errno, info_len, sizeof(struct bpf_prog_info),
memcmp(&prog_info, &prog_infos[i], info_len),
*(int *)prog_info.map_ids, saved_map_id);
close(prog_fd);
}
CHECK(nr_id_found != nr_iters,
"check total prog id found by get_next_id",
"nr_id_found %u(%u)\n",
nr_id_found, nr_iters);
/* Check bpf_map_get_next_id() */
nr_id_found = 0;
next_id = 0;
while (!bpf_map_get_next_id(next_id, &next_id)) {
struct bpf_map_info map_info = {};
int map_fd;
info_len = sizeof(map_info);
map_fd = bpf_map_get_fd_by_id(next_id);
if (map_fd < 0 && errno == ENOENT)
/* The bpf_map is in the dead row */
continue;
if (CHECK(map_fd < 0, "get-map-fd(next_id)",
"map_fd %d next_id %u errno %d\n",
map_fd, next_id, errno))
break;
for (i = 0; i < nr_iters; i++)
if (map_infos[i].id == next_id)
break;
if (i == nr_iters)
continue;
nr_id_found++;
err = bpf_map_lookup_elem(map_fd, &array_key, &array_value);
assert(!err);
err = bpf_obj_get_info_by_fd(map_fd, &map_info, &info_len);
CHECK(err || info_len != sizeof(struct bpf_map_info) ||
memcmp(&map_info, &map_infos[i], info_len) ||
array_value != array_magic_value,
"check get-map-info(next_id->fd)",
"err %d errno %d info_len %u(%lu) memcmp %d array_value %llu(%llu)\n",
err, errno, info_len, sizeof(struct bpf_map_info),
memcmp(&map_info, &map_infos[i], info_len),
array_value, array_magic_value);
close(map_fd);
}
CHECK(nr_id_found != nr_iters,
"check total map id found by get_next_id",
"nr_id_found %u(%u)\n",
nr_id_found, nr_iters);
done:
for (i = 0; i < nr_iters; i++)
bpf_object__close(objs[i]);
}
static void test_xdp(void)
{
struct vip key4 = {.protocol = 6, .family = AF_INET};
struct vip key6 = {.protocol = 6, .family = AF_INET6};
struct iptnl_info value4 = {.family = AF_INET};
struct iptnl_info value6 = {.family = AF_INET6};
const char *file = "./test_xdp.o";
struct bpf_object *obj;
char buf[128];
struct ipv6hdr *iph6 = (void *)buf + sizeof(struct ethhdr);
struct iphdr *iph = (void *)buf + sizeof(struct ethhdr);
__u32 duration, retval, size;
int err, prog_fd, map_fd;
err = bpf_prog_load(file, BPF_PROG_TYPE_XDP, &obj, &prog_fd);
if (err) {
error_cnt++;
return;
}
map_fd = bpf_find_map(__func__, obj, "vip2tnl");
if (map_fd < 0)
goto out;
bpf_map_update_elem(map_fd, &key4, &value4, 0);
bpf_map_update_elem(map_fd, &key6, &value6, 0);
err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4),
buf, &size, &retval, &duration);
CHECK(err || errno || retval != XDP_TX || size != 74 ||
iph->protocol != IPPROTO_IPIP, "ipv4",
"err %d errno %d retval %d size %d\n",
err, errno, retval, size);
err = bpf_prog_test_run(prog_fd, 1, &pkt_v6, sizeof(pkt_v6),
buf, &size, &retval, &duration);
CHECK(err || errno || retval != XDP_TX || size != 114 ||
iph6->nexthdr != IPPROTO_IPV6, "ipv6",
"err %d errno %d retval %d size %d\n",
err, errno, retval, size);
out:
bpf_object__close(obj);
}
#define MAGIC_VAL 0x1234
#define NUM_ITER 100000
#define VIP_NUM 5
static void test_l4lb(void)
{
unsigned int nr_cpus = bpf_num_possible_cpus();
const char *file = "./test_l4lb.o";
struct vip key = {.protocol = 6};
struct vip_meta {
__u32 flags;
__u32 vip_num;
} value = {.vip_num = VIP_NUM};
__u32 stats_key = VIP_NUM;
struct vip_stats {
__u64 bytes;
__u64 pkts;
} stats[nr_cpus];
struct real_definition {
union {
__be32 dst;
__be32 dstv6[4];
};
__u8 flags;
} real_def = {.dst = MAGIC_VAL};
__u32 ch_key = 11, real_num = 3;
__u32 duration, retval, size;
int err, i, prog_fd, map_fd;
__u64 bytes = 0, pkts = 0;
struct bpf_object *obj;
char buf[128];
u32 *magic = (u32 *)buf;
err = bpf_prog_load(file, BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd);
if (err) {
error_cnt++;
return;
}
map_fd = bpf_find_map(__func__, obj, "vip_map");
if (map_fd < 0)
goto out;
bpf_map_update_elem(map_fd, &key, &value, 0);
map_fd = bpf_find_map(__func__, obj, "ch_rings");
if (map_fd < 0)
goto out;
bpf_map_update_elem(map_fd, &ch_key, &real_num, 0);
map_fd = bpf_find_map(__func__, obj, "reals");
if (map_fd < 0)
goto out;
bpf_map_update_elem(map_fd, &real_num, &real_def, 0);
err = bpf_prog_test_run(prog_fd, NUM_ITER, &pkt_v4, sizeof(pkt_v4),
buf, &size, &retval, &duration);
CHECK(err || errno || retval != 7/*TC_ACT_REDIRECT*/ || size != 54 ||
*magic != MAGIC_VAL, "ipv4",
"err %d errno %d retval %d size %d magic %x\n",
err, errno, retval, size, *magic);
err = bpf_prog_test_run(prog_fd, NUM_ITER, &pkt_v6, sizeof(pkt_v6),
buf, &size, &retval, &duration);
CHECK(err || errno || retval != 7/*TC_ACT_REDIRECT*/ || size != 74 ||
*magic != MAGIC_VAL, "ipv6",
"err %d errno %d retval %d size %d magic %x\n",
err, errno, retval, size, *magic);
map_fd = bpf_find_map(__func__, obj, "stats");
if (map_fd < 0)
goto out;
bpf_map_lookup_elem(map_fd, &stats_key, stats);
for (i = 0; i < nr_cpus; i++) {
bytes += stats[i].bytes;
pkts += stats[i].pkts;
}
if (bytes != MAGIC_BYTES * NUM_ITER * 2 || pkts != NUM_ITER * 2) {
error_cnt++;
printf("test_l4lb:FAIL:stats %lld %lld\n", bytes, pkts);
}
out:
bpf_object__close(obj);
}
static int bpf_pipeline_setdel_rules(struct net_mat_rule *rule, bool set_rule)
{
__u8 *key, *value, *tcache;
int err;
unsigned int i;
/* Assert on these because we expect matchlib should never pass us
* ill-formed rules. Added assert in the interim because I'm using
* this to fuzz-test the middle layer and want hard errors in lower
* layer when something goes wrong.
*/
assert(rule->table_id < BPF_MATCH_MAX_TABLES);
/* BPF backend uses a linear reference scheme where uid maps
* 1:1 with hw_rule_ids. So when the user ids greater than
* the map size drop them.
*
* Should middle layer catch this?
*/
printf("%s: rule %i max %i set:%s\n", __func__, rule->uid, table_aux[rule->table_id].max_elem, set_rule ? "yes" : "no");
assert(rule->uid < table_aux[rule->table_id].max_elem);
/*
if (uid > table_aux[rule.table_id].max_elem) {
MAT_LOG(DEBUG, "set_rule rule uid greater than table size!\n";
return -EINVAL;
}
*/
key = calloc(1, table_aux[rule->table_id].size_key);
if (!key)
return -ENOMEM;
tcache = table_cache[rule->table_id];
/* deleting a rule is just an update with a zero'd value
* so we only setup 'value' on set_rules.
*/
if (set_rule) {
value = calloc(1, table_aux[rule->table_id].size_value);
if (!value) {
free(key);
return -ENOMEM;
}
err = bpf_match_to_key(rule->table_id, rule->matches, key);
if (err)
return err;
err = bpf_match_to_value(rule->actions, value);
if (err)
return err;
bpf_map_update_elem((__u32)table_fds[rule->table_id],
(__u8 *) key,
value);
memcpy(&tcache[rule->uid], key, table_aux[rule->table_id].size_key);
} else {
key = (__u8 *)&tcache[rule->uid];
bpf_map_delete_elem((__u32)table_fds[rule->table_id],
(__u8 *) key);
}
printf("%s: using key: ", __func__);
for (i = 0; i < table_aux[rule->table_id].size_key; i++)
printf("%02x\n", key[i]);
printf("\n");
if (!set_rule)
memset(&tcache[rule->uid], 0, table_aux[rule->table_id].size_key);
return 0;
}
int main(int argc, char **argv)
{
unsigned char opt_flags[256] = {};
unsigned int kill_after_s = 0;
const char *optstr = "i:a:p:s:d:m:T:P:SNh";
int min_port = 0, max_port = 0;
struct iptnl_info tnl = {};
struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
struct vip vip = {};
char filename[256];
int opt;
int i;
tnl.family = AF_UNSPEC;
vip.protocol = IPPROTO_TCP;
for (i = 0; i < strlen(optstr); i++)
if (optstr[i] != 'h' && 'a' <= optstr[i] && optstr[i] <= 'z')
opt_flags[(unsigned char)optstr[i]] = 1;
while ((opt = getopt(argc, argv, optstr)) != -1) {
unsigned short family;
unsigned int *v6;
switch (opt) {
case 'i':
ifindex = atoi(optarg);
break;
case 'a':
vip.family = parse_ipstr(optarg, vip.daddr.v6);
if (vip.family == AF_UNSPEC)
return 1;
break;
case 'p':
if (parse_ports(optarg, &min_port, &max_port))
return 1;
break;
case 'P':
vip.protocol = atoi(optarg);
break;
case 's':
case 'd':
if (opt == 's')
v6 = tnl.saddr.v6;
else
v6 = tnl.daddr.v6;
family = parse_ipstr(optarg, v6);
if (family == AF_UNSPEC)
return 1;
if (tnl.family == AF_UNSPEC) {
tnl.family = family;
} else if (tnl.family != family) {
fprintf(stderr,
"The IP version of the src and dst addresses used in the IP encapsulation does not match\n");
return 1;
}
break;
case 'm':
if (!ether_aton_r(optarg,
(struct ether_addr *)tnl.dmac)) {
fprintf(stderr, "Invalid mac address:%s\n",
optarg);
return 1;
}
break;
case 'T':
kill_after_s = atoi(optarg);
break;
case 'S':
xdp_flags |= XDP_FLAGS_SKB_MODE;
break;
case 'N':
xdp_flags |= XDP_FLAGS_DRV_MODE;
break;
default:
usage(argv[0]);
return 1;
}
opt_flags[opt] = 0;
}
for (i = 0; i < strlen(optstr); i++) {
if (opt_flags[(unsigned int)optstr[i]]) {
fprintf(stderr, "Missing argument -%c\n", optstr[i]);
usage(argv[0]);
return 1;
}
}
if (setrlimit(RLIMIT_MEMLOCK, &r)) {
perror("setrlimit(RLIMIT_MEMLOCK, RLIM_INFINITY)");
return 1;
}
snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
if (load_bpf_file(filename)) {
printf("%s", bpf_log_buf);
return 1;
}
if (!prog_fd[0]) {
printf("load_bpf_file: %s\n", strerror(errno));
return 1;
}
signal(SIGINT, int_exit);
signal(SIGTERM, int_exit);
while (min_port <= max_port) {
vip.dport = htons(min_port++);
if (bpf_map_update_elem(map_fd[1], &vip, &tnl, BPF_NOEXIST)) {
perror("bpf_map_update_elem(&vip2tnl)");
return 1;
}
}
if (bpf_set_link_xdp_fd(ifindex, prog_fd[0], xdp_flags) < 0) {
printf("link set xdp fd failed\n");
return 1;
}
poll_stats(kill_after_s);
bpf_set_link_xdp_fd(ifindex, -1, xdp_flags);
return 0;
}
int bpf_testcb(struct bpf_sock_ops *skops)
{
int rv = -1;
int op;
op = (int) skops->op;
if (bpf_ntohl(skops->remote_port) != TESTPORT) {
skops->reply = -1;
return 0;
}
switch (op) {
case BPF_SOCK_OPS_TIMEOUT_INIT:
case BPF_SOCK_OPS_RWND_INIT:
case BPF_SOCK_OPS_NEEDS_ECN:
case BPF_SOCK_OPS_BASE_RTT:
case BPF_SOCK_OPS_RTO_CB:
rv = 1;
break;
case BPF_SOCK_OPS_TCP_CONNECT_CB:
case BPF_SOCK_OPS_TCP_LISTEN_CB:
case BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB:
case BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB:
bpf_sock_ops_cb_flags_set(skops, (BPF_SOCK_OPS_RETRANS_CB_FLAG|
BPF_SOCK_OPS_RTO_CB_FLAG));
rv = 1;
break;
case BPF_SOCK_OPS_RETRANS_CB: {
__u32 key = 0;
struct tcpnotify_globals g, *gp;
struct tcp_notifier msg = {
.type = 0xde,
.subtype = 0xad,
.source = 0xbe,
.hash = 0xef,
};
rv = 1;
/* Update results */
gp = bpf_map_lookup_elem(&global_map, &key);
if (!gp)
break;
g = *gp;
g.total_retrans = skops->total_retrans;
g.ncalls++;
bpf_map_update_elem(&global_map, &key, &g,
BPF_ANY);
bpf_perf_event_output(skops, &perf_event_map,
BPF_F_CURRENT_CPU,
&msg, sizeof(msg));
}
break;
default:
rv = -1;
}
skops->reply = rv;
return 1;
}
char _license[] SEC("license") = "GPL";
/* Size of the LRU amp is 2
* Add key=1 (+1 key)
* Add key=2 (+1 key)
* Lookup Key=1
* Add Key=3
* => Key=2 will be removed by LRU
* Iterate map. Only found key=1 and key=3
*/
static void test_lru_sanity0(int map_type, int map_flags)
{
unsigned long long key, value[nr_cpus];
int lru_map_fd, expected_map_fd;
int next_cpu = 0;
printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type,
map_flags);
assert(sched_next_online(0, &next_cpu) != -1);
if (map_flags & BPF_F_NO_COMMON_LRU)
lru_map_fd = create_map(map_type, map_flags, 2 * nr_cpus);
else
lru_map_fd = create_map(map_type, map_flags, 2);
assert(lru_map_fd != -1);
expected_map_fd = create_map(BPF_MAP_TYPE_HASH, 0, 2);
assert(expected_map_fd != -1);
value[0] = 1234;
/* insert key=1 element */
key = 1;
assert(!bpf_map_update_elem(lru_map_fd, &key, value, BPF_NOEXIST));
assert(!bpf_map_update_elem(expected_map_fd, &key, value,
BPF_NOEXIST));
/* BPF_NOEXIST means: add new element if it doesn't exist */
assert(bpf_map_update_elem(lru_map_fd, &key, value, BPF_NOEXIST) == -1
/* key=1 already exists */
&& errno == EEXIST);
assert(bpf_map_update_elem(lru_map_fd, &key, value, -1) == -1 &&
errno == EINVAL);
/* insert key=2 element */
/* check that key=2 is not found */
key = 2;
assert(bpf_map_lookup_elem(lru_map_fd, &key, value) == -1 &&
errno == ENOENT);
/* BPF_EXIST means: update existing element */
assert(bpf_map_update_elem(lru_map_fd, &key, value, BPF_EXIST) == -1 &&
/* key=2 is not there */
errno == ENOENT);
assert(!bpf_map_update_elem(lru_map_fd, &key, value, BPF_NOEXIST));
/* insert key=3 element */
/* check that key=3 is not found */
key = 3;
assert(bpf_map_lookup_elem(lru_map_fd, &key, value) == -1 &&
errno == ENOENT);
/* check that key=1 can be found and mark the ref bit to
* stop LRU from removing key=1
*/
key = 1;
assert(!bpf_map_lookup_elem(lru_map_fd, &key, value));
assert(value[0] == 1234);
key = 3;
assert(!bpf_map_update_elem(lru_map_fd, &key, value, BPF_NOEXIST));
assert(!bpf_map_update_elem(expected_map_fd, &key, value,
BPF_NOEXIST));
/* key=2 has been removed from the LRU */
key = 2;
assert(bpf_map_lookup_elem(lru_map_fd, &key, value) == -1);
assert(map_equal(lru_map_fd, expected_map_fd));
close(expected_map_fd);
close(lru_map_fd);
printf("Pass\n");
}
int main(int argc, char **argv)
{
const char *optstr = "SN";
char filename[256];
int ret, opt, key = 0;
while ((opt = getopt(argc, argv, optstr)) != -1) {
switch (opt) {
case 'S':
xdp_flags |= XDP_FLAGS_SKB_MODE;
break;
case 'N':
xdp_flags |= XDP_FLAGS_DRV_MODE;
break;
default:
usage(basename(argv[0]));
return 1;
}
}
if (optind == argc) {
printf("usage: %s IFINDEX_IN IFINDEX_OUT\n", argv[0]);
return 1;
}
ifindex_in = strtoul(argv[optind], NULL, 0);
ifindex_out = strtoul(argv[optind + 1], NULL, 0);
printf("input: %d output: %d\n", ifindex_in, ifindex_out);
snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
if (load_bpf_file(filename)) {
printf("%s", bpf_log_buf);
return 1;
}
if (!prog_fd[0]) {
printf("load_bpf_file: %s\n", strerror(errno));
return 1;
}
if (set_link_xdp_fd(ifindex_in, prog_fd[0], xdp_flags) < 0) {
printf("ERROR: link set xdp fd failed on %d\n", ifindex_in);
return 1;
}
/* Loading dummy XDP prog on out-device */
if (set_link_xdp_fd(ifindex_out, prog_fd[1],
(xdp_flags | XDP_FLAGS_UPDATE_IF_NOEXIST)) < 0) {
printf("WARN: link set xdp fd failed on %d\n", ifindex_out);
ifindex_out_xdp_dummy_attached = false;
}
signal(SIGINT, int_exit);
signal(SIGTERM, int_exit);
printf("map[0] (vports) = %i, map[1] (map) = %i, map[2] (count) = %i\n",
map_fd[0], map_fd[1], map_fd[2]);
/* populate virtual to physical port map */
ret = bpf_map_update_elem(map_fd[0], &key, &ifindex_out, 0);
if (ret) {
perror("bpf_update_elem");
goto out;
}
poll_stats(2, ifindex_out);
out:
return 0;
}
static int bpf_perf_event_open(int map_fd, int key, int cpu)
{
struct perf_event_attr attr = {
.sample_type = PERF_SAMPLE_RAW | PERF_SAMPLE_TIME,
.type = PERF_TYPE_SOFTWARE,
.config = PERF_COUNT_SW_BPF_OUTPUT,
};
int pmu_fd;
pmu_fd = sys_perf_event_open(&attr, -1, cpu, -1, 0);
if (pmu_fd < 0) {
p_err("failed to open perf event %d for CPU %d", key, cpu);
return -1;
}
if (bpf_map_update_elem(map_fd, &key, &pmu_fd, BPF_ANY)) {
p_err("failed to update map for event %d for CPU %d", key, cpu);
goto err_close;
}
if (ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0)) {
p_err("failed to enable event %d for CPU %d", key, cpu);
goto err_close;
}
return pmu_fd;
err_close:
close(pmu_fd);
return -1;
}
int do_event_pipe(int argc, char **argv)
{
int i, nfds, map_fd, index = -1, cpu = -1;
struct bpf_map_info map_info = {};
struct event_ring_info *rings;
size_t tmp_buf_sz = 0;
void *tmp_buf = NULL;
struct pollfd *pfds;
__u32 map_info_len;
bool do_all = true;
map_info_len = sizeof(map_info);
map_fd = map_parse_fd_and_info(&argc, &argv, &map_info, &map_info_len);
if (map_fd < 0)
return -1;
if (map_info.type != BPF_MAP_TYPE_PERF_EVENT_ARRAY) {
p_err("map is not a perf event array");
goto err_close_map;
}
while (argc) {
if (argc < 2)
BAD_ARG();
if (is_prefix(*argv, "cpu")) {
char *endptr;
NEXT_ARG();
cpu = strtoul(*argv, &endptr, 0);
if (*endptr) {
p_err("can't parse %s as CPU ID", **argv);
goto err_close_map;
}
NEXT_ARG();
} else if (is_prefix(*argv, "index")) {
char *endptr;
NEXT_ARG();
index = strtoul(*argv, &endptr, 0);
if (*endptr) {
p_err("can't parse %s as index", **argv);
goto err_close_map;
}
NEXT_ARG();
} else {
BAD_ARG();
}
do_all = false;
}
if (!do_all) {
if (index == -1 || cpu == -1) {
p_err("cpu and index must be specified together");
goto err_close_map;
}
nfds = 1;
} else {
nfds = min(get_possible_cpus(), map_info.max_entries);
cpu = 0;
index = 0;
}
rings = calloc(nfds, sizeof(rings[0]));
if (!rings)
goto err_close_map;
pfds = calloc(nfds, sizeof(pfds[0]));
if (!pfds)
goto err_free_rings;
for (i = 0; i < nfds; i++) {
rings[i].cpu = cpu + i;
rings[i].key = index + i;
rings[i].fd = bpf_perf_event_open(map_fd, rings[i].key,
rings[i].cpu);
if (rings[i].fd < 0)
goto err_close_fds_prev;
rings[i].mem = perf_event_mmap(rings[i].fd);
if (!rings[i].mem)
goto err_close_fds_current;
pfds[i].fd = rings[i].fd;
pfds[i].events = POLLIN;
}
signal(SIGINT, int_exit);
signal(SIGHUP, int_exit);
signal(SIGTERM, int_exit);
if (json_output)
jsonw_start_array(json_wtr);
while (!stop) {
poll(pfds, nfds, 200);
for (i = 0; i < nfds; i++)
perf_event_read(&rings[i], &tmp_buf, &tmp_buf_sz);
}
free(tmp_buf);
if (json_output)
jsonw_end_array(json_wtr);
for (i = 0; i < nfds; i++) {
perf_event_unmap(rings[i].mem);
close(rings[i].fd);
}
free(pfds);
free(rings);
close(map_fd);
return 0;
err_close_fds_prev:
while (i--) {
perf_event_unmap(rings[i].mem);
err_close_fds_current:
close(rings[i].fd);
}
free(pfds);
err_free_rings:
free(rings);
err_close_map:
close(map_fd);
return -1;
}
/* Size of the LRU map is 2*tgt_free
* It is to test the active/inactive list rotation
* Insert 1 to 2*tgt_free (+2*tgt_free keys)
* Lookup key 1 to tgt_free*3/2
* Add 1+2*tgt_free to tgt_free*5/2 (+tgt_free/2 keys)
* => key 1+tgt_free*3/2 to 2*tgt_free are removed from LRU
*/
static void test_lru_sanity3(int map_type, int map_flags, unsigned int tgt_free)
{
unsigned long long key, end_key, value[nr_cpus];
int lru_map_fd, expected_map_fd;
unsigned int batch_size;
unsigned int map_size;
int next_cpu = 0;
printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type,
map_flags);
assert(sched_next_online(0, &next_cpu) != -1);
batch_size = tgt_free / 2;
assert(batch_size * 2 == tgt_free);
map_size = tgt_free * 2;
if (map_flags & BPF_F_NO_COMMON_LRU)
lru_map_fd = create_map(map_type, map_flags,
map_size * nr_cpus);
else
lru_map_fd = create_map(map_type, map_flags, map_size);
assert(lru_map_fd != -1);
expected_map_fd = create_map(BPF_MAP_TYPE_HASH, 0, map_size);
assert(expected_map_fd != -1);
value[0] = 1234;
/* Insert 1 to 2*tgt_free (+2*tgt_free keys) */
end_key = 1 + (2 * tgt_free);
for (key = 1; key < end_key; key++)
assert(!bpf_map_update_elem(lru_map_fd, &key, value,
BPF_NOEXIST));
/* Lookup key 1 to tgt_free*3/2 */
end_key = tgt_free + batch_size;
for (key = 1; key < end_key; key++) {
assert(!bpf_map_lookup_elem(lru_map_fd, &key, value));
assert(!bpf_map_update_elem(expected_map_fd, &key, value,
BPF_NOEXIST));
}
/* Add 1+2*tgt_free to tgt_free*5/2
* (+tgt_free/2 keys)
*/
key = 2 * tgt_free + 1;
end_key = key + batch_size;
for (; key < end_key; key++) {
assert(!bpf_map_update_elem(lru_map_fd, &key, value,
BPF_NOEXIST));
assert(!bpf_map_update_elem(expected_map_fd, &key, value,
BPF_NOEXIST));
}
assert(map_equal(lru_map_fd, expected_map_fd));
close(expected_map_fd);
close(lru_map_fd);
printf("Pass\n");
}
tmp = *a;
*a = *b;
*b = tmp;
}
static int create_cpu_entry(__u32 cpu, __u32 queue_size,
__u32 avail_idx, bool new)
{
__u32 curr_cpus_count = 0;
__u32 key = 0;
int ret;
/* Add a CPU entry to cpumap, as this allocate a cpu entry in
* the kernel for the cpu.
*/
ret = bpf_map_update_elem(map_fd[0], &cpu, &queue_size, 0);
if (ret) {
fprintf(stderr, "Create CPU entry failed (err:%d)\n", ret);
exit(EXIT_FAIL_BPF);
}
/* Inform bpf_prog's that a new CPU is available to select
* from via some control maps.
*/
/* map_fd[5] = cpus_available */
ret = bpf_map_update_elem(map_fd[5], &avail_idx, &cpu, 0);
if (ret) {
fprintf(stderr, "Add to avail CPUs failed\n");
exit(EXIT_FAIL_BPF);
}
static void test(void)
{
int listen_fd, cli_fd, accept_fd, epfd, err;
struct epoll_event ev;
socklen_t addrlen;
addrlen = sizeof(struct sockaddr_in6);
ev.events = EPOLLIN;
epfd = epoll_create(1);
CHECK(epfd == -1, "epoll_create()", "epfd:%d errno:%d", epfd, errno);
/* Prepare listen_fd */
listen_fd = socket(AF_INET6, SOCK_STREAM | SOCK_NONBLOCK, 0);
CHECK(listen_fd == -1, "socket()", "listen_fd:%d errno:%d",
listen_fd, errno);
init_loopback6(&srv_sa6);
err = bind(listen_fd, (struct sockaddr *)&srv_sa6, sizeof(srv_sa6));
CHECK(err, "bind(listen_fd)", "err:%d errno:%d", err, errno);
err = getsockname(listen_fd, (struct sockaddr *)&srv_sa6, &addrlen);
CHECK(err, "getsockname(listen_fd)", "err:%d errno:%d", err, errno);
err = listen(listen_fd, 1);
CHECK(err, "listen(listen_fd)", "err:%d errno:%d", err, errno);
/* Prepare cli_fd */
cli_fd = socket(AF_INET6, SOCK_STREAM | SOCK_NONBLOCK, 0);
CHECK(cli_fd == -1, "socket()", "cli_fd:%d errno:%d", cli_fd, errno);
init_loopback6(&cli_sa6);
err = bind(cli_fd, (struct sockaddr *)&cli_sa6, sizeof(cli_sa6));
CHECK(err, "bind(cli_fd)", "err:%d errno:%d", err, errno);
err = getsockname(cli_fd, (struct sockaddr *)&cli_sa6, &addrlen);
CHECK(err, "getsockname(cli_fd)", "err:%d errno:%d",
err, errno);
/* Update addr_map with srv_sa6 and cli_sa6 */
err = bpf_map_update_elem(addr_map_fd, &srv_idx, &srv_sa6, 0);
CHECK(err, "map_update", "err:%d errno:%d", err, errno);
err = bpf_map_update_elem(addr_map_fd, &cli_idx, &cli_sa6, 0);
CHECK(err, "map_update", "err:%d errno:%d", err, errno);
/* Connect from cli_sa6 to srv_sa6 */
err = connect(cli_fd, (struct sockaddr *)&srv_sa6, addrlen);
printf("srv_sa6.sin6_port:%u cli_sa6.sin6_port:%u\n\n",
ntohs(srv_sa6.sin6_port), ntohs(cli_sa6.sin6_port));
CHECK(err && errno != EINPROGRESS,
"connect(cli_fd)", "err:%d errno:%d", err, errno);
ev.data.fd = listen_fd;
err = epoll_ctl(epfd, EPOLL_CTL_ADD, listen_fd, &ev);
CHECK(err, "epoll_ctl(EPOLL_CTL_ADD, listen_fd)", "err:%d errno:%d",
err, errno);
/* Accept the connection */
/* Have some timeout in accept(listen_fd). Just in case. */
err = epoll_wait(epfd, &ev, 1, 1000);
CHECK(err != 1 || ev.data.fd != listen_fd,
"epoll_wait(listen_fd)",
"err:%d errno:%d ev.data.fd:%d listen_fd:%d",
err, errno, ev.data.fd, listen_fd);
accept_fd = accept(listen_fd, NULL, NULL);
CHECK(accept_fd == -1, "accept(listen_fd)", "accept_fd:%d errno:%d",
accept_fd, errno);
close(listen_fd);
/* Send some data from accept_fd to cli_fd */
err = send(accept_fd, DATA, DATA_LEN, 0);
CHECK(err != DATA_LEN, "send(accept_fd)", "err:%d errno:%d",
err, errno);
/* Have some timeout in recv(cli_fd). Just in case. */
ev.data.fd = cli_fd;
err = epoll_ctl(epfd, EPOLL_CTL_ADD, cli_fd, &ev);
CHECK(err, "epoll_ctl(EPOLL_CTL_ADD, cli_fd)", "err:%d errno:%d",
err, errno);
err = epoll_wait(epfd, &ev, 1, 1000);
CHECK(err != 1 || ev.data.fd != cli_fd,
"epoll_wait(cli_fd)", "err:%d errno:%d ev.data.fd:%d cli_fd:%d",
err, errno, ev.data.fd, cli_fd);
err = recv(cli_fd, NULL, 0, MSG_TRUNC);
CHECK(err, "recv(cli_fd)", "err:%d errno:%d", err, errno);
close(epfd);
close(accept_fd);
close(cli_fd);
check_result();
}
static int test_multiprog(void)
{
__u32 prog_ids[4], prog_cnt = 0, attach_flags, saved_prog_id;
int cg1 = 0, cg2 = 0, cg3 = 0, cg4 = 0, cg5 = 0, key = 0;
int drop_prog, allow_prog[6] = {}, rc = 0;
unsigned long long value;
int i = 0;
for (i = 0; i < 6; i++) {
allow_prog[i] = prog_load_cnt(1, 1 << i);
if (!allow_prog[i])
goto err;
}
drop_prog = prog_load_cnt(0, 1);
if (!drop_prog)
goto err;
if (setup_cgroup_environment())
goto err;
cg1 = create_and_get_cgroup("/cg1");
if (cg1 < 0)
goto err;
cg2 = create_and_get_cgroup("/cg1/cg2");
if (cg2 < 0)
goto err;
cg3 = create_and_get_cgroup("/cg1/cg2/cg3");
if (cg3 < 0)
goto err;
cg4 = create_and_get_cgroup("/cg1/cg2/cg3/cg4");
if (cg4 < 0)
goto err;
cg5 = create_and_get_cgroup("/cg1/cg2/cg3/cg4/cg5");
if (cg5 < 0)
goto err;
if (join_cgroup("/cg1/cg2/cg3/cg4/cg5"))
goto err;
if (bpf_prog_attach(allow_prog[0], cg1, BPF_CGROUP_INET_EGRESS,
BPF_F_ALLOW_MULTI)) {
log_err("Attaching prog to cg1");
goto err;
}
if (!bpf_prog_attach(allow_prog[0], cg1, BPF_CGROUP_INET_EGRESS,
BPF_F_ALLOW_MULTI)) {
log_err("Unexpected success attaching the same prog to cg1");
goto err;
}
if (bpf_prog_attach(allow_prog[1], cg1, BPF_CGROUP_INET_EGRESS,
BPF_F_ALLOW_MULTI)) {
log_err("Attaching prog2 to cg1");
goto err;
}
if (bpf_prog_attach(allow_prog[2], cg2, BPF_CGROUP_INET_EGRESS,
BPF_F_ALLOW_OVERRIDE)) {
log_err("Attaching prog to cg2");
goto err;
}
if (bpf_prog_attach(allow_prog[3], cg3, BPF_CGROUP_INET_EGRESS,
BPF_F_ALLOW_MULTI)) {
log_err("Attaching prog to cg3");
goto err;
}
if (bpf_prog_attach(allow_prog[4], cg4, BPF_CGROUP_INET_EGRESS,
BPF_F_ALLOW_OVERRIDE)) {
log_err("Attaching prog to cg4");
goto err;
}
if (bpf_prog_attach(allow_prog[5], cg5, BPF_CGROUP_INET_EGRESS, 0)) {
log_err("Attaching prog to cg5");
goto err;
}
assert(system(PING_CMD) == 0);
assert(bpf_map_lookup_elem(map_fd, &key, &value) == 0);
assert(value == 1 + 2 + 8 + 32);
/* query the number of effective progs in cg5 */
assert(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, BPF_F_QUERY_EFFECTIVE,
NULL, NULL, &prog_cnt) == 0);
assert(prog_cnt == 4);
/* retrieve prog_ids of effective progs in cg5 */
assert(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, BPF_F_QUERY_EFFECTIVE,
&attach_flags, prog_ids, &prog_cnt) == 0);
assert(prog_cnt == 4);
assert(attach_flags == 0);
saved_prog_id = prog_ids[0];
/* check enospc handling */
prog_ids[0] = 0;
prog_cnt = 2;
assert(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, BPF_F_QUERY_EFFECTIVE,
&attach_flags, prog_ids, &prog_cnt) == -1 &&
errno == ENOSPC);
assert(prog_cnt == 4);
/* check that prog_ids are returned even when buffer is too small */
assert(prog_ids[0] == saved_prog_id);
/* retrieve prog_id of single attached prog in cg5 */
prog_ids[0] = 0;
assert(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, 0,
NULL, prog_ids, &prog_cnt) == 0);
assert(prog_cnt == 1);
assert(prog_ids[0] == saved_prog_id);
/* detach bottom program and ping again */
if (bpf_prog_detach2(-1, cg5, BPF_CGROUP_INET_EGRESS)) {
log_err("Detaching prog from cg5");
goto err;
}
value = 0;
assert(bpf_map_update_elem(map_fd, &key, &value, 0) == 0);
assert(system(PING_CMD) == 0);
assert(bpf_map_lookup_elem(map_fd, &key, &value) == 0);
assert(value == 1 + 2 + 8 + 16);
/* detach 3rd from bottom program and ping again */
errno = 0;
if (!bpf_prog_detach2(0, cg3, BPF_CGROUP_INET_EGRESS)) {
log_err("Unexpected success on detach from cg3");
goto err;
}
if (bpf_prog_detach2(allow_prog[3], cg3, BPF_CGROUP_INET_EGRESS)) {
log_err("Detaching from cg3");
goto err;
}
value = 0;
assert(bpf_map_update_elem(map_fd, &key, &value, 0) == 0);
assert(system(PING_CMD) == 0);
assert(bpf_map_lookup_elem(map_fd, &key, &value) == 0);
assert(value == 1 + 2 + 16);
/* detach 2nd from bottom program and ping again */
if (bpf_prog_detach2(-1, cg4, BPF_CGROUP_INET_EGRESS)) {
log_err("Detaching prog from cg4");
goto err;
}
value = 0;
assert(bpf_map_update_elem(map_fd, &key, &value, 0) == 0);
assert(system(PING_CMD) == 0);
assert(bpf_map_lookup_elem(map_fd, &key, &value) == 0);
assert(value == 1 + 2 + 4);
prog_cnt = 4;
assert(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, BPF_F_QUERY_EFFECTIVE,
&attach_flags, prog_ids, &prog_cnt) == 0);
assert(prog_cnt == 3);
assert(attach_flags == 0);
assert(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, 0,
NULL, prog_ids, &prog_cnt) == 0);
assert(prog_cnt == 0);
goto out;
err:
rc = 1;
out:
for (i = 0; i < 6; i++)
if (allow_prog[i] > 0)
close(allow_prog[i]);
close(cg1);
close(cg2);
close(cg3);
close(cg4);
close(cg5);
cleanup_cgroup_environment();
if (!rc)
printf("### multi:PASS\n");
else
printf("### multi:FAIL\n");
return rc;
}
/* Size of the LRU map 1.5 * tgt_free
* Insert 1 to tgt_free (+tgt_free keys)
* Update 1 to tgt_free/2
* => The original 1 to tgt_free/2 will be removed due to
* the LRU shrink process
* Re-insert 1 to tgt_free/2 again and do a lookup immeidately
* Insert 1+tgt_free to tgt_free*3/2
* Insert 1+tgt_free*3/2 to tgt_free*5/2
* => Key 1+tgt_free to tgt_free*3/2
* will be removed from LRU because it has never
* been lookup and ref bit is not set
*/
static void test_lru_sanity2(int map_type, int map_flags, unsigned int tgt_free)
{
unsigned long long key, value[nr_cpus];
unsigned long long end_key;
int lru_map_fd, expected_map_fd;
unsigned int batch_size;
unsigned int map_size;
int next_cpu = 0;
if (map_flags & BPF_F_NO_COMMON_LRU)
/* Ther percpu lru list (i.e each cpu has its own LRU
* list) does not have a local free list. Hence,
* it will only free old nodes till there is no free
* from the LRU list. Hence, this test does not apply
* to BPF_F_NO_COMMON_LRU
*/
return;
printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type,
map_flags);
assert(sched_next_online(0, &next_cpu) != -1);
batch_size = tgt_free / 2;
assert(batch_size * 2 == tgt_free);
map_size = tgt_free + batch_size;
if (map_flags & BPF_F_NO_COMMON_LRU)
lru_map_fd = create_map(map_type, map_flags,
map_size * nr_cpus);
else
lru_map_fd = create_map(map_type, map_flags, map_size);
assert(lru_map_fd != -1);
expected_map_fd = create_map(BPF_MAP_TYPE_HASH, 0, map_size);
assert(expected_map_fd != -1);
value[0] = 1234;
/* Insert 1 to tgt_free (+tgt_free keys) */
end_key = 1 + tgt_free;
for (key = 1; key < end_key; key++)
assert(!bpf_map_update_elem(lru_map_fd, &key, value,
BPF_NOEXIST));
/* Any bpf_map_update_elem will require to acquire a new node
* from LRU first.
*
* The local list is running out of free nodes.
* It gets from the global LRU list which tries to
* shrink the inactive list to get tgt_free
* number of free nodes.
*
* Hence, the oldest key 1 to tgt_free/2
* are removed from the LRU list.
*/
key = 1;
if (map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) {
assert(!bpf_map_update_elem(lru_map_fd, &key, value,
BPF_NOEXIST));
assert(!bpf_map_delete_elem(lru_map_fd, &key));
} else {
assert(bpf_map_update_elem(lru_map_fd, &key, value,
BPF_EXIST));
}
/* Re-insert 1 to tgt_free/2 again and do a lookup
* immeidately.
*/
end_key = 1 + batch_size;
value[0] = 4321;
for (key = 1; key < end_key; key++) {
assert(bpf_map_lookup_elem(lru_map_fd, &key, value));
assert(!bpf_map_update_elem(lru_map_fd, &key, value,
BPF_NOEXIST));
assert(!bpf_map_lookup_elem(lru_map_fd, &key, value));
assert(value[0] == 4321);
assert(!bpf_map_update_elem(expected_map_fd, &key, value,
BPF_NOEXIST));
}
value[0] = 1234;
/* Insert 1+tgt_free to tgt_free*3/2 */
end_key = 1 + tgt_free + batch_size;
for (key = 1 + tgt_free; key < end_key; key++)
/* These newly added but not referenced keys will be
* gone during the next LRU shrink.
*/
assert(!bpf_map_update_elem(lru_map_fd, &key, value,
BPF_NOEXIST));
/* Insert 1+tgt_free*3/2 to tgt_free*5/2 */
end_key = key + tgt_free;
for (; key < end_key; key++) {
assert(!bpf_map_update_elem(lru_map_fd, &key, value,
BPF_NOEXIST));
assert(!bpf_map_update_elem(expected_map_fd, &key, value,
BPF_NOEXIST));
}
assert(map_equal(lru_map_fd, expected_map_fd));
close(expected_map_fd);
close(lru_map_fd);
printf("Pass\n");
}
