summaryrefslogtreecommitdiff
path: root/tools
diff options
context:
space:
mode:
Diffstat (limited to 'tools')
-rw-r--r--tools/include/uapi/linux/bpf.h85
-rw-r--r--tools/lib/bpf/libbpf.c104
-rw-r--r--tools/testing/selftests/bpf/prog_tests/get_func_ip_test.c53
-rw-r--r--tools/testing/selftests/bpf/prog_tests/sockmap_listen.c406
-rw-r--r--tools/testing/selftests/bpf/prog_tests/timer.c55
-rw-r--r--tools/testing/selftests/bpf/prog_tests/timer_mim.c69
-rw-r--r--tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c105
-rw-r--r--tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c43
-rw-r--r--tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c39
-rw-r--r--tools/testing/selftests/bpf/progs/get_func_ip_test.c73
-rw-r--r--tools/testing/selftests/bpf/progs/test_tc_tunnel.c1
-rw-r--r--tools/testing/selftests/bpf/progs/test_xdp_context_test_run.c20
-rw-r--r--tools/testing/selftests/bpf/progs/timer.c297
-rw-r--r--tools/testing/selftests/bpf/progs/timer_mim.c88
-rw-r--r--tools/testing/selftests/bpf/progs/timer_mim_reject.c74
-rw-r--r--tools/testing/selftests/net/Makefile2
-rw-r--r--tools/testing/selftests/net/config1
-rw-r--r--tools/testing/selftests/net/ioam6.sh297
-rw-r--r--tools/testing/selftests/net/ioam6_parser.c402
-rwxr-xr-xtools/testing/selftests/net/veth.sh183
-rw-r--r--tools/testing/selftests/tc-testing/tc-tests/actions/skbmod.json24
21 files changed, 2276 insertions, 145 deletions
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index bf9252c7381e..2db6925e04f4 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -324,9 +324,6 @@ union bpf_iter_link_info {
* **BPF_PROG_TYPE_SK_LOOKUP**
* *data_in* and *data_out* must be NULL.
*
- * **BPF_PROG_TYPE_XDP**
- * *ctx_in* and *ctx_out* must be NULL.
- *
* **BPF_PROG_TYPE_RAW_TRACEPOINT**,
* **BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE**
*
@@ -3249,7 +3246,7 @@ union bpf_attr {
* long bpf_sk_select_reuseport(struct sk_reuseport_md *reuse, struct bpf_map *map, void *key, u64 flags)
* Description
* Select a **SO_REUSEPORT** socket from a
- * **BPF_MAP_TYPE_REUSEPORT_ARRAY** *map*.
+ * **BPF_MAP_TYPE_REUSEPORT_SOCKARRAY** *map*.
* It checks the selected socket is matching the incoming
* request in the socket buffer.
* Return
@@ -4780,6 +4777,76 @@ union bpf_attr {
* Execute close syscall for given FD.
* Return
* A syscall result.
+ *
+ * long bpf_timer_init(struct bpf_timer *timer, struct bpf_map *map, u64 flags)
+ * Description
+ * Initialize the timer.
+ * First 4 bits of *flags* specify clockid.
+ * Only CLOCK_MONOTONIC, CLOCK_REALTIME, CLOCK_BOOTTIME are allowed.
+ * All other bits of *flags* are reserved.
+ * The verifier will reject the program if *timer* is not from
+ * the same *map*.
+ * Return
+ * 0 on success.
+ * **-EBUSY** if *timer* is already initialized.
+ * **-EINVAL** if invalid *flags* are passed.
+ * **-EPERM** if *timer* is in a map that doesn't have any user references.
+ * The user space should either hold a file descriptor to a map with timers
+ * or pin such map in bpffs. When map is unpinned or file descriptor is
+ * closed all timers in the map will be cancelled and freed.
+ *
+ * long bpf_timer_set_callback(struct bpf_timer *timer, void *callback_fn)
+ * Description
+ * Configure the timer to call *callback_fn* static function.
+ * Return
+ * 0 on success.
+ * **-EINVAL** if *timer* was not initialized with bpf_timer_init() earlier.
+ * **-EPERM** if *timer* is in a map that doesn't have any user references.
+ * The user space should either hold a file descriptor to a map with timers
+ * or pin such map in bpffs. When map is unpinned or file descriptor is
+ * closed all timers in the map will be cancelled and freed.
+ *
+ * long bpf_timer_start(struct bpf_timer *timer, u64 nsecs, u64 flags)
+ * Description
+ * Set timer expiration N nanoseconds from the current time. The
+ * configured callback will be invoked in soft irq context on some cpu
+ * and will not repeat unless another bpf_timer_start() is made.
+ * In such case the next invocation can migrate to a different cpu.
+ * Since struct bpf_timer is a field inside map element the map
+ * owns the timer. The bpf_timer_set_callback() will increment refcnt
+ * of BPF program to make sure that callback_fn code stays valid.
+ * When user space reference to a map reaches zero all timers
+ * in a map are cancelled and corresponding program's refcnts are
+ * decremented. This is done to make sure that Ctrl-C of a user
+ * process doesn't leave any timers running. If map is pinned in
+ * bpffs the callback_fn can re-arm itself indefinitely.
+ * bpf_map_update/delete_elem() helpers and user space sys_bpf commands
+ * cancel and free the timer in the given map element.
+ * The map can contain timers that invoke callback_fn-s from different
+ * programs. The same callback_fn can serve different timers from
+ * different maps if key/value layout matches across maps.
+ * Every bpf_timer_set_callback() can have different callback_fn.
+ *
+ * Return
+ * 0 on success.
+ * **-EINVAL** if *timer* was not initialized with bpf_timer_init() earlier
+ * or invalid *flags* are passed.
+ *
+ * long bpf_timer_cancel(struct bpf_timer *timer)
+ * Description
+ * Cancel the timer and wait for callback_fn to finish if it was running.
+ * Return
+ * 0 if the timer was not active.
+ * 1 if the timer was active.
+ * **-EINVAL** if *timer* was not initialized with bpf_timer_init() earlier.
+ * **-EDEADLK** if callback_fn tried to call bpf_timer_cancel() on its
+ * own timer which would have led to a deadlock otherwise.
+ *
+ * u64 bpf_get_func_ip(void *ctx)
+ * Description
+ * Get address of the traced function (for tracing and kprobe programs).
+ * Return
+ * Address of the traced function.
*/
#define __BPF_FUNC_MAPPER(FN) \
FN(unspec), \
@@ -4951,6 +5018,11 @@ union bpf_attr {
FN(sys_bpf), \
FN(btf_find_by_name_kind), \
FN(sys_close), \
+ FN(timer_init), \
+ FN(timer_set_callback), \
+ FN(timer_start), \
+ FN(timer_cancel), \
+ FN(get_func_ip), \
/* */
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
@@ -6077,6 +6149,11 @@ struct bpf_spin_lock {
__u32 val;
};
+struct bpf_timer {
+ __u64 :64;
+ __u64 :64;
+} __attribute__((aligned(8)));
+
struct bpf_sysctl {
__u32 write; /* Sysctl is being read (= 0) or written (= 1).
* Allows 1,2,4-byte read, but no write.
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 6f5e2757bb3c..4ccfae30e681 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -3894,6 +3894,42 @@ static int bpf_map_find_btf_info(struct bpf_object *obj, struct bpf_map *map)
return 0;
}
+static int bpf_get_map_info_from_fdinfo(int fd, struct bpf_map_info *info)
+{
+ char file[PATH_MAX], buff[4096];
+ FILE *fp;
+ __u32 val;
+ int err;
+
+ snprintf(file, sizeof(file), "/proc/%d/fdinfo/%d", getpid(), fd);
+ memset(info, 0, sizeof(*info));
+
+ fp = fopen(file, "r");
+ if (!fp) {
+ err = -errno;
+ pr_warn("failed to open %s: %d. No procfs support?\n", file,
+ err);
+ return err;
+ }
+
+ while (fgets(buff, sizeof(buff), fp)) {
+ if (sscanf(buff, "map_type:\t%u", &val) == 1)
+ info->type = val;
+ else if (sscanf(buff, "key_size:\t%u", &val) == 1)
+ info->key_size = val;
+ else if (sscanf(buff, "value_size:\t%u", &val) == 1)
+ info->value_size = val;
+ else if (sscanf(buff, "max_entries:\t%u", &val) == 1)
+ info->max_entries = val;
+ else if (sscanf(buff, "map_flags:\t%i", &val) == 1)
+ info->map_flags = val;
+ }
+
+ fclose(fp);
+
+ return 0;
+}
+
int bpf_map__reuse_fd(struct bpf_map *map, int fd)
{
struct bpf_map_info info = {};
@@ -3902,6 +3938,8 @@ int bpf_map__reuse_fd(struct bpf_map *map, int fd)
char *new_name;
err = bpf_obj_get_info_by_fd(fd, &info, &len);
+ if (err && errno == EINVAL)
+ err = bpf_get_map_info_from_fdinfo(fd, &info);
if (err)
return libbpf_err(err);
@@ -4381,12 +4419,16 @@ static bool map_is_reuse_compat(const struct bpf_map *map, int map_fd)
struct bpf_map_info map_info = {};
char msg[STRERR_BUFSIZE];
__u32 map_info_len;
+ int err;
map_info_len = sizeof(map_info);
- if (bpf_obj_get_info_by_fd(map_fd, &map_info, &map_info_len)) {
- pr_warn("failed to get map info for map FD %d: %s\n",
- map_fd, libbpf_strerror_r(errno, msg, sizeof(msg)));
+ err = bpf_obj_get_info_by_fd(map_fd, &map_info, &map_info_len);
+ if (err && errno == EINVAL)
+ err = bpf_get_map_info_from_fdinfo(map_fd, &map_info);
+ if (err) {
+ pr_warn("failed to get map info for map FD %d: %s\n", map_fd,
+ libbpf_strerror_r(errno, msg, sizeof(msg)));
return false;
}
@@ -10304,19 +10346,25 @@ static int perf_event_open_probe(bool uprobe, bool retprobe, const char *name,
return pfd;
}
-struct bpf_link *bpf_program__attach_kprobe(struct bpf_program *prog,
- bool retprobe,
- const char *func_name)
+struct bpf_program_attach_kprobe_opts {
+ bool retprobe;
+ unsigned long offset;
+};
+
+static struct bpf_link*
+bpf_program__attach_kprobe_opts(struct bpf_program *prog,
+ const char *func_name,
+ struct bpf_program_attach_kprobe_opts *opts)
{
char errmsg[STRERR_BUFSIZE];
struct bpf_link *link;
int pfd, err;
- pfd = perf_event_open_probe(false /* uprobe */, retprobe, func_name,
- 0 /* offset */, -1 /* pid */);
+ pfd = perf_event_open_probe(false /* uprobe */, opts->retprobe, func_name,
+ opts->offset, -1 /* pid */);
if (pfd < 0) {
pr_warn("prog '%s': failed to create %s '%s' perf event: %s\n",
- prog->name, retprobe ? "kretprobe" : "kprobe", func_name,
+ prog->name, opts->retprobe ? "kretprobe" : "kprobe", func_name,
libbpf_strerror_r(pfd, errmsg, sizeof(errmsg)));
return libbpf_err_ptr(pfd);
}
@@ -10325,23 +10373,53 @@ struct bpf_link *bpf_program__attach_kprobe(struct bpf_program *prog,
if (err) {
close(pfd);
pr_warn("prog '%s': failed to attach to %s '%s': %s\n",
- prog->name, retprobe ? "kretprobe" : "kprobe", func_name,
+ prog->name, opts->retprobe ? "kretprobe" : "kprobe", func_name,
libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
return libbpf_err_ptr(err);
}
return link;
}
+struct bpf_link *bpf_program__attach_kprobe(struct bpf_program *prog,
+ bool retprobe,
+ const char *func_name)
+{
+ struct bpf_program_attach_kprobe_opts opts = {
+ .retprobe = retprobe,
+ };
+
+ return bpf_program__attach_kprobe_opts(prog, func_name, &opts);
+}
+
static struct bpf_link *attach_kprobe(const struct bpf_sec_def *sec,
struct bpf_program *prog)
{
+ struct bpf_program_attach_kprobe_opts opts;
+ unsigned long offset = 0;
+ struct bpf_link *link;
const char *func_name;
- bool retprobe;
+ char *func;
+ int n, err;
func_name = prog->sec_name + sec->len;
- retprobe = strcmp(sec->sec, "kretprobe/") == 0;
+ opts.retprobe = strcmp(sec->sec, "kretprobe/") == 0;
+
+ n = sscanf(func_name, "%m[a-zA-Z0-9_.]+%lx", &func, &offset);
+ if (n < 1) {
+ err = -EINVAL;
+ pr_warn("kprobe name is invalid: %s\n", func_name);
+ return libbpf_err_ptr(err);
+ }
+ if (opts.retprobe && offset != 0) {
+ err = -EINVAL;
+ pr_warn("kretprobes do not support offset specification\n");
+ return libbpf_err_ptr(err);
+ }
- return bpf_program__attach_kprobe(prog, retprobe, func_name);
+ opts.offset = offset;
+ link = bpf_program__attach_kprobe_opts(prog, func, &opts);
+ free(func);
+ return link;
}
struct bpf_link *bpf_program__attach_uprobe(struct bpf_program *prog,
diff --git a/tools/testing/selftests/bpf/prog_tests/get_func_ip_test.c b/tools/testing/selftests/bpf/prog_tests/get_func_ip_test.c
new file mode 100644
index 000000000000..088b3653610d
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/get_func_ip_test.c
@@ -0,0 +1,53 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+#include "get_func_ip_test.skel.h"
+
+void test_get_func_ip_test(void)
+{
+ struct get_func_ip_test *skel = NULL;
+ __u32 duration = 0, retval;
+ int err, prog_fd;
+
+ skel = get_func_ip_test__open();
+ if (!ASSERT_OK_PTR(skel, "get_func_ip_test__open"))
+ return;
+
+ /* test6 is x86_64 specifc because of the instruction
+ * offset, disabling it for all other archs
+ */
+#ifndef __x86_64__
+ bpf_program__set_autoload(skel->progs.test6, false);
+#endif
+
+ err = get_func_ip_test__load(skel);
+ if (!ASSERT_OK(err, "get_func_ip_test__load"))
+ goto cleanup;
+
+ err = get_func_ip_test__attach(skel);
+ if (!ASSERT_OK(err, "get_func_ip_test__attach"))
+ goto cleanup;
+
+ prog_fd = bpf_program__fd(skel->progs.test1);
+ err = bpf_prog_test_run(prog_fd, 1, NULL, 0,
+ NULL, NULL, &retval, &duration);
+ ASSERT_OK(err, "test_run");
+ ASSERT_EQ(retval, 0, "test_run");
+
+ prog_fd = bpf_program__fd(skel->progs.test5);
+ err = bpf_prog_test_run(prog_fd, 1, NULL, 0,
+ NULL, NULL, &retval, &duration);
+
+ ASSERT_OK(err, "test_run");
+
+ ASSERT_EQ(skel->bss->test1_result, 1, "test1_result");
+ ASSERT_EQ(skel->bss->test2_result, 1, "test2_result");
+ ASSERT_EQ(skel->bss->test3_result, 1, "test3_result");
+ ASSERT_EQ(skel->bss->test4_result, 1, "test4_result");
+ ASSERT_EQ(skel->bss->test5_result, 1, "test5_result");
+#ifdef __x86_64__
+ ASSERT_EQ(skel->bss->test6_result, 1, "test6_result");
+#endif
+
+cleanup:
+ get_func_ip_test__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
index 515229f24a93..a9f1bf9d5dff 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
@@ -351,9 +351,11 @@ static void test_insert_opened(int family, int sotype, int mapfd)
errno = 0;
value = s;
err = bpf_map_update_elem(mapfd, &key, &value, BPF_NOEXIST);
- if (!err || errno != EOPNOTSUPP)
- FAIL_ERRNO("map_update: expected EOPNOTSUPP");
-
+ if (sotype == SOCK_STREAM) {
+ if (!err || errno != EOPNOTSUPP)
+ FAIL_ERRNO("map_update: expected EOPNOTSUPP");
+ } else if (err)
+ FAIL_ERRNO("map_update: expected success");
xclose(s);
}
@@ -919,6 +921,23 @@ static const char *redir_mode_str(enum redir_mode mode)
}
}
+static int add_to_sockmap(int sock_mapfd, int fd1, int fd2)
+{
+ u64 value;
+ u32 key;
+ int err;
+
+ key = 0;
+ value = fd1;
+ err = xbpf_map_update_elem(sock_mapfd, &key, &value, BPF_NOEXIST);
+ if (err)
+ return err;
+
+ key = 1;
+ value = fd2;
+ return xbpf_map_update_elem(sock_mapfd, &key, &value, BPF_NOEXIST);
+}
+
static void redir_to_connected(int family, int sotype, int sock_mapfd,
int verd_mapfd, enum redir_mode mode)
{
@@ -928,7 +947,6 @@ static void redir_to_connected(int family, int sotype, int sock_mapfd,
unsigned int pass;
socklen_t len;
int err, n;
- u64 value;
u32 key;
char b;
@@ -965,15 +983,7 @@ static void redir_to_connected(int family, int sotype, int sock_mapfd,
if (p1 < 0)
goto close_cli1;
- key = 0;
- value = p0;
- err = xbpf_map_update_elem(sock_mapfd, &key, &value, BPF_NOEXIST);
- if (err)
- goto close_peer1;
-
- key = 1;
- value = p1;
- err = xbpf_map_update_elem(sock_mapfd, &key, &value, BPF_NOEXIST);
+ err = add_to_sockmap(sock_mapfd, p0, p1);
if (err)
goto close_peer1;
@@ -1061,7 +1071,6 @@ static void redir_to_listening(int family, int sotype, int sock_mapfd,
int s, c, p, err, n;
unsigned int drop;
socklen_t len;
- u64 value;
u32 key;
zero_verdict_count(verd_mapfd);
@@ -1086,15 +1095,7 @@ static void redir_to_listening(int family, int sotype, int sock_mapfd,
if (p < 0)
goto close_cli;
- key = 0;
- value = s;
- err = xbpf_map_update_elem(sock_mapfd, &key, &value, BPF_NOEXIST);
- if (err)
- goto close_peer;
-
- key = 1;
- value = p;
- err = xbpf_map_update_elem(sock_mapfd, &key, &value, BPF_NOEXIST);
+ err = add_to_sockmap(sock_mapfd, s, p);
if (err)
goto close_peer;
@@ -1346,7 +1347,6 @@ static void test_reuseport_mixed_groups(int family, int sotype, int sock_map,
int s1, s2, c, err;
unsigned int drop;
socklen_t len;
- u64 value;
u32 key;
zero_verdict_count(verd_map);
@@ -1360,16 +1360,10 @@ static void test_reuseport_mixed_groups(int family, int sotype, int sock_map,
if (s2 < 0)
goto close_srv1;
- key = 0;
- value = s1;
- err = xbpf_map_update_elem(sock_map, &key, &value, BPF_NOEXIST);
+ err = add_to_sockmap(sock_map, s1, s2);
if (err)
goto close_srv2;
- key = 1;
- value = s2;
- err = xbpf_map_update_elem(sock_map, &key, &value, BPF_NOEXIST);
-
/* Connect to s2, reuseport BPF selects s1 via sock_map[0] */
len = sizeof(addr);
err = xgetsockname(s2, sockaddr(&addr), &len);
@@ -1441,6 +1435,8 @@ static const char *family_str(sa_family_t family)
return "IPv4";
case AF_INET6:
return "IPv6";
+ case AF_UNIX:
+ return "Unix";
default:
return "unknown";
}
@@ -1563,6 +1559,99 @@ static void test_redir(struct test_sockmap_listen *skel, struct bpf_map *map,
}
}
+static void unix_redir_to_connected(int sotype, int sock_mapfd,
+ int verd_mapfd, enum redir_mode mode)
+{
+ const char *log_prefix = redir_mode_str(mode);
+ int c0, c1, p0, p1;
+ unsigned int pass;
+ int retries = 100;
+ int err, n;
+ int sfd[2];
+ u32 key;
+ char b;
+
+ zero_verdict_count(verd_mapfd);
+
+ if (socketpair(AF_UNIX, sotype | SOCK_NONBLOCK, 0, sfd))
+ return;
+ c0 = sfd[0], p0 = sfd[1];
+
+ if (socketpair(AF_UNIX, sotype | SOCK_NONBLOCK, 0, sfd))
+ goto close0;
+ c1 = sfd[0], p1 = sfd[1];
+
+ err = add_to_sockmap(sock_mapfd, p0, p1);
+ if (err)
+ goto close;
+
+ n = write(c1, "a", 1);
+ if (n < 0)
+ FAIL_ERRNO("%s: write", log_prefix);
+ if (n == 0)
+ FAIL("%s: incomplete write", log_prefix);
+ if (n < 1)
+ goto close;
+
+ key = SK_PASS;
+ err = xbpf_map_lookup_elem(verd_mapfd, &key, &pass);
+ if (err)
+ goto close;
+ if (pass != 1)
+ FAIL("%s: want pass count 1, have %d", log_prefix, pass);
+
+again:
+ n = read(mode == REDIR_INGRESS ? p0 : c0, &b, 1);
+ if (n < 0) {
+ if (errno == EAGAIN && retries--)
+ goto again;
+ FAIL_ERRNO("%s: read", log_prefix);
+ }
+ if (n == 0)
+ FAIL("%s: incomplete read", log_prefix);
+
+close:
+ xclose(c1);
+ xclose(p1);
+close0:
+ xclose(c0);
+ xclose(p0);
+}
+
+static void unix_skb_redir_to_connected(struct test_sockmap_listen *skel,
+ struct bpf_map *inner_map, int sotype)
+{
+ int verdict = bpf_program__fd(skel->progs.prog_skb_verdict);
+ int verdict_map = bpf_map__fd(skel->maps.verdict_map);
+ int sock_map = bpf_map__fd(inner_map);
+ int err;
+
+ err = xbpf_prog_attach(verdict, sock_map, BPF_SK_SKB_VERDICT, 0);
+ if (err)
+ return;
+
+ skel->bss->test_ingress = false;
+ unix_redir_to_connected(sotype, sock_map, verdict_map, REDIR_EGRESS);
+ skel->bss->test_ingress = true;
+ unix_redir_to_connected(sotype, sock_map, verdict_map, REDIR_INGRESS);
+
+ xbpf_prog_detach2(verdict, sock_map, BPF_SK_SKB_VERDICT);
+}
+
+static void test_unix_redir(struct test_sockmap_listen *skel, struct bpf_map *map,
+ int sotype)
+{
+ const char *family_name, *map_name;
+ char s[MAX_TEST_NAME];
+
+ family_name = family_str(AF_UNIX);
+ map_name = map_type_str(map);
+ snprintf(s, sizeof(s), "%s %s %s", map_name, family_name, __func__);
+ if (!test__start_subtest(s))
+ return;
+ unix_skb_redir_to_connected(skel, map, sotype);
+}
+
static void test_reuseport(struct test_sockmap_listen *skel,
struct bpf_map *map, int family, int sotype)
{
@@ -1603,33 +1692,27 @@ static void test_reuseport(struct test_sockmap_listen *skel,
}
}
-static void udp_redir_to_connected(int family, int sotype, int sock_mapfd,
- int verd_mapfd, enum redir_mode mode)
+static int udp_socketpair(int family, int *s, int *c)
{
- const char *log_prefix = redir_mode_str(mode);
struct sockaddr_storage addr;
- int c0, c1, p0, p1;
- unsigned int pass;
- int retries = 100;
socklen_t len;
- int err, n;
- u64 value;
- u32 key;
- char b;
-
- zero_verdict_count(verd_mapfd);
+ int p0, c0;
+ int err;
- p0 = socket_loopback(family, sotype | SOCK_NONBLOCK);
+ p0 = socket_loopback(family, SOCK_DGRAM | SOCK_NONBLOCK);
if (p0 < 0)
- return;
+ return p0;
+
len = sizeof(addr);
err = xgetsockname(p0, sockaddr(&addr), &len);
if (err)
goto close_peer0;
- c0 = xsocket(family, sotype | SOCK_NONBLOCK, 0);
- if (c0 < 0)
+ c0 = xsocket(family, SOCK_DGRAM | SOCK_NONBLOCK, 0);
+ if (c0 < 0) {
+ err = c0;
goto close_peer0;
+ }
err = xconnect(c0, sockaddr(&addr), len);
if (err)
goto close_cli0;
@@ -1640,35 +1723,131 @@ static void udp_redir_to_connected(int family, int sotype, int sock_mapfd,
if (err)
goto close_cli0;
- p1 = socket_loopback(family, sotype | SOCK_NONBLOCK);
- if (p1 < 0)
- goto close_cli0;
- err = xgetsockname(p1, sockaddr(&addr), &len);
+ *s = p0;
+ *c = c0;
+ return 0;
+
+close_cli0:
+ xclose(c0);
+close_peer0:
+ xclose(p0);
+ return err;
+}
+
+static void udp_redir_to_connected(int family, int sock_mapfd, int verd_mapfd,
+ enum redir_mode mode)
+{
+ const char *log_prefix = redir_mode_str(mode);
+ int c0, c1, p0, p1;
+ unsigned int pass;
+ int retries = 100;
+ int err, n;
+ u32 key;
+ char b;
+
+ zero_verdict_count(verd_mapfd);
+
+ err = udp_socketpair(family, &p0, &c0);
+ if (err)
+ return;
+ err = udp_socketpair(family, &p1, &c1);
if (err)
goto close_cli0;
- c1 = xsocket(family, sotype | SOCK_NONBLOCK, 0);
- if (c1 < 0)
- goto close_peer1;
- err = xconnect(c1, sockaddr(&addr), len);
+ err = add_to_sockmap(sock_mapfd, p0, p1);
if (err)
goto close_cli1;
- err = xgetsockname(c1, sockaddr(&addr), &len);
- if (err)
+
+ n = write(c1, "a", 1);
+ if (n < 0)
+ FAIL_ERRNO("%s: write", log_prefix);
+ if (n == 0)
+ FAIL("%s: incomplete write", log_prefix);
+ if (n < 1)
goto close_cli1;
- err = xconnect(p1, sockaddr(&addr), len);
+
+ key = SK_PASS;
+ err = xbpf_map_lookup_elem(verd_mapfd, &key, &pass);
if (err)
goto close_cli1;
+ if (pass != 1)
+ FAIL("%s: want pass count 1, have %d", log_prefix, pass);
- key = 0;
- value = p0;
- err = xbpf_map_update_elem(sock_mapfd, &key, &value, BPF_NOEXIST);
+again:
+ n = read(mode == REDIR_INGRESS ? p0 : c0, &b, 1);
+ if (n < 0) {
+ if (errno == EAGAIN && retries--)
+ goto again;
+ FAIL_ERRNO("%s: read", log_prefix);
+ }
+ if (n == 0)
+ FAIL("%s: incomplete read", log_prefix);
+
+close_cli1:
+ xclose(c1);
+ xclose(p1);
+close_cli0:
+ xclose(c0);
+ xclose(p0);
+}
+
+static void udp_skb_redir_to_connected(struct test_sockmap_listen *skel,
+ struct bpf_map *inner_map, int family)
+{
+ int verdict = bpf_program__fd(skel->progs.prog_skb_verdict);
+ int verdict_map = bpf_map__fd(skel->maps.verdict_map);
+ int sock_map = bpf_map__fd(inner_map);
+ int err;
+
+ err = xbpf_prog_attach(verdict, sock_map, BPF_SK_SKB_VERDICT, 0);
if (err)
- goto close_cli1;
+ return;
- key = 1;
- value = p1;
- err = xbpf_map_update_elem(sock_mapfd, &key, &value, BPF_NOEXIST);
+ skel->bss->test_ingress = false;
+ udp_redir_to_connected(family, sock_map, verdict_map, REDIR_EGRESS);
+ skel->bss->test_ingress = true;
+ udp_redir_to_connected(family, sock_map, verdict_map, REDIR_INGRESS);
+
+ xbpf_prog_detach2(verdict, sock_map, BPF_SK_SKB_VERDICT);
+}
+
+static void test_udp_redir(struct test_sockmap_listen *skel, struct bpf_map *map,
+ int family)
+{
+ const char *family_name, *map_name;
+ char s[MAX_TEST_NAME];
+
+ family_name = family_str(family);
+ map_name = map_type_str(map);
+ snprintf(s, sizeof(s), "%s %s %s", map_name, family_name, __func__);
+ if (!test__start_subtest(s))
+ return;
+ udp_skb_redir_to_connected(skel, map, family);
+}
+
+static void udp_unix_redir_to_connected(int family, int sock_mapfd,
+ int verd_mapfd, enum redir_mode mode)
+{
+ const char *log_prefix = redir_mode_str(mode);
+ int c0, c1, p0, p1;
+ unsigned int pass;
+ int retries = 100;
+ int err, n;
+ int sfd[2];
+ u32 key;
+ char b;
+
+ zero_verdict_count(verd_mapfd);
+
+ if (socketpair(AF_UNIX, SOCK_DGRAM | SOCK_NONBLOCK, 0, sfd))
+ return;
+ c0 = sfd[0], p0 = sfd[1];
+
+ err = udp_socketpair(family, &p1, &c1);
+ if (err)
+ goto close;
+
+ err = add_to_sockmap(sock_mapfd, p0, p1);
if (err)
goto close_cli1;
@@ -1699,16 +1878,89 @@ again:
close_cli1:
xclose(c1);
-close_peer1:
+ xclose(p1);
+close:
+ xclose(c0);
+ xclose(p0);
+}
+
+static void udp_unix_skb_redir_to_connected(struct test_sockmap_listen *skel,
+ struct bpf_map *inner_map, int family)
+{
+ int verdict = bpf_program__fd(skel->progs.prog_skb_verdict);
+ int verdict_map = bpf_map__fd(skel->maps.verdict_map);
+ int sock_map = bpf_map__fd(inner_map);
+ int err;
+
+ err = xbpf_prog_attach(verdict, sock_map, BPF_SK_SKB_VERDICT, 0);
+ if (err)
+ return;
+
+ skel->bss->test_ingress = false;
+ udp_unix_redir_to_connected(family, sock_map, verdict_map, REDIR_EGRESS);
+ skel->bss->test_ingress = true;
+ udp_unix_redir_to_connected(family, sock_map, verdict_map, REDIR_INGRESS);
+
+ xbpf_prog_detach2(verdict, sock_map, BPF_SK_SKB_VERDICT);
+}
+
+static void unix_udp_redir_to_connected(int family, int sock_mapfd,
+ int verd_mapfd, enum redir_mode mode)
+{
+ const char *log_prefix = redir_mode_str(mode);
+ int c0, c1, p0, p1;
+ unsigned int pass;
+ int err, n;
+ int sfd[2];
+ u32 key;
+ char b;
+
+ zero_verdict_count(verd_mapfd);
+
+ err = udp_socketpair(family, &p0, &c0);
+ if (err)
+ return;
+
+ if (socketpair(AF_UNIX, SOCK_DGRAM | SOCK_NONBLOCK, 0, sfd))
+ goto close_cli0;
+ c1 = sfd[0], p1 = sfd[1];
+
+ err = add_to_sockmap(sock_mapfd, p0, p1);
+ if (err)
+ goto close;
+
+ n = write(c1, "a", 1);
+ if (n < 0)
+ FAIL_ERRNO("%s: write", log_prefix);
+ if (n == 0)
+ FAIL("%s: incomplete write", log_prefix);
+ if (n < 1)
+ goto close;
+
+ key = SK_PASS;
+ err = xbpf_map_lookup_elem(verd_mapfd, &key, &pass);
+ if (err)
+ goto close;
+ if (pass != 1)
+ FAIL("%s: want pass count 1, have %d", log_prefix, pass);
+
+ n = read(mode == REDIR_INGRESS ? p0 : c0, &b, 1);
+ if (n < 0)
+ FAIL_ERRNO("%s: read", log_prefix);
+ if (n == 0)
+ FAIL("%s: incomplete read", log_prefix);
+
+close:
+ xclose(c1);
xclose(p1);
close_cli0:
xclose(c0);
-close_peer0:
xclose(p0);
+
}
-static void udp_skb_redir_to_connected(struct test_sockmap_listen *skel,
- struct bpf_map *inner_map, int family)
+static void unix_udp_skb_redir_to_connected(struct test_sockmap_listen *skel,
+ struct bpf_map *inner_map, int family)
{
int verdict = bpf_program__fd(skel->progs.prog_skb_verdict);
int verdict_map = bpf_map__fd(skel->maps.verdict_map);
@@ -1720,17 +1972,15 @@ static void udp_skb_redir_to_connected(struct test_sockmap_listen *skel,
return;
skel->bss->test_ingress = false;
- udp_redir_to_connected(family, SOCK_DGRAM, sock_map, verdict_map,
- REDIR_EGRESS);
+ unix_udp_redir_to_connected(family, sock_map, verdict_map, REDIR_EGRESS);
skel->bss->test_ingress = true;
- udp_redir_to_connected(family, SOCK_DGRAM, sock_map, verdict_map,
- REDIR_INGRESS);
+ unix_udp_redir_to_connected(family, sock_map, verdict_map, REDIR_INGRESS);
xbpf_prog_detach2(verdict, sock_map, BPF_SK_SKB_VERDICT);
}
-static void test_udp_redir(struct test_sockmap_listen *skel, struct bpf_map *map,
- int family)
+static void test_udp_unix_redir(struct test_sockmap_listen *skel, struct bpf_map *map,
+ int family)
{
const char *family_name, *map_name;
char s[MAX_TEST_NAME];
@@ -1740,7 +1990,8 @@ static void test_udp_redir(struct test_sockmap_listen *skel, struct bpf_map *map
snprintf(s, sizeof(s), "%s %s %s", map_name, family_name, __func__);
if (!test__start_subtest(s))
return;
- udp_skb_redir_to_connected(skel, map, family);
+ udp_unix_skb_redir_to_connected(skel, map, family);
+ unix_udp_skb_redir_to_connected(skel, map, family);
}
static void run_tests(struct test_sockmap_listen *skel, struct bpf_map *map,
@@ -1752,6 +2003,7 @@ static void run_tests(struct test_sockmap_listen *skel, struct bpf_map *map,
test_reuseport(skel, map, family, SOCK_STREAM);
test_reuseport(skel, map, family, SOCK_DGRAM);
test_udp_redir(skel, map, family);
+ test_udp_unix_redir(skel, map, family);
}
void test_sockmap_listen(void)
@@ -1767,10 +2019,12 @@ void test_sockmap_listen(void)
skel->bss->test_sockmap = true;
run_tests(skel, skel->maps.sock_map, AF_INET);
run_tests(skel, skel->maps.sock_map, AF_INET6);
+ test_unix_redir(skel, skel->maps.sock_map, SOCK_DGRAM);
skel->bss->test_sockmap = false;
run_tests(skel, skel->maps.sock_hash, AF_INET);
run_tests(skel, skel->maps.sock_hash, AF_INET6);
+ test_unix_redir(skel, skel->maps.sock_hash, SOCK_DGRAM);
test_sockmap_listen__destroy(skel);
}
diff --git a/tools/testing/selftests/bpf/prog_tests/timer.c b/tools/testing/selftests/bpf/prog_tests/timer.c
new file mode 100644
index 000000000000..25f40e1b9967
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/timer.c
@@ -0,0 +1,55 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+#include <test_progs.h>
+#include "timer.skel.h"
+
+static int timer(struct timer *timer_skel)
+{
+ int err, prog_fd;
+ __u32 duration = 0, retval;
+
+ err = timer__attach(timer_skel);
+ if (!ASSERT_OK(err, "timer_attach"))
+ return err;
+
+ ASSERT_EQ(timer_skel->data->callback_check, 52, "callback_check1");
+ ASSERT_EQ(timer_skel->data->callback2_check, 52, "callback2_check1");
+
+ prog_fd = bpf_program__fd(timer_skel->progs.test1);
+ err = bpf_prog_test_run(prog_fd, 1, NULL, 0,
+ NULL, NULL, &retval, &duration);
+ ASSERT_OK(err, "test_run");
+ ASSERT_EQ(retval, 0, "test_run");
+ timer__detach(timer_skel);
+
+ usleep(50); /* 10 usecs should be enough, but give it extra */
+ /* check that timer_cb1() was executed 10+10 times */
+ ASSERT_EQ(timer_skel->data->callback_check, 42, "callback_check2");
+ ASSERT_EQ(timer_skel->data->callback2_check, 42, "callback2_check2");
+
+ /* check that timer_cb2() was executed twice */
+ ASSERT_EQ(timer_skel->bss->bss_data, 10, "bss_data");
+
+ /* check that there were no errors in timer execution */
+ ASSERT_EQ(timer_skel->bss->err, 0, "err");
+
+ /* check that code paths completed */
+ ASSERT_EQ(timer_skel->bss->ok, 1 | 2 | 4, "ok");
+
+ return 0;
+}
+
+void test_timer(void)
+{
+ struct timer *timer_skel = NULL;
+ int err;
+
+ timer_skel = timer__open_and_load();
+ if (!ASSERT_OK_PTR(timer_skel, "timer_skel_load"))
+ goto cleanup;
+
+ err = timer(timer_skel);
+ ASSERT_OK(err, "timer");
+cleanup:
+ timer__destroy(timer_skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/timer_mim.c b/tools/testing/selftests/bpf/prog_tests/timer_mim.c
new file mode 100644
index 000000000000..f5acbcbe33a4
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/timer_mim.c
@@ -0,0 +1,69 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+#include <test_progs.h>
+#include "timer_mim.skel.h"
+#include "timer_mim_reject.skel.h"
+
+static int timer_mim(struct timer_mim *timer_skel)
+{
+ __u32 duration = 0, retval;
+ __u64 cnt1, cnt2;
+ int err, prog_fd, key1 = 1;
+
+ err = timer_mim__attach(timer_skel);
+ if (!ASSERT_OK(err, "timer_attach"))
+ return err;
+
+ prog_fd = bpf_program__fd(timer_skel->progs.test1);
+ err = bpf_prog_test_run(prog_fd, 1, NULL, 0,
+ NULL, NULL, &retval, &duration);
+ ASSERT_OK(err, "test_run");
+ ASSERT_EQ(retval, 0, "test_run");
+ timer_mim__detach(timer_skel);
+
+ /* check that timer_cb[12] are incrementing 'cnt' */
+ cnt1 = READ_ONCE(timer_skel->bss->cnt);
+ usleep(200); /* 100 times more than interval */
+ cnt2 = READ_ONCE(timer_skel->bss->cnt);
+ ASSERT_GT(cnt2, cnt1, "cnt");
+
+ ASSERT_EQ(timer_skel->bss->err, 0, "err");
+ /* check that code paths completed */
+ ASSERT_EQ(timer_skel->bss->ok, 1 | 2, "ok");
+
+ close(bpf_map__fd(timer_skel->maps.inner_htab));
+ err = bpf_map_delete_elem(bpf_map__fd(timer_skel->maps.outer_arr), &key1);
+ ASSERT_EQ(err, 0, "delete inner map");
+
+ /* check that timer_cb[12] are no longer running */
+ cnt1 = READ_ONCE(timer_skel->bss->cnt);
+ usleep(200);
+ cnt2 = READ_ONCE(timer_skel->bss->cnt);
+ ASSERT_EQ(cnt2, cnt1, "cnt");
+
+ return 0;
+}
+
+void test_timer_mim(void)
+{
+ struct timer_mim_reject *timer_reject_skel = NULL;
+ libbpf_print_fn_t old_print_fn = NULL;
+ struct timer_mim *timer_skel = NULL;
+ int err;
+
+ old_print_fn = libbpf_set_print(NULL);
+ timer_reject_skel = timer_mim_reject__open_and_load();
+ libbpf_set_print(old_print_fn);
+ if (!ASSERT_ERR_PTR(timer_reject_skel, "timer_reject_skel_load"))
+ goto cleanup;
+
+ timer_skel = timer_mim__open_and_load();
+ if (!ASSERT_OK_PTR(timer_skel, "timer_skel_load"))
+ goto cleanup;
+
+ err = timer_mim(timer_skel);
+ ASSERT_OK(err, "timer_mim");
+cleanup:
+ timer_mim__destroy(timer_skel);
+ timer_mim_reject__destroy(timer_reject_skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c b/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c
new file mode 100644
index 000000000000..ab4952b9fb1d
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c
@@ -0,0 +1,105 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+#include <network_helpers.h>
+#include "test_xdp_context_test_run.skel.h"
+
+void test_xdp_context_error(int prog_fd, struct bpf_test_run_opts opts,
+ __u32 data_meta, __u32 data, __u32 data_end,
+ __u32 ingress_ifindex, __u32 rx_queue_index,
+ __u32 egress_ifindex)
+{
+ struct xdp_md ctx = {
+ .data = data,
+ .data_end = data_end,
+ .data_meta = data_meta,
+ .ingress_ifindex = ingress_ifindex,
+ .rx_queue_index = rx_queue_index,
+ .egress_ifindex = egress_ifindex,
+ };
+ int err;
+
+ opts.ctx_in = &ctx;
+ opts.ctx_size_in = sizeof(ctx);
+ err = bpf_prog_test_run_opts(prog_fd, &opts);
+ ASSERT_EQ(errno, EINVAL, "errno-EINVAL");
+ ASSERT_ERR(err, "bpf_prog_test_run");
+}
+
+void test_xdp_context_test_run(void)
+{
+ struct test_xdp_context_test_run *skel = NULL;
+ char data[sizeof(pkt_v4) + sizeof(__u32)];
+ char bad_ctx[sizeof(struct xdp_md) + 1];
+ struct xdp_md ctx_in, ctx_out;
+ DECLARE_LIBBPF_OPTS(bpf_test_run_opts, opts,
+ .data_in = &data,
+ .data_size_in = sizeof(data),
+ .ctx_out = &ctx_out,
+ .ctx_size_out = sizeof(ctx_out),
+ .repeat = 1,
+ );
+ int err, prog_fd;
+
+ skel = test_xdp_context_test_run__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "skel"))
+ return;
+ prog_fd = bpf_program__fd(skel->progs.xdp_context);
+
+ /* Data past the end of the kernel's struct xdp_md must be 0 */
+ bad_ctx[sizeof(bad_ctx) - 1] = 1;
+ opts.ctx_in = bad_ctx;
+ opts.ctx_size_in = sizeof(bad_ctx);
+ err = bpf_prog_test_run_opts(prog_fd, &opts);
+ ASSERT_EQ(errno, E2BIG, "extradata-errno");
+ ASSERT_ERR(err, "bpf_prog_test_run(extradata)");
+
+ *(__u32 *)data = XDP_PASS;
+ *(struct ipv4_packet *)(data + sizeof(__u32)) = pkt_v4;
+ opts.ctx_in = &ctx_in;
+ opts.ctx_size_in = sizeof(ctx_in);
+ memset(&ctx_in, 0, sizeof(ctx_in));
+ ctx_in.data_meta = 0;
+ ctx_in.data = sizeof(__u32);
+ ctx_in.data_end = ctx_in.data + sizeof(pkt_v4);
+ err = bpf_prog_test_run_opts(prog_fd, &opts);
+ ASSERT_OK(err, "bpf_prog_test_run(valid)");
+ ASSERT_EQ(opts.retval, XDP_PASS, "valid-retval");
+ ASSERT_EQ(opts.data_size_out, sizeof(pkt_v4), "valid-datasize");
+ ASSERT_EQ(opts.ctx_size_out, opts.ctx_size_in, "valid-ctxsize");
+ ASSERT_EQ(ctx_out.data_meta, 0, "valid-datameta");
+ ASSERT_EQ(ctx_out.data, 0, "valid-data");
+ ASSERT_EQ(ctx_out.data_end, sizeof(pkt_v4), "valid-dataend");
+
+ /* Meta data's size must be a multiple of 4 */
+ test_xdp_context_error(prog_fd, opts, 0, 1, sizeof(data), 0, 0, 0);
+
+ /* data_meta must reference the start of data */
+ test_xdp_context_error(prog_fd, opts, 4, sizeof(__u32), sizeof(data),
+ 0, 0, 0);
+
+ /* Meta data must be 32 bytes or smaller */
+ test_xdp_context_error(prog_fd, opts, 0, 36, sizeof(data), 0, 0, 0);
+
+ /* Total size of data must match data_end - data_meta */
+ test_xdp_context_error(prog_fd, opts, 0, sizeof(__u32),
+ sizeof(data) - 1, 0, 0, 0);
+ test_xdp_context_error(prog_fd, opts, 0, sizeof(__u32),
+ sizeof(data) + 1, 0, 0, 0);
+
+ /* RX queue cannot be specified without specifying an ingress */
+ test_xdp_context_error(prog_fd, opts, 0, sizeof(__u32), sizeof(data),
+ 0, 1, 0);
+
+ /* Interface 1 is always the loopback interface which always has only
+ * one RX queue (index 0). This makes index 1 an invalid rx queue index
+ * for interface 1.
+ */
+ test_xdp_context_error(prog_fd, opts, 0, sizeof(__u32), sizeof(data),
+ 1, 1, 0);
+
+ /* The egress cannot be specified */
+ test_xdp_context_error(prog_fd, opts, 0, sizeof(__u32), sizeof(data),
+ 0, 0, 1);
+
+ test_xdp_context_test_run__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c b/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c
index 0176573fe4e7..8755effd80b0 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c
@@ -7,64 +7,53 @@
#define IFINDEX_LO 1
-void test_xdp_with_cpumap_helpers(void)
+void test_xdp_cpumap_attach(void)
{
struct test_xdp_with_cpumap_helpers *skel;
struct bpf_prog_info info = {};
+ __u32 len = sizeof(info);
struct bpf_cpumap_val val = {
.qsize = 192,
};
- __u32 duration = 0, idx = 0;
- __u32 len = sizeof(info);
int err, prog_fd, map_fd;
+ __u32 idx = 0;
skel = test_xdp_with_cpumap_helpers__open_and_load();
- if (CHECK_FAIL(!skel)) {
- perror("test_xdp_with_cpumap_helpers__open_and_load");
+ if (!ASSERT_OK_PTR(skel, "test_xdp_with_cpumap_helpers__open_and_load"))
return;
- }
- /* can not attach program with cpumaps that allow programs
- * as xdp generic
- */
prog_fd = bpf_program__fd(skel->progs.xdp_redir_prog);
err = bpf_set_link_xdp_fd(IFINDEX_LO, prog_fd, XDP_FLAGS_SKB_MODE);
- CHECK(err == 0, "Generic attach of program with 8-byte CPUMAP",
- "should have failed\n");
+ if (!ASSERT_OK(err, "Generic attach of program with 8-byte CPUMAP"))
+ goto out_close;
+
+ err = bpf_set_link_xdp_fd(IFINDEX_LO, -1, XDP_FLAGS_SKB_MODE);
+ ASSERT_OK(err, "XDP program detach");
prog_fd = bpf_program__fd(skel->progs.xdp_dummy_cm);
map_fd = bpf_map__fd(skel->maps.cpu_map);
err = bpf_obj_get_info_by_fd(prog_fd, &info, &len);
- if (CHECK_FAIL(err))
+ if (!ASSERT_OK(err, "bpf_obj_get_info_by_fd"))
goto out_close;
val.bpf_prog.fd = prog_fd;
err = bpf_map_update_elem(map_fd, &idx, &val, 0);
- CHECK(err, "Add program to cpumap entry", "err %d errno %d\n",
- err, errno);
+ ASSERT_OK(err, "Add program to cpumap entry");
err = bpf_map_lookup_elem(map_fd, &idx, &val);
- CHECK(err, "Read cpumap entry", "err %d errno %d\n", err, errno);
- CHECK(info.id != val.bpf_prog.id, "Expected program id in cpumap entry",
- "expected %u read %u\n", info.id, val.bpf_prog.id);
+ ASSERT_OK(err, "Read cpumap entry");
+ ASSERT_EQ(info.id, val.bpf_prog.id, "Match program id to cpumap entry prog_id");
/* can not attach BPF_XDP_CPUMAP program to a device */
err = bpf_set_link_xdp_fd(IFINDEX_LO, prog_fd, XDP_FLAGS_SKB_MODE);
- CHECK(err == 0, "Attach of BPF_XDP_CPUMAP program",
- "should have failed\n");
+ if (!ASSERT_NEQ(err, 0, "Attach of BPF_XDP_CPUMAP program"))
+ bpf_set_link_xdp_fd(IFINDEX_LO, -1, XDP_FLAGS_SKB_MODE);
val.qsize = 192;
val.bpf_prog.fd = bpf_program__fd(skel->progs.xdp_dummy_prog);
err = bpf_map_update_elem(map_fd, &idx, &val, 0);
- CHECK(err == 0, "Add non-BPF_XDP_CPUMAP program to cpumap entry",
- "should have failed\n");
+ ASSERT_NEQ(err, 0, "Add non-BPF_XDP_CPUMAP program to cpumap entry");
out_close:
test_xdp_with_cpumap_helpers__destroy(skel);
}
-
-void test_xdp_cpumap_attach(void)
-{
- if (test__start_subtest("cpumap_with_progs"))
- test_xdp_with_cpumap_helpers();
-}
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c b/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c
index 88ef3ec8ac4c..c72af030ff10 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c
@@ -16,50 +16,45 @@ void test_xdp_with_devmap_helpers(void)
.ifindex = IFINDEX_LO,
};
__u32 len = sizeof(info);
- __u32 duration = 0, idx = 0;
int err, dm_fd, map_fd;
+ __u32 idx = 0;
skel = test_xdp_with_devmap_helpers__open_and_load();
- if (CHECK_FAIL(!skel)) {
- perror("test_xdp_with_devmap_helpers__open_and_load");
+ if (!ASSERT_OK_PTR(skel, "test_xdp_with_devmap_helpers__open_and_load"))
return;
- }
- /* can not attach program with DEVMAPs that allow programs
- * as xdp generic
- */
dm_fd = bpf_program__fd(skel->progs.xdp_redir_prog);
err = bpf_set_link_xdp_fd(IFINDEX_LO, dm_fd, XDP_FLAGS_SKB_MODE);
- CHECK(err == 0, "Generic attach of program with 8-byte devmap",
- "should have failed\n");
+ if (!ASSERT_OK(err, "Generic attach of program with 8-byte devmap"))
+ goto out_close;
+
+ err = bpf_set_link_xdp_fd(IFINDEX_LO, -1, XDP_FLAGS_SKB_MODE);
+ ASSERT_OK(err, "XDP program detach");
dm_fd = bpf_program__fd(skel->progs.xdp_dummy_dm);
map_fd = bpf_map__fd(skel->maps.dm_ports);
err = bpf_obj_get_info_by_fd(dm_fd, &info, &len);
- if (CHECK_FAIL(err))
+ if (!ASSERT_OK(err, "bpf_obj_get_info_by_fd"))
goto out_close;
val.bpf_prog.fd = dm_fd;
err = bpf_map_update_elem(map_fd, &idx, &val, 0);
- CHECK(err, "Add program to devmap entry",
- "err %d errno %d\n", err, errno);
+ ASSERT_OK(err, "Add program to devmap entry");
err = bpf_map_lookup_elem(map_fd, &idx, &val);
- CHECK(err, "Read devmap entry", "err %d errno %d\n", err, errno);
- CHECK(info.id != val.bpf_prog.id, "Expected program id in devmap entry",
- "expected %u read %u\n", info.id, val.bpf_prog.id);
+ ASSERT_OK(err, "Read devmap entry");
+ ASSERT_EQ(info.id, val.bpf_prog.id, "Match program id to devmap entry prog_id");
/* can not attach BPF_XDP_DEVMAP program to a device */
err = bpf_set_link_xdp_fd(IFINDEX_LO, dm_fd, XDP_FLAGS_SKB_MODE);
- CHECK(err == 0, "Attach of BPF_XDP_DEVMAP program",
- "should have failed\n");
+ if (!ASSERT_NEQ(err, 0, "Attach of BPF_XDP_DEVMAP program"))
+ bpf_set_link_xdp_fd(IFINDEX_LO, -1, XDP_FLAGS_SKB_MODE);
val.ifindex = 1;
val.bpf_prog.fd = bpf_program__fd(skel->progs.xdp_dummy_prog);
err = bpf_map_update_elem(map_fd, &idx, &val, 0);
- CHECK(err == 0, "Add non-BPF_XDP_DEVMAP program to devmap entry",
- "should have failed\n");
+ ASSERT_NEQ(err, 0, "Add non-BPF_XDP_DEVMAP program to devmap entry");
out_close:
test_xdp_with_devmap_helpers__destroy(skel);
@@ -68,12 +63,10 @@ out_close:
void test_neg_xdp_devmap_helpers(void)
{
struct test_xdp_devmap_helpers *skel;
- __u32 duration = 0;
skel = test_xdp_devmap_helpers__open_and_load();
- if (CHECK(skel,
- "Load of XDP program accessing egress ifindex without attach type",
- "should have failed\n")) {
+ if (!ASSERT_EQ(skel, NULL,
+ "Load of XDP program accessing egress ifindex without attach type")) {
test_xdp_devmap_helpers__destroy(skel);
}
}
diff --git a/tools/testing/selftests/bpf/progs/get_func_ip_test.c b/tools/testing/selftests/bpf/progs/get_func_ip_test.c
new file mode 100644
index 000000000000..acd587b6e859
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/get_func_ip_test.c
@@ -0,0 +1,73 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+extern const void bpf_fentry_test1 __ksym;
+extern const void bpf_fentry_test2 __ksym;
+extern const void bpf_fentry_test3 __ksym;
+extern const void bpf_fentry_test4 __ksym;
+extern const void bpf_modify_return_test __ksym;
+extern const void bpf_fentry_test6 __ksym;
+
+__u64 test1_result = 0;
+SEC("fentry/bpf_fentry_test1")
+int BPF_PROG(test1, int a)
+{
+ __u64 addr = bpf_get_func_ip(ctx);
+
+ test1_result = (const void *) addr == &bpf_fentry_test1;
+ return 0;
+}
+
+__u64 test2_result = 0;
+SEC("fexit/bpf_fentry_test2")
+int BPF_PROG(test2, int a)
+{
+ __u64 addr = bpf_get_func_ip(ctx);
+
+ test2_result = (const void *) addr == &bpf_fentry_test2;
+ return 0;
+}
+
+__u64 test3_result = 0;
+SEC("kprobe/bpf_fentry_test3")
+int test3(struct pt_regs *ctx)
+{
+ __u64 addr = bpf_get_func_ip(ctx);
+
+ test3_result = (const void *) addr == &bpf_fentry_test3;
+ return 0;
+}
+
+__u64 test4_result = 0;
+SEC("kretprobe/bpf_fentry_test4")
+int BPF_KRETPROBE(test4)
+{
+ __u64 addr = bpf_get_func_ip(ctx);
+
+ test4_result = (const void *) addr == &bpf_fentry_test4;
+ return 0;
+}
+
+__u64 test5_result = 0;
+SEC("fmod_ret/bpf_modify_return_test")
+int BPF_PROG(test5, int a, int *b, int ret)
+{
+ __u64 addr = bpf_get_func_ip(ctx);
+
+ test5_result = (const void *) addr == &bpf_modify_return_test;
+ return ret;
+}
+
+__u64 test6_result = 0;
+SEC("kprobe/bpf_fentry_test6+0x5")
+int test6(struct pt_regs *ctx)
+{
+ __u64 addr = bpf_get_func_ip(ctx);
+
+ test6_result = (const void *) addr == &bpf_fentry_test6 + 5;
+ return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/test_tc_tunnel.c b/tools/testing/selftests/bpf/progs/test_tc_tunnel.c
index 84cd63259554..a0e7762b1e5a 100644
--- a/tools/testing/selftests/bpf/progs/test_tc_tunnel.c
+++ b/tools/testing/selftests/bpf/progs/test_tc_tunnel.c
@@ -528,7 +528,6 @@ int __encap_ip6vxlan_eth(struct __sk_buff *skb)
static int decap_internal(struct __sk_buff *skb, int off, int len, char proto)
{
- char buf[sizeof(struct v6hdr)];
struct gre_hdr greh;
struct udphdr udph;
int olen = len;
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_context_test_run.c b/tools/testing/selftests/bpf/progs/test_xdp_context_test_run.c
new file mode 100644
index 000000000000..d7b88cd05afd
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_xdp_context_test_run.c
@@ -0,0 +1,20 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+SEC("xdp")
+int xdp_context(struct xdp_md *xdp)
+{
+ void *data = (void *)(long)xdp->data;
+ __u32 *metadata = (void *)(long)xdp->data_meta;
+ __u32 ret;
+
+ if (metadata + 1 > data)
+ return XDP_ABORTED;
+ ret = *metadata;
+ if (bpf_xdp_adjust_meta(xdp, 4))
+ return XDP_ABORTED;
+ return ret;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/timer.c b/tools/testing/selftests/bpf/progs/timer.c
new file mode 100644
index 000000000000..5f5309791649
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/timer.c
@@ -0,0 +1,297 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+#include <linux/bpf.h>
+#include <time.h>
+#include <errno.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_tcp_helpers.h"
+
+char _license[] SEC("license") = "GPL";
+struct hmap_elem {
+ int counter;
+ struct bpf_timer timer;
+ struct bpf_spin_lock lock; /* unused */
+};
+
+struct {
+ __uint(type, BPF_MAP_TYPE_HASH);
+ __uint(max_entries, 1000);
+ __type(key, int);
+ __type(value, struct hmap_elem);
+} hmap SEC(".maps");
+
+struct {
+ __uint(type, BPF_MAP_TYPE_HASH);
+ __uint(map_flags, BPF_F_NO_PREALLOC);
+ __uint(max_entries, 1000);
+ __type(key, int);
+ __type(value, struct hmap_elem);
+} hmap_malloc SEC(".maps");
+
+struct elem {
+ struct bpf_timer t;
+};
+
+struct {
+ __uint(type, BPF_MAP_TYPE_ARRAY);
+ __uint(max_entries, 2);
+ __type(key, int);
+ __type(value, struct elem);
+} array SEC(".maps");
+
+struct {
+ __uint(type, BPF_MAP_TYPE_LRU_HASH);
+ __uint(max_entries, 4);
+ __type(key, int);
+ __type(value, struct elem);
+} lru SEC(".maps");
+
+__u64 bss_data;
+__u64 err;
+__u64 ok;
+__u64 callback_check = 52;
+__u64 callback2_check = 52;
+
+#define ARRAY 1
+#define HTAB 2
+#define HTAB_MALLOC 3
+#define LRU 4
+
+/* callback for array and lru timers */
+static int timer_cb1(void *map, int *key, struct bpf_timer *timer)
+{
+ /* increment bss variable twice.
+ * Once via array timer callback and once via lru timer callback
+ */
+ bss_data += 5;
+
+ /* *key == 0 - the callback was called for array timer.
+ * *key == 4 - the callback was called from lru timer.
+ */
+ if (*key == ARRAY) {
+ struct bpf_timer *lru_timer;
+ int lru_key = LRU;
+
+ /* rearm array timer to be called again in ~35 seconds */
+ if (bpf_timer_start(timer, 1ull << 35, 0) != 0)
+ err |= 1;
+
+ lru_timer = bpf_map_lookup_elem(&lru, &lru_key);
+ if (!lru_timer)
+ return 0;
+ bpf_timer_set_callback(lru_timer, timer_cb1);
+ if (bpf_timer_start(lru_timer, 0, 0) != 0)
+ err |= 2;
+ } else if (*key == LRU) {
+ int lru_key, i;
+
+ for (i = LRU + 1;
+ i <= 100 /* for current LRU eviction algorithm this number
+ * should be larger than ~ lru->max_entries * 2
+ */;
+ i++) {
+ struct elem init = {};
+
+ /* lru_key cannot be used as loop induction variable
+ * otherwise the loop will be unbounded.
+ */
+ lru_key = i;
+
+ /* add more elements into lru map to push out current
+ * element and force deletion of this timer
+ */
+ bpf_map_update_elem(map, &lru_key, &init, 0);
+ /* look it up to bump it into active list */
+ bpf_map_lookup_elem(map, &lru_key);
+
+ /* keep adding until *key changes underneath,
+ * which means that key/timer memory was reused
+ */
+ if (*key != LRU)
+ break;
+ }
+
+ /* check that the timer was removed */
+ if (bpf_timer_cancel(timer) != -EINVAL)
+ err |= 4;
+ ok |= 1;
+ }
+ return 0;
+}
+
+SEC("fentry/bpf_fentry_test1")
+int BPF_PROG(test1, int a)
+{
+ struct bpf_timer *arr_timer, *lru_timer;
+ struct elem init = {};
+ int lru_key = LRU;
+ int array_key = ARRAY;
+
+ arr_timer = bpf_map_lookup_elem(&array, &array_key);
+ if (!arr_timer)
+ return 0;
+ bpf_timer_init(arr_timer, &array, CLOCK_MONOTONIC);
+
+ bpf_map_update_elem(&lru, &lru_key, &init, 0);
+ lru_timer = bpf_map_lookup_elem(&lru, &lru_key);
+ if (!lru_timer)
+ return 0;
+ bpf_timer_init(lru_timer, &lru, CLOCK_MONOTONIC);
+
+ bpf_timer_set_callback(arr_timer, timer_cb1);
+ bpf_timer_start(arr_timer, 0 /* call timer_cb1 asap */, 0);
+
+ /* init more timers to check that array destruction
+ * doesn't leak timer memory.
+ */
+ array_key = 0;
+ arr_timer = bpf_map_lookup_elem(&array, &array_key);
+ if (!arr_timer)
+ return 0;
+ bpf_timer_init(arr_timer, &array, CLOCK_MONOTONIC);
+ return 0;
+}
+
+/* callback for prealloc and non-prealloca hashtab timers */
+static int timer_cb2(void *map, int *key, struct hmap_elem *val)
+{
+ if (*key == HTAB)
+ callback_check--;
+ else
+ callback2_check--;
+ if (val->counter > 0 && --val->counter) {
+ /* re-arm the timer again to execute after 1 usec */
+ bpf_timer_start(&val->timer, 1000, 0);
+ } else if (*key == HTAB) {
+ struct bpf_timer *arr_timer;
+ int array_key = ARRAY;
+
+ /* cancel arr_timer otherwise bpf_fentry_test1 prog
+ * will stay alive forever.
+ */
+ arr_timer = bpf_map_lookup_elem(&array, &array_key);
+ if (!arr_timer)
+ return 0;
+ if (bpf_timer_cancel(arr_timer) != 1)
+ /* bpf_timer_cancel should return 1 to indicate
+ * that arr_timer was active at this time
+ */
+ err |= 8;
+
+ /* try to cancel ourself. It shouldn't deadlock. */
+ if (bpf_timer_cancel(&val->timer) != -EDEADLK)
+ err |= 16;
+
+ /* delete this key and this timer anyway.
+ * It shouldn't deadlock either.
+ */
+ bpf_map_delete_elem(map, key);
+
+ /* in preallocated hashmap both 'key' and 'val' could have been
+ * reused to store another map element (like in LRU above),
+ * but in controlled test environment the below test works.
+ * It's not a use-after-free. The memory is owned by the map.
+ */
+ if (bpf_timer_start(&val->timer, 1000, 0) != -EINVAL)
+ err |= 32;
+ ok |= 2;
+ } else {
+ if (*key != HTAB_MALLOC)
+ err |= 64;
+
+ /* try to cancel ourself. It shouldn't deadlock. */
+ if (bpf_timer_cancel(&val->timer) != -EDEADLK)
+ err |= 128;
+
+ /* delete this key and this timer anyway.
+ * It shouldn't deadlock either.
+ */
+ bpf_map_delete_elem(map, key);
+
+ /* in non-preallocated hashmap both 'key' and 'val' are RCU
+ * protected and still valid though this element was deleted
+ * from the map. Arm this timer for ~35 seconds. When callback
+ * finishes the call_rcu will invoke:
+ * htab_elem_free_rcu
+ * check_and_free_timer
+ * bpf_timer_cancel_and_free
+ * to cancel this 35 second sleep and delete the timer for real.
+ */
+ if (bpf_timer_start(&val->timer, 1ull << 35, 0) != 0)
+ err |= 256;
+ ok |= 4;
+ }
+ return 0;
+}
+
+int bpf_timer_test(void)
+{
+ struct hmap_elem *val;
+ int key = HTAB, key_malloc = HTAB_MALLOC;
+
+ val = bpf_map_lookup_elem(&hmap, &key);
+ if (val) {
+ if (bpf_timer_init(&val->timer, &hmap, CLOCK_BOOTTIME) != 0)
+ err |= 512;
+ bpf_timer_set_callback(&val->timer, timer_cb2);
+ bpf_timer_start(&val->timer, 1000, 0);
+ }
+ val = bpf_map_lookup_elem(&hmap_malloc, &key_malloc);
+ if (val) {
+ if (bpf_timer_init(&val->timer, &hmap_malloc, CLOCK_BOOTTIME) != 0)
+ err |= 1024;
+ bpf_timer_set_callback(&val->timer, timer_cb2);
+ bpf_timer_start(&val->timer, 1000, 0);
+ }
+ return 0;
+}
+
+SEC("fentry/bpf_fentry_test2")
+int BPF_PROG(test2, int a, int b)
+{
+ struct hmap_elem init = {}, *val;
+ int key = HTAB, key_malloc = HTAB_MALLOC;
+
+ init.counter = 10; /* number of times to trigger timer_cb2 */
+ bpf_map_update_elem(&hmap, &key, &init, 0);
+ val = bpf_map_lookup_elem(&hmap, &key);
+ if (val)
+ bpf_timer_init(&val->timer, &hmap, CLOCK_BOOTTIME);
+ /* update the same key to free the timer */
+ bpf_map_update_elem(&hmap, &key, &init, 0);
+
+ bpf_map_update_elem(&hmap_malloc, &key_malloc, &init, 0);
+ val = bpf_map_lookup_elem(&hmap_malloc, &key_malloc);
+ if (val)
+ bpf_timer_init(&val->timer, &hmap_malloc, CLOCK_BOOTTIME);
+ /* update the same key to free the timer */
+ bpf_map_update_elem(&hmap_malloc, &key_malloc, &init, 0);
+
+ /* init more timers to check that htab operations
+ * don't leak timer memory.
+ */
+ key = 0;
+ bpf_map_update_elem(&hmap, &key, &init, 0);
+ val = bpf_map_lookup_elem(&hmap, &key);
+ if (val)
+ bpf_timer_init(&val->timer, &hmap, CLOCK_BOOTTIME);
+ bpf_map_delete_elem(&hmap, &key);
+ bpf_map_update_elem(&hmap, &key, &init, 0);
+ val = bpf_map_lookup_elem(&hmap, &key);
+ if (val)
+ bpf_timer_init(&val->timer, &hmap, CLOCK_BOOTTIME);
+
+ /* and with non-prealloc htab */
+ key_malloc = 0;
+ bpf_map_update_elem(&hmap_malloc, &key_malloc, &init, 0);
+ val = bpf_map_lookup_elem(&hmap_malloc, &key_malloc);
+ if (val)
+ bpf_timer_init(&val->timer, &hmap_malloc, CLOCK_BOOTTIME);
+ bpf_map_delete_elem(&hmap_malloc, &key_malloc);
+ bpf_map_update_elem(&hmap_malloc, &key_malloc, &init, 0);
+ val = bpf_map_lookup_elem(&hmap_malloc, &key_malloc);
+ if (val)
+ bpf_timer_init(&val->timer, &hmap_malloc, CLOCK_BOOTTIME);
+
+ return bpf_timer_test();
+}
diff --git a/tools/testing/selftests/bpf/progs/timer_mim.c b/tools/testing/selftests/bpf/progs/timer_mim.c
new file mode 100644
index 000000000000..2fee7ab105ef
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/timer_mim.c
@@ -0,0 +1,88 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+#include <linux/bpf.h>
+#include <time.h>
+#include <errno.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_tcp_helpers.h"
+
+char _license[] SEC("license") = "GPL";
+struct hmap_elem {
+ int pad; /* unused */
+ struct bpf_timer timer;
+};
+
+struct inner_map {
+ __uint(type, BPF_MAP_TYPE_HASH);
+ __uint(max_entries, 1024);
+ __type(key, int);
+ __type(value, struct hmap_elem);
+} inner_htab SEC(".maps");
+
+#define ARRAY_KEY 1
+#define HASH_KEY 1234
+
+struct outer_arr {
+ __uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS);
+ __uint(max_entries, 2);
+ __uint(key_size, sizeof(int));
+ __uint(value_size, sizeof(int));
+ __array(values, struct inner_map);
+} outer_arr SEC(".maps") = {
+ .values = { [ARRAY_KEY] = &inner_htab },
+};
+
+__u64 err;
+__u64 ok;
+__u64 cnt;
+
+static int timer_cb1(void *map, int *key, struct hmap_elem *val);
+
+static int timer_cb2(void *map, int *key, struct hmap_elem *val)
+{
+ cnt++;
+ bpf_timer_set_callback(&val->timer, timer_cb1);
+ if (bpf_timer_start(&val->timer, 1000, 0))
+ err |= 1;
+ ok |= 1;
+ return 0;
+}
+
+/* callback for inner hash map */
+static int timer_cb1(void *map, int *key, struct hmap_elem *val)
+{
+ cnt++;
+ bpf_timer_set_callback(&val->timer, timer_cb2);
+ if (bpf_timer_start(&val->timer, 1000, 0))
+ err |= 2;
+ /* Do a lookup to make sure 'map' and 'key' pointers are correct */
+ bpf_map_lookup_elem(map, key);
+ ok |= 2;
+ return 0;
+}
+
+SEC("fentry/bpf_fentry_test1")
+int BPF_PROG(test1, int a)
+{
+ struct hmap_elem init = {};
+ struct bpf_map *inner_map;
+ struct hmap_elem *val;
+ int array_key = ARRAY_KEY;
+ int hash_key = HASH_KEY;
+
+ inner_map = bpf_map_lookup_elem(&outer_arr, &array_key);
+ if (!inner_map)
+ return 0;
+
+ bpf_map_update_elem(inner_map, &hash_key, &init, 0);
+ val = bpf_map_lookup_elem(inner_map, &hash_key);
+ if (!val)
+ return 0;
+
+ bpf_timer_init(&val->timer, inner_map, CLOCK_MONOTONIC);
+ if (bpf_timer_set_callback(&val->timer, timer_cb1))
+ err |= 4;
+ if (bpf_timer_start(&val->timer, 0, 0))
+ err |= 8;
+ return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/timer_mim_reject.c b/tools/testing/selftests/bpf/progs/timer_mim_reject.c
new file mode 100644
index 000000000000..5d648e3d8a41
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/timer_mim_reject.c
@@ -0,0 +1,74 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+#include <linux/bpf.h>
+#include <time.h>
+#include <errno.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_tcp_helpers.h"
+
+char _license[] SEC("license") = "GPL";
+struct hmap_elem {
+ int pad; /* unused */
+ struct bpf_timer timer;
+};
+
+struct inner_map {
+ __uint(type, BPF_MAP_TYPE_HASH);
+ __uint(max_entries, 1024);
+ __type(key, int);
+ __type(value, struct hmap_elem);
+} inner_htab SEC(".maps");
+
+#define ARRAY_KEY 1
+#define ARRAY_KEY2 2
+#define HASH_KEY 1234
+
+struct outer_arr {
+ __uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS);
+ __uint(max_entries, 2);
+ __uint(key_size, sizeof(int));
+ __uint(value_size, sizeof(int));
+ __array(values, struct inner_map);
+} outer_arr SEC(".maps") = {
+ .values = { [ARRAY_KEY] = &inner_htab },
+};
+
+__u64 err;
+__u64 ok;
+__u64 cnt;
+
+/* callback for inner hash map */
+static int timer_cb(void *map, int *key, struct hmap_elem *val)
+{
+ return 0;
+}
+
+SEC("fentry/bpf_fentry_test1")
+int BPF_PROG(test1, int a)
+{
+ struct hmap_elem init = {};
+ struct bpf_map *inner_map, *inner_map2;
+ struct hmap_elem *val;
+ int array_key = ARRAY_KEY;
+ int array_key2 = ARRAY_KEY2;
+ int hash_key = HASH_KEY;
+
+ inner_map = bpf_map_lookup_elem(&outer_arr, &array_key);
+ if (!inner_map)
+ return 0;
+
+ inner_map2 = bpf_map_lookup_elem(&outer_arr, &array_key2);
+ if (!inner_map2)
+ return 0;
+ bpf_map_update_elem(inner_map, &hash_key, &init, 0);
+ val = bpf_map_lookup_elem(inner_map, &hash_key);
+ if (!val)
+ return 0;
+
+ bpf_timer_init(&val->timer, inner_map2, CLOCK_MONOTONIC);
+ if (bpf_timer_set_callback(&val->timer, timer_cb))
+ err |= 4;
+ if (bpf_timer_start(&val->timer, 0, 0))
+ err |= 8;
+ return 0;
+}
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 79c9eb0034d5..5b169e915679 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -25,6 +25,7 @@ TEST_PROGS += bareudp.sh
TEST_PROGS += unicast_extensions.sh
TEST_PROGS += udpgro_fwd.sh
TEST_PROGS += veth.sh
+TEST_PROGS += ioam6.sh
TEST_PROGS_EXTENDED := in_netns.sh
TEST_GEN_FILES = socket nettest
TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy reuseport_addr_any
@@ -36,6 +37,7 @@ TEST_GEN_FILES += fin_ack_lat
TEST_GEN_FILES += reuseaddr_ports_exhausted
TEST_GEN_FILES += hwtstamp_config rxtimestamp timestamping txtimestamp
TEST_GEN_FILES += ipsec
+TEST_GEN_FILES += ioam6_parser
TEST_GEN_PROGS = reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa
TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict tls
diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config
index 6f905b53904f..21b646d10b88 100644
--- a/tools/testing/selftests/net/config
+++ b/tools/testing/selftests/net/config
@@ -42,3 +42,4 @@ CONFIG_NET_CLS_FLOWER=m
CONFIG_NET_ACT_TUNNEL_KEY=m
CONFIG_NET_ACT_MIRRED=m
CONFIG_BAREUDP=m
+CONFIG_IPV6_IOAM6_LWTUNNEL=y
diff --git a/tools/testing/selftests/net/ioam6.sh b/tools/testing/selftests/net/ioam6.sh
new file mode 100644
index 000000000000..bcf15487e584
--- /dev/null
+++ b/tools/testing/selftests/net/ioam6.sh
@@ -0,0 +1,297 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
+#
+# Author: Justin Iurman <justin.iurman@uliege.be>
+#
+# This test evaluates the IOAM insertion for IPv6 by checking the IOAM data
+# integrity on the receiver.
+#
+# The topology is formed by 3 nodes: Alpha (sender), Beta (router in-between)
+# and Gamma (receiver). An IOAM domain is configured from Alpha to Gamma only,
+# which means not on the reverse path. When Gamma is the destination, Alpha
+# adds an IOAM option (Pre-allocated Trace) inside a Hop-by-hop and fills the
+# trace with its own IOAM data. Beta and Gamma also fill the trace. The IOAM
+# data integrity is checked on Gamma, by comparing with the pre-defined IOAM
+# configuration (see below).
+#
+# +-------------------+ +-------------------+
+# | | | |
+# | alpha netns | | gamma netns |
+# | | | |
+# | +-------------+ | | +-------------+ |
+# | | veth0 | | | | veth0 | |
+# | | db01::2/64 | | | | db02::2/64 | |
+# | +-------------+ | | +-------------+ |
+# | . | | . |
+# +-------------------+ +-------------------+
+# . .
+# . .
+# . .
+# +----------------------------------------------------+
+# | . . |
+# | +-------------+ +-------------+ |
+# | | veth0 | | veth1 | |
+# | | db01::1/64 | ................ | db02::1/64 | |
+# | +-------------+ +-------------+ |
+# | |
+# | beta netns |
+# | |
+# +--------------------------+-------------------------+
+#
+#
+# ~~~~~~~~~~~~~~~~~~~~~~
+# | IOAM configuration |
+# ~~~~~~~~~~~~~~~~~~~~~~
+#
+# Alpha
+# +-----------------------------------------------------------+
+# | Type | Value |
+# +-----------------------------------------------------------+
+# | Node ID | 1 |
+# +-----------------------------------------------------------+
+# | Node Wide ID | 11111111 |
+# +-----------------------------------------------------------+
+# | Ingress ID | 0xffff (default value) |
+# +-----------------------------------------------------------+
+# | Ingress Wide ID | 0xffffffff (default value) |
+# +-----------------------------------------------------------+
+# | Egress ID | 101 |
+# +-----------------------------------------------------------+
+# | Egress Wide ID | 101101 |
+# +-----------------------------------------------------------+
+# | Namespace Data | 0xdeadbee0 |
+# +-----------------------------------------------------------+
+# | Namespace Wide Data | 0xcafec0caf00dc0de |
+# +-----------------------------------------------------------+
+# | Schema ID | 777 |
+# +-----------------------------------------------------------+
+# | Schema Data | something that will be 4n-aligned |
+# +-----------------------------------------------------------+
+#
+# Note: When Gamma is the destination, Alpha adds an IOAM Pre-allocated Trace
+# option inside a Hop-by-hop, where 164 bytes are pre-allocated for the
+# trace, with 123 as the IOAM-Namespace and with 0xfff00200 as the trace
+# type (= all available options at this time). As a result, and based on
+# IOAM configurations here, only both Alpha and Beta should be capable of
+# inserting their IOAM data while Gamma won't have enough space and will
+# set the overflow bit.
+#
+# Beta
+# +-----------------------------------------------------------+
+# | Type | Value |
+# +-----------------------------------------------------------+
+# | Node ID | 2 |
+# +-----------------------------------------------------------+
+# | Node Wide ID | 22222222 |
+# +-----------------------------------------------------------+
+# | Ingress ID | 201 |
+# +-----------------------------------------------------------+
+# | Ingress Wide ID | 201201 |
+# +-----------------------------------------------------------+
+# | Egress ID | 202 |
+# +-----------------------------------------------------------+
+# | Egress Wide ID | 202202 |
+# +-----------------------------------------------------------+
+# | Namespace Data | 0xdeadbee1 |
+# +-----------------------------------------------------------+
+# | Namespace Wide Data | 0xcafec0caf11dc0de |
+# +-----------------------------------------------------------+
+# | Schema ID | 0xffffff (= None) |
+# +-----------------------------------------------------------+
+# | Schema Data | |
+# +-----------------------------------------------------------+
+#
+# Gamma
+# +-----------------------------------------------------------+
+# | Type | Value |
+# +-----------------------------------------------------------+
+# | Node ID | 3 |
+# +-----------------------------------------------------------+
+# | Node Wide ID | 33333333 |
+# +-----------------------------------------------------------+
+# | Ingress ID | 301 |
+# +-----------------------------------------------------------+
+# | Ingress Wide ID | 301301 |
+# +-----------------------------------------------------------+
+# | Egress ID | 0xffff (default value) |
+# +-----------------------------------------------------------+
+# | Egress Wide ID | 0xffffffff (default value) |
+# +-----------------------------------------------------------+
+# | Namespace Data | 0xdeadbee2 |
+# +-----------------------------------------------------------+
+# | Namespace Wide Data | 0xcafec0caf22dc0de |
+# +-----------------------------------------------------------+
+# | Schema ID | 0xffffff (= None) |
+# +-----------------------------------------------------------+
+# | Schema Data | |
+# +-----------------------------------------------------------+
+
+#===============================================================================
+#
+# WARNING:
+# Do NOT modify the following configuration unless you know what you're doing.
+#
+IOAM_NAMESPACE=123
+IOAM_TRACE_TYPE=0xfff00200
+IOAM_PREALLOC_DATA_SIZE=164
+
+ALPHA=(
+ 1 # ID
+ 11111111 # Wide ID
+ 0xffff # Ingress ID
+ 0xffffffff # Ingress Wide ID
+ 101 # Egress ID
+ 101101 # Egress Wide ID
+ 0xdeadbee0 # Namespace Data
+ 0xcafec0caf00dc0de # Namespace Wide Data
+ 777 # Schema ID (0xffffff = None)
+ "something that will be 4n-aligned" # Schema Data
+)
+
+BETA=(
+ 2
+ 22222222
+ 201
+ 201201
+ 202
+ 202202
+ 0xdeadbee1
+ 0xcafec0caf11dc0de
+ 0xffffff
+ ""
+)
+
+GAMMA=(
+ 3
+ 33333333
+ 301
+ 301301
+ 0xffff
+ 0xffffffff
+ 0xdeadbee2
+ 0xcafec0caf22dc0de
+ 0xffffff
+ ""
+)
+#===============================================================================
+
+if [ "$(id -u)" -ne 0 ]; then
+ echo "SKIP: Need root privileges"
+ exit 1
+fi
+
+if [ ! -x "$(command -v ip)" ]; then
+ echo "SKIP: Could not run test without ip tool"
+ exit 1
+fi
+
+ip ioam &>/dev/null
+if [ $? = 1 ]; then
+ echo "SKIP: ip tool must include IOAM"
+ exit 1
+fi
+
+if [ ! -e /proc/sys/net/ipv6/ioam6_id ]; then
+ echo "SKIP: ioam6 sysctls do not exist"
+ exit 1
+fi
+
+cleanup()
+{
+ ip link del ioam-veth-alpha 2>/dev/null || true
+ ip link del ioam-veth-gamma 2>/dev/null || true
+
+ ip netns del ioam-node-alpha || true
+ ip netns del ioam-node-beta || true
+ ip netns del ioam-node-gamma || true
+}
+
+setup()
+{
+ ip netns add ioam-node-alpha
+ ip netns add ioam-node-beta
+ ip netns add ioam-node-gamma
+
+ ip link add name ioam-veth-alpha type veth peer name ioam-veth-betaL
+ ip link add name ioam-veth-betaR type veth peer name ioam-veth-gamma
+
+ ip link set ioam-veth-alpha netns ioam-node-alpha
+ ip link set ioam-veth-betaL netns ioam-node-beta
+ ip link set ioam-veth-betaR netns ioam-node-beta
+ ip link set ioam-veth-gamma netns ioam-node-gamma
+
+ ip -netns ioam-node-alpha link set ioam-veth-alpha name veth0
+ ip -netns ioam-node-beta link set ioam-veth-betaL name veth0
+ ip -netns ioam-node-beta link set ioam-veth-betaR name veth1
+ ip -netns ioam-node-gamma link set ioam-veth-gamma name veth0
+
+ ip -netns ioam-node-alpha addr add db01::2/64 dev veth0
+ ip -netns ioam-node-alpha link set veth0 up
+ ip -netns ioam-node-alpha link set lo up
+ ip -netns ioam-node-alpha route add default via db01::1
+
+ ip -netns ioam-node-beta addr add db01::1/64 dev veth0
+ ip -netns ioam-node-beta addr add db02::1/64 dev veth1
+ ip -netns ioam-node-beta link set veth0 up
+ ip -netns ioam-node-beta link set veth1 up
+ ip -netns ioam-node-beta link set lo up
+
+ ip -netns ioam-node-gamma addr add db02::2/64 dev veth0
+ ip -netns ioam-node-gamma link set veth0 up
+ ip -netns ioam-node-gamma link set lo up
+ ip -netns ioam-node-gamma route add default via db02::1
+
+ # - IOAM config -
+ ip netns exec ioam-node-alpha sysctl -wq net.ipv6.ioam6_id=${ALPHA[0]}
+ ip netns exec ioam-node-alpha sysctl -wq net.ipv6.ioam6_id_wide=${ALPHA[1]}
+ ip netns exec ioam-node-alpha sysctl -wq net.ipv6.conf.veth0.ioam6_id=${ALPHA[4]}
+ ip netns exec ioam-node-alpha sysctl -wq net.ipv6.conf.veth0.ioam6_id_wide=${ALPHA[5]}
+ ip -netns ioam-node-alpha ioam namespace add ${IOAM_NAMESPACE} data ${ALPHA[6]} wide ${ALPHA[7]}
+ ip -netns ioam-node-alpha ioam schema add ${ALPHA[8]} "${ALPHA[9]}"
+ ip -netns ioam-node-alpha ioam namespace set ${IOAM_NAMESPACE} schema ${ALPHA[8]}
+ ip -netns ioam-node-alpha route add db02::/64 encap ioam6 trace type ${IOAM_TRACE_TYPE:0:-2} ns ${IOAM_NAMESPACE} size ${IOAM_PREALLOC_DATA_SIZE} via db01::1 dev veth0
+
+ ip netns exec ioam-node-beta sysctl -wq net.ipv6.conf.all.forwarding=1
+ ip netns exec ioam-node-beta sysctl -wq net.ipv6.ioam6_id=${BETA[0]}
+ ip netns exec ioam-node-beta sysctl -wq net.ipv6.ioam6_id_wide=${BETA[1]}
+ ip netns exec ioam-node-beta sysctl -wq net.ipv6.conf.veth0.ioam6_enabled=1
+ ip netns exec ioam-node-beta sysctl -wq net.ipv6.conf.veth0.ioam6_id=${BETA[2]}
+ ip netns exec ioam-node-beta sysctl -wq net.ipv6.conf.veth0.ioam6_id_wide=${BETA[3]}
+ ip netns exec ioam-node-beta sysctl -wq net.ipv6.conf.veth1.ioam6_id=${BETA[4]}
+ ip netns exec ioam-node-beta sysctl -wq net.ipv6.conf.veth1.ioam6_id_wide=${BETA[5]}
+ ip -netns ioam-node-beta ioam namespace add ${IOAM_NAMESPACE} data ${BETA[6]} wide ${BETA[7]}
+
+ ip netns exec ioam-node-gamma sysctl -wq net.ipv6.ioam6_id=${GAMMA[0]}
+ ip netns exec ioam-node-gamma sysctl -wq net.ipv6.ioam6_id_wide=${GAMMA[1]}
+ ip netns exec ioam-node-gamma sysctl -wq net.ipv6.conf.veth0.ioam6_enabled=1
+ ip netns exec ioam-node-gamma sysctl -wq net.ipv6.conf.veth0.ioam6_id=${GAMMA[2]}
+ ip netns exec ioam-node-gamma sysctl -wq net.ipv6.conf.veth0.ioam6_id_wide=${GAMMA[3]}
+ ip -netns ioam-node-gamma ioam namespace add ${IOAM_NAMESPACE} data ${GAMMA[6]} wide ${GAMMA[7]}
+}
+
+run()
+{
+ echo -n "IOAM test... "
+
+ ip netns exec ioam-node-alpha ping6 -c 5 -W 1 db02::2 &>/dev/null
+ if [ $? != 0 ]; then
+ echo "FAILED"
+ cleanup &>/dev/null
+ exit 0
+ fi
+
+ ip netns exec ioam-node-gamma ./ioam6_parser veth0 2 ${IOAM_NAMESPACE} ${IOAM_TRACE_TYPE} 64 ${ALPHA[0]} ${ALPHA[1]} ${ALPHA[2]} ${ALPHA[3]} ${ALPHA[4]} ${ALPHA[5]} ${ALPHA[6]} ${ALPHA[7]} ${ALPHA[8]} "${ALPHA[9]}" 63 ${BETA[0]} ${BETA[1]} ${BETA[2]} ${BETA[3]} ${BETA[4]} ${BETA[5]} ${BETA[6]} ${BETA[7]} ${BETA[8]} &
+
+ local spid=$!
+ sleep 0.1
+
+ ip netns exec ioam-node-alpha ping6 -c 5 -W 1 db02::2 &>/dev/null
+
+ wait $spid
+ [ $? = 0 ] && echo "PASSED" || echo "FAILED"
+}
+
+cleanup &>/dev/null
+setup
+run
+cleanup &>/dev/null
diff --git a/tools/testing/selftests/net/ioam6_parser.c b/tools/testing/selftests/net/ioam6_parser.c
new file mode 100644
index 000000000000..2256cf5ad637
--- /dev/null
+++ b/tools/testing/selftests/net/ioam6_parser.c
@@ -0,0 +1,402 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Author: Justin Iurman (justin.iurman@uliege.be)
+ *
+ * IOAM parser for IPv6, see ioam6.sh for details.
+ */
+#include <asm/byteorder.h>
+#include <linux/const.h>
+#include <linux/if_ether.h>
+#include <linux/ioam6.h>
+#include <linux/ipv6.h>
+#include <sys/socket.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+
+struct node_args {
+ __u32 id;
+ __u64 wide;
+ __u16 ingr_id;
+ __u16 egr_id;
+ __u32 ingr_wide;
+ __u32 egr_wide;
+ __u32 ns_data;
+ __u64 ns_wide;
+ __u32 sc_id;
+ __u8 hop_limit;
+ __u8 *sc_data; /* NULL when sc_id = 0xffffff (default empty value) */
+};
+
+/* expected args per node, in that order */
+enum {
+ NODE_ARG_HOP_LIMIT,
+ NODE_ARG_ID,
+ NODE_ARG_WIDE,
+ NODE_ARG_INGR_ID,
+ NODE_ARG_INGR_WIDE,
+ NODE_ARG_EGR_ID,
+ NODE_ARG_EGR_WIDE,
+ NODE_ARG_NS_DATA,
+ NODE_ARG_NS_WIDE,
+ NODE_ARG_SC_ID,
+ __NODE_ARG_MAX,
+};
+
+#define NODE_ARGS_SIZE __NODE_ARG_MAX
+
+struct args {
+ __u16 ns_id;
+ __u32 trace_type;
+ __u8 n_node;
+ __u8 *ifname;
+ struct node_args node[0];
+};
+
+/* expected args, in that order */
+enum {
+ ARG_IFNAME,
+ ARG_N_NODE,
+ ARG_NS_ID,
+ ARG_TRACE_TYPE,
+ __ARG_MAX,
+};
+
+#define ARGS_SIZE __ARG_MAX
+
+int check_ioam6_node_data(__u8 **p, struct ioam6_trace_hdr *trace, __u8 hlim,
+ __u32 id, __u64 wide, __u16 ingr_id, __u32 ingr_wide,
+ __u16 egr_id, __u32 egr_wide, __u32 ns_data,
+ __u64 ns_wide, __u32 sc_id, __u8 *sc_data)
+{
+ __u64 raw64;
+ __u32 raw32;
+ __u8 sc_len;
+
+ if (trace->type.bit0) {
+ raw32 = __be32_to_cpu(*((__u32 *)*p));
+ if (hlim != (raw32 >> 24) || id != (raw32 & 0xffffff))
+ return 1;
+ *p += sizeof(__u32);
+ }
+
+ if (trace->type.bit1) {
+ raw32 = __be32_to_cpu(*((__u32 *)*p));
+ if (ingr_id != (raw32 >> 16) || egr_id != (raw32 & 0xffff))
+ return 1;
+ *p += sizeof(__u32);
+ }
+
+ if (trace->type.bit2)
+ *p += sizeof(__u32);
+
+ if (trace->type.bit3)
+ *p += sizeof(__u32);
+
+ if (trace->type.bit4) {
+ if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff)
+ return 1;
+ *p += sizeof(__u32);
+ }
+
+ if (trace->type.bit5) {
+ if (__be32_to_cpu(*((__u32 *)*p)) != ns_data)
+ return 1;
+ *p += sizeof(__u32);
+ }
+
+ if (trace->type.bit6) {
+ if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff)
+ return 1;
+ *p += sizeof(__u32);
+ }
+
+ if (trace->type.bit7) {
+ if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff)
+ return 1;
+ *p += sizeof(__u32);
+ }
+
+ if (trace->type.bit8) {
+ raw64 = __be64_to_cpu(*((__u64 *)*p));
+ if (hlim != (raw64 >> 56) || wide != (raw64 & 0xffffffffffffff))
+ return 1;
+ *p += sizeof(__u64);
+ }
+
+ if (trace->type.bit9) {
+ if (__be32_to_cpu(*((__u32 *)*p)) != ingr_wide)
+ return 1;
+ *p += sizeof(__u32);
+
+ if (__be32_to_cpu(*((__u32 *)*p)) != egr_wide)
+ return 1;
+ *p += sizeof(__u32);
+ }
+
+ if (trace->type.bit10) {
+ if (__be64_to_cpu(*((__u64 *)*p)) != ns_wide)
+ return 1;
+ *p += sizeof(__u64);
+ }
+
+ if (trace->type.bit11) {
+ if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff)
+ return 1;
+ *p += sizeof(__u32);
+ }
+
+ if (trace->type.bit22) {
+ raw32 = __be32_to_cpu(*((__u32 *)*p));
+ sc_len = sc_data ? __ALIGN_KERNEL(strlen(sc_data), 4) : 0;
+ if (sc_len != (raw32 >> 24) * 4 || sc_id != (raw32 & 0xffffff))
+ return 1;
+ *p += sizeof(__u32);
+
+ if (sc_data) {
+ if (strncmp(*p, sc_data, strlen(sc_data)))
+ return 1;
+
+ *p += strlen(sc_data);
+ sc_len -= strlen(sc_data);
+
+ while (sc_len--) {
+ if (**p != '\0')
+ return 1;
+ *p += sizeof(__u8);
+ }
+ }
+ }
+
+ return 0;
+}
+
+int check_ioam6_trace(struct ioam6_trace_hdr *trace, struct args *args)
+{
+ __u8 *p;
+ int i;
+
+ if (__be16_to_cpu(trace->namespace_id) != args->ns_id ||
+ __be32_to_cpu(trace->type_be32) != args->trace_type)
+ return 1;
+
+ p = trace->data + trace->remlen * 4;
+
+ for (i = args->n_node - 1; i >= 0; i--) {
+ if (check_ioam6_node_data(&p, trace,
+ args->node[i].hop_limit,
+ args->node[i].id,
+ args->node[i].wide,
+ args->node[i].ingr_id,
+ args->node[i].ingr_wide,
+ args->node[i].egr_id,
+ args->node[i].egr_wide,
+ args->node[i].ns_data,
+ args->node[i].ns_wide,
+ args->node[i].sc_id,
+ args->node[i].sc_data))
+ return 1;
+ }
+
+ return 0;
+}
+
+int parse_node_args(int *argcp, char ***argvp, struct node_args *node)
+{
+ char **argv = *argvp;
+
+ if (*argcp < NODE_ARGS_SIZE)
+ return 1;
+
+ node->hop_limit = strtoul(argv[NODE_ARG_HOP_LIMIT], NULL, 10);
+ if (!node->hop_limit) {
+ node->hop_limit = strtoul(argv[NODE_ARG_HOP_LIMIT], NULL, 16);
+ if (!node->hop_limit)
+ return 1;
+ }
+
+ node->id = strtoul(argv[NODE_ARG_ID], NULL, 10);
+ if (!node->id) {
+ node->id = strtoul(argv[NODE_ARG_ID], NULL, 16);
+ if (!node->id)
+ return 1;
+ }
+
+ node->wide = strtoull(argv[NODE_ARG_WIDE], NULL, 10);
+ if (!node->wide) {
+ node->wide = strtoull(argv[NODE_ARG_WIDE], NULL, 16);
+ if (!node->wide)
+ return 1;
+ }
+
+ node->ingr_id = strtoul(argv[NODE_ARG_INGR_ID], NULL, 10);
+ if (!node->ingr_id) {
+ node->ingr_id = strtoul(argv[NODE_ARG_INGR_ID], NULL, 16);
+ if (!node->ingr_id)
+ return 1;
+ }
+
+ node->ingr_wide = strtoul(argv[NODE_ARG_INGR_WIDE], NULL, 10);
+ if (!node->ingr_wide) {
+ node->ingr_wide = strtoul(argv[NODE_ARG_INGR_WIDE], NULL, 16);
+ if (!node->ingr_wide)
+ return 1;
+ }
+
+ node->egr_id = strtoul(argv[NODE_ARG_EGR_ID], NULL, 10);
+ if (!node->egr_id) {
+ node->egr_id = strtoul(argv[NODE_ARG_EGR_ID], NULL, 16);
+ if (!node->egr_id)
+ return 1;
+ }
+
+ node->egr_wide = strtoul(argv[NODE_ARG_EGR_WIDE], NULL, 10);
+ if (!node->egr_wide) {
+ node->egr_wide = strtoul(argv[NODE_ARG_EGR_WIDE], NULL, 16);
+ if (!node->egr_wide)
+ return 1;
+ }
+
+ node->ns_data = strtoul(argv[NODE_ARG_NS_DATA], NULL, 16);
+ if (!node->ns_data)
+ return 1;
+
+ node->ns_wide = strtoull(argv[NODE_ARG_NS_WIDE], NULL, 16);
+ if (!node->ns_wide)
+ return 1;
+
+ node->sc_id = strtoul(argv[NODE_ARG_SC_ID], NULL, 10);
+ if (!node->sc_id) {
+ node->sc_id = strtoul(argv[NODE_ARG_SC_ID], NULL, 16);
+ if (!node->sc_id)
+ return 1;
+ }
+
+ *argcp -= NODE_ARGS_SIZE;
+ *argvp += NODE_ARGS_SIZE;
+
+ if (node->sc_id != 0xffffff) {
+ if (!*argcp)
+ return 1;
+
+ node->sc_data = argv[NODE_ARG_SC_ID + 1];
+
+ *argcp -= 1;
+ *argvp += 1;
+ }
+
+ return 0;
+}
+
+struct args *parse_args(int argc, char **argv)
+{
+ struct args *args;
+ int n_node, i;
+
+ if (argc < ARGS_SIZE)
+ goto out;
+
+ n_node = strtoul(argv[ARG_N_NODE], NULL, 10);
+ if (!n_node || n_node > 10)
+ goto out;
+
+ args = calloc(1, sizeof(*args) + n_node * sizeof(struct node_args));
+ if (!args)
+ goto out;
+
+ args->ns_id = strtoul(argv[ARG_NS_ID], NULL, 10);
+ if (!args->ns_id)
+ goto free;
+
+ args->trace_type = strtoul(argv[ARG_TRACE_TYPE], NULL, 16);
+ if (!args->trace_type)
+ goto free;
+
+ args->n_node = n_node;
+ args->ifname = argv[ARG_IFNAME];
+
+ argv += ARGS_SIZE;
+ argc -= ARGS_SIZE;
+
+ for (i = 0; i < n_node; i++) {
+ if (parse_node_args(&argc, &argv, &args->node[i]))
+ goto free;
+ }
+
+ if (argc)
+ goto free;
+
+ return args;
+free:
+ free(args);
+out:
+ return NULL;
+}
+
+int main(int argc, char **argv)
+{
+ int ret, fd, pkts, size, hoplen, found;
+ struct ioam6_trace_hdr *ioam6h;
+ struct ioam6_hdr *opt;
+ struct ipv6hdr *ip6h;
+ __u8 buffer[400], *p;
+ struct args *args;
+
+ args = parse_args(argc - 1, argv + 1);
+ if (!args) {
+ ret = 1;
+ goto out;
+ }
+
+ fd = socket(AF_PACKET, SOCK_DGRAM, __cpu_to_be16(ETH_P_IPV6));
+ if (!fd) {
+ ret = 1;
+ goto out;
+ }
+
+ if (setsockopt(fd, SOL_SOCKET, SO_BINDTODEVICE,
+ args->ifname, strlen(args->ifname))) {
+ ret = 1;
+ goto close;
+ }
+
+ pkts = 0;
+ found = 0;
+ while (pkts < 3 && !found) {
+ size = recv(fd, buffer, sizeof(buffer), 0);
+ ip6h = (struct ipv6hdr *)buffer;
+ pkts++;
+
+ if (ip6h->nexthdr == IPPROTO_HOPOPTS) {
+ p = buffer + sizeof(*ip6h);
+ hoplen = (p[1] + 1) << 3;
+
+ p += sizeof(struct ipv6_hopopt_hdr);
+ while (hoplen > 0) {
+ opt = (struct ioam6_hdr *)p;
+
+ if (opt->opt_type == IPV6_TLV_IOAM &&
+ opt->type == IOAM6_TYPE_PREALLOC) {
+ found = 1;
+
+ p += sizeof(*opt);
+ ioam6h = (struct ioam6_trace_hdr *)p;
+
+ ret = check_ioam6_trace(ioam6h, args);
+ break;
+ }
+
+ p += opt->opt_len + 2;
+ hoplen -= opt->opt_len + 2;
+ }
+ }
+ }
+
+ if (!found)
+ ret = 1;
+close:
+ close(fd);
+out:
+ free(args);
+ return ret;
+}
diff --git a/tools/testing/selftests/net/veth.sh b/tools/testing/selftests/net/veth.sh
index 11d7cdb898c0..19eac3e44c06 100755
--- a/tools/testing/selftests/net/veth.sh
+++ b/tools/testing/selftests/net/veth.sh
@@ -13,7 +13,7 @@ readonly NS_DST=$BASE$DST
readonly BM_NET_V4=192.168.1.
readonly BM_NET_V6=2001:db8::
-readonly NPROCS=`nproc`
+readonly CPUS=`nproc`
ret=0
cleanup() {
@@ -75,6 +75,29 @@ chk_tso_flag() {
__chk_flag "$1" $2 $3 tcp-segmentation-offload
}
+chk_channels() {
+ local msg="$1"
+ local target=$2
+ local rx=$3
+ local tx=$4
+
+ local dev=veth$target
+
+ local cur_rx=`ip netns exec $BASE$target ethtool -l $dev |\
+ grep RX: | tail -n 1 | awk '{print $2}' `
+ local cur_tx=`ip netns exec $BASE$target ethtool -l $dev |\
+ grep TX: | tail -n 1 | awk '{print $2}'`
+ local cur_combined=`ip netns exec $BASE$target ethtool -l $dev |\
+ grep Combined: | tail -n 1 | awk '{print $2}'`
+
+ printf "%-60s" "$msg"
+ if [ "$cur_rx" = "$rx" -a "$cur_tx" = "$tx" -a "$cur_combined" = "n/a" ]; then
+ echo " ok "
+ else
+ echo " fail rx:$rx:$cur_rx tx:$tx:$cur_tx combined:n/a:$cur_combined"
+ fi
+}
+
chk_gro() {
local msg="$1"
local expected=$2
@@ -107,11 +130,100 @@ chk_gro() {
fi
}
+__change_channels()
+{
+ local cur_cpu
+ local end=$1
+ local cur
+ local i
+
+ while true; do
+ printf -v cur '%(%s)T'
+ [ $cur -le $end ] || break
+
+ for i in `seq 1 $CPUS`; do
+ ip netns exec $NS_SRC ethtool -L veth$SRC rx $i tx $i
+ ip netns exec $NS_DST ethtool -L veth$DST rx $i tx $i
+ done
+
+ for i in `seq 1 $((CPUS - 1))`; do
+ cur_cpu=$((CPUS - $i))
+ ip netns exec $NS_SRC ethtool -L veth$SRC rx $cur_cpu tx $cur_cpu
+ ip netns exec $NS_DST ethtool -L veth$DST rx $cur_cpu tx $cur_cpu
+ done
+ done
+}
+
+__send_data() {
+ local end=$1
+
+ while true; do
+ printf -v cur '%(%s)T'
+ [ $cur -le $end ] || break
+
+ ip netns exec $NS_SRC ./udpgso_bench_tx -4 -s 1000 -M 300 -D $BM_NET_V4$DST
+ done
+}
+
+do_stress() {
+ local end
+ printf -v end '%(%s)T'
+ end=$((end + $STRESS))
+
+ ip netns exec $NS_SRC ethtool -L veth$SRC rx 3 tx 3
+ ip netns exec $NS_DST ethtool -L veth$DST rx 3 tx 3
+
+ ip netns exec $NS_DST ./udpgso_bench_rx &
+ local rx_pid=$!
+
+ echo "Running stress test for $STRESS seconds..."
+ __change_channels $end &
+ local ch_pid=$!
+ __send_data $end &
+ local data_pid_1=$!
+ __send_data $end &
+ local data_pid_2=$!
+ __send_data $end &
+ local data_pid_3=$!
+ __send_data $end &
+ local data_pid_4=$!
+
+ wait $ch_pid $data_pid_1 $data_pid_2 $data_pid_3 $data_pid_4
+ kill -9 $rx_pid
+ echo "done"
+
+ # restore previous setting
+ ip netns exec $NS_SRC ethtool -L veth$SRC rx 2 tx 2
+ ip netns exec $NS_DST ethtool -L veth$DST rx 2 tx 1
+}
+
+usage() {
+ echo "Usage: $0 [-h] [-s <seconds>]"
+ echo -e "\t-h: show this help"
+ echo -e "\t-s: run optional stress tests for the given amount of seconds"
+}
+
+STRESS=0
+while getopts "hs:" option; do
+ case "$option" in
+ "h")
+ usage $0
+ exit 0
+ ;;
+ "s")
+ STRESS=$OPTARG
+ ;;
+ esac
+done
+
if [ ! -f ../bpf/xdp_dummy.o ]; then
echo "Missing xdp_dummy helper. Build bpf selftest first"
exit 1
fi
+[ $CPUS -lt 2 ] && echo "Only one CPU available, some tests will be skipped"
+[ $STRESS -gt 0 -a $CPUS -lt 3 ] && echo " stress test will be skipped, too"
+
create_ns
chk_gro_flag "default - gro flag" $SRC off
chk_gro_flag " - peer gro flag" $DST off
@@ -134,6 +246,8 @@ chk_gro " - aggregation with TSO off" 1
cleanup
create_ns
+chk_channels "default channels" $DST 1 1
+
ip -n $NS_DST link set dev veth$DST down
ip netns exec $NS_DST ethtool -K veth$DST gro on
chk_gro_flag "with gro enabled on link down - gro flag" $DST on
@@ -147,6 +261,56 @@ chk_gro " - aggregation with TSO off" 1
cleanup
create_ns
+
+CUR_TX=1
+CUR_RX=1
+if [ $CPUS -gt 1 ]; then
+ ip netns exec $NS_DST ethtool -L veth$DST tx 2
+ chk_channels "setting tx channels" $DST 1 2
+ CUR_TX=2
+fi
+
+if [ $CPUS -gt 2 ]; then
+ ip netns exec $NS_DST ethtool -L veth$DST rx 3 tx 3
+ chk_channels "setting both rx and tx channels" $DST 3 3
+ CUR_RX=3
+ CUR_TX=3
+fi
+
+ip netns exec $NS_DST ethtool -L veth$DST combined 2 2>/dev/null
+chk_channels "bad setting: combined channels" $DST $CUR_RX $CUR_TX
+
+ip netns exec $NS_DST ethtool -L veth$DST tx $((CPUS + 1)) 2>/dev/null
+chk_channels "setting invalid channels nr" $DST $CUR_RX $CUR_TX
+
+if [ $CPUS -gt 1 ]; then
+ # this also tests queues nr reduction
+ ip netns exec $NS_DST ethtool -L veth$DST rx 1 tx 2 2>/dev/null
+ ip netns exec $NS_SRC ethtool -L veth$SRC rx 1 tx 2 2>/dev/null
+ printf "%-60s" "bad setting: XDP with RX nr less than TX"
+ ip -n $NS_DST link set dev veth$DST xdp object ../bpf/xdp_dummy.o \
+ section xdp_dummy 2>/dev/null &&\
+ echo "fail - set operation successful ?!?" || echo " ok "
+
+ # the following tests will run with multiple channels active
+ ip netns exec $NS_SRC ethtool -L veth$SRC rx 2
+ ip netns exec $NS_DST ethtool -L veth$DST rx 2
+ ip -n $NS_DST link set dev veth$DST xdp object ../bpf/xdp_dummy.o \
+ section xdp_dummy 2>/dev/null
+ printf "%-60s" "bad setting: reducing RX nr below peer TX with XDP set"
+ ip netns exec $NS_DST ethtool -L veth$DST rx 1 2>/dev/null &&\
+ echo "fail - set operation successful ?!?" || echo " ok "
+ CUR_RX=2
+ CUR_TX=2
+fi
+
+if [ $CPUS -gt 2 ]; then
+ printf "%-60s" "bad setting: increasing peer TX nr above RX with XDP set"
+ ip netns exec $NS_SRC ethtool -L veth$SRC tx 3 2>/dev/null &&\
+ echo "fail - set operation successful ?!?" || echo " ok "
+ chk_channels "setting invalid channels nr" $DST 2 2
+fi
+
ip -n $NS_DST link set dev veth$DST xdp object ../bpf/xdp_dummy.o section xdp_dummy 2>/dev/null
chk_gro_flag "with xdp attached - gro flag" $DST on
chk_gro_flag " - peer gro flag" $SRC off
@@ -167,10 +331,27 @@ chk_gro_flag " - after gro on xdp off, gro flag" $DST on
chk_gro_flag " - peer gro flag" $SRC off
chk_tso_flag " - tso flag" $SRC on
chk_tso_flag " - peer tso flag" $DST on
+
+if [ $CPUS -gt 1 ]; then
+ ip netns exec $NS_DST ethtool -L veth$DST tx 1
+ chk_channels "decreasing tx channels with device down" $DST 2 1
+fi
+
ip -n $NS_DST link set dev veth$DST up
ip -n $NS_SRC link set dev veth$SRC up
chk_gro " - aggregation" 1
+if [ $CPUS -gt 1 ]; then
+ [ $STRESS -gt 0 -a $CPUS -gt 2 ] && do_stress
+
+ ip -n $NS_DST link set dev veth$DST down
+ ip -n $NS_SRC link set dev veth$SRC down
+ ip netns exec $NS_DST ethtool -L veth$DST tx 2
+ chk_channels "increasing tx channels with device down" $DST 2 2
+ ip -n $NS_DST link set dev veth$DST up
+ ip -n $NS_SRC link set dev veth$SRC up
+fi
+
ip netns exec $NS_DST ethtool -K veth$DST gro off
ip netns exec $NS_SRC ethtool -K veth$SRC tx-udp-segmentation off
chk_gro "aggregation again with default and TSO off" 10
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/skbmod.json b/tools/testing/selftests/tc-testing/tc-tests/actions/skbmod.json
index 6eb4c4f97060..742f2290973e 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/skbmod.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/skbmod.json
@@ -417,5 +417,29 @@
"teardown": [
"$TC actions flush action skbmod"
]
+ },
+ {
+ "id": "fe09",
+ "name": "Add skbmod action to mark ECN bits",
+ "category": [
+ "actions",
+ "skbmod"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action skbmod",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action skbmod ecn",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action skbmod index 1",
+ "matchPattern": "action order [0-9]*: skbmod pipe ecn",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action skbmod"
+ ]
}
]