Added a selftest for tcpbpf (sock_ops) that checks that the appropriate
callbacks occured and that it can access tcp_sock fields and that their
values are correct.
Run with command: ./test_tcpbpf_user
Signed-off-by: Lawrence Brakmo <bra...@fb.com>
---
tools/include/uapi/linux/bpf.h | 70 +++++++++++++-
tools/testing/selftests/bpf/Makefile | 4 +-
tools/testing/selftests/bpf/tcp_client.py | 52 ++++++++++
tools/testing/selftests/bpf/tcp_server.py | 79 ++++++++++++++++
tools/testing/selftests/bpf/test_tcpbpf_kern.c | 125 +++++++++++++++++++++++++
tools/testing/selftests/bpf/test_tcpbpf_user.c | 113 ++++++++++++++++++++++
6 files changed, 438 insertions(+), 5 deletions(-)
create mode 100755 tools/testing/selftests/bpf/tcp_client.py
create mode 100755 tools/testing/selftests/bpf/tcp_server.py
create mode 100644 tools/testing/selftests/bpf/test_tcpbpf_kern.c
create mode 100644 tools/testing/selftests/bpf/test_tcpbpf_user.c
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 4e8c60a..1fcd86f 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -945,8 +945,9 @@ struct bpf_map_info {
struct bpf_sock_ops {
__u32 op;
union {
- __u32 reply;
- __u32 replylong[4];
+ __u32 args[4]; /* Optionally passed to bpf program */
+ __u32 reply; /* Returned by bpf program */
+ __u32 replylong[4]; /* Optionally returned by bpf prog */
};
__u32 family;
__u32 remote_ip4; /* Stored in network byte order */
@@ -955,6 +956,33 @@ struct bpf_sock_ops {
__u32 local_ip6[4]; /* Stored in network byte order */
__u32 remote_port; /* Stored in network byte order */
__u32 local_port; /* stored in host byte order */
+ __u32 is_fullsock; /* Some TCP fields are only valid if
+ * there is a full socket. If not, the
+ * fields read as zero.
+ */
+ __u32 snd_cwnd;
+ __u32 srtt_us; /* Averaged RTT << 3 in usecs */
+ __u32 bpf_sock_ops_flags; /* flags defined in uapi/linux/tcp.h */
+ __u32 state;
+ __u32 rtt_min;
+ __u32 snd_ssthresh;
+ __u32 rcv_nxt;
+ __u32 snd_nxt;
+ __u32 snd_una;
+ __u32 mss_cache;
+ __u32 ecn_flags;
+ __u32 rate_delivered;
+ __u32 rate_interval_us;
+ __u32 packets_out;
+ __u32 retrans_out;
+ __u32 total_retrans;
+ __u32 segs_in;
+ __u32 data_segs_in;
+ __u32 segs_out;
+ __u32 data_segs_out;
+ __u64 bytes_received;
+ __u64 bytes_acked;
+ __u32 sk_txhash;
};
/* List of known BPF sock_ops operators.
@@ -990,6 +1018,41 @@ enum {
* a congestion threshold. RTTs above
* this indicate congestion
*/
+ BPF_SOCK_OPS_RTO_CB, /* Called when an RTO has triggered.
+ * Arg1: value of icsk_retransmits
+ * Arg2: value of icsk_rto
+ * Arg3: whether RTO has expired
+ */
+ BPF_SOCK_OPS_RETRANS_CB, /* Called when skb is retransmitted.
+ * Arg1: sequence number of 1st byte
+ * Arg2: # segments
+ */
+ BPF_SOCK_OPS_STATE_CB, /* Called when TCP changes state.
+ * Arg1: old_state
+ * Arg2: new_state
+ */
+};
+
+/* List of TCP states. There is a build check in net/ipv4/tcp.c to detect
+ * changes between the TCP and BPF versions. Ideally this should never happen.
+ * If it does, we need to add code to convert them before calling
+ * the BPF sock_ops function.
+ */
+enum {
+ BPF_TCP_ESTABLISHED = 1,
+ BPF_TCP_SYN_SENT,
+ BPF_TCP_SYN_RECV,
+ BPF_TCP_FIN_WAIT1,
+ BPF_TCP_FIN_WAIT2,
+ BPF_TCP_TIME_WAIT,
+ BPF_TCP_CLOSE,
+ BPF_TCP_CLOSE_WAIT,
+ BPF_TCP_LAST_ACK,
+ BPF_TCP_LISTEN,
+ BPF_TCP_CLOSING, /* Now a valid state */
+ BPF_TCP_NEW_SYN_RECV,
+
+ BPF_TCP_MAX_STATES /* Leave at the end! */
};
#define TCP_BPF_IW 1001 /* Set TCP initial congestion window */
@@ -1009,7 +1072,8 @@ struct bpf_perf_event_value {
#define BPF_DEVCG_DEV_CHAR (1ULL << 1)
struct bpf_cgroup_dev_ctx {
- __u32 access_type; /* (access << 16) | type */
+ /* access_type encoded as (BPF_DEVCG_ACC_* << 16) | BPF_DEVCG_DEV_* */
+ __u32 access_type;
__u32 major;
__u32 minor;
};
diff --git a/tools/testing/selftests/bpf/Makefile
b/tools/testing/selftests/bpf/Makefile
index 1304753..8e032a2 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -14,12 +14,12 @@ CFLAGS += -Wall -O2 -I$(APIDIR) -I$(LIBDIR) -I$(GENDIR)
$(GENFLAGS) -I../../../i
LDLIBS += -lcap -lelf -lrt
TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map
test_progs \
- test_align test_verifier_log test_dev_cgroup
+ test_align test_verifier_log test_dev_cgroup test_tcpbpf_user
TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o
test_obj_id.o \
test_pkt_md_access.o test_xdp_redirect.o test_xdp_meta.o
sockmap_parse_prog.o \
sockmap_verdict_prog.o dev_cgroup.o sample_ret0.o test_tracepoint.o \
- test_l4lb_noinline.o test_xdp_noinline.o
+ test_l4lb_noinline.o test_xdp_noinline.o test_tcpbpf_kern.o
TEST_PROGS := test_kmod.sh test_xdp_redirect.sh test_xdp_meta.sh \
test_offload.py
diff --git a/tools/testing/selftests/bpf/tcp_client.py
b/tools/testing/selftests/bpf/tcp_client.py
new file mode 100755
index 0000000..ac2ce32
--- /dev/null
+++ b/tools/testing/selftests/bpf/tcp_client.py
@@ -0,0 +1,52 @@
+#!/usr/local/bin/python
+#
+# SPDX-License-Identifier: GPL-2.0
+#
+
+import sys, os, os.path, getopt
+import socket, time
+import subprocess
+import select
+
+def read(sock, n):
+ buf = ''
+ while len(buf) < n:
+ rem = n - len(buf)
+ try: s = sock.recv(rem)
+ except (socket.error), e: return ''
+ buf += s
+ return buf
+
+def send(sock, s):
+ total = len(s)
+ count = 0
+ while count < total:
+ try: n = sock.send(s)
+ except (socket.error), e: n = 0
+ if n == 0:
+ return count;
+ count += n
+ return count
+
+
+serverPort = int(sys.argv[1])
+HostName = socket.gethostname()
+
+time.sleep(1)
+
+# create active socket
+sock = socket.socket(socket.AF_INET6, socket.SOCK_STREAM)
+try:
+ sock.connect((HostName, serverPort))
+except socket.error as e:
+ sys.exit(1)
+
+buf = ''
+n = 0
+while n < 1000:
+ buf += '+'
+ n += 1
+
+n = send(sock, buf)
+n = read(sock, 500)
+sys.exit(0)
diff --git a/tools/testing/selftests/bpf/tcp_server.py
b/tools/testing/selftests/bpf/tcp_server.py
new file mode 100755
index 0000000..9e5db0d
--- /dev/null
+++ b/tools/testing/selftests/bpf/tcp_server.py
@@ -0,0 +1,79 @@
+#!/usr/local/bin/python
+#
+# SPDX-License-Identifier: GPL-2.0
+#
+
+import sys, os, os.path, getopt
+import socket, time
+import subprocess
+import select
+
+def read(sock, n):
+ buf = ''
+ while len(buf) < n:
+ rem = n - len(buf)
+ try: s = sock.recv(rem)
+ except (socket.error), e: return ''
+ buf += s
+ return buf
+
+def send(sock, s):
+ total = len(s)
+ count = 0
+ while count < total:
+ try: n = sock.send(s)
+ except (socket.error), e: n = 0
+ if n == 0:
+ return count;
+ count += n
+ return count
+
+
+SERVER_PORT = 12877
+MAX_PORTS = 2
+
+serverPort = SERVER_PORT
+serverSocket = None
+
+HostName = socket.gethostname()
+
+# create passive socket
+serverSocket = socket.socket(socket.AF_INET6, socket.SOCK_STREAM)
+host = socket.gethostname()
+
+while serverPort < SERVER_PORT + 5:
+ try: serverSocket.bind((host, serverPort))
+ except socket.error as msg:
+ serverPort += 1
+ continue
+ break
+
+cmdStr = ("./tcp_client.py %d &") % (serverPort)
+os.system(cmdStr)
+
+buf = ''
+n = 0
+while n < 500:
+ buf += '.'
+ n += 1
+
+serverSocket.listen(MAX_PORTS)
+readList = [serverSocket]
+
+while True:
+ readyRead, readyWrite, inError = \
+ select.select(readList, [], [], 10)
+
+ if len(readyRead) > 0:
+ waitCount = 0
+ for sock in readyRead:
+ if sock == serverSocket:
+ (clientSocket, address) = serverSocket.accept()
+ address = str(address[0])
+ readList.append(clientSocket)
+ else:
+ s = read(sock, 1000)
+ n = send(sock, buf)
+ sock.close()
+ time.sleep(1)
+ sys.exit(0)
diff --git a/tools/testing/selftests/bpf/test_tcpbpf_kern.c
b/tools/testing/selftests/bpf/test_tcpbpf_kern.c
new file mode 100644
index 0000000..0fa7429
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_tcpbpf_kern.c
@@ -0,0 +1,125 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <stddef.h>
+#include <string.h>
+#include <linux/bpf.h>
+#include <linux/if_ether.h>
+#include <linux/if_packet.h>
+#include <linux/ip.h>
+#include <linux/in6.h>
+#include <linux/types.h>
+#include <linux/socket.h>
+#include <netinet/in.h>
+#include "bpf_helpers.h"
+#include "bpf_endian.h"
+
+struct globals {
+ __u32 event_map;
+ __u32 total_retrans;
+ __u32 data_segs_in;
+ __u32 data_segs_out;
+ __u64 bytes_received;
+ __u64 bytes_acked;
+};
+
+struct bpf_map_def SEC("maps") global_map = {
+ .type = BPF_MAP_TYPE_ARRAY,
+ .key_size = sizeof(__u32),
+ .value_size = sizeof(struct globals),
+ .max_entries = 2,
+};
+
+static inline void update_event_map(int event)
+{
+ __u32 key = 0;
+ struct globals g, *gp;
+
+ gp = bpf_map_lookup_elem(&global_map, &key);
+ if (gp == NULL) {
+ struct globals g = {0, 0, 0, 0, 0, 0};
+
+ g.event_map |= (1 << event);
+ bpf_map_update_elem(&global_map, &key, &g,
+ BPF_ANY);
+ } else {
+ g = *gp;
+ g.event_map |= (1 << event);
+ bpf_map_update_elem(&global_map, &key, &g,
+ BPF_ANY);
+ }
+}
+
+int _version SEC("version") = 1;
+
+SEC("sockops")
+int bpf_testcb(struct bpf_sock_ops *skops)
+{
+ int rv = -1;
+ int op;
+ int init_seq = 0;
+ int ret = 0;
+ int v = 0;
+
+ /* For testing purposes, only execute rest of BPF program
+ * if remote port number is in the range 12877..12887
+ * I.e. the active side of the connection
+ */
+ if ((bpf_ntohl(skops->remote_port) < 12877 ||
+ bpf_ntohl(skops->remote_port) >= 12887)) {
+ skops->reply = -1;
+ return 1;
+ }
+
+ op = (int) skops->op;
+
+ /* Check that both hosts are within same datacenter. For this example
+ * it is the case when the first 5.5 bytes of their IPv6 addresses are
+ * the same.
+ */
+ if (1) {
+ update_event_map(op);
+
+ switch (op) {
+ case BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB:
+ skops->bpf_sock_ops_flags = 0xfff;
+ init_seq = skops->snd_nxt;
+ break;
+ case BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB:
+ init_seq = skops->snd_nxt;
+ skops->bpf_sock_ops_flags = 0xfff;
+ skops->sk_txhash = 0x12345f;
+ v = 0xff;
+ ret = bpf_setsockopt(skops, SOL_IPV6, IPV6_TCLASS, &v,
+ sizeof(v));
+ break;
+ case BPF_SOCK_OPS_RTO_CB:
+ break;
+ case BPF_SOCK_OPS_RETRANS_CB:
+ break;
+ case BPF_SOCK_OPS_STATE_CB:
+ if (skops->args[1] == BPF_TCP_CLOSE) {
+ __u32 key = 0;
+ struct globals g, *gp;
+
+ gp = bpf_map_lookup_elem(&global_map, &key);
+ if (!gp)
+ break;
+ g = *gp;
+ g.total_retrans = skops->total_retrans;
+ g.data_segs_in = skops->data_segs_in;
+ g.data_segs_out = skops->data_segs_out;
+ g.bytes_received = skops->bytes_received;
+ g.bytes_acked = skops->bytes_acked;
+ bpf_map_update_elem(&global_map, &key, &g,
+ BPF_ANY);
+ }
+ break;
+ default:
+ rv = -1;
+ }
+ } else {
+ rv = -1;
+ }
+ skops->reply = rv;
+ return 1;
+}
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_tcpbpf_user.c
b/tools/testing/selftests/bpf/test_tcpbpf_user.c
new file mode 100644
index 0000000..38665ea
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_tcpbpf_user.c
@@ -0,0 +1,113 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <unistd.h>
+#include <errno.h>
+#include <signal.h>
+#include <string.h>
+#include <assert.h>
+#include <linux/perf_event.h>
+#include <linux/ptrace.h>
+#include <linux/bpf.h>
+#include <sys/ioctl.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+#include "bpf_util.h"
+#include <linux/perf_event.h>
+
+struct globals {
+ __u32 event_map;
+ __u32 total_retrans;
+ __u32 data_segs_in;
+ __u32 data_segs_out;
+ __u64 bytes_received;
+ __u64 bytes_acked;
+};
+
+static int bpf_find_map(const char *test, struct bpf_object *obj,
+ const char *name)
+{
+ struct bpf_map *map;
+
+ map = bpf_object__find_map_by_name(obj, name);
+ if (!map) {
+ printf("%s:FAIL:map '%s' not found\n", test, name);
+ return -1;
+ }
+ return bpf_map__fd(map);
+}
+
+#define SYSTEM(CMD) \
+ do { \
+ if (system(CMD)) { \
+ printf("system(%s) FAILS!\n", CMD); \
+ } \
+ } while (0)
+
+int main(int argc, char **argv)
+{
+ struct globals g = {0, 0, 0, 0, 0, 0};
+ __u32 key = 0;
+ int rv;
+ int pid;
+ int error = EXIT_FAILURE;
+ int cg_fd, prog_fd, map_fd;
+ char cmd[100], *dir;
+ const char *file = "test_tcpbpf_kern.o";
+ struct bpf_object *obj;
+ struct stat buffer;
+
+ dir = "/tmp/cgroupv2/foo";
+
+ if (stat(dir, &buffer) != 0) {
+ SYSTEM("mkdir -p /tmp/cgroupv2");
+ SYSTEM("mount -t cgroup2 none /tmp/cgroupv2");
+ SYSTEM("mkdir -p /tmp/cgroupv2/foo");
+ }
+ pid = (int) getpid();
+ sprintf(cmd, "echo %d >> /tmp/cgroupv2/foo/cgroup.procs", pid);
+ SYSTEM(cmd);
+
+ cg_fd = open(dir, O_DIRECTORY, O_RDONLY);
+ if (bpf_prog_load(file, BPF_PROG_TYPE_SOCK_OPS, &obj, &prog_fd)) {
+// if (load_bpf_file(prog)) {
+ printf("FAILED: load_bpf_file failed for: %s\n", file);
+// printf("%s", bpf_log_buf);
+ goto err;
+ }
+
+ rv = bpf_prog_attach(prog_fd, cg_fd, BPF_CGROUP_SOCK_OPS, 0);
+ if (rv) {
+ printf("FAILED: bpf_prog_attach: %d (%s)\n",
+ error, strerror(errno));
+ goto err;
+ }
+
+ SYSTEM("./tcp_server.py");
+
+ map_fd = bpf_find_map(__func__, obj, "global_map");
+ if (map_fd < 0)
+ goto err;
+
+ rv = bpf_map_lookup_elem(map_fd, &key, &g);
+ if (rv != 0) {
+ printf("FAILED: bpf_map_lookup_elem returns %d\n", rv);
+ goto err;
+ }
+
+ if (g.bytes_received != 501 || g.bytes_acked != 1002 ||
+ g.data_segs_in != 1 || g.data_segs_out != 1 ||
+ g.event_map != 0x45e) {
+ printf("FAILED: Wrong stats\n");
+ goto err;
+ }
+ printf("PASSED!\n");
+ error = 0;
+err:
+ bpf_prog_detach(cg_fd, BPF_CGROUP_SOCK_OPS);
+ return error;
+}
--
2.9.5
