bpf: add selftest for tcpbpf

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
Adding the flag "-d" will show why it did not pass.
Signed-off-by: Lawrence Brakmo <brakmo@fb.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

tools/include/uapi/linux/bpf.h

@@ -17,7 +17,7 @@
 #define BPF_ALU64	0x07	/* alu mode in double word width */
 
 /* ld/ldx fields */
-#define BPF_DW		0x18	/* double word */
+#define BPF_DW		0x18	/* double word (64-bit) */
 #define BPF_XADD	0xc0	/* exclusive add */
 
 /* alu/jmp fields */
@@ -642,6 +642,14 @@ union bpf_attr {
  *     @optlen: length of optval in bytes
  *     Return: 0 or negative error
  *
+ * int bpf_sock_ops_cb_flags_set(bpf_sock_ops, flags)
+ *     Set callback flags for sock_ops
+ *     @bpf_sock_ops: pointer to bpf_sock_ops_kern struct
+ *     @flags: flags value
+ *     Return: 0 for no error
+ *             -EINVAL if there is no full tcp socket
+ *             bits in flags that are not supported by current kernel
+ *
  * int bpf_skb_adjust_room(skb, len_diff, mode, flags)
  *     Grow or shrink room in sk_buff.
  *     @skb: pointer to skb
@@ -748,7 +756,8 @@ union bpf_attr {
 	FN(perf_event_read_value),	\
 	FN(perf_prog_read_value),	\
 	FN(getsockopt),			\
-	FN(override_return),
+	FN(override_return),		\
+	FN(sock_ops_cb_flags_set),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
@@ -952,8 +961,9 @@ 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 */
@@ -968,8 +978,39 @@ struct bpf_sock_ops {
 				 */
 	__u32 snd_cwnd;
 	__u32 srtt_us;		/* Averaged RTT << 3 in usecs */
+	__u32 bpf_sock_ops_cb_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;
+	__u32 lost_out;
+	__u32 sacked_out;
+	__u32 sk_txhash;
+	__u64 bytes_received;
+	__u64 bytes_acked;
 };
 
+/* Definitions for bpf_sock_ops_cb_flags */
+#define BPF_SOCK_OPS_RTO_CB_FLAG	(1<<0)
+#define BPF_SOCK_OPS_RETRANS_CB_FLAG	(1<<1)
+#define BPF_SOCK_OPS_STATE_CB_FLAG	(1<<2)
+#define BPF_SOCK_OPS_ALL_CB_FLAGS       0x7		/* Mask of all currently
+							 * supported cb flags
+							 */
+
 /* List of known BPF sock_ops operators.
  * New entries can only be added at the end
  */
@@ -1003,6 +1044,43 @@ 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
+					 * Arg3: return value of
+					 *       tcp_transmit_skb (0 => success)
+					 */
+	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 */

tools/testing/selftests/bpf/Makefile

@@ -14,13 +14,13 @@ 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_stacktrace_map.o \
-	sample_map_ret0.o
+	sample_map_ret0.o test_tcpbpf_kern.o
 
 TEST_PROGS := test_kmod.sh test_xdp_redirect.sh test_xdp_meta.sh \
 	test_offload.py

tools/testing/selftests/bpf/bpf_helpers.h

@@ -71,6 +71,8 @@ static int (*bpf_setsockopt)(void *ctx, int level, int optname, void *optval,
 static int (*bpf_getsockopt)(void *ctx, int level, int optname, void *optval,
 			     int optlen) =
 	(void *) BPF_FUNC_getsockopt;
+static int (*bpf_sock_ops_cb_flags_set)(void *ctx, int flags) =
+	(void *) BPF_FUNC_sock_ops_cb_flags_set;
 static int (*bpf_sk_redirect_map)(void *ctx, void *map, int key, int flags) =
 	(void *) BPF_FUNC_sk_redirect_map;
 static int (*bpf_sock_map_update)(void *map, void *key, void *value,

tools/testing/selftests/bpf/tcp_client.py

+#!/usr/bin/env python2
+#
+# 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()
+
+# 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
+
+sock.settimeout(1);
+n = send(sock, buf)
+n = read(sock, 500)
+sys.exit(0)

tools/testing/selftests/bpf/tcp_server.py

+#!/usr/bin/env python2
+#
+# 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()
+
+try: serverSocket.bind((host, 0))
+except socket.error as msg:
+    print 'bind fails: ', msg
+
+sn = serverSocket.getsockname()
+serverPort = sn[1]
+
+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, [], [], 2)
+
+    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:
+                sock.settimeout(1);
+                s = read(sock, 1000)
+                n = send(sock, buf)
+                sock.close()
+                serverSocket.close()
+                sys.exit(0)
+    else:
+        print 'Select timeout!'
+        sys.exit(1)

tools/testing/selftests/bpf/test_tcpbpf.h

+// SPDX-License-Identifier: GPL-2.0
+
+#ifndef _TEST_TCPBPF_H
+#define _TEST_TCPBPF_H
+
+struct tcpbpf_globals {
+	__u32 event_map;
+	__u32 total_retrans;
+	__u32 data_segs_in;
+	__u32 data_segs_out;
+	__u32 bad_cb_test_rv;
+	__u32 good_cb_test_rv;
+	__u64 bytes_received;
+	__u64 bytes_acked;
+};
+#endif

tools/testing/selftests/bpf/test_tcpbpf_kern.c

+// 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 <linux/tcp.h>
+#include <netinet/in.h>
+#include "bpf_helpers.h"
+#include "bpf_endian.h"
+#include "test_tcpbpf.h"
+
+struct bpf_map_def SEC("maps") global_map = {
+	.type = BPF_MAP_TYPE_ARRAY,
+	.key_size = sizeof(__u32),
+	.value_size = sizeof(struct tcpbpf_globals),
+	.max_entries = 2,
+};
+
+static inline void update_event_map(int event)
+{
+	__u32 key = 0;
+	struct tcpbpf_globals g, *gp;
+
+	gp = bpf_map_lookup_elem(&global_map, &key);
+	if (gp == NULL) {
+		struct tcpbpf_globals g = {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 bad_call_rv = 0;
+	int good_call_rv = 0;
+	int op;
+	int v = 0;
+
+	op = (int) skops->op;
+
+	update_event_map(op);
+
+	switch (op) {
+	case BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB:
+		/* Test failure to set largest cb flag (assumes not defined) */
+		bad_call_rv = bpf_sock_ops_cb_flags_set(skops, 0x80);
+		/* Set callback */
+		good_call_rv = bpf_sock_ops_cb_flags_set(skops,
+						 BPF_SOCK_OPS_STATE_CB_FLAG);
+		/* Update results */
+		{
+			__u32 key = 0;
+			struct tcpbpf_globals g, *gp;
+
+			gp = bpf_map_lookup_elem(&global_map, &key);
+			if (!gp)
+				break;
+			g = *gp;
+			g.bad_cb_test_rv = bad_call_rv;
+			g.good_cb_test_rv = good_call_rv;
+			bpf_map_update_elem(&global_map, &key, &g,
+					    BPF_ANY);
+		}
+		break;
+	case BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB:
+		/* Set callback */
+//		good_call_rv = bpf_sock_ops_cb_flags_set(skops,
+//						 BPF_SOCK_OPS_STATE_CB_FLAG);
+		skops->sk_txhash = 0x12345f;
+		v = 0xff;
+		rv = 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 tcpbpf_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;
+	}
+	skops->reply = rv;
+	return 1;
+}
+char _license[] SEC("license") = "GPL";

tools/testing/selftests/bpf/test_tcpbpf_user.c

+// 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>
+#include "test_tcpbpf.h"
+
+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)
+{
+	const char *file = "test_tcpbpf_kern.o";
+	struct tcpbpf_globals g = {0};
+	int cg_fd, prog_fd, map_fd;
+	bool debug_flag = false;
+	int error = EXIT_FAILURE;
+	struct bpf_object *obj;
+	char cmd[100], *dir;
+	struct stat buffer;
+	__u32 key = 0;
+	int pid;
+	int rv;
+
+	if (argc > 1 && strcmp(argv[1], "-d") == 0)
+		debug_flag = true;
+
+	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)) {
+		printf("FAILED: load_bpf_file failed for: %s\n", file);
+		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 ^ 0x47e) != 0 || g.bad_cb_test_rv != 0x80 ||
+		g.good_cb_test_rv != 0) {
+		printf("FAILED: Wrong stats\n");
+		if (debug_flag) {
+			printf("\n");
+			printf("bytes_received: %d (expecting 501)\n",
+			       (int)g.bytes_received);
+			printf("bytes_acked:    %d (expecting 1002)\n",
+			       (int)g.bytes_acked);
+			printf("data_segs_in:   %d (expecting 1)\n",
+			       g.data_segs_in);
+			printf("data_segs_out:  %d (expecting 1)\n",
+			       g.data_segs_out);
+			printf("event_map:      0x%x (at least 0x47e)\n",
+			       g.event_map);
+			printf("bad_cb_test_rv: 0x%x (expecting 0x80)\n",
+			       g.bad_cb_test_rv);
+			printf("good_cb_test_rv:0x%x (expecting 0)\n",
+			       g.good_cb_test_rv);
+		}
+		goto err;
+	}
+	printf("PASSED!\n");
+	error = 0;
+err:
+	bpf_prog_detach(cg_fd, BPF_CGROUP_SOCK_OPS);
+	return error;
+
+}