bpf: sockmap sample support for bpf_msg_cork_bytes()

Add sample application support for the bpf_msg_cork_bytes helper. This
lets the user specify how many bytes each verdict should apply to.

Similar to apply_bytes() tests these can be run as a stand-alone test
when used without other options or inline with other tests by using
the txmsg_cork option along with any of the basic tests txmsg,
txmsg_redir, txmsg_drop.

Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

samples/sockmap/sockmap_kern.c

@@ -64,6 +64,13 @@ struct bpf_map_def SEC("maps") sock_apply_bytes = {
 	.max_entries = 1
 };
 
+struct bpf_map_def SEC("maps") sock_cork_bytes = {
+	.type = BPF_MAP_TYPE_ARRAY,
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.max_entries = 1
+};
+
 SEC("sk_skb1")
 int bpf_prog1(struct __sk_buff *skb)
 {
@@ -135,6 +142,9 @@ int bpf_prog4(struct sk_msg_md *msg)
 	bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero);
 	if (bytes)
 		bpf_msg_apply_bytes(msg, *bytes);
+	bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero);
+	if (bytes)
+		bpf_msg_cork_bytes(msg, *bytes);
 	return SK_PASS;
 }
 
@@ -143,13 +153,16 @@ int bpf_prog5(struct sk_msg_md *msg)
 {
 	void *data_end = (void *)(long) msg->data_end;
 	void *data = (void *)(long) msg->data;
-	int *bytes, err = 0, zero = 0;
+	int *bytes, err1 = -1, err2 = -1, zero = 0;
 
 	bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero);
 	if (bytes)
-		err = bpf_msg_apply_bytes(msg, *bytes);
-	bpf_printk("sk_msg2: data length %i err %i\n",
-		   (__u64)data_end - (__u64)data, err);
+		err1 = bpf_msg_apply_bytes(msg, *bytes);
+	bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero);
+	if (bytes)
+		err2 = bpf_msg_cork_bytes(msg, *bytes);
+	bpf_printk("sk_msg2: data length %i err1 %i err2 %i\n",
+		   (__u64)data_end - (__u64)data, err1, err2);
 	return SK_PASS;
 }
 
@@ -163,6 +176,9 @@ int bpf_prog6(struct sk_msg_md *msg)
 	bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero);
 	if (bytes)
 		bpf_msg_apply_bytes(msg, *bytes);
+	bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero);
+	if (bytes)
+		bpf_msg_cork_bytes(msg, *bytes);
 	return bpf_msg_redirect_map(msg, &sock_map_redir, zero, 0);
 }
 
@@ -171,13 +187,17 @@ int bpf_prog7(struct sk_msg_md *msg)
 {
 	void *data_end = (void *)(long) msg->data_end;
 	void *data = (void *)(long) msg->data;
-	int *bytes, err = 0, zero = 0;
+	int *bytes, err1 = 0, err2 = 0, zero = 0;
 
 	bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero);
 	if (bytes)
-		err = bpf_msg_apply_bytes(msg, *bytes);
-	bpf_printk("sk_msg3: redirect(%iB) err=%i\n",
-		   (__u64)data_end - (__u64)data, err);
+		err1 = bpf_msg_apply_bytes(msg, *bytes);
+	bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero);
+	if (bytes)
+		err2 = bpf_msg_cork_bytes(msg, *bytes);
+
+	bpf_printk("sk_msg3: redirect(%iB) err1=%i err2=%i\n",
+		   (__u64)data_end - (__u64)data, err1, err2);
 	return bpf_msg_redirect_map(msg, &sock_map_redir, zero, 0);
 }
 
@@ -198,5 +218,22 @@ int bpf_prog8(struct sk_msg_md *msg)
 	}
 	return SK_PASS;
 }
+SEC("sk_msg6")
+int bpf_prog9(struct sk_msg_md *msg)
+{
+	void *data_end = (void *)(long) msg->data_end;
+	void *data = (void *)(long) msg->data;
+	int ret = 0, *bytes, zero = 0;
+
+	bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero);
+	if (bytes) {
+		if (((__u64)data_end - (__u64)data) >= *bytes)
+			return SK_PASS;
+		ret = bpf_msg_cork_bytes(msg, *bytes);
+		if (ret)
+			return SK_DROP;
+	}
+	return SK_PASS;
+}
 
 char _license[] SEC("license") = "GPL";

samples/sockmap/sockmap_user.c

@@ -60,6 +60,7 @@ int txmsg_noisy;
 int txmsg_redir;
 int txmsg_redir_noisy;
 int txmsg_apply;
+int txmsg_cork;
 
 static const struct option long_options[] = {
 	{"help",	no_argument,		NULL, 'h' },
@@ -75,6 +76,7 @@ static const struct option long_options[] = {
 	{"txmsg_redir",		no_argument,	&txmsg_redir, 1  },
 	{"txmsg_redir_noisy",	no_argument,	&txmsg_redir_noisy, 1},
 	{"txmsg_apply",	required_argument,	NULL, 'a'},
+	{"txmsg_cork",	required_argument,	NULL, 'k'},
 	{0, 0, NULL, 0 }
 };
 
@@ -551,6 +553,9 @@ int main(int argc, char **argv)
 		case 'a':
 			txmsg_apply = atoi(optarg);
 			break;
+		case 'k':
+			txmsg_cork = atoi(optarg);
+			break;
 		case 'c':
 			cg_fd = open(optarg, O_DIRECTORY, O_RDONLY);
 			if (cg_fd < 0) {
@@ -671,6 +676,8 @@ int main(int argc, char **argv)
 		tx_prog_fd = prog_fd[6];
 	else if (txmsg_apply)
 		tx_prog_fd = prog_fd[7];
+	else if (txmsg_cork)
+		tx_prog_fd = prog_fd[8];
 	else
 		tx_prog_fd = 0;
 
@@ -716,6 +723,18 @@ int main(int argc, char **argv)
 				return err;
 			}
 		}
+
+		if (txmsg_cork) {
+			err = bpf_map_update_elem(map_fd[4],
+						  &i, &txmsg_cork, BPF_ANY);
+			if (err) {
+				fprintf(stderr,
+					"ERROR: bpf_map_update_elem (cork_bytes):  %d (%s\n",
+					err, strerror(errno));
+				return err;
+			}
+		}
+
 	}
 	if (test == PING_PONG)
 		err = forever_ping_pong(rate, &options);

tools/include/uapi/linux/bpf.h

@@ -792,7 +792,8 @@ union bpf_attr {
 	FN(override_return),		\
 	FN(sock_ops_cb_flags_set),	\
 	FN(msg_redirect_map),		\
-	FN(msg_apply_bytes),
+	FN(msg_apply_bytes),		\
+	FN(msg_cork_bytes),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call

tools/testing/selftests/bpf/bpf_helpers.h

@@ -90,6 +90,8 @@ static int (*bpf_msg_redirect_map)(void *ctx, void *map, int key, int flags) =
 	(void *) BPF_FUNC_msg_redirect_map;
 static int (*bpf_msg_apply_bytes)(void *ctx, int len) =
 	(void *) BPF_FUNC_msg_apply_bytes;
+static int (*bpf_msg_cork_bytes)(void *ctx, int len) =
+	(void *) BPF_FUNC_msg_cork_bytes;
 
 /* llvm builtin functions that eBPF C program may use to
  * emit BPF_LD_ABS and BPF_LD_IND instructions