selftests/bpf: Make sure optvals > PAGE_SIZE are bypassed

We are relying on the fact, that we can pass > sizeof(int) optvals
to the SOL_IP+IP_FREEBIND option (the kernel will take first 4 bytes).
In the BPF program we check that we can only touch PAGE_SIZE bytes,
but the real optlen is PAGE_SIZE * 2. In both cases, we override it to
some predefined value and trim the optlen.

Also, let's modify exiting IP_TOS usecase to test optlen=0 case
where BPF program just bypasses the data as is.

Signed-off-by: Stanislav Fomichev <[e-mail]>
Signed-off-by: Alexei Starovoitov <[e-mail]>
Link: https://lore.kernel.org/bpf/[e-mail]

tools/testing/selftests/bpf/prog_tests/sockopt_sk.c

···
 		char cc[16]; /* TCP_CA_NAME_MAX */
 	} buf = {};
 	socklen_t optlen;
+	char *big_buf = NULL;
 
 	fd = socket(AF_INET, SOCK_STREAM, 0);
 	if (fd < 0) {
···
 
 	/* IP_TOS - BPF bypass */
 
-	buf.u8[0] = 0x08;
-	err = setsockopt(fd, SOL_IP, IP_TOS, &buf, 1);
+	optlen = getpagesize() * 2;
+	big_buf = calloc(1, optlen);
+	if (!big_buf) {
+		log_err("Couldn't allocate two pages");
+		goto err;
+	}
+
+	*(int *)big_buf = 0x08;
+	err = setsockopt(fd, SOL_IP, IP_TOS, big_buf, optlen);
 	if (err) {
 		log_err("Failed to call setsockopt(IP_TOS)");
 		goto err;
 	}
 
-	buf.u8[0] = 0x00;
+	memset(big_buf, 0, optlen);
 	optlen = 1;
-	err = getsockopt(fd, SOL_IP, IP_TOS, &buf, &optlen);
+	err = getsockopt(fd, SOL_IP, IP_TOS, big_buf, &optlen);
 	if (err) {
 		log_err("Failed to call getsockopt(IP_TOS)");
 		goto err;
 	}
 
-	if (buf.u8[0] != 0x08) {
-		log_err("Unexpected getsockopt(IP_TOS) buf[0] 0x%02x != 0x08",
-			buf.u8[0]);
+	if (*(int *)big_buf != 0x08) {
+		log_err("Unexpected getsockopt(IP_TOS) optval 0x%x != 0x08",
+			*(int *)big_buf);
 		goto err;
 	}
 
···
 	if (buf.u8[0] != 0x01) {
 		log_err("Unexpected buf[0] 0x%02x != 0x01", buf.u8[0]);
 		goto err;
+	}
+
+	/* IP_FREEBIND - BPF can't access optval past PAGE_SIZE */
+
+	optlen = getpagesize() * 2;
+	memset(big_buf, 0, optlen);
+
+	err = setsockopt(fd, SOL_IP, IP_FREEBIND, big_buf, optlen);
+	if (err != 0) {
+		log_err("Failed to call setsockopt, ret=%d", err);
+		goto err;
+	}
+
+	err = getsockopt(fd, SOL_IP, IP_FREEBIND, big_buf, &optlen);
+	if (err != 0) {
+		log_err("Failed to call getsockopt, ret=%d", err);
+		goto err;
+	}
+
+	if (optlen != 1 || *(__u8 *)big_buf != 0x55) {
+		log_err("Unexpected IP_FREEBIND getsockopt, optlen=%d, optval=0x%x",
+			optlen, *(__u8 *)big_buf);
 	}
 
 	/* SO_SNDBUF is overwritten */
···
 		goto err;
 	}
 
+	free(big_buf);
 	close(fd);
 	return 0;
 err:
+	free(big_buf);
 	close(fd);
 	return -1;
 }

tools/testing/selftests/bpf/progs/sockopt_sk.c

···
 char _license[] SEC("license") = "GPL";
 __u32 _version SEC("version") = 1;
 
+#ifndef PAGE_SIZE
+#define PAGE_SIZE 4096
+#endif
+
 #define SOL_CUSTOM			0xdeadbeef
 
 struct sockopt_sk {
···
 	__u8 *optval = ctx->optval;
 	struct sockopt_sk *storage;
 
-	if (ctx->level == SOL_IP && ctx->optname == IP_TOS)
+	if (ctx->level == SOL_IP && ctx->optname == IP_TOS) {
 		/* Not interested in SOL_IP:IP_TOS;
 		 * let next BPF program in the cgroup chain or kernel
 		 * handle it.
 		 */
+		ctx->optlen = 0; /* bypass optval>PAGE_SIZE */
 		return 1;
+	}
 
 	if (ctx->level == SOL_SOCKET && ctx->optname == SO_SNDBUF) {
 		/* Not interested in SOL_SOCKET:SO_SNDBUF;
···
 		 * let next BPF program in the cgroup chain or kernel
 		 * handle it.
 		 */
+		return 1;
+	}
+
+	if (ctx->level == SOL_IP && ctx->optname == IP_FREEBIND) {
+		if (optval + 1 > optval_end)
+			return 0; /* EPERM, bounds check */
+
+		ctx->retval = 0; /* Reset system call return value to zero */
+
+		/* Always export 0x55 */
+		optval[0] = 0x55;
+		ctx->optlen = 1;
+
+		/* Userspace buffer is PAGE_SIZE * 2, but BPF
+		 * program can only see the first PAGE_SIZE
+		 * bytes of data.
+		 */
+		if (optval_end - optval != PAGE_SIZE)
+			return 0; /* EPERM, unexpected data size */
+
 		return 1;
 	}
 
···
 	__u8 *optval = ctx->optval;
 	struct sockopt_sk *storage;
 
-	if (ctx->level == SOL_IP && ctx->optname == IP_TOS)
+	if (ctx->level == SOL_IP && ctx->optname == IP_TOS) {
 		/* Not interested in SOL_IP:IP_TOS;
 		 * let next BPF program in the cgroup chain or kernel
 		 * handle it.
 		 */
+		ctx->optlen = 0; /* bypass optval>PAGE_SIZE */
 		return 1;
+	}
 
 	if (ctx->level == SOL_SOCKET && ctx->optname == SO_SNDBUF) {
 		/* Overwrite SO_SNDBUF value */
···
 
 		memcpy(optval, "cubic", 5);
 		ctx->optlen = 5;
+
+		return 1;
+	}
+
+	if (ctx->level == SOL_IP && ctx->optname == IP_FREEBIND) {
+		/* Original optlen is larger than PAGE_SIZE. */
+		if (ctx->optlen != PAGE_SIZE * 2)
+			return 0; /* EPERM, unexpected data size */
+
+		if (optval + 1 > optval_end)
+			return 0; /* EPERM, bounds check */
+
+		/* Make sure we can trim the buffer. */
+		optval[0] = 0;
+		ctx->optlen = 1;
+
+		/* Usepace buffer is PAGE_SIZE * 2, but BPF
+		 * program can only see the first PAGE_SIZE
+		 * bytes of data.
+		 */
+		if (optval_end - optval != PAGE_SIZE)
+			return 0; /* EPERM, unexpected data size */
 
 		return 1;
 	}