wasi-sockets: Add services database and implement getservbyname/getservbyport functions (WebAssembly#532)

This is a follow-up PR for WebAssembly#524 by implementing the following features:

- Embeds a minimal network services database with 17 common protocols,
suggested by @badeend. The database array is a weak symbol allowing
applications to override the default database at link time.
- Updates `getaddrinfo` to resolve named services in the address info.
For example `getaddrinfo("google.com", "https", NULL, &res);`
- Implements the `getservbyname` and `getservbyport` functions. These
functions are implemented using a static variable (`global_serv`), which
holds the returned service entry. This approach is acceptable because
these functions [are defined as not being
thread-safe](https://man.archlinux.org/man/getservbyname.3.en).

~~Additionally, this PR introduces an optional, more comprehensive
services database (`sockets_full_services_db.c`), based on Debian
Bookworm's `/etc/services` file (320 entries). To use this database,
link with the `-lc-full-services-db` flag.~~

Author: Henkru

expected/wasm32-wasip2/defined-symbols.txt

@@ -333,10 +333,13 @@ __wasi_sock_accept
 __wasi_sock_recv
 __wasi_sock_send
 __wasi_sock_shutdown
+__wasi_sockets_services_db
 __wasi_sockets_utils__any_addr
 __wasi_sockets_utils__borrow_network
 __wasi_sockets_utils__create_streams
 __wasi_sockets_utils__drop_streams
+__wasi_sockets_utils__get_service_entry_by_name
+__wasi_sockets_utils__get_service_entry_by_port
 __wasi_sockets_utils__map_error
 __wasi_sockets_utils__output_addr_validate
 __wasi_sockets_utils__output_addr_write

libc-bottom-half/headers/private/wasi/sockets_utils.h

@@ -26,6 +26,17 @@ typedef struct {
 	};
 } output_sockaddr_t;
 
+typedef struct {
+	char *s_name;
+	uint16_t port;
+	uint16_t protocol;
+} service_entry_t;
+
+typedef enum {
+	SERVICE_PROTOCOL_TCP = 1,
+	SERVICE_PROTOCOL_UDP = 2
+} service_protocol_e;
+
 network_borrow_network_t __wasi_sockets_utils__borrow_network();
 int __wasi_sockets_utils__map_error(network_error_code_t wasi_error);
 bool __wasi_sockets_utils__parse_address(
@@ -50,5 +61,7 @@ bool __wasi_sockets_utils__stream(udp_socket_t *socket,
 				  network_error_code_t *error);
 void __wasi_sockets_utils__drop_streams(udp_socket_streams_t streams);
 int __wasi_sockets_utils__parse_port(const char *port);
+const service_entry_t *__wasi_sockets_utils__get_service_entry_by_name(const char *name);
+const service_entry_t *__wasi_sockets_utils__get_service_entry_by_port(const uint16_t port);
 
 #endif

libc-bottom-half/sources/netdb.c

@@ -7,6 +7,8 @@
 
 _Thread_local int h_errno = 0;
 
+static struct servent global_serv = { 0 };
+
 static int map_error(ip_name_lookup_error_code_t error)
 {
 	switch (error) {
@@ -27,6 +29,7 @@ static int map_error(ip_name_lookup_error_code_t error)
 
 static int add_addr(ip_name_lookup_option_ip_address_t address,
 		    in_port_t port,
+			int socktype,
 		    const struct addrinfo *restrict hint,
 		    struct addrinfo **restrict current,
 		    struct addrinfo **restrict res)
@@ -117,7 +120,7 @@ static int add_addr(ip_name_lookup_option_ip_address_t address,
 	*result = (struct addrinfo){
 		.ai_family = family,
 		.ai_flags = 0,
-		.ai_socktype = SOCK_STREAM,
+		.ai_socktype = socktype,
 		.ai_protocol = 0,
 		.ai_addrlen = addrlen,
 		.ai_addr = addr,
@@ -136,6 +139,29 @@ static int add_addr(ip_name_lookup_option_ip_address_t address,
         return 0;
 }
 
+static bool set_global_serv_entry(const service_entry_t *entry, const char *proto) {
+	if (!entry) {
+		return false; // Service not found
+	}
+
+	global_serv.s_name = entry->s_name;
+	global_serv.s_port = htons(entry->port);
+	global_serv.s_aliases = NULL;
+
+	// If proto is NULL then any protocol is matched
+	if ((!proto || strcmp(proto, "tcp") == 0) && entry->protocol & SERVICE_PROTOCOL_TCP) {
+		global_serv.s_proto = "tcp";
+	}
+	else if ((!proto || strcmp(proto, "udp") == 0) && entry->protocol & SERVICE_PROTOCOL_UDP) {
+		global_serv.s_proto = "udp";
+	}
+	else {
+		return false; // Protocol not supported
+	}
+
+	return true;
+}
+
 int getaddrinfo(const char *restrict host, const char *restrict serv,
 		const struct addrinfo *restrict hint,
 		struct addrinfo **restrict res)
@@ -155,27 +181,39 @@ int getaddrinfo(const char *restrict host, const char *restrict serv,
 		ip_name_lookup_borrow_resolve_address_stream_t stream_borrow =
 			ip_name_lookup_borrow_resolve_address_stream(stream);
 		// The 'serv' parameter can be either a port number or a service name.
-		//
-		// TODO wasi-sockets: If the conversion of 'serv' to a valid port
-		// number fails, use getservbyname() to resolve the service name to
-		// its corresponding port number. This can be done after the
-		// getservbyname function is implemented.)
 		int port = 0;
+		uint16_t protocol = SERVICE_PROTOCOL_TCP;
 		if (serv != NULL) {
 			port = __wasi_sockets_utils__parse_port(serv);
 			if (port < 0) {
-				return EAI_NONAME;
+				const service_entry_t *service = __wasi_sockets_utils__get_service_entry_by_name(serv);
+				if (service) {
+					port = service->port;
+					protocol = service->protocol;
+				}
+				else {
+					return EAI_NONAME;
+				}
 			}
 		}
 		while (true) {
 			ip_name_lookup_option_ip_address_t address;
 			if (ip_name_lookup_method_resolve_address_stream_resolve_next_address(
 				    stream_borrow, &address, &error)) {
 				if (address.is_some) {
-					int error = add_addr(address, htons(port), hint,
-							     &current, res);
-					if (error) {
-						return error;
+					if (protocol & SERVICE_PROTOCOL_TCP) {
+						int error = add_addr(address, htons(port), SOCK_STREAM,
+										hint, &current, res);
+						if (error) {
+							return error;
+						}
+					}
+					if (protocol & SERVICE_PROTOCOL_UDP) {
+						int error = add_addr(address, htons(port), SOCK_DGRAM,
+										hint, &current, res);
+						if (error) {
+							return error;
+						}
 					}
 				} else {
 					return 0;
@@ -236,14 +274,20 @@ const char *hstrerror(int err)
 
 struct servent *getservbyname(const char *name, const char *proto)
 {
-	// TODO wasi-sockets
-	return NULL;
+	const service_entry_t *entry = __wasi_sockets_utils__get_service_entry_by_name(name);
+	if (!set_global_serv_entry(entry, proto)) {
+		return NULL;
+	}
+	return &global_serv;
 }
 
 struct servent *getservbyport(int port, const char *proto)
 {
-	// TODO wasi-sockets
-	return NULL;
+	const service_entry_t *entry = __wasi_sockets_utils__get_service_entry_by_port(htons(port));
+	if (!set_global_serv_entry(entry, proto)) {
+		return NULL;
+	}
+	return &global_serv;
 }
 
 struct protoent *getprotobyname(const char *name)

libc-bottom-half/sources/sockets_utils.c

@@ -1,11 +1,33 @@
 #include <errno.h>
 #include <stdlib.h>
 #include <ctype.h>
+#include <string.h>
 
 #include <wasi/sockets_utils.h>
 
 static network_own_network_t global_network;
 static bool global_network_initialized = false;
+static const service_entry_t global_services[] = {
+    { "domain",      53,  SERVICE_PROTOCOL_TCP | SERVICE_PROTOCOL_UDP },
+    { "ftp",         21,  SERVICE_PROTOCOL_TCP },
+    { "ftp-data",    20,  SERVICE_PROTOCOL_TCP },
+    { "ftps",        990, SERVICE_PROTOCOL_TCP },
+    { "ftps-data",   989, SERVICE_PROTOCOL_TCP },
+    { "http",        80,  SERVICE_PROTOCOL_TCP | SERVICE_PROTOCOL_UDP },
+    { "https",       443, SERVICE_PROTOCOL_TCP | SERVICE_PROTOCOL_UDP },
+    { "imap",        143, SERVICE_PROTOCOL_TCP },
+    { "imaps",       993, SERVICE_PROTOCOL_TCP },
+    { "ntp",         123, SERVICE_PROTOCOL_TCP },
+    { "pop3",        110, SERVICE_PROTOCOL_TCP },
+    { "pop3s",       995, SERVICE_PROTOCOL_TCP },
+    { "smtp",        25,  SERVICE_PROTOCOL_TCP },
+    { "ssh",         22,  SERVICE_PROTOCOL_TCP },
+    { "submission",  587, SERVICE_PROTOCOL_TCP },
+    { "submissions", 465, SERVICE_PROTOCOL_TCP },
+    { "telnet",      23,  SERVICE_PROTOCOL_TCP },
+    { 0 },
+};
+weak_alias(global_services, __wasi_sockets_services_db);
 
 network_borrow_network_t __wasi_sockets_utils__borrow_network()
 {
@@ -482,3 +504,33 @@ int __wasi_sockets_utils__parse_port(const char *restrict port_str)
 
     return (int)port;
 }
+
+const service_entry_t *__wasi_sockets_utils__get_service_entry_by_name(const char *name)
+{
+    if (!name) {
+        return NULL;
+    }
+
+    const service_entry_t *entry = __wasi_sockets_services_db;
+    while(entry->s_name) {
+        if (strcmp(name, entry->s_name) == 0) {
+            return entry;
+        }
+        ++entry;
+    }
+
+    return NULL;
+}
+
+const service_entry_t *__wasi_sockets_utils__get_service_entry_by_port(const uint16_t port)
+{
+    const service_entry_t *entry = __wasi_sockets_services_db;
+    while(entry->s_name) {
+        if (entry->port == port) {
+            return entry;
+        }
+        ++entry;
+    }
+
+    return NULL;
+}