getaddrinfo: add EAI_NODATA error code to distinguish NODATA vs NxDomain

this was apparently omitted long ago out of a lack of understanding of
its importance and the fact that POSIX doesn't specify it. despite not
being officially standardized, however, it turns out that at least
AIX, glibc, NetBSD, OpenBSD, QNX, and Solaris document and support it.

in certain usage cases, such as implementing a DNS gateway on top of
the stub resolver interfaces, it's necessary to distinguish the case
where a name does not exit (NxDomain) from one where it exists but has
no addresses (or other records) of the requested type (NODATA). in
fact, even the legacy gethostbyname API had this distinction, which we
were previously unable to support correctly because the backend lacked
it.

apart from fixing an important functionality gap, adding this
distinction helps clarify to users how search domain fallback works
(falling back in cases corresponding to EAI_NONAME, not in ones
corresponding to EAI_NODATA), a topic that has been a source of
ongoing confusion and frustration.

as a result of this change, EAI_NONAME is no longer a valid universal
error code for getaddrinfo in the case where AI_ADDRCONFIG has
suppressed use of all address families. in order to return an accurate
result in this case, getaddrinfo is modified to still perform at least
one lookup. this will almost surely fail (with a network error, since
there is no v4 or v6 network to query DNS over) unless a result comes
from the hosts file or from ip literal parsing, but in case it does
succeed, the result is replaced by EAI_NODATA.

glibc has a related error code, EAI_ADDRFAMILY, that could be used for
the AI_ADDRCONFIG case and certain NODATA cases, but distinguishing
them properly in full generality seems to require additional DNS
queries that are otherwise not useful. on glibc, it is only used for
ip literals with mismatching family, not for DNS or hosts file results
where the name has addresses only in the opposite family. since this
seems misleading and inconsistent, and since EAI_NODATA already covers
the semantic case where the "name" exists but doesn't have any
addresses in the requested family, we do not adopt EAI_ADDRFAMILY at
this time. this could be changed at some point if desired, but the
logic for getting all the corner cases with AI_ADDRCONFIG right is
slightly nontrivial.

5 files changed, 12 insertions, 6 deletions

diff --git a/src/network/gai_strerror.c b/src/network/gai_strerror.c
index 9596580..56b7150 100644
--- a/src/network/gai_strerror.c
+++ b/src/network/gai_strerror.c
@@ -6,7 +6,7 @@ static const char msgs[] =
 	"Name does not resolve\0"
 	"Try again\0"
 	"Non-recoverable error\0"
-	"Unknown error\0"
+	"Name has no usable address\0"
 	"Unrecognized address family or invalid length\0"
 	"Unrecognized socket type\0"
 	"Unrecognized service\0"
diff --git a/src/network/getaddrinfo.c b/src/network/getaddrinfo.c
index 9df045f..64ad259 100644
--- a/src/network/getaddrinfo.c
+++ b/src/network/getaddrinfo.c
@@ -16,6 +16,7 @@ int getaddrinfo(const char *restrict host, const char *restrict serv, const stru
 	char canon[256], *outcanon;
 	int nservs, naddrs, nais, canon_len, i, j, k;
 	int family = AF_UNSPEC, flags = 0, proto = 0, socktype = 0;
+	int no_family = 0;
 	struct aibuf *out;
 
 	if (!host && !serv) return EAI_NONAME;
@@ -82,7 +83,7 @@ int getaddrinfo(const char *restrict host, const char *restrict serv, const stru
 			default:
 				return EAI_SYSTEM;
 			}
-			if (family == tf[i]) return EAI_NONAME;
+			if (family == tf[i]) no_family = 1;
 			family = tf[1-i];
 		}
 	}
@@ -93,6 +94,8 @@ int getaddrinfo(const char *restrict host, const char *restrict serv, const stru
 	naddrs = __lookup_name(addrs, canon, host, family, flags);
 	if (naddrs < 0) return naddrs;
 
+	if (no_family) return EAI_NODATA;
+
 	nais = nservs * naddrs;
 	canon_len = strlen(canon);
 	out = calloc(1, nais * sizeof(*out) + canon_len + 1);
diff --git a/src/network/gethostbyname2_r.c b/src/network/gethostbyname2_r.c
index c9f3acc..a5eb67f 100644
--- a/src/network/gethostbyname2_r.c
+++ b/src/network/gethostbyname2_r.c
@@ -23,6 +23,9 @@ int gethostbyname2_r(const char *name, int af,
 	case EAI_NONAME:
 		*err = HOST_NOT_FOUND;
 		return 0;
+	case EAI_NODATA:
+		*err = NO_DATA;
+		return 0;
 	case EAI_AGAIN:
 		*err = TRY_AGAIN;
 		return EAGAIN;
diff --git a/src/network/lookup_ipliteral.c b/src/network/lookup_ipliteral.c
index 2fddab7..1e76620 100644
--- a/src/network/lookup_ipliteral.c
+++ b/src/network/lookup_ipliteral.c
@@ -15,7 +15,7 @@ int __lookup_ipliteral(struct address buf[static 1], const char *name, int famil
 	struct in6_addr a6;
 	if (__inet_aton(name, &a4) > 0) {
 		if (family == AF_INET6) /* wrong family */
-			return EAI_NONAME;
+			return EAI_NODATA;
 		memcpy(&buf[0].addr, &a4, sizeof a4);
 		buf[0].family = AF_INET;
 		buf[0].scopeid = 0;
@@ -34,7 +34,7 @@ int __lookup_ipliteral(struct address buf[static 1], const char *name, int famil
 	if (inet_pton(AF_INET6, name, &a6) <= 0)
 		return 0;
 	if (family == AF_INET) /* wrong family */
-		return EAI_NONAME;
+		return EAI_NODATA;
 
 	memcpy(&buf[0].addr, &a6, sizeof a6);
 	buf[0].family = AF_INET6;
diff --git a/src/network/lookup_name.c b/src/network/lookup_name.c
index bec6ba2..37d481f 100644
--- a/src/network/lookup_name.c
+++ b/src/network/lookup_name.c
@@ -79,7 +79,7 @@ static int name_from_hosts(struct address buf[static MAXADDRS], char canon[stati
 		case 0:
 			continue;
 		default:
-			badfam = EAI_NONAME;
+			badfam = EAI_NODATA;
 			break;
 		}
 
@@ -175,7 +175,7 @@ static int name_from_dns(struct address buf[static MAXADDRS], char canon[static
 		__dns_parse(abuf[i], alens[i], dns_parse_callback, &ctx);
 
 	if (ctx.cnt) return ctx.cnt;
-	return EAI_NONAME;
+	return EAI_NODATA;
 }
 
 static int name_from_dns_search(struct address buf[static MAXADDRS], char canon[static 256], const char *name, int family)