sctp: Fixup v4mapped behaviour to comply with Sock API
The SCTP socket extensions API document describes the v4mapping option as
follows:
8.1.15. Set/Clear IPv4 Mapped Addresses (SCTP_I_WANT_MAPPED_V4_ADDR)
This socket option is a Boolean flag which turns on or off the
mapping of IPv4 addresses. If this option is turned on, then IPv4
addresses will be mapped to V6 representation. If this option is
turned off, then no mapping will be done of V4 addresses and a user
will receive both PF_INET6 and PF_INET type addresses on the socket.
See [RFC3542] for more details on mapped V6 addresses.
This description isn't really in line with what the code does though.
Introduce addr_to_user (renamed addr_v4map), which should be called
before any sockaddr is passed back to user space. The new function
places the sockaddr into the correct format depending on the
SCTP_I_WANT_MAPPED_V4_ADDR option.
Audit all places that touched v4mapped and either sanely construct
a v4 or v6 address then call addr_to_user, or drop the
unnecessary v4mapped check entirely.
Audit all places that call addr_to_user and verify they are on a sycall
return path.
Add a custom getname that formats the address properly.
Several bugs are addressed:
- SCTP_I_WANT_MAPPED_V4_ADDR=0 often returned garbage for
addresses to user space
- The addr_len returned from recvmsg was not correct when
returning AF_INET on a v6 socket
- flowlabel and scope_id were not zerod when promoting
a v4 to v6
- Some syscalls like bind and connect behaved differently
depending on v4mapped
Tested bind, getpeername, getsockname, connect, and recvmsg for proper
behaviour in v4mapped = 1 and 0 cases.
Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
Tested-by: Jason Gunthorpe <jgunthorpe@obsidianresearch.com>
Signed-off-by: Jason Gunthorpe <jgunthorpe@obsidianresearch.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 743308f..eb71d49 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -254,7 +254,7 @@
if (id_asoc && (id_asoc != addr_asoc))
return NULL;
- sctp_get_pf_specific(sk->sk_family)->addr_v4map(sctp_sk(sk),
+ sctp_get_pf_specific(sk->sk_family)->addr_to_user(sctp_sk(sk),
(union sctp_addr *)addr);
return transport;
@@ -396,7 +396,7 @@
/* Copy back into socket for getsockname() use. */
if (!ret) {
inet_sk(sk)->inet_sport = htons(inet_sk(sk)->inet_num);
- af->to_sk_saddr(addr, sk);
+ sp->pf->to_sk_saddr(addr, sk);
}
return ret;
@@ -1053,7 +1053,6 @@
struct sctp_association *asoc2;
struct sctp_transport *transport;
union sctp_addr to;
- struct sctp_af *af;
sctp_scope_t scope;
long timeo;
int err = 0;
@@ -1081,6 +1080,8 @@
/* Walk through the addrs buffer and count the number of addresses. */
addr_buf = kaddrs;
while (walk_size < addrs_size) {
+ struct sctp_af *af;
+
if (walk_size + sizeof(sa_family_t) > addrs_size) {
err = -EINVAL;
goto out_free;
@@ -1205,8 +1206,7 @@
/* Initialize sk's dport and daddr for getpeername() */
inet_sk(sk)->inet_dport = htons(asoc->peer.port);
- af = sctp_get_af_specific(sa_addr->sa.sa_family);
- af->to_sk_daddr(sa_addr, sk);
+ sp->pf->to_sk_daddr(sa_addr, sk);
sk->sk_err = 0;
/* in-kernel sockets don't generally have a file allocated to them
@@ -4255,7 +4255,7 @@
memcpy(&status.sstat_primary.spinfo_address, &transport->ipaddr,
transport->af_specific->sockaddr_len);
/* Map ipv4 address into v4-mapped-on-v6 address. */
- sctp_get_pf_specific(sk->sk_family)->addr_v4map(sctp_sk(sk),
+ sctp_get_pf_specific(sk->sk_family)->addr_to_user(sctp_sk(sk),
(union sctp_addr *)&status.sstat_primary.spinfo_address);
status.sstat_primary.spinfo_state = transport->state;
status.sstat_primary.spinfo_cwnd = transport->cwnd;
@@ -4413,8 +4413,8 @@
int sctp_do_peeloff(struct sock *sk, sctp_assoc_t id, struct socket **sockp)
{
struct sctp_association *asoc = sctp_id2assoc(sk, id);
+ struct sctp_sock *sp = sctp_sk(sk);
struct socket *sock;
- struct sctp_af *af;
int err = 0;
if (!asoc)
@@ -4436,8 +4436,7 @@
/* Make peeled-off sockets more like 1-1 accepted sockets.
* Set the daddr and initialize id to something more random
*/
- af = sctp_get_af_specific(asoc->peer.primary_addr.sa.sa_family);
- af->to_sk_daddr(&asoc->peer.primary_addr, sk);
+ sp->pf->to_sk_daddr(&asoc->peer.primary_addr, sk);
/* Populate the fields of the newsk from the oldsk and migrate the
* asoc to the newsk.
@@ -4821,8 +4820,8 @@
list_for_each_entry(from, &asoc->peer.transport_addr_list,
transports) {
memcpy(&temp, &from->ipaddr, sizeof(temp));
- sctp_get_pf_specific(sk->sk_family)->addr_v4map(sp, &temp);
- addrlen = sctp_get_af_specific(temp.sa.sa_family)->sockaddr_len;
+ addrlen = sctp_get_pf_specific(sk->sk_family)
+ ->addr_to_user(sp, &temp);
if (space_left < addrlen)
return -ENOMEM;
if (copy_to_user(to, &temp, addrlen))
@@ -4866,9 +4865,9 @@
if (!temp.v4.sin_port)
temp.v4.sin_port = htons(port);
- sctp_get_pf_specific(sk->sk_family)->addr_v4map(sctp_sk(sk),
- &temp);
- addrlen = sctp_get_af_specific(temp.sa.sa_family)->sockaddr_len;
+ addrlen = sctp_get_pf_specific(sk->sk_family)
+ ->addr_to_user(sctp_sk(sk), &temp);
+
if (space_left < addrlen) {
cnt = -ENOMEM;
break;
@@ -4956,8 +4955,8 @@
*/
list_for_each_entry(addr, &bp->address_list, list) {
memcpy(&temp, &addr->a, sizeof(temp));
- sctp_get_pf_specific(sk->sk_family)->addr_v4map(sp, &temp);
- addrlen = sctp_get_af_specific(temp.sa.sa_family)->sockaddr_len;
+ addrlen = sctp_get_pf_specific(sk->sk_family)
+ ->addr_to_user(sp, &temp);
if (space_left < addrlen) {
err = -ENOMEM; /*fixme: right error?*/
goto out;
@@ -5016,7 +5015,7 @@
memcpy(&prim.ssp_addr, &asoc->peer.primary_path->ipaddr,
asoc->peer.primary_path->af_specific->sockaddr_len);
- sctp_get_pf_specific(sk->sk_family)->addr_v4map(sp,
+ sctp_get_pf_specific(sk->sk_family)->addr_to_user(sp,
(union sctp_addr *)&prim.ssp_addr);
if (put_user(len, optlen))
