8 files changed, 160 insertions, 149 deletions

diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index 5ae609200674..ee13d28d39d1 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -1239,78 +1239,107 @@ void sctp_assoc_update(struct sctp_association *asoc,
 }
 
 /* Update the retran path for sending a retransmitted packet.
- * Round-robin through the active transports, else round-robin
- * through the inactive transports as this is the next best thing
- * we can try.
+ * See also RFC4960, 6.4. Multi-Homed SCTP Endpoints:
+ *
+ *   When there is outbound data to send and the primary path
+ *   becomes inactive (e.g., due to failures), or where the
+ *   SCTP user explicitly requests to send data to an
+ *   inactive destination transport address, before reporting
+ *   an error to its ULP, the SCTP endpoint should try to send
+ *   the data to an alternate active destination transport
+ *   address if one exists.
+ *
+ *   When retransmitting data that timed out, if the endpoint
+ *   is multihomed, it should consider each source-destination
+ *   address pair in its retransmission selection policy.
+ *   When retransmitting timed-out data, the endpoint should
+ *   attempt to pick the most divergent source-destination
+ *   pair from the original source-destination pair to which
+ *   the packet was transmitted.
+ *
+ *   Note: Rules for picking the most divergent source-destination
+ *   pair are an implementation decision and are not specified
+ *   within this document.
+ *
+ * Our basic strategy is to round-robin transports in priorities
+ * according to sctp_state_prio_map[] e.g., if no such
+ * transport with state SCTP_ACTIVE exists, round-robin through
+ * SCTP_UNKNOWN, etc. You get the picture.
  */
-void sctp_assoc_update_retran_path(struct sctp_association *asoc)
+static const u8 sctp_trans_state_to_prio_map[] = {
+        [SCTP_ACTIVE]   = 3,    /* best case */
+        [SCTP_UNKNOWN]  = 2,
+        [SCTP_PF]       = 1,
+        [SCTP_INACTIVE] = 0,    /* worst case */
+};
+
+static u8 sctp_trans_score(const struct sctp_transport *trans)
 {
-        struct sctp_transport *t, *next;
-        struct list_head *head = &asoc->peer.transport_addr_list;
-        struct list_head *pos;
+        return sctp_trans_state_to_prio_map[trans->state];
+}
 
-        if (asoc->peer.transport_count == 1)
-                return;
+static struct sctp_transport *sctp_trans_elect_best(struct sctp_transport *curr,
+                                                    struct sctp_transport *best)
+{
+        if (best == NULL)
+                return curr;
 
-        /* Find the next transport in a round-robin fashion. */
-        t = asoc->peer.retran_path;
-        pos = &t->transports;
-        next = NULL;
+        return sctp_trans_score(curr) > sctp_trans_score(best) ? curr : best;
+}
 
-        while (1) {
-                /* Skip the head. */
-                if (pos->next == head)
-                        pos = head->next;
-                else
-                        pos = pos->next;
+void sctp_assoc_update_retran_path(struct sctp_association *asoc)
+{
+        struct sctp_transport *trans = asoc->peer.retran_path;
+        struct sctp_transport *trans_next = NULL;
 
-                t = list_entry(pos, struct sctp_transport, transports);
+        /* We're done as we only have the one and only path. */
+        if (asoc->peer.transport_count == 1)
+                return;
+        /* If active_path and retran_path are the same and active,
+         * then this is the only active path. Use it.
+         */
+        if (asoc->peer.active_path == asoc->peer.retran_path &&
+            asoc->peer.active_path->state == SCTP_ACTIVE)
+                return;
 
-                /* We have exhausted the list, but didn't find any
-                 * other active transports.  If so, use the next
-                 * transport.
-                 */
-                if (t == asoc->peer.retran_path) {
-                        t = next;
+        /* Iterate from retran_path's successor back to retran_path. */
+        for (trans = list_next_entry(trans, transports); 1;
+             trans = list_next_entry(trans, transports)) {
+                /* Manually skip the head element. */
+                if (&trans->transports == &asoc->peer.transport_addr_list)
+                        continue;
+                if (trans->state == SCTP_UNCONFIRMED)
+                        continue;
+                trans_next = sctp_trans_elect_best(trans, trans_next);
+                /* Active is good enough for immediate return. */
+                if (trans_next->state == SCTP_ACTIVE)
                         break;
-                }
-
-                /* Try to find an active transport. */
-
-                if ((t->state == SCTP_ACTIVE) ||
-                    (t->state == SCTP_UNKNOWN)) {
+                /* We've reached the end, time to update path. */
+                if (trans == asoc->peer.retran_path)
                         break;
-                } else {
-                        /* Keep track of the next transport in case
-                         * we don't find any active transport.
-                         */
-                        if (t->state != SCTP_UNCONFIRMED && !next)
-                                next = t;
-                }
         }
 
-        if (t)
-                asoc->peer.retran_path = t;
-        else
-                t = asoc->peer.retran_path;
+        if (trans_next != NULL)
+                asoc->peer.retran_path = trans_next;
 
-        pr_debug("%s: association:%p addr:%pISpc\n", __func__, asoc,
-                 &t->ipaddr.sa);
+        pr_debug("%s: association:%p updated new path to addr:%pISpc\n",
+                 __func__, asoc, &asoc->peer.retran_path->ipaddr.sa);
 }
 
-/* Choose the transport for sending retransmit packet.  */
-struct sctp_transport *sctp_assoc_choose_alter_transport(
-        struct sctp_association *asoc, struct sctp_transport *last_sent_to)
+struct sctp_transport *
+sctp_assoc_choose_alter_transport(struct sctp_association *asoc,
+                                  struct sctp_transport *last_sent_to)
 {
         /* If this is the first time packet is sent, use the active path,
          * else use the retran path. If the last packet was sent over the
          * retran path, update the retran path and use it.
          */
-        if (!last_sent_to)
+        if (last_sent_to == NULL) {
                 return asoc->peer.active_path;
-        else {
+        } else {
                 if (last_sent_to == asoc->peer.retran_path)
                         sctp_assoc_update_retran_path(asoc);
+
                 return asoc->peer.retran_path;
         }
 }
@@ -1367,44 +1396,35 @@ static inline bool sctp_peer_needs_update(struct sctp_association *asoc)
         return false;
 }
 
-/* Increase asoc's rwnd by len and send any window update SACK if needed. */
-void sctp_assoc_rwnd_increase(struct sctp_association *asoc, unsigned int len)
+/* Update asoc's rwnd for the approximated state in the buffer,
+ * and check whether SACK needs to be sent.
+ */
+void sctp_assoc_rwnd_update(struct sctp_association *asoc, bool update_peer)
 {
+        int rx_count;
         struct sctp_chunk *sack;
         struct timer_list *timer;
 
-        if (asoc->rwnd_over) {
-                if (asoc->rwnd_over >= len) {
-                        asoc->rwnd_over -= len;
-                } else {
-                        asoc->rwnd += (len - asoc->rwnd_over);
-                        asoc->rwnd_over = 0;
-                }
-        } else {
-                asoc->rwnd += len;
-        }
+        if (asoc->ep->rcvbuf_policy)
+                rx_count = atomic_read(&asoc->rmem_alloc);
+        else
+                rx_count = atomic_read(&asoc->base.sk->sk_rmem_alloc);
 
-        /* If we had window pressure, start recovering it
-         * once our rwnd had reached the accumulated pressure
-         * threshold.  The idea is to recover slowly, but up
-         * to the initial advertised window.
-         */
-        if (asoc->rwnd_press && asoc->rwnd >= asoc->rwnd_press) {
-                int change = min(asoc->pathmtu, asoc->rwnd_press);
-                asoc->rwnd += change;
-                asoc->rwnd_press -= change;
-        }
+        if ((asoc->base.sk->sk_rcvbuf - rx_count) > 0)
+                asoc->rwnd = (asoc->base.sk->sk_rcvbuf - rx_count) >> 1;
+        else
+                asoc->rwnd = 0;
 
-        pr_debug("%s: asoc:%p rwnd increased by %d to (%u, %u) - %u\n",
-                 __func__, asoc, len, asoc->rwnd, asoc->rwnd_over,
-                 asoc->a_rwnd);
+        pr_debug("%s: asoc:%p rwnd=%u, rx_count=%d, sk_rcvbuf=%d\n",
+                 __func__, asoc, asoc->rwnd, rx_count,
+                 asoc->base.sk->sk_rcvbuf);
 
         /* Send a window update SACK if the rwnd has increased by at least the
          * minimum of the association's PMTU and half of the receive buffer.
          * The algorithm used is similar to the one described in
          * Section 4.2.3.3 of RFC 1122.
          */
-        if (sctp_peer_needs_update(asoc)) {
+        if (update_peer && sctp_peer_needs_update(asoc)) {
                 asoc->a_rwnd = asoc->rwnd;
 
                 pr_debug("%s: sending window update SACK- asoc:%p rwnd:%u "
@@ -1426,45 +1446,6 @@ void sctp_assoc_rwnd_increase(struct sctp_association *asoc, unsigned int len)
         }
 }
 
-/* Decrease asoc's rwnd by len. */
-void sctp_assoc_rwnd_decrease(struct sctp_association *asoc, unsigned int len)
-{
-        int rx_count;
-        int over = 0;
-
-        if (unlikely(!asoc->rwnd || asoc->rwnd_over))
-                pr_debug("%s: association:%p has asoc->rwnd:%u, "
-                         "asoc->rwnd_over:%u!\n", __func__, asoc,
-                         asoc->rwnd, asoc->rwnd_over);
-
-        if (asoc->ep->rcvbuf_policy)
-                rx_count = atomic_read(&asoc->rmem_alloc);
-        else
-                rx_count = atomic_read(&asoc->base.sk->sk_rmem_alloc);
-
-        /* If we've reached or overflowed our receive buffer, announce
-         * a 0 rwnd if rwnd would still be positive.  Store the
-         * the potential pressure overflow so that the window can be restored
-         * back to original value.
-         */
-        if (rx_count >= asoc->base.sk->sk_rcvbuf)
-                over = 1;
-
-        if (asoc->rwnd >= len) {
-                asoc->rwnd -= len;
-                if (over) {
-                        asoc->rwnd_press += asoc->rwnd;
-                        asoc->rwnd = 0;
-                }
-        } else {
-                asoc->rwnd_over = len - asoc->rwnd;
-                asoc->rwnd = 0;
-        }
-
-        pr_debug("%s: asoc:%p rwnd decreased by %d to (%u, %u, %u)\n",
-                 __func__, asoc, len, asoc->rwnd, asoc->rwnd_over,
-                 asoc->rwnd_press);
-}
 
 /* Build the bind address list for the association based on info from the
  * local endpoint and the remote peer.
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index 0f6259a6a932..2b1738ef9394 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -662,6 +662,8 @@ static struct sock *sctp_v6_create_accept_sk(struct sock *sk,
          */
         sctp_v6_to_sk_daddr(&asoc->peer.primary_addr, newsk);
 
+        newsk->sk_v6_rcv_saddr = sk->sk_v6_rcv_saddr;
+
         sk_refcnt_debug_inc(newsk);
 
         if (newsk->sk_prot->init(newsk)) {
diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
index 632090b961c3..3a1767ef3201 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -1421,8 +1421,8 @@ static void sctp_chunk_destroy(struct sctp_chunk *chunk)
         BUG_ON(!list_empty(&chunk->list));
         list_del_init(&chunk->transmitted_list);
 
-        /* Free the chunk skb data and the SCTP_chunk stub itself. */
-        dev_kfree_skb(chunk->skb);
+        consume_skb(chunk->skb);
+        consume_skb(chunk->auth_chunk);
 
         SCTP_DBG_OBJCNT_DEC(chunk);
         kmem_cache_free(sctp_chunk_cachep, chunk);
diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c
index bd859154000e..5d6883ff00c3 100644
--- a/net/sctp/sm_sideeffect.c
+++ b/net/sctp/sm_sideeffect.c
@@ -495,11 +495,12 @@ static void sctp_do_8_2_transport_strike(sctp_cmd_seq_t *commands,
         }
 
         /* If the transport error count is greater than the pf_retrans
-         * threshold, and less than pathmaxrtx, then mark this transport
-         * as Partially Failed, ee SCTP Quick Failover Draft, secon 5.1,
-         * point 1
+         * threshold, and less than pathmaxrtx, and if the current state
+         * is not SCTP_UNCONFIRMED, then mark this transport as Partially
+         * Failed, see SCTP Quick Failover Draft, section 5.1
          */
         if ((transport->state != SCTP_PF) &&
+           (transport->state != SCTP_UNCONFIRMED) &&
            (asoc->pf_retrans < transport->pathmaxrxt) &&
            (transport->error_count > asoc->pf_retrans)) {
 
diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index 483dcd71b3c5..01e002430c85 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -758,6 +758,12 @@ sctp_disposition_t sctp_sf_do_5_1D_ce(struct net *net,
                 struct sctp_chunk auth;
                 sctp_ierror_t ret;
 
+                /* Make sure that we and the peer are AUTH capable */
+                if (!net->sctp.auth_enable || !new_asoc->peer.auth_capable) {
+                        sctp_association_free(new_asoc);
+                        return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
+                }
+
                 /* set-up our fake chunk so that we can process it */
                 auth.skb = chunk->auth_chunk;
                 auth.asoc = chunk->asoc;
@@ -768,10 +774,6 @@ sctp_disposition_t sctp_sf_do_5_1D_ce(struct net *net,
                 auth.transport = chunk->transport;
 
                 ret = sctp_sf_authenticate(net, ep, new_asoc, type, &auth);
-
-                /* We can now safely free the auth_chunk clone */
-                kfree_skb(chunk->auth_chunk);
-
                 if (ret != SCTP_IERROR_NO_ERROR) {
                         sctp_association_free(new_asoc);
                         return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
@@ -6176,7 +6178,7 @@ static int sctp_eat_data(const struct sctp_association *asoc,
          * PMTU.  In cases, such as loopback, this might be a rather
          * large spill over.
          */
-        if ((!chunk->data_accepted) && (!asoc->rwnd || asoc->rwnd_over ||
+        if ((!chunk->data_accepted) && (!asoc->rwnd ||
             (datalen > asoc->rwnd + asoc->frag_point))) {
 
                 /* If this is the next TSN, consider reneging to make
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 9e91d6e5df63..981aaf8b6ace 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -64,6 +64,7 @@
 #include <linux/crypto.h>
 #include <linux/slab.h>
 #include <linux/file.h>
+#include <linux/compat.h>
 
 #include <net/ip.h>
 #include <net/icmp.h>
@@ -1368,11 +1369,19 @@ static int sctp_setsockopt_connectx(struct sock *sk,
 /*
  * New (hopefully final) interface for the API.
  * We use the sctp_getaddrs_old structure so that use-space library
- * can avoid any unnecessary allocations.   The only defferent part
+ * can avoid any unnecessary allocations. The only different part
  * is that we store the actual length of the address buffer into the
- * addrs_num structure member.  That way we can re-use the existing
+ * addrs_num structure member. That way we can re-use the existing
  * code.
  */
+#ifdef CONFIG_COMPAT
+struct compat_sctp_getaddrs_old {
+        sctp_assoc_t    assoc_id;
+        s32             addr_num;
+        compat_uptr_t   addrs;          /* struct sockaddr * */
+};
+#endif
+
 static int sctp_getsockopt_connectx3(struct sock *sk, int len,
                                      char __user *optval,
                                      int __user *optlen)
@@ -1381,16 +1390,30 @@ static int sctp_getsockopt_connectx3(struct sock *sk, int len,
         sctp_assoc_t assoc_id = 0;
         int err = 0;
 
-        if (len < sizeof(param))
-                return -EINVAL;
+#ifdef CONFIG_COMPAT
+        if (is_compat_task()) {
+                struct compat_sctp_getaddrs_old param32;
 
-        if (copy_from_user(&param, optval, sizeof(param)))
-                return -EFAULT;
+                if (len < sizeof(param32))
+                        return -EINVAL;
+                if (copy_from_user(&param32, optval, sizeof(param32)))
+                        return -EFAULT;
 
-        err = __sctp_setsockopt_connectx(sk,
-                        (struct sockaddr __user *)param.addrs,
-                        param.addr_num, &assoc_id);
+                param.assoc_id = param32.assoc_id;
+                param.addr_num = param32.addr_num;
+                param.addrs = compat_ptr(param32.addrs);
+        } else
+#endif
+        {
+                if (len < sizeof(param))
+                        return -EINVAL;
+                if (copy_from_user(&param, optval, sizeof(param)))
+                        return -EFAULT;
+        }
 
+        err = __sctp_setsockopt_connectx(sk, (struct sockaddr __user *)
+                                         param.addrs, param.addr_num,
+                                         &assoc_id);
         if (err == 0 || err == -EINPROGRESS) {
                 if (copy_to_user(optval, &assoc_id, sizeof(assoc_id)))
                         return -EFAULT;
@@ -2092,12 +2115,6 @@ static int sctp_recvmsg(struct kiocb *iocb, struct sock *sk,
                 sctp_skb_pull(skb, copied);
                 skb_queue_head(&sk->sk_receive_queue, skb);
 
-                /* When only partial message is copied to the user, increase
-                 * rwnd by that amount. If all the data in the skb is read,
-                 * rwnd is updated when the event is freed.
-                 */
-                if (!sctp_ulpevent_is_notification(event))
-                        sctp_assoc_rwnd_increase(event->asoc, copied);
                 goto out;
         } else if ((event->msg_flags & MSG_NOTIFICATION) ||
                    (event->msg_flags & MSG_EOR))
diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c
index 7135e617ab0f..35c8923b5554 100644
--- a/net/sctp/sysctl.c
+++ b/net/sctp/sysctl.c
@@ -151,6 +151,7 @@ static struct ctl_table sctp_net_table[] = {
         },
         {
                 .procname       = "cookie_hmac_alg",
+                .data           = &init_net.sctp.sctp_hmac_alg,
                 .maxlen         = 8,
                 .mode           = 0644,
                 .proc_handler   = proc_sctp_do_hmac_alg,
@@ -401,15 +402,18 @@ static int proc_sctp_do_rto_max(struct ctl_table *ctl, int write,
 
 int sctp_sysctl_net_register(struct net *net)
 {
-        struct ctl_table *table;
-        int i;
+        struct ctl_table *table = sctp_net_table;
+
+        if (!net_eq(net, &init_net)) {
+                int i;
 
-        table = kmemdup(sctp_net_table, sizeof(sctp_net_table), GFP_KERNEL);
-        if (!table)
-                return -ENOMEM;
+                table = kmemdup(sctp_net_table, sizeof(sctp_net_table), GFP_KERNEL);
+                if (!table)
+                        return -ENOMEM;
 
-        for (i = 0; table[i].data; i++)
-                table[i].data += (char *)(&net->sctp) - (char *)&init_net.sctp;
+                for (i = 0; table[i].data; i++)
+                        table[i].data += (char *)(&net->sctp) - (char *)&init_net.sctp;
+        }
 
         net->sctp.sysctl_header = register_net_sysctl(net, "net/sctp", table);
         return 0;
diff --git a/net/sctp/ulpevent.c b/net/sctp/ulpevent.c
index 85c64658bd0b..8d198ae03606 100644
--- a/net/sctp/ulpevent.c
+++ b/net/sctp/ulpevent.c
@@ -989,7 +989,7 @@ static void sctp_ulpevent_receive_data(struct sctp_ulpevent *event,
         skb = sctp_event2skb(event);
         /* Set the owner and charge rwnd for bytes received.  */
         sctp_ulpevent_set_owner(event, asoc);
-        sctp_assoc_rwnd_decrease(asoc, skb_headlen(skb));
+        sctp_assoc_rwnd_update(asoc, false);
 
         if (!skb->data_len)
                 return;
@@ -1011,6 +1011,7 @@ static void sctp_ulpevent_release_data(struct sctp_ulpevent *event)
 {
         struct sk_buff *skb, *frag;
         unsigned int    len;
+        struct sctp_association *asoc;
 
         /* Current stack structures assume that the rcv buffer is
          * per socket.   For UDP style sockets this is not true as
@@ -1035,8 +1036,11 @@ static void sctp_ulpevent_release_data(struct sctp_ulpevent *event)
         }
 
 done:
-        sctp_assoc_rwnd_increase(event->asoc, len);
+        asoc = event->asoc;
+        sctp_association_hold(asoc);
         sctp_ulpevent_release_owner(event);
+        sctp_assoc_rwnd_update(asoc, true);
+        sctp_association_put(asoc);
 }
 
 static void sctp_ulpevent_release_frag_data(struct sctp_ulpevent *event)