dccp: Per-socket initialisation of feature negotiation

This provides feature-negotiation initialisation for both DCCP sockets
and DCCP request_sockets, to support feature negotiation during
connection setup.

It also resolves a FIXME regarding the congestion control
initialisation.

Thanks to Wei Yongjun for help with the IPv6 side of this patch.

Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk>
Acked-by: Ian McDonald <ian.mcdonald@jandi.co.nz>
Signed-off-by: David S. Miller <davem@davemloft.net>

8 files changed, 69 insertions, 6 deletions

diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h
index d6fed595a3ff..dee4a90886d6 100644
--- a/net/dccp/dccp.h
+++ b/net/dccp/dccp.h
@@ -252,7 +252,8 @@ extern const char *dccp_state_name(const int state);
 extern void dccp_set_state(struct sock *sk, const int state);
 extern void dccp_done(struct sock *sk);
 
-extern void dccp_reqsk_init(struct request_sock *req, struct sk_buff *skb);
+extern int  dccp_reqsk_init(struct request_sock *rq, struct dccp_sock const *dp,
+                            struct sk_buff const *skb);
 
 extern int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb);
 
diff --git a/net/dccp/feat.c b/net/dccp/feat.c
index 9a37b6ce3aca..069d8ffe4c6f 100644
--- a/net/dccp/feat.c
+++ b/net/dccp/feat.c
@@ -90,6 +90,20 @@ static u8 dccp_feat_type(u8 feat_num)
         return dccp_feat_table[idx].reconciliation;
 }
 
+/* copy constructor, fval must not already contain allocated memory */
+static int dccp_feat_clone_sp_val(dccp_feat_val *fval, u8 const *val, u8 len)
+{
+        fval->sp.len = len;
+        if (fval->sp.len > 0) {
+                fval->sp.vec = kmemdup(val, len, gfp_any());
+                if (fval->sp.vec == NULL) {
+                        fval->sp.len = 0;
+                        return -ENOBUFS;
+                }
+        }
+        return 0;
+}
+
 static void dccp_feat_val_destructor(u8 feat_num, dccp_feat_val *val)
 {
         if (unlikely(val == NULL))
@@ -99,6 +113,28 @@ static void dccp_feat_val_destructor(u8 feat_num, dccp_feat_val *val)
         memset(val, 0, sizeof(*val));
 }
 
+static struct dccp_feat_entry *
+              dccp_feat_clone_entry(struct dccp_feat_entry const *original)
+{
+        struct dccp_feat_entry *new;
+        u8 type = dccp_feat_type(original->feat_num);
+
+        if (type == FEAT_UNKNOWN)
+                return NULL;
+
+        new = kmemdup(original, sizeof(struct dccp_feat_entry), gfp_any());
+        if (new == NULL)
+                return NULL;
+
+        if (type == FEAT_SP && dccp_feat_clone_sp_val(&new->val,
+                                                      original->val.sp.vec,
+                                                      original->val.sp.len)) {
+                kfree(new);
+                return NULL;
+        }
+        return new;
+}
+
 static void dccp_feat_entry_destructor(struct dccp_feat_entry *entry)
 {
         if (entry != NULL) {
@@ -133,6 +169,25 @@ void dccp_feat_list_purge(struct list_head *fn_list)
 }
 EXPORT_SYMBOL_GPL(dccp_feat_list_purge);
 
+/* generate @to as full clone of @from - @to must not contain any nodes */
+int dccp_feat_clone_list(struct list_head const *from, struct list_head *to)
+{
+        struct dccp_feat_entry *entry, *new;
+
+        INIT_LIST_HEAD(to);
+        list_for_each_entry(entry, from, node) {
+                new = dccp_feat_clone_entry(entry);
+                if (new == NULL)
+                        goto cloning_failed;
+                list_add_tail(&new->node, to);
+        }
+        return 0;
+
+cloning_failed:
+        dccp_feat_list_purge(to);
+        return -ENOMEM;
+}
+
 int dccp_feat_change(struct dccp_minisock *dmsk, u8 type, u8 feature,
                      u8 *val, u8 len, gfp_t gfp)
 {
diff --git a/net/dccp/feat.h b/net/dccp/feat.h
index 56df82ceef09..f5e99b39712a 100644
--- a/net/dccp/feat.h
+++ b/net/dccp/feat.h
@@ -96,6 +96,7 @@ extern int  dccp_feat_confirm_recv(struct sock *sk, u8 type, u8 feature,
                                    u8 *val, u8 len);
 extern void dccp_feat_clean(struct dccp_minisock *dmsk);
 extern int  dccp_feat_clone(struct sock *oldsk, struct sock *newsk);
+extern int  dccp_feat_clone_list(struct list_head const *, struct list_head *);
 extern int  dccp_feat_init(struct dccp_minisock *dmsk);
 
 #endif /* _DCCP_FEAT_H */
diff --git a/net/dccp/input.c b/net/dccp/input.c
index 779d0ed9ae94..3070015edc75 100644
--- a/net/dccp/input.c
+++ b/net/dccp/input.c
@@ -590,8 +590,6 @@ int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
                         if (inet_csk(sk)->icsk_af_ops->conn_request(sk,
                                                                     skb) < 0)
                                 return 1;
-
-                        /* FIXME: do congestion control initialization */
                         goto discard;
                 }
                 if (dh->dccph_type == DCCP_PKT_RESET)
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index 01e3e0206254..cbf522dfecc4 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -595,7 +595,8 @@ int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
         if (req == NULL)
                 goto drop;
 
-        dccp_reqsk_init(req, skb);
+        if (dccp_reqsk_init(req, dccp_sk(sk), skb))
+                goto drop_and_free;
 
         dreq = dccp_rsk(req);
         if (dccp_parse_options(sk, dreq, skb))
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index d4ce1224e008..4e172ccfd76c 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -426,7 +426,8 @@ static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
         if (req == NULL)
                 goto drop;
 
-        dccp_reqsk_init(req, skb);
+        if (dccp_reqsk_init(req, dccp_sk(sk), skb))
+                goto drop_and_free;
 
         dreq = dccp_rsk(req);
         if (dccp_parse_options(sk, dreq, skb))
diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c
index e6bf99e3e41a..afdacbb94d75 100644
--- a/net/dccp/minisocks.c
+++ b/net/dccp/minisocks.c
@@ -125,6 +125,7 @@ struct sock *dccp_create_openreq_child(struct sock *sk,
                 newdp->dccps_timestamp_time = dreq->dreq_timestamp_time;
                 newicsk->icsk_rto           = DCCP_TIMEOUT_INIT;
 
+                INIT_LIST_HEAD(&newdp->dccps_featneg);
                 if (dccp_feat_clone(sk, newsk))
                         goto out_free;
 
@@ -304,7 +305,8 @@ void dccp_reqsk_send_ack(struct sock *sk, struct sk_buff *skb,
 
 EXPORT_SYMBOL_GPL(dccp_reqsk_send_ack);
 
-void dccp_reqsk_init(struct request_sock *req, struct sk_buff *skb)
+int dccp_reqsk_init(struct request_sock *req,
+                    struct dccp_sock const *dp, struct sk_buff const *skb)
 {
         struct dccp_request_sock *dreq = dccp_rsk(req);
 
@@ -313,6 +315,9 @@ void dccp_reqsk_init(struct request_sock *req, struct sk_buff *skb)
         inet_rsk(req)->acked      = 0;
         req->rcv_wnd              = sysctl_dccp_feat_sequence_window;
         dreq->dreq_timestamp_echo = 0;
+
+        /* inherit feature negotiation options from listening socket */
+        return dccp_feat_clone_list(&dp->dccps_featneg, &dreq->dreq_featneg);
 }
 
 EXPORT_SYMBOL_GPL(dccp_reqsk_init);
diff --git a/net/dccp/proto.c b/net/dccp/proto.c
index d0bd34819761..1cdf4ae99605 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -193,6 +193,7 @@ int dccp_init_sock(struct sock *sk, const __u8 ctl_sock_initialized)
 
         dccp_init_xmit_timers(sk);
 
+        INIT_LIST_HEAD(&dp->dccps_featneg);
         /*
          * FIXME: We're hardcoding the CCID, and doing this at this point makes
          * the listening (master) sock get CCID control blocks, which is not