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>
diff --git a/include/linux/dccp.h b/include/linux/dccp.h
index 3978aff..484b8a1 100644
--- a/include/linux/dccp.h
+++ b/include/linux/dccp.h
@@ -412,6 +412,7 @@
* @dreq_iss: initial sequence number sent on the Response (RFC 4340, 7.1)
* @dreq_isr: initial sequence number received on the Request
* @dreq_service: service code present on the Request (there is just one)
+ * @dreq_featneg: feature negotiation options for this connection
* The following two fields are analogous to the ones in dccp_sock:
* @dreq_timestamp_echo: last received timestamp to echo (13.1)
* @dreq_timestamp_echo: the time of receiving the last @dreq_timestamp_echo
@@ -421,6 +422,7 @@
__u64 dreq_iss;
__u64 dreq_isr;
__be32 dreq_service;
+ struct list_head dreq_featneg;
__u32 dreq_timestamp_echo;
__u32 dreq_timestamp_time;
};
@@ -498,6 +500,7 @@
* @dccps_mss_cache - current value of MSS (path MTU minus header sizes)
* @dccps_rate_last - timestamp for rate-limiting DCCP-Sync (RFC 4340, 7.5.4)
* @dccps_minisock - associated minisock (accessed via dccp_msk)
+ * @dccps_featneg - tracks feature-negotiation state (mostly during handshake)
* @dccps_hc_rx_ackvec - rx half connection ack vector
* @dccps_hc_rx_ccid - CCID used for the receiver (or receiving half-connection)
* @dccps_hc_tx_ccid - CCID used for the sender (or sending half-connection)
@@ -535,6 +538,7 @@
__u64 dccps_ndp_count:48;
unsigned long dccps_rate_last;
struct dccp_minisock dccps_minisock;
+ struct list_head dccps_featneg;
struct dccp_ackvec *dccps_hc_rx_ackvec;
struct ccid *dccps_hc_rx_ccid;
struct ccid *dccps_hc_tx_ccid;
diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h
index b4bc6e09..ab096c0 100644
--- a/net/dccp/dccp.h
+++ b/net/dccp/dccp.h
@@ -252,7 +252,8 @@
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 2ec2cd1..faade82 100644
--- a/net/dccp/feat.c
+++ b/net/dccp/feat.c
@@ -279,6 +279,25 @@
}
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 94203c2..7e953fd 100644
--- a/net/dccp/feat.h
+++ b/net/dccp/feat.h
@@ -95,6 +95,7 @@
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 779d0ed..3070015 100644
--- a/net/dccp/input.c
+++ b/net/dccp/input.c
@@ -590,8 +590,6 @@
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 882c5c4..0ce84ea 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -595,7 +595,8 @@
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 5e1ee0d..33e8a1e 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -424,7 +424,8 @@
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 b2804e2d..e487133 100644
--- a/net/dccp/minisocks.c
+++ b/net/dccp/minisocks.c
@@ -125,6 +125,7 @@
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 @@
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);
@@ -312,6 +314,9 @@
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 d0bd348..1cdf4ae 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -193,6 +193,7 @@
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