From 61e6473efbd6087e1db3aaa93a5266c5bfd8aa99 Mon Sep 17 00:00:00 2001
From: Gerrit Renker <gerrit@erg.abdn.ac.uk>
Date: Tue, 4 Nov 2008 23:54:04 -0800
Subject: dccp: List management for new feature negotiation

This adds list initial fields and list management functions for the
new feature negotiation implementation.

Thanks to Arnaldo for suggestions and improvements.

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>
---
 net/dccp/dccp.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'net/dccp/dccp.h')

diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h
index b4bc6e095a0e..d6fed595a3ff 100644
--- a/net/dccp/dccp.h
+++ b/net/dccp/dccp.h
@@ -441,6 +441,8 @@ static inline int dccp_ack_pending(const struct sock *sk)
 	       inet_csk_ack_scheduled(sk);
 }
 
+extern void dccp_feat_list_purge(struct list_head *fn_list);
+
 extern int dccp_insert_options(struct sock *sk, struct sk_buff *skb);
 extern int dccp_insert_options_rsk(struct dccp_request_sock*, struct sk_buff*);
 extern int dccp_insert_option_elapsed_time(struct sock *sk,
-- 
cgit v1.2.3


From ac75773c2742d82cbcb078708df406e9017224b7 Mon Sep 17 00:00:00 2001
From: Gerrit Renker <gerrit@erg.abdn.ac.uk>
Date: Tue, 4 Nov 2008 23:55:49 -0800
Subject: 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>
---
 include/linux/dccp.h |  4 ++++
 net/dccp/dccp.h      |  3 ++-
 net/dccp/feat.c      | 55 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 net/dccp/feat.h      |  1 +
 net/dccp/input.c     |  2 --
 net/dccp/ipv4.c      |  3 ++-
 net/dccp/ipv6.c      |  3 ++-
 net/dccp/minisocks.c |  7 ++++++-
 net/dccp/proto.c     |  1 +
 9 files changed, 73 insertions(+), 6 deletions(-)

(limited to 'net/dccp/dccp.h')

diff --git a/include/linux/dccp.h b/include/linux/dccp.h
index 3978aff197d9..484b8a1fb023 100644
--- a/include/linux/dccp.h
+++ b/include/linux/dccp.h
@@ -412,6 +412,7 @@ extern void dccp_minisock_init(struct dccp_minisock *dmsk);
  * @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 @@ struct dccp_request_sock {
 	__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 @@ struct dccp_ackvec;
  * @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 @@ struct dccp_sock {
 	__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 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
-- 
cgit v1.2.3


From 9eca0a47dee201a73967026985b5f0a79a46bd36 Mon Sep 17 00:00:00 2001
From: Gerrit Renker <gerrit@erg.abdn.ac.uk>
Date: Wed, 12 Nov 2008 00:48:44 -0800
Subject: dccp: Resolve dependencies of features on choice of CCID

This provides a missing link in the code chain, as several features implicitly
depend and/or rely on the choice of CCID. Most notably, this is the Send Ack Vector
feature, but also Ack Ratio and Send Loss Event Rate (also taken care of).

For Send Ack Vector, the situation is as follows:
 * since CCID2 mandates the use of Ack Vectors, there is no point in allowing
   endpoints which use CCID2 to disable Ack Vector features such a connection;

 * a peer with a TX CCID of CCID2 will always expect Ack Vectors, and a peer
   with a RX CCID of CCID2 must always send Ack Vectors (RFC 4341, sec. 4);

 * for all other CCIDs, the use of (Send) Ack Vector is optional and thus
   negotiable. However, this implies that the code negotiating the use of Ack
   Vectors also supports it (i.e. is able to supply and to either parse or
   ignore received Ack Vectors). Since this is not the case (CCID-3 has no Ack
   Vector support), the use of Ack Vectors is here disabled, with a comment
   in the source code.

An analogous consideration arises for the Send Loss Event Rate feature,
since the CCID-3 implementation does not support the loss interval options
of RFC 4342. To make such use explicit, corresponding feature-negotiation
options are inserted which signal the use of the loss event rate option,
as it is used by the CCID3 code.

Lastly, the values of the Ack Ratio feature are matched to the choice of CCID.

The patch implements this as a function which is called after the user has
made all other registrations for changing default values of features.

The table is variable-length, the reserved (and hence for feature-negotiation
invalid, confirmed by considering section 19.4 of RFC 4340) feature number `0'
is used to mark the end of the table.

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>
---
 net/dccp/dccp.h   |   1 +
 net/dccp/feat.c   | 160 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
 net/dccp/output.c |   4 ++
 net/dccp/proto.c  |   3 +
 4 files changed, 168 insertions(+)

(limited to 'net/dccp/dccp.h')

diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h
index dee4a90886d6..1881527bdcd7 100644
--- a/net/dccp/dccp.h
+++ b/net/dccp/dccp.h
@@ -442,6 +442,7 @@ static inline int dccp_ack_pending(const struct sock *sk)
 	       inet_csk_ack_scheduled(sk);
 }
 
+extern int  dccp_feat_finalise_settings(struct dccp_sock *dp);
 extern void dccp_feat_list_purge(struct list_head *fn_list);
 
 extern int dccp_insert_options(struct sock *sk, struct sk_buff *skb);
diff --git a/net/dccp/feat.c b/net/dccp/feat.c
index f79fb5e33f5e..4c4144147325 100644
--- a/net/dccp/feat.c
+++ b/net/dccp/feat.c
@@ -400,6 +400,166 @@ int dccp_feat_change(struct dccp_minisock *dmsk, u8 type, u8 feature,
 
 EXPORT_SYMBOL_GPL(dccp_feat_change);
 
+/*
+ *	Tracking features whose value depend on the choice of CCID
+ *
+ * This is designed with an extension in mind so that a list walk could be done
+ * before activating any features. However, the existing framework was found to
+ * work satisfactorily up until now, the automatic verification is left open.
+ * When adding new CCIDs, add a corresponding dependency table here.
+ */
+static const struct ccid_dependency *dccp_feat_ccid_deps(u8 ccid, bool is_local)
+{
+	static const struct ccid_dependency ccid2_dependencies[2][2] = {
+		/*
+		 * CCID2 mandates Ack Vectors (RFC 4341, 4.): as CCID is a TX
+		 * feature and Send Ack Vector is an RX feature, `is_local'
+		 * needs to be reversed.
+		 */
+		{	/* Dependencies of the receiver-side (remote) CCID2 */
+			{
+				.dependent_feat	= DCCPF_SEND_ACK_VECTOR,
+				.is_local	= true,
+				.is_mandatory	= true,
+				.val		= 1
+			},
+			{ 0, 0, 0, 0 }
+		},
+		{	/* Dependencies of the sender-side (local) CCID2 */
+			{
+				.dependent_feat	= DCCPF_SEND_ACK_VECTOR,
+				.is_local	= false,
+				.is_mandatory	= true,
+				.val		= 1
+			},
+			{ 0, 0, 0, 0 }
+		}
+	};
+	static const struct ccid_dependency ccid3_dependencies[2][5] = {
+		{	/*
+			 * Dependencies of the receiver-side CCID3
+			 */
+			{	/* locally disable Ack Vectors */
+				.dependent_feat	= DCCPF_SEND_ACK_VECTOR,
+				.is_local	= true,
+				.is_mandatory	= false,
+				.val		= 0
+			},
+			{	/* see below why Send Loss Event Rate is on */
+				.dependent_feat	= DCCPF_SEND_LEV_RATE,
+				.is_local	= true,
+				.is_mandatory	= true,
+				.val		= 1
+			},
+			{	/* NDP Count is needed as per RFC 4342, 6.1.1 */
+				.dependent_feat	= DCCPF_SEND_NDP_COUNT,
+				.is_local	= false,
+				.is_mandatory	= true,
+				.val		= 1
+			},
+			{ 0, 0, 0, 0 },
+		},
+		{	/*
+			 * CCID3 at the TX side: we request that the HC-receiver
+			 * will not send Ack Vectors (they will be ignored, so
+			 * Mandatory is not set); we enable Send Loss Event Rate
+			 * (Mandatory since the implementation does not support
+			 * the Loss Intervals option of RFC 4342, 8.6).
+			 * The last two options are for peer's information only.
+			*/
+			{
+				.dependent_feat	= DCCPF_SEND_ACK_VECTOR,
+				.is_local	= false,
+				.is_mandatory	= false,
+				.val		= 0
+			},
+			{
+				.dependent_feat	= DCCPF_SEND_LEV_RATE,
+				.is_local	= false,
+				.is_mandatory	= true,
+				.val		= 1
+			},
+			{	/* this CCID does not support Ack Ratio */
+				.dependent_feat	= DCCPF_ACK_RATIO,
+				.is_local	= true,
+				.is_mandatory	= false,
+				.val		= 0
+			},
+			{	/* tell receiver we are sending NDP counts */
+				.dependent_feat	= DCCPF_SEND_NDP_COUNT,
+				.is_local	= true,
+				.is_mandatory	= false,
+				.val		= 1
+			},
+			{ 0, 0, 0, 0 }
+		}
+	};
+	switch (ccid) {
+	case DCCPC_CCID2:
+		return ccid2_dependencies[is_local];
+	case DCCPC_CCID3:
+		return ccid3_dependencies[is_local];
+	default:
+		return NULL;
+	}
+}
+
+/**
+ * dccp_feat_propagate_ccid - Resolve dependencies of features on choice of CCID
+ * @fn: feature-negotiation list to update
+ * @id: CCID number to track
+ * @is_local: whether TX CCID (1) or RX CCID (0) is meant
+ * This function needs to be called after registering all other features.
+ */
+static int dccp_feat_propagate_ccid(struct list_head *fn, u8 id, bool is_local)
+{
+	const struct ccid_dependency *table = dccp_feat_ccid_deps(id, is_local);
+	int i, rc = (table == NULL);
+
+	for (i = 0; rc == 0 && table[i].dependent_feat != DCCPF_RESERVED; i++)
+		if (dccp_feat_type(table[i].dependent_feat) == FEAT_SP)
+			rc = __feat_register_sp(fn, table[i].dependent_feat,
+						    table[i].is_local,
+						    table[i].is_mandatory,
+						    &table[i].val, 1);
+		else
+			rc = __feat_register_nn(fn, table[i].dependent_feat,
+						    table[i].is_mandatory,
+						    table[i].val);
+	return rc;
+}
+
+/**
+ * dccp_feat_finalise_settings  -  Finalise settings before starting negotiation
+ * @dp: client or listening socket (settings will be inherited)
+ * This is called after all registrations (socket initialisation, sysctls, and
+ * sockopt calls), and before sending the first packet containing Change options
+ * (ie. client-Request or server-Response), to ensure internal consistency.
+ */
+int dccp_feat_finalise_settings(struct dccp_sock *dp)
+{
+	struct list_head *fn = &dp->dccps_featneg;
+	struct dccp_feat_entry *entry;
+	int i = 2, ccids[2] = { -1, -1 };
+
+	/*
+	 * Propagating CCIDs:
+	 * 1) not useful to propagate CCID settings if this host advertises more
+	 *    than one CCID: the choice of CCID  may still change - if this is
+	 *    the client, or if this is the server and the client sends
+	 *    singleton CCID values.
+	 * 2) since is that propagate_ccid changes the list, we defer changing
+	 *    the sorted list until after the traversal.
+	 */
+	list_for_each_entry(entry, fn, node)
+		if (entry->feat_num == DCCPF_CCID && entry->val.sp.len == 1)
+			ccids[entry->is_local] = entry->val.sp.vec[0];
+	while (i--)
+		if (ccids[i] > 0 && dccp_feat_propagate_ccid(fn, ccids[i], i))
+			return -1;
+	return 0;
+}
+
 static int dccp_feat_update_ccid(struct sock *sk, u8 type, u8 new_ccid_nr)
 {
 	struct dccp_sock *dp = dccp_sk(sk);
diff --git a/net/dccp/output.c b/net/dccp/output.c
index 809d803d5006..92f3f6f2ef51 100644
--- a/net/dccp/output.c
+++ b/net/dccp/output.c
@@ -469,6 +469,10 @@ int dccp_connect(struct sock *sk)
 	struct sk_buff *skb;
 	struct inet_connection_sock *icsk = inet_csk(sk);
 
+	/* do not connect if feature negotiation setup fails */
+	if (dccp_feat_finalise_settings(dccp_sk(sk)))
+		return -EPROTO;
+
 	dccp_connect_init(sk);
 
 	skb = alloc_skb(sk->sk_prot->max_header, sk->sk_allocation);
diff --git a/net/dccp/proto.c b/net/dccp/proto.c
index b4b10cbd8880..46cb3490d48e 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -278,6 +278,9 @@ static inline int dccp_listen_start(struct sock *sk, int backlog)
 	struct dccp_sock *dp = dccp_sk(sk);
 
 	dp->dccps_role = DCCP_ROLE_LISTEN;
+	/* do not start to listen if feature negotiation setup fails */
+	if (dccp_feat_finalise_settings(dp))
+		return -EPROTO;
 	return inet_csk_listen_start(sk, backlog);
 }
 
-- 
cgit v1.2.3


From 0c1168398ecbfacbb27203b281bde20ec9f78017 Mon Sep 17 00:00:00 2001
From: Gerrit Renker <gerrit@erg.abdn.ac.uk>
Date: Sun, 16 Nov 2008 22:49:52 -0800
Subject: dccp: Mechanism to resolve CCID dependencies

This adds a hook to resolve features whose value depends on the choice of
CCID. It is done at the server since it can only be done after the CCID
values have been negotiated; i.e. the client will add its CCID preference
list on the Change options sent in the Request, which will be reconciled
with the local preference list of the server.

The concept is documented on
http://www.erg.abdn.ac.uk/users/gerrit/dccp/notes/feature_negotiation/\
				implementation_notes.html#ccid_dependencies

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>
---
 net/dccp/dccp.h   |  1 +
 net/dccp/feat.c   | 37 +++++++++++++++++++++++++++++++++++++
 net/dccp/output.c | 13 +++++++++----
 3 files changed, 47 insertions(+), 4 deletions(-)

(limited to 'net/dccp/dccp.h')

diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h
index 1881527bdcd7..e656dafb5d96 100644
--- a/net/dccp/dccp.h
+++ b/net/dccp/dccp.h
@@ -443,6 +443,7 @@ static inline int dccp_ack_pending(const struct sock *sk)
 }
 
 extern int  dccp_feat_finalise_settings(struct dccp_sock *dp);
+extern int  dccp_feat_server_ccid_dependencies(struct dccp_request_sock *dreq);
 extern void dccp_feat_list_purge(struct list_head *fn_list);
 
 extern int dccp_insert_options(struct sock *sk, struct sk_buff *skb);
diff --git a/net/dccp/feat.c b/net/dccp/feat.c
index 4c4144147325..4f86a48723f6 100644
--- a/net/dccp/feat.c
+++ b/net/dccp/feat.c
@@ -166,6 +166,18 @@ static void dccp_feat_entry_destructor(struct dccp_feat_entry *entry)
  * - SP values are always freshly allocated
  * - list is sorted in increasing order of feature number (faster lookup)
  */
+static struct dccp_feat_entry *dccp_feat_list_lookup(struct list_head *fn_list,
+						     u8 feat_num, bool is_local)
+{
+	struct dccp_feat_entry *entry;
+
+	list_for_each_entry(entry, fn_list, node)
+		if (entry->feat_num == feat_num && entry->is_local == is_local)
+			return entry;
+		else if (entry->feat_num > feat_num)
+			break;
+	return NULL;
+}
 
 /**
  * dccp_feat_entry_new  -  Central list update routine (called by all others)
@@ -560,6 +572,31 @@ int dccp_feat_finalise_settings(struct dccp_sock *dp)
 	return 0;
 }
 
+/**
+ * dccp_feat_server_ccid_dependencies  -  Resolve CCID-dependent features
+ * It is the server which resolves the dependencies once the CCID has been
+ * fully negotiated. If no CCID has been negotiated, it uses the default CCID.
+ */
+int dccp_feat_server_ccid_dependencies(struct dccp_request_sock *dreq)
+{
+	struct list_head *fn = &dreq->dreq_featneg;
+	struct dccp_feat_entry *entry;
+	u8 is_local, ccid;
+
+	for (is_local = 0; is_local <= 1; is_local++) {
+		entry = dccp_feat_list_lookup(fn, DCCPF_CCID, is_local);
+
+		if (entry != NULL && !entry->empty_confirm)
+			ccid = entry->val.sp.vec[0];
+		else
+			ccid = dccp_feat_default_value(DCCPF_CCID);
+
+		if (dccp_feat_propagate_ccid(fn, ccid, is_local))
+			return -1;
+	}
+	return 0;
+}
+
 static int dccp_feat_update_ccid(struct sock *sk, u8 type, u8 new_ccid_nr)
 {
 	struct dccp_sock *dp = dccp_sk(sk);
diff --git a/net/dccp/output.c b/net/dccp/output.c
index 92f3f6f2ef51..fea30cdc0bee 100644
--- a/net/dccp/output.c
+++ b/net/dccp/output.c
@@ -339,10 +339,12 @@ struct sk_buff *dccp_make_response(struct sock *sk, struct dst_entry *dst,
 	DCCP_SKB_CB(skb)->dccpd_type = DCCP_PKT_RESPONSE;
 	DCCP_SKB_CB(skb)->dccpd_seq  = dreq->dreq_iss;
 
-	if (dccp_insert_options_rsk(dreq, skb)) {
-		kfree_skb(skb);
-		return NULL;
-	}
+	/* Resolve feature dependencies resulting from choice of CCID */
+	if (dccp_feat_server_ccid_dependencies(dreq))
+		goto response_failed;
+
+	if (dccp_insert_options_rsk(dreq, skb))
+		goto response_failed;
 
 	/* Build and checksum header */
 	dh = dccp_zeroed_hdr(skb, dccp_header_size);
@@ -363,6 +365,9 @@ struct sk_buff *dccp_make_response(struct sock *sk, struct dst_entry *dst,
 	inet_rsk(req)->acked = 1;
 	DCCP_INC_STATS(DCCP_MIB_OUTSEGS);
 	return skb;
+response_failed:
+	kfree_skb(skb);
+	return NULL;
 }
 
 EXPORT_SYMBOL_GPL(dccp_make_response);
-- 
cgit v1.2.3


From dd9c0e363cef32b7d6f23d4c87e8dfe4f91fd1c5 Mon Sep 17 00:00:00 2001
From: Gerrit Renker <gerrit@erg.abdn.ac.uk>
Date: Sun, 16 Nov 2008 22:55:08 -0800
Subject: dccp: Deprecate Ack Ratio sysctl

This patch deprecates the Ack Ratio sysctl, since
 * Ack Ratio is entirely ignored by CCID-3 and CCID-4,
 * Ack Ratio currently doesn't work in CCID-2 (i.e. is always set to 1);
 * even if it would work in CCID-2, there is no point for a user to change it:
   - Ack Ratio is constrained by cwnd (RFC 4341, 6.1.2),
   - if Ack Ratio > cwnd, the system resorts to spurious RTO timeouts
     (since waiting for Acks which will never arrive in this window),
   - cwnd is not a user-configurable value.

The only reasonable place for Ack Ratio is to print it for debugging. It is
planned to do this later on, as part of e.g. dccp_probe.

With this patch Ack Ratio is now under full control of feature negotiation:
 * Ack Ratio is resolved as a dependency of the selected CCID;
 * if the chosen CCID supports it (i.e. CCID == CCID-2), Ack Ratio is set to
   the default of 2, following RFC 4340, 11.3 - "New connections start with Ack
   Ratio 2 for both endpoints";
 * what happens then is part of another patch set, since it concerns the
   dynamic update of Ack Ratio while the connection is in full flight.

Thanks to Tomasz Grobelny for discussion leading up to this patch.

Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk>
Acked-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/dccp.txt | 3 ---
 include/linux/dccp.h              | 2 --
 net/dccp/dccp.h                   | 1 -
 net/dccp/minisocks.c              | 1 -
 net/dccp/options.c                | 1 -
 net/dccp/sysctl.c                 | 7 -------
 6 files changed, 15 deletions(-)

(limited to 'net/dccp/dccp.h')

diff --git a/Documentation/networking/dccp.txt b/Documentation/networking/dccp.txt
index f0aeb20fa63b..43df4487379b 100644
--- a/Documentation/networking/dccp.txt
+++ b/Documentation/networking/dccp.txt
@@ -125,9 +125,6 @@ send_ndp = 1
 send_ackvec = 1
 	Whether or not to send Ack Vector options (sec. 11.5).
 
-ack_ratio = 2
-	The default Ack Ratio (sec. 11.3) to use.
-
 tx_ccid = 2
 	Default CCID for the sender-receiver half-connection.
 
diff --git a/include/linux/dccp.h b/include/linux/dccp.h
index 5a5a89935dbc..eda389ce04f4 100644
--- a/include/linux/dccp.h
+++ b/include/linux/dccp.h
@@ -368,7 +368,6 @@ static inline unsigned int dccp_hdr_len(const struct sk_buff *skb)
   * @dccpms_ccid - Congestion Control Id (CCID) (section 10)
   * @dccpms_send_ack_vector - Send Ack Vector Feature (section 11.5)
   * @dccpms_send_ndp_count - Send NDP Count Feature (7.7.2)
-  * @dccpms_ack_ratio - Ack Ratio Feature (section 11.3)
   * @dccpms_pending - List of features being negotiated
   * @dccpms_conf -
   */
@@ -378,7 +377,6 @@ struct dccp_minisock {
 	__u8			dccpms_tx_ccid;
 	__u8			dccpms_send_ack_vector;
 	__u8			dccpms_send_ndp_count;
-	__u8			dccpms_ack_ratio;
 	struct list_head	dccpms_pending;
 	struct list_head	dccpms_conf;
 };
diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h
index e656dafb5d96..031ce350d3c1 100644
--- a/net/dccp/dccp.h
+++ b/net/dccp/dccp.h
@@ -98,7 +98,6 @@ extern int  sysctl_dccp_retries2;
 extern int  sysctl_dccp_feat_sequence_window;
 extern int  sysctl_dccp_feat_rx_ccid;
 extern int  sysctl_dccp_feat_tx_ccid;
-extern int  sysctl_dccp_feat_ack_ratio;
 extern int  sysctl_dccp_feat_send_ack_vector;
 extern int  sysctl_dccp_feat_send_ndp_count;
 extern int  sysctl_dccp_tx_qlen;
diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c
index afdacbb94d75..ed61bc58e41e 100644
--- a/net/dccp/minisocks.c
+++ b/net/dccp/minisocks.c
@@ -47,7 +47,6 @@ void dccp_minisock_init(struct dccp_minisock *dmsk)
 	dmsk->dccpms_sequence_window = sysctl_dccp_feat_sequence_window;
 	dmsk->dccpms_rx_ccid	     = sysctl_dccp_feat_rx_ccid;
 	dmsk->dccpms_tx_ccid	     = sysctl_dccp_feat_tx_ccid;
-	dmsk->dccpms_ack_ratio	     = sysctl_dccp_feat_ack_ratio;
 	dmsk->dccpms_send_ack_vector = sysctl_dccp_feat_send_ack_vector;
 	dmsk->dccpms_send_ndp_count  = sysctl_dccp_feat_send_ndp_count;
 }
diff --git a/net/dccp/options.c b/net/dccp/options.c
index 67a171a1268c..515ad45013ad 100644
--- a/net/dccp/options.c
+++ b/net/dccp/options.c
@@ -26,7 +26,6 @@
 int sysctl_dccp_feat_sequence_window = DCCPF_INITIAL_SEQUENCE_WINDOW;
 int sysctl_dccp_feat_rx_ccid	      = DCCPF_INITIAL_CCID;
 int sysctl_dccp_feat_tx_ccid	      = DCCPF_INITIAL_CCID;
-int sysctl_dccp_feat_ack_ratio	      = DCCPF_INITIAL_ACK_RATIO;
 int sysctl_dccp_feat_send_ack_vector = DCCPF_INITIAL_SEND_ACK_VECTOR;
 int sysctl_dccp_feat_send_ndp_count  = DCCPF_INITIAL_SEND_NDP_COUNT;
 
diff --git a/net/dccp/sysctl.c b/net/dccp/sysctl.c
index 21295993fdb8..f6e54f433e29 100644
--- a/net/dccp/sysctl.c
+++ b/net/dccp/sysctl.c
@@ -40,13 +40,6 @@ static struct ctl_table dccp_default_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
-	{
-		.procname	= "ack_ratio",
-		.data		= &sysctl_dccp_feat_ack_ratio,
-		.maxlen		= sizeof(sysctl_dccp_feat_ack_ratio),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
 	{
 		.procname	= "send_ackvec",
 		.data		= &sysctl_dccp_feat_send_ack_vector,
-- 
cgit v1.2.3


From dd24c00191d5e4a1ae896aafe33c6b8095ab4bd1 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <dada1@cosmosbay.com>
Date: Tue, 25 Nov 2008 21:17:14 -0800
Subject: net: Use a percpu_counter for orphan_count

Instead of using one atomic_t per protocol, use a percpu_counter
for "orphan_count", to reduce cache line contention on
heavy duty network servers.

Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sock.h              |  2 +-
 include/net/tcp.h               |  2 +-
 net/dccp/dccp.h                 |  2 +-
 net/dccp/proto.c                | 16 ++++++++++------
 net/ipv4/inet_connection_sock.c |  4 ++--
 net/ipv4/proc.c                 |  2 +-
 net/ipv4/tcp.c                  | 12 +++++++-----
 net/ipv4/tcp_timer.c            |  2 +-
 8 files changed, 24 insertions(+), 18 deletions(-)

(limited to 'net/dccp/dccp.h')

diff --git a/include/net/sock.h b/include/net/sock.h
index a2a3890959c4..5a3a151bd730 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -666,7 +666,7 @@ struct proto {
 	unsigned int		obj_size;
 	int			slab_flags;
 
-	atomic_t		*orphan_count;
+	struct percpu_counter	*orphan_count;
 
 	struct request_sock_ops	*rsk_prot;
 	struct timewait_sock_ops *twsk_prot;
diff --git a/include/net/tcp.h b/include/net/tcp.h
index cbca3b8a133d..de1e91d959b8 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -46,7 +46,7 @@
 
 extern struct inet_hashinfo tcp_hashinfo;
 
-extern atomic_t tcp_orphan_count;
+extern struct percpu_counter tcp_orphan_count;
 extern void tcp_time_wait(struct sock *sk, int state, int timeo);
 
 #define MAX_TCP_HEADER	(128 + MAX_HEADER)
diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h
index 031ce350d3c1..33a1127270c1 100644
--- a/net/dccp/dccp.h
+++ b/net/dccp/dccp.h
@@ -49,7 +49,7 @@ extern int dccp_debug;
 
 extern struct inet_hashinfo dccp_hashinfo;
 
-extern atomic_t dccp_orphan_count;
+extern struct percpu_counter dccp_orphan_count;
 
 extern void dccp_time_wait(struct sock *sk, int state, int timeo);
 
diff --git a/net/dccp/proto.c b/net/dccp/proto.c
index ea85c423cdbd..db225f93cd5a 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -40,8 +40,7 @@ DEFINE_SNMP_STAT(struct dccp_mib, dccp_statistics) __read_mostly;
 
 EXPORT_SYMBOL_GPL(dccp_statistics);
 
-atomic_t dccp_orphan_count = ATOMIC_INIT(0);
-
+struct percpu_counter dccp_orphan_count;
 EXPORT_SYMBOL_GPL(dccp_orphan_count);
 
 struct inet_hashinfo dccp_hashinfo;
@@ -1000,7 +999,7 @@ adjudge_to_death:
 	state = sk->sk_state;
 	sock_hold(sk);
 	sock_orphan(sk);
-	atomic_inc(sk->sk_prot->orphan_count);
+	percpu_counter_inc(sk->sk_prot->orphan_count);
 
 	/*
 	 * It is the last release_sock in its life. It will remove backlog.
@@ -1064,18 +1063,21 @@ static int __init dccp_init(void)
 {
 	unsigned long goal;
 	int ehash_order, bhash_order, i;
-	int rc = -ENOBUFS;
+	int rc;
 
 	BUILD_BUG_ON(sizeof(struct dccp_skb_cb) >
 		     FIELD_SIZEOF(struct sk_buff, cb));
-
+	rc = percpu_counter_init(&dccp_orphan_count, 0);
+	if (rc)
+		goto out;
+	rc = -ENOBUFS;
 	inet_hashinfo_init(&dccp_hashinfo);
 	dccp_hashinfo.bind_bucket_cachep =
 		kmem_cache_create("dccp_bind_bucket",
 				  sizeof(struct inet_bind_bucket), 0,
 				  SLAB_HWCACHE_ALIGN, NULL);
 	if (!dccp_hashinfo.bind_bucket_cachep)
-		goto out;
+		goto out_free_percpu;
 
 	/*
 	 * Size and allocate the main established and bind bucket
@@ -1168,6 +1170,8 @@ out_free_dccp_ehash:
 out_free_bind_bucket_cachep:
 	kmem_cache_destroy(dccp_hashinfo.bind_bucket_cachep);
 	dccp_hashinfo.bind_bucket_cachep = NULL;
+out_free_percpu:
+	percpu_counter_destroy(&dccp_orphan_count);
 	goto out;
 }
 
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 05af807ca9b9..1ccdbba528be 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -561,7 +561,7 @@ void inet_csk_destroy_sock(struct sock *sk)
 
 	sk_refcnt_debug_release(sk);
 
-	atomic_dec(sk->sk_prot->orphan_count);
+	percpu_counter_dec(sk->sk_prot->orphan_count);
 	sock_put(sk);
 }
 
@@ -641,7 +641,7 @@ void inet_csk_listen_stop(struct sock *sk)
 
 		sock_orphan(child);
 
-		atomic_inc(sk->sk_prot->orphan_count);
+		percpu_counter_inc(sk->sk_prot->orphan_count);
 
 		inet_csk_destroy_sock(child);
 
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index 4944b47ad628..614958b7c276 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -54,7 +54,7 @@ static int sockstat_seq_show(struct seq_file *seq, void *v)
 	socket_seq_show(seq);
 	seq_printf(seq, "TCP: inuse %d orphan %d tw %d alloc %d mem %d\n",
 		   sock_prot_inuse_get(net, &tcp_prot),
-		   atomic_read(&tcp_orphan_count),
+		   (int)percpu_counter_sum_positive(&tcp_orphan_count),
 		   tcp_death_row.tw_count,
 		   (int)percpu_counter_sum_positive(&tcp_sockets_allocated),
 		   atomic_read(&tcp_memory_allocated));
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index e6fade9ebf62..019243408623 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -277,8 +277,7 @@
 
 int sysctl_tcp_fin_timeout __read_mostly = TCP_FIN_TIMEOUT;
 
-atomic_t tcp_orphan_count = ATOMIC_INIT(0);
-
+struct percpu_counter tcp_orphan_count;
 EXPORT_SYMBOL_GPL(tcp_orphan_count);
 
 int sysctl_tcp_mem[3] __read_mostly;
@@ -1837,7 +1836,7 @@ adjudge_to_death:
 	state = sk->sk_state;
 	sock_hold(sk);
 	sock_orphan(sk);
-	atomic_inc(sk->sk_prot->orphan_count);
+	percpu_counter_inc(sk->sk_prot->orphan_count);
 
 	/* It is the last release_sock in its life. It will remove backlog. */
 	release_sock(sk);
@@ -1888,9 +1887,11 @@ adjudge_to_death:
 		}
 	}
 	if (sk->sk_state != TCP_CLOSE) {
+		int orphan_count = percpu_counter_read_positive(
+						sk->sk_prot->orphan_count);
+
 		sk_mem_reclaim(sk);
-		if (tcp_too_many_orphans(sk,
-				atomic_read(sk->sk_prot->orphan_count))) {
+		if (tcp_too_many_orphans(sk, orphan_count)) {
 			if (net_ratelimit())
 				printk(KERN_INFO "TCP: too many of orphaned "
 				       "sockets\n");
@@ -2689,6 +2690,7 @@ void __init tcp_init(void)
 	BUILD_BUG_ON(sizeof(struct tcp_skb_cb) > sizeof(skb->cb));
 
 	percpu_counter_init(&tcp_sockets_allocated, 0);
+	percpu_counter_init(&tcp_orphan_count, 0);
 	tcp_hashinfo.bind_bucket_cachep =
 		kmem_cache_create("tcp_bind_bucket",
 				  sizeof(struct inet_bind_bucket), 0,
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 3df339e3e363..cc4e6d27dedc 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -65,7 +65,7 @@ static void tcp_write_err(struct sock *sk)
 static int tcp_out_of_resources(struct sock *sk, int do_reset)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
-	int orphans = atomic_read(&tcp_orphan_count);
+	int orphans = percpu_counter_read_positive(&tcp_orphan_count);
 
 	/* If peer does not open window for long time, or did not transmit
 	 * anything for long time, penalize it. */
-- 
cgit v1.2.3


From 0971d17ca3d80f61863f4750091a64448bf91600 Mon Sep 17 00:00:00 2001
From: Gerrit Renker <gerrit@erg.abdn.ac.uk>
Date: Mon, 1 Dec 2008 23:27:31 -0800
Subject: dccp: Insert feature-negotiation options into skb

This patch replaces the earlier insertion routine from options.c, so that
code specific to feature negotiation can remain in feat.c. This is possible
by calling a function already existing in options.c.

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>
---
 net/dccp/dccp.h |  2 ++
 net/dccp/feat.c | 65 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 67 insertions(+)

(limited to 'net/dccp/dccp.h')

diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h
index 33a1127270c1..4ed7c5936bcf 100644
--- a/net/dccp/dccp.h
+++ b/net/dccp/dccp.h
@@ -443,6 +443,8 @@ static inline int dccp_ack_pending(const struct sock *sk)
 
 extern int  dccp_feat_finalise_settings(struct dccp_sock *dp);
 extern int  dccp_feat_server_ccid_dependencies(struct dccp_request_sock *dreq);
+extern int  dccp_feat_insert_opts(struct dccp_sock*, struct dccp_request_sock*,
+				  struct sk_buff *skb);
 extern void dccp_feat_list_purge(struct list_head *fn_list);
 
 extern int dccp_insert_options(struct sock *sk, struct sk_buff *skb);
diff --git a/net/dccp/feat.c b/net/dccp/feat.c
index 2c2216f64b1b..d90caa7198c3 100644
--- a/net/dccp/feat.c
+++ b/net/dccp/feat.c
@@ -272,6 +272,20 @@ cloning_failed:
 	return -ENOMEM;
 }
 
+/**
+ * dccp_feat_valid_nn_length  -  Enforce length constraints on NN options
+ * Length is between 0 and %DCCP_OPTVAL_MAXLEN. Used for outgoing packets only,
+ * incoming options are accepted as long as their values are valid.
+ */
+static u8 dccp_feat_valid_nn_length(u8 feat_num)
+{
+	if (feat_num == DCCPF_ACK_RATIO)	/* RFC 4340, 11.3 and 6.6.8 */
+		return 2;
+	if (feat_num == DCCPF_SEQUENCE_WINDOW)	/* RFC 4340, 7.5.2 and 6.5  */
+		return 6;
+	return 0;
+}
+
 static u8 dccp_feat_is_valid_nn_val(u8 feat_num, u64 val)
 {
 	switch (feat_num) {
@@ -313,6 +327,57 @@ static u8 dccp_feat_sp_list_ok(u8 feat_num, u8 const *sp_list, u8 sp_len)
 	return 1;
 }
 
+/**
+ * dccp_feat_insert_opts  -  Generate FN options from current list state
+ * @skb: next sk_buff to be sent to the peer
+ * @dp: for client during handshake and general negotiation
+ * @dreq: used by the server only (all Changes/Confirms in LISTEN/RESPOND)
+ */
+int dccp_feat_insert_opts(struct dccp_sock *dp, struct dccp_request_sock *dreq,
+			  struct sk_buff *skb)
+{
+	struct list_head *fn = dreq ? &dreq->dreq_featneg : &dp->dccps_featneg;
+	struct dccp_feat_entry *pos, *next;
+	u8 opt, type, len, *ptr, nn_in_nbo[DCCP_OPTVAL_MAXLEN];
+	bool rpt;
+
+	/* put entries into @skb in the order they appear in the list */
+	list_for_each_entry_safe_reverse(pos, next, fn, node) {
+		opt  = dccp_feat_genopt(pos);
+		type = dccp_feat_type(pos->feat_num);
+		rpt  = false;
+
+		if (pos->empty_confirm) {
+			len = 0;
+			ptr = NULL;
+		} else {
+			if (type == FEAT_SP) {
+				len = pos->val.sp.len;
+				ptr = pos->val.sp.vec;
+				rpt = pos->needs_confirm;
+			} else if (type == FEAT_NN) {
+				len = dccp_feat_valid_nn_length(pos->feat_num);
+				ptr = nn_in_nbo;
+				dccp_encode_value_var(pos->val.nn, ptr, len);
+			} else {
+				DCCP_BUG("unknown feature %u", pos->feat_num);
+				return -1;
+			}
+		}
+
+		if (dccp_insert_fn_opt(skb, opt, pos->feat_num, ptr, len, rpt))
+			return -1;
+		if (pos->needs_mandatory && dccp_insert_option_mandatory(skb))
+			return -1;
+		/*
+		 * Enter CHANGING after transmitting the Change option (6.6.2).
+		 */
+		if (pos->state == FEAT_INITIALISING)
+			pos->state = FEAT_CHANGING;
+	}
+	return 0;
+}
+
 /**
  * __feat_register_nn  -  Register new NN value on socket
  * @fn: feature-negotiation list to register with
-- 
cgit v1.2.3


From 422d9cdcb85b3622d08a590fed66021af7aea333 Mon Sep 17 00:00:00 2001
From: Gerrit Renker <gerrit@erg.abdn.ac.uk>
Date: Mon, 1 Dec 2008 23:34:01 -0800
Subject: dccp: Feature activation handlers

This patch provides the post-processing of feature negotiation state, after
the negotiation has completed.

To this purpose, handlers are used and added to the dccp_feat_table. Each
handler is passed a boolean flag whether the RX or TX side of the feature
is meant.

Several handlers are provided already, new handlers can easily be added.

The initialisation is now fully dynamic, i.e. CCIDs are activated only
after the feature negotiation. The integration of this dynamic activation
is done in the subsequent patches.

Thanks to Wei Yongjun for pointing out the necessity of skipping over empty
Confirm options while copying the negotiated feature values.

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>
---
 net/dccp/dccp.h |   1 +
 net/dccp/feat.c | 213 +++++++++++++++++++++++++++++++++++++++++++++++++++++---
 2 files changed, 204 insertions(+), 10 deletions(-)

(limited to 'net/dccp/dccp.h')

diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h
index 4ed7c5936bcf..94f6785f81ec 100644
--- a/net/dccp/dccp.h
+++ b/net/dccp/dccp.h
@@ -445,6 +445,7 @@ extern int  dccp_feat_finalise_settings(struct dccp_sock *dp);
 extern int  dccp_feat_server_ccid_dependencies(struct dccp_request_sock *dreq);
 extern int  dccp_feat_insert_opts(struct dccp_sock*, struct dccp_request_sock*,
 				  struct sk_buff *skb);
+extern int  dccp_feat_activate_values(struct sock *sk, struct list_head *fn);
 extern void dccp_feat_list_purge(struct list_head *fn_list);
 
 extern int dccp_insert_options(struct sock *sk, struct sk_buff *skb);
diff --git a/net/dccp/feat.c b/net/dccp/feat.c
index bc00c038e4a5..b127189550f1 100644
--- a/net/dccp/feat.c
+++ b/net/dccp/feat.c
@@ -25,11 +25,101 @@
 
 #define DCCP_FEAT_SP_NOAGREE (-123)
 
+/*
+ * Feature activation handlers.
+ *
+ * These all use an u64 argument, to provide enough room for NN/SP features. At
+ * this stage the negotiated values have been checked to be within their range.
+ */
+static int dccp_hdlr_ccid(struct sock *sk, u64 ccid, bool rx)
+{
+	struct dccp_sock *dp = dccp_sk(sk);
+	struct ccid *new_ccid = ccid_new(ccid, sk, rx, gfp_any());
+
+	if (new_ccid == NULL)
+		return -ENOMEM;
+
+	if (rx) {
+		ccid_hc_rx_delete(dp->dccps_hc_rx_ccid, sk);
+		dp->dccps_hc_rx_ccid = new_ccid;
+	} else {
+		ccid_hc_tx_delete(dp->dccps_hc_tx_ccid, sk);
+		dp->dccps_hc_tx_ccid = new_ccid;
+	}
+	return 0;
+}
+
+static int dccp_hdlr_seq_win(struct sock *sk, u64 seq_win, bool rx)
+{
+	if (!rx)
+		dccp_msk(sk)->dccpms_sequence_window = seq_win;
+	return 0;
+}
+
+static int dccp_hdlr_ack_ratio(struct sock *sk, u64 ratio, bool rx)
+{
+	if (rx)
+		dccp_sk(sk)->dccps_r_ack_ratio = ratio;
+	else
+		dccp_sk(sk)->dccps_l_ack_ratio = ratio;
+	return 0;
+}
+
+static int dccp_hdlr_ackvec(struct sock *sk, u64 enable, bool rx)
+{
+	struct dccp_sock *dp = dccp_sk(sk);
+
+	if (rx) {
+		if (enable && dp->dccps_hc_rx_ackvec == NULL) {
+			dp->dccps_hc_rx_ackvec = dccp_ackvec_alloc(gfp_any());
+			if (dp->dccps_hc_rx_ackvec == NULL)
+				return -ENOMEM;
+		} else if (!enable) {
+			dccp_ackvec_free(dp->dccps_hc_rx_ackvec);
+			dp->dccps_hc_rx_ackvec = NULL;
+		}
+	}
+	return 0;
+}
+
+static int dccp_hdlr_ndp(struct sock *sk, u64 enable, bool rx)
+{
+	if (!rx)
+		dccp_msk(sk)->dccpms_send_ndp_count = (enable > 0);
+	return 0;
+}
+
+/*
+ * Minimum Checksum Coverage is located at the RX side (9.2.1). This means that
+ * `rx' holds when the sending peer informs about his partial coverage via a
+ * ChangeR() option. In the other case, we are the sender and the receiver
+ * announces its coverage via ChangeL() options. The policy here is to honour
+ * such communication by enabling the corresponding partial coverage - but only
+ * if it has not been set manually before; the warning here means that all
+ * packets will be dropped.
+ */
+static int dccp_hdlr_min_cscov(struct sock *sk, u64 cscov, bool rx)
+{
+	struct dccp_sock *dp = dccp_sk(sk);
+
+	if (rx)
+		dp->dccps_pcrlen = cscov;
+	else {
+		if (dp->dccps_pcslen == 0)
+			dp->dccps_pcslen = cscov;
+		else if (cscov > dp->dccps_pcslen)
+			DCCP_WARN("CsCov %u too small, peer requires >= %u\n",
+				  dp->dccps_pcslen, (u8)cscov);
+	}
+	return 0;
+}
+
 static const struct {
 	u8			feat_num;		/* DCCPF_xxx */
 	enum dccp_feat_type	rxtx;			/* RX or TX  */
 	enum dccp_feat_type	reconciliation;		/* SP or NN  */
 	u8			default_value;		/* as in 6.4 */
+	int (*activation_hdlr)(struct sock *sk, u64 val, bool rx);
 /*
  *    Lookup table for location and type of features (from RFC 4340/4342)
  *  +--------------------------+----+-----+----+----+---------+-----------+
@@ -49,16 +139,16 @@ static const struct {
  *  +--------------------------+----+-----+----+----+---------+-----------+
  */
 } dccp_feat_table[] = {
-	{ DCCPF_CCID,		 FEAT_AT_TX, FEAT_SP, 2 },
-	{ DCCPF_SHORT_SEQNOS,	 FEAT_AT_TX, FEAT_SP, 0 },
-	{ DCCPF_SEQUENCE_WINDOW, FEAT_AT_TX, FEAT_NN, 100 },
-	{ DCCPF_ECN_INCAPABLE,	 FEAT_AT_RX, FEAT_SP, 0 },
-	{ DCCPF_ACK_RATIO,	 FEAT_AT_TX, FEAT_NN, 2 },
-	{ DCCPF_SEND_ACK_VECTOR, FEAT_AT_RX, FEAT_SP, 0 },
-	{ DCCPF_SEND_NDP_COUNT,  FEAT_AT_TX, FEAT_SP, 0 },
-	{ DCCPF_MIN_CSUM_COVER,  FEAT_AT_RX, FEAT_SP, 0 },
-	{ DCCPF_DATA_CHECKSUM,	 FEAT_AT_RX, FEAT_SP, 0 },
-	{ DCCPF_SEND_LEV_RATE,	 FEAT_AT_RX, FEAT_SP, 0 },
+	{ DCCPF_CCID,		 FEAT_AT_TX, FEAT_SP, 2,   dccp_hdlr_ccid     },
+	{ DCCPF_SHORT_SEQNOS,	 FEAT_AT_TX, FEAT_SP, 0,   NULL },
+	{ DCCPF_SEQUENCE_WINDOW, FEAT_AT_TX, FEAT_NN, 100, dccp_hdlr_seq_win  },
+	{ DCCPF_ECN_INCAPABLE,	 FEAT_AT_RX, FEAT_SP, 0,   NULL },
+	{ DCCPF_ACK_RATIO,	 FEAT_AT_TX, FEAT_NN, 2,   dccp_hdlr_ack_ratio},
+	{ DCCPF_SEND_ACK_VECTOR, FEAT_AT_RX, FEAT_SP, 0,   dccp_hdlr_ackvec   },
+	{ DCCPF_SEND_NDP_COUNT,  FEAT_AT_TX, FEAT_SP, 0,   dccp_hdlr_ndp      },
+	{ DCCPF_MIN_CSUM_COVER,  FEAT_AT_RX, FEAT_SP, 0,   dccp_hdlr_min_cscov},
+	{ DCCPF_DATA_CHECKSUM,	 FEAT_AT_RX, FEAT_SP, 0,   NULL },
+	{ DCCPF_SEND_LEV_RATE,	 FEAT_AT_RX, FEAT_SP, 0,   NULL },
 };
 #define DCCP_FEAT_SUPPORTED_MAX		ARRAY_SIZE(dccp_feat_table)
 
@@ -104,6 +194,41 @@ static int dccp_feat_default_value(u8 feat_num)
 	return idx < 0 ? 0 : dccp_feat_table[idx].default_value;
 }
 
+static int __dccp_feat_activate(struct sock *sk, const int idx,
+				const bool is_local, dccp_feat_val const *fval)
+{
+	bool rx;
+	u64 val;
+
+	if (idx < 0 || idx >= DCCP_FEAT_SUPPORTED_MAX)
+		return -1;
+	if (dccp_feat_table[idx].activation_hdlr == NULL)
+		return 0;
+
+	if (fval == NULL) {
+		val = dccp_feat_table[idx].default_value;
+	} else if (dccp_feat_table[idx].reconciliation == FEAT_SP) {
+		if (fval->sp.vec == NULL) {
+			/*
+			 * This can happen when an empty Confirm is sent
+			 * for an SP (i.e. known) feature. In this case
+			 * we would be using the default anyway.
+			 */
+			DCCP_CRIT("Feature #%d undefined: using default", idx);
+			val = dccp_feat_table[idx].default_value;
+		} else {
+			val = fval->sp.vec[0];
+		}
+	} else {
+		val = fval->nn;
+	}
+
+	/* Location is RX if this is a local-RX or remote-TX feature */
+	rx = (is_local == (dccp_feat_table[idx].rxtx == FEAT_AT_RX));
+
+	return dccp_feat_table[idx].activation_hdlr(sk, val, rx);
+}
+
 /* Test for "Req'd" feature (RFC 4340, 6.4) */
 static inline int dccp_feat_must_be_understood(u8 feat_num)
 {
@@ -1512,6 +1637,74 @@ out:
 
 EXPORT_SYMBOL_GPL(dccp_feat_init);
 
+int dccp_feat_activate_values(struct sock *sk, struct list_head *fn_list)
+{
+	struct dccp_sock *dp = dccp_sk(sk);
+	struct dccp_feat_entry *cur, *next;
+	int idx;
+	dccp_feat_val *fvals[DCCP_FEAT_SUPPORTED_MAX][2] = {
+		 [0 ... DCCP_FEAT_SUPPORTED_MAX-1] = { NULL, NULL }
+	};
+
+	list_for_each_entry(cur, fn_list, node) {
+		/*
+		 * An empty Confirm means that either an unknown feature type
+		 * or an invalid value was present. In the first case there is
+		 * nothing to activate, in the other the default value is used.
+		 */
+		if (cur->empty_confirm)
+			continue;
+
+		idx = dccp_feat_index(cur->feat_num);
+		if (idx < 0) {
+			DCCP_BUG("Unknown feature %u", cur->feat_num);
+			goto activation_failed;
+		}
+		if (cur->state != FEAT_STABLE) {
+			DCCP_CRIT("Negotiation of %s %u failed in state %u",
+				  cur->is_local ? "local" : "remote",
+				  cur->feat_num, cur->state);
+			goto activation_failed;
+		}
+		fvals[idx][cur->is_local] = &cur->val;
+	}
+
+	/*
+	 * Activate in decreasing order of index, so that the CCIDs are always
+	 * activated as the last feature. This avoids the case where a CCID
+	 * relies on the initialisation of one or more features that it depends
+	 * on (e.g. Send NDP Count, Send Ack Vector, and Ack Ratio features).
+	 */
+	for (idx = DCCP_FEAT_SUPPORTED_MAX; --idx >= 0;)
+		if (__dccp_feat_activate(sk, idx, 0, fvals[idx][0]) ||
+		    __dccp_feat_activate(sk, idx, 1, fvals[idx][1])) {
+			DCCP_CRIT("Could not activate %d", idx);
+			goto activation_failed;
+		}
+
+	/* Clean up Change options which have been confirmed already */
+	list_for_each_entry_safe(cur, next, fn_list, node)
+		if (!cur->needs_confirm)
+			dccp_feat_list_pop(cur);
+
+	dccp_pr_debug("Activation OK\n");
+	return 0;
+
+activation_failed:
+	/*
+	 * We clean up everything that may have been allocated, since
+	 * it is difficult to track at which stage negotiation failed.
+	 * This is ok, since all allocation functions below are robust
+	 * against NULL arguments.
+	 */
+	ccid_hc_rx_delete(dp->dccps_hc_rx_ccid, sk);
+	ccid_hc_tx_delete(dp->dccps_hc_tx_ccid, sk);
+	dp->dccps_hc_rx_ccid = dp->dccps_hc_tx_ccid = NULL;
+	dccp_ackvec_free(dp->dccps_hc_rx_ackvec);
+	dp->dccps_hc_rx_ackvec = NULL;
+	return -1;
+}
+
 #ifdef CONFIG_IP_DCCP_DEBUG
 const char *dccp_feat_typename(const u8 type)
 {
-- 
cgit v1.2.3


From 4098dce5be537a157eed4a326efd464109825b8b Mon Sep 17 00:00:00 2001
From: Gerrit Renker <gerrit@erg.abdn.ac.uk>
Date: Mon, 8 Dec 2008 01:18:37 -0800
Subject: dccp: Remove manual influence on NDP Count feature

Updating the NDP count feature is handled automatically now:
 * for CCID-2 it is disabled, since the code does not use NDP counts;
 * for CCID-3 it is enabled, as NDP counts are used to determine loss lengths.

Allowing the user to change NDP values leads to unpredictable and failing
behaviour, since it is then possible to disable NDP counts even when they
are needed (e.g. in CCID-3).

This means that only those user settings are sensible that agree with the
values for Send NDP Count implied by the choice of CCID. But those settings
are already activated by the feature negotiation (CCID dependency tracking),
hence this form of support is redundant.

At startup the initialisation of the NDP count feature uses the default
value of 0, which is done implicitly by the zeroing-out of the socket when
it is allocated. If the choice of CCID or feature negotiation enables NDP
count, this will then be updated via the NDP activation handler.

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>
---
 Documentation/networking/dccp.txt | 3 ---
 include/linux/dccp.h              | 4 ++--
 net/dccp/dccp.h                   | 1 -
 net/dccp/feat.c                   | 2 +-
 net/dccp/minisocks.c              | 1 -
 net/dccp/options.c                | 4 +---
 net/dccp/sysctl.c                 | 7 -------
 7 files changed, 4 insertions(+), 18 deletions(-)

(limited to 'net/dccp/dccp.h')

diff --git a/Documentation/networking/dccp.txt b/Documentation/networking/dccp.txt
index a203d132dbef..1403745ab406 100644
--- a/Documentation/networking/dccp.txt
+++ b/Documentation/networking/dccp.txt
@@ -133,9 +133,6 @@ retries2
 	importance for retransmitted acknowledgments and feature negotiation,
 	data packets are never retransmitted. Analogue of tcp_retries2.
 
-send_ndp = 1
-	Whether or not to send NDP count options (sec. 7.7.2).
-
 send_ackvec = 1
 	Whether or not to send Ack Vector options (sec. 11.5).
 
diff --git a/include/linux/dccp.h b/include/linux/dccp.h
index 46daea312d92..60e94438eadd 100644
--- a/include/linux/dccp.h
+++ b/include/linux/dccp.h
@@ -371,14 +371,12 @@ static inline unsigned int dccp_hdr_len(const struct sk_buff *skb)
   *
   * @dccpms_sequence_window - Sequence Window Feature (section 7.5.2)
   * @dccpms_send_ack_vector - Send Ack Vector Feature (section 11.5)
-  * @dccpms_send_ndp_count - Send NDP Count Feature (7.7.2)
   * @dccpms_pending - List of features being negotiated
   * @dccpms_conf -
   */
 struct dccp_minisock {
 	__u64			dccpms_sequence_window;
 	__u8			dccpms_send_ack_vector;
-	__u8			dccpms_send_ndp_count;
 	struct list_head	dccpms_pending;
 	struct list_head	dccpms_conf;
 };
@@ -490,6 +488,7 @@ struct dccp_ackvec;
  * @dccps_r_ack_ratio - feature-remote Ack Ratio
  * @dccps_pcslen - sender   partial checksum coverage (via sockopt)
  * @dccps_pcrlen - receiver partial checksum coverage (via sockopt)
+ * @dccps_send_ndp_count - local Send NDP Count feature (7.7.2)
  * @dccps_ndp_count - number of Non Data Packets since last data packet
  * @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)
@@ -529,6 +528,7 @@ struct dccp_sock {
 	__u16				dccps_r_ack_ratio;
 	__u8				dccps_pcslen:4;
 	__u8				dccps_pcrlen:4;
+	__u8				dccps_send_ndp_count:1;
 	__u64				dccps_ndp_count:48;
 	unsigned long			dccps_rate_last;
 	struct dccp_minisock		dccps_minisock;
diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h
index 94f6785f81ec..e0759d098b9a 100644
--- a/net/dccp/dccp.h
+++ b/net/dccp/dccp.h
@@ -99,7 +99,6 @@ extern int  sysctl_dccp_feat_sequence_window;
 extern int  sysctl_dccp_feat_rx_ccid;
 extern int  sysctl_dccp_feat_tx_ccid;
 extern int  sysctl_dccp_feat_send_ack_vector;
-extern int  sysctl_dccp_feat_send_ndp_count;
 extern int  sysctl_dccp_tx_qlen;
 extern int  sysctl_dccp_sync_ratelimit;
 
diff --git a/net/dccp/feat.c b/net/dccp/feat.c
index a0d5891a37bf..30f9fb76b921 100644
--- a/net/dccp/feat.c
+++ b/net/dccp/feat.c
@@ -85,7 +85,7 @@ static int dccp_hdlr_ackvec(struct sock *sk, u64 enable, bool rx)
 static int dccp_hdlr_ndp(struct sock *sk, u64 enable, bool rx)
 {
 	if (!rx)
-		dccp_msk(sk)->dccpms_send_ndp_count = (enable > 0);
+		dccp_sk(sk)->dccps_send_ndp_count = (enable > 0);
 	return 0;
 }
 
diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c
index 210c346899ba..02b14812464a 100644
--- a/net/dccp/minisocks.c
+++ b/net/dccp/minisocks.c
@@ -46,7 +46,6 @@ void dccp_minisock_init(struct dccp_minisock *dmsk)
 {
 	dmsk->dccpms_sequence_window = sysctl_dccp_feat_sequence_window;
 	dmsk->dccpms_send_ack_vector = sysctl_dccp_feat_send_ack_vector;
-	dmsk->dccpms_send_ndp_count  = sysctl_dccp_feat_send_ndp_count;
 }
 
 void dccp_time_wait(struct sock *sk, int state, int timeo)
diff --git a/net/dccp/options.c b/net/dccp/options.c
index debb1008c7ad..e9d674874b4e 100644
--- a/net/dccp/options.c
+++ b/net/dccp/options.c
@@ -27,7 +27,6 @@ int sysctl_dccp_feat_sequence_window = DCCPF_INITIAL_SEQUENCE_WINDOW;
 int sysctl_dccp_feat_rx_ccid	      = DCCPF_INITIAL_CCID;
 int sysctl_dccp_feat_tx_ccid	      = DCCPF_INITIAL_CCID;
 int sysctl_dccp_feat_send_ack_vector = DCCPF_INITIAL_SEND_ACK_VECTOR;
-int sysctl_dccp_feat_send_ndp_count  = DCCPF_INITIAL_SEND_NDP_COUNT;
 
 u64 dccp_decode_value_var(const u8 *bf, const u8 len)
 {
@@ -531,8 +530,7 @@ int dccp_insert_options(struct sock *sk, struct sk_buff *skb)
 
 	DCCP_SKB_CB(skb)->dccpd_opt_len = 0;
 
-	if (dmsk->dccpms_send_ndp_count &&
-	    dccp_insert_option_ndp(sk, skb))
+	if (dp->dccps_send_ndp_count && dccp_insert_option_ndp(sk, skb))
 		return -1;
 
 	if (DCCP_SKB_CB(skb)->dccpd_type != DCCP_PKT_DATA) {
diff --git a/net/dccp/sysctl.c b/net/dccp/sysctl.c
index f6e54f433e29..587c12f915c1 100644
--- a/net/dccp/sysctl.c
+++ b/net/dccp/sysctl.c
@@ -47,13 +47,6 @@ static struct ctl_table dccp_default_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
-	{
-		.procname	= "send_ndp",
-		.data		= &sysctl_dccp_feat_send_ndp_count,
-		.maxlen		= sizeof(sysctl_dccp_feat_send_ndp_count),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
 	{
 		.procname	= "request_retries",
 		.data		= &sysctl_dccp_request_retries,
-- 
cgit v1.2.3


From 6fdd34d43bff8be9bb925b49d87a0ee144d2ab07 Mon Sep 17 00:00:00 2001
From: Gerrit Renker <gerrit@erg.abdn.ac.uk>
Date: Mon, 8 Dec 2008 01:19:06 -0800
Subject: dccp ccid-2: Phase out the use of boolean Ack Vector sysctl

This removes the use of the sysctl and the minisock variable for the Send Ack
Vector feature, as it now is handled fully dynamically via feature negotiation
(i.e. when CCID-2 is enabled, Ack Vectors are automatically enabled as per
 RFC 4341, 4.).

Using a sysctl in parallel to this implementation would open the door to
crashes, since much of the code relies on tests of the boolean minisock /
sysctl variable. Thus, this patch replaces all tests of type

	if (dccp_msk(sk)->dccpms_send_ack_vector)
		/* ... */
with
	if (dp->dccps_hc_rx_ackvec != NULL)
		/* ... */

The dccps_hc_rx_ackvec is allocated by the dccp_hdlr_ackvec() when feature
negotiation concluded that Ack Vectors are to be used on the half-connection.
Otherwise, it is NULL (due to dccp_init_sock/dccp_create_openreq_child),
so that the test is a valid one.

The activation handler for Ack Vectors is called as soon as the feature
negotiation has concluded at the
 * server when the Ack marking the transition RESPOND => OPEN arrives;
 * client after it has sent its ACK, marking the transition REQUEST => PARTOPEN.

Adding the sequence number of the Response packet to the Ack Vector has been
removed, since
 (a) connection establishment implies that the Response has been received;
 (b) the CCIDs only look at packets received in the (PART)OPEN state, i.e.
     this entry will always be ignored;
 (c) it can not be used for anything useful - to detect loss for instance, only
     packets received after the loss can serve as pseudo-dupacks.

There was a FIXME to change the error code when dccp_ackvec_add() fails.
I removed this after finding out that:
 * the check whether ackno < ISN is already made earlier,
 * this Response is likely the 1st packet with an Ackno that the client gets,
 * so when dccp_ackvec_add() fails, the reason is likely not a packet error.

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>
---
 Documentation/networking/dccp.txt |  3 ---
 include/linux/dccp.h              |  3 ---
 net/dccp/dccp.h                   |  3 +--
 net/dccp/diag.c                   |  2 +-
 net/dccp/input.c                  | 12 +++---------
 net/dccp/minisocks.c              |  1 -
 net/dccp/options.c                |  7 ++-----
 net/dccp/proto.c                  |  3 +--
 net/dccp/sysctl.c                 |  7 -------
 9 files changed, 8 insertions(+), 33 deletions(-)

(limited to 'net/dccp/dccp.h')

diff --git a/Documentation/networking/dccp.txt b/Documentation/networking/dccp.txt
index 1403745ab406..7a3bb1abb830 100644
--- a/Documentation/networking/dccp.txt
+++ b/Documentation/networking/dccp.txt
@@ -133,9 +133,6 @@ retries2
 	importance for retransmitted acknowledgments and feature negotiation,
 	data packets are never retransmitted. Analogue of tcp_retries2.
 
-send_ackvec = 1
-	Whether or not to send Ack Vector options (sec. 11.5).
-
 tx_ccid = 2
 	Default CCID for the sender-receiver half-connection. Depending on the
 	choice of CCID, the Send Ack Vector feature is enabled automatically.
diff --git a/include/linux/dccp.h b/include/linux/dccp.h
index 60e94438eadd..61734e27abb7 100644
--- a/include/linux/dccp.h
+++ b/include/linux/dccp.h
@@ -360,7 +360,6 @@ static inline unsigned int dccp_hdr_len(const struct sk_buff *skb)
 #define DCCPF_INITIAL_SEQUENCE_WINDOW		100
 #define DCCPF_INITIAL_ACK_RATIO			2
 #define DCCPF_INITIAL_CCID			DCCPC_CCID2
-#define DCCPF_INITIAL_SEND_ACK_VECTOR		1
 /* FIXME: for now we're default to 1 but it should really be 0 */
 #define DCCPF_INITIAL_SEND_NDP_COUNT		1
 
@@ -370,13 +369,11 @@ static inline unsigned int dccp_hdr_len(const struct sk_buff *skb)
   * Will be used to pass the state from dccp_request_sock to dccp_sock.
   *
   * @dccpms_sequence_window - Sequence Window Feature (section 7.5.2)
-  * @dccpms_send_ack_vector - Send Ack Vector Feature (section 11.5)
   * @dccpms_pending - List of features being negotiated
   * @dccpms_conf -
   */
 struct dccp_minisock {
 	__u64			dccpms_sequence_window;
-	__u8			dccpms_send_ack_vector;
 	struct list_head	dccpms_pending;
 	struct list_head	dccpms_conf;
 };
diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h
index e0759d098b9a..0bc4c9a02e19 100644
--- a/net/dccp/dccp.h
+++ b/net/dccp/dccp.h
@@ -98,7 +98,6 @@ extern int  sysctl_dccp_retries2;
 extern int  sysctl_dccp_feat_sequence_window;
 extern int  sysctl_dccp_feat_rx_ccid;
 extern int  sysctl_dccp_feat_tx_ccid;
-extern int  sysctl_dccp_feat_send_ack_vector;
 extern int  sysctl_dccp_tx_qlen;
 extern int  sysctl_dccp_sync_ratelimit;
 
@@ -434,7 +433,7 @@ static inline int dccp_ack_pending(const struct sock *sk)
 	const struct dccp_sock *dp = dccp_sk(sk);
 	return dp->dccps_timestamp_echo != 0 ||
 #ifdef CONFIG_IP_DCCP_ACKVEC
-	       (dccp_msk(sk)->dccpms_send_ack_vector &&
+	       (dp->dccps_hc_rx_ackvec != NULL &&
 		dccp_ackvec_pending(dp->dccps_hc_rx_ackvec)) ||
 #endif
 	       inet_csk_ack_scheduled(sk);
diff --git a/net/dccp/diag.c b/net/dccp/diag.c
index d1e100395efb..652a1b67f727 100644
--- a/net/dccp/diag.c
+++ b/net/dccp/diag.c
@@ -29,7 +29,7 @@ static void dccp_get_info(struct sock *sk, struct tcp_info *info)
 	info->tcpi_backoff	= icsk->icsk_backoff;
 	info->tcpi_pmtu		= icsk->icsk_pmtu_cookie;
 
-	if (dccp_msk(sk)->dccpms_send_ack_vector)
+	if (dp->dccps_hc_rx_ackvec != NULL)
 		info->tcpi_options |= TCPI_OPT_SACK;
 
 	ccid_hc_rx_get_info(dp->dccps_hc_rx_ccid, sk, info);
diff --git a/net/dccp/input.c b/net/dccp/input.c
index 0672b7e1763e..5eb443f656c1 100644
--- a/net/dccp/input.c
+++ b/net/dccp/input.c
@@ -163,7 +163,7 @@ static void dccp_event_ack_recv(struct sock *sk, struct sk_buff *skb)
 {
 	struct dccp_sock *dp = dccp_sk(sk);
 
-	if (dccp_msk(sk)->dccpms_send_ack_vector)
+	if (dp->dccps_hc_rx_ackvec != NULL)
 		dccp_ackvec_check_rcv_ackno(dp->dccps_hc_rx_ackvec, sk,
 					    DCCP_SKB_CB(skb)->dccpd_ack_seq);
 }
@@ -375,7 +375,7 @@ int dccp_rcv_established(struct sock *sk, struct sk_buff *skb,
 	if (DCCP_SKB_CB(skb)->dccpd_ack_seq != DCCP_PKT_WITHOUT_ACK_SEQ)
 		dccp_event_ack_recv(sk, skb);
 
-	if (dccp_msk(sk)->dccpms_send_ack_vector &&
+	if (dp->dccps_hc_rx_ackvec != NULL &&
 	    dccp_ackvec_add(dp->dccps_hc_rx_ackvec, sk,
 			    DCCP_SKB_CB(skb)->dccpd_seq,
 			    DCCP_ACKVEC_STATE_RECEIVED))
@@ -434,12 +434,6 @@ static int dccp_rcv_request_sent_state_process(struct sock *sk,
 			dp->dccps_syn_rtt = dccp_sample_rtt(sk, 10 * (tstamp -
 			    dp->dccps_options_received.dccpor_timestamp_echo));
 
-		if (dccp_msk(sk)->dccpms_send_ack_vector &&
-		    dccp_ackvec_add(dp->dccps_hc_rx_ackvec, sk,
-				    DCCP_SKB_CB(skb)->dccpd_seq,
-				    DCCP_ACKVEC_STATE_RECEIVED))
-			goto out_invalid_packet; /* FIXME: change error code */
-
 		/* Stop the REQUEST timer */
 		inet_csk_clear_xmit_timer(sk, ICSK_TIME_RETRANS);
 		WARN_ON(sk->sk_send_head == NULL);
@@ -637,7 +631,7 @@ int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
 		if (dcb->dccpd_ack_seq != DCCP_PKT_WITHOUT_ACK_SEQ)
 			dccp_event_ack_recv(sk, skb);
 
-		if (dccp_msk(sk)->dccpms_send_ack_vector &&
+		if (dp->dccps_hc_rx_ackvec != NULL &&
 		    dccp_ackvec_add(dp->dccps_hc_rx_ackvec, sk,
 				    DCCP_SKB_CB(skb)->dccpd_seq,
 				    DCCP_ACKVEC_STATE_RECEIVED))
diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c
index 02b14812464a..6821ae33dd37 100644
--- a/net/dccp/minisocks.c
+++ b/net/dccp/minisocks.c
@@ -45,7 +45,6 @@ EXPORT_SYMBOL_GPL(dccp_death_row);
 void dccp_minisock_init(struct dccp_minisock *dmsk)
 {
 	dmsk->dccpms_sequence_window = sysctl_dccp_feat_sequence_window;
-	dmsk->dccpms_send_ack_vector = sysctl_dccp_feat_send_ack_vector;
 }
 
 void dccp_time_wait(struct sock *sk, int state, int timeo)
diff --git a/net/dccp/options.c b/net/dccp/options.c
index e9d674874b4e..7b1165c21f51 100644
--- a/net/dccp/options.c
+++ b/net/dccp/options.c
@@ -26,7 +26,6 @@
 int sysctl_dccp_feat_sequence_window = DCCPF_INITIAL_SEQUENCE_WINDOW;
 int sysctl_dccp_feat_rx_ccid	      = DCCPF_INITIAL_CCID;
 int sysctl_dccp_feat_tx_ccid	      = DCCPF_INITIAL_CCID;
-int sysctl_dccp_feat_send_ack_vector = DCCPF_INITIAL_SEND_ACK_VECTOR;
 
 u64 dccp_decode_value_var(const u8 *bf, const u8 len)
 {
@@ -145,8 +144,7 @@ int dccp_parse_options(struct sock *sk, struct dccp_request_sock *dreq,
 		case DCCPO_ACK_VECTOR_1:
 			if (dccp_packet_without_ack(skb))   /* RFC 4340, 11.4 */
 				break;
-
-			if (dccp_msk(sk)->dccpms_send_ack_vector &&
+			if (dp->dccps_hc_rx_ackvec != NULL &&
 			    dccp_ackvec_parse(sk, skb, &ackno, opt, value, len))
 				goto out_invalid_option;
 			break;
@@ -526,7 +524,6 @@ static void dccp_insert_option_padding(struct sk_buff *skb)
 int dccp_insert_options(struct sock *sk, struct sk_buff *skb)
 {
 	struct dccp_sock *dp = dccp_sk(sk);
-	struct dccp_minisock *dmsk = dccp_msk(sk);
 
 	DCCP_SKB_CB(skb)->dccpd_opt_len = 0;
 
@@ -547,7 +544,7 @@ int dccp_insert_options(struct sock *sk, struct sk_buff *skb)
 			if (dccp_insert_option_timestamp(sk, skb))
 				return -1;
 
-		} else if (dmsk->dccpms_send_ack_vector	&&
+		} else if (dp->dccps_hc_rx_ackvec != NULL &&
 			   dccp_ackvec_pending(dp->dccps_hc_rx_ackvec) &&
 			   dccp_insert_option_ackvec(sk, skb)) {
 				return -1;
diff --git a/net/dccp/proto.c b/net/dccp/proto.c
index 0941f8fe1675..d5c2bacb713c 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -201,7 +201,6 @@ EXPORT_SYMBOL_GPL(dccp_init_sock);
 void dccp_destroy_sock(struct sock *sk)
 {
 	struct dccp_sock *dp = dccp_sk(sk);
-	struct dccp_minisock *dmsk = dccp_msk(sk);
 
 	/*
 	 * DCCP doesn't use sk_write_queue, just sk_send_head
@@ -219,7 +218,7 @@ void dccp_destroy_sock(struct sock *sk)
 	kfree(dp->dccps_service_list);
 	dp->dccps_service_list = NULL;
 
-	if (dmsk->dccpms_send_ack_vector) {
+	if (dp->dccps_hc_rx_ackvec != NULL) {
 		dccp_ackvec_free(dp->dccps_hc_rx_ackvec);
 		dp->dccps_hc_rx_ackvec = NULL;
 	}
diff --git a/net/dccp/sysctl.c b/net/dccp/sysctl.c
index 587c12f915c1..018e210875e1 100644
--- a/net/dccp/sysctl.c
+++ b/net/dccp/sysctl.c
@@ -40,13 +40,6 @@ static struct ctl_table dccp_default_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
-	{
-		.procname	= "send_ackvec",
-		.data		= &sysctl_dccp_feat_send_ack_vector,
-		.maxlen		= sizeof(sysctl_dccp_feat_send_ack_vector),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
 	{
 		.procname	= "request_retries",
 		.data		= &sysctl_dccp_request_retries,
-- 
cgit v1.2.3