Merge master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6

* master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6:
  [NetLabel]: update docs with website information
  [NetLabel]: rework the Netlink attribute handling (part 2)
  [NetLabel]: rework the Netlink attribute handling (part 1)
  [Netlink]: add nla_validate_nested()
  [NETLINK]: add nla_for_each_nested() to the interface list
  [NetLabel]: change the SELinux permissions
  [NetLabel]: make the CIPSOv4 cache spinlocks bottom half safe
  [NetLabel]: correct improper handling of non-NetLabel peer contexts
  [TCP]: make cubic the default
  [TCP]: default congestion control menu
  [ATM] he: Fix __init/__devinit conflict
  [NETFILTER]: Add dscp,DSCP headers to header-y
  [DCCP]: Introduce dccp_probe
  [DCCP]: Use constants for CCIDs
  [DCCP]: Introduce constants for CCID numbers
  [DCCP]: Allow default/fallback service code.

32 files changed, 1389 insertions, 1505 deletions

diff --git a/Documentation/networking/dccp.txt b/Documentation/networking/dccp.txt
index c45daabd3bf..74563b38ffd 100644
--- a/Documentation/networking/dccp.txt
+++ b/Documentation/networking/dccp.txt
@@ -1,7 +1,6 @@
 DCCP protocol
 ============
 
-Last updated: 10 November 2005
 
 Contents
 ========
@@ -42,8 +41,11 @@ Socket options
 DCCP_SOCKOPT_PACKET_SIZE is used for CCID3 to set default packet size for
 calculations.
 
-DCCP_SOCKOPT_SERVICE sets the service. This is compulsory as per the
-specification. If you don't set it you will get EPROTO.
+DCCP_SOCKOPT_SERVICE sets the service. The specification mandates use of
+service codes (RFC 4340, sec. 8.1.2); if this socket option is not set,
+the socket will fall back to 0 (which means that no meaningful service code
+is present). Connecting sockets set at most one service option; for
+listening sockets, multiple service codes can be specified.
 
 Notes
 =====
diff --git a/MAINTAINERS b/MAINTAINERS
index 16af51ba44a..23348c0d37b 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -2031,6 +2031,13 @@ L:	netfilter@lists.netfilter.org
 L:	netfilter-devel@lists.netfilter.org
 S:	Supported
 
+NETLABEL
+P:	Paul Moore
+M:	paul.moore@hp.com
+W:	http://netlabel.sf.net
+L:	netdev@vger.kernel.org
+S:	Supported
+
 NETROM NETWORK LAYER
 P:	Ralf Baechle
 M:	ralf@linux-mips.org
diff --git a/drivers/atm/he.c b/drivers/atm/he.c
index 41e052fecd7..f2511b42dba 100644
--- a/drivers/atm/he.c
+++ b/drivers/atm/he.c
@@ -454,7 +454,7 @@ rate_to_atmf(unsigned rate)		/* cps to atm forum format */
 	return (NONZERO | (exp << 9) | (rate & 0x1ff));
 }
 
-static void __init
+static void __devinit
 he_init_rx_lbfp0(struct he_dev *he_dev)
 {
 	unsigned i, lbm_offset, lbufd_index, lbuf_addr, lbuf_count;
@@ -485,7 +485,7 @@ he_init_rx_lbfp0(struct he_dev *he_dev)
 	he_writel(he_dev, he_dev->r0_numbuffs, RLBF0_C);
 }
 
-static void __init
+static void __devinit
 he_init_rx_lbfp1(struct he_dev *he_dev)
 {
 	unsigned i, lbm_offset, lbufd_index, lbuf_addr, lbuf_count;
@@ -516,7 +516,7 @@ he_init_rx_lbfp1(struct he_dev *he_dev)
 	he_writel(he_dev, he_dev->r1_numbuffs, RLBF1_C);
 }
 
-static void __init
+static void __devinit
 he_init_tx_lbfp(struct he_dev *he_dev)
 {
 	unsigned i, lbm_offset, lbufd_index, lbuf_addr, lbuf_count;
@@ -546,7 +546,7 @@ he_init_tx_lbfp(struct he_dev *he_dev)
 	he_writel(he_dev, lbufd_index - 1, TLBF_T);
 }
 
-static int __init
+static int __devinit
 he_init_tpdrq(struct he_dev *he_dev)
 {
 	he_dev->tpdrq_base = pci_alloc_consistent(he_dev->pci_dev,
@@ -568,7 +568,7 @@ he_init_tpdrq(struct he_dev *he_dev)
 	return 0;
 }
 
-static void __init
+static void __devinit
 he_init_cs_block(struct he_dev *he_dev)
 {
 	unsigned clock, rate, delta;
@@ -664,7 +664,7 @@ he_init_cs_block(struct he_dev *he_dev)
 
 }
 
-static int __init
+static int __devinit
 he_init_cs_block_rcm(struct he_dev *he_dev)
 {
 	unsigned (*rategrid)[16][16];
@@ -785,7 +785,7 @@ he_init_cs_block_rcm(struct he_dev *he_dev)
 	return 0;
 }
 
-static int __init
+static int __devinit
 he_init_group(struct he_dev *he_dev, int group)
 {
 	int i;
@@ -955,7 +955,7 @@ he_init_group(struct he_dev *he_dev, int group)
 	return 0;
 }
 
-static int __init
+static int __devinit
 he_init_irq(struct he_dev *he_dev)
 {
 	int i;
diff --git a/include/linux/dccp.h b/include/linux/dccp.h
index 2d7671c92c0..d6f4ec467a4 100644
--- a/include/linux/dccp.h
+++ b/include/linux/dccp.h
@@ -169,6 +169,12 @@ enum {
 	DCCPO_MAX_CCID_SPECIFIC = 255,
 };
 
+/* DCCP CCIDS */
+enum {
+	DCCPC_CCID2 = 2,
+	DCCPC_CCID3 = 3,
+};
+
 /* DCCP features */
 enum {
 	DCCPF_RESERVED = 0,
@@ -320,7 +326,7 @@ static inline unsigned int dccp_hdr_len(const struct sk_buff *skb)
 /* initial values for each feature */
 #define DCCPF_INITIAL_SEQUENCE_WINDOW		100
 #define DCCPF_INITIAL_ACK_RATIO			2
-#define DCCPF_INITIAL_CCID			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
@@ -404,6 +410,7 @@ struct dccp_service_list {
 };
 
 #define DCCP_SERVICE_INVALID_VALUE htonl((__u32)-1)
+#define DCCP_SERVICE_CODE_IS_ABSENT 		 0
 
 static inline int dccp_list_has_service(const struct dccp_service_list *sl,
 					const __be32 service)
@@ -484,11 +491,6 @@ static inline struct dccp_minisock *dccp_msk(const struct sock *sk)
 	return (struct dccp_minisock *)&dccp_sk(sk)->dccps_minisock;
 }
 
-static inline int dccp_service_not_initialized(const struct sock *sk)
-{
-	return dccp_sk(sk)->dccps_service == DCCP_SERVICE_INVALID_VALUE;
-}
-
 static inline const char *dccp_role(const struct sock *sk)
 {
 	switch (dccp_sk(sk)->dccps_role) {
diff --git a/include/linux/netfilter/Kbuild b/include/linux/netfilter/Kbuild
index 9a285cecf24..312bd2ffee3 100644
--- a/include/linux/netfilter/Kbuild
+++ b/include/linux/netfilter/Kbuild
@@ -10,6 +10,8 @@ header-y += xt_connmark.h
 header-y += xt_CONNMARK.h
 header-y += xt_conntrack.h
 header-y += xt_dccp.h
+header-y += xt_dscp.h
+header-y += xt_DSCP.h
 header-y += xt_esp.h
 header-y += xt_helper.h
 header-y += xt_length.h
diff --git a/include/net/cipso_ipv4.h b/include/net/cipso_ipv4.h
index 59406e0dc5b..2d72496c202 100644
--- a/include/net/cipso_ipv4.h
+++ b/include/net/cipso_ipv4.h
@@ -130,8 +130,9 @@ extern int cipso_v4_rbm_strictvalid;
 int cipso_v4_doi_add(struct cipso_v4_doi *doi_def);
 int cipso_v4_doi_remove(u32 doi, void (*callback) (struct rcu_head * head));
 struct cipso_v4_doi *cipso_v4_doi_getdef(u32 doi);
-struct sk_buff *cipso_v4_doi_dump_all(size_t headroom);
-struct sk_buff *cipso_v4_doi_dump(u32 doi, size_t headroom);
+int cipso_v4_doi_walk(u32 *skip_cnt,
+		     int (*callback) (struct cipso_v4_doi *doi_def, void *arg),
+	             void *cb_arg);
 int cipso_v4_doi_domhsh_add(struct cipso_v4_doi *doi_def, const char *domain);
 int cipso_v4_doi_domhsh_remove(struct cipso_v4_doi *doi_def,
 			       const char *domain);
@@ -152,14 +153,11 @@ static inline struct cipso_v4_doi *cipso_v4_doi_getdef(u32 doi)
 	return NULL;
 }
 
-static inline struct sk_buff *cipso_v4_doi_dump_all(size_t headroom)
+static inline int cipso_v4_doi_walk(u32 *skip_cnt,
+		     int (*callback) (struct cipso_v4_doi *doi_def, void *arg),
+		     void *cb_arg)
 {
-	return NULL;
-}
-
-static inline struct sk_buff *cipso_v4_doi_dump(u32 doi, size_t headroom)
-{
-	return NULL;
+	return 0;
 }
 
 static inline int cipso_v4_doi_domhsh_add(struct cipso_v4_doi *doi_def,
@@ -205,6 +203,7 @@ void cipso_v4_error(struct sk_buff *skb, int error, u32 gateway);
 int cipso_v4_socket_setattr(const struct socket *sock,
 			    const struct cipso_v4_doi *doi_def,
 			    const struct netlbl_lsm_secattr *secattr);
+int cipso_v4_sock_getattr(struct sock *sk, struct netlbl_lsm_secattr *secattr);
 int cipso_v4_socket_getattr(const struct socket *sock,
 			    struct netlbl_lsm_secattr *secattr);
 int cipso_v4_skbuff_getattr(const struct sk_buff *skb,
@@ -225,6 +224,12 @@ static inline int cipso_v4_socket_setattr(const struct socket *sock,
 	return -ENOSYS;
 }
 
+static inline int cipso_v4_sock_getattr(struct sock *sk,
+					struct netlbl_lsm_secattr *secattr)
+{
+	return -ENOSYS;
+}
+
 static inline int cipso_v4_socket_getattr(const struct socket *sock,
 					  struct netlbl_lsm_secattr *secattr)
 {
diff --git a/include/net/netlabel.h b/include/net/netlabel.h
index dd5780b3691..6692430063f 100644
--- a/include/net/netlabel.h
+++ b/include/net/netlabel.h
@@ -57,9 +57,8 @@
  * The payload is dependent on the subsystem specified in the
  * 'nlmsghdr->nlmsg_type' and should be defined below, supporting functions
  * should be defined in the corresponding net/netlabel/netlabel_<subsys>.h|c
- * file.  All of the fields in the NetLabel payload are NETLINK attributes, the
- * length of each field is the length of the NETLINK attribute payload, see
- * include/net/netlink.h for more information on NETLINK attributes.
+ * file.  All of the fields in the NetLabel payload are NETLINK attributes, see
+ * the include/net/netlink.h file for more information on NETLINK attributes.
  *
  */
 
@@ -82,50 +81,6 @@
 #define NETLBL_NLTYPE_UNLABELED         5
 #define NETLBL_NLTYPE_UNLABELED_NAME    "NLBL_UNLBL"
 
-/* NetLabel return codes */
-#define NETLBL_E_OK                     0
-
-/*
- * Helper functions
- */
-
-#define NETLBL_LEN_U8                   nla_total_size(sizeof(u8))
-#define NETLBL_LEN_U16                  nla_total_size(sizeof(u16))
-#define NETLBL_LEN_U32                  nla_total_size(sizeof(u32))
-
-/**
- * netlbl_netlink_alloc_skb - Allocate a NETLINK message buffer
- * @head: the amount of headroom in bytes
- * @body: the desired size (minus headroom) in bytes
- * @gfp_flags: the alloc flags to pass to alloc_skb()
- *
- * Description:
- * Allocate a NETLINK message buffer based on the sizes given in @head and
- * @body.  If @head is greater than zero skb_reserve() is called to reserve
- * @head bytes at the start of the buffer.  Returns a valid sk_buff pointer on
- * success, NULL on failure.
- *
- */
-static inline struct sk_buff *netlbl_netlink_alloc_skb(size_t head,
-						       size_t body,
-						       gfp_t gfp_flags)
-{
-	struct sk_buff *skb;
-
-	skb = alloc_skb(NLMSG_ALIGN(head + body), gfp_flags);
-	if (skb == NULL)
-		return NULL;
-	if (head > 0) {
-		skb_reserve(skb, head);
-		if (skb_tailroom(skb) < body) {
-			kfree_skb(skb);
-			return NULL;
-		}
-	}
-
-	return skb;
-}
-
 /*
  * NetLabel - Kernel API for accessing the network packet label mappings.
  *
@@ -238,6 +193,8 @@ static inline void netlbl_secattr_free(struct netlbl_lsm_secattr *secattr,
 #ifdef CONFIG_NETLABEL
 int netlbl_socket_setattr(const struct socket *sock,
 			  const struct netlbl_lsm_secattr *secattr);
+int netlbl_sock_getattr(struct sock *sk,
+			struct netlbl_lsm_secattr *secattr);
 int netlbl_socket_getattr(const struct socket *sock,
 			  struct netlbl_lsm_secattr *secattr);
 int netlbl_skbuff_getattr(const struct sk_buff *skb,
@@ -250,6 +207,12 @@ static inline int netlbl_socket_setattr(const struct socket *sock,
 	return -ENOSYS;
 }
 
+static inline int netlbl_sock_getattr(struct sock *sk,
+				      struct netlbl_lsm_secattr *secattr)
+{
+	return -ENOSYS;
+}
+
 static inline int netlbl_socket_getattr(const struct socket *sock,
 					struct netlbl_lsm_secattr *secattr)
 {
diff --git a/include/net/netlink.h b/include/net/netlink.h
index 11dc2e7f679..4ab68a7a636 100644
--- a/include/net/netlink.h
+++ b/include/net/netlink.h
@@ -146,11 +146,13 @@
  *   nla_ok(nla, remaining)		does nla fit into remaining bytes?
  *   nla_next(nla, remaining)		get next netlink attribute
  *   nla_validate()			validate a stream of attributes
+ *   nla_validate_nested()		validate a stream of nested attributes
  *   nla_find()				find attribute in stream of attributes
  *   nla_find_nested()			find attribute in nested attributes
  *   nla_parse()			parse and validate stream of attrs
  *   nla_parse_nested()			parse nested attribuets
  *   nla_for_each_attr()		loop over all attributes
+ *   nla_for_each_nested()		loop over the nested attributes
  *=========================================================================
  */
 
@@ -950,6 +952,24 @@ static inline int nla_nest_cancel(struct sk_buff *skb, struct nlattr *start)
 }
 
 /**
+ * nla_validate_nested - Validate a stream of nested attributes
+ * @start: container attribute
+ * @maxtype: maximum attribute type to be expected
+ * @policy: validation policy
+ *
+ * Validates all attributes in the nested attribute stream against the
+ * specified policy. Attributes with a type exceeding maxtype will be
+ * ignored. See documenation of struct nla_policy for more details.
+ *
+ * Returns 0 on success or a negative error code.
+ */
+static inline int nla_validate_nested(struct nlattr *start, int maxtype,
+				      struct nla_policy *policy)
+{
+	return nla_validate(nla_data(start), nla_len(start), maxtype, policy);
+}
+
+/**
  * nla_for_each_attr - iterate over a stream of attributes
  * @pos: loop counter, set to current attribute
  * @head: head of attribute stream
diff --git a/net/dccp/Kconfig b/net/dccp/Kconfig
index 859e3359fcd..e2a095d0fd8 100644
--- a/net/dccp/Kconfig
+++ b/net/dccp/Kconfig
@@ -40,6 +40,22 @@ config IP_DCCP_DEBUG
 
 	  Just say N.
 
+config NET_DCCPPROBE
+	tristate "DCCP connection probing"
+	depends on PROC_FS && KPROBES
+	---help---
+	This module allows for capturing the changes to DCCP connection
+	state in response to incoming packets. It is used for debugging
+	DCCP congestion avoidance modules. If you don't understand
+	what was just said, you don't need it: say N.
+
+	Documentation on how to use the packet generator can be found
+	at http://linux-net.osdl.org/index.php/DccpProbe
+
+	To compile this code as a module, choose M here: the
+	module will be called dccp_probe.
+
+
 endmenu
 
 endmenu
diff --git a/net/dccp/Makefile b/net/dccp/Makefile
index 7696e219b05..17ed99c4661 100644
--- a/net/dccp/Makefile
+++ b/net/dccp/Makefile
@@ -11,9 +11,11 @@ dccp_ipv4-y := ipv4.o
 dccp-$(CONFIG_IP_DCCP_ACKVEC) += ackvec.o
 
 obj-$(CONFIG_INET_DCCP_DIAG) += dccp_diag.o
+obj-$(CONFIG_NET_DCCPPROBE) += dccp_probe.o
 
 dccp-$(CONFIG_SYSCTL) += sysctl.o
 
 dccp_diag-y := diag.o
+dccp_probe-y := probe.o
 
 obj-y += ccids/
diff --git a/net/dccp/ccids/ccid2.c b/net/dccp/ccids/ccid2.c
index 457dd3db7f4..2efb505aeb3 100644
--- a/net/dccp/ccids/ccid2.c
+++ b/net/dccp/ccids/ccid2.c
@@ -808,7 +808,7 @@ static void ccid2_hc_rx_packet_recv(struct sock *sk, struct sk_buff *skb)
 }
 
 static struct ccid_operations ccid2 = {
-	.ccid_id		= 2,
+	.ccid_id		= DCCPC_CCID2,
 	.ccid_name		= "ccid2",
 	.ccid_owner		= THIS_MODULE,
 	.ccid_hc_tx_obj_size	= sizeof(struct ccid2_hc_tx_sock),
diff --git a/net/dccp/ccids/ccid3.c b/net/dccp/ccids/ccid3.c
index 195aa956622..67d2dc0e7c6 100644
--- a/net/dccp/ccids/ccid3.c
+++ b/net/dccp/ccids/ccid3.c
@@ -1240,7 +1240,7 @@ static int ccid3_hc_tx_getsockopt(struct sock *sk, const int optname, int len,
 }
 
 static struct ccid_operations ccid3 = {
-	.ccid_id		   = 3,
+	.ccid_id		   = DCCPC_CCID3,
 	.ccid_name		   = "ccid3",
 	.ccid_owner		   = THIS_MODULE,
 	.ccid_hc_tx_obj_size	   = sizeof(struct ccid3_hc_tx_sock),
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index 9a1a76a7dc4..66be29b6f50 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -56,9 +56,6 @@ int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 
 	dp->dccps_role = DCCP_ROLE_CLIENT;
 
-	if (dccp_service_not_initialized(sk))
-		return -EPROTO;
-
 	if (addr_len < sizeof(struct sockaddr_in))
 		return -EINVAL;
 
diff --git a/net/dccp/probe.c b/net/dccp/probe.c
new file mode 100644
index 00000000000..146496fce2e
--- /dev/null
+++ b/net/dccp/probe.c
@@ -0,0 +1,198 @@
+/*
+ * dccp_probe - Observe the DCCP flow with kprobes.
+ *
+ * The idea for this came from Werner Almesberger's umlsim
+ * Copyright (C) 2004, Stephen Hemminger <shemminger@osdl.org>
+ *
+ * Modified for DCCP from Stephen Hemminger's code
+ * Copyright (C) 2006, Ian McDonald <ian.mcdonald@jandi.co.nz>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+
+#include <linux/kernel.h>
+#include <linux/kprobes.h>
+#include <linux/socket.h>
+#include <linux/dccp.h>
+#include <linux/proc_fs.h>
+#include <linux/module.h>
+#include <linux/kfifo.h>
+#include <linux/vmalloc.h>
+
+#include "dccp.h"
+#include "ccid.h"
+#include "ccids/ccid3.h"
+
+static int port;
+
+static int bufsize = 64 * 1024;
+
+static const char procname[] = "dccpprobe";
+
+struct {
+	struct kfifo	  *fifo;
+	spinlock_t	  lock;
+	wait_queue_head_t wait;
+	struct timeval	  tstart;
+} dccpw;
+
+static void printl(const char *fmt, ...)
+{
+	va_list args;
+	int len;
+	struct timeval now;
+	char tbuf[256];
+
+	va_start(args, fmt);
+	do_gettimeofday(&now);
+
+	now.tv_sec -= dccpw.tstart.tv_sec;
+	now.tv_usec -= dccpw.tstart.tv_usec;
+	if (now.tv_usec < 0) {
+		--now.tv_sec;
+		now.tv_usec += 1000000;
+	}
+
+	len = sprintf(tbuf, "%lu.%06lu ",
+		      (unsigned long) now.tv_sec,
+		      (unsigned long) now.tv_usec);
+	len += vscnprintf(tbuf+len, sizeof(tbuf)-len, fmt, args);
+	va_end(args);
+
+	kfifo_put(dccpw.fifo, tbuf, len);
+	wake_up(&dccpw.wait);
+}
+
+static int jdccp_sendmsg(struct kiocb *iocb, struct sock *sk,
+			 struct msghdr *msg, size_t size)
+{
+	const struct dccp_minisock *dmsk = dccp_msk(sk);
+	const struct inet_sock *inet = inet_sk(sk);
+	const struct ccid3_hc_tx_sock *hctx;
+
+	if (dmsk->dccpms_tx_ccid == DCCPC_CCID3)
+		hctx = ccid3_hc_tx_sk(sk);
+	else
+		hctx = NULL;
+
+	if (port == 0 || ntohs(inet->dport) == port ||
+	    ntohs(inet->sport) == port) {
+		if (hctx)
+			printl("%d.%d.%d.%d:%u %d.%d.%d.%d:%u %d %d %d %d %d\n",
+			   NIPQUAD(inet->saddr), ntohs(inet->sport),
+			   NIPQUAD(inet->daddr), ntohs(inet->dport), size,
+			   hctx->ccid3hctx_s, hctx->ccid3hctx_rtt,
+			   hctx->ccid3hctx_p, hctx->ccid3hctx_t_ipi);
+		else
+			printl("%d.%d.%d.%d:%u %d.%d.%d.%d:%u %d\n",
+			   NIPQUAD(inet->saddr), ntohs(inet->sport),
+			   NIPQUAD(inet->daddr), ntohs(inet->dport), size);
+	}
+
+	jprobe_return();
+	return 0;
+}
+
+static struct jprobe dccp_send_probe = {
+	.kp	= { .addr = (kprobe_opcode_t *)&dccp_sendmsg, },
+	.entry	= (kprobe_opcode_t *)&jdccp_sendmsg,
+};
+
+static int dccpprobe_open(struct inode *inode, struct file *file)
+{
+	kfifo_reset(dccpw.fifo);
+	do_gettimeofday(&dccpw.tstart);
+	return 0;
+}
+
+static ssize_t dccpprobe_read(struct file *file, char __user *buf,
+			      size_t len, loff_t *ppos)
+{
+	int error = 0, cnt = 0;
+	unsigned char *tbuf;
+
+	if (!buf || len < 0)
+		return -EINVAL;
+
+	if (len == 0)
+		return 0;
+
+	tbuf = vmalloc(len);
+	if (!tbuf)
+		return -ENOMEM;
+
+	error = wait_event_interruptible(dccpw.wait,
+					 __kfifo_len(dccpw.fifo) != 0);
+	if (error)
+		goto out_free;
+
+	cnt = kfifo_get(dccpw.fifo, tbuf, len);
+	error = copy_to_user(buf, tbuf, cnt);
+
+out_free:
+	vfree(tbuf);
+
+	return error ? error : cnt;
+}
+
+static struct file_operations dccpprobe_fops = {
+	.owner	 = THIS_MODULE,
+	.open	 = dccpprobe_open,
+	.read    = dccpprobe_read,
+};
+
+static __init int dccpprobe_init(void)
+{
+	int ret = -ENOMEM;
+
+	init_waitqueue_head(&dccpw.wait);
+	spin_lock_init(&dccpw.lock);
+	dccpw.fifo = kfifo_alloc(bufsize, GFP_KERNEL, &dccpw.lock);
+
+	if (!proc_net_fops_create(procname, S_IRUSR, &dccpprobe_fops))
+		goto err0;
+
+	ret = register_jprobe(&dccp_send_probe);
+	if (ret)
+		goto err1;
+
+	pr_info("DCCP watch registered (port=%d)\n", port);
+	return 0;
+err1:
+	proc_net_remove(procname);
+err0:
+	kfifo_free(dccpw.fifo);
+	return ret;
+}
+module_init(dccpprobe_init);
+
+static __exit void dccpprobe_exit(void)
+{
+	kfifo_free(dccpw.fifo);
+	proc_net_remove(procname);
+	unregister_jprobe(&dccp_send_probe);
+
+}
+module_exit(dccpprobe_exit);
+
+MODULE_PARM_DESC(port, "Port to match (0=all)");
+module_param(port, int, 0);
+
+MODULE_PARM_DESC(bufsize, "Log buffer size (default 64k)");
+module_param(bufsize, int, 0);
+
+MODULE_AUTHOR("Ian McDonald <ian.mcdonald@jandi.co.nz>");
+MODULE_DESCRIPTION("DCCP snooper");
+MODULE_LICENSE("GPL");
diff --git a/net/dccp/proto.c b/net/dccp/proto.c
index 962df0ea31a..72cbdcfc2c6 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -217,7 +217,7 @@ int dccp_init_sock(struct sock *sk, const __u8 ctl_sock_initialized)
 	icsk->icsk_sync_mss	= dccp_sync_mss;
 	dp->dccps_mss_cache	= 536;
 	dp->dccps_role		= DCCP_ROLE_UNDEFINED;
-	dp->dccps_service	= DCCP_SERVICE_INVALID_VALUE;
+	dp->dccps_service	= DCCP_SERVICE_CODE_IS_ABSENT;
 	dp->dccps_l_ack_ratio	= dp->dccps_r_ack_ratio = 1;
 
 	return 0;
@@ -267,12 +267,6 @@ static inline int dccp_listen_start(struct sock *sk)
 	struct dccp_sock *dp = dccp_sk(sk);
 
 	dp->dccps_role = DCCP_ROLE_LISTEN;
-	/*
-	 * Apps need to use setsockopt(DCCP_SOCKOPT_SERVICE)
-	 * before calling listen()
-	 */
-	if (dccp_service_not_initialized(sk))
-		return -EPROTO;
 	return inet_csk_listen_start(sk, TCP_SYNQ_HSIZE);
 }
 
@@ -540,9 +534,6 @@ static int dccp_getsockopt_service(struct sock *sk, int len,
 	int err = -ENOENT, slen = 0, total_len = sizeof(u32);
 
 	lock_sock(sk);
-	if (dccp_service_not_initialized(sk))
-		goto out;
-
 	if ((sl = dp->dccps_service_list) != NULL) {
 		slen = sl->dccpsl_nr * sizeof(u32);
 		total_len += slen;
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index 1650b64415a..30af4a4dfcc 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -448,24 +448,22 @@ config INET_TCP_DIAG
 	depends on INET_DIAG
 	def_tristate INET_DIAG
 
-config TCP_CONG_ADVANCED
+menuconfig TCP_CONG_ADVANCED
 	bool "TCP: advanced congestion control"
 	---help---
 	  Support for selection of various TCP congestion control
 	  modules.
 
 	  Nearly all users can safely say no here, and a safe default
-	  selection will be made (BIC-TCP with new Reno as a fallback).
+	  selection will be made (CUBIC with new Reno as a fallback).
 
 	  If unsure, say N.
 
-# TCP Reno is builtin (required as fallback)
-menu "TCP congestion control"
-	depends on TCP_CONG_ADVANCED
+if TCP_CONG_ADVANCED
 
 config TCP_CONG_BIC
 	tristate "Binary Increase Congestion (BIC) control"
-	default y
+	default m
 	---help---
 	BIC-TCP is a sender-side only change that ensures a linear RTT
 	fairness under large windows while offering both scalability and
@@ -479,7 +477,7 @@ config TCP_CONG_BIC
 
 config TCP_CONG_CUBIC
 	tristate "CUBIC TCP"
-	default m
+	default y
 	---help---
 	This is version 2.0 of BIC-TCP which uses a cubic growth function
 	among other techniques.
@@ -574,12 +572,49 @@ config TCP_CONG_VENO
 	loss packets.
 	See http://www.ntu.edu.sg/home5/ZHOU0022/papers/CPFu03a.pdf
 
-endmenu
+choice
+	prompt "Default TCP congestion control"
+	default DEFAULT_CUBIC
+	help
+	  Select the TCP congestion control that will be used by default
+	  for all connections.
 
-config TCP_CONG_BIC
+	config DEFAULT_BIC
+		bool "Bic" if TCP_CONG_BIC=y
+
+	config DEFAULT_CUBIC
+		bool "Cubic" if TCP_CONG_CUBIC=y
+
+	config DEFAULT_HTCP
+		bool "Htcp" if TCP_CONG_HTCP=y
+
+	config DEFAULT_VEGAS
+		bool "Vegas" if TCP_CONG_VEGAS=y
+
+	config DEFAULT_WESTWOOD
+		bool "Westwood" if TCP_CONG_WESTWOOD=y
+
+	config DEFAULT_RENO
+		bool "Reno"
+
+endchoice
+
+endif
+
+config TCP_CONG_CUBIC
 	tristate
 	depends on !TCP_CONG_ADVANCED
 	default y
 
+config DEFAULT_TCP_CONG
+	string
+	default "bic" if DEFAULT_BIC
+	default "cubic" if DEFAULT_CUBIC
+	default "htcp" if DEFAULT_HTCP
+	default "vegas" if DEFAULT_VEGAS
+	default "westwood" if DEFAULT_WESTWOOD
+	default "reno" if DEFAULT_RENO
+	default "cubic"
+
 source "net/ipv4/ipvs/Kconfig"
 
diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c
index 80a2a0911b4..e6ce0b3ba62 100644
--- a/net/ipv4/cipso_ipv4.c
+++ b/net/ipv4/cipso_ipv4.c
@@ -259,7 +259,7 @@ void cipso_v4_cache_invalidate(void)
 	u32 iter;
 
 	for (iter = 0; iter < CIPSO_V4_CACHE_BUCKETS; iter++) {
-		spin_lock(&cipso_v4_cache[iter].lock);
+		spin_lock_bh(&cipso_v4_cache[iter].lock);
 		list_for_each_entry_safe(entry,
 					 tmp_entry,
 					 &cipso_v4_cache[iter].list, list) {
@@ -267,7 +267,7 @@ void cipso_v4_cache_invalidate(void)
 			cipso_v4_cache_entry_free(entry);
 		}
 		cipso_v4_cache[iter].size = 0;
-		spin_unlock(&cipso_v4_cache[iter].lock);
+		spin_unlock_bh(&cipso_v4_cache[iter].lock);
 	}
 
 	return;
@@ -309,7 +309,7 @@ static int cipso_v4_cache_check(const unsigned char *key,
 
 	hash = cipso_v4_map_cache_hash(key, key_len);
 	bkt = hash & (CIPSO_V4_CACHE_BUCKETBITS - 1);
-	spin_lock(&cipso_v4_cache[bkt].lock);
+	spin_lock_bh(&cipso_v4_cache[bkt].lock);
 	list_for_each_entry(entry, &cipso_v4_cache[bkt].list, list) {
 		if (entry->hash == hash &&
 		    entry->key_len == key_len &&
@@ -318,7 +318,7 @@ static int cipso_v4_cache_check(const unsigned char *key,
 			secattr->cache.free = entry->lsm_data.free;
 			secattr->cache.data = entry->lsm_data.data;
 			if (prev_entry == NULL) {
-				spin_unlock(&cipso_v4_cache[bkt].lock);
+