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.

Documentation/networking/dccp.txt

 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
 =====

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

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;

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) {

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

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)
 {

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)
 {

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
  *=========================================================================
  */
 
@@ -949,6 +951,24 @@ static inline int nla_nest_cancel(struct sk_buff *skb, struct nlattr *start)
 	return nlmsg_trim(skb, 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

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

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/

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),

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),

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;
 

net/dccp/probe.c

+/*
+ * 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");

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;

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"
 

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);
+				spin_unlock_bh(&cipso_v4_cache[bkt].lock);
 				return 0;
 			}
 
@@ -333,12 +333,12 @@ static int cipso_v4_cache_check(const unsigned char *key,
 					   &prev_entry->list);
 			}
 
-			spin_unlock(&cipso_v4_cache[bkt].lock);
+			spin_unlock_bh(&cipso_v4_cache[bkt].lock);
 			return 0;
 		}
 		prev_entry = entry;
 	}
-	spin_unlock(&cipso_v4_cache[bkt].lock);
+	spin_unlock_bh(&cipso_v4_cache[bkt].lock);
 
 	return -ENOENT;
 }
@@ -387,7 +387,7 @@ int cipso_v4_cache_add(const struct sk_buff *skb,
 	entry->lsm_data.data = secattr->cache.data;
 
 	bkt = entry->hash & (CIPSO_V4_CACHE_BUCKETBITS - 1);
-	spin_lock(&cipso_v4_cache[bkt].lock);
+	spin_lock_bh(&cipso_v4_cache[bkt].lock);
 	if (cipso_v4_cache[bkt].size < cipso_v4_cache_bucketsize) {
 		list_add(&entry->list, &cipso_v4_cache[bkt].list);
 		cipso_v4_cache[bkt].size += 1;
@@ -398,7 +398,7 @@ int cipso_v4_cache_add(const struct sk_buff *skb,
 		list_add(&entry->list, &cipso_v4_cache[bkt].list);
 		cipso_v4_cache_entry_free(old_entry);
 	}
-	spin_unlock(&cipso_v4_cache[bkt].lock);
+	spin_unlock_bh(&cipso_v4_cache[bkt].lock);
 
 	return 0;
 
@@ -530,197 +530,42 @@ struct cipso_v4_doi *cipso_v4_doi_getdef(u32 doi)
 }
 
 /**
- * cipso_v4_doi_dump_all - Dump all the CIPSO DOI definitions into a sk_buff
- * @headroom: the amount of headroom to allocate for the sk_buff
+ * cipso_v4_doi_walk - Iterate through the DOI definitions
+ * @skip_cnt: skip past this number of DOI definitions, updated
+ * @callback: callback for each DOI definition
+ * @cb_arg: argument for the callback function
  *
  * Description:
- * Dump a list of all the configured DOI values into a sk_buff.  The returned
- * sk_buff has room at the front of the sk_buff for @headroom bytes.  See
- * net/netlabel/netlabel_cipso_v4.h for the LISTALL message format.  This
- * function may fail if another process is changing the DOI list at the same
- * time.  Returns a pointer to a sk_buff on success, NULL on error.
+ * Iterate over the DOI definition list, skipping the first @skip_cnt entries.
+ * For each entry call @callback, if @callback returns a negative value stop
+ * 'walking' through the list and return.  Updates the value in @skip_cnt upon
+ * return.  Returns zero on success, negative values on failure.
  *
  */
-struct sk_buff *cipso_v4_doi_dump_all(size_t headroom)
+int cipso_v4_doi_walk(u32 *skip_cnt,
+		     int (*callback) (struct cipso_v4_doi *doi_def, void *arg),
+		     void *cb_arg)
 {
-	struct sk_buff *skb = NULL;
-	struct cipso_v4_doi *iter;
+	int ret_val = -ENOENT;
 	u32 doi_cnt = 0;
-	ssize_t buf_len;
+	struct cipso_v4_doi *iter_doi;
 
-	buf_len = NETLBL_LEN_U32;
 	rcu_read_lock();
-	list_for_each_entry_rcu(iter, &cipso_v4_doi_list, list)
-		if (iter->valid) {
-			doi_cnt += 1;
-			buf_len += 2 * NETLBL_LEN_U32;
-		}
-
-	skb = netlbl_netlink_alloc_skb(headroom, buf_len, GFP_ATOMIC);
-	if (skb == NULL)
-		goto doi_dump_all_failure;
-
-	if (nla_put_u32(skb, NLA_U32, doi_cnt) != 0)
-		goto doi_dump_all_failure;
-	buf_len -= NETLBL_LEN_U32;
-	list_for_each_entry_rcu(iter, &cipso_v4_doi_list, list)
-		if (iter->valid) {
-			if (buf_len < 2 * NETLBL_LEN_U32)
-				goto doi_dump_all_failure;
-			if (nla_put_u32(skb, NLA_U32, iter->doi) != 0)
-				goto doi_dump_all_failure;
-			if (nla_put_u32(skb, NLA_U32, iter->type) != 0)
-				goto doi_dump_all_failure;
-			buf_len -= 2 * NETLBL_LEN_U32;
-		}
-	rcu_read_unlock();
-
-	return skb;
-
-doi_dump_all_failure:
-	rcu_read_unlock();
-	kfree(skb);
-	return NULL;
-}
-
-/**
- * cipso_v4_doi_dump - Dump a CIPSO DOI definition into a sk_buff
- * @doi: the DOI value
- * @headroom: the amount of headroom to allocate for the sk_buff
- *
- * Description:
- * Lookup the DOI definition matching @doi and dump it's contents into a
- * sk_buff.  The returned sk_buff has room at the front of the sk_buff for
- * @headroom bytes.  See net/netlabel/netlabel_cipso_v4.h for the LIST message
- * format.  This function may fail if another process is changing the DOI list
- * at the same time.  Returns a pointer to a sk_buff on success, NULL on error.
- *
- */
-struct sk_buff *cipso_v4_doi_dump(u32 doi, size_t headroom)
-{
-	struct sk_buff *skb = NULL;
-	struct cipso_v4_doi *iter;
-	u32 tag_cnt = 0;
-	u32 lvl_cnt = 0;
-	u32 cat_cnt = 0;
-	ssize_t buf_len;
-	ssize_t tmp;
-
-	rcu_read_lock();
-	iter = cipso_v4_doi_getdef(doi);
-	if (iter == NULL)
-		goto doi_dump_failure;
-	buf_len = NETLBL_LEN_U32;
-	switch (iter->type) {
-	case CIPSO_V4_MAP_PASS:
-		buf_len += NETLBL_LEN_U32;
-		while(tag_cnt < CIPSO_V4_TAG_MAXCNT &&
-		      iter->tags[tag_cnt] != CIPSO_V4_TAG_INVALID) {
-			tag_cnt += 1;
-			buf_len += NETLBL_LEN_U8;
-		}
-		break;
-	case CIPSO_V4_MAP_STD:
-		buf_len += 3 * NETLBL_LEN_U32;
-		while (tag_cnt < CIPSO_V4_TAG_MAXCNT &&
-		       iter->tags[tag_cnt] != CIPSO_V4_TAG_INVALID) {
-			tag_cnt += 1;
-			buf_len += NETLBL_LEN_U8;
-		}
-		for (tmp = 0; tmp < iter->map.std->lvl.local_size; tmp++)
-			if (iter->map.std->lvl.local[tmp] !=
-			    CIPSO_V4_INV_LVL) {
-				lvl_cnt += 1;
-				buf_len += NETLBL_LEN_U32 + NETLBL_LEN_U8;
-			}
-		for (tmp = 0; tmp < iter->map.std->cat.local_size; tmp++)
-			if (iter->map.std->cat.local[tmp] !=
-			    CIPSO_V4_INV_CAT) {
-				cat_cnt += 1;
-				buf_len += NETLBL_LEN_U32 + NETLBL_LEN_U16;
+	list_for_each_entry_rcu(iter_doi, &cipso_v4_doi_list, list)
+		if (iter_doi->valid) {
+			if (doi_cnt++ < *skip_cnt)
+				continue;
+			ret_val = callback(iter_doi, cb_arg);
+			if (ret_val < 0) {
+				doi_cnt--;
+				goto doi_walk_return;
 			}
-		break;
-	}
-
-	skb = netlbl_netlink_alloc_skb(headroom, buf_len, GFP_ATOMIC);
-	if (skb == NULL)
-		goto doi_dump_failure;
-
-	if (nla_put_u32(skb, NLA_U32, iter->type) != 0)
-		goto doi_dump_failure;
-	buf_len -= NETLBL_LEN_U32;
-	if (iter != cipso_v4_doi_getdef(doi))
-		goto doi_dump_failure;
-	switch (iter->type) {
-	case CIPSO_V4_MAP_PASS:
-		if (nla_put_u32(skb, NLA_U32, tag_cnt) != 0)
-			goto doi_dump_failure;
-		buf_len -= NETLBL_LEN_U32;
-		for (tmp = 0;
-		     tmp < CIPSO_V4_TAG_MAXCNT &&
-			     iter->tags[tmp] != CIPSO_V4_TAG_INVALID;
-		     tmp++) {
-			if (buf_len < NETLBL_LEN_U8)
-				goto doi_dump_failure;
-			if (nla_put_u8(skb, NLA_U8, iter->tags[tmp]) != 0)
-				goto doi_dump_failure;
-			buf_len -= NETLBL_LEN_U8;
 		}
-		break;
-	case CIPSO_V4_MAP_STD:
-		if (nla_put_u32(skb, NLA_U32, tag_cnt) != 0)
-			goto doi_dump_failure;
-		if (nla_put_u32(skb, NLA_U32, lvl_cnt) != 0)
-			goto doi_dump_failure;
-		if (nla_put_u32(skb, NLA_U32, cat_cnt) != 0)
-			goto doi_dump_failure;
-		buf_len -= 3 * NETLBL_LEN_U32;
-		for (tmp = 0;
-		     tmp < CIPSO_V4_TAG_MAXCNT &&
-			     iter->tags[tmp] != CIPSO_V4_TAG_INVALID;
-		     tmp++) {
-			if (buf_len < NETLBL_LEN_U8)
-				goto doi_dump_failure;
-			if (nla_put_u8(skb, NLA_U8, iter->tags[tmp]) != 0)
-				goto doi_dump_failure;
-			buf_len -= NETLBL_LEN_U8;
-		}
-		for (tmp = 0; tmp < iter->map.std->lvl.local_size; tmp++)
-			if (iter->map.std->lvl.local[tmp] !=
-			    CIPSO_V4_INV_LVL) {
-				if (buf_len < NETLBL_LEN_U32 + NETLBL_LEN_U8)
-					goto doi_dump_failure;
-				if (nla_put_u32(skb, NLA_U32, tmp) != 0)
-					goto doi_dump_failure;
-				if (nla_put_u8(skb,
-					   NLA_U8,
-					   iter->map.std->lvl.local[tmp]) != 0)
-					goto doi_dump_failure;
-				buf_len -= NETLBL_LEN_U32 + NETLBL_LEN_U8;
-			}
-		for (tmp = 0; tmp < iter->map.std->cat.local_size; tmp++)
-			if (iter->map.std->cat.local[tmp] !=
-			    CIPSO_V4_INV_CAT) {
-				if (buf_len < NETLBL_LEN_U32 + NETLBL_LEN_U16)
-					goto doi_dump_failure;
-				if (nla_put_u32(skb, NLA_U32, tmp) != 0)
-					goto doi_dump_failure;
-				if (nla_put_u16(skb,
-					   NLA_U16,
-					   iter->map.std->cat.local[tmp]) != 0)
-					goto doi_dump_failure;
-				buf_len -= NETLBL_LEN_U32 + NETLBL_LEN_U16;
-			}
-		break;
-	}
-	rcu_read_unlock();
-
-	return skb;
 
-doi_dump_failure:
+doi_walk_return:
 	rcu_read_unlock();
-	kfree(skb);
-	return NULL;
+	*skip_cnt = doi_cnt;
+	return ret_val;
 }
 
 /**
@@ -1486,43 +1331,40 @@ int cipso_v4_socket_setattr(const struct socket *sock,
 }
 
 /**
- * cipso_v4_socket_getattr - Get the security attributes from a socket
- * @sock: the socket
+ * cipso_v4_sock_getattr - Get the security attributes from a sock
+ * @sk: the sock
  * @secattr: the security attributes
  *
  * Description:
- * Query @sock to see if there is a CIPSO option attached to the socket and if
- * there is return the CIPSO security attributes in @secattr.  Returns zero on
- * success and negative values on failure.
+ * Query @sk to see if there is a CIPSO option attached to the sock and if
+ * there is return the CIPSO security attributes in @secattr.  This function
+ * requires that @sk be locked, or privately held, but it does not do any
+ * locking itself.  Returns zero on success and negative values on failure.
  *
  */
-int cipso_v4_socket_getattr(const struct socket *sock,
-			    struct netlbl_lsm_secattr *secattr)
+int cipso_v4_sock_getattr(struct sock *sk, struct netlbl_lsm_secattr *secattr)
 {
 	int ret_val = -ENOMSG;
-	struct sock *sk;
 	struct inet_sock *sk_inet;
 	unsigned char *cipso_ptr;
 	u32 doi;
 	struct cipso_v4_doi *doi_def;
 
-	sk = sock->sk;
-	lock_sock(sk);
 	sk_inet = inet_sk(sk);
 	if (sk_inet->opt == NULL || sk_inet->opt->cipso == 0)
-		goto socket_getattr_return;
+		return -ENOMSG;
 	cipso_ptr = sk_inet->opt->__data + sk_inet->opt->cipso -
 		sizeof(struct iphdr);
 	ret_val = cipso_v4_cache_check(cipso_ptr, cipso_ptr[1], secattr);
 	if (ret_val == 0)
-		goto socket_getattr_return;
+		return ret_val;
 
 	doi = ntohl(*(u32 *)&cipso_ptr[2]);
 	rcu_read_lock();
 	doi_def = cipso_v4_doi_getdef(doi);
 	if (doi_def == NULL) {
 		rcu_read_unlock();
-		goto socket_getattr_return;
+		return -ENOMSG;
 	}
 	switch (cipso_ptr[6]) {
 	case CIPSO_V4_TAG_RBITMAP:
@@ -1533,8 +1375,29 @@ int cipso_v4_socket_getattr(const struct socket *sock,
 	}
 	rcu_read_unlock();
 
-socket_getattr_return:
-	release_sock(sk);
+	return ret_val;
+}
+
+/**
+ * cipso_v4_socket_getattr - Get the security attributes from a socket
+ * @sock: the socket
+ * @secattr: the security attributes
+ *
+ * Description:
+ * Query @sock to see if there is a CIPSO option attached to the socket and if
+ * there is return the CIPSO security attributes in @secattr.  Returns zero on
+ * success and negative values on failure.
+ *
+ */
+int cipso_v4_socket_getattr(const struct socket *sock,
+			    struct netlbl_lsm_secattr *secattr)
+{
+	int ret_val;
+
+	lock_sock(sock->sk);
+	ret_val = cipso_v4_sock_getattr(sock->sk, secattr);
+	release_sock(sock->sk);
+
 	return ret_val;
 }
 

net/ipv4/sysctl_net_ipv4.c

@@ -129,6 +129,12 @@ static int sysctl_tcp_congestion_control(ctl_table *table, int __user *name,
 	return ret;
 }
 
+static int __init tcp_congestion_default(void)
+{
+	return tcp_set_default_congestion_control(CONFIG_DEFAULT_TCP_CONG);
+}
+
+late_initcall(tcp_congestion_default);
 
 ctl_table ipv4_table[] = {
         {

net/ipv4/tcp_cong.c

@@ -48,7 +48,7 @@ int tcp_register_congestion_control(struct tcp_congestion_ops *ca)
 		printk(KERN_NOTICE "TCP %s already registered\n", ca->name);
 		ret = -EEXIST;
 	} else {
-		list_add_rcu(&ca->list, &tcp_cong_list);
+		list_add_tail_rcu(&ca->list, &tcp_cong_list);
 		printk(KERN_INFO "TCP %s registered\n", ca->name);
 	}
 	spin_unlock(&tcp_cong_list_lock);

net/netlabel/Kconfig

@@ -9,6 +9,9 @@ config NETLABEL
 	---help---
 	  NetLabel provides support for explicit network packet labeling
 	  protocols such as CIPSO and RIPSO.  For more information see
-	  Documentation/netlabel.
+	  Documentation/netlabel as well as the NetLabel SourceForge project
+	  for configuration tools and additional documentation.
+
+	   * http://netlabel.sf.net
 
 	  If you are unsure, say N.

net/netlabel/netlabel_cipso_v4.h

@@ -34,175 +34,71 @@
 #include <net/netlabel.h>
 
 /*
- * The following NetLabel payloads are supported by the CIPSO subsystem, all
- * of which are preceeded by the nlmsghdr struct.
+ * The following NetLabel payloads are supported by the CIPSO subsystem.
  *
- * o ACK:
- *   Sent by the kernel in response to an applications message, applications
- *   should never send this message.
+ * o ADD:
+ *   Sent by an application to add a new DOI mapping table.
  *
- *   +----------------------+-----------------------+
- *   | seq number (32 bits) | return code (32 bits) |
- *   +----------------------+-----------------------+
+ *   Required attributes:
  *
- *     seq number:  the sequence number of the original message, taken from the
- *                  nlmsghdr structure
- *     return code: return value, based on errno values
+ *     NLBL_CIPSOV4_A_DOI
+ *     NLBL_CIPSOV4_A_MTYPE
+ *     NLBL_CIPSOV4_A_TAGLST
  *
- * o ADD:
- *   Sent by an application to add a new DOI mapping table, after completion
- *   of the task the kernel should ACK this message.
- *
- *   +---------------+--------------------+---------------------+
- *   | DOI (32 bits) | map type (32 bits) | tag count (32 bits) | ...
- *   +---------------+--------------------+---------------------+
- *
- *   +-----------------+
- *   | tag #X (8 bits) | ... repeated
- *   +-----------------+
- *
- *   +-------------- ---- --- -- -
- *   | mapping data
- *   +-------------- ---- --- -- -
- *
- *     DOI:          the DOI value
- *     map type:     the mapping table type (defined in the cipso_ipv4.h header
- *                   as CIPSO_V4_MAP_*)
- *     tag count:    the number of tags, must be greater than zero
- *     tag:          the CIPSO tag for the DOI, tags listed first are given
- *                   higher priorirty when sending packets
- *     mapping data: specific to the map type (see below)
- *
- *   CIPSO_V4_MAP_STD
- *
- *   +------------------+-----------------------+----------------------+
- *   | levels (32 bits) | max l level (32 bits) | max r level (8 bits) | ...
- *   +------------------+-----------------------+----------------------+
- *
- *   +----------------------+---------------------+---------------------+
- *   | categories (32 bits) | max l cat (32 bits) | max r cat (16 bits) | ...
- *   +----------------------+---------------------+---------------------+
- *
- *   +--------------------------+-------------------------+
- *   | local level #X (32 bits) | CIPSO level #X (8 bits) | ... repeated
- *   +--------------------------+-------------------------+
- *
- *   +-----------------------------+-----------------------------+
- *   | local category #X (32 bits) | CIPSO category #X (16 bits) | ... repeated
- *   +-----------------------------+-----------------------------+
- *
- *     levels:         the number of level mappings
- *     max l level:    the highest local level
- *     max r level:    the highest remote/CIPSO level
- *     categories:     the number of category mappings
- *     max l cat:      the highest local category
- *     max r cat:      the highest remote/CIPSO category
- *     local level:    the local part of a level mapping
- *     CIPSO level:    the remote/CIPSO part of a level mapping
- *     local category: the local part of a category mapping
- *     CIPSO category: the remote/CIPSO part of a category mapping
- *
- *   CIPSO_V4_MAP_PASS
- *
- *   No mapping data is needed for this map type.
+ *   If using CIPSO_V4_MAP_STD the following attributes are required:
+ *
+ *     NLBL_CIPSOV4_A_MLSLVLLST
+ *     NLBL_CIPSOV4_A_MLSCATLST
+ *
+ *   If using CIPSO_V4_MAP_PASS no additional attributes are required.
  *
  * o REMOVE:
  *   Sent by an application to remove a specific DOI mapping table from the
- *   CIPSO V4 system.  The kernel should ACK this message.
+ *   CIPSO V4 system.
  *
- *   +---------------+
- *   | DOI (32 bits) |
- *   +---------------+
+ *   Required attributes:
  *
- *     DOI:          the DOI value
+ *     NLBL_CIPSOV4_A_DOI
  *
  * o LIST:
- *   Sent by an application to list the details of a DOI definition.  The
- *   kernel should send an ACK on error or a response as indicated below.  The
- *   application generated message format is shown below.
+ *   Sent by an application to list the details of a DOI definition.  On
+ *   success the kernel should send a response using the following format.
  *
- *   +---------------+
- *   | DOI (32 bits) |
- *   +---------------+
+ *   Required attributes:
  *
- *     DOI:          the DOI value
+ *     NLBL_CIPSOV4_A_DOI
  *
  *   The valid response message format depends on the type of the DOI mapping,
- *   the known formats are shown below.
- *
- *   +--------------------+
- *   | map type (32 bits) | ...
- *   +--------------------+
- *
- *     map type:       the DOI mapping table type (defined in the cipso_ipv4.h
- *                     header as CIPSO_V4_MAP_*)
- *
- *   (map type == CIPSO_V4_MAP_STD)
- *
- *   +----------------+------------------+----------------------+
- *   | tags (32 bits) | levels (32 bits) | categories (32 bits) | ...
- *   +----------------+------------------+----------------------+
+ *   the defined formats are shown below.
  *
- *   +-----------------+
- *   | tag #X (8 bits) | ... repeated
- *   +-----------------+
+ *   Required attributes:
  *
- *   +--------------------------+-------------------------+
- *   | local level #X (32 bits) | CIPSO level #X (8 bits) | ... repeated
- *   +--------------------------+-------------------------+
+ *     NLBL_CIPSOV4_A_MTYPE
+ *     NLBL_CIPSOV4_A_TAGLST
  *
- *   +-----------------------------+-----------------------------+
- *   | local category #X (32 bits) | CIPSO category #X (16 bits) | ... repeated
- *   +-----------------------------+-----------------------------+
+ *   If using CIPSO_V4_MAP_STD the following attributes are required:
  *
- *     tags:           the number of CIPSO tag types
- *     levels:         the number of level mappings
- *     categories:     the number of category mappings
- *     tag:            the tag number, tags listed first are given higher
- *                     priority when sending packets
- *     local level:    the local part of a level mapping
- *     CIPSO level:    the remote/CIPSO part of a level mapping
- *     local category: the local part of a category mapping
- *     CIPSO category: the remote/CIPSO part of a category mapping
+ *     NLBL_CIPSOV4_A_MLSLVLLST
+ *     NLBL_CIPSOV4_A_MLSCATLST
  *
- *   (map type == CIPSO_V4_MAP_PASS)
- *
- *   +----------------+
- *   | tags (32 bits) | ...
- *   +----------------+
- *
- *   +-----------------+
- *   | tag #X (8 bits) | ... repeated
- *   +-----------------+
- *
- *     tags:           the number of CIPSO tag types
- *     tag:            the tag number, tags listed first are given higher
- *                     priority when sending packets
+ *   If using CIPSO_V4_MAP_PASS no additional attributes are required.
  *
  * o LISTALL:
  *   This message is sent by an application to list the valid DOIs on the
- *   system.  There is no payload and the kernel should respond with an ACK
- *   or the following message.
- *
- *   +---------------------+------------------+-----------------------+
- *   | DOI count (32 bits) | DOI #X (32 bits) | map type #X (32 bits) |
- *   +---------------------+------------------+-----------------------+
+ *   system.  When sent by an application there is no payload and the
+ *   NLM_F_DUMP flag should be set.  The kernel should respond with a series of
+ *   the following messages.
  *
- *   +-----------------------+
- *   | map type #X (32 bits) | ...
- *   +-----------------------+
+ *   Required attributes:
  *
- *     DOI count:      the number of DOIs
- *     DOI:            the DOI value
- *     map type:       the DOI mapping table type (defined in the cipso_ipv4.h
- *                     header as CIPSO_V4_MAP_*)
+ *    NLBL_CIPSOV4_A_DOI
+ *    NLBL_CIPSOV4_A_MTYPE
  *
  */
 
 /* NetLabel CIPSOv4 commands */
 enum {
 	NLBL_CIPSOV4_C_UNSPEC,
-	NLBL_CIPSOV4_C_ACK,
 	NLBL_CIPSOV4_C_ADD,
 	NLBL_CIPSOV4_C_REMOVE,
 	NLBL_CIPSOV4_C_LIST,
@@ -211,6 +107,59 @@ enum {
 };
 #define NLBL_CIPSOV4_C_MAX (__NLBL_CIPSOV4_C_MAX - 1)
 
+/* NetLabel CIPSOv4 attributes */
+enum {
+	NLBL_CIPSOV4_A_UNSPEC,
+	NLBL_CIPSOV4_A_DOI,
+	/* (NLA_U32)
+	 * the DOI value */
+	NLBL_CIPSOV4_A_MTYPE,
+	/* (NLA_U32)
+	 * the mapping table type (defined in the cipso_ipv4.h header as
+	 * CIPSO_V4_MAP_*) */
+	NLBL_CIPSOV4_A_TAG,
+	/* (NLA_U8)
+	 * a CIPSO tag type, meant to be used within a NLBL_CIPSOV4_A_TAGLST
+	 * attribute */
+	NLBL_CIPSOV4_A_TAGLST,
+	/* (NLA_NESTED)
+	 * the CIPSO tag list for the DOI, there must be at least one
+	 * NLBL_CIPSOV4_A_TAG attribute, tags listed first are given higher
+	 * priorirty when sending packets */
+	NLBL_CIPSOV4_A_MLSLVLLOC,
+	/* (NLA_U32)
+	 * the local MLS sensitivity level */
+	NLBL_CIPSOV4_A_MLSLVLREM,
+	/* (NLA_U32)
+	 * the remote MLS sensitivity level */
+	NLBL_CIPSOV4_A_MLSLVL,
+	/* (NLA_NESTED)
+	 * a MLS sensitivity level mapping, must contain only one attribute of
+	 * each of the following types: NLBL_CIPSOV4_A_MLSLVLLOC and
+	 * NLBL_CIPSOV4_A_MLSLVLREM */
+	NLBL_CIPSOV4_A_MLSLVLLST,
+	/* (NLA_NESTED)
+	 * the CIPSO level mappings, there must be at least one
+	 * NLBL_CIPSOV4_A_MLSLVL attribute */
+	NLBL_CIPSOV4_A_MLSCATLOC,
+	/* (NLA_U32)
+	 * the local MLS category */
+	NLBL_CIPSOV4_A_MLSCATREM,
+	/* (NLA_U32)
+	 * the remote MLS category */
+	NLBL_CIPSOV4_A_MLSCAT,
+	/* (NLA_NESTED)
+	 * a MLS category mapping, must contain only one attribute of each of
+	 * the following types: NLBL_CIPSOV4_A_MLSCATLOC and
+	 * NLBL_CIPSOV4_A_MLSCATREM */
+	NLBL_CIPSOV4_A_MLSCATLST,
+	/* (NLA_NESTED)
+	 * the CIPSO category mappings, there must be at least one
+	 * NLBL_CIPSOV4_A_MLSCAT attribute */
+	__NLBL_CIPSOV4_A_MAX,
+};
+#define NLBL_CIPSOV4_A_MAX (__NLBL_CIPSOV4_A_MAX - 1)
+
 /* NetLabel protocol functions */
 int netlbl_cipsov4_genl_init(void);
 

net/netlabel/netlabel_domainhash.c

@@ -354,160 +354,51 @@ struct netlbl_dom_map *netlbl_domhsh_getentry(const char *domain)
 }
 
 /**
- * netlbl_domhsh_dump - Dump the domain hash table into a sk_buff
+ * netlbl_domhsh_walk - Iterate through the domain mapping hash table
+ * @skip_bkt: the number of buckets to skip at the start
+ * @skip_chain: the number of entries to skip in the first iterated bucket
+ * @callback: callback for each entry
+ * @cb_arg: argument for the callback function
  *
  * Description:
- * Dump the domain hash table into a buffer suitable for returning to an
- * application in response to a NetLabel management DOMAIN message.  This
- * function may fail if another process is growing the hash table at the same
- * time.  The returned sk_buff has room at the front of the sk_buff for
- * @headroom bytes.  See netlabel.h for the DOMAIN message format.  Returns a
- * pointer to a sk_buff on success, NULL on error.
+ * Interate over the domain mapping hash table, skipping the first @skip_bkt
+ * buckets and @skip_chain entries.  For each entry in the table call
+ * @callback, if @callback returns a negative value stop 'walking' through the
+ * table and return.  Updates the values in @skip_bkt and @skip_chain on
+ * return.  Returns zero on succcess, negative values on failure.
  *
  */
-struct sk_buff *netlbl_domhsh_dump(size_t headroom)
+int netlbl_domhsh_walk(u32 *skip_bkt,
+		     u32 *skip_chain,
+		     int (*callback) (struct netlbl_dom_map *entry, void *arg),
+		     void *cb_arg)
 {
-	struct sk_buff *skb = NULL;
-	ssize_t buf_len;
-	u32 bkt_iter;
-	u32 dom_cnt = 0;
-	struct netlbl_domhsh_tbl *hsh_tbl;
-	struct netlbl_dom_map *list_iter;
-	ssize_t tmp_len;
+	int ret_val = -ENOENT;
+	u32 iter_bkt;
+	struct netlbl_dom_map *iter_entry;
+	u32 chain_cnt = 0;
 
-	buf_len = NETLBL_LEN_U32;
 	rcu_read_lock();
-	hsh_tbl = rcu_dereference(netlbl_domhsh);
-	for (bkt_iter = 0; bkt_iter < hsh_tbl->size; bkt_iter++)
-		list_for_each_entry_rcu(list_iter,
-					&hsh_tbl->tbl[bkt_iter], list) {
-			buf_len += NETLBL_LEN_U32 +
-				nla_total_size(strlen(list_iter->domain) + 1);
-			switch (list_iter->type) {
-			case NETLBL_NLTYPE_UNLABELED:
-				break;
-			case NETLBL_NLTYPE_CIPSOV4:
-				buf_len += 2 * NETLBL_LEN_U32;
-				break;
-			}
-			dom_cnt++;
-		}
-
-	skb = netlbl_netlink_alloc_skb(headroom, buf_len, GFP_ATOMIC);
-	if (skb == NULL)
-		goto dump_failure;
-
-	if (nla_put_u32(skb, NLA_U32, dom_cnt) != 0)
-		goto dump_failure;
-	buf_len -= NETLBL_LEN_U32;
-	hsh_tbl = rcu_dereference(netlbl_domhsh);
-	for (bkt_iter = 0; bkt_iter < hsh_tbl->size; bkt_iter++)
-		list_for_each_entry_rcu(list_iter,
-					&hsh_tbl->tbl[bkt_iter], list) {
-			tmp_len = nla_total_size(strlen(list_iter->domain) +
-						 1);
-			if (buf_len < NETLBL_LEN_U32 + tmp_len)
-				goto dump_failure;
-			if (nla_put_string(skb,
-					   NLA_STRING,
-					   list_iter->domain) != 0)
-				goto dump_failure;
-			if (nla_put_u32(skb, NLA_U32, list_iter->type) != 0)
-				goto dump_failure;
-			buf_len -= NETLBL_LEN_U32 + tmp_len;
-			switch (list_iter->type) {
-			case NETLBL_NLTYPE_UNLABELED:
-				break;
-			case NETLBL_NLTYPE_CIPSOV4:
-				if (buf_len < 2 * NETLBL_LEN_U32)
-					goto dump_failure;
-				if (nla_put_u32(skb,
-				       NLA_U32,
-				       list_iter->type_def.cipsov4->type) != 0)
-					goto dump_failure;
-				if (nla_put_u32(skb,
-				       NLA_U32,
-				       list_iter->type_def.cipsov4->doi) != 0)
-					goto dump_failure;
-				buf_len -= 2 * NETLBL_LEN_U32;
-				break;
+	for (iter_bkt = *skip_bkt;
+	     iter_bkt < rcu_dereference(netlbl_domhsh)->size;
+	     iter_bkt++, chain_cnt = 0) {
+		list_for_each_entry_rcu(iter_entry,
+					&netlbl_domhsh->tbl[iter_bkt],
+					list)
+			if (iter_entry->valid) {
+				if (chain_cnt++ < *skip_chain)
+					continue;
+				ret_val = callback(iter_entry, cb_arg);
+				if (ret_val < 0) {
+					chain_cnt--;
+					goto walk_return;
+				}
 			}
-		}
-	rcu_read_unlock();
-
-	return skb;
-
-dump_failure:
-	rcu_read_unlock();
-	kfree_skb(skb);
-	return NULL;
-}
-
-/**
- * netlbl_domhsh_dump_default - Dump the default domain mapping into a sk_buff
- *
- * Description:
- * Dump the default domain mapping into a buffer suitable for returning to an
- * application in response to a NetLabel management DEFDOMAIN message.  This
- * function may fail if another process is changing the default domain mapping
- * at the same time.  The returned sk_buff has room at the front of the
- * skb_buff for @headroom bytes.  See netlabel.h for the DEFDOMAIN message
- * format.  Returns a pointer to a sk_buff on success, NULL on error.
- *
- */
-struct sk_buff *netlbl_domhsh_dump_default(size_t headroom)
-{
-	struct sk_buff *skb;
-	ssize_t buf_len;
-	struct netlbl_dom_map *entry;
-
-	buf_len = NETLBL_LEN_U32;
-	rcu_read_lock();
-	entry = rcu_dereference(netlbl_domhsh_def);
-	if (entry != NULL)
-		switch (entry->type) {
-		case NETLBL_NLTYPE_UNLABELED:
-			break;
-		case NETLBL_NLTYPE_CIPSOV4:
-			buf_len += 2 * NETLBL_LEN_U32;
-			break;
-		}
-
-	skb = netlbl_netlink_alloc_skb(headroom, buf_len, GFP_ATOMIC);
-	if (skb == NULL)
-		goto dump_default_failure;
-
-	if (entry != rcu_dereference(netlbl_domhsh_def))
-		goto dump_default_failure;
-	if (entry != NULL) {
-		if (nla_put_u32(skb, NLA_U32, entry->type) != 0)
-			goto dump_default_failure;
-		buf_len -= NETLBL_LEN_U32;
-		switch (entry->type) {
-		case NETLBL_NLTYPE_UNLABELED:
-			break;
-		case NETLBL_NLTYPE_CIPSOV4:
-			if (buf_len < 2 * NETLBL_LEN_U32)
-				goto dump_default_failure;
-			if (nla_put_u32(skb,
-					NLA_U32,
-					entry->type_def.cipsov4->type) != 0)
-				goto dump_default_failure;
-			if (nla_put_u32(skb,
-					NLA_U32,
-					entry->type_def.cipsov4->doi) != 0)
-				goto dump_default_failure;
-			buf_len -= 2 * NETLBL_LEN_U32;
-			break;
-		}
-	} else
-		nla_put_u32(skb, NLA_U32, NETLBL_NLTYPE_NONE);
-	rcu_read_unlock();
-
-	return skb;
+	}
 
-dump_default_failure:
+walk_return:
 	rcu_read_unlock();
-	kfree_skb(skb);
-	return NULL;
+	*skip_bkt = iter_bkt;
+	*skip_chain = chain_cnt;
+	return ret_val;
 }

net/netlabel/netlabel_domainhash.h

@@ -61,7 +61,9 @@ int netlbl_domhsh_add(struct netlbl_dom_map *entry);
 int netlbl_domhsh_add_default(struct netlbl_dom_map *entry);
 int netlbl_domhsh_remove_default(void);
 struct netlbl_dom_map *netlbl_domhsh_getentry(const char *domain);
-struct sk_buff *netlbl_domhsh_dump(size_t headroom);
-struct sk_buff *netlbl_domhsh_dump_default(size_t headroom);
+int netlbl_domhsh_walk(u32 *skip_bkt,
+		     u32 *skip_chain,
+		     int (*callback) (struct netlbl_dom_map *entry, void *arg),
+		     void *cb_arg);
 
 #endif

net/netlabel/netlabel_kapi.c

@@ -84,6 +84,29 @@ int netlbl_socket_setattr(const struct socket *sock,
 	return ret_val;
 }
 
+/**
+ * netlbl_sock_getattr - Determine the security attributes of a sock
+ * @sk: the sock
+ * @secattr: the security attributes
+ *
+ * Description:
+ * Examines the given sock to see any NetLabel style labeling has been
+ * applied to the sock, if so it parses the socket label and returns the
+ * security attributes in @secattr.  Returns zero on success, negative values
+ * on failure.
+ *
+ */
+int netlbl_sock_getattr(struct sock *sk, struct netlbl_lsm_secattr *secattr)
+{
+	int ret_val;
+
+	ret_val = cipso_v4_sock_getattr(sk, secattr);
+	if (ret_val == 0)
+		return 0;
+
+	return netlbl_unlabel_getattr(secattr);
+}
+
 /**
  * netlbl_socket_getattr - Determine the security attributes of a socket
  * @sock: the socket

net/netlabel/netlabel_mgmt.h

@@ -34,212 +34,137 @@
 #include <net/netlabel.h>
 
 /*
- * The following NetLabel payloads are supported by the management interface,
- * all of which are preceeded by the nlmsghdr struct.
- *
- * o ACK:
- *   Sent by the kernel in response to an applications message, applications
- *   should never send this message.
- *
- *   +----------------------+-----------------------+
- *   | seq number (32 bits) | return code (32 bits) |
- *   +----------------------+-----------------------+
- *
- *     seq number:  the sequence number of the original message, taken from the
- *                  nlmsghdr structure
- *     return code: return value, based on errno values
+ * The following NetLabel payloads are supported by the management interface.
  *
  * o ADD:
  *   Sent by an application to add a domain mapping to the NetLabel system.
- *   The kernel should respond with an ACK.
- *
- *   +-------------------+
- *   | domains (32 bits) | ...
- *   +-------------------+
- *
- *     domains: the number of domains in the message
- *
- *   +--------------------------+-------------------------+
- *   | domain string (variable) | protocol type (32 bits) | ...
- *   +--------------------------+-------------------------+
  *
- *   +-------------- ---- --- -- -
- *   | mapping data                ... repeated
- *   +-------------- ---- --- -- -
+ *   Required attributes:
  *
- *     domain string: the domain string, NULL terminated
- *     protocol type: the protocol type (defined by NETLBL_NLTYPE_*)
- *     mapping data:  specific to the map type (see below)
+ *     NLBL_MGMT_A_DOMAIN
+ *     NLBL_MGMT_A_PROTOCOL
  *
- *   NETLBL_NLTYPE_UNLABELED
+ *   If using NETLBL_NLTYPE_CIPSOV4 the following attributes are required:
  *
- *     No mapping data for this protocol type.
+ *     NLBL_MGMT_A_CV4DOI
  *
- *   NETLBL_NLTYPE_CIPSOV4
- *
- *   +---------------+
- *   | doi (32 bits) |
- *   +---------------+
- *
- *     doi:  the CIPSO DOI value
+ *   If using NETLBL_NLTYPE_UNLABELED no other attributes are required.
  *
  * o REMOVE:
  *   Sent by an application to remove a domain mapping from the NetLabel
- *   system.  The kernel should ACK this message.
- *
- *   +-------------------+
- *   | domains (32 bits) | ...
- *   +-------------------+
+ *   system.
  *
- *     domains: the number of domains in the message
+ *   Required attributes:
  *
- *   +--------------------------+
- *   | domain string (variable) | ...
- *   +--------------------------+
+ *     NLBL_MGMT_A_DOMAIN
  *
- *     domain string: the domain string, NULL terminated
- *
- * o LIST:
+ * o LISTALL:
  *   This message can be sent either from an application or by the kernel in
- *   response to an application generated LIST message.  When sent by an
- *   application there is no payload.  The kernel should respond to a LIST
- *   message either with a LIST message on success or an ACK message on
- *   failure.
- *
- *   +-------------------+
- *   | domains (32 bits) | ...
- *   +-------------------+
- *
- *     domains: the number of domains in the message
+ *   response to an application generated LISTALL message.  When sent by an
+ *   application there is no payload and the NLM_F_DUMP flag should be set.
+ *   The kernel should respond with a series of the following messages.
  *
- *   +--------------------------+
- *   | domain string (variable) | ...
- *   +--------------------------+
+ *   Required attributes:
  *
- *   +-------------------------+-------------- ---- --- -- -
- *   | protocol type (32 bits) | mapping data                ... repeated
- *   +-------------------------+-------------- ---- --- -- -
+ *     NLBL_MGMT_A_DOMAIN
+ *     NLBL_MGMT_A_PROTOCOL
  *
- *     domain string: the domain string, NULL terminated
- *     protocol type: the protocol type (defined by NETLBL_NLTYPE_*)
- *     mapping data:  specific to the map type (see below)
+ *   If using NETLBL_NLTYPE_CIPSOV4 the following attributes are required:
  *
- *   NETLBL_NLTYPE_UNLABELED
+ *     NLBL_MGMT_A_CV4DOI
  *
- *     No mapping data for this protocol type.
- *
- *   NETLBL_NLTYPE_CIPSOV4
- *
- *   +----------------+---------------+
- *   | type (32 bits) | doi (32 bits) |
- *   +----------------+---------------+
- *
- *     type: the CIPSO mapping table type (defined in the cipso_ipv4.h header
- *           as CIPSO_V4_MAP_*)
- *     doi:  the CIPSO DOI value
+ *   If using NETLBL_NLTYPE_UNLABELED no other attributes are required.
  *
  * o ADDDEF:
  *   Sent by an application to set the default domain mapping for the NetLabel
- *   system.  The kernel should respond with an ACK.
+ *   system.
  *
- *   +-------------------------+-------------- ---- --- -- -
- *   | protocol type (32 bits) | mapping data                ... repeated
- *   +-------------------------+-------------- ---- --- -- -
+ *   Required attributes:
  *
- *     protocol type: the protocol type (defined by NETLBL_NLTYPE_*)
- *     mapping data:  specific to the map type (see below)
+ *     NLBL_MGMT_A_PROTOCOL
  *
- *   NETLBL_NLTYPE_UNLABELED
+ *   If using NETLBL_NLTYPE_CIPSOV4 the following attributes are required:
  *
- *     No mapping data for this protocol type.
+ *     NLBL_MGMT_A_CV4DOI
  *
- *   NETLBL_NLTYPE_CIPSOV4
- *
- *   +---------------+
- *   | doi (32 bits) |
- *   +---------------+
- *
- *     doi:  the CIPSO DOI value
+ *   If using NETLBL_NLTYPE_UNLABELED no other attributes are required.
  *
  * o REMOVEDEF:
  *   Sent by an application to remove the default domain mapping from the
- *   NetLabel system, there is no payload.  The kernel should ACK this message.
+ *   NetLabel system, there is no payload.
  *
  * o LISTDEF:
  *   This message can be sent either from an application or by the kernel in
  *   response to an application generated LISTDEF message.  When sent by an
- *   application there is no payload.  The kernel should respond to a
- *   LISTDEF message either with a LISTDEF message on success or an ACK message
- *   on failure.
- *
- *   +-------------------------+-------------- ---- --- -- -
- *   | protocol type (32 bits) | mapping data                ... repeated
- *   +-------------------------+-------------- ---- --- -- -
+ *   application there is no payload.  On success the kernel should send a
+ *   response using the following format.
  *
- *     protocol type: the protocol type (defined by NETLBL_NLTYPE_*)
- *     mapping data:  specific to the map type (see below)
+ *   Required attributes:
  *
- *   NETLBL_NLTYPE_UNLABELED
+ *     NLBL_MGMT_A_PROTOCOL
  *
- *     No mapping data for this protocol type.
+ *   If using NETLBL_NLTYPE_CIPSOV4 the following attributes are required:
  *
- *   NETLBL_NLTYPE_CIPSOV4
+ *     NLBL_MGMT_A_CV4DOI
  *
- *   +----------------+---------------+
- *   | type (32 bits) | doi (32 bits) |
- *   +----------------+---------------+
+ *   If using NETLBL_NLTYPE_UNLABELED no other attributes are required.
  *
- *     type: the CIPSO mapping table type (defined in the cipso_ipv4.h header
- *           as CIPSO_V4_MAP_*)
- *     doi:  the CIPSO DOI value
+ * o PROTOCOLS:
+ *   Sent by an application to request a list of configured NetLabel protocols
+ *   in the kernel.  When sent by an application there is no payload and the
+ *   NLM_F_DUMP flag should be set.  The kernel should respond with a series of
+ *   the following messages.
  *
- * o MODULES:
- *   Sent by an application to request a list of configured NetLabel modules
- *   in the kernel.  When sent by an application there is no payload.
+ *   Required attributes:
  *
- *   +-------------------+
- *   | modules (32 bits) | ...
- *   +-------------------+
- *
- *     modules: the number of modules in the message, if this is an application
- *              generated message and the value is zero then return a list of
- *              the configured modules
- *
- *   +------------------+
- *   | module (32 bits) | ... repeated
- *   +------------------+
- *
- *     module: the module number as defined by NETLBL_NLTYPE_*
+ *     NLBL_MGMT_A_PROTOCOL
  *
  * o VERSION:
- *   Sent by an application to request the NetLabel version string.  When sent
- *   by an application there is no payload.  This message type is also used by
- *   the kernel to respond to an VERSION request.
+ *   Sent by an application to request the NetLabel version.  When sent by an
+ *   application there is no payload.  This message type is also used by the
+ *   kernel to respond to an VERSION request.
  *
- *   +-------------------+
- *   | version (32 bits) |
- *   +-------------------+
+ *   Required attributes:
  *
- *     version: the protocol version number
+ *     NLBL_MGMT_A_VERSION
  *
  */
 
 /* NetLabel Management commands */
 enum {
 	NLBL_MGMT_C_UNSPEC,
-	NLBL_MGMT_C_ACK,
 	NLBL_MGMT_C_ADD,
 	NLBL_MGMT_C_REMOVE,
-	NLBL_MGMT_C_LIST,
+	NLBL_MGMT_C_LISTALL,
 	NLBL_MGMT_C_ADDDEF,
 	NLBL_MGMT_C_REMOVEDEF,
 	NLBL_MGMT_C_LISTDEF,
-	NLBL_MGMT_C_MODULES,
+	NLBL_MGMT_C_PROTOCOLS,
 	NLBL_MGMT_C_VERSION,
 	__NLBL_MGMT_C_MAX,
 };
 #define NLBL_MGMT_C_MAX (__NLBL_MGMT_C_MAX - 1)
 
+/* NetLabel Management attributes */
+enum {
+	NLBL_MGMT_A_UNSPEC,
+	NLBL_MGMT_A_DOMAIN,
+	/* (NLA_NUL_STRING)
+	 * the NULL terminated LSM domain string */
+	NLBL_MGMT_A_PROTOCOL,
+	/* (NLA_U32)
+	 * the NetLabel protocol type (defined by NETLBL_NLTYPE_*) */
+	NLBL_MGMT_A_VERSION,
+	/* (NLA_U32)
+	 * the NetLabel protocol version number (defined by
+	 * NETLBL_PROTO_VERSION) */
+	NLBL_MGMT_A_CV4DOI,
+	/* (NLA_U32)
+	 * the CIPSOv4 DOI value */
+	__NLBL_MGMT_A_MAX,
+};
+#define NLBL_MGMT_A_MAX (__NLBL_MGMT_A_MAX - 1)
+
 /* NetLabel protocol functions */
 int netlbl_mgmt_genl_init(void);
 

net/netlabel/netlabel_unlabeled.c

@@ -55,9 +55,13 @@ static struct genl_family netlbl_unlabel_gnl_family = {
 	.hdrsize = 0,
 	.name = NETLBL_NLTYPE_UNLABELED_NAME,
 	.version = NETLBL_PROTO_VERSION,
-	.maxattr = 0,
+	.maxattr = NLBL_UNLABEL_A_MAX,
 };
 
+/* NetLabel Netlink attribute policy */
+static struct nla_policy netlbl_unlabel_genl_policy[NLBL_UNLABEL_A_MAX + 1] = {
+	[NLBL_UNLABEL_A_ACPTFLG] = { .type = NLA_U8 },
+};
 
 /*
  * NetLabel Command Handlers
@@ -75,31 +79,18 @@ static struct genl_family netlbl_unlabel_gnl_family = {
  */
 static int netlbl_unlabel_accept(struct sk_buff *skb, struct genl_info *info)
 {
-	int ret_val;
-	struct nlattr *data = netlbl_netlink_payload_data(skb);
-	u32 value;
-
-	ret_val = netlbl_netlink_cap_check(skb, CAP_NET_ADMIN);
-	if (ret_val != 0)
-		return ret_val;
+	int ret_val = -EINVAL;
+	u8 value;
 
-	if (netlbl_netlink_payload_len(skb) == NETLBL_LEN_U32) {
-		value = nla_get_u32(data);
+	if (info->attrs[NLBL_UNLABEL_A_ACPTFLG]) {
+		value = nla_get_u8(info->attrs[NLBL_UNLABEL_A_ACPTFLG]);
 		if (value == 1 || value == 0) {
 			atomic_set(&netlabel_unlabel_accept_flg, value);
-			netlbl_netlink_send_ack(info,
-						netlbl_unlabel_gnl_family.id,
-						NLBL_UNLABEL_C_ACK,
-						NETLBL_E_OK);
-			return 0;
+			ret_val = 0;
 		}
 	}
 
-	netlbl_netlink_send_ack(info,
-				netlbl_unlabel_gnl_family.id,
-				NLBL_UNLABEL_C_ACK,
-				EINVAL);
-	return -EINVAL;
+	return ret_val;
 }
 
 /**
@@ -114,39 +105,39 @@ static int netlbl_unlabel_accept(struct sk_buff *skb, struct genl_info *info)
  */
 static int netlbl_unlabel_list(struct sk_buff *skb, struct genl_info *info)
 {
-	int ret_val = -ENOMEM;
+	int ret_val = -EINVAL;
 	struct sk_buff *ans_skb;
+	void *data;
 
-	ans_skb = netlbl_netlink_alloc_skb(0,
-					   GENL_HDRLEN + NETLBL_LEN_U32,
-					   GFP_KERNEL);
+	ans_skb = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
 	if (ans_skb == NULL)
 		goto list_failure;
-
-	if (netlbl_netlink_hdr_put(ans_skb,
-				   info->snd_pid,
-				   0,
-				   netlbl_unlabel_gnl_family.id,
-				   NLBL_UNLABEL_C_LIST) == NULL)
+	data = netlbl_netlink_hdr_put(ans_skb,
+				      info->snd_pid,
+				      info->snd_seq,
+				      netlbl_unlabel_gnl_family.id,
+				      0,
+				      NLBL_UNLABEL_C_LIST);
+	if (data == NULL) {
+		ret_val = -ENOMEM;
 		goto list_failure;
+	}
 
-	ret_val = nla_put_u32(ans_skb,
-			      NLA_U32,
-			      atomic_read(&netlabel_unlabel_accept_flg));
+	ret_val = nla_put_u8(ans_skb,
+			     NLBL_UNLABEL_A_ACPTFLG,
+			     atomic_read(&netlabel_unlabel_accept_flg));
 	if (ret_val != 0)
 		goto list_failure;
 
-	ret_val = netlbl_netlink_snd(ans_skb, info->snd_pid);
+	genlmsg_end(ans_skb, data);
+
+	ret_val = genlmsg_unicast(ans_skb, info->snd_pid);
 	if (ret_val != 0)
 		goto list_failure;
-
 	return 0;
 
 list_failure:
-	netlbl_netlink_send_ack(info,
-				netlbl_unlabel_gnl_family.id,
-				NLBL_UNLABEL_C_ACK,
-				-ret_val);
+	kfree(ans_skb);
 	return ret_val;
 }
 
@@ -157,7 +148,8 @@ static int netlbl_unlabel_list(struct sk_buff *skb, struct genl_info *info)
 
 static struct genl_ops netlbl_unlabel_genl_c_accept = {
 	.cmd = NLBL_UNLABEL_C_ACCEPT,
-	.flags = 0,
+	.flags = GENL_ADMIN_PERM,
+	.policy = netlbl_unlabel_genl_policy,
 	.doit = netlbl_unlabel_accept,
 	.dumpit = NULL,
 };
@@ -165,6 +157,7 @@ static struct genl_ops netlbl_unlabel_genl_c_accept = {
 static struct genl_ops netlbl_unlabel_genl_c_list = {
 	.cmd = NLBL_UNLABEL_C_LIST,
 	.flags = 0,
+	.policy = netlbl_unlabel_genl_policy,
 	.doit = netlbl_unlabel_list,
 	.dumpit = NULL,
 };
@@ -218,10 +211,8 @@ int netlbl_unlabel_genl_init(void)
  */
 int netlbl_unlabel_getattr(struct netlbl_lsm_secattr *secattr)
 {
-	if (atomic_read(&netlabel_unlabel_accept_flg) == 1) {
-		memset(secattr, 0, sizeof(*secattr));
-		return 0;
-	}
+	if (atomic_read(&netlabel_unlabel_accept_flg) == 1)
+		return netlbl_secattr_init(secattr);
 
 	return -ENOMSG;
 }

net/netlabel/netlabel_unlabeled.h

@@ -36,56 +36,47 @@
 /*
  * The following NetLabel payloads are supported by the Unlabeled subsystem.
  *
- * o ACK:
- *   Sent by the kernel in response to an applications message, applications
- *   should never send this message.
- *
- *   +----------------------+-----------------------+
- *   | seq number (32 bits) | return code (32 bits) |
- *   +----------------------+-----------------------+
- *
- *     seq number:  the sequence number of the original message, taken from the
- *                  nlmsghdr structure
- *     return code: return value, based on errno values
- *
  * o ACCEPT
  *   This message is sent from an application to specify if the kernel should
  *   allow unlabled packets to pass if they do not match any of the static
  *   mappings defined in the unlabeled module.
  *
- *   +-----------------+
- *   | allow (32 bits) |
- *   +-----------------+
+ *   Required attributes:
  *
- *     allow: if true (1) then allow the packets to pass, if false (0) then
- *            reject the packets
+ *     NLBL_UNLABEL_A_ACPTFLG
  *
  * o LIST
  *   This message can be sent either from an application or by the kernel in
  *   response to an application generated LIST message.  When sent by an
  *   application there is no payload.  The kernel should respond to a LIST
- *   message either with a LIST message on success or an ACK message on
- *   failure.
+ *   message with a LIST message on success.
  *
- *   +-----------------------+
- *   | accept flag (32 bits) |
- *   +-----------------------+
+ *   Required attributes:
  *
- *     accept flag: if true (1) then unlabeled packets are allowed to pass,
- *                  if false (0) then unlabeled packets are rejected
+ *     NLBL_UNLABEL_A_ACPTFLG
  *
  */
 
 /* NetLabel Unlabeled commands */
 enum {
 	NLBL_UNLABEL_C_UNSPEC,
-	NLBL_UNLABEL_C_ACK,
 	NLBL_UNLABEL_C_ACCEPT,
 	NLBL_UNLABEL_C_LIST,
 	__NLBL_UNLABEL_C_MAX,
 };
 #define NLBL_UNLABEL_C_MAX (__NLBL_UNLABEL_C_MAX - 1)
 
+/* NetLabel Unlabeled attributes */
+enum {
+	NLBL_UNLABEL_A_UNSPEC,
+	NLBL_UNLABEL_A_ACPTFLG,
+	/* (NLA_U8)
+	 * if true then unlabeled packets are allowed to pass, else unlabeled
+	 * packets are rejected */
+	__NLBL_UNLABEL_A_MAX,
+};
+#define NLBL_UNLABEL_A_MAX (__NLBL_UNLABEL_A_MAX - 1)
+
 /* NetLabel protocol functions */
 int netlbl_unlabel_genl_init(void);
 

net/netlabel/netlabel_user.c

@@ -74,85 +74,3 @@ int netlbl_netlink_init(void)
 
 	return 0;
 }
-
-/*
- * NetLabel Common Protocol Functions
- */
-
-/**
- * netlbl_netlink_send_ack - Send an ACK message
- * @info: the generic NETLINK information
- * @genl_family: the generic NETLINK family ID value
- * @ack_cmd: the generic NETLINK family ACK command value
- * @ret_code: return code to use
- *
- * Description:
- * This function sends an ACK message to the sender of the NETLINK message
- * specified by @info.
- *
- */
-void netlbl_netlink_send_ack(const struct genl_info *info,
-			     u32 genl_family,
-			     u8 ack_cmd,
-			     u32 ret_code)
-{
-	size_t data_size;
-	struct sk_buff *skb;
-
-	data_size = GENL_HDRLEN + 2 * NETLBL_LEN_U32;
-	skb = netlbl_netlink_alloc_skb(0, data_size, GFP_KERNEL);
-	if (skb == NULL)
-		return;
-
-	if (netlbl_netlink_hdr_put(skb,
-				   info->snd_pid,
-				   0,
-				   genl_family,
-				   ack_cmd) == NULL)
-		goto send_ack_failure;
-
-	if (nla_put_u32(skb, NLA_U32, info->snd_seq) != 0)
-		goto send_ack_failure;
-	if (nla_put_u32(skb, NLA_U32, ret_code) != 0)
-		goto send_ack_failure;
-
-	netlbl_netlink_snd(skb, info->snd_pid);
-	return;
-
-send_ack_failure:
-	kfree_skb(skb);
-}
-
-/*
- * NETLINK I/O Functions
- */
-
-/**
- * netlbl_netlink_snd - Send a NetLabel message
- * @skb: NetLabel message
- * @pid: destination PID
- *
- * Description:
- * Sends a unicast NetLabel message over the NETLINK socket.
- *
- */
-int netlbl_netlink_snd(struct sk_buff *skb, u32 pid)
-{
-	return genlmsg_unicast(skb, pid);
-}
-
-/**
- * netlbl_netlink_snd - Send a NetLabel message
- * @skb: NetLabel message
- * @pid: sending PID
- * @group: multicast group id
- *
- * Description:
- * Sends a multicast NetLabel message over the NETLINK socket to all members
- * of @group except @pid.
- *
- */
-int netlbl_netlink_snd_multicast(struct sk_buff *skb, u32 pid, u32 group)
-{
-	return genlmsg_multicast(skb, pid, group, GFP_KERNEL);
-}

net/netlabel/netlabel_user.h

@@ -40,72 +40,6 @@
 
 /* NetLabel NETLINK helper functions */
 
-/**
- * netlbl_netlink_cap_check - Check the NETLINK msg capabilities
- * @skb: the NETLINK buffer
- * @req_cap: the required capability
- *
- * Description:
- * Check the NETLINK buffer's capabilities against the required capabilities.
- * Returns zero on success, negative values on failure.
- *
- */
-static inline int netlbl_netlink_cap_check(const struct sk_buff *skb,
-					   kernel_cap_t req_cap)
-{
-	if (cap_raised(NETLINK_CB(skb).eff_cap, req_cap))
-		return 0;
-	return -EPERM;
-}
-
-/**
- * netlbl_getinc_u8 - Read a u8 value from a nlattr stream and move on
- * @nla: the attribute
- * @rem_len: remaining length
- *
- * Description:
- * Return a u8 value pointed to by @nla and advance it to the next attribute.
- *
- */
-static inline u8 netlbl_getinc_u8(struct nlattr **nla, int *rem_len)
-{
-	u8 val = nla_get_u8(*nla);
-	*nla = nla_next(*nla, rem_len);
-	return val;
-}
-
-/**
- * netlbl_getinc_u16 - Read a u16 value from a nlattr stream and move on
- * @nla: the attribute
- * @rem_len: remaining length
- *
- * Description:
- * Return a u16 value pointed to by @nla and advance it to the next attribute.
- *
- */
-static inline u16 netlbl_getinc_u16(struct nlattr **nla, int *rem_len)
-{
-	u16 val = nla_get_u16(*nla);
-	*nla = nla_next(*nla, rem_len);
-	return val;
-}
-
-/**
- * netlbl_getinc_u32 - Read a u32 value from a nlattr stream and move on
- * @nla: the attribute
- * @rem_len: remaining length
- *
- * Description:
- * Return a u32 value pointed to by @nla and advance it to the next attribute.
- *
- */
-static inline u32 netlbl_getinc_u32(struct nlattr **nla, int *rem_len)
-{
-	u32 val = nla_get_u32(*nla);
-	*nla = nla_next(*nla, rem_len);
-	return val;
-}
-
 /**
  * netlbl_netlink_hdr_put - Write the NETLINK buffers into a sk_buff
  * @skb: the packet
@@ -124,6 +58,7 @@ static inline void *netlbl_netlink_hdr_put(struct sk_buff *skb,
 					   u32 pid,
 					   u32 seq,
 					   int type,
+					   int flags,
 					   u8 cmd)
 {
 	return genlmsg_put(skb,
@@ -131,85 +66,13 @@ static inline void *netlbl_netlink_hdr_put(struct sk_buff *skb,
 			   seq,
 			   type,
 			   0,
-			   0,
+			   flags,
 			   cmd,
 			   NETLBL_PROTO_VERSION);
 }
 
-/**
- * netlbl_netlink_hdr_push - Write the NETLINK buffers into a sk_buff
- * @skb: the packet
- * @pid: the PID of the receipient
- * @seq: the sequence number
- * @type: the generic NETLINK message family type
- * @cmd: command
- *
- * Description:
- * Write both a NETLINK nlmsghdr structure and a Generic NETLINK genlmsghdr
- * struct to the packet.
- *
- */
-static inline void netlbl_netlink_hdr_push(struct sk_buff *skb,
-					   u32 pid,
-					   u32 seq,
-					   int type,
-					   u8 cmd)
-
-{
-	struct nlmsghdr *nlh;
-	struct genlmsghdr *hdr;
-
-	nlh = (struct nlmsghdr *)skb_push(skb, NLMSG_SPACE(GENL_HDRLEN));
-	nlh->nlmsg_type = type;
-	nlh->nlmsg_len = skb->len;
-	nlh->nlmsg_flags = 0;
-	nlh->nlmsg_pid = pid;
-	nlh->nlmsg_seq = seq;
-
-	hdr = nlmsg_data(nlh);
-	hdr->cmd = cmd;
-	hdr->version = NETLBL_PROTO_VERSION;
-	hdr->reserved = 0;
-}
-
-/**
- * netlbl_netlink_payload_len - Return the length of the payload
- * @skb: the NETLINK buffer
- *
- * Description:
- * This function returns the length of the NetLabel payload.
- *
- */
-static inline u32 netlbl_netlink_payload_len(const struct sk_buff *skb)
-{
-	return nlmsg_len((struct nlmsghdr *)skb->data) - GENL_HDRLEN;
-}
-
-/**
- * netlbl_netlink_payload_data - Returns a pointer to the start of the payload
- * @skb: the NETLINK buffer
- *
- * Description:
- * This function returns a pointer to the start of the NetLabel payload.
- *
- */
-static inline void *netlbl_netlink_payload_data(const struct sk_buff *skb)
-{
-  return (unsigned char *)nlmsg_data((struct nlmsghdr *)skb->data) +
-	  GENL_HDRLEN;
-}
-
-/* NetLabel common protocol functions */
-
-void netlbl_netlink_send_ack(const struct genl_info *info,
-			     u32 genl_family,
-			     u8 ack_cmd,
-			     u32 ret_code);
-
 /* NetLabel NETLINK I/O functions */
 
 int netlbl_netlink_init(void);
-int netlbl_netlink_snd(struct sk_buff *skb, u32 pid);
-int netlbl_netlink_snd_multicast(struct sk_buff *skb, u32 pid, u32 group);
 
 #endif

security/selinux/ss/services.c

@@ -2502,14 +2502,24 @@ void selinux_netlbl_sock_graft(struct sock *sk, struct socket *sock)
 {
 	struct inode_security_struct *isec = SOCK_INODE(sock)->i_security;
 	struct sk_security_struct *sksec = sk->sk_security;
+	struct netlbl_lsm_secattr secattr;
+	u32 nlbl_peer_sid;
 
 	sksec->sclass = isec->sclass;
 
 	if (sk->sk_family != PF_INET)
 		return;
 
+	netlbl_secattr_init(&secattr);
+	if (netlbl_sock_getattr(sk, &secattr) == 0 &&
+	    selinux_netlbl_secattr_to_sid(NULL,
+					  &secattr,
+					  sksec->sid,
+					  &nlbl_peer_sid) == 0)
+		sksec->peer_sid = nlbl_peer_sid;
+	netlbl_secattr_destroy(&secattr, 0);
+
 	sksec->nlbl_state = NLBL_REQUIRE;
-	sksec->peer_sid = sksec->sid;
 
 	/* Try to set the NetLabel on the socket to save time later, if we fail
 	 * here we will pick up the pieces in later calls to
@@ -2601,7 +2611,7 @@ int selinux_netlbl_sock_rcv_skb(struct sk_security_struct *sksec,
 	u32 netlbl_sid;
 	u32 recv_perm;
 
-	rc = selinux_netlbl_skbuff_getsid(skb, sksec->sid, &netlbl_sid);
+	rc = selinux_netlbl_skbuff_getsid(skb, SECINITSID_NETMSG, &netlbl_sid);
 	if (rc != 0)
 		return rc;
 
@@ -2610,13 +2620,13 @@ int selinux_netlbl_sock_rcv_skb(struct sk_security_struct *sksec,
 
 	switch (sksec->sclass) {
 	case SECCLASS_UDP_SOCKET:
-		recv_perm = UDP_SOCKET__RECV_MSG;
+		recv_perm = UDP_SOCKET__RECVFROM;
 		break;
 	case SECCLASS_TCP_SOCKET:
-		recv_perm = TCP_SOCKET__RECV_MSG;
+		recv_perm = TCP_SOCKET__RECVFROM;
 		break;
 	default:
-		recv_perm = RAWIP_SOCKET__RECV_MSG;
+		recv_perm = RAWIP_SOCKET__RECVFROM;
 	}
 
 	rc = avc_has_perm(sksec->sid,