From 7c73e1bd21bc54b20b2d4ad0fc1a94ca0b76c285 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?YOSHIFUJI=20Hideaki=20/=20=E5=90=89=E8=97=A4=E8=8B=B1?=
 =?UTF-8?q?=E6=98=8E?= <yoshfuji@linux-ipv6.org>
Date: Fri, 21 Dec 2007 22:58:04 +0900
Subject: [PATCH 01/15] rto_min value display overflow

Reported by: Satoru SATOH <satoru.satoh@gmail.com>
"ip route show" does not print correct value when larger rto_min is
set (e.g. 3sec).

This problem is because of overflow in print_route() and
the patch below is a workaround fix for that.

[root test]# ./iproute2.git.org/ip/ip route show dev eth1
192.168.140.0/24  proto kernel  scope link  src 192.168.140.130
169.254.0.0/16  scope link
[root test]# ./iproute2.git.org/ip/ip route change 192.168.140.0/24
dev eth1 rto_min 3s
[root test]# ./iproute2.git.org/ip/ip route show dev eth1
192.168.140.0/24  scope link  rto_min lock 2ms     <-- wrong
169.254.0.0/16  scope link
[root test]# ./iproute2.git/ip/ip route show dev eth1  # patched version
192.168.140.0/24  scope link  rto_min lock 3000ms  <-- correct
169.254.0.0/16  scope link

This is a simpler fix.

Signed-off-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org>
---
 ip/iproute.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/ip/iproute.c b/ip/iproute.c
index f4200aef..7a885b0c 100644
--- a/ip/iproute.c
+++ b/ip/iproute.c
@@ -509,7 +509,7 @@ int print_route(const struct sockaddr_nl *who, struct nlmsghdr *n, void *arg)
 			    i != RTAX_RTO_MIN)
 				fprintf(fp, " %u", *(unsigned*)RTA_DATA(mxrta[i]));
 			else {
-				unsigned val = *(unsigned*)RTA_DATA(mxrta[i]);
+				unsigned long long val = *(unsigned*)RTA_DATA(mxrta[i]);
 
 				val *= 1000;
 				if (i == RTAX_RTT)
@@ -517,7 +517,7 @@ int print_route(const struct sockaddr_nl *who, struct nlmsghdr *n, void *arg)
 				else if (i == RTAX_RTTVAR)
 					val /= 4;
 				if (val >= hz)
-					fprintf(fp, " %ums", val/hz);
+					fprintf(fp, " %llums", val/hz);
 				else
 					fprintf(fp, " %.2fms", (float)val/hz);
 			}

From d84914a0c566516e13502fa555a92a2fb7968bb5 Mon Sep 17 00:00:00 2001
From: Vitaliy Gusev <vgusev@openvz.org>
Date: Mon, 17 Dec 2007 16:06:38 +0300
Subject: [PATCH 02/15] Fix lost export-dynamic

get_link_kind() fails for statically linked modules (vlan, veth, etc.) if "ip"
was linked without "export-dynamic".

Signed-off-by: Vitaliy Gusev <vgusev@openvz.org>

--
Thank,
Vitaliy Gusev
Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org>
---
 ip/Makefile | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/ip/Makefile b/ip/Makefile
index 448efb90..b427d581 100644
--- a/ip/Makefile
+++ b/ip/Makefile
@@ -24,3 +24,5 @@ clean:
 	rm -f $(ALLOBJ) $(TARGETS)
 
 LDLIBS += -ldl
+
+LDFLAGS += -Wl,-export-dynamic

From 909dfe2c7ebcfe853b2fe4f995be1c4681d5a2a5 Mon Sep 17 00:00:00 2001
From: Pavel Emelyanov <xemul@openvz.org>
Date: Thu, 19 Jul 2007 13:32:31 +0400
Subject: [PATCH 03/15] iplink_parse() routine

This routine parses CLI attributes, describing generic link
parameters such as name, address, etc.

This is mostly copy-pasted from iplink_modify().

Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Acked-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org>
---
 include/utils.h |   3 +
 ip/iplink.c     | 251 ++++++++++++++++++++++++++----------------------
 2 files changed, 138 insertions(+), 116 deletions(-)

diff --git a/include/utils.h b/include/utils.h
index 9ee55fdc..7223a10d 100644
--- a/include/utils.h
+++ b/include/utils.h
@@ -147,4 +147,7 @@ extern int cmdlineno;
 extern ssize_t getcmdline(char **line, size_t *len, FILE *in);
 extern int makeargs(char *line, char *argv[], int maxargs);
 
+struct iplink_req;
+int iplink_parse(int argc, char **argv, struct iplink_req *req,
+		char **name, char **type, char **link, char **dev);
 #endif /* __UTILS_H__ */
diff --git a/ip/iplink.c b/ip/iplink.c
index f28f91c3..95801a6c 100644
--- a/ip/iplink.c
+++ b/ip/iplink.c
@@ -143,22 +143,145 @@ static int iplink_have_newlink(void)
 }
 #endif /* ! IPLINK_IOCTL_COMPAT */
 
-static int iplink_modify(int cmd, unsigned int flags, int argc, char **argv)
+struct iplink_req {
+	struct nlmsghdr		n;
+	struct ifinfomsg	i;
+	char			buf[1024];
+};
+
+int iplink_parse(int argc, char **argv, struct iplink_req *req,
+		char **name, char **type, char **link, char **dev)
 {
+	int ret, len;
+	char abuf[32];
 	int qlen = -1;
 	int mtu = -1;
+
+	ret = argc;
+
+	while (argc > 0) {
+		if (strcmp(*argv, "up") == 0) {
+			req->i.ifi_change |= IFF_UP;
+			req->i.ifi_flags |= IFF_UP;
+		} else if (strcmp(*argv, "down") == 0) {
+			req->i.ifi_change |= IFF_UP;
+			req->i.ifi_flags &= ~IFF_UP;
+		} else if (strcmp(*argv, "name") == 0) {
+			NEXT_ARG();
+			*name = *argv;
+		} else if (matches(*argv, "link") == 0) {
+			NEXT_ARG();
+			*link = *argv;
+		} else if (matches(*argv, "address") == 0) {
+			NEXT_ARG();
+			len = ll_addr_a2n(abuf, sizeof(abuf), *argv);
+			addattr_l(&req->n, sizeof(*req), IFLA_ADDRESS, abuf, len);
+		} else if (matches(*argv, "broadcast") == 0 ||
+				strcmp(*argv, "brd") == 0) {
+			NEXT_ARG();
+			len = ll_addr_a2n(abuf, sizeof(abuf), *argv);
+			addattr_l(&req->n, sizeof(*req), IFLA_BROADCAST, abuf, len);
+		} else if (matches(*argv, "txqueuelen") == 0 ||
+				strcmp(*argv, "qlen") == 0 ||
+				matches(*argv, "txqlen") == 0) {
+			NEXT_ARG();
+			if (qlen != -1)
+				duparg("txqueuelen", *argv);
+			if (get_integer(&qlen,  *argv, 0))
+				invarg("Invalid \"txqueuelen\" value\n", *argv);
+			addattr_l(&req->n, sizeof(*req), IFLA_TXQLEN, &qlen, 4);
+		} else if (strcmp(*argv, "mtu") == 0) {
+			NEXT_ARG();
+			if (mtu != -1)
+				duparg("mtu", *argv);
+			if (get_integer(&mtu, *argv, 0))
+				invarg("Invalid \"mtu\" value\n", *argv);
+			addattr_l(&req->n, sizeof(*req), IFLA_MTU, &mtu, 4);
+		} else if (strcmp(*argv, "multicast") == 0) {
+			NEXT_ARG();
+			req->i.ifi_change |= IFF_MULTICAST;
+			if (strcmp(*argv, "on") == 0) {
+				req->i.ifi_flags |= IFF_MULTICAST;
+			} else if (strcmp(*argv, "off") == 0) {
+				req->i.ifi_flags &= ~IFF_MULTICAST;
+			} else
+				return on_off("multicast");
+		} else if (strcmp(*argv, "allmulticast") == 0) {
+			NEXT_ARG();
+			req->i.ifi_change |= IFF_ALLMULTI;
+			if (strcmp(*argv, "on") == 0) {
+				req->i.ifi_flags |= IFF_ALLMULTI;
+			} else if (strcmp(*argv, "off") == 0) {
+				req->i.ifi_flags &= ~IFF_ALLMULTI;
+			} else
+				return on_off("allmulticast");
+		} else if (strcmp(*argv, "promisc") == 0) {
+			NEXT_ARG();
+			req->i.ifi_change |= IFF_PROMISC;
+			if (strcmp(*argv, "on") == 0) {
+				req->i.ifi_flags |= IFF_PROMISC;
+			} else if (strcmp(*argv, "off") == 0) {
+				req->i.ifi_flags &= ~IFF_PROMISC;
+			} else
+				return on_off("promisc");
+		} else if (strcmp(*argv, "trailers") == 0) {
+			NEXT_ARG();
+			req->i.ifi_change |= IFF_NOTRAILERS;
+			if (strcmp(*argv, "off") == 0) {
+				req->i.ifi_flags |= IFF_NOTRAILERS;
+			} else if (strcmp(*argv, "on") == 0) {
+				req->i.ifi_flags &= ~IFF_NOTRAILERS;
+			} else
+				return on_off("trailers");
+		} else if (strcmp(*argv, "arp") == 0) {
+			NEXT_ARG();
+			req->i.ifi_change |= IFF_NOARP;
+			if (strcmp(*argv, "on") == 0) {
+				req->i.ifi_flags &= ~IFF_NOARP;
+			} else if (strcmp(*argv, "off") == 0) {
+				req->i.ifi_flags |= IFF_NOARP;
+			} else
+				return on_off("noarp");
+#ifdef IFF_DYNAMIC
+		} else if (matches(*argv, "dynamic") == 0) {
+			NEXT_ARG();
+			req->i.ifi_change |= IFF_DYNAMIC;
+			if (strcmp(*argv, "on") == 0) {
+				req->i.ifi_flags |= IFF_DYNAMIC;
+			} else if (strcmp(*argv, "off") == 0) {
+				req->i.ifi_flags &= ~IFF_DYNAMIC;
+			} else
+				return on_off("dynamic");
+#endif
+		} else if (matches(*argv, "type") == 0) {
+			NEXT_ARG();
+			*type = *argv;
+			argc--; argv++;
+			break;
+		} else {
+			if (strcmp(*argv, "dev") == 0) {
+				NEXT_ARG();
+			}
+			if (*dev)
+				duparg2("dev", *argv);
+			*dev = *argv;
+		}
+		argc--; argv++;
+	}
+
+	return ret - argc;
+}
+
+static int iplink_modify(int cmd, unsigned int flags, int argc, char **argv)
+{
 	int len;
-	char abuf[32];
 	char *dev = NULL;
 	char *name = NULL;
 	char *link = NULL;
 	char *type = NULL;
 	struct link_util *lu = NULL;
-	struct {
-		struct nlmsghdr		n;
-		struct ifinfomsg	i;
-		char			buf[1024];
-	} req;
+	struct iplink_req req;
+	int ret;
 
 	memset(&req, 0, sizeof(req));
 
@@ -167,116 +290,12 @@ static int iplink_modify(int cmd, unsigned int flags, int argc, char **argv)
 	req.n.nlmsg_type = cmd;
 	req.i.ifi_family = preferred_family;
 
-	while (argc > 0) {
-		if (strcmp(*argv, "up") == 0) {
-			req.i.ifi_change |= IFF_UP;
-			req.i.ifi_flags |= IFF_UP;
-		} else if (strcmp(*argv, "down") == 0) {
-			req.i.ifi_change |= IFF_UP;
-			req.i.ifi_flags &= ~IFF_UP;
-		} else if (strcmp(*argv, "name") == 0) {
-			NEXT_ARG();
-			name = *argv;
-		} else if (matches(*argv, "link") == 0) {
-			NEXT_ARG();
-			link = *argv;
-		} else if (matches(*argv, "address") == 0) {
-			NEXT_ARG();
-			len = ll_addr_a2n(abuf, sizeof(abuf), *argv);
-			addattr_l(&req.n, sizeof(req), IFLA_ADDRESS, abuf, len);
-		} else if (matches(*argv, "broadcast") == 0 ||
-			   strcmp(*argv, "brd") == 0) {
-			NEXT_ARG();
-			len = ll_addr_a2n(abuf, sizeof(abuf), *argv);
-			addattr_l(&req.n, sizeof(req), IFLA_BROADCAST, abuf, len);
-		} else if (matches(*argv, "txqueuelen") == 0 ||
-			   strcmp(*argv, "qlen") == 0 ||
-			   matches(*argv, "txqlen") == 0) {
-			NEXT_ARG();
-			if (qlen != -1)
-				duparg("txqueuelen", *argv);
-			if (get_integer(&qlen,  *argv, 0))
-				invarg("Invalid \"txqueuelen\" value\n", *argv);
-			addattr_l(&req.n, sizeof(req), IFLA_TXQLEN, &qlen, 4);
-		} else if (strcmp(*argv, "mtu") == 0) {
-			NEXT_ARG();
-			if (mtu != -1)
-				duparg("mtu", *argv);
-			if (get_integer(&mtu, *argv, 0))
-				invarg("Invalid \"mtu\" value\n", *argv);
-			addattr_l(&req.n, sizeof(req), IFLA_MTU, &mtu, 4);
-		} else if (strcmp(*argv, "multicast") == 0) {
-			NEXT_ARG();
-			req.i.ifi_change |= IFF_MULTICAST;
-			if (strcmp(*argv, "on") == 0) {
-				req.i.ifi_flags |= IFF_MULTICAST;
-			} else if (strcmp(*argv, "off") == 0) {
-				req.i.ifi_flags &= ~IFF_MULTICAST;
-			} else
-				return on_off("multicast");
-		} else if (strcmp(*argv, "allmulticast") == 0) {
-			NEXT_ARG();
-			req.i.ifi_change |= IFF_ALLMULTI;
-			if (strcmp(*argv, "on") == 0) {
-				req.i.ifi_flags |= IFF_ALLMULTI;
-			} else if (strcmp(*argv, "off") == 0) {
-				req.i.ifi_flags &= ~IFF_ALLMULTI;
-			} else
-				return on_off("allmulticast");
-		} else if (strcmp(*argv, "promisc") == 0) {
-			NEXT_ARG();
-			req.i.ifi_change |= IFF_PROMISC;
-			if (strcmp(*argv, "on") == 0) {
-				req.i.ifi_flags |= IFF_PROMISC;
-			} else if (strcmp(*argv, "off") == 0) {
-				req.i.ifi_flags &= ~IFF_PROMISC;
-			} else
-				return on_off("promisc");
-		} else if (strcmp(*argv, "trailers") == 0) {
-			NEXT_ARG();
-			req.i.ifi_change |= IFF_NOTRAILERS;
-			if (strcmp(*argv, "off") == 0) {
-				req.i.ifi_flags |= IFF_NOTRAILERS;
-			} else if (strcmp(*argv, "on") == 0) {
-				req.i.ifi_flags &= ~IFF_NOTRAILERS;
-			} else
-				return on_off("trailers");
-		} else if (strcmp(*argv, "arp") == 0) {
-			NEXT_ARG();
-			req.i.ifi_change |= IFF_NOARP;
-			if (strcmp(*argv, "on") == 0) {
-				req.i.ifi_flags &= ~IFF_NOARP;
-			} else if (strcmp(*argv, "off") == 0) {
-				req.i.ifi_flags |= IFF_NOARP;
-			} else
-				return on_off("noarp");
-#ifdef IFF_DYNAMIC
-		} else if (matches(*argv, "dynamic") == 0) {
-			NEXT_ARG();
-			req.i.ifi_change |= IFF_DYNAMIC;
-			if (strcmp(*argv, "on") == 0) {
-				req.i.ifi_flags |= IFF_DYNAMIC;
-			} else if (strcmp(*argv, "off") == 0) {
-				req.i.ifi_flags &= ~IFF_DYNAMIC;
-			} else
-				return on_off("dynamic");
-#endif
-		} else if (matches(*argv, "type") == 0) {
-			NEXT_ARG();
-			type = *argv;
-			argc--; argv++;
-			break;
-		} else {
-                        if (strcmp(*argv, "dev") == 0) {
-				NEXT_ARG();
-			}
-			if (dev)
-				duparg2("dev", *argv);
-			dev = *argv;
-		}
-		argc--; argv++;
-	}
+	ret = iplink_parse(argc, argv, &req, &name, &type, &link, &dev);
+	if (ret < 0)
+		return ret;
 
+	argc -= ret;
+	argv += ret;
 	ll_init_map(&rth);
 
 	if (type) {

From f9329ccaf933a9dee5760de6979c7be6f17e253f Mon Sep 17 00:00:00 2001
From: Vitaliy Gusev <vgusev@openvz.org>
Date: Tue, 18 Dec 2007 15:15:38 +0300
Subject: [PATCH 04/15] veth device link management

Signed-off-by: Vitaliy Gusev <vgusev@openvz.org>
Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org>
---
 ip/link_veth.c | 80 +++++++++++++++++---------------------------------
 ip/veth.h      |  2 --
 2 files changed, 27 insertions(+), 55 deletions(-)

diff --git a/ip/link_veth.c b/ip/link_veth.c
index a4764f2e..226b4ef4 100644
--- a/ip/link_veth.c
+++ b/ip/link_veth.c
@@ -10,78 +10,52 @@
  *
  */
 
-#include <stdio.h>
 #include <string.h>
 
 #include "utils.h"
 #include "ip_common.h"
 #include "veth.h"
 
-#define ETH_ALEN	6
+#define	IFNAMSIZ	16
 
 static void usage(void)
 {
-	printf("Usage: ip link add ... type veth "
-			"[peer <peer-name>] [mac <mac>] [peer_mac <mac>]\n");
+	printf("Usage: ip link <options> type veth "
+		"[peer <options>]\nTo get <options> type "
+		"'ip link add help'\n");
 }
 
 static int veth_parse_opt(struct link_util *lu, int argc, char **argv,
 		struct nlmsghdr *hdr)
 {
-	__u8 mac[ETH_ALEN];
-
-	for (; argc != 0; argv++, argc--) {
-		if (strcmp(*argv, "peer") == 0) {
-			argv++;
-			argc--;
-			if (argc == 0) {
-				usage();
-				return -1;
-			}
-
-			addattr_l(hdr, 1024, VETH_INFO_PEER,
-					*argv, strlen(*argv));
-
-			continue;
-		}
-
-		if (strcmp(*argv, "mac") == 0) {
-			argv++;
-			argc--;
-			if (argc == 0) {
-				usage();
-				return -1;
-			}
-
-			if (hexstring_a2n(*argv, mac, sizeof(mac)) == NULL)
-				return -1;
-
-			addattr_l(hdr, 1024, VETH_INFO_MAC,
-					mac, ETH_ALEN);
-			continue;
-		}
-
-		if (strcmp(*argv, "peer_mac") == 0) {
-			argv++;
-			argc--;
-			if (argc == 0) {
-				usage();
-				return -1;
-			}
-
-			if (hexstring_a2n(*argv, mac, sizeof(mac)) == NULL)
-				return -1;
-
-			addattr_l(hdr, 1024, VETH_INFO_PEER_MAC,
-					mac, ETH_ALEN);
-			continue;
-		}
+	char *name, *type, *link, *dev;
+	int err, len;
+	struct rtattr * data;
 
+	if (strcmp(argv[0], "peer") != 0) {
 		usage();
 		return -1;
 	}
 
-	return 0;
+	data = NLMSG_TAIL(hdr);
+	addattr_l(hdr, 1024, VETH_INFO_PEER, NULL, 0);
+
+	hdr->nlmsg_len += sizeof(struct ifinfomsg);
+
+	err = iplink_parse(argc - 1, argv + 1, (struct iplink_req *)hdr,
+			&name, &type, &link, &dev);
+	if (err < 0)
+		return err;
+
+	if (name) {
+		len = strlen(name) + 1;
+		if (len > IFNAMSIZ)
+			invarg("\"name\" too long\n", *argv);
+		addattr_l(hdr, 1024, IFLA_IFNAME, name, len);
+	}
+
+	data->rta_len = (void *)NLMSG_TAIL(hdr) - (void *)data;
+	return argc - 1 - err;
 }
 
 struct link_util veth_link_util = {
diff --git a/ip/veth.h b/ip/veth.h
index b84a5301..aa2e6f91 100644
--- a/ip/veth.h
+++ b/ip/veth.h
@@ -3,9 +3,7 @@
 
 enum {
 	VETH_INFO_UNSPEC,
-	VETH_INFO_MAC,
 	VETH_INFO_PEER,
-	VETH_INFO_PEER_MAC,
 
 	__VETH_INFO_MAX
 #define VETH_INFO_MAX	(__VETH_INFO_MAX - 1)

From c595fda55bfed9753851de5675aa310f523564b3 Mon Sep 17 00:00:00 2001
From: Stephen Hemminger <shemminger@linux-foundation.org>
Date: Fri, 21 Dec 2007 09:37:30 -0800
Subject: [PATCH 05/15] veth: use kernel header file

Use santized kernel header for veth.h and put in correct place
to prevent possible future problems with API.

Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org>
---
 {ip => include/net}/veth.h |  4 ++--
 ip/link_veth.c             | 13 ++++++-------
 2 files changed, 8 insertions(+), 9 deletions(-)
 rename {ip => include/net}/veth.h (71%)

diff --git a/ip/veth.h b/include/net/veth.h
similarity index 71%
rename from ip/veth.h
rename to include/net/veth.h
index aa2e6f91..3354c1eb 100644
--- a/ip/veth.h
+++ b/include/net/veth.h
@@ -1,5 +1,5 @@
-#ifndef __NET_VETH_H__
-#define __NET_VETH_H__
+#ifndef __NET_VETH_H_
+#define __NET_VETH_H_
 
 enum {
 	VETH_INFO_UNSPEC,
diff --git a/ip/link_veth.c b/ip/link_veth.c
index 226b4ef4..9dfb78f6 100644
--- a/ip/link_veth.c
+++ b/ip/link_veth.c
@@ -11,22 +11,21 @@
  */
 
 #include <string.h>
+#include <net/if.h>
+#include <net/veth.h>
 
 #include "utils.h"
 #include "ip_common.h"
-#include "veth.h"
-
-#define	IFNAMSIZ	16
 
 static void usage(void)
 {
 	printf("Usage: ip link <options> type veth "
-		"[peer <options>]\nTo get <options> type "
-		"'ip link add help'\n");
+	       "[peer <options>]\nTo get <options> type "
+	       "'ip link add help'\n");
 }
 
 static int veth_parse_opt(struct link_util *lu, int argc, char **argv,
-		struct nlmsghdr *hdr)
+			  struct nlmsghdr *hdr)
 {
 	char *name, *type, *link, *dev;
 	int err, len;
@@ -43,7 +42,7 @@ static int veth_parse_opt(struct link_util *lu, int argc, char **argv,
 	hdr->nlmsg_len += sizeof(struct ifinfomsg);
 
 	err = iplink_parse(argc - 1, argv + 1, (struct iplink_req *)hdr,
-			&name, &type, &link, &dev);
+			   &name, &type, &link, &dev);
 	if (err < 0)
 		return err;
 

From 235ac6a41d9d0439cce4eca8acdd31cac28605fc Mon Sep 17 00:00:00 2001
From: Stephen Hemminger <shemminger@linux-foundation.org>
Date: Fri, 21 Dec 2007 09:53:45 -0800
Subject: [PATCH 06/15] snapshot target

Add Makefile target to create snapshot file.

Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org>
---
 Makefile           | 4 ++++
 include/SNAPSHOT.h | 2 +-
 2 files changed, 5 insertions(+), 1 deletion(-)

diff --git a/Makefile b/Makefile
index 6c976dd9..de04176d 100644
--- a/Makefile
+++ b/Makefile
@@ -59,6 +59,10 @@ install: all
 	install -m 0755 -d $(DESTDIR)$(MANDIR)/man3
 	install -m 0644 $(shell find man/man3 -maxdepth 1 -type f) $(DESTDIR)$(MANDIR)/man3
 
+snapshot:
+	echo "static const char SNAPSHOT[] = \""`date +%y%m%d`"\";" \
+		> include/SNAPSHOT.h
+
 clean:
 	rm -f cscope.*
 	@for i in $(SUBDIRS) doc; \
diff --git a/include/SNAPSHOT.h b/include/SNAPSHOT.h
index dde2804d..cdeb2067 100644
--- a/include/SNAPSHOT.h
+++ b/include/SNAPSHOT.h
@@ -1 +1 @@
-static char SNAPSHOT[] = "071016";
+static const char SNAPSHOT[] = "071221";

From 118c923cc09551d3428e2905a69c07c5719988e5 Mon Sep 17 00:00:00 2001
From: Stephen Hemminger <shemminger@linux-foundation.org>
Date: Tue, 25 Dec 2007 12:38:08 -0800
Subject: [PATCH 07/15] veth.h move to linux/

Move veth.h to linux/ since it is an API.

Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org>
---
 include/{net => linux}/veth.h | 0
 ip/link_veth.c                | 2 +-
 2 files changed, 1 insertion(+), 1 deletion(-)
 rename include/{net => linux}/veth.h (100%)

diff --git a/include/net/veth.h b/include/linux/veth.h
similarity index 100%
rename from include/net/veth.h
rename to include/linux/veth.h
diff --git a/ip/link_veth.c b/ip/link_veth.c
index 9dfb78f6..9f5e8715 100644
--- a/ip/link_veth.c
+++ b/ip/link_veth.c
@@ -12,7 +12,7 @@
 
 #include <string.h>
 #include <net/if.h>
-#include <net/veth.h>
+#include <linux/veth.h>
 
 #include "utils.h"
 #include "ip_common.h"

From ea5dd59c03b36fe2acec8f03a8d7a2f7b7036b04 Mon Sep 17 00:00:00 2001
From: Stephen Hemminger <stephen.hemminger@vyatta.com>
Date: Mon, 31 Dec 2007 10:15:03 -0800
Subject: [PATCH 08/15] Manual page fixes

These are from debian sid.

Signed-off-by: Stephen Hemminger <stephen.hemminger@vyatta.com>
---
 man/man8/ip.8 | 2 +-
 man/man8/ss.8 | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/man/man8/ip.8 b/man/man8/ip.8
index 8fd6d528..84ec6f3d 100644
--- a/man/man8/ip.8
+++ b/man/man8/ip.8
@@ -32,7 +32,7 @@ maddr " | "  mroute " | " monitor " }"
 .br
 .BR promisc " { " on " | " off " } |"
 .br
-.BR allmulti " { " on " | " off " } |"
+.BR allmulticast " { " on " | " off " } |"
 .br
 .BR dynamic " { " on " | " off " } |"
 .br
diff --git a/man/man8/ss.8 b/man/man8/ss.8
index 19f341e6..015feb38 100644
--- a/man/man8/ss.8
+++ b/man/man8/ss.8
@@ -107,7 +107,7 @@ Display all UDP sockets.
 .B ss -o state established '( dport = :ssh or sport = :ssh )'
 Display all established ssh connections.
 .TP
-.B ss -x src \"/tmp/.X11-unix/*\"
+.B ss -x src /tmp/.X11-unix/*
 Find all local processes connected to X server.
 .TP
 .B ss -o state fin-wait-1 '( sport = :http or sport = :https )' dst 193.233.7/24

From 6b1ac654e9364ad279d3c82d8a3ef93efa9f3dfa Mon Sep 17 00:00:00 2001
From: Stephen Hemminger <stephen.hemminger@vyatta.com>
Date: Mon, 31 Dec 2007 10:29:52 -0800
Subject: [PATCH 09/15] add decode of match rules

Show ip address etc when decoding output of tc filter show

Signed-off-by: Stephen Hemminger <stephen.hemminger@vyatta.com>
---
 include/utils.h |  1 +
 lib/utils.c     | 35 ++++++++++++----------------
 tc/f_u32.c      | 61 +++++++++++++++++++++++++++++++++++++++----------
 3 files changed, 64 insertions(+), 33 deletions(-)

diff --git a/include/utils.h b/include/utils.h
index 7223a10d..5daed6b3 100644
--- a/include/utils.h
+++ b/include/utils.h
@@ -74,6 +74,7 @@ extern int get_addr_1(inet_prefix *dst, const char *arg, int family);
 extern int get_prefix_1(inet_prefix *dst, char *arg, int family);
 extern int get_addr(inet_prefix *dst, const char *arg, int family);
 extern int get_prefix(inet_prefix *dst, char *arg, int family);
+extern int mask2bits(__u32 netmask);
 
 extern int get_integer(int *val, const char *arg, int base);
 extern int get_unsigned(unsigned *val, const char *arg, int base);
diff --git a/lib/utils.c b/lib/utils.c
index 84948513..d99deacd 100644
--- a/lib/utils.c
+++ b/lib/utils.c
@@ -47,27 +47,18 @@ int get_integer(int *val, const char *arg, int base)
 	return 0;
 }
 
-/* a valid netmask must be 2^n - 1 */
-static int is_valid_netmask(const inet_prefix *addr)
-{
-        uint32_t host;
-
-        if (addr->family != AF_INET)
-                return 0;
-
-        host = ~ntohl(addr->data[0]);
-
-        return (host & (host + 1)) == 0;
-}
-
-static unsigned cidr(const inet_prefix *addr)
+int mask2bits(__u32 netmask)
 {
 	unsigned bits = 0;
-	u_int32_t mask;
+	__u32 mask = ntohl(netmask);
+	__u32 host = ~mask;
 
-	for (mask = ntohl(addr->data[0]); mask; mask <<= 1)
+	/* a valid netmask must be 2^n - 1 */
+	if ((host & (host + 1)) != 0)
+		return -1;
+
+	for (; mask; mask <<= 1)
 		++bits;
-
 	return bits;
 }
 
@@ -79,11 +70,13 @@ static int get_netmask(unsigned *val, const char *arg, int base)
 		return 0;
 
 	/* try coverting dotted quad to CIDR */
-	if (!get_addr_1(&addr, arg, AF_INET)) {
-		if (is_valid_netmask(&addr))
+	if (!get_addr_1(&addr, arg, AF_INET) && addr.family == AF_INET) {
+		int b = mask2bits(addr.data[0]);
+		
+		if (b >= 0) {
+			*val = b;
 			return 0;
-
-	        *val = cidr(&addr);
+		}
 	}
 
 	return -1;
diff --git a/tc/f_u32.c b/tc/f_u32.c
index 1ac671b3..91f2838b 100644
--- a/tc/f_u32.c
+++ b/tc/f_u32.c
@@ -473,7 +473,7 @@ done:
 	*argv_p = argv;
 	return res;
 }
-
+				
 static int parse_ip6(int *argc_p, char ***argv_p, struct tc_u32_sel *sel)
 {
 	int res = -1;
@@ -564,6 +564,7 @@ done:
 	return res;
 }
 
+
 static int parse_icmp(int *argc_p, char ***argv_p, struct tc_u32_sel *sel)
 {
 	int res = -1;
@@ -771,7 +772,47 @@ static int parse_hashkey(int *argc_p, char ***argv_p, struct tc_u32_sel *sel)
 	return 0;
 }
 
-static int u32_parse_opt(struct filter_util *qu, char *handle, int argc, char **argv, struct nlmsghdr *n)
+static void show_key(FILE *f, const struct tc_u32_key *key)
+{
+	char abuf[256];
+
+	if (show_raw)
+		goto raw;
+
+	switch (key->off) {
+	case 12:
+	case 16: {
+			int bits = mask2bits(key->mask);
+			if (bits >= 0) {
+				fprintf(f, "\n  %s %s/%d\n", 
+					key->off == 12 ? "src" : "dst",
+					inet_ntop(AF_INET, &key->val, abuf, sizeof(abuf)),
+					bits);
+				return;
+			}
+		}
+		break;
+
+	case 20:
+	case 22:
+		if (key->mask == ntohl(0xffff)) {
+			fprintf(f, "\n  %s %u\n", 
+				key->off == 20 ? "sport" : "dport",
+				(unsigned short) ntohl(key->val));
+			return;
+		}
+	}
+
+raw:
+	fprintf(f, "\n  match %08x/%08x at %s%d",
+		(unsigned int)ntohl(key->val),
+		(unsigned int)ntohl(key->mask),
+		key->offmask ? "nexthdr+" : "",
+		key->off);
+}
+
+static int u32_parse_opt(struct filter_util *qu, char *handle, 
+			 int argc, char **argv, struct nlmsghdr *n)
 {
 	struct {
 		struct tc_u32_sel sel;
@@ -966,7 +1007,8 @@ static int u32_parse_opt(struct filter_util *qu, char *handle, int argc, char **
 	return 0;
 }
 
-static int u32_print_opt(struct filter_util *qu, FILE *f, struct rtattr *opt, __u32 handle)
+static int u32_print_opt(struct filter_util *qu, FILE *f, struct rtattr *opt,
+			 __u32 handle)
 {
 	struct rtattr *tb[TCA_U32_MAX+1];
 	struct tc_u32_sel *sel = NULL;
@@ -1037,17 +1079,12 @@ static int u32_print_opt(struct filter_util *qu, FILE *f, struct rtattr *opt, __
 	}
 
 	if (sel) {
-		int i;
-		struct tc_u32_key *key = sel->keys;
 		if (sel->nkeys) {
-			for (i=0; i<sel->nkeys; i++, key++) {
-				fprintf(f, "\n  match %08x/%08x at %s%d",
-					(unsigned int)ntohl(key->val),
-					(unsigned int)ntohl(key->mask),
-					key->offmask ? "nexthdr+" : "",
-					key->off);
+			int i;
+			for (i=0; i<sel->nkeys; i++) {
+				show_key(f, sel->keys + i);
 				if (show_stats && NULL != pf)
-					fprintf(f, " (success %lld ) ",
+					fprintf(f, " (success %llu ) ",
 						(unsigned long long) pf->kcnts[i]);
 			}
 		}

From 2188a84d1c43ccf2d0b75829898f203891d4a7e5 Mon Sep 17 00:00:00 2001
From: Stephen Hemminger <stephen.hemminger@vyatta.com>
Date: Mon, 31 Dec 2007 10:30:40 -0800
Subject: [PATCH 10/15] snapshot 31 Dec 2007

Signed-off-by: Stephen Hemminger <stephen.hemminger@vyatta.com>
---
 include/SNAPSHOT.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/SNAPSHOT.h b/include/SNAPSHOT.h
index cdeb2067..56a58ac0 100644
--- a/include/SNAPSHOT.h
+++ b/include/SNAPSHOT.h
@@ -1 +1 @@
-static const char SNAPSHOT[] = "071221";
+static const char SNAPSHOT[] = "071231";

From 77aa4d03a7e54dc1cb40f4497a8882fb0c7deb48 Mon Sep 17 00:00:00 2001
From: Stephen Hemminger <stephen.hemminger@vyatta.com>
Date: Mon, 31 Dec 2007 10:41:18 -0800
Subject: [PATCH 11/15] Use netinet/tcp.h (with correction) rather than kernel
 headers

Fix the userspace header file rather than importing more
kernel headers.

Signed-off-by: Stephen Hemminger <stephen.hemminger@vyatta.com>
---
 include/linux/tcp.h      | 174 ---------------------------------------
 include/net/tcp_states.h |  50 -----------
 misc/ss.c                |   3 +-
 3 files changed, 1 insertion(+), 226 deletions(-)
 delete mode 100644 include/linux/tcp.h
 delete mode 100644 include/net/tcp_states.h

diff --git a/include/linux/tcp.h b/include/linux/tcp.h
deleted file mode 100644
index dd2985e7..00000000
--- a/include/linux/tcp.h
+++ /dev/null
@@ -1,174 +0,0 @@
-/*
- * INET		An implementation of the TCP/IP protocol suite for the LINUX
- *		operating system.  INET is implemented using the  BSD Socket
- *		interface as the means of communication with the user level.
- *
- *		Definitions for the TCP protocol.
- *
- * Version:	@(#)tcp.h	1.0.2	04/28/93
- *
- * Author:	Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
- *
- *		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.
- */
-#ifndef _LINUX_TCP_H
-#define _LINUX_TCP_H
-
-#include <linux/types.h>
-#include <asm/byteorder.h>
-#include <linux/socket.h>
-
-struct tcphdr {
-	__be16	source;
-	__be16	dest;
-	__be32	seq;
-	__be32	ack_seq;
-#if defined(__LITTLE_ENDIAN_BITFIELD)
-	__u16	res1:4,
-		doff:4,
-		fin:1,
-		syn:1,
-		rst:1,
-		psh:1,
-		ack:1,
-		urg:1,
-		ece:1,
-		cwr:1;
-#elif defined(__BIG_ENDIAN_BITFIELD)
-	__u16	doff:4,
-		res1:4,
-		cwr:1,
-		ece:1,
-		urg:1,
-		ack:1,
-		psh:1,
-		rst:1,
-		syn:1,
-		fin:1;
-#else
-#error	"Adjust your <asm/byteorder.h> defines"
-#endif	
-	__be16	window;
-	__sum16	check;
-	__be16	urg_ptr;
-};
-
-/*
- *	The union cast uses a gcc extension to avoid aliasing problems
- *  (union is compatible to any of its members)
- *  This means this part of the code is -fstrict-aliasing safe now.
- */
-union tcp_word_hdr { 
-	struct tcphdr hdr;
-	__be32 		  words[5];
-}; 
-
-#define tcp_flag_word(tp) ( ((union tcp_word_hdr *)(tp))->words [3]) 
-
-enum { 
-	TCP_FLAG_CWR = __constant_htonl(0x00800000), 
-	TCP_FLAG_ECE = __constant_htonl(0x00400000), 
-	TCP_FLAG_URG = __constant_htonl(0x00200000), 
-	TCP_FLAG_ACK = __constant_htonl(0x00100000), 
-	TCP_FLAG_PSH = __constant_htonl(0x00080000), 
-	TCP_FLAG_RST = __constant_htonl(0x00040000), 
-	TCP_FLAG_SYN = __constant_htonl(0x00020000), 
-	TCP_FLAG_FIN = __constant_htonl(0x00010000),
-	TCP_RESERVED_BITS = __constant_htonl(0x0F000000),
-	TCP_DATA_OFFSET = __constant_htonl(0xF0000000)
-}; 
-
-/* TCP socket options */
-#define TCP_NODELAY		1	/* Turn off Nagle's algorithm. */
-#define TCP_MAXSEG		2	/* Limit MSS */
-#define TCP_CORK		3	/* Never send partially complete segments */
-#define TCP_KEEPIDLE		4	/* Start keeplives after this period */
-#define TCP_KEEPINTVL		5	/* Interval between keepalives */
-#define TCP_KEEPCNT		6	/* Number of keepalives before death */
-#define TCP_SYNCNT		7	/* Number of SYN retransmits */
-#define TCP_LINGER2		8	/* Life time of orphaned FIN-WAIT-2 state */
-#define TCP_DEFER_ACCEPT	9	/* Wake up listener only when data arrive */
-#define TCP_WINDOW_CLAMP	10	/* Bound advertised window */
-#define TCP_INFO		11	/* Information about this connection. */
-#define TCP_QUICKACK		12	/* Block/reenable quick acks */
-#define TCP_CONGESTION		13	/* Congestion control algorithm */
-#define TCP_MD5SIG		14	/* TCP MD5 Signature (RFC2385) */
-
-#define TCPI_OPT_TIMESTAMPS	1
-#define TCPI_OPT_SACK		2
-#define TCPI_OPT_WSCALE		4
-#define TCPI_OPT_ECN		8
-
-enum tcp_ca_state
-{
-	TCP_CA_Open = 0,
-#define TCPF_CA_Open	(1<<TCP_CA_Open)
-	TCP_CA_Disorder = 1,
-#define TCPF_CA_Disorder (1<<TCP_CA_Disorder)
-	TCP_CA_CWR = 2,
-#define TCPF_CA_CWR	(1<<TCP_CA_CWR)
-	TCP_CA_Recovery = 3,
-#define TCPF_CA_Recovery (1<<TCP_CA_Recovery)
-	TCP_CA_Loss = 4
-#define TCPF_CA_Loss	(1<<TCP_CA_Loss)
-};
-
-struct tcp_info
-{
-	__u8	tcpi_state;
-	__u8	tcpi_ca_state;
-	__u8	tcpi_retransmits;
-	__u8	tcpi_probes;
-	__u8	tcpi_backoff;
-	__u8	tcpi_options;
-	__u8	tcpi_snd_wscale : 4, tcpi_rcv_wscale : 4;
-
-	__u32	tcpi_rto;
-	__u32	tcpi_ato;
-	__u32	tcpi_snd_mss;
-	__u32	tcpi_rcv_mss;
-
-	__u32	tcpi_unacked;
-	__u32	tcpi_sacked;
-	__u32	tcpi_lost;
-	__u32	tcpi_retrans;
-	__u32	tcpi_fackets;
-
-	/* Times. */
-	__u32	tcpi_last_data_sent;
-	__u32	tcpi_last_ack_sent;     /* Not remembered, sorry. */
-	__u32	tcpi_last_data_recv;
-	__u32	tcpi_last_ack_recv;
-
-	/* Metrics. */
-	__u32	tcpi_pmtu;
-	__u32	tcpi_rcv_ssthresh;
-	__u32	tcpi_rtt;
-	__u32	tcpi_rttvar;
-	__u32	tcpi_snd_ssthresh;
-	__u32	tcpi_snd_cwnd;
-	__u32	tcpi_advmss;
-	__u32	tcpi_reordering;
-
-	__u32	tcpi_rcv_rtt;
-	__u32	tcpi_rcv_space;
-
-	__u32	tcpi_total_retrans;
-};
-
-/* for TCP_MD5SIG socket option */
-#define TCP_MD5SIG_MAXKEYLEN	80
-
-struct tcp_md5sig {
-	struct __kernel_sockaddr_storage tcpm_addr;	/* address associated */
-	__u16	__tcpm_pad1;				/* zero */
-	__u16	tcpm_keylen;				/* key length */
-	__u32	__tcpm_pad2;				/* zero */
-	__u8	tcpm_key[TCP_MD5SIG_MAXKEYLEN];		/* key (binary) */
-};
-
-
-#endif	/* _LINUX_TCP_H */
diff --git a/include/net/tcp_states.h b/include/net/tcp_states.h
deleted file mode 100644
index b0b64598..00000000
--- a/include/net/tcp_states.h
+++ /dev/null
@@ -1,50 +0,0 @@
-/*
- * INET		An implementation of the TCP/IP protocol suite for the LINUX
- *		operating system.  INET is implemented using the  BSD Socket
- *		interface as the means of communication with the user level.
- *
- *		Definitions for the TCP protocol sk_state field.
- *
- *		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.
- */
-#ifndef _LINUX_TCP_STATES_H
-#define _LINUX_TCP_STATES_H
-
-enum {
-	TCP_ESTABLISHED = 1,
-	TCP_SYN_SENT,
-	TCP_SYN_RECV,
-	TCP_FIN_WAIT1,
-	TCP_FIN_WAIT2,
-	TCP_TIME_WAIT,
-	TCP_CLOSE,
-	TCP_CLOSE_WAIT,
-	TCP_LAST_ACK,
-	TCP_LISTEN,
-	TCP_CLOSING,	/* Now a valid state */
-
-	TCP_MAX_STATES	/* Leave at the end! */
-};
-
-#define TCP_STATE_MASK	0xF
-
-#define TCP_ACTION_FIN	(1 << 7)
-
-enum {
-	TCPF_ESTABLISHED = (1 << 1),
-	TCPF_SYN_SENT	 = (1 << 2),
-	TCPF_SYN_RECV	 = (1 << 3),
-	TCPF_FIN_WAIT1	 = (1 << 4),
-	TCPF_FIN_WAIT2	 = (1 << 5),
-	TCPF_TIME_WAIT	 = (1 << 6),
-	TCPF_CLOSE	 = (1 << 7),
-	TCPF_CLOSE_WAIT	 = (1 << 8),
-	TCPF_LAST_ACK	 = (1 << 9),
-	TCPF_LISTEN	 = (1 << 10),
-	TCPF_CLOSING	 = (1 << 11) 
-};
-
-#endif	/* _LINUX_TCP_STATES_H */
diff --git a/misc/ss.c b/misc/ss.c
index 5d14f132..53558515 100644
--- a/misc/ss.c
+++ b/misc/ss.c
@@ -33,9 +33,8 @@
 #include "libnetlink.h"
 #include "SNAPSHOT.h"
 
+#include <netinet/tcp.h>
 #include <linux/inet_diag.h>
-#include <linux/tcp.h>
-#include <net/tcp_states.h>
 
 int resolve_hosts = 0;
 int resolve_services = 1;

From bccd014b866daa21002f7ac682cee57a9fe003e3 Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer <hawk@comx.dk>
Date: Tue, 11 Sep 2007 16:59:58 +0200
Subject: [PATCH 12/15] Overhead calculation is now done in the kernel.

The only current user is HTB. HTB overhead argument is now passed on
to the kernel (in the struct tc_ratespec). Also correct the data
types.

Signed-off-by: Jesper Dangaard Brouer <hawk@comx.dk>
Signed-off-by: Stephen Hemminger <stephen.hemminger@vyatta.com>
---
 tc/q_htb.c   | 17 ++++++++++-------
 tc/tc_core.c |  4 ----
 2 files changed, 10 insertions(+), 11 deletions(-)

diff --git a/tc/q_htb.c b/tc/q_htb.c
index 53e3f787..310d36d1 100644
--- a/tc/q_htb.c
+++ b/tc/q_htb.c
@@ -107,8 +107,9 @@ static int htb_parse_class_opt(struct qdisc_util *qu, int argc, char **argv, str
 	__u32 rtab[256],ctab[256];
 	unsigned buffer=0,cbuffer=0;
 	int cell_log=-1,ccell_log = -1;
-	unsigned mtu, mpu;
-	unsigned char mpu8 = 0, overhead = 0;
+	unsigned mtu;
+	unsigned short mpu = 0;
+	unsigned short overhead = 0;
 	struct rtattr *tail;
 
 	memset(&opt, 0, sizeof(opt)); mtu = 1600; /* eth packet len */
@@ -127,12 +128,12 @@ static int htb_parse_class_opt(struct qdisc_util *qu, int argc, char **argv, str
 			}
 		} else if (matches(*argv, "mpu") == 0) {
 			NEXT_ARG();
-			if (get_u8(&mpu8, *argv, 10)) {
+			if (get_u16(&mpu, *argv, 10)) {
 				explain1("mpu"); return -1;
 			}
 		} else if (matches(*argv, "overhead") == 0) {
 			NEXT_ARG();
-			if (get_u8(&overhead, *argv, 10)) {
+			if (get_u16(&overhead, *argv, 10)) {
 				explain1("overhead"); return -1;
 			}
 		} else if (matches(*argv, "quantum") == 0) {
@@ -206,9 +207,11 @@ static int htb_parse_class_opt(struct qdisc_util *qu, int argc, char **argv, str
 	if (!buffer) buffer = opt.rate.rate / get_hz() + mtu;
 	if (!cbuffer) cbuffer = opt.ceil.rate / get_hz() + mtu;
 
-/* encode overhead and mpu, 8 bits each, into lower 16 bits */
-	mpu = (unsigned)mpu8 | (unsigned)overhead << 8;
-	opt.ceil.mpu = mpu; opt.rate.mpu = mpu;
+	opt.ceil.overhead = overhead;
+	opt.rate.overhead = overhead;
+
+	opt.ceil.mpu = mpu;
+	opt.rate.mpu = mpu;
 
 	if ((cell_log = tc_calc_rtable(opt.rate.rate, rtab, cell_log, mtu, mpu)) < 0) {
 		fprintf(stderr, "htb: failed to calculate rate table.\n");
diff --git a/tc/tc_core.c b/tc/tc_core.c
index 1365e081..3908c886 100644
--- a/tc/tc_core.c
+++ b/tc/tc_core.c
@@ -73,8 +73,6 @@ int tc_calc_rtable(unsigned bps, __u32 *rtab, int cell_log, unsigned mtu,
 		   unsigned mpu)
 {
 	int i;
-	unsigned overhead = (mpu >> 8) & 0xFF;
-	mpu = mpu & 0xFF;
 
 	if (mtu == 0)
 		mtu = 2047;
@@ -86,8 +84,6 @@ int tc_calc_rtable(unsigned bps, __u32 *rtab, int cell_log, unsigned mtu,
 	}
 	for (i=0; i<256; i++) {
 		unsigned sz = (i<<cell_log);
-		if (overhead)
-			sz += overhead;
 		if (sz < mpu)
 			sz = mpu;
 		rtab[i] = tc_calc_xmittime(bps, sz);

From d5f46f9cc3856af532e852ef29fd7ddfd141faf0 Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer <hawk@comx.dk>
Date: Wed, 5 Sep 2007 10:47:47 +0200
Subject: [PATCH 13/15] Cleanup: tc_calc_rtable().

Change tc_calc_rtable() to take a tc_ratespec struct as an
argument. (cell_log still needs to be passed on as a parameter,
because -1 indicate that the cell_log needs to be computed by the
function.).

Signed-off-by: Jesper Dangaard Brouer <hawk@comx.dk>
Signed-off-by: Stephen Hemminger <stephen.hemminger@vyatta.com>
---
 tc/m_police.c | 10 ++++------
 tc/q_cbq.c    | 10 ++++------
 tc/q_htb.c    |  6 ++----
 tc/q_tbf.c    | 11 +++++------
 tc/tc_core.c  |  6 ++++--
 tc/tc_core.h  |  2 +-
 6 files changed, 20 insertions(+), 25 deletions(-)

diff --git a/tc/m_police.c b/tc/m_police.c
index 5d2528b8..acdfd223 100644
--- a/tc/m_police.c
+++ b/tc/m_police.c
@@ -263,22 +263,20 @@ int act_parse_police(struct action_util *a,int *argc_p, char ***argv_p, int tca_
 	}
 
 	if (p.rate.rate) {
-		if ((Rcell_log = tc_calc_rtable(p.rate.rate, rtab, Rcell_log, mtu, mpu)) < 0) {
+		p.rate.mpu = mpu;
+		if (tc_calc_rtable(&p.rate, rtab, Rcell_log, mtu) < 0) {
 			fprintf(stderr, "TBF: failed to calculate rate table.\n");
 			return -1;
 		}
 		p.burst = tc_calc_xmittime(p.rate.rate, buffer);
-		p.rate.cell_log = Rcell_log;
-		p.rate.mpu = mpu;
 	}
 	p.mtu = mtu;
 	if (p.peakrate.rate) {
-		if ((Pcell_log = tc_calc_rtable(p.peakrate.rate, ptab, Pcell_log, mtu, mpu)) < 0) {
+		p.peakrate.mpu = mpu;
+		if (tc_calc_rtable(&p.peakrate, ptab, Pcell_log, mtu) < 0) {
 			fprintf(stderr, "POLICE: failed to calculate peak rate table.\n");
 			return -1;
 		}
-		p.peakrate.cell_log = Pcell_log;
-		p.peakrate.mpu = mpu;
 	}
 
 	tail = NLMSG_TAIL(n);
diff --git a/tc/q_cbq.c b/tc/q_cbq.c
index f2b4ce87..df98312e 100644
--- a/tc/q_cbq.c
+++ b/tc/q_cbq.c
@@ -137,12 +137,11 @@ static int cbq_parse_opt(struct qdisc_util *qu, int argc, char **argv, struct nl
 	if (allot < (avpkt*3)/2)
 		allot = (avpkt*3)/2;
 
-	if ((cell_log = tc_calc_rtable(r.rate, rtab, cell_log, allot, mpu)) < 0) {
+	r.mpu = mpu;
+	if (tc_calc_rtable(&r, rtab, cell_log, allot) < 0) {
 		fprintf(stderr, "CBQ: failed to calculate rate table.\n");
 		return -1;
 	}
-	r.cell_log = cell_log;
-	r.mpu = mpu;
 
 	if (ewma_log < 0)
 		ewma_log = TC_CBQ_DEF_EWMA;
@@ -336,12 +335,11 @@ static int cbq_parse_class_opt(struct qdisc_util *qu, int argc, char **argv, str
 		unsigned pktsize = wrr.allot;
 		if (wrr.allot < (lss.avpkt*3)/2)
 			wrr.allot = (lss.avpkt*3)/2;
-		if ((cell_log = tc_calc_rtable(r.rate, rtab, cell_log, pktsize, mpu)) < 0) {
+		r.mpu = mpu;
+		if (tc_calc_rtable(&r, rtab, cell_log, pktsize) < 0) {
 			fprintf(stderr, "CBQ: failed to calculate rate table.\n");
 			return -1;
 		}
-		r.cell_log = cell_log;
-		r.mpu = mpu;
 	}
 	if (ewma_log < 0)
 		ewma_log = TC_CBQ_DEF_EWMA;
diff --git a/tc/q_htb.c b/tc/q_htb.c
index 310d36d1..e24ad6de 100644
--- a/tc/q_htb.c
+++ b/tc/q_htb.c
@@ -213,19 +213,17 @@ static int htb_parse_class_opt(struct qdisc_util *qu, int argc, char **argv, str
 	opt.ceil.mpu = mpu;
 	opt.rate.mpu = mpu;
 
-	if ((cell_log = tc_calc_rtable(opt.rate.rate, rtab, cell_log, mtu, mpu)) < 0) {
+	if (tc_calc_rtable(&opt.rate, rtab, cell_log, mtu) < 0) {
 		fprintf(stderr, "htb: failed to calculate rate table.\n");
 		return -1;
 	}
 	opt.buffer = tc_calc_xmittime(opt.rate.rate, buffer);
-	opt.rate.cell_log = cell_log;
 
-	if ((ccell_log = tc_calc_rtable(opt.ceil.rate, ctab, cell_log, mtu, mpu)) < 0) {
+	if (tc_calc_rtable(&opt.ceil, ctab, ccell_log, mtu) < 0) {
 		fprintf(stderr, "htb: failed to calculate ceil rate table.\n");
 		return -1;
 	}
 	opt.cbuffer = tc_calc_xmittime(opt.ceil.rate, cbuffer);
-	opt.ceil.cell_log = ccell_log;
 
 	tail = NLMSG_TAIL(n);
 	addattr_l(n, 1024, TCA_OPTIONS, NULL, 0);
diff --git a/tc/q_tbf.c b/tc/q_tbf.c
index 1fc05f49..c7b4f0f4 100644
--- a/tc/q_tbf.c
+++ b/tc/q_tbf.c
@@ -170,21 +170,20 @@ static int tbf_parse_opt(struct qdisc_util *qu, int argc, char **argv, struct nl
 		opt.limit = lim;
 	}
 
-	if ((Rcell_log = tc_calc_rtable(opt.rate.rate, rtab, Rcell_log, mtu, mpu)) < 0) {
+	opt.rate.mpu = mpu;
+	if (tc_calc_rtable(&opt.rate, rtab, Rcell_log, mtu) < 0) {
 		fprintf(stderr, "TBF: failed to calculate rate table.\n");
 		return -1;
 	}
 	opt.buffer = tc_calc_xmittime(opt.rate.rate, buffer);
-	opt.rate.cell_log = Rcell_log;
-	opt.rate.mpu = mpu;
+
 	if (opt.peakrate.rate) {
-		if ((Pcell_log = tc_calc_rtable(opt.peakrate.rate, ptab, Pcell_log, mtu, mpu)) < 0) {
+		opt.peakrate.mpu = mpu;
+		if (tc_calc_rtable(&opt.peakrate, ptab, Pcell_log, mtu) < 0) {
 			fprintf(stderr, "TBF: failed to calculate peak rate table.\n");
 			return -1;
 		}
 		opt.mtu = tc_calc_xmittime(opt.peakrate.rate, mtu);
-		opt.peakrate.cell_log = Pcell_log;
-		opt.peakrate.mpu = mpu;
 	}
 
 	tail = NLMSG_TAIL(n);
diff --git a/tc/tc_core.c b/tc/tc_core.c
index 3908c886..b5e362fa 100644
--- a/tc/tc_core.c
+++ b/tc/tc_core.c
@@ -69,10 +69,11 @@ unsigned tc_calc_xmitsize(unsigned rate, unsigned ticks)
    rtab[pkt_len>>cell_log] = pkt_xmit_time
  */
 
-int tc_calc_rtable(unsigned bps, __u32 *rtab, int cell_log, unsigned mtu,
-		   unsigned mpu)
+int tc_calc_rtable(struct tc_ratespec *r, __u32 *rtab, int cell_log, unsigned mtu)
 {
 	int i;
+	unsigned bps = r->rate;
+	unsigned mpu = r->mpu;
 
 	if (mtu == 0)
 		mtu = 2047;
@@ -88,6 +89,7 @@ int tc_calc_rtable(unsigned bps, __u32 *rtab, int cell_log, unsigned mtu,
 			sz = mpu;
 		rtab[i] = tc_calc_xmittime(bps, sz);
 	}
+	r->cell_log=cell_log;
 	return cell_log;
 }
 
diff --git a/tc/tc_core.h b/tc/tc_core.h
index 3a0ed7cc..080a0cda 100644
--- a/tc/tc_core.h
+++ b/tc/tc_core.h
@@ -13,7 +13,7 @@ unsigned tc_core_time2ktime(unsigned time);
 unsigned tc_core_ktime2time(unsigned ktime);
 unsigned tc_calc_xmittime(unsigned rate, unsigned size);
 unsigned tc_calc_xmitsize(unsigned rate, unsigned ticks);
-int tc_calc_rtable(unsigned bps, __u32 *rtab, int cell_log, unsigned mtu, unsigned mpu);
+int tc_calc_rtable(struct tc_ratespec *r, __u32 *rtab, int cell_log, unsigned mtu);
 
 int tc_setup_estimator(unsigned A, unsigned time_const, struct tc_estimator *est);
 

From eeee367d91c4004c9f75749b5b09e21fa9244b51 Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer <hawk@comx.dk>
Date: Wed, 5 Sep 2007 15:24:51 +0200
Subject: [PATCH 14/15] Change the rate table calc of transmit cost to use
 upper bound value.

Patrick McHardy, Cite: 'its better to overestimate than underestimate
to stay in control of the queue'.

Illustrating the rate table array:
 Legend description
   rtab[x]   : Array index x of rtab[x]
   xmit_sz   : Transmit size contained in rtab[x] (normally transmit time)
   maps[a-b] : Packet sizes from a to b, will map into rtab[x]

Current/old rate table mapping (cell_log:3):
 rtab[0]:=xmit_sz:0  maps[0-7]
 rtab[1]:=xmit_sz:8  maps[8-15]
 rtab[2]:=xmit_sz:16 maps[16-23]
 rtab[3]:=xmit_sz:24 maps[24-31]
 rtab[4]:=xmit_sz:32 maps[32-39]
 rtab[5]:=xmit_sz:40 maps[40-47]
 rtab[6]:=xmit_sz:48 maps[48-55]

New rate table mapping, with kernel cell_align support.
 rtab[0]:=xmit_sz:8  maps[0-8]
 rtab[1]:=xmit_sz:16 maps[9-16]
 rtab[2]:=xmit_sz:24 maps[17-24]
 rtab[3]:=xmit_sz:32 maps[25-32]
 rtab[4]:=xmit_sz:40 maps[33-40]
 rtab[5]:=xmit_sz:48 maps[41-48]
 rtab[6]:=xmit_sz:56 maps[49-56]

New TC util on a kernel WITHOUT support for cell_align
 rtab[0]:=xmit_sz:8 maps[0-7]
 rtab[1]:=xmit_sz:16 maps[8-15]
 rtab[2]:=xmit_sz:24 maps[16-23]
 rtab[3]:=xmit_sz:32 maps[24-31]
 rtab[4]:=xmit_sz:40 maps[32-39]
 rtab[5]:=xmit_sz:48 maps[40-47]
 rtab[6]:=xmit_sz:56 maps[48-55]

Signed-off-by: Jesper Dangaard Brouer <hawk@comx.dk>
Signed-off-by: Stephen Hemminger <stephen.hemminger@vyatta.com>
---
 tc/tc_core.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/tc/tc_core.c b/tc/tc_core.c
index b5e362fa..9ae4d8e5 100644
--- a/tc/tc_core.c
+++ b/tc/tc_core.c
@@ -84,11 +84,12 @@ int tc_calc_rtable(struct tc_ratespec *r, __u32 *rtab, int cell_log, unsigned mt
 			cell_log++;
 	}
 	for (i=0; i<256; i++) {
-		unsigned sz = (i<<cell_log);
+		unsigned sz = ((i+1)<<cell_log);
 		if (sz < mpu)
 			sz = mpu;
 		rtab[i] = tc_calc_xmittime(bps, sz);
 	}
+	r->cell_align=-1; // Due to the sz calc
 	r->cell_log=cell_log;
 	return cell_log;
 }

From 53c017880b311d7d68926109d4248c900286f6b7 Mon Sep 17 00:00:00 2001
From: Denys Fedoryshchenko <nuclearcat@nuclearcat.com>
Date: Mon, 24 Dec 2007 11:51:11 -0500
Subject: [PATCH 15/15] iptables compatiablity

New iptables 1.4.0 has some library names changed from libipt to libxt.
It is prefferable also to open libxt_ first, as newer "style".

Signed-off-by: Denys Fedoryshchenko <nuclearcat@nuclearcat.com>
Signed-off-by: Jamal Hadi Salim <hadi@cyberus.ca>
Signed-off-by: Stephen Hemminger <stephen.hemminger@vyatta.com>
---
 tc/m_ipt.c | 24 ++++++++++++++++++++++--
 1 file changed, 22 insertions(+), 2 deletions(-)

diff --git a/tc/m_ipt.c b/tc/m_ipt.c
index acbb8d2d..f2a9305d 100644
--- a/tc/m_ipt.c
+++ b/tc/m_ipt.c
@@ -68,6 +68,13 @@ register_target(struct iptables_target *me)
 
 }
 
+void
+xtables_register_target(struct iptables_target *me)
+{
+	me->next = t_list;
+	t_list = me;
+}
+
 void
 exit_tryhelp(int status)
 {
@@ -248,11 +255,24 @@ get_target_name(const char *name)
 		}
 	}
 
-	sprintf(path,  "%s/libipt_%s.so",lib_dir, new_name);
+	/* try libxt_xx first */
+	sprintf(path, "%s/libxt_%s.so", lib_dir, new_name);
 	handle = dlopen(path, RTLD_LAZY);
 	if (!handle) {
-		sprintf(path, lib_dir, "/libipt_%s.so", lname);
+		/* try libipt_xx next */
+		sprintf(path, "%s/libipt_%s.so", lib_dir, new_name);
 		handle = dlopen(path, RTLD_LAZY);
+
+		if (!handle) {
+			sprintf(path, "%s/libxt_%s.so", lib_dir , lname);
+			handle = dlopen(path, RTLD_LAZY);
+		}
+
+		if (!handle) {
+			sprintf(path, "%s/libipt_%s.so", lib_dir , lname);
+			handle = dlopen(path, RTLD_LAZY);
+		}
+		/* ok, lets give up .. */
 		if (!handle) {
 			fputs(dlerror(), stderr);
 			printf("\n");