Netem support for reorder

Update include files and add support for TCP_CONG

ChangeLog

+2005-06-22  Stephen Hemminger  <shemminger@dxpl.pdx.osdl.net>
+
+	* Update include files to 2.6.12
+	* Add ss support for TCP_CONG
+
 2005-06-13  Steven Whitehouse <steve@chygwyn.com>
 
 	* Decnet doc's update

include/linux/pkt_sched.h

@@ -427,6 +427,7 @@ enum
 	TCA_NETEM_UNSPEC,
 	TCA_NETEM_CORR,
 	TCA_NETEM_DELAY_DIST,
+	TCA_NETEM_REORDER,
 	__TCA_NETEM_MAX,
 };
 
@@ -437,7 +438,7 @@ struct tc_netem_qopt
 	__u32	latency;	/* added delay (us) */
 	__u32   limit;		/* fifo limit (packets) */
 	__u32	loss;		/* random packet loss (0=none ~0=100%) */
-	__u32	gap;		/* re-ordering gap (0 for delay all) */
+	__u32	gap;		/* re-ordering gap (0 for none) */
 	__u32   duplicate;	/* random packet dup  (0=none ~0=100%) */
 	__u32	jitter;		/* random jitter in latency (us) */
 };
@@ -449,6 +450,12 @@ struct tc_netem_corr
 	__u32	dup_corr;	/* duplicate correlation  */
 };
 
+struct tc_netem_reorder
+{
+	__u32	probability;
+	__u32	correlation;
+};
+
 #define NETEM_DIST_SCALE	8192
 
 #endif

include/linux/rtnetlink.h

@@ -89,10 +89,21 @@ enum {
 	RTM_GETANYCAST	= 62,
 #define RTM_GETANYCAST	RTM_GETANYCAST
 
-	RTM_MAX,
-#define RTM_MAX		RTM_MAX
+	RTM_NEWNEIGHTBL	= 64,
+#define RTM_NEWNEIGHTBL	RTM_NEWNEIGHTBL
+	RTM_GETNEIGHTBL	= 66,
+#define RTM_GETNEIGHTBL	RTM_GETNEIGHTBL
+	RTM_SETNEIGHTBL,
+#define RTM_SETNEIGHTBL	RTM_SETNEIGHTBL
+
+	__RTM_MAX,
+#define RTM_MAX		(((__RTM_MAX + 3) & ~3) - 1)
 };
 
+#define RTM_NR_MSGTYPES	(RTM_MAX + 1 - RTM_BASE)
+#define RTM_NR_FAMILIES	(RTM_NR_MSGTYPES >> 2)
+#define RTM_FAM(cmd)	(((cmd) - RTM_BASE) >> 2)
+
 /* 
    Generic structure for encapsulation of optional route information.
    It is reminiscent of sockaddr, but with sa_family replaced
@@ -398,19 +409,6 @@ enum
 
 #define IFA_MAX (__IFA_MAX - 1)
 
-/*
- * Quirk for IPv4 address deletion to allow exact deletion of equal
- * addresses varying only in prefix length. A explicit exact comparison
- * of the prefix length will only be done if IFA_PREFIX_EXACT_DEL is
- * ORed to ifa_prefixlen.
- *
- * Note: This special treatment is only understood while deleting
- *       addresses and will lead to unexpected behaviour if used
- *       otherwise.
- */
-#define IFA_PREFIX_EXACT_DEL	0x40
-#define IFA_REAL_DEL_PREFIX(l)	((l) & 0x3f)
-
 /* ifa_flags */
 
 #define IFA_F_SECONDARY		0x01
@@ -502,6 +500,106 @@ struct nda_cacheinfo
 	__u32		ndm_refcnt;
 };
 
+
+/*****************************************************************
+ *		Neighbour tables specific messages.
+ *
+ * To retrieve the neighbour tables send RTM_GETNEIGHTBL with the
+ * NLM_F_DUMP flag set. Every neighbour table configuration is
+ * spread over multiple messages to avoid running into message
+ * size limits on systems with many interfaces. The first message
+ * in the sequence transports all not device specific data such as
+ * statistics, configuration, and the default parameter set.
+ * This message is followed by 0..n messages carrying device
+ * specific parameter sets.
+ * Although the ordering should be sufficient, NDTA_NAME can be
+ * used to identify sequences. The initial message can be identified
+ * by checking for NDTA_CONFIG. The device specific messages do
+ * not contain this TLV but have NDTPA_IFINDEX set to the
+ * corresponding interface index.
+ *
+ * To change neighbour table attributes, send RTM_SETNEIGHTBL
+ * with NDTA_NAME set. Changeable attribute include NDTA_THRESH[1-3],
+ * NDTA_GC_INTERVAL, and all TLVs in NDTA_PARMS unless marked
+ * otherwise. Device specific parameter sets can be changed by
+ * setting NDTPA_IFINDEX to the interface index of the corresponding
+ * device.
+ ****/
+
+struct ndt_stats
+{
+	__u64		ndts_allocs;
+	__u64		ndts_destroys;
+	__u64		ndts_hash_grows;
+	__u64		ndts_res_failed;
+	__u64		ndts_lookups;
+	__u64		ndts_hits;
+	__u64		ndts_rcv_probes_mcast;
+	__u64		ndts_rcv_probes_ucast;
+	__u64		ndts_periodic_gc_runs;
+	__u64		ndts_forced_gc_runs;
+};
+
+enum {
+	NDTPA_UNSPEC,
+	NDTPA_IFINDEX,			/* u32, unchangeable */
+	NDTPA_REFCNT,			/* u32, read-only */
+	NDTPA_REACHABLE_TIME,		/* u64, read-only, msecs */
+	NDTPA_BASE_REACHABLE_TIME,	/* u64, msecs */
+	NDTPA_RETRANS_TIME,		/* u64, msecs */
+	NDTPA_GC_STALETIME,		/* u64, msecs */
+	NDTPA_DELAY_PROBE_TIME,		/* u64, msecs */
+	NDTPA_QUEUE_LEN,		/* u32 */
+	NDTPA_APP_PROBES,		/* u32 */
+	NDTPA_UCAST_PROBES,		/* u32 */
+	NDTPA_MCAST_PROBES,		/* u32 */
+	NDTPA_ANYCAST_DELAY,		/* u64, msecs */
+	NDTPA_PROXY_DELAY,		/* u64, msecs */
+	NDTPA_PROXY_QLEN,		/* u32 */
+	NDTPA_LOCKTIME,			/* u64, msecs */
+	__NDTPA_MAX
+};
+#define NDTPA_MAX (__NDTPA_MAX - 1)
+
+struct ndtmsg
+{
+	__u8		ndtm_family;
+	__u8		ndtm_pad1;
+	__u16		ndtm_pad2;
+};
+
+struct ndt_config
+{
+	__u16		ndtc_key_len;
+	__u16		ndtc_entry_size;
+	__u32		ndtc_entries;
+	__u32		ndtc_last_flush;	/* delta to now in msecs */
+	__u32		ndtc_last_rand;		/* delta to now in msecs */
+	__u32		ndtc_hash_rnd;
+	__u32		ndtc_hash_mask;
+	__u32		ndtc_hash_chain_gc;
+	__u32		ndtc_proxy_qlen;
+};
+
+enum {
+	NDTA_UNSPEC,
+	NDTA_NAME,			/* char *, unchangeable */
+	NDTA_THRESH1,			/* u32 */
+	NDTA_THRESH2,			/* u32 */
+	NDTA_THRESH3,			/* u32 */
+	NDTA_CONFIG,			/* struct ndt_config, read-only */
+	NDTA_PARMS,			/* nested TLV NDTPA_* */
+	NDTA_STATS,			/* struct ndt_stats, read-only */
+	NDTA_GC_INTERVAL,		/* u64, msecs */
+	__NDTA_MAX
+};
+#define NDTA_MAX (__NDTA_MAX - 1)
+
+#define NDTA_RTA(r) ((struct rtattr*)(((char*)(r)) + \
+		     NLMSG_ALIGN(sizeof(struct ndtmsg))))
+#define NDTA_PAYLOAD(n) NLMSG_PAYLOAD(n,sizeof(struct ndtmsg))
+
+
 /****
  *		General form of address family dependent message.
  ****/

include/linux/tcp_diag.h

@@ -99,9 +99,10 @@ enum
 	TCPDIAG_MEMINFO,
 	TCPDIAG_INFO,
 	TCPDIAG_VEGASINFO,
+	TCPDIAG_CONG,
 };
 
-#define TCPDIAG_MAX TCPDIAG_VEGASINFO
+#define TCPDIAG_MAX TCPDIAG_CONG
 
 
 /* TCPDIAG_MEM */
@@ -123,5 +124,4 @@ struct tcpvegas_info {
 	__u32	tcpv_minrtt;
 };
 
-
 #endif /* _TCP_DIAG_H_ */

include/linux/xfrm.h

@@ -140,8 +140,11 @@ enum {
 	XFRM_MSG_FLUSHPOLICY,
 #define XFRM_MSG_FLUSHPOLICY XFRM_MSG_FLUSHPOLICY
 
-	XFRM_MSG_MAX
+	__XFRM_MSG_MAX
 };
+#define XFRM_MSG_MAX (__XFRM_MSG_MAX - 1)
+
+#define XFRM_NR_MSGTYPES (XFRM_MSG_MAX + 1 - XFRM_MSG_BASE)
 
 struct xfrm_user_tmpl {
 	struct xfrm_id		id;
@@ -171,6 +174,8 @@ enum xfrm_attr_type_t {
 	XFRMA_ALG_COMP,		/* struct xfrm_algo */
 	XFRMA_ENCAP,		/* struct xfrm_algo + struct xfrm_encap_tmpl */
 	XFRMA_TMPL,		/* 1 or more struct xfrm_user_tmpl */
+	XFRMA_SA,
+	XFRMA_POLICY,
 	__XFRMA_MAX
 
 #define XFRMA_MAX (__XFRMA_MAX - 1)
@@ -254,5 +259,7 @@ struct xfrm_usersa_flush {
 
 #define XFRMGRP_ACQUIRE		1
 #define XFRMGRP_EXPIRE		2
+#define XFRMGRP_SA		4
+#define XFRMGRP_POLICY		8
 
 #endif /* _LINUX_XFRM_H */

misc/ss.c

@@ -1338,6 +1338,9 @@ static void tcp_show_info(const struct nlmsghdr *nlh, struct tcpdiagmsg *r)
 			if (info->tcpi_options & TCPI_OPT_ECN)
 				printf(" ecn");
 		}
+		if (tb[TCPDIAG_CONG])
+			printf("%s", (char *) RTA_DATA(tb[TCPDIAG_CONG]));
+
 		if (info->tcpi_options & TCPI_OPT_WSCALE) 
 			printf(" wscale:%d,%d", info->tcpi_snd_wscale,
 			       info->tcpi_rcv_wscale);
@@ -1358,12 +1361,9 @@ static void tcp_show_info(const struct nlmsghdr *nlh, struct tcpdiagmsg *r)
 			const struct tcpvegas_info *vinfo
 				= RTA_DATA(tb[TCPDIAG_VEGASINFO]);
 
-			if (vinfo->tcpv_enabled)
-				printf(" vegas");
-
-			if (vinfo->tcpv_rtt && 
-			    vinfo->tcpv_rtt != 0x7fffffff)
-			    rtt =  vinfo->tcpv_rtt;
+			if (vinfo->tcpv_enabled && 
+			    vinfo->tcpv_rtt && vinfo->tcpv_rtt != 0x7fffffff)
+				rtt =  vinfo->tcpv_rtt;
 		}
 
 		if (rtt > 0 && info->tcpi_snd_mss && info->tcpi_snd_cwnd) {
@@ -1442,7 +1442,6 @@ int tcp_show_sock(struct nlmsghdr *nlh, struct filter *f)
 	printf("\n");
 
 	return 0;
-
 }
 
 int tcp_show_netlink(struct filter *f, FILE *dump_fp)
@@ -1480,9 +1479,13 @@ int tcp_show_netlink(struct filter *f, FILE *dump_fp)
 	if (show_tcpinfo) {
 		req.r.tcpdiag_ext |= (1<<(TCPDIAG_INFO-1));
 		req.r.tcpdiag_ext |= (1<<(TCPDIAG_VEGASINFO-1));
+		req.r.tcpdiag_ext |= (1<<(TCPDIAG_CONG-1));
 	}
 
-	iov[0] = (struct iovec){ &req, sizeof(req) };
+	iov[0] = (struct iovec){ 
+		.iov_base = &req, 
+		.iov_len = sizeof(req) 
+	};
 	if (f->f) {
 		bclen = ssfilter_bytecompile(f->f, &bc);
 		rta.rta_type = TCPDIAG_REQ_BYTECODE;
@@ -1493,17 +1496,19 @@ int tcp_show_netlink(struct filter *f, FILE *dump_fp)
 	}
 
 	msg = (struct msghdr) {
-		(void*)&nladdr, sizeof(nladdr),
-		iov,	f->f ? 3 : 1,
-		NULL,	0,
-		0
+		.msg_name = (void*)&nladdr, 
+		.msg_namelen = sizeof(nladdr),
+		.msg_iov = iov,	
+		.msg_iovlen = f->f ? 3 : 1,
 	};
 
 	if (sendmsg(fd, &msg, 0) < 0)
 		return -1;
 
-
-	iov[0] = (struct iovec){ buf, sizeof(buf) };
+	iov[0] = (struct iovec){ 
+		.iov_base = buf, 
+		.iov_len = sizeof(buf) 
+	};
 
 	while (1) {
 		int status;

tc/q_netem.c

@@ -29,11 +29,11 @@ static void explain(void)
 {
 	fprintf(stderr, 
 "Usage: ... netem [ limit PACKETS ] \n" \
-"		  [ delay TIME [ JITTER [CORRELATION]]]\n" \
+"                 [ delay TIME [ JITTER [CORRELATION]]]\n" \
+"                 [ distribution {uniform|normal|pareto|paretonormal} ]\n" \
 "                 [ drop PERCENT [CORRELATION]] \n" \
 "                 [ duplicate PERCENT [CORRELATION]]\n" \
-"		  [ distribution {uniform|normal|pareto|paretonormal} ]\n" \
-"                 [ gap PACKETS ]\n");
+"                 [ reorder PRECENT [CORRELATION] [ gap DISTANCE ]]\n");
 }
 
 static void explain1(const char *arg)
@@ -127,11 +127,13 @@ static int netem_parse_opt(struct qdisc_util *qu, int argc, char **argv,
 	struct rtattr *tail;
 	struct tc_netem_qopt opt;
 	struct tc_netem_corr cor;
+	struct tc_netem_reorder reorder;
 	__s16 dist_data[MAXDIST];
 
 	memset(&opt, 0, sizeof(opt));
 	opt.limit = 1000;
 	memset(&cor, 0, sizeof(cor));
+	memset(&reorder, 0, sizeof(reorder));
 
 	while (argc > 0) {
 		if (matches(*argv, "limit") == 0) {
@@ -178,6 +180,19 @@ static int netem_parse_opt(struct qdisc_util *qu, int argc, char **argv,
 					return -1;
 				}
 			}
+		} else if (matches(*argv, "reorder") == 0) {
+			NEXT_ARG();
+			if (get_percent(&reorder.probability, *argv)) {
+				explain1("reorder");
+				return -1;
+			}
+			if (NEXT_IS_NUMBER()) {
+				NEXT_ARG();
+				if (get_percent(&reorder.correlation, *argv)) {
+					explain1("reorder");
+					return -1;
+				}
+			}
 		} else if (matches(*argv, "gap") == 0) {
 			NEXT_ARG();
 			if (get_u32(&opt.gap, *argv, 0)) {
@@ -215,8 +230,27 @@ static int netem_parse_opt(struct qdisc_util *qu, int argc, char **argv,
 
 	tail = NLMSG_TAIL(n);
 
+	if (reorder.probability) {
+		if (opt.latency == 0) {
+			fprintf(stderr, "reordering not possible without specifying some delay\n");
+		}
+		if (opt.gap == 0)
+			opt.gap = 1;
+	} else if (opt.gap > 0) {
+		fprintf(stderr, "gap specified without reorder probability\n");
+		explain();
+		return -1;
+	}
+
+	if (dist_size > 0 && (opt.latency == 0 || opt.jitter == 0)) {
+		fprintf(stderr, "distribution specified but no latency and jitter values\n");
+		explain();
+		return -1;
+	}
+
 	addattr_l(n, 1024, TCA_OPTIONS, &opt, sizeof(opt));
 	addattr_l(n, 1024, TCA_NETEM_CORR, &cor, sizeof(cor));
+	addattr_l(n, 1024, TCA_NETEM_REORDER, &reorder, sizeof(reorder));
 
 	if (dist_size > 0) {
 		addattr_l(n, 32768, TCA_NETEM_DELAY_DIST,
@@ -229,6 +263,7 @@ static int netem_parse_opt(struct qdisc_util *qu, int argc, char **argv,
 static int netem_print_opt(struct qdisc_util *qu, FILE *f, struct rtattr *opt)
 {
 	const struct tc_netem_corr *cor = NULL;
+	const struct tc_netem_reorder *reorder = NULL;
 	struct tc_netem_qopt qopt;
 	int len = RTA_PAYLOAD(opt) - sizeof(qopt);
 	SPRINT_BUF(b1);
@@ -252,6 +287,11 @@ static int netem_print_opt(struct qdisc_util *qu, FILE *f, struct rtattr *opt)
 				return -1;
 			cor = RTA_DATA(tb[TCA_NETEM_CORR]);
 		}
+		if (tb[TCA_NETEM_REORDER]) {
+			if (RTA_PAYLOAD(tb[TCA_NETEM_REORDER]) < sizeof(*reorder))
+				return -1;
+			reorder = RTA_DATA(tb[TCA_NETEM_REORDER]);
+		}
 	}
 
 	fprintf(f, "limit %d", qopt.limit);
@@ -278,6 +318,14 @@ static int netem_print_opt(struct qdisc_util *qu, FILE *f, struct rtattr *opt)
 		if (cor && cor->dup_corr)
 			fprintf(f, " %s", sprint_percent(cor->dup_corr, b1));
 	}
+			
+	if (reorder && reorder->probability) {
+		fprintf(f, " reorder %s", 
+			sprint_percent(reorder->probability, b1));
+		if (reorder->correlation)
+			fprintf(f, " %s", 
+				sprint_percent(reorder->correlation, b1));
+	}
 
 	if (qopt.gap)
 		fprintf(f, " gap %lu", (unsigned long)qopt.gap);