[PATCH] iproute2: sch_rr support in tc

[PATCH] iproute2: sch_rr support in tc

[PJ Waskiewicz]

Stephen,

These patches are resubmissions of patches that were approved, but didn't
get merged.  The first patch is Patrick McHardy's nested compat attribute
patch to the netlink libraries.  The second patch adds multiqueue and sch_rr
functionality to tc.  The multiqueue features have been merged to 2.6.23, so
we'll need these patches to manage the new kernel features.

These patches are unmodified from the version that was approved.  They've been
applied to the latest iproute2 commit.

-- 
PJ Waskiewicz <peter.p.waskiewicz.jr@intel.com>

[PATCH 1/2] IPROUTE2: RTNETLINK nested attributes

[PJ Waskiewicz]

From: Patrick McHardy <kaber@trash.net>

This adds capability for iproute2 to send nested attributes to the
kernel, while maintaining backwards compatibility.

Signed-off-by: Patrick McHardy <kaber@trash.net>
---

 include/libnetlink.h |    9 +++++++++
 lib/libnetlink.c     |   46 ++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 55 insertions(+), 0 deletions(-)

diff --git a/include/libnetlink.h b/include/libnetlink.h
index 49e248e..b67c5a5 100644
--- a/include/libnetlink.h
+++ b/include/libnetlink.h
@@ -39,15 +39,24 @@ extern int rtnl_send(struct rtnl_handle *rth, const char *buf, int);
 extern int addattr32(struct nlmsghdr *n, int maxlen, int type, __u32 data);
 extern int addattr_l(struct nlmsghdr *n, int maxlen, int type, const void *data, int alen);
 extern int addraw_l(struct nlmsghdr *n, int maxlen, const void *data, int len);
+extern struct rtattr *addattr_nest(struct nlmsghdr *n, int maxlen, int type);
+extern int addattr_nest_end(struct nlmsghdr *n, struct rtattr *nest);
+extern struct rtattr *addattr_nest_compat(struct nlmsghdr *n, int maxlen, int type, const void *data, int len);
+extern int addattr_nest_compat_end(struct nlmsghdr *n, struct rtattr *nest);
 extern int rta_addattr32(struct rtattr *rta, int maxlen, int type, __u32 data);
 extern int rta_addattr_l(struct rtattr *rta, int maxlen, int type, const void *data, int alen);
 
 extern int parse_rtattr(struct rtattr *tb[], int max, struct rtattr *rta, int len);
 extern int parse_rtattr_byindex(struct rtattr *tb[], int max, struct rtattr *rta, int len);
+extern int __parse_rtattr_nested_compat(struct rtattr *tb[], int max, struct rtattr *rta, int len);
 
 #define parse_rtattr_nested(tb, max, rta) \
 	(parse_rtattr((tb), (max), RTA_DATA(rta), RTA_PAYLOAD(rta)))
 
+#define parse_rtattr_nested_compat(tb, max, rta, data, len) \
+({	data = RTA_PAYLOAD(rta) >= len ? RTA_DATA(rta) : NULL; \
+	__parse_rtattr_nested_compat(tb, max, rta, len); })
+
 extern int rtnl_listen(struct rtnl_handle *, rtnl_filter_t handler,
 		       void *jarg);
 extern int rtnl_from_file(FILE *, rtnl_filter_t handler,
diff --git a/lib/libnetlink.c b/lib/libnetlink.c
index 555dd5c..12883fe 100644
--- a/lib/libnetlink.c
+++ b/lib/libnetlink.c
@@ -527,6 +527,39 @@ int addraw_l(struct nlmsghdr *n, int maxlen, const void *data, int len)
 	return 0;
 }
 
+struct rtattr *addattr_nest(struct nlmsghdr *n, int maxlen, int type)
+{
+	struct rtattr *nest = NLMSG_TAIL(n);
+
+	addattr_l(n, maxlen, type, NULL, 0);
+	return nest;
+}
+
+int addattr_nest_end(struct nlmsghdr *n, struct rtattr *nest)
+{
+	nest->rta_len = (void *)NLMSG_TAIL(n) - (void *)nest;
+	return n->nlmsg_len;
+}
+
+struct rtattr *addattr_nest_compat(struct nlmsghdr *n, int maxlen, int type,
+				   const void *data, int len)
+{
+	struct rtattr *start = NLMSG_TAIL(n);
+
+	addattr_l(n, maxlen, type, data, len);
+	addattr_nest(n, maxlen, type);
+	return start;
+}
+
+int addattr_nest_compat_end(struct nlmsghdr *n, struct rtattr *start)
+{
+	struct rtattr *nest = (void *)start + NLMSG_ALIGN(start->rta_len);
+
+	start->rta_len = (void *)NLMSG_TAIL(n) - (void *)start;
+	addattr_nest_end(n, nest);
+	return n->nlmsg_len;
+}
+
 int rta_addattr32(struct rtattr *rta, int maxlen, int type, __u32 data)
 {
 	int len = RTA_LENGTH(4);
@@ -589,3 +622,16 @@ int parse_rtattr_byindex(struct rtattr *tb[], int max, struct rtattr *rta, int l
 		fprintf(stderr, "!!!Deficit %d, rta_len=%d\n", len, rta->rta_len);
 	return i;
 }
+
+int __parse_rtattr_nested_compat(struct rtattr *tb[], int max, struct rtattr *rta,
+			         int len)
+{
+	if (RTA_PAYLOAD(rta) < len)
+		return -1;
+	if (RTA_PAYLOAD(rta) >= RTA_ALIGN(len) + sizeof(struct rtattr)) {
+		rta = RTA_DATA(rta) + RTA_ALIGN(len);
+		return parse_rtattr_nested(tb, max, rta);
+	}
+	memset(tb, 0, sizeof(struct rtattr *) * max);
+	return 0;
+}

[PATCH 2/2] iproute2: sch_rr support in tc

[PJ Waskiewicz]

This patch applies on top of Patrick McHardy's RTNETLINK
patches to add nested compat attributes.  This is needed to maintain
ABI for sch_{rr|prio} in the kernel with respect to tc.  A new option,
namely multiqueue, was added to sch_prio and sch_rr.  This will allow
a user to turn multiqueue support on for sch_prio or sch_rr at loadtime.
Also, tc qdisc ls will display whether or not multiqueue is enabled on
that qdisc.  When in multiqueue mode, a user can specify a value of 0 for
bands, and the number of bands will be created to match the number of
queues on the device.

This patch is to support the new sch_rr (round-robin) qdisc being proposed
in NET for multiqueue network device support in the Linux network stack.
It uses q_prio.c as the template, since the qdiscs are nearly identical,
outside of the ->dequeue() routine.

Signed-off-by: Peter P Waskiewicz Jr <peter.p.waskiewicz.jr@intel.com>
---

 include/linux/pkt_sched.h |    9 +++
 tc/q_prio.c               |   24 +++++++--
 tc/q_rr.c                 |  127 +++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 155 insertions(+), 5 deletions(-)

diff --git a/include/linux/pkt_sched.h b/include/linux/pkt_sched.h
index d10f353..4f1531b 100644
--- a/include/linux/pkt_sched.h
+++ b/include/linux/pkt_sched.h
@@ -101,6 +101,15 @@ struct tc_prio_qopt
 	__u8	priomap[TC_PRIO_MAX+1];	/* Map: logical priority -> PRIO band */
 };
 
+enum
+{
+        TCA_PRIO_UNSPEC,
+        TCA_PRIO_MQ,
+        __TCA_PRIO_MAX
+};
+
+#define TCA_PRIO_MAX    (__TCA_PRIO_MAX - 1)
+
 /* TBF section */
 
 struct tc_tbf_qopt
diff --git a/tc/q_prio.c b/tc/q_prio.c
index d696e1b..6883edb 100644
--- a/tc/q_prio.c
+++ b/tc/q_prio.c
@@ -29,7 +29,7 @@
 
 static void explain(void)
 {
-	fprintf(stderr, "Usage: ... prio bands NUMBER priomap P1 P2...\n");
+	fprintf(stderr, "Usage: ... prio bands NUMBER priomap P1 P2...[multiqueue]\n");
 }
 
 #define usage() return(-1)
@@ -40,6 +40,8 @@ static int prio_parse_opt(struct qdisc_util *qu, int argc, char **argv, struct n
 	int pmap_mode = 0;
 	int idx = 0;
 	struct tc_prio_qopt opt={3,{ 1, 2, 2, 2, 1, 2, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1 }};
+	struct rtattr *nest;
+	unsigned char mq = 0;
 
 	while (argc > 0) {
 		if (strcmp(*argv, "bands") == 0) {
@@ -57,6 +59,8 @@ static int prio_parse_opt(struct qdisc_util *qu, int argc, char **argv, struct n
 				return -1;
 			}
 			pmap_mode = 1;
+		} else if (strcmp(*argv, "multiqueue") == 0) {
+			mq = 1;
 		} else if (strcmp(*argv, "help") == 0) {
 			explain();
 			return -1;
@@ -90,7 +94,10 @@ static int prio_parse_opt(struct qdisc_util *qu, int argc, char **argv, struct n
 			opt.priomap[idx] = opt.priomap[TC_PRIO_BESTEFFORT];
 	}
 */
-	addattr_l(n, 1024, TCA_OPTIONS, &opt, sizeof(opt));
+	nest = addattr_nest_compat(n, 1024, TCA_OPTIONS, &opt, sizeof(opt));
+	if (mq)
+		addattr_l(n, 1024, TCA_PRIO_MQ, NULL, 0);
+	addattr_nest_compat_end(n, nest);
 	return 0;
 }
 
@@ -98,16 +105,23 @@ int prio_print_opt(struct qdisc_util *qu, FILE *f, struct rtattr *opt)
 {
 	int i;
 	struct tc_prio_qopt *qopt;
+	struct rtattr *tb[TCA_PRIO_MAX+1];
 
 	if (opt == NULL)
 		return 0;
 
-	if (RTA_PAYLOAD(opt)  < sizeof(*qopt))
-		return -1;
-	qopt = RTA_DATA(opt);
+	if (parse_rtattr_nested_compat(tb, TCA_PRIO_MAX, opt, qopt,
+					sizeof(*qopt)))
+                return -1;
+
 	fprintf(f, "bands %u priomap ", qopt->bands);
 	for (i=0; i<=TC_PRIO_MAX; i++)
 		fprintf(f, " %d", qopt->priomap[i]);
+
+	if (tb[TCA_PRIO_MQ])
+		fprintf(f, " multiqueue: %s ",
+		    *(unsigned char *)RTA_DATA(tb[TCA_PRIO_MQ]) ? "on" : "off");
+
 	return 0;
 }
 
diff --git a/tc/q_rr.c b/tc/q_rr.c
new file mode 100644
index 0000000..9335c47
--- /dev/null
+++ b/tc/q_rr.c
@@ -0,0 +1,127 @@
+/*
+ * q_rr.c		RR.
+ *
+ *		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.
+ *
+ * Authors:	PJ Waskiewicz, <peter.p.waskiewicz.jr@intel.com>
+ * Original Authors:	Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> (from PRIO)
+ *
+ * Changes:
+ *
+ * Ole Husgaard <sparre@login.dknet.dk>: 990513: prio2band map was always reset.
+ * J Hadi Salim <hadi@cyberus.ca>: 990609: priomap fix.
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <string.h>
+
+#include "utils.h"
+#include "tc_util.h"
+
+static void explain(void)
+{
+	fprintf(stderr, "Usage: ... rr bands NUMBER priomap P1 P2... [multiqueue]\n");
+}
+
+#define usage() return(-1)
+
+static int rr_parse_opt(struct qdisc_util *qu, int argc, char **argv, struct nlmsghdr *n)
+{
+	int ok = 0;
+	int pmap_mode = 0;
+	int idx = 0;
+	struct tc_prio_qopt opt={3,{ 1, 2, 2, 2, 1, 2, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1 }};
+	struct rtattr *nest;
+	unsigned char mq = 0;
+
+	while (argc > 0) {
+		if (strcmp(*argv, "bands") == 0) {
+			if (pmap_mode)
+				explain();
+			NEXT_ARG();
+			if (get_integer(&opt.bands, *argv, 10)) {
+				fprintf(stderr, "Illegal \"bands\"\n");
+				return -1;
+			}
+			ok++;
+		} else if (strcmp(*argv, "priomap") == 0) {
+			if (pmap_mode) {
+				fprintf(stderr, "Error: duplicate priomap\n");
+				return -1;
+			}
+			pmap_mode = 1;
+		} else if (strcmp(*argv, "help") == 0) {
+			explain();
+			return -1;
+		} else if (strcmp(*argv, "multiqueue") == 0) {
+			mq = 1;
+		} else {
+			unsigned band;
+			if (!pmap_mode) {
+				fprintf(stderr, "What is \"%s\"?\n", *argv);
+				explain();
+				return -1;
+			}
+			if (get_unsigned(&band, *argv, 10)) {
+				fprintf(stderr, "Illegal \"priomap\" element\n");
+				return -1;
+			}
+			if (band > opt.bands) {
+				fprintf(stderr, "\"priomap\" element is out of bands\n");
+				return -1;
+			}
+			if (idx > TC_PRIO_MAX) {
+				fprintf(stderr, "\"priomap\" index > TC_RR_MAX=%u\n", TC_PRIO_MAX);
+				return -1;
+			}
+			opt.priomap[idx++] = band;
+		}
+		argc--; argv++;
+	}
+
+	nest = addattr_nest_compat(n, 1024, TCA_OPTIONS, &opt, sizeof(opt));
+	if (mq)
+		addattr_l(n, 1024, TCA_PRIO_MQ, NULL, 0);
+	addattr_nest_compat_end(n, nest);
+	return 0;
+}
+
+int rr_print_opt(struct qdisc_util *qu, FILE *f, struct rtattr *opt)
+{
+	int i;
+	struct tc_prio_qopt *qopt;
+	struct rtattr *tb[TCA_PRIO_MAX + 1];
+
+	if (opt == NULL)
+		return 0;
+
+	if (parse_rtattr_nested_compat(tb, TCA_PRIO_MAX, opt, qopt,
+						sizeof(*qopt)))
+		return -1;
+
+	fprintf(f, "bands %u priomap ", qopt->bands);
+	for (i=0; i <= TC_PRIO_MAX; i++)
+		fprintf(f, " %d", qopt->priomap[i]);
+
+	if (tb[TCA_PRIO_MQ])
+		fprintf(f, " multiqueue: %s ",
+		    *(unsigned char *)RTA_DATA(tb[TCA_PRIO_MQ]) ? "on" : "off");
+
+	return 0;
+}
+
+struct qdisc_util rr_qdisc_util = {
+	.id	 	= "rr",
+	.parse_qopt	= rr_parse_opt,
+	.print_qopt	= rr_print_opt,
+};