[PATCH iproute2-next] Add tc(8) userspace support for SKB Priority qdisc

[PATCH iproute2-next] Add tc(8) userspace support for SKB Priority qdisc

[Nishanth Devarajan]

sch_skbprio is a qdisc that prioritizes packets according to their skb->priority
field. Under congestion, it drops already-enqueued lower priority packets to
make space available for higher priority packets. Skbprio was conceived as a
solution for denial-of-service defenses that need to route packets with
different priorities as a means to overcome DoS attacks.

Signed-off-by: Nishanth Devarajan <ndev2021@gmail.com>
Reviewed-by: Michel Machado <michel@digirati.com.br>
---
 include/uapi/linux/pkt_sched.h |  7 ++++
 man/man8/tc-skbprio.8          | 70 ++++++++++++++++++++++++++++++++++++
 tc/Makefile                    |  1 +
 tc/q_skbprio.c                 | 81 ++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 159 insertions(+)
 create mode 100644 man/man8/tc-skbprio.8
 create mode 100644 tc/q_skbprio.c

diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h
index 37b5096..81af99e 100644
--- a/include/uapi/linux/pkt_sched.h
+++ b/include/uapi/linux/pkt_sched.h
@@ -124,6 +124,12 @@ struct tc_fifo_qopt {
 	__u32	limit;	/* Queue length: bytes for bfifo, packets for pfifo */
 };
 
+/* SKBPRIO section */
+
+struct tc_skbprio_qopt {
+	__u32	limit;		/* Queue length in packets. */
+};
+
 /* PRIO section */
 
 #define TCQ_PRIO_BANDS	16
@@ -256,6 +262,7 @@ struct tc_red_qopt {
 #define TC_RED_ECN		1
 #define TC_RED_HARDDROP		2
 #define TC_RED_ADAPTATIVE	4
+#define TC_RED_OFFLOADED	8
 };
 
 struct tc_red_xstats {
diff --git a/man/man8/tc-skbprio.8 b/man/man8/tc-skbprio.8
new file mode 100644
index 0000000..ae4f9e1
--- /dev/null
+++ b/man/man8/tc-skbprio.8
@@ -0,0 +1,70 @@
+.TH SKBPRIO 8 "27 July 2018" "iproute2" "Linux"
+.SH NAME
+skbprio \- SKB Priority Queue
+
+.SH SYNOPSIS
+.B tc qdisc ... add skbprio
+.B [ limit
+packets
+.B ]
+
+.SH DESCRIPTION
+SKB Priority Queue is a queueing discipline intended to prioritize
+the most important packets during a denial-of-service (
+.B DoS
+) attack. The priority of a packet is given by
+.B skb->priority
+, where a higher value places the packet closer to the exit of the queue. When
+the queue is full, the lowest priority packet in the queue is dropped to make
+room for the packet to be added if it has higher priority. If the packet to be
+added has lower priority than all packets in the queue, it is dropped.
+
+Without SKB priority queue, queue length limits must be imposed
+on individual sub-queues, and there is no straightforward way to enforce
+a global queue length limit across all priorities. SKBprio queue enforces a
+global queue length limit while not restricting the lengths of individual
+sub-queues.
+
+While SKB Priority Queue is agnostic to how
+.B skb->priority
+is assigned. A typical use case is to copy
+the 6-bit DS field of IPv4 and IPv6 packets using
+.BR tc-skbedit (8)
+. If
+.B skb->priority
+is greater or equal to 64, the priority is assumed to be 63.
+Priorities less than 64 are taken at face value.
+
+SKB Priority Queue enables routers to locally decide which
+packets to drop under a DoS attack.
+Priorities should be assigned to packets such that the higher the priority,
+the more expected behavior a source shows.
+So sources have an incentive to play by the rules.
+
+.SH ALGORITHM
+
+Skbprio maintains 64 lists (priorities go from 0 to 63).
+When a packet is enqueued, it gets inserted at the
+.B tail
+of its priority list. When a packet needs to be sent out to the network, it is
+taken from the head of the highest priority list. When the queue is full,
+the packet at the tail of the lowest priority list is dropped to serve the
+ingress packet - if it is of higher priority, otherwise the ingress packet is
+dropped. This algorithm allocates as much bandwidth as possible to high
+priority packets, while only servicing low priority packets when
+there is enough bandwidth.
+
+.SH PARAMETERS
+.TP
+limit
+Maximum queue size specified in packets. It defaults to 64.
+The range for this parameter is [0, UINT32_MAX].
+
+.SH SEE ALSO
+.BR tc-prio (8),
+.BR tc-skbedit (8)
+
+.SH AUTHORS
+Nishanth Devarajan <devarajn@uci.edu>, Michel Machado <michel@digirati.com.br>
+
+This manpage maintained by Bert Hubert <ahu@ds9a.nl>
diff --git a/tc/Makefile b/tc/Makefile
index dfd0026..7646105 100644
--- a/tc/Makefile
+++ b/tc/Makefile
@@ -71,6 +71,7 @@ TCMODULES += q_clsact.o
 TCMODULES += e_bpf.o
 TCMODULES += f_matchall.o
 TCMODULES += q_cbs.o
+TCMODULES += q_skbprio.o
 
 TCSO :=
 ifeq ($(TC_CONFIG_ATM),y)
diff --git a/tc/q_skbprio.c b/tc/q_skbprio.c
new file mode 100644
index 0000000..a2a5077
--- /dev/null
+++ b/tc/q_skbprio.c
@@ -0,0 +1,81 @@
+/*
+ * q_skbprio.c		SKB PRIORITY QUEUE.
+ *
+ *		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:	Nishanth Devarajan, <ndev2021@gmail.com>
+ *
+ */
+
+#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: ... <skbprio> [ limit NUMBER ]\n");
+}
+
+static int skbprio_parse_opt(struct qdisc_util *qu, int argc, char **argv,
+			     struct nlmsghdr *n, const char *dev)
+{
+	int ok = 0;
+	struct tc_skbprio_qopt opt = {};
+
+	while (argc > 0) {
+		if (strcmp(*argv, "limit") == 0) {
+			NEXT_ARG();
+			if (get_size(&opt.limit, *argv)) {
+				fprintf(stderr, "%s: Illegal value for \"limit\": \"%s\"\n", qu->id, *argv);
+				return -1;
+			}
+			ok++;
+		}
+		else if (strcmp(*argv, "help") == 0) {
+			explain();
+			return -1;
+		} else {
+			fprintf(stderr, "%s: unknown parameter \"%s\"\n", qu->id, *argv);
+			explain();
+			return -1;
+		}
+		argc--; argv++;
+	}
+
+	if (ok)
+		addattr_l(n, 1024, TCA_OPTIONS, &opt, sizeof(opt));
+	return 0;
+}
+
+static int skbprio_print_opt(struct qdisc_util *qu, FILE *f, struct rtattr *opt)
+{
+	struct tc_skbprio_qopt *qopt;
+
+	if (opt == NULL)
+		return 0;
+
+	if (RTA_PAYLOAD(opt)  < sizeof(*qopt))
+		return -1;
+	qopt = RTA_DATA(opt);
+	fprintf(f, "limit %u ", qopt->limit);
+	return 0;
+}
+
+
+struct qdisc_util skbprio_qdisc_util = {
+	.id = "skbprio",
+	.parse_qopt = skbprio_parse_opt,
+	.print_qopt = skbprio_print_opt,
+};
-- 
1.9.1