path: root/package/network/utils/iproute2/patches/950-add-cake-to-tc.patch

diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h
index 37b5096a..66da5df9 100644
--- a/include/uapi/linux/pkt_sched.h
+++ b/include/uapi/linux/pkt_sched.h
@@ -934,4 +934,75 @@ enum {
 
 #define TCA_CBS_MAX (__TCA_CBS_MAX - 1)
 
+/* CAKE */
+enum {
+	TCA_CAKE_UNSPEC,
+	TCA_CAKE_BASE_RATE,
+	TCA_CAKE_DIFFSERV_MODE,
+	TCA_CAKE_ATM,
+	TCA_CAKE_FLOW_MODE,
+	TCA_CAKE_OVERHEAD,
+	TCA_CAKE_RTT,
+	TCA_CAKE_TARGET,
+	TCA_CAKE_AUTORATE,
+	TCA_CAKE_MEMORY,
+	TCA_CAKE_NAT,
+	TCA_CAKE_RAW, // was _ETHERNET
+	TCA_CAKE_WASH,
+	TCA_CAKE_MPU,
+	TCA_CAKE_INGRESS,
+	TCA_CAKE_ACK_FILTER,
+	__TCA_CAKE_MAX
+};
+#define TCA_CAKE_MAX	(__TCA_CAKE_MAX - 1)
+
+struct tc_cake_traffic_stats {
+	__u32 packets;
+	__u32 link_ms;
+	__u64 bytes;
+};
+
+#define TC_CAKE_MAX_TINS (8)
+struct tc_cake_tin_stats {
+
+	__u32 threshold_rate;
+	__u32 target_us;
+	struct tc_cake_traffic_stats sent;
+	struct tc_cake_traffic_stats dropped;
+	struct tc_cake_traffic_stats ecn_marked;
+	struct tc_cake_traffic_stats backlog;
+	__u32 interval_us;
+	__u32 way_indirect_hits;
+	__u32 way_misses;
+	__u32 way_collisions;
+	__u32 peak_delay_us; /* ~= bulk flow delay */
+	__u32 avge_delay_us;
+	__u32 base_delay_us; /* ~= sparse flows delay */
+	__u16 sparse_flows;
+	__u16 bulk_flows;
+	__u16 unresponse_flows;
+	__u16 spare;
+	__u32 max_skblen;
+	struct tc_cake_traffic_stats ack_drops;
+};
+
+struct tc_cake_xstats {
+	__u16 version;
+	__u16 tin_stats_size; /* == sizeof(struct tc_cake_tin_stats) */
+	__u32 capacity_estimate;
+	__u32 memory_limit;
+	__u32 memory_used;
+	__u8  tin_cnt;
+	__u8  avg_trnoff;
+	__u16 max_trnlen;
+	__u16 max_adjlen;
+	__u16 min_trnlen;
+	__u16 min_adjlen;
+
+	__u16 spare1;
+	__u32 spare2;
+
+	struct tc_cake_tin_stats tin_stats[0]; /* keep last */
+};
+
 #endif
diff --git a/man/man8/tc-cake.8 b/man/man8/tc-cake.8
new file mode 100644
index 00000000..ff77db8f
--- /dev/null
+++ b/man/man8/tc-cake.8
@@ -0,0 +1,678 @@
+.TH CAKE 8 "23 November 2017" "iproute2" "Linux"
+.SH NAME
+CAKE \- COMMON Applications Kept Enhanced (CAKE)
+.SH SYNOPSIS
+.B tc qdisc ... cake
+.br
+[
+.BR bandwidth
+RATE |
+.BR unlimited*
+|
+.BR autorate_ingress
+]
+.br
+[
+.BR rtt
+TIME |
+.BR datacentre
+|
+.BR lan
+|
+.BR metro
+|
+.BR regional
+|
+.BR internet*
+|
+.BR oceanic
+|
+.BR satellite
+|
+.BR interplanetary
+]
+.br
+[
+.BR besteffort
+|
+.BR diffserv8
+|
+.BR diffserv4
+|
+.BR diffserv-llt
+|
+.BR diffserv3*
+]
+.br
+[
+.BR flowblind
+|
+.BR srchost
+|
+.BR dsthost
+|
+.BR hosts
+|
+.BR flows
+|
+.BR dual-srchost
+|
+.BR dual-dsthost
+|
+.BR triple-isolate*
+]
+.br
+[
+.BR nat
+|
+.BR nonat*
+]
+.br
+[
+.BR wash
+|
+.BR nowash*
+]
+.br
+[
+.BR ack-filter
+|
+.BR ack-filter-aggressive
+|
+.BR no-ack-filter*
+]
+.br
+[
+.BR memlimit
+LIMIT ]
+.br
+[
+.BR ptm
+|
+.BR atm
+|
+.BR noatm*
+]
+.br
+[
+.BR overhead
+N |
+.BR conservative
+|
+.BR raw*
+]
+.br
+[
+.BR mpu
+N ]
+.br
+[
+.BR ingress
+|
+.BR egress*
+]
+.br
+(* marks defaults)
+
+
+.SH DESCRIPTION
+CAKE (Common Applications Kept Enhanced) is a shaping-capable queue discipline
+which uses both AQM and FQ.  It combines COBALT, which is an AQM algorithm
+combining Codel and BLUE, a shaper which operates in deficit mode, and a variant
+of DRR++ for flow isolation.  8-way set-associative hashing is used to virtually
+eliminate hash collisions.  Priority queuing is available through a simplified
+diffserv implementation.  Overhead compensation for various encapsulation
+schemes is tightly integrated.
+
+All settings are optional; the default settings are chosen to be sensible in
+most common deployments.  Most people will only need to set the
+.B bandwidth
+parameter to get useful results, but reading the
+.B Overhead Compensation
+and
+.B Round Trip Time
+sections is strongly encouraged.
+
+.SH SHAPER PARAMETERS
+CAKE uses a deficit-mode shaper, which does not exhibit the initial burst
+typical of token-bucket shapers.  It will automatically burst precisely as much
+as required to maintain the configured throughput.  As such, it is very
+straightforward to configure.
+.PP
+.B unlimited
+(default)
+.br
+	No limit on the bandwidth.
+.PP
+.B bandwidth
+RATE
+.br
+	Set the shaper bandwidth.  See
+.BR tc(8)
+or examples below for details of the RATE value.
+.PP
+.B autorate_ingress
+.br
+	Automatic capacity estimation based on traffic arriving at this qdisc.
+This is most likely to be useful with cellular links, which tend to change
+quality randomly.  A
+.B bandwidth
+parameter can be used in conjunction to specify an initial estimate.  The shaper
+will periodically be set to a bandwidth slightly below the estimated rate.  This
+estimator cannot estimate the bandwidth of links downstream of itself.
+
+.SH OVERHEAD COMPENSATION PARAMETERS
+The size of each packet on the wire may differ from that seen by Linux.  The
+following parameters allow CAKE to compensate for this difference by internally
+considering each packet to be bigger than Linux informs it.  To assist users who
+are not expert network engineers, keywords have been provided to represent a
+number of common link technologies.
+
+.SS	Manual Overhead Specification
+.B overhead
+BYTES
+.br
+	Adds BYTES to the size of each packet.  BYTES may be negative; values
+between -64 and 256 (inclusive) are accepted.
+.PP
+.B mpu
+BYTES
+.br
+	Rounds each packet (including overhead) up to a minimum length
+BYTES. BYTES may not be negative; values between 0 and 256 (inclusive)
+are accepted.
+.PP
+.B atm
+.br
+	Compensates for ATM cell framing, which is normally found on ADSL links.
+This is performed after the
+.B overhead
+parameter above.  ATM uses fixed 53-byte cells, each of which can carry 48 bytes
+payload.
+.PP
+.B ptm
+.br
+	Compensates for PTM encoding, which is normally found on VDSL2 links and
+uses a 64b/65b encoding scheme. It is even more efficient to simply
+derate the specified shaper bandwidth by a factor of 64/65 or 0.984. See
+ITU G.992.3 Annex N and IEEE 802.3 Section 61.3 for details.
+.PP
+.B noatm
+.br
+	Disables ATM and PTM compensation.
+
+.SS	Failsafe Overhead Keywords
+These two keywords are provided for quick-and-dirty setup.  Use them if you
+can't be bothered to read the rest of this section.
+.PP
+.B raw
+(default)
+.br
+	Turns off all overhead compensation in CAKE.  The packet size reported
+by Linux will be used directly.
+.PP
+	Other overhead keywords may be added after "raw".  The effect of this is
+to make the overhead compensation operate relative to the reported packet size,
+not the underlying IP packet size.
+.PP
+.B conservative
+.br
+	Compensates for more overhead than is likely to occur on any
+widely-deployed link technology.
+.br
+	Equivalent to
+.B overhead 48 atm.
+
+.SS ADSL Overhead Keywords
+Most ADSL modems have a way to check which framing scheme is in use.  Often this
+is also specified in the settings document provided by the ISP.  The keywords in
+this section are intended to correspond with these sources of information.  All
+of them implicitly set the
+.B atm
+flag.
+.PP
+.B pppoa-vcmux
+.br
+	Equivalent to
+.B overhead 10 atm
+.PP
+.B pppoa-llc
+.br
+	Equivalent to
+.B overhead 14 atm
+.PP
+.B pppoe-vcmux
+.br
+	Equivalent to
+.B overhead 32 atm
+.PP
+.B pppoe-llcsnap
+.br
+	Equivalent to
+.B overhead 40 atm
+.PP
+.B bridged-vcmux
+.br
+	Equivalent to
+.B overhead 24 atm
+.PP
+.B bridged-llcsnap
+.br
+	Equivalent to
+.B overhead 32 atm
+.PP
+.B ipoa-vcmux
+.br
+	Equivalent to
+.B overhead 8 atm
+.PP
+.B ipoa-llcsnap
+.br
+	Equivalent to
+.B overhead 16 atm
+.PP
+See also the Ethernet Correction Factors section below.
+
+.SS VDSL2 Overhead Keywords
+ATM was dropped from VDSL2 in favour of PTM, which is a much more
+straightforward framing scheme.  Some ISPs retained PPPoE for compatibility with
+their existing back-end systems.
+.PP
+.B pppoe-ptm
+.br
+	Equivalent to
+.B overhead 30 ptm
+
+.br
+	PPPoE: 2B PPP + 6B PPPoE +
+.br
+	ETHERNET: 6B dest MAC + 6B src MAC + 2B ethertype + 4B Frame Check Sequence +
+.br
+	PTM: 1B Start of Frame (S) + 1B End of Frame (Ck) + 2B TC-CRC (PTM-FCS)
+.br
+.PP
+.B bridged-ptm
+.br
+	Equivalent to
+.B overhead 22 ptm
+.br
+	ETHERNET: 6B dest MAC + 6B src MAC + 2B ethertype + 4B Frame Check Sequence +
+.br
+	PTM: 1B Start of Frame (S) + 1B End of Frame (Ck) + 2B TC-CRC (PTM-FCS)
+.br
+.PP
+See also the Ethernet Correction Factors section below.
+
+.SS DOCSIS Cable Overhead Keyword
+DOCSIS is the universal standard for providing Internet service over cable-TV
+infrastructure.
+
+In this case, the actual on-wire overhead is less important than the packet size
+the head-end equipment uses for shaping and metering.  This is specified to be
+an Ethernet frame including the CRC (aka FCS).
+.PP
+.B docsis
+.br
+	Equivalent to
+.B overhead 18 mpu 64 noatm
+
+.SS Ethernet Overhead Keywords
+.PP
+.B ethernet
+.br
+	Accounts for Ethernet's preamble, inter-frame gap, and Frame Check
+Sequence.  Use this keyword when the bottleneck being shaped for is an
+actual Ethernet cable.
+.br
+	Equivalent to
+.B overhead 38 mpu 84 noatm
+.PP
+.B ether-vlan
+.br
+	Adds 4 bytes to the overhead compensation, accounting for an IEEE 802.1Q
+VLAN header appended to the Ethernet frame header.  NB: Some ISPs use one or
+even two of these within PPPoE; this keyword may be repeated as necessary to
+express this.
+
+.SH ROUND TRIP TIME PARAMETERS
+Active Queue Management (AQM) consists of embedding congestion signals in the
+packet flow, which receivers use to instruct senders to slow down when the queue
+is persistently occupied.  CAKE uses ECN signalling when available, and packet
+drops otherwise, according to a combination of the Codel and BLUE AQM algorithms
+called COBALT.
+
+Very short latencies require a very rapid AQM response to adequately control
+latency.  However, such a rapid response tends to impair throughput when the
+actual RTT is relatively long.  CAKE allows specifying the RTT it assumes for
+tuning various parameters.  Actual RTTs within an order of magnitude of this
+will generally work well for both throughput and latency management.
+
+At the 'lan' setting and below, the time constants are similar in magnitude to
+the jitter in the Linux kernel itself, so congestion might be signalled
+prematurely. The flows will then become sparse and total throughput reduced,
+leaving little or no back-pressure for the fairness logic to work against. Use
+the "metro" setting for local lans unless you have a custom kernel.
+.PP
+.B rtt
+TIME
+.br
+	Manually specify an RTT.
+.PP
+.B datacentre
+.br
+	For extremely high-performance 10GigE+ networks only.  Equivalent to
+.B rtt 100us.
+.PP
+.B lan
+.br
+	For pure Ethernet (not Wi-Fi) networks, at home or in the office.  Don't
+use this when shaping for an Internet access link.  Equivalent to
+.B rtt 1ms.
+.PP
+.B metro
+.br
+	For traffic mostly within a single city.  Equivalent to
+.B rtt 10ms.
+.PP
+.B regional
+.br
+	For traffic mostly within a European-sized country.  Equivalent to
+.B rtt 30ms.
+.PP
+.B internet
+(default)
+.br
+	This is suitable for most Internet traffic.  Equivalent to
+.B rtt 100ms.
+.PP
+.B oceanic
+.br
+	For Internet traffic with generally above-average latency, such as that
+suffered by Australasian residents.  Equivalent to
+.B rtt 300ms.
+.PP
+.B satellite
+.br
+	For traffic via geostationary satellites.  Equivalent to
+.B rtt 1000ms.
+.PP
+.B interplanetary
+.br
+	So named because Jupiter is about 1 light-hour from Earth.  Use this to
+(almost) completely disable AQM actions.  Equivalent to
+.B rtt 1000s.
+
+.SH FLOW ISOLATION PARAMETERS
+With flow isolation enabled, CAKE places packets from different flows into
+different queues, each of which carries its own AQM state.  Packets from each
+queue are then delivered fairly, according to a DRR++ algorithm which minimises
+latency for "sparse" flows.  CAKE uses a set-associative hashing algorithm to
+minimise flow collisions.
+
+These keywords specify whether fairness based on source address, destination
+address, individual flows, or any combination of those is desired.
+.PP
+.B flowblind
+.br
+	Disables flow isolation; all traffic passes through a single queue for
+each tin.
+.PP
+.B srchost
+.br
+	Flows are defined only by source address.  Could be useful on the egress
+path of an ISP backhaul.
+.PP
+.B dsthost
+.br
+	Flows are defined only by destination address.  Could be useful on the
+ingress path of an ISP backhaul.
+.PP
+.B hosts
+.br
+	Flows are defined by source-destination host pairs.  This is host
+isolation, rather than flow isolation.
+.PP
+.B flows
+.br
+	Flows are defined by the entire 5-tuple of source address, destination
+address, transport protocol, source port and destination port.  This is the type
+of flow isolation performed by SFQ and fq_codel.
+.PP
+.B dual-srchost
+.br
+	Flows are defined by the 5-tuple, and fairness is applied first over
+source addresses, then over individual flows.  Good for use on egress traffic
+from a LAN to the internet, where it'll prevent any one LAN host from
+monopolising the uplink, regardless of the number of flows they use.
+.PP
+.B dual-dsthost
+.br
+	Flows are defined by the 5-tuple, and fairness is applied first over
+destination addresses, then over individual flows.  Good for use on ingress
+traffic to a LAN from the internet, where it'll prevent any one LAN host from
+monopolising the downlink, regardless of the number of flows they use.
+.PP
+.B triple-isolate
+(default)
+.br
+	Flows are defined by the 5-tuple, and fairness is applied over source
+*and* destination addresses intelligently (ie. not merely by host-pairs), and
+also over individual flows.  Use this if you're not certain whether to use
+dual-srchost or dual-dsthost; it'll do both jobs at once, preventing any one
+host on *either* side of the link from monopolising it with a large number of
+flows.
+.PP
+.B nat
+.br
+	Instructs Cake to perform a NAT lookup before applying flow-isolation
+rules, to determine the true addresses and port numbers of the packet, to
+improve fairness between hosts "inside" the NAT.  This has no practical effect
+in "flowblind" or "flows" modes, or if NAT is performed on a different host.
+.PP
+.B nonat
+(default)
+.br
+	Cake will not perform a NAT lookup.  Flow isolation will be performed
+using the addresses and port numbers directly visible to the interface Cake is
+attached to.
+
+.SH PRIORITY QUEUE PARAMETERS
+CAKE can divide traffic into "tins" based on the Diffserv field.  Each tin has
+its own independent set of flow-isolation queues, and is serviced based on a WRR
+algorithm.  To avoid perverse Diffserv marking incentives, tin weights have a
+"priority sharing" value when bandwidth used by that tin is below a threshold,
+and a lower "bandwidth sharing" value when above.  Bandwidth is compared against
+the threshold using the same algorithm as the deficit-mode shaper.
+
+Detailed customisation of tin parameters is not provided.  The following presets
+perform all necessary tuning, relative to the current shaper bandwidth and RTT
+settings.
+.PP
+.B besteffort
+.br
+	Disables priority queuing by placing all traffic in one tin.
+.PP
+.B precedence
+.br
+	Enables legacy interpretation of TOS "Precedence" field.  Use of this
+preset on the modern Internet is firmly discouraged.
+.PP
+.B diffserv-llt
+.br
+	Provides a "Latency-Loss Tradeoff" implementation with five tins:
+.br
+		Low Loss (TOS1, TOS2), 100% threshold, increased Codel target.
+.br
+		Best Effort (general), 100% threshold, normal Codel target & interval.
+.br
+		Low Latency (TOS4, TOS5, VA, EF), 100% threshold, reduced Codel interval.
+.br
+		Bulk (CS1), 6.25% threshold, normal Codel target & interval.
+.br
+		Net Control (CS6, CS7), 6.25% threshold, increased Codel target & interval.
+.PP
+.B diffserv4
+.br
+	Provides a general-purpose Diffserv implementation with four tins:
+.br
+		Bulk (CS1), 6.25% threshold, generally low priority.
+.br
+		Best Effort (general), 100% threshold.
+.br
+		Video (AF4x, AF3x, CS3, AF2x, CS2, TOS4, TOS1), 50% threshold.
+.br
+		Voice (CS7, CS6, EF, VA, CS5, CS4), 25% threshold.
+.PP
+.B diffserv3
+(default)
+.br
+	Provides a simple, general-purpose Diffserv implementation with three tins:
+.br
+		Bulk (CS1), 6.25% threshold, generally low priority.
+.br
+		Best Effort (general), 100% threshold.
+.br
+		Voice (CS7, CS6, EF, VA, TOS4), 25% threshold, reduced Codel interval.
+
+.SH OTHER PARAMETERS
+.B memlimit
+LIMIT
+.br
+	Limit the memory consumed by Cake to LIMIT bytes. Note that this does
+not translate directly to queue size (so do not size this based on bandwidth
+delay product considerations, but rather on worst case acceptable memory
+consumption), as there is some overhead in the data structures containing the
+packets, especially for small packets.
+
+	By default, the limit is calculated based on the bandwidth and RTT
+settings.
+
+.PP
+.B wash
+
+.br
+	Traffic entering your diffserv domain is frequently mis-marked in
+transit from the perspective of your network, and traffic exiting yours may be
+mis-marked from the perspective of the transiting provider.
+
+Apply the wash option to clear all extra diffserv (but not ECN bits), after
+priority queuing has taken place.
+
+If you are shaping inbound, and cannot trust the diffserv markings (as is the
+case for Comcast Cable, among others), it is best to use a single queue
+"besteffort" mode with wash.
+
+.SH EXAMPLES
+# tc qdisc delete root dev eth0
+.br
+# tc qdisc add root dev eth0 cake bandwidth 9500Kbit pppoe-ptm ether-vlan
+.br
+# tc -s qdisc show dev eth0
+.br
+qdisc cake 8007: root refcnt 6 bandwidth 9500Kbit diffserv3 triple-isolate rtt 100.0ms ptm overhead 34 via-ethernet total_overhead 34 hard_header_len 14
+ Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0)
+ backlog 0b 0p requeues 0
+ memory used: 0b of 4Mb
+ capacity estimate: 9500Kbit
+.br
+                 Bulk   Best Effort      Voice
+.br
+  thresh     593744bit    9500Kbit    2375Kbit
+.br
+  target        30.6ms       5.0ms       7.6ms
+.br
+  interval     125.6ms     100.0ms     102.6ms
+.br
+  pk_delay         0us         0us         0us
+.br
+  av_delay         0us         0us         0us
+.br
+  sp_delay         0us         0us         0us
+.br
+  pkts               0           0           0
+.br
+  bytes              0           0           0
+.br
+  way_inds           0           0           0
+.br
+  way_miss           0           0           0
+.br
+  way_cols           0           0           0
+.br
+  drops              0           0           0
+.br
+  marks              0           0           0
+.br
+  ack_drop           0           0           0
+.br
+  sp_flows           0           0           0
+.br
+  bk_flows           0           0           0
+.br
+  un_flows           0           0           0
+.br
+  max_len            0           0           0
+.br
+
+After some use:
+.br
+# tc -s qdisc show dev eth0
+
+qdisc cake 8007: root refcnt 6 bandwidth 9500Kbit diffserv3 triple-isolate rtt 100.0ms ptm overhead 34 via-ethernet total_overhead 34 hard_header_len 14
+ Sent 110769306 bytes 313857 pkt (dropped 18, overlimits 741791 requeues 0)
+ backlog 0b 0p requeues 0
+ memory used: 110488b of 4Mb
+ capacity estimate: 9500Kbit
+.br
+                 Bulk   Best Effort      Voice
+.br
+  thresh     593744bit    9500Kbit    2375Kbit
+.br
+  target        30.6ms       5.0ms       7.6ms
+.br
+  interval     125.6ms     100.0ms     102.6ms
+.br
+  pk_delay      16.0ms       545us        15us
+.br
+  av_delay       2.4ms       161us         3us
+.br
+  sp_delay        59us         1us         1us
+.br
+  pkts           32866      195815       85194
+.br
+  bytes        8132614    69517496    33122156
+.br
+  way_inds           0       29208           0
+.br
+  way_miss           7         173          17
+.br
+  way_cols           0           0           0
+.br
+  drops             10           7           1
+.br
+  marks            217         692         300
+.br
+  ack_drop           0           0           0
+.br
+  sp_flows           0           0           0
+.br
+  bk_flows           0           0           1
+.br
+  un_flows           0           0           0
+.br
+  max_len         3028        3012        3028
+.br
+
+.SH SEE ALSO
+.BR tc (8),
+.BR tc-codel (8),
+.BR tc-fq_codel (8),
+.BR tc-red (8)
+
+.SH AUTHORS
+Cake's principal author is Jonathan Morton, with contributions from
+Tony Ambardar, Kevin Darbyshire-Bryant, Toke Høiland-Jørgensen,
+Sebastian Moeller, Ryan Mounce, Dean Scarff, Nils Andreas Svee, and Dave Täht.
+
+This manual page was written by Loganaden Velvindron. Please report corrections
+to the Linux Networking mailing list <netdev@vger.kernel.org>.
diff --git a/tc/Makefile b/tc/Makefile
index 3716dd6a..69f50a6b 100644
--- a/tc/Makefile
+++ b/tc/Makefile
@@ -64,6 +64,7 @@ TCMODULES += em_meta.o
 TCMODULES += q_mqprio.o
 TCMODULES += q_codel.o
 TCMODULES += q_fq_codel.o
+TCMODULES += q_cake.o
 TCMODULES += q_fq.o
 TCMODULES += q_pie.o
 TCMODULES += q_hhf.o
diff --git a/tc/q_cake.c b/tc/q_cake.c
new file mode 100644
index 00000000..44cadb63
--- /dev/null
+++ b/tc/q_cake.c
@@ -0,0 +1,770 @@
+/* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */
+/*
+ * Common Applications Kept Enhanced  --  CAKE
+ *
+ *  Copyright (C) 2014-2018 Jonathan Morton <chromatix99@gmail.com>
+ *  Copyright (C) 2017-2018 Toke Høiland-Jørgensen <toke@toke.dk>
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions, and the following disclaimer,
+ *    without modification.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. The names of the authors may not be used to endorse or promote products
+ *    derived from this software without specific prior written permission.
+ *
+ * Alternatively, provided that this notice is retained in full, this
+ * software may be distributed under the terms of the GNU General
+ * Public License ("GPL") version 2, in which case the provisions of the
+ * GPL apply INSTEAD OF those given above.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH
+ * DAMAGE.
+ *
+ */
+
+#include <stddef.h>
+#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: ... cake [ bandwidth RATE | unlimited* | autorate_ingress ]\n"
+"                [ rtt TIME | datacentre | lan | metro | regional |\n"
+"                  internet* | oceanic | satellite | interplanetary ]\n"
+"                [ besteffort | diffserv8 | diffserv4 | diffserv-llt |\n"
+"                  diffserv3* ]\n"
+"                [ flowblind | srchost | dsthost | hosts | flows |\n"
+"                  dual-srchost | dual-dsthost | triple-isolate* ]\n"
+"                [ nat | nonat* ]\n"
+"                [ wash | nowash* ]\n"
+"                [ ack-filter | ack-filter-aggressive | no-ack-filter* ]\n"
+"                [ memlimit LIMIT ]\n"
+"                [ ptm | atm | noatm* ] [ overhead N | conservative | raw* ]\n"
+"                [ mpu N ] [ ingress | egress* ]\n"
+"                (* marks defaults)\n");
+}
+
+static int cake_parse_opt(struct qdisc_util *qu, int argc, char **argv,
+			  struct nlmsghdr *n, const char *dev)
+{
+	int unlimited = 0;
+	unsigned bandwidth = 0;
+	unsigned interval = 0;
+	unsigned target = 0;
+	unsigned diffserv = 0;
+	unsigned memlimit = 0;
+	int  overhead = 0;
+	bool overhead_set = false;
+	bool overhead_override = false;
+	int mpu = 0;
+	int flowmode = -1;
+	int nat = -1;
+	int atm = -1;
+	int autorate = -1;
+	int wash = -1;
+	int ingress = -1;
+	int ack_filter = -1;
+	struct rtattr *tail;
+
+	while (argc > 0) {
+		if (strcmp(*argv, "bandwidth") == 0) {
+			NEXT_ARG();
+			if (get_rate(&bandwidth, *argv)) {
+				fprintf(stderr, "Illegal \"bandwidth\"\n");
+				return -1;
+			}
+			unlimited = 0;
+			autorate = 0;
+		} else if (strcmp(*argv, "unlimited") == 0) {
+			bandwidth = 0;
+			unlimited = 1;
+			autorate = 0;
+		} else if (strcmp(*argv, "autorate_ingress") == 0) {
+			autorate = 1;
+
+		} else if (strcmp(*argv, "rtt") == 0) {
+			NEXT_ARG();
+			if (get_time(&interval, *argv)) {
+				fprintf(stderr, "Illegal \"rtt\"\n");
+				return -1;
+			}
+			target = interval / 20;
+			if(!target)
+				target = 1;
+		} else if (strcmp(*argv, "datacentre") == 0) {
+			interval = 100;
+			target   =   5;
+		} else if (strcmp(*argv, "lan") == 0) {
+			interval = 1000;
+			target   =   50;
+		} else if (strcmp(*argv, "metro") == 0) {
+			interval = 10000;
+			target   =   500;
+		} else if (strcmp(*argv, "regional") == 0) {
+			interval = 30000;
+			target    = 1500;
+		} else if (strcmp(*argv, "internet") == 0) {
+			interval = 100000;
+			target   =   5000;
+		} else if (strcmp(*argv, "oceanic") == 0) {
+			interval = 300000;
+			target   =  15000;
+		} else if (strcmp(*argv, "satellite") == 0) {
+			interval = 1000000;
+			target   =   50000;
+		} else if (strcmp(*argv, "interplanetary") == 0) {
+			interval = 1000000000;
+			target   =   50000000;
+
+		} else if (strcmp(*argv, "besteffort") == 0) {
+			diffserv = 1;
+		} else if (strcmp(*argv, "precedence") == 0) {
+			diffserv = 2;
+		} else if (strcmp(*argv, "diffserv8") == 0) {
+			diffserv = 3;
+		} else if (strcmp(*argv, "diffserv4") == 0) {
+			diffserv = 4;
+		} else if (strcmp(*argv, "diffserv") == 0) {
+			diffserv = 4;
+		} else if (strcmp(*argv, "diffserv-llt") == 0) {
+			diffserv = 5;
+		} else if (strcmp(*argv, "diffserv3") == 0) {
+			diffserv = 6;
+
+		} else if (strcmp(*argv, "nowash") == 0) {
+			wash = 0;
+		} else if (strcmp(*argv, "wash") == 0) {
+			wash = 1;
+
+		} else if (strcmp(*argv, "flowblind") == 0) {
+			flowmode = 0;
+		} else if (strcmp(*argv, "srchost") == 0) {
+			flowmode = 1;
+		} else if (strcmp(*argv, "dsthost") == 0) {
+			flowmode = 2;
+		} else if (strcmp(*argv, "hosts") == 0) {
+			flowmode = 3;
+		} else if (strcmp(*argv, "flows") == 0) {
+			flowmode = 4;
+		} else if (strcmp(*argv, "dual-srchost") == 0) {
+			flowmode = 5;
+		} else if (strcmp(*argv, "dual-dsthost") == 0) {
+			flowmode = 6;
+		} else if (strcmp(*argv, "triple-isolate") == 0) {
+			flowmode = 7;
+
+		} else if (strcmp(*argv, "nat") == 0) {
+			nat = 1;
+		} else if (strcmp(*argv, "nonat") == 0) {
+			nat = 0;
+
+		} else if (strcmp(*argv, "ptm") == 0) {
+			atm = 2;
+		} else if (strcmp(*argv, "atm") == 0) {
+			atm = 1;
+		} else if (strcmp(*argv, "noatm") == 0) {
+			atm = 0;
+
+		} else if (strcmp(*argv, "raw") == 0) {
+			atm = 0;
+			overhead = 0;
+			overhead_set = true;
+			overhead_override = true;
+		} else if (strcmp(*argv, "conservative") == 0) {
+			/*
+			 * Deliberately over-estimate overhead:
+			 * one whole ATM cell plus ATM framing.
+			 * A safe choice if the actual overhead is unknown.
+			 */
+			atm = 1;
+			overhead = 48;
+			overhead_set = true;
+
+		/* Various ADSL framing schemes, all over ATM cells */
+		} else if (strcmp(*argv, "ipoa-vcmux") == 0) {
+			atm = 1;
+			overhead += 8;
+			overhead_set = true;
+		} else if (strcmp(*argv, "ipoa-llcsnap") == 0) {
+			atm = 1;
+			overhead += 16;
+			overhead_set = true;
+		} else if (strcmp(*argv, "bridged-vcmux") == 0) {
+			atm = 1;
+			overhead += 24;
+			overhead_set = true;
+		} else if (strcmp(*argv, "bridged-llcsnap") == 0) {
+			atm = 1;
+			overhead += 32;
+			overhead_set = true;
+		} else if (strcmp(*argv, "pppoa-vcmux") == 0) {
+			atm = 1;
+			overhead += 10;
+			overhead_set = true;
+		} else if (strcmp(*argv, "pppoa-llc") == 0) {
+			atm = 1;
+			overhead += 14;
+			overhead_set = true;
+		} else if (strcmp(*argv, "pppoe-vcmux") == 0) {
+			atm = 1;
+			overhead += 32;
+			overhead_set = true;
+		} else if (strcmp(*argv, "pppoe-llcsnap") == 0) {
+			atm = 1;
+			overhead += 40;
+			overhead_set = true;
+
+		/* Typical VDSL2 framing schemes, both over PTM */
+		/* PTM has 64b/65b coding which absorbs some bandwidth */
+		} else if (strcmp(*argv, "pppoe-ptm") == 0) {
+			/* 2B PPP + 6B PPPoE + 6B dest MAC + 6B src MAC
+			 * + 2B ethertype + 4B Frame Check Sequence
+			 * + 1B Start of Frame (S) + 1B End of Frame (Ck)
+			 * + 2B TC-CRC (PTM-FCS) = 30B
+			 */
+			atm = 2;
+			overhead += 30;
+			overhead_set = true;
+		} else if (strcmp(*argv, "bridged-ptm") == 0) {
+			/* 6B dest MAC + 6B src MAC + 2B ethertype
+			 * + 4B Frame Check Sequence
+			 * + 1B Start of Frame (S) + 1B End of Frame (Ck)
+			 * + 2B TC-CRC (PTM-FCS) = 22B
+			 */
+			atm = 2;
+			overhead += 22;
+			overhead_set = true;
+
+		} else if (strcmp(*argv, "via-ethernet") == 0) {
+			/*
+			 * We used to use this flag to manually compensate for
+			 * Linux including the Ethernet header on Ethernet-type
+			 * interfaces, but not on IP-type interfaces.
+			 *
+			 * It is no longer needed, because Cake now adjusts for
+			 * that automatically, and is thus ignored.
+			 *
+			 * It would be deleted entirely, but it appears in the
+			 * stats output when the automatic compensation is
+			 * active.
+			 */
+
+		} else if (strcmp(*argv, "ethernet") == 0) {
+			/* ethernet pre-amble & interframe gap & FCS
+			 * you may need to add vlan tag */
+			overhead += 38;
+			overhead_set = true;
+			mpu = 84;
+
+		/* Additional Ethernet-related overhead used by some ISPs */
+		} else if (strcmp(*argv, "ether-vlan") == 0) {
+			/* 802.1q VLAN tag - may be repeated */
+			overhead += 4;
+			overhead_set = true;
+
+		/*
+		 * DOCSIS cable shapers account for Ethernet frame with FCS,
+		 * but not interframe gap or preamble.
+		 */
+		} else if (strcmp(*argv, "docsis") == 0) {
+			atm = 0;
+			overhead += 18;
+			overhead_set = true;
+			mpu = 64;
+
+		} else if (strcmp(*argv, "overhead") == 0) {
+			char* p = NULL;
+			NEXT_ARG();
+			overhead = strtol(*argv, &p, 10);
+			if(!p || *p || !*argv || overhead < -64 || overhead > 256) {
+				fprintf(stderr, "Illegal \"overhead\", valid range is -64 to 256\\n");
+				return -1;
+			}
+			overhead_set = true;
+
+		} else if (strcmp(*argv, "mpu") == 0) {
+			char* p = NULL;
+			NEXT_ARG();
+			mpu = strtol(*argv, &p, 10);
+			if(!p || *p || !*argv || mpu < 0 || mpu > 256) {
+				fprintf(stderr, "Illegal \"mpu\", valid range is 0 to 256\\n");
+				return -1;
+			}
+
+		} else if (strcmp(*argv, "ingress") == 0) {
+			ingress = 1;
+		} else if (strcmp(*argv, "egress") == 0) {
+			ingress = 0;
+
+		} else if (strcmp(*argv, "no-ack-filter") == 0) {
+			ack_filter = 0;
+		} else if (strcmp(*argv, "ack-filter") == 0) {
+			ack_filter = 0x0200;
+		} else if (strcmp(*argv, "ack-filter-aggressive") == 0) {
+			ack_filter = 0x0600;
+
+		} else if (strcmp(*argv, "memlimit") == 0) {
+			NEXT_ARG();
+			if(get_size(&memlimit, *argv)) {
+				fprintf(stderr, "Illegal value for \"memlimit\": \"%s\"\n", *argv);
+				return -1;
+			}
+
+		} else if (strcmp(*argv, "help") == 0) {
+			explain();
+			return -1;
+		} else {
+			fprintf(stderr, "What is \"%s\"?\n", *argv);
+			explain();
+			return -1;
+		}
+		argc--; argv++;
+	}
+
+	tail = NLMSG_TAIL(n);
+	addattr_l(n, 1024, TCA_OPTIONS, NULL, 0);
+	if (bandwidth || unlimited)
+		addattr_l(n, 1024, TCA_CAKE_BASE_RATE, &bandwidth, sizeof(bandwidth));
+	if (diffserv)
+		addattr_l(n, 1024, TCA_CAKE_DIFFSERV_MODE, &diffserv, sizeof(diffserv));
+	if (atm != -1)
+		addattr_l(n, 1024, TCA_CAKE_ATM, &atm, sizeof(atm));
+	if (flowmode != -1)
+		addattr_l(n, 1024, TCA_CAKE_FLOW_MODE, &flowmode, sizeof(flowmode));
+	if (overhead_set)
+		addattr_l(n, 1024, TCA_CAKE_OVERHEAD, &overhead, sizeof(overhead));
+	if (overhead_override) {
+		unsigned zero = 0;
+		addattr_l(n, 1024, TCA_CAKE_RAW, &zero, sizeof(zero));
+	}
+	if (mpu > 0)
+		addattr_l(n, 1024, TCA_CAKE_MPU, &mpu, sizeof(mpu));
+	if (interval)
+		addattr_l(n, 1024, TCA_CAKE_RTT, &interval, sizeof(interval));
+	if (target)
+		addattr_l(n, 1024, TCA_CAKE_TARGET, &target, sizeof(target));
+	if (autorate != -1)
+		addattr_l(n, 1024, TCA_CAKE_AUTORATE, &autorate, sizeof(autorate));
+	if (memlimit)
+		addattr_l(n, 1024, TCA_CAKE_MEMORY, &memlimit, sizeof(memlimit));
+	if (nat != -1)
+		addattr_l(n, 1024, TCA_CAKE_NAT, &nat, sizeof(nat));
+	if (wash != -1)
+		addattr_l(n, 1024, TCA_CAKE_WASH, &wash, sizeof(wash));
+	if (ingress != -1)
+		addattr_l(n, 1024, TCA_CAKE_INGRESS, &ingress, sizeof(ingress));
+	if (ack_filter != -1)
+		addattr_l(n, 1024, TCA_CAKE_ACK_FILTER, &ack_filter, sizeof(ack_filter));
+
+	tail->rta_len = (void *) NLMSG_TAIL(n) - (void *) tail;
+	return 0;
+}
+
+
+static int cake_print_opt(struct qdisc_util *qu, FILE *f, struct rtattr *opt)
+{
+	struct rtattr *tb[TCA_CAKE_MAX + 1];
+	unsigned bandwidth = 0;
+	unsigned diffserv = 0;
+	unsigned flowmode = 0;
+	unsigned interval = 0;
+	unsigned memlimit = 0;
+	int overhead = 0;
+	int raw = 0;
+	int mpu = 0;
+	int atm = 0;
+	int nat = 0;
+	int autorate = 0;
+	int wash = 0;
+	int ingress = 0;
+	int ack_filter = 0;
+	SPRINT_BUF(b1);
+	SPRINT_BUF(b2);
+
+	if (opt == NULL)
+		return 0;
+
+	parse_rtattr_nested(tb, TCA_CAKE_MAX, opt);
+
+	if (tb[TCA_CAKE_BASE_RATE] &&
+	    RTA_PAYLOAD(tb[TCA_CAKE_BASE_RATE]) >= sizeof(__u32)) {
+		bandwidth = rta_getattr_u32(tb[TCA_CAKE_BASE_RATE]);
+		if(bandwidth) {
+			print_uint(PRINT_JSON, "bandwidth", NULL, bandwidth);
+			print_string(PRINT_FP, NULL, "bandwidth %s ", sprint_rate(bandwidth, b1));
+		} else
+			print_string(PRINT_ANY, "bandwidth", "bandwidth %s ", "unlimited");
+	}
+	if (tb[TCA_CAKE_AUTORATE] &&
+		RTA_PAYLOAD(tb[TCA_CAKE_AUTORATE]) >= sizeof(__u32)) {
+		autorate = rta_getattr_u32(tb[TCA_CAKE_AUTORATE]);
+		if(autorate == 1)
+			print_string(PRINT_ANY, "autorate", "autorate_%s ", "ingress");
+		else if(autorate)
+			print_string(PRINT_ANY, "autorate", "(?autorate?) ", "unknown");
+	}
+	if (tb[TCA_CAKE_DIFFSERV_MODE] &&
+	    RTA_PAYLOAD(tb[TCA_CAKE_DIFFSERV_MODE]) >= sizeof(__u32)) {
+		diffserv = rta_getattr_u32(tb[TCA_CAKE_DIFFSERV_MODE]);
+		switch(diffserv) {
+		case 1:
+			print_string(PRINT_ANY, "diffserv", "%s ", "besteffort");
+			break;
+		case 2:
+			print_string(PRINT_ANY, "diffserv", "%s ", "precedence");
+			break;
+		case 3:
+			print_string(PRINT_ANY, "diffserv", "%s ", "diffserv8");
+			break;
+		case 4:
+			print_string(PRINT_ANY, "diffserv", "%s ", "diffserv4");
+			break;
+		case 5:
+			print_string(PRINT_ANY, "diffserv", "%s ", "diffserv-llt");
+			break;
+		case 6:
+			print_string(PRINT_ANY, "diffserv", "%s ", "diffserv3");
+			break;
+		default:
+			print_string(PRINT_ANY, "diffserv", "(?diffserv?) ", "unknown");
+			break;
+		};
+	}
+	if (tb[TCA_CAKE_FLOW_MODE] &&
+	    RTA_PAYLOAD(tb[TCA_CAKE_FLOW_MODE]) >= sizeof(__u32)) {
+		flowmode = rta_getattr_u32(tb[TCA_CAKE_FLOW_MODE]);
+		nat = !!(flowmode & 64);
+		flowmode &= ~64;
+		switch(flowmode) {
+		case 0:
+			print_string(PRINT_ANY, "flowmode", "%s ", "flowblind");
+			break;
+		case 1:
+			print_string(PRINT_ANY, "flowmode", "%s ", "srchost");
+			break;
+		case 2:
+			print_string(PRINT_ANY, "flowmode", "%s ", "dsthost");
+			break;
+		case 3:
+			print_string(PRINT_ANY, "flowmode", "%s ", "hosts");
+			break;
+		case 4:
+			print_string(PRINT_ANY, "flowmode", "%s ", "flows");
+			break;
+		case 5:
+			print_string(PRINT_ANY, "flowmode", "%s ", "dual-srchost");
+			break;
+		case 6:
+			print_string(PRINT_ANY, "flowmode", "%s ", "dual-dsthost");
+			break;
+		case 7:
+			print_string(PRINT_ANY, "flowmode", "%s ", "triple-isolate");
+			break;
+		default:
+			print_string(PRINT_ANY, "flowmode", "(?flowmode?) ", "unknown");
+			break;
+		};
+
+		if(nat)
+			print_string(PRINT_FP, NULL, "nat ", NULL);
+		print_bool(PRINT_JSON, "nat", NULL, nat);
+	}
+	if (tb[TCA_CAKE_WASH] &&
+	    RTA_PAYLOAD(tb[TCA_CAKE_WASH]) >= sizeof(__u32)) {
+		wash = rta_getattr_u32(tb[TCA_CAKE_WASH]);
+	}
+	if (tb[TCA_CAKE_ATM] &&
+	    RTA_PAYLOAD(tb[TCA_CAKE_ATM]) >= sizeof(__u32)) {
+		atm = rta_getattr_u32(tb[TCA_CAKE_ATM]);
+	}
+	if (tb[TCA_CAKE_OVERHEAD] &&
+	    RTA_PAYLOAD(tb[TCA_CAKE_OVERHEAD]) >= sizeof(__u32)) {
+		overhead = rta_getattr_u32(tb[TCA_CAKE_OVERHEAD]);
+	}
+	if (tb[TCA_CAKE_MPU] &&
+	    RTA_PAYLOAD(tb[TCA_CAKE_MPU]) >= sizeof(__u32)) {
+		mpu = rta_getattr_u32(tb[TCA_CAKE_MPU]);
+	}
+	if (tb[TCA_CAKE_INGRESS] &&
+	    RTA_PAYLOAD(tb[TCA_CAKE_INGRESS]) >= sizeof(__u32)) {
+		ingress = rta_getattr_u32(tb[TCA_CAKE_INGRESS]);
+	}
+	if (tb[TCA_CAKE_ACK_FILTER] &&
+	    RTA_PAYLOAD(tb[TCA_CAKE_ACK_FILTER]) >= sizeof(__u32)) {
+		ack_filter = rta_getattr_u32(tb[TCA_CAKE_ACK_FILTER]);
+	}
+	if (tb[TCA_CAKE_RAW]) {
+		raw = 1;
+	}
+	if (tb[TCA_CAKE_RTT] &&
+	    RTA_PAYLOAD(tb[TCA_CAKE_RTT]) >= sizeof(__u32)) {
+		interval = rta_getattr_u32(tb[TCA_CAKE_RTT]);
+	}
+
+	if (wash)
+		print_string(PRINT_FP, NULL, "wash ", NULL);
+	print_bool(PRINT_JSON, "wash", NULL, wash);
+
+	if (ingress)
+		print_string(PRINT_FP, NULL, "ingress ", NULL);
+	print_bool(PRINT_JSON, "ingress", NULL, ingress);
+
+	if (ack_filter == 0x0600)
+		print_string(PRINT_ANY, "ack-filter", "ack-filter-%s ", "aggressive");
+	else if (ack_filter)
+		print_string(PRINT_ANY, "ack-filter", "ack-filter ", "enabled");
+	else
+		print_string(PRINT_JSON, "ack-filter", NULL, "disabled");
+
+	if (interval)
+		print_string(PRINT_FP, NULL, "rtt %s ", sprint_time(interval, b2));
+	print_uint(PRINT_JSON, "rtt", NULL, interval);
+
+	if (raw)
+		print_string(PRINT_FP, NULL, "raw ", NULL);
+	print_bool(PRINT_JSON, "raw", NULL, raw);
+
+	if (atm == 1)
+		print_string(PRINT_ANY, "atm", "%s ", "atm");
+	else if (atm == 2)
+		print_string(PRINT_ANY, "atm", "%s ", "ptm");
+	else if (!raw)
+		print_string(PRINT_ANY, "atm", "%s ", "noatm");
+
+	print_uint(PRINT_ANY, "overhead", "overhead %d ", overhead);
+
+	if (mpu)
+		print_uint(PRINT_ANY, "mpu", "mpu %d ", mpu);
+
+	if (memlimit) {
+		print_uint(PRINT_JSON, "memlimit", NULL, memlimit);
+		print_string(PRINT_FP, NULL, "memlimit %s", sprint_size(memlimit, b1));
+	}
+
+	return 0;
+}
+
+#define FOR_EACH_TIN(xstats, tst, i)				\
+	for(tst = xstats->tin_stats, i = 0;			\
+	i < xstats->tin_cnt;						\
+	    i++, tst = ((void *) xstats->tin_stats) + xstats->tin_stats_size * i)
+
+static void cake_print_json_tin(struct tc_cake_tin_stats *tst)
+{
+	open_json_object(NULL);
+	print_uint(PRINT_JSON, "threshold_rate", NULL, tst->threshold_rate);
+	print_uint(PRINT_JSON, "target", NULL, tst->target_us);
+	print_uint(PRINT_JSON, "interval", NULL, tst->interval_us);
+	print_uint(PRINT_JSON, "peak_delay", NULL, tst->peak_delay_us);
+	print_uint(PRINT_JSON, "average_delay", NULL, tst->avge_delay_us);
+	print_uint(PRINT_JSON, "base_delay", NULL, tst->base_delay_us);
+	print_uint(PRINT_JSON, "sent_packets", NULL, tst->sent.packets);
+	print_uint(PRINT_JSON, "sent_bytes", NULL, tst->sent.bytes);
+	print_uint(PRINT_JSON, "way_indirect_hits", NULL, tst->way_indirect_hits);
+	print_uint(PRINT_JSON, "way_misses", NULL, tst->way_misses);
+	print_uint(PRINT_JSON, "way_collisions", NULL, tst->way_collisions);
+	print_uint(PRINT_JSON, "drops", NULL, tst->dropped.packets);
+	print_uint(PRINT_JSON, "ecn_mark", NULL, tst->ecn_marked.packets);
+	print_uint(PRINT_JSON, "ack_drops", NULL, tst->ack_drops.packets);
+	print_uint(PRINT_JSON, "sparse_flows", NULL, tst->sparse_flows);
+	print_uint(PRINT_JSON, "bulk_flows", NULL, tst->bulk_flows);
+	print_uint(PRINT_JSON, "unresponsive_flows", NULL, tst->unresponse_flows);
+	print_uint(PRINT_JSON, "max_pkt_len", NULL, tst->max_skblen);
+	close_json_object();
+}
+
+static int cake_print_xstats(struct qdisc_util *qu, FILE *f,
+			     struct rtattr *xstats)
+{
+	struct tc_cake_xstats     *stnc;
+	struct tc_cake_tin_stats  *tst;
+	SPRINT_BUF(b1);
+	int i;
+
+	if (xstats == NULL)
+		return 0;
+
+	if (RTA_PAYLOAD(xstats) < sizeof(*stnc))
+		return -1;
+
+	stnc = RTA_DATA(xstats);
+
+	if (stnc->version < 0x101 ||
+	    RTA_PAYLOAD(xstats) < (sizeof(struct tc_cake_xstats) +
+				    stnc->tin_stats_size * stnc->tin_cnt))
+		return -1;
+
+	print_uint(PRINT_JSON, "memory_used", NULL, stnc->memory_used);
+	print_uint(PRINT_JSON, "memory_limit", NULL, stnc->memory_limit);
+	print_uint(PRINT_JSON, "capacity_estimate", NULL, stnc->capacity_estimate);
+
+	print_string(PRINT_FP, NULL, " memory used: %s",
+		sprint_size(stnc->memory_used, b1));
+	print_string(PRINT_FP, NULL, " of %s\n",
+		sprint_size(stnc->memory_limit, b1));
+	print_string(PRINT_FP, NULL, " capacity estimate: %s\n",
+		sprint_rate(stnc->capacity_estimate, b1));
+
+	print_uint(PRINT_ANY, "min_transport_size", " min/max transport layer size: %10u",
+		stnc->min_trnlen);
+	print_uint(PRINT_ANY, "max_transport_size", " /%8u\n", stnc->max_trnlen);
+	print_uint(PRINT_ANY, "min_adj_size", " min/max overhead-adjusted size: %8u",
+		stnc->min_adjlen);
+	print_uint(PRINT_ANY, "max_adj_size", " /%8u\n", stnc->max_adjlen);
+	print_uint(PRINT_ANY, "avg_hdr_offset", " average transport hdr offset: %10u\n\n",
+		stnc->avg_trnoff);
+
+	if (is_json_context()) {
+		open_json_array(PRINT_JSON, "tins");
+		FOR_EACH_TIN(stnc, tst, i)
+			cake_print_json_tin(tst);
+		close_json_array(PRINT_JSON, NULL);
+		return 0;
+	}
+
+
+	switch(stnc->tin_cnt) {
+	case 3:
+		fprintf(f, "                   Bulk  Best Effort        Voice\n");
+		break;
+
+	case 4:
+		fprintf(f, "                   Bulk  Best Effort        Video        Voice\n");
+		break;
+
+	case 5:
+		fprintf(f, "               Low Loss  Best Effort    Low Delay         Bulk  Net Control\n");
+		break;
+
+	default:
+		fprintf(f, "          ");
+		for(i=0; i < stnc->tin_cnt; i++)
+			fprintf(f, "        Tin %u", i);
+		fprintf(f, "\n");
+	};
+
+	fprintf(f, "  thresh  ");
+	FOR_EACH_TIN(stnc, tst, i)
+		fprintf(f, " %12s", sprint_rate(tst->threshold_rate, b1));
+	fprintf(f, "\n");
+
+	fprintf(f, "  target  ");
+	FOR_EACH_TIN(stnc, tst, i)
+		fprintf(f, " %12s", sprint_time(tst->target_us, b1));
+	fprintf(f, "\n");
+
+	fprintf(f, "  interval");
+	FOR_EACH_TIN(stnc, tst, i)
+		fprintf(f, " %12s", sprint_time(tst->interval_us, b1));
+	fprintf(f, "\n");
+
+	fprintf(f, "  pk_delay");
+	FOR_EACH_TIN(stnc, tst, i)
+		fprintf(f, " %12s", sprint_time(tst->peak_delay_us, b1));
+	fprintf(f, "\n");
+
+	fprintf(f, "  av_delay");
+	FOR_EACH_TIN(stnc, tst, i)
+		fprintf(f, " %12s", sprint_time(tst->avge_delay_us, b1));
+	fprintf(f, "\n");
+
+	fprintf(f, "  sp_delay");
+	FOR_EACH_TIN(stnc, tst, i)
+		fprintf(f, " %12s", sprint_time(tst->base_delay_us, b1));
+	fprintf(f, "\n");
+
+	fprintf(f, "  pkts    ");
+	FOR_EACH_TIN(stnc, tst, i)
+		fprintf(f, " %12u", tst->sent.packets);
+	fprintf(f, "\n");
+
+	fprintf(f, "  bytes   ");
+	FOR_EACH_TIN(stnc, tst, i)
+		fprintf(f, " %12llu", tst->sent.bytes);
+	fprintf(f, "\n");
+
+	fprintf(f, "  way_inds");
+	FOR_EACH_TIN(stnc, tst, i)
+		fprintf(f, " %12u", tst->way_indirect_hits);
+	fprintf(f, "\n");
+
+	fprintf(f, "  way_miss");
+	FOR_EACH_TIN(stnc, tst, i)
+		fprintf(f, " %12u", tst->way_misses);
+	fprintf(f, "\n");
+
+	fprintf(f, "  way_cols");
+	FOR_EACH_TIN(stnc, tst, i)
+		fprintf(f, " %12u", tst->way_collisions);
+	fprintf(f, "\n");
+
+	fprintf(f, "  drops   ");
+	FOR_EACH_TIN(stnc, tst, i)
+		fprintf(f, " %12u", tst->dropped.packets);
+	fprintf(f, "\n");
+
+	fprintf(f, "  marks   ");
+	FOR_EACH_TIN(stnc, tst, i)
+		fprintf(f, " %12u", tst->ecn_marked.packets);
+	fprintf(f, "\n");
+
+	fprintf(f, "  ack_drop");
+	FOR_EACH_TIN(stnc, tst, i)
+		fprintf(f, " %12u", tst->ack_drops.packets);
+	fprintf(f, "\n");
+
+	fprintf(f, "  sp_flows");
+	FOR_EACH_TIN(stnc, tst, i)
+		fprintf(f, " %12u", tst->sparse_flows);
+	fprintf(f, "\n");
+
+	fprintf(f, "  bk_flows");
+	FOR_EACH_TIN(stnc, tst, i)
+		fprintf(f, " %12u", tst->bulk_flows);
+	fprintf(f, "\n");
+
+	fprintf(f, "  un_flows");
+	FOR_EACH_TIN(stnc, tst, i)
+		fprintf(f, " %12u", tst->unresponse_flows);
+	fprintf(f, "\n");
+
+	fprintf(f, "  max_len ");
+	FOR_EACH_TIN(stnc, tst, i)
+		fprintf(f, " %12u", tst->max_skblen);
+	fprintf(f, "\n");
+
+	return 0;
+}
+
+struct qdisc_util cake_qdisc_util = {
+	.id		= "cake",
+	.parse_qopt	= cake_parse_opt,
+	.print_qopt	= cake_print_opt,
+	.print_xstats	= cake_print_xstats,
+};