net: sched: add Flow Queue PIE packet scheduler

Principles:
  - Packets are classified on flows.
  - This is a Stochastic model (as we use a hash, several flows might
                                be hashed to the same slot)
  - Each flow has a PIE managed queue.
  - Flows are linked onto two (Round Robin) lists,
    so that new flows have priority on old ones.
  - For a given flow, packets are not reordered.
  - Drops during enqueue only.
  - ECN capability is off by default.
  - ECN threshold (if ECN is enabled) is at 10% by default.
  - Uses timestamps to calculate queue delay by default.

Usage:
tc qdisc ... fq_pie [ limit PACKETS ] [ flows NUMBER ]
                    [ target TIME ] [ tupdate TIME ]
                    [ alpha NUMBER ] [ beta NUMBER ]
                    [ quantum BYTES ] [ memory_limit BYTES ]
                    [ ecnprob PERCENTAGE ] [ [no]ecn ]
                    [ [no]bytemode ] [ [no_]dq_rate_estimator ]

defaults:
  limit: 10240 packets, flows: 1024
  target: 15 ms, tupdate: 15 ms (in jiffies)
  alpha: 1/8, beta : 5/4
  quantum: device MTU, memory_limit: 32 Mb
  ecnprob: 10%, ecn: off
  bytemode: off, dq_rate_estimator: off

Signed-off-by: Mohit P. Tahiliani <[email protected]>
Signed-off-by: Sachin D. Patil <[email protected]>
Signed-off-by: V. Saicharan <[email protected]>
Signed-off-by: Mohit Bhasi <[email protected]>
Signed-off-by: Leslie Monis <[email protected]>
Signed-off-by: Gautam Ramakrishnan <[email protected]>
Signed-off-by: David S. Miller <[email protected]>

Author: mohittahiliani

include/net/pie.h

@@ -81,9 +81,11 @@ struct pie_stats {
 /**
  * struct pie_skb_cb - contains private skb vars
  * @enqueue_time:	timestamp when the packet is enqueued
+ * @mem_usage:		size of the skb during enqueue
  */
 struct pie_skb_cb {
 	psched_time_t enqueue_time;
+	u32 mem_usage;
 };
 
 static inline void pie_params_init(struct pie_params *params)

include/uapi/linux/pkt_sched.h

@@ -971,6 +971,37 @@ struct tc_pie_xstats {
 	__u32 ecn_mark;			/* packets marked with ecn*/
 };
 
+/* FQ PIE */
+enum {
+	TCA_FQ_PIE_UNSPEC,
+	TCA_FQ_PIE_LIMIT,
+	TCA_FQ_PIE_FLOWS,
+	TCA_FQ_PIE_TARGET,
+	TCA_FQ_PIE_TUPDATE,
+	TCA_FQ_PIE_ALPHA,
+	TCA_FQ_PIE_BETA,
+	TCA_FQ_PIE_QUANTUM,
+	TCA_FQ_PIE_MEMORY_LIMIT,
+	TCA_FQ_PIE_ECN_PROB,
+	TCA_FQ_PIE_ECN,
+	TCA_FQ_PIE_BYTEMODE,
+	TCA_FQ_PIE_DQ_RATE_ESTIMATOR,
+	__TCA_FQ_PIE_MAX
+};
+#define TCA_FQ_PIE_MAX   (__TCA_FQ_PIE_MAX - 1)
+
+struct tc_fq_pie_xstats {
+	__u32 packets_in;	/* total number of packets enqueued */
+	__u32 dropped;		/* packets dropped due to fq_pie_action */
+	__u32 overlimit;	/* dropped due to lack of space in queue */
+	__u32 overmemory;	/* dropped due to lack of memory in queue */
+	__u32 ecn_mark;		/* packets marked with ecn */
+	__u32 new_flow_count;	/* count of new flows created by packets */
+	__u32 new_flows_len;	/* count of flows in new list */
+	__u32 old_flows_len;	/* count of flows in old list */
+	__u32 memory_usage;	/* total memory across all queues */
+};
+
 /* CBS */
 struct tc_cbs_qopt {
 	__u8 offload;

net/sched/Kconfig

@@ -366,6 +366,19 @@ config NET_SCH_PIE
 
 	  If unsure, say N.
 
+config NET_SCH_FQ_PIE
+	depends on NET_SCH_PIE
+	tristate "Flow Queue Proportional Integral controller Enhanced (FQ-PIE)"
+	help
+	  Say Y here if you want to use the Flow Queue Proportional Integral
+	  controller Enhanced (FQ-PIE) packet scheduling algorithm.
+	  For more information, please see https://tools.ietf.org/html/rfc8033
+
+	  To compile this driver as a module, choose M here: the module
+	  will be called sch_fq_pie.
+
+	  If unsure, say N.
+
 config NET_SCH_INGRESS
 	tristate "Ingress/classifier-action Qdisc"
 	depends on NET_CLS_ACT

net/sched/Makefile

@@ -59,6 +59,7 @@ obj-$(CONFIG_NET_SCH_CAKE)	+= sch_cake.o
 obj-$(CONFIG_NET_SCH_FQ)	+= sch_fq.o
 obj-$(CONFIG_NET_SCH_HHF)	+= sch_hhf.o
 obj-$(CONFIG_NET_SCH_PIE)	+= sch_pie.o
+obj-$(CONFIG_NET_SCH_FQ_PIE)	+= sch_fq_pie.o
 obj-$(CONFIG_NET_SCH_CBS)	+= sch_cbs.o
 obj-$(CONFIG_NET_SCH_ETF)	+= sch_etf.o
 obj-$(CONFIG_NET_SCH_TAPRIO)	+= sch_taprio.o