Merge branch 'net-sched-add-Flow-Queue-PIE-packet-scheduler'

Gautam Ramakrishnan says:

====================
net: sched: add Flow Queue PIE packet scheduler

Flow Queue PIE packet scheduler

This patch series implements the Flow Queue Proportional
Integral controller Enhanced (FQ-PIE) active queue
Management algorithm. It is an enhancement over the PIE
algorithm. It integrates the PIE aqm with a deficit round robin
scheme.

FQ-PIE is implemented over the latest version of PIE which
uses timestamps to calculate queue delay with an additional
option of using average dequeue rate to calculate the queue
delay. This patch also adds a memory limit of all the packets
across all queues to a default value of 32Mb.

 - Patch #1
   - Creates pie.h and moves all small functions and structures
     common to PIE and FQ-PIE here. The functions are all made
     inline.
 - Patch #2 - #8
   - Addresses code formatting, indentation, comment changes
     and rearrangement of structure members.
 - Patch #9
   - Refactors sch_pie.c by changing arguments to
     calculate_probability(), [pie_]drop_early() and
     pie_process_dequeue() to make it generic enough to
     be used by sch_fq_pie.c. These functions are exported
     to be used by sch_fq_pie.c.
 - Patch #10
   - Adds the FQ-PIE Qdisc.

For more information:
https://tools.ietf.org/html/rfc8033

Changes from v6 to v7
 - Call tcf_block_put() when destroying the Qdisc as suggested
   by Jakub Kicinski.

Changes from v5 to v6
 - Rearranged struct members according to their access pattern
   and to remove holes.

Changes from v4 to v5
 - This patch series breaks down patch 1 of v4 into
   separate logical commits as suggested by David Miller.

Changes from v3 to v4
 - Used non deprecated version of nla_parse_nested
 - Used SZ_32M macro
 - Removed an unused variable
 - Code cleanup
 All suggested by Jakub and Toke.

Changes from v2 to v3
 - Exported drop_early, pie_process_dequeue and
   calculate_probability functions from sch_pie as
   suggested by Stephen Hemminger.

Changes from v1 ( and RFC patch) to v2
 - Added timestamp to calculate queue delay as recommended
   by Dave Taht
 - Packet memory limit implemented as recommended by Toke.
 - Added external classifier as recommended by Toke.
 - Used NET_XMIT_CN instead of NET_XMIT_DROP as the return
   value in the fq_pie_qdisc_enqueue function.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

include/net/pie.h

+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef __NET_SCHED_PIE_H
+#define __NET_SCHED_PIE_H
+
+#include <linux/ktime.h>
+#include <linux/skbuff.h>
+#include <linux/types.h>
+#include <net/inet_ecn.h>
+#include <net/pkt_sched.h>
+
+#define MAX_PROB	U64_MAX
+#define DTIME_INVALID	U64_MAX
+#define QUEUE_THRESHOLD	16384
+#define DQCOUNT_INVALID	-1
+#define PIE_SCALE	8
+
+/**
+ * struct pie_params - contains pie parameters
+ * @target:		target delay in pschedtime
+ * @tudpate:		interval at which drop probability is calculated
+ * @limit:		total number of packets that can be in the queue
+ * @alpha:		parameter to control drop probability
+ * @beta:		parameter to control drop probability
+ * @ecn:		is ECN marking of packets enabled
+ * @bytemode:		is drop probability scaled based on pkt size
+ * @dq_rate_estimator:	is Little's law used for qdelay calculation
+ */
+struct pie_params {
+	psched_time_t target;
+	u32 tupdate;
+	u32 limit;
+	u32 alpha;
+	u32 beta;
+	u8 ecn;
+	u8 bytemode;
+	u8 dq_rate_estimator;
+};
+
+/**
+ * struct pie_vars - contains pie variables
+ * @qdelay:			current queue delay
+ * @qdelay_old:			queue delay in previous qdelay calculation
+ * @burst_time:			burst time allowance
+ * @dq_tstamp:			timestamp at which dq rate was last calculated
+ * @prob:			drop probability
+ * @accu_prob:			accumulated drop probability
+ * @dq_count:			number of bytes dequeued in a measurement cycle
+ * @avg_dq_rate:		calculated average dq rate
+ * @qlen_old:			queue length during previous qdelay calculation
+ * @accu_prob_overflows:	number of times accu_prob overflows
+ */
+struct pie_vars {
+	psched_time_t qdelay;
+	psched_time_t qdelay_old;
+	psched_time_t burst_time;
+	psched_time_t dq_tstamp;
+	u64 prob;
+	u64 accu_prob;
+	u64 dq_count;
+	u32 avg_dq_rate;
+	u32 qlen_old;
+	u8 accu_prob_overflows;
+};
+
+/**
+ * struct pie_stats - contains pie stats
+ * @packets_in:	total number of packets enqueued
+ * @dropped:	packets dropped due to pie action
+ * @overlimit:	packets dropped due to lack of space in queue
+ * @ecn_mark:	packets marked with ECN
+ * @maxq:	maximum queue size
+ */
+struct pie_stats {
+	u32 packets_in;
+	u32 dropped;
+	u32 overlimit;
+	u32 ecn_mark;
+	u32 maxq;
+};
+
+/**
+ * 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)
+{
+	params->target = PSCHED_NS2TICKS(15 * NSEC_PER_MSEC);	/* 15 ms */
+	params->tupdate = usecs_to_jiffies(15 * USEC_PER_MSEC);	/* 15 ms */
+	params->limit = 1000;
+	params->alpha = 2;
+	params->beta = 20;
+	params->ecn = false;
+	params->bytemode = false;
+	params->dq_rate_estimator = false;
+}
+
+static inline void pie_vars_init(struct pie_vars *vars)
+{
+	vars->burst_time = PSCHED_NS2TICKS(150 * NSEC_PER_MSEC); /* 150 ms */
+	vars->dq_tstamp = DTIME_INVALID;
+	vars->accu_prob = 0;
+	vars->dq_count = DQCOUNT_INVALID;
+	vars->avg_dq_rate = 0;
+	vars->accu_prob_overflows = 0;
+}
+
+static inline struct pie_skb_cb *get_pie_cb(const struct sk_buff *skb)
+{
+	qdisc_cb_private_validate(skb, sizeof(struct pie_skb_cb));
+	return (struct pie_skb_cb *)qdisc_skb_cb(skb)->data;
+}
+
+static inline psched_time_t pie_get_enqueue_time(const struct sk_buff *skb)
+{
+	return get_pie_cb(skb)->enqueue_time;
+}
+
+static inline void pie_set_enqueue_time(struct sk_buff *skb)
+{
+	get_pie_cb(skb)->enqueue_time = psched_get_time();
+}
+
+bool pie_drop_early(struct Qdisc *sch, struct pie_params *params,
+		    struct pie_vars *vars, u32 qlen, u32 packet_size);
+
+void pie_process_dequeue(struct sk_buff *skb, struct pie_params *params,
+			 struct pie_vars *vars, u32 qlen);
+
+void pie_calculate_probability(struct pie_params *params, struct pie_vars *vars,
+			       u32 qlen);
+
+#endif

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