Commit 8aad37d1 authored by Jakub Kicinski's avatar Jakub Kicinski
Browse files

Merge branch 'dualpi2-patch' 

Chia-Yu Chang says:

====================
DUALPI2 patch

This patch serise adds DualPI Improved with a Square (DualPI2) with
following features:
 * Supports congestion controls that comply with the Prague requirements
   in RFC9331 (e.g. TCP-Prague)
 * Coupled dual-queue that separates the L4S traffic in a low latency
   queue (L-queue), without harming remaining traffic that is scheduled
   in classic queue (C-queue) due to congestion-coupling using PI2
   as defined in RFC9332
 * Configurable overload strategies
 * Use of sojourn time to reliably estimate queue delay
 * Supports ECN L4S-identifier (IP.ECN==0b*1) to classify traffic into
   respective queues

For more details of DualPI2, please refer IETF RFC9332
(https://datatracker.ietf.org/doc/html/rfc9332).
====================

Link: https://patch.msgid.link/20250722095915.24485-1-chia-yu.chang@nokia-bell-labs.com


Signed-off-by: default avatarJakub Kicinski <kuba@kernel.org>
parents 1cdf3f2d 68db0ff2

Documentation/netlink/specs/tc.yaml

+149 −2
Original line number Diff line number Diff line
@@ -56,6 +56,23 @@ definitions: 
      - tundf

      - tunoam

      - tuncrit

  -

    name: dualpi2-drop-overload

    type: enum

    entries: [overflow, drop]

  -

    name: dualpi2-drop-early

    type: enum

    entries: [drop-dequeue, drop-enqueue]

  -

    name: dualpi2-ecn-mask

    type: enum

    value-start: 1

    entries: [l4s-ect, cla-ect, any-ect]

  -

    name: dualpi2-split-gso

    type: enum

    entries: [no-split-gso, split-gso]

  -

    name: tc-stats

    type: struct
@@ -825,6 +842,58 @@ definitions: 
      -

        name: drop-overmemory

        type: u32

  -

    name: tc-dualpi2-xstats

    type: struct

    members:

      -

        name: prob

        type: u32

        doc: Current base PI probability

      -

        name: delay-c

        type: u32

        doc: Current C-queue delay in microseconds

      -

        name: delay-l

        type: u32

        doc: Current L-queue delay in microseconds

      -

        name: pkts-in-c

        type: u32

        doc: Number of packets enqueued in the C-queue

      -

        name: pkts-in-l

        type: u32

        doc: Number of packets enqueued in the L-queue

      -

        name: maxq

        type: u32

        doc: Maximum number of packets seen by the DualPI2

      -

        name: ecn-mark

        type: u32

        doc: All packets marked with ECN

      -

        name: step-mark

        type: u32

        doc: Only packets marked with ECN due to L-queue step AQM

      -

        name: credit

        type: s32

        doc: Current credit value for WRR

      -

        name: memory-used

        type: u32

        doc: Memory used in bytes by the DualPI2

      -

        name: max-memory-used

        type: u32

        doc: Maximum memory used in bytes by the DualPI2

      -

        name: memory-limit

        type: u32

        doc: Memory limit in bytes

  -

    name: tc-fq-pie-xstats

    type: struct
@@ -848,7 +917,7 @@ definitions: 
      -

        name: ecn-mark

        type: u32

        doc: Packets marked with ecn

        doc: Packets marked with ECN

      -

        name: new-flow-count

        type: u32
@@ -991,7 +1060,7 @@ definitions: 
      -

        name: ecn-mark

        type: u32

        doc: Packets marked with ecn

        doc: Packets marked with ECN

  -

    name: tc-red-xstats

    type: struct
@@ -2284,6 +2353,78 @@ attribute-sets: 
      -

        name: quantum

        type: u32

  -

    name: dualpi2-attrs

    name-prefix: tca-dualpi2-

    attributes:

      -

        name: limit

        type: u32

        doc: Limit of total number of packets in queue

      -

        name: memory-limit

        type: u32

        doc: Memory limit of total number of packets in queue

      -

        name: target

        type: u32

        doc: Classic target delay in microseconds

      -

        name: tupdate

        type: u32

        doc: Drop probability update interval time in microseconds

      -

        name: alpha

        type: u32

        doc: Integral gain factor in Hz for PI controller

      -

        name: beta

        type: u32

        doc: Proportional gain factor in Hz for PI controller

      -

        name: step-thresh-pkts

        type: u32

        doc: L4S step marking threshold in packets

      -

        name: step-thresh-us

        type: u32

        doc: L4S Step marking threshold in microseconds

      -

        name: min-qlen-step

        type: u32

        doc: Packets enqueued to the L-queue can apply the step threshold

             when the queue length of L-queue is larger than this value.

             (0 is recommended)

      -

        name: coupling

        type: u8

        doc: Probability coupling factor between Classic and L4S

             (2 is recommended)

      -

        name: drop-overload

        type: u8

        doc: Control the overload strategy (drop to preserve latency or

             let the queue overflow)

        enum: dualpi2-drop-overload

      -

        name: drop-early

        type: u8

        doc: Decide where the Classic packets are PI-based dropped or marked

        enum: dualpi2-drop-early

      -

        name: c-protection

        type: u8

        doc: Classic WRR weight in percentage (from 0 to 100)

      -

        name: ecn-mask

        type: u8

        doc: Configure the L-queue ECN classifier

        enum: dualpi2-ecn-mask

      -

        name: split-gso

        type: u8

        doc: Split aggregated skb or not

        enum: dualpi2-split-gso

  -

    name: ematch-attrs

    name-prefix: tca-ematch-
@@ -3708,6 +3849,9 @@ sub-messages: 
      -

        value: drr

        attribute-set: drr-attrs

      -

        value: dualpi2

        attribute-set: dualpi2-attrs

      -

        value: etf

        attribute-set: etf-attrs
@@ -3875,6 +4019,9 @@ sub-messages: 
      -

        value: codel

        fixed-header: tc-codel-xstats

      -

        value: dualpi2

        fixed-header: tc-dualpi2-xstats

      -

        value: fq

        fixed-header: tc-fq-qd-stats

include/net/dropreason-core.h

+6 −0
Original line number Diff line number Diff line
@@ -126,6 +126,7 @@ 
	FN(CANFD_RX_INVALID_FRAME)	\

	FN(CANXL_RX_INVALID_FRAME)	\

	FN(PFMEMALLOC)	\

	FN(DUALPI2_STEP_DROP)		\

	FNe(MAX)



/**
@@ -604,6 +605,11 @@ enum skb_drop_reason { 
	 * reached a path or socket not eligible for use of memory reserves

	 */

	SKB_DROP_REASON_PFMEMALLOC,

	/**

	 * @SKB_DROP_REASON_DUALPI2_STEP_DROP: dropped by the step drop

	 * threshold of DualPI2 qdisc.

	 */

	SKB_DROP_REASON_DUALPI2_STEP_DROP,

	/**

	 * @SKB_DROP_REASON_MAX: the maximum of core drop reasons, which

	 * shouldn't be used as a real 'reason' - only for tracing code gen

include/uapi/linux/pkt_sched.h

+68 −0
Original line number Diff line number Diff line
@@ -1211,4 +1211,72 @@ enum { 


#define TCA_ETS_MAX (__TCA_ETS_MAX - 1)



/* DUALPI2 */

enum tc_dualpi2_drop_overload {

	TC_DUALPI2_DROP_OVERLOAD_OVERFLOW = 0,

	TC_DUALPI2_DROP_OVERLOAD_DROP = 1,

	__TCA_DUALPI2_DROP_OVERLOAD_MAX,

};

#define TCA_DUALPI2_DROP_OVERLOAD_MAX (__TCA_DUALPI2_DROP_OVERLOAD_MAX - 1)



enum tc_dualpi2_drop_early {

	TC_DUALPI2_DROP_EARLY_DROP_DEQUEUE = 0,

	TC_DUALPI2_DROP_EARLY_DROP_ENQUEUE = 1,

	__TCA_DUALPI2_DROP_EARLY_MAX,

};

#define TCA_DUALPI2_DROP_EARLY_MAX (__TCA_DUALPI2_DROP_EARLY_MAX - 1)



enum tc_dualpi2_ecn_mask {

	TC_DUALPI2_ECN_MASK_L4S_ECT = 1,

	TC_DUALPI2_ECN_MASK_CLA_ECT = 2,

	TC_DUALPI2_ECN_MASK_ANY_ECT = 3,

	__TCA_DUALPI2_ECN_MASK_MAX,

};

#define TCA_DUALPI2_ECN_MASK_MAX (__TCA_DUALPI2_ECN_MASK_MAX - 1)



enum tc_dualpi2_split_gso {

	TC_DUALPI2_SPLIT_GSO_NO_SPLIT_GSO = 0,

	TC_DUALPI2_SPLIT_GSO_SPLIT_GSO = 1,

	__TCA_DUALPI2_SPLIT_GSO_MAX,

};

#define TCA_DUALPI2_SPLIT_GSO_MAX (__TCA_DUALPI2_SPLIT_GSO_MAX - 1)



enum {

	TCA_DUALPI2_UNSPEC,

	TCA_DUALPI2_LIMIT,		/* Packets */

	TCA_DUALPI2_MEMORY_LIMIT,	/* Bytes */

	TCA_DUALPI2_TARGET,		/* us */

	TCA_DUALPI2_TUPDATE,		/* us */

	TCA_DUALPI2_ALPHA,		/* Hz scaled up by 256 */

	TCA_DUALPI2_BETA,		/* Hz scaled up by 256 */

	TCA_DUALPI2_STEP_THRESH_PKTS,	/* Step threshold in packets */

	TCA_DUALPI2_STEP_THRESH_US,	/* Step threshold in microseconds */

	TCA_DUALPI2_MIN_QLEN_STEP,	/* Minimum qlen to apply STEP_THRESH */

	TCA_DUALPI2_COUPLING,		/* Coupling factor between queues */

	TCA_DUALPI2_DROP_OVERLOAD,	/* Whether to drop on overload */

	TCA_DUALPI2_DROP_EARLY,		/* Whether to drop on enqueue */

	TCA_DUALPI2_C_PROTECTION,	/* Percentage */

	TCA_DUALPI2_ECN_MASK,		/* L4S queue classification mask */

	TCA_DUALPI2_SPLIT_GSO,		/* Split GSO packets at enqueue */

	TCA_DUALPI2_PAD,

	__TCA_DUALPI2_MAX

};



#define TCA_DUALPI2_MAX   (__TCA_DUALPI2_MAX - 1)



struct tc_dualpi2_xstats {

	__u32 prob;		/* current probability */

	__u32 delay_c;		/* current delay in C queue */

	__u32 delay_l;		/* current delay in L queue */

	__u32 packets_in_c;	/* number of packets enqueued in C queue */

	__u32 packets_in_l;	/* number of packets enqueued in L queue */

	__u32 maxq;		/* maximum queue size */

	__u32 ecn_mark;		/* packets marked with ecn*/

	__u32 step_marks;	/* ECN marks due to the step AQM */

	__s32 credit;		/* current c_protection credit */

	__u32 memory_used;	/* Memory used by both queues */

	__u32 max_memory_used;	/* Maximum used memory */

	__u32 memory_limit;	/* Memory limit of both queues */

};



#endif

net/sched/Kconfig

+12 −0
Original line number Diff line number Diff line
@@ -415,6 +415,18 @@ config NET_SCH_BPF 


	  If unsure, say N.



config NET_SCH_DUALPI2

	tristate "Dual Queue PI Square (DUALPI2) scheduler"

	help

	  Say Y here if you want to use the Dual Queue Proportional Integral

	  Controller Improved with a Square scheduling algorithm.

	  For more information, please see https://tools.ietf.org/html/rfc9332



	  To compile this driver as a module, choose M here: the module

	  will be called sch_dualpi2.



	  If unsure, say N.



menuconfig NET_SCH_DEFAULT

	bool "Allow override default queue discipline"

	help

net/sched/Makefile

+1 −0
Original line number Diff line number Diff line
@@ -63,6 +63,7 @@ obj-$(CONFIG_NET_SCH_CBS) += sch_cbs.o 
obj-$(CONFIG_NET_SCH_ETF)	+= sch_etf.o

obj-$(CONFIG_NET_SCH_TAPRIO)	+= sch_taprio.o

obj-$(CONFIG_NET_SCH_BPF)	+= bpf_qdisc.o

obj-$(CONFIG_NET_SCH_DUALPI2)	+= sch_dualpi2.o



obj-$(CONFIG_NET_CLS_U32)	+= cls_u32.o

obj-$(CONFIG_NET_CLS_ROUTE4)	+= cls_route.o