Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-nextgrafted

Pull networking updates from Jakub Kicinski:
 "Core:

   - Add dedicated kmem_cache for typical/small skb->head, avoid having
     to access struct page at kfree time, and improve memory use.

   - Introduce sysctl to set default RPS configuration for new netdevs.

   - Define Netlink protocol specification format which can be used to
     describe messages used by each family and auto-generate parsers.
     Add tools for generating kernel data structures and uAPI headers.

   - Expose all net/core sysctls inside netns.

   - Remove 4s sleep in netpoll if carrier is instantly detected on
     boot.

   - Add configurable limit of MDB entries per port, and port-vlan.

   - Continue populating drop reasons throughout the stack.

   - Retire a handful of legacy Qdiscs and classifiers.

  Protocols:

   - Support IPv4 big TCP (TSO frames larger than 64kB).

   - Add IP_LOCAL_PORT_RANGE socket option, to control local port range
     on socket by socket basis.

   - Track and report in procfs number of MPTCP sockets used.

   - Support mixing IPv4 and IPv6 flows in the in-kernel MPTCP path
     manager.

   - IPv6: don't check net.ipv6.route.max_size and rely on garbage
     collection to free memory (similarly to IPv4).

   - Support Penultimate Segment Pop (PSP) flavor in SRv6 (RFC8986).

   - ICMP: add per-rate limit counters.

   - Add support for user scanning requests in ieee802154.

   - Remove static WEP support.

   - Support minimal Wi-Fi 7 Extremely High Throughput (EHT) rate
     reporting.

   - WiFi 7 EHT channel puncturing support (client & AP).

  BPF:

   - Add a rbtree data structure following the "next-gen data structure"
     precedent set by recently added linked list, that is, by using
     kfunc + kptr instead of adding a new BPF map type.

   - Expose XDP hints via kfuncs with initial support for RX hash and
     timestamp metadata.

   - Add BPF_F_NO_TUNNEL_KEY extension to bpf_skb_set_tunnel_key to
     better support decap on GRE tunnel devices not operating in collect
     metadata.

   - Improve x86 JIT's codegen for PROBE_MEM runtime error checks.

   - Remove the need for trace_printk_lock for bpf_trace_printk and
     bpf_trace_vprintk helpers.

   - Extend libbpf's bpf_tracing.h support for tracing arguments of
     kprobes/uprobes and syscall as a special case.

   - Significantly reduce the search time for module symbols by
     livepatch and BPF.

   - Enable cpumasks to be used as kptrs, which is useful for tracing
     programs tracking which tasks end up running on which CPUs in
     different time intervals.

   - Add support for BPF trampoline on s390x and riscv64.

   - Add capability to export the XDP features supported by the NIC.

   - Add __bpf_kfunc tag for marking kernel functions as kfuncs.

   - Add cgroup.memory=nobpf kernel parameter option to disable BPF
     memory accounting for container environments.

  Netfilter:

   - Remove the CLUSTERIP target. It has been marked as obsolete for
     years, and we still have WARN splats wrt races of the out-of-band
     /proc interface installed by this target.

   - Add 'destroy' commands to nf_tables. They are identical to the
     existing 'delete' commands, but do not return an error if the
     referenced object (set, chain, rule...) did not exist.

  Driver API:

   - Improve cpumask_local_spread() locality to help NICs set the right
     IRQ affinity on AMD platforms.

   - Separate C22 and C45 MDIO bus transactions more clearly.

   - Introduce new DCB table to control DSCP rewrite on egress.

   - Support configuration of Physical Layer Collision Avoidance (PLCA)
     Reconciliation Sublayer (RS) (802.3cg-2019). Modern version of
     shared medium Ethernet.

   - Support for MAC Merge layer (IEEE 802.3-2018 clause 99). Allowing
     preemption of low priority frames by high priority frames.

   - Add support for controlling MACSec offload using netlink SET.

   - Rework devlink instance refcounts to allow registration and
     de-registration under the instance lock. Split the code into
     multiple files, drop some of the unnecessarily granular locks and
     factor out common parts of netlink operation handling.

   - Add TX frame aggregation parameters (for USB drivers).

   - Add a new attr TCA_EXT_WARN_MSG to report TC (offload) warning
     messages with notifications for debug.

   - Allow offloading of UDP NEW connections via act_ct.

   - Add support for per action HW stats in TC.

   - Support hardware miss to TC action (continue processing in SW from
     a specific point in the action chain).

   - Warn if old Wireless Extension user space interface is used with
     modern cfg80211/mac80211 drivers. Do not support Wireless
     Extensions for Wi-Fi 7 devices at all. Everyone should switch to
     using nl80211 interface instead.

   - Improve the CAN bit timing configuration. Use extack to return
     error messages directly to user space, update the SJW handling,
     including the definition of a new default value that will benefit
     CAN-FD controllers, by increasing their oscillator tolerance.

  New hardware / drivers:

   - Ethernet:
      - nVidia BlueField-3 support (control traffic driver)
      - Ethernet support for imx93 SoCs
      - Motorcomm yt8531 gigabit Ethernet PHY
      - onsemi NCN26000 10BASE-T1S PHY (with support for PLCA)
      - Microchip LAN8841 PHY (incl. cable diagnostics and PTP)
      - Amlogic gxl MDIO mux

   - WiFi:
      - RealTek RTL8188EU (rtl8xxxu)
      - Qualcomm Wi-Fi 7 devices (ath12k)

   - CAN:
      - Renesas R-Car V4H

  Drivers:

   - Bluetooth:
      - Set Per Platform Antenna Gain (PPAG) for Intel controllers.

   - Ethernet NICs:
      - Intel (1G, igc):
         - support TSN / Qbv / packet scheduling features of i226 model
      - Intel (100G, ice):
         - use GNSS subsystem instead of TTY
         - multi-buffer XDP support
         - extend support for GPIO pins to E823 devices
      - nVidia/Mellanox:
         - update the shared buffer configuration on PFC commands
         - implement PTP adjphase function for HW offset control
         - TC support for Geneve and GRE with VF tunnel offload
         - more efficient crypto key management method
         - multi-port eswitch support
      - Netronome/Corigine:
         - add DCB IEEE support
         - support IPsec offloading for NFP3800
      - Freescale/NXP (enetc):
         - support XDP_REDIRECT for XDP non-linear buffers
         - improve reconfig, avoid link flap and waiting for idle
         - support MAC Merge layer
      - Other NICs:
         - sfc/ef100: add basic devlink support for ef100
         - ionic: rx_push mode operation (writing descriptors via MMIO)
         - bnxt: use the auxiliary bus abstraction for RDMA
         - r8169: disable ASPM and reset bus in case of tx timeout
         - cpsw: support QSGMII mode for J721e CPSW9G
         - cpts: support pulse-per-second output
         - ngbe: add an mdio bus driver
         - usbnet: optimize usbnet_bh() by avoiding unnecessary queuing
         - r8152: handle devices with FW with NCM support
         - amd-xgbe: support 10Mbps, 2.5GbE speeds and rx-adaptation
         - virtio-net: support multi buffer XDP
         - virtio/vsock: replace virtio_vsock_pkt with sk_buff
         - tsnep: XDP support

   - Ethernet high-speed switches:
      - nVidia/Mellanox (mlxsw):
         - add support for latency TLV (in FW control messages)
      - Microchip (sparx5):
         - separate explicit and implicit traffic forwarding rules, make
           the implicit rules always active
         - add support for egress DSCP rewrite
         - IS0 VCAP support (Ingress Classification)
         - IS2 VCAP filters (protos, L3 addrs, L4 ports, flags, ToS
           etc.)
         - ES2 VCAP support (Egress Access Control)
         - support for Per-Stream Filtering and Policing (802.1Q,
           8.6.5.1)

   - Ethernet embedded switches:
      - Marvell (mv88e6xxx):
         - add MAB (port auth) offload support
         - enable PTP receive for mv88e6390
      - NXP (ocelot):
         - support MAC Merge layer
         - support for the the vsc7512 internal copper phys
      - Microchip:
         - lan9303: convert to PHYLINK
         - lan966x: support TC flower filter statistics
         - lan937x: PTP support for KSZ9563/KSZ8563 and LAN937x
         - lan937x: support Credit Based Shaper configuration
         - ksz9477: support Energy Efficient Ethernet
      - other:
         - qca8k: convert to regmap read/write API, use bulk operations
         - rswitch: Improve TX timestamp accuracy

   - Intel WiFi (iwlwifi):
      - EHT (Wi-Fi 7) rate reporting
      - STEP equalizer support: transfer some STEP (connection to radio
        on platforms with integrated wifi) related parameters from the
        BIOS to the firmware.

   - Qualcomm 802.11ax WiFi (ath11k):
      - IPQ5018 support
      - Fine Timing Measurement (FTM) responder role support
      - channel 177 support

   - MediaTek WiFi (mt76):
      - per-PHY LED support
      - mt7996: EHT (Wi-Fi 7) support
      - Wireless Ethernet Dispatch (WED) reset support
      - switch to using page pool allocator

   - RealTek WiFi (rtw89):
      - support new version of Bluetooth co-existance

   - Mobile:
      - rmnet: support TX aggregation"

* tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1872 commits)
  page_pool: add a comment explaining the fragment counter usage
  net: ethtool: fix __ethtool_dev_mm_supported() implementation
  ethtool: pse-pd: Fix double word in comments
  xsk: add linux/vmalloc.h to xsk.c
  sefltests: netdevsim: wait for devlink instance after netns removal
  selftest: fib_tests: Always cleanup before exit
  net/mlx5e: Align IPsec ASO result memory to be as required by hardware
  net/mlx5e: TC, Set CT miss to the specific ct action instance
  net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG
  net/mlx5: Refactor tc miss handling to a single function
  net/mlx5: Kconfig: Make tc offload depend on tc skb extension
  net/sched: flower: Support hardware miss to tc action
  net/sched: flower: Move filter handle initialization earlier
  net/sched: cls_api: Support hardware miss to tc action
  net/sched: Rename user cookie and act cookie
  sfc: fix builds without CONFIG_RTC_LIB
  sfc: clean up some inconsistent indentings
  net/mlx4_en: Introduce flexible array to silence overflow warning
  net: lan966x: Fix possible deadlock inside PTP
  net/ulp: Remove redundant ->clone() test in inet_clone_ulp().
  ...

1 files changed, 515 insertions, 0 deletions

diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c
new file mode 100644
index 000000000..19c851125
--- /dev/null
+++ b/net/sched/sch_choke.c
@@ -0,0 +1,515 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * net/sched/sch_choke.c	CHOKE scheduler
+ *
+ * Copyright (c) 2011 Stephen Hemminger <shemminger@vyatta.com>
+ * Copyright (c) 2011 Eric Dumazet <eric.dumazet@gmail.com>
+ */
+
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/skbuff.h>
+#include <linux/vmalloc.h>
+#include <net/pkt_sched.h>
+#include <net/pkt_cls.h>
+#include <net/inet_ecn.h>
+#include <net/red.h>
+#include <net/flow_dissector.h>
+
+/*
+   CHOKe stateless AQM for fair bandwidth allocation
+   =================================================
+
+   CHOKe (CHOose and Keep for responsive flows, CHOose and Kill for
+   unresponsive flows) is a variant of RED that penalizes misbehaving flows but
+   maintains no flow state. The difference from RED is an additional step
+   during the enqueuing process. If average queue size is over the
+   low threshold (qmin), a packet is chosen at random from the queue.
+   If both the new and chosen packet are from the same flow, both
+   are dropped. Unlike RED, CHOKe is not really a "classful" qdisc because it
+   needs to access packets in queue randomly. It has a minimal class
+   interface to allow overriding the builtin flow classifier with
+   filters.
+
+   Source:
+   R. Pan, B. Prabhakar, and K. Psounis, "CHOKe, A Stateless
+   Active Queue Management Scheme for Approximating Fair Bandwidth Allocation",
+   IEEE INFOCOM, 2000.
+
+   A. Tang, J. Wang, S. Low, "Understanding CHOKe: Throughput and Spatial
+   Characteristics", IEEE/ACM Transactions on Networking, 2004
+
+ */
+
+/* Upper bound on size of sk_buff table (packets) */
+#define CHOKE_MAX_QUEUE	(128*1024 - 1)
+
+struct choke_sched_data {
+/* Parameters */
+	u32		 limit;
+	unsigned char	 flags;
+
+	struct red_parms parms;
+
+/* Variables */
+	struct red_vars  vars;
+	struct {
+		u32	prob_drop;	/* Early probability drops */
+		u32	prob_mark;	/* Early probability marks */
+		u32	forced_drop;	/* Forced drops, qavg > max_thresh */
+		u32	forced_mark;	/* Forced marks, qavg > max_thresh */
+		u32	pdrop;          /* Drops due to queue limits */
+		u32	matched;	/* Drops to flow match */
+	} stats;
+
+	unsigned int	 head;
+	unsigned int	 tail;
+
+	unsigned int	 tab_mask; /* size - 1 */
+
+	struct sk_buff **tab;
+};
+
+/* number of elements in queue including holes */
+static unsigned int choke_len(const struct choke_sched_data *q)
+{
+	return (q->tail - q->head) & q->tab_mask;
+}
+
+/* Is ECN parameter configured */
+static int use_ecn(const struct choke_sched_data *q)
+{
+	return q->flags & TC_RED_ECN;
+}
+
+/* Should packets over max just be dropped (versus marked) */
+static int use_harddrop(const struct choke_sched_data *q)
+{
+	return q->flags & TC_RED_HARDDROP;
+}
+
+/* Move head pointer forward to skip over holes */
+static void choke_zap_head_holes(struct choke_sched_data *q)
+{
+	do {
+		q->head = (q->head + 1) & q->tab_mask;
+		if (q->head == q->tail)
+			break;
+	} while (q->tab[q->head] == NULL);
+}
+
+/* Move tail pointer backwards to reuse holes */
+static void choke_zap_tail_holes(struct choke_sched_data *q)
+{
+	do {
+		q->tail = (q->tail - 1) & q->tab_mask;
+		if (q->head == q->tail)
+			break;
+	} while (q->tab[q->tail] == NULL);
+}
+
+/* Drop packet from queue array by creating a "hole" */
+static void choke_drop_by_idx(struct Qdisc *sch, unsigned int idx,
+			      struct sk_buff **to_free)
+{
+	struct choke_sched_data *q = qdisc_priv(sch);
+	struct sk_buff *skb = q->tab[idx];
+
+	q->tab[idx] = NULL;
+
+	if (idx == q->head)
+		choke_zap_head_holes(q);
+	if (idx == q->tail)
+		choke_zap_tail_holes(q);
+
+	qdisc_qstats_backlog_dec(sch, skb);
+	qdisc_tree_reduce_backlog(sch, 1, qdisc_pkt_len(skb));
+	qdisc_drop(skb, sch, to_free);
+	--sch->q.qlen;
+}
+
+struct choke_skb_cb {
+	u8			keys_valid;
+	struct			flow_keys_digest keys;
+};
+
+static inline struct choke_skb_cb *choke_skb_cb(const struct sk_buff *skb)
+{
+	qdisc_cb_private_validate(skb, sizeof(struct choke_skb_cb));
+	return (struct choke_skb_cb *)qdisc_skb_cb(skb)->data;
+}
+
+/*
+ * Compare flow of two packets
+ *  Returns true only if source and destination address and port match.
+ *          false for special cases
+ */
+static bool choke_match_flow(struct sk_buff *skb1,
+			     struct sk_buff *skb2)
+{
+	struct flow_keys temp;
+
+	if (skb1->protocol != skb2->protocol)
+		return false;
+
+	if (!choke_skb_cb(skb1)->keys_valid) {
+		choke_skb_cb(skb1)->keys_valid = 1;
+		skb_flow_dissect_flow_keys(skb1, &temp, 0);
+		make_flow_keys_digest(&choke_skb_cb(skb1)->keys, &temp);
+	}
+
+	if (!choke_skb_cb(skb2)->keys_valid) {
+		choke_skb_cb(skb2)->keys_valid = 1;
+		skb_flow_dissect_flow_keys(skb2, &temp, 0);
+		make_flow_keys_digest(&choke_skb_cb(skb2)->keys, &temp);
+	}
+
+	return !memcmp(&choke_skb_cb(skb1)->keys,
+		       &choke_skb_cb(skb2)->keys,
+		       sizeof(choke_skb_cb(skb1)->keys));
+}
+
+/*
+ * Select a packet at random from queue
+ * HACK: since queue can have holes from previous deletion; retry several
+ *   times to find a random skb but then just give up and return the head
+ * Will return NULL if queue is empty (q->head == q->tail)
+ */
+static struct sk_buff *choke_peek_random(const struct choke_sched_data *q,
+					 unsigned int *pidx)
+{
+	struct sk_buff *skb;
+	int retrys = 3;
+
+	do {
+		*pidx = (q->head + get_random_u32_below(choke_len(q))) & q->tab_mask;
+		skb = q->tab[*pidx];
+		if (skb)
+			return skb;
+	} while (--retrys > 0);
+
+	return q->tab[*pidx = q->head];
+}
+
+/*
+ * Compare new packet with random packet in queue
+ * returns true if matched and sets *pidx
+ */
+static bool choke_match_random(const struct choke_sched_data *q,
+			       struct sk_buff *nskb,
+			       unsigned int *pidx)
+{
+	struct sk_buff *oskb;
+
+	if (q->head == q->tail)
+		return false;
+
+	oskb = choke_peek_random(q, pidx);
+	return choke_match_flow(oskb, nskb);
+}
+
+static int choke_enqueue(struct sk_buff *skb, struct Qdisc *sch,
+			 struct sk_buff **to_free)
+{
+	struct choke_sched_data *q = qdisc_priv(sch);
+	const struct red_parms *p = &q->parms;
+
+	choke_skb_cb(skb)->keys_valid = 0;
+	/* Compute average queue usage (see RED) */
+	q->vars.qavg = red_calc_qavg(p, &q->vars, sch->q.qlen);
+	if (red_is_idling(&q->vars))
+		red_end_of_idle_period(&q->vars);
+
+	/* Is queue small? */
+	if (q->vars.qavg <= p->qth_min)
+		q->vars.qcount = -1;
+	else {
+		unsigned int idx;
+
+		/* Draw a packet at random from queue and compare flow */
+		if (choke_match_random(q, skb, &idx)) {
+			q->stats.matched++;
+			choke_drop_by_idx(sch, idx, to_free);
+			goto congestion_drop;
+		}
+
+		/* Queue is large, always mark/drop */
+		if (q->vars.qavg > p->qth_max) {
+			q->vars.qcount = -1;
+
+			qdisc_qstats_overlimit(sch);
+			if (use_harddrop(q) || !use_ecn(q) ||
+			    !INET_ECN_set_ce(skb)) {
+				q->stats.forced_drop++;
+				goto congestion_drop;
+			}
+
+			q->stats.forced_mark++;
+		} else if (++q->vars.qcount) {
+			if (red_mark_probability(p, &q->vars, q->vars.qavg)) {
+				q->vars.qcount = 0;
+				q->vars.qR = red_random(p);
+
+				qdisc_qstats_overlimit(sch);
+				if (!use_ecn(q) || !INET_ECN_set_ce(skb)) {
+					q->stats.prob_drop++;
+					goto congestion_drop;
+				}
+
+				q->stats.prob_mark++;
+			}
+		} else
+			q->vars.qR = red_random(p);
+	}
+
+	/* Admit new packet */
+	if (sch->q.qlen < q->limit) {
+		q->tab[q->tail] = skb;
+		q->tail = (q->tail + 1) & q->tab_mask;
+		++sch->q.qlen;
+		qdisc_qstats_backlog_inc(sch, skb);
+		return NET_XMIT_SUCCESS;
+	}
+
+	q->stats.pdrop++;
+	return qdisc_drop(skb, sch, to_free);
+
+congestion_drop:
+	qdisc_drop(skb, sch, to_free);
+	return NET_XMIT_CN;
+}
+
+static struct sk_buff *choke_dequeue(struct Qdisc *sch)
+{
+	struct choke_sched_data *q = qdisc_priv(sch);
+	struct sk_buff *skb;
+
+	if (q->head == q->tail) {
+		if (!red_is_idling(&q->vars))
+			red_start_of_idle_period(&q->vars);
+		return NULL;
+	}
+
+	skb = q->tab[q->head];
+	q->tab[q->head] = NULL;
+	choke_zap_head_holes(q);
+	--sch->q.qlen;
+	qdisc_qstats_backlog_dec(sch, skb);
+	qdisc_bstats_update(sch, skb);
+
+	return skb;
+}
+
+static void choke_reset(struct Qdisc *sch)
+{
+	struct choke_sched_data *q = qdisc_priv(sch);
+
+	while (q->head != q->tail) {
+		struct sk_buff *skb = q->tab[q->head];
+
+		q->head = (q->head + 1) & q->tab_mask;
+		if (!skb)
+			continue;
+		rtnl_qdisc_drop(skb, sch);
+	}
+
+	if (q->tab)
+		memset(q->tab, 0, (q->tab_mask + 1) * sizeof(struct sk_buff *));
+	q->head = q->tail = 0;
+	red_restart(&q->vars);
+}
+
+static const struct nla_policy choke_policy[TCA_CHOKE_MAX + 1] = {
+	[TCA_CHOKE_PARMS]	= { .len = sizeof(struct tc_red_qopt) },
+	[TCA_CHOKE_STAB]	= { .len = RED_STAB_SIZE },
+	[TCA_CHOKE_MAX_P]	= { .type = NLA_U32 },
+};
+
+
+static void choke_free(void *addr)
+{
+	kvfree(addr);
+}
+
+static int choke_change(struct Qdisc *sch, struct nlattr *opt,
+			struct netlink_ext_ack *extack)
+{
+	struct choke_sched_data *q = qdisc_priv(sch);
+	struct nlattr *tb[TCA_CHOKE_MAX + 1];
+	const struct tc_red_qopt *ctl;
+	int err;
+	struct sk_buff **old = NULL;
+	unsigned int mask;
+	u32 max_P;
+	u8 *stab;
+
+	if (opt == NULL)
+		return -EINVAL;
+
+	err = nla_parse_nested_deprecated(tb, TCA_CHOKE_MAX, opt,
+					  choke_policy, NULL);
+	if (err < 0)
+		return err;
+
+	if (tb[TCA_CHOKE_PARMS] == NULL ||
+	    tb[TCA_CHOKE_STAB] == NULL)
+		return -EINVAL;
+
+	max_P = tb[TCA_CHOKE_MAX_P] ? nla_get_u32(tb[TCA_CHOKE_MAX_P]) : 0;
+
+	ctl = nla_data(tb[TCA_CHOKE_PARMS]);
+	stab = nla_data(tb[TCA_CHOKE_STAB]);
+	if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog, ctl->Scell_log, stab))
+		return -EINVAL;
+
+	if (ctl->limit > CHOKE_MAX_QUEUE)
+		return -EINVAL;
+
+	mask = roundup_pow_of_two(ctl->limit + 1) - 1;
+	if (mask != q->tab_mask) {
+		struct sk_buff **ntab;
+
+		ntab = kvcalloc(mask + 1, sizeof(struct sk_buff *), GFP_KERNEL);
+		if (!ntab)
+			return -ENOMEM;
+
+		sch_tree_lock(sch);
+		old = q->tab;
+		if (old) {
+			unsigned int oqlen = sch->q.qlen, tail = 0;
+			unsigned dropped = 0;
+
+			while (q->head != q->tail) {
+				struct sk_buff *skb = q->tab[q->head];
+
+				q->head = (q->head + 1) & q->tab_mask;
+				if (!skb)
+					continue;
+				if (tail < mask) {
+					ntab[tail++] = skb;
+					continue;
+				}
+				dropped += qdisc_pkt_len(skb);
+				qdisc_qstats_backlog_dec(sch, skb);
+				--sch->q.qlen;
+				rtnl_qdisc_drop(skb, sch);
+			}
+			qdisc_tree_reduce_backlog(sch, oqlen - sch->q.qlen, dropped);
+			q->head = 0;
+			q->tail = tail;
+		}
+
+		q->tab_mask = mask;
+		q->tab = ntab;
+	} else
+		sch_tree_lock(sch);
+
+	q->flags = ctl->flags;
+	q->limit = ctl->limit;
+
+	red_set_parms(&q->parms, ctl->qth_min, ctl->qth_max, ctl->Wlog,
+		      ctl->Plog, ctl->Scell_log,
+		      stab,
+		      max_P);
+	red_set_vars(&q->vars);
+
+	if (q->head == q->tail)
+		red_end_of_idle_period(&q->vars);
+
+	sch_tree_unlock(sch);
+	choke_free(old);
+	return 0;
+}
+
+static int choke_init(struct Qdisc *sch, struct nlattr *opt,
+		      struct netlink_ext_ack *extack)
+{
+	return choke_change(sch, opt, extack);
+}
+
+static int choke_dump(struct Qdisc *sch, struct sk_buff *skb)
+{
+	struct choke_sched_data *q = qdisc_priv(sch);
+	struct nlattr *opts = NULL;
+	struct tc_red_qopt opt = {
+		.limit		= q->limit,
+		.flags		= q->flags,
+		.qth_min	= q->parms.qth_min >> q->parms.Wlog,
+		.qth_max	= q->parms.qth_max >> q->parms.Wlog,
+		.Wlog		= q->parms.Wlog,
+		.Plog		= q->parms.Plog,
+		.Scell_log	= q->parms.Scell_log,
+	};
+
+	opts = nla_nest_start_noflag(skb, TCA_OPTIONS);
+	if (opts == NULL)
+		goto nla_put_failure;
+
+	if (nla_put(skb, TCA_CHOKE_PARMS, sizeof(opt), &opt) ||
+	    nla_put_u32(skb, TCA_CHOKE_MAX_P, q->parms.max_P))
+		goto nla_put_failure;
+	return nla_nest_end(skb, opts);
+
+nla_put_failure:
+	nla_nest_cancel(skb, opts);
+	return -EMSGSIZE;
+}
+
+static int choke_dump_stats(struct Qdisc *sch, struct gnet_dump *d)
+{
+	struct choke_sched_data *q = qdisc_priv(sch);
+	struct tc_choke_xstats st = {
+		.early	= q->stats.prob_drop + q->stats.forced_drop,
+		.marked	= q->stats.prob_mark + q->stats.forced_mark,
+		.pdrop	= q->stats.pdrop,
+		.matched = q->stats.matched,
+	};
+
+	return gnet_stats_copy_app(d, &st, sizeof(st));
+}
+
+static void choke_destroy(struct Qdisc *sch)
+{
+	struct choke_sched_data *q = qdisc_priv(sch);
+
+	choke_free(q->tab);
+}
+
+static struct sk_buff *choke_peek_head(struct Qdisc *sch)
+{
+	struct choke_sched_data *q = qdisc_priv(sch);
+
+	return (q->head != q->tail) ? q->tab[q->head] : NULL;
+}
+
+static struct Qdisc_ops choke_qdisc_ops __read_mostly = {
+	.id		=	"choke",
+	.priv_size	=	sizeof(struct choke_sched_data),
+
+	.enqueue	=	choke_enqueue,
+	.dequeue	=	choke_dequeue,
+	.peek		=	choke_peek_head,
+	.init		=	choke_init,
+	.destroy	=	choke_destroy,
+	.reset		=	choke_reset,
+	.change		=	choke_change,
+	.dump		=	choke_dump,
+	.dump_stats	=	choke_dump_stats,
+	.owner		=	THIS_MODULE,
+};
+
+static int __init choke_module_init(void)
+{
+	return register_qdisc(&choke_qdisc_ops);
+}
+
+static void __exit choke_module_exit(void)
+{
+	unregister_qdisc(&choke_qdisc_ops);
+}
+
+module_init(choke_module_init)
+module_exit(choke_module_exit)
+
+MODULE_LICENSE("GPL");