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, 496 insertions, 0 deletions

diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c
new file mode 100644
index 000000000..e35a4e90f
--- /dev/null
+++ b/net/sched/sch_drr.c
@@ -0,0 +1,496 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * net/sched/sch_drr.c         Deficit Round Robin scheduler
+ *
+ * Copyright (c) 2008 Patrick McHardy <kaber@trash.net>
+ */
+
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/init.h>
+#include <linux/errno.h>
+#include <linux/netdevice.h>
+#include <linux/pkt_sched.h>
+#include <net/sch_generic.h>
+#include <net/pkt_sched.h>
+#include <net/pkt_cls.h>
+
+struct drr_class {
+	struct Qdisc_class_common	common;
+	unsigned int			filter_cnt;
+
+	struct gnet_stats_basic_sync		bstats;
+	struct gnet_stats_queue		qstats;
+	struct net_rate_estimator __rcu *rate_est;
+	struct list_head		alist;
+	struct Qdisc			*qdisc;
+
+	u32				quantum;
+	u32				deficit;
+};
+
+struct drr_sched {
+	struct list_head		active;
+	struct tcf_proto __rcu		*filter_list;
+	struct tcf_block		*block;
+	struct Qdisc_class_hash		clhash;
+};
+
+static struct drr_class *drr_find_class(struct Qdisc *sch, u32 classid)
+{
+	struct drr_sched *q = qdisc_priv(sch);
+	struct Qdisc_class_common *clc;
+
+	clc = qdisc_class_find(&q->clhash, classid);
+	if (clc == NULL)
+		return NULL;
+	return container_of(clc, struct drr_class, common);
+}
+
+static const struct nla_policy drr_policy[TCA_DRR_MAX + 1] = {
+	[TCA_DRR_QUANTUM]	= { .type = NLA_U32 },
+};
+
+static int drr_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
+			    struct nlattr **tca, unsigned long *arg,
+			    struct netlink_ext_ack *extack)
+{
+	struct drr_sched *q = qdisc_priv(sch);
+	struct drr_class *cl = (struct drr_class *)*arg;
+	struct nlattr *opt = tca[TCA_OPTIONS];
+	struct nlattr *tb[TCA_DRR_MAX + 1];
+	u32 quantum;
+	int err;
+
+	if (!opt) {
+		NL_SET_ERR_MSG(extack, "DRR options are required for this operation");
+		return -EINVAL;
+	}
+
+	err = nla_parse_nested_deprecated(tb, TCA_DRR_MAX, opt, drr_policy,
+					  extack);
+	if (err < 0)
+		return err;
+
+	if (tb[TCA_DRR_QUANTUM]) {
+		quantum = nla_get_u32(tb[TCA_DRR_QUANTUM]);
+		if (quantum == 0) {
+			NL_SET_ERR_MSG(extack, "Specified DRR quantum cannot be zero");
+			return -EINVAL;
+		}
+	} else
+		quantum = psched_mtu(qdisc_dev(sch));
+
+	if (cl != NULL) {
+		if (tca[TCA_RATE]) {
+			err = gen_replace_estimator(&cl->bstats, NULL,
+						    &cl->rate_est,
+						    NULL, true,
+						    tca[TCA_RATE]);
+			if (err) {
+				NL_SET_ERR_MSG(extack, "Failed to replace estimator");
+				return err;
+			}
+		}
+
+		sch_tree_lock(sch);
+		if (tb[TCA_DRR_QUANTUM])
+			cl->quantum = quantum;
+		sch_tree_unlock(sch);
+
+		return 0;
+	}
+
+	cl = kzalloc(sizeof(struct drr_class), GFP_KERNEL);
+	if (cl == NULL)
+		return -ENOBUFS;
+
+	gnet_stats_basic_sync_init(&cl->bstats);
+	cl->common.classid = classid;
+	cl->quantum	   = quantum;
+	cl->qdisc	   = qdisc_create_dflt(sch->dev_queue,
+					       &pfifo_qdisc_ops, classid,
+					       NULL);
+	if (cl->qdisc == NULL)
+		cl->qdisc = &noop_qdisc;
+	else
+		qdisc_hash_add(cl->qdisc, true);
+
+	if (tca[TCA_RATE]) {
+		err = gen_replace_estimator(&cl->bstats, NULL, &cl->rate_est,
+					    NULL, true, tca[TCA_RATE]);
+		if (err) {
+			NL_SET_ERR_MSG(extack, "Failed to replace estimator");
+			qdisc_put(cl->qdisc);
+			kfree(cl);
+			return err;
+		}
+	}
+
+	sch_tree_lock(sch);
+	qdisc_class_hash_insert(&q->clhash, &cl->common);
+	sch_tree_unlock(sch);
+
+	qdisc_class_hash_grow(sch, &q->clhash);
+
+	*arg = (unsigned long)cl;
+	return 0;
+}
+
+static void drr_destroy_class(struct Qdisc *sch, struct drr_class *cl)
+{
+	gen_kill_estimator(&cl->rate_est);
+	qdisc_put(cl->qdisc);
+	kfree(cl);
+}
+
+static int drr_delete_class(struct Qdisc *sch, unsigned long arg,
+			    struct netlink_ext_ack *extack)
+{
+	struct drr_sched *q = qdisc_priv(sch);
+	struct drr_class *cl = (struct drr_class *)arg;
+
+	if (cl->filter_cnt > 0)
+		return -EBUSY;
+
+	sch_tree_lock(sch);
+
+	qdisc_purge_queue(cl->qdisc);
+	qdisc_class_hash_remove(&q->clhash, &cl->common);
+
+	sch_tree_unlock(sch);
+
+	drr_destroy_class(sch, cl);
+	return 0;
+}
+
+static unsigned long drr_search_class(struct Qdisc *sch, u32 classid)
+{
+	return (unsigned long)drr_find_class(sch, classid);
+}
+
+static struct tcf_block *drr_tcf_block(struct Qdisc *sch, unsigned long cl,
+				       struct netlink_ext_ack *extack)
+{
+	struct drr_sched *q = qdisc_priv(sch);
+
+	if (cl) {
+		NL_SET_ERR_MSG(extack, "DRR classid must be zero");
+		return NULL;
+	}
+
+	return q->block;
+}
+
+static unsigned long drr_bind_tcf(struct Qdisc *sch, unsigned long parent,
+				  u32 classid)
+{
+	struct drr_class *cl = drr_find_class(sch, classid);
+
+	if (cl != NULL)
+		cl->filter_cnt++;
+
+	return (unsigned long)cl;
+}
+
+static void drr_unbind_tcf(struct Qdisc *sch, unsigned long arg)
+{
+	struct drr_class *cl = (struct drr_class *)arg;
+
+	cl->filter_cnt--;
+}
+
+static int drr_graft_class(struct Qdisc *sch, unsigned long arg,
+			   struct Qdisc *new, struct Qdisc **old,
+			   struct netlink_ext_ack *extack)
+{
+	struct drr_class *cl = (struct drr_class *)arg;
+
+	if (new == NULL) {
+		new = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops,
+					cl->common.classid, NULL);
+		if (new == NULL)
+			new = &noop_qdisc;
+	}
+
+	*old = qdisc_replace(sch, new, &cl->qdisc);
+	return 0;
+}
+
+static struct Qdisc *drr_class_leaf(struct Qdisc *sch, unsigned long arg)
+{
+	struct drr_class *cl = (struct drr_class *)arg;
+
+	return cl->qdisc;
+}
+
+static void drr_qlen_notify(struct Qdisc *csh, unsigned long arg)
+{
+	struct drr_class *cl = (struct drr_class *)arg;
+
+	list_del(&cl->alist);
+}
+
+static int drr_dump_class(struct Qdisc *sch, unsigned long arg,
+			  struct sk_buff *skb, struct tcmsg *tcm)
+{
+	struct drr_class *cl = (struct drr_class *)arg;
+	struct nlattr *nest;
+
+	tcm->tcm_parent	= TC_H_ROOT;
+	tcm->tcm_handle	= cl->common.classid;
+	tcm->tcm_info	= cl->qdisc->handle;
+
+	nest = nla_nest_start_noflag(skb, TCA_OPTIONS);
+	if (nest == NULL)
+		goto nla_put_failure;
+	if (nla_put_u32(skb, TCA_DRR_QUANTUM, cl->quantum))
+		goto nla_put_failure;
+	return nla_nest_end(skb, nest);
+
+nla_put_failure:
+	nla_nest_cancel(skb, nest);
+	return -EMSGSIZE;
+}
+
+static int drr_dump_class_stats(struct Qdisc *sch, unsigned long arg,
+				struct gnet_dump *d)
+{
+	struct drr_class *cl = (struct drr_class *)arg;
+	__u32 qlen = qdisc_qlen_sum(cl->qdisc);
+	struct Qdisc *cl_q = cl->qdisc;
+	struct tc_drr_stats xstats;
+
+	memset(&xstats, 0, sizeof(xstats));
+	if (qlen)
+		xstats.deficit = cl->deficit;
+
+	if (gnet_stats_copy_basic(d, NULL, &cl->bstats, true) < 0 ||
+	    gnet_stats_copy_rate_est(d, &cl->rate_est) < 0 ||
+	    gnet_stats_copy_queue(d, cl_q->cpu_qstats, &cl_q->qstats, qlen) < 0)
+		return -1;
+
+	return gnet_stats_copy_app(d, &xstats, sizeof(xstats));
+}
+
+static void drr_walk(struct Qdisc *sch, struct qdisc_walker *arg)
+{
+	struct drr_sched *q = qdisc_priv(sch);
+	struct drr_class *cl;
+	unsigned int i;
+
+	if (arg->stop)
+		return;
+
+	for (i = 0; i < q->clhash.hashsize; i++) {
+		hlist_for_each_entry(cl, &q->clhash.hash[i], common.hnode) {
+			if (!tc_qdisc_stats_dump(sch, (unsigned long)cl, arg))
+				return;
+		}
+	}
+}
+
+static struct drr_class *drr_classify(struct sk_buff *skb, struct Qdisc *sch,
+				      int *qerr)
+{
+	struct drr_sched *q = qdisc_priv(sch);
+	struct drr_class *cl;
+	struct tcf_result res;
+	struct tcf_proto *fl;
+	int result;
+
+	if (TC_H_MAJ(skb->priority ^ sch->handle) == 0) {
+		cl = drr_find_class(sch, skb->priority);
+		if (cl != NULL)
+			return cl;
+	}
+
+	*qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
+	fl = rcu_dereference_bh(q->filter_list);
+	result = tcf_classify(skb, NULL, fl, &res, false);
+	if (result >= 0) {
+#ifdef CONFIG_NET_CLS_ACT
+		switch (result) {
+		case TC_ACT_QUEUED:
+		case TC_ACT_STOLEN:
+		case TC_ACT_TRAP:
+			*qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN;
+			fallthrough;
+		case TC_ACT_SHOT:
+			return NULL;
+		}
+#endif
+		cl = (struct drr_class *)res.class;
+		if (cl == NULL)
+			cl = drr_find_class(sch, res.classid);
+		return cl;
+	}
+	return NULL;
+}
+
+static int drr_enqueue(struct sk_buff *skb, struct Qdisc *sch,
+		       struct sk_buff **to_free)
+{
+	unsigned int len = qdisc_pkt_len(skb);
+	struct drr_sched *q = qdisc_priv(sch);
+	struct drr_class *cl;
+	int err = 0;
+	bool first;
+
+	cl = drr_classify(skb, sch, &err);
+	if (cl == NULL) {
+		if (err & __NET_XMIT_BYPASS)
+			qdisc_qstats_drop(sch);
+		__qdisc_drop(skb, to_free);
+		return err;
+	}
+
+	first = !cl->qdisc->q.qlen;
+	err = qdisc_enqueue(skb, cl->qdisc, to_free);
+	if (unlikely(err != NET_XMIT_SUCCESS)) {
+		if (net_xmit_drop_count(err)) {
+			cl->qstats.drops++;
+			qdisc_qstats_drop(sch);
+		}
+		return err;
+	}
+
+	if (first) {
+		list_add_tail(&cl->alist, &q->active);
+		cl->deficit = cl->quantum;
+	}
+
+	sch->qstats.backlog += len;
+	sch->q.qlen++;
+	return err;
+}
+
+static struct sk_buff *drr_dequeue(struct Qdisc *sch)
+{
+	struct drr_sched *q = qdisc_priv(sch);
+	struct drr_class *cl;
+	struct sk_buff *skb;
+	unsigned int len;
+
+	if (list_empty(&q->active))
+		goto out;
+	while (1) {
+		cl = list_first_entry(&q->active, struct drr_class, alist);
+		skb = cl->qdisc->ops->peek(cl->qdisc);
+		if (skb == NULL) {
+			qdisc_warn_nonwc(__func__, cl->qdisc);
+			goto out;
+		}
+
+		len = qdisc_pkt_len(skb);
+		if (len <= cl->deficit) {
+			cl->deficit -= len;
+			skb = qdisc_dequeue_peeked(cl->qdisc);
+			if (unlikely(skb == NULL))
+				goto out;
+			if (cl->qdisc->q.qlen == 0)
+				list_del(&cl->alist);
+
+			bstats_update(&cl->bstats, skb);
+			qdisc_bstats_update(sch, skb);
+			qdisc_qstats_backlog_dec(sch, skb);
+			sch->q.qlen--;
+			return skb;
+		}
+
+		cl->deficit += cl->quantum;
+		list_move_tail(&cl->alist, &q->active);
+	}
+out:
+	return NULL;
+}
+
+static int drr_init_qdisc(struct Qdisc *sch, struct nlattr *opt,
+			  struct netlink_ext_ack *extack)
+{
+	struct drr_sched *q = qdisc_priv(sch);
+	int err;
+
+	err = tcf_block_get(&q->block, &q->filter_list, sch, extack);
+	if (err)
+		return err;
+	err = qdisc_class_hash_init(&q->clhash);
+	if (err < 0)
+		return err;
+	INIT_LIST_HEAD(&q->active);
+	return 0;
+}
+
+static void drr_reset_qdisc(struct Qdisc *sch)
+{
+	struct drr_sched *q = qdisc_priv(sch);
+	struct drr_class *cl;
+	unsigned int i;
+
+	for (i = 0; i < q->clhash.hashsize; i++) {
+		hlist_for_each_entry(cl, &q->clhash.hash[i], common.hnode) {
+			if (cl->qdisc->q.qlen)
+				list_del(&cl->alist);
+			qdisc_reset(cl->qdisc);
+		}
+	}
+}
+
+static void drr_destroy_qdisc(struct Qdisc *sch)
+{
+	struct drr_sched *q = qdisc_priv(sch);
+	struct drr_class *cl;
+	struct hlist_node *next;
+	unsigned int i;
+
+	tcf_block_put(q->block);
+
+	for (i = 0; i < q->clhash.hashsize; i++) {
+		hlist_for_each_entry_safe(cl, next, &q->clhash.hash[i],
+					  common.hnode)
+			drr_destroy_class(sch, cl);
+	}
+	qdisc_class_hash_destroy(&q->clhash);
+}
+
+static const struct Qdisc_class_ops drr_class_ops = {
+	.change		= drr_change_class,
+	.delete		= drr_delete_class,
+	.find		= drr_search_class,
+	.tcf_block	= drr_tcf_block,
+	.bind_tcf	= drr_bind_tcf,
+	.unbind_tcf	= drr_unbind_tcf,
+	.graft		= drr_graft_class,
+	.leaf		= drr_class_leaf,
+	.qlen_notify	= drr_qlen_notify,
+	.dump		= drr_dump_class,
+	.dump_stats	= drr_dump_class_stats,
+	.walk		= drr_walk,
+};
+
+static struct Qdisc_ops drr_qdisc_ops __read_mostly = {
+	.cl_ops		= &drr_class_ops,
+	.id		= "drr",
+	.priv_size	= sizeof(struct drr_sched),
+	.enqueue	= drr_enqueue,
+	.dequeue	= drr_dequeue,
+	.peek		= qdisc_peek_dequeued,
+	.init		= drr_init_qdisc,
+	.reset		= drr_reset_qdisc,
+	.destroy	= drr_destroy_qdisc,
+	.owner		= THIS_MODULE,
+};
+
+static int __init drr_init(void)
+{
+	return register_qdisc(&drr_qdisc_ops);
+}
+
+static void __exit drr_exit(void)
+{
+	unregister_qdisc(&drr_qdisc_ops);
+}
+
+module_init(drr_init);
+module_exit(drr_exit);
+MODULE_LICENSE("GPL");