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_etf.c b/net/sched/sch_etf.c
new file mode 100644
index 000000000..61d1f0e32
--- /dev/null
+++ b/net/sched/sch_etf.c
@@ -0,0 +1,515 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/* net/sched/sch_etf.c  Earliest TxTime First queueing discipline.
+ *
+ * Authors:	Jesus Sanchez-Palencia <jesus.sanchez-palencia@intel.com>
+ *		Vinicius Costa Gomes <vinicius.gomes@intel.com>
+ */
+
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/errno.h>
+#include <linux/errqueue.h>
+#include <linux/rbtree.h>
+#include <linux/skbuff.h>
+#include <linux/posix-timers.h>
+#include <net/netlink.h>
+#include <net/sch_generic.h>
+#include <net/pkt_sched.h>
+#include <net/sock.h>
+
+#define DEADLINE_MODE_IS_ON(x) ((x)->flags & TC_ETF_DEADLINE_MODE_ON)
+#define OFFLOAD_IS_ON(x) ((x)->flags & TC_ETF_OFFLOAD_ON)
+#define SKIP_SOCK_CHECK_IS_SET(x) ((x)->flags & TC_ETF_SKIP_SOCK_CHECK)
+
+struct etf_sched_data {
+	bool offload;
+	bool deadline_mode;
+	bool skip_sock_check;
+	int clockid;
+	int queue;
+	s32 delta; /* in ns */
+	ktime_t last; /* The txtime of the last skb sent to the netdevice. */
+	struct rb_root_cached head;
+	struct qdisc_watchdog watchdog;
+	ktime_t (*get_time)(void);
+};
+
+static const struct nla_policy etf_policy[TCA_ETF_MAX + 1] = {
+	[TCA_ETF_PARMS]	= { .len = sizeof(struct tc_etf_qopt) },
+};
+
+static inline int validate_input_params(struct tc_etf_qopt *qopt,
+					struct netlink_ext_ack *extack)
+{
+	/* Check if params comply to the following rules:
+	 *	* Clockid and delta must be valid.
+	 *
+	 *	* Dynamic clockids are not supported.
+	 *
+	 *	* Delta must be a positive integer.
+	 *
+	 * Also note that for the HW offload case, we must
+	 * expect that system clocks have been synchronized to PHC.
+	 */
+	if (qopt->clockid < 0) {
+		NL_SET_ERR_MSG(extack, "Dynamic clockids are not supported");
+		return -ENOTSUPP;
+	}
+
+	if (qopt->clockid != CLOCK_TAI) {
+		NL_SET_ERR_MSG(extack, "Invalid clockid. CLOCK_TAI must be used");
+		return -EINVAL;
+	}
+
+	if (qopt->delta < 0) {
+		NL_SET_ERR_MSG(extack, "Delta must be positive");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static bool is_packet_valid(struct Qdisc *sch, struct sk_buff *nskb)
+{
+	struct etf_sched_data *q = qdisc_priv(sch);
+	ktime_t txtime = nskb->tstamp;
+	struct sock *sk = nskb->sk;
+	ktime_t now;
+
+	if (q->skip_sock_check)
+		goto skip;
+
+	if (!sk || !sk_fullsock(sk))
+		return false;
+
+	if (!sock_flag(sk, SOCK_TXTIME))
+		return false;
+
+	/* We don't perform crosstimestamping.
+	 * Drop if packet's clockid differs from qdisc's.
+	 */
+	if (sk->sk_clockid != q->clockid)
+		return false;
+
+	if (sk->sk_txtime_deadline_mode != q->deadline_mode)
+		return false;
+
+skip:
+	now = q->get_time();
+	if (ktime_before(txtime, now) || ktime_before(txtime, q->last))
+		return false;
+
+	return true;
+}
+
+static struct sk_buff *etf_peek_timesortedlist(struct Qdisc *sch)
+{
+	struct etf_sched_data *q = qdisc_priv(sch);
+	struct rb_node *p;
+
+	p = rb_first_cached(&q->head);
+	if (!p)
+		return NULL;
+
+	return rb_to_skb(p);
+}
+
+static void reset_watchdog(struct Qdisc *sch)
+{
+	struct etf_sched_data *q = qdisc_priv(sch);
+	struct sk_buff *skb = etf_peek_timesortedlist(sch);
+	ktime_t next;
+
+	if (!skb) {
+		qdisc_watchdog_cancel(&q->watchdog);
+		return;
+	}
+
+	next = ktime_sub_ns(skb->tstamp, q->delta);
+	qdisc_watchdog_schedule_ns(&q->watchdog, ktime_to_ns(next));
+}
+
+static void report_sock_error(struct sk_buff *skb, u32 err, u8 code)
+{
+	struct sock_exterr_skb *serr;
+	struct sk_buff *clone;
+	ktime_t txtime = skb->tstamp;
+	struct sock *sk = skb->sk;
+
+	if (!sk || !sk_fullsock(sk) || !(sk->sk_txtime_report_errors))
+		return;
+
+	clone = skb_clone(skb, GFP_ATOMIC);
+	if (!clone)
+		return;
+
+	serr = SKB_EXT_ERR(clone);
+	serr->ee.ee_errno = err;
+	serr->ee.ee_origin = SO_EE_ORIGIN_TXTIME;
+	serr->ee.ee_type = 0;
+	serr->ee.ee_code = code;
+	serr->ee.ee_pad = 0;
+	serr->ee.ee_data = (txtime >> 32); /* high part of tstamp */
+	serr->ee.ee_info = txtime; /* low part of tstamp */
+
+	if (sock_queue_err_skb(sk, clone))
+		kfree_skb(clone);
+}
+
+static int etf_enqueue_timesortedlist(struct sk_buff *nskb, struct Qdisc *sch,
+				      struct sk_buff **to_free)
+{
+	struct etf_sched_data *q = qdisc_priv(sch);
+	struct rb_node **p = &q->head.rb_root.rb_node, *parent = NULL;
+	ktime_t txtime = nskb->tstamp;
+	bool leftmost = true;
+
+	if (!is_packet_valid(sch, nskb)) {
+		report_sock_error(nskb, EINVAL,
+				  SO_EE_CODE_TXTIME_INVALID_PARAM);
+		return qdisc_drop(nskb, sch, to_free);
+	}
+
+	while (*p) {
+		struct sk_buff *skb;
+
+		parent = *p;
+		skb = rb_to_skb(parent);
+		if (ktime_compare(txtime, skb->tstamp) >= 0) {
+			p = &parent->rb_right;
+			leftmost = false;
+		} else {
+			p = &parent->rb_left;
+		}
+	}
+	rb_link_node(&nskb->rbnode, parent, p);
+	rb_insert_color_cached(&nskb->rbnode, &q->head, leftmost);
+
+	qdisc_qstats_backlog_inc(sch, nskb);
+	sch->q.qlen++;
+
+	/* Now we may need to re-arm the qdisc watchdog for the next packet. */
+	reset_watchdog(sch);
+
+	return NET_XMIT_SUCCESS;
+}
+
+static void timesortedlist_drop(struct Qdisc *sch, struct sk_buff *skb,
+				ktime_t now)
+{
+	struct etf_sched_data *q = qdisc_priv(sch);
+	struct sk_buff *to_free = NULL;
+	struct sk_buff *tmp = NULL;
+
+	skb_rbtree_walk_from_safe(skb, tmp) {
+		if (ktime_after(skb->tstamp, now))
+			break;
+
+		rb_erase_cached(&skb->rbnode, &q->head);
+
+		/* The rbnode field in the skb re-uses these fields, now that
+		 * we are done with the rbnode, reset them.
+		 */
+		skb->next = NULL;
+		skb->prev = NULL;
+		skb->dev = qdisc_dev(sch);
+
+		report_sock_error(skb, ECANCELED, SO_EE_CODE_TXTIME_MISSED);
+
+		qdisc_qstats_backlog_dec(sch, skb);
+		qdisc_drop(skb, sch, &to_free);
+		qdisc_qstats_overlimit(sch);
+		sch->q.qlen--;
+	}
+
+	kfree_skb_list(to_free);
+}
+
+static void timesortedlist_remove(struct Qdisc *sch, struct sk_buff *skb)
+{
+	struct etf_sched_data *q = qdisc_priv(sch);
+
+	rb_erase_cached(&skb->rbnode, &q->head);
+
+	/* The rbnode field in the skb re-uses these fields, now that
+	 * we are done with the rbnode, reset them.
+	 */
+	skb->next = NULL;
+	skb->prev = NULL;
+	skb->dev = qdisc_dev(sch);
+
+	qdisc_qstats_backlog_dec(sch, skb);
+
+	qdisc_bstats_update(sch, skb);
+
+	q->last = skb->tstamp;
+
+	sch->q.qlen--;
+}
+
+static struct sk_buff *etf_dequeue_timesortedlist(struct Qdisc *sch)
+{
+	struct etf_sched_data *q = qdisc_priv(sch);
+	struct sk_buff *skb;
+	ktime_t now, next;
+
+	skb = etf_peek_timesortedlist(sch);
+	if (!skb)
+		return NULL;
+
+	now = q->get_time();
+
+	/* Drop if packet has expired while in queue. */
+	if (ktime_before(skb->tstamp, now)) {
+		timesortedlist_drop(sch, skb, now);
+		skb = NULL;
+		goto out;
+	}
+
+	/* When in deadline mode, dequeue as soon as possible and change the
+	 * txtime from deadline to (now + delta).
+	 */
+	if (q->deadline_mode) {
+		timesortedlist_remove(sch, skb);
+		skb->tstamp = now;
+		goto out;
+	}
+
+	next = ktime_sub_ns(skb->tstamp, q->delta);
+
+	/* Dequeue only if now is within the [txtime - delta, txtime] range. */
+	if (ktime_after(now, next))
+		timesortedlist_remove(sch, skb);
+	else
+		skb = NULL;
+
+out:
+	/* Now we may need to re-arm the qdisc watchdog for the next packet. */
+	reset_watchdog(sch);
+
+	return skb;
+}
+
+static void etf_disable_offload(struct net_device *dev,
+				struct etf_sched_data *q)
+{
+	struct tc_etf_qopt_offload etf = { };
+	const struct net_device_ops *ops;
+	int err;
+
+	if (!q->offload)
+		return;
+
+	ops = dev->netdev_ops;
+	if (!ops->ndo_setup_tc)
+		return;
+
+	etf.queue = q->queue;
+	etf.enable = 0;
+
+	err = ops->ndo_setup_tc(dev, TC_SETUP_QDISC_ETF, &etf);
+	if (err < 0)
+		pr_warn("Couldn't disable ETF offload for queue %d\n",
+			etf.queue);
+}
+
+static int etf_enable_offload(struct net_device *dev, struct etf_sched_data *q,
+			      struct netlink_ext_ack *extack)
+{
+	const struct net_device_ops *ops = dev->netdev_ops;
+	struct tc_etf_qopt_offload etf = { };
+	int err;
+
+	if (!ops->ndo_setup_tc) {
+		NL_SET_ERR_MSG(extack, "Specified device does not support ETF offload");
+		return -EOPNOTSUPP;
+	}
+
+	etf.queue = q->queue;
+	etf.enable = 1;
+
+	err = ops->ndo_setup_tc(dev, TC_SETUP_QDISC_ETF, &etf);
+	if (err < 0) {
+		NL_SET_ERR_MSG(extack, "Specified device failed to setup ETF hardware offload");
+		return err;
+	}
+
+	return 0;
+}
+
+static int etf_init(struct Qdisc *sch, struct nlattr *opt,
+		    struct netlink_ext_ack *extack)
+{
+	struct etf_sched_data *q = qdisc_priv(sch);
+	struct net_device *dev = qdisc_dev(sch);
+	struct nlattr *tb[TCA_ETF_MAX + 1];
+	struct tc_etf_qopt *qopt;
+	int err;
+
+	if (!opt) {
+		NL_SET_ERR_MSG(extack,
+			       "Missing ETF qdisc options which are mandatory");
+		return -EINVAL;
+	}
+
+	err = nla_parse_nested_deprecated(tb, TCA_ETF_MAX, opt, etf_policy,
+					  extack);
+	if (err < 0)
+		return err;
+
+	if (!tb[TCA_ETF_PARMS]) {
+		NL_SET_ERR_MSG(extack, "Missing mandatory ETF parameters");
+		return -EINVAL;
+	}
+
+	qopt = nla_data(tb[TCA_ETF_PARMS]);
+
+	pr_debug("delta %d clockid %d offload %s deadline %s\n",
+		 qopt->delta, qopt->clockid,
+		 OFFLOAD_IS_ON(qopt) ? "on" : "off",
+		 DEADLINE_MODE_IS_ON(qopt) ? "on" : "off");
+
+	err = validate_input_params(qopt, extack);
+	if (err < 0)
+		return err;
+
+	q->queue = sch->dev_queue - netdev_get_tx_queue(dev, 0);
+
+	if (OFFLOAD_IS_ON(qopt)) {
+		err = etf_enable_offload(dev, q, extack);
+		if (err < 0)
+			return err;
+	}
+
+	/* Everything went OK, save the parameters used. */
+	q->delta = qopt->delta;
+	q->clockid = qopt->clockid;
+	q->offload = OFFLOAD_IS_ON(qopt);
+	q->deadline_mode = DEADLINE_MODE_IS_ON(qopt);
+	q->skip_sock_check = SKIP_SOCK_CHECK_IS_SET(qopt);
+
+	switch (q->clockid) {
+	case CLOCK_REALTIME:
+		q->get_time = ktime_get_real;
+		break;
+	case CLOCK_MONOTONIC:
+		q->get_time = ktime_get;
+		break;
+	case CLOCK_BOOTTIME:
+		q->get_time = ktime_get_boottime;
+		break;
+	case CLOCK_TAI:
+		q->get_time = ktime_get_clocktai;
+		break;
+	default:
+		NL_SET_ERR_MSG(extack, "Clockid is not supported");
+		return -ENOTSUPP;
+	}
+
+	qdisc_watchdog_init_clockid(&q->watchdog, sch, q->clockid);
+
+	return 0;
+}
+
+static void timesortedlist_clear(struct Qdisc *sch)
+{
+	struct etf_sched_data *q = qdisc_priv(sch);
+	struct rb_node *p = rb_first_cached(&q->head);
+
+	while (p) {
+		struct sk_buff *skb = rb_to_skb(p);
+
+		p = rb_next(p);
+
+		rb_erase_cached(&skb->rbnode, &q->head);
+		rtnl_kfree_skbs(skb, skb);
+		sch->q.qlen--;
+	}
+}
+
+static void etf_reset(struct Qdisc *sch)
+{
+	struct etf_sched_data *q = qdisc_priv(sch);
+
+	/* Only cancel watchdog if it's been initialized. */
+	if (q->watchdog.qdisc == sch)
+		qdisc_watchdog_cancel(&q->watchdog);
+
+	/* No matter which mode we are on, it's safe to clear both lists. */
+	timesortedlist_clear(sch);
+	__qdisc_reset_queue(&sch->q);
+
+	q->last = 0;
+}
+
+static void etf_destroy(struct Qdisc *sch)
+{
+	struct etf_sched_data *q = qdisc_priv(sch);
+	struct net_device *dev = qdisc_dev(sch);
+
+	/* Only cancel watchdog if it's been initialized. */
+	if (q->watchdog.qdisc == sch)
+		qdisc_watchdog_cancel(&q->watchdog);
+
+	etf_disable_offload(dev, q);
+}
+
+static int etf_dump(struct Qdisc *sch, struct sk_buff *skb)
+{
+	struct etf_sched_data *q = qdisc_priv(sch);
+	struct tc_etf_qopt opt = { };
+	struct nlattr *nest;
+
+	nest = nla_nest_start_noflag(skb, TCA_OPTIONS);
+	if (!nest)
+		goto nla_put_failure;
+
+	opt.delta = q->delta;
+	opt.clockid = q->clockid;
+	if (q->offload)
+		opt.flags |= TC_ETF_OFFLOAD_ON;
+
+	if (q->deadline_mode)
+		opt.flags |= TC_ETF_DEADLINE_MODE_ON;
+
+	if (q->skip_sock_check)
+		opt.flags |= TC_ETF_SKIP_SOCK_CHECK;
+
+	if (nla_put(skb, TCA_ETF_PARMS, sizeof(opt), &opt))
+		goto nla_put_failure;
+
+	return nla_nest_end(skb, nest);
+
+nla_put_failure:
+	nla_nest_cancel(skb, nest);
+	return -1;
+}
+
+static struct Qdisc_ops etf_qdisc_ops __read_mostly = {
+	.id		=	"etf",
+	.priv_size	=	sizeof(struct etf_sched_data),
+	.enqueue	=	etf_enqueue_timesortedlist,
+	.dequeue	=	etf_dequeue_timesortedlist,
+	.peek		=	etf_peek_timesortedlist,
+	.init		=	etf_init,
+	.reset		=	etf_reset,
+	.destroy	=	etf_destroy,
+	.dump		=	etf_dump,
+	.owner		=	THIS_MODULE,
+};
+
+static int __init etf_module_init(void)
+{
+	return register_qdisc(&etf_qdisc_ops);
+}
+
+static void __exit etf_module_exit(void)
+{
+	unregister_qdisc(&etf_qdisc_ops);
+}
+module_init(etf_module_init)
+module_exit(etf_module_exit)
+MODULE_LICENSE("GPL");