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, 635 insertions, 0 deletions

diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c
new file mode 100644
index 000000000..48ed87b91
--- /dev/null
+++ b/net/sched/sch_mqprio.c
@@ -0,0 +1,635 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * net/sched/sch_mqprio.c
+ *
+ * Copyright (c) 2010 John Fastabend <john.r.fastabend@intel.com>
+ */
+
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/errno.h>
+#include <linux/skbuff.h>
+#include <linux/module.h>
+#include <net/netlink.h>
+#include <net/pkt_sched.h>
+#include <net/sch_generic.h>
+#include <net/pkt_cls.h>
+
+#include "sch_mqprio_lib.h"
+
+struct mqprio_sched {
+	struct Qdisc		**qdiscs;
+	u16 mode;
+	u16 shaper;
+	int hw_offload;
+	u32 flags;
+	u64 min_rate[TC_QOPT_MAX_QUEUE];
+	u64 max_rate[TC_QOPT_MAX_QUEUE];
+};
+
+static int mqprio_enable_offload(struct Qdisc *sch,
+				 const struct tc_mqprio_qopt *qopt,
+				 struct netlink_ext_ack *extack)
+{
+	struct tc_mqprio_qopt_offload mqprio = {.qopt = *qopt};
+	struct mqprio_sched *priv = qdisc_priv(sch);
+	struct net_device *dev = qdisc_dev(sch);
+	int err, i;
+
+	switch (priv->mode) {
+	case TC_MQPRIO_MODE_DCB:
+		if (priv->shaper != TC_MQPRIO_SHAPER_DCB)
+			return -EINVAL;
+		break;
+	case TC_MQPRIO_MODE_CHANNEL:
+		mqprio.flags = priv->flags;
+		if (priv->flags & TC_MQPRIO_F_MODE)
+			mqprio.mode = priv->mode;
+		if (priv->flags & TC_MQPRIO_F_SHAPER)
+			mqprio.shaper = priv->shaper;
+		if (priv->flags & TC_MQPRIO_F_MIN_RATE)
+			for (i = 0; i < mqprio.qopt.num_tc; i++)
+				mqprio.min_rate[i] = priv->min_rate[i];
+		if (priv->flags & TC_MQPRIO_F_MAX_RATE)
+			for (i = 0; i < mqprio.qopt.num_tc; i++)
+				mqprio.max_rate[i] = priv->max_rate[i];
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_MQPRIO,
+					    &mqprio);
+	if (err)
+		return err;
+
+	priv->hw_offload = mqprio.qopt.hw;
+
+	return 0;
+}
+
+static void mqprio_disable_offload(struct Qdisc *sch)
+{
+	struct tc_mqprio_qopt_offload mqprio = { { 0 } };
+	struct mqprio_sched *priv = qdisc_priv(sch);
+	struct net_device *dev = qdisc_dev(sch);
+
+	switch (priv->mode) {
+	case TC_MQPRIO_MODE_DCB:
+	case TC_MQPRIO_MODE_CHANNEL:
+		dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_MQPRIO,
+					      &mqprio);
+		break;
+	}
+}
+
+static void mqprio_destroy(struct Qdisc *sch)
+{
+	struct net_device *dev = qdisc_dev(sch);
+	struct mqprio_sched *priv = qdisc_priv(sch);
+	unsigned int ntx;
+
+	if (priv->qdiscs) {
+		for (ntx = 0;
+		     ntx < dev->num_tx_queues && priv->qdiscs[ntx];
+		     ntx++)
+			qdisc_put(priv->qdiscs[ntx]);
+		kfree(priv->qdiscs);
+	}
+
+	if (priv->hw_offload && dev->netdev_ops->ndo_setup_tc)
+		mqprio_disable_offload(sch);
+	else
+		netdev_set_num_tc(dev, 0);
+}
+
+static int mqprio_parse_opt(struct net_device *dev, struct tc_mqprio_qopt *qopt,
+			    const struct tc_mqprio_caps *caps,
+			    struct netlink_ext_ack *extack)
+{
+	int err;
+
+	/* Limit qopt->hw to maximum supported offload value.  Drivers have
+	 * the option of overriding this later if they don't support the a
+	 * given offload type.
+	 */
+	if (qopt->hw > TC_MQPRIO_HW_OFFLOAD_MAX)
+		qopt->hw = TC_MQPRIO_HW_OFFLOAD_MAX;
+
+	/* If hardware offload is requested, we will leave 3 options to the
+	 * device driver:
+	 * - populate the queue counts itself (and ignore what was requested)
+	 * - validate the provided queue counts by itself (and apply them)
+	 * - request queue count validation here (and apply them)
+	 */
+	err = mqprio_validate_qopt(dev, qopt,
+				   !qopt->hw || caps->validate_queue_counts,
+				   false, extack);
+	if (err)
+		return err;
+
+	/* If ndo_setup_tc is not present then hardware doesn't support offload
+	 * and we should return an error.
+	 */
+	if (qopt->hw && !dev->netdev_ops->ndo_setup_tc)
+		return -EINVAL;
+
+	return 0;
+}
+
+static const struct nla_policy mqprio_policy[TCA_MQPRIO_MAX + 1] = {
+	[TCA_MQPRIO_MODE]	= { .len = sizeof(u16) },
+	[TCA_MQPRIO_SHAPER]	= { .len = sizeof(u16) },
+	[TCA_MQPRIO_MIN_RATE64]	= { .type = NLA_NESTED },
+	[TCA_MQPRIO_MAX_RATE64]	= { .type = NLA_NESTED },
+};
+
+static int parse_attr(struct nlattr *tb[], int maxtype, struct nlattr *nla,
+		      const struct nla_policy *policy, int len)
+{
+	int nested_len = nla_len(nla) - NLA_ALIGN(len);
+
+	if (nested_len >= nla_attr_size(0))
+		return nla_parse_deprecated(tb, maxtype,
+					    nla_data(nla) + NLA_ALIGN(len),
+					    nested_len, policy, NULL);
+
+	memset(tb, 0, sizeof(struct nlattr *) * (maxtype + 1));
+	return 0;
+}
+
+static int mqprio_parse_nlattr(struct Qdisc *sch, struct tc_mqprio_qopt *qopt,
+			       struct nlattr *opt)
+{
+	struct mqprio_sched *priv = qdisc_priv(sch);
+	struct nlattr *tb[TCA_MQPRIO_MAX + 1];
+	struct nlattr *attr;
+	int i, rem, err;
+
+	err = parse_attr(tb, TCA_MQPRIO_MAX, opt, mqprio_policy,
+			 sizeof(*qopt));
+	if (err < 0)
+		return err;
+
+	if (!qopt->hw)
+		return -EINVAL;
+
+	if (tb[TCA_MQPRIO_MODE]) {
+		priv->flags |= TC_MQPRIO_F_MODE;
+		priv->mode = *(u16 *)nla_data(tb[TCA_MQPRIO_MODE]);
+	}
+
+	if (tb[TCA_MQPRIO_SHAPER]) {
+		priv->flags |= TC_MQPRIO_F_SHAPER;
+		priv->shaper = *(u16 *)nla_data(tb[TCA_MQPRIO_SHAPER]);
+	}
+
+	if (tb[TCA_MQPRIO_MIN_RATE64]) {
+		if (priv->shaper != TC_MQPRIO_SHAPER_BW_RATE)
+			return -EINVAL;
+		i = 0;
+		nla_for_each_nested(attr, tb[TCA_MQPRIO_MIN_RATE64],
+				    rem) {
+			if (nla_type(attr) != TCA_MQPRIO_MIN_RATE64)
+				return -EINVAL;
+			if (i >= qopt->num_tc)
+				break;
+			priv->min_rate[i] = *(u64 *)nla_data(attr);
+			i++;
+		}
+		priv->flags |= TC_MQPRIO_F_MIN_RATE;
+	}
+
+	if (tb[TCA_MQPRIO_MAX_RATE64]) {
+		if (priv->shaper != TC_MQPRIO_SHAPER_BW_RATE)
+			return -EINVAL;
+		i = 0;
+		nla_for_each_nested(attr, tb[TCA_MQPRIO_MAX_RATE64],
+				    rem) {
+			if (nla_type(attr) != TCA_MQPRIO_MAX_RATE64)
+				return -EINVAL;
+			if (i >= qopt->num_tc)
+				break;
+			priv->max_rate[i] = *(u64 *)nla_data(attr);
+			i++;
+		}
+		priv->flags |= TC_MQPRIO_F_MAX_RATE;
+	}
+
+	return 0;
+}
+
+static int mqprio_init(struct Qdisc *sch, struct nlattr *opt,
+		       struct netlink_ext_ack *extack)
+{
+	struct net_device *dev = qdisc_dev(sch);
+	struct mqprio_sched *priv = qdisc_priv(sch);
+	struct netdev_queue *dev_queue;
+	struct Qdisc *qdisc;
+	int i, err = -EOPNOTSUPP;
+	struct tc_mqprio_qopt *qopt = NULL;
+	struct tc_mqprio_caps caps;
+	int len;
+
+	BUILD_BUG_ON(TC_MAX_QUEUE != TC_QOPT_MAX_QUEUE);
+	BUILD_BUG_ON(TC_BITMASK != TC_QOPT_BITMASK);
+
+	if (sch->parent != TC_H_ROOT)
+		return -EOPNOTSUPP;
+
+	if (!netif_is_multiqueue(dev))
+		return -EOPNOTSUPP;
+
+	/* make certain can allocate enough classids to handle queues */
+	if (dev->num_tx_queues >= TC_H_MIN_PRIORITY)
+		return -ENOMEM;
+
+	if (!opt || nla_len(opt) < sizeof(*qopt))
+		return -EINVAL;
+
+	qdisc_offload_query_caps(dev, TC_SETUP_QDISC_MQPRIO,
+				 &caps, sizeof(caps));
+
+	qopt = nla_data(opt);
+	if (mqprio_parse_opt(dev, qopt, &caps, extack))
+		return -EINVAL;
+
+	len = nla_len(opt) - NLA_ALIGN(sizeof(*qopt));
+	if (len > 0) {
+		err = mqprio_parse_nlattr(sch, qopt, opt);
+		if (err)
+			return err;
+	}
+
+	/* pre-allocate qdisc, attachment can't fail */
+	priv->qdiscs = kcalloc(dev->num_tx_queues, sizeof(priv->qdiscs[0]),
+			       GFP_KERNEL);
+	if (!priv->qdiscs)
+		return -ENOMEM;
+
+	for (i = 0; i < dev->num_tx_queues; i++) {
+		dev_queue = netdev_get_tx_queue(dev, i);
+		qdisc = qdisc_create_dflt(dev_queue,
+					  get_default_qdisc_ops(dev, i),
+					  TC_H_MAKE(TC_H_MAJ(sch->handle),
+						    TC_H_MIN(i + 1)), extack);
+		if (!qdisc)
+			return -ENOMEM;
+
+		priv->qdiscs[i] = qdisc;
+		qdisc->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
+	}
+
+	/* If the mqprio options indicate that hardware should own
+	 * the queue mapping then run ndo_setup_tc otherwise use the
+	 * supplied and verified mapping
+	 */
+	if (qopt->hw) {
+		err = mqprio_enable_offload(sch, qopt, extack);
+		if (err)
+			return err;
+	} else {
+		netdev_set_num_tc(dev, qopt->num_tc);
+		for (i = 0; i < qopt->num_tc; i++)
+			netdev_set_tc_queue(dev, i,
+					    qopt->count[i], qopt->offset[i]);
+	}
+
+	/* Always use supplied priority mappings */
+	for (i = 0; i < TC_BITMASK + 1; i++)
+		netdev_set_prio_tc_map(dev, i, qopt->prio_tc_map[i]);
+
+	sch->flags |= TCQ_F_MQROOT;
+	return 0;
+}
+
+static void mqprio_attach(struct Qdisc *sch)
+{
+	struct net_device *dev = qdisc_dev(sch);
+	struct mqprio_sched *priv = qdisc_priv(sch);
+	struct Qdisc *qdisc, *old;
+	unsigned int ntx;
+
+	/* Attach underlying qdisc */
+	for (ntx = 0; ntx < dev->num_tx_queues; ntx++) {
+		qdisc = priv->qdiscs[ntx];
+		old = dev_graft_qdisc(qdisc->dev_queue, qdisc);
+		if (old)
+			qdisc_put(old);
+		if (ntx < dev->real_num_tx_queues)
+			qdisc_hash_add(qdisc, false);
+	}
+	kfree(priv->qdiscs);
+	priv->qdiscs = NULL;
+}
+
+static struct netdev_queue *mqprio_queue_get(struct Qdisc *sch,
+					     unsigned long cl)
+{
+	struct net_device *dev = qdisc_dev(sch);
+	unsigned long ntx = cl - 1;
+
+	if (ntx >= dev->num_tx_queues)
+		return NULL;
+	return netdev_get_tx_queue(dev, ntx);
+}
+
+static int mqprio_graft(struct Qdisc *sch, unsigned long cl, struct Qdisc *new,
+			struct Qdisc **old, struct netlink_ext_ack *extack)
+{
+	struct net_device *dev = qdisc_dev(sch);
+	struct netdev_queue *dev_queue = mqprio_queue_get(sch, cl);
+
+	if (!dev_queue)
+		return -EINVAL;
+
+	if (dev->flags & IFF_UP)
+		dev_deactivate(dev);
+
+	*old = dev_graft_qdisc(dev_queue, new);
+
+	if (new)
+		new->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
+
+	if (dev->flags & IFF_UP)
+		dev_activate(dev);
+
+	return 0;
+}
+
+static int dump_rates(struct mqprio_sched *priv,
+		      struct tc_mqprio_qopt *opt, struct sk_buff *skb)
+{
+	struct nlattr *nest;
+	int i;
+
+	if (priv->flags & TC_MQPRIO_F_MIN_RATE) {
+		nest = nla_nest_start_noflag(skb, TCA_MQPRIO_MIN_RATE64);
+		if (!nest)
+			goto nla_put_failure;
+
+		for (i = 0; i < opt->num_tc; i++) {
+			if (nla_put(skb, TCA_MQPRIO_MIN_RATE64,
+				    sizeof(priv->min_rate[i]),
+				    &priv->min_rate[i]))
+				goto nla_put_failure;
+		}
+		nla_nest_end(skb, nest);
+	}
+
+	if (priv->flags & TC_MQPRIO_F_MAX_RATE) {
+		nest = nla_nest_start_noflag(skb, TCA_MQPRIO_MAX_RATE64);
+		if (!nest)
+			goto nla_put_failure;
+
+		for (i = 0; i < opt->num_tc; i++) {
+			if (nla_put(skb, TCA_MQPRIO_MAX_RATE64,
+				    sizeof(priv->max_rate[i]),
+				    &priv->max_rate[i]))
+				goto nla_put_failure;
+		}
+		nla_nest_end(skb, nest);
+	}
+	return 0;
+
+nla_put_failure:
+	nla_nest_cancel(skb, nest);
+	return -1;
+}
+
+static int mqprio_dump(struct Qdisc *sch, struct sk_buff *skb)
+{
+	struct net_device *dev = qdisc_dev(sch);
+	struct mqprio_sched *priv = qdisc_priv(sch);
+	struct nlattr *nla = (struct nlattr *)skb_tail_pointer(skb);
+	struct tc_mqprio_qopt opt = { 0 };
+	struct Qdisc *qdisc;
+	unsigned int ntx;
+
+	sch->q.qlen = 0;
+	gnet_stats_basic_sync_init(&sch->bstats);
+	memset(&sch->qstats, 0, sizeof(sch->qstats));
+
+	/* MQ supports lockless qdiscs. However, statistics accounting needs
+	 * to account for all, none, or a mix of locked and unlocked child
+	 * qdiscs. Percpu stats are added to counters in-band and locking
+	 * qdisc totals are added at end.
+	 */
+	for (ntx = 0; ntx < dev->num_tx_queues; ntx++) {
+		qdisc = netdev_get_tx_queue(dev, ntx)->qdisc_sleeping;
+		spin_lock_bh(qdisc_lock(qdisc));
+
+		gnet_stats_add_basic(&sch->bstats, qdisc->cpu_bstats,
+				     &qdisc->bstats, false);
+		gnet_stats_add_queue(&sch->qstats, qdisc->cpu_qstats,
+				     &qdisc->qstats);
+		sch->q.qlen += qdisc_qlen(qdisc);
+
+		spin_unlock_bh(qdisc_lock(qdisc));
+	}
+
+	mqprio_qopt_reconstruct(dev, &opt);
+	opt.hw = priv->hw_offload;
+
+	if (nla_put(skb, TCA_OPTIONS, sizeof(opt), &opt))
+		goto nla_put_failure;
+
+	if ((priv->flags & TC_MQPRIO_F_MODE) &&
+	    nla_put_u16(skb, TCA_MQPRIO_MODE, priv->mode))
+		goto nla_put_failure;
+
+	if ((priv->flags & TC_MQPRIO_F_SHAPER) &&
+	    nla_put_u16(skb, TCA_MQPRIO_SHAPER, priv->shaper))
+		goto nla_put_failure;
+
+	if ((priv->flags & TC_MQPRIO_F_MIN_RATE ||
+	     priv->flags & TC_MQPRIO_F_MAX_RATE) &&
+	    (dump_rates(priv, &opt, skb) != 0))
+		goto nla_put_failure;
+
+	return nla_nest_end(skb, nla);
+nla_put_failure:
+	nlmsg_trim(skb, nla);
+	return -1;
+}
+
+static struct Qdisc *mqprio_leaf(struct Qdisc *sch, unsigned long cl)
+{
+	struct netdev_queue *dev_queue = mqprio_queue_get(sch, cl);
+
+	if (!dev_queue)
+		return NULL;
+
+	return dev_queue->qdisc_sleeping;
+}
+
+static unsigned long mqprio_find(struct Qdisc *sch, u32 classid)
+{
+	struct net_device *dev = qdisc_dev(sch);
+	unsigned int ntx = TC_H_MIN(classid);
+
+	/* There are essentially two regions here that have valid classid
+	 * values. The first region will have a classid value of 1 through
+	 * num_tx_queues. All of these are backed by actual Qdiscs.
+	 */
+	if (ntx < TC_H_MIN_PRIORITY)
+		return (ntx <= dev->num_tx_queues) ? ntx : 0;
+
+	/* The second region represents the hardware traffic classes. These
+	 * are represented by classid values of TC_H_MIN_PRIORITY through
+	 * TC_H_MIN_PRIORITY + netdev_get_num_tc - 1
+	 */
+	return ((ntx - TC_H_MIN_PRIORITY) < netdev_get_num_tc(dev)) ? ntx : 0;
+}
+
+static int mqprio_dump_class(struct Qdisc *sch, unsigned long cl,
+			 struct sk_buff *skb, struct tcmsg *tcm)
+{
+	if (cl < TC_H_MIN_PRIORITY) {
+		struct netdev_queue *dev_queue = mqprio_queue_get(sch, cl);
+		struct net_device *dev = qdisc_dev(sch);
+		int tc = netdev_txq_to_tc(dev, cl - 1);
+
+		tcm->tcm_parent = (tc < 0) ? 0 :
+			TC_H_MAKE(TC_H_MAJ(sch->handle),
+				  TC_H_MIN(tc + TC_H_MIN_PRIORITY));
+		tcm->tcm_info = dev_queue->qdisc_sleeping->handle;
+	} else {
+		tcm->tcm_parent = TC_H_ROOT;
+		tcm->tcm_info = 0;
+	}
+	tcm->tcm_handle |= TC_H_MIN(cl);
+	return 0;
+}
+
+static int mqprio_dump_class_stats(struct Qdisc *sch, unsigned long cl,
+				   struct gnet_dump *d)
+	__releases(d->lock)
+	__acquires(d->lock)
+{
+	if (cl >= TC_H_MIN_PRIORITY) {
+		int i;
+		__u32 qlen;
+		struct gnet_stats_queue qstats = {0};
+		struct gnet_stats_basic_sync bstats;
+		struct net_device *dev = qdisc_dev(sch);
+		struct netdev_tc_txq tc = dev->tc_to_txq[cl & TC_BITMASK];
+
+		gnet_stats_basic_sync_init(&bstats);
+		/* Drop lock here it will be reclaimed before touching
+		 * statistics this is required because the d->lock we
+		 * hold here is the look on dev_queue->qdisc_sleeping
+		 * also acquired below.
+		 */
+		if (d->lock)
+			spin_unlock_bh(d->lock);
+
+		for (i = tc.offset; i < tc.offset + tc.count; i++) {
+			struct netdev_queue *q = netdev_get_tx_queue(dev, i);
+			struct Qdisc *qdisc = rtnl_dereference(q->qdisc);
+
+			spin_lock_bh(qdisc_lock(qdisc));
+
+			gnet_stats_add_basic(&bstats, qdisc->cpu_bstats,
+					     &qdisc->bstats, false);
+			gnet_stats_add_queue(&qstats, qdisc->cpu_qstats,
+					     &qdisc->qstats);
+			sch->q.qlen += qdisc_qlen(qdisc);
+
+			spin_unlock_bh(qdisc_lock(qdisc));
+		}
+		qlen = qdisc_qlen(sch) + qstats.qlen;
+
+		/* Reclaim root sleeping lock before completing stats */
+		if (d->lock)
+			spin_lock_bh(d->lock);
+		if (gnet_stats_copy_basic(d, NULL, &bstats, false) < 0 ||
+		    gnet_stats_copy_queue(d, NULL, &qstats, qlen) < 0)
+			return -1;
+	} else {
+		struct netdev_queue *dev_queue = mqprio_queue_get(sch, cl);
+
+		sch = dev_queue->qdisc_sleeping;
+		if (gnet_stats_copy_basic(d, sch->cpu_bstats,
+					  &sch->bstats, true) < 0 ||
+		    qdisc_qstats_copy(d, sch) < 0)
+			return -1;
+	}
+	return 0;
+}
+
+static void mqprio_walk(struct Qdisc *sch, struct qdisc_walker *arg)
+{
+	struct net_device *dev = qdisc_dev(sch);
+	unsigned long ntx;
+
+	if (arg->stop)
+		return;
+
+	/* Walk hierarchy with a virtual class per tc */
+	arg->count = arg->skip;
+	for (ntx = arg->skip; ntx < netdev_get_num_tc(dev); ntx++) {
+		if (!tc_qdisc_stats_dump(sch, ntx + TC_H_MIN_PRIORITY, arg))
+			return;
+	}
+
+	/* Pad the values and skip over unused traffic classes */
+	if (ntx < TC_MAX_QUEUE) {
+		arg->count = TC_MAX_QUEUE;
+		ntx = TC_MAX_QUEUE;
+	}
+
+	/* Reset offset, sort out remaining per-queue qdiscs */
+	for (ntx -= TC_MAX_QUEUE; ntx < dev->num_tx_queues; ntx++) {
+		if (arg->fn(sch, ntx + 1, arg) < 0) {
+			arg->stop = 1;
+			return;
+		}
+		arg->count++;
+	}
+}
+
+static struct netdev_queue *mqprio_select_queue(struct Qdisc *sch,
+						struct tcmsg *tcm)
+{
+	return mqprio_queue_get(sch, TC_H_MIN(tcm->tcm_parent));
+}
+
+static const struct Qdisc_class_ops mqprio_class_ops = {
+	.graft		= mqprio_graft,
+	.leaf		= mqprio_leaf,
+	.find		= mqprio_find,
+	.walk		= mqprio_walk,
+	.dump		= mqprio_dump_class,
+	.dump_stats	= mqprio_dump_class_stats,
+	.select_queue	= mqprio_select_queue,
+};
+
+static struct Qdisc_ops mqprio_qdisc_ops __read_mostly = {
+	.cl_ops		= &mqprio_class_ops,
+	.id		= "mqprio",
+	.priv_size	= sizeof(struct mqprio_sched),
+	.init		= mqprio_init,
+	.destroy	= mqprio_destroy,
+	.attach		= mqprio_attach,
+	.change_real_num_tx = mq_change_real_num_tx,
+	.dump		= mqprio_dump,
+	.owner		= THIS_MODULE,
+};
+
+static int __init mqprio_module_init(void)
+{
+	return register_qdisc(&mqprio_qdisc_ops);
+}
+
+static void __exit mqprio_module_exit(void)
+{
+	unregister_qdisc(&mqprio_qdisc_ops);
+}
+
+module_init(mqprio_module_init);
+module_exit(mqprio_module_exit);
+
+MODULE_LICENSE("GPL");