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, 622 insertions, 0 deletions

diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c
new file mode 100644
index 000000000..277ad11f4
--- /dev/null
+++ b/net/sched/sch_tbf.c
@@ -0,0 +1,622 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * net/sched/sch_tbf.c	Token Bucket Filter queue.
+ *
+ * Authors:	Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
+ *		Dmitry Torokhov <dtor@mail.ru> - allow attaching inner qdiscs -
+ *						 original idea by Martin Devera
+ */
+
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/errno.h>
+#include <linux/skbuff.h>
+#include <net/netlink.h>
+#include <net/sch_generic.h>
+#include <net/pkt_cls.h>
+#include <net/pkt_sched.h>
+
+
+/*	Simple Token Bucket Filter.
+	=======================================
+
+	SOURCE.
+	-------
+
+	None.
+
+	Description.
+	------------
+
+	A data flow obeys TBF with rate R and depth B, if for any
+	time interval t_i...t_f the number of transmitted bits
+	does not exceed B + R*(t_f-t_i).
+
+	Packetized version of this definition:
+	The sequence of packets of sizes s_i served at moments t_i
+	obeys TBF, if for any i<=k:
+
+	s_i+....+s_k <= B + R*(t_k - t_i)
+
+	Algorithm.
+	----------
+
+	Let N(t_i) be B/R initially and N(t) grow continuously with time as:
+
+	N(t+delta) = min{B/R, N(t) + delta}
+
+	If the first packet in queue has length S, it may be
+	transmitted only at the time t_* when S/R <= N(t_*),
+	and in this case N(t) jumps:
+
+	N(t_* + 0) = N(t_* - 0) - S/R.
+
+
+
+	Actually, QoS requires two TBF to be applied to a data stream.
+	One of them controls steady state burst size, another
+	one with rate P (peak rate) and depth M (equal to link MTU)
+	limits bursts at a smaller time scale.
+
+	It is easy to see that P>R, and B>M. If P is infinity, this double
+	TBF is equivalent to a single one.
+
+	When TBF works in reshaping mode, latency is estimated as:
+
+	lat = max ((L-B)/R, (L-M)/P)
+
+
+	NOTES.
+	------
+
+	If TBF throttles, it starts a watchdog timer, which will wake it up
+	when it is ready to transmit.
+	Note that the minimal timer resolution is 1/HZ.
+	If no new packets arrive during this period,
+	or if the device is not awaken by EOI for some previous packet,
+	TBF can stop its activity for 1/HZ.
+
+
+	This means, that with depth B, the maximal rate is
+
+	R_crit = B*HZ
+
+	F.e. for 10Mbit ethernet and HZ=100 the minimal allowed B is ~10Kbytes.
+
+	Note that the peak rate TBF is much more tough: with MTU 1500
+	P_crit = 150Kbytes/sec. So, if you need greater peak
+	rates, use alpha with HZ=1000 :-)
+
+	With classful TBF, limit is just kept for backwards compatibility.
+	It is passed to the default bfifo qdisc - if the inner qdisc is
+	changed the limit is not effective anymore.
+*/
+
+struct tbf_sched_data {
+/* Parameters */
+	u32		limit;		/* Maximal length of backlog: bytes */
+	u32		max_size;
+	s64		buffer;		/* Token bucket depth/rate: MUST BE >= MTU/B */
+	s64		mtu;
+	struct psched_ratecfg rate;
+	struct psched_ratecfg peak;
+
+/* Variables */
+	s64	tokens;			/* Current number of B tokens */
+	s64	ptokens;		/* Current number of P tokens */
+	s64	t_c;			/* Time check-point */
+	struct Qdisc	*qdisc;		/* Inner qdisc, default - bfifo queue */
+	struct qdisc_watchdog watchdog;	/* Watchdog timer */
+};
+
+
+/* Time to Length, convert time in ns to length in bytes
+ * to determinate how many bytes can be sent in given time.
+ */
+static u64 psched_ns_t2l(const struct psched_ratecfg *r,
+			 u64 time_in_ns)
+{
+	/* The formula is :
+	 * len = (time_in_ns * r->rate_bytes_ps) / NSEC_PER_SEC
+	 */
+	u64 len = time_in_ns * r->rate_bytes_ps;
+
+	do_div(len, NSEC_PER_SEC);
+
+	if (unlikely(r->linklayer == TC_LINKLAYER_ATM)) {
+		do_div(len, 53);
+		len = len * 48;
+	}
+
+	if (len > r->overhead)
+		len -= r->overhead;
+	else
+		len = 0;
+
+	return len;
+}
+
+static void tbf_offload_change(struct Qdisc *sch)
+{
+	struct tbf_sched_data *q = qdisc_priv(sch);
+	struct net_device *dev = qdisc_dev(sch);
+	struct tc_tbf_qopt_offload qopt;
+
+	if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc)
+		return;
+
+	qopt.command = TC_TBF_REPLACE;
+	qopt.handle = sch->handle;
+	qopt.parent = sch->parent;
+	qopt.replace_params.rate = q->rate;
+	qopt.replace_params.max_size = q->max_size;
+	qopt.replace_params.qstats = &sch->qstats;
+
+	dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_TBF, &qopt);
+}
+
+static void tbf_offload_destroy(struct Qdisc *sch)
+{
+	struct net_device *dev = qdisc_dev(sch);
+	struct tc_tbf_qopt_offload qopt;
+
+	if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc)
+		return;
+
+	qopt.command = TC_TBF_DESTROY;
+	qopt.handle = sch->handle;
+	qopt.parent = sch->parent;
+	dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_TBF, &qopt);
+}
+
+static int tbf_offload_dump(struct Qdisc *sch)
+{
+	struct tc_tbf_qopt_offload qopt;
+
+	qopt.command = TC_TBF_STATS;
+	qopt.handle = sch->handle;
+	qopt.parent = sch->parent;
+	qopt.stats.bstats = &sch->bstats;
+	qopt.stats.qstats = &sch->qstats;
+
+	return qdisc_offload_dump_helper(sch, TC_SETUP_QDISC_TBF, &qopt);
+}
+
+static void tbf_offload_graft(struct Qdisc *sch, struct Qdisc *new,
+			      struct Qdisc *old, struct netlink_ext_ack *extack)
+{
+	struct tc_tbf_qopt_offload graft_offload = {
+		.handle		= sch->handle,
+		.parent		= sch->parent,
+		.child_handle	= new->handle,
+		.command	= TC_TBF_GRAFT,
+	};
+
+	qdisc_offload_graft_helper(qdisc_dev(sch), sch, new, old,
+				   TC_SETUP_QDISC_TBF, &graft_offload, extack);
+}
+
+/* GSO packet is too big, segment it so that tbf can transmit
+ * each segment in time
+ */
+static int tbf_segment(struct sk_buff *skb, struct Qdisc *sch,
+		       struct sk_buff **to_free)
+{
+	struct tbf_sched_data *q = qdisc_priv(sch);
+	struct sk_buff *segs, *nskb;
+	netdev_features_t features = netif_skb_features(skb);
+	unsigned int len = 0, prev_len = qdisc_pkt_len(skb);
+	int ret, nb;
+
+	segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK);
+
+	if (IS_ERR_OR_NULL(segs))
+		return qdisc_drop(skb, sch, to_free);
+
+	nb = 0;
+	skb_list_walk_safe(segs, segs, nskb) {
+		skb_mark_not_on_list(segs);
+		qdisc_skb_cb(segs)->pkt_len = segs->len;
+		len += segs->len;
+		ret = qdisc_enqueue(segs, q->qdisc, to_free);
+		if (ret != NET_XMIT_SUCCESS) {
+			if (net_xmit_drop_count(ret))
+				qdisc_qstats_drop(sch);
+		} else {
+			nb++;
+		}
+	}
+	sch->q.qlen += nb;
+	if (nb > 1)
+		qdisc_tree_reduce_backlog(sch, 1 - nb, prev_len - len);
+	consume_skb(skb);
+	return nb > 0 ? NET_XMIT_SUCCESS : NET_XMIT_DROP;
+}
+
+static int tbf_enqueue(struct sk_buff *skb, struct Qdisc *sch,
+		       struct sk_buff **to_free)
+{
+	struct tbf_sched_data *q = qdisc_priv(sch);
+	unsigned int len = qdisc_pkt_len(skb);
+	int ret;
+
+	if (qdisc_pkt_len(skb) > q->max_size) {
+		if (skb_is_gso(skb) &&
+		    skb_gso_validate_mac_len(skb, q->max_size))
+			return tbf_segment(skb, sch, to_free);
+		return qdisc_drop(skb, sch, to_free);
+	}
+	ret = qdisc_enqueue(skb, q->qdisc, to_free);
+	if (ret != NET_XMIT_SUCCESS) {
+		if (net_xmit_drop_count(ret))
+			qdisc_qstats_drop(sch);
+		return ret;
+	}
+
+	sch->qstats.backlog += len;
+	sch->q.qlen++;
+	return NET_XMIT_SUCCESS;
+}
+
+static bool tbf_peak_present(const struct tbf_sched_data *q)
+{
+	return q->peak.rate_bytes_ps;
+}
+
+static struct sk_buff *tbf_dequeue(struct Qdisc *sch)
+{
+	struct tbf_sched_data *q = qdisc_priv(sch);
+	struct sk_buff *skb;
+
+	skb = q->qdisc->ops->peek(q->qdisc);
+
+	if (skb) {
+		s64 now;
+		s64 toks;
+		s64 ptoks = 0;
+		unsigned int len = qdisc_pkt_len(skb);
+
+		now = ktime_get_ns();
+		toks = min_t(s64, now - q->t_c, q->buffer);
+
+		if (tbf_peak_present(q)) {
+			ptoks = toks + q->ptokens;
+			if (ptoks > q->mtu)
+				ptoks = q->mtu;
+			ptoks -= (s64) psched_l2t_ns(&q->peak, len);
+		}
+		toks += q->tokens;
+		if (toks > q->buffer)
+			toks = q->buffer;
+		toks -= (s64) psched_l2t_ns(&q->rate, len);
+
+		if ((toks|ptoks) >= 0) {
+			skb = qdisc_dequeue_peeked(q->qdisc);
+			if (unlikely(!skb))
+				return NULL;
+
+			q->t_c = now;
+			q->tokens = toks;
+			q->ptokens = ptoks;
+			qdisc_qstats_backlog_dec(sch, skb);
+			sch->q.qlen--;
+			qdisc_bstats_update(sch, skb);
+			return skb;
+		}
+
+		qdisc_watchdog_schedule_ns(&q->watchdog,
+					   now + max_t(long, -toks, -ptoks));
+
+		/* Maybe we have a shorter packet in the queue,
+		   which can be sent now. It sounds cool,
+		   but, however, this is wrong in principle.
+		   We MUST NOT reorder packets under these circumstances.
+
+		   Really, if we split the flow into independent
+		   subflows, it would be a very good solution.
+		   This is the main idea of all FQ algorithms
+		   (cf. CSZ, HPFQ, HFSC)
+		 */
+
+		qdisc_qstats_overlimit(sch);
+	}
+	return NULL;
+}
+
+static void tbf_reset(struct Qdisc *sch)
+{
+	struct tbf_sched_data *q = qdisc_priv(sch);
+
+	qdisc_reset(q->qdisc);
+	q->t_c = ktime_get_ns();
+	q->tokens = q->buffer;
+	q->ptokens = q->mtu;
+	qdisc_watchdog_cancel(&q->watchdog);
+}
+
+static const struct nla_policy tbf_policy[TCA_TBF_MAX + 1] = {
+	[TCA_TBF_PARMS]	= { .len = sizeof(struct tc_tbf_qopt) },
+	[TCA_TBF_RTAB]	= { .type = NLA_BINARY, .len = TC_RTAB_SIZE },
+	[TCA_TBF_PTAB]	= { .type = NLA_BINARY, .len = TC_RTAB_SIZE },
+	[TCA_TBF_RATE64]	= { .type = NLA_U64 },
+	[TCA_TBF_PRATE64]	= { .type = NLA_U64 },
+	[TCA_TBF_BURST] = { .type = NLA_U32 },
+	[TCA_TBF_PBURST] = { .type = NLA_U32 },
+};
+
+static int tbf_change(struct Qdisc *sch, struct nlattr *opt,
+		      struct netlink_ext_ack *extack)
+{
+	int err;
+	struct tbf_sched_data *q = qdisc_priv(sch);
+	struct nlattr *tb[TCA_TBF_MAX + 1];
+	struct tc_tbf_qopt *qopt;
+	struct Qdisc *child = NULL;
+	struct Qdisc *old = NULL;
+	struct psched_ratecfg rate;
+	struct psched_ratecfg peak;
+	u64 max_size;
+	s64 buffer, mtu;
+	u64 rate64 = 0, prate64 = 0;
+
+	err = nla_parse_nested_deprecated(tb, TCA_TBF_MAX, opt, tbf_policy,
+					  NULL);
+	if (err < 0)
+		return err;
+
+	err = -EINVAL;
+	if (tb[TCA_TBF_PARMS] == NULL)
+		goto done;
+
+	qopt = nla_data(tb[TCA_TBF_PARMS]);
+	if (qopt->rate.linklayer == TC_LINKLAYER_UNAWARE)
+		qdisc_put_rtab(qdisc_get_rtab(&qopt->rate,
+					      tb[TCA_TBF_RTAB],
+					      NULL));
+
+	if (qopt->peakrate.linklayer == TC_LINKLAYER_UNAWARE)
+			qdisc_put_rtab(qdisc_get_rtab(&qopt->peakrate,
+						      tb[TCA_TBF_PTAB],
+						      NULL));
+
+	buffer = min_t(u64, PSCHED_TICKS2NS(qopt->buffer), ~0U);
+	mtu = min_t(u64, PSCHED_TICKS2NS(qopt->mtu), ~0U);
+
+	if (tb[TCA_TBF_RATE64])
+		rate64 = nla_get_u64(tb[TCA_TBF_RATE64]);
+	psched_ratecfg_precompute(&rate, &qopt->rate, rate64);
+
+	if (tb[TCA_TBF_BURST]) {
+		max_size = nla_get_u32(tb[TCA_TBF_BURST]);
+		buffer = psched_l2t_ns(&rate, max_size);
+	} else {
+		max_size = min_t(u64, psched_ns_t2l(&rate, buffer), ~0U);
+	}
+
+	if (qopt->peakrate.rate) {
+		if (tb[TCA_TBF_PRATE64])
+			prate64 = nla_get_u64(tb[TCA_TBF_PRATE64]);
+		psched_ratecfg_precompute(&peak, &qopt->peakrate, prate64);
+		if (peak.rate_bytes_ps <= rate.rate_bytes_ps) {
+			pr_warn_ratelimited("sch_tbf: peakrate %llu is lower than or equals to rate %llu !\n",
+					peak.rate_bytes_ps, rate.rate_bytes_ps);
+			err = -EINVAL;
+			goto done;
+		}
+
+		if (tb[TCA_TBF_PBURST]) {
+			u32 pburst = nla_get_u32(tb[TCA_TBF_PBURST]);
+			max_size = min_t(u32, max_size, pburst);
+			mtu = psched_l2t_ns(&peak, pburst);
+		} else {
+			max_size = min_t(u64, max_size, psched_ns_t2l(&peak, mtu));
+		}
+	} else {
+		memset(&peak, 0, sizeof(peak));
+	}
+
+	if (max_size < psched_mtu(qdisc_dev(sch)))
+		pr_warn_ratelimited("sch_tbf: burst %llu is lower than device %s mtu (%u) !\n",
+				    max_size, qdisc_dev(sch)->name,
+				    psched_mtu(qdisc_dev(sch)));
+
+	if (!max_size) {
+		err = -EINVAL;
+		goto done;
+	}
+
+	if (q->qdisc != &noop_qdisc) {
+		err = fifo_set_limit(q->qdisc, qopt->limit);
+		if (err)
+			goto done;
+	} else if (qopt->limit > 0) {
+		child = fifo_create_dflt(sch, &bfifo_qdisc_ops, qopt->limit,
+					 extack);
+		if (IS_ERR(child)) {
+			err = PTR_ERR(child);
+			goto done;
+		}
+
+		/* child is fifo, no need to check for noop_qdisc */
+		qdisc_hash_add(child, true);
+	}
+
+	sch_tree_lock(sch);
+	if (child) {
+		qdisc_tree_flush_backlog(q->qdisc);
+		old = q->qdisc;
+		q->qdisc = child;
+	}
+	q->limit = qopt->limit;
+	if (tb[TCA_TBF_PBURST])
+		q->mtu = mtu;
+	else
+		q->mtu = PSCHED_TICKS2NS(qopt->mtu);
+	q->max_size = max_size;
+	if (tb[TCA_TBF_BURST])
+		q->buffer = buffer;
+	else
+		q->buffer = PSCHED_TICKS2NS(qopt->buffer);
+	q->tokens = q->buffer;
+	q->ptokens = q->mtu;
+
+	memcpy(&q->rate, &rate, sizeof(struct psched_ratecfg));
+	memcpy(&q->peak, &peak, sizeof(struct psched_ratecfg));
+
+	sch_tree_unlock(sch);
+	qdisc_put(old);
+	err = 0;
+
+	tbf_offload_change(sch);
+done:
+	return err;
+}
+
+static int tbf_init(struct Qdisc *sch, struct nlattr *opt,
+		    struct netlink_ext_ack *extack)
+{
+	struct tbf_sched_data *q = qdisc_priv(sch);
+
+	qdisc_watchdog_init(&q->watchdog, sch);
+	q->qdisc = &noop_qdisc;
+
+	if (!opt)
+		return -EINVAL;
+
+	q->t_c = ktime_get_ns();
+
+	return tbf_change(sch, opt, extack);
+}
+
+static void tbf_destroy(struct Qdisc *sch)
+{
+	struct tbf_sched_data *q = qdisc_priv(sch);
+
+	qdisc_watchdog_cancel(&q->watchdog);
+	tbf_offload_destroy(sch);
+	qdisc_put(q->qdisc);
+}
+
+static int tbf_dump(struct Qdisc *sch, struct sk_buff *skb)
+{
+	struct tbf_sched_data *q = qdisc_priv(sch);
+	struct nlattr *nest;
+	struct tc_tbf_qopt opt;
+	int err;
+
+	err = tbf_offload_dump(sch);
+	if (err)
+		return err;
+
+	nest = nla_nest_start_noflag(skb, TCA_OPTIONS);
+	if (nest == NULL)
+		goto nla_put_failure;
+
+	opt.limit = q->limit;
+	psched_ratecfg_getrate(&opt.rate, &q->rate);
+	if (tbf_peak_present(q))
+		psched_ratecfg_getrate(&opt.peakrate, &q->peak);
+	else
+		memset(&opt.peakrate, 0, sizeof(opt.peakrate));
+	opt.mtu = PSCHED_NS2TICKS(q->mtu);
+	opt.buffer = PSCHED_NS2TICKS(q->buffer);
+	if (nla_put(skb, TCA_TBF_PARMS, sizeof(opt), &opt))
+		goto nla_put_failure;
+	if (q->rate.rate_bytes_ps >= (1ULL << 32) &&
+	    nla_put_u64_64bit(skb, TCA_TBF_RATE64, q->rate.rate_bytes_ps,
+			      TCA_TBF_PAD))
+		goto nla_put_failure;
+	if (tbf_peak_present(q) &&
+	    q->peak.rate_bytes_ps >= (1ULL << 32) &&
+	    nla_put_u64_64bit(skb, TCA_TBF_PRATE64, q->peak.rate_bytes_ps,
+			      TCA_TBF_PAD))
+		goto nla_put_failure;
+
+	return nla_nest_end(skb, nest);
+
+nla_put_failure:
+	nla_nest_cancel(skb, nest);
+	return -1;
+}
+
+static int tbf_dump_class(struct Qdisc *sch, unsigned long cl,
+			  struct sk_buff *skb, struct tcmsg *tcm)
+{
+	struct tbf_sched_data *q = qdisc_priv(sch);
+
+	tcm->tcm_handle |= TC_H_MIN(1);
+	tcm->tcm_info = q->qdisc->handle;
+
+	return 0;
+}
+
+static int tbf_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new,
+		     struct Qdisc **old, struct netlink_ext_ack *extack)
+{
+	struct tbf_sched_data *q = qdisc_priv(sch);
+
+	if (new == NULL)
+		new = &noop_qdisc;
+
+	*old = qdisc_replace(sch, new, &q->qdisc);
+
+	tbf_offload_graft(sch, new, *old, extack);
+	return 0;
+}
+
+static struct Qdisc *tbf_leaf(struct Qdisc *sch, unsigned long arg)
+{
+	struct tbf_sched_data *q = qdisc_priv(sch);
+	return q->qdisc;
+}
+
+static unsigned long tbf_find(struct Qdisc *sch, u32 classid)
+{
+	return 1;
+}
+
+static void tbf_walk(struct Qdisc *sch, struct qdisc_walker *walker)
+{
+	if (!walker->stop) {
+		tc_qdisc_stats_dump(sch, 1, walker);
+	}
+}
+
+static const struct Qdisc_class_ops tbf_class_ops = {
+	.graft		=	tbf_graft,
+	.leaf		=	tbf_leaf,
+	.find		=	tbf_find,
+	.walk		=	tbf_walk,
+	.dump		=	tbf_dump_class,
+};
+
+static struct Qdisc_ops tbf_qdisc_ops __read_mostly = {
+	.next		=	NULL,
+	.cl_ops		=	&tbf_class_ops,
+	.id		=	"tbf",
+	.priv_size	=	sizeof(struct tbf_sched_data),
+	.enqueue	=	tbf_enqueue,
+	.dequeue	=	tbf_dequeue,
+	.peek		=	qdisc_peek_dequeued,
+	.init		=	tbf_init,
+	.reset		=	tbf_reset,
+	.destroy	=	tbf_destroy,
+	.change		=	tbf_change,
+	.dump		=	tbf_dump,
+	.owner		=	THIS_MODULE,
+};
+
+static int __init tbf_module_init(void)
+{
+	return register_qdisc(&tbf_qdisc_ops);
+}
+
+static void __exit tbf_module_exit(void)
+{
+	unregister_qdisc(&tbf_qdisc_ops);
+}
+module_init(tbf_module_init)
+module_exit(tbf_module_exit)
+MODULE_LICENSE("GPL");