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, 729 insertions, 0 deletions

diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c
new file mode 100644
index 000000000..1871a1c02
--- /dev/null
+++ b/net/sched/sch_sfb.c
@@ -0,0 +1,729 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * net/sched/sch_sfb.c	  Stochastic Fair Blue
+ *
+ * Copyright (c) 2008-2011 Juliusz Chroboczek <jch@pps.jussieu.fr>
+ * Copyright (c) 2011 Eric Dumazet <eric.dumazet@gmail.com>
+ *
+ * W. Feng, D. Kandlur, D. Saha, K. Shin. Blue:
+ * A New Class of Active Queue Management Algorithms.
+ * U. Michigan CSE-TR-387-99, April 1999.
+ *
+ * http://www.thefengs.com/wuchang/blue/CSE-TR-387-99.pdf
+ */
+
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/skbuff.h>
+#include <linux/random.h>
+#include <linux/siphash.h>
+#include <net/ip.h>
+#include <net/pkt_sched.h>
+#include <net/pkt_cls.h>
+#include <net/inet_ecn.h>
+
+/*
+ * SFB uses two B[l][n] : L x N arrays of bins (L levels, N bins per level)
+ * This implementation uses L = 8 and N = 16
+ * This permits us to split one 32bit hash (provided per packet by rxhash or
+ * external classifier) into 8 subhashes of 4 bits.
+ */
+#define SFB_BUCKET_SHIFT 4
+#define SFB_NUMBUCKETS	(1 << SFB_BUCKET_SHIFT) /* N bins per Level */
+#define SFB_BUCKET_MASK (SFB_NUMBUCKETS - 1)
+#define SFB_LEVELS	(32 / SFB_BUCKET_SHIFT) /* L */
+
+/* SFB algo uses a virtual queue, named "bin" */
+struct sfb_bucket {
+	u16		qlen; /* length of virtual queue */
+	u16		p_mark; /* marking probability */
+};
+
+/* We use a double buffering right before hash change
+ * (Section 4.4 of SFB reference : moving hash functions)
+ */
+struct sfb_bins {
+	siphash_key_t	  perturbation; /* siphash key */
+	struct sfb_bucket bins[SFB_LEVELS][SFB_NUMBUCKETS];
+};
+
+struct sfb_sched_data {
+	struct Qdisc	*qdisc;
+	struct tcf_proto __rcu *filter_list;
+	struct tcf_block *block;
+	unsigned long	rehash_interval;
+	unsigned long	warmup_time;	/* double buffering warmup time in jiffies */
+	u32		max;
+	u32		bin_size;	/* maximum queue length per bin */
+	u32		increment;	/* d1 */
+	u32		decrement;	/* d2 */
+	u32		limit;		/* HARD maximal queue length */
+	u32		penalty_rate;
+	u32		penalty_burst;
+	u32		tokens_avail;
+	unsigned long	rehash_time;
+	unsigned long	token_time;
+
+	u8		slot;		/* current active bins (0 or 1) */
+	bool		double_buffering;
+	struct sfb_bins bins[2];
+
+	struct {
+		u32	earlydrop;
+		u32	penaltydrop;
+		u32	bucketdrop;
+		u32	queuedrop;
+		u32	childdrop;	/* drops in child qdisc */
+		u32	marked;		/* ECN mark */
+	} stats;
+};
+
+/*
+ * Each queued skb might be hashed on one or two bins
+ * We store in skb_cb the two hash values.
+ * (A zero value means double buffering was not used)
+ */
+struct sfb_skb_cb {
+	u32 hashes[2];
+};
+
+static inline struct sfb_skb_cb *sfb_skb_cb(const struct sk_buff *skb)
+{
+	qdisc_cb_private_validate(skb, sizeof(struct sfb_skb_cb));
+	return (struct sfb_skb_cb *)qdisc_skb_cb(skb)->data;
+}
+
+/*
+ * If using 'internal' SFB flow classifier, hash comes from skb rxhash
+ * If using external classifier, hash comes from the classid.
+ */
+static u32 sfb_hash(const struct sk_buff *skb, u32 slot)
+{
+	return sfb_skb_cb(skb)->hashes[slot];
+}
+
+/* Probabilities are coded as Q0.16 fixed-point values,
+ * with 0xFFFF representing 65535/65536 (almost 1.0)
+ * Addition and subtraction are saturating in [0, 65535]
+ */
+static u32 prob_plus(u32 p1, u32 p2)
+{
+	u32 res = p1 + p2;
+
+	return min_t(u32, res, SFB_MAX_PROB);
+}
+
+static u32 prob_minus(u32 p1, u32 p2)
+{
+	return p1 > p2 ? p1 - p2 : 0;
+}
+
+static void increment_one_qlen(u32 sfbhash, u32 slot, struct sfb_sched_data *q)
+{
+	int i;
+	struct sfb_bucket *b = &q->bins[slot].bins[0][0];
+
+	for (i = 0; i < SFB_LEVELS; i++) {
+		u32 hash = sfbhash & SFB_BUCKET_MASK;
+
+		sfbhash >>= SFB_BUCKET_SHIFT;
+		if (b[hash].qlen < 0xFFFF)
+			b[hash].qlen++;
+		b += SFB_NUMBUCKETS; /* next level */
+	}
+}
+
+static void increment_qlen(const struct sfb_skb_cb *cb, struct sfb_sched_data *q)
+{
+	u32 sfbhash;
+
+	sfbhash = cb->hashes[0];
+	if (sfbhash)
+		increment_one_qlen(sfbhash, 0, q);
+
+	sfbhash = cb->hashes[1];
+	if (sfbhash)
+		increment_one_qlen(sfbhash, 1, q);
+}
+
+static void decrement_one_qlen(u32 sfbhash, u32 slot,
+			       struct sfb_sched_data *q)
+{
+	int i;
+	struct sfb_bucket *b = &q->bins[slot].bins[0][0];
+
+	for (i = 0; i < SFB_LEVELS; i++) {
+		u32 hash = sfbhash & SFB_BUCKET_MASK;
+
+		sfbhash >>= SFB_BUCKET_SHIFT;
+		if (b[hash].qlen > 0)
+			b[hash].qlen--;
+		b += SFB_NUMBUCKETS; /* next level */
+	}
+}
+
+static void decrement_qlen(const struct sk_buff *skb, struct sfb_sched_data *q)
+{
+	u32 sfbhash;
+
+	sfbhash = sfb_hash(skb, 0);
+	if (sfbhash)
+		decrement_one_qlen(sfbhash, 0, q);
+
+	sfbhash = sfb_hash(skb, 1);
+	if (sfbhash)
+		decrement_one_qlen(sfbhash, 1, q);
+}
+
+static void decrement_prob(struct sfb_bucket *b, struct sfb_sched_data *q)
+{
+	b->p_mark = prob_minus(b->p_mark, q->decrement);
+}
+
+static void increment_prob(struct sfb_bucket *b, struct sfb_sched_data *q)
+{
+	b->p_mark = prob_plus(b->p_mark, q->increment);
+}
+
+static void sfb_zero_all_buckets(struct sfb_sched_data *q)
+{
+	memset(&q->bins, 0, sizeof(q->bins));
+}
+
+/*
+ * compute max qlen, max p_mark, and avg p_mark
+ */
+static u32 sfb_compute_qlen(u32 *prob_r, u32 *avgpm_r, const struct sfb_sched_data *q)
+{
+	int i;
+	u32 qlen = 0, prob = 0, totalpm = 0;
+	const struct sfb_bucket *b = &q->bins[q->slot].bins[0][0];
+
+	for (i = 0; i < SFB_LEVELS * SFB_NUMBUCKETS; i++) {
+		if (qlen < b->qlen)
+			qlen = b->qlen;
+		totalpm += b->p_mark;
+		if (prob < b->p_mark)
+			prob = b->p_mark;
+		b++;
+	}
+	*prob_r = prob;
+	*avgpm_r = totalpm / (SFB_LEVELS * SFB_NUMBUCKETS);
+	return qlen;
+}
+
+
+static void sfb_init_perturbation(u32 slot, struct sfb_sched_data *q)
+{
+	get_random_bytes(&q->bins[slot].perturbation,
+			 sizeof(q->bins[slot].perturbation));
+}
+
+static void sfb_swap_slot(struct sfb_sched_data *q)
+{
+	sfb_init_perturbation(q->slot, q);
+	q->slot ^= 1;
+	q->double_buffering = false;
+}
+
+/* Non elastic flows are allowed to use part of the bandwidth, expressed
+ * in "penalty_rate" packets per second, with "penalty_burst" burst
+ */
+static bool sfb_rate_limit(struct sk_buff *skb, struct sfb_sched_data *q)
+{
+	if (q->penalty_rate == 0 || q->penalty_burst == 0)
+		return true;
+
+	if (q->tokens_avail < 1) {
+		unsigned long age = min(10UL * HZ, jiffies - q->token_time);
+
+		q->tokens_avail = (age * q->penalty_rate) / HZ;
+		if (q->tokens_avail > q->penalty_burst)
+			q->tokens_avail = q->penalty_burst;
+		q->token_time = jiffies;
+		if (q->tokens_avail < 1)
+			return true;
+	}
+
+	q->tokens_avail--;
+	return false;
+}
+
+static bool sfb_classify(struct sk_buff *skb, struct tcf_proto *fl,
+			 int *qerr, u32 *salt)
+{
+	struct tcf_result res;
+	int result;
+
+	result = tcf_classify(skb, NULL, fl, &res, false);
+	if (result >= 0) {
+#ifdef CONFIG_NET_CLS_ACT
+		switch (result) {
+		case TC_ACT_STOLEN:
+		case TC_ACT_QUEUED:
+		case TC_ACT_TRAP:
+			*qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN;
+			fallthrough;
+		case TC_ACT_SHOT:
+			return false;
+		}
+#endif
+		*salt = TC_H_MIN(res.classid);
+		return true;
+	}
+	return false;
+}
+
+static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch,
+		       struct sk_buff **to_free)
+{
+
+	struct sfb_sched_data *q = qdisc_priv(sch);
+	unsigned int len = qdisc_pkt_len(skb);
+	struct Qdisc *child = q->qdisc;
+	struct tcf_proto *fl;
+	struct sfb_skb_cb cb;
+	int i;
+	u32 p_min = ~0;
+	u32 minqlen = ~0;
+	u32 r, sfbhash;
+	u32 slot = q->slot;
+	int ret = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
+
+	if (unlikely(sch->q.qlen >= q->limit)) {
+		qdisc_qstats_overlimit(sch);
+		q->stats.queuedrop++;
+		goto drop;
+	}
+
+	if (q->rehash_interval > 0) {
+		unsigned long limit = q->rehash_time + q->rehash_interval;
+
+		if (unlikely(time_after(jiffies, limit))) {
+			sfb_swap_slot(q);
+			q->rehash_time = jiffies;
+		} else if (unlikely(!q->double_buffering && q->warmup_time > 0 &&
+				    time_after(jiffies, limit - q->warmup_time))) {
+			q->double_buffering = true;
+		}
+	}
+
+	fl = rcu_dereference_bh(q->filter_list);
+	if (fl) {
+		u32 salt;
+
+		/* If using external classifiers, get result and record it. */
+		if (!sfb_classify(skb, fl, &ret, &salt))
+			goto other_drop;
+		sfbhash = siphash_1u32(salt, &q->bins[slot].perturbation);
+	} else {
+		sfbhash = skb_get_hash_perturb(skb, &q->bins[slot].perturbation);
+	}
+
+
+	if (!sfbhash)
+		sfbhash = 1;
+	sfb_skb_cb(skb)->hashes[slot] = sfbhash;
+
+	for (i = 0; i < SFB_LEVELS; i++) {
+		u32 hash = sfbhash & SFB_BUCKET_MASK;
+		struct sfb_bucket *b = &q->bins[slot].bins[i][hash];
+
+		sfbhash >>= SFB_BUCKET_SHIFT;
+		if (b->qlen == 0)
+			decrement_prob(b, q);
+		else if (b->qlen >= q->bin_size)
+			increment_prob(b, q);
+		if (minqlen > b->qlen)
+			minqlen = b->qlen;
+		if (p_min > b->p_mark)
+			p_min = b->p_mark;
+	}
+
+	slot ^= 1;
+	sfb_skb_cb(skb)->hashes[slot] = 0;
+
+	if (unlikely(minqlen >= q->max)) {
+		qdisc_qstats_overlimit(sch);
+		q->stats.bucketdrop++;
+		goto drop;
+	}
+
+	if (unlikely(p_min >= SFB_MAX_PROB)) {
+		/* Inelastic flow */
+		if (q->double_buffering) {
+			sfbhash = skb_get_hash_perturb(skb,
+			    &q->bins[slot].perturbation);
+			if (!sfbhash)
+				sfbhash = 1;
+			sfb_skb_cb(skb)->hashes[slot] = sfbhash;
+
+			for (i = 0; i < SFB_LEVELS; i++) {
+				u32 hash = sfbhash & SFB_BUCKET_MASK;
+				struct sfb_bucket *b = &q->bins[slot].bins[i][hash];
+
+				sfbhash >>= SFB_BUCKET_SHIFT;
+				if (b->qlen == 0)
+					decrement_prob(b, q);
+				else if (b->qlen >= q->bin_size)
+					increment_prob(b, q);
+			}
+		}
+		if (sfb_rate_limit(skb, q)) {
+			qdisc_qstats_overlimit(sch);
+			q->stats.penaltydrop++;
+			goto drop;
+		}
+		goto enqueue;
+	}
+
+	r = get_random_u16() & SFB_MAX_PROB;
+
+	if (unlikely(r < p_min)) {
+		if (unlikely(p_min > SFB_MAX_PROB / 2)) {
+			/* If we're marking that many packets, then either
+			 * this flow is unresponsive, or we're badly congested.
+			 * In either case, we want to start dropping packets.
+			 */
+			if (r < (p_min - SFB_MAX_PROB / 2) * 2) {
+				q->stats.earlydrop++;
+				goto drop;
+			}
+		}
+		if (INET_ECN_set_ce(skb)) {
+			q->stats.marked++;
+		} else {
+			q->stats.earlydrop++;
+			goto drop;
+		}
+	}
+
+enqueue:
+	memcpy(&cb, sfb_skb_cb(skb), sizeof(cb));
+	ret = qdisc_enqueue(skb, child, to_free);
+	if (likely(ret == NET_XMIT_SUCCESS)) {
+		sch->qstats.backlog += len;
+		sch->q.qlen++;
+		increment_qlen(&cb, q);
+	} else if (net_xmit_drop_count(ret)) {
+		q->stats.childdrop++;
+		qdisc_qstats_drop(sch);
+	}
+	return ret;
+
+drop:
+	qdisc_drop(skb, sch, to_free);
+	return NET_XMIT_CN;
+other_drop:
+	if (ret & __NET_XMIT_BYPASS)
+		qdisc_qstats_drop(sch);
+	kfree_skb(skb);
+	return ret;
+}
+
+static struct sk_buff *sfb_dequeue(struct Qdisc *sch)
+{
+	struct sfb_sched_data *q = qdisc_priv(sch);
+	struct Qdisc *child = q->qdisc;
+	struct sk_buff *skb;
+
+	skb = child->dequeue(q->qdisc);
+
+	if (skb) {
+		qdisc_bstats_update(sch, skb);
+		qdisc_qstats_backlog_dec(sch, skb);
+		sch->q.qlen--;
+		decrement_qlen(skb, q);
+	}
+
+	return skb;
+}
+
+static struct sk_buff *sfb_peek(struct Qdisc *sch)
+{
+	struct sfb_sched_data *q = qdisc_priv(sch);
+	struct Qdisc *child = q->qdisc;
+
+	return child->ops->peek(child);
+}
+
+/* No sfb_drop -- impossible since the child doesn't return the dropped skb. */
+
+static void sfb_reset(struct Qdisc *sch)
+{
+	struct sfb_sched_data *q = qdisc_priv(sch);
+
+	if (likely(q->qdisc))
+		qdisc_reset(q->qdisc);
+	q->slot = 0;
+	q->double_buffering = false;
+	sfb_zero_all_buckets(q);
+	sfb_init_perturbation(0, q);
+}
+
+static void sfb_destroy(struct Qdisc *sch)
+{
+	struct sfb_sched_data *q = qdisc_priv(sch);
+
+	tcf_block_put(q->block);
+	qdisc_put(q->qdisc);
+}
+
+static const struct nla_policy sfb_policy[TCA_SFB_MAX + 1] = {
+	[TCA_SFB_PARMS]	= { .len = sizeof(struct tc_sfb_qopt) },
+};
+
+static const struct tc_sfb_qopt sfb_default_ops = {
+	.rehash_interval = 600 * MSEC_PER_SEC,
+	.warmup_time = 60 * MSEC_PER_SEC,
+	.limit = 0,
+	.max = 25,
+	.bin_size = 20,
+	.increment = (SFB_MAX_PROB + 500) / 1000, /* 0.1 % */
+	.decrement = (SFB_MAX_PROB + 3000) / 6000,
+	.penalty_rate = 10,
+	.penalty_burst = 20,
+};
+
+static int sfb_change(struct Qdisc *sch, struct nlattr *opt,
+		      struct netlink_ext_ack *extack)
+{
+	struct sfb_sched_data *q = qdisc_priv(sch);
+	struct Qdisc *child, *old;
+	struct nlattr *tb[TCA_SFB_MAX + 1];
+	const struct tc_sfb_qopt *ctl = &sfb_default_ops;
+	u32 limit;
+	int err;
+
+	if (opt) {
+		err = nla_parse_nested_deprecated(tb, TCA_SFB_MAX, opt,
+						  sfb_policy, NULL);
+		if (err < 0)
+			return -EINVAL;
+
+		if (tb[TCA_SFB_PARMS] == NULL)
+			return -EINVAL;
+
+		ctl = nla_data(tb[TCA_SFB_PARMS]);
+	}
+
+	limit = ctl->limit;
+	if (limit == 0)
+		limit = qdisc_dev(sch)->tx_queue_len;
+
+	child = fifo_create_dflt(sch, &pfifo_qdisc_ops, limit, extack);
+	if (IS_ERR(child))
+		return PTR_ERR(child);
+
+	if (child != &noop_qdisc)
+		qdisc_hash_add(child, true);
+	sch_tree_lock(sch);
+
+	qdisc_purge_queue(q->qdisc);
+	old = q->qdisc;
+	q->qdisc = child;
+
+	q->rehash_interval = msecs_to_jiffies(ctl->rehash_interval);
+	q->warmup_time = msecs_to_jiffies(ctl->warmup_time);
+	q->rehash_time = jiffies;
+	q->limit = limit;
+	q->increment = ctl->increment;
+	q->decrement = ctl->decrement;
+	q->max = ctl->max;
+	q->bin_size = ctl->bin_size;
+	q->penalty_rate = ctl->penalty_rate;
+	q->penalty_burst = ctl->penalty_burst;
+	q->tokens_avail = ctl->penalty_burst;
+	q->token_time = jiffies;
+
+	q->slot = 0;
+	q->double_buffering = false;
+	sfb_zero_all_buckets(q);
+	sfb_init_perturbation(0, q);
+	sfb_init_perturbation(1, q);
+
+	sch_tree_unlock(sch);
+	qdisc_put(old);
+
+	return 0;
+}
+
+static int sfb_init(struct Qdisc *sch, struct nlattr *opt,
+		    struct netlink_ext_ack *extack)
+{
+	struct sfb_sched_data *q = qdisc_priv(sch);
+	int err;
+
+	err = tcf_block_get(&q->block, &q->filter_list, sch, extack);
+	if (err)
+		return err;
+
+	q->qdisc = &noop_qdisc;
+	return sfb_change(sch, opt, extack);
+}
+
+static int sfb_dump(struct Qdisc *sch, struct sk_buff *skb)
+{
+	struct sfb_sched_data *q = qdisc_priv(sch);
+	struct nlattr *opts;
+	struct tc_sfb_qopt opt = {
+		.rehash_interval = jiffies_to_msecs(q->rehash_interval),
+		.warmup_time = jiffies_to_msecs(q->warmup_time),
+		.limit = q->limit,
+		.max = q->max,
+		.bin_size = q->bin_size,
+		.increment = q->increment,
+		.decrement = q->decrement,
+		.penalty_rate = q->penalty_rate,
+		.penalty_burst = q->penalty_burst,
+	};
+
+	sch->qstats.backlog = q->qdisc->qstats.backlog;
+	opts = nla_nest_start_noflag(skb, TCA_OPTIONS);
+	if (opts == NULL)
+		goto nla_put_failure;
+	if (nla_put(skb, TCA_SFB_PARMS, sizeof(opt), &opt))
+		goto nla_put_failure;
+	return nla_nest_end(skb, opts);
+
+nla_put_failure:
+	nla_nest_cancel(skb, opts);
+	return -EMSGSIZE;
+}
+
+static int sfb_dump_stats(struct Qdisc *sch, struct gnet_dump *d)
+{
+	struct sfb_sched_data *q = qdisc_priv(sch);
+	struct tc_sfb_xstats st = {
+		.earlydrop = q->stats.earlydrop,
+		.penaltydrop = q->stats.penaltydrop,
+		.bucketdrop = q->stats.bucketdrop,
+		.queuedrop = q->stats.queuedrop,
+		.childdrop = q->stats.childdrop,
+		.marked = q->stats.marked,
+	};
+
+	st.maxqlen = sfb_compute_qlen(&st.maxprob, &st.avgprob, q);
+
+	return gnet_stats_copy_app(d, &st, sizeof(st));
+}
+
+static int sfb_dump_class(struct Qdisc *sch, unsigned long cl,
+			  struct sk_buff *skb, struct tcmsg *tcm)
+{
+	return -ENOSYS;
+}
+
+static int sfb_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new,
+		     struct Qdisc **old, struct netlink_ext_ack *extack)
+{
+	struct sfb_sched_data *q = qdisc_priv(sch);
+
+	if (new == NULL)
+		new = &noop_qdisc;
+
+	*old = qdisc_replace(sch, new, &q->qdisc);
+	return 0;
+}
+
+static struct Qdisc *sfb_leaf(struct Qdisc *sch, unsigned long arg)
+{
+	struct sfb_sched_data *q = qdisc_priv(sch);
+
+	return q->qdisc;
+}
+
+static unsigned long sfb_find(struct Qdisc *sch, u32 classid)
+{
+	return 1;
+}
+
+static void sfb_unbind(struct Qdisc *sch, unsigned long arg)
+{
+}
+
+static int sfb_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
+			    struct nlattr **tca, unsigned long *arg,
+			    struct netlink_ext_ack *extack)
+{
+	return -ENOSYS;
+}
+
+static int sfb_delete(struct Qdisc *sch, unsigned long cl,
+		      struct netlink_ext_ack *extack)
+{
+	return -ENOSYS;
+}
+
+static void sfb_walk(struct Qdisc *sch, struct qdisc_walker *walker)
+{
+	if (!walker->stop) {
+		tc_qdisc_stats_dump(sch, 1, walker);
+	}
+}
+
+static struct tcf_block *sfb_tcf_block(struct Qdisc *sch, unsigned long cl,
+				       struct netlink_ext_ack *extack)
+{
+	struct sfb_sched_data *q = qdisc_priv(sch);
+
+	if (cl)
+		return NULL;
+	return q->block;
+}
+
+static unsigned long sfb_bind(struct Qdisc *sch, unsigned long parent,
+			      u32 classid)
+{
+	return 0;
+}
+
+
+static const struct Qdisc_class_ops sfb_class_ops = {
+	.graft		=	sfb_graft,
+	.leaf		=	sfb_leaf,
+	.find		=	sfb_find,
+	.change		=	sfb_change_class,
+	.delete		=	sfb_delete,
+	.walk		=	sfb_walk,
+	.tcf_block	=	sfb_tcf_block,
+	.bind_tcf	=	sfb_bind,
+	.unbind_tcf	=	sfb_unbind,
+	.dump		=	sfb_dump_class,
+};
+
+static struct Qdisc_ops sfb_qdisc_ops __read_mostly = {
+	.id		=	"sfb",
+	.priv_size	=	sizeof(struct sfb_sched_data),
+	.cl_ops		=	&sfb_class_ops,
+	.enqueue	=	sfb_enqueue,
+	.dequeue	=	sfb_dequeue,
+	.peek		=	sfb_peek,
+	.init		=	sfb_init,
+	.reset		=	sfb_reset,
+	.destroy	=	sfb_destroy,
+	.change		=	sfb_change,
+	.dump		=	sfb_dump,
+	.dump_stats	=	sfb_dump_stats,
+	.owner		=	THIS_MODULE,
+};
+
+static int __init sfb_module_init(void)
+{
+	return register_qdisc(&sfb_qdisc_ops);
+}
+
+static void __exit sfb_module_exit(void)
+{
+	unregister_qdisc(&sfb_qdisc_ops);
+}
+
+module_init(sfb_module_init)
+module_exit(sfb_module_exit)
+
+MODULE_DESCRIPTION("Stochastic Fair Blue queue discipline");
+MODULE_AUTHOR("Juliusz Chroboczek");
+MODULE_AUTHOR("Eric Dumazet");
+MODULE_LICENSE("GPL");