From 5b7c4cabbb65f5c469464da6c5f614cbd7f730f2 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 21 Feb 2023 18:24:12 -0800 Subject: Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next 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(). ... --- samples/bpf/hbm_kern.h | 215 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 215 insertions(+) create mode 100644 samples/bpf/hbm_kern.h (limited to 'samples/bpf/hbm_kern.h') diff --git a/samples/bpf/hbm_kern.h b/samples/bpf/hbm_kern.h new file mode 100644 index 000000000..1752a46a2 --- /dev/null +++ b/samples/bpf/hbm_kern.h @@ -0,0 +1,215 @@ +/* SPDX-License-Identifier: GPL-2.0 + * + * Copyright (c) 2019 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + * + * Include file for sample Host Bandwidth Manager (HBM) BPF programs + */ +#define KBUILD_MODNAME "foo" +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "hbm.h" + +#define DROP_PKT 0 +#define ALLOW_PKT 1 +#define TCP_ECN_OK 1 +#define CWR 2 + +#ifndef HBM_DEBUG // Define HBM_DEBUG to enable debugging +#undef bpf_printk +#define bpf_printk(fmt, ...) +#endif + +#define INITIAL_CREDIT_PACKETS 100 +#define MAX_BYTES_PER_PACKET 1500 +#define MARK_THRESH (40 * MAX_BYTES_PER_PACKET) +#define DROP_THRESH (80 * 5 * MAX_BYTES_PER_PACKET) +#define LARGE_PKT_DROP_THRESH (DROP_THRESH - (15 * MAX_BYTES_PER_PACKET)) +#define MARK_REGION_SIZE (LARGE_PKT_DROP_THRESH - MARK_THRESH) +#define LARGE_PKT_THRESH 120 +#define MAX_CREDIT (100 * MAX_BYTES_PER_PACKET) +#define INIT_CREDIT (INITIAL_CREDIT_PACKETS * MAX_BYTES_PER_PACKET) + +// Time base accounting for fq's EDT +#define BURST_SIZE_NS 100000 // 100us +#define MARK_THRESH_NS 50000 // 50us +#define DROP_THRESH_NS 500000 // 500us +// Reserve 20us of queuing for small packets (less than 120 bytes) +#define LARGE_PKT_DROP_THRESH_NS (DROP_THRESH_NS - 20000) +#define MARK_REGION_SIZE_NS (LARGE_PKT_DROP_THRESH_NS - MARK_THRESH_NS) + +// rate in bytes per ns << 20 +#define CREDIT_PER_NS(delta, rate) ((((u64)(delta)) * (rate)) >> 20) +#define BYTES_PER_NS(delta, rate) ((((u64)(delta)) * (rate)) >> 20) +#define BYTES_TO_NS(bytes, rate) div64_u64(((u64)(bytes)) << 20, (u64)(rate)) + +struct { + __uint(type, BPF_MAP_TYPE_CGROUP_STORAGE); + __type(key, struct bpf_cgroup_storage_key); + __type(value, struct hbm_vqueue); +} queue_state SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, u32); + __type(value, struct hbm_queue_stats); +} queue_stats SEC(".maps"); + +struct hbm_pkt_info { + int cwnd; + int rtt; + int packets_out; + bool is_ip; + bool is_tcp; + short ecn; +}; + +static int get_tcp_info(struct __sk_buff *skb, struct hbm_pkt_info *pkti) +{ + struct bpf_sock *sk; + struct bpf_tcp_sock *tp; + + sk = skb->sk; + if (sk) { + sk = bpf_sk_fullsock(sk); + if (sk) { + if (sk->protocol == IPPROTO_TCP) { + tp = bpf_tcp_sock(sk); + if (tp) { + pkti->cwnd = tp->snd_cwnd; + pkti->rtt = tp->srtt_us >> 3; + pkti->packets_out = tp->packets_out; + return 0; + } + } + } + } + pkti->cwnd = 0; + pkti->rtt = 0; + pkti->packets_out = 0; + return 1; +} + +static void hbm_get_pkt_info(struct __sk_buff *skb, + struct hbm_pkt_info *pkti) +{ + struct iphdr iph; + struct ipv6hdr *ip6h; + + pkti->cwnd = 0; + pkti->rtt = 0; + bpf_skb_load_bytes(skb, 0, &iph, 12); + if (iph.version == 6) { + ip6h = (struct ipv6hdr *)&iph; + pkti->is_ip = true; + pkti->is_tcp = (ip6h->nexthdr == 6); + pkti->ecn = (ip6h->flow_lbl[0] >> 4) & INET_ECN_MASK; + } else if (iph.version == 4) { + pkti->is_ip = true; + pkti->is_tcp = (iph.protocol == 6); + pkti->ecn = iph.tos & INET_ECN_MASK; + } else { + pkti->is_ip = false; + pkti->is_tcp = false; + pkti->ecn = 0; + } + if (pkti->is_tcp) + get_tcp_info(skb, pkti); +} + +static __always_inline void hbm_init_vqueue(struct hbm_vqueue *qdp, int rate) +{ + bpf_printk("Initializing queue_state, rate:%d\n", rate * 128); + qdp->lasttime = bpf_ktime_get_ns(); + qdp->credit = INIT_CREDIT; + qdp->rate = rate * 128; +} + +static __always_inline void hbm_init_edt_vqueue(struct hbm_vqueue *qdp, + int rate) +{ + unsigned long long curtime; + + curtime = bpf_ktime_get_ns(); + bpf_printk("Initializing queue_state, rate:%d\n", rate * 128); + qdp->lasttime = curtime - BURST_SIZE_NS; // support initial burst + qdp->credit = 0; // not used + qdp->rate = rate * 128; +} + +static __always_inline void hbm_update_stats(struct hbm_queue_stats *qsp, + int len, + unsigned long long curtime, + bool congestion_flag, + bool drop_flag, + bool cwr_flag, + bool ecn_ce_flag, + struct hbm_pkt_info *pkti, + int credit) +{ + int rv = ALLOW_PKT; + + if (qsp != NULL) { + // Following is needed for work conserving + __sync_add_and_fetch(&(qsp->bytes_total), len); + if (qsp->stats) { + // Optionally update statistics + if (qsp->firstPacketTime == 0) + qsp->firstPacketTime = curtime; + qsp->lastPacketTime = curtime; + __sync_add_and_fetch(&(qsp->pkts_total), 1); + if (congestion_flag) { + __sync_add_and_fetch(&(qsp->pkts_marked), 1); + __sync_add_and_fetch(&(qsp->bytes_marked), len); + } + if (drop_flag) { + __sync_add_and_fetch(&(qsp->pkts_dropped), 1); + __sync_add_and_fetch(&(qsp->bytes_dropped), + len); + } + if (ecn_ce_flag) + __sync_add_and_fetch(&(qsp->pkts_ecn_ce), 1); + if (pkti->cwnd) { + __sync_add_and_fetch(&(qsp->sum_cwnd), + pkti->cwnd); + __sync_add_and_fetch(&(qsp->sum_cwnd_cnt), 1); + } + if (pkti->rtt) + __sync_add_and_fetch(&(qsp->sum_rtt), + pkti->rtt); + __sync_add_and_fetch(&(qsp->sum_credit), credit); + + if (drop_flag) + rv = DROP_PKT; + if (cwr_flag) + rv |= 2; + if (rv == DROP_PKT) + __sync_add_and_fetch(&(qsp->returnValCount[0]), + 1); + else if (rv == ALLOW_PKT) + __sync_add_and_fetch(&(qsp->returnValCount[1]), + 1); + else if (rv == 2) + __sync_add_and_fetch(&(qsp->returnValCount[2]), + 1); + else if (rv == 3) + __sync_add_and_fetch(&(qsp->returnValCount[3]), + 1); + } + } +} -- cgit v1.2.3