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/xdp_sample.bpf.c | 266 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 266 insertions(+) create mode 100644 samples/bpf/xdp_sample.bpf.c (limited to 'samples/bpf/xdp_sample.bpf.c') diff --git a/samples/bpf/xdp_sample.bpf.c b/samples/bpf/xdp_sample.bpf.c new file mode 100644 index 000000000..0eb7e1dca --- /dev/null +++ b/samples/bpf/xdp_sample.bpf.c @@ -0,0 +1,266 @@ +// SPDX-License-Identifier: GPL-2.0 +/* GPLv2, Copyright(c) 2017 Jesper Dangaard Brouer, Red Hat, Inc. */ +#include "xdp_sample.bpf.h" + +#include +#include +#include + +array_map rx_cnt SEC(".maps"); +array_map redir_err_cnt SEC(".maps"); +array_map cpumap_enqueue_cnt SEC(".maps"); +array_map cpumap_kthread_cnt SEC(".maps"); +array_map exception_cnt SEC(".maps"); +array_map devmap_xmit_cnt SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_HASH); + __uint(max_entries, 32 * 32); + __type(key, u64); + __type(value, struct datarec); +} devmap_xmit_cnt_multi SEC(".maps"); + +const volatile int nr_cpus = 0; + +/* These can be set before loading so that redundant comparisons can be DCE'd by + * the verifier, and only actual matches are tried after loading tp_btf program. + * This allows sample to filter tracepoint stats based on net_device. + */ +const volatile int from_match[32] = {}; +const volatile int to_match[32] = {}; + +int cpumap_map_id = 0; + +/* Find if b is part of set a, but if a is empty set then evaluate to true */ +#define IN_SET(a, b) \ + ({ \ + bool __res = !(a)[0]; \ + for (int i = 0; i < ARRAY_SIZE(a) && (a)[i]; i++) { \ + __res = (a)[i] == (b); \ + if (__res) \ + break; \ + } \ + __res; \ + }) + +static __always_inline __u32 xdp_get_err_key(int err) +{ + switch (err) { + case 0: + return 0; + case -EINVAL: + return 2; + case -ENETDOWN: + return 3; + case -EMSGSIZE: + return 4; + case -EOPNOTSUPP: + return 5; + case -ENOSPC: + return 6; + default: + return 1; + } +} + +static __always_inline int xdp_redirect_collect_stat(int from, int err) +{ + u32 cpu = bpf_get_smp_processor_id(); + u32 key = XDP_REDIRECT_ERROR; + struct datarec *rec; + u32 idx; + + if (!IN_SET(from_match, from)) + return 0; + + key = xdp_get_err_key(err); + + idx = key * nr_cpus + cpu; + rec = bpf_map_lookup_elem(&redir_err_cnt, &idx); + if (!rec) + return 0; + if (key) + NO_TEAR_INC(rec->dropped); + else + NO_TEAR_INC(rec->processed); + return 0; /* Indicate event was filtered (no further processing)*/ + /* + * Returning 1 here would allow e.g. a perf-record tracepoint + * to see and record these events, but it doesn't work well + * in-practice as stopping perf-record also unload this + * bpf_prog. Plus, there is additional overhead of doing so. + */ +} + +SEC("tp_btf/xdp_redirect_err") +int BPF_PROG(tp_xdp_redirect_err, const struct net_device *dev, + const struct bpf_prog *xdp, const void *tgt, int err, + const struct bpf_map *map, u32 index) +{ + return xdp_redirect_collect_stat(dev->ifindex, err); +} + +SEC("tp_btf/xdp_redirect_map_err") +int BPF_PROG(tp_xdp_redirect_map_err, const struct net_device *dev, + const struct bpf_prog *xdp, const void *tgt, int err, + const struct bpf_map *map, u32 index) +{ + return xdp_redirect_collect_stat(dev->ifindex, err); +} + +SEC("tp_btf/xdp_redirect") +int BPF_PROG(tp_xdp_redirect, const struct net_device *dev, + const struct bpf_prog *xdp, const void *tgt, int err, + const struct bpf_map *map, u32 index) +{ + return xdp_redirect_collect_stat(dev->ifindex, err); +} + +SEC("tp_btf/xdp_redirect_map") +int BPF_PROG(tp_xdp_redirect_map, const struct net_device *dev, + const struct bpf_prog *xdp, const void *tgt, int err, + const struct bpf_map *map, u32 index) +{ + return xdp_redirect_collect_stat(dev->ifindex, err); +} + +SEC("tp_btf/xdp_cpumap_enqueue") +int BPF_PROG(tp_xdp_cpumap_enqueue, int map_id, unsigned int processed, + unsigned int drops, int to_cpu) +{ + u32 cpu = bpf_get_smp_processor_id(); + struct datarec *rec; + u32 idx; + + if (cpumap_map_id && cpumap_map_id != map_id) + return 0; + + idx = to_cpu * nr_cpus + cpu; + rec = bpf_map_lookup_elem(&cpumap_enqueue_cnt, &idx); + if (!rec) + return 0; + NO_TEAR_ADD(rec->processed, processed); + NO_TEAR_ADD(rec->dropped, drops); + /* Record bulk events, then userspace can calc average bulk size */ + if (processed > 0) + NO_TEAR_INC(rec->issue); + /* Inception: It's possible to detect overload situations, via + * this tracepoint. This can be used for creating a feedback + * loop to XDP, which can take appropriate actions to mitigate + * this overload situation. + */ + return 0; +} + +SEC("tp_btf/xdp_cpumap_kthread") +int BPF_PROG(tp_xdp_cpumap_kthread, int map_id, unsigned int processed, + unsigned int drops, int sched, struct xdp_cpumap_stats *xdp_stats) +{ + struct datarec *rec; + u32 cpu; + + if (cpumap_map_id && cpumap_map_id != map_id) + return 0; + + cpu = bpf_get_smp_processor_id(); + rec = bpf_map_lookup_elem(&cpumap_kthread_cnt, &cpu); + if (!rec) + return 0; + NO_TEAR_ADD(rec->processed, processed); + NO_TEAR_ADD(rec->dropped, drops); + NO_TEAR_ADD(rec->xdp_pass, xdp_stats->pass); + NO_TEAR_ADD(rec->xdp_drop, xdp_stats->drop); + NO_TEAR_ADD(rec->xdp_redirect, xdp_stats->redirect); + /* Count times kthread yielded CPU via schedule call */ + if (sched) + NO_TEAR_INC(rec->issue); + return 0; +} + +SEC("tp_btf/xdp_exception") +int BPF_PROG(tp_xdp_exception, const struct net_device *dev, + const struct bpf_prog *xdp, u32 act) +{ + u32 cpu = bpf_get_smp_processor_id(); + struct datarec *rec; + u32 key = act, idx; + + if (!IN_SET(from_match, dev->ifindex)) + return 0; + if (!IN_SET(to_match, dev->ifindex)) + return 0; + + if (key > XDP_REDIRECT) + key = XDP_REDIRECT + 1; + + idx = key * nr_cpus + cpu; + rec = bpf_map_lookup_elem(&exception_cnt, &idx); + if (!rec) + return 0; + NO_TEAR_INC(rec->dropped); + + return 0; +} + +SEC("tp_btf/xdp_devmap_xmit") +int BPF_PROG(tp_xdp_devmap_xmit, const struct net_device *from_dev, + const struct net_device *to_dev, int sent, int drops, int err) +{ + struct datarec *rec; + int idx_in, idx_out; + u32 cpu; + + idx_in = from_dev->ifindex; + idx_out = to_dev->ifindex; + + if (!IN_SET(from_match, idx_in)) + return 0; + if (!IN_SET(to_match, idx_out)) + return 0; + + cpu = bpf_get_smp_processor_id(); + rec = bpf_map_lookup_elem(&devmap_xmit_cnt, &cpu); + if (!rec) + return 0; + NO_TEAR_ADD(rec->processed, sent); + NO_TEAR_ADD(rec->dropped, drops); + /* Record bulk events, then userspace can calc average bulk size */ + NO_TEAR_INC(rec->info); + /* Record error cases, where no frame were sent */ + /* Catch API error of drv ndo_xdp_xmit sent more than count */ + if (err || drops < 0) + NO_TEAR_INC(rec->issue); + return 0; +} + +SEC("tp_btf/xdp_devmap_xmit") +int BPF_PROG(tp_xdp_devmap_xmit_multi, const struct net_device *from_dev, + const struct net_device *to_dev, int sent, int drops, int err) +{ + struct datarec empty = {}; + struct datarec *rec; + int idx_in, idx_out; + u64 idx; + + idx_in = from_dev->ifindex; + idx_out = to_dev->ifindex; + idx = idx_in; + idx = idx << 32 | idx_out; + + if (!IN_SET(from_match, idx_in)) + return 0; + if (!IN_SET(to_match, idx_out)) + return 0; + + bpf_map_update_elem(&devmap_xmit_cnt_multi, &idx, &empty, BPF_NOEXIST); + rec = bpf_map_lookup_elem(&devmap_xmit_cnt_multi, &idx); + if (!rec) + return 0; + + NO_TEAR_ADD(rec->processed, sent); + NO_TEAR_ADD(rec->dropped, drops); + NO_TEAR_INC(rec->info); + if (err || drops < 0) + NO_TEAR_INC(rec->issue); + return 0; +} -- cgit v1.2.3