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(). ... --- tools/testing/selftests/bpf/progs/test_seg6_loop.c | 260 +++++++++++++++++++++ 1 file changed, 260 insertions(+) create mode 100644 tools/testing/selftests/bpf/progs/test_seg6_loop.c (limited to 'tools/testing/selftests/bpf/progs/test_seg6_loop.c') diff --git a/tools/testing/selftests/bpf/progs/test_seg6_loop.c b/tools/testing/selftests/bpf/progs/test_seg6_loop.c new file mode 100644 index 000000000..a7278f064 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_seg6_loop.c @@ -0,0 +1,260 @@ +#include +#include +#include +#include +#include +#include +#include + +/* Packet parsing state machine helpers. */ +#define cursor_advance(_cursor, _len) \ + ({ void *_tmp = _cursor; _cursor += _len; _tmp; }) + +#define SR6_FLAG_ALERT (1 << 4) + +#define BPF_PACKET_HEADER __attribute__((packed)) + +struct ip6_t { + unsigned int ver:4; + unsigned int priority:8; + unsigned int flow_label:20; + unsigned short payload_len; + unsigned char next_header; + unsigned char hop_limit; + unsigned long long src_hi; + unsigned long long src_lo; + unsigned long long dst_hi; + unsigned long long dst_lo; +} BPF_PACKET_HEADER; + +struct ip6_addr_t { + unsigned long long hi; + unsigned long long lo; +} BPF_PACKET_HEADER; + +struct ip6_srh_t { + unsigned char nexthdr; + unsigned char hdrlen; + unsigned char type; + unsigned char segments_left; + unsigned char first_segment; + unsigned char flags; + unsigned short tag; + + struct ip6_addr_t segments[0]; +} BPF_PACKET_HEADER; + +struct sr6_tlv_t { + unsigned char type; + unsigned char len; + unsigned char value[0]; +} BPF_PACKET_HEADER; + +static __always_inline struct ip6_srh_t *get_srh(struct __sk_buff *skb) +{ + void *cursor, *data_end; + struct ip6_srh_t *srh; + struct ip6_t *ip; + uint8_t *ipver; + + data_end = (void *)(long)skb->data_end; + cursor = (void *)(long)skb->data; + ipver = (uint8_t *)cursor; + + if ((void *)ipver + sizeof(*ipver) > data_end) + return NULL; + + if ((*ipver >> 4) != 6) + return NULL; + + ip = cursor_advance(cursor, sizeof(*ip)); + if ((void *)ip + sizeof(*ip) > data_end) + return NULL; + + if (ip->next_header != 43) + return NULL; + + srh = cursor_advance(cursor, sizeof(*srh)); + if ((void *)srh + sizeof(*srh) > data_end) + return NULL; + + if (srh->type != 4) + return NULL; + + return srh; +} + +static __always_inline int update_tlv_pad(struct __sk_buff *skb, + uint32_t new_pad, uint32_t old_pad, + uint32_t pad_off) +{ + int err; + + if (new_pad != old_pad) { + err = bpf_lwt_seg6_adjust_srh(skb, pad_off, + (int) new_pad - (int) old_pad); + if (err) + return err; + } + + if (new_pad > 0) { + char pad_tlv_buf[16] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, + 0, 0, 0}; + struct sr6_tlv_t *pad_tlv = (struct sr6_tlv_t *) pad_tlv_buf; + + pad_tlv->type = SR6_TLV_PADDING; + pad_tlv->len = new_pad - 2; + + err = bpf_lwt_seg6_store_bytes(skb, pad_off, + (void *)pad_tlv_buf, new_pad); + if (err) + return err; + } + + return 0; +} + +static __always_inline int is_valid_tlv_boundary(struct __sk_buff *skb, + struct ip6_srh_t *srh, + uint32_t *tlv_off, + uint32_t *pad_size, + uint32_t *pad_off) +{ + uint32_t srh_off, cur_off; + int offset_valid = 0; + int err; + + srh_off = (char *)srh - (char *)(long)skb->data; + // cur_off = end of segments, start of possible TLVs + cur_off = srh_off + sizeof(*srh) + + sizeof(struct ip6_addr_t) * (srh->first_segment + 1); + + *pad_off = 0; + + // we can only go as far as ~10 TLVs due to the BPF max stack size + // workaround: define induction variable "i" as "long" instead + // of "int" to prevent alu32 sub-register spilling. + #pragma clang loop unroll(disable) + for (long i = 0; i < 100; i++) { + struct sr6_tlv_t tlv; + + if (cur_off == *tlv_off) + offset_valid = 1; + + if (cur_off >= srh_off + ((srh->hdrlen + 1) << 3)) + break; + + err = bpf_skb_load_bytes(skb, cur_off, &tlv, sizeof(tlv)); + if (err) + return err; + + if (tlv.type == SR6_TLV_PADDING) { + *pad_size = tlv.len + sizeof(tlv); + *pad_off = cur_off; + + if (*tlv_off == srh_off) { + *tlv_off = cur_off; + offset_valid = 1; + } + break; + + } else if (tlv.type == SR6_TLV_HMAC) { + break; + } + + cur_off += sizeof(tlv) + tlv.len; + } // we reached the padding or HMAC TLVs, or the end of the SRH + + if (*pad_off == 0) + *pad_off = cur_off; + + if (*tlv_off == -1) + *tlv_off = cur_off; + else if (!offset_valid) + return -EINVAL; + + return 0; +} + +static __always_inline int add_tlv(struct __sk_buff *skb, + struct ip6_srh_t *srh, uint32_t tlv_off, + struct sr6_tlv_t *itlv, uint8_t tlv_size) +{ + uint32_t srh_off = (char *)srh - (char *)(long)skb->data; + uint8_t len_remaining, new_pad; + uint32_t pad_off = 0; + uint32_t pad_size = 0; + uint32_t partial_srh_len; + int err; + + if (tlv_off != -1) + tlv_off += srh_off; + + if (itlv->type == SR6_TLV_PADDING || itlv->type == SR6_TLV_HMAC) + return -EINVAL; + + err = is_valid_tlv_boundary(skb, srh, &tlv_off, &pad_size, &pad_off); + if (err) + return err; + + err = bpf_lwt_seg6_adjust_srh(skb, tlv_off, sizeof(*itlv) + itlv->len); + if (err) + return err; + + err = bpf_lwt_seg6_store_bytes(skb, tlv_off, (void *)itlv, tlv_size); + if (err) + return err; + + // the following can't be moved inside update_tlv_pad because the + // bpf verifier has some issues with it + pad_off += sizeof(*itlv) + itlv->len; + partial_srh_len = pad_off - srh_off; + len_remaining = partial_srh_len % 8; + new_pad = 8 - len_remaining; + + if (new_pad == 1) // cannot pad for 1 byte only + new_pad = 9; + else if (new_pad == 8) + new_pad = 0; + + return update_tlv_pad(skb, new_pad, pad_size, pad_off); +} + +// Add an Egress TLV fc00::4, add the flag A, +// and apply End.X action to fc42::1 +SEC("lwt_seg6local") +int __add_egr_x(struct __sk_buff *skb) +{ + unsigned long long hi = 0xfc42000000000000; + unsigned long long lo = 0x1; + struct ip6_srh_t *srh = get_srh(skb); + uint8_t new_flags = SR6_FLAG_ALERT; + struct ip6_addr_t addr; + int err, offset; + + if (srh == NULL) + return BPF_DROP; + + uint8_t tlv[20] = {2, 18, 0, 0, 0xfd, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, + 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x4}; + + err = add_tlv(skb, srh, (srh->hdrlen+1) << 3, + (struct sr6_tlv_t *)&tlv, 20); + if (err) + return BPF_DROP; + + offset = sizeof(struct ip6_t) + offsetof(struct ip6_srh_t, flags); + err = bpf_lwt_seg6_store_bytes(skb, offset, + (void *)&new_flags, sizeof(new_flags)); + if (err) + return BPF_DROP; + + addr.lo = bpf_cpu_to_be64(lo); + addr.hi = bpf_cpu_to_be64(hi); + err = bpf_lwt_seg6_action(skb, SEG6_LOCAL_ACTION_END_X, + (void *)&addr, sizeof(addr)); + if (err) + return BPF_DROP; + return BPF_REDIRECT; +} +char __license[] SEC("license") = "GPL"; -- cgit v1.2.3