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(). ... --- drivers/net/ethernet/netronome/nfp/bpf/main.c | 547 ++++++++++++++++++++++++++ 1 file changed, 547 insertions(+) create mode 100644 drivers/net/ethernet/netronome/nfp/bpf/main.c (limited to 'drivers/net/ethernet/netronome/nfp/bpf/main.c') diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.c b/drivers/net/ethernet/netronome/nfp/bpf/main.c new file mode 100644 index 000000000..f469950c7 --- /dev/null +++ b/drivers/net/ethernet/netronome/nfp/bpf/main.c @@ -0,0 +1,547 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* Copyright (C) 2017-2018 Netronome Systems, Inc. */ + +#include + +#include "../nfpcore/nfp_cpp.h" +#include "../nfpcore/nfp_nffw.h" +#include "../nfpcore/nfp_nsp.h" +#include "../nfp_app.h" +#include "../nfp_main.h" +#include "../nfp_net.h" +#include "../nfp_port.h" +#include "fw.h" +#include "main.h" + +const struct rhashtable_params nfp_bpf_maps_neutral_params = { + .nelem_hint = 4, + .key_len = sizeof_field(struct bpf_map, id), + .key_offset = offsetof(struct nfp_bpf_neutral_map, map_id), + .head_offset = offsetof(struct nfp_bpf_neutral_map, l), + .automatic_shrinking = true, +}; + +static bool nfp_net_ebpf_capable(struct nfp_net *nn) +{ +#ifdef __LITTLE_ENDIAN + struct nfp_app_bpf *bpf = nn->app->priv; + + return nn->cap & NFP_NET_CFG_CTRL_BPF && + bpf->abi_version && + nn_readb(nn, NFP_NET_CFG_BPF_ABI) == bpf->abi_version; +#else + return false; +#endif +} + +static int +nfp_bpf_xdp_offload(struct nfp_app *app, struct nfp_net *nn, + struct bpf_prog *prog, struct netlink_ext_ack *extack) +{ + bool running, xdp_running; + + if (!nfp_net_ebpf_capable(nn)) + return -EINVAL; + + running = nn->dp.ctrl & NFP_NET_CFG_CTRL_BPF; + xdp_running = running && nn->xdp_hw.prog; + + if (!prog && !xdp_running) + return 0; + if (prog && running && !xdp_running) + return -EBUSY; + + return nfp_net_bpf_offload(nn, prog, running, extack); +} + +static const char *nfp_bpf_extra_cap(struct nfp_app *app, struct nfp_net *nn) +{ + return nfp_net_ebpf_capable(nn) ? "BPF" : ""; +} + +static int +nfp_bpf_vnic_alloc(struct nfp_app *app, struct nfp_net *nn, unsigned int id) +{ + struct nfp_pf *pf = app->pf; + struct nfp_bpf_vnic *bv; + int err; + + if (!pf->eth_tbl) { + nfp_err(pf->cpp, "No ETH table\n"); + return -EINVAL; + } + if (pf->max_data_vnics != pf->eth_tbl->count) { + nfp_err(pf->cpp, "ETH entries don't match vNICs (%d vs %d)\n", + pf->max_data_vnics, pf->eth_tbl->count); + return -EINVAL; + } + + bv = kzalloc(sizeof(*bv), GFP_KERNEL); + if (!bv) + return -ENOMEM; + nn->app_priv = bv; + + err = nfp_app_nic_vnic_alloc(app, nn, id); + if (err) + goto err_free_priv; + + bv->start_off = nn_readw(nn, NFP_NET_CFG_BPF_START); + bv->tgt_done = nn_readw(nn, NFP_NET_CFG_BPF_DONE); + + return 0; +err_free_priv: + kfree(nn->app_priv); + return err; +} + +static void nfp_bpf_vnic_free(struct nfp_app *app, struct nfp_net *nn) +{ + struct nfp_bpf_vnic *bv = nn->app_priv; + + WARN_ON(bv->tc_prog); + kfree(bv); +} + +static int nfp_bpf_setup_tc_block_cb(enum tc_setup_type type, + void *type_data, void *cb_priv) +{ + struct tc_cls_bpf_offload *cls_bpf = type_data; + struct nfp_net *nn = cb_priv; + struct bpf_prog *oldprog; + struct nfp_bpf_vnic *bv; + int err; + + if (type != TC_SETUP_CLSBPF) { + NL_SET_ERR_MSG_MOD(cls_bpf->common.extack, + "only offload of BPF classifiers supported"); + return -EOPNOTSUPP; + } + if (!tc_cls_can_offload_and_chain0(nn->dp.netdev, &cls_bpf->common)) + return -EOPNOTSUPP; + if (!nfp_net_ebpf_capable(nn)) { + NL_SET_ERR_MSG_MOD(cls_bpf->common.extack, + "NFP firmware does not support eBPF offload"); + return -EOPNOTSUPP; + } + if (cls_bpf->common.protocol != htons(ETH_P_ALL)) { + NL_SET_ERR_MSG_MOD(cls_bpf->common.extack, + "only ETH_P_ALL supported as filter protocol"); + return -EOPNOTSUPP; + } + + /* Only support TC direct action */ + if (!cls_bpf->exts_integrated || + tcf_exts_has_actions(cls_bpf->exts)) { + NL_SET_ERR_MSG_MOD(cls_bpf->common.extack, + "only direct action with no legacy actions supported"); + return -EOPNOTSUPP; + } + + if (cls_bpf->command != TC_CLSBPF_OFFLOAD) + return -EOPNOTSUPP; + + bv = nn->app_priv; + oldprog = cls_bpf->oldprog; + + /* Don't remove if oldprog doesn't match driver's state */ + if (bv->tc_prog != oldprog) { + oldprog = NULL; + if (!cls_bpf->prog) + return 0; + } + + err = nfp_net_bpf_offload(nn, cls_bpf->prog, oldprog, + cls_bpf->common.extack); + if (err) + return err; + + bv->tc_prog = cls_bpf->prog; + nn->port->tc_offload_cnt = !!bv->tc_prog; + return 0; +} + +static LIST_HEAD(nfp_bpf_block_cb_list); + +static int nfp_bpf_setup_tc(struct nfp_app *app, struct net_device *netdev, + enum tc_setup_type type, void *type_data) +{ + struct nfp_net *nn = netdev_priv(netdev); + + switch (type) { + case TC_SETUP_BLOCK: + return flow_block_cb_setup_simple(type_data, + &nfp_bpf_block_cb_list, + nfp_bpf_setup_tc_block_cb, + nn, nn, true); + default: + return -EOPNOTSUPP; + } +} + +static int +nfp_bpf_check_mtu(struct nfp_app *app, struct net_device *netdev, int new_mtu) +{ + struct nfp_net *nn = netdev_priv(netdev); + struct nfp_bpf_vnic *bv; + struct bpf_prog *prog; + + if (~nn->dp.ctrl & NFP_NET_CFG_CTRL_BPF) + return 0; + + if (nn->xdp_hw.prog) { + prog = nn->xdp_hw.prog; + } else { + bv = nn->app_priv; + prog = bv->tc_prog; + } + + if (nfp_bpf_offload_check_mtu(nn, prog, new_mtu)) { + nn_info(nn, "BPF offload active, potential packet access beyond hardware packet boundary"); + return -EBUSY; + } + return 0; +} + +static int +nfp_bpf_parse_cap_adjust_head(struct nfp_app_bpf *bpf, void __iomem *value, + u32 length) +{ + struct nfp_bpf_cap_tlv_adjust_head __iomem *cap = value; + struct nfp_cpp *cpp = bpf->app->pf->cpp; + + if (length < sizeof(*cap)) { + nfp_err(cpp, "truncated adjust_head TLV: %d\n", length); + return -EINVAL; + } + + bpf->adjust_head.flags = readl(&cap->flags); + bpf->adjust_head.off_min = readl(&cap->off_min); + bpf->adjust_head.off_max = readl(&cap->off_max); + bpf->adjust_head.guaranteed_sub = readl(&cap->guaranteed_sub); + bpf->adjust_head.guaranteed_add = readl(&cap->guaranteed_add); + + if (bpf->adjust_head.off_min > bpf->adjust_head.off_max) { + nfp_err(cpp, "invalid adjust_head TLV: min > max\n"); + return -EINVAL; + } + if (!FIELD_FIT(UR_REG_IMM_MAX, bpf->adjust_head.off_min) || + !FIELD_FIT(UR_REG_IMM_MAX, bpf->adjust_head.off_max)) { + nfp_warn(cpp, "disabling adjust_head - driver expects min/max to fit in as immediates\n"); + memset(&bpf->adjust_head, 0, sizeof(bpf->adjust_head)); + return 0; + } + + return 0; +} + +static int +nfp_bpf_parse_cap_func(struct nfp_app_bpf *bpf, void __iomem *value, u32 length) +{ + struct nfp_bpf_cap_tlv_func __iomem *cap = value; + + if (length < sizeof(*cap)) { + nfp_err(bpf->app->cpp, "truncated function TLV: %d\n", length); + return -EINVAL; + } + + switch (readl(&cap->func_id)) { + case BPF_FUNC_map_lookup_elem: + bpf->helpers.map_lookup = readl(&cap->func_addr); + break; + case BPF_FUNC_map_update_elem: + bpf->helpers.map_update = readl(&cap->func_addr); + break; + case BPF_FUNC_map_delete_elem: + bpf->helpers.map_delete = readl(&cap->func_addr); + break; + case BPF_FUNC_perf_event_output: + bpf->helpers.perf_event_output = readl(&cap->func_addr); + break; + } + + return 0; +} + +static int +nfp_bpf_parse_cap_maps(struct nfp_app_bpf *bpf, void __iomem *value, u32 length) +{ + struct nfp_bpf_cap_tlv_maps __iomem *cap = value; + + if (length < sizeof(*cap)) { + nfp_err(bpf->app->cpp, "truncated maps TLV: %d\n", length); + return -EINVAL; + } + + bpf->maps.types = readl(&cap->types); + bpf->maps.max_maps = readl(&cap->max_maps); + bpf->maps.max_elems = readl(&cap->max_elems); + bpf->maps.max_key_sz = readl(&cap->max_key_sz); + bpf->maps.max_val_sz = readl(&cap->max_val_sz); + bpf->maps.max_elem_sz = readl(&cap->max_elem_sz); + + return 0; +} + +static int +nfp_bpf_parse_cap_random(struct nfp_app_bpf *bpf, void __iomem *value, + u32 length) +{ + bpf->pseudo_random = true; + return 0; +} + +static int +nfp_bpf_parse_cap_qsel(struct nfp_app_bpf *bpf, void __iomem *value, u32 length) +{ + bpf->queue_select = true; + return 0; +} + +static int +nfp_bpf_parse_cap_adjust_tail(struct nfp_app_bpf *bpf, void __iomem *value, + u32 length) +{ + bpf->adjust_tail = true; + return 0; +} + +static int +nfp_bpf_parse_cap_cmsg_multi_ent(struct nfp_app_bpf *bpf, void __iomem *value, + u32 length) +{ + bpf->cmsg_multi_ent = true; + return 0; +} + +static int +nfp_bpf_parse_cap_abi_version(struct nfp_app_bpf *bpf, void __iomem *value, + u32 length) +{ + if (length < 4) { + nfp_err(bpf->app->cpp, "truncated ABI version TLV: %d\n", + length); + return -EINVAL; + } + + bpf->abi_version = readl(value); + if (bpf->abi_version < 2 || bpf->abi_version > 3) { + nfp_warn(bpf->app->cpp, "unsupported BPF ABI version: %d\n", + bpf->abi_version); + bpf->abi_version = 0; + } + + return 0; +} + +static int nfp_bpf_parse_capabilities(struct nfp_app *app) +{ + struct nfp_cpp *cpp = app->pf->cpp; + struct nfp_cpp_area *area; + u8 __iomem *mem, *start; + + mem = nfp_rtsym_map(app->pf->rtbl, "_abi_bpf_capabilities", "bpf.cap", + 8, &area); + if (IS_ERR(mem)) + return PTR_ERR(mem) == -ENOENT ? 0 : PTR_ERR(mem); + + start = mem; + while (mem - start + 8 <= nfp_cpp_area_size(area)) { + u8 __iomem *value; + u32 type, length; + + type = readl(mem); + length = readl(mem + 4); + value = mem + 8; + + mem += 8 + length; + if (mem - start > nfp_cpp_area_size(area)) + goto err_release_free; + + switch (type) { + case NFP_BPF_CAP_TYPE_FUNC: + if (nfp_bpf_parse_cap_func(app->priv, value, length)) + goto err_release_free; + break; + case NFP_BPF_CAP_TYPE_ADJUST_HEAD: + if (nfp_bpf_parse_cap_adjust_head(app->priv, value, + length)) + goto err_release_free; + break; + case NFP_BPF_CAP_TYPE_MAPS: + if (nfp_bpf_parse_cap_maps(app->priv, value, length)) + goto err_release_free; + break; + case NFP_BPF_CAP_TYPE_RANDOM: + if (nfp_bpf_parse_cap_random(app->priv, value, length)) + goto err_release_free; + break; + case NFP_BPF_CAP_TYPE_QUEUE_SELECT: + if (nfp_bpf_parse_cap_qsel(app->priv, value, length)) + goto err_release_free; + break; + case NFP_BPF_CAP_TYPE_ADJUST_TAIL: + if (nfp_bpf_parse_cap_adjust_tail(app->priv, value, + length)) + goto err_release_free; + break; + case NFP_BPF_CAP_TYPE_ABI_VERSION: + if (nfp_bpf_parse_cap_abi_version(app->priv, value, + length)) + goto err_release_free; + break; + case NFP_BPF_CAP_TYPE_CMSG_MULTI_ENT: + if (nfp_bpf_parse_cap_cmsg_multi_ent(app->priv, value, + length)) + goto err_release_free; + break; + default: + nfp_dbg(cpp, "unknown BPF capability: %d\n", type); + break; + } + } + if (mem - start != nfp_cpp_area_size(area)) { + nfp_err(cpp, "BPF capabilities left after parsing, parsed:%zd total length:%zu\n", + mem - start, nfp_cpp_area_size(area)); + goto err_release_free; + } + + nfp_cpp_area_release_free(area); + + return 0; + +err_release_free: + nfp_err(cpp, "invalid BPF capabilities at offset:%zd\n", mem - start); + nfp_cpp_area_release_free(area); + return -EINVAL; +} + +static void nfp_bpf_init_capabilities(struct nfp_app_bpf *bpf) +{ + bpf->abi_version = 2; /* Original BPF ABI version */ +} + +static int nfp_bpf_ndo_init(struct nfp_app *app, struct net_device *netdev) +{ + struct nfp_app_bpf *bpf = app->priv; + + return bpf_offload_dev_netdev_register(bpf->bpf_dev, netdev); +} + +static void nfp_bpf_ndo_uninit(struct nfp_app *app, struct net_device *netdev) +{ + struct nfp_app_bpf *bpf = app->priv; + + bpf_offload_dev_netdev_unregister(bpf->bpf_dev, netdev); +} + +static int nfp_bpf_start(struct nfp_app *app) +{ + struct nfp_app_bpf *bpf = app->priv; + + if (app->ctrl->dp.mtu < nfp_bpf_ctrl_cmsg_min_mtu(bpf)) { + nfp_err(bpf->app->cpp, + "ctrl channel MTU below min required %u < %u\n", + app->ctrl->dp.mtu, nfp_bpf_ctrl_cmsg_min_mtu(bpf)); + return -EINVAL; + } + + if (bpf->cmsg_multi_ent) + bpf->cmsg_cache_cnt = nfp_bpf_ctrl_cmsg_cache_cnt(bpf); + else + bpf->cmsg_cache_cnt = 1; + + return 0; +} + +static int nfp_bpf_init(struct nfp_app *app) +{ + struct nfp_app_bpf *bpf; + int err; + + bpf = kzalloc(sizeof(*bpf), GFP_KERNEL); + if (!bpf) + return -ENOMEM; + bpf->app = app; + app->priv = bpf; + + INIT_LIST_HEAD(&bpf->map_list); + + err = nfp_ccm_init(&bpf->ccm, app); + if (err) + goto err_free_bpf; + + err = rhashtable_init(&bpf->maps_neutral, &nfp_bpf_maps_neutral_params); + if (err) + goto err_clean_ccm; + + nfp_bpf_init_capabilities(bpf); + + err = nfp_bpf_parse_capabilities(app); + if (err) + goto err_free_neutral_maps; + + if (bpf->abi_version < 3) { + bpf->cmsg_key_sz = CMSG_MAP_KEY_LW * 4; + bpf->cmsg_val_sz = CMSG_MAP_VALUE_LW * 4; + } else { + bpf->cmsg_key_sz = bpf->maps.max_key_sz; + bpf->cmsg_val_sz = bpf->maps.max_val_sz; + app->ctrl_mtu = nfp_bpf_ctrl_cmsg_mtu(bpf); + } + + bpf->bpf_dev = bpf_offload_dev_create(&nfp_bpf_dev_ops, bpf); + err = PTR_ERR_OR_ZERO(bpf->bpf_dev); + if (err) + goto err_free_neutral_maps; + + return 0; + +err_free_neutral_maps: + rhashtable_destroy(&bpf->maps_neutral); +err_clean_ccm: + nfp_ccm_clean(&bpf->ccm); +err_free_bpf: + kfree(bpf); + return err; +} + +static void nfp_bpf_clean(struct nfp_app *app) +{ + struct nfp_app_bpf *bpf = app->priv; + + bpf_offload_dev_destroy(bpf->bpf_dev); + nfp_ccm_clean(&bpf->ccm); + WARN_ON(!list_empty(&bpf->map_list)); + WARN_ON(bpf->maps_in_use || bpf->map_elems_in_use); + rhashtable_free_and_destroy(&bpf->maps_neutral, + nfp_check_rhashtable_empty, NULL); + kfree(bpf); +} + +const struct nfp_app_type app_bpf = { + .id = NFP_APP_BPF_NIC, + .name = "ebpf", + + .ctrl_cap_mask = 0, + + .init = nfp_bpf_init, + .clean = nfp_bpf_clean, + .start = nfp_bpf_start, + + .check_mtu = nfp_bpf_check_mtu, + + .extra_cap = nfp_bpf_extra_cap, + + .ndo_init = nfp_bpf_ndo_init, + .ndo_uninit = nfp_bpf_ndo_uninit, + + .vnic_alloc = nfp_bpf_vnic_alloc, + .vnic_free = nfp_bpf_vnic_free, + + .ctrl_msg_rx = nfp_bpf_ctrl_msg_rx, + .ctrl_msg_rx_raw = nfp_bpf_ctrl_msg_rx_raw, + + .setup_tc = nfp_bpf_setup_tc, + .bpf = nfp_ndo_bpf, + .xdp_offload = nfp_bpf_xdp_offload, +}; -- cgit v1.2.3