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/netdevsim/bpf.c | 653 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 653 insertions(+) create mode 100644 drivers/net/netdevsim/bpf.c (limited to 'drivers/net/netdevsim/bpf.c') diff --git a/drivers/net/netdevsim/bpf.c b/drivers/net/netdevsim/bpf.c new file mode 100644 index 000000000..f60eb97e3 --- /dev/null +++ b/drivers/net/netdevsim/bpf.c @@ -0,0 +1,653 @@ +/* + * Copyright (C) 2017 Netronome Systems, Inc. + * + * This software is licensed under the GNU General License Version 2, + * June 1991 as shown in the file COPYING in the top-level directory of this + * source tree. + * + * THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" + * WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, + * BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS + * FOR A PARTICULAR PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE + * OF THE PROGRAM IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME + * THE COST OF ALL NECESSARY SERVICING, REPAIR OR CORRECTION. + */ + +#include +#include +#include +#include +#include +#include +#include + +#include "netdevsim.h" + +#define pr_vlog(env, fmt, ...) \ + bpf_verifier_log_write(env, "[netdevsim] " fmt, ##__VA_ARGS__) + +struct nsim_bpf_bound_prog { + struct nsim_dev *nsim_dev; + struct bpf_prog *prog; + struct dentry *ddir; + const char *state; + bool is_loaded; + struct list_head l; +}; + +#define NSIM_BPF_MAX_KEYS 2 + +struct nsim_bpf_bound_map { + struct netdevsim *ns; + struct bpf_offloaded_map *map; + struct mutex mutex; + struct nsim_map_entry { + void *key; + void *value; + } entry[NSIM_BPF_MAX_KEYS]; + struct list_head l; +}; + +static int nsim_bpf_string_show(struct seq_file *file, void *data) +{ + const char **str = file->private; + + if (*str) + seq_printf(file, "%s\n", *str); + + return 0; +} +DEFINE_SHOW_ATTRIBUTE(nsim_bpf_string); + +static int +nsim_bpf_verify_insn(struct bpf_verifier_env *env, int insn_idx, int prev_insn) +{ + struct nsim_bpf_bound_prog *state; + int ret = 0; + + state = env->prog->aux->offload->dev_priv; + if (state->nsim_dev->bpf_bind_verifier_delay && !insn_idx) + msleep(state->nsim_dev->bpf_bind_verifier_delay); + + if (insn_idx == env->prog->len - 1) { + pr_vlog(env, "Hello from netdevsim!\n"); + + if (!state->nsim_dev->bpf_bind_verifier_accept) + ret = -EOPNOTSUPP; + } + + return ret; +} + +static int nsim_bpf_finalize(struct bpf_verifier_env *env) +{ + return 0; +} + +static bool nsim_xdp_offload_active(struct netdevsim *ns) +{ + return ns->xdp_hw.prog; +} + +static void nsim_prog_set_loaded(struct bpf_prog *prog, bool loaded) +{ + struct nsim_bpf_bound_prog *state; + + if (!prog || !prog->aux->offload) + return; + + state = prog->aux->offload->dev_priv; + state->is_loaded = loaded; +} + +static int +nsim_bpf_offload(struct netdevsim *ns, struct bpf_prog *prog, bool oldprog) +{ + nsim_prog_set_loaded(ns->bpf_offloaded, false); + + WARN(!!ns->bpf_offloaded != oldprog, + "bad offload state, expected offload %sto be active", + oldprog ? "" : "not "); + ns->bpf_offloaded = prog; + ns->bpf_offloaded_id = prog ? prog->aux->id : 0; + nsim_prog_set_loaded(prog, true); + + return 0; +} + +int nsim_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 bpf_prog *prog = cls_bpf->prog; + struct netdevsim *ns = cb_priv; + struct bpf_prog *oldprog; + + if (type != TC_SETUP_CLSBPF) { + NSIM_EA(cls_bpf->common.extack, + "only offload of BPF classifiers supported"); + return -EOPNOTSUPP; + } + + if (!tc_cls_can_offload_and_chain0(ns->netdev, &cls_bpf->common)) + return -EOPNOTSUPP; + + if (cls_bpf->common.protocol != htons(ETH_P_ALL)) { + NSIM_EA(cls_bpf->common.extack, + "only ETH_P_ALL supported as filter protocol"); + return -EOPNOTSUPP; + } + + if (!ns->bpf_tc_accept) { + NSIM_EA(cls_bpf->common.extack, + "netdevsim configured to reject BPF TC offload"); + return -EOPNOTSUPP; + } + /* Note: progs without skip_sw will probably not be dev bound */ + if (prog && !prog->aux->offload && !ns->bpf_tc_non_bound_accept) { + NSIM_EA(cls_bpf->common.extack, + "netdevsim configured to reject unbound programs"); + return -EOPNOTSUPP; + } + + if (cls_bpf->command != TC_CLSBPF_OFFLOAD) + return -EOPNOTSUPP; + + oldprog = cls_bpf->oldprog; + + /* Don't remove if oldprog doesn't match driver's state */ + if (ns->bpf_offloaded != oldprog) { + oldprog = NULL; + if (!cls_bpf->prog) + return 0; + if (ns->bpf_offloaded) { + NSIM_EA(cls_bpf->common.extack, + "driver and netdev offload states mismatch"); + return -EBUSY; + } + } + + return nsim_bpf_offload(ns, cls_bpf->prog, oldprog); +} + +int nsim_bpf_disable_tc(struct netdevsim *ns) +{ + if (ns->bpf_offloaded && !nsim_xdp_offload_active(ns)) + return -EBUSY; + return 0; +} + +static int nsim_xdp_offload_prog(struct netdevsim *ns, struct netdev_bpf *bpf) +{ + if (!nsim_xdp_offload_active(ns) && !bpf->prog) + return 0; + if (!nsim_xdp_offload_active(ns) && bpf->prog && ns->bpf_offloaded) { + NSIM_EA(bpf->extack, "TC program is already loaded"); + return -EBUSY; + } + + return nsim_bpf_offload(ns, bpf->prog, nsim_xdp_offload_active(ns)); +} + +static int +nsim_xdp_set_prog(struct netdevsim *ns, struct netdev_bpf *bpf, + struct xdp_attachment_info *xdp) +{ + int err; + + if (bpf->command == XDP_SETUP_PROG && !ns->bpf_xdpdrv_accept) { + NSIM_EA(bpf->extack, "driver XDP disabled in DebugFS"); + return -EOPNOTSUPP; + } + if (bpf->command == XDP_SETUP_PROG_HW && !ns->bpf_xdpoffload_accept) { + NSIM_EA(bpf->extack, "XDP offload disabled in DebugFS"); + return -EOPNOTSUPP; + } + + if (bpf->command == XDP_SETUP_PROG_HW) { + err = nsim_xdp_offload_prog(ns, bpf); + if (err) + return err; + } + + xdp_attachment_setup(xdp, bpf); + + return 0; +} + +static int nsim_bpf_create_prog(struct nsim_dev *nsim_dev, + struct bpf_prog *prog) +{ + struct nsim_bpf_bound_prog *state; + char name[16]; + int ret; + + state = kzalloc(sizeof(*state), GFP_KERNEL); + if (!state) + return -ENOMEM; + + state->nsim_dev = nsim_dev; + state->prog = prog; + state->state = "verify"; + + /* Program id is not populated yet when we create the state. */ + sprintf(name, "%u", nsim_dev->prog_id_gen++); + state->ddir = debugfs_create_dir(name, nsim_dev->ddir_bpf_bound_progs); + if (IS_ERR(state->ddir)) { + ret = PTR_ERR(state->ddir); + kfree(state); + return ret; + } + + debugfs_create_u32("id", 0400, state->ddir, &prog->aux->id); + debugfs_create_file("state", 0400, state->ddir, + &state->state, &nsim_bpf_string_fops); + debugfs_create_bool("loaded", 0400, state->ddir, &state->is_loaded); + + list_add_tail(&state->l, &nsim_dev->bpf_bound_progs); + + prog->aux->offload->dev_priv = state; + + return 0; +} + +static int nsim_bpf_verifier_prep(struct bpf_prog *prog) +{ + struct nsim_dev *nsim_dev = + bpf_offload_dev_priv(prog->aux->offload->offdev); + + if (!nsim_dev->bpf_bind_accept) + return -EOPNOTSUPP; + + return nsim_bpf_create_prog(nsim_dev, prog); +} + +static int nsim_bpf_translate(struct bpf_prog *prog) +{ + struct nsim_bpf_bound_prog *state = prog->aux->offload->dev_priv; + + state->state = "xlated"; + return 0; +} + +static void nsim_bpf_destroy_prog(struct bpf_prog *prog) +{ + struct nsim_bpf_bound_prog *state; + + state = prog->aux->offload->dev_priv; + WARN(state->is_loaded, + "offload state destroyed while program still bound"); + debugfs_remove_recursive(state->ddir); + list_del(&state->l); + kfree(state); +} + +static const struct bpf_prog_offload_ops nsim_bpf_dev_ops = { + .insn_hook = nsim_bpf_verify_insn, + .finalize = nsim_bpf_finalize, + .prepare = nsim_bpf_verifier_prep, + .translate = nsim_bpf_translate, + .destroy = nsim_bpf_destroy_prog, +}; + +static int nsim_setup_prog_checks(struct netdevsim *ns, struct netdev_bpf *bpf) +{ + if (bpf->prog && bpf->prog->aux->offload) { + NSIM_EA(bpf->extack, "attempt to load offloaded prog to drv"); + return -EINVAL; + } + if (ns->netdev->mtu > NSIM_XDP_MAX_MTU) { + NSIM_EA(bpf->extack, "MTU too large w/ XDP enabled"); + return -EINVAL; + } + return 0; +} + +static int +nsim_setup_prog_hw_checks(struct netdevsim *ns, struct netdev_bpf *bpf) +{ + struct nsim_bpf_bound_prog *state; + + if (!bpf->prog) + return 0; + + if (!bpf->prog->aux->offload) { + NSIM_EA(bpf->extack, "xdpoffload of non-bound program"); + return -EINVAL; + } + + state = bpf->prog->aux->offload->dev_priv; + if (WARN_ON(strcmp(state->state, "xlated"))) { + NSIM_EA(bpf->extack, "offloading program in bad state"); + return -EINVAL; + } + return 0; +} + +static bool +nsim_map_key_match(struct bpf_map *map, struct nsim_map_entry *e, void *key) +{ + return e->key && !memcmp(key, e->key, map->key_size); +} + +static int nsim_map_key_find(struct bpf_offloaded_map *offmap, void *key) +{ + struct nsim_bpf_bound_map *nmap = offmap->dev_priv; + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(nmap->entry); i++) + if (nsim_map_key_match(&offmap->map, &nmap->entry[i], key)) + return i; + + return -ENOENT; +} + +static int +nsim_map_alloc_elem(struct bpf_offloaded_map *offmap, unsigned int idx) +{ + struct nsim_bpf_bound_map *nmap = offmap->dev_priv; + + nmap->entry[idx].key = kmalloc(offmap->map.key_size, + GFP_KERNEL_ACCOUNT | __GFP_NOWARN); + if (!nmap->entry[idx].key) + return -ENOMEM; + nmap->entry[idx].value = kmalloc(offmap->map.value_size, + GFP_KERNEL_ACCOUNT | __GFP_NOWARN); + if (!nmap->entry[idx].value) { + kfree(nmap->entry[idx].key); + nmap->entry[idx].key = NULL; + return -ENOMEM; + } + + return 0; +} + +static int +nsim_map_get_next_key(struct bpf_offloaded_map *offmap, + void *key, void *next_key) +{ + struct nsim_bpf_bound_map *nmap = offmap->dev_priv; + int idx = -ENOENT; + + mutex_lock(&nmap->mutex); + + if (key) + idx = nsim_map_key_find(offmap, key); + if (idx == -ENOENT) + idx = 0; + else + idx++; + + for (; idx < ARRAY_SIZE(nmap->entry); idx++) { + if (nmap->entry[idx].key) { + memcpy(next_key, nmap->entry[idx].key, + offmap->map.key_size); + break; + } + } + + mutex_unlock(&nmap->mutex); + + if (idx == ARRAY_SIZE(nmap->entry)) + return -ENOENT; + return 0; +} + +static int +nsim_map_lookup_elem(struct bpf_offloaded_map *offmap, void *key, void *value) +{ + struct nsim_bpf_bound_map *nmap = offmap->dev_priv; + int idx; + + mutex_lock(&nmap->mutex); + + idx = nsim_map_key_find(offmap, key); + if (idx >= 0) + memcpy(value, nmap->entry[idx].value, offmap->map.value_size); + + mutex_unlock(&nmap->mutex); + + return idx < 0 ? idx : 0; +} + +static int +nsim_map_update_elem(struct bpf_offloaded_map *offmap, + void *key, void *value, u64 flags) +{ + struct nsim_bpf_bound_map *nmap = offmap->dev_priv; + int idx, err = 0; + + mutex_lock(&nmap->mutex); + + idx = nsim_map_key_find(offmap, key); + if (idx < 0 && flags == BPF_EXIST) { + err = idx; + goto exit_unlock; + } + if (idx >= 0 && flags == BPF_NOEXIST) { + err = -EEXIST; + goto exit_unlock; + } + + if (idx < 0) { + for (idx = 0; idx < ARRAY_SIZE(nmap->entry); idx++) + if (!nmap->entry[idx].key) + break; + if (idx == ARRAY_SIZE(nmap->entry)) { + err = -E2BIG; + goto exit_unlock; + } + + err = nsim_map_alloc_elem(offmap, idx); + if (err) + goto exit_unlock; + } + + memcpy(nmap->entry[idx].key, key, offmap->map.key_size); + memcpy(nmap->entry[idx].value, value, offmap->map.value_size); +exit_unlock: + mutex_unlock(&nmap->mutex); + + return err; +} + +static int nsim_map_delete_elem(struct bpf_offloaded_map *offmap, void *key) +{ + struct nsim_bpf_bound_map *nmap = offmap->dev_priv; + int idx; + + if (offmap->map.map_type == BPF_MAP_TYPE_ARRAY) + return -EINVAL; + + mutex_lock(&nmap->mutex); + + idx = nsim_map_key_find(offmap, key); + if (idx >= 0) { + kfree(nmap->entry[idx].key); + kfree(nmap->entry[idx].value); + memset(&nmap->entry[idx], 0, sizeof(nmap->entry[idx])); + } + + mutex_unlock(&nmap->mutex); + + return idx < 0 ? idx : 0; +} + +static const struct bpf_map_dev_ops nsim_bpf_map_ops = { + .map_get_next_key = nsim_map_get_next_key, + .map_lookup_elem = nsim_map_lookup_elem, + .map_update_elem = nsim_map_update_elem, + .map_delete_elem = nsim_map_delete_elem, +}; + +static int +nsim_bpf_map_alloc(struct netdevsim *ns, struct bpf_offloaded_map *offmap) +{ + struct nsim_bpf_bound_map *nmap; + int i, err; + + if (WARN_ON(offmap->map.map_type != BPF_MAP_TYPE_ARRAY && + offmap->map.map_type != BPF_MAP_TYPE_HASH)) + return -EINVAL; + if (offmap->map.max_entries > NSIM_BPF_MAX_KEYS) + return -ENOMEM; + if (offmap->map.map_flags) + return -EINVAL; + + nmap = kzalloc(sizeof(*nmap), GFP_KERNEL_ACCOUNT); + if (!nmap) + return -ENOMEM; + + offmap->dev_priv = nmap; + nmap->ns = ns; + nmap->map = offmap; + mutex_init(&nmap->mutex); + + if (offmap->map.map_type == BPF_MAP_TYPE_ARRAY) { + for (i = 0; i < ARRAY_SIZE(nmap->entry); i++) { + u32 *key; + + err = nsim_map_alloc_elem(offmap, i); + if (err) + goto err_free; + key = nmap->entry[i].key; + *key = i; + memset(nmap->entry[i].value, 0, offmap->map.value_size); + } + } + + offmap->dev_ops = &nsim_bpf_map_ops; + list_add_tail(&nmap->l, &ns->nsim_dev->bpf_bound_maps); + + return 0; + +err_free: + while (--i >= 0) { + kfree(nmap->entry[i].key); + kfree(nmap->entry[i].value); + } + kfree(nmap); + return err; +} + +static void nsim_bpf_map_free(struct bpf_offloaded_map *offmap) +{ + struct nsim_bpf_bound_map *nmap = offmap->dev_priv; + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(nmap->entry); i++) { + kfree(nmap->entry[i].key); + kfree(nmap->entry[i].value); + } + list_del_init(&nmap->l); + mutex_destroy(&nmap->mutex); + kfree(nmap); +} + +int nsim_bpf(struct net_device *dev, struct netdev_bpf *bpf) +{ + struct netdevsim *ns = netdev_priv(dev); + int err; + + ASSERT_RTNL(); + + switch (bpf->command) { + case XDP_SETUP_PROG: + err = nsim_setup_prog_checks(ns, bpf); + if (err) + return err; + + return nsim_xdp_set_prog(ns, bpf, &ns->xdp); + case XDP_SETUP_PROG_HW: + err = nsim_setup_prog_hw_checks(ns, bpf); + if (err) + return err; + + return nsim_xdp_set_prog(ns, bpf, &ns->xdp_hw); + case BPF_OFFLOAD_MAP_ALLOC: + if (!ns->bpf_map_accept) + return -EOPNOTSUPP; + + return nsim_bpf_map_alloc(ns, bpf->offmap); + case BPF_OFFLOAD_MAP_FREE: + nsim_bpf_map_free(bpf->offmap); + return 0; + default: + return -EINVAL; + } +} + +int nsim_bpf_dev_init(struct nsim_dev *nsim_dev) +{ + int err; + + INIT_LIST_HEAD(&nsim_dev->bpf_bound_progs); + INIT_LIST_HEAD(&nsim_dev->bpf_bound_maps); + + nsim_dev->ddir_bpf_bound_progs = debugfs_create_dir("bpf_bound_progs", + nsim_dev->ddir); + if (IS_ERR(nsim_dev->ddir_bpf_bound_progs)) + return PTR_ERR(nsim_dev->ddir_bpf_bound_progs); + + nsim_dev->bpf_dev = bpf_offload_dev_create(&nsim_bpf_dev_ops, nsim_dev); + err = PTR_ERR_OR_ZERO(nsim_dev->bpf_dev); + if (err) + return err; + + nsim_dev->bpf_bind_accept = true; + debugfs_create_bool("bpf_bind_accept", 0600, nsim_dev->ddir, + &nsim_dev->bpf_bind_accept); + debugfs_create_u32("bpf_bind_verifier_delay", 0600, nsim_dev->ddir, + &nsim_dev->bpf_bind_verifier_delay); + nsim_dev->bpf_bind_verifier_accept = true; + debugfs_create_bool("bpf_bind_verifier_accept", 0600, nsim_dev->ddir, + &nsim_dev->bpf_bind_verifier_accept); + return 0; +} + +void nsim_bpf_dev_exit(struct nsim_dev *nsim_dev) +{ + WARN_ON(!list_empty(&nsim_dev->bpf_bound_progs)); + WARN_ON(!list_empty(&nsim_dev->bpf_bound_maps)); + bpf_offload_dev_destroy(nsim_dev->bpf_dev); +} + +int nsim_bpf_init(struct netdevsim *ns) +{ + struct dentry *ddir = ns->nsim_dev_port->ddir; + int err; + + err = bpf_offload_dev_netdev_register(ns->nsim_dev->bpf_dev, + ns->netdev); + if (err) + return err; + + debugfs_create_u32("bpf_offloaded_id", 0400, ddir, + &ns->bpf_offloaded_id); + + ns->bpf_tc_accept = true; + debugfs_create_bool("bpf_tc_accept", 0600, ddir, + &ns->bpf_tc_accept); + debugfs_create_bool("bpf_tc_non_bound_accept", 0600, ddir, + &ns->bpf_tc_non_bound_accept); + ns->bpf_xdpdrv_accept = true; + debugfs_create_bool("bpf_xdpdrv_accept", 0600, ddir, + &ns->bpf_xdpdrv_accept); + ns->bpf_xdpoffload_accept = true; + debugfs_create_bool("bpf_xdpoffload_accept", 0600, ddir, + &ns->bpf_xdpoffload_accept); + + ns->bpf_map_accept = true; + debugfs_create_bool("bpf_map_accept", 0600, ddir, + &ns->bpf_map_accept); + + return 0; +} + +void nsim_bpf_uninit(struct netdevsim *ns) +{ + WARN_ON(ns->xdp.prog); + WARN_ON(ns->xdp_hw.prog); + WARN_ON(ns->bpf_offloaded); + bpf_offload_dev_netdev_unregister(ns->nsim_dev->bpf_dev, ns->netdev); +} -- cgit v1.2.3