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(). ... --- kernel/bpf/net_namespace.c | 567 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 567 insertions(+) create mode 100644 kernel/bpf/net_namespace.c (limited to 'kernel/bpf/net_namespace.c') diff --git a/kernel/bpf/net_namespace.c b/kernel/bpf/net_namespace.c new file mode 100644 index 000000000..868cc2c43 --- /dev/null +++ b/kernel/bpf/net_namespace.c @@ -0,0 +1,567 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include +#include +#include +#include + +/* + * Functions to manage BPF programs attached to netns + */ + +struct bpf_netns_link { + struct bpf_link link; + enum bpf_attach_type type; + enum netns_bpf_attach_type netns_type; + + /* We don't hold a ref to net in order to auto-detach the link + * when netns is going away. Instead we rely on pernet + * pre_exit callback to clear this pointer. Must be accessed + * with netns_bpf_mutex held. + */ + struct net *net; + struct list_head node; /* node in list of links attached to net */ +}; + +/* Protects updates to netns_bpf */ +DEFINE_MUTEX(netns_bpf_mutex); + +static void netns_bpf_attach_type_unneed(enum netns_bpf_attach_type type) +{ + switch (type) { +#ifdef CONFIG_INET + case NETNS_BPF_SK_LOOKUP: + static_branch_dec(&bpf_sk_lookup_enabled); + break; +#endif + default: + break; + } +} + +static void netns_bpf_attach_type_need(enum netns_bpf_attach_type type) +{ + switch (type) { +#ifdef CONFIG_INET + case NETNS_BPF_SK_LOOKUP: + static_branch_inc(&bpf_sk_lookup_enabled); + break; +#endif + default: + break; + } +} + +/* Must be called with netns_bpf_mutex held. */ +static void netns_bpf_run_array_detach(struct net *net, + enum netns_bpf_attach_type type) +{ + struct bpf_prog_array *run_array; + + run_array = rcu_replace_pointer(net->bpf.run_array[type], NULL, + lockdep_is_held(&netns_bpf_mutex)); + bpf_prog_array_free(run_array); +} + +static int link_index(struct net *net, enum netns_bpf_attach_type type, + struct bpf_netns_link *link) +{ + struct bpf_netns_link *pos; + int i = 0; + + list_for_each_entry(pos, &net->bpf.links[type], node) { + if (pos == link) + return i; + i++; + } + return -ENOENT; +} + +static int link_count(struct net *net, enum netns_bpf_attach_type type) +{ + struct list_head *pos; + int i = 0; + + list_for_each(pos, &net->bpf.links[type]) + i++; + return i; +} + +static void fill_prog_array(struct net *net, enum netns_bpf_attach_type type, + struct bpf_prog_array *prog_array) +{ + struct bpf_netns_link *pos; + unsigned int i = 0; + + list_for_each_entry(pos, &net->bpf.links[type], node) { + prog_array->items[i].prog = pos->link.prog; + i++; + } +} + +static void bpf_netns_link_release(struct bpf_link *link) +{ + struct bpf_netns_link *net_link = + container_of(link, struct bpf_netns_link, link); + enum netns_bpf_attach_type type = net_link->netns_type; + struct bpf_prog_array *old_array, *new_array; + struct net *net; + int cnt, idx; + + mutex_lock(&netns_bpf_mutex); + + /* We can race with cleanup_net, but if we see a non-NULL + * struct net pointer, pre_exit has not run yet and wait for + * netns_bpf_mutex. + */ + net = net_link->net; + if (!net) + goto out_unlock; + + /* Mark attach point as unused */ + netns_bpf_attach_type_unneed(type); + + /* Remember link position in case of safe delete */ + idx = link_index(net, type, net_link); + list_del(&net_link->node); + + cnt = link_count(net, type); + if (!cnt) { + netns_bpf_run_array_detach(net, type); + goto out_unlock; + } + + old_array = rcu_dereference_protected(net->bpf.run_array[type], + lockdep_is_held(&netns_bpf_mutex)); + new_array = bpf_prog_array_alloc(cnt, GFP_KERNEL); + if (!new_array) { + WARN_ON(bpf_prog_array_delete_safe_at(old_array, idx)); + goto out_unlock; + } + fill_prog_array(net, type, new_array); + rcu_assign_pointer(net->bpf.run_array[type], new_array); + bpf_prog_array_free(old_array); + +out_unlock: + net_link->net = NULL; + mutex_unlock(&netns_bpf_mutex); +} + +static int bpf_netns_link_detach(struct bpf_link *link) +{ + bpf_netns_link_release(link); + return 0; +} + +static void bpf_netns_link_dealloc(struct bpf_link *link) +{ + struct bpf_netns_link *net_link = + container_of(link, struct bpf_netns_link, link); + + kfree(net_link); +} + +static int bpf_netns_link_update_prog(struct bpf_link *link, + struct bpf_prog *new_prog, + struct bpf_prog *old_prog) +{ + struct bpf_netns_link *net_link = + container_of(link, struct bpf_netns_link, link); + enum netns_bpf_attach_type type = net_link->netns_type; + struct bpf_prog_array *run_array; + struct net *net; + int idx, ret; + + if (old_prog && old_prog != link->prog) + return -EPERM; + if (new_prog->type != link->prog->type) + return -EINVAL; + + mutex_lock(&netns_bpf_mutex); + + net = net_link->net; + if (!net || !check_net(net)) { + /* Link auto-detached or netns dying */ + ret = -ENOLINK; + goto out_unlock; + } + + run_array = rcu_dereference_protected(net->bpf.run_array[type], + lockdep_is_held(&netns_bpf_mutex)); + idx = link_index(net, type, net_link); + ret = bpf_prog_array_update_at(run_array, idx, new_prog); + if (ret) + goto out_unlock; + + old_prog = xchg(&link->prog, new_prog); + bpf_prog_put(old_prog); + +out_unlock: + mutex_unlock(&netns_bpf_mutex); + return ret; +} + +static int bpf_netns_link_fill_info(const struct bpf_link *link, + struct bpf_link_info *info) +{ + const struct bpf_netns_link *net_link = + container_of(link, struct bpf_netns_link, link); + unsigned int inum = 0; + struct net *net; + + mutex_lock(&netns_bpf_mutex); + net = net_link->net; + if (net && check_net(net)) + inum = net->ns.inum; + mutex_unlock(&netns_bpf_mutex); + + info->netns.netns_ino = inum; + info->netns.attach_type = net_link->type; + return 0; +} + +static void bpf_netns_link_show_fdinfo(const struct bpf_link *link, + struct seq_file *seq) +{ + struct bpf_link_info info = {}; + + bpf_netns_link_fill_info(link, &info); + seq_printf(seq, + "netns_ino:\t%u\n" + "attach_type:\t%u\n", + info.netns.netns_ino, + info.netns.attach_type); +} + +static const struct bpf_link_ops bpf_netns_link_ops = { + .release = bpf_netns_link_release, + .dealloc = bpf_netns_link_dealloc, + .detach = bpf_netns_link_detach, + .update_prog = bpf_netns_link_update_prog, + .fill_link_info = bpf_netns_link_fill_info, + .show_fdinfo = bpf_netns_link_show_fdinfo, +}; + +/* Must be called with netns_bpf_mutex held. */ +static int __netns_bpf_prog_query(const union bpf_attr *attr, + union bpf_attr __user *uattr, + struct net *net, + enum netns_bpf_attach_type type) +{ + __u32 __user *prog_ids = u64_to_user_ptr(attr->query.prog_ids); + struct bpf_prog_array *run_array; + u32 prog_cnt = 0, flags = 0; + + run_array = rcu_dereference_protected(net->bpf.run_array[type], + lockdep_is_held(&netns_bpf_mutex)); + if (run_array) + prog_cnt = bpf_prog_array_length(run_array); + + if (copy_to_user(&uattr->query.attach_flags, &flags, sizeof(flags))) + return -EFAULT; + if (copy_to_user(&uattr->query.prog_cnt, &prog_cnt, sizeof(prog_cnt))) + return -EFAULT; + if (!attr->query.prog_cnt || !prog_ids || !prog_cnt) + return 0; + + return bpf_prog_array_copy_to_user(run_array, prog_ids, + attr->query.prog_cnt); +} + +int netns_bpf_prog_query(const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + enum netns_bpf_attach_type type; + struct net *net; + int ret; + + if (attr->query.query_flags) + return -EINVAL; + + type = to_netns_bpf_attach_type(attr->query.attach_type); + if (type < 0) + return -EINVAL; + + net = get_net_ns_by_fd(attr->query.target_fd); + if (IS_ERR(net)) + return PTR_ERR(net); + + mutex_lock(&netns_bpf_mutex); + ret = __netns_bpf_prog_query(attr, uattr, net, type); + mutex_unlock(&netns_bpf_mutex); + + put_net(net); + return ret; +} + +int netns_bpf_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog) +{ + struct bpf_prog_array *run_array; + enum netns_bpf_attach_type type; + struct bpf_prog *attached; + struct net *net; + int ret; + + if (attr->target_fd || attr->attach_flags || attr->replace_bpf_fd) + return -EINVAL; + + type = to_netns_bpf_attach_type(attr->attach_type); + if (type < 0) + return -EINVAL; + + net = current->nsproxy->net_ns; + mutex_lock(&netns_bpf_mutex); + + /* Attaching prog directly is not compatible with links */ + if (!list_empty(&net->bpf.links[type])) { + ret = -EEXIST; + goto out_unlock; + } + + switch (type) { + case NETNS_BPF_FLOW_DISSECTOR: + ret = flow_dissector_bpf_prog_attach_check(net, prog); + break; + default: + ret = -EINVAL; + break; + } + if (ret) + goto out_unlock; + + attached = net->bpf.progs[type]; + if (attached == prog) { + /* The same program cannot be attached twice */ + ret = -EINVAL; + goto out_unlock; + } + + run_array = rcu_dereference_protected(net->bpf.run_array[type], + lockdep_is_held(&netns_bpf_mutex)); + if (run_array) { + WRITE_ONCE(run_array->items[0].prog, prog); + } else { + run_array = bpf_prog_array_alloc(1, GFP_KERNEL); + if (!run_array) { + ret = -ENOMEM; + goto out_unlock; + } + run_array->items[0].prog = prog; + rcu_assign_pointer(net->bpf.run_array[type], run_array); + } + + net->bpf.progs[type] = prog; + if (attached) + bpf_prog_put(attached); + +out_unlock: + mutex_unlock(&netns_bpf_mutex); + + return ret; +} + +/* Must be called with netns_bpf_mutex held. */ +static int __netns_bpf_prog_detach(struct net *net, + enum netns_bpf_attach_type type, + struct bpf_prog *old) +{ + struct bpf_prog *attached; + + /* Progs attached via links cannot be detached */ + if (!list_empty(&net->bpf.links[type])) + return -EINVAL; + + attached = net->bpf.progs[type]; + if (!attached || attached != old) + return -ENOENT; + netns_bpf_run_array_detach(net, type); + net->bpf.progs[type] = NULL; + bpf_prog_put(attached); + return 0; +} + +int netns_bpf_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype) +{ + enum netns_bpf_attach_type type; + struct bpf_prog *prog; + int ret; + + if (attr->target_fd) + return -EINVAL; + + type = to_netns_bpf_attach_type(attr->attach_type); + if (type < 0) + return -EINVAL; + + prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype); + if (IS_ERR(prog)) + return PTR_ERR(prog); + + mutex_lock(&netns_bpf_mutex); + ret = __netns_bpf_prog_detach(current->nsproxy->net_ns, type, prog); + mutex_unlock(&netns_bpf_mutex); + + bpf_prog_put(prog); + + return ret; +} + +static int netns_bpf_max_progs(enum netns_bpf_attach_type type) +{ + switch (type) { + case NETNS_BPF_FLOW_DISSECTOR: + return 1; + case NETNS_BPF_SK_LOOKUP: + return 64; + default: + return 0; + } +} + +static int netns_bpf_link_attach(struct net *net, struct bpf_link *link, + enum netns_bpf_attach_type type) +{ + struct bpf_netns_link *net_link = + container_of(link, struct bpf_netns_link, link); + struct bpf_prog_array *run_array; + int cnt, err; + + mutex_lock(&netns_bpf_mutex); + + cnt = link_count(net, type); + if (cnt >= netns_bpf_max_progs(type)) { + err = -E2BIG; + goto out_unlock; + } + /* Links are not compatible with attaching prog directly */ + if (net->bpf.progs[type]) { + err = -EEXIST; + goto out_unlock; + } + + switch (type) { + case NETNS_BPF_FLOW_DISSECTOR: + err = flow_dissector_bpf_prog_attach_check(net, link->prog); + break; + case NETNS_BPF_SK_LOOKUP: + err = 0; /* nothing to check */ + break; + default: + err = -EINVAL; + break; + } + if (err) + goto out_unlock; + + run_array = bpf_prog_array_alloc(cnt + 1, GFP_KERNEL); + if (!run_array) { + err = -ENOMEM; + goto out_unlock; + } + + list_add_tail(&net_link->node, &net->bpf.links[type]); + + fill_prog_array(net, type, run_array); + run_array = rcu_replace_pointer(net->bpf.run_array[type], run_array, + lockdep_is_held(&netns_bpf_mutex)); + bpf_prog_array_free(run_array); + + /* Mark attach point as used */ + netns_bpf_attach_type_need(type); + +out_unlock: + mutex_unlock(&netns_bpf_mutex); + return err; +} + +int netns_bpf_link_create(const union bpf_attr *attr, struct bpf_prog *prog) +{ + enum netns_bpf_attach_type netns_type; + struct bpf_link_primer link_primer; + struct bpf_netns_link *net_link; + enum bpf_attach_type type; + struct net *net; + int err; + + if (attr->link_create.flags) + return -EINVAL; + + type = attr->link_create.attach_type; + netns_type = to_netns_bpf_attach_type(type); + if (netns_type < 0) + return -EINVAL; + + net = get_net_ns_by_fd(attr->link_create.target_fd); + if (IS_ERR(net)) + return PTR_ERR(net); + + net_link = kzalloc(sizeof(*net_link), GFP_USER); + if (!net_link) { + err = -ENOMEM; + goto out_put_net; + } + bpf_link_init(&net_link->link, BPF_LINK_TYPE_NETNS, + &bpf_netns_link_ops, prog); + net_link->net = net; + net_link->type = type; + net_link->netns_type = netns_type; + + err = bpf_link_prime(&net_link->link, &link_primer); + if (err) { + kfree(net_link); + goto out_put_net; + } + + err = netns_bpf_link_attach(net, &net_link->link, netns_type); + if (err) { + bpf_link_cleanup(&link_primer); + goto out_put_net; + } + + put_net(net); + return bpf_link_settle(&link_primer); + +out_put_net: + put_net(net); + return err; +} + +static int __net_init netns_bpf_pernet_init(struct net *net) +{ + int type; + + for (type = 0; type < MAX_NETNS_BPF_ATTACH_TYPE; type++) + INIT_LIST_HEAD(&net->bpf.links[type]); + + return 0; +} + +static void __net_exit netns_bpf_pernet_pre_exit(struct net *net) +{ + enum netns_bpf_attach_type type; + struct bpf_netns_link *net_link; + + mutex_lock(&netns_bpf_mutex); + for (type = 0; type < MAX_NETNS_BPF_ATTACH_TYPE; type++) { + netns_bpf_run_array_detach(net, type); + list_for_each_entry(net_link, &net->bpf.links[type], node) { + net_link->net = NULL; /* auto-detach link */ + netns_bpf_attach_type_unneed(type); + } + if (net->bpf.progs[type]) + bpf_prog_put(net->bpf.progs[type]); + } + mutex_unlock(&netns_bpf_mutex); +} + +static struct pernet_operations netns_bpf_pernet_ops __net_initdata = { + .init = netns_bpf_pernet_init, + .pre_exit = netns_bpf_pernet_pre_exit, +}; + +static int __init netns_bpf_init(void) +{ + return register_pernet_subsys(&netns_bpf_pernet_ops); +} + +subsys_initcall(netns_bpf_init); -- cgit v1.2.3