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(). ... --- net/nfc/rawsock.c | 421 ++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 421 insertions(+) create mode 100644 net/nfc/rawsock.c (limited to 'net/nfc/rawsock.c') diff --git a/net/nfc/rawsock.c b/net/nfc/rawsock.c new file mode 100644 index 000000000..5125392bb --- /dev/null +++ b/net/nfc/rawsock.c @@ -0,0 +1,421 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (C) 2011 Instituto Nokia de Tecnologia + * + * Authors: + * Aloisio Almeida Jr + * Lauro Ramos Venancio + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": %s: " fmt, __func__ + +#include +#include +#include +#include + +#include "nfc.h" + +static struct nfc_sock_list raw_sk_list = { + .lock = __RW_LOCK_UNLOCKED(raw_sk_list.lock) +}; + +static void nfc_sock_link(struct nfc_sock_list *l, struct sock *sk) +{ + write_lock(&l->lock); + sk_add_node(sk, &l->head); + write_unlock(&l->lock); +} + +static void nfc_sock_unlink(struct nfc_sock_list *l, struct sock *sk) +{ + write_lock(&l->lock); + sk_del_node_init(sk); + write_unlock(&l->lock); +} + +static void rawsock_write_queue_purge(struct sock *sk) +{ + pr_debug("sk=%p\n", sk); + + spin_lock_bh(&sk->sk_write_queue.lock); + __skb_queue_purge(&sk->sk_write_queue); + nfc_rawsock(sk)->tx_work_scheduled = false; + spin_unlock_bh(&sk->sk_write_queue.lock); +} + +static void rawsock_report_error(struct sock *sk, int err) +{ + pr_debug("sk=%p err=%d\n", sk, err); + + sk->sk_shutdown = SHUTDOWN_MASK; + sk->sk_err = -err; + sk_error_report(sk); + + rawsock_write_queue_purge(sk); +} + +static int rawsock_release(struct socket *sock) +{ + struct sock *sk = sock->sk; + + pr_debug("sock=%p sk=%p\n", sock, sk); + + if (!sk) + return 0; + + if (sock->type == SOCK_RAW) + nfc_sock_unlink(&raw_sk_list, sk); + + sock_orphan(sk); + sock_put(sk); + + return 0; +} + +static int rawsock_connect(struct socket *sock, struct sockaddr *_addr, + int len, int flags) +{ + struct sock *sk = sock->sk; + struct sockaddr_nfc *addr = (struct sockaddr_nfc *)_addr; + struct nfc_dev *dev; + int rc = 0; + + pr_debug("sock=%p sk=%p flags=%d\n", sock, sk, flags); + + if (!addr || len < sizeof(struct sockaddr_nfc) || + addr->sa_family != AF_NFC) + return -EINVAL; + + pr_debug("addr dev_idx=%u target_idx=%u protocol=%u\n", + addr->dev_idx, addr->target_idx, addr->nfc_protocol); + + lock_sock(sk); + + if (sock->state == SS_CONNECTED) { + rc = -EISCONN; + goto error; + } + + dev = nfc_get_device(addr->dev_idx); + if (!dev) { + rc = -ENODEV; + goto error; + } + + if (addr->target_idx > dev->target_next_idx - 1 || + addr->target_idx < dev->target_next_idx - dev->n_targets) { + rc = -EINVAL; + goto put_dev; + } + + rc = nfc_activate_target(dev, addr->target_idx, addr->nfc_protocol); + if (rc) + goto put_dev; + + nfc_rawsock(sk)->dev = dev; + nfc_rawsock(sk)->target_idx = addr->target_idx; + sock->state = SS_CONNECTED; + sk->sk_state = TCP_ESTABLISHED; + sk->sk_state_change(sk); + + release_sock(sk); + return 0; + +put_dev: + nfc_put_device(dev); +error: + release_sock(sk); + return rc; +} + +static int rawsock_add_header(struct sk_buff *skb) +{ + *(u8 *)skb_push(skb, NFC_HEADER_SIZE) = 0; + + return 0; +} + +static void rawsock_data_exchange_complete(void *context, struct sk_buff *skb, + int err) +{ + struct sock *sk = (struct sock *) context; + + BUG_ON(in_hardirq()); + + pr_debug("sk=%p err=%d\n", sk, err); + + if (err) + goto error; + + err = rawsock_add_header(skb); + if (err) + goto error_skb; + + err = sock_queue_rcv_skb(sk, skb); + if (err) + goto error_skb; + + spin_lock_bh(&sk->sk_write_queue.lock); + if (!skb_queue_empty(&sk->sk_write_queue)) + schedule_work(&nfc_rawsock(sk)->tx_work); + else + nfc_rawsock(sk)->tx_work_scheduled = false; + spin_unlock_bh(&sk->sk_write_queue.lock); + + sock_put(sk); + return; + +error_skb: + kfree_skb(skb); + +error: + rawsock_report_error(sk, err); + sock_put(sk); +} + +static void rawsock_tx_work(struct work_struct *work) +{ + struct sock *sk = to_rawsock_sk(work); + struct nfc_dev *dev = nfc_rawsock(sk)->dev; + u32 target_idx = nfc_rawsock(sk)->target_idx; + struct sk_buff *skb; + int rc; + + pr_debug("sk=%p target_idx=%u\n", sk, target_idx); + + if (sk->sk_shutdown & SEND_SHUTDOWN) { + rawsock_write_queue_purge(sk); + return; + } + + skb = skb_dequeue(&sk->sk_write_queue); + kcov_remote_start_common(skb_get_kcov_handle(skb)); + + sock_hold(sk); + rc = nfc_data_exchange(dev, target_idx, skb, + rawsock_data_exchange_complete, sk); + if (rc) { + rawsock_report_error(sk, rc); + sock_put(sk); + } + kcov_remote_stop(); +} + +static int rawsock_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) +{ + struct sock *sk = sock->sk; + struct nfc_dev *dev = nfc_rawsock(sk)->dev; + struct sk_buff *skb; + int rc; + + pr_debug("sock=%p sk=%p len=%zu\n", sock, sk, len); + + if (msg->msg_namelen) + return -EOPNOTSUPP; + + if (sock->state != SS_CONNECTED) + return -ENOTCONN; + + skb = nfc_alloc_send_skb(dev, sk, msg->msg_flags, len, &rc); + if (skb == NULL) + return rc; + + rc = memcpy_from_msg(skb_put(skb, len), msg, len); + if (rc < 0) { + kfree_skb(skb); + return rc; + } + + spin_lock_bh(&sk->sk_write_queue.lock); + __skb_queue_tail(&sk->sk_write_queue, skb); + if (!nfc_rawsock(sk)->tx_work_scheduled) { + schedule_work(&nfc_rawsock(sk)->tx_work); + nfc_rawsock(sk)->tx_work_scheduled = true; + } + spin_unlock_bh(&sk->sk_write_queue.lock); + + return len; +} + +static int rawsock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, + int flags) +{ + struct sock *sk = sock->sk; + struct sk_buff *skb; + int copied; + int rc; + + pr_debug("sock=%p sk=%p len=%zu flags=%d\n", sock, sk, len, flags); + + skb = skb_recv_datagram(sk, flags, &rc); + if (!skb) + return rc; + + copied = skb->len; + if (len < copied) { + msg->msg_flags |= MSG_TRUNC; + copied = len; + } + + rc = skb_copy_datagram_msg(skb, 0, msg, copied); + + skb_free_datagram(sk, skb); + + return rc ? : copied; +} + +static const struct proto_ops rawsock_ops = { + .family = PF_NFC, + .owner = THIS_MODULE, + .release = rawsock_release, + .bind = sock_no_bind, + .connect = rawsock_connect, + .socketpair = sock_no_socketpair, + .accept = sock_no_accept, + .getname = sock_no_getname, + .poll = datagram_poll, + .ioctl = sock_no_ioctl, + .listen = sock_no_listen, + .shutdown = sock_no_shutdown, + .sendmsg = rawsock_sendmsg, + .recvmsg = rawsock_recvmsg, + .mmap = sock_no_mmap, +}; + +static const struct proto_ops rawsock_raw_ops = { + .family = PF_NFC, + .owner = THIS_MODULE, + .release = rawsock_release, + .bind = sock_no_bind, + .connect = sock_no_connect, + .socketpair = sock_no_socketpair, + .accept = sock_no_accept, + .getname = sock_no_getname, + .poll = datagram_poll, + .ioctl = sock_no_ioctl, + .listen = sock_no_listen, + .shutdown = sock_no_shutdown, + .sendmsg = sock_no_sendmsg, + .recvmsg = rawsock_recvmsg, + .mmap = sock_no_mmap, +}; + +static void rawsock_destruct(struct sock *sk) +{ + pr_debug("sk=%p\n", sk); + + if (sk->sk_state == TCP_ESTABLISHED) { + nfc_deactivate_target(nfc_rawsock(sk)->dev, + nfc_rawsock(sk)->target_idx, + NFC_TARGET_MODE_IDLE); + nfc_put_device(nfc_rawsock(sk)->dev); + } + + skb_queue_purge(&sk->sk_receive_queue); + + if (!sock_flag(sk, SOCK_DEAD)) { + pr_err("Freeing alive NFC raw socket %p\n", sk); + return; + } +} + +static int rawsock_create(struct net *net, struct socket *sock, + const struct nfc_protocol *nfc_proto, int kern) +{ + struct sock *sk; + + pr_debug("sock=%p\n", sock); + + if ((sock->type != SOCK_SEQPACKET) && (sock->type != SOCK_RAW)) + return -ESOCKTNOSUPPORT; + + if (sock->type == SOCK_RAW) { + if (!ns_capable(net->user_ns, CAP_NET_RAW)) + return -EPERM; + sock->ops = &rawsock_raw_ops; + } else { + sock->ops = &rawsock_ops; + } + + sk = sk_alloc(net, PF_NFC, GFP_ATOMIC, nfc_proto->proto, kern); + if (!sk) + return -ENOMEM; + + sock_init_data(sock, sk); + sk->sk_protocol = nfc_proto->id; + sk->sk_destruct = rawsock_destruct; + sock->state = SS_UNCONNECTED; + if (sock->type == SOCK_RAW) + nfc_sock_link(&raw_sk_list, sk); + else { + INIT_WORK(&nfc_rawsock(sk)->tx_work, rawsock_tx_work); + nfc_rawsock(sk)->tx_work_scheduled = false; + } + + return 0; +} + +void nfc_send_to_raw_sock(struct nfc_dev *dev, struct sk_buff *skb, + u8 payload_type, u8 direction) +{ + struct sk_buff *skb_copy = NULL, *nskb; + struct sock *sk; + u8 *data; + + read_lock(&raw_sk_list.lock); + + sk_for_each(sk, &raw_sk_list.head) { + if (!skb_copy) { + skb_copy = __pskb_copy_fclone(skb, NFC_RAW_HEADER_SIZE, + GFP_ATOMIC, true); + if (!skb_copy) + continue; + + data = skb_push(skb_copy, NFC_RAW_HEADER_SIZE); + + data[0] = dev ? dev->idx : 0xFF; + data[1] = direction & 0x01; + data[1] |= (payload_type << 1); + } + + nskb = skb_clone(skb_copy, GFP_ATOMIC); + if (!nskb) + continue; + + if (sock_queue_rcv_skb(sk, nskb)) + kfree_skb(nskb); + } + + read_unlock(&raw_sk_list.lock); + + kfree_skb(skb_copy); +} +EXPORT_SYMBOL(nfc_send_to_raw_sock); + +static struct proto rawsock_proto = { + .name = "NFC_RAW", + .owner = THIS_MODULE, + .obj_size = sizeof(struct nfc_rawsock), +}; + +static const struct nfc_protocol rawsock_nfc_proto = { + .id = NFC_SOCKPROTO_RAW, + .proto = &rawsock_proto, + .owner = THIS_MODULE, + .create = rawsock_create +}; + +int __init rawsock_init(void) +{ + int rc; + + rc = nfc_proto_register(&rawsock_nfc_proto); + + return rc; +} + +void rawsock_exit(void) +{ + nfc_proto_unregister(&rawsock_nfc_proto); +} -- cgit v1.2.3