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/xfrm/espintcp.c | 583 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 583 insertions(+) create mode 100644 net/xfrm/espintcp.c (limited to 'net/xfrm/espintcp.c') diff --git a/net/xfrm/espintcp.c b/net/xfrm/espintcp.c new file mode 100644 index 000000000..872b80188 --- /dev/null +++ b/net/xfrm/espintcp.c @@ -0,0 +1,583 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include +#include +#include +#include +#include +#include +#if IS_ENABLED(CONFIG_IPV6) +#include +#endif + +static void handle_nonesp(struct espintcp_ctx *ctx, struct sk_buff *skb, + struct sock *sk) +{ + if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf || + !sk_rmem_schedule(sk, skb, skb->truesize)) { + XFRM_INC_STATS(sock_net(sk), LINUX_MIB_XFRMINERROR); + kfree_skb(skb); + return; + } + + skb_set_owner_r(skb, sk); + + memset(skb->cb, 0, sizeof(skb->cb)); + skb_queue_tail(&ctx->ike_queue, skb); + ctx->saved_data_ready(sk); +} + +static void handle_esp(struct sk_buff *skb, struct sock *sk) +{ + struct tcp_skb_cb *tcp_cb = (struct tcp_skb_cb *)skb->cb; + + skb_reset_transport_header(skb); + + /* restore IP CB, we need at least IP6CB->nhoff */ + memmove(skb->cb, &tcp_cb->header, sizeof(tcp_cb->header)); + + rcu_read_lock(); + skb->dev = dev_get_by_index_rcu(sock_net(sk), skb->skb_iif); + local_bh_disable(); +#if IS_ENABLED(CONFIG_IPV6) + if (sk->sk_family == AF_INET6) + ipv6_stub->xfrm6_rcv_encap(skb, IPPROTO_ESP, 0, TCP_ENCAP_ESPINTCP); + else +#endif + xfrm4_rcv_encap(skb, IPPROTO_ESP, 0, TCP_ENCAP_ESPINTCP); + local_bh_enable(); + rcu_read_unlock(); +} + +static void espintcp_rcv(struct strparser *strp, struct sk_buff *skb) +{ + struct espintcp_ctx *ctx = container_of(strp, struct espintcp_ctx, + strp); + struct strp_msg *rxm = strp_msg(skb); + int len = rxm->full_len - 2; + u32 nonesp_marker; + int err; + + /* keepalive packet? */ + if (unlikely(len == 1)) { + u8 data; + + err = skb_copy_bits(skb, rxm->offset + 2, &data, 1); + if (err < 0) { + XFRM_INC_STATS(sock_net(strp->sk), LINUX_MIB_XFRMINHDRERROR); + kfree_skb(skb); + return; + } + + if (data == 0xff) { + kfree_skb(skb); + return; + } + } + + /* drop other short messages */ + if (unlikely(len <= sizeof(nonesp_marker))) { + XFRM_INC_STATS(sock_net(strp->sk), LINUX_MIB_XFRMINHDRERROR); + kfree_skb(skb); + return; + } + + err = skb_copy_bits(skb, rxm->offset + 2, &nonesp_marker, + sizeof(nonesp_marker)); + if (err < 0) { + XFRM_INC_STATS(sock_net(strp->sk), LINUX_MIB_XFRMINHDRERROR); + kfree_skb(skb); + return; + } + + /* remove header, leave non-ESP marker/SPI */ + if (!pskb_pull(skb, rxm->offset + 2)) { + XFRM_INC_STATS(sock_net(strp->sk), LINUX_MIB_XFRMINERROR); + kfree_skb(skb); + return; + } + + if (pskb_trim(skb, rxm->full_len - 2) != 0) { + XFRM_INC_STATS(sock_net(strp->sk), LINUX_MIB_XFRMINERROR); + kfree_skb(skb); + return; + } + + if (nonesp_marker == 0) + handle_nonesp(ctx, skb, strp->sk); + else + handle_esp(skb, strp->sk); +} + +static int espintcp_parse(struct strparser *strp, struct sk_buff *skb) +{ + struct strp_msg *rxm = strp_msg(skb); + __be16 blen; + u16 len; + int err; + + if (skb->len < rxm->offset + 2) + return 0; + + err = skb_copy_bits(skb, rxm->offset, &blen, sizeof(blen)); + if (err < 0) + return err; + + len = be16_to_cpu(blen); + if (len < 2) + return -EINVAL; + + return len; +} + +static int espintcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, + int flags, int *addr_len) +{ + struct espintcp_ctx *ctx = espintcp_getctx(sk); + struct sk_buff *skb; + int err = 0; + int copied; + int off = 0; + + skb = __skb_recv_datagram(sk, &ctx->ike_queue, flags, &off, &err); + if (!skb) { + if (err == -EAGAIN && sk->sk_shutdown & RCV_SHUTDOWN) + return 0; + return err; + } + + copied = len; + if (copied > skb->len) + copied = skb->len; + else if (copied < skb->len) + msg->msg_flags |= MSG_TRUNC; + + err = skb_copy_datagram_msg(skb, 0, msg, copied); + if (unlikely(err)) { + kfree_skb(skb); + return err; + } + + if (flags & MSG_TRUNC) + copied = skb->len; + kfree_skb(skb); + return copied; +} + +int espintcp_queue_out(struct sock *sk, struct sk_buff *skb) +{ + struct espintcp_ctx *ctx = espintcp_getctx(sk); + + if (skb_queue_len(&ctx->out_queue) >= READ_ONCE(netdev_max_backlog)) + return -ENOBUFS; + + __skb_queue_tail(&ctx->out_queue, skb); + + return 0; +} +EXPORT_SYMBOL_GPL(espintcp_queue_out); + +/* espintcp length field is 2B and length includes the length field's size */ +#define MAX_ESPINTCP_MSG (((1 << 16) - 1) - 2) + +static int espintcp_sendskb_locked(struct sock *sk, struct espintcp_msg *emsg, + int flags) +{ + do { + int ret; + + ret = skb_send_sock_locked(sk, emsg->skb, + emsg->offset, emsg->len); + if (ret < 0) + return ret; + + emsg->len -= ret; + emsg->offset += ret; + } while (emsg->len > 0); + + kfree_skb(emsg->skb); + memset(emsg, 0, sizeof(*emsg)); + + return 0; +} + +static int espintcp_sendskmsg_locked(struct sock *sk, + struct espintcp_msg *emsg, int flags) +{ + struct sk_msg *skmsg = &emsg->skmsg; + struct scatterlist *sg; + int done = 0; + int ret; + + flags |= MSG_SENDPAGE_NOTLAST; + sg = &skmsg->sg.data[skmsg->sg.start]; + do { + size_t size = sg->length - emsg->offset; + int offset = sg->offset + emsg->offset; + struct page *p; + + emsg->offset = 0; + + if (sg_is_last(sg)) + flags &= ~MSG_SENDPAGE_NOTLAST; + + p = sg_page(sg); +retry: + ret = do_tcp_sendpages(sk, p, offset, size, flags); + if (ret < 0) { + emsg->offset = offset - sg->offset; + skmsg->sg.start += done; + return ret; + } + + if (ret != size) { + offset += ret; + size -= ret; + goto retry; + } + + done++; + put_page(p); + sk_mem_uncharge(sk, sg->length); + sg = sg_next(sg); + } while (sg); + + memset(emsg, 0, sizeof(*emsg)); + + return 0; +} + +static int espintcp_push_msgs(struct sock *sk, int flags) +{ + struct espintcp_ctx *ctx = espintcp_getctx(sk); + struct espintcp_msg *emsg = &ctx->partial; + int err; + + if (!emsg->len) + return 0; + + if (ctx->tx_running) + return -EAGAIN; + ctx->tx_running = 1; + + if (emsg->skb) + err = espintcp_sendskb_locked(sk, emsg, flags); + else + err = espintcp_sendskmsg_locked(sk, emsg, flags); + if (err == -EAGAIN) { + ctx->tx_running = 0; + return flags & MSG_DONTWAIT ? -EAGAIN : 0; + } + if (!err) + memset(emsg, 0, sizeof(*emsg)); + + ctx->tx_running = 0; + + return err; +} + +int espintcp_push_skb(struct sock *sk, struct sk_buff *skb) +{ + struct espintcp_ctx *ctx = espintcp_getctx(sk); + struct espintcp_msg *emsg = &ctx->partial; + unsigned int len; + int offset; + + if (sk->sk_state != TCP_ESTABLISHED) { + kfree_skb(skb); + return -ECONNRESET; + } + + offset = skb_transport_offset(skb); + len = skb->len - offset; + + espintcp_push_msgs(sk, 0); + + if (emsg->len) { + kfree_skb(skb); + return -ENOBUFS; + } + + skb_set_owner_w(skb, sk); + + emsg->offset = offset; + emsg->len = len; + emsg->skb = skb; + + espintcp_push_msgs(sk, 0); + + return 0; +} +EXPORT_SYMBOL_GPL(espintcp_push_skb); + +static int espintcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) +{ + long timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); + struct espintcp_ctx *ctx = espintcp_getctx(sk); + struct espintcp_msg *emsg = &ctx->partial; + struct iov_iter pfx_iter; + struct kvec pfx_iov = {}; + size_t msglen = size + 2; + char buf[2] = {0}; + int err, end; + + if (msg->msg_flags & ~MSG_DONTWAIT) + return -EOPNOTSUPP; + + if (size > MAX_ESPINTCP_MSG) + return -EMSGSIZE; + + if (msg->msg_controllen) + return -EOPNOTSUPP; + + lock_sock(sk); + + err = espintcp_push_msgs(sk, msg->msg_flags & MSG_DONTWAIT); + if (err < 0) { + if (err != -EAGAIN || !(msg->msg_flags & MSG_DONTWAIT)) + err = -ENOBUFS; + goto unlock; + } + + sk_msg_init(&emsg->skmsg); + while (1) { + /* only -ENOMEM is possible since we don't coalesce */ + err = sk_msg_alloc(sk, &emsg->skmsg, msglen, 0); + if (!err) + break; + + err = sk_stream_wait_memory(sk, &timeo); + if (err) + goto fail; + } + + *((__be16 *)buf) = cpu_to_be16(msglen); + pfx_iov.iov_base = buf; + pfx_iov.iov_len = sizeof(buf); + iov_iter_kvec(&pfx_iter, ITER_SOURCE, &pfx_iov, 1, pfx_iov.iov_len); + + err = sk_msg_memcopy_from_iter(sk, &pfx_iter, &emsg->skmsg, + pfx_iov.iov_len); + if (err < 0) + goto fail; + + err = sk_msg_memcopy_from_iter(sk, &msg->msg_iter, &emsg->skmsg, size); + if (err < 0) + goto fail; + + end = emsg->skmsg.sg.end; + emsg->len = size; + sk_msg_iter_var_prev(end); + sg_mark_end(sk_msg_elem(&emsg->skmsg, end)); + + tcp_rate_check_app_limited(sk); + + err = espintcp_push_msgs(sk, msg->msg_flags & MSG_DONTWAIT); + /* this message could be partially sent, keep it */ + + release_sock(sk); + + return size; + +fail: + sk_msg_free(sk, &emsg->skmsg); + memset(emsg, 0, sizeof(*emsg)); +unlock: + release_sock(sk); + return err; +} + +static struct proto espintcp_prot __ro_after_init; +static struct proto_ops espintcp_ops __ro_after_init; +static struct proto espintcp6_prot; +static struct proto_ops espintcp6_ops; +static DEFINE_MUTEX(tcpv6_prot_mutex); + +static void espintcp_data_ready(struct sock *sk) +{ + struct espintcp_ctx *ctx = espintcp_getctx(sk); + + trace_sk_data_ready(sk); + + strp_data_ready(&ctx->strp); +} + +static void espintcp_tx_work(struct work_struct *work) +{ + struct espintcp_ctx *ctx = container_of(work, + struct espintcp_ctx, work); + struct sock *sk = ctx->strp.sk; + + lock_sock(sk); + if (!ctx->tx_running) + espintcp_push_msgs(sk, 0); + release_sock(sk); +} + +static void espintcp_write_space(struct sock *sk) +{ + struct espintcp_ctx *ctx = espintcp_getctx(sk); + + schedule_work(&ctx->work); + ctx->saved_write_space(sk); +} + +static void espintcp_destruct(struct sock *sk) +{ + struct espintcp_ctx *ctx = espintcp_getctx(sk); + + ctx->saved_destruct(sk); + kfree(ctx); +} + +bool tcp_is_ulp_esp(struct sock *sk) +{ + return sk->sk_prot == &espintcp_prot || sk->sk_prot == &espintcp6_prot; +} +EXPORT_SYMBOL_GPL(tcp_is_ulp_esp); + +static void build_protos(struct proto *espintcp_prot, + struct proto_ops *espintcp_ops, + const struct proto *orig_prot, + const struct proto_ops *orig_ops); +static int espintcp_init_sk(struct sock *sk) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + struct strp_callbacks cb = { + .rcv_msg = espintcp_rcv, + .parse_msg = espintcp_parse, + }; + struct espintcp_ctx *ctx; + int err; + + /* sockmap is not compatible with espintcp */ + if (sk->sk_user_data) + return -EBUSY; + + ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); + if (!ctx) + return -ENOMEM; + + err = strp_init(&ctx->strp, sk, &cb); + if (err) + goto free; + + __sk_dst_reset(sk); + + strp_check_rcv(&ctx->strp); + skb_queue_head_init(&ctx->ike_queue); + skb_queue_head_init(&ctx->out_queue); + + if (sk->sk_family == AF_INET) { + sk->sk_prot = &espintcp_prot; + sk->sk_socket->ops = &espintcp_ops; + } else { + mutex_lock(&tcpv6_prot_mutex); + if (!espintcp6_prot.recvmsg) + build_protos(&espintcp6_prot, &espintcp6_ops, sk->sk_prot, sk->sk_socket->ops); + mutex_unlock(&tcpv6_prot_mutex); + + sk->sk_prot = &espintcp6_prot; + sk->sk_socket->ops = &espintcp6_ops; + } + ctx->saved_data_ready = sk->sk_data_ready; + ctx->saved_write_space = sk->sk_write_space; + ctx->saved_destruct = sk->sk_destruct; + sk->sk_data_ready = espintcp_data_ready; + sk->sk_write_space = espintcp_write_space; + sk->sk_destruct = espintcp_destruct; + rcu_assign_pointer(icsk->icsk_ulp_data, ctx); + INIT_WORK(&ctx->work, espintcp_tx_work); + + /* avoid using task_frag */ + sk->sk_allocation = GFP_ATOMIC; + sk->sk_use_task_frag = false; + + return 0; + +free: + kfree(ctx); + return err; +} + +static void espintcp_release(struct sock *sk) +{ + struct espintcp_ctx *ctx = espintcp_getctx(sk); + struct sk_buff_head queue; + struct sk_buff *skb; + + __skb_queue_head_init(&queue); + skb_queue_splice_init(&ctx->out_queue, &queue); + + while ((skb = __skb_dequeue(&queue))) + espintcp_push_skb(sk, skb); + + tcp_release_cb(sk); +} + +static void espintcp_close(struct sock *sk, long timeout) +{ + struct espintcp_ctx *ctx = espintcp_getctx(sk); + struct espintcp_msg *emsg = &ctx->partial; + + strp_stop(&ctx->strp); + + sk->sk_prot = &tcp_prot; + barrier(); + + cancel_work_sync(&ctx->work); + strp_done(&ctx->strp); + + skb_queue_purge(&ctx->out_queue); + skb_queue_purge(&ctx->ike_queue); + + if (emsg->len) { + if (emsg->skb) + kfree_skb(emsg->skb); + else + sk_msg_free(sk, &emsg->skmsg); + } + + tcp_close(sk, timeout); +} + +static __poll_t espintcp_poll(struct file *file, struct socket *sock, + poll_table *wait) +{ + __poll_t mask = datagram_poll(file, sock, wait); + struct sock *sk = sock->sk; + struct espintcp_ctx *ctx = espintcp_getctx(sk); + + if (!skb_queue_empty(&ctx->ike_queue)) + mask |= EPOLLIN | EPOLLRDNORM; + + return mask; +} + +static void build_protos(struct proto *espintcp_prot, + struct proto_ops *espintcp_ops, + const struct proto *orig_prot, + const struct proto_ops *orig_ops) +{ + memcpy(espintcp_prot, orig_prot, sizeof(struct proto)); + memcpy(espintcp_ops, orig_ops, sizeof(struct proto_ops)); + espintcp_prot->sendmsg = espintcp_sendmsg; + espintcp_prot->recvmsg = espintcp_recvmsg; + espintcp_prot->close = espintcp_close; + espintcp_prot->release_cb = espintcp_release; + espintcp_ops->poll = espintcp_poll; +} + +static struct tcp_ulp_ops espintcp_ulp __read_mostly = { + .name = "espintcp", + .owner = THIS_MODULE, + .init = espintcp_init_sk, +}; + +void __init espintcp_init(void) +{ + build_protos(&espintcp_prot, &espintcp_ops, &tcp_prot, &inet_stream_ops); + + tcp_register_ulp(&espintcp_ulp); +} -- cgit v1.2.3