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/tipc/net.c | 345 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 345 insertions(+) create mode 100644 net/tipc/net.c (limited to 'net/tipc/net.c') diff --git a/net/tipc/net.c b/net/tipc/net.c new file mode 100644 index 000000000..0e95572e5 --- /dev/null +++ b/net/tipc/net.c @@ -0,0 +1,345 @@ +/* + * net/tipc/net.c: TIPC network routing code + * + * Copyright (c) 1995-2006, 2014, Ericsson AB + * Copyright (c) 2005, 2010-2011, Wind River Systems + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#include "core.h" +#include "net.h" +#include "name_distr.h" +#include "subscr.h" +#include "socket.h" +#include "node.h" +#include "bcast.h" +#include "link.h" +#include "netlink.h" +#include "monitor.h" + +/* + * The TIPC locking policy is designed to ensure a very fine locking + * granularity, permitting complete parallel access to individual + * port and node/link instances. The code consists of four major + * locking domains, each protected with their own disjunct set of locks. + * + * 1: The bearer level. + * RTNL lock is used to serialize the process of configuring bearer + * on update side, and RCU lock is applied on read side to make + * bearer instance valid on both paths of message transmission and + * reception. + * + * 2: The node and link level. + * All node instances are saved into two tipc_node_list and node_htable + * lists. The two lists are protected by node_list_lock on write side, + * and they are guarded with RCU lock on read side. Especially node + * instance is destroyed only when TIPC module is removed, and we can + * confirm that there has no any user who is accessing the node at the + * moment. Therefore, Except for iterating the two lists within RCU + * protection, it's no needed to hold RCU that we access node instance + * in other places. + * + * In addition, all members in node structure including link instances + * are protected by node spin lock. + * + * 3: The transport level of the protocol. + * This consists of the structures port, (and its user level + * representations, such as user_port and tipc_sock), reference and + * tipc_user (port.c, reg.c, socket.c). + * + * This layer has four different locks: + * - The tipc_port spin_lock. This is protecting each port instance + * from parallel data access and removal. Since we can not place + * this lock in the port itself, it has been placed in the + * corresponding reference table entry, which has the same life + * cycle as the module. This entry is difficult to access from + * outside the TIPC core, however, so a pointer to the lock has + * been added in the port instance, -to be used for unlocking + * only. + * - A read/write lock to protect the reference table itself (teg.c). + * (Nobody is using read-only access to this, so it can just as + * well be changed to a spin_lock) + * - A spin lock to protect the registry of kernel/driver users (reg.c) + * - A global spin_lock (tipc_port_lock), which only task is to ensure + * consistency where more than one port is involved in an operation, + * i.e., when a port is part of a linked list of ports. + * There are two such lists; 'port_list', which is used for management, + * and 'wait_list', which is used to queue ports during congestion. + * + * 4: The name table (name_table.c, name_distr.c, subscription.c) + * - There is one big read/write-lock (tipc_nametbl_lock) protecting the + * overall name table structure. Nothing must be added/removed to + * this structure without holding write access to it. + * - There is one local spin_lock per sub_sequence, which can be seen + * as a sub-domain to the tipc_nametbl_lock domain. It is used only + * for translation operations, and is needed because a translation + * steps the root of the 'publication' linked list between each lookup. + * This is always used within the scope of a tipc_nametbl_lock(read). + * - A local spin_lock protecting the queue of subscriber events. +*/ + +static void tipc_net_finalize(struct net *net, u32 addr); + +int tipc_net_init(struct net *net, u8 *node_id, u32 addr) +{ + if (tipc_own_id(net)) { + pr_info("Cannot configure node identity twice\n"); + return -1; + } + pr_info("Started in network mode\n"); + + if (node_id) + tipc_set_node_id(net, node_id); + if (addr) + tipc_net_finalize(net, addr); + return 0; +} + +static void tipc_net_finalize(struct net *net, u32 addr) +{ + struct tipc_net *tn = tipc_net(net); + struct tipc_socket_addr sk = {0, addr}; + struct tipc_uaddr ua; + + tipc_uaddr(&ua, TIPC_SERVICE_RANGE, TIPC_CLUSTER_SCOPE, + TIPC_NODE_STATE, addr, addr); + + if (cmpxchg(&tn->node_addr, 0, addr)) + return; + tipc_set_node_addr(net, addr); + tipc_named_reinit(net); + tipc_sk_reinit(net); + tipc_mon_reinit_self(net); + tipc_nametbl_publish(net, &ua, &sk, addr); +} + +void tipc_net_finalize_work(struct work_struct *work) +{ + struct tipc_net *tn = container_of(work, struct tipc_net, work); + + tipc_net_finalize(tipc_link_net(tn->bcl), tn->trial_addr); +} + +void tipc_net_stop(struct net *net) +{ + if (!tipc_own_id(net)) + return; + + rtnl_lock(); + tipc_bearer_stop(net); + tipc_node_stop(net); + rtnl_unlock(); + + pr_info("Left network mode\n"); +} + +static int __tipc_nl_add_net(struct net *net, struct tipc_nl_msg *msg) +{ + struct tipc_net *tn = net_generic(net, tipc_net_id); + u64 *w0 = (u64 *)&tn->node_id[0]; + u64 *w1 = (u64 *)&tn->node_id[8]; + struct nlattr *attrs; + void *hdr; + + hdr = genlmsg_put(msg->skb, msg->portid, msg->seq, &tipc_genl_family, + NLM_F_MULTI, TIPC_NL_NET_GET); + if (!hdr) + return -EMSGSIZE; + + attrs = nla_nest_start_noflag(msg->skb, TIPC_NLA_NET); + if (!attrs) + goto msg_full; + + if (nla_put_u32(msg->skb, TIPC_NLA_NET_ID, tn->net_id)) + goto attr_msg_full; + if (nla_put_u64_64bit(msg->skb, TIPC_NLA_NET_NODEID, *w0, 0)) + goto attr_msg_full; + if (nla_put_u64_64bit(msg->skb, TIPC_NLA_NET_NODEID_W1, *w1, 0)) + goto attr_msg_full; + nla_nest_end(msg->skb, attrs); + genlmsg_end(msg->skb, hdr); + + return 0; + +attr_msg_full: + nla_nest_cancel(msg->skb, attrs); +msg_full: + genlmsg_cancel(msg->skb, hdr); + + return -EMSGSIZE; +} + +int tipc_nl_net_dump(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct net *net = sock_net(skb->sk); + int err; + int done = cb->args[0]; + struct tipc_nl_msg msg; + + if (done) + return 0; + + msg.skb = skb; + msg.portid = NETLINK_CB(cb->skb).portid; + msg.seq = cb->nlh->nlmsg_seq; + + err = __tipc_nl_add_net(net, &msg); + if (err) + goto out; + + done = 1; +out: + cb->args[0] = done; + + return skb->len; +} + +int __tipc_nl_net_set(struct sk_buff *skb, struct genl_info *info) +{ + struct nlattr *attrs[TIPC_NLA_NET_MAX + 1]; + struct net *net = sock_net(skb->sk); + struct tipc_net *tn = tipc_net(net); + int err; + + if (!info->attrs[TIPC_NLA_NET]) + return -EINVAL; + + err = nla_parse_nested_deprecated(attrs, TIPC_NLA_NET_MAX, + info->attrs[TIPC_NLA_NET], + tipc_nl_net_policy, info->extack); + + if (err) + return err; + + /* Can't change net id once TIPC has joined a network */ + if (tipc_own_addr(net)) + return -EPERM; + + if (attrs[TIPC_NLA_NET_ID]) { + u32 val; + + val = nla_get_u32(attrs[TIPC_NLA_NET_ID]); + if (val < 1 || val > 9999) + return -EINVAL; + + tn->net_id = val; + } + + if (attrs[TIPC_NLA_NET_ADDR]) { + u32 addr; + + addr = nla_get_u32(attrs[TIPC_NLA_NET_ADDR]); + if (!addr) + return -EINVAL; + tn->legacy_addr_format = true; + tipc_net_init(net, NULL, addr); + } + + if (attrs[TIPC_NLA_NET_NODEID]) { + u8 node_id[NODE_ID_LEN]; + u64 *w0 = (u64 *)&node_id[0]; + u64 *w1 = (u64 *)&node_id[8]; + + if (!attrs[TIPC_NLA_NET_NODEID_W1]) + return -EINVAL; + *w0 = nla_get_u64(attrs[TIPC_NLA_NET_NODEID]); + *w1 = nla_get_u64(attrs[TIPC_NLA_NET_NODEID_W1]); + tipc_net_init(net, node_id, 0); + } + return 0; +} + +int tipc_nl_net_set(struct sk_buff *skb, struct genl_info *info) +{ + int err; + + rtnl_lock(); + err = __tipc_nl_net_set(skb, info); + rtnl_unlock(); + + return err; +} + +static int __tipc_nl_addr_legacy_get(struct net *net, struct tipc_nl_msg *msg) +{ + struct tipc_net *tn = tipc_net(net); + struct nlattr *attrs; + void *hdr; + + hdr = genlmsg_put(msg->skb, msg->portid, msg->seq, &tipc_genl_family, + 0, TIPC_NL_ADDR_LEGACY_GET); + if (!hdr) + return -EMSGSIZE; + + attrs = nla_nest_start(msg->skb, TIPC_NLA_NET); + if (!attrs) + goto msg_full; + + if (tn->legacy_addr_format) + if (nla_put_flag(msg->skb, TIPC_NLA_NET_ADDR_LEGACY)) + goto attr_msg_full; + + nla_nest_end(msg->skb, attrs); + genlmsg_end(msg->skb, hdr); + + return 0; + +attr_msg_full: + nla_nest_cancel(msg->skb, attrs); +msg_full: + genlmsg_cancel(msg->skb, hdr); + + return -EMSGSIZE; +} + +int tipc_nl_net_addr_legacy_get(struct sk_buff *skb, struct genl_info *info) +{ + struct net *net = sock_net(skb->sk); + struct tipc_nl_msg msg; + struct sk_buff *rep; + int err; + + rep = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); + if (!rep) + return -ENOMEM; + + msg.skb = rep; + msg.portid = info->snd_portid; + msg.seq = info->snd_seq; + + err = __tipc_nl_addr_legacy_get(net, &msg); + if (err) { + nlmsg_free(msg.skb); + return err; + } + + return genlmsg_reply(msg.skb, info); +} -- cgit v1.2.3