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/name_distr.c | 411 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 411 insertions(+) create mode 100644 net/tipc/name_distr.c (limited to 'net/tipc/name_distr.c') diff --git a/net/tipc/name_distr.c b/net/tipc/name_distr.c new file mode 100644 index 000000000..190b49c5c --- /dev/null +++ b/net/tipc/name_distr.c @@ -0,0 +1,411 @@ +/* + * net/tipc/name_distr.c: TIPC name distribution code + * + * Copyright (c) 2000-2006, 2014-2019, Ericsson AB + * Copyright (c) 2005, 2010-2011, Wind River Systems + * Copyright (c) 2020-2021, Red Hat Inc + * 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 "link.h" +#include "name_distr.h" + +int sysctl_tipc_named_timeout __read_mostly = 2000; + +/** + * publ_to_item - add publication info to a publication message + * @p: publication info + * @i: location of item in the message + */ +static void publ_to_item(struct distr_item *i, struct publication *p) +{ + i->type = htonl(p->sr.type); + i->lower = htonl(p->sr.lower); + i->upper = htonl(p->sr.upper); + i->port = htonl(p->sk.ref); + i->key = htonl(p->key); +} + +/** + * named_prepare_buf - allocate & initialize a publication message + * @net: the associated network namespace + * @type: message type + * @size: payload size + * @dest: destination node + * + * The buffer returned is of size INT_H_SIZE + payload size + */ +static struct sk_buff *named_prepare_buf(struct net *net, u32 type, u32 size, + u32 dest) +{ + struct sk_buff *buf = tipc_buf_acquire(INT_H_SIZE + size, GFP_ATOMIC); + u32 self = tipc_own_addr(net); + struct tipc_msg *msg; + + if (buf != NULL) { + msg = buf_msg(buf); + tipc_msg_init(self, msg, NAME_DISTRIBUTOR, + type, INT_H_SIZE, dest); + msg_set_size(msg, INT_H_SIZE + size); + } + return buf; +} + +/** + * tipc_named_publish - tell other nodes about a new publication by this node + * @net: the associated network namespace + * @p: the new publication + */ +struct sk_buff *tipc_named_publish(struct net *net, struct publication *p) +{ + struct name_table *nt = tipc_name_table(net); + struct distr_item *item; + struct sk_buff *skb; + + if (p->scope == TIPC_NODE_SCOPE) { + list_add_tail_rcu(&p->binding_node, &nt->node_scope); + return NULL; + } + write_lock_bh(&nt->cluster_scope_lock); + list_add_tail(&p->binding_node, &nt->cluster_scope); + write_unlock_bh(&nt->cluster_scope_lock); + skb = named_prepare_buf(net, PUBLICATION, ITEM_SIZE, 0); + if (!skb) { + pr_warn("Publication distribution failure\n"); + return NULL; + } + msg_set_named_seqno(buf_msg(skb), nt->snd_nxt++); + msg_set_non_legacy(buf_msg(skb)); + item = (struct distr_item *)msg_data(buf_msg(skb)); + publ_to_item(item, p); + return skb; +} + +/** + * tipc_named_withdraw - tell other nodes about a withdrawn publication by this node + * @net: the associated network namespace + * @p: the withdrawn publication + */ +struct sk_buff *tipc_named_withdraw(struct net *net, struct publication *p) +{ + struct name_table *nt = tipc_name_table(net); + struct distr_item *item; + struct sk_buff *skb; + + write_lock_bh(&nt->cluster_scope_lock); + list_del(&p->binding_node); + write_unlock_bh(&nt->cluster_scope_lock); + if (p->scope == TIPC_NODE_SCOPE) + return NULL; + + skb = named_prepare_buf(net, WITHDRAWAL, ITEM_SIZE, 0); + if (!skb) { + pr_warn("Withdrawal distribution failure\n"); + return NULL; + } + msg_set_named_seqno(buf_msg(skb), nt->snd_nxt++); + msg_set_non_legacy(buf_msg(skb)); + item = (struct distr_item *)msg_data(buf_msg(skb)); + publ_to_item(item, p); + return skb; +} + +/** + * named_distribute - prepare name info for bulk distribution to another node + * @net: the associated network namespace + * @list: list of messages (buffers) to be returned from this function + * @dnode: node to be updated + * @pls: linked list of publication items to be packed into buffer chain + * @seqno: sequence number for this message + */ +static void named_distribute(struct net *net, struct sk_buff_head *list, + u32 dnode, struct list_head *pls, u16 seqno) +{ + struct publication *publ; + struct sk_buff *skb = NULL; + struct distr_item *item = NULL; + u32 msg_dsz = ((tipc_node_get_mtu(net, dnode, 0, false) - INT_H_SIZE) / + ITEM_SIZE) * ITEM_SIZE; + u32 msg_rem = msg_dsz; + struct tipc_msg *hdr; + + list_for_each_entry(publ, pls, binding_node) { + /* Prepare next buffer: */ + if (!skb) { + skb = named_prepare_buf(net, PUBLICATION, msg_rem, + dnode); + if (!skb) { + pr_warn("Bulk publication failure\n"); + return; + } + hdr = buf_msg(skb); + msg_set_bc_ack_invalid(hdr, true); + msg_set_bulk(hdr); + msg_set_non_legacy(hdr); + item = (struct distr_item *)msg_data(hdr); + } + + /* Pack publication into message: */ + publ_to_item(item, publ); + item++; + msg_rem -= ITEM_SIZE; + + /* Append full buffer to list: */ + if (!msg_rem) { + __skb_queue_tail(list, skb); + skb = NULL; + msg_rem = msg_dsz; + } + } + if (skb) { + hdr = buf_msg(skb); + msg_set_size(hdr, INT_H_SIZE + (msg_dsz - msg_rem)); + skb_trim(skb, INT_H_SIZE + (msg_dsz - msg_rem)); + __skb_queue_tail(list, skb); + } + hdr = buf_msg(skb_peek_tail(list)); + msg_set_last_bulk(hdr); + msg_set_named_seqno(hdr, seqno); +} + +/** + * tipc_named_node_up - tell specified node about all publications by this node + * @net: the associated network namespace + * @dnode: destination node + * @capabilities: peer node's capabilities + */ +void tipc_named_node_up(struct net *net, u32 dnode, u16 capabilities) +{ + struct name_table *nt = tipc_name_table(net); + struct tipc_net *tn = tipc_net(net); + struct sk_buff_head head; + u16 seqno; + + __skb_queue_head_init(&head); + spin_lock_bh(&tn->nametbl_lock); + if (!(capabilities & TIPC_NAMED_BCAST)) + nt->rc_dests++; + seqno = nt->snd_nxt; + spin_unlock_bh(&tn->nametbl_lock); + + read_lock_bh(&nt->cluster_scope_lock); + named_distribute(net, &head, dnode, &nt->cluster_scope, seqno); + tipc_node_xmit(net, &head, dnode, 0); + read_unlock_bh(&nt->cluster_scope_lock); +} + +/** + * tipc_publ_purge - remove publication associated with a failed node + * @net: the associated network namespace + * @p: the publication to remove + * @addr: failed node's address + * + * Invoked for each publication issued by a newly failed node. + * Removes publication structure from name table & deletes it. + */ +static void tipc_publ_purge(struct net *net, struct publication *p, u32 addr) +{ + struct tipc_net *tn = tipc_net(net); + struct publication *_p; + struct tipc_uaddr ua; + + tipc_uaddr(&ua, TIPC_SERVICE_RANGE, p->scope, p->sr.type, + p->sr.lower, p->sr.upper); + spin_lock_bh(&tn->nametbl_lock); + _p = tipc_nametbl_remove_publ(net, &ua, &p->sk, p->key); + if (_p) + tipc_node_unsubscribe(net, &_p->binding_node, addr); + spin_unlock_bh(&tn->nametbl_lock); + if (_p) + kfree_rcu(_p, rcu); +} + +void tipc_publ_notify(struct net *net, struct list_head *nsub_list, + u32 addr, u16 capabilities) +{ + struct name_table *nt = tipc_name_table(net); + struct tipc_net *tn = tipc_net(net); + + struct publication *publ, *tmp; + + list_for_each_entry_safe(publ, tmp, nsub_list, binding_node) + tipc_publ_purge(net, publ, addr); + spin_lock_bh(&tn->nametbl_lock); + if (!(capabilities & TIPC_NAMED_BCAST)) + nt->rc_dests--; + spin_unlock_bh(&tn->nametbl_lock); +} + +/** + * tipc_update_nametbl - try to process a nametable update and notify + * subscribers + * @net: the associated network namespace + * @i: location of item in the message + * @node: node address + * @dtype: name distributor message type + * + * tipc_nametbl_lock must be held. + * Return: the publication item if successful, otherwise NULL. + */ +static bool tipc_update_nametbl(struct net *net, struct distr_item *i, + u32 node, u32 dtype) +{ + struct publication *p = NULL; + struct tipc_socket_addr sk; + struct tipc_uaddr ua; + u32 key = ntohl(i->key); + + tipc_uaddr(&ua, TIPC_SERVICE_RANGE, TIPC_CLUSTER_SCOPE, + ntohl(i->type), ntohl(i->lower), ntohl(i->upper)); + sk.ref = ntohl(i->port); + sk.node = node; + + if (dtype == PUBLICATION) { + p = tipc_nametbl_insert_publ(net, &ua, &sk, key); + if (p) { + tipc_node_subscribe(net, &p->binding_node, node); + return true; + } + } else if (dtype == WITHDRAWAL) { + p = tipc_nametbl_remove_publ(net, &ua, &sk, key); + if (p) { + tipc_node_unsubscribe(net, &p->binding_node, node); + kfree_rcu(p, rcu); + return true; + } + pr_warn_ratelimited("Failed to remove binding %u,%u from %u\n", + ua.sr.type, ua.sr.lower, node); + } else { + pr_warn_ratelimited("Unknown name table message received\n"); + } + return false; +} + +static struct sk_buff *tipc_named_dequeue(struct sk_buff_head *namedq, + u16 *rcv_nxt, bool *open) +{ + struct sk_buff *skb, *tmp; + struct tipc_msg *hdr; + u16 seqno; + + spin_lock_bh(&namedq->lock); + skb_queue_walk_safe(namedq, skb, tmp) { + if (unlikely(skb_linearize(skb))) { + __skb_unlink(skb, namedq); + kfree_skb(skb); + continue; + } + hdr = buf_msg(skb); + seqno = msg_named_seqno(hdr); + if (msg_is_last_bulk(hdr)) { + *rcv_nxt = seqno; + *open = true; + } + + if (msg_is_bulk(hdr) || msg_is_legacy(hdr)) { + __skb_unlink(skb, namedq); + spin_unlock_bh(&namedq->lock); + return skb; + } + + if (*open && (*rcv_nxt == seqno)) { + (*rcv_nxt)++; + __skb_unlink(skb, namedq); + spin_unlock_bh(&namedq->lock); + return skb; + } + + if (less(seqno, *rcv_nxt)) { + __skb_unlink(skb, namedq); + kfree_skb(skb); + continue; + } + } + spin_unlock_bh(&namedq->lock); + return NULL; +} + +/** + * tipc_named_rcv - process name table update messages sent by another node + * @net: the associated network namespace + * @namedq: queue to receive from + * @rcv_nxt: store last received seqno here + * @open: last bulk msg was received (FIXME) + */ +void tipc_named_rcv(struct net *net, struct sk_buff_head *namedq, + u16 *rcv_nxt, bool *open) +{ + struct tipc_net *tn = tipc_net(net); + struct distr_item *item; + struct tipc_msg *hdr; + struct sk_buff *skb; + u32 count, node; + + spin_lock_bh(&tn->nametbl_lock); + while ((skb = tipc_named_dequeue(namedq, rcv_nxt, open))) { + hdr = buf_msg(skb); + node = msg_orignode(hdr); + item = (struct distr_item *)msg_data(hdr); + count = msg_data_sz(hdr) / ITEM_SIZE; + while (count--) { + tipc_update_nametbl(net, item, node, msg_type(hdr)); + item++; + } + kfree_skb(skb); + } + spin_unlock_bh(&tn->nametbl_lock); +} + +/** + * tipc_named_reinit - re-initialize local publications + * @net: the associated network namespace + * + * This routine is called whenever TIPC networking is enabled. + * All name table entries published by this node are updated to reflect + * the node's new network address. + */ +void tipc_named_reinit(struct net *net) +{ + struct name_table *nt = tipc_name_table(net); + struct tipc_net *tn = tipc_net(net); + struct publication *p; + u32 self = tipc_own_addr(net); + + spin_lock_bh(&tn->nametbl_lock); + + list_for_each_entry_rcu(p, &nt->node_scope, binding_node) + p->sk.node = self; + list_for_each_entry_rcu(p, &nt->cluster_scope, binding_node) + p->sk.node = self; + nt->rc_dests = 0; + spin_unlock_bh(&tn->nametbl_lock); +} -- cgit v1.2.3