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(). ... --- drivers/infiniband/core/netlink.c | 331 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 331 insertions(+) create mode 100644 drivers/infiniband/core/netlink.c (limited to 'drivers/infiniband/core/netlink.c') diff --git a/drivers/infiniband/core/netlink.c b/drivers/infiniband/core/netlink.c new file mode 100644 index 000000000..1b2cc9e45 --- /dev/null +++ b/drivers/infiniband/core/netlink.c @@ -0,0 +1,331 @@ +/* + * Copyright (c) 2017 Mellanox Technologies Inc. All rights reserved. + * Copyright (c) 2010 Voltaire Inc. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - 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. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#define pr_fmt(fmt) "%s:%s: " fmt, KBUILD_MODNAME, __func__ + +#include +#include +#include +#include +#include +#include +#include +#include "core_priv.h" + +static struct { + const struct rdma_nl_cbs *cb_table; + /* Synchronizes between ongoing netlink commands and netlink client + * unregistration. + */ + struct rw_semaphore sem; +} rdma_nl_types[RDMA_NL_NUM_CLIENTS]; + +bool rdma_nl_chk_listeners(unsigned int group) +{ + struct rdma_dev_net *rnet = rdma_net_to_dev_net(&init_net); + + return netlink_has_listeners(rnet->nl_sock, group); +} +EXPORT_SYMBOL(rdma_nl_chk_listeners); + +static bool is_nl_msg_valid(unsigned int type, unsigned int op) +{ + static const unsigned int max_num_ops[RDMA_NL_NUM_CLIENTS] = { + [RDMA_NL_IWCM] = RDMA_NL_IWPM_NUM_OPS, + [RDMA_NL_LS] = RDMA_NL_LS_NUM_OPS, + [RDMA_NL_NLDEV] = RDMA_NLDEV_NUM_OPS, + }; + + /* + * This BUILD_BUG_ON is intended to catch addition of new + * RDMA netlink protocol without updating the array above. + */ + BUILD_BUG_ON(RDMA_NL_NUM_CLIENTS != 6); + + if (type >= RDMA_NL_NUM_CLIENTS) + return false; + + return (op < max_num_ops[type]) ? true : false; +} + +static const struct rdma_nl_cbs * +get_cb_table(const struct sk_buff *skb, unsigned int type, unsigned int op) +{ + const struct rdma_nl_cbs *cb_table; + + /* + * Currently only NLDEV client is supporting netlink commands in + * non init_net net namespace. + */ + if (sock_net(skb->sk) != &init_net && type != RDMA_NL_NLDEV) + return NULL; + + cb_table = READ_ONCE(rdma_nl_types[type].cb_table); + if (!cb_table) { + /* + * Didn't get valid reference of the table, attempt module + * load once. + */ + up_read(&rdma_nl_types[type].sem); + + request_module("rdma-netlink-subsys-%u", type); + + down_read(&rdma_nl_types[type].sem); + cb_table = READ_ONCE(rdma_nl_types[type].cb_table); + } + if (!cb_table || (!cb_table[op].dump && !cb_table[op].doit)) + return NULL; + return cb_table; +} + +void rdma_nl_register(unsigned int index, + const struct rdma_nl_cbs cb_table[]) +{ + if (WARN_ON(!is_nl_msg_valid(index, 0)) || + WARN_ON(READ_ONCE(rdma_nl_types[index].cb_table))) + return; + + /* Pairs with the READ_ONCE in is_nl_valid() */ + smp_store_release(&rdma_nl_types[index].cb_table, cb_table); +} +EXPORT_SYMBOL(rdma_nl_register); + +void rdma_nl_unregister(unsigned int index) +{ + down_write(&rdma_nl_types[index].sem); + rdma_nl_types[index].cb_table = NULL; + up_write(&rdma_nl_types[index].sem); +} +EXPORT_SYMBOL(rdma_nl_unregister); + +void *ibnl_put_msg(struct sk_buff *skb, struct nlmsghdr **nlh, int seq, + int len, int client, int op, int flags) +{ + *nlh = nlmsg_put(skb, 0, seq, RDMA_NL_GET_TYPE(client, op), len, flags); + if (!*nlh) + return NULL; + return nlmsg_data(*nlh); +} +EXPORT_SYMBOL(ibnl_put_msg); + +int ibnl_put_attr(struct sk_buff *skb, struct nlmsghdr *nlh, + int len, void *data, int type) +{ + if (nla_put(skb, type, len, data)) { + nlmsg_cancel(skb, nlh); + return -EMSGSIZE; + } + return 0; +} +EXPORT_SYMBOL(ibnl_put_attr); + +static int rdma_nl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, + struct netlink_ext_ack *extack) +{ + int type = nlh->nlmsg_type; + unsigned int index = RDMA_NL_GET_CLIENT(type); + unsigned int op = RDMA_NL_GET_OP(type); + const struct rdma_nl_cbs *cb_table; + int err = -EINVAL; + + if (!is_nl_msg_valid(index, op)) + return -EINVAL; + + down_read(&rdma_nl_types[index].sem); + cb_table = get_cb_table(skb, index, op); + if (!cb_table) + goto done; + + if ((cb_table[op].flags & RDMA_NL_ADMIN_PERM) && + !netlink_capable(skb, CAP_NET_ADMIN)) { + err = -EPERM; + goto done; + } + + /* + * LS responses overload the 0x100 (NLM_F_ROOT) flag. Don't + * mistakenly call the .dump() function. + */ + if (index == RDMA_NL_LS) { + if (cb_table[op].doit) + err = cb_table[op].doit(skb, nlh, extack); + goto done; + } + /* FIXME: Convert IWCM to properly handle doit callbacks */ + if ((nlh->nlmsg_flags & NLM_F_DUMP) || index == RDMA_NL_IWCM) { + struct netlink_dump_control c = { + .dump = cb_table[op].dump, + }; + if (c.dump) + err = netlink_dump_start(skb->sk, skb, nlh, &c); + goto done; + } + + if (cb_table[op].doit) + err = cb_table[op].doit(skb, nlh, extack); +done: + up_read(&rdma_nl_types[index].sem); + return err; +} + +/* + * This function is similar to netlink_rcv_skb with one exception: + * It calls to the callback for the netlink messages without NLM_F_REQUEST + * flag. These messages are intended for RDMA_NL_LS consumer, so it is allowed + * for that consumer only. + */ +static int rdma_nl_rcv_skb(struct sk_buff *skb, int (*cb)(struct sk_buff *, + struct nlmsghdr *, + struct netlink_ext_ack *)) +{ + struct netlink_ext_ack extack = {}; + struct nlmsghdr *nlh; + int err; + + while (skb->len >= nlmsg_total_size(0)) { + int msglen; + + nlh = nlmsg_hdr(skb); + err = 0; + + if (nlh->nlmsg_len < NLMSG_HDRLEN || skb->len < nlh->nlmsg_len) + return 0; + + /* + * Generally speaking, the only requests are handled + * by the kernel, but RDMA_NL_LS is different, because it + * runs backward netlink scheme. Kernel initiates messages + * and waits for reply with data to keep pathrecord cache + * in sync. + */ + if (!(nlh->nlmsg_flags & NLM_F_REQUEST) && + (RDMA_NL_GET_CLIENT(nlh->nlmsg_type) != RDMA_NL_LS)) + goto ack; + + /* Skip control messages */ + if (nlh->nlmsg_type < NLMSG_MIN_TYPE) + goto ack; + + err = cb(skb, nlh, &extack); + if (err == -EINTR) + goto skip; + +ack: + if (nlh->nlmsg_flags & NLM_F_ACK || err) + netlink_ack(skb, nlh, err, &extack); + +skip: + msglen = NLMSG_ALIGN(nlh->nlmsg_len); + if (msglen > skb->len) + msglen = skb->len; + skb_pull(skb, msglen); + } + + return 0; +} + +static void rdma_nl_rcv(struct sk_buff *skb) +{ + rdma_nl_rcv_skb(skb, &rdma_nl_rcv_msg); +} + +int rdma_nl_unicast(struct net *net, struct sk_buff *skb, u32 pid) +{ + struct rdma_dev_net *rnet = rdma_net_to_dev_net(net); + int err; + + err = netlink_unicast(rnet->nl_sock, skb, pid, MSG_DONTWAIT); + return (err < 0) ? err : 0; +} +EXPORT_SYMBOL(rdma_nl_unicast); + +int rdma_nl_unicast_wait(struct net *net, struct sk_buff *skb, __u32 pid) +{ + struct rdma_dev_net *rnet = rdma_net_to_dev_net(net); + int err; + + err = netlink_unicast(rnet->nl_sock, skb, pid, 0); + return (err < 0) ? err : 0; +} +EXPORT_SYMBOL(rdma_nl_unicast_wait); + +int rdma_nl_multicast(struct net *net, struct sk_buff *skb, + unsigned int group, gfp_t flags) +{ + struct rdma_dev_net *rnet = rdma_net_to_dev_net(net); + + return nlmsg_multicast(rnet->nl_sock, skb, 0, group, flags); +} +EXPORT_SYMBOL(rdma_nl_multicast); + +void rdma_nl_init(void) +{ + int idx; + + for (idx = 0; idx < RDMA_NL_NUM_CLIENTS; idx++) + init_rwsem(&rdma_nl_types[idx].sem); +} + +void rdma_nl_exit(void) +{ + int idx; + + for (idx = 0; idx < RDMA_NL_NUM_CLIENTS; idx++) + WARN(rdma_nl_types[idx].cb_table, + "Netlink client %d wasn't released prior to unloading %s\n", + idx, KBUILD_MODNAME); +} + +int rdma_nl_net_init(struct rdma_dev_net *rnet) +{ + struct net *net = read_pnet(&rnet->net); + struct netlink_kernel_cfg cfg = { + .input = rdma_nl_rcv, + }; + struct sock *nls; + + nls = netlink_kernel_create(net, NETLINK_RDMA, &cfg); + if (!nls) + return -ENOMEM; + + nls->sk_sndtimeo = 10 * HZ; + rnet->nl_sock = nls; + return 0; +} + +void rdma_nl_net_exit(struct rdma_dev_net *rnet) +{ + netlink_kernel_release(rnet->nl_sock); +} + +MODULE_ALIAS_NET_PF_PROTO(PF_NETLINK, NETLINK_RDMA); -- cgit v1.2.3