aboutsummaryrefslogtreecommitdiff
path: root/net/phonet/pn_netlink.c
diff options
context:
space:
mode:
authorLibravatar Linus Torvalds <torvalds@linux-foundation.org>2023-02-21 18:24:12 -0800
committerLibravatar Linus Torvalds <torvalds@linux-foundation.org>2023-02-21 18:24:12 -0800
commit5b7c4cabbb65f5c469464da6c5f614cbd7f730f2 (patch)
treecc5c2d0a898769fd59549594fedb3ee6f84e59a0 /net/phonet/pn_netlink.c
downloadlinux-5b7c4cabbb65f5c469464da6c5f614cbd7f730f2.tar.gz
linux-5b7c4cabbb65f5c469464da6c5f614cbd7f730f2.zip
Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-nextgrafted
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(). ...
Diffstat (limited to '')
-rw-r--r--net/phonet/pn_netlink.c306
1 files changed, 306 insertions, 0 deletions
diff --git a/net/phonet/pn_netlink.c b/net/phonet/pn_netlink.c
new file mode 100644
index 000000000..59aebe296
--- /dev/null
+++ b/net/phonet/pn_netlink.c
@@ -0,0 +1,306 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * File: pn_netlink.c
+ *
+ * Phonet netlink interface
+ *
+ * Copyright (C) 2008 Nokia Corporation.
+ *
+ * Authors: Sakari Ailus <sakari.ailus@nokia.com>
+ * Remi Denis-Courmont
+ */
+
+#include <linux/kernel.h>
+#include <linux/netlink.h>
+#include <linux/phonet.h>
+#include <linux/slab.h>
+#include <net/sock.h>
+#include <net/phonet/pn_dev.h>
+
+/* Device address handling */
+
+static int fill_addr(struct sk_buff *skb, struct net_device *dev, u8 addr,
+ u32 portid, u32 seq, int event);
+
+void phonet_address_notify(int event, struct net_device *dev, u8 addr)
+{
+ struct sk_buff *skb;
+ int err = -ENOBUFS;
+
+ skb = nlmsg_new(NLMSG_ALIGN(sizeof(struct ifaddrmsg)) +
+ nla_total_size(1), GFP_KERNEL);
+ if (skb == NULL)
+ goto errout;
+ err = fill_addr(skb, dev, addr, 0, 0, event);
+ if (err < 0) {
+ WARN_ON(err == -EMSGSIZE);
+ kfree_skb(skb);
+ goto errout;
+ }
+ rtnl_notify(skb, dev_net(dev), 0,
+ RTNLGRP_PHONET_IFADDR, NULL, GFP_KERNEL);
+ return;
+errout:
+ rtnl_set_sk_err(dev_net(dev), RTNLGRP_PHONET_IFADDR, err);
+}
+
+static const struct nla_policy ifa_phonet_policy[IFA_MAX+1] = {
+ [IFA_LOCAL] = { .type = NLA_U8 },
+};
+
+static int addr_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
+ struct netlink_ext_ack *extack)
+{
+ struct net *net = sock_net(skb->sk);
+ struct nlattr *tb[IFA_MAX+1];
+ struct net_device *dev;
+ struct ifaddrmsg *ifm;
+ int err;
+ u8 pnaddr;
+
+ if (!netlink_capable(skb, CAP_NET_ADMIN))
+ return -EPERM;
+
+ if (!netlink_capable(skb, CAP_SYS_ADMIN))
+ return -EPERM;
+
+ ASSERT_RTNL();
+
+ err = nlmsg_parse_deprecated(nlh, sizeof(*ifm), tb, IFA_MAX,
+ ifa_phonet_policy, extack);
+ if (err < 0)
+ return err;
+
+ ifm = nlmsg_data(nlh);
+ if (tb[IFA_LOCAL] == NULL)
+ return -EINVAL;
+ pnaddr = nla_get_u8(tb[IFA_LOCAL]);
+ if (pnaddr & 3)
+ /* Phonet addresses only have 6 high-order bits */
+ return -EINVAL;
+
+ dev = __dev_get_by_index(net, ifm->ifa_index);
+ if (dev == NULL)
+ return -ENODEV;
+
+ if (nlh->nlmsg_type == RTM_NEWADDR)
+ err = phonet_address_add(dev, pnaddr);
+ else
+ err = phonet_address_del(dev, pnaddr);
+ if (!err)
+ phonet_address_notify(nlh->nlmsg_type, dev, pnaddr);
+ return err;
+}
+
+static int fill_addr(struct sk_buff *skb, struct net_device *dev, u8 addr,
+ u32 portid, u32 seq, int event)
+{
+ struct ifaddrmsg *ifm;
+ struct nlmsghdr *nlh;
+
+ nlh = nlmsg_put(skb, portid, seq, event, sizeof(*ifm), 0);
+ if (nlh == NULL)
+ return -EMSGSIZE;
+
+ ifm = nlmsg_data(nlh);
+ ifm->ifa_family = AF_PHONET;
+ ifm->ifa_prefixlen = 0;
+ ifm->ifa_flags = IFA_F_PERMANENT;
+ ifm->ifa_scope = RT_SCOPE_LINK;
+ ifm->ifa_index = dev->ifindex;
+ if (nla_put_u8(skb, IFA_LOCAL, addr))
+ goto nla_put_failure;
+ nlmsg_end(skb, nlh);
+ return 0;
+
+nla_put_failure:
+ nlmsg_cancel(skb, nlh);
+ return -EMSGSIZE;
+}
+
+static int getaddr_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
+{
+ struct phonet_device_list *pndevs;
+ struct phonet_device *pnd;
+ int dev_idx = 0, dev_start_idx = cb->args[0];
+ int addr_idx = 0, addr_start_idx = cb->args[1];
+
+ pndevs = phonet_device_list(sock_net(skb->sk));
+ rcu_read_lock();
+ list_for_each_entry_rcu(pnd, &pndevs->list, list) {
+ u8 addr;
+
+ if (dev_idx > dev_start_idx)
+ addr_start_idx = 0;
+ if (dev_idx++ < dev_start_idx)
+ continue;
+
+ addr_idx = 0;
+ for_each_set_bit(addr, pnd->addrs, 64) {
+ if (addr_idx++ < addr_start_idx)
+ continue;
+
+ if (fill_addr(skb, pnd->netdev, addr << 2,
+ NETLINK_CB(cb->skb).portid,
+ cb->nlh->nlmsg_seq, RTM_NEWADDR) < 0)
+ goto out;
+ }
+ }
+
+out:
+ rcu_read_unlock();
+ cb->args[0] = dev_idx;
+ cb->args[1] = addr_idx;
+
+ return skb->len;
+}
+
+/* Routes handling */
+
+static int fill_route(struct sk_buff *skb, struct net_device *dev, u8 dst,
+ u32 portid, u32 seq, int event)
+{
+ struct rtmsg *rtm;
+ struct nlmsghdr *nlh;
+
+ nlh = nlmsg_put(skb, portid, seq, event, sizeof(*rtm), 0);
+ if (nlh == NULL)
+ return -EMSGSIZE;
+
+ rtm = nlmsg_data(nlh);
+ rtm->rtm_family = AF_PHONET;
+ rtm->rtm_dst_len = 6;
+ rtm->rtm_src_len = 0;
+ rtm->rtm_tos = 0;
+ rtm->rtm_table = RT_TABLE_MAIN;
+ rtm->rtm_protocol = RTPROT_STATIC;
+ rtm->rtm_scope = RT_SCOPE_UNIVERSE;
+ rtm->rtm_type = RTN_UNICAST;
+ rtm->rtm_flags = 0;
+ if (nla_put_u8(skb, RTA_DST, dst) ||
+ nla_put_u32(skb, RTA_OIF, dev->ifindex))
+ goto nla_put_failure;
+ nlmsg_end(skb, nlh);
+ return 0;
+
+nla_put_failure:
+ nlmsg_cancel(skb, nlh);
+ return -EMSGSIZE;
+}
+
+void rtm_phonet_notify(int event, struct net_device *dev, u8 dst)
+{
+ struct sk_buff *skb;
+ int err = -ENOBUFS;
+
+ skb = nlmsg_new(NLMSG_ALIGN(sizeof(struct ifaddrmsg)) +
+ nla_total_size(1) + nla_total_size(4), GFP_KERNEL);
+ if (skb == NULL)
+ goto errout;
+ err = fill_route(skb, dev, dst, 0, 0, event);
+ if (err < 0) {
+ WARN_ON(err == -EMSGSIZE);
+ kfree_skb(skb);
+ goto errout;
+ }
+ rtnl_notify(skb, dev_net(dev), 0,
+ RTNLGRP_PHONET_ROUTE, NULL, GFP_KERNEL);
+ return;
+errout:
+ rtnl_set_sk_err(dev_net(dev), RTNLGRP_PHONET_ROUTE, err);
+}
+
+static const struct nla_policy rtm_phonet_policy[RTA_MAX+1] = {
+ [RTA_DST] = { .type = NLA_U8 },
+ [RTA_OIF] = { .type = NLA_U32 },
+};
+
+static int route_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
+ struct netlink_ext_ack *extack)
+{
+ struct net *net = sock_net(skb->sk);
+ struct nlattr *tb[RTA_MAX+1];
+ struct net_device *dev;
+ struct rtmsg *rtm;
+ int err;
+ u8 dst;
+
+ if (!netlink_capable(skb, CAP_NET_ADMIN))
+ return -EPERM;
+
+ if (!netlink_capable(skb, CAP_SYS_ADMIN))
+ return -EPERM;
+
+ ASSERT_RTNL();
+
+ err = nlmsg_parse_deprecated(nlh, sizeof(*rtm), tb, RTA_MAX,
+ rtm_phonet_policy, extack);
+ if (err < 0)
+ return err;
+
+ rtm = nlmsg_data(nlh);
+ if (rtm->rtm_table != RT_TABLE_MAIN || rtm->rtm_type != RTN_UNICAST)
+ return -EINVAL;
+ if (tb[RTA_DST] == NULL || tb[RTA_OIF] == NULL)
+ return -EINVAL;
+ dst = nla_get_u8(tb[RTA_DST]);
+ if (dst & 3) /* Phonet addresses only have 6 high-order bits */
+ return -EINVAL;
+
+ dev = __dev_get_by_index(net, nla_get_u32(tb[RTA_OIF]));
+ if (dev == NULL)
+ return -ENODEV;
+
+ if (nlh->nlmsg_type == RTM_NEWROUTE)
+ err = phonet_route_add(dev, dst);
+ else
+ err = phonet_route_del(dev, dst);
+ if (!err)
+ rtm_phonet_notify(nlh->nlmsg_type, dev, dst);
+ return err;
+}
+
+static int route_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
+{
+ struct net *net = sock_net(skb->sk);
+ u8 addr;
+
+ rcu_read_lock();
+ for (addr = cb->args[0]; addr < 64; addr++) {
+ struct net_device *dev = phonet_route_get_rcu(net, addr << 2);
+
+ if (!dev)
+ continue;
+
+ if (fill_route(skb, dev, addr << 2, NETLINK_CB(cb->skb).portid,
+ cb->nlh->nlmsg_seq, RTM_NEWROUTE) < 0)
+ goto out;
+ }
+
+out:
+ rcu_read_unlock();
+ cb->args[0] = addr;
+
+ return skb->len;
+}
+
+int __init phonet_netlink_register(void)
+{
+ int err = rtnl_register_module(THIS_MODULE, PF_PHONET, RTM_NEWADDR,
+ addr_doit, NULL, 0);
+ if (err)
+ return err;
+
+ /* Further rtnl_register_module() cannot fail */
+ rtnl_register_module(THIS_MODULE, PF_PHONET, RTM_DELADDR,
+ addr_doit, NULL, 0);
+ rtnl_register_module(THIS_MODULE, PF_PHONET, RTM_GETADDR,
+ NULL, getaddr_dumpit, 0);
+ rtnl_register_module(THIS_MODULE, PF_PHONET, RTM_NEWROUTE,
+ route_doit, NULL, 0);
+ rtnl_register_module(THIS_MODULE, PF_PHONET, RTM_DELROUTE,
+ route_doit, NULL, 0);
+ rtnl_register_module(THIS_MODULE, PF_PHONET, RTM_GETROUTE,
+ NULL, route_dumpit, 0);
+ return 0;
+}