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/core/dst.c | 355 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 355 insertions(+) create mode 100644 net/core/dst.c (limited to 'net/core/dst.c') diff --git a/net/core/dst.c b/net/core/dst.c new file mode 100644 index 000000000..31c08a338 --- /dev/null +++ b/net/core/dst.c @@ -0,0 +1,355 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * net/core/dst.c Protocol independent destination cache. + * + * Authors: Alexey Kuznetsov, + * + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include + +int dst_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb) +{ + kfree_skb(skb); + return 0; +} +EXPORT_SYMBOL(dst_discard_out); + +const struct dst_metrics dst_default_metrics = { + /* This initializer is needed to force linker to place this variable + * into const section. Otherwise it might end into bss section. + * We really want to avoid false sharing on this variable, and catch + * any writes on it. + */ + .refcnt = REFCOUNT_INIT(1), +}; +EXPORT_SYMBOL(dst_default_metrics); + +void dst_init(struct dst_entry *dst, struct dst_ops *ops, + struct net_device *dev, int initial_ref, int initial_obsolete, + unsigned short flags) +{ + dst->dev = dev; + netdev_hold(dev, &dst->dev_tracker, GFP_ATOMIC); + dst->ops = ops; + dst_init_metrics(dst, dst_default_metrics.metrics, true); + dst->expires = 0UL; +#ifdef CONFIG_XFRM + dst->xfrm = NULL; +#endif + dst->input = dst_discard; + dst->output = dst_discard_out; + dst->error = 0; + dst->obsolete = initial_obsolete; + dst->header_len = 0; + dst->trailer_len = 0; +#ifdef CONFIG_IP_ROUTE_CLASSID + dst->tclassid = 0; +#endif + dst->lwtstate = NULL; + atomic_set(&dst->__refcnt, initial_ref); + dst->__use = 0; + dst->lastuse = jiffies; + dst->flags = flags; + if (!(flags & DST_NOCOUNT)) + dst_entries_add(ops, 1); +} +EXPORT_SYMBOL(dst_init); + +void *dst_alloc(struct dst_ops *ops, struct net_device *dev, + int initial_ref, int initial_obsolete, unsigned short flags) +{ + struct dst_entry *dst; + + if (ops->gc && + !(flags & DST_NOCOUNT) && + dst_entries_get_fast(ops) > ops->gc_thresh) + ops->gc(ops); + + dst = kmem_cache_alloc(ops->kmem_cachep, GFP_ATOMIC); + if (!dst) + return NULL; + + dst_init(dst, ops, dev, initial_ref, initial_obsolete, flags); + + return dst; +} +EXPORT_SYMBOL(dst_alloc); + +struct dst_entry *dst_destroy(struct dst_entry * dst) +{ + struct dst_entry *child = NULL; + + smp_rmb(); + +#ifdef CONFIG_XFRM + if (dst->xfrm) { + struct xfrm_dst *xdst = (struct xfrm_dst *) dst; + + child = xdst->child; + } +#endif + if (!(dst->flags & DST_NOCOUNT)) + dst_entries_add(dst->ops, -1); + + if (dst->ops->destroy) + dst->ops->destroy(dst); + netdev_put(dst->dev, &dst->dev_tracker); + + lwtstate_put(dst->lwtstate); + + if (dst->flags & DST_METADATA) + metadata_dst_free((struct metadata_dst *)dst); + else + kmem_cache_free(dst->ops->kmem_cachep, dst); + + dst = child; + if (dst) + dst_release_immediate(dst); + return NULL; +} +EXPORT_SYMBOL(dst_destroy); + +static void dst_destroy_rcu(struct rcu_head *head) +{ + struct dst_entry *dst = container_of(head, struct dst_entry, rcu_head); + + dst = dst_destroy(dst); +} + +/* Operations to mark dst as DEAD and clean up the net device referenced + * by dst: + * 1. put the dst under blackhole interface and discard all tx/rx packets + * on this route. + * 2. release the net_device + * This function should be called when removing routes from the fib tree + * in preparation for a NETDEV_DOWN/NETDEV_UNREGISTER event and also to + * make the next dst_ops->check() fail. + */ +void dst_dev_put(struct dst_entry *dst) +{ + struct net_device *dev = dst->dev; + + dst->obsolete = DST_OBSOLETE_DEAD; + if (dst->ops->ifdown) + dst->ops->ifdown(dst, dev, true); + dst->input = dst_discard; + dst->output = dst_discard_out; + dst->dev = blackhole_netdev; + netdev_ref_replace(dev, blackhole_netdev, &dst->dev_tracker, + GFP_ATOMIC); +} +EXPORT_SYMBOL(dst_dev_put); + +void dst_release(struct dst_entry *dst) +{ + if (dst) { + int newrefcnt; + + newrefcnt = atomic_dec_return(&dst->__refcnt); + if (WARN_ONCE(newrefcnt < 0, "dst_release underflow")) + net_warn_ratelimited("%s: dst:%p refcnt:%d\n", + __func__, dst, newrefcnt); + if (!newrefcnt) + call_rcu_hurry(&dst->rcu_head, dst_destroy_rcu); + } +} +EXPORT_SYMBOL(dst_release); + +void dst_release_immediate(struct dst_entry *dst) +{ + if (dst) { + int newrefcnt; + + newrefcnt = atomic_dec_return(&dst->__refcnt); + if (WARN_ONCE(newrefcnt < 0, "dst_release_immediate underflow")) + net_warn_ratelimited("%s: dst:%p refcnt:%d\n", + __func__, dst, newrefcnt); + if (!newrefcnt) + dst_destroy(dst); + } +} +EXPORT_SYMBOL(dst_release_immediate); + +u32 *dst_cow_metrics_generic(struct dst_entry *dst, unsigned long old) +{ + struct dst_metrics *p = kmalloc(sizeof(*p), GFP_ATOMIC); + + if (p) { + struct dst_metrics *old_p = (struct dst_metrics *)__DST_METRICS_PTR(old); + unsigned long prev, new; + + refcount_set(&p->refcnt, 1); + memcpy(p->metrics, old_p->metrics, sizeof(p->metrics)); + + new = (unsigned long) p; + prev = cmpxchg(&dst->_metrics, old, new); + + if (prev != old) { + kfree(p); + p = (struct dst_metrics *)__DST_METRICS_PTR(prev); + if (prev & DST_METRICS_READ_ONLY) + p = NULL; + } else if (prev & DST_METRICS_REFCOUNTED) { + if (refcount_dec_and_test(&old_p->refcnt)) + kfree(old_p); + } + } + BUILD_BUG_ON(offsetof(struct dst_metrics, metrics) != 0); + return (u32 *)p; +} +EXPORT_SYMBOL(dst_cow_metrics_generic); + +/* Caller asserts that dst_metrics_read_only(dst) is false. */ +void __dst_destroy_metrics_generic(struct dst_entry *dst, unsigned long old) +{ + unsigned long prev, new; + + new = ((unsigned long) &dst_default_metrics) | DST_METRICS_READ_ONLY; + prev = cmpxchg(&dst->_metrics, old, new); + if (prev == old) + kfree(__DST_METRICS_PTR(old)); +} +EXPORT_SYMBOL(__dst_destroy_metrics_generic); + +struct dst_entry *dst_blackhole_check(struct dst_entry *dst, u32 cookie) +{ + return NULL; +} + +u32 *dst_blackhole_cow_metrics(struct dst_entry *dst, unsigned long old) +{ + return NULL; +} + +struct neighbour *dst_blackhole_neigh_lookup(const struct dst_entry *dst, + struct sk_buff *skb, + const void *daddr) +{ + return NULL; +} + +void dst_blackhole_update_pmtu(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb, u32 mtu, + bool confirm_neigh) +{ +} +EXPORT_SYMBOL_GPL(dst_blackhole_update_pmtu); + +void dst_blackhole_redirect(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb) +{ +} +EXPORT_SYMBOL_GPL(dst_blackhole_redirect); + +unsigned int dst_blackhole_mtu(const struct dst_entry *dst) +{ + unsigned int mtu = dst_metric_raw(dst, RTAX_MTU); + + return mtu ? : dst->dev->mtu; +} +EXPORT_SYMBOL_GPL(dst_blackhole_mtu); + +static struct dst_ops dst_blackhole_ops = { + .family = AF_UNSPEC, + .neigh_lookup = dst_blackhole_neigh_lookup, + .check = dst_blackhole_check, + .cow_metrics = dst_blackhole_cow_metrics, + .update_pmtu = dst_blackhole_update_pmtu, + .redirect = dst_blackhole_redirect, + .mtu = dst_blackhole_mtu, +}; + +static void __metadata_dst_init(struct metadata_dst *md_dst, + enum metadata_type type, u8 optslen) +{ + struct dst_entry *dst; + + dst = &md_dst->dst; + dst_init(dst, &dst_blackhole_ops, NULL, 1, DST_OBSOLETE_NONE, + DST_METADATA | DST_NOCOUNT); + memset(dst + 1, 0, sizeof(*md_dst) + optslen - sizeof(*dst)); + md_dst->type = type; +} + +struct metadata_dst *metadata_dst_alloc(u8 optslen, enum metadata_type type, + gfp_t flags) +{ + struct metadata_dst *md_dst; + + md_dst = kmalloc(sizeof(*md_dst) + optslen, flags); + if (!md_dst) + return NULL; + + __metadata_dst_init(md_dst, type, optslen); + + return md_dst; +} +EXPORT_SYMBOL_GPL(metadata_dst_alloc); + +void metadata_dst_free(struct metadata_dst *md_dst) +{ +#ifdef CONFIG_DST_CACHE + if (md_dst->type == METADATA_IP_TUNNEL) + dst_cache_destroy(&md_dst->u.tun_info.dst_cache); +#endif + if (md_dst->type == METADATA_XFRM) + dst_release(md_dst->u.xfrm_info.dst_orig); + kfree(md_dst); +} +EXPORT_SYMBOL_GPL(metadata_dst_free); + +struct metadata_dst __percpu * +metadata_dst_alloc_percpu(u8 optslen, enum metadata_type type, gfp_t flags) +{ + int cpu; + struct metadata_dst __percpu *md_dst; + + md_dst = __alloc_percpu_gfp(sizeof(struct metadata_dst) + optslen, + __alignof__(struct metadata_dst), flags); + if (!md_dst) + return NULL; + + for_each_possible_cpu(cpu) + __metadata_dst_init(per_cpu_ptr(md_dst, cpu), type, optslen); + + return md_dst; +} +EXPORT_SYMBOL_GPL(metadata_dst_alloc_percpu); + +void metadata_dst_free_percpu(struct metadata_dst __percpu *md_dst) +{ + int cpu; + + for_each_possible_cpu(cpu) { + struct metadata_dst *one_md_dst = per_cpu_ptr(md_dst, cpu); + +#ifdef CONFIG_DST_CACHE + if (one_md_dst->type == METADATA_IP_TUNNEL) + dst_cache_destroy(&one_md_dst->u.tun_info.dst_cache); +#endif + if (one_md_dst->type == METADATA_XFRM) + dst_release(one_md_dst->u.xfrm_info.dst_orig); + } + free_percpu(md_dst); +} +EXPORT_SYMBOL_GPL(metadata_dst_free_percpu); -- cgit v1.2.3