aboutsummaryrefslogtreecommitdiff
path: root/net/netfilter/nft_hash.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/netfilter/nft_hash.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 'net/netfilter/nft_hash.c')
-rw-r--r--net/netfilter/nft_hash.c286
1 files changed, 286 insertions, 0 deletions
diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c
new file mode 100644
index 000000000..ee8d487b6
--- /dev/null
+++ b/net/netfilter/nft_hash.c
@@ -0,0 +1,286 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2016 Laura Garcia <nevola@gmail.com>
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables_core.h>
+#include <linux/jhash.h>
+
+struct nft_jhash {
+ u8 sreg;
+ u8 dreg;
+ u8 len;
+ bool autogen_seed:1;
+ u32 modulus;
+ u32 seed;
+ u32 offset;
+};
+
+static void nft_jhash_eval(const struct nft_expr *expr,
+ struct nft_regs *regs,
+ const struct nft_pktinfo *pkt)
+{
+ struct nft_jhash *priv = nft_expr_priv(expr);
+ const void *data = &regs->data[priv->sreg];
+ u32 h;
+
+ h = reciprocal_scale(jhash(data, priv->len, priv->seed),
+ priv->modulus);
+
+ regs->data[priv->dreg] = h + priv->offset;
+}
+
+struct nft_symhash {
+ u8 dreg;
+ u32 modulus;
+ u32 offset;
+};
+
+static void nft_symhash_eval(const struct nft_expr *expr,
+ struct nft_regs *regs,
+ const struct nft_pktinfo *pkt)
+{
+ struct nft_symhash *priv = nft_expr_priv(expr);
+ struct sk_buff *skb = pkt->skb;
+ u32 h;
+
+ h = reciprocal_scale(__skb_get_hash_symmetric(skb), priv->modulus);
+
+ regs->data[priv->dreg] = h + priv->offset;
+}
+
+static const struct nla_policy nft_hash_policy[NFTA_HASH_MAX + 1] = {
+ [NFTA_HASH_SREG] = { .type = NLA_U32 },
+ [NFTA_HASH_DREG] = { .type = NLA_U32 },
+ [NFTA_HASH_LEN] = { .type = NLA_U32 },
+ [NFTA_HASH_MODULUS] = { .type = NLA_U32 },
+ [NFTA_HASH_SEED] = { .type = NLA_U32 },
+ [NFTA_HASH_OFFSET] = { .type = NLA_U32 },
+ [NFTA_HASH_TYPE] = { .type = NLA_U32 },
+};
+
+static int nft_jhash_init(const struct nft_ctx *ctx,
+ const struct nft_expr *expr,
+ const struct nlattr * const tb[])
+{
+ struct nft_jhash *priv = nft_expr_priv(expr);
+ u32 len;
+ int err;
+
+ if (!tb[NFTA_HASH_SREG] ||
+ !tb[NFTA_HASH_DREG] ||
+ !tb[NFTA_HASH_LEN] ||
+ !tb[NFTA_HASH_MODULUS])
+ return -EINVAL;
+
+ if (tb[NFTA_HASH_OFFSET])
+ priv->offset = ntohl(nla_get_be32(tb[NFTA_HASH_OFFSET]));
+
+ err = nft_parse_u32_check(tb[NFTA_HASH_LEN], U8_MAX, &len);
+ if (err < 0)
+ return err;
+ if (len == 0)
+ return -ERANGE;
+
+ priv->len = len;
+
+ err = nft_parse_register_load(tb[NFTA_HASH_SREG], &priv->sreg, len);
+ if (err < 0)
+ return err;
+
+ priv->modulus = ntohl(nla_get_be32(tb[NFTA_HASH_MODULUS]));
+ if (priv->modulus < 1)
+ return -ERANGE;
+
+ if (priv->offset + priv->modulus - 1 < priv->offset)
+ return -EOVERFLOW;
+
+ if (tb[NFTA_HASH_SEED]) {
+ priv->seed = ntohl(nla_get_be32(tb[NFTA_HASH_SEED]));
+ } else {
+ priv->autogen_seed = true;
+ get_random_bytes(&priv->seed, sizeof(priv->seed));
+ }
+
+ return nft_parse_register_store(ctx, tb[NFTA_HASH_DREG], &priv->dreg,
+ NULL, NFT_DATA_VALUE, sizeof(u32));
+}
+
+static int nft_symhash_init(const struct nft_ctx *ctx,
+ const struct nft_expr *expr,
+ const struct nlattr * const tb[])
+{
+ struct nft_symhash *priv = nft_expr_priv(expr);
+
+ if (!tb[NFTA_HASH_DREG] ||
+ !tb[NFTA_HASH_MODULUS])
+ return -EINVAL;
+
+ if (tb[NFTA_HASH_OFFSET])
+ priv->offset = ntohl(nla_get_be32(tb[NFTA_HASH_OFFSET]));
+
+ priv->modulus = ntohl(nla_get_be32(tb[NFTA_HASH_MODULUS]));
+ if (priv->modulus < 1)
+ return -ERANGE;
+
+ if (priv->offset + priv->modulus - 1 < priv->offset)
+ return -EOVERFLOW;
+
+ return nft_parse_register_store(ctx, tb[NFTA_HASH_DREG],
+ &priv->dreg, NULL, NFT_DATA_VALUE,
+ sizeof(u32));
+}
+
+static int nft_jhash_dump(struct sk_buff *skb,
+ const struct nft_expr *expr, bool reset)
+{
+ const struct nft_jhash *priv = nft_expr_priv(expr);
+
+ if (nft_dump_register(skb, NFTA_HASH_SREG, priv->sreg))
+ goto nla_put_failure;
+ if (nft_dump_register(skb, NFTA_HASH_DREG, priv->dreg))
+ goto nla_put_failure;
+ if (nla_put_be32(skb, NFTA_HASH_LEN, htonl(priv->len)))
+ goto nla_put_failure;
+ if (nla_put_be32(skb, NFTA_HASH_MODULUS, htonl(priv->modulus)))
+ goto nla_put_failure;
+ if (!priv->autogen_seed &&
+ nla_put_be32(skb, NFTA_HASH_SEED, htonl(priv->seed)))
+ goto nla_put_failure;
+ if (priv->offset != 0)
+ if (nla_put_be32(skb, NFTA_HASH_OFFSET, htonl(priv->offset)))
+ goto nla_put_failure;
+ if (nla_put_be32(skb, NFTA_HASH_TYPE, htonl(NFT_HASH_JENKINS)))
+ goto nla_put_failure;
+ return 0;
+
+nla_put_failure:
+ return -1;
+}
+
+static bool nft_jhash_reduce(struct nft_regs_track *track,
+ const struct nft_expr *expr)
+{
+ const struct nft_jhash *priv = nft_expr_priv(expr);
+
+ nft_reg_track_cancel(track, priv->dreg, sizeof(u32));
+
+ return false;
+}
+
+static int nft_symhash_dump(struct sk_buff *skb,
+ const struct nft_expr *expr, bool reset)
+{
+ const struct nft_symhash *priv = nft_expr_priv(expr);
+
+ if (nft_dump_register(skb, NFTA_HASH_DREG, priv->dreg))
+ goto nla_put_failure;
+ if (nla_put_be32(skb, NFTA_HASH_MODULUS, htonl(priv->modulus)))
+ goto nla_put_failure;
+ if (priv->offset != 0)
+ if (nla_put_be32(skb, NFTA_HASH_OFFSET, htonl(priv->offset)))
+ goto nla_put_failure;
+ if (nla_put_be32(skb, NFTA_HASH_TYPE, htonl(NFT_HASH_SYM)))
+ goto nla_put_failure;
+ return 0;
+
+nla_put_failure:
+ return -1;
+}
+
+static bool nft_symhash_reduce(struct nft_regs_track *track,
+ const struct nft_expr *expr)
+{
+ struct nft_symhash *priv = nft_expr_priv(expr);
+ struct nft_symhash *symhash;
+
+ if (!nft_reg_track_cmp(track, expr, priv->dreg)) {
+ nft_reg_track_update(track, expr, priv->dreg, sizeof(u32));
+ return false;
+ }
+
+ symhash = nft_expr_priv(track->regs[priv->dreg].selector);
+ if (priv->offset != symhash->offset ||
+ priv->modulus != symhash->modulus) {
+ nft_reg_track_update(track, expr, priv->dreg, sizeof(u32));
+ return false;
+ }
+
+ if (!track->regs[priv->dreg].bitwise)
+ return true;
+
+ return false;
+}
+
+static struct nft_expr_type nft_hash_type;
+static const struct nft_expr_ops nft_jhash_ops = {
+ .type = &nft_hash_type,
+ .size = NFT_EXPR_SIZE(sizeof(struct nft_jhash)),
+ .eval = nft_jhash_eval,
+ .init = nft_jhash_init,
+ .dump = nft_jhash_dump,
+ .reduce = nft_jhash_reduce,
+};
+
+static const struct nft_expr_ops nft_symhash_ops = {
+ .type = &nft_hash_type,
+ .size = NFT_EXPR_SIZE(sizeof(struct nft_symhash)),
+ .eval = nft_symhash_eval,
+ .init = nft_symhash_init,
+ .dump = nft_symhash_dump,
+ .reduce = nft_symhash_reduce,
+};
+
+static const struct nft_expr_ops *
+nft_hash_select_ops(const struct nft_ctx *ctx,
+ const struct nlattr * const tb[])
+{
+ u32 type;
+
+ if (!tb[NFTA_HASH_TYPE])
+ return &nft_jhash_ops;
+
+ type = ntohl(nla_get_be32(tb[NFTA_HASH_TYPE]));
+ switch (type) {
+ case NFT_HASH_SYM:
+ return &nft_symhash_ops;
+ case NFT_HASH_JENKINS:
+ return &nft_jhash_ops;
+ default:
+ break;
+ }
+ return ERR_PTR(-EOPNOTSUPP);
+}
+
+static struct nft_expr_type nft_hash_type __read_mostly = {
+ .name = "hash",
+ .select_ops = nft_hash_select_ops,
+ .policy = nft_hash_policy,
+ .maxattr = NFTA_HASH_MAX,
+ .owner = THIS_MODULE,
+};
+
+static int __init nft_hash_module_init(void)
+{
+ return nft_register_expr(&nft_hash_type);
+}
+
+static void __exit nft_hash_module_exit(void)
+{
+ nft_unregister_expr(&nft_hash_type);
+}
+
+module_init(nft_hash_module_init);
+module_exit(nft_hash_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Laura Garcia <nevola@gmail.com>");
+MODULE_ALIAS_NFT_EXPR("hash");
+MODULE_DESCRIPTION("Netfilter nftables hash module");