aboutsummaryrefslogtreecommitdiff
path: root/net/netfilter/xt_RATEEST.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/xt_RATEEST.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/xt_RATEEST.c')
-rw-r--r--net/netfilter/xt_RATEEST.c233
1 files changed, 233 insertions, 0 deletions
diff --git a/net/netfilter/xt_RATEEST.c b/net/netfilter/xt_RATEEST.c
new file mode 100644
index 000000000..80f6624e2
--- /dev/null
+++ b/net/netfilter/xt_RATEEST.c
@@ -0,0 +1,233 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * (C) 2007 Patrick McHardy <kaber@trash.net>
+ */
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <linux/gen_stats.h>
+#include <linux/jhash.h>
+#include <linux/rtnetlink.h>
+#include <linux/random.h>
+#include <linux/slab.h>
+#include <net/gen_stats.h>
+#include <net/netlink.h>
+#include <net/netns/generic.h>
+
+#include <linux/netfilter/x_tables.h>
+#include <linux/netfilter/xt_RATEEST.h>
+#include <net/netfilter/xt_rateest.h>
+
+#define RATEEST_HSIZE 16
+
+struct xt_rateest_net {
+ struct mutex hash_lock;
+ struct hlist_head hash[RATEEST_HSIZE];
+};
+
+static unsigned int xt_rateest_id;
+
+static unsigned int jhash_rnd __read_mostly;
+
+static unsigned int xt_rateest_hash(const char *name)
+{
+ return jhash(name, sizeof_field(struct xt_rateest, name), jhash_rnd) &
+ (RATEEST_HSIZE - 1);
+}
+
+static void xt_rateest_hash_insert(struct xt_rateest_net *xn,
+ struct xt_rateest *est)
+{
+ unsigned int h;
+
+ h = xt_rateest_hash(est->name);
+ hlist_add_head(&est->list, &xn->hash[h]);
+}
+
+static struct xt_rateest *__xt_rateest_lookup(struct xt_rateest_net *xn,
+ const char *name)
+{
+ struct xt_rateest *est;
+ unsigned int h;
+
+ h = xt_rateest_hash(name);
+ hlist_for_each_entry(est, &xn->hash[h], list) {
+ if (strcmp(est->name, name) == 0) {
+ est->refcnt++;
+ return est;
+ }
+ }
+
+ return NULL;
+}
+
+struct xt_rateest *xt_rateest_lookup(struct net *net, const char *name)
+{
+ struct xt_rateest_net *xn = net_generic(net, xt_rateest_id);
+ struct xt_rateest *est;
+
+ mutex_lock(&xn->hash_lock);
+ est = __xt_rateest_lookup(xn, name);
+ mutex_unlock(&xn->hash_lock);
+ return est;
+}
+EXPORT_SYMBOL_GPL(xt_rateest_lookup);
+
+void xt_rateest_put(struct net *net, struct xt_rateest *est)
+{
+ struct xt_rateest_net *xn = net_generic(net, xt_rateest_id);
+
+ mutex_lock(&xn->hash_lock);
+ if (--est->refcnt == 0) {
+ hlist_del(&est->list);
+ gen_kill_estimator(&est->rate_est);
+ /*
+ * gen_estimator est_timer() might access est->lock or bstats,
+ * wait a RCU grace period before freeing 'est'
+ */
+ kfree_rcu(est, rcu);
+ }
+ mutex_unlock(&xn->hash_lock);
+}
+EXPORT_SYMBOL_GPL(xt_rateest_put);
+
+static unsigned int
+xt_rateest_tg(struct sk_buff *skb, const struct xt_action_param *par)
+{
+ const struct xt_rateest_target_info *info = par->targinfo;
+ struct gnet_stats_basic_sync *stats = &info->est->bstats;
+
+ spin_lock_bh(&info->est->lock);
+ u64_stats_add(&stats->bytes, skb->len);
+ u64_stats_inc(&stats->packets);
+ spin_unlock_bh(&info->est->lock);
+
+ return XT_CONTINUE;
+}
+
+static int xt_rateest_tg_checkentry(const struct xt_tgchk_param *par)
+{
+ struct xt_rateest_net *xn = net_generic(par->net, xt_rateest_id);
+ struct xt_rateest_target_info *info = par->targinfo;
+ struct xt_rateest *est;
+ struct {
+ struct nlattr opt;
+ struct gnet_estimator est;
+ } cfg;
+ int ret;
+
+ if (strnlen(info->name, sizeof(est->name)) >= sizeof(est->name))
+ return -ENAMETOOLONG;
+
+ net_get_random_once(&jhash_rnd, sizeof(jhash_rnd));
+
+ mutex_lock(&xn->hash_lock);
+ est = __xt_rateest_lookup(xn, info->name);
+ if (est) {
+ mutex_unlock(&xn->hash_lock);
+ /*
+ * If estimator parameters are specified, they must match the
+ * existing estimator.
+ */
+ if ((!info->interval && !info->ewma_log) ||
+ (info->interval != est->params.interval ||
+ info->ewma_log != est->params.ewma_log)) {
+ xt_rateest_put(par->net, est);
+ return -EINVAL;
+ }
+ info->est = est;
+ return 0;
+ }
+
+ ret = -ENOMEM;
+ est = kzalloc(sizeof(*est), GFP_KERNEL);
+ if (!est)
+ goto err1;
+
+ gnet_stats_basic_sync_init(&est->bstats);
+ strscpy(est->name, info->name, sizeof(est->name));
+ spin_lock_init(&est->lock);
+ est->refcnt = 1;
+ est->params.interval = info->interval;
+ est->params.ewma_log = info->ewma_log;
+
+ cfg.opt.nla_len = nla_attr_size(sizeof(cfg.est));
+ cfg.opt.nla_type = TCA_STATS_RATE_EST;
+ cfg.est.interval = info->interval;
+ cfg.est.ewma_log = info->ewma_log;
+
+ ret = gen_new_estimator(&est->bstats, NULL, &est->rate_est,
+ &est->lock, NULL, &cfg.opt);
+ if (ret < 0)
+ goto err2;
+
+ info->est = est;
+ xt_rateest_hash_insert(xn, est);
+ mutex_unlock(&xn->hash_lock);
+ return 0;
+
+err2:
+ kfree(est);
+err1:
+ mutex_unlock(&xn->hash_lock);
+ return ret;
+}
+
+static void xt_rateest_tg_destroy(const struct xt_tgdtor_param *par)
+{
+ struct xt_rateest_target_info *info = par->targinfo;
+
+ xt_rateest_put(par->net, info->est);
+}
+
+static struct xt_target xt_rateest_tg_reg __read_mostly = {
+ .name = "RATEEST",
+ .revision = 0,
+ .family = NFPROTO_UNSPEC,
+ .target = xt_rateest_tg,
+ .checkentry = xt_rateest_tg_checkentry,
+ .destroy = xt_rateest_tg_destroy,
+ .targetsize = sizeof(struct xt_rateest_target_info),
+ .usersize = offsetof(struct xt_rateest_target_info, est),
+ .me = THIS_MODULE,
+};
+
+static __net_init int xt_rateest_net_init(struct net *net)
+{
+ struct xt_rateest_net *xn = net_generic(net, xt_rateest_id);
+ int i;
+
+ mutex_init(&xn->hash_lock);
+ for (i = 0; i < ARRAY_SIZE(xn->hash); i++)
+ INIT_HLIST_HEAD(&xn->hash[i]);
+ return 0;
+}
+
+static struct pernet_operations xt_rateest_net_ops = {
+ .init = xt_rateest_net_init,
+ .id = &xt_rateest_id,
+ .size = sizeof(struct xt_rateest_net),
+};
+
+static int __init xt_rateest_tg_init(void)
+{
+ int err = register_pernet_subsys(&xt_rateest_net_ops);
+
+ if (err)
+ return err;
+ return xt_register_target(&xt_rateest_tg_reg);
+}
+
+static void __exit xt_rateest_tg_fini(void)
+{
+ xt_unregister_target(&xt_rateest_tg_reg);
+ unregister_pernet_subsys(&xt_rateest_net_ops);
+}
+
+
+MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Xtables: packet rate estimator");
+MODULE_ALIAS("ipt_RATEEST");
+MODULE_ALIAS("ip6t_RATEEST");
+module_init(xt_rateest_tg_init);
+module_exit(xt_rateest_tg_fini);