aboutsummaryrefslogtreecommitdiff
path: root/net/netfilter/xt_sctp.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_sctp.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_sctp.c')
-rw-r--r--net/netfilter/xt_sctp.c198
1 files changed, 198 insertions, 0 deletions
diff --git a/net/netfilter/xt_sctp.c b/net/netfilter/xt_sctp.c
new file mode 100644
index 000000000..e8961094a
--- /dev/null
+++ b/net/netfilter/xt_sctp.c
@@ -0,0 +1,198 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <net/ip.h>
+#include <net/ipv6.h>
+#include <linux/sctp.h>
+
+#include <linux/netfilter/x_tables.h>
+#include <linux/netfilter/xt_sctp.h>
+#include <linux/netfilter_ipv4/ip_tables.h>
+#include <linux/netfilter_ipv6/ip6_tables.h>
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Kiran Kumar Immidi");
+MODULE_DESCRIPTION("Xtables: SCTP protocol packet match");
+MODULE_ALIAS("ipt_sctp");
+MODULE_ALIAS("ip6t_sctp");
+
+#define SCCHECK(cond, option, flag, invflag) (!((flag) & (option)) \
+ || (!!((invflag) & (option)) ^ (cond)))
+
+static bool
+match_flags(const struct xt_sctp_flag_info *flag_info,
+ const int flag_count,
+ u_int8_t chunktype,
+ u_int8_t chunkflags)
+{
+ int i;
+
+ for (i = 0; i < flag_count; i++)
+ if (flag_info[i].chunktype == chunktype)
+ return (chunkflags & flag_info[i].flag_mask) == flag_info[i].flag;
+
+ return true;
+}
+
+static inline bool
+match_packet(const struct sk_buff *skb,
+ unsigned int offset,
+ const struct xt_sctp_info *info,
+ bool *hotdrop)
+{
+ u_int32_t chunkmapcopy[256 / sizeof (u_int32_t)];
+ const struct sctp_chunkhdr *sch;
+ struct sctp_chunkhdr _sch;
+ int chunk_match_type = info->chunk_match_type;
+ const struct xt_sctp_flag_info *flag_info = info->flag_info;
+ int flag_count = info->flag_count;
+
+#ifdef DEBUG
+ int i = 0;
+#endif
+
+ if (chunk_match_type == SCTP_CHUNK_MATCH_ALL)
+ SCTP_CHUNKMAP_COPY(chunkmapcopy, info->chunkmap);
+
+ do {
+ sch = skb_header_pointer(skb, offset, sizeof(_sch), &_sch);
+ if (sch == NULL || sch->length == 0) {
+ pr_debug("Dropping invalid SCTP packet.\n");
+ *hotdrop = true;
+ return false;
+ }
+#ifdef DEBUG
+ pr_debug("Chunk num: %d\toffset: %d\ttype: %d\tlength: %d"
+ "\tflags: %x\n",
+ ++i, offset, sch->type, htons(sch->length),
+ sch->flags);
+#endif
+ offset += SCTP_PAD4(ntohs(sch->length));
+
+ pr_debug("skb->len: %d\toffset: %d\n", skb->len, offset);
+
+ if (SCTP_CHUNKMAP_IS_SET(info->chunkmap, sch->type)) {
+ switch (chunk_match_type) {
+ case SCTP_CHUNK_MATCH_ANY:
+ if (match_flags(flag_info, flag_count,
+ sch->type, sch->flags)) {
+ return true;
+ }
+ break;
+
+ case SCTP_CHUNK_MATCH_ALL:
+ if (match_flags(flag_info, flag_count,
+ sch->type, sch->flags))
+ SCTP_CHUNKMAP_CLEAR(chunkmapcopy, sch->type);
+ break;
+
+ case SCTP_CHUNK_MATCH_ONLY:
+ if (!match_flags(flag_info, flag_count,
+ sch->type, sch->flags))
+ return false;
+ break;
+ }
+ } else {
+ switch (chunk_match_type) {
+ case SCTP_CHUNK_MATCH_ONLY:
+ return false;
+ }
+ }
+ } while (offset < skb->len);
+
+ switch (chunk_match_type) {
+ case SCTP_CHUNK_MATCH_ALL:
+ return SCTP_CHUNKMAP_IS_CLEAR(chunkmapcopy);
+ case SCTP_CHUNK_MATCH_ANY:
+ return false;
+ case SCTP_CHUNK_MATCH_ONLY:
+ return true;
+ }
+
+ /* This will never be reached, but required to stop compiler whine */
+ return false;
+}
+
+static bool
+sctp_mt(const struct sk_buff *skb, struct xt_action_param *par)
+{
+ const struct xt_sctp_info *info = par->matchinfo;
+ const struct sctphdr *sh;
+ struct sctphdr _sh;
+
+ if (par->fragoff != 0) {
+ pr_debug("Dropping non-first fragment.. FIXME\n");
+ return false;
+ }
+
+ sh = skb_header_pointer(skb, par->thoff, sizeof(_sh), &_sh);
+ if (sh == NULL) {
+ pr_debug("Dropping evil TCP offset=0 tinygram.\n");
+ par->hotdrop = true;
+ return false;
+ }
+ pr_debug("spt: %d\tdpt: %d\n", ntohs(sh->source), ntohs(sh->dest));
+
+ return SCCHECK(ntohs(sh->source) >= info->spts[0]
+ && ntohs(sh->source) <= info->spts[1],
+ XT_SCTP_SRC_PORTS, info->flags, info->invflags) &&
+ SCCHECK(ntohs(sh->dest) >= info->dpts[0]
+ && ntohs(sh->dest) <= info->dpts[1],
+ XT_SCTP_DEST_PORTS, info->flags, info->invflags) &&
+ SCCHECK(match_packet(skb, par->thoff + sizeof(_sh),
+ info, &par->hotdrop),
+ XT_SCTP_CHUNK_TYPES, info->flags, info->invflags);
+}
+
+static int sctp_mt_check(const struct xt_mtchk_param *par)
+{
+ const struct xt_sctp_info *info = par->matchinfo;
+
+ if (info->flags & ~XT_SCTP_VALID_FLAGS)
+ return -EINVAL;
+ if (info->invflags & ~XT_SCTP_VALID_FLAGS)
+ return -EINVAL;
+ if (info->invflags & ~info->flags)
+ return -EINVAL;
+ if (!(info->flags & XT_SCTP_CHUNK_TYPES))
+ return 0;
+ if (info->chunk_match_type & (SCTP_CHUNK_MATCH_ALL |
+ SCTP_CHUNK_MATCH_ANY | SCTP_CHUNK_MATCH_ONLY))
+ return 0;
+ return -EINVAL;
+}
+
+static struct xt_match sctp_mt_reg[] __read_mostly = {
+ {
+ .name = "sctp",
+ .family = NFPROTO_IPV4,
+ .checkentry = sctp_mt_check,
+ .match = sctp_mt,
+ .matchsize = sizeof(struct xt_sctp_info),
+ .proto = IPPROTO_SCTP,
+ .me = THIS_MODULE
+ },
+ {
+ .name = "sctp",
+ .family = NFPROTO_IPV6,
+ .checkentry = sctp_mt_check,
+ .match = sctp_mt,
+ .matchsize = sizeof(struct xt_sctp_info),
+ .proto = IPPROTO_SCTP,
+ .me = THIS_MODULE
+ },
+};
+
+static int __init sctp_mt_init(void)
+{
+ return xt_register_matches(sctp_mt_reg, ARRAY_SIZE(sctp_mt_reg));
+}
+
+static void __exit sctp_mt_exit(void)
+{
+ xt_unregister_matches(sctp_mt_reg, ARRAY_SIZE(sctp_mt_reg));
+}
+
+module_init(sctp_mt_init);
+module_exit(sctp_mt_exit);