aboutsummaryrefslogtreecommitdiffstats
path: root/net/sched/cls_flower.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2022-10-04 13:38:03 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2022-10-04 13:38:03 -0700
commit0326074ff4652329f2a1a9c8685104576bd8d131 (patch)
tree9a7574c7ccb05bf4c7cb34fc5a65457bb8f495cb /net/sched/cls_flower.c
parentMerge tag 'landlock-6.1-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/mic/linux (diff)
parenteth: pse: add missing static inlines (diff)
downloadlinux-dev-0326074ff4652329f2a1a9c8685104576bd8d131.tar.xz
linux-dev-0326074ff4652329f2a1a9c8685104576bd8d131.zip
Merge tag 'net-next-6.1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next
Pull networking updates from Jakub Kicinski: "Core: - Introduce and use a single page frag cache for allocating small skb heads, clawing back the 10-20% performance regression in UDP flood test from previous fixes. - Run packets which already went thru HW coalescing thru SW GRO. This significantly improves TCP segment coalescing and simplifies deployments as different workloads benefit from HW or SW GRO. - Shrink the size of the base zero-copy send structure. - Move TCP init under a new slow / sleepable version of DO_ONCE(). BPF: - Add BPF-specific, any-context-safe memory allocator. - Add helpers/kfuncs for PKCS#7 signature verification from BPF programs. - Define a new map type and related helpers for user space -> kernel communication over a ring buffer (BPF_MAP_TYPE_USER_RINGBUF). - Allow targeting BPF iterators to loop through resources of one task/thread. - Add ability to call selected destructive functions. Expose crash_kexec() to allow BPF to trigger a kernel dump. Use CAP_SYS_BOOT check on the loading process to judge permissions. - Enable BPF to collect custom hierarchical cgroup stats efficiently by integrating with the rstat framework. - Support struct arguments for trampoline based programs. Only structs with size <= 16B and x86 are supported. - Invoke cgroup/connect{4,6} programs for unprivileged ICMP ping sockets (instead of just TCP and UDP sockets). - Add a helper for accessing CLOCK_TAI for time sensitive network related programs. - Support accessing network tunnel metadata's flags. - Make TCP SYN ACK RTO tunable by BPF programs with TCP Fast Open. - Add support for writing to Netfilter's nf_conn:mark. Protocols: - WiFi: more Extremely High Throughput (EHT) and Multi-Link Operation (MLO) work (802.11be, WiFi 7). - vsock: improve support for SO_RCVLOWAT. - SMC: support SO_REUSEPORT. - Netlink: define and document how to use netlink in a "modern" way. Support reporting missing attributes via extended ACK. - IPSec: support collect metadata mode for xfrm interfaces. - TCPv6: send consistent autoflowlabel in SYN_RECV state and RST packets. - TCP: introduce optional per-netns connection hash table to allow better isolation between namespaces (opt-in, at the cost of memory and cache pressure). - MPTCP: support TCP_FASTOPEN_CONNECT. - Add NEXT-C-SID support in Segment Routing (SRv6) End behavior. - Adjust IP_UNICAST_IF sockopt behavior for connected UDP sockets. - Open vSwitch: - Allow specifying ifindex of new interfaces. - Allow conntrack and metering in non-initial user namespace. - TLS: support the Korean ARIA-GCM crypto algorithm. - Remove DECnet support. Driver API: - Allow selecting the conduit interface used by each port in DSA switches, at runtime. - Ethernet Power Sourcing Equipment and Power Device support. - Add tc-taprio support for queueMaxSDU parameter, i.e. setting per traffic class max frame size for time-based packet schedules. - Support PHY rate matching - adapting between differing host-side and link-side speeds. - Introduce QUSGMII PHY mode and 1000BASE-KX interface mode. - Validate OF (device tree) nodes for DSA shared ports; make phylink-related properties mandatory on DSA and CPU ports. Enforcing more uniformity should allow transitioning to phylink. - Require that flash component name used during update matches one of the components for which version is reported by info_get(). - Remove "weight" argument from driver-facing NAPI API as much as possible. It's one of those magic knobs which seemed like a good idea at the time but is too indirect to use in practice. - Support offload of TLS connections with 256 bit keys. New hardware / drivers: - Ethernet: - Microchip KSZ9896 6-port Gigabit Ethernet Switch - Renesas Ethernet AVB (EtherAVB-IF) Gen4 SoCs - Analog Devices ADIN1110 and ADIN2111 industrial single pair Ethernet (10BASE-T1L) MAC+PHY. - Rockchip RV1126 Gigabit Ethernet (a version of stmmac IP). - Ethernet SFPs / modules: - RollBall / Hilink / Turris 10G copper SFPs - HALNy GPON module - WiFi: - CYW43439 SDIO chipset (brcmfmac) - CYW89459 PCIe chipset (brcmfmac) - BCM4378 on Apple platforms (brcmfmac) Drivers: - CAN: - gs_usb: HW timestamp support - Ethernet PHYs: - lan8814: cable diagnostics - Ethernet NICs: - Intel (100G): - implement control of FCS/CRC stripping - port splitting via devlink - L2TPv3 filtering offload - nVidia/Mellanox: - tunnel offload for sub-functions - MACSec offload, w/ Extended packet number and replay window offload - significantly restructure, and optimize the AF_XDP support, align the behavior with other vendors - Huawei: - configuring DSCP map for traffic class selection - querying standard FEC statistics - querying SerDes lane number via ethtool - Marvell/Cavium: - egress priority flow control - MACSec offload - AMD/SolarFlare: - PTP over IPv6 and raw Ethernet - small / embedded: - ax88772: convert to phylink (to support SFP cages) - altera: tse: convert to phylink - ftgmac100: support fixed link - enetc: standard Ethtool counters - macb: ZynqMP SGMII dynamic configuration support - tsnep: support multi-queue and use page pool - lan743x: Rx IP & TCP checksum offload - igc: add xdp frags support to ndo_xdp_xmit - Ethernet high-speed switches: - Marvell (prestera): - support SPAN port features (traffic mirroring) - nexthop object offloading - Microchip (sparx5): - multicast forwarding offload - QoS queuing offload (tc-mqprio, tc-tbf, tc-ets) - Ethernet embedded switches: - Marvell (mv88e6xxx): - support RGMII cmode - NXP (felix): - standardized ethtool counters - Microchip (lan966x): - QoS queuing offload (tc-mqprio, tc-tbf, tc-cbs, tc-ets) - traffic policing and mirroring - link aggregation / bonding offload - QUSGMII PHY mode support - Qualcomm 802.11ax WiFi (ath11k): - cold boot calibration support on WCN6750 - support to connect to a non-transmit MBSSID AP profile - enable remain-on-channel support on WCN6750 - Wake-on-WLAN support for WCN6750 - support to provide transmit power from firmware via nl80211 - support to get power save duration for each client - spectral scan support for 160 MHz - MediaTek WiFi (mt76): - WiFi-to-Ethernet bridging offload for MT7986 chips - RealTek WiFi (rtw89): - P2P support" * tag 'net-next-6.1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1864 commits) eth: pse: add missing static inlines once: rename _SLOW to _SLEEPABLE net: pse-pd: add regulator based PSE driver dt-bindings: net: pse-dt: add bindings for regulator based PoDL PSE controller ethtool: add interface to interact with Ethernet Power Equipment net: mdiobus: search for PSE nodes by parsing PHY nodes. net: mdiobus: fwnode_mdiobus_register_phy() rework error handling net: add framework to support Ethernet PSE and PDs devices dt-bindings: net: phy: add PoDL PSE property net: marvell: prestera: Propagate nh state from hw to kernel net: marvell: prestera: Add neighbour cache accounting net: marvell: prestera: add stub handler neighbour events net: marvell: prestera: Add heplers to interact with fib_notifier_info net: marvell: prestera: Add length macros for prestera_ip_addr net: marvell: prestera: add delayed wq and flush wq on deinit net: marvell: prestera: Add strict cleanup of fib arbiter net: marvell: prestera: Add cleanup of allocated fib_nodes net: marvell: prestera: Add router nexthops ABI eth: octeon: fix build after netif_napi_add() changes net/mlx5: E-Switch, Return EBUSY if can't get mode lock ...
Diffstat (limited to 'net/sched/cls_flower.c')
-rw-r--r--net/sched/cls_flower.c23
1 files changed, 17 insertions, 6 deletions
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 041d63ff809a..25bc57ee6ea1 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -69,6 +69,7 @@ struct fl_flow_key {
struct flow_dissector_key_hash hash;
struct flow_dissector_key_num_of_vlans num_of_vlans;
struct flow_dissector_key_pppoe pppoe;
+ struct flow_dissector_key_l2tpv3 l2tpv3;
} __aligned(BITS_PER_LONG / 8); /* Ensure that we can do comparisons as longs. */
struct fl_flow_mask_range {
@@ -712,6 +713,7 @@ static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = {
[TCA_FLOWER_KEY_NUM_OF_VLANS] = { .type = NLA_U8 },
[TCA_FLOWER_KEY_PPPOE_SID] = { .type = NLA_U16 },
[TCA_FLOWER_KEY_PPP_PROTO] = { .type = NLA_U16 },
+ [TCA_FLOWER_KEY_L2TPV3_SID] = { .type = NLA_U32 },
};
@@ -1790,6 +1792,11 @@ static int fl_set_key(struct net *net, struct nlattr **tb,
fl_set_key_val(tb, key->arp.tha, TCA_FLOWER_KEY_ARP_THA,
mask->arp.tha, TCA_FLOWER_KEY_ARP_THA_MASK,
sizeof(key->arp.tha));
+ } else if (key->basic.ip_proto == IPPROTO_L2TP) {
+ fl_set_key_val(tb, &key->l2tpv3.session_id,
+ TCA_FLOWER_KEY_L2TPV3_SID,
+ &mask->l2tpv3.session_id, TCA_FLOWER_UNSPEC,
+ sizeof(key->l2tpv3.session_id));
}
if (key->basic.ip_proto == IPPROTO_TCP ||
@@ -1970,6 +1977,8 @@ static void fl_init_dissector(struct flow_dissector *dissector,
FLOW_DISSECTOR_KEY_NUM_OF_VLANS, num_of_vlans);
FL_KEY_SET_IF_MASKED(mask, keys, cnt,
FLOW_DISSECTOR_KEY_PPPOE, pppoe);
+ FL_KEY_SET_IF_MASKED(mask, keys, cnt,
+ FLOW_DISSECTOR_KEY_L2TPV3, l2tpv3);
skb_flow_dissector_init(dissector, keys, cnt);
}
@@ -3196,6 +3205,13 @@ static int fl_dump_key(struct sk_buff *skb, struct net *net,
mask->arp.tha, TCA_FLOWER_KEY_ARP_THA_MASK,
sizeof(key->arp.tha))))
goto nla_put_failure;
+ else if (key->basic.ip_proto == IPPROTO_L2TP &&
+ fl_dump_key_val(skb, &key->l2tpv3.session_id,
+ TCA_FLOWER_KEY_L2TPV3_SID,
+ &mask->l2tpv3.session_id,
+ TCA_FLOWER_UNSPEC,
+ sizeof(key->l2tpv3.session_id)))
+ goto nla_put_failure;
if ((key->basic.ip_proto == IPPROTO_TCP ||
key->basic.ip_proto == IPPROTO_UDP ||
@@ -3389,12 +3405,7 @@ static void fl_bind_class(void *fh, u32 classid, unsigned long cl, void *q,
{
struct cls_fl_filter *f = fh;
- if (f && f->res.classid == classid) {
- if (cl)
- __tcf_bind_filter(q, &f->res, base);
- else
- __tcf_unbind_filter(q, &f->res);
- }
+ tc_cls_bind_class(classid, cl, q, &f->res, base);
}
static bool fl_delete_empty(struct tcf_proto *tp)