summaryrefslogtreecommitdiff
path: root/drivers/net/ethernet/netronome/nfp/flower/conntrack.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 /drivers/net/ethernet/netronome/nfp/flower/conntrack.c
parent522667b24f08009591c90e75bfe2ffb67f555498 (diff)
parent681bf011b9b5989c6e9db6beb64494918aab9a43 (diff)
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 'drivers/net/ethernet/netronome/nfp/flower/conntrack.c')
-rw-r--r--drivers/net/ethernet/netronome/nfp/flower/conntrack.c242
1 files changed, 234 insertions, 8 deletions
diff --git a/drivers/net/ethernet/netronome/nfp/flower/conntrack.c b/drivers/net/ethernet/netronome/nfp/flower/conntrack.c
index b3b2a23b8d89..f693119541d5 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/conntrack.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/conntrack.c
@@ -1,6 +1,9 @@
// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
/* Copyright (C) 2021 Corigine, Inc. */
+#include <net/tc_act/tc_csum.h>
+#include <net/tc_act/tc_ct.h>
+
#include "conntrack.h"
#include "../nfp_port.h"
@@ -56,9 +59,17 @@ bool is_pre_ct_flow(struct flow_cls_offload *flow)
int i;
flow_action_for_each(i, act, &flow->rule->action) {
- if (act->id == FLOW_ACTION_CT && !act->ct.action)
- return true;
+ if (act->id == FLOW_ACTION_CT) {
+ /* The pre_ct rule only have the ct or ct nat action, cannot
+ * contains other ct action e.g ct commit and so on.
+ */
+ if ((!act->ct.action || act->ct.action == TCA_CT_ACT_NAT))
+ return true;
+ else
+ return false;
+ }
}
+
return false;
}
@@ -66,13 +77,37 @@ bool is_post_ct_flow(struct flow_cls_offload *flow)
{
struct flow_rule *rule = flow_cls_offload_flow_rule(flow);
struct flow_dissector *dissector = rule->match.dissector;
+ struct flow_action_entry *act;
+ bool exist_ct_clear = false;
struct flow_match_ct ct;
+ int i;
+
+ /* post ct entry cannot contains any ct action except ct_clear. */
+ flow_action_for_each(i, act, &flow->rule->action) {
+ if (act->id == FLOW_ACTION_CT) {
+ /* ignore ct clear action. */
+ if (act->ct.action == TCA_CT_ACT_CLEAR) {
+ exist_ct_clear = true;
+ continue;
+ }
+
+ return false;
+ }
+ }
if (dissector->used_keys & BIT(FLOW_DISSECTOR_KEY_CT)) {
flow_rule_match_ct(rule, &ct);
if (ct.key->ct_state & TCA_FLOWER_KEY_CT_FLAGS_ESTABLISHED)
return true;
+ } else {
+ /* when do nat with ct, the post ct entry ignore the ct status,
+ * will match the nat field(sip/dip) instead. In this situation,
+ * the flow chain index is not zero and contains ct clear action.
+ */
+ if (flow->common.chain_index && exist_ct_clear)
+ return true;
}
+
return false;
}
@@ -168,6 +203,20 @@ static void *get_mangled_tos_ttl(struct flow_rule *rule, void *buf,
return buf;
}
+/* Note entry1 and entry2 are not swappable. only skip ip and
+ * tport merge check for pre_ct and post_ct when pre_ct do nat.
+ */
+static bool nfp_ct_merge_check_cannot_skip(struct nfp_fl_ct_flow_entry *entry1,
+ struct nfp_fl_ct_flow_entry *entry2)
+{
+ /* only pre_ct have NFP_FL_ACTION_DO_NAT flag. */
+ if ((entry1->flags & NFP_FL_ACTION_DO_NAT) &&
+ entry2->type == CT_TYPE_POST_CT)
+ return false;
+
+ return true;
+}
+
/* Note entry1 and entry2 are not swappable, entry1 should be
* the former flow whose mangle action need be taken into account
* if existed, and entry2 should be the latter flow whose action
@@ -225,7 +274,12 @@ static int nfp_ct_merge_check(struct nfp_fl_ct_flow_entry *entry1,
goto check_failed;
}
- if (ovlp_keys & BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS)) {
+ /* if pre ct entry do nat, the nat ip exists in nft entry,
+ * will be do merge check when do nft and post ct merge,
+ * so skip this ip merge check here.
+ */
+ if ((ovlp_keys & BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS)) &&
+ nfp_ct_merge_check_cannot_skip(entry1, entry2)) {
struct flow_match_ipv4_addrs match1, match2;
flow_rule_match_ipv4_addrs(entry1->rule, &match1);
@@ -242,7 +296,12 @@ static int nfp_ct_merge_check(struct nfp_fl_ct_flow_entry *entry1,
goto check_failed;
}
- if (ovlp_keys & BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS)) {
+ /* if pre ct entry do nat, the nat ip exists in nft entry,
+ * will be do merge check when do nft and post ct merge,
+ * so skip this ip merge check here.
+ */
+ if ((ovlp_keys & BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS)) &&
+ nfp_ct_merge_check_cannot_skip(entry1, entry2)) {
struct flow_match_ipv6_addrs match1, match2;
flow_rule_match_ipv6_addrs(entry1->rule, &match1);
@@ -259,7 +318,12 @@ static int nfp_ct_merge_check(struct nfp_fl_ct_flow_entry *entry1,
goto check_failed;
}
- if (ovlp_keys & BIT(FLOW_DISSECTOR_KEY_PORTS)) {
+ /* if pre ct entry do nat, the nat tport exists in nft entry,
+ * will be do merge check when do nft and post ct merge,
+ * so skip this tport merge check here.
+ */
+ if ((ovlp_keys & BIT(FLOW_DISSECTOR_KEY_PORTS)) &&
+ nfp_ct_merge_check_cannot_skip(entry1, entry2)) {
enum flow_action_mangle_base htype = FLOW_ACT_MANGLE_UNSPEC;
struct flow_match_ports match1, match2;
@@ -404,12 +468,55 @@ check_failed:
return -EINVAL;
}
+static int nfp_ct_check_vlan_merge(struct flow_action_entry *a_in,
+ struct flow_rule *rule)
+{
+ struct flow_match_vlan match;
+
+ if (unlikely(flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CVLAN)))
+ return -EOPNOTSUPP;
+
+ /* post_ct does not match VLAN KEY, can be merged. */
+ if (likely(!flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)))
+ return 0;
+
+ switch (a_in->id) {
+ /* pre_ct has pop vlan, post_ct cannot match VLAN KEY, cannot be merged. */
+ case FLOW_ACTION_VLAN_POP:
+ return -EOPNOTSUPP;
+
+ case FLOW_ACTION_VLAN_PUSH:
+ case FLOW_ACTION_VLAN_MANGLE:
+ flow_rule_match_vlan(rule, &match);
+ /* different vlan id, cannot be merged. */
+ if ((match.key->vlan_id & match.mask->vlan_id) ^
+ (a_in->vlan.vid & match.mask->vlan_id))
+ return -EOPNOTSUPP;
+
+ /* different tpid, cannot be merged. */
+ if ((match.key->vlan_tpid & match.mask->vlan_tpid) ^
+ (a_in->vlan.proto & match.mask->vlan_tpid))
+ return -EOPNOTSUPP;
+
+ /* different priority, cannot be merged. */
+ if ((match.key->vlan_priority & match.mask->vlan_priority) ^
+ (a_in->vlan.prio & match.mask->vlan_priority))
+ return -EOPNOTSUPP;
+
+ break;
+ default:
+ return -EOPNOTSUPP;
+ }
+
+ return 0;
+}
+
static int nfp_ct_merge_act_check(struct nfp_fl_ct_flow_entry *pre_ct_entry,
struct nfp_fl_ct_flow_entry *post_ct_entry,
struct nfp_fl_ct_flow_entry *nft_entry)
{
struct flow_action_entry *act;
- int i;
+ int i, err;
/* Check for pre_ct->action conflicts */
flow_action_for_each(i, act, &pre_ct_entry->rule->action) {
@@ -417,6 +524,10 @@ static int nfp_ct_merge_act_check(struct nfp_fl_ct_flow_entry *pre_ct_entry,
case FLOW_ACTION_VLAN_PUSH:
case FLOW_ACTION_VLAN_POP:
case FLOW_ACTION_VLAN_MANGLE:
+ err = nfp_ct_check_vlan_merge(act, post_ct_entry->rule);
+ if (err)
+ return err;
+ break;
case FLOW_ACTION_MPLS_PUSH:
case FLOW_ACTION_MPLS_POP:
case FLOW_ACTION_MPLS_MANGLE:
@@ -468,6 +579,12 @@ static int nfp_ct_check_meta(struct nfp_fl_ct_flow_entry *post_ct_entry,
return -EINVAL;
return 0;
+ } else {
+ /* post_ct with ct clear action will not match the
+ * ct status when nft is nat entry.
+ */
+ if (nft_entry->flags & NFP_FL_ACTION_DO_MANGLE)
+ return 0;
}
return -EINVAL;
@@ -537,11 +654,37 @@ nfp_fl_calc_key_layers_sz(struct nfp_fl_key_ls in_key_ls, uint16_t *map)
return key_size;
}
+/* get the csum flag according the ip proto and mangle action. */
+static void nfp_fl_get_csum_flag(struct flow_action_entry *a_in, u8 ip_proto, u32 *csum)
+{
+ if (a_in->id != FLOW_ACTION_MANGLE)
+ return;
+
+ switch (a_in->mangle.htype) {
+ case FLOW_ACT_MANGLE_HDR_TYPE_IP4:
+ *csum |= TCA_CSUM_UPDATE_FLAG_IPV4HDR;
+ if (ip_proto == IPPROTO_TCP)
+ *csum |= TCA_CSUM_UPDATE_FLAG_TCP;
+ else if (ip_proto == IPPROTO_UDP)
+ *csum |= TCA_CSUM_UPDATE_FLAG_UDP;
+ break;
+ case FLOW_ACT_MANGLE_HDR_TYPE_TCP:
+ *csum |= TCA_CSUM_UPDATE_FLAG_TCP;
+ break;
+ case FLOW_ACT_MANGLE_HDR_TYPE_UDP:
+ *csum |= TCA_CSUM_UPDATE_FLAG_UDP;
+ break;
+ default:
+ break;
+ }
+}
+
static int nfp_fl_merge_actions_offload(struct flow_rule **rules,
struct nfp_flower_priv *priv,
struct net_device *netdev,
struct nfp_fl_payload *flow_pay)
{
+ enum flow_action_hw_stats tmp_stats = FLOW_ACTION_HW_STATS_DONT_CARE;
struct flow_action_entry *a_in;
int i, j, num_actions, id;
struct flow_rule *a_rule;
@@ -551,15 +694,25 @@ static int nfp_fl_merge_actions_offload(struct flow_rule **rules,
rules[CT_TYPE_NFT]->action.num_entries +
rules[CT_TYPE_POST_CT]->action.num_entries;
- a_rule = flow_rule_alloc(num_actions);
+ /* Add one action to make sure there is enough room to add an checksum action
+ * when do nat.
+ */
+ a_rule = flow_rule_alloc(num_actions + 1);
if (!a_rule)
return -ENOMEM;
/* Actions need a BASIC dissector. */
a_rule->match = rules[CT_TYPE_PRE_CT]->match;
+ /* post_ct entry have one action at least. */
+ if (rules[CT_TYPE_POST_CT]->action.num_entries != 0) {
+ tmp_stats = rules[CT_TYPE_POST_CT]->action.entries[0].hw_stats;
+ }
/* Copy actions */
for (j = 0; j < _CT_TYPE_MAX; j++) {
+ u32 csum_updated = 0;
+ u8 ip_proto = 0;
+
if (flow_rule_match_key(rules[j], FLOW_DISSECTOR_KEY_BASIC)) {
struct flow_match_basic match;
@@ -571,8 +724,10 @@ static int nfp_fl_merge_actions_offload(struct flow_rule **rules,
* through the subflows and assign the proper subflow to a_rule
*/
flow_rule_match_basic(rules[j], &match);
- if (match.mask->ip_proto)
+ if (match.mask->ip_proto) {
a_rule->match = rules[j]->match;
+ ip_proto = match.key->ip_proto;
+ }
}
for (i = 0; i < rules[j]->action.num_entries; i++) {
@@ -589,11 +744,32 @@ static int nfp_fl_merge_actions_offload(struct flow_rule **rules,
case FLOW_ACTION_CT_METADATA:
continue;
default:
+ /* nft entry is generated by tc ct, which mangle action do not care
+ * the stats, inherit the post entry stats to meet the
+ * flow_action_hw_stats_check.
+ */
+ if (j == CT_TYPE_NFT) {
+ if (a_in->hw_stats == FLOW_ACTION_HW_STATS_DONT_CARE)
+ a_in->hw_stats = tmp_stats;
+ nfp_fl_get_csum_flag(a_in, ip_proto, &csum_updated);
+ }
memcpy(&a_rule->action.entries[offset++],
a_in, sizeof(struct flow_action_entry));
break;
}
}
+ /* nft entry have mangle action, but do not have checksum action when do NAT,
+ * hardware will automatically fix IPv4 and TCP/UDP checksum. so add an csum action
+ * to meet csum action check.
+ */
+ if (csum_updated) {
+ struct flow_action_entry *csum_action;
+
+ csum_action = &a_rule->action.entries[offset++];
+ csum_action->id = FLOW_ACTION_CSUM;
+ csum_action->csum_flags = csum_updated;
+ csum_action->hw_stats = tmp_stats;
+ }
}
/* Some actions would have been ignored, so update the num_entries field */
@@ -1191,6 +1367,49 @@ static struct net_device *get_netdev_from_rule(struct flow_rule *rule)
return NULL;
}
+static void nfp_nft_ct_translate_mangle_action(struct flow_action_entry *mangle_action)
+{
+ if (mangle_action->id != FLOW_ACTION_MANGLE)
+ return;
+
+ switch (mangle_action->mangle.htype) {
+ case FLOW_ACT_MANGLE_HDR_TYPE_IP4:
+ case FLOW_ACT_MANGLE_HDR_TYPE_IP6:
+ mangle_action->mangle.val = (__force u32)cpu_to_be32(mangle_action->mangle.val);
+ mangle_action->mangle.mask = (__force u32)cpu_to_be32(mangle_action->mangle.mask);
+ return;
+
+ case FLOW_ACT_MANGLE_HDR_TYPE_TCP:
+ case FLOW_ACT_MANGLE_HDR_TYPE_UDP:
+ mangle_action->mangle.val = (__force u16)cpu_to_be16(mangle_action->mangle.val);
+ mangle_action->mangle.mask = (__force u16)cpu_to_be16(mangle_action->mangle.mask);
+ return;
+
+ default:
+ return;
+ }
+}
+
+static int nfp_nft_ct_set_flow_flag(struct flow_action_entry *act,
+ struct nfp_fl_ct_flow_entry *entry)
+{
+ switch (act->id) {
+ case FLOW_ACTION_CT:
+ if (act->ct.action == TCA_CT_ACT_NAT)
+ entry->flags |= NFP_FL_ACTION_DO_NAT;
+ break;
+
+ case FLOW_ACTION_MANGLE:
+ entry->flags |= NFP_FL_ACTION_DO_MANGLE;
+ break;
+
+ default:
+ break;
+ }
+
+ return 0;
+}
+
static struct
nfp_fl_ct_flow_entry *nfp_fl_ct_add_flow(struct nfp_fl_ct_zone_entry *zt,
struct net_device *netdev,
@@ -1257,6 +1476,13 @@ nfp_fl_ct_flow_entry *nfp_fl_ct_add_flow(struct nfp_fl_ct_zone_entry *zt,
new_act = &entry->rule->action.entries[i];
memcpy(new_act, act, sizeof(struct flow_action_entry));
+ /* nft entry mangle field is host byte order, need translate to
+ * network byte order.
+ */
+ if (is_nft)
+ nfp_nft_ct_translate_mangle_action(new_act);
+
+ nfp_nft_ct_set_flow_flag(new_act, entry);
/* Entunnel is a special case, need to allocate and copy
* tunnel info.
*/