7400b06396
If the AVX2 set is available, we can exploit the repetitive
characteristic of this algorithm to provide a fast, vectorised
version by using 256-bit wide AVX2 operations for bucket loads and
bitwise intersections.
In most cases, this implementation consistently outperforms rbtree
set instances despite the fact they are configured to use a given,
single, ranged data type out of the ones used for performance
measurements by the nft_concat_range.sh kselftest.
That script, injecting packets directly on the ingoing device path
with pktgen, reports, averaged over five runs on a single AMD Epyc
7402 thread (3.35GHz, 768 KiB L1D$, 12 MiB L2$), the figures below.
CONFIG_RETPOLINE was not set here.
Note that this is not a fair comparison over hash and rbtree set
types: non-ranged entries (used to have a reference for hash types)
would be matched faster than this, and matching on a single field
only (which is the case for rbtree) is also significantly faster.
However, it's not possible at the moment to choose this set type
for non-ranged entries, and the current implementation also needs
a few minor adjustments in order to match on less than two fields.
---------------.-----------------------------------.------------.
AMD Epyc 7402 | baselines, Mpps | this patch |
1 thread |___________________________________|____________|
3.35GHz | | | | | |
768KiB L1D$ | netdev | hash | rbtree | | |
---------------| hook | no | single | | pipapo |
type entries | drop | ranges | field | pipapo | AVX2 |
---------------|--------|--------|--------|--------|------------|
net,port | | | | | |
1000 | 19.0 | 10.4 | 3.8 | 4.0 | 7.5 +87% |
---------------|--------|--------|--------|--------|------------|
port,net | | | | | |
100 | 18.8 | 10.3 | 5.8 | 6.3 | 8.1 +29% |
---------------|--------|--------|--------|--------|------------|
net6,port | | | | | |
1000 | 16.4 | 7.6 | 1.8 | 2.1 | 4.8 +128% |
---------------|--------|--------|--------|--------|------------|
port,proto | | | | | |
30000 | 19.6 | 11.6 | 3.9 | 0.5 | 2.6 +420% |
---------------|--------|--------|--------|--------|------------|
net6,port,mac | | | | | |
10 | 16.5 | 5.4 | 4.3 | 3.4 | 4.7 +38% |
---------------|--------|--------|--------|--------|------------|
net6,port,mac, | | | | | |
proto 1000 | 16.5 | 5.7 | 1.9 | 1.4 | 3.6 +26% |
---------------|--------|--------|--------|--------|------------|
net,mac | | | | | |
1000 | 19.0 | 8.4 | 3.9 | 2.5 | 6.4 +156% |
---------------'--------'--------'--------'--------'------------'
A similar strategy could be easily reused to implement specialised
versions for other SIMD sets, and I plan to post at least a NEON
version at a later time.
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
217 lines
9.0 KiB
Makefile
217 lines
9.0 KiB
Makefile
# SPDX-License-Identifier: GPL-2.0
|
|
netfilter-objs := core.o nf_log.o nf_queue.o nf_sockopt.o utils.o
|
|
|
|
nf_conntrack-y := nf_conntrack_core.o nf_conntrack_standalone.o nf_conntrack_expect.o nf_conntrack_helper.o \
|
|
nf_conntrack_proto.o nf_conntrack_proto_generic.o nf_conntrack_proto_tcp.o nf_conntrack_proto_udp.o \
|
|
nf_conntrack_proto_icmp.o \
|
|
nf_conntrack_extend.o nf_conntrack_acct.o nf_conntrack_seqadj.o
|
|
|
|
nf_conntrack-$(subst m,y,$(CONFIG_IPV6)) += nf_conntrack_proto_icmpv6.o
|
|
nf_conntrack-$(CONFIG_NF_CONNTRACK_TIMEOUT) += nf_conntrack_timeout.o
|
|
nf_conntrack-$(CONFIG_NF_CONNTRACK_TIMESTAMP) += nf_conntrack_timestamp.o
|
|
nf_conntrack-$(CONFIG_NF_CONNTRACK_EVENTS) += nf_conntrack_ecache.o
|
|
nf_conntrack-$(CONFIG_NF_CONNTRACK_LABELS) += nf_conntrack_labels.o
|
|
nf_conntrack-$(CONFIG_NF_CT_PROTO_DCCP) += nf_conntrack_proto_dccp.o
|
|
nf_conntrack-$(CONFIG_NF_CT_PROTO_SCTP) += nf_conntrack_proto_sctp.o
|
|
nf_conntrack-$(CONFIG_NF_CT_PROTO_GRE) += nf_conntrack_proto_gre.o
|
|
|
|
obj-$(CONFIG_NETFILTER) = netfilter.o
|
|
|
|
obj-$(CONFIG_NETFILTER_NETLINK) += nfnetlink.o
|
|
obj-$(CONFIG_NETFILTER_NETLINK_ACCT) += nfnetlink_acct.o
|
|
obj-$(CONFIG_NETFILTER_NETLINK_QUEUE) += nfnetlink_queue.o
|
|
obj-$(CONFIG_NETFILTER_NETLINK_LOG) += nfnetlink_log.o
|
|
obj-$(CONFIG_NETFILTER_NETLINK_OSF) += nfnetlink_osf.o
|
|
|
|
# connection tracking
|
|
obj-$(CONFIG_NF_CONNTRACK) += nf_conntrack.o
|
|
|
|
# netlink interface for nf_conntrack
|
|
obj-$(CONFIG_NF_CT_NETLINK) += nf_conntrack_netlink.o
|
|
obj-$(CONFIG_NF_CT_NETLINK_TIMEOUT) += nfnetlink_cttimeout.o
|
|
obj-$(CONFIG_NF_CT_NETLINK_HELPER) += nfnetlink_cthelper.o
|
|
|
|
# connection tracking helpers
|
|
nf_conntrack_h323-objs := nf_conntrack_h323_main.o nf_conntrack_h323_asn1.o
|
|
|
|
obj-$(CONFIG_NF_CONNTRACK_AMANDA) += nf_conntrack_amanda.o
|
|
obj-$(CONFIG_NF_CONNTRACK_FTP) += nf_conntrack_ftp.o
|
|
obj-$(CONFIG_NF_CONNTRACK_H323) += nf_conntrack_h323.o
|
|
obj-$(CONFIG_NF_CONNTRACK_IRC) += nf_conntrack_irc.o
|
|
obj-$(CONFIG_NF_CONNTRACK_BROADCAST) += nf_conntrack_broadcast.o
|
|
obj-$(CONFIG_NF_CONNTRACK_NETBIOS_NS) += nf_conntrack_netbios_ns.o
|
|
obj-$(CONFIG_NF_CONNTRACK_SNMP) += nf_conntrack_snmp.o
|
|
obj-$(CONFIG_NF_CONNTRACK_PPTP) += nf_conntrack_pptp.o
|
|
obj-$(CONFIG_NF_CONNTRACK_SANE) += nf_conntrack_sane.o
|
|
obj-$(CONFIG_NF_CONNTRACK_SIP) += nf_conntrack_sip.o
|
|
obj-$(CONFIG_NF_CONNTRACK_TFTP) += nf_conntrack_tftp.o
|
|
|
|
nf_nat-y := nf_nat_core.o nf_nat_proto.o nf_nat_helper.o
|
|
|
|
# generic transport layer logging
|
|
obj-$(CONFIG_NF_LOG_COMMON) += nf_log_common.o
|
|
|
|
# packet logging for netdev family
|
|
obj-$(CONFIG_NF_LOG_NETDEV) += nf_log_netdev.o
|
|
|
|
obj-$(CONFIG_NF_NAT) += nf_nat.o
|
|
nf_nat-$(CONFIG_NF_NAT_REDIRECT) += nf_nat_redirect.o
|
|
nf_nat-$(CONFIG_NF_NAT_MASQUERADE) += nf_nat_masquerade.o
|
|
|
|
# NAT helpers
|
|
obj-$(CONFIG_NF_NAT_AMANDA) += nf_nat_amanda.o
|
|
obj-$(CONFIG_NF_NAT_FTP) += nf_nat_ftp.o
|
|
obj-$(CONFIG_NF_NAT_IRC) += nf_nat_irc.o
|
|
obj-$(CONFIG_NF_NAT_SIP) += nf_nat_sip.o
|
|
obj-$(CONFIG_NF_NAT_TFTP) += nf_nat_tftp.o
|
|
|
|
# SYNPROXY
|
|
obj-$(CONFIG_NETFILTER_SYNPROXY) += nf_synproxy_core.o
|
|
|
|
obj-$(CONFIG_NETFILTER_CONNCOUNT) += nf_conncount.o
|
|
|
|
# generic packet duplication from netdev family
|
|
obj-$(CONFIG_NF_DUP_NETDEV) += nf_dup_netdev.o
|
|
|
|
# nf_tables
|
|
nf_tables-objs := nf_tables_core.o nf_tables_api.o nft_chain_filter.o \
|
|
nf_tables_trace.o nft_immediate.o nft_cmp.o nft_range.o \
|
|
nft_bitwise.o nft_byteorder.o nft_payload.o nft_lookup.o \
|
|
nft_dynset.o nft_meta.o nft_rt.o nft_exthdr.o \
|
|
nft_chain_route.o nf_tables_offload.o \
|
|
nft_set_hash.o nft_set_bitmap.o nft_set_rbtree.o \
|
|
nft_set_pipapo.o
|
|
|
|
ifdef CONFIG_X86_64
|
|
ifneq (,$(findstring -DCONFIG_AS_AVX2=1,$(KBUILD_CFLAGS)))
|
|
nf_tables-objs += nft_set_pipapo_avx2.o
|
|
endif
|
|
endif
|
|
|
|
obj-$(CONFIG_NF_TABLES) += nf_tables.o
|
|
obj-$(CONFIG_NFT_COMPAT) += nft_compat.o
|
|
obj-$(CONFIG_NFT_CONNLIMIT) += nft_connlimit.o
|
|
obj-$(CONFIG_NFT_NUMGEN) += nft_numgen.o
|
|
obj-$(CONFIG_NFT_CT) += nft_ct.o
|
|
obj-$(CONFIG_NFT_FLOW_OFFLOAD) += nft_flow_offload.o
|
|
obj-$(CONFIG_NFT_LIMIT) += nft_limit.o
|
|
obj-$(CONFIG_NFT_NAT) += nft_nat.o
|
|
obj-$(CONFIG_NFT_OBJREF) += nft_objref.o
|
|
obj-$(CONFIG_NFT_QUEUE) += nft_queue.o
|
|
obj-$(CONFIG_NFT_QUOTA) += nft_quota.o
|
|
obj-$(CONFIG_NFT_REJECT) += nft_reject.o
|
|
obj-$(CONFIG_NFT_REJECT_INET) += nft_reject_inet.o
|
|
obj-$(CONFIG_NFT_TUNNEL) += nft_tunnel.o
|
|
obj-$(CONFIG_NFT_COUNTER) += nft_counter.o
|
|
obj-$(CONFIG_NFT_LOG) += nft_log.o
|
|
obj-$(CONFIG_NFT_MASQ) += nft_masq.o
|
|
obj-$(CONFIG_NFT_REDIR) += nft_redir.o
|
|
obj-$(CONFIG_NFT_HASH) += nft_hash.o
|
|
obj-$(CONFIG_NFT_FIB) += nft_fib.o
|
|
obj-$(CONFIG_NFT_FIB_INET) += nft_fib_inet.o
|
|
obj-$(CONFIG_NFT_FIB_NETDEV) += nft_fib_netdev.o
|
|
obj-$(CONFIG_NFT_SOCKET) += nft_socket.o
|
|
obj-$(CONFIG_NFT_OSF) += nft_osf.o
|
|
obj-$(CONFIG_NFT_TPROXY) += nft_tproxy.o
|
|
obj-$(CONFIG_NFT_XFRM) += nft_xfrm.o
|
|
obj-$(CONFIG_NFT_SYNPROXY) += nft_synproxy.o
|
|
|
|
obj-$(CONFIG_NFT_NAT) += nft_chain_nat.o
|
|
|
|
# nf_tables netdev
|
|
obj-$(CONFIG_NFT_DUP_NETDEV) += nft_dup_netdev.o
|
|
obj-$(CONFIG_NFT_FWD_NETDEV) += nft_fwd_netdev.o
|
|
|
|
# flow table infrastructure
|
|
obj-$(CONFIG_NF_FLOW_TABLE) += nf_flow_table.o
|
|
nf_flow_table-objs := nf_flow_table_core.o nf_flow_table_ip.o \
|
|
nf_flow_table_offload.o
|
|
|
|
obj-$(CONFIG_NF_FLOW_TABLE_INET) += nf_flow_table_inet.o
|
|
|
|
# generic X tables
|
|
obj-$(CONFIG_NETFILTER_XTABLES) += x_tables.o xt_tcpudp.o
|
|
|
|
# combos
|
|
obj-$(CONFIG_NETFILTER_XT_MARK) += xt_mark.o
|
|
obj-$(CONFIG_NETFILTER_XT_CONNMARK) += xt_connmark.o
|
|
obj-$(CONFIG_NETFILTER_XT_SET) += xt_set.o
|
|
obj-$(CONFIG_NETFILTER_XT_NAT) += xt_nat.o
|
|
|
|
# targets
|
|
obj-$(CONFIG_NETFILTER_XT_TARGET_AUDIT) += xt_AUDIT.o
|
|
obj-$(CONFIG_NETFILTER_XT_TARGET_CHECKSUM) += xt_CHECKSUM.o
|
|
obj-$(CONFIG_NETFILTER_XT_TARGET_CLASSIFY) += xt_CLASSIFY.o
|
|
obj-$(CONFIG_NETFILTER_XT_TARGET_CONNSECMARK) += xt_CONNSECMARK.o
|
|
obj-$(CONFIG_NETFILTER_XT_TARGET_CT) += xt_CT.o
|
|
obj-$(CONFIG_NETFILTER_XT_TARGET_DSCP) += xt_DSCP.o
|
|
obj-$(CONFIG_NETFILTER_XT_TARGET_HL) += xt_HL.o
|
|
obj-$(CONFIG_NETFILTER_XT_TARGET_HMARK) += xt_HMARK.o
|
|
obj-$(CONFIG_NETFILTER_XT_TARGET_LED) += xt_LED.o
|
|
obj-$(CONFIG_NETFILTER_XT_TARGET_LOG) += xt_LOG.o
|
|
obj-$(CONFIG_NETFILTER_XT_TARGET_NETMAP) += xt_NETMAP.o
|
|
obj-$(CONFIG_NETFILTER_XT_TARGET_NFLOG) += xt_NFLOG.o
|
|
obj-$(CONFIG_NETFILTER_XT_TARGET_NFQUEUE) += xt_NFQUEUE.o
|
|
obj-$(CONFIG_NETFILTER_XT_TARGET_RATEEST) += xt_RATEEST.o
|
|
obj-$(CONFIG_NETFILTER_XT_TARGET_REDIRECT) += xt_REDIRECT.o
|
|
obj-$(CONFIG_NETFILTER_XT_TARGET_MASQUERADE) += xt_MASQUERADE.o
|
|
obj-$(CONFIG_NETFILTER_XT_TARGET_SECMARK) += xt_SECMARK.o
|
|
obj-$(CONFIG_NETFILTER_XT_TARGET_TPROXY) += xt_TPROXY.o
|
|
obj-$(CONFIG_NETFILTER_XT_TARGET_TCPMSS) += xt_TCPMSS.o
|
|
obj-$(CONFIG_NETFILTER_XT_TARGET_TCPOPTSTRIP) += xt_TCPOPTSTRIP.o
|
|
obj-$(CONFIG_NETFILTER_XT_TARGET_TEE) += xt_TEE.o
|
|
obj-$(CONFIG_NETFILTER_XT_TARGET_TRACE) += xt_TRACE.o
|
|
obj-$(CONFIG_NETFILTER_XT_TARGET_IDLETIMER) += xt_IDLETIMER.o
|
|
|
|
# matches
|
|
obj-$(CONFIG_NETFILTER_XT_MATCH_ADDRTYPE) += xt_addrtype.o
|
|
obj-$(CONFIG_NETFILTER_XT_MATCH_BPF) += xt_bpf.o
|
|
obj-$(CONFIG_NETFILTER_XT_MATCH_CLUSTER) += xt_cluster.o
|
|
obj-$(CONFIG_NETFILTER_XT_MATCH_COMMENT) += xt_comment.o
|
|
obj-$(CONFIG_NETFILTER_XT_MATCH_CONNBYTES) += xt_connbytes.o
|
|
obj-$(CONFIG_NETFILTER_XT_MATCH_CONNLABEL) += xt_connlabel.o
|
|
obj-$(CONFIG_NETFILTER_XT_MATCH_CONNLIMIT) += xt_connlimit.o
|
|
obj-$(CONFIG_NETFILTER_XT_MATCH_CONNTRACK) += xt_conntrack.o
|
|
obj-$(CONFIG_NETFILTER_XT_MATCH_CPU) += xt_cpu.o
|
|
obj-$(CONFIG_NETFILTER_XT_MATCH_DCCP) += xt_dccp.o
|
|
obj-$(CONFIG_NETFILTER_XT_MATCH_DEVGROUP) += xt_devgroup.o
|
|
obj-$(CONFIG_NETFILTER_XT_MATCH_DSCP) += xt_dscp.o
|
|
obj-$(CONFIG_NETFILTER_XT_MATCH_ECN) += xt_ecn.o
|
|
obj-$(CONFIG_NETFILTER_XT_MATCH_ESP) += xt_esp.o
|
|
obj-$(CONFIG_NETFILTER_XT_MATCH_HASHLIMIT) += xt_hashlimit.o
|
|
obj-$(CONFIG_NETFILTER_XT_MATCH_HELPER) += xt_helper.o
|
|
obj-$(CONFIG_NETFILTER_XT_MATCH_HL) += xt_hl.o
|
|
obj-$(CONFIG_NETFILTER_XT_MATCH_IPCOMP) += xt_ipcomp.o
|
|
obj-$(CONFIG_NETFILTER_XT_MATCH_IPRANGE) += xt_iprange.o
|
|
obj-$(CONFIG_NETFILTER_XT_MATCH_IPVS) += xt_ipvs.o
|
|
obj-$(CONFIG_NETFILTER_XT_MATCH_L2TP) += xt_l2tp.o
|
|
obj-$(CONFIG_NETFILTER_XT_MATCH_LENGTH) += xt_length.o
|
|
obj-$(CONFIG_NETFILTER_XT_MATCH_LIMIT) += xt_limit.o
|
|
obj-$(CONFIG_NETFILTER_XT_MATCH_MAC) += xt_mac.o
|
|
obj-$(CONFIG_NETFILTER_XT_MATCH_MULTIPORT) += xt_multiport.o
|
|
obj-$(CONFIG_NETFILTER_XT_MATCH_NFACCT) += xt_nfacct.o
|
|
obj-$(CONFIG_NETFILTER_XT_MATCH_OSF) += xt_osf.o
|
|
obj-$(CONFIG_NETFILTER_XT_MATCH_OWNER) += xt_owner.o
|
|
obj-$(CONFIG_NETFILTER_XT_MATCH_CGROUP) += xt_cgroup.o
|
|
obj-$(CONFIG_NETFILTER_XT_MATCH_PHYSDEV) += xt_physdev.o
|
|
obj-$(CONFIG_NETFILTER_XT_MATCH_PKTTYPE) += xt_pkttype.o
|
|
obj-$(CONFIG_NETFILTER_XT_MATCH_POLICY) += xt_policy.o
|
|
obj-$(CONFIG_NETFILTER_XT_MATCH_QUOTA) += xt_quota.o
|
|
obj-$(CONFIG_NETFILTER_XT_MATCH_RATEEST) += xt_rateest.o
|
|
obj-$(CONFIG_NETFILTER_XT_MATCH_REALM) += xt_realm.o
|
|
obj-$(CONFIG_NETFILTER_XT_MATCH_RECENT) += xt_recent.o
|
|
obj-$(CONFIG_NETFILTER_XT_MATCH_SCTP) += xt_sctp.o
|
|
obj-$(CONFIG_NETFILTER_XT_MATCH_SOCKET) += xt_socket.o
|
|
obj-$(CONFIG_NETFILTER_XT_MATCH_STATE) += xt_state.o
|
|
obj-$(CONFIG_NETFILTER_XT_MATCH_STATISTIC) += xt_statistic.o
|
|
obj-$(CONFIG_NETFILTER_XT_MATCH_STRING) += xt_string.o
|
|
obj-$(CONFIG_NETFILTER_XT_MATCH_TCPMSS) += xt_tcpmss.o
|
|
obj-$(CONFIG_NETFILTER_XT_MATCH_TIME) += xt_time.o
|
|
obj-$(CONFIG_NETFILTER_XT_MATCH_U32) += xt_u32.o
|
|
|
|
# ipset
|
|
obj-$(CONFIG_IP_SET) += ipset/
|
|
|
|
# IPVS
|
|
obj-$(CONFIG_IP_VS) += ipvs/
|