linux/net/ipv4
Willem de Bruijn f214f915e7 tcp: enable MSG_ZEROCOPY
Enable support for MSG_ZEROCOPY to the TCP stack. TSO and GSO are
both supported. Only data sent to remote destinations is sent without
copying. Packets looped onto a local destination have their payload
copied to avoid unbounded latency.

Tested:
  A 10x TCP_STREAM between two hosts showed a reduction in netserver
  process cycles by up to 70%, depending on packet size. Systemwide,
  savings are of course much less pronounced, at up to 20% best case.

  msg_zerocopy.sh 4 tcp:

  without zerocopy
    tx=121792 (7600 MB) txc=0 zc=n
    rx=60458 (7600 MB)

  with zerocopy
    tx=286257 (17863 MB) txc=286257 zc=y
    rx=140022 (17863 MB)

  This test opens a pair of sockets over veth, one one calls send with
  64KB and optionally MSG_ZEROCOPY and on the other reads the initial
  bytes. The receiver truncates, so this is strictly an upper bound on
  what is achievable. It is more representative of sending data out of
  a physical NIC (when payload is not touched, either).

Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-08-03 21:37:30 -07:00
..
netfilter netfilter: nf_tables: only allow in/output for arp packets 2017-07-17 17:02:44 +02:00
af_inet.c ipv4: Introduce ipip_offload_init helper function. 2017-08-03 09:27:07 -07:00
ah4.c Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/klassert/ipsec-next 2017-06-23 14:17:31 -04:00
arp.c networking: make skb_put & friends return void pointers 2017-06-16 11:48:39 -04:00
cipso_ipv4.c net, ipv4: convert cipso_v4_doi.refcount from atomic_t to refcount_t 2017-07-04 01:29:04 -07:00
datagram.c
devinet.c net: convert in_device.refcnt from atomic_t to refcount_t 2017-07-01 07:39:08 -07:00
esp4_offload.c esp4/6: Fix GSO path for non-GSO SW-crypto packets 2017-04-19 07:48:57 +02:00
esp4.c net: convert sock.sk_wmem_alloc from atomic_t to refcount_t 2017-07-01 07:39:08 -07:00
fib_frontend.c net: core: Make the FIB notification chain generic 2017-08-03 15:35:59 -07:00
fib_lookup.h net: add extack arg to lwtunnel build state 2017-05-30 11:55:32 -04:00
fib_notifier.c net: fib_rules: Implement notification logic in core 2017-08-03 15:35:59 -07:00
fib_rules.c net: fib_rules: Implement notification logic in core 2017-08-03 15:35:59 -07:00
fib_semantics.c net: core: Make the FIB notification chain generic 2017-08-03 15:35:59 -07:00
fib_trie.c net: core: Make the FIB notification chain generic 2017-08-03 15:35:59 -07:00
fou.c fou: make local function static 2017-05-21 13:42:36 -04:00
gre_demux.c Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net 2016-06-30 05:03:36 -04:00
gre_offload.c net: Remove all references to SKB_GSO_UDP. 2017-07-17 09:52:58 -07:00
icmp.c Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net 2017-06-15 11:59:32 -04:00
igmp.c net: convert ip_mc_list.refcnt from atomic_t to refcount_t 2017-07-01 07:39:08 -07:00
inet_connection_sock.c net: convert sock.sk_refcnt from atomic_t to refcount_t 2017-07-01 07:39:08 -07:00
inet_diag.c tcp: remove early retransmit 2017-01-13 22:37:16 -05:00
inet_fragment.c net: convert inet_frag_queue.refcnt from atomic_t to refcount_t 2017-07-01 07:39:09 -07:00
inet_hashtables.c net: make sk_ehashfn() static 2017-07-03 03:29:14 -07:00
inet_timewait_sock.c net: convert sock.sk_refcnt from atomic_t to refcount_t 2017-07-01 07:39:08 -07:00
inetpeer.c inetpeer: remove AVL implementation in favor of RB tree 2017-07-17 08:59:01 -07:00
ip_forward.c ipv4: allow local fragmentation in ip_finish_output_gso() 2016-11-03 16:10:26 -04:00
ip_fragment.c net: convert inet_frag_queue.refcnt from atomic_t to refcount_t 2017-07-01 07:39:09 -07:00
ip_gre.c net: add netlink_ext_ack argument to rtnl_link_ops.validate 2017-06-26 23:13:22 -04:00
ip_input.c net: Add sysctl to toggle early demux for tcp and udp 2017-03-24 13:17:07 -07:00
ip_options.c Replace <asm/uaccess.h> with <linux/uaccess.h> globally 2016-12-24 11:46:01 -08:00
ip_output.c Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net 2017-07-21 03:38:43 +01:00
ip_sockglue.c do_ip_setsockopt(): don't open-code memdup_user() 2017-06-30 02:04:09 -04:00
ip_tunnel_core.c net: store port/representator id in metadata_dst 2017-06-25 11:42:01 -04:00
ip_tunnel.c ip_tunnel: fix potential issue in ip_tunnel_rcv 2017-06-16 12:01:29 -04:00
ip_vti.c vti: revert flush x-netns xfrm cache when vti interface is removed 2017-07-18 11:13:41 -07:00
ipcomp.c
ipconfig.c networking: convert many more places to skb_put_zero() 2017-06-16 11:48:35 -04:00
ipip.c net: add netlink_ext_ack argument to rtnl_link_ops.validate 2017-06-26 23:13:22 -04:00
ipmr.c net: ipmr: ipmr_get_table() returns NULL 2017-07-12 08:18:46 -07:00
Kconfig Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/klassert/ipsec-next 2017-02-16 21:25:49 -05:00
Makefile tcp: ULP infrastructure 2017-06-15 12:12:40 -04:00
netfilter.c netfilter: use skb_to_full_sk in ip_route_me_harder 2017-02-28 12:49:36 +01:00
ping.c net: convert sock.sk_refcnt from atomic_t to refcount_t 2017-07-01 07:39:08 -07:00
proc.c tcp: remove unused mib counters 2017-07-31 14:37:50 -07:00
protocol.c net: Add sysctl to toggle early demux for tcp and udp 2017-03-24 13:17:07 -07:00
raw_diag.c net: ip, raw_diag -- Use jump for exiting from nested loop 2016-11-03 15:25:26 -04:00
raw.c net: convert sock.sk_refcnt from atomic_t to refcount_t 2017-07-01 07:39:08 -07:00
route.c Add wait_for_random_bytes() and get_random_*_wait() functions so that 2017-07-15 12:44:02 -07:00
syncookies.c ipv4: ipv6: initialize treq->txhash in cookie_v[46]_check() 2017-07-18 11:22:51 -07:00
sysctl_net_ipv4.c tcp: remove low_latency sysctl 2017-07-31 14:37:49 -07:00
tcp_bbr.c tcp_bbr: init pacing rate on first RTT sample 2017-07-15 14:43:29 -07:00
tcp_bic.c tcp: bic, cubic: use tcp_jiffies32 instead of tcp_time_stamp 2017-05-17 16:06:01 -04:00
tcp_cdg.c sched/headers: Prepare for new header dependencies before moving code to <linux/sched/clock.h> 2017-03-02 08:42:27 +01:00
tcp_cong.c bpf: Add support for changing congestion control 2017-07-01 16:15:14 -07:00
tcp_cubic.c tcp: bic, cubic: use tcp_jiffies32 instead of tcp_time_stamp 2017-05-17 16:06:01 -04:00
tcp_dctcp.c Revert "dctcp: update cwnd on congestion event" 2016-12-06 11:34:24 -05:00
tcp_diag.c net: diag: Fix refcnt leak in error path destroying socket 2016-08-23 23:11:36 -07:00
tcp_fastopen.c bpf: Add TCP connection BPF callbacks 2017-07-01 16:15:14 -07:00
tcp_highspeed.c tcp: add cwnd_undo functions to various tcp cc algorithms 2016-11-21 13:20:17 -05:00
tcp_htcp.c tcp: replace misc tcp_time_stamp to tcp_jiffies32 2017-05-17 16:06:01 -04:00
tcp_hybla.c tcp: make undo_cwnd mandatory for congestion modules 2016-11-21 13:20:17 -05:00
tcp_illinois.c tcp: add cwnd_undo functions to various tcp cc algorithms 2016-11-21 13:20:17 -05:00
tcp_input.c tcp: remove extra POLL_OUT added for finished active connect() 2017-08-03 09:30:47 -07:00
tcp_ipv4.c tcp: remove low_latency sysctl 2017-07-31 14:37:49 -07:00
tcp_lp.c tcp: switch TCP TS option (RFC 7323) to 1ms clock 2017-05-17 16:06:01 -04:00
tcp_metrics.c tcp: use tcp_jiffies32 to feed tp->snd_cwnd_stamp 2017-05-17 16:06:01 -04:00
tcp_minisocks.c tcp: remove header prediction 2017-07-31 14:37:49 -07:00
tcp_nv.c tcpnv: do not export local function 2017-05-21 13:42:36 -04:00
tcp_offload.c net: convert sock.sk_wmem_alloc from atomic_t to refcount_t 2017-07-01 07:39:08 -07:00
tcp_output.c Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net 2017-08-01 10:07:50 -07:00
tcp_probe.c tcp: remove redundant argument from tcp_rcv_established() 2017-07-24 17:28:12 -07:00
tcp_rate.c tcp: export do_tcp_sendpages and tcp_rate_check_app_limited functions 2017-06-15 12:12:40 -04:00
tcp_recovery.c tcp: adjust tail loss probe timeout 2017-07-19 16:14:10 -07:00
tcp_scalable.c tcp: add cwnd_undo functions to various tcp cc algorithms 2016-11-21 13:20:17 -05:00
tcp_timer.c tcp: remove prequeue support 2017-07-31 14:37:49 -07:00
tcp_ulp.c tcp: fix out-of-bounds access in ULP sysctl 2017-06-23 14:10:05 -04:00
tcp_vegas.c tcp: make undo_cwnd mandatory for congestion modules 2016-11-21 13:20:17 -05:00
tcp_vegas.h
tcp_veno.c tcp: add cwnd_undo functions to various tcp cc algorithms 2016-11-21 13:20:17 -05:00
tcp_westwood.c tcp: remove CA_ACK_SLOWPATH 2017-07-31 14:37:50 -07:00
tcp_yeah.c tcp: add cwnd_undo functions to various tcp cc algorithms 2016-11-21 13:20:17 -05:00
tcp.c tcp: enable MSG_ZEROCOPY 2017-08-03 21:37:30 -07:00
tunnel4.c tunnels: correct conditional build of MPLS and IPv6 2016-07-11 13:27:06 -07:00
udp_diag.c net: convert sock.sk_refcnt from atomic_t to refcount_t 2017-07-01 07:39:08 -07:00
udp_impl.h udp: make *udp*_queue_rcv_skb() functions static 2017-05-18 10:23:33 -04:00
udp_offload.c inet: Remove software UFO fragmenting code. 2017-07-17 09:52:58 -07:00
udp_tunnel.c net: add infrastructure to un-offload UDP tunnel port 2017-07-24 13:52:59 -07:00
udp.c udp6: fix socket leak on early demux 2017-07-29 14:19:03 -07:00
udplite.c udplite: call proper backlog handlers 2016-11-24 15:32:14 -05:00
xfrm4_input.c esp: Add a software GRO codepath 2017-02-15 11:04:11 +01:00
xfrm4_mode_beet.c networking: make skb_pull & friends return void pointers 2017-06-16 11:48:39 -04:00
xfrm4_mode_transport.c xfrm: Add encapsulation header offsets while SKB is not encrypted 2017-04-14 10:07:39 +02:00
xfrm4_mode_tunnel.c xfrm: Add encapsulation header offsets while SKB is not encrypted 2017-04-14 10:07:39 +02:00
xfrm4_output.c xfrm: Add an IPsec hardware offloading API 2017-04-14 10:06:10 +02:00
xfrm4_policy.c xfrm: remove flow cache 2017-07-18 11:13:41 -07:00
xfrm4_protocol.c xfrm: input: constify xfrm_input_afinfo 2017-02-09 10:22:17 +01:00
xfrm4_state.c xfrm: remove unused function 2017-01-10 10:57:12 +01:00
xfrm4_tunnel.c