linux/include/net
Tim Chen 0856a30409 Scm: Remove unnecessary pid & credential references in Unix socket's send and receive path
Patch series 109f6e39..7361c36c back in 2.6.36 added functionality to
allow credentials to work across pid namespaces for packets sent via
UNIX sockets.  However, the atomic reference counts on pid and
credentials caused plenty of cache bouncing when there are numerous
threads of the same pid sharing a UNIX socket.  This patch mitigates the
problem by eliminating extraneous reference counts on pid and
credentials on both send and receive path of UNIX sockets. I found a 2x
improvement in hackbench's threaded case.

On the receive path in unix_dgram_recvmsg, currently there is an
increment of reference count on pid and credentials in scm_set_cred.
Then there are two decrement of the reference counts.  Once in scm_recv
and once when skb_free_datagram call skb->destructor function
unix_destruct_scm.  One pair of increment and decrement of ref count on
pid and credentials can be eliminated from the receive path.  Until we
destroy the skb, we already set a reference when we created the skb on
the send side.

On the send path, there are two increments of ref count on pid and
credentials, once in scm_send and once in unix_scm_to_skb.  Then there
is a decrement of the reference counts in scm_destroy's call to
scm_destroy_cred at the end of unix_dgram_sendmsg functions.   One pair
of increment and decrement of the reference counts can be removed so we
only need to increment the ref counts once.

By incorporating these changes, for hackbench running on a 4 socket
NHM-EX machine with 40 cores, the execution of hackbench on
50 groups of 20 threads sped up by factor of 2.

Hackbench command used for testing:
./hackbench 50 thread 2000

Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2011-08-24 19:41:13 -07:00
..
9p fs/9p: add 9P2000.L unlinkat operation 2011-07-23 09:32:52 -05:00
bluetooth Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/linville/wireless-next-2.6 into for-davem 2011-07-15 10:05:24 -04:00
caif caif: Add CAIF HSI Link layer driver 2011-06-01 21:15:38 -07:00
irda Fix common misspellings 2011-03-31 11:26:23 -03:00
iucv af_iucv: add HiperSockets transport 2011-08-13 01:10:16 -07:00
netfilter atomic: use <linux/atomic.h> 2011-07-26 16:49:47 -07:00
netns atomic: use <linux/atomic.h> 2011-07-26 16:49:47 -07:00
phonet net: dont hold rtnl mutex during netlink dump callbacks 2011-05-02 15:26:28 -07:00
sctp sctp: Bundle HEAERTBEAT into ASCONF_ACK 2011-08-24 19:41:13 -07:00
tc_act net/sched: add ACT_CSUM action to update packets checksums 2010-08-20 01:42:59 -07:00
act_api.h net: sched: constify tcf_proto and tc_action 2011-07-06 02:52:16 -07:00
addrconf.h ipv6: updates to privacy addresses per RFC 4941. 2011-08-01 18:05:00 -07:00
af_ieee802154.h
af_rxrpc.h net: Remove __KERNEL__ cpp checks from include/net 2011-04-24 10:54:56 -07:00
af_unix.h net: Remove __KERNEL__ cpp checks from include/net 2011-04-24 10:54:56 -07:00
ah.h ipsec: update MAX_AH_AUTH_LEN to support sha512 2011-01-13 21:48:25 -08:00
arp.h net: Add ->neigh_lookup() operation to dst_ops 2011-07-18 00:40:17 -07:00
atmclip.h net: Remove __KERNEL__ cpp checks from include/net 2011-04-24 10:54:56 -07:00
ax25.h atomic: use <linux/atomic.h> 2011-07-26 16:49:47 -07:00
ax88796.h
cfg80211-wext.h cfg80211: remove unused wext handler exports 2011-08-08 14:26:29 -04:00
cfg80211.h nl80211/cfg80211: Add extra IE configuration to AP mode setup 2011-08-12 13:45:04 -04:00
checksum.h
cipso_ipv4.h doc: Update the email address for Paul Moore in various source files 2011-08-01 17:58:33 -07:00
cls_cgroup.h Merge commit 'v2.6.36-rc7' into core/rcu 2010-10-07 09:43:45 +02:00
compat.h net: Add sendmmsg socket system call 2011-05-05 11:10:14 -07:00
datalink.h
dcbevent.h net_dcb: add application notifiers 2010-12-31 10:47:46 -08:00
dcbnl.h dcbnl: Add CEE notification 2011-07-05 23:42:17 -07:00
dn_dev.h decnet: RCU conversion and get rid of dev_base_lock 2010-11-08 13:50:08 -08:00
dn_fib.h decnet: Convert to use flowidn where applicable. 2011-03-12 15:08:55 -08:00
dn_neigh.h
dn_nsp.h net: use __packed annotation 2010-06-03 03:21:52 -07:00
dn_route.h decnet: Convert to use flowidn where applicable. 2011-03-12 15:08:55 -08:00
dn.h decnet: Convert to use flowidn where applicable. 2011-03-12 15:08:55 -08:00
dsa.h
dsfield.h
dst_ops.h net: Add ->neigh_lookup() operation to dst_ops 2011-07-18 00:40:17 -07:00
dst.h rps: Add flag to skb to indicate rxhash is based on L4 tuple 2011-08-17 20:06:03 -07:00
esp.h
ethoc.h
fib_rules.h fib_rules: __rcu annotates ctarget 2010-10-27 11:37:32 -07:00
flow.h atomic: use <linux/atomic.h> 2011-07-26 16:49:47 -07:00
garp.h garp: remove last synchronize_rcu() call 2011-05-12 17:46:56 -04:00
gen_stats.h Fix common misspellings 2011-03-31 11:26:23 -03:00
genetlink.h netlink: advertise incomplete dumps 2011-06-22 16:09:45 -04:00
gre.h PPTP: PPP over IPv4 (Point-to-Point Tunneling Protocol) 2010-08-21 23:05:39 -07:00
icmp.h inetpeer: Move ICMP rate limiting state into inet_peer entries. 2011-02-04 15:59:53 -08:00
ieee80211_radiotap.h mac80211: add MCS information to radiotap 2011-01-28 15:44:29 -05:00
ieee802154_netdev.h
ieee802154.h
if_inet6.h ipv6: updates to privacy addresses per RFC 4941. 2011-08-01 18:05:00 -07:00
inet6_connection_sock.h inet: Pass flowi to ->queue_xmit(). 2011-05-08 15:28:28 -07:00
inet6_hashtables.h tcp: Fix a connect() race with timewait sockets 2009-12-08 20:17:51 -08:00
inet_common.h inet, inet6: make tcp_sendmsg() and tcp_sendpage() through inet_sendmsg() and inet_sendpage() 2010-07-12 20:21:46 -07:00
inet_connection_sock.h ipv4: Make caller provide flowi4 key to inet_csk_route_req(). 2011-05-18 18:32:03 -04:00
inet_ecn.h ipv6: restore correct ECN handling on TCP xmit 2011-05-12 18:52:14 -04:00
inet_frag.h fragment: add fast path for in-order fragments 2010-06-30 13:44:29 -07:00
inet_hashtables.h atomic: use <linux/atomic.h> 2011-07-26 16:49:47 -07:00
inet_sock.h ipv4: route non-local sources for raw socket 2011-08-07 22:52:32 -07:00
inet_timewait_sock.h atomic: use <linux/atomic.h> 2011-07-26 16:49:47 -07:00
inetpeer.h atomic: use <linux/atomic.h> 2011-07-26 16:49:47 -07:00
ip6_checksum.h
ip6_fib.h ipv6: Get rid of rt6i_nexthop macro. 2011-07-17 23:11:35 -07:00
ip6_route.h net: Remove __KERNEL__ cpp checks from include/net 2011-04-24 10:54:56 -07:00
ip6_tunnel.h tunnels: add _rcu annotations 2010-10-25 13:09:45 -07:00
ip_fib.h ipv4: Call fib_select_default() only when actually necessary. 2011-04-14 15:05:22 -07:00
ip_vs.h atomic: use <linux/atomic.h> 2011-07-26 16:49:47 -07:00
ip.h ipv4: Add ip_defrag() agent IP_DEFRAG_AF_PACKET. 2011-07-05 22:34:52 -07:00
ipcomp.h percpu: add __percpu sparse annotations to net 2010-02-16 23:05:38 -08:00
ipconfig.h
ipip.h tunnels: add __rcu annotations 2010-10-27 11:37:32 -07:00
ipv6.h ipv6: make fragment identifications less predictable 2011-07-21 21:25:58 -07:00
ipx.h net: Remove __KERNEL__ cpp checks from include/net 2011-04-24 10:54:56 -07:00
iw_handler.h Fix common misspellings 2011-03-31 11:26:23 -03:00
lapb.h
lib80211.h lib80211: remove exports for functions not called by other modules 2011-08-09 15:42:36 -04:00
llc_c_ac.h
llc_c_ev.h
llc_c_st.h
llc_conn.h llc: use a device based hash table to speed up multicast delivery 2009-12-26 20:43:57 -08:00
llc_if.h
llc_pdu.h bonding,llc: Fix structure sizeof incompatibility for some PDUs 2011-05-13 15:13:24 -04:00
llc_s_ac.h
llc_s_ev.h
llc_s_st.h
llc_sap.h
llc.h atomic: use <linux/atomic.h> 2011-07-26 16:49:47 -07:00
mac80211.h mac80211: remove offchannel_tx API 2011-08-08 16:04:05 -04:00
mip6.h net: use __packed annotation 2010-06-03 03:21:52 -07:00
mld.h ipv6 mcast: Introduce include/net/mld.h for MLD definitions. 2010-04-23 13:35:55 +09:00
ndisc.h net: Remove __KERNEL__ cpp checks from include/net 2011-04-24 10:54:56 -07:00
neighbour.h atomic: use <linux/atomic.h> 2011-07-26 16:49:47 -07:00
net_namespace.h atomic: use <linux/atomic.h> 2011-07-26 16:49:47 -07:00
net_ratelimit.h net: Kill ratelimit.h dependency in linux/net.h 2011-05-27 13:41:33 -04:00
netdma.h
netevent.h net: Remove __KERNEL__ cpp checks from include/net 2011-04-24 10:54:56 -07:00
netlabel.h doc: Update the email address for Paul Moore in various source files 2011-08-01 17:58:33 -07:00
netlink.h netlink: advertise incomplete dumps 2011-06-22 16:09:45 -04:00
netrom.h include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h 2010-03-30 22:02:32 +09:00
nexthop.h
nfc.h NFC: add nfc generic netlink interface 2011-07-05 15:26:57 -04:00
nl802154.h
p8022.h
ping.h net: ping: fix build failure 2011-05-17 14:16:58 -04:00
pkt_cls.h net: Fix range checks in tcf_valid_offset(). 2010-12-21 12:43:16 -08:00
pkt_sched.h net: sched: constify tcf_proto and tc_action 2011-07-06 02:52:16 -07:00
protocol.h net: change netdev->features to u32 2011-01-24 15:32:47 -08:00
psnap.h
raw.h include/net/raw.h: Convert raw_seq_private macro to inline 2010-09-08 13:42:22 -07:00
rawv6.h net: Remove __KERNEL__ cpp checks from include/net 2011-04-24 10:54:56 -07:00
red.h sched: remove unused backlog in RED stats 2011-01-12 19:00:39 -08:00
regulatory.h cfg80211: Fix regulatory bug with multiple cards and delays 2010-11-22 15:48:51 -05:00
request_sock.h tcp: account SYN-ACK timeouts & retransmissions 2010-01-17 19:09:39 -08:00
rose.h rose: Add length checks to CALL_REQUEST parsing 2011-03-27 17:59:04 -07:00
route.h ipv4: Pass explicit destination address to rt_bind_peer(). 2011-05-18 18:42:43 -04:00
rtnetlink.h rtnetlink: Compute and store minimum ifinfo dump size 2011-06-09 20:38:07 -07:00
sch_generic.h net: sched: constify tcf_proto and tc_action 2011-07-06 02:52:16 -07:00
scm.h Scm: Remove unnecessary pid & credential references in Unix socket's send and receive path 2011-08-24 19:41:13 -07:00
secure_seq.h net: Compute protocol sequence numbers and fragment IDs using MD5. 2011-08-06 18:33:19 -07:00
slhc_vj.h
snmp.h snmp: reduce percpu needs by 50% 2011-06-11 16:23:59 -07:00
sock.h rps: Add flag to skb to indicate rxhash is based on L4 tuple 2011-08-17 20:06:03 -07:00
stp.h
tcp_states.h
tcp.h tcp: RFC2988bis + taking RTT sample from 3WHS for the passive open side 2011-06-08 17:05:30 -07:00
timewait_sock.h timewait_sock: Create and use getpeer op. 2010-12-01 18:09:13 -08:00
transp_v6.h net: Remove __KERNEL__ cpp checks from include/net 2011-04-24 10:54:56 -07:00
udp.h udp: Switch to ip_finish_skb 2011-03-01 12:35:03 -08:00
udplite.h udp: Switch to ip_finish_skb 2011-03-01 12:35:03 -08:00
wext.h
wimax.h net: wimax: Remove of unused 'rfkill_input' pointer 2011-06-24 17:50:44 -07:00
wpan-phy.h Fix common misspellings 2011-03-31 11:26:23 -03:00
x25.h X25 remove bkl in subscription ioctls 2010-11-28 11:12:20 -08:00
x25device.h X25: Add if_x25.h and x25 to device identifiers 2010-04-22 16:12:36 -07:00
xfrm.h Merge branch 'master' of master.kernel.org:/pub/scm/linux/kernel/git/davem/net-3.6 2011-05-11 14:26:58 -04:00