summaryrefslogtreecommitdiff
path: root/net
AgeCommit message (Collapse)AuthorFilesLines
2011-03-01udp: Add lockless transmit pathHerbert Xu1-1/+14
The UDP transmit path has been running under the socket lock for a long time because of the corking feature. This means that transmitting to the same socket in multiple threads does not scale at all. However, as most users don't actually use corking, the locking can be removed in the common case. This patch creates a lockless fast path where corking is not used. Please note that this does create a slight inaccuracy in the enforcement of socket send buffer limits. In particular, we may exceed the socket limit by up to (number of CPUs) * (packet size) because of the way the limit is computed. As the primary purpose of socket buffers is to indicate congestion, this should not be a great problem for now. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Acked-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-03-01udp: Switch to ip_finish_skbHerbert Xu1-33/+50
This patch converts UDP to use the new ip_finish_skb API. This would then allows us to more easily use ip_make_skb which allows UDP to run without a socket lock. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Acked-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-03-01inet: Add ip_make_skb and ip_finish_skbHerbert Xu1-14/+51
This patch adds the helper ip_make_skb which is like ip_append_data and ip_push_pending_frames all rolled into one, except that it does not send the skb produced. The sending part is carried out by ip_send_skb, which the transport protocol can call after it has tweaked the skb. It is meant to be called in cases where corking is not used should have a one-to-one correspondence to sendmsg. This patch also adds the helper ip_finish_skb which is meant to be replace ip_push_pending_frames when corking is required. Previously the protocol stack would peek at the socket write queue and add its header to the first packet. With ip_finish_skb, the protocol stack can directly operate on the final skb instead, just like the non-corking case with ip_make_skb. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Acked-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-03-01inet: Remove explicit write references to sk/inet in ip_append_dataHerbert Xu1-98/+140
In order to allow simultaneous calls to ip_append_data on the same socket, it must not modify any shared state in sk or inet (other than those that are designed to allow that such as atomic counters). This patch abstracts out write references to sk and inet_sk in ip_append_data and its friends so that we may use the underlying code in parallel. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Acked-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-03-01inet: Remove unused sk_sndmsg_* from UFOHerbert Xu3-5/+0
UFO doesn't really use the sk_sndmsg_* parameters so touching them is pointless. It can't use them anyway since the whole point of UFO is to use the original pages without copying. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Acked-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-02-28net: TX timestamps for IPv6 UDP packetsAnders Berggren1-0/+17
Enabling TX timestamps (SO_TIMESTAMPING) for IPv6 UDP packets, in the same fashion as for IPv4. Necessary in order for NICs such as Intel 82580 to timestamp IPv6 packets. Signed-off-by: Anders Berggren <anders@halon.se> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-02-28llc: avoid skb_clone() if there is only one handlerChangli Gao1-12/+13
Signed-off-by: Changli Gao <xiaosuo@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-02-28net: Forgot to commit net/core/dev.c part of Jiri's ->rx_handler patch.David S. Miller1-88/+31
Signed-off-by: David S. Miller <davem@davemloft.net>
2011-02-28xfrm: Pass const xfrm_address_t objects to xfrm_state_lookup* and xfrm_find_acq.David S. Miller1-4/+8
Signed-off-by: David S. Miller <davem@davemloft.net>
2011-02-28xfrm: Pass name as const to xfrm_*_get_byname().David S. Miller2-5/+5
Signed-off-by: David S. Miller <davem@davemloft.net>
2011-02-28bond: service netpoll arp queue on master deviceAmerigo Wang1-0/+11
Neil pointed out that we can't send ARP reply on behalf of slaves, we need to move the arp queue to their bond device. Signed-off-by: WANG Cong <amwang@redhat.com> Acked-by: Neil Horman <nhorman@tuxdriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-02-28netpoll: remove IFF_IN_NETPOLL flagAmerigo Wang1-2/+0
V4: rebase to net-next-2.6 This patch removes the flag IFF_IN_NETPOLL, we don't need it any more since we have netpoll_tx_running() now. Signed-off-by: WANG Cong <amwang@redhat.com> Acked-by: Neil Horman <nhorman@tuxdriver.com> Cc: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-02-26pfkey: Use const where possible.David S. Miller1-94/+107
This actually pointed out a (seemingly known) bug where we mangle the pfkey header in a potentially shared SKB, which is fixed here. Signed-off-by: David S. Miller <davem@davemloft.net>
2011-02-26sched: protocol only needed when CONFIG_NET_CLS_ACT is enabledHagen Paul Pfeifer1-2/+2
Signed-off-by: Hagen Paul Pfeifer <hagen@jauu.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-02-26ipv6: ignore rtnl_unicast() return codeHagen Paul Pfeifer1-2/+1
rtnl_unicast() return value is not of interest, we can silently ignore it, save some instructions and four byte on the stack. Signed-off-by: Hagen Paul Pfeifer <hagen@jauu.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-02-26ipv6: variable next is never used in this functionHagen Paul Pfeifer1-3/+1
Signed-off-by: Hagen Paul Pfeifer <hagen@jauu.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-02-26ipv6: hash is calculated but not used afterwardsHagen Paul Pfeifer1-3/+0
hash is declared and assigned but not used anymore. ipv6_addr_hash() exhibit no side-effects. Signed-off-by: Hagen Paul Pfeifer <hagen@jauu.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-02-26ipv6: totlen is declared and assigned but not usedHagen Paul Pfeifer1-3/+0
Signed-off-by: Hagen Paul Pfeifer <hagen@jauu.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-02-26dccp: newdp is declared/assigned but never be usedHagen Paul Pfeifer1-3/+0
Declaration and assignment of newdp is removed. Usage of dccp_sk() exhibit no side effects. Signed-off-by: Hagen Paul Pfeifer <hagen@jauu.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-02-25phonet: Protect pipe_do_remove() with appropriate ifdefs.David S. Miller1-0/+2
It is only used when CONFIG_PHONET_PIPECTRLR is not set. Signed-off-by: David S. Miller <davem@davemloft.net>
2011-02-25Phonet: fix flawed "SYN/ACK" logicRémi Denis-Courmont1-78/+47
* Do not fail if the peer supports more or less than 3 algorithms. * Ignore unknown congestion control algorithms instead of failing. * Simplify congestion algorithm negotiation (largest is best). * Do not use a static buffer. * Fix off-by-two read overflow. * Avoid extra memory copy (in addition to skb_copy_bits()). The previous code really made no sense. Signed-off-by: Rémi Denis-Courmont <remi.denis-courmont@nokia.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-02-25Phonet: don't bother with transaction IDs (especially for indications)Rémi Denis-Courmont1-35/+14
Signed-off-by: Rémi Denis-Courmont <remi.denis-courmont@nokia.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-02-25Phonet: remove redumdant pep->pipe_stateRémi Denis-Courmont1-19/+6
sk->sk_state already contains the pipe state. Signed-off-by: Rémi Denis-Courmont <remi.denis-courmont@nokia.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-02-25Phonet: use socket destination in pipe protocolRémi Denis-Courmont1-25/+16
Signed-off-by: Rémi Denis-Courmont <remi.denis-courmont@nokia.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-02-25Phonet: implement per-socket destination/peer addressRémi Denis-Courmont2-7/+16
Signed-off-by: Rémi Denis-Courmont <remi.denis-courmont@nokia.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-02-25Phonet: allow multiple listen() and fix small race conditionRémi Denis-Courmont1-5/+5
Signed-off-by: Rémi Denis-Courmont <remi.denis-courmont@nokia.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-02-25sch_netem: Need to include vmalloc.hDavid S. Miller1-0/+1
Signed-off-by: David S. Miller <davem@davemloft.net>
2011-02-25Merge branch 'for-davem' of ↵David S. Miller31-1452/+3849
git://git.kernel.org/pub/scm/linux/kernel/git/linville/wireless-next-2.6
2011-02-25sch_choke: add choke_skb_cbEric Dumazet1-2/+13
Better document choke skb->cb[] use, like we did in netem and sfb This adds a compile time check to make sure we dont exhaust skb->cb[] space. Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> CC: Stephen Hemminger <shemminger@vyatta.com> CC: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-02-25netem: update version and cleanupstephen hemminger1-6/+4
Get rid of debug message that are not useful, and enable the log messages in case of error. Signed-off-by: Stephen Hemminger <shemminger@vyatta.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-02-25netem: revised correlated loss generatorstephen hemminger1-4/+270
This is a patch originated with Stefano Salsano and Fabio Ludovici. It provides several alternative loss models for use with netem. This patch adds two state machine based loss models. See: http://netgroup.uniroma2.it/twiki/bin/view.cgi/Main/NetemCLG Signed-off-by: Stephen Hemminger <shemminger@vyatta.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-02-25Revert "sch_netem: Remove classful functionality"stephen hemminger1-8/+79
Many users have wanted the old functionality that was lost to be able to use pfifo as inner qdisc for netem. The reason that netem could not be classful with the older API was because of the limitations of the old dequeue/requeue interface; now that qdisc API has a peek function, there is no longer a problem with using any inner qdisc's. This reverts commit 02201464119334690fe209849843881b8e9cfa9f. Signed-off-by: Stephen Hemminger <shemminger@vyatta.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-02-25netem: define NETEM_DIST_MAXstephen hemminger1-1/+1
Rather than magic constant in code, expose the maximum size of packet distribution table in API. In iproute2, q_netem defines MAX_DIST as 16K already. Signed-off-by: Stephen Hemminger <shemminger@vyatta.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-02-25netem: use vmalloc for distribution tablestephen hemminger1-4/+18
The netem probability table can be large (up to 64K bytes) which may be too large to allocate in one contiguous chunk. Signed-off-by: Stephen Hemminger <shemminger@vyatta.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-02-25netem: cleanup dump codestephen hemminger1-6/+3
Use nla_put_nested to update netlink attribute value. Signed-off-by: Stephen Hemminger <shemminger@vyatta.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-02-25ipv4: Rearrange how ip_route_newports() gets port keys.David S. Miller2-4/+12
ip_route_newports() is the only place in the entire kernel that cares about the port members in the routing cache entry's lookup flow key. Therefore the only reason we store an entire flow inside of the struct rtentry is for this one special case. Rewrite ip_route_newports() such that: 1) The caller passes in the original port values, so we don't need to use the rth->fl.fl_ip_{s,d}port values to remember them. 2) The lookup flow is constructed by hand instead of being copied from the routing cache entry's flow. Signed-off-by: David S. Miller <davem@davemloft.net>
2011-02-24xfrm: Const'ify xfrm_address_t args to xfrm_state_find.David S. Miller1-2/+2
This required a const'ification in xfrm_init_tempstate() too. Signed-off-by: David S. Miller <davem@davemloft.net>
2011-02-24xfrm: Remove unused 'saddr' and 'daddr' args to xfrm_state_look_at.David S. Miller1-3/+2
Signed-off-by: David S. Miller <davem@davemloft.net>
2011-02-24xfrm: Const'ify xfrm_address_t args to __xfrm_state_lookup{,_byaddr}.David S. Miller1-2/+8
Signed-off-by: David S. Miller <davem@davemloft.net>
2011-02-24xfrm: Const'ify xfrm_tmpl arg to xfrm_init_tempstate.David S. Miller1-1/+1
Signed-off-by: David S. Miller <davem@davemloft.net>
2011-02-24xfrm: Const'ify xfrm_address_t args to xfrm_*_hash.David S. Miller1-5/+6
Signed-off-by: David S. Miller <davem@davemloft.net>
2011-02-24xfrm: Const'ify sec_path arg to secpath_has_nontransport.David S. Miller1-1/+1
Signed-off-by: David S. Miller <davem@davemloft.net>
2011-02-24xfrm: Const'ify ptr args to xfrm_policy_ok.David S. Miller1-1/+1
Signed-off-by: David S. Miller <davem@davemloft.net>
2011-02-24xfrm: Const'ify ptr args to xfrm_state_ok.David S. Miller1-1/+1
Signed-off-by: David S. Miller <davem@davemloft.net>
2011-02-24xfrm: Const'ify selector arg to xfrm_dst_update_parent.David S. Miller1-1/+1
Signed-off-by: David S. Miller <davem@davemloft.net>
2011-02-24xfrm: Const'ify policy arg to clone_policy.David S. Miller1-1/+1
Signed-off-by: David S. Miller <davem@davemloft.net>
2011-02-24xfrm: Const'ify policy arg and local selector in xfrm_policy_match.David S. Miller1-2/+3
Signed-off-by: David S. Miller <davem@davemloft.net>
2011-02-24xfrm: Const'ify local xfrm_address_t pointers in xfrm_policy_lookup_bytype.David S. Miller1-1/+1
Signed-off-by: David S. Miller <davem@davemloft.net>
2011-02-24xfrm: Const'ify selector args in xfrm_migrate paths.David S. Miller1-4/+4
Signed-off-by: David S. Miller <davem@davemloft.net>
2011-02-24xfrm: Const'ify address args to hash helpers.David S. Miller2-15/+26
Signed-off-by: David S. Miller <davem@davemloft.net>
generated by cgit v1.2.3 (git 2.39.0) at 2025-01-18 20:53:31 +0300