summaryrefslogtreecommitdiffstats
path: root/net/ipv4 (follow)
Commit message (Collapse)AuthorAgeFilesLines
* atm: clip: Use device neigh support on top of "arp_tbl".David Miller2011-12-012-13/+2
| | | | | | | Instead of instantiating an entire new neigh_table instance just for ATM handling, use the neigh device private facility. Signed-off-by: David S. Miller <davem@davemloft.net>
* neigh: Do not set tbl->entry_size in ipv4/ipv6 neigh tables.David Miller2011-12-011-1/+0
| | | | | | Let the core self-size the neigh entry based upon the key length. Signed-off-by: David S. Miller <davem@davemloft.net>
* tcp: inherit listener congestion control for passive cnxEric Dumazet2011-11-302-1/+4
| | | | | | | | | | | | | | | | | Rick Jones reported that TCP_CONGESTION sockopt performed on a listener was ignored for its children sockets : right after accept() the congestion control for new socket is the system default one. This seems an oversight of the initial design (quoted from Stephen) Based on prior investigation and patch from Rick. Reported-by: Rick Jones <rick.jones2@hp.com> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> CC: Stephen Hemminger <shemminger@vyatta.com> CC: Yuchung Cheng <ycheng@google.com> Tested-by: Rick Jones <rick.jones2@hp.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* ipv4: remove useless codes in ipmr_device_event()RongQing.Li2011-11-301-3/+1
| | | | | | | | | | | Commit 7dc00c82 added a 'notify' parameter for vif_delete() to distinguish whether to unregister the device. When notify=1 means we does not need to unregister the device, so calling unregister_netdevice_many is useless. Signed-off-by: RongQing.Li <roy.qing.li@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* tcp: avoid frag allocation for small framesEric Dumazet2011-11-291-3/+6
| | | | | | | | | | | | | | | | | | | | | | | | | | | tcp_sendmsg() uses select_size() helper to choose skb head size when a new skb must be allocated. If GSO is enabled for the socket, current strategy is to force all payload data to be outside of headroom, in PAGE fragments. This strategy is not welcome for small packets, wasting memory. Experiments show that best results are obtained when using 2048 bytes for skb head (This includes the skb overhead and various headers) This patch provides better len/truesize ratios for packets sent to loopback device, and reduce memory needs for in-flight loopback packets, particularly on arches with big pages. If a sender sends many 1-byte packets to an unresponsive application, receiver rmem_alloc will grow faster and will stop queuing these packets sooner, or will collapse its receive queue to free excess memory. netperf -t TCP_RR results are improved by ~4 %, and many workloads are improved as well (tbench, mysql...) Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* tcp: do not scale TSO segment size with reordering degreeNeal Cardwell2011-11-292-2/+2
| | | | | | | | | | | | | | | | Since 2005 (c1b4a7e69576d65efc31a8cea0714173c2841244) tcp_tso_should_defer has been using tcp_max_burst() as a target limit for deciding how large to make outgoing TSO packets when not using sysctl_tcp_tso_win_divisor. But since 2008 (dd9e0dda66ba38a2ddd1405ac279894260dc5c36) tcp_max_burst() returns the reordering degree. We should not have tcp_tso_should_defer attempt to build larger segments just because there is more reordering. This commit splits the notion of deferral size used in TSO from the notion of burst size used in cwnd moderation, and returns the TSO deferral limit to its original value. Signed-off-by: Neal Cardwell <ncardwell@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* net: dont call jump_label_dec from irq contextEric Dumazet2011-11-291-2/+4
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Igor Maravic reported an error caused by jump_label_dec() being called from IRQ context : BUG: sleeping function called from invalid context at kernel/mutex.c:271 in_atomic(): 1, irqs_disabled(): 0, pid: 0, name: swapper 1 lock held by swapper/0: #0: (&n->timer){+.-...}, at: [<ffffffff8107ce90>] call_timer_fn+0x0/0x340 Pid: 0, comm: swapper Not tainted 3.2.0-rc2-net-next-mpls+ #1 Call Trace: <IRQ> [<ffffffff8104f417>] __might_sleep+0x137/0x1f0 [<ffffffff816b9a2f>] mutex_lock_nested+0x2f/0x370 [<ffffffff810a89fd>] ? trace_hardirqs_off+0xd/0x10 [<ffffffff8109a37f>] ? local_clock+0x6f/0x80 [<ffffffff810a90a5>] ? lock_release_holdtime.part.22+0x15/0x1a0 [<ffffffff81557929>] ? sock_def_write_space+0x59/0x160 [<ffffffff815e936e>] ? arp_error_report+0x3e/0x90 [<ffffffff810969cd>] atomic_dec_and_mutex_lock+0x5d/0x80 [<ffffffff8112fc1d>] jump_label_dec+0x1d/0x50 [<ffffffff81566525>] net_disable_timestamp+0x15/0x20 [<ffffffff81557a75>] sock_disable_timestamp+0x45/0x50 [<ffffffff81557b00>] __sk_free+0x80/0x200 [<ffffffff815578d0>] ? sk_send_sigurg+0x70/0x70 [<ffffffff815e936e>] ? arp_error_report+0x3e/0x90 [<ffffffff81557cba>] sock_wfree+0x3a/0x70 [<ffffffff8155c2b0>] skb_release_head_state+0x70/0x120 [<ffffffff8155c0b6>] __kfree_skb+0x16/0x30 [<ffffffff8155c119>] kfree_skb+0x49/0x170 [<ffffffff815e936e>] arp_error_report+0x3e/0x90 [<ffffffff81575bd9>] neigh_invalidate+0x89/0xc0 [<ffffffff81578dbe>] neigh_timer_handler+0x9e/0x2a0 [<ffffffff81578d20>] ? neigh_update+0x640/0x640 [<ffffffff81073558>] __do_softirq+0xc8/0x3a0 Since jump_label_{inc|dec} must be called from process context only, we must defer jump_label_dec() if net_disable_timestamp() is called from interrupt context. Reported-by: Igor Maravic <igorm@etf.rs> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* tcp: tcp_sendmsg() wrong access to sk_route_capsEric Dumazet2011-11-291-4/+4
| | | | | | | | | | Now sk_route_caps is u64, its dangerous to use an integer to store result of an AND operator. It wont work if NETIF_F_SG is moved on the upper part of u64. Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> CC: Michał Mirosław <mirq-linux@rere.qmqm.pl> Signed-off-by: David S. Miller <davem@davemloft.net>
* tcp: skip cwnd moderation in TCP_CA_Open in tcp_try_to_openNeal Cardwell2011-11-281-1/+2
| | | | | | | | | | | | | The problem: Senders were overriding cwnd values picked during an undo by calling tcp_moderate_cwnd() in tcp_try_to_open(). The fix: Don't moderate cwnd in tcp_try_to_open() if we're in TCP_CA_Open, since doing so is generally unnecessary and specifically would override a DSACK-based undo of a cwnd reduction made in fast recovery. Signed-off-by: Neal Cardwell <ncardwell@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* tcp: allow undo from reordered DSACKsNeal Cardwell2011-11-281-13/+2
| | | | | | | | | | | | | | | | | | | | | | | | Previously, SACK-enabled connections hung around in TCP_CA_Disorder state while snd_una==high_seq, just waiting to accumulate DSACKs and hopefully undo a cwnd reduction. This could and did lead to the following unfortunate scenario: if some incoming ACKs advance snd_una beyond high_seq then we were setting undo_marker to 0 and moving to TCP_CA_Open, so if (due to reordering in the ACK return path) we shortly thereafter received a DSACK then we were no longer able to undo the cwnd reduction. The change: Simplify the congestion avoidance state machine by removing the behavior where SACK-enabled connections hung around in the TCP_CA_Disorder state just waiting for DSACKs. Instead, when snd_una advances to high_seq or beyond we typically move to TCP_CA_Open immediately and allow an undo in either TCP_CA_Open or TCP_CA_Disorder if we later receive enough DSACKs. Other patches in this series will provide other changes that are necessary to fully fix this problem. Signed-off-by: Neal Cardwell <ncardwell@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* tcp: use SACKs and DSACKs that arrive on ACKs below snd_unaNeal Cardwell2011-11-281-3/+7
| | | | | | | | | | | | | | | | | | | | | The bug: When the ACK field is below snd_una (which can happen when ACKs are reordered), senders ignored DSACKs (preventing undo) and did not call tcp_fastretrans_alert, so they did not increment prr_delivered to reflect newly-SACKed sequence ranges, and did not call tcp_xmit_retransmit_queue, thus passing up chances to send out more retransmitted and new packets based on any newly-SACKed packets. The change: When the ACK field is below snd_una (the "old_ack" goto label), call tcp_fastretrans_alert to allow undo based on any newly-arrived DSACKs and try to send out more packets based on newly-SACKed packets. Other patches in this series will provide other changes that are necessary to fully fix this problem. Signed-off-by: Neal Cardwell <ncardwell@google.com> Acked-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi> Signed-off-by: David S. Miller <davem@davemloft.net>
* tcp: use DSACKs that arrive when packets_out is 0Neal Cardwell2011-11-281-0/+4
| | | | | | | | | | | | | | | | The bug: Senders ignored DSACKs after recovery when there were no outstanding packets (a common scenario for HTTP servers). The change: when there are no outstanding packets (the "no_queue" goto label), call tcp_fastretrans_alert() in order to use DSACKs to undo congestion window reductions. Other patches in this series will provide other changes that are necessary to fully fix this problem. Signed-off-by: Neal Cardwell <ncardwell@google.com> Acked-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi> Signed-off-by: David S. Miller <davem@davemloft.net>
* tcp: make is_dupack a parameter to tcp_fastretrans_alert()Neal Cardwell2011-11-281-4/+8
| | | | | | | | | | | Allow callers to decide whether an ACK is a duplicate ACK. This is a prerequisite to allowing fastretrans_alert to be called from new contexts, such as the no_queue and old_ack code paths, from which we have extra info that tells us whether an ACK is a dupack. Signed-off-by: Neal Cardwell <ncardwell@google.com> Acked-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi> Signed-off-by: David S. Miller <davem@davemloft.net>
* Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/netDavid S. Miller2011-11-266-16/+27
|\ | | | | | | | | Conflicts: net/ipv4/inet_diag.c
| * ipv4: Don't use the cached pmtu informations for input routesSteffen Klassert2011-11-261-2/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | The pmtu informations on the inetpeer are visible for output and input routes. On packet forwarding, we might propagate a learned pmtu to the sender. As we update the pmtu informations of the inetpeer on demand, the original sender of the forwarded packets might never notice when the pmtu to that inetpeer increases. So use the mtu of the outgoing device on packet forwarding instead of the pmtu to the final destination. Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * net: Move mtu handling down to the protocol depended handlersSteffen Klassert2011-11-261-2/+9
| | | | | | | | | | | | | | | | | | We move all mtu handling from dst_mtu() down to the protocol layer. So each protocol can implement the mtu handling in a different manner. Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * net: Rename the dst_opt default_mtu method to mtuSteffen Klassert2011-11-261-5/+5
| | | | | | | | | | | | | | | | | | We plan to invoke the dst_opt->default_mtu() method unconditioally from dst_mtu(). So rename the method to dst_opt->mtu() to match the name with the new meaning. Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * route: Use the device mtu as the default for blackhole routesSteffen Klassert2011-11-261-1/+1
| | | | | | | | | | | | | | | | | | | | As it is, we return null as the default mtu of blackhole routes. This may lead to a propagation of a bogus pmtu if the default_mtu method of a blackhole route is invoked. So return dst->dev->mtu as the default mtu instead. Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * ipv4: Save nexthop address of LSRR/SSRR option to IPCB.Li Wei2011-11-242-3/+4
| | | | | | | | | | | | | | | | | | | | | | | | | | We can not update iph->daddr in ip_options_rcv_srr(), It is too early. When some exception ocurred later (eg. in ip_forward() when goto sr_failed) we need the ip header be identical to the original one as ICMP need it. Add a field 'nexthop' in struct ip_options to save nexthop of LSRR or SSRR option. Signed-off-by: Li Wei <lw@cn.fujitsu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * ipv4 : igmp : fix error handle in ip_mc_add_src()Jun Zhao2011-11-231-1/+2
| | | | | | | | | | | | | | | | | | | | When add sources to interface failure, need to roll back the sfcount[MODE] to before state. We need to match it corresponding. Acked-by: David L Stevens <dlstevens@us.ibm.com> Acked-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: Jun Zhao <mypopydev@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * netfilter: Remove NOTRACK/RAW dependency on NETFILTER_ADVANCED.David S. Miller2011-11-231-1/+0
| | | | | | | | | | | | | | | | Distributions are using this in their default scripts, so don't hide them behind the advanced setting. Reported-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: David S. Miller <davem@davemloft.net>
| * net-netlink: fix diag to export IPv4 tos for dual-stack IPv6 socketsMaciej Żenczykowski2011-11-221-5/+9
| | | | | | | | | | Signed-off-by: Maciej Żenczykowski <maze@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | net: remove ipv6_addr_copy()Alexey Dobriyan2011-11-222-14/+8
| | | | | | | | | | | | | | C assignment can handle struct in6_addr copying. Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/netDavid S. Miller2011-11-216-61/+65
|\| | | | | | | | | | | | | | | | | | | | | | | The forcedeth changes had a conflict with the conversion over to atomic u64 statistics in net-next. The libertas cfg.c code had a conflict with the bss reference counting fix by John Linville in net-next. Conflicts: drivers/net/ethernet/nvidia/forcedeth.c drivers/net/wireless/libertas/cfg.c
| * ipv4: fix redirect handlingEric Dumazet2011-11-181-51/+59
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | commit f39925dbde77 (ipv4: Cache learned redirect information in inetpeer.) introduced a regression in ICMP redirect handling. It assumed ipv4_dst_check() would be called because all possible routes were attached to the inetpeer we modify in ip_rt_redirect(), but thats not true. commit 7cc9150ebe (route: fix ICMP redirect validation) tried to fix this but solution was not complete. (It fixed only one route) So we must lookup existing routes (including different TOS values) and call check_peer_redir() on them. Reported-by: Ivan Zahariev <famzah@icdsoft.com> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> CC: Flavio Leitner <fbl@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * ping: dont increment ICMP_MIB_INERRORSEric Dumazet2011-11-181-2/+0
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ping module incorrectly increments ICMP_MIB_INERRORS if feeded with a frame not belonging to its own sockets. RFC 2011 states that ICMP_MIB_INERRORS should count "the number of ICMP messages which the entiry received but determined as having ICMP-specific errors (bad ICMP checksums, bad length, etc.)." Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> CC: Vasiliy Kulikov <segoon@openwall.com> Acked-by: Flavio Leitner <fbl@redhat.com> Acked-by: Vasiliy Kulikov <segoon@openwall.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * tcp: clear xmit timers in tcp_v4_syn_recv_sock()Eric Dumazet2011-11-161-0/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Simon Kirby reported divides by zero errors in __tcp_select_window() This happens when inet_csk_route_child_sock() returns a NULL pointer : We free new socket while we eventually armed keepalive timer in tcp_create_openreq_child() Fix this by a call to tcp_clear_xmit_timers() [ This is a followup to commit 918eb39962dff (net: add missing bh_unlock_sock() calls) ] Reported-by: Simon Kirby <sim@hostway.ca> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Tested-by: Simon Kirby <sim@hostway.ca> Signed-off-by: David S. Miller <davem@davemloft.net>
| * net-netlink: Add a new attribute to expose TCLASS values via netlinkMaciej Żenczykowski2011-11-141-2/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | commit 3ceca749668a52bd795585e0f71c6f0b04814f7b added a TOS attribute. Unfortunately TOS and TCLASS are both present in a dual-stack v6 socket, furthermore they can have different values. As such one cannot in a sane way expose both through a single attribute. Signed-off-by: Maciej Żenczyowski <maze@google.com> CC: Murali Raja <muralira@google.com> CC: Stephen Hemminger <shemminger@vyatta.com> CC: Eric Dumazet <eric.dumazet@gmail.com> CC: David S. Miller <davem@davemloft.net> Signed-off-by: David S. Miller <davem@davemloft.net>
| * ah: Don't return NET_XMIT_DROP on input.Nick Bowler2011-11-131-2/+0
| | | | | | | | | | | | | | | | | | | | | | | | When the ahash driver returns -EBUSY, AH4/6 input functions return NET_XMIT_DROP, presumably copied from the output code path. But returning transmit codes on input doesn't make a lot of sense. Since NET_XMIT_DROP is a positive int, this gets interpreted as the next header type (i.e., success). As that can only end badly, remove the check. Signed-off-by: Nick Bowler <nbowler@elliptictech.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * ipv4: fix for ip_options_rcv_srr() daddr update.Li Wei2011-11-091-0/+1
| | | | | | | | | | | | | | | | | | When opt->srr_is_hit is set skb_rtable(skb) has been updated for 'nexthop' and iph->daddr should always equals to skb_rtable->rt_dst holds, We need update iph->daddr either. Signed-off-by: Li Wei <lw@cn.fujitsu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * ah: Read nexthdr value before overwriting it in ahash input callback.Nick Bowler2011-11-091-2/+2
| | | | | | | | | | | | | | | | | | The AH4/6 ahash input callbacks read out the nexthdr field from the AH header *after* they overwrite that header. This is obviously not going to end well. Fix it up. Signed-off-by: Nick Bowler <nbowler@elliptictech.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * ah: Correctly pass error codes in ahash output callback.Nick Bowler2011-11-091-2/+0
| | | | | | | | | | | | | | | | | | | | | | | | | | | | The AH4/6 ahash output callbacks pass nexthdr to xfrm_output_resume instead of the error code. This appears to be a copy+paste error from the input case, where nexthdr is expected. This causes the driver to continuously add AH headers to the datagram until either an allocation fails and the packet is dropped or the ahash driver hits a synchronous fallback and the resulting monstrosity is transmitted. Correct this issue by simply passing the error code unadulterated. Signed-off-by: Nick Bowler <nbowler@elliptictech.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | ip_gre: Set needed_headroom dynamically againHerbert Xu2011-11-181-0/+2
| | | | | | | | | | | | | | | | | | | | | | ip_gre: Set needed_headroom dynamically again Now that all needed_headroom users have been fixed up so that we can safely increase needed_headroom, this patch restore the dynamic update of needed_headroom. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
* | ipv4: Remove all uses of LL_ALLOCATED_SPACEHerbert Xu2011-11-184-10/+22
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ipv4: Remove all uses of LL_ALLOCATED_SPACE The macro LL_ALLOCATED_SPACE was ill-conceived. It applies the alignment to the sum of needed_headroom and needed_tailroom. As the amount that is then reserved for head room is needed_headroom with alignment, this means that the tail room left may be too small. This patch replaces all uses of LL_ALLOCATED_SPACE in net/ipv4 with the macro LL_RESERVED_SPACE and direct reference to needed_tailroom. This also fixes the problem with needed_headroom changing between allocating the skb and reserving the head room. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
* | net: introduce and use netdev_features_t for device features setsMichał Mirosław2011-11-163-3/+6
| | | | | | | | | | | | | | | | | | | | v2: add couple missing conversions in drivers split unexporting netdev_fix_features() implemented %pNF convert sock::sk_route_(no?)caps Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl> Signed-off-by: David S. Miller <davem@davemloft.net>
* | ipv4: fix a memory leak in ic_bootp_send_ifRongQing.Li2011-11-141-2/+7
| | | | | | | | | | | | | | when dev_hard_header() failed, the newly allocated skb should be freed. Signed-off-by: RongQing.Li <roy.qing.li@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | neigh: new unresolved queue limitsEric Dumazet2011-11-141-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Le mercredi 09 novembre 2011 à 16:21 -0500, David Miller a écrit : > From: David Miller <davem@davemloft.net> > Date: Wed, 09 Nov 2011 16:16:44 -0500 (EST) > > > From: Eric Dumazet <eric.dumazet@gmail.com> > > Date: Wed, 09 Nov 2011 12:14:09 +0100 > > > >> unres_qlen is the number of frames we are able to queue per unresolved > >> neighbour. Its default value (3) was never changed and is responsible > >> for strange drops, especially if IP fragments are used, or multiple > >> sessions start in parallel. Even a single tcp flow can hit this limit. > > ... > > > > Ok, I've applied this, let's see what happens :-) > > Early answer, build fails. > > Please test build this patch with DECNET enabled and resubmit. The > decnet neigh layer still refers to the removed ->queue_len member. > > Thanks. Ouch, this was fixed on one machine yesterday, but not the other one I used this morning, sorry. [PATCH V5 net-next] neigh: new unresolved queue limits unres_qlen is the number of frames we are able to queue per unresolved neighbour. Its default value (3) was never changed and is responsible for strange drops, especially if IP fragments are used, or multiple sessions start in parallel. Even a single tcp flow can hit this limit. $ arp -d 192.168.20.108 ; ping -c 2 -s 8000 192.168.20.108 PING 192.168.20.108 (192.168.20.108) 8000(8028) bytes of data. 8008 bytes from 192.168.20.108: icmp_seq=2 ttl=64 time=0.322 ms Signed-off-by: David S. Miller <davem@davemloft.net>
* | ipv4: PKTINFO doesnt need dst referenceEric Dumazet2011-11-093-19/+22
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Le lundi 07 novembre 2011 à 15:33 +0100, Eric Dumazet a écrit : > At least, in recent kernels we dont change dst->refcnt in forwarding > patch (usinf NOREF skb->dst) > > One particular point is the atomic_inc(dst->refcnt) we have to perform > when queuing an UDP packet if socket asked PKTINFO stuff (for example a > typical DNS server has to setup this option) > > I have one patch somewhere that stores the information in skb->cb[] and > avoid the atomic_{inc|dec}(dst->refcnt). > OK I found it, I did some extra tests and believe its ready. [PATCH net-next] ipv4: IP_PKTINFO doesnt need dst reference When a socket uses IP_PKTINFO notifications, we currently force a dst reference for each received skb. Reader has to access dst to get needed information (rt_iif & rt_spec_dst) and must release dst reference. We also forced a dst reference if skb was put in socket backlog, even without IP_PKTINFO handling. This happens under stress/load. We can instead store the needed information in skb->cb[], so that only softirq handler really access dst, improving cache hit ratios. This removes two atomic operations per packet, and false sharing as well. On a benchmark using a mono threaded receiver (doing only recvmsg() calls), I can reach 720.000 pps instead of 570.000 pps. IP_PKTINFO is typically used by DNS servers, and any multihomed aware UDP application. Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | ipv4: reduce percpu needs for icmpmsg mibsEric Dumazet2011-11-092-9/+8
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Reading /proc/net/snmp on a machine with a lot of cpus is very expensive (can be ~88000 us). This is because ICMPMSG MIB uses 4096 bytes per cpu, and folding values for all possible cpus can read 16 Mbytes of memory. ICMP messages are not considered as fast path on a typical server, and eventually few cpus handle them anyway. We can afford an atomic operation instead of using percpu data. This saves 4096 bytes per cpu and per network namespace. Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | net: rename sk_clone to sk_clone_lockEric Dumazet2011-11-082-5/+14
| | | | | | | | | | | | | | | | | | | | Make clear that sk_clone() and inet_csk_clone() return a locked socket. Add _lock() prefix and kerneldoc. Suggested-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | net: better pcpu data alignmentEric Dumazet2011-11-082-2/+2
|/ | | | | | | | | | | Tunnels can force an alignment of their percpu data to reduce number of cache lines used in fast path, or read in .ndo_get_stats() percpu_alloc() is a very fine grained allocator, so any small hole will be used anyway. Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* ipv4: Fix inetpeer expire time informationSteffen Klassert2011-11-081-3/+7
| | | | | | | | | | | | As we update the learned pmtu informations on demand, we might report a nagative expiration time value to userspace if the pmtu informations are already expired and we have not send a packet to that inetpeer after expiration. With this patch we send a expire time of null to userspace after expiration until the next packet is send to that inetpeer. Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* tcp: Fix comments for Nagle algorithmFeng King2011-11-081-1/+1
| | | | | | | | TCP_NODELAY is weaker than TCP_CORK, when TCP_CORK was set, small segments will always pass Nagle test regardless of TCP_NODELAY option. Signed-off-by: Feng King <kinwin2008@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* Merge branch 'modsplit-Oct31_2011' of ↵Linus Torvalds2011-11-0719-0/+19
|\ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | git://git.kernel.org/pub/scm/linux/kernel/git/paulg/linux * 'modsplit-Oct31_2011' of git://git.kernel.org/pub/scm/linux/kernel/git/paulg/linux: (230 commits) Revert "tracing: Include module.h in define_trace.h" irq: don't put module.h into irq.h for tracking irqgen modules. bluetooth: macroize two small inlines to avoid module.h ip_vs.h: fix implicit use of module_get/module_put from module.h nf_conntrack.h: fix up fallout from implicit moduleparam.h presence include: replace linux/module.h with "struct module" wherever possible include: convert various register fcns to macros to avoid include chaining crypto.h: remove unused crypto_tfm_alg_modname() inline uwb.h: fix implicit use of asm/page.h for PAGE_SIZE pm_runtime.h: explicitly requires notifier.h linux/dmaengine.h: fix implicit use of bitmap.h and asm/page.h miscdevice.h: fix up implicit use of lists and types stop_machine.h: fix implicit use of smp.h for smp_processor_id of: fix implicit use of errno.h in include/linux/of.h of_platform.h: delete needless include <linux/module.h> acpi: remove module.h include from platform/aclinux.h miscdevice.h: delete unnecessary inclusion of module.h device_cgroup.h: delete needless include <linux/module.h> net: sch_generic remove redundant use of <linux/module.h> net: inet_timewait_sock doesnt need <linux/module.h> ... Fix up trivial conflicts (other header files, and removal of the ab3550 mfd driver) in - drivers/media/dvb/frontends/dibx000_common.c - drivers/media/video/{mt9m111.c,ov6650.c} - drivers/mfd/ab3550-core.c - include/linux/dmaengine.h
| * net: Add export.h for EXPORT_SYMBOL/THIS_MODULE to non-modulesPaul Gortmaker2011-11-0116-0/+16
| | | | | | | | | | | | | | | | | | These files are non modular, but need to export symbols using the macros now living in export.h -- call out the include so that things won't break when we remove the implicit presence of module.h from everywhere. Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
| * net: Fix files explicitly needing to include module.hPaul Gortmaker2011-11-013-0/+3
| | | | | | | | | | | | | | | | | | With calls to modular infrastructure, these files really needs the full module.h header. Call it out so some of the cleanups of implicit and unrequired includes elsewhere can be cleaned up. Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
* | net: add missing bh_unlock_sock() callsEric Dumazet2011-11-031-0/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Simon Kirby reported lockdep warnings and following messages : [104661.897577] huh, entered softirq 3 NET_RX ffffffff81613740 preempt_count 00000101, exited with 00000102? [104661.923653] huh, entered softirq 3 NET_RX ffffffff81613740 preempt_count 00000101, exited with 00000102? Problem comes from commit 0e734419 (ipv4: Use inet_csk_route_child_sock() in DCCP and TCP.) If inet_csk_route_child_sock() returns NULL, we should release socket lock before freeing it. Another lock imbalance exists if __inet_inherit_port() returns an error since commit 093d282321da ( tproxy: fix hash locking issue when using port redirection in __inet_inherit_port()) a backport is also needed for >= 2.6.37 kernels. Reported-by: Simon Kirby <sim@hostway.ca> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Tested-by: Eric Dumazet <eric.dumazet@gmail.com> CC: Balazs Scheidler <bazsi@balabit.hu> CC: KOVACS Krisztian <hidden@balabit.hu> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Tested-by: Simon Kirby <sim@hostway.ca> Signed-off-by: David S. Miller <davem@davemloft.net>
* | udp: fix a race in encap_rcv handlingEric Dumazet2011-11-021-3/+5
| | | | | | | | | | | | | | | | | | | | udp_queue_rcv_skb() has a possible race in encap_rcv handling, since this pointer can be changed anytime. We should use ACCESS_ONCE() to close the race. Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | net: make the tcp and udp file_operations for the /proc stuff constArjan van de Ven2011-11-013-23/+34
| | | | | | | | | | | | | | | | | | | | | | | | | | the tcp and udp code creates a set of struct file_operations at runtime while it can also be done at compile time, with the added benefit of then having these file operations be const. the trickiest part was to get the "THIS_MODULE" reference right; the naive method of declaring a struct in the place of registration would not work for this reason. Signed-off-by: Arjan van de Ven <arjan@linux.intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | netfilter: Remove unnecessary OOM logging messagesJoe Perches2011-11-013-24/+3
| | | | | | | | | | | | | | | | | | | | Site specific OOM messages are duplications of a generic MM out of memory message and aren't really useful, so just delete them. Signed-off-by: Joe Perches <joe@perches.com> Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
generated by cgit v1.2.3 (git 2.39.1) at 2025-01-27 11:32:14 +0100