aboutsummaryrefslogtreecommitdiffstats
path: root/net/ipv4/tcp_input.c
Commit message (Expand)AuthorAgeFilesLines
* tcp: fix ssthresh u16 leftoverIlpo Järvinen2009-09-151-1/+1
* Revert Backoff [v3]: Revert RTO on ICMP destination unreachableDamian Lukowski2009-09-011-3/+2
* tcp: fix loop in ofo handling code and reduce its complexityIlpo Järvinen2009-05-291-17/+11
* tcp: Use SKB queue and list helpers instead of doing it by-hand.David S. Miller2009-05-281-35/+83
* Merge branch 'master' of master.kernel.org:/pub/scm/linux/kernel/git/davem/ne...David S. Miller2009-05-081-10/+0
|\
| * tcp: Fix tcp_prequeue() to get correct rto_min valueSatoru SATOH2009-05-041-10/+0
* | tcp: extend ECN sysctl to allow server-side only ECNIlpo Järvinen2009-05-041-1/+1
|/
* tcp: fix >2 iw selectionIlpo Järvinen2009-04-141-0/+3
* tcp: Discard segments that ack data not yet sentJohn Dykstra2009-03-221-10/+17
* net/*: use linux/kernel.h swap()Ilpo Järvinen2009-03-211-20/+3
* tcp: simplify tcp_current_mssIlpo Järvinen2009-03-151-1/+1
* tcp: don't check mtu probe completion in the loopIlpo Järvinen2009-03-151-7/+6
* tcp: consolidate paws checkIlpo Järvinen2009-03-151-6/+5
* tcp: kill dead end_seq variable in clean_rtx_queueIlpo Järvinen2009-03-151-3/+0
* tcp: remove pointless .dsack/.num_sacks codeIlpo Järvinen2009-03-151-5/+2
* tcp: tcp_init_wl / tcp_update_wl argument cleanupHantzis Fotis2009-03-021-5/+4
* tcp: kill eff_sacks "cache", the sole user can calculate itselfIlpo Järvinen2009-03-021-13/+2
* tcp: separate timeout marking loop to it's own functionIlpo Järvinen2009-03-021-24/+39
* tcp: remove redundant code from tcp_mark_lost_retransIlpo Järvinen2009-03-021-4/+12
* tcp: fix lost_cnt_hint miscountsIlpo Järvinen2009-03-021-8/+5
* tcp: fix retrans_out leaksIlpo Järvinen2009-03-011-4/+5
* net_dma: convert to dma_find_channelDan Williams2009-01-061-1/+1
* tcp: share code through function, not through copy-paste. :-)Ilpo Järvinen2008-12-051-7/+10
* tcp: drop tcp_bound_rto, merge content of it tcp_set_rtoIlpo Järvinen2008-12-051-9/+3
* tcp: no need to pass prev skb around, reduces arg pressureIlpo Järvinen2008-12-051-5/+4
* tcp: introduce struct tcp_sacktag_state to reduce arg pressureIlpo Järvinen2008-12-051-71/+74
* tcp: make mtu probe failure to not break gso'ed skbs unnecessarilyIlpo Järvinen2008-12-051-12/+7
* tcp: Fix thinko making the not-shiftable to cover S|R as wellIlpo Järvinen2008-12-051-1/+1
* tcp: force mss equality with the next skb too.Ilpo Järvinen2008-12-051-5/+4
* tcp: tcp_limit_reno_sacked can become staticIlpo Järvinen2008-11-251-1/+1
* tcp: add some mibs to track collapsingIlpo Järvinen2008-11-241-0/+4
* tcp: Make shifting not clear the hintsIlpo Järvinen2008-11-241-2/+14
* tcp: Try to restore large SKBs while SACK processingIlpo Järvinen2008-11-241-7/+249
* tcp: make tcp_sacktag_one able to handle partial skb tooIlpo Järvinen2008-11-241-15/+17
* tcp: Make SACK code to split only at mss boundariesIlpo Järvinen2008-11-241-4/+23
* tcp: more aggressive skippingIlpo Järvinen2008-11-241-1/+1
* tcp: move tcp_simple_retransmit to tcp_inputIlpo Järvinen2008-11-241-1/+52
* net: replace NIPQUAD() in net/ipv4/ net/ipv6/Harvey Harrison2008-10-311-2/+2
* net: replace %p6 with %pI6Harvey Harrison2008-10-291-1/+1
* net: replace uses of NIP6_FMT with %p6Harvey Harrison2008-10-281-2/+2
* Merge branch 'master' of master.kernel.org:/pub/scm/linux/kernel/git/davem/ne...David S. Miller2008-10-081-1/+2
|\
| * tcp: Fix possible double-ack w/ user dmaAli Saidi2008-10-071-1/+2
* | tcp: cleanup messy initializerIlpo Järvinen2008-10-071-2/+2
* | tcp: kill pointless urg_modeIlpo Järvinen2008-10-071-5/+6
* | tcp: Fix queue traversal in tcp_use_frto().David S. Miller2008-09-231-0/+2
* | net: Remove __skb_insert() calls outside of skbuff internals.David S. Miller2008-09-211-2/+2
* | tcp: don't clear lost_skb_hint when not necessaryIlpo Järvinen2008-09-201-1/+13
* | tcp: don't clear retransmit_skb_hint when not necessaryIlpo Järvinen2008-09-201-1/+3
* | tcp: No need to clear retransmit_skb_hint when SACKingIlpo Järvinen2008-09-201-7/+0
* | tcp: Kill precaution that's very likely obsoleteIlpo Järvinen2008-09-201-4/+0