| Commit message (Expand) | Author | Age | Files | Lines |
|---|
| * | tcp/syncache: Set flowid and hash type properly for SYN|ACK | Sepherosa Ziehau | 2016-04-29 | 1 | -5/+11 |
| * | Indentation issues. | Pedro F. Giffuni | 2016-04-20 | 1 | -3/+2 |
| * | kernel: use our nitems() macro when it is available through param.h. | Pedro F. Giffuni | 2016-04-19 | 1 | -2/+2 |
| * | Mfp: r296309 | Bjoern A. Zeeb | 2016-04-09 | 1 | -2/+6 |
| * | Redo r294869. The array of counters for TCP states doesn't belong to | Gleb Smirnoff | 2016-03-15 | 1 | -3/+3 |
| * | Grab a snap amount of TCP connections in syncache from tcpstat. | Gleb Smirnoff | 2016-01-27 | 1 | -19/+0 |
| * | Augment struct tcpstat with tcps_states[], which is used for book-keeping | Gleb Smirnoff | 2016-01-27 | 1 | -1/+12 |
| * | Implementation of server-side TCP Fast Open (TFO) [RFC7413]. | Patrick Kelsey | 2015-12-24 | 1 | -8/+123 |
| * | First cut of the modularization of our TCP stack. Still | Randall Stewart | 2015-12-16 | 1 | -0/+22 |
| * | Use Jenkins hash for TCP syncache. | Gleb Smirnoff | 2015-09-05 | 1 | -52/+20 |
| * | Decompose TCP INP_INFO lock to increase short-lived TCP connections scalability: | Julien Charbon | 2015-08-03 | 1 | -4/+16 |
| * | Make syncookie_mac() use 'tcp_seq irs' in computing hash. | Hiren Panchasara | 2015-01-30 | 1 | -0/+1 |
| * | Start process of removing the use of the deprecated "M_FLOWID" flag | Hans Petter Selasky | 2014-12-01 | 1 | -3/+1 |
| * | Remove SYSCTL_VNET_* macros, and simply put CTLFLAG_VNET where needed. | Gleb Smirnoff | 2014-11-07 | 1 | -8/+8 |
| * | Fix typo. | Andrey V. Elsukov | 2014-10-31 | 1 | -1/+1 |
| * | * Split tcp_signature_compute() into 2 pieces: | Alexander V. Chernikov | 2014-09-27 | 1 | -12/+34 |
| * | In tcp_input(), don't acquire the pcbinfo global write lock for SYN | John Baldwin | 2014-09-04 | 1 | -3/+0 |
| * | syncache_lookup() is a file local function. Make it static and | Bjoern A. Zeeb | 2014-05-24 | 1 | -2/+1 |
| * | Ensure that the flowid hashtype is assigned to the inp if the flowid | Adrian Chadd | 2014-05-18 | 1 | -0/+1 |
| * | Utilize SYSCTL_UMA_CUR() to export usage of syncache and | Gleb Smirnoff | 2014-02-07 | 1 | -13/+2 |
| * | Decrease lock contention within the TCP accept case by removing | George V. Neville-Neil | 2014-01-28 | 1 | -1/+3 |
| * | If the flowid is available for the mbuf that finalised the creation | Adrian Chadd | 2014-01-18 | 1 | -0/+10 |
| * | The r48589 promised to remove implicit inclusion of if_var.h soon. Prepare | Gleb Smirnoff | 2013-10-26 | 1 | -0/+1 |
| * | Implement the ip, tcp, and udp DTrace providers. The probe definitions use | Mark Johnston | 2013-08-25 | 1 | -1/+1 |
| * | Free the non-fatal "timestamp missing" debug string manually as it is | Andre Oppermann | 2013-07-16 | 1 | -1/+4 |
| * | Improve SYN cookies by encoding the MSS, WSCALE (window scaling) and SACK | Andre Oppermann | 2013-07-11 | 1 | -207/+355 |
| * | Extend debug logging of TCP timestamp related specification | Andre Oppermann | 2013-07-10 | 1 | -0/+17 |
| * | uma_zone_set_max() directly returns the rounded effective zone | Andre Oppermann | 2013-02-01 | 1 | -2/+2 |
| * | Add TCP_OFFLOAD hook in syncache_respond for IPv6 too, just like the one | Navdeep Parhar | 2013-01-25 | 1 | -0/+9 |
| * | Fix sysctl_handle_int() usage. Either arg1 or arg2 should be supplied, | Gleb Smirnoff | 2012-12-25 | 1 | -1/+1 |
| * | Mechanically substitute flags from historic mbuf allocator with | Gleb Smirnoff | 2012-12-05 | 1 | -1/+1 |
| * | For retransmits of SYN|ACK from the syncache use the slightly more | Andre Oppermann | 2012-10-28 | 1 | -1/+1 |
| * | Change the syncache count reporting the current number of entries | Andre Oppermann | 2012-10-28 | 1 | -8/+15 |
| * | When SYN or SYN/ACK had to be retransmitted RFC5681 requires us to | Andre Oppermann | 2012-10-28 | 1 | -2/+3 |
| * | Switch the entire IPv4 stack to keep the IP packet header | Gleb Smirnoff | 2012-10-22 | 1 | -3/+3 |
| * | - Updated TOE support in the kernel. | Navdeep Parhar | 2012-06-19 | 1 | -73/+62 |
| * | It turns out that too many drivers are not only parsing the L2/3/4 | Bjoern A. Zeeb | 2012-05-28 | 1 | -1/+2 |
| * | MFp4 bz_ipv6_fast: | Bjoern A. Zeeb | 2012-05-25 | 1 | -5/+4 |
| * | Fix PAWS (Protect Against Wrapped Sequence numbers) in cases when | Bjoern A. Zeeb | 2012-02-15 | 1 | -4/+4 |
| * | Add new socket options: TCP_KEEPINIT, TCP_KEEPIDLE, TCP_KEEPINTVL and | Gleb Smirnoff | 2012-02-05 | 1 | -1/+9 |
| * | Mark all SYSCTL_NODEs static that have no corresponding SYSCTL_DECLs. | Ed Schouten | 2011-11-07 | 1 | -1/+2 |
| * | Implement a CPU-affine TCP and UDP connection lookup data structure, | Robert Watson | 2011-06-06 | 1 | -1/+8 |
| * | Add _mbuf() variants of various inpcb-related interfaces, including lookup, | Robert Watson | 2011-06-04 | 1 | -4/+4 |
| * | Decompose the current single inpcbinfo lock into two locks: | Robert Watson | 2011-05-30 | 1 | -0/+5 |
| * | Make the TCP code compile without INET. Sort #includes and add #ifdef INETs. | Bjoern A. Zeeb | 2011-04-30 | 1 | -5/+24 |
| * | Add the possibility to verify MD5 hash of incoming TCP packets. | Attilio Rao | 2011-04-25 | 1 | -4/+5 |
| * | Fix typos - remove duplicate "the". | Rebecca Cran | 2011-02-21 | 1 | -1/+1 |
| * | sysctl(9) cleanup checkpoint: amd64 GENERIC builds cleanly. | Matthew D Fleming | 2011-01-12 | 1 | -5/+5 |
| * | After some off-list discussion, revert a number of changes to the | Dimitry Andric | 2010-11-22 | 1 | -3/+3 |
| * | Apply the STATIC_VNET_DEFINE and STATIC_DPCPU_DEFINE macros throughout | Dimitry Andric | 2010-11-14 | 1 | -3/+3 |
