| Commit message (Expand) | Author | Age | Files | Lines |
|---|
| * | Improve carp(4) locking: | glebius | 2015-04-21 | 1 | -62/+39 |
| * | Provide functions to determine presence of a given address | glebius | 2015-04-17 | 2 | -0/+25 |
| * | Fix an old and well-documented use-after-free race condition in | jch | 2015-04-16 | 4 | -100/+206 |
| * | Fix RSS build - netisr input / NETISR_IP_DIRECT is used here. | adrian | 2015-04-15 | 1 | -0/+1 |
| * | Replace struct filedesc argument in getsock_cap with struct thread | mjg | 2015-04-11 | 1 | -4/+4 |
| * | fd: remove filedesc argument from fdclose | mjg | 2015-04-11 | 1 | -1/+1 |
| * | Attempt to fix build after 281351 by defining full prototype for the | delphij | 2015-04-11 | 1 | -4/+4 |
| * | o Use Jenkins hash. With previous hash, for a single source IP address and | glebius | 2015-04-10 | 1 | -4/+7 |
| * | Move all code related to IP fragment reassembly to ip_reass.c. Some | glebius | 2015-04-10 | 3 | -562/+666 |
| * | Now that IP reassembly is no longer under single lock, book-keeping amount | glebius | 2015-04-09 | 1 | -130/+100 |
| * | In the ip_reass() do packet examination and adjusting before acquiring | glebius | 2015-04-09 | 1 | -34/+35 |
| * | Make ip reassembly queue mutexes per-vnet, putting them into the structure | glebius | 2015-04-09 | 1 | -28/+26 |
| * | Use TAILQ_FOREACH_SAFE() instead of implementing it ourselves. | glebius | 2015-04-09 | 1 | -9/+4 |
| * | If V_maxnipq is set to zero, drain the queue here and now, instead of | glebius | 2015-04-09 | 1 | -4/+4 |
| * | o Since we always update either fragdrop or fragtimeout stat counter when we | glebius | 2015-04-09 | 1 | -39/+32 |
| * | Rename ip_drain_locked() to ip_drain_vnet(), since the function differs | glebius | 2015-04-09 | 1 | -6/+4 |
| * | Move the IPv4 reassembly queue locking from a single lock to be per-bucket (g... | adrian | 2015-04-07 | 1 | -35/+85 |
| * | Improve patch for SA-15:04.igmp to solve a potential buffer overflow. | delphij | 2015-04-07 | 1 | -4/+3 |
| * | Add sleepable lock to protect at least against two parallel SIOCSVHs. | glebius | 2015-04-06 | 1 | -3/+5 |
| * | Extend fixes made in r278103 and r38754 by copying the complete packet | hselasky | 2015-04-02 | 1 | -7/+13 |
| * | Provide better debugging information in tcp_timer_activate() and | jch | 2015-04-02 | 1 | -2/+2 |
| * | Provide a comment explaining issues with the counter(9) trick, so that | glebius | 2015-04-02 | 1 | -0/+14 |
| * | Try to unbreak the build after r280971 by providing the missing | bz | 2015-04-02 | 1 | -0/+1 |
| * | o Use new function ip_fillid() in all places throughout the kernel, | glebius | 2015-04-01 | 9 | -57/+95 |
| * | Use appropriate timeout_t* instead of void* in tcp_timer_activate() | jch | 2015-03-31 | 1 | -1/+1 |
| * | VNETalize random IP ID engine. | glebius | 2015-03-28 | 1 | -41/+64 |
| * | Initialize random IP ID engine via SYSINIT() instead of doing that on | glebius | 2015-03-28 | 1 | -55/+34 |
| * | On multi CPU systems, we may emit successive packets with the same id. | fabient | 2015-03-27 | 2 | -5/+15 |
| * | Improve the selection of the destination address of SACK chunks. | tuexen | 2015-03-26 | 2 | -20/+4 |
| * | Make sure that we don't free an SCTP shared key too early. | tuexen | 2015-03-25 | 1 | -2/+2 |
| * | Use the reference count of the right SCTP inp. | tuexen | 2015-03-25 | 1 | -1/+1 |
| * | Fix two bugs which resulted in a screwed up end point list: | tuexen | 2015-03-24 | 2 | -8/+9 |
| * | The addition of flowid and flowtype in r280233 and r280237 respectively forgot | lstewart | 2015-03-24 | 1 | -1/+1 |
| * | Fix the bug in the handling of fragmented abandoned SCTP user messages report... | tuexen | 2015-03-24 | 1 | -3/+5 |
| * | Fix an accounting bug related to the per stream chunk counter. | tuexen | 2015-03-24 | 1 | -6/+2 |
| * | When an ICMP message is received and the MTU shrinks, only | tuexen | 2015-03-23 | 1 | -13/+11 |
| * | Remove a useless assignment. | tuexen | 2015-03-23 | 1 | -2/+0 |
| * | Add connection flow type to siftr(4). | hiren | 2015-03-19 | 1 | -3/+8 |
| * | Add connection flowid to siftr(4). | hiren | 2015-03-18 | 1 | -3/+8 |
| * | Correctly const-ify things. | adrian | 2015-03-18 | 1 | -2/+2 |
| * | Go back to using sbuf_new() with a preallocated large buffer, to avoid | ian | 2015-03-14 | 1 | -1/+4 |
| * | Use sbuf_new_for_sysctl() instead of plain sbuf_new() to ensure sysctl | ian | 2015-03-14 | 1 | -5/+3 |
| * | Fix `ipfw fwd tablearg'. Use dedicated field nh4 in struct table_value | ae | 2015-03-13 | 1 | -3/+4 |
| * | Update a comment to get it aligned with the code change. | tuexen | 2015-03-11 | 1 | -1/+4 |
| * | It seems that sb_acc is a better replacement for sb_cc than sb_ccc. At | tuexen | 2015-03-11 | 1 | -1/+1 |
| * | Fix the adaptation of the path state when thresholds are changed | tuexen | 2015-03-11 | 1 | -16/+16 |
| * | Keep track on the socket lock state. This fixes a bug showing up on | tuexen | 2015-03-10 | 1 | -8/+12 |
| * | Unlock the stcb when using setsockopt() for the SCTP_PEER_ADDR_THLDS option. | tuexen | 2015-03-10 | 1 | -0/+1 |
| * | Add a SCTP socket option to limit the cwnd for each path. | tuexen | 2015-03-10 | 9 | -11/+104 |
| * | Fix a typo. | tuexen | 2015-03-10 | 1 | -1/+1 |
