| Commit message (Expand) | Author | Age | Files | Lines |
|---|
| * | spelling |   jsg | 2021-03-10 | 1 | -5/+5 |
| * | Turns off the direct ACK on every other segment |   jan | 2021-02-03 | 1 | -5/+4 |
| * | Break a glass ceiling on cwnd due to integer division during congestion |   procter | 2020-06-19 | 1 | -2/+2 |
| * | Checking the IPsec policy is expensive. Check only when IPsec is used. |   tobhe | 2019-12-06 | 1 | -14/+16 |
| * | Change the default security level for incoming IPsec flows from | tobhe | 2019-11-29 | 1 | -22/+23 |
| * | Prevent underflows in tp->snd_wnd if the remote side ACKs more than |   bluhm | 2019-11-11 | 1 | -3/+9 |
| * | Count the number of TCP SACK options that were dropped due to the | bluhm | 2019-07-12 | 1 | -8/+9 |
| * | Received SACK options are managed by a linked list at the TCP socket. | bluhm | 2019-07-10 | 1 | -1/+5 |
| * | Do not acknowledge a received ack-only tcp packet that we would drop due to |   friehm | 2018-09-17 | 1 | -2/+4 |
| * | Coverity CID 1470233 complainst that the m != NULL check in | bluhm | 2018-07-23 | 1 | -4/+3 |
| * | Assert that the INP_IPV6 in in6_pcbconnect() is correct. Just call | bluhm | 2018-06-14 | 1 | -22/+4 |
| * | The output from tcp debug sockets was incomplete. After detach tp | bluhm | 2018-06-11 | 1 | -33/+11 |
| * | Historically there were slow and fast tcp timeouts. That is why | bluhm | 2018-05-08 | 1 | -3/+3 |
| * | Make divert lookup similar for all socket types. If PF_TAG_DIVERTED | bluhm | 2017-12-04 | 1 | -7/+7 |
| * | Simplify the reverse PCB lookup logic. The PF_TAG_TRANSLATE_LOCALHOST | bluhm | 2017-12-01 | 1 | -10/+5 |
| * | Sprinkle some NET_ASSERT_LOCKED(), const and co to prepare running |   mpi | 2017-11-20 | 1 | -1/+2 |
| * | The TF_BLOCKOUTPUT flag is set around all sorwakeup() and sowwakeup() | bluhm | 2017-11-08 | 1 | -1/+13 |
| * | Remove the TCP_FACK option and associated #if{,n}def code. |   job | 2017-10-25 | 1 | -111/+2 |
| * | Refactor handling of partial TCP acknowledgements |   mikeb | 2017-10-24 | 1 | -93/+81 |
| * | Unconditionally enable TCP selective acknowledgements (SACK) | mikeb | 2017-10-22 | 1 | -72/+25 |
| * | Remove NET_LOCK()'s argument. | mpi | 2017-08-11 | 1 | -5/+4 |
| * | Assert that the corresponding socket is locked when manipulating socket | mpi | 2017-06-26 | 1 | -14/+14 |
| * | Merge the content of <netinet/tcpip.h> and <netinet6/tcpipv6.h> in | mpi | 2017-05-18 | 1 | -2/+1 |
| * | Checking for IPv4 mapped addreses and dropping the packet is done | bluhm | 2017-05-06 | 1 | -8/+1 |
| * | If m is not a continuous mbuf cluster, m_pullup() in pr_input may | bluhm | 2017-05-04 | 1 | -2/+2 |
| * | Back out rev 1.185 (which made the code match the comment) and |   millert | 2017-05-03 | 1 | -7/+4 |
| * | Use the rt_rmx defines that hide the struct rt_kmetrics indirection. | bluhm | 2017-04-19 | 1 | -4/+4 |
| * | Use the address family passed down with pr_input to simplify | bluhm | 2017-04-17 | 1 | -48/+4 |
| * | Pass down the address family through the pr_input calls. This | bluhm | 2017-04-14 | 1 | -3/+2 |
| * | percpu counters for TCP stats |   jca | 2017-02-09 | 1 | -85/+80 |
| * | Change the IPv4 pr_input function to the way IPv6 is implemented, | bluhm | 2017-01-29 | 1 | -27/+18 |
| * | Since raw_input() and route_input() are gone from pr_input, we can | bluhm | 2017-01-25 | 1 | -8/+2 |
| * | Remove NULL checks before m_free(9), it deals with it. | mpi | 2017-01-10 | 1 | -7/+4 |
| * | Introduce the NET_LOCK() a rwlock used to serialize accesses to the parts | mpi | 2016-12-19 | 1 | -10/+10 |
| * | Be consistent and do not use braces for single line statements. | mpi | 2016-11-16 | 1 | -10/+7 |
| * | Kill recursive splsoftnet()s. | mpi | 2016-11-16 | 1 | -28/+27 |
| * | Use __func__ in panic strings to reduce noise when grepping. | mpi | 2016-11-15 | 1 | -4/+4 |
| * | Use goto for consistently instead of splx() and return. | mpi | 2016-11-07 | 1 | -5/+4 |
| * | One more timeout_set_proc(9) conversion. | mpi | 2016-10-04 | 1 | -2/+2 |
| * | For incomming connections keep the TF_NOPUSH flag if TCP_NOPUSH was | bluhm | 2016-09-19 | 1 | -2/+2 |
| * | all pools have their ipl set via pool_setipl, so fold it into pool_init. |   dlg | 2016-09-15 | 1 | -4/+3 |
| * | Use 'sc_route{4,6}' directly instead of casting them to 'struct route *'. | mpi | 2016-08-31 | 1 | -6/+3 |
| * | Make the size for the syn cache hash array tunable. As we are | bluhm | 2016-07-20 | 1 | -8/+31 |
| * | Make accepted sockets inherit IP_TTL from the listening socket. | jca | 2016-07-01 | 1 | -2/+5 |
| * | Missing "break;" in switch statement; repairs IP_MINTTL. | jca | 2016-06-27 | 1 | -1/+2 |
| * | Implement IPV6_MINHOPCOUNT support. | jca | 2016-06-27 | 1 | -3/+13 |
| * | Copy inp_hops from the listening socket to the accepted one and use | bluhm | 2016-06-27 | 1 | -2/+3 |
| * | The variable swapping between inp, newinp and oldinpcb in syn_cache_get() | bluhm | 2016-06-27 | 1 | -20/+9 |
| * | Fix typo in comment. From Kapetanakis Giannis | bluhm | 2016-06-09 | 1 | -2/+2 |
| * | If one of the TCP syn cache buckets overflow, it might be a collision | bluhm | 2016-03-31 | 1 | -1/+6 |
