| Commit message (Expand) | Author | Age | Files | Lines |
|---|
| * | Convert the tcp segment reassembly queue to UMA and limit the maximum | andre | 2004-02-24 | 1 | -9/+77 |
| * | Backout MT_TAG removal (i.e. bring back MT_TAGs) for now, as dummynet is | mlaier | 2004-02-18 | 1 | -2/+6 |
| * | IPSEC and FAST_IPSEC have the same internal API now; | ume | 2004-02-17 | 1 | -16/+8 |
| * | This set of changes eliminates the use of MT_TAG "pseudo mbufs", replacing | mlaier | 2004-02-13 | 1 | -6/+2 |
| * | Brucification. | bms | 2004-02-13 | 1 | -1/+1 |
| * | Remove an unnecessary initialization that crept in from the code which | bms | 2004-02-12 | 1 | -2/+1 |
| * | Initial import of RFC 2385 (TCP-MD5) digest support. | bms | 2004-02-11 | 1 | -1/+16 |
| * | pass pcb rather than so. it is expected that per socket policy | ume | 2004-02-03 | 1 | -2/+2 |
| * | Merge from DragonFlyBSD rev 1.10: | hsu | 2004-01-20 | 1 | -6/+5 |
| * | Limiters and sanity checks for TCP MSS (maximum segement size) | andre | 2004-01-08 | 1 | -0/+60 |
| * | Enable the following TCP options by default to give it more exposure: | andre | 2004-01-06 | 1 | -2/+2 |
| * | Restructure a too broad ifdef which was disabling the setting of the | andre | 2003-11-25 | 1 | -2/+4 |
| * | Introduce tcp_hostcache and remove the tcp specific metrics from | andre | 2003-11-20 | 1 | -144/+200 |
| * | Introduce a MAC label reference in 'struct inpcb', which caches | rwatson | 2003-11-18 | 1 | -2/+2 |
| * | dropwithreset is not needed in this case as tcp_drop() is already notifying | andre | 2003-11-12 | 1 | -1/+1 |
| * | o correct locking problem: the inpcb must be held across tcp_respond | sam | 2003-11-08 | 1 | -3/+3 |
| * | speedup stream socket recv handling by tracking the tail of | sam | 2003-10-28 | 1 | -3/+3 |
| * | enclose IPv6 part with ifdef INET6. | ume | 2003-10-20 | 1 | -2/+3 |
| * | correct linkmtu handling. | ume | 2003-10-20 | 1 | -2/+11 |
| * | - add dom_if{attach,detach} framework. | ume | 2003-10-17 | 1 | -2/+1 |
| * | A number of patches in the last years have created new return paths | harti | 2003-08-13 | 1 | -0/+21 |
| * | Unify the "send high" and "recover" variables as specified in the | hsu | 2003-07-15 | 1 | -19/+24 |
| * | Add /* FALLTHROUGH */ | phk | 2003-05-31 | 1 | -0/+1 |
| * | Correct a bug introduced with reduced TCP state handling; make | rwatson | 2003-05-07 | 1 | -1/+1 |
| * | Explicitly declare 'int' parameters. | obrien | 2003-04-21 | 1 | -0/+1 |
| * | Observe conservation of packets when entering Fast Recovery while | hsu | 2003-04-01 | 1 | -3/+21 |
| * | Greatly simplify the unlocking logic by holding the TCP protocol lock until | hsu | 2003-03-13 | 1 | -8/+2 |
| * | Add support for RFC 3390, which allows for a variable-sized | hsu | 2003-03-13 | 1 | -2/+9 |
| * | Implement the Limited Transmit algorithm (RFC 3042). | hsu | 2003-03-12 | 1 | -0/+14 |
| * | Remove a panic(); if the zone allocator can't provide more timewait | jlemon | 2003-03-08 | 1 | -4/+3 |
| * | In timewait state, if the incoming segment is a pure in-sequence ack | jlemon | 2003-02-26 | 1 | -2/+4 |
| * | The TCP protocol lock may still be held if the reassembly queue dropped FIN. | jlemon | 2003-02-26 | 1 | -1/+2 |
| * | tcp_twstart() need to be called with the TCP protocol lock held to avoid | hsu | 2003-02-24 | 1 | -6/+8 |
| * | Pass the right function to callout_reset() for a compressed | hsu | 2003-02-24 | 1 | -1/+1 |
| * | Yesterday just wasn't my day. Remove testing delta that crept into the diff. | jlemon | 2003-02-23 | 1 | -1/+1 |
| * | Check to see if the TF_DELACK flag is set before returning from | jlemon | 2003-02-22 | 1 | -8/+7 |
| * | Add a TCP TIMEWAIT state which uses less space than a fullblown TCP | jlemon | 2003-02-19 | 1 | -30/+186 |
| * | Correct comments. | jlemon | 2003-02-19 | 1 | -7/+4 |
| * | Clean up delayed acks and T/TCP interactions: | jlemon | 2003-02-19 | 1 | -28/+27 |
| * | The protocol lock is always held in the dropafterack case, so we don't | hsu | 2003-02-13 | 1 | -2/+2 |
| * | Add the TCP flags to the log message whenever log_in_vain is 1, not | cjc | 2003-02-02 | 1 | -8/+3 |
| * | Fix NewReno. | hsu | 2003-01-13 | 1 | -41/+44 |
| * | Remove the PAWS ack-on-ack debugging printf(). | dillon | 2002-12-30 | 1 | -5/+2 |
| * | Unravel a nested conditional. | hsu | 2002-12-20 | 1 | -21/+12 |
| * | Fix syntax in last commit. | dillon | 2002-12-17 | 1 | -3/+3 |
| * | Bruce forwarded this tidbit from an analysis Van Jacobson did on an | dillon | 2002-12-14 | 1 | -1/+6 |
| * | a better solution to building FAST_IPSEC w/o INET6 | sam | 2002-11-10 | 1 | -4/+0 |
| * | fixup FAST_IPSEC build w/o INET6 | sam | 2002-11-08 | 1 | -1/+4 |
| * | - Consistently update snd_wl1, snd_wl2, and rcv_up in the header | jeff | 2002-10-31 | 1 | -1/+15 |
| * | Don't need to check if SO_OOBINLINE is defined. | hsu | 2002-10-30 | 1 | -13/+8 |
