An error occurred fetching the project authors.
- 10 Sep, 2004 3 commits
-
-
David S. Miller authored
We run into a potential problem if we are doing TSO and we reduce the congestion window. We might create a case where the TSO packet is what we need to resend but the congestion window is not large enough to allow it through. The fix is very simple, since tcp_retransmit_skb() is going to chop the size of the packet down to size of the normal non-TSO MSS, we can pretend at the top level that each SKB is composed of only one real MSS worth of data. Signed-off-by: David S. Miller <davem@davemloft.net>
-
David S. Miller authored
Calls to tcp_fragment() change the tso_factor of an SKB, so we need to deal with that. Signed-off-by: David S. Miller <davem@davemloft.net>
-
David S. Miller authored
Do not reference the tso_factor of SKB buff until it is initialized. Signed-off-by: David S. Miller <davem@davemloft.net>
-
- 09 Sep, 2004 2 commits
-
-
David S. Miller authored
We divide by the wrong MSS. Signed-off-by: David S. Miller <davem@davemloft.net>
-
David S. Miller authored
Unused outside of tcp_output.c Signed-off-by: David S. Miller <davem@davemloft.net>
-
- 08 Sep, 2004 1 commit
-
-
Baruch Even authored
Signed-off-by: David S. Miller <davem@davemloft.net>
-
- 07 Sep, 2004 3 commits
-
-
David S. Miller authored
It needs to be set so that congestion window calculations have a valid value to work with. This means that doing it at write queue running time is too late. Signed-off-by: David S. Miller <davem@davemloft.net>
-
David S. Miller authored
Eliminate tp->mss_tso_factor. Instead, we calculate the SKB tso factor as we walk the write queue for initial transmit or fragment SKBs. Signed-off-by: David S. Miller <davem@davemloft.net>
-
David S. Miller authored
Previously TSO would not abide by the congestion window properly. Essentially, each TSO packet would be trated just like 1 normal packet, even though a TSO packet generates more than 1 normal packet. This violates congestion window rules entirely. So now we record the TSO factor, a count of how many real packets a TSO packet will generate, and include this in all the packet counting routines. This initial version has a bug in that skb_entail() is not the correct time to figure out the TSO factor for the SKB, and tp->mss_tso_factor is not necessarily the right value for a given SKB. Will fix this up next. Signed-off-by: David S. Miller <davem@davemloft.net>
-
- 26 Aug, 2004 1 commit
-
-
Stephen Hemminger authored
This patch gets rid of the tcp_default_win_scale sysctl and instead computes the optimum maximum window scale. It just means one less thing to have to tune. I also moved the code out of the inline because it gets called three places and isn't in the critical path. As a side effect, it will cause a smaller window scale for many people since the default tcp_rmem fits in a win_scale of 2. This is allows for finer grain windows (good), but may mask some of the problems with bad implementations we have already seen (bad). Signed-off-by: Stephen Hemminger <shemminger@osdl.org> Signed-off-by: David S. Miller <davem@redhat.com>
-
- 22 Jul, 2004 1 commit
-
-
David S. Miller authored
Signed-off-by: David S. Miller <davem@redhat.com>
-
- 08 Jul, 2004 1 commit
-
-
Hideaki Yoshifuji authored
Signed-off-by: Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org>
-
- 07 Jul, 2004 1 commit
-
-
John Heffner authored
Signed-off-by: John Heffner <jheffner@psc.edu> Signed-off-by: David S. Miller <davem@redhat.com>
-
- 01 Jul, 2004 1 commit
-
-
Stephen Hemminger authored
Current 2.6.7 tree acts as if it is alway under memory pressure because a recent change did a s/tcp_memory_pressure/tcp_prot.memory_pressure/. The problem is tcp_prot.memory_pressure is a pointer, so it is always non-zero! Rather than using *tcp_prot.memory_pressure, just go back to looking at tcp_memory_pressure. Signed-off-by: Stephen Hemminger <shemminger@osdl.org> Signed-off-by: David S. Miller <davem@redhat.com>
-
- 23 Jun, 2004 1 commit
-
-
Arnaldo Carvalho de Melo authored
Only new requirement was to add a max_header field to struct sock sk_prot member. Signed-off-by: Arnaldo Carvalho de Melo <acme@conectiva.com.br>
-
- 22 Jun, 2004 2 commits
-
-
Arnaldo Carvalho de Melo authored
Signed-off-by: Arnaldo Carvalho de Melo <acme@conectiva.com.br>
-
Arnaldo Carvalho de Melo authored
The poor cousins also need this, LLC will be the first to use it. Signed-off-by: Arnaldo Carvalho de Melo <acme@conectiva.com.br>
-
- 21 Jun, 2004 1 commit
-
-
Arnaldo Carvalho de Melo authored
Will be used by the poor cousins Signed-of-by: Arnaldo Carvalho de Melo <acme@conectiva.com.br>
-
- 20 Jun, 2004 1 commit
-
-
Arnaldo Carvalho de Melo authored
Signed-off-by: Arnaldo Carvalho de Melo <acme@conectiva.com.br>
-
- 12 Jun, 2004 1 commit
-
-
Arnaldo Carvalho de Melo authored
Move tcp sk_wmem_queued related functions to net/core/stream.c, will be used by other SOCK_STREAM protocols, starting with LLC. Also move the tcp_charge_skb to sock.h, for the same reasons. Signed-off-by: Arnaldo Carvalho de Melo <acme@conectiva.com.br>
-
- 09 Jun, 2004 1 commit
-
-
Arnaldo Carvalho de Melo authored
This makes the best practices already in place in bluetooth and tcp/ip available for all protocols, i.e. references must be managed when associating timers with struct sock instances, also makes the code a bit more clean. Signed-off-by: Arnaldo Carvalho de Melo <acme@conectiva.com.br>
-
- 27 Apr, 2004 1 commit
-
-
Stephen Hemminger authored
The function tcp_send_skb is only called from tcp_fin, and is always called with force_queue=1. Therefore, it no longer needs to be global and the code to send right now can be removed. Because it always queues, change the name as well, and fix up the comment.
-
- 21 Apr, 2004 2 commits
-
-
David S. Miller authored
A forward port of an old 2.3.x kernel hack done years ago. I (DaveM) did the first rough port, Stephen Hemminger actually cleaned it up and made it usable.
-
David S. Miller authored
-
- 28 Sep, 2003 1 commit
-
-
Arnaldo Carvalho de Melo authored
-
- 25 Jun, 2003 1 commit
-
-
David S. Miller authored
1) Remove srtt etc. tests in tcp_init_cwnd, was buggy anyways. 2) Add RTAX_INITCWMD route metric, use this in tcp_init_cwnd() if non-zero. 3) Add RTAX_FEATURES (to enable/disable ECN/SACK/TIMESTAMPS on a per-route basis), currently unused.
-
- 05 Jun, 2003 1 commit
-
-
Alexey Kuznetsov authored
reconciling TCP_CORK and TCP_NODELAY
-
- 04 Jun, 2003 1 commit
-
-
Arnaldo Carvalho de Melo authored
With this the data dependency is reduced to just making sure that the first member of both struct sock and struct tcp_tw_bucket are a struct sock_common. Also makes it easier to grep for struct sock and struct tcp_tw_bucket usage in the tree as all the members in those structs are prefixed, respectively, with sk_ and tw_, like struct inode (i_), struct block_device (bd_), etc. Checked namespace with make tags/ctags, just one colision with the macros for the struct sock members, with a wanrouter struct, fixed that s/sk_state/state_sk/g in the wanrouter struct. Checked as well if the names of the members in both structs collided with some macro, none found.
-
- 28 May, 2003 1 commit
-
-
Arnaldo Carvalho de Melo authored
This makes: 1. simpler primitive to access struct sock flags, shorter 2. we check if the flag is valid by using enum sock_flags 3. we can change the implementation to an open coded bit operations if it proves to be faster than the more general bit manipulation routines now used, i.e. we only have to change sock.h, not the whole net tree like now
-
- 28 Apr, 2003 1 commit
-
-
Steven Cole authored
-
- 06 Apr, 2003 1 commit
-
-
James Morris authored
-
- 19 Mar, 2003 1 commit
-
-
Alexey Kuznetsov authored
1. Add local_df field to struct sk_buff to mark packets which are to be fragmented locally despite of their IPv6ness of IP DF flag 2. Add ext2_header_len to tcp_opt to keep memory of part of header length depending on route 3. Add trailer_len to struct dst_entry and xfrm_state to know how much of space should be reserved at tail of frame for subsequent transformations. 4. [BUG] icv_trun_len must be used while mss claculation, not icv_full_length.
-
- 02 Mar, 2003 1 commit
-
-
James Morris authored
-
- 10 Feb, 2003 1 commit
-
-
David S. Miller authored
-
- 28 Jan, 2003 1 commit
-
-
Alexey Kuznetsov authored
-
- 21 Jan, 2003 1 commit
-
-
Sridhar Samudrala authored
-
- 20 Jan, 2003 1 commit
-
-
Sridhar Samudrala authored
-
- 24 Oct, 2002 1 commit
-
-
Alexey Kuznetsov authored
- Changed dst named metrics, to RTAX_MAX metrics array. - Add inline shorthands to access them - Add update_pmtu and get_mss to DST ops. - Add path component to DST, it is DST itself by default.
-
- 02 Sep, 2002 1 commit
-
-
Alexey Kuznetsov authored
-
- 28 Aug, 2002 1 commit
-
-
Alexey Kuznetsov authored
-