mptcp: support for queuing data at mptcp-level
Get series with b4
b4 am [email protected]Versions newest first · linked by author and title
- v3 Latest13 patches 9 repliesIn review
- v213 patches 1 replySuperseded
- v19 patches 3 repliesSuperseded
Patches in v3 No applies recorded yet
| # | Subject and files | Size | Replies | Applied |
|---|---|---|---|---|
| 1/13 | mptcp: more DATA FIN fixesnet/ net/ | +6 | 1 reply | |
| 2/13 | mptcp: don't skip needed acknet/ | +4 | 0 replies | |
| 3/13 | tcp: factor out __tcp_close() helperinclude/ net/ | +8 | 0 replies | |
| 4/13 | mptcp: introduce mptcp_schedule_worknet/ net/ net/ | +21 | 0 replies | |
| 5/13 | mptcp: reduce the arguments of mptcp_sendmsg_fragnet/ | +29 | 0 replies | |
| 6/13 | mptcp: add accounting for pending datanet/ net/ | +36 | 0 replies | |
| 7/13 | mptcp: introduce MPTCP snd_nxtnet/ net/ net/ | +16 | 0 replies | |
| 8/13 | mptcp: refactor shutdown and closenet/ net/ net/ +1 more | +216 | 0 replies | |
| 9/13 | mptcp: move page frag allocation in mptcp_sendmsg()net/ | +188 | 0 replies | |
| 10/13 | mptcp: try to push pending data on snd una updatesnet/ | +3 | 0 replies | |
| 11/13 | mptcp: rework poll+nospace handlingnet/ net/ net/ | +54 | 0 replies | |
| 12/13 | mptcp: keep track of advertised windows right edgenet/ net/ net/ | +67 | 4 replies | |
| 13/13 | mptcp: send explicit ack on delayed ack_seq incrnet/ | +22 | 0 replies |
Reviews trailers per patch
No Reviewed-by, Acked-by or Tested-by trailers for v3 yet.
Cover letter [MPTCP] [PATCH v3 00/13] mptcp: support for queuing data at mptcp-level
This is necessary to cope correctly with large sendbuffer (larger then snd wnd) while respecting the MPTCP level snd window.
A major rework of both xmit and shudown path is required to support this feature (patches 8 and 9). To try to keep the related patches as small as possible, a bunch of new helpers is created by patches 3-7.
Note that patch 5 can stand for it's own merit and possibly be upstreamed soon.
Finally patch 10 uses the MPTCP equivalent of tcp_push_pending_frames(), to spool queued data ad MPTCP level, as soon as the windows allow that.
Patches 1 and 2 are bugfixes for the current upstream tree will target -net/-net-next soon.
Patch 13 is possibly a bit too aggressive, perhaps it could be left staging in export branch for a while.
This iteration fixes all known pending issue present in previous snapshow. Note that we still hit some unexpected out of receive window events, but the issue was already present in the export branch and its fix is unrelated to this work.
Florian Westphal (2):
mptcp: rework poll+nospace handling
mptcp: keep track of advertised windows right edge
Paolo Abeni (11):
mptcp: more DATA FIN fixes
mptcp: don't skip needed ack
tcp: factor out __tcp_close() helper
mptcp: introduce mptcp_schedule_work
mptcp: reduce the arguments of mptcp_sendmsg_frag
mptcp: add accounting for pending data
mptcp: introduce MPTCP snd_nxt
mptcp: refactor shutdown and close
mptcp: move page frag allocation in mptcp_sendmsg()
mptcp: try to push pending data on snd una updates
mptcp: send explicit ack on delayed ack_seq incr
include/net/tcp.h | 1 + net/ipv4/tcp.c | 9 +- net/mptcp/options.c | 40 +- net/mptcp/pm.c | 3 +- net/mptcp/protocol.c | 909 +++++++++++++++++++++++++------------------ net/mptcp/protocol.h | 69 +++- net/mptcp/subflow.c | 34 +- 7 files changed, 648 insertions(+), 417 deletions(-)
Signature · 1 line
2.26.2