Commit Graph

11 Commits

Author SHA1 Message Date
JackDoan 3b1004588d spicy offload chkpt 2026-08-03 16:40:36 -05:00
JackDoan 5ea48c1677 stop trying to interpret TCP, reorder via message counter and hostinfo-creation-order 2026-08-03 14:42:25 -05:00
JackDoan d7bcfb5d6b drop TxBatcher interface 2026-07-31 13:58:33 -05:00
JackDoan 93946faf7a drop ECN support for this release 2026-07-31 13:38:16 -05:00
JackDoan 7ee5e29758 docs: align comments with the code they describe
- multi_coalesce/batch: the ordering contract now states what Flush
  actually guarantees -- per-flow DATA order -- and names the two
  shapes later data may legally overtake (pure ACKs by design, and
  unparseable in-flow shapes as an accepted tradeoff).
- validVnetHdr claimed DATA_VALID makes the stack skip L4 checksum
  verification; the tun write path ignores that bit entirely. What the
  header buys is the absence of NEEDS_CSUM.
- tun_darwin Write said "only valid for single threaded use"; it is
  concurrency-safe and concurrent callers exist.
- udp_coalesce eviction comment said "Seal it" but never sets sealed.
- recordCapability: note the gauges are process-global while the state
  is per-socket (last writer wins).
- drop a stale tunReadBufSize reference.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_014ugV2edVqoz3tBvq9J6yWp
2026-07-29 17:48:47 -05:00
Nate Brown 88872a8433 Don't fail on the batch at the first error (#1826) 2026-07-27 14:43:30 -05:00
JackDoan ef0e3015f9 decrypt in place 2026-07-24 16:44:05 -05:00
JackDoan 69fa9e4a2e unslop some comments 2026-07-24 16:39:03 -05:00
JackDoan f04dd3bcc3 switch to ASM vector checksum 2026-07-24 16:37:30 -05:00
JackDoan 187afac7b5 GSO/GRO offloads, with TCP+ECN and UDP support 2026-07-24 16:37:30 -05:00
JackDoan e7b121c82f better and batched tun interface 2026-07-24 16:33:52 -05:00