laantungir/fips
1
0
Fork 0
mirror of https://github.com/jmcorgan/fips.git synced 2026-10-06 03:28:24 +00:00
Code Issues Packages Projects Releases Wiki Activity

Correct what the changelog says the native API uses on FreeBSD

Browse Source 
The entry said the listener uses SOCK_SEQPACKET on Linux and FreeBSD. That
was true when it was written and is not true now: FreeBSD accepts the
constant and returns something that is not an atomic-record socket, so it
takes SOCK_DGRAM alongside macOS, for a different reason and with the same
effect. The entry now says which kernel does what and that both facts were
measured on the image rather than inferred.
This commit is contained in:
Johnathan Corgan
2026-08-22 14:54:17 +01:00
parent 8005eedf41
commit a1f57c1f0a
1 changed files with 12 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files
CHANGELOG.md
+12 -9
View File
@@ -78,15 +78,18 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
counterpart in Berkeley sockets and a client author must know it: the v1
wire carries no half-close, so nothing peer-driven ever closes a flow, and a
server written to read until the flow ends waits for a signal that cannot
arrive. The listener uses `SOCK_SEQPACKET` on Linux and FreeBSD and
`SOCK_DGRAM` on macOS, which does not implement `SOCK_SEQPACKET` for
`AF_UNIX`; both keep the message boundaries the API's contract with its
clients rests on. The two kernels signal a closed peer differently and were
measured rather than reasoned about, so the receive path treats a Darwin
`ECONNRESET` as end of file alongside the `POLLHUP` and zero-byte read that
Linux gives. `EAGAIN` is deliberately not in that company: it means the
socket is empty and the peer alive, so it stays an error and the caller
waits again.
arrive. The listener uses `SOCK_SEQPACKET` on Linux and `SOCK_DGRAM` on macOS
and FreeBSD; both keep the message boundaries the API's contract with its
clients rests on. macOS does not implement `SOCK_SEQPACKET` for `AF_UNIX` at
all. FreeBSD accepts the constant and returns a socket that is not an
atomic-record socket, so consecutive messages coalesce and a zero-length
message is dropped rather than delivered; both were measured on the FreeBSD
15.1 image rather than reasoned about. The three kernels signal a closed
peer differently and were measured too, so the receive path treats a Darwin
or FreeBSD `ECONNRESET` as end of file alongside the `POLLHUP` and
zero-byte read that Linux gives. `EAGAIN` is deliberately not in that
company: it means the socket is empty and the peer alive, so it stays an
error and the caller waits again.
#### OpenWrt mesh