Instead of using generic socket code, create Netlink specific socket
buffer. It is a simple TAILQ of writes that came from userland. This
saves us one memory allocation that could fail and one memory copy.
Details
Details
- Reviewers
melifaro rcm - Group Reviewers
network - Commits
- rG660bd40a598a: netlink: use domain specific send buffer
Diff Detail
Diff Detail
- Repository
- rG FreeBSD src repository
- Lint
Lint Skipped - Unit
Tests Skipped - Build Status
Buildable 54346 Build 51236: arc lint + arc unit
Event Timeline
| sys/netlink/netlink_io.c | ||
|---|---|---|
| 237 | any concerns on copying the previous approach? (grab all Q and the insert back if we hit the limit)? | |