NetBSD/doc/TODO.smpnet
2017-02-10 03:59:02 +00:00

98 lines
1.8 KiB
Plaintext

$NetBSD: TODO.smpnet,v 1.2 2017/02/10 03:59:02 ozaki-r Exp $
MP-safe components
==================
- bridge(4)
- bpf(4)
- gif(4)
- npf(7)
- pfil(9)
- pppoe(4)
- if_spppsubr.c
- tun(4)
- vioif(4)
- vmx(4)
- wm(4)
- Layer 2 (only Ethernet)
- if_ethersubr.c
- Most Layer 3
Non MP-safe components and kernel options
=========================================
- agr(4)
- altq(4)
- carp(4)
- etherip(4)
- faith(4)
- gre(4)
- ieee80211(4)
- ipf(4)
- ipsec(4)
- kttcp(4)
- mpls(4)
- opencrypto(9)
- pf(4)
- ppp(4)
- sl(4)
- stf(4)
- strip(4)
- if_srt
- tap(4)
- vlan(4)
- netsmb
- netnatm
- netisbn
- netatalk
- netbt
- netkey
- if_arcsubr.c
- if_atmsubr.c
- if_ecosubr.c
- if_fddisubr.c
- if_hippisubr.c
- if_ieee1394subr.c
- if_tokensubr.c
- DCCP
- IGMP
- IPSELSRC
- MROUTING
- NFS
- PIM
- SCTP
- TCP
- UDP
- Layer 4
- IP multicast
- Most network device drivers
Know issues
===========
bpf
---
MP-ification of bpf requires all of bpf_mtap* are called in normal LWP context
or softint context, i.e., not in hardware interrupt context. For Tx, all
bpf_mtap satisfy the requrement. For Rx, most of bpf_mtap are called in softint.
Unfortunately some bpf_mtap on Rx are still called in hardware interrupt context.
This is the list of the functions that have such bpf_mtap:
- sca_frame_process() @ sys/dev/ic/hd64570.c
- en_intr() @ sys/dev/ic/midway.c
- rxintr_cleanup() and txintr_cleanup() @ sys/dev/pci/if_lmc.c
- ipr_rx_data_rdy() @ sys/netisdn/i4b_ipr.c
Ideally we should make the functions run in softint somehow, but we don't have
actual devices, no time (or interest/love) to work on the task, so instead we
provide a deferred bpf_mtap mechanism that forcibly runs bpf_mtap in softint
context. It's a workaround and once the functions run in softint, we should use
the original bpf_mtap again.