Commit Graph

19 Commits

Author SHA1 Message Date
maxv cd974a5908 Remove the Econet code. It was part of acorn26, which was removed a
month ago.
2018-02-27 14:28:01 +00:00
ozaki-r 21a3f65ab7 Mention the limitation of enabling both NET_MPSAFE and ALTQ 2017-12-05 03:23:29 +00:00
ozaki-r 9faa031948 Mention IPv6 address selection policy isn't MP-safe yet
Though it's not a problem until a policy is set.
2017-11-20 09:01:20 +00:00
ozaki-r 3a2af74328 Mention ec_multi* 2017-10-25 07:35:40 +00:00
ozaki-r e3d0b2cc0d Mention NOMPSAFE 2017-10-12 03:31:39 +00:00
knakahara 3ceeffee3e add opencrypto(9)'s scalability comment 2017-10-12 03:27:00 +00:00
ozaki-r a38b799eca Write known issues on scalability 2017-08-10 09:26:55 +00:00
ozaki-r fbb0de677c Update
ipsec(4), opencrypto(9) and vlan(4) are now MP-safe.
2017-08-10 09:08:54 +00:00
ozaki-r a0123401b6 Write about bpf's statistic counters 2017-03-30 06:50:53 +00:00
ozaki-r 6dc0e16b98 Write about lingering obsolete variables due to kvm(3) 2017-03-30 04:37:58 +00:00
msaitoh ff07a3d986 Add ixv(4) to MP-safe component's list. 2017-03-11 07:23:13 +00:00
ozaki-r c5fe62ba0f Add ixg(4) 2017-03-11 06:40:19 +00:00
ozaki-r 1d5210cbd3 Tidy up again 2017-03-09 06:21:54 +00:00
ozaki-r 5562362b1a Tidy up the lists 2017-03-08 07:32:58 +00:00
ozaki-r ab05762cd7 Remove multicast stuffs from the list of Non MP-safe components 2017-03-08 06:59:36 +00:00
ozaki-r 24d5bbc8ed Add l2tp(4) 2017-02-22 04:44:16 +00:00
ozaki-r 0e2f0c63b2 Add BRIDGE_IPF 2017-02-13 04:01:11 +00:00
ozaki-r e87e25be9f Add many entries 2017-02-10 03:59:02 +00:00
ozaki-r 9674e2224b Defer bpf_mtap in Rx interrupt context to softint
bpf_mtap of some drivers is still called in hardware interrupt context.
We want to run them in softint as well as bpf_mtap of most drivers
(see if_percpuq_softint and if_input).

To this end, bpf_mtap_softint mechanism is implemented; it defers
bpf_mtap processing to a dedicated softint for a target driver.
By using the machanism, we can move bpf_mtap processing to softint
without changing target drivers much while it adds some overhead
on CPU and memory. Once target drivers are changed to softint-based,
we should return to normal bpf_mtap.

Proposed on tech-kern and tech-net
2017-01-24 09:05:27 +00:00