Commit Graph

34 Commits

Author SHA1 Message Date
thorpej b8e08ca413 FDDI support has been removed. 2020-01-20 18:40:06 +00:00
thorpej 0c1c4978e2 Token Ring has been removed. 2020-01-19 20:02:23 +00:00
thorpej 6d2f94e573 HIPPI has been removed. 2020-01-19 16:58:22 +00:00
msaitoh ec1e322ab7 Protecting ec_multi* of ethercom with ec_lock have been finished now. 2020-01-06 15:21:29 +00:00
msaitoh 2d56e9f118 Add aq(4) and ixl(4) to the MPSAFE component list. 2020-01-06 05:38:59 +00:00
ozaki-r 611478defb Add another known issue (if_flags) 2019-03-27 06:56:37 +00:00
ozaki-r d0b5d19ecc Add another known issue 2019-03-26 05:17:17 +00:00
pgoyette f24c721fc4 Note that kernels with NET_MPSAFE won't work with non-NET_MPSAFE modules.
XXX The initial merge of the [pgoyette-compat] branch will NOT address
XXX this issue.
2019-01-21 02:28:25 +00:00
maxv 02d7a902b5 Drop LMC-related entry from TODO.smpnet, and note removal of LMC. 2018-12-12 07:07:30 +00:00
maxv 23198f3a45 remove references to isdn 2018-09-23 13:48:16 +00:00
maxv f1e25333a2 Note removal of midway and NATM, and prune the entries from TODO.smpnet. 2018-09-06 06:46:25 +00:00
maxv 735ddbc5b3 Retire EtherIP, we have L2TP instead. 2018-08-14 14:49:13 +00:00
ozaki-r 40e17cbfc8 Add ipsecif(4) 2018-08-07 07:19:28 +00:00
ozaki-r 6647f64d95 Categorize non MP-safe components into protected and unprotected ones 2018-08-07 07:19:09 +00:00
msaitoh 483517e3bb Move txintr_setup() stuff from lmc_interrupt() and do it in ifnet_start().
Now we can use bpf_mtap() in the TX path. Not tested.
2018-06-25 09:32:28 +00:00
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