src/sys/dev/hyperv/netvsc, branch release/13.1.0 FreeBSD source tree https://cgit-dev.freebsd.org/src/atom?h=release%2F13.1.0 2021-12-10T10:50:01Z Hyper-V: hn: Enter network epoch when required 2021-12-10T10:50:01Z Michael Tuexen tuexen@FreeBSD.org 2021-08-26T17:27:04Z urn:sha1:42cb69e147e30000bd35c97d4212da4540b862dd PR: 254695 (cherry picked from commit 26d79d40a74fc804c76acd88a1f8f10f9827a2b3) if_hn: Fix a few typos in comments and a sysctl description 2021-12-03T15:54:11Z Gordon Bergling gbe@FreeBSD.org 2021-11-30T09:35:14Z urn:sha1:f51048b535b3082ce1336c631e36a37b4b5a9735 - s/segement/segment/ (cherry picked from commit b15a632c418f6532fe7c3002b4085c61b1e278b0) netvsc: Fix a typo in a comment 2021-10-06T06:19:58Z Gordon Bergling gbe@FreeBSD.org 2021-10-02T08:42:18Z urn:sha1:badbe6a4a8171ee07c6c364849134f464e9c9276 - s/prefered/preferred/ (cherry picked from commit 9ebd651b58502f0572a7832d088f53f7a2ad00a5) Hyper-V: hn: Initialize the internal field of per packet info on tx path 2021-03-29T10:21:30Z Wei Hu whu@FreeBSD.org 2021-03-15T10:20:52Z urn:sha1:2fbdbfaa0c4407547060f8a0ca4d0d04bbf09f9e The RSC support feature introduced a bit field "rm_internal" in struct rndis_pktinfo with total size unchanged. The guest does not use this field in the tx path. However we need to initialize it to zero in case older hosts which are not aware of this field. Fixes: a491581f ("Hyper-V: hn: Enable vSwitch RSC support") MFC after: 2 weeks Sponsored by: Microsoft (cherry picked from commit 805dbff6c36a6cd84491aa53a02315fa025734cc) Hyper-V: hn: Enable vSwitch RSC support in hn netvsc driver 2021-03-29T10:20:03Z Wei Hu whu@FreeBSD.org 2021-03-12T04:35:16Z urn:sha1:cdc59163ff8e8f2a98ef8ca02773d1d2047e3aae Receive Segment Coalescing (RSC) in the vSwitch is a feature available in Windows Server 2019 hosts and later. It reduces the per packet processing overhead by coalescing multiple TCP segments when possible. This happens mostly when TCP traffics are among different guests on same host. This patch adds netvsc driver support for this feature. The patch also updates NVS version to 6.1 as needed for RSC enablement. MFC after: 2 weeks Sponsored by: Microsoft Differential Revision: https://reviews.freebsd.org/D29075 (cherry picked from commit a491581f3f8df07cdff0236bd556895205929af4) Hyper-V: hn: Store host hash value in flowid 2021-03-29T10:18:20Z Wei Hu whu@FreeBSD.org 2021-02-24T05:07:46Z urn:sha1:a86be0da9a03840bcf19499428e8868728c0082e When rx packet contains hash value sent from host, store it in the mbuf's flowid field so when the same mbuf is on the tx path, the hash value can be used by the host to determine the outgoing network queue. MFC after: 2 weeks Sponsored by: Microsoft (cherry picked from commit 80f39bd95f22322152709ea5fae3a3c546044c9c) Hyper-V: hn: Relinquish cpu in HN_LOCK to avoid deadlock 2020-10-15T11:44:28Z Wei Hu whu@FreeBSD.org 2020-10-15T11:44:28Z urn:sha1:b3460f44524b145c6c8a760ebe65052560a810bf The try lock loop in HN_LOCK put the thread spinning on cpu if the lock is not available. It is possible to cause deadlock if the thread holding the lock is sleeping. Relinquish the cpu to work around this problem even it doesn't completely solve the issue. The priority inversion could cause the livelock no matter how less likely it could happen. A more complete solution may be needed in the future. Reported by: Microsoft, Netapp MFC after: 2 weeks Sponsored by: Microsoft Mark more nodes as CTLFLAG_MPSAFE or CTLFLAG_NEEDGIANT (17 of many) 2020-02-26T14:26:36Z Pawel Biernacki kaktus@FreeBSD.org 2020-02-26T14:26:36Z urn:sha1:7029da5c36f2d3cf6bb6c81bf551229f416399e8 r357614 added CTLFLAG_NEEDGIANT to make it easier to find nodes that are still not MPSAFE (or already are but aren’t properly marked). Use it in preparation for a general review of all nodes. This is non-functional change that adds annotations to SYSCTL_NODE and SYSCTL_PROC nodes using one of the soon-to-be-required flags. Mark all obvious cases as MPSAFE. All entries that haven't been marked as MPSAFE before are by default marked as NEEDGIANT Approved by: kib (mentor, blanket) Commented by: kib, gallatin, melifaro Differential Revision: https://reviews.freebsd.org/D23718 Although most of the NIC drivers are epoch ready, due to peer pressure 2020-02-24T21:07:30Z Gleb Smirnoff glebius@FreeBSD.org 2020-02-24T21:07:30Z urn:sha1:e87c4940156c9a218cab4fd35f4d487dc57e7aa3 switch over to opt-in instead of opt-out for epoch. Instead of IFF_NEEDSEPOCH, provide IFF_KNOWSEPOCH. If driver marks itself with IFF_KNOWSEPOCH, then ether_input() would not enter epoch when processing its packets. Now this will create recursive entrance in epoch in >90% network drivers, but will guarantee safeness of the transition. Mark several tested drivers as IFF_KNOWSEPOCH. Reviewed by: hselasky, jeff, bz, gallatin Differential Revision: https://reviews.freebsd.org/D23674 Introduce flag IFF_NEEDSEPOCH that marks Ethernet interfaces that 2020-01-23T01:41:09Z Gleb Smirnoff glebius@FreeBSD.org 2020-01-23T01:41:09Z urn:sha1:0921628ddce1c29441ddb694e04e9c1e9fe356c8 supposedly may call into ether_input() without network epoch. They all need to be reviewed before 13.0-RELEASE. Some may need be fixed. The flag is not planned to be used in the kernel for a long time.