https://reviews.freebsd.org/D31648 It looks like these assertion checks broke the if_oce NIC driver. The first assert happens instantly upon loading the driver.
root@honeycomb-bsd ~# kldload if_oce oce0: <Emulex CNA NIC function:///11.0.50.0///> mem 0x46080000-0x46083fff,0x46000000-0x4601ffff,0x46020000-0x4603ffff at device 0.0 on pci1 oce1: <Emulex CNA NIC function:///11.0.50.0///> mem 0x46084000-0x46087fff,0x46040000-0x4605ffff,0x46060000-0x4607ffff at device 0.1 on pci1 panic: Assertion in_epoch(net_epoch_preempt) failed at /usr/src/sys/netinet/tcp_lro.c:1492 cpuid = 2 time = 1639350682 KDB: stack backtrace: db_trace_self() at db_trace_self db_trace_self_wrapper() at db_trace_self_wrapper+0x30 vpanic() at vpanic+0x174 panic() at panic+0x44 tcp_lro_flush_all() at tcp_lro_flush_all+0x1b0 oce_rq_handler() at oce_rq_handler+0x1f0 oce_intr() at oce_intr+0xdc taskqueue_run_locked() at taskqueue_run_locked+0x178 taskqueue_thread_loop() at taskqueue_thread_loop+0xc8 fork_exit() at fork_exit+0x74 fork_trampoline() at fork_trampoline+0x14 KDB: enter: panic [ thread pid 0 tid 100547 ] Stopped at kdb_enter+0x44: undefined f901811f db>
I put up a fix in review D33395. Can you test it? I don't have the hardware and therefore can't test it.
With that patch, driver is loading. And trying to push some traffic through seems to be working just fine. Thanks for the super fast response! root@honeycomb-bsd ~# speedtest-cli Retrieving speedtest.net configuration... Testing from --- (x.x.x.x)... Retrieving speedtest.net server list... Selecting best server based on ping... Hosted by Green House Data, Inc (Seattle, WA) [3.33 km]: 3.456 ms Testing download speed................................................................................ Download: 823.39 Mbit/s Testing upload speed...................................................................................................... Upload: 677.72 Mbit/s
(In reply to Vincent Milum Jr from comment #3) The patch has been updated. Could you test the new version, since I don't have the hardware to test the patch?
So far, so good with the new patch! :)
A commit in branch main references this bug: URL: https://cgit.FreeBSD.org/src/commit/?id=e363f832cfb283a543fa8e47ebd9e51817994fde commit e363f832cfb283a543fa8e47ebd9e51817994fde Author: Michael Tuexen <tuexen@FreeBSD.org> AuthorDate: 2021-12-18 22:43:00 +0000 Commit: Michael Tuexen <tuexen@FreeBSD.org> CommitDate: 2021-12-18 22:43:00 +0000 if_oce: fix epoch handling Thanks to gallatin@ for suggesting the patch. PR: 260330 Reported by: Vincent Milum Jr. Reviewed by: gallatin, glebius Tested by: Vincent Milum Jr. MFC after: 3 days Differential Revision: https://reviews.freebsd.org/D33395 sys/dev/oce/oce_if.c | 6 +++++- sys/dev/oce/oce_if.h | 1 + sys/dev/oce/oce_queue.c | 5 ++++- 3 files changed, 10 insertions(+), 2 deletions(-)
(In reply to Vincent Milum Jr from comment #5) Thanks for testing! The patch is committed.
A commit in branch stable/13 references this bug: URL: https://cgit.FreeBSD.org/src/commit/?id=257cd2f8c3c5f43dc6c16d49bea731d4c872ebec commit 257cd2f8c3c5f43dc6c16d49bea731d4c872ebec Author: Michael Tuexen <tuexen@FreeBSD.org> AuthorDate: 2021-12-18 22:43:00 +0000 Commit: Michael Tuexen <tuexen@FreeBSD.org> CommitDate: 2022-02-22 23:52:15 +0000 if_oce: fix epoch handling Thanks to gallatin@ for suggesting the patch. PR: 260330 Reported by: Vincent Milum Jr. Reviewed by: gallatin, glebius Tested by: Vincent Milum Jr. Differential Revision: https://reviews.freebsd.org/D33395 (cherry picked from commit e363f832cfb283a543fa8e47ebd9e51817994fde) sys/dev/oce/oce_if.c | 6 +++++- sys/dev/oce/oce_if.h | 1 + sys/dev/oce/oce_queue.c | 5 ++++- 3 files changed, 10 insertions(+), 2 deletions(-)