diff options
| author |  Johannes Berg <johannes.berg@intel.com>
| 2021-09-16 13:09:22 +0200 |
|---|---|---|
| committer |  Richard Weinberger <richard@nod.at>
| 2021-12-21 21:29:30 +0100 |
| commit | 85e73968a040c642fd38f6cba5b73b61f5d0f052 (patch) | |
| tree | 4f092ae8b992d08d18e2da50022e25f0a98fb3b4 /arch/x86/um/sys_call_table_32.c | |
| parent | lib/logic_iomem: Fix operation on 32-bit (diff) | |
| download | linux-85e73968a040c642fd38f6cba5b73b61f5d0f052.tar.gz linux-85e73968a040c642fd38f6cba5b73b61f5d0f052.tar.bz2 linux-85e73968a040c642fd38f6cba5b73b61f5d0f052.zip | |
um: virtio_uml: Fix time-travel external time propagation
When creating an external event, the current time needs to
be propagated to other participants of a simulation. This
is done in the places here where we kick a virtq etc.
However, it must be done for _all_ external events, and
that includes making the initial socket connection and
later closing it. Call time_travel_propagate_time() to do
this before making or closing the socket connection.
Apparently, at least for the initial connection creation,
due to the remote side in my use cases using microseconds
(rather than nanoseconds), this wasn't a problem yet; only
started failing between 5.14-rc1 and 5.15-rc1 (didn't test
others much), or possibly depending on the configuration,
where more delays happen before the virtio devices are
initialized.
Fixes: 88ce64249233 ("um: Implement time-travel=ext")
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Richard Weinberger <richard@nod.at>
Diffstat (limited to 'arch/x86/um/sys_call_table_32.c')
0 files changed, 0 insertions, 0 deletions