illumos

2021-09-27

10:25 PM illumos gate Feature #14024: bhyve vm_suspend should be more flexible

Although @bhyve(1)@ does not use the forced-reinit, and propolis is configured to quiesce its vCPU threads prior to a... Patrick Mooney

09:39 PM illumos gate Feature #14024: bhyve vm_suspend should be more flexible

I ran all of the usual-suspects guests on a platform featuring this change. Each one successfully booted, and after ... Patrick Mooney

07:12 PM illumos gate Feature #14024: bhyve vm_suspend should be more flexible

The proposed fix for this adds a @VM_REINIT_F_FORCE_SUSPEND@ flag, available for use in @VM_REINIT@ ioctl calls. The... Patrick Mooney

06:01 PM illumos gate Bug #14100: bhyve misses TLB flush for shadowed cr0

In addition to the specific Windows+SMEP test, I also ran the typical gauntlet of guest tests on Intel gear with the ... Patrick Mooney

04:57 PM illumos gate Bug #14100: bhyve misses TLB flush for shadowed cr0

This has been tested on Intel hardware capable of SMEP, where exposing that capability to Windows under bhyve was cau... Patrick Mooney

2021-09-24

03:32 AM illumos gate Bug #14101: bhyve should expose shadowed bits in CRs

With the proposed fix in place, changes to cr0 which effect the shadowed bits are observable when reading the value b... Patrick Mooney

03:06 AM illumos gate Bug #14101: bhyve should expose shadowed bits in CRs

Prior to putting the fix in place, shadowed bits are not reflected in values queried from cr0 (and cr4):... Patrick Mooney

2021-09-23

04:50 AM illumos gate Bug #14101: bhyve should expose shadowed bits in CRs

It should be noted that the SVM logic for this properly handles the shadowed bits in %cr0 (and does not shadow %cr4) Patrick Mooney

04:49 AM illumos gate Bug #14101 (Closed): bhyve should expose shadowed bits in CRs

The VMX side of bhyve requires shadowing certain bits in %cr0 and %cr4, since they are required to be 0 or 1, regardl... Patrick Mooney

04:44 AM illumos gate Bug #14100 (Closed): bhyve misses TLB flush for shadowed cr0

During initial testing for #14081, which includes an update which exposes SMEP/SMAP to tests, several folks discovere... Patrick Mooney