On Tue, 10 Aug 2021 01:04:38 +0100,
Oliver Upton [off-list ref] wrote:

On Wed, Aug 4, 2021 at 3:03 PM Oliver Upton [off-list ref] wrote:

quoted

On Wed, Aug 4, 2021 at 4:05 AM Oliver Upton [off-list ref] wrote:

quoted

On Wed, Aug 4, 2021 at 1:58 AM Oliver Upton [off-list ref] wrote:

quoted

KVM's current means of saving/restoring system counters is plagued with
temporal issues. At least on ARM64 and x86, we migrate the guest's
system counter by-value through the respective guest system register
values (cntvct_el0, ia32_tsc). Restoring system counters by-value is
brittle as the state is not idempotent: the host system counter is still
oscillating between the attempted save and restore. Furthermore, VMMs
may wish to transparently live migrate guest VMs, meaning that they
include the elapsed time due to live migration blackout in the guest
system counter view. The VMM thread could be preempted for any number of
reasons (scheduler, L0 hypervisor under nested) between the time that
it calculates the desired guest counter value and when KVM actually sets
this counter state.

Despite the value-based interface that we present to userspace, KVM
actually has idempotent guest controls by way of system counter offsets.
We can avoid all of the issues associated with a value-based interface
by abstracting these offset controls in new ioctls. This series
introduces new vCPU device attributes to provide userspace access to the
vCPU's system counter offset.

Patch 1 addresses a possible race in KVM_GET_CLOCK where
use_master_clock is read outside of the pvclock_gtod_sync_lock.

Patch 2 adopts Paolo's suggestion, augmenting the KVM_{GET,SET}_CLOCK
ioctls to provide userspace with a (host_tsc, realtime) instant. This is
essential for a VMM to perform precise migration of the guest's system
counters.

Patches 3-4 are some preparatory changes for exposing the TSC offset to
userspace. Patch 5 provides a vCPU attribute to provide userspace access
to the TSC offset.

Patches 6-7 implement a test for the new additions to
KVM_{GET,SET}_CLOCK.

Patch 8 fixes some assertions in the kvm device attribute helpers.

Patches 9-10 implement at test for the tsc offset attribute introduced in
patch 5.

Paolo,

Is there anything else you're waiting to see for the x86 portion of
this series after addressing Sean's comments? There's some work
remaining on the arm64 side, though I believe the two architectures
are now disjoint for this series.

I think at this stage it would make sense to split the series in two
and drive them independently.

Thanks,

	M.

-- 
Without deviation from the norm, progress is not possible.