May be "causes". But not sure, as disabling this feature solves the
issue (no hypervisor crash) and we have reports that the same code base
works fine on Haswell (again no hardware support for PML in Haswell, but
code base is same. But inherently it leads to non-execution of PML code
path, so no crash)
Anshul
On 08/02/17 15:37, Jan Beulich wrote:
On 08.02.17 at 15:58, <anshul.mak...@citrix.com> wrote:
Code is trying to destroy multiple vcpus held by the domain:
complete_domain_destroy->hvm_vcpu_destroy() for each vcpu.
In vmx_vcpu_destroy, we have a call for vmx_vcpu_disable_pml which leads
to a race while destroying foreign vcpu's with other domains rebooting
on the same vcpus .
With a single domain reboot, no race is observed.
Commit e18d4274772e52ac81fda1acb246d11ef666e5fe causes this race condition.
Causes or exposes? I ask because the similar reports we have are
all on 4.4.x, i.e. no PML code there at all.
Jan
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel