x86: vdso: use __pvclock_read_cycles
authorPaolo Bonzini <pbonzini@redhat.com>
Thu, 9 Jun 2016 18:12:34 +0000 (20:12 +0200)
committerPaolo Bonzini <pbonzini@redhat.com>
Thu, 4 Aug 2016 11:52:21 +0000 (13:52 +0200)
commitabe9efa79be02cf2ba27f643b214b07877bb050b
treec6dc89fa650f50a2409307d0a92ed00d5d8fbb32
parent3aed64f6d341cdb62bb2d6232589fb13448ce063
x86: vdso: use __pvclock_read_cycles

The new simplified __pvclock_read_cycles does the same computation
as vread_pvclock, except that (because it takes the pvclock_vcpu_time_info
pointer) it has to be moved inside the loop.  Since the loop is expected to
never roll, this makes no difference.

Acked-by: Andy Lutomirski <luto@kernel.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
arch/x86/entry/vdso/vclock_gettime.c