Re: [PATCH 2/2] x86: vdso: use __pvclock_read_cycles

2016-07-06 Thread Andy Lutomirski
On Mon, Jun 27, 2016 at 7:19 AM, Paolo Bonzini wrote: > 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

Re: [PATCH 2/2] x86: vdso: use __pvclock_read_cycles

2016-07-06 Thread Andy Lutomirski
On Mon, Jun 27, 2016 at 7:19 AM, Paolo Bonzini wrote: > 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

[PATCH 2/2] x86: vdso: use __pvclock_read_cycles

2016-06-27 Thread Paolo Bonzini
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. Signed-off-by: Paolo Bonzini

[PATCH 2/2] x86: vdso: use __pvclock_read_cycles

2016-06-27 Thread Paolo Bonzini
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. Signed-off-by: Paolo Bonzini ---