Re: [Xen-devel] [PATCH] x86/time: update TSC stamp on restore from deep C-state

2020-01-16 Thread Roger Pau Monné
On Thu, Jan 16, 2020 at 12:09:12PM +, Igor Druzhinin wrote: > On 16/01/2020 09:38, Jan Beulich wrote: > > On 16.01.2020 10:33, Roger Pau Monné wrote: > >> On Wed, Jan 15, 2020 at 05:21:16PM +0100, Jan Beulich wrote: > >>> On 15.01.2020 14:44, Roger Pau Monné wrote: > On Wed, Jan 15, 2020 a

Re: [Xen-devel] [PATCH] x86/time: update TSC stamp on restore from deep C-state

2020-01-16 Thread Igor Druzhinin
On 16/01/2020 09:38, Jan Beulich wrote: > On 16.01.2020 10:33, Roger Pau Monné wrote: >> On Wed, Jan 15, 2020 at 05:21:16PM +0100, Jan Beulich wrote: >>> On 15.01.2020 14:44, Roger Pau Monné wrote: On Wed, Jan 15, 2020 at 01:49:22PM +0100, Jan Beulich wrote: > What I'm then worried about i

Re: [Xen-devel] [PATCH] x86/time: update TSC stamp on restore from deep C-state

2020-01-16 Thread Jan Beulich
On 16.01.2020 10:33, Roger Pau Monné wrote: > On Wed, Jan 15, 2020 at 05:21:16PM +0100, Jan Beulich wrote: >> On 15.01.2020 14:44, Roger Pau Monné wrote: >>> On Wed, Jan 15, 2020 at 01:49:22PM +0100, Jan Beulich wrote: What I'm then worried about is too little progress observable by guest

Re: [Xen-devel] [PATCH] x86/time: update TSC stamp on restore from deep C-state

2020-01-16 Thread Roger Pau Monné
On Wed, Jan 15, 2020 at 05:21:16PM +0100, Jan Beulich wrote: > On 15.01.2020 14:44, Roger Pau Monné wrote: > > On Wed, Jan 15, 2020 at 01:49:22PM +0100, Jan Beulich wrote: > >> What I'm then worried about is too > >> little progress observable by guests. The PV time protocol > >> ought to be fine i

Re: [Xen-devel] [PATCH] x86/time: update TSC stamp on restore from deep C-state

2020-01-15 Thread Jan Beulich
On 15.01.2020 14:44, Roger Pau Monné wrote: > On Wed, Jan 15, 2020 at 01:49:22PM +0100, Jan Beulich wrote: >> What I'm then worried about is too >> little progress observable by guests. The PV time protocol >> ought to be fine in this regard (and consumers of raw TSC values >> are on their own anyw

Re: [Xen-devel] [PATCH] x86/time: update TSC stamp on restore from deep C-state

2020-01-15 Thread Andrew Cooper
On 15/01/2020 12:54, Jan Beulich wrote: > On 15.01.2020 13:47, Igor Druzhinin wrote: >> On 15/01/2020 12:39, Jan Beulich wrote: >>> On 15.01.2020 13:28, Igor Druzhinin wrote: On 15/01/2020 11:32, Jan Beulich wrote: > On 14.01.2020 20:36, Igor Druzhinin wrote: >> If ITSC is not availabl

Re: [Xen-devel] [PATCH] x86/time: update TSC stamp on restore from deep C-state

2020-01-15 Thread Igor Druzhinin
On 15/01/2020 13:23, Roger Pau Monné wrote: > On Wed, Jan 15, 2020 at 12:36:08PM +, Igor Druzhinin wrote: >> On 15/01/2020 09:47, Roger Pau Monné wrote: >>> On Tue, Jan 14, 2020 at 07:36:21PM +, Igor Druzhinin wrote: If ITSC is not available on CPU (e.g if running nested as PV shim) >>

Re: [Xen-devel] [PATCH] x86/time: update TSC stamp on restore from deep C-state

2020-01-15 Thread Roger Pau Monné
On Wed, Jan 15, 2020 at 01:49:22PM +0100, Jan Beulich wrote: > On 15.01.2020 12:53, Roger Pau Monné wrote: > > On Wed, Jan 15, 2020 at 12:40:27PM +0100, Jan Beulich wrote: > >> On 15.01.2020 10:47, Roger Pau Monné wrote: > >>> On Tue, Jan 14, 2020 at 07:36:21PM +, Igor Druzhinin wrote: > -

Re: [Xen-devel] [PATCH] x86/time: update TSC stamp on restore from deep C-state

2020-01-15 Thread Roger Pau Monné
On Wed, Jan 15, 2020 at 12:36:08PM +, Igor Druzhinin wrote: > On 15/01/2020 09:47, Roger Pau Monné wrote: > > On Tue, Jan 14, 2020 at 07:36:21PM +, Igor Druzhinin wrote: > >> If ITSC is not available on CPU (e.g if running nested as PV shim) > >> then X86_FEATURE_NONSTOP_TSC is not advertis

Re: [Xen-devel] [PATCH] x86/time: update TSC stamp on restore from deep C-state

2020-01-15 Thread Jan Beulich
On 15.01.2020 13:47, Igor Druzhinin wrote: > On 15/01/2020 12:39, Jan Beulich wrote: >> On 15.01.2020 13:28, Igor Druzhinin wrote: >>> On 15/01/2020 11:32, Jan Beulich wrote: On 14.01.2020 20:36, Igor Druzhinin wrote: > If ITSC is not available on CPU (e.g if running nested as PV shim) >>>

Re: [Xen-devel] [PATCH] x86/time: update TSC stamp on restore from deep C-state

2020-01-15 Thread Jan Beulich
On 15.01.2020 12:53, Roger Pau Monné wrote: > On Wed, Jan 15, 2020 at 12:40:27PM +0100, Jan Beulich wrote: >> On 15.01.2020 10:47, Roger Pau Monné wrote: >>> On Tue, Jan 14, 2020 at 07:36:21PM +, Igor Druzhinin wrote: --- a/xen/arch/x86/time.c +++ b/xen/arch/x86/time.c @@ -955,10

Re: [Xen-devel] [PATCH] x86/time: update TSC stamp on restore from deep C-state

2020-01-15 Thread Igor Druzhinin
On 15/01/2020 12:39, Jan Beulich wrote: > On 15.01.2020 13:28, Igor Druzhinin wrote: >> On 15/01/2020 11:32, Jan Beulich wrote: >>> On 14.01.2020 20:36, Igor Druzhinin wrote: If ITSC is not available on CPU (e.g if running nested as PV shim) then X86_FEATURE_NONSTOP_TSC is not advertised

Re: [Xen-devel] [PATCH] x86/time: update TSC stamp on restore from deep C-state

2020-01-15 Thread Jan Beulich
On 15.01.2020 13:31, Igor Druzhinin wrote: > On 15/01/2020 12:25, Igor Druzhinin wrote: >> On 15/01/2020 11:40, Jan Beulich wrote: >>> On 15.01.2020 10:47, Roger Pau Monné wrote: On Tue, Jan 14, 2020 at 07:36:21PM +, Igor Druzhinin wrote: > --- a/xen/arch/x86/time.c > +++ b/xen/arc

Re: [Xen-devel] [PATCH] x86/time: update TSC stamp on restore from deep C-state

2020-01-15 Thread Jan Beulich
On 15.01.2020 13:28, Igor Druzhinin wrote: > On 15/01/2020 11:32, Jan Beulich wrote: >> On 14.01.2020 20:36, Igor Druzhinin wrote: >>> If ITSC is not available on CPU (e.g if running nested as PV shim) >>> then X86_FEATURE_NONSTOP_TSC is not advertised in certain cases, i.e. >>> all AMD and some ol

Re: [Xen-devel] [PATCH] x86/time: update TSC stamp on restore from deep C-state

2020-01-15 Thread Igor Druzhinin
On 15/01/2020 09:47, Roger Pau Monné wrote: > On Tue, Jan 14, 2020 at 07:36:21PM +, Igor Druzhinin wrote: >> If ITSC is not available on CPU (e.g if running nested as PV shim) >> then X86_FEATURE_NONSTOP_TSC is not advertised in certain cases, i.e. >> all AMD and some old Intel processors. In w

Re: [Xen-devel] [PATCH] x86/time: update TSC stamp on restore from deep C-state

2020-01-15 Thread Igor Druzhinin
On 15/01/2020 12:25, Igor Druzhinin wrote: > On 15/01/2020 11:40, Jan Beulich wrote: >> On 15.01.2020 10:47, Roger Pau Monné wrote: >>> On Tue, Jan 14, 2020 at 07:36:21PM +, Igor Druzhinin wrote: --- a/xen/arch/x86/time.c +++ b/xen/arch/x86/time.c @@ -955,10 +955,16 @@ u64 stime2

Re: [Xen-devel] [PATCH] x86/time: update TSC stamp on restore from deep C-state

2020-01-15 Thread Igor Druzhinin
On 15/01/2020 11:32, Jan Beulich wrote: > On 14.01.2020 20:36, Igor Druzhinin wrote: >> If ITSC is not available on CPU (e.g if running nested as PV shim) >> then X86_FEATURE_NONSTOP_TSC is not advertised in certain cases, i.e. >> all AMD and some old Intel processors. In which case TSC would need

Re: [Xen-devel] [PATCH] x86/time: update TSC stamp on restore from deep C-state

2020-01-15 Thread Igor Druzhinin
On 15/01/2020 11:40, Jan Beulich wrote: > On 15.01.2020 10:47, Roger Pau Monné wrote: >> On Tue, Jan 14, 2020 at 07:36:21PM +, Igor Druzhinin wrote: >>> --- a/xen/arch/x86/time.c >>> +++ b/xen/arch/x86/time.c >>> @@ -955,10 +955,16 @@ u64 stime2tsc(s_time_t stime) >>> >>> void cstate_restore

Re: [Xen-devel] [PATCH] x86/time: update TSC stamp on restore from deep C-state

2020-01-15 Thread Roger Pau Monné
On Wed, Jan 15, 2020 at 12:40:27PM +0100, Jan Beulich wrote: > On 15.01.2020 10:47, Roger Pau Monné wrote: > > On Tue, Jan 14, 2020 at 07:36:21PM +, Igor Druzhinin wrote: > >> --- a/xen/arch/x86/time.c > >> +++ b/xen/arch/x86/time.c > >> @@ -955,10 +955,16 @@ u64 stime2tsc(s_time_t stime) > >>

Re: [Xen-devel] [PATCH] x86/time: update TSC stamp on restore from deep C-state

2020-01-15 Thread Jan Beulich
On 15.01.2020 10:47, Roger Pau Monné wrote: > On Tue, Jan 14, 2020 at 07:36:21PM +, Igor Druzhinin wrote: >> --- a/xen/arch/x86/time.c >> +++ b/xen/arch/x86/time.c >> @@ -955,10 +955,16 @@ u64 stime2tsc(s_time_t stime) >> >> void cstate_restore_tsc(void) >> { >> +struct cpu_time *t = &t

Re: [Xen-devel] [PATCH] x86/time: update TSC stamp on restore from deep C-state

2020-01-15 Thread Jan Beulich
On 14.01.2020 20:36, Igor Druzhinin wrote: > If ITSC is not available on CPU (e.g if running nested as PV shim) > then X86_FEATURE_NONSTOP_TSC is not advertised in certain cases, i.e. > all AMD and some old Intel processors. In which case TSC would need to > be restored on CPU from platform time by

Re: [Xen-devel] [PATCH] x86/time: update TSC stamp on restore from deep C-state

2020-01-15 Thread Roger Pau Monné
On Tue, Jan 14, 2020 at 07:36:21PM +, Igor Druzhinin wrote: > If ITSC is not available on CPU (e.g if running nested as PV shim) > then X86_FEATURE_NONSTOP_TSC is not advertised in certain cases, i.e. > all AMD and some old Intel processors. In which case TSC would need to > be restored on CPU

[Xen-devel] [PATCH] x86/time: update TSC stamp on restore from deep C-state

2020-01-14 Thread Igor Druzhinin
If ITSC is not available on CPU (e.g if running nested as PV shim) then X86_FEATURE_NONSTOP_TSC is not advertised in certain cases, i.e. all AMD and some old Intel processors. In which case TSC would need to be restored on CPU from platform time by Xen upon exiting deep C-states. As platform time