[PATCH v3] x86/time: Don't use virtual TSC if host and guest frequencies are equal

[PATCH v3] x86/time: Don't use virtual TSC if host and guest frequencies are equal

[Boris Ostrovsky]

Commit 82713ec8d2 ("x86: use native RDTSC(P) execution when guest and
host frequencies are the same") left out optimization for PV guests
when host and guest run at the same frequency.

For such a case we should be able not to use virtual TSC regardless
of whether we are runing before or after a migration (i.e. regardless
of incarnation value).

Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Suggested-by: Jan Beulich <JBeulich@suse.com>
---
Changes in v3:
* Replace ASSERT with a comment

 xen/arch/x86/time.c | 15 +++++++--------
 1 file changed, 7 insertions(+), 8 deletions(-)

diff --git a/xen/arch/x86/time.c b/xen/arch/x86/time.c
index b4988bf..69278c3 100644
--- a/xen/arch/x86/time.c
+++ b/xen/arch/x86/time.c
@@ -2024,17 +2024,16 @@ void tsc_set_info(struct domain *d,
         d->arch.vtsc_offset = get_s_time() - elapsed_nsec;
         d->arch.tsc_khz = gtsc_khz ?: cpu_khz;
         set_time_scale(&d->arch.vtsc_to_ns, d->arch.tsc_khz * 1000);
+
         /*
-         * In default mode use native TSC if the host has safe TSC and:
-         *  HVM/PVH: host and guest frequencies are the same (either
-         *           "naturally" or via TSC scaling)
-         *  PV: guest has not migrated yet (and thus arch.tsc_khz == cpu_khz)
+         * When a guest is created gtsc_khz is passed in as zero,
+         * making d->arch.tsc_khz == cpu_khz. Thus no need to test
+         * 'incarnation == 0'.
          */
         if ( tsc_mode == TSC_MODE_DEFAULT && host_tsc_is_safe() &&
-             (is_hvm_domain(d) ?
-              (d->arch.tsc_khz == cpu_khz ||
-               hvm_get_tsc_scaling_ratio(d->arch.tsc_khz)) :
-              incarnation == 0) )
+             (d->arch.tsc_khz == cpu_khz ||
+              (is_hvm_domain(d) &&
+               hvm_get_tsc_scaling_ratio(d->arch.tsc_khz))) )
         {
     case TSC_MODE_NEVER_EMULATE:
             d->arch.vtsc = 0;
-- 
1.8.3.1


_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel

Re: [PATCH v3] x86/time: Don't use virtual TSC if host and guest frequencies are equal

[Jan Beulich]

>>> On 17.03.17 at 19:15, <boris.ostrovsky@oracle.com> wrote:
> Commit 82713ec8d2 ("x86: use native RDTSC(P) execution when guest and
> host frequencies are the same") left out optimization for PV guests
> when host and guest run at the same frequency.
> 
> For such a case we should be able not to use virtual TSC regardless
> of whether we are runing before or after a migration (i.e. regardless
> of incarnation value).
> 
> Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
> Suggested-by: Jan Beulich <JBeulich@suse.com>

Reviewed-by: Jan Beulich <jbeulich@suse.com>



_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel

Re: [PATCH v3] x86/time: Don't use virtual TSC if host and guest frequencies are equal

[Olaf Hering]

[-- Attachment #1.1: Type: text/plain, Size: 1308 bytes --]

Am Fri, 17 Mar 2017 14:15:26 -0400
schrieb Boris Ostrovsky <boris.ostrovsky@oracle.com>:

> Commit 82713ec8d2 ("x86: use native RDTSC(P) execution when guest and
> host frequencies are the same") left out optimization for PV guests
> when host and guest run at the same frequency.
> 
> For such a case we should be able not to use virtual TSC regardless
> of whether we are runing before or after a migration (i.e. regardless
> of incarnation value).


I think this part of tscmode.txt may needs an update now.
Doesn't the "always emulated for PV" meant the part which was changed?


...
The default mode (tsc_mode==0) checks TSC-safeness of the underlying
hardware on which the virtual machine is launched.  If it is
TSC-safe, rdtsc will execute at hardware speed; if it is not, rdtsc
will be emulated.  Once a virtual machine is save/restored or migrated,
however, there are two possibilities:  For a paravirtualized (PV) domain,
TSC will always be emulated.  For a fully-virtualized (HVM) domain,
TSC remains native IF the source physical machine and target physical machine
have the same TSC frequency; else TSC is emulated.  Note that, though
emulated, the "apparent" TSC frequency will be the TSC frequency
of the initial physical machine, even after migration.
...

Olaf

[-- Attachment #1.2: Digitale Signatur von OpenPGP --]
[-- Type: application/pgp-signature, Size: 195 bytes --]

[-- Attachment #2: Type: text/plain, Size: 127 bytes --]

_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel