From: Jeremy Fitzhardinge <jeremy@goop.org>
To: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Cc: linux-kernel@vger.kernel.org, xen-devel@lists.xensource.com,
Don Dutile <ddutile@redhat.com>
Subject: Re: [PATCH 10/11] Support VIRQ_TIMER and pvclock on HVM
Date: Tue, 25 May 2010 13:24:21 -0700 [thread overview]
Message-ID: <4BFC31F5.9040806@goop.org> (raw)
In-Reply-To: <1274725657-1149-10-git-send-email-stefano.stabellini@eu.citrix.com>
On 05/24/2010 11:27 AM, Stefano Stabellini wrote:
> Use the paravirtualized timer (VIRQ_TIMER) as timer and the
> paravirtualized clock (pvclock) as wallclock on HVM domains too.
>
That's not quite correct. There's the Xen clockevent driver, the Xen
clocksource, and a distinct-but-related Xen notion of wallclock time.
In general, clocksources and wallclock don't have much direct
relationship to each other.
> Any interaction with emulated hardware is not very fast, so using the
> paravirtualized timer instead of the emulated hpet is defenitely a
>
"definitely"
> performance improvement.
>
Are there accuracy/stability/precision improvements too?
J
> Signed-off-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
> ---
> arch/x86/xen/enlighten.c | 31 +++++++++++++++++++++++++++++++
> arch/x86/xen/suspend.c | 4 ++++
> include/xen/interface/features.h | 3 +++
> 3 files changed, 38 insertions(+), 0 deletions(-)
>
> diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
> index cb316b5..88e8a09 100644
> --- a/arch/x86/xen/enlighten.c
> +++ b/arch/x86/xen/enlighten.c
> @@ -1307,6 +1307,36 @@ static struct notifier_block __cpuinitdata xen_hvm_cpu_notifier = {
> .notifier_call = xen_hvm_cpu_notify,
> };
>
> +static void xen_hvm_setup_cpu_clockevents(void)
> +{
> + int cpu = smp_processor_id();
> + xen_setup_runstate_info(cpu);
> + xen_setup_timer(cpu);
> + xen_setup_cpu_clockevents();
> +}
> +
> +static void init_hvm_time(void)
> +{
> + /* vector callback is needed otherwise we cannot receive interrupts
> + * on cpu > 0 */
> + if (!xen_have_vector_callback && num_present_cpus() > 1)
> + return;
> + if (!xen_feature(XENFEAT_hvm_safe_pvclock)) {
> + printk(KERN_INFO "Xen doesn't support pvclock on HVM,"
> + "disable pv timer\n");
> + return;
> + }
> +
> + pv_time_ops = xen_time_ops;
> + x86_init.timers.timer_init = xen_time_init;
> + x86_init.timers.setup_percpu_clockev = x86_init_noop;
> + x86_cpuinit.setup_percpu_clockev = xen_hvm_setup_cpu_clockevents;
> +
> + x86_platform.calibrate_tsc = xen_tsc_khz;
> + x86_platform.get_wallclock = xen_get_wallclock;
> + x86_platform.set_wallclock = xen_set_wallclock;
> +}
> +
> void __init xen_guest_init(void)
> {
> int r;
> @@ -1326,4 +1356,5 @@ void __init xen_guest_init(void)
> register_cpu_notifier(&xen_hvm_cpu_notifier);
> have_vcpu_info_placement = 0;
> x86_init.irqs.intr_init = xen_init_IRQ;
> + init_hvm_time();
> }
> diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c
> index ef517ee..02c3253 100644
> --- a/arch/x86/xen/suspend.c
> +++ b/arch/x86/xen/suspend.c
> @@ -28,8 +28,12 @@ void xen_pre_suspend(void)
>
> void xen_hvm_post_suspend(int suspend_cancelled)
> {
> + int cpu;
> init_shared_info();
> xen_callback_vector();
> + for_each_online_cpu(cpu) {
> + xen_setup_runstate_info(cpu);
> + }
> }
>
> void xen_post_suspend(int suspend_cancelled)
> diff --git a/include/xen/interface/features.h b/include/xen/interface/features.h
> index 8ab08b9..70d2563 100644
> --- a/include/xen/interface/features.h
> +++ b/include/xen/interface/features.h
> @@ -44,6 +44,9 @@
> /* x86: Does this Xen host support the HVM callback vector type? */
> #define XENFEAT_hvm_callback_vector 8
>
> +/* x86: pvclock algorithm is safe to use on HVM */
> +#define XENFEAT_hvm_safe_pvclock 9
> +
> #define XENFEAT_NR_SUBMAPS 1
>
> #endif /* __XEN_PUBLIC_FEATURES_H__ */
>
WARNING: multiple messages have this Message-ID (diff)
From: Jeremy Fitzhardinge <jeremy@goop.org>
To: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Cc: xen-devel@lists.xensource.com, Don Dutile <ddutile@redhat.com>,
linux-kernel@vger.kernel.org
Subject: Re: [PATCH 10/11] Support VIRQ_TIMER and pvclock on HVM
Date: Tue, 25 May 2010 13:24:21 -0700 [thread overview]
Message-ID: <4BFC31F5.9040806@goop.org> (raw)
In-Reply-To: <1274725657-1149-10-git-send-email-stefano.stabellini@eu.citrix.com>
On 05/24/2010 11:27 AM, Stefano Stabellini wrote:
> Use the paravirtualized timer (VIRQ_TIMER) as timer and the
> paravirtualized clock (pvclock) as wallclock on HVM domains too.
>
That's not quite correct. There's the Xen clockevent driver, the Xen
clocksource, and a distinct-but-related Xen notion of wallclock time.
In general, clocksources and wallclock don't have much direct
relationship to each other.
> Any interaction with emulated hardware is not very fast, so using the
> paravirtualized timer instead of the emulated hpet is defenitely a
>
"definitely"
> performance improvement.
>
Are there accuracy/stability/precision improvements too?
J
> Signed-off-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
> ---
> arch/x86/xen/enlighten.c | 31 +++++++++++++++++++++++++++++++
> arch/x86/xen/suspend.c | 4 ++++
> include/xen/interface/features.h | 3 +++
> 3 files changed, 38 insertions(+), 0 deletions(-)
>
> diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
> index cb316b5..88e8a09 100644
> --- a/arch/x86/xen/enlighten.c
> +++ b/arch/x86/xen/enlighten.c
> @@ -1307,6 +1307,36 @@ static struct notifier_block __cpuinitdata xen_hvm_cpu_notifier = {
> .notifier_call = xen_hvm_cpu_notify,
> };
>
> +static void xen_hvm_setup_cpu_clockevents(void)
> +{
> + int cpu = smp_processor_id();
> + xen_setup_runstate_info(cpu);
> + xen_setup_timer(cpu);
> + xen_setup_cpu_clockevents();
> +}
> +
> +static void init_hvm_time(void)
> +{
> + /* vector callback is needed otherwise we cannot receive interrupts
> + * on cpu > 0 */
> + if (!xen_have_vector_callback && num_present_cpus() > 1)
> + return;
> + if (!xen_feature(XENFEAT_hvm_safe_pvclock)) {
> + printk(KERN_INFO "Xen doesn't support pvclock on HVM,"
> + "disable pv timer\n");
> + return;
> + }
> +
> + pv_time_ops = xen_time_ops;
> + x86_init.timers.timer_init = xen_time_init;
> + x86_init.timers.setup_percpu_clockev = x86_init_noop;
> + x86_cpuinit.setup_percpu_clockev = xen_hvm_setup_cpu_clockevents;
> +
> + x86_platform.calibrate_tsc = xen_tsc_khz;
> + x86_platform.get_wallclock = xen_get_wallclock;
> + x86_platform.set_wallclock = xen_set_wallclock;
> +}
> +
> void __init xen_guest_init(void)
> {
> int r;
> @@ -1326,4 +1356,5 @@ void __init xen_guest_init(void)
> register_cpu_notifier(&xen_hvm_cpu_notifier);
> have_vcpu_info_placement = 0;
> x86_init.irqs.intr_init = xen_init_IRQ;
> + init_hvm_time();
> }
> diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c
> index ef517ee..02c3253 100644
> --- a/arch/x86/xen/suspend.c
> +++ b/arch/x86/xen/suspend.c
> @@ -28,8 +28,12 @@ void xen_pre_suspend(void)
>
> void xen_hvm_post_suspend(int suspend_cancelled)
> {
> + int cpu;
> init_shared_info();
> xen_callback_vector();
> + for_each_online_cpu(cpu) {
> + xen_setup_runstate_info(cpu);
> + }
> }
>
> void xen_post_suspend(int suspend_cancelled)
> diff --git a/include/xen/interface/features.h b/include/xen/interface/features.h
> index 8ab08b9..70d2563 100644
> --- a/include/xen/interface/features.h
> +++ b/include/xen/interface/features.h
> @@ -44,6 +44,9 @@
> /* x86: Does this Xen host support the HVM callback vector type? */
> #define XENFEAT_hvm_callback_vector 8
>
> +/* x86: pvclock algorithm is safe to use on HVM */
> +#define XENFEAT_hvm_safe_pvclock 9
> +
> #define XENFEAT_NR_SUBMAPS 1
>
> #endif /* __XEN_PUBLIC_FEATURES_H__ */
>
next prev parent reply other threads:[~2010-05-25 20:24 UTC|newest]
Thread overview: 47+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-05-24 18:25 [PATCH 0 of 12] PV on HVM Xen Stefano Stabellini
2010-05-24 18:25 ` Stefano Stabellini
2010-05-24 18:27 ` [PATCH 01/11] Add support for hvm_op Stefano Stabellini
2010-05-24 18:27 ` [PATCH 02/11] early PV on HVM Stefano Stabellini
2010-05-24 18:27 ` [PATCH 03/11] evtchn delivery " Stefano Stabellini
2010-05-24 18:27 ` [PATCH 04/11] Fix find_unbound_irq in presence of ioapic irqs Stefano Stabellini
2010-05-26 18:26 ` [Xen-devel] " Konrad Rzeszutek Wilk
2010-05-27 14:49 ` Stefano Stabellini
2010-05-27 15:36 ` Konrad Rzeszutek Wilk
2010-05-27 15:36 ` Konrad Rzeszutek Wilk
2010-05-24 18:27 ` [PATCH 05/11] Xen PCI platform device driver Stefano Stabellini
2010-05-28 8:55 ` [Xen-devel] " Zhigang Wang
2010-05-28 14:18 ` Stefano Stabellini
2010-05-28 14:18 ` Stefano Stabellini
2010-05-24 18:27 ` [PATCH 06/11] Add suspend\resume support for PV on HVM guests Stefano Stabellini
2010-05-25 20:20 ` Jeremy Fitzhardinge
2010-05-25 20:20 ` Jeremy Fitzhardinge
2010-05-24 18:27 ` [PATCH 07/11] Allow xen platform pci device to be compiled as a module Stefano Stabellini
2010-05-24 18:27 ` [PATCH 08/11] Fix possible NULL pointer dereference in print_IO_APIC Stefano Stabellini
2010-05-24 18:27 ` [PATCH 09/11] __setup_vector_irq: handle NULL chip_data Stefano Stabellini
2010-05-24 18:27 ` [PATCH 10/11] Support VIRQ_TIMER and pvclock on HVM Stefano Stabellini
2010-05-25 20:24 ` Jeremy Fitzhardinge [this message]
2010-05-25 20:24 ` Jeremy Fitzhardinge
2010-05-26 13:08 ` Stefano Stabellini
2010-05-24 18:27 ` [PATCH 11/11] Unplug emulated disks and nics Stefano Stabellini
2010-05-25 20:31 ` Jeremy Fitzhardinge
2010-05-26 12:27 ` Stefano Stabellini
2010-05-26 20:59 ` Jeremy Fitzhardinge
2010-05-27 12:29 ` Stefano Stabellini
2010-05-27 12:29 ` Stefano Stabellini
[not found] ` <m2n.s.1OHcBK-0018DA@chiark.greenend.org.uk>
2010-05-27 14:49 ` [Xen-devel] " Ian Jackson
2010-05-27 14:49 ` Ian Jackson
2010-05-27 17:25 ` [Xen-devel] " Stefano Stabellini
2010-05-27 17:51 ` Jeremy Fitzhardinge
2010-05-27 17:51 ` Jeremy Fitzhardinge
2010-05-27 18:10 ` [Xen-devel] " Stefano Stabellini
2010-05-27 18:10 ` Stefano Stabellini
2010-05-24 18:29 ` [PATCH 0 of 12] PV on HVM Xen Stefano Stabellini
2010-05-24 18:30 ` Boris Derzhavets
2010-05-24 19:06 ` [Xen-devel] " Stefano Stabellini
2010-05-25 6:14 ` Boris Derzhavets
2010-05-25 9:55 ` [Xen-devel] " Stefano Stabellini
2010-05-25 11:15 ` Boris Derzhavets
2010-05-24 18:36 ` Boris Derzhavets
2010-05-28 10:25 ` Boris Derzhavets
2010-05-28 10:45 ` Pasi Kärkkäinen
2010-05-28 11:06 ` Stefano Stabellini
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=4BFC31F5.9040806@goop.org \
--to=jeremy@goop.org \
--cc=ddutile@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=stefano.stabellini@eu.citrix.com \
--cc=xen-devel@lists.xensource.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.