* Re: [PATCH v4 for-4.9] x86/vpmu: add cpu hot unplug notifier for vpmu
@ 2017-05-26 5:20 Kang, Luwei
2017-05-26 6:04 ` Jan Beulich
2017-05-31 6:54 ` Jan Beulich
0 siblings, 2 replies; 6+ messages in thread
From: Kang, Luwei @ 2017-05-26 5:20 UTC (permalink / raw)
To: xen-devel, julien.grall
Cc: andrew.cooper3, boris.ostrovsky, Hao, Xudong, jbeulich
Hi Julien,
Follow your advice, I change the tag to [PATCH v4 for-4.9] because of we hope this patch can be merged in Xen 4.9.
Hi Jan,
If there have anything need to change in this patch?
Thanks,
Luwei Kang
> -----Original Message-----
> From: Kang, Luwei
> Sent: Tuesday, May 23, 2017 4:46 AM
> To: xen-devel@lists.xen.org
> Cc: jbeulich@suse.com; andrew.cooper3@citrix.com; boris.ostrovsky@oracle.com; Kang, Luwei <luwei.kang@intel.com>
> Subject: [PATCH v4] x86/vpmu: add cpu hot unplug notifier for vpmu
>
> Currently, Hot unplug a physical CPU with vpmu enabled may cause system hang due to send a remote call to an offlined pCPU. This
> patch add a cpu hot unplug notifer to save vpmu context before cpu offline.
>
> Consider one scenario, hot unplug pCPU N with vpmu enabled.
> The vcpu which running on this pCPU will be switch to other online cpu. A remote call will be send to pCPU N to save the vpmu
> context before loading the vpmu context on this pCPU.
> System will hang in function on_select_cpus() because of that pCPU is offlined and can not do any respond.
>
> The purpose of add a VPMU_CONTEXT_LOADED check in vpmu_arch_destroy() before send a remote call to save vpmu contex is:
> a. when a vpmu context has been loaded in a remote pCPU, make a
> remote call to save the vpmu contex and stop counters is necessary.
> b. VPMU_CONTEXT_LOADED flag will be reset if a pCPU is offlined.
> this check will prevent send a remote call to an offlined pCPU.
>
> Signed-off-by: Luwei Kang <luwei.kang@intel.com>
> ---
> v4:
> 1.remove cpu_online() check in vpm_load(); 2.remove "vpmu_" prefix; 3.fix a coding style; 4.add some commit message about
> VPMU_CONTEXT_LOADED in vpmu_arch_destroy();
> v3:
> 1.add cpu_online() check in vpm_load() and vpmu_arch_destroy(); 2.add vpmu_ prefix. rename cpu_callback() to
> vpmu_cpu_callback();
> v2:
> 1.fix some typo and coding style;
> 2.change "swith" to "if" in cpu_callback() because of there just have one case; 3.add VPMU_CONTEX_LOADED check before send
> remote call in vpmu_arch_destroy();
> ---
> xen/arch/x86/cpu/vpmu.c | 45 +++++++++++++++++++++++++++++++++++++++++----
> 1 file changed, 41 insertions(+), 4 deletions(-)
>
> diff --git a/xen/arch/x86/cpu/vpmu.c b/xen/arch/x86/cpu/vpmu.c index 03401fd..1f7830b 100644
> --- a/xen/arch/x86/cpu/vpmu.c
> +++ b/xen/arch/x86/cpu/vpmu.c
> @@ -21,6 +21,7 @@
> #include <xen/xenoprof.h>
> #include <xen/event.h>
> #include <xen/guest_access.h>
> +#include <xen/cpu.h>
> #include <asm/regs.h>
> #include <asm/types.h>
> #include <asm/msr.h>
> @@ -575,15 +576,21 @@ static void vpmu_arch_destroy(struct vcpu *v)
> * We will test it again in vpmu_clear_last() with interrupts
> * disabled to make sure we don't clear someone else.
> */
> - if ( per_cpu(last_vcpu, vpmu->last_pcpu) == v )
> + if ( cpu_online(vpmu->last_pcpu) &&
> + per_cpu(last_vcpu, vpmu->last_pcpu) == v )
> on_selected_cpus(cpumask_of(vpmu->last_pcpu),
> vpmu_clear_last, v, 1);
>
> if ( vpmu->arch_vpmu_ops && vpmu->arch_vpmu_ops->arch_vpmu_destroy )
> {
> - /* Unload VPMU first. This will stop counters */
> - on_selected_cpus(cpumask_of(vcpu_vpmu(v)->last_pcpu),
> - vpmu_save_force, v, 1);
> + /*
> + * Unload VPMU first if VPMU_CONTEXT_LOADED being set.
> + * This will stop counters.
> + */
> + if ( vpmu_is_set(vpmu, VPMU_CONTEXT_LOADED) )
> + on_selected_cpus(cpumask_of(vcpu_vpmu(v)->last_pcpu),
> + vpmu_save_force, v, 1);
> +
> vpmu->arch_vpmu_ops->arch_vpmu_destroy(v);
> }
> }
> @@ -835,6 +842,33 @@ long do_xenpmu_op(unsigned int op, XEN_GUEST_HANDLE_PARAM(xen_pmu_params_t) arg)
> return ret;
> }
>
> +static int cpu_callback(
> + struct notifier_block *nfb, unsigned long action, void *hcpu) {
> + unsigned int cpu = (unsigned long)hcpu;
> + struct vcpu *vcpu = per_cpu(last_vcpu, cpu);
> + struct vpmu_struct *vpmu;
> +
> + if ( !vcpu )
> + return NOTIFY_DONE;
> +
> + vpmu = vcpu_vpmu(vcpu);
> + if ( !vpmu_is_set(vpmu, VPMU_CONTEXT_ALLOCATED) )
> + return NOTIFY_DONE;
> +
> + if ( action == CPU_DYING )
> + {
> + vpmu_save_force(vcpu);
> + vpmu_reset(vpmu, VPMU_CONTEXT_LOADED);
> + }
> +
> + return NOTIFY_DONE;
> +}
> +
> +static struct notifier_block cpu_nfb = {
> + .notifier_call = cpu_callback
> +};
> +
> static int __init vpmu_init(void)
> {
> int vendor = current_cpu_data.x86_vendor; @@ -872,8 +906,11 @@ static int __init vpmu_init(void)
> }
>
> if ( vpmu_mode != XENPMU_MODE_OFF )
> + {
> + register_cpu_notifier(&cpu_nfb);
> printk(XENLOG_INFO "VPMU: version " __stringify(XENPMU_VER_MAJ) "."
> __stringify(XENPMU_VER_MIN) "\n");
> + }
> else
> opt_vpmu_enabled = 0;
>
> --
> 1.8.3.1
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel
^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: [PATCH v4 for-4.9] x86/vpmu: add cpu hot unplug notifier for vpmu
2017-05-26 5:20 [PATCH v4 for-4.9] x86/vpmu: add cpu hot unplug notifier for vpmu Kang, Luwei
@ 2017-05-26 6:04 ` Jan Beulich
2017-05-31 6:54 ` Jan Beulich
1 sibling, 0 replies; 6+ messages in thread
From: Jan Beulich @ 2017-05-26 6:04 UTC (permalink / raw)
To: julien.grall, Luwei Kang
Cc: andrew.cooper3, boris.ostrovsky, Xudong Hao, xen-devel
>>> On 26.05.17 at 07:20, <luwei.kang@intel.com> wrote:
> Hi Jan,
> If there have anything need to change in this patch?
I didn't get to look at v4 yet - too busy with other stuff.
Jan
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel
^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: [PATCH v4 for-4.9] x86/vpmu: add cpu hot unplug notifier for vpmu
2017-05-26 5:20 [PATCH v4 for-4.9] x86/vpmu: add cpu hot unplug notifier for vpmu Kang, Luwei
2017-05-26 6:04 ` Jan Beulich
@ 2017-05-31 6:54 ` Jan Beulich
2017-05-31 9:23 ` Julien Grall
1 sibling, 1 reply; 6+ messages in thread
From: Jan Beulich @ 2017-05-31 6:54 UTC (permalink / raw)
To: julien.grall
Cc: andrew.cooper3, boris.ostrovsky, Luwei Kang, Xudong Hao, xen-devel
>>> On 26.05.17 at 07:20, <luwei.kang@intel.com> wrote:
> Hi Julien,
> Follow your advice, I change the tag to [PATCH v4 for-4.9] because of we
> hope this patch can be merged in Xen 4.9.
Ping?
Jan
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel
^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: [PATCH v4 for-4.9] x86/vpmu: add cpu hot unplug notifier for vpmu
2017-05-31 6:54 ` Jan Beulich
@ 2017-05-31 9:23 ` Julien Grall
2017-05-31 9:46 ` Jan Beulich
0 siblings, 1 reply; 6+ messages in thread
From: Julien Grall @ 2017-05-31 9:23 UTC (permalink / raw)
To: Jan Beulich
Cc: andrew.cooper3, boris.ostrovsky, Luwei Kang, Xudong Hao, xen-devel
Hi,
On 05/31/2017 07:54 AM, Jan Beulich wrote:
>>>> On 26.05.17 at 07:20, <luwei.kang@intel.com> wrote:
>> Hi Julien,
>> Follow your advice, I change the tag to [PATCH v4 for-4.9] because of we
>> hope this patch can be merged in Xen 4.9.
>
> Ping?
Sorry for the late reply. I was waiting for staging to re-open before
going through the potential list of patches to go in Xen 4.9.
Am I right that vPMU is disabled by default? I.e a user would have to
pass "vpmu" on the command line to use it? ([1] seems to confirm that)
Cheers,
[1] https://patchwork.kernel.org/patch/9254313/
--
Julien Grall
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel
^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: [PATCH v4 for-4.9] x86/vpmu: add cpu hot unplug notifier for vpmu
2017-05-31 9:23 ` Julien Grall
@ 2017-05-31 9:46 ` Jan Beulich
2017-05-31 10:23 ` Julien Grall
0 siblings, 1 reply; 6+ messages in thread
From: Jan Beulich @ 2017-05-31 9:46 UTC (permalink / raw)
To: Julien Grall
Cc: andrew.cooper3, boris.ostrovsky, Luwei Kang, Xudong Hao, xen-devel
>>> On 31.05.17 at 11:23, <julien.grall@arm.com> wrote:
> On 05/31/2017 07:54 AM, Jan Beulich wrote:
>>>>> On 26.05.17 at 07:20, <luwei.kang@intel.com> wrote:
>>> Hi Julien,
>>> Follow your advice, I change the tag to [PATCH v4 for-4.9] because of we
>>> hope this patch can be merged in Xen 4.9.
>>
>> Ping?
>
> Sorry for the late reply. I was waiting for staging to re-open before
> going through the potential list of patches to go in Xen 4.9.
>
> Am I right that vPMU is disabled by default? I.e a user would have to
> pass "vpmu" on the command line to use it? ([1] seems to confirm that)
Yes. And enabling it renders the entire configuration unsupported
(XSA-163).
Jan
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel
^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: [PATCH v4 for-4.9] x86/vpmu: add cpu hot unplug notifier for vpmu
2017-05-31 9:46 ` Jan Beulich
@ 2017-05-31 10:23 ` Julien Grall
0 siblings, 0 replies; 6+ messages in thread
From: Julien Grall @ 2017-05-31 10:23 UTC (permalink / raw)
To: Jan Beulich
Cc: andrew.cooper3, boris.ostrovsky, Luwei Kang, Xudong Hao, xen-devel
On 31/05/17 10:46, Jan Beulich wrote:
>>>> On 31.05.17 at 11:23, <julien.grall@arm.com> wrote:
>> On 05/31/2017 07:54 AM, Jan Beulich wrote:
>>>>>> On 26.05.17 at 07:20, <luwei.kang@intel.com> wrote:
>>>> Hi Julien,
>>>> Follow your advice, I change the tag to [PATCH v4 for-4.9] because of we
>>>> hope this patch can be merged in Xen 4.9.
>>>
>>> Ping?
>>
>> Sorry for the late reply. I was waiting for staging to re-open before
>> going through the potential list of patches to go in Xen 4.9.
>>
>> Am I right that vPMU is disabled by default? I.e a user would have to
>> pass "vpmu" on the command line to use it? ([1] seems to confirm that)
>
> Yes. And enabling it renders the entire configuration unsupported
> (XSA-163).
On that basis:
Release-acked-by: Julien Grall <julien.grall@arm.com>
Cheers,
--
Julien Grall
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel
^ permalink raw reply [flat|nested] 6+ messages in thread
end of thread, other threads:[~2017-05-31 10:23 UTC | newest]
Thread overview: 6+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2017-05-26 5:20 [PATCH v4 for-4.9] x86/vpmu: add cpu hot unplug notifier for vpmu Kang, Luwei
2017-05-26 6:04 ` Jan Beulich
2017-05-31 6:54 ` Jan Beulich
2017-05-31 9:23 ` Julien Grall
2017-05-31 9:46 ` Jan Beulich
2017-05-31 10:23 ` Julien Grall
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.