linux-kernel - Re: [PATCH RFC v3 1/6] x86/paravirt: Add pv_idle

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <9a4f53f3-225f-0e99-d9b2-d89656b8fb31@suse.com>
Date:   Tue, 14 Nov 2017 11:27:52 +0100
From:   Juergen Gross <jgross@...e.com>
To:     Quan Xu <quan.xu0@...il.com>, Quan Xu <quan.xu03@...il.com>,
        kvm@...r.kernel.org, linux-doc@...r.kernel.org,
        linux-fsdevel@...r.kernel.org, linux-kernel@...r.kernel.org,
        virtualization@...ts.linux-foundation.org, x86@...nel.org,
        xen-devel@...ts.xenproject.org
Cc:     Yang Zhang <yang.zhang.wz@...il.com>,
        Alok Kataria <akataria@...are.com>,
        Rusty Russell <rusty@...tcorp.com.au>,
        Thomas Gleixner <tglx@...utronix.de>,
        Ingo Molnar <mingo@...hat.com>,
        "H. Peter Anvin" <hpa@...or.com>
Subject: Re: [PATCH RFC v3 1/6] x86/paravirt: Add pv_idle_ops to paravirt ops

On 14/11/17 10:38, Quan Xu wrote:
> 
> 
> On 2017/11/14 15:30, Juergen Gross wrote:
>> On 14/11/17 08:02, Quan Xu wrote:
>>>
>>> On 2017/11/13 18:53, Juergen Gross wrote:
>>>> On 13/11/17 11:06, Quan Xu wrote:
>>>>> From: Quan Xu <quan.xu0@...il.com>
>>>>>
>>>>> So far, pv_idle_ops.poll is the only ops for pv_idle. .poll is called
>>>>> in idle path which will poll for a while before we enter the real idle
>>>>> state.
>>>>>
>>>>> In virtualization, idle path includes several heavy operations
>>>>> includes timer access(LAPIC timer or TSC deadline timer) which will
>>>>> hurt performance especially for latency intensive workload like
>>>>> message
>>>>> passing task. The cost is mainly from the vmexit which is a hardware
>>>>> context switch between virtual machine and hypervisor. Our solution is
>>>>> to poll for a while and do not enter real idle path if we can get the
>>>>> schedule event during polling.
>>>>>
>>>>> Poll may cause the CPU waste so we adopt a smart polling mechanism to
>>>>> reduce the useless poll.
>>>>>
>>>>> Signed-off-by: Yang Zhang <yang.zhang.wz@...il.com>
>>>>> Signed-off-by: Quan Xu <quan.xu0@...il.com>
>>>>> Cc: Juergen Gross <jgross@...e.com>
>>>>> Cc: Alok Kataria <akataria@...are.com>
>>>>> Cc: Rusty Russell <rusty@...tcorp.com.au>
>>>>> Cc: Thomas Gleixner <tglx@...utronix.de>
>>>>> Cc: Ingo Molnar <mingo@...hat.com>
>>>>> Cc: "H. Peter Anvin" <hpa@...or.com>
>>>>> Cc: x86@...nel.org
>>>>> Cc: virtualization@...ts.linux-foundation.org
>>>>> Cc: linux-kernel@...r.kernel.org
>>>>> Cc: xen-devel@...ts.xenproject.org
>>>> Hmm, is the idle entry path really so critical to performance that a
>>>> new
>>>> pvops function is necessary?
>>> Juergen, Here is the data we get when running benchmark netperf:
>>>   1. w/o patch and disable kvm dynamic poll (halt_poll_ns=0):
>>>      29031.6 bit/s -- 76.1 %CPU
>>>
>>>   2. w/ patch and disable kvm dynamic poll (halt_poll_ns=0):
>>>      35787.7 bit/s -- 129.4 %CPU
>>>
>>>   3. w/ kvm dynamic poll:
>>>      35735.6 bit/s -- 200.0 %CPU
>>>
>>>   4. w/patch and w/ kvm dynamic poll:
>>>      42225.3 bit/s -- 198.7 %CPU
>>>
>>>   5. idle=poll
>>>      37081.7 bit/s -- 998.1 %CPU
>>>
>>>
>>>
>>>   w/ this patch, we will improve performance by 23%.. even we could
>>> improve
>>>   performance by 45.4%, if we use w/patch and w/ kvm dynamic poll.
>>> also the
>>>   cost of CPU is much lower than 'idle=poll' case..
>> I don't question the general idea. I just think pvops isn't the best way
>> to implement it.
>>
>>>> Wouldn't a function pointer, maybe guarded
>>>> by a static key, be enough? A further advantage would be that this
>>>> would
>>>> work on other architectures, too.
>>> I assume this feature will be ported to other archs.. a new pvops makes
> 
>       sorry, a typo.. /other archs/other hypervisors/
>       it refers hypervisor like Xen, HyperV and VMware)..
> 
>>> code
>>> clean and easy to maintain. also I tried to add it into existed pvops,
>>> but it
>>> doesn't match.
>> You are aware that pvops is x86 only?
> 
> yes, I'm aware..
> 
>> I really don't see the big difference in maintainability compared to the
>> static key / function pointer variant:
>>
>> void (*guest_idle_poll_func)(void);
>> struct static_key guest_idle_poll_key __read_mostly;
>>
>> static inline void guest_idle_poll(void)
>> {
>>     if (static_key_false(&guest_idle_poll_key))
>>         guest_idle_poll_func();
>> }
> 
> 
> 
> thank you for your sample code :)
> I agree there is no big difference.. I think we are discussion for two
> things:
>  1) x86 VM on different hypervisors
>  2) different archs VM on kvm hypervisor
> 
> What I want to do is x86 VM on different hypervisors, such as kvm / xen
> / hyperv ..

Why limit the solution to x86 if the more general solution isn't
harder?

As you didn't give any reason why the pvops approach is better other
than you don't care for non-x86 platforms you won't get an "Ack" from
me for this patch.

> 
>> And KVM would just need to set guest_idle_poll_func and enable the
>> static key. Works on non-x86 architectures, too.
>>
> 
> .. referred to 'pv_mmu_ops', HyperV and Xen can implement their own
> functions for 'pv_mmu_ops'.
> I think it is the same to pv_idle_ops.
> 
> with above explaination, do you still think I need to define the static
> key/function pointer variant?
> 
> btw, any interest to port it to Xen HVM guest? :)

Maybe. But this should work for Xen on ARM, too.


Juergen