All of lore.kernel.org
 help / color / mirror / Atom feed
From: Waiman Long <longman@redhat.com>
To: Guo Hui <guohui@uniontech.com>, peterz@infradead.org
Cc: jgross@suse.com, srivatsa@csail.mit.edu, amakhalov@vmware.com,
	pv-drivers@vmware.com, tglx@linutronix.de, mingo@redhat.com,
	bp@alien8.de, dave.hansen@linux.intel.com, x86@kernel.org,
	hpa@zytor.com, will@kernel.org, boqun.feng@gmail.com,
	virtualization@lists.linux-foundation.org,
	wangxiaohua@uniontech.com, linux-kernel@vger.kernel.org
Subject: Re: [PATCH v2] x86/paravirt: useless assignment instructions cause Unixbench full core performance degradation
Date: Mon, 27 Jun 2022 09:25:54 -0400	[thread overview]
Message-ID: <14a3278e-0299-8138-ff73-654d0208bdfa@redhat.com> (raw)
In-Reply-To: <62b94621.1c69fb81.3a378.57ccSMTPIN_ADDED_BROKEN@mx.google.com>

On 6/27/22 01:54, Guo Hui wrote:
> Thank you very much Longman, my patch is as you said, only disable 
> node_cpu on X86, enable node_cpu on arm64, powerpc, s390 architectures;
> the code is in file arch/x86/kernel/paravirt-spinlocks.c:
>     DECLARE_STATIC_KEY_FALSE(preemted_key);
>     static_branch_enable(&preemted_key);
>
> the default value of preemted_key is false and the if conditional 
> statement is reversed,
> the code is in file kernel/locking/osq_lock.c:
>     DEFINE_STATIC_KEY_FALSE(preemted_key);
>
>     static inline int node_cpu(struct optimistic_spin_node *node)
>     {
>         int cpu = 0;
>
>         if (!static_branch_unlikely(&preemted_key))
>             cpu = node->cpu - 1;
>
>         return cpu;
>   }
>
> In this way, only one nop instruction is added to architectures arm64, 
> powerpc and s390, including virtual machines, without any other changes.

You are right. I am probably too tired last night to read the patch more 
carefully.

Cheers,
Longman


WARNING: multiple messages have this Message-ID (diff)
From: Waiman Long <longman@redhat.com>
To: Guo Hui <guohui@uniontech.com>, peterz@infradead.org
Cc: jgross@suse.com, x86@kernel.org, hpa@zytor.com,
	pv-drivers@vmware.com, boqun.feng@gmail.com,
	dave.hansen@linux.intel.com, linux-kernel@vger.kernel.org,
	virtualization@lists.linux-foundation.org, mingo@redhat.com,
	bp@alien8.de, amakhalov@vmware.com, tglx@linutronix.de,
	will@kernel.org, wangxiaohua@uniontech.com
Subject: Re: [PATCH v2] x86/paravirt: useless assignment instructions cause Unixbench full core performance degradation
Date: Mon, 27 Jun 2022 09:25:54 -0400	[thread overview]
Message-ID: <14a3278e-0299-8138-ff73-654d0208bdfa@redhat.com> (raw)
In-Reply-To: <62b94621.1c69fb81.3a378.57ccSMTPIN_ADDED_BROKEN@mx.google.com>

On 6/27/22 01:54, Guo Hui wrote:
> Thank you very much Longman, my patch is as you said, only disable 
> node_cpu on X86, enable node_cpu on arm64, powerpc, s390 architectures;
> the code is in file arch/x86/kernel/paravirt-spinlocks.c:
>     DECLARE_STATIC_KEY_FALSE(preemted_key);
>     static_branch_enable(&preemted_key);
>
> the default value of preemted_key is false and the if conditional 
> statement is reversed,
> the code is in file kernel/locking/osq_lock.c:
>     DEFINE_STATIC_KEY_FALSE(preemted_key);
>
>     static inline int node_cpu(struct optimistic_spin_node *node)
>     {
>         int cpu = 0;
>
>         if (!static_branch_unlikely(&preemted_key))
>             cpu = node->cpu - 1;
>
>         return cpu;
>   }
>
> In this way, only one nop instruction is added to architectures arm64, 
> powerpc and s390, including virtual machines, without any other changes.

You are right. I am probably too tired last night to read the patch more 
carefully.

Cheers,
Longman

_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization

  parent reply	other threads:[~2022-06-27 13:26 UTC|newest]

Thread overview: 26+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-06-23 15:50 [PATCH] x86/paravirt: useless assignment instructions cause Unixbench full core performance degradation Guo Hui
2022-06-23 21:54 ` Waiman Long
2022-06-27  2:13   ` [PATCH v2] " Guo Hui
2022-06-27  3:02     ` Waiman Long
2022-06-27  3:02       ` Waiman Long
     [not found]       ` <62b94621.1c69fb81.3a378.57ccSMTPIN_ADDED_BROKEN@mx.google.com>
2022-06-27 13:25         ` Waiman Long [this message]
2022-06-27 13:25           ` Waiman Long
2022-06-27  5:57     ` Juergen Gross via Virtualization
2022-06-27  5:57       ` Juergen Gross
2022-06-27  7:07       ` [PATCH v3] " Guo Hui
2022-06-27  7:49     ` [PATCH v2] " Peter Zijlstra
2022-06-27  7:49       ` Peter Zijlstra
     [not found]       ` <3c020577-2045-fa12-9e33-65ece10bda30@uniontech.com>
2022-06-27  9:30         ` Peter Zijlstra
2022-06-27  9:30           ` Peter Zijlstra
2022-06-27 14:27       ` [PATCH v4] " Guo Hui
2022-06-27 15:42         ` Juergen Gross
2022-06-27 15:42           ` Juergen Gross via Virtualization
2022-06-27 15:58         ` Waiman Long
2022-06-27 15:58           ` Waiman Long
2022-06-28  4:31           ` [PATCH v5] " Guo Hui
2022-06-28 12:54           ` [PATCH v6] " Guo Hui
2022-06-28 14:15             ` Waiman Long
2022-06-28 14:15               ` Waiman Long
2022-06-28 16:12               ` [PATCH v7] " Guo Hui
2022-06-28 17:28                 ` Waiman Long
2022-06-28 17:28                   ` Waiman Long

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=14a3278e-0299-8138-ff73-654d0208bdfa@redhat.com \
    --to=longman@redhat.com \
    --cc=amakhalov@vmware.com \
    --cc=boqun.feng@gmail.com \
    --cc=bp@alien8.de \
    --cc=dave.hansen@linux.intel.com \
    --cc=guohui@uniontech.com \
    --cc=hpa@zytor.com \
    --cc=jgross@suse.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@redhat.com \
    --cc=peterz@infradead.org \
    --cc=pv-drivers@vmware.com \
    --cc=srivatsa@csail.mit.edu \
    --cc=tglx@linutronix.de \
    --cc=virtualization@lists.linux-foundation.org \
    --cc=wangxiaohua@uniontech.com \
    --cc=will@kernel.org \
    --cc=x86@kernel.org \
    /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.