mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Wanpeng Li <kernellwp@gmail.com>
To: linux-kernel@vger.kernel.org, kvm@vger.kernel.org
Cc: Paolo Bonzini <pbonzini@redhat.com>,
	Sean Christopherson <sean.j.christopherson@intel.com>,
	Vitaly Kuznetsov <vkuznets@redhat.com>,
	Wanpeng Li <wanpengli@tencent.com>,
	Jim Mattson <jmattson@google.com>, Joerg Roedel <joro@8bytes.org>,
	Haiwei Li <lihaiwei@tencent.com>
Subject: [PATCH v2 0/5] KVM: VMX: Tscdeadline timer emulation fastpath
Date: Thu, 23 Apr 2020 17:01:42 +0800	[thread overview]
Message-ID: <1587632507-18997-1-git-send-email-wanpengli@tencent.com> (raw)

IPI and Timer cause the main vmexits in cloud environment observation, 
after single target IPI fastpath, let's optimize tscdeadline timer 
latency by introducing tscdeadline timer emulation fastpath, it will 
skip various KVM related checks when possible. i.e. after vmexit due 
to tscdeadline timer emulation, handle it and vmentry immediately 
without checking various kvm stuff when possible. 

Testing on SKX Server.

cyclictest in guest(w/o mwait exposed, adaptive advance lapic timer is default -1):

5632.75ns -> 4559.25ns, 19%

kvm-unit-test/vmexit.flat:

w/o APICv, w/o advance timer:
tscdeadline_immed: 4780.75 -> 3851    19.4%
tscdeadline:       7474    -> 6528.5  12.7%

w/o APICv, w/ adaptive advance timer default -1:
tscdeadline_immed: 4845.75 -> 3930.5  18.9%
tscdeadline:       6048    -> 5871.75    3%

w/ APICv, w/o avanced timer:
tscdeadline_immed: 2919    -> 2467.75 15.5%
tscdeadline:       5661.75 -> 5188.25  8.4%

w/ APICv, w/ adaptive advance timer default -1:
tscdeadline_immed: 3018.5  -> 2561    15.2%
tscdeadline:       4663.75 -> 4537     2.7%

Tested-by: Haiwei Li <lihaiwei@tencent.com>
Cc: Haiwei Li <lihaiwei@tencent.com>

v1 -> v2:
 * move more stuff from vmx.c to lapic.c
 * remove redundant checking
 * check more conditions to bail out CONT_RUN
 * not break AMD
 * not handle LVTT sepecial
 * cleanup codes

Wanpeng Li (5):
  KVM: LAPIC: Introduce interrupt delivery fastpath
  KVM: X86: Introduce need_cancel_enter_guest helper
  KVM: VMX: Introduce generic fastpath handler
  KVM: X86: TSCDEADLINE MSR emulation fastpath
  KVM: VMX: Handle preemption timer fastpath

 arch/x86/include/asm/kvm_host.h |  2 +
 arch/x86/kvm/lapic.c            | 98 +++++++++++++++++++++++++++++++++++++++--
 arch/x86/kvm/lapic.h            |  2 +
 arch/x86/kvm/svm/avic.c         |  5 +++
 arch/x86/kvm/svm/svm.c          |  1 +
 arch/x86/kvm/svm/svm.h          |  1 +
 arch/x86/kvm/vmx/vmx.c          | 69 ++++++++++++++++++++++++-----
 arch/x86/kvm/x86.c              | 42 ++++++++++++++----
 arch/x86/kvm/x86.h              |  1 +
 9 files changed, 199 insertions(+), 22 deletions(-)

-- 
2.7.4


             reply	other threads:[~2020-04-23  9:01 UTC|newest]

Thread overview: 19+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-04-23  9:01 Wanpeng Li [this message]
2020-04-23  9:01 ` [PATCH v2 1/5] KVM: LAPIC: Introduce interrupt delivery fastpath Wanpeng Li
2020-04-23  9:25   ` Paolo Bonzini
2020-04-23  9:35     ` Wanpeng Li
2020-04-23  9:39       ` Paolo Bonzini
2020-04-23  9:44         ` Wanpeng Li
2020-04-23  9:52           ` Paolo Bonzini
2020-04-23  9:01 ` [PATCH v2 2/5] KVM: X86: Introduce need_cancel_enter_guest helper Wanpeng Li
2020-04-23  9:01 ` [PATCH v2 3/5] KVM: VMX: Introduce generic fastpath handler Wanpeng Li
2020-04-23  9:01 ` [PATCH v2 4/5] KVM: X86: TSCDEADLINE MSR emulation fastpath Wanpeng Li
2020-04-23  9:37   ` Paolo Bonzini
2020-04-23  9:54     ` Wanpeng Li
2020-04-23 10:28       ` Paolo Bonzini
2020-04-23  9:01 ` [PATCH v2 5/5] KVM: VMX: Handle preemption timer fastpath Wanpeng Li
2020-04-23  9:40   ` Paolo Bonzini
2020-04-23  9:56     ` Wanpeng Li
2020-04-23 10:29       ` Paolo Bonzini
2020-04-24  6:38         ` Wanpeng Li
2020-04-26  7:38   ` kbuild test robot

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=1587632507-18997-1-git-send-email-wanpengli@tencent.com \
    --to=kernellwp@gmail.com \
    --cc=jmattson@google.com \
    --cc=joro@8bytes.org \
    --cc=kvm@vger.kernel.org \
    --cc=lihaiwei@tencent.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=pbonzini@redhat.com \
    --cc=sean.j.christopherson@intel.com \
    --cc=vkuznets@redhat.com \
    --cc=wanpengli@tencent.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

all inboxes | Powered by JetHome®