mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Gleb Natapov <gleb@redhat.com>
To: kvm@vger.kernel.org
Cc: linux-mm@kvack.org, linux-kernel@vger.kernel.org, avi@redhat.com,
	mingo@elte.hu, a.p.zijlstra@chello.nl, tglx@linutronix.de,
	hpa@zytor.com, riel@redhat.com
Subject: [PATCH v2 00/12] KVM: Add asynchronous page fault for PV guest.
Date: Mon, 23 Nov 2009 16:05:55 +0200	[thread overview]
Message-ID: <1258985167-29178-1-git-send-email-gleb@redhat.com> (raw)

KVM virtuaize guest memory by means of shadow pages or HW assistance
like NPT/EPT. Not all memory used by a guest is mapped into the guest
address space or even present in a host memory at any given time.
When vcpu tries to access memory page that is not mapped into guest
address space KVM is notified about it. KVM maps the page into guest
address space and resumes vcpu execution. If the page is swapped out
from host memory vcpu execution is suspended till page is not swapped
into the memory again. This is inefficient since vcpu can do other work
(run other task or serve interrupts) while page gets swapped in.

To overcome this inefficient this patch series implements "asynchronous
page fault" for paravirtualized  KVM guests. If a page that vcpu is trying
to access is swapped out KVM sends async PF to the vcpu and continues vcpu
execution. Requested page is swapped in by another thread in parallel.
When vcpu gets async PF it puts the task that faulted to sleep until
"wake up" interrupt is delivered. When page is brought to host memory
KVM sends "wake up" interrupt and the guest task resumes execution.

Changes:
 v1->v2
   Use MSR instead of hypercall.
   Move most of the code into arch independent place.
   halt inside a guest instead of doing "wait for page" hypercall if
    preemption is disabled.
   
Gleb Natapov (12):
  Move kvm_smp_prepare_boot_cpu() from kvmclock.c to kvm.c.
  Add PV MSR to enable asynchronous page faults delivery.
  Add async PF initialization to PV guest.
  Add "handle page fault" PV helper.
  Handle asynchronous page fault in a PV guest.
  Export __get_user_pages_fast.
  Add get_user_pages() variant that fails if major fault is required.
  Inject asynchronous page fault into a guest if page is swapped out.
  Retry fault before vmentry
  Maintain preemptability count even for !CONFIG_PREEMPT kernels
  Handle async PF in non preemptable context.
  Send async PF when guest is not in userspace too.

 arch/x86/include/asm/kvm_host.h       |   22 +++-
 arch/x86/include/asm/kvm_para.h       |   11 ++
 arch/x86/include/asm/paravirt.h       |    7 +
 arch/x86/include/asm/paravirt_types.h |    4 +
 arch/x86/kernel/kvm.c                 |  215 +++++++++++++++++++++++++++++++
 arch/x86/kernel/kvmclock.c            |   13 +--
 arch/x86/kernel/paravirt.c            |    8 +
 arch/x86/kernel/paravirt_patch_32.c   |    8 +
 arch/x86/kernel/paravirt_patch_64.c   |    7 +
 arch/x86/kernel/smpboot.c             |    3 +
 arch/x86/kvm/Kconfig                  |    2 +
 arch/x86/kvm/mmu.c                    |   46 ++++++-
 arch/x86/kvm/paging_tmpl.h            |   50 +++++++-
 arch/x86/kvm/x86.c                    |   86 ++++++++++++-
 arch/x86/mm/fault.c                   |    3 +
 arch/x86/mm/gup.c                     |    2 +
 fs/ncpfs/mmap.c                       |    2 +
 include/linux/hardirq.h               |   14 +--
 include/linux/kvm.h                   |    1 +
 include/linux/kvm_host.h              |   27 ++++
 include/linux/kvm_para.h              |    2 +
 include/linux/mm.h                    |    5 +
 include/linux/preempt.h               |   22 +++-
 include/linux/sched.h                 |    4 -
 include/trace/events/kvm.h            |   60 +++++++++
 kernel/sched.c                        |    6 -
 lib/kernel_lock.c                     |    1 +
 mm/filemap.c                          |    3 +
 mm/memory.c                           |   31 ++++-
 mm/shmem.c                            |    8 +-
 virt/kvm/Kconfig                      |    3 +
 virt/kvm/kvm_main.c                   |  227 ++++++++++++++++++++++++++++++++-
 32 files changed, 846 insertions(+), 57 deletions(-)


             reply	other threads:[~2009-11-23 14:09 UTC|newest]

Thread overview: 30+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2009-11-23 14:05 Gleb Natapov [this message]
2009-11-23 14:05 ` [PATCH v2 01/12] Move kvm_smp_prepare_boot_cpu() from kvmclock.c to kvm.c Gleb Natapov
2009-11-23 14:05 ` [PATCH v2 02/12] Add PV MSR to enable asynchronous page faults delivery Gleb Natapov
2009-11-25 12:32   ` Avi Kivity
2009-11-23 14:05 ` [PATCH v2 03/12] Add async PF initialization to PV guest Gleb Natapov
2009-11-23 14:05 ` [PATCH v2 04/12] Add "handle page fault" PV helper Gleb Natapov
2009-11-23 15:32   ` Peter Zijlstra
2009-11-23 14:06 ` [PATCH v2 05/12] Handle asynchronous page fault in a PV guest Gleb Natapov
2009-11-25 12:45   ` Avi Kivity
2009-11-23 14:06 ` [PATCH v2 06/12] Export __get_user_pages_fast Gleb Natapov
2009-11-23 14:06 ` [PATCH v2 07/12] Add get_user_pages() variant that fails if major fault is required Gleb Natapov
2009-11-23 14:06 ` [PATCH v2 08/12] Inject asynchronous page fault into a guest if page is swapped out Gleb Natapov
2009-11-25 13:03   ` Avi Kivity
2009-11-23 14:06 ` [PATCH v2 09/12] Retry fault before vmentry Gleb Natapov
2009-11-25 13:09   ` Avi Kivity
2009-11-25 13:20     ` Gleb Natapov
2009-11-23 14:06 ` [PATCH v2 10/12] Maintain preemptability count even for !CONFIG_PREEMPT kernels Gleb Natapov
2009-11-23 15:34   ` Peter Zijlstra
2009-11-23 15:58     ` Gleb Natapov
2009-11-23 17:30       ` Christoph Lameter
2009-11-24  7:12         ` Gleb Natapov
2009-11-24 15:14           ` Christoph Lameter
2009-11-30 10:56             ` Gleb Natapov
2009-11-30 10:58               ` Gleb Natapov
2009-11-30 10:59                 ` Peter Zijlstra
2009-11-30 11:01                   ` Avi Kivity
2009-11-30 11:05                   ` Peter Zijlstra
2009-11-30 16:23                     ` Christoph Lameter
2009-11-23 14:06 ` [PATCH v2 11/12] Handle async PF in non preemptable context Gleb Natapov
2009-11-23 14:06 ` [PATCH v2 12/12] Send async PF when guest is not in userspace too Gleb Natapov

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=1258985167-29178-1-git-send-email-gleb@redhat.com \
    --to=gleb@redhat.com \
    --cc=a.p.zijlstra@chello.nl \
    --cc=avi@redhat.com \
    --cc=hpa@zytor.com \
    --cc=kvm@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mingo@elte.hu \
    --cc=riel@redhat.com \
    --cc=tglx@linutronix.de \
    /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

Powered by JetHome