From: Avi Kivity <avi@redhat.com>
To: Tomoki Sekiyama <tomoki.sekiyama.qu@hitachi.com>
Cc: kvm@vger.kernel.org, linux-kernel@vger.kernel.org,
x86@kernel.org, yrl.pp-manager.tt@hitachi.com,
Marcelo Tosatti <mtosatti@redhat.com>,
Thomas Gleixner <tglx@linutronix.de>,
Ingo Molnar <mingo@redhat.com>, "H. Peter Anvin" <hpa@zytor.com>
Subject: Re: [RFC PATCH 18/18] x86: request TLB flush to slave CPU using NMI
Date: Thu, 28 Jun 2012 19:38:58 +0300 [thread overview]
Message-ID: <4FEC88A2.5040103@redhat.com> (raw)
In-Reply-To: <20120628060853.19298.32233.stgit@localhost.localdomain>
On 06/28/2012 09:08 AM, Tomoki Sekiyama wrote:
> For slave CPUs, it is inapropriate to request TLB flush using IPI.
> because the IPI may be sent to a KVM guest when the slave CPU is running
> the guest with direct interrupt routing.
>
> Instead, it registers a TLB flush request in per-cpu bitmask and send a NMI
> to interrupt execution of the guest. Then, NMI handler will check the
> requests and handles the requests.
Currently x86's get_user_pages_fast() depends on TLB flushes being held
up by local_irq_disable(). With this patch, this is no longer true and
get_user_pages_fast() can race with page table freeing. There are
patches from Peter Zijlstra to remove this dependency though. NMIs are
still slow and fragile when compared to normal interrupts, so this patch
is somewhat problematic.
--
error compiling committee.c: too many arguments to function
next prev parent reply other threads:[~2012-06-28 16:38 UTC|newest]
Thread overview: 33+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-06-28 6:07 [RFC PATCH 00/18] KVM: x86: CPU isolation and direct interrupts handling by guests Tomoki Sekiyama
2012-06-28 6:07 ` [RFC PATCH 01/18] x86: Split memory hotplug function from cpu_up() as cpu_memory_up() Tomoki Sekiyama
2012-06-28 6:07 ` [RFC PATCH 02/18] x86: Add a facility to use offlined CPUs as slave CPUs Tomoki Sekiyama
2012-06-28 6:07 ` [RFC PATCH 03/18] x86: Support hrtimer on " Tomoki Sekiyama
2012-06-28 6:07 ` [RFC PATCH 04/18] KVM: Replace local_irq_disable/enable with local_irq_save/restore Tomoki Sekiyama
2012-06-28 6:07 ` [RFC PATCH 05/18] KVM: Enable/Disable virtualization on slave CPUs are activated/dying Tomoki Sekiyama
2012-06-28 6:07 ` [RFC PATCH 06/18] KVM: Add facility to run guests on slave CPUs Tomoki Sekiyama
2012-06-28 17:02 ` Avi Kivity
2012-06-29 9:26 ` Tomoki Sekiyama
2012-06-28 6:07 ` [RFC PATCH 07/18] KVM: handle page faults occured in slave CPUs on online CPUs Tomoki Sekiyama
2012-06-28 6:08 ` [RFC PATCH 08/18] KVM: Add KVM_GET_SLAVE_CPU and KVM_SET_SLAVE_CPU to vCPU ioctl Tomoki Sekiyama
2012-06-28 6:08 ` [RFC PATCH 09/18] KVM: Go back to online CPU on VM exit by external interrupt Tomoki Sekiyama
2012-06-28 6:08 ` [RFC PATCH 10/18] KVM: proxy slab operations for slave CPUs on online CPUs Tomoki Sekiyama
2012-06-28 6:08 ` [RFC PATCH 11/18] KVM: no exiting from guest when slave CPU halted Tomoki Sekiyama
2012-06-28 6:08 ` [RFC PATCH 12/18] x86/apic: Enable external interrupt routing to slave CPUs Tomoki Sekiyama
2012-06-28 6:08 ` [RFC PATCH 13/18] x86/apic: IRQ vector remapping on slave for " Tomoki Sekiyama
2012-06-28 6:08 ` [RFC PATCH 14/18] KVM: Directly handle interrupts by guests without VM EXIT on " Tomoki Sekiyama
2012-06-28 6:08 ` [RFC PATCH 15/18] KVM: vmx: Add definitions PIN_BASED_PREEMPTION_TIMER Tomoki Sekiyama
2012-06-28 6:08 ` [RFC PATCH 16/18] KVM: add kvm_arch_vcpu_prevent_run to prevent VM ENTER when NMI is received Tomoki Sekiyama
2012-06-28 16:48 ` Avi Kivity
2012-06-29 9:26 ` Tomoki Sekiyama
2012-06-28 6:08 ` [RFC PATCH 17/18] KVM: route assigned devices' MSI/MSI-X directly to guests on slave CPUs Tomoki Sekiyama
2012-06-28 6:08 ` [RFC PATCH 18/18] x86: request TLB flush to slave CPU using NMI Tomoki Sekiyama
2012-06-28 16:38 ` Avi Kivity [this message]
2012-06-29 9:26 ` Tomoki Sekiyama
2012-06-28 16:58 ` [RFC PATCH 00/18] KVM: x86: CPU isolation and direct interrupts handling by guests Avi Kivity
2012-06-28 17:26 ` Jan Kiszka
2012-06-28 17:34 ` Avi Kivity
2012-06-29 9:25 ` Tomoki Sekiyama
2012-06-29 14:56 ` Avi Kivity
2012-07-06 10:33 ` Tomoki Sekiyama
2012-07-12 9:04 ` Avi Kivity
2012-07-04 9:33 ` Tomoki Sekiyama
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=4FEC88A2.5040103@redhat.com \
--to=avi@redhat.com \
--cc=hpa@zytor.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=mtosatti@redhat.com \
--cc=tglx@linutronix.de \
--cc=tomoki.sekiyama.qu@hitachi.com \
--cc=x86@kernel.org \
--cc=yrl.pp-manager.tt@hitachi.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;
as well as URLs for NNTP newsgroup(s).