From: Andrew Cooper <andrew.cooper3@citrix.com>
To: Jan Beulich <JBeulich@suse.com>
Cc: Sergey Dyasli <sergey.dyasli@citrix.com>,
Kevin Tian <kevin.tian@intel.com>,
Kevin.Mayer@gdata.de, Anshul Makkar <anshul.makkar@citrix.com>,
Jun Nakajima <jun.nakajima@intel.com>,
xen-devel <xen-devel@lists.xenproject.org>
Subject: Re: [PATCH 1/2] VMX: fix VMCS race on context-switch paths
Date: Wed, 15 Feb 2017 11:29:47 +0000 [thread overview]
Message-ID: <d58a156f-ef96-1590-4327-08a0162bdf76@citrix.com> (raw)
In-Reply-To: <58A4215F0200007800139F85@prv-mh.provo.novell.com>
On 15/02/17 08:37, Jan Beulich wrote:
>>>> On 14.02.17 at 16:16, <andrew.cooper3@citrix.com> wrote:
>> On 14/02/17 10:28, Jan Beulich wrote:
>>> --- a/xen/arch/x86/hvm/vmx/vmcs.c
>>> +++ b/xen/arch/x86/hvm/vmx/vmcs.c
>>> @@ -552,6 +552,27 @@ static void vmx_load_vmcs(struct vcpu *v
>>> local_irq_restore(flags);
>>> }
>>>
>>> +void vmx_vmcs_reload(struct vcpu *v)
>>> +{
>>> + /*
>>> + * As we're running with interrupts disabled, we can't acquire
>>> + * v->arch.hvm_vmx.vmcs_lock here. However, with interrupts disabled
>>> + * the VMCS can't be taken away from us anymore if we still own it.
>>> + */
>>> + ASSERT(!local_irq_is_enabled());
>>> + if ( v->arch.hvm_vmx.vmcs_pa == this_cpu(current_vmcs) )
>>> + return;
>>> + ASSERT(!this_cpu(current_vmcs));
>>> +
>>> + /*
>>> + * Wait for the remote side to be done with the VMCS before loading
>>> + * it here.
>>> + */
>>> + while ( v->arch.hvm_vmx.active_cpu != -1 )
>>> + cpu_relax();
>> Doesn't this need a ACCESS_ONCE() read?
>>
>> While the compiled code (using GCC 4.9) isn't an infinite loop, I am not
>> aware of anything which prevents a compiler hoisting the comparison out
>> as being constant.
> That's the (intended) side effect of cpu_relax() having a memory
> clobber.
Ah ok. In which case that should be fine.
~Andrew
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel
next prev parent reply other threads:[~2017-02-15 11:29 UTC|newest]
Thread overview: 27+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-02-14 10:23 [PATCH 0/2] x86: context switch handling adjustments Jan Beulich
2017-02-14 10:28 ` [PATCH 1/2] VMX: fix VMCS race on context-switch paths Jan Beulich
2017-02-14 15:16 ` Andrew Cooper
2017-02-15 8:37 ` Jan Beulich
2017-02-15 11:29 ` Andrew Cooper [this message]
2017-02-15 10:27 ` Sergey Dyasli
2017-02-15 11:00 ` Jan Beulich
2017-02-15 11:13 ` Sergey Dyasli
2017-02-15 11:24 ` Jan Beulich
2017-02-15 11:39 ` Jan Beulich
2017-02-15 11:48 ` Sergey Dyasli
2017-02-15 11:55 ` Jan Beulich
2017-02-15 13:03 ` Jan Beulich
2017-02-15 13:40 ` Sergey Dyasli
2017-02-15 14:29 ` Jan Beulich
2017-02-15 14:44 ` Jan Beulich
2017-02-15 13:20 ` Jan Beulich
2017-02-15 14:55 ` Sergey Dyasli
2017-02-15 15:15 ` Jan Beulich
2017-02-16 8:29 ` Sergey Dyasli
2017-02-16 9:26 ` Jan Beulich
2017-02-14 10:29 ` [PATCH 2/2] x86: package up context switch hook pointers Jan Beulich
2017-02-14 15:26 ` Andrew Cooper
2017-02-15 8:42 ` Jan Beulich
2017-02-15 11:34 ` Andrew Cooper
2017-02-15 11:40 ` Jan Beulich
2017-02-14 22:18 ` Boris Ostrovsky
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=d58a156f-ef96-1590-4327-08a0162bdf76@citrix.com \
--to=andrew.cooper3@citrix.com \
--cc=JBeulich@suse.com \
--cc=Kevin.Mayer@gdata.de \
--cc=anshul.makkar@citrix.com \
--cc=jun.nakajima@intel.com \
--cc=kevin.tian@intel.com \
--cc=sergey.dyasli@citrix.com \
--cc=xen-devel@lists.xenproject.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.