All of lore.kernel.org
 help / color / mirror / Atom feed
From: "Tian, Kevin" <kevin.tian@intel.com>
To: "Wu, Feng" <feng.wu@intel.com>,
	"Zhang, Yang Z" <yang.z.zhang@intel.com>,
	"xen-devel@lists.xen.org" <xen-devel@lists.xen.org>
Cc: "keir@xen.org" <keir@xen.org>, "JBeulich@suse.com" <JBeulich@suse.com>
Subject: Re: [RFC v1 12/15] vmx: Properly handle notification event when vCPU is running
Date: Thu, 2 Apr 2015 06:08:12 +0000	[thread overview]
Message-ID: <AADFC41AFE54684AB9EE6CBC0274A5D1261FB73B@SHSMSX101.ccr.corp.intel.com> (raw)
In-Reply-To: <E959C4978C3B6342920538CF579893F002469581@SHSMSX104.ccr.corp.intel.com>

> From: Wu, Feng
> Sent: Friday, March 27, 2015 12:58 PM
> 
> 
> 
> > -----Original Message-----
> > From: Zhang, Yang Z
> > Sent: Friday, March 27, 2015 12:44 PM
> > To: Wu, Feng; xen-devel@lists.xen.org
> > Cc: JBeulich@suse.com; keir@xen.org; Tian, Kevin
> > Subject: RE: [RFC v1 12/15] vmx: Properly handle notification event when
> vCPU
> > is running
> >
> > Wu, Feng wrote on 2015-03-27:
> > >
> > >
> > > Zhang, Yang Z wrote on 2015-03-25:
> > >> when vCPU is running
> > >>
> > >> Wu, Feng wrote on 2015-03-25:
> > >>> When a vCPU is running in Root mode and a notification event has
> > >>> been injected to it. we need to set VCPU_KICK_SOFTIRQ for the
> > >>> current cpu, so the pending interrupt in PIRR will be synced to
> > >>> vIRR before
> > > VM-Exit in time.
> > >>
> > >> Shouldn't the pending interrupt be synced unconditionally before next
> > >> vmentry? What happens if we didn't set the softirq?
> > >
> > > If we didn't set the softirq in the notification handler, the
> > > interrupts happened exactly before VM-entry cannot be delivered to
> > > guest at this time. Please see the following code fragments from
> > > xen/arch/x86/hvm/vmx/entry.S: (pls pay attention to the comments)
> > >
> > > .Lvmx_do_vmentry
> > >
> > > ......
> > > 		/* If Vt-d engine issues a notification event here,
> > >          * it cannot be delivered to guest during this VM-entry
> > >          * without raising the softirq in notification handler. */
> > >         cmp  %ecx,(%rdx,%rax,1)
> > >         jnz  .Lvmx_process_softirqs
> > > ......
> > >
> > >         je   .Lvmx_launch
> > > ......
> > >
> > >
> > > .Lvmx_process_softirqs:
> > >         sti
> > >         call do_softirq
> > >         jmp  .Lvmx_do_vmentry
> >
> > You are right! This helps me to recall why raise the softirq when delivering
> the
> > PI.
> 
> Yes, __vmx_deliver_posted_interrupt() is the software way to deliver PI, it sets
> the
> softirq for this purpose, however, when VT-d HW delivers PI, we have no
> control to
> the HW itself, hence we need to set this softirq in the Notification Event
> handler.
> 

could you include this information in the comment so others can easily
understand this requirement? from code you only mentioned VCPU_KICK
_SOFTIRQ is required, but how it leads to PIRR->VIRR sync is not explained.

Thanks
Kevin

  reply	other threads:[~2015-04-02  6:08 UTC|newest]

Thread overview: 101+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-03-25 12:31 [RFC v1 00/15] Add VT-d Posted-Interrupts support Feng Wu
2015-03-25 12:31 ` [RFC v1 01/15] iommu: Add iommu_intpost to control VT-d Posted-Interrupts feature Feng Wu
2015-03-26 17:39   ` Andrew Cooper
2015-03-27  4:46     ` Wu, Feng
2015-03-27  9:55       ` Andrew Cooper
2015-03-27  9:52     ` Jan Beulich
2015-03-25 12:31 ` [RFC v1 02/15] vt-d: VT-d Posted-Interrupts feature detection Feng Wu
2015-03-26 18:12   ` Andrew Cooper
2015-03-27  1:21     ` Wu, Feng
2015-03-27 10:06       ` Andrew Cooper
2015-03-27 13:41         ` Wu, Feng
2015-03-25 12:31 ` [RFC v1 03/15] vmx: Extend struct pi_desc to support VT-d Posted-Interrupts Feng Wu
2015-03-26 18:37   ` Andrew Cooper
2015-03-27  1:32     ` Wu, Feng
2015-03-25 12:31 ` [RFC v1 04/15] vmx: Add some helper functions for Posted-Interrupts Feng Wu
2015-03-26 18:44   ` Andrew Cooper
2015-03-25 12:31 ` [RFC v1 05/15] vmx: Initialize VT-d Posted-Interrupts Descriptor Feng Wu
2015-03-26 18:53   ` Andrew Cooper
2015-03-27  1:45     ` Wu, Feng
2015-03-26 19:29   ` Konrad Rzeszutek Wilk
2015-03-27  1:45     ` Wu, Feng
2015-05-04  5:32     ` Wu, Feng
2015-05-04  8:10       ` Jan Beulich
2015-05-04  8:36       ` Andrew Cooper
2015-05-04  9:07         ` Wu, Feng
2015-03-25 12:31 ` [RFC v1 06/15] vt-d: Extend struct iremap_entry to support VT-d Posted-Interrupts Feng Wu
2015-03-26 19:00   ` Andrew Cooper
2015-03-27  1:53     ` Wu, Feng
2015-03-27  9:58       ` Jan Beulich
2015-04-02  6:32         ` Tian, Kevin
2015-03-25 12:31 ` [RFC v1 07/15] vt-d: Add API to update IRTE when VT-d PI is used Feng Wu
2015-03-26 19:17   ` Andrew Cooper
2015-03-27  2:13     ` Wu, Feng
2015-03-27 10:02       ` Jan Beulich
2015-03-27  4:52     ` Wu, Feng
2015-03-26 19:36   ` Konrad Rzeszutek Wilk
2015-03-27  1:59     ` Wu, Feng
2015-04-02  5:34   ` Tian, Kevin
2015-04-02  6:02     ` Wu, Feng
2015-03-25 12:31 ` [RFC v1 08/15] Update IRTE according to guest interrupt config changes Feng Wu
2015-03-26 19:46   ` Konrad Rzeszutek Wilk
2015-03-27  5:45     ` Wu, Feng
2015-03-26 19:59   ` Andrew Cooper
2015-03-27  5:49     ` Wu, Feng
2015-03-27 11:31       ` Andrew Cooper
2015-04-02  5:52   ` Tian, Kevin
2015-04-02  6:20     ` Wu, Feng
2015-04-02  6:49       ` Tian, Kevin
2015-04-02  8:02         ` Wu, Feng
2015-04-03  8:29           ` Tian, Kevin
2015-03-25 12:31 ` [RFC v1 09/15] Add a new per-vCPU tasklet to wakeup the blocked vCPU Feng Wu
2015-04-02  5:53   ` Tian, Kevin
2015-04-02  7:20     ` Wu, Feng
2015-03-25 12:31 ` [RFC v1 10/15] vmx: Define two per-cpu variants Feng Wu
2015-03-26 19:59   ` Andrew Cooper
2015-04-02  5:54   ` Tian, Kevin
2015-04-02  6:24     ` Wu, Feng
2015-03-25 12:31 ` [RFC v1 11/15] vmx: Add a global wake-up vector for VT-d Posted-Interrupts Feng Wu
2015-03-26 20:07   ` Andrew Cooper
2015-04-02  6:00   ` Tian, Kevin
2015-04-02  7:18     ` Wu, Feng
2015-04-08  9:02       ` Tian, Kevin
2015-04-08 11:14         ` Wu, Feng
2015-03-25 12:31 ` [RFC v1 12/15] vmx: Properly handle notification event when vCPU is running Feng Wu
2015-03-25 14:14   ` Zhang, Yang Z
2015-03-27  4:40     ` Wu, Feng
2015-03-27  4:44       ` Zhang, Yang Z
2015-03-27  4:57         ` Wu, Feng
2015-04-02  6:08           ` Tian, Kevin [this message]
2015-04-02  7:21             ` Wu, Feng
2015-04-02 19:15             ` Konrad Rzeszutek Wilk
2015-04-03  2:00               ` Wu, Feng
2015-04-03 13:36                 ` Konrad Rzeszutek Wilk
2015-04-07  0:35                   ` Wu, Feng
2015-03-26 19:57   ` Konrad Rzeszutek Wilk
2015-03-27  3:06     ` Wu, Feng
2015-03-25 12:31 ` [RFC v1 13/15] Update Posted-Interrupts Descriptor during vCPU scheduling Feng Wu
2015-03-26 20:16   ` Andrew Cooper
2015-03-27  2:59     ` Wu, Feng
2015-04-02  6:24   ` Tian, Kevin
2015-04-02  8:39     ` Wu, Feng
2015-04-08  8:53       ` Tian, Kevin
2015-04-08 11:01         ` Wu, Feng
2015-04-09  2:37           ` Tian, Kevin
2015-03-25 12:31 ` [RFC v1 14/15] Suppress posting interrupts when 'SN' is set Feng Wu
2015-03-26 20:34   ` Andrew Cooper
2015-03-27  3:00     ` Wu, Feng
2015-03-27 12:06       ` Andrew Cooper
2015-03-27 13:45         ` Wu, Feng
2015-03-27 13:49           ` Andrew Cooper
2015-03-30  2:11             ` Wu, Feng
2015-03-30 10:11               ` Andrew Cooper
2015-03-25 12:31 ` [RFC v1 15/15] Add a command line parameter for VT-d posted-interrupts Feng Wu
2015-03-26 18:50 ` [RFC v1 00/15] Add VT-d Posted-Interrupts support Konrad Rzeszutek Wilk
2015-03-27  1:06   ` Wu, Feng
2015-03-27 14:44     ` Konrad Rzeszutek Wilk
2015-04-01 13:21 ` Wu, Feng
2015-04-13 12:12   ` Jan Beulich
2015-04-13 23:38     ` Wu, Feng
2015-04-24 17:50     ` Wu, Feng
2015-04-27 23:40       ` Jan Beulich

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=AADFC41AFE54684AB9EE6CBC0274A5D1261FB73B@SHSMSX101.ccr.corp.intel.com \
    --to=kevin.tian@intel.com \
    --cc=JBeulich@suse.com \
    --cc=feng.wu@intel.com \
    --cc=keir@xen.org \
    --cc=xen-devel@lists.xen.org \
    --cc=yang.z.zhang@intel.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 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.