public inbox for kvm@vger.kernel.org
 help / color / mirror / Atom feed
From: Sheng Yang <yasker@gmail.com>
To: Avi Kivity <avi@redhat.com>
Cc: Sheng Yang <sheng@linux.intel.com>, kvm@vger.kernel.org
Subject: Re: [PATCH 09/10] KVM: Enable MSI for device assignment
Date: Tue, 4 Nov 2008 22:57:16 +0800	[thread overview]
Message-ID: <20081104145716.GD18696@yukikaze> (raw)
In-Reply-To: <49105DA7.3020204@redhat.com>

On Tue, Nov 04, 2008 at 04:35:19PM +0200, Avi Kivity wrote:
> Sheng Yang wrote:
>>> In fact, it's not just for pci.  We could msi-enable e1000 and get   
>>> improved performance there as well.
>>>     
>>
>> E1000? Don't understand... Sounds like INTx->MSI...
>>   
>
> There are msi-capable e1000 cards.  If we upgrade qemu's e1000 to  
> support msi, and if the guest supports msi, it will be msi all the way.

Oh, forgot we got e1000 emulation in qemu...
>
>>>> But I guess what you means is only set
>>>> gsi can result in kvm_set_irq() deliver the MSI correctly. I think this can
>>>> be done. Associating gsi with guest_msi_addr and guest_msi_data in a linked
>>>> list, for gsi >= IOAPIC_PINS,
>>>>       
>>> Let's say, (gsi >> 24) == 1.  That gives us 16M potential MSIs.
>>>     
>>
>> Confused... GSI become a bitmap?
>>   
>
> A structure...
>
> struct gsi {
>    u32 n : 24;
>    u32 type : 8; // 0 -> classic gsi, 1 -> msi
> };

I just don't understand why we need 24 bits for n? GSI can be that wide?

--
regards
Yang, Sheng
>
>
> -- 
> error compiling committee.c: too many arguments to function
>
> --
> To unsubscribe from this list: send the line "unsubscribe kvm" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html

  reply	other threads:[~2008-11-04 14:57 UTC|newest]

Thread overview: 31+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2008-10-31  4:50 [PATCH 0/10][v4] Enable MSI for KVM assigned device kernel part Sheng Yang
2008-10-31  4:50 ` [PATCH 01/10] KVM: Move ack notifier register and IRQ sourcd ID request Sheng Yang
2008-10-31  4:50 ` [PATCH 02/10] KVM: Separate update irq to a single function Sheng Yang
2008-10-31  4:50 ` [PATCH 03/10] KVM: Replace irq_requested with more generic irq_requested_type Sheng Yang
2008-10-31  4:50 ` [PATCH 04/10] KVM: Clean up assigned_device_update_irq Sheng Yang
2008-10-31  4:50 ` [PATCH 05/10] KVM: Add fields for MSI device assignment Sheng Yang
2008-11-04 11:05   ` Avi Kivity
2008-10-31  4:50 ` [PATCH 06/10] KVM: Export ioapic_get_delivery_bitmask Sheng Yang
2008-11-04 11:07   ` Avi Kivity
2008-11-04 11:09     ` Sheng Yang
2008-10-31  4:50 ` [PATCH 07/10] x86: Add MSI delivery mode value Sheng Yang
2008-11-04 11:09   ` Avi Kivity
2008-11-04 11:37     ` Sheng Yang
2008-10-31  4:50 ` [PATCH 08/10] KVM: Add assigned_device_msi_dispatch() Sheng Yang
2008-11-04 11:17   ` Avi Kivity
2008-11-04 11:17     ` Sheng Yang
2008-10-31  4:50 ` [PATCH 09/10] KVM: Enable MSI for device assignment Sheng Yang
2008-11-04 11:23   ` Avi Kivity
2008-11-04 13:25     ` Sheng Yang
2008-11-04 13:32       ` Avi Kivity
2008-11-04 13:58         ` Sheng Yang
2008-11-04 14:35           ` Avi Kivity
2008-11-04 14:57             ` Sheng Yang [this message]
2008-11-04 15:01               ` Avi Kivity
2008-11-04 15:14                 ` Sheng Yang
2008-10-31  4:50 ` [PATCH 10/10] KVM: MSI to INTx translate Sheng Yang
2008-11-04 11:25   ` Avi Kivity
2008-11-04 11:40     ` Sheng Yang
2008-11-04 11:57       ` Avi Kivity
2008-11-04 12:55         ` Sheng Yang
  -- strict thread matches above, loose matches on Subject: below --
2008-10-30  8:20 [RFC][PATCH 0/10][v3] Enable MSI for KVM assigned device Sheng Yang
2008-10-30  8:20 ` [PATCH 09/10] KVM: Enable MSI for device assignment Sheng Yang

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=20081104145716.GD18696@yukikaze \
    --to=yasker@gmail.com \
    --cc=avi@redhat.com \
    --cc=kvm@vger.kernel.org \
    --cc=sheng@linux.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox