All of lore.kernel.org
 help / color / mirror / Atom feed
From: Anthony Liguori <aliguori@us.ibm.com>
To: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Rusty Russell <rusty@rustcorp.com.au>,
	virtualization@lists.linux-foundation.org, kvm@vger.kernel.org,
	KONRAD Frederic <fred.konrad@greensocs.com>,
	Paolo Bonzini <pbonzini@redhat.com>,
	Peter Maydell <peter.maydell@linaro.org>,
	Stefan Hajnoczi <stefanha@redhat.com>,
	gleb@redhat.com,
	Benjamin Herrenschmidt <benh@kernel.crashing.org>
Subject: Re: [PATCH RFC] virtio-pci: new config layout: using memory BAR
Date: Wed, 05 Jun 2013 16:53:07 -0500	[thread overview]
Message-ID: <87d2s0mdh8.fsf@codemonkey.ws> (raw)
In-Reply-To: <20130605211405.GA31928@redhat.com>

"Michael S. Tsirkin" <mst@redhat.com> writes:

> On Wed, Jun 05, 2013 at 03:42:57PM -0500, Anthony Liguori wrote:
>> "Michael S. Tsirkin" <mst@redhat.com> writes:
>> 
>> Can you explain?  I thought the whole trick with separating out the
>> virtqueue notification register was to regain the performance?
>
> Yes but this trick only works well with NPT (it's still a bit
> slower than PIO but not so drastically).
> Without NPT you still need a page walk so it will be slow.

Do you mean NPT/EPT?

If your concern is shadow paging, then I think you're concerned about
hardware that is so slow to start with that it's not worth considering.

>> >> It also maps to what regular hardware does.  I highly doubt that there
>> >> are any real PCI cards that made the shift from PCI to PCI-e without
>> >> bumping at least a revision ID.
>> >
>> > Only because the chance it's 100% compatible on the software level is 0.
>> > It always has some hardware specific quirks.
>> > No such excuse here.
>> >
>> >> It also means we don't need to play games about sometimes enabling IO
>> >> bars and sometimes not.
>> >
>> > This last paragraph is wrong, it ignores the issues 3) to 5) 
>> > I added above.
>> >
>> > If you do take them into account:
>> > 	- there are reasons to add MMIO BAR to PCI,
>> > 	  even without PCI express
>> 
>> So far, the only reason you've provided is "it doesn't work on some
>> architectures."  Which architectures?
>
> PowerPC wants this.

Existing PowerPC remaps PIO to MMAP so it works fine today.

Future platforms may not do this but future platforms can use a
different device.  They certainly won't be able to use the existing
drivers anyway.

Ben, am I wrong here?

>> > 	- we won't be able to drop IO BAR from virtio
>> 
>> An IO BAR is useless if it means we can't have more than 12 devices.
>
>
> It's not useless. A smart BIOS can enable devices one by one as
> it tries to boot from them.

A smart BIOS can also use MMIO to program virtio.

Regards,

Anthony Liguori


  parent reply	other threads:[~2013-06-05 21:53 UTC|newest]

Thread overview: 109+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-05-28 16:03 [PATCH RFC] virtio-pci: new config layout: using memory BAR Michael S. Tsirkin
2013-05-28 17:15 ` Anthony Liguori
2013-05-28 17:32   ` Michael S. Tsirkin
2013-05-28 17:43     ` Paolo Bonzini
2013-05-29  2:02       ` Laszlo Ersek
2013-05-29  2:02         ` Laszlo Ersek
2013-05-29  4:33       ` Rusty Russell
2013-05-29  7:27         ` Paolo Bonzini
2013-05-29  8:05           ` Michael S. Tsirkin
2013-05-29 10:07           ` Laszlo Ersek
2013-05-29  4:33       ` Rusty Russell
2013-05-28 18:53     ` Anthony Liguori
2013-05-28 19:27       ` Michael S. Tsirkin
2013-05-29  4:31   ` Rusty Russell
2013-05-29  4:31     ` Rusty Russell
2013-05-29  8:24     ` Michael S. Tsirkin
2013-05-29  8:52       ` Paolo Bonzini
2013-05-29  9:00       ` Peter Maydell
2013-05-29 10:08         ` Michael S. Tsirkin
2013-05-29 10:53           ` Peter Maydell
2013-05-29 12:16             ` Michael S. Tsirkin
2013-05-29 12:28               ` Paolo Bonzini
2013-05-29 12:37                 ` Michael S. Tsirkin
2013-05-29 12:52     ` Anthony Liguori
2013-05-29 12:52       ` Anthony Liguori
2013-05-29 13:24       ` Michael S. Tsirkin
2013-05-29 13:35         ` Peter Maydell
2013-05-29 13:35         ` Peter Maydell
2013-05-29 13:41         ` Paolo Bonzini
2013-05-29 14:02           ` Michael S. Tsirkin
2013-05-29 14:18           ` Anthony Liguori
2013-05-29 14:18           ` Anthony Liguori
2013-05-30  7:43           ` Michael S. Tsirkin
2013-05-29 14:16         ` Anthony Liguori
2013-05-29 14:30           ` Michael S. Tsirkin
2013-05-29 14:32             ` Paolo Bonzini
2013-05-29 14:52               ` Michael S. Tsirkin
2013-05-29 14:55             ` Anthony Liguori
2013-05-29 16:12               ` Michael S. Tsirkin
2013-05-29 18:16               ` Michael S. Tsirkin
2013-05-29 14:55             ` Anthony Liguori
2013-05-29 14:16         ` Anthony Liguori
2013-05-30  3:58       ` Rusty Russell
2013-05-30  3:58         ` Rusty Russell
2013-05-30  5:55         ` Michael S. Tsirkin
2013-05-30  7:55         ` Michael S. Tsirkin
2013-06-03  0:17           ` Rusty Russell
2013-05-30 13:53         ` Anthony Liguori
2013-05-30 13:53           ` Anthony Liguori
2013-05-30 14:01           ` Michael S. Tsirkin
2013-06-03  0:26             ` Rusty Russell
2013-06-03 10:11               ` Michael S. Tsirkin
2013-06-04  5:31                 ` Rusty Russell
2013-06-04  6:42                   ` Michael S. Tsirkin
2013-06-05  7:19                     ` Rusty Russell
2013-06-05 10:22                       ` Michael S. Tsirkin
2013-06-05 12:59                     ` Anthony Liguori
2013-06-05 14:09                       ` Michael S. Tsirkin
2013-06-05 15:08                         ` Anthony Liguori
2013-06-05 15:19                           ` Michael S. Tsirkin
2013-06-05 15:46                             ` Anthony Liguori
2013-06-05 15:46                             ` Anthony Liguori
2013-06-05 16:20                               ` Michael S. Tsirkin
2013-06-05 18:57                                 ` Anthony Liguori
2013-06-05 19:43                                   ` Michael S. Tsirkin
2013-06-05 19:52                                     ` Michael S. Tsirkin
2013-06-05 20:45                                       ` Anthony Liguori
2013-06-05 21:15                                         ` H. Peter Anvin
2013-06-05 21:15                                         ` Michael S. Tsirkin
2013-06-05 20:42                                     ` Anthony Liguori
2013-06-05 21:14                                       ` Michael S. Tsirkin
2013-06-05 21:53                                         ` Anthony Liguori
2013-06-05 21:53                                         ` Anthony Liguori [this message]
2013-06-05 22:19                                           ` Benjamin Herrenschmidt
2013-06-05 22:53                                             ` Anthony Liguori
2013-06-05 23:27                                               ` Benjamin Herrenschmidt
2013-06-05 19:54                                   ` Michael S. Tsirkin
2013-06-06  3:42                                   ` Rusty Russell
2013-06-06 14:59                                     ` Anthony Liguori
2013-06-07  1:58                                       ` Rusty Russell
2013-06-07  8:25                                       ` Peter Maydell
2013-06-05 21:10                                 ` H. Peter Anvin
2013-06-05 21:17                                   ` Michael S. Tsirkin
2013-06-05 21:50                                   ` Anthony Liguori
2013-06-05 21:55                                     ` H. Peter Anvin
2013-06-05 22:08                                       ` Anthony Liguori
2013-06-05 23:07                                         ` H. Peter Anvin
2013-06-06  0:41                                           ` Anthony Liguori
2013-06-06  6:34                                             ` Gleb Natapov
2013-06-06 13:53                                               ` H. Peter Anvin
2013-06-06 15:02                                               ` Anthony Liguori
2013-06-06 15:02                                               ` Anthony Liguori
2013-06-07 11:30                                                 ` Gleb Natapov
2013-06-11  7:10                                                 ` Michael S. Tsirkin
2013-06-11  7:53                                                   ` Gleb Natapov
2013-06-11  8:02                                                     ` Michael S. Tsirkin
2013-06-11  8:03                                                       ` Gleb Natapov
2013-06-11  8:19                                                         ` Michael S. Tsirkin
2013-06-11  8:22                                                           ` Gleb Natapov
2013-06-11  8:30                                                             ` Michael S. Tsirkin
2013-06-11  8:32                                                               ` Gleb Natapov
2013-06-11  8:04                                                       ` Michael S. Tsirkin
2013-06-06 15:06                                               ` Gerd Hoffmann
2013-06-06 15:10                                                 ` Gleb Natapov
2013-06-06 15:19                                                   ` H. Peter Anvin
2013-06-06 15:22                                                   ` Gerd Hoffmann
2013-07-08  4:25                                                   ` Kevin O'Connor
2013-06-06  8:02                   ` Michael S. Tsirkin
2013-05-28 17:15 ` Anthony Liguori

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=87d2s0mdh8.fsf@codemonkey.ws \
    --to=aliguori@us.ibm.com \
    --cc=benh@kernel.crashing.org \
    --cc=fred.konrad@greensocs.com \
    --cc=gleb@redhat.com \
    --cc=kvm@vger.kernel.org \
    --cc=mst@redhat.com \
    --cc=pbonzini@redhat.com \
    --cc=peter.maydell@linaro.org \
    --cc=rusty@rustcorp.com.au \
    --cc=stefanha@redhat.com \
    --cc=virtualization@lists.linux-foundation.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.