From mboxrd@z Thu Jan  1 00:00:00 1970
Received: from eggs.gnu.org ([2001:4830:134:3::10]:41694)
	by lists.gnu.org with esmtp (Exim 4.71)
	(envelope-from <alex.nlnnfn@gmail.com>) id 1afVtZ-0002aV-5f
	for qemu-devel@nongnu.org; Mon, 14 Mar 2016 13:03:05 -0400
Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71)
	(envelope-from <alex.nlnnfn@gmail.com>) id 1afVtW-0006Fg-04
	for qemu-devel@nongnu.org; Mon, 14 Mar 2016 13:03:05 -0400
Received: from mail-wm0-x22f.google.com ([2a00:1450:400c:c09::22f]:35487)
	by eggs.gnu.org with esmtp (Exim 4.71)
	(envelope-from <alex.nlnnfn@gmail.com>) id 1afVtV-0006F1-OQ
	for qemu-devel@nongnu.org; Mon, 14 Mar 2016 13:03:01 -0400
Received: by mail-wm0-x22f.google.com with SMTP id l68so117371043wml.0
	for <qemu-devel@nongnu.org>; Mon, 14 Mar 2016 10:03:01 -0700 (PDT)
Received: from comet (46-116-250-113.bb.netvision.net.il. [46.116.250.113])
	by smtp.gmail.com with ESMTPSA id
	u14sm16925099wmu.8.2016.03.14.10.03.00 for <qemu-devel@nongnu.org>
	(version=TLSv1/SSLv3 cipher=OTHER);
	Mon, 14 Mar 2016 10:03:00 -0700 (PDT)
Date: Mon, 14 Mar 2016 19:02:57 +0200
From: alexnln <alex.nlnnfn@gmail.com>
Message-Id: <20160314190257.de92aaddb8dce2f3bb1eda61@gmail.com>
Mime-Version: 1.0
Content-Type: text/plain; charset=US-ASCII
Content-Transfer-Encoding: 7bit
Subject: [Qemu-devel] e1000 emulation and mmio_exists counter
List-Id: <qemu-devel.nongnu.org>
List-Unsubscribe: <https://lists.nongnu.org/mailman/options/qemu-devel>,
	<mailto:qemu-devel-request@nongnu.org?subject=unsubscribe>
List-Archive: <http://lists.nongnu.org/archive/html/qemu-devel>
List-Post: <mailto:qemu-devel@nongnu.org>
List-Help: <mailto:qemu-devel-request@nongnu.org?subject=help>
List-Subscribe: <https://lists.nongnu.org/mailman/listinfo/qemu-devel>,
	<mailto:qemu-devel-request@nongnu.org?subject=subscribe>
To: qemu-devel@nongnu.org

Hi list,

I am testing e1000 emulation with qemu 2.5. Command line:
-netdev tap,fd=21,id=hostnet0 \
-device e1000,netdev=hostnet0,id=net0,mac=$MAC1,bus=pci.0,addr=0x4

AFAIU, e1000 is emulated in qemu (userspace) and each i/o should cause 
vmexit to userspace. And each exit to userspace should increment 
mmio_exits counter (/sys/kernel/debug/kvm/mmio_exits).

As I see in kvm code, 
kvm_mmu_page_fault() in arch/x86/kvm/mmu.c, case for EMULATE_USER_EXIT.
http://lxr.free-electrons.com/source/arch/x86/kvm/mmu.c#L4391

However, when I run load I see that mmio_exits counter is almost constant.
What am I missing here?

Thank you