From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([140.186.70.92]:46724) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1QnnIl-00027a-Li for qemu-devel@nongnu.org; Mon, 01 Aug 2011 03:52:40 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1QnnIk-0004N7-Hk for qemu-devel@nongnu.org; Mon, 01 Aug 2011 03:52:39 -0400 Received: from fmmailgate01.web.de ([217.72.192.221]:56593) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1QnnIk-0004N3-AL for qemu-devel@nongnu.org; Mon, 01 Aug 2011 03:52:38 -0400 Message-ID: <4E365B3A.7050701@web.de> Date: Mon, 01 Aug 2011 09:52:26 +0200 From: Jan Kiszka MIME-Version: 1.0 References: <1312141678-5141-1-git-send-email-avi@redhat.com> <4E365718.2060500@web.de> In-Reply-To: <4E365718.2060500@web.de> Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="------------enig2B2D78A97006DCF0AFB4DA8E" Sender: jan.kiszka@web.de Subject: Re: [Qemu-devel] [PATCH] memory: synchronize dirty bitmap before unmapping a range List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Avi Kivity Cc: qemu-devel@nongnu.org, kvm@vger.kernel.org This is an OpenPGP/MIME signed message (RFC 2440 and 3156) --------------enig2B2D78A97006DCF0AFB4DA8E Content-Type: text/plain; charset=ISO-8859-15 Content-Transfer-Encoding: quoted-printable On 2011-08-01 09:34, Jan Kiszka wrote: > On 2011-07-31 21:47, Avi Kivity wrote: >> When a range is being unmapped, ask accelerators (e.g. kvm) to synchro= nize the >> dirty bitmap to avoid losing information forever. >> >> Fixes grub2 screen update. >=20 > I does. >=20 > But something is still broken. As I reported before, the performance of= > grub2 startup is an order of magnitude slower than with the existing > code. According to ftrace, we are getting tons of additional > EPT_MISCONFIG exits over the 0xA0000 segment. But I haven't spot the > difference yet. The effective slot setup as communicated to kvm looks > innocent. I take it back: We obviously once in a while resume the guest with the vga segment unmapped. And that, of course, ends up doing mmio instead of plain ram accesses. Jan --------------enig2B2D78A97006DCF0AFB4DA8E Content-Type: application/pgp-signature; name="signature.asc" Content-Description: OpenPGP digital signature Content-Disposition: attachment; filename="signature.asc" -----BEGIN PGP SIGNATURE----- Version: GnuPG v2.0.16 (GNU/Linux) Comment: Using GnuPG with Mozilla - http://enigmail.mozdev.org/ iEYEARECAAYFAk42Wz0ACgkQitSsb3rl5xQ+xQCfYPDXLmvNFnEdJXLmiygTlyiH U/kAoNqJhdKF4BhHnLwiQNZ7sawjzAnL =OJAF -----END PGP SIGNATURE----- --------------enig2B2D78A97006DCF0AFB4DA8E--