From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:32981) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1bFAZw-0008C6-G2 for qemu-devel@nongnu.org; Mon, 20 Jun 2016 21:34:13 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1bFAZr-0006Xd-HD for qemu-devel@nongnu.org; Mon, 20 Jun 2016 21:34:11 -0400 Received: from mga09.intel.com ([134.134.136.24]:6974) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1bFAZr-0006XZ-B4 for qemu-devel@nongnu.org; Mon, 20 Jun 2016 21:34:07 -0400 Date: Tue, 21 Jun 2016 09:23:08 +0800 From: Chao Peng Message-ID: <20160621012308.GH21465@pengc-linux.bj.intel.com> Reply-To: Chao Peng References: <1466151257-96318-1-git-send-email-chao.p.peng@linux.intel.com> <20160620060129.GE21465@pengc-linux.bj.intel.com> <76b78e27-c14f-ebb5-baab-a0bf75a60a10@redhat.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <76b78e27-c14f-ebb5-baab-a0bf75a60a10@redhat.com> Subject: Re: [Qemu-devel] [RFC 0/9] Introduce light weight PC platform pc-lite List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Paolo Bonzini Cc: Haozhong Zhang , Xiao Guangrong , Eduardo Habkost , "Michael S. Tsirkin" , qemu-devel@nongnu.org, anthony.xu@intel.com, gor Mammedov , Richard Henderson > It would be nice to at least see the patches. :) > > I think a lightweight q35 platform that can run the usual firmware could > be acceptable in QEMU. OK, I will send out v2. > > >> 2) this: > >> > >>> - it loads guest kernel directly, no BIOS, no bootloader, no realmode > >>> code; > >> > >> ... which is related to Linux-only support. How much does this gain > >> over a minimal firmware (either SeaBIOS with the fw_cfg DMA interface, > >> or qboot with cbfs in parallel flash)? > > > > We have tried Q35 version (as described above) with both SeaBIOS and qboot. > > The 'perfect' time with optimized BIOS we have seen is ~15ms, with the > > additional time in kernel real mode code, the total time overhead comparing > > to current Linux-aware implementation is more than 40ms. This sounds still > > a little too much for us. > > I guess it is related to real mode decompression code? Yes, that's the major part. > > My main issue is that there are other things that the firmware does. > Not all of them are necessary (e.g. SMRAM is not needed, most PCI > devices need not be initialized), but in general we don't like putting > code in QEMU that modifies the guest state. For example another Intel > person is adding code to SeaBIOS that initializes the feature control MSR. > > I wonder if Linux could run as a multiboot-compliant ELF file, and what > the performance would be... Multiboot omits the real mode stub. > I can look into this. Thanks. Chao