similar to: xennet: skb rides the rocket: 20 slots

When counting required slots for skb, netback directly uses DIV_ROUND_UP to get slots required by header data. This is wrong when offset in the page of header data is not zero, and is also inconsistent with following calculation for required slot in netbk_gop_skb. In netbk_gop_skb, required slots are calculated based on offset and len in page of header data. It is possible that required slots

When counting required slots for skb, netback directly uses DIV_ROUND_UP to get slots required by header data. This is wrong when offset in the page of header data is not zero, and is also inconsistent with following calculation for required slot in netbk_gop_skb. In netbk_gop_skb, required slots are calculated based on offset and len in page of header data. It is possible that required slots

On Wed, Jan 11, 2012 at 04:52:36PM +0800, Zhenzhong Duan wrote: > add polling interface to xen-netfront device to support netconsole > Ian, any thoughts on the spinlock changes? > Signed-off-by: Tina.Yang <tina.yang@oracle.com> > Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> > Cc: Jeremy Fitzhardinge <jeremy@goop.org> > Signed-off-by: Zhenzhong.Duan

Hi, I ran into an issue where netback driver is crashing with BUG_ON(npo.meta_prod > ARRAY_SIZE(netbk->meta)). It is happening in Intel 10Gbps network when larger mtu values are used. The problem seems to be the way the slots are counted. After applying this patch things ran fine in my environment. I request to validate my changes. Thanks Siva

This dependence is undesirable and logically incorrect. It''s undesirable because Xen network protocol should not depend on a OS-specific constant. It''s incorrect because the ring slots required doesn''t correspond to the number of frags a SKB has (consider compound page frags). This patch removes this dependence by correctly counting the ring slots required.

From: Julia Lawall <julia at diku.dk> The kernel.h macro DIV_ROUND_UP performs the computation (((n) + (d) - 1) / (d)) but is perhaps more readable. An extract of the semantic patch that makes this change is as follows: (http://www.emn.fr/x-info/coccinelle/) // <smpl> @haskernel@ @@ #include <linux/kernel.h> @depends on haskernel@ expression n,d; @@ ( - (n + d - 1) / d +

Hello, I installed the signed drivers from http://wiki.univention.de/index.php?title=Installing-signed-GPLPV-drivers and I ran into a BSOD on a Windows 2008 Server R2 Enterprise domU with a large number of vcpu''s. The BSOD is related to xennet.sys. After some trials I found that it runs fine up to 15 cores. From 16 or more, the BSOD kicks in when booting the domU. The hardware (4 times

I have installed the 210 gplpv (debug), when I try to update them with current gplpv I get a BSOD even so when I try to uninstall them. Now I have made a bootentry that specifies NOGPLPV, what gives me a bootable system after such a crash, I found (uninstalling the leftover driver packages after getting bsod during uninstall of the main package) that uninstalling the net driver leads to bsod. Now

Hi all, when I try to build an initial ramdisk with the option --with=xennet, I get the following error No module xennet found for kernel 2.6.18.8-xen I looked at the /lib/modules/2.6.18.8-xen/kernel/drivers/xen and there is no xennet module over there, which causes the problem. How can I get the xennet module? Thanks, Luca _______________________________________________ Xen-users

I''m going to set up a PVM on xen-3.3.1 debian-amd64. I need advices about the best methods to install a fresh debian on it (i.e. how to choose the kernel for pvm) . I''ve installed xen from sources and only have one xen kernel in /boot which I''m using for dom0; should I use the same kernel for domUs? There is any problem on use vcpus=2; the other vm is an hvm running

If I try to ifup eth0, I get the following: Device eth0 does not seem to be present, delaying initialization. DomU: Linux fedora1 2.6.16-1.2133_FC5xenU #1 SMP Tue Jun 6 02:58:27 EDT 2006 i686 i686 i386 GNU/Linux config: kernel = "/boot/vmlinuz-2.6-xenU" #ramdisk="/boot/initrd-2.6.16-1.2133_FC5xenU.img" memory = 128 name = "fedora1" #dhcp = "dhcp" disk =

Dear List-Colleagues: I have been working on installing Xen on Suse 10.3 for some time now. I am green as grass - both a total newbie to Xen and a relative newbie to Linux (as well as a total newbie to SuSE). Currently, I am at the point that when I click on the Xen entry in my grub loader I see Xen starting and running through much of its early setup. Eventually, however, it quits on

Hi there. I have been dealing with a conundrum off and on with a VPS of mine. Windows 2003 Standard 32 bit on a Xen HVM instance. Been trying to get the GPLPV drivers working to help boost performance but always seem to run into one major issue: The PV network device looks like it works but actual connectivity is non-existant. Everything else in the GPLPV driver suite works fine. What I want to

I''m been busily converting the xenpci and xenvbd drivers from WDF to WDM to resolve a few issues including potential licensing problems with the Microsoft WDF and to (hopefully) allow them to function as boot drivers when doing install and system recovery. It was a fairly major rewrite of xenpci, and xenvbd, which are now working (booting and running without crashes so far). I

I''m been busily converting the xenpci and xenvbd drivers from WDF to WDM to resolve a few issues including potential licensing problems with the Microsoft WDF and to (hopefully) allow them to function as boot drivers when doing install and system recovery. It was a fairly major rewrite of xenpci, and xenvbd, which are now working (booting and running without crashes so far). I

Commit 2613af0ed18a ("virtio_net: migrate mergeable rx buffers to page frag allocators") changed the mergeable receive buffer size from PAGE_SIZE to MTU-size. However, the merge buffer size does not take into account the size of the virtio-net header. Consequently, packets that are MTU-size will take two buffers intead of one (to store the virtio-net header), substantially decreasing the

Commit 2613af0ed18a ("virtio_net: migrate mergeable rx buffers to page frag allocators") changed the mergeable receive buffer size from PAGE_SIZE to MTU-size. However, the merge buffer size does not take into account the size of the virtio-net header. Consequently, packets that are MTU-size will take two buffers intead of one (to store the virtio-net header), substantially decreasing the

Hello James, I am doing quite rigorous torture tests with Xen and GPLPV. Let me first repeat the test setup: Use Xen 4.1.1 and kernel 2.6.32.36 (commit ae333e9). Configure 2 HVMs called VM1 and VM2 as follows (per HVM): 2 VCPUs, 2 virtual disks, 1024 MB RAM, viridian=1 Install Windows 2008 R2 SP1, do install everything twice - never clone. Install GPLPV, iometer 2006.07.27, prime95 26.6 x64,

I''ve just uploaded a prerelease of 0.9.9 to http://www.meadowcourt.org/downloads/ Please read the following before using: It fixes a few disk related bugs... I''ve just been testing it on a Windows Small Business Server 2003 R2 I have just restored from tape into a DomU from a backup of a physical system and it''s working fine - 0.9.8 BSOD''d almost immediately

I''ve just uploaded a prerelease of 0.9.9 to http://www.meadowcourt.org/downloads/ Please read the following before using: It fixes a few disk related bugs... I''ve just been testing it on a Windows Small Business Server 2003 R2 I have just restored from tape into a DomU from a backup of a physical system and it''s working fine - 0.9.8 BSOD''d almost immediately