similar to: [PATCH] xen-netfront: Avoid unaligned accesses to IP header.

Align ip header to a 16 byte boundary. This patch eliminates noisy warnings on IA64. Signed-off-by: Isaku Yamahata <yamahata at valinux.co.jp> --- drivers/net/xen-netfront.c | 5 ++++- 1 files changed, 4 insertions(+), 1 deletions(-) diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index 44aed80..2724688 100644 --- a/drivers/net/xen-netfront.c +++

Hi all, When I run the iperf benchmark to measure the TCP throughput between a physical machine and a VM, the TCP server which is a Xen VM crashed. Do you know what''s the problem of this bug? Thanks. [ 100.973027] BUG: unable to handle kernel NULL pointer dereference at 0000000000000008 [ 100.973040] IP: [<ffffffff81455f16>] xennet_alloc_rx_buffers+0x166/0x350 [ 100.973050] PGD

use set_xen_guest_handle() instead of direct assigning. > linux-2.6/drivers/xen/events.c: In function 'xen_poll_irq': > linux-2.6/drivers/xen/events.c:757: error: incompatible types in assignment > make[4]: *** [drivers/xen/events.o] Error 1 Signed-off-by: Isaku Yamahata <yamahata at valinux.co.jp> --- drivers/xen/events.c | 2 +- 1 files changed, 1 insertions(+), 1

wrap load_cr3() in manage.c by xen_pre_device_suspend() because it is x86 dependent. Signed-off-by: Isaku Yamahata <yamahata at valinux.co.jp> --- arch/x86/xen/suspend.c | 5 +++++ drivers/xen/manage.c | 3 +-- include/xen/xen-ops.h | 1 + 3 files changed, 7 insertions(+), 2 deletions(-) diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c index 2a234db..ac139a2 100644

This patch fixes compilation error on ia64. include asm/xen/hypervisor.h instead of asm-x86/xen/hypervisor.h use xen_pv_domain() instead of is_running_on_xen() > CC drivers/xen/cpu_hotplug.o > In file included from /linux-2.6/drivers/xen/cpu_hotplug.c:5: > /linux-2.6/include/asm-x86/xen/hypervisor.h:44:22: error: asm/desc.h: No such file or directory >

clean up of xencomm.c. is_phys_contiguous() is arch dependent function that depends on how virtual memory are laid out. So split out the function into arch specific code. Signed-off-by: Isaku Yamahata <yamahata at valinux.co.jp> Cc: "Luck, Tony" <tony.luck at intel.com> --- drivers/xen/xencomm.c | 23 ++++------------------- 1 files changed, 4 insertions(+), 19

>From 6dd3a58c8a9fa25d56aa258eda70871710951da0 Mon Sep 17 00:00:00 2001 From: Isaku Yamahata <yamahata@valinux.co.jp> Date: Mon, 25 Aug 2008 14:27:49 +0900 Subject: [PATCH] fix cross compilation. When cross compile, INSTALL is set to cross-install by --install configure option. However it is overwritten by including $(XEN_ROOT)/tools/Rules.mk so that install command fails to strip as

use set_xen_guest_handle() instead of direct assigning. > linux-2.6/drivers/xen/events.c: In function 'xen_poll_irq': > linux-2.6/drivers/xen/events.c:757: error: incompatible types in assignment > make[4]: *** [drivers/xen/events.o] Error 1 Signed-off-by: Isaku Yamahata <yamahata at valinux.co.jp> --- drivers/xen/events.c | 2 +- 1 files changed, 1 insertions(+), 1

use set_xen_guest_handle() instead of direct assigning. > linux-2.6/drivers/xen/events.c: In function 'xen_poll_irq': > linux-2.6/drivers/xen/events.c:757: error: incompatible types in assignment > make[4]: *** [drivers/xen/events.o] Error 1 Signed-off-by: Isaku Yamahata <yamahata at valinux.co.jp> --- drivers/xen/events.c | 2 +- 1 files changed, 1 insertions(+), 1

This patch fixes compilation error on ia64. include asm/xen/hypervisor.h instead of asm-x86/xen/hypervisor.h use xen_pv_domain() instead of is_running_on_xen() > CC drivers/xen/cpu_hotplug.o > In file included from /linux-2.6/drivers/xen/cpu_hotplug.c:5: > /linux-2.6/include/asm-x86/xen/hypervisor.h:44:22: error: asm/desc.h: No such file or directory >

This patch fixes compilation error on ia64. include asm/xen/hypervisor.h instead of asm-x86/xen/hypervisor.h use xen_pv_domain() instead of is_running_on_xen() > CC drivers/xen/cpu_hotplug.o > In file included from /linux-2.6/drivers/xen/cpu_hotplug.c:5: > /linux-2.6/include/asm-x86/xen/hypervisor.h:44:22: error: asm/desc.h: No such file or directory >

This patch adds a new feature called feature-split-event-channels for netfront, enabling it to handle TX and RX events separately. If netback does not support this feature, it falls back to use single event channel. Signed-off-by: Wei Liu <wei.liu2@citrix.com> Reviewed-by: David Vrabel <david.vrabel@citrix.com> --- drivers/net/xen-netfront.c | 173

This function is in fact counting the ring slots required for responses. Separate the concepts of ring slots and skb frags make the code clearer, as now netfront and netback can have different MAX_SKB_FRAGS, slot and frag are not mapped 1:1 any more. Signed-off-by: Wei Liu <wei.liu2@citrix.com> Reviewed-by: David Vrabel <david.vrabel@citrix.com> --- drivers/net/xen-netfront.c | 18

Signed-off-by: Ian Campbell <ian.campbell@citrix.com> Cc: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: xen-devel@lists.xensource.com Cc: netdev@vger.kernel.org --- drivers/net/xen-netfront.c | 34 +++++++++++++++++++--------------- 1 files changed, 19 insertions(+), 15 deletions(-) diff --git

This patchset is ia64/xen domU patch take 10 which is rebased to 2.6.27-rc4. This patchset implements ia64/xen domU support based on ia64/pv_ops frame work which was sent as another patchest. This patchset does the followings. - Some preparation work. Mainly importing header files to define related structures. - Then, define functions related to hypercall which is the way to communicate with

This patchset is ia64/xen domU patch take 10 which is rebased to 2.6.27-rc4. This patchset implements ia64/xen domU support based on ia64/pv_ops frame work which was sent as another patchest. This patchset does the followings. - Some preparation work. Mainly importing header files to define related structures. - Then, define functions related to hypercall which is the way to communicate with

> It appears that when alloc''ing a skb, it is bring padded by > an arbitrarily > (and excessive) long value. The value for this padding > really only needs to > be 24. 24 = 14 for the ethernet header + 2 for the cache > alignment + 4 for > the CRC + 4 for the VLAN flags. Given that we''re allocating page sized buffers the current situation

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 +

There would seem to be a potential deadlock in the netfront accelerator plugin support. When the configured accelerator changes in xenstore, netfront tries to load the new plugin using request_module(). It does this from a workqueue work item. request_module() will invoke modprobe which in some circumstances (I''m not sure exactly what - I''ve not managed to reproduce it myself)

In netfront, the current driver reserves pools of grant refs for the tx and rx paths, each big enough to satisfy one virtual nic. With more than one nic active you will run out. Both the tx and rx path will BUG() when you do. This patch creates separate tx and rx ref pools for each interface. Signed-off-by: Jim Dykman <dykman@us.ibm.com> Jim