On Tuesday 15 July 2008 18:55:37 Avi Kivity wrote:
Yang, Sheng wrote:
On Tuesday 15 July 2008 02:36:36 Joerg Roedel wrote:
If NPT is enabled after loading both KVM modules on AMD and it
should be disabled, both KVM modules must be reloaded. If only
the architecture module is reloaded the
From c4a2cad8b91ac4c0b04a5ccd1f0bfab1d7e6ef37 Mon Sep 17 00:00:00 2001
From: Sheng Yang [EMAIL PROTECTED]
Date: Wed, 16 Jul 2008 09:21:22 +0800
Subject: [PATCH] KVM: VMX: Fix bypass_guest_pf enabling when disable
EPT in module parameter
Signed-off-by: Sheng Yang [EMAIL PROTECTED]
---
From bcbe1b5c4c6098f122accba4f00f6617baf807f7 Mon Sep 17 00:00:00 2001
From: Sheng Yang [EMAIL PROTECTED]
Date: Wed, 16 Jul 2008 09:25:40 +0800
Subject: [PATCH] KVM: VMX: Fix undefined beaviour of EPT after reload
kvm-intel.ko
As well as move set base/mask ptes to vmx_init().
Signed-off-by:
The following series adds support for qemu's audio configure option lists
that were added in kvm-71 to support selecting which interface will be used
to enable audio in the host from the guest (oss, alsa, sdl, esd, fmod, or
pulseaudio) and which audio devices emulation to enable for the guest
Extending the cleanup logic used in a patch from Jindrich Makovicka,
changes the default option to pass the full option to qemu's
configure and add a passthrough for qemu options that use a space
separated list of options like the list for audio drivers enabled
or the list for audio devices
Avi Kivity wrote:
Zhang, Xiantao wrote:
From 03ac444d1ab4446c587e8180ceaba60b9e75b28d Mon Sep 17 00:00:00
2001 From: Xiantao Zhang [EMAIL PROTECTED]
Date: Fri, 11 Jul 2008 10:13:08 +0800
Subject: [PATCH] KVM: external module: Moving x86-speicif files to
x86 directory.
Create x86
Avi Kivity wrote:
Alexander Graf wrote:
Avi Kivity wrote:
Alexander Graf wrote:
Netware writes and reads to the DEBUGCTL and LAST*IP MSRs without
further checks and is really confused to receive a #GP during that.
To make it happy we should just make them stubs, which is exactly
what SVM
somehow missing from sysemu.h after a qemu merge and otherwise complaining
with the following warning :
kvm-71/qemu/migration.c: In function 'migration_init_ssh':
kvm-71/qemu/migration.c:629: warning: implicit declaration of function
'qemu_get_launch_info'
Signed-off-by: Carlo Marcelo
added by mistake as part of 4820cce75999b2673a964eb87601229a4bd78ad9
Signed-off-by: Carlo Marcelo Arenas Belon [EMAIL PROTECTED]
---
qemu/qemu-kvm.h |2 --
1 files changed, 0 insertions(+), 2 deletions(-)
diff --git a/qemu/qemu-kvm.h b/qemu/qemu-kvm.h
index 8b7dcde..7e28428 100644
---
* Yang, Sheng [EMAIL PROTECTED] [2008-07-16 11:26]:
Hi Martin, can you show more dmesg here?
It doesn't contain any other messages from kvm. If you still want it,
let me know.
And if it can be reproduce stable?
I can reproduce this 100%.
Anyway, I just tried 2.6.26 with FlexPriority
In last few tests that we made with PCI-passthrough and VT-d using
iperf, we were able to get the same throughput as on native OS with a 1G
NIC (with higher CPU utilization).
The following patches are the PCI-passthrough patches that Amit sent
(re-based on the last kvm tree), followed by a few
Signed-off-by: Ben-Ami Yassour [EMAIL PROTECTED]
---
arch/x86/kvm/x86.c |2 +-
1 files changed, 1 insertions(+), 1 deletions(-)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 8d25b4a..65b307d 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -343,9 +343,9 @@ static void
This patch fixes a few problems with the interrupt handling for
passthrough devices.
1. Pass the interrupt handler the pointer to the device, so we do not
need to lock the pcipt lock in the interrupt handler.
2. Remove the pt_irq_handled bitmap - it is no longer needed.
3. Split
This patch includes the functions to support VT-d for passthrough
devices.
[Ben: fixed memory pinning, cleanup]
Signed-off-by: Kay, Allen M [EMAIL PROTECTED]
Signed-off-by: Weidong Han [EMAIL PROTECTED]
Signed-off-by: Ben-Ami Yassour [EMAIL PROTECTED]
---
arch/x86/kvm/Makefile |2 +-
Avoid mapping mmio memory slots.
Signed-off-by: Ben-Ami Yassour [EMAIL PROTECTED]
---
arch/x86/kvm/vtd.c | 20 +---
include/asm-x86/kvm_host.h |2 ++
virt/kvm/kvm_main.c|2 +-
3 files changed, 16 insertions(+), 8 deletions(-)
diff --git
From: Kay, Allen M [EMAIL PROTECTED]
This patch extends the VT-d driver to support KVM
[Ben: fixed memory pinning]
Signed-off-by: Kay, Allen M [EMAIL PROTECTED]
Signed-off-by: Weidong Han [EMAIL PROTECTED]
Signed-off-by: Ben-Ami Yassour [EMAIL PROTECTED]
---
drivers/pci/dmar.c
From: Amit Shah [EMAIL PROTECTED]
This will be useful for acking irqs of assigned devices
Signed-off-by: Amit Shah [EMAIL PROTECTED]
---
virt/kvm/ioapic.c |3 +++
virt/kvm/ioapic.h |1 +
2 files changed, 4 insertions(+), 0 deletions(-)
diff --git a/virt/kvm/ioapic.c b/virt/kvm/ioapic.c
Yang, Sheng wrote:
On Tuesday 15 July 2008 23:19:07 Dor Laor wrote:
Martin Michlmayr wrote:
I installed a Windows XP SP2 guest on a Debian x86_64 host The
installation itself went fine but kvm aborts when when XP starts
during Windows XP Setup. XP mentions something with
intelppm.sys
paolo pedaletti wrote:
Hi,
I hope this is the right ml to submit my problem.
Abstract: I can't setup 2 different network inside my VMs, one public
and one private.
Scheme:
eth0 -
-| proxy |---eth1
|- |
H| |
O| eth0 - |
Bugs item #2019053, was opened at 2008-07-16 03:10
Message generated for change (Comment added) made by avik
You can respond by visiting:
https://sourceforge.net/tracker/?func=detailatid=893831aid=2019053group_id=180599
Please note that this message will contain a full copy of the comment
When a timer fires, posix_timer_event() zeroes out its
pre-allocated siginfo structure, initialises it and then
queues up the signal with send_sigqueue().
However, we may have previously queued up this signal, in
which case we only want to increment si_overrun and
re-initialising the siginfo
Ben-Ami Yassour wrote:
This patch fixes a few problems with the interrupt handling for
passthrough devices.
Well, fold it into the patch it fixes. There is no point in sending a
buggy patch and a fix in the same patchset.
--
error compiling committee.c: too many arguments to function
Ben-Ami Yassour wrote:
From: Han, Weidong [EMAIL PROTECTED]
This patch adds support for handling PCI devices that are assigned to
the guest (PCI passthrough).
+
+/*
+ * Used to find a registered host PCI device (a passthrough device)
+ * during ioctls, interrupts or EOI
+ */
+struct
Bugs item #2019053, was opened at 2008-07-15 18:10
Message generated for change (Comment added) made by alex_williamson
You can respond by visiting:
https://sourceforge.net/tracker/?func=detailatid=893831aid=2019053group_id=180599
Please note that this message will contain a full copy of the
On Wed, 2008-07-16 at 17:36 +0300, Avi Kivity wrote:
Ben-Ami Yassour wrote:
In last few tests that we made with PCI-passthrough and VT-d using
iperf, we were able to get the same throughput as on native OS with a 1G
NIC
Excellent!
(with higher CPU utilization).
How much
Ben-Ami Yassour wrote:
(with higher CPU utilization).
How much higher?
Here are some numbers for running iperf -l 1M:
e1000 NIC (behind a PCI bridge)
Bandwidth (Mbit/sec)CPU utilization
Native OS 771 18%
Native
Ben-Ami Yassour wrote:
On Wed, 2008-07-16 at 17:36 +0300, Avi Kivity wrote:
Ben-Ami Yassour wrote:
In last few tests that we made with PCI-passthrough and VT-d using
iperf, we were able to get the same throughput as on native OS with a 1G
NIC
Excellent!
(with higher CPU
This is an update patch for libkvm to build and work on s390.
It should address all comments from Avi as well as some aspects I have found:
o implement kvm_show_regs
o use s390 instead of s390x in file names. It is commonly used for 31 and
64bit systems
o dont define __s390__ and __s390x__ in
On Wed, 2008-07-16 at 15:50 +0100, Mark McLoughlin wrote:
The race was observed with a modified kvm-userspace when
running a guest under heavy network load. When it occurs,
KVM never sees another SIGALRM signal because although
the signal is queued up the appropriate bit is never set
in the
From: Amit Shah [EMAIL PROTECTED]
This patch adds support for handling PCI devices that are assigned to
the guest (PCI passthrough).
The device to be assigned to the guest is registered in the host kernel
and interrupt delivery is handled. If a device is already assigned, or
the device driver
From: Amit Shah [EMAIL PROTECTED]
This patch adds support for handling PCI devices that are assigned to
the guest (PCI passthrough).
The device to be assigned to the guest is registered in the host kernel
and interrupt delivery is handled. If a device is already assigned, or
the device driver
Please ignore this repeated patch
--
To unsubscribe from this list: send the line unsubscribe kvm in
the body of a message to [EMAIL PROTECTED]
More majordomo info at http://vger.kernel.org/majordomo-info.html
Ben-Ami Yassour wrote:
That CPU utilization is extremely high and somewhat illogical if native
w/vt-d has almost no CPU impact. Have you run oprofile yet or have any
insight into where CPU is being burnt?
What does kvm_stat look like? I wonder if there are a large number of
PIO exits.
hi there
i was using kvm-70 and kernel 2.6.25 on debian lenny for two weeks
without problems. processor is an AMD Opteron 2350. now out of
the nowwhere there is a problem with 1 of 4 guests (1x debian etch amd64,
1x debian etch i386, 1x ubuntu 7.10 amd64, 1x ubuntu 7.10 i386)
On the host i
On a suggestion of Anthony's, I tried a defconfig kernel.
It is now bombing out on an assertion in the lapic code:
http://sr71.net/~dave/linux/2.6.26-oops1.txt
-- Dave
--
To unsubscribe from this list: send the line unsubscribe kvm in
the body of a message to [EMAIL PROTECTED]
More
As the comment in the diff mentions, VMX does not accept any bit in
the range 11:0 of ES,CS,FS,GS,SS segment registers limit field to
be zero with the granulity bit set to one.
So clear granularity and adjust the limit accordingly.
Signed-off-by: Marcelo Tosatti [EMAIL PROTECTED]
Index:
On Wed, 2008-07-16 at 14:44 -0700, Dave Hansen wrote:
On a suggestion of Anthony's, I tried a defconfig kernel.
It is now bombing out on an assertion in the lapic code:
http://sr71.net/~dave/linux/2.6.26-oops1.txt
I think I found it!!!
$ (objdump -d kvm.ko ; objdump -d kvm-intel.ko
paolo pedaletti wrote:
Hi,
I hope this is the right ml to submit my problem.
Abstract: I can't setup 2 different network inside my VMs, one public
and one private.
Scheme:
eth0 -
-| proxy |---eth1
|- |
H| |
O| eth0 - |
* Uri Lublin [EMAIL PROTECTED] [2008-07-16 18:15]:
Client side, for installation, we already have a solution that works for
all types of guests:
http://kvm.qumranet.com/kvmwiki/KVMTest
which is already integrated as a client test in autotest. Once you
record your installation via
Some comments below. :)
On Wednesday 16 July 2008 23:56:50 Ben-Ami Yassour wrote:
From: Amit Shah [EMAIL PROTECTED]
This patch adds support for handling PCI devices that are assigned
to the guest (PCI passthrough).
The device to be assigned to the guest is registered in the host
kernel and
Avi Kivity wrote:
+static void kvm_pci_pt_work_fn(struct work_struct *work) +{
+struct kvm_pci_pt_dev_list *match;
+struct kvm_pci_pt_work *int_work;
+int source;
+unsigned long flags;
+int guest_irq;
+int host_irq;
+
+int_work = container_of(work, struct
Anthony Liguori wrote:
Ben-Ami Yassour wrote:
On Wed, 2008-07-16 at 17:36 +0300, Avi Kivity wrote:
Ben-Ami Yassour wrote:
In last few tests that we made with PCI-passthrough and VT-d using
iperf, we were able to get the same throughput as on native OS
with a 1G NIC
Excellent!
Dave Hansen wrote:
On a suggestion of Anthony's, I tried a defconfig kernel.
It is now bombing out on an assertion in the lapic code:
http://sr71.net/~dave/linux/2.6.26-oops1.txt
Well that assert is plain wrong:
static int apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic
Dave Hansen wrote:
On Wed, 2008-07-16 at 14:44 -0700, Dave Hansen wrote:
On a suggestion of Anthony's, I tried a defconfig kernel.
It is now bombing out on an assertion in the lapic code:
http://sr71.net/~dave/linux/2.6.26-oops1.txt
I think I found it!!!
$ (objdump -d
44 matches
Mail list logo