The following two patches contain VT-d support for device assignment
for KVM guests.
The first patch contains the changes that are required to the generic
VT-d code.
The second patch contains the changes to KVM.
I've updated the 2nd patch to use VT-d only when requested by a parameter
on the co
Based on a patch by: Kay, Allen M <[EMAIL PROTECTED]>
This patch enables PCI device assignment based on VT-d support.
When a device is assigned to the guest, the guest memory is pinned and
the mapping is updated in the VT-d IOMMU.
Signed-off-by: Kay, Allen M <[EMAIL PROTECTED]>
Signed-off-by: Wei
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]>
Signed-off-by: Amit Shah <[EMAIL
* On Thursday 21 Aug 2008 16:35:57 Ben-Ami Yassour wrote:
> On Thu, 2008-08-21 at 12:13 +0530, Amit Shah wrote:
> > * On Thursday 07 Aug 2008 19:44:47 Ben-Ami Yassour wrote:
> > > Based on a patch by: Kay, Allen M <[EMAIL PROTECTED]>
> > >
> > > This patch enables pci device assignment based on VT-
Hello everybody,
we're running cluster of two hosts with tens (~45 running) of kvms,
and now I noticed that some nodes are loosing link under heavy load.
following appears in dmesg:
[ 422.077128] NETDEV WATCHDOG: eth0: transmit timed out
[ 422.077215] eth0: Transmit timeout, status d 2b5
On Fri, Aug 22, 2008 at 05:54:53AM +, Max Krasnyansky wrote:
> While trying to make VX-3000 camera work on XP under KVM I realized that
> we do not necessarily have to find original TD address. All we care about
> is the token which identifies the transfer rather well (direction, endpoint,
> si
Hi, Avi
Please help to apply this patch. It will fix kvm/ia64's networking
issue.
Thanks
Xiantao
>From fe6e28ce9295acba107438979fe6ead0d24f7e20 Mon Sep 17 00:00:00 2001
From: Xiantao Zhang <[EMAIL PROTECTED]>
Date: Fri, 22 Aug 2008 17:14:15 +0800
Subject: [PATCH] KVM: Qemu: Enable kvm/ia64's ne
On Fri, Aug 22, 2008 at 05:54:31AM +, Max Krasnyansky wrote:
> Fixes regression reported agains Linux 2.6.18.
> Looks like XP and newer Linux kernels are less sensitive
> to length returned for control transfers.
>
> Signed-off-by: Max Krasnyansky <[EMAIL PROTECTED]>
Applied, thanks.
> ---
>
Bugs item #2067179, was opened at 2008-08-22 12:25
Message generated for change (Tracker Item Submitted) made by Item Submitter
You can respond by visiting:
https://sourceforge.net/tracker/?func=detail&atid=893831&aid=2067179&group_id=180599
Please note that this message will contain a full copy
Avi Kivity wrote:
> The big change is of course full swapping support, finally delivering
> the full range of Linux memory management operations to kvm. You will
> need a 2.6.27 host to use this functionality, however.
>
> Other noteworthy changes: speedups of both virtio-net and qcow2 with
> cac
On Fri, 22 Aug 2008, Amit Shah wrote:
The following two patches contain VT-d support for device assignment
for KVM guests.
The first patch contains the changes that are required to the generic
VT-d code.
The second patch contains the changes to KVM.
I've updated the 2nd patch to use VT-d only
* On Friday 22 Aug 2008 19:24:13 Byron Stanoszek wrote:
> On Fri, 22 Aug 2008, Amit Shah wrote:
> > The following two patches contain VT-d support for device assignment
> > for KVM guests.
> >
> > The first patch contains the changes that are required to the generic
> > VT-d code.
> >
> > The secon
On Fri, Aug 22, 2008 at 09:54:13AM -0400, Byron Stanoszek wrote:
> Is it possible to log any physical PCI accesses from the guest?
> This could be handy for reverse-engineering device drivers, among
> other things.
With PCI passthrough It is possible in theory to log mmio's and pio's
executed by
This patchset introduces a generic shadow walker. We currently walk shadow
pagetables in two places: direct maps and paging mode maps. Since we're
about to introduce a third walk (invlpg), we ought to have a generic
facility for walking shadows.
The first two patches are fixes/cleanups and are i
The two paths are equivalent except for one argument, which is already
available. Merge the two codepaths.
Signed-off-by: Avi Kivity <[EMAIL PROTECTED]>
---
arch/x86/kvm/mmu.c | 11 +++
1 files changed, 3 insertions(+), 8 deletions(-)
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu
The shadow code assigns a pte directly in one place, which is nonatomic on
i386 can can cause random memory references. Fix by using an atomic setter.
Signed-off-by: Avi Kivity <[EMAIL PROTECTED]>
---
arch/x86/kvm/paging_tmpl.h |2 +-
1 files changed, 1 insertions(+), 1 deletions(-)
diff --
We currently walk the shadow page tables in two places: direct map (for
real mode and two dimensional paging) and paging mode shadow. Since we
anticipate requiring a third walk (for invlpg), it makes sense to have
a generic facility for shadow walk.
This patch adds such a shadow walker, walks the
Signed-off-by: Avi Kivity <[EMAIL PROTECTED]>
---
arch/x86/kvm/mmu.c | 94 +++-
1 files changed, 56 insertions(+), 38 deletions(-)
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 17da753..682dbf8 100644
--- a/arch/x86/kvm/mmu.c
+++ b/ar
Signed-off-by: Avi Kivity <[EMAIL PROTECTED]>
---
arch/x86/kvm/paging_tmpl.h | 158
1 files changed, 86 insertions(+), 72 deletions(-)
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index ebb26a0..b7064e1 100644
--- a/arch/x86/kv
The current curses code doesn't set the initial monitor text console to the size
of the terminal and fails to adjust properly after a resize. The attach patches
create the initial console based on the size of the terminal instead of
defaulting to 80x25, and also hook ensure that text_console_resi
The current console output is broken in curses mode size the default starting
size might not match the launching terminal size. Change initial size to be
based on the terminal. Also, resize events fail to ensure that both the text
console and curses display areas are the same size; this causes br
Signed-off-by: Ryan Harper <[EMAIL PROTECTED]>
diff --git a/console.c b/console.c
index 89bdc52..c7a5a80 100644
--- a/console.c
+++ b/console.c
@@ -172,7 +172,7 @@ void vga_hw_screen_dump(const char *filename)
previous_active_console = active_console;
active_console = consoles[0];
/
Muli Ben-Yehuda wrote:
> With PCI passthrough It is possible in theory to log mmio's and pio's
> executed by the guest, as well as interrupts delivered to the guest,
> although it will have a performance impact. It is not possible to log
> DMAs in a simple manner, but you could hook up a PCI analyz
Farkas Levente wrote:
> what is the current recommended way to build kernel module for kvm?
> until now it was a simple
> make KDIR=...
> in the linux dir, but it's no longer working. first of all now is
> required to run configure for kernel module too, second the above make
> now get into an infi
Nikola Ciprich wrote:
> Hello everybody,
> we're running cluster of two hosts with tens (~45 running) of kvms,
> and now I noticed that some nodes are loosing link under heavy load.
>
> following appears in dmesg:
> [ 422.077128] NETDEV WATCHDOG: eth0: transmit timed out
> [ 422.077215] eth0: Tr
Amit Shah wrote:
> diff --git a/include/linux/kvm.h b/include/linux/kvm.h
> index d9ef7d3..2956e35 100644
> --- a/include/linux/kvm.h
> +++ b/include/linux/kvm.h
> @@ -495,4 +495,6 @@ struct kvm_assigned_irq {
> __u32 flags;
> };
>
> +#define KVM_DEV_ASSIGN_USE_VTD (1 << 1)
> +
> #endif
>
Amit Shah wrote:
> The following two patches contain VT-d support for device assignment
> for KVM guests.
>
> The first patch contains the changes that are required to the generic
> VT-d code.
>
> The second patch contains the changes to KVM.
>
> I've updated the 2nd patch to use VT-d only when req
On Fri, Aug 22, 2008 at 09:12:32PM +0300, Avi Kivity wrote:
> Muli Ben-Yehuda wrote:
> > With PCI passthrough It is possible in theory to log mmio's and pio's
> > executed by the guest, as well as interrupts delivered to the guest,
> > although it will have a performance impact. It is not possible
On Fri, Aug 22, 2008 at 09:21:15PM +0300, Avi Kivity wrote:
> You mean, iommu=on.
Agreed. This should also be the default if not dma=xxx is specfied and
a capable IOMMU is found.
> Or rather
>
> dma=iommu
> dma=none (1:1 mapping, or dma-less devices, or I'm Feeling Lucky)
> dma=cooperativ
On Fri, Aug 22, 2008 at 09:02:33PM +0530, Amit Shah wrote:
> All the PCI accesses happen from the userspace components in qemu;
> it's certainly possible to log activity.
Actually, with direct-mmio we bypass QEMU and get a nice boost in
performance, and it should be possible to bypass QEMU for (m
Muli Ben-Yehuda wrote:
> On Fri, Aug 22, 2008 at 09:02:33PM +0530, Amit Shah wrote:
>
>
>> All the PCI accesses happen from the userspace components in qemu;
>> it's certainly possible to log activity.
>>
>
> Actually, with direct-mmio we bypass QEMU and get a nice boost in
> performance, a
On Fri, Aug 22, 2008 at 09:37:16PM +0300, Avi Kivity wrote:
> > Actually, with direct-mmio we bypass QEMU and get a nice boost in
> > performance, and it should be possible to bypass QEMU for (most)
> > PIO's too.
>
> Since there is no pio remapping, there's no way to ensure there's a
> free pio
Hi,
I have been playing with KVM and was wondering about the following question:
is there a resource configuration setting that would enforce a fraction of
CPU to be guaranteed for a KVM guest? What I have on mind is something
similar to the "reservation" setting on VMware (used to be called
Avi Kivity wrote:
> Nikola Ciprich wrote:
>> Hello everybody,
>> we're running cluster of two hosts with tens (~45 running) of kvms,
>> and now I noticed that some nodes are loosing link under heavy load.
>>
>> following appears in dmesg:
>> [ 422.077128] NETDEV WATCHDOG: eth0: transmit timed out
2008/8/22 Ryan Harper <[EMAIL PROTECTED]>:
> The current console output is broken in curses mode size the default starting
> size might not match the launching terminal size. Change initial size to be
> based on the terminal. Also, resize events fail to ensure that both the text
> console and cur
* andrzej zaborowski <[EMAIL PROTECTED]> [2008-08-22 17:40]:
> 2008/8/22 Ryan Harper <[EMAIL PROTECTED]>:
> > The current console output is broken in curses mode size the default
> > starting
> > size might not match the launching terminal size. Change initial size to be
> > based on the terminal
fork'ing inside qemu can create stale shadow entries without mmu
notifiers.
--
--
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
When qemu fork's (ssh migration, qemu-nbd, slirp), the guest memory
mapping becomes shared and write-protected by parent and child, until
execve switches to a new mm.
Since kernel commit 7885a4fbebcbae1f8594445a46aefb9d97353594,
get_user_pages with force=1 parameter will break COW during this wind
From: Anthony Liguori <[EMAIL PROTECTED]>
This patch adds a kvm_has_sync_mmu routine to libkvm. This allows
userspace to query the existence of mmu notifiers which is important for
ballooning since madvise() is not safe from userspace without it.
Signed-off-by: Anthony Liguori <[EMAIL PROTECTED]
>From 2c14c54eed790553fddbcb3970f0967a4aa79dca Mon Sep 17 00:00:00 2001
From: Xiantao Zhang <[EMAIL PROTECTED]>
Date: Sat, 23 Aug 2008 10:21:06 +0800
Subject: [PATCH] KVM: kvm/ia64: select ANON_INODES PREEMPT_NOTIFIERS,
once
virtualization configured.
Once virtulization configured, make PREEMPT_NO
40 matches
Mail list logo