On Sat, Sep 27, 2008 at 02:28:03PM +0800, Han, Weidong wrote:
From f2f722515135d95016f2d2ab55cc2aaf23d2fd80 Mon Sep 17 00:00:00 2001
From: Weidong Han [EMAIL PROTECTED]
Date: Sat, 27 Sep 2008 14:28:07 +0800
Subject: [PATCH] Support multiple device assignment to one guest
Current VT-d
On Sat, Sep 27, 2008 at 01:16:22PM +0300, Avi Kivity wrote:
Using MSI works around the issue nicely, since interrupts are no
longer shared. I imagine SR-IOV also fixes the issue.
SR-IOV mandates the use of either MSI or MSI-X for VFs.
Cheers,
Muli
--
The First Workshop on I/O Virtualization
On Sat, Sep 27, 2008 at 01:24:31PM +0300, Avi Kivity wrote:
I strongly disagree. You are advocating something that is
potentially unsafe---for the sake of code simplicity?! I am
advocating caution in what we let an *untrusted* guest do.
Why would it be unsafe?
Because on at least one
On Wednesday 24 September 2008 17:51:24 Avi Kivity wrote:
Yang, Sheng wrote:
2. shared guest pci interrupts
That's a correctness issue. No matter how many interrupts we have, we
may have sharing issues. Of course with only three the issue is very
pressing since we will get sharing
Muli Ben-Yehuda wrote:
On Sat, Sep 27, 2008 at 02:28:03PM +0800, Han, Weidong wrote:
From f2f722515135d95016f2d2ab55cc2aaf23d2fd80 Mon Sep 17 00:00:00
2001
From: Weidong Han [EMAIL PROTECTED]
Date: Sat, 27 Sep 2008 14:28:07 +0800
Subject: [PATCH] Support multiple device assignment to one
* On Saturday 27 Sep 2008 13:27:46 Thomas Fjellstrom wrote:
On Saturday 27 September 2008, Han, Weidong wrote:
Thomas Fjellstrom wrote:
On Saturday 27 September 2008, Han, Weidong wrote:
Hi Thomas,
the patches of passthrough/VT-d on kvm.git are already checked in.
With Amit's
* On Sunday 28 Sep 2008 10:09:13 Avi Kivity wrote:
Jan C. Bernauer wrote:
Hi,
I have about the same problem, so excuse me for hijacking this thread.
My hardware consists of a 780g/SB700 Mainboard and a 4850e AMD CPU, and
I'm interested in forwarding a DVB-C tuner card to the guest.
[EMAIL PROTECTED] wrote:
LINT0 of the LAPIC can be used to route PIT events as NMI watchdog ticks
into the guest. This patch aligns the in-kernel irqchip emulation with
the user space irqchip with already supports this feature. The trick is
to route PIT interrupts to all LAPIC's LVT0 lines.
[EMAIL PROTECTED] wrote:
Version 4 of this series includes the following fixes:
- Handle NMI task gates (Gleb Natapov)
- Clear internal NMI states on VCPU reset (Gleb Natapov)
- Typo fixes and minor cleanups (Sheng Yang and /me)
Hope we are now reaching a mergable state.
Looks very
Avi Kivity wrote:
[EMAIL PROTECTED] wrote:
Version 4 of this series includes the following fixes:
- Handle NMI task gates (Gleb Natapov)
- Clear internal NMI states on VCPU reset (Gleb Natapov)
- Typo fixes and minor cleanups (Sheng Yang and /me)
Hope we are now reaching a mergable
Avi Kivity wrote:
[EMAIL PROTECTED] wrote:
LINT0 of the LAPIC can be used to route PIT events as NMI watchdog ticks
into the guest. This patch aligns the in-kernel irqchip emulation with
the user space irqchip with already supports this feature. The trick is
to route PIT interrupts to all
On Sun, Sep 28, 2008 at 12:45:38PM +0300, Avi Kivity wrote:
[EMAIL PROTECTED] wrote:
Version 4 of this series includes the following fixes:
- Handle NMI task gates (Gleb Natapov)
- Clear internal NMI states on VCPU reset (Gleb Natapov)
- Typo fixes and minor cleanups (Sheng Yang and /me)
On Fri, Sep 26, 2008 at 09:30:47AM +0200, [EMAIL PROTECTED] wrote:
Properly set GUEST_INTR_STATE_NMI and reset nmi_injected when a
task-switch vmexit happened due to a task gate being used for handling
NMIs. Also avoid the false warning about valid vectoring info in
kvm_handle_exit.
Based
On Fri, Sep 26, 2008 at 09:30:48AM +0200, [EMAIL PROTECTED] wrote:
CPU reset invalidates pending or already injected NMIs, therefore reset
the related state variables.
Based on original patch by Gleb Natapov.
Signed-off-by: Gleb Natapov [EMAIL PROTECTED]
Signed-off-by: Jan Kiszka [EMAIL
Hi list,
some month ago, I submitted this issue:
http://www.mail-archive.com/[EMAIL PROTECTED]/msg16688.html
Recently, I solved the problem, here's how :
The backtrace of the generated core dump showed the following :
Program terminated with signal 11, Segmentation fault.
[New process
On Sun, Sep 28, 2008 at 02:43:26PM +0800, Han, Weidong wrote:
For pvdma, why each BDF will need its own domain for intra-guest
protection?
Because if more than one BDF shares an address space, BDFa will be
able to DMA to BDFb's buffers, and vice versa. The point of
intra-guest (not
On Sun, Sep 28, 2008 at 02:34:19PM +0800, Han, Weidong wrote:
I don't understand why this approach reduces IOTLB utility. How to
say unrelated devices with unrelated buffers competing for the same
resource? Multiple devices shares one page table should improve
IOTLB utility, because some
On Mon, 22 Sep 2008 20:21:21 +0200
Joerg Roedel [EMAIL PROTECTED] wrote:
This patch enables stackable dma_ops on x86. To do this, it also enables
the per-device dma_ops on i386.
Signed-off-by: Joerg Roedel [EMAIL PROTECTED]
---
arch/x86/kernel/pci-dma.c | 26
On Mon, 22 Sep 2008 20:21:12 +0200
Joerg Roedel [EMAIL PROTECTED] wrote:
Hi,
this patch series implements stackable dma_ops on x86. This is useful to
be able to fall back to a different dma_ops implementation if one can
not handle a particular device (as necessary for example with
The default for .slot is 0, which is wrong for all other kvm-slots.
This fixes enabling/disabling kvm dirty page logging.
Signed-off-by: Uri Lublin [EMAIL PROTECTED]
---
libkvm/libkvm.c |1 +
1 files changed, 1 insertions(+), 0 deletions(-)
diff --git a/libkvm/libkvm.c b/libkvm/libkvm.c
Instead of just printing an error message.
Signed-off-by: Uri Lublin [EMAIL PROTECTED]
---
qemu/vl.c |2 ++
1 files changed, 2 insertions(+), 0 deletions(-)
diff --git a/qemu/vl.c b/qemu/vl.c
index b34a114..9a4a4ec 100644
--- a/qemu/vl.c
+++ b/qemu/vl.c
@@ -7117,6 +7117,8 @@ int
Similar to include/asm.
Otherwise, if already exists, the new symlink is created under the old linked
directory.
Signed-off-by: Uri Lublin [EMAIL PROTECTED]
---
kernel/Makefile |2 +-
1 files changed, 1 insertions(+), 1 deletions(-)
diff --git a/kernel/Makefile b/kernel/Makefile
index
Uri Lublin wrote:
Instead of just printing an error message.
Applied, thanks.
--
error compiling committee.c: too many arguments to function
--
To unsubscribe from this list: send the line unsubscribe kvm in
the body of a message to [EMAIL PROTECTED]
More majordomo info at
Uri Lublin wrote:
Similar to include/asm.
Otherwise, if already exists, the new symlink is created under the old linked
directory.
Applied, thanks.
--
error compiling committee.c: too many arguments to function
--
To unsubscribe from this list: send the line unsubscribe kvm in
the body of
Alex Williamson wrote:
I guess the SSDT support was prior to the last merge, and appropriately
dropped. The most interesting new feature is a boot menu to allow the
user to override the boot device. That seems pretty useful. Other
things like better printing of the devices and support for
From: Mohammed Gamal [EMAIL PROTECTED]
This adds the std and cld instructions to the emulator.
Encountered while running the BIOS with invalid guest
state emulation enabled.
Signed-off-by: Mohammed Gamal [EMAIL PROTECTED]
Signed-off-by: Avi Kivity [EMAIL PROTECTED]
---
Here is the third and last batch of the KVM updates for the 2.6.28 merge window.
Linux 2.6.28 KVM will introduce support for pci device assignment and will
improve overall emulation accuracy.
Amit Shah (1):
KVM: Device Assignment: Free device structures if IRQ allocation
fails
Avi Kivity
From: Xiantao Zhang [EMAIL PROTECTED]
Two ioctl arch functions are added to set vcpu's smp state.
Signed-off-by: Xiantao Zhang [EMAIL PROTECTED]
Signed-off-by: Avi Kivity [EMAIL PROTECTED]
---
arch/ia64/kvm/kvm-ia64.c | 37 +++--
1 files changed, 35
From: Sheng Yang [EMAIL PROTECTED]
EPT is 4 level by default in 32pae(48 bits), but the addr parameter
of kvm_shadow_walk-entry() only accept unsigned long as virtual
address, which is 32bit in 32pae. This result in SHADOW_PT_INDEX()
overflow when try to fetch level 4 index.
Fix it by extend
From: Avi Kivity [EMAIL PROTECTED]
These can help show whether a guest is making progress or not.
Signed-off-by: Avi Kivity [EMAIL PROTECTED]
---
arch/x86/kvm/svm.c |1 +
arch/x86/kvm/vmx.c |1 +
arch/x86/kvm/x86.c |1 +
include/asm-x86/kvm_host.h |1 +
4
From: Marcelo Tosatti [EMAIL PROTECTED]
Offline or uninitialized vcpu's can be executed if requested to perform
userspace work.
Follow Avi's suggestion to handle halted vcpu's in the main loop,
simplifying kvm_emulate_halt(). Introduce a new vcpu-requests bit to
indicate events that promote
From: Mohammed Gamal [EMAIL PROTECTED]
Add call near absolute instruction.
Signed-off-by: Mohammed Gamal [EMAIL PROTECTED]
Signed-off-by: Avi Kivity [EMAIL PROTECTED]
---
arch/x86/kvm/x86_emulate.c | 11 ++-
1 files changed, 10 insertions(+), 1 deletions(-)
diff --git
From: Hollis Blanchard [EMAIL PROTECTED]
And it gets in the way of get_user_pages_fast().
Signed-off-by: Hollis Blanchard [EMAIL PROTECTED]
Signed-off-by: Avi Kivity [EMAIL PROTECTED]
---
arch/powerpc/kvm/44x_tlb.c |8 +---
1 files changed, 1 insertions(+), 7 deletions(-)
diff --git
From: Jan Kiszka [EMAIL PROTECTED]
Commit 1c0f4f5011829dac96347b5f84ba37c2252e1e08 left a useless access
of VM_ENTRY_INTR_INFO_FIELD in vmx_intr_assist behind. Clean this up.
Signed-off-by: Jan Kiszka [EMAIL PROTECTED]
Signed-off-by: Avi Kivity [EMAIL PROTECTED]
---
arch/x86/kvm/vmx.c |3
From: Sheng Yang [EMAIL PROTECTED]
For MSR_IA32_FEATURE_CONTROL is already there.
Signed-off-by: Sheng Yang [EMAIL PROTECTED]
Signed-off-by: Avi Kivity [EMAIL PROTECTED]
---
arch/x86/kvm/vmx.h |3 ---
include/asm-x86/msr-index.h |3 +++
2 files changed, 3 insertions(+), 3
From: Marcelo Tosatti [EMAIL PROTECTED]
Since KVM: x86: do not execute halted vcpus, HLT by vcpu0 before system
reset by the IO thread will hang the guest.
Mark vcpu as runnable in such case.
Signed-off-by: Marcelo Tosatti [EMAIL PROTECTED]
Signed-off-by: Avi Kivity [EMAIL PROTECTED]
---
From: Sheng Yang [EMAIL PROTECTED]
Signed-off-by: Sheng Yang [EMAIL PROTECTED]
Signed-off-by: Avi Kivity [EMAIL PROTECTED]
---
arch/x86/kvm/vmx.c | 18 +-
arch/x86/kvm/vmx.h |4 ++--
2 files changed, 11 insertions(+), 11 deletions(-)
diff --git a/arch/x86/kvm/vmx.c
From: Amit Shah [EMAIL PROTECTED]
When an IRQ allocation fails, we free up the device structures and
disable the device so that we can unregister the device in the
userspace and not expose it to the guest at all.
Signed-off-by: Amit Shah [EMAIL PROTECTED]
Signed-off-by: Avi Kivity [EMAIL
From: Marcelo Tosatti [EMAIL PROTECTED]
kvm_vm_fault is invoked with mmap_sem held in read mode. Since gfn_to_page
will be converted to get_user_pages_fast, which requires this lock NOT
to be held, switch to opencoded get_user_pages.
Signed-off-by: Marcelo Tosatti [EMAIL PROTECTED]
From: Harvey Harrison [EMAIL PROTECTED]
Noticed by sparse:
arch/x86/kvm/x86.c:3591:5: warning: symbol 'kvm_load_realmode_segment' was not
declared. Should it be static?
Signed-off-by: Harvey Harrison [EMAIL PROTECTED]
Signed-off-by: Avi Kivity [EMAIL PROTECTED]
---
arch/x86/kvm/x86.c |2 +-
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
From: Guillaume Thouvenin [EMAIL PROTECTED]
Add decode entries for these opcodes; execution is already implemented.
Signed-off-by: Guillaume Thouvenin [EMAIL PROTECTED]
Signed-off-by: Avi Kivity [EMAIL PROTECTED]
---
arch/x86/kvm/x86_emulate.c |3 ++-
1 files changed, 2 insertions(+), 1
From: Guillaume Thouvenin [EMAIL PROTECTED]
Add DstAcc operand type. That means that there are 4 bits now for
DstMask.
In the good old days cpus would have only one register that was able to
fully participate in arithmetic operations, typically called A for
Accumulator. The x86 retains this
From: Guillaume Thouvenin [EMAIL PROTECTED]
For instruction 'and al,imm' we use DstAcc instead of doing
the emulation directly into the instruction's opcode.
Signed-off-by: Guillaume Thouvenin [EMAIL PROTECTED]
Signed-off-by: Avi Kivity [EMAIL PROTECTED]
---
arch/x86/kvm/x86_emulate.c | 21
From: Ben-Ami Yassour [EMAIL PROTECTED]
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.
[Amit: Expose
From: Joerg Roedel [EMAIL PROTECTED]
Signed-off-by: Joerg Roedel [EMAIL PROTECTED]
Signed-off-by: Avi Kivity [EMAIL PROTECTED]
---
MAINTAINERS |7 +++
1 files changed, 7 insertions(+), 0 deletions(-)
diff --git a/MAINTAINERS b/MAINTAINERS
index cad81a2..232ff4a 100644
--- a/MAINTAINERS
On Sun, Sep 28, 2008 at 11:21:23PM +0900, FUJITA Tomonori wrote:
+struct dma_mapping_ops *find_dma_ops_for_device(struct device *dev)
+{
+ int i;
+ unsigned long flags;
+ struct dma_mapping_ops *entry, *ops = NULL;
+
+ read_lock_irqsave(dma_ops_list_lock, flags);
+
+
On Sun, Sep 28, 2008 at 11:21:26PM +0900, FUJITA Tomonori wrote:
On Mon, 22 Sep 2008 20:21:12 +0200
Joerg Roedel [EMAIL PROTECTED] wrote:
Hi,
this patch series implements stackable dma_ops on x86. This is useful to
be able to fall back to a different dma_ops implementation if one can
A fairly significant release. First the caveat:
kvm-76 userspace will not work with the kvm modules supplied by Linux
2.6.24 or below. Note that you can still use the external module
provided by this release (or earlier ones) with Linux 2.6.16 and above,
so this should not affect normal
On Sat, Sep 27, 2008 at 03:13:21AM +0300, Muli Ben-Yehuda wrote:
On Fri, Sep 26, 2008 at 02:32:43PM +0200, Joerg Roedel wrote:
Ok, the allocation only matters for dma_alloc_coherent. Fujita
introduced a generic software-based dma_alloc_coherent recently
which you can use for that. I think
Hi Everyone,
I just downloaded and ran the new kvm-76 (upgrading from kvm-74) and I
have a few issues.
I am running Ubuntu 8.04 (Hardy) as my host and Windows XP as my guest.
I am using VT-d and the kernel modules loaded correctly.
Here is the command I use to start kvm:
kvm-bridge -hda
Bugs item #2063072, was opened at 2008-08-21 06:29
Message generated for change (Comment added) made by okinu
You can respond by visiting:
https://sourceforge.net/tracker/?func=detailatid=893831aid=2063072group_id=180599
Please note that this message will contain a full copy of the comment
Bugs item #2135076, was opened at 2008-09-29 11:02
Message generated for change (Tracker Item Submitted) made by Item Submitter
You can respond by visiting:
https://sourceforge.net/tracker/?func=detailatid=893831aid=2135076group_id=180599
Please note that this message will contain a full copy of
I am running a custom compiled 2.6.24 kernel on a 64-bit Intel system and had
no issues compling and running kvm-75.
I downloaded kvm-76 and compiled and installed it, but I cannot get the modules
to load properly.
I have temporarily gone back to kvm-75.
I am seeing this output in dmesg:
From c7e6b365ce145caead0355b87e873c3180a47c5b Mon Sep 17 00:00:00 2001
From: Zhang xiantao [EMAIL PROTECTED]
Date: Thu, 11 Sep 2008 13:19:32 +0800
Subject: [PATCH] kvm/vt-d: Moving vtd.c from arch/x86/kvm/ to virt/kvm/
Preparation for kvm/ia64 VT-d support.
Signed-off-by: Zhang xiantao [EMAIL
From 6840c86b777e4a561cc3df7222cf5eb0b0bb9226 Mon Sep 17 00:00:00 2001
From: Xiantao Zhang [EMAIL PROTECTED]
Date: Sat, 27 Sep 2008 10:59:36 +0800
Subject: [PATCH] kvm: Moving device_assignment logic to kvm_main.c
To share with other archs, this patch moves device_assignment
logic to common
From 3211cc7a86ba050114733f847361478ab25619d7 Mon Sep 17 00:00:00 2001
From: Xiantao Zhang [EMAIL PROTECTED]
Date: Sat, 27 Sep 2008 10:55:40 +0800
Subject: [PATCH] kvm: Changing is_mmio_pfn to kvm_is_mmio_pfn, and make
it common
for all archs.
Using kvm prefix to aovid polluting kernel's name
From bb0c01b997d16ff1c1b9b0e797a581577c385b54 Mon Sep 17 00:00:00 2001
From: Xiantao Zhang [EMAIL PROTECTED]
Date: Mon, 29 Sep 2008 10:59:30 +0800
Subject: [PATCH] kvm: Split arch/x86/kvm/irq.c to two parts.
Moving irq ack notification logic as common, and make
it shared with ia64 side.
From 458f35267872176ed470fd6c5156ccc874ce1dfe Mon Sep 17 00:00:00 2001
From: Xiantao Zhang [EMAIL PROTECTED]
Date: Sat, 27 Sep 2008 11:46:36 +0800
Subject: [PATCH] kvm: Moving irqchip_in_kernel from ioapic.h to irq.h
Moving irqchip_in_kernel from ioapic.h to irq.h.
Signed-off-by: Xiantao Zhang
If the vt-d patchset is picked up, please apply this patch to
userspace.git for external module support.
From 36c21b2cb81077b176c7447ccc77ce2823c79af5 Mon Sep 17 00:00:00 2001
From: Xiantao Zhang [EMAIL PROTECTED]
Date: Mon, 29 Sep 2008 11:54:31 +0800
Subject: [PATCH] kvm: External module:
60 matches
Mail list logo