From: Glauber Costa [EMAIL PROTECTED]
Callers of int 0x13 usually rely on the carry flag being
clear/set to indicate the status of the interrupt execution.
However, our current code clear or set the flags register,
which is totally useless. Whichever value it has, will
be overwritten by the
If an assigned device shares a guest irq with an emulated
device then we currently interpret an ack generated by the
emulated device as originating from the assigned device
leading to e.g. Unbalanced enable for IRQ 4347 from the
enable_irq() in kvm_assigned_dev_ack_irq().
The fix is fairly simple
Avi Kivity wrote:
- something did a read-modify-write cycle on cr4 (which contains the
svm enable bit) while kvm enabled that bit
Well, there are a couple of code paths that do this. I'll look into it.
--
error compiling committee.c: too many arguments to function
--
To unsubscribe from
Avi Kivity wrote:
Avi Kivity wrote:
- something did a read-modify-write cycle on cr4 (which contains the
svm enable bit) while kvm enabled that bit
Well, there are a couple of code paths that do this. I'll look into it.
Sorry, that's EFER. It could be something doing a read-modify-write
Daniel P. Berrange wrote:
On Tue, Dec 02, 2008 at 10:25:49AM +0800, Zhang, Yang wrote:
This patch to save the nvram. It save the nvram by specify the arg of
-name.And the saved file named by the arg. If do not specify the arg,
it will not save the nvram
I think we might be better off
This patch introduces the API to abstract the exported VT-d functions
for KVM into a generic API. This way the AMD IOMMU implementation can
plug into this API later.
Signed-off-by: Joerg Roedel [EMAIL PROTECTED]
---
include/linux/iommu.h | 109 +
Signed-off-by: Joerg Roedel [EMAIL PROTECTED]
---
drivers/base/iommu.c | 100 ++
1 files changed, 100 insertions(+), 0 deletions(-)
create mode 100644 drivers/base/iommu.c
diff --git a/drivers/base/iommu.c b/drivers/base/iommu.c
new file mode
Impace: file renamed
The code in the vtd.c file can be reused for other IOMMUs as well. So
rename it to make it clear that it handle more than VT-d.
Signed-off-by: Joerg Roedel [EMAIL PROTECTED]
---
arch/ia64/kvm/Makefile |2 +-
arch/x86/kvm/Makefile |2 +-
virt/kvm/{vtd.c =
On Tue, Dec 02, 2008 at 03:01:20PM +0200, Avi Kivity wrote:
Daniel P. Berrange wrote:
On Tue, Dec 02, 2008 at 10:25:49AM +0800, Zhang, Yang wrote:
This patch to save the nvram. It save the nvram by specify the arg of
-name.And the saved file named by the arg. If do not specify the arg,
Bugs item #2138166, was opened at 2008-09-30 15:39
Message generated for change (Comment added) made by technologov
You can respond by visiting:
https://sourceforge.net/tracker/?func=detailatid=893831aid=2138166group_id=180599
Please note that this message will contain a full copy of the comment
Bugs item #2138166, was opened at 2008-09-30 08:39
Message generated for change (Settings changed) made by johnrrousseau
You can respond by visiting:
https://sourceforge.net/tracker/?func=detailatid=893831aid=2138166group_id=180599
Please note that this message will contain a full copy of the
Bugs item #2353811, was opened at 2008-11-27 17:44
Message generated for change (Comment added) made by technologov
You can respond by visiting:
https://sourceforge.net/tracker/?func=detailatid=893831aid=2353811group_id=180599
Please note that this message will contain a full copy of the comment
Bugs item #2088475, was opened at 2008-09-02 11:37
Message generated for change (Comment added) made by technologov
You can respond by visiting:
https://sourceforge.net/tracker/?func=detailatid=893831aid=2088475group_id=180599
Please note that this message will contain a full copy of the comment
Linus, please pull some kvm fixes from repo and branch at:
git://git.kernel.org/pub/scm/linux/kernel/git/avi/kvm.git
kvm-updates/2.6.28
There are a couple of fixes for the out-of-sync mmu, a fix for a lost
irq while injecting an nmi (which causes guests with an nmi watchdog to
hang), as
Bugs item #2138166, was opened at 2008-09-30 15:39
Message generated for change (Comment added) made by technologov
You can respond by visiting:
https://sourceforge.net/tracker/?func=detailatid=893831aid=2138166group_id=180599
Please note that this message will contain a full copy of the comment
From: Weidong Han [EMAIL PROTECTED]
In order to support multiple device assignment for KVM, this patch does
following main changes:
- extend dmar_domain to own multiple devices from different iommus,
use a bitmap of iommus to replace iommu pointer in dmar_domain.
- implement independent low
Glauber Costa wrote:
Callers of int 0x13 usually rely on the carry flag being
clear/set to indicate the status of the interrupt execution.
However, our current code clear or set the flags register,
which is totally useless. Whichever value it has, will
be overwritten by the flags value _before_
Avi Kivity wrote:
Applied, thanks.
-.macro clc
-push %ax
-pushf
-pop %ax
-and $(~FLAGS_CF), %ax
-push %ax
-popf
-pop %ax
Anthony, any reason you did not use the 'clc' instruction instead of a
macro?
Propensity for pain?
I have no idea. I assume I had a
This patchset supports VT-d multiple device assignment for KVM.
Main changes from V2 to V3:
- change intel iommu APIs, which are consistent with Joerg's generic iommu APIs.
- split to a serial smaller patches for easy reviewing.
Regards,
Weidong--
To unsubscribe from this list: send the line
move page table handling utility functions from intel-iommu.c to
dma_remapping.h, because some of them will be used in other .c files.
Signed-off-by: Weidong Han [EMAIL PROTECTED]
---
drivers/pci/intel-iommu.c | 45
include/linux/dma_remapping.h |
Support dmar_domain own multiple devices from different iommus, which are set
in iommu bitmap. add function domain_get_iommu() to get the only one iommu of
domain in native VT-d usage.
Signed-off-by: Weidong Han [EMAIL PROTECTED]
---
drivers/pci/intel-iommu.c | 102
agaw may be different across iommus.
Signed-off-by: Weidong Han [EMAIL PROTECTED]
---
drivers/pci/dmar.c| 14 ++
include/linux/dma_remapping.h |2 ++
include/linux/intel-iommu.h |1 +
3 files changed, 17 insertions(+), 0 deletions(-)
diff --git
in dmar_domain, more than one iommus may be included in iommu_bmp. Due to
Coherency capability may be different across iommus, set this variable to
indicate iommu access is coherent or not. Only when all related iommus in a
dmar_domain are all coherent, iommu access of this domain is coherent.
By default, one domain owns one device, like native VT-d usage.
For kvm VT-d usage, more than one devices across iommus may be assigned to one
domain, flag DOMAIN_FLAG_VIRTUAL_MACHINE is for this usage.
Signed-off-by: Weidong Han [EMAIL PROTECTED]
---
drivers/pci/intel-iommu.c |3 ++-
Separate add/remove domain device info functions for virtual machine VT-d from
natvie VT-d.
Signed-off-by: Weidong Han [EMAIL PROTECTED]
---
drivers/pci/intel-iommu.c | 164 +++-
include/linux/dma_remapping.h |1 +
2 files changed, 160
For some common low level functions which will be also used by virtual machine
usage, use domain_flush_cache instead of __iommu_flush_cache.
Signed-off-by: Weidong Han [EMAIL PROTECTED]
---
drivers/pci/intel-iommu.c | 40
1 files changed, 24
Signed-off-by: Weidong Han [EMAIL PROTECTED]
---
drivers/pci/intel-iommu.c | 104 -
1 files changed, 103 insertions(+), 1 deletions(-)
diff --git a/drivers/pci/intel-iommu.c b/drivers/pci/intel-iommu.c
index b00a8f2..e96b3bc 100644
---
vm_domid won't be set in context, find available domain id for a device from
its iommu.
For a virtual machine domain, a default agaw will be set, and skip top levels
of page tables for iommu which has less agaw than default.
Signed-off-by: Weidong Han [EMAIL PROTECTED]
---
These APIs will be used by kvm VT-d. The domain used by these APIs is virtual
machine domain (domain flag is DOMAIN_FLAG_VIRTUAL_MACHINE).
Signed-off-by: Weidong Han [EMAIL PROTECTED]
---
drivers/pci/intel-iommu.c | 128 ---
include/linux/intel-iommu.h
Support device assignment, it can be used in device hotplug.
Signed-off-by: Weidong Han [EMAIL PROTECTED]
---
include/linux/kvm.h |5 +
include/linux/kvm_host.h |8
virt/kvm/kvm_main.c | 42 ++
virt/kvm/vtd.c |
intel iommu APIs are updated, use the new APIs.
In addition, change kvm_iommu_map_guest() to just create the domain, let
kvm_iommu_assign_device() assign device.
Signed-off-by: Weidong Han [EMAIL PROTECTED]
---
include/linux/kvm_host.h | 15 +--
virt/kvm/kvm_main.c |7 +++-
There is a race between a close of the file descriptors and module
unload in the kvm module.
You can easily trigger this problem by applying this debug patch:
--- kvm.orig/virt/kvm/kvm_main.c
+++ kvm/virt/kvm/kvm_main.c
@@ -648,10 +648,14 @@ void kvm_free_physmem(struct kvm *kvm)
The same guest did it again.
# uname -a
Linux spaceball 2.6.27.6 #1 SMP Fri Nov 14 11:51:10 CET 2008 i686 QEMU
Virtual CPU version 0.9.1 AuthenticAMD GNU/Linux
# date
Thu Dec 19 01:54:27 WET 1912
# uptime
01:54:29 up 14666 days, 21:17, 12 users, load average: 3.99, 3.97, 3.91
What can I do
Signed-off-by: Joerg Roedel [EMAIL PROTECTED]
---
drivers/pci/intel-iommu.c | 13 +
1 files changed, 13 insertions(+), 0 deletions(-)
diff --git a/drivers/pci/intel-iommu.c b/drivers/pci/intel-iommu.c
index 2e8b102..bb6f771 100644
--- a/drivers/pci/intel-iommu.c
+++
Signed-off-by: Joerg Roedel [EMAIL PROTECTED]
---
drivers/pci/intel-iommu.c | 15 ---
include/linux/intel-iommu.h |2 --
2 files changed, 8 insertions(+), 9 deletions(-)
diff --git a/drivers/pci/intel-iommu.c b/drivers/pci/intel-iommu.c
index ac22973..2e8b102 100644
---
Bugs item #2318236, was opened at 2008-11-20 13:41
Message generated for change (Comment added) made by ryandbair
You can respond by visiting:
https://sourceforge.net/tracker/?func=detailatid=893831aid=2318236group_id=180599
Please note that this message will contain a full copy of the comment
Mark McLoughlin wrote:
We will obviously never pass a NULL struct kvm_irq_ack_notifier* to
this functions. They are always embedded in the assigned device
structure, so the assertion add nothing.
The irqchip_in_kernel() assertion is very out of place - clearly
this little abstraction needs to
There is an imbalance for anonymous inodes. If the fops-owner field is set,
the module reference count of owner is decreases on release.
(filp_close -- __fput --- fops_put)
On the other hand, anon_inode_getfd does not increase the module reference
count of owner. This causes two problems:
-
Hello Avi,
here is the latest respin of my fixes for the kvm module unload problem:
[PATCH 1/2] anon_inodes: use fops-owner for module refcount
[PATCH 2/2] kvm: set owner of cpu and vm file operations
Both patches fix module reference counting problems and only matter for module
unload -
Signed-off-by: Joerg Roedel [EMAIL PROTECTED]
---
drivers/pci/intel-iommu.c | 22 +++---
include/linux/intel-iommu.h |4
2 files changed, 11 insertions(+), 15 deletions(-)
diff --git a/drivers/pci/intel-iommu.c b/drivers/pci/intel-iommu.c
index 62ae6b1..ac22973
Bugs item #2353510, was opened at 2008-11-27 14:46
Message generated for change (Comment added) made by technologov
You can respond by visiting:
https://sourceforge.net/tracker/?func=detailatid=893831aid=2353510group_id=180599
Please note that this message will contain a full copy of the comment
-Original Message-
From: Dor Laor [mailto:[EMAIL PROTECTED]
Sent: Monday, December 01, 2008 5:27 PM
To: Adrian Schmitz
Cc: kvm@vger.kernel.org; Avi Kivity
Subject: Re: STOP error with virtio on KVM-79/2.6.18/Win2k3 x64 guest
What driver version are you using? Version 2 is
Signed-off-by: Joerg Roedel [EMAIL PROTECTED]
---
arch/ia64/kvm/Makefile |2 +-
arch/x86/include/asm/kvm_host.h |3 +-
arch/x86/kvm/Makefile |2 +-
virt/kvm/iommu.c| 68 ---
virt/kvm/kvm_main.c |2
Bugs item #2088475, was opened at 2008-09-02 11:37
Message generated for change (Comment added) made by technologov
You can respond by visiting:
https://sourceforge.net/tracker/?func=detailatid=893831aid=2088475group_id=180599
Please note that this message will contain a full copy of the comment
These two IOMMUs can implement the current version of this API. So
select the API if one or both of these IOMMU drivers is selected.
Signed-off-by: Joerg Roedel [EMAIL PROTECTED]
---
arch/ia64/Kconfig |3 +++
arch/x86/Kconfig |3 +++
drivers/base/Makefile |1 +
3 files
It adds a missing KVM string in the signature of the CPUID. Without
it signature[2] is not well defined.
Signed-off-by: Guillaume Thouvenin [EMAIL PROTECTED]
---
qemu/qemu-kvm-x86.c |2 +-
1 files changed, 1 insertions(+), 1 deletions(-)
diff --git a/qemu/qemu-kvm-x86.c
Signed-off-by: Joerg Roedel [EMAIL PROTECTED]
---
drivers/pci/intel-iommu.c | 30 +-
include/linux/intel-iommu.h |2 --
2 files changed, 17 insertions(+), 15 deletions(-)
diff --git a/drivers/pci/intel-iommu.c b/drivers/pci/intel-iommu.c
index 7f12852..59b9cdb
On Tue, Dec 02, 2008 at 10:25:49AM +0800, Zhang, Yang wrote:
This patch to save the nvram. It save the nvram by specify the arg of
-name.And the saved file named by the arg. If do not specify the arg,
it will not save the nvram
I think we might be better off having an explicit command line
Anthony Liguori wrote:
1) On TX, we vmsplice() from the sg buffer to one pipe. This will end
up being vmsplice_to_pipe() in the kernel which is zero-copy.
That implies we do the MAC address switching in userspace (or that this
is a point-to-point protocol, which severely limits its
From: Weidong Han [EMAIL PROTECTED]
This patch changes to use new APIs for KVM VT-d, and add device
deassignment for hotplug.
[Joerg: coding style cleanups]
Signed-off-by: Weidong Han [EMAIL PROTECTED]
Signed-off-by: Joerg Roedel [EMAIL PROTECTED]
---
include/linux/kvm.h |5 ++
Signed-off-by: Hollis Blanchard [EMAIL PROTECTED]
---
qemu/hw/device_tree.c | 14 +++---
qemu/hw/device_tree.h | 12 ++--
2 files changed, 13 insertions(+), 13 deletions(-)
diff --git a/qemu/hw/device_tree.c b/qemu/hw/device_tree.c
index e73129d..2621ff1 100644
---
These patches fix the kvm-userspace qemu build after a recent merge with
upstream qemu.
I'm also seeing a build dependency issue with dyngen-opc.h that I don't see
upstream. I haven't sorted that out yet, but make
qemu/ppcemb-softmmu/dyngen-opc.h first works around the problem.
-Hollis
--
To
Signed-off-by: Hollis Blanchard [EMAIL PROTECTED]
---
qemu/hw/ppc440_bamboo.c | 37 +
1 files changed, 21 insertions(+), 16 deletions(-)
diff --git a/qemu/hw/ppc440_bamboo.c b/qemu/hw/ppc440_bamboo.c
index bf42245..79e4ea8 100644
---
Mark McLoughlin wrote:
Make sure kvm_request_irq_source_id() never returns
KVM_USERSPACE_IRQ_SOURCE_ID.
Likewise, check that kvm_free_irq_source_id() never accepts
KVM_USERSPACE_IRQ_SOURCE_ID.
An alternative way to do this is to drop the distinction
KVM_USERSPACE_IRQ_SOURCE_ID has, and
Luis Henriques wrote:
On Sun, Nov 30, 2008 at 10:44:55PM +0200, Avi Kivity wrote:
Luis Henriques wrote:
No, I was not able to reproduce the issue. Please let me know if you need some
more information on my system (.config, for instance).
Were you using some other
Hollis Blanchard wrote:
Well, it happens, but I do wish that more people would use cscope or
even grep to find all users of a symbol.
That's reasonable.
I also wish that Avi would get his PPC box working so he could catch
build breaks like these. Cross-compilers would do as well.
I
* Alan Cox ([EMAIL PROTECTED]) wrote:
+ r = !memcmp(old_digest, sha1_item-sha1val, SHA1_DIGEST_SIZE);
+ mutex_unlock(sha1_lock);
+ if (r) {
+ char *old_addr, *new_addr;
+ old_addr = kmap_atomic(oldpage, KM_USER0);
+ new_addr = kmap_atomic(newpage,
On Tue, 2 Dec 2008 10:07:24 -0800
Chris Wright [EMAIL PROTECTED] wrote:
* Alan Cox ([EMAIL PROTECTED]) wrote:
+ r = !memcmp(old_digest, sha1_item-sha1val, SHA1_DIGEST_SIZE);
+ mutex_unlock(sha1_lock);
+ if (r) {
+ char *old_addr, *new_addr;
+ old_addr =
I just spent a number of hours tracking this one down, and I'm not too
thrilled about it. vp_find_vq() does the memory allocation for virtio
PCI rings, and it uses kzalloc() to do it. This is bad because the ring
memory *must* be page-aligned.
According to Anthony, at the time this code was
On Tue, Dec 02, 2008 at 02:23:52PM +0200, Avi Kivity wrote:
Luis Henriques wrote:
On Sun, Nov 30, 2008 at 10:44:55PM +0200, Avi Kivity wrote:
Luis Henriques wrote:
No, I was not able to reproduce the issue. Please let me know if you need
some
more information on my system
Hollis Blanchard wrote:
Finally, we could use the interface intended for exactly this purpose:
the page allocator. If there's some problem with high memory, don't
allocate it with GFP_HIGHMEM.
Can you work up a patch to do this?
Regards,
Anthony Liguori
--
To unsubscribe from this list:
Luis Henriques wrote:
Ok, I am not sure but there is a possibility of having the vboxdrv driver
loaded. _But_ I was not using, i.e., I do not use VirtualBox. In my
attempts to reproduce the issue, I tried to load this module but, unfortunatly,
my distro has this package broken ATM (err... in
Luis Henriques wrote:
Ok, I am not sure but there is a possibility of having the vboxdrv driver
loaded. _But_ I was not using, i.e., I do not use VirtualBox. In my
attempts to reproduce the issue, I tried to load this module but, unfortunatly,
my distro has this package broken ATM (err... in
(I am CC'ing to Steven Rostedt since he might be interested on this)
On Tue, Dec 02, 2008 at 07:09:14PM +, Luis Henriques wrote:
On Tue, Dec 02, 2008 at 02:23:52PM +0200, Avi Kivity wrote:
Luis Henriques wrote:
On Sun, Nov 30, 2008 at 10:44:55PM +0200, Avi Kivity wrote:
Luis
[ added Ingo too ]
On Tue, 2008-12-02 at 19:46 +, Luis Henriques wrote:
(I am CC'ing to Steven Rostedt since he might be interested on this)
On Tue, Dec 02, 2008 at 07:09:14PM +, Luis Henriques wrote:
I have some other information to had to my previous email. However, I do not
Steven Rostedt wrote:
The following must be available without recursion for the function
tracer to work:
local_irq_save/restore
smp_processor_id
preempt_enable/disable_notrace
atomic_inc/dec
In arch/x86/kvm/svm.c, function svm_vcpu_run(), everything between the
vmrun instruction
On Tue, 2008-12-02 at 22:38 +0200, Avi Kivity wrote:
Steven Rostedt wrote:
The following must be available without recursion for the function
tracer to work:
local_irq_save/restore
smp_processor_id
preempt_enable/disable_notrace
atomic_inc/dec
In arch/x86/kvm/svm.c,
Steven Rostedt wrote:
In arch/x86/kvm/svm.c, function svm_vcpu_run(), everything between the
vmrun instruction and the call to load_host_msrs() is executed without a
live pda, so no smp_processor_id(). Could easily be fixed by
rearranging things.
That would be best, but if you have
On Tue, Dec 02, 2008 at 02:09:39PM +0200, Avi Kivity wrote:
xming wrote:
The same guest did it again.
# uname -a
Linux spaceball 2.6.27.6 #1 SMP Fri Nov 14 11:51:10 CET 2008 i686 QEMU
Virtual CPU version 0.9.1 AuthenticAMD GNU/Linux
# date
Thu Dec 19 01:54:27 WET 1912
# uptime
On Tue, 2 Dec 2008, Luis Henriques wrote:
Unfortunately, I have only my laptop (where the crash is occuring) and no
serial port on it (I am not able to get any output from the console). Do you
have any suggestion on how to collect information on the crash? I can try to
configure Kdump
* Alan Cox ([EMAIL PROTECTED]) wrote:
On Tue, 2 Dec 2008 10:07:24 -0800
Chris Wright [EMAIL PROTECTED] wrote:
* Alan Cox ([EMAIL PROTECTED]) wrote:
+ r = !memcmp(old_digest, sha1_item-sha1val, SHA1_DIGEST_SIZE);
+ mutex_unlock(sha1_lock);
+ if (r) {
+
On Tue, 2 Dec 2008 13:24:11 -0800
Chris Wright [EMAIL PROTECTED] wrote:
Using current known techniques. A random collision is just as bad
news.
And, just to clarify, your concern would extend to any digest based
comparison? Or are you specifically concerned about sha1?
Wouldn't this
Formerly, we used to maintain a per-vcpu shadow TLB and on every entry to the
guest would load this array into the hardware TLB. This consumed 1280 bytes of
memory (64 entries of 16 bytes plus a struct page pointer each), and also
required some assembly to loop over the array on every entry.
Store shadow TLB entries in memory, but only use it on host context switch
(instead of every guest entry). This improves performance for most workloads on
440 by reducing the guest TLB miss rate.
Signed-off-by: Hollis Blanchard [EMAIL PROTECTED]
diff --git a/arch/powerpc/include/asm/kvm_44x.h
KVM currently ignores the host's round robin TLB eviction selection, instead
maintaining its own TLB state and its own round robin index. However, by
participating in the normal 44x TLB selection, we can drop the alternate TLB
processing in KVM. This results in a significant performance
KVM on 440 has always been able to handle large guest mappings with 4K host
pages -- we must, since the guest kernel uses 256MB mappings.
This patch makes KVM work when the host has large pages too (tested with 64K).
Signed-off-by: Hollis Blanchard [EMAIL PROTECTED]
diff --git
The only significant changes were to kvmppc_exit_timing_write() and
kvmppc_exit_timing_show(), both of which were dramatically simplified.
Signed-off-by: Hollis Blanchard [EMAIL PROTECTED]
diff --git a/arch/powerpc/include/asm/kvm_host.h
b/arch/powerpc/include/asm/kvm_host.h
---
Hi Avi, here's the latest batch of PowerPC kernel patches.
The first set dramatically improve performance. Most importantly, we add
support for large host pages with KVM (i.e. PAGE_SHIFT 12). (Large *guest*
pages have already been supported since day 1, since the guest kernel uses
them for the
Existing KVM statistics are either just counters (kvm_stat) reported for
KVM generally or trace based aproaches like kvm_trace.
For KVM on powerpc we had the need to track the timings of the different exit
types. While this could be achieved parsing data created with a kvm_trace
extension this
On Wednesday 03 December 2008 05:38:21 Hollis Blanchard wrote:
I just spent a number of hours tracking this one down, and I'm not too
thrilled about it. vp_find_vq() does the memory allocation for virtio
PCI rings, and it uses kzalloc() to do it. This is bad because the ring
memory *must* be
On Tue, 2 Dec 2008 13:24:11 -0800
Chris Wright [EMAIL PROTECTED] wrote:
* Alan Cox ([EMAIL PROTECTED]) wrote:
On Tue, 2 Dec 2008 10:07:24 -0800
Chris Wright [EMAIL PROTECTED] wrote:
* Alan Cox ([EMAIL PROTECTED]) wrote:
+ r = !memcmp(old_digest, sha1_item-sha1val,
On Wed, 2008-12-03 at 08:35 +1030, Rusty Russell wrote:
On Wednesday 03 December 2008 05:38:21 Hollis Blanchard wrote:
I just spent a number of hours tracking this one down, and I'm not too
thrilled about it. vp_find_vq() does the memory allocation for virtio
PCI rings, and it uses
I have a way to reproduce my instance of the problem easily now. I was
trying
to build a new kernel on my guest, and found that depmod hangs guests every
time.
In my case, I only have an amd processor - I don't have an intel
host to try it on, right now, but it happens on Ubuntu 8.04
Sounds like your configuration is very similar to mine.
I'm also on a vanilla kernel (2.6.27.7 in my case) with kvm-79 and
AMD processors.
You sparked my curiosity on the depmod -a issue, so I spent some time trying
it on different configurations.
I have two servers:
* 1.8GHz AMD Opteron
On Tue, Dec 2, 2008 at 1:27 AM, Yu Zhao [EMAIL PROTECTED] wrote:
SR-IOV drivers of Intel 82576 NIC are available. There are two parts
of the drivers: Physical Function driver and Virtual Function driver.
The PF driver is based on the IGB driver and is used to control PF to
allocate hardware
Daniel P. Berrange wrote:
On Tue, Dec 02, 2008 at 03:01:20PM +0200, Avi Kivity wrote:
Daniel P. Berrange wrote:
On Tue, Dec 02, 2008 at 10:25:49AM +0800, Zhang, Yang wrote:
This patch to save the nvram. It save the nvram by specify the arg
of -name.And the saved file named by the arg. If do
On Tue, Dec 02, 2008 at 02:01:11PM +0100, Joerg Roedel wrote:
Hi,
this patch series makes the current KVM device passthrough code generic
enough so that other IOMMU implementation can also plug into this code.
It works by factoring the functions Vt-d code exports to KVM into a
generic
Ok, I will save it in current directory and don't read nvram from file, if
don't specify -nvram.
Best Regards
--yang
-Original Message-
From: Zhang, Xiantao
Sent: 2008年12月3日 14:02
To: Daniel P. Berrange; Avi Kivity
Cc: Zhang, Yang; [EMAIL PROTECTED]; kvm@vger.kernel.org
Subject: RE:
MMIO of assigned device is registered as memory slot. Size of memory slot in
KVM must be page size multiple. But MMIO of some devices (e.g. EHCI controller)
is not page size mutiple, so it fails to register these MMIOs, thus device
assignment fails. In order to solve it, need to register target
On Tue, Dec 02, 2008 at 07:44:05PM -0800, Greg KH wrote:
On Tue, Dec 02, 2008 at 02:01:11PM +0100, Joerg Roedel wrote:
Hi,
this patch series makes the current KVM device passthrough code generic
enough so that other IOMMU implementation can also plug into this code.
It works by
On Wed, Dec 03, 2008 at 08:50:49AM +0100, Joerg Roedel wrote:
On Tue, Dec 02, 2008 at 07:44:05PM -0800, Greg KH wrote:
On Tue, Dec 02, 2008 at 02:01:11PM +0100, Joerg Roedel wrote:
Hi,
this patch series makes the current KVM device passthrough code generic
enough so that other
Signed-off-by: Hollis Blanchard [EMAIL PROTECTED]
---
qemu/hw/device_tree.c | 14 +++---
qemu/hw/device_tree.h | 12 ++--
2 files changed, 13 insertions(+), 13 deletions(-)
diff --git a/qemu/hw/device_tree.c b/qemu/hw/device_tree.c
index e73129d..2621ff1 100644
---
Signed-off-by: Hollis Blanchard [EMAIL PROTECTED]
---
qemu/hw/ppc440_bamboo.c | 37 +
1 files changed, 21 insertions(+), 16 deletions(-)
diff --git a/qemu/hw/ppc440_bamboo.c b/qemu/hw/ppc440_bamboo.c
index bf42245..79e4ea8 100644
---
These patches fix the kvm-userspace qemu build after a recent merge with
upstream qemu.
I'm also seeing a build dependency issue with dyngen-opc.h that I don't see
upstream. I haven't sorted that out yet, but make
qemu/ppcemb-softmmu/dyngen-opc.h first works around the problem.
-Hollis
--
To
94 matches
Mail list logo