Public bug reported:
I've got qemu-kvm 0.12.5 on Gentoo Linux on an amd64 host. Both HTML
documentation and compiled-in command line help state that -cpu ?
should give me a list of possible values for the -cpu command line
switch. In fact that switch results in an error message: Unable to find
On 10/06/10 02:28, Alon Levy wrote:
Does this work with live migration? I can't see how it would.
No, it doesn't right now. It would require cooperation with the client,
to tell it to reconnect to the target qemu (kind of like spice).
I think until we have this migration should have
readv writev, read write respectively from the current offset
of the file hence their use has to be preceeded by a call to lseek.
preadv/writev can be used instead, as they take the offset as an argument.
This saves one system call( lseek ).
In case preadv is not supported, it is implemented by
Hi,
$subject says all ...
Triggered by mounting the filesystem. F14 guest.
(gdb) #0 0x00399f4329c5 in raise () from /lib64/libc.so.6
#1 0x00399f4341a5 in abort () from /lib64/libc.so.6
#2 0x00399f42b955 in __assert_fail () from /lib64/libc.so.6
#3 0x004209a4 in
On 10/06/2010 12:46 AM, linux_...@proinbox.com wrote:
Attached is a patch that allows qemu to have up to 32 NICs, without
using the qdev -device method.
I'd rather there be no fixed limit and we validate that when add fails
because there isn't a TCP slot available, we do the right thing.
On 10/05/2010 09:29 PM, Alex Williamson wrote:
On Tue, 2010-10-05 at 14:58 -0600, Alex Williamson wrote:
On Tue, 2010-10-05 at 15:49 -0500, Anthony Liguori wrote:
On 10/05/2010 03:46 PM, Alex Williamson wrote:
On Tue, 2010-10-05 at 15:41 -0500, Anthony Liguori wrote:
fix up errors returned to include errno, not just -1
Signed-off-by: Michael S. Tsirkin m...@redhat.com
---
hw/vhost.c |2 ++
1 files changed, 2 insertions(+), 0 deletions(-)
diff --git a/hw/vhost.c b/hw/vhost.c
index 5ac283b..2e5d7a6 100644
--- a/hw/vhost.c
+++ b/hw/vhost.c
@@ -516,12
vhost irqfd support: case where many vqs are
mapped to a single msix vector is currently broken.
Fix it up.
Signed-off-by: Michael S. Tsirkin m...@redhat.com
---
hw/msix.c | 68 ++-
hw/msix.h |4 +-
hw/pci.h|3 +-
When using irqfd with vhost-net to inject interrupts,
a single evenfd might inject multiple interrupts.
Implementing this is much easier with a single
per-device callback to set guest notifiers.
Signed-off-by: Michael S. Tsirkin m...@redhat.com
---
hw/vhost.c | 52
When guest maps a vector to multiple vqs, qemu kvm triggers an assert.
A simple way to test this is by supplying vectors=2 for
virtio-net-pci in qemu-kvm.
The first 2 patches apply to qemu.git. The 3d does not,
it has to be applied only to qemu-kvm.git.
Avi, marcelo, I think to prevent bisect
On a related note, there are more uses of BUG_ON() in hw/virtio-9p.c
which can be triggered from the guest:
submit_pdu():
BUG_ON(pdu-id = ARRAY_SIZE(pdu_handlers));
BUG_ON(handler == NULL);
handle_9p_output():
BUG_ON(pdu-elem.out_num == 0 || pdu-elem.in_num == 0);
vhost irqfd support: case where many vqs are
mapped to a single msix vector is currently broken.
Fix it up.
Signed-off-by: Michael S. Tsirkin m...@redhat.com
---
This is on top of the qemu patchset, which is unchanged.
Fixes from v1:
correct error handling
hw/msix.c | 68
On Sun, 2010-10-03 at 22:18 +0200, Michael S. Tsirkin wrote:
Move all of vhost-net start/stop logic to a single routine,
and call it from everywhere.
Additionally, start/stop vhost-net on link up/down:
we should not transmit anything if user asked us to
put the link down.
Signed-off-by:
On Mon, 2010-10-04 at 18:13 +0200, Michael S. Tsirkin wrote:
With -netdev, virtio devices present offload
features to guest, depending on the backend used.
Thus, removing host netdev peer while guest is
active leads to guest-visible inconsistency and/or crashes.
As a solution, while guest
With -netdev, virtio devices present offload
features to guest, depending on the backend used.
Thus, removing host netdev peer while guest is
active leads to guest-visible inconsistency and/or crashes.
As a solution, while guest (NIC) peer device exists,
we prevent the host peer from being
On Wed, 2010-10-06 at 18:04 +0200, Michael S. Tsirkin wrote:
With -netdev, virtio devices present offload
features to guest, depending on the backend used.
Thus, removing host netdev peer while guest is
active leads to guest-visible inconsistency and/or crashes.
As a solution, while guest
On Wed, Oct 06, 2010 at 10:10:51AM +0900, Hidetoshi Seto wrote:
(snip)
Index: qemu/kvm.h
===
--- qemu.orig/kvm.h
+++ qemu/kvm.h
@@ -110,6 +110,9 @@ int kvm_arch_init_vcpu(CPUState *env);
void
On Wed, Oct 06, 2010 at 10:58:36AM +0900, Hidetoshi Seto wrote:
I got some more question:
(2010/10/05 3:54), Marcelo Tosatti wrote:
Index: qemu/target-i386/cpu.h
===
--- qemu.orig/target-i386/cpu.h
+++
On Wed, Oct 06, 2010 at 09:48:06AM -0600, Alex Williamson wrote:
+void qemu_del_vlan_client(VLANClientState *vc)
+{
+/* If there is a peer NIC, delete and cleanup client, but do not free.
*/
+if (!vc-vlan vc-peer vc-peer-info-type ==
NET_CLIENT_TYPE_NIC) {
+
Am 06.10.2010 09:58, schrieb Martin von Gagern:
Public bug reported:
I've got qemu-kvm 0.12.5 on Gentoo Linux on an amd64 host. Both HTML
documentation and compiled-in command line help state that -cpu ?
should give me a list of possible values for the -cpu command line
switch. In fact that
On 10/06/2010 11:04 AM, Michael S. Tsirkin wrote:
With -netdev, virtio devices present offload
features to guest, depending on the backend used.
Thus, removing host netdev peer while guest is
active leads to guest-visible inconsistency and/or crashes.
As a solution, while guest (NIC) peer
On 06.10.2010 18:30, Stefan Weil wrote:
Does one of these work:
-cpu \?
-cpu '?'
If yes, then the shell's wildcard expansion caused your problem.
Yes indeed. Should have thought of that myself. Nevertheless, a note in
the manual might help others like me. Thanks in any case!
On Wed, 2010-10-06 at 16:56 +0200, Michael S. Tsirkin wrote:
vhost irqfd support: case where many vqs are
mapped to a single msix vector is currently broken.
Fix it up.
Signed-off-by: Michael S. Tsirkin m...@redhat.com
---
This is on top of the qemu patchset, which is unchanged.
Fixes
On Wed, Oct 06, 2010 at 11:35:08AM -0500, Anthony Liguori wrote:
On 10/06/2010 11:04 AM, Michael S. Tsirkin wrote:
With -netdev, virtio devices present offload
features to guest, depending on the backend used.
Thus, removing host netdev peer while guest is
active leads to guest-visible
On Wed, Oct 06, 2010 at 10:48:44AM -0600, Alex Williamson wrote:
-int msix_unset_mask_notifier(PCIDevice *dev, unsigned vector)
+static int msix_unset_mask_notifier_for_vector(PCIDevice *dev, unsigned
vector)
{
int r = 0;
-void *opaque;
if (vector =
On 10/06/2010 11:58 AM, Michael S. Tsirkin wrote:
On Wed, Oct 06, 2010 at 11:35:08AM -0500, Anthony Liguori wrote:
On 10/06/2010 11:04 AM, Michael S. Tsirkin wrote:
With -netdev, virtio devices present offload
features to guest, depending on the backend used.
Thus, removing host
On Wed, Oct 06, 2010 at 12:13:35PM -0500, Anthony Liguori wrote:
On 10/06/2010 11:58 AM, Michael S. Tsirkin wrote:
On Wed, Oct 06, 2010 at 11:35:08AM -0500, Anthony Liguori wrote:
On 10/06/2010 11:04 AM, Michael S. Tsirkin wrote:
With -netdev, virtio devices present offload
features to guest,
On Wed, 2010-10-06 at 19:02 +0200, Michael S. Tsirkin wrote:
On Wed, Oct 06, 2010 at 10:48:44AM -0600, Alex Williamson wrote:
-int msix_unset_mask_notifier(PCIDevice *dev, unsigned vector)
+static int msix_unset_mask_notifier_for_vector(PCIDevice *dev, unsigned
vector)
{
int
On Wed, Oct 06, 2010 at 11:24:24AM -0600, Alex Williamson wrote:
On Wed, 2010-10-06 at 19:02 +0200, Michael S. Tsirkin wrote:
On Wed, Oct 06, 2010 at 10:48:44AM -0600, Alex Williamson wrote:
-int msix_unset_mask_notifier(PCIDevice *dev, unsigned vector)
+static int
commit ce6325ff1af34dbaee91c8d28e792277e43f1227
Author: Glauber Costa gco...@redhat.com
Date: Wed Mar 5 17:01:10 2008 -0300
Augment info cpus
This patch exposes the thread id associated with each
cpu through the already well known 'info cpus' interface.
Signed-off-by: Marcelo
Port qemu-kvm's MCE support
commit c68b2374c9048812f488e00ffb95db66c0bc07a7
Author: Huang Ying ying.hu...@intel.com
Date: Mon Jul 20 10:00:53 2009 +0800
Add MCE simulation support to qemu/kvm
KVM ioctls are used to initialize MCE simulation and inject MCE. The
real MCE
Port qemu-kvm's
commit 1bab5d11545d8de5facf46c28630085a2f9651ae
Author: Huang Ying ying.hu...@intel.com
Date: Wed Mar 3 16:52:46 2010 +0800
Add savevm/loadvm support for MCE
MCE registers are saved/load into/from CPUState in
kvm_arch_save/load_regs. To simulate the MCG_STATUS
Port qemu-kvm's KVM MCE (Machine Check Exception) handling to qemu. It
allows qemu to propagate MCEs to the guest.
v2:
- rename do_qemu_ram_addr_from_host.
- fix kvm_on_sigbus/kvm_on_sigbus_vcpu naming.
- fix bank register restoration (Dean Nelson).
Port qemu-kvm's signalfd compat code.
commit 5a7fdd0abd7cd24dac205317a4195446ab8748b5
Author: Anthony Liguori aligu...@us.ibm.com
Date: Wed May 7 11:55:47 2008 -0500
Use signalfd() in io-thread
This patch reworks the IO thread to use signalfd() instead of sigtimedwait()
This
From: Huang Ying ying.hu...@intel.com
In QEMU-KVM, physical address != RAM address. While MCE simulation
needs physical address instead of RAM address. So
kvm_physical_memory_addr_from_ram() is implemented to do the
conversion, and it is invoked before being filled in the IA32_MCi_ADDR
MSR.
To be used by next patches.
Signed-off-by: Marcelo Tosatti mtosa...@redhat.com
Index: qemu/cpu-common.h
===
--- qemu.orig/cpu-common.h
+++ qemu/cpu-common.h
@@ -47,7 +47,8 @@ void qemu_ram_free(ram_addr_t addr);
/* This should only
Block SIGALRM, SIGIO and consume them via signalfd.
Signed-off-by: Marcelo Tosatti mtosa...@redhat.com
Index: qemu/cpus.c
===
--- qemu.orig/cpus.c
+++ qemu/cpus.c
@@ -33,6 +33,7 @@
#include exec-all.h
#include cpus.h
+#include
Port qemu-kvm's
commit 4b62fff1101a7ad77553147717a8bd3bf79df7ef
Author: Huang Ying ying.hu...@intel.com
Date: Mon Sep 21 10:43:25 2009 +0800
MCE: Relay UCR MCE to guest
UCR (uncorrected recovery) MCE is supported in recent Intel CPUs,
where some hardware error such as some
On 10/6/2010 5:48 AM, Gerd Hoffmann wrote:
Hi,
$subject says all ...
Triggered by mounting the filesystem. F14 guest.
Ah. This is introduced by c9ba47dc5d8679efa4d5425aa27e0f8132920fb5
v9fs_string_sprintf() doesn't support %lu. I will send a patch to fix this
shortly.
- JV
(gdb) #0
On 10/06/2010 11:05 AM, Marcelo Tosatti wrote:
On Wed, Oct 06, 2010 at 10:58:36AM +0900, Hidetoshi Seto wrote:
I got some more question:
(2010/10/05 3:54), Marcelo Tosatti wrote:
Index: qemu/target-i386/cpu.h
===
---
On 10/6/2010 7:42 AM, Stefan Hajnoczi wrote:
On a related note, there are more uses of BUG_ON() in hw/virtio-9p.c
which can be triggered from the guest:
submit_pdu():
BUG_ON(pdu-id = ARRAY_SIZE(pdu_handlers));
BUG_ON(handler == NULL);
handle_9p_output():
On Tue, Sep 28, 2010 at 12:05:20PM +0200, Roedel, Joerg wrote:
On Tue, Sep 28, 2010 at 05:37:58AM -0400, Avi Kivity wrote:
On 09/28/2010 11:28 AM, Roedel, Joerg wrote:
Weird, it worked here as I tested it. I had it on qemu/master and with
all three patches. But patch 1 should not make
On Mon, Sep 27, 2010 at 03:16:15PM +0200, Joerg Roedel wrote:
As requested by Alex this patch makes kvm64 the default CPU
model when qemu is started with -enable-kvm. This takes only
effect for qemu-versions newer or equal to 0.14.0.
Signed-off-by: Joerg Roedel joerg.roe...@amd.com
---
On 10/05/2010 07:28 PM, Alon Levy wrote:
- Anthony Liguorianth...@codemonkey.ws wrote:
On 10/05/2010 04:32 PM, Alon Levy wrote:
This patch adds a new device, it is described in full in the second
patch
intro and also in the documentation in docs. In brief it
On 10/06/2010 03:55 AM, Gerd Hoffmann wrote:
On 10/06/10 02:28, Alon Levy wrote:
Does this work with live migration? I can't see how it would.
No, it doesn't right now. It would require cooperation with the client,
to tell it to reconnect to the target qemu (kind of like spice).
I
_GNU_SOURCE is already defined in QEMU_CFLAGS which
is passed to gcc in shell function compile_prog.
Removing the definition from several checks avoids compiler warnings
(which are now written to config.log).
Signed-off-by: Stefan Weil w...@mail.berlios.de
---
configure |4
1 files
On 10/06/2010 01:53 PM, Marcelo Tosatti wrote:
On Mon, Sep 27, 2010 at 03:16:15PM +0200, Joerg Roedel wrote:
As requested by Alex this patch makes kvm64 the default CPU
model when qemu is started with -enable-kvm. This takes only
effect for qemu-versions newer or equal to 0.14.0.
On 10/06/2010 12:34 PM, Marcelo Tosatti wrote:
Port qemu-kvm's MCE support
commit c68b2374c9048812f488e00ffb95db66c0bc07a7
Author: Huang Yingying.hu...@intel.com
Date: Mon Jul 20 10:00:53 2009 +0800
Add MCE simulation support to qemu/kvm
KVM ioctls are used to initialize MCE
I'm still not very tuned-in into the code, but I think this piece should
use _raw access primitives:
diff --git a/linux-user/signal.c b/linux-user/signal.c
index 77683f7..097da9d 100644
--- a/linux-user/signal.c
+++ b/linux-user/signal.c
@@ -982,8 +982,8 @@ restore_sigcontext(CPUX86State *env,
Anybody using a russian keyboard layout who can test this change and
confirm it works as expected?
There's no need to rebuild qemu to test it. Just changing the keymap
file on /us/share/qemu to remove the last two lines (shown below) should
be enough.
On Fri, Oct 01, 2010 at 03:14:28PM -0300,
On 10/6/2010 10:58 AM, Venkateswararao Jujjuri (JV) wrote:
On 10/6/2010 5:48 AM, Gerd Hoffmann wrote:
Hi,
$subject says all ...
Triggered by mounting the filesystem. F14 guest.
Ah. This is introduced by c9ba47dc5d8679efa4d5425aa27e0f8132920fb5
v9fs_string_sprintf() doesn't support
Our code paths for saving or migrating a VM are full of functions that
return void, leaving no opportunity for a device to cancel a migration,
either from error or incompatibility. The ivshmem driver attempted to
solve this with a no_migrate flag on the save state entry. I think the
more generic
Carry the vmsd pre_save error reporting through pci_device_save().
Signed-off-by: Alex Williamson alex.william...@redhat.com
---
hw/grackle_pci.c |4 +---
hw/gt64xxx.c |3 +--
hw/ivshmem.c |7 ++-
hw/openpic.c |4 +---
hw/pci.c |9 +++--
hw/pci.h
Carry pci_device_save() error through to virtio_save().
Signed-off-by: Alex Williamson alex.william...@redhat.com
---
hw/virtio-balloon.c|6 +-
hw/virtio-blk.c|6 +-
hw/virtio-net.c|7 ++-
hw/virtio-pci.c| 10 --
This allows vmsd based saves to also have a way to signal that
they can't be saved or migrated.
Signed-off-by: Alex Williamson alex.william...@redhat.com
---
hw/fdc.c |3 ++-
hw/hpet.c |3 ++-
hw/hw.h |6 +++---
hw/i2c.c |3 ++-
This lets a save state handler NAK a migration or cancel if
it runs into problems.
Signed-off-by: Alex Williamson alex.william...@redhat.com
---
block-migration.c |4 +++-
hw/hw.h |2 +-
savevm.c | 18 +++---
3 files changed, 19 insertions(+), 5
Some devices may not always able to save their state, allow
the save handler to return an error.
Signed-off-by: Alex Williamson alex.william...@redhat.com
---
hw/adb.c|8 ++--
hw/ads7846.c|4 +++-
hw/arm_gic.c|4 +++-
Now that the save state handlers can return error, individual drivers
can cancel a migration if they hit an error or don't support it. This
makes the unmigratable callback redundant. Remove it and change the
only user to cancel the migration in a set_params callback, which
actually happens much
Blue Swirl (11):
block: avoid a write only variable
cirrus: avoid write only variables
eepro100: initialize a variable in all cases
lsi53c895a: avoid a write only variable
Delete write only variables
mips_fulong2e: Delete write only variables
cris: avoid write only variables
vnc:
Compiling with GCC 4.6.0 20100925 produced warnings:
/src/qemu/hw/eepro100.c: In function 'eepro100_read4':
/src/qemu/hw/eepro100.c:1351:14: error: 'val' may be used
uninitialized in this function [-Werror=uninitialized]
/src/qemu/hw/eepro100.c: In function 'eepro100_read2':
Compiling with GCC 4.6.0 20100925 produced a warning:
/src/qemu/hw/lsi53c895a.c: In function 'lsi_do_msgout':
/src/qemu/hw/lsi53c895a.c:848:9: error: variable 'len' set but not
used [-Werror=unused-but-set-variable]
Fix by making the variable declaration and its uses also conditional
to debug
Compiling with GCC 4.6.0 20100925 produced warnings like:
/src/qemu/net/tap-win32.c: In function 'tap_win32_open':
/src/qemu/net/tap-win32.c:582:12: error: variable 'hThread' set but
not used [-Werror=unused-but-set-variable]
Fix by removing the unused variables.
Signed-off-by: Blue Swirl
Compiling with GCC 4.6.0 20100925 produced a warning:
/src/qemu/block/qcow2-refcount.c: In function 'update_refcount':
/src/qemu/block/qcow2-refcount.c:552:13: error: variable 'dummy' set
but not used [-Werror=unused-but-set-variable]
Fix by adding a function that does not generate a warning when
Compiling with GCC 4.6.0 20100925 produced warnings:
/src/qemu/target-cris/op_helper.c: In function 'helper_movl_sreg_reg':
/src/qemu/target-cris/op_helper.c:145:8: error: variable 'tlb_v' set
but not used [-Werror=unused-but-set-variable]
In file included from
Compiling with GCC 4.6.0 20100925 produced a lot of warnings like:
In file included from /src/qemu/hw/cirrus_vga_rop.h:174:0,
from /src/qemu/hw/cirrus_vga.c:284:
/src/qemu/hw/cirrus_vga_rop2.h: In function 'cirrus_patternfill_0_8':
/src/qemu/hw/cirrus_vga_rop2.h:48:18: error:
Compiling with GCC 4.6.0 20100925 produced warnings like:
/src/qemu/hw/mips_fulong2e.c: In function 'mips_fulong2e_init':
/src/qemu/hw/mips_fulong2e.c:274:16: error: variable 'rtc_state' set
but not used [-Werror=unused-but-set-variable]
/src/qemu/hw/mips_fulong2e.c:268:16: error: variable
Compiling with GCC 4.6.0 20100925 produced warnings:
/src/qemu/ui/vnc.c: In function 'vnc_client_cache_auth':
/src/qemu/ui/vnc.c:217:12: error: variable 'qdict' set but not used
[-Werror=unused-but-set-variable]
/src/qemu/ui/vnc.c: In function 'vnc_display_open':
/src/qemu/ui/vnc.c:2526:9: error:
On 06.10.2010, at 23:34, Blue Swirl wrote:
Compiling with GCC 4.6.0 20100925 produced warnings:
/src/qemu/target-ppc/op_helper.c: In function 'helper_icbi':
/src/qemu/target-ppc/op_helper.c:351:14: error: variable 'tmp' set but
not used [-Werror=unused-but-set-variable]
Compiling with GCC 4.6.0 20100925 produced warnings:
/src/qemu/target-i386/op_helper.c: In function 'switch_tss':
/src/qemu/target-i386/op_helper.c:283:53: error: variable 'new_trap'
set but not used [-Werror=unused-but-set-variable]
Fix by deleting the variable.
Alternatively the flag could be
Compiling with GCC 4.6.0 20100925 produced warnings:
/src/qemu/target-ppc/op_helper.c: In function 'helper_icbi':
/src/qemu/target-ppc/op_helper.c:351:14: error: variable 'tmp' set but
not used [-Werror=unused-but-set-variable]
/src/qemu/target-ppc/op_helper.c: In function 'do_6xx_tlb':
- Anthony Liguori anth...@codemonkey.ws wrote:
On 10/06/2010 03:55 AM, Gerd Hoffmann wrote:
On 10/06/10 02:28, Alon Levy wrote:
Does this work with live migration? I can't see how it would.
No, it doesn't right now. It would require cooperation with the
client,
to tell it
On Wed, Oct 06, 2010 at 11:24:24AM -0600, Alex Williamson wrote:
You could always keep the functions as separate wrapper callers of the
common function so you only need to keep true = unset, false = set
straight in one place. Thanks,
Just to show why it does not work, I did exactly this: as
- Anthony Liguori anth...@codemonkey.ws wrote:
On 10/05/2010 07:28 PM, Alon Levy wrote:
- Anthony Liguorianth...@codemonkey.ws wrote:
On 10/05/2010 04:32 PM, Alon Levy wrote:
This patch adds a new device, it is described in full in the
second
patch
On Wed, 2010-10-06 at 23:44 +0200, Michael S. Tsirkin wrote:
On Wed, Oct 06, 2010 at 11:24:24AM -0600, Alex Williamson wrote:
You could always keep the functions as separate wrapper callers of the
common function so you only need to keep true = unset, false = set
straight in one place.
(2010/10/07 3:10), Dean Nelson wrote:
On 10/06/2010 11:05 AM, Marcelo Tosatti wrote:
On Wed, Oct 06, 2010 at 10:58:36AM +0900, Hidetoshi Seto wrote:
I got some more question:
(2010/10/05 3:54), Marcelo Tosatti wrote:
Index: qemu/target-i386/cpu.h
06.10.2010 23:56, Eduardo Habkost wrote:
Anybody using a russian keyboard layout who can test this change and
confirm it works as expected?
I can perform such a testing - in theory. But in practice, I was never
able to figure out this -k $lang stuff, -- neither in qemu nor in other
apps like
06.10.2010 23:56, Eduardo Habkost wrote:
Anybody using a russian keyboard layout who can test this change and
confirm it works as expected?
Um, regardless of my previous email, the change is indeed correct and
needed, or else the slash/question key (the one that's usually on the
left from the
Hi :)
On Thu, Oct 7, 2010 at 02:44, Lluís xscr...@gmx.net wrote:
I'm still not very tuned-in into the code, but I think this piece should
use _raw access primitives:
I know nothing about your patch, but I suggest to rewrite this post so
it follows patch submission format e.g comment, signed
78 matches
Mail list logo