Il 03/07/2014 20:17, Stefan Hajnoczi ha scritto:
On Thu, Jul 3, 2014 at 6:59 PM, Paolo Bonzini wrote:
Looks like a very interesting optimization for the block layer. If we
can get some performance results - especially how it improves the
virtio-blk dataplane regression - maybe we should merge
On 03.07.14 18:59, Andreas Färber wrote:
Am 03.07.2014 18:46, schrieb Peter Maydell:
On 24 June 2014 07:06, Alistair Francis wrote:
SysBusDevice::init is deprecated. Convert to Object::init and
Note that there is no Object::init, only TypeInfo::instance_init.
Device::realize as prescribed
Il 04/07/2014 07:10, Ming Lei ha scritto:
With both the two coroutine patches and the block plug&unplug patches,
performance of qemu.git/master virtio-blk dataplane can recover to level of
QEMU 2.0.
So the excessive writes (to eventfd and irqfd) are not a problem?
That'd be a relief. :)
Paol
Il 03/07/2014 21:09, Jesse Barnes ha scritto:
Practically speaking, we could probably assume specific CPU/PCH combos,
as I don't think they're generally mixed across generations, though SNB
and IVB did have compatible sockets, so there is the possibility of
mixing CPT and PPT PCHs, but those are
On 2014-07-03 22:30, Michael S. Tsirkin wrote:
> On Thu, Jul 03, 2014 at 06:45:03PM +0200, Jan Kiszka wrote:
>> On 2014-07-03 12:02, Michael S. Tsirkin wrote:
>>> On Thu, Jul 03, 2014 at 10:43:57AM +0200, Jan Kiszka wrote:
On 2014-07-03 10:26, Le Tan wrote:
> In map_page() in hw/ide/ahci.c
On Thu, Jul 3, 2014 at 9:51 PM, Stefan Hajnoczi wrote:
> The coroutine pool reuses exited coroutines to make qemu_coroutine_create()
> cheap. The size of the pool is capped to prevent it from hogging memory after
> a period of high coroutine activity. Previously the max size was hardcoded to
> 6
On 07/03/2014 05:50 PM, Al Viro wrote:
> OK, looks sane. Next (trivial) bug: in translate_one()
> case 0xF800:
> /* WH64 */
> /* No-op */
> break;
> should be followed by
> case 0xFC00:
> /* WH64EN */
> /* No-op */
>
On 07/03/2014 08:56 PM, Hu Tao wrote:
> On Thu, Jul 03, 2014 at 06:33:28AM -0600, Eric Blake wrote:
>> On 07/03/2014 12:10 AM, Hu Tao wrote:
>>> This patch fixes two problems of memory-backend-file:
>>>
>>> 1. If user adds a memory-backend-file object using object_add command,
>>>specifying a n
This patch implements .bdrv_io_plug, .bdrv_io_unplug and
.bdrv_flush_io_queue callbacks for linux-aio Block Drivers,
so that submitting I/O as a batch can be supported on linux-aio.
Signed-off-by: Ming Lei
---
block/linux-aio.c | 93 +++--
block/
Before commit 580b6b2aa2(dataplane: use the QEMU block
layer for I/O), dataplane for virtio-blk submits block
I/O as a batch.
This commit 580b6b2aa2 replaces the custom linux AIO
implementation(including submit I/O as a batch) with QEMU
block layer, but this commit causes ~40% throughput regressio
Hi,
The commit 580b6b2aa2(dataplane: use the QEMU block layer for I/O)
introduces ~40% throughput regression on virtio-blk dataplane, and
one of causes is that submitting I/O as a batch is removed.
This patchset trys to introduce this mechanism on block, at least,
linux-aio can benefit from that.
This patch introduces three APIs so that following
patches can support queuing I/O requests and submitting them
as a batch for improving I/O performance.
Reviewed-by: Paolo Bonzini
Signed-off-by: Ming Lei
---
block.c | 31 +++
include/block/block.
On Thu, Jul 03, 2014 at 06:33:28AM -0600, Eric Blake wrote:
> On 07/03/2014 12:10 AM, Hu Tao wrote:
> > This patch fixes two problems of memory-backend-file:
> >
> > 1. If user adds a memory-backend-file object using object_add command,
> >specifying a non-existing directory for property mem-p
On Thu, Jul 03, 2014 at 09:51:13AM +0300, Michael S. Tsirkin wrote:
> On Thu, Jul 03, 2014 at 02:10:55PM +0800, Hu Tao wrote:
> > Introduce memory_region_init_ram_nofail() and
> > memory_region_init_ram_ptr_nofail(), which are the same as
> > memory_region_init_ram() and memory_region_init_ram_ptr(
On Thu, Jul 03, 2014 at 01:19:19PM -0700, Richard Henderson wrote:
> I believe I have a tidy solution to these /v insns. New patch set shortly.
OK, looks sane. Next (trivial) bug: in translate_one()
case 0xF800:
/* WH64 */
/* No-op */
break;
should be
On Fri, Jul 04, 2014 at 12:05:37AM +0100, Peter Maydell wrote:
> On 3 July 2014 23:47, Al Viro wrote:
> > How can that be correct? Suppose a = b = 0. We get
> > tcg_gen_eqv_i64(tmp, va, vb); -> tmp = -1
> > tcg_gen_mov_i64(tmp2, va); -> tmp2 = 0
> > tcg_gen_add_i64(vc, va, vb);
On Fri, Jul 4, 2014 at 2:59 AM, Andreas Färber wrote:
> Am 03.07.2014 18:46, schrieb Peter Maydell:
>> On 24 June 2014 07:06, Alistair Francis wrote:
>>> SysBusDevice::init is deprecated. Convert to Object::init and
>
> Note that there is no Object::init, only TypeInfo::instance_init.
>
So I've
On 3 July 2014 23:47, Al Viro wrote:
> How can that be correct? Suppose a = b = 0. We get
> tcg_gen_eqv_i64(tmp, va, vb); -> tmp = -1
> tcg_gen_mov_i64(tmp2, va); -> tmp2 = 0
> tcg_gen_add_i64(vc, va, vb);-> c = 0
> tcg_gen_xor_i64(tmp2, tmp2, vc);-> tmp2 = 0
> tcg
On Thu, Jul 03, 2014 at 01:19:19PM -0700, Richard Henderson wrote:
> > Grr... Wrong check, obviously - we want to check that tmp + MSB(tmp2) is 0.
> > Something like
> > setcond_32 tmp2, tmp2, zero, TCG_COND_LT
> > add_i32 tmp, tmp2, tmp
> > callhelper_IOV_if_n
Virtio header has been changed to compile and work with a real device.
Functions bus_foreach and device_find have been implemented for PCI.
Virtio-blk test case now opens a fake device.
Signed-off-by: Marc Marí
---
tests/Makefile|3 +-
tests/libqos/virtio-pci.c | 78 +++
On 07/03/14 16:25, Eric Blake wrote:
On 07/03/2014 01:45 PM, Eduardo Habkost wrote:
This fixes the following crash:
$ qemu-system-x86_64 -global container.xxx=y
hw/core/qdev-properties-system.c:399:qdev_add_one_global: Object
0x7f7eff234100 is not an instance of type device
Abor
We should raise INV for infinities as well, not OVR+INE.
Reported-by: Al Viro
Signed-off-by: Richard Henderson
---
target-alpha/fpu_helper.c | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/target-alpha/fpu_helper.c b/target-alpha/fpu_helper.c
index 2b6c96b..9b297de 100644
On 02.07.2014 10:17, Hu Tao wrote:
This adds preallocation=falloc and preallocation=full mode to qcow2
image creation.
preallocation=full allocates disk space by writing zeros to disk to
ensure disk space in any cases.
preallocation=falloc likes preallocation=full, but allocates disk space
by p
We need to write the result to the destination register before
raising any exception. Thus inline the code for each insn, and
check for any exception after we're done.
Reported-by: Al Viro
Signed-off-by: Richard Henderson
---
target-alpha/helper.h | 7 +-
target-alpha/int_helper.c | 5
The qualifiers can suppress the raising of exceptions, but real
hardware still records that the exceptions occurred.
Reported-by: Al Viro
Signed-off-by: Richard Henderson
---
target-alpha/fpu_helper.c | 67 ++-
target-alpha/translate.c | 41 +
When we use QUAL_RM_D, we copy fpcr_dyn_round to float_status.
When we install a new FPCR value, we update fpcr_dyn_round.
Reset the status of the cache so that we re-copy for the next
fp insn that requires dynamic rounding.
Signed-off-by: Richard Henderson
---
target-alpha/translate.c | 5 +
Floating-point overflow is a different bit from integer overflow.
Reported-by: Al Viro
Signed-off-by: Richard Henderson
---
target-alpha/fpu_helper.c | 25 ++---
target-alpha/helper.h | 1 -
target-alpha/translate.c | 17 -
3 files changed, 14 insertion
Previously forgotten, the kernel needs the software completion bit to
know that it needs to emulate software completion qualified insns.
Reported-by: Al Viro
Signed-off-by: Richard Henderson
---
target-alpha/fpu_helper.c | 5 ++---
1 file changed, 2 insertions(+), 3 deletions(-)
diff --git a/t
On Thu, Jul 03, 2014 at 06:45:03PM +0200, Jan Kiszka wrote:
> On 2014-07-03 12:02, Michael S. Tsirkin wrote:
> > On Thu, Jul 03, 2014 at 10:43:57AM +0200, Jan Kiszka wrote:
> >> On 2014-07-03 10:26, Le Tan wrote:
> >>> In map_page() in hw/ide/ahci.c, replace cpu_physical_memory_map() and
> >>> cpu_
On Thu, 3 Jul 2014 14:26:12 -0400
Konrad Rzeszutek Wilk wrote:
> On Thu, Jul 03, 2014 at 10:32:12AM +0300, Michael S. Tsirkin wrote:
> > On Wed, Jul 02, 2014 at 12:23:37PM -0400, Konrad Rzeszutek Wilk wrote:
> > > On Wed, Jul 02, 2014 at 04:50:15PM +0200, Paolo Bonzini wrote:
> > > > Il 02/07/201
On 07/02/2014 09:50 AM, Andrea Arcangeli wrote:
> The MADV_USERFAULT feature should be generic enough that it can
> provide the userfaults to the Android volatile range feature too, on
> access of reclaimed volatile pages.
Maybe.
I certainly can't keep track of all the versions of the variations
On Thu, Jul 03, 2014 at 06:34:33PM +0100, Richard W.M. Jones wrote:
> There's also a TCG-only mode, but the test ran so slowly as to be
> inconclusive. I might leave it going overnight.
Well I got bored with the TCG test after about 4 hours. It appears to
hang launching the L3 guest, reproducibl
I never got around to actually posting v1, although I sent a link to the
branch, buried in another thread. I've rebased the branch and added 3
more patches to cover more issued raised by Al since the v1.
I've used this to clean up all of the errors in glibc mainline wrt
math/test-double.out, due
The range +- 2**63 - 2**64 was returning the wrong truncated
result. We also incorrectly signaled overflow for -2**63.
Reported-by: Al Viro
Signed-off-by: Richard Henderson
---
target-alpha/fpu_helper.c | 10 +-
1 file changed, 5 insertions(+), 5 deletions(-)
diff --git a/target-alpha
On 02.07.2014 10:17, Hu Tao wrote:
This adds preallocation=falloc and preallocation=full mode to qcow2
image creation.
preallocation=full allocates disk space by writing zeros to disk to
ensure disk space in any cases.
preallocation=falloc likes preallocation=full, but allocates disk space
by p
On 07/02/2014 02:17 AM, Hu Tao wrote:
> Suggested-by: Markus Armbruster
> Reviewed-by: Max Reitz
> Signed-off-by: Hu Tao
> ---
> blockdev.c | 30 ++
> include/qapi/util.h | 17 +
> qapi/Makefile.objs | 1 +
> qapi/qapi-util.c| 32 ++
We were not representing the IOV (integer overflow) exception at all.
For ease of implementation, allocate a generic bit in softfloat, even
though softfloat will never raise the exception itself.
This can be licensed under either the softfloat-2a or -2b license.
Reported-by: Al Viro
Signed-off-b
PC should be one past the faulting insn. Add better commentary
for the machine-check exception path.
Reported-by: Al Viro
Signed-off-by: Richard Henderson
---
target-alpha/helper.c | 2 ++
target-alpha/mem_helper.c | 9 -
2 files changed, 10 insertions(+), 1 deletion(-)
diff --git
On 07/02/2014 02:17 AM, Hu Tao wrote:
> and avoid converting it back later.
>
> Reviewed-by: Max Reitz
> Signed-off-by: Hu Tao
> ---
> block/qcow2.c | 10 +-
> block/raw-posix.c | 6 +++---
> block/raw-win32.c | 6 +++---
> 3 files changed, 11 insertions(+), 11 deletions(-)
Revie
On Thu, Jul 03, 2014 at 12:09:28PM -0700, Jesse Barnes wrote:
> On Thu, 3 Jul 2014 14:26:12 -0400
> Konrad Rzeszutek Wilk wrote:
>
> > On Thu, Jul 03, 2014 at 10:32:12AM +0300, Michael S. Tsirkin wrote:
> > > On Wed, Jul 02, 2014 at 12:23:37PM -0400, Konrad Rzeszutek Wilk wrote:
> > > > On Wed, J
On 07/03/2014 01:45 PM, Eduardo Habkost wrote:
> This fixes the following crash:
>
> $ qemu-system-x86_64 -global container.xxx=y
> hw/core/qdev-properties-system.c:399:qdev_add_one_global: Object
> 0x7f7eff234100 is not an instance of type device
> Aborted (core dumped)
>
> New beha
On 07/03/2014 11:25 AM, Al Viro wrote:
> On Thu, Jul 03, 2014 at 07:51:04AM +0100, Al Viro wrote:
>
>> FWIW, why not just generate
>> trunc_i64_i32 tmp, va
>> trunc_i64_i32 tmp2, vb
>> muls2_i32 tmp2, tmp, tmp, tmp2
>> ext32s_i64 vc, tmp2
>> maybe_overflow_32 tmp
>> where
On Thu, Jul 03, 2014 at 08:00:04PM +0200, Alexander Graf wrote:
>
> On 03.07.14 19:57, Peter Maydell wrote:
> >On 3 July 2014 18:39, Alexander Graf wrote:
> >>Mac OS X reads ICR on every interrupt. When the IRQ line is shared, this may
> >>result in a race where LSC is not interpreted yet, but al
On 02.07.2014 10:17, Hu Tao wrote:
This patch adds a new option preallocation for raw format, and implements
falloc and full preallocation.
Signed-off-by: Hu Tao
---
block/raw-posix.c | 62 ---
1 file changed, 55 insertions(+), 7 deletions(
On 02.07.2014 10:17, Hu Tao wrote:
This patch prepares for the subsequent patches.
Reviewed-by: Fam Zheng
Reviewed-by: Eric Blake
Signed-off-by: Hu Tao
---
block/qcow2.c| 16
qapi/block-core.json | 17 +
2 files changed, 25 insertions(+), 8 deletio
This fixes the following crash:
$ qemu-system-x86_64 -global container.xxx=y
hw/core/qdev-properties-system.c:399:qdev_add_one_global: Object
0x7f7eff234100 is not an instance of type device
Aborted (core dumped)
New behavior will be to just warn, just like when non-existing clas
nam
Patch 1 (which was submitted previously but has fallen through the cracks)
fixes:
$ qemu-system-x86_64 -global cpu.xxx=y
qemu-system-x86_64: Property '.xxx' not found
Aborted (core dumped)
Patch 2 fixes:
$ qemu-system-x86_64 -global container.xxx=y
hw/core
It would be much better if we didn't terminate QEMU inside
device_post_init(), but at least exiting cleanly is better than aborting
and dumping core.
Before this patch:
$ qemu-system-x86_64 -global cpu.xxx=y
qemu-system-x86_64: Property '.xxx' not found
Aborted (core dumped)
After th
On Thu, Jul 3, 2014 at 3:59 PM, Eric Blake wrote:
> On 07/03/2014 07:52 AM, Stefan Hajnoczi wrote:
>> Allow coroutine users to adjust the pool size. For example, if the
>> guest has multiple emulated disk drives we should keep around more
>> coroutines.
>>
>> Signed-off-by: Stefan Hajnoczi
>> --
On Thu, Jul 03, 2014 at 10:32:12AM +0300, Michael S. Tsirkin wrote:
> On Wed, Jul 02, 2014 at 12:23:37PM -0400, Konrad Rzeszutek Wilk wrote:
> > On Wed, Jul 02, 2014 at 04:50:15PM +0200, Paolo Bonzini wrote:
> > > Il 02/07/2014 16:00, Konrad Rzeszutek Wilk ha scritto:
> > > >With this long thread I
On Thu, Jul 03, 2014 at 11:00:37AM +0800, Chen, Tiejun wrote:
> >>
> >>Is that about correct?
> >>
> >>What are folks timezones and the best days next week to talk about
> >>this on either Google Hangout or the phone?
> >
> >UK timezone. Maybe Friday afternoon so that afterwards we can go have
> >e
On Thu, Jul 03, 2014 at 07:51:04AM +0100, Al Viro wrote:
> FWIW, why not just generate
> trunc_i64_i32 tmp, va
> trunc_i64_i32 tmp2, vb
> muls2_i32 tmp2, tmp, tmp, tmp2
> ext32s_i64 vc, tmp2
> maybe_overflow_32 tmp
> where maybe_overflow throws IOV unless tmp is 0 or
On Thu, Jul 3, 2014 at 6:59 PM, Paolo Bonzini wrote:
Looks like a very interesting optimization for the block layer. If we
can get some performance results - especially how it improves the
virtio-blk dataplane regression - maybe we should merge it for 2.1.
> @@ -247,9 +248,22 @@ ThreadPool *aio
On 03.07.14 19:57, Peter Maydell wrote:
On 3 July 2014 18:39, Alexander Graf wrote:
Mac OS X reads ICR on every interrupt. When the IRQ line is shared, this may
result in a race where LSC is not interpreted yet, but already gets cleared.
The guest already has a way of telling us that it can i
On 3 July 2014 18:39, Alexander Graf wrote:
> Mac OS X reads ICR on every interrupt. When the IRQ line is shared, this may
> result in a race where LSC is not interpreted yet, but already gets cleared.
>
> The guest already has a way of telling us that it can interpret LSC events
> though and that
Mac OS X reads ICR on every interrupt. When the IRQ line is shared, this may
result in a race where LSC is not interpreted yet, but already gets cleared.
The guest already has a way of telling us that it can interpret LSC events
though and that's via the interrupt mask register (IMS).
So if we ju
If you have odd Intel or AMD hardware, I'd appreciate if you could
test my disk image which recursively launches nested KVM until
something breaks:
http://rwmj.wordpress.com/2014/07/03/super-nested-kvm/#content
FWIW:
* AMD FX(tm)-8320 Eight-Core Processor:
L3 guest fails to boot with
[ 30
On 03.07.14 18:43, Gabriel L. Somlo wrote:
On Thu, Jul 03, 2014 at 05:25:04PM +0200, Alexander Graf wrote:
Maybe the IRQ line is simply never shared on real Macs :). Who knows.
Does this (untested!) patch make it work for you?
Yep, it works. Doesn't break OSX on q35, Linux (F20) or windows (7
Am 03.07.2014 18:46, schrieb Peter Maydell:
> On 24 June 2014 07:06, Alistair Francis wrote:
>> SysBusDevice::init is deprecated. Convert to Object::init and
Note that there is no Object::init, only TypeInfo::instance_init.
>> Device::realize as prescribed by QOM conventions.
>>
>> Signed-off-by
In many cases, the call to event_notifier_set in aio_notify is unnecessary.
In particular, if we are executing aio_dispatch, or if aio_poll is not
blocking, we know that we will soon get to the next loop iteration (if
necessary); the thread that hosts the AioContext's event loop does not
need any n
On 24 June 2014 07:06, Alistair Francis wrote:
> SysBusDevice::init is deprecated. Convert to Object::init and
> Device::realize as prescribed by QOM conventions.
>
> Signed-off-by: Alistair Francis
> ---
>
> hw/char/cadence_uart.c | 29 -
> 1 files changed, 16 inse
On 2014-07-03 12:02, Michael S. Tsirkin wrote:
> On Thu, Jul 03, 2014 at 10:43:57AM +0200, Jan Kiszka wrote:
>> On 2014-07-03 10:26, Le Tan wrote:
>>> In map_page() in hw/ide/ahci.c, replace cpu_physical_memory_map() and
>>> cpu_physical_memory_unmap() with dma_memory_map() and dma_memory_unmap(),
On Thu, Jul 03, 2014 at 05:25:04PM +0200, Alexander Graf wrote:
> Maybe the IRQ line is simply never shared on real Macs :). Who knows.
>
> Does this (untested!) patch make it work for you?
Yep, it works. Doesn't break OSX on q35, Linux (F20) or windows (7)
either :)
Thanks,
--Gabriel
> diff --
On 03.07.2014 [10:03:10 +0300], Michael S. Tsirkin wrote:
> On Tue, Jul 01, 2014 at 01:11:08PM -0700, Nishanth Aravamudan wrote:
> > As suggested by Eduardo Habkost, rename nb_numa_nodes to num_numa_nodes
> > throughout the code, as that reflects the use of the variable more
> > clearly.
> >
> > S
Il 03/07/2014 17:25, Alexander Graf ha scritto:
Maybe the IRQ line is simply never shared on real Macs :).
That's most likely the case, or else it uses MSI.
Consider that QEMU only uses 2 GSIs for the four PCI interrupts (10 11),
while real PIIX-era hardware used 4 (5 9 10 11, I think).
Pa
Il 03/07/2014 18:02, Stefan Hajnoczi ha scritto:
Hot unplug is broken in qemu.git/master
(92259b7f434b382fc865d1f65f7d5adeed295749 aka 2.0-rc0).
It can be bisected but I won't be able to do that today. Here are the
details if anyone has ideas:
Most likely my fault (memory region QOMification)
Hot unplug is broken in qemu.git/master
(92259b7f434b382fc865d1f65f7d5adeed295749 aka 2.0-rc0).
It can be bisected but I won't be able to do that today. Here are the
details if anyone has ideas:
$ x86_64-softmmu/qemu-system-x86_64 -enable-kvm -cpu host -m 1024
-drive if=virtio,cache=none,file=te
In this case, 'ret' is already '-1', so need not do it again.
Signed-off-by: Chen Gang
---
qemu-img.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/qemu-img.c b/qemu-img.c
index c98896b..d4518e7 100644
--- a/qemu-img.c
+++ b/qemu-img.c
@@ -246,7 +246,6 @@ static int read_password(char *buf,
On Wed, Jul 2, 2014 at 10:25 AM, Christian Borntraeger
wrote:
> On 01/07/14 17:25, Stefan Hajnoczi wrote:
>> This series fixes issues recently introduced when unifying virtio-blk
>> dataplane's request handling with non-dataplane virtio-blk.
>>
>> The problems include broken memory allocation for
From: KONRAD Frederic
This takes icount clock in account for icount extra computation so icount
clock's timers will be triggered at the exact time.
Signed-off-by: KONRAD Frederic
Reviewed-by: Paolo Bonzini
---
cpus.c | 10 ++
1 file changed, 10 insertions(+)
diff --git a/cpus.c b/cpu
From: KONRAD Frederic
Notify events on icount clock when CPU loop exits.
Signed-off-by: KONRAD Frederic
Reviewed-by: Paolo Bonzini
---
cpus.c | 5 +
1 file changed, 5 insertions(+)
diff --git a/cpus.c b/cpus.c
index 6bba30b..dc2dc21 100644
--- a/cpus.c
+++ b/cpus.c
@@ -992,6 +992,11 @@ s
From: KONRAD Frederic
This introduces a new timer based only on instruction counter and without any
compensation.
Signed-off-by: KONRAD Frederic
---
cpus.c | 19 ---
include/qemu/timer.h | 9 -
qemu-timer.c | 8 +++-
stubs/cpu-get-icoun
On 03.07.14 16:14, Gabriel L. Somlo wrote:
On Thu, Jul 03, 2014 at 04:02:06PM +0200, Alexander Graf wrote:
On 03.07.14 15:58, Gabriel L. Somlo wrote:
On Thu, Jul 03, 2014 at 03:20:50PM +0200, Alexander Graf wrote:
On 03.07.2014, at 15:17, Gabriel L. Somlo wrote:
On Thu, Jul 03, 2014 at 10:
From: KONRAD Frederic
Hi everybody,
This is the sixth version of this RFC (see the changes below).
Those are the two first patch-set we have been worked on for reverse execution.
The first part is fully reviewed except the "icount: introduce icount timer"
patch maybe we can merge them?
The fi
From: KONRAD Frederic
This fixes a bug where qemu_icount and qemu_icount_bias are not migrated.
It adds a subsection "timer/icount" to vmstate_timers so icount is migrated only
when needed.
Signed-off-by: KONRAD Frederic
Reviewed-by: Amit Shah
Reviewed-by: Juan Quintela
---
cpus.c | 27 +
From: KONRAD Frederic
This creates QEMU options for reverse execution.
Signed-off-by: KONRAD Frederic
---
cpus.c | 15 +++
qemu-options.hx | 6 +-
vl.c| 6 ++
3 files changed, 26 insertions(+), 1 deletion(-)
diff --git a/cpus.c b/cpus.c
index 740c6e5
From: KONRAD Frederic
This allows QEMU to trigger a debug exception when rexec_dbg_requested
is set.
Signed-off-by: KONRAD Frederic
---
cpu-exec.c | 13 +
1 file changed, 13 insertions(+)
diff --git a/cpu-exec.c b/cpu-exec.c
index 38e5f02..82e2568 100644
--- a/cpu-exec.c
+++ b/cpu
From: KONRAD Frederic
This makes qemu_savevm_state public for reverse-execution.
Signed-off-by: KONRAD Frederic
Reviewed-by: Amit Shah
Reviewed-by: Juan Quintela
---
include/sysemu/sysemu.h | 1 +
savevm.c| 2 +-
2 files changed, 2 insertions(+), 1 deletion(-)
diff --git a/i
Paolo Bonzini writes:
> Il 03/07/2014 09:19, Markus Armbruster ha scritto:
>>> > I think there is a page with unfinished transition. Can you add this one?
>> Do you mean the transition to qdev?
>>
>> If yes, isn't that covered by "Making all devices QOM objects"?
>> Sometimes we create new trans
From: KONRAD Frederic
We don't want to warp on host clock as it is not deterministic for replay.
So this patch warp icount on the next QEMU_VIRTUAL_CLOCK event if reverse
execution is enabled.
The normal behaviour is kept when reverse execution is disabled.
Signed-off-by: KONRAD Frederic
---
On 30.06.14 16:30, Alexey Kardashevskiy wrote:
Here are 2 patches to simplify handling of the same CPUs with slightly
different PVRs.
Now with a callback instead of additional levels in PPC CPU QOM class tree.
Please comment. Thanks.
Thanks, applied to ppc-next (2.1)
Alex
On 03.07.14 16:14, Gabriel L. Somlo wrote:
On Thu, Jul 03, 2014 at 04:02:06PM +0200, Alexander Graf wrote:
On 03.07.14 15:58, Gabriel L. Somlo wrote:
On Thu, Jul 03, 2014 at 03:20:50PM +0200, Alexander Graf wrote:
On 03.07.2014, at 15:17, Gabriel L. Somlo wrote:
On Thu, Jul 03, 2014 at 10:
So far it was enough to have a base PVR value and mask per CPU
family such as POWER7 or POWER8. However there CPUs which are
completely architecturally compatible but have different PVRs such
as POWER7/POWER7+ and POWER8/POWER8E. For these CPUs, top 16 bits
are CPU family and low 16 bits are the ve
From: KONRAD Frederic
This adds cpu_icount_to_ns function which is needed for reverse execution.
It returns the time for a specific instruction.
Signed-off-by: KONRAD Frederic
Reviewed-by: Paolo Bonzini
---
cpus.c | 9 +++--
include/qemu/timer.h | 1 +
2 files changed, 8 in
From: KONRAD Frederic
This introduces the basic reverse-execution mechanism.
Signed-off-by: KONRAD Frederic
---
Makefile.target | 1 +
cpus.c | 6 +
include/reverse-execution.h | 41 ++
reverse-execution.c | 308
From: KONRAD Frederic
This puts qemu_icount and qemu_icount_bias into TimerState structure to allow
them to be migrated.
Signed-off-by: KONRAD Frederic
Reviewed-by: Paolo Bonzini
---
cpus.c | 29 -
1 file changed, 16 insertions(+), 13 deletions(-)
diff --git a/cpu
From: Sebastian Tanase
Make icount parameter use QemuOpts style options in order
to easily add other suboptions.
Signed-off-by: Sebastian Tanase
Tested-by: Camille Bégué
---
cpus.c| 10 +-
include/qemu-common.h | 3 ++-
qemu-options.hx | 4 ++--
qtest.c
From: KONRAD Frederic
This adds some trace-events for reverse execution.
Signed-off-by: KONRAD Frederic
---
trace-events | 6 ++
1 file changed, 6 insertions(+)
diff --git a/trace-events b/trace-events
index 11a17a8..66f9e08 100644
--- a/trace-events
+++ b/trace-events
@@ -1301,3 +1301,9
From: KONRAD Frederic
This allows gdb to reverse step QEMU: reverse-stepi and reverse-cont commands
are allowed.
When step_backward is called, QEMU restores a snapshot before the actual
instruction and stops (with a debug exit) when the previous instruction is
reached.
Signed-off-by: KONRAD Fre
Thanks, that's great to know!
--
You received this bug notification because you are a member of qemu-
devel-ml, which is subscribed to QEMU.
https://bugs.launchpad.net/bugs/1307473
Title:
guest hang due to missing clock interrupt
Status in QEMU:
New
Status in “linux” package in Ubuntu:
Co
On Thu, Jul 03, 2014 at 04:02:06PM +0200, Alexander Graf wrote:
>
> On 03.07.14 15:58, Gabriel L. Somlo wrote:
> >On Thu, Jul 03, 2014 at 03:20:50PM +0200, Alexander Graf wrote:
> >>On 03.07.2014, at 15:17, Gabriel L. Somlo wrote:
> >>
> >>>On Thu, Jul 03, 2014 at 10:04:55AM +0200, Alexander Graf
Hi Christopher,
On Thu, Jul 03, 2014 at 09:45:07AM -0400, Christopher Covington wrote:
> CRIU uses the soft dirty bit in /proc/pid/clear_refs and /proc/pid/pagemap to
> implement its pre-copy memory migration.
>
> http://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/tree/Documentation/v
On 07/03/2014 07:52 AM, Stefan Hajnoczi wrote:
> When a BlockDriverState is associated with a storage controller
> DeviceState we expect guest I/O. Use this opportunity to bump the
> coroutine pool size by 64.
>
> This patch ensures that the coroutine pool size scales with the number
> of drives
On 03.07.14 15:58, Gabriel L. Somlo wrote:
On Thu, Jul 03, 2014 at 03:20:50PM +0200, Alexander Graf wrote:
On 03.07.2014, at 15:17, Gabriel L. Somlo wrote:
On Thu, Jul 03, 2014 at 10:04:55AM +0200, Alexander Graf wrote:
so Ethernet, SATA, and USB, all sharing IRQ 11. Is there an easy way
to
On 07/03/2014 07:52 AM, Stefan Hajnoczi wrote:
> Allow coroutine users to adjust the pool size. For example, if the
> guest has multiple emulated disk drives we should keep around more
> coroutines.
>
> Signed-off-by: Stefan Hajnoczi
> ---
> include/block/coroutine.h | 11 +++
> qemu-co
On 03.07.14 15:25, Alexey Kardashevskiy wrote:
The changelog is:
> Quieten the grub warning
> Add boot menu support
> boot from disk having chrp-boot file
> fat16: fix read and remove debug messages
> dhcparch define missing in compilation
> pci-scan: reserve memory for pci-bri
On Thu, Jul 03, 2014 at 03:20:50PM +0200, Alexander Graf wrote:
>
> On 03.07.2014, at 15:17, Gabriel L. Somlo wrote:
>
> > On Thu, Jul 03, 2014 at 10:04:55AM +0200, Alexander Graf wrote:
> >>> so Ethernet, SATA, and USB, all sharing IRQ 11. Is there an easy way
> >>> to force one of those to use
On 16 June 2014 16:05, Sean Bruno wrote:
> Signed-off-by: Sean Bruno
> ---
> bsd-user/freebsd/strace.list | 1 +
> 1 file changed, 1 insertion(+)
>
> diff --git a/bsd-user/freebsd/strace.list b/bsd-user/freebsd/strace.list
> index 2800a2d..f10caaa 100644
> --- a/bsd-user/freebsd/strace.list
> ++
On 20 June 2014 01:19, Sean Bruno wrote:
> From: Stacey Son
>
> This change moves the system call handler for sysctl(2) and
> sysarch(2) from syscall.c to the OS and arch dependent directories.
> This eliminates many of the #ifdef's in syscall.c. These system
> call handlers are now located in t
On 03.07.14 15:32, Alexey Kardashevskiy wrote:
So far it was enough to have a base PVR value and mask per CPU
family such as POWER7 or POWER8. However there CPUs which are
completely architecturally compatible but have different PVRs such
as POWER7/POWER7+ and POWER8/POWER8E. For these CPUs, top
1 - 100 of 166 matches
Mail list logo
