On Mon, 2016-08-29 at 10:30 -0400, David Gibson wrote:
>
> Possibly. In fact, I'm planning to eliminate cpu->cpu_dt_id at some
> point, in favour of having the machine type construct the id when it
> actually builds the dt. It's not really a cpu level construct.
On PowerNV it is as it's equal t
On Mon, Aug 29, 2016 at 10:53:04PM -0600, Alex Williamson wrote:
> On Mon, 29 Aug 2016 21:52:20 -0600
> Alex Williamson wrote:
>
> > On Mon, 29 Aug 2016 21:23:25 -0600
> > Alex Williamson wrote:
> >
> > > On Tue, 30 Aug 2016 05:27:17 +0300
> > > "Michael S. Tsirkin" wrote:
> > >
> > > > Mod
On Mon, 29 Aug 2016 21:52:20 -0600
Alex Williamson wrote:
> On Mon, 29 Aug 2016 21:23:25 -0600
> Alex Williamson wrote:
>
> > On Tue, 30 Aug 2016 05:27:17 +0300
> > "Michael S. Tsirkin" wrote:
> >
> > > Modern virtio pci devices can set VIRTIO_F_IOMMU_PLATFORM
> > > to signal they are safe
Gonglei (2):
crypto: fix building complaint
e1000: fix buliding complaint
crypto/tlscredsx509.c | 2 +-
hw/net/e1000e_core.c | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
--
1.7.12.4
gnutls commit 846753877d renamed LIBGNUTLS_VERSION_NUMBER to
GNUTLS_VERSION_NUMBER.
If using gnutls before that verion, we'll get the below warning:
crypto/tlscredsx509.c:618:5: warning: "GNUTLS_VERSION_NUMBER" is not defined
Signed-off-by: Gonglei
---
crypto/tlscredsx509.c | 2 +-
1 file chang
Oops, please see the v2.
Regards,
-Gonglei
> -Original Message-
> From: Gonglei (Arei)
> Sent: Tuesday, August 30, 2016 12:06 PM
> To: qemu-devel@nongnu.org
> Cc: berra...@redhat.com; dmi...@daynix.com; Gonglei (Arei)
> Subject: [PATCH 0/2] fix buliding complaint
>
>
> Gonglei (2):
>
hw/net/e1000e_core.c:56: warning: e1000e_set_interrupt_cause declared inline
after being called
hw/net/e1000e_core.c:56: warning: previous declaration of
e1000e_set_interrupt_cause was here
Signed-off-by: Gonglei
---
hw/net/e1000e_core.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
d
Gonglei (2):
crypto: fix building complaint
e1000: fix buliding complaint
crypto/tlscredsx509.c | 2 +-
hw/net/e1000e_core.c | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
--
1.7.12.4
hw/net/e1000e_core.c:56: warning: e1000e_set_interrupt_cause declared inline
after being called
hw/net/e1000e_core.c:56: warning: previous declaration of
e1000e_set_interrupt_cause was here
Signed-off-by: Gonglei
---
hw/net/e1000e_core.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
d
On Wed, Aug 10, 2016 at 5:03 PM, Juan Quintela wrote:
> Lai Jiangshan wrote:
>
> Hi
>
> First of all, I like a lot the patchset, but I would preffer to split it
> to find "possible" bugs along the lines, especially in postcopy, but not only.
Hello, thanks for review and comments
I tried to make
hw/net/e1000e_core.c:56: warning: e1000e_set_interrupt_cause declared inline
after being called
hw/net/e1000e_core.c:56: warning: previous declaration of
e1000e_set_interrupt_cause was here
Signed-off-by: Gonglei
---
hw/net/e1000e_core.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
d
On Mon, Aug 29, 2016 at 09:52:20PM -0600, Alex Williamson wrote:
> On Mon, 29 Aug 2016 21:23:25 -0600
> Alex Williamson wrote:
>
> > On Tue, 30 Aug 2016 05:27:17 +0300
> > "Michael S. Tsirkin" wrote:
> >
> > > Modern virtio pci devices can set VIRTIO_F_IOMMU_PLATFORM
> > > to signal they are sa
On Mon, 29 Aug 2016 21:23:25 -0600
Alex Williamson wrote:
> On Tue, 30 Aug 2016 05:27:17 +0300
> "Michael S. Tsirkin" wrote:
>
> > Modern virtio pci devices can set VIRTIO_F_IOMMU_PLATFORM
> > to signal they are safe to use with an IOMMU.
> >
> > Without this bit, exposing the device to usersp
On Tue, Aug 30, 2016 at 11:16:25AM +0800, Jason Wang wrote:
>
>
> On 2016年08月30日 10:27, Michael S. Tsirkin wrote:
> > Legacy virtio devices always bypassed an IOMMU, so using them with vfio was
> > never safe.
>
> And it actually won't work since GPA is assumed in the device. So I'm not
> sure t
On Mon, Aug 29, 2016 at 09:23:25PM -0600, Alex Williamson wrote:
> On Tue, 30 Aug 2016 05:27:17 +0300
> "Michael S. Tsirkin" wrote:
>
> > Modern virtio pci devices can set VIRTIO_F_IOMMU_PLATFORM
> > to signal they are safe to use with an IOMMU.
> >
> > Without this bit, exposing the device to u
On Tue, 30 Aug 2016 11:06:58 +0800
Jason Wang wrote:
> From: Peter Xu
>
> This reverts commit 3cb3b1549f5401dc3a5e1d073e34063dc274136f. Vhost
> device IOTLB API will get notified and send invalidation request to
> vhost through this notifier.
AFAICT this series does not address the original pr
Hi,
Your series failed automatic build test. Please find the testing commands and
their output below. If you have docker installed, you can probably reproduce it
locally.
Subject: [Qemu-devel] [PATCH for 2.8 00/11] virtio/vhost DMAR support
Type: series
Message-id: 1472526419-5900-1-git-send-emai
Hi,
Your series seems to have some coding style problems. See output below for
more information:
Subject: [Qemu-devel] [PATCH for 2.8 00/11] virtio/vhost DMAR support
Type: series
Message-id: 1472526419-5900-1-git-send-email-jasow...@redhat.com
=== TEST SCRIPT BEGIN ===
#!/bin/bash
BASE=base
n=
On Tue, 30 Aug 2016 05:27:17 +0300
"Michael S. Tsirkin" wrote:
> Modern virtio pci devices can set VIRTIO_F_IOMMU_PLATFORM
> to signal they are safe to use with an IOMMU.
>
> Without this bit, exposing the device to userspace is unsafe, so probe
> and fail VFIO initialization unless noiommu is e
From: Peter Xu
This reverts commit 3cb3b1549f5401dc3a5e1d073e34063dc274136f. Vhost
device IOTLB API will get notified and send invalidation request to
vhost through this notifier.
Cc: Alex Williamson
Signed-off-by: Peter Xu
Signed-off-by: Jason Wang
---
hw/i386/intel_iommu.c | 12 ---
Public bug reported:
ROCCAT Kone XTD mouse will randomly stop working in the guest until it's
restarted. Windows Event Viewer shows an error in i8042prt, with the
message "Could not set the mouse resolution". The XML log:
- http://schemas.microsoft.com/win/2004/08/events/event";>
-
23
This patches enable the Address Translation Service support for virtio
pci devices. This is needed for a guest visible Device IOTLB
implementation and will be required by vhost device IOTLB API
implementation for intel IOMMU.
Cc: Michael S. Tsirkin
Signed-off-by: Jason Wang
---
hw/pci/pcie.c
On 2016年08月30日 10:27, Michael S. Tsirkin wrote:
Legacy virtio devices always bypassed an IOMMU, so using them with vfio was
never safe.
And it actually won't work since GPA is assumed in the device. So I'm
not sure this is must since we should get a IOMMU fault in this case.
This adds a
This patch enables device IOTLB support for intel iommu. The major
work is to implement QI device IOTLB descriptor processing and notify
the device through iommu notifier.
Future work:
- Device IOTLB error processing, invalid and timeout
Cc: Paolo Bonzini
Cc: Richard Henderson
Cc: Eduardo Habko
This patches implements Device IOTLB support for vhost kernel. This is
done through:
1) switch to use dma helpers when map/unmap vrings from vhost codes
2) kernel support for Device IOTLB API:
- allow vhost-net to query the IOMMU IOTLB entry through eventfd
- enable the ability for qemu to update
This patch provides ATSR which was a requirement for software that
wants to enable ATS on endpoint devices behind a Root Port. This is
done simply by setting ALL_PORTS which indicates all PCI-Express Root
Ports support ATS transactions.
---
hw/i386/acpi-build.c| 9 +
include/hw/acp
Cc: Paolo Bonzini
Signed-off-by: Jason Wang
---
memory.c | 9 +
1 file changed, 9 insertions(+)
diff --git a/memory.c b/memory.c
index 0eb6895..ca0a698 100644
--- a/memory.c
+++ b/memory.c
@@ -1515,6 +1515,11 @@ bool memory_region_is_logging(MemoryRegion *mr, uint8_t
client)
void me
This patch introduces a helper to query the iotlb entry for a
possible iova. This will be used by later device IOTLB API to enable
the capability for a dataplane (e.g vhost) to query the IOTLB.
Cc: Paolo Bonzini
Cc: Peter Crosthwaite
Cc: Richard Henderson
Signed-off-by: Jason Wang
---
exec.c
To avoid duplicated name and ease debugging.
Cc: Michael S. Tsirkin
Cc: Paolo Bonzini
Cc: Richard Henderson
Cc: Eduardo Habkost
Acked-by: Peter Xu
Signed-off-by: Jason Wang
---
hw/i386/intel_iommu.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/hw/i386/intel_iommu.c
Currently, all virtio devices bypass IOMMU completely. This is because
address_space_memory is assumed and used during DMA emulation. This
patch converts the virtio core API to use DMA API. This idea is
- introducing a new transport specific helper to query the dma address
space. (only pci versi
We use the pointer to stack for key for new address space, this will break hash
table searching, fixing by g_malloc() a new key instead.
Cc: Michael S. Tsirkin
Cc: Paolo Bonzini
Cc: Richard Henderson
Cc: Eduardo Habkost
Acked-by: Peter Xu
Signed-off-by: Jason Wang
---
hw/i386/intel_iommu.c
Signed-off-by: Jason Wang
---
include/standard-headers/linux/input-event-codes.h | 32 +
include/standard-headers/linux/input.h | 1 +
include/standard-headers/linux/virtio_config.h | 10 +-
include/standard-headers/linux/virtio_ids.h| 1 +
include/st
Hi all:
As the userspace vitio driver became popular, more and more request
were received for secure DMA environemt (DMAR). So this series tries
to makeDMAR works for virtio/vhost. The idea is let virtio/vhost
co-work with userspace iommu implememtation. This is done through:
- for virtio, when p
The basic version of pcache driver for easy preparation of a patch set.
Signed-off-by: Pavel Butsykin
---
block/Makefile.objs | 1 +
block/pcache.c | 156
2 files changed, 157 insertions(+)
create mode 100644 block/pcache.c
diff --git
In case of node assert we will print the fields of a pcache node, this can be
useful for catching bugs.
Signed-off-by: Pavel Butsykin
---
block/pcache.c | 52 +++-
1 file changed, 35 insertions(+), 17 deletions(-)
diff --git a/block/pcache.c b/blo
Modern virtio pci devices can set VIRTIO_F_IOMMU_PLATFORM
to signal they are safe to use with an IOMMU.
Without this bit, exposing the device to userspace is unsafe, so probe
and fail VFIO initialization unless noiommu is enabled.
Signed-off-by: Michael S. Tsirkin
---
drivers/vfio/pci/vfio_pci_
When using vfio, callers might want to know whether device is added
to a regular group or an non-iommu group.
Report this status from vfio_is_noiommu_group_dev.
Signed-off-by: Michael S. Tsirkin
---
include/linux/vfio.h | 2 ++
drivers/vfio/vfio.c | 12
2 files changed, 14 insert
Legacy virtio devices always bypassed an IOMMU, so using them with vfio was
never safe. This adds a quirk detecting these and disabling VFIO unless the
noiommu mode is used. At the moment, this only applies to virtio-pci devices.
The patch might make sense on stable as well.
Michael S. Tsirkin
On 08/28/2016 03:44 PM, Greg Kurz wrote:
On Fri, 26 Aug 2016 18:05:31 +0200
Cédric Le Goater wrote:
When issuing a chassis 'powerdown' control command, the routine
qemu_system_shutdown_request() should be used to exit the guest.
qemu_system_powerdown_request() will initiate a soft shutdown whi
These are mandatory per PAPR and available on Linux 4.3 and newer kernels. The
calls in question are required to run FreeBSD guests with reasonable
performance, so enable them if possible.
Signed-off-by: Nathan Whitehorn
---
hw/ppc/spapr.c | 3 +++
target-ppc/kvm.c | 6 ++
target
From: Andrey Yurovsky
Add the "cortex-a7" CPU with features and registers matching the Cortex-A7
MPCore Technical Reference Manual and the Cortex-A7 Floating-Point Unit
Technical Reference Manual. The A7 is very similar to the A15.
Tested via the "virt" machine.
Signed-off-by: Andrey Yurovsky
On Mon, Aug 29, 2016 at 3:41 PM, Peter Maydell wrote:
> On 29 August 2016 at 18:36, Andrey Yurovsky wrote:
>> From: Andrey Yurovsky
>>
>> Add the "cortex-a7" CPU with features and registers matching the Cortex-A7
>> MPCore Technical Reference Manual and the Cortex-A7 Floating-Point Unit
>> Techn
Public bug reported:
Currently virtio-input devices cannot be used before the kernel loads.
This is not really a full bug but it would be much more useful if you
can use the keyboard+mouse this way.
** Affects: qemu
Importance: Undecided
Status: New
--
You received this bug notifi
Of all the gin joints in all the towns in all the world, Peter Maydell had to
walk into mine at 12:51:04 on Monday 29 August 2016 and say:
> On 29 August 2016 at 13:59, Bill Paul wrote:
> > Unfortunately it's been a frustrating experience because there seem to be
> > several key places where QEM
his change allow us to generalize the completion of all requests.
Signed-off-by: Pavel Butsykin
---
block/pcache.c | 14 --
1 file changed, 8 insertions(+), 6 deletions(-)
diff --git a/block/pcache.c b/block/pcache.c
index 435f2b4..1ff4c6a 100644
--- a/block/pcache.c
+++ b/block/pc
Signed-off-by: Pranith Kumar
---
tests/Makefile.include | 1 +
tests/tcg/Makefile.include | 20
2 files changed, 21 insertions(+)
create mode 100644 tests/tcg/Makefile.include
diff --git a/tests/Makefile.include b/tests/Makefile.include
index 14be491..141281b 100644
--
Signed-off-by: Pranith Kumar
---
tests/tcg/{ => mips}/hello-mips.c | 0
1 file changed, 0 insertions(+), 0 deletions(-)
rename tests/tcg/{ => mips}/hello-mips.c (100%)
diff --git a/tests/tcg/hello-mips.c b/tests/tcg/mips/hello-mips.c
similarity index 100%
rename from tests/tcg/hello-mips.c
rena
Signed-off-by: Pranith Kumar
---
tests/tcg/arm/Makefile| 45 +++
tests/tcg/{ => arm}/hello-arm.c | 0
tests/tcg/{ => arm}/test-arm-iwmmxt.s | 0
3 files changed, 45 insertions(+)
create mode 100644 tests/tcg/arm/Makefile
rename tests/tcg/{
Signed-off-by: Pranith Kumar
---
tests/tcg/misc/Makefile | 75 +++
tests/tcg/{ => misc}/linux-test.c | 3 ++
tests/tcg/{ => misc}/sha1.c | 0
tests/tcg/{ => misc}/test-mmap.c | 0
tests/tcg/{ => misc}/test_path.c | 0
tests/tcg/{ => misc}/
Hello,
This patch series cleans up the tcg tests in tests/tcg folder.
The tests have bit-rotten and were not compiling or running. I fixed
the Makefiles to make them compile but there are tests which do not
pass.
The motivation is to add litmus tests to each arch and have them run
using the 'mak
Write-through is another way to keep the cache up-to-date. Even if this
case will be rare, a node write buf is easier than a node drop.
Signed-off-by: Pavel Butsykin
---
block/pcache.c | 28
1 file changed, 20 insertions(+), 8 deletions(-)
diff --git a/block/pcache.
Why don't we use rbtree from glib? We need pointer to the parent node.
For optimal implementation storing of cached chunks in the rbtree
need to get next and previous nodes and content of parent node
is very useful for effective implementation of these functions. In this
implementation of rbtree (
Signed-off-by: Pavel Butsykin
---
include/qemu/atomic.h | 8
1 file changed, 8 insertions(+)
diff --git a/include/qemu/atomic.h b/include/qemu/atomic.h
index 7e13fca..7087d0f 100644
--- a/include/qemu/atomic.h
+++ b/include/qemu/atomic.h
@@ -152,6 +152,10 @@
_old;
On 29 August 2016 at 18:36, Andrey Yurovsky wrote:
> From: Andrey Yurovsky
>
> Add the "cortex-a7" CPU with features and registers matching the Cortex-A7
> MPCore Technical Reference Manual and the Cortex-A7 Floating-Point Unit
> Technical Reference Manual. The A7 is very similar to the A15.
>
>
When randomly reading data will be a lot of readahead, resulting in a loss of
productivity. In order to avoid added checking the requests line before
making the readahead. It also makes no sense to cache new requests,
because a cache hit on this data is very unlikely.
Signed-off-by: Pavel Butsykin
The prefetch cache aims to improve the performance of sequential read data.
Of most interest here are the requests of a small size of data for sequential
read, such requests can be optimized by extending them and moving into
the prefetch cache. However, there are 2 issues:
- In aggregate only a s
After applying this patch aio read can pick up data from the pcache.
for correct driver work added 3 things:
1. Filling the qiov out of the cache.
2. Request completes. This is necessary to inform the upper level,
that the data for the request has already been obtained.
3. Cache Invalidation in th
For storing requests use an rbtree, here are add basic operations on the
rbtree to work with cache nodes.
Signed-off-by: Pavel Butsykin
---
block/pcache.c | 190 -
1 file changed, 189 insertions(+), 1 deletion(-)
diff --git a/block/pcache
Signed-off-by: Pavel Butsykin
---
block/pcache.c | 9 +
1 file changed, 9 insertions(+)
diff --git a/block/pcache.c b/block/pcache.c
index 74a4bc4..7f221d6 100644
--- a/block/pcache.c
+++ b/block/pcache.c
@@ -28,6 +28,15 @@
#include "qapi/error.h"
#include "qapi/qmp/qstring.h"
+#defi
If the pcache has a bug with node reference, then s->death_node_list can help
to know about it.
Signed-off-by: Pavel Butsykin
---
block/pcache.c | 45 +++--
1 file changed, 39 insertions(+), 6 deletions(-)
diff --git a/block/pcache.c b/block/pcache.c
ind
Now we can't drop nodes until aio write request will not be completed,
because there is no guarantee that in the interval of time between the start
request and its completion can be cached overlapping chunk of blocks
and some data in the cache will be irrelevant.
Also became possible when aio writ
The pcache is directed to certain situations to sequential reads.
This concept allows to drop parts of the cache that were already used, which
will reduce the size of cache and the number of displaced nodes.
Signed-off-by: Pavel Butsykin
---
block/pcache.c | 24 +++-
1 file c
Signed-off-by: Pavel Butsykin
---
block/pcache.c | 43 +++
1 file changed, 35 insertions(+), 8 deletions(-)
diff --git a/block/pcache.c b/block/pcache.c
index 770bbc0..74a4bc4 100644
--- a/block/pcache.c
+++ b/block/pcache.c
@@ -24,12 +24,22 @@
#include
Added error handling aio requests to pcache driver. If the request fails,
then fails all pending requests.
Signed-off-by: Pavel Butsykin
---
block/pcache.c | 33 ++---
1 file changed, 22 insertions(+), 11 deletions(-)
diff --git a/block/pcache.c b/block/pcache.c
inde
On 29 August 2016 at 17:07, Aleksandar Markovic
wrote:
> From: Aleksandar Markovic
>
> This patch corrects target_semid64_ds structure definition for Mips.
>
> See, for example definition of semid64_ds for Mips in Linux kernel:
> arch/mips/include/uapi/asm/sembuf.h#L13.
>
> This patch will also f
From: Aleksandar Markovic
Structure flock is defined for Mips in a way defferent than any other
platform. For reference, see Linux kernel files:
arch/mips/include/uapi/asm/fcntl.h#L63 (for Mips)
include/uapi/asm-generic/fcntl.h#L195 (for all other platforms)
This patch fix this problem, by amen
From: Aleksandar Markovic
This series fixes several wrong definitions of preprocessor constants and
structures in Qemu user mode.
All patches are completely isolated Mips issues.
The serias fixes certain number of LTP test failures, if executed in
Qemu user mode for Mips platform.
Aleksandar M
From: Aleksandar Markovic
For some reason, Qemu's TARGET_F_GETOWN constant for Mips does not
match the correct value of correspondant F_GETOWN. This patch fixes
this problem.
For reference, see Mips' F_GETOWN definition in Linux kernel at
arch/mips/include/uapi/asm/fcntl.h#L44.
This patch also
From: Aleksandar Markovic
This patch corrects target_semid64_ds structure definition for Mips.
See, for example definition of semid64_ds for Mips in Linux kernel:
arch/mips/include/uapi/asm/sembuf.h#L13.
This patch will also fix certain semaphore-related LTP tests for Mips,
if they are executed
This is a simple solution to the problem of displacement of cache memory.
The LRU can be useful to avoid the displacement of the nodes, which have
been partially read.
Signed-off-by: Pavel Butsykin
---
block/pcache.c | 74 +-
1 file changed
for case when the cache partially covers request we are part of the request
is filled from the cache, and the other part request from disk. Also add
reference counting for nodes, as way to maintain multithreading.
There is still no full synchronization in multithreaded mode.
Signed-off-by: Pavel
On 29 August 2016 at 15:51, Peter Maydell wrote:
> There were some patches posted to the list last year (?) which had
> a go at fixing this, but unfortunately they got stalled in code
> review and the original submitter ran out of time/energy to finish
> the job. Getting those sorted out and into
> On 29 Aug 2016, at 23:30, Bill Paul wrote:
>
> I just wish all of this was in once place.
me too.
my sources are public, and I support anyone who wants to take parts of them to
improve the main source tree.
unfortunately I do not have the resources to do this. :-(
> Currently this vector
Of all the gin joints in all the towns in all the world, Liviu Ionescu had to
walk into mine at 12:19:42 on Monday 29 August 2016 and say:
> > On 29 Aug 2016, at 20:59, Bill Paul wrote:
> >
> > I recently started tinkering with ChibiOS as part of a small personal
> > project ...
>
> I did most
On 29 August 2016 at 13:59, Bill Paul wrote:
> Unfortunately it's been a frustrating experience because there seem to be
> several key places where QEMU's hardware emulation diverges from reality. The
> ChibiOS examples often seem to depend on behavior that is valid for actual
> hardware but which
This change will allow more efficient use of cache memory and
filter the case for which the pcache isn't efficient. We miss requests
that are not required in the optimization and thereby reducing the number
of unnecessary readaheads.
Add pcache-max-aio-size open parameter.
Signed-off-by: Pavel B
Implementation of obtaining fragments of the cache belonging to one area
of request. This will allow to handle the case when a request is partially
hits the cache.
Signed-off-by: Pavel Butsykin
---
block/pcache.c | 60 +-
1 file changed, 59
if the next block is cached, then we need to check the size of node to
ensure full readahead.
Signed-off-by: Pavel Butsykin
---
block/pcache.c | 51 +--
1 file changed, 49 insertions(+), 2 deletions(-)
diff --git a/block/pcache.c b/block/pcache.c
Hi,
I've been trying to install a Solaris 8 image using QEMU on a CentOS
machine this past week using mainly Artyom's blog (
http://tyom.blogspot.com/2009/12/solaris-under-qemu-how-to.html) and
neozeed's blog (
http://virtuallyfun.superglobalmegacorp.com/2010/10/03/formatting-disks-for-solaris/#co
Add pcache-full-size open parameter.
Signed-off-by: Pavel Butsykin
---
block/pcache.c | 22 +-
1 file changed, 21 insertions(+), 1 deletion(-)
diff --git a/block/pcache.c b/block/pcache.c
index f5022f9..54d4526 100644
--- a/block/pcache.c
+++ b/block/pcache.c
@@ -79,6 +79,8
Public bug reported:
qemu-monitor screendump often using 10-20% cpu usage of one core to take
a small capture.
Most of the CPU usage seems to come from libpixman. There were many
reports of libpixman becoming 8 times slower in newer releases.
https://github.com/qemu/qemu/blob/0c56c6ab68902281094
On 08/28/2016 12:34 PM, Greg Kurz wrote:
>>
>> For the sake of simplicity, I'd rather have the target names to follow the
>> same rules as other file names, and return ENOENT directly (the link you
>> provide states it is a valid option).
>>
>> Peter,
>>
>> Since you suggested to do explicit error
On Mon, Aug 29, 2016 at 03:54:10PM +0800, Xiao Guangrong wrote:
>
> Hi Ross,
>
> Sorry for the delay, i just returned back from KVM Forum.
>
> On 08/20/2016 02:30 AM, Ross Zwisler wrote:
> > On Fri, Aug 19, 2016 at 07:59:29AM -0700, Dan Williams wrote:
> > > On Fri, Aug 19, 2016 at 4:19 AM, Xiao
Heya!
> On 29 Aug 2016, at 08:06, Stefan Hajnoczi wrote:
>
> At KVM Forum an interesting idea was proposed to avoid
> bdrv_drain_all() during live migration. Mike Cui and Felipe Franciosi
> mentioned running at queue depth 1. It needs more thought to make it
> workable but I want to capture it
> On 29 Aug 2016, at 20:59, Bill Paul wrote:
>
> I recently started tinkering with ChibiOS as part of a small personal project
> ...
I did most of the development for the µOS++/CMSIS++
(http://micro-os-plus.github.io) on STM32F4DISCOVERY board, emulated by GNU ARM
Eclipse QEMU, which impleme
I recently started tinkering with ChibiOS as part of a small personal project
and wanted to test some of the demo configurations that it has with a machine
simulator before going all in on a reference board. I decided to try QEMU
2.6.0. I was mainly interested in an ARM Cortex-M machine, so I fi
Handle alignment of buffers, so that the vector paths can be
used more often. Add versions for AVX1 and SSE4.1, both of
which have incremental improvements over SSE2.
Signed-off-by: Richard Henderson
---
util/bufferiszero.c | 209
1 file chan
Allow selection of several acceleration functions
based on the size and alignment of the buffer.
Do not require ifunc support for AVX2 acceleration.
Signed-off-by: Richard Henderson
---
configure | 21 +---
util/bufferiszero.c | 349
Signed-off-by: Richard Henderson
---
include/qemu/cutils.h | 1 +
tests/Makefile.include| 3 ++
tests/test-bufferiszero.c | 78 +++
util/bufferiszero.c | 7 +
4 files changed, 89 insertions(+)
create mode 100644 tests/test-bufferis
The revised integer version is 4 times faster than the neon version
on an AppliedMicro Mustang. Even with hand scheduling and additional
unrolling I cannot make any neon version run as fast as the integer.
Signed-off-by: Richard Henderson
---
util/bufferiszero.c | 15 ---
1 file cha
There's no real knowledge of the cacheline size,
just prefetching one loop ahead.
Signed-off-by: Richard Henderson
---
util/bufferiszero.c | 5 +
1 file changed, 5 insertions(+)
diff --git a/util/bufferiszero.c b/util/bufferiszero.c
index c356415..2c5801b 100644
--- a/util/bufferiszero.c
++
Signed-off-by: Richard Henderson
---
util/Makefile.objs | 1 +
util/bufferiszero.c | 272
util/cutils.c | 244 --
3 files changed, 273 insertions(+), 244 deletions(-)
create mode 100644 util
Changes from v2 to v3:
* Unit testing. This includes having x86 attempt all versions of
the accelerator that will run on the hardware. Thus an avx2 host
will run the basic test 5 times (1.5sec on my laptop).
* Drop the ppc and aarch64 specializations. I have improved the
basic
For ppc64le, gcc6 does extremely poorly with the Altivec code.
Moreover, on POWER7 and POWER8, a hand-optimized Altivec version
turns out to be no faster than the revised integer version, and
therefore not worth the effort.
Signed-off-by: Richard Henderson
---
util/bufferiszero.c | 55 +-
Since the two users don't make use of the returned offset,
beyond ensuring that the entire buffer is zero, consider the
can_use_buffer_find_nonzero_offset and buffer_find_nonzero_offset
functions internal.
Reviewed-by: Dr. David Alan Gilbert
Signed-off-by: Richard Henderson
---
include/qemu/cut
Stefan Hajnoczi writes:
> On Wed, Aug 24, 2016 at 12:25:54PM +0200, Lluís Vilanova wrote:
>> Stefan Hajnoczi writes:
>>
>> > On Sun, Aug 21, 2016 at 02:32:34PM +0200, Lluís Vilanova wrote:
>> >> Unfortuntely, I've been unable to to make dtrace recognise QEMU's events
>> >> (I'm
>> >> only able t
From: Aleksandar Markovic
This patch series adds support for three syscalls to the Qemu user mode.
Each patch fixes certain LTP test failures that occur if LTP tests are
executed in Qemu user mode. This improvement will be in effect for all
platforms supported by Qemu. Altogether, there are 10 L
From: Aleksandar Markovic
This patch implements Qemu user mode sysfs() syscall support.
Syscall sysfs() involves returning information about the filesystem types
currently present in the kernel, and can operate in three distinct flavors,
depending on its first argument.
The implementation is ba
From: Aleksandar Markovic
This patch implements Qemu user mode adjtimex() syscall support.
Syscall adjtimex() reads and optionally sets parameters for a clock
adjustment algorithm used in network synchonization or similar scenarios.
The implementation is based on invocation of host's adjtimex()
From: Aleksandar Markovic
This patch implements Qemu user mode ustat() syscall support.
Syscall ustat() returns information about a mounted filesystem.
The implementation is similar to the implementations of statfs(),
fstatfs() and other related syscalls. It is based on invocation of
host's ust
1 - 100 of 181 matches
Mail list logo
