for
tx, one for rx,
so vq can run on different threads.
2.make network front-end onto glib, currently virtio net dataplane
Liu Ping Fan (5):
net: introduce glib function for network
net: port tap onto glib
net: resolve race of tap backend and its peer
net: port vde onto glib
net: port
Signed-off-by: Liu Ping Fan pingf...@linux.vnet.ibm.com
---
net/vde.c | 15 ++-
1 files changed, 14 insertions(+), 1 deletions(-)
diff --git a/net/vde.c b/net/vde.c
index 4dea32d..be5a032 100644
--- a/net/vde.c
+++ b/net/vde.c
@@ -60,6 +60,16 @@ static ssize_t vde_receive
On Thu, Mar 28, 2013 at 10:32 PM, Stefan Hajnoczi stefa...@gmail.com wrote:
On Thu, Mar 28, 2013 at 03:55:52PM +0800, Liu Ping Fan wrote:
From: Liu Ping Fan pingf...@linux.vnet.ibm.com
Bind each NetClientState with a GSource(ie,NetClientSource). Currently,
these GSource attached with default
On Fri, Jan 11, 2013 at 2:57 AM, Vasilis Liaskovitis
vasilis.liaskovi...@profitbricks.com wrote:
IIRC q35 supports memory hotplug natively (picked up in some
discussion). Is that correct?
From previous discussion I also understand that q35 supports native hotplug.
Sections 5.1 and 5.2
On Thu, Mar 28, 2013 at 9:40 PM, Stefan Hajnoczi stefa...@gmail.com wrote:
On Thu, Mar 28, 2013 at 09:42:47AM +0100, Paolo Bonzini wrote:
Il 28/03/2013 08:55, Liu Ping Fan ha scritto:
3rd. block layer's AioContext will block other AioContexts on the same
thread.
I cannot understand
On Thu, Mar 28, 2013 at 10:55 PM, Stefan Hajnoczi stefa...@gmail.com wrote:
On Thu, Mar 28, 2013 at 03:55:51PM +0800, Liu Ping Fan wrote:
From: Liu Ping Fan pingf...@linux.vnet.ibm.com
These series aim to make the whole network re-entrant, here only apply
backend and frontend
From: Liu Ping Fan pingf...@linux.vnet.ibm.com
This is an proposal similar to push core listener out of biglock
for core listener out of biglock,
refer to orignal plan posted by Marcelo Tosatti,
http://lists.gnu.org/archive/html/qemu-devel/2012-06/msg04315.html
While core
From: Liu Ping Fan pingf...@linux.vnet.ibm.com
This pair of interface are optinal, except for those device which is
used outside the biglock's protection for hot unplug. Currently,
HostMem used by virtio-blk dataplane is outside biglock, so the RAM
device should implement this.
Signed-off
From: Liu Ping Fan pingf...@linux.vnet.ibm.com
The hostmem listener will translate gpa to hva quickly. Make it
global, so other component can use it.
Also this patch adopt MemoryRegionOps's ref/unref interface to
make it survive the RAM hotunplug.
Signed-off-by: Liu Ping Fan pingf
From: Liu Ping Fan pingf...@linux.vnet.ibm.com
Signed-off-by: Liu Ping Fan pingf...@linux.vnet.ibm.com
---
vl.c |2 ++
1 files changed, 2 insertions(+), 0 deletions(-)
diff --git a/vl.c b/vl.c
index 7643f16..46a25cf 100644
--- a/vl.c
+++ b/vl.c
@@ -4157,6 +4157,7 @@ int main(int argc, char
From: Liu Ping Fan pingf...@linux.vnet.ibm.com
When lookup gpa to hva, the corresponding MemoryRegion will be exposed
to caller, and will release by caller later
Signed-off-by: Liu Ping Fan pingf...@linux.vnet.ibm.com
---
hw/dataplane/vring.c | 88
From: Liu Ping Fan pingf...@linux.vnet.ibm.com
virtio-blk will reference to RAM's memoryRegion when the req has been
done. So we can avoid to call bdrv_drain_all() when RAM hot unplug.
Signed-off-by: Liu Ping Fan pingf...@linux.vnet.ibm.com
---
hw/dataplane/virtio-blk.c | 52
On Thu, Mar 28, 2013 at 10:44 PM, Peter Maydell
peter.mayd...@linaro.org wrote:
On 28 March 2013 08:08, Liu Ping Fan pingf...@linux.vnet.ibm.com wrote:
In theroy, the high priority should commit earlier, it is the same
reason as the sequence of Lower = earlier (during add), later (during del
On Thu, Mar 28, 2013 at 10:34 PM, Stefan Hajnoczi stefa...@gmail.com wrote:
On Thu, Mar 28, 2013 at 03:55:53PM +0800, Liu Ping Fan wrote:
From: Liu Ping Fan pingf...@linux.vnet.ibm.com
Signed-off-by: Liu Ping Fan pingf...@linux.vnet.ibm.com
---
net/tap.c |7 ++-
1 files changed, 6
On Thu, Mar 28, 2013 at 10:47 PM, Stefan Hajnoczi stefa...@gmail.com wrote:
On Thu, Mar 28, 2013 at 03:55:54PM +0800, Liu Ping Fan wrote:
From: Liu Ping Fan pingf...@linux.vnet.ibm.com
Attach each hubport with a GSource. Currently the GSource is attached
to default main context, and the hub
From: Liu Ping Fan pingf...@linux.vnet.ibm.com
These series aim to make the whole network re-entrant, here only apply backend
and frontend,
and for the netcore, separated patches have been sent out. All of these will
prepare us for
moving towards making network layer mutlit-thread.
Finally
From: Liu Ping Fan pingf...@linux.vnet.ibm.com
Bind each NetClientState with a GSource(ie,NetClientSource). Currently,
these GSource attached with default context, but in future, after
resolving the race between handlers and the interface exposed by NetClientInfo
and other re-entrant issue, we
From: Liu Ping Fan pingf...@linux.vnet.ibm.com
Signed-off-by: Liu Ping Fan pingf...@linux.vnet.ibm.com
---
net/tap.c |7 ++-
1 files changed, 6 insertions(+), 1 deletions(-)
diff --git a/net/tap.c b/net/tap.c
index 0b663d1..401161c 100644
--- a/net/tap.c
+++ b/net/tap.c
@@ -321,9
From: Liu Ping Fan pingf...@linux.vnet.ibm.com
Attach each hubport with a GSource. Currently the GSource is attached
to default main context, and the hub still run on iothread, but in
future, after making the whole layer thread-safe, we will admit ports
to run on different thread.
Signed-off
From: Liu Ping Fan pingf...@linux.vnet.ibm.com
Signed-off-by: Liu Ping Fan pingf...@linux.vnet.ibm.com
---
hw/virtio-net.c | 165 +++
hw/virtio.c |6 ++
hw/virtio.h |2 +
3 files changed, 173 insertions(+), 0 deletions(-)
diff
On Thu, Mar 28, 2013 at 5:29 PM, Vasilis Liaskovitis
vasilis.liaskovi...@profitbricks.com wrote:
Hi,
[...]
I haven't updated the series for a while, but I can rework if there is
a more
clear direction for the community.
Another open issue is reference counting of
In theroy, the high priority should commit earlier, it is the same
reason as the sequence of Lower = earlier (during add), later (during del)
Signed-off-by: Liu Ping Fan pingf...@linux.vnet.ibm.com
---
memory.c |2 +-
1 files changed, 1 insertions(+), 1 deletions(-)
diff --git a/memory.c b
On Wed, Mar 27, 2013 at 12:07 AM, Stefan Hajnoczi stefa...@redhat.com wrote:
There are several places where QEMU accidentally relies on the O_NONBLOCK
state
of passed file descriptors. Exposing O_NONBLOCK state makes it part of the
QMP
If in future, we push more backend on their dedicated
On Wed, Mar 13, 2013 at 6:58 PM, Paolo Bonzini pbonz...@redhat.com wrote:
Il 13/03/2013 06:59, Liu Ping Fan ha scritto:
These series aim to port network backend onto glib, and
prepare for moving towards making network layer mutlit-thread.
The brief of the whole aim and plan is documented
Signed-off-by: Liu Ping Fan pingf...@linux.vnet.ibm.com
---
include/net/net.h | 21
net/net.c | 89 +
net/tap.c | 57 +++--
3 files changed, 156 insertions(+), 11 deletions(-)
diff
From: Liu Ping Fan pingf...@linux.vnet.ibm.com
Attach each hubport with a GSource. Currently the GSource is attached
to default main context, and the hub still run on iothread, but in
future, after making the whole layer thread-safe, we will admit ports
to run on different thread(GMainContext
On Wed, Mar 13, 2013 at 6:39 PM, Paolo Bonzini pbonz...@redhat.com wrote:
Il 13/03/2013 02:26, liu ping fan ha scritto:
On Tue, Mar 12, 2013 at 4:55 PM, Paolo Bonzini pbonz...@redhat.com wrote:
Il 07/03/2013 03:53, Liu Ping Fan ha scritto:
From: Liu Ping Fan pingf...@linux.vnet.ibm.com
On Tue, Mar 12, 2013 at 4:55 PM, Paolo Bonzini pbonz...@redhat.com wrote:
Il 07/03/2013 03:53, Liu Ping Fan ha scritto:
From: Liu Ping Fan pingf...@linux.vnet.ibm.com
Introduce nc-send_lock, it shield off the race of nc-peer's reader and
deleter. With it, after deleter finish, no new
On Tue, Mar 12, 2013 at 4:50 PM, Paolo Bonzini pbonz...@redhat.com wrote:
Il 07/03/2013 03:53, Liu Ping Fan ha scritto:
From: Liu Ping Fan pingf...@linux.vnet.ibm.com
Forward packet to other hub ports by their AioContext.
Signed-off-by: Liu Ping Fan pingf...@linux.vnet.ibm.com
---
hw/qdev
use AioContext instead of GSource, but after discussion,
I think with GSource, we can integrated with glib more closely.
Liu Ping Fan (2):
net: port tap onto glib
net: port hub onto glib
hw/qdev-properties-system.c |1 +
include/net/net.h | 24 +++
include/net/queue.h
a small comment below:
On Fri, Nov 09, 2012 at 11:14:30AM +0800, Liu Ping Fan wrote:
From: Liu Ping Fan pingf...@linux.vnet.ibm.com
Signed-off-by: Liu Ping Fan pingf...@linux.vnet.ibm.com
---
cpu-common.h |8 ++--
cputlb.c |4 ++--
dma-helpers.c |4
On Wed, Mar 6, 2013 at 5:30 AM, mdroth mdr...@linux.vnet.ibm.com wrote:
On Sun, Mar 03, 2013 at 09:21:19PM +0800, Liu Ping Fan wrote:
From: Liu Ping Fan pingf...@linux.vnet.ibm.com
This series aim to make netlayer re-entrant, so netlayer can
run out of biglock safely.
I think most
From: Liu Ping Fan pingf...@linux.vnet.ibm.com
changes v1-v2
Because the NetQueue is exposed not just from qemu_send_queue_xx(), so
separating locks -- use NetQueue(NetQueue-lock) to protect the queue, and
use nc-send_lock for the access of nc-peer so we can protect the sender
from
From: Liu Ping Fan pingf...@linux.vnet.ibm.com
Forward packet to other hub ports by their AioContext.
Signed-off-by: Liu Ping Fan pingf...@linux.vnet.ibm.com
---
hw/qdev-properties-system.c |1 +
include/block/aio.h |1 +
include/net/net.h |5 +
include/net
From: Liu Ping Fan pingf...@linux.vnet.ibm.com
Signed-off-by: Liu Ping Fan pingf...@linux.vnet.ibm.com
---
net/hub.c | 27 ++-
1 files changed, 26 insertions(+), 1 deletions(-)
diff --git a/net/hub.c b/net/hub.c
index 73c1f26..47fe72c 100644
--- a/net/hub.c
+++ b/net
From: Liu Ping Fan pingf...@linux.vnet.ibm.com
Signed-off-by: Liu Ping Fan pingf...@linux.vnet.ibm.com
---
net/queue.c | 11 +++
1 files changed, 11 insertions(+), 0 deletions(-)
diff --git a/net/queue.c b/net/queue.c
index 67959f8..f7ff020 100644
--- a/net/queue.c
+++ b/net/queue.c
From: Liu Ping Fan pingf...@linux.vnet.ibm.com
Introduce nc-send_lock, it shield off the race of nc-peer's reader and
deleter. With it, after deleter finish, no new qemu_send_packet_xx()
can reach -send_queue, so no new reference(packet-sender) to nc will
be appended to nc-peer-send_queue
From: Liu Ping Fan pingf...@linux.vnet.ibm.com
With refcnt, NetClientState's caller can run agaist reclaimer.
Signed-off-by: Liu Ping Fan pingf...@linux.vnet.ibm.com
---
hw/qdev-properties-system.c | 14 +
include/net/net.h |3 ++
net/hub.c |3
On Mon, Mar 4, 2013 at 11:04 PM, Paolo Bonzini pbonz...@redhat.com wrote:
Il 04/03/2013 15:49, Stefan Hajnoczi ha scritto:
Use nc-transfer_lock to protect the nc-peer-send_queue. All of the
Please use consistent names: the lock protects -send_queue so it's best
called send_queue_lock or
On Mon, Mar 4, 2013 at 10:49 PM, Stefan Hajnoczi stefa...@gmail.com wrote:
On Sun, Mar 03, 2013 at 09:21:21PM +0800, Liu Ping Fan wrote:
From: Liu Ping Fan pingf...@linux.vnet.ibm.com
Use nc-transfer_lock to protect the nc-peer-send_queue. All of the
Please use consistent names: the lock
On Mon, Mar 4, 2013 at 10:35 PM, Stefan Hajnoczi stefa...@gmail.com wrote:
On Sun, Mar 03, 2013 at 09:21:20PM +0800, Liu Ping Fan wrote:
@@ -44,6 +47,7 @@ typedef ssize_t (NetReceiveIOV)(NetClientState *, const
struct iovec *, int);
typedef void (NetCleanup) (NetClientState *);
typedef
On Mon, Mar 4, 2013 at 11:19 PM, Stefan Hajnoczi stefa...@gmail.com wrote:
On Sun, Mar 03, 2013 at 09:21:22PM +0800, Liu Ping Fan wrote:
diff --git a/net/hub.c b/net/hub.c
index 97c3ac3..ab4448e 100644
--- a/net/hub.c
+++ b/net/hub.c
@@ -36,6 +36,7 @@ typedef struct NetHubPort
On Tue, Mar 5, 2013 at 10:45 AM, liu ping fan qemul...@gmail.com wrote:
On Mon, Mar 4, 2013 at 10:49 PM, Stefan Hajnoczi stefa...@gmail.com wrote:
On Sun, Mar 03, 2013 at 09:21:21PM +0800, Liu Ping Fan wrote:
From: Liu Ping Fan pingf...@linux.vnet.ibm.com
Use nc-transfer_lock to protect
From: Liu Ping Fan pingf...@linux.vnet.ibm.com
This series aim to make netlayer re-entrant, so netlayer can
run out of biglock safely.
Liu Ping Fan (3):
net: spread hub on AioContexts
net: introduce lock to protect NetClientState's send_queue
net: make netclient re-entrant with refcnt
hw
From: Liu Ping Fan pingf...@linux.vnet.ibm.com
Forward packet to other hub ports by their AioContext.
Signed-off-by: Liu Ping Fan pingf...@linux.vnet.ibm.com
---
hw/qdev-properties-system.c |1 +
include/block/aio.h |1 +
include/net/net.h |5 +
include/net
From: Liu Ping Fan pingf...@linux.vnet.ibm.com
Use nc-transfer_lock to protect the nc-peer-send_queue. All of the
deleter and senders will sync on this lock, so we can also survive across
unplug.
Signed-off-by: Liu Ping Fan pingf...@linux.vnet.ibm.com
---
include/net/net.h |4 +++
include
From: Liu Ping Fan pingf...@linux.vnet.ibm.com
With refcnt, NetClientState's caller can run agaist reclaimer.
Signed-off-by: Liu Ping Fan pingf...@linux.vnet.ibm.com
---
hw/qdev-properties-system.c | 14 ++
include/net/net.h |3 +++
net/hub.c | 29
On Fri, Feb 22, 2013 at 4:55 AM, mdroth mdr...@linux.vnet.ibm.com wrote:
On Thu, Feb 21, 2013 at 08:54:50PM +0800, Liu Ping Fan wrote:
From: Liu Ping Fan pingf...@linux.vnet.ibm.com
This is a emulation to virtio-blk dataplane, which push the data
handling out of biglock. And it is a try
On Tue, Feb 26, 2013 at 1:53 AM, Paolo Bonzini pbonz...@redhat.com wrote:
Il 25/02/2013 18:35, mdroth ha scritto:
Moving more of the os_host_main_loop_wait to AioContext would be
possible (timers are on the todo list, in fact), but we should only do
it as need arises.
Were you planning on
+0800, Liu Ping Fan wrote:
This is a emulation to virtio-blk dataplane, which push the data
handling out of biglock. And it is a try to implement this process
in userspace, while vhost-net in kernel.
What's the motivation for doing this?
I haven't looked carefully at the patches
From: Liu Ping Fan pingf...@linux.vnet.ibm.com
Re-initialize the members of vring correctly is required when
restored from img.
Signed-off-by: Liu Ping Fan pingf...@linux.vnet.ibm.com
---
hw/dataplane/vring.c |6 ++
hw/dataplane/vring.h |1 +
2 files changed, 7 insertions(+), 0
From: Liu Ping Fan pingf...@linux.vnet.ibm.com
When event poll can work with normal fd, we can port them
onto the event loop.
Signed-off-by: Liu Ping Fan pingf...@linux.vnet.ibm.com
---
hw/dataplane/event-poll.c | 36
hw/dataplane/event-poll.h |8
From: Liu Ping Fan pingf...@linux.vnet.ibm.com
With this extra arg -- event type, we can support the standard
events dispatched by epoll_wait()
Signed-off-by: Liu Ping Fan pingf...@linux.vnet.ibm.com
---
hw/dataplane/event-poll.c |4 ++--
hw/dataplane/event-poll.h |2 +-
hw/dataplane
From: Liu Ping Fan pingf...@linux.vnet.ibm.com
This is a emulation to virtio-blk dataplane, which push the data
handling out of biglock. And it is a try to implement this process
in userspace, while vhost-net in kernel.
Signed-off-by: Liu Ping Fan pingf...@linux.vnet.ibm.com
---
hw/dataplane
From: Liu Ping Fan pingf...@linux.vnet.ibm.com
Signed-off-by: Liu Ping Fan pingf...@linux.vnet.ibm.com
---
hw/virtio-net.c | 38 ++
hw/virtio-net.h |3 +++
hw/virtio-pci.c |2 +-
3 files changed, 42 insertions(+), 1 deletions(-)
diff --git a/hw
optimized).
Todo:
implement fine lock for net-subsystem
Liu Ping Fan (9):
vring: split the modification and publish of used ring
vring: introduce vring_restore() to restore from img
event poll: make epoll work for normal fd
event poll: pass event type to event callback
event poll: enable
From: Liu Ping Fan pingf...@linux.vnet.ibm.com
Signed-off-by: Liu Ping Fan pingf...@linux.vnet.ibm.com
---
hw/dataplane/virtio-net.c | 22 +++
hw/dataplane/virtio-net.h |6 +++
include/net/tap.h |6 +++
net/tap.c | 92
From: Liu Ping Fan pingf...@linux.vnet.ibm.com
Currently, vring_push() modify used ring and publish it, but
sometime, we need to gather the changes and publish them all
at once. So introduce vring_fill(), vring_flush().
Signed-off-by: Liu Ping Fan pingf...@linux.vnet.ibm.com
---
hw/dataplane
From: Liu Ping Fan pingf...@linux.vnet.ibm.com
Set handled event count at initialized time for the dedicated
thread.
Signed-off-by: Liu Ping Fan pingf...@linux.vnet.ibm.com
---
hw/dataplane/event-poll.c | 31 ++-
hw/dataplane/event-poll.h |4 +++-
hw/dataplane
From: Liu Ping Fan pingf...@linux.vnet.ibm.com
Signed-off-by: Liu Ping Fan pingf...@linux.vnet.ibm.com
---
configure | 12
hw/dataplane/Makefile.objs |4 +++-
2 files changed, 15 insertions(+), 1 deletions(-)
diff --git a/configure b/configure
index 837a84a
Hi Jan and Cam,
It has been tested with uio driver. And other opinion for the code?
Regards,
Pingfan
On Thu, Dec 6, 2012 at 2:37 PM, Liu Ping Fan qemul...@gmail.com wrote:
From: Liu Ping Fan pingf...@linux.vnet.ibm.com
Using irqfd, so we can avoid switch between kernel and user when
VMs
On Thu, Dec 6, 2012 at 4:47 AM, Stefan Hajnoczi stefa...@redhat.com wrote:
The data plane thread needs to map guest physical addresses to host
pointers. Normally this is done with cpu_physical_memory_map() but the
function assumes the global mutex is held. The data plane thread does
not
On Thu, Dec 6, 2012 at 1:10 PM, Cam Macdonell c...@cs.ualberta.ca wrote:
On Wed, Dec 5, 2012 at 1:50 AM, Jan Kiszka jan.kis...@siemens.com wrote:
On 2012-12-05 06:34, Cam Macdonell wrote:
static void ivshmem_write_config(PCIDevice *pci_dev, uint32_t address,
From: Liu Ping Fan pingf...@linux.vnet.ibm.com
This logic has been integrated into pci core, so remove it.
Signed-off-by: Liu Ping Fan pingf...@linux.vnet.ibm.com
Signed-off-by: Cam Macdonell c...@cs.ualberta.ca
---
hw/ivshmem.c |1 -
1 files changed, 0 insertions(+), 1 deletions(-)
diff
From: Liu Ping Fan pingf...@linux.vnet.ibm.com
Using irqfd, so we can avoid switch between kernel and user when
VMs interrupts each other.
Signed-off-by: Liu Ping Fan pingf...@linux.vnet.ibm.com
Signed-off-by: Cam Macdonell c...@cs.ualberta.ca
---
hw/ivshmem.c | 54
Any suggestion? Or new design idea for this?
Thanks
Pingfan
On Sun, Nov 25, 2012 at 10:02 AM, Liu Ping Fan qemul...@gmail.com wrote:
From: Liu Ping Fan pingf...@linux.vnet.ibm.com
v1:
https://lists.gnu.org/archive/html/qemu-devel/2012-07/msg03312.html
v2:
http://lists.gnu.org/archive/html
On Thu, Nov 29, 2012 at 12:42 PM, Cam Macdonell c...@cs.ualberta.ca wrote:
On Tue, Nov 27, 2012 at 7:53 PM, liu ping fan qemul...@gmail.com wrote:
On Wed, Nov 28, 2012 at 5:48 AM, Cam Macdonell c...@cs.ualberta.ca wrote:
On Sat, Nov 24, 2012 at 8:51 PM, Liu Ping Fan qemul...@gmail.com wrote
On Thu, Nov 29, 2012 at 1:16 AM, Richard Henderson r...@twiddle.net wrote:
On 11/24/2012 06:02 PM, Liu Ping Fan wrote:
-obj-ref--;
/* parent always holds a reference to its children */
-if (obj-ref == 0) {
+if (__sync_fetch_and_sub(obj-ref, 1) == 1
ping?
On Sun, Nov 25, 2012 at 11:51 AM, Liu Ping Fan qemul...@gmail.com wrote:
From: Liu Ping Fan pingf...@linux.vnet.ibm.com
This logic has been integrated into pci core, so remove it.
Signed-off-by: Liu Ping Fan pingf...@linux.vnet.ibm.com
---
hw/ivshmem.c |1 -
1 files changed, 0
On Wed, Nov 28, 2012 at 5:48 AM, Cam Macdonell c...@cs.ualberta.ca wrote:
On Sat, Nov 24, 2012 at 8:51 PM, Liu Ping Fan qemul...@gmail.com wrote:
From: Liu Ping Fan pingf...@linux.vnet.ibm.com
Using irqfd, so we can avoid switch between kernel and user when
VMs interrupts each other.
Nice
From: Liu Ping Fan pingf...@linux.vnet.ibm.com
v1:
https://lists.gnu.org/archive/html/qemu-devel/2012-07/msg03312.html
v2:
http://lists.gnu.org/archive/html/qemu-devel/2012-08/msg01275.html
v3:
http://lists.nongnu.org/archive/html/qemu-devel/2012-09/msg01474.html
v4:
http://lists.gnu.org
From: Liu Ping Fan pingf...@linux.vnet.ibm.com
Signed-off-by: Liu Ping Fan pingf...@linux.vnet.ibm.com
---
qom/object.c |5 ++---
1 files changed, 2 insertions(+), 3 deletions(-)
diff --git a/qom/object.c b/qom/object.c
index e3e9242..1a697b3 100644
--- a/qom/object.c
+++ b/qom/object.c
From: Liu Ping Fan pingf...@linux.vnet.ibm.com
When device unplug has been ack by guest, we first remove it from memory
to prevent incoming access from dispatcher. Then we isolate it from
device composition tree
Signed-off-by: Liu Ping Fan pingf...@linux.vnet.ibm.com
---
hw/qdev.c | 26
From: Liu Ping Fan pingf...@linux.vnet.ibm.com
Signed-off-by: Liu Ping Fan pingf...@linux.vnet.ibm.com
---
hw/acpi_piix4.c |2 +-
hw/pci.c| 13 -
hw/pci.h|1 +
3 files changed, 14 insertions(+), 2 deletions(-)
diff --git a/hw/acpi_piix4.c b/hw/acpi_piix4.c
From: Liu Ping Fan pingf...@linux.vnet.ibm.com
For those address spaces which want to be able out of big lock, they
will be protected by their own local.
Signed-off-by: Liu Ping Fan pingf...@linux.vnet.ibm.com
---
memory.c |1 +
memory.h |3 +++
2 files changed, 4 insertions(+), 0
From: Liu Ping Fan pingf...@linux.vnet.ibm.com
Without biglock, we try to protect the mr by increase refcnt.
If we cannot inc refcnt, go backward and resort to biglock.
Another point is memory radix-tree can be flushed by another
thread, so we should get the copy of terminal mr to survive
from
From: Liu Ping Fan pingf...@linux.vnet.ibm.com
After breaking down big lock, nested MMIO request which not targeting
at RAM can cause deadlock issue. Supposing the scene: dev_a,b with
fine-grain locks lockA/B, then ABBA dealock issue can be triggered.
We fix this by tracing and rejecting
From: Liu Ping Fan pingf...@linux.vnet.ibm.com
To anti the recursive big lock, introduce separate interfaces to allow
address space dispatcher called with/without big lock.
Signed-off-by: Liu Ping Fan pingf...@linux.vnet.ibm.com
---
cpu-common.h |3 +++
exec.c | 21
From: Liu Ping Fan pingf...@linux.vnet.ibm.com
This logic has been integrated into pci core, so remove it.
Signed-off-by: Liu Ping Fan pingf...@linux.vnet.ibm.com
---
hw/ivshmem.c |1 -
1 files changed, 0 insertions(+), 1 deletions(-)
diff --git a/hw/ivshmem.c b/hw/ivshmem.c
index f6dbb21
From: Liu Ping Fan pingf...@linux.vnet.ibm.com
Using irqfd, so we can avoid switch between kernel and user when
VMs interrupts each other.
Signed-off-by: Liu Ping Fan pingf...@linux.vnet.ibm.com
---
hw/ivshmem.c | 54 +-
1 files changed, 53
On Thu, Nov 22, 2012 at 7:40 PM, Jan Kiszka jan.kis...@siemens.com wrote:
On 2012-11-22 03:48, liu ping fan wrote:
On Wed, Nov 21, 2012 at 8:43 PM, Jan Kiszka jan.kis...@siemens.com wrote:
On 2012-11-21 07:02, Liu Ping Fan wrote:
[...]
+static int ivshmem_vector_use(PCIDevice *dev, unsigned
On Wed, Nov 21, 2012 at 8:43 PM, Jan Kiszka jan.kis...@siemens.com wrote:
On 2012-11-21 07:02, Liu Ping Fan wrote:
From: Liu Ping Fan pingf...@linux.vnet.ibm.com
Using irqfd, so we can avoid switch between kernel and user when
VMs interrupts each other.
Signed-off-by: Liu Ping Fan pingf
On Sun, Nov 18, 2012 at 6:04 PM, Avi Kivity a...@redhat.com wrote:
On 11/15/2012 09:47 AM, liu ping fan wrote:
On Wed, Nov 14, 2012 at 5:47 PM, Paolo Bonzini pbonz...@redhat.com wrote:
Il 14/11/2012 10:38, liu ping fan ha scritto:
On Tue, Nov 13, 2012 at 6:11 PM, Paolo Bonzini pbonz
On Fri, Nov 16, 2012 at 8:03 AM, Richard Henderson r...@twiddle.net wrote:
On 2012-11-14 23:47, liu ping fan wrote:
Probably I made a mistake here, in vhost, log =
__sync_fetch_and_and(from, 0) is used to fetch 64bits atomically in
the case 32bits qemu running on 64bits linux. Right
From: Liu Ping Fan pingf...@linux.vnet.ibm.com
Using irqfd, so we can avoid switch between kernel and user when
VMs interrupts each other.
Signed-off-by: Liu Ping Fan pingf...@linux.vnet.ibm.com
---
hw/ivshmem.c | 48 +++-
1 files changed, 47
On Tue, Nov 13, 2012 at 6:11 PM, Paolo Bonzini pbonz...@redhat.com wrote:
Il 05/11/2012 06:38, Liu Ping Fan ha scritto:
From: Liu Ping Fan pingf...@linux.vnet.ibm.com
If out of global lock, we will be challenged by SMP in low level,
so need atomic ops.
This file is a wrapper
On Wed, Nov 14, 2012 at 5:47 PM, Paolo Bonzini pbonz...@redhat.com wrote:
Il 14/11/2012 10:38, liu ping fan ha scritto:
On Tue, Nov 13, 2012 at 6:11 PM, Paolo Bonzini pbonz...@redhat.com wrote:
Il 05/11/2012 06:38, Liu Ping Fan ha scritto:
From: Liu Ping Fan pingf...@linux.vnet.ibm.com
On Mon, Nov 12, 2012 at 4:48 PM, Paolo Bonzini pbonz...@redhat.com wrote:
Il 12/11/2012 07:22, liu ping fan ha scritto:
On Sat, Nov 10, 2012 at 9:54 AM, Paolo Bonzini pbonz...@redhat.com wrote:
Il 09/11/2012 04:14, Liu Ping Fan ha scritto:
From: Liu Ping Fan pingf...@linux.vnet.ibm.com
On Mon, Nov 12, 2012 at 5:27 PM, Paolo Bonzini pbonz...@redhat.com wrote:
Il 05/11/2012 06:38, Liu Ping Fan ha scritto:
+void qdev_unplug_complete(DeviceState *dev, Error **errp)
+{
+/* isolate from mem view */
+qdev_unmap(dev);
+/* isolate from device tree
On Mon, Nov 12, 2012 at 5:54 PM, Paolo Bonzini pbonz...@redhat.com wrote:
Il 05/11/2012 06:38, Liu Ping Fan ha scritto:
From: Liu Ping Fan pingf...@linux.vnet.ibm.com
If out of global lock, we will be challenged by SMP in low level,
so need atomic ops.
This file is a wrapper of GCC atomic
On Sat, Nov 10, 2012 at 9:54 AM, Paolo Bonzini pbonz...@redhat.com wrote:
Il 09/11/2012 04:14, Liu Ping Fan ha scritto:
From: Liu Ping Fan pingf...@linux.vnet.ibm.com
Signed-off-by: Liu Ping Fan pingf...@linux.vnet.ibm.com
---
cpu-all.h |1 +
exec.c| 46
On Sat, Nov 10, 2012 at 9:49 AM, Paolo Bonzini pbonz...@redhat.com wrote:
Il 09/11/2012 04:14, Liu Ping Fan ha scritto:
From: Liu Ping Fan pingf...@linux.vnet.ibm.com
Signed-off-by: Liu Ping Fan pingf...@linux.vnet.ibm.com
---
exec.c | 21 +
1 files changed, 13
From: Liu Ping Fan pingf...@linux.vnet.ibm.com
No access google.
For background, please refer to discussion for [RFC PATCH v3 05/19] Implement
dimm device abstraction
Liu Ping Fan (3):
bouce buffer has fine grain lock
ramlist: apply fine grain lock for ram_list
make address_space_map
From: Liu Ping Fan pingf...@linux.vnet.ibm.com
Signed-off-by: Liu Ping Fan pingf...@linux.vnet.ibm.com
---
exec.c | 21 +
1 files changed, 13 insertions(+), 8 deletions(-)
diff --git a/exec.c b/exec.c
index 73d5242..fe84718 100644
--- a/exec.c
+++ b/exec.c
@@ -3296,6
From: Liu Ping Fan pingf...@linux.vnet.ibm.com
Signed-off-by: Liu Ping Fan pingf...@linux.vnet.ibm.com
---
cpu-all.h |1 +
exec.c| 46 +++---
2 files changed, 40 insertions(+), 7 deletions(-)
diff --git a/cpu-all.h b/cpu-all.h
index 6aa7e58
From: Liu Ping Fan pingf...@linux.vnet.ibm.com
Signed-off-by: Liu Ping Fan pingf...@linux.vnet.ibm.com
---
cpu-common.h |8 ++--
cputlb.c |4 ++--
dma-helpers.c |4 +++-
dma.h |5 -
exec.c| 45
Ping? Any further comments?
Thanks and regards,
Pingfan
On Mon, Nov 5, 2012 at 3:00 PM, Jan Kiszka jan.kis...@web.de wrote:
On 2012-11-05 06:38, Liu Ping Fan wrote:
From: Liu Ping Fan pingf...@linux.vnet.ibm.com
v1:
https://lists.gnu.org/archive/html/qemu-devel/2012-07/msg03312.html
v2
On Mon, Oct 29, 2012 at 4:51 PM, Paolo Bonzini pbonz...@redhat.com wrote:
Il 29/10/2012 00:48, Liu Ping Fan ha scritto:
Signed-off-by: Liu Ping Fan pingf...@linux.vnet.ibm.com
---
cpus.c|3 ++
exec.c| 58
+
qemu
On Fri, Nov 2, 2012 at 6:39 PM, Jan Kiszka jan.kis...@siemens.com wrote:
On 2012-10-29 00:48, Liu Ping Fan wrote:
Signed-off-by: Liu Ping Fan pingf...@linux.vnet.ibm.com
---
cpus.c|3 ++
exec.c| 58
+
qemu
From: Liu Ping Fan pingf...@linux.vnet.ibm.com
v1:
https://lists.gnu.org/archive/html/qemu-devel/2012-07/msg03312.html
v2:
http://lists.gnu.org/archive/html/qemu-devel/2012-08/msg01275.html
v3:
http://lists.nongnu.org/archive/html/qemu-devel/2012-09/msg01474.html
v4:
http://lists.gnu.org
401 - 500 of 750 matches
Mail list logo
