On Sat, Oct 03, 2015 at 07:33:16PM +0300, Michael S. Tsirkin wrote:
> On Fri, Oct 02, 2015 at 06:18:51PM +0200, Paolo Bonzini wrote:
> >
> >
> > On 24/09/2015 15:20, Michael S. Tsirkin wrote:
> > > From: Yuanhan Liu
> > >
> > > Quote from M
On Thu, Nov 05, 2015 at 11:42:15AM +, Peter Maydell wrote:
> On 3 October 2015 at 17:33, Michael S. Tsirkin wrote:
> > On Fri, Oct 02, 2015 at 06:18:51PM +0200, Paolo Bonzini wrote:
> >>
> >>
> >> On 24/09/2015 15:20, Michael S. Tsirkin wrote:
> >
On Fri, Nov 06, 2015 at 10:01:58AM +, Peter Maydell wrote:
> On 6 November 2015 at 01:34, Yuanhan Liu wrote:
> > On Thu, Nov 05, 2015 at 11:42:15AM +, Peter Maydell wrote:
> >> On 3 October 2015 at 17:33, Michael S. Tsirkin wrote:
> >> > On Fri, Oct 02, 2
Thanks.
Reviewed-by: Yuanhan Liu
--yliu
On Wed, Nov 11, 2015 at 02:53:29PM +0800, Wen Congyang wrote:
> Signed-off-by: Wen Congyang
> ---
> net/vhost-user.c | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/net/vhost-user.c b/net/vh
Signed-off-by: Yuanhan Liu
---
hw/virtio/vhost-user.c| 7 +++
include/hw/virtio/vhost-backend.h | 6 ++
2 files changed, 13 insertions(+)
diff --git a/hw/virtio/vhost-user.c b/hw/virtio/vhost-user.c
index 4766f98..2d8bdbd 100644
--- a/hw/virtio/vhost-user.c
+++ b/hw/virtio
When a virtio net driver is unloaded (unbind), virtio_net_reset happens.
For vhost net, we should also send a message (RESET_OWNER) to the backend
to do some proper reset settings.
Signed-off-by: Yuanhan Liu
---
hw/net/vhost_net.c | 20 ++--
hw/net/virtio-net.c | 14
This patch basically reverts commit d1f8b30e.
It turned out that it breaks stuff, so revert it:
http://lists.nongnu.org/archive/html/qemu-devel/2015-10/msg00949.html
CC: "Michael S. Tsirkin"
Reported-by: Paolo Bonzini
Signed-off-by: Yuanhan Liu
---
docs/specs/vhost-user
to send this version.
---
Yuanhan Liu (5):
vhost: rename RESET_DEVICE backto RESET_OWNER
vhost: reset vhost net when virtio_net_reset happens
vhost: introduce vhost_set/get_protocol_features callbacks
vhost: send SET_PROTOCOL_FEATURES at start
vhost: send SET_VRING_ENABLE at start/stop
docs/
So that the backend can restore the protocol features after a reset.
Signed-off-by: Yuanhan Liu
---
hw/virtio/vhost.c | 8
1 file changed, 8 insertions(+)
diff --git a/hw/virtio/vhost.c b/hw/virtio/vhost.c
index de29968..be48511 100644
--- a/hw/virtio/vhost.c
+++ b/hw/virtio/vhost.c
Send SET_VRING_ENABLE at start/stop, to give the backend
an explicit sign of our state.
Signed-off-by: Yuanhan Liu
---
hw/virtio/vhost.c | 9 +
1 file changed, 9 insertions(+)
diff --git a/hw/virtio/vhost.c b/hw/virtio/vhost.c
index be48511..0e956b5 100644
--- a/hw/virtio/vhost.c
+++ b
On Thu, Nov 12, 2015 at 03:33:41PM +0200, Michael S. Tsirkin wrote:
> On Wed, Nov 11, 2015 at 09:24:36PM +0800, Yuanhan Liu wrote:
> >
> > Patch 1 rename RESET_DEVICE back to RESET_OWNER
> >
> > Patch 2 introduced a new function: vhost_net_reset(), which is invoked
>
On Thu, Nov 12, 2015 at 04:44:19PM +0200, Michael S. Tsirkin wrote:
> On Thu, Nov 12, 2015 at 10:08:15PM +0800, Yuanhan Liu wrote:
> > On Thu, Nov 12, 2015 at 03:33:41PM +0200, Michael S. Tsirkin wrote:
> > > On Wed, Nov 11, 2015 at 09:24:36PM +0800, Yuanhan Liu wrote:
> &
First of all, RESET_OWNER message is sent incorrectly, as it's sent
before GET_VRING_BASE. And the reset message would let the later call
get nothing correct.
And, sending SET_VRING_ENABLE at stop, which has already been done,
makes more sense than RESET_OWNER.
Signed-off-by: Yuanha
But not depend on PROTOCOL_F_MQ feature bit. So that we could use
SET_VRING_ENABLE to sign the backend on stop, even if MQ is disabled.
That's reasonable, since we will have one queue pair at least.
Signed-off-by: Yuanhan Liu
---
hw/virtio/vhost-user.c | 2 +-
1 file changed, 1 insertion(
On Fri, Nov 13, 2015 at 12:24:52PM +0200, Michael S. Tsirkin wrote:
> On Fri, Nov 13, 2015 at 10:03:29AM +0800, Yuanhan Liu wrote:
> > On Thu, Nov 12, 2015 at 04:44:19PM +0200, Michael S. Tsirkin wrote:
> > > On Thu, Nov 12, 2015 at 10:08:15PM +0800, Yuanhan Liu wrote:
> >
gt; This is important for MQ, because a Linux guest expects TX
> packets to be completed even if it disables some queues
> temporarily.
Thanks for the clarification. And
Reviewed-by: Yuanhan Liu
--yliu
>
> Cc: Yuanhan Liu
> Cc: Victor Kaplansky
> Signed-off-by: Michae
On Tue, Nov 24, 2015 at 11:23:34PM +0200, Michael S. Tsirkin wrote:
> On Tue, Nov 24, 2015 at 10:05:27PM +0100, Thibaut Collet wrote:
> > On Tue, Nov 24, 2015 at 9:52 PM, Michael S. Tsirkin wrote:
> > > On Tue, Nov 24, 2015 at 05:10:36PM +0100, Thibaut Collet wrote:
> > >> This patch reverts parti
d is
> wrong.
Reviewed-by: Yuanhan Liu
BTW, we should also update the spec about ring stop, right?
--yliu
>
> Reported-by: Thibaut Collet
> Cc: Yuanhan Liu
> Signed-off-by: Michael S. Tsirkin
> ---
> hw/virtio/vhost.c | 9 -
> 1 file changed, 9 deletions(-)
On Thu, Nov 26, 2015 at 06:52:56PM +0200, Michael S. Tsirkin wrote:
> On Thu, Nov 26, 2015 at 09:46:08AM +0800, Yuanhan Liu wrote:
> > On Wed, Nov 25, 2015 at 02:42:05PM +0200, Michael S. Tsirkin wrote:
> > > This reverts commit 3a12f32229a046f4d4ab0a3a52fb01d2d5a1ab76.
>
On Wed, Dec 02, 2015 at 01:50:35PM +0200, Michael S. Tsirkin wrote:
> We dropped the implementation of vhost_dev_query,
> drop it from the header file as well.
>
> Signed-off-by: Michael S. Tsirkin
Reviewed-by: Yuanhan Liu
--yliu
> ---
> include/hw/virtio/vhost
Setting VHOST_USER_PROTOCOL_F_MQ protocol feature bit to claim that we
support MQ feature, and simply assume we support 2 queue pairs at most.
Cc: Michael S. Tsirkin
Cc: Jason Wang
Signed-off-by: Yuanhan Liu
---
tests/vhost-user-test.c | 18 --
1 file changed, 16 insertions
They are VHOST_USER_XXX instead of VHOST_XXX messages.
Also, add VHOST_USER_GET_QUEUE_NUM to the section that
requries replies.
Cc: Michael S. Tsirkin
Signed-off-by: Yuanhan Liu
---
docs/specs/vhost-user.txt | 17 +
1 file changed, 9 insertions(+), 8 deletions(-)
diff --git a
This reverts commit d1f8b30ec8dde0318fd1b98d24a64926feae9625.
It turned out that it breaks stuff, so revert it:
http://lists.nongnu.org/archive/html/qemu-devel/2015-10/msg00949.html
CC: "Michael S. Tsirkin"
Reported-by: Paolo Bonzini
Signed-off-by: Yuanhan Liu
---
docs/s
On Fri, Oct 16, 2015 at 10:21:40AM +0300, Michael S. Tsirkin wrote:
> On Fri, Oct 16, 2015 at 03:18:59PM +0800, Yuanhan Liu wrote:
> > This reverts commit d1f8b30ec8dde0318fd1b98d24a64926feae9625.
> >
> > It turned out that it breaks stuff, so revert it:
> >
>
On Fri, Oct 16, 2015 at 10:20:08AM +0300, Michael S. Tsirkin wrote:
> On Fri, Oct 16, 2015 at 03:19:01PM +0800, Yuanhan Liu wrote:
> > Setting VHOST_USER_PROTOCOL_F_MQ protocol feature bit to claim that we
> > support MQ feature, and simply assume we support 2 queue pairs at
On Fri, Oct 16, 2015 at 10:47:49AM +0300, Michael S. Tsirkin wrote:
> On Fri, Oct 16, 2015 at 03:32:56PM +0800, Yuanhan Liu wrote:
> > On Fri, Oct 16, 2015 at 10:21:40AM +0300, Michael S. Tsirkin wrote:
> > > On Fri, Oct 16, 2015 at 03:18:59PM +0800, Yuanhan Liu wrote:
> >
On Fri, Oct 16, 2015 at 11:15:23AM +0300, Michael S. Tsirkin wrote:
> On Fri, Oct 16, 2015 at 04:04:09PM +0800, Yuanhan Liu wrote:
> > On Fri, Oct 16, 2015 at 10:47:49AM +0300, Michael S. Tsirkin wrote:
> > > On Fri, Oct 16, 2015 at 03:32:56PM +0800, Yuanhan Liu wrote:
> >
Setting VHOST_USER_PROTOCOL_F_MQ protocol feature bit to claim that we
support MQ feature, and simply assume we support 0xff queue pairs at most.
Cc: Michael S. Tsirkin
Cc: Jason Wang
Signed-off-by: Yuanhan Liu
---
v2: use macro to define the max queues we support
---
tests/vhost-user-test.c
They are VHOST_USER_XXX instead of VHOST_XXX messages.
Also, add VHOST_USER_GET_QUEUE_NUM to the section that
requries replies.
Cc: Michael S. Tsirkin
Signed-off-by: Yuanhan Liu
---
docs/specs/vhost-user.txt | 17 +
1 file changed, 9 insertions(+), 8 deletions(-)
diff --git a
This reverts commit d1f8b30ec8dde0318fd1b98d24a64926feae9625.
It turned out that it breaks stuff, so revert it:
http://lists.nongnu.org/archive/html/qemu-devel/2015-10/msg00949.html
CC: "Michael S. Tsirkin"
Reported-by: Paolo Bonzini
Signed-off-by: Yuanhan Liu
---
docs/s
ned-off-by: Yuanhan Liu
---
hw/net/vhost_net.c | 7 ---
1 file changed, 7 deletions(-)
diff --git a/hw/net/vhost_net.c b/hw/net/vhost_net.c
index 804f5c9..95da5f8 100644
--- a/hw/net/vhost_net.c
+++ b/hw/net/vhost_net.c
@@ -293,13 +293,6 @@ static void vhost_net_stop_one(struct vhos
Send VHOST_USER_SET_VRING_ENABLE at start/stop when multiple queue
is negotiated, to inform the backend that we are ready or not.
And exclude VHOST_USER_GET_QUEUE_NUM as one time request, as we need
to get max_queues for each vhost_dev.
Suggested-by: Michael S. Tsirkin
Signed-off-by: Yuanhan
On Fri, Oct 16, 2015 at 10:47:49AM +0300, Michael S. Tsirkin wrote:
> On Fri, Oct 16, 2015 at 03:32:56PM +0800, Yuanhan Liu wrote:
> > On Fri, Oct 16, 2015 at 10:21:40AM +0300, Michael S. Tsirkin wrote:
> > > On Fri, Oct 16, 2015 at 03:18:59PM +0800, Yuanhan Liu wrote:
> >
On Wed, Oct 21, 2015 at 12:15:52PM +0300, Michael S. Tsirkin wrote:
> On Wed, Oct 21, 2015 at 04:55:16PM +0800, Yuanhan Liu wrote:
> > On Fri, Oct 16, 2015 at 10:47:49AM +0300, Michael S. Tsirkin wrote:
> > > On Fri, Oct 16, 2015 at 03:32:56PM +0800, Yuanhan Liu wrote:
> >
On Wed, Oct 21, 2015 at 01:40:59PM +0300, Michael S. Tsirkin wrote:
> On Wed, Oct 21, 2015 at 05:07:14PM +0800, Yuanhan Liu wrote:
> > This reverts commit d1f8b30ec8dde0318fd1b98d24a64926feae9625.
> >
> > It turned out that it breaks stuff, so revert it:
> >
>
On Wed, Oct 21, 2015 at 01:39:11PM +0300, Michael S. Tsirkin wrote:
> On Wed, Oct 21, 2015 at 05:07:18PM +0800, Yuanhan Liu wrote:
> > Send VHOST_USER_SET_VRING_ENABLE at start/stop when multiple queue
> > is negotiated, to inform the backend that we are ready or not.
>
> OK
On Wed, Oct 21, 2015 at 05:13:49PM +0300, Michael S. Tsirkin wrote:
> On Wed, Oct 21, 2015 at 09:04:17PM +0800, Yuanhan Liu wrote:
> > On Wed, Oct 21, 2015 at 01:40:59PM +0300, Michael S. Tsirkin wrote:
> > > On Wed, Oct 21, 2015 at 05:07:14PM +0800, Yuanhan Liu wrote:
> >
On Wed, Oct 21, 2015 at 05:11:44PM +0300, Michael S. Tsirkin wrote:
> On Wed, Oct 21, 2015 at 09:43:16PM +0800, Yuanhan Liu wrote:
> > On Wed, Oct 21, 2015 at 01:39:11PM +0300, Michael S. Tsirkin wrote:
> > > On Wed, Oct 21, 2015 at 05:07:18PM +0800, Yuanhan Liu w
later.
Patch 2 is a minor fix or request naming in vhost-user spec
Patch 3 adds the vhost-user mq unit test
---
Yuanhan Liu (3):
vhost: rename VHOST_RESET_DEVICE back to VHOST_RESET_OWNER
doc: vhost-user: request naming fix
vhost-user-test: add multiple queue test
docs/specs/vhost-user.txt
Setting VHOST_USER_PROTOCOL_F_MQ protocol feature bit to claim that we
support MQ feature, and simply assume we support 2 queue pairs at most.
Cc: Michael S. Tsirkin
Cc: Jason Wang
Signed-off-by: Yuanhan Liu
---
tests/vhost-user-test.c | 23 +--
1 file changed, 21
They are VHOST_USER_XXX instead of VHOST_XXX messages.
Also, add VHOST_USER_GET_QUEUE_NUM to the section that
requries replies.
Cc: Michael S. Tsirkin
Signed-off-by: Yuanhan Liu
---
docs/specs/vhost-user.txt | 21 +++--
1 file changed, 11 insertions(+), 10 deletions(-)
diff
It turned out that it breaks stuff (VHOST_RESET_OWNER is not defined),
so revert it:
http://lists.nongnu.org/archive/html/qemu-devel/2015-10/msg00949.html
CC: "Michael S. Tsirkin"
Reported-by: Paolo Bonzini
Signed-off-by: Yuanhan Liu
---
docs/specs/vhost-user.txt | 4 ++--
On Mon, Sep 14, 2015 at 06:00:41PM +0800, Jason Wang wrote:
>
>
> On 09/08/2015 03:38 PM, Yuanhan Liu wrote:
> > From: Ouyang Changchun
> >
> > This patch is initially based a patch from Nikolay Nikolaev.
> >
> > Here is the latest version for adding vh
y Jason Wang.
Thanks.
--yliu
---
Changchun Ouyang (2):
vhost-user: add multiple queue support
vhost-user: add a new message to disable/enable a specific virt queue.
Michael S. Tsirkin (1):
vhost-user: add protocol feature negotiation
Yuanhan Liu (4):
vhost-user: use VHOST_USER_XXX
Quote from Michael:
We really should rename VHOST_RESET_OWNER to VHOST_RESET_DEVICE.
Suggested-by: Michael S. Tsirkin
Signed-off-by: Yuanhan Liu
---
docs/specs/vhost-user.txt | 4 ++--
hw/net/vhost_net.c | 2 +-
hw/virtio/vhost-user.c | 6 +++---
linux-headers/linux
So that we could let vhost_user_call to handle extented requests,
such as VHOST_USER_GET/SET_PROTOCOL_FEATURES, instead of invoking
vhost_user_read/write and constructing the msg again by ourself.
Signed-off-by: Yuanhan Liu
---
hw/virtio/vhost-user.c | 38
done in the following patch.
Signed-off-by: Yuanhan Liu
---
docs/specs/vhost-user.txt | 11 +++
hw/net/vhost_net.c| 7 +++
hw/virtio/vhost-user.c| 15 ++-
include/hw/virtio/vhost.h | 1 +
include/net/vhost_net.h | 1 +
5 files changed, 34 insertions(+), 1
lue from net->nc->queue_index.
Signed-off-by: Nikolay Nikolaev
Signed-off-by: Changchun Ouyang
Signed-off-by: Yuanhan Liu
---
docs/specs/vhost-user.txt | 13 +
hw/net/vhost_net.c| 10 ++--
hw/virtio/vhost-user.c| 26 +
hw/virtio/vhost.c | 5 +-
ne
tate;
v8: set net->dev.vq_index correctly inside vhost_net_init() based on the
value from net->nc->queue_index.
Signed-off-by: Nikolay Nikolaev
Signed-off-by: Changchun Ouyang
Signed-off-by: Yuanhan Liu
---
docs/specs/vhost-user.txt | 13 +
hw/net/vhost_net.c| 5 +-
hw/v
1 to max virt
queue pair.
Signed-off-by: Changchun Ouyang
Signed-off-by: Yuanhan Liu
---
docs/specs/vhost-user.txt | 12 +++-
hw/net/vhost_net.c| 18 ++
hw/net/virtio-net.c | 8
hw/virtio/vhost-user.c
Minusing the idx with the base(dev->vq_index) for vhost-kernel, and
then adding it back for vhost-user doesn't seem right. Here introduces
a new method vhost_backend_get_vq_index() for getting the right vq
index for following vhost messages calls.
Suggested-by: Jason Wang
Signed-off-by:
From: "Michael S. Tsirkin"
Support a separate bitmask for vhost-user protocol features,
and messages to get/set protocol features.
Invoke them at init.
No features are defined yet.
v2: leverage vhost_user_call for request handling -- Yuanhan Liu
Signed-off-by: Michael S. Tsirkin
On Tue, Sep 15, 2015 at 08:56:05AM -0600, Eric Blake wrote:
> On 09/15/2015 01:10 AM, Yuanhan Liu wrote:
> > From: Changchun Ouyang
> >
> > This patch is initially based a patch from Nikolay Nikolaev.
>
> Subject line confusion - this is titled 1/2, but in reply to
On Tue, Sep 15, 2015 at 09:02:07AM -0600, Eric Blake wrote:
> On 09/15/2015 01:10 AM, Yuanhan Liu wrote:
> > From: Changchun Ouyang
> >
> > This patch is initially based a patch from Nikolay Nikolaev.
> >
> > Here is the latest version for adding vhost-us
On Wed, Sep 16, 2015 at 10:06:56AM +0800, Yuanhan Liu wrote:
> On Tue, Sep 15, 2015 at 09:02:07AM -0600, Eric Blake wrote:
> > On 09/15/2015 01:10 AM, Yuanhan Liu wrote:
> > > From: Changchun Ouyang
> > >
> > > This patch is initially based a patch from Nikola
On Wed, Sep 16, 2015 at 11:12:08AM +0300, Michael S. Tsirkin wrote:
> On Tue, Sep 15, 2015 at 03:10:27PM +0800, Yuanhan Liu wrote:
> > Hi,
> >
> > Here is the updated patch set for enabling vhost-user multiple queue.
>
> Will review, thanks.
Thank you!
> BTW, plea
On Wed, Sep 16, 2015 at 11:10:35AM +0300, Michael S. Tsirkin wrote:
> On Wed, Sep 16, 2015 at 10:06:56AM +0800, Yuanhan Liu wrote:
> > If not, I'd like to put them into the commit log, as putting it
> > outside the commit log gives unnecessary extra burden to patch
> >
On Wed, Sep 16, 2015 at 02:39:06PM +0300, Marcel Apfelbaum wrote:
> On 09/15/2015 10:10 AM, Yuanhan Liu wrote:
> >Hi,
> >
> >Here is the updated patch set for enabling vhost-user multiple queue.
>
> Hi,
>
> I think this series will not work with the current DPDK
On Wed, Sep 16, 2015 at 08:15:59AM -0600, Eric Blake wrote:
> On 09/15/2015 08:06 PM, Yuanhan Liu wrote:
>
> >> Up to here is mostly fine for the commit message. Meanwhile...
> >>
> >>> v9: per suggested by Jason Wang, we could invoke qemu_chr_add_handle
On Thu, Sep 17, 2015 at 03:12:55PM +0800, Jason Wang wrote:
>
>
> On 09/15/2015 03:10 PM, Yuanhan Liu wrote:
> > From: "Michael S. Tsirkin"
> >
> > Support a separate bitmask for vhost-user protocol features,
> > and messages to get/set protocol featur
On Thu, Sep 17, 2015 at 03:23:55PM +0300, Michael S. Tsirkin wrote:
> On Tue, Sep 15, 2015 at 03:10:27PM +0800, Yuanhan Liu wrote:
> > Hi,
> >
> > Here is the updated patch set for enabling vhost-user multiple queue.
> > This patch set introduces
yliu
---
Changchun Ouyang (2):
vhost-user: add multiple queue support
vhost-user: add a new message to disable/enable a specific virt queue.
Michael S. Tsirkin (1):
vhost-user: add protocol feature negotiation
Yuanhan Liu (4):
vhost-user: use VHOST_USER_XXX macro for switch statement
vhos
From: "Michael S. Tsirkin"
Support a separate bitmask for vhost-user protocol features,
and messages to get/set protocol features.
Invoke them at init.
No features are defined yet.
[ leverage vhost_user_call for request handling -- Yuanhan Liu ]
Signed-off-by: Michael S. Tsirkin
Quote from Michael:
We really should rename VHOST_RESET_OWNER to VHOST_RESET_DEVICE.
Suggested-by: Michael S. Tsirkin
Signed-off-by: Yuanhan Liu
---
docs/specs/vhost-user.txt | 4 ++--
hw/net/vhost_net.c | 2 +-
hw/virtio/vhost-user.c | 6 +++---
linux-headers/linux
Minusing the idx with the base(dev->vq_index) for vhost-kernel, and
then adding it back for vhost-user doesn't seem right. Here introduces
a new method vhost_backend_get_vq_index() for getting the right vq
index for following vhost messages calls.
Suggested-by: Jason Wang
Signed-off-by:
done in the following patch.
Signed-off-by: Yuanhan Liu
---
docs/specs/vhost-user.txt | 11 +++
hw/net/vhost_net.c| 7 +++
hw/virtio/vhost-user.c| 15 ++-
include/hw/virtio/vhost.h | 1 +
include/net/vhost_net.h | 1 +
5 files changed, 34 insertions(+), 1
So that we could let vhost_user_call to handle extented requests,
such as VHOST_USER_GET/SET_PROTOCOL_FEATURES, instead of invoking
vhost_user_read/write and constructing the msg again by ourself.
Signed-off-by: Yuanhan Liu
---
hw/virtio/vhost-user.c | 38
above messages, we simply ignore them when they are not sent the first
time.
Signed-off-by: Nikolay Nikolaev
Signed-off-by: Changchun Ouyang
Signed-off-by: Yuanhan Liu
---
v10: don't treat VHOST_USER_SET/GET_[PROTOCOL]_FEATURES as one time
request, as the two feature bits need to be sto
1 to max virt
queue pair.
Signed-off-by: Changchun Ouyang
Signed-off-by: Yuanhan Liu
---
docs/specs/vhost-user.txt | 12 +++-
hw/net/vhost_net.c| 18 ++
hw/net/virtio-net.c | 8
hw/virtio/vhost-user.c
On Tue, Sep 22, 2015 at 03:52:49PM -0300, Eduardo Habkost wrote:
> On Fri, Sep 18, 2015 at 10:58:43PM +0800, Yuanhan Liu wrote:
> [...]
> > diff --git a/net/vhost-user.c b/net/vhost-user.c
> > index 93dcecd..4fa3d64 100644
> > --- a/net/vhost-user.c
&g
On Tue, Sep 22, 2015 at 05:56:16PM +0800, Jason Wang wrote:
>
>
> On 09/18/2015 10:58 PM, Yuanhan Liu wrote:
> > This is for querying how many queues the backend supports if it has mq
> > support(when VHOST_USER_PROTOCOL_F_MQ flag is set from the quried
On Tue, Sep 22, 2015 at 08:47:04AM -0600, Eric Blake wrote:
> On 09/18/2015 08:58 AM, Yuanhan Liu wrote:
> > From: Changchun Ouyang
> >
> > Add a new message, VHOST_USER_SET_VRING_ENABLE, to enable or disable
> > a specific virt queue, which is similar to attach/deta
On Tue, Sep 22, 2015 at 08:06:58PM -0600, Eric Blake wrote:
> On 09/22/2015 08:05 PM, Yuanhan Liu wrote:
>
> >>> + * VHOST_USER_SET_VRING_ENABLE
> >>> +
> >>> + Id: 18
> >>> + Equivalent ioctl: N/A
> >>> + Master pay
On Wed, Sep 23, 2015 at 10:12:10AM +0800, Jason Wang wrote:
>
>
> On 09/23/2015 09:57 AM, Yuanhan Liu wrote:
> > On Tue, Sep 22, 2015 at 06:14:14PM +0800, Jason Wang wrote:
> >>
> > [...]
> >>> -static void net_vhost_link_down(VhostUserSt
On Tue, Sep 22, 2015 at 06:14:14PM +0800, Jason Wang wrote:
>
>
[...]
> > -static void net_vhost_link_down(VhostUserState *s, bool link_down)
> > +static void net_vhost_link_down(int queues, NetClientState *ncs[],
> > +bool link_down)
> > {
> > -s->nc.link_dow
So that we could let vhost_user_call to handle extented requests,
such as VHOST_USER_GET/SET_PROTOCOL_FEATURES, instead of invoking
vhost_user_read/write and constructing the msg again by ourself.
Signed-off-by: Yuanhan Liu
---
hw/virtio/vhost-user.c | 38
above messages, we simply ignore them when they are not sent the first
time.
Signed-off-by: Nikolay Nikolaev
Signed-off-by: Changchun Ouyang
Signed-off-by: Yuanhan Liu
---
v11: inovke qmp_set_link() directly -- Suggested by Jason Wang
v10: don't treat VHOST_USER_SET/GET_[PROTOCOL]_FEATURES a
1 to max virt
queue pair.
Signed-off-by: Changchun Ouyang
Signed-off-by: Yuanhan Liu
---
v11: fix typo
---
docs/specs/vhost-user.txt | 12 +++-
hw/net/vhost_net.c| 18 ++
hw/net/virtio-net.c | 8
hw/virtio/vhost-u
new message to disable/enable a specific virt queue.
Michael S. Tsirkin (1):
vhost-user: add protocol feature negotiation
Yuanhan Liu (4):
vhost-user: use VHOST_USER_XXX macro for switch statement
vhost: rename VHOST_RESET_OWNER to VHOST_RESET_DEVICE
vhost-user: add VHOST_USER_GET_QUEUE_
From: "Michael S. Tsirkin"
Support a separate bitmask for vhost-user protocol features,
and messages to get/set protocol features.
Invoke them at init.
No features are defined yet.
[ leverage vhost_user_call for request handling -- Yuanhan Liu ]
Signed-off-by: Michael S. Tsirkin
Quote from Michael:
We really should rename VHOST_RESET_OWNER to VHOST_RESET_DEVICE.
Suggested-by: Michael S. Tsirkin
Signed-off-by: Yuanhan Liu
---
docs/specs/vhost-user.txt | 4 ++--
hw/net/vhost_net.c | 2 +-
hw/virtio/vhost-user.c | 6 +++---
linux-headers/linux
done in the following patch.
Signed-off-by: Yuanhan Liu
---
v11: define a dummy vhost_net_get_max_queues when !CONFIG_VHOST_NET.
---
docs/specs/vhost-user.txt | 11 +++
hw/net/vhost_net.c| 12
hw/virtio/vhost-user.c| 15 ++-
include/hw/virtio/vhost.h
Minusing the idx with the base(dev->vq_index) for vhost-kernel, and
then adding it back for vhost-user doesn't seem right. Here introduces
a new method vhost_backend_get_vq_index() for getting the right vq
index for following vhost messages calls.
Suggested-by: Jason Wang
Signed-off-by:
On Wed, Sep 23, 2015 at 12:20:00PM +0800, Yuanhan Liu wrote:
> From: Changchun Ouyang
>
[...]
> static void net_vhost_user_event(void *opaque, int event)
> {
> -VhostUserState *s = opaque;
> +const char *name = opaque;
> +NetClientState *ncs[MAX_QUEUE_NUM];
>
On Thu, Sep 24, 2015 at 01:34:31PM +0800, Jason Wang wrote:
>
>
> Some nitpicks and comments. If you plan to send another version, please
> consider to fix them.
I will, but I'd like to hold a while before getting more comments from
Michael; I don't want to repost a whole new version too often f
On Thu, Sep 24, 2015 at 01:13:24PM +0300, Marcel Apfelbaum wrote:
> On 09/23/2015 07:19 AM, Yuanhan Liu wrote:
> >From: "Michael S. Tsirkin"
> >
> >Support a separate bitmask for vhost-user protocol features,
> >and messages to get/set protocol features.
On Thu, Sep 24, 2015 at 01:13:24PM +0300, Marcel Apfelbaum wrote:
> >diff --git a/hw/net/vhost_net.c b/hw/net/vhost_net.c
> >index 1d76b94..9d32d76 100644
> >--- a/hw/net/vhost_net.c
> >+++ b/hw/net/vhost_net.c
> >@@ -152,8 +152,10 @@ struct vhost_net *vhost_net_init(VhostNetOptions
> >*options)
>
So that we could let vhost_user_call to handle extented requests,
such as VHOST_USER_GET/SET_PROTOCOL_FEATURES, instead of invoking
vhost_user_read/write and constructing the msg again by ourself.
Signed-off-by: Yuanhan Liu
Reviewed-by: Marcel Apfelbaum
Tested-by: Marcel Apfelbaum
---
hw
event handler once. Which is also suggested by Jason Wang.
Thanks.
--yliu
---
Changchun Ouyang (2):
vhost-user: add multiple queue support
vhost-user: add a new message to disable/enable a specific virt queue.
Michael S. Tsirkin (1):
vhost-user: add protocol feature negotia
imply ignore them when they are not sent the first
time.
Signed-off-by: Nikolay Nikolaev
Signed-off-by: Changchun Ouyang
Signed-off-by: Yuanhan Liu
Reviewed-by: Jason Wang
Tested-by: Marcel Apfelbaum
---
v12: rename vhost_user_one_time_request() to vhost_user_dev_request().
From: "Michael S. Tsirkin"
Support a separate bitmask for vhost-user protocol features,
and messages to get/set protocol features.
Invoke them at init.
No features are defined yet.
[ leverage vhost_user_call for request handling -- Yuanhan Liu ]
Signed-off-by: Michael S. Tsirkin
done in the following patch.
Signed-off-by: Yuanhan Liu
Reviewed-by: Marcel Apfelbaum
Tested-by: Marcel Apfelbaum
---
v12: mark VHOST_USER_GET_QUEUE_NUM as a message need reply.
---
docs/specs/vhost-user.txt | 12
hw/net/vhost_net.c| 12
hw/virtio/vhost-user.c
1 to max virt
queue pair.
Signed-off-by: Changchun Ouyang
Signed-off-by: Yuanhan Liu
Reviewed-by: Jason Wang
Tested-by: Marcel Apfelbaum
---
docs/specs/vhost-user.txt | 12 +++-
hw/net/vhost_net.c| 18 ++
hw/net/virtio-net.c
e, instead of per-queue
or something else.
Suggested-by: Michael S. Tsirkin
Signed-off-by: Yuanhan Liu
Reviewed-by: Marcel Apfelbaum
Tested-by: Marcel Apfelbaum
---
docs/specs/vhost-user.txt | 4 ++--
hw/net/vhost_net.c | 2 +-
hw/virtio/vhost-user.c | 6 +++---
linux-headers/linu
d-off-by: Yuanhan Liu
Reviewed-by: Jason Wang
Tested-by: Marcel Apfelbaum
---
hw/virtio/vhost-backend.c | 10 +-
hw/virtio/vhost-user.c| 12 ++--
hw/virtio/vhost.c | 15 ++-
include/hw/virtio/vhost-backend.h | 2 ++
4 files changed, 27 in
Quote from Michael:
We really should rename VHOST_RESET_OWNER to VHOST_RESET_DEVICE.
Suggested-by: Michael S. Tsirkin
Signed-off-by: Yuanhan Liu
---
docs/specs/vhost-user.txt | 4 ++--
hw/net/vhost_net.c | 2 +-
hw/virtio/vhost-user.c | 6 +++---
linux-headers/linux
add a new message to disable/enable a specific virt queue.
Michael S. Tsirkin (1):
vhost-user: add protocol feature negotiation
Ouyang Changchun (1):
vhost-user: add multiple queue support
Yuanhan Liu (4):
vhost-user: use VHOST_USER_XXX macro for switch statement
vhost: rename VHOST_RESET_
So that we could let vhost_user_call to handle extented requests,
such as VHOST_USER_GET/SET_PROTOCOL_FEATURES, instead of invoking
vhost_user_read/write and constructing the msg again by ourself.
Signed-off-by: Yuanhan Liu
---
hw/virtio/vhost-user.c | 37
From: "Michael S. Tsirkin"
Support a separate bitmask for vhost-user protocol features,
and messages to get/set protocol features.
Invoke them at init.
No features are defined yet.
v2: leverage vhost_user_call for request handling -- Yuanhan Liu
Signed-off-by: Michael S. Tsirkin
aev
Signed-off-by: Changchun Ouyang
Signed-off-by: Yuanhan Liu
---
docs/specs/vhost-user.txt | 13 +
hw/virtio/vhost-user.c| 31 ++-
include/net/net.h | 1 +
net/vhost-user.c | 136 --
qapi-schema.json
1 - 100 of 170 matches
Mail list logo
