On 2017年01月12日 17:40, Tan, Jianfeng wrote:
Hi Jason,
Ok, just want to show its advantages. It can be added on top.
And two more suggestions:
- better to split tap support out of vhost file
Good suggestion! Will do that in next version.
- kernel support more than 8 queues on recent kernel,
Hi Jason,
Ok, just want to show its advantages. It can be added on top.
And two more suggestions:
- better to split tap support out of vhost file
Good suggestion! Will do that in next version.
- kernel support more than 8 queues on recent kernel, so there's no
need to limit it to 8. When ru
On 2017年01月11日 11:13, Tan, Jianfeng wrote:
On 1/11/2017 10:42 AM, Jason Wang wrote:
On 2017年01月10日 14:11, Tan, Jianfeng wrote:
Hi Jason,
On 1/9/2017 12:39 PM, Jason Wang wrote:
On 2016年12月23日 15:14, Jianfeng Tan wrote:
This patch add support vhost kernel as the backend for virtio_u
On 1/11/2017 10:42 AM, Jason Wang wrote:
On 2017年01月10日 14:11, Tan, Jianfeng wrote:
Hi Jason,
On 1/9/2017 12:39 PM, Jason Wang wrote:
On 2016年12月23日 15:14, Jianfeng Tan wrote:
This patch add support vhost kernel as the backend for virtio_user.
Three main hook functions are added:
-
On 2017年01月11日 10:30, Tan, Jianfeng wrote:
Hi Jason,
On 1/9/2017 12:39 PM, Jason Wang wrote:
+if (!enable) {
+if (dev->tapfds[pair_idx]) {
+close(dev->tapfds[pair_idx]);
+dev->tapfds[pair_idx] = -1;
+}
+return vhost_kernel_set_backend(vhos
On 2017年01月10日 14:11, Tan, Jianfeng wrote:
Hi Jason,
On 1/9/2017 12:39 PM, Jason Wang wrote:
On 2016年12月23日 15:14, Jianfeng Tan wrote:
This patch add support vhost kernel as the backend for virtio_user.
Three main hook functions are added:
- vhost_kernel_setup() to open char device, e
Hi Jason,
On 1/9/2017 12:39 PM, Jason Wang wrote:
+if (!enable) {
+if (dev->tapfds[pair_idx]) {
+close(dev->tapfds[pair_idx]);
+dev->tapfds[pair_idx] = -1;
+}
+return vhost_kernel_set_backend(vhostfd, -1);
If this is used to for thing like e
On 1/10/2017 4:46 PM, Thomas Monjalon wrote:
2017-01-10 14:11, Tan, Jianfeng:
On 1/9/2017 12:39 PM, Jason Wang wrote:
On 2016年12月23日 15:14, Jianfeng Tan wrote:
[...]
+/* TUNSETIFF ifr flags */
+#define IFF_TAP 0x0002
+#define IFF_NO_PI0x1000
+#define IFF_ONE_QUEUE0x2000
2017-01-10 14:11, Tan, Jianfeng:
> On 1/9/2017 12:39 PM, Jason Wang wrote:
> > On 2016年12月23日 15:14, Jianfeng Tan wrote:
> [...]
> >> +/* TUNSETIFF ifr flags */
> >> +#define IFF_TAP 0x0002
> >> +#define IFF_NO_PI0x1000
> >> +#define IFF_ONE_QUEUE0x2000
> >> +#define IFF_VNET_H
Hi Jason,
On 1/9/2017 12:39 PM, Jason Wang wrote:
On 2016年12月23日 15:14, Jianfeng Tan wrote:
This patch add support vhost kernel as the backend for virtio_user.
Three main hook functions are added:
- vhost_kernel_setup() to open char device, each vq pair needs one
vhostfd;
- vhost_
On 2017年01月04日 15:22, Tan, Jianfeng wrote:
Sorry, I forget to reply this comment.
On 12/26/2016 3:44 PM, Yuanhan Liu wrote:
[...]
+
+/* Does not work when VIRTIO_F_IOMMU_PLATFORM now, why? */
Because this feature need the vhost IOTLB support from the device
emulation. Patches for QEMU
On 2016年12月23日 15:14, Jianfeng Tan wrote:
This patch add support vhost kernel as the backend for virtio_user.
Three main hook functions are added:
- vhost_kernel_setup() to open char device, each vq pair needs one
vhostfd;
- vhost_kernel_ioctl() to communicate control messages with v
On Wed, Jan 04, 2017 at 03:22:08PM +0800, Tan, Jianfeng wrote:
>
> Sorry, I forget to reply this comment.
>
> On 12/26/2016 3:44 PM, Yuanhan Liu wrote:
> >[...]
> >>+
> >>+ /* Does not work when VIRTIO_F_IOMMU_PLATFORM now, why? */
> >Because this feature need the vhost IOTLB support from the d
Sorry, I forget to reply this comment.
On 12/26/2016 3:44 PM, Yuanhan Liu wrote:
[...]
+
+ /* Does not work when VIRTIO_F_IOMMU_PLATFORM now, why? */
Because this feature need the vhost IOTLB support from the device
emulation. Patches for QEMU hasn't been merged yet, but it has been
the
On Fri, Dec 23, 2016 at 07:14:24AM +, Jianfeng Tan wrote:
> + * Copyright(c) 2010-2016 Intel Corporation. All rights reserved.
^
I think it should be 2016.
> +/* By default, vhost kernel module allows 64 regions, but DPDK allows
> + * 256 segments. As a relief,
This patch add support vhost kernel as the backend for virtio_user.
Three main hook functions are added:
- vhost_kernel_setup() to open char device, each vq pair needs one
vhostfd;
- vhost_kernel_ioctl() to communicate control messages with vhost
kernel module;
- vhost_kernel_enable_q
16 matches
Mail list logo
