This patch implement the logic of bind/unbind xsk pool to sq and rq.
Signed-off-by: Xuan Zhuo
Acked-by: Jason Wang
---
drivers/net/virtio_net.c | 53
1 file changed, 53 insertions(+)
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index
The driver's tx napi is very important for XSK. It is responsible for
obtaining data from the XSK queue and sending it out.
At the beginning, we need to trigger tx napi.
virtnet_free_old_xmit distinguishes three type ptr(skb, xdp frame, xsk
buffer) by the last bits of the pointer.
Signed-off-by:
Since xsk's TX queue is consumed by TX NAPI, if sq is bound to xsk, then
we must stop tx napi from being disabled.
Signed-off-by: Xuan Zhuo
Acked-by: Jason Wang
---
drivers/net/virtio_net.c | 10 +-
1 file changed, 9 insertions(+), 1 deletion(-)
diff --git a/drivers/net/virtio_net.c b/
Now, we support AF_XDP(xsk). Add NETDEV_XDP_ACT_XSK_ZEROCOPY to
xdp_features.
Signed-off-by: Xuan Zhuo
Acked-by: Jason Wang
---
drivers/net/virtio_net.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 7db586770249..
virtio-net rq submits premapped per-buffer by setting sg page to NULL;
Signed-off-by: Xuan Zhuo
Acked-by: Jason Wang
---
drivers/net/virtio_net.c | 22 +++---
1 file changed, 11 insertions(+), 11 deletions(-)
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
inde
If send queue sent some packets, we update the tx timeout
record to prevent the tx timeout.
Signed-off-by: Xuan Zhuo
Acked-by: Jason Wang
---
drivers/net/virtio_net.c | 7 +++
1 file changed, 7 insertions(+)
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 57642bd83b7
To make the code readable, introduce vring_need_unmap_buffer() to
replace do_unmap.
use_dma_api premapped -> vring_need_unmap_buffer()
1. false falsefalse
2. truefalsetrue
3. truetrue false
Signed-off-by: Xuan Zhuo
Acked-by: Jason Wang
---
drive
Two APIs are introduced to submit premapped per-buffers.
int virtqueue_add_inbuf_premapped(struct virtqueue *vq,
struct scatterlist *sg, unsigned int num,
void *data,
void *ctx,
The current configuration sets the virtqueue (vq) to premapped mode,
implying that all buffers submitted to this queue must be mapped ahead
of time. This presents a challenge for the virtnet send queue (sq): the
virtnet driver would be required to keep track of dma information for vq
size * 17, whi
Because the af-xdp will introduce a new xmit type, so I refactor the
xmit type mechanism first.
We know both xdp_frame and sk_buff are at least 4 bytes aligned.
For the xdp tx, we do not pass any pointer to virtio core as data,
we just need to pass the len of the packet. So we will push len
to the
v4:
1. rebase net-next
2. update the kdoc for the new APIs
v3:
1. use sg_dma_address/length api to set the premapped sg
2. remove 'premapped' parameter from the new APIs
3. tweak the comment of commit #2,#3
v2:
1. use new api to submit premapped buffer instead of using sgs
Now, this API is useless. remove it.
Signed-off-by: Xuan Zhuo
Acked-by: Jason Wang
---
drivers/net/virtio_net.c | 13 --
drivers/virtio/virtio_ring.c | 48
include/linux/virtio.h | 2 --
3 files changed, 63 deletions(-)
diff --git a/drive
The subsequent commit needs to know whether every indirect buffer is
premapped or not. So we need to introduce an extra struct for every
indirect buffer to record this info.
Signed-off-by: Xuan Zhuo
Acked-by: Jason Wang
---
drivers/virtio/virtio_ring.c | 112 ---
The subsequent commit needs to know whether every indirect buffer is
premapped or not. So we need to introduce an extra struct for every
indirect buffer to record this info.
Signed-off-by: Xuan Zhuo
Acked-by: Jason Wang
---
drivers/virtio/virtio_ring.c | 60 +---
On Thu, 7 Nov 2024 16:54:56 +0800 Xuan Zhuo wrote:
> + * Returns zero or a negative error (ie. ENOSPC, ENOMEM, EIO).
> + * Returns zero or a negative error (ie. ENOSPC, ENOMEM, EIO).
Looks like we need a rebase, doesn't apply any more.
When you rebase please correct the kdoc, looks like the off
On 07.11.2024 23:46, Michal Luczaj wrote:
> Kernel queues MSG_ZEROCOPY completion notifications on the error queue.
> Where they remain, until explicitly recv()ed. To prevent memory leaks,
> clean up the queue when the socket is destroyed.
>
> unreferenced object 0x8881028beb00 (size 224):
On 07.11.2024 23:46, Michal Luczaj wrote:
> Add a missing kfree_skb() to prevent memory leaks.
>
> Fixes: 581512a6dc93 ("vsock/virtio: MSG_ZEROCOPY flag support")
> Reviewed-by: Stefano Garzarella
> Signed-off-by: Michal Luczaj
> ---
> net/vmw_vsock/virtio_transport_common.c | 1 +
> 1 file
On 06.11.2024 20:51, Michal Luczaj wrote:
> Add a missing kfree_skb() to prevent memory leaks.
>
> Fixes: 581512a6dc93 ("vsock/virtio: MSG_ZEROCOPY flag support")
> Signed-off-by: Michal Luczaj
> ---
> net/vmw_vsock/virtio_transport_common.c | 1 +
> 1 file changed, 1 insertion(+)
Acked-by:
18 matches
Mail list logo
