On 8/20/2024 1:09 PM, Michael S. Tsirkin wrote:
On Tue, Aug 20, 2024 at 12:44:46PM -0700, Si-Wei Liu wrote:
On 8/20/2024 12:19 AM, Xuan Zhuo wrote:
leads to regression on VM with the sysctl value of:
- net.core.high_order_alloc_disable=1
which could see reliable crashes or scp failure (sc
On Tue, Aug 20, 2024 at 03:19:13PM +0800, Xuan Zhuo wrote:
> leads to regression on VM with the sysctl value of:
>
> - net.core.high_order_alloc_disable=1
>
> which could see reliable crashes or scp failure (scp a file 100M in size
> to VM):
>
> The issue is that the virtnet_rq_dma takes up 16 b
On Tue, Aug 20, 2024 at 12:44:46PM -0700, Si-Wei Liu wrote:
>
>
> On 8/20/2024 12:19 AM, Xuan Zhuo wrote:
> > leads to regression on VM with the sysctl value of:
> >
> > - net.core.high_order_alloc_disable=1
> >
> > which could see reliable crashes or scp failure (scp a file 100M in size
> > to
On 8/20/2024 12:19 AM, Xuan Zhuo wrote:
leads to regression on VM with the sysctl value of:
- net.core.high_order_alloc_disable=1
which could see reliable crashes or scp failure (scp a file 100M in size
to VM):
The issue is that the virtnet_rq_dma takes up 16 bytes at the beginning
of a new
On Tue, Aug 20, 2024 at 03:19:13PM +0800, Xuan Zhuo wrote:
> leads to regression on VM with the sysctl value of:
>
> - net.core.high_order_alloc_disable=1
> which could see reliable crashes or scp failure (scp a file 100M in size
> to VM):
>
> The issue is that the virtnet_rq_dma takes up 16
From: Xuan Zhuo
Date: Tue, 20 Aug 2024 15:19:13 +0800
> leads to regression on VM with the sysctl value of:
Where's the beginning of the sentence? You mean, "This overflow leads"?
>
> - net.core.high_order_alloc_disable=1
This `- ` can be removed - at least some syntax highlighters color it i
Now, this API is useless. remove it.
Signed-off-by: Xuan Zhuo
---
drivers/virtio/virtio_ring.c | 48
include/linux/virtio.h | 2 --
2 files changed, 50 deletions(-)
diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index 7efddc7
virtnet_free_old_xmit distinguishes three type ptr(skb, xdp frame, xsk
buffer) by the last bits of the pointer.
Signed-off-by: Xuan Zhuo
---
drivers/net/virtio_net.c | 85
1 file changed, 59 insertions(+), 26 deletions(-)
diff --git a/drivers/net/virtio_
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 a898568bed5
Now, we supported AF_XDP(xsk). Add NETDEV_XDP_ACT_XSK_ZEROCOPY to
xdp_features.
Signed-off-by: Xuan Zhuo
---
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 28c5f9e77fa3..8e4578ec1937 100644
1. this commit hardens dma unmap for indirect
2. the subsequent commit uses the struct extra to record whether the
buffers need to be unmapped or not. So we need a struct extra for
every desc, whatever it is indirect or not.
Signed-off-by: Xuan Zhuo
---
drivers/virtio/virtio_ring.c | 57 ++
This patch implement the logic of bind/unbind xsk pool to sq and rq.
Signed-off-by: Xuan Zhuo
---
drivers/net/virtio_net.c | 54
1 file changed, 54 insertions(+)
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 96abee36738b..6a36a20
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.
Signed-off-by: Xuan Zhuo
---
drivers/net/virtio_net.c | 127 ++-
1 file changed, 125 inse
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/
Because the af-xdp will introduce a new xmit type, so I refactor the
xmit type mechanism first.
We use the last two bits of the pointer to distinguish the xmit type,
so we can distinguish four xmit types. Now we have three types: skb,
orphan and xdp.
Signed-off-by: Xuan Zhuo
---
drivers/net/vir
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
virtio-net rq submits premapped buffer per buffer.
And removes the call of the virtnet_rq_set_premapped().
Signed-off-by: Xuan Zhuo
---
drivers/net/virtio_net.c | 31 ---
1 file changed, 8 insertions(+), 23 deletions(-)
diff --git a/drivers/net/virtio_net.c b/drivers
1. this commit hardens dma unmap for indirect
2. the subsequent commit uses the struct extra to record whether the
buffers need to be unmapped or not. So we need a struct extra for
every desc, whatever it is indirect or not.
Signed-off-by: Xuan Zhuo
---
drivers/virtio/virtio_ring.c | 122 +
## AF_XDP
XDP socket(AF_XDP) is an excellent bypass kernel network framework. The zero
copy feature of xsk (XDP socket) needs to be supported by the driver. The
performance of zero copy is very good. mlx5 and intel ixgbe already support
this feature, This patch set allows virtio-net to support xsk
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
leads to regression on VM with the sysctl value of:
- net.core.high_order_alloc_disable=1
which could see reliable crashes or scp failure (scp a file 100M in size
to VM):
The issue is that the virtnet_rq_dma takes up 16 bytes at the beginning
of a new frag. When the frag size is larger than PAGE
21 matches
Mail list logo
