15/08/2022 03:27, Hu, Jiayu:
> From: Jun Qiu
> >
> > I don't think the stack(software) cares if the length of a packet is less
> > than 60,
> > especially when receiving it.
> > In the linux kernel, if the packet length does not match the IP
> > total-length,
> > the packet is flushed to the st
> -Original Message-
> From: Jun Qiu
> Sent: Thursday, July 28, 2022 7:02 PM
> To: Hu, Jiayu ; dev@dpdk.org
> Cc: sta...@dpdk.org
> Subject: RE: [PATCH] gro: fix gro with ethernet tail padding bytes
>
> I don't think the stack(software) cares if the lengt
iu ; dev@dpdk.org
Cc: sta...@dpdk.org
Subject: RE: [PATCH] gro: fix gro with ethernet tail padding bytes
Hi Jun,
> -Original Message-
> From: Jun Qiu
> Sent: Wednesday, July 27, 2022 4:01 PM
> To: dev@dpdk.org
> Cc: Hu, Jiayu ; sta...@dpdk.org
> Subject: [PATCH] gr
Hi Jun,
> -Original Message-
> From: Jun Qiu
> Sent: Wednesday, July 27, 2022 4:01 PM
> To: dev@dpdk.org
> Cc: Hu, Jiayu ; sta...@dpdk.org
> Subject: [PATCH] gro: fix gro with ethernet tail padding bytes
>
> Exclude CRC fields, the minimum Ethernet packet length
Exclude CRC fields, the minimum Ethernet packet
length is 60 bytes. When the actual packet length
is less than 60 bytes, padding is added to the tail.
When GRO is performed on a packet containing a padding
field, mbuf->pkt_len is the one that contains the
padding field, which leads to the error of
5 matches
Mail list logo
