[PATCH v5 net-next 01/36] net: Introduce direct data placement tcp offload

[Eric Dumazet]

On Thu, Jul 22, 2021 at 1:04 PM Boris Pismenny <borisp at nvidia.com> wrote:
>
> From: Boris Pismenny <borisp at mellanox.com>
>
>
...

>  };
>
>  const char
> diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
> index e6ca5a1f3b59..4a7160bba09b 100644
> --- a/net/ipv4/tcp_input.c
> +++ b/net/ipv4/tcp_input.c
> @@ -5149,6 +5149,9 @@ tcp_collapse(struct sock *sk, struct sk_buff_head *list, struct rb_root *root,
>                 memcpy(nskb->cb, skb->cb, sizeof(skb->cb));
>  #ifdef CONFIG_TLS_DEVICE
>                 nskb->decrypted = skb->decrypted;
> +#endif
> +#ifdef CONFIG_ULP_DDP
> +               nskb->ddp_crc = skb->ddp_crc;

Probably you do not want to attempt any collapse if skb->ddp_crc is
set right there.

>  #endif
>                 TCP_SKB_CB(nskb)->seq = TCP_SKB_CB(nskb)->end_seq = start;
>                 if (list)
> @@ -5182,6 +5185,11 @@ tcp_collapse(struct sock *sk, struct sk_buff_head *list, struct rb_root *root,
>  #ifdef CONFIG_TLS_DEVICE
>                                 if (skb->decrypted != nskb->decrypted)
>                                         goto end;
> +#endif
> +#ifdef CONFIG_ULP_DDP
> +
> +                               if (skb->ddp_crc != nskb->ddp_crc)

This checks only the second, third, and remaining skbs.

> +                                       goto end;
>  #endif
>                         }
>                 }


tcp_collapse() is copying data from small skbs to pack it to bigger
skb (one page of payload), in case
of memory emergency/pressure (socket queues are full)

If your changes are trying to avoid 'needless'  copies, maybe you
should reconsider and let the emergency packing be done.

If the copy is not _possible_, you should rephrase your changelog to
clearly state the kernel _cannot_ access this memory in any way.