[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CANaxB-wSegSBot-8YCeiw-CsfdubRJMacC6nmRPLyoD4eGSc-w@mail.gmail.com>
Date: Thu, 6 Jun 2024 15:16:56 -0700
From: Andrei Vagin <avagin@...il.com>
To: joshwash@...gle.com
Cc: netdev@...r.kernel.org, davem@...emloft.net, kuba@...nel.org,
stable@...nel.org, Praveen Kaligineedi <pkaligineedi@...gle.com>,
Harshitha Ramamurthy <hramamurthy@...gle.com>, Eric Dumazet <edumazet@...gle.com>,
Jeroen de Borst <jeroendb@...gle.com>, Shailend Chand <shailend@...gle.com>,
Paolo Abeni <pabeni@...hat.com>, Willem de Bruijn <willemb@...gle.com>,
Rushil Gupta <rushilg@...gle.com>, Catherine Sullivan <csully@...gle.com>, Bailey Forrest <bcf@...gle.com>,
open list <linux-kernel@...r.kernel.org>
Subject: Re: [PATCH net] gve: ignore nonrelevant GSO type bits when processing
TSO headers
On Thu, Jun 6, 2024 at 12:22 PM <joshwash@...gle.com> wrote:
>
> From: Joshua Washington <joshwash@...gle.com>
>
> TSO currently fails when the skb's gso_type field has more than one bit
> set.
>
> TSO packets can be passed from userspace using PF_PACKET, TUNTAP and a
> few others, using virtio_net_hdr (e.g., PACKET_VNET_HDR). This includes
> virtualization, such as QEMU, a real use-case.
Here is the bug report where this issue was triggered by gVisor:
https://github.com/google/gvisor/issues/10344
>
> The gso_type and gso_size fields as passed from userspace in
> virtio_net_hdr are not trusted blindly by the kernel. It adds gso_type
> |= SKB_GSO_DODGY to force the packet to enter the software GSO stack
> for verification.
>
> This issue might similarly come up when the CWR bit is set in the TCP
> header for congestion control, causing the SKB_GSO_TCP_ECN gso_type bit
> to be set.
>
> Fixes: a57e5de476be ("gve: DQO: Add TX path")
>
> Signed-off-by: Joshua Washington <joshwash@...gle.com>
> Reviewed-by: Praveen Kaligineedi <pkaligineedi@...gle.com>
> Reviewed-by: Harshitha Ramamurthy <hramamurthy@...gle.com>
> Suggested-by: Eric Dumazet <edumazet@...gle.com>
Acked-by: Andrei Vagin <avagin@...il.com>
Thanks,
Andrei
Powered by blists - more mailing lists