Re: [PATCH v3] virtio: Work around frames incorrectly marked as gso

2020-02-26 Thread David Miller
From: anton.iva...@cambridgegreys.com Date: Mon, 24 Feb 2020 13:25:50 + > From: Anton Ivanov > > Some of the locally generated frames marked as GSO which > arrive at virtio_net_hdr_from_skb() have no GSO_TYPE, no > fragments (data_len = 0) and length significantly shorter > than the MTU (752

Re: [PATCH v3] virtio: Work around frames incorrectly marked as gso

2020-02-25 Thread Anton Ivanov
On 25/02/2020 16:26, Willem de Bruijn wrote: An skb_dump() + dump_stack() when the packet socket gets such a packet may point us to the root cause and fix that. We tried dump stack, it was not informative - it was just the recvmmsg call stack coming from the UML until it hits the relevant recv

Re: [PATCH v3] virtio: Work around frames incorrectly marked as gso

2020-02-25 Thread Willem de Bruijn
> An skb_dump() + dump_stack() when the packet socket gets such a > packet may point us to the root cause and fix that. > >>> > >>> We tried dump stack, it was not informative - it was just the recvmmsg > >>> call stack coming from the UML until it hits the relevant recv bit in > >>> af_p

Re: [PATCH v3] virtio: Work around frames incorrectly marked as gso

2020-02-25 Thread Anton Ivanov
On 25/02/2020 07:48, Anton Ivanov wrote: On 24/02/2020 22:22, Willem de Bruijn wrote: On Mon, Feb 24, 2020 at 4:00 PM Anton Ivanov wrote: On 24/02/2020 20:20, Willem de Bruijn wrote: On Mon, Feb 24, 2020 at 2:55 PM Anton Ivanov wrote: On 24/02/2020 19:27, Willem de Bruijn wrote: On Mo

Re: [PATCH v3] virtio: Work around frames incorrectly marked as gso

2020-02-24 Thread Anton Ivanov
On 24/02/2020 22:22, Willem de Bruijn wrote: On Mon, Feb 24, 2020 at 4:00 PM Anton Ivanov wrote: On 24/02/2020 20:20, Willem de Bruijn wrote: On Mon, Feb 24, 2020 at 2:55 PM Anton Ivanov wrote: On 24/02/2020 19:27, Willem de Bruijn wrote: On Mon, Feb 24, 2020 at 8:26 AM wrote: From: A

Re: [PATCH v3] virtio: Work around frames incorrectly marked as gso

2020-02-24 Thread Anton Ivanov
On 25/02/2020 04:02, Jason Wang wrote: On 2020/2/25 上午6:22, Willem de Bruijn wrote: On Mon, Feb 24, 2020 at 4:00 PM Anton Ivanov wrote: On 24/02/2020 20:20, Willem de Bruijn wrote: On Mon, Feb 24, 2020 at 2:55 PM Anton Ivanov wrote: On 24/02/2020 19:27, Willem de Bruijn wrote: On Mon, F

Re: [PATCH v3] virtio: Work around frames incorrectly marked as gso

2020-02-24 Thread Jason Wang
On 2020/2/25 上午6:22, Willem de Bruijn wrote: On Mon, Feb 24, 2020 at 4:00 PM Anton Ivanov wrote: On 24/02/2020 20:20, Willem de Bruijn wrote: On Mon, Feb 24, 2020 at 2:55 PM Anton Ivanov wrote: On 24/02/2020 19:27, Willem de Bruijn wrote: On Mon, Feb 24, 2020 at 8:26 AM wrote: From: Anto

Re: [PATCH v3] virtio: Work around frames incorrectly marked as gso

2020-02-24 Thread Willem de Bruijn
On Mon, Feb 24, 2020 at 4:00 PM Anton Ivanov wrote: > > On 24/02/2020 20:20, Willem de Bruijn wrote: > > On Mon, Feb 24, 2020 at 2:55 PM Anton Ivanov > > wrote: > >> On 24/02/2020 19:27, Willem de Bruijn wrote: > >>> On Mon, Feb 24, 2020 at 8:26 AM wrote: > From: Anton Ivanov > >

Re: [PATCH v3] virtio: Work around frames incorrectly marked as gso

2020-02-24 Thread Anton Ivanov
On 24/02/2020 20:20, Willem de Bruijn wrote: On Mon, Feb 24, 2020 at 2:55 PM Anton Ivanov wrote: On 24/02/2020 19:27, Willem de Bruijn wrote: On Mon, Feb 24, 2020 at 8:26 AM wrote: From: Anton Ivanov Some of the locally generated frames marked as GSO which arrive at virtio_net_hdr_from_skb

Re: [PATCH v3] virtio: Work around frames incorrectly marked as gso

2020-02-24 Thread Willem de Bruijn
On Mon, Feb 24, 2020 at 2:55 PM Anton Ivanov wrote: > > On 24/02/2020 19:27, Willem de Bruijn wrote: > > On Mon, Feb 24, 2020 at 8:26 AM wrote: > >> > >> From: Anton Ivanov > >> > >> Some of the locally generated frames marked as GSO which > >> arrive at virtio_net_hdr_from_skb() have no GSO_TYP

Re: [PATCH v3] virtio: Work around frames incorrectly marked as gso

2020-02-24 Thread Anton Ivanov
On 24/02/2020 19:27, Willem de Bruijn wrote: On Mon, Feb 24, 2020 at 8:26 AM wrote: From: Anton Ivanov Some of the locally generated frames marked as GSO which arrive at virtio_net_hdr_from_skb() have no GSO_TYPE, no fragments (data_len = 0) and length significantly shorter than the MTU (752

Re: [PATCH v3] virtio: Work around frames incorrectly marked as gso

2020-02-24 Thread Willem de Bruijn
On Mon, Feb 24, 2020 at 8:26 AM wrote: > > From: Anton Ivanov > > Some of the locally generated frames marked as GSO which > arrive at virtio_net_hdr_from_skb() have no GSO_TYPE, no > fragments (data_len = 0) and length significantly shorter > than the MTU (752 in my experiments). Do we understa

Re: [PATCH v3] virtio: Work around frames incorrectly marked as gso

2020-02-24 Thread Michael S. Tsirkin
On Mon, Feb 24, 2020 at 01:25:50PM +, anton.iva...@cambridgegreys.com wrote: > From: Anton Ivanov > > Some of the locally generated frames marked as GSO which > arrive at virtio_net_hdr_from_skb() have no GSO_TYPE, no > fragments (data_len = 0) and length significantly shorter > than the MTU

[PATCH v3] virtio: Work around frames incorrectly marked as gso

2020-02-24 Thread anton . ivanov
From: Anton Ivanov Some of the locally generated frames marked as GSO which arrive at virtio_net_hdr_from_skb() have no GSO_TYPE, no fragments (data_len = 0) and length significantly shorter than the MTU (752 in my experiments). This is observed on raw sockets reading off vEth interfaces in all