On Wed, Dec 5, 2018 at 12:33 PM Peter Oskolkov <posk.de...@gmail.com> wrote: > > FWIW, I find the patch really useful - I applied it to my local dev > repo (with minor changes) and use skb_dump() a lot now. It would be > great if it makes its way into net-next in some form.
+1 very informative. skb_warn_bad_offload would also benefit from more packet detail. And please consider logging device info, too. I'm currently debugging a (non-reproducible so far, so relying purely on the log message) stack trace for a packet that triggers that warning in validate_xmit_skb on the path to an unknown virtual device. > On Fri, Nov 30, 2018 at 12:15 PM Saeed Mahameed <sae...@mellanox.com> wrote: > > > > On Thu, 2018-11-22 at 17:45 -0800, Cong Wang wrote: > > > On Wed, Nov 21, 2018 at 11:33 AM Saeed Mahameed <sae...@mellanox.com> > > > wrote: > > > > On Wed, 2018-11-21 at 10:26 -0800, Eric Dumazet wrote: > > > > > On Wed, Nov 21, 2018 at 10:17 AM Cong Wang < > > > > > xiyou.wangc...@gmail.com> > > > > > wrote: > > > > > > On Wed, Nov 21, 2018 at 5:05 AM Eric Dumazet < > > > > > > eric.duma...@gmail.com> wrote: > > > > > > > > > > > > > > On 11/20/2018 06:13 PM, Cong Wang wrote: > > > > > > > > Currently, we only dump a few selected skb fields in > > > > > > > > netdev_rx_csum_fault(). It is not suffient for debugging > > > > > > > > checksum > > > > > > > > fault. This patch introduces skb_dump() which dumps skb mac > > > > > > > > header, > > > > > > > > network header and its whole skb->data too. > > > > > > > > > > > > > > > > Cc: Herbert Xu <herb...@gondor.apana.org.au> > > > > > > > > Cc: Eric Dumazet <eduma...@google.com> > > > > > > > > Cc: David Miller <da...@davemloft.net> > > > > > > > > Signed-off-by: Cong Wang <xiyou.wangc...@gmail.com> > > > > > > > > --- > > > > > > > > + print_hex_dump(level, "skb data: ", > > > > > > > > DUMP_PREFIX_OFFSET, > > > > > > > > 16, 1, > > > > > > > > + skb->data, skb->len, false); > > > > > > > > > > > > > > As I mentioned to David, we want all the bytes that were > > > > > > > maybe > > > > > > > already pulled > > > > > > > > > > > > > > (skb->head starting point, not skb->data) > > > > > > > > > > > > Hmm, with mac header and network header, it is effectively from > > > > > > skb->head, no? > > > > > > Is there anything between skb->head and mac header? > > > > > > > > > > Oh, I guess we wanted a single hex dump, or we need some user > > > > > program > > > > > to be able to > > > > > rebuild from different memory zones the original > > > > > CHECKSUM_COMPLETE > > > > > value. > > > > > > > > > > > > > Normally the driver keeps some headroom @skb->head, so the actual > > > > mac > > > > header starts @ skb->head + driver_specific_headroom > > > > > > Good to know, but this headroom isn't covered by skb->csum, so > > > not useful here, right? The skb->csum for mlx5 only covers network > > > header and its payload. > > > > correct > >
