Messages in this thread | | | Date | Mon, 3 Jul 2023 11:25:50 -0600 | Subject | Re: Memory providers multiplexing (Was: [PATCH net-next v4 4/5] page_pool: remove PP_FLAG_PAGE_FRAG flag) | From | David Ahern <> |
| |
On 7/3/23 11:15 AM, Eric Dumazet wrote: > On Mon, Jul 3, 2023 at 4:45 PM David Ahern <dsahern@kernel.org> wrote: > >> That is my expectation. The tcpdump is just an easy example of accessing >> the skb page frags. skb_copy_and_csum_bits used by icmp is another >> example that can walk frags wanting access to device memory. You did not >> cause a panic or trip a WARN_ON for example with the tcpdump? >> > > ICMP packets do not land on the queues having devmem buffers, for > obvious reasons.
I was not referring to ICMP packets coming in to the nic, but rather an icmp getting triggered during stack processing.
> > Only chosen TCP flows are steered to these queues.
of course.
| |