Re: [net-next PATCH] tcp: Add logic to check for SYN w/ data in tcp_simple_retransmit

On Sat, Dec 12, 2020 at 11:07 AM Yuchung Cheng wrote: > > On Sat, Dec 12, 2020 at 11:01 AM Alexander Duyck > wrote: > > > > On Sat, Dec 12, 2020 at 10:34 AM Yuchung Cheng wrote: > > > > > > On Fri, Dec 11, 2020 at 5:28 PM Alexander Duyck > > > wrote: > > > > > > > > From: Alexander Duyck > > >

Re: [net-next PATCH] tcp: Add logic to check for SYN w/ data in tcp_simple_retransmit

On Sat, Dec 12, 2020 at 11:01 AM Alexander Duyck wrote: > > On Sat, Dec 12, 2020 at 10:34 AM Yuchung Cheng wrote: > > > > On Fri, Dec 11, 2020 at 5:28 PM Alexander Duyck > > wrote: > > > > > > From: Alexander Duyck > > > > > > There are cases where a fastopen SYN may trigger either a ICMP_TOOBI

Re: [net-next PATCH] tcp: Add logic to check for SYN w/ data in tcp_simple_retransmit

On Sat, Dec 12, 2020 at 10:34 AM Yuchung Cheng wrote: > > On Fri, Dec 11, 2020 at 5:28 PM Alexander Duyck > wrote: > > > > From: Alexander Duyck > > > > There are cases where a fastopen SYN may trigger either a ICMP_TOOBIG > > message in the case of IPv6 or a fragmentation request in the case of

Re: [net-next PATCH] tcp: Add logic to check for SYN w/ data in tcp_simple_retransmit

On Fri, Dec 11, 2020 at 5:28 PM Alexander Duyck wrote: > > From: Alexander Duyck > > There are cases where a fastopen SYN may trigger either a ICMP_TOOBIG > message in the case of IPv6 or a fragmentation request in the case of > IPv4. This results in the socket stalling for a second or more as it

[net-next PATCH] tcp: Add logic to check for SYN w/ data in tcp_simple_retransmit

From: Alexander Duyck There are cases where a fastopen SYN may trigger either a ICMP_TOOBIG message in the case of IPv6 or a fragmentation request in the case of IPv4. This results in the socket stalling for a second or more as it does not respond to the message by retransmitting the SYN frame.