[PATCH net-next 00/20] tcp: optimizations for linux-5.17 · Eric Dumazet <hidden> · 2021-11-16
[PATCH net-next 07/20] ipv6: shrink struct ipcm6_cookie · Eric Dumazet <hidden> · 2021-11-15
[PATCH net-next 06/20] net: remove sk_route_nocaps · Eric Dumazet <hidden> · 2021-11-15
[PATCH net-next 12/20] tcp: add RETPOLINE mitigation to sk_backlog_rcv · Eric Dumazet <hidden> · 2021-11-15
[PATCH net-next 13/20] tcp: annotate data-races on tp->segs_in and tp->data_segs_in · Eric Dumazet <hidden> · 2021-11-15
[PATCH net-next 11/20] tcp: small optimization in tcp recvmsg() · Eric Dumazet <hidden> · 2021-11-15
[PATCH net-next 15/20] tcp: tp->urg_data is unlikely to be set · Eric Dumazet <hidden> · 2021-11-15
[PATCH net-next 17/20] tcp: defer skb freeing after socket lock is released · Eric Dumazet <hidden> · 2021-11-15
Re: [PATCH net-next 17/20] tcp: defer skb freeing after socket lock is released · Jakub Kicinski <kuba@kernel.org> · 2021-11-16
Re: [PATCH net-next 17/20] tcp: defer skb freeing after socket lock is released · Eric Dumazet <edumazet@google.com> · 2021-11-16
Re: [PATCH net-next 17/20] tcp: defer skb freeing after socket lock is released · Jakub Kicinski <kuba@kernel.org> · 2021-11-16
Re: [PATCH net-next 17/20] tcp: defer skb freeing after socket lock is released · Eric Dumazet <edumazet@google.com> · 2021-11-16
Re: [PATCH net-next 17/20] tcp: defer skb freeing after socket lock is released · Jakub Kicinski <kuba@kernel.org> · 2021-11-16
Re: [PATCH net-next 17/20] tcp: defer skb freeing after socket lock is released · Eric Dumazet <edumazet@google.com> · 2021-11-16
Re: [PATCH net-next 17/20] tcp: defer skb freeing after socket lock is released · Jakub Kicinski <kuba@kernel.org> · 2021-11-16
Re: [PATCH net-next 17/20] tcp: defer skb freeing after socket lock is released · David Ahern <hidden> · 2021-11-16
Re: [PATCH net-next 17/20] tcp: defer skb freeing after socket lock is released · Eric Dumazet <edumazet@google.com> · 2021-11-16
[PATCH net-next 20/20] net: move early demux fields close to sk_refcnt · Eric Dumazet <hidden> · 2021-11-15
[PATCH net-next 19/20] tcp: do not call tcp_cleanup_rbuf() if we have a backlog · Eric Dumazet <hidden> · 2021-11-15
Re: [PATCH net-next 00/20] tcp: optimizations for linux-5.17 · Soheil Hassas Yeganeh <hidden> · 2021-11-15
Re: [PATCH net-next 00/20] tcp: optimizations for linux-5.17 · Paolo Abeni <pabeni@redhat.com> · 2021-11-15
Re: [PATCH net-next 00/20] tcp: optimizations for linux-5.17 · Eric Dumazet <edumazet@google.com> · 2021-11-15
Re: [PATCH net-next 00/20] tcp: optimizations for linux-5.17 · Eric Dumazet <edumazet@google.com> · 2021-11-16
Re: [PATCH net-next 00/20] tcp: optimizations for linux-5.17 · Arjun Roy <hidden> · 2021-11-16
Re: [PATCH net-next 00/20] tcp: optimizations for linux-5.17 · David Miller <davem@davemloft.net> · 2021-11-16
Re: [PATCH net-next 00/20] tcp: optimizations for linux-5.17 · Eric Dumazet <edumazet@google.com> · 2021-11-16
[PATCH net-next 16/20] tcp: avoid indirect calls to sock_rfree · Eric Dumazet <hidden> · 2021-11-16
Re: [PATCH net-next 16/20] tcp: avoid indirect calls to sock_rfree · Arjun Roy <hidden> · 2021-11-16
[PATCH net-next 18/20] tcp: check local var (timeo) before socket fields in one test · Eric Dumazet <hidden> · 2021-11-16
[PATCH net-next 09/20] net: forward_alloc_get depends on CONFIG_MPTCP · Eric Dumazet <hidden> · 2021-11-16
[PATCH net-next 05/20] net: remove sk_route_forced_caps · Eric Dumazet <hidden> · 2021-11-16
[PATCH net-next 14/20] tcp: annotate races around tp->urg_data · Eric Dumazet <hidden> · 2021-11-16
[PATCH net-next 02/20] tcp: remove dead code in __tcp_v6_send_check() · Eric Dumazet <hidden> · 2021-11-16
Re: [PATCH net-next 02/20] tcp: remove dead code in __tcp_v6_send_check() · David Ahern <hidden> · 2021-11-16
Re: [PATCH net-next 02/20] tcp: remove dead code in __tcp_v6_send_check() · Eric Dumazet <edumazet@google.com> · 2021-11-16
[PATCH net-next 04/20] net: use sk_is_tcp() in more places · Eric Dumazet <hidden> · 2021-11-16
[PATCH net-next 08/20] net: shrink struct sock by 8 bytes · Eric Dumazet <hidden> · 2021-11-16
[PATCH net-next 10/20] net: cache align tcp_memory_allocated, tcp_sockets_allocated · Eric Dumazet <hidden> · 2021-11-16
[PATCH net-next 03/20] tcp: small optimization in tcp_v6_send_check() · Eric Dumazet <hidden> · 2021-11-16
[PATCH net-next 01/20] tcp: minor optimization in tcp_add_backlog() · Eric Dumazet <hidden> · 2021-11-16

Re: [PATCH net-next 17/20] tcp: defer skb freeing after socket lock is released

From: Jakub Kicinski <kuba@kernel.org>
Date: 2021-11-16 14:27:39

On Mon, 15 Nov 2021 11:02:46 -0800 Eric Dumazet wrote:

One cpu can now be fully utilized for the kernel->user copy,
and another cpu is handling BH processing and skb/page
allocs/frees (assuming RFS is not forcing use of a single CPU)

Are you saying the kernel->user copy is not under the socket lock
today? I'm working on getting the crypto & copy from under the socket
lock for ktls, and it looked like tcp does the copy under the lock.

`h`	back out one level
`j`	next message in thread
`k`	previous message in thread
`l`	drill in
`Esc`	close help / fold thread tree
`?`	toggle this help