tcp: avoid premature drops in tcp_add_backlog()

Browse source

While testing TCP performance with latest trees,
I saw suspect SOCKET_BACKLOG drops.

tcp_add_backlog() computes its limit with :

    limit = (u32)READ_ONCE(sk->sk_rcvbuf) +
            (u32)(READ_ONCE(sk->sk_sndbuf) >> 1);
    limit += 64 * 1024;

This does not take into account that sk->sk_backlog.len
is reset only at the very end of __release_sock().

Both sk->sk_backlog.len and sk->sk_rmem_alloc could reach
sk_rcvbuf in normal conditions.

We should double sk->sk_rcvbuf contribution in the formula
to absorb bubbles in the backlog, which happen more often
for very fast flows.

This change maintains decent protection against abuses.

Fixes: c377411f24 ("net: sk_add_backlog() take rmem_alloc into account")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20240423125620.3309458-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

...

This commit is contained in:

Eric Dumazet 2024-04-23 12:56:20 +00:00 • committed by Jakub Kicinski

parent e6be197f23

commit ec00ed472b

1 changed files with 11 additions and 2 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download patch file Download diff file Expand all files Collapse all files

13

net/ipv4/tcp_ipv4.c

View file