diff options
| author | Eric Dumazet <edumazet@google.com> | 2024-04-23 12:56:20 +0000 |
|---|---|---|
| committer | Jakub Kicinski <kuba@kernel.org> | 2024-04-25 12:15:02 -0700 |
| commit | ec00ed472bdb7d0af840da68c8c11bff9f4d9caa (patch) | |
| tree | 7b9bb64d8735b8f6f94c6b211959765da79f2f46 /net/ipv4/tcp_ipv4.c | |
| parent | e6be197f23c5cf15fb4a5acac213b77f80e8cf96 (diff) | |
tcp: avoid premature drops in tcp_add_backlog()
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: c377411f2494 ("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>
Diffstat (limited to 'net/ipv4/tcp_ipv4.c')
| -rw-r--r-- | net/ipv4/tcp_ipv4.c | 13 |
1 files changed, 11 insertions, 2 deletions
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 88c83ac42129..e06f0cd04f7e 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1995,7 +1995,7 @@ int tcp_v4_early_demux(struct sk_buff *skb) bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb, enum skb_drop_reason *reason) { - u32 limit, tail_gso_size, tail_gso_segs; + u32 tail_gso_size, tail_gso_segs; struct skb_shared_info *shinfo; const struct tcphdr *th; struct tcphdr *thtail; @@ -2004,6 +2004,7 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb, bool fragstolen; u32 gso_segs; u32 gso_size; + u64 limit; int delta; /* In case all data was pulled from skb frags (in __pskb_pull_tail()), @@ -2099,7 +2100,13 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb, __skb_push(skb, hdrlen); no_coalesce: - limit = (u32)READ_ONCE(sk->sk_rcvbuf) + (u32)(READ_ONCE(sk->sk_sndbuf) >> 1); + /* sk->sk_backlog.len is reset only at the end of __release_sock(). + * Both sk->sk_backlog.len and sk->sk_rmem_alloc could reach + * sk_rcvbuf in normal conditions. + */ + limit = ((u64)READ_ONCE(sk->sk_rcvbuf)) << 1; + + limit += ((u32)READ_ONCE(sk->sk_sndbuf)) >> 1; /* Only socket owner can try to collapse/prune rx queues * to reduce memory overhead, so add a little headroom here. @@ -2107,6 +2114,8 @@ no_coalesce: */ limit += 64 * 1024; + limit = min_t(u64, limit, UINT_MAX); + if (unlikely(sk_add_backlog(sk, skb, limit))) { bh_unlock_sock(sk); *reason = SKB_DROP_REASON_SOCKET_BACKLOG; |