From: Eric Dumazet edumazet@google.com
stable inclusion from stable-v6.6.33 commit 00bb933578acd88395bf6e770cacdbe2d6a0be86 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IAD6H2
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...
--------------------------------
[ Upstream commit ec00ed472bdb7d0af840da68c8c11bff9f4d9caa ]
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 Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Wang Hai wanghai38@huawei.com --- net/ipv4/tcp_ipv4.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-)
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index de1424efb996..1d2740b92083 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1823,7 +1823,7 @@ 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; @@ -1832,6 +1832,7 @@ 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()), @@ -1929,7 +1930,13 @@ 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. @@ -1937,6 +1944,8 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb, */ 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;