diff options
| author | Paolo Abeni <pabeni@redhat.com> | 2022-10-20 19:48:52 +0200 |
|---|---|---|
| committer | David S. Miller <davem@davemloft.net> | 2022-10-24 10:52:50 +0100 |
| commit | 8a3854c7b8e4532063b14bed34115079b7d0cb36 (patch) | |
| tree | cd84d6b901d6d1e14185481909982e4f267cd512 /net | |
| parent | a5ef058dc4d9a3e60d1808a0700e18e0e37e408e (diff) | |
| download | linux-8a3854c7b8e4532063b14bed34115079b7d0cb36.tar.gz linux-8a3854c7b8e4532063b14bed34115079b7d0cb36.tar.bz2 linux-8a3854c7b8e4532063b14bed34115079b7d0cb36.zip | |
udp: track the forward memory release threshold in an hot cacheline
When the receiver process and the BH runs on different cores,
udp_rmem_release() experience a cache miss while accessing sk_rcvbuf,
as the latter shares the same cacheline with sk_forward_alloc, written
by the BH.
With this patch, UDP tracks the rcvbuf value and its update via custom
SOL_SOCKET socket options, and copies the forward memory threshold value
used by udp_rmem_release() in a different cacheline, already accessed by
the above function and uncontended.
Since the UDP socket init operation grown a bit, factor out the common
code between v4 and v6 in a shared helper.
Overall the above give a 10% peek throughput increase under UDP flood.
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Acked-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net')
| -rw-r--r-- | net/ipv4/udp.c | 18 | ||||
| -rw-r--r-- | net/ipv6/udp.c | 4 |
2 files changed, 17 insertions, 5 deletions
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index c83e5271030b..e77c8f0e9087 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1448,7 +1448,7 @@ static void udp_rmem_release(struct sock *sk, int size, int partial, if (likely(partial)) { up->forward_deficit += size; size = up->forward_deficit; - if (size < (sk->sk_rcvbuf >> 2) && + if (size < READ_ONCE(up->forward_threshold) && !skb_queue_empty(&up->reader_queue)) return; } else { @@ -1622,7 +1622,7 @@ static void udp_destruct_sock(struct sock *sk) int udp_init_sock(struct sock *sk) { - skb_queue_head_init(&udp_sk(sk)->reader_queue); + udp_lib_init_sock(sk); sk->sk_destruct = udp_destruct_sock; return 0; } @@ -2671,6 +2671,18 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname, int err = 0; int is_udplite = IS_UDPLITE(sk); + if (level == SOL_SOCKET) { + err = sk_setsockopt(sk, level, optname, optval, optlen); + + if (optname == SO_RCVBUF || optname == SO_RCVBUFFORCE) { + sockopt_lock_sock(sk); + /* paired with READ_ONCE in udp_rmem_release() */ + WRITE_ONCE(up->forward_threshold, sk->sk_rcvbuf >> 2); + sockopt_release_sock(sk); + } + return err; + } + if (optlen < sizeof(int)) return -EINVAL; @@ -2784,7 +2796,7 @@ EXPORT_SYMBOL(udp_lib_setsockopt); int udp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen) { - if (level == SOL_UDP || level == SOL_UDPLITE) + if (level == SOL_UDP || level == SOL_UDPLITE || level == SOL_SOCKET) return udp_lib_setsockopt(sk, level, optname, optval, optlen, udp_push_pending_frames); diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 2260406740d3..297f7cc06044 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -64,7 +64,7 @@ static void udpv6_destruct_sock(struct sock *sk) int udpv6_init_sock(struct sock *sk) { - skb_queue_head_init(&udp_sk(sk)->reader_queue); + udp_lib_init_sock(sk); sk->sk_destruct = udpv6_destruct_sock; return 0; } @@ -1669,7 +1669,7 @@ void udpv6_destroy_sock(struct sock *sk) int udpv6_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen) { - if (level == SOL_UDP || level == SOL_UDPLITE) + if (level == SOL_UDP || level == SOL_UDPLITE || level == SOL_SOCKET) return udp_lib_setsockopt(sk, level, optname, optval, optlen, udp_v6_push_pending_frames); |