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>
This commit is contained in:
Paolo Abeni 2022-10-20 19:48:52 +02:00 committed by David S. Miller
parent a5ef058dc4
commit 8a3854c7b8
4 changed files with 29 additions and 5 deletions

View File

@ -87,6 +87,9 @@ struct udp_sock {
/* This field is dirtied by udp_recvmsg() */
int forward_deficit;
/* This fields follows rcvbuf value, and is touched by udp_recvmsg */
int forward_threshold;
};
#define UDP_MAX_SEGMENTS (1 << 6UL)

View File

@ -174,6 +174,15 @@ INDIRECT_CALLABLE_DECLARE(int udpv6_rcv(struct sk_buff *));
struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb,
netdev_features_t features, bool is_ipv6);
static inline void udp_lib_init_sock(struct sock *sk)
{
struct udp_sock *up = udp_sk(sk);
skb_queue_head_init(&up->reader_queue);
up->forward_threshold = sk->sk_rcvbuf >> 2;
set_bit(SOCK_CUSTOM_SOCKOPT, &sk->sk_socket->flags);
}
/* hash routines shared between UDPv4/6 and UDP-Litev4/6 */
static inline int udp_lib_hash(struct sock *sk)
{

View File

@ -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);

View File

@ -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);