| Message ID | 2dede94e742d8096d6ac5e0f1979054ee158d9a8.1666287924.git.pabeni@redhat.com (mailing list archive) |
|---|---|
| State | Accepted |
| Commit | 8a3854c7b8e4532063b14bed34115079b7d0cb36 |
| Delegated to: | Netdev Maintainers |
| Headers | show |
| Series | udp: avoid false sharing on receive | expand |
On Thu, Oct 20, 2022 at 10:49 AM Paolo Abeni <pabeni@redhat.com> wrote: > > 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>
From: Paolo Abeni <pabeni@redhat.com> Date: Thu, 20 Oct 2022 19:48:52 +0200 > 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> Acked-by: Kuniyuki Iwashima <kuniyu@amazon.com> Thank you! > --- > v1 -> v2: > - factor out common init helper for udp && udpv6 sock (Kuniyuki) > --- > include/linux/udp.h | 3 +++ > include/net/udp.h | 9 +++++++++ > net/ipv4/udp.c | 18 +++++++++++++++--- > net/ipv6/udp.c | 4 ++-- > 4 files changed, 29 insertions(+), 5 deletions(-) > > diff --git a/include/linux/udp.h b/include/linux/udp.h > index e96da4157d04..5cdba00a904a 100644 > --- a/include/linux/udp.h > +++ b/include/linux/udp.h > @@ -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) > diff --git a/include/net/udp.h b/include/net/udp.h > index fee053bcd17c..de4b528522bb 100644 > --- a/include/net/udp.h > +++ b/include/net/udp.h > @@ -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) > { > diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c > index 8126f67d18b3..e361ad93999e 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 8d09f0ea5b8c..b0bc4e27ec2f 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; > } > @@ -1671,7 +1671,7 @@ 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); > -- > 2.37.3
diff --git a/include/linux/udp.h b/include/linux/udp.h index e96da4157d04..5cdba00a904a 100644 --- a/include/linux/udp.h +++ b/include/linux/udp.h @@ -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) diff --git a/include/net/udp.h b/include/net/udp.h index fee053bcd17c..de4b528522bb 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -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) { diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 8126f67d18b3..e361ad93999e 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 8d09f0ea5b8c..b0bc4e27ec2f 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; } @@ -1671,7 +1671,7 @@ 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);
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> --- v1 -> v2: - factor out common init helper for udp && udpv6 sock (Kuniyuki) --- include/linux/udp.h | 3 +++ include/net/udp.h | 9 +++++++++ net/ipv4/udp.c | 18 +++++++++++++++--- net/ipv6/udp.c | 4 ++-- 4 files changed, 29 insertions(+), 5 deletions(-)