net: introduce SO_INCOMING_CPU

Alternative to RPS/RFS is to use hardware support for multiple
queues.

Then split a set of million of sockets into worker threads, each
one using epoll() to manage events on its own socket pool.

Ideally, we want one thread per RX/TX queue/cpu, but we have no way to
know after accept() or connect() on which queue/cpu a socket is managed.

We normally use one cpu per RX queue (IRQ smp_affinity being properly
set), so remembering on socket structure which cpu delivered last packet
is enough to solve the problem.

After accept(), connect(), or even file descriptor passing around
processes, applications can use :

 int cpu;
 socklen_t len = sizeof(cpu);

 getsockopt(fd, SOL_SOCKET, SO_INCOMING_CPU, &cpu, &len);

And use this information to put the socket into the right silo
for optimal performance, as all networking stack should run
on the appropriate cpu, without need to send IPI (RPS/RFS).

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

21 files changed, 52 insertions, 2 deletions

diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h
index 3de1394..e2fe070 100644
--- a/arch/alpha/include/uapi/asm/socket.h
+++ b/arch/alpha/include/uapi/asm/socket.h
@@ -87,4 +87,6 @@
 
 #define SO_BPF_EXTENSIONS	48
 
+#define SO_INCOMING_CPU		49
+
 #endif /* _UAPI_ASM_SOCKET_H */
diff --git a/arch/avr32/include/uapi/asm/socket.h b/arch/avr32/include/uapi/asm/socket.h
index 6e6cd15..92121b0 100644
--- a/arch/avr32/include/uapi/asm/socket.h
+++ b/arch/avr32/include/uapi/asm/socket.h
@@ -80,4 +80,6 @@
 
 #define SO_BPF_EXTENSIONS	48
 
+#define SO_INCOMING_CPU		49
+
 #endif /* _UAPI__ASM_AVR32_SOCKET_H */
diff --git a/arch/cris/include/uapi/asm/socket.h b/arch/cris/include/uapi/asm/socket.h
index ed94e5e..60f60f5 100644
--- a/arch/cris/include/uapi/asm/socket.h
+++ b/arch/cris/include/uapi/asm/socket.h
@@ -82,6 +82,8 @@
 
 #define SO_BPF_EXTENSIONS	48
 
+#define SO_INCOMING_CPU		49
+
 #endif /* _ASM_SOCKET_H */
 
 
diff --git a/arch/frv/include/uapi/asm/socket.h b/arch/frv/include/uapi/asm/socket.h
index ca2c6e6..2c68902 100644
--- a/arch/frv/include/uapi/asm/socket.h
+++ b/arch/frv/include/uapi/asm/socket.h
@@ -80,5 +80,7 @@
 
 #define SO_BPF_EXTENSIONS	48
 
+#define SO_INCOMING_CPU		49
+
 #endif /* _ASM_SOCKET_H */
 
diff --git a/arch/ia64/include/uapi/asm/socket.h b/arch/ia64/include/uapi/asm/socket.h
index a1b49ba..09a93fb 100644
--- a/arch/ia64/include/uapi/asm/socket.h
+++ b/arch/ia64/include/uapi/asm/socket.h
@@ -89,4 +89,6 @@
 
 #define SO_BPF_EXTENSIONS	48
 
+#define SO_INCOMING_CPU		49
+
 #endif /* _ASM_IA64_SOCKET_H */
diff --git a/arch/m32r/include/uapi/asm/socket.h b/arch/m32r/include/uapi/asm/socket.h
index 6c9a24b..e858981 100644
--- a/arch/m32r/include/uapi/asm/socket.h
+++ b/arch/m32r/include/uapi/asm/socket.h
@@ -80,4 +80,6 @@
 
 #define SO_BPF_EXTENSIONS	48
 
+#define SO_INCOMING_CPU		49
+
 #endif /* _ASM_M32R_SOCKET_H */
diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h
index a14baa2..2e9ee8c 100644
--- a/arch/mips/include/uapi/asm/socket.h
+++ b/arch/mips/include/uapi/asm/socket.h
@@ -98,4 +98,6 @@
 
 #define SO_BPF_EXTENSIONS	48
 
+#define SO_INCOMING_CPU		49
+
 #endif /* _UAPI_ASM_SOCKET_H */
diff --git a/arch/mn10300/include/uapi/asm/socket.h b/arch/mn10300/include/uapi/asm/socket.h
index 6aa3ce1..f3492e8c9 100644
--- a/arch/mn10300/include/uapi/asm/socket.h
+++ b/arch/mn10300/include/uapi/asm/socket.h
@@ -80,4 +80,6 @@
 
 #define SO_BPF_EXTENSIONS	48
 
+#define SO_INCOMING_CPU		49
+
 #endif /* _ASM_SOCKET_H */
diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h
index fe35cea..7984a1c 100644
--- a/arch/parisc/include/uapi/asm/socket.h
+++ b/arch/parisc/include/uapi/asm/socket.h
@@ -79,4 +79,6 @@
 
 #define SO_BPF_EXTENSIONS	0x4029
 
+#define SO_INCOMING_CPU		0x402A
+
 #endif /* _UAPI_ASM_SOCKET_H */
diff --git a/arch/powerpc/include/uapi/asm/socket.h b/arch/powerpc/include/uapi/asm/socket.h
index a9c3e2e..3474e4e 100644
--- a/arch/powerpc/include/uapi/asm/socket.h
+++ b/arch/powerpc/include/uapi/asm/socket.h
@@ -87,4 +87,6 @@
 
 #define SO_BPF_EXTENSIONS	48
 
+#define SO_INCOMING_CPU		49
+
 #endif	/* _ASM_POWERPC_SOCKET_H */
diff --git a/arch/s390/include/uapi/asm/socket.h b/arch/s390/include/uapi/asm/socket.h
index e031332..8457636 100644
--- a/arch/s390/include/uapi/asm/socket.h
+++ b/arch/s390/include/uapi/asm/socket.h
@@ -86,4 +86,6 @@
 
 #define SO_BPF_EXTENSIONS	48
 
+#define SO_INCOMING_CPU		49
+
 #endif /* _ASM_SOCKET_H */
diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h
index 54d9608..4a8003a 100644
--- a/arch/sparc/include/uapi/asm/socket.h
+++ b/arch/sparc/include/uapi/asm/socket.h
@@ -76,6 +76,8 @@
 
 #define SO_BPF_EXTENSIONS	0x0032
 
+#define SO_INCOMING_CPU		0x0033
+
 /* Security levels - as per NRL IPv6 - don't actually do anything */
 #define SO_SECURITY_AUTHENTICATION		0x5001
 #define SO_SECURITY_ENCRYPTION_TRANSPORT	0x5002
diff --git a/arch/xtensa/include/uapi/asm/socket.h b/arch/xtensa/include/uapi/asm/socket.h
index 39acec0c..c46f6a6 100644
--- a/arch/xtensa/include/uapi/asm/socket.h
+++ b/arch/xtensa/include/uapi/asm/socket.h
@@ -91,4 +91,6 @@
 
 #define SO_BPF_EXTENSIONS	48
 
+#define SO_INCOMING_CPU		49
+
 #endif	/* _XTENSA_SOCKET_H */
diff --git a/include/net/sock.h b/include/net/sock.h
index 6767d75..7789b59 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -273,6 +273,7 @@ struct cg_proto;
   *	@sk_rcvtimeo: %SO_RCVTIMEO setting
   *	@sk_sndtimeo: %SO_SNDTIMEO setting
   *	@sk_rxhash: flow hash received from netif layer
+  *	@sk_incoming_cpu: record cpu processing incoming packets
   *	@sk_txhash: computed flow hash for use on transmit
   *	@sk_filter: socket filtering instructions
   *	@sk_protinfo: private area, net family specific, when not using slab
@@ -350,6 +351,12 @@ struct sock {
 #ifdef CONFIG_RPS
 	__u32			sk_rxhash;
 #endif
+	u16			sk_incoming_cpu;
+	/* 16bit hole
+	 * Warned : sk_incoming_cpu can be set from softirq,
+	 * Do not use this hole without fully understanding possible issues.
+	 */
+
 	__u32			sk_txhash;
 #ifdef CONFIG_NET_RX_BUSY_POLL
 	unsigned int		sk_napi_id;
@@ -833,6 +840,11 @@ static inline int sk_backlog_rcv(struct sock *sk, struct sk_buff *skb)
 	return sk->sk_backlog_rcv(sk, skb);
 }
 
+static inline void sk_incoming_cpu_update(struct sock *sk)
+{
+	sk->sk_incoming_cpu = raw_smp_processor_id();
+}
+
 static inline void sock_rps_record_flow_hash(__u32 hash)
 {
 #ifdef CONFIG_RPS
diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h
index ea0796b..f541cce 100644
--- a/include/uapi/asm-generic/socket.h
+++ b/include/uapi/asm-generic/socket.h
@@ -82,4 +82,6 @@
 
 #define SO_BPF_EXTENSIONS	48
 
+#define SO_INCOMING_CPU		49
+
 #endif /* __ASM_GENERIC_SOCKET_H */
diff --git a/net/core/sock.c b/net/core/sock.c
index ac56dd0..0725cf0 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1213,6 +1213,10 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
 		v.val = sk->sk_max_pacing_rate;
 		break;
 
+	case SO_INCOMING_CPU:
+		v.val = sk->sk_incoming_cpu;
+		break;
+
 	default:
 		return -ENOPROTOOPT;
 	}
@@ -1517,6 +1521,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 
 		newsk->sk_err	   = 0;
 		newsk->sk_priority = 0;
+		newsk->sk_incoming_cpu = raw_smp_processor_id();
 		/*
 		 * Before updating sk_refcnt, we must commit prior changes to memory
 		 * (Documentation/RCU/rculist_nulls.txt for details)
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 8893598..2c6a955 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1663,6 +1663,7 @@ process:
 	if (sk_filter(sk, skb))
 		goto discard_and_relse;
 
+	sk_incoming_cpu_update(sk);
 	skb->dev = NULL;
 
 	bh_lock_sock_nested(sk);
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 5d0fdca..d137516 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1445,6 +1445,7 @@ static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 	if (inet_sk(sk)->inet_daddr) {
 		sock_rps_save_rxhash(sk, skb);
 		sk_mark_napi_id(sk, skb);
+		sk_incoming_cpu_update(sk);
 	}
 
 	rc = sock_queue_rcv_skb(sk, skb);
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index fd8e50b..1985b49 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1456,6 +1456,7 @@ process:
 	if (sk_filter(sk, skb))
 		goto discard_and_relse;
 
+	sk_incoming_cpu_update(sk);
 	skb->dev = NULL;
 
 	bh_lock_sock_nested(sk);
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index b756355..d1fe362 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -577,6 +577,7 @@ static int __udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 	if (!ipv6_addr_any(&sk->sk_v6_daddr)) {
 		sock_rps_save_rxhash(sk, skb);
 		sk_mark_napi_id(sk, skb);
+		sk_incoming_cpu_update(sk);
 	}
 
 	rc = sock_queue_rcv_skb(sk, skb);
diff --git a/net/sctp/ulpqueue.c b/net/sctp/ulpqueue.c
index d49dc2ed..ce469d6 100644
--- a/net/sctp/ulpqueue.c
+++ b/net/sctp/ulpqueue.c
@@ -205,9 +205,10 @@ int sctp_ulpq_tail_event(struct sctp_ulpq *ulpq, struct sctp_ulpevent *event)
 	if (sock_flag(sk, SOCK_DEAD) || (sk->sk_shutdown & RCV_SHUTDOWN))
 		goto out_free;
 
-	if (!sctp_ulpevent_is_notification(event))
+	if (!sctp_ulpevent_is_notification(event)) {
 		sk_mark_napi_id(sk, skb);
-
+		sk_incoming_cpu_update(sk);
+	}
 	/* Check if the user wishes to receive this event.  */
 	if (!sctp_ulpevent_is_enabled(event, &sctp_sk(sk)->subscribe))
 		goto out_free;