Merge branch 'tcp-optimizations'

Eric Dumazet says:

====================
tcp: optimizations for linux-5.17

Mostly small improvements in this series.

The notable change is in "defer skb freeing after
socket lock is released" in recvmsg() (and RX zerocopy)

The idea is to try to let skb freeing to BH handler,
whenever possible, or at least perform the freeing
outside of the socket lock section, for much improved
performance. This idea can probably be extended
to other protocols.

 Tests on a 100Gbit NIC
 Max throughput for one TCP_STREAM flow, over 10 runs.

 MTU : 1500  (1428 bytes of TCP payload per MSS)
 Before: 55 Gbit
 After:  66 Gbit

 MTU : 4096+ (4096 bytes of TCP payload, plus TCP/IPv6 headers)
 Before: 82 Gbit
 After:  95 Gbit
====================

Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Author: davem330

include/linux/skbuff.h

@@ -36,6 +36,7 @@
 #include <linux/splice.h>
 #include <linux/in6.h>
 #include <linux/if_packet.h>
+#include <linux/llist.h>
 #include <net/flow.h>
 #include <net/page_pool.h>
 #if IS_ENABLED(CONFIG_NF_CONNTRACK)
@@ -743,6 +744,7 @@ struct sk_buff {
 		};
 		struct rb_node		rbnode; /* used in netem, ip4 defrag, and tcp stack */
 		struct list_head	list;
+		struct llist_node	ll_node;
 	};
 
 	union {

include/linux/skmsg.h

@@ -507,12 +507,6 @@ static inline bool sk_psock_strp_enabled(struct sk_psock *psock)
 	return !!psock->saved_data_ready;
 }
 
-static inline bool sk_is_tcp(const struct sock *sk)
-{
-	return sk->sk_type == SOCK_STREAM &&
-	       sk->sk_protocol == IPPROTO_TCP;
-}
-
 static inline bool sk_is_udp(const struct sock *sk)
 {
 	return sk->sk_type == SOCK_DGRAM &&

include/net/ip6_checksum.h

@@ -65,15 +65,9 @@ static inline void __tcp_v6_send_check(struct sk_buff *skb,
 {
 	struct tcphdr *th = tcp_hdr(skb);
 
-	if (skb->ip_summed == CHECKSUM_PARTIAL) {
-		th->check = ~tcp_v6_check(skb->len, saddr, daddr, 0);
-		skb->csum_start = skb_transport_header(skb) - skb->head;
-		skb->csum_offset = offsetof(struct tcphdr, check);
-	} else {
-		th->check = tcp_v6_check(skb->len, saddr, daddr,
-					 csum_partial(th, th->doff << 2,
-						      skb->csum));
-	}
+	th->check = ~tcp_v6_check(skb->len, saddr, daddr, 0);
+	skb->csum_start = skb_transport_header(skb) - skb->head;
+	skb->csum_offset = offsetof(struct tcphdr, check);
 }
 
 static inline void tcp_v6_gso_csum_prep(struct sk_buff *skb)

include/net/ipv6.h

@@ -345,9 +345,9 @@ struct ipcm6_cookie {
 	struct sockcm_cookie sockc;
 	__s16 hlimit;
 	__s16 tclass;
+	__u16 gso_size;
 	__s8  dontfrag;
 	struct ipv6_txoptions *opt;
-	__u16 gso_size;
 };
 
 static inline void ipcm6_init(struct ipcm6_cookie *ipc6)

include/net/sock.h

@@ -63,6 +63,7 @@
 #include <linux/indirect_call_wrapper.h>
 #include <linux/atomic.h>
 #include <linux/refcount.h>
+#include <linux/llist.h>
 #include <net/dst.h>
 #include <net/checksum.h>
 #include <net/tcp_states.h>
@@ -284,9 +285,7 @@ struct bpf_local_storage;
   *	@sk_no_check_tx: %SO_NO_CHECK setting, set checksum in TX packets
   *	@sk_no_check_rx: allow zero checksum in RX packets
   *	@sk_route_caps: route capabilities (e.g. %NETIF_F_TSO)
-  *	@sk_route_nocaps: forbidden route capabilities (e.g NETIF_F_GSO_MASK)
-  *	@sk_route_forced_caps: static, forced route capabilities
-  *		(set in tcp_init_sock())
+  *	@sk_gso_disabled: if set, NETIF_F_GSO_MASK is forbidden.
   *	@sk_gso_type: GSO type (e.g. %SKB_GSO_TCPV4)
   *	@sk_gso_max_size: Maximum GSO segment size to build
   *	@sk_gso_max_segs: Maximum number of GSO segments
@@ -391,6 +390,11 @@ struct sock {
 #define sk_flags		__sk_common.skc_flags
 #define sk_rxhash		__sk_common.skc_rxhash
 
+	/* early demux fields */
+	struct dst_entry	*sk_rx_dst;
+	int			sk_rx_dst_ifindex;
+	u32			sk_rx_dst_cookie;
+
 	socket_lock_t		sk_lock;
 	atomic_t		sk_drops;
 	int			sk_rcvlowat;
@@ -410,6 +414,8 @@ struct sock {
 		struct sk_buff	*head;
 		struct sk_buff	*tail;
 	} sk_backlog;
+	struct llist_head defer_list;
+
 #define sk_rmem_alloc sk_backlog.rmem_alloc
 
 	int			sk_forward_alloc;
@@ -431,9 +437,6 @@ struct sock {
 #ifdef CONFIG_XFRM
 	struct xfrm_policy __rcu *sk_policy[2];
 #endif
-	struct dst_entry	*sk_rx_dst;
-	int			sk_rx_dst_ifindex;
-	u32			sk_rx_dst_cookie;
 
 	struct dst_entry __rcu	*sk_dst_cache;
 	atomic_t		sk_omem_alloc;
@@ -460,8 +463,6 @@ struct sock {
 	unsigned long		sk_max_pacing_rate;
 	struct page_frag	sk_frag;
 	netdev_features_t	sk_route_caps;
-	netdev_features_t	sk_route_nocaps;
-	netdev_features_t	sk_route_forced_caps;
 	int			sk_gso_type;
 	unsigned int		sk_gso_max_size;
 	gfp_t			sk_allocation;
@@ -471,7 +472,7 @@ struct sock {
 	 * Because of non atomicity rules, all
 	 * changes are protected by socket lock.
 	 */
-	u8			sk_padding : 1,
+	u8			sk_gso_disabled : 1,
 				sk_kern_sock : 1,
 				sk_no_check_tx : 1,
 				sk_no_check_rx : 1,
@@ -493,6 +494,7 @@ struct sock {
 	u16			sk_busy_poll_budget;
 #endif
 	spinlock_t		sk_peer_lock;
+	int			sk_bind_phc;
 	struct pid		*sk_peer_pid;
 	const struct cred	*sk_peer_cred;
 
@@ -502,7 +504,6 @@ struct sock {
 	seqlock_t		sk_stamp_seq;
 #endif
 	u16			sk_tsflags;
-	int			sk_bind_phc;
 	u8			sk_shutdown;
 	u32			sk_tskey;
 	atomic_t		sk_zckey;
@@ -1022,12 +1023,18 @@ static inline __must_check int sk_add_backlog(struct sock *sk, struct sk_buff *s
 
 int __sk_backlog_rcv(struct sock *sk, struct sk_buff *skb);
 
+INDIRECT_CALLABLE_DECLARE(int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb));
+INDIRECT_CALLABLE_DECLARE(int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb));
+
 static inline int sk_backlog_rcv(struct sock *sk, struct sk_buff *skb)
 {
 	if (sk_memalloc_socks() && skb_pfmemalloc(skb))
 		return __sk_backlog_rcv(sk, skb);
 
-	return sk->sk_backlog_rcv(sk, skb);
+	return INDIRECT_CALL_INET(sk->sk_backlog_rcv,
+				  tcp_v6_do_rcv,
+				  tcp_v4_do_rcv,
+				  sk, skb);
 }
 
 static inline void sk_incoming_cpu_update(struct sock *sk)
@@ -1210,7 +1217,9 @@ struct proto {
 	unsigned int		inuse_idx;
 #endif
 
+#if IS_ENABLED(CONFIG_MPTCP)
 	int			(*forward_alloc_get)(const struct sock *sk);
+#endif
 
 	bool			(*stream_memory_free)(const struct sock *sk, int wake);
 	bool			(*sock_is_readable)(struct sock *sk);
@@ -1299,10 +1308,11 @@ INDIRECT_CALLABLE_DECLARE(bool tcp_stream_memory_free(const struct sock *sk, int
 
 static inline int sk_forward_alloc_get(const struct sock *sk)
 {
-	if (!sk->sk_prot->forward_alloc_get)
-		return sk->sk_forward_alloc;
-
-	return sk->sk_prot->forward_alloc_get(sk);
+#if IS_ENABLED(CONFIG_MPTCP)
+	if (sk->sk_prot->forward_alloc_get)
+		return sk->sk_prot->forward_alloc_get(sk);
+#endif
+	return sk->sk_forward_alloc;
 }
 
 static inline bool __sk_stream_memory_free(const struct sock *sk, int wake)
@@ -2124,10 +2134,10 @@ static inline bool sk_can_gso(const struct sock *sk)
 
 void sk_setup_caps(struct sock *sk, struct dst_entry *dst);
 
-static inline void sk_nocaps_add(struct sock *sk, netdev_features_t flags)
+static inline void sk_gso_disable(struct sock *sk)
 {
-	sk->sk_route_nocaps |= flags;
-	sk->sk_route_caps &= ~flags;
+	sk->sk_gso_disabled = 1;
+	sk->sk_route_caps &= ~NETIF_F_GSO_MASK;
 }
 
 static inline int skb_do_copy_data_nocache(struct sock *sk, struct sk_buff *skb,
@@ -2638,6 +2648,11 @@ static inline void skb_setup_tx_timestamp(struct sk_buff *skb, __u16 tsflags)
 			   &skb_shinfo(skb)->tskey);
 }
 
+static inline bool sk_is_tcp(const struct sock *sk)
+{
+	return sk->sk_type == SOCK_STREAM && sk->sk_protocol == IPPROTO_TCP;
+}
+
 /**
  * sk_eat_skb - Release a skb if it is no longer needed
  * @sk: socket to eat this skb from

include/net/tcp.h

@@ -1368,6 +1368,16 @@ static inline bool tcp_checksum_complete(struct sk_buff *skb)
 }
 
 bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb);
+
+void __sk_defer_free_flush(struct sock *sk);
+
+static inline void sk_defer_free_flush(struct sock *sk)
+{
+	if (llist_empty(&sk->defer_list))
+		return;
+	__sk_defer_free_flush(sk);
+}
+
 int tcp_filter(struct sock *sk, struct sk_buff *skb);
 void tcp_set_state(struct sock *sk, int state);
 void tcp_done(struct sock *sk);
@@ -2172,9 +2182,13 @@ static inline void tcp_segs_in(struct tcp_sock *tp, const struct sk_buff *skb)
 	u16 segs_in;
 
 	segs_in = max_t(u16, 1, skb_shinfo(skb)->gso_segs);
-	tp->segs_in += segs_in;
+
+	/* We update these fields while other threads might
+	 * read them from tcp_get_info()
+	 */
+	WRITE_ONCE(tp->segs_in, tp->segs_in + segs_in);
 	if (skb->len > tcp_hdrlen(skb))
-		tp->data_segs_in += segs_in;
+		WRITE_ONCE(tp->data_segs_in, tp->data_segs_in + segs_in);
 }
 
 /*

net/core/skbuff.c

@@ -4849,8 +4849,7 @@ static void __skb_complete_tx_timestamp(struct sk_buff *skb,
 	serr->header.h4.iif = skb->dev ? skb->dev->ifindex : 0;
 	if (sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID) {
 		serr->ee.ee_data = skb_shinfo(skb)->tskey;
-		if (sk->sk_protocol == IPPROTO_TCP &&
-		    sk->sk_type == SOCK_STREAM)
+		if (sk_is_tcp(sk))
 			serr->ee.ee_data -= sk->sk_tskey;
 	}
 
@@ -4919,8 +4918,7 @@ void __skb_tstamp_tx(struct sk_buff *orig_skb,
 	if (tsonly) {
 #ifdef CONFIG_INET
 		if ((sk->sk_tsflags & SOF_TIMESTAMPING_OPT_STATS) &&
-		    sk->sk_protocol == IPPROTO_TCP &&
-		    sk->sk_type == SOCK_STREAM) {
+		    sk_is_tcp(sk)) {
 			skb = tcp_get_timestamping_opt_stats(sk, orig_skb,
 							     ack_skb);
 			opt_stats = true;

net/core/sock.c

@@ -327,7 +327,10 @@ int __sk_backlog_rcv(struct sock *sk, struct sk_buff *skb)
 	BUG_ON(!sock_flag(sk, SOCK_MEMALLOC));
 
 	noreclaim_flag = memalloc_noreclaim_save();
-	ret = sk->sk_backlog_rcv(sk, skb);
+	ret = INDIRECT_CALL_INET(sk->sk_backlog_rcv,
+				 tcp_v6_do_rcv,
+				 tcp_v4_do_rcv,
+				 sk, skb);
 	memalloc_noreclaim_restore(noreclaim_flag);
 
 	return ret;
@@ -872,8 +875,7 @@ int sock_set_timestamping(struct sock *sk, int optname,
 
 	if (val & SOF_TIMESTAMPING_OPT_ID &&
 	    !(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID)) {
-		if (sk->sk_protocol == IPPROTO_TCP &&
-		    sk->sk_type == SOCK_STREAM) {
+		if (sk_is_tcp(sk)) {
 			if ((1 << sk->sk_state) &
 			    (TCPF_CLOSE | TCPF_LISTEN))
 				return -EINVAL;
@@ -1370,8 +1372,7 @@ int sock_setsockopt(struct socket *sock, int level, int optname,
 
 	case SO_ZEROCOPY:
 		if (sk->sk_family == PF_INET || sk->sk_family == PF_INET6) {
-			if (!((sk->sk_type == SOCK_STREAM &&
-			       sk->sk_protocol == IPPROTO_TCP) ||
+			if (!(sk_is_tcp(sk) ||
 			      (sk->sk_type == SOCK_DGRAM &&
 			       sk->sk_protocol == IPPROTO_UDP)))
 				ret = -ENOTSUPP;
@@ -2246,10 +2247,13 @@ void sk_setup_caps(struct sock *sk, struct dst_entry *dst)
 	u32 max_segs = 1;
 
 	sk_dst_set(sk, dst);
-	sk->sk_route_caps = dst->dev->features | sk->sk_route_forced_caps;
+	sk->sk_route_caps = dst->dev->features;
+	if (sk_is_tcp(sk))
+		sk->sk_route_caps |= NETIF_F_GSO;
 	if (sk->sk_route_caps & NETIF_F_GSO)
 		sk->sk_route_caps |= NETIF_F_GSO_SOFTWARE;
-	sk->sk_route_caps &= ~sk->sk_route_nocaps;
+	if (unlikely(sk->sk_gso_disabled))
+		sk->sk_route_caps &= ~NETIF_F_GSO_MASK;
 	if (sk_can_gso(sk)) {
 		if (dst->header_len && !xfrm_dst_offload_ok(dst)) {
 			sk->sk_route_caps &= ~NETIF_F_GSO_MASK;