Merge branch 'ipv6-net-opts'

Pavel Begunkov says:

====================
generic net and ipv6 minor optimisations

1-3 inline simple functions that only reshuffle arguments possibly adding
extra zero args, and call another function. It was benchmarked before with
a bunch of extra patches, see for details

https://lore.kernel.org/netdev/cover.1648981570.git.asml.silence@gmail.com/

It may increase the binary size, but it's the right thing to do and at least
without modules it actually sheds some bytes for some standard-ish config.

   text    data     bss     dec     hex filename
9627200       0       0 9627200  92e640 ./arch/x86_64/boot/bzImage
   text    data     bss     dec     hex filename
9627104       0       0 9627104  92e5e0 ./arch/x86_64/boot/bzImage
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

include/linux/netdevice.h

@@ -2940,10 +2940,20 @@ u16 dev_pick_tx_zero(struct net_device *dev, struct sk_buff *skb,
 u16 dev_pick_tx_cpu_id(struct net_device *dev, struct sk_buff *skb,
 		       struct net_device *sb_dev);
 
-int dev_queue_xmit(struct sk_buff *skb);
-int dev_queue_xmit_accel(struct sk_buff *skb, struct net_device *sb_dev);
+int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev);
 int __dev_direct_xmit(struct sk_buff *skb, u16 queue_id);
 
+static inline int dev_queue_xmit(struct sk_buff *skb)
+{
+	return __dev_queue_xmit(skb, NULL);
+}
+
+static inline int dev_queue_xmit_accel(struct sk_buff *skb,
+				       struct net_device *sb_dev)
+{
+	return __dev_queue_xmit(skb, sb_dev);
+}
+
 static inline int dev_direct_xmit(struct sk_buff *skb, u16 queue_id)
 {
 	int ret;

include/linux/skbuff.h

@@ -684,20 +684,6 @@ struct ubuf_info {
 int mm_account_pinned_pages(struct mmpin *mmp, size_t size);
 void mm_unaccount_pinned_pages(struct mmpin *mmp);
 
-struct ubuf_info *msg_zerocopy_alloc(struct sock *sk, size_t size);
-struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size,
-				       struct ubuf_info *uarg);
-
-void msg_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref);
-
-void msg_zerocopy_callback(struct sk_buff *skb, struct ubuf_info *uarg,
-			   bool success);
-
-int skb_zerocopy_iter_dgram(struct sk_buff *skb, struct msghdr *msg, int len);
-int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb,
-			     struct msghdr *msg, int len,
-			     struct ubuf_info *uarg);
-
 /* This data is invariant across clones and lives at
  * the end of the header data, ie. at skb->end.
  */
@@ -1679,6 +1665,28 @@ static inline void skb_set_end_offset(struct sk_buff *skb, unsigned int offset)
 }
 #endif
 
+struct ubuf_info *msg_zerocopy_alloc(struct sock *sk, size_t size);
+struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size,
+				       struct ubuf_info *uarg);
+
+void msg_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref);
+
+void msg_zerocopy_callback(struct sk_buff *skb, struct ubuf_info *uarg,
+			   bool success);
+
+int __zerocopy_sg_from_iter(struct sock *sk, struct sk_buff *skb,
+			    struct iov_iter *from, size_t length);
+
+static inline int skb_zerocopy_iter_dgram(struct sk_buff *skb,
+					  struct msghdr *msg, int len)
+{
+	return __zerocopy_sg_from_iter(skb->sk, skb, &msg->msg_iter, len);
+}
+
+int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb,
+			     struct msghdr *msg, int len,
+			     struct ubuf_info *uarg);
+
 /* Internal */
 #define skb_shinfo(SKB)	((struct skb_shared_info *)(skb_end_pointer(SKB)))
 

include/net/sock.h

@@ -1823,11 +1823,17 @@ int sock_getsockopt(struct socket *sock, int level, int op,
 		    char __user *optval, int __user *optlen);
 int sock_gettstamp(struct socket *sock, void __user *userstamp,
 		   bool timeval, bool time32);
-struct sk_buff *sock_alloc_send_skb(struct sock *sk, unsigned long size,
-				    int noblock, int *errcode);
 struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len,
 				     unsigned long data_len, int noblock,
 				     int *errcode, int max_page_order);
+
+static inline struct sk_buff *sock_alloc_send_skb(struct sock *sk,
+						  unsigned long size,
+						  int noblock, int *errcode)
+{
+	return sock_alloc_send_pskb(sk, size, 0, noblock, errcode, 0);
+}
+
 void *sock_kmalloc(struct sock *sk, int size, gfp_t priority);
 void sock_kfree_s(struct sock *sk, void *mem, int size);
 void sock_kzfree_s(struct sock *sk, void *mem, int size);

net/core/datagram.c

@@ -62,8 +62,6 @@
 #include <trace/events/skb.h>
 #include <net/busy_poll.h>
 
-#include "datagram.h"
-
 /*
  *	Is a socket 'connection oriented' ?
  */

net/core/datagram.h

-/* SPDX-License-Identifier: GPL-2.0 */
-
-#ifndef _NET_CORE_DATAGRAM_H_
-#define _NET_CORE_DATAGRAM_H_
-
-#include <linux/types.h>
-
-struct sock;
-struct sk_buff;
-struct iov_iter;
-
-int __zerocopy_sg_from_iter(struct sock *sk, struct sk_buff *skb,
-			    struct iov_iter *from, size_t length);
-
-#endif /* _NET_CORE_DATAGRAM_H_ */

net/core/dev.c

@@ -4111,7 +4111,7 @@ struct netdev_queue *netdev_core_pick_tx(struct net_device *dev,
  *      the BH enable code must have IRQs enabled so that it will not deadlock.
  *          --BLG
  */
-static int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev)
+int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev)
 {
 	struct net_device *dev = skb->dev;
 	struct netdev_queue *txq = NULL;
@@ -4235,18 +4235,7 @@ static int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev)
 	rcu_read_unlock_bh();
 	return rc;
 }
-
-int dev_queue_xmit(struct sk_buff *skb)
-{
-	return __dev_queue_xmit(skb, NULL);
-}
-EXPORT_SYMBOL(dev_queue_xmit);
-
-int dev_queue_xmit_accel(struct sk_buff *skb, struct net_device *sb_dev)
-{
-	return __dev_queue_xmit(skb, sb_dev);
-}
-EXPORT_SYMBOL(dev_queue_xmit_accel);
+EXPORT_SYMBOL(__dev_queue_xmit);
 
 int __dev_direct_xmit(struct sk_buff *skb, u16 queue_id)
 {

net/core/skbuff.c

@@ -80,7 +80,6 @@
 #include <linux/user_namespace.h>
 #include <linux/indirect_call_wrapper.h>
 
-#include "datagram.h"
 #include "sock_destructor.h"
 
 struct kmem_cache *skbuff_head_cache __ro_after_init;
@@ -1340,12 +1339,6 @@ void msg_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref)
 }
 EXPORT_SYMBOL_GPL(msg_zerocopy_put_abort);
 
-int skb_zerocopy_iter_dgram(struct sk_buff *skb, struct msghdr *msg, int len)
-{
-	return __zerocopy_sg_from_iter(skb->sk, skb, &msg->msg_iter, len);
-}
-EXPORT_SYMBOL_GPL(skb_zerocopy_iter_dgram);
-
 int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb,
 			     struct msghdr *msg, int len,
 			     struct ubuf_info *uarg)

net/core/sock.c

@@ -2635,13 +2635,6 @@ struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len,
 }
 EXPORT_SYMBOL(sock_alloc_send_pskb);
 
-struct sk_buff *sock_alloc_send_skb(struct sock *sk, unsigned long size,
-				    int noblock, int *errcode)
-{
-	return sock_alloc_send_pskb(sk, size, 0, noblock, errcode, 0);
-}
-EXPORT_SYMBOL(sock_alloc_send_skb);
-
 int __sock_cmsg_send(struct sock *sk, struct msghdr *msg, struct cmsghdr *cmsg,
 		     struct sockcm_cookie *sockc)
 {

net/ipv6/ip6_output.c

@@ -119,19 +119,21 @@ static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff *
 	rcu_read_lock_bh();
 	nexthop = rt6_nexthop((struct rt6_info *)dst, daddr);
 	neigh = __ipv6_neigh_lookup_noref(dev, nexthop);
-	if (unlikely(!neigh))
-		neigh = __neigh_create(&nd_tbl, nexthop, dev, false);
-	if (!IS_ERR(neigh)) {
-		sock_confirm_neigh(skb, neigh);
-		ret = neigh_output(neigh, skb, false);
-		rcu_read_unlock_bh();
-		return ret;
+
+	if (unlikely(IS_ERR_OR_NULL(neigh))) {
+		if (unlikely(!neigh))
+			neigh = __neigh_create(&nd_tbl, nexthop, dev, false);
+		if (IS_ERR(neigh)) {
+			rcu_read_unlock_bh();
+			IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTNOROUTES);
+			kfree_skb_reason(skb, SKB_DROP_REASON_NEIGH_CREATEFAIL);
+			return -EINVAL;
+		}
 	}
+	sock_confirm_neigh(skb, neigh);
+	ret = neigh_output(neigh, skb, false);
 	rcu_read_unlock_bh();
-
-	IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTNOROUTES);
-	kfree_skb_reason(skb, SKB_DROP_REASON_NEIGH_CREATEFAIL);
-	return -EINVAL;
+	return ret;
 }
 
 static int
@@ -198,7 +200,6 @@ static int ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff *s
 	ret = BPF_CGROUP_RUN_PROG_INET_EGRESS(sk, skb);
 	switch (ret) {
 	case NET_XMIT_SUCCESS:
-		return __ip6_finish_output(net, sk, skb);
 	case NET_XMIT_CN:
 		return __ip6_finish_output(net, sk, skb) ? : ret;
 	default: