net: use indirect call wrappers for skb_copy_datagram_iter()

TCP recvmsg() calls skb_copy_datagram_iter(), which
calls an indirect function (cb pointing to simple_copy_to_iter())
for every MSS (fragment) present in the skb.

CONFIG_RETPOLINE=y forces a very expensive operation
that we can avoid thanks to indirect call wrappers.

This patch gives a 13% increase of performance on
a single flow, if the bottleneck is the thread reading
the TCP socket.

Fixes: 950fcaecd5cc ("datagram: consolidate datagram copy to iter helpers")
Signed-off-by: Eric Dumazet <[e-mail]>
Acked-by: Paolo Abeni <[e-mail]>
Acked-by: Willem de Bruijn <[e-mail]>
Signed-off-by: David S. Miller <[e-mail]>

net/core/datagram.c

···
 #include <linux/slab.h>
 #include <linux/pagemap.h>
 #include <linux/uio.h>
+#include <linux/indirect_call_wrapper.h>
 
 #include <net/protocol.h>
 #include <linux/skbuff.h>
···
 }
 EXPORT_SYMBOL(skb_kill_datagram);
 
+INDIRECT_CALLABLE_DECLARE(static size_t simple_copy_to_iter(const void *addr,
+						size_t bytes,
+						void *data __always_unused,
+						struct iov_iter *i));
+
 static int __skb_datagram_iter(const struct sk_buff *skb, int offset,
 			       struct iov_iter *to, int len, bool fault_short,
 			       size_t (*cb)(const void *, size_t, void *,
···
 	if (copy > 0) {
 		if (copy > len)
 			copy = len;
-		n = cb(skb->data + offset, copy, data, to);
+		n = INDIRECT_CALL_1(cb, simple_copy_to_iter,
+				    skb->data + offset, copy, data, to);
 		offset += n;
 		if (n != copy)
 			goto short_copy;
···
 
 			if (copy > len)
 				copy = len;
-			n = cb(vaddr + skb_frag_off(frag) + offset - start,
-			       copy, data, to);
+			n = INDIRECT_CALL_1(cb, simple_copy_to_iter,
+					vaddr + skb_frag_off(frag) + offset - start,
+					copy, data, to);
 			kunmap(page);
 			offset += n;
 			if (n != copy)