udp: msg_zerocopy

Extend zerocopy to udp sockets. Allow setting sockopt SO_ZEROCOPY and
interpret flag MSG_ZEROCOPY.

This patch was previously part of the zerocopy RFC patchsets. Zerocopy
is not effective at small MTU. With segmentation offload building
larger datagrams, the benefit of page flipping outweights the cost of
generating a completion notification.

tools/testing/selftests/net/msg_zerocopy.sh after applying follow-on
test patch and making skb_orphan_frags_rx same as skb_orphan_frags:

    ipv4 udp -t 1
    tx=191312 (11938 MB) txc=0 zc=n
    rx=191312 (11938 MB)
    ipv4 udp -z -t 1
    tx=304507 (19002 MB) txc=304507 zc=y
    rx=304507 (19002 MB)
    ok
    ipv6 udp -t 1
    tx=174485 (10888 MB) txc=0 zc=n
    rx=174485 (10888 MB)
    ipv6 udp -z -t 1
    tx=294801 (18396 MB) txc=294801 zc=y
    rx=294801 (18396 MB)
    ok

Changes
  v1 -> v2
    - Fixup reverse christmas tree violation
  v2 -> v3
    - Split refcount avoidance optimization into separate patch
      - Fix refcount leak on error in fragmented case
        (thanks to Paolo Abeni for pointing this one out!)
      - Fix refcount inc on zero
      - Test sock_flag SOCK_ZEROCOPY directly in __ip_append_data.
        This is needed since commit 5cf4a8532c99 ("tcp: really ignore
	MSG_ZEROCOPY if no SO_ZEROCOPY") did the same for tcp.

Signed-off-by: Willem de Bruijn <willemb@google.com>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 22 insertions, 1 deletions

diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 5dbec21856f4..6f843aff628c 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -867,6 +867,7 @@ static int __ip_append_data(struct sock *sk,
 			    unsigned int flags)
 {
 	struct inet_sock *inet = inet_sk(sk);
+	struct ubuf_info *uarg = NULL;
 	struct sk_buff *skb;
 
 	struct ip_options *opt = cork->opt;
@@ -916,6 +917,19 @@ static int __ip_append_data(struct sock *sk,
 	    (!exthdrlen || (rt->dst.dev->features & NETIF_F_HW_ESP_TX_CSUM)))
 		csummode = CHECKSUM_PARTIAL;
 
+	if (flags & MSG_ZEROCOPY && length && sock_flag(sk, SOCK_ZEROCOPY)) {
+		uarg = sock_zerocopy_realloc(sk, length, skb_zcopy(skb));
+		if (!uarg)
+			return -ENOBUFS;
+		if (rt->dst.dev->features & NETIF_F_SG &&
+		    csummode == CHECKSUM_PARTIAL) {
+			paged = true;
+		} else {
+			uarg->zerocopy = 0;
+			skb_zcopy_set(skb, uarg);
+		}
+	}
+
 	cork->length += length;
 
 	/* So, what's going on in the loop below?
@@ -1006,6 +1020,7 @@ alloc_new_skb:
 			cork->tx_flags = 0;
 			skb_shinfo(skb)->tskey = tskey;
 			tskey = 0;
+			skb_zcopy_set(skb, uarg);
 
 			/*
 			 *	Find where to start putting bytes.
@@ -1068,7 +1083,7 @@ alloc_new_skb:
 				err = -EFAULT;
 				goto error;
 			}
-		} else {
+		} else if (!uarg || !uarg->zerocopy) {
 			int i = skb_shinfo(skb)->nr_frags;
 
 			err = -ENOMEM;
@@ -1098,6 +1113,10 @@ alloc_new_skb:
 			skb->data_len += copy;
 			skb->truesize += copy;
 			wmem_alloc_delta += copy;
+		} else {
+			err = skb_zerocopy_iter_dgram(skb, from, copy);
+			if (err < 0)
+				goto error;
 		}
 		offset += copy;
 		length -= copy;
@@ -1105,11 +1124,13 @@ alloc_new_skb:
 
 	if (wmem_alloc_delta)
 		refcount_add(wmem_alloc_delta, &sk->sk_wmem_alloc);
+	sock_zerocopy_put(uarg);
 	return 0;
 
 error_efault:
 	err = -EFAULT;
 error:
+	sock_zerocopy_put_abort(uarg);
 	cork->length -= length;
 	IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTDISCARDS);
 	refcount_add(wmem_alloc_delta, &sk->sk_wmem_alloc);