From mboxrd@z Thu Jan 1 00:00:00 1970 From: Willem de Bruijn Subject: [PATCH net-next RFC 08/10] packet: enable sendmsg zerocopy Date: Thu, 20 Aug 2015 10:36:47 -0400 Message-ID: <1440081408-12302-9-git-send-email-willemb@google.com> References: <1440081408-12302-1-git-send-email-willemb@google.com> Cc: mst@redhat.com, jasowang@redhat.com, Willem de Bruijn To: netdev@vger.kernel.org Return-path: Received: from mail-qk0-f179.google.com ([209.85.220.179]:36478 "EHLO mail-qk0-f179.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752662AbbHTOg6 (ORCPT ); Thu, 20 Aug 2015 10:36:58 -0400 Received: by qkep139 with SMTP id p139so16167970qke.3 for ; Thu, 20 Aug 2015 07:36:57 -0700 (PDT) In-Reply-To: <1440081408-12302-1-git-send-email-willemb@google.com> Sender: netdev-owner@vger.kernel.org List-ID: From: Willem de Bruijn Support MSG_ZEROCOPY on PF_PACKET transmission. Signed-off-by: Willem de Bruijn --- net/packet/af_packet.c | 45 +++++++++++++++++++++++++++++++++++---------- 1 file changed, 35 insertions(+), 10 deletions(-) diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index b5afe53..8c5588b 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2476,28 +2476,47 @@ out: static struct sk_buff *packet_alloc_skb(struct sock *sk, size_t prepad, size_t reserve, size_t len, - size_t linear, int noblock, + size_t linear, int flags, int *err) { struct sk_buff *skb; + size_t data_len; - /* Under a page? Don't bother with paged skb. */ - if (prepad + len < PAGE_SIZE || !linear) - linear = len; + if (flags & MSG_ZEROCOPY) { + /* Minimize linear, but respect header lower bound */ + linear = min(len, max_t(size_t, linear, MAX_HEADER)); + data_len = 0; + } else { + /* Under a page? Don't bother with paged skb. */ + if (prepad + len < PAGE_SIZE || !linear) + linear = len; + data_len = len - linear; + } - skb = sock_alloc_send_pskb(sk, prepad + linear, len - linear, noblock, - err, 0); + skb = sock_alloc_send_pskb(sk, prepad + linear, data_len, + flags & MSG_DONTWAIT, err, 0); if (!skb) return NULL; skb_reserve(skb, reserve); skb_put(skb, linear); - skb->data_len = len - linear; - skb->len += len - linear; + skb->data_len = data_len; + skb->len += data_len; return skb; } +static int packet_zerocopy_sg_from_iovec(struct sk_buff *skb, + struct msghdr *msg, size_t size) +{ + if (zerocopy_sg_from_iter(skb, &msg->msg_iter)) + return -EIO; + if (!skb_zerocopy_alloc(skb, size)) + return -ENOMEM; + + return 0; +} + static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; @@ -2515,6 +2534,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) int hlen, tlen; int extra_len = 0; ssize_t n; + bool zerocopy = msg->msg_flags & MSG_ZEROCOPY; /* * Get and verify the address. @@ -2611,7 +2631,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) tlen = dev->needed_tailroom; skb = packet_alloc_skb(sk, hlen + tlen, hlen, len, __virtio16_to_cpu(false, vnet_hdr.hdr_len), - msg->msg_flags & MSG_DONTWAIT, &err); + msg->msg_flags, &err); if (skb == NULL) goto out_unlock; @@ -2628,7 +2648,11 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) } /* Returns -EFAULT on error */ - err = skb_copy_datagram_from_iter(skb, offset, &msg->msg_iter, len); + if (zerocopy) + err = packet_zerocopy_sg_from_iovec(skb, msg, len); + else + err = skb_copy_datagram_from_iter(skb, offset, &msg->msg_iter, + len); if (err) goto out_free; @@ -2690,6 +2714,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) return len; out_free: + sock_zerocopy_put_abort(skb_zcopy(skb)); kfree_skb(skb); out_unlock: if (dev) -- 2.5.0.276.gf5e568e