From: Willem de Bruijn <will...@google.com>
When sending large datagrams that are later segmented, store data in
page frags to avoid copying from linear in skb_segment.
This logic will also be used by zerocopy.
Signed-off-by: Willem de Bruijn <will...@google.com>
---
net/ipv4/ip_output.c | 15 +++++++++++----
net/ipv6/ip6_output.c | 19 ++++++++++++++-----
2 files changed, 25 insertions(+), 9 deletions(-)
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 7abfb24ec5e5..9ccd6c28e420 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -878,11 +878,13 @@ static int __ip_append_data(struct sock *sk,
struct rtable *rt = (struct rtable *)cork->dst;
unsigned int wmem_alloc_delta = 0;
u32 tskey = 0;
+ bool paged;
skb = skb_peek_tail(queue);
exthdrlen = !skb ? rt->dst.header_len : 0;
mtu = cork->gso_size ? IP_MAX_MTU : cork->fragsize;
+ paged = !!cork->gso_size;
if (cork->tx_flags & SKBTX_ANY_SW_TSTAMP &&
sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID)
@@ -934,6 +936,7 @@ static int __ip_append_data(struct sock *sk,
unsigned int fraglen;
unsigned int fraggap;
unsigned int alloclen;
+ unsigned int pagedlen = 0;
struct sk_buff *skb_prev;
alloc_new_skb:
skb_prev = skb;
@@ -954,8 +957,12 @@ static int __ip_append_data(struct sock *sk,
if ((flags & MSG_MORE) &&
!(rt->dst.dev->features&NETIF_F_SG))
alloclen = mtu;
- else
+ else if (!paged)
alloclen = fraglen;
+ else {
+ alloclen = min_t(int, fraglen, MAX_HEADER);
+ pagedlen = fraglen - alloclen;
+ }
alloclen += exthdrlen;
@@ -999,7 +1006,7 @@ static int __ip_append_data(struct sock *sk,
/*
* Find where to start putting bytes.
*/
- data = skb_put(skb, fraglen + exthdrlen);
+ data = skb_put(skb, fraglen + exthdrlen - pagedlen);
skb_set_network_header(skb, exthdrlen);
skb->transport_header = (skb->network_header +
fragheaderlen);
@@ -1015,7 +1022,7 @@ static int __ip_append_data(struct sock *sk,
pskb_trim_unique(skb_prev, maxfraglen);
}
- copy = datalen - transhdrlen - fraggap;
+ copy = datalen - transhdrlen - fraggap - pagedlen;
if (copy > 0 && getfrag(from, data + transhdrlen,
offset, copy, fraggap, skb) < 0) {
err = -EFAULT;
kfree_skb(skb);
@@ -1023,7 +1030,7 @@ static int __ip_append_data(struct sock *sk,
}
offset += copy;
- length -= datalen - fraggap;
+ length -= copy + transhdrlen;
transhdrlen = 0;
exthdrlen = 0;
csummode = CHECKSUM_NONE;
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 3ce947c1d173..9fbcec4fb946 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1270,6 +1270,7 @@ static int __ip6_append_data(struct sock *sk,
int csummode = CHECKSUM_NONE;
unsigned int maxnonfragsize, headersize;
unsigned int wmem_alloc_delta = 0;
+ bool paged;
skb = skb_peek_tail(queue);
if (!skb) {
@@ -1277,6 +1278,7 @@ static int __ip6_append_data(struct sock *sk,
dst_exthdrlen = rt->dst.header_len - rt->rt6i_nfheader_len;
}
+ paged = !!cork->gso_size;
mtu = cork->gso_size ? IP6_MAX_MTU : cork->fragsize;
orig_mtu = mtu;
@@ -1368,6 +1370,7 @@ static int __ip6_append_data(struct sock *sk,
unsigned int fraglen;
unsigned int fraggap;
unsigned int alloclen;
+ unsigned int pagedlen = 0;
alloc_new_skb:
/* There's no room in the current skb */
if (skb)
@@ -1390,11 +1393,17 @@ static int __ip6_append_data(struct sock *sk,
if (datalen > (cork->length <= mtu && !(cork->flags &
IPCORK_ALLFRAG) ? mtu : maxfraglen) - fragheaderlen)
datalen = maxfraglen - fragheaderlen -
rt->dst.trailer_len;
+ fraglen = datalen + fragheaderlen;
+
if ((flags & MSG_MORE) &&
!(rt->dst.dev->features&NETIF_F_SG))
alloclen = mtu;
- else
- alloclen = datalen + fragheaderlen;
+ else if (!paged)
+ alloclen = fraglen;
+ else {
+ alloclen = min_t(int, fraglen, MAX_HEADER);
+ pagedlen = fraglen - alloclen;
+ }
alloclen += dst_exthdrlen;
@@ -1416,7 +1425,7 @@ static int __ip6_append_data(struct sock *sk,
*/
alloclen += sizeof(struct frag_hdr);
- copy = datalen - transhdrlen - fraggap;
+ copy = datalen - transhdrlen - fraggap - pagedlen;
if (copy < 0) {
err = -EINVAL;
goto error;
@@ -1455,7 +1464,7 @@ static int __ip6_append_data(struct sock *sk,
/*
* Find where to start putting bytes
*/
- data = skb_put(skb, fraglen);
+ data = skb_put(skb, fraglen - pagedlen);
skb_set_network_header(skb, exthdrlen);
data += fragheaderlen;
skb->transport_header = (skb->network_header +
@@ -1478,7 +1487,7 @@ static int __ip6_append_data(struct sock *sk,
}
offset += copy;
- length -= datalen - fraggap;
+ length -= copy + transhdrlen;
transhdrlen = 0;
exthdrlen = 0;
dst_exthdrlen = 0;
--
2.17.0.484.g0c8726318c-goog
