[NET]: Merge TSO/UFO fields in sk_buff
Having separate fields in sk_buff for TSO/UFO (tso_size/ufo_size) is not
going to scale if we add any more segmentation methods (e.g., DCCP). So
let's merge them.
They were used to tell the protocol of a packet. This function has been
subsumed by the new gso_type field. This is essentially a set of netdev
feature bits (shifted by 16 bits) that are required to process a specific
skb. As such it's easy to tell whether a given device can process a GSO
skb: you just have to and the gso_type field and the netdev's features
field.
I've made gso_type a conjunction. The idea is that you have a base type
(e.g., SKB_GSO_TCPV4) that can be modified further to support new features.
For example, if we add a hardware TSO type that supports ECN, they would
declare NETIF_F_TSO | NETIF_F_TSO_ECN. All TSO packets with CWR set would
have a gso_type of SKB_GSO_TCPV4 | SKB_GSO_TCPV4_ECN while all other TSO
packets would be SKB_GSO_TCPV4. This means that only the CWR packets need
to be emulated in software.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c
index 0dca027c..8be9f21 100644
--- a/net/bridge/br_forward.c
+++ b/net/bridge/br_forward.c
@@ -34,8 +34,8 @@
int br_dev_queue_push_xmit(struct sk_buff *skb)
{
- /* drop mtu oversized packets except tso */
- if (packet_length(skb) > skb->dev->mtu && !skb_shinfo(skb)->tso_size)
+ /* drop mtu oversized packets except gso */
+ if (packet_length(skb) > skb->dev->mtu && !skb_shinfo(skb)->gso_size)
kfree_skb(skb);
else {
#ifdef CONFIG_BRIDGE_NETFILTER
diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c
index 3e41f9d..8298a51 100644
--- a/net/bridge/br_netfilter.c
+++ b/net/bridge/br_netfilter.c
@@ -761,7 +761,7 @@
{
if (skb->protocol == htons(ETH_P_IP) &&
skb->len > skb->dev->mtu &&
- !(skb_shinfo(skb)->ufo_size || skb_shinfo(skb)->tso_size))
+ !skb_shinfo(skb)->gso_size)
return ip_fragment(skb, br_dev_queue_push_xmit);
else
return br_dev_queue_push_xmit(skb);
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index fe63d4e..368d985 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -172,9 +172,9 @@
shinfo = skb_shinfo(skb);
atomic_set(&shinfo->dataref, 1);
shinfo->nr_frags = 0;
- shinfo->tso_size = 0;
- shinfo->tso_segs = 0;
- shinfo->ufo_size = 0;
+ shinfo->gso_size = 0;
+ shinfo->gso_segs = 0;
+ shinfo->gso_type = 0;
shinfo->ip6_frag_id = 0;
shinfo->frag_list = NULL;
@@ -238,8 +238,9 @@
atomic_set(&(skb_shinfo(skb)->dataref), 1);
skb_shinfo(skb)->nr_frags = 0;
- skb_shinfo(skb)->tso_size = 0;
- skb_shinfo(skb)->tso_segs = 0;
+ skb_shinfo(skb)->gso_size = 0;
+ skb_shinfo(skb)->gso_segs = 0;
+ skb_shinfo(skb)->gso_type = 0;
skb_shinfo(skb)->frag_list = NULL;
out:
return skb;
@@ -528,8 +529,9 @@
#endif
skb_copy_secmark(new, old);
atomic_set(&new->users, 1);
- skb_shinfo(new)->tso_size = skb_shinfo(old)->tso_size;
- skb_shinfo(new)->tso_segs = skb_shinfo(old)->tso_segs;
+ skb_shinfo(new)->gso_size = skb_shinfo(old)->gso_size;
+ skb_shinfo(new)->gso_segs = skb_shinfo(old)->gso_segs;
+ skb_shinfo(new)->gso_type = skb_shinfo(old)->gso_type;
}
/**
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 8538aac..7624fd1 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -210,8 +210,7 @@
return dst_output(skb);
}
#endif
- if (skb->len > dst_mtu(skb->dst) &&
- !(skb_shinfo(skb)->ufo_size || skb_shinfo(skb)->tso_size))
+ if (skb->len > dst_mtu(skb->dst) && !skb_shinfo(skb)->gso_size)
return ip_fragment(skb, ip_finish_output2);
else
return ip_finish_output2(skb);
@@ -362,7 +361,7 @@
}
ip_select_ident_more(iph, &rt->u.dst, sk,
- (skb_shinfo(skb)->tso_segs ?: 1) - 1);
+ (skb_shinfo(skb)->gso_segs ?: 1) - 1);
/* Add an IP checksum. */
ip_send_check(iph);
@@ -744,7 +743,8 @@
(length - transhdrlen));
if (!err) {
/* specify the length of each IP datagram fragment*/
- skb_shinfo(skb)->ufo_size = (mtu - fragheaderlen);
+ skb_shinfo(skb)->gso_size = mtu - fragheaderlen;
+ skb_shinfo(skb)->gso_type = SKB_GSO_UDPV4;
__skb_queue_tail(&sk->sk_write_queue, skb);
return 0;
@@ -1087,14 +1087,16 @@
inet->cork.length += size;
if ((sk->sk_protocol == IPPROTO_UDP) &&
- (rt->u.dst.dev->features & NETIF_F_UFO))
- skb_shinfo(skb)->ufo_size = (mtu - fragheaderlen);
+ (rt->u.dst.dev->features & NETIF_F_UFO)) {
+ skb_shinfo(skb)->gso_size = mtu - fragheaderlen;
+ skb_shinfo(skb)->gso_type = SKB_GSO_UDPV4;
+ }
while (size > 0) {
int i;
- if (skb_shinfo(skb)->ufo_size)
+ if (skb_shinfo(skb)->gso_size)
len = size;
else {
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 74998f2..062dd1a 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -571,7 +571,7 @@
skb->ip_summed = CHECKSUM_HW;
tp->write_seq += copy;
TCP_SKB_CB(skb)->end_seq += copy;
- skb_shinfo(skb)->tso_segs = 0;
+ skb_shinfo(skb)->gso_segs = 0;
if (!copied)
TCP_SKB_CB(skb)->flags &= ~TCPCB_FLAG_PSH;
@@ -818,7 +818,7 @@
tp->write_seq += copy;
TCP_SKB_CB(skb)->end_seq += copy;
- skb_shinfo(skb)->tso_segs = 0;
+ skb_shinfo(skb)->gso_segs = 0;
from += copy;
copied += copy;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index e08245b..94fe5b1 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1073,7 +1073,7 @@
else
pkt_len = (end_seq -
TCP_SKB_CB(skb)->seq);
- if (tcp_fragment(sk, skb, pkt_len, skb_shinfo(skb)->tso_size))
+ if (tcp_fragment(sk, skb, pkt_len, skb_shinfo(skb)->gso_size))
break;
pcount = tcp_skb_pcount(skb);
}
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 07bb5a2..bdd71db 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -515,15 +515,17 @@
/* Avoid the costly divide in the normal
* non-TSO case.
*/
- skb_shinfo(skb)->tso_segs = 1;
- skb_shinfo(skb)->tso_size = 0;
+ skb_shinfo(skb)->gso_segs = 1;
+ skb_shinfo(skb)->gso_size = 0;
+ skb_shinfo(skb)->gso_type = 0;
} else {
unsigned int factor;
factor = skb->len + (mss_now - 1);
factor /= mss_now;
- skb_shinfo(skb)->tso_segs = factor;
- skb_shinfo(skb)->tso_size = mss_now;
+ skb_shinfo(skb)->gso_segs = factor;
+ skb_shinfo(skb)->gso_size = mss_now;
+ skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4;
}
}
@@ -914,7 +916,7 @@
if (!tso_segs ||
(tso_segs > 1 &&
- skb_shinfo(skb)->tso_size != mss_now)) {
+ tcp_skb_mss(skb) != mss_now)) {
tcp_set_skb_tso_segs(sk, skb, mss_now);
tso_segs = tcp_skb_pcount(skb);
}
@@ -1724,8 +1726,9 @@
tp->snd_una == (TCP_SKB_CB(skb)->end_seq - 1)) {
if (!pskb_trim(skb, 0)) {
TCP_SKB_CB(skb)->seq = TCP_SKB_CB(skb)->end_seq - 1;
- skb_shinfo(skb)->tso_segs = 1;
- skb_shinfo(skb)->tso_size = 0;
+ skb_shinfo(skb)->gso_segs = 1;
+ skb_shinfo(skb)->gso_size = 0;
+ skb_shinfo(skb)->gso_type = 0;
skb->ip_summed = CHECKSUM_NONE;
skb->csum = 0;
}
@@ -1930,8 +1933,9 @@
skb->csum = 0;
TCP_SKB_CB(skb)->flags = (TCPCB_FLAG_ACK | TCPCB_FLAG_FIN);
TCP_SKB_CB(skb)->sacked = 0;
- skb_shinfo(skb)->tso_segs = 1;
- skb_shinfo(skb)->tso_size = 0;
+ skb_shinfo(skb)->gso_segs = 1;
+ skb_shinfo(skb)->gso_size = 0;
+ skb_shinfo(skb)->gso_type = 0;
/* FIN eats a sequence byte, write_seq advanced by tcp_queue_skb(). */
TCP_SKB_CB(skb)->seq = tp->write_seq;
@@ -1963,8 +1967,9 @@
skb->csum = 0;
TCP_SKB_CB(skb)->flags = (TCPCB_FLAG_ACK | TCPCB_FLAG_RST);
TCP_SKB_CB(skb)->sacked = 0;
- skb_shinfo(skb)->tso_segs = 1;
- skb_shinfo(skb)->tso_size = 0;
+ skb_shinfo(skb)->gso_segs = 1;
+ skb_shinfo(skb)->gso_size = 0;
+ skb_shinfo(skb)->gso_type = 0;
/* Send it off. */
TCP_SKB_CB(skb)->seq = tcp_acceptable_seq(sk, tp);
@@ -2047,8 +2052,9 @@
TCP_SKB_CB(skb)->seq = tcp_rsk(req)->snt_isn;
TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(skb)->seq + 1;
TCP_SKB_CB(skb)->sacked = 0;
- skb_shinfo(skb)->tso_segs = 1;
- skb_shinfo(skb)->tso_size = 0;
+ skb_shinfo(skb)->gso_segs = 1;
+ skb_shinfo(skb)->gso_size = 0;
+ skb_shinfo(skb)->gso_type = 0;
th->seq = htonl(TCP_SKB_CB(skb)->seq);
th->ack_seq = htonl(tcp_rsk(req)->rcv_isn + 1);
if (req->rcv_wnd == 0) { /* ignored for retransmitted syns */
@@ -2152,8 +2158,9 @@
TCP_SKB_CB(buff)->flags = TCPCB_FLAG_SYN;
TCP_ECN_send_syn(sk, tp, buff);
TCP_SKB_CB(buff)->sacked = 0;
- skb_shinfo(buff)->tso_segs = 1;
- skb_shinfo(buff)->tso_size = 0;
+ skb_shinfo(buff)->gso_segs = 1;
+ skb_shinfo(buff)->gso_size = 0;
+ skb_shinfo(buff)->gso_type = 0;
buff->csum = 0;
TCP_SKB_CB(buff)->seq = tp->write_seq++;
TCP_SKB_CB(buff)->end_seq = tp->write_seq;
@@ -2257,8 +2264,9 @@
buff->csum = 0;
TCP_SKB_CB(buff)->flags = TCPCB_FLAG_ACK;
TCP_SKB_CB(buff)->sacked = 0;
- skb_shinfo(buff)->tso_segs = 1;
- skb_shinfo(buff)->tso_size = 0;
+ skb_shinfo(buff)->gso_segs = 1;
+ skb_shinfo(buff)->gso_size = 0;
+ skb_shinfo(buff)->gso_type = 0;
/* Send it off, this clears delayed acks for us. */
TCP_SKB_CB(buff)->seq = TCP_SKB_CB(buff)->end_seq = tcp_acceptable_seq(sk, tp);
@@ -2293,8 +2301,9 @@
skb->csum = 0;
TCP_SKB_CB(skb)->flags = TCPCB_FLAG_ACK;
TCP_SKB_CB(skb)->sacked = urgent;
- skb_shinfo(skb)->tso_segs = 1;
- skb_shinfo(skb)->tso_size = 0;
+ skb_shinfo(skb)->gso_segs = 1;
+ skb_shinfo(skb)->gso_size = 0;
+ skb_shinfo(skb)->gso_type = 0;
/* Use a previous sequence. This should cause the other
* end to send an ack. Don't queue or clone SKB, just
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index d29620f..abb94de 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -148,7 +148,7 @@
int ip6_output(struct sk_buff *skb)
{
- if ((skb->len > dst_mtu(skb->dst) && !skb_shinfo(skb)->ufo_size) ||
+ if ((skb->len > dst_mtu(skb->dst) && !skb_shinfo(skb)->gso_size) ||
dst_allfrag(skb->dst))
return ip6_fragment(skb, ip6_output2);
else
@@ -833,8 +833,9 @@
struct frag_hdr fhdr;
/* specify the length of each IP datagram fragment*/
- skb_shinfo(skb)->ufo_size = (mtu - fragheaderlen) -
- sizeof(struct frag_hdr);
+ skb_shinfo(skb)->gso_size = mtu - fragheaderlen -
+ sizeof(struct frag_hdr);
+ skb_shinfo(skb)->gso_type = SKB_GSO_UDPV4;
ipv6_select_ident(skb, &fhdr);
skb_shinfo(skb)->ip6_frag_id = fhdr.identification;
__skb_queue_tail(&sk->sk_write_queue, skb);
