net: tcp: move GRO/GSO functions to tcp_offload

Would be good to make things explicit and move those functions to
a new file called tcp_offload.c, thus make this similar to tcpv6_offload.c.
While moving all related functions into tcp_offload.c, we can also
make some of them static, since they are only used there. Also, add
an explicit registration function.

Suggested-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This commit is contained in:
Daniel Borkmann 2013-06-07 05:11:46 +00:00 committed by David S. Miller
parent 5ee9859157
commit 28850dc7c7
6 changed files with 341 additions and 322 deletions

View File

@ -1541,15 +1541,14 @@ extern struct request_sock_ops tcp6_request_sock_ops;
extern void tcp_v4_destroy_sock(struct sock *sk);
extern int tcp_v4_gso_send_check(struct sk_buff *skb);
extern struct sk_buff *tcp_tso_segment(struct sk_buff *skb,
netdev_features_t features);
extern struct sk_buff **tcp_gro_receive(struct sk_buff **head,
struct sk_buff *skb);
extern struct sk_buff **tcp4_gro_receive(struct sk_buff **head,
struct sk_buff *skb);
extern int tcp_gro_complete(struct sk_buff *skb);
extern int tcp4_gro_complete(struct sk_buff *skb);
extern void __tcp_v4_send_check(struct sk_buff *skb, __be32 saddr,
__be32 daddr);
#ifdef CONFIG_PROC_FS
extern int tcp4_proc_init(void);
@ -1584,6 +1583,8 @@ struct tcp_request_sock_ops {
#endif
};
extern int tcpv4_offload_init(void);
extern void tcp_v4_init(void);
extern void tcp_init(void);

View File

@ -8,7 +8,7 @@ obj-y := route.o inetpeer.o protocol.o \
inet_timewait_sock.o inet_connection_sock.o \
tcp.o tcp_input.o tcp_output.o tcp_timer.o tcp_ipv4.o \
tcp_minisocks.o tcp_cong.o tcp_metrics.o tcp_fastopen.o \
datagram.o raw.o udp.o udplite.o \
tcp_offload.o datagram.o raw.o udp.o udplite.o \
arp.o icmp.o devinet.o af_inet.o igmp.o \
fib_frontend.o fib_semantics.o fib_trie.o \
inet_fragment.o ping.o

View File

@ -1559,15 +1559,6 @@ static const struct net_protocol tcp_protocol = {
.netns_ok = 1,
};
static const struct net_offload tcp_offload = {
.callbacks = {
.gso_send_check = tcp_v4_gso_send_check,
.gso_segment = tcp_tso_segment,
.gro_receive = tcp4_gro_receive,
.gro_complete = tcp4_gro_complete,
},
};
static const struct net_protocol udp_protocol = {
.handler = udp_rcv,
.err_handler = udp_err,
@ -1683,8 +1674,8 @@ static int __init ipv4_offload_init(void)
*/
if (inet_add_offload(&udp_offload, IPPROTO_UDP) < 0)
pr_crit("%s: Cannot add UDP protocol offload\n", __func__);
if (inet_add_offload(&tcp_offload, IPPROTO_TCP) < 0)
pr_crit("%s: Cannot add TCP protocol offlaod\n", __func__);
if (tcpv4_offload_init() < 0)
pr_crit("%s: Cannot add TCP protocol offload\n", __func__);
dev_add_offload(&ip_packet_offload);
return 0;

View File

@ -2877,247 +2877,6 @@ int compat_tcp_getsockopt(struct sock *sk, int level, int optname,
EXPORT_SYMBOL(compat_tcp_getsockopt);
#endif
struct sk_buff *tcp_tso_segment(struct sk_buff *skb,
netdev_features_t features)
{
struct sk_buff *segs = ERR_PTR(-EINVAL);
struct tcphdr *th;
unsigned int thlen;
unsigned int seq;
__be32 delta;
unsigned int oldlen;
unsigned int mss;
struct sk_buff *gso_skb = skb;
__sum16 newcheck;
bool ooo_okay, copy_destructor;
if (!pskb_may_pull(skb, sizeof(*th)))
goto out;
th = tcp_hdr(skb);
thlen = th->doff * 4;
if (thlen < sizeof(*th))
goto out;
if (!pskb_may_pull(skb, thlen))
goto out;
oldlen = (u16)~skb->len;
__skb_pull(skb, thlen);
mss = tcp_skb_mss(skb);
if (unlikely(skb->len <= mss))
goto out;
if (skb_gso_ok(skb, features | NETIF_F_GSO_ROBUST)) {
/* Packet is from an untrusted source, reset gso_segs. */
int type = skb_shinfo(skb)->gso_type;
if (unlikely(type &
~(SKB_GSO_TCPV4 |
SKB_GSO_DODGY |
SKB_GSO_TCP_ECN |
SKB_GSO_TCPV6 |
SKB_GSO_GRE |
SKB_GSO_MPLS |
SKB_GSO_UDP_TUNNEL |
0) ||
!(type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))))
goto out;
skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(skb->len, mss);
segs = NULL;
goto out;
}
copy_destructor = gso_skb->destructor == tcp_wfree;
ooo_okay = gso_skb->ooo_okay;
/* All segments but the first should have ooo_okay cleared */
skb->ooo_okay = 0;
segs = skb_segment(skb, features);
if (IS_ERR(segs))
goto out;
/* Only first segment might have ooo_okay set */
segs->ooo_okay = ooo_okay;
delta = htonl(oldlen + (thlen + mss));
skb = segs;
th = tcp_hdr(skb);
seq = ntohl(th->seq);
newcheck = ~csum_fold((__force __wsum)((__force u32)th->check +
(__force u32)delta));
do {
th->fin = th->psh = 0;
th->check = newcheck;
if (skb->ip_summed != CHECKSUM_PARTIAL)
th->check =
csum_fold(csum_partial(skb_transport_header(skb),
thlen, skb->csum));
seq += mss;
if (copy_destructor) {
skb->destructor = gso_skb->destructor;
skb->sk = gso_skb->sk;
/* {tcp|sock}_wfree() use exact truesize accounting :
* sum(skb->truesize) MUST be exactly be gso_skb->truesize
* So we account mss bytes of 'true size' for each segment.
* The last segment will contain the remaining.
*/
skb->truesize = mss;
gso_skb->truesize -= mss;
}
skb = skb->next;
th = tcp_hdr(skb);
th->seq = htonl(seq);
th->cwr = 0;
} while (skb->next);
/* Following permits TCP Small Queues to work well with GSO :
* The callback to TCP stack will be called at the time last frag
* is freed at TX completion, and not right now when gso_skb
* is freed by GSO engine
*/
if (copy_destructor) {
swap(gso_skb->sk, skb->sk);
swap(gso_skb->destructor, skb->destructor);
swap(gso_skb->truesize, skb->truesize);
}
delta = htonl(oldlen + (skb_tail_pointer(skb) -
skb_transport_header(skb)) +
skb->data_len);
th->check = ~csum_fold((__force __wsum)((__force u32)th->check +
(__force u32)delta));
if (skb->ip_summed != CHECKSUM_PARTIAL)
th->check = csum_fold(csum_partial(skb_transport_header(skb),
thlen, skb->csum));
out:
return segs;
}
EXPORT_SYMBOL(tcp_tso_segment);
struct sk_buff **tcp_gro_receive(struct sk_buff **head, struct sk_buff *skb)
{
struct sk_buff **pp = NULL;
struct sk_buff *p;
struct tcphdr *th;
struct tcphdr *th2;
unsigned int len;
unsigned int thlen;
__be32 flags;
unsigned int mss = 1;
unsigned int hlen;
unsigned int off;
int flush = 1;
int i;
off = skb_gro_offset(skb);
hlen = off + sizeof(*th);
th = skb_gro_header_fast(skb, off);
if (skb_gro_header_hard(skb, hlen)) {
th = skb_gro_header_slow(skb, hlen, off);
if (unlikely(!th))
goto out;
}
thlen = th->doff * 4;
if (thlen < sizeof(*th))
goto out;
hlen = off + thlen;
if (skb_gro_header_hard(skb, hlen)) {
th = skb_gro_header_slow(skb, hlen, off);
if (unlikely(!th))
goto out;
}
skb_gro_pull(skb, thlen);
len = skb_gro_len(skb);
flags = tcp_flag_word(th);
for (; (p = *head); head = &p->next) {
if (!NAPI_GRO_CB(p)->same_flow)
continue;
th2 = tcp_hdr(p);
if (*(u32 *)&th->source ^ *(u32 *)&th2->source) {
NAPI_GRO_CB(p)->same_flow = 0;
continue;
}
goto found;
}
goto out_check_final;
found:
flush = NAPI_GRO_CB(p)->flush;
flush |= (__force int)(flags & TCP_FLAG_CWR);
flush |= (__force int)((flags ^ tcp_flag_word(th2)) &
~(TCP_FLAG_CWR | TCP_FLAG_FIN | TCP_FLAG_PSH));
flush |= (__force int)(th->ack_seq ^ th2->ack_seq);
for (i = sizeof(*th); i < thlen; i += 4)
flush |= *(u32 *)((u8 *)th + i) ^
*(u32 *)((u8 *)th2 + i);
mss = tcp_skb_mss(p);
flush |= (len - 1) >= mss;
flush |= (ntohl(th2->seq) + skb_gro_len(p)) ^ ntohl(th->seq);
if (flush || skb_gro_receive(head, skb)) {
mss = 1;
goto out_check_final;
}
p = *head;
th2 = tcp_hdr(p);
tcp_flag_word(th2) |= flags & (TCP_FLAG_FIN | TCP_FLAG_PSH);
out_check_final:
flush = len < mss;
flush |= (__force int)(flags & (TCP_FLAG_URG | TCP_FLAG_PSH |
TCP_FLAG_RST | TCP_FLAG_SYN |
TCP_FLAG_FIN));
if (p && (!NAPI_GRO_CB(skb)->same_flow || flush))
pp = head;
out:
NAPI_GRO_CB(skb)->flush |= flush;
return pp;
}
EXPORT_SYMBOL(tcp_gro_receive);
int tcp_gro_complete(struct sk_buff *skb)
{
struct tcphdr *th = tcp_hdr(skb);
skb->csum_start = skb_transport_header(skb) - skb->head;
skb->csum_offset = offsetof(struct tcphdr, check);
skb->ip_summed = CHECKSUM_PARTIAL;
skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count;
if (th->cwr)
skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_ECN;
return 0;
}
EXPORT_SYMBOL(tcp_gro_complete);
#ifdef CONFIG_TCP_MD5SIG
static struct tcp_md5sig_pool __percpu *tcp_md5sig_pool __read_mostly;
static DEFINE_MUTEX(tcp_md5sig_mutex);

View File

@ -545,8 +545,7 @@ out:
sock_put(sk);
}
static void __tcp_v4_send_check(struct sk_buff *skb,
__be32 saddr, __be32 daddr)
void __tcp_v4_send_check(struct sk_buff *skb, __be32 saddr, __be32 daddr)
{
struct tcphdr *th = tcp_hdr(skb);
@ -571,23 +570,6 @@ void tcp_v4_send_check(struct sock *sk, struct sk_buff *skb)
}
EXPORT_SYMBOL(tcp_v4_send_check);
int tcp_v4_gso_send_check(struct sk_buff *skb)
{
const struct iphdr *iph;
struct tcphdr *th;
if (!pskb_may_pull(skb, sizeof(*th)))
return -EINVAL;
iph = ip_hdr(skb);
th = tcp_hdr(skb);
th->check = 0;
skb->ip_summed = CHECKSUM_PARTIAL;
__tcp_v4_send_check(skb, iph->saddr, iph->daddr);
return 0;
}
/*
* This routine will send an RST to the other tcp.
*
@ -2795,52 +2777,6 @@ void tcp4_proc_exit(void)
}
#endif /* CONFIG_PROC_FS */
struct sk_buff **tcp4_gro_receive(struct sk_buff **head, struct sk_buff *skb)
{
const struct iphdr *iph = skb_gro_network_header(skb);
__wsum wsum;
__sum16 sum;
switch (skb->ip_summed) {
case CHECKSUM_COMPLETE:
if (!tcp_v4_check(skb_gro_len(skb), iph->saddr, iph->daddr,
skb->csum)) {
skb->ip_summed = CHECKSUM_UNNECESSARY;
break;
}
flush:
NAPI_GRO_CB(skb)->flush = 1;
return NULL;
case CHECKSUM_NONE:
wsum = csum_tcpudp_nofold(iph->saddr, iph->daddr,
skb_gro_len(skb), IPPROTO_TCP, 0);
sum = csum_fold(skb_checksum(skb,
skb_gro_offset(skb),
skb_gro_len(skb),
wsum));
if (sum)
goto flush;
skb->ip_summed = CHECKSUM_UNNECESSARY;
break;
}
return tcp_gro_receive(head, skb);
}
int tcp4_gro_complete(struct sk_buff *skb)
{
const struct iphdr *iph = ip_hdr(skb);
struct tcphdr *th = tcp_hdr(skb);
th->check = ~tcp_v4_check(skb->len - skb_transport_offset(skb),
iph->saddr, iph->daddr, 0);
skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4;
return tcp_gro_complete(skb);
}
struct proto tcp_prot = {
.name = "TCP",
.owner = THIS_MODULE,

332
net/ipv4/tcp_offload.c Normal file
View File

@ -0,0 +1,332 @@
/*
* IPV4 GSO/GRO offload support
* Linux INET implementation
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*
* TCPv4 GSO/GRO support
*/
#include <linux/skbuff.h>
#include <net/tcp.h>
#include <net/protocol.h>
struct sk_buff *tcp_tso_segment(struct sk_buff *skb,
netdev_features_t features)
{
struct sk_buff *segs = ERR_PTR(-EINVAL);
struct tcphdr *th;
unsigned int thlen;
unsigned int seq;
__be32 delta;
unsigned int oldlen;
unsigned int mss;
struct sk_buff *gso_skb = skb;
__sum16 newcheck;
bool ooo_okay, copy_destructor;
if (!pskb_may_pull(skb, sizeof(*th)))
goto out;
th = tcp_hdr(skb);
thlen = th->doff * 4;
if (thlen < sizeof(*th))
goto out;
if (!pskb_may_pull(skb, thlen))
goto out;
oldlen = (u16)~skb->len;
__skb_pull(skb, thlen);
mss = tcp_skb_mss(skb);
if (unlikely(skb->len <= mss))
goto out;
if (skb_gso_ok(skb, features | NETIF_F_GSO_ROBUST)) {
/* Packet is from an untrusted source, reset gso_segs. */
int type = skb_shinfo(skb)->gso_type;
if (unlikely(type &
~(SKB_GSO_TCPV4 |
SKB_GSO_DODGY |
SKB_GSO_TCP_ECN |
SKB_GSO_TCPV6 |
SKB_GSO_GRE |
SKB_GSO_MPLS |
SKB_GSO_UDP_TUNNEL |
0) ||
!(type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))))
goto out;
skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(skb->len, mss);
segs = NULL;
goto out;
}
copy_destructor = gso_skb->destructor == tcp_wfree;
ooo_okay = gso_skb->ooo_okay;
/* All segments but the first should have ooo_okay cleared */
skb->ooo_okay = 0;
segs = skb_segment(skb, features);
if (IS_ERR(segs))
goto out;
/* Only first segment might have ooo_okay set */
segs->ooo_okay = ooo_okay;
delta = htonl(oldlen + (thlen + mss));
skb = segs;
th = tcp_hdr(skb);
seq = ntohl(th->seq);
newcheck = ~csum_fold((__force __wsum)((__force u32)th->check +
(__force u32)delta));
do {
th->fin = th->psh = 0;
th->check = newcheck;
if (skb->ip_summed != CHECKSUM_PARTIAL)
th->check =
csum_fold(csum_partial(skb_transport_header(skb),
thlen, skb->csum));
seq += mss;
if (copy_destructor) {
skb->destructor = gso_skb->destructor;
skb->sk = gso_skb->sk;
/* {tcp|sock}_wfree() use exact truesize accounting :
* sum(skb->truesize) MUST be exactly be gso_skb->truesize
* So we account mss bytes of 'true size' for each segment.
* The last segment will contain the remaining.
*/
skb->truesize = mss;
gso_skb->truesize -= mss;
}
skb = skb->next;
th = tcp_hdr(skb);
th->seq = htonl(seq);
th->cwr = 0;
} while (skb->next);
/* Following permits TCP Small Queues to work well with GSO :
* The callback to TCP stack will be called at the time last frag
* is freed at TX completion, and not right now when gso_skb
* is freed by GSO engine
*/
if (copy_destructor) {
swap(gso_skb->sk, skb->sk);
swap(gso_skb->destructor, skb->destructor);
swap(gso_skb->truesize, skb->truesize);
}
delta = htonl(oldlen + (skb_tail_pointer(skb) -
skb_transport_header(skb)) +
skb->data_len);
th->check = ~csum_fold((__force __wsum)((__force u32)th->check +
(__force u32)delta));
if (skb->ip_summed != CHECKSUM_PARTIAL)
th->check = csum_fold(csum_partial(skb_transport_header(skb),
thlen, skb->csum));
out:
return segs;
}
EXPORT_SYMBOL(tcp_tso_segment);
struct sk_buff **tcp_gro_receive(struct sk_buff **head, struct sk_buff *skb)
{
struct sk_buff **pp = NULL;
struct sk_buff *p;
struct tcphdr *th;
struct tcphdr *th2;
unsigned int len;
unsigned int thlen;
__be32 flags;
unsigned int mss = 1;
unsigned int hlen;
unsigned int off;
int flush = 1;
int i;
off = skb_gro_offset(skb);
hlen = off + sizeof(*th);
th = skb_gro_header_fast(skb, off);
if (skb_gro_header_hard(skb, hlen)) {
th = skb_gro_header_slow(skb, hlen, off);
if (unlikely(!th))
goto out;
}
thlen = th->doff * 4;
if (thlen < sizeof(*th))
goto out;
hlen = off + thlen;
if (skb_gro_header_hard(skb, hlen)) {
th = skb_gro_header_slow(skb, hlen, off);
if (unlikely(!th))
goto out;
}
skb_gro_pull(skb, thlen);
len = skb_gro_len(skb);
flags = tcp_flag_word(th);
for (; (p = *head); head = &p->next) {
if (!NAPI_GRO_CB(p)->same_flow)
continue;
th2 = tcp_hdr(p);
if (*(u32 *)&th->source ^ *(u32 *)&th2->source) {
NAPI_GRO_CB(p)->same_flow = 0;
continue;
}
goto found;
}
goto out_check_final;
found:
flush = NAPI_GRO_CB(p)->flush;
flush |= (__force int)(flags & TCP_FLAG_CWR);
flush |= (__force int)((flags ^ tcp_flag_word(th2)) &
~(TCP_FLAG_CWR | TCP_FLAG_FIN | TCP_FLAG_PSH));
flush |= (__force int)(th->ack_seq ^ th2->ack_seq);
for (i = sizeof(*th); i < thlen; i += 4)
flush |= *(u32 *)((u8 *)th + i) ^
*(u32 *)((u8 *)th2 + i);
mss = tcp_skb_mss(p);
flush |= (len - 1) >= mss;
flush |= (ntohl(th2->seq) + skb_gro_len(p)) ^ ntohl(th->seq);
if (flush || skb_gro_receive(head, skb)) {
mss = 1;
goto out_check_final;
}
p = *head;
th2 = tcp_hdr(p);
tcp_flag_word(th2) |= flags & (TCP_FLAG_FIN | TCP_FLAG_PSH);
out_check_final:
flush = len < mss;
flush |= (__force int)(flags & (TCP_FLAG_URG | TCP_FLAG_PSH |
TCP_FLAG_RST | TCP_FLAG_SYN |
TCP_FLAG_FIN));
if (p && (!NAPI_GRO_CB(skb)->same_flow || flush))
pp = head;
out:
NAPI_GRO_CB(skb)->flush |= flush;
return pp;
}
EXPORT_SYMBOL(tcp_gro_receive);
int tcp_gro_complete(struct sk_buff *skb)
{
struct tcphdr *th = tcp_hdr(skb);
skb->csum_start = skb_transport_header(skb) - skb->head;
skb->csum_offset = offsetof(struct tcphdr, check);
skb->ip_summed = CHECKSUM_PARTIAL;
skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count;
if (th->cwr)
skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_ECN;
return 0;
}
EXPORT_SYMBOL(tcp_gro_complete);
static int tcp_v4_gso_send_check(struct sk_buff *skb)
{
const struct iphdr *iph;
struct tcphdr *th;
if (!pskb_may_pull(skb, sizeof(*th)))
return -EINVAL;
iph = ip_hdr(skb);
th = tcp_hdr(skb);
th->check = 0;
skb->ip_summed = CHECKSUM_PARTIAL;
__tcp_v4_send_check(skb, iph->saddr, iph->daddr);
return 0;
}
static struct sk_buff **tcp4_gro_receive(struct sk_buff **head, struct sk_buff *skb)
{
const struct iphdr *iph = skb_gro_network_header(skb);
__wsum wsum;
__sum16 sum;
switch (skb->ip_summed) {
case CHECKSUM_COMPLETE:
if (!tcp_v4_check(skb_gro_len(skb), iph->saddr, iph->daddr,
skb->csum)) {
skb->ip_summed = CHECKSUM_UNNECESSARY;
break;
}
flush:
NAPI_GRO_CB(skb)->flush = 1;
return NULL;
case CHECKSUM_NONE:
wsum = csum_tcpudp_nofold(iph->saddr, iph->daddr,
skb_gro_len(skb), IPPROTO_TCP, 0);
sum = csum_fold(skb_checksum(skb,
skb_gro_offset(skb),
skb_gro_len(skb),
wsum));
if (sum)
goto flush;
skb->ip_summed = CHECKSUM_UNNECESSARY;
break;
}
return tcp_gro_receive(head, skb);
}
static int tcp4_gro_complete(struct sk_buff *skb)
{
const struct iphdr *iph = ip_hdr(skb);
struct tcphdr *th = tcp_hdr(skb);
th->check = ~tcp_v4_check(skb->len - skb_transport_offset(skb),
iph->saddr, iph->daddr, 0);
skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4;
return tcp_gro_complete(skb);
}
static const struct net_offload tcpv4_offload = {
.callbacks = {
.gso_send_check = tcp_v4_gso_send_check,
.gso_segment = tcp_tso_segment,
.gro_receive = tcp4_gro_receive,
.gro_complete = tcp4_gro_complete,
},
};
int __init tcpv4_offload_init(void)
{
return inet_add_offload(&tcpv4_offload, IPPROTO_TCP);
}