diff options
author | Linus Torvalds <torvalds@g5.osdl.org> | 2006-06-23 08:00:01 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@g5.osdl.org> | 2006-06-23 08:00:01 -0700 |
commit | 199f4c9f76fd8b030405abddf294e771f888de03 (patch) | |
tree | ee4f104a7562e1fd76882bc40f2de7d90812e1df /net/ipv4 | |
parent | 37224470c8c6d90a4062e76a08d4dc1fcf91fc89 (diff) | |
parent | ca6bb5d7ab22ac79f608fe6cbc6b12de6a5a19f0 (diff) |
Merge master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6
* master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6:
[NET]: Require CAP_NET_ADMIN to create tuntap devices.
[NET]: fix net-core kernel-doc
[TCP]: Move inclusion of <linux/dmaengine.h> to correct place in <linux/tcp.h>
[IPSEC]: Handle GSO packets
[NET]: Added GSO toggle
[NET]: Add software TSOv4
[NET]: Add generic segmentation offload
[NET]: Merge TSO/UFO fields in sk_buff
[NET]: Prevent transmission after dev_deactivate
[IPV6] ADDRCONF: Fix default source address selection without CONFIG_IPV6_PRIVACY
[IPV6]: Fix source address selection.
[NET]: Avoid allocating skb in skb_pad
Diffstat (limited to 'net/ipv4')
-rw-r--r-- | net/ipv4/af_inet.c | 51 | ||||
-rw-r--r-- | net/ipv4/ip_output.c | 16 | ||||
-rw-r--r-- | net/ipv4/tcp.c | 66 | ||||
-rw-r--r-- | net/ipv4/tcp_input.c | 2 | ||||
-rw-r--r-- | net/ipv4/tcp_output.c | 47 | ||||
-rw-r--r-- | net/ipv4/xfrm4_output.c | 54 |
6 files changed, 199 insertions, 37 deletions
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 0a277453526..461216b4794 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -68,6 +68,7 @@ */ #include <linux/config.h> +#include <linux/err.h> #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> @@ -1096,6 +1097,54 @@ int inet_sk_rebuild_header(struct sock *sk) EXPORT_SYMBOL(inet_sk_rebuild_header); +static struct sk_buff *inet_gso_segment(struct sk_buff *skb, int sg) +{ + struct sk_buff *segs = ERR_PTR(-EINVAL); + struct iphdr *iph; + struct net_protocol *ops; + int proto; + int ihl; + int id; + + if (!pskb_may_pull(skb, sizeof(*iph))) + goto out; + + iph = skb->nh.iph; + ihl = iph->ihl * 4; + if (ihl < sizeof(*iph)) + goto out; + + if (!pskb_may_pull(skb, ihl)) + goto out; + + skb->h.raw = __skb_pull(skb, ihl); + iph = skb->nh.iph; + id = ntohs(iph->id); + proto = iph->protocol & (MAX_INET_PROTOS - 1); + segs = ERR_PTR(-EPROTONOSUPPORT); + + rcu_read_lock(); + ops = rcu_dereference(inet_protos[proto]); + if (ops && ops->gso_segment) + segs = ops->gso_segment(skb, sg); + rcu_read_unlock(); + + if (IS_ERR(segs)) + goto out; + + skb = segs; + do { + iph = skb->nh.iph; + iph->id = htons(id++); + iph->tot_len = htons(skb->len - skb->mac_len); + iph->check = 0; + iph->check = ip_fast_csum(skb->nh.raw, iph->ihl); + } while ((skb = skb->next)); + +out: + return segs; +} + #ifdef CONFIG_IP_MULTICAST static struct net_protocol igmp_protocol = { .handler = igmp_rcv, @@ -1105,6 +1154,7 @@ static struct net_protocol igmp_protocol = { static struct net_protocol tcp_protocol = { .handler = tcp_v4_rcv, .err_handler = tcp_v4_err, + .gso_segment = tcp_tso_segment, .no_policy = 1, }; @@ -1150,6 +1200,7 @@ static int ipv4_proc_init(void); static struct packet_type ip_packet_type = { .type = __constant_htons(ETH_P_IP), .func = ip_rcv, + .gso_segment = inet_gso_segment, }; static int __init inet_init(void) diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 8538aac3d14..7624fd1d8f9 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -210,8 +210,7 @@ static inline int ip_finish_output(struct sk_buff *skb) 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 @@ packet_routed: } 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 @@ static inline int ip_ufo_append_data(struct sock *sk, (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 @@ ssize_t ip_append_page(struct sock *sk, struct page *page, 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 74998f25007..0e029c4e290 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -258,6 +258,7 @@ #include <linux/random.h> #include <linux/bootmem.h> #include <linux/cache.h> +#include <linux/err.h> #include <net/icmp.h> #include <net/tcp.h> @@ -571,7 +572,7 @@ new_segment: 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 +819,7 @@ new_segment: 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; @@ -2144,6 +2145,67 @@ 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, int sg) +{ + struct sk_buff *segs = ERR_PTR(-EINVAL); + struct tcphdr *th; + unsigned thlen; + unsigned int seq; + unsigned int delta; + unsigned int oldlen; + unsigned int len; + + if (!pskb_may_pull(skb, sizeof(*th))) + goto out; + + th = skb->h.th; + thlen = th->doff * 4; + if (thlen < sizeof(*th)) + goto out; + + if (!pskb_may_pull(skb, thlen)) + goto out; + + oldlen = ~htonl(skb->len); + __skb_pull(skb, thlen); + + segs = skb_segment(skb, sg); + if (IS_ERR(segs)) + goto out; + + len = skb_shinfo(skb)->gso_size; + delta = csum_add(oldlen, htonl(thlen + len)); + + skb = segs; + th = skb->h.th; + seq = ntohl(th->seq); + + do { + th->fin = th->psh = 0; + + if (skb->ip_summed == CHECKSUM_NONE) { + th->check = csum_fold(csum_partial( + skb->h.raw, thlen, csum_add(skb->csum, delta))); + } + + seq += len; + skb = skb->next; + th = skb->h.th; + + th->seq = htonl(seq); + th->cwr = 0; + } while (skb->next); + + if (skb->ip_summed == CHECKSUM_NONE) { + delta = csum_add(oldlen, htonl(skb->tail - skb->h.raw)); + th->check = csum_fold(csum_partial( + skb->h.raw, thlen, csum_add(skb->csum, delta))); + } + +out: + return segs; +} + extern void __skb_cb_too_small_for_tcp(int, int); extern struct tcp_congestion_ops tcp_reno; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index e08245bdda3..94fe5b1f9dc 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1073,7 +1073,7 @@ tcp_sacktag_write_queue(struct sock *sk, struct sk_buff *ack_skb, u32 prior_snd_ 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 07bb5a2b375..bdd71db8bf9 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -515,15 +515,17 @@ static void tcp_set_skb_tso_segs(struct sock *sk, struct sk_buff *skb, unsigned /* 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 @@ static int tcp_init_tso_segs(struct sock *sk, struct sk_buff *skb, unsigned int 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 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) 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 @@ void tcp_send_fin(struct sock *sk) 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 @@ void tcp_send_active_reset(struct sock *sk, gfp_t priority) 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 @@ struct sk_buff * tcp_make_synack(struct sock *sk, struct dst_entry *dst, 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 @@ int tcp_connect(struct sock *sk) 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 @@ void tcp_send_ack(struct sock *sk) 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 @@ static int tcp_xmit_probe_skb(struct sock *sk, int urgent) 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/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c index ac9d91d4bb0..193363e2293 100644 --- a/net/ipv4/xfrm4_output.c +++ b/net/ipv4/xfrm4_output.c @@ -9,6 +9,8 @@ */ #include <linux/compiler.h> +#include <linux/if_ether.h> +#include <linux/kernel.h> #include <linux/skbuff.h> #include <linux/spinlock.h> #include <linux/netfilter_ipv4.h> @@ -97,16 +99,10 @@ error_nolock: goto out_exit; } -static int xfrm4_output_finish(struct sk_buff *skb) +static int xfrm4_output_finish2(struct sk_buff *skb) { int err; -#ifdef CONFIG_NETFILTER - if (!skb->dst->xfrm) { - IPCB(skb)->flags |= IPSKB_REROUTED; - return dst_output(skb); - } -#endif while (likely((err = xfrm4_output_one(skb)) == 0)) { nf_reset(skb); @@ -119,7 +115,7 @@ static int xfrm4_output_finish(struct sk_buff *skb) return dst_output(skb); err = nf_hook(PF_INET, NF_IP_POST_ROUTING, &skb, NULL, - skb->dst->dev, xfrm4_output_finish); + skb->dst->dev, xfrm4_output_finish2); if (unlikely(err != 1)) break; } @@ -127,6 +123,48 @@ static int xfrm4_output_finish(struct sk_buff *skb) return err; } +static int xfrm4_output_finish(struct sk_buff *skb) +{ + struct sk_buff *segs; + +#ifdef CONFIG_NETFILTER + if (!skb->dst->xfrm) { + IPCB(skb)->flags |= IPSKB_REROUTED; + return dst_output(skb); + } +#endif + + if (!skb_shinfo(skb)->gso_size) + return xfrm4_output_finish2(skb); + + skb->protocol = htons(ETH_P_IP); + segs = skb_gso_segment(skb, 0); + kfree_skb(skb); + if (unlikely(IS_ERR(segs))) + return PTR_ERR(segs); + + do { + struct sk_buff *nskb = segs->next; + int err; + + segs->next = NULL; + err = xfrm4_output_finish2(segs); + + if (unlikely(err)) { + while ((segs = nskb)) { + nskb = segs->next; + segs->next = NULL; + kfree_skb(segs); + } + return err; + } + + segs = nskb; + } while (segs); + + return 0; +} + int xfrm4_output(struct sk_buff *skb) { return NF_HOOK_COND(PF_INET, NF_IP_POST_ROUTING, skb, NULL, skb->dst->dev, |