mirror of
https://github.com/torvalds/linux.git
synced 2026-05-27 08:33:17 +02:00
Merge branch 'ipv6-misc-changes-in-output-path'
Eric Dumazet says: ==================== ipv6: misc changes in output path Small optimizations mostly in ip6_xmit() path. TX performance increases by about 3 %. Patches 5-7: add dst4_mtu() and dst6_mtu() to save space. Last patch colocates inet6_cork in inet_cork_full. This series reduces kernel size by 494 bytes on x86_64: scripts/bloat-o-meter -t vmlinux.old vmlinux.new add/remove: 4/2 grow/shrink: 9/23 up/down: 665/-1159 (-494) Function old new delta ip6_finish_output_gso_slowpath_drop - 197 +197 ip6_xmit 1452 1595 +143 do_ipv6_getsockopt 2855 2950 +95 kzalloc_noprof - 55 +55 ip4ip6_err 918 955 +37 __icmp_send 1499 1532 +33 do_ip_getsockopt 2573 2605 +32 __ip6_append_data 4109 4137 +28 __pfx_kzalloc_noprof - 16 +16 __pfx_ip6_finish_output_gso_slowpath_drop - 16 +16 ipmr_prepare_xmit 1232 1238 +6 ip6_forward 1905 1909 +4 ip6_cork_release 108 111 +3 ipv6_push_nfrag_opts 489 486 -3 ipv6_push_frag_opts 90 87 -3 ip6_finish_output2 1446 1437 -9 ip6_tnl_xmit 2639 2627 -12 ip6_default_advmss 176 160 -16 __ip6_rt_update_pmtu 1087 1071 -16 tcp_v6_syn_recv_sock 1715 1696 -19 tcp_v4_syn_recv_sock 1107 1088 -19 __ip_make_skb 1339 1320 -19 ip_setup_cork 406 385 -21 ip6_setup_cork 732 710 -22 rawv6_push_pending_frames 581 556 -25 ip6_push_pending_frames 184 157 -27 udpv6_splice_eof 203 170 -33 ip6_flush_pending_frames 220 183 -37 ip6_append_data 349 312 -37 udp_v6_push_pending_frames 155 115 -40 sit_tunnel_xmit 1957 1914 -43 __pfx_dst_mtu 64 - -64 tcp_v4_mtu_reduced 289 220 -69 tcp_v6_mtu_reduced 209 139 -70 ip6_make_skb 574 484 -90 ip6_finish_output 827 697 -130 dst_mtu 160 - -160 fib6_nh_mtu_change 511 336 -175 Total: Before=22584400, After=22583906, chg -0.00% ==================== Link: https://patch.msgid.link/20260130210303.3888261-1-edumazet@google.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
This commit is contained in:
Jakub Kicinski
commit
8755aae4aa
|
|
@ -205,13 +205,6 @@ struct ipv6_mc_socklist;
|
|||
struct ipv6_ac_socklist;
|
||||
struct ipv6_fl_socklist;
|
||||
|
||||
struct inet6_cork {
|
||||
struct ipv6_txoptions *opt;
|
||||
u8 hop_limit;
|
||||
u8 tclass;
|
||||
u8 dontfrag:1;
|
||||
};
|
||||
|
||||
/* struct ipv6_pinfo - ipv6 private area */
|
||||
struct ipv6_pinfo {
|
||||
/* Used in tx path (inet6_csk_route_socket(), ip6_xmit()) */
|
||||
|
|
@ -267,7 +260,6 @@ struct ipv6_pinfo {
|
|||
|
||||
struct sk_buff *pktoptions;
|
||||
struct sk_buff *rxpmtu;
|
||||
struct inet6_cork cork;
|
||||
|
||||
struct ipv6_mc_socklist __rcu *ipv6_mc_list;
|
||||
struct ipv6_ac_socklist *ipv6_ac_list;
|
||||
|
|
|
|||
|
|
@ -219,6 +219,12 @@ static inline u32 dst_mtu(const struct dst_entry *dst)
|
|||
return INDIRECT_CALL_INET(dst->ops->mtu, ip6_mtu, ipv4_mtu, dst);
|
||||
}
|
||||
|
||||
/* Variant of dst_mtu() for IPv4 users. */
|
||||
static inline u32 dst4_mtu(const struct dst_entry *dst)
|
||||
{
|
||||
return INDIRECT_CALL_1(dst->ops->mtu, ipv4_mtu, dst);
|
||||
}
|
||||
|
||||
/* RTT metrics are stored in milliseconds for user ABI, but used as jiffies */
|
||||
static inline unsigned long dst_metric_rtt(const struct dst_entry *dst, int metric)
|
||||
{
|
||||
|
|
|
|||
|
|
@ -159,6 +159,13 @@ static inline bool inet_sk_bound_dev_eq(const struct net *net,
|
|||
#endif
|
||||
}
|
||||
|
||||
struct inet6_cork {
|
||||
struct ipv6_txoptions *opt;
|
||||
u8 hop_limit;
|
||||
u8 tclass;
|
||||
u8 dontfrag:1;
|
||||
};
|
||||
|
||||
struct inet_cork {
|
||||
unsigned int flags;
|
||||
__be32 addr;
|
||||
|
|
@ -179,6 +186,9 @@ struct inet_cork {
|
|||
struct inet_cork_full {
|
||||
struct inet_cork base;
|
||||
struct flowi fl;
|
||||
#if IS_ENABLED(CONFIG_IPV6)
|
||||
struct inet6_cork base6;
|
||||
#endif
|
||||
};
|
||||
|
||||
struct ip_mc_socklist;
|
||||
|
|
|
|||
|
|
@ -266,6 +266,12 @@ static inline bool ipv6_anycast_destination(const struct dst_entry *dst,
|
|||
int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
|
||||
int (*output)(struct net *, struct sock *, struct sk_buff *));
|
||||
|
||||
/* Variant of dst_mtu() for IPv6 users */
|
||||
static inline u32 dst6_mtu(const struct dst_entry *dst)
|
||||
{
|
||||
return INDIRECT_CALL_1(dst->ops->mtu, ip6_mtu, dst);
|
||||
}
|
||||
|
||||
static inline unsigned int ip6_skb_dst_mtu(const struct sk_buff *skb)
|
||||
{
|
||||
const struct ipv6_pinfo *np = skb->sk && !dev_recursion_level() ?
|
||||
|
|
|
|||
|
|
@ -1107,8 +1107,7 @@ void ip6_flush_pending_frames(struct sock *sk);
|
|||
int ip6_send_skb(struct sk_buff *skb);
|
||||
|
||||
struct sk_buff *__ip6_make_skb(struct sock *sk, struct sk_buff_head *queue,
|
||||
struct inet_cork_full *cork,
|
||||
struct inet6_cork *v6_cork);
|
||||
struct inet_cork_full *cork);
|
||||
struct sk_buff *ip6_make_skb(struct sock *sk,
|
||||
int getfrag(void *from, char *to, int offset,
|
||||
int len, int odd, struct sk_buff *skb),
|
||||
|
|
@ -1119,8 +1118,7 @@ struct sk_buff *ip6_make_skb(struct sock *sk,
|
|||
|
||||
static inline struct sk_buff *ip6_finish_skb(struct sock *sk)
|
||||
{
|
||||
return __ip6_make_skb(sk, &sk->sk_write_queue, &inet_sk(sk)->cork,
|
||||
&inet6_sk(sk)->cork);
|
||||
return __ip6_make_skb(sk, &sk->sk_write_queue, &inet_sk(sk)->cork);
|
||||
}
|
||||
|
||||
int ip6_dst_lookup(struct net *net, struct sock *sk, struct dst_entry **dst,
|
||||
|
|
@ -1151,11 +1149,11 @@ int ip6_local_out(struct net *net, struct sock *sk, struct sk_buff *skb);
|
|||
* Extension header (options) processing
|
||||
*/
|
||||
|
||||
void ipv6_push_nfrag_opts(struct sk_buff *skb, struct ipv6_txoptions *opt,
|
||||
u8 *proto, struct in6_addr **daddr_p,
|
||||
struct in6_addr *saddr);
|
||||
void ipv6_push_frag_opts(struct sk_buff *skb, struct ipv6_txoptions *opt,
|
||||
u8 *proto);
|
||||
u8 ipv6_push_nfrag_opts(struct sk_buff *skb, struct ipv6_txoptions *opt,
|
||||
u8 proto, struct in6_addr **daddr_p,
|
||||
struct in6_addr *saddr);
|
||||
u8 ipv6_push_frag_opts(struct sk_buff *skb, struct ipv6_txoptions *opt,
|
||||
u8 proto);
|
||||
|
||||
int ipv6_skip_exthdr(const struct sk_buff *, int start, u8 *nexthdrp,
|
||||
__be16 *frag_offp);
|
||||
|
|
|
|||
|
|
@ -945,7 +945,7 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info,
|
|||
|
||||
/* RFC says return as much as we can without exceeding 576 bytes. */
|
||||
|
||||
room = dst_mtu(&rt->dst);
|
||||
room = dst4_mtu(&rt->dst);
|
||||
if (room > 576)
|
||||
room = 576;
|
||||
room -= sizeof(struct iphdr) + icmp_param->replyopts.opt.optlen;
|
||||
|
|
|
|||
|
|
@ -1300,7 +1300,7 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork,
|
|||
return -EFAULT;
|
||||
|
||||
cork->fragsize = ip_sk_use_pmtu(sk) ?
|
||||
dst_mtu(&rt->dst) : READ_ONCE(rt->dst.dev->mtu);
|
||||
dst4_mtu(&rt->dst) : READ_ONCE(rt->dst.dev->mtu);
|
||||
|
||||
if (!inetdev_valid_mtu(cork->fragsize))
|
||||
return -ENETUNREACH;
|
||||
|
|
@ -1439,7 +1439,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk,
|
|||
pmtudisc = READ_ONCE(inet->pmtudisc);
|
||||
if (pmtudisc == IP_PMTUDISC_DO ||
|
||||
pmtudisc == IP_PMTUDISC_PROBE ||
|
||||
(skb->len <= dst_mtu(&rt->dst) &&
|
||||
(skb->len <= dst4_mtu(&rt->dst) &&
|
||||
ip_dont_fragment(sk, &rt->dst)))
|
||||
df = htons(IP_DF);
|
||||
|
||||
|
|
|
|||
|
|
@ -1634,7 +1634,7 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname,
|
|||
val = 0;
|
||||
dst = sk_dst_get(sk);
|
||||
if (dst) {
|
||||
val = dst_mtu(dst);
|
||||
val = dst4_mtu(dst);
|
||||
dst_release(dst);
|
||||
}
|
||||
if (!val)
|
||||
|
|
|
|||
|
|
@ -1895,7 +1895,7 @@ static int ipmr_prepare_xmit(struct net *net, struct mr_table *mrt,
|
|||
return -1;
|
||||
}
|
||||
|
||||
if (skb->len+encap > dst_mtu(&rt->dst) && (ntohs(iph->frag_off) & IP_DF)) {
|
||||
if (skb->len+encap > dst4_mtu(&rt->dst) && (ntohs(iph->frag_off) & IP_DF)) {
|
||||
/* Do not fragment multicasts. Alas, IPv4 does not
|
||||
* allow to send ICMP, so that packets will disappear
|
||||
* to blackhole.
|
||||
|
|
|
|||
|
|
@ -303,7 +303,7 @@ void nf_send_reset(struct net *net, struct sock *sk, struct sk_buff *oldskb,
|
|||
goto free_nskb;
|
||||
|
||||
/* "Never happens" */
|
||||
if (nskb->len > dst_mtu(skb_dst(nskb)))
|
||||
if (nskb->len > dst4_mtu(skb_dst(nskb)))
|
||||
goto free_nskb;
|
||||
|
||||
nf_ct_attach(nskb, oldskb);
|
||||
|
|
|
|||
|
|
@ -374,7 +374,7 @@ void tcp_v4_mtu_reduced(struct sock *sk)
|
|||
{
|
||||
struct inet_sock *inet = inet_sk(sk);
|
||||
struct dst_entry *dst;
|
||||
u32 mtu;
|
||||
u32 mtu, dmtu;
|
||||
|
||||
if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE))
|
||||
return;
|
||||
|
|
@ -386,15 +386,14 @@ void tcp_v4_mtu_reduced(struct sock *sk)
|
|||
/* Something is about to be wrong... Remember soft error
|
||||
* for the case, if this connection will not able to recover.
|
||||
*/
|
||||
if (mtu < dst_mtu(dst) && ip_dont_fragment(sk, dst))
|
||||
dmtu = dst4_mtu(dst);
|
||||
if (mtu < dmtu && ip_dont_fragment(sk, dst))
|
||||
WRITE_ONCE(sk->sk_err_soft, EMSGSIZE);
|
||||
|
||||
mtu = dst_mtu(dst);
|
||||
|
||||
if (inet->pmtudisc != IP_PMTUDISC_DONT &&
|
||||
ip_sk_accept_pmtu(sk) &&
|
||||
inet_csk(sk)->icsk_pmtu_cookie > mtu) {
|
||||
tcp_sync_mss(sk, mtu);
|
||||
inet_csk(sk)->icsk_pmtu_cookie > dmtu) {
|
||||
tcp_sync_mss(sk, dmtu);
|
||||
|
||||
/* Resend the TCP packet because it's
|
||||
* clear that the old packet has been
|
||||
|
|
@ -1760,7 +1759,7 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
|
|||
|
||||
tcp_ca_openreq_child(newsk, dst);
|
||||
|
||||
tcp_sync_mss(newsk, dst_mtu(dst));
|
||||
tcp_sync_mss(newsk, dst4_mtu(dst));
|
||||
newtp->advmss = tcp_mss_clamp(tcp_sk(sk), dst_metric_advmss(dst));
|
||||
|
||||
tcp_initialize_rcv_mss(newsk);
|
||||
|
|
|
|||
|
|
@ -1074,9 +1074,9 @@ int ipv6_parse_hopopts(struct sk_buff *skb)
|
|||
* for headers.
|
||||
*/
|
||||
|
||||
static void ipv6_push_rthdr0(struct sk_buff *skb, u8 *proto,
|
||||
struct ipv6_rt_hdr *opt,
|
||||
struct in6_addr **addr_p, struct in6_addr *saddr)
|
||||
static u8 ipv6_push_rthdr0(struct sk_buff *skb, u8 proto,
|
||||
struct ipv6_rt_hdr *opt,
|
||||
struct in6_addr **addr_p, struct in6_addr *saddr)
|
||||
{
|
||||
struct rt0_hdr *phdr, *ihdr;
|
||||
int hops;
|
||||
|
|
@ -1095,13 +1095,13 @@ static void ipv6_push_rthdr0(struct sk_buff *skb, u8 *proto,
|
|||
phdr->addr[hops - 1] = **addr_p;
|
||||
*addr_p = ihdr->addr;
|
||||
|
||||
phdr->rt_hdr.nexthdr = *proto;
|
||||
*proto = NEXTHDR_ROUTING;
|
||||
phdr->rt_hdr.nexthdr = proto;
|
||||
return NEXTHDR_ROUTING;
|
||||
}
|
||||
|
||||
static void ipv6_push_rthdr4(struct sk_buff *skb, u8 *proto,
|
||||
struct ipv6_rt_hdr *opt,
|
||||
struct in6_addr **addr_p, struct in6_addr *saddr)
|
||||
static u8 ipv6_push_rthdr4(struct sk_buff *skb, u8 proto,
|
||||
struct ipv6_rt_hdr *opt,
|
||||
struct in6_addr **addr_p, struct in6_addr *saddr)
|
||||
{
|
||||
struct ipv6_sr_hdr *sr_phdr, *sr_ihdr;
|
||||
int plen, hops;
|
||||
|
|
@ -1144,58 +1144,61 @@ static void ipv6_push_rthdr4(struct sk_buff *skb, u8 *proto,
|
|||
}
|
||||
#endif
|
||||
|
||||
sr_phdr->nexthdr = *proto;
|
||||
*proto = NEXTHDR_ROUTING;
|
||||
sr_phdr->nexthdr = proto;
|
||||
return NEXTHDR_ROUTING;
|
||||
}
|
||||
|
||||
static void ipv6_push_rthdr(struct sk_buff *skb, u8 *proto,
|
||||
struct ipv6_rt_hdr *opt,
|
||||
struct in6_addr **addr_p, struct in6_addr *saddr)
|
||||
static u8 ipv6_push_rthdr(struct sk_buff *skb, u8 proto,
|
||||
struct ipv6_rt_hdr *opt,
|
||||
struct in6_addr **addr_p, struct in6_addr *saddr)
|
||||
{
|
||||
switch (opt->type) {
|
||||
case IPV6_SRCRT_TYPE_0:
|
||||
case IPV6_SRCRT_STRICT:
|
||||
case IPV6_SRCRT_TYPE_2:
|
||||
ipv6_push_rthdr0(skb, proto, opt, addr_p, saddr);
|
||||
proto = ipv6_push_rthdr0(skb, proto, opt, addr_p, saddr);
|
||||
break;
|
||||
case IPV6_SRCRT_TYPE_4:
|
||||
ipv6_push_rthdr4(skb, proto, opt, addr_p, saddr);
|
||||
proto = ipv6_push_rthdr4(skb, proto, opt, addr_p, saddr);
|
||||
break;
|
||||
default:
|
||||
break;
|
||||
}
|
||||
return proto;
|
||||
}
|
||||
|
||||
static void ipv6_push_exthdr(struct sk_buff *skb, u8 *proto, u8 type, struct ipv6_opt_hdr *opt)
|
||||
static u8 ipv6_push_exthdr(struct sk_buff *skb, u8 proto, u8 type, struct ipv6_opt_hdr *opt)
|
||||
{
|
||||
struct ipv6_opt_hdr *h = skb_push(skb, ipv6_optlen(opt));
|
||||
|
||||
memcpy(h, opt, ipv6_optlen(opt));
|
||||
h->nexthdr = *proto;
|
||||
*proto = type;
|
||||
h->nexthdr = proto;
|
||||
return type;
|
||||
}
|
||||
|
||||
void ipv6_push_nfrag_opts(struct sk_buff *skb, struct ipv6_txoptions *opt,
|
||||
u8 *proto,
|
||||
struct in6_addr **daddr, struct in6_addr *saddr)
|
||||
u8 ipv6_push_nfrag_opts(struct sk_buff *skb, struct ipv6_txoptions *opt,
|
||||
u8 proto,
|
||||
struct in6_addr **daddr, struct in6_addr *saddr)
|
||||
{
|
||||
if (opt->srcrt) {
|
||||
ipv6_push_rthdr(skb, proto, opt->srcrt, daddr, saddr);
|
||||
proto = ipv6_push_rthdr(skb, proto, opt->srcrt, daddr, saddr);
|
||||
/*
|
||||
* IPV6_RTHDRDSTOPTS is ignored
|
||||
* unless IPV6_RTHDR is set (RFC3542).
|
||||
*/
|
||||
if (opt->dst0opt)
|
||||
ipv6_push_exthdr(skb, proto, NEXTHDR_DEST, opt->dst0opt);
|
||||
proto = ipv6_push_exthdr(skb, proto, NEXTHDR_DEST, opt->dst0opt);
|
||||
}
|
||||
if (opt->hopopt)
|
||||
ipv6_push_exthdr(skb, proto, NEXTHDR_HOP, opt->hopopt);
|
||||
proto = ipv6_push_exthdr(skb, proto, NEXTHDR_HOP, opt->hopopt);
|
||||
return proto;
|
||||
}
|
||||
|
||||
void ipv6_push_frag_opts(struct sk_buff *skb, struct ipv6_txoptions *opt, u8 *proto)
|
||||
u8 ipv6_push_frag_opts(struct sk_buff *skb, struct ipv6_txoptions *opt, u8 proto)
|
||||
{
|
||||
if (opt->dst1opt)
|
||||
ipv6_push_exthdr(skb, proto, NEXTHDR_DEST, opt->dst1opt);
|
||||
proto = ipv6_push_exthdr(skb, proto, NEXTHDR_DEST, opt->dst1opt);
|
||||
return proto;
|
||||
}
|
||||
EXPORT_SYMBOL(ipv6_push_frag_opts);
|
||||
|
||||
|
|
|
|||
|
|
@ -1057,7 +1057,7 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb,
|
|||
/* TooBig packet may have updated dst->dev's mtu */
|
||||
if (!t->parms.collect_md && dst) {
|
||||
mtu = READ_ONCE(dst_dev(dst)->mtu);
|
||||
if (dst_mtu(dst) > mtu)
|
||||
if (dst6_mtu(dst) > mtu)
|
||||
dst->ops->update_pmtu(dst, NULL, skb, mtu, false);
|
||||
}
|
||||
err = ip6_tnl_xmit(skb, dev, dsfield, &fl6, encap_limit, &mtu,
|
||||
|
|
|
|||
|
|
@ -80,7 +80,7 @@ static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff *
|
|||
|
||||
hdr = ipv6_hdr(skb);
|
||||
daddr = &hdr->daddr;
|
||||
if (ipv6_addr_is_multicast(daddr)) {
|
||||
if (unlikely(ipv6_addr_is_multicast(daddr))) {
|
||||
if (!(dev->flags & IFF_LOOPBACK) && sk_mc_loop(sk) &&
|
||||
((mroute6_is_socket(net, skb) &&
|
||||
!(IP6CB(skb)->flags & IP6SKB_FORWARDED)) ||
|
||||
|
|
@ -179,8 +179,8 @@ ip6_finish_output_gso_slowpath_drop(struct net *net, struct sock *sk,
|
|||
static int ip6_finish_output_gso(struct net *net, struct sock *sk,
|
||||
struct sk_buff *skb, unsigned int mtu)
|
||||
{
|
||||
if (!(IP6CB(skb)->flags & IP6SKB_FAKEJUMBO) &&
|
||||
!skb_gso_validate_network_len(skb, mtu))
|
||||
if (unlikely(!(IP6CB(skb)->flags & IP6SKB_FAKEJUMBO) &&
|
||||
!skb_gso_validate_network_len(skb, mtu)))
|
||||
return ip6_finish_output_gso_slowpath_drop(net, sk, skb, mtu);
|
||||
|
||||
return ip6_finish_output2(net, sk, skb);
|
||||
|
|
@ -202,8 +202,8 @@ static int __ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff
|
|||
if (skb_is_gso(skb))
|
||||
return ip6_finish_output_gso(net, sk, skb, mtu);
|
||||
|
||||
if (skb->len > mtu ||
|
||||
(IP6CB(skb)->frag_max_size && skb->len > IP6CB(skb)->frag_max_size))
|
||||
if (unlikely(skb->len > mtu ||
|
||||
(IP6CB(skb)->frag_max_size && skb->len > IP6CB(skb)->frag_max_size)))
|
||||
return ip6_fragment(net, sk, skb, ip6_finish_output2);
|
||||
|
||||
return ip6_finish_output2(net, sk, skb);
|
||||
|
|
@ -301,19 +301,20 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
|
|||
}
|
||||
}
|
||||
|
||||
if (opt) {
|
||||
if (unlikely(opt)) {
|
||||
seg_len += opt->opt_nflen + opt->opt_flen;
|
||||
|
||||
if (opt->opt_flen)
|
||||
ipv6_push_frag_opts(skb, opt, &proto);
|
||||
proto = ipv6_push_frag_opts(skb, opt, proto);
|
||||
|
||||
if (opt->opt_nflen)
|
||||
ipv6_push_nfrag_opts(skb, opt, &proto, &first_hop,
|
||||
&fl6->saddr);
|
||||
proto = ipv6_push_nfrag_opts(skb, opt, proto,
|
||||
&first_hop,
|
||||
&fl6->saddr);
|
||||
}
|
||||
|
||||
if (unlikely(seg_len > IPV6_MAXPLEN)) {
|
||||
hop_jumbo = skb_push(skb, hoplen);
|
||||
hop_jumbo = __skb_push(skb, hoplen);
|
||||
|
||||
hop_jumbo->nexthdr = proto;
|
||||
hop_jumbo->hdrlen = 0;
|
||||
|
|
@ -326,7 +327,7 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
|
|||
IP6CB(skb)->flags |= IP6SKB_FAKEJUMBO;
|
||||
}
|
||||
|
||||
skb_push(skb, sizeof(struct ipv6hdr));
|
||||
__skb_push(skb, sizeof(struct ipv6hdr));
|
||||
skb_reset_network_header(skb);
|
||||
hdr = ipv6_hdr(skb);
|
||||
|
||||
|
|
@ -352,8 +353,8 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
|
|||
skb->priority = priority;
|
||||
skb->mark = mark;
|
||||
|
||||
mtu = dst_mtu(dst);
|
||||
if ((skb->len <= mtu) || skb->ignore_df || skb_is_gso(skb)) {
|
||||
mtu = dst6_mtu(dst);
|
||||
if (likely((skb->len <= mtu) || skb->ignore_df || skb_is_gso(skb))) {
|
||||
IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTREQUESTS);
|
||||
|
||||
/* if egress device is enslaved to an L3 master device pass the
|
||||
|
|
@ -382,7 +383,7 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
|
|||
ipv6_local_error((struct sock *)sk, EMSGSIZE, fl6, mtu);
|
||||
|
||||
IP6_INC_STATS(net, idev, IPSTATS_MIB_FRAGFAILS);
|
||||
kfree_skb(skb);
|
||||
kfree_skb_reason(skb, SKB_DROP_REASON_PKT_TOO_BIG);
|
||||
unlock:
|
||||
rcu_read_unlock();
|
||||
return ret;
|
||||
|
|
@ -653,7 +654,7 @@ int ip6_forward(struct sk_buff *skb)
|
|||
if (mtu < IPV6_MIN_MTU)
|
||||
mtu = IPV6_MIN_MTU;
|
||||
|
||||
if (ip6_pkt_too_big(skb, mtu)) {
|
||||
if (unlikely(ip6_pkt_too_big(skb, mtu))) {
|
||||
/* Again, force OUTPUT device used as source address */
|
||||
skb->dev = dev;
|
||||
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
|
||||
|
|
@ -1352,12 +1353,13 @@ static void ip6_append_data_mtu(unsigned int *mtu,
|
|||
}
|
||||
|
||||
static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork,
|
||||
struct inet6_cork *v6_cork, struct ipcm6_cookie *ipc6,
|
||||
struct ipcm6_cookie *ipc6,
|
||||
struct rt6_info *rt)
|
||||
{
|
||||
struct ipv6_txoptions *nopt, *opt = ipc6->opt;
|
||||
struct inet6_cork *v6_cork = &cork->base6;
|
||||
struct ipv6_pinfo *np = inet6_sk(sk);
|
||||
unsigned int mtu, frag_size;
|
||||
struct ipv6_txoptions *nopt, *opt = ipc6->opt;
|
||||
|
||||
/* callers pass dst together with a reference, set it first so
|
||||
* ip6_cork_release() can put it down even in case of an error.
|
||||
|
|
@ -1367,7 +1369,7 @@ static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork,
|
|||
/*
|
||||
* setup for corking
|
||||
*/
|
||||
if (opt) {
|
||||
if (unlikely(opt)) {
|
||||
if (WARN_ON(v6_cork->opt))
|
||||
return -EINVAL;
|
||||
|
||||
|
|
@ -1402,10 +1404,10 @@ static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork,
|
|||
v6_cork->dontfrag = ipc6->dontfrag;
|
||||
if (rt->dst.flags & DST_XFRM_TUNNEL)
|
||||
mtu = READ_ONCE(np->pmtudisc) >= IPV6_PMTUDISC_PROBE ?
|
||||
READ_ONCE(rt->dst.dev->mtu) : dst_mtu(&rt->dst);
|
||||
READ_ONCE(rt->dst.dev->mtu) : dst6_mtu(&rt->dst);
|
||||
else
|
||||
mtu = READ_ONCE(np->pmtudisc) >= IPV6_PMTUDISC_PROBE ?
|
||||
READ_ONCE(rt->dst.dev->mtu) : dst_mtu(xfrm_dst_path(&rt->dst));
|
||||
READ_ONCE(rt->dst.dev->mtu) : dst6_mtu(xfrm_dst_path(&rt->dst));
|
||||
|
||||
frag_size = READ_ONCE(np->frag_size);
|
||||
if (frag_size && frag_size < mtu)
|
||||
|
|
@ -1430,17 +1432,17 @@ static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork,
|
|||
static int __ip6_append_data(struct sock *sk,
|
||||
struct sk_buff_head *queue,
|
||||
struct inet_cork_full *cork_full,
|
||||
struct inet6_cork *v6_cork,
|
||||
struct page_frag *pfrag,
|
||||
int getfrag(void *from, char *to, int offset,
|
||||
int len, int odd, struct sk_buff *skb),
|
||||
void *from, size_t length, int transhdrlen,
|
||||
unsigned int flags)
|
||||
{
|
||||
struct sk_buff *skb, *skb_prev = NULL;
|
||||
unsigned int maxfraglen, fragheaderlen, mtu, orig_mtu, pmtu;
|
||||
struct inet6_cork *v6_cork = &cork_full->base6;
|
||||
struct inet_cork *cork = &cork_full->base;
|
||||
struct flowi6 *fl6 = &cork_full->fl.u.ip6;
|
||||
unsigned int maxfraglen, fragheaderlen, mtu, orig_mtu, pmtu;
|
||||
struct sk_buff *skb, *skb_prev = NULL;
|
||||
struct ubuf_info *uarg = NULL;
|
||||
int exthdrlen = 0;
|
||||
int dst_exthdrlen = 0;
|
||||
|
|
@ -1843,7 +1845,6 @@ int ip6_append_data(struct sock *sk,
|
|||
struct rt6_info *rt, unsigned int flags)
|
||||
{
|
||||
struct inet_sock *inet = inet_sk(sk);
|
||||
struct ipv6_pinfo *np = inet6_sk(sk);
|
||||
int exthdrlen;
|
||||
int err;
|
||||
|
||||
|
|
@ -1854,7 +1855,7 @@ int ip6_append_data(struct sock *sk,
|
|||
* setup for corking
|
||||
*/
|
||||
dst_hold(&rt->dst);
|
||||
err = ip6_setup_cork(sk, &inet->cork, &np->cork,
|
||||
err = ip6_setup_cork(sk, &inet->cork,
|
||||
ipc6, rt);
|
||||
if (err)
|
||||
return err;
|
||||
|
|
@ -1868,7 +1869,7 @@ int ip6_append_data(struct sock *sk,
|
|||
}
|
||||
|
||||
return __ip6_append_data(sk, &sk->sk_write_queue, &inet->cork,
|
||||
&np->cork, sk_page_frag(sk), getfrag,
|
||||
sk_page_frag(sk), getfrag,
|
||||
from, length, transhdrlen, flags);
|
||||
}
|
||||
EXPORT_SYMBOL_GPL(ip6_append_data);
|
||||
|
|
@ -1881,10 +1882,11 @@ static void ip6_cork_steal_dst(struct sk_buff *skb, struct inet_cork_full *cork)
|
|||
skb_dst_set(skb, dst);
|
||||
}
|
||||
|
||||
static void ip6_cork_release(struct inet_cork_full *cork,
|
||||
struct inet6_cork *v6_cork)
|
||||
static void ip6_cork_release(struct inet_cork_full *cork)
|
||||
{
|
||||
if (v6_cork->opt) {
|
||||
struct inet6_cork *v6_cork = &cork->base6;
|
||||
|
||||
if (unlikely(v6_cork->opt)) {
|
||||
struct ipv6_txoptions *opt = v6_cork->opt;
|
||||
|
||||
kfree(opt->dst0opt);
|
||||
|
|
@ -1903,15 +1905,14 @@ static void ip6_cork_release(struct inet_cork_full *cork,
|
|||
|
||||
struct sk_buff *__ip6_make_skb(struct sock *sk,
|
||||
struct sk_buff_head *queue,
|
||||
struct inet_cork_full *cork,
|
||||
struct inet6_cork *v6_cork)
|
||||
struct inet_cork_full *cork)
|
||||
{
|
||||
struct sk_buff *skb, *tmp_skb;
|
||||
struct sk_buff **tail_skb;
|
||||
struct in6_addr *final_dst;
|
||||
struct net *net = sock_net(sk);
|
||||
struct ipv6hdr *hdr;
|
||||
struct ipv6_txoptions *opt = v6_cork->opt;
|
||||
struct ipv6_txoptions *opt;
|
||||
struct rt6_info *rt = dst_rt6_info(cork->base.dst);
|
||||
struct flowi6 *fl6 = &cork->fl.u.ip6;
|
||||
unsigned char proto = fl6->flowi6_proto;
|
||||
|
|
@ -1940,19 +1941,22 @@ struct sk_buff *__ip6_make_skb(struct sock *sk,
|
|||
__skb_pull(skb, skb_network_header_len(skb));
|
||||
|
||||
final_dst = &fl6->daddr;
|
||||
if (opt && opt->opt_flen)
|
||||
ipv6_push_frag_opts(skb, opt, &proto);
|
||||
if (opt && opt->opt_nflen)
|
||||
ipv6_push_nfrag_opts(skb, opt, &proto, &final_dst, &fl6->saddr);
|
||||
|
||||
opt = cork->base6.opt;
|
||||
if (unlikely(opt)) {
|
||||
if (opt->opt_flen)
|
||||
proto = ipv6_push_frag_opts(skb, opt, proto);
|
||||
if (opt->opt_nflen)
|
||||
proto = ipv6_push_nfrag_opts(skb, opt, proto,
|
||||
&final_dst, &fl6->saddr);
|
||||
}
|
||||
skb_push(skb, sizeof(struct ipv6hdr));
|
||||
skb_reset_network_header(skb);
|
||||
hdr = ipv6_hdr(skb);
|
||||
|
||||
ip6_flow_hdr(hdr, v6_cork->tclass,
|
||||
ip6_flow_hdr(hdr, cork->base6.tclass,
|
||||
ip6_make_flowlabel(net, skb, fl6->flowlabel,
|
||||
ip6_autoflowlabel(net, sk), fl6));
|
||||
hdr->hop_limit = v6_cork->hop_limit;
|
||||
hdr->hop_limit = cork->base6.hop_limit;
|
||||
hdr->nexthdr = proto;
|
||||
hdr->saddr = fl6->saddr;
|
||||
hdr->daddr = *final_dst;
|
||||
|
|
@ -1966,7 +1970,7 @@ struct sk_buff *__ip6_make_skb(struct sock *sk,
|
|||
|
||||
ip6_cork_steal_dst(skb, cork);
|
||||
IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTREQUESTS);
|
||||
if (proto == IPPROTO_ICMPV6) {
|
||||
if (unlikely(proto == IPPROTO_ICMPV6)) {
|
||||
struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb));
|
||||
u8 icmp6_type;
|
||||
|
||||
|
|
@ -1979,7 +1983,7 @@ struct sk_buff *__ip6_make_skb(struct sock *sk,
|
|||
ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS);
|
||||
}
|
||||
|
||||
ip6_cork_release(cork, v6_cork);
|
||||
ip6_cork_release(cork);
|
||||
out:
|
||||
return skb;
|
||||
}
|
||||
|
|
@ -2018,8 +2022,7 @@ EXPORT_SYMBOL_GPL(ip6_push_pending_frames);
|
|||
|
||||
static void __ip6_flush_pending_frames(struct sock *sk,
|
||||
struct sk_buff_head *queue,
|
||||
struct inet_cork_full *cork,
|
||||
struct inet6_cork *v6_cork)
|
||||
struct inet_cork_full *cork)
|
||||
{
|
||||
struct sk_buff *skb;
|
||||
|
||||
|
|
@ -2030,13 +2033,13 @@ static void __ip6_flush_pending_frames(struct sock *sk,
|
|||
kfree_skb(skb);
|
||||
}
|
||||
|
||||
ip6_cork_release(cork, v6_cork);
|
||||
ip6_cork_release(cork);
|
||||
}
|
||||
|
||||
void ip6_flush_pending_frames(struct sock *sk)
|
||||
{
|
||||
__ip6_flush_pending_frames(sk, &sk->sk_write_queue,
|
||||
&inet_sk(sk)->cork, &inet6_sk(sk)->cork);
|
||||
&inet_sk(sk)->cork);
|
||||
}
|
||||
EXPORT_SYMBOL_GPL(ip6_flush_pending_frames);
|
||||
|
||||
|
|
@ -2047,9 +2050,8 @@ struct sk_buff *ip6_make_skb(struct sock *sk,
|
|||
struct ipcm6_cookie *ipc6, struct rt6_info *rt,
|
||||
unsigned int flags, struct inet_cork_full *cork)
|
||||
{
|
||||
struct inet6_cork v6_cork;
|
||||
struct sk_buff_head queue;
|
||||
int exthdrlen = (ipc6->opt ? ipc6->opt->opt_flen : 0);
|
||||
struct sk_buff_head queue;
|
||||
int err;
|
||||
|
||||
if (flags & MSG_PROBE) {
|
||||
|
|
@ -2062,21 +2064,21 @@ struct sk_buff *ip6_make_skb(struct sock *sk,
|
|||
cork->base.flags = 0;
|
||||
cork->base.addr = 0;
|
||||
cork->base.opt = NULL;
|
||||
v6_cork.opt = NULL;
|
||||
err = ip6_setup_cork(sk, cork, &v6_cork, ipc6, rt);
|
||||
cork->base6.opt = NULL;
|
||||
err = ip6_setup_cork(sk, cork, ipc6, rt);
|
||||
if (err) {
|
||||
ip6_cork_release(cork, &v6_cork);
|
||||
ip6_cork_release(cork);
|
||||
return ERR_PTR(err);
|
||||
}
|
||||
|
||||
err = __ip6_append_data(sk, &queue, cork, &v6_cork,
|
||||
err = __ip6_append_data(sk, &queue, cork,
|
||||
¤t->task_frag, getfrag, from,
|
||||
length + exthdrlen, transhdrlen + exthdrlen,
|
||||
flags);
|
||||
if (err) {
|
||||
__ip6_flush_pending_frames(sk, &queue, cork, &v6_cork);
|
||||
__ip6_flush_pending_frames(sk, &queue, cork);
|
||||
return ERR_PTR(err);
|
||||
}
|
||||
|
||||
return __ip6_make_skb(sk, &queue, cork, &v6_cork);
|
||||
return __ip6_make_skb(sk, &queue, cork);
|
||||
}
|
||||
|
|
|
|||
|
|
@ -638,7 +638,7 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
|
|||
|
||||
/* change mtu on this route */
|
||||
if (rel_type == ICMP_DEST_UNREACH && rel_code == ICMP_FRAG_NEEDED) {
|
||||
if (rel_info > dst_mtu(skb_dst(skb2)))
|
||||
if (rel_info > dst6_mtu(skb_dst(skb2)))
|
||||
goto out;
|
||||
|
||||
skb_dst_update_pmtu_no_confirm(skb2, rel_info);
|
||||
|
|
@ -1187,7 +1187,7 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield,
|
|||
t->parms.name);
|
||||
goto tx_err_dst_release;
|
||||
}
|
||||
mtu = dst_mtu(dst) - eth_hlen - psh_hlen - t->tun_hlen;
|
||||
mtu = dst6_mtu(dst) - eth_hlen - psh_hlen - t->tun_hlen;
|
||||
if (encap_limit >= 0) {
|
||||
max_headroom += 8;
|
||||
mtu -= 8;
|
||||
|
|
@ -1265,7 +1265,7 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield,
|
|||
|
||||
if (encap_limit >= 0) {
|
||||
init_tel_txopt(&opt, encap_limit);
|
||||
ipv6_push_frag_opts(skb, &opt.ops, &proto);
|
||||
proto = ipv6_push_frag_opts(skb, &opt.ops, proto);
|
||||
}
|
||||
|
||||
skb_push(skb, sizeof(struct ipv6hdr));
|
||||
|
|
|
|||
|
|
@ -1184,7 +1184,7 @@ int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
|
|||
rcu_read_lock();
|
||||
dst = __sk_dst_get(sk);
|
||||
if (dst)
|
||||
val = dst_mtu(dst);
|
||||
val = dst6_mtu(dst);
|
||||
rcu_read_unlock();
|
||||
if (!val)
|
||||
return -ENOTCONN;
|
||||
|
|
@ -1283,7 +1283,7 @@ int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
|
|||
rcu_read_lock();
|
||||
dst = __sk_dst_get(sk);
|
||||
if (dst)
|
||||
mtuinfo.ip6m_mtu = dst_mtu(dst);
|
||||
mtuinfo.ip6m_mtu = dst6_mtu(dst);
|
||||
rcu_read_unlock();
|
||||
if (!mtuinfo.ip6m_mtu)
|
||||
return -ENOTCONN;
|
||||
|
|
|
|||
|
|
@ -529,7 +529,7 @@ static int rawv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6,
|
|||
|
||||
offset = rp->offset;
|
||||
total_len = inet_sk(sk)->cork.base.length;
|
||||
opt = inet6_sk(sk)->cork.opt;
|
||||
opt = inet_sk(sk)->cork.base6.opt;
|
||||
total_len -= opt ? opt->opt_flen : 0;
|
||||
|
||||
if (offset >= total_len - 1) {
|
||||
|
|
|
|||
|
|
@ -2049,6 +2049,8 @@ static void rt6_update_exception_stamp_rt(struct rt6_info *rt)
|
|||
static bool rt6_mtu_change_route_allowed(struct inet6_dev *idev,
|
||||
struct rt6_info *rt, int mtu)
|
||||
{
|
||||
u32 dmtu = dst6_mtu(&rt->dst);
|
||||
|
||||
/* If the new MTU is lower than the route PMTU, this new MTU will be the
|
||||
* lowest MTU in the path: always allow updating the route PMTU to
|
||||
* reflect PMTU decreases.
|
||||
|
|
@ -2059,10 +2061,10 @@ static bool rt6_mtu_change_route_allowed(struct inet6_dev *idev,
|
|||
* handle this.
|
||||
*/
|
||||
|
||||
if (dst_mtu(&rt->dst) >= mtu)
|
||||
if (dmtu >= mtu)
|
||||
return true;
|
||||
|
||||
if (dst_mtu(&rt->dst) == idev->cnf.mtu6)
|
||||
if (dmtu == idev->cnf.mtu6)
|
||||
return true;
|
||||
|
||||
return false;
|
||||
|
|
@ -2932,7 +2934,7 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk,
|
|||
|
||||
if (mtu < IPV6_MIN_MTU)
|
||||
return;
|
||||
if (mtu >= dst_mtu(dst))
|
||||
if (mtu >= dst6_mtu(dst))
|
||||
return;
|
||||
|
||||
if (!rt6_cache_allowed_for_pmtu(rt6)) {
|
||||
|
|
@ -3248,7 +3250,7 @@ EXPORT_SYMBOL_GPL(ip6_sk_redirect);
|
|||
|
||||
static unsigned int ip6_default_advmss(const struct dst_entry *dst)
|
||||
{
|
||||
unsigned int mtu = dst_mtu(dst);
|
||||
unsigned int mtu = dst6_mtu(dst);
|
||||
struct net *net;
|
||||
|
||||
mtu -= sizeof(struct ipv6hdr) + sizeof(struct tcphdr);
|
||||
|
|
|
|||
|
|
@ -962,7 +962,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
|
|||
}
|
||||
|
||||
if (df) {
|
||||
mtu = dst_mtu(&rt->dst) - t_hlen;
|
||||
mtu = dst4_mtu(&rt->dst) - t_hlen;
|
||||
|
||||
if (mtu < IPV4_MIN_MTU) {
|
||||
DEV_STATS_INC(dev, collisions);
|
||||
|
|
|
|||
|
|
@ -351,7 +351,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr_unsized *uaddr,
|
|||
static void tcp_v6_mtu_reduced(struct sock *sk)
|
||||
{
|
||||
struct dst_entry *dst;
|
||||
u32 mtu;
|
||||
u32 mtu, dmtu;
|
||||
|
||||
if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE))
|
||||
return;
|
||||
|
|
@ -368,8 +368,9 @@ static void tcp_v6_mtu_reduced(struct sock *sk)
|
|||
if (!dst)
|
||||
return;
|
||||
|
||||
if (inet_csk(sk)->icsk_pmtu_cookie > dst_mtu(dst)) {
|
||||
tcp_sync_mss(sk, dst_mtu(dst));
|
||||
dmtu = dst6_mtu(dst);
|
||||
if (inet_csk(sk)->icsk_pmtu_cookie > dmtu) {
|
||||
tcp_sync_mss(sk, dmtu);
|
||||
tcp_simple_retransmit(sk);
|
||||
}
|
||||
}
|
||||
|
|
@ -1467,7 +1468,7 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
|
|||
|
||||
tcp_ca_openreq_child(newsk, dst);
|
||||
|
||||
tcp_sync_mss(newsk, dst_mtu(dst));
|
||||
tcp_sync_mss(newsk, dst6_mtu(dst));
|
||||
newtp->advmss = tcp_mss_clamp(tcp_sk(sk), dst_metric_advmss(dst));
|
||||
|
||||
tcp_initialize_rcv_mss(newsk);
|
||||
|
|
|
|||
Loading…
Reference in New Issue
Block a user