linux/include/net/inet_ecn.h
Steinar H. Gunderson ca06707022 ipv6: restore correct ECN handling on TCP xmit
Since commit e9df2e8fd8 (Use appropriate sock tclass setting for
routing lookup) we lost ability to properly add ECN codemarks to ipv6
TCP frames.

It seems like TCP_ECN_send() calls INET_ECN_xmit(), which only sets the
ECN bit in the IPv4 ToS field (inet_sk(sk)->tos), but after the patch,
what's checked is inet6_sk(sk)->tclass, which is a completely different
field.

Close bug https://bugzilla.kernel.org/show_bug.cgi?id=34322

[Eric Dumazet] : added the INET_ECN_dontxmit() fix and replace macros
by inline functions for clarity.

Signed-off-by: Steinar H. Gunderson <sgunderson@bigfoot.com>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Cc: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2011-05-12 18:52:14 -04:00

141 lines
3.0 KiB
C

#ifndef _INET_ECN_H_
#define _INET_ECN_H_
#include <linux/ip.h>
#include <linux/skbuff.h>
#include <net/inet_sock.h>
#include <net/dsfield.h>
enum {
INET_ECN_NOT_ECT = 0,
INET_ECN_ECT_1 = 1,
INET_ECN_ECT_0 = 2,
INET_ECN_CE = 3,
INET_ECN_MASK = 3,
};
static inline int INET_ECN_is_ce(__u8 dsfield)
{
return (dsfield & INET_ECN_MASK) == INET_ECN_CE;
}
static inline int INET_ECN_is_not_ect(__u8 dsfield)
{
return (dsfield & INET_ECN_MASK) == INET_ECN_NOT_ECT;
}
static inline int INET_ECN_is_capable(__u8 dsfield)
{
return dsfield & INET_ECN_ECT_0;
}
static inline __u8 INET_ECN_encapsulate(__u8 outer, __u8 inner)
{
outer &= ~INET_ECN_MASK;
outer |= !INET_ECN_is_ce(inner) ? (inner & INET_ECN_MASK) :
INET_ECN_ECT_0;
return outer;
}
static inline void INET_ECN_xmit(struct sock *sk)
{
inet_sk(sk)->tos |= INET_ECN_ECT_0;
if (inet6_sk(sk) != NULL)
inet6_sk(sk)->tclass |= INET_ECN_ECT_0;
}
static inline void INET_ECN_dontxmit(struct sock *sk)
{
inet_sk(sk)->tos &= ~INET_ECN_MASK;
if (inet6_sk(sk) != NULL)
inet6_sk(sk)->tclass &= ~INET_ECN_MASK;
}
#define IP6_ECN_flow_init(label) do { \
(label) &= ~htonl(INET_ECN_MASK << 20); \
} while (0)
#define IP6_ECN_flow_xmit(sk, label) do { \
if (INET_ECN_is_capable(inet6_sk(sk)->tclass)) \
(label) |= htonl(INET_ECN_ECT_0 << 20); \
} while (0)
static inline int IP_ECN_set_ce(struct iphdr *iph)
{
u32 check = (__force u32)iph->check;
u32 ecn = (iph->tos + 1) & INET_ECN_MASK;
/*
* After the last operation we have (in binary):
* INET_ECN_NOT_ECT => 01
* INET_ECN_ECT_1 => 10
* INET_ECN_ECT_0 => 11
* INET_ECN_CE => 00
*/
if (!(ecn & 2))
return !ecn;
/*
* The following gives us:
* INET_ECN_ECT_1 => check += htons(0xFFFD)
* INET_ECN_ECT_0 => check += htons(0xFFFE)
*/
check += (__force u16)htons(0xFFFB) + (__force u16)htons(ecn);
iph->check = (__force __sum16)(check + (check>=0xFFFF));
iph->tos |= INET_ECN_CE;
return 1;
}
static inline void IP_ECN_clear(struct iphdr *iph)
{
iph->tos &= ~INET_ECN_MASK;
}
static inline void ipv4_copy_dscp(unsigned int dscp, struct iphdr *inner)
{
dscp &= ~INET_ECN_MASK;
ipv4_change_dsfield(inner, INET_ECN_MASK, dscp);
}
struct ipv6hdr;
static inline int IP6_ECN_set_ce(struct ipv6hdr *iph)
{
if (INET_ECN_is_not_ect(ipv6_get_dsfield(iph)))
return 0;
*(__be32*)iph |= htonl(INET_ECN_CE << 20);
return 1;
}
static inline void IP6_ECN_clear(struct ipv6hdr *iph)
{
*(__be32*)iph &= ~htonl(INET_ECN_MASK << 20);
}
static inline void ipv6_copy_dscp(unsigned int dscp, struct ipv6hdr *inner)
{
dscp &= ~INET_ECN_MASK;
ipv6_change_dsfield(inner, INET_ECN_MASK, dscp);
}
static inline int INET_ECN_set_ce(struct sk_buff *skb)
{
switch (skb->protocol) {
case cpu_to_be16(ETH_P_IP):
if (skb->network_header + sizeof(struct iphdr) <= skb->tail)
return IP_ECN_set_ce(ip_hdr(skb));
break;
case cpu_to_be16(ETH_P_IPV6):
if (skb->network_header + sizeof(struct ipv6hdr) <= skb->tail)
return IP6_ECN_set_ce(ipv6_hdr(skb));
break;
}
return 0;
}
#endif