kernel_optimize_test/include/net/flow.h
Julian Anastasov e6b45241c5 ipv4: reset flowi parameters on route connect
Eric Dumazet found that commit 813b3b5db8
(ipv4: Use caller's on-stack flowi as-is in output
route lookups.) that comes in 3.0 added a regression.
The problem appears to be that resulting flowi4_oif is
used incorrectly as input parameter to some routing lookups.
The result is that when connecting to local port without
listener if the IP address that is used is not on a loopback
interface we incorrectly assign RTN_UNICAST to the output
route because no route is matched by oif=lo. The RST packet
can not be sent immediately by tcp_v4_send_reset because
it expects RTN_LOCAL.

	So, change ip_route_connect and ip_route_newports to
update the flowi4 fields that are input parameters because
we do not want unnecessary binding to oif.

	To make it clear what are the input parameters that
can be modified during lookup and to show which fields of
floiw4 are reused add a new function to update the flowi4
structure: flowi4_update_output.

Thanks to Yurij M. Plotnikov for providing a bug report including a
program to reproduce the problem.

Thanks to Eric Dumazet for tracking the problem down to
tcp_v4_send_reset and providing initial fix.

Reported-by: Yurij M. Plotnikov <Yurij.Plotnikov@oktetlabs.ru>
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Acked-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-02-04 19:29:48 -05:00

227 lines
5.7 KiB
C

/*
*
* Generic internet FLOW.
*
*/
#ifndef _NET_FLOW_H
#define _NET_FLOW_H
#include <linux/socket.h>
#include <linux/in6.h>
#include <linux/atomic.h>
struct flowi_common {
int flowic_oif;
int flowic_iif;
__u32 flowic_mark;
__u8 flowic_tos;
__u8 flowic_scope;
__u8 flowic_proto;
__u8 flowic_flags;
#define FLOWI_FLAG_ANYSRC 0x01
#define FLOWI_FLAG_PRECOW_METRICS 0x02
#define FLOWI_FLAG_CAN_SLEEP 0x04
__u32 flowic_secid;
};
union flowi_uli {
struct {
__be16 dport;
__be16 sport;
} ports;
struct {
__u8 type;
__u8 code;
} icmpt;
struct {
__le16 dport;
__le16 sport;
} dnports;
__be32 spi;
__be32 gre_key;
struct {
__u8 type;
} mht;
};
struct flowi4 {
struct flowi_common __fl_common;
#define flowi4_oif __fl_common.flowic_oif
#define flowi4_iif __fl_common.flowic_iif
#define flowi4_mark __fl_common.flowic_mark
#define flowi4_tos __fl_common.flowic_tos
#define flowi4_scope __fl_common.flowic_scope
#define flowi4_proto __fl_common.flowic_proto
#define flowi4_flags __fl_common.flowic_flags
#define flowi4_secid __fl_common.flowic_secid
/* (saddr,daddr) must be grouped, same order as in IP header */
__be32 saddr;
__be32 daddr;
union flowi_uli uli;
#define fl4_sport uli.ports.sport
#define fl4_dport uli.ports.dport
#define fl4_icmp_type uli.icmpt.type
#define fl4_icmp_code uli.icmpt.code
#define fl4_ipsec_spi uli.spi
#define fl4_mh_type uli.mht.type
#define fl4_gre_key uli.gre_key
} __attribute__((__aligned__(BITS_PER_LONG/8)));
static inline void flowi4_init_output(struct flowi4 *fl4, int oif,
__u32 mark, __u8 tos, __u8 scope,
__u8 proto, __u8 flags,
__be32 daddr, __be32 saddr,
__be16 dport, __be16 sport)
{
fl4->flowi4_oif = oif;
fl4->flowi4_iif = 0;
fl4->flowi4_mark = mark;
fl4->flowi4_tos = tos;
fl4->flowi4_scope = scope;
fl4->flowi4_proto = proto;
fl4->flowi4_flags = flags;
fl4->flowi4_secid = 0;
fl4->daddr = daddr;
fl4->saddr = saddr;
fl4->fl4_dport = dport;
fl4->fl4_sport = sport;
}
/* Reset some input parameters after previous lookup */
static inline void flowi4_update_output(struct flowi4 *fl4, int oif, __u8 tos,
__be32 daddr, __be32 saddr)
{
fl4->flowi4_oif = oif;
fl4->flowi4_tos = tos;
fl4->daddr = daddr;
fl4->saddr = saddr;
}
struct flowi6 {
struct flowi_common __fl_common;
#define flowi6_oif __fl_common.flowic_oif
#define flowi6_iif __fl_common.flowic_iif
#define flowi6_mark __fl_common.flowic_mark
#define flowi6_tos __fl_common.flowic_tos
#define flowi6_scope __fl_common.flowic_scope
#define flowi6_proto __fl_common.flowic_proto
#define flowi6_flags __fl_common.flowic_flags
#define flowi6_secid __fl_common.flowic_secid
struct in6_addr daddr;
struct in6_addr saddr;
__be32 flowlabel;
union flowi_uli uli;
#define fl6_sport uli.ports.sport
#define fl6_dport uli.ports.dport
#define fl6_icmp_type uli.icmpt.type
#define fl6_icmp_code uli.icmpt.code
#define fl6_ipsec_spi uli.spi
#define fl6_mh_type uli.mht.type
#define fl6_gre_key uli.gre_key
} __attribute__((__aligned__(BITS_PER_LONG/8)));
struct flowidn {
struct flowi_common __fl_common;
#define flowidn_oif __fl_common.flowic_oif
#define flowidn_iif __fl_common.flowic_iif
#define flowidn_mark __fl_common.flowic_mark
#define flowidn_scope __fl_common.flowic_scope
#define flowidn_proto __fl_common.flowic_proto
#define flowidn_flags __fl_common.flowic_flags
__le16 daddr;
__le16 saddr;
union flowi_uli uli;
#define fld_sport uli.ports.sport
#define fld_dport uli.ports.dport
} __attribute__((__aligned__(BITS_PER_LONG/8)));
struct flowi {
union {
struct flowi_common __fl_common;
struct flowi4 ip4;
struct flowi6 ip6;
struct flowidn dn;
} u;
#define flowi_oif u.__fl_common.flowic_oif
#define flowi_iif u.__fl_common.flowic_iif
#define flowi_mark u.__fl_common.flowic_mark
#define flowi_tos u.__fl_common.flowic_tos
#define flowi_scope u.__fl_common.flowic_scope
#define flowi_proto u.__fl_common.flowic_proto
#define flowi_flags u.__fl_common.flowic_flags
#define flowi_secid u.__fl_common.flowic_secid
} __attribute__((__aligned__(BITS_PER_LONG/8)));
static inline struct flowi *flowi4_to_flowi(struct flowi4 *fl4)
{
return container_of(fl4, struct flowi, u.ip4);
}
static inline struct flowi *flowi6_to_flowi(struct flowi6 *fl6)
{
return container_of(fl6, struct flowi, u.ip6);
}
static inline struct flowi *flowidn_to_flowi(struct flowidn *fldn)
{
return container_of(fldn, struct flowi, u.dn);
}
typedef unsigned long flow_compare_t;
static inline size_t flow_key_size(u16 family)
{
switch (family) {
case AF_INET:
BUILD_BUG_ON(sizeof(struct flowi4) % sizeof(flow_compare_t));
return sizeof(struct flowi4) / sizeof(flow_compare_t);
case AF_INET6:
BUILD_BUG_ON(sizeof(struct flowi6) % sizeof(flow_compare_t));
return sizeof(struct flowi6) / sizeof(flow_compare_t);
case AF_DECnet:
BUILD_BUG_ON(sizeof(struct flowidn) % sizeof(flow_compare_t));
return sizeof(struct flowidn) / sizeof(flow_compare_t);
}
return 0;
}
#define FLOW_DIR_IN 0
#define FLOW_DIR_OUT 1
#define FLOW_DIR_FWD 2
struct net;
struct sock;
struct flow_cache_ops;
struct flow_cache_object {
const struct flow_cache_ops *ops;
};
struct flow_cache_ops {
struct flow_cache_object *(*get)(struct flow_cache_object *);
int (*check)(struct flow_cache_object *);
void (*delete)(struct flow_cache_object *);
};
typedef struct flow_cache_object *(*flow_resolve_t)(
struct net *net, const struct flowi *key, u16 family,
u8 dir, struct flow_cache_object *oldobj, void *ctx);
extern struct flow_cache_object *flow_cache_lookup(
struct net *net, const struct flowi *key, u16 family,
u8 dir, flow_resolve_t resolver, void *ctx);
extern void flow_cache_flush(void);
extern void flow_cache_flush_deferred(void);
extern atomic_t flow_cache_genid;
#endif