Commit c10237e0 authored by David S. Miller's avatar David S. Miller

Revert "ipv4: tcp: dont cache unconfirmed intput dst"

This reverts commit c074da28.

This change has several unwanted side effects:

1) Sockets will cache the DST_NOCACHE route in sk->sk_rx_dst and we'll
   thus never create a real cached route.

2) All TCP traffic will use DST_NOCACHE and never use the routing
   cache at all.
Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parent e440cf2c
...@@ -37,7 +37,7 @@ ...@@ -37,7 +37,7 @@
/* This is used to register protocols. */ /* This is used to register protocols. */
struct net_protocol { struct net_protocol {
int (*early_demux)(struct sk_buff *skb, bool *nocache); int (*early_demux)(struct sk_buff *skb);
int (*handler)(struct sk_buff *skb); int (*handler)(struct sk_buff *skb);
void (*err_handler)(struct sk_buff *skb, u32 info); void (*err_handler)(struct sk_buff *skb, u32 info);
int (*gso_send_check)(struct sk_buff *skb); int (*gso_send_check)(struct sk_buff *skb);
......
...@@ -201,18 +201,18 @@ static inline struct rtable *ip_route_output_gre(struct net *net, struct flowi4 ...@@ -201,18 +201,18 @@ static inline struct rtable *ip_route_output_gre(struct net *net, struct flowi4
} }
extern int ip_route_input_common(struct sk_buff *skb, __be32 dst, __be32 src, extern int ip_route_input_common(struct sk_buff *skb, __be32 dst, __be32 src,
u8 tos, struct net_device *devin, bool noref, bool nocache); u8 tos, struct net_device *devin, bool noref);
static inline int ip_route_input(struct sk_buff *skb, __be32 dst, __be32 src, static inline int ip_route_input(struct sk_buff *skb, __be32 dst, __be32 src,
u8 tos, struct net_device *devin) u8 tos, struct net_device *devin)
{ {
return ip_route_input_common(skb, dst, src, tos, devin, false, false); return ip_route_input_common(skb, dst, src, tos, devin, false);
} }
static inline int ip_route_input_noref(struct sk_buff *skb, __be32 dst, __be32 src, static inline int ip_route_input_noref(struct sk_buff *skb, __be32 dst, __be32 src,
u8 tos, struct net_device *devin, bool nocache) u8 tos, struct net_device *devin)
{ {
return ip_route_input_common(skb, dst, src, tos, devin, true, nocache); return ip_route_input_common(skb, dst, src, tos, devin, true);
} }
extern void ipv4_update_pmtu(struct sk_buff *skb, struct net *net, u32 mtu, extern void ipv4_update_pmtu(struct sk_buff *skb, struct net *net, u32 mtu,
......
...@@ -325,7 +325,7 @@ extern void tcp_v4_err(struct sk_buff *skb, u32); ...@@ -325,7 +325,7 @@ extern void tcp_v4_err(struct sk_buff *skb, u32);
extern void tcp_shutdown (struct sock *sk, int how); extern void tcp_shutdown (struct sock *sk, int how);
extern int tcp_v4_early_demux(struct sk_buff *skb, bool *nocache); extern int tcp_v4_early_demux(struct sk_buff *skb);
extern int tcp_v4_rcv(struct sk_buff *skb); extern int tcp_v4_rcv(struct sk_buff *skb);
extern struct inet_peer *tcp_v4_get_peer(struct sock *sk); extern struct inet_peer *tcp_v4_get_peer(struct sock *sk);
......
...@@ -828,7 +828,7 @@ static int arp_process(struct sk_buff *skb) ...@@ -828,7 +828,7 @@ static int arp_process(struct sk_buff *skb)
} }
if (arp->ar_op == htons(ARPOP_REQUEST) && if (arp->ar_op == htons(ARPOP_REQUEST) &&
ip_route_input_noref(skb, tip, sip, 0, dev, false) == 0) { ip_route_input_noref(skb, tip, sip, 0, dev) == 0) {
rt = skb_rtable(skb); rt = skb_rtable(skb);
addr_type = rt->rt_type; addr_type = rt->rt_type;
......
...@@ -259,7 +259,7 @@ static void ip_expire(unsigned long arg) ...@@ -259,7 +259,7 @@ static void ip_expire(unsigned long arg)
skb_dst_drop(head); skb_dst_drop(head);
iph = ip_hdr(head); iph = ip_hdr(head);
err = ip_route_input_noref(head, iph->daddr, iph->saddr, err = ip_route_input_noref(head, iph->daddr, iph->saddr,
iph->tos, head->dev, false); iph->tos, head->dev);
if (err) if (err)
goto out_rcu_unlock; goto out_rcu_unlock;
......
...@@ -326,7 +326,6 @@ static int ip_rcv_finish(struct sk_buff *skb) ...@@ -326,7 +326,6 @@ static int ip_rcv_finish(struct sk_buff *skb)
*/ */
if (skb_dst(skb) == NULL) { if (skb_dst(skb) == NULL) {
int err = -ENOENT; int err = -ENOENT;
bool nocache = false;
if (sysctl_ip_early_demux) { if (sysctl_ip_early_demux) {
const struct net_protocol *ipprot; const struct net_protocol *ipprot;
...@@ -335,13 +334,13 @@ static int ip_rcv_finish(struct sk_buff *skb) ...@@ -335,13 +334,13 @@ static int ip_rcv_finish(struct sk_buff *skb)
rcu_read_lock(); rcu_read_lock();
ipprot = rcu_dereference(inet_protos[protocol]); ipprot = rcu_dereference(inet_protos[protocol]);
if (ipprot && ipprot->early_demux) if (ipprot && ipprot->early_demux)
err = ipprot->early_demux(skb, &nocache); err = ipprot->early_demux(skb);
rcu_read_unlock(); rcu_read_unlock();
} }
if (err) { if (err) {
err = ip_route_input_noref(skb, iph->daddr, iph->saddr, err = ip_route_input_noref(skb, iph->daddr, iph->saddr,
iph->tos, skb->dev, nocache); iph->tos, skb->dev);
if (unlikely(err)) { if (unlikely(err)) {
if (err == -EXDEV) if (err == -EXDEV)
NET_INC_STATS_BH(dev_net(skb->dev), NET_INC_STATS_BH(dev_net(skb->dev),
......
...@@ -2214,7 +2214,7 @@ static int ip_mkroute_input(struct sk_buff *skb, ...@@ -2214,7 +2214,7 @@ static int ip_mkroute_input(struct sk_buff *skb,
*/ */
static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
u8 tos, struct net_device *dev, bool nocache) u8 tos, struct net_device *dev)
{ {
struct fib_result res; struct fib_result res;
struct in_device *in_dev = __in_dev_get_rcu(dev); struct in_device *in_dev = __in_dev_get_rcu(dev);
...@@ -2353,8 +2353,6 @@ out: return err; ...@@ -2353,8 +2353,6 @@ out: return err;
rth->dst.error= -err; rth->dst.error= -err;
rth->rt_flags &= ~RTCF_LOCAL; rth->rt_flags &= ~RTCF_LOCAL;
} }
if (nocache)
rth->dst.flags |= DST_NOCACHE;
hash = rt_hash(daddr, saddr, fl4.flowi4_iif, rt_genid(net)); hash = rt_hash(daddr, saddr, fl4.flowi4_iif, rt_genid(net));
rth = rt_intern_hash(hash, rth, skb, fl4.flowi4_iif); rth = rt_intern_hash(hash, rth, skb, fl4.flowi4_iif);
err = 0; err = 0;
...@@ -2397,7 +2395,7 @@ out: return err; ...@@ -2397,7 +2395,7 @@ out: return err;
} }
int ip_route_input_common(struct sk_buff *skb, __be32 daddr, __be32 saddr, int ip_route_input_common(struct sk_buff *skb, __be32 daddr, __be32 saddr,
u8 tos, struct net_device *dev, bool noref, bool nocache) u8 tos, struct net_device *dev, bool noref)
{ {
struct rtable *rth; struct rtable *rth;
unsigned int hash; unsigned int hash;
...@@ -2473,7 +2471,7 @@ int ip_route_input_common(struct sk_buff *skb, __be32 daddr, __be32 saddr, ...@@ -2473,7 +2471,7 @@ int ip_route_input_common(struct sk_buff *skb, __be32 daddr, __be32 saddr,
rcu_read_unlock(); rcu_read_unlock();
return -EINVAL; return -EINVAL;
} }
res = ip_route_input_slow(skb, daddr, saddr, tos, dev, nocache); res = ip_route_input_slow(skb, daddr, saddr, tos, dev);
rcu_read_unlock(); rcu_read_unlock();
return res; return res;
} }
......
...@@ -1673,7 +1673,7 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb) ...@@ -1673,7 +1673,7 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)
} }
EXPORT_SYMBOL(tcp_v4_do_rcv); EXPORT_SYMBOL(tcp_v4_do_rcv);
int tcp_v4_early_demux(struct sk_buff *skb, bool *no_dst_cache) int tcp_v4_early_demux(struct sk_buff *skb)
{ {
struct net *net = dev_net(skb->dev); struct net *net = dev_net(skb->dev);
const struct iphdr *iph; const struct iphdr *iph;
...@@ -1719,8 +1719,6 @@ int tcp_v4_early_demux(struct sk_buff *skb, bool *no_dst_cache) ...@@ -1719,8 +1719,6 @@ int tcp_v4_early_demux(struct sk_buff *skb, bool *no_dst_cache)
} }
} }
} }
} else {
*no_dst_cache = true;
} }
out_err: out_err:
......
...@@ -28,7 +28,7 @@ static inline int xfrm4_rcv_encap_finish(struct sk_buff *skb) ...@@ -28,7 +28,7 @@ static inline int xfrm4_rcv_encap_finish(struct sk_buff *skb)
const struct iphdr *iph = ip_hdr(skb); const struct iphdr *iph = ip_hdr(skb);
if (ip_route_input_noref(skb, iph->daddr, iph->saddr, if (ip_route_input_noref(skb, iph->daddr, iph->saddr,
iph->tos, skb->dev, false)) iph->tos, skb->dev))
goto drop; goto drop;
} }
return dst_input(skb); return dst_input(skb);
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment