| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <20120620.031543.1511134879638711616.davem@davemloft.net>
Date: Wed, 20 Jun 2012 03:15:43 -0700 (PDT)
From: David Miller <davem@...emloft.net>
To: eric.dumazet@...il.com
Cc: shemminger@...tta.com, netdev@...r.kernel.org
Subject: Re: [PATCH v2] ipv4: Early TCP socket demux.
From: David Miller <davem@...emloft.net>
Date: Tue, 19 Jun 2012 23:14:12 -0700 (PDT)
> From: Eric Dumazet <eric.dumazet@...il.com>
> Date: Wed, 20 Jun 2012 07:59:00 +0200
>
>> On Tue, 2012-06-19 at 21:46 -0700, David Miller wrote:
>>
>>> These numbers can be decreased further, because since we're already
>>> looking at the TCP header we can pre-cook the TCP control block in the
>>> SKB and skip much of the stuff that tcp_v4_rcv() does since we've done
>>> it already in the early demux code.
>>
>> It could be done at GRO level and remove one another demux.
>>
>> As routers probably have no use of GRO, no need of additional knob.
>
> That's a great idea.
Here's what I have so far, the ipv6 implementation we get nearly for
free :-)
Initially I tried to use ->gro_complete() for this as it was more
natural, but we abort before we get there for a lot of cases where we
want to use the early demux and cached route (ACKs, FINs, sub-mss
sized packets, etc.)
diff --git a/include/net/protocol.h b/include/net/protocol.h
index 967b926..a1b1b53 100644
--- a/include/net/protocol.h
+++ b/include/net/protocol.h
@@ -37,7 +37,6 @@
/* This is used to register protocols. */
struct net_protocol {
- int (*early_demux)(struct sk_buff *skb);
int (*handler)(struct sk_buff *skb);
void (*err_handler)(struct sk_buff *skb, u32 info);
int (*gso_send_check)(struct sk_buff *skb);
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 5b21522..c1b5626 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -2956,6 +2956,12 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb)
return -ENOMEM;
__copy_skb_header(nskb, p);
+ if (p->sk) {
+ nskb->sk = p->sk;
+ nskb->destructor = p->destructor;
+ p->sk = NULL;
+ p->destructor = NULL;
+ }
nskb->mac_len = p->mac_len;
skb_reserve(nskb, headroom);
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 07a02f6..0aabad7 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1519,7 +1519,6 @@ static const struct net_protocol igmp_protocol = {
#endif
static const struct net_protocol tcp_protocol = {
- .early_demux = tcp_v4_early_demux,
.handler = tcp_v4_rcv,
.err_handler = tcp_v4_err,
.gso_send_check = tcp_v4_gso_send_check,
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index 93b092c..c4fe1d2 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -323,32 +323,19 @@ static int ip_rcv_finish(struct sk_buff *skb)
* how the packet travels inside Linux networking.
*/
if (skb_dst(skb) == NULL) {
- const struct net_protocol *ipprot;
- int protocol = iph->protocol;
- int err;
-
- rcu_read_lock();
- ipprot = rcu_dereference(inet_protos[protocol]);
- err = -ENOENT;
- if (ipprot && ipprot->early_demux)
- err = ipprot->early_demux(skb);
- rcu_read_unlock();
-
- if (err) {
- err = ip_route_input_noref(skb, iph->daddr, iph->saddr,
- iph->tos, skb->dev);
- if (unlikely(err)) {
- if (err == -EHOSTUNREACH)
- IP_INC_STATS_BH(dev_net(skb->dev),
- IPSTATS_MIB_INADDRERRORS);
- else if (err == -ENETUNREACH)
- IP_INC_STATS_BH(dev_net(skb->dev),
- IPSTATS_MIB_INNOROUTES);
- else if (err == -EXDEV)
- NET_INC_STATS_BH(dev_net(skb->dev),
- LINUX_MIB_IPRPFILTER);
- goto drop;
- }
+ int err = ip_route_input_noref(skb, iph->daddr, iph->saddr,
+ iph->tos, skb->dev);
+ if (unlikely(err)) {
+ if (err == -EHOSTUNREACH)
+ IP_INC_STATS_BH(dev_net(skb->dev),
+ IPSTATS_MIB_INADDRERRORS);
+ else if (err == -ENETUNREACH)
+ IP_INC_STATS_BH(dev_net(skb->dev),
+ IPSTATS_MIB_INNOROUTES);
+ else if (err == -EXDEV)
+ NET_INC_STATS_BH(dev_net(skb->dev),
+ LINUX_MIB_IPRPFILTER);
+ goto drop;
}
}
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 13857df..2a483ad 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1671,52 +1671,6 @@ csum_err:
}
EXPORT_SYMBOL(tcp_v4_do_rcv);
-int tcp_v4_early_demux(struct sk_buff *skb)
-{
- struct net *net = dev_net(skb->dev);
- const struct iphdr *iph;
- const struct tcphdr *th;
- struct sock *sk;
- int err;
-
- err = -ENOENT;
- if (skb->pkt_type != PACKET_HOST)
- goto out_err;
-
- if (!pskb_may_pull(skb, ip_hdrlen(skb) + sizeof(struct tcphdr)))
- goto out_err;
-
- iph = ip_hdr(skb);
- th = (struct tcphdr *) ((char *)iph + ip_hdrlen(skb));
-
- if (th->doff < sizeof(struct tcphdr) / 4)
- goto out_err;
-
- if (!pskb_may_pull(skb, ip_hdrlen(skb) + th->doff * 4))
- goto out_err;
-
- sk = __inet_lookup_established(net, &tcp_hashinfo,
- iph->saddr, th->source,
- iph->daddr, th->dest,
- skb->dev->ifindex);
- if (sk) {
- skb->sk = sk;
- skb->destructor = sock_edemux;
- if (sk->sk_state != TCP_TIME_WAIT) {
- struct dst_entry *dst = sk->sk_rx_dst;
- if (dst)
- dst = dst_check(dst, 0);
- if (dst) {
- skb_dst_set_noref(skb, dst);
- err = 0;
- }
- }
- }
-
-out_err:
- return err;
-}
-
/*
* From tcp_input.c
*/
@@ -2576,6 +2530,7 @@ void tcp4_proc_exit(void)
struct sk_buff **tcp4_gro_receive(struct sk_buff **head, struct sk_buff *skb)
{
const struct iphdr *iph = skb_gro_network_header(skb);
+ struct sk_buff **pp;
switch (skb->ip_summed) {
case CHECKSUM_COMPLETE:
@@ -2591,7 +2546,36 @@ struct sk_buff **tcp4_gro_receive(struct sk_buff **head, struct sk_buff *skb)
return NULL;
}
- return tcp_gro_receive(head, skb);
+ pp = tcp_gro_receive(head, skb);
+
+ if (!NAPI_GRO_CB(skb)->same_flow) {
+ const struct tcphdr *th = tcp_hdr(skb);
+ struct net_device *dev = skb->dev;
+ struct sock *sk;
+
+ sk = __inet_lookup_established(dev_net(dev), &tcp_hashinfo,
+ iph->saddr, th->source,
+ iph->daddr, th->dest,
+ dev->ifindex);
+ if (sk) {
+ skb_orphan(skb);
+ skb->sk = sk;
+ skb->destructor = sock_edemux;
+ if (!skb_dst(skb) &&
+ sk->sk_state != TCP_TIME_WAIT) {
+ struct dst_entry *dst = sk->sk_rx_dst;
+ if (dst)
+ dst = dst_check(dst, 0);
+ if (dst) {
+ struct rtable *rt = (struct rtable *) dst;
+
+ if (rt->rt_iif == dev->ifindex)
+ skb_dst_set_noref(skb, dst);
+ }
+ }
+ }
+ }
+ return pp;
}
int tcp4_gro_complete(struct sk_buff *skb)
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 26a8862..b8ea463 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -797,6 +797,7 @@ static struct sk_buff **tcp6_gro_receive(struct sk_buff **head,
struct sk_buff *skb)
{
const struct ipv6hdr *iph = skb_gro_network_header(skb);
+ struct sk_buff **pp;
switch (skb->ip_summed) {
case CHECKSUM_COMPLETE:
@@ -812,7 +813,32 @@ static struct sk_buff **tcp6_gro_receive(struct sk_buff **head,
return NULL;
}
- return tcp_gro_receive(head, skb);
+ pp = tcp_gro_receive(head, skb);
+
+ if (!NAPI_GRO_CB(skb)->same_flow) {
+ const struct tcphdr *th = tcp_hdr(skb);
+ struct net_device *dev = skb->dev;
+ struct sock *sk;
+
+ sk = __inet6_lookup_established(dev_net(dev), &tcp_hashinfo,
+ &iph->saddr, th->source,
+ &iph->daddr, th->dest,
+ dev->ifindex);
+ if (sk) {
+ skb_orphan(skb);
+ skb->sk = sk;
+ skb->destructor = sock_edemux;
+ if (!skb_dst(skb) &&
+ sk->sk_state != TCP_TIME_WAIT) {
+ struct dst_entry *dst = sk->sk_rx_dst;
+ if (dst)
+ dst = dst_check(dst, 0);
+ if (dst)
+ skb_dst_set(skb, dst);
+ }
+ }
+ }
+ return pp;
}
static int tcp6_gro_complete(struct sk_buff *skb)
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Powered by blists - more mailing lists