From: Eric Dumazet <eric.dumazet@gmail.com>
To: Christoph Lameter <cl@linux-foundation.org>
Cc: David Miller <davem@davemloft.net>,
netdev@vger.kernel.org, shemminger@vyatta.com
Subject: Re: [PATCH] IP: Increment INADDRERRORS if routing for a packet is not successful
Date: Wed, 02 Jun 2010 21:25:32 +0200 [thread overview]
Message-ID: <1275506732.2519.23.camel@edumazet-laptop> (raw)
In-Reply-To: <alpine.DEB.2.00.1006021355040.32431@router.home>
Le mercredi 02 juin 2010 à 13:59 -0500, Christoph Lameter a écrit :
> The rp_filter is rejecting traffic coming into a NIC for which the kernel
> has a multicast join list that indicates that this traffic is expected on
> this NIC. You could consult the MC subscription list to verify that the
> traffic is coming into the right NIC.
>
> In the MC case the user can explicitly specify through which NIC the
> traffic is expected. See IP_ADD_MEMBERSHIP.
This has litle to do with MC. We certainly are not going to check MC
membership in fib_validate_source() !
Say we have eth0 on 192.168.0.1/24 and eth1 on 192.168.0.2/24
Then we cannot use rp_filter = 1, even with unicast trafic.
I really dont understand why you would setup rp_filter in such a
situation. This wont work.
Now, I agree we should have a counter somewhere to help admins to
understand their error ;)
Here is patch I am currently testing.
I finaly created a new counter, because its a linux specific check.
diff --git a/include/linux/snmp.h b/include/linux/snmp.h
index 5279771..ebb0c80 100644
--- a/include/linux/snmp.h
+++ b/include/linux/snmp.h
@@ -229,6 +229,7 @@ enum
LINUX_MIB_TCPBACKLOGDROP,
LINUX_MIB_TCPMINTTLDROP, /* RFC 5082 */
LINUX_MIB_TCPDEFERACCEPTDROP,
+ LINUX_MIB_IPRPFILTER, /* IP Reverse Path Filter (rp_filter) */
__LINUX_MIB_MAX
};
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 4f0ed45..e830f7a 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -284,7 +284,7 @@ int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif,
if (no_addr)
goto last_resort;
if (rpf == 1)
- goto e_inval;
+ goto e_rpf;
fl.oif = dev->ifindex;
ret = 0;
@@ -299,7 +299,7 @@ int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif,
last_resort:
if (rpf)
- goto e_inval;
+ goto e_rpf;
*spec_dst = inet_select_addr(dev, 0, RT_SCOPE_UNIVERSE);
*itag = 0;
return 0;
@@ -308,6 +308,8 @@ e_inval_res:
fib_res_put(&res);
e_inval:
return -EINVAL;
+e_rpf:
+ return -EXDEV;
}
static inline __be32 sk_extract_addr(struct sockaddr *addr)
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index d930dc5..d52c9da 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -340,6 +340,9 @@ static int ip_rcv_finish(struct sk_buff *skb)
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/proc.c b/net/ipv4/proc.c
index 3dc9914..e320ca6 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -252,6 +252,7 @@ static const struct snmp_mib snmp4_net_list[] = {
SNMP_MIB_ITEM("TCPBacklogDrop", LINUX_MIB_TCPBACKLOGDROP),
SNMP_MIB_ITEM("TCPMinTTLDrop", LINUX_MIB_TCPMINTTLDROP),
SNMP_MIB_ITEM("TCPDeferAcceptDrop", LINUX_MIB_TCPDEFERACCEPTDROP),
+ SNMP_MIB_ITEM("IPReversePathFilter", LINUX_MIB_IPRPFILTER),
SNMP_MIB_SENTINEL
};
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 8495bce..3a264f7 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1851,6 +1851,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
__be32 spec_dst;
struct in_device *in_dev = in_dev_get(dev);
u32 itag = 0;
+ int err;
/* Primary sanity checks. */
@@ -1865,10 +1866,12 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
if (!ipv4_is_local_multicast(daddr))
goto e_inval;
spec_dst = inet_select_addr(dev, 0, RT_SCOPE_LINK);
- } else if (fib_validate_source(saddr, 0, tos, 0,
- dev, &spec_dst, &itag, 0) < 0)
- goto e_inval;
-
+ } else {
+ err = fib_validate_source(saddr, 0, tos, 0, dev, &spec_dst,
+ &itag, 0);
+ if (err < 0)
+ goto e_err;
+ }
rth = dst_alloc(&ipv4_dst_ops);
if (!rth)
goto e_nobufs;
@@ -1922,6 +1925,9 @@ e_nobufs:
e_inval:
in_dev_put(in_dev);
return -EINVAL;
+e_err:
+ in_dev_put(in_dev);
+ return err;
}
@@ -1985,7 +1991,6 @@ static int __mkroute_input(struct sk_buff *skb,
ip_handle_martian_source(in_dev->dev, in_dev, skb, daddr,
saddr);
- err = -EINVAL;
goto cleanup;
}
@@ -2191,7 +2196,7 @@ brd_input:
err = fib_validate_source(saddr, 0, tos, 0, dev, &spec_dst,
&itag, skb->mark);
if (err < 0)
- goto martian_source;
+ goto martian_source_keep_err;
if (err)
flags |= RTCF_DIRECTSRC;
}
@@ -2272,8 +2277,10 @@ e_nobufs:
goto done;
martian_source:
+ err = -EINVAL;
+martian_source_keep_err:
ip_handle_martian_source(dev, in_dev, skb, daddr, saddr);
- goto e_inval;
+ goto done;
}
int ip_route_input_common(struct sk_buff *skb, __be32 daddr, __be32 saddr,
next prev parent reply other threads:[~2010-06-02 19:25 UTC|newest]
Thread overview: 28+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-06-01 21:13 [PATCH] IP: Increment INADDRERRORS if routing for a packet is not successful Christoph Lameter
2010-06-01 22:07 ` Eric Dumazet
2010-06-01 22:23 ` David Miller
2010-06-02 15:27 ` Christoph Lameter
2010-06-02 15:29 ` David Miller
2010-06-02 15:32 ` Eric Dumazet
2010-06-02 16:12 ` Christoph Lameter
2010-06-02 16:19 ` David Miller
2010-06-02 16:27 ` Christoph Lameter
2010-06-02 16:33 ` Eric Dumazet
2010-06-02 16:49 ` Christoph Lameter
2010-06-02 17:12 ` David Miller
2010-06-02 17:19 ` Eric Dumazet
2010-06-02 17:41 ` Neil Horman
2010-06-02 17:31 ` David Miller
2010-06-02 17:46 ` Eric Dumazet
2010-06-02 18:01 ` Christoph Lameter
2010-06-02 18:41 ` Eric Dumazet
2010-06-02 18:59 ` Christoph Lameter
2010-06-02 19:25 ` Eric Dumazet [this message]
2010-06-02 20:11 ` Christoph Lameter
2010-06-02 22:05 ` [PATCH net-next-2.6] ipv4: add LINUX_MIB_IPRPFILTER snmp counter Eric Dumazet
2010-06-03 10:19 ` David Miller
2010-06-03 3:50 ` [PATCH] IP: Increment INADDRERRORS if routing for a packet is not successful Bill Fink
2010-06-03 3:54 ` Eric Dumazet
2010-06-03 4:56 ` Bill Fink
2010-06-02 16:28 ` Eric Dumazet
2010-06-02 16:35 ` Christoph Lameter
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1275506732.2519.23.camel@edumazet-laptop \
--to=eric.dumazet@gmail.com \
--cc=cl@linux-foundation.org \
--cc=davem@davemloft.net \
--cc=netdev@vger.kernel.org \
--cc=shemminger@vyatta.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox