net: reevalulate autoflowlabel setting after sysctl setting

sysctl.ip6.auto_flowlabels is default 1. In our hosts, we set it to 2.
If sockopt doesn't set autoflowlabel, outcome packets from the hosts are
supposed to not include flowlabel. This is true for normal packet, but
not for reset packet.

The reason is ipv6_pinfo.autoflowlabel is set in sock creation. Later if
we change sysctl.ip6.auto_flowlabels, the ipv6_pinfo.autoflowlabel isn't
changed, so the sock will keep the old behavior in terms of auto
flowlabel. Reset packet is suffering from this problem, because reset
packet is sent from a special control socket, which is created at boot
time. Since sysctl.ipv6.auto_flowlabels is 1 by default, the control
socket will always have its ipv6_pinfo.autoflowlabel set, even after
user set sysctl.ipv6.auto_flowlabels to 1, so reset packset will always
have flowlabel. Normal sock created before sysctl setting suffers from
the same issue. We can't even turn off autoflowlabel unless we kill all
socks in the hosts.

To fix this, if IPV6_AUTOFLOWLABEL sockopt is used, we use the
autoflowlabel setting from user, otherwise we always call
ip6_default_np_autolabel() which has the new settings of sysctl.

Note, this changes behavior a little bit. Before commit 42240901f7c4
(ipv6: Implement different admin modes for automatic flow labels), the
autoflowlabel behavior of a sock isn't sticky, eg, if sysctl changes,
existing connection will change autoflowlabel behavior. After that
commit, autoflowlabel behavior is sticky in the whole life of the sock.
With this patch, the behavior isn't sticky again.

Cc: Martin KaFai Lau <kafai@fb.com>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Tom Herbert <tom@quantonium.net>
Signed-off-by: Shaohua Li <shli@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index cb18c6290ca87290996e636f3eda14eb03d26316..8415bf1a9776245b810c8f92fa16c98eb038a45f 100644 (file)
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -273,7 +273,8 @@ struct ipv6_pinfo {
                                                 * 100: prefer care-of address
                                                 */
                                dontfrag:1,
-                               autoflowlabel:1;
+                               autoflowlabel:1,
+                               autoflowlabel_set:1;
        __u8                    min_hopcount;
        __u8                    tclass;
        __be32                  rcv_flowinfo;

diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index c26f71234b9c01a82ec9d40423ee28957468ed46..c9441ca4539936486291147a47a84ef1b2ecf095 100644 (file)
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -210,7 +210,6 @@ lookup_protocol:
        np->mcast_hops  = IPV6_DEFAULT_MCASTHOPS;
        np->mc_loop     = 1;
        np->pmtudisc    = IPV6_PMTUDISC_WANT;
-       np->autoflowlabel = ip6_default_np_autolabel(net);
        np->repflow     = net->ipv6.sysctl.flowlabel_reflect;
        sk->sk_ipv6only = net->ipv6.sysctl.bindv6only;
 

diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 5110a418cc4d0c1040506394460cb482698d8c15..f7dd51c4231415fd1321fd431194d896ea2d1689 100644 (file)
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -166,6 +166,14 @@ int ip6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
                            !(IP6CB(skb)->flags & IP6SKB_REROUTED));
 }
 
+static bool ip6_autoflowlabel(struct net *net, const struct ipv6_pinfo *np)
+{
+       if (!np->autoflowlabel_set)
+               return ip6_default_np_autolabel(net);
+       else
+               return np->autoflowlabel;
+}
+
 /*
  * xmit an sk_buff (used by TCP, SCTP and DCCP)
  * Note : socket lock is not held for SYNACK packets, but might be modified
@@ -230,7 +238,7 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
                hlimit = ip6_dst_hoplimit(dst);
 
        ip6_flow_hdr(hdr, tclass, ip6_make_flowlabel(net, skb, fl6->flowlabel,
-                                                    np->autoflowlabel, fl6));
+                               ip6_autoflowlabel(net, np), fl6));
 
        hdr->payload_len = htons(seg_len);
        hdr->nexthdr = proto;
@@ -1626,7 +1634,7 @@ struct sk_buff *__ip6_make_skb(struct sock *sk,
 
        ip6_flow_hdr(hdr, v6_cork->tclass,
                     ip6_make_flowlabel(net, skb, fl6->flowlabel,
-                                       np->autoflowlabel, fl6));
+                                       ip6_autoflowlabel(net, np), fl6));
        hdr->hop_limit = v6_cork->hop_limit;
        hdr->nexthdr = proto;
        hdr->saddr = fl6->saddr;

diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index b9404feabd7857fe0873fbc4f346d281f3600807..2d4680e0376f41deee6c999eadaf9409353e0b4a 100644 (file)
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -886,6 +886,7 @@ pref_skip_coa:
                break;
        case IPV6_AUTOFLOWLABEL:
                np->autoflowlabel = valbool;
+               np->autoflowlabel_set = 1;
                retv = 0;
                break;
        case IPV6_RECVFRAGSIZE: