| Message ID | 4BAA4F3F.70703@openvz.org |
|---|---|
| State | Superseded, archived |
| Delegated to: | David Miller |
| Headers | show |
On Wed, Mar 24, 2010 at 08:43:27PM +0300, Pavel Emelyanov wrote: > The the rebuild changes the genid which in turn is used at the > hash calculation. Thus if we don't restart and go on with the > inserting the rt will happen in wrong chain. > > This doesn't seem critical to me, since the proper rt entry will > be hashed at next skb. > > Signed-off-by: Pavel Emelyanov <xemul@openvz.org> > --- > net/ipv4/route.c | 18 ++++++++++++------ > 1 files changed, 12 insertions(+), 6 deletions(-) > > diff --git a/net/ipv4/route.c b/net/ipv4/route.c > index 28c1c2f..bbce53e 100644 > --- a/net/ipv4/route.c > +++ b/net/ipv4/route.c > @@ -1097,7 +1097,7 @@ static int slow_chain_length(const struct rtable *head) > } > > static int rt_intern_hash(unsigned hash, struct rtable *rt, > - struct rtable **rp, struct sk_buff *skb) > + struct rtable **rp, struct sk_buff *skb, int in) > { > struct rtable *rth, **rthp; > unsigned long now; > @@ -1217,6 +1217,12 @@ restart: > rt->u.dst.dev->name, num); > } > rt_emergency_hash_rebuild(net); > + spin_unlock_bh(rt_hash_lock_addr(hash)); > + > + hash = rt_hash(rt->fl.fl4_dst, rt->fl.fl4_src, > + in ? rt->fl.iif : rt->fl.oif, > + rt_genid(net)); > + goto restart; > } > } Why pass in a flag here? Perhaps it would be easier just to pass in the ifindex that was origionally used by the caller of rt_intern_hash so that the hash could be redone without needing to toggle on the value of the flag. Regards Neil > -- To unsubscribe from this list: send the line "unsubscribe netdev" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
>> @@ -1217,6 +1217,12 @@ restart: >> rt->u.dst.dev->name, num); >> } >> rt_emergency_hash_rebuild(net); >> + spin_unlock_bh(rt_hash_lock_addr(hash)); >> + >> + hash = rt_hash(rt->fl.fl4_dst, rt->fl.fl4_src, >> + in ? rt->fl.iif : rt->fl.oif, >> + rt_genid(net)); >> + goto restart; >> } >> } > Why pass in a flag here? Perhaps it would be easier just to pass in the ifindex > that was origionally used by the caller of rt_intern_hash so that the hash could > be redone without needing to toggle on the value of the flag. That's perfectly fine with me. I'll resend the patch shortly. > Regards > Neil > >> > -- To unsubscribe from this list: send the line "unsubscribe netdev" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 28c1c2f..bbce53e 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1097,7 +1097,7 @@ static int slow_chain_length(const struct rtable *head) } static int rt_intern_hash(unsigned hash, struct rtable *rt, - struct rtable **rp, struct sk_buff *skb) + struct rtable **rp, struct sk_buff *skb, int in) { struct rtable *rth, **rthp; unsigned long now; @@ -1217,6 +1217,12 @@ restart: rt->u.dst.dev->name, num); } rt_emergency_hash_rebuild(net); + spin_unlock_bh(rt_hash_lock_addr(hash)); + + hash = rt_hash(rt->fl.fl4_dst, rt->fl.fl4_src, + in ? rt->fl.iif : rt->fl.oif, + rt_genid(net)); + goto restart; } } @@ -1477,7 +1483,7 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw, &netevent); rt_del(hash, rth); - if (!rt_intern_hash(hash, rt, &rt, NULL)) + if (!rt_intern_hash(hash, rt, &rt, NULL, 0)) ip_rt_put(rt); goto do_next; } @@ -1930,7 +1936,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, in_dev_put(in_dev); hash = rt_hash(daddr, saddr, dev->ifindex, rt_genid(dev_net(dev))); - return rt_intern_hash(hash, rth, NULL, skb); + return rt_intern_hash(hash, rth, NULL, skb, 1); e_nobufs: in_dev_put(in_dev); @@ -2097,7 +2103,7 @@ static int ip_mkroute_input(struct sk_buff *skb, /* put it into the cache */ hash = rt_hash(daddr, saddr, fl->iif, rt_genid(dev_net(rth->u.dst.dev))); - return rt_intern_hash(hash, rth, NULL, skb); + return rt_intern_hash(hash, rth, NULL, skb, 1); } /* @@ -2254,7 +2260,7 @@ local_input: } rth->rt_type = res.type; hash = rt_hash(daddr, saddr, fl.iif, rt_genid(net)); - err = rt_intern_hash(hash, rth, NULL, skb); + err = rt_intern_hash(hash, rth, NULL, skb, 1); goto done; no_route: @@ -2501,7 +2507,7 @@ static int ip_mkroute_output(struct rtable **rp, if (err == 0) { hash = rt_hash(oldflp->fl4_dst, oldflp->fl4_src, oldflp->oif, rt_genid(dev_net(dev_out))); - err = rt_intern_hash(hash, rth, rp, NULL); + err = rt_intern_hash(hash, rth, rp, NULL, 0); } return err;
The the rebuild changes the genid which in turn is used at the hash calculation. Thus if we don't restart and go on with the inserting the rt will happen in wrong chain. This doesn't seem critical to me, since the proper rt entry will be hashed at next skb. Signed-off-by: Pavel Emelyanov <xemul@openvz.org> --- net/ipv4/route.c | 18 ++++++++++++------ 1 files changed, 12 insertions(+), 6 deletions(-) -- To unsubscribe from this list: send the line "unsubscribe netdev" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html