Revert "ipv4: L3 hash-based multipath"

This reverts commit 0e884c78ee19e902f300ed147083c28a0c6302f0.

3 files changed, 72 insertions, 98 deletions

diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index 7a51fd8d99e4..727d6e9a9685 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -79,7 +79,7 @@ struct fib_nh {
 	unsigned char		nh_scope;
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 	int			nh_weight;
-	atomic_t		nh_upper_bound;
+	int			nh_power;
 #endif
 #ifdef CONFIG_IP_ROUTE_CLASSID
 	__u32			nh_tclassid;
@@ -118,7 +118,7 @@ struct fib_info {
 #define fib_advmss fib_metrics[RTAX_ADVMSS-1]
 	int			fib_nhs;
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
-	int			fib_weight;
+	int			fib_power;
 #endif
 	struct rcu_head		rcu;
 	struct fib_nh		fib_nh[0];
@@ -320,15 +320,7 @@ int ip_fib_check_default(__be32 gw, struct net_device *dev);
 int fib_sync_down_dev(struct net_device *dev, unsigned long event);
 int fib_sync_down_addr(struct net *net, __be32 local);
 int fib_sync_up(struct net_device *dev, unsigned int nh_flags);
-
-extern u32 fib_multipath_secret __read_mostly;
-
-static inline int fib_multipath_hash(__be32 saddr, __be32 daddr)
-{
-	return jhash_2words(saddr, daddr, fib_multipath_secret) >> 1;
-}
-
-void fib_select_multipath(struct fib_result *res, int hash);
+void fib_select_multipath(struct fib_result *res);
 
 /* Exported by fib_trie.c */
 void fib_trie_init(void);
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 0c49d2f3bbc0..064bd3caaa4f 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -57,7 +57,8 @@ static unsigned int fib_info_cnt;
 static struct hlist_head fib_info_devhash[DEVINDEX_HASHSIZE];
 
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
-u32 fib_multipath_secret __read_mostly;
+
+static DEFINE_SPINLOCK(fib_multipath_lock);
 
 #define for_nexthops(fi) {						\
 	int nhsel; const struct fib_nh *nh;				\
@@ -531,67 +532,7 @@ errout:
 	return ret;
 }
 
-static void fib_rebalance(struct fib_info *fi)
-{
-	int total;
-	int w;
-	struct in_device *in_dev;
-
-	if (fi->fib_nhs < 2)
-		return;
-
-	total = 0;
-	for_nexthops(fi) {
-		if (nh->nh_flags & RTNH_F_DEAD)
-			continue;
-
-		in_dev = __in_dev_get_rcu(nh->nh_dev);
-
-		if (in_dev &&
-		    IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) &&
-		    nh->nh_flags & RTNH_F_LINKDOWN)
-			continue;
-
-		total += nh->nh_weight;
-	} endfor_nexthops(fi);
-
-	w = 0;
-	change_nexthops(fi) {
-		int upper_bound;
-
-		in_dev = __in_dev_get_rcu(nexthop_nh->nh_dev);
-
-		if (nexthop_nh->nh_flags & RTNH_F_DEAD) {
-			upper_bound = -1;
-		} else if (in_dev &&
-			   IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) &&
-			   nexthop_nh->nh_flags & RTNH_F_LINKDOWN) {
-			upper_bound = -1;
-		} else {
-			w += nexthop_nh->nh_weight;
-			upper_bound = DIV_ROUND_CLOSEST(2147483648LL * w,
-							total) - 1;
-		}
-
-		atomic_set(&nexthop_nh->nh_upper_bound, upper_bound);
-	} endfor_nexthops(fi);
-
-	net_get_random_once(&fib_multipath_secret,
-			    sizeof(fib_multipath_secret));
-}
-
-static inline void fib_add_weight(struct fib_info *fi,
-				  const struct fib_nh *nh)
-{
-	fi->fib_weight += nh->nh_weight;
-}
-
-#else /* CONFIG_IP_ROUTE_MULTIPATH */
-
-#define fib_rebalance(fi) do { } while (0)
-#define fib_add_weight(fi, nh) do { } while (0)
-
-#endif /* CONFIG_IP_ROUTE_MULTIPATH */
+#endif
 
 static int fib_encap_match(struct net *net, u16 encap_type,
 			   struct nlattr *encap,
@@ -1153,11 +1094,8 @@ struct fib_info *fib_create_info(struct fib_config *cfg)
 
 	change_nexthops(fi) {
 		fib_info_update_nh_saddr(net, nexthop_nh);
-		fib_add_weight(fi, nexthop_nh);
 	} endfor_nexthops(fi)
 
-	fib_rebalance(fi);
-
 link_it:
 	ofi = fib_find_info(fi);
 	if (ofi) {
@@ -1379,6 +1317,12 @@ int fib_sync_down_dev(struct net_device *dev, unsigned long event)
 					nexthop_nh->nh_flags |= RTNH_F_LINKDOWN;
 					break;
 				}
+#ifdef CONFIG_IP_ROUTE_MULTIPATH
+				spin_lock_bh(&fib_multipath_lock);
+				fi->fib_power -= nexthop_nh->nh_power;
+				nexthop_nh->nh_power = 0;
+				spin_unlock_bh(&fib_multipath_lock);
+#endif
 				dead++;
 			}
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
@@ -1401,8 +1345,6 @@ int fib_sync_down_dev(struct net_device *dev, unsigned long event)
 			}
 			ret++;
 		}
-
-		fib_rebalance(fi);
 	}
 
 	return ret;
@@ -1525,15 +1467,20 @@ int fib_sync_up(struct net_device *dev, unsigned int nh_flags)
 			    !__in_dev_get_rtnl(dev))
 				continue;
 			alive++;
+#ifdef CONFIG_IP_ROUTE_MULTIPATH
+			spin_lock_bh(&fib_multipath_lock);
+			nexthop_nh->nh_power = 0;
+			nexthop_nh->nh_flags &= ~nh_flags;
+			spin_unlock_bh(&fib_multipath_lock);
+#else
 			nexthop_nh->nh_flags &= ~nh_flags;
+#endif
 		} endfor_nexthops(fi)
 
 		if (alive > 0) {
 			fi->fib_flags &= ~nh_flags;
 			ret++;
 		}
-
-		fib_rebalance(fi);
 	}
 
 	return ret;
@@ -1541,19 +1488,62 @@ int fib_sync_up(struct net_device *dev, unsigned int nh_flags)
 
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 
-void fib_select_multipath(struct fib_result *res, int hash)
+/*
+ * The algorithm is suboptimal, but it provides really
+ * fair weighted route distribution.
+ */
+void fib_select_multipath(struct fib_result *res)
 {
 	struct fib_info *fi = res->fi;
+	struct in_device *in_dev;
+	int w;
 
-	for_nexthops(fi) {
-		if (hash > atomic_read(&nh->nh_upper_bound))
-			continue;
+	spin_lock_bh(&fib_multipath_lock);
+	if (fi->fib_power <= 0) {
+		int power = 0;
+		change_nexthops(fi) {
+			in_dev = __in_dev_get_rcu(nexthop_nh->nh_dev);
+			if (nexthop_nh->nh_flags & RTNH_F_DEAD)
+				continue;
+			if (in_dev &&
+			    IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) &&
+			    nexthop_nh->nh_flags & RTNH_F_LINKDOWN)
+				continue;
+			power += nexthop_nh->nh_weight;
+			nexthop_nh->nh_power = nexthop_nh->nh_weight;
+		} endfor_nexthops(fi);
+		fi->fib_power = power;
+		if (power <= 0) {
+			spin_unlock_bh(&fib_multipath_lock);
+			/* Race condition: route has just become dead. */
+			res->nh_sel = 0;
+			return;
+		}
+	}
 
-		res->nh_sel = nhsel;
-		return;
+
+	/* w should be random number [0..fi->fib_power-1],
+	 * it is pretty bad approximation.
+	 */
+
+	w = jiffies % fi->fib_power;
+
+	change_nexthops(fi) {
+		if (!(nexthop_nh->nh_flags & RTNH_F_DEAD) &&
+		    nexthop_nh->nh_power) {
+			w -= nexthop_nh->nh_power;
+			if (w <= 0) {
+				nexthop_nh->nh_power--;
+				fi->fib_power--;
+				res->nh_sel = nhsel;
+				spin_unlock_bh(&fib_multipath_lock);
+				return;
+			}
+		}
 	} endfor_nexthops(fi);
 
 	/* Race condition: route has just become dead. */
 	res->nh_sel = 0;
+	spin_unlock_bh(&fib_multipath_lock);
 }
 #endif
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 0cca44476b1e..76ca4e75f785 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1658,12 +1658,8 @@ static int ip_mkroute_input(struct sk_buff *skb,
 			    __be32 daddr, __be32 saddr, u32 tos)
 {
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
-	if (res->fi && res->fi->fib_nhs > 1) {
-		int h;
-
-		h = fib_multipath_hash(saddr, daddr);
-		fib_select_multipath(res, h);
-	}
+	if (res->fi && res->fi->fib_nhs > 1)
+		fib_select_multipath(res);
 #endif
 
 	/* create a routing cache entry */
@@ -2193,12 +2189,8 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4)
 	}
 
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
-	if (res.fi->fib_nhs > 1 && fl4->flowi4_oif == 0) {
-		int h;
-
-		h = fib_multipath_hash(fl4->saddr, fl4->daddr);
-		fib_select_multipath(&res, h);
-	}
+	if (res.fi->fib_nhs > 1 && fl4->flowi4_oif == 0)
+		fib_select_multipath(&res);
 	else
 #endif
 	if (!res.prefixlen &&