Merge branch 'ipv6-addrconf-hash-improvements-and-cleanups'

Eric Dumazet says:

====================
ipv6: addrconf: hash improvements and cleanups

Remove unecessary BH blocking, and bring IPv6 addrconf to modern world,
with per netns hash perturbation and decent hash size.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 46 insertions, 50 deletions

diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index b8b16437c6d5..15b5ffd7253d 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -58,7 +58,7 @@ struct in6_validator_info {
 	struct netlink_ext_ack	*extack;
 };
 
-#define IN6_ADDR_HSIZE_SHIFT	4
+#define IN6_ADDR_HSIZE_SHIFT	8
 #define IN6_ADDR_HSIZE		(1 << IN6_ADDR_HSIZE_SHIFT)
 
 int addrconf_init(void);
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 93f9c0a61911..5a8a10229a07 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -192,8 +192,6 @@ static void ipv6_ifa_notify(int event, struct inet6_ifaddr *ifa);
 
 static void inet6_prefix_notify(int event, struct inet6_dev *idev,
 				struct prefix_info *pinfo);
-static bool ipv6_chk_same_addr(struct net *net, const struct in6_addr *addr,
-			       struct net_device *dev);
 
 static struct ipv6_devconf ipv6_devconf __read_mostly = {
 	.forwarding		= 0,
@@ -952,30 +950,44 @@ ipv6_link_dev_addr(struct inet6_dev *idev, struct inet6_ifaddr *ifp)
 	list_add_tail_rcu(&ifp->if_list, p);
 }
 
-static u32 inet6_addr_hash(const struct in6_addr *addr)
+static u32 inet6_addr_hash(const struct net *net, const struct in6_addr *addr)
 {
-	return hash_32(ipv6_addr_hash(addr), IN6_ADDR_HSIZE_SHIFT);
+	u32 val = ipv6_addr_hash(addr) ^ net_hash_mix(net);
+
+	return hash_32(val, IN6_ADDR_HSIZE_SHIFT);
+}
+
+static bool ipv6_chk_same_addr(struct net *net, const struct in6_addr *addr,
+			       struct net_device *dev, unsigned int hash)
+{
+	struct inet6_ifaddr *ifp;
+
+	hlist_for_each_entry(ifp, &inet6_addr_lst[hash], addr_lst) {
+		if (!net_eq(dev_net(ifp->idev->dev), net))
+			continue;
+		if (ipv6_addr_equal(&ifp->addr, addr)) {
+			if (!dev || ifp->idev->dev == dev)
+				return true;
+		}
+	}
+	return false;
 }
 
 static int ipv6_add_addr_hash(struct net_device *dev, struct inet6_ifaddr *ifa)
 {
-	unsigned int hash;
+	unsigned int hash = inet6_addr_hash(dev_net(dev), &ifa->addr);
 	int err = 0;
 
 	spin_lock(&addrconf_hash_lock);
 
 	/* Ignore adding duplicate addresses on an interface */
-	if (ipv6_chk_same_addr(dev_net(dev), &ifa->addr, dev)) {
+	if (ipv6_chk_same_addr(dev_net(dev), &ifa->addr, dev, hash)) {
 		ADBG("ipv6_add_addr: already assigned\n");
 		err = -EEXIST;
-		goto out;
+	} else {
+		hlist_add_head_rcu(&ifa->addr_lst, &inet6_addr_lst[hash]);
 	}
 
-	/* Add to big hash table */
-	hash = inet6_addr_hash(&ifa->addr);
-	hlist_add_head_rcu(&ifa->addr_lst, &inet6_addr_lst[hash]);
-
-out:
 	spin_unlock(&addrconf_hash_lock);
 
 	return err;
@@ -1828,11 +1840,11 @@ int ipv6_chk_addr_and_flags(struct net *net, const struct in6_addr *addr,
 			    const struct net_device *dev, int strict,
 			    u32 banned_flags)
 {
+	unsigned int hash = inet6_addr_hash(net, addr);
 	struct inet6_ifaddr *ifp;
-	unsigned int hash = inet6_addr_hash(addr);
 	u32 ifp_flags;
 
-	rcu_read_lock_bh();
+	rcu_read_lock();
 	hlist_for_each_entry_rcu(ifp, &inet6_addr_lst[hash], addr_lst) {
 		if (!net_eq(dev_net(ifp->idev->dev), net))
 			continue;
@@ -1846,32 +1858,16 @@ int ipv6_chk_addr_and_flags(struct net *net, const struct in6_addr *addr,
 		    !(ifp_flags&banned_flags) &&
 		    (!dev || ifp->idev->dev == dev ||
 		     !(ifp->scope&(IFA_LINK|IFA_HOST) || strict))) {
-			rcu_read_unlock_bh();
+			rcu_read_unlock();
 			return 1;
 		}
 	}
 
-	rcu_read_unlock_bh();
+	rcu_read_unlock();
 	return 0;
 }
 EXPORT_SYMBOL(ipv6_chk_addr_and_flags);
 
-static bool ipv6_chk_same_addr(struct net *net, const struct in6_addr *addr,
-			       struct net_device *dev)
-{
-	unsigned int hash = inet6_addr_hash(addr);
-	struct inet6_ifaddr *ifp;
-
-	hlist_for_each_entry(ifp, &inet6_addr_lst[hash], addr_lst) {
-		if (!net_eq(dev_net(ifp->idev->dev), net))
-			continue;
-		if (ipv6_addr_equal(&ifp->addr, addr)) {
-			if (!dev || ifp->idev->dev == dev)
-				return true;
-		}
-	}
-	return false;
-}
 
 /* Compares an address/prefix_len with addresses on device @dev.
  * If one is found it returns true.
@@ -1923,11 +1919,11 @@ EXPORT_SYMBOL(ipv6_chk_prefix);
 struct inet6_ifaddr *ipv6_get_ifaddr(struct net *net, const struct in6_addr *addr,
 				     struct net_device *dev, int strict)
 {
+	unsigned int hash = inet6_addr_hash(net, addr);
 	struct inet6_ifaddr *ifp, *result = NULL;
-	unsigned int hash = inet6_addr_hash(addr);
 
-	rcu_read_lock_bh();
-	hlist_for_each_entry_rcu_bh(ifp, &inet6_addr_lst[hash], addr_lst) {
+	rcu_read_lock();
+	hlist_for_each_entry_rcu(ifp, &inet6_addr_lst[hash], addr_lst) {
 		if (!net_eq(dev_net(ifp->idev->dev), net))
 			continue;
 		if (ipv6_addr_equal(&ifp->addr, addr)) {
@@ -1939,7 +1935,7 @@ struct inet6_ifaddr *ipv6_get_ifaddr(struct net *net, const struct in6_addr *add
 			}
 		}
 	}
-	rcu_read_unlock_bh();
+	rcu_read_unlock();
 
 	return result;
 }
@@ -4101,9 +4097,9 @@ struct if6_iter_state {
 
 static struct inet6_ifaddr *if6_get_first(struct seq_file *seq, loff_t pos)
 {
-	struct inet6_ifaddr *ifa = NULL;
 	struct if6_iter_state *state = seq->private;
 	struct net *net = seq_file_net(seq);
+	struct inet6_ifaddr *ifa = NULL;
 	int p = 0;
 
 	/* initial bucket if pos is 0 */
@@ -4113,7 +4109,7 @@ static struct inet6_ifaddr *if6_get_first(struct seq_file *seq, loff_t pos)
 	}
 
 	for (; state->bucket < IN6_ADDR_HSIZE; ++state->bucket) {
-		hlist_for_each_entry_rcu_bh(ifa, &inet6_addr_lst[state->bucket],
+		hlist_for_each_entry_rcu(ifa, &inet6_addr_lst[state->bucket],
 					 addr_lst) {
 			if (!net_eq(dev_net(ifa->idev->dev), net))
 				continue;
@@ -4139,7 +4135,7 @@ static struct inet6_ifaddr *if6_get_next(struct seq_file *seq,
 	struct if6_iter_state *state = seq->private;
 	struct net *net = seq_file_net(seq);
 
-	hlist_for_each_entry_continue_rcu_bh(ifa, addr_lst) {
+	hlist_for_each_entry_continue_rcu(ifa, addr_lst) {
 		if (!net_eq(dev_net(ifa->idev->dev), net))
 			continue;
 		state->offset++;
@@ -4148,7 +4144,7 @@ static struct inet6_ifaddr *if6_get_next(struct seq_file *seq,
 
 	while (++state->bucket < IN6_ADDR_HSIZE) {
 		state->offset = 0;
-		hlist_for_each_entry_rcu_bh(ifa,
+		hlist_for_each_entry_rcu(ifa,
 				     &inet6_addr_lst[state->bucket], addr_lst) {
 			if (!net_eq(dev_net(ifa->idev->dev), net))
 				continue;
@@ -4161,9 +4157,9 @@ static struct inet6_ifaddr *if6_get_next(struct seq_file *seq,
 }
 
 static void *if6_seq_start(struct seq_file *seq, loff_t *pos)
-	__acquires(rcu_bh)
+	__acquires(rcu)
 {
-	rcu_read_lock_bh();
+	rcu_read_lock();
 	return if6_get_first(seq, *pos);
 }
 
@@ -4177,9 +4173,9 @@ static void *if6_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 }
 
 static void if6_seq_stop(struct seq_file *seq, void *v)
-	__releases(rcu_bh)
+	__releases(rcu)
 {
-	rcu_read_unlock_bh();
+	rcu_read_unlock();
 }
 
 static int if6_seq_show(struct seq_file *seq, void *v)
@@ -4248,12 +4244,12 @@ void if6_proc_exit(void)
 /* Check if address is a home address configured on any interface. */
 int ipv6_chk_home_addr(struct net *net, const struct in6_addr *addr)
 {
-	int ret = 0;
+	unsigned int hash = inet6_addr_hash(net, addr);
 	struct inet6_ifaddr *ifp = NULL;
-	unsigned int hash = inet6_addr_hash(addr);
+	int ret = 0;
 
-	rcu_read_lock_bh();
-	hlist_for_each_entry_rcu_bh(ifp, &inet6_addr_lst[hash], addr_lst) {
+	rcu_read_lock();
+	hlist_for_each_entry_rcu(ifp, &inet6_addr_lst[hash], addr_lst) {
 		if (!net_eq(dev_net(ifp->idev->dev), net))
 			continue;
 		if (ipv6_addr_equal(&ifp->addr, addr) &&
@@ -4262,7 +4258,7 @@ int ipv6_chk_home_addr(struct net *net, const struct in6_addr *addr)
 			break;
 		}
 	}
-	rcu_read_unlock_bh();
+	rcu_read_unlock();
 	return ret;
 }
 #endif