[PATCH net-next 0/7] ipv6: addrconf: hash improvements and cleanups

[PATCH net-next 0/7] ipv6: addrconf: hash improvements and cleanups

[Eric Dumazet]

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

Eric Dumazet (7):
  ipv6: addrconf: move ipv6_chk_same_addr() to avoid forward declaration
  ipv6: addrconf: factorize inet6_addr_hash() call
  ipv6: addrconf: add per netns perturbation in inet6_addr_hash()
  ipv6: addrconf: do not block BH in ipv6_chk_addr_and_flags()
  ipv6: addrconf: do not block BH in ipv6_get_ifaddr()
  ipv6: addrconf: do not block BH in /proc/net/if_inet6 handling
  ipv6: addrconf: do not block BH in ipv6_chk_home_addr()

 include/net/addrconf.h |  2 +-
 net/ipv6/addrconf.c    | 94 ++++++++++++++++++++++++--------------------------
 2 files changed, 46 insertions(+), 50 deletions(-)

-- 
2.15.0.rc0.271.g36b669edcc-goog

[PATCH net-next 1/7] ipv6: addrconf: move ipv6_chk_same_addr() to avoid forward declaration

[Eric Dumazet]

ipv6_chk_same_addr() is only used by ipv6_add_addr_hash(),
so moving it avoids a forward declaration.

Signed-off-by: Eric Dumazet <edumazet@google.com>
---
 net/ipv6/addrconf.c | 35 +++++++++++++++++------------------
 1 file changed, 17 insertions(+), 18 deletions(-)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 93f9c0a619119f0520363206fbdc1aae49fbb1e6..9228030e34970c1d6380e95e8c193496448ea8ac 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,
@@ -957,6 +955,23 @@ static u32 inet6_addr_hash(const struct in6_addr *addr)
 	return hash_32(ipv6_addr_hash(addr), 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 = 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;
+}
+
 static int ipv6_add_addr_hash(struct net_device *dev, struct inet6_ifaddr *ifa)
 {
 	unsigned int hash;
@@ -1856,22 +1871,6 @@ int ipv6_chk_addr_and_flags(struct net *net, const struct in6_addr *addr,
 }
 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.
-- 
2.15.0.rc0.271.g36b669edcc-goog

[PATCH net-next 2/7] ipv6: addrconf: factorize inet6_addr_hash() call

[Eric Dumazet]

ipv6_add_addr_hash() can compute the hash value outside of
locked section and pass it to ipv6_chk_same_addr().

Signed-off-by: Eric Dumazet <edumazet@google.com>
---
 net/ipv6/addrconf.c | 15 +++++----------
 1 file changed, 5 insertions(+), 10 deletions(-)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 9228030e34970c1d6380e95e8c193496448ea8ac..c1a5028f394c75d347fe703573548fd617b5c142 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -956,9 +956,8 @@ static u32 inet6_addr_hash(const struct in6_addr *addr)
 }
 
 static bool ipv6_chk_same_addr(struct net *net, const struct in6_addr *addr,
-			       struct net_device *dev)
+			       struct net_device *dev, unsigned int hash)
 {
-	unsigned int hash = inet6_addr_hash(addr);
 	struct inet6_ifaddr *ifp;
 
 	hlist_for_each_entry(ifp, &inet6_addr_lst[hash], addr_lst) {
@@ -974,23 +973,19 @@ static bool ipv6_chk_same_addr(struct net *net, const struct in6_addr *addr,
 
 static int ipv6_add_addr_hash(struct net_device *dev, struct inet6_ifaddr *ifa)
 {
-	unsigned int hash;
+	unsigned int hash = inet6_addr_hash(&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;
-- 
2.15.0.rc0.271.g36b669edcc-goog

[PATCH net-next 3/7] ipv6: addrconf: add per netns perturbation in inet6_addr_hash()

[Eric Dumazet]

Bring IPv6 in par with IPv4 :

- Use net_hash_mix() to spread addresses a bit more.
- Use 256 slots hash table instead of 16

Signed-off-by: Eric Dumazet <edumazet@google.com>
---
 include/net/addrconf.h |  2 +-
 net/ipv6/addrconf.c    | 16 +++++++++-------
 2 files changed, 10 insertions(+), 8 deletions(-)

diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index b8b16437c6d5bcb9c8b5c42b4f9c0161b477d605..15b5ffd7253d6088f2444ada5de99e4977e143ff 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 c1a5028f394c75d347fe703573548fd617b5c142..d70d98122053652b4f4420786de8788c6c9385ff 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -950,9 +950,11 @@ 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,
@@ -973,7 +975,7 @@ static bool ipv6_chk_same_addr(struct net *net, const struct in6_addr *addr,
 
 static int ipv6_add_addr_hash(struct net_device *dev, struct inet6_ifaddr *ifa)
 {
-	unsigned int hash = inet6_addr_hash(&ifa->addr);
+	unsigned int hash = inet6_addr_hash(dev_net(dev), &ifa->addr);
 	int err = 0;
 
 	spin_lock(&addrconf_hash_lock);
@@ -1838,8 +1840,8 @@ 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();
@@ -1917,8 +1919,8 @@ 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) {
@@ -4242,9 +4244,9 @@ 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) {
-- 
2.15.0.rc0.271.g36b669edcc-goog

[PATCH net-next 4/7] ipv6: addrconf: do not block BH in ipv6_chk_addr_and_flags()

[Eric Dumazet]

rcu_read_lock() is enough here, as inet6_ifa_finish_destroy()
uses kfree_rcu()

Signed-off-by: Eric Dumazet <edumazet@google.com>
---
 net/ipv6/addrconf.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index d70d98122053652b4f4420786de8788c6c9385ff..a6cf37b7e34c461e204153078be92c3e297b3ec2 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -1844,7 +1844,7 @@ int ipv6_chk_addr_and_flags(struct net *net, const struct in6_addr *addr,
 	struct inet6_ifaddr *ifp;
 	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;
@@ -1858,12 +1858,12 @@ 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);
-- 
2.15.0.rc0.271.g36b669edcc-goog

[PATCH net-next 5/7] ipv6: addrconf: do not block BH in ipv6_get_ifaddr()

[Eric Dumazet]

rcu_read_lock() is enough here, no need to block BH.

Signed-off-by: Eric Dumazet <edumazet@google.com>
---
 net/ipv6/addrconf.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index a6cf37b7e34c461e204153078be92c3e297b3ec2..6c1e7ffb62ff2333d63b3c7639d99649d43b32fc 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -1922,8 +1922,8 @@ struct inet6_ifaddr *ipv6_get_ifaddr(struct net *net, const struct in6_addr *add
 	unsigned int hash = inet6_addr_hash(net, addr);
 	struct inet6_ifaddr *ifp, *result = NULL;
 
-	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)) {
@@ -1935,7 +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;
 }
-- 
2.15.0.rc0.271.g36b669edcc-goog

[PATCH net-next 6/7] ipv6: addrconf: do not block BH in /proc/net/if_inet6 handling

[Eric Dumazet]

Table is really RCU protected, no need to block BH

Signed-off-by: Eric Dumazet <edumazet@google.com>
---
 net/ipv6/addrconf.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 6c1e7ffb62ff2333d63b3c7639d99649d43b32fc..9232e9537082ea44f5e0af4e4b0d052d780395fd 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -4097,9 +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 */
@@ -4109,7 +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;
@@ -4135,7 +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++;
@@ -4144,7 +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;
@@ -4157,9 +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);
 }
 
@@ -4173,9 +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)
-- 
2.15.0.rc0.271.g36b669edcc-goog

[PATCH net-next 7/7] ipv6: addrconf: do not block BH in ipv6_chk_home_addr()

[Eric Dumazet]

rcu_read_lock() is enough here, no need to block BH.

Signed-off-by: Eric Dumazet <edumazet@google.com>
---
 net/ipv6/addrconf.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 9232e9537082ea44f5e0af4e4b0d052d780395fd..5a8a10229a07fe3d3f96b237e744332c192a509f 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -4248,8 +4248,8 @@ int ipv6_chk_home_addr(struct net *net, const struct in6_addr *addr)
 	struct inet6_ifaddr *ifp = NULL;
 	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) &&
@@ -4258,7 +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
-- 
2.15.0.rc0.271.g36b669edcc-goog

Re: [PATCH net-next 0/7] ipv6: addrconf: hash improvements and cleanups

[David Miller]

From: Eric Dumazet <edumazet@google.com>
Date: Mon, 23 Oct 2017 16:17:44 -0700

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

Series applied.