diff mbox series

[net-next,03/11] ipv6/addrconf: switch to per netns inet6_addr_lst hash table

Message ID 20220207171756.1304544-4-eric.dumazet@gmail.com (mailing list archive)
State Superseded
Delegated to: Netdev Maintainers
Headers show
Series net: speedup netns dismantles | expand

Checks

Context Check Description
netdev/tree_selection success Clearly marked for net-next
netdev/fixes_present success Fixes tag not required for -next series
netdev/subject_prefix success Link
netdev/cover_letter success Series has a cover letter
netdev/patch_count success Link
netdev/header_inline success No static functions without inline keyword in header files
netdev/build_32bit success Errors and warnings before: 0 this patch: 0
netdev/cc_maintainers warning 1 maintainers not CCed: yoshfuji@linux-ipv6.org
netdev/build_clang success Errors and warnings before: 0 this patch: 0
netdev/module_param success Was 0 now: 0
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/verify_fixes success No Fixes tag
netdev/build_allmodconfig_warn success Errors and warnings before: 0 this patch: 0
netdev/checkpatch warning WARNING: line length of 82 exceeds 80 columns WARNING: line length of 84 exceeds 80 columns WARNING: line length of 87 exceeds 80 columns WARNING: line length of 90 exceeds 80 columns
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/source_inline success Was 0 now: 0

Commit Message

Eric Dumazet Feb. 7, 2022, 5:17 p.m. UTC 
From: Eric Dumazet <edumazet@google.com>

IPv6 does not scale very well with the number of IPv6 addresses.
It uses a global (shared by all netns) hash table with 256 buckets.

Some functions like addrconf_verify_rtnl() and addrconf_ifdown()
have to iterate all addresses in the hash table.

I have seen addrconf_verify_rtnl() holding the cpu for 10ms or more.

Switch to the per netns hashtable (and spinlock) added
in prior patches.

This considerably speeds up netns dismantle times on hosts
with thousands of netns.

Signed-off-by: Eric Dumazet <edumazet@google.com>
---
 net/ipv6/addrconf.c | 77 ++++++++++++++-------------------------------
 1 file changed, 23 insertions(+), 54 deletions(-)

Comments

David Ahern Feb. 8, 2022, 4:12 a.m. UTC | #1 
On 2/7/22 9:17 AM, Eric Dumazet wrote:
> From: Eric Dumazet <edumazet@google.com>
> 
> IPv6 does not scale very well with the number of IPv6 addresses.
> It uses a global (shared by all netns) hash table with 256 buckets.
> 
> Some functions like addrconf_verify_rtnl() and addrconf_ifdown()
> have to iterate all addresses in the hash table.
> 
> I have seen addrconf_verify_rtnl() holding the cpu for 10ms or more.
> 
> Switch to the per netns hashtable (and spinlock) added
> in prior patches.
> 
> This considerably speeds up netns dismantle times on hosts
> with thousands of netns.

this has to speed up many aspects of ipv6 addresses, not just the teardown.

> 
> Signed-off-by: Eric Dumazet <edumazet@google.com>
> ---
>  net/ipv6/addrconf.c | 77 ++++++++++++++-------------------------------
>  1 file changed, 23 insertions(+), 54 deletions(-)
> 

Reviewed-by: David Ahern <dsahern@kernel.org>
diff mbox series

Patch

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index dab291cd39ba20c8dad29854297e8699c067b1e7..4f402bc38f056e08f3761e63a7bc7a51e54e9384 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -146,11 +146,6 @@  static int ipv6_generate_stable_address(struct in6_addr *addr,
 
 #define IN6_ADDR_HSIZE_SHIFT	8
 #define IN6_ADDR_HSIZE		(1 << IN6_ADDR_HSIZE_SHIFT)
-/*
- *	Configured unicast address hash table
- */
-static struct hlist_head inet6_addr_lst[IN6_ADDR_HSIZE];
-static DEFINE_SPINLOCK(addrconf_hash_lock);
 
 static void addrconf_verify(struct net *net);
 static void addrconf_verify_rtnl(struct net *net);
@@ -1009,9 +1004,7 @@  static bool ipv6_chk_same_addr(struct net *net, const struct in6_addr *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;
+	hlist_for_each_entry(ifp, &net->ipv6.inet6_addr_lst[hash], addr_lst) {
 		if (ipv6_addr_equal(&ifp->addr, addr)) {
 			if (!dev || ifp->idev->dev == dev)
 				return true;
@@ -1022,20 +1015,21 @@  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(dev_net(dev), &ifa->addr);
+	struct net *net = dev_net(dev);
+	unsigned int hash = inet6_addr_hash(net, &ifa->addr);
 	int err = 0;
 
-	spin_lock(&addrconf_hash_lock);
+	spin_lock(&net->ipv6.addrconf_hash_lock);
 
 	/* Ignore adding duplicate addresses on an interface */
-	if (ipv6_chk_same_addr(dev_net(dev), &ifa->addr, dev, hash)) {
+	if (ipv6_chk_same_addr(net, &ifa->addr, dev, hash)) {
 		netdev_dbg(dev, "ipv6_add_addr: already assigned\n");
 		err = -EEXIST;
 	} else {
-		hlist_add_head_rcu(&ifa->addr_lst, &inet6_addr_lst[hash]);
+		hlist_add_head_rcu(&ifa->addr_lst, &net->ipv6.inet6_addr_lst[hash]);
 	}
 
-	spin_unlock(&addrconf_hash_lock);
+	spin_unlock(&net->ipv6.addrconf_hash_lock);
 
 	return err;
 }
@@ -1259,9 +1253,10 @@  cleanup_prefix_route(struct inet6_ifaddr *ifp, unsigned long expires,
 
 static void ipv6_del_addr(struct inet6_ifaddr *ifp)
 {
-	int state;
 	enum cleanup_prefix_rt_t action = CLEANUP_PREFIX_RT_NOP;
+	struct net *net = dev_net(ifp->idev->dev);
 	unsigned long expires;
+	int state;
 
 	ASSERT_RTNL();
 
@@ -1273,9 +1268,9 @@  static void ipv6_del_addr(struct inet6_ifaddr *ifp)
 	if (state == INET6_IFADDR_STATE_DEAD)
 		goto out;
 
-	spin_lock_bh(&addrconf_hash_lock);
+	spin_lock_bh(&net->ipv6.addrconf_hash_lock);
 	hlist_del_init_rcu(&ifp->addr_lst);
-	spin_unlock_bh(&addrconf_hash_lock);
+	spin_unlock_bh(&net->ipv6.addrconf_hash_lock);
 
 	write_lock_bh(&ifp->idev->lock);
 
@@ -1918,10 +1913,8 @@  __ipv6_chk_addr_and_flags(struct net *net, const struct in6_addr *addr,
 	if (skip_dev_check)
 		dev = NULL;
 
-	hlist_for_each_entry_rcu(ifp, &inet6_addr_lst[hash], addr_lst) {
+	hlist_for_each_entry_rcu(ifp, &net->ipv6.inet6_addr_lst[hash], addr_lst) {
 		ndev = ifp->idev->dev;
-		if (!net_eq(dev_net(ndev), net))
-			continue;
 
 		if (l3mdev_master_dev_rcu(ndev) != l3mdev)
 			continue;
@@ -2025,9 +2018,7 @@  struct inet6_ifaddr *ipv6_get_ifaddr(struct net *net, const struct in6_addr *add
 	struct inet6_ifaddr *ifp, *result = NULL;
 
 	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;
+	hlist_for_each_entry_rcu(ifp, &net->ipv6.inet6_addr_lst[hash], addr_lst) {
 		if (ipv6_addr_equal(&ifp->addr, addr)) {
 			if (!dev || ifp->idev->dev == dev ||
 			    !(ifp->scope&(IFA_LINK|IFA_HOST) || strict)) {
@@ -2094,7 +2085,7 @@  static int addrconf_dad_end(struct inet6_ifaddr *ifp)
 void addrconf_dad_failure(struct sk_buff *skb, struct inet6_ifaddr *ifp)
 {
 	struct inet6_dev *idev = ifp->idev;
-	struct net *net = dev_net(ifp->idev->dev);
+	struct net *net = dev_net(idev->dev);
 
 	if (addrconf_dad_end(ifp)) {
 		in6_ifa_put(ifp);
@@ -3770,9 +3761,9 @@  static int addrconf_ifdown(struct net_device *dev, bool unregister)
 
 	/* Step 2: clear hash table */
 	for (i = 0; i < IN6_ADDR_HSIZE; i++) {
-		struct hlist_head *h = &inet6_addr_lst[i];
+		struct hlist_head *h = &net->ipv6.inet6_addr_lst[i];
 
-		spin_lock_bh(&addrconf_hash_lock);
+		spin_lock_bh(&net->ipv6.addrconf_hash_lock);
 restart:
 		hlist_for_each_entry_rcu(ifa, h, addr_lst) {
 			if (ifa->idev == idev) {
@@ -3788,7 +3779,7 @@  static int addrconf_ifdown(struct net_device *dev, bool unregister)
 				}
 			}
 		}
-		spin_unlock_bh(&addrconf_hash_lock);
+		spin_unlock_bh(&net->ipv6.addrconf_hash_lock);
 	}
 
 	write_lock_bh(&idev->lock);
@@ -4286,10 +4277,8 @@  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(ifa, &inet6_addr_lst[state->bucket],
+		hlist_for_each_entry_rcu(ifa, &net->ipv6.inet6_addr_lst[state->bucket],
 					 addr_lst) {
-			if (!net_eq(dev_net(ifa->idev->dev), net))
-				continue;
 			/* sync with offset */
 			if (p < state->offset) {
 				p++;
@@ -4312,8 +4301,6 @@  static struct inet6_ifaddr *if6_get_next(struct seq_file *seq,
 	struct net *net = seq_file_net(seq);
 
 	hlist_for_each_entry_continue_rcu(ifa, addr_lst) {
-		if (!net_eq(dev_net(ifa->idev->dev), net))
-			continue;
 		state->offset++;
 		return ifa;
 	}
@@ -4321,9 +4308,7 @@  static struct inet6_ifaddr *if6_get_next(struct seq_file *seq,
 	state->offset = 0;
 	while (++state->bucket < IN6_ADDR_HSIZE) {
 		hlist_for_each_entry_rcu(ifa,
-				     &inet6_addr_lst[state->bucket], addr_lst) {
-			if (!net_eq(dev_net(ifa->idev->dev), net))
-				continue;
+				     &net->ipv6.inet6_addr_lst[state->bucket], addr_lst) {
 			return ifa;
 		}
 	}
@@ -4411,9 +4396,7 @@  int ipv6_chk_home_addr(struct net *net, const struct in6_addr *addr)
 	int ret = 0;
 
 	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;
+	hlist_for_each_entry_rcu(ifp, &net->ipv6.inet6_addr_lst[hash], addr_lst) {
 		if (ipv6_addr_equal(&ifp->addr, addr) &&
 		    (ifp->flags & IFA_F_HOMEADDRESS)) {
 			ret = 1;
@@ -4451,9 +4434,7 @@  int ipv6_chk_rpl_srh_loop(struct net *net, const struct in6_addr *segs,
 		hash = inet6_addr_hash(net, addr);
 
 		hash_found = false;
-		hlist_for_each_entry_rcu(ifp, &inet6_addr_lst[hash], addr_lst) {
-			if (!net_eq(dev_net(ifp->idev->dev), net))
-				continue;
+		hlist_for_each_entry_rcu(ifp, &net->ipv6.inet6_addr_lst[hash], addr_lst) {
 
 			if (ipv6_addr_equal(&ifp->addr, addr)) {
 				hash_found = true;
@@ -4498,7 +4479,7 @@  static void addrconf_verify_rtnl(struct net *net)
 
 	for (i = 0; i < IN6_ADDR_HSIZE; i++) {
 restart:
-		hlist_for_each_entry_rcu_bh(ifp, &inet6_addr_lst[i], addr_lst) {
+		hlist_for_each_entry_rcu_bh(ifp, &net->ipv6.inet6_addr_lst[i], addr_lst) {
 			unsigned long age;
 
 			/* When setting preferred_lft to a value not zero or
@@ -7233,7 +7214,7 @@  static struct rtnl_af_ops inet6_ops __read_mostly = {
 int __init addrconf_init(void)
 {
 	struct inet6_dev *idev;
-	int i, err;
+	int err;
 
 	err = ipv6_addr_label_init();
 	if (err < 0) {
@@ -7280,9 +7261,6 @@  int __init addrconf_init(void)
 
 	ip6_route_init_special_entries();
 
-	for (i = 0; i < IN6_ADDR_HSIZE; i++)
-		INIT_HLIST_HEAD(&inet6_addr_lst[i]);
-
 	register_netdevice_notifier(&ipv6_dev_notf);
 
 	addrconf_verify(&init_net);
@@ -7343,7 +7321,6 @@  int __init addrconf_init(void)
 void addrconf_cleanup(void)
 {
 	struct net_device *dev;
-	int i;
 
 	unregister_netdevice_notifier(&ipv6_dev_notf);
 	unregister_pernet_subsys(&addrconf_ops);
@@ -7361,14 +7338,6 @@  void addrconf_cleanup(void)
 	}
 	addrconf_ifdown(init_net.loopback_dev, true);
 
-	/*
-	 *	Check hash table.
-	 */
-	spin_lock_bh(&addrconf_hash_lock);
-	for (i = 0; i < IN6_ADDR_HSIZE; i++)
-		WARN_ON(!hlist_empty(&inet6_addr_lst[i]));
-	spin_unlock_bh(&addrconf_hash_lock);
-
 	rtnl_unlock();
 
 	destroy_workqueue(addrconf_wq);