net: ipv6: Make address flushing on ifdown optional - v2

Currently, all ipv6 addresses are flushed when the interface is configured down, even static address:

[root@f20 ~]# ip -6 addr add dev eth1 2000:11:1:1::1/64
[root@f20 ~]# ip addr show dev eth1
3: eth1: <BROADCAST,MULTICAST> mtu 1500 qdisc noop state DOWN group default qlen 1000

     link/ether 02:04:11:22:33:01 brd ff:ff:ff:ff:ff:ff
     inet6 2000:11:1:1::1/64 scope global tentative
        valid_lft forever preferred_lft forever

[root@f20 ~]# ip link set dev eth1 up
[root@f20 ~]# ip link set dev eth1 down
[root@f20 ~]# ip addr show dev eth1
3: eth1: <BROADCAST,MULTICAST> mtu 1500 qdisc pfifo_fast state DOWN group default qlen 1000

     link/ether 02:04:11:22:33:01 brd ff:ff:ff:ff:ff:ff

Add a new sysctl to make this behavior optional. The new setting defaults to flush all addresses to maintain backwards compatibility. When the setting is reset static addresses are not flushed:

[root@f20 ~]# echo 0 > /proc/sys/net/ipv6/conf/eth1/flush_addr_on_down [root@f20 ~]# ip -6 addr add dev eth1 2000:11:1:1::1/64
[root@f20 ~]# ip addr show dev eth1
3: eth1: <BROADCAST,MULTICAST> mtu 1500 qdisc pfifo_fast state DOWN group default qlen 1000

     link/ether 02:04:11:22:33:01 brd ff:ff:ff:ff:ff:ff
     inet6 2000:11:1:1::1/64 scope global tentative
        valid_lft forever preferred_lft forever

[root@f20 ~]# ip link set dev eth1 up
[root@f20 ~]# ip link set dev eth1 down
[root@f20 ~]# ip addr show dev eth1
3: eth1: <BROADCAST,MULTICAST> mtu 1500 qdisc pfifo_fast state DOWN group default qlen 1000

     link/ether 02:04:11:22:33:01 brd ff:ff:ff:ff:ff:ff
     inet6 2000:11:1:1::1/64 scope global
        valid_lft forever preferred_lft forever
     inet6 fe80::4:11ff:fe22:3301/64 scope link
        valid_lft forever preferred_lft forever

v2:
- only keep static addresses as suggested by Hannes
- added new managed flag to track configured addresses
- on ifdown do not remove from configured address from inet6_addr_lst
- on ifdown reset the TENTATIVE flag and set state to DAD so that DAD is redone when link is brought up again

Suggested-by Hannes Frederic Sowa <[email protected]>

Signed-off-by David Ahern <[email protected]>

Cc Hannes Frederic Sowa <[email protected]>

Signed-off-by David Ahern <[email protected]>

---
  include/linux/ipv6.h      |  1 +
  include/net/if_inet6.h    |  1 +
  include/uapi/linux/ipv6.h |  1 +
  net/ipv6/addrconf.c       | 55 ++++++++++++++++++++++++++++++++++++++---------
  4 files changed, 48 insertions(+), 10 deletions(-)

include/linux/ipv6.h +1 -0

index 2805062c013f..b91b7c8be023 100644
@@ -53,6 +53,7 @@ struct ipv6_devconf {
  	__s32           ndisc_notify;
  	__s32		suppress_frag_ndisc;
  	__s32		accept_ra_mtu;
+	__s32		flush_addr_on_down;
  	void		*sysctl;
  };
 

include/net/if_inet6.h +1 -0

index 98e5f9578f86..3b6323111f77 100644
@@ -72,6 +72,7 @@ struct inet6_ifaddr {
  	int			regen_count;
 
  	bool			tokenized;
+	bool			managed;
 
  	struct rcu_head		rcu;
  	struct in6_addr		peer_addr;

include/uapi/linux/ipv6.h +1 -0

index 437a6a4b125a..ed10d4ba8340 100644
@@ -170,6 +170,7 @@ enum {
  	DEVCONF_ACCEPT_RA_FROM_LOCAL,
  	DEVCONF_USE_OPTIMISTIC,
  	DEVCONF_ACCEPT_RA_MTU,
+	DEVCONF_FLUSH_ON_DOWN,
  	DEVCONF_MAX
  };
 

net/ipv6/addrconf.c +45 -10

index 7dcc065e2160..e0e82aad2116 100644
@@ -202,6 +202,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = {
  	.accept_dad		= 1,
  	.suppress_frag_ndisc	= 1,
  	.accept_ra_mtu		= 1,
+	.flush_addr_on_down	= 1,
  };
 
  static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = {

@@ -240,6 +241,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = {
  	.accept_dad		= 1,
  	.suppress_frag_ndisc	= 1,
  	.accept_ra_mtu		= 1,
+	.flush_addr_on_down	= 1,
  };
 
  /* Check if a valid qdisc is available */

@@ -870,6 +872,7 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr,
  	ifa->prefered_lft = prefered_lft;
  	ifa->cstamp = ifa->tstamp = jiffies;
  	ifa->tokenized = false;
+	ifa->managed = false;
 
  	ifa->rt = rt;
 

@@ -2510,6 +2513,8 @@ static int inet6_addr_add(struct net *net, int ifindex,
  			    valid_lft, prefered_lft);
 
  	if (!IS_ERR(ifp)) {
+		ifp->managed = true;
+
  		if (!(ifa_flags & IFA_F_NOPREFIXROUTE)) {
  			addrconf_prefix_route(&ifp->addr, ifp->prefix_len, dev,
  					      expires, flags);

@@ -3032,8 +3037,9 @@ static int addrconf_ifdown(struct net_device *dev, int how)
  {
  	struct net *net = dev_net(dev);
  	struct inet6_dev *idev;
-	struct inet6_ifaddr *ifa;
+	struct inet6_ifaddr *ifa, *tmp;
  	int state, i;
+	struct list_head del_list;
 
  	ASSERT_RTNL();
 

@@ -3067,9 +3073,12 @@ static int addrconf_ifdown(struct net_device *dev, int how)
  restart:
  		hlist_for_each_entry_rcu(ifa, h, addr_lst) {
  			if (ifa->idev == idev) {
-				hlist_del_init_rcu(&ifa->addr_lst);
  				addrconf_del_dad_work(ifa);
-				goto restart;
+				if (how || idev->cnf.flush_addr_on_down ||
+				    !ifa->managed) {
+					hlist_del_init_rcu(&ifa->addr_lst);
+					goto restart;
+				}
  			}
  		}
  		spin_unlock_bh(&addrconf_hash_lock);

@@ -3103,14 +3112,35 @@ restart:
  		write_lock_bh(&idev->lock);
  	}
 
-	while (!list_empty(&idev->addr_list)) {
-		ifa = list_first_entry(&idev->addr_list,
+	INIT_LIST_HEAD(&del_list);
+	list_for_each_entry_safe(ifa, tmp, &idev->addr_list, if_list) {
+		/*
+		 * on NETDEV_DOWN events do not flush managed (user configured)
+		 * addresses unless configured to do so. If the address is not
+		 * deleted reset flags and state such that DAD is re-done on a
+ 		 * subsequent link up.
+ 		 */
+		if (!how && !idev->cnf.flush_addr_on_down && ifa->managed) {
+	    		if (!(ifa->flags & IFA_F_NODAD)) {
+				ifa->flags |= IFA_F_TENTATIVE;
+				ifa->state = INET6_IFADDR_STATE_DAD;
+			}
+		} else {
+			list_del(&ifa->if_list);
+			list_add(&ifa->if_list, &del_list);
+		}
+	}
+
+	write_unlock_bh(&idev->lock);
+
+	while (!list_empty(&del_list)) {
+		ifa = list_first_entry(&del_list,
  				       struct inet6_ifaddr, if_list);
+
  		addrconf_del_dad_work(ifa);
 
  		list_del(&ifa->if_list);
 
-		write_unlock_bh(&idev->lock);
 
  		spin_lock_bh(&ifa->state_lock);
  		state = ifa->state;

@@ -3122,12 +3152,8 @@ restart:
  			inet6addr_notifier_call_chain(NETDEV_DOWN, ifa);
  		}
  		in6_ifa_put(ifa);
-
-		write_lock_bh(&idev->lock);
  	}
 
-	write_unlock_bh(&idev->lock);
-
  	/* Step 5: Discard anycast and multicast list */
  	if (how) {
  		ipv6_ac_destroy_dev(idev);

@@ -4383,6 +4409,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf,
  	array[DEVCONF_SUPPRESS_FRAG_NDISC] = cnf->suppress_frag_ndisc;
  	array[DEVCONF_ACCEPT_RA_FROM_LOCAL] = cnf->accept_ra_from_local;
  	array[DEVCONF_ACCEPT_RA_MTU] = cnf->accept_ra_mtu;
+	array[DEVCONF_FLUSH_ON_DOWN] = cnf->flush_addr_on_down;
  }
 
  static inline size_t inet6_ifla6_size(void)

@@ -5269,6 +5296,14 @@ static struct addrconf_sysctl_table
  			.proc_handler	= proc_dointvec,
  		},
  		{
+			.procname       = "flush_addr_on_down",
+			.data           = &ipv6_devconf.flush_addr_on_down,
+			.maxlen         = sizeof(int),
+			.mode           = 0644,
+			.proc_handler   = proc_dointvec,
+
+		},
+		{
  			/* sentinel */
  		}
  	},

Currently, all ipv6 addresses are flushed when the interface is configured down, even static address:

include/linux/ipv6.h +1 -0

index 2805062c013f..b91b7c8be023 100644
@@ -53,6 +53,7 @@ struct ipv6_devconf {
 	__s32           ndisc_notify;
 	__s32		suppress_frag_ndisc;
 	__s32		accept_ra_mtu;
+	__s32		flush_addr_on_down;
 	void		*sysctl;
 };

Currently, all ipv6 addresses are flushed when the interface is configured down, even static address:

[root@f20 ~]# ip -6 addr add dev eth1 2000:11:1:1::1/64
[root@f20 ~]# ip addr show dev eth1
3: eth1: <BROADCAST,MULTICAST> mtu 1500 qdisc noop state DOWN group default qlen 1000

    link/ether 02:04:11:22:33:01 brd ff:ff:ff:ff:ff:ff
    inet6 2000:11:1:1::1/64 scope global tentative
       valid_lft forever preferred_lft forever

[root@f20 ~]# ip link set dev eth1 up
[root@f20 ~]# ip link set dev eth1 down
[root@f20 ~]# ip addr show dev eth1
3: eth1: <BROADCAST,MULTICAST> mtu 1500 qdisc pfifo_fast state DOWN group default qlen 1000

    link/ether 02:04:11:22:33:01 brd ff:ff:ff:ff:ff:ff

Add a new sysctl to make this behavior optional. The new setting defaults to flush all addresses to maintain backwards compatibility. When the setting is reset static addresses are not flushed:

[root@f20 ~]# echo 0 > /proc/sys/net/ipv6/conf/eth1/flush_addr_on_down [root@f20 ~]# ip -6 addr add dev eth1 2000:11:1:1::1/64
[root@f20 ~]# ip addr show dev eth1
3: eth1: <BROADCAST,MULTICAST> mtu 1500 qdisc pfifo_fast state DOWN group default qlen 1000

    link/ether 02:04:11:22:33:01 brd ff:ff:ff:ff:ff:ff
    inet6 2000:11:1:1::1/64 scope global tentative
       valid_lft forever preferred_lft forever

[root@f20 ~]# ip link set dev eth1 up
[root@f20 ~]# ip link set dev eth1 down
[root@f20 ~]# ip addr show dev eth1
3: eth1: <BROADCAST,MULTICAST> mtu 1500 qdisc pfifo_fast state DOWN group default qlen 1000

    link/ether 02:04:11:22:33:01 brd ff:ff:ff:ff:ff:ff
    inet6 2000:11:1:1::1/64 scope global
       valid_lft forever preferred_lft forever
    inet6 fe80::4:11ff:fe22:3301/64 scope link
       valid_lft forever preferred_lft forever

v2:
- only keep static addresses as suggested by Hannes
- added new managed flag to track configured addresses
- on ifdown do not remove from configured address from inet6_addr_lst
- on ifdown reset the TENTATIVE flag and set state to DAD so that DAD is redone when link is brought up again

Suggested-by Hannes Frederic Sowa <[email protected]>

Signed-off-by David Ahern <[email protected]>

Cc Hannes Frederic Sowa <[email protected]>

Signed-off-by David Ahern <[email protected]>

Checkpatch complains about space before tab, which could be your mailer mangling the patch.

This should probably go into the netconf netlink message as well.

Quoted 2 lines · Stephen Hemminger

Checkpatch complains about space before tab, which could be your mailer mangling the patch.

Yes, found that a couple of days ago. I use 'git send-email' to send the patches, and I have a pre-commit hook to run checkpatch.pl. Perhaps I goofed something in the recent latptop transitions.

Quoted 1 line

Quoted 2 lines

This should probably go into the netconf netlink message as well.

Not sure I understand this point. Can you point me to a code reference to look up?

Quoted 2 lines · Stephen Hemminger

Checkpatch complains about space before tab, which could be your mailer mangling the patch.

Yes, found that a couple of days ago. I use 'git send-email' to send the patches, and I have a pre-commit hook to run checkpatch.pl. Perhaps I goofed something in the recent latptop transitions.

Quoted 3 lines

This should probably go into the netconf netlink message as well.

Not sure I understand this point. Can you point me to a code reference to look up?

Though that did remind me that I should add a blurb in Documentation/networking/ip-sysctl.txt.

David