Commit eecbb169 authored by Jakub Kicinski's avatar Jakub Kicinski
Browse files

Merge branch 'ipv6-drop-rtnl-from-mcast-c-and-anycast-c' 

Kuniyuki Iwashima says:

====================
ipv6: Drop RTNL from mcast.c and anycast.c

This is a prep series for RCU conversion of RTM_NEWNEIGH, which needs
RTNL during neigh_table.{pconstructor,pdestructor}() touching IPv6
multicast code.

Currently, IPv6 multicast code is protected by lock_sock() and
inet6_dev->mc_lock, and RTNL is not actually needed.

In addition, anycast code is also in the same situation and does not
need RTNL at all.

This series removes RTNL from net/ipv6/{mcast.c,anycast.c} and finally
removes setsockopt_needs_rtnl() from do_ipv6_setsockopt().

v2: https://lore.kernel.org/20250624202616.526600-1-kuni1840@gmail.com
v1: https://lore.kernel.org/20250616233417.1153427-1-kuni1840@gmail.com
====================

Link: https://patch.msgid.link/20250702230210.3115355-1-kuni1840@gmail.com


Signed-off-by: default avatarJakub Kicinski <kuba@kernel.org>
parents 01af0001 db38443d

include/linux/netdevice.h

+2 −2
Original line number Diff line number Diff line
@@ -3332,7 +3332,7 @@ int dev_get_iflink(const struct net_device *dev); 
int dev_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb);

int dev_fill_forward_path(const struct net_device *dev, const u8 *daddr,

			  struct net_device_path_stack *stack);

struct net_device *__dev_get_by_flags(struct net *net, unsigned short flags,

struct net_device *dev_get_by_flags_rcu(struct net *net, unsigned short flags,

					unsigned short mask);

struct net_device *dev_get_by_name(struct net *net, const char *name);

struct net_device *dev_get_by_name_rcu(struct net *net, const char *name);

net/core/dev.c

+18 −20
Original line number Diff line number Diff line
@@ -1267,33 +1267,31 @@ struct net_device *dev_getfirstbyhwtype(struct net *net, unsigned short type) 
EXPORT_SYMBOL(dev_getfirstbyhwtype);



/**

 *	__dev_get_by_flags - find any device with given flags

 * dev_get_by_flags_rcu - find any device with given flags

 * @net: the applicable net namespace

 * @if_flags: IFF_* values

 * @mask: bitmask of bits in if_flags to check

 *

 *	Search for any interface with the given flags. Returns NULL if a device

 *	is not found or a pointer to the device. Must be called inside

 *	rtnl_lock(), and result refcount is unchanged.

 * Search for any interface with the given flags.

 *

 * Context: rcu_read_lock() must be held.

 * Returns: NULL if a device is not found or a pointer to the device.

 */



struct net_device *__dev_get_by_flags(struct net *net, unsigned short if_flags,

struct net_device *dev_get_by_flags_rcu(struct net *net, unsigned short if_flags,

					unsigned short mask)

{

	struct net_device *dev, *ret;



	ASSERT_RTNL();

	struct net_device *dev;



	ret = NULL;

	for_each_netdev(net, dev) {

		if (((dev->flags ^ if_flags) & mask) == 0) {

			ret = dev;

			break;

	for_each_netdev_rcu(net, dev) {

		if (((READ_ONCE(dev->flags) ^ if_flags) & mask) == 0) {

			dev_hold(dev);

			return dev;

		}

	}

	return ret;



	return NULL;

}

EXPORT_SYMBOL(__dev_get_by_flags);

EXPORT_IPV6_MOD(dev_get_by_flags_rcu);



/**

 *	dev_valid_name - check if name is okay for network device

net/ipv6/addrconf.c

+4 −8
Original line number Diff line number Diff line
@@ -2229,32 +2229,29 @@ void addrconf_dad_failure(struct sk_buff *skb, struct inet6_ifaddr *ifp) 
	in6_ifa_put(ifp);

}



/* Join to solicited addr multicast group.

 * caller must hold RTNL */

/* Join to solicited addr multicast group. */

void addrconf_join_solict(struct net_device *dev, const struct in6_addr *addr)

{

	struct in6_addr maddr;



	if (dev->flags&(IFF_LOOPBACK|IFF_NOARP))

	if (READ_ONCE(dev->flags) & (IFF_LOOPBACK | IFF_NOARP))

		return;



	addrconf_addr_solict_mult(addr, &maddr);

	ipv6_dev_mc_inc(dev, &maddr);

}



/* caller must hold RTNL */

void addrconf_leave_solict(struct inet6_dev *idev, const struct in6_addr *addr)

{

	struct in6_addr maddr;



	if (idev->dev->flags&(IFF_LOOPBACK|IFF_NOARP))

	if (READ_ONCE(idev->dev->flags) & (IFF_LOOPBACK | IFF_NOARP))

		return;



	addrconf_addr_solict_mult(addr, &maddr);

	__ipv6_dev_mc_dec(idev, &maddr);

}



/* caller must hold RTNL */

static void addrconf_join_anycast(struct inet6_ifaddr *ifp)

{

	struct in6_addr addr;
@@ -2267,7 +2264,6 @@ static void addrconf_join_anycast(struct inet6_ifaddr *ifp) 
	__ipv6_dev_ac_inc(ifp->idev, &addr);

}



/* caller must hold RTNL */

static void addrconf_leave_anycast(struct inet6_ifaddr *ifp)

{

	struct in6_addr addr;
@@ -3865,7 +3861,7 @@ static int addrconf_ifdown(struct net_device *dev, bool unregister) 
	 *	   Do not dev_put!

	 */

	if (unregister) {

		idev->dead = 1;

		WRITE_ONCE(idev->dead, 1);



		/* protected by rtnl_lock */

		RCU_INIT_POINTER(dev->ip6_ptr, NULL);

net/ipv6/anycast.c

+58 −42
Original line number Diff line number Diff line
@@ -47,6 +47,9 @@ 
static struct hlist_head inet6_acaddr_lst[IN6_ADDR_HSIZE];

static DEFINE_SPINLOCK(acaddr_hash_lock);



#define ac_dereference(a, idev)						\

	rcu_dereference_protected(a, lockdep_is_held(&(idev)->lock))



static int ipv6_dev_ac_dec(struct net_device *dev, const struct in6_addr *addr);



static u32 inet6_acaddr_hash(const struct net *net,
@@ -64,14 +67,11 @@ static u32 inet6_acaddr_hash(const struct net *net, 
int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr)

{

	struct ipv6_pinfo *np = inet6_sk(sk);

	struct ipv6_ac_socklist *pac = NULL;

	struct net *net = sock_net(sk);

	struct net_device *dev = NULL;

	struct inet6_dev *idev;

	struct ipv6_ac_socklist *pac;

	struct net *net = sock_net(sk);

	int	ishost = !net->ipv6.devconf_all->forwarding;

	int	err = 0;



	ASSERT_RTNL();

	int err = 0, ishost;



	if (!ns_capable(net->user_ns, CAP_NET_ADMIN))

		return -EPERM;
@@ -79,32 +79,43 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr) 
		return -EINVAL;



	if (ifindex)

		dev = __dev_get_by_index(net, ifindex);

		dev = dev_get_by_index(net, ifindex);



	if (ipv6_chk_addr_and_flags(net, addr, dev, true, 0, IFA_F_TENTATIVE))

		return -EINVAL;

	if (ipv6_chk_addr_and_flags(net, addr, dev, true, 0, IFA_F_TENTATIVE)) {

		err = -EINVAL;

		goto error;

	}



	pac = sock_kmalloc(sk, sizeof(struct ipv6_ac_socklist), GFP_KERNEL);

	if (!pac)

		return -ENOMEM;

	if (!pac) {

		err = -ENOMEM;

		goto error;

	}



	pac->acl_next = NULL;

	pac->acl_addr = *addr;



	ishost = !READ_ONCE(net->ipv6.devconf_all->forwarding);



	if (ifindex == 0) {

		struct rt6_info *rt;



		rcu_read_lock();

		rt = rt6_lookup(net, addr, NULL, 0, NULL, 0);

		if (rt) {

			dev = rt->dst.dev;

			dev = dst_dev(&rt->dst);

			dev_hold(dev);

			ip6_rt_put(rt);

		} else if (ishost) {

			rcu_read_unlock();

			err = -EADDRNOTAVAIL;

			goto error;

		} else {

			/* router, no matching interface: just pick one */

			dev = __dev_get_by_flags(net, IFF_UP,

			dev = dev_get_by_flags_rcu(net, IFF_UP,

						   IFF_UP | IFF_LOOPBACK);

		}

		rcu_read_unlock();

	}



	if (!dev) {
@@ -112,7 +123,7 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr) 
		goto error;

	}



	idev = __in6_dev_get(dev);

	idev = in6_dev_get(dev);

	if (!idev) {

		if (ifindex)

			err = -ENODEV;
@@ -120,8 +131,9 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr) 
			err = -EADDRNOTAVAIL;

		goto error;

	}



	/* reset ishost, now that we have a specific device */

	ishost = !idev->cnf.forwarding;

	ishost = !READ_ONCE(idev->cnf.forwarding);



	pac->acl_ifindex = dev->ifindex;
@@ -134,7 +146,7 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr) 
		if (ishost)

			err = -EADDRNOTAVAIL;

		if (err)

			goto error;

			goto error_idev;

	}



	err = __ipv6_dev_ac_inc(idev, addr);
@@ -144,7 +156,11 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr) 
		pac = NULL;

	}



error_idev:

	in6_dev_put(idev);

error:

	dev_put(dev);



	if (pac)

		sock_kfree_s(sk, pac, sizeof(*pac));

	return err;
@@ -155,12 +171,10 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr) 
 */

int ipv6_sock_ac_drop(struct sock *sk, int ifindex, const struct in6_addr *addr)

{

	struct ipv6_pinfo *np = inet6_sk(sk);

	struct net_device *dev;

	struct ipv6_ac_socklist *pac, *prev_pac;

	struct ipv6_pinfo *np = inet6_sk(sk);

	struct net *net = sock_net(sk);



	ASSERT_RTNL();

	struct net_device *dev;



	prev_pac = NULL;

	for (pac = np->ipv6_ac_list; pac; pac = pac->acl_next) {
@@ -176,9 +190,11 @@ int ipv6_sock_ac_drop(struct sock *sk, int ifindex, const struct in6_addr *addr) 
	else

		np->ipv6_ac_list = pac->acl_next;



	dev = __dev_get_by_index(net, pac->acl_ifindex);

	if (dev)

	dev = dev_get_by_index(net, pac->acl_ifindex);

	if (dev) {

		ipv6_dev_ac_dec(dev, &pac->acl_addr);

		dev_put(dev);

	}



	sock_kfree_s(sk, pac, sizeof(*pac));

	return 0;
@@ -187,21 +203,20 @@ int ipv6_sock_ac_drop(struct sock *sk, int ifindex, const struct in6_addr *addr) 
void __ipv6_sock_ac_close(struct sock *sk)

{

	struct ipv6_pinfo *np = inet6_sk(sk);

	struct net *net = sock_net(sk);

	struct net_device *dev = NULL;

	struct ipv6_ac_socklist *pac;

	struct net *net = sock_net(sk);

	int	prev_index;

	int prev_index = 0;



	ASSERT_RTNL();

	pac = np->ipv6_ac_list;

	np->ipv6_ac_list = NULL;



	prev_index = 0;

	while (pac) {

		struct ipv6_ac_socklist *next = pac->acl_next;



		if (pac->acl_ifindex != prev_index) {

			dev = __dev_get_by_index(net, pac->acl_ifindex);

			dev_put(dev);

			dev = dev_get_by_index(net, pac->acl_ifindex);

			prev_index = pac->acl_ifindex;

		}

		if (dev)
@@ -209,6 +224,8 @@ void __ipv6_sock_ac_close(struct sock *sk) 
		sock_kfree_s(sk, pac, sizeof(*pac));

		pac = next;

	}



	dev_put(dev);

}



void ipv6_sock_ac_close(struct sock *sk)
@@ -217,9 +234,8 @@ void ipv6_sock_ac_close(struct sock *sk) 


	if (!np->ipv6_ac_list)

		return;

	rtnl_lock();



	__ipv6_sock_ac_close(sk);

	rtnl_unlock();

}



static void ipv6_add_acaddr_hash(struct net *net, struct ifacaddr6 *aca)
@@ -319,16 +335,14 @@ int __ipv6_dev_ac_inc(struct inet6_dev *idev, const struct in6_addr *addr) 
	struct net *net;

	int err;



	ASSERT_RTNL();



	write_lock_bh(&idev->lock);

	if (idev->dead) {

		err = -ENODEV;

		goto out;

	}



	for (aca = rtnl_dereference(idev->ac_list); aca;

	     aca = rtnl_dereference(aca->aca_next)) {

	for (aca = ac_dereference(idev->ac_list, idev); aca;

	     aca = ac_dereference(aca->aca_next, idev)) {

		if (ipv6_addr_equal(&aca->aca_addr, addr)) {

			aca->aca_users++;

			err = 0;
@@ -380,12 +394,10 @@ int __ipv6_dev_ac_dec(struct inet6_dev *idev, const struct in6_addr *addr) 
{

	struct ifacaddr6 *aca, *prev_aca;



	ASSERT_RTNL();



	write_lock_bh(&idev->lock);

	prev_aca = NULL;

	for (aca = rtnl_dereference(idev->ac_list); aca;

	     aca = rtnl_dereference(aca->aca_next)) {

	for (aca = ac_dereference(idev->ac_list, idev); aca;

	     aca = ac_dereference(aca->aca_next, idev)) {

		if (ipv6_addr_equal(&aca->aca_addr, addr))

			break;

		prev_aca = aca;
@@ -414,14 +426,18 @@ int __ipv6_dev_ac_dec(struct inet6_dev *idev, const struct in6_addr *addr) 
	return 0;

}



/* called with rtnl_lock() */

static int ipv6_dev_ac_dec(struct net_device *dev, const struct in6_addr *addr)

{

	struct inet6_dev *idev = __in6_dev_get(dev);

	struct inet6_dev *idev = in6_dev_get(dev);

	int err;



	if (!idev)

		return -ENODEV;

	return __ipv6_dev_ac_dec(idev, addr);



	err = __ipv6_dev_ac_dec(idev, addr);

	in6_dev_put(idev);



	return err;

}



void ipv6_ac_destroy_dev(struct inet6_dev *idev)
@@ -429,7 +445,7 @@ void ipv6_ac_destroy_dev(struct inet6_dev *idev) 
	struct ifacaddr6 *aca;



	write_lock_bh(&idev->lock);

	while ((aca = rtnl_dereference(idev->ac_list)) != NULL) {

	while ((aca = ac_dereference(idev->ac_list, idev)) != NULL) {

		rcu_assign_pointer(idev->ac_list, aca->aca_next);

		write_unlock_bh(&idev->lock);

net/ipv6/ipv6_sockglue.c

+2 −26
Original line number Diff line number Diff line
@@ -117,26 +117,6 @@ struct ipv6_txoptions *ipv6_update_options(struct sock *sk, 
	return opt;

}



static bool setsockopt_needs_rtnl(int optname)

{

	switch (optname) {

	case IPV6_ADDRFORM:

	case IPV6_ADD_MEMBERSHIP:

	case IPV6_DROP_MEMBERSHIP:

	case IPV6_JOIN_ANYCAST:

	case IPV6_LEAVE_ANYCAST:

	case MCAST_JOIN_GROUP:

	case MCAST_LEAVE_GROUP:

	case MCAST_JOIN_SOURCE_GROUP:

	case MCAST_LEAVE_SOURCE_GROUP:

	case MCAST_BLOCK_SOURCE:

	case MCAST_UNBLOCK_SOURCE:

	case MCAST_MSFILTER:

		return true;

	}

	return false;

}



static int copy_group_source_from_sockptr(struct group_source_req *greqs,

		sockptr_t optval, int optlen)

{
@@ -395,9 +375,8 @@ int do_ipv6_setsockopt(struct sock *sk, int level, int optname, 
{

	struct ipv6_pinfo *np = inet6_sk(sk);

	struct net *net = sock_net(sk);

	int val, valbool;

	int retv = -ENOPROTOOPT;

	bool needs_rtnl = setsockopt_needs_rtnl(optname);

	int val, valbool;



	if (sockptr_is_null(optval))

		val = 0;
@@ -562,8 +541,7 @@ int do_ipv6_setsockopt(struct sock *sk, int level, int optname, 
		return 0;

	}

	}

	if (needs_rtnl)

		rtnl_lock();



	sockopt_lock_sock(sk);



	/* Another thread has converted the socket into IPv4 with
@@ -969,8 +947,6 @@ int do_ipv6_setsockopt(struct sock *sk, int level, int optname, 


unlock:

	sockopt_release_sock(sk);

	if (needs_rtnl)

		rtnl_unlock();



	return retv;