mld: convert ipv6_mc_socklist->sflist to RCU

The sflist has been protected by rwlock so that the critical section
is atomic context.
In order to switch this context, changing locking is needed.
The sflist actually already protected by RTNL So if it's converted
to use RCU, its control path context can be switched to sleepable.

Suggested-by: Cong Wang <[e-mail]>
Signed-off-by: Taehee Yoo <[e-mail]>
Signed-off-by: David S. Miller <[e-mail]>

include/net/if_inet6.h

···
 struct ip6_sf_socklist {
 	unsigned int		sl_max;
 	unsigned int		sl_count;
+	struct rcu_head		rcu;
 	struct in6_addr		sl_addr[];
 };
 
···
 	int			ifindex;
 	unsigned int		sfmode;		/* MCAST_{INCLUDE,EXCLUDE} */
 	struct ipv6_mc_socklist __rcu *next;
-	rwlock_t		sflock;
-	struct ip6_sf_socklist	*sflist;
+	struct ip6_sf_socklist	__rcu *sflist;
 	struct rcu_head		rcu;
 };
 

net/ipv6/mcast.c

···
 
 	mc_lst->ifindex = dev->ifindex;
 	mc_lst->sfmode = mode;
-	rwlock_init(&mc_lst->sflock);
-	mc_lst->sflist = NULL;
+	RCU_INIT_POINTER(mc_lst->sflist, NULL);
 
 	/*
 	 *	now add/increase the group membership on the device
···
 	struct net *net = sock_net(sk);
 	int i, j, rv;
 	int leavegroup = 0;
-	int pmclocked = 0;
 	int err;
 
 	source = &((struct sockaddr_in6 *)&pgsr->gsr_source)->sin6_addr;
···
 		goto done;
 	}
 	/* if a source filter was set, must be the same mode as before */
-	if (pmc->sflist) {
+	if (rcu_access_pointer(pmc->sflist)) {
 		if (pmc->sfmode != omode) {
 			err = -EINVAL;
 			goto done;
···
 		pmc->sfmode = omode;
 	}
 
-	write_lock(&pmc->sflock);
-	pmclocked = 1;
-
-	psl = pmc->sflist;
+	psl = rtnl_dereference(pmc->sflist);
 	if (!add) {
 		if (!psl)
 			goto done;	/* err = -EADDRNOTAVAIL */
···
 		if (psl) {
 			for (i = 0; i < psl->sl_count; i++)
 				newpsl->sl_addr[i] = psl->sl_addr[i];
-			sock_kfree_s(sk, psl, IP6_SFLSIZE(psl->sl_max));
+			atomic_sub(IP6_SFLSIZE(psl->sl_max), &sk->sk_omem_alloc);
+			kfree_rcu(psl, rcu);
 		}
-		pmc->sflist = psl = newpsl;
+		psl = newpsl;
+		rcu_assign_pointer(pmc->sflist, psl);
 	}
 	rv = 1;	/* > 0 for insert logic below if sl_count is 0 */
 	for (i = 0; i < psl->sl_count; i++) {
···
 	/* update the interface list */
 	ip6_mc_add_src(idev, group, omode, 1, source, 1);
 done:
-	if (pmclocked)
-		write_unlock(&pmc->sflock);
 	read_unlock_bh(&idev->lock);
 	rcu_read_unlock();
 	if (leavegroup)
···
 		(void) ip6_mc_add_src(idev, group, gsf->gf_fmode, 0, NULL, 0);
 	}
 
-	write_lock(&pmc->sflock);
-	psl = pmc->sflist;
+	psl = rtnl_dereference(pmc->sflist);
 	if (psl) {
 		(void) ip6_mc_del_src(idev, group, pmc->sfmode,
 			psl->sl_count, psl->sl_addr, 0);
-		sock_kfree_s(sk, psl, IP6_SFLSIZE(psl->sl_max));
+		atomic_sub(IP6_SFLSIZE(psl->sl_max), &sk->sk_omem_alloc);
+		kfree_rcu(psl, rcu);
 	} else
 		(void) ip6_mc_del_src(idev, group, pmc->sfmode, 0, NULL, 0);
-	pmc->sflist = newpsl;
+	rcu_assign_pointer(pmc->sflist, newpsl);
 	pmc->sfmode = gsf->gf_fmode;
-	write_unlock(&pmc->sflock);
 	err = 0;
 done:
 	read_unlock_bh(&idev->lock);
···
 	if (!pmc)		/* must have a prior join */
 		goto done;
 	gsf->gf_fmode = pmc->sfmode;
-	psl = pmc->sflist;
+	psl = rtnl_dereference(pmc->sflist);
 	count = psl ? psl->sl_count : 0;
 	read_unlock_bh(&idev->lock);
 	rcu_read_unlock();
 
 	copycount = count < gsf->gf_numsrc ? count : gsf->gf_numsrc;
 	gsf->gf_numsrc = count;
-	/* changes to psl require the socket lock, and a write lock
-	 * on pmc->sflock. We have the socket lock so reading here is safe.
-	 */
+
 	for (i = 0; i < copycount; i++, p++) {
 		struct sockaddr_in6 *psin6;
 		struct sockaddr_storage ss;
···
 		rcu_read_unlock();
 		return np->mc_all;
 	}
-	read_lock(&mc->sflock);
-	psl = mc->sflist;
+	psl = rcu_dereference(mc->sflist);
 	if (!psl) {
 		rv = mc->sfmode == MCAST_EXCLUDE;
 	} else {
···
 		if (mc->sfmode == MCAST_EXCLUDE && i < psl->sl_count)
 			rv = false;
 	}
-	read_unlock(&mc->sflock);
 	rcu_read_unlock();
 
 	return rv;
···
 static int ip6_mc_leave_src(struct sock *sk, struct ipv6_mc_socklist *iml,
 			    struct inet6_dev *idev)
 {
+	struct ip6_sf_socklist *psl;
 	int err;
 
-	write_lock_bh(&iml->sflock);
-	if (!iml->sflist) {
+	psl = rtnl_dereference(iml->sflist);
+
+	if (!psl) {
 		/* any-source empty exclude case */
 		err = ip6_mc_del_src(idev, &iml->addr, iml->sfmode, 0, NULL, 0);
 	} else {
 		err = ip6_mc_del_src(idev, &iml->addr, iml->sfmode,
-				iml->sflist->sl_count, iml->sflist->sl_addr, 0);
-		sock_kfree_s(sk, iml->sflist, IP6_SFLSIZE(iml->sflist->sl_max));
-		iml->sflist = NULL;
+				psl->sl_count, psl->sl_addr, 0);
+		RCU_INIT_POINTER(iml->sflist, NULL);
+		atomic_sub(IP6_SFLSIZE(psl->sl_max), &sk->sk_omem_alloc);
+		kfree_rcu(psl, rcu);
 	}
-	write_unlock_bh(&iml->sflock);
 	return err;
 }