Merge branch 'master' of master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6

* 'master' of master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6: (51 commits)
  [IPV6]: Fix again the fl6_sock_lookup() fixed locking
  [NETFILTER]: nf_conntrack_tcp: fix connection reopening fix
  [IPV6]: Fix race in ipv6_flowlabel_opt() when inserting two labels
  [IPV6]: Lost locking in fl6_sock_lookup
  [IPV6]: Lost locking when inserting a flowlabel in ipv6_fl_list
  [NETFILTER]: xt_sctp: fix mistake to pass a pointer where array is required
  [NET]: Fix OOPS due to missing check in dev_parse_header().
  [TCP]: Remove lost_retrans zero seqno special cases
  [NET]: fix carrier-on bug?
  [NET]: Fix uninitialised variable in ip_frag_reasm()
  [IPSEC]: Rename mode to outer_mode and add inner_mode
  [IPSEC]: Disallow combinations of RO and AH/ESP/IPCOMP
  [IPSEC]: Use the top IPv4 route's peer instead of the bottom
  [IPSEC]: Store afinfo pointer in xfrm_mode
  [IPSEC]: Add missing BEET checks
  [IPSEC]: Move type and mode map into xfrm_state.c
  [IPSEC]: Fix length check in xfrm_parse_spi
  [IPSEC]: Move ip_summed zapping out of xfrm6_rcv_spi
  [IPSEC]: Get nexthdr from caller in xfrm6_rcv_spi
  [IPSEC]: Move tunnel parsing for IPv4 out of xfrm4_input
  ...

1 files changed, 40 insertions, 17 deletions

diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c
index 217d60f..b12cc22 100644
--- a/net/ipv6/ip6_flowlabel.c
+++ b/net/ipv6/ip6_flowlabel.c
@@ -154,8 +154,10 @@ static void ip6_fl_gc(unsigned long dummy)
 	write_unlock(&ip6_fl_lock);
 }
 
-static int fl_intern(struct ip6_flowlabel *fl, __be32 label)
+static struct ip6_flowlabel *fl_intern(struct ip6_flowlabel *fl, __be32 label)
 {
+	struct ip6_flowlabel *lfl;
+
 	fl->label = label & IPV6_FLOWLABEL_MASK;
 
 	write_lock_bh(&ip6_fl_lock);
@@ -163,12 +165,26 @@ static int fl_intern(struct ip6_flowlabel *fl, __be32 label)
 		for (;;) {
 			fl->label = htonl(net_random())&IPV6_FLOWLABEL_MASK;
 			if (fl->label) {
-				struct ip6_flowlabel *lfl;
 				lfl = __fl_lookup(fl->label);
 				if (lfl == NULL)
 					break;
 			}
 		}
+	} else {
+		/*
+		 * we dropper the ip6_fl_lock, so this entry could reappear
+		 * and we need to recheck with it.
+		 *
+		 * OTOH no need to search the active socket first, like it is
+		 * done in ipv6_flowlabel_opt - sock is locked, so new entry
+		 * with the same label can only appear on another sock
+		 */
+		lfl = __fl_lookup(fl->label);
+		if (lfl != NULL) {
+			atomic_inc(&lfl->users);
+			write_unlock_bh(&ip6_fl_lock);
+			return lfl;
+		}
 	}
 
 	fl->lastuse = jiffies;
@@ -176,7 +192,7 @@ static int fl_intern(struct ip6_flowlabel *fl, __be32 label)
 	fl_ht[FL_HASH(fl->label)] = fl;
 	atomic_inc(&fl_size);
 	write_unlock_bh(&ip6_fl_lock);
-	return 0;
+	return NULL;
 }
 
 
@@ -190,14 +206,17 @@ struct ip6_flowlabel * fl6_sock_lookup(struct sock *sk, __be32 label)
 
 	label &= IPV6_FLOWLABEL_MASK;
 
+	read_lock_bh(&ip6_sk_fl_lock);
 	for (sfl=np->ipv6_fl_list; sfl; sfl = sfl->next) {
 		struct ip6_flowlabel *fl = sfl->fl;
 		if (fl->label == label) {
 			fl->lastuse = jiffies;
 			atomic_inc(&fl->users);
+			read_unlock_bh(&ip6_sk_fl_lock);
 			return fl;
 		}
 	}
+	read_unlock_bh(&ip6_sk_fl_lock);
 	return NULL;
 }
 
@@ -409,6 +428,16 @@ static int ipv6_opt_cmp(struct ipv6_txoptions *o1, struct ipv6_txoptions *o2)
 	return 0;
 }
 
+static inline void fl_link(struct ipv6_pinfo *np, struct ipv6_fl_socklist *sfl,
+		struct ip6_flowlabel *fl)
+{
+	write_lock_bh(&ip6_sk_fl_lock);
+	sfl->fl = fl;
+	sfl->next = np->ipv6_fl_list;
+	np->ipv6_fl_list = sfl;
+	write_unlock_bh(&ip6_sk_fl_lock);
+}
+
 int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen)
 {
 	int err;
@@ -416,7 +445,8 @@ int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen)
 	struct in6_flowlabel_req freq;
 	struct ipv6_fl_socklist *sfl1=NULL;
 	struct ipv6_fl_socklist *sfl, **sflp;
-	struct ip6_flowlabel *fl;
+	struct ip6_flowlabel *fl, *fl1 = NULL;
+
 
 	if (optlen < sizeof(freq))
 		return -EINVAL;
@@ -472,8 +502,6 @@ int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen)
 		sfl1 = kmalloc(sizeof(*sfl1), GFP_KERNEL);
 
 		if (freq.flr_label) {
-			struct ip6_flowlabel *fl1 = NULL;
-
 			err = -EEXIST;
 			read_lock_bh(&ip6_sk_fl_lock);
 			for (sfl = np->ipv6_fl_list; sfl; sfl = sfl->next) {
@@ -492,6 +520,7 @@ int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen)
 			if (fl1 == NULL)
 				fl1 = fl_lookup(freq.flr_label);
 			if (fl1) {
+recheck:
 				err = -EEXIST;
 				if (freq.flr_flags&IPV6_FL_F_EXCL)
 					goto release;
@@ -513,11 +542,7 @@ int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen)
 					fl1->linger = fl->linger;
 				if ((long)(fl->expires - fl1->expires) > 0)
 					fl1->expires = fl->expires;
-				write_lock_bh(&ip6_sk_fl_lock);
-				sfl1->fl = fl1;
-				sfl1->next = np->ipv6_fl_list;
-				np->ipv6_fl_list = sfl1;
-				write_unlock_bh(&ip6_sk_fl_lock);
+				fl_link(np, sfl1, fl1);
 				fl_free(fl);
 				return 0;
 
@@ -534,9 +559,9 @@ release:
 		if (sfl1 == NULL || (err = mem_check(sk)) != 0)
 			goto done;
 
-		err = fl_intern(fl, freq.flr_label);
-		if (err)
-			goto done;
+		fl1 = fl_intern(fl, freq.flr_label);
+		if (fl1 != NULL)
+			goto recheck;
 
 		if (!freq.flr_label) {
 			if (copy_to_user(&((struct in6_flowlabel_req __user *) optval)->flr_label,
@@ -545,9 +570,7 @@ release:
 			}
 		}
 
-		sfl1->fl = fl;
-		sfl1->next = np->ipv6_fl_list;
-		np->ipv6_fl_list = sfl1;
+		fl_link(np, sfl1, fl);
 		return 0;
 
 	default: