From def6775369fab9d36817b9a6bc58cab67f53f1dc Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Mon, 2 Mar 2015 00:07:37 -0600
Subject: neigh: Move neigh_compat_output into ax25_ip.c

The only caller is now is ax25_neigh_construct so move
neigh_compat_output into ax25_ip.c make it static and rename it
ax25_neigh_output.

Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: linux-hams@vger.kernel.org
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/neighbour.c | 20 --------------------
 1 file changed, 20 deletions(-)

(limited to 'net/core/neighbour.c')

diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 70fe9e10ac86..8a319ff3e8d1 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -1280,26 +1280,6 @@ static void neigh_hh_init(struct neighbour *n, struct dst_entry *dst)
 	write_unlock_bh(&n->lock);
 }
 
-/* This function can be used in contexts, where only old dev_queue_xmit
- * worked, f.e. if you want to override normal output path (eql, shaper),
- * but resolution is not made yet.
- */
-
-int neigh_compat_output(struct neighbour *neigh, struct sk_buff *skb)
-{
-	struct net_device *dev = skb->dev;
-
-	__skb_pull(skb, skb_network_offset(skb));
-
-	if (dev_hard_header(skb, dev, ntohs(skb->protocol), NULL, NULL,
-			    skb->len) < 0 &&
-	    dev_rebuild_header(skb))
-		return 0;
-
-	return dev_queue_xmit(skb);
-}
-EXPORT_SYMBOL(neigh_compat_output);
-
 /* Slow and careful. */
 
 int neigh_resolve_output(struct neighbour *neigh, struct sk_buff *skb)
-- 
cgit 1.4.1


From bdf53c58490bb52e17636eca8ad18d2c38ec3cb8 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Mon, 2 Mar 2015 00:13:22 -0600
Subject: neigh: Don't require dst in neigh_hh_init

- Add protocol to neigh_tbl so that dst->ops->protocol is not needed
- Acquire the device from neigh->dev

This results in a neigh_hh_init that will cache the samve values
regardless of the packets flowing through it.

Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/neighbour.h | 1 +
 net/core/neighbour.c    | 8 ++++----
 net/decnet/dn_neigh.c   | 1 +
 net/ipv4/arp.c          | 1 +
 net/ipv6/ndisc.c        | 1 +
 5 files changed, 8 insertions(+), 4 deletions(-)

(limited to 'net/core/neighbour.c')

diff --git a/include/net/neighbour.h b/include/net/neighbour.h
index bc66babb5f27..9f912e4d4232 100644
--- a/include/net/neighbour.h
+++ b/include/net/neighbour.h
@@ -193,6 +193,7 @@ struct neigh_table {
 	int			family;
 	int			entry_size;
 	int			key_len;
+	__be16			protocol;
 	__u32			(*hash)(const void *pkey,
 					const struct net_device *dev,
 					__u32 *hash_rnd);
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 8a319ff3e8d1..af72b863e968 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -1263,10 +1263,10 @@ struct neighbour *neigh_event_ns(struct neigh_table *tbl,
 EXPORT_SYMBOL(neigh_event_ns);
 
 /* called with read_lock_bh(&n->lock); */
-static void neigh_hh_init(struct neighbour *n, struct dst_entry *dst)
+static void neigh_hh_init(struct neighbour *n)
 {
-	struct net_device *dev = dst->dev;
-	__be16 prot = dst->ops->protocol;
+	struct net_device *dev = n->dev;
+	__be16 prot = n->tbl->protocol;
 	struct hh_cache	*hh = &n->hh;
 
 	write_lock_bh(&n->lock);
@@ -1296,7 +1296,7 @@ int neigh_resolve_output(struct neighbour *neigh, struct sk_buff *skb)
 		unsigned int seq;
 
 		if (dev->header_ops->cache && !neigh->hh.hh_len)
-			neigh_hh_init(neigh, dst);
+			neigh_hh_init(neigh);
 
 		do {
 			__skb_pull(skb, skb_network_offset(skb));
diff --git a/net/decnet/dn_neigh.c b/net/decnet/dn_neigh.c
index 7ca7c3143da3..f123c6c6748c 100644
--- a/net/decnet/dn_neigh.c
+++ b/net/decnet/dn_neigh.c
@@ -97,6 +97,7 @@ struct neigh_table dn_neigh_table = {
 	.family =			PF_DECnet,
 	.entry_size =			NEIGH_ENTRY_SIZE(sizeof(struct dn_neigh)),
 	.key_len =			sizeof(__le16),
+	.protocol =			cpu_to_be16(ETH_P_DNA_RT),
 	.hash =				dn_neigh_hash,
 	.constructor =			dn_neigh_construct,
 	.id =				"dn_neigh_cache",
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index bca5b9d9b442..6b8aad6a0d7d 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -152,6 +152,7 @@ static const struct neigh_ops arp_direct_ops = {
 struct neigh_table arp_tbl = {
 	.family		= AF_INET,
 	.key_len	= 4,
+	.protocol	= cpu_to_be16(ETH_P_IP),
 	.hash		= arp_hash,
 	.constructor	= arp_constructor,
 	.proxy_redo	= parp_redo,
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 471ed24aabae..e363bbc2420d 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -117,6 +117,7 @@ static const struct neigh_ops ndisc_direct_ops = {
 struct neigh_table nd_tbl = {
 	.family =	AF_INET6,
 	.key_len =	sizeof(struct in6_addr),
+	.protocol =	cpu_to_be16(ETH_P_IPV6),
 	.hash =		ndisc_hash,
 	.constructor =	ndisc_constructor,
 	.pconstructor =	pndisc_constructor,
-- 
cgit 1.4.1


From 435e8eb27edb4da0b47b9b980239bd59057a7362 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Mon, 2 Mar 2015 00:14:14 -0600
Subject: neigh: Don't require a dst in neigh_resolve_output

Having a dst helps a little bit for teql but is fundamentally
unnecessary and there are code paths where a dst is not available that
it would be nice to use the neighbour cache.

Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/neighbour.c | 6 ------
 1 file changed, 6 deletions(-)

(limited to 'net/core/neighbour.c')

diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index af72b863e968..0f48ea3affed 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -1284,12 +1284,8 @@ static void neigh_hh_init(struct neighbour *n)
 
 int neigh_resolve_output(struct neighbour *neigh, struct sk_buff *skb)
 {
-	struct dst_entry *dst = skb_dst(skb);
 	int rc = 0;
 
-	if (!dst)
-		goto discard;
-
 	if (!neigh_event_send(neigh, skb)) {
 		int err;
 		struct net_device *dev = neigh->dev;
@@ -1312,8 +1308,6 @@ int neigh_resolve_output(struct neighbour *neigh, struct sk_buff *skb)
 	}
 out:
 	return rc;
-discard:
-	neigh_dbg(1, "%s: dst=%p neigh=%p\n", __func__, dst, neigh);
 out_kfree_skb:
 	rc = -EINVAL;
 	kfree_skb(skb);
-- 
cgit 1.4.1


From 60395a20ffd74166ea373ea91418d6f98fa7fdfb Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Tue, 3 Mar 2015 17:10:44 -0600
Subject: neigh: Factor out ___neigh_lookup_noref

While looking at the mpls code I found myself writing yet another
version of neigh_lookup_noref.  We currently have __ipv4_lookup_noref
and __ipv6_lookup_noref.

So to make my work a little easier and to make it a smidge easier to
verify/maintain the mpls code in the future I stopped and wrote
___neigh_lookup_noref.  Then I rewote __ipv4_lookup_noref and
__ipv6_lookup_noref in terms of this new function.  I tested my new
version by verifying that the same code is generated in
ip_finish_output2 and ip6_finish_output2 where these functions are
inlined.

To get to ___neigh_lookup_noref I added a new neighbour cache table
function key_eq.  So that the static size of the key would be
available.

I also added __neigh_lookup_noref for people who want to to lookup
a neighbour table entry quickly but don't know which neibhgour table
they are going to look up.

Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/arp.h       | 19 ++++--------------
 include/net/ndisc.h     | 19 +-----------------
 include/net/neighbour.h | 52 +++++++++++++++++++++++++++++++++++++++++++++++++
 net/core/neighbour.c    | 20 +++++--------------
 net/decnet/dn_neigh.c   |  6 ++++++
 net/ipv4/arp.c          |  9 ++++++++-
 net/ipv6/ndisc.c        |  7 +++++++
 7 files changed, 83 insertions(+), 49 deletions(-)

(limited to 'net/core/neighbour.c')

diff --git a/include/net/arp.h b/include/net/arp.h
index 21ee1860abbc..5e0f891d476c 100644
--- a/include/net/arp.h
+++ b/include/net/arp.h
@@ -9,28 +9,17 @@
 
 extern struct neigh_table arp_tbl;
 
-static inline u32 arp_hashfn(u32 key, const struct net_device *dev, u32 hash_rnd)
+static inline u32 arp_hashfn(const void *pkey, const struct net_device *dev, u32 *hash_rnd)
 {
+	u32 key = *(const u32 *)pkey;
 	u32 val = key ^ hash32_ptr(dev);
 
-	return val * hash_rnd;
+	return val * hash_rnd[0];
 }
 
 static inline struct neighbour *__ipv4_neigh_lookup_noref(struct net_device *dev, u32 key)
 {
-	struct neigh_hash_table *nht = rcu_dereference_bh(arp_tbl.nht);
-	struct neighbour *n;
-	u32 hash_val;
-
-	hash_val = arp_hashfn(key, dev, nht->hash_rnd[0]) >> (32 - nht->hash_shift);
-	for (n = rcu_dereference_bh(nht->hash_buckets[hash_val]);
-	     n != NULL;
-	     n = rcu_dereference_bh(n->next)) {
-		if (n->dev == dev && *(u32 *)n->primary_key == key)
-			return n;
-	}
-
-	return NULL;
+	return ___neigh_lookup_noref(&arp_tbl, neigh_key_eq32, arp_hashfn, &key, dev);
 }
 
 static inline struct neighbour *__ipv4_neigh_lookup(struct net_device *dev, u32 key)
diff --git a/include/net/ndisc.h b/include/net/ndisc.h
index 6bbda34d5e59..b3a7751251b4 100644
--- a/include/net/ndisc.h
+++ b/include/net/ndisc.h
@@ -156,24 +156,7 @@ static inline u32 ndisc_hashfn(const void *pkey, const struct net_device *dev, _
 
 static inline struct neighbour *__ipv6_neigh_lookup_noref(struct net_device *dev, const void *pkey)
 {
-	struct neigh_hash_table *nht;
-	const u32 *p32 = pkey;
-	struct neighbour *n;
-	u32 hash_val;
-
-	nht = rcu_dereference_bh(nd_tbl.nht);
-	hash_val = ndisc_hashfn(pkey, dev, nht->hash_rnd) >> (32 - nht->hash_shift);
-	for (n = rcu_dereference_bh(nht->hash_buckets[hash_val]);
-	     n != NULL;
-	     n = rcu_dereference_bh(n->next)) {
-		u32 *n32 = (u32 *) n->primary_key;
-		if (n->dev == dev &&
-		    ((n32[0] ^ p32[0]) | (n32[1] ^ p32[1]) |
-		     (n32[2] ^ p32[2]) | (n32[3] ^ p32[3])) == 0)
-			return n;
-	}
-
-	return NULL;
+	return ___neigh_lookup_noref(&nd_tbl, neigh_key_eq128, ndisc_hashfn, pkey, dev);
 }
 
 static inline struct neighbour *__ipv6_neigh_lookup(struct net_device *dev, const void *pkey)
diff --git a/include/net/neighbour.h b/include/net/neighbour.h
index 9f912e4d4232..14e3f017966b 100644
--- a/include/net/neighbour.h
+++ b/include/net/neighbour.h
@@ -197,6 +197,7 @@ struct neigh_table {
 	__u32			(*hash)(const void *pkey,
 					const struct net_device *dev,
 					__u32 *hash_rnd);
+	bool			(*key_eq)(const struct neighbour *, const void *pkey);
 	int			(*constructor)(struct neighbour *);
 	int			(*pconstructor)(struct pneigh_entry *);
 	void			(*pdestructor)(struct pneigh_entry *);
@@ -247,6 +248,57 @@ static inline void *neighbour_priv(const struct neighbour *n)
 #define NEIGH_UPDATE_F_ISROUTER			0x40000000
 #define NEIGH_UPDATE_F_ADMIN			0x80000000
 
+
+static inline bool neigh_key_eq16(const struct neighbour *n, const void *pkey)
+{
+	return *(const u16 *)n->primary_key == *(const u16 *)pkey;
+}
+
+static inline bool neigh_key_eq32(const struct neighbour *n, const void *pkey)
+{
+	return *(const u32 *)n->primary_key == *(const u32 *)pkey;
+}
+
+static inline bool neigh_key_eq128(const struct neighbour *n, const void *pkey)
+{
+	const u32 *n32 = (const u32 *)n->primary_key;
+	const u32 *p32 = pkey;
+
+	return ((n32[0] ^ p32[0]) | (n32[1] ^ p32[1]) |
+		(n32[2] ^ p32[2]) | (n32[3] ^ p32[3])) == 0;
+}
+
+static inline struct neighbour *___neigh_lookup_noref(
+	struct neigh_table *tbl,
+	bool (*key_eq)(const struct neighbour *n, const void *pkey),
+	__u32 (*hash)(const void *pkey,
+		      const struct net_device *dev,
+		      __u32 *hash_rnd),
+	const void *pkey,
+	struct net_device *dev)
+{
+	struct neigh_hash_table *nht = rcu_dereference_bh(tbl->nht);
+	struct neighbour *n;
+	u32 hash_val;
+
+	hash_val = hash(pkey, dev, nht->hash_rnd) >> (32 - nht->hash_shift);
+	for (n = rcu_dereference_bh(nht->hash_buckets[hash_val]);
+	     n != NULL;
+	     n = rcu_dereference_bh(n->next)) {
+		if (n->dev == dev && key_eq(n, pkey))
+			return n;
+	}
+
+	return NULL;
+}
+
+static inline struct neighbour *__neigh_lookup_noref(struct neigh_table *tbl,
+						     const void *pkey,
+						     struct net_device *dev)
+{
+	return ___neigh_lookup_noref(tbl, tbl->key_eq, tbl->hash, pkey, dev);
+}
+
 void neigh_table_init(int index, struct neigh_table *tbl);
 int neigh_table_clear(int index, struct neigh_table *tbl);
 struct neighbour *neigh_lookup(struct neigh_table *tbl, const void *pkey,
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 0f48ea3affed..fe3c6eac5805 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -397,25 +397,15 @@ struct neighbour *neigh_lookup(struct neigh_table *tbl, const void *pkey,
 			       struct net_device *dev)
 {
 	struct neighbour *n;
-	int key_len = tbl->key_len;
-	u32 hash_val;
-	struct neigh_hash_table *nht;
 
 	NEIGH_CACHE_STAT_INC(tbl, lookups);
 
 	rcu_read_lock_bh();
-	nht = rcu_dereference_bh(tbl->nht);
-	hash_val = tbl->hash(pkey, dev, nht->hash_rnd) >> (32 - nht->hash_shift);
-
-	for (n = rcu_dereference_bh(nht->hash_buckets[hash_val]);
-	     n != NULL;
-	     n = rcu_dereference_bh(n->next)) {
-		if (dev == n->dev && !memcmp(n->primary_key, pkey, key_len)) {
-			if (!atomic_inc_not_zero(&n->refcnt))
-				n = NULL;
-			NEIGH_CACHE_STAT_INC(tbl, hits);
-			break;
-		}
+	n = __neigh_lookup_noref(tbl, pkey, dev);
+	if (n) {
+		if (!atomic_inc_not_zero(&n->refcnt))
+			n = NULL;
+		NEIGH_CACHE_STAT_INC(tbl, hits);
 	}
 
 	rcu_read_unlock_bh();
diff --git a/net/decnet/dn_neigh.c b/net/decnet/dn_neigh.c
index f123c6c6748c..ee7d1cef0027 100644
--- a/net/decnet/dn_neigh.c
+++ b/net/decnet/dn_neigh.c
@@ -93,12 +93,18 @@ static u32 dn_neigh_hash(const void *pkey,
 	return jhash_2words(*(__u16 *)pkey, 0, hash_rnd[0]);
 }
 
+static bool dn_key_eq(const struct neighbour *neigh, const void *pkey)
+{
+	return neigh_key_eq16(neigh, pkey);
+}
+
 struct neigh_table dn_neigh_table = {
 	.family =			PF_DECnet,
 	.entry_size =			NEIGH_ENTRY_SIZE(sizeof(struct dn_neigh)),
 	.key_len =			sizeof(__le16),
 	.protocol =			cpu_to_be16(ETH_P_DNA_RT),
 	.hash =				dn_neigh_hash,
+	.key_eq =			dn_key_eq,
 	.constructor =			dn_neigh_construct,
 	.id =				"dn_neigh_cache",
 	.parms ={
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index 6b8aad6a0d7d..5f5c674e130a 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -122,6 +122,7 @@
  *	Interface to generic neighbour cache.
  */
 static u32 arp_hash(const void *pkey, const struct net_device *dev, __u32 *hash_rnd);
+static bool arp_key_eq(const struct neighbour *n, const void *pkey);
 static int arp_constructor(struct neighbour *neigh);
 static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb);
 static void arp_error_report(struct neighbour *neigh, struct sk_buff *skb);
@@ -154,6 +155,7 @@ struct neigh_table arp_tbl = {
 	.key_len	= 4,
 	.protocol	= cpu_to_be16(ETH_P_IP),
 	.hash		= arp_hash,
+	.key_eq		= arp_key_eq,
 	.constructor	= arp_constructor,
 	.proxy_redo	= parp_redo,
 	.id		= "arp_cache",
@@ -209,7 +211,12 @@ static u32 arp_hash(const void *pkey,
 		    const struct net_device *dev,
 		    __u32 *hash_rnd)
 {
-	return arp_hashfn(*(u32 *)pkey, dev, *hash_rnd);
+	return arp_hashfn(pkey, dev, hash_rnd);
+}
+
+static bool arp_key_eq(const struct neighbour *neigh, const void *pkey)
+{
+	return neigh_key_eq32(neigh, pkey);
 }
 
 static int arp_constructor(struct neighbour *neigh)
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index e363bbc2420d..247ad7c298f7 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -84,6 +84,7 @@ do {								\
 static u32 ndisc_hash(const void *pkey,
 		      const struct net_device *dev,
 		      __u32 *hash_rnd);
+static bool ndisc_key_eq(const struct neighbour *neigh, const void *pkey);
 static int ndisc_constructor(struct neighbour *neigh);
 static void ndisc_solicit(struct neighbour *neigh, struct sk_buff *skb);
 static void ndisc_error_report(struct neighbour *neigh, struct sk_buff *skb);
@@ -119,6 +120,7 @@ struct neigh_table nd_tbl = {
 	.key_len =	sizeof(struct in6_addr),
 	.protocol =	cpu_to_be16(ETH_P_IPV6),
 	.hash =		ndisc_hash,
+	.key_eq =	ndisc_key_eq,
 	.constructor =	ndisc_constructor,
 	.pconstructor =	pndisc_constructor,
 	.pdestructor =	pndisc_destructor,
@@ -295,6 +297,11 @@ static u32 ndisc_hash(const void *pkey,
 	return ndisc_hashfn(pkey, dev, hash_rnd);
 }
 
+static bool ndisc_key_eq(const struct neighbour *n, const void *pkey)
+{
+	return neigh_key_eq128(n, pkey);
+}
+
 static int ndisc_constructor(struct neighbour *neigh)
 {
 	struct in6_addr *addr = (struct in6_addr *)&neigh->primary_key;
-- 
cgit 1.4.1


From 4fd3d7d9e868ffbdb0e7a67c5c8e9dfdcd846a62 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Tue, 3 Mar 2015 17:11:16 -0600
Subject: neigh: Add helper function neigh_xmit

For MPLS I am building the code so that either the neighbour mac
address can be specified or we can have a next hop in ipv4 or ipv6.

The kind of next hop we have is indicated by the neighbour table
pointer.  A neighbour table pointer of NULL is a link layer address.
A non-NULL neighbour table pointer indicates which neighbour table and
thus which address family the next hop address is in that we need to
look up.

The code either sends a packet directly or looks up the appropriate
neighbour table entry and sends the packet.

Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/neighbour.h |  3 +++
 net/core/neighbour.c    | 34 ++++++++++++++++++++++++++++++++++
 2 files changed, 37 insertions(+)

(limited to 'net/core/neighbour.c')

diff --git a/include/net/neighbour.h b/include/net/neighbour.h
index 14e3f017966b..afb8237b0a8c 100644
--- a/include/net/neighbour.h
+++ b/include/net/neighbour.h
@@ -358,6 +358,7 @@ void neigh_for_each(struct neigh_table *tbl,
 		    void (*cb)(struct neighbour *, void *), void *cookie);
 void __neigh_for_each_release(struct neigh_table *tbl,
 			      int (*cb)(struct neighbour *));
+int neigh_xmit(int fam, struct net_device *, const void *, struct sk_buff *);
 void pneigh_for_each(struct neigh_table *tbl,
 		     void (*cb)(struct pneigh_entry *));
 
@@ -511,4 +512,6 @@ static inline void neigh_ha_snapshot(char *dst, const struct neighbour *n,
 		memcpy(dst, n->ha, dev->addr_len);
 	} while (read_seqretry(&n->ha_lock, seq));
 }
+
+
 #endif
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index fe3c6eac5805..cffaf00561e7 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -2391,6 +2391,40 @@ void __neigh_for_each_release(struct neigh_table *tbl,
 }
 EXPORT_SYMBOL(__neigh_for_each_release);
 
+int neigh_xmit(int family, struct net_device *dev,
+	       const void *addr, struct sk_buff *skb)
+{
+	int err;
+	if (family == AF_PACKET) {
+		err = dev_hard_header(skb, dev, ntohs(skb->protocol),
+				      addr, NULL, skb->len);
+		if (err < 0)
+			goto out_kfree_skb;
+		err = dev_queue_xmit(skb);
+	} else {
+		struct neigh_table *tbl;
+		struct neighbour *neigh;
+
+		err = -ENETDOWN;
+		tbl = neigh_find_table(family);
+		if (!tbl)
+			goto out;
+		neigh = __neigh_lookup_noref(tbl, addr, dev);
+		if (!neigh)
+			neigh = __neigh_create(tbl, addr, dev, false);
+		err = PTR_ERR(neigh);
+		if (IS_ERR(neigh))
+			goto out_kfree_skb;
+		err = neigh->output(neigh, skb);
+	}
+out:
+	return err;
+out_kfree_skb:
+	kfree_skb(skb);
+	goto out;
+}
+EXPORT_SYMBOL(neigh_xmit);
+
 #ifdef CONFIG_PROC_FS
 
 static struct neighbour *neigh_get_first(struct seq_file *seq)
-- 
cgit 1.4.1


From b79bda3d38ae67940f1740f7e015f284eb551680 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Sat, 7 Mar 2015 16:25:56 -0600
Subject: neigh: Use neigh table index for neigh_packet_xmit

Remove a little bit of unnecessary work when transmitting a packet with
neigh_packet_xmit.  Use the neighbour table index not the address family
as a parameter.

Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/neighbour.h |  1 +
 net/core/neighbour.c    | 22 +++++++++++-----------
 net/mpls/af_mpls.c      | 35 ++++++++++++++++++++++-------------
 3 files changed, 34 insertions(+), 24 deletions(-)

(limited to 'net/core/neighbour.c')

diff --git a/include/net/neighbour.h b/include/net/neighbour.h
index afb8237b0a8c..d48b8ec8b5f4 100644
--- a/include/net/neighbour.h
+++ b/include/net/neighbour.h
@@ -226,6 +226,7 @@ enum {
 	NEIGH_ND_TABLE = 1,
 	NEIGH_DN_TABLE = 2,
 	NEIGH_NR_TABLES,
+	NEIGH_LINK_TABLE = NEIGH_NR_TABLES /* Pseudo table for neigh_xmit */
 };
 
 static inline int neigh_parms_family(struct neigh_parms *p)
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index cffaf00561e7..ad07990e943d 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -2391,22 +2391,15 @@ void __neigh_for_each_release(struct neigh_table *tbl,
 }
 EXPORT_SYMBOL(__neigh_for_each_release);
 
-int neigh_xmit(int family, struct net_device *dev,
+int neigh_xmit(int index, struct net_device *dev,
 	       const void *addr, struct sk_buff *skb)
 {
-	int err;
-	if (family == AF_PACKET) {
-		err = dev_hard_header(skb, dev, ntohs(skb->protocol),
-				      addr, NULL, skb->len);
-		if (err < 0)
-			goto out_kfree_skb;
-		err = dev_queue_xmit(skb);
-	} else {
+	int err = -EAFNOSUPPORT;
+	if (likely(index < NEIGH_NR_TABLES)) {
 		struct neigh_table *tbl;
 		struct neighbour *neigh;
 
-		err = -ENETDOWN;
-		tbl = neigh_find_table(family);
+		tbl = neigh_tables[index];
 		if (!tbl)
 			goto out;
 		neigh = __neigh_lookup_noref(tbl, addr, dev);
@@ -2417,6 +2410,13 @@ int neigh_xmit(int family, struct net_device *dev,
 			goto out_kfree_skb;
 		err = neigh->output(neigh, skb);
 	}
+	else if (index == NEIGH_LINK_TABLE) {
+		err = dev_hard_header(skb, dev, ntohs(skb->protocol),
+				      addr, NULL, skb->len);
+		if (err < 0)
+			goto out_kfree_skb;
+		err = dev_queue_xmit(skb);
+	}
 out:
 	return err;
 out_kfree_skb:
diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c
index e120074157de..0ad8f7141be2 100644
--- a/net/mpls/af_mpls.c
+++ b/net/mpls/af_mpls.c
@@ -28,9 +28,9 @@ struct mpls_route { /* next hop label forwarding entry */
 	struct rcu_head		rt_rcu;
 	u32			rt_label[MAX_NEW_LABELS];
 	u8			rt_protocol; /* routing protocol that set this entry */
-	u8			rt_labels:2,
-				rt_via_alen:6;
-	unsigned short		rt_via_family;
+	u8			rt_labels;
+	u8			rt_via_alen;
+	u8			rt_via_table;
 	u8			rt_via[0];
 };
 
@@ -201,7 +201,7 @@ static int mpls_forward(struct sk_buff *skb, struct net_device *dev,
 		}
 	}
 
-	err = neigh_xmit(rt->rt_via_family, out_dev, rt->rt_via, skb);
+	err = neigh_xmit(rt->rt_via_table, out_dev, rt->rt_via, skb);
 	if (err)
 		net_dbg_ratelimited("%s: packet transmission failed: %d\n",
 				    __func__, err);
@@ -225,7 +225,7 @@ static const struct nla_policy rtm_mpls_policy[RTA_MAX+1] = {
 struct mpls_route_config {
 	u32		rc_protocol;
 	u32		rc_ifindex;
-	u16		rc_via_family;
+	u16		rc_via_table;
 	u16		rc_via_alen;
 	u8		rc_via[MAX_VIA_ALEN];
 	u32		rc_label;
@@ -343,7 +343,7 @@ static int mpls_route_add(struct mpls_route_config *cfg)
 		goto errout;
 
 	err = -EINVAL;
-	if ((cfg->rc_via_family == AF_PACKET) &&
+	if ((cfg->rc_via_table == NEIGH_LINK_TABLE) &&
 	    (dev->addr_len != cfg->rc_via_alen))
 		goto errout;
 
@@ -376,7 +376,7 @@ static int mpls_route_add(struct mpls_route_config *cfg)
 		rt->rt_label[i] = cfg->rc_output_label[i];
 	rt->rt_protocol = cfg->rc_protocol;
 	RCU_INIT_POINTER(rt->rt_dev, dev);
-	rt->rt_via_family = cfg->rc_via_family;
+	rt->rt_via_table = cfg->rc_via_table;
 	memcpy(rt->rt_via, cfg->rc_via, cfg->rc_via_alen);
 
 	mpls_route_update(net, index, NULL, rt, &cfg->rc_nlinfo);
@@ -448,15 +448,22 @@ static struct notifier_block mpls_dev_notifier = {
 };
 
 static int nla_put_via(struct sk_buff *skb,
-		       u16 family, const void *addr, int alen)
+		       u8 table, const void *addr, int alen)
 {
+	static const int table_to_family[NEIGH_NR_TABLES + 1] = {
+		AF_INET, AF_INET6, AF_DECnet, AF_PACKET,
+	};
 	struct nlattr *nla;
 	struct rtvia *via;
+	int family = AF_UNSPEC;
 
 	nla = nla_reserve(skb, RTA_VIA, alen + 2);
 	if (!nla)
 		return -EMSGSIZE;
 
+	if (table <= NEIGH_NR_TABLES)
+		family = table_to_family[table];
+
 	via = nla_data(nla);
 	via->rtvia_family = family;
 	memcpy(via->rtvia_addr, addr, alen);
@@ -599,21 +606,23 @@ static int rtm_to_route_config(struct sk_buff *skb,  struct nlmsghdr *nlh,
 			struct rtvia *via = nla_data(nla);
 			if (nla_len(nla) < offsetof(struct rtvia, rtvia_addr))
 				goto errout;
-			cfg->rc_via_family = via->rtvia_family;
 			cfg->rc_via_alen   = nla_len(nla) -
 				offsetof(struct rtvia, rtvia_addr);
 			if (cfg->rc_via_alen > MAX_VIA_ALEN)
 				goto errout;
 
 			/* Validate the address family */
-			switch(cfg->rc_via_family) {
+			switch(via->rtvia_family) {
 			case AF_PACKET:
+				cfg->rc_via_table = NEIGH_LINK_TABLE;
 				break;
 			case AF_INET:
+				cfg->rc_via_table = NEIGH_ARP_TABLE;
 				if (cfg->rc_via_alen != 4)
 					goto errout;
 				break;
 			case AF_INET6:
+				cfg->rc_via_table = NEIGH_ND_TABLE;
 				if (cfg->rc_via_alen != 16)
 					goto errout;
 				break;
@@ -686,7 +695,7 @@ static int mpls_dump_route(struct sk_buff *skb, u32 portid, u32 seq, int event,
 	if (rt->rt_labels &&
 	    nla_put_labels(skb, RTA_NEWDST, rt->rt_labels, rt->rt_label))
 		goto nla_put_failure;
-	if (nla_put_via(skb, rt->rt_via_family, rt->rt_via, rt->rt_via_alen))
+	if (nla_put_via(skb, rt->rt_via_table, rt->rt_via, rt->rt_via_alen))
 		goto nla_put_failure;
 	dev = rtnl_dereference(rt->rt_dev);
 	if (dev && nla_put_u32(skb, RTA_OIF, dev->ifindex))
@@ -799,7 +808,7 @@ static int resize_platform_label_table(struct net *net, size_t limit)
 			goto nort0;
 		RCU_INIT_POINTER(rt0->rt_dev, lo);
 		rt0->rt_protocol = RTPROT_KERNEL;
-		rt0->rt_via_family = AF_PACKET;
+		rt0->rt_via_table = NEIGH_LINK_TABLE;
 		memcpy(rt0->rt_via, lo->dev_addr, lo->addr_len);
 	}
 	if (limit > LABEL_IPV6_EXPLICIT_NULL) {
@@ -809,7 +818,7 @@ static int resize_platform_label_table(struct net *net, size_t limit)
 			goto nort2;
 		RCU_INIT_POINTER(rt2->rt_dev, lo);
 		rt2->rt_protocol = RTPROT_KERNEL;
-		rt2->rt_via_family = AF_PACKET;
+		rt2->rt_via_table = NEIGH_LINK_TABLE;
 		memcpy(rt2->rt_via, lo->dev_addr, lo->addr_len);
 	}
 
-- 
cgit 1.4.1


From efd7ef1c1929d7a0329d4349252863c04d6f1729 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Wed, 11 Mar 2015 23:04:08 -0500
Subject: net: Kill hold_net release_net

hold_net and release_net were an idea that turned out to be useless.
The code has been disabled since 2008.  Kill the code it is long past due.

Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h     |  3 +--
 include/net/fib_rules.h       |  9 +--------
 include/net/net_namespace.h   | 29 -----------------------------
 include/net/sock.h            |  2 +-
 net/core/dev.c                |  2 --
 net/core/fib_rules.c          | 17 +++--------------
 net/core/neighbour.c          |  9 ++-------
 net/core/net_namespace.c      | 11 -----------
 net/core/sock.c               |  1 -
 net/ipv4/fib_semantics.c      |  3 +--
 net/ipv4/inet_hashtables.c    |  3 +--
 net/ipv4/inet_timewait_sock.c |  3 +--
 net/ipv6/addrlabel.c          |  5 +----
 net/ipv6/ip6_flowlabel.c      |  3 +--
 net/openvswitch/datapath.c    |  4 +---
 15 files changed, 14 insertions(+), 90 deletions(-)

(limited to 'net/core/neighbour.c')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 1354ae83efc8..cede40d9cac9 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1864,8 +1864,7 @@ static inline
 void dev_net_set(struct net_device *dev, struct net *net)
 {
 #ifdef CONFIG_NET_NS
-	release_net(dev->nd_net);
-	dev->nd_net = hold_net(net);
+	dev->nd_net = net;
 #endif
 }
 
diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h
index 88d2ae526961..6d67383a5114 100644
--- a/include/net/fib_rules.h
+++ b/include/net/fib_rules.h
@@ -95,17 +95,10 @@ static inline void fib_rule_get(struct fib_rule *rule)
 	atomic_inc(&rule->refcnt);
 }
 
-static inline void fib_rule_put_rcu(struct rcu_head *head)
-{
-	struct fib_rule *rule = container_of(head, struct fib_rule, rcu);
-	release_net(rule->fr_net);
-	kfree(rule);
-}
-
 static inline void fib_rule_put(struct fib_rule *rule)
 {
 	if (atomic_dec_and_test(&rule->refcnt))
-		call_rcu(&rule->rcu, fib_rule_put_rcu);
+		kfree_rcu(rule, rcu);
 }
 
 static inline u32 frh_get_table(struct fib_rule_hdr *frh, struct nlattr **nla)
diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index e086f4030dd2..fab51ceeabf3 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -49,11 +49,6 @@ struct net {
 	atomic_t		count;		/* To decided when the network
 						 *  namespace should be shut down.
 						 */
-#ifdef NETNS_REFCNT_DEBUG
-	atomic_t		use_count;	/* To track references we
-						 * destroy on demand
-						 */
-#endif
 	spinlock_t		rules_mod_lock;
 
 	atomic64_t		cookie_gen;
@@ -236,30 +231,6 @@ int net_eq(const struct net *net1, const struct net *net2)
 #endif
 
 
-#ifdef NETNS_REFCNT_DEBUG
-static inline struct net *hold_net(struct net *net)
-{
-	if (net)
-		atomic_inc(&net->use_count);
-	return net;
-}
-
-static inline void release_net(struct net *net)
-{
-	if (net)
-		atomic_dec(&net->use_count);
-}
-#else
-static inline struct net *hold_net(struct net *net)
-{
-	return net;
-}
-
-static inline void release_net(struct net *net)
-{
-}
-#endif
-
 #ifdef CONFIG_NET_NS
 
 static inline void write_pnet(struct net **pnet, struct net *net)
diff --git a/include/net/sock.h b/include/net/sock.h
index d996c633bec2..95b2c1c220f9 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2204,7 +2204,7 @@ static inline void sk_change_net(struct sock *sk, struct net *net)
 
 	if (!net_eq(current_net, net)) {
 		put_net(current_net);
-		sock_net_set(sk, hold_net(net));
+		sock_net_set(sk, net);
 	}
 }
 
diff --git a/net/core/dev.c b/net/core/dev.c
index 962ee9d71964..39fe369b46ad 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -6841,8 +6841,6 @@ void free_netdev(struct net_device *dev)
 {
 	struct napi_struct *p, *n;
 
-	release_net(dev_net(dev));
-
 	netif_free_tx_queues(dev);
 #ifdef CONFIG_SYSFS
 	kvfree(dev->_rx);
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index b55677fed1c8..68ea6950cad1 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -31,7 +31,7 @@ int fib_default_rule_add(struct fib_rules_ops *ops,
 	r->pref = pref;
 	r->table = table;
 	r->flags = flags;
-	r->fr_net = hold_net(ops->fro_net);
+	r->fr_net = ops->fro_net;
 
 	r->suppress_prefixlen = -1;
 	r->suppress_ifgroup = -1;
@@ -116,7 +116,6 @@ static int __fib_rules_register(struct fib_rules_ops *ops)
 		if (ops->family == o->family)
 			goto errout;
 
-	hold_net(net);
 	list_add_tail_rcu(&ops->list, &net->rules_ops);
 	err = 0;
 errout:
@@ -160,15 +159,6 @@ static void fib_rules_cleanup_ops(struct fib_rules_ops *ops)
 	}
 }
 
-static void fib_rules_put_rcu(struct rcu_head *head)
-{
-	struct fib_rules_ops *ops = container_of(head, struct fib_rules_ops, rcu);
-	struct net *net = ops->fro_net;
-
-	release_net(net);
-	kfree(ops);
-}
-
 void fib_rules_unregister(struct fib_rules_ops *ops)
 {
 	struct net *net = ops->fro_net;
@@ -178,7 +168,7 @@ void fib_rules_unregister(struct fib_rules_ops *ops)
 	fib_rules_cleanup_ops(ops);
 	spin_unlock(&net->rules_mod_lock);
 
-	call_rcu(&ops->rcu, fib_rules_put_rcu);
+	kfree_rcu(ops, rcu);
 }
 EXPORT_SYMBOL_GPL(fib_rules_unregister);
 
@@ -303,7 +293,7 @@ static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh)
 		err = -ENOMEM;
 		goto errout;
 	}
-	rule->fr_net = hold_net(net);
+	rule->fr_net = net;
 
 	if (tb[FRA_PRIORITY])
 		rule->pref = nla_get_u32(tb[FRA_PRIORITY]);
@@ -423,7 +413,6 @@ static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh)
 	return 0;
 
 errout_free:
-	release_net(rule->fr_net);
 	kfree(rule);
 errout:
 	rules_ops_put(ops);
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index ad07990e943d..0e8b32efc031 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -591,7 +591,7 @@ struct pneigh_entry * pneigh_lookup(struct neigh_table *tbl,
 	if (!n)
 		goto out;
 
-	write_pnet(&n->net, hold_net(net));
+	write_pnet(&n->net, net);
 	memcpy(n->key, pkey, key_len);
 	n->dev = dev;
 	if (dev)
@@ -600,7 +600,6 @@ struct pneigh_entry * pneigh_lookup(struct neigh_table *tbl,
 	if (tbl->pconstructor && tbl->pconstructor(n)) {
 		if (dev)
 			dev_put(dev);
-		release_net(net);
 		kfree(n);
 		n = NULL;
 		goto out;
@@ -634,7 +633,6 @@ int pneigh_delete(struct neigh_table *tbl, struct net *net, const void *pkey,
 				tbl->pdestructor(n);
 			if (n->dev)
 				dev_put(n->dev);
-			release_net(pneigh_net(n));
 			kfree(n);
 			return 0;
 		}
@@ -657,7 +655,6 @@ static int pneigh_ifdown(struct neigh_table *tbl, struct net_device *dev)
 					tbl->pdestructor(n);
 				if (n->dev)
 					dev_put(n->dev);
-				release_net(pneigh_net(n));
 				kfree(n);
 				continue;
 			}
@@ -1428,11 +1425,10 @@ struct neigh_parms *neigh_parms_alloc(struct net_device *dev,
 				neigh_rand_reach_time(NEIGH_VAR(p, BASE_REACHABLE_TIME));
 		dev_hold(dev);
 		p->dev = dev;
-		write_pnet(&p->net, hold_net(net));
+		write_pnet(&p->net, net);
 		p->sysctl_table = NULL;
 
 		if (ops->ndo_neigh_setup && ops->ndo_neigh_setup(dev, p)) {
-			release_net(net);
 			dev_put(dev);
 			kfree(p);
 			return NULL;
@@ -1472,7 +1468,6 @@ EXPORT_SYMBOL(neigh_parms_release);
 
 static void neigh_parms_destroy(struct neigh_parms *parms)
 {
-	release_net(neigh_parms_net(parms));
 	kfree(parms);
 }
 
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index cb5290b8c428..e5e96b0f6717 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -236,10 +236,6 @@ static __net_init int setup_net(struct net *net, struct user_namespace *user_ns)
 	net->user_ns = user_ns;
 	idr_init(&net->netns_ids);
 
-#ifdef NETNS_REFCNT_DEBUG
-	atomic_set(&net->use_count, 0);
-#endif
-
 	list_for_each_entry(ops, &pernet_list, list) {
 		error = ops_init(ops, net);
 		if (error < 0)
@@ -294,13 +290,6 @@ out_free:
 
 static void net_free(struct net *net)
 {
-#ifdef NETNS_REFCNT_DEBUG
-	if (unlikely(atomic_read(&net->use_count) != 0)) {
-		pr_emerg("network namespace not free! Usage: %d\n",
-			 atomic_read(&net->use_count));
-		return;
-	}
-#endif
 	kfree(rcu_access_pointer(net->gen));
 	kmem_cache_free(net_cachep, net);
 }
diff --git a/net/core/sock.c b/net/core/sock.c
index a9a9c2ff9260..c8842f279f7a 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1455,7 +1455,6 @@ void sk_release_kernel(struct sock *sk)
 
 	sock_hold(sk);
 	sock_release(sk->sk_socket);
-	release_net(sock_net(sk));
 	sock_net_set(sk, get_net(&init_net));
 	sock_put(sk);
 }
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index c6d267442dac..66c1e4fbf884 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -213,7 +213,6 @@ static void free_fib_info_rcu(struct rcu_head *head)
 		rt_fibinfo_free(&nexthop_nh->nh_rth_input);
 	} endfor_nexthops(fi);
 
-	release_net(fi->fib_net);
 	if (fi->fib_metrics != (u32 *) dst_default_metrics)
 		kfree(fi->fib_metrics);
 	kfree(fi);
@@ -814,7 +813,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg)
 	} else
 		fi->fib_metrics = (u32 *) dst_default_metrics;
 
-	fi->fib_net = hold_net(net);
+	fi->fib_net = net;
 	fi->fib_protocol = cfg->fc_protocol;
 	fi->fib_scope = cfg->fc_scope;
 	fi->fib_flags = cfg->fc_flags;
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 9111a4e22155..f6a12b97d12b 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -61,7 +61,7 @@ struct inet_bind_bucket *inet_bind_bucket_create(struct kmem_cache *cachep,
 	struct inet_bind_bucket *tb = kmem_cache_alloc(cachep, GFP_ATOMIC);
 
 	if (tb != NULL) {
-		write_pnet(&tb->ib_net, hold_net(net));
+		write_pnet(&tb->ib_net, net);
 		tb->port      = snum;
 		tb->fastreuse = 0;
 		tb->fastreuseport = 0;
@@ -79,7 +79,6 @@ void inet_bind_bucket_destroy(struct kmem_cache *cachep, struct inet_bind_bucket
 {
 	if (hlist_empty(&tb->owners)) {
 		__hlist_del(&tb->node);
-		release_net(ib_net(tb));
 		kmem_cache_free(cachep, tb);
 	}
 }
diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c
index 2bd980526631..86ebf020925b 100644
--- a/net/ipv4/inet_timewait_sock.c
+++ b/net/ipv4/inet_timewait_sock.c
@@ -98,7 +98,6 @@ void inet_twsk_free(struct inet_timewait_sock *tw)
 #ifdef SOCK_REFCNT_DEBUG
 	pr_debug("%s timewait_sock %p released\n", tw->tw_prot->name, tw);
 #endif
-	release_net(twsk_net(tw));
 	kmem_cache_free(tw->tw_prot->twsk_prot->twsk_slab, tw);
 	module_put(owner);
 }
@@ -196,7 +195,7 @@ struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk, const int stat
 		tw->tw_transparent  = inet->transparent;
 		tw->tw_prot	    = sk->sk_prot_creator;
 		atomic64_set(&tw->tw_cookie, atomic64_read(&sk->sk_cookie));
-		twsk_net_set(tw, hold_net(sock_net(sk)));
+		twsk_net_set(tw, sock_net(sk));
 		/*
 		 * Because we use RCU lookups, we should not set tw_refcnt
 		 * to a non null value before everything is setup for this
diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c
index e43e79d0a612..59c793040498 100644
--- a/net/ipv6/addrlabel.c
+++ b/net/ipv6/addrlabel.c
@@ -129,9 +129,6 @@ static const __net_initconst struct ip6addrlbl_init_table
 /* Object management */
 static inline void ip6addrlbl_free(struct ip6addrlbl_entry *p)
 {
-#ifdef CONFIG_NET_NS
-	release_net(p->lbl_net);
-#endif
 	kfree(p);
 }
 
@@ -241,7 +238,7 @@ static struct ip6addrlbl_entry *ip6addrlbl_alloc(struct net *net,
 	newp->label = label;
 	INIT_HLIST_NODE(&newp->list);
 #ifdef CONFIG_NET_NS
-	newp->lbl_net = hold_net(net);
+	newp->lbl_net = net;
 #endif
 	atomic_set(&newp->refcnt, 1);
 	return newp;
diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c
index f45d6db50a45..457303886fd4 100644
--- a/net/ipv6/ip6_flowlabel.c
+++ b/net/ipv6/ip6_flowlabel.c
@@ -100,7 +100,6 @@ static void fl_free(struct ip6_flowlabel *fl)
 	if (fl) {
 		if (fl->share == IPV6_FL_S_PROCESS)
 			put_pid(fl->owner.pid);
-		release_net(fl->fl_net);
 		kfree(fl->opt);
 		kfree_rcu(fl, rcu);
 	}
@@ -403,7 +402,7 @@ fl_create(struct net *net, struct sock *sk, struct in6_flowlabel_req *freq,
 		}
 	}
 
-	fl->fl_net = hold_net(net);
+	fl->fl_net = net;
 	fl->expires = jiffies;
 	err = fl6_renew(fl, freq->flr_linger, freq->flr_expires);
 	if (err)
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 5bae7243c577..096c6276e6b9 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -203,7 +203,6 @@ static void destroy_dp_rcu(struct rcu_head *rcu)
 
 	ovs_flow_tbl_destroy(&dp->table);
 	free_percpu(dp->stats_percpu);
-	release_net(ovs_dp_get_net(dp));
 	kfree(dp->ports);
 	kfree(dp);
 }
@@ -1501,7 +1500,7 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info)
 	if (dp == NULL)
 		goto err_free_reply;
 
-	ovs_dp_set_net(dp, hold_net(sock_net(skb->sk)));
+	ovs_dp_set_net(dp, sock_net(skb->sk));
 
 	/* Allocate table. */
 	err = ovs_flow_tbl_init(&dp->table);
@@ -1575,7 +1574,6 @@ err_destroy_percpu:
 err_destroy_table:
 	ovs_flow_tbl_destroy(&dp->table);
 err_free_dp:
-	release_net(ovs_dp_get_net(dp));
 	kfree(dp);
 err_free_reply:
 	kfree_skb(reply);
-- 
cgit 1.4.1


From 8da86466b83787df0d4b89ec81c310de072d101c Mon Sep 17 00:00:00 2001
From: YOSHIFUJI Hideaki/吉藤英明 <hideaki.yoshifuji@miraclelinux.com>
Date: Thu, 19 Mar 2015 22:41:46 +0900
Subject: net: neighbour: Add mcast_resolicit to configure the number of
 multicast resolicitations in PROBE state.

We send unicast neighbor (ARP or NDP) solicitations ucast_probes
times in PROBE state.  Zhu Yanjun reported that some implementation
does not reply against them and the entry will become FAILED, which
is undesirable.

We had been dealt with such nodes by sending multicast probes mcast_
solicit times after unicast probes in PROBE state.  In 2003, I made
a change not to send them to improve compatibility with IPv6 NDP.

Let's introduce per-protocol per-interface sysctl knob "mcast_
reprobe" to configure the number of multicast (re)solicitation for
reconfirmation in PROBE state.  The default is 0, since we have
been doing so for 10+ years.

Reported-by: Zhu Yanjun <Yanjun.Zhu@windriver.com>
CC: Ulf Samuelsson <ulf.samuelsson@ericsson.com>
Signed-off-by: YOSHIFUJI Hideaki <hideaki.yoshifuji@miraclelinux.com>
Signed-off-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/neighbour.h        |  1 +
 include/uapi/linux/neighbour.h |  1 +
 net/core/neighbour.c           | 15 +++++++++++----
 3 files changed, 13 insertions(+), 4 deletions(-)

(limited to 'net/core/neighbour.c')

diff --git a/include/net/neighbour.h b/include/net/neighbour.h
index e7bdf5170802..bd33e66f49aa 100644
--- a/include/net/neighbour.h
+++ b/include/net/neighbour.h
@@ -42,6 +42,7 @@ enum {
 	NEIGH_VAR_MCAST_PROBES,
 	NEIGH_VAR_UCAST_PROBES,
 	NEIGH_VAR_APP_PROBES,
+	NEIGH_VAR_MCAST_REPROBES,
 	NEIGH_VAR_RETRANS_TIME,
 	NEIGH_VAR_BASE_REACHABLE_TIME,
 	NEIGH_VAR_DELAY_PROBE_TIME,
diff --git a/include/uapi/linux/neighbour.h b/include/uapi/linux/neighbour.h
index 3873a35509aa..2e35c61bbdd1 100644
--- a/include/uapi/linux/neighbour.h
+++ b/include/uapi/linux/neighbour.h
@@ -126,6 +126,7 @@ enum {
 	NDTPA_PROXY_QLEN,		/* u32 */
 	NDTPA_LOCKTIME,			/* u64, msecs */
 	NDTPA_QUEUE_LENBYTES,		/* u32 */
+	NDTPA_MCAST_REPROBES,		/* u32 */
 	__NDTPA_MAX
 };
 #define NDTPA_MAX (__NDTPA_MAX - 1)
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 0e8b32efc031..3de654256028 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -817,10 +817,9 @@ out:
 static __inline__ int neigh_max_probes(struct neighbour *n)
 {
 	struct neigh_parms *p = n->parms;
-	int max_probes = NEIGH_VAR(p, UCAST_PROBES) + NEIGH_VAR(p, APP_PROBES);
-	if (!(n->nud_state & NUD_PROBE))
-		max_probes += NEIGH_VAR(p, MCAST_PROBES);
-	return max_probes;
+	return NEIGH_VAR(p, UCAST_PROBES) + NEIGH_VAR(p, APP_PROBES) +
+	       (n->nud_state & NUD_PROBE ? NEIGH_VAR(p, MCAST_REPROBES) :
+	        NEIGH_VAR(p, MCAST_PROBES));
 }
 
 static void neigh_invalidate(struct neighbour *neigh)
@@ -1742,6 +1741,8 @@ static int neightbl_fill_parms(struct sk_buff *skb, struct neigh_parms *parms)
 			NEIGH_VAR(parms, UCAST_PROBES)) ||
 	    nla_put_u32(skb, NDTPA_MCAST_PROBES,
 			NEIGH_VAR(parms, MCAST_PROBES)) ||
+	    nla_put_u32(skb, NDTPA_MCAST_REPROBES,
+			NEIGH_VAR(parms, MCAST_REPROBES)) ||
 	    nla_put_msecs(skb, NDTPA_REACHABLE_TIME, parms->reachable_time) ||
 	    nla_put_msecs(skb, NDTPA_BASE_REACHABLE_TIME,
 			  NEIGH_VAR(parms, BASE_REACHABLE_TIME)) ||
@@ -1901,6 +1902,7 @@ static const struct nla_policy nl_ntbl_parm_policy[NDTPA_MAX+1] = {
 	[NDTPA_APP_PROBES]		= { .type = NLA_U32 },
 	[NDTPA_UCAST_PROBES]		= { .type = NLA_U32 },
 	[NDTPA_MCAST_PROBES]		= { .type = NLA_U32 },
+	[NDTPA_MCAST_REPROBES]		= { .type = NLA_U32 },
 	[NDTPA_BASE_REACHABLE_TIME]	= { .type = NLA_U64 },
 	[NDTPA_GC_STALETIME]		= { .type = NLA_U64 },
 	[NDTPA_DELAY_PROBE_TIME]	= { .type = NLA_U64 },
@@ -2001,6 +2003,10 @@ static int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh)
 				NEIGH_VAR_SET(p, MCAST_PROBES,
 					      nla_get_u32(tbp[i]));
 				break;
+			case NDTPA_MCAST_REPROBES:
+				NEIGH_VAR_SET(p, MCAST_REPROBES,
+					      nla_get_u32(tbp[i]));
+				break;
 			case NDTPA_BASE_REACHABLE_TIME:
 				NEIGH_VAR_SET(p, BASE_REACHABLE_TIME,
 					      nla_get_msecs(tbp[i]));
@@ -2987,6 +2993,7 @@ static struct neigh_sysctl_table {
 		NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(MCAST_PROBES, "mcast_solicit"),
 		NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(UCAST_PROBES, "ucast_solicit"),
 		NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(APP_PROBES, "app_solicit"),
+		NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(MCAST_REPROBES, "mcast_resolicit"),
 		NEIGH_SYSCTL_USERHZ_JIFFIES_ENTRY(RETRANS_TIME, "retrans_time"),
 		NEIGH_SYSCTL_JIFFIES_ENTRY(BASE_REACHABLE_TIME, "base_reachable_time"),
 		NEIGH_SYSCTL_JIFFIES_ENTRY(DELAY_PROBE_TIME, "delay_first_probe_time"),
-- 
cgit 1.4.1